diff options
author | Mark Benvenuto <mark.benvenuto@mongodb.com> | 2016-10-14 10:58:34 -0400 |
---|---|---|
committer | Mark Benvenuto <mark.benvenuto@mongodb.com> | 2016-10-14 10:58:34 -0400 |
commit | 3fe7917512f6e481c1539c68d28a35772233c3f1 (patch) | |
tree | fe311509c784939dcabd2833e005f1ec6611df78 | |
parent | 30b18a9a2b42e88c9ddef2aa32e72d3baf5a4890 (diff) | |
download | mongo-3fe7917512f6e481c1539c68d28a35772233c3f1.tar.gz |
SERVER-24662 Remove PCRE 8.38
(cherry picked from commit 52c31b56459607bbebd9c6f7b70d2b4f4ba55f76)
128 files changed, 0 insertions, 80439 deletions
diff --git a/src/third_party/pcre-8.38/132html b/src/third_party/pcre-8.38/132html deleted file mode 100755 index e00024970a5..00000000000 --- a/src/third_party/pcre-8.38/132html +++ /dev/null @@ -1,313 +0,0 @@ -#! /usr/bin/perl -w - -# Script to turn PCRE man pages into HTML - - -# Subroutine to handle font changes and other escapes - -sub do_line { -my($s) = $_[0]; - -$s =~ s/</</g; # Deal with < and > -$s =~ s/>/>/g; -$s =~ s"\\fI(.*?)\\f[RP]"<i>$1</i>"g; -$s =~ s"\\fB(.*?)\\f[RP]"<b>$1</b>"g; -$s =~ s"\\e"\\"g; -$s =~ s/(?<=Copyright )\(c\)/©/g; -$s; -} - -# Subroutine to ensure not in a paragraph - -sub end_para { -if ($inpara) - { - print TEMP "</PRE>\n" if ($inpre); - print TEMP "</P>\n"; - } -$inpara = $inpre = 0; -$wrotetext = 0; -} - -# Subroutine to start a new paragraph - -sub new_para { -&end_para(); -print TEMP "<P>\n"; -$inpara = 1; -} - - -# Main program - -$innf = 0; -$inpara = 0; -$inpre = 0; -$wrotetext = 0; -$toc = 0; -$ref = 1; - -while ($#ARGV >= 0 && $ARGV[0] =~ /^-/) - { - $toc = 1 if $ARGV[0] eq "-toc"; - shift; - } - -# Initial output to STDOUT - -print <<End ; -<html> -<head> -<title>$ARGV[0] specification</title> -</head> -<body bgcolor="#FFFFFF" text="#00005A" link="#0066FF" alink="#3399FF" vlink="#2222BB"> -<h1>$ARGV[0] man page</h1> -<p> -Return to the <a href="index.html">PCRE index page</a>. -</p> -<p> -This page is part of the PCRE HTML documentation. It was generated automatically -from the original man page. If there is any nonsense in it, please consult the -man page, in case the conversion went wrong. -<br> -End - -print "<ul>\n" if ($toc); - -open(TEMP, ">/tmp/$$") || die "Can't open /tmp/$$ for output\n"; - -while (<STDIN>) - { - # Handle lines beginning with a dot - - if (/^\./) - { - # Some of the PCRE man pages used to contain instances of .br. However, - # they should have all been removed because they cause trouble in some - # (other) automated systems that translate man pages to HTML. Complain if - # we find .br or .in (another macro that is deprecated). - - if (/^\.br/ || /^\.in/) - { - print STDERR "\n*** Deprecated macro encountered - rewrite needed\n"; - print STDERR "*** $_\n"; - die "*** Processing abandoned\n"; - } - - # Instead of .br, relevent "literal" sections are enclosed in .nf/.fi. - - elsif (/^\.nf/) - { - $innf = 1; - } - - elsif (/^\.fi/) - { - $innf = 0; - } - - # Handling .sp is subtle. If it is inside a literal section, do nothing if - # the next line is a non literal text line; similarly, if not inside a - # literal section, do nothing if a literal follows, unless we are inside - # a .nf/.ne section. The point being that the <pre> and </pre> that delimit - # literal sections will do the spacing. Always skip if no previous output. - - elsif (/^\.sp/) - { - if ($wrotetext) - { - $_ = <STDIN>; - if ($inpre) - { - print TEMP "\n" if (/^[\s.]/); - } - else - { - print TEMP "<br>\n<br>\n" if ($innf || !/^[\s.]/); - } - redo; # Now process the lookahead line we just read - } - } - elsif (/^\.TP/ || /^\.PP/ || /^\.P/) - { - &new_para(); - } - elsif (/^\.SH\s*("?)(.*)\1/) - { - # Ignore the NAME section - if ($2 =~ /^NAME\b/) - { - <STDIN>; - next; - } - - &end_para(); - my($title) = &do_line($2); - if ($toc) - { - printf("<li><a name=\"TOC%d\" href=\"#SEC%d\">$title</a>\n", - $ref, $ref); - printf TEMP ("<br><a name=\"SEC%d\" href=\"#TOC1\">$title</a><br>\n", - $ref); - $ref++; - } - else - { - print TEMP "<br><b>\n$title\n</b><br>\n"; - } - } - elsif (/^\.SS\s*("?)(.*)\1/) - { - &end_para(); - my($title) = &do_line($2); - print TEMP "<br><b>\n$title\n</b><br>\n"; - } - elsif (/^\.B\s*(.*)/) - { - &new_para() if (!$inpara); - $_ = &do_line($1); - s/"(.*?)"/$1/g; - print TEMP "<b>$_</b>\n"; - $wrotetext = 1; - } - elsif (/^\.I\s*(.*)/) - { - &new_para() if (!$inpara); - $_ = &do_line($1); - s/"(.*?)"/$1/g; - print TEMP "<i>$_</i>\n"; - $wrotetext = 1; - } - - # A comment that starts "HREF" takes the next line as a name that - # is turned into a hyperlink, using the text given, which might be - # in a special font. If it ends in () or (digits) or punctuation, they - # aren't part of the link. - - elsif (/^\.\\"\s*HREF/) - { - $_=<STDIN>; - chomp; - $_ = &do_line($_); - $_ =~ s/\s+$//; - $_ =~ /^(?:<.>)?([^<(]+)(?:\(\))?(?:<\/.>)?(?:\(\d+\))?[.,;:]?$/; - print TEMP "<a href=\"$1.html\">$_</a>\n"; - } - - # A comment that starts "HTML" inserts literal HTML - - elsif (/^\.\\"\s*HTML\s*(.*)/) - { - print TEMP $1; - } - - # A comment that starts < inserts that HTML at the end of the - # *next* input line - so as not to get a newline between them. - - elsif (/^\.\\"\s*(<.*>)/) - { - my($markup) = $1; - $_=<STDIN>; - chomp; - $_ = &do_line($_); - $_ =~ s/\s+$//; - print TEMP "$_$markup\n"; - } - - # A comment that starts JOIN joins the next two lines together, with one - # space between them. Then that line is processed. This is used in some - # displays where two lines are needed for the "man" version. JOINSH works - # the same, except that it assumes this is a shell command, so removes - # continuation backslashes. - - elsif (/^\.\\"\s*JOIN(SH)?/) - { - my($one,$two); - $one = <STDIN>; - $two = <STDIN>; - $one =~ s/\s*\\e\s*$// if (defined($1)); - chomp($one); - $two =~ s/^\s+//; - $_ = "$one $two"; - redo; # Process the joined lines - } - - # .EX/.EE are used in the pcredemo page to bracket the entire program, - # which is unmodified except for turning backslash into "\e". - - elsif (/^\.EX\s*$/) - { - print TEMP "<PRE>\n"; - while (<STDIN>) - { - last if /^\.EE\s*$/; - s/\\e/\\/g; - s/&/&/g; - s/</</g; - s/>/>/g; - print TEMP; - } - } - - # Ignore anything not recognized - - next; - } - - # Line does not begin with a dot. Replace blank lines with new paragraphs - - if (/^\s*$/) - { - &end_para() if ($wrotetext); - next; - } - - # Convert fonts changes and output an ordinary line. Ensure that indented - # lines are marked as literal. - - $_ = &do_line($_); - &new_para() if (!$inpara); - - if (/^\s/) - { - if (!$inpre) - { - print TEMP "<pre>\n"; - $inpre = 1; - } - } - elsif ($inpre) - { - print TEMP "</pre>\n"; - $inpre = 0; - } - - # Add <br> to the end of a non-literal line if we are within .nf/.fi - - $_ .= "<br>\n" if (!$inpre && $innf); - - print TEMP; - $wrotetext = 1; - } - -# The TOC, if present, will have been written - terminate it - -print "</ul>\n" if ($toc); - -# Copy the remainder to the standard output - -close(TEMP); -open(TEMP, "/tmp/$$") || die "Can't open /tmp/$$ for input\n"; - -print while (<TEMP>); - -print <<End ; -<p> -Return to the <a href="index.html">PCRE index page</a>. -</p> -End - -close(TEMP); -unlink("/tmp/$$"); - -# End diff --git a/src/third_party/pcre-8.38/AUTHORS b/src/third_party/pcre-8.38/AUTHORS deleted file mode 100644 index d33723f198a..00000000000 --- a/src/third_party/pcre-8.38/AUTHORS +++ /dev/null @@ -1,45 +0,0 @@ -THE MAIN PCRE LIBRARY ---------------------- - -Written by: Philip Hazel -Email local part: ph10 -Email domain: cam.ac.uk - -University of Cambridge Computing Service, -Cambridge, England. - -Copyright (c) 1997-2015 University of Cambridge -All rights reserved - - -PCRE JUST-IN-TIME COMPILATION SUPPORT -------------------------------------- - -Written by: Zoltan Herczeg -Email local part: hzmester -Emain domain: freemail.hu - -Copyright(c) 2010-2015 Zoltan Herczeg -All rights reserved. - - -STACK-LESS JUST-IN-TIME COMPILER --------------------------------- - -Written by: Zoltan Herczeg -Email local part: hzmester -Emain domain: freemail.hu - -Copyright(c) 2009-2015 Zoltan Herczeg -All rights reserved. - - -THE C++ WRAPPER LIBRARY ------------------------ - -Written by: Google Inc. - -Copyright (c) 2007-2012 Google Inc -All rights reserved - -#### diff --git a/src/third_party/pcre-8.38/COPYING b/src/third_party/pcre-8.38/COPYING deleted file mode 100644 index 58eed01b61d..00000000000 --- a/src/third_party/pcre-8.38/COPYING +++ /dev/null @@ -1,5 +0,0 @@ -PCRE LICENCE - -Please see the file LICENCE in the PCRE distribution for licensing details. - -End diff --git a/src/third_party/pcre-8.38/ChangeLog b/src/third_party/pcre-8.38/ChangeLog deleted file mode 100644 index 5e5bf188cea..00000000000 --- a/src/third_party/pcre-8.38/ChangeLog +++ /dev/null @@ -1,5918 +0,0 @@ -ChangeLog for PCRE ------------------- - -Note that the PCRE 8.xx series (PCRE1) is now in a bugfix-only state. All -development is happening in the PCRE2 10.xx series. - -Version 8.38 23-November-2015 ------------------------------ - -1. If a group that contained a recursive back reference also contained a - forward reference subroutine call followed by a non-forward-reference - subroutine call, for example /.((?2)(?R)\1)()/, pcre2_compile() failed to - compile correct code, leading to undefined behaviour or an internally - detected error. This bug was discovered by the LLVM fuzzer. - -2. Quantification of certain items (e.g. atomic back references) could cause - incorrect code to be compiled when recursive forward references were - involved. For example, in this pattern: /(?1)()((((((\1++))\x85)+)|))/. - This bug was discovered by the LLVM fuzzer. - -3. A repeated conditional group whose condition was a reference by name caused - a buffer overflow if there was more than one group with the given name. - This bug was discovered by the LLVM fuzzer. - -4. A recursive back reference by name within a group that had the same name as - another group caused a buffer overflow. For example: - /(?J)(?'d'(?'d'\g{d}))/. This bug was discovered by the LLVM fuzzer. - -5. A forward reference by name to a group whose number is the same as the - current group, for example in this pattern: /(?|(\k'Pm')|(?'Pm'))/, caused - a buffer overflow at compile time. This bug was discovered by the LLVM - fuzzer. - -6. A lookbehind assertion within a set of mutually recursive subpatterns could - provoke a buffer overflow. This bug was discovered by the LLVM fuzzer. - -7. Another buffer overflow bug involved duplicate named groups with a - reference between their definition, with a group that reset capture - numbers, for example: /(?J:(?|(?'R')(\k'R')|((?'R'))))/. This has been - fixed by always allowing for more memory, even if not needed. (A proper fix - is implemented in PCRE2, but it involves more refactoring.) - -8. There was no check for integer overflow in subroutine calls such as (?123). - -9. The table entry for \l in EBCDIC environments was incorrect, leading to its - being treated as a literal 'l' instead of causing an error. - -10. There was a buffer overflow if pcre_exec() was called with an ovector of - size 1. This bug was found by american fuzzy lop. - -11. If a non-capturing group containing a conditional group that could match - an empty string was repeated, it was not identified as matching an empty - string itself. For example: /^(?:(?(1)x|)+)+$()/. - -12. In an EBCDIC environment, pcretest was mishandling the escape sequences - \a and \e in test subject lines. - -13. In an EBCDIC environment, \a in a pattern was converted to the ASCII - instead of the EBCDIC value. - -14. The handling of \c in an EBCDIC environment has been revised so that it is - now compatible with the specification in Perl's perlebcdic page. - -15. The EBCDIC character 0x41 is a non-breaking space, equivalent to 0xa0 in - ASCII/Unicode. This has now been added to the list of characters that are - recognized as white space in EBCDIC. - -16. When PCRE was compiled without UCP support, the use of \p and \P gave an - error (correctly) when used outside a class, but did not give an error - within a class. - -17. \h within a class was incorrectly compiled in EBCDIC environments. - -18. A pattern with an unmatched closing parenthesis that contained a backward - assertion which itself contained a forward reference caused buffer - overflow. And example pattern is: /(?=di(?<=(?1))|(?=(.))))/. - -19. JIT should return with error when the compiled pattern requires more stack - space than the maximum. - -20. A possessively repeated conditional group that could match an empty string, - for example, /(?(R))*+/, was incorrectly compiled. - -21. Fix infinite recursion in the JIT compiler when certain patterns such as - /(?:|a|){100}x/ are analysed. - -22. Some patterns with character classes involving [: and \\ were incorrectly - compiled and could cause reading from uninitialized memory or an incorrect - error diagnosis. - -23. Pathological patterns containing many nested occurrences of [: caused - pcre_compile() to run for a very long time. - -24. A conditional group with only one branch has an implicit empty alternative - branch and must therefore be treated as potentially matching an empty - string. - -25. If (?R was followed by - or + incorrect behaviour happened instead of a - diagnostic. - -26. Arrange to give up on finding the minimum matching length for overly - complex patterns. - -27. Similar to (4) above: in a pattern with duplicated named groups and an - occurrence of (?| it is possible for an apparently non-recursive back - reference to become recursive if a later named group with the relevant - number is encountered. This could lead to a buffer overflow. Wen Guanxing - from Venustech ADLAB discovered this bug. - -28. If pcregrep was given the -q option with -c or -l, or when handling a - binary file, it incorrectly wrote output to stdout. - -29. The JIT compiler did not restore the control verb head in case of *THEN - control verbs. This issue was found by Karl Skomski with a custom LLVM - fuzzer. - -30. Error messages for syntax errors following \g and \k were giving inaccurate - offsets in the pattern. - -31. Added a check for integer overflow in conditions (?(<digits>) and - (?(R<digits>). This omission was discovered by Karl Skomski with the LLVM - fuzzer. - -32. Handling recursive references such as (?2) when the reference is to a group - later in the pattern uses code that is very hacked about and error-prone. - It has been re-written for PCRE2. Here in PCRE1, a check has been added to - give an internal error if it is obvious that compiling has gone wrong. - -33. The JIT compiler should not check repeats after a {0,1} repeat byte code. - This issue was found by Karl Skomski with a custom LLVM fuzzer. - -34. The JIT compiler should restore the control chain for empty possessive - repeats. This issue was found by Karl Skomski with a custom LLVM fuzzer. - -35. Match limit check added to JIT recursion. This issue was found by Karl - Skomski with a custom LLVM fuzzer. - -36. Yet another case similar to 27 above has been circumvented by an - unconditional allocation of extra memory. This issue is fixed "properly" in - PCRE2 by refactoring the way references are handled. Wen Guanxing - from Venustech ADLAB discovered this bug. - -37. Fix two assertion fails in JIT. These issues were found by Karl Skomski - with a custom LLVM fuzzer. - -38. Fixed a corner case of range optimization in JIT. - -39. An incorrect error "overran compiling workspace" was given if there were - exactly enough group forward references such that the last one extended - into the workspace safety margin. The next one would have expanded the - workspace. The test for overflow was not including the safety margin. - -40. A match limit issue is fixed in JIT which was found by Karl Skomski - with a custom LLVM fuzzer. - -41. Remove the use of /dev/null in testdata/testinput2, because it doesn't - work under Windows. (Why has it taken so long for anyone to notice?) - -42. In a character class such as [\W\p{Any}] where both a negative-type escape - ("not a word character") and a property escape were present, the property - escape was being ignored. - -43. Fix crash caused by very long (*MARK) or (*THEN) names. - -44. A sequence such as [[:punct:]b] that is, a POSIX character class followed - by a single ASCII character in a class item, was incorrectly compiled in - UCP mode. The POSIX class got lost, but only if the single character - followed it. - -45. [:punct:] in UCP mode was matching some characters in the range 128-255 - that should not have been matched. - -46. If [:^ascii:] or [:^xdigit:] or [:^cntrl:] are present in a non-negated - class, all characters with code points greater than 255 are in the class. - When a Unicode property was also in the class (if PCRE_UCP is set, escapes - such as \w are turned into Unicode properties), wide characters were not - correctly handled, and could fail to match. - - -Version 8.37 28-April-2015 --------------------------- - -1. When an (*ACCEPT) is triggered inside capturing parentheses, it arranges - for those parentheses to be closed with whatever has been captured so far. - However, it was failing to mark any other groups between the hightest - capture so far and the currrent group as "unset". Thus, the ovector for - those groups contained whatever was previously there. An example is the - pattern /(x)|((*ACCEPT))/ when matched against "abcd". - -2. If an assertion condition was quantified with a minimum of zero (an odd - thing to do, but it happened), SIGSEGV or other misbehaviour could occur. - -3. If a pattern in pcretest input had the P (POSIX) modifier followed by an - unrecognized modifier, a crash could occur. - -4. An attempt to do global matching in pcretest with a zero-length ovector - caused a crash. - -5. Fixed a memory leak during matching that could occur for a subpattern - subroutine call (recursive or otherwise) if the number of captured groups - that had to be saved was greater than ten. - -6. Catch a bad opcode during auto-possessification after compiling a bad UTF - string with NO_UTF_CHECK. This is a tidyup, not a bug fix, as passing bad - UTF with NO_UTF_CHECK is documented as having an undefined outcome. - -7. A UTF pattern containing a "not" match of a non-ASCII character and a - subroutine reference could loop at compile time. Example: /[^\xff]((?1))/. - -8. When a pattern is compiled, it remembers the highest back reference so that - when matching, if the ovector is too small, extra memory can be obtained to - use instead. A conditional subpattern whose condition is a check on a - capture having happened, such as, for example in the pattern - /^(?:(a)|b)(?(1)A|B)/, is another kind of back reference, but it was not - setting the highest backreference number. This mattered only if pcre_exec() - was called with an ovector that was too small to hold the capture, and there - was no other kind of back reference (a situation which is probably quite - rare). The effect of the bug was that the condition was always treated as - FALSE when the capture could not be consulted, leading to a incorrect - behaviour by pcre_exec(). This bug has been fixed. - -9. A reference to a duplicated named group (either a back reference or a test - for being set in a conditional) that occurred in a part of the pattern where - PCRE_DUPNAMES was not set caused the amount of memory needed for the pattern - to be incorrectly calculated, leading to overwriting. - -10. A mutually recursive set of back references such as (\2)(\1) caused a - segfault at study time (while trying to find the minimum matching length). - The infinite loop is now broken (with the minimum length unset, that is, - zero). - -11. If an assertion that was used as a condition was quantified with a minimum - of zero, matching went wrong. In particular, if the whole group had - unlimited repetition and could match an empty string, a segfault was - likely. The pattern (?(?=0)?)+ is an example that caused this. Perl allows - assertions to be quantified, but not if they are being used as conditions, - so the above pattern is faulted by Perl. PCRE has now been changed so that - it also rejects such patterns. - -12. A possessive capturing group such as (a)*+ with a minimum repeat of zero - failed to allow the zero-repeat case if pcre2_exec() was called with an - ovector too small to capture the group. - -13. Fixed two bugs in pcretest that were discovered by fuzzing and reported by - Red Hat Product Security: - - (a) A crash if /K and /F were both set with the option to save the compiled - pattern. - - (b) Another crash if the option to print captured substrings in a callout - was combined with setting a null ovector, for example \O\C+ as a subject - string. - -14. A pattern such as "((?2){0,1999}())?", which has a group containing a - forward reference repeated a large (but limited) number of times within a - repeated outer group that has a zero minimum quantifier, caused incorrect - code to be compiled, leading to the error "internal error: - previously-checked referenced subpattern not found" when an incorrect - memory address was read. This bug was reported as "heap overflow", - discovered by Kai Lu of Fortinet's FortiGuard Labs and given the CVE number - CVE-2015-2325. - -23. A pattern such as "((?+1)(\1))/" containing a forward reference subroutine - call within a group that also contained a recursive back reference caused - incorrect code to be compiled. This bug was reported as "heap overflow", - discovered by Kai Lu of Fortinet's FortiGuard Labs, and given the CVE - number CVE-2015-2326. - -24. Computing the size of the JIT read-only data in advance has been a source - of various issues, and new ones are still appear unfortunately. To fix - existing and future issues, size computation is eliminated from the code, - and replaced by on-demand memory allocation. - -25. A pattern such as /(?i)[A-`]/, where characters in the other case are - adjacent to the end of the range, and the range contained characters with - more than one other case, caused incorrect behaviour when compiled in UTF - mode. In that example, the range a-j was left out of the class. - -26. Fix JIT compilation of conditional blocks, which assertion - is converted to (*FAIL). E.g: /(?(?!))/. - -27. The pattern /(?(?!)^)/ caused references to random memory. This bug was - discovered by the LLVM fuzzer. - -28. The assertion (?!) is optimized to (*FAIL). This was not handled correctly - when this assertion was used as a condition, for example (?(?!)a|b). In - pcre2_match() it worked by luck; in pcre2_dfa_match() it gave an incorrect - error about an unsupported item. - -29. For some types of pattern, for example /Z*(|d*){216}/, the auto- - possessification code could take exponential time to complete. A recursion - depth limit of 1000 has been imposed to limit the resources used by this - optimization. - -30. A pattern such as /(*UTF)[\S\V\H]/, which contains a negated special class - such as \S in non-UCP mode, explicit wide characters (> 255) can be ignored - because \S ensures they are all in the class. The code for doing this was - interacting badly with the code for computing the amount of space needed to - compile the pattern, leading to a buffer overflow. This bug was discovered - by the LLVM fuzzer. - -31. A pattern such as /((?2)+)((?1))/ which has mutual recursion nested inside - other kinds of group caused stack overflow at compile time. This bug was - discovered by the LLVM fuzzer. - -32. A pattern such as /(?1)(?#?'){8}(a)/ which had a parenthesized comment - between a subroutine call and its quantifier was incorrectly compiled, - leading to buffer overflow or other errors. This bug was discovered by the - LLVM fuzzer. - -33. The illegal pattern /(?(?<E>.*!.*)?)/ was not being diagnosed as missing an - assertion after (?(. The code was failing to check the character after - (?(?< for the ! or = that would indicate a lookbehind assertion. This bug - was discovered by the LLVM fuzzer. - -34. A pattern such as /X((?2)()*+){2}+/ which has a possessive quantifier with - a fixed maximum following a group that contains a subroutine reference was - incorrectly compiled and could trigger buffer overflow. This bug was - discovered by the LLVM fuzzer. - -35. A mutual recursion within a lookbehind assertion such as (?<=((?2))((?1))) - caused a stack overflow instead of the diagnosis of a non-fixed length - lookbehind assertion. This bug was discovered by the LLVM fuzzer. - -36. The use of \K in a positive lookbehind assertion in a non-anchored pattern - (e.g. /(?<=\Ka)/) could make pcregrep loop. - -37. There was a similar problem to 36 in pcretest for global matches. - -38. If a greedy quantified \X was preceded by \C in UTF mode (e.g. \C\X*), - and a subsequent item in the pattern caused a non-match, backtracking over - the repeated \X did not stop, but carried on past the start of the subject, - causing reference to random memory and/or a segfault. There were also some - other cases where backtracking after \C could crash. This set of bugs was - discovered by the LLVM fuzzer. - -39. The function for finding the minimum length of a matching string could take - a very long time if mutual recursion was present many times in a pattern, - for example, /((?2){73}(?2))((?1))/. A better mutual recursion detection - method has been implemented. This infelicity was discovered by the LLVM - fuzzer. - -40. Static linking against the PCRE library using the pkg-config module was - failing on missing pthread symbols. - - -Version 8.36 26-September-2014 ------------------------------- - -1. Got rid of some compiler warnings in the C++ modules that were shown up by - -Wmissing-field-initializers and -Wunused-parameter. - -2. The tests for quantifiers being too big (greater than 65535) were being - applied after reading the number, and stupidly assuming that integer - overflow would give a negative number. The tests are now applied as the - numbers are read. - -3. Tidy code in pcre_exec.c where two branches that used to be different are - now the same. - -4. The JIT compiler did not generate match limit checks for certain - bracketed expressions with quantifiers. This may lead to exponential - backtracking, instead of returning with PCRE_ERROR_MATCHLIMIT. This - issue should be resolved now. - -5. Fixed an issue, which occures when nested alternatives are optimized - with table jumps. - -6. Inserted two casts and changed some ints to size_t in the light of some - reported 64-bit compiler warnings (Bugzilla 1477). - -7. Fixed a bug concerned with zero-minimum possessive groups that could match - an empty string, which sometimes were behaving incorrectly in the - interpreter (though correctly in the JIT matcher). This pcretest input is - an example: - - '\A(?:[^"]++|"(?:[^"]*+|"")*+")++' - NON QUOTED "QUOT""ED" AFTER "NOT MATCHED - - the interpreter was reporting a match of 'NON QUOTED ' only, whereas the - JIT matcher and Perl both matched 'NON QUOTED "QUOT""ED" AFTER '. The test - for an empty string was breaking the inner loop and carrying on at a lower - level, when possessive repeated groups should always return to a higher - level as they have no backtrack points in them. The empty string test now - occurs at the outer level. - -8. Fixed a bug that was incorrectly auto-possessifying \w+ in the pattern - ^\w+(?>\s*)(?<=\w) which caused it not to match "test test". - -9. Give a compile-time error for \o{} (as Perl does) and for \x{} (which Perl - doesn't). - -10. Change 8.34/15 introduced a bug that caused the amount of memory needed - to hold a pattern to be incorrectly computed (too small) when there were - named back references to duplicated names. This could cause "internal - error: code overflow" or "double free or corruption" or other memory - handling errors. - -11. When named subpatterns had the same prefixes, back references could be - confused. For example, in this pattern: - - /(?P<Name>a)?(?P<Name2>b)?(?(<Name>)c|d)*l/ - - the reference to 'Name' was incorrectly treated as a reference to a - duplicate name. - -12. A pattern such as /^s?c/mi8 where the optional character has more than - one "other case" was incorrectly compiled such that it would only try to - match starting at "c". - -13. When a pattern starting with \s was studied, VT was not included in the - list of possible starting characters; this should have been part of the - 8.34/18 patch. - -14. If a character class started [\Qx]... where x is any character, the class - was incorrectly terminated at the ]. - -15. If a pattern that started with a caseless match for a character with more - than one "other case" was studied, PCRE did not set up the starting code - unit bit map for the list of possible characters. Now it does. This is an - optimization improvement, not a bug fix. - -16. The Unicode data tables have been updated to Unicode 7.0.0. - -17. Fixed a number of memory leaks in pcregrep. - -18. Avoid a compiler warning (from some compilers) for a function call with - a cast that removes "const" from an lvalue by using an intermediate - variable (to which the compiler does not object). - -19. Incorrect code was compiled if a group that contained an internal recursive - back reference was optional (had quantifier with a minimum of zero). This - example compiled incorrect code: /(((a\2)|(a*)\g<-1>))*/ and other examples - caused segmentation faults because of stack overflows at compile time. - -20. A pattern such as /((?(R)a|(?1)))+/, which contains a recursion within a - group that is quantified with an indefinite repeat, caused a compile-time - loop which used up all the system stack and provoked a segmentation fault. - This was not the same bug as 19 above. - -21. Add PCRECPP_EXP_DECL declaration to operator<< in pcre_stringpiece.h. - Patch by Mike Frysinger. - - -Version 8.35 04-April-2014 --------------------------- - -1. A new flag is set, when property checks are present in an XCLASS. - When this flag is not set, PCRE can perform certain optimizations - such as studying these XCLASS-es. - -2. The auto-possessification of character sets were improved: a normal - and an extended character set can be compared now. Furthermore - the JIT compiler optimizes more character set checks. - -3. Got rid of some compiler warnings for potentially uninitialized variables - that show up only when compiled with -O2. - -4. A pattern such as (?=ab\K) that uses \K in an assertion can set the start - of a match later then the end of the match. The pcretest program was not - handling the case sensibly - it was outputting from the start to the next - binary zero. It now reports this situation in a message, and outputs the - text from the end to the start. - -5. Fast forward search is improved in JIT. Instead of the first three - characters, any three characters with fixed position can be searched. - Search order: first, last, middle. - -6. Improve character range checks in JIT. Characters are read by an inprecise - function now, which returns with an unknown value if the character code is - above a certain threshold (e.g: 256). The only limitation is that the value - must be bigger than the threshold as well. This function is useful when - the characters above the threshold are handled in the same way. - -7. The macros whose names start with RAWUCHAR are placeholders for a future - mode in which only the bottom 21 bits of 32-bit data items are used. To - make this more memorable for those maintaining the code, the names have - been changed to start with UCHAR21, and an extensive comment has been added - to their definition. - -8. Add missing (new) files sljitNativeTILEGX.c and sljitNativeTILEGX-encoder.c - to the export list in Makefile.am (they were accidentally omitted from the - 8.34 tarball). - -9. The informational output from pcretest used the phrase "starting byte set" - which is inappropriate for the 16-bit and 32-bit libraries. As the output - for "first char" and "need char" really means "non-UTF-char", I've changed - "byte" to "char", and slightly reworded the output. The documentation about - these values has also been (I hope) clarified. - -10. Another JIT related optimization: use table jumps for selecting the correct - backtracking path, when more than four alternatives are present inside a - bracket. - -11. Empty match is not possible, when the minimum length is greater than zero, - and there is no \K in the pattern. JIT should avoid empty match checks in - such cases. - -12. In a caseless character class with UCP support, when a character with more - than one alternative case was not the first character of a range, not all - the alternative cases were added to the class. For example, s and \x{17f} - are both alternative cases for S: the class [RST] was handled correctly, - but [R-T] was not. - -13. The configure.ac file always checked for pthread support when JIT was - enabled. This is not used in Windows, so I have put this test inside a - check for the presence of windows.h (which was already tested for). - -14. Improve pattern prefix search by a simplified Boyer-Moore algorithm in JIT. - The algorithm provides a way to skip certain starting offsets, and usually - faster than linear prefix searches. - -15. Change 13 for 8.20 updated RunTest to check for the 'fr' locale as well - as for 'fr_FR' and 'french'. For some reason, however, it then used the - Windows-specific input and output files, which have 'french' screwed in. - So this could never have worked. One of the problems with locales is that - they aren't always the same. I have now updated RunTest so that it checks - the output of the locale test (test 3) against three different output - files, and it allows the test to pass if any one of them matches. With luck - this should make the test pass on some versions of Solaris where it was - failing. Because of the uncertainty, the script did not used to stop if - test 3 failed; it now does. If further versions of a French locale ever - come to light, they can now easily be added. - -16. If --with-pcregrep-bufsize was given a non-integer value such as "50K", - there was a message during ./configure, but it did not stop. This now - provokes an error. The invalid example in README has been corrected. - If a value less than the minimum is given, the minimum value has always - been used, but now a warning is given. - -17. If --enable-bsr-anycrlf was set, the special 16/32-bit test failed. This - was a bug in the test system, which is now fixed. Also, the list of various - configurations that are tested for each release did not have one with both - 16/32 bits and --enable-bar-anycrlf. It now does. - -18. pcretest was missing "-C bsr" for displaying the \R default setting. - -19. Little endian PowerPC systems are supported now by the JIT compiler. - -20. The fast forward newline mechanism could enter to an infinite loop on - certain invalid UTF-8 input. Although we don't support these cases - this issue can be fixed by a performance optimization. - -21. Change 33 of 8.34 is not sufficient to ensure stack safety because it does - not take account if existing stack usage. There is now a new global - variable called pcre_stack_guard that can be set to point to an external - function to check stack availability. It is called at the start of - processing every parenthesized group. - -22. A typo in the code meant that in ungreedy mode the max/min qualifier - behaved like a min-possessive qualifier, and, for example, /a{1,3}b/U did - not match "ab". - -23. When UTF was disabled, the JIT program reported some incorrect compile - errors. These messages are silenced now. - -24. Experimental support for ARM-64 and MIPS-64 has been added to the JIT - compiler. - -25. Change all the temporary files used in RunGrepTest to be different to those - used by RunTest so that the tests can be run simultaneously, for example by - "make -j check". - - -Version 8.34 15-December-2013 ------------------------------ - -1. Add pcre[16|32]_jit_free_unused_memory to forcibly free unused JIT - executable memory. Patch inspired by Carsten Klein. - -2. ./configure --enable-coverage defined SUPPORT_GCOV in config.h, although - this macro is never tested and has no effect, because the work to support - coverage involves only compiling and linking options and special targets in - the Makefile. The comment in config.h implied that defining the macro would - enable coverage support, which is totally false. There was also support for - setting this macro in the CMake files (my fault, I just copied it from - configure). SUPPORT_GCOV has now been removed. - -3. Make a small performance improvement in strlen16() and strlen32() in - pcretest. - -4. Change 36 for 8.33 left some unreachable statements in pcre_exec.c, - detected by the Solaris compiler (gcc doesn't seem to be able to diagnose - these cases). There was also one in pcretest.c. - -5. Cleaned up a "may be uninitialized" compiler warning in pcre_exec.c. - -6. In UTF mode, the code for checking whether a group could match an empty - string (which is used for indefinitely repeated groups to allow for - breaking an infinite loop) was broken when the group contained a repeated - negated single-character class with a character that occupied more than one - data item and had a minimum repetition of zero (for example, [^\x{100}]* in - UTF-8 mode). The effect was undefined: the group might or might not be - deemed as matching an empty string, or the program might have crashed. - -7. The code for checking whether a group could match an empty string was not - recognizing that \h, \H, \v, \V, and \R must match a character. - -8. Implemented PCRE_INFO_MATCH_EMPTY, which yields 1 if the pattern can match - an empty string. If it can, pcretest shows this in its information output. - -9. Fixed two related bugs that applied to Unicode extended grapheme clusters - that were repeated with a maximizing qualifier (e.g. \X* or \X{2,5}) when - matched by pcre_exec() without using JIT: - - (a) If the rest of the pattern did not match after a maximal run of - grapheme clusters, the code for backing up to try with fewer of them - did not always back up over a full grapheme when characters that do not - have the modifier quality were involved, e.g. Hangul syllables. - - (b) If the match point in a subject started with modifier character, and - there was no match, the code could incorrectly back up beyond the match - point, and potentially beyond the first character in the subject, - leading to a segfault or an incorrect match result. - -10. A conditional group with an assertion condition could lead to PCRE - recording an incorrect first data item for a match if no other first data - item was recorded. For example, the pattern (?(?=ab)ab) recorded "a" as a - first data item, and therefore matched "ca" after "c" instead of at the - start. - -11. Change 40 for 8.33 (allowing pcregrep to find empty strings) showed up a - bug that caused the command "echo a | ./pcregrep -M '|a'" to loop. - -12. The source of pcregrep now includes z/OS-specific code so that it can be - compiled for z/OS as part of the special z/OS distribution. - -13. Added the -T and -TM options to pcretest. - -14. The code in pcre_compile.c for creating the table of named capturing groups - has been refactored. Instead of creating the table dynamically during the - actual compiling pass, the information is remembered during the pre-compile - pass (on the stack unless there are more than 20 named groups, in which - case malloc() is used) and the whole table is created before the actual - compile happens. This has simplified the code (it is now nearly 150 lines - shorter) and prepared the way for better handling of references to groups - with duplicate names. - -15. A back reference to a named subpattern when there is more than one of the - same name now checks them in the order in which they appear in the pattern. - The first one that is set is used for the reference. Previously only the - first one was inspected. This change makes PCRE more compatible with Perl. - -16. Unicode character properties were updated from Unicode 6.3.0. - -17. The compile-time code for auto-possessification has been refactored, based - on a patch by Zoltan Herczeg. It now happens after instead of during - compilation. The code is cleaner, and more cases are handled. The option - PCRE_NO_AUTO_POSSESS is added for testing purposes, and the -O and /O - options in pcretest are provided to set it. It can also be set by - (*NO_AUTO_POSSESS) at the start of a pattern. - -18. The character VT has been added to the default ("C" locale) set of - characters that match \s and are generally treated as white space, - following this same change in Perl 5.18. There is now no difference between - "Perl space" and "POSIX space". Whether VT is treated as white space in - other locales depends on the locale. - -19. The code for checking named groups as conditions, either for being set or - for being recursed, has been refactored (this is related to 14 and 15 - above). Processing unduplicated named groups should now be as fast at - numerical groups, and processing duplicated groups should be faster than - before. - -20. Two patches to the CMake build system, by Alexander Barkov: - - (1) Replace the "source" command by "." in CMakeLists.txt because - "source" is a bash-ism. - - (2) Add missing HAVE_STDINT_H and HAVE_INTTYPES_H to config-cmake.h.in; - without these the CMake build does not work on Solaris. - -21. Perl has changed its handling of \8 and \9. If there is no previously - encountered capturing group of those numbers, they are treated as the - literal characters 8 and 9 instead of a binary zero followed by the - literals. PCRE now does the same. - -22. Following Perl, added \o{} to specify codepoints in octal, making it - possible to specify values greater than 0777 and also making them - unambiguous. - -23. Perl now gives an error for missing closing braces after \x{... instead of - treating the string as literal. PCRE now does the same. - -24. RunTest used to grumble if an inappropriate test was selected explicitly, - but just skip it when running all tests. This make it awkward to run ranges - of tests when one of them was inappropriate. Now it just skips any - inappropriate tests, as it always did when running all tests. - -25. If PCRE_AUTO_CALLOUT and PCRE_UCP were set for a pattern that contained - character types such as \d or \w, too many callouts were inserted, and the - data that they returned was rubbish. - -26. In UCP mode, \s was not matching two of the characters that Perl matches, - namely NEL (U+0085) and MONGOLIAN VOWEL SEPARATOR (U+180E), though they - were matched by \h. The code has now been refactored so that the lists of - the horizontal and vertical whitespace characters used for \h and \v (which - are defined only in one place) are now also used for \s. - -27. Add JIT support for the 64 bit TileGX architecture. - Patch by Jiong Wang (Tilera Corporation). - -28. Possessive quantifiers for classes (both explicit and automatically - generated) now use special opcodes instead of wrapping in ONCE brackets. - -29. Whereas an item such as A{4}+ ignored the possessivenes of the quantifier - (because it's meaningless), this was not happening when PCRE_CASELESS was - set. Not wrong, but inefficient. - -30. Updated perltest.pl to add /u (force Unicode mode) when /W (use Unicode - properties for \w, \d, etc) is present in a test regex. Otherwise if the - test contains no characters greater than 255, Perl doesn't realise it - should be using Unicode semantics. - -31. Upgraded the handling of the POSIX classes [:graph:], [:print:], and - [:punct:] when PCRE_UCP is set so as to include the same characters as Perl - does in Unicode mode. - -32. Added the "forbid" facility to pcretest so that putting tests into the - wrong test files can sometimes be quickly detected. - -33. There is now a limit (default 250) on the depth of nesting of parentheses. - This limit is imposed to control the amount of system stack used at compile - time. It can be changed at build time by --with-parens-nest-limit=xxx or - the equivalent in CMake. - -34. Character classes such as [A-\d] or [a-[:digit:]] now cause compile-time - errors. Perl warns for these when in warning mode, but PCRE has no facility - for giving warnings. - -35. Change 34 for 8.13 allowed quantifiers on assertions, because Perl does. - However, this was not working for (?!) because it is optimized to (*FAIL), - for which PCRE does not allow quantifiers. The optimization is now disabled - when a quantifier follows (?!). I can't see any use for this, but it makes - things uniform. - -36. Perl no longer allows group names to start with digits, so I have made this - change also in PCRE. It simplifies the code a bit. - -37. In extended mode, Perl ignores spaces before a + that indicates a - possessive quantifier. PCRE allowed a space before the quantifier, but not - before the possessive +. It now does. - -38. The use of \K (reset reported match start) within a repeated possessive - group such as (a\Kb)*+ was not working. - -40. Document that the same character tables must be used at compile time and - run time, and that the facility to pass tables to pcre_exec() and - pcre_dfa_exec() is for use only with saved/restored patterns. - -41. Applied Jeff Trawick's patch CMakeLists.txt, which "provides two new - features for Builds with MSVC: - - 1. Support pcre.rc and/or pcreposix.rc (as is already done for MinGW - builds). The .rc files can be used to set FileDescription and many other - attributes. - - 2. Add an option (-DINSTALL_MSVC_PDB) to enable installation of .pdb files. - This allows higher-level build scripts which want .pdb files to avoid - hard-coding the exact files needed." - -42. Added support for [[:<:]] and [[:>:]] as used in the BSD POSIX library to - mean "start of word" and "end of word", respectively, as a transition aid. - -43. A minimizing repeat of a class containing codepoints greater than 255 in - non-UTF 16-bit or 32-bit modes caused an internal error when PCRE was - compiled to use the heap for recursion. - -44. Got rid of some compiler warnings for unused variables when UTF but not UCP - is configured. - - -Version 8.33 28-May-2013 ------------------------- - -1. Added 'U' to some constants that are compared to unsigned integers, to - avoid compiler signed/unsigned warnings. Added (int) casts to unsigned - variables that are added to signed variables, to ensure the result is - signed and can be negated. - -2. Applied patch by Daniel Richard G for quashing MSVC warnings to the - CMake config files. - -3. Revise the creation of config.h.generic so that all boolean macros are - #undefined, whereas non-boolean macros are #ifndef/#endif-ed. This makes - overriding via -D on the command line possible. - -4. Changing the definition of the variable "op" in pcre_exec.c from pcre_uchar - to unsigned int is reported to make a quite noticeable speed difference in - a specific Windows environment. Testing on Linux did also appear to show - some benefit (and it is clearly not harmful). Also fixed the definition of - Xop which should be unsigned. - -5. Related to (4), changing the definition of the intermediate variable cc - in repeated character loops from pcre_uchar to pcre_uint32 also gave speed - improvements. - -6. Fix forward search in JIT when link size is 3 or greater. Also removed some - unnecessary spaces. - -7. Adjust autogen.sh and configure.ac to lose warnings given by automake 1.12 - and later. - -8. Fix two buffer over read issues in 16 and 32 bit modes. Affects JIT only. - -9. Optimizing fast_forward_start_bits in JIT. - -10. Adding support for callouts in JIT, and fixing some issues revealed - during this work. Namely: - - (a) Unoptimized capturing brackets incorrectly reset on backtrack. - - (b) Minimum length was not checked before the matching is started. - -11. The value of capture_last that is passed to callouts was incorrect in some - cases when there was a capture on one path that was subsequently abandoned - after a backtrack. Also, the capture_last value is now reset after a - recursion, since all captures are also reset in this case. - -12. The interpreter no longer returns the "too many substrings" error in the - case when an overflowing capture is in a branch that is subsequently - abandoned after a backtrack. - -13. In the pathological case when an offset vector of size 2 is used, pcretest - now prints out the matched string after a yield of 0 or 1. - -14. Inlining subpatterns in recursions, when certain conditions are fulfilled. - Only supported by the JIT compiler at the moment. - -15. JIT compiler now supports 32 bit Macs thanks to Lawrence Velazquez. - -16. Partial matches now set offsets[2] to the "bumpalong" value, that is, the - offset of the starting point of the matching process, provided the offsets - vector is large enough. - -17. The \A escape now records a lookbehind value of 1, though its execution - does not actually inspect the previous character. This is to ensure that, - in partial multi-segment matching, at least one character from the old - segment is retained when a new segment is processed. Otherwise, if there - are no lookbehinds in the pattern, \A might match incorrectly at the start - of a new segment. - -18. Added some #ifdef __VMS code into pcretest.c to help VMS implementations. - -19. Redefined some pcre_uchar variables in pcre_exec.c as pcre_uint32; this - gives some modest performance improvement in 8-bit mode. - -20. Added the PCRE-specific property \p{Xuc} for matching characters that can - be expressed in certain programming languages using Universal Character - Names. - -21. Unicode validation has been updated in the light of Unicode Corrigendum #9, - which points out that "non characters" are not "characters that may not - appear in Unicode strings" but rather "characters that are reserved for - internal use and have only local meaning". - -22. When a pattern was compiled with automatic callouts (PCRE_AUTO_CALLOUT) and - there was a conditional group that depended on an assertion, if the - assertion was false, the callout that immediately followed the alternation - in the condition was skipped when pcre_exec() was used for matching. - -23. Allow an explicit callout to be inserted before an assertion that is the - condition for a conditional group, for compatibility with automatic - callouts, which always insert a callout at this point. - -24. In 8.31, (*COMMIT) was confined to within a recursive subpattern. Perl also - confines (*SKIP) and (*PRUNE) in the same way, and this has now been done. - -25. (*PRUNE) is now supported by the JIT compiler. - -26. Fix infinite loop when /(?<=(*SKIP)ac)a/ is matched against aa. - -27. Fix the case where there are two or more SKIPs with arguments that may be - ignored. - -28. (*SKIP) is now supported by the JIT compiler. - -29. (*THEN) is now supported by the JIT compiler. - -30. Update RunTest with additional test selector options. - -31. The way PCRE handles backtracking verbs has been changed in two ways. - - (1) Previously, in something like (*COMMIT)(*SKIP), COMMIT would override - SKIP. Now, PCRE acts on whichever backtracking verb is reached first by - backtracking. In some cases this makes it more Perl-compatible, but Perl's - rather obscure rules do not always do the same thing. - - (2) Previously, backtracking verbs were confined within assertions. This is - no longer the case for positive assertions, except for (*ACCEPT). Again, - this sometimes improves Perl compatibility, and sometimes does not. - -32. A number of tests that were in test 2 because Perl did things differently - have been moved to test 1, because either Perl or PCRE has changed, and - these tests are now compatible. - -32. Backtracking control verbs are now handled in the same way in JIT and - interpreter. - -33. An opening parenthesis in a MARK/PRUNE/SKIP/THEN name in a pattern that - contained a forward subroutine reference caused a compile error. - -34. Auto-detect and optimize limited repetitions in JIT. - -35. Implement PCRE_NEVER_UTF to lock out the use of UTF, in particular, - blocking (*UTF) etc. - -36. In the interpreter, maximizing pattern repetitions for characters and - character types now use tail recursion, which reduces stack usage. - -37. The value of the max lookbehind was not correctly preserved if a compiled - and saved regex was reloaded on a host of different endianness. - -38. Implemented (*LIMIT_MATCH) and (*LIMIT_RECURSION). As part of the extension - of the compiled pattern block, expand the flags field from 16 to 32 bits - because it was almost full. - -39. Try madvise first before posix_madvise. - -40. Change 7 for PCRE 7.9 made it impossible for pcregrep to find empty lines - with a pattern such as ^$. It has taken 4 years for anybody to notice! The - original change locked out all matches of empty strings. This has been - changed so that one match of an empty string per line is recognized. - Subsequent searches on the same line (for colouring or for --only-matching, - for example) do not recognize empty strings. - -41. Applied a user patch to fix a number of spelling mistakes in comments. - -42. Data lines longer than 65536 caused pcretest to crash. - -43. Clarified the data type for length and startoffset arguments for pcre_exec - and pcre_dfa_exec in the function-specific man pages, where they were - explicitly stated to be in bytes, never having been updated. I also added - some clarification to the pcreapi man page. - -44. A call to pcre_dfa_exec() with an output vector size less than 2 caused - a segmentation fault. - - -Version 8.32 30-November-2012 ------------------------------ - -1. Improved JIT compiler optimizations for first character search and single - character iterators. - -2. Supporting IBM XL C compilers for PPC architectures in the JIT compiler. - Patch by Daniel Richard G. - -3. Single character iterator optimizations in the JIT compiler. - -4. Improved JIT compiler optimizations for character ranges. - -5. Rename the "leave" variable names to "quit" to improve WinCE compatibility. - Reported by Giuseppe D'Angelo. - -6. The PCRE_STARTLINE bit, indicating that a match can occur only at the start - of a line, was being set incorrectly in cases where .* appeared inside - atomic brackets at the start of a pattern, or where there was a subsequent - *PRUNE or *SKIP. - -7. Improved instruction cache flush for POWER/PowerPC. - Patch by Daniel Richard G. - -8. Fixed a number of issues in pcregrep, making it more compatible with GNU - grep: - - (a) There is now no limit to the number of patterns to be matched. - - (b) An error is given if a pattern is too long. - - (c) Multiple uses of --exclude, --exclude-dir, --include, and --include-dir - are now supported. - - (d) --exclude-from and --include-from (multiple use) have been added. - - (e) Exclusions and inclusions now apply to all files and directories, not - just to those obtained from scanning a directory recursively. - - (f) Multiple uses of -f and --file-list are now supported. - - (g) In a Windows environment, the default for -d has been changed from - "read" (the GNU grep default) to "skip", because otherwise the presence - of a directory in the file list provokes an error. - - (h) The documentation has been revised and clarified in places. - -9. Improve the matching speed of capturing brackets. - -10. Changed the meaning of \X so that it now matches a Unicode extended - grapheme cluster. - -11. Patch by Daniel Richard G to the autoconf files to add a macro for sorting - out POSIX threads when JIT support is configured. - -12. Added support for PCRE_STUDY_EXTRA_NEEDED. - -13. In the POSIX wrapper regcomp() function, setting re_nsub field in the preg - structure could go wrong in environments where size_t is not the same size - as int. - -14. Applied user-supplied patch to pcrecpp.cc to allow PCRE_NO_UTF8_CHECK to be - set. - -15. The EBCDIC support had decayed; later updates to the code had included - explicit references to (e.g.) \x0a instead of CHAR_LF. There has been a - general tidy up of EBCDIC-related issues, and the documentation was also - not quite right. There is now a test that can be run on ASCII systems to - check some of the EBCDIC-related things (but is it not a full test). - -16. The new PCRE_STUDY_EXTRA_NEEDED option is now used by pcregrep, resulting - in a small tidy to the code. - -17. Fix JIT tests when UTF is disabled and both 8 and 16 bit mode are enabled. - -18. If the --only-matching (-o) option in pcregrep is specified multiple - times, each one causes appropriate output. For example, -o1 -o2 outputs the - substrings matched by the 1st and 2nd capturing parentheses. A separating - string can be specified by --om-separator (default empty). - -19. Improving the first n character searches. - -20. Turn case lists for horizontal and vertical white space into macros so that - they are defined only once. - -21. This set of changes together give more compatible Unicode case-folding - behaviour for characters that have more than one other case when UCP - support is available. - - (a) The Unicode property table now has offsets into a new table of sets of - three or more characters that are case-equivalent. The MultiStage2.py - script that generates these tables (the pcre_ucd.c file) now scans - CaseFolding.txt instead of UnicodeData.txt for character case - information. - - (b) The code for adding characters or ranges of characters to a character - class has been abstracted into a generalized function that also handles - case-independence. In UTF-mode with UCP support, this uses the new data - to handle characters with more than one other case. - - (c) A bug that is fixed as a result of (b) is that codepoints less than 256 - whose other case is greater than 256 are now correctly matched - caselessly. Previously, the high codepoint matched the low one, but not - vice versa. - - (d) The processing of \h, \H, \v, and \ in character classes now makes use - of the new class addition function, using character lists defined as - macros alongside the case definitions of 20 above. - - (e) Caseless back references now work with characters that have more than - one other case. - - (f) General caseless matching of characters with more than one other case - is supported. - -22. Unicode character properties were updated from Unicode 6.2.0 - -23. Improved CMake support under Windows. Patch by Daniel Richard G. - -24. Add support for 32-bit character strings, and UTF-32 - -25. Major JIT compiler update (code refactoring and bugfixing). - Experimental Sparc 32 support is added. - -26. Applied a modified version of Daniel Richard G's patch to create - pcre.h.generic and config.h.generic by "make" instead of in the - PrepareRelease script. - -27. Added a definition for CHAR_NULL (helpful for the z/OS port), and use it in - pcre_compile.c when checking for a zero character. - -28. Introducing a native interface for JIT. Through this interface, the compiled - machine code can be directly executed. The purpose of this interface is to - provide fast pattern matching, so several sanity checks are not performed. - However, feature tests are still performed. The new interface provides - 1.4x speedup compared to the old one. - -29. If pcre_exec() or pcre_dfa_exec() was called with a negative value for - the subject string length, the error given was PCRE_ERROR_BADOFFSET, which - was confusing. There is now a new error PCRE_ERROR_BADLENGTH for this case. - -30. In 8-bit UTF-8 mode, pcretest failed to give an error for data codepoints - greater than 0x7fffffff (which cannot be represented in UTF-8, even under - the "old" RFC 2279). Instead, it ended up passing a negative length to - pcre_exec(). - -31. Add support for GCC's visibility feature to hide internal functions. - -32. Running "pcretest -C pcre8" or "pcretest -C pcre16" gave a spurious error - "unknown -C option" after outputting 0 or 1. - -33. There is now support for generating a code coverage report for the test - suite in environments where gcc is the compiler and lcov is installed. This - is mainly for the benefit of the developers. - -34. If PCRE is built with --enable-valgrind, certain memory regions are marked - unaddressable using valgrind annotations, allowing valgrind to detect - invalid memory accesses. This is mainly for the benefit of the developers. - -25. (*UTF) can now be used to start a pattern in any of the three libraries. - -26. Give configure error if --enable-cpp but no C++ compiler found. - - -Version 8.31 06-July-2012 -------------------------- - -1. Fixing a wrong JIT test case and some compiler warnings. - -2. Removed a bashism from the RunTest script. - -3. Add a cast to pcre_exec.c to fix the warning "unary minus operator applied - to unsigned type, result still unsigned" that was given by an MS compiler - on encountering the code "-sizeof(xxx)". - -4. Partial matching support is added to the JIT compiler. - -5. Fixed several bugs concerned with partial matching of items that consist - of more than one character: - - (a) /^(..)\1/ did not partially match "aba" because checking references was - done on an "all or nothing" basis. This also applied to repeated - references. - - (b) \R did not give a hard partial match if \r was found at the end of the - subject. - - (c) \X did not give a hard partial match after matching one or more - characters at the end of the subject. - - (d) When newline was set to CRLF, a pattern such as /a$/ did not recognize - a partial match for the string "\r". - - (e) When newline was set to CRLF, the metacharacter "." did not recognize - a partial match for a CR character at the end of the subject string. - -6. If JIT is requested using /S++ or -s++ (instead of just /S+ or -s+) when - running pcretest, the text "(JIT)" added to the output whenever JIT is - actually used to run the match. - -7. Individual JIT compile options can be set in pcretest by following -s+[+] - or /S+[+] with a digit between 1 and 7. - -8. OP_NOT now supports any UTF character not just single-byte ones. - -9. (*MARK) control verb is now supported by the JIT compiler. - -10. The command "./RunTest list" lists the available tests without actually - running any of them. (Because I keep forgetting what they all are.) - -11. Add PCRE_INFO_MAXLOOKBEHIND. - -12. Applied a (slightly modified) user-supplied patch that improves performance - when the heap is used for recursion (compiled with --disable-stack-for- - recursion). Instead of malloc and free for each heap frame each time a - logical recursion happens, frames are retained on a chain and re-used where - possible. This sometimes gives as much as 30% improvement. - -13. As documented, (*COMMIT) is now confined to within a recursive subpattern - call. - -14. As documented, (*COMMIT) is now confined to within a positive assertion. - -15. It is now possible to link pcretest with libedit as an alternative to - libreadline. - -16. (*COMMIT) control verb is now supported by the JIT compiler. - -17. The Unicode data tables have been updated to Unicode 6.1.0. - -18. Added --file-list option to pcregrep. - -19. Added binary file support to pcregrep, including the -a, --binary-files, - -I, and --text options. - -20. The madvise function is renamed for posix_madvise for QNX compatibility - reasons. Fixed by Giuseppe D'Angelo. - -21. Fixed a bug for backward assertions with REVERSE 0 in the JIT compiler. - -22. Changed the option for creating symbolic links for 16-bit man pages from - -s to -sf so that re-installing does not cause issues. - -23. Support PCRE_NO_START_OPTIMIZE in JIT as (*MARK) support requires it. - -24. Fixed a very old bug in pcretest that caused errors with restarted DFA - matches in certain environments (the workspace was not being correctly - retained). Also added to pcre_dfa_exec() a simple plausibility check on - some of the workspace data at the beginning of a restart. - -25. \s*\R was auto-possessifying the \s* when it should not, whereas \S*\R - was not doing so when it should - probably a typo introduced by SVN 528 - (change 8.10/14). - -26. When PCRE_UCP was not set, \w+\x{c4} was incorrectly auto-possessifying the - \w+ when the character tables indicated that \x{c4} was a word character. - There were several related cases, all because the tests for doing a table - lookup were testing for characters less than 127 instead of 255. - -27. If a pattern contains capturing parentheses that are not used in a match, - their slots in the ovector are set to -1. For those that are higher than - any matched groups, this happens at the end of processing. In the case when - there were back references that the ovector was too small to contain - (causing temporary malloc'd memory to be used during matching), and the - highest capturing number was not used, memory off the end of the ovector - was incorrectly being set to -1. (It was using the size of the temporary - memory instead of the true size.) - -28. To catch bugs like 27 using valgrind, when pcretest is asked to specify an - ovector size, it uses memory at the end of the block that it has got. - -29. Check for an overlong MARK name and give an error at compile time. The - limit is 255 for the 8-bit library and 65535 for the 16-bit library. - -30. JIT compiler update. - -31. JIT is now supported on jailbroken iOS devices. Thanks for Ruiger - Rill for the patch. - -32. Put spaces around SLJIT_PRINT_D in the JIT compiler. Required by CXX11. - -33. Variable renamings in the PCRE-JIT compiler. No functionality change. - -34. Fixed typos in pcregrep: in two places there was SUPPORT_LIBZ2 instead of - SUPPORT_LIBBZ2. This caused a build problem when bzip2 but not gzip (zlib) - was enabled. - -35. Improve JIT code generation for greedy plus quantifier. - -36. When /((?:a?)*)*c/ or /((?>a?)*)*c/ was matched against "aac", it set group - 1 to "aa" instead of to an empty string. The bug affected repeated groups - that could potentially match an empty string. - -37. Optimizing single character iterators in JIT. - -38. Wide characters specified with \uxxxx in JavaScript mode are now subject to - the same checks as \x{...} characters in non-JavaScript mode. Specifically, - codepoints that are too big for the mode are faulted, and in a UTF mode, - disallowed codepoints are also faulted. - -39. If PCRE was compiled with UTF support, in three places in the DFA - matcher there was code that should only have been obeyed in UTF mode, but - was being obeyed unconditionally. In 8-bit mode this could cause incorrect - processing when bytes with values greater than 127 were present. In 16-bit - mode the bug would be provoked by values in the range 0xfc00 to 0xdc00. In - both cases the values are those that cannot be the first data item in a UTF - character. The three items that might have provoked this were recursions, - possessively repeated groups, and atomic groups. - -40. Ensure that libpcre is explicitly listed in the link commands for pcretest - and pcregrep, because some OS require shared objects to be explicitly - passed to ld, causing the link step to fail if they are not. - -41. There were two incorrect #ifdefs in pcre_study.c, meaning that, in 16-bit - mode, patterns that started with \h* or \R* might be incorrectly matched. - - -Version 8.30 04-February-2012 ------------------------------ - -1. Renamed "isnumber" as "is_a_number" because in some Mac environments this - name is defined in ctype.h. - -2. Fixed a bug in fixed-length calculation for lookbehinds that would show up - only in quite long subpatterns. - -3. Removed the function pcre_info(), which has been obsolete and deprecated - since it was replaced by pcre_fullinfo() in February 2000. - -4. For a non-anchored pattern, if (*SKIP) was given with a name that did not - match a (*MARK), and the match failed at the start of the subject, a - reference to memory before the start of the subject could occur. This bug - was introduced by fix 17 of release 8.21. - -5. A reference to an unset group with zero minimum repetition was giving - totally wrong answers (in non-JavaScript-compatibility mode). For example, - /(another)?(\1?)test/ matched against "hello world test". This bug was - introduced in release 8.13. - -6. Add support for 16-bit character strings (a large amount of work involving - many changes and refactorings). - -7. RunGrepTest failed on msys because \r\n was replaced by whitespace when the - command "pattern=`printf 'xxx\r\njkl'`" was run. The pattern is now taken - from a file. - -8. Ovector size of 2 is also supported by JIT based pcre_exec (the ovector size - rounding is not applied in this particular case). - -9. The invalid Unicode surrogate codepoints U+D800 to U+DFFF are now rejected - if they appear, or are escaped, in patterns. - -10. Get rid of a number of -Wunused-but-set-variable warnings. - -11. The pattern /(?=(*:x))(q|)/ matches an empty string, and returns the mark - "x". The similar pattern /(?=(*:x))((*:y)q|)/ did not return a mark at all. - Oddly, Perl behaves the same way. PCRE has been fixed so that this pattern - also returns the mark "x". This bug applied to capturing parentheses, - non-capturing parentheses, and atomic parentheses. It also applied to some - assertions. - -12. Stephen Kelly's patch to CMakeLists.txt allows it to parse the version - information out of configure.ac instead of relying on pcre.h.generic, which - is not stored in the repository. - -13. Applied Dmitry V. Levin's patch for a more portable method for linking with - -lreadline. - -14. ZH added PCRE_CONFIG_JITTARGET; added its output to pcretest -C. - -15. Applied Graycode's patch to put the top-level frame on the stack rather - than the heap when not using the stack for recursion. This gives a - performance improvement in many cases when recursion is not deep. - -16. Experimental code added to "pcretest -C" to output the stack frame size. - - -Version 8.21 12-Dec-2011 ------------------------- - -1. Updating the JIT compiler. - -2. JIT compiler now supports OP_NCREF, OP_RREF and OP_NRREF. New test cases - are added as well. - -3. Fix cache-flush issue on PowerPC (It is still an experimental JIT port). - PCRE_EXTRA_TABLES is not suported by JIT, and should be checked before - calling _pcre_jit_exec. Some extra comments are added. - -4. (*MARK) settings inside atomic groups that do not contain any capturing - parentheses, for example, (?>a(*:m)), were not being passed out. This bug - was introduced by change 18 for 8.20. - -5. Supporting of \x, \U and \u in JavaScript compatibility mode based on the - ECMA-262 standard. - -6. Lookbehinds such as (?<=a{2}b) that contained a fixed repetition were - erroneously being rejected as "not fixed length" if PCRE_CASELESS was set. - This bug was probably introduced by change 9 of 8.13. - -7. While fixing 6 above, I noticed that a number of other items were being - incorrectly rejected as "not fixed length". This arose partly because newer - opcodes had not been added to the fixed-length checking code. I have (a) - corrected the bug and added tests for these items, and (b) arranged for an - error to occur if an unknown opcode is encountered while checking for fixed - length instead of just assuming "not fixed length". The items that were - rejected were: (*ACCEPT), (*COMMIT), (*FAIL), (*MARK), (*PRUNE), (*SKIP), - (*THEN), \h, \H, \v, \V, and single character negative classes with fixed - repetitions, e.g. [^a]{3}, with and without PCRE_CASELESS. - -8. A possessively repeated conditional subpattern such as (?(?=c)c|d)++ was - being incorrectly compiled and would have given unpredicatble results. - -9. A possessively repeated subpattern with minimum repeat count greater than - one behaved incorrectly. For example, (A){2,}+ behaved as if it was - (A)(A)++ which meant that, after a subsequent mismatch, backtracking into - the first (A) could occur when it should not. - -10. Add a cast and remove a redundant test from the code. - -11. JIT should use pcre_malloc/pcre_free for allocation. - -12. Updated pcre-config so that it no longer shows -L/usr/lib, which seems - best practice nowadays, and helps with cross-compiling. (If the exec_prefix - is anything other than /usr, -L is still shown). - -13. In non-UTF-8 mode, \C is now supported in lookbehinds and DFA matching. - -14. Perl does not support \N without a following name in a [] class; PCRE now - also gives an error. - -15. If a forward reference was repeated with an upper limit of around 2000, - it caused the error "internal error: overran compiling workspace". The - maximum number of forward references (including repeats) was limited by the - internal workspace, and dependent on the LINK_SIZE. The code has been - rewritten so that the workspace expands (via pcre_malloc) if necessary, and - the default depends on LINK_SIZE. There is a new upper limit (for safety) - of around 200,000 forward references. While doing this, I also speeded up - the filling in of repeated forward references. - -16. A repeated forward reference in a pattern such as (a)(?2){2}(.) was - incorrectly expecting the subject to contain another "a" after the start. - -17. When (*SKIP:name) is activated without a corresponding (*MARK:name) earlier - in the match, the SKIP should be ignored. This was not happening; instead - the SKIP was being treated as NOMATCH. For patterns such as - /A(*MARK:A)A+(*SKIP:B)Z|AAC/ this meant that the AAC branch was never - tested. - -18. The behaviour of (*MARK), (*PRUNE), and (*THEN) has been reworked and is - now much more compatible with Perl, in particular in cases where the result - is a non-match for a non-anchored pattern. For example, if - /b(*:m)f|a(*:n)w/ is matched against "abc", the non-match returns the name - "m", where previously it did not return a name. A side effect of this - change is that for partial matches, the last encountered mark name is - returned, as for non matches. A number of tests that were previously not - Perl-compatible have been moved into the Perl-compatible test files. The - refactoring has had the pleasing side effect of removing one argument from - the match() function, thus reducing its stack requirements. - -19. If the /S+ option was used in pcretest to study a pattern using JIT, - subsequent uses of /S (without +) incorrectly behaved like /S+. - -21. Retrieve executable code size support for the JIT compiler and fixing - some warnings. - -22. A caseless match of a UTF-8 character whose other case uses fewer bytes did - not work when the shorter character appeared right at the end of the - subject string. - -23. Added some (int) casts to non-JIT modules to reduce warnings on 64-bit - systems. - -24. Added PCRE_INFO_JITSIZE to pass on the value from (21) above, and also - output it when the /M option is used in pcretest. - -25. The CheckMan script was not being included in the distribution. Also, added - an explicit "perl" to run Perl scripts from the PrepareRelease script - because this is reportedly needed in Windows. - -26. If study data was being save in a file and studying had not found a set of - "starts with" bytes for the pattern, the data written to the file (though - never used) was taken from uninitialized memory and so caused valgrind to - complain. - -27. Updated RunTest.bat as provided by Sheri Pierce. - -28. Fixed a possible uninitialized memory bug in pcre_jit_compile.c. - -29. Computation of memory usage for the table of capturing group names was - giving an unnecessarily large value. - - -Version 8.20 21-Oct-2011 ------------------------- - -1. Change 37 of 8.13 broke patterns like [:a]...[b:] because it thought it had - a POSIX class. After further experiments with Perl, which convinced me that - Perl has bugs and confusions, a closing square bracket is no longer allowed - in a POSIX name. This bug also affected patterns with classes that started - with full stops. - -2. If a pattern such as /(a)b|ac/ is matched against "ac", there is no - captured substring, but while checking the failing first alternative, - substring 1 is temporarily captured. If the output vector supplied to - pcre_exec() was not big enough for this capture, the yield of the function - was still zero ("insufficient space for captured substrings"). This cannot - be totally fixed without adding another stack variable, which seems a lot - of expense for a edge case. However, I have improved the situation in cases - such as /(a)(b)x|abc/ matched against "abc", where the return code - indicates that fewer than the maximum number of slots in the ovector have - been set. - -3. Related to (2) above: when there are more back references in a pattern than - slots in the output vector, pcre_exec() uses temporary memory during - matching, and copies in the captures as far as possible afterwards. It was - using the entire output vector, but this conflicts with the specification - that only 2/3 is used for passing back captured substrings. Now it uses - only the first 2/3, for compatibility. This is, of course, another edge - case. - -4. Zoltan Herczeg's just-in-time compiler support has been integrated into the - main code base, and can be used by building with --enable-jit. When this is - done, pcregrep automatically uses it unless --disable-pcregrep-jit or the - runtime --no-jit option is given. - -5. When the number of matches in a pcre_dfa_exec() run exactly filled the - ovector, the return from the function was zero, implying that there were - other matches that did not fit. The correct "exactly full" value is now - returned. - -6. If a subpattern that was called recursively or as a subroutine contained - (*PRUNE) or any other control that caused it to give a non-standard return, - invalid errors such as "Error -26 (nested recursion at the same subject - position)" or even infinite loops could occur. - -7. If a pattern such as /a(*SKIP)c|b(*ACCEPT)|/ was studied, it stopped - computing the minimum length on reaching *ACCEPT, and so ended up with the - wrong value of 1 rather than 0. Further investigation indicates that - computing a minimum subject length in the presence of *ACCEPT is difficult - (think back references, subroutine calls), and so I have changed the code - so that no minimum is registered for a pattern that contains *ACCEPT. - -8. If (*THEN) was present in the first (true) branch of a conditional group, - it was not handled as intended. [But see 16 below.] - -9. Replaced RunTest.bat and CMakeLists.txt with improved versions provided by - Sheri Pierce. - -10. A pathological pattern such as /(*ACCEPT)a/ was miscompiled, thinking that - the first byte in a match must be "a". - -11. Change 17 for 8.13 increased the recursion depth for patterns like - /a(?:.)*?a/ drastically. I've improved things by remembering whether a - pattern contains any instances of (*THEN). If it does not, the old - optimizations are restored. It would be nice to do this on a per-group - basis, but at the moment that is not feasible. - -12. In some environments, the output of pcretest -C is CRLF terminated. This - broke RunTest's code that checks for the link size. A single white space - character after the value is now allowed for. - -13. RunTest now checks for the "fr" locale as well as for "fr_FR" and "french". - For "fr", it uses the Windows-specific input and output files. - -14. If (*THEN) appeared in a group that was called recursively or as a - subroutine, it did not work as intended. [But see next item.] - -15. Consider the pattern /A (B(*THEN)C) | D/ where A, B, C, and D are complex - pattern fragments (but not containing any | characters). If A and B are - matched, but there is a failure in C so that it backtracks to (*THEN), PCRE - was behaving differently to Perl. PCRE backtracked into A, but Perl goes to - D. In other words, Perl considers parentheses that do not contain any | - characters to be part of a surrounding alternative, whereas PCRE was - treading (B(*THEN)C) the same as (B(*THEN)C|(*FAIL)) -- which Perl handles - differently. PCRE now behaves in the same way as Perl, except in the case - of subroutine/recursion calls such as (?1) which have in any case always - been different (but PCRE had them first :-). - -16. Related to 15 above: Perl does not treat the | in a conditional group as - creating alternatives. Such a group is treated in the same way as an - ordinary group without any | characters when processing (*THEN). PCRE has - been changed to match Perl's behaviour. - -17. If a user had set PCREGREP_COLO(U)R to something other than 1:31, the - RunGrepTest script failed. - -18. Change 22 for version 13 caused atomic groups to use more stack. This is - inevitable for groups that contain captures, but it can lead to a lot of - stack use in large patterns. The old behaviour has been restored for atomic - groups that do not contain any capturing parentheses. - -19. If the PCRE_NO_START_OPTIMIZE option was set for pcre_compile(), it did not - suppress the check for a minimum subject length at run time. (If it was - given to pcre_exec() or pcre_dfa_exec() it did work.) - -20. Fixed an ASCII-dependent infelicity in pcretest that would have made it - fail to work when decoding hex characters in data strings in EBCDIC - environments. - -21. It appears that in at least one Mac OS environment, the isxdigit() function - is implemented as a macro that evaluates to its argument more than once, - contravening the C 90 Standard (I haven't checked a later standard). There - was an instance in pcretest which caused it to go wrong when processing - \x{...} escapes in subject strings. The has been rewritten to avoid using - things like p++ in the argument of isxdigit(). - - -Version 8.13 16-Aug-2011 ------------------------- - -1. The Unicode data tables have been updated to Unicode 6.0.0. - -2. Two minor typos in pcre_internal.h have been fixed. - -3. Added #include <string.h> to pcre_scanner_unittest.cc, pcrecpp.cc, and - pcrecpp_unittest.cc. They are needed for strcmp(), memset(), and strchr() - in some environments (e.g. Solaris 10/SPARC using Sun Studio 12U2). - -4. There were a number of related bugs in the code for matching backrefences - caselessly in UTF-8 mode when codes for the characters concerned were - different numbers of bytes. For example, U+023A and U+2C65 are an upper - and lower case pair, using 2 and 3 bytes, respectively. The main bugs were: - (a) A reference to 3 copies of a 2-byte code matched only 2 of a 3-byte - code. (b) A reference to 2 copies of a 3-byte code would not match 2 of a - 2-byte code at the end of the subject (it thought there wasn't enough data - left). - -5. Comprehensive information about what went wrong is now returned by - pcre_exec() and pcre_dfa_exec() when the UTF-8 string check fails, as long - as the output vector has at least 2 elements. The offset of the start of - the failing character and a reason code are placed in the vector. - -6. When the UTF-8 string check fails for pcre_compile(), the offset that is - now returned is for the first byte of the failing character, instead of the - last byte inspected. This is an incompatible change, but I hope it is small - enough not to be a problem. It makes the returned offset consistent with - pcre_exec() and pcre_dfa_exec(). - -7. pcretest now gives a text phrase as well as the error number when - pcre_exec() or pcre_dfa_exec() fails; if the error is a UTF-8 check - failure, the offset and reason code are output. - -8. When \R was used with a maximizing quantifier it failed to skip backwards - over a \r\n pair if the subsequent match failed. Instead, it just skipped - back over a single character (\n). This seems wrong (because it treated the - two characters as a single entity when going forwards), conflicts with the - documentation that \R is equivalent to (?>\r\n|\n|...etc), and makes the - behaviour of \R* different to (\R)*, which also seems wrong. The behaviour - has been changed. - -9. Some internal refactoring has changed the processing so that the handling - of the PCRE_CASELESS and PCRE_MULTILINE options is done entirely at compile - time (the PCRE_DOTALL option was changed this way some time ago: version - 7.7 change 16). This has made it possible to abolish the OP_OPT op code, - which was always a bit of a fudge. It also means that there is one less - argument for the match() function, which reduces its stack requirements - slightly. This change also fixes an incompatibility with Perl: the pattern - (?i:([^b]))(?1) should not match "ab", but previously PCRE gave a match. - -10. More internal refactoring has drastically reduced the number of recursive - calls to match() for possessively repeated groups such as (abc)++ when - using pcre_exec(). - -11. While implementing 10, a number of bugs in the handling of groups were - discovered and fixed: - - (?<=(a)+) was not diagnosed as invalid (non-fixed-length lookbehind). - (a|)*(?1) gave a compile-time internal error. - ((a|)+)+ did not notice that the outer group could match an empty string. - (^a|^)+ was not marked as anchored. - (.*a|.*)+ was not marked as matching at start or after a newline. - -12. Yet more internal refactoring has removed another argument from the match() - function. Special calls to this function are now indicated by setting a - value in a variable in the "match data" data block. - -13. Be more explicit in pcre_study() instead of relying on "default" for - opcodes that mean there is no starting character; this means that when new - ones are added and accidentally left out of pcre_study(), testing should - pick them up. - -14. The -s option of pcretest has been documented for ages as being an old - synonym of -m (show memory usage). I have changed it to mean "force study - for every regex", that is, assume /S for every regex. This is similar to -i - and -d etc. It's slightly incompatible, but I'm hoping nobody is still - using it. It makes it easier to run collections of tests with and without - study enabled, and thereby test pcre_study() more easily. All the standard - tests are now run with and without -s (but some patterns can be marked as - "never study" - see 20 below). - -15. When (*ACCEPT) was used in a subpattern that was called recursively, the - restoration of the capturing data to the outer values was not happening - correctly. - -16. If a recursively called subpattern ended with (*ACCEPT) and matched an - empty string, and PCRE_NOTEMPTY was set, pcre_exec() thought the whole - pattern had matched an empty string, and so incorrectly returned a no - match. - -17. There was optimizing code for the last branch of non-capturing parentheses, - and also for the obeyed branch of a conditional subexpression, which used - tail recursion to cut down on stack usage. Unfortunately, now that there is - the possibility of (*THEN) occurring in these branches, tail recursion is - no longer possible because the return has to be checked for (*THEN). These - two optimizations have therefore been removed. [But see 8.20/11 above.] - -18. If a pattern containing \R was studied, it was assumed that \R always - matched two bytes, thus causing the minimum subject length to be - incorrectly computed because \R can also match just one byte. - -19. If a pattern containing (*ACCEPT) was studied, the minimum subject length - was incorrectly computed. - -20. If /S is present twice on a test pattern in pcretest input, it now - *disables* studying, thereby overriding the use of -s on the command line - (see 14 above). This is necessary for one or two tests to keep the output - identical in both cases. - -21. When (*ACCEPT) was used in an assertion that matched an empty string and - PCRE_NOTEMPTY was set, PCRE applied the non-empty test to the assertion. - -22. When an atomic group that contained a capturing parenthesis was - successfully matched, but the branch in which it appeared failed, the - capturing was not being forgotten if a higher numbered group was later - captured. For example, /(?>(a))b|(a)c/ when matching "ac" set capturing - group 1 to "a", when in fact it should be unset. This applied to multi- - branched capturing and non-capturing groups, repeated or not, and also to - positive assertions (capturing in negative assertions does not happen - in PCRE) and also to nested atomic groups. - -23. Add the ++ qualifier feature to pcretest, to show the remainder of the - subject after a captured substring, to make it easier to tell which of a - number of identical substrings has been captured. - -24. The way atomic groups are processed by pcre_exec() has been changed so that - if they are repeated, backtracking one repetition now resets captured - values correctly. For example, if ((?>(a+)b)+aabab) is matched against - "aaaabaaabaabab" the value of captured group 2 is now correctly recorded as - "aaa". Previously, it would have been "a". As part of this code - refactoring, the way recursive calls are handled has also been changed. - -25. If an assertion condition captured any substrings, they were not passed - back unless some other capturing happened later. For example, if - (?(?=(a))a) was matched against "a", no capturing was returned. - -26. When studying a pattern that contained subroutine calls or assertions, - the code for finding the minimum length of a possible match was handling - direct recursions such as (xxx(?1)|yyy) but not mutual recursions (where - group 1 called group 2 while simultaneously a separate group 2 called group - 1). A stack overflow occurred in this case. I have fixed this by limiting - the recursion depth to 10. - -27. Updated RunTest.bat in the distribution to the version supplied by Tom - Fortmann. This supports explicit test numbers on the command line, and has - argument validation and error reporting. - -28. An instance of \X with an unlimited repeat could fail if at any point the - first character it looked at was a mark character. - -29. Some minor code refactoring concerning Unicode properties and scripts - should reduce the stack requirement of match() slightly. - -30. Added the '=' option to pcretest to check the setting of unused capturing - slots at the end of the pattern, which are documented as being -1, but are - not included in the return count. - -31. If \k was not followed by a braced, angle-bracketed, or quoted name, PCRE - compiled something random. Now it gives a compile-time error (as does - Perl). - -32. A *MARK encountered during the processing of a positive assertion is now - recorded and passed back (compatible with Perl). - -33. If --only-matching or --colour was set on a pcregrep call whose pattern - had alternative anchored branches, the search for a second match in a line - was done as if at the line start. Thus, for example, /^01|^02/ incorrectly - matched the line "0102" twice. The same bug affected patterns that started - with a backwards assertion. For example /\b01|\b02/ also matched "0102" - twice. - -34. Previously, PCRE did not allow quantification of assertions. However, Perl - does, and because of capturing effects, quantifying parenthesized - assertions may at times be useful. Quantifiers are now allowed for - parenthesized assertions. - -35. A minor code tidy in pcre_compile() when checking options for \R usage. - -36. \g was being checked for fancy things in a character class, when it should - just be a literal "g". - -37. PCRE was rejecting [:a[:digit:]] whereas Perl was not. It seems that the - appearance of a nested POSIX class supersedes an apparent external class. - For example, [:a[:digit:]b:] matches "a", "b", ":", or a digit. Also, - unescaped square brackets may also appear as part of class names. For - example, [:a[:abc]b:] gives unknown class "[:abc]b:]". PCRE now behaves - more like Perl. (But see 8.20/1 above.) - -38. PCRE was giving an error for \N with a braced quantifier such as {1,} (this - was because it thought it was \N{name}, which is not supported). - -39. Add minix to OS list not supporting the -S option in pcretest. - -40. PCRE tries to detect cases of infinite recursion at compile time, but it - cannot analyze patterns in sufficient detail to catch mutual recursions - such as ((?1))((?2)). There is now a runtime test that gives an error if a - subgroup is called recursively as a subpattern for a second time at the - same position in the subject string. In previous releases this might have - been caught by the recursion limit, or it might have run out of stack. - -41. A pattern such as /(?(R)a+|(?R)b)/ is quite safe, as the recursion can - happen only once. PCRE was, however incorrectly giving a compile time error - "recursive call could loop indefinitely" because it cannot analyze the - pattern in sufficient detail. The compile time test no longer happens when - PCRE is compiling a conditional subpattern, but actual runaway loops are - now caught at runtime (see 40 above). - -42. It seems that Perl allows any characters other than a closing parenthesis - to be part of the NAME in (*MARK:NAME) and other backtracking verbs. PCRE - has been changed to be the same. - -43. Updated configure.ac to put in more quoting round AC_LANG_PROGRAM etc. so - as not to get warnings when autogen.sh is called. Also changed - AC_PROG_LIBTOOL (deprecated) to LT_INIT (the current macro). - -44. To help people who use pcregrep to scan files containing exceedingly long - lines, the following changes have been made: - - (a) The default value of the buffer size parameter has been increased from - 8K to 20K. (The actual buffer used is three times this size.) - - (b) The default can be changed by ./configure --with-pcregrep-bufsize when - PCRE is built. - - (c) A --buffer-size=n option has been added to pcregrep, to allow the size - to be set at run time. - - (d) Numerical values in pcregrep options can be followed by K or M, for - example --buffer-size=50K. - - (e) If a line being scanned overflows pcregrep's buffer, an error is now - given and the return code is set to 2. - -45. Add a pointer to the latest mark to the callout data block. - -46. The pattern /.(*F)/, when applied to "abc" with PCRE_PARTIAL_HARD, gave a - partial match of an empty string instead of no match. This was specific to - the use of ".". - -47. The pattern /f.*/8s, when applied to "for" with PCRE_PARTIAL_HARD, gave a - complete match instead of a partial match. This bug was dependent on both - the PCRE_UTF8 and PCRE_DOTALL options being set. - -48. For a pattern such as /\babc|\bdef/ pcre_study() was failing to set up the - starting byte set, because \b was not being ignored. - - -Version 8.12 15-Jan-2011 ------------------------- - -1. Fixed some typos in the markup of the man pages, and wrote a script that - checks for such things as part of the documentation building process. - -2. On a big-endian 64-bit system, pcregrep did not correctly process the - --match-limit and --recursion-limit options (added for 8.11). In - particular, this made one of the standard tests fail. (The integer value - went into the wrong half of a long int.) - -3. If the --colour option was given to pcregrep with -v (invert match), it - did strange things, either producing crazy output, or crashing. It should, - of course, ignore a request for colour when reporting lines that do not - match. - -4. Another pcregrep bug caused similar problems if --colour was specified with - -M (multiline) and the pattern match finished with a line ending. - -5. In pcregrep, when a pattern that ended with a literal newline sequence was - matched in multiline mode, the following line was shown as part of the - match. This seems wrong, so I have changed it. - -6. Another pcregrep bug in multiline mode, when --colour was specified, caused - the check for further matches in the same line (so they could be coloured) - to overrun the end of the current line. If another match was found, it was - incorrectly shown (and then shown again when found in the next line). - -7. If pcregrep was compiled under Windows, there was a reference to the - function pcregrep_exit() before it was defined. I am assuming this was - the cause of the "error C2371: 'pcregrep_exit' : redefinition;" that was - reported by a user. I've moved the definition above the reference. - - -Version 8.11 10-Dec-2010 ------------------------- - -1. (*THEN) was not working properly if there were untried alternatives prior - to it in the current branch. For example, in ((a|b)(*THEN)(*F)|c..) it - backtracked to try for "b" instead of moving to the next alternative branch - at the same level (in this case, to look for "c"). The Perl documentation - is clear that when (*THEN) is backtracked onto, it goes to the "next - alternative in the innermost enclosing group". - -2. (*COMMIT) was not overriding (*THEN), as it does in Perl. In a pattern - such as (A(*COMMIT)B(*THEN)C|D) any failure after matching A should - result in overall failure. Similarly, (*COMMIT) now overrides (*PRUNE) and - (*SKIP), (*SKIP) overrides (*PRUNE) and (*THEN), and (*PRUNE) overrides - (*THEN). - -3. If \s appeared in a character class, it removed the VT character from - the class, even if it had been included by some previous item, for example - in [\x00-\xff\s]. (This was a bug related to the fact that VT is not part - of \s, but is part of the POSIX "space" class.) - -4. A partial match never returns an empty string (because you can always - match an empty string at the end of the subject); however the checking for - an empty string was starting at the "start of match" point. This has been - changed to the "earliest inspected character" point, because the returned - data for a partial match starts at this character. This means that, for - example, /(?<=abc)def/ gives a partial match for the subject "abc" - (previously it gave "no match"). - -5. Changes have been made to the way PCRE_PARTIAL_HARD affects the matching - of $, \z, \Z, \b, and \B. If the match point is at the end of the string, - previously a full match would be given. However, setting PCRE_PARTIAL_HARD - has an implication that the given string is incomplete (because a partial - match is preferred over a full match). For this reason, these items now - give a partial match in this situation. [Aside: previously, the one case - /t\b/ matched against "cat" with PCRE_PARTIAL_HARD set did return a partial - match rather than a full match, which was wrong by the old rules, but is - now correct.] - -6. There was a bug in the handling of #-introduced comments, recognized when - PCRE_EXTENDED is set, when PCRE_NEWLINE_ANY and PCRE_UTF8 were also set. - If a UTF-8 multi-byte character included the byte 0x85 (e.g. +U0445, whose - UTF-8 encoding is 0xd1,0x85), this was misinterpreted as a newline when - scanning for the end of the comment. (*Character* 0x85 is an "any" newline, - but *byte* 0x85 is not, in UTF-8 mode). This bug was present in several - places in pcre_compile(). - -7. Related to (6) above, when pcre_compile() was skipping #-introduced - comments when looking ahead for named forward references to subpatterns, - the only newline sequence it recognized was NL. It now handles newlines - according to the set newline convention. - -8. SunOS4 doesn't have strerror() or strtoul(); pcregrep dealt with the - former, but used strtoul(), whereas pcretest avoided strtoul() but did not - cater for a lack of strerror(). These oversights have been fixed. - -9. Added --match-limit and --recursion-limit to pcregrep. - -10. Added two casts needed to build with Visual Studio when NO_RECURSE is set. - -11. When the -o option was used, pcregrep was setting a return code of 1, even - when matches were found, and --line-buffered was not being honoured. - -12. Added an optional parentheses number to the -o and --only-matching options - of pcregrep. - -13. Imitating Perl's /g action for multiple matches is tricky when the pattern - can match an empty string. The code to do it in pcretest and pcredemo - needed fixing: - - (a) When the newline convention was "crlf", pcretest got it wrong, skipping - only one byte after an empty string match just before CRLF (this case - just got forgotten; "any" and "anycrlf" were OK). - - (b) The pcretest code also had a bug, causing it to loop forever in UTF-8 - mode when an empty string match preceded an ASCII character followed by - a non-ASCII character. (The code for advancing by one character rather - than one byte was nonsense.) - - (c) The pcredemo.c sample program did not have any code at all to handle - the cases when CRLF is a valid newline sequence. - -14. Neither pcre_exec() nor pcre_dfa_exec() was checking that the value given - as a starting offset was within the subject string. There is now a new - error, PCRE_ERROR_BADOFFSET, which is returned if the starting offset is - negative or greater than the length of the string. In order to test this, - pcretest is extended to allow the setting of negative starting offsets. - -15. In both pcre_exec() and pcre_dfa_exec() the code for checking that the - starting offset points to the beginning of a UTF-8 character was - unnecessarily clumsy. I tidied it up. - -16. Added PCRE_ERROR_SHORTUTF8 to make it possible to distinguish between a - bad UTF-8 sequence and one that is incomplete when using PCRE_PARTIAL_HARD. - -17. Nobody had reported that the --include_dir option, which was added in - release 7.7 should have been called --include-dir (hyphen, not underscore) - for compatibility with GNU grep. I have changed it to --include-dir, but - left --include_dir as an undocumented synonym, and the same for - --exclude-dir, though that is not available in GNU grep, at least as of - release 2.5.4. - -18. At a user's suggestion, the macros GETCHAR and friends (which pick up UTF-8 - characters from a string of bytes) have been redefined so as not to use - loops, in order to improve performance in some environments. At the same - time, I abstracted some of the common code into auxiliary macros to save - repetition (this should not affect the compiled code). - -19. If \c was followed by a multibyte UTF-8 character, bad things happened. A - compile-time error is now given if \c is not followed by an ASCII - character, that is, a byte less than 128. (In EBCDIC mode, the code is - different, and any byte value is allowed.) - -20. Recognize (*NO_START_OPT) at the start of a pattern to set the PCRE_NO_ - START_OPTIMIZE option, which is now allowed at compile time - but just - passed through to pcre_exec() or pcre_dfa_exec(). This makes it available - to pcregrep and other applications that have no direct access to PCRE - options. The new /Y option in pcretest sets this option when calling - pcre_compile(). - -21. Change 18 of release 8.01 broke the use of named subpatterns for recursive - back references. Groups containing recursive back references were forced to - be atomic by that change, but in the case of named groups, the amount of - memory required was incorrectly computed, leading to "Failed: internal - error: code overflow". This has been fixed. - -22. Some patches to pcre_stringpiece.h, pcre_stringpiece_unittest.cc, and - pcretest.c, to avoid build problems in some Borland environments. - - -Version 8.10 25-Jun-2010 ------------------------- - -1. Added support for (*MARK:ARG) and for ARG additions to PRUNE, SKIP, and - THEN. - -2. (*ACCEPT) was not working when inside an atomic group. - -3. Inside a character class, \B is treated as a literal by default, but - faulted if PCRE_EXTRA is set. This mimics Perl's behaviour (the -w option - causes the error). The code is unchanged, but I tidied the documentation. - -4. Inside a character class, PCRE always treated \R and \X as literals, - whereas Perl faults them if its -w option is set. I have changed PCRE so - that it faults them when PCRE_EXTRA is set. - -5. Added support for \N, which always matches any character other than - newline. (It is the same as "." when PCRE_DOTALL is not set.) - -6. When compiling pcregrep with newer versions of gcc which may have - FORTIFY_SOURCE set, several warnings "ignoring return value of 'fwrite', - declared with attribute warn_unused_result" were given. Just casting the - result to (void) does not stop the warnings; a more elaborate fudge is - needed. I've used a macro to implement this. - -7. Minor change to pcretest.c to avoid a compiler warning. - -8. Added four artifical Unicode properties to help with an option to make - \s etc use properties (see next item). The new properties are: Xan - (alphanumeric), Xsp (Perl space), Xps (POSIX space), and Xwd (word). - -9. Added PCRE_UCP to make \b, \d, \s, \w, and certain POSIX character classes - use Unicode properties. (*UCP) at the start of a pattern can be used to set - this option. Modified pcretest to add /W to test this facility. Added - REG_UCP to make it available via the POSIX interface. - -10. Added --line-buffered to pcregrep. - -11. In UTF-8 mode, if a pattern that was compiled with PCRE_CASELESS was - studied, and the match started with a letter with a code point greater than - 127 whose first byte was different to the first byte of the other case of - the letter, the other case of this starting letter was not recognized - (#976). - -12. If a pattern that was studied started with a repeated Unicode property - test, for example, \p{Nd}+, there was the theoretical possibility of - setting up an incorrect bitmap of starting bytes, but fortunately it could - not have actually happened in practice until change 8 above was made (it - added property types that matched character-matching opcodes). - -13. pcre_study() now recognizes \h, \v, and \R when constructing a bit map of - possible starting bytes for non-anchored patterns. - -14. Extended the "auto-possessify" feature of pcre_compile(). It now recognizes - \R, and also a number of cases that involve Unicode properties, both - explicit and implicit when PCRE_UCP is set. - -15. If a repeated Unicode property match (e.g. \p{Lu}*) was used with non-UTF-8 - input, it could crash or give wrong results if characters with values - greater than 0xc0 were present in the subject string. (Detail: it assumed - UTF-8 input when processing these items.) - -16. Added a lot of (int) casts to avoid compiler warnings in systems where - size_t is 64-bit (#991). - -17. Added a check for running out of memory when PCRE is compiled with - --disable-stack-for-recursion (#990). - -18. If the last data line in a file for pcretest does not have a newline on - the end, a newline was missing in the output. - -19. The default pcre_chartables.c file recognizes only ASCII characters (values - less than 128) in its various bitmaps. However, there is a facility for - generating tables according to the current locale when PCRE is compiled. It - turns out that in some environments, 0x85 and 0xa0, which are Unicode space - characters, are recognized by isspace() and therefore were getting set in - these tables, and indeed these tables seem to approximate to ISO 8859. This - caused a problem in UTF-8 mode when pcre_study() was used to create a list - of bytes that can start a match. For \s, it was including 0x85 and 0xa0, - which of course cannot start UTF-8 characters. I have changed the code so - that only real ASCII characters (less than 128) and the correct starting - bytes for UTF-8 encodings are set for characters greater than 127 when in - UTF-8 mode. (When PCRE_UCP is set - see 9 above - the code is different - altogether.) - -20. Added the /T option to pcretest so as to be able to run tests with non- - standard character tables, thus making it possible to include the tests - used for 19 above in the standard set of tests. - -21. A pattern such as (?&t)(?#()(?(DEFINE)(?<t>a)) which has a forward - reference to a subpattern the other side of a comment that contains an - opening parenthesis caused either an internal compiling error, or a - reference to the wrong subpattern. - - -Version 8.02 19-Mar-2010 ------------------------- - -1. The Unicode data tables have been updated to Unicode 5.2.0. - -2. Added the option --libs-cpp to pcre-config, but only when C++ support is - configured. - -3. Updated the licensing terms in the pcregexp.pas file, as agreed with the - original author of that file, following a query about its status. - -4. On systems that do not have stdint.h (e.g. Solaris), check for and include - inttypes.h instead. This fixes a bug that was introduced by change 8.01/8. - -5. A pattern such as (?&t)*+(?(DEFINE)(?<t>.)) which has a possessive - quantifier applied to a forward-referencing subroutine call, could compile - incorrect code or give the error "internal error: previously-checked - referenced subpattern not found". - -6. Both MS Visual Studio and Symbian OS have problems with initializing - variables to point to external functions. For these systems, therefore, - pcre_malloc etc. are now initialized to local functions that call the - relevant global functions. - -7. There were two entries missing in the vectors called coptable and poptable - in pcre_dfa_exec.c. This could lead to memory accesses outsize the vectors. - I've fixed the data, and added a kludgy way of testing at compile time that - the lengths are correct (equal to the number of opcodes). - -8. Following on from 7, I added a similar kludge to check the length of the - eint vector in pcreposix.c. - -9. Error texts for pcre_compile() are held as one long string to avoid too - much relocation at load time. To find a text, the string is searched, - counting zeros. There was no check for running off the end of the string, - which could happen if a new error number was added without updating the - string. - -10. \K gave a compile-time error if it appeared in a lookbehind assersion. - -11. \K was not working if it appeared in an atomic group or in a group that - was called as a "subroutine", or in an assertion. Perl 5.11 documents that - \K is "not well defined" if used in an assertion. PCRE now accepts it if - the assertion is positive, but not if it is negative. - -12. Change 11 fortuitously reduced the size of the stack frame used in the - "match()" function of pcre_exec.c by one pointer. Forthcoming - implementation of support for (*MARK) will need an extra pointer on the - stack; I have reserved it now, so that the stack frame size does not - decrease. - -13. A pattern such as (?P<L1>(?P<L2>0)|(?P>L2)(?P>L1)) in which the only other - item in branch that calls a recursion is a subroutine call - as in the - second branch in the above example - was incorrectly given the compile- - time error "recursive call could loop indefinitely" because pcre_compile() - was not correctly checking the subroutine for matching a non-empty string. - -14. The checks for overrunning compiling workspace could trigger after an - overrun had occurred. This is a "should never occur" error, but it can be - triggered by pathological patterns such as hundreds of nested parentheses. - The checks now trigger 100 bytes before the end of the workspace. - -15. Fix typo in configure.ac: "srtoq" should be "strtoq". - - -Version 8.01 19-Jan-2010 ------------------------- - -1. If a pattern contained a conditional subpattern with only one branch (in - particular, this includes all (*DEFINE) patterns), a call to pcre_study() - computed the wrong minimum data length (which is of course zero for such - subpatterns). This could cause incorrect "no match" results. - -2. For patterns such as (?i)a(?-i)b|c where an option setting at the start of - the pattern is reset in the first branch, pcre_compile() failed with - "internal error: code overflow at offset...". This happened only when - the reset was to the original external option setting. (An optimization - abstracts leading options settings into an external setting, which was the - cause of this.) - -3. A pattern such as ^(?!a(*SKIP)b) where a negative assertion contained one - of the verbs SKIP, PRUNE, or COMMIT, did not work correctly. When the - assertion pattern did not match (meaning that the assertion was true), it - was incorrectly treated as false if the SKIP had been reached during the - matching. This also applied to assertions used as conditions. - -4. If an item that is not supported by pcre_dfa_exec() was encountered in an - assertion subpattern, including such a pattern used as a condition, - unpredictable results occurred, instead of the error return - PCRE_ERROR_DFA_UITEM. - -5. The C++ GlobalReplace function was not working like Perl for the special - situation when an empty string is matched. It now does the fancy magic - stuff that is necessary. - -6. In pcre_internal.h, obsolete includes to setjmp.h and stdarg.h have been - removed. (These were left over from very, very early versions of PCRE.) - -7. Some cosmetic changes to the code to make life easier when compiling it - as part of something else: - - (a) Change DEBUG to PCRE_DEBUG. - - (b) In pcre_compile(), rename the member of the "branch_chain" structure - called "current" as "current_branch", to prevent a collision with the - Linux macro when compiled as a kernel module. - - (c) In pcre_study(), rename the function set_bit() as set_table_bit(), to - prevent a collision with the Linux macro when compiled as a kernel - module. - -8. In pcre_compile() there are some checks for integer overflows that used to - cast potentially large values to (double). This has been changed to that - when building, a check for int64_t is made, and if it is found, it is used - instead, thus avoiding the use of floating point arithmetic. (There is no - other use of FP in PCRE.) If int64_t is not found, the fallback is to - double. - -9. Added two casts to avoid signed/unsigned warnings from VS Studio Express - 2005 (difference between two addresses compared to an unsigned value). - -10. Change the standard AC_CHECK_LIB test for libbz2 in configure.ac to a - custom one, because of the following reported problem in Windows: - - - libbz2 uses the Pascal calling convention (WINAPI) for the functions - under Win32. - - The standard autoconf AC_CHECK_LIB fails to include "bzlib.h", - therefore missing the function definition. - - The compiler thus generates a "C" signature for the test function. - - The linker fails to find the "C" function. - - PCRE fails to configure if asked to do so against libbz2. - -11. When running libtoolize from libtool-2.2.6b as part of autogen.sh, these - messages were output: - - Consider adding `AC_CONFIG_MACRO_DIR([m4])' to configure.ac and - rerunning libtoolize, to keep the correct libtool macros in-tree. - Consider adding `-I m4' to ACLOCAL_AMFLAGS in Makefile.am. - - I have done both of these things. - -12. Although pcre_dfa_exec() does not use nearly as much stack as pcre_exec() - most of the time, it *can* run out if it is given a pattern that contains a - runaway infinite recursion. I updated the discussion in the pcrestack man - page. - -13. Now that we have gone to the x.xx style of version numbers, the minor - version may start with zero. Using 08 or 09 is a bad idea because users - might check the value of PCRE_MINOR in their code, and 08 or 09 may be - interpreted as invalid octal numbers. I've updated the previous comment in - configure.ac, and also added a check that gives an error if 08 or 09 are - used. - -14. Change 8.00/11 was not quite complete: code had been accidentally omitted, - causing partial matching to fail when the end of the subject matched \W - in a UTF-8 pattern where \W was quantified with a minimum of 3. - -15. There were some discrepancies between the declarations in pcre_internal.h - of _pcre_is_newline(), _pcre_was_newline(), and _pcre_valid_utf8() and - their definitions. The declarations used "const uschar *" and the - definitions used USPTR. Even though USPTR is normally defined as "const - unsigned char *" (and uschar is typedeffed as "unsigned char"), it was - reported that: "This difference in casting confuses some C++ compilers, for - example, SunCC recognizes above declarations as different functions and - generates broken code for hbpcre." I have changed the declarations to use - USPTR. - -16. GNU libtool is named differently on some systems. The autogen.sh script now - tries several variants such as glibtoolize (MacOSX) and libtoolize1x - (FreeBSD). - -17. Applied Craig's patch that fixes an HP aCC compile error in pcre 8.00 - (strtoXX undefined when compiling pcrecpp.cc). The patch contains this - comment: "Figure out how to create a longlong from a string: strtoll and - equivalent. It's not enough to call AC_CHECK_FUNCS: hpux has a strtoll, for - instance, but it only takes 2 args instead of 3!" - -18. A subtle bug concerned with back references has been fixed by a change of - specification, with a corresponding code fix. A pattern such as - ^(xa|=?\1a)+$ which contains a back reference inside the group to which it - refers, was giving matches when it shouldn't. For example, xa=xaaa would - match that pattern. Interestingly, Perl (at least up to 5.11.3) has the - same bug. Such groups have to be quantified to be useful, or contained - inside another quantified group. (If there's no repetition, the reference - can never match.) The problem arises because, having left the group and - moved on to the rest of the pattern, a later failure that backtracks into - the group uses the captured value from the final iteration of the group - rather than the correct earlier one. I have fixed this in PCRE by forcing - any group that contains a reference to itself to be an atomic group; that - is, there cannot be any backtracking into it once it has completed. This is - similar to recursive and subroutine calls. - - -Version 8.00 19-Oct-09 ----------------------- - -1. The table for translating pcre_compile() error codes into POSIX error codes - was out-of-date, and there was no check on the pcre_compile() error code - being within the table. This could lead to an OK return being given in - error. - -2. Changed the call to open a subject file in pcregrep from fopen(pathname, - "r") to fopen(pathname, "rb"), which fixed a problem with some of the tests - in a Windows environment. - -3. The pcregrep --count option prints the count for each file even when it is - zero, as does GNU grep. However, pcregrep was also printing all files when - --files-with-matches was added. Now, when both options are given, it prints - counts only for those files that have at least one match. (GNU grep just - prints the file name in this circumstance, but including the count seems - more useful - otherwise, why use --count?) Also ensured that the - combination -clh just lists non-zero counts, with no names. - -4. The long form of the pcregrep -F option was incorrectly implemented as - --fixed_strings instead of --fixed-strings. This is an incompatible change, - but it seems right to fix it, and I didn't think it was worth preserving - the old behaviour. - -5. The command line items --regex=pattern and --regexp=pattern were not - recognized by pcregrep, which required --regex pattern or --regexp pattern - (with a space rather than an '='). The man page documented the '=' forms, - which are compatible with GNU grep; these now work. - -6. No libpcreposix.pc file was created for pkg-config; there was just - libpcre.pc and libpcrecpp.pc. The omission has been rectified. - -7. Added #ifndef SUPPORT_UCP into the pcre_ucd.c module, to reduce its size - when UCP support is not needed, by modifying the Python script that - generates it from Unicode data files. This should not matter if the module - is correctly used as a library, but I received one complaint about 50K of - unwanted data. My guess is that the person linked everything into his - program rather than using a library. Anyway, it does no harm. - -8. A pattern such as /\x{123}{2,2}+/8 was incorrectly compiled; the trigger - was a minimum greater than 1 for a wide character in a possessive - repetition. The same bug could also affect patterns like /(\x{ff}{0,2})*/8 - which had an unlimited repeat of a nested, fixed maximum repeat of a wide - character. Chaos in the form of incorrect output or a compiling loop could - result. - -9. The restrictions on what a pattern can contain when partial matching is - requested for pcre_exec() have been removed. All patterns can now be - partially matched by this function. In addition, if there are at least two - slots in the offset vector, the offset of the earliest inspected character - for the match and the offset of the end of the subject are set in them when - PCRE_ERROR_PARTIAL is returned. - -10. Partial matching has been split into two forms: PCRE_PARTIAL_SOFT, which is - synonymous with PCRE_PARTIAL, for backwards compatibility, and - PCRE_PARTIAL_HARD, which causes a partial match to supersede a full match, - and may be more useful for multi-segment matching. - -11. Partial matching with pcre_exec() is now more intuitive. A partial match - used to be given if ever the end of the subject was reached; now it is - given only if matching could not proceed because another character was - needed. This makes a difference in some odd cases such as Z(*FAIL) with the - string "Z", which now yields "no match" instead of "partial match". In the - case of pcre_dfa_exec(), "no match" is given if every matching path for the - final character ended with (*FAIL). - -12. Restarting a match using pcre_dfa_exec() after a partial match did not work - if the pattern had a "must contain" character that was already found in the - earlier partial match, unless partial matching was again requested. For - example, with the pattern /dog.(body)?/, the "must contain" character is - "g". If the first part-match was for the string "dog", restarting with - "sbody" failed. This bug has been fixed. - -13. The string returned by pcre_dfa_exec() after a partial match has been - changed so that it starts at the first inspected character rather than the - first character of the match. This makes a difference only if the pattern - starts with a lookbehind assertion or \b or \B (\K is not supported by - pcre_dfa_exec()). It's an incompatible change, but it makes the two - matching functions compatible, and I think it's the right thing to do. - -14. Added a pcredemo man page, created automatically from the pcredemo.c file, - so that the demonstration program is easily available in environments where - PCRE has not been installed from source. - -15. Arranged to add -DPCRE_STATIC to cflags in libpcre.pc, libpcreposix.cp, - libpcrecpp.pc and pcre-config when PCRE is not compiled as a shared - library. - -16. Added REG_UNGREEDY to the pcreposix interface, at the request of a user. - It maps to PCRE_UNGREEDY. It is not, of course, POSIX-compatible, but it - is not the first non-POSIX option to be added. Clearly some people find - these options useful. - -17. If a caller to the POSIX matching function regexec() passes a non-zero - value for nmatch with a NULL value for pmatch, the value of - nmatch is forced to zero. - -18. RunGrepTest did not have a test for the availability of the -u option of - the diff command, as RunTest does. It now checks in the same way as - RunTest, and also checks for the -b option. - -19. If an odd number of negated classes containing just a single character - interposed, within parentheses, between a forward reference to a named - subpattern and the definition of the subpattern, compilation crashed with - an internal error, complaining that it could not find the referenced - subpattern. An example of a crashing pattern is /(?&A)(([^m])(?<A>))/. - [The bug was that it was starting one character too far in when skipping - over the character class, thus treating the ] as data rather than - terminating the class. This meant it could skip too much.] - -20. Added PCRE_NOTEMPTY_ATSTART in order to be able to correctly implement the - /g option in pcretest when the pattern contains \K, which makes it possible - to have an empty string match not at the start, even when the pattern is - anchored. Updated pcretest and pcredemo to use this option. - -21. If the maximum number of capturing subpatterns in a recursion was greater - than the maximum at the outer level, the higher number was returned, but - with unset values at the outer level. The correct (outer level) value is - now given. - -22. If (*ACCEPT) appeared inside capturing parentheses, previous releases of - PCRE did not set those parentheses (unlike Perl). I have now found a way to - make it do so. The string so far is captured, making this feature - compatible with Perl. - -23. The tests have been re-organized, adding tests 11 and 12, to make it - possible to check the Perl 5.10 features against Perl 5.10. - -24. Perl 5.10 allows subroutine calls in lookbehinds, as long as the subroutine - pattern matches a fixed length string. PCRE did not allow this; now it - does. Neither allows recursion. - -25. I finally figured out how to implement a request to provide the minimum - length of subject string that was needed in order to match a given pattern. - (It was back references and recursion that I had previously got hung up - on.) This code has now been added to pcre_study(); it finds a lower bound - to the length of subject needed. It is not necessarily the greatest lower - bound, but using it to avoid searching strings that are too short does give - some useful speed-ups. The value is available to calling programs via - pcre_fullinfo(). - -26. While implementing 25, I discovered to my embarrassment that pcretest had - not been passing the result of pcre_study() to pcre_dfa_exec(), so the - study optimizations had never been tested with that matching function. - Oops. What is worse, even when it was passed study data, there was a bug in - pcre_dfa_exec() that meant it never actually used it. Double oops. There - were also very few tests of studied patterns with pcre_dfa_exec(). - -27. If (?| is used to create subpatterns with duplicate numbers, they are now - allowed to have the same name, even if PCRE_DUPNAMES is not set. However, - on the other side of the coin, they are no longer allowed to have different - names, because these cannot be distinguished in PCRE, and this has caused - confusion. (This is a difference from Perl.) - -28. When duplicate subpattern names are present (necessarily with different - numbers, as required by 27 above), and a test is made by name in a - conditional pattern, either for a subpattern having been matched, or for - recursion in such a pattern, all the associated numbered subpatterns are - tested, and the overall condition is true if the condition is true for any - one of them. This is the way Perl works, and is also more like the way - testing by number works. - - -Version 7.9 11-Apr-09 ---------------------- - -1. When building with support for bzlib/zlib (pcregrep) and/or readline - (pcretest), all targets were linked against these libraries. This included - libpcre, libpcreposix, and libpcrecpp, even though they do not use these - libraries. This caused unwanted dependencies to be created. This problem - has been fixed, and now only pcregrep is linked with bzlib/zlib and only - pcretest is linked with readline. - -2. The "typedef int BOOL" in pcre_internal.h that was included inside the - "#ifndef FALSE" condition by an earlier change (probably 7.8/18) has been - moved outside it again, because FALSE and TRUE are already defined in AIX, - but BOOL is not. - -3. The pcre_config() function was treating the PCRE_MATCH_LIMIT and - PCRE_MATCH_LIMIT_RECURSION values as ints, when they should be long ints. - -4. The pcregrep documentation said spaces were inserted as well as colons (or - hyphens) following file names and line numbers when outputting matching - lines. This is not true; no spaces are inserted. I have also clarified the - wording for the --colour (or --color) option. - -5. In pcregrep, when --colour was used with -o, the list of matching strings - was not coloured; this is different to GNU grep, so I have changed it to be - the same. - -6. When --colo(u)r was used in pcregrep, only the first matching substring in - each matching line was coloured. Now it goes on to look for further matches - of any of the test patterns, which is the same behaviour as GNU grep. - -7. A pattern that could match an empty string could cause pcregrep to loop; it - doesn't make sense to accept an empty string match in pcregrep, so I have - locked it out (using PCRE's PCRE_NOTEMPTY option). By experiment, this - seems to be how GNU grep behaves. [But see later change 40 for release - 8.33.] - -8. The pattern (?(?=.*b)b|^) was incorrectly compiled as "match must be at - start or after a newline", because the conditional assertion was not being - correctly handled. The rule now is that both the assertion and what follows - in the first alternative must satisfy the test. - -9. If auto-callout was enabled in a pattern with a conditional group whose - condition was an assertion, PCRE could crash during matching, both with - pcre_exec() and pcre_dfa_exec(). - -10. The PCRE_DOLLAR_ENDONLY option was not working when pcre_dfa_exec() was - used for matching. - -11. Unicode property support in character classes was not working for - characters (bytes) greater than 127 when not in UTF-8 mode. - -12. Added the -M command line option to pcretest. - -14. Added the non-standard REG_NOTEMPTY option to the POSIX interface. - -15. Added the PCRE_NO_START_OPTIMIZE match-time option. - -16. Added comments and documentation about mis-use of no_arg in the C++ - wrapper. - -17. Implemented support for UTF-8 encoding in EBCDIC environments, a patch - from Martin Jerabek that uses macro names for all relevant character and - string constants. - -18. Added to pcre_internal.h two configuration checks: (a) If both EBCDIC and - SUPPORT_UTF8 are set, give an error; (b) If SUPPORT_UCP is set without - SUPPORT_UTF8, define SUPPORT_UTF8. The "configure" script handles both of - these, but not everybody uses configure. - -19. A conditional group that had only one branch was not being correctly - recognized as an item that could match an empty string. This meant that an - enclosing group might also not be so recognized, causing infinite looping - (and probably a segfault) for patterns such as ^"((?(?=[a])[^"])|b)*"$ - with the subject "ab", where knowledge that the repeated group can match - nothing is needed in order to break the loop. - -20. If a pattern that was compiled with callouts was matched using pcre_dfa_ - exec(), but without supplying a callout function, matching went wrong. - -21. If PCRE_ERROR_MATCHLIMIT occurred during a recursion, there was a memory - leak if the size of the offset vector was greater than 30. When the vector - is smaller, the saved offsets during recursion go onto a local stack - vector, but for larger vectors malloc() is used. It was failing to free - when the recursion yielded PCRE_ERROR_MATCH_LIMIT (or any other "abnormal" - error, in fact). - -22. There was a missing #ifdef SUPPORT_UTF8 round one of the variables in the - heapframe that is used only when UTF-8 support is enabled. This caused no - problem, but was untidy. - -23. Steven Van Ingelgem's patch to CMakeLists.txt to change the name - CMAKE_BINARY_DIR to PROJECT_BINARY_DIR so that it works when PCRE is - included within another project. - -24. Steven Van Ingelgem's patches to add more options to the CMake support, - slightly modified by me: - - (a) PCRE_BUILD_TESTS can be set OFF not to build the tests, including - not building pcregrep. - - (b) PCRE_BUILD_PCREGREP can be see OFF not to build pcregrep, but only - if PCRE_BUILD_TESTS is also set OFF, because the tests use pcregrep. - -25. Forward references, both numeric and by name, in patterns that made use of - duplicate group numbers, could behave incorrectly or give incorrect errors, - because when scanning forward to find the reference group, PCRE was not - taking into account the duplicate group numbers. A pattern such as - ^X(?3)(a)(?|(b)|(q))(Y) is an example. - -26. Changed a few more instances of "const unsigned char *" to USPTR, making - the feature of a custom pointer more persuasive (as requested by a user). - -27. Wrapped the definitions of fileno and isatty for Windows, which appear in - pcretest.c, inside #ifndefs, because it seems they are sometimes already - pre-defined. - -28. Added support for (*UTF8) at the start of a pattern. - -29. Arrange for flags added by the "release type" setting in CMake to be shown - in the configuration summary. - - -Version 7.8 05-Sep-08 ---------------------- - -1. Replaced UCP searching code with optimized version as implemented for Ad - Muncher (http://www.admuncher.com/) by Peter Kankowski. This uses a two- - stage table and inline lookup instead of a function, giving speed ups of 2 - to 5 times on some simple patterns that I tested. Permission was given to - distribute the MultiStage2.py script that generates the tables (it's not in - the tarball, but is in the Subversion repository). - -2. Updated the Unicode datatables to Unicode 5.1.0. This adds yet more - scripts. - -3. Change 12 for 7.7 introduced a bug in pcre_study() when a pattern contained - a group with a zero qualifier. The result of the study could be incorrect, - or the function might crash, depending on the pattern. - -4. Caseless matching was not working for non-ASCII characters in back - references. For example, /(\x{de})\1/8i was not matching \x{de}\x{fe}. - It now works when Unicode Property Support is available. - -5. In pcretest, an escape such as \x{de} in the data was always generating - a UTF-8 string, even in non-UTF-8 mode. Now it generates a single byte in - non-UTF-8 mode. If the value is greater than 255, it gives a warning about - truncation. - -6. Minor bugfix in pcrecpp.cc (change "" == ... to NULL == ...). - -7. Added two (int) casts to pcregrep when printing the difference of two - pointers, in case they are 64-bit values. - -8. Added comments about Mac OS X stack usage to the pcrestack man page and to - test 2 if it fails. - -9. Added PCRE_CALL_CONVENTION just before the names of all exported functions, - and a #define of that name to empty if it is not externally set. This is to - allow users of MSVC to set it if necessary. - -10. The PCRE_EXP_DEFN macro which precedes exported functions was missing from - the convenience functions in the pcre_get.c source file. - -11. An option change at the start of a pattern that had top-level alternatives - could cause overwriting and/or a crash. This command provoked a crash in - some environments: - - printf "/(?i)[\xc3\xa9\xc3\xbd]|[\xc3\xa9\xc3\xbdA]/8\n" | pcretest - - This potential security problem was recorded as CVE-2008-2371. - -12. For a pattern where the match had to start at the beginning or immediately - after a newline (e.g /.*anything/ without the DOTALL flag), pcre_exec() and - pcre_dfa_exec() could read past the end of the passed subject if there was - no match. To help with detecting such bugs (e.g. with valgrind), I modified - pcretest so that it places the subject at the end of its malloc-ed buffer. - -13. The change to pcretest in 12 above threw up a couple more cases when pcre_ - exec() might read past the end of the data buffer in UTF-8 mode. - -14. A similar bug to 7.3/2 existed when the PCRE_FIRSTLINE option was set and - the data contained the byte 0x85 as part of a UTF-8 character within its - first line. This applied both to normal and DFA matching. - -15. Lazy qualifiers were not working in some cases in UTF-8 mode. For example, - /^[^d]*?$/8 failed to match "abc". - -16. Added a missing copyright notice to pcrecpp_internal.h. - -17. Make it more clear in the documentation that values returned from - pcre_exec() in ovector are byte offsets, not character counts. - -18. Tidied a few places to stop certain compilers from issuing warnings. - -19. Updated the Virtual Pascal + BCC files to compile the latest v7.7, as - supplied by Stefan Weber. I made a further small update for 7.8 because - there is a change of source arrangements: the pcre_searchfuncs.c module is - replaced by pcre_ucd.c. - - -Version 7.7 07-May-08 ---------------------- - -1. Applied Craig's patch to sort out a long long problem: "If we can't convert - a string to a long long, pretend we don't even have a long long." This is - done by checking for the strtoq, strtoll, and _strtoi64 functions. - -2. Applied Craig's patch to pcrecpp.cc to restore ABI compatibility with - pre-7.6 versions, which defined a global no_arg variable instead of putting - it in the RE class. (See also #8 below.) - -3. Remove a line of dead code, identified by coverity and reported by Nuno - Lopes. - -4. Fixed two related pcregrep bugs involving -r with --include or --exclude: - - (1) The include/exclude patterns were being applied to the whole pathnames - of files, instead of just to the final components. - - (2) If there was more than one level of directory, the subdirectories were - skipped unless they satisfied the include/exclude conditions. This is - inconsistent with GNU grep (and could even be seen as contrary to the - pcregrep specification - which I improved to make it absolutely clear). - The action now is always to scan all levels of directory, and just - apply the include/exclude patterns to regular files. - -5. Added the --include_dir and --exclude_dir patterns to pcregrep, and used - --exclude_dir in the tests to avoid scanning .svn directories. - -6. Applied Craig's patch to the QuoteMeta function so that it escapes the - NUL character as backslash + 0 rather than backslash + NUL, because PCRE - doesn't support NULs in patterns. - -7. Added some missing "const"s to declarations of static tables in - pcre_compile.c and pcre_dfa_exec.c. - -8. Applied Craig's patch to pcrecpp.cc to fix a problem in OS X that was - caused by fix #2 above. (Subsequently also a second patch to fix the - first patch. And a third patch - this was a messy problem.) - -9. Applied Craig's patch to remove the use of push_back(). - -10. Applied Alan Lehotsky's patch to add REG_STARTEND support to the POSIX - matching function regexec(). - -11. Added support for the Oniguruma syntax \g<name>, \g<n>, \g'name', \g'n', - which, however, unlike Perl's \g{...}, are subroutine calls, not back - references. PCRE supports relative numbers with this syntax (I don't think - Oniguruma does). - -12. Previously, a group with a zero repeat such as (...){0} was completely - omitted from the compiled regex. However, this means that if the group - was called as a subroutine from elsewhere in the pattern, things went wrong - (an internal error was given). Such groups are now left in the compiled - pattern, with a new opcode that causes them to be skipped at execution - time. - -13. Added the PCRE_JAVASCRIPT_COMPAT option. This makes the following changes - to the way PCRE behaves: - - (a) A lone ] character is dis-allowed (Perl treats it as data). - - (b) A back reference to an unmatched subpattern matches an empty string - (Perl fails the current match path). - - (c) A data ] in a character class must be notated as \] because if the - first data character in a class is ], it defines an empty class. (In - Perl it is not possible to have an empty class.) The empty class [] - never matches; it forces failure and is equivalent to (*FAIL) or (?!). - The negative empty class [^] matches any one character, independently - of the DOTALL setting. - -14. A pattern such as /(?2)[]a()b](abc)/ which had a forward reference to a - non-existent subpattern following a character class starting with ']' and - containing () gave an internal compiling error instead of "reference to - non-existent subpattern". Fortunately, when the pattern did exist, the - compiled code was correct. (When scanning forwards to check for the - existence of the subpattern, it was treating the data ']' as terminating - the class, so got the count wrong. When actually compiling, the reference - was subsequently set up correctly.) - -15. The "always fail" assertion (?!) is optimzed to (*FAIL) by pcre_compile; - it was being rejected as not supported by pcre_dfa_exec(), even though - other assertions are supported. I have made pcre_dfa_exec() support - (*FAIL). - -16. The implementation of 13c above involved the invention of a new opcode, - OP_ALLANY, which is like OP_ANY but doesn't check the /s flag. Since /s - cannot be changed at match time, I realized I could make a small - improvement to matching performance by compiling OP_ALLANY instead of - OP_ANY for "." when DOTALL was set, and then removing the runtime tests - on the OP_ANY path. - -17. Compiling pcretest on Windows with readline support failed without the - following two fixes: (1) Make the unistd.h include conditional on - HAVE_UNISTD_H; (2) #define isatty and fileno as _isatty and _fileno. - -18. Changed CMakeLists.txt and cmake/FindReadline.cmake to arrange for the - ncurses library to be included for pcretest when ReadLine support is - requested, but also to allow for it to be overridden. This patch came from - Daniel Bergström. - -19. There was a typo in the file ucpinternal.h where f0_rangeflag was defined - as 0x00f00000 instead of 0x00800000. Luckily, this would not have caused - any errors with the current Unicode tables. Thanks to Peter Kankowski for - spotting this. - - -Version 7.6 28-Jan-08 ---------------------- - -1. A character class containing a very large number of characters with - codepoints greater than 255 (in UTF-8 mode, of course) caused a buffer - overflow. - -2. Patch to cut out the "long long" test in pcrecpp_unittest when - HAVE_LONG_LONG is not defined. - -3. Applied Christian Ehrlicher's patch to update the CMake build files to - bring them up to date and include new features. This patch includes: - - - Fixed PH's badly added libz and libbz2 support. - - Fixed a problem with static linking. - - Added pcredemo. [But later removed - see 7 below.] - - Fixed dftables problem and added an option. - - Added a number of HAVE_XXX tests, including HAVE_WINDOWS_H and - HAVE_LONG_LONG. - - Added readline support for pcretest. - - Added an listing of the option settings after cmake has run. - -4. A user submitted a patch to Makefile that makes it easy to create - "pcre.dll" under mingw when using Configure/Make. I added stuff to - Makefile.am that cause it to include this special target, without - affecting anything else. Note that the same mingw target plus all - the other distribution libraries and programs are now supported - when configuring with CMake (see 6 below) instead of with - Configure/Make. - -5. Applied Craig's patch that moves no_arg into the RE class in the C++ code. - This is an attempt to solve the reported problem "pcrecpp::no_arg is not - exported in the Windows port". It has not yet been confirmed that the patch - solves the problem, but it does no harm. - -6. Applied Sheri's patch to CMakeLists.txt to add NON_STANDARD_LIB_PREFIX and - NON_STANDARD_LIB_SUFFIX for dll names built with mingw when configured - with CMake, and also correct the comment about stack recursion. - -7. Remove the automatic building of pcredemo from the ./configure system and - from CMakeLists.txt. The whole idea of pcredemo.c is that it is an example - of a program that users should build themselves after PCRE is installed, so - building it automatically is not really right. What is more, it gave - trouble in some build environments. - -8. Further tidies to CMakeLists.txt from Sheri and Christian. - - -Version 7.5 10-Jan-08 ---------------------- - -1. Applied a patch from Craig: "This patch makes it possible to 'ignore' - values in parens when parsing an RE using the C++ wrapper." - -2. Negative specials like \S did not work in character classes in UTF-8 mode. - Characters greater than 255 were excluded from the class instead of being - included. - -3. The same bug as (2) above applied to negated POSIX classes such as - [:^space:]. - -4. PCRECPP_STATIC was referenced in pcrecpp_internal.h, but nowhere was it - defined or documented. It seems to have been a typo for PCRE_STATIC, so - I have changed it. - -5. The construct (?&) was not diagnosed as a syntax error (it referenced the - first named subpattern) and a construct such as (?&a) would reference the - first named subpattern whose name started with "a" (in other words, the - length check was missing). Both these problems are fixed. "Subpattern name - expected" is now given for (?&) (a zero-length name), and this patch also - makes it give the same error for \k'' (previously it complained that that - was a reference to a non-existent subpattern). - -6. The erroneous patterns (?+-a) and (?-+a) give different error messages; - this is right because (?- can be followed by option settings as well as by - digits. I have, however, made the messages clearer. - -7. Patterns such as (?(1)a|b) (a pattern that contains fewer subpatterns - than the number used in the conditional) now cause a compile-time error. - This is actually not compatible with Perl, which accepts such patterns, but - treats the conditional as always being FALSE (as PCRE used to), but it - seems to me that giving a diagnostic is better. - -8. Change "alphameric" to the more common word "alphanumeric" in comments - and messages. - -9. Fix two occurrences of "backslash" in comments that should have been - "backspace". - -10. Remove two redundant lines of code that can never be obeyed (their function - was moved elsewhere). - -11. The program that makes PCRE's Unicode character property table had a bug - which caused it to generate incorrect table entries for sequences of - characters that have the same character type, but are in different scripts. - It amalgamated them into a single range, with the script of the first of - them. In other words, some characters were in the wrong script. There were - thirteen such cases, affecting characters in the following ranges: - - U+002b0 - U+002c1 - U+0060c - U+0060d - U+0061e - U+00612 - U+0064b - U+0065e - U+0074d - U+0076d - U+01800 - U+01805 - U+01d00 - U+01d77 - U+01d9b - U+01dbf - U+0200b - U+0200f - U+030fc - U+030fe - U+03260 - U+0327f - U+0fb46 - U+0fbb1 - U+10450 - U+1049d - -12. The -o option (show only the matching part of a line) for pcregrep was not - compatible with GNU grep in that, if there was more than one match in a - line, it showed only the first of them. It now behaves in the same way as - GNU grep. - -13. If the -o and -v options were combined for pcregrep, it printed a blank - line for every non-matching line. GNU grep prints nothing, and pcregrep now - does the same. The return code can be used to tell if there were any - non-matching lines. - -14. Added --file-offsets and --line-offsets to pcregrep. - -15. The pattern (?=something)(?R) was not being diagnosed as a potentially - infinitely looping recursion. The bug was that positive lookaheads were not - being skipped when checking for a possible empty match (negative lookaheads - and both kinds of lookbehind were skipped). - -16. Fixed two typos in the Windows-only code in pcregrep.c, and moved the - inclusion of <windows.h> to before rather than after the definition of - INVALID_FILE_ATTRIBUTES (patch from David Byron). - -17. Specifying a possessive quantifier with a specific limit for a Unicode - character property caused pcre_compile() to compile bad code, which led at - runtime to PCRE_ERROR_INTERNAL (-14). Examples of patterns that caused this - are: /\p{Zl}{2,3}+/8 and /\p{Cc}{2}+/8. It was the possessive "+" that - caused the error; without that there was no problem. - -18. Added --enable-pcregrep-libz and --enable-pcregrep-libbz2. - -19. Added --enable-pcretest-libreadline. - -20. In pcrecpp.cc, the variable 'count' was incremented twice in - RE::GlobalReplace(). As a result, the number of replacements returned was - double what it should be. I removed one of the increments, but Craig sent a - later patch that removed the other one (the right fix) and added unit tests - that check the return values (which was not done before). - -21. Several CMake things: - - (1) Arranged that, when cmake is used on Unix, the libraries end up with - the names libpcre and libpcreposix, not just pcre and pcreposix. - - (2) The above change means that pcretest and pcregrep are now correctly - linked with the newly-built libraries, not previously installed ones. - - (3) Added PCRE_SUPPORT_LIBREADLINE, PCRE_SUPPORT_LIBZ, PCRE_SUPPORT_LIBBZ2. - -22. In UTF-8 mode, with newline set to "any", a pattern such as .*a.*=.b.* - crashed when matching a string such as a\x{2029}b (note that \x{2029} is a - UTF-8 newline character). The key issue is that the pattern starts .*; - this means that the match must be either at the beginning, or after a - newline. The bug was in the code for advancing after a failed match and - checking that the new position followed a newline. It was not taking - account of UTF-8 characters correctly. - -23. PCRE was behaving differently from Perl in the way it recognized POSIX - character classes. PCRE was not treating the sequence [:...:] as a - character class unless the ... were all letters. Perl, however, seems to - allow any characters between [: and :], though of course it rejects as - unknown any "names" that contain non-letters, because all the known class - names consist only of letters. Thus, Perl gives an error for [[:1234:]], - for example, whereas PCRE did not - it did not recognize a POSIX character - class. This seemed a bit dangerous, so the code has been changed to be - closer to Perl. The behaviour is not identical to Perl, because PCRE will - diagnose an unknown class for, for example, [[:l\ower:]] where Perl will - treat it as [[:lower:]]. However, PCRE does now give "unknown" errors where - Perl does, and where it didn't before. - -24. Rewrite so as to remove the single use of %n from pcregrep because in some - Windows environments %n is disabled by default. - - -Version 7.4 21-Sep-07 ---------------------- - -1. Change 7.3/28 was implemented for classes by looking at the bitmap. This - means that a class such as [\s] counted as "explicit reference to CR or - LF". That isn't really right - the whole point of the change was to try to - help when there was an actual mention of one of the two characters. So now - the change happens only if \r or \n (or a literal CR or LF) character is - encountered. - -2. The 32-bit options word was also used for 6 internal flags, but the numbers - of both had grown to the point where there were only 3 bits left. - Fortunately, there was spare space in the data structure, and so I have - moved the internal flags into a new 16-bit field to free up more option - bits. - -3. The appearance of (?J) at the start of a pattern set the DUPNAMES option, - but did not set the internal JCHANGED flag - either of these is enough to - control the way the "get" function works - but the PCRE_INFO_JCHANGED - facility is supposed to tell if (?J) was ever used, so now (?J) at the - start sets both bits. - -4. Added options (at build time, compile time, exec time) to change \R from - matching any Unicode line ending sequence to just matching CR, LF, or CRLF. - -5. doc/pcresyntax.html was missing from the distribution. - -6. Put back the definition of PCRE_ERROR_NULLWSLIMIT, for backward - compatibility, even though it is no longer used. - -7. Added macro for snprintf to pcrecpp_unittest.cc and also for strtoll and - strtoull to pcrecpp.cc to select the available functions in WIN32 when the - windows.h file is present (where different names are used). [This was - reversed later after testing - see 16 below.] - -8. Changed all #include <config.h> to #include "config.h". There were also - some further <pcre.h> cases that I changed to "pcre.h". - -9. When pcregrep was used with the --colour option, it missed the line ending - sequence off the lines that it output. - -10. It was pointed out to me that arrays of string pointers cause lots of - relocations when a shared library is dynamically loaded. A technique of - using a single long string with a table of offsets can drastically reduce - these. I have refactored PCRE in four places to do this. The result is - dramatic: - - Originally: 290 - After changing UCP table: 187 - After changing error message table: 43 - After changing table of "verbs" 36 - After changing table of Posix names 22 - - Thanks to the folks working on Gregex for glib for this insight. - -11. --disable-stack-for-recursion caused compiling to fail unless -enable- - unicode-properties was also set. - -12. Updated the tests so that they work when \R is defaulted to ANYCRLF. - -13. Added checks for ANY and ANYCRLF to pcrecpp.cc where it previously - checked only for CRLF. - -14. Added casts to pcretest.c to avoid compiler warnings. - -15. Added Craig's patch to various pcrecpp modules to avoid compiler warnings. - -16. Added Craig's patch to remove the WINDOWS_H tests, that were not working, - and instead check for _strtoi64 explicitly, and avoid the use of snprintf() - entirely. This removes changes made in 7 above. - -17. The CMake files have been updated, and there is now more information about - building with CMake in the NON-UNIX-USE document. - - -Version 7.3 28-Aug-07 ---------------------- - - 1. In the rejigging of the build system that eventually resulted in 7.1, the - line "#include <pcre.h>" was included in pcre_internal.h. The use of angle - brackets there is not right, since it causes compilers to look for an - installed pcre.h, not the version that is in the source that is being - compiled (which of course may be different). I have changed it back to: - - #include "pcre.h" - - I have a vague recollection that the change was concerned with compiling in - different directories, but in the new build system, that is taken care of - by the VPATH setting the Makefile. - - 2. The pattern .*$ when run in not-DOTALL UTF-8 mode with newline=any failed - when the subject happened to end in the byte 0x85 (e.g. if the last - character was \x{1ec5}). *Character* 0x85 is one of the "any" newline - characters but of course it shouldn't be taken as a newline when it is part - of another character. The bug was that, for an unlimited repeat of . in - not-DOTALL UTF-8 mode, PCRE was advancing by bytes rather than by - characters when looking for a newline. - - 3. A small performance improvement in the DOTALL UTF-8 mode .* case. - - 4. Debugging: adjusted the names of opcodes for different kinds of parentheses - in debug output. - - 5. Arrange to use "%I64d" instead of "%lld" and "%I64u" instead of "%llu" for - long printing in the pcrecpp unittest when running under MinGW. - - 6. ESC_K was left out of the EBCDIC table. - - 7. Change 7.0/38 introduced a new limit on the number of nested non-capturing - parentheses; I made it 1000, which seemed large enough. Unfortunately, the - limit also applies to "virtual nesting" when a pattern is recursive, and in - this case 1000 isn't so big. I have been able to remove this limit at the - expense of backing off one optimization in certain circumstances. Normally, - when pcre_exec() would call its internal match() function recursively and - immediately return the result unconditionally, it uses a "tail recursion" - feature to save stack. However, when a subpattern that can match an empty - string has an unlimited repetition quantifier, it no longer makes this - optimization. That gives it a stack frame in which to save the data for - checking that an empty string has been matched. Previously this was taken - from the 1000-entry workspace that had been reserved. So now there is no - explicit limit, but more stack is used. - - 8. Applied Daniel's patches to solve problems with the import/export magic - syntax that is required for Windows, and which was going wrong for the - pcreposix and pcrecpp parts of the library. These were overlooked when this - problem was solved for the main library. - - 9. There were some crude static tests to avoid integer overflow when computing - the size of patterns that contain repeated groups with explicit upper - limits. As the maximum quantifier is 65535, the maximum group length was - set at 30,000 so that the product of these two numbers did not overflow a - 32-bit integer. However, it turns out that people want to use groups that - are longer than 30,000 bytes (though not repeat them that many times). - Change 7.0/17 (the refactoring of the way the pattern size is computed) has - made it possible to implement the integer overflow checks in a much more - dynamic way, which I have now done. The artificial limitation on group - length has been removed - we now have only the limit on the total length of - the compiled pattern, which depends on the LINK_SIZE setting. - -10. Fixed a bug in the documentation for get/copy named substring when - duplicate names are permitted. If none of the named substrings are set, the - functions return PCRE_ERROR_NOSUBSTRING (7); the doc said they returned an - empty string. - -11. Because Perl interprets \Q...\E at a high level, and ignores orphan \E - instances, patterns such as [\Q\E] or [\E] or even [^\E] cause an error, - because the ] is interpreted as the first data character and the - terminating ] is not found. PCRE has been made compatible with Perl in this - regard. Previously, it interpreted [\Q\E] as an empty class, and [\E] could - cause memory overwriting. - -10. Like Perl, PCRE automatically breaks an unlimited repeat after an empty - string has been matched (to stop an infinite loop). It was not recognizing - a conditional subpattern that could match an empty string if that - subpattern was within another subpattern. For example, it looped when - trying to match (((?(1)X|))*) but it was OK with ((?(1)X|)*) where the - condition was not nested. This bug has been fixed. - -12. A pattern like \X?\d or \P{L}?\d in non-UTF-8 mode could cause a backtrack - past the start of the subject in the presence of bytes with the top bit - set, for example "\x8aBCD". - -13. Added Perl 5.10 experimental backtracking controls (*FAIL), (*F), (*PRUNE), - (*SKIP), (*THEN), (*COMMIT), and (*ACCEPT). - -14. Optimized (?!) to (*FAIL). - -15. Updated the test for a valid UTF-8 string to conform to the later RFC 3629. - This restricts code points to be within the range 0 to 0x10FFFF, excluding - the "low surrogate" sequence 0xD800 to 0xDFFF. Previously, PCRE allowed the - full range 0 to 0x7FFFFFFF, as defined by RFC 2279. Internally, it still - does: it's just the validity check that is more restrictive. - -16. Inserted checks for integer overflows during escape sequence (backslash) - processing, and also fixed erroneous offset values for syntax errors during - backslash processing. - -17. Fixed another case of looking too far back in non-UTF-8 mode (cf 12 above) - for patterns like [\PPP\x8a]{1,}\x80 with the subject "A\x80". - -18. An unterminated class in a pattern like (?1)\c[ with a "forward reference" - caused an overrun. - -19. A pattern like (?:[\PPa*]*){8,} which had an "extended class" (one with - something other than just ASCII characters) inside a group that had an - unlimited repeat caused a loop at compile time (while checking to see - whether the group could match an empty string). - -20. Debugging a pattern containing \p or \P could cause a crash. For example, - [\P{Any}] did so. (Error in the code for printing property names.) - -21. An orphan \E inside a character class could cause a crash. - -22. A repeated capturing bracket such as (A)? could cause a wild memory - reference during compilation. - -23. There are several functions in pcre_compile() that scan along a compiled - expression for various reasons (e.g. to see if it's fixed length for look - behind). There were bugs in these functions when a repeated \p or \P was - present in the pattern. These operators have additional parameters compared - with \d, etc, and these were not being taken into account when moving along - the compiled data. Specifically: - - (a) A item such as \p{Yi}{3} in a lookbehind was not treated as fixed - length. - - (b) An item such as \pL+ within a repeated group could cause crashes or - loops. - - (c) A pattern such as \p{Yi}+(\P{Yi}+)(?1) could give an incorrect - "reference to non-existent subpattern" error. - - (d) A pattern like (\P{Yi}{2}\277)? could loop at compile time. - -24. A repeated \S or \W in UTF-8 mode could give wrong answers when multibyte - characters were involved (for example /\S{2}/8g with "A\x{a3}BC"). - -25. Using pcregrep in multiline, inverted mode (-Mv) caused it to loop. - -26. Patterns such as [\P{Yi}A] which include \p or \P and just one other - character were causing crashes (broken optimization). - -27. Patterns such as (\P{Yi}*\277)* (group with possible zero repeat containing - \p or \P) caused a compile-time loop. - -28. More problems have arisen in unanchored patterns when CRLF is a valid line - break. For example, the unstudied pattern [\r\n]A does not match the string - "\r\nA" because change 7.0/46 below moves the current point on by two - characters after failing to match at the start. However, the pattern \nA - *does* match, because it doesn't start till \n, and if [\r\n]A is studied, - the same is true. There doesn't seem any very clean way out of this, but - what I have chosen to do makes the common cases work: PCRE now takes note - of whether there can be an explicit match for \r or \n anywhere in the - pattern, and if so, 7.0/46 no longer applies. As part of this change, - there's a new PCRE_INFO_HASCRORLF option for finding out whether a compiled - pattern has explicit CR or LF references. - -29. Added (*CR) etc for changing newline setting at start of pattern. - - -Version 7.2 19-Jun-07 ---------------------- - - 1. If the fr_FR locale cannot be found for test 3, try the "french" locale, - which is apparently normally available under Windows. - - 2. Re-jig the pcregrep tests with different newline settings in an attempt - to make them independent of the local environment's newline setting. - - 3. Add code to configure.ac to remove -g from the CFLAGS default settings. - - 4. Some of the "internals" tests were previously cut out when the link size - was not 2, because the output contained actual offsets. The recent new - "Z" feature of pcretest means that these can be cut out, making the tests - usable with all link sizes. - - 5. Implemented Stan Switzer's goto replacement for longjmp() when not using - stack recursion. This gives a massive performance boost under BSD, but just - a small improvement under Linux. However, it saves one field in the frame - in all cases. - - 6. Added more features from the forthcoming Perl 5.10: - - (a) (?-n) (where n is a string of digits) is a relative subroutine or - recursion call. It refers to the nth most recently opened parentheses. - - (b) (?+n) is also a relative subroutine call; it refers to the nth next - to be opened parentheses. - - (c) Conditions that refer to capturing parentheses can be specified - relatively, for example, (?(-2)... or (?(+3)... - - (d) \K resets the start of the current match so that everything before - is not part of it. - - (e) \k{name} is synonymous with \k<name> and \k'name' (.NET compatible). - - (f) \g{name} is another synonym - part of Perl 5.10's unification of - reference syntax. - - (g) (?| introduces a group in which the numbering of parentheses in each - alternative starts with the same number. - - (h) \h, \H, \v, and \V match horizontal and vertical whitespace. - - 7. Added two new calls to pcre_fullinfo(): PCRE_INFO_OKPARTIAL and - PCRE_INFO_JCHANGED. - - 8. A pattern such as (.*(.)?)* caused pcre_exec() to fail by either not - terminating or by crashing. Diagnosed by Viktor Griph; it was in the code - for detecting groups that can match an empty string. - - 9. A pattern with a very large number of alternatives (more than several - hundred) was running out of internal workspace during the pre-compile - phase, where pcre_compile() figures out how much memory will be needed. A - bit of new cunning has reduced the workspace needed for groups with - alternatives. The 1000-alternative test pattern now uses 12 bytes of - workspace instead of running out of the 4096 that are available. - -10. Inserted some missing (unsigned int) casts to get rid of compiler warnings. - -11. Applied patch from Google to remove an optimization that didn't quite work. - The report of the bug said: - - pcrecpp::RE("a*").FullMatch("aaa") matches, while - pcrecpp::RE("a*?").FullMatch("aaa") does not, and - pcrecpp::RE("a*?\\z").FullMatch("aaa") does again. - -12. If \p or \P was used in non-UTF-8 mode on a character greater than 127 - it matched the wrong number of bytes. - - -Version 7.1 24-Apr-07 ---------------------- - - 1. Applied Bob Rossi and Daniel G's patches to convert the build system to one - that is more "standard", making use of automake and other Autotools. There - is some re-arrangement of the files and adjustment of comments consequent - on this. - - 2. Part of the patch fixed a problem with the pcregrep tests. The test of -r - for recursive directory scanning broke on some systems because the files - are not scanned in any specific order and on different systems the order - was different. A call to "sort" has been inserted into RunGrepTest for the - approprate test as a short-term fix. In the longer term there may be an - alternative. - - 3. I had an email from Eric Raymond about problems translating some of PCRE's - man pages to HTML (despite the fact that I distribute HTML pages, some - people do their own conversions for various reasons). The problems - concerned the use of low-level troff macros .br and .in. I have therefore - removed all such uses from the man pages (some were redundant, some could - be replaced by .nf/.fi pairs). The 132html script that I use to generate - HTML has been updated to handle .nf/.fi and to complain if it encounters - .br or .in. - - 4. Updated comments in configure.ac that get placed in config.h.in and also - arranged for config.h to be included in the distribution, with the name - config.h.generic, for the benefit of those who have to compile without - Autotools (compare pcre.h, which is now distributed as pcre.h.generic). - - 5. Updated the support (such as it is) for Virtual Pascal, thanks to Stefan - Weber: (1) pcre_internal.h was missing some function renames; (2) updated - makevp.bat for the current PCRE, using the additional files - makevp_c.txt, makevp_l.txt, and pcregexp.pas. - - 6. A Windows user reported a minor discrepancy with test 2, which turned out - to be caused by a trailing space on an input line that had got lost in his - copy. The trailing space was an accident, so I've just removed it. - - 7. Add -Wl,-R... flags in pcre-config.in for *BSD* systems, as I'm told - that is needed. - - 8. Mark ucp_table (in ucptable.h) and ucp_gentype (in pcre_ucp_searchfuncs.c) - as "const" (a) because they are and (b) because it helps the PHP - maintainers who have recently made a script to detect big data structures - in the php code that should be moved to the .rodata section. I remembered - to update Builducptable as well, so it won't revert if ucptable.h is ever - re-created. - - 9. Added some extra #ifdef SUPPORT_UTF8 conditionals into pcretest.c, - pcre_printint.src, pcre_compile.c, pcre_study.c, and pcre_tables.c, in - order to be able to cut out the UTF-8 tables in the latter when UTF-8 - support is not required. This saves 1.5-2K of code, which is important in - some applications. - - Later: more #ifdefs are needed in pcre_ord2utf8.c and pcre_valid_utf8.c - so as not to refer to the tables, even though these functions will never be - called when UTF-8 support is disabled. Otherwise there are problems with a - shared library. - -10. Fixed two bugs in the emulated memmove() function in pcre_internal.h: - - (a) It was defining its arguments as char * instead of void *. - - (b) It was assuming that all moves were upwards in memory; this was true - a long time ago when I wrote it, but is no longer the case. - - The emulated memove() is provided for those environments that have neither - memmove() nor bcopy(). I didn't think anyone used it these days, but that - is clearly not the case, as these two bugs were recently reported. - -11. The script PrepareRelease is now distributed: it calls 132html, CleanTxt, - and Detrail to create the HTML documentation, the .txt form of the man - pages, and it removes trailing spaces from listed files. It also creates - pcre.h.generic and config.h.generic from pcre.h and config.h. In the latter - case, it wraps all the #defines with #ifndefs. This script should be run - before "make dist". - -12. Fixed two fairly obscure bugs concerned with quantified caseless matching - with Unicode property support. - - (a) For a maximizing quantifier, if the two different cases of the - character were of different lengths in their UTF-8 codings (there are - some cases like this - I found 11), and the matching function had to - back up over a mixture of the two cases, it incorrectly assumed they - were both the same length. - - (b) When PCRE was configured to use the heap rather than the stack for - recursion during matching, it was not correctly preserving the data for - the other case of a UTF-8 character when checking ahead for a match - while processing a minimizing repeat. If the check also involved - matching a wide character, but failed, corruption could cause an - erroneous result when trying to check for a repeat of the original - character. - -13. Some tidying changes to the testing mechanism: - - (a) The RunTest script now detects the internal link size and whether there - is UTF-8 and UCP support by running ./pcretest -C instead of relying on - values substituted by "configure". (The RunGrepTest script already did - this for UTF-8.) The configure.ac script no longer substitutes the - relevant variables. - - (b) The debugging options /B and /D in pcretest show the compiled bytecode - with length and offset values. This means that the output is different - for different internal link sizes. Test 2 is skipped for link sizes - other than 2 because of this, bypassing the problem. Unfortunately, - there was also a test in test 3 (the locale tests) that used /B and - failed for link sizes other than 2. Rather than cut the whole test out, - I have added a new /Z option to pcretest that replaces the length and - offset values with spaces. This is now used to make test 3 independent - of link size. (Test 2 will be tidied up later.) - -14. If erroroffset was passed as NULL to pcre_compile, it provoked a - segmentation fault instead of returning the appropriate error message. - -15. In multiline mode when the newline sequence was set to "any", the pattern - ^$ would give a match between the \r and \n of a subject such as "A\r\nB". - This doesn't seem right; it now treats the CRLF combination as the line - ending, and so does not match in that case. It's only a pattern such as ^$ - that would hit this one: something like ^ABC$ would have failed after \r - and then tried again after \r\n. - -16. Changed the comparison command for RunGrepTest from "diff -u" to "diff -ub" - in an attempt to make files that differ only in their line terminators - compare equal. This works on Linux. - -17. Under certain error circumstances pcregrep might try to free random memory - as it exited. This is now fixed, thanks to valgrind. - -19. In pcretest, if the pattern /(?m)^$/g<any> was matched against the string - "abc\r\n\r\n", it found an unwanted second match after the second \r. This - was because its rules for how to advance for /g after matching an empty - string at the end of a line did not allow for this case. They now check for - it specially. - -20. pcretest is supposed to handle patterns and data of any length, by - extending its buffers when necessary. It was getting this wrong when the - buffer for a data line had to be extended. - -21. Added PCRE_NEWLINE_ANYCRLF which is like ANY, but matches only CR, LF, or - CRLF as a newline sequence. - -22. Code for handling Unicode properties in pcre_dfa_exec() wasn't being cut - out by #ifdef SUPPORT_UCP. This did no harm, as it could never be used, but - I have nevertheless tidied it up. - -23. Added some casts to kill warnings from HP-UX ia64 compiler. - -24. Added a man page for pcre-config. - - -Version 7.0 19-Dec-06 ---------------------- - - 1. Fixed a signed/unsigned compiler warning in pcre_compile.c, shown up by - moving to gcc 4.1.1. - - 2. The -S option for pcretest uses setrlimit(); I had omitted to #include - sys/time.h, which is documented as needed for this function. It doesn't - seem to matter on Linux, but it showed up on some releases of OS X. - - 3. It seems that there are systems where bytes whose values are greater than - 127 match isprint() in the "C" locale. The "C" locale should be the - default when a C program starts up. In most systems, only ASCII printing - characters match isprint(). This difference caused the output from pcretest - to vary, making some of the tests fail. I have changed pcretest so that: - - (a) When it is outputting text in the compiled version of a pattern, bytes - other than 32-126 are always shown as hex escapes. - - (b) When it is outputting text that is a matched part of a subject string, - it does the same, unless a different locale has been set for the match - (using the /L modifier). In this case, it uses isprint() to decide. - - 4. Fixed a major bug that caused incorrect computation of the amount of memory - required for a compiled pattern when options that changed within the - pattern affected the logic of the preliminary scan that determines the - length. The relevant options are -x, and -i in UTF-8 mode. The result was - that the computed length was too small. The symptoms of this bug were - either the PCRE error "internal error: code overflow" from pcre_compile(), - or a glibc crash with a message such as "pcretest: free(): invalid next - size (fast)". Examples of patterns that provoked this bug (shown in - pcretest format) are: - - /(?-x: )/x - /(?x)(?-x: \s*#\s*)/ - /((?i)[\x{c0}])/8 - /(?i:[\x{c0}])/8 - - HOWEVER: Change 17 below makes this fix obsolete as the memory computation - is now done differently. - - 5. Applied patches from Google to: (a) add a QuoteMeta function to the C++ - wrapper classes; (b) implement a new function in the C++ scanner that is - more efficient than the old way of doing things because it avoids levels of - recursion in the regex matching; (c) add a paragraph to the documentation - for the FullMatch() function. - - 6. The escape sequence \n was being treated as whatever was defined as - "newline". Not only was this contrary to the documentation, which states - that \n is character 10 (hex 0A), but it also went horribly wrong when - "newline" was defined as CRLF. This has been fixed. - - 7. In pcre_dfa_exec.c the value of an unsigned integer (the variable called c) - was being set to -1 for the "end of line" case (supposedly a value that no - character can have). Though this value is never used (the check for end of - line is "zero bytes in current character"), it caused compiler complaints. - I've changed it to 0xffffffff. - - 8. In pcre_version.c, the version string was being built by a sequence of - C macros that, in the event of PCRE_PRERELEASE being defined as an empty - string (as it is for production releases) called a macro with an empty - argument. The C standard says the result of this is undefined. The gcc - compiler treats it as an empty string (which was what was wanted) but it is - reported that Visual C gives an error. The source has been hacked around to - avoid this problem. - - 9. On the advice of a Windows user, included <io.h> and <fcntl.h> in Windows - builds of pcretest, and changed the call to _setmode() to use _O_BINARY - instead of 0x8000. Made all the #ifdefs test both _WIN32 and WIN32 (not all - of them did). - -10. Originally, pcretest opened its input and output without "b"; then I was - told that "b" was needed in some environments, so it was added for release - 5.0 to both the input and output. (It makes no difference on Unix-like - systems.) Later I was told that it is wrong for the input on Windows. I've - now abstracted the modes into two macros, to make it easier to fiddle with - them, and removed "b" from the input mode under Windows. - -11. Added pkgconfig support for the C++ wrapper library, libpcrecpp. - -12. Added -help and --help to pcretest as an official way of being reminded - of the options. - -13. Removed some redundant semicolons after macro calls in pcrecpparg.h.in - and pcrecpp.cc because they annoy compilers at high warning levels. - -14. A bit of tidying/refactoring in pcre_exec.c in the main bumpalong loop. - -15. Fixed an occurrence of == in configure.ac that should have been = (shell - scripts are not C programs :-) and which was not noticed because it works - on Linux. - -16. pcretest is supposed to handle any length of pattern and data line (as one - line or as a continued sequence of lines) by extending its input buffer if - necessary. This feature was broken for very long pattern lines, leading to - a string of junk being passed to pcre_compile() if the pattern was longer - than about 50K. - -17. I have done a major re-factoring of the way pcre_compile() computes the - amount of memory needed for a compiled pattern. Previously, there was code - that made a preliminary scan of the pattern in order to do this. That was - OK when PCRE was new, but as the facilities have expanded, it has become - harder and harder to keep it in step with the real compile phase, and there - have been a number of bugs (see for example, 4 above). I have now found a - cunning way of running the real compile function in a "fake" mode that - enables it to compute how much memory it would need, while actually only - ever using a few hundred bytes of working memory and without too many - tests of the mode. This should make future maintenance and development - easier. A side effect of this work is that the limit of 200 on the nesting - depth of parentheses has been removed (though this was never a serious - limitation, I suspect). However, there is a downside: pcre_compile() now - runs more slowly than before (30% or more, depending on the pattern). I - hope this isn't a big issue. There is no effect on runtime performance. - -18. Fixed a minor bug in pcretest: if a pattern line was not terminated by a - newline (only possible for the last line of a file) and it was a - pattern that set a locale (followed by /Lsomething), pcretest crashed. - -19. Added additional timing features to pcretest. (1) The -tm option now times - matching only, not compiling. (2) Both -t and -tm can be followed, as a - separate command line item, by a number that specifies the number of - repeats to use when timing. The default is 50000; this gives better - precision, but takes uncomfortably long for very large patterns. - -20. Extended pcre_study() to be more clever in cases where a branch of a - subpattern has no definite first character. For example, (a*|b*)[cd] would - previously give no result from pcre_study(). Now it recognizes that the - first character must be a, b, c, or d. - -21. There was an incorrect error "recursive call could loop indefinitely" if - a subpattern (or the entire pattern) that was being tested for matching an - empty string contained only one non-empty item after a nested subpattern. - For example, the pattern (?>\x{100}*)\d(?R) provoked this error - incorrectly, because the \d was being skipped in the check. - -22. The pcretest program now has a new pattern option /B and a command line - option -b, which is equivalent to adding /B to every pattern. This causes - it to show the compiled bytecode, without the additional information that - -d shows. The effect of -d is now the same as -b with -i (and similarly, /D - is the same as /B/I). - -23. A new optimization is now able automatically to treat some sequences such - as a*b as a*+b. More specifically, if something simple (such as a character - or a simple class like \d) has an unlimited quantifier, and is followed by - something that cannot possibly match the quantified thing, the quantifier - is automatically "possessified". - -24. A recursive reference to a subpattern whose number was greater than 39 - went wrong under certain circumstances in UTF-8 mode. This bug could also - have affected the operation of pcre_study(). - -25. Realized that a little bit of performance could be had by replacing - (c & 0xc0) == 0xc0 with c >= 0xc0 when processing UTF-8 characters. - -26. Timing data from pcretest is now shown to 4 decimal places instead of 3. - -27. Possessive quantifiers such as a++ were previously implemented by turning - them into atomic groups such as ($>a+). Now they have their own opcodes, - which improves performance. This includes the automatically created ones - from 23 above. - -28. A pattern such as (?=(\w+))\1: which simulates an atomic group using a - lookahead was broken if it was not anchored. PCRE was mistakenly expecting - the first matched character to be a colon. This applied both to named and - numbered groups. - -29. The ucpinternal.h header file was missing its idempotency #ifdef. - -30. I was sent a "project" file called libpcre.a.dev which I understand makes - building PCRE on Windows easier, so I have included it in the distribution. - -31. There is now a check in pcretest against a ridiculously large number being - returned by pcre_exec() or pcre_dfa_exec(). If this happens in a /g or /G - loop, the loop is abandoned. - -32. Forward references to subpatterns in conditions such as (?(2)...) where - subpattern 2 is defined later cause pcre_compile() to search forwards in - the pattern for the relevant set of parentheses. This search went wrong - when there were unescaped parentheses in a character class, parentheses - escaped with \Q...\E, or parentheses in a #-comment in /x mode. - -33. "Subroutine" calls and backreferences were previously restricted to - referencing subpatterns earlier in the regex. This restriction has now - been removed. - -34. Added a number of extra features that are going to be in Perl 5.10. On the - whole, these are just syntactic alternatives for features that PCRE had - previously implemented using the Python syntax or my own invention. The - other formats are all retained for compatibility. - - (a) Named groups can now be defined as (?<name>...) or (?'name'...) as well - as (?P<name>...). The new forms, as well as being in Perl 5.10, are - also .NET compatible. - - (b) A recursion or subroutine call to a named group can now be defined as - (?&name) as well as (?P>name). - - (c) A backreference to a named group can now be defined as \k<name> or - \k'name' as well as (?P=name). The new forms, as well as being in Perl - 5.10, are also .NET compatible. - - (d) A conditional reference to a named group can now use the syntax - (?(<name>) or (?('name') as well as (?(name). - - (e) A "conditional group" of the form (?(DEFINE)...) can be used to define - groups (named and numbered) that are never evaluated inline, but can be - called as "subroutines" from elsewhere. In effect, the DEFINE condition - is always false. There may be only one alternative in such a group. - - (f) A test for recursion can be given as (?(R1).. or (?(R&name)... as well - as the simple (?(R). The condition is true only if the most recent - recursion is that of the given number or name. It does not search out - through the entire recursion stack. - - (g) The escape \gN or \g{N} has been added, where N is a positive or - negative number, specifying an absolute or relative reference. - -35. Tidied to get rid of some further signed/unsigned compiler warnings and - some "unreachable code" warnings. - -36. Updated the Unicode property tables to Unicode version 5.0.0. Amongst other - things, this adds five new scripts. - -37. Perl ignores orphaned \E escapes completely. PCRE now does the same. - There were also incompatibilities regarding the handling of \Q..\E inside - character classes, for example with patterns like [\Qa\E-\Qz\E] where the - hyphen was adjacent to \Q or \E. I hope I've cleared all this up now. - -38. Like Perl, PCRE detects when an indefinitely repeated parenthesized group - matches an empty string, and forcibly breaks the loop. There were bugs in - this code in non-simple cases. For a pattern such as ^(a()*)* matched - against aaaa the result was just "a" rather than "aaaa", for example. Two - separate and independent bugs (that affected different cases) have been - fixed. - -39. Refactored the code to abolish the use of different opcodes for small - capturing bracket numbers. This is a tidy that I avoided doing when I - removed the limit on the number of capturing brackets for 3.5 back in 2001. - The new approach is not only tidier, it makes it possible to reduce the - memory needed to fix the previous bug (38). - -40. Implemented PCRE_NEWLINE_ANY to recognize any of the Unicode newline - sequences (http://unicode.org/unicode/reports/tr18/) as "newline" when - processing dot, circumflex, or dollar metacharacters, or #-comments in /x - mode. - -41. Add \R to match any Unicode newline sequence, as suggested in the Unicode - report. - -42. Applied patch, originally from Ari Pollak, modified by Google, to allow - copy construction and assignment in the C++ wrapper. - -43. Updated pcregrep to support "--newline=any". In the process, I fixed a - couple of bugs that could have given wrong results in the "--newline=crlf" - case. - -44. Added a number of casts and did some reorganization of signed/unsigned int - variables following suggestions from Dair Grant. Also renamed the variable - "this" as "item" because it is a C++ keyword. - -45. Arranged for dftables to add - - #include "pcre_internal.h" - - to pcre_chartables.c because without it, gcc 4.x may remove the array - definition from the final binary if PCRE is built into a static library and - dead code stripping is activated. - -46. For an unanchored pattern, if a match attempt fails at the start of a - newline sequence, and the newline setting is CRLF or ANY, and the next two - characters are CRLF, advance by two characters instead of one. - - -Version 6.7 04-Jul-06 ---------------------- - - 1. In order to handle tests when input lines are enormously long, pcretest has - been re-factored so that it automatically extends its buffers when - necessary. The code is crude, but this _is_ just a test program. The - default size has been increased from 32K to 50K. - - 2. The code in pcre_study() was using the value of the re argument before - testing it for NULL. (Of course, in any sensible call of the function, it - won't be NULL.) - - 3. The memmove() emulation function in pcre_internal.h, which is used on - systems that lack both memmove() and bcopy() - that is, hardly ever - - was missing a "static" storage class specifier. - - 4. When UTF-8 mode was not set, PCRE looped when compiling certain patterns - containing an extended class (one that cannot be represented by a bitmap - because it contains high-valued characters or Unicode property items, e.g. - [\pZ]). Almost always one would set UTF-8 mode when processing such a - pattern, but PCRE should not loop if you do not (it no longer does). - [Detail: two cases were found: (a) a repeated subpattern containing an - extended class; (b) a recursive reference to a subpattern that followed a - previous extended class. It wasn't skipping over the extended class - correctly when UTF-8 mode was not set.] - - 5. A negated single-character class was not being recognized as fixed-length - in lookbehind assertions such as (?<=[^f]), leading to an incorrect - compile error "lookbehind assertion is not fixed length". - - 6. The RunPerlTest auxiliary script was showing an unexpected difference - between PCRE and Perl for UTF-8 tests. It turns out that it is hard to - write a Perl script that can interpret lines of an input file either as - byte characters or as UTF-8, which is what "perltest" was being required to - do for the non-UTF-8 and UTF-8 tests, respectively. Essentially what you - can't do is switch easily at run time between having the "use utf8;" pragma - or not. In the end, I fudged it by using the RunPerlTest script to insert - "use utf8;" explicitly for the UTF-8 tests. - - 7. In multiline (/m) mode, PCRE was matching ^ after a terminating newline at - the end of the subject string, contrary to the documentation and to what - Perl does. This was true of both matching functions. Now it matches only at - the start of the subject and immediately after *internal* newlines. - - 8. A call of pcre_fullinfo() from pcretest to get the option bits was passing - a pointer to an int instead of a pointer to an unsigned long int. This - caused problems on 64-bit systems. - - 9. Applied a patch from the folks at Google to pcrecpp.cc, to fix "another - instance of the 'standard' template library not being so standard". - -10. There was no check on the number of named subpatterns nor the maximum - length of a subpattern name. The product of these values is used to compute - the size of the memory block for a compiled pattern. By supplying a very - long subpattern name and a large number of named subpatterns, the size - computation could be caused to overflow. This is now prevented by limiting - the length of names to 32 characters, and the number of named subpatterns - to 10,000. - -11. Subpatterns that are repeated with specific counts have to be replicated in - the compiled pattern. The size of memory for this was computed from the - length of the subpattern and the repeat count. The latter is limited to - 65535, but there was no limit on the former, meaning that integer overflow - could in principle occur. The compiled length of a repeated subpattern is - now limited to 30,000 bytes in order to prevent this. - -12. Added the optional facility to have named substrings with the same name. - -13. Added the ability to use a named substring as a condition, using the - Python syntax: (?(name)yes|no). This overloads (?(R)... and names that - are numbers (not recommended). Forward references are permitted. - -14. Added forward references in named backreferences (if you see what I mean). - -15. In UTF-8 mode, with the PCRE_DOTALL option set, a quantified dot in the - pattern could run off the end of the subject. For example, the pattern - "(?s)(.{1,5})"8 did this with the subject "ab". - -16. If PCRE_DOTALL or PCRE_MULTILINE were set, pcre_dfa_exec() behaved as if - PCRE_CASELESS was set when matching characters that were quantified with ? - or *. - -17. A character class other than a single negated character that had a minimum - but no maximum quantifier - for example [ab]{6,} - was not handled - correctly by pce_dfa_exec(). It would match only one character. - -18. A valid (though odd) pattern that looked like a POSIX character - class but used an invalid character after [ (for example [[,abc,]]) caused - pcre_compile() to give the error "Failed: internal error: code overflow" or - in some cases to crash with a glibc free() error. This could even happen if - the pattern terminated after [[ but there just happened to be a sequence of - letters, a binary zero, and a closing ] in the memory that followed. - -19. Perl's treatment of octal escapes in the range \400 to \777 has changed - over the years. Originally (before any Unicode support), just the bottom 8 - bits were taken. Thus, for example, \500 really meant \100. Nowadays the - output from "man perlunicode" includes this: - - The regular expression compiler produces polymorphic opcodes. That - is, the pattern adapts to the data and automatically switches to - the Unicode character scheme when presented with Unicode data--or - instead uses a traditional byte scheme when presented with byte - data. - - Sadly, a wide octal escape does not cause a switch, and in a string with - no other multibyte characters, these octal escapes are treated as before. - Thus, in Perl, the pattern /\500/ actually matches \100 but the pattern - /\500|\x{1ff}/ matches \500 or \777 because the whole thing is treated as a - Unicode string. - - I have not perpetrated such confusion in PCRE. Up till now, it took just - the bottom 8 bits, as in old Perl. I have now made octal escapes with - values greater than \377 illegal in non-UTF-8 mode. In UTF-8 mode they - translate to the appropriate multibyte character. - -29. Applied some refactoring to reduce the number of warnings from Microsoft - and Borland compilers. This has included removing the fudge introduced - seven years ago for the OS/2 compiler (see 2.02/2 below) because it caused - a warning about an unused variable. - -21. PCRE has not included VT (character 0x0b) in the set of whitespace - characters since release 4.0, because Perl (from release 5.004) does not. - [Or at least, is documented not to: some releases seem to be in conflict - with the documentation.] However, when a pattern was studied with - pcre_study() and all its branches started with \s, PCRE still included VT - as a possible starting character. Of course, this did no harm; it just - caused an unnecessary match attempt. - -22. Removed a now-redundant internal flag bit that recorded the fact that case - dependency changed within the pattern. This was once needed for "required - byte" processing, but is no longer used. This recovers a now-scarce options - bit. Also moved the least significant internal flag bit to the most- - significant bit of the word, which was not previously used (hangover from - the days when it was an int rather than a uint) to free up another bit for - the future. - -23. Added support for CRLF line endings as well as CR and LF. As well as the - default being selectable at build time, it can now be changed at runtime - via the PCRE_NEWLINE_xxx flags. There are now options for pcregrep to - specify that it is scanning data with non-default line endings. - -24. Changed the definition of CXXLINK to make it agree with the definition of - LINK in the Makefile, by replacing LDFLAGS to CXXFLAGS. - -25. Applied Ian Taylor's patches to avoid using another stack frame for tail - recursions. This makes a big different to stack usage for some patterns. - -26. If a subpattern containing a named recursion or subroutine reference such - as (?P>B) was quantified, for example (xxx(?P>B)){3}, the calculation of - the space required for the compiled pattern went wrong and gave too small a - value. Depending on the environment, this could lead to "Failed: internal - error: code overflow at offset 49" or "glibc detected double free or - corruption" errors. - -27. Applied patches from Google (a) to support the new newline modes and (b) to - advance over multibyte UTF-8 characters in GlobalReplace. - -28. Change free() to pcre_free() in pcredemo.c. Apparently this makes a - difference for some implementation of PCRE in some Windows version. - -29. Added some extra testing facilities to pcretest: - - \q<number> in a data line sets the "match limit" value - \Q<number> in a data line sets the "match recursion limt" value - -S <number> sets the stack size, where <number> is in megabytes - - The -S option isn't available for Windows. - - -Version 6.6 06-Feb-06 ---------------------- - - 1. Change 16(a) for 6.5 broke things, because PCRE_DATA_SCOPE was not defined - in pcreposix.h. I have copied the definition from pcre.h. - - 2. Change 25 for 6.5 broke compilation in a build directory out-of-tree - because pcre.h is no longer a built file. - - 3. Added Jeff Friedl's additional debugging patches to pcregrep. These are - not normally included in the compiled code. - - -Version 6.5 01-Feb-06 ---------------------- - - 1. When using the partial match feature with pcre_dfa_exec(), it was not - anchoring the second and subsequent partial matches at the new starting - point. This could lead to incorrect results. For example, with the pattern - /1234/, partially matching against "123" and then "a4" gave a match. - - 2. Changes to pcregrep: - - (a) All non-match returns from pcre_exec() were being treated as failures - to match the line. Now, unless the error is PCRE_ERROR_NOMATCH, an - error message is output. Some extra information is given for the - PCRE_ERROR_MATCHLIMIT and PCRE_ERROR_RECURSIONLIMIT errors, which are - probably the only errors that are likely to be caused by users (by - specifying a regex that has nested indefinite repeats, for instance). - If there are more than 20 of these errors, pcregrep is abandoned. - - (b) A binary zero was treated as data while matching, but terminated the - output line if it was written out. This has been fixed: binary zeroes - are now no different to any other data bytes. - - (c) Whichever of the LC_ALL or LC_CTYPE environment variables is set is - used to set a locale for matching. The --locale=xxxx long option has - been added (no short equivalent) to specify a locale explicitly on the - pcregrep command, overriding the environment variables. - - (d) When -B was used with -n, some line numbers in the output were one less - than they should have been. - - (e) Added the -o (--only-matching) option. - - (f) If -A or -C was used with -c (count only), some lines of context were - accidentally printed for the final match. - - (g) Added the -H (--with-filename) option. - - (h) The combination of options -rh failed to suppress file names for files - that were found from directory arguments. - - (i) Added the -D (--devices) and -d (--directories) options. - - (j) Added the -F (--fixed-strings) option. - - (k) Allow "-" to be used as a file name for -f as well as for a data file. - - (l) Added the --colo(u)r option. - - (m) Added Jeffrey Friedl's -S testing option, but within #ifdefs so that it - is not present by default. - - 3. A nasty bug was discovered in the handling of recursive patterns, that is, - items such as (?R) or (?1), when the recursion could match a number of - alternatives. If it matched one of the alternatives, but subsequently, - outside the recursion, there was a failure, the code tried to back up into - the recursion. However, because of the way PCRE is implemented, this is not - possible, and the result was an incorrect result from the match. - - In order to prevent this happening, the specification of recursion has - been changed so that all such subpatterns are automatically treated as - atomic groups. Thus, for example, (?R) is treated as if it were (?>(?R)). - - 4. I had overlooked the fact that, in some locales, there are characters for - which isalpha() is true but neither isupper() nor islower() are true. In - the fr_FR locale, for instance, the \xAA and \xBA characters (ordmasculine - and ordfeminine) are like this. This affected the treatment of \w and \W - when they appeared in character classes, but not when they appeared outside - a character class. The bit map for "word" characters is now created - separately from the results of isalnum() instead of just taking it from the - upper, lower, and digit maps. (Plus the underscore character, of course.) - - 5. The above bug also affected the handling of POSIX character classes such as - [[:alpha:]] and [[:alnum:]]. These do not have their own bit maps in PCRE's - permanent tables. Instead, the bit maps for such a class were previously - created as the appropriate unions of the upper, lower, and digit bitmaps. - Now they are created by subtraction from the [[:word:]] class, which has - its own bitmap. - - 6. The [[:blank:]] character class matches horizontal, but not vertical space. - It is created by subtracting the vertical space characters (\x09, \x0a, - \x0b, \x0c) from the [[:space:]] bitmap. Previously, however, the - subtraction was done in the overall bitmap for a character class, meaning - that a class such as [\x0c[:blank:]] was incorrect because \x0c would not - be recognized. This bug has been fixed. - - 7. Patches from the folks at Google: - - (a) pcrecpp.cc: "to handle a corner case that may or may not happen in - real life, but is still worth protecting against". - - (b) pcrecpp.cc: "corrects a bug when negative radixes are used with - regular expressions". - - (c) pcre_scanner.cc: avoid use of std::count() because not all systems - have it. - - (d) Split off pcrecpparg.h from pcrecpp.h and had the former built by - "configure" and the latter not, in order to fix a problem somebody had - with compiling the Arg class on HP-UX. - - (e) Improve the error-handling of the C++ wrapper a little bit. - - (f) New tests for checking recursion limiting. - - 8. The pcre_memmove() function, which is used only if the environment does not - have a standard memmove() function (and is therefore rarely compiled), - contained two bugs: (a) use of int instead of size_t, and (b) it was not - returning a result (though PCRE never actually uses the result). - - 9. In the POSIX regexec() interface, if nmatch is specified as a ridiculously - large number - greater than INT_MAX/(3*sizeof(int)) - REG_ESPACE is - returned instead of calling malloc() with an overflowing number that would - most likely cause subsequent chaos. - -10. The debugging option of pcretest was not showing the NO_AUTO_CAPTURE flag. - -11. The POSIX flag REG_NOSUB is now supported. When a pattern that was compiled - with this option is matched, the nmatch and pmatch options of regexec() are - ignored. - -12. Added REG_UTF8 to the POSIX interface. This is not defined by POSIX, but is - provided in case anyone wants to the the POSIX interface with UTF-8 - strings. - -13. Added CXXLDFLAGS to the Makefile parameters to provide settings only on the - C++ linking (needed for some HP-UX environments). - -14. Avoid compiler warnings in get_ucpname() when compiled without UCP support - (unused parameter) and in the pcre_printint() function (omitted "default" - switch label when the default is to do nothing). - -15. Added some code to make it possible, when PCRE is compiled as a C++ - library, to replace subject pointers for pcre_exec() with a smart pointer - class, thus making it possible to process discontinuous strings. - -16. The two macros PCRE_EXPORT and PCRE_DATA_SCOPE are confusing, and perform - much the same function. They were added by different people who were trying - to make PCRE easy to compile on non-Unix systems. It has been suggested - that PCRE_EXPORT be abolished now that there is more automatic apparatus - for compiling on Windows systems. I have therefore replaced it with - PCRE_DATA_SCOPE. This is set automatically for Windows; if not set it - defaults to "extern" for C or "extern C" for C++, which works fine on - Unix-like systems. It is now possible to override the value of PCRE_DATA_ - SCOPE with something explicit in config.h. In addition: - - (a) pcreposix.h still had just "extern" instead of either of these macros; - I have replaced it with PCRE_DATA_SCOPE. - - (b) Functions such as _pcre_xclass(), which are internal to the library, - but external in the C sense, all had PCRE_EXPORT in their definitions. - This is apparently wrong for the Windows case, so I have removed it. - (It makes no difference on Unix-like systems.) - -17. Added a new limit, MATCH_LIMIT_RECURSION, which limits the depth of nesting - of recursive calls to match(). This is different to MATCH_LIMIT because - that limits the total number of calls to match(), not all of which increase - the depth of recursion. Limiting the recursion depth limits the amount of - stack (or heap if NO_RECURSE is set) that is used. The default can be set - when PCRE is compiled, and changed at run time. A patch from Google adds - this functionality to the C++ interface. - -18. Changes to the handling of Unicode character properties: - - (a) Updated the table to Unicode 4.1.0. - - (b) Recognize characters that are not in the table as "Cn" (undefined). - - (c) I revised the way the table is implemented to a much improved format - which includes recognition of ranges. It now supports the ranges that - are defined in UnicodeData.txt, and it also amalgamates other - characters into ranges. This has reduced the number of entries in the - table from around 16,000 to around 3,000, thus reducing its size - considerably. I realized I did not need to use a tree structure after - all - a binary chop search is just as efficient. Having reduced the - number of entries, I extended their size from 6 bytes to 8 bytes to - allow for more data. - - (d) Added support for Unicode script names via properties such as \p{Han}. - -19. In UTF-8 mode, a backslash followed by a non-Ascii character was not - matching that character. - -20. When matching a repeated Unicode property with a minimum greater than zero, - (for example \pL{2,}), PCRE could look past the end of the subject if it - reached it while seeking the minimum number of characters. This could - happen only if some of the characters were more than one byte long, because - there is a check for at least the minimum number of bytes. - -21. Refactored the implementation of \p and \P so as to be more general, to - allow for more different types of property in future. This has changed the - compiled form incompatibly. Anybody with saved compiled patterns that use - \p or \P will have to recompile them. - -22. Added "Any" and "L&" to the supported property types. - -23. Recognize \x{...} as a code point specifier, even when not in UTF-8 mode, - but give a compile time error if the value is greater than 0xff. - -24. The man pages for pcrepartial, pcreprecompile, and pcre_compile2 were - accidentally not being installed or uninstalled. - -25. The pcre.h file was built from pcre.h.in, but the only changes that were - made were to insert the current release number. This seemed silly, because - it made things harder for people building PCRE on systems that don't run - "configure". I have turned pcre.h into a distributed file, no longer built - by "configure", with the version identification directly included. There is - no longer a pcre.h.in file. - - However, this change necessitated a change to the pcre-config script as - well. It is built from pcre-config.in, and one of the substitutions was the - release number. I have updated configure.ac so that ./configure now finds - the release number by grepping pcre.h. - -26. Added the ability to run the tests under valgrind. - - -Version 6.4 05-Sep-05 ---------------------- - - 1. Change 6.0/10/(l) to pcregrep introduced a bug that caused separator lines - "--" to be printed when multiple files were scanned, even when none of the - -A, -B, or -C options were used. This is not compatible with Gnu grep, so I - consider it to be a bug, and have restored the previous behaviour. - - 2. A couple of code tidies to get rid of compiler warnings. - - 3. The pcretest program used to cheat by referring to symbols in the library - whose names begin with _pcre_. These are internal symbols that are not - really supposed to be visible externally, and in some environments it is - possible to suppress them. The cheating is now confined to including - certain files from the library's source, which is a bit cleaner. - - 4. Renamed pcre.in as pcre.h.in to go with pcrecpp.h.in; it also makes the - file's purpose clearer. - - 5. Reorganized pcre_ucp_findchar(). - - -Version 6.3 15-Aug-05 ---------------------- - - 1. The file libpcre.pc.in did not have general read permission in the tarball. - - 2. There were some problems when building without C++ support: - - (a) If C++ support was not built, "make install" and "make test" still - tried to test it. - - (b) There were problems when the value of CXX was explicitly set. Some - changes have been made to try to fix these, and ... - - (c) --disable-cpp can now be used to explicitly disable C++ support. - - (d) The use of @CPP_OBJ@ directly caused a blank line preceded by a - backslash in a target when C++ was disabled. This confuses some - versions of "make", apparently. Using an intermediate variable solves - this. (Same for CPP_LOBJ.) - - 3. $(LINK_FOR_BUILD) now includes $(CFLAGS_FOR_BUILD) and $(LINK) - (non-Windows) now includes $(CFLAGS) because these flags are sometimes - necessary on certain architectures. - - 4. Added a setting of -export-symbols-regex to the link command to remove - those symbols that are exported in the C sense, but actually are local - within the library, and not documented. Their names all begin with - "_pcre_". This is not a perfect job, because (a) we have to except some - symbols that pcretest ("illegally") uses, and (b) the facility isn't always - available (and never for static libraries). I have made a note to try to - find a way round (a) in the future. - - -Version 6.2 01-Aug-05 ---------------------- - - 1. There was no test for integer overflow of quantifier values. A construction - such as {1111111111111111} would give undefined results. What is worse, if - a minimum quantifier for a parenthesized subpattern overflowed and became - negative, the calculation of the memory size went wrong. This could have - led to memory overwriting. - - 2. Building PCRE using VPATH was broken. Hopefully it is now fixed. - - 3. Added "b" to the 2nd argument of fopen() in dftables.c, for non-Unix-like - operating environments where this matters. - - 4. Applied Giuseppe Maxia's patch to add additional features for controlling - PCRE options from within the C++ wrapper. - - 5. Named capturing subpatterns were not being correctly counted when a pattern - was compiled. This caused two problems: (a) If there were more than 100 - such subpatterns, the calculation of the memory needed for the whole - compiled pattern went wrong, leading to an overflow error. (b) Numerical - back references of the form \12, where the number was greater than 9, were - not recognized as back references, even though there were sufficient - previous subpatterns. - - 6. Two minor patches to pcrecpp.cc in order to allow it to compile on older - versions of gcc, e.g. 2.95.4. - - -Version 6.1 21-Jun-05 ---------------------- - - 1. There was one reference to the variable "posix" in pcretest.c that was not - surrounded by "#if !defined NOPOSIX". - - 2. Make it possible to compile pcretest without DFA support, UTF8 support, or - the cross-check on the old pcre_info() function, for the benefit of the - cut-down version of PCRE that is currently imported into Exim. - - 3. A (silly) pattern starting with (?i)(?-i) caused an internal space - allocation error. I've done the easy fix, which wastes 2 bytes for sensible - patterns that start (?i) but I don't think that matters. The use of (?i) is - just an example; this all applies to the other options as well. - - 4. Since libtool seems to echo the compile commands it is issuing, the output - from "make" can be reduced a bit by putting "@" in front of each libtool - compile command. - - 5. Patch from the folks at Google for configure.in to be a bit more thorough - in checking for a suitable C++ installation before trying to compile the - C++ stuff. This should fix a reported problem when a compiler was present, - but no suitable headers. - - 6. The man pages all had just "PCRE" as their title. I have changed them to - be the relevant file name. I have also arranged that these names are - retained in the file doc/pcre.txt, which is a concatenation in text format - of all the man pages except the little individual ones for each function. - - 7. The NON-UNIX-USE file had not been updated for the different set of source - files that come with release 6. I also added a few comments about the C++ - wrapper. - - -Version 6.0 07-Jun-05 ---------------------- - - 1. Some minor internal re-organization to help with my DFA experiments. - - 2. Some missing #ifdef SUPPORT_UCP conditionals in pcretest and printint that - didn't matter for the library itself when fully configured, but did matter - when compiling without UCP support, or within Exim, where the ucp files are - not imported. - - 3. Refactoring of the library code to split up the various functions into - different source modules. The addition of the new DFA matching code (see - below) to a single monolithic source would have made it really too - unwieldy, quite apart from causing all the code to be include in a - statically linked application, when only some functions are used. This is - relevant even without the DFA addition now that patterns can be compiled in - one application and matched in another. - - The downside of splitting up is that there have to be some external - functions and data tables that are used internally in different modules of - the library but which are not part of the API. These have all had their - names changed to start with "_pcre_" so that they are unlikely to clash - with other external names. - - 4. Added an alternate matching function, pcre_dfa_exec(), which matches using - a different (DFA) algorithm. Although it is slower than the original - function, it does have some advantages for certain types of matching - problem. - - 5. Upgrades to pcretest in order to test the features of pcre_dfa_exec(), - including restarting after a partial match. - - 6. A patch for pcregrep that defines INVALID_FILE_ATTRIBUTES if it is not - defined when compiling for Windows was sent to me. I have put it into the - code, though I have no means of testing or verifying it. - - 7. Added the pcre_refcount() auxiliary function. - - 8. Added the PCRE_FIRSTLINE option. This constrains an unanchored pattern to - match before or at the first newline in the subject string. In pcretest, - the /f option on a pattern can be used to set this. - - 9. A repeated \w when used in UTF-8 mode with characters greater than 256 - would behave wrongly. This has been present in PCRE since release 4.0. - -10. A number of changes to the pcregrep command: - - (a) Refactored how -x works; insert ^(...)$ instead of setting - PCRE_ANCHORED and checking the length, in preparation for adding - something similar for -w. - - (b) Added the -w (match as a word) option. - - (c) Refactored the way lines are read and buffered so as to have more - than one at a time available. - - (d) Implemented a pcregrep test script. - - (e) Added the -M (multiline match) option. This allows patterns to match - over several lines of the subject. The buffering ensures that at least - 8K, or the rest of the document (whichever is the shorter) is available - for matching (and similarly the previous 8K for lookbehind assertions). - - (f) Changed the --help output so that it now says - - -w, --word-regex(p) - - instead of two lines, one with "regex" and the other with "regexp" - because that confused at least one person since the short forms are the - same. (This required a bit of code, as the output is generated - automatically from a table. It wasn't just a text change.) - - (g) -- can be used to terminate pcregrep options if the next thing isn't an - option but starts with a hyphen. Could be a pattern or a path name - starting with a hyphen, for instance. - - (h) "-" can be given as a file name to represent stdin. - - (i) When file names are being printed, "(standard input)" is used for - the standard input, for compatibility with GNU grep. Previously - "<stdin>" was used. - - (j) The option --label=xxx can be used to supply a name to be used for - stdin when file names are being printed. There is no short form. - - (k) Re-factored the options decoding logic because we are going to add - two more options that take data. Such options can now be given in four - different ways, e.g. "-fname", "-f name", "--file=name", "--file name". - - (l) Added the -A, -B, and -C options for requesting that lines of context - around matches be printed. - - (m) Added the -L option to print the names of files that do not contain - any matching lines, that is, the complement of -l. - - (n) The return code is 2 if any file cannot be opened, but pcregrep does - continue to scan other files. - - (o) The -s option was incorrectly implemented. For compatibility with other - greps, it now suppresses the error message for a non-existent or non- - accessible file (but not the return code). There is a new option called - -q that suppresses the output of matching lines, which was what -s was - previously doing. - - (p) Added --include and --exclude options to specify files for inclusion - and exclusion when recursing. - -11. The Makefile was not using the Autoconf-supported LDFLAGS macro properly. - Hopefully, it now does. - -12. Missing cast in pcre_study(). - -13. Added an "uninstall" target to the makefile. - -14. Replaced "extern" in the function prototypes in Makefile.in with - "PCRE_DATA_SCOPE", which defaults to 'extern' or 'extern "C"' in the Unix - world, but is set differently for Windows. - -15. Added a second compiling function called pcre_compile2(). The only - difference is that it has an extra argument, which is a pointer to an - integer error code. When there is a compile-time failure, this is set - non-zero, in addition to the error test pointer being set to point to an - error message. The new argument may be NULL if no error number is required - (but then you may as well call pcre_compile(), which is now just a - wrapper). This facility is provided because some applications need a - numeric error indication, but it has also enabled me to tidy up the way - compile-time errors are handled in the POSIX wrapper. - -16. Added VPATH=.libs to the makefile; this should help when building with one - prefix path and installing with another. (Or so I'm told by someone who - knows more about this stuff than I do.) - -17. Added a new option, REG_DOTALL, to the POSIX function regcomp(). This - passes PCRE_DOTALL to the pcre_compile() function, making the "." character - match everything, including newlines. This is not POSIX-compatible, but - somebody wanted the feature. From pcretest it can be activated by using - both the P and the s flags. - -18. AC_PROG_LIBTOOL appeared twice in Makefile.in. Removed one. - -19. libpcre.pc was being incorrectly installed as executable. - -20. A couple of places in pcretest check for end-of-line by looking for '\n'; - it now also looks for '\r' so that it will work unmodified on Windows. - -21. Added Google's contributed C++ wrapper to the distribution. - -22. Added some untidy missing memory free() calls in pcretest, to keep - Electric Fence happy when testing. - - - -Version 5.0 13-Sep-04 ---------------------- - - 1. Internal change: literal characters are no longer packed up into items - containing multiple characters in a single byte-string. Each character - is now matched using a separate opcode. However, there may be more than one - byte in the character in UTF-8 mode. - - 2. The pcre_callout_block structure has two new fields: pattern_position and - next_item_length. These contain the offset in the pattern to the next match - item, and its length, respectively. - - 3. The PCRE_AUTO_CALLOUT option for pcre_compile() requests the automatic - insertion of callouts before each pattern item. Added the /C option to - pcretest to make use of this. - - 4. On the advice of a Windows user, the lines - - #if defined(_WIN32) || defined(WIN32) - _setmode( _fileno( stdout ), 0x8000 ); - #endif /* defined(_WIN32) || defined(WIN32) */ - - have been added to the source of pcretest. This apparently does useful - magic in relation to line terminators. - - 5. Changed "r" and "w" in the calls to fopen() in pcretest to "rb" and "wb" - for the benefit of those environments where the "b" makes a difference. - - 6. The icc compiler has the same options as gcc, but "configure" doesn't seem - to know about it. I have put a hack into configure.in that adds in code - to set GCC=yes if CC=icc. This seems to end up at a point in the - generated configure script that is early enough to affect the setting of - compiler options, which is what is needed, but I have no means of testing - whether it really works. (The user who reported this had patched the - generated configure script, which of course I cannot do.) - - LATER: After change 22 below (new libtool files), the configure script - seems to know about icc (and also ecc). Therefore, I have commented out - this hack in configure.in. - - 7. Added support for pkg-config (2 patches were sent in). - - 8. Negated POSIX character classes that used a combination of internal tables - were completely broken. These were [[:^alpha:]], [[:^alnum:]], and - [[:^ascii]]. Typically, they would match almost any characters. The other - POSIX classes were not broken in this way. - - 9. Matching the pattern "\b.*?" against "ab cd", starting at offset 1, failed - to find the match, as PCRE was deluded into thinking that the match had to - start at the start point or following a newline. The same bug applied to - patterns with negative forward assertions or any backward assertions - preceding ".*" at the start, unless the pattern required a fixed first - character. This was a failing pattern: "(?!.bcd).*". The bug is now fixed. - -10. In UTF-8 mode, when moving forwards in the subject after a failed match - starting at the last subject character, bytes beyond the end of the subject - string were read. - -11. Renamed the variable "class" as "classbits" to make life easier for C++ - users. (Previously there was a macro definition, but it apparently wasn't - enough.) - -12. Added the new field "tables" to the extra data so that tables can be passed - in at exec time, or the internal tables can be re-selected. This allows - a compiled regex to be saved and re-used at a later time by a different - program that might have everything at different addresses. - -13. Modified the pcre-config script so that, when run on Solaris, it shows a - -R library as well as a -L library. - -14. The debugging options of pcretest (-d on the command line or D on a - pattern) showed incorrect output for anything following an extended class - that contained multibyte characters and which was followed by a quantifier. - -15. Added optional support for general category Unicode character properties - via the \p, \P, and \X escapes. Unicode property support implies UTF-8 - support. It adds about 90K to the size of the library. The meanings of the - inbuilt class escapes such as \d and \s have NOT been changed. - -16. Updated pcredemo.c to include calls to free() to release the memory for the - compiled pattern. - -17. The generated file chartables.c was being created in the source directory - instead of in the building directory. This caused the build to fail if the - source directory was different from the building directory, and was - read-only. - -18. Added some sample Win commands from Mark Tetrode into the NON-UNIX-USE - file. No doubt somebody will tell me if they don't make sense... Also added - Dan Mooney's comments about building on OpenVMS. - -19. Added support for partial matching via the PCRE_PARTIAL option for - pcre_exec() and the \P data escape in pcretest. - -20. Extended pcretest with 3 new pattern features: - - (i) A pattern option of the form ">rest-of-line" causes pcretest to - write the compiled pattern to the file whose name is "rest-of-line". - This is a straight binary dump of the data, with the saved pointer to - the character tables forced to be NULL. The study data, if any, is - written too. After writing, pcretest reads a new pattern. - - (ii) If, instead of a pattern, "<rest-of-line" is given, pcretest reads a - compiled pattern from the given file. There must not be any - occurrences of "<" in the file name (pretty unlikely); if there are, - pcretest will instead treat the initial "<" as a pattern delimiter. - After reading in the pattern, pcretest goes on to read data lines as - usual. - - (iii) The F pattern option causes pcretest to flip the bytes in the 32-bit - and 16-bit fields in a compiled pattern, to simulate a pattern that - was compiled on a host of opposite endianness. - -21. The pcre-exec() function can now cope with patterns that were compiled on - hosts of opposite endianness, with this restriction: - - As for any compiled expression that is saved and used later, the tables - pointer field cannot be preserved; the extra_data field in the arguments - to pcre_exec() should be used to pass in a tables address if a value - other than the default internal tables were used at compile time. - -22. Calling pcre_exec() with a negative value of the "ovecsize" parameter is - now diagnosed as an error. Previously, most of the time, a negative number - would have been treated as zero, but if in addition "ovector" was passed as - NULL, a crash could occur. - -23. Updated the files ltmain.sh, config.sub, config.guess, and aclocal.m4 with - new versions from the libtool 1.5 distribution (the last one is a copy of - a file called libtool.m4). This seems to have fixed the need to patch - "configure" to support Darwin 1.3 (which I used to do). However, I still - had to patch ltmain.sh to ensure that ${SED} is set (it isn't on my - workstation). - -24. Changed the PCRE licence to be the more standard "BSD" licence. - - -Version 4.5 01-Dec-03 ---------------------- - - 1. There has been some re-arrangement of the code for the match() function so - that it can be compiled in a version that does not call itself recursively. - Instead, it keeps those local variables that need separate instances for - each "recursion" in a frame on the heap, and gets/frees frames whenever it - needs to "recurse". Keeping track of where control must go is done by means - of setjmp/longjmp. The whole thing is implemented by a set of macros that - hide most of the details from the main code, and operates only if - NO_RECURSE is defined while compiling pcre.c. If PCRE is built using the - "configure" mechanism, "--disable-stack-for-recursion" turns on this way of - operating. - - To make it easier for callers to provide specially tailored get/free - functions for this usage, two new functions, pcre_stack_malloc, and - pcre_stack_free, are used. They are always called in strict stacking order, - and the size of block requested is always the same. - - The PCRE_CONFIG_STACKRECURSE info parameter can be used to find out whether - PCRE has been compiled to use the stack or the heap for recursion. The - -C option of pcretest uses this to show which version is compiled. - - A new data escape \S, is added to pcretest; it causes the amounts of store - obtained and freed by both kinds of malloc/free at match time to be added - to the output. - - 2. Changed the locale test to use "fr_FR" instead of "fr" because that's - what's available on my current Linux desktop machine. - - 3. When matching a UTF-8 string, the test for a valid string at the start has - been extended. If start_offset is not zero, PCRE now checks that it points - to a byte that is the start of a UTF-8 character. If not, it returns - PCRE_ERROR_BADUTF8_OFFSET (-11). Note: the whole string is still checked; - this is necessary because there may be backward assertions in the pattern. - When matching the same subject several times, it may save resources to use - PCRE_NO_UTF8_CHECK on all but the first call if the string is long. - - 4. The code for checking the validity of UTF-8 strings has been tightened so - that it rejects (a) strings containing 0xfe or 0xff bytes and (b) strings - containing "overlong sequences". - - 5. Fixed a bug (appearing twice) that I could not find any way of exploiting! - I had written "if ((digitab[*p++] && chtab_digit) == 0)" where the "&&" - should have been "&", but it just so happened that all the cases this let - through by mistake were picked up later in the function. - - 6. I had used a variable called "isblank" - this is a C99 function, causing - some compilers to warn. To avoid this, I renamed it (as "blankclass"). - - 7. Cosmetic: (a) only output another newline at the end of pcretest if it is - prompting; (b) run "./pcretest /dev/null" at the start of the test script - so the version is shown; (c) stop "make test" echoing "./RunTest". - - 8. Added patches from David Burgess to enable PCRE to run on EBCDIC systems. - - 9. The prototype for memmove() for systems that don't have it was using - size_t, but the inclusion of the header that defines size_t was later. I've - moved the #includes for the C headers earlier to avoid this. - -10. Added some adjustments to the code to make it easier to compiler on certain - special systems: - - (a) Some "const" qualifiers were missing. - (b) Added the macro EXPORT before all exported functions; by default this - is defined to be empty. - (c) Changed the dftables auxiliary program (that builds chartables.c) so - that it reads its output file name as an argument instead of writing - to the standard output and assuming this can be redirected. - -11. In UTF-8 mode, if a recursive reference (e.g. (?1)) followed a character - class containing characters with values greater than 255, PCRE compilation - went into a loop. - -12. A recursive reference to a subpattern that was within another subpattern - that had a minimum quantifier of zero caused PCRE to crash. For example, - (x(y(?2))z)? provoked this bug with a subject that got as far as the - recursion. If the recursively-called subpattern itself had a zero repeat, - that was OK. - -13. In pcretest, the buffer for reading a data line was set at 30K, but the - buffer into which it was copied (for escape processing) was still set at - 1024, so long lines caused crashes. - -14. A pattern such as /[ab]{1,3}+/ failed to compile, giving the error - "internal error: code overflow...". This applied to any character class - that was followed by a possessive quantifier. - -15. Modified the Makefile to add libpcre.la as a prerequisite for - libpcreposix.la because I was told this is needed for a parallel build to - work. - -16. If a pattern that contained .* following optional items at the start was - studied, the wrong optimizing data was generated, leading to matching - errors. For example, studying /[ab]*.*c/ concluded, erroneously, that any - matching string must start with a or b or c. The correct conclusion for - this pattern is that a match can start with any character. - - -Version 4.4 13-Aug-03 ---------------------- - - 1. In UTF-8 mode, a character class containing characters with values between - 127 and 255 was not handled correctly if the compiled pattern was studied. - In fixing this, I have also improved the studying algorithm for such - classes (slightly). - - 2. Three internal functions had redundant arguments passed to them. Removal - might give a very teeny performance improvement. - - 3. Documentation bug: the value of the capture_top field in a callout is *one - more than* the number of the hightest numbered captured substring. - - 4. The Makefile linked pcretest and pcregrep with -lpcre, which could result - in incorrectly linking with a previously installed version. They now link - explicitly with libpcre.la. - - 5. configure.in no longer needs to recognize Cygwin specially. - - 6. A problem in pcre.in for Windows platforms is fixed. - - 7. If a pattern was successfully studied, and the -d (or /D) flag was given to - pcretest, it used to include the size of the study block as part of its - output. Unfortunately, the structure contains a field that has a different - size on different hardware architectures. This meant that the tests that - showed this size failed. As the block is currently always of a fixed size, - this information isn't actually particularly useful in pcretest output, so - I have just removed it. - - 8. Three pre-processor statements accidentally did not start in column 1. - Sadly, there are *still* compilers around that complain, even though - standard C has not required this for well over a decade. Sigh. - - 9. In pcretest, the code for checking callouts passed small integers in the - callout_data field, which is a void * field. However, some picky compilers - complained about the casts involved for this on 64-bit systems. Now - pcretest passes the address of the small integer instead, which should get - rid of the warnings. - -10. By default, when in UTF-8 mode, PCRE now checks for valid UTF-8 strings at - both compile and run time, and gives an error if an invalid UTF-8 sequence - is found. There is a option for disabling this check in cases where the - string is known to be correct and/or the maximum performance is wanted. - -11. In response to a bug report, I changed one line in Makefile.in from - - -Wl,--out-implib,.libs/lib@WIN_PREFIX@pcreposix.dll.a \ - to - -Wl,--out-implib,.libs/@WIN_PREFIX@libpcreposix.dll.a \ - - to look similar to other lines, but I have no way of telling whether this - is the right thing to do, as I do not use Windows. No doubt I'll get told - if it's wrong... - - -Version 4.3 21-May-03 ---------------------- - -1. Two instances of @WIN_PREFIX@ omitted from the Windows targets in the - Makefile. - -2. Some refactoring to improve the quality of the code: - - (i) The utf8_table... variables are now declared "const". - - (ii) The code for \cx, which used the "case flipping" table to upper case - lower case letters, now just substracts 32. This is ASCII-specific, - but the whole concept of \cx is ASCII-specific, so it seems - reasonable. - - (iii) PCRE was using its character types table to recognize decimal and - hexadecimal digits in the pattern. This is silly, because it handles - only 0-9, a-f, and A-F, but the character types table is locale- - specific, which means strange things might happen. A private - table is now used for this - though it costs 256 bytes, a table is - much faster than multiple explicit tests. Of course, the standard - character types table is still used for matching digits in subject - strings against \d. - - (iv) Strictly, the identifier ESC_t is reserved by POSIX (all identifiers - ending in _t are). So I've renamed it as ESC_tee. - -3. The first argument for regexec() in the POSIX wrapper should have been - defined as "const". - -4. Changed pcretest to use malloc() for its buffers so that they can be - Electric Fenced for debugging. - -5. There were several places in the code where, in UTF-8 mode, PCRE would try - to read one or more bytes before the start of the subject string. Often this - had no effect on PCRE's behaviour, but in some circumstances it could - provoke a segmentation fault. - -6. A lookbehind at the start of a pattern in UTF-8 mode could also cause PCRE - to try to read one or more bytes before the start of the subject string. - -7. A lookbehind in a pattern matched in non-UTF-8 mode on a PCRE compiled with - UTF-8 support could misbehave in various ways if the subject string - contained bytes with the 0x80 bit set and the 0x40 bit unset in a lookbehind - area. (PCRE was not checking for the UTF-8 mode flag, and trying to move - back over UTF-8 characters.) - - -Version 4.2 14-Apr-03 ---------------------- - -1. Typo "#if SUPPORT_UTF8" instead of "#ifdef SUPPORT_UTF8" fixed. - -2. Changes to the building process, supplied by Ronald Landheer-Cieslak - [ON_WINDOWS]: new variable, "#" on non-Windows platforms - [NOT_ON_WINDOWS]: new variable, "#" on Windows platforms - [WIN_PREFIX]: new variable, "cyg" for Cygwin - * Makefile.in: use autoconf substitution for OBJEXT, EXEEXT, BUILD_OBJEXT - and BUILD_EXEEXT - Note: automatic setting of the BUILD variables is not yet working - set CPPFLAGS and BUILD_CPPFLAGS (but don't use yet) - should be used at - compile-time but not at link-time - [LINK]: use for linking executables only - make different versions for Windows and non-Windows - [LINKLIB]: new variable, copy of UNIX-style LINK, used for linking - libraries - [LINK_FOR_BUILD]: new variable - [OBJEXT]: use throughout - [EXEEXT]: use throughout - <winshared>: new target - <wininstall>: new target - <dftables.o>: use native compiler - <dftables>: use native linker - <install>: handle Windows platform correctly - <clean>: ditto - <check>: ditto - copy DLL to top builddir before testing - - As part of these changes, -no-undefined was removed again. This was reported - to give trouble on HP-UX 11.0, so getting rid of it seems like a good idea - in any case. - -3. Some tidies to get rid of compiler warnings: - - . In the match_data structure, match_limit was an unsigned long int, whereas - match_call_count was an int. I've made them both unsigned long ints. - - . In pcretest the fact that a const uschar * doesn't automatically cast to - a void * provoked a warning. - - . Turning on some more compiler warnings threw up some "shadow" variables - and a few more missing casts. - -4. If PCRE was complied with UTF-8 support, but called without the PCRE_UTF8 - option, a class that contained a single character with a value between 128 - and 255 (e.g. /[\xFF]/) caused PCRE to crash. - -5. If PCRE was compiled with UTF-8 support, but called without the PCRE_UTF8 - option, a class that contained several characters, but with at least one - whose value was between 128 and 255 caused PCRE to crash. - - -Version 4.1 12-Mar-03 ---------------------- - -1. Compiling with gcc -pedantic found a couple of places where casts were -needed, and a string in dftables.c that was longer than standard compilers are -required to support. - -2. Compiling with Sun's compiler found a few more places where the code could -be tidied up in order to avoid warnings. - -3. The variables for cross-compiling were called HOST_CC and HOST_CFLAGS; the -first of these names is deprecated in the latest Autoconf in favour of the name -CC_FOR_BUILD, because "host" is typically used to mean the system on which the -compiled code will be run. I can't find a reference for HOST_CFLAGS, but by -analogy I have changed it to CFLAGS_FOR_BUILD. - -4. Added -no-undefined to the linking command in the Makefile, because this is -apparently helpful for Windows. To make it work, also added "-L. -lpcre" to the -linking step for the pcreposix library. - -5. PCRE was failing to diagnose the case of two named groups with the same -name. - -6. A problem with one of PCRE's optimizations was discovered. PCRE remembers a -literal character that is needed in the subject for a match, and scans along to -ensure that it is present before embarking on the full matching process. This -saves time in cases of nested unlimited repeats that are never going to match. -Problem: the scan can take a lot of time if the subject is very long (e.g. -megabytes), thus penalizing straightforward matches. It is now done only if the -amount of subject to be scanned is less than 1000 bytes. - -7. A lesser problem with the same optimization is that it was recording the -first character of an anchored pattern as "needed", thus provoking a search -right along the subject, even when the first match of the pattern was going to -fail. The "needed" character is now not set for anchored patterns, unless it -follows something in the pattern that is of non-fixed length. Thus, it still -fulfils its original purpose of finding quick non-matches in cases of nested -unlimited repeats, but isn't used for simple anchored patterns such as /^abc/. - - -Version 4.0 17-Feb-03 ---------------------- - -1. If a comment in an extended regex that started immediately after a meta-item -extended to the end of string, PCRE compiled incorrect data. This could lead to -all kinds of weird effects. Example: /#/ was bad; /()#/ was bad; /a#/ was not. - -2. Moved to autoconf 2.53 and libtool 1.4.2. - -3. Perl 5.8 no longer needs "use utf8" for doing UTF-8 things. Consequently, -the special perltest8 script is no longer needed - all the tests can be run -from a single perltest script. - -4. From 5.004, Perl has not included the VT character (0x0b) in the set defined -by \s. It has now been removed in PCRE. This means it isn't recognized as -whitespace in /x regexes too, which is the same as Perl. Note that the POSIX -class [:space:] *does* include VT, thereby creating a mess. - -5. Added the class [:blank:] (a GNU extension from Perl 5.8) to match only -space and tab. - -6. Perl 5.005 was a long time ago. It's time to amalgamate the tests that use -its new features into the main test script, reducing the number of scripts. - -7. Perl 5.8 has changed the meaning of patterns like /a(?i)b/. Earlier versions -were backward compatible, and made the (?i) apply to the whole pattern, as if -/i were given. Now it behaves more logically, and applies the option setting -only to what follows. PCRE has been changed to follow suit. However, if it -finds options settings right at the start of the pattern, it extracts them into -the global options, as before. Thus, they show up in the info data. - -8. Added support for the \Q...\E escape sequence. Characters in between are -treated as literals. This is slightly different from Perl in that $ and @ are -also handled as literals inside the quotes. In Perl, they will cause variable -interpolation. Note the following examples: - - Pattern PCRE matches Perl matches - - \Qabc$xyz\E abc$xyz abc followed by the contents of $xyz - \Qabc\$xyz\E abc\$xyz abc\$xyz - \Qabc\E\$\Qxyz\E abc$xyz abc$xyz - -For compatibility with Perl, \Q...\E sequences are recognized inside character -classes as well as outside them. - -9. Re-organized 3 code statements in pcretest to avoid "overflow in -floating-point constant arithmetic" warnings from a Microsoft compiler. Added a -(size_t) cast to one statement in pcretest and one in pcreposix to avoid -signed/unsigned warnings. - -10. SunOS4 doesn't have strtoul(). This was used only for unpicking the -o -option for pcretest, so I've replaced it by a simple function that does just -that job. - -11. pcregrep was ending with code 0 instead of 2 for the commands "pcregrep" or -"pcregrep -". - -12. Added "possessive quantifiers" ?+, *+, ++, and {,}+ which come from Sun's -Java package. This provides some syntactic sugar for simple cases of what my -documentation calls "once-only subpatterns". A pattern such as x*+ is the same -as (?>x*). In other words, if what is inside (?>...) is just a single repeated -item, you can use this simplified notation. Note that only makes sense with -greedy quantifiers. Consequently, the use of the possessive quantifier forces -greediness, whatever the setting of the PCRE_UNGREEDY option. - -13. A change of greediness default within a pattern was not taking effect at -the current level for patterns like /(b+(?U)a+)/. It did apply to parenthesized -subpatterns that followed. Patterns like /b+(?U)a+/ worked because the option -was abstracted outside. - -14. PCRE now supports the \G assertion. It is true when the current matching -position is at the start point of the match. This differs from \A when the -starting offset is non-zero. Used with the /g option of pcretest (or similar -code), it works in the same way as it does for Perl's /g option. If all -alternatives of a regex begin with \G, the expression is anchored to the start -match position, and the "anchored" flag is set in the compiled expression. - -15. Some bugs concerning the handling of certain option changes within patterns -have been fixed. These applied to options other than (?ims). For example, -"a(?x: b c )d" did not match "XabcdY" but did match "Xa b c dY". It should have -been the other way round. Some of this was related to change 7 above. - -16. PCRE now gives errors for /[.x.]/ and /[=x=]/ as unsupported POSIX -features, as Perl does. Previously, PCRE gave the warnings only for /[[.x.]]/ -and /[[=x=]]/. PCRE now also gives an error for /[:name:]/ because it supports -POSIX classes only within a class (e.g. /[[:alpha:]]/). - -17. Added support for Perl's \C escape. This matches one byte, even in UTF8 -mode. Unlike ".", it always matches newline, whatever the setting of -PCRE_DOTALL. However, PCRE does not permit \C to appear in lookbehind -assertions. Perl allows it, but it doesn't (in general) work because it can't -calculate the length of the lookbehind. At least, that's the case for Perl -5.8.0 - I've been told they are going to document that it doesn't work in -future. - -18. Added an error diagnosis for escapes that PCRE does not support: these are -\L, \l, \N, \P, \p, \U, \u, and \X. - -19. Although correctly diagnosing a missing ']' in a character class, PCRE was -reading past the end of the pattern in cases such as /[abcd/. - -20. PCRE was getting more memory than necessary for patterns with classes that -contained both POSIX named classes and other characters, e.g. /[[:space:]abc/. - -21. Added some code, conditional on #ifdef VPCOMPAT, to make life easier for -compiling PCRE for use with Virtual Pascal. - -22. Small fix to the Makefile to make it work properly if the build is done -outside the source tree. - -23. Added a new extension: a condition to go with recursion. If a conditional -subpattern starts with (?(R) the "true" branch is used if recursion has -happened, whereas the "false" branch is used only at the top level. - -24. When there was a very long string of literal characters (over 255 bytes -without UTF support, over 250 bytes with UTF support), the computation of how -much memory was required could be incorrect, leading to segfaults or other -strange effects. - -25. PCRE was incorrectly assuming anchoring (either to start of subject or to -start of line for a non-DOTALL pattern) when a pattern started with (.*) and -there was a subsequent back reference to those brackets. This meant that, for -example, /(.*)\d+\1/ failed to match "abc123bc". Unfortunately, it isn't -possible to check for precisely this case. All we can do is abandon the -optimization if .* occurs inside capturing brackets when there are any back -references whatsoever. (See below for a better fix that came later.) - -26. The handling of the optimization for finding the first character of a -non-anchored pattern, and for finding a character that is required later in the -match were failing in some cases. This didn't break the matching; it just -failed to optimize when it could. The way this is done has been re-implemented. - -27. Fixed typo in error message for invalid (?R item (it said "(?p"). - -28. Added a new feature that provides some of the functionality that Perl -provides with (?{...}). The facility is termed a "callout". The way it is done -in PCRE is for the caller to provide an optional function, by setting -pcre_callout to its entry point. Like pcre_malloc and pcre_free, this is a -global variable. By default it is unset, which disables all calling out. To get -the function called, the regex must include (?C) at appropriate points. This -is, in fact, equivalent to (?C0), and any number <= 255 may be given with (?C). -This provides a means of identifying different callout points. When PCRE -reaches such a point in the regex, if pcre_callout has been set, the external -function is called. It is provided with data in a structure called -pcre_callout_block, which is defined in pcre.h. If the function returns 0, -matching continues; if it returns a non-zero value, the match at the current -point fails. However, backtracking will occur if possible. [This was changed -later and other features added - see item 49 below.] - -29. pcretest is upgraded to test the callout functionality. It provides a -callout function that displays information. By default, it shows the start of -the match and the current position in the text. There are some new data escapes -to vary what happens: - - \C+ in addition, show current contents of captured substrings - \C- do not supply a callout function - \C!n return 1 when callout number n is reached - \C!n!m return 1 when callout number n is reached for the mth time - -30. If pcregrep was called with the -l option and just a single file name, it -output "<stdin>" if a match was found, instead of the file name. - -31. Improve the efficiency of the POSIX API to PCRE. If the number of capturing -slots is less than POSIX_MALLOC_THRESHOLD, use a block on the stack to pass to -pcre_exec(). This saves a malloc/free per call. The default value of -POSIX_MALLOC_THRESHOLD is 10; it can be changed by --with-posix-malloc-threshold -when configuring. - -32. The default maximum size of a compiled pattern is 64K. There have been a -few cases of people hitting this limit. The code now uses macros to handle the -storing of links as offsets within the compiled pattern. It defaults to 2-byte -links, but this can be changed to 3 or 4 bytes by --with-link-size when -configuring. Tests 2 and 5 work only with 2-byte links because they output -debugging information about compiled patterns. - -33. Internal code re-arrangements: - -(a) Moved the debugging function for printing out a compiled regex into - its own source file (printint.c) and used #include to pull it into - pcretest.c and, when DEBUG is defined, into pcre.c, instead of having two - separate copies. - -(b) Defined the list of op-code names for debugging as a macro in - internal.h so that it is next to the definition of the opcodes. - -(c) Defined a table of op-code lengths for simpler skipping along compiled - code. This is again a macro in internal.h so that it is next to the - definition of the opcodes. - -34. Added support for recursive calls to individual subpatterns, along the -lines of Robin Houston's patch (but implemented somewhat differently). - -35. Further mods to the Makefile to help Win32. Also, added code to pcregrep to -allow it to read and process whole directories in Win32. This code was -contributed by Lionel Fourquaux; it has not been tested by me. - -36. Added support for named subpatterns. The Python syntax (?P<name>...) is -used to name a group. Names consist of alphanumerics and underscores, and must -be unique. Back references use the syntax (?P=name) and recursive calls use -(?P>name) which is a PCRE extension to the Python extension. Groups still have -numbers. The function pcre_fullinfo() can be used after compilation to extract -a name/number map. There are three relevant calls: - - PCRE_INFO_NAMEENTRYSIZE yields the size of each entry in the map - PCRE_INFO_NAMECOUNT yields the number of entries - PCRE_INFO_NAMETABLE yields a pointer to the map. - -The map is a vector of fixed-size entries. The size of each entry depends on -the length of the longest name used. The first two bytes of each entry are the -group number, most significant byte first. There follows the corresponding -name, zero terminated. The names are in alphabetical order. - -37. Make the maximum literal string in the compiled code 250 for the non-UTF-8 -case instead of 255. Making it the same both with and without UTF-8 support -means that the same test output works with both. - -38. There was a case of malloc(0) in the POSIX testing code in pcretest. Avoid -calling malloc() with a zero argument. - -39. Change 25 above had to resort to a heavy-handed test for the .* anchoring -optimization. I've improved things by keeping a bitmap of backreferences with -numbers 1-31 so that if .* occurs inside capturing brackets that are not in -fact referenced, the optimization can be applied. It is unlikely that a -relevant occurrence of .* (i.e. one which might indicate anchoring or forcing -the match to follow \n) will appear inside brackets with a number greater than -31, but if it does, any back reference > 31 suppresses the optimization. - -40. Added a new compile-time option PCRE_NO_AUTO_CAPTURE. This has the effect -of disabling numbered capturing parentheses. Any opening parenthesis that is -not followed by ? behaves as if it were followed by ?: but named parentheses -can still be used for capturing (and they will acquire numbers in the usual -way). - -41. Redesigned the return codes from the match() function into yes/no/error so -that errors can be passed back from deep inside the nested calls. A malloc -failure while inside a recursive subpattern call now causes the -PCRE_ERROR_NOMEMORY return instead of quietly going wrong. - -42. It is now possible to set a limit on the number of times the match() -function is called in a call to pcre_exec(). This facility makes it possible to -limit the amount of recursion and backtracking, though not in a directly -obvious way, because the match() function is used in a number of different -circumstances. The count starts from zero for each position in the subject -string (for non-anchored patterns). The default limit is, for compatibility, a -large number, namely 10 000 000. You can change this in two ways: - -(a) When configuring PCRE before making, you can use --with-match-limit=n - to set a default value for the compiled library. - -(b) For each call to pcre_exec(), you can pass a pcre_extra block in which - a different value is set. See 45 below. - -If the limit is exceeded, pcre_exec() returns PCRE_ERROR_MATCHLIMIT. - -43. Added a new function pcre_config(int, void *) to enable run-time extraction -of things that can be changed at compile time. The first argument specifies -what is wanted and the second points to where the information is to be placed. -The current list of available information is: - - PCRE_CONFIG_UTF8 - -The output is an integer that is set to one if UTF-8 support is available; -otherwise it is set to zero. - - PCRE_CONFIG_NEWLINE - -The output is an integer that it set to the value of the code that is used for -newline. It is either LF (10) or CR (13). - - PCRE_CONFIG_LINK_SIZE - -The output is an integer that contains the number of bytes used for internal -linkage in compiled expressions. The value is 2, 3, or 4. See item 32 above. - - PCRE_CONFIG_POSIX_MALLOC_THRESHOLD - -The output is an integer that contains the threshold above which the POSIX -interface uses malloc() for output vectors. See item 31 above. - - PCRE_CONFIG_MATCH_LIMIT - -The output is an unsigned integer that contains the default limit of the number -of match() calls in a pcre_exec() execution. See 42 above. - -44. pcretest has been upgraded by the addition of the -C option. This causes it -to extract all the available output from the new pcre_config() function, and to -output it. The program then exits immediately. - -45. A need has arisen to pass over additional data with calls to pcre_exec() in -order to support additional features. One way would have been to define -pcre_exec2() (for example) with extra arguments, but this would not have been -extensible, and would also have required all calls to the original function to -be mapped to the new one. Instead, I have chosen to extend the mechanism that -is used for passing in "extra" data from pcre_study(). - -The pcre_extra structure is now exposed and defined in pcre.h. It currently -contains the following fields: - - flags a bitmap indicating which of the following fields are set - study_data opaque data from pcre_study() - match_limit a way of specifying a limit on match() calls for a specific - call to pcre_exec() - callout_data data for callouts (see 49 below) - -The flag bits are also defined in pcre.h, and are - - PCRE_EXTRA_STUDY_DATA - PCRE_EXTRA_MATCH_LIMIT - PCRE_EXTRA_CALLOUT_DATA - -The pcre_study() function now returns one of these new pcre_extra blocks, with -the actual study data pointed to by the study_data field, and the -PCRE_EXTRA_STUDY_DATA flag set. This can be passed directly to pcre_exec() as -before. That is, this change is entirely upwards-compatible and requires no -change to existing code. - -If you want to pass in additional data to pcre_exec(), you can either place it -in a pcre_extra block provided by pcre_study(), or create your own pcre_extra -block. - -46. pcretest has been extended to test the PCRE_EXTRA_MATCH_LIMIT feature. If a -data string contains the escape sequence \M, pcretest calls pcre_exec() several -times with different match limits, until it finds the minimum value needed for -pcre_exec() to complete. The value is then output. This can be instructive; for -most simple matches the number is quite small, but for pathological cases it -gets very large very quickly. - -47. There's a new option for pcre_fullinfo() called PCRE_INFO_STUDYSIZE. It -returns the size of the data block pointed to by the study_data field in a -pcre_extra block, that is, the value that was passed as the argument to -pcre_malloc() when PCRE was getting memory in which to place the information -created by pcre_study(). The fourth argument should point to a size_t variable. -pcretest has been extended so that this information is shown after a successful -pcre_study() call when information about the compiled regex is being displayed. - -48. Cosmetic change to Makefile: there's no need to have / after $(DESTDIR) -because what follows is always an absolute path. (Later: it turns out that this -is more than cosmetic for MinGW, because it doesn't like empty path -components.) - -49. Some changes have been made to the callout feature (see 28 above): - -(i) A callout function now has three choices for what it returns: - - 0 => success, carry on matching - > 0 => failure at this point, but backtrack if possible - < 0 => serious error, return this value from pcre_exec() - - Negative values should normally be chosen from the set of PCRE_ERROR_xxx - values. In particular, returning PCRE_ERROR_NOMATCH forces a standard - "match failed" error. The error number PCRE_ERROR_CALLOUT is reserved for - use by callout functions. It will never be used by PCRE itself. - -(ii) The pcre_extra structure (see 45 above) has a void * field called - callout_data, with corresponding flag bit PCRE_EXTRA_CALLOUT_DATA. The - pcre_callout_block structure has a field of the same name. The contents of - the field passed in the pcre_extra structure are passed to the callout - function in the corresponding field in the callout block. This makes it - easier to use the same callout-containing regex from multiple threads. For - testing, the pcretest program has a new data escape - - \C*n pass the number n (may be negative) as callout_data - - If the callout function in pcretest receives a non-zero value as - callout_data, it returns that value. - -50. Makefile wasn't handling CFLAGS properly when compiling dftables. Also, -there were some redundant $(CFLAGS) in commands that are now specified as -$(LINK), which already includes $(CFLAGS). - -51. Extensions to UTF-8 support are listed below. These all apply when (a) PCRE -has been compiled with UTF-8 support *and* pcre_compile() has been compiled -with the PCRE_UTF8 flag. Patterns that are compiled without that flag assume -one-byte characters throughout. Note that case-insensitive matching applies -only to characters whose values are less than 256. PCRE doesn't support the -notion of cases for higher-valued characters. - -(i) A character class whose characters are all within 0-255 is handled as - a bit map, and the map is inverted for negative classes. Previously, a - character > 255 always failed to match such a class; however it should - match if the class was a negative one (e.g. [^ab]). This has been fixed. - -(ii) A negated character class with a single character < 255 is coded as - "not this character" (OP_NOT). This wasn't working properly when the test - character was multibyte, either singly or repeated. - -(iii) Repeats of multibyte characters are now handled correctly in UTF-8 - mode, for example: \x{100}{2,3}. - -(iv) The character escapes \b, \B, \d, \D, \s, \S, \w, and \W (either - singly or repeated) now correctly test multibyte characters. However, - PCRE doesn't recognize any characters with values greater than 255 as - digits, spaces, or word characters. Such characters always match \D, \S, - and \W, and never match \d, \s, or \w. - -(v) Classes may now contain characters and character ranges with values - greater than 255. For example: [ab\x{100}-\x{400}]. - -(vi) pcregrep now has a --utf-8 option (synonym -u) which makes it call - PCRE in UTF-8 mode. - -52. The info request value PCRE_INFO_FIRSTCHAR has been renamed -PCRE_INFO_FIRSTBYTE because it is a byte value. However, the old name is -retained for backwards compatibility. (Note that LASTLITERAL is also a byte -value.) - -53. The single man page has become too large. I have therefore split it up into -a number of separate man pages. These also give rise to individual HTML pages; -these are now put in a separate directory, and there is an index.html page that -lists them all. Some hyperlinking between the pages has been installed. - -54. Added convenience functions for handling named capturing parentheses. - -55. Unknown escapes inside character classes (e.g. [\M]) and escapes that -aren't interpreted therein (e.g. [\C]) are literals in Perl. This is now also -true in PCRE, except when the PCRE_EXTENDED option is set, in which case they -are faulted. - -56. Introduced HOST_CC and HOST_CFLAGS which can be set in the environment when -calling configure. These values are used when compiling the dftables.c program -which is run to generate the source of the default character tables. They -default to the values of CC and CFLAGS. If you are cross-compiling PCRE, -you will need to set these values. - -57. Updated the building process for Windows DLL, as provided by Fred Cox. - - -Version 3.9 02-Jan-02 ---------------------- - -1. A bit of extraneous text had somehow crept into the pcregrep documentation. - -2. If --disable-static was given, the building process failed when trying to -build pcretest and pcregrep. (For some reason it was using libtool to compile -them, which is not right, as they aren't part of the library.) - - -Version 3.8 18-Dec-01 ---------------------- - -1. The experimental UTF-8 code was completely screwed up. It was packing the -bytes in the wrong order. How dumb can you get? - - -Version 3.7 29-Oct-01 ---------------------- - -1. In updating pcretest to check change 1 of version 3.6, I screwed up. -This caused pcretest, when used on the test data, to segfault. Unfortunately, -this didn't happen under Solaris 8, where I normally test things. - -2. The Makefile had to be changed to make it work on BSD systems, where 'make' -doesn't seem to recognize that ./xxx and xxx are the same file. (This entry -isn't in ChangeLog distributed with 3.7 because I forgot when I hastily made -this fix an hour or so after the initial 3.7 release.) - - -Version 3.6 23-Oct-01 ---------------------- - -1. Crashed with /(sens|respons)e and \1ibility/ and "sense and sensibility" if -offsets passed as NULL with zero offset count. - -2. The config.guess and config.sub files had not been updated when I moved to -the latest autoconf. - - -Version 3.5 15-Aug-01 ---------------------- - -1. Added some missing #if !defined NOPOSIX conditionals in pcretest.c that -had been forgotten. - -2. By using declared but undefined structures, we can avoid using "void" -definitions in pcre.h while keeping the internal definitions of the structures -private. - -3. The distribution is now built using autoconf 2.50 and libtool 1.4. From a -user point of view, this means that both static and shared libraries are built -by default, but this can be individually controlled. More of the work of -handling this static/shared cases is now inside libtool instead of PCRE's make -file. - -4. The pcretest utility is now installed along with pcregrep because it is -useful for users (to test regexs) and by doing this, it automatically gets -relinked by libtool. The documentation has been turned into a man page, so -there are now .1, .txt, and .html versions in /doc. - -5. Upgrades to pcregrep: - (i) Added long-form option names like gnu grep. - (ii) Added --help to list all options with an explanatory phrase. - (iii) Added -r, --recursive to recurse into sub-directories. - (iv) Added -f, --file to read patterns from a file. - -6. pcre_exec() was referring to its "code" argument before testing that -argument for NULL (and giving an error if it was NULL). - -7. Upgraded Makefile.in to allow for compiling in a different directory from -the source directory. - -8. Tiny buglet in pcretest: when pcre_fullinfo() was called to retrieve the -options bits, the pointer it was passed was to an int instead of to an unsigned -long int. This mattered only on 64-bit systems. - -9. Fixed typo (3.4/1) in pcre.h again. Sigh. I had changed pcre.h (which is -generated) instead of pcre.in, which it its source. Also made the same change -in several of the .c files. - -10. A new release of gcc defines printf() as a macro, which broke pcretest -because it had an ifdef in the middle of a string argument for printf(). Fixed -by using separate calls to printf(). - -11. Added --enable-newline-is-cr and --enable-newline-is-lf to the configure -script, to force use of CR or LF instead of \n in the source. On non-Unix -systems, the value can be set in config.h. - -12. The limit of 200 on non-capturing parentheses is a _nesting_ limit, not an -absolute limit. Changed the text of the error message to make this clear, and -likewise updated the man page. - -13. The limit of 99 on the number of capturing subpatterns has been removed. -The new limit is 65535, which I hope will not be a "real" limit. - - -Version 3.4 22-Aug-00 ---------------------- - -1. Fixed typo in pcre.h: unsigned const char * changed to const unsigned char *. - -2. Diagnose condition (?(0) as an error instead of crashing on matching. - - -Version 3.3 01-Aug-00 ---------------------- - -1. If an octal character was given, but the value was greater than \377, it -was not getting masked to the least significant bits, as documented. This could -lead to crashes in some systems. - -2. Perl 5.6 (if not earlier versions) accepts classes like [a-\d] and treats -the hyphen as a literal. PCRE used to give an error; it now behaves like Perl. - -3. Added the functions pcre_free_substring() and pcre_free_substring_list(). -These just pass their arguments on to (pcre_free)(), but they are provided -because some uses of PCRE bind it to non-C systems that can call its functions, -but cannot call free() or pcre_free() directly. - -4. Add "make test" as a synonym for "make check". Corrected some comments in -the Makefile. - -5. Add $(DESTDIR)/ in front of all the paths in the "install" target in the -Makefile. - -6. Changed the name of pgrep to pcregrep, because Solaris has introduced a -command called pgrep for grepping around the active processes. - -7. Added the beginnings of support for UTF-8 character strings. - -8. Arranged for the Makefile to pass over the settings of CC, CFLAGS, and -RANLIB to ./ltconfig so that they are used by libtool. I think these are all -the relevant ones. (AR is not passed because ./ltconfig does its own figuring -out for the ar command.) - - -Version 3.2 12-May-00 ---------------------- - -This is purely a bug fixing release. - -1. If the pattern /((Z)+|A)*/ was matched agained ZABCDEFG it matched Z instead -of ZA. This was just one example of several cases that could provoke this bug, -which was introduced by change 9 of version 2.00. The code for breaking -infinite loops after an iteration that matches an empty string was't working -correctly. - -2. The pcretest program was not imitating Perl correctly for the pattern /a*/g -when matched against abbab (for example). After matching an empty string, it -wasn't forcing anchoring when setting PCRE_NOTEMPTY for the next attempt; this -caused it to match further down the string than it should. - -3. The code contained an inclusion of sys/types.h. It isn't clear why this -was there because it doesn't seem to be needed, and it causes trouble on some -systems, as it is not a Standard C header. It has been removed. - -4. Made 4 silly changes to the source to avoid stupid compiler warnings that -were reported on the Macintosh. The changes were from - - while ((c = *(++ptr)) != 0 && c != '\n'); -to - while ((c = *(++ptr)) != 0 && c != '\n') ; - -Totally extraordinary, but if that's what it takes... - -5. PCRE is being used in one environment where neither memmove() nor bcopy() is -available. Added HAVE_BCOPY and an autoconf test for it; if neither -HAVE_MEMMOVE nor HAVE_BCOPY is set, use a built-in emulation function which -assumes the way PCRE uses memmove() (always moving upwards). - -6. PCRE is being used in one environment where strchr() is not available. There -was only one use in pcre.c, and writing it out to avoid strchr() probably gives -faster code anyway. - - -Version 3.1 09-Feb-00 ---------------------- - -The only change in this release is the fixing of some bugs in Makefile.in for -the "install" target: - -(1) It was failing to install pcreposix.h. - -(2) It was overwriting the pcre.3 man page with the pcreposix.3 man page. - - -Version 3.0 01-Feb-00 ---------------------- - -1. Add support for the /+ modifier to perltest (to output $` like it does in -pcretest). - -2. Add support for the /g modifier to perltest. - -3. Fix pcretest so that it behaves even more like Perl for /g when the pattern -matches null strings. - -4. Fix perltest so that it doesn't do unwanted things when fed an empty -pattern. Perl treats empty patterns specially - it reuses the most recent -pattern, which is not what we want. Replace // by /(?#)/ in order to avoid this -effect. - -5. The POSIX interface was broken in that it was just handing over the POSIX -captured string vector to pcre_exec(), but (since release 2.00) PCRE has -required a bigger vector, with some working space on the end. This means that -the POSIX wrapper now has to get and free some memory, and copy the results. - -6. Added some simple autoconf support, placing the test data and the -documentation in separate directories, re-organizing some of the -information files, and making it build pcre-config (a GNU standard). Also added -libtool support for building PCRE as a shared library, which is now the -default. - -7. Got rid of the leading zero in the definition of PCRE_MINOR because 08 and -09 are not valid octal constants. Single digits will be used for minor values -less than 10. - -8. Defined REG_EXTENDED and REG_NOSUB as zero in the POSIX header, so that -existing programs that set these in the POSIX interface can use PCRE without -modification. - -9. Added a new function, pcre_fullinfo() with an extensible interface. It can -return all that pcre_info() returns, plus additional data. The pcre_info() -function is retained for compatibility, but is considered to be obsolete. - -10. Added experimental recursion feature (?R) to handle one common case that -Perl 5.6 will be able to do with (?p{...}). - -11. Added support for POSIX character classes like [:alpha:], which Perl is -adopting. - - -Version 2.08 31-Aug-99 ----------------------- - -1. When startoffset was not zero and the pattern began with ".*", PCRE was not -trying to match at the startoffset position, but instead was moving forward to -the next newline as if a previous match had failed. - -2. pcretest was not making use of PCRE_NOTEMPTY when repeating for /g and /G, -and could get into a loop if a null string was matched other than at the start -of the subject. - -3. Added definitions of PCRE_MAJOR and PCRE_MINOR to pcre.h so the version can -be distinguished at compile time, and for completeness also added PCRE_DATE. - -5. Added Paul Sokolovsky's minor changes to make it easy to compile a Win32 DLL -in GnuWin32 environments. - - -Version 2.07 29-Jul-99 ----------------------- - -1. The documentation is now supplied in plain text form and HTML as well as in -the form of man page sources. - -2. C++ compilers don't like assigning (void *) values to other pointer types. -In particular this affects malloc(). Although there is no problem in Standard -C, I've put in casts to keep C++ compilers happy. - -3. Typo on pcretest.c; a cast of (unsigned char *) in the POSIX regexec() call -should be (const char *). - -4. If NOPOSIX is defined, pcretest.c compiles without POSIX support. This may -be useful for non-Unix systems who don't want to bother with the POSIX stuff. -However, I haven't made this a standard facility. The documentation doesn't -mention it, and the Makefile doesn't support it. - -5. The Makefile now contains an "install" target, with editable destinations at -the top of the file. The pcretest program is not installed. - -6. pgrep -V now gives the PCRE version number and date. - -7. Fixed bug: a zero repetition after a literal string (e.g. /abcde{0}/) was -causing the entire string to be ignored, instead of just the last character. - -8. If a pattern like /"([^\\"]+|\\.)*"/ is applied in the normal way to a -non-matching string, it can take a very, very long time, even for strings of -quite modest length, because of the nested recursion. PCRE now does better in -some of these cases. It does this by remembering the last required literal -character in the pattern, and pre-searching the subject to ensure it is present -before running the real match. In other words, it applies a heuristic to detect -some types of certain failure quickly, and in the above example, if presented -with a string that has no trailing " it gives "no match" very quickly. - -9. A new runtime option PCRE_NOTEMPTY causes null string matches to be ignored; -other alternatives are tried instead. - - -Version 2.06 09-Jun-99 ----------------------- - -1. Change pcretest's output for amount of store used to show just the code -space, because the remainder (the data block) varies in size between 32-bit and -64-bit systems. - -2. Added an extra argument to pcre_exec() to supply an offset in the subject to -start matching at. This allows lookbehinds to work when searching for multiple -occurrences in a string. - -3. Added additional options to pcretest for testing multiple occurrences: - - /+ outputs the rest of the string that follows a match - /g loops for multiple occurrences, using the new startoffset argument - /G loops for multiple occurrences by passing an incremented pointer - -4. PCRE wasn't doing the "first character" optimization for patterns starting -with \b or \B, though it was doing it for other lookbehind assertions. That is, -it wasn't noticing that a match for a pattern such as /\bxyz/ has to start with -the letter 'x'. On long subject strings, this gives a significant speed-up. - - -Version 2.05 21-Apr-99 ----------------------- - -1. Changed the type of magic_number from int to long int so that it works -properly on 16-bit systems. - -2. Fixed a bug which caused patterns starting with .* not to work correctly -when the subject string contained newline characters. PCRE was assuming -anchoring for such patterns in all cases, which is not correct because .* will -not pass a newline unless PCRE_DOTALL is set. It now assumes anchoring only if -DOTALL is set at top level; otherwise it knows that patterns starting with .* -must be retried after every newline in the subject. - - -Version 2.04 18-Feb-99 ----------------------- - -1. For parenthesized subpatterns with repeats whose minimum was zero, the -computation of the store needed to hold the pattern was incorrect (too large). -If such patterns were nested a few deep, this could multiply and become a real -problem. - -2. Added /M option to pcretest to show the memory requirement of a specific -pattern. Made -m a synonym of -s (which does this globally) for compatibility. - -3. Subpatterns of the form (regex){n,m} (i.e. limited maximum) were being -compiled in such a way that the backtracking after subsequent failure was -pessimal. Something like (a){0,3} was compiled as (a)?(a)?(a)? instead of -((a)((a)(a)?)?)? with disastrous performance if the maximum was of any size. - - -Version 2.03 02-Feb-99 ----------------------- - -1. Fixed typo and small mistake in man page. - -2. Added 4th condition (GPL supersedes if conflict) and created separate -LICENCE file containing the conditions. - -3. Updated pcretest so that patterns such as /abc\/def/ work like they do in -Perl, that is the internal \ allows the delimiter to be included in the -pattern. Locked out the use of \ as a delimiter. If \ immediately follows -the final delimiter, add \ to the end of the pattern (to test the error). - -4. Added the convenience functions for extracting substrings after a successful -match. Updated pcretest to make it able to test these functions. - - -Version 2.02 14-Jan-99 ----------------------- - -1. Initialized the working variables associated with each extraction so that -their saving and restoring doesn't refer to uninitialized store. - -2. Put dummy code into study.c in order to trick the optimizer of the IBM C -compiler for OS/2 into generating correct code. Apparently IBM isn't going to -fix the problem. - -3. Pcretest: the timing code wasn't using LOOPREPEAT for timing execution -calls, and wasn't printing the correct value for compiling calls. Increased the -default value of LOOPREPEAT, and the number of significant figures in the -times. - -4. Changed "/bin/rm" in the Makefile to "-rm" so it works on Windows NT. - -5. Renamed "deftables" as "dftables" to get it down to 8 characters, to avoid -a building problem on Windows NT with a FAT file system. - - -Version 2.01 21-Oct-98 ----------------------- - -1. Changed the API for pcre_compile() to allow for the provision of a pointer -to character tables built by pcre_maketables() in the current locale. If NULL -is passed, the default tables are used. - - -Version 2.00 24-Sep-98 ----------------------- - -1. Since the (>?) facility is in Perl 5.005, don't require PCRE_EXTRA to enable -it any more. - -2. Allow quantification of (?>) groups, and make it work correctly. - -3. The first character computation wasn't working for (?>) groups. - -4. Correct the implementation of \Z (it is permitted to match on the \n at the -end of the subject) and add 5.005's \z, which really does match only at the -very end of the subject. - -5. Remove the \X "cut" facility; Perl doesn't have it, and (?> is neater. - -6. Remove the ability to specify CASELESS, MULTILINE, DOTALL, and -DOLLAR_END_ONLY at runtime, to make it possible to implement the Perl 5.005 -localized options. All options to pcre_study() were also removed. - -7. Add other new features from 5.005: - - $(?<= positive lookbehind - $(?<! negative lookbehind - (?imsx-imsx) added the unsetting capability - such a setting is global if at outer level; local otherwise - (?imsx-imsx:) non-capturing groups with option setting - (?(cond)re|re) conditional pattern matching - - A backreference to itself in a repeated group matches the previous - captured string. - -8. General tidying up of studying (both automatic and via "study") -consequential on the addition of new assertions. - -9. As in 5.005, unlimited repeated groups that could match an empty substring -are no longer faulted at compile time. Instead, the loop is forcibly broken at -runtime if any iteration does actually match an empty substring. - -10. Include the RunTest script in the distribution. - -11. Added tests from the Perl 5.005_02 distribution. This showed up a few -discrepancies, some of which were old and were also with respect to 5.004. They -have now been fixed. - - -Version 1.09 28-Apr-98 ----------------------- - -1. A negated single character class followed by a quantifier with a minimum -value of one (e.g. [^x]{1,6} ) was not compiled correctly. This could lead to -program crashes, or just wrong answers. This did not apply to negated classes -containing more than one character, or to minima other than one. - - -Version 1.08 27-Mar-98 ----------------------- - -1. Add PCRE_UNGREEDY to invert the greediness of quantifiers. - -2. Add (?U) and (?X) to set PCRE_UNGREEDY and PCRE_EXTRA respectively. The -latter must appear before anything that relies on it in the pattern. - - -Version 1.07 16-Feb-98 ----------------------- - -1. A pattern such as /((a)*)*/ was not being diagnosed as in error (unlimited -repeat of a potentially empty string). - - -Version 1.06 23-Jan-98 ----------------------- - -1. Added Markus Oberhumer's little patches for C++. - -2. Literal strings longer than 255 characters were broken. - - -Version 1.05 23-Dec-97 ----------------------- - -1. Negated character classes containing more than one character were failing if -PCRE_CASELESS was set at run time. - - -Version 1.04 19-Dec-97 ----------------------- - -1. Corrected the man page, where some "const" qualifiers had been omitted. - -2. Made debugging output print "{0,xxx}" instead of just "{,xxx}" to agree with -input syntax. - -3. Fixed memory leak which occurred when a regex with back references was -matched with an offsets vector that wasn't big enough. The temporary memory -that is used in this case wasn't being freed if the match failed. - -4. Tidied pcretest to ensure it frees memory that it gets. - -5. Temporary memory was being obtained in the case where the passed offsets -vector was exactly big enough. - -6. Corrected definition of offsetof() from change 5 below. - -7. I had screwed up change 6 below and broken the rules for the use of -setjmp(). Now fixed. - - -Version 1.03 18-Dec-97 ----------------------- - -1. A erroneous regex with a missing opening parenthesis was correctly -diagnosed, but PCRE attempted to access brastack[-1], which could cause crashes -on some systems. - -2. Replaced offsetof(real_pcre, code) by offsetof(real_pcre, code[0]) because -it was reported that one broken compiler failed on the former because "code" is -also an independent variable. - -3. The erroneous regex a[]b caused an array overrun reference. - -4. A regex ending with a one-character negative class (e.g. /[^k]$/) did not -fail on data ending with that character. (It was going on too far, and checking -the next character, typically a binary zero.) This was specific to the -optimized code for single-character negative classes. - -5. Added a contributed patch from the TIN world which does the following: - - + Add an undef for memmove, in case the the system defines a macro for it. - - + Add a definition of offsetof(), in case there isn't one. (I don't know - the reason behind this - offsetof() is part of the ANSI standard - but - it does no harm). - - + Reduce the ifdef's in pcre.c using macro DPRINTF, thereby eliminating - most of the places where whitespace preceded '#'. I have given up and - allowed the remaining 2 cases to be at the margin. - - + Rename some variables in pcre to eliminate shadowing. This seems very - pedantic, but does no harm, of course. - -6. Moved the call to setjmp() into its own function, to get rid of warnings -from gcc -Wall, and avoided calling it at all unless PCRE_EXTRA is used. - -7. Constructs such as \d{8,} were compiling into the equivalent of -\d{8}\d{0,65527} instead of \d{8}\d* which didn't make much difference to the -outcome, but in this particular case used more store than had been allocated, -which caused the bug to be discovered because it threw up an internal error. - -8. The debugging code in both pcre and pcretest for outputting the compiled -form of a regex was going wrong in the case of back references followed by -curly-bracketed repeats. - - -Version 1.02 12-Dec-97 ----------------------- - -1. Typos in pcre.3 and comments in the source fixed. - -2. Applied a contributed patch to get rid of places where it used to remove -'const' from variables, and fixed some signed/unsigned and uninitialized -variable warnings. - -3. Added the "runtest" target to Makefile. - -4. Set default compiler flag to -O2 rather than just -O. - - -Version 1.01 19-Nov-97 ----------------------- - -1. PCRE was failing to diagnose unlimited repeat of empty string for patterns -like /([ab]*)*/, that is, for classes with more than one character in them. - -2. Likewise, it wasn't diagnosing patterns with "once-only" subpatterns, such -as /((?>a*))*/ (a PCRE_EXTRA facility). - - -Version 1.00 18-Nov-97 ----------------------- - -1. Added compile-time macros to support systems such as SunOS4 which don't have -memmove() or strerror() but have other things that can be used instead. - -2. Arranged that "make clean" removes the executables. - - -Version 0.99 27-Oct-97 ----------------------- - -1. Fixed bug in code for optimizing classes with only one character. It was -initializing a 32-byte map regardless, which could cause it to run off the end -of the memory it had got. - -2. Added, conditional on PCRE_EXTRA, the proposed (?>REGEX) construction. - - -Version 0.98 22-Oct-97 ----------------------- - -1. Fixed bug in code for handling temporary memory usage when there are more -back references than supplied space in the ovector. This could cause segfaults. - - -Version 0.97 21-Oct-97 ----------------------- - -1. Added the \X "cut" facility, conditional on PCRE_EXTRA. - -2. Optimized negated single characters not to use a bit map. - -3. Brought error texts together as macro definitions; clarified some of them; -fixed one that was wrong - it said "range out of order" when it meant "invalid -escape sequence". - -4. Changed some char * arguments to const char *. - -5. Added PCRE_NOTBOL and PCRE_NOTEOL (from POSIX). - -6. Added the POSIX-style API wrapper in pcreposix.a and testing facilities in -pcretest. - - -Version 0.96 16-Oct-97 ----------------------- - -1. Added a simple "pgrep" utility to the distribution. - -2. Fixed an incompatibility with Perl: "{" is now treated as a normal character -unless it appears in one of the precise forms "{ddd}", "{ddd,}", or "{ddd,ddd}" -where "ddd" means "one or more decimal digits". - -3. Fixed serious bug. If a pattern had a back reference, but the call to -pcre_exec() didn't supply a large enough ovector to record the related -identifying subpattern, the match always failed. PCRE now remembers the number -of the largest back reference, and gets some temporary memory in which to save -the offsets during matching if necessary, in order to ensure that -backreferences always work. - -4. Increased the compatibility with Perl in a number of ways: - - (a) . no longer matches \n by default; an option PCRE_DOTALL is provided - to request this handling. The option can be set at compile or exec time. - - (b) $ matches before a terminating newline by default; an option - PCRE_DOLLAR_ENDONLY is provided to override this (but not in multiline - mode). The option can be set at compile or exec time. - - (c) The handling of \ followed by a digit other than 0 is now supposed to be - the same as Perl's. If the decimal number it represents is less than 10 - or there aren't that many previous left capturing parentheses, an octal - escape is read. Inside a character class, it's always an octal escape, - even if it is a single digit. - - (d) An escaped but undefined alphabetic character is taken as a literal, - unless PCRE_EXTRA is set. Currently this just reserves the remaining - escapes. - - (e) {0} is now permitted. (The previous item is removed from the compiled - pattern). - -5. Changed all the names of code files so that the basic parts are no longer -than 10 characters, and abolished the teeny "globals.c" file. - -6. Changed the handling of character classes; they are now done with a 32-byte -bit map always. - -7. Added the -d and /D options to pcretest to make it possible to look at the -internals of compilation without having to recompile pcre. - - -Version 0.95 23-Sep-97 ----------------------- - -1. Fixed bug in pre-pass concerning escaped "normal" characters such as \x5c or -\x20 at the start of a run of normal characters. These were being treated as -real characters, instead of the source characters being re-checked. - - -Version 0.94 18-Sep-97 ----------------------- - -1. The functions are now thread-safe, with the caveat that the global variables -containing pointers to malloc() and free() or alternative functions are the -same for all threads. - -2. Get pcre_study() to generate a bitmap of initial characters for non- -anchored patterns when this is possible, and use it if passed to pcre_exec(). - - -Version 0.93 15-Sep-97 ----------------------- - -1. /(b)|(:+)/ was computing an incorrect first character. - -2. Add pcre_study() to the API and the passing of pcre_extra to pcre_exec(), -but not actually doing anything yet. - -3. Treat "-" characters in classes that cannot be part of ranges as literals, -as Perl does (e.g. [-az] or [az-]). - -4. Set the anchored flag if a branch starts with .* or .*? because that tests -all possible positions. - -5. Split up into different modules to avoid including unneeded functions in a -compiled binary. However, compile and exec are still in one module. The "study" -function is split off. - -6. The character tables are now in a separate module whose source is generated -by an auxiliary program - but can then be edited by hand if required. There are -now no calls to isalnum(), isspace(), isdigit(), isxdigit(), tolower() or -toupper() in the code. - -7. Turn the malloc/free funtions variables into pcre_malloc and pcre_free and -make them global. Abolish the function for setting them, as the caller can now -set them directly. - - -Version 0.92 11-Sep-97 ----------------------- - -1. A repeat with a fixed maximum and a minimum of 1 for an ordinary character -(e.g. /a{1,3}/) was broken (I mis-optimized it). - -2. Caseless matching was not working in character classes if the characters in -the pattern were in upper case. - -3. Make ranges like [W-c] work in the same way as Perl for caseless matching. - -4. Make PCRE_ANCHORED public and accept as a compile option. - -5. Add an options word to pcre_exec() and accept PCRE_ANCHORED and -PCRE_CASELESS at run time. Add escapes \A and \I to pcretest to cause it to -pass them. - -6. Give an error if bad option bits passed at compile or run time. - -7. Add PCRE_MULTILINE at compile and exec time, and (?m) as well. Add \M to -pcretest to cause it to pass that flag. - -8. Add pcre_info(), to get the number of identifying subpatterns, the stored -options, and the first character, if set. - -9. Recognize C+ or C{n,m} where n >= 1 as providing a fixed starting character. - - -Version 0.91 10-Sep-97 ----------------------- - -1. PCRE was failing to diagnose unlimited repeats of subpatterns that could -match the empty string as in /(a*)*/. It was looping and ultimately crashing. - -2. PCRE was looping on encountering an indefinitely repeated back reference to -a subpattern that had matched an empty string, e.g. /(a|)\1*/. It now does what -Perl does - treats the match as successful. - -**** diff --git a/src/third_party/pcre-8.38/CheckMan b/src/third_party/pcre-8.38/CheckMan deleted file mode 100755 index 480d735481e..00000000000 --- a/src/third_party/pcre-8.38/CheckMan +++ /dev/null @@ -1,67 +0,0 @@ -#! /usr/bin/perl - -# A script to scan PCRE's man pages to check for typos in the control -# sequences. I use only a small set of the available repertoire, so it is -# straightforward to check that nothing else has slipped in by mistake. This -# script should be called in the doc directory. - -$yield = 0; - -while (scalar(@ARGV) > 0) - { - $line = 0; - $file = shift @ARGV; - - open (IN, $file) || die "Failed to open $file\n"; - - while (<IN>) - { - $line++; - if (/^\s*$/) - { - printf "Empty line $line of $file\n"; - $yield = 1; - } - elsif (/^\./) - { - if (!/^\.\s*$| - ^\.B\s+\S| - ^\.TH\s\S| - ^\.SH\s\S| - ^\.SS\s\S| - ^\.TP(?:\s?\d+)?\s*$| - ^\.SM\s*$| - ^\.br\s*$| - ^\.rs\s*$| - ^\.sp\s*$| - ^\.nf\s*$| - ^\.fi\s*$| - ^\.P\s*$| - ^\.PP\s*$| - ^\.\\"(?:\ HREF)?\s*$| - ^\.\\"\sHTML\s<a\shref="[^"]+?">\s*$| - ^\.\\"\sHTML\s<a\sname="[^"]+?"><\/a>\s*$| - ^\.\\"\s<\/a>\s*$| - ^\.\\"\sJOINSH\s*$| - ^\.\\"\sJOIN\s*$/x - ) - { - printf "Bad control line $line of $file\n"; - $yield = 1; - } - } - else - { - if (/\\[^ef]|\\f[^IBP]/) - { - printf "Bad backslash in line $line of $file\n"; - $yield = 1; - } - } - } - - close(IN); - } - -exit $yield; -# End diff --git a/src/third_party/pcre-8.38/CleanTxt b/src/third_party/pcre-8.38/CleanTxt deleted file mode 100755 index 1f42519c8d7..00000000000 --- a/src/third_party/pcre-8.38/CleanTxt +++ /dev/null @@ -1,113 +0,0 @@ -#! /usr/bin/perl -w - -# Script to take the output of nroff -man and remove all the backspacing and -# the page footers and the screen commands etc so that it is more usefully -# readable online. In fact, in the latest nroff, intermediate footers don't -# seem to be generated any more. - -$blankcount = 0; -$lastwascut = 0; -$firstheader = 1; - -# Input on STDIN; output to STDOUT. - -while (<STDIN>) - { - s/\x1b\[\d+m//g; # Remove screen controls "ESC [ number m" - s/.\x8//g; # Remove "char, backspace" - - # Handle header lines. Retain only the first one we encounter, but remove - # the blank line that follows. Any others (e.g. at end of document) and the - # following blank line are dropped. - - if (/^PCRE(\w*)\(([13])\)\s+PCRE\1\(\2\)$/) - { - if ($firstheader) - { - $firstheader = 0; - print; - $lastprinted = $_; - $lastwascut = 0; - } - $_=<STDIN>; # Remove a blank that follows - next; - } - - # Count runs of empty lines - - if (/^\s*$/) - { - $blankcount++; - $lastwascut = 0; - next; - } - - # If a chunk of lines has been cut out (page footer) and the next line - # has a different indentation, put back one blank line. - - if ($lastwascut && $blankcount < 1 && defined($lastprinted)) - { - ($a) = $lastprinted =~ /^(\s*)/; - ($b) = $_ =~ /^(\s*)/; - $blankcount++ if ($a ne $b); - } - - # We get here only when we have a non-blank line in hand. If it was preceded - # by 3 or more blank lines, read the next 3 lines and see if they are blank. - # If so, remove all 7 lines, and remember that we have just done a cut. - - if ($blankcount >= 3) - { - for ($i = 0; $i < 3; $i++) - { - $next[$i] = <STDIN>; - $next[$i] = "" if !defined $next[$i]; - $next[$i] =~ s/\x1b\[\d+m//g; # Remove screen controls "ESC [ number m" - $next[$i] =~ s/.\x8//g; # Remove "char, backspace" - } - - # Cut out chunks of the form <3 blanks><non-blank><3 blanks> - - if ($next[0] =~ /^\s*$/ && - $next[1] =~ /^\s*$/ && - $next[2] =~ /^\s*$/) - { - $blankcount -= 3; - $lastwascut = 1; - } - - # Otherwise output the saved blanks, the current, and the next three - # lines. Remember the last printed line. - - else - { - for ($i = 0; $i < $blankcount; $i++) { print "\n"; } - print; - for ($i = 0; $i < 3; $i++) - { - $next[$i] =~ s/.\x8//g; - print $next[$i]; - $lastprinted = $_; - } - $lastwascut = 0; - $blankcount = 0; - } - } - - # This non-blank line is not preceded by 3 or more blank lines. Output - # any blanks there are, and the line. Remember it. Force two blank lines - # before headings. - - else - { - $blankcount = 2 if /^\S/ && !/^Last updated/ && !/^Copyright/ && - defined($lastprinted); - for ($i = 0; $i < $blankcount; $i++) { print "\n"; } - print; - $lastprinted = $_; - $lastwascut = 0; - $blankcount = 0; - } - } - -# End diff --git a/src/third_party/pcre-8.38/Detrail b/src/third_party/pcre-8.38/Detrail deleted file mode 100755 index 1c5c7e9cae1..00000000000 --- a/src/third_party/pcre-8.38/Detrail +++ /dev/null @@ -1,35 +0,0 @@ -#!/usr/bin/perl - -# This is a script for removing trailing whitespace from lines in files that -# are listed on the command line. - -# This subroutine does the work for one file. - -sub detrail { -my($file) = $_[0]; -my($changed) = 0; -open(IN, "$file") || die "Can't open $file for input"; -@lines = <IN>; -close(IN); -foreach (@lines) - { - if (/\s+\n$/) - { - s/\s+\n$/\n/; - $changed = 1; - } - } -if ($changed) - { - open(OUT, ">$file") || die "Can't open $file for output"; - print OUT @lines; - close(OUT); - } -} - -# This is the main program - -$, = ""; # Output field separator -for ($i = 0; $i < @ARGV; $i++) { &detrail($ARGV[$i]); } - -# End diff --git a/src/third_party/pcre-8.38/HACKING b/src/third_party/pcre-8.38/HACKING deleted file mode 100644 index 691b7a14e50..00000000000 --- a/src/third_party/pcre-8.38/HACKING +++ /dev/null @@ -1,528 +0,0 @@ -Technical Notes about PCRE --------------------------- - -These are very rough technical notes that record potentially useful information -about PCRE internals. For information about testing PCRE, see the pcretest -documentation and the comment at the head of the RunTest file. - - -Historical note 1 ------------------ - -Many years ago I implemented some regular expression functions to an algorithm -suggested by Martin Richards. These were not Unix-like in form, and were quite -restricted in what they could do by comparison with Perl. The interesting part -about the algorithm was that the amount of space required to hold the compiled -form of an expression was known in advance. The code to apply an expression did -not operate by backtracking, as the original Henry Spencer code and current -Perl code does, but instead checked all possibilities simultaneously by keeping -a list of current states and checking all of them as it advanced through the -subject string. In the terminology of Jeffrey Friedl's book, it was a "DFA -algorithm", though it was not a traditional Finite State Machine (FSM). When -the pattern was all used up, all remaining states were possible matches, and -the one matching the longest subset of the subject string was chosen. This did -not necessarily maximize the individual wild portions of the pattern, as is -expected in Unix and Perl-style regular expressions. - - -Historical note 2 ------------------ - -By contrast, the code originally written by Henry Spencer (which was -subsequently heavily modified for Perl) compiles the expression twice: once in -a dummy mode in order to find out how much store will be needed, and then for -real. (The Perl version probably doesn't do this any more; I'm talking about -the original library.) The execution function operates by backtracking and -maximizing (or, optionally, minimizing in Perl) the amount of the subject that -matches individual wild portions of the pattern. This is an "NFA algorithm" in -Friedl's terminology. - - -OK, here's the real stuff -------------------------- - -For the set of functions that form the "basic" PCRE library (which are -unrelated to those mentioned above), I tried at first to invent an algorithm -that used an amount of store bounded by a multiple of the number of characters -in the pattern, to save on compiling time. However, because of the greater -complexity in Perl regular expressions, I couldn't do this. In any case, a -first pass through the pattern is helpful for other reasons. - - -Support for 16-bit and 32-bit data strings -------------------------------------------- - -From release 8.30, PCRE supports 16-bit as well as 8-bit data strings; and from -release 8.32, PCRE supports 32-bit data strings. The library can be compiled -in any combination of 8-bit, 16-bit or 32-bit modes, creating up to three -different libraries. In the description that follows, the word "short" is used -for a 16-bit data quantity, and the word "unit" is used for a quantity that is -a byte in 8-bit mode, a short in 16-bit mode and a 32-bit word in 32-bit mode. -However, so as not to over-complicate the text, the names of PCRE functions are -given in 8-bit form only. - - -Computing the memory requirement: how it was --------------------------------------------- - -Up to and including release 6.7, PCRE worked by running a very degenerate first -pass to calculate a maximum store size, and then a second pass to do the real -compile - which might use a bit less than the predicted amount of memory. The -idea was that this would turn out faster than the Henry Spencer code because -the first pass is degenerate and the second pass can just store stuff straight -into the vector, which it knows is big enough. - - -Computing the memory requirement: how it is -------------------------------------------- - -By the time I was working on a potential 6.8 release, the degenerate first pass -had become very complicated and hard to maintain. Indeed one of the early -things I did for 6.8 was to fix Yet Another Bug in the memory computation. Then -I had a flash of inspiration as to how I could run the real compile function in -a "fake" mode that enables it to compute how much memory it would need, while -actually only ever using a few hundred bytes of working memory, and without too -many tests of the mode that might slow it down. So I refactored the compiling -functions to work this way. This got rid of about 600 lines of source. It -should make future maintenance and development easier. As this was such a major -change, I never released 6.8, instead upping the number to 7.0 (other quite -major changes were also present in the 7.0 release). - -A side effect of this work was that the previous limit of 200 on the nesting -depth of parentheses was removed. However, there is a downside: pcre_compile() -runs more slowly than before (30% or more, depending on the pattern) because it -is doing a full analysis of the pattern. My hope was that this would not be a -big issue, and in the event, nobody has commented on it. - -At release 8.34, a limit on the nesting depth of parentheses was re-introduced -(default 250, settable at build time) so as to put a limit on the amount of -system stack used by pcre_compile(). This is a safety feature for environments -with small stacks where the patterns are provided by users. - - -Traditional matching function ------------------------------ - -The "traditional", and original, matching function is called pcre_exec(), and -it implements an NFA algorithm, similar to the original Henry Spencer algorithm -and the way that Perl works. This is not surprising, since it is intended to be -as compatible with Perl as possible. This is the function most users of PCRE -will use most of the time. From release 8.20, if PCRE is compiled with -just-in-time (JIT) support, and studying a compiled pattern with JIT is -successful, the JIT code is run instead of the normal pcre_exec() code, but the -result is the same. - - -Supplementary matching function -------------------------------- - -From PCRE 6.0, there is also a supplementary matching function called -pcre_dfa_exec(). This implements a DFA matching algorithm that searches -simultaneously for all possible matches that start at one point in the subject -string. (Going back to my roots: see Historical Note 1 above.) This function -intreprets the same compiled pattern data as pcre_exec(); however, not all the -facilities are available, and those that are do not always work in quite the -same way. See the user documentation for details. - -The algorithm that is used for pcre_dfa_exec() is not a traditional FSM, -because it may have a number of states active at one time. More work would be -needed at compile time to produce a traditional FSM where only one state is -ever active at once. I believe some other regex matchers work this way. JIT -support is not available for this kind of matching. - - -Changeable options ------------------- - -The /i, /m, or /s options (PCRE_CASELESS, PCRE_MULTILINE, PCRE_DOTALL, and some -others) may change in the middle of patterns. From PCRE 8.13, their processing -is handled entirely at compile time by generating different opcodes for the -different settings. The runtime functions do not need to keep track of an -options state any more. - - -Format of compiled patterns ---------------------------- - -The compiled form of a pattern is a vector of unsigned units (bytes in 8-bit -mode, shorts in 16-bit mode, 32-bit words in 32-bit mode), containing items of -variable length. The first unit in an item contains an opcode, and the length -of the item is either implicit in the opcode or contained in the data that -follows it. - -In many cases listed below, LINK_SIZE data values are specified for offsets -within the compiled pattern. LINK_SIZE always specifies a number of bytes. The -default value for LINK_SIZE is 2, but PCRE can be compiled to use 3-byte or -4-byte values for these offsets, although this impairs the performance. (3-byte -LINK_SIZE values are available only in 8-bit mode.) Specifing a LINK_SIZE -larger than 2 is necessary only when patterns whose compiled length is greater -than 64K are going to be processed. In this description, we assume the "normal" -compilation options. Data values that are counts (e.g. quantifiers) are two -bytes long in 8-bit mode (most significant byte first), or one unit in 16-bit -and 32-bit modes. - - -Opcodes with no following data ------------------------------- - -These items are all just one unit long - - OP_END end of pattern - OP_ANY match any one character other than newline - OP_ALLANY match any one character, including newline - OP_ANYBYTE match any single unit, even in UTF-8/16 mode - OP_SOD match start of data: \A - OP_SOM, start of match (subject + offset): \G - OP_SET_SOM, set start of match (\K) - OP_CIRC ^ (start of data) - OP_CIRCM ^ multiline mode (start of data or after newline) - OP_NOT_WORD_BOUNDARY \W - OP_WORD_BOUNDARY \w - OP_NOT_DIGIT \D - OP_DIGIT \d - OP_NOT_HSPACE \H - OP_HSPACE \h - OP_NOT_WHITESPACE \S - OP_WHITESPACE \s - OP_NOT_VSPACE \V - OP_VSPACE \v - OP_NOT_WORDCHAR \W - OP_WORDCHAR \w - OP_EODN match end of data or newline at end: \Z - OP_EOD match end of data: \z - OP_DOLL $ (end of data, or before final newline) - OP_DOLLM $ multiline mode (end of data or before newline) - OP_EXTUNI match an extended Unicode grapheme cluster - OP_ANYNL match any Unicode newline sequence - - OP_ASSERT_ACCEPT ) - OP_ACCEPT ) These are Perl 5.10's "backtracking control - OP_COMMIT ) verbs". If OP_ACCEPT is inside capturing - OP_FAIL ) parentheses, it may be preceded by one or more - OP_PRUNE ) OP_CLOSE, each followed by a count that - OP_SKIP ) indicates which parentheses must be closed. - OP_THEN ) - -OP_ASSERT_ACCEPT is used when (*ACCEPT) is encountered within an assertion. -This ends the assertion, not the entire pattern match. - - -Backtracking control verbs with optional data ---------------------------------------------- - -(*THEN) without an argument generates the opcode OP_THEN and no following data. -OP_MARK is followed by the mark name, preceded by a one-unit length, and -followed by a binary zero. For (*PRUNE), (*SKIP), and (*THEN) with arguments, -the opcodes OP_PRUNE_ARG, OP_SKIP_ARG, and OP_THEN_ARG are used, with the name -following in the same format as OP_MARK. - - -Matching literal characters ---------------------------- - -The OP_CHAR opcode is followed by a single character that is to be matched -casefully. For caseless matching, OP_CHARI is used. In UTF-8 or UTF-16 modes, -the character may be more than one unit long. In UTF-32 mode, characters -are always exactly one unit long. - -If there is only one character in a character class, OP_CHAR or OP_CHARI is -used for a positive class, and OP_NOT or OP_NOTI for a negative one (that is, -for something like [^a]). - - -Repeating single characters ---------------------------- - -The common repeats (*, +, ?), when applied to a single character, use the -following opcodes, which come in caseful and caseless versions: - - Caseful Caseless - OP_STAR OP_STARI - OP_MINSTAR OP_MINSTARI - OP_POSSTAR OP_POSSTARI - OP_PLUS OP_PLUSI - OP_MINPLUS OP_MINPLUSI - OP_POSPLUS OP_POSPLUSI - OP_QUERY OP_QUERYI - OP_MINQUERY OP_MINQUERYI - OP_POSQUERY OP_POSQUERYI - -Each opcode is followed by the character that is to be repeated. In ASCII mode, -these are two-unit items; in UTF-8 or UTF-16 modes, the length is variable; in -UTF-32 mode these are one-unit items. Those with "MIN" in their names are the -minimizing versions. Those with "POS" in their names are possessive versions. -Other repeats make use of these opcodes: - - Caseful Caseless - OP_UPTO OP_UPTOI - OP_MINUPTO OP_MINUPTOI - OP_POSUPTO OP_POSUPTOI - OP_EXACT OP_EXACTI - -Each of these is followed by a count and then the repeated character. OP_UPTO -matches from 0 to the given number. A repeat with a non-zero minimum and a -fixed maximum is coded as an OP_EXACT followed by an OP_UPTO (or OP_MINUPTO or -OPT_POSUPTO). - -Another set of matching repeating opcodes (called OP_NOTSTAR, OP_NOTSTARI, -etc.) are used for repeated, negated, single-character classes such as [^a]*. -The normal single-character opcodes (OP_STAR, etc.) are used for repeated -positive single-character classes. - - -Repeating character types -------------------------- - -Repeats of things like \d are done exactly as for single characters, except -that instead of a character, the opcode for the type is stored in the data -unit. The opcodes are: - - OP_TYPESTAR - OP_TYPEMINSTAR - OP_TYPEPOSSTAR - OP_TYPEPLUS - OP_TYPEMINPLUS - OP_TYPEPOSPLUS - OP_TYPEQUERY - OP_TYPEMINQUERY - OP_TYPEPOSQUERY - OP_TYPEUPTO - OP_TYPEMINUPTO - OP_TYPEPOSUPTO - OP_TYPEEXACT - - -Match by Unicode property -------------------------- - -OP_PROP and OP_NOTPROP are used for positive and negative matches of a -character by testing its Unicode property (the \p and \P escape sequences). -Each is followed by two units that encode the desired property as a type and a -value. The types are a set of #defines of the form PT_xxx, and the values are -enumerations of the form ucp_xx, defined in the ucp.h source file. The value is -relevant only for PT_GC (General Category), PT_PC (Particular Category), and -PT_SC (Script). - -Repeats of these items use the OP_TYPESTAR etc. set of opcodes, followed by -three units: OP_PROP or OP_NOTPROP, and then the desired property type and -value. - - -Character classes ------------------ - -If there is only one character in a class, OP_CHAR or OP_CHARI is used for a -positive class, and OP_NOT or OP_NOTI for a negative one (that is, for -something like [^a]). - -A set of repeating opcodes (called OP_NOTSTAR etc.) are used for repeated, -negated, single-character classes. The normal single-character opcodes -(OP_STAR, etc.) are used for repeated positive single-character classes. - -When there is more than one character in a class, and all the code points are -less than 256, OP_CLASS is used for a positive class, and OP_NCLASS for a -negative one. In either case, the opcode is followed by a 32-byte (16-short, -8-word) bit map containing a 1 bit for every character that is acceptable. The -bits are counted from the least significant end of each unit. In caseless mode, -bits for both cases are set. - -The reason for having both OP_CLASS and OP_NCLASS is so that, in UTF-8/16/32 -mode, subject characters with values greater than 255 can be handled correctly. -For OP_CLASS they do not match, whereas for OP_NCLASS they do. - -For classes containing characters with values greater than 255 or that contain -\p or \P, OP_XCLASS is used. It optionally uses a bit map if any code points -are less than 256, followed by a list of pairs (for a range) and single -characters. In caseless mode, both cases are explicitly listed. - -OP_XCLASS is followed by a unit containing flag bits: XCL_NOT indicates that -this is a negative class, and XCL_MAP indicates that a bit map is present. -There follows the bit map, if XCL_MAP is set, and then a sequence of items -coded as follows: - - XCL_END marks the end of the list - XCL_SINGLE one character follows - XCL_RANGE two characters follow - XCL_PROP a Unicode property (type, value) follows - XCL_NOTPROP a Unicode property (type, value) follows - -If a range starts with a code point less than 256 and ends with one greater -than 256, an XCL_RANGE item is used, without setting any bits in the bit map. -This means that if no other items in the class set bits in the map, a map is -not needed. - - -Back references ---------------- - -OP_REF (caseful) or OP_REFI (caseless) is followed by a count containing the -reference number if the reference is to a unique capturing group (either by -number or by name). When named groups are used, there may be more than one -group with the same name. In this case, a reference by name generates OP_DNREF -or OP_DNREFI. These are followed by two counts: the index (not the byte offset) -in the group name table of the first entry for the requred name, followed by -the number of groups with the same name. - - -Repeating character classes and back references ------------------------------------------------ - -Single-character classes are handled specially (see above). This section -applies to other classes and also to back references. In both cases, the repeat -information follows the base item. The matching code looks at the following -opcode to see if it is one of - - OP_CRSTAR - OP_CRMINSTAR - OP_CRPOSSTAR - OP_CRPLUS - OP_CRMINPLUS - OP_CRPOSPLUS - OP_CRQUERY - OP_CRMINQUERY - OP_CRPOSQUERY - OP_CRRANGE - OP_CRMINRANGE - OP_CRPOSRANGE - -All but the last three are single-unit items, with no data. The others are -followed by the minimum and maximum repeat counts. - - -Brackets and alternation ------------------------- - -A pair of non-capturing round brackets is wrapped round each expression at -compile time, so alternation always happens in the context of brackets. - -[Note for North Americans: "bracket" to some English speakers, including -myself, can be round, square, curly, or pointy. Hence this usage rather than -"parentheses".] - -Non-capturing brackets use the opcode OP_BRA. Originally PCRE was limited to 99 -capturing brackets and it used a different opcode for each one. From release -3.5, the limit was removed by putting the bracket number into the data for -higher-numbered brackets. From release 7.0 all capturing brackets are handled -this way, using the single opcode OP_CBRA. - -A bracket opcode is followed by LINK_SIZE bytes which give the offset to the -next alternative OP_ALT or, if there aren't any branches, to the matching -OP_KET opcode. Each OP_ALT is followed by LINK_SIZE bytes giving the offset to -the next one, or to the OP_KET opcode. For capturing brackets, the bracket -number is a count that immediately follows the offset. - -OP_KET is used for subpatterns that do not repeat indefinitely, and OP_KETRMIN -and OP_KETRMAX are used for indefinite repetitions, minimally or maximally -respectively (see below for possessive repetitions). All three are followed by -LINK_SIZE bytes giving (as a positive number) the offset back to the matching -bracket opcode. - -If a subpattern is quantified such that it is permitted to match zero times, it -is preceded by one of OP_BRAZERO, OP_BRAMINZERO, or OP_SKIPZERO. These are -single-unit opcodes that tell the matcher that skipping the following -subpattern entirely is a valid branch. In the case of the first two, not -skipping the pattern is also valid (greedy and non-greedy). The third is used -when a pattern has the quantifier {0,0}. It cannot be entirely discarded, -because it may be called as a subroutine from elsewhere in the regex. - -A subpattern with an indefinite maximum repetition is replicated in the -compiled data its minimum number of times (or once with OP_BRAZERO if the -minimum is zero), with the final copy terminating with OP_KETRMIN or OP_KETRMAX -as appropriate. - -A subpattern with a bounded maximum repetition is replicated in a nested -fashion up to the maximum number of times, with OP_BRAZERO or OP_BRAMINZERO -before each replication after the minimum, so that, for example, (abc){2,5} is -compiled as (abc)(abc)((abc)((abc)(abc)?)?)?, except that each bracketed group -has the same number. - -When a repeated subpattern has an unbounded upper limit, it is checked to see -whether it could match an empty string. If this is the case, the opcode in the -final replication is changed to OP_SBRA or OP_SCBRA. This tells the matcher -that it needs to check for matching an empty string when it hits OP_KETRMIN or -OP_KETRMAX, and if so, to break the loop. - - -Possessive brackets -------------------- - -When a repeated group (capturing or non-capturing) is marked as possessive by -the "+" notation, e.g. (abc)++, different opcodes are used. Their names all -have POS on the end, e.g. OP_BRAPOS instead of OP_BRA and OP_SCPBRPOS instead -of OP_SCBRA. The end of such a group is marked by OP_KETRPOS. If the minimum -repetition is zero, the group is preceded by OP_BRAPOSZERO. - - -Once-only (atomic) groups -------------------------- - -These are just like other subpatterns, but they start with the opcode -OP_ONCE or OP_ONCE_NC. The former is used when there are no capturing brackets -within the atomic group; the latter when there are. The distinction is needed -for when there is a backtrack to before the group - any captures within the -group must be reset, so it is necessary to retain backtracking points inside -the group even after it is complete in order to do this. When there are no -captures in an atomic group, all the backtracking can be discarded when it is -complete. This is more efficient, and also uses less stack. - -The check for matching an empty string in an unbounded repeat is handled -entirely at runtime, so there are just these two opcodes for atomic groups. - - -Assertions ----------- - -Forward assertions are also just like other subpatterns, but starting with one -of the opcodes OP_ASSERT or OP_ASSERT_NOT. Backward assertions use the opcodes -OP_ASSERTBACK and OP_ASSERTBACK_NOT, and the first opcode inside the assertion -is OP_REVERSE, followed by a count of the number of characters to move back the -pointer in the subject string. In ASCII mode, the count is a number of units, -but in UTF-8/16 mode each character may occupy more than one unit; in UTF-32 -mode each character occupies exactly one unit. A separate count is present in -each alternative of a lookbehind assertion, allowing them to have different -fixed lengths. - - -Conditional subpatterns ------------------------ - -These are like other subpatterns, but they start with the opcode OP_COND, or -OP_SCOND for one that might match an empty string in an unbounded repeat. If -the condition is a back reference, this is stored at the start of the -subpattern using the opcode OP_CREF followed by a count containing the -reference number, provided that the reference is to a unique capturing group. -If the reference was by name and there is more than one group with that name, -OP_DNCREF is used instead. It is followed by two counts: the index in the group -names table, and the number of groups with the same name. - -If the condition is "in recursion" (coded as "(?(R)"), or "in recursion of -group x" (coded as "(?(Rx)"), the group number is stored at the start of the -subpattern using the opcode OP_RREF (with a value of zero for "the whole -pattern") or OP_DNRREF (with data as for OP_DNCREF). For a DEFINE condition, -just the single unit OP_DEF is used (it has no associated data). Otherwise, a -conditional subpattern always starts with one of the assertions. - - -Recursion ---------- - -Recursion either matches the current regex, or some subexpression. The opcode -OP_RECURSE is followed by aLINK_SIZE value that is the offset to the starting -bracket from the start of the whole pattern. From release 6.5, OP_RECURSE is -automatically wrapped inside OP_ONCE brackets, because otherwise some patterns -broke it. OP_RECURSE is also used for "subroutine" calls, even though they are -not strictly a recursion. - - -Callout -------- - -OP_CALLOUT is followed by one unit of data that holds a callout number in the -range 0 to 254 for manual callouts, or 255 for an automatic callout. In both -cases there follows a count giving the offset in the pattern string to the -start of the following item, and another count giving the length of this item. -These values make is possible for pcretest to output useful tracing information -using automatic callouts. - -Philip Hazel -November 2013 diff --git a/src/third_party/pcre-8.38/INSTALL b/src/third_party/pcre-8.38/INSTALL deleted file mode 100644 index 2099840756e..00000000000 --- a/src/third_party/pcre-8.38/INSTALL +++ /dev/null @@ -1,370 +0,0 @@ -Installation Instructions -************************* - -Copyright (C) 1994-1996, 1999-2002, 2004-2013 Free Software Foundation, -Inc. - - Copying and distribution of this file, with or without modification, -are permitted in any medium without royalty provided the copyright -notice and this notice are preserved. This file is offered as-is, -without warranty of any kind. - -Basic Installation -================== - - Briefly, the shell command `./configure && make && make install' -should configure, build, and install this package. The following -more-detailed instructions are generic; see the `README' file for -instructions specific to this package. Some packages provide this -`INSTALL' file but do not implement all of the features documented -below. The lack of an optional feature in a given package is not -necessarily a bug. More recommendations for GNU packages can be found -in *note Makefile Conventions: (standards)Makefile Conventions. - - The `configure' shell script attempts to guess correct values for -various system-dependent variables used during compilation. It uses -those values to create a `Makefile' in each directory of the package. -It may also create one or more `.h' files containing system-dependent -definitions. Finally, it creates a shell script `config.status' that -you can run in the future to recreate the current configuration, and a -file `config.log' containing compiler output (useful mainly for -debugging `configure'). - - It can also use an optional file (typically called `config.cache' -and enabled with `--cache-file=config.cache' or simply `-C') that saves -the results of its tests to speed up reconfiguring. Caching is -disabled by default to prevent problems with accidental use of stale -cache files. - - If you need to do unusual things to compile the package, please try -to figure out how `configure' could check whether to do them, and mail -diffs or instructions to the address given in the `README' so they can -be considered for the next release. If you are using the cache, and at -some point `config.cache' contains results you don't want to keep, you -may remove or edit it. - - The file `configure.ac' (or `configure.in') is used to create -`configure' by a program called `autoconf'. You need `configure.ac' if -you want to change it or regenerate `configure' using a newer version -of `autoconf'. - - The simplest way to compile this package is: - - 1. `cd' to the directory containing the package's source code and type - `./configure' to configure the package for your system. - - Running `configure' might take a while. While running, it prints - some messages telling which features it is checking for. - - 2. Type `make' to compile the package. - - 3. Optionally, type `make check' to run any self-tests that come with - the package, generally using the just-built uninstalled binaries. - - 4. Type `make install' to install the programs and any data files and - documentation. When installing into a prefix owned by root, it is - recommended that the package be configured and built as a regular - user, and only the `make install' phase executed with root - privileges. - - 5. Optionally, type `make installcheck' to repeat any self-tests, but - this time using the binaries in their final installed location. - This target does not install anything. Running this target as a - regular user, particularly if the prior `make install' required - root privileges, verifies that the installation completed - correctly. - - 6. You can remove the program binaries and object files from the - source code directory by typing `make clean'. To also remove the - files that `configure' created (so you can compile the package for - a different kind of computer), type `make distclean'. There is - also a `make maintainer-clean' target, but that is intended mainly - for the package's developers. If you use it, you may have to get - all sorts of other programs in order to regenerate files that came - with the distribution. - - 7. Often, you can also type `make uninstall' to remove the installed - files again. In practice, not all packages have tested that - uninstallation works correctly, even though it is required by the - GNU Coding Standards. - - 8. Some packages, particularly those that use Automake, provide `make - distcheck', which can by used by developers to test that all other - targets like `make install' and `make uninstall' work correctly. - This target is generally not run by end users. - -Compilers and Options -===================== - - Some systems require unusual options for compilation or linking that -the `configure' script does not know about. Run `./configure --help' -for details on some of the pertinent environment variables. - - You can give `configure' initial values for configuration parameters -by setting variables in the command line or in the environment. Here -is an example: - - ./configure CC=c99 CFLAGS=-g LIBS=-lposix - - *Note Defining Variables::, for more details. - -Compiling For Multiple Architectures -==================================== - - You can compile the package for more than one kind of computer at the -same time, by placing the object files for each architecture in their -own directory. To do this, you can use GNU `make'. `cd' to the -directory where you want the object files and executables to go and run -the `configure' script. `configure' automatically checks for the -source code in the directory that `configure' is in and in `..'. This -is known as a "VPATH" build. - - With a non-GNU `make', it is safer to compile the package for one -architecture at a time in the source code directory. After you have -installed the package for one architecture, use `make distclean' before -reconfiguring for another architecture. - - On MacOS X 10.5 and later systems, you can create libraries and -executables that work on multiple system types--known as "fat" or -"universal" binaries--by specifying multiple `-arch' options to the -compiler but only a single `-arch' option to the preprocessor. Like -this: - - ./configure CC="gcc -arch i386 -arch x86_64 -arch ppc -arch ppc64" \ - CXX="g++ -arch i386 -arch x86_64 -arch ppc -arch ppc64" \ - CPP="gcc -E" CXXCPP="g++ -E" - - This is not guaranteed to produce working output in all cases, you -may have to build one architecture at a time and combine the results -using the `lipo' tool if you have problems. - -Installation Names -================== - - By default, `make install' installs the package's commands under -`/usr/local/bin', include files under `/usr/local/include', etc. You -can specify an installation prefix other than `/usr/local' by giving -`configure' the option `--prefix=PREFIX', where PREFIX must be an -absolute file name. - - You can specify separate installation prefixes for -architecture-specific files and architecture-independent files. If you -pass the option `--exec-prefix=PREFIX' to `configure', the package uses -PREFIX as the prefix for installing programs and libraries. -Documentation and other data files still use the regular prefix. - - In addition, if you use an unusual directory layout you can give -options like `--bindir=DIR' to specify different values for particular -kinds of files. Run `configure --help' for a list of the directories -you can set and what kinds of files go in them. In general, the -default for these options is expressed in terms of `${prefix}', so that -specifying just `--prefix' will affect all of the other directory -specifications that were not explicitly provided. - - The most portable way to affect installation locations is to pass the -correct locations to `configure'; however, many packages provide one or -both of the following shortcuts of passing variable assignments to the -`make install' command line to change installation locations without -having to reconfigure or recompile. - - The first method involves providing an override variable for each -affected directory. For example, `make install -prefix=/alternate/directory' will choose an alternate location for all -directory configuration variables that were expressed in terms of -`${prefix}'. Any directories that were specified during `configure', -but not in terms of `${prefix}', must each be overridden at install -time for the entire installation to be relocated. The approach of -makefile variable overrides for each directory variable is required by -the GNU Coding Standards, and ideally causes no recompilation. -However, some platforms have known limitations with the semantics of -shared libraries that end up requiring recompilation when using this -method, particularly noticeable in packages that use GNU Libtool. - - The second method involves providing the `DESTDIR' variable. For -example, `make install DESTDIR=/alternate/directory' will prepend -`/alternate/directory' before all installation names. The approach of -`DESTDIR' overrides is not required by the GNU Coding Standards, and -does not work on platforms that have drive letters. On the other hand, -it does better at avoiding recompilation issues, and works well even -when some directory options were not specified in terms of `${prefix}' -at `configure' time. - -Optional Features -================= - - If the package supports it, you can cause programs to be installed -with an extra prefix or suffix on their names by giving `configure' the -option `--program-prefix=PREFIX' or `--program-suffix=SUFFIX'. - - Some packages pay attention to `--enable-FEATURE' options to -`configure', where FEATURE indicates an optional part of the package. -They may also pay attention to `--with-PACKAGE' options, where PACKAGE -is something like `gnu-as' or `x' (for the X Window System). The -`README' should mention any `--enable-' and `--with-' options that the -package recognizes. - - For packages that use the X Window System, `configure' can usually -find the X include and library files automatically, but if it doesn't, -you can use the `configure' options `--x-includes=DIR' and -`--x-libraries=DIR' to specify their locations. - - Some packages offer the ability to configure how verbose the -execution of `make' will be. For these packages, running `./configure ---enable-silent-rules' sets the default to minimal output, which can be -overridden with `make V=1'; while running `./configure ---disable-silent-rules' sets the default to verbose, which can be -overridden with `make V=0'. - -Particular systems -================== - - On HP-UX, the default C compiler is not ANSI C compatible. If GNU -CC is not installed, it is recommended to use the following options in -order to use an ANSI C compiler: - - ./configure CC="cc -Ae -D_XOPEN_SOURCE=500" - -and if that doesn't work, install pre-built binaries of GCC for HP-UX. - - HP-UX `make' updates targets which have the same time stamps as -their prerequisites, which makes it generally unusable when shipped -generated files such as `configure' are involved. Use GNU `make' -instead. - - On OSF/1 a.k.a. Tru64, some versions of the default C compiler cannot -parse its `<wchar.h>' header file. The option `-nodtk' can be used as -a workaround. If GNU CC is not installed, it is therefore recommended -to try - - ./configure CC="cc" - -and if that doesn't work, try - - ./configure CC="cc -nodtk" - - On Solaris, don't put `/usr/ucb' early in your `PATH'. This -directory contains several dysfunctional programs; working variants of -these programs are available in `/usr/bin'. So, if you need `/usr/ucb' -in your `PATH', put it _after_ `/usr/bin'. - - On Haiku, software installed for all users goes in `/boot/common', -not `/usr/local'. It is recommended to use the following options: - - ./configure --prefix=/boot/common - -Specifying the System Type -========================== - - There may be some features `configure' cannot figure out -automatically, but needs to determine by the type of machine the package -will run on. Usually, assuming the package is built to be run on the -_same_ architectures, `configure' can figure that out, but if it prints -a message saying it cannot guess the machine type, give it the -`--build=TYPE' option. TYPE can either be a short name for the system -type, such as `sun4', or a canonical name which has the form: - - CPU-COMPANY-SYSTEM - -where SYSTEM can have one of these forms: - - OS - KERNEL-OS - - See the file `config.sub' for the possible values of each field. If -`config.sub' isn't included in this package, then this package doesn't -need to know the machine type. - - If you are _building_ compiler tools for cross-compiling, you should -use the option `--target=TYPE' to select the type of system they will -produce code for. - - If you want to _use_ a cross compiler, that generates code for a -platform different from the build platform, you should specify the -"host" platform (i.e., that on which the generated programs will -eventually be run) with `--host=TYPE'. - -Sharing Defaults -================ - - If you want to set default values for `configure' scripts to share, -you can create a site shell script called `config.site' that gives -default values for variables like `CC', `cache_file', and `prefix'. -`configure' looks for `PREFIX/share/config.site' if it exists, then -`PREFIX/etc/config.site' if it exists. Or, you can set the -`CONFIG_SITE' environment variable to the location of the site script. -A warning: not all `configure' scripts look for a site script. - -Defining Variables -================== - - Variables not defined in a site shell script can be set in the -environment passed to `configure'. However, some packages may run -configure again during the build, and the customized values of these -variables may be lost. In order to avoid this problem, you should set -them in the `configure' command line, using `VAR=value'. For example: - - ./configure CC=/usr/local2/bin/gcc - -causes the specified `gcc' to be used as the C compiler (unless it is -overridden in the site shell script). - -Unfortunately, this technique does not work for `CONFIG_SHELL' due to -an Autoconf limitation. Until the limitation is lifted, you can use -this workaround: - - CONFIG_SHELL=/bin/bash ./configure CONFIG_SHELL=/bin/bash - -`configure' Invocation -====================== - - `configure' recognizes the following options to control how it -operates. - -`--help' -`-h' - Print a summary of all of the options to `configure', and exit. - -`--help=short' -`--help=recursive' - Print a summary of the options unique to this package's - `configure', and exit. The `short' variant lists options used - only in the top level, while the `recursive' variant lists options - also present in any nested packages. - -`--version' -`-V' - Print the version of Autoconf used to generate the `configure' - script, and exit. - -`--cache-file=FILE' - Enable the cache: use and save the results of the tests in FILE, - traditionally `config.cache'. FILE defaults to `/dev/null' to - disable caching. - -`--config-cache' -`-C' - Alias for `--cache-file=config.cache'. - -`--quiet' -`--silent' -`-q' - Do not print messages saying which checks are being made. To - suppress all normal output, redirect it to `/dev/null' (any error - messages will still be shown). - -`--srcdir=DIR' - Look for the package's source code in directory DIR. Usually - `configure' can determine that directory automatically. - -`--prefix=DIR' - Use DIR as the installation prefix. *note Installation Names:: - for more details, including other options available for fine-tuning - the installation locations. - -`--no-create' -`-n' - Run the configure checks, but stop before creating any output - files. - -`configure' also accepts some other, not widely useful, options. Run -`configure --help' for more details. diff --git a/src/third_party/pcre-8.38/LICENCE b/src/third_party/pcre-8.38/LICENCE deleted file mode 100644 index 9f6f98e477f..00000000000 --- a/src/third_party/pcre-8.38/LICENCE +++ /dev/null @@ -1,93 +0,0 @@ -PCRE LICENCE ------------- - -PCRE is a library of functions to support regular expressions whose syntax -and semantics are as close as possible to those of the Perl 5 language. - -Release 8 of PCRE is distributed under the terms of the "BSD" licence, as -specified below. The documentation for PCRE, supplied in the "doc" -directory, is distributed under the same terms as the software itself. The data -in the testdata directory is not copyrighted and is in the public domain. - -The basic library functions are written in C and are freestanding. Also -included in the distribution is a set of C++ wrapper functions, and a -just-in-time compiler that can be used to optimize pattern matching. These -are both optional features that can be omitted when the library is built. - - -THE BASIC LIBRARY FUNCTIONS ---------------------------- - -Written by: Philip Hazel -Email local part: ph10 -Email domain: cam.ac.uk - -University of Cambridge Computing Service, -Cambridge, England. - -Copyright (c) 1997-2015 University of Cambridge -All rights reserved. - - -PCRE JUST-IN-TIME COMPILATION SUPPORT -------------------------------------- - -Written by: Zoltan Herczeg -Email local part: hzmester -Emain domain: freemail.hu - -Copyright(c) 2010-2015 Zoltan Herczeg -All rights reserved. - - -STACK-LESS JUST-IN-TIME COMPILER --------------------------------- - -Written by: Zoltan Herczeg -Email local part: hzmester -Emain domain: freemail.hu - -Copyright(c) 2009-2015 Zoltan Herczeg -All rights reserved. - - -THE C++ WRAPPER FUNCTIONS -------------------------- - -Contributed by: Google Inc. - -Copyright (c) 2007-2012, Google Inc. -All rights reserved. - - -THE "BSD" LICENCE ------------------ - -Redistribution and use in source and binary forms, with or without -modification, are permitted provided that the following conditions are met: - - * Redistributions of source code must retain the above copyright notice, - this list of conditions and the following disclaimer. - - * Redistributions in binary form must reproduce the above copyright - notice, this list of conditions and the following disclaimer in the - documentation and/or other materials provided with the distribution. - - * Neither the name of the University of Cambridge nor the name of Google - Inc. nor the names of their contributors may be used to endorse or - promote products derived from this software without specific prior - written permission. - -THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS" -AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE -IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE -ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR CONTRIBUTORS BE -LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR -CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF -SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS -INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN -CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) -ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE -POSSIBILITY OF SUCH DAMAGE. - -End diff --git a/src/third_party/pcre-8.38/NEWS b/src/third_party/pcre-8.38/NEWS deleted file mode 100644 index 7e42dcb3603..00000000000 --- a/src/third_party/pcre-8.38/NEWS +++ /dev/null @@ -1,716 +0,0 @@ -News about PCRE releases ------------------------- - -Release 8.38 23-November-2015 ------------------------------ - -This is bug-fix release. Note that this library (now called PCRE1) is now being -maintained for bug fixes only. New projects are advised to use the new PCRE2 -libraries. - - -Release 8.37 28-April-2015 --------------------------- - -This is bug-fix release. Note that this library (now called PCRE1) is now being -maintained for bug fixes only. New projects are advised to use the new PCRE2 -libraries. - - -Release 8.36 26-September-2014 ------------------------------- - -This is primarily a bug-fix release. However, in addition, the Unicode data -tables have been updated to Unicode 7.0.0. - - -Release 8.35 04-April-2014 --------------------------- - -There have been performance improvements for classes containing non-ASCII -characters and the "auto-possessification" feature has been extended. Other -minor improvements have been implemented and bugs fixed. There is a new callout -feature to enable applications to do detailed stack checks at compile time, to -avoid running out of stack for deeply nested parentheses. The JIT compiler has -been extended with experimental support for ARM-64, MIPS-64, and PPC-LE. - - -Release 8.34 15-December-2013 ------------------------------ - -As well as fixing the inevitable bugs, performance has been improved by -refactoring and extending the amount of "auto-possessification" that PCRE does. -Other notable changes: - -. Implemented PCRE_INFO_MATCH_EMPTY, which yields 1 if the pattern can match - an empty string. If it can, pcretest shows this in its information output. - -. A back reference to a named subpattern when there is more than one of the - same name now checks them in the order in which they appear in the pattern. - The first one that is set is used for the reference. Previously only the - first one was inspected. This change makes PCRE more compatible with Perl. - -. Unicode character properties were updated from Unicode 6.3.0. - -. The character VT has been added to the set of characters that match \s and - are generally treated as white space, following this same change in Perl - 5.18. There is now no difference between "Perl space" and "POSIX space". - -. Perl has changed its handling of \8 and \9. If there is no previously - encountered capturing group of those numbers, they are treated as the - literal characters 8 and 9 instead of a binary zero followed by the - literals. PCRE now does the same. - -. Following Perl, added \o{} to specify codepoints in octal, making it - possible to specify values greater than 0777 and also making them - unambiguous. - -. In UCP mode, \s was not matching two of the characters that Perl matches, - namely NEL (U+0085) and MONGOLIAN VOWEL SEPARATOR (U+180E), though they - were matched by \h. - -. Add JIT support for the 64 bit TileGX architecture. - -. Upgraded the handling of the POSIX classes [:graph:], [:print:], and - [:punct:] when PCRE_UCP is set so as to include the same characters as Perl - does in Unicode mode. - -. Perl no longer allows group names to start with digits, so I have made this - change also in PCRE. - -. Added support for [[:<:]] and [[:>:]] as used in the BSD POSIX library to - mean "start of word" and "end of word", respectively, as a transition aid. - - -Release 8.33 28-May-2013 --------------------------- - -A number of bugs are fixed, and some performance improvements have been made. -There are also some new features, of which these are the most important: - -. The behaviour of the backtracking verbs has been rationalized and - documented in more detail. - -. JIT now supports callouts and all of the backtracking verbs. - -. Unicode validation has been updated in the light of Unicode Corrigendum #9, - which points out that "non characters" are not "characters that may not - appear in Unicode strings" but rather "characters that are reserved for - internal use and have only local meaning". - -. (*LIMIT_MATCH=d) and (*LIMIT_RECURSION=d) have been added so that the - creator of a pattern can specify lower (but not higher) limits for the - matching process. - -. The PCRE_NEVER_UTF option is available to prevent pattern-writers from using - the (*UTF) feature, as this could be a security issue. - - -Release 8.32 30-November-2012 ------------------------------ - -This release fixes a number of bugs, but also has some new features. These are -the highlights: - -. There is now support for 32-bit character strings and UTF-32. Like the - 16-bit support, this is done by compiling a separate 32-bit library. - -. \X now matches a Unicode extended grapheme cluster. - -. Case-independent matching of Unicode characters that have more than one - "other case" now makes all three (or more) characters equivalent. This - applies, for example, to Greek Sigma, which has two lowercase versions. - -. Unicode character properties are updated to Unicode 6.2.0. - -. The EBCDIC support, which had decayed, has had a spring clean. - -. A number of JIT optimizations have been added, which give faster JIT - execution speed. In addition, a new direct interface to JIT execution is - available. This bypasses some of the sanity checks of pcre_exec() to give a - noticeable speed-up. - -. A number of issues in pcregrep have been fixed, making it more compatible - with GNU grep. In particular, --exclude and --include (and variants) apply - to all files now, not just those obtained from scanning a directory - recursively. In Windows environments, the default action for directories is - now "skip" instead of "read" (which provokes an error). - -. If the --only-matching (-o) option in pcregrep is specified multiple - times, each one causes appropriate output. For example, -o1 -o2 outputs the - substrings matched by the 1st and 2nd capturing parentheses. A separating - string can be specified by --om-separator (default empty). - -. When PCRE is built via Autotools using a version of gcc that has the - "visibility" feature, it is used to hide internal library functions that are - not part of the public API. - - -Release 8.31 06-July-2012 -------------------------- - -This is mainly a bug-fixing release, with a small number of developments: - -. The JIT compiler now supports partial matching and the (*MARK) and - (*COMMIT) verbs. - -. PCRE_INFO_MAXLOOKBEHIND can be used to find the longest lookbehind in a - pattern. - -. There should be a performance improvement when using the heap instead of the - stack for recursion. - -. pcregrep can now be linked with libedit as an alternative to libreadline. - -. pcregrep now has a --file-list option where the list of files to scan is - given as a file. - -. pcregrep now recognizes binary files and there are related options. - -. The Unicode tables have been updated to 6.1.0. - -As always, the full list of changes is in the ChangeLog file. - - -Release 8.30 04-February-2012 ------------------------------ - -Release 8.30 introduces a major new feature: support for 16-bit character -strings, compiled as a separate library. There are a few changes to the -8-bit library, in addition to some bug fixes. - -. The pcre_info() function, which has been obsolete for over 10 years, has - been removed. - -. When a compiled pattern was saved to a file and later reloaded on a host - with different endianness, PCRE used automatically to swap the bytes in some - of the data fields. With the advent of the 16-bit library, where more of this - swapping is needed, it is no longer done automatically. Instead, the bad - endianness is detected and a specific error is given. The user can then call - a new function called pcre_pattern_to_host_byte_order() (or an equivalent - 16-bit function) to do the swap. - -. In UTF-8 mode, the values 0xd800 to 0xdfff are not legal Unicode - code points and are now faulted. (They are the so-called "surrogates" - that are reserved for coding high values in UTF-16.) - - -Release 8.21 12-Dec-2011 ------------------------- - -This is almost entirely a bug-fix release. The only new feature is the ability -to obtain the size of the memory used by the JIT compiler. - - -Release 8.20 21-Oct-2011 ------------------------- - -The main change in this release is the inclusion of Zoltan Herczeg's -just-in-time compiler support, which can be accessed by building PCRE with ---enable-jit. Large performance benefits can be had in many situations. 8.20 -also fixes an unfortunate bug that was introduced in 8.13 as well as tidying up -a number of infelicities and differences from Perl. - - -Release 8.13 16-Aug-2011 ------------------------- - -This is mainly a bug-fix release. There has been a lot of internal refactoring. -The Unicode tables have been updated. The only new feature in the library is -the passing of *MARK information to callouts. Some additions have been made to -pcretest to make testing easier and more comprehensive. There is a new option -for pcregrep to adjust its internal buffer size. - - -Release 8.12 15-Jan-2011 ------------------------- - -This release fixes some bugs in pcregrep, one of which caused the tests to fail -on 64-bit big-endian systems. There are no changes to the code of the library. - - -Release 8.11 10-Dec-2010 ------------------------- - -A number of bugs in the library and in pcregrep have been fixed. As always, see -ChangeLog for details. The following are the non-bug-fix changes: - -. Added --match-limit and --recursion-limit to pcregrep. - -. Added an optional parentheses number to the -o and --only-matching options - of pcregrep. - -. Changed the way PCRE_PARTIAL_HARD affects the matching of $, \z, \Z, \b, and - \B. - -. Added PCRE_ERROR_SHORTUTF8 to make it possible to distinguish between a - bad UTF-8 sequence and one that is incomplete when using PCRE_PARTIAL_HARD. - -. Recognize (*NO_START_OPT) at the start of a pattern to set the PCRE_NO_ - START_OPTIMIZE option, which is now allowed at compile time - - -Release 8.10 25-Jun-2010 ------------------------- - -There are two major additions: support for (*MARK) and friends, and the option -PCRE_UCP, which changes the behaviour of \b, \d, \s, and \w (and their -opposites) so that they make use of Unicode properties. There are also a number -of lesser new features, and several bugs have been fixed. A new option, ---line-buffered, has been added to pcregrep, for use when it is connected to -pipes. - - -Release 8.02 19-Mar-2010 ------------------------- - -Another bug-fix release. - - -Release 8.01 19-Jan-2010 ------------------------- - -This is a bug-fix release. Several bugs in the code itself and some bugs and -infelicities in the build system have been fixed. - - -Release 8.00 19-Oct-09 ----------------------- - -Bugs have been fixed in the library and in pcregrep. There are also some -enhancements. Restrictions on patterns used for partial matching have been -removed, extra information is given for partial matches, the partial matching -process has been improved, and an option to make a partial match override a -full match is available. The "study" process has been enhanced by finding a -lower bound matching length. Groups with duplicate numbers may now have -duplicated names without the use of PCRE_DUPNAMES. However, they may not have -different names. The documentation has been revised to reflect these changes. -The version number has been expanded to 3 digits as it is clear that the rate -of change is not slowing down. - - -Release 7.9 11-Apr-09 ---------------------- - -Mostly bugfixes and tidies with just a couple of minor functional additions. - - -Release 7.8 05-Sep-08 ---------------------- - -More bug fixes, plus a performance improvement in Unicode character property -lookup. - - -Release 7.7 07-May-08 ---------------------- - -This is once again mainly a bug-fix release, but there are a couple of new -features. - - -Release 7.6 28-Jan-08 ---------------------- - -The main reason for having this release so soon after 7.5 is because it fixes a -potential buffer overflow problem in pcre_compile() when run in UTF-8 mode. In -addition, the CMake configuration files have been brought up to date. - - -Release 7.5 10-Jan-08 ---------------------- - -This is mainly a bug-fix release. However the ability to link pcregrep with -libz or libbz2 and the ability to link pcretest with libreadline have been -added. Also the --line-offsets and --file-offsets options were added to -pcregrep. - - -Release 7.4 21-Sep-07 ---------------------- - -The only change of specification is the addition of options to control whether -\R matches any Unicode line ending (the default) or just CR, LF, and CRLF. -Otherwise, the changes are bug fixes and a refactoring to reduce the number of -relocations needed in a shared library. There have also been some documentation -updates, in particular, some more information about using CMake to build PCRE -has been added to the NON-UNIX-USE file. - - -Release 7.3 28-Aug-07 ---------------------- - -Most changes are bug fixes. Some that are not: - -1. There is some support for Perl 5.10's experimental "backtracking control - verbs" such as (*PRUNE). - -2. UTF-8 checking is now as per RFC 3629 instead of RFC 2279; this is more - restrictive in the strings it accepts. - -3. Checking for potential integer overflow has been made more dynamic, and as a - consequence there is no longer a hard limit on the size of a subpattern that - has a limited repeat count. - -4. When CRLF is a valid line-ending sequence, pcre_exec() and pcre_dfa_exec() - no longer advance by two characters instead of one when an unanchored match - fails at CRLF if there are explicit CR or LF matches within the pattern. - This gets rid of some anomalous effects that previously occurred. - -5. Some PCRE-specific settings for varying the newline options at the start of - a pattern have been added. - - -Release 7.2 19-Jun-07 ---------------------- - -WARNING: saved patterns that were compiled by earlier versions of PCRE must be -recompiled for use with 7.2 (necessitated by the addition of \K, \h, \H, \v, -and \V). - -Correction to the notes for 7.1: the note about shared libraries for Windows is -wrong. Previously, three libraries were built, but each could function -independently. For example, the pcreposix library also included all the -functions from the basic pcre library. The change is that the three libraries -are no longer independent. They are like the Unix libraries. To use the -pcreposix functions, for example, you need to link with both the pcreposix and -the basic pcre library. - -Some more features from Perl 5.10 have been added: - - (?-n) and (?+n) relative references for recursion and subroutines. - - (?(-n) and (?(+n) relative references as conditions. - - \k{name} and \g{name} are synonyms for \k<name>. - - \K to reset the start of the matched string; for example, (foo)\Kbar - matches bar preceded by foo, but only sets bar as the matched string. - - (?| introduces a group where the capturing parentheses in each alternative - start from the same number; for example, (?|(abc)|(xyz)) sets capturing - parentheses number 1 in both cases. - - \h, \H, \v, \V match horizontal and vertical whitespace, respectively. - - -Release 7.1 24-Apr-07 ---------------------- - -There is only one new feature in this release: a linebreak setting of -PCRE_NEWLINE_ANYCRLF. It is a cut-down version of PCRE_NEWLINE_ANY, which -recognizes only CRLF, CR, and LF as linebreaks. - -A few bugs are fixed (see ChangeLog for details), but the major change is a -complete re-implementation of the build system. This now has full Autotools -support and so is now "standard" in some sense. It should help with compiling -PCRE in a wide variety of environments. - -NOTE: when building shared libraries for Windows, three dlls are now built, -called libpcre, libpcreposix, and libpcrecpp. Previously, everything was -included in a single dll. - -Another important change is that the dftables auxiliary program is no longer -compiled and run at "make" time by default. Instead, a default set of character -tables (assuming ASCII coding) is used. If you want to use dftables to generate -the character tables as previously, add --enable-rebuild-chartables to the -"configure" command. You must do this if you are compiling PCRE to run on a -system that uses EBCDIC code. - -There is a discussion about character tables in the README file. The default is -not to use dftables so that that there is no problem when cross-compiling. - - -Release 7.0 19-Dec-06 ---------------------- - -This release has a new major number because there have been some internal -upheavals to facilitate the addition of new optimizations and other facilities, -and to make subsequent maintenance and extension easier. Compilation is likely -to be a bit slower, but there should be no major effect on runtime performance. -Previously compiled patterns are NOT upwards compatible with this release. If -you have saved compiled patterns from a previous release, you will have to -re-compile them. Important changes that are visible to users are: - -1. The Unicode property tables have been updated to Unicode 5.0.0, which adds - some more scripts. - -2. The option PCRE_NEWLINE_ANY causes PCRE to recognize any Unicode newline - sequence as a newline. - -3. The \R escape matches a single Unicode newline sequence as a single unit. - -4. New features that will appear in Perl 5.10 are now in PCRE. These include - alternative Perl syntax for named parentheses, and Perl syntax for - recursion. - -5. The C++ wrapper interface has been extended by the addition of a - QuoteMeta function and the ability to allow copy construction and - assignment. - -For a complete list of changes, see the ChangeLog file. - - -Release 6.7 04-Jul-06 ---------------------- - -The main additions to this release are the ability to use the same name for -multiple sets of parentheses, and support for CRLF line endings in both the -library and pcregrep (and in pcretest for testing). - -Thanks to Ian Taylor, the stack usage for many kinds of pattern has been -significantly reduced for certain subject strings. - - -Release 6.5 01-Feb-06 ---------------------- - -Important changes in this release: - -1. A number of new features have been added to pcregrep. - -2. The Unicode property tables have been updated to Unicode 4.1.0, and the - supported properties have been extended with script names such as "Arabic", - and the derived properties "Any" and "L&". This has necessitated a change to - the interal format of compiled patterns. Any saved compiled patterns that - use \p or \P must be recompiled. - -3. The specification of recursion in patterns has been changed so that all - recursive subpatterns are automatically treated as atomic groups. Thus, for - example, (?R) is treated as if it were (?>(?R)). This is necessary because - otherwise there are situations where recursion does not work. - -See the ChangeLog for a complete list of changes, which include a number of bug -fixes and tidies. - - -Release 6.0 07-Jun-05 ---------------------- - -The release number has been increased to 6.0 because of the addition of several -major new pieces of functionality. - -A new function, pcre_dfa_exec(), which implements pattern matching using a DFA -algorithm, has been added. This has a number of advantages for certain cases, -though it does run more slowly, and lacks the ability to capture substrings. On -the other hand, it does find all matches, not just the first, and it works -better for partial matching. The pcrematching man page discusses the -differences. - -The pcretest program has been enhanced so that it can make use of the new -pcre_dfa_exec() matching function and the extra features it provides. - -The distribution now includes a C++ wrapper library. This is built -automatically if a C++ compiler is found. The pcrecpp man page discusses this -interface. - -The code itself has been re-organized into many more files, one for each -function, so it no longer requires everything to be linked in when static -linkage is used. As a consequence, some internal functions have had to have -their names exposed. These functions all have names starting with _pcre_. They -are undocumented, and are not intended for use by outside callers. - -The pcregrep program has been enhanced with new functionality such as -multiline-matching and options for output more matching context. See the -ChangeLog for a complete list of changes to the library and the utility -programs. - - -Release 5.0 13-Sep-04 ---------------------- - -The licence under which PCRE is released has been changed to the more -conventional "BSD" licence. - -In the code, some bugs have been fixed, and there are also some major changes -in this release (which is why I've increased the number to 5.0). Some changes -are internal rearrangements, and some provide a number of new facilities. The -new features are: - -1. There's an "automatic callout" feature that inserts callouts before every - item in the regex, and there's a new callout field that gives the position - in the pattern - useful for debugging and tracing. - -2. The extra_data structure can now be used to pass in a set of character - tables at exec time. This is useful if compiled regex are saved and re-used - at a later time when the tables may not be at the same address. If the - default internal tables are used, the pointer saved with the compiled - pattern is now set to NULL, which means that you don't need to do anything - special unless you are using custom tables. - -3. It is possible, with some restrictions on the content of the regex, to - request "partial" matching. A special return code is given if all of the - subject string matched part of the regex. This could be useful for testing - an input field as it is being typed. - -4. There is now some optional support for Unicode character properties, which - means that the patterns items such as \p{Lu} and \X can now be used. Only - the general category properties are supported. If PCRE is compiled with this - support, an additional 90K data structure is include, which increases the - size of the library dramatically. - -5. There is support for saving compiled patterns and re-using them later. - -6. There is support for running regular expressions that were compiled on a - different host with the opposite endianness. - -7. The pcretest program has been extended to accommodate the new features. - -The main internal rearrangement is that sequences of literal characters are no -longer handled as strings. Instead, each character is handled on its own. This -makes some UTF-8 handling easier, and makes the support of partial matching -possible. Compiled patterns containing long literal strings will be larger as a -result of this change; I hope that performance will not be much affected. - - -Release 4.5 01-Dec-03 ---------------------- - -Again mainly a bug-fix and tidying release, with only a couple of new features: - -1. It's possible now to compile PCRE so that it does not use recursive -function calls when matching. Instead it gets memory from the heap. This slows -things down, but may be necessary on systems with limited stacks. - -2. UTF-8 string checking has been tightened to reject overlong sequences and to -check that a starting offset points to the start of a character. Failure of the -latter returns a new error code: PCRE_ERROR_BADUTF8_OFFSET. - -3. PCRE can now be compiled for systems that use EBCDIC code. - - -Release 4.4 21-Aug-03 ---------------------- - -This is mainly a bug-fix and tidying release. The only new feature is that PCRE -checks UTF-8 strings for validity by default. There is an option to suppress -this, just in case anybody wants that teeny extra bit of performance. - - -Releases 4.1 - 4.3 ------------------- - -Sorry, I forgot about updating the NEWS file for these releases. Please take a -look at ChangeLog. - - -Release 4.0 17-Feb-03 ---------------------- - -There have been a lot of changes for the 4.0 release, adding additional -functionality and mending bugs. Below is a list of the highlights of the new -functionality. For full details of these features, please consult the -documentation. For a complete list of changes, see the ChangeLog file. - -1. Support for Perl's \Q...\E escapes. - -2. "Possessive quantifiers" ?+, *+, ++, and {,}+ which come from Sun's Java -package. They provide some syntactic sugar for simple cases of "atomic -grouping". - -3. Support for the \G assertion. It is true when the current matching position -is at the start point of the match. - -4. A new feature that provides some of the functionality that Perl provides -with (?{...}). The facility is termed a "callout". The way it is done in PCRE -is for the caller to provide an optional function, by setting pcre_callout to -its entry point. To get the function called, the regex must include (?C) at -appropriate points. - -5. Support for recursive calls to individual subpatterns. This makes it really -easy to get totally confused. - -6. Support for named subpatterns. The Python syntax (?P<name>...) is used to -name a group. - -7. Several extensions to UTF-8 support; it is now fairly complete. There is an -option for pcregrep to make it operate in UTF-8 mode. - -8. The single man page has been split into a number of separate man pages. -These also give rise to individual HTML pages which are put in a separate -directory. There is an index.html page that lists them all. Some hyperlinking -between the pages has been installed. - - -Release 3.5 15-Aug-01 ---------------------- - -1. The configuring system has been upgraded to use later versions of autoconf -and libtool. By default it builds both a shared and a static library if the OS -supports it. You can use --disable-shared or --disable-static on the configure -command if you want only one of them. - -2. The pcretest utility is now installed along with pcregrep because it is -useful for users (to test regexs) and by doing this, it automatically gets -relinked by libtool. The documentation has been turned into a man page, so -there are now .1, .txt, and .html versions in /doc. - -3. Upgrades to pcregrep: - (i) Added long-form option names like gnu grep. - (ii) Added --help to list all options with an explanatory phrase. - (iii) Added -r, --recursive to recurse into sub-directories. - (iv) Added -f, --file to read patterns from a file. - -4. Added --enable-newline-is-cr and --enable-newline-is-lf to the configure -script, to force use of CR or LF instead of \n in the source. On non-Unix -systems, the value can be set in config.h. - -5. The limit of 200 on non-capturing parentheses is a _nesting_ limit, not an -absolute limit. Changed the text of the error message to make this clear, and -likewise updated the man page. - -6. The limit of 99 on the number of capturing subpatterns has been removed. -The new limit is 65535, which I hope will not be a "real" limit. - - -Release 3.3 01-Aug-00 ---------------------- - -There is some support for UTF-8 character strings. This is incomplete and -experimental. The documentation describes what is and what is not implemented. -Otherwise, this is just a bug-fixing release. - - -Release 3.0 01-Feb-00 ---------------------- - -1. A "configure" script is now used to configure PCRE for Unix systems. It -builds a Makefile, a config.h file, and the pcre-config script. - -2. PCRE is built as a shared library by default. - -3. There is support for POSIX classes such as [:alpha:]. - -5. There is an experimental recursion feature. - ----------------------------------------------------------------------------- - IMPORTANT FOR THOSE UPGRADING FROM VERSIONS BEFORE 2.00 - -Please note that there has been a change in the API such that a larger -ovector is required at matching time, to provide some additional workspace. -The new man page has details. This change was necessary in order to support -some of the new functionality in Perl 5.005. - - IMPORTANT FOR THOSE UPGRADING FROM VERSION 2.00 - -Another (I hope this is the last!) change has been made to the API for the -pcre_compile() function. An additional argument has been added to make it -possible to pass over a pointer to character tables built in the current -locale by pcre_maketables(). To use the default tables, this new argument -should be passed as NULL. - - IMPORTANT FOR THOSE UPGRADING FROM VERSION 2.05 - -Yet another (and again I hope this really is the last) change has been made -to the API for the pcre_exec() function. An additional argument has been -added to make it possible to start the match other than at the start of the -subject string. This is important if there are lookbehinds. The new man -page has the details, but you just want to convert existing programs, all -you need to do is to stick in a new fifth argument to pcre_exec(), with a -value of zero. For example, change - - pcre_exec(pattern, extra, subject, length, options, ovec, ovecsize) -to - pcre_exec(pattern, extra, subject, length, 0, options, ovec, ovecsize) - -**** diff --git a/src/third_party/pcre-8.38/NON-AUTOTOOLS-BUILD b/src/third_party/pcre-8.38/NON-AUTOTOOLS-BUILD deleted file mode 100644 index 3910059106b..00000000000 --- a/src/third_party/pcre-8.38/NON-AUTOTOOLS-BUILD +++ /dev/null @@ -1,772 +0,0 @@ -Building PCRE without using autotools -------------------------------------- - -NOTE: This document relates to PCRE releases that use the original API, with -library names libpcre, libpcre16, and libpcre32. January 2015 saw the first -release of a new API, known as PCRE2, with release numbers starting at 10.00 -and library names libpcre2-8, libpcre2-16, and libpcre2-32. The old libraries -(now called PCRE1) are still being maintained for bug fixes, but there will be -no new development. New projects are advised to use the new PCRE2 libraries. - - -This document contains the following sections: - - General - Generic instructions for the PCRE C library - The C++ wrapper functions - Building for virtual Pascal - Stack size in Windows environments - Linking programs in Windows environments - Calling conventions in Windows environments - Comments about Win32 builds - Building PCRE on Windows with CMake - Use of relative paths with CMake on Windows - Testing with RunTest.bat - Building under Windows CE with Visual Studio 200x - Building under Windows with BCC5.5 - Building using Borland C++ Builder 2007 (CB2007) and higher - Building PCRE on OpenVMS - Building PCRE on Stratus OpenVOS - Building PCRE on native z/OS and z/VM - - -GENERAL - -I (Philip Hazel) have no experience of Windows or VMS sytems and how their -libraries work. The items in the PCRE distribution and Makefile that relate to -anything other than Linux systems are untested by me. - -There are some other comments and files (including some documentation in CHM -format) in the Contrib directory on the FTP site: - - ftp://ftp.csx.cam.ac.uk/pub/software/programming/pcre/Contrib - -The basic PCRE library consists entirely of code written in Standard C, and so -should compile successfully on any system that has a Standard C compiler and -library. The C++ wrapper functions are a separate issue (see below). - -The PCRE distribution includes a "configure" file for use by the configure/make -(autotools) build system, as found in many Unix-like environments. The README -file contains information about the options for "configure". - -There is also support for CMake, which some users prefer, especially in Windows -environments, though it can also be run in Unix-like environments. See the -section entitled "Building PCRE on Windows with CMake" below. - -Versions of config.h and pcre.h are distributed in the PCRE tarballs under the -names config.h.generic and pcre.h.generic. These are provided for those who -build PCRE without using "configure" or CMake. If you use "configure" or CMake, -the .generic versions are not used. - - -GENERIC INSTRUCTIONS FOR THE PCRE C LIBRARY - -The following are generic instructions for building the PCRE C library "by -hand". If you are going to use CMake, this section does not apply to you; you -can skip ahead to the CMake section. - - (1) Copy or rename the file config.h.generic as config.h, and edit the macro - settings that it contains to whatever is appropriate for your environment. - - In particular, you can alter the definition of the NEWLINE macro to - specify what character(s) you want to be interpreted as line terminators. - In an EBCDIC environment, you MUST change NEWLINE, because its default - value is 10, an ASCII LF. The usual EBCDIC newline character is 21 (0x15, - NL), though in some cases it may be 37 (0x25). - - When you compile any of the PCRE modules, you must specify -DHAVE_CONFIG_H - to your compiler so that config.h is included in the sources. - - An alternative approach is not to edit config.h, but to use -D on the - compiler command line to make any changes that you need to the - configuration options. In this case -DHAVE_CONFIG_H must not be set. - - NOTE: There have been occasions when the way in which certain parameters - in config.h are used has changed between releases. (In the configure/make - world, this is handled automatically.) When upgrading to a new release, - you are strongly advised to review config.h.generic before re-using what - you had previously. - - (2) Copy or rename the file pcre.h.generic as pcre.h. - - (3) EITHER: - Copy or rename file pcre_chartables.c.dist as pcre_chartables.c. - - OR: - Compile dftables.c as a stand-alone program (using -DHAVE_CONFIG_H if - you have set up config.h), and then run it with the single argument - "pcre_chartables.c". This generates a set of standard character tables - and writes them to that file. The tables are generated using the default - C locale for your system. If you want to use a locale that is specified - by LC_xxx environment variables, add the -L option to the dftables - command. You must use this method if you are building on a system that - uses EBCDIC code. - - The tables in pcre_chartables.c are defaults. The caller of PCRE can - specify alternative tables at run time. - - (4) Ensure that you have the following header files: - - pcre_internal.h - ucp.h - - (5) For an 8-bit library, compile the following source files, setting - -DHAVE_CONFIG_H as a compiler option if you have set up config.h with your - configuration, or else use other -D settings to change the configuration - as required. - - pcre_byte_order.c - pcre_chartables.c - pcre_compile.c - pcre_config.c - pcre_dfa_exec.c - pcre_exec.c - pcre_fullinfo.c - pcre_get.c - pcre_globals.c - pcre_jit_compile.c - pcre_maketables.c - pcre_newline.c - pcre_ord2utf8.c - pcre_refcount.c - pcre_string_utils.c - pcre_study.c - pcre_tables.c - pcre_ucd.c - pcre_valid_utf8.c - pcre_version.c - pcre_xclass.c - - Make sure that you include -I. in the compiler command (or equivalent for - an unusual compiler) so that all included PCRE header files are first - sought in the current directory. Otherwise you run the risk of picking up - a previously-installed file from somewhere else. - - Note that you must still compile pcre_jit_compile.c, even if you have not - defined SUPPORT_JIT in config.h, because when JIT support is not - configured, dummy functions are compiled. When JIT support IS configured, - pcre_jit_compile.c #includes sources from the sljit subdirectory, where - there should be 16 files, all of whose names begin with "sljit". - - (6) Now link all the compiled code into an object library in whichever form - your system keeps such libraries. This is the basic PCRE C 8-bit library. - If your system has static and shared libraries, you may have to do this - once for each type. - - (7) If you want to build a 16-bit library (as well as, or instead of the 8-bit - or 32-bit libraries) repeat steps 5-6 with the following files: - - pcre16_byte_order.c - pcre16_chartables.c - pcre16_compile.c - pcre16_config.c - pcre16_dfa_exec.c - pcre16_exec.c - pcre16_fullinfo.c - pcre16_get.c - pcre16_globals.c - pcre16_jit_compile.c - pcre16_maketables.c - pcre16_newline.c - pcre16_ord2utf16.c - pcre16_refcount.c - pcre16_string_utils.c - pcre16_study.c - pcre16_tables.c - pcre16_ucd.c - pcre16_utf16_utils.c - pcre16_valid_utf16.c - pcre16_version.c - pcre16_xclass.c - - (8) If you want to build a 32-bit library (as well as, or instead of the 8-bit - or 16-bit libraries) repeat steps 5-6 with the following files: - - pcre32_byte_order.c - pcre32_chartables.c - pcre32_compile.c - pcre32_config.c - pcre32_dfa_exec.c - pcre32_exec.c - pcre32_fullinfo.c - pcre32_get.c - pcre32_globals.c - pcre32_jit_compile.c - pcre32_maketables.c - pcre32_newline.c - pcre32_ord2utf32.c - pcre32_refcount.c - pcre32_string_utils.c - pcre32_study.c - pcre32_tables.c - pcre32_ucd.c - pcre32_utf32_utils.c - pcre32_valid_utf32.c - pcre32_version.c - pcre32_xclass.c - - (9) If you want to build the POSIX wrapper functions (which apply only to the - 8-bit library), ensure that you have the pcreposix.h file and then compile - pcreposix.c (remembering -DHAVE_CONFIG_H if necessary). Link the result - (on its own) as the pcreposix library. - -(10) The pcretest program can be linked with any combination of the 8-bit, - 16-bit and 32-bit libraries (depending on what you selected in config.h). - Compile pcretest.c and pcre_printint.c (again, don't forget - -DHAVE_CONFIG_H) and link them together with the appropriate library/ies. - If you compiled an 8-bit library, pcretest also needs the pcreposix - wrapper library unless you compiled it with -DNOPOSIX. - -(11) Run pcretest on the testinput files in the testdata directory, and check - that the output matches the corresponding testoutput files. There are - comments about what each test does in the section entitled "Testing PCRE" - in the README file. If you compiled more than one of the 8-bit, 16-bit and - 32-bit libraries, you need to run pcretest with the -16 option to do - 16-bit tests and with the -32 option to do 32-bit tests. - - Some tests are relevant only when certain build-time options are selected. - For example, test 4 is for UTF-8/UTF-16/UTF-32 support, and will not run - if you have built PCRE without it. See the comments at the start of each - testinput file. If you have a suitable Unix-like shell, the RunTest script - will run the appropriate tests for you. The command "RunTest list" will - output a list of all the tests. - - Note that the supplied files are in Unix format, with just LF characters - as line terminators. You may need to edit them to change this if your - system uses a different convention. If you are using Windows, you probably - should use the wintestinput3 file instead of testinput3 (and the - corresponding output file). This is a locale test; wintestinput3 sets the - locale to "french" rather than "fr_FR", and there some minor output - differences. - -(12) If you have built PCRE with SUPPORT_JIT, the JIT features will be tested - by the testdata files. However, you might also like to build and run - the freestanding JIT test program, pcre_jit_test.c. - -(13) If you want to use the pcregrep command, compile and link pcregrep.c; it - uses only the basic 8-bit PCRE library (it does not need the pcreposix - library). - - -THE C++ WRAPPER FUNCTIONS - -The PCRE distribution also contains some C++ wrapper functions and tests, -applicable to the 8-bit library, which were contributed by Google Inc. On a -system that can use "configure" and "make", the functions are automatically -built into a library called pcrecpp. It should be straightforward to compile -the .cc files manually on other systems. The files called xxx_unittest.cc are -test programs for each of the corresponding xxx.cc files. - - -BUILDING FOR VIRTUAL PASCAL - -A script for building PCRE using Borland's C++ compiler for use with VPASCAL -was contributed by Alexander Tokarev. Stefan Weber updated the script and added -additional files. The following files in the distribution are for building PCRE -for use with VP/Borland: makevp_c.txt, makevp_l.txt, makevp.bat, pcregexp.pas. - - -STACK SIZE IN WINDOWS ENVIRONMENTS - -The default processor stack size of 1Mb in some Windows environments is too -small for matching patterns that need much recursion. In particular, test 2 may -fail because of this. Normally, running out of stack causes a crash, but there -have been cases where the test program has just died silently. See your linker -documentation for how to increase stack size if you experience problems. The -Linux default of 8Mb is a reasonable choice for the stack, though even that can -be too small for some pattern/subject combinations. - -PCRE has a compile configuration option to disable the use of stack for -recursion so that heap is used instead. However, pattern matching is -significantly slower when this is done. There is more about stack usage in the -"pcrestack" documentation. - - -LINKING PROGRAMS IN WINDOWS ENVIRONMENTS - -If you want to statically link a program against a PCRE library in the form of -a non-dll .a file, you must define PCRE_STATIC before including pcre.h or -pcrecpp.h, otherwise the pcre_malloc() and pcre_free() exported functions will -be declared __declspec(dllimport), with unwanted results. - - -CALLING CONVENTIONS IN WINDOWS ENVIRONMENTS - -It is possible to compile programs to use different calling conventions using -MSVC. Search the web for "calling conventions" for more information. To make it -easier to change the calling convention for the exported functions in the -PCRE library, the macro PCRE_CALL_CONVENTION is present in all the external -definitions. It can be set externally when compiling (e.g. in CFLAGS). If it is -not set, it defaults to empty; the default calling convention is then used -(which is what is wanted most of the time). - - -COMMENTS ABOUT WIN32 BUILDS (see also "BUILDING PCRE ON WINDOWS WITH CMAKE") - -There are two ways of building PCRE using the "configure, make, make install" -paradigm on Windows systems: using MinGW or using Cygwin. These are not at all -the same thing; they are completely different from each other. There is also -support for building using CMake, which some users find a more straightforward -way of building PCRE under Windows. - -The MinGW home page (http://www.mingw.org/) says this: - - MinGW: A collection of freely available and freely distributable Windows - specific header files and import libraries combined with GNU toolsets that - allow one to produce native Windows programs that do not rely on any - 3rd-party C runtime DLLs. - -The Cygwin home page (http://www.cygwin.com/) says this: - - Cygwin is a Linux-like environment for Windows. It consists of two parts: - - . A DLL (cygwin1.dll) which acts as a Linux API emulation layer providing - substantial Linux API functionality - - . A collection of tools which provide Linux look and feel. - - The Cygwin DLL currently works with all recent, commercially released x86 32 - bit and 64 bit versions of Windows, with the exception of Windows CE. - -On both MinGW and Cygwin, PCRE should build correctly using: - - ./configure && make && make install - -This should create two libraries called libpcre and libpcreposix, and, if you -have enabled building the C++ wrapper, a third one called libpcrecpp. These are -independent libraries: when you link with libpcreposix or libpcrecpp you must -also link with libpcre, which contains the basic functions. (Some earlier -releases of PCRE included the basic libpcre functions in libpcreposix. This no -longer happens.) - -A user submitted a special-purpose patch that makes it easy to create -"pcre.dll" under mingw32 using the "msys" environment. It provides "pcre.dll" -as a special target. If you use this target, no other files are built, and in -particular, the pcretest and pcregrep programs are not built. An example of how -this might be used is: - - ./configure --enable-utf --disable-cpp CFLAGS="-03 -s"; make pcre.dll - -Using Cygwin's compiler generates libraries and executables that depend on -cygwin1.dll. If a library that is generated this way is distributed, -cygwin1.dll has to be distributed as well. Since cygwin1.dll is under the GPL -licence, this forces not only PCRE to be under the GPL, but also the entire -application. A distributor who wants to keep their own code proprietary must -purchase an appropriate Cygwin licence. - -MinGW has no such restrictions. The MinGW compiler generates a library or -executable that can run standalone on Windows without any third party dll or -licensing issues. - -But there is more complication: - -If a Cygwin user uses the -mno-cygwin Cygwin gcc flag, what that really does is -to tell Cygwin's gcc to use the MinGW gcc. Cygwin's gcc is only acting as a -front end to MinGW's gcc (if you install Cygwin's gcc, you get both Cygwin's -gcc and MinGW's gcc). So, a user can: - -. Build native binaries by using MinGW or by getting Cygwin and using - -mno-cygwin. - -. Build binaries that depend on cygwin1.dll by using Cygwin with the normal - compiler flags. - -The test files that are supplied with PCRE are in UNIX format, with LF -characters as line terminators. Unless your PCRE library uses a default newline -option that includes LF as a valid newline, it may be necessary to change the -line terminators in the test files to get some of the tests to work. - - -BUILDING PCRE ON WINDOWS WITH CMAKE - -CMake is an alternative configuration facility that can be used instead of -"configure". CMake creates project files (make files, solution files, etc.) -tailored to numerous development environments, including Visual Studio, -Borland, Msys, MinGW, NMake, and Unix. If possible, use short paths with no -spaces in the names for your CMake installation and your PCRE source and build -directories. - -The following instructions were contributed by a PCRE user. If they are not -followed exactly, errors may occur. In the event that errors do occur, it is -recommended that you delete the CMake cache before attempting to repeat the -CMake build process. In the CMake GUI, the cache can be deleted by selecting -"File > Delete Cache". - -1. Install the latest CMake version available from http://www.cmake.org/, and - ensure that cmake\bin is on your path. - -2. Unzip (retaining folder structure) the PCRE source tree into a source - directory such as C:\pcre. You should ensure your local date and time - is not earlier than the file dates in your source dir if the release is - very new. - -3. Create a new, empty build directory, preferably a subdirectory of the - source dir. For example, C:\pcre\pcre-xx\build. - -4. Run cmake-gui from the Shell envirornment of your build tool, for example, - Msys for Msys/MinGW or Visual Studio Command Prompt for VC/VC++. Do not try - to start Cmake from the Windows Start menu, as this can lead to errors. - -5. Enter C:\pcre\pcre-xx and C:\pcre\pcre-xx\build for the source and build - directories, respectively. - -6. Hit the "Configure" button. - -7. Select the particular IDE / build tool that you are using (Visual - Studio, MSYS makefiles, MinGW makefiles, etc.) - -8. The GUI will then list several configuration options. This is where - you can enable UTF-8 support or other PCRE optional features. - -9. Hit "Configure" again. The adjacent "Generate" button should now be - active. - -10. Hit "Generate". - -11. The build directory should now contain a usable build system, be it a - solution file for Visual Studio, makefiles for MinGW, etc. Exit from - cmake-gui and use the generated build system with your compiler or IDE. - E.g., for MinGW you can run "make", or for Visual Studio, open the PCRE - solution, select the desired configuration (Debug, or Release, etc.) and - build the ALL_BUILD project. - -12. If during configuration with cmake-gui you've elected to build the test - programs, you can execute them by building the test project. E.g., for - MinGW: "make test"; for Visual Studio build the RUN_TESTS project. The - most recent build configuration is targeted by the tests. A summary of - test results is presented. Complete test output is subsequently - available for review in Testing\Temporary under your build dir. - - -USE OF RELATIVE PATHS WITH CMAKE ON WINDOWS - -A PCRE user comments as follows: I thought that others may want to know the -current state of CMAKE_USE_RELATIVE_PATHS support on Windows. Here it is: - --- AdditionalIncludeDirectories is only partially modified (only the - first path - see below) --- Only some of the contained file paths are modified - shown below for - pcre.vcproj --- It properly modifies - -I am sure CMake people can fix that if they want to. Until then one will -need to replace existing absolute paths in project files with relative -paths manually (e.g. from VS) - relative to project file location. I did -just that before being told to try CMAKE_USE_RELATIVE_PATHS. Not a big -deal. - -AdditionalIncludeDirectories="E:\builds\pcre\build;E:\builds\pcre\pcre-7.5;" -AdditionalIncludeDirectories=".;E:\builds\pcre\pcre-7.5;" - -RelativePath="pcre.h" -RelativePath="pcre_chartables.c" -RelativePath="pcre_chartables.c.rule" - - -TESTING WITH RUNTEST.BAT - -If configured with CMake, building the test project ("make test" or building -ALL_TESTS in Visual Studio) creates (and runs) pcre_test.bat (and depending -on your configuration options, possibly other test programs) in the build -directory. Pcre_test.bat runs RunTest.Bat with correct source and exe paths. - -For manual testing with RunTest.bat, provided the build dir is a subdirectory -of the source directory: Open command shell window. Chdir to the location -of your pcretest.exe and pcregrep.exe programs. Call RunTest.bat with -"..\RunTest.Bat" or "..\..\RunTest.bat" as appropriate. - -To run only a particular test with RunTest.Bat provide a test number argument. - -Otherwise: - -1. Copy RunTest.bat into the directory where pcretest.exe and pcregrep.exe - have been created. - -2. Edit RunTest.bat to indentify the full or relative location of - the pcre source (wherein which the testdata folder resides), e.g.: - - set srcdir=C:\pcre\pcre-8.20 - -3. In a Windows command environment, chdir to the location of your bat and - exe programs. - -4. Run RunTest.bat. Test outputs will automatically be compared to expected - results, and discrepancies will be identified in the console output. - -To independently test the just-in-time compiler, run pcre_jit_test.exe. -To test pcrecpp, run pcrecpp_unittest.exe, pcre_stringpiece_unittest.exe and -pcre_scanner_unittest.exe. - - -BUILDING UNDER WINDOWS CE WITH VISUAL STUDIO 200x - -Vincent Richomme sent a zip archive of files to help with this process. They -can be found in the file "pcre-vsbuild.zip" in the Contrib directory of the FTP -site. - - -BUILDING UNDER WINDOWS WITH BCC5.5 - -Michael Roy sent these comments about building PCRE under Windows with BCC5.5: - -Some of the core BCC libraries have a version of PCRE from 1998 built in, which -can lead to pcre_exec() giving an erroneous PCRE_ERROR_NULL from a version -mismatch. I'm including an easy workaround below, if you'd like to include it -in the non-unix instructions: - -When linking a project with BCC5.5, pcre.lib must be included before any of the -libraries cw32.lib, cw32i.lib, cw32mt.lib, and cw32mti.lib on the command line. - - -BUILDING USING BORLAND C++ BUILDER 2007 (CB2007) AND HIGHER - -A PCRE user sent these comments about this environment (see also the comment -from another user that follows them): - -The XE versions of C++ Builder come with a RegularExpressionsCore class which -contain a version of TPerlRegEx. However, direct use of the C PCRE library may -be desirable. - -The default makevp.bat, however, supplied with PCRE builds a version of PCRE -that is not usable with any version of C++ Builder because the compiler ships -with an embedded version of PCRE, version 2.01 from 1998! [See also the note -about BCC5.5 above.] If you want to use PCRE you'll need to rename the -functions (pcre_compile to pcre_compile_bcc, etc) or do as I have done and just -use the 16 bit versions. I'm using std::wstring everywhere anyway. Since the -embedded version of PCRE does not have the 16 bit function names, there is no -conflict. - -Building PCRE using a C++ Builder static library project file (recommended): - -1. Rename or remove pcre.h, pcreposi.h, and pcreposix.h from your C++ Builder -original include path. - -2. Download PCRE from pcre.org and extract to a directory. - -3. Rename pcre_chartables.c.dist to pcre_chartables.c, pcre.h.generic to -pcre.h, and config.h.generic to config.h. - -4. Edit pcre.h and pcre_config.c so that they include config.h. - -5. Edit config.h like so: - -Comment out the following lines: -#define PACKAGE "pcre" -#define PACKAGE_BUGREPORT "" -#define PACKAGE_NAME "PCRE" -#define PACKAGE_STRING "PCRE 8.32" -#define PACKAGE_TARNAME "pcre" -#define PACKAGE_URL "" -#define PACKAGE_VERSION "8.32" - -Add the following lines: -#ifndef SUPPORT_UTF -#define SUPPORT_UTF 100 // any value is fine -#endif - -#ifndef SUPPORT_UCP -#define SUPPORT_UCP 101 // any value is fine -#endif - -#ifndef SUPPORT_UCP -#define SUPPORT_PCRE16 102 // any value is fine -#endif - -#ifndef SUPPORT_UTF8 -#define SUPPORT_UTF8 103 // any value is fine -#endif - -6. Build a C++ Builder project using the IDE. Go to File / New / Other and -choose Static Library. You can name it pcre.cbproj or whatever. Now set your -paths by going to Project / Options. Set the Include path. Do this from the -"Base" option to apply to both Release and Debug builds. Now add the following -files to the project: - -pcre.h -pcre16_byte_order.c -pcre16_chartables.c -pcre16_compile.c -pcre16_config.c -pcre16_dfa_exec.c -pcre16_exec.c -pcre16_fullinfo.c -pcre16_get.c -pcre16_globals.c -pcre16_maketables.c -pcre16_newline.c -pcre16_ord2utf16.c -pcre16_printint.c -pcre16_refcount.c -pcre16_string_utils.c -pcre16_study.c -pcre16_tables.c -pcre16_ucd.c -pcre16_utf16_utils.c -pcre16_valid_utf16.c -pcre16_version.c -pcre16_xclass.c - -//Optional -pcre_version.c - -7. After compiling the .lib file, copy the .lib and header files to a project -you want to use PCRE with. Enjoy. - -Optional ... Building PCRE using the makevp.bat file: - -1. Edit makevp_c.txt and makevp_l.txt and change all the names to the 16 bit -versions. - -2. Edit makevp.bat and set the path to C++ Builder. Run makevp.bat. - -Another PCRE user added this comment: - -Another approach I successfully used for some years with BCB 5 and 6 was to -make sure that include and library paths of PCRE are configured before the -default paths of the IDE in the dialogs where one can manage those paths. -Afterwards one can open the project files using a text editor and manually add -the self created library for pcre itself, pcrecpp doesn't ship with the IDE, in -the library nodes where the IDE manages its own libraries to link against in -front of the IDE-own libraries. This way one can use the default PCRE function -names without getting access violations on runtime. - - <ALLLIB value="libpcre.lib $(LIBFILES) $(LIBRARIES) import32.lib cp32mt.lib"/> - - -BUILDING PCRE ON OPENVMS - -Stephen Hoffman sent the following, in December 2012: - -"Here <http://labs.hoffmanlabs.com/node/1847> is a very short write-up on the -OpenVMS port and here - -<http://labs.hoffmanlabs.com/labsnotes/pcre-vms-8_32.zip> - -is a zip with the OpenVMS files, and with one modified testing-related PCRE -file." This is a port of PCRE 8.32. - -Earlier, Dan Mooney sent the following comments about building PCRE on OpenVMS. -They relate to an older version of PCRE that used fewer source files, so the -exact commands will need changing. See the current list of source files above. - -"It was quite easy to compile and link the library. I don't have a formal -make file but the attached file [reproduced below] contains the OpenVMS DCL -commands I used to build the library. I had to add #define -POSIX_MALLOC_THRESHOLD 10 to pcre.h since it was not defined anywhere. - -The library was built on: -O/S: HP OpenVMS v7.3-1 -Compiler: Compaq C v6.5-001-48BCD -Linker: vA13-01 - -The test results did not match 100% due to the issues you mention in your -documentation regarding isprint(), iscntrl(), isgraph() and ispunct(). I -modified some of the character tables temporarily and was able to get the -results to match. Tests using the fr locale did not match since I don't have -that locale loaded. The study size was always reported to be 3 less than the -value in the standard test output files." - -========================= -$! This DCL procedure builds PCRE on OpenVMS -$! -$! I followed the instructions in the non-unix-use file in the distribution. -$! -$ COMPILE == "CC/LIST/NOMEMBER_ALIGNMENT/PREFIX_LIBRARY_ENTRIES=ALL_ENTRIES -$ COMPILE DFTABLES.C -$ LINK/EXE=DFTABLES.EXE DFTABLES.OBJ -$ RUN DFTABLES.EXE/OUTPUT=CHARTABLES.C -$ COMPILE MAKETABLES.C -$ COMPILE GET.C -$ COMPILE STUDY.C -$! I had to set POSIX_MALLOC_THRESHOLD to 10 in PCRE.H since the symbol -$! did not seem to be defined anywhere. -$! I edited pcre.h and added #DEFINE SUPPORT_UTF8 to enable UTF8 support. -$ COMPILE PCRE.C -$ LIB/CREATE PCRE MAKETABLES.OBJ, GET.OBJ, STUDY.OBJ, PCRE.OBJ -$! I had to set POSIX_MALLOC_THRESHOLD to 10 in PCRE.H since the symbol -$! did not seem to be defined anywhere. -$ COMPILE PCREPOSIX.C -$ LIB/CREATE PCREPOSIX PCREPOSIX.OBJ -$ COMPILE PCRETEST.C -$ LINK/EXE=PCRETEST.EXE PCRETEST.OBJ, PCRE/LIB, PCREPOSIX/LIB -$! C programs that want access to command line arguments must be -$! defined as a symbol -$ PCRETEST :== "$ SYS$ROADSUSERS:[DMOONEY.REGEXP]PCRETEST.EXE" -$! Arguments must be enclosed in quotes. -$ PCRETEST "-C" -$! Test results: -$! -$! The test results did not match 100%. The functions isprint(), iscntrl(), -$! isgraph() and ispunct() on OpenVMS must not produce the same results -$! as the system that built the test output files provided with the -$! distribution. -$! -$! The study size did not match and was always 3 less on OpenVMS. -$! -$! Locale could not be set to fr -$! -========================= - - -BUILDING PCRE ON STRATUS OPENVOS - -These notes on the port of PCRE to VOS (lightly edited) were supplied by -Ashutosh Warikoo, whose email address has the local part awarikoo and the -domain nse.co.in. The port was for version 7.9 in August 2009. - -1. Building PCRE - -I built pcre on OpenVOS Release 17.0.1at using GNU Tools 3.4a without any -problems. I used the following packages to build PCRE: - - ftp://ftp.stratus.com/pub/vos/posix/ga/posix.save.evf.gz - -Please read and follow the instructions that come with these packages. To start -the build of pcre, from the root of the package type: - - ./build.sh - -2. Installing PCRE - -Once you have successfully built PCRE, login to the SysAdmin group, switch to -the root user, and type - - [ !create_dir (master_disk)>usr --if needed ] - [ !create_dir (master_disk)>usr>local --if needed ] - !gmake install - -This installs PCRE and its man pages into /usr/local. You can add -(master_disk)>usr>local>bin to your command search paths, or if you are in -BASH, add /usr/local/bin to the PATH environment variable. - -4. Restrictions - -This port requires readline library optionally. However during the build I -faced some yet unexplored errors while linking with readline. As it was an -optional component I chose to disable it. - -5. Known Problems - -I ran the test suite, but you will have to be your own judge of whether this -command, and this port, suits your purposes. If you find any problems that -appear to be related to the port itself, please let me know. Please see the -build.log file in the root of the package also. - - -BUILDING PCRE ON NATIVE Z/OS AND Z/VM - -z/OS and z/VM are operating systems for mainframe computers, produced by IBM. -The character code used is EBCDIC, not ASCII or Unicode. In z/OS, UNIX APIs and -applications can be supported through UNIX System Services, and in such an -environment PCRE can be built in the same way as in other systems. However, in -native z/OS (without UNIX System Services) and in z/VM, special ports are -required. For details, please see this web site: - - http://www.zaconsultants.net - -You may download PCRE from WWW.CBTTAPE.ORG, file 882.  Everything, source and -executable, is in EBCDIC and native z/OS file formats and this is the -recommended download site. - -========================== -Last Updated: 25 June 2015 diff --git a/src/third_party/pcre-8.38/NON-UNIX-USE b/src/third_party/pcre-8.38/NON-UNIX-USE deleted file mode 100644 index a25546b6ff5..00000000000 --- a/src/third_party/pcre-8.38/NON-UNIX-USE +++ /dev/null @@ -1,7 +0,0 @@ -Compiling PCRE on non-Unix systems ----------------------------------- - -This has been renamed to better reflect its contents. Please see the file -NON-AUTOTOOLS-BUILD for details of how to build PCRE without using autotools. - -#### diff --git a/src/third_party/pcre-8.38/PrepareRelease b/src/third_party/pcre-8.38/PrepareRelease deleted file mode 100755 index 9891e08d67f..00000000000 --- a/src/third_party/pcre-8.38/PrepareRelease +++ /dev/null @@ -1,258 +0,0 @@ -#/bin/sh - -# Script to prepare the files for building a PCRE release. It does some -# processing of the documentation, detrails files, and creates pcre.h.generic -# and config.h.generic (for use by builders who can't run ./configure). - -# You must run this script before runnning "make dist". If its first argument -# is "doc", it stops after preparing the documentation. There are no other -# arguments. The script makes use of the following files: - -# 132html A Perl script that converts a .1 or .3 man page into HTML. It -# "knows" the relevant troff constructs that are used in the PCRE -# man pages. - -# CheckMan A Perl script that checks man pages for typos in the mark up. - -# CleanTxt A Perl script that cleans up the output of "nroff -man" by -# removing backspaces and other redundant text so as to produce -# a readable .txt file. - -# Detrail A Perl script that removes trailing spaces from files. - -# doc/index.html.src -# A file that is copied as index.html into the doc/html directory -# when the HTML documentation is built. It works like this so that -# doc/html can be deleted and re-created from scratch. - -# README & NON-AUTOTOOLS-BUILD -# These files are copied into the doc/html directory, with .txt -# extensions so that they can by hyperlinked from the HTML -# documentation, because some people just go to the HTML without -# looking for text files. - - -# First, sort out the documentation. Remove pcredemo.3 first because it won't -# pass the markup check (it is created below, using markup that none of the -# other pages use). - -cd doc -echo Processing documentation - -/bin/rm -f pcredemo.3 - -# Check the remaining man pages - -perl ../CheckMan *.1 *.3 -if [ $? != 0 ] ; then exit 1; fi - -# Make Text form of the documentation. It needs some mangling to make it -# tidy for online reading. Concatenate all the .3 stuff, but omit the -# individual function pages. - -cat <<End >pcre.txt ------------------------------------------------------------------------------ -This file contains a concatenation of the PCRE man pages, converted to plain -text format for ease of searching with a text editor, or for use on systems -that do not have a man page processor. The small individual files that give -synopses of each function in the library have not been included. Neither has -the pcredemo program. There are separate text files for the pcregrep and -pcretest commands. ------------------------------------------------------------------------------ - - -End - -echo "Making pcre.txt" -for file in pcre pcre16 pcre32 pcrebuild pcrematching pcreapi pcrecallout \ - pcrecompat pcrepattern pcresyntax pcreunicode pcrejit pcrepartial \ - pcreprecompile pcreperform pcreposix pcrecpp pcresample \ - pcrelimits pcrestack ; do - echo " Processing $file.3" - nroff -c -man $file.3 >$file.rawtxt - perl ../CleanTxt <$file.rawtxt >>pcre.txt - /bin/rm $file.rawtxt - echo "------------------------------------------------------------------------------" >>pcre.txt - if [ "$file" != "pcresample" ] ; then - echo " " >>pcre.txt - echo " " >>pcre.txt - fi -done - -# The three commands -for file in pcretest pcregrep pcre-config ; do - echo Making $file.txt - nroff -c -man $file.1 >$file.rawtxt - perl ../CleanTxt <$file.rawtxt >$file.txt - /bin/rm $file.rawtxt -done - - -# Make pcredemo.3 from the pcredemo.c source file - -echo "Making pcredemo.3" -perl <<"END" >pcredemo.3 - open(IN, "../pcredemo.c") || die "Failed to open pcredemo.c\n"; - open(OUT, ">pcredemo.3") || die "Failed to open pcredemo.3\n"; - print OUT ".\\\" Start example.\n" . - ".de EX\n" . - ". nr mE \\\\n(.f\n" . - ". nf\n" . - ". nh\n" . - ". ft CW\n" . - "..\n" . - ".\n" . - ".\n" . - ".\\\" End example.\n" . - ".de EE\n" . - ". ft \\\\n(mE\n" . - ". fi\n" . - ". hy \\\\n(HY\n" . - "..\n" . - ".\n" . - ".EX\n" ; - while (<IN>) - { - s/\\/\\e/g; - print OUT; - } - print OUT ".EE\n"; - close(IN); - close(OUT); -END -if [ $? != 0 ] ; then exit 1; fi - - -# Make HTML form of the documentation. - -echo "Making HTML documentation" -/bin/rm html/* -cp index.html.src html/index.html -cp ../README html/README.txt -cp ../NON-AUTOTOOLS-BUILD html/NON-AUTOTOOLS-BUILD.txt - -for file in *.1 ; do - base=`basename $file .1` - echo " Making $base.html" - perl ../132html -toc $base <$file >html/$base.html -done - -# Exclude table of contents for function summaries. It seems that expr -# forces an anchored regex. Also exclude them for small pages that have -# only one section. - -for file in *.3 ; do - base=`basename $file .3` - toc=-toc - if [ `expr $base : '.*_'` -ne 0 ] ; then toc="" ; fi - if [ "$base" = "pcresample" ] || \ - [ "$base" = "pcrestack" ] || \ - [ "$base" = "pcrecompat" ] || \ - [ "$base" = "pcrelimits" ] || \ - [ "$base" = "pcreperform" ] || \ - [ "$base" = "pcreunicode" ] ; then - toc="" - fi - echo " Making $base.html" - perl ../132html $toc $base <$file >html/$base.html - if [ $? != 0 ] ; then exit 1; fi -done - -# End of documentation processing; stop if only documentation required. - -cd .. -echo Documentation done -if [ "$1" = "doc" ] ; then exit; fi - -# These files are detrailed; do not detrail the test data because there may be -# significant trailing spaces. Do not detrail RunTest.bat, because it has CRLF -# line endings and the detrail script removes all trailing white space. The -# configure files are also omitted from the detrailing. We don't bother with -# those pcre[16|32]_xx files that just define COMPILE_PCRE16 and then #include the -# common file, because they aren't going to change. - -files="\ - Makefile.am \ - Makefile.in \ - configure.ac \ - README \ - LICENCE \ - COPYING \ - AUTHORS \ - NEWS \ - NON-UNIX-USE \ - NON-AUTOTOOLS-BUILD \ - INSTALL \ - 132html \ - CleanTxt \ - Detrail \ - ChangeLog \ - CMakeLists.txt \ - RunGrepTest \ - RunTest \ - pcre-config.in \ - libpcre.pc.in \ - libpcre16.pc.in \ - libpcre32.pc.in \ - libpcreposix.pc.in \ - libpcrecpp.pc.in \ - config.h.in \ - pcre_chartables.c.dist \ - pcredemo.c \ - pcregrep.c \ - pcretest.c \ - dftables.c \ - pcreposix.c \ - pcreposix.h \ - pcre.h.in \ - pcre_internal.h \ - pcre_byte_order.c \ - pcre_compile.c \ - pcre_config.c \ - pcre_dfa_exec.c \ - pcre_exec.c \ - pcre_fullinfo.c \ - pcre_get.c \ - pcre_globals.c \ - pcre_jit_compile.c \ - pcre_jit_test.c \ - pcre_maketables.c \ - pcre_newline.c \ - pcre_ord2utf8.c \ - pcre16_ord2utf16.c \ - pcre32_ord2utf32.c \ - pcre_printint.c \ - pcre_refcount.c \ - pcre_string_utils.c \ - pcre_study.c \ - pcre_tables.c \ - pcre_valid_utf8.c \ - pcre_version.c \ - pcre_xclass.c \ - pcre16_utf16_utils.c \ - pcre32_utf32_utils.c \ - pcre16_valid_utf16.c \ - pcre32_valid_utf32.c \ - pcre_scanner.cc \ - pcre_scanner.h \ - pcre_scanner_unittest.cc \ - pcrecpp.cc \ - pcrecpp.h \ - pcrecpparg.h.in \ - pcrecpp_unittest.cc \ - pcre_stringpiece.cc \ - pcre_stringpiece.h.in \ - pcre_stringpiece_unittest.cc \ - perltest.pl \ - ucp.h \ - makevp.bat \ - pcre.def \ - libpcre.def \ - libpcreposix.def" - -echo Detrailing -perl ./Detrail $files doc/p* doc/html/* - -echo Done - -#End diff --git a/src/third_party/pcre-8.38/README b/src/third_party/pcre-8.38/README deleted file mode 100644 index 4887ebf350e..00000000000 --- a/src/third_party/pcre-8.38/README +++ /dev/null @@ -1,1002 +0,0 @@ -README file for PCRE (Perl-compatible regular expression library) ------------------------------------------------------------------ - -NOTE: This set of files relates to PCRE releases that use the original API, -with library names libpcre, libpcre16, and libpcre32. January 2015 saw the -first release of a new API, known as PCRE2, with release numbers starting at -10.00 and library names libpcre2-8, libpcre2-16, and libpcre2-32. The old -libraries (now called PCRE1) are still being maintained for bug fixes, but -there will be no new development. New projects are advised to use the new PCRE2 -libraries. - - -The latest release of PCRE1 is always available in three alternative formats -from: - - ftp://ftp.csx.cam.ac.uk/pub/software/programming/pcre/pcre-xxx.tar.gz - ftp://ftp.csx.cam.ac.uk/pub/software/programming/pcre/pcre-xxx.tar.bz2 - ftp://ftp.csx.cam.ac.uk/pub/software/programming/pcre/pcre-xxx.zip - -There is a mailing list for discussion about the development of PCRE at -pcre-dev@exim.org. You can access the archives and subscribe or manage your -subscription here: - - https://lists.exim.org/mailman/listinfo/pcre-dev - -Please read the NEWS file if you are upgrading from a previous release. -The contents of this README file are: - - The PCRE APIs - Documentation for PCRE - Contributions by users of PCRE - Building PCRE on non-Unix-like systems - Building PCRE without using autotools - Building PCRE using autotools - Retrieving configuration information - Shared libraries - Cross-compiling using autotools - Using HP's ANSI C++ compiler (aCC) - Compiling in Tru64 using native compilers - Using Sun's compilers for Solaris - Using PCRE from MySQL - Making new tarballs - Testing PCRE - Character tables - File manifest - - -The PCRE APIs -------------- - -PCRE is written in C, and it has its own API. There are three sets of -functions, one for the 8-bit library, which processes strings of bytes, one for -the 16-bit library, which processes strings of 16-bit values, and one for the -32-bit library, which processes strings of 32-bit values. The distribution also -includes a set of C++ wrapper functions (see the pcrecpp man page for details), -courtesy of Google Inc., which can be used to call the 8-bit PCRE library from -C++. Other C++ wrappers have been created from time to time. See, for example: -https://github.com/YasserAsmi/regexp, which aims to be simple and similar in -style to the C API. - -The distribution also contains a set of C wrapper functions (again, just for -the 8-bit library) that are based on the POSIX regular expression API (see the -pcreposix man page). These end up in the library called libpcreposix. Note that -this just provides a POSIX calling interface to PCRE; the regular expressions -themselves still follow Perl syntax and semantics. The POSIX API is restricted, -and does not give full access to all of PCRE's facilities. - -The header file for the POSIX-style functions is called pcreposix.h. The -official POSIX name is regex.h, but I did not want to risk possible problems -with existing files of that name by distributing it that way. To use PCRE with -an existing program that uses the POSIX API, pcreposix.h will have to be -renamed or pointed at by a link. - -If you are using the POSIX interface to PCRE and there is already a POSIX regex -library installed on your system, as well as worrying about the regex.h header -file (as mentioned above), you must also take care when linking programs to -ensure that they link with PCRE's libpcreposix library. Otherwise they may pick -up the POSIX functions of the same name from the other library. - -One way of avoiding this confusion is to compile PCRE with the addition of --Dregcomp=PCREregcomp (and similarly for the other POSIX functions) to the -compiler flags (CFLAGS if you are using "configure" -- see below). This has the -effect of renaming the functions so that the names no longer clash. Of course, -you have to do the same thing for your applications, or write them using the -new names. - - -Documentation for PCRE ----------------------- - -If you install PCRE in the normal way on a Unix-like system, you will end up -with a set of man pages whose names all start with "pcre". The one that is just -called "pcre" lists all the others. In addition to these man pages, the PCRE -documentation is supplied in two other forms: - - 1. There are files called doc/pcre.txt, doc/pcregrep.txt, and - doc/pcretest.txt in the source distribution. The first of these is a - concatenation of the text forms of all the section 3 man pages except - the listing of pcredemo.c and those that summarize individual functions. - The other two are the text forms of the section 1 man pages for the - pcregrep and pcretest commands. These text forms are provided for ease of - scanning with text editors or similar tools. They are installed in - <prefix>/share/doc/pcre, where <prefix> is the installation prefix - (defaulting to /usr/local). - - 2. A set of files containing all the documentation in HTML form, hyperlinked - in various ways, and rooted in a file called index.html, is distributed in - doc/html and installed in <prefix>/share/doc/pcre/html. - -Users of PCRE have contributed files containing the documentation for various -releases in CHM format. These can be found in the Contrib directory of the FTP -site (see next section). - - -Contributions by users of PCRE ------------------------------- - -You can find contributions from PCRE users in the directory - - ftp://ftp.csx.cam.ac.uk/pub/software/programming/pcre/Contrib - -There is a README file giving brief descriptions of what they are. Some are -complete in themselves; others are pointers to URLs containing relevant files. -Some of this material is likely to be well out-of-date. Several of the earlier -contributions provided support for compiling PCRE on various flavours of -Windows (I myself do not use Windows). Nowadays there is more Windows support -in the standard distribution, so these contibutions have been archived. - -A PCRE user maintains downloadable Windows binaries of the pcregrep and -pcretest programs here: - - http://www.rexegg.com/pcregrep-pcretest.html - - -Building PCRE on non-Unix-like systems --------------------------------------- - -For a non-Unix-like system, please read the comments in the file -NON-AUTOTOOLS-BUILD, though if your system supports the use of "configure" and -"make" you may be able to build PCRE using autotools in the same way as for -many Unix-like systems. - -PCRE can also be configured using the GUI facility provided by CMake's -cmake-gui command. This creates Makefiles, solution files, etc. The file -NON-AUTOTOOLS-BUILD has information about CMake. - -PCRE has been compiled on many different operating systems. It should be -straightforward to build PCRE on any system that has a Standard C compiler and -library, because it uses only Standard C functions. - - -Building PCRE without using autotools -------------------------------------- - -The use of autotools (in particular, libtool) is problematic in some -environments, even some that are Unix or Unix-like. See the NON-AUTOTOOLS-BUILD -file for ways of building PCRE without using autotools. - - -Building PCRE using autotools ------------------------------ - -If you are using HP's ANSI C++ compiler (aCC), please see the special note -in the section entitled "Using HP's ANSI C++ compiler (aCC)" below. - -The following instructions assume the use of the widely used "configure; make; -make install" (autotools) process. - -To build PCRE on system that supports autotools, first run the "configure" -command from the PCRE distribution directory, with your current directory set -to the directory where you want the files to be created. This command is a -standard GNU "autoconf" configuration script, for which generic instructions -are supplied in the file INSTALL. - -Most commonly, people build PCRE within its own distribution directory, and in -this case, on many systems, just running "./configure" is sufficient. However, -the usual methods of changing standard defaults are available. For example: - -CFLAGS='-O2 -Wall' ./configure --prefix=/opt/local - -This command specifies that the C compiler should be run with the flags '-O2 --Wall' instead of the default, and that "make install" should install PCRE -under /opt/local instead of the default /usr/local. - -If you want to build in a different directory, just run "configure" with that -directory as current. For example, suppose you have unpacked the PCRE source -into /source/pcre/pcre-xxx, but you want to build it in /build/pcre/pcre-xxx: - -cd /build/pcre/pcre-xxx -/source/pcre/pcre-xxx/configure - -PCRE is written in C and is normally compiled as a C library. However, it is -possible to build it as a C++ library, though the provided building apparatus -does not have any features to support this. - -There are some optional features that can be included or omitted from the PCRE -library. They are also documented in the pcrebuild man page. - -. By default, both shared and static libraries are built. You can change this - by adding one of these options to the "configure" command: - - --disable-shared - --disable-static - - (See also "Shared libraries on Unix-like systems" below.) - -. By default, only the 8-bit library is built. If you add --enable-pcre16 to - the "configure" command, the 16-bit library is also built. If you add - --enable-pcre32 to the "configure" command, the 32-bit library is also built. - If you want only the 16-bit or 32-bit library, use --disable-pcre8 to disable - building the 8-bit library. - -. If you are building the 8-bit library and want to suppress the building of - the C++ wrapper library, you can add --disable-cpp to the "configure" - command. Otherwise, when "configure" is run without --disable-pcre8, it will - try to find a C++ compiler and C++ header files, and if it succeeds, it will - try to build the C++ wrapper. - -. If you want to include support for just-in-time compiling, which can give - large performance improvements on certain platforms, add --enable-jit to the - "configure" command. This support is available only for certain hardware - architectures. If you try to enable it on an unsupported architecture, there - will be a compile time error. - -. When JIT support is enabled, pcregrep automatically makes use of it, unless - you add --disable-pcregrep-jit to the "configure" command. - -. If you want to make use of the support for UTF-8 Unicode character strings in - the 8-bit library, or UTF-16 Unicode character strings in the 16-bit library, - or UTF-32 Unicode character strings in the 32-bit library, you must add - --enable-utf to the "configure" command. Without it, the code for handling - UTF-8, UTF-16 and UTF-8 is not included in the relevant library. Even - when --enable-utf is included, the use of a UTF encoding still has to be - enabled by an option at run time. When PCRE is compiled with this option, its - input can only either be ASCII or UTF-8/16/32, even when running on EBCDIC - platforms. It is not possible to use both --enable-utf and --enable-ebcdic at - the same time. - -. There are no separate options for enabling UTF-8, UTF-16 and UTF-32 - independently because that would allow ridiculous settings such as requesting - UTF-16 support while building only the 8-bit library. However, the option - --enable-utf8 is retained for backwards compatibility with earlier releases - that did not support 16-bit or 32-bit character strings. It is synonymous with - --enable-utf. It is not possible to configure one library with UTF support - and the other without in the same configuration. - -. If, in addition to support for UTF-8/16/32 character strings, you want to - include support for the \P, \p, and \X sequences that recognize Unicode - character properties, you must add --enable-unicode-properties to the - "configure" command. This adds about 30K to the size of the library (in the - form of a property table); only the basic two-letter properties such as Lu - are supported. - -. You can build PCRE to recognize either CR or LF or the sequence CRLF or any - of the preceding, or any of the Unicode newline sequences as indicating the - end of a line. Whatever you specify at build time is the default; the caller - of PCRE can change the selection at run time. The default newline indicator - is a single LF character (the Unix standard). You can specify the default - newline indicator by adding --enable-newline-is-cr or --enable-newline-is-lf - or --enable-newline-is-crlf or --enable-newline-is-anycrlf or - --enable-newline-is-any to the "configure" command, respectively. - - If you specify --enable-newline-is-cr or --enable-newline-is-crlf, some of - the standard tests will fail, because the lines in the test files end with - LF. Even if the files are edited to change the line endings, there are likely - to be some failures. With --enable-newline-is-anycrlf or - --enable-newline-is-any, many tests should succeed, but there may be some - failures. - -. By default, the sequence \R in a pattern matches any Unicode line ending - sequence. This is independent of the option specifying what PCRE considers to - be the end of a line (see above). However, the caller of PCRE can restrict \R - to match only CR, LF, or CRLF. You can make this the default by adding - --enable-bsr-anycrlf to the "configure" command (bsr = "backslash R"). - -. When called via the POSIX interface, PCRE uses malloc() to get additional - storage for processing capturing parentheses if there are more than 10 of - them in a pattern. You can increase this threshold by setting, for example, - - --with-posix-malloc-threshold=20 - - on the "configure" command. - -. PCRE has a counter that limits the depth of nesting of parentheses in a - pattern. This limits the amount of system stack that a pattern uses when it - is compiled. The default is 250, but you can change it by setting, for - example, - - --with-parens-nest-limit=500 - -. PCRE has a counter that can be set to limit the amount of resources it uses - when matching a pattern. If the limit is exceeded during a match, the match - fails. The default is ten million. You can change the default by setting, for - example, - - --with-match-limit=500000 - - on the "configure" command. This is just the default; individual calls to - pcre_exec() can supply their own value. There is more discussion on the - pcreapi man page. - -. There is a separate counter that limits the depth of recursive function calls - during a matching process. This also has a default of ten million, which is - essentially "unlimited". You can change the default by setting, for example, - - --with-match-limit-recursion=500000 - - Recursive function calls use up the runtime stack; running out of stack can - cause programs to crash in strange ways. There is a discussion about stack - sizes in the pcrestack man page. - -. The default maximum compiled pattern size is around 64K. You can increase - this by adding --with-link-size=3 to the "configure" command. In the 8-bit - library, PCRE then uses three bytes instead of two for offsets to different - parts of the compiled pattern. In the 16-bit library, --with-link-size=3 is - the same as --with-link-size=4, which (in both libraries) uses four-byte - offsets. Increasing the internal link size reduces performance. In the 32-bit - library, the only supported link size is 4. - -. You can build PCRE so that its internal match() function that is called from - pcre_exec() does not call itself recursively. Instead, it uses memory blocks - obtained from the heap via the special functions pcre_stack_malloc() and - pcre_stack_free() to save data that would otherwise be saved on the stack. To - build PCRE like this, use - - --disable-stack-for-recursion - - on the "configure" command. PCRE runs more slowly in this mode, but it may be - necessary in environments with limited stack sizes. This applies only to the - normal execution of the pcre_exec() function; if JIT support is being - successfully used, it is not relevant. Equally, it does not apply to - pcre_dfa_exec(), which does not use deeply nested recursion. There is a - discussion about stack sizes in the pcrestack man page. - -. For speed, PCRE uses four tables for manipulating and identifying characters - whose code point values are less than 256. By default, it uses a set of - tables for ASCII encoding that is part of the distribution. If you specify - - --enable-rebuild-chartables - - a program called dftables is compiled and run in the default C locale when - you obey "make". It builds a source file called pcre_chartables.c. If you do - not specify this option, pcre_chartables.c is created as a copy of - pcre_chartables.c.dist. See "Character tables" below for further information. - -. It is possible to compile PCRE for use on systems that use EBCDIC as their - character code (as opposed to ASCII/Unicode) by specifying - - --enable-ebcdic - - This automatically implies --enable-rebuild-chartables (see above). However, - when PCRE is built this way, it always operates in EBCDIC. It cannot support - both EBCDIC and UTF-8/16/32. There is a second option, --enable-ebcdic-nl25, - which specifies that the code value for the EBCDIC NL character is 0x25 - instead of the default 0x15. - -. In environments where valgrind is installed, if you specify - - --enable-valgrind - - PCRE will use valgrind annotations to mark certain memory regions as - unaddressable. This allows it to detect invalid memory accesses, and is - mostly useful for debugging PCRE itself. - -. In environments where the gcc compiler is used and lcov version 1.6 or above - is installed, if you specify - - --enable-coverage - - the build process implements a code coverage report for the test suite. The - report is generated by running "make coverage". If ccache is installed on - your system, it must be disabled when building PCRE for coverage reporting. - You can do this by setting the environment variable CCACHE_DISABLE=1 before - running "make" to build PCRE. There is more information about coverage - reporting in the "pcrebuild" documentation. - -. The pcregrep program currently supports only 8-bit data files, and so - requires the 8-bit PCRE library. It is possible to compile pcregrep to use - libz and/or libbz2, in order to read .gz and .bz2 files (respectively), by - specifying one or both of - - --enable-pcregrep-libz - --enable-pcregrep-libbz2 - - Of course, the relevant libraries must be installed on your system. - -. The default size (in bytes) of the internal buffer used by pcregrep can be - set by, for example: - - --with-pcregrep-bufsize=51200 - - The value must be a plain integer. The default is 20480. - -. It is possible to compile pcretest so that it links with the libreadline - or libedit libraries, by specifying, respectively, - - --enable-pcretest-libreadline or --enable-pcretest-libedit - - If this is done, when pcretest's input is from a terminal, it reads it using - the readline() function. This provides line-editing and history facilities. - Note that libreadline is GPL-licenced, so if you distribute a binary of - pcretest linked in this way, there may be licensing issues. These can be - avoided by linking with libedit (which has a BSD licence) instead. - - Enabling libreadline causes the -lreadline option to be added to the pcretest - build. In many operating environments with a sytem-installed readline - library this is sufficient. However, in some environments (e.g. if an - unmodified distribution version of readline is in use), it may be necessary - to specify something like LIBS="-lncurses" as well. This is because, to quote - the readline INSTALL, "Readline uses the termcap functions, but does not link - with the termcap or curses library itself, allowing applications which link - with readline the to choose an appropriate library." If you get error - messages about missing functions tgetstr, tgetent, tputs, tgetflag, or tgoto, - this is the problem, and linking with the ncurses library should fix it. - -The "configure" script builds the following files for the basic C library: - -. Makefile the makefile that builds the library -. config.h build-time configuration options for the library -. pcre.h the public PCRE header file -. pcre-config script that shows the building settings such as CFLAGS - that were set for "configure" -. libpcre.pc ) data for the pkg-config command -. libpcre16.pc ) -. libpcre32.pc ) -. libpcreposix.pc ) -. libtool script that builds shared and/or static libraries - -Versions of config.h and pcre.h are distributed in the PCRE tarballs under the -names config.h.generic and pcre.h.generic. These are provided for those who -have to built PCRE without using "configure" or CMake. If you use "configure" -or CMake, the .generic versions are not used. - -When building the 8-bit library, if a C++ compiler is found, the following -files are also built: - -. libpcrecpp.pc data for the pkg-config command -. pcrecpparg.h header file for calling PCRE via the C++ wrapper -. pcre_stringpiece.h header for the C++ "stringpiece" functions - -The "configure" script also creates config.status, which is an executable -script that can be run to recreate the configuration, and config.log, which -contains compiler output from tests that "configure" runs. - -Once "configure" has run, you can run "make". This builds the the libraries -libpcre, libpcre16 and/or libpcre32, and a test program called pcretest. If you -enabled JIT support with --enable-jit, a test program called pcre_jit_test is -built as well. - -If the 8-bit library is built, libpcreposix and the pcregrep command are also -built, and if a C++ compiler was found on your system, and you did not disable -it with --disable-cpp, "make" builds the C++ wrapper library, which is called -libpcrecpp, as well as some test programs called pcrecpp_unittest, -pcre_scanner_unittest, and pcre_stringpiece_unittest. - -The command "make check" runs all the appropriate tests. Details of the PCRE -tests are given below in a separate section of this document. - -You can use "make install" to install PCRE into live directories on your -system. The following are installed (file names are all relative to the -<prefix> that is set when "configure" is run): - - Commands (bin): - pcretest - pcregrep (if 8-bit support is enabled) - pcre-config - - Libraries (lib): - libpcre16 (if 16-bit support is enabled) - libpcre32 (if 32-bit support is enabled) - libpcre (if 8-bit support is enabled) - libpcreposix (if 8-bit support is enabled) - libpcrecpp (if 8-bit and C++ support is enabled) - - Configuration information (lib/pkgconfig): - libpcre16.pc - libpcre32.pc - libpcre.pc - libpcreposix.pc - libpcrecpp.pc (if C++ support is enabled) - - Header files (include): - pcre.h - pcreposix.h - pcre_scanner.h ) - pcre_stringpiece.h ) if C++ support is enabled - pcrecpp.h ) - pcrecpparg.h ) - - Man pages (share/man/man{1,3}): - pcregrep.1 - pcretest.1 - pcre-config.1 - pcre.3 - pcre*.3 (lots more pages, all starting "pcre") - - HTML documentation (share/doc/pcre/html): - index.html - *.html (lots more pages, hyperlinked from index.html) - - Text file documentation (share/doc/pcre): - AUTHORS - COPYING - ChangeLog - LICENCE - NEWS - README - pcre.txt (a concatenation of the man(3) pages) - pcretest.txt the pcretest man page - pcregrep.txt the pcregrep man page - pcre-config.txt the pcre-config man page - -If you want to remove PCRE from your system, you can run "make uninstall". -This removes all the files that "make install" installed. However, it does not -remove any directories, because these are often shared with other programs. - - -Retrieving configuration information ------------------------------------- - -Running "make install" installs the command pcre-config, which can be used to -recall information about the PCRE configuration and installation. For example: - - pcre-config --version - -prints the version number, and - - pcre-config --libs - -outputs information about where the library is installed. This command can be -included in makefiles for programs that use PCRE, saving the programmer from -having to remember too many details. - -The pkg-config command is another system for saving and retrieving information -about installed libraries. Instead of separate commands for each library, a -single command is used. For example: - - pkg-config --cflags pcre - -The data is held in *.pc files that are installed in a directory called -<prefix>/lib/pkgconfig. - - -Shared libraries ----------------- - -The default distribution builds PCRE as shared libraries and static libraries, -as long as the operating system supports shared libraries. Shared library -support relies on the "libtool" script which is built as part of the -"configure" process. - -The libtool script is used to compile and link both shared and static -libraries. They are placed in a subdirectory called .libs when they are newly -built. The programs pcretest and pcregrep are built to use these uninstalled -libraries (by means of wrapper scripts in the case of shared libraries). When -you use "make install" to install shared libraries, pcregrep and pcretest are -automatically re-built to use the newly installed shared libraries before being -installed themselves. However, the versions left in the build directory still -use the uninstalled libraries. - -To build PCRE using static libraries only you must use --disable-shared when -configuring it. For example: - -./configure --prefix=/usr/gnu --disable-shared - -Then run "make" in the usual way. Similarly, you can use --disable-static to -build only shared libraries. - - -Cross-compiling using autotools -------------------------------- - -You can specify CC and CFLAGS in the normal way to the "configure" command, in -order to cross-compile PCRE for some other host. However, you should NOT -specify --enable-rebuild-chartables, because if you do, the dftables.c source -file is compiled and run on the local host, in order to generate the inbuilt -character tables (the pcre_chartables.c file). This will probably not work, -because dftables.c needs to be compiled with the local compiler, not the cross -compiler. - -When --enable-rebuild-chartables is not specified, pcre_chartables.c is created -by making a copy of pcre_chartables.c.dist, which is a default set of tables -that assumes ASCII code. Cross-compiling with the default tables should not be -a problem. - -If you need to modify the character tables when cross-compiling, you should -move pcre_chartables.c.dist out of the way, then compile dftables.c by hand and -run it on the local host to make a new version of pcre_chartables.c.dist. -Then when you cross-compile PCRE this new version of the tables will be used. - - -Using HP's ANSI C++ compiler (aCC) ----------------------------------- - -Unless C++ support is disabled by specifying the "--disable-cpp" option of the -"configure" script, you must include the "-AA" option in the CXXFLAGS -environment variable in order for the C++ components to compile correctly. - -Also, note that the aCC compiler on PA-RISC platforms may have a defect whereby -needed libraries fail to get included when specifying the "-AA" compiler -option. If you experience unresolved symbols when linking the C++ programs, -use the workaround of specifying the following environment variable prior to -running the "configure" script: - - CXXLDFLAGS="-lstd_v2 -lCsup_v2" - - -Compiling in Tru64 using native compilers ------------------------------------------ - -The following error may occur when compiling with native compilers in the Tru64 -operating system: - - CXX libpcrecpp_la-pcrecpp.lo -cxx: Error: /usr/lib/cmplrs/cxx/V7.1-006/include/cxx/iosfwd, line 58: #error - directive: "cannot include iosfwd -- define __USE_STD_IOSTREAM to - override default - see section 7.1.2 of the C++ Using Guide" -#error "cannot include iosfwd -- define __USE_STD_IOSTREAM to override default -- see section 7.1.2 of the C++ Using Guide" - -This may be followed by other errors, complaining that 'namespace "std" has no -member'. The solution to this is to add the line - -#define __USE_STD_IOSTREAM 1 - -to the config.h file. - - -Using Sun's compilers for Solaris ---------------------------------- - -A user reports that the following configurations work on Solaris 9 sparcv9 and -Solaris 9 x86 (32-bit): - - Solaris 9 sparcv9: ./configure --disable-cpp CC=/bin/cc CFLAGS="-m64 -g" - Solaris 9 x86: ./configure --disable-cpp CC=/bin/cc CFLAGS="-g" - - -Using PCRE from MySQL ---------------------- - -On systems where both PCRE and MySQL are installed, it is possible to make use -of PCRE from within MySQL, as an alternative to the built-in pattern matching. -There is a web page that tells you how to do this: - - http://www.mysqludf.org/lib_mysqludf_preg/index.php - - -Making new tarballs -------------------- - -The command "make dist" creates three PCRE tarballs, in tar.gz, tar.bz2, and -zip formats. The command "make distcheck" does the same, but then does a trial -build of the new distribution to ensure that it works. - -If you have modified any of the man page sources in the doc directory, you -should first run the PrepareRelease script before making a distribution. This -script creates the .txt and HTML forms of the documentation from the man pages. - - -Testing PCRE ------------- - -To test the basic PCRE library on a Unix-like system, run the RunTest script. -There is another script called RunGrepTest that tests the options of the -pcregrep command. If the C++ wrapper library is built, three test programs -called pcrecpp_unittest, pcre_scanner_unittest, and pcre_stringpiece_unittest -are also built. When JIT support is enabled, another test program called -pcre_jit_test is built. - -Both the scripts and all the program tests are run if you obey "make check" or -"make test". For other environments, see the instructions in -NON-AUTOTOOLS-BUILD. - -The RunTest script runs the pcretest test program (which is documented in its -own man page) on each of the relevant testinput files in the testdata -directory, and compares the output with the contents of the corresponding -testoutput files. RunTest uses a file called testtry to hold the main output -from pcretest. Other files whose names begin with "test" are used as working -files in some tests. - -Some tests are relevant only when certain build-time options were selected. For -example, the tests for UTF-8/16/32 support are run only if --enable-utf was -used. RunTest outputs a comment when it skips a test. - -Many of the tests that are not skipped are run up to three times. The second -run forces pcre_study() to be called for all patterns except for a few in some -tests that are marked "never study" (see the pcretest program for how this is -done). If JIT support is available, the non-DFA tests are run a third time, -this time with a forced pcre_study() with the PCRE_STUDY_JIT_COMPILE option. -This testing can be suppressed by putting "nojit" on the RunTest command line. - -The entire set of tests is run once for each of the 8-bit, 16-bit and 32-bit -libraries that are enabled. If you want to run just one set of tests, call -RunTest with either the -8, -16 or -32 option. - -If valgrind is installed, you can run the tests under it by putting "valgrind" -on the RunTest command line. To run pcretest on just one or more specific test -files, give their numbers as arguments to RunTest, for example: - - RunTest 2 7 11 - -You can also specify ranges of tests such as 3-6 or 3- (meaning 3 to the -end), or a number preceded by ~ to exclude a test. For example: - - Runtest 3-15 ~10 - -This runs tests 3 to 15, excluding test 10, and just ~13 runs all the tests -except test 13. Whatever order the arguments are in, the tests are always run -in numerical order. - -You can also call RunTest with the single argument "list" to cause it to output -a list of tests. - -The first test file can be fed directly into the perltest.pl script to check -that Perl gives the same results. The only difference you should see is in the -first few lines, where the Perl version is given instead of the PCRE version. - -The second set of tests check pcre_fullinfo(), pcre_study(), -pcre_copy_substring(), pcre_get_substring(), pcre_get_substring_list(), error -detection, and run-time flags that are specific to PCRE, as well as the POSIX -wrapper API. It also uses the debugging flags to check some of the internals of -pcre_compile(). - -If you build PCRE with a locale setting that is not the standard C locale, the -character tables may be different (see next paragraph). In some cases, this may -cause failures in the second set of tests. For example, in a locale where the -isprint() function yields TRUE for characters in the range 128-255, the use of -[:isascii:] inside a character class defines a different set of characters, and -this shows up in this test as a difference in the compiled code, which is being -listed for checking. Where the comparison test output contains [\x00-\x7f] the -test will contain [\x00-\xff], and similarly in some other cases. This is not a -bug in PCRE. - -The third set of tests checks pcre_maketables(), the facility for building a -set of character tables for a specific locale and using them instead of the -default tables. The tests make use of the "fr_FR" (French) locale. Before -running the test, the script checks for the presence of this locale by running -the "locale" command. If that command fails, or if it doesn't include "fr_FR" -in the list of available locales, the third test cannot be run, and a comment -is output to say why. If running this test produces instances of the error - - ** Failed to set locale "fr_FR" - -in the comparison output, it means that locale is not available on your system, -despite being listed by "locale". This does not mean that PCRE is broken. - -[If you are trying to run this test on Windows, you may be able to get it to -work by changing "fr_FR" to "french" everywhere it occurs. Alternatively, use -RunTest.bat. The version of RunTest.bat included with PCRE 7.4 and above uses -Windows versions of test 2. More info on using RunTest.bat is included in the -document entitled NON-UNIX-USE.] - -The fourth and fifth tests check the UTF-8/16/32 support and error handling and -internal UTF features of PCRE that are not relevant to Perl, respectively. The -sixth and seventh tests do the same for Unicode character properties support. - -The eighth, ninth, and tenth tests check the pcre_dfa_exec() alternative -matching function, in non-UTF-8/16/32 mode, UTF-8/16/32 mode, and UTF-8/16/32 -mode with Unicode property support, respectively. - -The eleventh test checks some internal offsets and code size features; it is -run only when the default "link size" of 2 is set (in other cases the sizes -change) and when Unicode property support is enabled. - -The twelfth test is run only when JIT support is available, and the thirteenth -test is run only when JIT support is not available. They test some JIT-specific -features such as information output from pcretest about JIT compilation. - -The fourteenth, fifteenth, and sixteenth tests are run only in 8-bit mode, and -the seventeenth, eighteenth, and nineteenth tests are run only in 16/32-bit -mode. These are tests that generate different output in the two modes. They are -for general cases, UTF-8/16/32 support, and Unicode property support, -respectively. - -The twentieth test is run only in 16/32-bit mode. It tests some specific -16/32-bit features of the DFA matching engine. - -The twenty-first and twenty-second tests are run only in 16/32-bit mode, when -the link size is set to 2 for the 16-bit library. They test reloading -pre-compiled patterns. - -The twenty-third and twenty-fourth tests are run only in 16-bit mode. They are -for general cases, and UTF-16 support, respectively. - -The twenty-fifth and twenty-sixth tests are run only in 32-bit mode. They are -for general cases, and UTF-32 support, respectively. - - -Character tables ----------------- - -For speed, PCRE uses four tables for manipulating and identifying characters -whose code point values are less than 256. The final argument of the -pcre_compile() function is a pointer to a block of memory containing the -concatenated tables. A call to pcre_maketables() can be used to generate a set -of tables in the current locale. If the final argument for pcre_compile() is -passed as NULL, a set of default tables that is built into the binary is used. - -The source file called pcre_chartables.c contains the default set of tables. By -default, this is created as a copy of pcre_chartables.c.dist, which contains -tables for ASCII coding. However, if --enable-rebuild-chartables is specified -for ./configure, a different version of pcre_chartables.c is built by the -program dftables (compiled from dftables.c), which uses the ANSI C character -handling functions such as isalnum(), isalpha(), isupper(), islower(), etc. to -build the table sources. This means that the default C locale which is set for -your system will control the contents of these default tables. You can change -the default tables by editing pcre_chartables.c and then re-building PCRE. If -you do this, you should take care to ensure that the file does not get -automatically re-generated. The best way to do this is to move -pcre_chartables.c.dist out of the way and replace it with your customized -tables. - -When the dftables program is run as a result of --enable-rebuild-chartables, -it uses the default C locale that is set on your system. It does not pay -attention to the LC_xxx environment variables. In other words, it uses the -system's default locale rather than whatever the compiling user happens to have -set. If you really do want to build a source set of character tables in a -locale that is specified by the LC_xxx variables, you can run the dftables -program by hand with the -L option. For example: - - ./dftables -L pcre_chartables.c.special - -The first two 256-byte tables provide lower casing and case flipping functions, -respectively. The next table consists of three 32-byte bit maps which identify -digits, "word" characters, and white space, respectively. These are used when -building 32-byte bit maps that represent character classes for code points less -than 256. - -The final 256-byte table has bits indicating various character types, as -follows: - - 1 white space character - 2 letter - 4 decimal digit - 8 hexadecimal digit - 16 alphanumeric or '_' - 128 regular expression metacharacter or binary zero - -You should not alter the set of characters that contain the 128 bit, as that -will cause PCRE to malfunction. - - -File manifest -------------- - -The distribution should contain the files listed below. Where a file name is -given as pcre[16|32]_xxx it means that there are three files, one with the name -pcre_xxx, one with the name pcre16_xx, and a third with the name pcre32_xxx. - -(A) Source files of the PCRE library functions and their headers: - - dftables.c auxiliary program for building pcre_chartables.c - when --enable-rebuild-chartables is specified - - pcre_chartables.c.dist a default set of character tables that assume ASCII - coding; used, unless --enable-rebuild-chartables is - specified, by copying to pcre[16]_chartables.c - - pcreposix.c ) - pcre[16|32]_byte_order.c ) - pcre[16|32]_compile.c ) - pcre[16|32]_config.c ) - pcre[16|32]_dfa_exec.c ) - pcre[16|32]_exec.c ) - pcre[16|32]_fullinfo.c ) - pcre[16|32]_get.c ) sources for the functions in the library, - pcre[16|32]_globals.c ) and some internal functions that they use - pcre[16|32]_jit_compile.c ) - pcre[16|32]_maketables.c ) - pcre[16|32]_newline.c ) - pcre[16|32]_refcount.c ) - pcre[16|32]_string_utils.c ) - pcre[16|32]_study.c ) - pcre[16|32]_tables.c ) - pcre[16|32]_ucd.c ) - pcre[16|32]_version.c ) - pcre[16|32]_xclass.c ) - pcre_ord2utf8.c ) - pcre_valid_utf8.c ) - pcre16_ord2utf16.c ) - pcre16_utf16_utils.c ) - pcre16_valid_utf16.c ) - pcre32_utf32_utils.c ) - pcre32_valid_utf32.c ) - - pcre[16|32]_printint.c ) debugging function that is used by pcretest, - ) and can also be #included in pcre_compile() - - pcre.h.in template for pcre.h when built by "configure" - pcreposix.h header for the external POSIX wrapper API - pcre_internal.h header for internal use - sljit/* 16 files that make up the JIT compiler - ucp.h header for Unicode property handling - - config.h.in template for config.h, which is built by "configure" - - pcrecpp.h public header file for the C++ wrapper - pcrecpparg.h.in template for another C++ header file - pcre_scanner.h public header file for C++ scanner functions - pcrecpp.cc ) - pcre_scanner.cc ) source for the C++ wrapper library - - pcre_stringpiece.h.in template for pcre_stringpiece.h, the header for the - C++ stringpiece functions - pcre_stringpiece.cc source for the C++ stringpiece functions - -(B) Source files for programs that use PCRE: - - pcredemo.c simple demonstration of coding calls to PCRE - pcregrep.c source of a grep utility that uses PCRE - pcretest.c comprehensive test program - -(C) Auxiliary files: - - 132html script to turn "man" pages into HTML - AUTHORS information about the author of PCRE - ChangeLog log of changes to the code - CleanTxt script to clean nroff output for txt man pages - Detrail script to remove trailing spaces - HACKING some notes about the internals of PCRE - INSTALL generic installation instructions - LICENCE conditions for the use of PCRE - COPYING the same, using GNU's standard name - Makefile.in ) template for Unix Makefile, which is built by - ) "configure" - Makefile.am ) the automake input that was used to create - ) Makefile.in - NEWS important changes in this release - NON-UNIX-USE the previous name for NON-AUTOTOOLS-BUILD - NON-AUTOTOOLS-BUILD notes on building PCRE without using autotools - PrepareRelease script to make preparations for "make dist" - README this file - RunTest a Unix shell script for running tests - RunGrepTest a Unix shell script for pcregrep tests - aclocal.m4 m4 macros (generated by "aclocal") - config.guess ) files used by libtool, - config.sub ) used only when building a shared library - configure a configuring shell script (built by autoconf) - configure.ac ) the autoconf input that was used to build - ) "configure" and config.h - depcomp ) script to find program dependencies, generated by - ) automake - doc/*.3 man page sources for PCRE - doc/*.1 man page sources for pcregrep and pcretest - doc/index.html.src the base HTML page - doc/html/* HTML documentation - doc/pcre.txt plain text version of the man pages - doc/pcretest.txt plain text documentation of test program - doc/perltest.txt plain text documentation of Perl test program - install-sh a shell script for installing files - libpcre16.pc.in template for libpcre16.pc for pkg-config - libpcre32.pc.in template for libpcre32.pc for pkg-config - libpcre.pc.in template for libpcre.pc for pkg-config - libpcreposix.pc.in template for libpcreposix.pc for pkg-config - libpcrecpp.pc.in template for libpcrecpp.pc for pkg-config - ltmain.sh file used to build a libtool script - missing ) common stub for a few missing GNU programs while - ) installing, generated by automake - mkinstalldirs script for making install directories - perltest.pl Perl test program - pcre-config.in source of script which retains PCRE information - pcre_jit_test.c test program for the JIT compiler - pcrecpp_unittest.cc ) - pcre_scanner_unittest.cc ) test programs for the C++ wrapper - pcre_stringpiece_unittest.cc ) - testdata/testinput* test data for main library tests - testdata/testoutput* expected test results - testdata/grep* input and output for pcregrep tests - testdata/* other supporting test files - -(D) Auxiliary files for cmake support - - cmake/COPYING-CMAKE-SCRIPTS - cmake/FindPackageHandleStandardArgs.cmake - cmake/FindEditline.cmake - cmake/FindReadline.cmake - CMakeLists.txt - config-cmake.h.in - -(E) Auxiliary files for VPASCAL - - makevp.bat - makevp_c.txt - makevp_l.txt - pcregexp.pas - -(F) Auxiliary files for building PCRE "by hand" - - pcre.h.generic ) a version of the public PCRE header file - ) for use in non-"configure" environments - config.h.generic ) a version of config.h for use in non-"configure" - ) environments - -(F) Miscellaneous - - RunTest.bat a script for running tests under Windows - -Philip Hazel -Email local part: ph10 -Email domain: cam.ac.uk -Last updated: 10 February 2015 diff --git a/src/third_party/pcre-8.38/RunGrepTest b/src/third_party/pcre-8.38/RunGrepTest deleted file mode 100755 index a6e93d34892..00000000000 --- a/src/third_party/pcre-8.38/RunGrepTest +++ /dev/null @@ -1,584 +0,0 @@ -#! /bin/sh - -# Run pcregrep tests. The assumption is that the PCRE tests check the library -# itself. What we are checking here is the file handling and options that are -# supported by pcregrep. This script must be run in the build directory. - -# Set the C locale, so that sort(1) behaves predictably. - -LC_ALL=C -export LC_ALL - -# Remove any non-default colouring and aliases that the caller may have set. - -unset PCREGREP_COLOUR PCREGREP_COLOR -unset cp ls mv rm - -# Remember the current (build) directory, set the program to be tested, and -# valgrind settings when requested. - -builddir=`pwd` -pcregrep=$builddir/pcregrep - -valgrind= -while [ $# -gt 0 ] ; do - case $1 in - valgrind) valgrind="valgrind -q --leak-check=no --smc-check=all";; - *) echo "RunGrepTest: Unknown argument $1"; exit 1;; - esac - shift -done - -echo " " -pcregrep_version=`$pcregrep -V` -if [ "$valgrind" = "" ] ; then - echo "Testing $pcregrep_version" -else - echo "Testing $pcregrep_version using valgrind" -fi - -# Set up a suitable "diff" command for comparison. Some systems have a diff -# that lacks a -u option. Try to deal with this; better do the test for the -b -# option as well. - -cf="diff" -diff -b /dev/null /dev/null 2>/dev/null && cf="diff -b" -diff -u /dev/null /dev/null 2>/dev/null && cf="diff -u" -diff -ub /dev/null /dev/null 2>/dev/null && cf="diff -ub" - -# If this test is being run from "make check", $srcdir will be set. If not, set -# it to the current or parent directory, whichever one contains the test data. -# Subsequently, we run most of the pcregrep tests in the source directory so -# that the file names in the output are always the same. - -if [ -z "$srcdir" -o ! -d "$srcdir/testdata" ] ; then - if [ -d "./testdata" ] ; then - srcdir=. - elif [ -d "../testdata" ] ; then - srcdir=.. - else - echo "Cannot find the testdata directory" - exit 1 - fi -fi - -# Check for the availability of UTF-8 support - -./pcretest -C utf >/dev/null -utf8=$? - -echo "Testing pcregrep main features" - -echo "---------------------------- Test 1 ------------------------------" >testtrygrep -(cd $srcdir; $valgrind $pcregrep PATTERN ./testdata/grepinput) >>testtrygrep -echo "RC=$?" >>testtrygrep - -echo "---------------------------- Test 2 ------------------------------" >>testtrygrep -(cd $srcdir; $valgrind $pcregrep '^PATTERN' ./testdata/grepinput) >>testtrygrep -echo "RC=$?" >>testtrygrep - -echo "---------------------------- Test 3 ------------------------------" >>testtrygrep -(cd $srcdir; $valgrind $pcregrep -in PATTERN ./testdata/grepinput) >>testtrygrep -echo "RC=$?" >>testtrygrep - -echo "---------------------------- Test 4 ------------------------------" >>testtrygrep -(cd $srcdir; $valgrind $pcregrep -ic PATTERN ./testdata/grepinput) >>testtrygrep -echo "RC=$?" >>testtrygrep - -echo "---------------------------- Test 5 ------------------------------" >>testtrygrep -(cd $srcdir; $valgrind $pcregrep -in PATTERN ./testdata/grepinput ./testdata/grepinputx) >>testtrygrep -echo "RC=$?" >>testtrygrep - -echo "---------------------------- Test 6 ------------------------------" >>testtrygrep -(cd $srcdir; $valgrind $pcregrep -inh PATTERN ./testdata/grepinput ./testdata/grepinputx) >>testtrygrep -echo "RC=$?" >>testtrygrep - -echo "---------------------------- Test 7 ------------------------------" >>testtrygrep -(cd $srcdir; $valgrind $pcregrep -il PATTERN ./testdata/grepinput ./testdata/grepinputx) >>testtrygrep -echo "RC=$?" >>testtrygrep - -echo "---------------------------- Test 8 ------------------------------" >>testtrygrep -(cd $srcdir; $valgrind $pcregrep -l PATTERN ./testdata/grepinput ./testdata/grepinputx) >>testtrygrep -echo "RC=$?" >>testtrygrep - -echo "---------------------------- Test 9 ------------------------------" >>testtrygrep -(cd $srcdir; $valgrind $pcregrep -q PATTERN ./testdata/grepinput ./testdata/grepinputx) >>testtrygrep -echo "RC=$?" >>testtrygrep - -echo "---------------------------- Test 10 -----------------------------" >>testtrygrep -(cd $srcdir; $valgrind $pcregrep -q NEVER-PATTERN ./testdata/grepinput ./testdata/grepinputx) >>testtrygrep -echo "RC=$?" >>testtrygrep - -echo "---------------------------- Test 11 -----------------------------" >>testtrygrep -(cd $srcdir; $valgrind $pcregrep -vn pattern ./testdata/grepinputx) >>testtrygrep -echo "RC=$?" >>testtrygrep - -echo "---------------------------- Test 12 -----------------------------" >>testtrygrep -(cd $srcdir; $valgrind $pcregrep -ix pattern ./testdata/grepinputx) >>testtrygrep -echo "RC=$?" >>testtrygrep - -echo "---------------------------- Test 13 -----------------------------" >>testtrygrep -echo seventeen >testtemp1grep -(cd $srcdir; $valgrind $pcregrep -f./testdata/greplist -f $builddir/testtemp1grep ./testdata/grepinputx) >>testtrygrep -echo "RC=$?" >>testtrygrep - -echo "---------------------------- Test 14 -----------------------------" >>testtrygrep -(cd $srcdir; $valgrind $pcregrep -w pat ./testdata/grepinput ./testdata/grepinputx) >>testtrygrep -echo "RC=$?" >>testtrygrep - -echo "---------------------------- Test 15 -----------------------------" >>testtrygrep -(cd $srcdir; $valgrind $pcregrep 'abc^*' ./testdata/grepinput) 2>>testtrygrep >>testtrygrep -echo "RC=$?" >>testtrygrep - -echo "---------------------------- Test 16 -----------------------------" >>testtrygrep -(cd $srcdir; $valgrind $pcregrep abc ./testdata/grepinput ./testdata/nonexistfile) 2>>testtrygrep >>testtrygrep -echo "RC=$?" >>testtrygrep - -echo "---------------------------- Test 17 -----------------------------" >>testtrygrep -(cd $srcdir; $valgrind $pcregrep -M 'the\noutput' ./testdata/grepinput) >>testtrygrep -echo "RC=$?" >>testtrygrep - -echo "---------------------------- Test 18 -----------------------------" >>testtrygrep -(cd $srcdir; $valgrind $pcregrep -Mn '(the\noutput|dog\.\n--)' ./testdata/grepinput) >>testtrygrep -echo "RC=$?" >>testtrygrep - -echo "---------------------------- Test 19 -----------------------------" >>testtrygrep -(cd $srcdir; $valgrind $pcregrep -Mix 'Pattern' ./testdata/grepinputx) >>testtrygrep -echo "RC=$?" >>testtrygrep - -echo "---------------------------- Test 20 -----------------------------" >>testtrygrep -(cd $srcdir; $valgrind $pcregrep -Mixn 'complete pair\nof lines' ./testdata/grepinputx) >>testtrygrep -echo "RC=$?" >>testtrygrep - -echo "---------------------------- Test 21 -----------------------------" >>testtrygrep -(cd $srcdir; $valgrind $pcregrep -nA3 'four' ./testdata/grepinputx) >>testtrygrep -echo "RC=$?" >>testtrygrep - -echo "---------------------------- Test 22 -----------------------------" >>testtrygrep -(cd $srcdir; $valgrind $pcregrep -nB3 'four' ./testdata/grepinputx) >>testtrygrep -echo "RC=$?" >>testtrygrep - -echo "---------------------------- Test 23 -----------------------------" >>testtrygrep -(cd $srcdir; $valgrind $pcregrep -C3 'four' ./testdata/grepinputx) >>testtrygrep -echo "RC=$?" >>testtrygrep - -echo "---------------------------- Test 24 -----------------------------" >>testtrygrep -(cd $srcdir; $valgrind $pcregrep -A9 'four' ./testdata/grepinputx) >>testtrygrep -echo "RC=$?" >>testtrygrep - -echo "---------------------------- Test 25 -----------------------------" >>testtrygrep -(cd $srcdir; $valgrind $pcregrep -nB9 'four' ./testdata/grepinputx) >>testtrygrep -echo "RC=$?" >>testtrygrep - -echo "---------------------------- Test 26 -----------------------------" >>testtrygrep -(cd $srcdir; $valgrind $pcregrep -A9 -B9 'four' ./testdata/grepinputx) >>testtrygrep -echo "RC=$?" >>testtrygrep - -echo "---------------------------- Test 27 -----------------------------" >>testtrygrep -(cd $srcdir; $valgrind $pcregrep -A10 'four' ./testdata/grepinputx) >>testtrygrep -echo "RC=$?" >>testtrygrep - -echo "---------------------------- Test 28 -----------------------------" >>testtrygrep -(cd $srcdir; $valgrind $pcregrep -nB10 'four' ./testdata/grepinputx) >>testtrygrep -echo "RC=$?" >>testtrygrep - -echo "---------------------------- Test 29 -----------------------------" >>testtrygrep -(cd $srcdir; $valgrind $pcregrep -C12 -B10 'four' ./testdata/grepinputx) >>testtrygrep -echo "RC=$?" >>testtrygrep - -echo "---------------------------- Test 30 -----------------------------" >>testtrygrep -(cd $srcdir; $valgrind $pcregrep -inB3 'pattern' ./testdata/grepinput ./testdata/grepinputx) >>testtrygrep -echo "RC=$?" >>testtrygrep - -echo "---------------------------- Test 31 -----------------------------" >>testtrygrep -(cd $srcdir; $valgrind $pcregrep -inA3 'pattern' ./testdata/grepinput ./testdata/grepinputx) >>testtrygrep -echo "RC=$?" >>testtrygrep - -echo "---------------------------- Test 32 -----------------------------" >>testtrygrep -(cd $srcdir; $valgrind $pcregrep -L 'fox' ./testdata/grepinput ./testdata/grepinputx) >>testtrygrep -echo "RC=$?" >>testtrygrep - -echo "---------------------------- Test 33 -----------------------------" >>testtrygrep -(cd $srcdir; $valgrind $pcregrep 'fox' ./testdata/grepnonexist) >>testtrygrep 2>&1 -echo "RC=$?" >>testtrygrep - -echo "---------------------------- Test 34 -----------------------------" >>testtrygrep -(cd $srcdir; $valgrind $pcregrep -s 'fox' ./testdata/grepnonexist) >>testtrygrep 2>&1 -echo "RC=$?" >>testtrygrep - -echo "---------------------------- Test 35 -----------------------------" >>testtrygrep -(cd $srcdir; $valgrind $pcregrep -L -r --include=grepinputx --include grepinput8 --exclude-dir='^\.' 'fox' ./testdata | sort) >>testtrygrep -echo "RC=$?" >>testtrygrep - -echo "---------------------------- Test 36 -----------------------------" >>testtrygrep -(cd $srcdir; $valgrind $pcregrep -L -r --include=grepinput --exclude 'grepinput$' --exclude=grepinput8 --exclude-dir='^\.' 'fox' ./testdata | sort) >>testtrygrep -echo "RC=$?" >>testtrygrep - -echo "---------------------------- Test 37 -----------------------------" >>testtrygrep -(cd $srcdir; $valgrind $pcregrep '^(a+)*\d' ./testdata/grepinput) >>testtrygrep 2>teststderrgrep -echo "RC=$?" >>testtrygrep -echo "======== STDERR ========" >>testtrygrep -cat teststderrgrep >>testtrygrep - -echo "---------------------------- Test 38 ------------------------------" >>testtrygrep -(cd $srcdir; $valgrind $pcregrep '>\x00<' ./testdata/grepinput) >>testtrygrep -echo "RC=$?" >>testtrygrep - -echo "---------------------------- Test 39 ------------------------------" >>testtrygrep -(cd $srcdir; $valgrind $pcregrep -A1 'before the binary zero' ./testdata/grepinput) >>testtrygrep -echo "RC=$?" >>testtrygrep - -echo "---------------------------- Test 40 ------------------------------" >>testtrygrep -(cd $srcdir; $valgrind $pcregrep -B1 'after the binary zero' ./testdata/grepinput) >>testtrygrep -echo "RC=$?" >>testtrygrep - -echo "---------------------------- Test 41 ------------------------------" >>testtrygrep -(cd $srcdir; $valgrind $pcregrep -B1 -o '\w+ the binary zero' ./testdata/grepinput) >>testtrygrep -echo "RC=$?" >>testtrygrep - -echo "---------------------------- Test 42 ------------------------------" >>testtrygrep -(cd $srcdir; $valgrind $pcregrep -B1 -onH '\w+ the binary zero' ./testdata/grepinput) >>testtrygrep -echo "RC=$?" >>testtrygrep - -echo "---------------------------- Test 43 ------------------------------" >>testtrygrep -(cd $srcdir; $valgrind $pcregrep -on 'before|zero|after' ./testdata/grepinput) >>testtrygrep -echo "RC=$?" >>testtrygrep - -echo "---------------------------- Test 44 ------------------------------" >>testtrygrep -(cd $srcdir; $valgrind $pcregrep -on -e before -ezero -e after ./testdata/grepinput) >>testtrygrep -echo "RC=$?" >>testtrygrep - -echo "---------------------------- Test 45 ------------------------------" >>testtrygrep -(cd $srcdir; $valgrind $pcregrep -on -f ./testdata/greplist -e binary ./testdata/grepinput) >>testtrygrep -echo "RC=$?" >>testtrygrep - -echo "---------------------------- Test 46 ------------------------------" >>testtrygrep -(cd $srcdir; $valgrind $pcregrep -eabc -e '(unclosed' ./testdata/grepinput) 2>>testtrygrep >>testtrygrep -echo "RC=$?" >>testtrygrep - -echo "---------------------------- Test 47 ------------------------------" >>testtrygrep -(cd $srcdir; $valgrind $pcregrep -Fx "AB.VE -elephant" ./testdata/grepinput) >>testtrygrep -echo "RC=$?" >>testtrygrep - -echo "---------------------------- Test 48 ------------------------------" >>testtrygrep -(cd $srcdir; $valgrind $pcregrep -F "AB.VE -elephant" ./testdata/grepinput) >>testtrygrep -echo "RC=$?" >>testtrygrep - -echo "---------------------------- Test 49 ------------------------------" >>testtrygrep -(cd $srcdir; $valgrind $pcregrep -F -e DATA -e "AB.VE -elephant" ./testdata/grepinput) >>testtrygrep -echo "RC=$?" >>testtrygrep - -echo "---------------------------- Test 50 ------------------------------" >>testtrygrep -(cd $srcdir; $valgrind $pcregrep "^(abc|def|ghi|jkl)" ./testdata/grepinputx) >>testtrygrep -echo "RC=$?" >>testtrygrep - -echo "---------------------------- Test 51 ------------------------------" >>testtrygrep -(cd $srcdir; $valgrind $pcregrep -Mv "brown\sfox" ./testdata/grepinputv) >>testtrygrep -echo "RC=$?" >>testtrygrep - -echo "---------------------------- Test 52 ------------------------------" >>testtrygrep -(cd $srcdir; $valgrind $pcregrep --colour=always jumps ./testdata/grepinputv) >>testtrygrep -echo "RC=$?" >>testtrygrep - -echo "---------------------------- Test 53 ------------------------------" >>testtrygrep -(cd $srcdir; $valgrind $pcregrep --file-offsets 'before|zero|after' ./testdata/grepinput) >>testtrygrep -echo "RC=$?" >>testtrygrep - -echo "---------------------------- Test 54 ------------------------------" >>testtrygrep -(cd $srcdir; $valgrind $pcregrep --line-offsets 'before|zero|after' ./testdata/grepinput) >>testtrygrep -echo "RC=$?" >>testtrygrep - -echo "---------------------------- Test 55 -----------------------------" >>testtrygrep -(cd $srcdir; $valgrind $pcregrep -f./testdata/greplist --color=always ./testdata/grepinputx) >>testtrygrep -echo "RC=$?" >>testtrygrep - -echo "---------------------------- Test 56 -----------------------------" >>testtrygrep -(cd $srcdir; $valgrind $pcregrep -c lazy ./testdata/grepinput*) >>testtrygrep -echo "RC=$?" >>testtrygrep - -echo "---------------------------- Test 57 -----------------------------" >>testtrygrep -(cd $srcdir; $valgrind $pcregrep -c -l lazy ./testdata/grepinput*) >>testtrygrep -echo "RC=$?" >>testtrygrep - -echo "---------------------------- Test 58 -----------------------------" >>testtrygrep -(cd $srcdir; $valgrind $pcregrep --regex=PATTERN ./testdata/grepinput) >>testtrygrep -echo "RC=$?" >>testtrygrep - -echo "---------------------------- Test 59 -----------------------------" >>testtrygrep -(cd $srcdir; $valgrind $pcregrep --regexp=PATTERN ./testdata/grepinput) >>testtrygrep -echo "RC=$?" >>testtrygrep - -echo "---------------------------- Test 60 -----------------------------" >>testtrygrep -(cd $srcdir; $valgrind $pcregrep --regex PATTERN ./testdata/grepinput) >>testtrygrep -echo "RC=$?" >>testtrygrep - -echo "---------------------------- Test 61 -----------------------------" >>testtrygrep -(cd $srcdir; $valgrind $pcregrep --regexp PATTERN ./testdata/grepinput) >>testtrygrep -echo "RC=$?" >>testtrygrep - -echo "---------------------------- Test 62 -----------------------------" >>testtrygrep -(cd $srcdir; $valgrind $pcregrep --match-limit=1000 --no-jit -M 'This is a file(.|\R)*file.' ./testdata/grepinput) >>testtrygrep 2>&1 -echo "RC=$?" >>testtrygrep - -echo "---------------------------- Test 63 -----------------------------" >>testtrygrep -(cd $srcdir; $valgrind $pcregrep --recursion-limit=1000 --no-jit -M 'This is a file(.|\R)*file.' ./testdata/grepinput) >>testtrygrep 2>&1 -echo "RC=$?" >>testtrygrep - -echo "---------------------------- Test 64 ------------------------------" >>testtrygrep -(cd $srcdir; $valgrind $pcregrep -o1 '(?<=PAT)TERN (ap(pear)s)' ./testdata/grepinput) >>testtrygrep -echo "RC=$?" >>testtrygrep - -echo "---------------------------- Test 65 ------------------------------" >>testtrygrep -(cd $srcdir; $valgrind $pcregrep -o2 '(?<=PAT)TERN (ap(pear)s)' ./testdata/grepinput) >>testtrygrep -echo "RC=$?" >>testtrygrep - -echo "---------------------------- Test 66 ------------------------------" >>testtrygrep -(cd $srcdir; $valgrind $pcregrep -o3 '(?<=PAT)TERN (ap(pear)s)' ./testdata/grepinput) >>testtrygrep -echo "RC=$?" >>testtrygrep - -echo "---------------------------- Test 67 ------------------------------" >>testtrygrep -(cd $srcdir; $valgrind $pcregrep -o12 '(?<=PAT)TERN (ap(pear)s)' ./testdata/grepinput) >>testtrygrep -echo "RC=$?" >>testtrygrep - -echo "---------------------------- Test 68 ------------------------------" >>testtrygrep -(cd $srcdir; $valgrind $pcregrep --only-matching=2 '(?<=PAT)TERN (ap(pear)s)' ./testdata/grepinput) >>testtrygrep -echo "RC=$?" >>testtrygrep - -echo "---------------------------- Test 69 -----------------------------" >>testtrygrep -(cd $srcdir; $valgrind $pcregrep -vn --colour=always pattern ./testdata/grepinputx) >>testtrygrep -echo "RC=$?" >>testtrygrep - -echo "---------------------------- Test 70 -----------------------------" >>testtrygrep -(cd $srcdir; $valgrind $pcregrep --color=always -M "triple:\t.*\n\n" ./testdata/grepinput3) >>testtrygrep -echo "RC=$?" >>testtrygrep - -echo "---------------------------- Test 71 -----------------------------" >>testtrygrep -(cd $srcdir; $valgrind $pcregrep -o "^01|^02|^03" ./testdata/grepinput) >>testtrygrep -echo "RC=$?" >>testtrygrep - -echo "---------------------------- Test 72 -----------------------------" >>testtrygrep -(cd $srcdir; $valgrind $pcregrep --color=always "^01|^02|^03" ./testdata/grepinput) >>testtrygrep -echo "RC=$?" >>testtrygrep - -echo "---------------------------- Test 73 -----------------------------" >>testtrygrep -(cd $srcdir; $valgrind $pcregrep -o --colour=always "^01|^02|^03" ./testdata/grepinput) >>testtrygrep -echo "RC=$?" >>testtrygrep - -echo "---------------------------- Test 74 -----------------------------" >>testtrygrep -(cd $srcdir; $valgrind $pcregrep -o "^01|02|^03" ./testdata/grepinput) >>testtrygrep -echo "RC=$?" >>testtrygrep - -echo "---------------------------- Test 75 -----------------------------" >>testtrygrep -(cd $srcdir; $valgrind $pcregrep --color=always "^01|02|^03" ./testdata/grepinput) >>testtrygrep -echo "RC=$?" >>testtrygrep - -echo "---------------------------- Test 76 -----------------------------" >>testtrygrep -(cd $srcdir; $valgrind $pcregrep -o --colour=always "^01|02|^03" ./testdata/grepinput) >>testtrygrep -echo "RC=$?" >>testtrygrep - -echo "---------------------------- Test 77 -----------------------------" >>testtrygrep -(cd $srcdir; $valgrind $pcregrep -o "^01|^02|03" ./testdata/grepinput) >>testtrygrep -echo "RC=$?" >>testtrygrep - -echo "---------------------------- Test 78 -----------------------------" >>testtrygrep -(cd $srcdir; $valgrind $pcregrep --color=always "^01|^02|03" ./testdata/grepinput) >>testtrygrep -echo "RC=$?" >>testtrygrep - -echo "---------------------------- Test 79 -----------------------------" >>testtrygrep -(cd $srcdir; $valgrind $pcregrep -o --colour=always "^01|^02|03" ./testdata/grepinput) >>testtrygrep -echo "RC=$?" >>testtrygrep - -echo "---------------------------- Test 80 -----------------------------" >>testtrygrep -(cd $srcdir; $valgrind $pcregrep -o "\b01|\b02" ./testdata/grepinput) >>testtrygrep -echo "RC=$?" >>testtrygrep - -echo "---------------------------- Test 81 -----------------------------" >>testtrygrep -(cd $srcdir; $valgrind $pcregrep --color=always "\\b01|\\b02" ./testdata/grepinput) >>testtrygrep -echo "RC=$?" >>testtrygrep - -echo "---------------------------- Test 82 -----------------------------" >>testtrygrep -(cd $srcdir; $valgrind $pcregrep -o --colour=always "\\b01|\\b02" ./testdata/grepinput) >>testtrygrep -echo "RC=$?" >>testtrygrep - -echo "---------------------------- Test 83 -----------------------------" >>testtrygrep -(cd $srcdir; $valgrind $pcregrep --buffer-size=100 "^a" ./testdata/grepinput3) >>testtrygrep 2>&1 -echo "RC=$?" >>testtrygrep - -echo "---------------------------- Test 84 -----------------------------" >>testtrygrep -echo testdata/grepinput3 >testtemp1grep -(cd $srcdir; $valgrind $pcregrep --file-list ./testdata/grepfilelist --file-list $builddir/testtemp1grep "fox|complete|t7") >>testtrygrep 2>&1 -echo "RC=$?" >>testtrygrep - -echo "---------------------------- Test 85 -----------------------------" >>testtrygrep -(cd $srcdir; $valgrind $pcregrep --file-list=./testdata/grepfilelist "dolor" ./testdata/grepinput3) >>testtrygrep 2>&1 -echo "RC=$?" >>testtrygrep - -echo "---------------------------- Test 86 -----------------------------" >>testtrygrep -(cd $srcdir; $valgrind $pcregrep "dog" ./testdata/grepbinary) >>testtrygrep 2>&1 -echo "RC=$?" >>testtrygrep - -echo "---------------------------- Test 87 -----------------------------" >>testtrygrep -(cd $srcdir; $valgrind $pcregrep "cat" ./testdata/grepbinary) >>testtrygrep 2>&1 -echo "RC=$?" >>testtrygrep - -echo "---------------------------- Test 88 -----------------------------" >>testtrygrep -(cd $srcdir; $valgrind $pcregrep -v "cat" ./testdata/grepbinary) >>testtrygrep 2>&1 -echo "RC=$?" >>testtrygrep - -echo "---------------------------- Test 89 -----------------------------" >>testtrygrep -(cd $srcdir; $valgrind $pcregrep -I "dog" ./testdata/grepbinary) >>testtrygrep 2>&1 -echo "RC=$?" >>testtrygrep - -echo "---------------------------- Test 90 -----------------------------" >>testtrygrep -(cd $srcdir; $valgrind $pcregrep --binary-files=without-match "dog" ./testdata/grepbinary) >>testtrygrep 2>&1 -echo "RC=$?" >>testtrygrep - -echo "---------------------------- Test 91 -----------------------------" >>testtrygrep -(cd $srcdir; $valgrind $pcregrep -a "dog" ./testdata/grepbinary) >>testtrygrep 2>&1 -echo "RC=$?" >>testtrygrep - -echo "---------------------------- Test 92 -----------------------------" >>testtrygrep -(cd $srcdir; $valgrind $pcregrep --binary-files=text "dog" ./testdata/grepbinary) >>testtrygrep 2>&1 -echo "RC=$?" >>testtrygrep - -echo "---------------------------- Test 93 -----------------------------" >>testtrygrep -(cd $srcdir; $valgrind $pcregrep --text "dog" ./testdata/grepbinary) >>testtrygrep 2>&1 -echo "RC=$?" >>testtrygrep - -echo "---------------------------- Test 94 -----------------------------" >>testtrygrep -(cd $srcdir; $valgrind $pcregrep -L -r --include=grepinputx --include grepinput8 'fox' ./testdata/grepinput* | sort) >>testtrygrep -echo "RC=$?" >>testtrygrep - -echo "---------------------------- Test 95 -----------------------------" >>testtrygrep -(cd $srcdir; $valgrind $pcregrep --file-list ./testdata/grepfilelist --exclude grepinputv "fox|complete") >>testtrygrep 2>&1 -echo "RC=$?" >>testtrygrep - -echo "---------------------------- Test 96 -----------------------------" >>testtrygrep -(cd $srcdir; $valgrind $pcregrep -L -r --include-dir=testdata --exclude '^(?!grepinput)' 'fox' ./test* | sort) >>testtrygrep -echo "RC=$?" >>testtrygrep - -echo "---------------------------- Test 97 -----------------------------" >>testtrygrep -echo "grepinput$" >testtemp1grep -echo "grepinput8" >>testtemp1grep -(cd $srcdir; $valgrind $pcregrep -L -r --include=grepinput --exclude-from $builddir/testtemp1grep --exclude-dir='^\.' 'fox' ./testdata | sort) >>testtrygrep -echo "RC=$?" >>testtrygrep - -echo "---------------------------- Test 98 -----------------------------" >>testtrygrep -echo "grepinput$" >testtemp1grep -echo "grepinput8" >>testtemp1grep -(cd $srcdir; $valgrind $pcregrep -L -r --exclude=grepinput3 --include=grepinput --exclude-from $builddir/testtemp1grep --exclude-dir='^\.' 'fox' ./testdata | sort) >>testtrygrep -echo "RC=$?" >>testtrygrep - -echo "---------------------------- Test 99 -----------------------------" >>testtrygrep -echo "grepinput$" >testtemp1grep -echo "grepinput8" >testtemp2grep -(cd $srcdir; $valgrind $pcregrep -L -r --include grepinput --exclude-from $builddir/testtemp1grep --exclude-from=$builddir/testtemp2grep --exclude-dir='^\.' 'fox' ./testdata | sort) >>testtrygrep -echo "RC=$?" >>testtrygrep - -echo "---------------------------- Test 100 ------------------------------" >>testtrygrep -(cd $srcdir; $valgrind $pcregrep -Ho2 --only-matching=1 -o3 '(\w+) binary (\w+)(\.)?' ./testdata/grepinput) >>testtrygrep -echo "RC=$?" >>testtrygrep - -echo "---------------------------- Test 101 ------------------------------" >>testtrygrep -(cd $srcdir; $valgrind $pcregrep -o3 -Ho2 -o12 --only-matching=1 -o3 --colour=always --om-separator='|' '(\w+) binary (\w+)(\.)?' ./testdata/grepinput) >>testtrygrep -echo "RC=$?" >>testtrygrep - -echo "---------------------------- Test 102 -----------------------------" >>testtrygrep -(cd $srcdir; $valgrind $pcregrep -n "^$" ./testdata/grepinput3) >>testtrygrep 2>&1 -echo "RC=$?" >>testtrygrep - -echo "---------------------------- Test 103 -----------------------------" >>testtrygrep -(cd $srcdir; $valgrind $pcregrep --only-matching "^$" ./testdata/grepinput3) >>testtrygrep 2>&1 -echo "RC=$?" >>testtrygrep - -echo "---------------------------- Test 104 -----------------------------" >>testtrygrep -(cd $srcdir; $valgrind $pcregrep -n --only-matching "^$" ./testdata/grepinput3) >>testtrygrep 2>&1 -echo "RC=$?" >>testtrygrep - -echo "---------------------------- Test 105 -----------------------------" >>testtrygrep -(cd $srcdir; $valgrind $pcregrep --colour=always "ipsum|" ./testdata/grepinput3) >>testtrygrep 2>&1 -echo "RC=$?" >>testtrygrep - -echo "---------------------------- Test 106 -----------------------------" >>testtrygrep -(cd $srcdir; echo "a" | $valgrind $pcregrep -M "|a" ) >>testtrygrep 2>&1 -echo "RC=$?" >>testtrygrep - -echo "---------------------------- Test 107 -----------------------------" >>testtrygrep -echo "a" >testtemp1grep -echo "aaaaa" >>testtemp1grep -(cd $srcdir; $valgrind $pcregrep --line-offsets '(?<=\Ka)' $builddir/testtemp1grep) >>testtrygrep 2>&1 -echo "RC=$?" >>testtrygrep - -echo "---------------------------- Test 108 ------------------------------" >>testtrygrep -(cd $srcdir; $valgrind $pcregrep -lq PATTERN ./testdata/grepinput ./testdata/grepinputx) >>testtrygrep -echo "RC=$?" >>testtrygrep - -echo "---------------------------- Test 109 -----------------------------" >>testtrygrep -(cd $srcdir; $valgrind $pcregrep -cq lazy ./testdata/grepinput*) >>testtrygrep -echo "RC=$?" >>testtrygrep - -# Now compare the results. - -$cf $srcdir/testdata/grepoutput testtrygrep -if [ $? != 0 ] ; then exit 1; fi - - -# These tests require UTF-8 support - -if [ $utf8 -ne 0 ] ; then - echo "Testing pcregrep UTF-8 features" - - echo "---------------------------- Test U1 ------------------------------" >testtrygrep - (cd $srcdir; $valgrind $pcregrep -n -u --newline=any "^X" ./testdata/grepinput8) >>testtrygrep - echo "RC=$?" >>testtrygrep - - echo "---------------------------- Test U2 ------------------------------" >>testtrygrep - (cd $srcdir; $valgrind $pcregrep -n -u -C 3 --newline=any "Match" ./testdata/grepinput8) >>testtrygrep - echo "RC=$?" >>testtrygrep - - $cf $srcdir/testdata/grepoutput8 testtrygrep - if [ $? != 0 ] ; then exit 1; fi - -else - echo "Skipping pcregrep UTF-8 tests: no UTF-8 support in PCRE library" -fi - - -# We go to some contortions to try to ensure that the tests for the various -# newline settings will work in environments where the normal newline sequence -# is not \n. Do not use exported files, whose line endings might be changed. -# Instead, create an input file using printf so that its contents are exactly -# what we want. Note the messy fudge to get printf to write a string that -# starts with a hyphen. These tests are run in the build directory. - -echo "Testing pcregrep newline settings" -printf "abc\rdef\r\nghi\njkl" >testNinputgrep - -printf "%c--------------------------- Test N1 ------------------------------\r\n" - >testtrygrep -$valgrind $pcregrep -n -N CR "^(abc|def|ghi|jkl)" testNinputgrep >>testtrygrep - -printf "%c--------------------------- Test N2 ------------------------------\r\n" - >>testtrygrep -$valgrind $pcregrep -n --newline=crlf "^(abc|def|ghi|jkl)" testNinputgrep >>testtrygrep - -printf "%c--------------------------- Test N3 ------------------------------\r\n" - >>testtrygrep -pattern=`printf 'def\rjkl'` -$valgrind $pcregrep -n --newline=cr -F "$pattern" testNinputgrep >>testtrygrep - -printf "%c--------------------------- Test N4 ------------------------------\r\n" - >>testtrygrep -$valgrind $pcregrep -n --newline=crlf -F -f $srcdir/testdata/greppatN4 testNinputgrep >>testtrygrep - -printf "%c--------------------------- Test N5 ------------------------------\r\n" - >>testtrygrep -$valgrind $pcregrep -n --newline=any "^(abc|def|ghi|jkl)" testNinputgrep >>testtrygrep - -printf "%c--------------------------- Test N6 ------------------------------\r\n" - >>testtrygrep -$valgrind $pcregrep -n --newline=anycrlf "^(abc|def|ghi|jkl)" testNinputgrep >>testtrygrep - -$cf $srcdir/testdata/grepoutputN testtrygrep -if [ $? != 0 ] ; then exit 1; fi - -exit 0 - -# End diff --git a/src/third_party/pcre-8.38/RunTest b/src/third_party/pcre-8.38/RunTest deleted file mode 100755 index 67cfbf07cf9..00000000000 --- a/src/third_party/pcre-8.38/RunTest +++ /dev/null @@ -1,1010 +0,0 @@ -#! /bin/sh - -############################################################################### -# Run the PCRE tests using the pcretest program. The appropriate tests are -# selected, depending on which build-time options were used. -# -# All tests are now run both with and without -s, to ensure that everything is -# tested with and without studying. However, there are some tests that produce -# different output after studying, typically when we are tracing the actual -# matching process (for example, using auto-callouts). In these few cases, the -# tests are duplicated in the files, one with /S to force studying always, and -# one with /SS to force *not* studying always. The use of -s doesn't then make -# any difference to their output. There is also one test which compiles invalid -# UTF-8 with the UTF-8 check turned off; for this, studying must also be -# disabled with /SS. -# -# When JIT support is available, all appropriate tests are also run with -s+ to -# test (again, almost) everything with studying and the JIT option, unless -# "nojit" is given on the command line. There are also two tests for -# JIT-specific features, one to be run when JIT support is available (unless -# "nojit" is specified), and one when it is not. -# -# Whichever of the 8-, 16- and 32-bit libraries exist are tested. It is also -# possible to select which to test by giving "-8", "-16" or "-32" on the -# command line. -# -# As well as "nojit", "-8", "-16", and "-32", arguments for this script are -# individual test numbers, ranges of tests such as 3-6 or 3- (meaning 3 to the -# end), or a number preceded by ~ to exclude a test. For example, "3-15 ~10" -# runs tests 3 to 15, excluding test 10, and just "~10" runs all the tests -# except test 10. Whatever order the arguments are in, the tests are always run -# in numerical order. -# -# The special argument "3S" runs test 3, stopping if it fails. Test 3 is the -# locale test, and failure usually means there's an issue with the locale -# rather than a bug in PCRE, so normally subsequent tests are run. "3S" is -# useful when you want to debug or update the test. -# -# Inappropriate tests are automatically skipped (with a comment to say so): for -# example, if JIT support is not compiled, test 12 is skipped, whereas if JIT -# support is compiled, test 13 is skipped. -# -# Other arguments can be one of the words "valgrind", "valgrind-log", or "sim" -# followed by an argument to run cross-compiled executables under a simulator, -# for example: -# -# RunTest 3 sim "qemu-arm -s 8388608" -# -# There are two special cases where only one argument is allowed: -# -# If the first and only argument is "ebcdic", the script runs the special -# EBCDIC test that can be useful for checking certain EBCDIC features, even -# when run in an ASCII environment. -# -# If the script is obeyed as "RunTest list", a list of available tests is -# output, but none of them are run. -############################################################################### - -# Define test titles in variables so that they can be output as a list. Some -# of them are modified (e.g. with -8 or -16) when used in the actual tests. - -title1="Test 1: Main functionality (Compatible with Perl >= 5.10)" -title2="Test 2: API, errors, internals, and non-Perl stuff" -title3="Test 3: Locale-specific features" -title4A="Test 4: UTF" -title4B=" support (Compatible with Perl >= 5.10)" -title5="Test 5: API, internals, and non-Perl stuff for UTF" -title6="Test 6: Unicode property support (Compatible with Perl >= 5.10)" -title7="Test 7: API, internals, and non-Perl stuff for Unicode property support" -title8="Test 8: DFA matching main functionality" -title9="Test 9: DFA matching with UTF" -title10="Test 10: DFA matching with Unicode properties" -title11="Test 11: Internal offsets and code size tests" -title12="Test 12: JIT-specific features (when JIT is available)" -title13="Test 13: JIT-specific features (when JIT is not available)" -title14="Test 14: Specials for the basic 8-bit library" -title15="Test 15: Specials for the 8-bit library with UTF-8 support" -title16="Test 16: Specials for the 8-bit library with Unicode propery support" -title17="Test 17: Specials for the basic 16/32-bit library" -title18="Test 18: Specials for the 16/32-bit library with UTF-16/32 support" -title19="Test 19: Specials for the 16/32-bit library with Unicode property support" -title20="Test 20: DFA specials for the basic 16/32-bit library" -title21="Test 21: Reloads for the basic 16/32-bit library" -title22="Test 22: Reloads for the 16/32-bit library with UTF-16/32 support" -title23="Test 23: Specials for the 16-bit library" -title24="Test 24: Specials for the 16-bit library with UTF-16 support" -title25="Test 25: Specials for the 32-bit library" -title26="Test 26: Specials for the 32-bit library with UTF-32 support" - -maxtest=26 - -if [ $# -eq 1 -a "$1" = "list" ]; then - echo $title1 - echo $title2 "(not UTF)" - echo $title3 - echo $title4A $title4B - echo $title5 support - echo $title6 - echo $title7 - echo $title8 - echo $title9 - echo $title10 - echo $title11 - echo $title12 - echo $title13 - echo $title14 - echo $title15 - echo $title16 - echo $title17 - echo $title18 - echo $title19 - echo $title20 - echo $title21 - echo $title22 - echo $title23 - echo $title24 - echo $title25 - echo $title26 - exit 0 -fi - -# Set up a suitable "diff" command for comparison. Some systems -# have a diff that lacks a -u option. Try to deal with this. - -cf="diff" -diff -u /dev/null /dev/null 2>/dev/null && cf="diff -u" - -# Find the test data - -if [ -n "$srcdir" -a -d "$srcdir" ] ; then - testdata="$srcdir/testdata" -elif [ -d "./testdata" ] ; then - testdata=./testdata -elif [ -d "../testdata" ] ; then - testdata=../testdata -else - echo "Cannot find the testdata directory" - exit 1 -fi - - -# ------ Special EBCDIC Test ------- - -if [ $# -eq 1 -a "$1" = "ebcdic" ]; then - ./pcretest -C ebcdic >/dev/null - ebcdic=$? - if [ $ebcdic -ne 1 ] ; then - echo "Cannot run EBCDIC tests: EBCDIC support not compiled" - exit 1 - fi - - for opt in "" "-s" "-dfa" "-s -dfa"; do - ./pcretest -q $opt $testdata/testinputEBC >testtry - if [ $? = 0 ] ; then - $cf $testdata/testoutputEBC testtry - if [ $? != 0 ] ; then exit 1; fi - else exit 1 - fi - if [ "$opt" = "-s" ] ; then echo " OK with study" - elif [ "$opt" = "-dfa" ] ; then echo " OK using DFA" - elif [ "$opt" = "-s -dfa" ] ; then echo " OK using DFA with study" - else echo " OK" - fi - done - -exit 0 -fi - - -# ------ Normal Tests ------ - -# Default values - -arg8= -arg16= -arg32= -nojit= -sim= -skip= -valgrind= - -# This is in case the caller has set aliases (as I do - PH) -unset cp ls mv rm - -# Process options and select which tests to run; for those that are explicitly -# requested, check that the necessary optional facilities are available. - -do1=no -do2=no -do3=no -do4=no -do5=no -do6=no -do7=no -do8=no -do9=no -do10=no -do11=no -do12=no -do13=no -do14=no -do15=no -do16=no -do17=no -do18=no -do19=no -do20=no -do21=no -do22=no -do23=no -do24=no -do25=no -do26=no - -while [ $# -gt 0 ] ; do - case $1 in - 1) do1=yes;; - 2) do2=yes;; - 3) do3=yes;; - 4) do4=yes;; - 5) do5=yes;; - 6) do6=yes;; - 7) do7=yes;; - 8) do8=yes;; - 9) do9=yes;; - 10) do10=yes;; - 11) do11=yes;; - 12) do12=yes;; - 13) do13=yes;; - 14) do14=yes;; - 15) do15=yes;; - 16) do16=yes;; - 17) do17=yes;; - 18) do18=yes;; - 19) do19=yes;; - 20) do20=yes;; - 21) do21=yes;; - 22) do22=yes;; - 23) do23=yes;; - 24) do24=yes;; - 25) do25=yes;; - 26) do26=yes;; - -8) arg8=yes;; - -16) arg16=yes;; - -32) arg32=yes;; - nojit) nojit=yes;; - sim) shift; sim=$1;; - valgrind) valgrind="valgrind --tool=memcheck -q --smc-check=all";; - valgrind-log) valgrind="valgrind --tool=memcheck --num-callers=30 --leak-check=no --error-limit=no --smc-check=all --log-file=report.%p ";; - ~*) - if expr "$1" : '~[0-9][0-9]*$' >/dev/null; then - skip="$skip `expr "$1" : '~\([0-9]*\)*$'`" - else - echo "Unknown option or test selector '$1'"; exit 1 - fi - ;; - *-*) - if expr "$1" : '[0-9][0-9]*-[0-9]*$' >/dev/null; then - tf=`expr "$1" : '\([0-9]*\)'` - tt=`expr "$1" : '.*-\([0-9]*\)'` - if [ "$tt" = "" ] ; then tt=$maxtest; fi - if expr \( "$tf" "<" 1 \) \| \( "$tt" ">" "$maxtest" \) >/dev/null; then - echo "Invalid test range '$1'"; exit 1 - fi - while expr "$tf" "<=" "$tt" >/dev/null; do - eval do${tf}=yes - tf=`expr $tf + 1` - done - else - echo "Invalid test range '$1'"; exit 1 - fi - ;; - *) echo "Unknown option or test selector '$1'"; exit 1;; - esac - shift -done - -# Find which optional facilities are available. - -$sim ./pcretest -C linksize >/dev/null -link_size=$? -if [ $link_size -lt 2 ] ; then - echo "Failed to find internal link size" - exit 1 -fi -if [ $link_size -gt 4 ] ; then - echo "Failed to find internal link size" - exit 1 -fi - -# All of 8-bit, 16-bit, and 32-bit character strings may be supported, but only -# one need be. - -$sim ./pcretest -C pcre8 >/dev/null -support8=$? -$sim ./pcretest -C pcre16 >/dev/null -support16=$? -$sim ./pcretest -C pcre32 >/dev/null -support32=$? - -# Initialize all bitsizes skipped - -test8=skip -test16=skip -test32=skip - -# If no bitsize arguments, select all that are available - -if [ "$arg8$arg16$arg32" = "" ] ; then - if [ $support8 -ne 0 ] ; then - test8= - fi - if [ $support16 -ne 0 ] ; then - test16=-16 - fi - if [ $support32 -ne 0 ] ; then - test32=-32 - fi - -# Select requested bit sizes - -else - if [ "$arg8" = yes ] ; then - if [ $support8 -eq 0 ] ; then - echo "Cannot run 8-bit library tests: 8-bit library not compiled" - exit 1 - fi - test8= - fi - if [ "$arg16" = yes ] ; then - if [ $support16 -eq 0 ] ; then - echo "Cannot run 16-bit library tests: 16-bit library not compiled" - exit 1 - fi - test16=-16 - fi - if [ "$arg32" = yes ] ; then - if [ $support32 -eq 0 ] ; then - echo "Cannot run 32-bit library tests: 32-bit library not compiled" - exit 1 - fi - test32=-32 - fi -fi - -# UTF support always applies to all bit sizes if both are supported; we can't -# have UTF-8 support without UTF-16 support (for example). - -$sim ./pcretest -C utf >/dev/null -utf=$? - -$sim ./pcretest -C ucp >/dev/null -ucp=$? - -jitopt= -$sim ./pcretest -C jit >/dev/null -jit=$? -if [ $jit -ne 0 -a "$nojit" != "yes" ] ; then - jitopt=-s+ -fi - -# If no specific tests were requested, select all. Those that are not -# relevant will be automatically skipped. - -if [ $do1 = no -a $do2 = no -a $do3 = no -a $do4 = no -a \ - $do5 = no -a $do6 = no -a $do7 = no -a $do8 = no -a \ - $do9 = no -a $do10 = no -a $do11 = no -a $do12 = no -a \ - $do13 = no -a $do14 = no -a $do15 = no -a $do16 = no -a \ - $do17 = no -a $do18 = no -a $do19 = no -a $do20 = no -a \ - $do21 = no -a $do22 = no -a $do23 = no -a $do24 = no -a \ - $do25 = no -a $do26 = no ] ; then - do1=yes - do2=yes - do3=yes - do4=yes - do5=yes - do6=yes - do7=yes - do8=yes - do9=yes - do10=yes - do11=yes - do12=yes - do13=yes - do14=yes - do15=yes - do16=yes - do17=yes - do18=yes - do19=yes - do20=yes - do21=yes - do22=yes - do23=yes - do24=yes - do25=yes - do26=yes -fi - -# Handle any explicit skips at this stage, so that an argument list may consist -# only of explicit skips. - -for i in $skip; do eval do$i=no; done - -# Show which release and which test data - -echo "" -echo PCRE C library tests using test data from $testdata -$sim ./pcretest /dev/null - -for bmode in "$test8" "$test16" "$test32"; do - case "$bmode" in - skip) continue;; - -16) if [ "$test8$test32" != "skipskip" ] ; then echo ""; fi - bits=16; echo "---- Testing 16-bit library ----"; echo "";; - -32) if [ "$test8$test16" != "skipskip" ] ; then echo ""; fi - bits=32; echo "---- Testing 32-bit library ----"; echo "";; - *) bits=8; echo "---- Testing 8-bit library ----"; echo "";; - esac - -# Primary test, compatible with JIT and all versions of Perl >= 5.8 - -if [ $do1 = yes ] ; then - echo $title1 - for opt in "" "-s" $jitopt; do - $sim $valgrind ./pcretest -q $bmode $opt $testdata/testinput1 testtry - if [ $? = 0 ] ; then - $cf $testdata/testoutput1 testtry - if [ $? != 0 ] ; then exit 1; fi - else exit 1 - fi - if [ "$opt" = "-s" ] ; then echo " OK with study" - elif [ "$opt" = "-s+" ] ; then echo " OK with JIT study" - else echo " OK" - fi - done -fi - -# PCRE tests that are not JIT or Perl-compatible: API, errors, internals - -if [ $do2 = yes ] ; then - echo $title2 "(not UTF-$bits)" - for opt in "" "-s" $jitopt; do - $sim $valgrind ./pcretest -q $bmode $opt $testdata/testinput2 testtry - if [ $? = 0 ] ; then - $cf $testdata/testoutput2 testtry - if [ $? != 0 ] ; then exit 1; fi - else - echo " " - echo "** Test 2 requires a lot of stack. If it has crashed with a" - echo "** segmentation fault, it may be that you do not have enough" - echo "** stack available by default. Please see the 'pcrestack' man" - echo "** page for a discussion of PCRE's stack usage." - echo " " - exit 1 - fi - if [ "$opt" = "-s" ] ; then echo " OK with study" - elif [ "$opt" = "-s+" ] ; then echo " OK with JIT study" - else echo " OK" - fi - done -fi - -# Locale-specific tests, provided that either the "fr_FR" or the "french" -# locale is available. The former is the Unix-like standard; the latter is -# for Windows. Another possibility is "fr". Unfortunately, different versions -# of the French locale give different outputs for some items. This test passes -# if the output matches any one of the alternative output files. - -if [ $do3 = yes ] ; then - locale -a | grep '^fr_FR$' >/dev/null - if [ $? -eq 0 ] ; then - locale=fr_FR - infile=$testdata/testinput3 - outfile=$testdata/testoutput3 - outfile2=$testdata/testoutput3A - outfile3=$testdata/testoutput3B - else - infile=test3input - outfile=test3output - outfile2=test3outputA - outfile3=test3outputB - locale -a | grep '^french$' >/dev/null - if [ $? -eq 0 ] ; then - locale=french - sed 's/fr_FR/french/' $testdata/testinput3 >test3input - sed 's/fr_FR/french/' $testdata/testoutput3 >test3output - sed 's/fr_FR/french/' $testdata/testoutput3A >test3outputA - sed 's/fr_FR/french/' $testdata/testoutput3B >test3outputB - else - locale -a | grep '^fr$' >/dev/null - if [ $? -eq 0 ] ; then - locale=fr - sed 's/fr_FR/fr/' $testdata/intestinput3 >test3input - sed 's/fr_FR/fr/' $testdata/intestoutput3 >test3output - sed 's/fr_FR/fr/' $testdata/intestoutput3A >test3outputA - sed 's/fr_FR/fr/' $testdata/intestoutput3B >test3outputB - else - locale= - fi - fi - fi - - if [ "$locale" != "" ] ; then - echo $title3 "(using '$locale' locale)" - for opt in "" "-s" $jitopt; do - $sim $valgrind ./pcretest -q $bmode $opt $infile testtry - if [ $? = 0 ] ; then - if $cf $outfile testtry >teststdout || \ - $cf $outfile2 testtry >teststdout || \ - $cf $outfile3 testtry >teststdout - then - if [ "$opt" = "-s" ] ; then echo " OK with study" - elif [ "$opt" = "-s+" ] ; then echo " OK with JIT study" - else echo " OK" - fi - else - echo "** Locale test did not run successfully. The output did not match" - echo " $outfile, $outfile2 or $outfile3." - echo " This may mean that there is a problem with the locale settings rather" - echo " than a bug in PCRE." - exit 1 - fi - else exit 1 - fi - done - else - echo "Cannot test locale-specific features - none of the 'fr_FR', 'fr' or" - echo "'french' locales exist, or the \"locale\" command is not available" - echo "to check for them." - echo " " - fi -fi - -# Additional tests for UTF support - -if [ $do4 = yes ] ; then - echo ${title4A}-${bits}${title4B} - if [ $utf -eq 0 ] ; then - echo " Skipped because UTF-$bits support is not available" - else - for opt in "" "-s" $jitopt; do - $sim $valgrind ./pcretest -q $bmode $opt $testdata/testinput4 testtry - if [ $? = 0 ] ; then - $cf $testdata/testoutput4 testtry - if [ $? != 0 ] ; then exit 1; fi - else exit 1 - fi - if [ "$opt" = "-s" ] ; then echo " OK with study" - elif [ "$opt" = "-s+" ] ; then echo " OK with JIT study" - else echo " OK" - fi - done - fi -fi - -if [ $do5 = yes ] ; then - echo ${title5}-${bits} support - if [ $utf -eq 0 ] ; then - echo " Skipped because UTF-$bits support is not available" - else - for opt in "" "-s" $jitopt; do - $sim $valgrind ./pcretest -q $bmode $opt $testdata/testinput5 testtry - if [ $? = 0 ] ; then - $cf $testdata/testoutput5 testtry - if [ $? != 0 ] ; then exit 1; fi - else exit 1 - fi - if [ "$opt" = "-s" ] ; then echo " OK with study" - elif [ "$opt" = "-s+" ] ; then echo " OK with JIT study" - else echo " OK" - fi - done - fi -fi - -if [ $do6 = yes ] ; then - echo $title6 - if [ $utf -eq 0 -o $ucp -eq 0 ] ; then - echo " Skipped because Unicode property support is not available" - else - for opt in "" "-s" $jitopt; do - $sim $valgrind ./pcretest -q $bmode $opt $testdata/testinput6 testtry - if [ $? = 0 ] ; then - $cf $testdata/testoutput6 testtry - if [ $? != 0 ] ; then exit 1; fi - else exit 1 - fi - if [ "$opt" = "-s" ] ; then echo " OK with study" - elif [ "$opt" = "-s+" ] ; then echo " OK with JIT study" - else echo " OK" - fi - done - fi -fi - -# Test non-Perl-compatible Unicode property support - -if [ $do7 = yes ] ; then - echo $title7 - if [ $utf -eq 0 -o $ucp -eq 0 ] ; then - echo " Skipped because Unicode property support is not available" - else - for opt in "" "-s" $jitopt; do - $sim $valgrind ./pcretest -q $bmode $opt $testdata/testinput7 testtry - if [ $? = 0 ] ; then - $cf $testdata/testoutput7 testtry - if [ $? != 0 ] ; then exit 1; fi - else exit 1 - fi - if [ "$opt" = "-s" ] ; then echo " OK with study" - elif [ "$opt" = "-s+" ] ; then echo " OK with JIT study" - else echo " OK" - fi - done - fi -fi - -# Tests for DFA matching support - -if [ $do8 = yes ] ; then - echo $title8 - for opt in "" "-s"; do - $sim $valgrind ./pcretest -q $bmode $opt -dfa $testdata/testinput8 testtry - if [ $? = 0 ] ; then - $cf $testdata/testoutput8 testtry - if [ $? != 0 ] ; then exit 1; fi - else exit 1 - fi - if [ "$opt" = "-s" ] ; then echo " OK with study" ; else echo " OK"; fi - done -fi - -if [ $do9 = yes ] ; then - echo ${title9}-${bits} - if [ $utf -eq 0 ] ; then - echo " Skipped because UTF-$bits support is not available" - else - for opt in "" "-s"; do - $sim $valgrind ./pcretest -q $bmode $opt -dfa $testdata/testinput9 testtry - if [ $? = 0 ] ; then - $cf $testdata/testoutput9 testtry - if [ $? != 0 ] ; then exit 1; fi - else exit 1 - fi - if [ "$opt" = "-s" ] ; then echo " OK with study" ; else echo " OK"; fi - done - fi -fi - -if [ $do10 = yes ] ; then - echo $title10 - if [ $utf -eq 0 -o $ucp -eq 0 ] ; then - echo " Skipped because Unicode property support is not available" - else - for opt in "" "-s"; do - $sim $valgrind ./pcretest -q $bmode $opt -dfa $testdata/testinput10 testtry - if [ $? = 0 ] ; then - $cf $testdata/testoutput10 testtry - if [ $? != 0 ] ; then exit 1; fi - else exit 1 - fi - if [ "$opt" = "-s" ] ; then echo " OK with study" ; else echo " OK"; fi - done - fi -fi - -# Test of internal offsets and code sizes. This test is run only when there -# is Unicode property support and the link size is 2. The actual tests are -# mostly the same as in some of the above, but in this test we inspect some -# offsets and sizes that require a known link size. This is a doublecheck for -# the maintainer, just in case something changes unexpectely. The output from -# this test is not the same in 8-bit and 16-bit modes. - -if [ $do11 = yes ] ; then - echo $title11 - if [ $link_size -ne 2 ] ; then - echo " Skipped because link size is not 2" - elif [ $ucp -eq 0 ] ; then - echo " Skipped because Unicode property support is not available" - else - for opt in "" "-s"; do - $sim $valgrind ./pcretest -q $bmode $opt $testdata/testinput11 testtry - if [ $? = 0 ] ; then - $cf $testdata/testoutput11-$bits testtry - if [ $? != 0 ] ; then exit 1; fi - else exit 1 - fi - if [ "$opt" = "-s" ] ; then echo " OK with study" ; else echo " OK"; fi - done - fi -fi - -# Test JIT-specific features when JIT is available - -if [ $do12 = yes ] ; then - echo $title12 - if [ $jit -eq 0 -o "$nojit" = "yes" ] ; then - echo " Skipped because JIT is not available or not usable" - else - $sim $valgrind ./pcretest -q $bmode $testdata/testinput12 testtry - if [ $? = 0 ] ; then - $cf $testdata/testoutput12 testtry - if [ $? != 0 ] ; then exit 1; fi - else exit 1 - fi - echo " OK" - fi -fi - -# Test JIT-specific features when JIT is not available - -if [ $do13 = yes ] ; then - echo $title13 - if [ $jit -ne 0 ] ; then - echo " Skipped because JIT is available" - else - $sim $valgrind ./pcretest -q $bmode $testdata/testinput13 testtry - if [ $? = 0 ] ; then - $cf $testdata/testoutput13 testtry - if [ $? != 0 ] ; then exit 1; fi - else exit 1 - fi - echo " OK" - fi -fi - -# Tests for 8-bit-specific features - -if [ "$do14" = yes ] ; then - echo $title14 - if [ "$bits" = "16" -o "$bits" = "32" ] ; then - echo " Skipped when running 16/32-bit tests" - else - cp -f $testdata/saved16 testsaved16 - cp -f $testdata/saved32 testsaved32 - for opt in "" "-s" $jitopt; do - $sim $valgrind ./pcretest -q $bmode $opt $testdata/testinput14 testtry - if [ $? = 0 ] ; then - $cf $testdata/testoutput14 testtry - if [ $? != 0 ] ; then exit 1; fi - else exit 1 - fi - if [ "$opt" = "-s" ] ; then echo " OK with study" - elif [ "$opt" = "-s+" ] ; then echo " OK with JIT study" - else echo " OK" - fi - done - fi -fi - -# Tests for 8-bit-specific features (needs UTF-8 support) - -if [ "$do15" = yes ] ; then - echo $title15 - if [ "$bits" = "16" -o "$bits" = "32" ] ; then - echo " Skipped when running 16/32-bit tests" - elif [ $utf -eq 0 ] ; then - echo " Skipped because UTF-$bits support is not available" - else - for opt in "" "-s" $jitopt; do - $sim $valgrind ./pcretest -q $bmode $opt $testdata/testinput15 testtry - if [ $? = 0 ] ; then - $cf $testdata/testoutput15 testtry - if [ $? != 0 ] ; then exit 1; fi - else exit 1 - fi - if [ "$opt" = "-s" ] ; then echo " OK with study" - elif [ "$opt" = "-s+" ] ; then echo " OK with JIT study" - else echo " OK" - fi - done - fi -fi - -# Tests for 8-bit-specific features (Unicode property support) - -if [ $do16 = yes ] ; then - echo $title16 - if [ "$bits" = "16" -o "$bits" = "32" ] ; then - echo " Skipped when running 16/32-bit tests" - elif [ $ucp -eq 0 ] ; then - echo " Skipped because Unicode property support is not available" - else - for opt in "" "-s" $jitopt; do - $sim $valgrind ./pcretest -q $bmode $opt $testdata/testinput16 testtry - if [ $? = 0 ] ; then - $cf $testdata/testoutput16 testtry - if [ $? != 0 ] ; then exit 1; fi - else exit 1 - fi - if [ "$opt" = "-s" ] ; then echo " OK with study" - elif [ "$opt" = "-s+" ] ; then echo " OK with JIT study" - else echo " OK" - fi - done - fi -fi - -# Tests for 16/32-bit-specific features - -if [ $do17 = yes ] ; then - echo $title17 - if [ "$bits" = "8" ] ; then - echo " Skipped when running 8-bit tests" - else - for opt in "" "-s" $jitopt; do - $sim $valgrind ./pcretest -q $bmode $opt $testdata/testinput17 testtry - if [ $? = 0 ] ; then - $cf $testdata/testoutput17 testtry - if [ $? != 0 ] ; then exit 1; fi - else exit 1 - fi - if [ "$opt" = "-s" ] ; then echo " OK with study" - elif [ "$opt" = "-s+" ] ; then echo " OK with JIT study" - else echo " OK" - fi - done - fi -fi - -# Tests for 16/32-bit-specific features (UTF-16/32 support) - -if [ $do18 = yes ] ; then - echo $title18 - if [ "$bits" = "8" ] ; then - echo " Skipped when running 8-bit tests" - elif [ $utf -eq 0 ] ; then - echo " Skipped because UTF-$bits support is not available" - else - for opt in "" "-s" $jitopt; do - $sim $valgrind ./pcretest -q $bmode $opt $testdata/testinput18 testtry - if [ $? = 0 ] ; then - $cf $testdata/testoutput18-$bits testtry - if [ $? != 0 ] ; then exit 1; fi - else exit 1 - fi - if [ "$opt" = "-s" ] ; then echo " OK with study" - elif [ "$opt" = "-s+" ] ; then echo " OK with JIT study" - else echo " OK" - fi - done - fi -fi - -# Tests for 16/32-bit-specific features (Unicode property support) - -if [ $do19 = yes ] ; then - echo $title19 - if [ "$bits" = "8" ] ; then - echo " Skipped when running 8-bit tests" - elif [ $ucp -eq 0 ] ; then - echo " Skipped because Unicode property support is not available" - else - for opt in "" "-s" $jitopt; do - $sim $valgrind ./pcretest -q $bmode $opt $testdata/testinput19 testtry - if [ $? = 0 ] ; then - $cf $testdata/testoutput19 testtry - if [ $? != 0 ] ; then exit 1; fi - else exit 1 - fi - if [ "$opt" = "-s" ] ; then echo " OK with study" - elif [ "$opt" = "-s+" ] ; then echo " OK with JIT study" - else echo " OK" - fi - done - fi -fi - -# Tests for 16/32-bit-specific features in DFA non-UTF-16/32 mode - -if [ $do20 = yes ] ; then - echo $title20 - if [ "$bits" = "8" ] ; then - echo " Skipped when running 8-bit tests" - else - for opt in "" "-s"; do - $sim $valgrind ./pcretest -q $bmode $opt -dfa $testdata/testinput20 testtry - if [ $? = 0 ] ; then - $cf $testdata/testoutput20 testtry - if [ $? != 0 ] ; then exit 1; fi - else exit 1 - fi - if [ "$opt" = "-s" ] ; then echo " OK with study" - else echo " OK" - fi - done - fi -fi - -# Tests for reloads with 16/32-bit library - -if [ $do21 = yes ] ; then - echo $title21 - if [ "$bits" = "8" ] ; then - echo " Skipped when running 8-bit tests" - elif [ $link_size -ne 2 ] ; then - echo " Skipped because link size is not 2" - else - cp -f $testdata/saved8 testsaved8 - cp -f $testdata/saved16LE-1 testsaved16LE-1 - cp -f $testdata/saved16BE-1 testsaved16BE-1 - cp -f $testdata/saved32LE-1 testsaved32LE-1 - cp -f $testdata/saved32BE-1 testsaved32BE-1 - $sim $valgrind ./pcretest -q $bmode $testdata/testinput21 testtry - if [ $? = 0 ] ; then - $cf $testdata/testoutput21-$bits testtry - if [ $? != 0 ] ; then exit 1; fi - else exit 1 - fi - echo " OK" - fi -fi - -# Tests for reloads with 16/32-bit library (UTF-16 support) - -if [ $do22 = yes ] ; then - echo $title22 - if [ "$bits" = "8" ] ; then - echo " Skipped when running 8-bit tests" - elif [ $utf -eq 0 ] ; then - echo " Skipped because UTF-$bits support is not available" - elif [ $link_size -ne 2 ] ; then - echo " Skipped because link size is not 2" - else - cp -f $testdata/saved16LE-2 testsaved16LE-2 - cp -f $testdata/saved16BE-2 testsaved16BE-2 - cp -f $testdata/saved32LE-2 testsaved32LE-2 - cp -f $testdata/saved32BE-2 testsaved32BE-2 - $sim $valgrind ./pcretest -q $bmode $testdata/testinput22 testtry - if [ $? = 0 ] ; then - $cf $testdata/testoutput22-$bits testtry - if [ $? != 0 ] ; then exit 1; fi - else exit 1 - fi - echo " OK" - fi -fi - -if [ $do23 = yes ] ; then - echo $title23 - if [ "$bits" = "8" -o "$bits" = "32" ] ; then - echo " Skipped when running 8/32-bit tests" - else - $sim $valgrind ./pcretest -q $bmode $testdata/testinput23 testtry - if [ $? = 0 ] ; then - $cf $testdata/testoutput23 testtry - if [ $? != 0 ] ; then exit 1; fi - else exit 1 - fi - echo " OK" - fi -fi - -if [ $do24 = yes ] ; then - echo $title24 - if [ "$bits" = "8" -o "$bits" = "32" ] ; then - echo " Skipped when running 8/32-bit tests" - elif [ $utf -eq 0 ] ; then - echo " Skipped because UTF-$bits support is not available" - else - $sim $valgrind ./pcretest -q $bmode $testdata/testinput24 testtry - if [ $? = 0 ] ; then - $cf $testdata/testoutput24 testtry - if [ $? != 0 ] ; then exit 1; fi - else exit 1 - fi - echo " OK" - fi -fi - -if [ $do25 = yes ] ; then - echo $title25 - if [ "$bits" = "8" -o "$bits" = "16" ] ; then - echo " Skipped when running 8/16-bit tests" - else - $sim $valgrind ./pcretest -q $bmode $testdata/testinput25 testtry - if [ $? = 0 ] ; then - $cf $testdata/testoutput25 testtry - if [ $? != 0 ] ; then exit 1; fi - else exit 1 - fi - echo " OK" - fi -fi - -if [ $do26 = yes ] ; then - echo $title26 - if [ "$bits" = "8" -o "$bits" = "16" ] ; then - echo " Skipped when running 8/16-bit tests" - elif [ $utf -eq 0 ] ; then - echo " Skipped because UTF-$bits support is not available" - else - $sim $valgrind ./pcretest -q $bmode $testdata/testinput26 testtry - if [ $? = 0 ] ; then - $cf $testdata/testoutput26 testtry - if [ $? != 0 ] ; then exit 1; fi - else exit 1 - fi - echo " OK" - fi -fi - -# End of loop for 8/16/32-bit tests -done - -# Clean up local working files -rm -f test3input test3output test3outputA testNinput testsaved* teststderr teststdout testtry - -# End diff --git a/src/third_party/pcre-8.38/RunTest.bat b/src/third_party/pcre-8.38/RunTest.bat deleted file mode 100644 index 35d7f71f9e8..00000000000 --- a/src/third_party/pcre-8.38/RunTest.bat +++ /dev/null @@ -1,616 +0,0 @@ -@echo off
-@rem This file must use CRLF linebreaks to function properly
-@rem and requires both pcretest and pcregrep
-@rem This file was originally contributed by Ralf Junker, and touched up by
-@rem Daniel Richard G. Tests 10-12 added by Philip H.
-@rem Philip H also changed test 3 to use "wintest" files.
-@rem
-@rem Updated by Tom Fortmann to support explicit test numbers on the command line.
-@rem Added argument validation and added error reporting.
-@rem
-@rem MS Windows batch file to run pcretest on testfiles with the correct
-@rem options.
-@rem
-@rem Sheri Pierce added logic to skip feature dependent tests
-@rem tests 4 5 9 15 and 18 require utf support
-@rem tests 6 7 10 16 and 19 require ucp support
-@rem 11 requires ucp and link size 2
-@rem 12 requires presence of jit support
-@rem 13 requires absence of jit support
-@rem Sheri P also added override tests for study and jit testing
-@rem Zoltan Herczeg added libpcre16 support
-@rem Zoltan Herczeg added libpcre32 support
-
-setlocal enabledelayedexpansion
-if [%srcdir%]==[] (
-if exist testdata\ set srcdir=.)
-if [%srcdir%]==[] (
-if exist ..\testdata\ set srcdir=..)
-if [%srcdir%]==[] (
-if exist ..\..\testdata\ set srcdir=..\..)
-if NOT exist %srcdir%\testdata\ (
-Error: echo distribution testdata folder not found!
-call :conferror
-exit /b 1
-goto :eof
-)
-
-if [%pcretest%]==[] set pcretest=.\pcretest.exe
-
-echo source dir is %srcdir%
-echo pcretest=%pcretest%
-
-if NOT exist %pcretest% (
-echo Error: %pcretest% not found!
-echo.
-call :conferror
-exit /b 1
-)
-
-%pcretest% -C linksize >NUL
-set link_size=%ERRORLEVEL%
-%pcretest% -C pcre8 >NUL
-set support8=%ERRORLEVEL%
-%pcretest% -C pcre16 >NUL
-set support16=%ERRORLEVEL%
-%pcretest% -C pcre32 >NUL
-set support32=%ERRORLEVEL%
-%pcretest% -C utf >NUL
-set utf=%ERRORLEVEL%
-%pcretest% -C ucp >NUL
-set ucp=%ERRORLEVEL%
-%pcretest% -C jit >NUL
-set jit=%ERRORLEVEL%
-
-if %support8% EQU 1 (
-if not exist testout8 md testout8
-if not exist testoutstudy8 md testoutstudy8
-if not exist testoutjit8 md testoutjit8
-)
-
-if %support16% EQU 1 (
-if not exist testout16 md testout16
-if not exist testoutstudy16 md testoutstudy16
-if not exist testoutjit16 md testoutjit16
-)
-
-if %support16% EQU 1 (
-if not exist testout32 md testout32
-if not exist testoutstudy32 md testoutstudy32
-if not exist testoutjit32 md testoutjit32
-)
-
-set do1=no
-set do2=no
-set do3=no
-set do4=no
-set do5=no
-set do6=no
-set do7=no
-set do8=no
-set do9=no
-set do10=no
-set do11=no
-set do12=no
-set do13=no
-set do14=no
-set do15=no
-set do16=no
-set do17=no
-set do18=no
-set do19=no
-set do20=no
-set do21=no
-set do22=no
-set do23=no
-set do24=no
-set do25=no
-set do26=no
-set all=yes
-
-for %%a in (%*) do (
- set valid=no
- for %%v in (1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26) do if %%v == %%a set valid=yes
- if "!valid!" == "yes" (
- set do%%a=yes
- set all=no
-) else (
- echo Invalid test number - %%a!
- echo Usage %0 [ test_number ] ...
- echo Where test_number is one or more optional test numbers 1 through 26, default is all tests.
- exit /b 1
-)
-)
-set failed="no"
-
-if "%all%" == "yes" (
- set do1=yes
- set do2=yes
- set do3=yes
- set do4=yes
- set do5=yes
- set do6=yes
- set do7=yes
- set do8=yes
- set do9=yes
- set do10=yes
- set do11=yes
- set do12=yes
- set do13=yes
- set do14=yes
- set do15=yes
- set do16=yes
- set do17=yes
- set do18=yes
- set do19=yes
- set do20=yes
- set do21=yes
- set do22=yes
- set do23=yes
- set do24=yes
- set do25=yes
- set do26=yes
-)
-
-@echo RunTest.bat's pcretest output is written to newly created subfolders named
-@echo testout, testoutstudy and testoutjit.
-@echo.
-
-set mode=
-set bits=8
-
-:nextMode
-if "%mode%" == "" (
- if %support8% EQU 0 goto modeSkip
- echo.
- echo ---- Testing 8-bit library ----
- echo.
-)
-if "%mode%" == "-16" (
- if %support16% EQU 0 goto modeSkip
- echo.
- echo ---- Testing 16-bit library ----
- echo.
-)
-if "%mode%" == "-32" (
- if %support32% EQU 0 goto modeSkip
- echo.
- echo ---- Testing 32-bit library ----
- echo.
-)
-if "%do1%" == "yes" call :do1
-if "%do2%" == "yes" call :do2
-if "%do3%" == "yes" call :do3
-if "%do4%" == "yes" call :do4
-if "%do5%" == "yes" call :do5
-if "%do6%" == "yes" call :do6
-if "%do7%" == "yes" call :do7
-if "%do8%" == "yes" call :do8
-if "%do9%" == "yes" call :do9
-if "%do10%" == "yes" call :do10
-if "%do11%" == "yes" call :do11
-if "%do12%" == "yes" call :do12
-if "%do13%" == "yes" call :do13
-if "%do14%" == "yes" call :do14
-if "%do15%" == "yes" call :do15
-if "%do16%" == "yes" call :do16
-if "%do17%" == "yes" call :do17
-if "%do18%" == "yes" call :do18
-if "%do19%" == "yes" call :do19
-if "%do20%" == "yes" call :do20
-if "%do21%" == "yes" call :do21
-if "%do22%" == "yes" call :do22
-if "%do23%" == "yes" call :do23
-if "%do24%" == "yes" call :do24
-if "%do25%" == "yes" call :do25
-if "%do26%" == "yes" call :do26
-:modeSkip
-if "%mode%" == "" (
- set mode=-16
- set bits=16
- goto nextMode
-)
-if "%mode%" == "-16" (
- set mode=-32
- set bits=32
- goto nextMode
-)
-
-@rem If mode is -32, testing is finished
-if %failed% == "yes" (
-echo In above output, one or more of the various tests failed!
-exit /b 1
-)
-echo All OK
-goto :eof
-
-:runsub
-@rem Function to execute pcretest and compare the output
-@rem Arguments are as follows:
-@rem
-@rem 1 = test number
-@rem 2 = outputdir
-@rem 3 = test name use double quotes
-@rem 4 - 9 = pcretest options
-
-if [%1] == [] (
- echo Missing test number argument!
- exit /b 1
-)
-
-if [%2] == [] (
- echo Missing outputdir!
- exit /b 1
-)
-
-if [%3] == [] (
- echo Missing test name argument!
- exit /b 1
-)
-
-set testinput=testinput%1
-set testoutput=testoutput%1
-if exist %srcdir%\testdata\win%testinput% (
- set testinput=wintestinput%1
- set testoutput=wintestoutput%1
-)
-
-echo Test %1: %3
-%pcretest% %mode% %4 %5 %6 %7 %8 %9 %srcdir%\testdata\%testinput% >%2%bits%\%testoutput%
-if errorlevel 1 (
- echo. failed executing command-line:
- echo. %pcretest% %mode% %4 %5 %6 %7 %8 %9 %srcdir%\testdata\%testinput% ^>%2%bits%\%testoutput%
- set failed="yes"
- goto :eof
-)
-
-set type=
-if [%1]==[11] (
- set type=-%bits%
-)
-if [%1]==[18] (
- set type=-%bits%
-)
-if [%1]==[21] (
- set type=-%bits%
-)
-if [%1]==[22] (
- set type=-%bits%
-)
-
-fc /n %srcdir%\testdata\%testoutput%%type% %2%bits%\%testoutput% >NUL
-
-if errorlevel 1 (
- echo. failed comparison: fc /n %srcdir%\testdata\%testoutput% %2%bits%\%testoutput%
- if [%1]==[2] (
- echo.
- echo ** Test 2 requires a lot of stack. PCRE can be configured to
- echo ** use heap for recursion. Otherwise, to pass Test 2
- echo ** you generally need to allocate 8 mb stack to PCRE.
- echo ** See the 'pcrestack' page for a discussion of PCRE's
- echo ** stack usage.
- echo.
-)
- if [%1]==[3] (
- echo.
- echo ** Test 3 failure usually means french locale is not
- echo ** available on the system, rather than a bug or problem with PCRE.
- echo.
- goto :eof
-)
-
- set failed="yes"
- goto :eof
-)
-
-echo. Passed.
-goto :eof
-
-:do1
-call :runsub 1 testout "Main functionality (Compatible with Perl >= 5.10)" -q
-call :runsub 1 testoutstudy "Test with Study Override" -q -s
-if %jit% EQU 1 call :runsub 1 testoutjit "Test with JIT Override" -q -s+
-goto :eof
-
-:do2
- call :runsub 2 testout "API, errors, internals, and non-Perl stuff" -q
- call :runsub 2 testoutstudy "Test with Study Override" -q -s
- if %jit% EQU 1 call :runsub 2 testoutjit "Test with JIT Override" -q -s+
-goto :eof
-
-:do3
- call :runsub 3 testout "Locale-specific features" -q
- call :runsub 3 testoutstudy "Test with Study Override" -q -s
- if %jit% EQU 1 call :runsub 3 testoutjit "Test with JIT Override" -q -s+
-goto :eof
-
-:do4
-if %utf% EQU 0 (
- echo Test 4 Skipped due to absence of UTF-%bits% support.
- goto :eof
-)
- call :runsub 4 testout "UTF-%bits% support - (Compatible with Perl >= 5.10)" -q
- call :runsub 4 testoutstudy "Test with Study Override" -q -s
- if %jit% EQU 1 call :runsub 4 testoutjit "Test with JIT Override" -q -s+
-goto :eof
-
-:do5
-if %utf% EQU 0 (
- echo Test 5 Skipped due to absence of UTF-%bits% support.
- goto :eof
-)
- call :runsub 5 testout "API, internals, and non-Perl stuff for UTF-%bits%" -q
- call :runsub 5 testoutstudy "Test with Study Override" -q -s
- if %jit% EQU 1 call :runsub 5 testoutjit "Test with JIT Override" -q -s+
-goto :eof
-
-:do6
-if %ucp% EQU 0 (
- echo Test 6 Skipped due to absence of Unicode property support.
- goto :eof
-)
- call :runsub 6 testout "Unicode property support (Compatible with Perl >= 5.10)" -q
- call :runsub 6 testoutstudy "Test with Study Override" -q -s
- if %jit% EQU 1 call :runsub 6 testoutjit "Test with JIT Override" -q -s+
-goto :eof
-
-:do7
-if %ucp% EQU 0 (
- echo Test 7 Skipped due to absence of Unicode property support.
- goto :eof
-)
- call :runsub 7 testout "API, internals, and non-Perl stuff for Unicode property support" -q
- call :runsub 7 testoutstudy "Test with Study Override" -q -s
- if %jit% EQU 1 call :runsub 7 testoutjit "Test with JIT Override" -q -s+
-goto :eof
-
-:do8
- call :runsub 8 testout "DFA matching main functionality" -q -dfa
- call :runsub 8 testoutstudy "Test with Study Override" -q -dfa -s
-goto :eof
-
-:do9
-if %utf% EQU 0 (
- echo Test 9 Skipped due to absence of UTF-%bits% support.
- goto :eof
-)
- call :runsub 9 testout "DFA matching with UTF-%bits%" -q -dfa
- call :runsub 9 testoutstudy "Test with Study Override" -q -dfa -s
- goto :eof
-
-:do10
-if %ucp% EQU 0 (
- echo Test 10 Skipped due to absence of Unicode property support.
- goto :eof
-)
- call :runsub 10 testout "DFA matching with Unicode properties" -q -dfa
- call :runsub 10 testoutstudy "Test with Study Override" -q -dfa -s
-goto :eof
-
-:do11
-if NOT %link_size% EQU 2 (
- echo Test 11 Skipped because link size is not 2.
- goto :eof
-)
-if %ucp% EQU 0 (
- echo Test 11 Skipped due to absence of Unicode property support.
- goto :eof
-)
- call :runsub 11 testout "Internal offsets and code size tests" -q
- call :runsub 11 testoutstudy "Test with Study Override" -q -s
-goto :eof
-
-:do12
-if %jit% EQU 0 (
- echo Test 12 Skipped due to absence of JIT support.
- goto :eof
-)
- call :runsub 12 testout "JIT-specific features (JIT available)" -q
-goto :eof
-
-:do13
-if %jit% EQU 1 (
- echo Test 13 Skipped due to presence of JIT support.
- goto :eof
-)
- call :runsub 13 testout "JIT-specific features (JIT not available)" -q
-goto :eof
-
-:do14
-if NOT %bits% EQU 8 (
- echo Test 14 Skipped when running 16/32-bit tests.
- goto :eof
-)
- copy /Y %srcdir%\testdata\saved16 testsaved16
- copy /Y %srcdir%\testdata\saved32 testsaved32
- call :runsub 14 testout "Specials for the basic 8-bit library" -q
- call :runsub 14 testoutstudy "Test with Study Override" -q -s
- if %jit% EQU 1 call :runsub 14 testoutjit "Test with JIT Override" -q -s+
-goto :eof
-
-:do15
-if NOT %bits% EQU 8 (
- echo Test 15 Skipped when running 16/32-bit tests.
- goto :eof
-)
-if %utf% EQU 0 (
- echo Test 15 Skipped due to absence of UTF-%bits% support.
- goto :eof
-)
- call :runsub 15 testout "Specials for the 8-bit library with UTF-%bits% support" -q
- call :runsub 15 testoutstudy "Test with Study Override" -q -s
- if %jit% EQU 1 call :runsub 15 testoutjit "Test with JIT Override" -q -s+
-goto :eof
-
-:do16
-if NOT %bits% EQU 8 (
- echo Test 16 Skipped when running 16/32-bit tests.
- goto :eof
-)
-if %ucp% EQU 0 (
- echo Test 16 Skipped due to absence of Unicode property support.
- goto :eof
-)
- call :runsub 16 testout "Specials for the 8-bit library with Unicode propery support" -q
- call :runsub 16 testoutstudy "Test with Study Override" -q -s
- if %jit% EQU 1 call :runsub 16 testoutjit "Test with JIT Override" -q -s+
-goto :eof
-
-:do17
-if %bits% EQU 8 (
- echo Test 17 Skipped when running 8-bit tests.
- goto :eof
-)
- call :runsub 17 testout "Specials for the basic 16/32-bit library" -q
- call :runsub 17 testoutstudy "Test with Study Override" -q -s
- if %jit% EQU 1 call :runsub 17 testoutjit "Test with JIT Override" -q -s+
-goto :eof
-
-:do18
-if %bits% EQU 8 (
- echo Test 18 Skipped when running 8-bit tests.
- goto :eof
-)
-if %utf% EQU 0 (
- echo Test 18 Skipped due to absence of UTF-%bits% support.
- goto :eof
-)
- call :runsub 18 testout "Specials for the 16/32-bit library with UTF-%bits% support" -q
- call :runsub 18 testoutstudy "Test with Study Override" -q -s
- if %jit% EQU 1 call :runsub 18 testoutjit "Test with JIT Override" -q -s+
-goto :eof
-
-:do19
-if %bits% EQU 8 (
- echo Test 19 Skipped when running 8-bit tests.
- goto :eof
-)
-if %ucp% EQU 0 (
- echo Test 19 Skipped due to absence of Unicode property support.
- goto :eof
-)
- call :runsub 19 testout "Specials for the 16/32-bit library with Unicode property support" -q
- call :runsub 19 testoutstudy "Test with Study Override" -q -s
- if %jit% EQU 1 call :runsub 19 testoutjit "Test with JIT Override" -q -s+
-goto :eof
-
-:do20
-if %bits% EQU 8 (
- echo Test 20 Skipped when running 8-bit tests.
- goto :eof
-)
- call :runsub 20 testout "DFA specials for the basic 16/32-bit library" -q -dfa
- call :runsub 20 testoutstudy "Test with Study Override" -q -dfa -s
-goto :eof
-
-:do21
-if %bits% EQU 8 (
- echo Test 21 Skipped when running 8-bit tests.
- goto :eof
-)
-if NOT %link_size% EQU 2 (
- echo Test 21 Skipped because link size is not 2.
- goto :eof
-)
-copy /Y %srcdir%\testdata\saved8 testsaved8
-copy /Y %srcdir%\testdata\saved16LE-1 testsaved16LE-1
-copy /Y %srcdir%\testdata\saved16BE-1 testsaved16BE-1
-copy /Y %srcdir%\testdata\saved32LE-1 testsaved32LE-1
-copy /Y %srcdir%\testdata\saved32BE-1 testsaved32BE-1
-call :runsub 21 testout "Reloads for the basic 16/32-bit library" -q
-call :runsub 21 testoutstudy "Test with Study Override" -q -s
-if %jit% EQU 1 call :runsub 21 testoutjit "Test with JIT Override" -q -s+
-goto :eof
-
-:do22
-if %bits% EQU 8 (
- echo Test 22 Skipped when running 8-bit tests.
- goto :eof
-)
-if %utf% EQU 0 (
- echo Test 22 Skipped due to absence of UTF-%bits% support.
- goto :eof
-)
-if NOT %link_size% EQU 2 (
- echo Test 22 Skipped because link size is not 2.
- goto :eof
-)
-copy /Y %srcdir%\testdata\saved16LE-2 testsaved16LE-2
-copy /Y %srcdir%\testdata\saved16BE-2 testsaved16BE-2
-copy /Y %srcdir%\testdata\saved32LE-2 testsaved32LE-2
-copy /Y %srcdir%\testdata\saved32BE-2 testsaved32BE-2
-call :runsub 22 testout "Reloads for the 16/32-bit library with UTF-16/32 support" -q
-call :runsub 22 testoutstudy "Test with Study Override" -q -s
-if %jit% EQU 1 call :runsub 22 testoutjit "Test with JIT Override" -q -s+
-goto :eof
-
-:do23
-if NOT %bits% EQU 16 (
- echo Test 23 Skipped when running 8/32-bit tests.
- goto :eof
-)
-call :runsub 23 testout "Specials for the 16-bit library" -q
-call :runsub 23 testoutstudy "Test with Study Override" -q -s
-if %jit% EQU 1 call :runsub 23 testoutjit "Test with JIT Override" -q -s+
-goto :eof
-
-:do24
-if NOT %bits% EQU 16 (
- echo Test 24 Skipped when running 8/32-bit tests.
- goto :eof
-)
-if %utf% EQU 0 (
- echo Test 24 Skipped due to absence of UTF-%bits% support.
- goto :eof
-)
-call :runsub 24 testout "Specials for the 16-bit library with UTF-16 support" -q
-call :runsub 24 testoutstudy "Test with Study Override" -q -s
-if %jit% EQU 1 call :runsub 24 testoutjit "Test with JIT Override" -q -s+
-goto :eof
-
-:do25
-if NOT %bits% EQU 32 (
- echo Test 25 Skipped when running 8/16-bit tests.
- goto :eof
-)
-call :runsub 25 testout "Specials for the 32-bit library" -q
-call :runsub 25 testoutstudy "Test with Study Override" -q -s
-if %jit% EQU 1 call :runsub 25 testoutjit "Test with JIT Override" -q -s+
-goto :eof
-
-:do26
-if NOT %bits% EQU 32 (
- echo Test 26 Skipped when running 8/16-bit tests.
- goto :eof
-)
-if %utf% EQU 0 (
- echo Test 26 Skipped due to absence of UTF-%bits% support.
- goto :eof
-)
-call :runsub 26 testout "Specials for the 32-bit library with UTF-32 support" -q
-call :runsub 26 testoutstudy "Test with Study Override" -q -s
-if %jit% EQU 1 call :runsub 26 testoutjit "Test with JIT Override" -q -s+
-goto :eof
-
-:conferror
-@echo.
-@echo Either your build is incomplete or you have a configuration error.
-@echo.
-@echo If configured with cmake and executed via "make test" or the MSVC "RUN_TESTS"
-@echo project, pcre_test.bat defines variables and automatically calls RunTest.bat.
-@echo For manual testing of all available features, after configuring with cmake
-@echo and building, you can run the built pcre_test.bat. For best results with
-@echo cmake builds and tests avoid directories with full path names that include
-@echo spaces for source or build.
-@echo.
-@echo Otherwise, if the build dir is in a subdir of the source dir, testdata needed
-@echo for input and verification should be found automatically when (from the
-@echo location of the the built exes) you call RunTest.bat. By default RunTest.bat
-@echo runs all tests compatible with the linked pcre library but it can be given
-@echo a test number as an argument.
-@echo.
-@echo If the build dir is not under the source dir you can either copy your exes
-@echo to the source folder or copy RunTest.bat and the testdata folder to the
-@echo location of your built exes and then run RunTest.bat.
-@echo.
-goto :eof
diff --git a/src/third_party/pcre-8.38/SConscript b/src/third_party/pcre-8.38/SConscript deleted file mode 100644 index e7b9a59a550..00000000000 --- a/src/third_party/pcre-8.38/SConscript +++ /dev/null @@ -1,68 +0,0 @@ -# -*- mode: python -*- - -Import("env") - -env = env.Clone() -env.Append( CPPDEFINES=[ "HAVE_CONFIG_H", ] ) - -def removeIfPresent(lst, item): - try: - lst.remove(item) - except ValueError: - pass - -for to_remove in ['-Werror', '-Wall', '-W']: - removeIfPresent(env['CCFLAGS'], to_remove) - -# Directories that include generated config.h for various platforms -# -# Generated via -# AutoTools (non-Windows) -# ./configure --disable-stack-for-recursion --enable-utf --enable-unicode-properties -# --with-match-limit=200000 --with-match-limit-recursion=4000 --enable-shared=no -# CMake (Windows) -# -DPCRE_SUPPORT_PCREGREP_JIT:BOOL="0" -DPCRE_BUILD_TESTS:BOOL="0" -# -DPCRE_POSIX_MALLOC_THRESHOLD:STRING="10" -DPCRE_MATCH_LIMIT_RECURSION:STRING="4000" -# -DPCRE_NO_RECURSE:BOOL="1" -DPCRE_LINK_SIZE:STRING="2" -DPCRE_NEWLINE:STRING="LF" -# -DPCRE_SUPPORT_UNICODE_PROPERTIES:BOOL="1" -DPCREGREP_BUFSIZE:STRING="20480" -# -DPCRE_MATCH_LIMIT:STRING="200000" -DPCRE_PARENS_NEST_LIMIT:STRING="250" -# -DPCRE_SUPPORT_UTF:BOOL="1" -# -if env.TargetOSIs('windows'): - env.Append(CPPPATH=["build_windows"]) -elif env.TargetOSIs('solaris'): - env.Append(CPPPATH=["build_solaris"]) -else: - env.Append(CPPPATH=["build_posix"]) - -env.Library( "pcrecpp", [ - # pcre - "pcre_byte_order.c", - "pcre_compile.c", - "pcre_config.c", - "pcre_dfa_exec.c", - "pcre_exec.c", - "pcre_fullinfo.c", - "pcre_get.c", - "pcre_globals.c", - "pcre_maketables.c", - "pcre_newline.c", - "pcre_ord2utf8.c", - "pcre_refcount.c", - "pcre_string_utils.c", - "pcre_study.c", - "pcre_tables.c", - "pcre_ucd.c", - "pcre_valid_utf8.c", - "pcre_version.c", - "pcre_xclass.c", - # pcre nodist - "pcre_chartables.c", - # pcre cpp - "pcrecpp.cc", - "pcre_scanner.cc", - "pcre_stringpiece.cc", - # pcre posix - "pcreposix.c", - ] ) - diff --git a/src/third_party/pcre-8.38/ar-lib b/src/third_party/pcre-8.38/ar-lib deleted file mode 100755 index 463b9ec0206..00000000000 --- a/src/third_party/pcre-8.38/ar-lib +++ /dev/null @@ -1,270 +0,0 @@ -#! /bin/sh -# Wrapper for Microsoft lib.exe - -me=ar-lib -scriptversion=2012-03-01.08; # UTC - -# Copyright (C) 2010-2014 Free Software Foundation, Inc. -# Written by Peter Rosin <peda@lysator.liu.se>. -# -# This program is free software; you can redistribute it and/or modify -# it under the terms of the GNU General Public License as published by -# the Free Software Foundation; either version 2, or (at your option) -# any later version. -# -# This program is distributed in the hope that it will be useful, -# but WITHOUT ANY WARRANTY; without even the implied warranty of -# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the -# GNU General Public License for more details. -# -# You should have received a copy of the GNU General Public License -# along with this program. If not, see <http://www.gnu.org/licenses/>. - -# As a special exception to the GNU General Public License, if you -# distribute this file as part of a program that contains a -# configuration script generated by Autoconf, you may include it under -# the same distribution terms that you use for the rest of that program. - -# This file is maintained in Automake, please report -# bugs to <bug-automake@gnu.org> or send patches to -# <automake-patches@gnu.org>. - - -# func_error message -func_error () -{ - echo "$me: $1" 1>&2 - exit 1 -} - -file_conv= - -# func_file_conv build_file -# Convert a $build file to $host form and store it in $file -# Currently only supports Windows hosts. -func_file_conv () -{ - file=$1 - case $file in - / | /[!/]*) # absolute file, and not a UNC file - if test -z "$file_conv"; then - # lazily determine how to convert abs files - case `uname -s` in - MINGW*) - file_conv=mingw - ;; - CYGWIN*) - file_conv=cygwin - ;; - *) - file_conv=wine - ;; - esac - fi - case $file_conv in - mingw) - file=`cmd //C echo "$file " | sed -e 's/"\(.*\) " *$/\1/'` - ;; - cygwin) - file=`cygpath -m "$file" || echo "$file"` - ;; - wine) - file=`winepath -w "$file" || echo "$file"` - ;; - esac - ;; - esac -} - -# func_at_file at_file operation archive -# Iterate over all members in AT_FILE performing OPERATION on ARCHIVE -# for each of them. -# When interpreting the content of the @FILE, do NOT use func_file_conv, -# since the user would need to supply preconverted file names to -# binutils ar, at least for MinGW. -func_at_file () -{ - operation=$2 - archive=$3 - at_file_contents=`cat "$1"` - eval set x "$at_file_contents" - shift - - for member - do - $AR -NOLOGO $operation:"$member" "$archive" || exit $? - done -} - -case $1 in - '') - func_error "no command. Try '$0 --help' for more information." - ;; - -h | --h*) - cat <<EOF -Usage: $me [--help] [--version] PROGRAM ACTION ARCHIVE [MEMBER...] - -Members may be specified in a file named with @FILE. -EOF - exit $? - ;; - -v | --v*) - echo "$me, version $scriptversion" - exit $? - ;; -esac - -if test $# -lt 3; then - func_error "you must specify a program, an action and an archive" -fi - -AR=$1 -shift -while : -do - if test $# -lt 2; then - func_error "you must specify a program, an action and an archive" - fi - case $1 in - -lib | -LIB \ - | -ltcg | -LTCG \ - | -machine* | -MACHINE* \ - | -subsystem* | -SUBSYSTEM* \ - | -verbose | -VERBOSE \ - | -wx* | -WX* ) - AR="$AR $1" - shift - ;; - *) - action=$1 - shift - break - ;; - esac -done -orig_archive=$1 -shift -func_file_conv "$orig_archive" -archive=$file - -# strip leading dash in $action -action=${action#-} - -delete= -extract= -list= -quick= -replace= -index= -create= - -while test -n "$action" -do - case $action in - d*) delete=yes ;; - x*) extract=yes ;; - t*) list=yes ;; - q*) quick=yes ;; - r*) replace=yes ;; - s*) index=yes ;; - S*) ;; # the index is always updated implicitly - c*) create=yes ;; - u*) ;; # TODO: don't ignore the update modifier - v*) ;; # TODO: don't ignore the verbose modifier - *) - func_error "unknown action specified" - ;; - esac - action=${action#?} -done - -case $delete$extract$list$quick$replace,$index in - yes,* | ,yes) - ;; - yesyes*) - func_error "more than one action specified" - ;; - *) - func_error "no action specified" - ;; -esac - -if test -n "$delete"; then - if test ! -f "$orig_archive"; then - func_error "archive not found" - fi - for member - do - case $1 in - @*) - func_at_file "${1#@}" -REMOVE "$archive" - ;; - *) - func_file_conv "$1" - $AR -NOLOGO -REMOVE:"$file" "$archive" || exit $? - ;; - esac - done - -elif test -n "$extract"; then - if test ! -f "$orig_archive"; then - func_error "archive not found" - fi - if test $# -gt 0; then - for member - do - case $1 in - @*) - func_at_file "${1#@}" -EXTRACT "$archive" - ;; - *) - func_file_conv "$1" - $AR -NOLOGO -EXTRACT:"$file" "$archive" || exit $? - ;; - esac - done - else - $AR -NOLOGO -LIST "$archive" | sed -e 's/\\/\\\\/g' | while read member - do - $AR -NOLOGO -EXTRACT:"$member" "$archive" || exit $? - done - fi - -elif test -n "$quick$replace"; then - if test ! -f "$orig_archive"; then - if test -z "$create"; then - echo "$me: creating $orig_archive" - fi - orig_archive= - else - orig_archive=$archive - fi - - for member - do - case $1 in - @*) - func_file_conv "${1#@}" - set x "$@" "@$file" - ;; - *) - func_file_conv "$1" - set x "$@" "$file" - ;; - esac - shift - shift - done - - if test -n "$orig_archive"; then - $AR -NOLOGO -OUT:"$archive" "$orig_archive" "$@" || exit $? - else - $AR -NOLOGO -OUT:"$archive" "$@" || exit $? - fi - -elif test -n "$list"; then - if test ! -f "$orig_archive"; then - func_error "archive not found" - fi - $AR -NOLOGO -LIST "$archive" || exit $? -fi diff --git a/src/third_party/pcre-8.38/build_posix/config.h b/src/third_party/pcre-8.38/build_posix/config.h deleted file mode 100644 index eab6a47ed6b..00000000000 --- a/src/third_party/pcre-8.38/build_posix/config.h +++ /dev/null @@ -1,348 +0,0 @@ -/* config.h. Generated from config.h.in by configure. */ -/* config.h.in. Generated from configure.ac by autoheader. */ - - -/* PCRE is written in Standard C, but there are a few non-standard things it -can cope with, allowing it to run on SunOS4 and other "close to standard" -systems. - -In environments that support the GNU autotools, config.h.in is converted into -config.h by the "configure" script. In environments that use CMake, -config-cmake.in is converted into config.h. If you are going to build PCRE "by -hand" without using "configure" or CMake, you should copy the distributed -config.h.generic to config.h, and edit the macro definitions to be the way you -need them. You must then add -DHAVE_CONFIG_H to all of your compile commands, -so that config.h is included at the start of every source. - -Alternatively, you can avoid editing by using -D on the compiler command line -to set the macro values. In this case, you do not have to set -DHAVE_CONFIG_H, -but if you do, default values will be taken from config.h for non-boolean -macros that are not defined on the command line. - -Boolean macros such as HAVE_STDLIB_H and SUPPORT_PCRE8 should either be defined -(conventionally to 1) for TRUE, and not defined at all for FALSE. All such -macros are listed as a commented #undef in config.h.generic. Macros such as -MATCH_LIMIT, whose actual value is relevant, have defaults defined, but are -surrounded by #ifndef/#endif lines so that the value can be overridden by -D. - -PCRE uses memmove() if HAVE_MEMMOVE is defined; otherwise it uses bcopy() if -HAVE_BCOPY is defined. If your system has neither bcopy() nor memmove(), make -sure both macros are undefined; an emulation function will then be used. */ - -/* By default, the \R escape sequence matches any Unicode line ending - character or sequence of characters. If BSR_ANYCRLF is defined (to any - value), this is changed so that backslash-R matches only CR, LF, or CRLF. - The build-time default can be overridden by the user of PCRE at runtime. */ -/* #undef BSR_ANYCRLF */ - -/* If you are compiling for a system that uses EBCDIC instead of ASCII - character codes, define this macro to any value. You must also edit the - NEWLINE macro below to set a suitable EBCDIC newline, commonly 21 (0x15). - On systems that can use "configure" or CMake to set EBCDIC, NEWLINE is - automatically adjusted. When EBCDIC is set, PCRE assumes that all input - strings are in EBCDIC. If you do not define this macro, PCRE will assume - input strings are ASCII or UTF-8/16/32 Unicode. It is not possible to build - a version of PCRE that supports both EBCDIC and UTF-8/16/32. */ -/* #undef EBCDIC */ - -/* In an EBCDIC environment, define this macro to any value to arrange for the - NL character to be 0x25 instead of the default 0x15. NL plays the role that - LF does in an ASCII/Unicode environment. The value must also be set in the - NEWLINE macro below. On systems that can use "configure" or CMake to set - EBCDIC_NL25, the adjustment of NEWLINE is automatic. */ -/* #undef EBCDIC_NL25 */ - -/* Define to 1 if you have the `bcopy' function. */ -#define HAVE_BCOPY 1 - -/* Define to 1 if you have the <bits/type_traits.h> header file. */ -/* #undef HAVE_BITS_TYPE_TRAITS_H */ - -/* Define to 1 if you have the <bzlib.h> header file. */ -#define HAVE_BZLIB_H 1 - -/* Define to 1 if you have the <dirent.h> header file. */ -#define HAVE_DIRENT_H 1 - -/* Define to 1 if you have the <dlfcn.h> header file. */ -#define HAVE_DLFCN_H 1 - -/* Define to 1 if you have the <editline/readline.h> header file. */ -/* #undef HAVE_EDITLINE_READLINE_H */ - -/* Define to 1 if you have the <edit/readline/readline.h> header file. */ -/* #undef HAVE_EDIT_READLINE_READLINE_H */ - -/* Define to 1 if you have the <inttypes.h> header file. */ -#define HAVE_INTTYPES_H 1 - -/* Define to 1 if you have the <limits.h> header file. */ -#define HAVE_LIMITS_H 1 - -/* Define to 1 if the system has the type `long long'. */ -#define HAVE_LONG_LONG 1 - -/* Define to 1 if you have the `memmove' function. */ -#define HAVE_MEMMOVE 1 - -/* Define to 1 if you have the <memory.h> header file. */ -#define HAVE_MEMORY_H 1 - -/* Define if you have POSIX threads libraries and header files. */ -/* #undef HAVE_PTHREAD */ - -/* Have PTHREAD_PRIO_INHERIT. */ -/* #undef HAVE_PTHREAD_PRIO_INHERIT */ - -/* Define to 1 if you have the <readline/history.h> header file. */ -/* #undef HAVE_READLINE_HISTORY_H */ - -/* Define to 1 if you have the <readline/readline.h> header file. */ -/* #undef HAVE_READLINE_READLINE_H */ - -/* Define to 1 if you have the <stdint.h> header file. */ -#define HAVE_STDINT_H 1 - -/* Define to 1 if you have the <stdlib.h> header file. */ -#define HAVE_STDLIB_H 1 - -/* Define to 1 if you have the `strerror' function. */ -#define HAVE_STRERROR 1 - -/* Define to 1 if you have the <string> header file. */ -#define HAVE_STRING 1 - -/* Define to 1 if you have the <strings.h> header file. */ -#define HAVE_STRINGS_H 1 - -/* Define to 1 if you have the <string.h> header file. */ -#define HAVE_STRING_H 1 - -/* Define to 1 if you have `strtoimax'. */ -/* #undef HAVE_STRTOIMAX */ - -/* Define to 1 if you have `strtoll'. */ -/* #undef HAVE_STRTOLL */ - -/* Define to 1 if you have `strtoq'. */ -#define HAVE_STRTOQ 1 - -/* Define to 1 if you have the <sys/stat.h> header file. */ -#define HAVE_SYS_STAT_H 1 - -/* Define to 1 if you have the <sys/types.h> header file. */ -#define HAVE_SYS_TYPES_H 1 - -/* Define to 1 if you have the <type_traits.h> header file. */ -/* #undef HAVE_TYPE_TRAITS_H */ - -/* Define to 1 if you have the <unistd.h> header file. */ -#define HAVE_UNISTD_H 1 - -/* Define to 1 if the system has the type `unsigned long long'. */ -#define HAVE_UNSIGNED_LONG_LONG 1 - -/* Define to 1 if the compiler supports simple visibility declarations. */ -#define HAVE_VISIBILITY 1 - -/* Define to 1 if you have the <windows.h> header file. */ -/* #undef HAVE_WINDOWS_H */ - -/* Define to 1 if you have the <zlib.h> header file. */ -#define HAVE_ZLIB_H 1 - -/* Define to 1 if you have `_strtoi64'. */ -/* #undef HAVE__STRTOI64 */ - -/* The value of LINK_SIZE determines the number of bytes used to store links - as offsets within the compiled regex. The default is 2, which allows for - compiled patterns up to 64K long. This covers the vast majority of cases. - However, PCRE can also be compiled to use 3 or 4 bytes instead. This allows - for longer patterns in extreme cases. */ -#define LINK_SIZE 2 - -/* Define to the sub-directory where libtool stores uninstalled libraries. */ -#define LT_OBJDIR ".libs/" - -/* The value of MATCH_LIMIT determines the default number of times the - internal match() function can be called during a single execution of - pcre_exec(). There is a runtime interface for setting a different limit. - The limit exists in order to catch runaway regular expressions that take - for ever to determine that they do not match. The default is set very large - so that it does not accidentally catch legitimate cases. */ -#define MATCH_LIMIT 200000 - -/* The above limit applies to all calls of match(), whether or not they - increase the recursion depth. In some environments it is desirable to limit - the depth of recursive calls of match() more strictly, in order to restrict - the maximum amount of stack (or heap, if NO_RECURSE is defined) that is - used. The value of MATCH_LIMIT_RECURSION applies only to recursive calls of - match(). To have any useful effect, it must be less than the value of - MATCH_LIMIT. The default is to use the same value as MATCH_LIMIT. There is - a runtime method for setting a different limit. */ -#define MATCH_LIMIT_RECURSION 4000 - -/* This limit is parameterized just in case anybody ever wants to change it. - Care must be taken if it is increased, because it guards against integer - overflow caused by enormously large patterns. */ -#define MAX_NAME_COUNT 10000 - -/* This limit is parameterized just in case anybody ever wants to change it. - Care must be taken if it is increased, because it guards against integer - overflow caused by enormously large patterns. */ -#define MAX_NAME_SIZE 32 - -/* The value of NEWLINE determines the default newline character sequence. - PCRE client programs can override this by selecting other values at run - time. In ASCII environments, the value can be 10 (LF), 13 (CR), or 3338 - (CRLF); in EBCDIC environments the value can be 21 or 37 (LF), 13 (CR), or - 3349 or 3365 (CRLF) because there are two alternative codepoints (0x15 and - 0x25) that are used as the NL line terminator that is equivalent to ASCII - LF. In both ASCII and EBCDIC environments the value can also be -1 (ANY), - or -2 (ANYCRLF). */ -#define NEWLINE 10 - -/* PCRE uses recursive function calls to handle backtracking while matching. - This can sometimes be a problem on systems that have stacks of limited - size. Define NO_RECURSE to any value to get a version that doesn't use - recursion in the match() function; instead it creates its own stack by - steam using pcre_recurse_malloc() to obtain memory from the heap. For more - detail, see the comments and other stuff just above the match() function. - */ -#define NO_RECURSE /**/ - -/* Name of package */ -#define PACKAGE "pcre" - -/* Define to the address where bug reports for this package should be sent. */ -#define PACKAGE_BUGREPORT "" - -/* Define to the full name of this package. */ -#define PACKAGE_NAME "PCRE" - -/* Define to the full name and version of this package. */ -#define PACKAGE_STRING "PCRE 8.38" - -/* Define to the one symbol short name of this package. */ -#define PACKAGE_TARNAME "pcre" - -/* Define to the home page for this package. */ -#define PACKAGE_URL "" - -/* Define to the version of this package. */ -#define PACKAGE_VERSION "8.38" - -/* The value of PARENS_NEST_LIMIT specifies the maximum depth of nested - parentheses (of any kind) in a pattern. This limits the amount of system - stack that is used while compiling a pattern. */ -#define PARENS_NEST_LIMIT 250 - -/* to make a symbol visible */ -#define PCRECPP_EXP_DECL extern __attribute__ ((visibility ("default"))) - -/* to make a symbol visible */ -#define PCRECPP_EXP_DEFN __attribute__ ((visibility ("default"))) - -/* The value of PCREGREP_BUFSIZE determines the size of buffer used by - pcregrep to hold parts of the file it is searching. This is also the - minimum value. The actual amount of memory used by pcregrep is three times - this number, because it allows for the buffering of "before" and "after" - lines. */ -#define PCREGREP_BUFSIZE 20480 - -/* to make a symbol visible */ -#define PCREPOSIX_EXP_DECL extern __attribute__ ((visibility ("default"))) - -/* to make a symbol visible */ -#define PCREPOSIX_EXP_DEFN extern __attribute__ ((visibility ("default"))) - -/* to make a symbol visible */ -#define PCRE_EXP_DATA_DEFN __attribute__ ((visibility ("default"))) - -/* to make a symbol visible */ -#define PCRE_EXP_DECL extern __attribute__ ((visibility ("default"))) - - -/* If you are compiling for a system other than a Unix-like system or - Win32, and it needs some magic to be inserted before the definition - of a function that is exported by the library, define this macro to - contain the relevant magic. If you do not define this macro, a suitable - __declspec value is used for Windows systems; in other environments - "extern" is used for a C compiler and "extern C" for a C++ compiler. - This macro apears at the start of every exported function that is part - of the external API. It does not appear on functions that are "external" - in the C sense, but which are internal to the library. */ -#define PCRE_EXP_DEFN __attribute__ ((visibility ("default"))) - -/* Define to any value if linking statically (TODO: make nice with Libtool) */ -#define PCRE_STATIC 1 - -/* When calling PCRE via the POSIX interface, additional working storage is - required for holding the pointers to capturing substrings because PCRE - requires three integers per substring, whereas the POSIX interface provides - only two. If the number of expected substrings is small, the wrapper - function uses space on the stack, because this is faster than using - malloc() for each call. The threshold above which the stack is no longer - used is defined by POSIX_MALLOC_THRESHOLD. */ -#define POSIX_MALLOC_THRESHOLD 10 - -/* Define to necessary symbol if this constant uses a non-standard name on - your system. */ -/* #undef PTHREAD_CREATE_JOINABLE */ - -/* Define to 1 if you have the ANSI C header files. */ -#define STDC_HEADERS 1 - -/* Define to any value to enable support for Just-In-Time compiling. */ -/* #undef SUPPORT_JIT */ - -/* Define to any value to allow pcregrep to be linked with libbz2, so that it - is able to handle .bz2 files. */ -/* #undef SUPPORT_LIBBZ2 */ - -/* Define to any value to allow pcretest to be linked with libedit. */ -/* #undef SUPPORT_LIBEDIT */ - -/* Define to any value to allow pcretest to be linked with libreadline. */ -/* #undef SUPPORT_LIBREADLINE */ - -/* Define to any value to allow pcregrep to be linked with libz, so that it is - able to handle .gz files. */ -/* #undef SUPPORT_LIBZ */ - -/* Define to any value to enable the 16 bit PCRE library. */ -/* #undef SUPPORT_PCRE16 */ - -/* Define to any value to enable the 32 bit PCRE library. */ -/* #undef SUPPORT_PCRE32 */ - -/* Define to any value to enable the 8 bit PCRE library. */ -#define SUPPORT_PCRE8 /**/ - -/* Define to any value to enable JIT support in pcregrep. */ -/* #undef SUPPORT_PCREGREP_JIT */ - -/* Define to any value to enable support for Unicode properties. */ -#define SUPPORT_UCP /**/ - -/* Define to any value to enable support for the UTF-8/16/32 Unicode encoding. - This will work even in an EBCDIC environment, but it is incompatible with - the EBCDIC macro. That is, PCRE can support *either* EBCDIC code *or* - ASCII/UTF-8/16/32, but not both at once. */ -#define SUPPORT_UTF /**/ - -/* Define to any value for valgrind support to find invalid memory reads. */ -/* #undef SUPPORT_VALGRIND */ - -/* Version number of package */ -#define VERSION "8.38" - -/* Define to empty if `const' does not conform to ANSI C. */ -/* #undef const */ - -/* Define to the type of a signed integer type of width exactly 64 bits if - such a type exists and the standard includes do not define it. */ -/* #undef int64_t */ - -/* Define to `unsigned int' if <sys/types.h> does not define. */ -/* #undef size_t */ diff --git a/src/third_party/pcre-8.38/build_solaris/config.h b/src/third_party/pcre-8.38/build_solaris/config.h deleted file mode 100644 index a2d53fe5fc5..00000000000 --- a/src/third_party/pcre-8.38/build_solaris/config.h +++ /dev/null @@ -1,348 +0,0 @@ -/* config.h. Generated from config.h.in by configure. */ -/* config.h.in. Generated from configure.ac by autoheader. */ - - -/* PCRE is written in Standard C, but there are a few non-standard things it -can cope with, allowing it to run on SunOS4 and other "close to standard" -systems. - -In environments that support the GNU autotools, config.h.in is converted into -config.h by the "configure" script. In environments that use CMake, -config-cmake.in is converted into config.h. If you are going to build PCRE "by -hand" without using "configure" or CMake, you should copy the distributed -config.h.generic to config.h, and edit the macro definitions to be the way you -need them. You must then add -DHAVE_CONFIG_H to all of your compile commands, -so that config.h is included at the start of every source. - -Alternatively, you can avoid editing by using -D on the compiler command line -to set the macro values. In this case, you do not have to set -DHAVE_CONFIG_H, -but if you do, default values will be taken from config.h for non-boolean -macros that are not defined on the command line. - -Boolean macros such as HAVE_STDLIB_H and SUPPORT_PCRE8 should either be defined -(conventionally to 1) for TRUE, and not defined at all for FALSE. All such -macros are listed as a commented #undef in config.h.generic. Macros such as -MATCH_LIMIT, whose actual value is relevant, have defaults defined, but are -surrounded by #ifndef/#endif lines so that the value can be overridden by -D. - -PCRE uses memmove() if HAVE_MEMMOVE is defined; otherwise it uses bcopy() if -HAVE_BCOPY is defined. If your system has neither bcopy() nor memmove(), make -sure both macros are undefined; an emulation function will then be used. */ - -/* By default, the \R escape sequence matches any Unicode line ending - character or sequence of characters. If BSR_ANYCRLF is defined (to any - value), this is changed so that backslash-R matches only CR, LF, or CRLF. - The build-time default can be overridden by the user of PCRE at runtime. */ -/* #undef BSR_ANYCRLF */ - -/* If you are compiling for a system that uses EBCDIC instead of ASCII - character codes, define this macro to any value. You must also edit the - NEWLINE macro below to set a suitable EBCDIC newline, commonly 21 (0x15). - On systems that can use "configure" or CMake to set EBCDIC, NEWLINE is - automatically adjusted. When EBCDIC is set, PCRE assumes that all input - strings are in EBCDIC. If you do not define this macro, PCRE will assume - input strings are ASCII or UTF-8/16/32 Unicode. It is not possible to build - a version of PCRE that supports both EBCDIC and UTF-8/16/32. */ -/* #undef EBCDIC */ - -/* In an EBCDIC environment, define this macro to any value to arrange for the - NL character to be 0x25 instead of the default 0x15. NL plays the role that - LF does in an ASCII/Unicode environment. The value must also be set in the - NEWLINE macro below. On systems that can use "configure" or CMake to set - EBCDIC_NL25, the adjustment of NEWLINE is automatic. */ -/* #undef EBCDIC_NL25 */ - -/* Define to 1 if you have the `bcopy' function. */ -#define HAVE_BCOPY 1 - -/* Define to 1 if you have the <bits/type_traits.h> header file. */ -/* #undef HAVE_BITS_TYPE_TRAITS_H */ - -/* Define to 1 if you have the <bzlib.h> header file. */ -#define HAVE_BZLIB_H 1 - -/* Define to 1 if you have the <dirent.h> header file. */ -#define HAVE_DIRENT_H 1 - -/* Define to 1 if you have the <dlfcn.h> header file. */ -#define HAVE_DLFCN_H 1 - -/* Define to 1 if you have the <editline/readline.h> header file. */ -/* #undef HAVE_EDITLINE_READLINE_H */ - -/* Define to 1 if you have the <edit/readline/readline.h> header file. */ -/* #undef HAVE_EDIT_READLINE_READLINE_H */ - -/* Define to 1 if you have the <inttypes.h> header file. */ -#define HAVE_INTTYPES_H 1 - -/* Define to 1 if you have the <limits.h> header file. */ -#define HAVE_LIMITS_H 1 - -/* Define to 1 if the system has the type `long long'. */ -#define HAVE_LONG_LONG 1 - -/* Define to 1 if you have the `memmove' function. */ -#define HAVE_MEMMOVE 1 - -/* Define to 1 if you have the <memory.h> header file. */ -#define HAVE_MEMORY_H 1 - -/* Define if you have POSIX threads libraries and header files. */ -/* #undef HAVE_PTHREAD */ - -/* Have PTHREAD_PRIO_INHERIT. */ -/* #undef HAVE_PTHREAD_PRIO_INHERIT */ - -/* Define to 1 if you have the <readline/history.h> header file. */ -/* #undef HAVE_READLINE_HISTORY_H */ - -/* Define to 1 if you have the <readline/readline.h> header file. */ -/* #undef HAVE_READLINE_READLINE_H */ - -/* Define to 1 if you have the <stdint.h> header file. */ -#define HAVE_STDINT_H 1 - -/* Define to 1 if you have the <stdlib.h> header file. */ -#define HAVE_STDLIB_H 1 - -/* Define to 1 if you have the `strerror' function. */ -#define HAVE_STRERROR 1 - -/* Define to 1 if you have the <string> header file. */ -#define HAVE_STRING 1 - -/* Define to 1 if you have the <strings.h> header file. */ -#define HAVE_STRINGS_H 1 - -/* Define to 1 if you have the <string.h> header file. */ -#define HAVE_STRING_H 1 - -/* Define to 1 if you have `strtoimax'. */ -/* #undef HAVE_STRTOIMAX */ - -/* Define to 1 if you have `strtoll'. */ -#define HAVE_STRTOLL 1 - -/* Define to 1 if you have `strtoq'. */ -/* #undef HAVE_STRTOQ */ - -/* Define to 1 if you have the <sys/stat.h> header file. */ -#define HAVE_SYS_STAT_H 1 - -/* Define to 1 if you have the <sys/types.h> header file. */ -#define HAVE_SYS_TYPES_H 1 - -/* Define to 1 if you have the <type_traits.h> header file. */ -/* #undef HAVE_TYPE_TRAITS_H */ - -/* Define to 1 if you have the <unistd.h> header file. */ -#define HAVE_UNISTD_H 1 - -/* Define to 1 if the system has the type `unsigned long long'. */ -#define HAVE_UNSIGNED_LONG_LONG 1 - -/* Define to 1 if the compiler supports simple visibility declarations. */ -#define HAVE_VISIBILITY 1 - -/* Define to 1 if you have the <windows.h> header file. */ -/* #undef HAVE_WINDOWS_H */ - -/* Define to 1 if you have the <zlib.h> header file. */ -#define HAVE_ZLIB_H 1 - -/* Define to 1 if you have `_strtoi64'. */ -/* #undef HAVE__STRTOI64 */ - -/* The value of LINK_SIZE determines the number of bytes used to store links - as offsets within the compiled regex. The default is 2, which allows for - compiled patterns up to 64K long. This covers the vast majority of cases. - However, PCRE can also be compiled to use 3 or 4 bytes instead. This allows - for longer patterns in extreme cases. */ -#define LINK_SIZE 2 - -/* Define to the sub-directory where libtool stores uninstalled libraries. */ -#define LT_OBJDIR ".libs/" - -/* The value of MATCH_LIMIT determines the default number of times the - internal match() function can be called during a single execution of - pcre_exec(). There is a runtime interface for setting a different limit. - The limit exists in order to catch runaway regular expressions that take - for ever to determine that they do not match. The default is set very large - so that it does not accidentally catch legitimate cases. */ -#define MATCH_LIMIT 200000 - -/* The above limit applies to all calls of match(), whether or not they - increase the recursion depth. In some environments it is desirable to limit - the depth of recursive calls of match() more strictly, in order to restrict - the maximum amount of stack (or heap, if NO_RECURSE is defined) that is - used. The value of MATCH_LIMIT_RECURSION applies only to recursive calls of - match(). To have any useful effect, it must be less than the value of - MATCH_LIMIT. The default is to use the same value as MATCH_LIMIT. There is - a runtime method for setting a different limit. */ -#define MATCH_LIMIT_RECURSION 4000 - -/* This limit is parameterized just in case anybody ever wants to change it. - Care must be taken if it is increased, because it guards against integer - overflow caused by enormously large patterns. */ -#define MAX_NAME_COUNT 10000 - -/* This limit is parameterized just in case anybody ever wants to change it. - Care must be taken if it is increased, because it guards against integer - overflow caused by enormously large patterns. */ -#define MAX_NAME_SIZE 32 - -/* The value of NEWLINE determines the default newline character sequence. - PCRE client programs can override this by selecting other values at run - time. In ASCII environments, the value can be 10 (LF), 13 (CR), or 3338 - (CRLF); in EBCDIC environments the value can be 21 or 37 (LF), 13 (CR), or - 3349 or 3365 (CRLF) because there are two alternative codepoints (0x15 and - 0x25) that are used as the NL line terminator that is equivalent to ASCII - LF. In both ASCII and EBCDIC environments the value can also be -1 (ANY), - or -2 (ANYCRLF). */ -#define NEWLINE 10 - -/* PCRE uses recursive function calls to handle backtracking while matching. - This can sometimes be a problem on systems that have stacks of limited - size. Define NO_RECURSE to any value to get a version that doesn't use - recursion in the match() function; instead it creates its own stack by - steam using pcre_recurse_malloc() to obtain memory from the heap. For more - detail, see the comments and other stuff just above the match() function. - */ -#define NO_RECURSE /**/ - -/* Name of package */ -#define PACKAGE "pcre" - -/* Define to the address where bug reports for this package should be sent. */ -#define PACKAGE_BUGREPORT "" - -/* Define to the full name of this package. */ -#define PACKAGE_NAME "PCRE" - -/* Define to the full name and version of this package. */ -#define PACKAGE_STRING "PCRE 8.38" - -/* Define to the one symbol short name of this package. */ -#define PACKAGE_TARNAME "pcre" - -/* Define to the home page for this package. */ -#define PACKAGE_URL "" - -/* Define to the version of this package. */ -#define PACKAGE_VERSION "8.38" - -/* The value of PARENS_NEST_LIMIT specifies the maximum depth of nested - parentheses (of any kind) in a pattern. This limits the amount of system - stack that is used while compiling a pattern. */ -#define PARENS_NEST_LIMIT 250 - -/* to make a symbol visible */ -#define PCRECPP_EXP_DECL extern __attribute__ ((visibility ("default"))) - -/* to make a symbol visible */ -#define PCRECPP_EXP_DEFN __attribute__ ((visibility ("default"))) - -/* The value of PCREGREP_BUFSIZE determines the size of buffer used by - pcregrep to hold parts of the file it is searching. This is also the - minimum value. The actual amount of memory used by pcregrep is three times - this number, because it allows for the buffering of "before" and "after" - lines. */ -#define PCREGREP_BUFSIZE 20480 - -/* to make a symbol visible */ -#define PCREPOSIX_EXP_DECL extern __attribute__ ((visibility ("default"))) - -/* to make a symbol visible */ -#define PCREPOSIX_EXP_DEFN extern __attribute__ ((visibility ("default"))) - -/* to make a symbol visible */ -#define PCRE_EXP_DATA_DEFN __attribute__ ((visibility ("default"))) - -/* to make a symbol visible */ -#define PCRE_EXP_DECL extern __attribute__ ((visibility ("default"))) - - -/* If you are compiling for a system other than a Unix-like system or - Win32, and it needs some magic to be inserted before the definition - of a function that is exported by the library, define this macro to - contain the relevant magic. If you do not define this macro, a suitable - __declspec value is used for Windows systems; in other environments - "extern" is used for a C compiler and "extern C" for a C++ compiler. - This macro apears at the start of every exported function that is part - of the external API. It does not appear on functions that are "external" - in the C sense, but which are internal to the library. */ -#define PCRE_EXP_DEFN __attribute__ ((visibility ("default"))) - -/* Define to any value if linking statically (TODO: make nice with Libtool) */ -#define PCRE_STATIC 1 - -/* When calling PCRE via the POSIX interface, additional working storage is - required for holding the pointers to capturing substrings because PCRE - requires three integers per substring, whereas the POSIX interface provides - only two. If the number of expected substrings is small, the wrapper - function uses space on the stack, because this is faster than using - malloc() for each call. The threshold above which the stack is no longer - used is defined by POSIX_MALLOC_THRESHOLD. */ -#define POSIX_MALLOC_THRESHOLD 10 - -/* Define to necessary symbol if this constant uses a non-standard name on - your system. */ -/* #undef PTHREAD_CREATE_JOINABLE */ - -/* Define to 1 if you have the ANSI C header files. */ -#define STDC_HEADERS 1 - -/* Define to any value to enable support for Just-In-Time compiling. */ -/* #undef SUPPORT_JIT */ - -/* Define to any value to allow pcregrep to be linked with libbz2, so that it - is able to handle .bz2 files. */ -/* #undef SUPPORT_LIBBZ2 */ - -/* Define to any value to allow pcretest to be linked with libedit. */ -/* #undef SUPPORT_LIBEDIT */ - -/* Define to any value to allow pcretest to be linked with libreadline. */ -/* #undef SUPPORT_LIBREADLINE */ - -/* Define to any value to allow pcregrep to be linked with libz, so that it is - able to handle .gz files. */ -/* #undef SUPPORT_LIBZ */ - -/* Define to any value to enable the 16 bit PCRE library. */ -/* #undef SUPPORT_PCRE16 */ - -/* Define to any value to enable the 32 bit PCRE library. */ -/* #undef SUPPORT_PCRE32 */ - -/* Define to any value to enable the 8 bit PCRE library. */ -#define SUPPORT_PCRE8 /**/ - -/* Define to any value to enable JIT support in pcregrep. */ -/* #undef SUPPORT_PCREGREP_JIT */ - -/* Define to any value to enable support for Unicode properties. */ -#define SUPPORT_UCP /**/ - -/* Define to any value to enable support for the UTF-8/16/32 Unicode encoding. - This will work even in an EBCDIC environment, but it is incompatible with - the EBCDIC macro. That is, PCRE can support *either* EBCDIC code *or* - ASCII/UTF-8/16/32, but not both at once. */ -#define SUPPORT_UTF /**/ - -/* Define to any value for valgrind support to find invalid memory reads. */ -/* #undef SUPPORT_VALGRIND */ - -/* Version number of package */ -#define VERSION "8.38" - -/* Define to empty if `const' does not conform to ANSI C. */ -/* #undef const */ - -/* Define to the type of a signed integer type of width exactly 64 bits if - such a type exists and the standard includes do not define it. */ -/* #undef int64_t */ - -/* Define to `unsigned int' if <sys/types.h> does not define. */ -/* #undef size_t */ diff --git a/src/third_party/pcre-8.38/build_windows/config.h b/src/third_party/pcre-8.38/build_windows/config.h deleted file mode 100644 index ae1d54bdabd..00000000000 --- a/src/third_party/pcre-8.38/build_windows/config.h +++ /dev/null @@ -1,57 +0,0 @@ -/* config.h for CMake builds */ - -/* #undef HAVE_DIRENT_H */ -#define HAVE_SYS_STAT_H 1 -#define HAVE_SYS_TYPES_H 1 -/* #undef HAVE_UNISTD_H */ -#define HAVE_WINDOWS_H 1 -#define HAVE_STDINT_H 1 -#define HAVE_INTTYPES_H 1 - -/* #undef HAVE_TYPE_TRAITS_H */ -/* #undef HAVE_BITS_TYPE_TRAITS_H */ - -/* #undef HAVE_BCOPY */ -#define HAVE_MEMMOVE 1 -#define HAVE_STRERROR 1 -#define HAVE_STRTOLL 1 -/* #undef HAVE_STRTOQ */ -#define HAVE__STRTOI64 1 - -#define PCRE_STATIC 1 - -#define SUPPORT_PCRE8 1 -/* #undef SUPPORT_PCRE16 */ -/* #undef SUPPORT_PCRE32 */ -/* #undef SUPPORT_JIT */ -/* #undef SUPPORT_PCREGREP_JIT */ -#define SUPPORT_UTF 1 -#define SUPPORT_UCP 1 -/* #undef EBCDIC */ -/* #undef EBCDIC_NL25 */ -/* #undef BSR_ANYCRLF */ -#define NO_RECURSE 1 - -#define HAVE_LONG_LONG 1 -#define HAVE_UNSIGNED_LONG_LONG 1 - -/* #undef SUPPORT_LIBBZ2 */ -/* #undef SUPPORT_LIBZ */ -/* #undef SUPPORT_LIBEDIT */ -/* #undef SUPPORT_LIBREADLINE */ - -/* #undef SUPPORT_VALGRIND */ -/* #undef SUPPORT_GCOV */ - -#define NEWLINE 10 -#define POSIX_MALLOC_THRESHOLD 10 -#define LINK_SIZE 2 -#define PARENS_NEST_LIMIT 250 -#define MATCH_LIMIT 200000 -#define MATCH_LIMIT_RECURSION 4000 -#define PCREGREP_BUFSIZE 20480 - -#define MAX_NAME_SIZE 32 -#define MAX_NAME_COUNT 10000 - -/* end config.h for CMake builds */ diff --git a/src/third_party/pcre-8.38/dftables.c b/src/third_party/pcre-8.38/dftables.c deleted file mode 100644 index 1fdc8e0f231..00000000000 --- a/src/third_party/pcre-8.38/dftables.c +++ /dev/null @@ -1,212 +0,0 @@ -/************************************************* -* Perl-Compatible Regular Expressions * -*************************************************/ - -/* PCRE is a library of functions to support regular expressions whose syntax -and semantics are as close as possible to those of the Perl 5 language. - - Written by Philip Hazel - Copyright (c) 1997-2012 University of Cambridge - ------------------------------------------------------------------------------ -Redistribution and use in source and binary forms, with or without -modification, are permitted provided that the following conditions are met: - - * Redistributions of source code must retain the above copyright notice, - this list of conditions and the following disclaimer. - - * Redistributions in binary form must reproduce the above copyright - notice, this list of conditions and the following disclaimer in the - documentation and/or other materials provided with the distribution. - - * Neither the name of the University of Cambridge nor the names of its - contributors may be used to endorse or promote products derived from - this software without specific prior written permission. - -THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS" -AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE -IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE -ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR CONTRIBUTORS BE -LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR -CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF -SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS -INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN -CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) -ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE -POSSIBILITY OF SUCH DAMAGE. ------------------------------------------------------------------------------ -*/ - - -/* This is a freestanding support program to generate a file containing -character tables for PCRE. The tables are built according to the current -locale. Now that pcre_maketables is a function visible to the outside world, we -make use of its code from here in order to be consistent. */ - -#ifdef HAVE_CONFIG_H -#include "config.h" -#endif - -#include <ctype.h> -#include <stdio.h> -#include <string.h> -#include <locale.h> - -#include "pcre_internal.h" - -#define DFTABLES /* pcre_maketables.c notices this */ -#include "pcre_maketables.c" - - -int main(int argc, char **argv) -{ -FILE *f; -int i = 1; -const unsigned char *tables; -const unsigned char *base_of_tables; - -/* By default, the default C locale is used rather than what the building user -happens to have set. However, if the -L option is given, set the locale from -the LC_xxx environment variables. */ - -if (argc > 1 && strcmp(argv[1], "-L") == 0) - { - setlocale(LC_ALL, ""); /* Set from environment variables */ - i++; - } - -if (argc < i + 1) - { - fprintf(stderr, "dftables: one filename argument is required\n"); - return 1; - } - -tables = pcre_maketables(); -base_of_tables = tables; - -f = fopen(argv[i], "wb"); -if (f == NULL) - { - fprintf(stderr, "dftables: failed to open %s for writing\n", argv[1]); - return 1; - } - -/* There are several fprintf() calls here, because gcc in pedantic mode -complains about the very long string otherwise. */ - -fprintf(f, - "/*************************************************\n" - "* Perl-Compatible Regular Expressions *\n" - "*************************************************/\n\n" - "/* This file was automatically written by the dftables auxiliary\n" - "program. It contains character tables that are used when no external\n" - "tables are passed to PCRE by the application that calls it. The tables\n" - "are used only for characters whose code values are less than 256.\n\n"); -fprintf(f, - "The following #includes are present because without them gcc 4.x may remove\n" - "the array definition from the final binary if PCRE is built into a static\n" - "library and dead code stripping is activated. This leads to link errors.\n" - "Pulling in the header ensures that the array gets flagged as \"someone\n" - "outside this compilation unit might reference this\" and so it will always\n" - "be supplied to the linker. */\n\n"); - -/* Force config.h in z/OS */ - -#if defined NATIVE_ZOS -fprintf(f, - "/* For z/OS, config.h is forced */\n" - "#ifndef HAVE_CONFIG_H\n" - "#define HAVE_CONFIG_H 1\n" - "#endif\n\n"); -#endif - -fprintf(f, - "#ifdef HAVE_CONFIG_H\n" - "#include \"config.h\"\n" - "#endif\n\n" - "#include \"pcre_internal.h\"\n\n"); - -fprintf(f, - "const pcre_uint8 PRIV(default_tables)[] = {\n\n" - "/* This table is a lower casing table. */\n\n"); - -fprintf(f, " "); -for (i = 0; i < 256; i++) - { - if ((i & 7) == 0 && i != 0) fprintf(f, "\n "); - fprintf(f, "%3d", *tables++); - if (i != 255) fprintf(f, ","); - } -fprintf(f, ",\n\n"); - -fprintf(f, "/* This table is a case flipping table. */\n\n"); - -fprintf(f, " "); -for (i = 0; i < 256; i++) - { - if ((i & 7) == 0 && i != 0) fprintf(f, "\n "); - fprintf(f, "%3d", *tables++); - if (i != 255) fprintf(f, ","); - } -fprintf(f, ",\n\n"); - -fprintf(f, - "/* This table contains bit maps for various character classes.\n" - "Each map is 32 bytes long and the bits run from the least\n" - "significant end of each byte. The classes that have their own\n" - "maps are: space, xdigit, digit, upper, lower, word, graph\n" - "print, punct, and cntrl. Other classes are built from combinations. */\n\n"); - -fprintf(f, " "); -for (i = 0; i < cbit_length; i++) - { - if ((i & 7) == 0 && i != 0) - { - if ((i & 31) == 0) fprintf(f, "\n"); - fprintf(f, "\n "); - } - fprintf(f, "0x%02x", *tables++); - if (i != cbit_length - 1) fprintf(f, ","); - } -fprintf(f, ",\n\n"); - -fprintf(f, - "/* This table identifies various classes of character by individual bits:\n" - " 0x%02x white space character\n" - " 0x%02x letter\n" - " 0x%02x decimal digit\n" - " 0x%02x hexadecimal digit\n" - " 0x%02x alphanumeric or '_'\n" - " 0x%02x regular expression metacharacter or binary zero\n*/\n\n", - ctype_space, ctype_letter, ctype_digit, ctype_xdigit, ctype_word, - ctype_meta); - -fprintf(f, " "); -for (i = 0; i < 256; i++) - { - if ((i & 7) == 0 && i != 0) - { - fprintf(f, " /* "); - if (isprint(i-8)) fprintf(f, " %c -", i-8); - else fprintf(f, "%3d-", i-8); - if (isprint(i-1)) fprintf(f, " %c ", i-1); - else fprintf(f, "%3d", i-1); - fprintf(f, " */\n "); - } - fprintf(f, "0x%02x", *tables++); - if (i != 255) fprintf(f, ","); - } - -fprintf(f, "};/* "); -if (isprint(i-8)) fprintf(f, " %c -", i-8); - else fprintf(f, "%3d-", i-8); -if (isprint(i-1)) fprintf(f, " %c ", i-1); - else fprintf(f, "%3d", i-1); -fprintf(f, " */\n\n/* End of pcre_chartables.c */\n"); - -fclose(f); -free((void *)base_of_tables); -return 0; -} - -/* End of dftables.c */ diff --git a/src/third_party/pcre-8.38/libpcre.pc.in b/src/third_party/pcre-8.38/libpcre.pc.in deleted file mode 100644 index 0a35da87f85..00000000000 --- a/src/third_party/pcre-8.38/libpcre.pc.in +++ /dev/null @@ -1,13 +0,0 @@ -# Package Information for pkg-config - -prefix=@prefix@ -exec_prefix=@exec_prefix@ -libdir=@libdir@ -includedir=@includedir@ - -Name: libpcre -Description: PCRE - Perl compatible regular expressions C library with 8 bit character support -Version: @PACKAGE_VERSION@ -Libs: -L${libdir} -lpcre -Libs.private: @PTHREAD_CFLAGS@ @PTHREAD_LIBS@ -Cflags: -I${includedir} @PCRE_STATIC_CFLAG@ diff --git a/src/third_party/pcre-8.38/libpcre16.pc.in b/src/third_party/pcre-8.38/libpcre16.pc.in deleted file mode 100644 index 080c9dcfe8a..00000000000 --- a/src/third_party/pcre-8.38/libpcre16.pc.in +++ /dev/null @@ -1,13 +0,0 @@ -# Package Information for pkg-config - -prefix=@prefix@ -exec_prefix=@exec_prefix@ -libdir=@libdir@ -includedir=@includedir@ - -Name: libpcre16 -Description: PCRE - Perl compatible regular expressions C library with 16 bit character support -Version: @PACKAGE_VERSION@ -Libs: -L${libdir} -lpcre16 -Libs.private: @PTHREAD_CFLAGS@ @PTHREAD_LIBS@ -Cflags: -I${includedir} @PCRE_STATIC_CFLAG@ diff --git a/src/third_party/pcre-8.38/libpcre32.pc.in b/src/third_party/pcre-8.38/libpcre32.pc.in deleted file mode 100644 index a3ae0e11fcf..00000000000 --- a/src/third_party/pcre-8.38/libpcre32.pc.in +++ /dev/null @@ -1,13 +0,0 @@ -# Package Information for pkg-config - -prefix=@prefix@ -exec_prefix=@exec_prefix@ -libdir=@libdir@ -includedir=@includedir@ - -Name: libpcre32 -Description: PCRE - Perl compatible regular expressions C library with 32 bit character support -Version: @PACKAGE_VERSION@ -Libs: -L${libdir} -lpcre32 -Libs.private: @PTHREAD_CFLAGS@ @PTHREAD_LIBS@ -Cflags: -I${includedir} @PCRE_STATIC_CFLAG@ diff --git a/src/third_party/pcre-8.38/libpcrecpp.pc.in b/src/third_party/pcre-8.38/libpcrecpp.pc.in deleted file mode 100644 index ef006fe47aa..00000000000 --- a/src/third_party/pcre-8.38/libpcrecpp.pc.in +++ /dev/null @@ -1,12 +0,0 @@ -# Package Information for pkg-config - -prefix=@prefix@ -exec_prefix=@exec_prefix@ -libdir=@libdir@ -includedir=@includedir@ - -Name: libpcrecpp -Description: PCRECPP - C++ wrapper for PCRE -Version: @PACKAGE_VERSION@ -Libs: -L${libdir} -lpcre -lpcrecpp -Cflags: -I${includedir} @PCRE_STATIC_CFLAG@ diff --git a/src/third_party/pcre-8.38/libpcreposix.pc.in b/src/third_party/pcre-8.38/libpcreposix.pc.in deleted file mode 100644 index c6c0b0c6c66..00000000000 --- a/src/third_party/pcre-8.38/libpcreposix.pc.in +++ /dev/null @@ -1,13 +0,0 @@ -# Package Information for pkg-config - -prefix=@prefix@ -exec_prefix=@exec_prefix@ -libdir=@libdir@ -includedir=@includedir@ - -Name: libpcreposix -Description: PCREPosix - Posix compatible interface to libpcre -Version: @PACKAGE_VERSION@ -Libs: -L${libdir} -lpcreposix -Cflags: -I${includedir} @PCRE_STATIC_CFLAG@ -Requires.private: libpcre diff --git a/src/third_party/pcre-8.38/makevp.bat b/src/third_party/pcre-8.38/makevp.bat deleted file mode 100644 index 5f795487eb9..00000000000 --- a/src/third_party/pcre-8.38/makevp.bat +++ /dev/null @@ -1,66 +0,0 @@ -:: AH 20-12-06 modified for new PCRE-7.0 and VP/BCC -:: PH 19-03-07 renamed !compile.txt and !linklib.txt as makevp-compile.txt and -:: makevp-linklib.txt -:: PH 26-03-07 re-renamed !compile.txt and !linklib.txt as makevp-c.txt and -:: makevp-l.txt -:: PH 29-03-07 hopefully the final rename to makevp_c and makevp_l -:: AH 27.08.08 updated for new PCRE-7.7 -:: required PCRE.H and CONFIG.H will be generated if not existing - -@echo off -echo. -echo Compiling PCRE with BORLAND C++ for VIRTUAL PASCAL -echo. - -REM This file was contributed by Alexander Tokarev for building PCRE for use -REM with Virtual Pascal. It has not been tested with the latest PCRE release. - -REM This file has been modified and extended to compile with newer PCRE releases -REM by Stefan Weber (Angels Holocaust). - -REM CHANGE THIS FOR YOUR BORLAND C++ COMPILER PATH -SET BORLAND=f:\bcc -REM location of the TASM binaries, if compiling with the -B BCC switch -SET TASM=f:\tasm - -SET PATH=%PATH%;%BORLAND%\bin;%TASM%\bin -SET PCRE_VER=77 -SET COMPILE_DEFAULTS=-DHAVE_CONFIG_H -DPCRE_STATIC -I%BORLAND%\include - -del pcre%PCRE_VER%.lib >nul 2>nul - -:: sh configure - -:: check for needed header files -if not exist pcre.h copy pcre.h.generic pcre.h -if not exist config.h copy config.h.generic config.h - -bcc32 -DDFTABLES %COMPILE_DEFAULTS% -L%BORLAND%\lib dftables.c -IF ERRORLEVEL 1 GOTO ERROR - -:: dftables > chartables.c -dftables pcre_chartables.c - -REM compile and link the PCRE library into lib: option -B for ASM compile works too -bcc32 -a4 -c -RT- -y- -v- -u- -R- -Q- -X -d -fp -ff -P- -O2 -Oc -Ov -3 -w-8004 -w-8064 -w-8065 -w-8012 -UDFTABLES -DVPCOMPAT %COMPILE_DEFAULTS% @makevp_c.txt -IF ERRORLEVEL 1 GOTO ERROR - -tlib %BORLAND%\lib\cw32.lib *calloc *del *strncmp *memcpy *memmove *memset *memcmp *strlen -IF ERRORLEVEL 1 GOTO ERROR -tlib pcre%PCRE_VER%.lib @makevp_l.txt +calloc.obj +del.obj +strncmp.obj +memcpy.obj +memmove.obj +memset.obj +memcmp.obj +strlen.obj -IF ERRORLEVEL 1 GOTO ERROR - -del *.obj *.tds *.bak >nul 2>nul - -echo --- -echo Now the library should be complete. Please check all messages above. -echo Don't care for warnings, it's OK. -goto END - -:ERROR -echo --- -echo Error while compiling PCRE. Aborting... -pause -goto END - -:END diff --git a/src/third_party/pcre-8.38/makevp_c.txt b/src/third_party/pcre-8.38/makevp_c.txt deleted file mode 100644 index 5648115405d..00000000000 --- a/src/third_party/pcre-8.38/makevp_c.txt +++ /dev/null @@ -1,21 +0,0 @@ -pcre_byte_order.c
-pcre_chartables.c
-pcre_compile.c
-pcre_config.c
-pcre_dfa_exec.c
-pcre_exec.c
-pcre_fullinfo.c
-pcre_get.c
-pcre_globals.c
-pcre_jit_compile.c
-pcre_maketables.c
-pcre_newline.c
-pcre_ord2utf8.c
-pcre_refcount.c
-pcre_string_utils.c
-pcre_study.c
-pcre_tables.c
-pcre_ucd.c
-pcre_valid_utf8.c
-pcre_version.c
-pcre_xclass.c
diff --git a/src/third_party/pcre-8.38/makevp_l.txt b/src/third_party/pcre-8.38/makevp_l.txt deleted file mode 100644 index 9b071e0f90a..00000000000 --- a/src/third_party/pcre-8.38/makevp_l.txt +++ /dev/null @@ -1,21 +0,0 @@ -+pcre_byte_order.obj &
-+pcre_chartables.obj &
-+pcre_compile.obj &
-+pcre_config.obj &
-+pcre_dfa_exec.obj &
-+pcre_exec.obj &
-+pcre_fullinfo.obj &
-+pcre_get.obj &
-+pcre_globals.obj &
-+pcre_jit_compile.obj &
-+pcre_maketables.obj &
-+pcre_newline.obj &
-+pcre_ord2utf8.obj &
-+pcre_refcount.obj &
-+pcre_string_utils.obj &
-+pcre_study.obj &
-+pcre_tables.obj &
-+pcre_ucd.obj &
-+pcre_valid_utf8.obj &
-+pcre_version.obj &
-+pcre_xclass.obj
diff --git a/src/third_party/pcre-8.38/pcre-config.in b/src/third_party/pcre-8.38/pcre-config.in deleted file mode 100644 index ac06a3325bc..00000000000 --- a/src/third_party/pcre-8.38/pcre-config.in +++ /dev/null @@ -1,133 +0,0 @@ -#!/bin/sh - -prefix=@prefix@ -exec_prefix=@exec_prefix@ -exec_prefix_set=no - -cflags="[--cflags]" - -if test @enable_cpp@ = yes ; then - libs="[--libs-cpp]" -else - libs= -fi - -if test @enable_pcre16@ = yes ; then - libs="[--libs16] $libs" -fi - -if test @enable_pcre32@ = yes ; then - libs="[--libs32] $libs" -fi - -if test @enable_pcre8@ = yes ; then - libs="[--libs] [--libs-posix] $libs" - cflags="$cflags [--cflags-posix]" -fi - -usage="Usage: pcre-config [--prefix] [--exec-prefix] [--version] $libs $cflags" - -if test $# -eq 0; then - echo "${usage}" 1>&2 - exit 1 -fi - -libR= -case `uname -s` in - *SunOS*) - libR=" -R@libdir@" - ;; - *BSD*) - libR=" -Wl,-R@libdir@" - ;; -esac - -libS= -if test @libdir@ != /usr/lib ; then - libS=-L@libdir@ -fi - -while test $# -gt 0; do - case "$1" in - -*=*) optarg=`echo "$1" | sed 's/[-_a-zA-Z0-9]*=//'` ;; - *) optarg= ;; - esac - - case $1 in - --prefix=*) - prefix=$optarg - if test $exec_prefix_set = no ; then - exec_prefix=$optarg - fi - ;; - --prefix) - echo $prefix - ;; - --exec-prefix=*) - exec_prefix=$optarg - exec_prefix_set=yes - ;; - --exec-prefix) - echo $exec_prefix - ;; - --version) - echo @PACKAGE_VERSION@ - ;; - --cflags) - if test @includedir@ != /usr/include ; then - includes=-I@includedir@ - fi - echo $includes @PCRE_STATIC_CFLAG@ - ;; - --cflags-posix) - if test @enable_pcre8@ = yes ; then - if test @includedir@ != /usr/include ; then - includes=-I@includedir@ - fi - echo $includes @PCRE_STATIC_CFLAG@ - else - echo "${usage}" 1>&2 - fi - ;; - --libs-posix) - if test @enable_pcre8@ = yes ; then - echo $libS$libR -lpcreposix -lpcre - else - echo "${usage}" 1>&2 - fi - ;; - --libs) - if test @enable_pcre8@ = yes ; then - echo $libS$libR -lpcre - else - echo "${usage}" 1>&2 - fi - ;; - --libs16) - if test @enable_pcre16@ = yes ; then - echo $libS$libR -lpcre16 - else - echo "${usage}" 1>&2 - fi - ;; - --libs32) - if test @enable_pcre32@ = yes ; then - echo $libS$libR -lpcre32 - else - echo "${usage}" 1>&2 - fi - ;; - --libs-cpp) - if test @enable_cpp@ = yes ; then - echo $libS$libR -lpcrecpp -lpcre - else - echo "${usage}" 1>&2 - fi - ;; - *) - echo "${usage}" 1>&2 - exit 1 - ;; - esac - shift -done diff --git a/src/third_party/pcre-8.38/pcre.h b/src/third_party/pcre-8.38/pcre.h deleted file mode 100644 index bf6351f8837..00000000000 --- a/src/third_party/pcre-8.38/pcre.h +++ /dev/null @@ -1,677 +0,0 @@ -/************************************************* -* Perl-Compatible Regular Expressions * -*************************************************/ - -/* This is the public header file for the PCRE library, to be #included by -applications that call the PCRE functions. - - Copyright (c) 1997-2014 University of Cambridge - ------------------------------------------------------------------------------ -Redistribution and use in source and binary forms, with or without -modification, are permitted provided that the following conditions are met: - - * Redistributions of source code must retain the above copyright notice, - this list of conditions and the following disclaimer. - - * Redistributions in binary form must reproduce the above copyright - notice, this list of conditions and the following disclaimer in the - documentation and/or other materials provided with the distribution. - - * Neither the name of the University of Cambridge nor the names of its - contributors may be used to endorse or promote products derived from - this software without specific prior written permission. - -THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS" -AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE -IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE -ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR CONTRIBUTORS BE -LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR -CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF -SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS -INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN -CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) -ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE -POSSIBILITY OF SUCH DAMAGE. ------------------------------------------------------------------------------ -*/ - -#ifndef _PCRE_H -#define _PCRE_H - -/* The current PCRE version information. */ - -#define PCRE_MAJOR 8 -#define PCRE_MINOR 38 -#define PCRE_PRERELEASE -#define PCRE_DATE 2015-11-23 - -/* When an application links to a PCRE DLL in Windows, the symbols that are -imported have to be identified as such. When building PCRE, the appropriate -export setting is defined in pcre_internal.h, which includes this file. So we -don't change existing definitions of PCRE_EXP_DECL and PCRECPP_EXP_DECL. */ - -#if defined(_WIN32) && !defined(PCRE_STATIC) -# ifndef PCRE_EXP_DECL -# define PCRE_EXP_DECL extern __declspec(dllimport) -# endif -# ifdef __cplusplus -# ifndef PCRECPP_EXP_DECL -# define PCRECPP_EXP_DECL extern __declspec(dllimport) -# endif -# ifndef PCRECPP_EXP_DEFN -# define PCRECPP_EXP_DEFN __declspec(dllimport) -# endif -# endif -#endif - -/* By default, we use the standard "extern" declarations. */ - -#ifndef PCRE_EXP_DECL -# ifdef __cplusplus -# define PCRE_EXP_DECL extern "C" -# else -# define PCRE_EXP_DECL extern -# endif -#endif - -#ifdef __cplusplus -# ifndef PCRECPP_EXP_DECL -# define PCRECPP_EXP_DECL extern -# endif -# ifndef PCRECPP_EXP_DEFN -# define PCRECPP_EXP_DEFN -# endif -#endif - -/* Have to include stdlib.h in order to ensure that size_t is defined; -it is needed here for malloc. */ - -#include <stdlib.h> - -/* Allow for C++ users */ - -#ifdef __cplusplus -extern "C" { -#endif - -/* Public options. Some are compile-time only, some are run-time only, and some -are both. Most of the compile-time options are saved with the compiled regex so -that they can be inspected during studying (and therefore JIT compiling). Note -that pcre_study() has its own set of options. Originally, all the options -defined here used distinct bits. However, almost all the bits in a 32-bit word -are now used, so in order to conserve them, option bits that were previously -only recognized at matching time (i.e. by pcre_exec() or pcre_dfa_exec()) may -also be used for compile-time options that affect only compiling and are not -relevant for studying or JIT compiling. - -Some options for pcre_compile() change its behaviour but do not affect the -behaviour of the execution functions. Other options are passed through to the -execution functions and affect their behaviour, with or without affecting the -behaviour of pcre_compile(). - -Options that can be passed to pcre_compile() are tagged Cx below, with these -variants: - -C1 Affects compile only -C2 Does not affect compile; affects exec, dfa_exec -C3 Affects compile, exec, dfa_exec -C4 Affects compile, exec, dfa_exec, study -C5 Affects compile, exec, study - -Options that can be set for pcre_exec() and/or pcre_dfa_exec() are flagged with -E and D, respectively. They take precedence over C3, C4, and C5 settings passed -from pcre_compile(). Those that are compatible with JIT execution are flagged -with J. */ - -#define PCRE_CASELESS 0x00000001 /* C1 */ -#define PCRE_MULTILINE 0x00000002 /* C1 */ -#define PCRE_DOTALL 0x00000004 /* C1 */ -#define PCRE_EXTENDED 0x00000008 /* C1 */ -#define PCRE_ANCHORED 0x00000010 /* C4 E D */ -#define PCRE_DOLLAR_ENDONLY 0x00000020 /* C2 */ -#define PCRE_EXTRA 0x00000040 /* C1 */ -#define PCRE_NOTBOL 0x00000080 /* E D J */ -#define PCRE_NOTEOL 0x00000100 /* E D J */ -#define PCRE_UNGREEDY 0x00000200 /* C1 */ -#define PCRE_NOTEMPTY 0x00000400 /* E D J */ -#define PCRE_UTF8 0x00000800 /* C4 ) */ -#define PCRE_UTF16 0x00000800 /* C4 ) Synonyms */ -#define PCRE_UTF32 0x00000800 /* C4 ) */ -#define PCRE_NO_AUTO_CAPTURE 0x00001000 /* C1 */ -#define PCRE_NO_UTF8_CHECK 0x00002000 /* C1 E D J ) */ -#define PCRE_NO_UTF16_CHECK 0x00002000 /* C1 E D J ) Synonyms */ -#define PCRE_NO_UTF32_CHECK 0x00002000 /* C1 E D J ) */ -#define PCRE_AUTO_CALLOUT 0x00004000 /* C1 */ -#define PCRE_PARTIAL_SOFT 0x00008000 /* E D J ) Synonyms */ -#define PCRE_PARTIAL 0x00008000 /* E D J ) */ - -/* This pair use the same bit. */ -#define PCRE_NEVER_UTF 0x00010000 /* C1 ) Overlaid */ -#define PCRE_DFA_SHORTEST 0x00010000 /* D ) Overlaid */ - -/* This pair use the same bit. */ -#define PCRE_NO_AUTO_POSSESS 0x00020000 /* C1 ) Overlaid */ -#define PCRE_DFA_RESTART 0x00020000 /* D ) Overlaid */ - -#define PCRE_FIRSTLINE 0x00040000 /* C3 */ -#define PCRE_DUPNAMES 0x00080000 /* C1 */ -#define PCRE_NEWLINE_CR 0x00100000 /* C3 E D */ -#define PCRE_NEWLINE_LF 0x00200000 /* C3 E D */ -#define PCRE_NEWLINE_CRLF 0x00300000 /* C3 E D */ -#define PCRE_NEWLINE_ANY 0x00400000 /* C3 E D */ -#define PCRE_NEWLINE_ANYCRLF 0x00500000 /* C3 E D */ -#define PCRE_BSR_ANYCRLF 0x00800000 /* C3 E D */ -#define PCRE_BSR_UNICODE 0x01000000 /* C3 E D */ -#define PCRE_JAVASCRIPT_COMPAT 0x02000000 /* C5 */ -#define PCRE_NO_START_OPTIMIZE 0x04000000 /* C2 E D ) Synonyms */ -#define PCRE_NO_START_OPTIMISE 0x04000000 /* C2 E D ) */ -#define PCRE_PARTIAL_HARD 0x08000000 /* E D J */ -#define PCRE_NOTEMPTY_ATSTART 0x10000000 /* E D J */ -#define PCRE_UCP 0x20000000 /* C3 */ - -/* Exec-time and get/set-time error codes */ - -#define PCRE_ERROR_NOMATCH (-1) -#define PCRE_ERROR_NULL (-2) -#define PCRE_ERROR_BADOPTION (-3) -#define PCRE_ERROR_BADMAGIC (-4) -#define PCRE_ERROR_UNKNOWN_OPCODE (-5) -#define PCRE_ERROR_UNKNOWN_NODE (-5) /* For backward compatibility */ -#define PCRE_ERROR_NOMEMORY (-6) -#define PCRE_ERROR_NOSUBSTRING (-7) -#define PCRE_ERROR_MATCHLIMIT (-8) -#define PCRE_ERROR_CALLOUT (-9) /* Never used by PCRE itself */ -#define PCRE_ERROR_BADUTF8 (-10) /* Same for 8/16/32 */ -#define PCRE_ERROR_BADUTF16 (-10) /* Same for 8/16/32 */ -#define PCRE_ERROR_BADUTF32 (-10) /* Same for 8/16/32 */ -#define PCRE_ERROR_BADUTF8_OFFSET (-11) /* Same for 8/16 */ -#define PCRE_ERROR_BADUTF16_OFFSET (-11) /* Same for 8/16 */ -#define PCRE_ERROR_PARTIAL (-12) -#define PCRE_ERROR_BADPARTIAL (-13) -#define PCRE_ERROR_INTERNAL (-14) -#define PCRE_ERROR_BADCOUNT (-15) -#define PCRE_ERROR_DFA_UITEM (-16) -#define PCRE_ERROR_DFA_UCOND (-17) -#define PCRE_ERROR_DFA_UMLIMIT (-18) -#define PCRE_ERROR_DFA_WSSIZE (-19) -#define PCRE_ERROR_DFA_RECURSE (-20) -#define PCRE_ERROR_RECURSIONLIMIT (-21) -#define PCRE_ERROR_NULLWSLIMIT (-22) /* No longer actually used */ -#define PCRE_ERROR_BADNEWLINE (-23) -#define PCRE_ERROR_BADOFFSET (-24) -#define PCRE_ERROR_SHORTUTF8 (-25) -#define PCRE_ERROR_SHORTUTF16 (-25) /* Same for 8/16 */ -#define PCRE_ERROR_RECURSELOOP (-26) -#define PCRE_ERROR_JIT_STACKLIMIT (-27) -#define PCRE_ERROR_BADMODE (-28) -#define PCRE_ERROR_BADENDIANNESS (-29) -#define PCRE_ERROR_DFA_BADRESTART (-30) -#define PCRE_ERROR_JIT_BADOPTION (-31) -#define PCRE_ERROR_BADLENGTH (-32) -#define PCRE_ERROR_UNSET (-33) - -/* Specific error codes for UTF-8 validity checks */ - -#define PCRE_UTF8_ERR0 0 -#define PCRE_UTF8_ERR1 1 -#define PCRE_UTF8_ERR2 2 -#define PCRE_UTF8_ERR3 3 -#define PCRE_UTF8_ERR4 4 -#define PCRE_UTF8_ERR5 5 -#define PCRE_UTF8_ERR6 6 -#define PCRE_UTF8_ERR7 7 -#define PCRE_UTF8_ERR8 8 -#define PCRE_UTF8_ERR9 9 -#define PCRE_UTF8_ERR10 10 -#define PCRE_UTF8_ERR11 11 -#define PCRE_UTF8_ERR12 12 -#define PCRE_UTF8_ERR13 13 -#define PCRE_UTF8_ERR14 14 -#define PCRE_UTF8_ERR15 15 -#define PCRE_UTF8_ERR16 16 -#define PCRE_UTF8_ERR17 17 -#define PCRE_UTF8_ERR18 18 -#define PCRE_UTF8_ERR19 19 -#define PCRE_UTF8_ERR20 20 -#define PCRE_UTF8_ERR21 21 -#define PCRE_UTF8_ERR22 22 /* Unused (was non-character) */ - -/* Specific error codes for UTF-16 validity checks */ - -#define PCRE_UTF16_ERR0 0 -#define PCRE_UTF16_ERR1 1 -#define PCRE_UTF16_ERR2 2 -#define PCRE_UTF16_ERR3 3 -#define PCRE_UTF16_ERR4 4 /* Unused (was non-character) */ - -/* Specific error codes for UTF-32 validity checks */ - -#define PCRE_UTF32_ERR0 0 -#define PCRE_UTF32_ERR1 1 -#define PCRE_UTF32_ERR2 2 /* Unused (was non-character) */ -#define PCRE_UTF32_ERR3 3 - -/* Request types for pcre_fullinfo() */ - -#define PCRE_INFO_OPTIONS 0 -#define PCRE_INFO_SIZE 1 -#define PCRE_INFO_CAPTURECOUNT 2 -#define PCRE_INFO_BACKREFMAX 3 -#define PCRE_INFO_FIRSTBYTE 4 -#define PCRE_INFO_FIRSTCHAR 4 /* For backwards compatibility */ -#define PCRE_INFO_FIRSTTABLE 5 -#define PCRE_INFO_LASTLITERAL 6 -#define PCRE_INFO_NAMEENTRYSIZE 7 -#define PCRE_INFO_NAMECOUNT 8 -#define PCRE_INFO_NAMETABLE 9 -#define PCRE_INFO_STUDYSIZE 10 -#define PCRE_INFO_DEFAULT_TABLES 11 -#define PCRE_INFO_OKPARTIAL 12 -#define PCRE_INFO_JCHANGED 13 -#define PCRE_INFO_HASCRORLF 14 -#define PCRE_INFO_MINLENGTH 15 -#define PCRE_INFO_JIT 16 -#define PCRE_INFO_JITSIZE 17 -#define PCRE_INFO_MAXLOOKBEHIND 18 -#define PCRE_INFO_FIRSTCHARACTER 19 -#define PCRE_INFO_FIRSTCHARACTERFLAGS 20 -#define PCRE_INFO_REQUIREDCHAR 21 -#define PCRE_INFO_REQUIREDCHARFLAGS 22 -#define PCRE_INFO_MATCHLIMIT 23 -#define PCRE_INFO_RECURSIONLIMIT 24 -#define PCRE_INFO_MATCH_EMPTY 25 - -/* Request types for pcre_config(). Do not re-arrange, in order to remain -compatible. */ - -#define PCRE_CONFIG_UTF8 0 -#define PCRE_CONFIG_NEWLINE 1 -#define PCRE_CONFIG_LINK_SIZE 2 -#define PCRE_CONFIG_POSIX_MALLOC_THRESHOLD 3 -#define PCRE_CONFIG_MATCH_LIMIT 4 -#define PCRE_CONFIG_STACKRECURSE 5 -#define PCRE_CONFIG_UNICODE_PROPERTIES 6 -#define PCRE_CONFIG_MATCH_LIMIT_RECURSION 7 -#define PCRE_CONFIG_BSR 8 -#define PCRE_CONFIG_JIT 9 -#define PCRE_CONFIG_UTF16 10 -#define PCRE_CONFIG_JITTARGET 11 -#define PCRE_CONFIG_UTF32 12 -#define PCRE_CONFIG_PARENS_LIMIT 13 - -/* Request types for pcre_study(). Do not re-arrange, in order to remain -compatible. */ - -#define PCRE_STUDY_JIT_COMPILE 0x0001 -#define PCRE_STUDY_JIT_PARTIAL_SOFT_COMPILE 0x0002 -#define PCRE_STUDY_JIT_PARTIAL_HARD_COMPILE 0x0004 -#define PCRE_STUDY_EXTRA_NEEDED 0x0008 - -/* Bit flags for the pcre[16|32]_extra structure. Do not re-arrange or redefine -these bits, just add new ones on the end, in order to remain compatible. */ - -#define PCRE_EXTRA_STUDY_DATA 0x0001 -#define PCRE_EXTRA_MATCH_LIMIT 0x0002 -#define PCRE_EXTRA_CALLOUT_DATA 0x0004 -#define PCRE_EXTRA_TABLES 0x0008 -#define PCRE_EXTRA_MATCH_LIMIT_RECURSION 0x0010 -#define PCRE_EXTRA_MARK 0x0020 -#define PCRE_EXTRA_EXECUTABLE_JIT 0x0040 - -/* Types */ - -struct real_pcre; /* declaration; the definition is private */ -typedef struct real_pcre pcre; - -struct real_pcre16; /* declaration; the definition is private */ -typedef struct real_pcre16 pcre16; - -struct real_pcre32; /* declaration; the definition is private */ -typedef struct real_pcre32 pcre32; - -struct real_pcre_jit_stack; /* declaration; the definition is private */ -typedef struct real_pcre_jit_stack pcre_jit_stack; - -struct real_pcre16_jit_stack; /* declaration; the definition is private */ -typedef struct real_pcre16_jit_stack pcre16_jit_stack; - -struct real_pcre32_jit_stack; /* declaration; the definition is private */ -typedef struct real_pcre32_jit_stack pcre32_jit_stack; - -/* If PCRE is compiled with 16 bit character support, PCRE_UCHAR16 must contain -a 16 bit wide signed data type. Otherwise it can be a dummy data type since -pcre16 functions are not implemented. There is a check for this in pcre_internal.h. */ -#ifndef PCRE_UCHAR16 -#define PCRE_UCHAR16 unsigned short -#endif - -#ifndef PCRE_SPTR16 -#define PCRE_SPTR16 const PCRE_UCHAR16 * -#endif - -/* If PCRE is compiled with 32 bit character support, PCRE_UCHAR32 must contain -a 32 bit wide signed data type. Otherwise it can be a dummy data type since -pcre32 functions are not implemented. There is a check for this in pcre_internal.h. */ -#ifndef PCRE_UCHAR32 -#define PCRE_UCHAR32 unsigned int -#endif - -#ifndef PCRE_SPTR32 -#define PCRE_SPTR32 const PCRE_UCHAR32 * -#endif - -/* When PCRE is compiled as a C++ library, the subject pointer type can be -replaced with a custom type. For conventional use, the public interface is a -const char *. */ - -#ifndef PCRE_SPTR -#define PCRE_SPTR const char * -#endif - -/* The structure for passing additional data to pcre_exec(). This is defined in -such as way as to be extensible. Always add new fields at the end, in order to -remain compatible. */ - -typedef struct pcre_extra { - unsigned long int flags; /* Bits for which fields are set */ - void *study_data; /* Opaque data from pcre_study() */ - unsigned long int match_limit; /* Maximum number of calls to match() */ - void *callout_data; /* Data passed back in callouts */ - const unsigned char *tables; /* Pointer to character tables */ - unsigned long int match_limit_recursion; /* Max recursive calls to match() */ - unsigned char **mark; /* For passing back a mark pointer */ - void *executable_jit; /* Contains a pointer to a compiled jit code */ -} pcre_extra; - -/* Same structure as above, but with 16 bit char pointers. */ - -typedef struct pcre16_extra { - unsigned long int flags; /* Bits for which fields are set */ - void *study_data; /* Opaque data from pcre_study() */ - unsigned long int match_limit; /* Maximum number of calls to match() */ - void *callout_data; /* Data passed back in callouts */ - const unsigned char *tables; /* Pointer to character tables */ - unsigned long int match_limit_recursion; /* Max recursive calls to match() */ - PCRE_UCHAR16 **mark; /* For passing back a mark pointer */ - void *executable_jit; /* Contains a pointer to a compiled jit code */ -} pcre16_extra; - -/* Same structure as above, but with 32 bit char pointers. */ - -typedef struct pcre32_extra { - unsigned long int flags; /* Bits for which fields are set */ - void *study_data; /* Opaque data from pcre_study() */ - unsigned long int match_limit; /* Maximum number of calls to match() */ - void *callout_data; /* Data passed back in callouts */ - const unsigned char *tables; /* Pointer to character tables */ - unsigned long int match_limit_recursion; /* Max recursive calls to match() */ - PCRE_UCHAR32 **mark; /* For passing back a mark pointer */ - void *executable_jit; /* Contains a pointer to a compiled jit code */ -} pcre32_extra; - -/* The structure for passing out data via the pcre_callout_function. We use a -structure so that new fields can be added on the end in future versions, -without changing the API of the function, thereby allowing old clients to work -without modification. */ - -typedef struct pcre_callout_block { - int version; /* Identifies version of block */ - /* ------------------------ Version 0 ------------------------------- */ - int callout_number; /* Number compiled into pattern */ - int *offset_vector; /* The offset vector */ - PCRE_SPTR subject; /* The subject being matched */ - int subject_length; /* The length of the subject */ - int start_match; /* Offset to start of this match attempt */ - int current_position; /* Where we currently are in the subject */ - int capture_top; /* Max current capture */ - int capture_last; /* Most recently closed capture */ - void *callout_data; /* Data passed in with the call */ - /* ------------------- Added for Version 1 -------------------------- */ - int pattern_position; /* Offset to next item in the pattern */ - int next_item_length; /* Length of next item in the pattern */ - /* ------------------- Added for Version 2 -------------------------- */ - const unsigned char *mark; /* Pointer to current mark or NULL */ - /* ------------------------------------------------------------------ */ -} pcre_callout_block; - -/* Same structure as above, but with 16 bit char pointers. */ - -typedef struct pcre16_callout_block { - int version; /* Identifies version of block */ - /* ------------------------ Version 0 ------------------------------- */ - int callout_number; /* Number compiled into pattern */ - int *offset_vector; /* The offset vector */ - PCRE_SPTR16 subject; /* The subject being matched */ - int subject_length; /* The length of the subject */ - int start_match; /* Offset to start of this match attempt */ - int current_position; /* Where we currently are in the subject */ - int capture_top; /* Max current capture */ - int capture_last; /* Most recently closed capture */ - void *callout_data; /* Data passed in with the call */ - /* ------------------- Added for Version 1 -------------------------- */ - int pattern_position; /* Offset to next item in the pattern */ - int next_item_length; /* Length of next item in the pattern */ - /* ------------------- Added for Version 2 -------------------------- */ - const PCRE_UCHAR16 *mark; /* Pointer to current mark or NULL */ - /* ------------------------------------------------------------------ */ -} pcre16_callout_block; - -/* Same structure as above, but with 32 bit char pointers. */ - -typedef struct pcre32_callout_block { - int version; /* Identifies version of block */ - /* ------------------------ Version 0 ------------------------------- */ - int callout_number; /* Number compiled into pattern */ - int *offset_vector; /* The offset vector */ - PCRE_SPTR32 subject; /* The subject being matched */ - int subject_length; /* The length of the subject */ - int start_match; /* Offset to start of this match attempt */ - int current_position; /* Where we currently are in the subject */ - int capture_top; /* Max current capture */ - int capture_last; /* Most recently closed capture */ - void *callout_data; /* Data passed in with the call */ - /* ------------------- Added for Version 1 -------------------------- */ - int pattern_position; /* Offset to next item in the pattern */ - int next_item_length; /* Length of next item in the pattern */ - /* ------------------- Added for Version 2 -------------------------- */ - const PCRE_UCHAR32 *mark; /* Pointer to current mark or NULL */ - /* ------------------------------------------------------------------ */ -} pcre32_callout_block; - -/* Indirection for store get and free functions. These can be set to -alternative malloc/free functions if required. Special ones are used in the -non-recursive case for "frames". There is also an optional callout function -that is triggered by the (?) regex item. For Virtual Pascal, these definitions -have to take another form. */ - -#ifndef VPCOMPAT -PCRE_EXP_DECL void *(*pcre_malloc)(size_t); -PCRE_EXP_DECL void (*pcre_free)(void *); -PCRE_EXP_DECL void *(*pcre_stack_malloc)(size_t); -PCRE_EXP_DECL void (*pcre_stack_free)(void *); -PCRE_EXP_DECL int (*pcre_callout)(pcre_callout_block *); -PCRE_EXP_DECL int (*pcre_stack_guard)(void); - -PCRE_EXP_DECL void *(*pcre16_malloc)(size_t); -PCRE_EXP_DECL void (*pcre16_free)(void *); -PCRE_EXP_DECL void *(*pcre16_stack_malloc)(size_t); -PCRE_EXP_DECL void (*pcre16_stack_free)(void *); -PCRE_EXP_DECL int (*pcre16_callout)(pcre16_callout_block *); -PCRE_EXP_DECL int (*pcre16_stack_guard)(void); - -PCRE_EXP_DECL void *(*pcre32_malloc)(size_t); -PCRE_EXP_DECL void (*pcre32_free)(void *); -PCRE_EXP_DECL void *(*pcre32_stack_malloc)(size_t); -PCRE_EXP_DECL void (*pcre32_stack_free)(void *); -PCRE_EXP_DECL int (*pcre32_callout)(pcre32_callout_block *); -PCRE_EXP_DECL int (*pcre32_stack_guard)(void); -#else /* VPCOMPAT */ -PCRE_EXP_DECL void *pcre_malloc(size_t); -PCRE_EXP_DECL void pcre_free(void *); -PCRE_EXP_DECL void *pcre_stack_malloc(size_t); -PCRE_EXP_DECL void pcre_stack_free(void *); -PCRE_EXP_DECL int pcre_callout(pcre_callout_block *); -PCRE_EXP_DECL int pcre_stack_guard(void); - -PCRE_EXP_DECL void *pcre16_malloc(size_t); -PCRE_EXP_DECL void pcre16_free(void *); -PCRE_EXP_DECL void *pcre16_stack_malloc(size_t); -PCRE_EXP_DECL void pcre16_stack_free(void *); -PCRE_EXP_DECL int pcre16_callout(pcre16_callout_block *); -PCRE_EXP_DECL int pcre16_stack_guard(void); - -PCRE_EXP_DECL void *pcre32_malloc(size_t); -PCRE_EXP_DECL void pcre32_free(void *); -PCRE_EXP_DECL void *pcre32_stack_malloc(size_t); -PCRE_EXP_DECL void pcre32_stack_free(void *); -PCRE_EXP_DECL int pcre32_callout(pcre32_callout_block *); -PCRE_EXP_DECL int pcre32_stack_guard(void); -#endif /* VPCOMPAT */ - -/* User defined callback which provides a stack just before the match starts. */ - -typedef pcre_jit_stack *(*pcre_jit_callback)(void *); -typedef pcre16_jit_stack *(*pcre16_jit_callback)(void *); -typedef pcre32_jit_stack *(*pcre32_jit_callback)(void *); - -/* Exported PCRE functions */ - -PCRE_EXP_DECL pcre *pcre_compile(const char *, int, const char **, int *, - const unsigned char *); -PCRE_EXP_DECL pcre16 *pcre16_compile(PCRE_SPTR16, int, const char **, int *, - const unsigned char *); -PCRE_EXP_DECL pcre32 *pcre32_compile(PCRE_SPTR32, int, const char **, int *, - const unsigned char *); -PCRE_EXP_DECL pcre *pcre_compile2(const char *, int, int *, const char **, - int *, const unsigned char *); -PCRE_EXP_DECL pcre16 *pcre16_compile2(PCRE_SPTR16, int, int *, const char **, - int *, const unsigned char *); -PCRE_EXP_DECL pcre32 *pcre32_compile2(PCRE_SPTR32, int, int *, const char **, - int *, const unsigned char *); -PCRE_EXP_DECL int pcre_config(int, void *); -PCRE_EXP_DECL int pcre16_config(int, void *); -PCRE_EXP_DECL int pcre32_config(int, void *); -PCRE_EXP_DECL int pcre_copy_named_substring(const pcre *, const char *, - int *, int, const char *, char *, int); -PCRE_EXP_DECL int pcre16_copy_named_substring(const pcre16 *, PCRE_SPTR16, - int *, int, PCRE_SPTR16, PCRE_UCHAR16 *, int); -PCRE_EXP_DECL int pcre32_copy_named_substring(const pcre32 *, PCRE_SPTR32, - int *, int, PCRE_SPTR32, PCRE_UCHAR32 *, int); -PCRE_EXP_DECL int pcre_copy_substring(const char *, int *, int, int, - char *, int); -PCRE_EXP_DECL int pcre16_copy_substring(PCRE_SPTR16, int *, int, int, - PCRE_UCHAR16 *, int); -PCRE_EXP_DECL int pcre32_copy_substring(PCRE_SPTR32, int *, int, int, - PCRE_UCHAR32 *, int); -PCRE_EXP_DECL int pcre_dfa_exec(const pcre *, const pcre_extra *, - const char *, int, int, int, int *, int , int *, int); -PCRE_EXP_DECL int pcre16_dfa_exec(const pcre16 *, const pcre16_extra *, - PCRE_SPTR16, int, int, int, int *, int , int *, int); -PCRE_EXP_DECL int pcre32_dfa_exec(const pcre32 *, const pcre32_extra *, - PCRE_SPTR32, int, int, int, int *, int , int *, int); -PCRE_EXP_DECL int pcre_exec(const pcre *, const pcre_extra *, PCRE_SPTR, - int, int, int, int *, int); -PCRE_EXP_DECL int pcre16_exec(const pcre16 *, const pcre16_extra *, - PCRE_SPTR16, int, int, int, int *, int); -PCRE_EXP_DECL int pcre32_exec(const pcre32 *, const pcre32_extra *, - PCRE_SPTR32, int, int, int, int *, int); -PCRE_EXP_DECL int pcre_jit_exec(const pcre *, const pcre_extra *, - PCRE_SPTR, int, int, int, int *, int, - pcre_jit_stack *); -PCRE_EXP_DECL int pcre16_jit_exec(const pcre16 *, const pcre16_extra *, - PCRE_SPTR16, int, int, int, int *, int, - pcre16_jit_stack *); -PCRE_EXP_DECL int pcre32_jit_exec(const pcre32 *, const pcre32_extra *, - PCRE_SPTR32, int, int, int, int *, int, - pcre32_jit_stack *); -PCRE_EXP_DECL void pcre_free_substring(const char *); -PCRE_EXP_DECL void pcre16_free_substring(PCRE_SPTR16); -PCRE_EXP_DECL void pcre32_free_substring(PCRE_SPTR32); -PCRE_EXP_DECL void pcre_free_substring_list(const char **); -PCRE_EXP_DECL void pcre16_free_substring_list(PCRE_SPTR16 *); -PCRE_EXP_DECL void pcre32_free_substring_list(PCRE_SPTR32 *); -PCRE_EXP_DECL int pcre_fullinfo(const pcre *, const pcre_extra *, int, - void *); -PCRE_EXP_DECL int pcre16_fullinfo(const pcre16 *, const pcre16_extra *, int, - void *); -PCRE_EXP_DECL int pcre32_fullinfo(const pcre32 *, const pcre32_extra *, int, - void *); -PCRE_EXP_DECL int pcre_get_named_substring(const pcre *, const char *, - int *, int, const char *, const char **); -PCRE_EXP_DECL int pcre16_get_named_substring(const pcre16 *, PCRE_SPTR16, - int *, int, PCRE_SPTR16, PCRE_SPTR16 *); -PCRE_EXP_DECL int pcre32_get_named_substring(const pcre32 *, PCRE_SPTR32, - int *, int, PCRE_SPTR32, PCRE_SPTR32 *); -PCRE_EXP_DECL int pcre_get_stringnumber(const pcre *, const char *); -PCRE_EXP_DECL int pcre16_get_stringnumber(const pcre16 *, PCRE_SPTR16); -PCRE_EXP_DECL int pcre32_get_stringnumber(const pcre32 *, PCRE_SPTR32); -PCRE_EXP_DECL int pcre_get_stringtable_entries(const pcre *, const char *, - char **, char **); -PCRE_EXP_DECL int pcre16_get_stringtable_entries(const pcre16 *, PCRE_SPTR16, - PCRE_UCHAR16 **, PCRE_UCHAR16 **); -PCRE_EXP_DECL int pcre32_get_stringtable_entries(const pcre32 *, PCRE_SPTR32, - PCRE_UCHAR32 **, PCRE_UCHAR32 **); -PCRE_EXP_DECL int pcre_get_substring(const char *, int *, int, int, - const char **); -PCRE_EXP_DECL int pcre16_get_substring(PCRE_SPTR16, int *, int, int, - PCRE_SPTR16 *); -PCRE_EXP_DECL int pcre32_get_substring(PCRE_SPTR32, int *, int, int, - PCRE_SPTR32 *); -PCRE_EXP_DECL int pcre_get_substring_list(const char *, int *, int, - const char ***); -PCRE_EXP_DECL int pcre16_get_substring_list(PCRE_SPTR16, int *, int, - PCRE_SPTR16 **); -PCRE_EXP_DECL int pcre32_get_substring_list(PCRE_SPTR32, int *, int, - PCRE_SPTR32 **); -PCRE_EXP_DECL const unsigned char *pcre_maketables(void); -PCRE_EXP_DECL const unsigned char *pcre16_maketables(void); -PCRE_EXP_DECL const unsigned char *pcre32_maketables(void); -PCRE_EXP_DECL int pcre_refcount(pcre *, int); -PCRE_EXP_DECL int pcre16_refcount(pcre16 *, int); -PCRE_EXP_DECL int pcre32_refcount(pcre32 *, int); -PCRE_EXP_DECL pcre_extra *pcre_study(const pcre *, int, const char **); -PCRE_EXP_DECL pcre16_extra *pcre16_study(const pcre16 *, int, const char **); -PCRE_EXP_DECL pcre32_extra *pcre32_study(const pcre32 *, int, const char **); -PCRE_EXP_DECL void pcre_free_study(pcre_extra *); -PCRE_EXP_DECL void pcre16_free_study(pcre16_extra *); -PCRE_EXP_DECL void pcre32_free_study(pcre32_extra *); -PCRE_EXP_DECL const char *pcre_version(void); -PCRE_EXP_DECL const char *pcre16_version(void); -PCRE_EXP_DECL const char *pcre32_version(void); - -/* Utility functions for byte order swaps. */ -PCRE_EXP_DECL int pcre_pattern_to_host_byte_order(pcre *, pcre_extra *, - const unsigned char *); -PCRE_EXP_DECL int pcre16_pattern_to_host_byte_order(pcre16 *, pcre16_extra *, - const unsigned char *); -PCRE_EXP_DECL int pcre32_pattern_to_host_byte_order(pcre32 *, pcre32_extra *, - const unsigned char *); -PCRE_EXP_DECL int pcre16_utf16_to_host_byte_order(PCRE_UCHAR16 *, - PCRE_SPTR16, int, int *, int); -PCRE_EXP_DECL int pcre32_utf32_to_host_byte_order(PCRE_UCHAR32 *, - PCRE_SPTR32, int, int *, int); - -/* JIT compiler related functions. */ - -PCRE_EXP_DECL pcre_jit_stack *pcre_jit_stack_alloc(int, int); -PCRE_EXP_DECL pcre16_jit_stack *pcre16_jit_stack_alloc(int, int); -PCRE_EXP_DECL pcre32_jit_stack *pcre32_jit_stack_alloc(int, int); -PCRE_EXP_DECL void pcre_jit_stack_free(pcre_jit_stack *); -PCRE_EXP_DECL void pcre16_jit_stack_free(pcre16_jit_stack *); -PCRE_EXP_DECL void pcre32_jit_stack_free(pcre32_jit_stack *); -PCRE_EXP_DECL void pcre_assign_jit_stack(pcre_extra *, - pcre_jit_callback, void *); -PCRE_EXP_DECL void pcre16_assign_jit_stack(pcre16_extra *, - pcre16_jit_callback, void *); -PCRE_EXP_DECL void pcre32_assign_jit_stack(pcre32_extra *, - pcre32_jit_callback, void *); -PCRE_EXP_DECL void pcre_jit_free_unused_memory(void); -PCRE_EXP_DECL void pcre16_jit_free_unused_memory(void); -PCRE_EXP_DECL void pcre32_jit_free_unused_memory(void); - -#ifdef __cplusplus -} /* extern "C" */ -#endif - -#endif /* End of pcre.h */ diff --git a/src/third_party/pcre-8.38/pcre.h.generic b/src/third_party/pcre-8.38/pcre.h.generic deleted file mode 100644 index bf6351f8837..00000000000 --- a/src/third_party/pcre-8.38/pcre.h.generic +++ /dev/null @@ -1,677 +0,0 @@ -/************************************************* -* Perl-Compatible Regular Expressions * -*************************************************/ - -/* This is the public header file for the PCRE library, to be #included by -applications that call the PCRE functions. - - Copyright (c) 1997-2014 University of Cambridge - ------------------------------------------------------------------------------ -Redistribution and use in source and binary forms, with or without -modification, are permitted provided that the following conditions are met: - - * Redistributions of source code must retain the above copyright notice, - this list of conditions and the following disclaimer. - - * Redistributions in binary form must reproduce the above copyright - notice, this list of conditions and the following disclaimer in the - documentation and/or other materials provided with the distribution. - - * Neither the name of the University of Cambridge nor the names of its - contributors may be used to endorse or promote products derived from - this software without specific prior written permission. - -THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS" -AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE -IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE -ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR CONTRIBUTORS BE -LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR -CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF -SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS -INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN -CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) -ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE -POSSIBILITY OF SUCH DAMAGE. ------------------------------------------------------------------------------ -*/ - -#ifndef _PCRE_H -#define _PCRE_H - -/* The current PCRE version information. */ - -#define PCRE_MAJOR 8 -#define PCRE_MINOR 38 -#define PCRE_PRERELEASE -#define PCRE_DATE 2015-11-23 - -/* When an application links to a PCRE DLL in Windows, the symbols that are -imported have to be identified as such. When building PCRE, the appropriate -export setting is defined in pcre_internal.h, which includes this file. So we -don't change existing definitions of PCRE_EXP_DECL and PCRECPP_EXP_DECL. */ - -#if defined(_WIN32) && !defined(PCRE_STATIC) -# ifndef PCRE_EXP_DECL -# define PCRE_EXP_DECL extern __declspec(dllimport) -# endif -# ifdef __cplusplus -# ifndef PCRECPP_EXP_DECL -# define PCRECPP_EXP_DECL extern __declspec(dllimport) -# endif -# ifndef PCRECPP_EXP_DEFN -# define PCRECPP_EXP_DEFN __declspec(dllimport) -# endif -# endif -#endif - -/* By default, we use the standard "extern" declarations. */ - -#ifndef PCRE_EXP_DECL -# ifdef __cplusplus -# define PCRE_EXP_DECL extern "C" -# else -# define PCRE_EXP_DECL extern -# endif -#endif - -#ifdef __cplusplus -# ifndef PCRECPP_EXP_DECL -# define PCRECPP_EXP_DECL extern -# endif -# ifndef PCRECPP_EXP_DEFN -# define PCRECPP_EXP_DEFN -# endif -#endif - -/* Have to include stdlib.h in order to ensure that size_t is defined; -it is needed here for malloc. */ - -#include <stdlib.h> - -/* Allow for C++ users */ - -#ifdef __cplusplus -extern "C" { -#endif - -/* Public options. Some are compile-time only, some are run-time only, and some -are both. Most of the compile-time options are saved with the compiled regex so -that they can be inspected during studying (and therefore JIT compiling). Note -that pcre_study() has its own set of options. Originally, all the options -defined here used distinct bits. However, almost all the bits in a 32-bit word -are now used, so in order to conserve them, option bits that were previously -only recognized at matching time (i.e. by pcre_exec() or pcre_dfa_exec()) may -also be used for compile-time options that affect only compiling and are not -relevant for studying or JIT compiling. - -Some options for pcre_compile() change its behaviour but do not affect the -behaviour of the execution functions. Other options are passed through to the -execution functions and affect their behaviour, with or without affecting the -behaviour of pcre_compile(). - -Options that can be passed to pcre_compile() are tagged Cx below, with these -variants: - -C1 Affects compile only -C2 Does not affect compile; affects exec, dfa_exec -C3 Affects compile, exec, dfa_exec -C4 Affects compile, exec, dfa_exec, study -C5 Affects compile, exec, study - -Options that can be set for pcre_exec() and/or pcre_dfa_exec() are flagged with -E and D, respectively. They take precedence over C3, C4, and C5 settings passed -from pcre_compile(). Those that are compatible with JIT execution are flagged -with J. */ - -#define PCRE_CASELESS 0x00000001 /* C1 */ -#define PCRE_MULTILINE 0x00000002 /* C1 */ -#define PCRE_DOTALL 0x00000004 /* C1 */ -#define PCRE_EXTENDED 0x00000008 /* C1 */ -#define PCRE_ANCHORED 0x00000010 /* C4 E D */ -#define PCRE_DOLLAR_ENDONLY 0x00000020 /* C2 */ -#define PCRE_EXTRA 0x00000040 /* C1 */ -#define PCRE_NOTBOL 0x00000080 /* E D J */ -#define PCRE_NOTEOL 0x00000100 /* E D J */ -#define PCRE_UNGREEDY 0x00000200 /* C1 */ -#define PCRE_NOTEMPTY 0x00000400 /* E D J */ -#define PCRE_UTF8 0x00000800 /* C4 ) */ -#define PCRE_UTF16 0x00000800 /* C4 ) Synonyms */ -#define PCRE_UTF32 0x00000800 /* C4 ) */ -#define PCRE_NO_AUTO_CAPTURE 0x00001000 /* C1 */ -#define PCRE_NO_UTF8_CHECK 0x00002000 /* C1 E D J ) */ -#define PCRE_NO_UTF16_CHECK 0x00002000 /* C1 E D J ) Synonyms */ -#define PCRE_NO_UTF32_CHECK 0x00002000 /* C1 E D J ) */ -#define PCRE_AUTO_CALLOUT 0x00004000 /* C1 */ -#define PCRE_PARTIAL_SOFT 0x00008000 /* E D J ) Synonyms */ -#define PCRE_PARTIAL 0x00008000 /* E D J ) */ - -/* This pair use the same bit. */ -#define PCRE_NEVER_UTF 0x00010000 /* C1 ) Overlaid */ -#define PCRE_DFA_SHORTEST 0x00010000 /* D ) Overlaid */ - -/* This pair use the same bit. */ -#define PCRE_NO_AUTO_POSSESS 0x00020000 /* C1 ) Overlaid */ -#define PCRE_DFA_RESTART 0x00020000 /* D ) Overlaid */ - -#define PCRE_FIRSTLINE 0x00040000 /* C3 */ -#define PCRE_DUPNAMES 0x00080000 /* C1 */ -#define PCRE_NEWLINE_CR 0x00100000 /* C3 E D */ -#define PCRE_NEWLINE_LF 0x00200000 /* C3 E D */ -#define PCRE_NEWLINE_CRLF 0x00300000 /* C3 E D */ -#define PCRE_NEWLINE_ANY 0x00400000 /* C3 E D */ -#define PCRE_NEWLINE_ANYCRLF 0x00500000 /* C3 E D */ -#define PCRE_BSR_ANYCRLF 0x00800000 /* C3 E D */ -#define PCRE_BSR_UNICODE 0x01000000 /* C3 E D */ -#define PCRE_JAVASCRIPT_COMPAT 0x02000000 /* C5 */ -#define PCRE_NO_START_OPTIMIZE 0x04000000 /* C2 E D ) Synonyms */ -#define PCRE_NO_START_OPTIMISE 0x04000000 /* C2 E D ) */ -#define PCRE_PARTIAL_HARD 0x08000000 /* E D J */ -#define PCRE_NOTEMPTY_ATSTART 0x10000000 /* E D J */ -#define PCRE_UCP 0x20000000 /* C3 */ - -/* Exec-time and get/set-time error codes */ - -#define PCRE_ERROR_NOMATCH (-1) -#define PCRE_ERROR_NULL (-2) -#define PCRE_ERROR_BADOPTION (-3) -#define PCRE_ERROR_BADMAGIC (-4) -#define PCRE_ERROR_UNKNOWN_OPCODE (-5) -#define PCRE_ERROR_UNKNOWN_NODE (-5) /* For backward compatibility */ -#define PCRE_ERROR_NOMEMORY (-6) -#define PCRE_ERROR_NOSUBSTRING (-7) -#define PCRE_ERROR_MATCHLIMIT (-8) -#define PCRE_ERROR_CALLOUT (-9) /* Never used by PCRE itself */ -#define PCRE_ERROR_BADUTF8 (-10) /* Same for 8/16/32 */ -#define PCRE_ERROR_BADUTF16 (-10) /* Same for 8/16/32 */ -#define PCRE_ERROR_BADUTF32 (-10) /* Same for 8/16/32 */ -#define PCRE_ERROR_BADUTF8_OFFSET (-11) /* Same for 8/16 */ -#define PCRE_ERROR_BADUTF16_OFFSET (-11) /* Same for 8/16 */ -#define PCRE_ERROR_PARTIAL (-12) -#define PCRE_ERROR_BADPARTIAL (-13) -#define PCRE_ERROR_INTERNAL (-14) -#define PCRE_ERROR_BADCOUNT (-15) -#define PCRE_ERROR_DFA_UITEM (-16) -#define PCRE_ERROR_DFA_UCOND (-17) -#define PCRE_ERROR_DFA_UMLIMIT (-18) -#define PCRE_ERROR_DFA_WSSIZE (-19) -#define PCRE_ERROR_DFA_RECURSE (-20) -#define PCRE_ERROR_RECURSIONLIMIT (-21) -#define PCRE_ERROR_NULLWSLIMIT (-22) /* No longer actually used */ -#define PCRE_ERROR_BADNEWLINE (-23) -#define PCRE_ERROR_BADOFFSET (-24) -#define PCRE_ERROR_SHORTUTF8 (-25) -#define PCRE_ERROR_SHORTUTF16 (-25) /* Same for 8/16 */ -#define PCRE_ERROR_RECURSELOOP (-26) -#define PCRE_ERROR_JIT_STACKLIMIT (-27) -#define PCRE_ERROR_BADMODE (-28) -#define PCRE_ERROR_BADENDIANNESS (-29) -#define PCRE_ERROR_DFA_BADRESTART (-30) -#define PCRE_ERROR_JIT_BADOPTION (-31) -#define PCRE_ERROR_BADLENGTH (-32) -#define PCRE_ERROR_UNSET (-33) - -/* Specific error codes for UTF-8 validity checks */ - -#define PCRE_UTF8_ERR0 0 -#define PCRE_UTF8_ERR1 1 -#define PCRE_UTF8_ERR2 2 -#define PCRE_UTF8_ERR3 3 -#define PCRE_UTF8_ERR4 4 -#define PCRE_UTF8_ERR5 5 -#define PCRE_UTF8_ERR6 6 -#define PCRE_UTF8_ERR7 7 -#define PCRE_UTF8_ERR8 8 -#define PCRE_UTF8_ERR9 9 -#define PCRE_UTF8_ERR10 10 -#define PCRE_UTF8_ERR11 11 -#define PCRE_UTF8_ERR12 12 -#define PCRE_UTF8_ERR13 13 -#define PCRE_UTF8_ERR14 14 -#define PCRE_UTF8_ERR15 15 -#define PCRE_UTF8_ERR16 16 -#define PCRE_UTF8_ERR17 17 -#define PCRE_UTF8_ERR18 18 -#define PCRE_UTF8_ERR19 19 -#define PCRE_UTF8_ERR20 20 -#define PCRE_UTF8_ERR21 21 -#define PCRE_UTF8_ERR22 22 /* Unused (was non-character) */ - -/* Specific error codes for UTF-16 validity checks */ - -#define PCRE_UTF16_ERR0 0 -#define PCRE_UTF16_ERR1 1 -#define PCRE_UTF16_ERR2 2 -#define PCRE_UTF16_ERR3 3 -#define PCRE_UTF16_ERR4 4 /* Unused (was non-character) */ - -/* Specific error codes for UTF-32 validity checks */ - -#define PCRE_UTF32_ERR0 0 -#define PCRE_UTF32_ERR1 1 -#define PCRE_UTF32_ERR2 2 /* Unused (was non-character) */ -#define PCRE_UTF32_ERR3 3 - -/* Request types for pcre_fullinfo() */ - -#define PCRE_INFO_OPTIONS 0 -#define PCRE_INFO_SIZE 1 -#define PCRE_INFO_CAPTURECOUNT 2 -#define PCRE_INFO_BACKREFMAX 3 -#define PCRE_INFO_FIRSTBYTE 4 -#define PCRE_INFO_FIRSTCHAR 4 /* For backwards compatibility */ -#define PCRE_INFO_FIRSTTABLE 5 -#define PCRE_INFO_LASTLITERAL 6 -#define PCRE_INFO_NAMEENTRYSIZE 7 -#define PCRE_INFO_NAMECOUNT 8 -#define PCRE_INFO_NAMETABLE 9 -#define PCRE_INFO_STUDYSIZE 10 -#define PCRE_INFO_DEFAULT_TABLES 11 -#define PCRE_INFO_OKPARTIAL 12 -#define PCRE_INFO_JCHANGED 13 -#define PCRE_INFO_HASCRORLF 14 -#define PCRE_INFO_MINLENGTH 15 -#define PCRE_INFO_JIT 16 -#define PCRE_INFO_JITSIZE 17 -#define PCRE_INFO_MAXLOOKBEHIND 18 -#define PCRE_INFO_FIRSTCHARACTER 19 -#define PCRE_INFO_FIRSTCHARACTERFLAGS 20 -#define PCRE_INFO_REQUIREDCHAR 21 -#define PCRE_INFO_REQUIREDCHARFLAGS 22 -#define PCRE_INFO_MATCHLIMIT 23 -#define PCRE_INFO_RECURSIONLIMIT 24 -#define PCRE_INFO_MATCH_EMPTY 25 - -/* Request types for pcre_config(). Do not re-arrange, in order to remain -compatible. */ - -#define PCRE_CONFIG_UTF8 0 -#define PCRE_CONFIG_NEWLINE 1 -#define PCRE_CONFIG_LINK_SIZE 2 -#define PCRE_CONFIG_POSIX_MALLOC_THRESHOLD 3 -#define PCRE_CONFIG_MATCH_LIMIT 4 -#define PCRE_CONFIG_STACKRECURSE 5 -#define PCRE_CONFIG_UNICODE_PROPERTIES 6 -#define PCRE_CONFIG_MATCH_LIMIT_RECURSION 7 -#define PCRE_CONFIG_BSR 8 -#define PCRE_CONFIG_JIT 9 -#define PCRE_CONFIG_UTF16 10 -#define PCRE_CONFIG_JITTARGET 11 -#define PCRE_CONFIG_UTF32 12 -#define PCRE_CONFIG_PARENS_LIMIT 13 - -/* Request types for pcre_study(). Do not re-arrange, in order to remain -compatible. */ - -#define PCRE_STUDY_JIT_COMPILE 0x0001 -#define PCRE_STUDY_JIT_PARTIAL_SOFT_COMPILE 0x0002 -#define PCRE_STUDY_JIT_PARTIAL_HARD_COMPILE 0x0004 -#define PCRE_STUDY_EXTRA_NEEDED 0x0008 - -/* Bit flags for the pcre[16|32]_extra structure. Do not re-arrange or redefine -these bits, just add new ones on the end, in order to remain compatible. */ - -#define PCRE_EXTRA_STUDY_DATA 0x0001 -#define PCRE_EXTRA_MATCH_LIMIT 0x0002 -#define PCRE_EXTRA_CALLOUT_DATA 0x0004 -#define PCRE_EXTRA_TABLES 0x0008 -#define PCRE_EXTRA_MATCH_LIMIT_RECURSION 0x0010 -#define PCRE_EXTRA_MARK 0x0020 -#define PCRE_EXTRA_EXECUTABLE_JIT 0x0040 - -/* Types */ - -struct real_pcre; /* declaration; the definition is private */ -typedef struct real_pcre pcre; - -struct real_pcre16; /* declaration; the definition is private */ -typedef struct real_pcre16 pcre16; - -struct real_pcre32; /* declaration; the definition is private */ -typedef struct real_pcre32 pcre32; - -struct real_pcre_jit_stack; /* declaration; the definition is private */ -typedef struct real_pcre_jit_stack pcre_jit_stack; - -struct real_pcre16_jit_stack; /* declaration; the definition is private */ -typedef struct real_pcre16_jit_stack pcre16_jit_stack; - -struct real_pcre32_jit_stack; /* declaration; the definition is private */ -typedef struct real_pcre32_jit_stack pcre32_jit_stack; - -/* If PCRE is compiled with 16 bit character support, PCRE_UCHAR16 must contain -a 16 bit wide signed data type. Otherwise it can be a dummy data type since -pcre16 functions are not implemented. There is a check for this in pcre_internal.h. */ -#ifndef PCRE_UCHAR16 -#define PCRE_UCHAR16 unsigned short -#endif - -#ifndef PCRE_SPTR16 -#define PCRE_SPTR16 const PCRE_UCHAR16 * -#endif - -/* If PCRE is compiled with 32 bit character support, PCRE_UCHAR32 must contain -a 32 bit wide signed data type. Otherwise it can be a dummy data type since -pcre32 functions are not implemented. There is a check for this in pcre_internal.h. */ -#ifndef PCRE_UCHAR32 -#define PCRE_UCHAR32 unsigned int -#endif - -#ifndef PCRE_SPTR32 -#define PCRE_SPTR32 const PCRE_UCHAR32 * -#endif - -/* When PCRE is compiled as a C++ library, the subject pointer type can be -replaced with a custom type. For conventional use, the public interface is a -const char *. */ - -#ifndef PCRE_SPTR -#define PCRE_SPTR const char * -#endif - -/* The structure for passing additional data to pcre_exec(). This is defined in -such as way as to be extensible. Always add new fields at the end, in order to -remain compatible. */ - -typedef struct pcre_extra { - unsigned long int flags; /* Bits for which fields are set */ - void *study_data; /* Opaque data from pcre_study() */ - unsigned long int match_limit; /* Maximum number of calls to match() */ - void *callout_data; /* Data passed back in callouts */ - const unsigned char *tables; /* Pointer to character tables */ - unsigned long int match_limit_recursion; /* Max recursive calls to match() */ - unsigned char **mark; /* For passing back a mark pointer */ - void *executable_jit; /* Contains a pointer to a compiled jit code */ -} pcre_extra; - -/* Same structure as above, but with 16 bit char pointers. */ - -typedef struct pcre16_extra { - unsigned long int flags; /* Bits for which fields are set */ - void *study_data; /* Opaque data from pcre_study() */ - unsigned long int match_limit; /* Maximum number of calls to match() */ - void *callout_data; /* Data passed back in callouts */ - const unsigned char *tables; /* Pointer to character tables */ - unsigned long int match_limit_recursion; /* Max recursive calls to match() */ - PCRE_UCHAR16 **mark; /* For passing back a mark pointer */ - void *executable_jit; /* Contains a pointer to a compiled jit code */ -} pcre16_extra; - -/* Same structure as above, but with 32 bit char pointers. */ - -typedef struct pcre32_extra { - unsigned long int flags; /* Bits for which fields are set */ - void *study_data; /* Opaque data from pcre_study() */ - unsigned long int match_limit; /* Maximum number of calls to match() */ - void *callout_data; /* Data passed back in callouts */ - const unsigned char *tables; /* Pointer to character tables */ - unsigned long int match_limit_recursion; /* Max recursive calls to match() */ - PCRE_UCHAR32 **mark; /* For passing back a mark pointer */ - void *executable_jit; /* Contains a pointer to a compiled jit code */ -} pcre32_extra; - -/* The structure for passing out data via the pcre_callout_function. We use a -structure so that new fields can be added on the end in future versions, -without changing the API of the function, thereby allowing old clients to work -without modification. */ - -typedef struct pcre_callout_block { - int version; /* Identifies version of block */ - /* ------------------------ Version 0 ------------------------------- */ - int callout_number; /* Number compiled into pattern */ - int *offset_vector; /* The offset vector */ - PCRE_SPTR subject; /* The subject being matched */ - int subject_length; /* The length of the subject */ - int start_match; /* Offset to start of this match attempt */ - int current_position; /* Where we currently are in the subject */ - int capture_top; /* Max current capture */ - int capture_last; /* Most recently closed capture */ - void *callout_data; /* Data passed in with the call */ - /* ------------------- Added for Version 1 -------------------------- */ - int pattern_position; /* Offset to next item in the pattern */ - int next_item_length; /* Length of next item in the pattern */ - /* ------------------- Added for Version 2 -------------------------- */ - const unsigned char *mark; /* Pointer to current mark or NULL */ - /* ------------------------------------------------------------------ */ -} pcre_callout_block; - -/* Same structure as above, but with 16 bit char pointers. */ - -typedef struct pcre16_callout_block { - int version; /* Identifies version of block */ - /* ------------------------ Version 0 ------------------------------- */ - int callout_number; /* Number compiled into pattern */ - int *offset_vector; /* The offset vector */ - PCRE_SPTR16 subject; /* The subject being matched */ - int subject_length; /* The length of the subject */ - int start_match; /* Offset to start of this match attempt */ - int current_position; /* Where we currently are in the subject */ - int capture_top; /* Max current capture */ - int capture_last; /* Most recently closed capture */ - void *callout_data; /* Data passed in with the call */ - /* ------------------- Added for Version 1 -------------------------- */ - int pattern_position; /* Offset to next item in the pattern */ - int next_item_length; /* Length of next item in the pattern */ - /* ------------------- Added for Version 2 -------------------------- */ - const PCRE_UCHAR16 *mark; /* Pointer to current mark or NULL */ - /* ------------------------------------------------------------------ */ -} pcre16_callout_block; - -/* Same structure as above, but with 32 bit char pointers. */ - -typedef struct pcre32_callout_block { - int version; /* Identifies version of block */ - /* ------------------------ Version 0 ------------------------------- */ - int callout_number; /* Number compiled into pattern */ - int *offset_vector; /* The offset vector */ - PCRE_SPTR32 subject; /* The subject being matched */ - int subject_length; /* The length of the subject */ - int start_match; /* Offset to start of this match attempt */ - int current_position; /* Where we currently are in the subject */ - int capture_top; /* Max current capture */ - int capture_last; /* Most recently closed capture */ - void *callout_data; /* Data passed in with the call */ - /* ------------------- Added for Version 1 -------------------------- */ - int pattern_position; /* Offset to next item in the pattern */ - int next_item_length; /* Length of next item in the pattern */ - /* ------------------- Added for Version 2 -------------------------- */ - const PCRE_UCHAR32 *mark; /* Pointer to current mark or NULL */ - /* ------------------------------------------------------------------ */ -} pcre32_callout_block; - -/* Indirection for store get and free functions. These can be set to -alternative malloc/free functions if required. Special ones are used in the -non-recursive case for "frames". There is also an optional callout function -that is triggered by the (?) regex item. For Virtual Pascal, these definitions -have to take another form. */ - -#ifndef VPCOMPAT -PCRE_EXP_DECL void *(*pcre_malloc)(size_t); -PCRE_EXP_DECL void (*pcre_free)(void *); -PCRE_EXP_DECL void *(*pcre_stack_malloc)(size_t); -PCRE_EXP_DECL void (*pcre_stack_free)(void *); -PCRE_EXP_DECL int (*pcre_callout)(pcre_callout_block *); -PCRE_EXP_DECL int (*pcre_stack_guard)(void); - -PCRE_EXP_DECL void *(*pcre16_malloc)(size_t); -PCRE_EXP_DECL void (*pcre16_free)(void *); -PCRE_EXP_DECL void *(*pcre16_stack_malloc)(size_t); -PCRE_EXP_DECL void (*pcre16_stack_free)(void *); -PCRE_EXP_DECL int (*pcre16_callout)(pcre16_callout_block *); -PCRE_EXP_DECL int (*pcre16_stack_guard)(void); - -PCRE_EXP_DECL void *(*pcre32_malloc)(size_t); -PCRE_EXP_DECL void (*pcre32_free)(void *); -PCRE_EXP_DECL void *(*pcre32_stack_malloc)(size_t); -PCRE_EXP_DECL void (*pcre32_stack_free)(void *); -PCRE_EXP_DECL int (*pcre32_callout)(pcre32_callout_block *); -PCRE_EXP_DECL int (*pcre32_stack_guard)(void); -#else /* VPCOMPAT */ -PCRE_EXP_DECL void *pcre_malloc(size_t); -PCRE_EXP_DECL void pcre_free(void *); -PCRE_EXP_DECL void *pcre_stack_malloc(size_t); -PCRE_EXP_DECL void pcre_stack_free(void *); -PCRE_EXP_DECL int pcre_callout(pcre_callout_block *); -PCRE_EXP_DECL int pcre_stack_guard(void); - -PCRE_EXP_DECL void *pcre16_malloc(size_t); -PCRE_EXP_DECL void pcre16_free(void *); -PCRE_EXP_DECL void *pcre16_stack_malloc(size_t); -PCRE_EXP_DECL void pcre16_stack_free(void *); -PCRE_EXP_DECL int pcre16_callout(pcre16_callout_block *); -PCRE_EXP_DECL int pcre16_stack_guard(void); - -PCRE_EXP_DECL void *pcre32_malloc(size_t); -PCRE_EXP_DECL void pcre32_free(void *); -PCRE_EXP_DECL void *pcre32_stack_malloc(size_t); -PCRE_EXP_DECL void pcre32_stack_free(void *); -PCRE_EXP_DECL int pcre32_callout(pcre32_callout_block *); -PCRE_EXP_DECL int pcre32_stack_guard(void); -#endif /* VPCOMPAT */ - -/* User defined callback which provides a stack just before the match starts. */ - -typedef pcre_jit_stack *(*pcre_jit_callback)(void *); -typedef pcre16_jit_stack *(*pcre16_jit_callback)(void *); -typedef pcre32_jit_stack *(*pcre32_jit_callback)(void *); - -/* Exported PCRE functions */ - -PCRE_EXP_DECL pcre *pcre_compile(const char *, int, const char **, int *, - const unsigned char *); -PCRE_EXP_DECL pcre16 *pcre16_compile(PCRE_SPTR16, int, const char **, int *, - const unsigned char *); -PCRE_EXP_DECL pcre32 *pcre32_compile(PCRE_SPTR32, int, const char **, int *, - const unsigned char *); -PCRE_EXP_DECL pcre *pcre_compile2(const char *, int, int *, const char **, - int *, const unsigned char *); -PCRE_EXP_DECL pcre16 *pcre16_compile2(PCRE_SPTR16, int, int *, const char **, - int *, const unsigned char *); -PCRE_EXP_DECL pcre32 *pcre32_compile2(PCRE_SPTR32, int, int *, const char **, - int *, const unsigned char *); -PCRE_EXP_DECL int pcre_config(int, void *); -PCRE_EXP_DECL int pcre16_config(int, void *); -PCRE_EXP_DECL int pcre32_config(int, void *); -PCRE_EXP_DECL int pcre_copy_named_substring(const pcre *, const char *, - int *, int, const char *, char *, int); -PCRE_EXP_DECL int pcre16_copy_named_substring(const pcre16 *, PCRE_SPTR16, - int *, int, PCRE_SPTR16, PCRE_UCHAR16 *, int); -PCRE_EXP_DECL int pcre32_copy_named_substring(const pcre32 *, PCRE_SPTR32, - int *, int, PCRE_SPTR32, PCRE_UCHAR32 *, int); -PCRE_EXP_DECL int pcre_copy_substring(const char *, int *, int, int, - char *, int); -PCRE_EXP_DECL int pcre16_copy_substring(PCRE_SPTR16, int *, int, int, - PCRE_UCHAR16 *, int); -PCRE_EXP_DECL int pcre32_copy_substring(PCRE_SPTR32, int *, int, int, - PCRE_UCHAR32 *, int); -PCRE_EXP_DECL int pcre_dfa_exec(const pcre *, const pcre_extra *, - const char *, int, int, int, int *, int , int *, int); -PCRE_EXP_DECL int pcre16_dfa_exec(const pcre16 *, const pcre16_extra *, - PCRE_SPTR16, int, int, int, int *, int , int *, int); -PCRE_EXP_DECL int pcre32_dfa_exec(const pcre32 *, const pcre32_extra *, - PCRE_SPTR32, int, int, int, int *, int , int *, int); -PCRE_EXP_DECL int pcre_exec(const pcre *, const pcre_extra *, PCRE_SPTR, - int, int, int, int *, int); -PCRE_EXP_DECL int pcre16_exec(const pcre16 *, const pcre16_extra *, - PCRE_SPTR16, int, int, int, int *, int); -PCRE_EXP_DECL int pcre32_exec(const pcre32 *, const pcre32_extra *, - PCRE_SPTR32, int, int, int, int *, int); -PCRE_EXP_DECL int pcre_jit_exec(const pcre *, const pcre_extra *, - PCRE_SPTR, int, int, int, int *, int, - pcre_jit_stack *); -PCRE_EXP_DECL int pcre16_jit_exec(const pcre16 *, const pcre16_extra *, - PCRE_SPTR16, int, int, int, int *, int, - pcre16_jit_stack *); -PCRE_EXP_DECL int pcre32_jit_exec(const pcre32 *, const pcre32_extra *, - PCRE_SPTR32, int, int, int, int *, int, - pcre32_jit_stack *); -PCRE_EXP_DECL void pcre_free_substring(const char *); -PCRE_EXP_DECL void pcre16_free_substring(PCRE_SPTR16); -PCRE_EXP_DECL void pcre32_free_substring(PCRE_SPTR32); -PCRE_EXP_DECL void pcre_free_substring_list(const char **); -PCRE_EXP_DECL void pcre16_free_substring_list(PCRE_SPTR16 *); -PCRE_EXP_DECL void pcre32_free_substring_list(PCRE_SPTR32 *); -PCRE_EXP_DECL int pcre_fullinfo(const pcre *, const pcre_extra *, int, - void *); -PCRE_EXP_DECL int pcre16_fullinfo(const pcre16 *, const pcre16_extra *, int, - void *); -PCRE_EXP_DECL int pcre32_fullinfo(const pcre32 *, const pcre32_extra *, int, - void *); -PCRE_EXP_DECL int pcre_get_named_substring(const pcre *, const char *, - int *, int, const char *, const char **); -PCRE_EXP_DECL int pcre16_get_named_substring(const pcre16 *, PCRE_SPTR16, - int *, int, PCRE_SPTR16, PCRE_SPTR16 *); -PCRE_EXP_DECL int pcre32_get_named_substring(const pcre32 *, PCRE_SPTR32, - int *, int, PCRE_SPTR32, PCRE_SPTR32 *); -PCRE_EXP_DECL int pcre_get_stringnumber(const pcre *, const char *); -PCRE_EXP_DECL int pcre16_get_stringnumber(const pcre16 *, PCRE_SPTR16); -PCRE_EXP_DECL int pcre32_get_stringnumber(const pcre32 *, PCRE_SPTR32); -PCRE_EXP_DECL int pcre_get_stringtable_entries(const pcre *, const char *, - char **, char **); -PCRE_EXP_DECL int pcre16_get_stringtable_entries(const pcre16 *, PCRE_SPTR16, - PCRE_UCHAR16 **, PCRE_UCHAR16 **); -PCRE_EXP_DECL int pcre32_get_stringtable_entries(const pcre32 *, PCRE_SPTR32, - PCRE_UCHAR32 **, PCRE_UCHAR32 **); -PCRE_EXP_DECL int pcre_get_substring(const char *, int *, int, int, - const char **); -PCRE_EXP_DECL int pcre16_get_substring(PCRE_SPTR16, int *, int, int, - PCRE_SPTR16 *); -PCRE_EXP_DECL int pcre32_get_substring(PCRE_SPTR32, int *, int, int, - PCRE_SPTR32 *); -PCRE_EXP_DECL int pcre_get_substring_list(const char *, int *, int, - const char ***); -PCRE_EXP_DECL int pcre16_get_substring_list(PCRE_SPTR16, int *, int, - PCRE_SPTR16 **); -PCRE_EXP_DECL int pcre32_get_substring_list(PCRE_SPTR32, int *, int, - PCRE_SPTR32 **); -PCRE_EXP_DECL const unsigned char *pcre_maketables(void); -PCRE_EXP_DECL const unsigned char *pcre16_maketables(void); -PCRE_EXP_DECL const unsigned char *pcre32_maketables(void); -PCRE_EXP_DECL int pcre_refcount(pcre *, int); -PCRE_EXP_DECL int pcre16_refcount(pcre16 *, int); -PCRE_EXP_DECL int pcre32_refcount(pcre32 *, int); -PCRE_EXP_DECL pcre_extra *pcre_study(const pcre *, int, const char **); -PCRE_EXP_DECL pcre16_extra *pcre16_study(const pcre16 *, int, const char **); -PCRE_EXP_DECL pcre32_extra *pcre32_study(const pcre32 *, int, const char **); -PCRE_EXP_DECL void pcre_free_study(pcre_extra *); -PCRE_EXP_DECL void pcre16_free_study(pcre16_extra *); -PCRE_EXP_DECL void pcre32_free_study(pcre32_extra *); -PCRE_EXP_DECL const char *pcre_version(void); -PCRE_EXP_DECL const char *pcre16_version(void); -PCRE_EXP_DECL const char *pcre32_version(void); - -/* Utility functions for byte order swaps. */ -PCRE_EXP_DECL int pcre_pattern_to_host_byte_order(pcre *, pcre_extra *, - const unsigned char *); -PCRE_EXP_DECL int pcre16_pattern_to_host_byte_order(pcre16 *, pcre16_extra *, - const unsigned char *); -PCRE_EXP_DECL int pcre32_pattern_to_host_byte_order(pcre32 *, pcre32_extra *, - const unsigned char *); -PCRE_EXP_DECL int pcre16_utf16_to_host_byte_order(PCRE_UCHAR16 *, - PCRE_SPTR16, int, int *, int); -PCRE_EXP_DECL int pcre32_utf32_to_host_byte_order(PCRE_UCHAR32 *, - PCRE_SPTR32, int, int *, int); - -/* JIT compiler related functions. */ - -PCRE_EXP_DECL pcre_jit_stack *pcre_jit_stack_alloc(int, int); -PCRE_EXP_DECL pcre16_jit_stack *pcre16_jit_stack_alloc(int, int); -PCRE_EXP_DECL pcre32_jit_stack *pcre32_jit_stack_alloc(int, int); -PCRE_EXP_DECL void pcre_jit_stack_free(pcre_jit_stack *); -PCRE_EXP_DECL void pcre16_jit_stack_free(pcre16_jit_stack *); -PCRE_EXP_DECL void pcre32_jit_stack_free(pcre32_jit_stack *); -PCRE_EXP_DECL void pcre_assign_jit_stack(pcre_extra *, - pcre_jit_callback, void *); -PCRE_EXP_DECL void pcre16_assign_jit_stack(pcre16_extra *, - pcre16_jit_callback, void *); -PCRE_EXP_DECL void pcre32_assign_jit_stack(pcre32_extra *, - pcre32_jit_callback, void *); -PCRE_EXP_DECL void pcre_jit_free_unused_memory(void); -PCRE_EXP_DECL void pcre16_jit_free_unused_memory(void); -PCRE_EXP_DECL void pcre32_jit_free_unused_memory(void); - -#ifdef __cplusplus -} /* extern "C" */ -#endif - -#endif /* End of pcre.h */ diff --git a/src/third_party/pcre-8.38/pcre.h.in b/src/third_party/pcre-8.38/pcre.h.in deleted file mode 100644 index 667a45ed575..00000000000 --- a/src/third_party/pcre-8.38/pcre.h.in +++ /dev/null @@ -1,677 +0,0 @@ -/************************************************* -* Perl-Compatible Regular Expressions * -*************************************************/ - -/* This is the public header file for the PCRE library, to be #included by -applications that call the PCRE functions. - - Copyright (c) 1997-2014 University of Cambridge - ------------------------------------------------------------------------------ -Redistribution and use in source and binary forms, with or without -modification, are permitted provided that the following conditions are met: - - * Redistributions of source code must retain the above copyright notice, - this list of conditions and the following disclaimer. - - * Redistributions in binary form must reproduce the above copyright - notice, this list of conditions and the following disclaimer in the - documentation and/or other materials provided with the distribution. - - * Neither the name of the University of Cambridge nor the names of its - contributors may be used to endorse or promote products derived from - this software without specific prior written permission. - -THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS" -AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE -IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE -ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR CONTRIBUTORS BE -LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR -CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF -SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS -INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN -CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) -ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE -POSSIBILITY OF SUCH DAMAGE. ------------------------------------------------------------------------------ -*/ - -#ifndef _PCRE_H -#define _PCRE_H - -/* The current PCRE version information. */ - -#define PCRE_MAJOR @PCRE_MAJOR@ -#define PCRE_MINOR @PCRE_MINOR@ -#define PCRE_PRERELEASE @PCRE_PRERELEASE@ -#define PCRE_DATE @PCRE_DATE@ - -/* When an application links to a PCRE DLL in Windows, the symbols that are -imported have to be identified as such. When building PCRE, the appropriate -export setting is defined in pcre_internal.h, which includes this file. So we -don't change existing definitions of PCRE_EXP_DECL and PCRECPP_EXP_DECL. */ - -#if defined(_WIN32) && !defined(PCRE_STATIC) -# ifndef PCRE_EXP_DECL -# define PCRE_EXP_DECL extern __declspec(dllimport) -# endif -# ifdef __cplusplus -# ifndef PCRECPP_EXP_DECL -# define PCRECPP_EXP_DECL extern __declspec(dllimport) -# endif -# ifndef PCRECPP_EXP_DEFN -# define PCRECPP_EXP_DEFN __declspec(dllimport) -# endif -# endif -#endif - -/* By default, we use the standard "extern" declarations. */ - -#ifndef PCRE_EXP_DECL -# ifdef __cplusplus -# define PCRE_EXP_DECL extern "C" -# else -# define PCRE_EXP_DECL extern -# endif -#endif - -#ifdef __cplusplus -# ifndef PCRECPP_EXP_DECL -# define PCRECPP_EXP_DECL extern -# endif -# ifndef PCRECPP_EXP_DEFN -# define PCRECPP_EXP_DEFN -# endif -#endif - -/* Have to include stdlib.h in order to ensure that size_t is defined; -it is needed here for malloc. */ - -#include <stdlib.h> - -/* Allow for C++ users */ - -#ifdef __cplusplus -extern "C" { -#endif - -/* Public options. Some are compile-time only, some are run-time only, and some -are both. Most of the compile-time options are saved with the compiled regex so -that they can be inspected during studying (and therefore JIT compiling). Note -that pcre_study() has its own set of options. Originally, all the options -defined here used distinct bits. However, almost all the bits in a 32-bit word -are now used, so in order to conserve them, option bits that were previously -only recognized at matching time (i.e. by pcre_exec() or pcre_dfa_exec()) may -also be used for compile-time options that affect only compiling and are not -relevant for studying or JIT compiling. - -Some options for pcre_compile() change its behaviour but do not affect the -behaviour of the execution functions. Other options are passed through to the -execution functions and affect their behaviour, with or without affecting the -behaviour of pcre_compile(). - -Options that can be passed to pcre_compile() are tagged Cx below, with these -variants: - -C1 Affects compile only -C2 Does not affect compile; affects exec, dfa_exec -C3 Affects compile, exec, dfa_exec -C4 Affects compile, exec, dfa_exec, study -C5 Affects compile, exec, study - -Options that can be set for pcre_exec() and/or pcre_dfa_exec() are flagged with -E and D, respectively. They take precedence over C3, C4, and C5 settings passed -from pcre_compile(). Those that are compatible with JIT execution are flagged -with J. */ - -#define PCRE_CASELESS 0x00000001 /* C1 */ -#define PCRE_MULTILINE 0x00000002 /* C1 */ -#define PCRE_DOTALL 0x00000004 /* C1 */ -#define PCRE_EXTENDED 0x00000008 /* C1 */ -#define PCRE_ANCHORED 0x00000010 /* C4 E D */ -#define PCRE_DOLLAR_ENDONLY 0x00000020 /* C2 */ -#define PCRE_EXTRA 0x00000040 /* C1 */ -#define PCRE_NOTBOL 0x00000080 /* E D J */ -#define PCRE_NOTEOL 0x00000100 /* E D J */ -#define PCRE_UNGREEDY 0x00000200 /* C1 */ -#define PCRE_NOTEMPTY 0x00000400 /* E D J */ -#define PCRE_UTF8 0x00000800 /* C4 ) */ -#define PCRE_UTF16 0x00000800 /* C4 ) Synonyms */ -#define PCRE_UTF32 0x00000800 /* C4 ) */ -#define PCRE_NO_AUTO_CAPTURE 0x00001000 /* C1 */ -#define PCRE_NO_UTF8_CHECK 0x00002000 /* C1 E D J ) */ -#define PCRE_NO_UTF16_CHECK 0x00002000 /* C1 E D J ) Synonyms */ -#define PCRE_NO_UTF32_CHECK 0x00002000 /* C1 E D J ) */ -#define PCRE_AUTO_CALLOUT 0x00004000 /* C1 */ -#define PCRE_PARTIAL_SOFT 0x00008000 /* E D J ) Synonyms */ -#define PCRE_PARTIAL 0x00008000 /* E D J ) */ - -/* This pair use the same bit. */ -#define PCRE_NEVER_UTF 0x00010000 /* C1 ) Overlaid */ -#define PCRE_DFA_SHORTEST 0x00010000 /* D ) Overlaid */ - -/* This pair use the same bit. */ -#define PCRE_NO_AUTO_POSSESS 0x00020000 /* C1 ) Overlaid */ -#define PCRE_DFA_RESTART 0x00020000 /* D ) Overlaid */ - -#define PCRE_FIRSTLINE 0x00040000 /* C3 */ -#define PCRE_DUPNAMES 0x00080000 /* C1 */ -#define PCRE_NEWLINE_CR 0x00100000 /* C3 E D */ -#define PCRE_NEWLINE_LF 0x00200000 /* C3 E D */ -#define PCRE_NEWLINE_CRLF 0x00300000 /* C3 E D */ -#define PCRE_NEWLINE_ANY 0x00400000 /* C3 E D */ -#define PCRE_NEWLINE_ANYCRLF 0x00500000 /* C3 E D */ -#define PCRE_BSR_ANYCRLF 0x00800000 /* C3 E D */ -#define PCRE_BSR_UNICODE 0x01000000 /* C3 E D */ -#define PCRE_JAVASCRIPT_COMPAT 0x02000000 /* C5 */ -#define PCRE_NO_START_OPTIMIZE 0x04000000 /* C2 E D ) Synonyms */ -#define PCRE_NO_START_OPTIMISE 0x04000000 /* C2 E D ) */ -#define PCRE_PARTIAL_HARD 0x08000000 /* E D J */ -#define PCRE_NOTEMPTY_ATSTART 0x10000000 /* E D J */ -#define PCRE_UCP 0x20000000 /* C3 */ - -/* Exec-time and get/set-time error codes */ - -#define PCRE_ERROR_NOMATCH (-1) -#define PCRE_ERROR_NULL (-2) -#define PCRE_ERROR_BADOPTION (-3) -#define PCRE_ERROR_BADMAGIC (-4) -#define PCRE_ERROR_UNKNOWN_OPCODE (-5) -#define PCRE_ERROR_UNKNOWN_NODE (-5) /* For backward compatibility */ -#define PCRE_ERROR_NOMEMORY (-6) -#define PCRE_ERROR_NOSUBSTRING (-7) -#define PCRE_ERROR_MATCHLIMIT (-8) -#define PCRE_ERROR_CALLOUT (-9) /* Never used by PCRE itself */ -#define PCRE_ERROR_BADUTF8 (-10) /* Same for 8/16/32 */ -#define PCRE_ERROR_BADUTF16 (-10) /* Same for 8/16/32 */ -#define PCRE_ERROR_BADUTF32 (-10) /* Same for 8/16/32 */ -#define PCRE_ERROR_BADUTF8_OFFSET (-11) /* Same for 8/16 */ -#define PCRE_ERROR_BADUTF16_OFFSET (-11) /* Same for 8/16 */ -#define PCRE_ERROR_PARTIAL (-12) -#define PCRE_ERROR_BADPARTIAL (-13) -#define PCRE_ERROR_INTERNAL (-14) -#define PCRE_ERROR_BADCOUNT (-15) -#define PCRE_ERROR_DFA_UITEM (-16) -#define PCRE_ERROR_DFA_UCOND (-17) -#define PCRE_ERROR_DFA_UMLIMIT (-18) -#define PCRE_ERROR_DFA_WSSIZE (-19) -#define PCRE_ERROR_DFA_RECURSE (-20) -#define PCRE_ERROR_RECURSIONLIMIT (-21) -#define PCRE_ERROR_NULLWSLIMIT (-22) /* No longer actually used */ -#define PCRE_ERROR_BADNEWLINE (-23) -#define PCRE_ERROR_BADOFFSET (-24) -#define PCRE_ERROR_SHORTUTF8 (-25) -#define PCRE_ERROR_SHORTUTF16 (-25) /* Same for 8/16 */ -#define PCRE_ERROR_RECURSELOOP (-26) -#define PCRE_ERROR_JIT_STACKLIMIT (-27) -#define PCRE_ERROR_BADMODE (-28) -#define PCRE_ERROR_BADENDIANNESS (-29) -#define PCRE_ERROR_DFA_BADRESTART (-30) -#define PCRE_ERROR_JIT_BADOPTION (-31) -#define PCRE_ERROR_BADLENGTH (-32) -#define PCRE_ERROR_UNSET (-33) - -/* Specific error codes for UTF-8 validity checks */ - -#define PCRE_UTF8_ERR0 0 -#define PCRE_UTF8_ERR1 1 -#define PCRE_UTF8_ERR2 2 -#define PCRE_UTF8_ERR3 3 -#define PCRE_UTF8_ERR4 4 -#define PCRE_UTF8_ERR5 5 -#define PCRE_UTF8_ERR6 6 -#define PCRE_UTF8_ERR7 7 -#define PCRE_UTF8_ERR8 8 -#define PCRE_UTF8_ERR9 9 -#define PCRE_UTF8_ERR10 10 -#define PCRE_UTF8_ERR11 11 -#define PCRE_UTF8_ERR12 12 -#define PCRE_UTF8_ERR13 13 -#define PCRE_UTF8_ERR14 14 -#define PCRE_UTF8_ERR15 15 -#define PCRE_UTF8_ERR16 16 -#define PCRE_UTF8_ERR17 17 -#define PCRE_UTF8_ERR18 18 -#define PCRE_UTF8_ERR19 19 -#define PCRE_UTF8_ERR20 20 -#define PCRE_UTF8_ERR21 21 -#define PCRE_UTF8_ERR22 22 /* Unused (was non-character) */ - -/* Specific error codes for UTF-16 validity checks */ - -#define PCRE_UTF16_ERR0 0 -#define PCRE_UTF16_ERR1 1 -#define PCRE_UTF16_ERR2 2 -#define PCRE_UTF16_ERR3 3 -#define PCRE_UTF16_ERR4 4 /* Unused (was non-character) */ - -/* Specific error codes for UTF-32 validity checks */ - -#define PCRE_UTF32_ERR0 0 -#define PCRE_UTF32_ERR1 1 -#define PCRE_UTF32_ERR2 2 /* Unused (was non-character) */ -#define PCRE_UTF32_ERR3 3 - -/* Request types for pcre_fullinfo() */ - -#define PCRE_INFO_OPTIONS 0 -#define PCRE_INFO_SIZE 1 -#define PCRE_INFO_CAPTURECOUNT 2 -#define PCRE_INFO_BACKREFMAX 3 -#define PCRE_INFO_FIRSTBYTE 4 -#define PCRE_INFO_FIRSTCHAR 4 /* For backwards compatibility */ -#define PCRE_INFO_FIRSTTABLE 5 -#define PCRE_INFO_LASTLITERAL 6 -#define PCRE_INFO_NAMEENTRYSIZE 7 -#define PCRE_INFO_NAMECOUNT 8 -#define PCRE_INFO_NAMETABLE 9 -#define PCRE_INFO_STUDYSIZE 10 -#define PCRE_INFO_DEFAULT_TABLES 11 -#define PCRE_INFO_OKPARTIAL 12 -#define PCRE_INFO_JCHANGED 13 -#define PCRE_INFO_HASCRORLF 14 -#define PCRE_INFO_MINLENGTH 15 -#define PCRE_INFO_JIT 16 -#define PCRE_INFO_JITSIZE 17 -#define PCRE_INFO_MAXLOOKBEHIND 18 -#define PCRE_INFO_FIRSTCHARACTER 19 -#define PCRE_INFO_FIRSTCHARACTERFLAGS 20 -#define PCRE_INFO_REQUIREDCHAR 21 -#define PCRE_INFO_REQUIREDCHARFLAGS 22 -#define PCRE_INFO_MATCHLIMIT 23 -#define PCRE_INFO_RECURSIONLIMIT 24 -#define PCRE_INFO_MATCH_EMPTY 25 - -/* Request types for pcre_config(). Do not re-arrange, in order to remain -compatible. */ - -#define PCRE_CONFIG_UTF8 0 -#define PCRE_CONFIG_NEWLINE 1 -#define PCRE_CONFIG_LINK_SIZE 2 -#define PCRE_CONFIG_POSIX_MALLOC_THRESHOLD 3 -#define PCRE_CONFIG_MATCH_LIMIT 4 -#define PCRE_CONFIG_STACKRECURSE 5 -#define PCRE_CONFIG_UNICODE_PROPERTIES 6 -#define PCRE_CONFIG_MATCH_LIMIT_RECURSION 7 -#define PCRE_CONFIG_BSR 8 -#define PCRE_CONFIG_JIT 9 -#define PCRE_CONFIG_UTF16 10 -#define PCRE_CONFIG_JITTARGET 11 -#define PCRE_CONFIG_UTF32 12 -#define PCRE_CONFIG_PARENS_LIMIT 13 - -/* Request types for pcre_study(). Do not re-arrange, in order to remain -compatible. */ - -#define PCRE_STUDY_JIT_COMPILE 0x0001 -#define PCRE_STUDY_JIT_PARTIAL_SOFT_COMPILE 0x0002 -#define PCRE_STUDY_JIT_PARTIAL_HARD_COMPILE 0x0004 -#define PCRE_STUDY_EXTRA_NEEDED 0x0008 - -/* Bit flags for the pcre[16|32]_extra structure. Do not re-arrange or redefine -these bits, just add new ones on the end, in order to remain compatible. */ - -#define PCRE_EXTRA_STUDY_DATA 0x0001 -#define PCRE_EXTRA_MATCH_LIMIT 0x0002 -#define PCRE_EXTRA_CALLOUT_DATA 0x0004 -#define PCRE_EXTRA_TABLES 0x0008 -#define PCRE_EXTRA_MATCH_LIMIT_RECURSION 0x0010 -#define PCRE_EXTRA_MARK 0x0020 -#define PCRE_EXTRA_EXECUTABLE_JIT 0x0040 - -/* Types */ - -struct real_pcre; /* declaration; the definition is private */ -typedef struct real_pcre pcre; - -struct real_pcre16; /* declaration; the definition is private */ -typedef struct real_pcre16 pcre16; - -struct real_pcre32; /* declaration; the definition is private */ -typedef struct real_pcre32 pcre32; - -struct real_pcre_jit_stack; /* declaration; the definition is private */ -typedef struct real_pcre_jit_stack pcre_jit_stack; - -struct real_pcre16_jit_stack; /* declaration; the definition is private */ -typedef struct real_pcre16_jit_stack pcre16_jit_stack; - -struct real_pcre32_jit_stack; /* declaration; the definition is private */ -typedef struct real_pcre32_jit_stack pcre32_jit_stack; - -/* If PCRE is compiled with 16 bit character support, PCRE_UCHAR16 must contain -a 16 bit wide signed data type. Otherwise it can be a dummy data type since -pcre16 functions are not implemented. There is a check for this in pcre_internal.h. */ -#ifndef PCRE_UCHAR16 -#define PCRE_UCHAR16 unsigned short -#endif - -#ifndef PCRE_SPTR16 -#define PCRE_SPTR16 const PCRE_UCHAR16 * -#endif - -/* If PCRE is compiled with 32 bit character support, PCRE_UCHAR32 must contain -a 32 bit wide signed data type. Otherwise it can be a dummy data type since -pcre32 functions are not implemented. There is a check for this in pcre_internal.h. */ -#ifndef PCRE_UCHAR32 -#define PCRE_UCHAR32 unsigned int -#endif - -#ifndef PCRE_SPTR32 -#define PCRE_SPTR32 const PCRE_UCHAR32 * -#endif - -/* When PCRE is compiled as a C++ library, the subject pointer type can be -replaced with a custom type. For conventional use, the public interface is a -const char *. */ - -#ifndef PCRE_SPTR -#define PCRE_SPTR const char * -#endif - -/* The structure for passing additional data to pcre_exec(). This is defined in -such as way as to be extensible. Always add new fields at the end, in order to -remain compatible. */ - -typedef struct pcre_extra { - unsigned long int flags; /* Bits for which fields are set */ - void *study_data; /* Opaque data from pcre_study() */ - unsigned long int match_limit; /* Maximum number of calls to match() */ - void *callout_data; /* Data passed back in callouts */ - const unsigned char *tables; /* Pointer to character tables */ - unsigned long int match_limit_recursion; /* Max recursive calls to match() */ - unsigned char **mark; /* For passing back a mark pointer */ - void *executable_jit; /* Contains a pointer to a compiled jit code */ -} pcre_extra; - -/* Same structure as above, but with 16 bit char pointers. */ - -typedef struct pcre16_extra { - unsigned long int flags; /* Bits for which fields are set */ - void *study_data; /* Opaque data from pcre_study() */ - unsigned long int match_limit; /* Maximum number of calls to match() */ - void *callout_data; /* Data passed back in callouts */ - const unsigned char *tables; /* Pointer to character tables */ - unsigned long int match_limit_recursion; /* Max recursive calls to match() */ - PCRE_UCHAR16 **mark; /* For passing back a mark pointer */ - void *executable_jit; /* Contains a pointer to a compiled jit code */ -} pcre16_extra; - -/* Same structure as above, but with 32 bit char pointers. */ - -typedef struct pcre32_extra { - unsigned long int flags; /* Bits for which fields are set */ - void *study_data; /* Opaque data from pcre_study() */ - unsigned long int match_limit; /* Maximum number of calls to match() */ - void *callout_data; /* Data passed back in callouts */ - const unsigned char *tables; /* Pointer to character tables */ - unsigned long int match_limit_recursion; /* Max recursive calls to match() */ - PCRE_UCHAR32 **mark; /* For passing back a mark pointer */ - void *executable_jit; /* Contains a pointer to a compiled jit code */ -} pcre32_extra; - -/* The structure for passing out data via the pcre_callout_function. We use a -structure so that new fields can be added on the end in future versions, -without changing the API of the function, thereby allowing old clients to work -without modification. */ - -typedef struct pcre_callout_block { - int version; /* Identifies version of block */ - /* ------------------------ Version 0 ------------------------------- */ - int callout_number; /* Number compiled into pattern */ - int *offset_vector; /* The offset vector */ - PCRE_SPTR subject; /* The subject being matched */ - int subject_length; /* The length of the subject */ - int start_match; /* Offset to start of this match attempt */ - int current_position; /* Where we currently are in the subject */ - int capture_top; /* Max current capture */ - int capture_last; /* Most recently closed capture */ - void *callout_data; /* Data passed in with the call */ - /* ------------------- Added for Version 1 -------------------------- */ - int pattern_position; /* Offset to next item in the pattern */ - int next_item_length; /* Length of next item in the pattern */ - /* ------------------- Added for Version 2 -------------------------- */ - const unsigned char *mark; /* Pointer to current mark or NULL */ - /* ------------------------------------------------------------------ */ -} pcre_callout_block; - -/* Same structure as above, but with 16 bit char pointers. */ - -typedef struct pcre16_callout_block { - int version; /* Identifies version of block */ - /* ------------------------ Version 0 ------------------------------- */ - int callout_number; /* Number compiled into pattern */ - int *offset_vector; /* The offset vector */ - PCRE_SPTR16 subject; /* The subject being matched */ - int subject_length; /* The length of the subject */ - int start_match; /* Offset to start of this match attempt */ - int current_position; /* Where we currently are in the subject */ - int capture_top; /* Max current capture */ - int capture_last; /* Most recently closed capture */ - void *callout_data; /* Data passed in with the call */ - /* ------------------- Added for Version 1 -------------------------- */ - int pattern_position; /* Offset to next item in the pattern */ - int next_item_length; /* Length of next item in the pattern */ - /* ------------------- Added for Version 2 -------------------------- */ - const PCRE_UCHAR16 *mark; /* Pointer to current mark or NULL */ - /* ------------------------------------------------------------------ */ -} pcre16_callout_block; - -/* Same structure as above, but with 32 bit char pointers. */ - -typedef struct pcre32_callout_block { - int version; /* Identifies version of block */ - /* ------------------------ Version 0 ------------------------------- */ - int callout_number; /* Number compiled into pattern */ - int *offset_vector; /* The offset vector */ - PCRE_SPTR32 subject; /* The subject being matched */ - int subject_length; /* The length of the subject */ - int start_match; /* Offset to start of this match attempt */ - int current_position; /* Where we currently are in the subject */ - int capture_top; /* Max current capture */ - int capture_last; /* Most recently closed capture */ - void *callout_data; /* Data passed in with the call */ - /* ------------------- Added for Version 1 -------------------------- */ - int pattern_position; /* Offset to next item in the pattern */ - int next_item_length; /* Length of next item in the pattern */ - /* ------------------- Added for Version 2 -------------------------- */ - const PCRE_UCHAR32 *mark; /* Pointer to current mark or NULL */ - /* ------------------------------------------------------------------ */ -} pcre32_callout_block; - -/* Indirection for store get and free functions. These can be set to -alternative malloc/free functions if required. Special ones are used in the -non-recursive case for "frames". There is also an optional callout function -that is triggered by the (?) regex item. For Virtual Pascal, these definitions -have to take another form. */ - -#ifndef VPCOMPAT -PCRE_EXP_DECL void *(*pcre_malloc)(size_t); -PCRE_EXP_DECL void (*pcre_free)(void *); -PCRE_EXP_DECL void *(*pcre_stack_malloc)(size_t); -PCRE_EXP_DECL void (*pcre_stack_free)(void *); -PCRE_EXP_DECL int (*pcre_callout)(pcre_callout_block *); -PCRE_EXP_DECL int (*pcre_stack_guard)(void); - -PCRE_EXP_DECL void *(*pcre16_malloc)(size_t); -PCRE_EXP_DECL void (*pcre16_free)(void *); -PCRE_EXP_DECL void *(*pcre16_stack_malloc)(size_t); -PCRE_EXP_DECL void (*pcre16_stack_free)(void *); -PCRE_EXP_DECL int (*pcre16_callout)(pcre16_callout_block *); -PCRE_EXP_DECL int (*pcre16_stack_guard)(void); - -PCRE_EXP_DECL void *(*pcre32_malloc)(size_t); -PCRE_EXP_DECL void (*pcre32_free)(void *); -PCRE_EXP_DECL void *(*pcre32_stack_malloc)(size_t); -PCRE_EXP_DECL void (*pcre32_stack_free)(void *); -PCRE_EXP_DECL int (*pcre32_callout)(pcre32_callout_block *); -PCRE_EXP_DECL int (*pcre32_stack_guard)(void); -#else /* VPCOMPAT */ -PCRE_EXP_DECL void *pcre_malloc(size_t); -PCRE_EXP_DECL void pcre_free(void *); -PCRE_EXP_DECL void *pcre_stack_malloc(size_t); -PCRE_EXP_DECL void pcre_stack_free(void *); -PCRE_EXP_DECL int pcre_callout(pcre_callout_block *); -PCRE_EXP_DECL int pcre_stack_guard(void); - -PCRE_EXP_DECL void *pcre16_malloc(size_t); -PCRE_EXP_DECL void pcre16_free(void *); -PCRE_EXP_DECL void *pcre16_stack_malloc(size_t); -PCRE_EXP_DECL void pcre16_stack_free(void *); -PCRE_EXP_DECL int pcre16_callout(pcre16_callout_block *); -PCRE_EXP_DECL int pcre16_stack_guard(void); - -PCRE_EXP_DECL void *pcre32_malloc(size_t); -PCRE_EXP_DECL void pcre32_free(void *); -PCRE_EXP_DECL void *pcre32_stack_malloc(size_t); -PCRE_EXP_DECL void pcre32_stack_free(void *); -PCRE_EXP_DECL int pcre32_callout(pcre32_callout_block *); -PCRE_EXP_DECL int pcre32_stack_guard(void); -#endif /* VPCOMPAT */ - -/* User defined callback which provides a stack just before the match starts. */ - -typedef pcre_jit_stack *(*pcre_jit_callback)(void *); -typedef pcre16_jit_stack *(*pcre16_jit_callback)(void *); -typedef pcre32_jit_stack *(*pcre32_jit_callback)(void *); - -/* Exported PCRE functions */ - -PCRE_EXP_DECL pcre *pcre_compile(const char *, int, const char **, int *, - const unsigned char *); -PCRE_EXP_DECL pcre16 *pcre16_compile(PCRE_SPTR16, int, const char **, int *, - const unsigned char *); -PCRE_EXP_DECL pcre32 *pcre32_compile(PCRE_SPTR32, int, const char **, int *, - const unsigned char *); -PCRE_EXP_DECL pcre *pcre_compile2(const char *, int, int *, const char **, - int *, const unsigned char *); -PCRE_EXP_DECL pcre16 *pcre16_compile2(PCRE_SPTR16, int, int *, const char **, - int *, const unsigned char *); -PCRE_EXP_DECL pcre32 *pcre32_compile2(PCRE_SPTR32, int, int *, const char **, - int *, const unsigned char *); -PCRE_EXP_DECL int pcre_config(int, void *); -PCRE_EXP_DECL int pcre16_config(int, void *); -PCRE_EXP_DECL int pcre32_config(int, void *); -PCRE_EXP_DECL int pcre_copy_named_substring(const pcre *, const char *, - int *, int, const char *, char *, int); -PCRE_EXP_DECL int pcre16_copy_named_substring(const pcre16 *, PCRE_SPTR16, - int *, int, PCRE_SPTR16, PCRE_UCHAR16 *, int); -PCRE_EXP_DECL int pcre32_copy_named_substring(const pcre32 *, PCRE_SPTR32, - int *, int, PCRE_SPTR32, PCRE_UCHAR32 *, int); -PCRE_EXP_DECL int pcre_copy_substring(const char *, int *, int, int, - char *, int); -PCRE_EXP_DECL int pcre16_copy_substring(PCRE_SPTR16, int *, int, int, - PCRE_UCHAR16 *, int); -PCRE_EXP_DECL int pcre32_copy_substring(PCRE_SPTR32, int *, int, int, - PCRE_UCHAR32 *, int); -PCRE_EXP_DECL int pcre_dfa_exec(const pcre *, const pcre_extra *, - const char *, int, int, int, int *, int , int *, int); -PCRE_EXP_DECL int pcre16_dfa_exec(const pcre16 *, const pcre16_extra *, - PCRE_SPTR16, int, int, int, int *, int , int *, int); -PCRE_EXP_DECL int pcre32_dfa_exec(const pcre32 *, const pcre32_extra *, - PCRE_SPTR32, int, int, int, int *, int , int *, int); -PCRE_EXP_DECL int pcre_exec(const pcre *, const pcre_extra *, PCRE_SPTR, - int, int, int, int *, int); -PCRE_EXP_DECL int pcre16_exec(const pcre16 *, const pcre16_extra *, - PCRE_SPTR16, int, int, int, int *, int); -PCRE_EXP_DECL int pcre32_exec(const pcre32 *, const pcre32_extra *, - PCRE_SPTR32, int, int, int, int *, int); -PCRE_EXP_DECL int pcre_jit_exec(const pcre *, const pcre_extra *, - PCRE_SPTR, int, int, int, int *, int, - pcre_jit_stack *); -PCRE_EXP_DECL int pcre16_jit_exec(const pcre16 *, const pcre16_extra *, - PCRE_SPTR16, int, int, int, int *, int, - pcre16_jit_stack *); -PCRE_EXP_DECL int pcre32_jit_exec(const pcre32 *, const pcre32_extra *, - PCRE_SPTR32, int, int, int, int *, int, - pcre32_jit_stack *); -PCRE_EXP_DECL void pcre_free_substring(const char *); -PCRE_EXP_DECL void pcre16_free_substring(PCRE_SPTR16); -PCRE_EXP_DECL void pcre32_free_substring(PCRE_SPTR32); -PCRE_EXP_DECL void pcre_free_substring_list(const char **); -PCRE_EXP_DECL void pcre16_free_substring_list(PCRE_SPTR16 *); -PCRE_EXP_DECL void pcre32_free_substring_list(PCRE_SPTR32 *); -PCRE_EXP_DECL int pcre_fullinfo(const pcre *, const pcre_extra *, int, - void *); -PCRE_EXP_DECL int pcre16_fullinfo(const pcre16 *, const pcre16_extra *, int, - void *); -PCRE_EXP_DECL int pcre32_fullinfo(const pcre32 *, const pcre32_extra *, int, - void *); -PCRE_EXP_DECL int pcre_get_named_substring(const pcre *, const char *, - int *, int, const char *, const char **); -PCRE_EXP_DECL int pcre16_get_named_substring(const pcre16 *, PCRE_SPTR16, - int *, int, PCRE_SPTR16, PCRE_SPTR16 *); -PCRE_EXP_DECL int pcre32_get_named_substring(const pcre32 *, PCRE_SPTR32, - int *, int, PCRE_SPTR32, PCRE_SPTR32 *); -PCRE_EXP_DECL int pcre_get_stringnumber(const pcre *, const char *); -PCRE_EXP_DECL int pcre16_get_stringnumber(const pcre16 *, PCRE_SPTR16); -PCRE_EXP_DECL int pcre32_get_stringnumber(const pcre32 *, PCRE_SPTR32); -PCRE_EXP_DECL int pcre_get_stringtable_entries(const pcre *, const char *, - char **, char **); -PCRE_EXP_DECL int pcre16_get_stringtable_entries(const pcre16 *, PCRE_SPTR16, - PCRE_UCHAR16 **, PCRE_UCHAR16 **); -PCRE_EXP_DECL int pcre32_get_stringtable_entries(const pcre32 *, PCRE_SPTR32, - PCRE_UCHAR32 **, PCRE_UCHAR32 **); -PCRE_EXP_DECL int pcre_get_substring(const char *, int *, int, int, - const char **); -PCRE_EXP_DECL int pcre16_get_substring(PCRE_SPTR16, int *, int, int, - PCRE_SPTR16 *); -PCRE_EXP_DECL int pcre32_get_substring(PCRE_SPTR32, int *, int, int, - PCRE_SPTR32 *); -PCRE_EXP_DECL int pcre_get_substring_list(const char *, int *, int, - const char ***); -PCRE_EXP_DECL int pcre16_get_substring_list(PCRE_SPTR16, int *, int, - PCRE_SPTR16 **); -PCRE_EXP_DECL int pcre32_get_substring_list(PCRE_SPTR32, int *, int, - PCRE_SPTR32 **); -PCRE_EXP_DECL const unsigned char *pcre_maketables(void); -PCRE_EXP_DECL const unsigned char *pcre16_maketables(void); -PCRE_EXP_DECL const unsigned char *pcre32_maketables(void); -PCRE_EXP_DECL int pcre_refcount(pcre *, int); -PCRE_EXP_DECL int pcre16_refcount(pcre16 *, int); -PCRE_EXP_DECL int pcre32_refcount(pcre32 *, int); -PCRE_EXP_DECL pcre_extra *pcre_study(const pcre *, int, const char **); -PCRE_EXP_DECL pcre16_extra *pcre16_study(const pcre16 *, int, const char **); -PCRE_EXP_DECL pcre32_extra *pcre32_study(const pcre32 *, int, const char **); -PCRE_EXP_DECL void pcre_free_study(pcre_extra *); -PCRE_EXP_DECL void pcre16_free_study(pcre16_extra *); -PCRE_EXP_DECL void pcre32_free_study(pcre32_extra *); -PCRE_EXP_DECL const char *pcre_version(void); -PCRE_EXP_DECL const char *pcre16_version(void); -PCRE_EXP_DECL const char *pcre32_version(void); - -/* Utility functions for byte order swaps. */ -PCRE_EXP_DECL int pcre_pattern_to_host_byte_order(pcre *, pcre_extra *, - const unsigned char *); -PCRE_EXP_DECL int pcre16_pattern_to_host_byte_order(pcre16 *, pcre16_extra *, - const unsigned char *); -PCRE_EXP_DECL int pcre32_pattern_to_host_byte_order(pcre32 *, pcre32_extra *, - const unsigned char *); -PCRE_EXP_DECL int pcre16_utf16_to_host_byte_order(PCRE_UCHAR16 *, - PCRE_SPTR16, int, int *, int); -PCRE_EXP_DECL int pcre32_utf32_to_host_byte_order(PCRE_UCHAR32 *, - PCRE_SPTR32, int, int *, int); - -/* JIT compiler related functions. */ - -PCRE_EXP_DECL pcre_jit_stack *pcre_jit_stack_alloc(int, int); -PCRE_EXP_DECL pcre16_jit_stack *pcre16_jit_stack_alloc(int, int); -PCRE_EXP_DECL pcre32_jit_stack *pcre32_jit_stack_alloc(int, int); -PCRE_EXP_DECL void pcre_jit_stack_free(pcre_jit_stack *); -PCRE_EXP_DECL void pcre16_jit_stack_free(pcre16_jit_stack *); -PCRE_EXP_DECL void pcre32_jit_stack_free(pcre32_jit_stack *); -PCRE_EXP_DECL void pcre_assign_jit_stack(pcre_extra *, - pcre_jit_callback, void *); -PCRE_EXP_DECL void pcre16_assign_jit_stack(pcre16_extra *, - pcre16_jit_callback, void *); -PCRE_EXP_DECL void pcre32_assign_jit_stack(pcre32_extra *, - pcre32_jit_callback, void *); -PCRE_EXP_DECL void pcre_jit_free_unused_memory(void); -PCRE_EXP_DECL void pcre16_jit_free_unused_memory(void); -PCRE_EXP_DECL void pcre32_jit_free_unused_memory(void); - -#ifdef __cplusplus -} /* extern "C" */ -#endif - -#endif /* End of pcre.h */ diff --git a/src/third_party/pcre-8.38/pcre16_byte_order.c b/src/third_party/pcre-8.38/pcre16_byte_order.c deleted file mode 100644 index 11d2973a3db..00000000000 --- a/src/third_party/pcre-8.38/pcre16_byte_order.c +++ /dev/null @@ -1,45 +0,0 @@ -/************************************************* -* Perl-Compatible Regular Expressions * -*************************************************/ - -/* PCRE is a library of functions to support regular expressions whose syntax -and semantics are as close as possible to those of the Perl 5 language. - - Written by Philip Hazel - Copyright (c) 1997-2012 University of Cambridge - ------------------------------------------------------------------------------ -Redistribution and use in source and binary forms, with or without -modification, are permitted provided that the following conditions are met: - - * Redistributions of source code must retain the above copyright notice, - this list of conditions and the following disclaimer. - - * Redistributions in binary form must reproduce the above copyright - notice, this list of conditions and the following disclaimer in the - documentation and/or other materials provided with the distribution. - - * Neither the name of the University of Cambridge nor the names of its - contributors may be used to endorse or promote products derived from - this software without specific prior written permission. - -THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS" -AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE -IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE -ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR CONTRIBUTORS BE -LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR -CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF -SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS -INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN -CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) -ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE -POSSIBILITY OF SUCH DAMAGE. ------------------------------------------------------------------------------ -*/ - -/* Generate code with 16 bit character support. */ -#define COMPILE_PCRE16 - -#include "pcre_byte_order.c" - -/* End of pcre16_byte_order.c */ diff --git a/src/third_party/pcre-8.38/pcre16_chartables.c b/src/third_party/pcre-8.38/pcre16_chartables.c deleted file mode 100644 index 7c0ff35f5e0..00000000000 --- a/src/third_party/pcre-8.38/pcre16_chartables.c +++ /dev/null @@ -1,45 +0,0 @@ -/************************************************* -* Perl-Compatible Regular Expressions * -*************************************************/ - -/* PCRE is a library of functions to support regular expressions whose syntax -and semantics are as close as possible to those of the Perl 5 language. - - Written by Philip Hazel - Copyright (c) 1997-2012 University of Cambridge - ------------------------------------------------------------------------------ -Redistribution and use in source and binary forms, with or without -modification, are permitted provided that the following conditions are met: - - * Redistributions of source code must retain the above copyright notice, - this list of conditions and the following disclaimer. - - * Redistributions in binary form must reproduce the above copyright - notice, this list of conditions and the following disclaimer in the - documentation and/or other materials provided with the distribution. - - * Neither the name of the University of Cambridge nor the names of its - contributors may be used to endorse or promote products derived from - this software without specific prior written permission. - -THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS" -AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE -IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE -ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR CONTRIBUTORS BE -LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR -CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF -SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS -INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN -CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) -ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE -POSSIBILITY OF SUCH DAMAGE. ------------------------------------------------------------------------------ -*/ - -/* Generate code with 16 bit character support. */ -#define COMPILE_PCRE16 - -#include "pcre_chartables.c" - -/* End of pcre16_chartables.c */ diff --git a/src/third_party/pcre-8.38/pcre16_compile.c b/src/third_party/pcre-8.38/pcre16_compile.c deleted file mode 100644 index e499b670877..00000000000 --- a/src/third_party/pcre-8.38/pcre16_compile.c +++ /dev/null @@ -1,45 +0,0 @@ -/************************************************* -* Perl-Compatible Regular Expressions * -*************************************************/ - -/* PCRE is a library of functions to support regular expressions whose syntax -and semantics are as close as possible to those of the Perl 5 language. - - Written by Philip Hazel - Copyright (c) 1997-2012 University of Cambridge - ------------------------------------------------------------------------------ -Redistribution and use in source and binary forms, with or without -modification, are permitted provided that the following conditions are met: - - * Redistributions of source code must retain the above copyright notice, - this list of conditions and the following disclaimer. - - * Redistributions in binary form must reproduce the above copyright - notice, this list of conditions and the following disclaimer in the - documentation and/or other materials provided with the distribution. - - * Neither the name of the University of Cambridge nor the names of its - contributors may be used to endorse or promote products derived from - this software without specific prior written permission. - -THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS" -AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE -IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE -ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR CONTRIBUTORS BE -LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR -CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF -SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS -INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN -CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) -ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE -POSSIBILITY OF SUCH DAMAGE. ------------------------------------------------------------------------------ -*/ - -/* Generate code with 16 bit character support. */ -#define COMPILE_PCRE16 - -#include "pcre_compile.c" - -/* End of pcre16_compile.c */ diff --git a/src/third_party/pcre-8.38/pcre16_config.c b/src/third_party/pcre-8.38/pcre16_config.c deleted file mode 100644 index b52138764f6..00000000000 --- a/src/third_party/pcre-8.38/pcre16_config.c +++ /dev/null @@ -1,45 +0,0 @@ -/************************************************* -* Perl-Compatible Regular Expressions * -*************************************************/ - -/* PCRE is a library of functions to support regular expressions whose syntax -and semantics are as close as possible to those of the Perl 5 language. - - Written by Philip Hazel - Copyright (c) 1997-2012 University of Cambridge - ------------------------------------------------------------------------------ -Redistribution and use in source and binary forms, with or without -modification, are permitted provided that the following conditions are met: - - * Redistributions of source code must retain the above copyright notice, - this list of conditions and the following disclaimer. - - * Redistributions in binary form must reproduce the above copyright - notice, this list of conditions and the following disclaimer in the - documentation and/or other materials provided with the distribution. - - * Neither the name of the University of Cambridge nor the names of its - contributors may be used to endorse or promote products derived from - this software without specific prior written permission. - -THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS" -AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE -IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE -ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR CONTRIBUTORS BE -LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR -CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF -SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS -INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN -CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) -ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE -POSSIBILITY OF SUCH DAMAGE. ------------------------------------------------------------------------------ -*/ - -/* Generate code with 16 bit character support. */ -#define COMPILE_PCRE16 - -#include "pcre_config.c" - -/* End of pcre16_config.c */ diff --git a/src/third_party/pcre-8.38/pcre16_dfa_exec.c b/src/third_party/pcre-8.38/pcre16_dfa_exec.c deleted file mode 100644 index 2ba740e972b..00000000000 --- a/src/third_party/pcre-8.38/pcre16_dfa_exec.c +++ /dev/null @@ -1,45 +0,0 @@ -/************************************************* -* Perl-Compatible Regular Expressions * -*************************************************/ - -/* PCRE is a library of functions to support regular expressions whose syntax -and semantics are as close as possible to those of the Perl 5 language. - - Written by Philip Hazel - Copyright (c) 1997-2012 University of Cambridge - ------------------------------------------------------------------------------ -Redistribution and use in source and binary forms, with or without -modification, are permitted provided that the following conditions are met: - - * Redistributions of source code must retain the above copyright notice, - this list of conditions and the following disclaimer. - - * Redistributions in binary form must reproduce the above copyright - notice, this list of conditions and the following disclaimer in the - documentation and/or other materials provided with the distribution. - - * Neither the name of the University of Cambridge nor the names of its - contributors may be used to endorse or promote products derived from - this software without specific prior written permission. - -THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS" -AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE -IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE -ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR CONTRIBUTORS BE -LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR -CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF -SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS -INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN -CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) -ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE -POSSIBILITY OF SUCH DAMAGE. ------------------------------------------------------------------------------ -*/ - -/* Generate code with 16 bit character support. */ -#define COMPILE_PCRE16 - -#include "pcre_dfa_exec.c" - -/* End of pcre16_dfa_exec.c */ diff --git a/src/third_party/pcre-8.38/pcre16_exec.c b/src/third_party/pcre-8.38/pcre16_exec.c deleted file mode 100644 index 7417b1770c6..00000000000 --- a/src/third_party/pcre-8.38/pcre16_exec.c +++ /dev/null @@ -1,45 +0,0 @@ -/************************************************* -* Perl-Compatible Regular Expressions * -*************************************************/ - -/* PCRE is a library of functions to support regular expressions whose syntax -and semantics are as close as possible to those of the Perl 5 language. - - Written by Philip Hazel - Copyright (c) 1997-2012 University of Cambridge - ------------------------------------------------------------------------------ -Redistribution and use in source and binary forms, with or without -modification, are permitted provided that the following conditions are met: - - * Redistributions of source code must retain the above copyright notice, - this list of conditions and the following disclaimer. - - * Redistributions in binary form must reproduce the above copyright - notice, this list of conditions and the following disclaimer in the - documentation and/or other materials provided with the distribution. - - * Neither the name of the University of Cambridge nor the names of its - contributors may be used to endorse or promote products derived from - this software without specific prior written permission. - -THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS" -AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE -IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE -ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR CONTRIBUTORS BE -LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR -CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF -SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS -INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN -CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) -ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE -POSSIBILITY OF SUCH DAMAGE. ------------------------------------------------------------------------------ -*/ - -/* Generate code with 16 bit character support. */ -#define COMPILE_PCRE16 - -#include "pcre_exec.c" - -/* End of pcre16_exec.c */ diff --git a/src/third_party/pcre-8.38/pcre16_fullinfo.c b/src/third_party/pcre-8.38/pcre16_fullinfo.c deleted file mode 100644 index 544dca6ed5c..00000000000 --- a/src/third_party/pcre-8.38/pcre16_fullinfo.c +++ /dev/null @@ -1,45 +0,0 @@ -/************************************************* -* Perl-Compatible Regular Expressions * -*************************************************/ - -/* PCRE is a library of functions to support regular expressions whose syntax -and semantics are as close as possible to those of the Perl 5 language. - - Written by Philip Hazel - Copyright (c) 1997-2012 University of Cambridge - ------------------------------------------------------------------------------ -Redistribution and use in source and binary forms, with or without -modification, are permitted provided that the following conditions are met: - - * Redistributions of source code must retain the above copyright notice, - this list of conditions and the following disclaimer. - - * Redistributions in binary form must reproduce the above copyright - notice, this list of conditions and the following disclaimer in the - documentation and/or other materials provided with the distribution. - - * Neither the name of the University of Cambridge nor the names of its - contributors may be used to endorse or promote products derived from - this software without specific prior written permission. - -THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS" -AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE -IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE -ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR CONTRIBUTORS BE -LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR -CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF -SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS -INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN -CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) -ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE -POSSIBILITY OF SUCH DAMAGE. ------------------------------------------------------------------------------ -*/ - -/* Generate code with 16 bit character support. */ -#define COMPILE_PCRE16 - -#include "pcre_fullinfo.c" - -/* End of pcre16_fullinfo.c */ diff --git a/src/third_party/pcre-8.38/pcre16_get.c b/src/third_party/pcre-8.38/pcre16_get.c deleted file mode 100644 index 3ded08c622c..00000000000 --- a/src/third_party/pcre-8.38/pcre16_get.c +++ /dev/null @@ -1,45 +0,0 @@ -/************************************************* -* Perl-Compatible Regular Expressions * -*************************************************/ - -/* PCRE is a library of functions to support regular expressions whose syntax -and semantics are as close as possible to those of the Perl 5 language. - - Written by Philip Hazel - Copyright (c) 1997-2012 University of Cambridge - ------------------------------------------------------------------------------ -Redistribution and use in source and binary forms, with or without -modification, are permitted provided that the following conditions are met: - - * Redistributions of source code must retain the above copyright notice, - this list of conditions and the following disclaimer. - - * Redistributions in binary form must reproduce the above copyright - notice, this list of conditions and the following disclaimer in the - documentation and/or other materials provided with the distribution. - - * Neither the name of the University of Cambridge nor the names of its - contributors may be used to endorse or promote products derived from - this software without specific prior written permission. - -THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS" -AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE -IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE -ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR CONTRIBUTORS BE -LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR -CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF -SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS -INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN -CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) -ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE -POSSIBILITY OF SUCH DAMAGE. ------------------------------------------------------------------------------ -*/ - -/* Generate code with 16 bit character support. */ -#define COMPILE_PCRE16 - -#include "pcre_get.c" - -/* End of pcre16_get.c */ diff --git a/src/third_party/pcre-8.38/pcre16_globals.c b/src/third_party/pcre-8.38/pcre16_globals.c deleted file mode 100644 index a136b3d8c22..00000000000 --- a/src/third_party/pcre-8.38/pcre16_globals.c +++ /dev/null @@ -1,45 +0,0 @@ -/************************************************* -* Perl-Compatible Regular Expressions * -*************************************************/ - -/* PCRE is a library of functions to support regular expressions whose syntax -and semantics are as close as possible to those of the Perl 5 language. - - Written by Philip Hazel - Copyright (c) 1997-2012 University of Cambridge - ------------------------------------------------------------------------------ -Redistribution and use in source and binary forms, with or without -modification, are permitted provided that the following conditions are met: - - * Redistributions of source code must retain the above copyright notice, - this list of conditions and the following disclaimer. - - * Redistributions in binary form must reproduce the above copyright - notice, this list of conditions and the following disclaimer in the - documentation and/or other materials provided with the distribution. - - * Neither the name of the University of Cambridge nor the names of its - contributors may be used to endorse or promote products derived from - this software without specific prior written permission. - -THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS" -AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE -IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE -ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR CONTRIBUTORS BE -LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR -CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF -SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS -INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN -CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) -ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE -POSSIBILITY OF SUCH DAMAGE. ------------------------------------------------------------------------------ -*/ - -/* Generate code with 16 bit character support. */ -#define COMPILE_PCRE16 - -#include "pcre_globals.c" - -/* End of pcre16_globals.c */ diff --git a/src/third_party/pcre-8.38/pcre16_jit_compile.c b/src/third_party/pcre-8.38/pcre16_jit_compile.c deleted file mode 100644 index ab0cacd7646..00000000000 --- a/src/third_party/pcre-8.38/pcre16_jit_compile.c +++ /dev/null @@ -1,45 +0,0 @@ -/************************************************* -* Perl-Compatible Regular Expressions * -*************************************************/ - -/* PCRE is a library of functions to support regular expressions whose syntax -and semantics are as close as possible to those of the Perl 5 language. - - Written by Philip Hazel - Copyright (c) 1997-2012 University of Cambridge - ------------------------------------------------------------------------------ -Redistribution and use in source and binary forms, with or without -modification, are permitted provided that the following conditions are met: - - * Redistributions of source code must retain the above copyright notice, - this list of conditions and the following disclaimer. - - * Redistributions in binary form must reproduce the above copyright - notice, this list of conditions and the following disclaimer in the - documentation and/or other materials provided with the distribution. - - * Neither the name of the University of Cambridge nor the names of its - contributors may be used to endorse or promote products derived from - this software without specific prior written permission. - -THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS" -AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE -IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE -ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR CONTRIBUTORS BE -LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR -CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF -SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS -INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN -CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) -ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE -POSSIBILITY OF SUCH DAMAGE. ------------------------------------------------------------------------------ -*/ - -/* Generate code with 16 bit character support. */ -#define COMPILE_PCRE16 - -#include "pcre_jit_compile.c" - -/* End of pcre16_jit_compile.c */ diff --git a/src/third_party/pcre-8.38/pcre16_maketables.c b/src/third_party/pcre-8.38/pcre16_maketables.c deleted file mode 100644 index b1cd1c579d6..00000000000 --- a/src/third_party/pcre-8.38/pcre16_maketables.c +++ /dev/null @@ -1,45 +0,0 @@ -/************************************************* -* Perl-Compatible Regular Expressions * -*************************************************/ - -/* PCRE is a library of functions to support regular expressions whose syntax -and semantics are as close as possible to those of the Perl 5 language. - - Written by Philip Hazel - Copyright (c) 1997-2012 University of Cambridge - ------------------------------------------------------------------------------ -Redistribution and use in source and binary forms, with or without -modification, are permitted provided that the following conditions are met: - - * Redistributions of source code must retain the above copyright notice, - this list of conditions and the following disclaimer. - - * Redistributions in binary form must reproduce the above copyright - notice, this list of conditions and the following disclaimer in the - documentation and/or other materials provided with the distribution. - - * Neither the name of the University of Cambridge nor the names of its - contributors may be used to endorse or promote products derived from - this software without specific prior written permission. - -THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS" -AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE -IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE -ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR CONTRIBUTORS BE -LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR -CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF -SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS -INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN -CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) -ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE -POSSIBILITY OF SUCH DAMAGE. ------------------------------------------------------------------------------ -*/ - -/* Generate code with 16 bit character support. */ -#define COMPILE_PCRE16 - -#include "pcre_maketables.c" - -/* End of pcre16_maketables.c */ diff --git a/src/third_party/pcre-8.38/pcre16_newline.c b/src/third_party/pcre-8.38/pcre16_newline.c deleted file mode 100644 index 7fe201400f5..00000000000 --- a/src/third_party/pcre-8.38/pcre16_newline.c +++ /dev/null @@ -1,45 +0,0 @@ -/************************************************* -* Perl-Compatible Regular Expressions * -*************************************************/ - -/* PCRE is a library of functions to support regular expressions whose syntax -and semantics are as close as possible to those of the Perl 5 language. - - Written by Philip Hazel - Copyright (c) 1997-2012 University of Cambridge - ------------------------------------------------------------------------------ -Redistribution and use in source and binary forms, with or without -modification, are permitted provided that the following conditions are met: - - * Redistributions of source code must retain the above copyright notice, - this list of conditions and the following disclaimer. - - * Redistributions in binary form must reproduce the above copyright - notice, this list of conditions and the following disclaimer in the - documentation and/or other materials provided with the distribution. - - * Neither the name of the University of Cambridge nor the names of its - contributors may be used to endorse or promote products derived from - this software without specific prior written permission. - -THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS" -AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE -IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE -ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR CONTRIBUTORS BE -LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR -CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF -SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS -INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN -CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) -ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE -POSSIBILITY OF SUCH DAMAGE. ------------------------------------------------------------------------------ -*/ - -/* Generate code with 16 bit character support. */ -#define COMPILE_PCRE16 - -#include "pcre_newline.c" - -/* End of pcre16_newline.c */ diff --git a/src/third_party/pcre-8.38/pcre16_ord2utf16.c b/src/third_party/pcre-8.38/pcre16_ord2utf16.c deleted file mode 100644 index 8e2ce5ea6c5..00000000000 --- a/src/third_party/pcre-8.38/pcre16_ord2utf16.c +++ /dev/null @@ -1,90 +0,0 @@ -/************************************************* -* Perl-Compatible Regular Expressions * -*************************************************/ - -/* PCRE is a library of functions to support regular expressions whose syntax -and semantics are as close as possible to those of the Perl 5 language. - - Written by Philip Hazel - Copyright (c) 1997-2012 University of Cambridge - ------------------------------------------------------------------------------ -Redistribution and use in source and binary forms, with or without -modification, are permitted provided that the following conditions are met: - - * Redistributions of source code must retain the above copyright notice, - this list of conditions and the following disclaimer. - - * Redistributions in binary form must reproduce the above copyright - notice, this list of conditions and the following disclaimer in the - documentation and/or other materials provided with the distribution. - - * Neither the name of the University of Cambridge nor the names of its - contributors may be used to endorse or promote products derived from - this software without specific prior written permission. - -THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS" -AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE -IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE -ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR CONTRIBUTORS BE -LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR -CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF -SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS -INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN -CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) -ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE -POSSIBILITY OF SUCH DAMAGE. ------------------------------------------------------------------------------ -*/ - - -/* This file contains a private PCRE function that converts an ordinal -character value into a UTF16 string. */ - -#ifdef HAVE_CONFIG_H -#include "config.h" -#endif - -/* Generate code with 16 bit character support. */ -#define COMPILE_PCRE16 - -#include "pcre_internal.h" - -/************************************************* -* Convert character value to UTF-16 * -*************************************************/ - -/* This function takes an integer value in the range 0 - 0x10ffff -and encodes it as a UTF-16 character in 1 to 2 pcre_uchars. - -Arguments: - cvalue the character value - buffer pointer to buffer for result - at least 2 pcre_uchars long - -Returns: number of characters placed in the buffer -*/ - -unsigned int -PRIV(ord2utf)(pcre_uint32 cvalue, pcre_uchar *buffer) -{ -#ifdef SUPPORT_UTF - -if (cvalue <= 0xffff) - { - *buffer = (pcre_uchar)cvalue; - return 1; - } - -cvalue -= 0x10000; -*buffer++ = 0xd800 | (cvalue >> 10); -*buffer = 0xdc00 | (cvalue & 0x3ff); -return 2; - -#else /* SUPPORT_UTF */ -(void)(cvalue); /* Keep compiler happy; this function won't ever be */ -(void)(buffer); /* called when SUPPORT_UTF is not defined. */ -return 0; -#endif /* SUPPORT_UTF */ -} - -/* End of pcre16_ord2utf16.c */ diff --git a/src/third_party/pcre-8.38/pcre16_printint.c b/src/third_party/pcre-8.38/pcre16_printint.c deleted file mode 100644 index 33d8c340200..00000000000 --- a/src/third_party/pcre-8.38/pcre16_printint.c +++ /dev/null @@ -1,45 +0,0 @@ -/************************************************* -* Perl-Compatible Regular Expressions * -*************************************************/ - -/* PCRE is a library of functions to support regular expressions whose syntax -and semantics are as close as possible to those of the Perl 5 language. - - Written by Philip Hazel - Copyright (c) 1997-2012 University of Cambridge - ------------------------------------------------------------------------------ -Redistribution and use in source and binary forms, with or without -modification, are permitted provided that the following conditions are met: - - * Redistributions of source code must retain the above copyright notice, - this list of conditions and the following disclaimer. - - * Redistributions in binary form must reproduce the above copyright - notice, this list of conditions and the following disclaimer in the - documentation and/or other materials provided with the distribution. - - * Neither the name of the University of Cambridge nor the names of its - contributors may be used to endorse or promote products derived from - this software without specific prior written permission. - -THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS" -AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE -IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE -ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR CONTRIBUTORS BE -LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR -CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF -SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS -INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN -CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) -ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE -POSSIBILITY OF SUCH DAMAGE. ------------------------------------------------------------------------------ -*/ - -/* Generate code with 16 bit character support. */ -#define COMPILE_PCRE16 - -#include "pcre_printint.c" - -/* End of pcre16_printint.c */ diff --git a/src/third_party/pcre-8.38/pcre16_refcount.c b/src/third_party/pcre-8.38/pcre16_refcount.c deleted file mode 100644 index d3d15439737..00000000000 --- a/src/third_party/pcre-8.38/pcre16_refcount.c +++ /dev/null @@ -1,45 +0,0 @@ -/************************************************* -* Perl-Compatible Regular Expressions * -*************************************************/ - -/* PCRE is a library of functions to support regular expressions whose syntax -and semantics are as close as possible to those of the Perl 5 language. - - Written by Philip Hazel - Copyright (c) 1997-2012 University of Cambridge - ------------------------------------------------------------------------------ -Redistribution and use in source and binary forms, with or without -modification, are permitted provided that the following conditions are met: - - * Redistributions of source code must retain the above copyright notice, - this list of conditions and the following disclaimer. - - * Redistributions in binary form must reproduce the above copyright - notice, this list of conditions and the following disclaimer in the - documentation and/or other materials provided with the distribution. - - * Neither the name of the University of Cambridge nor the names of its - contributors may be used to endorse or promote products derived from - this software without specific prior written permission. - -THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS" -AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE -IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE -ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR CONTRIBUTORS BE -LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR -CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF -SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS -INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN -CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) -ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE -POSSIBILITY OF SUCH DAMAGE. ------------------------------------------------------------------------------ -*/ - -/* Generate code with 16 bit character support. */ -#define COMPILE_PCRE16 - -#include "pcre_refcount.c" - -/* End of pcre16_refcount.c */ diff --git a/src/third_party/pcre-8.38/pcre16_string_utils.c b/src/third_party/pcre-8.38/pcre16_string_utils.c deleted file mode 100644 index 382c40799fb..00000000000 --- a/src/third_party/pcre-8.38/pcre16_string_utils.c +++ /dev/null @@ -1,45 +0,0 @@ -/************************************************* -* Perl-Compatible Regular Expressions * -*************************************************/ - -/* PCRE is a library of functions to support regular expressions whose syntax -and semantics are as close as possible to those of the Perl 5 language. - - Written by Philip Hazel - Copyright (c) 1997-2012 University of Cambridge - ------------------------------------------------------------------------------ -Redistribution and use in source and binary forms, with or without -modification, are permitted provided that the following conditions are met: - - * Redistributions of source code must retain the above copyright notice, - this list of conditions and the following disclaimer. - - * Redistributions in binary form must reproduce the above copyright - notice, this list of conditions and the following disclaimer in the - documentation and/or other materials provided with the distribution. - - * Neither the name of the University of Cambridge nor the names of its - contributors may be used to endorse or promote products derived from - this software without specific prior written permission. - -THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS" -AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE -IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE -ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR CONTRIBUTORS BE -LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR -CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF -SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS -INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN -CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) -ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE -POSSIBILITY OF SUCH DAMAGE. ------------------------------------------------------------------------------ -*/ - -/* Generate code with 16 bit character support. */ -#define COMPILE_PCRE16 - -#include "pcre_string_utils.c" - -/* End of pcre16_string_utils.c */ diff --git a/src/third_party/pcre-8.38/pcre16_study.c b/src/third_party/pcre-8.38/pcre16_study.c deleted file mode 100644 index f87de081fc4..00000000000 --- a/src/third_party/pcre-8.38/pcre16_study.c +++ /dev/null @@ -1,45 +0,0 @@ -/************************************************* -* Perl-Compatible Regular Expressions * -*************************************************/ - -/* PCRE is a library of functions to support regular expressions whose syntax -and semantics are as close as possible to those of the Perl 5 language. - - Written by Philip Hazel - Copyright (c) 1997-2012 University of Cambridge - ------------------------------------------------------------------------------ -Redistribution and use in source and binary forms, with or without -modification, are permitted provided that the following conditions are met: - - * Redistributions of source code must retain the above copyright notice, - this list of conditions and the following disclaimer. - - * Redistributions in binary form must reproduce the above copyright - notice, this list of conditions and the following disclaimer in the - documentation and/or other materials provided with the distribution. - - * Neither the name of the University of Cambridge nor the names of its - contributors may be used to endorse or promote products derived from - this software without specific prior written permission. - -THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS" -AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE -IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE -ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR CONTRIBUTORS BE -LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR -CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF -SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS -INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN -CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) -ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE -POSSIBILITY OF SUCH DAMAGE. ------------------------------------------------------------------------------ -*/ - -/* Generate code with 16 bit character support. */ -#define COMPILE_PCRE16 - -#include "pcre_study.c" - -/* End of pcre16_study.c */ diff --git a/src/third_party/pcre-8.38/pcre16_tables.c b/src/third_party/pcre-8.38/pcre16_tables.c deleted file mode 100644 index d84297093a4..00000000000 --- a/src/third_party/pcre-8.38/pcre16_tables.c +++ /dev/null @@ -1,45 +0,0 @@ -/************************************************* -* Perl-Compatible Regular Expressions * -*************************************************/ - -/* PCRE is a library of functions to support regular expressions whose syntax -and semantics are as close as possible to those of the Perl 5 language. - - Written by Philip Hazel - Copyright (c) 1997-2012 University of Cambridge - ------------------------------------------------------------------------------ -Redistribution and use in source and binary forms, with or without -modification, are permitted provided that the following conditions are met: - - * Redistributions of source code must retain the above copyright notice, - this list of conditions and the following disclaimer. - - * Redistributions in binary form must reproduce the above copyright - notice, this list of conditions and the following disclaimer in the - documentation and/or other materials provided with the distribution. - - * Neither the name of the University of Cambridge nor the names of its - contributors may be used to endorse or promote products derived from - this software without specific prior written permission. - -THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS" -AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE -IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE -ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR CONTRIBUTORS BE -LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR -CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF -SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS -INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN -CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) -ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE -POSSIBILITY OF SUCH DAMAGE. ------------------------------------------------------------------------------ -*/ - -/* Generate code with 16 bit character support. */ -#define COMPILE_PCRE16 - -#include "pcre_tables.c" - -/* End of pcre16_tables.c */ diff --git a/src/third_party/pcre-8.38/pcre16_ucd.c b/src/third_party/pcre-8.38/pcre16_ucd.c deleted file mode 100644 index ee23439a013..00000000000 --- a/src/third_party/pcre-8.38/pcre16_ucd.c +++ /dev/null @@ -1,45 +0,0 @@ -/************************************************* -* Perl-Compatible Regular Expressions * -*************************************************/ - -/* PCRE is a library of functions to support regular expressions whose syntax -and semantics are as close as possible to those of the Perl 5 language. - - Written by Philip Hazel - Copyright (c) 1997-2012 University of Cambridge - ------------------------------------------------------------------------------ -Redistribution and use in source and binary forms, with or without -modification, are permitted provided that the following conditions are met: - - * Redistributions of source code must retain the above copyright notice, - this list of conditions and the following disclaimer. - - * Redistributions in binary form must reproduce the above copyright - notice, this list of conditions and the following disclaimer in the - documentation and/or other materials provided with the distribution. - - * Neither the name of the University of Cambridge nor the names of its - contributors may be used to endorse or promote products derived from - this software without specific prior written permission. - -THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS" -AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE -IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE -ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR CONTRIBUTORS BE -LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR -CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF -SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS -INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN -CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) -ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE -POSSIBILITY OF SUCH DAMAGE. ------------------------------------------------------------------------------ -*/ - -/* Generate code with 16 bit character support. */ -#define COMPILE_PCRE16 - -#include "pcre_ucd.c" - -/* End of pcre16_ucd.c */ diff --git a/src/third_party/pcre-8.38/pcre16_utf16_utils.c b/src/third_party/pcre-8.38/pcre16_utf16_utils.c deleted file mode 100644 index 49ced0c0b1c..00000000000 --- a/src/third_party/pcre-8.38/pcre16_utf16_utils.c +++ /dev/null @@ -1,130 +0,0 @@ -/************************************************* -* Perl-Compatible Regular Expressions * -*************************************************/ - -/* PCRE is a library of functions to support regular expressions whose syntax -and semantics are as close as possible to those of the Perl 5 language. - - Written by Philip Hazel - Copyright (c) 1997-2012 University of Cambridge - ------------------------------------------------------------------------------ -Redistribution and use in source and binary forms, with or without -modification, are permitted provided that the following conditions are met: - - * Redistributions of source code must retain the above copyright notice, - this list of conditions and the following disclaimer. - - * Redistributions in binary form must reproduce the above copyright - notice, this list of conditions and the following disclaimer in the - documentation and/or other materials provided with the distribution. - - * Neither the name of the University of Cambridge nor the names of its - contributors may be used to endorse or promote products derived from - this software without specific prior written permission. - -THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS" -AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE -IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE -ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR CONTRIBUTORS BE -LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR -CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF -SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS -INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN -CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) -ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE -POSSIBILITY OF SUCH DAMAGE. ------------------------------------------------------------------------------ -*/ - - -/* This module contains a function for converting any UTF-16 character -strings to host byte order. */ - - -#ifdef HAVE_CONFIG_H -#include "config.h" -#endif - -/* Generate code with 16 bit character support. */ -#define COMPILE_PCRE16 - -#include "pcre_internal.h" - -/************************************************* -* Convert any UTF-16 string to host byte order * -*************************************************/ - -/* This function takes an UTF-16 string and converts -it to host byte order. The length can be explicitly set, -or automatically detected for zero terminated strings. -BOMs can be kept or discarded during the conversion. -Conversion can be done in place (output == input). - -Arguments: - output the output buffer, its size must be greater - or equal than the input string - input any UTF-16 string - length the number of 16-bit units in the input string - can be less than zero for zero terminated strings - host_byte_order - A non-zero value means the input is in host byte - order, which can be dynamically changed by BOMs later. - Initially it contains the starting byte order and returns - with the last byte order so it can be used for stream - processing. It can be NULL, which set the host byte - order mode by default. - keep_boms for a non-zero value, the BOM (0xfeff) characters - are copied as well - -Returns: the number of 16-bit units placed into the output buffer, - including the zero-terminator -*/ - -int -pcre16_utf16_to_host_byte_order(PCRE_UCHAR16 *output, PCRE_SPTR16 input, - int length, int *host_byte_order, int keep_boms) -{ -#ifdef SUPPORT_UTF -/* This function converts any UTF-16 string to host byte order and optionally -removes any Byte Order Marks (BOMS). Returns with the remainig length. */ -int host_bo = host_byte_order != NULL ? *host_byte_order : 1; -pcre_uchar *optr = (pcre_uchar *)output; -const pcre_uchar *iptr = (const pcre_uchar *)input; -const pcre_uchar *end; -/* The c variable must be unsigned. */ -register pcre_uchar c; - -if (length < 0) - length = STRLEN_UC(iptr) + 1; -end = iptr + length; - -while (iptr < end) - { - c = *iptr++; - if (c == 0xfeff || c == 0xfffe) - { - /* Detecting the byte order of the machine is unnecessary, it is - enough to know that the UTF-16 string has the same byte order or not. */ - host_bo = c == 0xfeff; - if (keep_boms != 0) - *optr++ = 0xfeff; - else - length--; - } - else - *optr++ = host_bo ? c : ((c >> 8) | (c << 8)); /* Flip bytes if needed. */ - } -if (host_byte_order != NULL) - *host_byte_order = host_bo; - -#else /* Not SUPPORT_UTF */ -(void)(output); /* Keep picky compilers happy */ -(void)(input); -(void)(keep_boms); -(void)(host_byte_order); -#endif /* SUPPORT_UTF */ -return length; -} - -/* End of pcre16_utf16_utils.c */ diff --git a/src/third_party/pcre-8.38/pcre16_valid_utf16.c b/src/third_party/pcre-8.38/pcre16_valid_utf16.c deleted file mode 100644 index 09076539d09..00000000000 --- a/src/third_party/pcre-8.38/pcre16_valid_utf16.c +++ /dev/null @@ -1,137 +0,0 @@ -/************************************************* -* Perl-Compatible Regular Expressions * -*************************************************/ - -/* PCRE is a library of functions to support regular expressions whose syntax -and semantics are as close as possible to those of the Perl 5 language. - - Written by Philip Hazel - Copyright (c) 1997-2013 University of Cambridge - ------------------------------------------------------------------------------ -Redistribution and use in source and binary forms, with or without -modification, are permitted provided that the following conditions are met: - - * Redistributions of source code must retain the above copyright notice, - this list of conditions and the following disclaimer. - - * Redistributions in binary form must reproduce the above copyright - notice, this list of conditions and the following disclaimer in the - documentation and/or other materials provided with the distribution. - - * Neither the name of the University of Cambridge nor the names of its - contributors may be used to endorse or promote products derived from - this software without specific prior written permission. - -THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS" -AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE -IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE -ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR CONTRIBUTORS BE -LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR -CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF -SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS -INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN -CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) -ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE -POSSIBILITY OF SUCH DAMAGE. ------------------------------------------------------------------------------ -*/ - - -/* This module contains an internal function for validating UTF-16 character -strings. */ - - -#ifdef HAVE_CONFIG_H -#include "config.h" -#endif - -/* Generate code with 16 bit character support. */ -#define COMPILE_PCRE16 - -#include "pcre_internal.h" - - -/************************************************* -* Validate a UTF-16 string * -*************************************************/ - -/* This function is called (optionally) at the start of compile or match, to -check that a supposed UTF-16 string is actually valid. The early check means -that subsequent code can assume it is dealing with a valid string. The check -can be turned off for maximum performance, but the consequences of supplying an -invalid string are then undefined. - -From release 8.21 more information about the details of the error are passed -back in the returned value: - -PCRE_UTF16_ERR0 No error -PCRE_UTF16_ERR1 Missing low surrogate at the end of the string -PCRE_UTF16_ERR2 Invalid low surrogate -PCRE_UTF16_ERR3 Isolated low surrogate -PCRE_UTF16_ERR4 Unused (was non-character) - -Arguments: - string points to the string - length length of string, or -1 if the string is zero-terminated - errp pointer to an error position offset variable - -Returns: = 0 if the string is a valid UTF-16 string - > 0 otherwise, setting the offset of the bad character -*/ - -int -PRIV(valid_utf)(PCRE_PUCHAR string, int length, int *erroroffset) -{ -#ifdef SUPPORT_UTF -register PCRE_PUCHAR p; -register pcre_uint32 c; - -if (length < 0) - { - for (p = string; *p != 0; p++); - length = p - string; - } - -for (p = string; length-- > 0; p++) - { - c = *p; - - if ((c & 0xf800) != 0xd800) - { - /* Normal UTF-16 code point. Neither high nor low surrogate. */ - } - else if ((c & 0x0400) == 0) - { - /* High surrogate. Must be a followed by a low surrogate. */ - if (length == 0) - { - *erroroffset = p - string; - return PCRE_UTF16_ERR1; - } - p++; - length--; - if ((*p & 0xfc00) != 0xdc00) - { - *erroroffset = p - string; - return PCRE_UTF16_ERR2; - } - } - else - { - /* Isolated low surrogate. Always an error. */ - *erroroffset = p - string; - return PCRE_UTF16_ERR3; - } - } - -#else /* SUPPORT_UTF */ -(void)(string); /* Keep picky compilers happy */ -(void)(length); -(void)(erroroffset); -#endif /* SUPPORT_UTF */ - -return PCRE_UTF16_ERR0; /* This indicates success */ -} - -/* End of pcre16_valid_utf16.c */ diff --git a/src/third_party/pcre-8.38/pcre16_version.c b/src/third_party/pcre-8.38/pcre16_version.c deleted file mode 100644 index e991b1a8cfd..00000000000 --- a/src/third_party/pcre-8.38/pcre16_version.c +++ /dev/null @@ -1,45 +0,0 @@ -/************************************************* -* Perl-Compatible Regular Expressions * -*************************************************/ - -/* PCRE is a library of functions to support regular expressions whose syntax -and semantics are as close as possible to those of the Perl 5 language. - - Written by Philip Hazel - Copyright (c) 1997-2012 University of Cambridge - ------------------------------------------------------------------------------ -Redistribution and use in source and binary forms, with or without -modification, are permitted provided that the following conditions are met: - - * Redistributions of source code must retain the above copyright notice, - this list of conditions and the following disclaimer. - - * Redistributions in binary form must reproduce the above copyright - notice, this list of conditions and the following disclaimer in the - documentation and/or other materials provided with the distribution. - - * Neither the name of the University of Cambridge nor the names of its - contributors may be used to endorse or promote products derived from - this software without specific prior written permission. - -THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS" -AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE -IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE -ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR CONTRIBUTORS BE -LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR -CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF -SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS -INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN -CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) -ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE -POSSIBILITY OF SUCH DAMAGE. ------------------------------------------------------------------------------ -*/ - -/* Generate code with 16 bit character support. */ -#define COMPILE_PCRE16 - -#include "pcre_version.c" - -/* End of pcre16_version.c */ diff --git a/src/third_party/pcre-8.38/pcre16_xclass.c b/src/third_party/pcre-8.38/pcre16_xclass.c deleted file mode 100644 index 5aac2a36c68..00000000000 --- a/src/third_party/pcre-8.38/pcre16_xclass.c +++ /dev/null @@ -1,45 +0,0 @@ -/************************************************* -* Perl-Compatible Regular Expressions * -*************************************************/ - -/* PCRE is a library of functions to support regular expressions whose syntax -and semantics are as close as possible to those of the Perl 5 language. - - Written by Philip Hazel - Copyright (c) 1997-2012 University of Cambridge - ------------------------------------------------------------------------------ -Redistribution and use in source and binary forms, with or without -modification, are permitted provided that the following conditions are met: - - * Redistributions of source code must retain the above copyright notice, - this list of conditions and the following disclaimer. - - * Redistributions in binary form must reproduce the above copyright - notice, this list of conditions and the following disclaimer in the - documentation and/or other materials provided with the distribution. - - * Neither the name of the University of Cambridge nor the names of its - contributors may be used to endorse or promote products derived from - this software without specific prior written permission. - -THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS" -AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE -IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE -ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR CONTRIBUTORS BE -LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR -CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF -SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS -INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN -CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) -ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE -POSSIBILITY OF SUCH DAMAGE. ------------------------------------------------------------------------------ -*/ - -/* Generate code with 16 bit character support. */ -#define COMPILE_PCRE16 - -#include "pcre_xclass.c" - -/* End of pcre16_xclass.c */ diff --git a/src/third_party/pcre-8.38/pcre32_byte_order.c b/src/third_party/pcre-8.38/pcre32_byte_order.c deleted file mode 100644 index 9cf5362730a..00000000000 --- a/src/third_party/pcre-8.38/pcre32_byte_order.c +++ /dev/null @@ -1,45 +0,0 @@ -/************************************************* -* Perl-Compatible Regular Expressions * -*************************************************/ - -/* PCRE is a library of functions to support regular expressions whose syntax -and semantics are as close as possible to those of the Perl 5 language. - - Written by Philip Hazel - Copyright (c) 1997-2012 University of Cambridge - ------------------------------------------------------------------------------ -Redistribution and use in source and binary forms, with or without -modification, are permitted provided that the following conditions are met: - - * Redistributions of source code must retain the above copyright notice, - this list of conditions and the following disclaimer. - - * Redistributions in binary form must reproduce the above copyright - notice, this list of conditions and the following disclaimer in the - documentation and/or other materials provided with the distribution. - - * Neither the name of the University of Cambridge nor the names of its - contributors may be used to endorse or promote products derived from - this software without specific prior written permission. - -THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS" -AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE -IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE -ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR CONTRIBUTORS BE -LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR -CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF -SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS -INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN -CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) -ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE -POSSIBILITY OF SUCH DAMAGE. ------------------------------------------------------------------------------ -*/ - -/* Generate code with 32 bit character support. */ -#define COMPILE_PCRE32 - -#include "pcre_byte_order.c" - -/* End of pcre32_byte_order.c */ diff --git a/src/third_party/pcre-8.38/pcre32_chartables.c b/src/third_party/pcre-8.38/pcre32_chartables.c deleted file mode 100644 index b5d8c23dbf1..00000000000 --- a/src/third_party/pcre-8.38/pcre32_chartables.c +++ /dev/null @@ -1,45 +0,0 @@ -/************************************************* -* Perl-Compatible Regular Expressions * -*************************************************/ - -/* PCRE is a library of functions to support regular expressions whose syntax -and semantics are as close as possible to those of the Perl 5 language. - - Written by Philip Hazel - Copyright (c) 1997-2012 University of Cambridge - ------------------------------------------------------------------------------ -Redistribution and use in source and binary forms, with or without -modification, are permitted provided that the following conditions are met: - - * Redistributions of source code must retain the above copyright notice, - this list of conditions and the following disclaimer. - - * Redistributions in binary form must reproduce the above copyright - notice, this list of conditions and the following disclaimer in the - documentation and/or other materials provided with the distribution. - - * Neither the name of the University of Cambridge nor the names of its - contributors may be used to endorse or promote products derived from - this software without specific prior written permission. - -THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS" -AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE -IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE -ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR CONTRIBUTORS BE -LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR -CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF -SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS -INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN -CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) -ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE -POSSIBILITY OF SUCH DAMAGE. ------------------------------------------------------------------------------ -*/ - -/* Generate code with 32 bit character support. */ -#define COMPILE_PCRE32 - -#include "pcre_chartables.c" - -/* End of pcre32_chartables.c */ diff --git a/src/third_party/pcre-8.38/pcre32_compile.c b/src/third_party/pcre-8.38/pcre32_compile.c deleted file mode 100644 index d781eb377e0..00000000000 --- a/src/third_party/pcre-8.38/pcre32_compile.c +++ /dev/null @@ -1,45 +0,0 @@ -/************************************************* -* Perl-Compatible Regular Expressions * -*************************************************/ - -/* PCRE is a library of functions to support regular expressions whose syntax -and semantics are as close as possible to those of the Perl 5 language. - - Written by Philip Hazel - Copyright (c) 1997-2012 University of Cambridge - ------------------------------------------------------------------------------ -Redistribution and use in source and binary forms, with or without -modification, are permitted provided that the following conditions are met: - - * Redistributions of source code must retain the above copyright notice, - this list of conditions and the following disclaimer. - - * Redistributions in binary form must reproduce the above copyright - notice, this list of conditions and the following disclaimer in the - documentation and/or other materials provided with the distribution. - - * Neither the name of the University of Cambridge nor the names of its - contributors may be used to endorse or promote products derived from - this software without specific prior written permission. - -THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS" -AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE -IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE -ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR CONTRIBUTORS BE -LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR -CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF -SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS -INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN -CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) -ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE -POSSIBILITY OF SUCH DAMAGE. ------------------------------------------------------------------------------ -*/ - -/* Generate code with 32 bit character support. */ -#define COMPILE_PCRE32 - -#include "pcre_compile.c" - -/* End of pcre32_compile.c */ diff --git a/src/third_party/pcre-8.38/pcre32_config.c b/src/third_party/pcre-8.38/pcre32_config.c deleted file mode 100644 index d63f3e9ea23..00000000000 --- a/src/third_party/pcre-8.38/pcre32_config.c +++ /dev/null @@ -1,45 +0,0 @@ -/************************************************* -* Perl-Compatible Regular Expressions * -*************************************************/ - -/* PCRE is a library of functions to support regular expressions whose syntax -and semantics are as close as possible to those of the Perl 5 language. - - Written by Philip Hazel - Copyright (c) 1997-2012 University of Cambridge - ------------------------------------------------------------------------------ -Redistribution and use in source and binary forms, with or without -modification, are permitted provided that the following conditions are met: - - * Redistributions of source code must retain the above copyright notice, - this list of conditions and the following disclaimer. - - * Redistributions in binary form must reproduce the above copyright - notice, this list of conditions and the following disclaimer in the - documentation and/or other materials provided with the distribution. - - * Neither the name of the University of Cambridge nor the names of its - contributors may be used to endorse or promote products derived from - this software without specific prior written permission. - -THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS" -AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE -IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE -ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR CONTRIBUTORS BE -LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR -CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF -SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS -INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN -CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) -ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE -POSSIBILITY OF SUCH DAMAGE. ------------------------------------------------------------------------------ -*/ - -/* Generate code with 32 bit character support. */ -#define COMPILE_PCRE32 - -#include "pcre_config.c" - -/* End of pcre32_config.c */ diff --git a/src/third_party/pcre-8.38/pcre32_dfa_exec.c b/src/third_party/pcre-8.38/pcre32_dfa_exec.c deleted file mode 100644 index b0bfd34f04d..00000000000 --- a/src/third_party/pcre-8.38/pcre32_dfa_exec.c +++ /dev/null @@ -1,45 +0,0 @@ -/************************************************* -* Perl-Compatible Regular Expressions * -*************************************************/ - -/* PCRE is a library of functions to support regular expressions whose syntax -and semantics are as close as possible to those of the Perl 5 language. - - Written by Philip Hazel - Copyright (c) 1997-2012 University of Cambridge - ------------------------------------------------------------------------------ -Redistribution and use in source and binary forms, with or without -modification, are permitted provided that the following conditions are met: - - * Redistributions of source code must retain the above copyright notice, - this list of conditions and the following disclaimer. - - * Redistributions in binary form must reproduce the above copyright - notice, this list of conditions and the following disclaimer in the - documentation and/or other materials provided with the distribution. - - * Neither the name of the University of Cambridge nor the names of its - contributors may be used to endorse or promote products derived from - this software without specific prior written permission. - -THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS" -AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE -IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE -ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR CONTRIBUTORS BE -LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR -CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF -SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS -INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN -CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) -ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE -POSSIBILITY OF SUCH DAMAGE. ------------------------------------------------------------------------------ -*/ - -/* Generate code with 32 bit character support. */ -#define COMPILE_PCRE32 - -#include "pcre_dfa_exec.c" - -/* End of pcre32_dfa_exec.c */ diff --git a/src/third_party/pcre-8.38/pcre32_exec.c b/src/third_party/pcre-8.38/pcre32_exec.c deleted file mode 100644 index 8170ed77d35..00000000000 --- a/src/third_party/pcre-8.38/pcre32_exec.c +++ /dev/null @@ -1,45 +0,0 @@ -/************************************************* -* Perl-Compatible Regular Expressions * -*************************************************/ - -/* PCRE is a library of functions to support regular expressions whose syntax -and semantics are as close as possible to those of the Perl 5 language. - - Written by Philip Hazel - Copyright (c) 1997-2012 University of Cambridge - ------------------------------------------------------------------------------ -Redistribution and use in source and binary forms, with or without -modification, are permitted provided that the following conditions are met: - - * Redistributions of source code must retain the above copyright notice, - this list of conditions and the following disclaimer. - - * Redistributions in binary form must reproduce the above copyright - notice, this list of conditions and the following disclaimer in the - documentation and/or other materials provided with the distribution. - - * Neither the name of the University of Cambridge nor the names of its - contributors may be used to endorse or promote products derived from - this software without specific prior written permission. - -THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS" -AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE -IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE -ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR CONTRIBUTORS BE -LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR -CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF -SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS -INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN -CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) -ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE -POSSIBILITY OF SUCH DAMAGE. ------------------------------------------------------------------------------ -*/ - -/* Generate code with 32 bit character support. */ -#define COMPILE_PCRE32 - -#include "pcre_exec.c" - -/* End of pcre32_exec.c */ diff --git a/src/third_party/pcre-8.38/pcre32_fullinfo.c b/src/third_party/pcre-8.38/pcre32_fullinfo.c deleted file mode 100644 index 6ecc5209a08..00000000000 --- a/src/third_party/pcre-8.38/pcre32_fullinfo.c +++ /dev/null @@ -1,45 +0,0 @@ -/************************************************* -* Perl-Compatible Regular Expressions * -*************************************************/ - -/* PCRE is a library of functions to support regular expressions whose syntax -and semantics are as close as possible to those of the Perl 5 language. - - Written by Philip Hazel - Copyright (c) 1997-2012 University of Cambridge - ------------------------------------------------------------------------------ -Redistribution and use in source and binary forms, with or without -modification, are permitted provided that the following conditions are met: - - * Redistributions of source code must retain the above copyright notice, - this list of conditions and the following disclaimer. - - * Redistributions in binary form must reproduce the above copyright - notice, this list of conditions and the following disclaimer in the - documentation and/or other materials provided with the distribution. - - * Neither the name of the University of Cambridge nor the names of its - contributors may be used to endorse or promote products derived from - this software without specific prior written permission. - -THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS" -AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE -IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE -ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR CONTRIBUTORS BE -LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR -CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF -SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS -INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN -CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) -ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE -POSSIBILITY OF SUCH DAMAGE. ------------------------------------------------------------------------------ -*/ - -/* Generate code with 32 bit character support. */ -#define COMPILE_PCRE32 - -#include "pcre_fullinfo.c" - -/* End of pcre32_fullinfo.c */ diff --git a/src/third_party/pcre-8.38/pcre32_get.c b/src/third_party/pcre-8.38/pcre32_get.c deleted file mode 100644 index d35deee0cd4..00000000000 --- a/src/third_party/pcre-8.38/pcre32_get.c +++ /dev/null @@ -1,45 +0,0 @@ -/************************************************* -* Perl-Compatible Regular Expressions * -*************************************************/ - -/* PCRE is a library of functions to support regular expressions whose syntax -and semantics are as close as possible to those of the Perl 5 language. - - Written by Philip Hazel - Copyright (c) 1997-2012 University of Cambridge - ------------------------------------------------------------------------------ -Redistribution and use in source and binary forms, with or without -modification, are permitted provided that the following conditions are met: - - * Redistributions of source code must retain the above copyright notice, - this list of conditions and the following disclaimer. - - * Redistributions in binary form must reproduce the above copyright - notice, this list of conditions and the following disclaimer in the - documentation and/or other materials provided with the distribution. - - * Neither the name of the University of Cambridge nor the names of its - contributors may be used to endorse or promote products derived from - this software without specific prior written permission. - -THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS" -AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE -IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE -ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR CONTRIBUTORS BE -LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR -CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF -SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS -INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN -CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) -ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE -POSSIBILITY OF SUCH DAMAGE. ------------------------------------------------------------------------------ -*/ - -/* Generate code with 32 bit character support. */ -#define COMPILE_PCRE32 - -#include "pcre_get.c" - -/* End of pcre32_get.c */ diff --git a/src/third_party/pcre-8.38/pcre32_globals.c b/src/third_party/pcre-8.38/pcre32_globals.c deleted file mode 100644 index 32e0914ca6d..00000000000 --- a/src/third_party/pcre-8.38/pcre32_globals.c +++ /dev/null @@ -1,45 +0,0 @@ -/************************************************* -* Perl-Compatible Regular Expressions * -*************************************************/ - -/* PCRE is a library of functions to support regular expressions whose syntax -and semantics are as close as possible to those of the Perl 5 language. - - Written by Philip Hazel - Copyright (c) 1997-2012 University of Cambridge - ------------------------------------------------------------------------------ -Redistribution and use in source and binary forms, with or without -modification, are permitted provided that the following conditions are met: - - * Redistributions of source code must retain the above copyright notice, - this list of conditions and the following disclaimer. - - * Redistributions in binary form must reproduce the above copyright - notice, this list of conditions and the following disclaimer in the - documentation and/or other materials provided with the distribution. - - * Neither the name of the University of Cambridge nor the names of its - contributors may be used to endorse or promote products derived from - this software without specific prior written permission. - -THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS" -AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE -IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE -ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR CONTRIBUTORS BE -LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR -CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF -SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS -INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN -CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) -ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE -POSSIBILITY OF SUCH DAMAGE. ------------------------------------------------------------------------------ -*/ - -/* Generate code with 32 bit character support. */ -#define COMPILE_PCRE32 - -#include "pcre_globals.c" - -/* End of pcre32_globals.c */ diff --git a/src/third_party/pcre-8.38/pcre32_jit_compile.c b/src/third_party/pcre-8.38/pcre32_jit_compile.c deleted file mode 100644 index 2e7c6f97c96..00000000000 --- a/src/third_party/pcre-8.38/pcre32_jit_compile.c +++ /dev/null @@ -1,45 +0,0 @@ -/************************************************* -* Perl-Compatible Regular Expressions * -*************************************************/ - -/* PCRE is a library of functions to support regular expressions whose syntax -and semantics are as close as possible to those of the Perl 5 language. - - Written by Philip Hazel - Copyright (c) 1997-2012 University of Cambridge - ------------------------------------------------------------------------------ -Redistribution and use in source and binary forms, with or without -modification, are permitted provided that the following conditions are met: - - * Redistributions of source code must retain the above copyright notice, - this list of conditions and the following disclaimer. - - * Redistributions in binary form must reproduce the above copyright - notice, this list of conditions and the following disclaimer in the - documentation and/or other materials provided with the distribution. - - * Neither the name of the University of Cambridge nor the names of its - contributors may be used to endorse or promote products derived from - this software without specific prior written permission. - -THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS" -AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE -IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE -ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR CONTRIBUTORS BE -LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR -CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF -SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS -INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN -CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) -ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE -POSSIBILITY OF SUCH DAMAGE. ------------------------------------------------------------------------------ -*/ - -/* Generate code with 32 bit character support. */ -#define COMPILE_PCRE32 - -#include "pcre_jit_compile.c" - -/* End of pcre32_jit_compile.c */ diff --git a/src/third_party/pcre-8.38/pcre32_maketables.c b/src/third_party/pcre-8.38/pcre32_maketables.c deleted file mode 100644 index 5d1b1c64c96..00000000000 --- a/src/third_party/pcre-8.38/pcre32_maketables.c +++ /dev/null @@ -1,45 +0,0 @@ -/************************************************* -* Perl-Compatible Regular Expressions * -*************************************************/ - -/* PCRE is a library of functions to support regular expressions whose syntax -and semantics are as close as possible to those of the Perl 5 language. - - Written by Philip Hazel - Copyright (c) 1997-2012 University of Cambridge - ------------------------------------------------------------------------------ -Redistribution and use in source and binary forms, with or without -modification, are permitted provided that the following conditions are met: - - * Redistributions of source code must retain the above copyright notice, - this list of conditions and the following disclaimer. - - * Redistributions in binary form must reproduce the above copyright - notice, this list of conditions and the following disclaimer in the - documentation and/or other materials provided with the distribution. - - * Neither the name of the University of Cambridge nor the names of its - contributors may be used to endorse or promote products derived from - this software without specific prior written permission. - -THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS" -AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE -IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE -ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR CONTRIBUTORS BE -LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR -CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF -SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS -INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN -CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) -ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE -POSSIBILITY OF SUCH DAMAGE. ------------------------------------------------------------------------------ -*/ - -/* Generate code with 32 bit character support. */ -#define COMPILE_PCRE32 - -#include "pcre_maketables.c" - -/* End of pcre32_maketables.c */ diff --git a/src/third_party/pcre-8.38/pcre32_newline.c b/src/third_party/pcre-8.38/pcre32_newline.c deleted file mode 100644 index 7f8d5360cdc..00000000000 --- a/src/third_party/pcre-8.38/pcre32_newline.c +++ /dev/null @@ -1,45 +0,0 @@ -/************************************************* -* Perl-Compatible Regular Expressions * -*************************************************/ - -/* PCRE is a library of functions to support regular expressions whose syntax -and semantics are as close as possible to those of the Perl 5 language. - - Written by Philip Hazel - Copyright (c) 1997-2012 University of Cambridge - ------------------------------------------------------------------------------ -Redistribution and use in source and binary forms, with or without -modification, are permitted provided that the following conditions are met: - - * Redistributions of source code must retain the above copyright notice, - this list of conditions and the following disclaimer. - - * Redistributions in binary form must reproduce the above copyright - notice, this list of conditions and the following disclaimer in the - documentation and/or other materials provided with the distribution. - - * Neither the name of the University of Cambridge nor the names of its - contributors may be used to endorse or promote products derived from - this software without specific prior written permission. - -THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS" -AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE -IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE -ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR CONTRIBUTORS BE -LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR -CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF -SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS -INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN -CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) -ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE -POSSIBILITY OF SUCH DAMAGE. ------------------------------------------------------------------------------ -*/ - -/* Generate code with 32 bit character support. */ -#define COMPILE_PCRE32 - -#include "pcre_newline.c" - -/* End of pcre32_newline.c */ diff --git a/src/third_party/pcre-8.38/pcre32_ord2utf32.c b/src/third_party/pcre-8.38/pcre32_ord2utf32.c deleted file mode 100644 index 606bcb3d7ba..00000000000 --- a/src/third_party/pcre-8.38/pcre32_ord2utf32.c +++ /dev/null @@ -1,82 +0,0 @@ -/************************************************* -* Perl-Compatible Regular Expressions * -*************************************************/ - -/* PCRE is a library of functions to support regular expressions whose syntax -and semantics are as close as possible to those of the Perl 5 language. - - Written by Philip Hazel - Copyright (c) 1997-2012 University of Cambridge - ------------------------------------------------------------------------------ -Redistribution and use in source and binary forms, with or without -modification, are permitted provided that the following conditions are met: - - * Redistributions of source code must retain the above copyright notice, - this list of conditions and the following disclaimer. - - * Redistributions in binary form must reproduce the above copyright - notice, this list of conditions and the following disclaimer in the - documentation and/or other materials provided with the distribution. - - * Neither the name of the University of Cambridge nor the names of its - contributors may be used to endorse or promote products derived from - this software without specific prior written permission. - -THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS" -AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE -IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE -ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR CONTRIBUTORS BE -LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR -CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF -SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS -INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN -CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) -ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE -POSSIBILITY OF SUCH DAMAGE. ------------------------------------------------------------------------------ -*/ - - -/* This file contains a private PCRE function that converts an ordinal -character value into a UTF32 string. */ - -#ifdef HAVE_CONFIG_H -#include "config.h" -#endif - -/* Generate code with 32 bit character support. */ -#define COMPILE_PCRE32 - -#include "pcre_internal.h" - -/************************************************* -* Convert character value to UTF-32 * -*************************************************/ - -/* This function takes an integer value in the range 0 - 0x10ffff -and encodes it as a UTF-32 character in 1 pcre_uchars. - -Arguments: - cvalue the character value - buffer pointer to buffer for result - at least 1 pcre_uchars long - -Returns: number of characters placed in the buffer -*/ - -unsigned int -PRIV(ord2utf)(pcre_uint32 cvalue, pcre_uchar *buffer) -{ -#ifdef SUPPORT_UTF - -*buffer = (pcre_uchar)cvalue; -return 1; - -#else /* SUPPORT_UTF */ -(void)(cvalue); /* Keep compiler happy; this function won't ever be */ -(void)(buffer); /* called when SUPPORT_UTF is not defined. */ -return 0; -#endif /* SUPPORT_UTF */ -} - -/* End of pcre32_ord2utf32.c */ diff --git a/src/third_party/pcre-8.38/pcre32_printint.c b/src/third_party/pcre-8.38/pcre32_printint.c deleted file mode 100644 index f3fd7b25e2c..00000000000 --- a/src/third_party/pcre-8.38/pcre32_printint.c +++ /dev/null @@ -1,45 +0,0 @@ -/************************************************* -* Perl-Compatible Regular Expressions * -*************************************************/ - -/* PCRE is a library of functions to support regular expressions whose syntax -and semantics are as close as possible to those of the Perl 5 language. - - Written by Philip Hazel - Copyright (c) 1997-2012 University of Cambridge - ------------------------------------------------------------------------------ -Redistribution and use in source and binary forms, with or without -modification, are permitted provided that the following conditions are met: - - * Redistributions of source code must retain the above copyright notice, - this list of conditions and the following disclaimer. - - * Redistributions in binary form must reproduce the above copyright - notice, this list of conditions and the following disclaimer in the - documentation and/or other materials provided with the distribution. - - * Neither the name of the University of Cambridge nor the names of its - contributors may be used to endorse or promote products derived from - this software without specific prior written permission. - -THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS" -AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE -IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE -ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR CONTRIBUTORS BE -LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR -CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF -SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS -INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN -CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) -ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE -POSSIBILITY OF SUCH DAMAGE. ------------------------------------------------------------------------------ -*/ - -/* Generate code with 32 bit character support. */ -#define COMPILE_PCRE32 - -#include "pcre_printint.c" - -/* End of pcre32_printint.c */ diff --git a/src/third_party/pcre-8.38/pcre32_refcount.c b/src/third_party/pcre-8.38/pcre32_refcount.c deleted file mode 100644 index dbdf432d82a..00000000000 --- a/src/third_party/pcre-8.38/pcre32_refcount.c +++ /dev/null @@ -1,45 +0,0 @@ -/************************************************* -* Perl-Compatible Regular Expressions * -*************************************************/ - -/* PCRE is a library of functions to support regular expressions whose syntax -and semantics are as close as possible to those of the Perl 5 language. - - Written by Philip Hazel - Copyright (c) 1997-2012 University of Cambridge - ------------------------------------------------------------------------------ -Redistribution and use in source and binary forms, with or without -modification, are permitted provided that the following conditions are met: - - * Redistributions of source code must retain the above copyright notice, - this list of conditions and the following disclaimer. - - * Redistributions in binary form must reproduce the above copyright - notice, this list of conditions and the following disclaimer in the - documentation and/or other materials provided with the distribution. - - * Neither the name of the University of Cambridge nor the names of its - contributors may be used to endorse or promote products derived from - this software without specific prior written permission. - -THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS" -AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE -IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE -ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR CONTRIBUTORS BE -LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR -CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF -SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS -INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN -CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) -ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE -POSSIBILITY OF SUCH DAMAGE. ------------------------------------------------------------------------------ -*/ - -/* Generate code with 32 bit character support. */ -#define COMPILE_PCRE32 - -#include "pcre_refcount.c" - -/* End of pcre32_refcount.c */ diff --git a/src/third_party/pcre-8.38/pcre32_string_utils.c b/src/third_party/pcre-8.38/pcre32_string_utils.c deleted file mode 100644 index e37b3d4805f..00000000000 --- a/src/third_party/pcre-8.38/pcre32_string_utils.c +++ /dev/null @@ -1,45 +0,0 @@ -/************************************************* -* Perl-Compatible Regular Expressions * -*************************************************/ - -/* PCRE is a library of functions to support regular expressions whose syntax -and semantics are as close as possible to those of the Perl 5 language. - - Written by Philip Hazel - Copyright (c) 1997-2012 University of Cambridge - ------------------------------------------------------------------------------ -Redistribution and use in source and binary forms, with or without -modification, are permitted provided that the following conditions are met: - - * Redistributions of source code must retain the above copyright notice, - this list of conditions and the following disclaimer. - - * Redistributions in binary form must reproduce the above copyright - notice, this list of conditions and the following disclaimer in the - documentation and/or other materials provided with the distribution. - - * Neither the name of the University of Cambridge nor the names of its - contributors may be used to endorse or promote products derived from - this software without specific prior written permission. - -THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS" -AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE -IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE -ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR CONTRIBUTORS BE -LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR -CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF -SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS -INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN -CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) -ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE -POSSIBILITY OF SUCH DAMAGE. ------------------------------------------------------------------------------ -*/ - -/* Generate code with 32 bit character support. */ -#define COMPILE_PCRE32 - -#include "pcre_string_utils.c" - -/* End of pcre32_string_utils.c */ diff --git a/src/third_party/pcre-8.38/pcre32_study.c b/src/third_party/pcre-8.38/pcre32_study.c deleted file mode 100644 index d3a3afed791..00000000000 --- a/src/third_party/pcre-8.38/pcre32_study.c +++ /dev/null @@ -1,45 +0,0 @@ -/************************************************* -* Perl-Compatible Regular Expressions * -*************************************************/ - -/* PCRE is a library of functions to support regular expressions whose syntax -and semantics are as close as possible to those of the Perl 5 language. - - Written by Philip Hazel - Copyright (c) 1997-2012 University of Cambridge - ------------------------------------------------------------------------------ -Redistribution and use in source and binary forms, with or without -modification, are permitted provided that the following conditions are met: - - * Redistributions of source code must retain the above copyright notice, - this list of conditions and the following disclaimer. - - * Redistributions in binary form must reproduce the above copyright - notice, this list of conditions and the following disclaimer in the - documentation and/or other materials provided with the distribution. - - * Neither the name of the University of Cambridge nor the names of its - contributors may be used to endorse or promote products derived from - this software without specific prior written permission. - -THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS" -AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE -IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE -ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR CONTRIBUTORS BE -LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR -CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF -SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS -INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN -CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) -ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE -POSSIBILITY OF SUCH DAMAGE. ------------------------------------------------------------------------------ -*/ - -/* Generate code with 32 bit character support. */ -#define COMPILE_PCRE32 - -#include "pcre_study.c" - -/* End of pcre32_study.c */ diff --git a/src/third_party/pcre-8.38/pcre32_tables.c b/src/third_party/pcre-8.38/pcre32_tables.c deleted file mode 100644 index 3d94cca33a1..00000000000 --- a/src/third_party/pcre-8.38/pcre32_tables.c +++ /dev/null @@ -1,45 +0,0 @@ -/************************************************* -* Perl-Compatible Regular Expressions * -*************************************************/ - -/* PCRE is a library of functions to support regular expressions whose syntax -and semantics are as close as possible to those of the Perl 5 language. - - Written by Philip Hazel - Copyright (c) 1997-2012 University of Cambridge - ------------------------------------------------------------------------------ -Redistribution and use in source and binary forms, with or without -modification, are permitted provided that the following conditions are met: - - * Redistributions of source code must retain the above copyright notice, - this list of conditions and the following disclaimer. - - * Redistributions in binary form must reproduce the above copyright - notice, this list of conditions and the following disclaimer in the - documentation and/or other materials provided with the distribution. - - * Neither the name of the University of Cambridge nor the names of its - contributors may be used to endorse or promote products derived from - this software without specific prior written permission. - -THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS" -AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE -IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE -ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR CONTRIBUTORS BE -LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR -CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF -SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS -INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN -CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) -ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE -POSSIBILITY OF SUCH DAMAGE. ------------------------------------------------------------------------------ -*/ - -/* Generate code with 32 bit character support. */ -#define COMPILE_PCRE32 - -#include "pcre_tables.c" - -/* End of pcre32_tables.c */ diff --git a/src/third_party/pcre-8.38/pcre32_ucd.c b/src/third_party/pcre-8.38/pcre32_ucd.c deleted file mode 100644 index befe22d3435..00000000000 --- a/src/third_party/pcre-8.38/pcre32_ucd.c +++ /dev/null @@ -1,45 +0,0 @@ -/************************************************* -* Perl-Compatible Regular Expressions * -*************************************************/ - -/* PCRE is a library of functions to support regular expressions whose syntax -and semantics are as close as possible to those of the Perl 5 language. - - Written by Philip Hazel - Copyright (c) 1997-2012 University of Cambridge - ------------------------------------------------------------------------------ -Redistribution and use in source and binary forms, with or without -modification, are permitted provided that the following conditions are met: - - * Redistributions of source code must retain the above copyright notice, - this list of conditions and the following disclaimer. - - * Redistributions in binary form must reproduce the above copyright - notice, this list of conditions and the following disclaimer in the - documentation and/or other materials provided with the distribution. - - * Neither the name of the University of Cambridge nor the names of its - contributors may be used to endorse or promote products derived from - this software without specific prior written permission. - -THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS" -AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE -IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE -ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR CONTRIBUTORS BE -LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR -CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF -SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS -INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN -CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) -ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE -POSSIBILITY OF SUCH DAMAGE. ------------------------------------------------------------------------------ -*/ - -/* Generate code with 32 bit character support. */ -#define COMPILE_PCRE32 - -#include "pcre_ucd.c" - -/* End of pcre32_ucd.c */ diff --git a/src/third_party/pcre-8.38/pcre32_utf32_utils.c b/src/third_party/pcre-8.38/pcre32_utf32_utils.c deleted file mode 100644 index f844e237165..00000000000 --- a/src/third_party/pcre-8.38/pcre32_utf32_utils.c +++ /dev/null @@ -1,141 +0,0 @@ -/************************************************* -* Perl-Compatible Regular Expressions * -*************************************************/ - -/* PCRE is a library of functions to support regular expressions whose syntax -and semantics are as close as possible to those of the Perl 5 language. - - Written by Philip Hazel - Copyright (c) 1997-2012 University of Cambridge - ------------------------------------------------------------------------------ -Redistribution and use in source and binary forms, with or without -modification, are permitted provided that the following conditions are met: - - * Redistributions of source code must retain the above copyright notice, - this list of conditions and the following disclaimer. - - * Redistributions in binary form must reproduce the above copyright - notice, this list of conditions and the following disclaimer in the - documentation and/or other materials provided with the distribution. - - * Neither the name of the University of Cambridge nor the names of its - contributors may be used to endorse or promote products derived from - this software without specific prior written permission. - -THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS" -AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE -IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE -ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR CONTRIBUTORS BE -LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR -CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF -SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS -INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN -CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) -ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE -POSSIBILITY OF SUCH DAMAGE. ------------------------------------------------------------------------------ -*/ - - -/* This module contains a function for converting any UTF-32 character -strings to host byte order. */ - - -#ifdef HAVE_CONFIG_H -#include "config.h" -#endif - -/* Generate code with 32 bit character support. */ -#define COMPILE_PCRE32 - -#include "pcre_internal.h" - -#ifdef SUPPORT_UTF -static pcre_uint32 -swap_uint32(pcre_uint32 value) -{ -return ((value & 0x000000ff) << 24) | - ((value & 0x0000ff00) << 8) | - ((value & 0x00ff0000) >> 8) | - (value >> 24); -} -#endif - - -/************************************************* -* Convert any UTF-32 string to host byte order * -*************************************************/ - -/* This function takes an UTF-32 string and converts -it to host byte order. The length can be explicitly set, -or automatically detected for zero terminated strings. -BOMs can be kept or discarded during the conversion. -Conversion can be done in place (output == input). - -Arguments: - output the output buffer, its size must be greater - or equal than the input string - input any UTF-32 string - length the number of 32-bit units in the input string - can be less than zero for zero terminated strings - host_byte_order - A non-zero value means the input is in host byte - order, which can be dynamically changed by BOMs later. - Initially it contains the starting byte order and returns - with the last byte order so it can be used for stream - processing. It can be NULL, which set the host byte - order mode by default. - keep_boms for a non-zero value, the BOM (0xfeff) characters - are copied as well - -Returns: the number of 32-bit units placed into the output buffer, - including the zero-terminator -*/ - -int -pcre32_utf32_to_host_byte_order(PCRE_UCHAR32 *output, PCRE_SPTR32 input, - int length, int *host_byte_order, int keep_boms) -{ -#ifdef SUPPORT_UTF -/* This function converts any UTF-32 string to host byte order and optionally -removes any Byte Order Marks (BOMS). Returns with the remainig length. */ -int host_bo = host_byte_order != NULL ? *host_byte_order : 1; -pcre_uchar *optr = (pcre_uchar *)output; -const pcre_uchar *iptr = (const pcre_uchar *)input; -const pcre_uchar *end; -/* The c variable must be unsigned. */ -register pcre_uchar c; - -if (length < 0) - end = iptr + STRLEN_UC(iptr) + 1; -else - end = iptr + length; - -while (iptr < end) - { - c = *iptr++; - if (c == 0x0000feffu || c == 0xfffe0000u) - { - /* Detecting the byte order of the machine is unnecessary, it is - enough to know that the UTF-32 string has the same byte order or not. */ - host_bo = c == 0x0000feffu; - if (keep_boms != 0) - *optr++ = 0x0000feffu; - } - else - *optr++ = host_bo ? c : swap_uint32(c); - } -if (host_byte_order != NULL) - *host_byte_order = host_bo; - -#else /* SUPPORT_UTF */ -(void)(output); /* Keep picky compilers happy */ -(void)(input); -(void)(keep_boms); -(void)(host_byte_order); -#endif /* SUPPORT_UTF */ -return length; -} - -/* End of pcre32_utf32_utils.c */ diff --git a/src/third_party/pcre-8.38/pcre32_valid_utf32.c b/src/third_party/pcre-8.38/pcre32_valid_utf32.c deleted file mode 100644 index 94cda1a2c4c..00000000000 --- a/src/third_party/pcre-8.38/pcre32_valid_utf32.c +++ /dev/null @@ -1,124 +0,0 @@ -/************************************************* -* Perl-Compatible Regular Expressions * -*************************************************/ - -/* PCRE is a library of functions to support regular expressions whose syntax -and semantics are as close as possible to those of the Perl 5 language. - - Written by Philip Hazel - Copyright (c) 1997-2013 University of Cambridge - ------------------------------------------------------------------------------ -Redistribution and use in source and binary forms, with or without -modification, are permitted provided that the following conditions are met: - - * Redistributions of source code must retain the above copyright notice, - this list of conditions and the following disclaimer. - - * Redistributions in binary form must reproduce the above copyright - notice, this list of conditions and the following disclaimer in the - documentation and/or other materials provided with the distribution. - - * Neither the name of the University of Cambridge nor the names of its - contributors may be used to endorse or promote products derived from - this software without specific prior written permission. - -THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS" -AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE -IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE -ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR CONTRIBUTORS BE -LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR -CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF -SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS -INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN -CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) -ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE -POSSIBILITY OF SUCH DAMAGE. ------------------------------------------------------------------------------ -*/ - - -/* This module contains an internal function for validating UTF-32 character -strings. */ - - -#ifdef HAVE_CONFIG_H -#include "config.h" -#endif - -/* Generate code with 32 bit character support. */ -#define COMPILE_PCRE32 - -#include "pcre_internal.h" - -/************************************************* -* Validate a UTF-32 string * -*************************************************/ - -/* This function is called (optionally) at the start of compile or match, to -check that a supposed UTF-32 string is actually valid. The early check means -that subsequent code can assume it is dealing with a valid string. The check -can be turned off for maximum performance, but the consequences of supplying an -invalid string are then undefined. - -More information about the details of the error are passed -back in the returned value: - -PCRE_UTF32_ERR0 No error -PCRE_UTF32_ERR1 Surrogate character -PCRE_UTF32_ERR2 Unused (was non-character) -PCRE_UTF32_ERR3 Character > 0x10ffff - -Arguments: - string points to the string - length length of string, or -1 if the string is zero-terminated - errp pointer to an error position offset variable - -Returns: = 0 if the string is a valid UTF-32 string - > 0 otherwise, setting the offset of the bad character -*/ - -int -PRIV(valid_utf)(PCRE_PUCHAR string, int length, int *erroroffset) -{ -#ifdef SUPPORT_UTF -register PCRE_PUCHAR p; -register pcre_uchar c; - -if (length < 0) - { - for (p = string; *p != 0; p++); - length = p - string; - } - -for (p = string; length-- > 0; p++) - { - c = *p; - - if ((c & 0xfffff800u) != 0xd800u) - { - /* Normal UTF-32 code point. Neither high nor low surrogate. */ - if (c > 0x10ffffu) - { - *erroroffset = p - string; - return PCRE_UTF32_ERR3; - } - } - else - { - /* A surrogate */ - *erroroffset = p - string; - return PCRE_UTF32_ERR1; - } - } - -#else /* SUPPORT_UTF */ -(void)(string); /* Keep picky compilers happy */ -(void)(length); -(void)(erroroffset); -#endif /* SUPPORT_UTF */ - -return PCRE_UTF32_ERR0; /* This indicates success */ -} - -/* End of pcre32_valid_utf32.c */ diff --git a/src/third_party/pcre-8.38/pcre32_version.c b/src/third_party/pcre-8.38/pcre32_version.c deleted file mode 100644 index fdaad9b0859..00000000000 --- a/src/third_party/pcre-8.38/pcre32_version.c +++ /dev/null @@ -1,45 +0,0 @@ -/************************************************* -* Perl-Compatible Regular Expressions * -*************************************************/ - -/* PCRE is a library of functions to support regular expressions whose syntax -and semantics are as close as possible to those of the Perl 5 language. - - Written by Philip Hazel - Copyright (c) 1997-2012 University of Cambridge - ------------------------------------------------------------------------------ -Redistribution and use in source and binary forms, with or without -modification, are permitted provided that the following conditions are met: - - * Redistributions of source code must retain the above copyright notice, - this list of conditions and the following disclaimer. - - * Redistributions in binary form must reproduce the above copyright - notice, this list of conditions and the following disclaimer in the - documentation and/or other materials provided with the distribution. - - * Neither the name of the University of Cambridge nor the names of its - contributors may be used to endorse or promote products derived from - this software without specific prior written permission. - -THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS" -AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE -IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE -ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR CONTRIBUTORS BE -LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR -CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF -SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS -INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN -CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) -ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE -POSSIBILITY OF SUCH DAMAGE. ------------------------------------------------------------------------------ -*/ - -/* Generate code with 32 bit character support. */ -#define COMPILE_PCRE32 - -#include "pcre_version.c" - -/* End of pcre32_version.c */ diff --git a/src/third_party/pcre-8.38/pcre32_xclass.c b/src/third_party/pcre-8.38/pcre32_xclass.c deleted file mode 100644 index 5662408ad5f..00000000000 --- a/src/third_party/pcre-8.38/pcre32_xclass.c +++ /dev/null @@ -1,45 +0,0 @@ -/************************************************* -* Perl-Compatible Regular Expressions * -*************************************************/ - -/* PCRE is a library of functions to support regular expressions whose syntax -and semantics are as close as possible to those of the Perl 5 language. - - Written by Philip Hazel - Copyright (c) 1997-2012 University of Cambridge - ------------------------------------------------------------------------------ -Redistribution and use in source and binary forms, with or without -modification, are permitted provided that the following conditions are met: - - * Redistributions of source code must retain the above copyright notice, - this list of conditions and the following disclaimer. - - * Redistributions in binary form must reproduce the above copyright - notice, this list of conditions and the following disclaimer in the - documentation and/or other materials provided with the distribution. - - * Neither the name of the University of Cambridge nor the names of its - contributors may be used to endorse or promote products derived from - this software without specific prior written permission. - -THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS" -AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE -IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE -ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR CONTRIBUTORS BE -LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR -CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF -SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS -INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN -CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) -ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE -POSSIBILITY OF SUCH DAMAGE. ------------------------------------------------------------------------------ -*/ - -/* Generate code with 32 bit character support. */ -#define COMPILE_PCRE32 - -#include "pcre_xclass.c" - -/* End of pcre32_xclass.c */ diff --git a/src/third_party/pcre-8.38/pcre_byte_order.c b/src/third_party/pcre-8.38/pcre_byte_order.c deleted file mode 100644 index cf5f12b04ea..00000000000 --- a/src/third_party/pcre-8.38/pcre_byte_order.c +++ /dev/null @@ -1,319 +0,0 @@ -/************************************************* -* Perl-Compatible Regular Expressions * -*************************************************/ - -/* PCRE is a library of functions to support regular expressions whose syntax -and semantics are as close as possible to those of the Perl 5 language. - - Written by Philip Hazel - Copyright (c) 1997-2014 University of Cambridge - ------------------------------------------------------------------------------ -Redistribution and use in source and binary forms, with or without -modification, are permitted provided that the following conditions are met: - - * Redistributions of source code must retain the above copyright notice, - this list of conditions and the following disclaimer. - - * Redistributions in binary form must reproduce the above copyright - notice, this list of conditions and the following disclaimer in the - documentation and/or other materials provided with the distribution. - - * Neither the name of the University of Cambridge nor the names of its - contributors may be used to endorse or promote products derived from - this software without specific prior written permission. - -THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS" -AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE -IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE -ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR CONTRIBUTORS BE -LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR -CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF -SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS -INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN -CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) -ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE -POSSIBILITY OF SUCH DAMAGE. ------------------------------------------------------------------------------ -*/ - - -/* This module contains an internal function that tests a compiled pattern to -see if it was compiled with the opposite endianness. If so, it uses an -auxiliary local function to flip the appropriate bytes. */ - - -#ifdef HAVE_CONFIG_H -#include "config.h" -#endif - -#include "pcre_internal.h" - - -/************************************************* -* Swap byte functions * -*************************************************/ - -/* The following functions swap the bytes of a pcre_uint16 -and pcre_uint32 value. - -Arguments: - value any number - -Returns: the byte swapped value -*/ - -static pcre_uint32 -swap_uint32(pcre_uint32 value) -{ -return ((value & 0x000000ff) << 24) | - ((value & 0x0000ff00) << 8) | - ((value & 0x00ff0000) >> 8) | - (value >> 24); -} - -static pcre_uint16 -swap_uint16(pcre_uint16 value) -{ -return (value >> 8) | (value << 8); -} - - -/************************************************* -* Test for a byte-flipped compiled regex * -*************************************************/ - -/* This function swaps the bytes of a compiled pattern usually -loaded form the disk. It also sets the tables pointer, which -is likely an invalid pointer after reload. - -Arguments: - argument_re points to the compiled expression - extra_data points to extra data or is NULL - tables points to the character tables or NULL - -Returns: 0 if the swap is successful, negative on error -*/ - -#if defined COMPILE_PCRE8 -PCRE_EXP_DECL int pcre_pattern_to_host_byte_order(pcre *argument_re, - pcre_extra *extra_data, const unsigned char *tables) -#elif defined COMPILE_PCRE16 -PCRE_EXP_DECL int pcre16_pattern_to_host_byte_order(pcre16 *argument_re, - pcre16_extra *extra_data, const unsigned char *tables) -#elif defined COMPILE_PCRE32 -PCRE_EXP_DECL int pcre32_pattern_to_host_byte_order(pcre32 *argument_re, - pcre32_extra *extra_data, const unsigned char *tables) -#endif -{ -REAL_PCRE *re = (REAL_PCRE *)argument_re; -pcre_study_data *study; -#ifndef COMPILE_PCRE8 -pcre_uchar *ptr; -int length; -#if defined SUPPORT_UTF && defined COMPILE_PCRE16 -BOOL utf; -BOOL utf16_char; -#endif /* SUPPORT_UTF && COMPILE_PCRE16 */ -#endif /* !COMPILE_PCRE8 */ - -if (re == NULL) return PCRE_ERROR_NULL; -if (re->magic_number == MAGIC_NUMBER) - { - if ((re->flags & PCRE_MODE) == 0) return PCRE_ERROR_BADMODE; - re->tables = tables; - return 0; - } - -if (re->magic_number != REVERSED_MAGIC_NUMBER) return PCRE_ERROR_BADMAGIC; -if ((swap_uint32(re->flags) & PCRE_MODE) == 0) return PCRE_ERROR_BADMODE; - -re->magic_number = MAGIC_NUMBER; -re->size = swap_uint32(re->size); -re->options = swap_uint32(re->options); -re->flags = swap_uint32(re->flags); -re->limit_match = swap_uint32(re->limit_match); -re->limit_recursion = swap_uint32(re->limit_recursion); - -#if defined COMPILE_PCRE8 || defined COMPILE_PCRE16 -re->first_char = swap_uint16(re->first_char); -re->req_char = swap_uint16(re->req_char); -#elif defined COMPILE_PCRE32 -re->first_char = swap_uint32(re->first_char); -re->req_char = swap_uint32(re->req_char); -#endif - -re->max_lookbehind = swap_uint16(re->max_lookbehind); -re->top_bracket = swap_uint16(re->top_bracket); -re->top_backref = swap_uint16(re->top_backref); -re->name_table_offset = swap_uint16(re->name_table_offset); -re->name_entry_size = swap_uint16(re->name_entry_size); -re->name_count = swap_uint16(re->name_count); -re->ref_count = swap_uint16(re->ref_count); -re->tables = tables; - -if (extra_data != NULL && (extra_data->flags & PCRE_EXTRA_STUDY_DATA) != 0) - { - study = (pcre_study_data *)extra_data->study_data; - study->size = swap_uint32(study->size); - study->flags = swap_uint32(study->flags); - study->minlength = swap_uint32(study->minlength); - } - -#ifndef COMPILE_PCRE8 -ptr = (pcre_uchar *)re + re->name_table_offset; -length = re->name_count * re->name_entry_size; -#if defined SUPPORT_UTF && defined COMPILE_PCRE16 -utf = (re->options & PCRE_UTF16) != 0; -utf16_char = FALSE; -#endif /* SUPPORT_UTF && COMPILE_PCRE16 */ - -while(TRUE) - { - /* Swap previous characters. */ - while (length-- > 0) - { -#if defined COMPILE_PCRE16 - *ptr = swap_uint16(*ptr); -#elif defined COMPILE_PCRE32 - *ptr = swap_uint32(*ptr); -#endif - ptr++; - } -#if defined SUPPORT_UTF && defined COMPILE_PCRE16 - if (utf16_char) - { - if (HAS_EXTRALEN(ptr[-1])) - { - /* We know that there is only one extra character in UTF-16. */ - *ptr = swap_uint16(*ptr); - ptr++; - } - } - utf16_char = FALSE; -#endif /* SUPPORT_UTF */ - - /* Get next opcode. */ - length = 0; -#if defined COMPILE_PCRE16 - *ptr = swap_uint16(*ptr); -#elif defined COMPILE_PCRE32 - *ptr = swap_uint32(*ptr); -#endif - switch (*ptr) - { - case OP_END: - return 0; - -#if defined SUPPORT_UTF && defined COMPILE_PCRE16 - case OP_CHAR: - case OP_CHARI: - case OP_NOT: - case OP_NOTI: - case OP_STAR: - case OP_MINSTAR: - case OP_PLUS: - case OP_MINPLUS: - case OP_QUERY: - case OP_MINQUERY: - case OP_UPTO: - case OP_MINUPTO: - case OP_EXACT: - case OP_POSSTAR: - case OP_POSPLUS: - case OP_POSQUERY: - case OP_POSUPTO: - case OP_STARI: - case OP_MINSTARI: - case OP_PLUSI: - case OP_MINPLUSI: - case OP_QUERYI: - case OP_MINQUERYI: - case OP_UPTOI: - case OP_MINUPTOI: - case OP_EXACTI: - case OP_POSSTARI: - case OP_POSPLUSI: - case OP_POSQUERYI: - case OP_POSUPTOI: - case OP_NOTSTAR: - case OP_NOTMINSTAR: - case OP_NOTPLUS: - case OP_NOTMINPLUS: - case OP_NOTQUERY: - case OP_NOTMINQUERY: - case OP_NOTUPTO: - case OP_NOTMINUPTO: - case OP_NOTEXACT: - case OP_NOTPOSSTAR: - case OP_NOTPOSPLUS: - case OP_NOTPOSQUERY: - case OP_NOTPOSUPTO: - case OP_NOTSTARI: - case OP_NOTMINSTARI: - case OP_NOTPLUSI: - case OP_NOTMINPLUSI: - case OP_NOTQUERYI: - case OP_NOTMINQUERYI: - case OP_NOTUPTOI: - case OP_NOTMINUPTOI: - case OP_NOTEXACTI: - case OP_NOTPOSSTARI: - case OP_NOTPOSPLUSI: - case OP_NOTPOSQUERYI: - case OP_NOTPOSUPTOI: - if (utf) utf16_char = TRUE; -#endif - /* Fall through. */ - - default: - length = PRIV(OP_lengths)[*ptr] - 1; - break; - - case OP_CLASS: - case OP_NCLASS: - /* Skip the character bit map. */ - ptr += 32/sizeof(pcre_uchar); - length = 0; - break; - - case OP_XCLASS: - /* Reverse the size of the XCLASS instance. */ - ptr++; -#if defined COMPILE_PCRE16 - *ptr = swap_uint16(*ptr); -#elif defined COMPILE_PCRE32 - *ptr = swap_uint32(*ptr); -#endif -#ifndef COMPILE_PCRE32 - if (LINK_SIZE > 1) - { - /* LINK_SIZE can be 1 or 2 in 16 bit mode. */ - ptr++; - *ptr = swap_uint16(*ptr); - } -#endif - ptr++; - length = (GET(ptr, -LINK_SIZE)) - (1 + LINK_SIZE + 1); -#if defined COMPILE_PCRE16 - *ptr = swap_uint16(*ptr); -#elif defined COMPILE_PCRE32 - *ptr = swap_uint32(*ptr); -#endif - if ((*ptr & XCL_MAP) != 0) - { - /* Skip the character bit map. */ - ptr += 32/sizeof(pcre_uchar); - length -= 32/sizeof(pcre_uchar); - } - break; - } - ptr++; - } -/* Control should never reach here in 16/32 bit mode. */ -#else /* In 8-bit mode, the pattern does not need to be processed. */ -return 0; -#endif /* !COMPILE_PCRE8 */ -} - -/* End of pcre_byte_order.c */ diff --git a/src/third_party/pcre-8.38/pcre_chartables.c b/src/third_party/pcre-8.38/pcre_chartables.c deleted file mode 100644 index 1e20ec29d05..00000000000 --- a/src/third_party/pcre-8.38/pcre_chartables.c +++ /dev/null @@ -1,198 +0,0 @@ -/************************************************* -* Perl-Compatible Regular Expressions * -*************************************************/ - -/* This file contains character tables that are used when no external tables -are passed to PCRE by the application that calls it. The tables are used only -for characters whose code values are less than 256. - -This is a default version of the tables that assumes ASCII encoding. A program -called dftables (which is distributed with PCRE) can be used to build -alternative versions of this file. This is necessary if you are running in an -EBCDIC environment, or if you want to default to a different encoding, for -example ISO-8859-1. When dftables is run, it creates these tables in the -current locale. If PCRE is configured with --enable-rebuild-chartables, this -happens automatically. - -The following #includes are present because without them gcc 4.x may remove the -array definition from the final binary if PCRE is built into a static library -and dead code stripping is activated. This leads to link errors. Pulling in the -header ensures that the array gets flagged as "someone outside this compilation -unit might reference this" and so it will always be supplied to the linker. */ - -#ifdef HAVE_CONFIG_H -#include "config.h" -#endif - -#include "pcre_internal.h" - -const pcre_uint8 PRIV(default_tables)[] = { - -/* This table is a lower casing table. */ - - 0, 1, 2, 3, 4, 5, 6, 7, - 8, 9, 10, 11, 12, 13, 14, 15, - 16, 17, 18, 19, 20, 21, 22, 23, - 24, 25, 26, 27, 28, 29, 30, 31, - 32, 33, 34, 35, 36, 37, 38, 39, - 40, 41, 42, 43, 44, 45, 46, 47, - 48, 49, 50, 51, 52, 53, 54, 55, - 56, 57, 58, 59, 60, 61, 62, 63, - 64, 97, 98, 99,100,101,102,103, - 104,105,106,107,108,109,110,111, - 112,113,114,115,116,117,118,119, - 120,121,122, 91, 92, 93, 94, 95, - 96, 97, 98, 99,100,101,102,103, - 104,105,106,107,108,109,110,111, - 112,113,114,115,116,117,118,119, - 120,121,122,123,124,125,126,127, - 128,129,130,131,132,133,134,135, - 136,137,138,139,140,141,142,143, - 144,145,146,147,148,149,150,151, - 152,153,154,155,156,157,158,159, - 160,161,162,163,164,165,166,167, - 168,169,170,171,172,173,174,175, - 176,177,178,179,180,181,182,183, - 184,185,186,187,188,189,190,191, - 192,193,194,195,196,197,198,199, - 200,201,202,203,204,205,206,207, - 208,209,210,211,212,213,214,215, - 216,217,218,219,220,221,222,223, - 224,225,226,227,228,229,230,231, - 232,233,234,235,236,237,238,239, - 240,241,242,243,244,245,246,247, - 248,249,250,251,252,253,254,255, - -/* This table is a case flipping table. */ - - 0, 1, 2, 3, 4, 5, 6, 7, - 8, 9, 10, 11, 12, 13, 14, 15, - 16, 17, 18, 19, 20, 21, 22, 23, - 24, 25, 26, 27, 28, 29, 30, 31, - 32, 33, 34, 35, 36, 37, 38, 39, - 40, 41, 42, 43, 44, 45, 46, 47, - 48, 49, 50, 51, 52, 53, 54, 55, - 56, 57, 58, 59, 60, 61, 62, 63, - 64, 97, 98, 99,100,101,102,103, - 104,105,106,107,108,109,110,111, - 112,113,114,115,116,117,118,119, - 120,121,122, 91, 92, 93, 94, 95, - 96, 65, 66, 67, 68, 69, 70, 71, - 72, 73, 74, 75, 76, 77, 78, 79, - 80, 81, 82, 83, 84, 85, 86, 87, - 88, 89, 90,123,124,125,126,127, - 128,129,130,131,132,133,134,135, - 136,137,138,139,140,141,142,143, - 144,145,146,147,148,149,150,151, - 152,153,154,155,156,157,158,159, - 160,161,162,163,164,165,166,167, - 168,169,170,171,172,173,174,175, - 176,177,178,179,180,181,182,183, - 184,185,186,187,188,189,190,191, - 192,193,194,195,196,197,198,199, - 200,201,202,203,204,205,206,207, - 208,209,210,211,212,213,214,215, - 216,217,218,219,220,221,222,223, - 224,225,226,227,228,229,230,231, - 232,233,234,235,236,237,238,239, - 240,241,242,243,244,245,246,247, - 248,249,250,251,252,253,254,255, - -/* This table contains bit maps for various character classes. Each map is 32 -bytes long and the bits run from the least significant end of each byte. The -classes that have their own maps are: space, xdigit, digit, upper, lower, word, -graph, print, punct, and cntrl. Other classes are built from combinations. */ - - 0x00,0x3e,0x00,0x00,0x01,0x00,0x00,0x00, - 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, - 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, - 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, - - 0x00,0x00,0x00,0x00,0x00,0x00,0xff,0x03, - 0x7e,0x00,0x00,0x00,0x7e,0x00,0x00,0x00, - 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, - 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, - - 0x00,0x00,0x00,0x00,0x00,0x00,0xff,0x03, - 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, - 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, - 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, - - 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, - 0xfe,0xff,0xff,0x07,0x00,0x00,0x00,0x00, - 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, - 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, - - 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, - 0x00,0x00,0x00,0x00,0xfe,0xff,0xff,0x07, - 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, - 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, - - 0x00,0x00,0x00,0x00,0x00,0x00,0xff,0x03, - 0xfe,0xff,0xff,0x87,0xfe,0xff,0xff,0x07, - 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, - 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, - - 0x00,0x00,0x00,0x00,0xfe,0xff,0xff,0xff, - 0xff,0xff,0xff,0xff,0xff,0xff,0xff,0x7f, - 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, - 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, - - 0x00,0x00,0x00,0x00,0xff,0xff,0xff,0xff, - 0xff,0xff,0xff,0xff,0xff,0xff,0xff,0x7f, - 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, - 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, - - 0x00,0x00,0x00,0x00,0xfe,0xff,0x00,0xfc, - 0x01,0x00,0x00,0xf8,0x01,0x00,0x00,0x78, - 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, - 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, - - 0xff,0xff,0xff,0xff,0x00,0x00,0x00,0x00, - 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x80, - 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, - 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, - -/* This table identifies various classes of character by individual bits: - 0x01 white space character - 0x02 letter - 0x04 decimal digit - 0x08 hexadecimal digit - 0x10 alphanumeric or '_' - 0x80 regular expression metacharacter or binary zero -*/ - - 0x80,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /* 0- 7 */ - 0x00,0x01,0x01,0x01,0x01,0x01,0x00,0x00, /* 8- 15 */ - 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /* 16- 23 */ - 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /* 24- 31 */ - 0x01,0x00,0x00,0x00,0x80,0x00,0x00,0x00, /* - ' */ - 0x80,0x80,0x80,0x80,0x00,0x00,0x80,0x00, /* ( - / */ - 0x1c,0x1c,0x1c,0x1c,0x1c,0x1c,0x1c,0x1c, /* 0 - 7 */ - 0x1c,0x1c,0x00,0x00,0x00,0x00,0x00,0x80, /* 8 - ? */ - 0x00,0x1a,0x1a,0x1a,0x1a,0x1a,0x1a,0x12, /* @ - G */ - 0x12,0x12,0x12,0x12,0x12,0x12,0x12,0x12, /* H - O */ - 0x12,0x12,0x12,0x12,0x12,0x12,0x12,0x12, /* P - W */ - 0x12,0x12,0x12,0x80,0x80,0x00,0x80,0x10, /* X - _ */ - 0x00,0x1a,0x1a,0x1a,0x1a,0x1a,0x1a,0x12, /* ` - g */ - 0x12,0x12,0x12,0x12,0x12,0x12,0x12,0x12, /* h - o */ - 0x12,0x12,0x12,0x12,0x12,0x12,0x12,0x12, /* p - w */ - 0x12,0x12,0x12,0x80,0x80,0x00,0x00,0x00, /* x -127 */ - 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /* 128-135 */ - 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /* 136-143 */ - 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /* 144-151 */ - 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /* 152-159 */ - 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /* 160-167 */ - 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /* 168-175 */ - 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /* 176-183 */ - 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /* 184-191 */ - 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /* 192-199 */ - 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /* 200-207 */ - 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /* 208-215 */ - 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /* 216-223 */ - 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /* 224-231 */ - 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /* 232-239 */ - 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /* 240-247 */ - 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00};/* 248-255 */ - -/* End of pcre_chartables.c */ diff --git a/src/third_party/pcre-8.38/pcre_chartables.c.dist b/src/third_party/pcre-8.38/pcre_chartables.c.dist deleted file mode 100644 index 1e20ec29d05..00000000000 --- a/src/third_party/pcre-8.38/pcre_chartables.c.dist +++ /dev/null @@ -1,198 +0,0 @@ -/************************************************* -* Perl-Compatible Regular Expressions * -*************************************************/ - -/* This file contains character tables that are used when no external tables -are passed to PCRE by the application that calls it. The tables are used only -for characters whose code values are less than 256. - -This is a default version of the tables that assumes ASCII encoding. A program -called dftables (which is distributed with PCRE) can be used to build -alternative versions of this file. This is necessary if you are running in an -EBCDIC environment, or if you want to default to a different encoding, for -example ISO-8859-1. When dftables is run, it creates these tables in the -current locale. If PCRE is configured with --enable-rebuild-chartables, this -happens automatically. - -The following #includes are present because without them gcc 4.x may remove the -array definition from the final binary if PCRE is built into a static library -and dead code stripping is activated. This leads to link errors. Pulling in the -header ensures that the array gets flagged as "someone outside this compilation -unit might reference this" and so it will always be supplied to the linker. */ - -#ifdef HAVE_CONFIG_H -#include "config.h" -#endif - -#include "pcre_internal.h" - -const pcre_uint8 PRIV(default_tables)[] = { - -/* This table is a lower casing table. */ - - 0, 1, 2, 3, 4, 5, 6, 7, - 8, 9, 10, 11, 12, 13, 14, 15, - 16, 17, 18, 19, 20, 21, 22, 23, - 24, 25, 26, 27, 28, 29, 30, 31, - 32, 33, 34, 35, 36, 37, 38, 39, - 40, 41, 42, 43, 44, 45, 46, 47, - 48, 49, 50, 51, 52, 53, 54, 55, - 56, 57, 58, 59, 60, 61, 62, 63, - 64, 97, 98, 99,100,101,102,103, - 104,105,106,107,108,109,110,111, - 112,113,114,115,116,117,118,119, - 120,121,122, 91, 92, 93, 94, 95, - 96, 97, 98, 99,100,101,102,103, - 104,105,106,107,108,109,110,111, - 112,113,114,115,116,117,118,119, - 120,121,122,123,124,125,126,127, - 128,129,130,131,132,133,134,135, - 136,137,138,139,140,141,142,143, - 144,145,146,147,148,149,150,151, - 152,153,154,155,156,157,158,159, - 160,161,162,163,164,165,166,167, - 168,169,170,171,172,173,174,175, - 176,177,178,179,180,181,182,183, - 184,185,186,187,188,189,190,191, - 192,193,194,195,196,197,198,199, - 200,201,202,203,204,205,206,207, - 208,209,210,211,212,213,214,215, - 216,217,218,219,220,221,222,223, - 224,225,226,227,228,229,230,231, - 232,233,234,235,236,237,238,239, - 240,241,242,243,244,245,246,247, - 248,249,250,251,252,253,254,255, - -/* This table is a case flipping table. */ - - 0, 1, 2, 3, 4, 5, 6, 7, - 8, 9, 10, 11, 12, 13, 14, 15, - 16, 17, 18, 19, 20, 21, 22, 23, - 24, 25, 26, 27, 28, 29, 30, 31, - 32, 33, 34, 35, 36, 37, 38, 39, - 40, 41, 42, 43, 44, 45, 46, 47, - 48, 49, 50, 51, 52, 53, 54, 55, - 56, 57, 58, 59, 60, 61, 62, 63, - 64, 97, 98, 99,100,101,102,103, - 104,105,106,107,108,109,110,111, - 112,113,114,115,116,117,118,119, - 120,121,122, 91, 92, 93, 94, 95, - 96, 65, 66, 67, 68, 69, 70, 71, - 72, 73, 74, 75, 76, 77, 78, 79, - 80, 81, 82, 83, 84, 85, 86, 87, - 88, 89, 90,123,124,125,126,127, - 128,129,130,131,132,133,134,135, - 136,137,138,139,140,141,142,143, - 144,145,146,147,148,149,150,151, - 152,153,154,155,156,157,158,159, - 160,161,162,163,164,165,166,167, - 168,169,170,171,172,173,174,175, - 176,177,178,179,180,181,182,183, - 184,185,186,187,188,189,190,191, - 192,193,194,195,196,197,198,199, - 200,201,202,203,204,205,206,207, - 208,209,210,211,212,213,214,215, - 216,217,218,219,220,221,222,223, - 224,225,226,227,228,229,230,231, - 232,233,234,235,236,237,238,239, - 240,241,242,243,244,245,246,247, - 248,249,250,251,252,253,254,255, - -/* This table contains bit maps for various character classes. Each map is 32 -bytes long and the bits run from the least significant end of each byte. The -classes that have their own maps are: space, xdigit, digit, upper, lower, word, -graph, print, punct, and cntrl. Other classes are built from combinations. */ - - 0x00,0x3e,0x00,0x00,0x01,0x00,0x00,0x00, - 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, - 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, - 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, - - 0x00,0x00,0x00,0x00,0x00,0x00,0xff,0x03, - 0x7e,0x00,0x00,0x00,0x7e,0x00,0x00,0x00, - 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, - 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, - - 0x00,0x00,0x00,0x00,0x00,0x00,0xff,0x03, - 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, - 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, - 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, - - 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, - 0xfe,0xff,0xff,0x07,0x00,0x00,0x00,0x00, - 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, - 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, - - 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, - 0x00,0x00,0x00,0x00,0xfe,0xff,0xff,0x07, - 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, - 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, - - 0x00,0x00,0x00,0x00,0x00,0x00,0xff,0x03, - 0xfe,0xff,0xff,0x87,0xfe,0xff,0xff,0x07, - 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, - 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, - - 0x00,0x00,0x00,0x00,0xfe,0xff,0xff,0xff, - 0xff,0xff,0xff,0xff,0xff,0xff,0xff,0x7f, - 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, - 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, - - 0x00,0x00,0x00,0x00,0xff,0xff,0xff,0xff, - 0xff,0xff,0xff,0xff,0xff,0xff,0xff,0x7f, - 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, - 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, - - 0x00,0x00,0x00,0x00,0xfe,0xff,0x00,0xfc, - 0x01,0x00,0x00,0xf8,0x01,0x00,0x00,0x78, - 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, - 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, - - 0xff,0xff,0xff,0xff,0x00,0x00,0x00,0x00, - 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x80, - 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, - 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, - -/* This table identifies various classes of character by individual bits: - 0x01 white space character - 0x02 letter - 0x04 decimal digit - 0x08 hexadecimal digit - 0x10 alphanumeric or '_' - 0x80 regular expression metacharacter or binary zero -*/ - - 0x80,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /* 0- 7 */ - 0x00,0x01,0x01,0x01,0x01,0x01,0x00,0x00, /* 8- 15 */ - 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /* 16- 23 */ - 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /* 24- 31 */ - 0x01,0x00,0x00,0x00,0x80,0x00,0x00,0x00, /* - ' */ - 0x80,0x80,0x80,0x80,0x00,0x00,0x80,0x00, /* ( - / */ - 0x1c,0x1c,0x1c,0x1c,0x1c,0x1c,0x1c,0x1c, /* 0 - 7 */ - 0x1c,0x1c,0x00,0x00,0x00,0x00,0x00,0x80, /* 8 - ? */ - 0x00,0x1a,0x1a,0x1a,0x1a,0x1a,0x1a,0x12, /* @ - G */ - 0x12,0x12,0x12,0x12,0x12,0x12,0x12,0x12, /* H - O */ - 0x12,0x12,0x12,0x12,0x12,0x12,0x12,0x12, /* P - W */ - 0x12,0x12,0x12,0x80,0x80,0x00,0x80,0x10, /* X - _ */ - 0x00,0x1a,0x1a,0x1a,0x1a,0x1a,0x1a,0x12, /* ` - g */ - 0x12,0x12,0x12,0x12,0x12,0x12,0x12,0x12, /* h - o */ - 0x12,0x12,0x12,0x12,0x12,0x12,0x12,0x12, /* p - w */ - 0x12,0x12,0x12,0x80,0x80,0x00,0x00,0x00, /* x -127 */ - 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /* 128-135 */ - 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /* 136-143 */ - 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /* 144-151 */ - 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /* 152-159 */ - 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /* 160-167 */ - 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /* 168-175 */ - 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /* 176-183 */ - 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /* 184-191 */ - 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /* 192-199 */ - 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /* 200-207 */ - 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /* 208-215 */ - 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /* 216-223 */ - 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /* 224-231 */ - 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /* 232-239 */ - 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /* 240-247 */ - 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00};/* 248-255 */ - -/* End of pcre_chartables.c */ diff --git a/src/third_party/pcre-8.38/pcre_compile.c b/src/third_party/pcre-8.38/pcre_compile.c deleted file mode 100644 index 4d3b3139dea..00000000000 --- a/src/third_party/pcre-8.38/pcre_compile.c +++ /dev/null @@ -1,9732 +0,0 @@ -/************************************************* -* Perl-Compatible Regular Expressions * -*************************************************/ - -/* PCRE is a library of functions to support regular expressions whose syntax -and semantics are as close as possible to those of the Perl 5 language. - - Written by Philip Hazel - Copyright (c) 1997-2014 University of Cambridge - ------------------------------------------------------------------------------ -Redistribution and use in source and binary forms, with or without -modification, are permitted provided that the following conditions are met: - - * Redistributions of source code must retain the above copyright notice, - this list of conditions and the following disclaimer. - - * Redistributions in binary form must reproduce the above copyright - notice, this list of conditions and the following disclaimer in the - documentation and/or other materials provided with the distribution. - - * Neither the name of the University of Cambridge nor the names of its - contributors may be used to endorse or promote products derived from - this software without specific prior written permission. - -THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS" -AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE -IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE -ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR CONTRIBUTORS BE -LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR -CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF -SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS -INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN -CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) -ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE -POSSIBILITY OF SUCH DAMAGE. ------------------------------------------------------------------------------ -*/ - - -/* This module contains the external function pcre_compile(), along with -supporting internal functions that are not used by other modules. */ - - -#ifdef HAVE_CONFIG_H -#include "config.h" -#endif - -#define NLBLOCK cd /* Block containing newline information */ -#define PSSTART start_pattern /* Field containing pattern start */ -#define PSEND end_pattern /* Field containing pattern end */ - -#include "pcre_internal.h" - - -/* When PCRE_DEBUG is defined, we need the pcre(16|32)_printint() function, which -is also used by pcretest. PCRE_DEBUG is not defined when building a production -library. We do not need to select pcre16_printint.c specially, because the -COMPILE_PCREx macro will already be appropriately set. */ - -#ifdef PCRE_DEBUG -/* pcre_printint.c should not include any headers */ -#define PCRE_INCLUDED -#include "pcre_printint.c" -#undef PCRE_INCLUDED -#endif - - -/* Macro for setting individual bits in class bitmaps. */ - -#define SETBIT(a,b) a[(b)/8] |= (1 << ((b)&7)) - -/* Maximum length value to check against when making sure that the integer that -holds the compiled pattern length does not overflow. We make it a bit less than -INT_MAX to allow for adding in group terminating bytes, so that we don't have -to check them every time. */ - -#define OFLOW_MAX (INT_MAX - 20) - -/* Definitions to allow mutual recursion */ - -static int - add_list_to_class(pcre_uint8 *, pcre_uchar **, int, compile_data *, - const pcre_uint32 *, unsigned int); - -static BOOL - compile_regex(int, pcre_uchar **, const pcre_uchar **, int *, BOOL, BOOL, int, int, - pcre_uint32 *, pcre_int32 *, pcre_uint32 *, pcre_int32 *, branch_chain *, - compile_data *, int *); - - - -/************************************************* -* Code parameters and static tables * -*************************************************/ - -/* This value specifies the size of stack workspace that is used during the -first pre-compile phase that determines how much memory is required. The regex -is partly compiled into this space, but the compiled parts are discarded as -soon as they can be, so that hopefully there will never be an overrun. The code -does, however, check for an overrun. The largest amount I've seen used is 218, -so this number is very generous. - -The same workspace is used during the second, actual compile phase for -remembering forward references to groups so that they can be filled in at the -end. Each entry in this list occupies LINK_SIZE bytes, so even when LINK_SIZE -is 4 there is plenty of room for most patterns. However, the memory can get -filled up by repetitions of forward references, for example patterns like -/(?1){0,1999}(b)/, and one user did hit the limit. The code has been changed so -that the workspace is expanded using malloc() in this situation. The value -below is therefore a minimum, and we put a maximum on it for safety. The -minimum is now also defined in terms of LINK_SIZE so that the use of malloc() -kicks in at the same number of forward references in all cases. */ - -#define COMPILE_WORK_SIZE (2048*LINK_SIZE) -#define COMPILE_WORK_SIZE_MAX (100*COMPILE_WORK_SIZE) - -/* This value determines the size of the initial vector that is used for -remembering named groups during the pre-compile. It is allocated on the stack, -but if it is too small, it is expanded using malloc(), in a similar way to the -workspace. The value is the number of slots in the list. */ - -#define NAMED_GROUP_LIST_SIZE 20 - -/* The overrun tests check for a slightly smaller size so that they detect the -overrun before it actually does run off the end of the data block. */ - -#define WORK_SIZE_SAFETY_MARGIN (100) - -/* Private flags added to firstchar and reqchar. */ - -#define REQ_CASELESS (1 << 0) /* Indicates caselessness */ -#define REQ_VARY (1 << 1) /* Reqchar followed non-literal item */ -/* Negative values for the firstchar and reqchar flags */ -#define REQ_UNSET (-2) -#define REQ_NONE (-1) - -/* Repeated character flags. */ - -#define UTF_LENGTH 0x10000000l /* The char contains its length. */ - -/* Table for handling escaped characters in the range '0'-'z'. Positive returns -are simple data values; negative values are for special things like \d and so -on. Zero means further processing is needed (for things like \x), or the escape -is invalid. */ - -#ifndef EBCDIC - -/* This is the "normal" table for ASCII systems or for EBCDIC systems running -in UTF-8 mode. */ - -static const short int escapes[] = { - 0, 0, - 0, 0, - 0, 0, - 0, 0, - 0, 0, - CHAR_COLON, CHAR_SEMICOLON, - CHAR_LESS_THAN_SIGN, CHAR_EQUALS_SIGN, - CHAR_GREATER_THAN_SIGN, CHAR_QUESTION_MARK, - CHAR_COMMERCIAL_AT, -ESC_A, - -ESC_B, -ESC_C, - -ESC_D, -ESC_E, - 0, -ESC_G, - -ESC_H, 0, - 0, -ESC_K, - 0, 0, - -ESC_N, 0, - -ESC_P, -ESC_Q, - -ESC_R, -ESC_S, - 0, 0, - -ESC_V, -ESC_W, - -ESC_X, 0, - -ESC_Z, CHAR_LEFT_SQUARE_BRACKET, - CHAR_BACKSLASH, CHAR_RIGHT_SQUARE_BRACKET, - CHAR_CIRCUMFLEX_ACCENT, CHAR_UNDERSCORE, - CHAR_GRAVE_ACCENT, ESC_a, - -ESC_b, 0, - -ESC_d, ESC_e, - ESC_f, 0, - -ESC_h, 0, - 0, -ESC_k, - 0, 0, - ESC_n, 0, - -ESC_p, 0, - ESC_r, -ESC_s, - ESC_tee, 0, - -ESC_v, -ESC_w, - 0, 0, - -ESC_z -}; - -#else - -/* This is the "abnormal" table for EBCDIC systems without UTF-8 support. */ - -static const short int escapes[] = { -/* 48 */ 0, 0, 0, '.', '<', '(', '+', '|', -/* 50 */ '&', 0, 0, 0, 0, 0, 0, 0, -/* 58 */ 0, 0, '!', '$', '*', ')', ';', '~', -/* 60 */ '-', '/', 0, 0, 0, 0, 0, 0, -/* 68 */ 0, 0, '|', ',', '%', '_', '>', '?', -/* 70 */ 0, 0, 0, 0, 0, 0, 0, 0, -/* 78 */ 0, '`', ':', '#', '@', '\'', '=', '"', -/* 80 */ 0, ESC_a, -ESC_b, 0, -ESC_d, ESC_e, ESC_f, 0, -/* 88 */-ESC_h, 0, 0, '{', 0, 0, 0, 0, -/* 90 */ 0, 0, -ESC_k, 0, 0, ESC_n, 0, -ESC_p, -/* 98 */ 0, ESC_r, 0, '}', 0, 0, 0, 0, -/* A0 */ 0, '~', -ESC_s, ESC_tee, 0,-ESC_v, -ESC_w, 0, -/* A8 */ 0,-ESC_z, 0, 0, 0, '[', 0, 0, -/* B0 */ 0, 0, 0, 0, 0, 0, 0, 0, -/* B8 */ 0, 0, 0, 0, 0, ']', '=', '-', -/* C0 */ '{',-ESC_A, -ESC_B, -ESC_C, -ESC_D,-ESC_E, 0, -ESC_G, -/* C8 */-ESC_H, 0, 0, 0, 0, 0, 0, 0, -/* D0 */ '}', 0, -ESC_K, 0, 0,-ESC_N, 0, -ESC_P, -/* D8 */-ESC_Q,-ESC_R, 0, 0, 0, 0, 0, 0, -/* E0 */ '\\', 0, -ESC_S, 0, 0,-ESC_V, -ESC_W, -ESC_X, -/* E8 */ 0,-ESC_Z, 0, 0, 0, 0, 0, 0, -/* F0 */ 0, 0, 0, 0, 0, 0, 0, 0, -/* F8 */ 0, 0, 0, 0, 0, 0, 0, 0 -}; - -/* We also need a table of characters that may follow \c in an EBCDIC -environment for characters 0-31. */ - -static unsigned char ebcdic_escape_c[] = "@ABCDEFGHIJKLMNOPQRSTUVWXYZ[\\]^_"; - -#endif - - -/* Table of special "verbs" like (*PRUNE). This is a short table, so it is -searched linearly. Put all the names into a single string, in order to reduce -the number of relocations when a shared library is dynamically linked. The -string is built from string macros so that it works in UTF-8 mode on EBCDIC -platforms. */ - -typedef struct verbitem { - int len; /* Length of verb name */ - int op; /* Op when no arg, or -1 if arg mandatory */ - int op_arg; /* Op when arg present, or -1 if not allowed */ -} verbitem; - -static const char verbnames[] = - "\0" /* Empty name is a shorthand for MARK */ - STRING_MARK0 - STRING_ACCEPT0 - STRING_COMMIT0 - STRING_F0 - STRING_FAIL0 - STRING_PRUNE0 - STRING_SKIP0 - STRING_THEN; - -static const verbitem verbs[] = { - { 0, -1, OP_MARK }, - { 4, -1, OP_MARK }, - { 6, OP_ACCEPT, -1 }, - { 6, OP_COMMIT, -1 }, - { 1, OP_FAIL, -1 }, - { 4, OP_FAIL, -1 }, - { 5, OP_PRUNE, OP_PRUNE_ARG }, - { 4, OP_SKIP, OP_SKIP_ARG }, - { 4, OP_THEN, OP_THEN_ARG } -}; - -static const int verbcount = sizeof(verbs)/sizeof(verbitem); - - -/* Substitutes for [[:<:]] and [[:>:]], which mean start and end of word in -another regex library. */ - -static const pcre_uchar sub_start_of_word[] = { - CHAR_BACKSLASH, CHAR_b, CHAR_LEFT_PARENTHESIS, CHAR_QUESTION_MARK, - CHAR_EQUALS_SIGN, CHAR_BACKSLASH, CHAR_w, CHAR_RIGHT_PARENTHESIS, '\0' }; - -static const pcre_uchar sub_end_of_word[] = { - CHAR_BACKSLASH, CHAR_b, CHAR_LEFT_PARENTHESIS, CHAR_QUESTION_MARK, - CHAR_LESS_THAN_SIGN, CHAR_EQUALS_SIGN, CHAR_BACKSLASH, CHAR_w, - CHAR_RIGHT_PARENTHESIS, '\0' }; - - -/* Tables of names of POSIX character classes and their lengths. The names are -now all in a single string, to reduce the number of relocations when a shared -library is dynamically loaded. The list of lengths is terminated by a zero -length entry. The first three must be alpha, lower, upper, as this is assumed -for handling case independence. The indices for graph, print, and punct are -needed, so identify them. */ - -static const char posix_names[] = - STRING_alpha0 STRING_lower0 STRING_upper0 STRING_alnum0 - STRING_ascii0 STRING_blank0 STRING_cntrl0 STRING_digit0 - STRING_graph0 STRING_print0 STRING_punct0 STRING_space0 - STRING_word0 STRING_xdigit; - -static const pcre_uint8 posix_name_lengths[] = { - 5, 5, 5, 5, 5, 5, 5, 5, 5, 5, 5, 5, 4, 6, 0 }; - -#define PC_GRAPH 8 -#define PC_PRINT 9 -#define PC_PUNCT 10 - - -/* Table of class bit maps for each POSIX class. Each class is formed from a -base map, with an optional addition or removal of another map. Then, for some -classes, there is some additional tweaking: for [:blank:] the vertical space -characters are removed, and for [:alpha:] and [:alnum:] the underscore -character is removed. The triples in the table consist of the base map offset, -second map offset or -1 if no second map, and a non-negative value for map -addition or a negative value for map subtraction (if there are two maps). The -absolute value of the third field has these meanings: 0 => no tweaking, 1 => -remove vertical space characters, 2 => remove underscore. */ - -static const int posix_class_maps[] = { - cbit_word, cbit_digit, -2, /* alpha */ - cbit_lower, -1, 0, /* lower */ - cbit_upper, -1, 0, /* upper */ - cbit_word, -1, 2, /* alnum - word without underscore */ - cbit_print, cbit_cntrl, 0, /* ascii */ - cbit_space, -1, 1, /* blank - a GNU extension */ - cbit_cntrl, -1, 0, /* cntrl */ - cbit_digit, -1, 0, /* digit */ - cbit_graph, -1, 0, /* graph */ - cbit_print, -1, 0, /* print */ - cbit_punct, -1, 0, /* punct */ - cbit_space, -1, 0, /* space */ - cbit_word, -1, 0, /* word - a Perl extension */ - cbit_xdigit,-1, 0 /* xdigit */ -}; - -/* Table of substitutes for \d etc when PCRE_UCP is set. They are replaced by -Unicode property escapes. */ - -#ifdef SUPPORT_UCP -static const pcre_uchar string_PNd[] = { - CHAR_BACKSLASH, CHAR_P, CHAR_LEFT_CURLY_BRACKET, - CHAR_N, CHAR_d, CHAR_RIGHT_CURLY_BRACKET, '\0' }; -static const pcre_uchar string_pNd[] = { - CHAR_BACKSLASH, CHAR_p, CHAR_LEFT_CURLY_BRACKET, - CHAR_N, CHAR_d, CHAR_RIGHT_CURLY_BRACKET, '\0' }; -static const pcre_uchar string_PXsp[] = { - CHAR_BACKSLASH, CHAR_P, CHAR_LEFT_CURLY_BRACKET, - CHAR_X, CHAR_s, CHAR_p, CHAR_RIGHT_CURLY_BRACKET, '\0' }; -static const pcre_uchar string_pXsp[] = { - CHAR_BACKSLASH, CHAR_p, CHAR_LEFT_CURLY_BRACKET, - CHAR_X, CHAR_s, CHAR_p, CHAR_RIGHT_CURLY_BRACKET, '\0' }; -static const pcre_uchar string_PXwd[] = { - CHAR_BACKSLASH, CHAR_P, CHAR_LEFT_CURLY_BRACKET, - CHAR_X, CHAR_w, CHAR_d, CHAR_RIGHT_CURLY_BRACKET, '\0' }; -static const pcre_uchar string_pXwd[] = { - CHAR_BACKSLASH, CHAR_p, CHAR_LEFT_CURLY_BRACKET, - CHAR_X, CHAR_w, CHAR_d, CHAR_RIGHT_CURLY_BRACKET, '\0' }; - -static const pcre_uchar *substitutes[] = { - string_PNd, /* \D */ - string_pNd, /* \d */ - string_PXsp, /* \S */ /* Xsp is Perl space, but from 8.34, Perl */ - string_pXsp, /* \s */ /* space and POSIX space are the same. */ - string_PXwd, /* \W */ - string_pXwd /* \w */ -}; - -/* The POSIX class substitutes must be in the order of the POSIX class names, -defined above, and there are both positive and negative cases. NULL means no -general substitute of a Unicode property escape (\p or \P). However, for some -POSIX classes (e.g. graph, print, punct) a special property code is compiled -directly. */ - -static const pcre_uchar string_pL[] = { - CHAR_BACKSLASH, CHAR_p, CHAR_LEFT_CURLY_BRACKET, - CHAR_L, CHAR_RIGHT_CURLY_BRACKET, '\0' }; -static const pcre_uchar string_pLl[] = { - CHAR_BACKSLASH, CHAR_p, CHAR_LEFT_CURLY_BRACKET, - CHAR_L, CHAR_l, CHAR_RIGHT_CURLY_BRACKET, '\0' }; -static const pcre_uchar string_pLu[] = { - CHAR_BACKSLASH, CHAR_p, CHAR_LEFT_CURLY_BRACKET, - CHAR_L, CHAR_u, CHAR_RIGHT_CURLY_BRACKET, '\0' }; -static const pcre_uchar string_pXan[] = { - CHAR_BACKSLASH, CHAR_p, CHAR_LEFT_CURLY_BRACKET, - CHAR_X, CHAR_a, CHAR_n, CHAR_RIGHT_CURLY_BRACKET, '\0' }; -static const pcre_uchar string_h[] = { - CHAR_BACKSLASH, CHAR_h, '\0' }; -static const pcre_uchar string_pXps[] = { - CHAR_BACKSLASH, CHAR_p, CHAR_LEFT_CURLY_BRACKET, - CHAR_X, CHAR_p, CHAR_s, CHAR_RIGHT_CURLY_BRACKET, '\0' }; -static const pcre_uchar string_PL[] = { - CHAR_BACKSLASH, CHAR_P, CHAR_LEFT_CURLY_BRACKET, - CHAR_L, CHAR_RIGHT_CURLY_BRACKET, '\0' }; -static const pcre_uchar string_PLl[] = { - CHAR_BACKSLASH, CHAR_P, CHAR_LEFT_CURLY_BRACKET, - CHAR_L, CHAR_l, CHAR_RIGHT_CURLY_BRACKET, '\0' }; -static const pcre_uchar string_PLu[] = { - CHAR_BACKSLASH, CHAR_P, CHAR_LEFT_CURLY_BRACKET, - CHAR_L, CHAR_u, CHAR_RIGHT_CURLY_BRACKET, '\0' }; -static const pcre_uchar string_PXan[] = { - CHAR_BACKSLASH, CHAR_P, CHAR_LEFT_CURLY_BRACKET, - CHAR_X, CHAR_a, CHAR_n, CHAR_RIGHT_CURLY_BRACKET, '\0' }; -static const pcre_uchar string_H[] = { - CHAR_BACKSLASH, CHAR_H, '\0' }; -static const pcre_uchar string_PXps[] = { - CHAR_BACKSLASH, CHAR_P, CHAR_LEFT_CURLY_BRACKET, - CHAR_X, CHAR_p, CHAR_s, CHAR_RIGHT_CURLY_BRACKET, '\0' }; - -static const pcre_uchar *posix_substitutes[] = { - string_pL, /* alpha */ - string_pLl, /* lower */ - string_pLu, /* upper */ - string_pXan, /* alnum */ - NULL, /* ascii */ - string_h, /* blank */ - NULL, /* cntrl */ - string_pNd, /* digit */ - NULL, /* graph */ - NULL, /* print */ - NULL, /* punct */ - string_pXps, /* space */ /* Xps is POSIX space, but from 8.34 */ - string_pXwd, /* word */ /* Perl and POSIX space are the same */ - NULL, /* xdigit */ - /* Negated cases */ - string_PL, /* ^alpha */ - string_PLl, /* ^lower */ - string_PLu, /* ^upper */ - string_PXan, /* ^alnum */ - NULL, /* ^ascii */ - string_H, /* ^blank */ - NULL, /* ^cntrl */ - string_PNd, /* ^digit */ - NULL, /* ^graph */ - NULL, /* ^print */ - NULL, /* ^punct */ - string_PXps, /* ^space */ /* Xps is POSIX space, but from 8.34 */ - string_PXwd, /* ^word */ /* Perl and POSIX space are the same */ - NULL /* ^xdigit */ -}; -#define POSIX_SUBSIZE (sizeof(posix_substitutes) / sizeof(pcre_uchar *)) -#endif - -#define STRING(a) # a -#define XSTRING(s) STRING(s) - -/* The texts of compile-time error messages. These are "char *" because they -are passed to the outside world. Do not ever re-use any error number, because -they are documented. Always add a new error instead. Messages marked DEAD below -are no longer used. This used to be a table of strings, but in order to reduce -the number of relocations needed when a shared library is loaded dynamically, -it is now one long string. We cannot use a table of offsets, because the -lengths of inserts such as XSTRING(MAX_NAME_SIZE) are not known. Instead, we -simply count through to the one we want - this isn't a performance issue -because these strings are used only when there is a compilation error. - -Each substring ends with \0 to insert a null character. This includes the final -substring, so that the whole string ends with \0\0, which can be detected when -counting through. */ - -static const char error_texts[] = - "no error\0" - "\\ at end of pattern\0" - "\\c at end of pattern\0" - "unrecognized character follows \\\0" - "numbers out of order in {} quantifier\0" - /* 5 */ - "number too big in {} quantifier\0" - "missing terminating ] for character class\0" - "invalid escape sequence in character class\0" - "range out of order in character class\0" - "nothing to repeat\0" - /* 10 */ - "internal error: invalid forward reference offset\0" - "internal error: unexpected repeat\0" - "unrecognized character after (? or (?-\0" - "POSIX named classes are supported only within a class\0" - "missing )\0" - /* 15 */ - "reference to non-existent subpattern\0" - "erroffset passed as NULL\0" - "unknown option bit(s) set\0" - "missing ) after comment\0" - "parentheses nested too deeply\0" /** DEAD **/ - /* 20 */ - "regular expression is too large\0" - "failed to get memory\0" - "unmatched parentheses\0" - "internal error: code overflow\0" - "unrecognized character after (?<\0" - /* 25 */ - "lookbehind assertion is not fixed length\0" - "malformed number or name after (?(\0" - "conditional group contains more than two branches\0" - "assertion expected after (?(\0" - "(?R or (?[+-]digits must be followed by )\0" - /* 30 */ - "unknown POSIX class name\0" - "POSIX collating elements are not supported\0" - "this version of PCRE is compiled without UTF support\0" - "spare error\0" /** DEAD **/ - "character value in \\x{} or \\o{} is too large\0" - /* 35 */ - "invalid condition (?(0)\0" - "\\C not allowed in lookbehind assertion\0" - "PCRE does not support \\L, \\l, \\N{name}, \\U, or \\u\0" - "number after (?C is > 255\0" - "closing ) for (?C expected\0" - /* 40 */ - "recursive call could loop indefinitely\0" - "unrecognized character after (?P\0" - "syntax error in subpattern name (missing terminator)\0" - "two named subpatterns have the same name\0" - "invalid UTF-8 string\0" - /* 45 */ - "support for \\P, \\p, and \\X has not been compiled\0" - "malformed \\P or \\p sequence\0" - "unknown property name after \\P or \\p\0" - "subpattern name is too long (maximum " XSTRING(MAX_NAME_SIZE) " characters)\0" - "too many named subpatterns (maximum " XSTRING(MAX_NAME_COUNT) ")\0" - /* 50 */ - "repeated subpattern is too long\0" /** DEAD **/ - "octal value is greater than \\377 in 8-bit non-UTF-8 mode\0" - "internal error: overran compiling workspace\0" - "internal error: previously-checked referenced subpattern not found\0" - "DEFINE group contains more than one branch\0" - /* 55 */ - "repeating a DEFINE group is not allowed\0" /** DEAD **/ - "inconsistent NEWLINE options\0" - "\\g is not followed by a braced, angle-bracketed, or quoted name/number or by a plain number\0" - "a numbered reference must not be zero\0" - "an argument is not allowed for (*ACCEPT), (*FAIL), or (*COMMIT)\0" - /* 60 */ - "(*VERB) not recognized or malformed\0" - "number is too big\0" - "subpattern name expected\0" - "digit expected after (?+\0" - "] is an invalid data character in JavaScript compatibility mode\0" - /* 65 */ - "different names for subpatterns of the same number are not allowed\0" - "(*MARK) must have an argument\0" - "this version of PCRE is not compiled with Unicode property support\0" -#ifndef EBCDIC - "\\c must be followed by an ASCII character\0" -#else - "\\c must be followed by a letter or one of [\\]^_?\0" -#endif - "\\k is not followed by a braced, angle-bracketed, or quoted name\0" - /* 70 */ - "internal error: unknown opcode in find_fixedlength()\0" - "\\N is not supported in a class\0" - "too many forward references\0" - "disallowed Unicode code point (>= 0xd800 && <= 0xdfff)\0" - "invalid UTF-16 string\0" - /* 75 */ - "name is too long in (*MARK), (*PRUNE), (*SKIP), or (*THEN)\0" - "character value in \\u.... sequence is too large\0" - "invalid UTF-32 string\0" - "setting UTF is disabled by the application\0" - "non-hex character in \\x{} (closing brace missing?)\0" - /* 80 */ - "non-octal character in \\o{} (closing brace missing?)\0" - "missing opening brace after \\o\0" - "parentheses are too deeply nested\0" - "invalid range in character class\0" - "group name must start with a non-digit\0" - /* 85 */ - "parentheses are too deeply nested (stack check)\0" - "digits missing in \\x{} or \\o{}\0" - ; - -/* Table to identify digits and hex digits. This is used when compiling -patterns. Note that the tables in chartables are dependent on the locale, and -may mark arbitrary characters as digits - but the PCRE compiling code expects -to handle only 0-9, a-z, and A-Z as digits when compiling. That is why we have -a private table here. It costs 256 bytes, but it is a lot faster than doing -character value tests (at least in some simple cases I timed), and in some -applications one wants PCRE to compile efficiently as well as match -efficiently. - -For convenience, we use the same bit definitions as in chartables: - - 0x04 decimal digit - 0x08 hexadecimal digit - -Then we can use ctype_digit and ctype_xdigit in the code. */ - -/* Using a simple comparison for decimal numbers rather than a memory read -is much faster, and the resulting code is simpler (the compiler turns it -into a subtraction and unsigned comparison). */ - -#define IS_DIGIT(x) ((x) >= CHAR_0 && (x) <= CHAR_9) - -#ifndef EBCDIC - -/* This is the "normal" case, for ASCII systems, and EBCDIC systems running in -UTF-8 mode. */ - -static const pcre_uint8 digitab[] = - { - 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /* 0- 7 */ - 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /* 8- 15 */ - 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /* 16- 23 */ - 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /* 24- 31 */ - 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /* - ' */ - 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /* ( - / */ - 0x0c,0x0c,0x0c,0x0c,0x0c,0x0c,0x0c,0x0c, /* 0 - 7 */ - 0x0c,0x0c,0x00,0x00,0x00,0x00,0x00,0x00, /* 8 - ? */ - 0x00,0x08,0x08,0x08,0x08,0x08,0x08,0x00, /* @ - G */ - 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /* H - O */ - 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /* P - W */ - 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /* X - _ */ - 0x00,0x08,0x08,0x08,0x08,0x08,0x08,0x00, /* ` - g */ - 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /* h - o */ - 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /* p - w */ - 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /* x -127 */ - 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /* 128-135 */ - 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /* 136-143 */ - 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /* 144-151 */ - 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /* 152-159 */ - 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /* 160-167 */ - 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /* 168-175 */ - 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /* 176-183 */ - 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /* 184-191 */ - 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /* 192-199 */ - 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /* 200-207 */ - 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /* 208-215 */ - 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /* 216-223 */ - 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /* 224-231 */ - 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /* 232-239 */ - 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /* 240-247 */ - 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00};/* 248-255 */ - -#else - -/* This is the "abnormal" case, for EBCDIC systems not running in UTF-8 mode. */ - -static const pcre_uint8 digitab[] = - { - 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /* 0- 7 0 */ - 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /* 8- 15 */ - 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /* 16- 23 10 */ - 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /* 24- 31 */ - 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /* 32- 39 20 */ - 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /* 40- 47 */ - 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /* 48- 55 30 */ - 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /* 56- 63 */ - 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /* - 71 40 */ - 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /* 72- | */ - 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /* & - 87 50 */ - 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /* 88- 95 */ - 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /* - -103 60 */ - 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /* 104- ? */ - 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /* 112-119 70 */ - 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /* 120- " */ - 0x00,0x08,0x08,0x08,0x08,0x08,0x08,0x00, /* 128- g 80 */ - 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /* h -143 */ - 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /* 144- p 90 */ - 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /* q -159 */ - 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /* 160- x A0 */ - 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /* y -175 */ - 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /* ^ -183 B0 */ - 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /* 184-191 */ - 0x00,0x08,0x08,0x08,0x08,0x08,0x08,0x00, /* { - G C0 */ - 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /* H -207 */ - 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /* } - P D0 */ - 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /* Q -223 */ - 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /* \ - X E0 */ - 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /* Y -239 */ - 0x0c,0x0c,0x0c,0x0c,0x0c,0x0c,0x0c,0x0c, /* 0 - 7 F0 */ - 0x0c,0x0c,0x00,0x00,0x00,0x00,0x00,0x00};/* 8 -255 */ - -static const pcre_uint8 ebcdic_chartab[] = { /* chartable partial dup */ - 0x80,0x00,0x00,0x00,0x00,0x01,0x00,0x00, /* 0- 7 */ - 0x00,0x00,0x00,0x00,0x01,0x01,0x00,0x00, /* 8- 15 */ - 0x00,0x00,0x00,0x00,0x00,0x01,0x00,0x00, /* 16- 23 */ - 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /* 24- 31 */ - 0x00,0x00,0x00,0x00,0x00,0x01,0x00,0x00, /* 32- 39 */ - 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /* 40- 47 */ - 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /* 48- 55 */ - 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /* 56- 63 */ - 0x01,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /* - 71 */ - 0x00,0x00,0x00,0x80,0x00,0x80,0x80,0x80, /* 72- | */ - 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /* & - 87 */ - 0x00,0x00,0x00,0x80,0x80,0x80,0x00,0x00, /* 88- 95 */ - 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /* - -103 */ - 0x00,0x00,0x00,0x00,0x00,0x10,0x00,0x80, /* 104- ? */ - 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /* 112-119 */ - 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /* 120- " */ - 0x00,0x1a,0x1a,0x1a,0x1a,0x1a,0x1a,0x12, /* 128- g */ - 0x12,0x12,0x00,0x00,0x00,0x00,0x00,0x00, /* h -143 */ - 0x00,0x12,0x12,0x12,0x12,0x12,0x12,0x12, /* 144- p */ - 0x12,0x12,0x00,0x00,0x00,0x00,0x00,0x00, /* q -159 */ - 0x00,0x00,0x12,0x12,0x12,0x12,0x12,0x12, /* 160- x */ - 0x12,0x12,0x00,0x00,0x00,0x00,0x00,0x00, /* y -175 */ - 0x80,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /* ^ -183 */ - 0x00,0x00,0x80,0x00,0x00,0x00,0x00,0x00, /* 184-191 */ - 0x80,0x1a,0x1a,0x1a,0x1a,0x1a,0x1a,0x12, /* { - G */ - 0x12,0x12,0x00,0x00,0x00,0x00,0x00,0x00, /* H -207 */ - 0x00,0x12,0x12,0x12,0x12,0x12,0x12,0x12, /* } - P */ - 0x12,0x12,0x00,0x00,0x00,0x00,0x00,0x00, /* Q -223 */ - 0x00,0x00,0x12,0x12,0x12,0x12,0x12,0x12, /* \ - X */ - 0x12,0x12,0x00,0x00,0x00,0x00,0x00,0x00, /* Y -239 */ - 0x1c,0x1c,0x1c,0x1c,0x1c,0x1c,0x1c,0x1c, /* 0 - 7 */ - 0x1c,0x1c,0x00,0x00,0x00,0x00,0x00,0x00};/* 8 -255 */ -#endif - - -/* This table is used to check whether auto-possessification is possible -between adjacent character-type opcodes. The left-hand (repeated) opcode is -used to select the row, and the right-hand opcode is use to select the column. -A value of 1 means that auto-possessification is OK. For example, the second -value in the first row means that \D+\d can be turned into \D++\d. - -The Unicode property types (\P and \p) have to be present to fill out the table -because of what their opcode values are, but the table values should always be -zero because property types are handled separately in the code. The last four -columns apply to items that cannot be repeated, so there is no need to have -rows for them. Note that OP_DIGIT etc. are generated only when PCRE_UCP is -*not* set. When it is set, \d etc. are converted into OP_(NOT_)PROP codes. */ - -#define APTROWS (LAST_AUTOTAB_LEFT_OP - FIRST_AUTOTAB_OP + 1) -#define APTCOLS (LAST_AUTOTAB_RIGHT_OP - FIRST_AUTOTAB_OP + 1) - -static const pcre_uint8 autoposstab[APTROWS][APTCOLS] = { -/* \D \d \S \s \W \w . .+ \C \P \p \R \H \h \V \v \X \Z \z $ $M */ - { 0, 1, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 1, 0, 0 }, /* \D */ - { 1, 0, 0, 1, 1, 0, 0, 0, 0, 0, 0, 1, 0, 1, 0, 1, 0, 1, 1, 1, 1 }, /* \d */ - { 0, 0, 0, 1, 0, 0, 0, 0, 0, 0, 0, 1, 0, 1, 0, 1, 0, 1, 1, 1, 1 }, /* \S */ - { 0, 1, 1, 0, 0, 1, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 1, 0, 0 }, /* \s */ - { 0, 1, 0, 0, 0, 1, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 1, 0, 0 }, /* \W */ - { 0, 0, 0, 1, 1, 0, 0, 0, 0, 0, 0, 1, 0, 1, 0, 1, 0, 1, 1, 1, 1 }, /* \w */ - { 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 1, 0, 0, 0, 0, 0, 0, 1, 0, 0 }, /* . */ - { 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 1, 0, 0 }, /* .+ */ - { 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 1, 0, 0 }, /* \C */ - { 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0 }, /* \P */ - { 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0 }, /* \p */ - { 0, 1, 0, 1, 0, 1, 1, 0, 0, 0, 0, 0, 0, 1, 0, 0, 0, 0, 1, 0, 0 }, /* \R */ - { 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 1, 0, 0, 0, 0, 1, 0, 0 }, /* \H */ - { 0, 1, 1, 0, 0, 1, 0, 0, 0, 0, 0, 1, 1, 0, 0, 1, 0, 0, 1, 0, 0 }, /* \h */ - { 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 1, 0, 0, 0, 1, 0, 0, 1, 0, 0 }, /* \V */ - { 0, 1, 1, 0, 0, 1, 0, 0, 0, 0, 0, 0, 0, 1, 1, 0, 0, 0, 1, 0, 0 }, /* \v */ - { 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 1, 0, 0 } /* \X */ -}; - - -/* This table is used to check whether auto-possessification is possible -between adjacent Unicode property opcodes (OP_PROP and OP_NOTPROP). The -left-hand (repeated) opcode is used to select the row, and the right-hand -opcode is used to select the column. The values are as follows: - - 0 Always return FALSE (never auto-possessify) - 1 Character groups are distinct (possessify if both are OP_PROP) - 2 Check character categories in the same group (general or particular) - 3 TRUE if the two opcodes are not the same (PROP vs NOTPROP) - - 4 Check left general category vs right particular category - 5 Check right general category vs left particular category - - 6 Left alphanum vs right general category - 7 Left space vs right general category - 8 Left word vs right general category - - 9 Right alphanum vs left general category - 10 Right space vs left general category - 11 Right word vs left general category - - 12 Left alphanum vs right particular category - 13 Left space vs right particular category - 14 Left word vs right particular category - - 15 Right alphanum vs left particular category - 16 Right space vs left particular category - 17 Right word vs left particular category -*/ - -static const pcre_uint8 propposstab[PT_TABSIZE][PT_TABSIZE] = { -/* ANY LAMP GC PC SC ALNUM SPACE PXSPACE WORD CLIST UCNC */ - { 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0 }, /* PT_ANY */ - { 0, 3, 0, 0, 0, 3, 1, 1, 0, 0, 0 }, /* PT_LAMP */ - { 0, 0, 2, 4, 0, 9, 10, 10, 11, 0, 0 }, /* PT_GC */ - { 0, 0, 5, 2, 0, 15, 16, 16, 17, 0, 0 }, /* PT_PC */ - { 0, 0, 0, 0, 2, 0, 0, 0, 0, 0, 0 }, /* PT_SC */ - { 0, 3, 6, 12, 0, 3, 1, 1, 0, 0, 0 }, /* PT_ALNUM */ - { 0, 1, 7, 13, 0, 1, 3, 3, 1, 0, 0 }, /* PT_SPACE */ - { 0, 1, 7, 13, 0, 1, 3, 3, 1, 0, 0 }, /* PT_PXSPACE */ - { 0, 0, 8, 14, 0, 0, 1, 1, 3, 0, 0 }, /* PT_WORD */ - { 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0 }, /* PT_CLIST */ - { 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 3 } /* PT_UCNC */ -}; - -/* This table is used to check whether auto-possessification is possible -between adjacent Unicode property opcodes (OP_PROP and OP_NOTPROP) when one -specifies a general category and the other specifies a particular category. The -row is selected by the general category and the column by the particular -category. The value is 1 if the particular category is not part of the general -category. */ - -static const pcre_uint8 catposstab[7][30] = { -/* Cc Cf Cn Co Cs Ll Lm Lo Lt Lu Mc Me Mn Nd Nl No Pc Pd Pe Pf Pi Po Ps Sc Sk Sm So Zl Zp Zs */ - { 0, 0, 0, 0, 0, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1 }, /* C */ - { 1, 1, 1, 1, 1, 0, 0, 0, 0, 0, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1 }, /* L */ - { 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 0, 0, 0, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1 }, /* M */ - { 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 0, 0, 0, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1 }, /* N */ - { 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 0, 0, 0, 0, 0, 0, 0, 1, 1, 1, 1, 1, 1, 1 }, /* P */ - { 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 0, 0, 0, 0, 1, 1, 1 }, /* S */ - { 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 0, 0, 0 } /* Z */ -}; - -/* This table is used when checking ALNUM, (PX)SPACE, SPACE, and WORD against -a general or particular category. The properties in each row are those -that apply to the character set in question. Duplication means that a little -unnecessary work is done when checking, but this keeps things much simpler -because they can all use the same code. For more details see the comment where -this table is used. - -Note: SPACE and PXSPACE used to be different because Perl excluded VT from -"space", but from Perl 5.18 it's included, so both categories are treated the -same here. */ - -static const pcre_uint8 posspropstab[3][4] = { - { ucp_L, ucp_N, ucp_N, ucp_Nl }, /* ALNUM, 3rd and 4th values redundant */ - { ucp_Z, ucp_Z, ucp_C, ucp_Cc }, /* SPACE and PXSPACE, 2nd value redundant */ - { ucp_L, ucp_N, ucp_P, ucp_Po } /* WORD */ -}; - -/* This table is used when converting repeating opcodes into possessified -versions as a result of an explicit possessive quantifier such as ++. A zero -value means there is no possessified version - in those cases the item in -question must be wrapped in ONCE brackets. The table is truncated at OP_CALLOUT -because all relevant opcodes are less than that. */ - -static const pcre_uint8 opcode_possessify[] = { - 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, /* 0 - 15 */ - 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, /* 16 - 31 */ - - 0, /* NOTI */ - OP_POSSTAR, 0, /* STAR, MINSTAR */ - OP_POSPLUS, 0, /* PLUS, MINPLUS */ - OP_POSQUERY, 0, /* QUERY, MINQUERY */ - OP_POSUPTO, 0, /* UPTO, MINUPTO */ - 0, /* EXACT */ - 0, 0, 0, 0, /* POS{STAR,PLUS,QUERY,UPTO} */ - - OP_POSSTARI, 0, /* STARI, MINSTARI */ - OP_POSPLUSI, 0, /* PLUSI, MINPLUSI */ - OP_POSQUERYI, 0, /* QUERYI, MINQUERYI */ - OP_POSUPTOI, 0, /* UPTOI, MINUPTOI */ - 0, /* EXACTI */ - 0, 0, 0, 0, /* POS{STARI,PLUSI,QUERYI,UPTOI} */ - - OP_NOTPOSSTAR, 0, /* NOTSTAR, NOTMINSTAR */ - OP_NOTPOSPLUS, 0, /* NOTPLUS, NOTMINPLUS */ - OP_NOTPOSQUERY, 0, /* NOTQUERY, NOTMINQUERY */ - OP_NOTPOSUPTO, 0, /* NOTUPTO, NOTMINUPTO */ - 0, /* NOTEXACT */ - 0, 0, 0, 0, /* NOTPOS{STAR,PLUS,QUERY,UPTO} */ - - OP_NOTPOSSTARI, 0, /* NOTSTARI, NOTMINSTARI */ - OP_NOTPOSPLUSI, 0, /* NOTPLUSI, NOTMINPLUSI */ - OP_NOTPOSQUERYI, 0, /* NOTQUERYI, NOTMINQUERYI */ - OP_NOTPOSUPTOI, 0, /* NOTUPTOI, NOTMINUPTOI */ - 0, /* NOTEXACTI */ - 0, 0, 0, 0, /* NOTPOS{STARI,PLUSI,QUERYI,UPTOI} */ - - OP_TYPEPOSSTAR, 0, /* TYPESTAR, TYPEMINSTAR */ - OP_TYPEPOSPLUS, 0, /* TYPEPLUS, TYPEMINPLUS */ - OP_TYPEPOSQUERY, 0, /* TYPEQUERY, TYPEMINQUERY */ - OP_TYPEPOSUPTO, 0, /* TYPEUPTO, TYPEMINUPTO */ - 0, /* TYPEEXACT */ - 0, 0, 0, 0, /* TYPEPOS{STAR,PLUS,QUERY,UPTO} */ - - OP_CRPOSSTAR, 0, /* CRSTAR, CRMINSTAR */ - OP_CRPOSPLUS, 0, /* CRPLUS, CRMINPLUS */ - OP_CRPOSQUERY, 0, /* CRQUERY, CRMINQUERY */ - OP_CRPOSRANGE, 0, /* CRRANGE, CRMINRANGE */ - 0, 0, 0, 0, /* CRPOS{STAR,PLUS,QUERY,RANGE} */ - - 0, 0, 0, /* CLASS, NCLASS, XCLASS */ - 0, 0, /* REF, REFI */ - 0, 0, /* DNREF, DNREFI */ - 0, 0 /* RECURSE, CALLOUT */ -}; - - - -/************************************************* -* Find an error text * -*************************************************/ - -/* The error texts are now all in one long string, to save on relocations. As -some of the text is of unknown length, we can't use a table of offsets. -Instead, just count through the strings. This is not a performance issue -because it happens only when there has been a compilation error. - -Argument: the error number -Returns: pointer to the error string -*/ - -static const char * -find_error_text(int n) -{ -const char *s = error_texts; -for (; n > 0; n--) - { - while (*s++ != CHAR_NULL) {}; - if (*s == CHAR_NULL) return "Error text not found (please report)"; - } -return s; -} - - - -/************************************************* -* Expand the workspace * -*************************************************/ - -/* This function is called during the second compiling phase, if the number of -forward references fills the existing workspace, which is originally a block on -the stack. A larger block is obtained from malloc() unless the ultimate limit -has been reached or the increase will be rather small. - -Argument: pointer to the compile data block -Returns: 0 if all went well, else an error number -*/ - -static int -expand_workspace(compile_data *cd) -{ -pcre_uchar *newspace; -int newsize = cd->workspace_size * 2; - -if (newsize > COMPILE_WORK_SIZE_MAX) newsize = COMPILE_WORK_SIZE_MAX; -if (cd->workspace_size >= COMPILE_WORK_SIZE_MAX || - newsize - cd->workspace_size < WORK_SIZE_SAFETY_MARGIN) - return ERR72; - -newspace = (PUBL(malloc))(IN_UCHARS(newsize)); -if (newspace == NULL) return ERR21; -memcpy(newspace, cd->start_workspace, cd->workspace_size * sizeof(pcre_uchar)); -cd->hwm = (pcre_uchar *)newspace + (cd->hwm - cd->start_workspace); -if (cd->workspace_size > COMPILE_WORK_SIZE) - (PUBL(free))((void *)cd->start_workspace); -cd->start_workspace = newspace; -cd->workspace_size = newsize; -return 0; -} - - - -/************************************************* -* Check for counted repeat * -*************************************************/ - -/* This function is called when a '{' is encountered in a place where it might -start a quantifier. It looks ahead to see if it really is a quantifier or not. -It is only a quantifier if it is one of the forms {ddd} {ddd,} or {ddd,ddd} -where the ddds are digits. - -Arguments: - p pointer to the first char after '{' - -Returns: TRUE or FALSE -*/ - -static BOOL -is_counted_repeat(const pcre_uchar *p) -{ -if (!IS_DIGIT(*p)) return FALSE; -p++; -while (IS_DIGIT(*p)) p++; -if (*p == CHAR_RIGHT_CURLY_BRACKET) return TRUE; - -if (*p++ != CHAR_COMMA) return FALSE; -if (*p == CHAR_RIGHT_CURLY_BRACKET) return TRUE; - -if (!IS_DIGIT(*p)) return FALSE; -p++; -while (IS_DIGIT(*p)) p++; - -return (*p == CHAR_RIGHT_CURLY_BRACKET); -} - - - -/************************************************* -* Handle escapes * -*************************************************/ - -/* This function is called when a \ has been encountered. It either returns a -positive value for a simple escape such as \n, or 0 for a data character which -will be placed in chptr. A backreference to group n is returned as negative n. -When UTF-8 is enabled, a positive value greater than 255 may be returned in -chptr. On entry, ptr is pointing at the \. On exit, it is on the final -character of the escape sequence. - -Arguments: - ptrptr points to the pattern position pointer - chptr points to a returned data character - errorcodeptr points to the errorcode variable - bracount number of previous extracting brackets - options the options bits - isclass TRUE if inside a character class - -Returns: zero => a data character - positive => a special escape sequence - negative => a back reference - on error, errorcodeptr is set -*/ - -static int -check_escape(const pcre_uchar **ptrptr, pcre_uint32 *chptr, int *errorcodeptr, - int bracount, int options, BOOL isclass) -{ -/* PCRE_UTF16 has the same value as PCRE_UTF8. */ -BOOL utf = (options & PCRE_UTF8) != 0; -const pcre_uchar *ptr = *ptrptr + 1; -pcre_uint32 c; -int escape = 0; -int i; - -GETCHARINCTEST(c, ptr); /* Get character value, increment pointer */ -ptr--; /* Set pointer back to the last byte */ - -/* If backslash is at the end of the pattern, it's an error. */ - -if (c == CHAR_NULL) *errorcodeptr = ERR1; - -/* Non-alphanumerics are literals. For digits or letters, do an initial lookup -in a table. A non-zero result is something that can be returned immediately. -Otherwise further processing may be required. */ - -#ifndef EBCDIC /* ASCII/UTF-8 coding */ -/* Not alphanumeric */ -else if (c < CHAR_0 || c > CHAR_z) {} -else if ((i = escapes[c - CHAR_0]) != 0) - { if (i > 0) c = (pcre_uint32)i; else escape = -i; } - -#else /* EBCDIC coding */ -/* Not alphanumeric */ -else if (c < CHAR_a || (!MAX_255(c) || (ebcdic_chartab[c] & 0x0E) == 0)) {} -else if ((i = escapes[c - 0x48]) != 0) { if (i > 0) c = (pcre_uint32)i; else escape = -i; } -#endif - -/* Escapes that need further processing, or are illegal. */ - -else - { - const pcre_uchar *oldptr; - BOOL braced, negated, overflow; - int s; - - switch (c) - { - /* A number of Perl escapes are not handled by PCRE. We give an explicit - error. */ - - case CHAR_l: - case CHAR_L: - *errorcodeptr = ERR37; - break; - - case CHAR_u: - if ((options & PCRE_JAVASCRIPT_COMPAT) != 0) - { - /* In JavaScript, \u must be followed by four hexadecimal numbers. - Otherwise it is a lowercase u letter. */ - if (MAX_255(ptr[1]) && (digitab[ptr[1]] & ctype_xdigit) != 0 - && MAX_255(ptr[2]) && (digitab[ptr[2]] & ctype_xdigit) != 0 - && MAX_255(ptr[3]) && (digitab[ptr[3]] & ctype_xdigit) != 0 - && MAX_255(ptr[4]) && (digitab[ptr[4]] & ctype_xdigit) != 0) - { - c = 0; - for (i = 0; i < 4; ++i) - { - register pcre_uint32 cc = *(++ptr); -#ifndef EBCDIC /* ASCII/UTF-8 coding */ - if (cc >= CHAR_a) cc -= 32; /* Convert to upper case */ - c = (c << 4) + cc - ((cc < CHAR_A)? CHAR_0 : (CHAR_A - 10)); -#else /* EBCDIC coding */ - if (cc >= CHAR_a && cc <= CHAR_z) cc += 64; /* Convert to upper case */ - c = (c << 4) + cc - ((cc >= CHAR_0)? CHAR_0 : (CHAR_A - 10)); -#endif - } - -#if defined COMPILE_PCRE8 - if (c > (utf ? 0x10ffffU : 0xffU)) -#elif defined COMPILE_PCRE16 - if (c > (utf ? 0x10ffffU : 0xffffU)) -#elif defined COMPILE_PCRE32 - if (utf && c > 0x10ffffU) -#endif - { - *errorcodeptr = ERR76; - } - else if (utf && c >= 0xd800 && c <= 0xdfff) *errorcodeptr = ERR73; - } - } - else - *errorcodeptr = ERR37; - break; - - case CHAR_U: - /* In JavaScript, \U is an uppercase U letter. */ - if ((options & PCRE_JAVASCRIPT_COMPAT) == 0) *errorcodeptr = ERR37; - break; - - /* In a character class, \g is just a literal "g". Outside a character - class, \g must be followed by one of a number of specific things: - - (1) A number, either plain or braced. If positive, it is an absolute - backreference. If negative, it is a relative backreference. This is a Perl - 5.10 feature. - - (2) Perl 5.10 also supports \g{name} as a reference to a named group. This - is part of Perl's movement towards a unified syntax for back references. As - this is synonymous with \k{name}, we fudge it up by pretending it really - was \k. - - (3) For Oniguruma compatibility we also support \g followed by a name or a - number either in angle brackets or in single quotes. However, these are - (possibly recursive) subroutine calls, _not_ backreferences. Just return - the ESC_g code (cf \k). */ - - case CHAR_g: - if (isclass) break; - if (ptr[1] == CHAR_LESS_THAN_SIGN || ptr[1] == CHAR_APOSTROPHE) - { - escape = ESC_g; - break; - } - - /* Handle the Perl-compatible cases */ - - if (ptr[1] == CHAR_LEFT_CURLY_BRACKET) - { - const pcre_uchar *p; - for (p = ptr+2; *p != CHAR_NULL && *p != CHAR_RIGHT_CURLY_BRACKET; p++) - if (*p != CHAR_MINUS && !IS_DIGIT(*p)) break; - if (*p != CHAR_NULL && *p != CHAR_RIGHT_CURLY_BRACKET) - { - escape = ESC_k; - break; - } - braced = TRUE; - ptr++; - } - else braced = FALSE; - - if (ptr[1] == CHAR_MINUS) - { - negated = TRUE; - ptr++; - } - else negated = FALSE; - - /* The integer range is limited by the machine's int representation. */ - s = 0; - overflow = FALSE; - while (IS_DIGIT(ptr[1])) - { - if (s > INT_MAX / 10 - 1) /* Integer overflow */ - { - overflow = TRUE; - break; - } - s = s * 10 + (int)(*(++ptr) - CHAR_0); - } - if (overflow) /* Integer overflow */ - { - while (IS_DIGIT(ptr[1])) - ptr++; - *errorcodeptr = ERR61; - break; - } - - if (braced && *(++ptr) != CHAR_RIGHT_CURLY_BRACKET) - { - *errorcodeptr = ERR57; - break; - } - - if (s == 0) - { - *errorcodeptr = ERR58; - break; - } - - if (negated) - { - if (s > bracount) - { - *errorcodeptr = ERR15; - break; - } - s = bracount - (s - 1); - } - - escape = -s; - break; - - /* The handling of escape sequences consisting of a string of digits - starting with one that is not zero is not straightforward. Perl has changed - over the years. Nowadays \g{} for backreferences and \o{} for octal are - recommended to avoid the ambiguities in the old syntax. - - Outside a character class, the digits are read as a decimal number. If the - number is less than 8 (used to be 10), or if there are that many previous - extracting left brackets, then it is a back reference. Otherwise, up to - three octal digits are read to form an escaped byte. Thus \123 is likely to - be octal 123 (cf \0123, which is octal 012 followed by the literal 3). If - the octal value is greater than 377, the least significant 8 bits are - taken. \8 and \9 are treated as the literal characters 8 and 9. - - Inside a character class, \ followed by a digit is always either a literal - 8 or 9 or an octal number. */ - - case CHAR_1: case CHAR_2: case CHAR_3: case CHAR_4: case CHAR_5: - case CHAR_6: case CHAR_7: case CHAR_8: case CHAR_9: - - if (!isclass) - { - oldptr = ptr; - /* The integer range is limited by the machine's int representation. */ - s = (int)(c -CHAR_0); - overflow = FALSE; - while (IS_DIGIT(ptr[1])) - { - if (s > INT_MAX / 10 - 1) /* Integer overflow */ - { - overflow = TRUE; - break; - } - s = s * 10 + (int)(*(++ptr) - CHAR_0); - } - if (overflow) /* Integer overflow */ - { - while (IS_DIGIT(ptr[1])) - ptr++; - *errorcodeptr = ERR61; - break; - } - if (s < 8 || s <= bracount) /* Check for back reference */ - { - escape = -s; - break; - } - ptr = oldptr; /* Put the pointer back and fall through */ - } - - /* Handle a digit following \ when the number is not a back reference. If - the first digit is 8 or 9, Perl used to generate a binary zero byte and - then treat the digit as a following literal. At least by Perl 5.18 this - changed so as not to insert the binary zero. */ - - if ((c = *ptr) >= CHAR_8) break; - - /* Fall through with a digit less than 8 */ - - /* \0 always starts an octal number, but we may drop through to here with a - larger first octal digit. The original code used just to take the least - significant 8 bits of octal numbers (I think this is what early Perls used - to do). Nowadays we allow for larger numbers in UTF-8 mode and 16-bit mode, - but no more than 3 octal digits. */ - - case CHAR_0: - c -= CHAR_0; - while(i++ < 2 && ptr[1] >= CHAR_0 && ptr[1] <= CHAR_7) - c = c * 8 + *(++ptr) - CHAR_0; -#ifdef COMPILE_PCRE8 - if (!utf && c > 0xff) *errorcodeptr = ERR51; -#endif - break; - - /* \o is a relatively new Perl feature, supporting a more general way of - specifying character codes in octal. The only supported form is \o{ddd}. */ - - case CHAR_o: - if (ptr[1] != CHAR_LEFT_CURLY_BRACKET) *errorcodeptr = ERR81; else - if (ptr[2] == CHAR_RIGHT_CURLY_BRACKET) *errorcodeptr = ERR86; else - { - ptr += 2; - c = 0; - overflow = FALSE; - while (*ptr >= CHAR_0 && *ptr <= CHAR_7) - { - register pcre_uint32 cc = *ptr++; - if (c == 0 && cc == CHAR_0) continue; /* Leading zeroes */ -#ifdef COMPILE_PCRE32 - if (c >= 0x20000000l) { overflow = TRUE; break; } -#endif - c = (c << 3) + cc - CHAR_0 ; -#if defined COMPILE_PCRE8 - if (c > (utf ? 0x10ffffU : 0xffU)) { overflow = TRUE; break; } -#elif defined COMPILE_PCRE16 - if (c > (utf ? 0x10ffffU : 0xffffU)) { overflow = TRUE; break; } -#elif defined COMPILE_PCRE32 - if (utf && c > 0x10ffffU) { overflow = TRUE; break; } -#endif - } - if (overflow) - { - while (*ptr >= CHAR_0 && *ptr <= CHAR_7) ptr++; - *errorcodeptr = ERR34; - } - else if (*ptr == CHAR_RIGHT_CURLY_BRACKET) - { - if (utf && c >= 0xd800 && c <= 0xdfff) *errorcodeptr = ERR73; - } - else *errorcodeptr = ERR80; - } - break; - - /* \x is complicated. In JavaScript, \x must be followed by two hexadecimal - numbers. Otherwise it is a lowercase x letter. */ - - case CHAR_x: - if ((options & PCRE_JAVASCRIPT_COMPAT) != 0) - { - if (MAX_255(ptr[1]) && (digitab[ptr[1]] & ctype_xdigit) != 0 - && MAX_255(ptr[2]) && (digitab[ptr[2]] & ctype_xdigit) != 0) - { - c = 0; - for (i = 0; i < 2; ++i) - { - register pcre_uint32 cc = *(++ptr); -#ifndef EBCDIC /* ASCII/UTF-8 coding */ - if (cc >= CHAR_a) cc -= 32; /* Convert to upper case */ - c = (c << 4) + cc - ((cc < CHAR_A)? CHAR_0 : (CHAR_A - 10)); -#else /* EBCDIC coding */ - if (cc >= CHAR_a && cc <= CHAR_z) cc += 64; /* Convert to upper case */ - c = (c << 4) + cc - ((cc >= CHAR_0)? CHAR_0 : (CHAR_A - 10)); -#endif - } - } - } /* End JavaScript handling */ - - /* Handle \x in Perl's style. \x{ddd} is a character number which can be - greater than 0xff in utf or non-8bit mode, but only if the ddd are hex - digits. If not, { used to be treated as a data character. However, Perl - seems to read hex digits up to the first non-such, and ignore the rest, so - that, for example \x{zz} matches a binary zero. This seems crazy, so PCRE - now gives an error. */ - - else - { - if (ptr[1] == CHAR_LEFT_CURLY_BRACKET) - { - ptr += 2; - if (*ptr == CHAR_RIGHT_CURLY_BRACKET) - { - *errorcodeptr = ERR86; - break; - } - c = 0; - overflow = FALSE; - while (MAX_255(*ptr) && (digitab[*ptr] & ctype_xdigit) != 0) - { - register pcre_uint32 cc = *ptr++; - if (c == 0 && cc == CHAR_0) continue; /* Leading zeroes */ - -#ifdef COMPILE_PCRE32 - if (c >= 0x10000000l) { overflow = TRUE; break; } -#endif - -#ifndef EBCDIC /* ASCII/UTF-8 coding */ - if (cc >= CHAR_a) cc -= 32; /* Convert to upper case */ - c = (c << 4) + cc - ((cc < CHAR_A)? CHAR_0 : (CHAR_A - 10)); -#else /* EBCDIC coding */ - if (cc >= CHAR_a && cc <= CHAR_z) cc += 64; /* Convert to upper case */ - c = (c << 4) + cc - ((cc >= CHAR_0)? CHAR_0 : (CHAR_A - 10)); -#endif - -#if defined COMPILE_PCRE8 - if (c > (utf ? 0x10ffffU : 0xffU)) { overflow = TRUE; break; } -#elif defined COMPILE_PCRE16 - if (c > (utf ? 0x10ffffU : 0xffffU)) { overflow = TRUE; break; } -#elif defined COMPILE_PCRE32 - if (utf && c > 0x10ffffU) { overflow = TRUE; break; } -#endif - } - - if (overflow) - { - while (MAX_255(*ptr) && (digitab[*ptr] & ctype_xdigit) != 0) ptr++; - *errorcodeptr = ERR34; - } - - else if (*ptr == CHAR_RIGHT_CURLY_BRACKET) - { - if (utf && c >= 0xd800 && c <= 0xdfff) *errorcodeptr = ERR73; - } - - /* If the sequence of hex digits does not end with '}', give an error. - We used just to recognize this construct and fall through to the normal - \x handling, but nowadays Perl gives an error, which seems much more - sensible, so we do too. */ - - else *errorcodeptr = ERR79; - } /* End of \x{} processing */ - - /* Read a single-byte hex-defined char (up to two hex digits after \x) */ - - else - { - c = 0; - while (i++ < 2 && MAX_255(ptr[1]) && (digitab[ptr[1]] & ctype_xdigit) != 0) - { - pcre_uint32 cc; /* Some compilers don't like */ - cc = *(++ptr); /* ++ in initializers */ -#ifndef EBCDIC /* ASCII/UTF-8 coding */ - if (cc >= CHAR_a) cc -= 32; /* Convert to upper case */ - c = c * 16 + cc - ((cc < CHAR_A)? CHAR_0 : (CHAR_A - 10)); -#else /* EBCDIC coding */ - if (cc <= CHAR_z) cc += 64; /* Convert to upper case */ - c = c * 16 + cc - ((cc >= CHAR_0)? CHAR_0 : (CHAR_A - 10)); -#endif - } - } /* End of \xdd handling */ - } /* End of Perl-style \x handling */ - break; - - /* For \c, a following letter is upper-cased; then the 0x40 bit is flipped. - An error is given if the byte following \c is not an ASCII character. This - coding is ASCII-specific, but then the whole concept of \cx is - ASCII-specific. (However, an EBCDIC equivalent has now been added.) */ - - case CHAR_c: - c = *(++ptr); - if (c == CHAR_NULL) - { - *errorcodeptr = ERR2; - break; - } -#ifndef EBCDIC /* ASCII/UTF-8 coding */ - if (c > 127) /* Excludes all non-ASCII in either mode */ - { - *errorcodeptr = ERR68; - break; - } - if (c >= CHAR_a && c <= CHAR_z) c -= 32; - c ^= 0x40; -#else /* EBCDIC coding */ - if (c >= CHAR_a && c <= CHAR_z) c += 64; - if (c == CHAR_QUESTION_MARK) - c = ('\\' == 188 && '`' == 74)? 0x5f : 0xff; - else - { - for (i = 0; i < 32; i++) - { - if (c == ebcdic_escape_c[i]) break; - } - if (i < 32) c = i; else *errorcodeptr = ERR68; - } -#endif - break; - - /* PCRE_EXTRA enables extensions to Perl in the matter of escapes. Any - other alphanumeric following \ is an error if PCRE_EXTRA was set; - otherwise, for Perl compatibility, it is a literal. This code looks a bit - odd, but there used to be some cases other than the default, and there may - be again in future, so I haven't "optimized" it. */ - - default: - if ((options & PCRE_EXTRA) != 0) switch(c) - { - default: - *errorcodeptr = ERR3; - break; - } - break; - } - } - -/* Perl supports \N{name} for character names, as well as plain \N for "not -newline". PCRE does not support \N{name}. However, it does support -quantification such as \N{2,3}. */ - -if (escape == ESC_N && ptr[1] == CHAR_LEFT_CURLY_BRACKET && - !is_counted_repeat(ptr+2)) - *errorcodeptr = ERR37; - -/* If PCRE_UCP is set, we change the values for \d etc. */ - -if ((options & PCRE_UCP) != 0 && escape >= ESC_D && escape <= ESC_w) - escape += (ESC_DU - ESC_D); - -/* Set the pointer to the final character before returning. */ - -*ptrptr = ptr; -*chptr = c; -return escape; -} - - - -#ifdef SUPPORT_UCP -/************************************************* -* Handle \P and \p * -*************************************************/ - -/* This function is called after \P or \p has been encountered, provided that -PCRE is compiled with support for Unicode properties. On entry, ptrptr is -pointing at the P or p. On exit, it is pointing at the final character of the -escape sequence. - -Argument: - ptrptr points to the pattern position pointer - negptr points to a boolean that is set TRUE for negation else FALSE - ptypeptr points to an unsigned int that is set to the type value - pdataptr points to an unsigned int that is set to the detailed property value - errorcodeptr points to the error code variable - -Returns: TRUE if the type value was found, or FALSE for an invalid type -*/ - -static BOOL -get_ucp(const pcre_uchar **ptrptr, BOOL *negptr, unsigned int *ptypeptr, - unsigned int *pdataptr, int *errorcodeptr) -{ -pcre_uchar c; -int i, bot, top; -const pcre_uchar *ptr = *ptrptr; -pcre_uchar name[32]; - -c = *(++ptr); -if (c == CHAR_NULL) goto ERROR_RETURN; - -*negptr = FALSE; - -/* \P or \p can be followed by a name in {}, optionally preceded by ^ for -negation. */ - -if (c == CHAR_LEFT_CURLY_BRACKET) - { - if (ptr[1] == CHAR_CIRCUMFLEX_ACCENT) - { - *negptr = TRUE; - ptr++; - } - for (i = 0; i < (int)(sizeof(name) / sizeof(pcre_uchar)) - 1; i++) - { - c = *(++ptr); - if (c == CHAR_NULL) goto ERROR_RETURN; - if (c == CHAR_RIGHT_CURLY_BRACKET) break; - name[i] = c; - } - if (c != CHAR_RIGHT_CURLY_BRACKET) goto ERROR_RETURN; - name[i] = 0; - } - -/* Otherwise there is just one following character */ - -else - { - name[0] = c; - name[1] = 0; - } - -*ptrptr = ptr; - -/* Search for a recognized property name using binary chop */ - -bot = 0; -top = PRIV(utt_size); - -while (bot < top) - { - int r; - i = (bot + top) >> 1; - r = STRCMP_UC_C8(name, PRIV(utt_names) + PRIV(utt)[i].name_offset); - if (r == 0) - { - *ptypeptr = PRIV(utt)[i].type; - *pdataptr = PRIV(utt)[i].value; - return TRUE; - } - if (r > 0) bot = i + 1; else top = i; - } - -*errorcodeptr = ERR47; -*ptrptr = ptr; -return FALSE; - -ERROR_RETURN: -*errorcodeptr = ERR46; -*ptrptr = ptr; -return FALSE; -} -#endif - - - -/************************************************* -* Read repeat counts * -*************************************************/ - -/* Read an item of the form {n,m} and return the values. This is called only -after is_counted_repeat() has confirmed that a repeat-count quantifier exists, -so the syntax is guaranteed to be correct, but we need to check the values. - -Arguments: - p pointer to first char after '{' - minp pointer to int for min - maxp pointer to int for max - returned as -1 if no max - errorcodeptr points to error code variable - -Returns: pointer to '}' on success; - current ptr on error, with errorcodeptr set non-zero -*/ - -static const pcre_uchar * -read_repeat_counts(const pcre_uchar *p, int *minp, int *maxp, int *errorcodeptr) -{ -int min = 0; -int max = -1; - -while (IS_DIGIT(*p)) - { - min = min * 10 + (int)(*p++ - CHAR_0); - if (min > 65535) - { - *errorcodeptr = ERR5; - return p; - } - } - -if (*p == CHAR_RIGHT_CURLY_BRACKET) max = min; else - { - if (*(++p) != CHAR_RIGHT_CURLY_BRACKET) - { - max = 0; - while(IS_DIGIT(*p)) - { - max = max * 10 + (int)(*p++ - CHAR_0); - if (max > 65535) - { - *errorcodeptr = ERR5; - return p; - } - } - if (max < min) - { - *errorcodeptr = ERR4; - return p; - } - } - } - -*minp = min; -*maxp = max; -return p; -} - - - -/************************************************* -* Find first significant op code * -*************************************************/ - -/* This is called by several functions that scan a compiled expression looking -for a fixed first character, or an anchoring op code etc. It skips over things -that do not influence this. For some calls, it makes sense to skip negative -forward and all backward assertions, and also the \b assertion; for others it -does not. - -Arguments: - code pointer to the start of the group - skipassert TRUE if certain assertions are to be skipped - -Returns: pointer to the first significant opcode -*/ - -static const pcre_uchar* -first_significant_code(const pcre_uchar *code, BOOL skipassert) -{ -for (;;) - { - switch ((int)*code) - { - case OP_ASSERT_NOT: - case OP_ASSERTBACK: - case OP_ASSERTBACK_NOT: - if (!skipassert) return code; - do code += GET(code, 1); while (*code == OP_ALT); - code += PRIV(OP_lengths)[*code]; - break; - - case OP_WORD_BOUNDARY: - case OP_NOT_WORD_BOUNDARY: - if (!skipassert) return code; - /* Fall through */ - - case OP_CALLOUT: - case OP_CREF: - case OP_DNCREF: - case OP_RREF: - case OP_DNRREF: - case OP_DEF: - code += PRIV(OP_lengths)[*code]; - break; - - default: - return code; - } - } -/* Control never reaches here */ -} - - - -/************************************************* -* Find the fixed length of a branch * -*************************************************/ - -/* Scan a branch and compute the fixed length of subject that will match it, -if the length is fixed. This is needed for dealing with backward assertions. -In UTF8 mode, the result is in characters rather than bytes. The branch is -temporarily terminated with OP_END when this function is called. - -This function is called when a backward assertion is encountered, so that if it -fails, the error message can point to the correct place in the pattern. -However, we cannot do this when the assertion contains subroutine calls, -because they can be forward references. We solve this by remembering this case -and doing the check at the end; a flag specifies which mode we are running in. - -Arguments: - code points to the start of the pattern (the bracket) - utf TRUE in UTF-8 / UTF-16 / UTF-32 mode - atend TRUE if called when the pattern is complete - cd the "compile data" structure - recurses chain of recurse_check to catch mutual recursion - -Returns: the fixed length, - or -1 if there is no fixed length, - or -2 if \C was encountered (in UTF-8 mode only) - or -3 if an OP_RECURSE item was encountered and atend is FALSE - or -4 if an unknown opcode was encountered (internal error) -*/ - -static int -find_fixedlength(pcre_uchar *code, BOOL utf, BOOL atend, compile_data *cd, - recurse_check *recurses) -{ -int length = -1; -recurse_check this_recurse; -register int branchlength = 0; -register pcre_uchar *cc = code + 1 + LINK_SIZE; - -/* Scan along the opcodes for this branch. If we get to the end of the -branch, check the length against that of the other branches. */ - -for (;;) - { - int d; - pcre_uchar *ce, *cs; - register pcre_uchar op = *cc; - - switch (op) - { - /* We only need to continue for OP_CBRA (normal capturing bracket) and - OP_BRA (normal non-capturing bracket) because the other variants of these - opcodes are all concerned with unlimited repeated groups, which of course - are not of fixed length. */ - - case OP_CBRA: - case OP_BRA: - case OP_ONCE: - case OP_ONCE_NC: - case OP_COND: - d = find_fixedlength(cc + ((op == OP_CBRA)? IMM2_SIZE : 0), utf, atend, cd, - recurses); - if (d < 0) return d; - branchlength += d; - do cc += GET(cc, 1); while (*cc == OP_ALT); - cc += 1 + LINK_SIZE; - break; - - /* Reached end of a branch; if it's a ket it is the end of a nested call. - If it's ALT it is an alternation in a nested call. An ACCEPT is effectively - an ALT. If it is END it's the end of the outer call. All can be handled by - the same code. Note that we must not include the OP_KETRxxx opcodes here, - because they all imply an unlimited repeat. */ - - case OP_ALT: - case OP_KET: - case OP_END: - case OP_ACCEPT: - case OP_ASSERT_ACCEPT: - if (length < 0) length = branchlength; - else if (length != branchlength) return -1; - if (*cc != OP_ALT) return length; - cc += 1 + LINK_SIZE; - branchlength = 0; - break; - - /* A true recursion implies not fixed length, but a subroutine call may - be OK. If the subroutine is a forward reference, we can't deal with - it until the end of the pattern, so return -3. */ - - case OP_RECURSE: - if (!atend) return -3; - cs = ce = (pcre_uchar *)cd->start_code + GET(cc, 1); /* Start subpattern */ - do ce += GET(ce, 1); while (*ce == OP_ALT); /* End subpattern */ - if (cc > cs && cc < ce) return -1; /* Recursion */ - else /* Check for mutual recursion */ - { - recurse_check *r = recurses; - for (r = recurses; r != NULL; r = r->prev) if (r->group == cs) break; - if (r != NULL) return -1; /* Mutual recursion */ - } - this_recurse.prev = recurses; - this_recurse.group = cs; - d = find_fixedlength(cs + IMM2_SIZE, utf, atend, cd, &this_recurse); - if (d < 0) return d; - branchlength += d; - cc += 1 + LINK_SIZE; - break; - - /* Skip over assertive subpatterns */ - - case OP_ASSERT: - case OP_ASSERT_NOT: - case OP_ASSERTBACK: - case OP_ASSERTBACK_NOT: - do cc += GET(cc, 1); while (*cc == OP_ALT); - cc += 1 + LINK_SIZE; - break; - - /* Skip over things that don't match chars */ - - case OP_MARK: - case OP_PRUNE_ARG: - case OP_SKIP_ARG: - case OP_THEN_ARG: - cc += cc[1] + PRIV(OP_lengths)[*cc]; - break; - - case OP_CALLOUT: - case OP_CIRC: - case OP_CIRCM: - case OP_CLOSE: - case OP_COMMIT: - case OP_CREF: - case OP_DEF: - case OP_DNCREF: - case OP_DNRREF: - case OP_DOLL: - case OP_DOLLM: - case OP_EOD: - case OP_EODN: - case OP_FAIL: - case OP_NOT_WORD_BOUNDARY: - case OP_PRUNE: - case OP_REVERSE: - case OP_RREF: - case OP_SET_SOM: - case OP_SKIP: - case OP_SOD: - case OP_SOM: - case OP_THEN: - case OP_WORD_BOUNDARY: - cc += PRIV(OP_lengths)[*cc]; - break; - - /* Handle literal characters */ - - case OP_CHAR: - case OP_CHARI: - case OP_NOT: - case OP_NOTI: - branchlength++; - cc += 2; -#ifdef SUPPORT_UTF - if (utf && HAS_EXTRALEN(cc[-1])) cc += GET_EXTRALEN(cc[-1]); -#endif - break; - - /* Handle exact repetitions. The count is already in characters, but we - need to skip over a multibyte character in UTF8 mode. */ - - case OP_EXACT: - case OP_EXACTI: - case OP_NOTEXACT: - case OP_NOTEXACTI: - branchlength += (int)GET2(cc,1); - cc += 2 + IMM2_SIZE; -#ifdef SUPPORT_UTF - if (utf && HAS_EXTRALEN(cc[-1])) cc += GET_EXTRALEN(cc[-1]); -#endif - break; - - case OP_TYPEEXACT: - branchlength += GET2(cc,1); - if (cc[1 + IMM2_SIZE] == OP_PROP || cc[1 + IMM2_SIZE] == OP_NOTPROP) - cc += 2; - cc += 1 + IMM2_SIZE + 1; - break; - - /* Handle single-char matchers */ - - case OP_PROP: - case OP_NOTPROP: - cc += 2; - /* Fall through */ - - case OP_HSPACE: - case OP_VSPACE: - case OP_NOT_HSPACE: - case OP_NOT_VSPACE: - case OP_NOT_DIGIT: - case OP_DIGIT: - case OP_NOT_WHITESPACE: - case OP_WHITESPACE: - case OP_NOT_WORDCHAR: - case OP_WORDCHAR: - case OP_ANY: - case OP_ALLANY: - branchlength++; - cc++; - break; - - /* The single-byte matcher isn't allowed. This only happens in UTF-8 mode; - otherwise \C is coded as OP_ALLANY. */ - - case OP_ANYBYTE: - return -2; - - /* Check a class for variable quantification */ - - case OP_CLASS: - case OP_NCLASS: -#if defined SUPPORT_UTF || defined COMPILE_PCRE16 || defined COMPILE_PCRE32 - case OP_XCLASS: - /* The original code caused an unsigned overflow in 64 bit systems, - so now we use a conditional statement. */ - if (op == OP_XCLASS) - cc += GET(cc, 1); - else - cc += PRIV(OP_lengths)[OP_CLASS]; -#else - cc += PRIV(OP_lengths)[OP_CLASS]; -#endif - - switch (*cc) - { - case OP_CRSTAR: - case OP_CRMINSTAR: - case OP_CRPLUS: - case OP_CRMINPLUS: - case OP_CRQUERY: - case OP_CRMINQUERY: - case OP_CRPOSSTAR: - case OP_CRPOSPLUS: - case OP_CRPOSQUERY: - return -1; - - case OP_CRRANGE: - case OP_CRMINRANGE: - case OP_CRPOSRANGE: - if (GET2(cc,1) != GET2(cc,1+IMM2_SIZE)) return -1; - branchlength += (int)GET2(cc,1); - cc += 1 + 2 * IMM2_SIZE; - break; - - default: - branchlength++; - } - break; - - /* Anything else is variable length */ - - case OP_ANYNL: - case OP_BRAMINZERO: - case OP_BRAPOS: - case OP_BRAPOSZERO: - case OP_BRAZERO: - case OP_CBRAPOS: - case OP_EXTUNI: - case OP_KETRMAX: - case OP_KETRMIN: - case OP_KETRPOS: - case OP_MINPLUS: - case OP_MINPLUSI: - case OP_MINQUERY: - case OP_MINQUERYI: - case OP_MINSTAR: - case OP_MINSTARI: - case OP_MINUPTO: - case OP_MINUPTOI: - case OP_NOTMINPLUS: - case OP_NOTMINPLUSI: - case OP_NOTMINQUERY: - case OP_NOTMINQUERYI: - case OP_NOTMINSTAR: - case OP_NOTMINSTARI: - case OP_NOTMINUPTO: - case OP_NOTMINUPTOI: - case OP_NOTPLUS: - case OP_NOTPLUSI: - case OP_NOTPOSPLUS: - case OP_NOTPOSPLUSI: - case OP_NOTPOSQUERY: - case OP_NOTPOSQUERYI: - case OP_NOTPOSSTAR: - case OP_NOTPOSSTARI: - case OP_NOTPOSUPTO: - case OP_NOTPOSUPTOI: - case OP_NOTQUERY: - case OP_NOTQUERYI: - case OP_NOTSTAR: - case OP_NOTSTARI: - case OP_NOTUPTO: - case OP_NOTUPTOI: - case OP_PLUS: - case OP_PLUSI: - case OP_POSPLUS: - case OP_POSPLUSI: - case OP_POSQUERY: - case OP_POSQUERYI: - case OP_POSSTAR: - case OP_POSSTARI: - case OP_POSUPTO: - case OP_POSUPTOI: - case OP_QUERY: - case OP_QUERYI: - case OP_REF: - case OP_REFI: - case OP_DNREF: - case OP_DNREFI: - case OP_SBRA: - case OP_SBRAPOS: - case OP_SCBRA: - case OP_SCBRAPOS: - case OP_SCOND: - case OP_SKIPZERO: - case OP_STAR: - case OP_STARI: - case OP_TYPEMINPLUS: - case OP_TYPEMINQUERY: - case OP_TYPEMINSTAR: - case OP_TYPEMINUPTO: - case OP_TYPEPLUS: - case OP_TYPEPOSPLUS: - case OP_TYPEPOSQUERY: - case OP_TYPEPOSSTAR: - case OP_TYPEPOSUPTO: - case OP_TYPEQUERY: - case OP_TYPESTAR: - case OP_TYPEUPTO: - case OP_UPTO: - case OP_UPTOI: - return -1; - - /* Catch unrecognized opcodes so that when new ones are added they - are not forgotten, as has happened in the past. */ - - default: - return -4; - } - } -/* Control never gets here */ -} - - - -/************************************************* -* Scan compiled regex for specific bracket * -*************************************************/ - -/* This little function scans through a compiled pattern until it finds a -capturing bracket with the given number, or, if the number is negative, an -instance of OP_REVERSE for a lookbehind. The function is global in the C sense -so that it can be called from pcre_study() when finding the minimum matching -length. - -Arguments: - code points to start of expression - utf TRUE in UTF-8 / UTF-16 / UTF-32 mode - number the required bracket number or negative to find a lookbehind - -Returns: pointer to the opcode for the bracket, or NULL if not found -*/ - -const pcre_uchar * -PRIV(find_bracket)(const pcre_uchar *code, BOOL utf, int number) -{ -for (;;) - { - register pcre_uchar c = *code; - - if (c == OP_END) return NULL; - - /* XCLASS is used for classes that cannot be represented just by a bit - map. This includes negated single high-valued characters. The length in - the table is zero; the actual length is stored in the compiled code. */ - - if (c == OP_XCLASS) code += GET(code, 1); - - /* Handle recursion */ - - else if (c == OP_REVERSE) - { - if (number < 0) return (pcre_uchar *)code; - code += PRIV(OP_lengths)[c]; - } - - /* Handle capturing bracket */ - - else if (c == OP_CBRA || c == OP_SCBRA || - c == OP_CBRAPOS || c == OP_SCBRAPOS) - { - int n = (int)GET2(code, 1+LINK_SIZE); - if (n == number) return (pcre_uchar *)code; - code += PRIV(OP_lengths)[c]; - } - - /* Otherwise, we can get the item's length from the table, except that for - repeated character types, we have to test for \p and \P, which have an extra - two bytes of parameters, and for MARK/PRUNE/SKIP/THEN with an argument, we - must add in its length. */ - - else - { - switch(c) - { - case OP_TYPESTAR: - case OP_TYPEMINSTAR: - case OP_TYPEPLUS: - case OP_TYPEMINPLUS: - case OP_TYPEQUERY: - case OP_TYPEMINQUERY: - case OP_TYPEPOSSTAR: - case OP_TYPEPOSPLUS: - case OP_TYPEPOSQUERY: - if (code[1] == OP_PROP || code[1] == OP_NOTPROP) code += 2; - break; - - case OP_TYPEUPTO: - case OP_TYPEMINUPTO: - case OP_TYPEEXACT: - case OP_TYPEPOSUPTO: - if (code[1 + IMM2_SIZE] == OP_PROP || code[1 + IMM2_SIZE] == OP_NOTPROP) - code += 2; - break; - - case OP_MARK: - case OP_PRUNE_ARG: - case OP_SKIP_ARG: - case OP_THEN_ARG: - code += code[1]; - break; - } - - /* Add in the fixed length from the table */ - - code += PRIV(OP_lengths)[c]; - - /* In UTF-8 mode, opcodes that are followed by a character may be followed by - a multi-byte character. The length in the table is a minimum, so we have to - arrange to skip the extra bytes. */ - -#if defined SUPPORT_UTF && !defined COMPILE_PCRE32 - if (utf) switch(c) - { - case OP_CHAR: - case OP_CHARI: - case OP_NOT: - case OP_NOTI: - case OP_EXACT: - case OP_EXACTI: - case OP_NOTEXACT: - case OP_NOTEXACTI: - case OP_UPTO: - case OP_UPTOI: - case OP_NOTUPTO: - case OP_NOTUPTOI: - case OP_MINUPTO: - case OP_MINUPTOI: - case OP_NOTMINUPTO: - case OP_NOTMINUPTOI: - case OP_POSUPTO: - case OP_POSUPTOI: - case OP_NOTPOSUPTO: - case OP_NOTPOSUPTOI: - case OP_STAR: - case OP_STARI: - case OP_NOTSTAR: - case OP_NOTSTARI: - case OP_MINSTAR: - case OP_MINSTARI: - case OP_NOTMINSTAR: - case OP_NOTMINSTARI: - case OP_POSSTAR: - case OP_POSSTARI: - case OP_NOTPOSSTAR: - case OP_NOTPOSSTARI: - case OP_PLUS: - case OP_PLUSI: - case OP_NOTPLUS: - case OP_NOTPLUSI: - case OP_MINPLUS: - case OP_MINPLUSI: - case OP_NOTMINPLUS: - case OP_NOTMINPLUSI: - case OP_POSPLUS: - case OP_POSPLUSI: - case OP_NOTPOSPLUS: - case OP_NOTPOSPLUSI: - case OP_QUERY: - case OP_QUERYI: - case OP_NOTQUERY: - case OP_NOTQUERYI: - case OP_MINQUERY: - case OP_MINQUERYI: - case OP_NOTMINQUERY: - case OP_NOTMINQUERYI: - case OP_POSQUERY: - case OP_POSQUERYI: - case OP_NOTPOSQUERY: - case OP_NOTPOSQUERYI: - if (HAS_EXTRALEN(code[-1])) code += GET_EXTRALEN(code[-1]); - break; - } -#else - (void)(utf); /* Keep compiler happy by referencing function argument */ -#endif - } - } -} - - - -/************************************************* -* Scan compiled regex for recursion reference * -*************************************************/ - -/* This little function scans through a compiled pattern until it finds an -instance of OP_RECURSE. - -Arguments: - code points to start of expression - utf TRUE in UTF-8 / UTF-16 / UTF-32 mode - -Returns: pointer to the opcode for OP_RECURSE, or NULL if not found -*/ - -static const pcre_uchar * -find_recurse(const pcre_uchar *code, BOOL utf) -{ -for (;;) - { - register pcre_uchar c = *code; - if (c == OP_END) return NULL; - if (c == OP_RECURSE) return code; - - /* XCLASS is used for classes that cannot be represented just by a bit - map. This includes negated single high-valued characters. The length in - the table is zero; the actual length is stored in the compiled code. */ - - if (c == OP_XCLASS) code += GET(code, 1); - - /* Otherwise, we can get the item's length from the table, except that for - repeated character types, we have to test for \p and \P, which have an extra - two bytes of parameters, and for MARK/PRUNE/SKIP/THEN with an argument, we - must add in its length. */ - - else - { - switch(c) - { - case OP_TYPESTAR: - case OP_TYPEMINSTAR: - case OP_TYPEPLUS: - case OP_TYPEMINPLUS: - case OP_TYPEQUERY: - case OP_TYPEMINQUERY: - case OP_TYPEPOSSTAR: - case OP_TYPEPOSPLUS: - case OP_TYPEPOSQUERY: - if (code[1] == OP_PROP || code[1] == OP_NOTPROP) code += 2; - break; - - case OP_TYPEPOSUPTO: - case OP_TYPEUPTO: - case OP_TYPEMINUPTO: - case OP_TYPEEXACT: - if (code[1 + IMM2_SIZE] == OP_PROP || code[1 + IMM2_SIZE] == OP_NOTPROP) - code += 2; - break; - - case OP_MARK: - case OP_PRUNE_ARG: - case OP_SKIP_ARG: - case OP_THEN_ARG: - code += code[1]; - break; - } - - /* Add in the fixed length from the table */ - - code += PRIV(OP_lengths)[c]; - - /* In UTF-8 mode, opcodes that are followed by a character may be followed - by a multi-byte character. The length in the table is a minimum, so we have - to arrange to skip the extra bytes. */ - -#if defined SUPPORT_UTF && !defined COMPILE_PCRE32 - if (utf) switch(c) - { - case OP_CHAR: - case OP_CHARI: - case OP_NOT: - case OP_NOTI: - case OP_EXACT: - case OP_EXACTI: - case OP_NOTEXACT: - case OP_NOTEXACTI: - case OP_UPTO: - case OP_UPTOI: - case OP_NOTUPTO: - case OP_NOTUPTOI: - case OP_MINUPTO: - case OP_MINUPTOI: - case OP_NOTMINUPTO: - case OP_NOTMINUPTOI: - case OP_POSUPTO: - case OP_POSUPTOI: - case OP_NOTPOSUPTO: - case OP_NOTPOSUPTOI: - case OP_STAR: - case OP_STARI: - case OP_NOTSTAR: - case OP_NOTSTARI: - case OP_MINSTAR: - case OP_MINSTARI: - case OP_NOTMINSTAR: - case OP_NOTMINSTARI: - case OP_POSSTAR: - case OP_POSSTARI: - case OP_NOTPOSSTAR: - case OP_NOTPOSSTARI: - case OP_PLUS: - case OP_PLUSI: - case OP_NOTPLUS: - case OP_NOTPLUSI: - case OP_MINPLUS: - case OP_MINPLUSI: - case OP_NOTMINPLUS: - case OP_NOTMINPLUSI: - case OP_POSPLUS: - case OP_POSPLUSI: - case OP_NOTPOSPLUS: - case OP_NOTPOSPLUSI: - case OP_QUERY: - case OP_QUERYI: - case OP_NOTQUERY: - case OP_NOTQUERYI: - case OP_MINQUERY: - case OP_MINQUERYI: - case OP_NOTMINQUERY: - case OP_NOTMINQUERYI: - case OP_POSQUERY: - case OP_POSQUERYI: - case OP_NOTPOSQUERY: - case OP_NOTPOSQUERYI: - if (HAS_EXTRALEN(code[-1])) code += GET_EXTRALEN(code[-1]); - break; - } -#else - (void)(utf); /* Keep compiler happy by referencing function argument */ -#endif - } - } -} - - - -/************************************************* -* Scan compiled branch for non-emptiness * -*************************************************/ - -/* This function scans through a branch of a compiled pattern to see whether it -can match the empty string or not. It is called from could_be_empty() -below and from compile_branch() when checking for an unlimited repeat of a -group that can match nothing. Note that first_significant_code() skips over -backward and negative forward assertions when its final argument is TRUE. If we -hit an unclosed bracket, we return "empty" - this means we've struck an inner -bracket whose current branch will already have been scanned. - -Arguments: - code points to start of search - endcode points to where to stop - utf TRUE if in UTF-8 / UTF-16 / UTF-32 mode - cd contains pointers to tables etc. - recurses chain of recurse_check to catch mutual recursion - -Returns: TRUE if what is matched could be empty -*/ - -static BOOL -could_be_empty_branch(const pcre_uchar *code, const pcre_uchar *endcode, - BOOL utf, compile_data *cd, recurse_check *recurses) -{ -register pcre_uchar c; -recurse_check this_recurse; - -for (code = first_significant_code(code + PRIV(OP_lengths)[*code], TRUE); - code < endcode; - code = first_significant_code(code + PRIV(OP_lengths)[c], TRUE)) - { - const pcre_uchar *ccode; - - c = *code; - - /* Skip over forward assertions; the other assertions are skipped by - first_significant_code() with a TRUE final argument. */ - - if (c == OP_ASSERT) - { - do code += GET(code, 1); while (*code == OP_ALT); - c = *code; - continue; - } - - /* For a recursion/subroutine call, if its end has been reached, which - implies a backward reference subroutine call, we can scan it. If it's a - forward reference subroutine call, we can't. To detect forward reference - we have to scan up the list that is kept in the workspace. This function is - called only when doing the real compile, not during the pre-compile that - measures the size of the compiled pattern. */ - - if (c == OP_RECURSE) - { - const pcre_uchar *scode = cd->start_code + GET(code, 1); - const pcre_uchar *endgroup = scode; - BOOL empty_branch; - - /* Test for forward reference or uncompleted reference. This is disabled - when called to scan a completed pattern by setting cd->start_workspace to - NULL. */ - - if (cd->start_workspace != NULL) - { - const pcre_uchar *tcode; - for (tcode = cd->start_workspace; tcode < cd->hwm; tcode += LINK_SIZE) - if ((int)GET(tcode, 0) == (int)(code + 1 - cd->start_code)) return TRUE; - if (GET(scode, 1) == 0) return TRUE; /* Unclosed */ - } - - /* If the reference is to a completed group, we need to detect whether this - is a recursive call, as otherwise there will be an infinite loop. If it is - a recursion, just skip over it. Simple recursions are easily detected. For - mutual recursions we keep a chain on the stack. */ - - do endgroup += GET(endgroup, 1); while (*endgroup == OP_ALT); - if (code >= scode && code <= endgroup) continue; /* Simple recursion */ - else - { - recurse_check *r = recurses; - for (r = recurses; r != NULL; r = r->prev) - if (r->group == scode) break; - if (r != NULL) continue; /* Mutual recursion */ - } - - /* Completed reference; scan the referenced group, remembering it on the - stack chain to detect mutual recursions. */ - - empty_branch = FALSE; - this_recurse.prev = recurses; - this_recurse.group = scode; - - do - { - if (could_be_empty_branch(scode, endcode, utf, cd, &this_recurse)) - { - empty_branch = TRUE; - break; - } - scode += GET(scode, 1); - } - while (*scode == OP_ALT); - - if (!empty_branch) return FALSE; /* All branches are non-empty */ - continue; - } - - /* Groups with zero repeats can of course be empty; skip them. */ - - if (c == OP_BRAZERO || c == OP_BRAMINZERO || c == OP_SKIPZERO || - c == OP_BRAPOSZERO) - { - code += PRIV(OP_lengths)[c]; - do code += GET(code, 1); while (*code == OP_ALT); - c = *code; - continue; - } - - /* A nested group that is already marked as "could be empty" can just be - skipped. */ - - if (c == OP_SBRA || c == OP_SBRAPOS || - c == OP_SCBRA || c == OP_SCBRAPOS) - { - do code += GET(code, 1); while (*code == OP_ALT); - c = *code; - continue; - } - - /* For other groups, scan the branches. */ - - if (c == OP_BRA || c == OP_BRAPOS || - c == OP_CBRA || c == OP_CBRAPOS || - c == OP_ONCE || c == OP_ONCE_NC || - c == OP_COND || c == OP_SCOND) - { - BOOL empty_branch; - if (GET(code, 1) == 0) return TRUE; /* Hit unclosed bracket */ - - /* If a conditional group has only one branch, there is a second, implied, - empty branch, so just skip over the conditional, because it could be empty. - Otherwise, scan the individual branches of the group. */ - - if (c == OP_COND && code[GET(code, 1)] != OP_ALT) - code += GET(code, 1); - else - { - empty_branch = FALSE; - do - { - if (!empty_branch && could_be_empty_branch(code, endcode, utf, cd, - recurses)) empty_branch = TRUE; - code += GET(code, 1); - } - while (*code == OP_ALT); - if (!empty_branch) return FALSE; /* All branches are non-empty */ - } - - c = *code; - continue; - } - - /* Handle the other opcodes */ - - switch (c) - { - /* Check for quantifiers after a class. XCLASS is used for classes that - cannot be represented just by a bit map. This includes negated single - high-valued characters. The length in PRIV(OP_lengths)[] is zero; the - actual length is stored in the compiled code, so we must update "code" - here. */ - -#if defined SUPPORT_UTF || !defined COMPILE_PCRE8 - case OP_XCLASS: - ccode = code += GET(code, 1); - goto CHECK_CLASS_REPEAT; -#endif - - case OP_CLASS: - case OP_NCLASS: - ccode = code + PRIV(OP_lengths)[OP_CLASS]; - -#if defined SUPPORT_UTF || !defined COMPILE_PCRE8 - CHECK_CLASS_REPEAT: -#endif - - switch (*ccode) - { - case OP_CRSTAR: /* These could be empty; continue */ - case OP_CRMINSTAR: - case OP_CRQUERY: - case OP_CRMINQUERY: - case OP_CRPOSSTAR: - case OP_CRPOSQUERY: - break; - - default: /* Non-repeat => class must match */ - case OP_CRPLUS: /* These repeats aren't empty */ - case OP_CRMINPLUS: - case OP_CRPOSPLUS: - return FALSE; - - case OP_CRRANGE: - case OP_CRMINRANGE: - case OP_CRPOSRANGE: - if (GET2(ccode, 1) > 0) return FALSE; /* Minimum > 0 */ - break; - } - break; - - /* Opcodes that must match a character */ - - case OP_ANY: - case OP_ALLANY: - case OP_ANYBYTE: - - case OP_PROP: - case OP_NOTPROP: - case OP_ANYNL: - - case OP_NOT_HSPACE: - case OP_HSPACE: - case OP_NOT_VSPACE: - case OP_VSPACE: - case OP_EXTUNI: - - case OP_NOT_DIGIT: - case OP_DIGIT: - case OP_NOT_WHITESPACE: - case OP_WHITESPACE: - case OP_NOT_WORDCHAR: - case OP_WORDCHAR: - - case OP_CHAR: - case OP_CHARI: - case OP_NOT: - case OP_NOTI: - - case OP_PLUS: - case OP_PLUSI: - case OP_MINPLUS: - case OP_MINPLUSI: - - case OP_NOTPLUS: - case OP_NOTPLUSI: - case OP_NOTMINPLUS: - case OP_NOTMINPLUSI: - - case OP_POSPLUS: - case OP_POSPLUSI: - case OP_NOTPOSPLUS: - case OP_NOTPOSPLUSI: - - case OP_EXACT: - case OP_EXACTI: - case OP_NOTEXACT: - case OP_NOTEXACTI: - - case OP_TYPEPLUS: - case OP_TYPEMINPLUS: - case OP_TYPEPOSPLUS: - case OP_TYPEEXACT: - - return FALSE; - - /* These are going to continue, as they may be empty, but we have to - fudge the length for the \p and \P cases. */ - - case OP_TYPESTAR: - case OP_TYPEMINSTAR: - case OP_TYPEPOSSTAR: - case OP_TYPEQUERY: - case OP_TYPEMINQUERY: - case OP_TYPEPOSQUERY: - if (code[1] == OP_PROP || code[1] == OP_NOTPROP) code += 2; - break; - - /* Same for these */ - - case OP_TYPEUPTO: - case OP_TYPEMINUPTO: - case OP_TYPEPOSUPTO: - if (code[1 + IMM2_SIZE] == OP_PROP || code[1 + IMM2_SIZE] == OP_NOTPROP) - code += 2; - break; - - /* End of branch */ - - case OP_KET: - case OP_KETRMAX: - case OP_KETRMIN: - case OP_KETRPOS: - case OP_ALT: - return TRUE; - - /* In UTF-8 mode, STAR, MINSTAR, POSSTAR, QUERY, MINQUERY, POSQUERY, UPTO, - MINUPTO, and POSUPTO and their caseless and negative versions may be - followed by a multibyte character. */ - -#if defined SUPPORT_UTF && !defined COMPILE_PCRE32 - case OP_STAR: - case OP_STARI: - case OP_NOTSTAR: - case OP_NOTSTARI: - - case OP_MINSTAR: - case OP_MINSTARI: - case OP_NOTMINSTAR: - case OP_NOTMINSTARI: - - case OP_POSSTAR: - case OP_POSSTARI: - case OP_NOTPOSSTAR: - case OP_NOTPOSSTARI: - - case OP_QUERY: - case OP_QUERYI: - case OP_NOTQUERY: - case OP_NOTQUERYI: - - case OP_MINQUERY: - case OP_MINQUERYI: - case OP_NOTMINQUERY: - case OP_NOTMINQUERYI: - - case OP_POSQUERY: - case OP_POSQUERYI: - case OP_NOTPOSQUERY: - case OP_NOTPOSQUERYI: - - if (utf && HAS_EXTRALEN(code[1])) code += GET_EXTRALEN(code[1]); - break; - - case OP_UPTO: - case OP_UPTOI: - case OP_NOTUPTO: - case OP_NOTUPTOI: - - case OP_MINUPTO: - case OP_MINUPTOI: - case OP_NOTMINUPTO: - case OP_NOTMINUPTOI: - - case OP_POSUPTO: - case OP_POSUPTOI: - case OP_NOTPOSUPTO: - case OP_NOTPOSUPTOI: - - if (utf && HAS_EXTRALEN(code[1 + IMM2_SIZE])) code += GET_EXTRALEN(code[1 + IMM2_SIZE]); - break; -#endif - - /* MARK, and PRUNE/SKIP/THEN with an argument must skip over the argument - string. */ - - case OP_MARK: - case OP_PRUNE_ARG: - case OP_SKIP_ARG: - case OP_THEN_ARG: - code += code[1]; - break; - - /* None of the remaining opcodes are required to match a character. */ - - default: - break; - } - } - -return TRUE; -} - - - -/************************************************* -* Scan compiled regex for non-emptiness * -*************************************************/ - -/* This function is called to check for left recursive calls. We want to check -the current branch of the current pattern to see if it could match the empty -string. If it could, we must look outwards for branches at other levels, -stopping when we pass beyond the bracket which is the subject of the recursion. -This function is called only during the real compile, not during the -pre-compile. - -Arguments: - code points to start of the recursion - endcode points to where to stop (current RECURSE item) - bcptr points to the chain of current (unclosed) branch starts - utf TRUE if in UTF-8 / UTF-16 / UTF-32 mode - cd pointers to tables etc - -Returns: TRUE if what is matched could be empty -*/ - -static BOOL -could_be_empty(const pcre_uchar *code, const pcre_uchar *endcode, - branch_chain *bcptr, BOOL utf, compile_data *cd) -{ -while (bcptr != NULL && bcptr->current_branch >= code) - { - if (!could_be_empty_branch(bcptr->current_branch, endcode, utf, cd, NULL)) - return FALSE; - bcptr = bcptr->outer; - } -return TRUE; -} - - - -/************************************************* -* Base opcode of repeated opcodes * -*************************************************/ - -/* Returns the base opcode for repeated single character type opcodes. If the -opcode is not a repeated character type, it returns with the original value. - -Arguments: c opcode -Returns: base opcode for the type -*/ - -static pcre_uchar -get_repeat_base(pcre_uchar c) -{ -return (c > OP_TYPEPOSUPTO)? c : - (c >= OP_TYPESTAR)? OP_TYPESTAR : - (c >= OP_NOTSTARI)? OP_NOTSTARI : - (c >= OP_NOTSTAR)? OP_NOTSTAR : - (c >= OP_STARI)? OP_STARI : - OP_STAR; -} - - - -#ifdef SUPPORT_UCP -/************************************************* -* Check a character and a property * -*************************************************/ - -/* This function is called by check_auto_possessive() when a property item -is adjacent to a fixed character. - -Arguments: - c the character - ptype the property type - pdata the data for the type - negated TRUE if it's a negated property (\P or \p{^) - -Returns: TRUE if auto-possessifying is OK -*/ - -static BOOL -check_char_prop(pcre_uint32 c, unsigned int ptype, unsigned int pdata, - BOOL negated) -{ -const pcre_uint32 *p; -const ucd_record *prop = GET_UCD(c); - -switch(ptype) - { - case PT_LAMP: - return (prop->chartype == ucp_Lu || - prop->chartype == ucp_Ll || - prop->chartype == ucp_Lt) == negated; - - case PT_GC: - return (pdata == PRIV(ucp_gentype)[prop->chartype]) == negated; - - case PT_PC: - return (pdata == prop->chartype) == negated; - - case PT_SC: - return (pdata == prop->script) == negated; - - /* These are specials */ - - case PT_ALNUM: - return (PRIV(ucp_gentype)[prop->chartype] == ucp_L || - PRIV(ucp_gentype)[prop->chartype] == ucp_N) == negated; - - /* Perl space used to exclude VT, but from Perl 5.18 it is included, which - means that Perl space and POSIX space are now identical. PCRE was changed - at release 8.34. */ - - case PT_SPACE: /* Perl space */ - case PT_PXSPACE: /* POSIX space */ - switch(c) - { - HSPACE_CASES: - VSPACE_CASES: - return negated; - - default: - return (PRIV(ucp_gentype)[prop->chartype] == ucp_Z) == negated; - } - break; /* Control never reaches here */ - - case PT_WORD: - return (PRIV(ucp_gentype)[prop->chartype] == ucp_L || - PRIV(ucp_gentype)[prop->chartype] == ucp_N || - c == CHAR_UNDERSCORE) == negated; - - case PT_CLIST: - p = PRIV(ucd_caseless_sets) + prop->caseset; - for (;;) - { - if (c < *p) return !negated; - if (c == *p++) return negated; - } - break; /* Control never reaches here */ - } - -return FALSE; -} -#endif /* SUPPORT_UCP */ - - - -/************************************************* -* Fill the character property list * -*************************************************/ - -/* Checks whether the code points to an opcode that can take part in auto- -possessification, and if so, fills a list with its properties. - -Arguments: - code points to start of expression - utf TRUE if in UTF-8 / UTF-16 / UTF-32 mode - fcc points to case-flipping table - list points to output list - list[0] will be filled with the opcode - list[1] will be non-zero if this opcode - can match an empty character string - list[2..7] depends on the opcode - -Returns: points to the start of the next opcode if *code is accepted - NULL if *code is not accepted -*/ - -static const pcre_uchar * -get_chr_property_list(const pcre_uchar *code, BOOL utf, - const pcre_uint8 *fcc, pcre_uint32 *list) -{ -pcre_uchar c = *code; -pcre_uchar base; -const pcre_uchar *end; -pcre_uint32 chr; - -#ifdef SUPPORT_UCP -pcre_uint32 *clist_dest; -const pcre_uint32 *clist_src; -#else -utf = utf; /* Suppress "unused parameter" compiler warning */ -#endif - -list[0] = c; -list[1] = FALSE; -code++; - -if (c >= OP_STAR && c <= OP_TYPEPOSUPTO) - { - base = get_repeat_base(c); - c -= (base - OP_STAR); - - if (c == OP_UPTO || c == OP_MINUPTO || c == OP_EXACT || c == OP_POSUPTO) - code += IMM2_SIZE; - - list[1] = (c != OP_PLUS && c != OP_MINPLUS && c != OP_EXACT && c != OP_POSPLUS); - - switch(base) - { - case OP_STAR: - list[0] = OP_CHAR; - break; - - case OP_STARI: - list[0] = OP_CHARI; - break; - - case OP_NOTSTAR: - list[0] = OP_NOT; - break; - - case OP_NOTSTARI: - list[0] = OP_NOTI; - break; - - case OP_TYPESTAR: - list[0] = *code; - code++; - break; - } - c = list[0]; - } - -switch(c) - { - case OP_NOT_DIGIT: - case OP_DIGIT: - case OP_NOT_WHITESPACE: - case OP_WHITESPACE: - case OP_NOT_WORDCHAR: - case OP_WORDCHAR: - case OP_ANY: - case OP_ALLANY: - case OP_ANYNL: - case OP_NOT_HSPACE: - case OP_HSPACE: - case OP_NOT_VSPACE: - case OP_VSPACE: - case OP_EXTUNI: - case OP_EODN: - case OP_EOD: - case OP_DOLL: - case OP_DOLLM: - return code; - - case OP_CHAR: - case OP_NOT: - GETCHARINCTEST(chr, code); - list[2] = chr; - list[3] = NOTACHAR; - return code; - - case OP_CHARI: - case OP_NOTI: - list[0] = (c == OP_CHARI) ? OP_CHAR : OP_NOT; - GETCHARINCTEST(chr, code); - list[2] = chr; - -#ifdef SUPPORT_UCP - if (chr < 128 || (chr < 256 && !utf)) - list[3] = fcc[chr]; - else - list[3] = UCD_OTHERCASE(chr); -#elif defined SUPPORT_UTF || !defined COMPILE_PCRE8 - list[3] = (chr < 256) ? fcc[chr] : chr; -#else - list[3] = fcc[chr]; -#endif - - /* The othercase might be the same value. */ - - if (chr == list[3]) - list[3] = NOTACHAR; - else - list[4] = NOTACHAR; - return code; - -#ifdef SUPPORT_UCP - case OP_PROP: - case OP_NOTPROP: - if (code[0] != PT_CLIST) - { - list[2] = code[0]; - list[3] = code[1]; - return code + 2; - } - - /* Convert only if we have enough space. */ - - clist_src = PRIV(ucd_caseless_sets) + code[1]; - clist_dest = list + 2; - code += 2; - - do { - if (clist_dest >= list + 8) - { - /* Early return if there is not enough space. This should never - happen, since all clists are shorter than 5 character now. */ - list[2] = code[0]; - list[3] = code[1]; - return code; - } - *clist_dest++ = *clist_src; - } - while(*clist_src++ != NOTACHAR); - - /* All characters are stored. The terminating NOTACHAR - is copied form the clist itself. */ - - list[0] = (c == OP_PROP) ? OP_CHAR : OP_NOT; - return code; -#endif - - case OP_NCLASS: - case OP_CLASS: -#if defined SUPPORT_UTF || !defined COMPILE_PCRE8 - case OP_XCLASS: - if (c == OP_XCLASS) - end = code + GET(code, 0) - 1; - else -#endif - end = code + 32 / sizeof(pcre_uchar); - - switch(*end) - { - case OP_CRSTAR: - case OP_CRMINSTAR: - case OP_CRQUERY: - case OP_CRMINQUERY: - case OP_CRPOSSTAR: - case OP_CRPOSQUERY: - list[1] = TRUE; - end++; - break; - - case OP_CRPLUS: - case OP_CRMINPLUS: - case OP_CRPOSPLUS: - end++; - break; - - case OP_CRRANGE: - case OP_CRMINRANGE: - case OP_CRPOSRANGE: - list[1] = (GET2(end, 1) == 0); - end += 1 + 2 * IMM2_SIZE; - break; - } - list[2] = (pcre_uint32)(end - code); - return end; - } -return NULL; /* Opcode not accepted */ -} - - - -/************************************************* -* Scan further character sets for match * -*************************************************/ - -/* Checks whether the base and the current opcode have a common character, in -which case the base cannot be possessified. - -Arguments: - code points to the byte code - utf TRUE in UTF-8 / UTF-16 / UTF-32 mode - cd static compile data - base_list the data list of the base opcode - -Returns: TRUE if the auto-possessification is possible -*/ - -static BOOL -compare_opcodes(const pcre_uchar *code, BOOL utf, const compile_data *cd, - const pcre_uint32 *base_list, const pcre_uchar *base_end, int *rec_limit) -{ -pcre_uchar c; -pcre_uint32 list[8]; -const pcre_uint32 *chr_ptr; -const pcre_uint32 *ochr_ptr; -const pcre_uint32 *list_ptr; -const pcre_uchar *next_code; -#if defined SUPPORT_UTF || !defined COMPILE_PCRE8 -const pcre_uchar *xclass_flags; -#endif -const pcre_uint8 *class_bitset; -const pcre_uint8 *set1, *set2, *set_end; -pcre_uint32 chr; -BOOL accepted, invert_bits; -BOOL entered_a_group = FALSE; - -if (*rec_limit == 0) return FALSE; ---(*rec_limit); - -/* Note: the base_list[1] contains whether the current opcode has greedy -(represented by a non-zero value) quantifier. This is a different from -other character type lists, which stores here that the character iterator -matches to an empty string (also represented by a non-zero value). */ - -for(;;) - { - /* All operations move the code pointer forward. - Therefore infinite recursions are not possible. */ - - c = *code; - - /* Skip over callouts */ - - if (c == OP_CALLOUT) - { - code += PRIV(OP_lengths)[c]; - continue; - } - - if (c == OP_ALT) - { - do code += GET(code, 1); while (*code == OP_ALT); - c = *code; - } - - switch(c) - { - case OP_END: - case OP_KETRPOS: - /* TRUE only in greedy case. The non-greedy case could be replaced by - an OP_EXACT, but it is probably not worth it. (And note that OP_EXACT - uses more memory, which we cannot get at this stage.) */ - - return base_list[1] != 0; - - case OP_KET: - /* If the bracket is capturing, and referenced by an OP_RECURSE, or - it is an atomic sub-pattern (assert, once, etc.) the non-greedy case - cannot be converted to a possessive form. */ - - if (base_list[1] == 0) return FALSE; - - switch(*(code - GET(code, 1))) - { - case OP_ASSERT: - case OP_ASSERT_NOT: - case OP_ASSERTBACK: - case OP_ASSERTBACK_NOT: - case OP_ONCE: - case OP_ONCE_NC: - /* Atomic sub-patterns and assertions can always auto-possessify their - last iterator. However, if the group was entered as a result of checking - a previous iterator, this is not possible. */ - - return !entered_a_group; - } - - code += PRIV(OP_lengths)[c]; - continue; - - case OP_ONCE: - case OP_ONCE_NC: - case OP_BRA: - case OP_CBRA: - next_code = code + GET(code, 1); - code += PRIV(OP_lengths)[c]; - - while (*next_code == OP_ALT) - { - if (!compare_opcodes(code, utf, cd, base_list, base_end, rec_limit)) - return FALSE; - code = next_code + 1 + LINK_SIZE; - next_code += GET(next_code, 1); - } - - entered_a_group = TRUE; - continue; - - case OP_BRAZERO: - case OP_BRAMINZERO: - - next_code = code + 1; - if (*next_code != OP_BRA && *next_code != OP_CBRA - && *next_code != OP_ONCE && *next_code != OP_ONCE_NC) return FALSE; - - do next_code += GET(next_code, 1); while (*next_code == OP_ALT); - - /* The bracket content will be checked by the - OP_BRA/OP_CBRA case above. */ - next_code += 1 + LINK_SIZE; - if (!compare_opcodes(next_code, utf, cd, base_list, base_end, rec_limit)) - return FALSE; - - code += PRIV(OP_lengths)[c]; - continue; - - default: - break; - } - - /* Check for a supported opcode, and load its properties. */ - - code = get_chr_property_list(code, utf, cd->fcc, list); - if (code == NULL) return FALSE; /* Unsupported */ - - /* If either opcode is a small character list, set pointers for comparing - characters from that list with another list, or with a property. */ - - if (base_list[0] == OP_CHAR) - { - chr_ptr = base_list + 2; - list_ptr = list; - } - else if (list[0] == OP_CHAR) - { - chr_ptr = list + 2; - list_ptr = base_list; - } - - /* Character bitsets can also be compared to certain opcodes. */ - - else if (base_list[0] == OP_CLASS || list[0] == OP_CLASS -#ifdef COMPILE_PCRE8 - /* In 8 bit, non-UTF mode, OP_CLASS and OP_NCLASS are the same. */ - || (!utf && (base_list[0] == OP_NCLASS || list[0] == OP_NCLASS)) -#endif - ) - { -#ifdef COMPILE_PCRE8 - if (base_list[0] == OP_CLASS || (!utf && base_list[0] == OP_NCLASS)) -#else - if (base_list[0] == OP_CLASS) -#endif - { - set1 = (pcre_uint8 *)(base_end - base_list[2]); - list_ptr = list; - } - else - { - set1 = (pcre_uint8 *)(code - list[2]); - list_ptr = base_list; - } - - invert_bits = FALSE; - switch(list_ptr[0]) - { - case OP_CLASS: - case OP_NCLASS: - set2 = (pcre_uint8 *) - ((list_ptr == list ? code : base_end) - list_ptr[2]); - break; - -#if defined SUPPORT_UTF || !defined COMPILE_PCRE8 - case OP_XCLASS: - xclass_flags = (list_ptr == list ? code : base_end) - list_ptr[2] + LINK_SIZE; - if ((*xclass_flags & XCL_HASPROP) != 0) return FALSE; - if ((*xclass_flags & XCL_MAP) == 0) - { - /* No bits are set for characters < 256. */ - if (list[1] == 0) return TRUE; - /* Might be an empty repeat. */ - continue; - } - set2 = (pcre_uint8 *)(xclass_flags + 1); - break; -#endif - - case OP_NOT_DIGIT: - invert_bits = TRUE; - /* Fall through */ - case OP_DIGIT: - set2 = (pcre_uint8 *)(cd->cbits + cbit_digit); - break; - - case OP_NOT_WHITESPACE: - invert_bits = TRUE; - /* Fall through */ - case OP_WHITESPACE: - set2 = (pcre_uint8 *)(cd->cbits + cbit_space); - break; - - case OP_NOT_WORDCHAR: - invert_bits = TRUE; - /* Fall through */ - case OP_WORDCHAR: - set2 = (pcre_uint8 *)(cd->cbits + cbit_word); - break; - - default: - return FALSE; - } - - /* Because the sets are unaligned, we need - to perform byte comparison here. */ - set_end = set1 + 32; - if (invert_bits) - { - do - { - if ((*set1++ & ~(*set2++)) != 0) return FALSE; - } - while (set1 < set_end); - } - else - { - do - { - if ((*set1++ & *set2++) != 0) return FALSE; - } - while (set1 < set_end); - } - - if (list[1] == 0) return TRUE; - /* Might be an empty repeat. */ - continue; - } - - /* Some property combinations also acceptable. Unicode property opcodes are - processed specially; the rest can be handled with a lookup table. */ - - else - { - pcre_uint32 leftop, rightop; - - leftop = base_list[0]; - rightop = list[0]; - -#ifdef SUPPORT_UCP - accepted = FALSE; /* Always set in non-unicode case. */ - if (leftop == OP_PROP || leftop == OP_NOTPROP) - { - if (rightop == OP_EOD) - accepted = TRUE; - else if (rightop == OP_PROP || rightop == OP_NOTPROP) - { - int n; - const pcre_uint8 *p; - BOOL same = leftop == rightop; - BOOL lisprop = leftop == OP_PROP; - BOOL risprop = rightop == OP_PROP; - BOOL bothprop = lisprop && risprop; - - /* There's a table that specifies how each combination is to be - processed: - 0 Always return FALSE (never auto-possessify) - 1 Character groups are distinct (possessify if both are OP_PROP) - 2 Check character categories in the same group (general or particular) - 3 Return TRUE if the two opcodes are not the same - ... see comments below - */ - - n = propposstab[base_list[2]][list[2]]; - switch(n) - { - case 0: break; - case 1: accepted = bothprop; break; - case 2: accepted = (base_list[3] == list[3]) != same; break; - case 3: accepted = !same; break; - - case 4: /* Left general category, right particular category */ - accepted = risprop && catposstab[base_list[3]][list[3]] == same; - break; - - case 5: /* Right general category, left particular category */ - accepted = lisprop && catposstab[list[3]][base_list[3]] == same; - break; - - /* This code is logically tricky. Think hard before fiddling with it. - The posspropstab table has four entries per row. Each row relates to - one of PCRE's special properties such as ALNUM or SPACE or WORD. - Only WORD actually needs all four entries, but using repeats for the - others means they can all use the same code below. - - The first two entries in each row are Unicode general categories, and - apply always, because all the characters they include are part of the - PCRE character set. The third and fourth entries are a general and a - particular category, respectively, that include one or more relevant - characters. One or the other is used, depending on whether the check - is for a general or a particular category. However, in both cases the - category contains more characters than the specials that are defined - for the property being tested against. Therefore, it cannot be used - in a NOTPROP case. - - Example: the row for WORD contains ucp_L, ucp_N, ucp_P, ucp_Po. - Underscore is covered by ucp_P or ucp_Po. */ - - case 6: /* Left alphanum vs right general category */ - case 7: /* Left space vs right general category */ - case 8: /* Left word vs right general category */ - p = posspropstab[n-6]; - accepted = risprop && lisprop == - (list[3] != p[0] && - list[3] != p[1] && - (list[3] != p[2] || !lisprop)); - break; - - case 9: /* Right alphanum vs left general category */ - case 10: /* Right space vs left general category */ - case 11: /* Right word vs left general category */ - p = posspropstab[n-9]; - accepted = lisprop && risprop == - (base_list[3] != p[0] && - base_list[3] != p[1] && - (base_list[3] != p[2] || !risprop)); - break; - - case 12: /* Left alphanum vs right particular category */ - case 13: /* Left space vs right particular category */ - case 14: /* Left word vs right particular category */ - p = posspropstab[n-12]; - accepted = risprop && lisprop == - (catposstab[p[0]][list[3]] && - catposstab[p[1]][list[3]] && - (list[3] != p[3] || !lisprop)); - break; - - case 15: /* Right alphanum vs left particular category */ - case 16: /* Right space vs left particular category */ - case 17: /* Right word vs left particular category */ - p = posspropstab[n-15]; - accepted = lisprop && risprop == - (catposstab[p[0]][base_list[3]] && - catposstab[p[1]][base_list[3]] && - (base_list[3] != p[3] || !risprop)); - break; - } - } - } - - else -#endif /* SUPPORT_UCP */ - - accepted = leftop >= FIRST_AUTOTAB_OP && leftop <= LAST_AUTOTAB_LEFT_OP && - rightop >= FIRST_AUTOTAB_OP && rightop <= LAST_AUTOTAB_RIGHT_OP && - autoposstab[leftop - FIRST_AUTOTAB_OP][rightop - FIRST_AUTOTAB_OP]; - - if (!accepted) return FALSE; - - if (list[1] == 0) return TRUE; - /* Might be an empty repeat. */ - continue; - } - - /* Control reaches here only if one of the items is a small character list. - All characters are checked against the other side. */ - - do - { - chr = *chr_ptr; - - switch(list_ptr[0]) - { - case OP_CHAR: - ochr_ptr = list_ptr + 2; - do - { - if (chr == *ochr_ptr) return FALSE; - ochr_ptr++; - } - while(*ochr_ptr != NOTACHAR); - break; - - case OP_NOT: - ochr_ptr = list_ptr + 2; - do - { - if (chr == *ochr_ptr) - break; - ochr_ptr++; - } - while(*ochr_ptr != NOTACHAR); - if (*ochr_ptr == NOTACHAR) return FALSE; /* Not found */ - break; - - /* Note that OP_DIGIT etc. are generated only when PCRE_UCP is *not* - set. When it is set, \d etc. are converted into OP_(NOT_)PROP codes. */ - - case OP_DIGIT: - if (chr < 256 && (cd->ctypes[chr] & ctype_digit) != 0) return FALSE; - break; - - case OP_NOT_DIGIT: - if (chr > 255 || (cd->ctypes[chr] & ctype_digit) == 0) return FALSE; - break; - - case OP_WHITESPACE: - if (chr < 256 && (cd->ctypes[chr] & ctype_space) != 0) return FALSE; - break; - - case OP_NOT_WHITESPACE: - if (chr > 255 || (cd->ctypes[chr] & ctype_space) == 0) return FALSE; - break; - - case OP_WORDCHAR: - if (chr < 255 && (cd->ctypes[chr] & ctype_word) != 0) return FALSE; - break; - - case OP_NOT_WORDCHAR: - if (chr > 255 || (cd->ctypes[chr] & ctype_word) == 0) return FALSE; - break; - - case OP_HSPACE: - switch(chr) - { - HSPACE_CASES: return FALSE; - default: break; - } - break; - - case OP_NOT_HSPACE: - switch(chr) - { - HSPACE_CASES: break; - default: return FALSE; - } - break; - - case OP_ANYNL: - case OP_VSPACE: - switch(chr) - { - VSPACE_CASES: return FALSE; - default: break; - } - break; - - case OP_NOT_VSPACE: - switch(chr) - { - VSPACE_CASES: break; - default: return FALSE; - } - break; - - case OP_DOLL: - case OP_EODN: - switch (chr) - { - case CHAR_CR: - case CHAR_LF: - case CHAR_VT: - case CHAR_FF: - case CHAR_NEL: -#ifndef EBCDIC - case 0x2028: - case 0x2029: -#endif /* Not EBCDIC */ - return FALSE; - } - break; - - case OP_EOD: /* Can always possessify before \z */ - break; - -#ifdef SUPPORT_UCP - case OP_PROP: - case OP_NOTPROP: - if (!check_char_prop(chr, list_ptr[2], list_ptr[3], - list_ptr[0] == OP_NOTPROP)) - return FALSE; - break; -#endif - - case OP_NCLASS: - if (chr > 255) return FALSE; - /* Fall through */ - - case OP_CLASS: - if (chr > 255) break; - class_bitset = (pcre_uint8 *) - ((list_ptr == list ? code : base_end) - list_ptr[2]); - if ((class_bitset[chr >> 3] & (1 << (chr & 7))) != 0) return FALSE; - break; - -#if defined SUPPORT_UTF || !defined COMPILE_PCRE8 - case OP_XCLASS: - if (PRIV(xclass)(chr, (list_ptr == list ? code : base_end) - - list_ptr[2] + LINK_SIZE, utf)) return FALSE; - break; -#endif - - default: - return FALSE; - } - - chr_ptr++; - } - while(*chr_ptr != NOTACHAR); - - /* At least one character must be matched from this opcode. */ - - if (list[1] == 0) return TRUE; - } - -/* Control never reaches here. There used to be a fail-save return FALSE; here, -but some compilers complain about an unreachable statement. */ - -} - - - -/************************************************* -* Scan compiled regex for auto-possession * -*************************************************/ - -/* Replaces single character iterations with their possessive alternatives -if appropriate. This function modifies the compiled opcode! - -Arguments: - code points to start of the byte code - utf TRUE in UTF-8 / UTF-16 / UTF-32 mode - cd static compile data - -Returns: nothing -*/ - -static void -auto_possessify(pcre_uchar *code, BOOL utf, const compile_data *cd) -{ -register pcre_uchar c; -const pcre_uchar *end; -pcre_uchar *repeat_opcode; -pcre_uint32 list[8]; -int rec_limit; - -for (;;) - { - c = *code; - - /* When a pattern with bad UTF-8 encoding is compiled with NO_UTF_CHECK, - it may compile without complaining, but may get into a loop here if the code - pointer points to a bad value. This is, of course a documentated possibility, - when NO_UTF_CHECK is set, so it isn't a bug, but we can detect this case and - just give up on this optimization. */ - - if (c >= OP_TABLE_LENGTH) return; - - if (c >= OP_STAR && c <= OP_TYPEPOSUPTO) - { - c -= get_repeat_base(c) - OP_STAR; - end = (c <= OP_MINUPTO) ? - get_chr_property_list(code, utf, cd->fcc, list) : NULL; - list[1] = c == OP_STAR || c == OP_PLUS || c == OP_QUERY || c == OP_UPTO; - - rec_limit = 1000; - if (end != NULL && compare_opcodes(end, utf, cd, list, end, &rec_limit)) - { - switch(c) - { - case OP_STAR: - *code += OP_POSSTAR - OP_STAR; - break; - - case OP_MINSTAR: - *code += OP_POSSTAR - OP_MINSTAR; - break; - - case OP_PLUS: - *code += OP_POSPLUS - OP_PLUS; - break; - - case OP_MINPLUS: - *code += OP_POSPLUS - OP_MINPLUS; - break; - - case OP_QUERY: - *code += OP_POSQUERY - OP_QUERY; - break; - - case OP_MINQUERY: - *code += OP_POSQUERY - OP_MINQUERY; - break; - - case OP_UPTO: - *code += OP_POSUPTO - OP_UPTO; - break; - - case OP_MINUPTO: - *code += OP_POSUPTO - OP_MINUPTO; - break; - } - } - c = *code; - } - else if (c == OP_CLASS || c == OP_NCLASS || c == OP_XCLASS) - { -#if defined SUPPORT_UTF || !defined COMPILE_PCRE8 - if (c == OP_XCLASS) - repeat_opcode = code + GET(code, 1); - else -#endif - repeat_opcode = code + 1 + (32 / sizeof(pcre_uchar)); - - c = *repeat_opcode; - if (c >= OP_CRSTAR && c <= OP_CRMINRANGE) - { - /* end must not be NULL. */ - end = get_chr_property_list(code, utf, cd->fcc, list); - - list[1] = (c & 1) == 0; - - rec_limit = 1000; - if (compare_opcodes(end, utf, cd, list, end, &rec_limit)) - { - switch (c) - { - case OP_CRSTAR: - case OP_CRMINSTAR: - *repeat_opcode = OP_CRPOSSTAR; - break; - - case OP_CRPLUS: - case OP_CRMINPLUS: - *repeat_opcode = OP_CRPOSPLUS; - break; - - case OP_CRQUERY: - case OP_CRMINQUERY: - *repeat_opcode = OP_CRPOSQUERY; - break; - - case OP_CRRANGE: - case OP_CRMINRANGE: - *repeat_opcode = OP_CRPOSRANGE; - break; - } - } - } - c = *code; - } - - switch(c) - { - case OP_END: - return; - - case OP_TYPESTAR: - case OP_TYPEMINSTAR: - case OP_TYPEPLUS: - case OP_TYPEMINPLUS: - case OP_TYPEQUERY: - case OP_TYPEMINQUERY: - case OP_TYPEPOSSTAR: - case OP_TYPEPOSPLUS: - case OP_TYPEPOSQUERY: - if (code[1] == OP_PROP || code[1] == OP_NOTPROP) code += 2; - break; - - case OP_TYPEUPTO: - case OP_TYPEMINUPTO: - case OP_TYPEEXACT: - case OP_TYPEPOSUPTO: - if (code[1 + IMM2_SIZE] == OP_PROP || code[1 + IMM2_SIZE] == OP_NOTPROP) - code += 2; - break; - -#if defined SUPPORT_UTF || !defined COMPILE_PCRE8 - case OP_XCLASS: - code += GET(code, 1); - break; -#endif - - case OP_MARK: - case OP_PRUNE_ARG: - case OP_SKIP_ARG: - case OP_THEN_ARG: - code += code[1]; - break; - } - - /* Add in the fixed length from the table */ - - code += PRIV(OP_lengths)[c]; - - /* In UTF-8 mode, opcodes that are followed by a character may be followed by - a multi-byte character. The length in the table is a minimum, so we have to - arrange to skip the extra bytes. */ - -#if defined SUPPORT_UTF && !defined COMPILE_PCRE32 - if (utf) switch(c) - { - case OP_CHAR: - case OP_CHARI: - case OP_NOT: - case OP_NOTI: - case OP_STAR: - case OP_MINSTAR: - case OP_PLUS: - case OP_MINPLUS: - case OP_QUERY: - case OP_MINQUERY: - case OP_UPTO: - case OP_MINUPTO: - case OP_EXACT: - case OP_POSSTAR: - case OP_POSPLUS: - case OP_POSQUERY: - case OP_POSUPTO: - case OP_STARI: - case OP_MINSTARI: - case OP_PLUSI: - case OP_MINPLUSI: - case OP_QUERYI: - case OP_MINQUERYI: - case OP_UPTOI: - case OP_MINUPTOI: - case OP_EXACTI: - case OP_POSSTARI: - case OP_POSPLUSI: - case OP_POSQUERYI: - case OP_POSUPTOI: - case OP_NOTSTAR: - case OP_NOTMINSTAR: - case OP_NOTPLUS: - case OP_NOTMINPLUS: - case OP_NOTQUERY: - case OP_NOTMINQUERY: - case OP_NOTUPTO: - case OP_NOTMINUPTO: - case OP_NOTEXACT: - case OP_NOTPOSSTAR: - case OP_NOTPOSPLUS: - case OP_NOTPOSQUERY: - case OP_NOTPOSUPTO: - case OP_NOTSTARI: - case OP_NOTMINSTARI: - case OP_NOTPLUSI: - case OP_NOTMINPLUSI: - case OP_NOTQUERYI: - case OP_NOTMINQUERYI: - case OP_NOTUPTOI: - case OP_NOTMINUPTOI: - case OP_NOTEXACTI: - case OP_NOTPOSSTARI: - case OP_NOTPOSPLUSI: - case OP_NOTPOSQUERYI: - case OP_NOTPOSUPTOI: - if (HAS_EXTRALEN(code[-1])) code += GET_EXTRALEN(code[-1]); - break; - } -#else - (void)(utf); /* Keep compiler happy by referencing function argument */ -#endif - } -} - - - -/************************************************* -* Check for POSIX class syntax * -*************************************************/ - -/* This function is called when the sequence "[:" or "[." or "[=" is -encountered in a character class. It checks whether this is followed by a -sequence of characters terminated by a matching ":]" or ".]" or "=]". If we -reach an unescaped ']' without the special preceding character, return FALSE. - -Originally, this function only recognized a sequence of letters between the -terminators, but it seems that Perl recognizes any sequence of characters, -though of course unknown POSIX names are subsequently rejected. Perl gives an -"Unknown POSIX class" error for [:f\oo:] for example, where previously PCRE -didn't consider this to be a POSIX class. Likewise for [:1234:]. - -The problem in trying to be exactly like Perl is in the handling of escapes. We -have to be sure that [abc[:x\]pqr] is *not* treated as containing a POSIX -class, but [abc[:x\]pqr:]] is (so that an error can be generated). The code -below handles the special cases \\ and \], but does not try to do any other -escape processing. This makes it different from Perl for cases such as -[:l\ower:] where Perl recognizes it as the POSIX class "lower" but PCRE does -not recognize "l\ower". This is a lesser evil than not diagnosing bad classes -when Perl does, I think. - -A user pointed out that PCRE was rejecting [:a[:digit:]] whereas Perl was not. -It seems that the appearance of a nested POSIX class supersedes an apparent -external class. For example, [:a[:digit:]b:] matches "a", "b", ":", or -a digit. - -In Perl, unescaped square brackets may also appear as part of class names. For -example, [:a[:abc]b:] gives unknown POSIX class "[:abc]b:]". However, for -[:a[:abc]b][b:] it gives unknown POSIX class "[:abc]b][b:]", which does not -seem right at all. PCRE does not allow closing square brackets in POSIX class -names. - -Arguments: - ptr pointer to the initial [ - endptr where to return the end pointer - -Returns: TRUE or FALSE -*/ - -static BOOL -check_posix_syntax(const pcre_uchar *ptr, const pcre_uchar **endptr) -{ -pcre_uchar terminator; /* Don't combine these lines; the Solaris cc */ -terminator = *(++ptr); /* compiler warns about "non-constant" initializer. */ -for (++ptr; *ptr != CHAR_NULL; ptr++) - { - if (*ptr == CHAR_BACKSLASH && - (ptr[1] == CHAR_RIGHT_SQUARE_BRACKET || - ptr[1] == CHAR_BACKSLASH)) - ptr++; - else if ((*ptr == CHAR_LEFT_SQUARE_BRACKET && ptr[1] == terminator) || - *ptr == CHAR_RIGHT_SQUARE_BRACKET) return FALSE; - else if (*ptr == terminator && ptr[1] == CHAR_RIGHT_SQUARE_BRACKET) - { - *endptr = ptr; - return TRUE; - } - } -return FALSE; -} - - - - -/************************************************* -* Check POSIX class name * -*************************************************/ - -/* This function is called to check the name given in a POSIX-style class entry -such as [:alnum:]. - -Arguments: - ptr points to the first letter - len the length of the name - -Returns: a value representing the name, or -1 if unknown -*/ - -static int -check_posix_name(const pcre_uchar *ptr, int len) -{ -const char *pn = posix_names; -register int yield = 0; -while (posix_name_lengths[yield] != 0) - { - if (len == posix_name_lengths[yield] && - STRNCMP_UC_C8(ptr, pn, (unsigned int)len) == 0) return yield; - pn += posix_name_lengths[yield] + 1; - yield++; - } -return -1; -} - - -/************************************************* -* Adjust OP_RECURSE items in repeated group * -*************************************************/ - -/* OP_RECURSE items contain an offset from the start of the regex to the group -that is referenced. This means that groups can be replicated for fixed -repetition simply by copying (because the recursion is allowed to refer to -earlier groups that are outside the current group). However, when a group is -optional (i.e. the minimum quantifier is zero), OP_BRAZERO or OP_SKIPZERO is -inserted before it, after it has been compiled. This means that any OP_RECURSE -items within it that refer to the group itself or any contained groups have to -have their offsets adjusted. That one of the jobs of this function. Before it -is called, the partially compiled regex must be temporarily terminated with -OP_END. - -This function has been extended to cope with forward references for recursions -and subroutine calls. It must check the list of such references for the -group we are dealing with. If it finds that one of the recursions in the -current group is on this list, it does not adjust the value in the reference -(which is a group number). After the group has been scanned, all the offsets in -the forward reference list for the group are adjusted. - -Arguments: - group points to the start of the group - adjust the amount by which the group is to be moved - utf TRUE in UTF-8 / UTF-16 / UTF-32 mode - cd contains pointers to tables etc. - save_hwm_offset the hwm forward reference offset at the start of the group - -Returns: nothing -*/ - -static void -adjust_recurse(pcre_uchar *group, int adjust, BOOL utf, compile_data *cd, - size_t save_hwm_offset) -{ -int offset; -pcre_uchar *hc; -pcre_uchar *ptr = group; - -while ((ptr = (pcre_uchar *)find_recurse(ptr, utf)) != NULL) - { - for (hc = (pcre_uchar *)cd->start_workspace + save_hwm_offset; hc < cd->hwm; - hc += LINK_SIZE) - { - offset = (int)GET(hc, 0); - if (cd->start_code + offset == ptr + 1) break; - } - - /* If we have not found this recursion on the forward reference list, adjust - the recursion's offset if it's after the start of this group. */ - - if (hc >= cd->hwm) - { - offset = (int)GET(ptr, 1); - if (cd->start_code + offset >= group) PUT(ptr, 1, offset + adjust); - } - - ptr += 1 + LINK_SIZE; - } - -/* Now adjust all forward reference offsets for the group. */ - -for (hc = (pcre_uchar *)cd->start_workspace + save_hwm_offset; hc < cd->hwm; - hc += LINK_SIZE) - { - offset = (int)GET(hc, 0); - PUT(hc, 0, offset + adjust); - } -} - - - -/************************************************* -* Insert an automatic callout point * -*************************************************/ - -/* This function is called when the PCRE_AUTO_CALLOUT option is set, to insert -callout points before each pattern item. - -Arguments: - code current code pointer - ptr current pattern pointer - cd pointers to tables etc - -Returns: new code pointer -*/ - -static pcre_uchar * -auto_callout(pcre_uchar *code, const pcre_uchar *ptr, compile_data *cd) -{ -*code++ = OP_CALLOUT; -*code++ = 255; -PUT(code, 0, (int)(ptr - cd->start_pattern)); /* Pattern offset */ -PUT(code, LINK_SIZE, 0); /* Default length */ -return code + 2 * LINK_SIZE; -} - - - -/************************************************* -* Complete a callout item * -*************************************************/ - -/* A callout item contains the length of the next item in the pattern, which -we can't fill in till after we have reached the relevant point. This is used -for both automatic and manual callouts. - -Arguments: - previous_callout points to previous callout item - ptr current pattern pointer - cd pointers to tables etc - -Returns: nothing -*/ - -static void -complete_callout(pcre_uchar *previous_callout, const pcre_uchar *ptr, compile_data *cd) -{ -int length = (int)(ptr - cd->start_pattern - GET(previous_callout, 2)); -PUT(previous_callout, 2 + LINK_SIZE, length); -} - - - -#ifdef SUPPORT_UCP -/************************************************* -* Get othercase range * -*************************************************/ - -/* This function is passed the start and end of a class range, in UTF-8 mode -with UCP support. It searches up the characters, looking for ranges of -characters in the "other" case. Each call returns the next one, updating the -start address. A character with multiple other cases is returned on its own -with a special return value. - -Arguments: - cptr points to starting character value; updated - d end value - ocptr where to put start of othercase range - odptr where to put end of othercase range - -Yield: -1 when no more - 0 when a range is returned - >0 the CASESET offset for char with multiple other cases - in this case, ocptr contains the original -*/ - -static int -get_othercase_range(pcre_uint32 *cptr, pcre_uint32 d, pcre_uint32 *ocptr, - pcre_uint32 *odptr) -{ -pcre_uint32 c, othercase, next; -unsigned int co; - -/* Find the first character that has an other case. If it has multiple other -cases, return its case offset value. */ - -for (c = *cptr; c <= d; c++) - { - if ((co = UCD_CASESET(c)) != 0) - { - *ocptr = c++; /* Character that has the set */ - *cptr = c; /* Rest of input range */ - return (int)co; - } - if ((othercase = UCD_OTHERCASE(c)) != c) break; - } - -if (c > d) return -1; /* Reached end of range */ - -/* Found a character that has a single other case. Search for the end of the -range, which is either the end of the input range, or a character that has zero -or more than one other cases. */ - -*ocptr = othercase; -next = othercase + 1; - -for (++c; c <= d; c++) - { - if ((co = UCD_CASESET(c)) != 0 || UCD_OTHERCASE(c) != next) break; - next++; - } - -*odptr = next - 1; /* End of othercase range */ -*cptr = c; /* Rest of input range */ -return 0; -} -#endif /* SUPPORT_UCP */ - - - -/************************************************* -* Add a character or range to a class * -*************************************************/ - -/* This function packages up the logic of adding a character or range of -characters to a class. The character values in the arguments will be within the -valid values for the current mode (8-bit, 16-bit, UTF, etc). This function is -mutually recursive with the function immediately below. - -Arguments: - classbits the bit map for characters < 256 - uchardptr points to the pointer for extra data - options the options word - cd contains pointers to tables etc. - start start of range character - end end of range character - -Returns: the number of < 256 characters added - the pointer to extra data is updated -*/ - -static int -add_to_class(pcre_uint8 *classbits, pcre_uchar **uchardptr, int options, - compile_data *cd, pcre_uint32 start, pcre_uint32 end) -{ -pcre_uint32 c; -pcre_uint32 classbits_end = (end <= 0xff ? end : 0xff); -int n8 = 0; - -/* If caseless matching is required, scan the range and process alternate -cases. In Unicode, there are 8-bit characters that have alternate cases that -are greater than 255 and vice-versa. Sometimes we can just extend the original -range. */ - -if ((options & PCRE_CASELESS) != 0) - { -#ifdef SUPPORT_UCP - if ((options & PCRE_UTF8) != 0) - { - int rc; - pcre_uint32 oc, od; - - options &= ~PCRE_CASELESS; /* Remove for recursive calls */ - c = start; - - while ((rc = get_othercase_range(&c, end, &oc, &od)) >= 0) - { - /* Handle a single character that has more than one other case. */ - - if (rc > 0) n8 += add_list_to_class(classbits, uchardptr, options, cd, - PRIV(ucd_caseless_sets) + rc, oc); - - /* Do nothing if the other case range is within the original range. */ - - else if (oc >= start && od <= end) continue; - - /* Extend the original range if there is overlap, noting that if oc < c, we - can't have od > end because a subrange is always shorter than the basic - range. Otherwise, use a recursive call to add the additional range. */ - - else if (oc < start && od >= start - 1) start = oc; /* Extend downwards */ - else if (od > end && oc <= end + 1) - { - end = od; /* Extend upwards */ - if (end > classbits_end) classbits_end = (end <= 0xff ? end : 0xff); - } - else n8 += add_to_class(classbits, uchardptr, options, cd, oc, od); - } - } - else -#endif /* SUPPORT_UCP */ - - /* Not UTF-mode, or no UCP */ - - for (c = start; c <= classbits_end; c++) - { - SETBIT(classbits, cd->fcc[c]); - n8++; - } - } - -/* Now handle the original range. Adjust the final value according to the bit -length - this means that the same lists of (e.g.) horizontal spaces can be used -in all cases. */ - -#if defined COMPILE_PCRE8 -#ifdef SUPPORT_UTF - if ((options & PCRE_UTF8) == 0) -#endif - if (end > 0xff) end = 0xff; - -#elif defined COMPILE_PCRE16 -#ifdef SUPPORT_UTF - if ((options & PCRE_UTF16) == 0) -#endif - if (end > 0xffff) end = 0xffff; - -#endif /* COMPILE_PCRE[8|16] */ - -/* Use the bitmap for characters < 256. Otherwise use extra data.*/ - -for (c = start; c <= classbits_end; c++) - { - /* Regardless of start, c will always be <= 255. */ - SETBIT(classbits, c); - n8++; - } - -#if defined SUPPORT_UTF || !defined COMPILE_PCRE8 -if (start <= 0xff) start = 0xff + 1; - -if (end >= start) - { - pcre_uchar *uchardata = *uchardptr; -#ifdef SUPPORT_UTF - if ((options & PCRE_UTF8) != 0) /* All UTFs use the same flag bit */ - { - if (start < end) - { - *uchardata++ = XCL_RANGE; - uchardata += PRIV(ord2utf)(start, uchardata); - uchardata += PRIV(ord2utf)(end, uchardata); - } - else if (start == end) - { - *uchardata++ = XCL_SINGLE; - uchardata += PRIV(ord2utf)(start, uchardata); - } - } - else -#endif /* SUPPORT_UTF */ - - /* Without UTF support, character values are constrained by the bit length, - and can only be > 256 for 16-bit and 32-bit libraries. */ - -#ifdef COMPILE_PCRE8 - {} -#else - if (start < end) - { - *uchardata++ = XCL_RANGE; - *uchardata++ = start; - *uchardata++ = end; - } - else if (start == end) - { - *uchardata++ = XCL_SINGLE; - *uchardata++ = start; - } -#endif - - *uchardptr = uchardata; /* Updata extra data pointer */ - } -#endif /* SUPPORT_UTF || !COMPILE_PCRE8 */ - -return n8; /* Number of 8-bit characters */ -} - - - - -/************************************************* -* Add a list of characters to a class * -*************************************************/ - -/* This function is used for adding a list of case-equivalent characters to a -class, and also for adding a list of horizontal or vertical whitespace. If the -list is in order (which it should be), ranges of characters are detected and -handled appropriately. This function is mutually recursive with the function -above. - -Arguments: - classbits the bit map for characters < 256 - uchardptr points to the pointer for extra data - options the options word - cd contains pointers to tables etc. - p points to row of 32-bit values, terminated by NOTACHAR - except character to omit; this is used when adding lists of - case-equivalent characters to avoid including the one we - already know about - -Returns: the number of < 256 characters added - the pointer to extra data is updated -*/ - -static int -add_list_to_class(pcre_uint8 *classbits, pcre_uchar **uchardptr, int options, - compile_data *cd, const pcre_uint32 *p, unsigned int except) -{ -int n8 = 0; -while (p[0] < NOTACHAR) - { - int n = 0; - if (p[0] != except) - { - while(p[n+1] == p[0] + n + 1) n++; - n8 += add_to_class(classbits, uchardptr, options, cd, p[0], p[n]); - } - p += n + 1; - } -return n8; -} - - - -/************************************************* -* Add characters not in a list to a class * -*************************************************/ - -/* This function is used for adding the complement of a list of horizontal or -vertical whitespace to a class. The list must be in order. - -Arguments: - classbits the bit map for characters < 256 - uchardptr points to the pointer for extra data - options the options word - cd contains pointers to tables etc. - p points to row of 32-bit values, terminated by NOTACHAR - -Returns: the number of < 256 characters added - the pointer to extra data is updated -*/ - -static int -add_not_list_to_class(pcre_uint8 *classbits, pcre_uchar **uchardptr, - int options, compile_data *cd, const pcre_uint32 *p) -{ -BOOL utf = (options & PCRE_UTF8) != 0; -int n8 = 0; -if (p[0] > 0) - n8 += add_to_class(classbits, uchardptr, options, cd, 0, p[0] - 1); -while (p[0] < NOTACHAR) - { - while (p[1] == p[0] + 1) p++; - n8 += add_to_class(classbits, uchardptr, options, cd, p[0] + 1, - (p[1] == NOTACHAR) ? (utf ? 0x10ffffu : 0xffffffffu) : p[1] - 1); - p++; - } -return n8; -} - - - -/************************************************* -* Compile one branch * -*************************************************/ - -/* Scan the pattern, compiling it into the a vector. If the options are -changed during the branch, the pointer is used to change the external options -bits. This function is used during the pre-compile phase when we are trying -to find out the amount of memory needed, as well as during the real compile -phase. The value of lengthptr distinguishes the two phases. - -Arguments: - optionsptr pointer to the option bits - codeptr points to the pointer to the current code point - ptrptr points to the current pattern pointer - errorcodeptr points to error code variable - firstcharptr place to put the first required character - firstcharflagsptr place to put the first character flags, or a negative number - reqcharptr place to put the last required character - reqcharflagsptr place to put the last required character flags, or a negative number - bcptr points to current branch chain - cond_depth conditional nesting depth - cd contains pointers to tables etc. - lengthptr NULL during the real compile phase - points to length accumulator during pre-compile phase - -Returns: TRUE on success - FALSE, with *errorcodeptr set non-zero on error -*/ - -static BOOL -compile_branch(int *optionsptr, pcre_uchar **codeptr, - const pcre_uchar **ptrptr, int *errorcodeptr, - pcre_uint32 *firstcharptr, pcre_int32 *firstcharflagsptr, - pcre_uint32 *reqcharptr, pcre_int32 *reqcharflagsptr, - branch_chain *bcptr, int cond_depth, - compile_data *cd, int *lengthptr) -{ -int repeat_type, op_type; -int repeat_min = 0, repeat_max = 0; /* To please picky compilers */ -int bravalue = 0; -int greedy_default, greedy_non_default; -pcre_uint32 firstchar, reqchar; -pcre_int32 firstcharflags, reqcharflags; -pcre_uint32 zeroreqchar, zerofirstchar; -pcre_int32 zeroreqcharflags, zerofirstcharflags; -pcre_int32 req_caseopt, reqvary, tempreqvary; -int options = *optionsptr; /* May change dynamically */ -int after_manual_callout = 0; -int length_prevgroup = 0; -register pcre_uint32 c; -int escape; -register pcre_uchar *code = *codeptr; -pcre_uchar *last_code = code; -pcre_uchar *orig_code = code; -pcre_uchar *tempcode; -BOOL inescq = FALSE; -BOOL groupsetfirstchar = FALSE; -const pcre_uchar *ptr = *ptrptr; -const pcre_uchar *tempptr; -const pcre_uchar *nestptr = NULL; -pcre_uchar *previous = NULL; -pcre_uchar *previous_callout = NULL; -size_t item_hwm_offset = 0; -pcre_uint8 classbits[32]; - -/* We can fish out the UTF-8 setting once and for all into a BOOL, but we -must not do this for other options (e.g. PCRE_EXTENDED) because they may change -dynamically as we process the pattern. */ - -#ifdef SUPPORT_UTF -/* PCRE_UTF[16|32] have the same value as PCRE_UTF8. */ -BOOL utf = (options & PCRE_UTF8) != 0; -#ifndef COMPILE_PCRE32 -pcre_uchar utf_chars[6]; -#endif -#else -BOOL utf = FALSE; -#endif - -/* Helper variables for OP_XCLASS opcode (for characters > 255). We define -class_uchardata always so that it can be passed to add_to_class() always, -though it will not be used in non-UTF 8-bit cases. This avoids having to supply -alternative calls for the different cases. */ - -pcre_uchar *class_uchardata; -#if defined SUPPORT_UTF || !defined COMPILE_PCRE8 -BOOL xclass; -pcre_uchar *class_uchardata_base; -#endif - -#ifdef PCRE_DEBUG -if (lengthptr != NULL) DPRINTF((">> start branch\n")); -#endif - -/* Set up the default and non-default settings for greediness */ - -greedy_default = ((options & PCRE_UNGREEDY) != 0); -greedy_non_default = greedy_default ^ 1; - -/* Initialize no first byte, no required byte. REQ_UNSET means "no char -matching encountered yet". It gets changed to REQ_NONE if we hit something that -matches a non-fixed char first char; reqchar just remains unset if we never -find one. - -When we hit a repeat whose minimum is zero, we may have to adjust these values -to take the zero repeat into account. This is implemented by setting them to -zerofirstbyte and zeroreqchar when such a repeat is encountered. The individual -item types that can be repeated set these backoff variables appropriately. */ - -firstchar = reqchar = zerofirstchar = zeroreqchar = 0; -firstcharflags = reqcharflags = zerofirstcharflags = zeroreqcharflags = REQ_UNSET; - -/* The variable req_caseopt contains either the REQ_CASELESS value -or zero, according to the current setting of the caseless flag. The -REQ_CASELESS leaves the lower 28 bit empty. It is added into the -firstchar or reqchar variables to record the case status of the -value. This is used only for ASCII characters. */ - -req_caseopt = ((options & PCRE_CASELESS) != 0)? REQ_CASELESS:0; - -/* Switch on next character until the end of the branch */ - -for (;; ptr++) - { - BOOL negate_class; - BOOL should_flip_negation; - BOOL possessive_quantifier; - BOOL is_quantifier; - BOOL is_recurse; - BOOL reset_bracount; - int class_has_8bitchar; - int class_one_char; -#if defined SUPPORT_UTF || !defined COMPILE_PCRE8 - BOOL xclass_has_prop; -#endif - int newoptions; - int recno; - int refsign; - int skipbytes; - pcre_uint32 subreqchar, subfirstchar; - pcre_int32 subreqcharflags, subfirstcharflags; - int terminator; - unsigned int mclength; - unsigned int tempbracount; - pcre_uint32 ec; - pcre_uchar mcbuffer[8]; - - /* Get next character in the pattern */ - - c = *ptr; - - /* If we are at the end of a nested substitution, revert to the outer level - string. Nesting only happens one level deep. */ - - if (c == CHAR_NULL && nestptr != NULL) - { - ptr = nestptr; - nestptr = NULL; - c = *ptr; - } - - /* If we are in the pre-compile phase, accumulate the length used for the - previous cycle of this loop. */ - - if (lengthptr != NULL) - { -#ifdef PCRE_DEBUG - if (code > cd->hwm) cd->hwm = code; /* High water info */ -#endif - if (code > cd->start_workspace + cd->workspace_size - - WORK_SIZE_SAFETY_MARGIN) /* Check for overrun */ - { - *errorcodeptr = ERR52; - goto FAILED; - } - - /* There is at least one situation where code goes backwards: this is the - case of a zero quantifier after a class (e.g. [ab]{0}). At compile time, - the class is simply eliminated. However, it is created first, so we have to - allow memory for it. Therefore, don't ever reduce the length at this point. - */ - - if (code < last_code) code = last_code; - - /* Paranoid check for integer overflow */ - - if (OFLOW_MAX - *lengthptr < code - last_code) - { - *errorcodeptr = ERR20; - goto FAILED; - } - - *lengthptr += (int)(code - last_code); - DPRINTF(("length=%d added %d c=%c (0x%x)\n", *lengthptr, - (int)(code - last_code), c, c)); - - /* If "previous" is set and it is not at the start of the work space, move - it back to there, in order to avoid filling up the work space. Otherwise, - if "previous" is NULL, reset the current code pointer to the start. */ - - if (previous != NULL) - { - if (previous > orig_code) - { - memmove(orig_code, previous, IN_UCHARS(code - previous)); - code -= previous - orig_code; - previous = orig_code; - } - } - else code = orig_code; - - /* Remember where this code item starts so we can pick up the length - next time round. */ - - last_code = code; - } - - /* In the real compile phase, just check the workspace used by the forward - reference list. */ - - else if (cd->hwm > cd->start_workspace + cd->workspace_size) - { - *errorcodeptr = ERR52; - goto FAILED; - } - - /* If in \Q...\E, check for the end; if not, we have a literal */ - - if (inescq && c != CHAR_NULL) - { - if (c == CHAR_BACKSLASH && ptr[1] == CHAR_E) - { - inescq = FALSE; - ptr++; - continue; - } - else - { - if (previous_callout != NULL) - { - if (lengthptr == NULL) /* Don't attempt in pre-compile phase */ - complete_callout(previous_callout, ptr, cd); - previous_callout = NULL; - } - if ((options & PCRE_AUTO_CALLOUT) != 0) - { - previous_callout = code; - code = auto_callout(code, ptr, cd); - } - goto NORMAL_CHAR; - } - /* Control does not reach here. */ - } - - /* In extended mode, skip white space and comments. We need a loop in order - to check for more white space and more comments after a comment. */ - - if ((options & PCRE_EXTENDED) != 0) - { - for (;;) - { - while (MAX_255(c) && (cd->ctypes[c] & ctype_space) != 0) c = *(++ptr); - if (c != CHAR_NUMBER_SIGN) break; - ptr++; - while (*ptr != CHAR_NULL) - { - if (IS_NEWLINE(ptr)) /* For non-fixed-length newline cases, */ - { /* IS_NEWLINE sets cd->nllen. */ - ptr += cd->nllen; - break; - } - ptr++; -#ifdef SUPPORT_UTF - if (utf) FORWARDCHAR(ptr); -#endif - } - c = *ptr; /* Either NULL or the char after a newline */ - } - } - - /* See if the next thing is a quantifier. */ - - is_quantifier = - c == CHAR_ASTERISK || c == CHAR_PLUS || c == CHAR_QUESTION_MARK || - (c == CHAR_LEFT_CURLY_BRACKET && is_counted_repeat(ptr+1)); - - /* Fill in length of a previous callout, except when the next thing is a - quantifier or when processing a property substitution string in UCP mode. */ - - if (!is_quantifier && previous_callout != NULL && nestptr == NULL && - after_manual_callout-- <= 0) - { - if (lengthptr == NULL) /* Don't attempt in pre-compile phase */ - complete_callout(previous_callout, ptr, cd); - previous_callout = NULL; - } - - /* Create auto callout, except for quantifiers, or while processing property - strings that are substituted for \w etc in UCP mode. */ - - if ((options & PCRE_AUTO_CALLOUT) != 0 && !is_quantifier && nestptr == NULL) - { - previous_callout = code; - code = auto_callout(code, ptr, cd); - } - - /* Process the next pattern item. */ - - switch(c) - { - /* ===================================================================*/ - case CHAR_NULL: /* The branch terminates at string end */ - case CHAR_VERTICAL_LINE: /* or | or ) */ - case CHAR_RIGHT_PARENTHESIS: - *firstcharptr = firstchar; - *firstcharflagsptr = firstcharflags; - *reqcharptr = reqchar; - *reqcharflagsptr = reqcharflags; - *codeptr = code; - *ptrptr = ptr; - if (lengthptr != NULL) - { - if (OFLOW_MAX - *lengthptr < code - last_code) - { - *errorcodeptr = ERR20; - goto FAILED; - } - *lengthptr += (int)(code - last_code); /* To include callout length */ - DPRINTF((">> end branch\n")); - } - return TRUE; - - - /* ===================================================================*/ - /* Handle single-character metacharacters. In multiline mode, ^ disables - the setting of any following char as a first character. */ - - case CHAR_CIRCUMFLEX_ACCENT: - previous = NULL; - if ((options & PCRE_MULTILINE) != 0) - { - if (firstcharflags == REQ_UNSET) - zerofirstcharflags = firstcharflags = REQ_NONE; - *code++ = OP_CIRCM; - } - else *code++ = OP_CIRC; - break; - - case CHAR_DOLLAR_SIGN: - previous = NULL; - *code++ = ((options & PCRE_MULTILINE) != 0)? OP_DOLLM : OP_DOLL; - break; - - /* There can never be a first char if '.' is first, whatever happens about - repeats. The value of reqchar doesn't change either. */ - - case CHAR_DOT: - if (firstcharflags == REQ_UNSET) firstcharflags = REQ_NONE; - zerofirstchar = firstchar; - zerofirstcharflags = firstcharflags; - zeroreqchar = reqchar; - zeroreqcharflags = reqcharflags; - previous = code; - item_hwm_offset = cd->hwm - cd->start_workspace; - *code++ = ((options & PCRE_DOTALL) != 0)? OP_ALLANY: OP_ANY; - break; - - - /* ===================================================================*/ - /* Character classes. If the included characters are all < 256, we build a - 32-byte bitmap of the permitted characters, except in the special case - where there is only one such character. For negated classes, we build the - map as usual, then invert it at the end. However, we use a different opcode - so that data characters > 255 can be handled correctly. - - If the class contains characters outside the 0-255 range, a different - opcode is compiled. It may optionally have a bit map for characters < 256, - but those above are are explicitly listed afterwards. A flag byte tells - whether the bitmap is present, and whether this is a negated class or not. - - In JavaScript compatibility mode, an isolated ']' causes an error. In - default (Perl) mode, it is treated as a data character. */ - - case CHAR_RIGHT_SQUARE_BRACKET: - if ((cd->external_options & PCRE_JAVASCRIPT_COMPAT) != 0) - { - *errorcodeptr = ERR64; - goto FAILED; - } - goto NORMAL_CHAR; - - /* In another (POSIX) regex library, the ugly syntax [[:<:]] and [[:>:]] is - used for "start of word" and "end of word". As these are otherwise illegal - sequences, we don't break anything by recognizing them. They are replaced - by \b(?=\w) and \b(?<=\w) respectively. Sequences like [a[:<:]] are - erroneous and are handled by the normal code below. */ - - case CHAR_LEFT_SQUARE_BRACKET: - if (STRNCMP_UC_C8(ptr+1, STRING_WEIRD_STARTWORD, 6) == 0) - { - nestptr = ptr + 7; - ptr = sub_start_of_word - 1; - continue; - } - - if (STRNCMP_UC_C8(ptr+1, STRING_WEIRD_ENDWORD, 6) == 0) - { - nestptr = ptr + 7; - ptr = sub_end_of_word - 1; - continue; - } - - /* Handle a real character class. */ - - previous = code; - item_hwm_offset = cd->hwm - cd->start_workspace; - - /* PCRE supports POSIX class stuff inside a class. Perl gives an error if - they are encountered at the top level, so we'll do that too. */ - - if ((ptr[1] == CHAR_COLON || ptr[1] == CHAR_DOT || - ptr[1] == CHAR_EQUALS_SIGN) && - check_posix_syntax(ptr, &tempptr)) - { - *errorcodeptr = (ptr[1] == CHAR_COLON)? ERR13 : ERR31; - goto FAILED; - } - - /* If the first character is '^', set the negation flag and skip it. Also, - if the first few characters (either before or after ^) are \Q\E or \E we - skip them too. This makes for compatibility with Perl. */ - - negate_class = FALSE; - for (;;) - { - c = *(++ptr); - if (c == CHAR_BACKSLASH) - { - if (ptr[1] == CHAR_E) - ptr++; - else if (STRNCMP_UC_C8(ptr + 1, STR_Q STR_BACKSLASH STR_E, 3) == 0) - ptr += 3; - else - break; - } - else if (!negate_class && c == CHAR_CIRCUMFLEX_ACCENT) - negate_class = TRUE; - else break; - } - - /* Empty classes are allowed in JavaScript compatibility mode. Otherwise, - an initial ']' is taken as a data character -- the code below handles - that. In JS mode, [] must always fail, so generate OP_FAIL, whereas - [^] must match any character, so generate OP_ALLANY. */ - - if (c == CHAR_RIGHT_SQUARE_BRACKET && - (cd->external_options & PCRE_JAVASCRIPT_COMPAT) != 0) - { - *code++ = negate_class? OP_ALLANY : OP_FAIL; - if (firstcharflags == REQ_UNSET) firstcharflags = REQ_NONE; - zerofirstchar = firstchar; - zerofirstcharflags = firstcharflags; - break; - } - - /* If a class contains a negative special such as \S, we need to flip the - negation flag at the end, so that support for characters > 255 works - correctly (they are all included in the class). */ - - should_flip_negation = FALSE; - - /* Extended class (xclass) will be used when characters > 255 - might match. */ - -#if defined SUPPORT_UTF || !defined COMPILE_PCRE8 - xclass = FALSE; - class_uchardata = code + LINK_SIZE + 2; /* For XCLASS items */ - class_uchardata_base = class_uchardata; /* Save the start */ -#endif - - /* For optimization purposes, we track some properties of the class: - class_has_8bitchar will be non-zero if the class contains at least one < - 256 character; class_one_char will be 1 if the class contains just one - character; xclass_has_prop will be TRUE if unicode property checks - are present in the class. */ - - class_has_8bitchar = 0; - class_one_char = 0; -#if defined SUPPORT_UTF || !defined COMPILE_PCRE8 - xclass_has_prop = FALSE; -#endif - - /* Initialize the 32-char bit map to all zeros. We build the map in a - temporary bit of memory, in case the class contains fewer than two - 8-bit characters because in that case the compiled code doesn't use the bit - map. */ - - memset(classbits, 0, 32 * sizeof(pcre_uint8)); - - /* Process characters until ] is reached. By writing this as a "do" it - means that an initial ] is taken as a data character. At the start of the - loop, c contains the first byte of the character. */ - - if (c != CHAR_NULL) do - { - const pcre_uchar *oldptr; - -#ifdef SUPPORT_UTF - if (utf && HAS_EXTRALEN(c)) - { /* Braces are required because the */ - GETCHARLEN(c, ptr, ptr); /* macro generates multiple statements */ - } -#endif - -#if defined SUPPORT_UTF || !defined COMPILE_PCRE8 - /* In the pre-compile phase, accumulate the length of any extra - data and reset the pointer. This is so that very large classes that - contain a zillion > 255 characters no longer overwrite the work space - (which is on the stack). We have to remember that there was XCLASS data, - however. */ - - if (class_uchardata > class_uchardata_base) xclass = TRUE; - - if (lengthptr != NULL && class_uchardata > class_uchardata_base) - { - *lengthptr += (int)(class_uchardata - class_uchardata_base); - class_uchardata = class_uchardata_base; - } -#endif - - /* Inside \Q...\E everything is literal except \E */ - - if (inescq) - { - if (c == CHAR_BACKSLASH && ptr[1] == CHAR_E) /* If we are at \E */ - { - inescq = FALSE; /* Reset literal state */ - ptr++; /* Skip the 'E' */ - continue; /* Carry on with next */ - } - goto CHECK_RANGE; /* Could be range if \E follows */ - } - - /* Handle POSIX class names. Perl allows a negation extension of the - form [:^name:]. A square bracket that doesn't match the syntax is - treated as a literal. We also recognize the POSIX constructions - [.ch.] and [=ch=] ("collating elements") and fault them, as Perl - 5.6 and 5.8 do. */ - - if (c == CHAR_LEFT_SQUARE_BRACKET && - (ptr[1] == CHAR_COLON || ptr[1] == CHAR_DOT || - ptr[1] == CHAR_EQUALS_SIGN) && check_posix_syntax(ptr, &tempptr)) - { - BOOL local_negate = FALSE; - int posix_class, taboffset, tabopt; - register const pcre_uint8 *cbits = cd->cbits; - pcre_uint8 pbits[32]; - - if (ptr[1] != CHAR_COLON) - { - *errorcodeptr = ERR31; - goto FAILED; - } - - ptr += 2; - if (*ptr == CHAR_CIRCUMFLEX_ACCENT) - { - local_negate = TRUE; - should_flip_negation = TRUE; /* Note negative special */ - ptr++; - } - - posix_class = check_posix_name(ptr, (int)(tempptr - ptr)); - if (posix_class < 0) - { - *errorcodeptr = ERR30; - goto FAILED; - } - - /* If matching is caseless, upper and lower are converted to - alpha. This relies on the fact that the class table starts with - alpha, lower, upper as the first 3 entries. */ - - if ((options & PCRE_CASELESS) != 0 && posix_class <= 2) - posix_class = 0; - - /* When PCRE_UCP is set, some of the POSIX classes are converted to - different escape sequences that use Unicode properties \p or \P. Others - that are not available via \p or \P generate XCL_PROP/XCL_NOTPROP - directly. */ - -#ifdef SUPPORT_UCP - if ((options & PCRE_UCP) != 0) - { - unsigned int ptype = 0; - int pc = posix_class + ((local_negate)? POSIX_SUBSIZE/2 : 0); - - /* The posix_substitutes table specifies which POSIX classes can be - converted to \p or \P items. */ - - if (posix_substitutes[pc] != NULL) - { - nestptr = tempptr + 1; - ptr = posix_substitutes[pc] - 1; - continue; - } - - /* There are three other classes that generate special property calls - that are recognized only in an XCLASS. */ - - else switch(posix_class) - { - case PC_GRAPH: - ptype = PT_PXGRAPH; - /* Fall through */ - case PC_PRINT: - if (ptype == 0) ptype = PT_PXPRINT; - /* Fall through */ - case PC_PUNCT: - if (ptype == 0) ptype = PT_PXPUNCT; - *class_uchardata++ = local_negate? XCL_NOTPROP : XCL_PROP; - *class_uchardata++ = ptype; - *class_uchardata++ = 0; - xclass_has_prop = TRUE; - ptr = tempptr + 1; - continue; - - /* For the other POSIX classes (ascii, xdigit) we are going to fall - through to the non-UCP case and build a bit map for characters with - code points less than 256. If we are in a negated POSIX class - within a non-negated overall class, characters with code points - greater than 255 must all match. In the special case where we have - not yet generated any xclass data, and this is the final item in - the overall class, we need do nothing: later on, the opcode - OP_NCLASS will be used to indicate that characters greater than 255 - are acceptable. If we have already seen an xclass item or one may - follow (we have to assume that it might if this is not the end of - the class), explicitly match all wide codepoints. */ - - default: - if (!negate_class && local_negate && - (xclass || tempptr[2] != CHAR_RIGHT_SQUARE_BRACKET)) - { - *class_uchardata++ = XCL_RANGE; - class_uchardata += PRIV(ord2utf)(0x100, class_uchardata); - class_uchardata += PRIV(ord2utf)(0x10ffff, class_uchardata); - } - break; - } - } -#endif - /* In the non-UCP case, or when UCP makes no difference, we build the - bit map for the POSIX class in a chunk of local store because we may be - adding and subtracting from it, and we don't want to subtract bits that - may be in the main map already. At the end we or the result into the - bit map that is being built. */ - - posix_class *= 3; - - /* Copy in the first table (always present) */ - - memcpy(pbits, cbits + posix_class_maps[posix_class], - 32 * sizeof(pcre_uint8)); - - /* If there is a second table, add or remove it as required. */ - - taboffset = posix_class_maps[posix_class + 1]; - tabopt = posix_class_maps[posix_class + 2]; - - if (taboffset >= 0) - { - if (tabopt >= 0) - for (c = 0; c < 32; c++) pbits[c] |= cbits[c + taboffset]; - else - for (c = 0; c < 32; c++) pbits[c] &= ~cbits[c + taboffset]; - } - - /* Now see if we need to remove any special characters. An option - value of 1 removes vertical space and 2 removes underscore. */ - - if (tabopt < 0) tabopt = -tabopt; - if (tabopt == 1) pbits[1] &= ~0x3c; - else if (tabopt == 2) pbits[11] &= 0x7f; - - /* Add the POSIX table or its complement into the main table that is - being built and we are done. */ - - if (local_negate) - for (c = 0; c < 32; c++) classbits[c] |= ~pbits[c]; - else - for (c = 0; c < 32; c++) classbits[c] |= pbits[c]; - - ptr = tempptr + 1; - /* Every class contains at least one < 256 character. */ - class_has_8bitchar = 1; - /* Every class contains at least two characters. */ - class_one_char = 2; - continue; /* End of POSIX syntax handling */ - } - - /* Backslash may introduce a single character, or it may introduce one - of the specials, which just set a flag. The sequence \b is a special - case. Inside a class (and only there) it is treated as backspace. We - assume that other escapes have more than one character in them, so - speculatively set both class_has_8bitchar and class_one_char bigger - than one. Unrecognized escapes fall through and are either treated - as literal characters (by default), or are faulted if - PCRE_EXTRA is set. */ - - if (c == CHAR_BACKSLASH) - { - escape = check_escape(&ptr, &ec, errorcodeptr, cd->bracount, options, - TRUE); - if (*errorcodeptr != 0) goto FAILED; - if (escape == 0) c = ec; - else if (escape == ESC_b) c = CHAR_BS; /* \b is backspace in a class */ - else if (escape == ESC_N) /* \N is not supported in a class */ - { - *errorcodeptr = ERR71; - goto FAILED; - } - else if (escape == ESC_Q) /* Handle start of quoted string */ - { - if (ptr[1] == CHAR_BACKSLASH && ptr[2] == CHAR_E) - { - ptr += 2; /* avoid empty string */ - } - else inescq = TRUE; - continue; - } - else if (escape == ESC_E) continue; /* Ignore orphan \E */ - - else - { - register const pcre_uint8 *cbits = cd->cbits; - /* Every class contains at least two < 256 characters. */ - class_has_8bitchar++; - /* Every class contains at least two characters. */ - class_one_char += 2; - - switch (escape) - { -#ifdef SUPPORT_UCP - case ESC_du: /* These are the values given for \d etc */ - case ESC_DU: /* when PCRE_UCP is set. We replace the */ - case ESC_wu: /* escape sequence with an appropriate \p */ - case ESC_WU: /* or \P to test Unicode properties instead */ - case ESC_su: /* of the default ASCII testing. */ - case ESC_SU: - nestptr = ptr; - ptr = substitutes[escape - ESC_DU] - 1; /* Just before substitute */ - class_has_8bitchar--; /* Undo! */ - continue; -#endif - case ESC_d: - for (c = 0; c < 32; c++) classbits[c] |= cbits[c+cbit_digit]; - continue; - - case ESC_D: - should_flip_negation = TRUE; - for (c = 0; c < 32; c++) classbits[c] |= ~cbits[c+cbit_digit]; - continue; - - case ESC_w: - for (c = 0; c < 32; c++) classbits[c] |= cbits[c+cbit_word]; - continue; - - case ESC_W: - should_flip_negation = TRUE; - for (c = 0; c < 32; c++) classbits[c] |= ~cbits[c+cbit_word]; - continue; - - /* Perl 5.004 onwards omitted VT from \s, but restored it at Perl - 5.18. Before PCRE 8.34, we had to preserve the VT bit if it was - previously set by something earlier in the character class. - Luckily, the value of CHAR_VT is 0x0b in both ASCII and EBCDIC, so - we could just adjust the appropriate bit. From PCRE 8.34 we no - longer treat \s and \S specially. */ - - case ESC_s: - for (c = 0; c < 32; c++) classbits[c] |= cbits[c+cbit_space]; - continue; - - case ESC_S: - should_flip_negation = TRUE; - for (c = 0; c < 32; c++) classbits[c] |= ~cbits[c+cbit_space]; - continue; - - /* The rest apply in both UCP and non-UCP cases. */ - - case ESC_h: - (void)add_list_to_class(classbits, &class_uchardata, options, cd, - PRIV(hspace_list), NOTACHAR); - continue; - - case ESC_H: - (void)add_not_list_to_class(classbits, &class_uchardata, options, - cd, PRIV(hspace_list)); - continue; - - case ESC_v: - (void)add_list_to_class(classbits, &class_uchardata, options, cd, - PRIV(vspace_list), NOTACHAR); - continue; - - case ESC_V: - (void)add_not_list_to_class(classbits, &class_uchardata, options, - cd, PRIV(vspace_list)); - continue; - - case ESC_p: - case ESC_P: -#ifdef SUPPORT_UCP - { - BOOL negated; - unsigned int ptype = 0, pdata = 0; - if (!get_ucp(&ptr, &negated, &ptype, &pdata, errorcodeptr)) - goto FAILED; - *class_uchardata++ = ((escape == ESC_p) != negated)? - XCL_PROP : XCL_NOTPROP; - *class_uchardata++ = ptype; - *class_uchardata++ = pdata; - xclass_has_prop = TRUE; - class_has_8bitchar--; /* Undo! */ - continue; - } -#else - *errorcodeptr = ERR45; - goto FAILED; -#endif - /* Unrecognized escapes are faulted if PCRE is running in its - strict mode. By default, for compatibility with Perl, they are - treated as literals. */ - - default: - if ((options & PCRE_EXTRA) != 0) - { - *errorcodeptr = ERR7; - goto FAILED; - } - class_has_8bitchar--; /* Undo the speculative increase. */ - class_one_char -= 2; /* Undo the speculative increase. */ - c = *ptr; /* Get the final character and fall through */ - break; - } - } - - /* Fall through if the escape just defined a single character (c >= 0). - This may be greater than 256. */ - - escape = 0; - - } /* End of backslash handling */ - - /* A character may be followed by '-' to form a range. However, Perl does - not permit ']' to be the end of the range. A '-' character at the end is - treated as a literal. Perl ignores orphaned \E sequences entirely. The - code for handling \Q and \E is messy. */ - - CHECK_RANGE: - while (ptr[1] == CHAR_BACKSLASH && ptr[2] == CHAR_E) - { - inescq = FALSE; - ptr += 2; - } - oldptr = ptr; - - /* Remember if \r or \n were explicitly used */ - - if (c == CHAR_CR || c == CHAR_NL) cd->external_flags |= PCRE_HASCRORLF; - - /* Check for range */ - - if (!inescq && ptr[1] == CHAR_MINUS) - { - pcre_uint32 d; - ptr += 2; - while (*ptr == CHAR_BACKSLASH && ptr[1] == CHAR_E) ptr += 2; - - /* If we hit \Q (not followed by \E) at this point, go into escaped - mode. */ - - while (*ptr == CHAR_BACKSLASH && ptr[1] == CHAR_Q) - { - ptr += 2; - if (*ptr == CHAR_BACKSLASH && ptr[1] == CHAR_E) - { ptr += 2; continue; } - inescq = TRUE; - break; - } - - /* Minus (hyphen) at the end of a class is treated as a literal, so put - back the pointer and jump to handle the character that preceded it. */ - - if (*ptr == CHAR_NULL || (!inescq && *ptr == CHAR_RIGHT_SQUARE_BRACKET)) - { - ptr = oldptr; - goto CLASS_SINGLE_CHARACTER; - } - - /* Otherwise, we have a potential range; pick up the next character */ - -#ifdef SUPPORT_UTF - if (utf) - { /* Braces are required because the */ - GETCHARLEN(d, ptr, ptr); /* macro generates multiple statements */ - } - else -#endif - d = *ptr; /* Not UTF-8 mode */ - - /* The second part of a range can be a single-character escape - sequence, but not any of the other escapes. Perl treats a hyphen as a - literal in such circumstances. However, in Perl's warning mode, a - warning is given, so PCRE now faults it as it is almost certainly a - mistake on the user's part. */ - - if (!inescq) - { - if (d == CHAR_BACKSLASH) - { - int descape; - descape = check_escape(&ptr, &d, errorcodeptr, cd->bracount, options, TRUE); - if (*errorcodeptr != 0) goto FAILED; - - /* 0 means a character was put into d; \b is backspace; any other - special causes an error. */ - - if (descape != 0) - { - if (descape == ESC_b) d = CHAR_BS; else - { - *errorcodeptr = ERR83; - goto FAILED; - } - } - } - - /* A hyphen followed by a POSIX class is treated in the same way. */ - - else if (d == CHAR_LEFT_SQUARE_BRACKET && - (ptr[1] == CHAR_COLON || ptr[1] == CHAR_DOT || - ptr[1] == CHAR_EQUALS_SIGN) && - check_posix_syntax(ptr, &tempptr)) - { - *errorcodeptr = ERR83; - goto FAILED; - } - } - - /* Check that the two values are in the correct order. Optimize - one-character ranges. */ - - if (d < c) - { - *errorcodeptr = ERR8; - goto FAILED; - } - if (d == c) goto CLASS_SINGLE_CHARACTER; /* A few lines below */ - - /* We have found a character range, so single character optimizations - cannot be done anymore. Any value greater than 1 indicates that there - is more than one character. */ - - class_one_char = 2; - - /* Remember an explicit \r or \n, and add the range to the class. */ - - if (d == CHAR_CR || d == CHAR_NL) cd->external_flags |= PCRE_HASCRORLF; - - class_has_8bitchar += - add_to_class(classbits, &class_uchardata, options, cd, c, d); - - continue; /* Go get the next char in the class */ - } - - /* Handle a single character - we can get here for a normal non-escape - char, or after \ that introduces a single character or for an apparent - range that isn't. Only the value 1 matters for class_one_char, so don't - increase it if it is already 2 or more ... just in case there's a class - with a zillion characters in it. */ - - CLASS_SINGLE_CHARACTER: - if (class_one_char < 2) class_one_char++; - - /* If xclass_has_prop is false and class_one_char is 1, we have the first - single character in the class, and there have been no prior ranges, or - XCLASS items generated by escapes. If this is the final character in the - class, we can optimize by turning the item into a 1-character OP_CHAR[I] - if it's positive, or OP_NOT[I] if it's negative. In the positive case, it - can cause firstchar to be set. Otherwise, there can be no first char if - this item is first, whatever repeat count may follow. In the case of - reqchar, save the previous value for reinstating. */ - - if (!inescq && -#ifdef SUPPORT_UCP - !xclass_has_prop && -#endif - class_one_char == 1 && ptr[1] == CHAR_RIGHT_SQUARE_BRACKET) - { - ptr++; - zeroreqchar = reqchar; - zeroreqcharflags = reqcharflags; - - if (negate_class) - { -#ifdef SUPPORT_UCP - int d; -#endif - if (firstcharflags == REQ_UNSET) firstcharflags = REQ_NONE; - zerofirstchar = firstchar; - zerofirstcharflags = firstcharflags; - - /* For caseless UTF-8 mode when UCP support is available, check - whether this character has more than one other case. If so, generate - a special OP_NOTPROP item instead of OP_NOTI. */ - -#ifdef SUPPORT_UCP - if (utf && (options & PCRE_CASELESS) != 0 && - (d = UCD_CASESET(c)) != 0) - { - *code++ = OP_NOTPROP; - *code++ = PT_CLIST; - *code++ = d; - } - else -#endif - /* Char has only one other case, or UCP not available */ - - { - *code++ = ((options & PCRE_CASELESS) != 0)? OP_NOTI: OP_NOT; -#if defined SUPPORT_UTF && !defined COMPILE_PCRE32 - if (utf && c > MAX_VALUE_FOR_SINGLE_CHAR) - code += PRIV(ord2utf)(c, code); - else -#endif - *code++ = c; - } - - /* We are finished with this character class */ - - goto END_CLASS; - } - - /* For a single, positive character, get the value into mcbuffer, and - then we can handle this with the normal one-character code. */ - -#if defined SUPPORT_UTF && !defined COMPILE_PCRE32 - if (utf && c > MAX_VALUE_FOR_SINGLE_CHAR) - mclength = PRIV(ord2utf)(c, mcbuffer); - else -#endif - { - mcbuffer[0] = c; - mclength = 1; - } - goto ONE_CHAR; - } /* End of 1-char optimization */ - - /* There is more than one character in the class, or an XCLASS item - has been generated. Add this character to the class. */ - - class_has_8bitchar += - add_to_class(classbits, &class_uchardata, options, cd, c, c); - } - - /* Loop until ']' reached. This "while" is the end of the "do" far above. - If we are at the end of an internal nested string, revert to the outer - string. */ - - while (((c = *(++ptr)) != CHAR_NULL || - (nestptr != NULL && - (ptr = nestptr, nestptr = NULL, c = *(++ptr)) != CHAR_NULL)) && - (c != CHAR_RIGHT_SQUARE_BRACKET || inescq)); - - /* Check for missing terminating ']' */ - - if (c == CHAR_NULL) - { - *errorcodeptr = ERR6; - goto FAILED; - } - - /* We will need an XCLASS if data has been placed in class_uchardata. In - the second phase this is a sufficient test. However, in the pre-compile - phase, class_uchardata gets emptied to prevent workspace overflow, so it - only if the very last character in the class needs XCLASS will it contain - anything at this point. For this reason, xclass gets set TRUE above when - uchar_classdata is emptied, and that's why this code is the way it is here - instead of just doing a test on class_uchardata below. */ - -#if defined SUPPORT_UTF || !defined COMPILE_PCRE8 - if (class_uchardata > class_uchardata_base) xclass = TRUE; -#endif - - /* If this is the first thing in the branch, there can be no first char - setting, whatever the repeat count. Any reqchar setting must remain - unchanged after any kind of repeat. */ - - if (firstcharflags == REQ_UNSET) firstcharflags = REQ_NONE; - zerofirstchar = firstchar; - zerofirstcharflags = firstcharflags; - zeroreqchar = reqchar; - zeroreqcharflags = reqcharflags; - - /* If there are characters with values > 255, we have to compile an - extended class, with its own opcode, unless there was a negated special - such as \S in the class, and PCRE_UCP is not set, because in that case all - characters > 255 are in the class, so any that were explicitly given as - well can be ignored. If (when there are explicit characters > 255 that must - be listed) there are no characters < 256, we can omit the bitmap in the - actual compiled code. */ - -#ifdef SUPPORT_UTF - if (xclass && (xclass_has_prop || !should_flip_negation || - (options & PCRE_UCP) != 0)) -#elif !defined COMPILE_PCRE8 - if (xclass && (xclass_has_prop || !should_flip_negation)) -#endif -#if defined SUPPORT_UTF || !defined COMPILE_PCRE8 - { - *class_uchardata++ = XCL_END; /* Marks the end of extra data */ - *code++ = OP_XCLASS; - code += LINK_SIZE; - *code = negate_class? XCL_NOT:0; - if (xclass_has_prop) *code |= XCL_HASPROP; - - /* If the map is required, move up the extra data to make room for it; - otherwise just move the code pointer to the end of the extra data. */ - - if (class_has_8bitchar > 0) - { - *code++ |= XCL_MAP; - memmove(code + (32 / sizeof(pcre_uchar)), code, - IN_UCHARS(class_uchardata - code)); - if (negate_class && !xclass_has_prop) - for (c = 0; c < 32; c++) classbits[c] = ~classbits[c]; - memcpy(code, classbits, 32); - code = class_uchardata + (32 / sizeof(pcre_uchar)); - } - else code = class_uchardata; - - /* Now fill in the complete length of the item */ - - PUT(previous, 1, (int)(code - previous)); - break; /* End of class handling */ - } - - /* Even though any XCLASS list is now discarded, we must allow for - its memory. */ - - if (lengthptr != NULL) - *lengthptr += (int)(class_uchardata - class_uchardata_base); -#endif - - /* If there are no characters > 255, or they are all to be included or - excluded, set the opcode to OP_CLASS or OP_NCLASS, depending on whether the - whole class was negated and whether there were negative specials such as \S - (non-UCP) in the class. Then copy the 32-byte map into the code vector, - negating it if necessary. */ - - *code++ = (negate_class == should_flip_negation) ? OP_CLASS : OP_NCLASS; - if (lengthptr == NULL) /* Save time in the pre-compile phase */ - { - if (negate_class) - for (c = 0; c < 32; c++) classbits[c] = ~classbits[c]; - memcpy(code, classbits, 32); - } - code += 32 / sizeof(pcre_uchar); - - END_CLASS: - break; - - - /* ===================================================================*/ - /* Various kinds of repeat; '{' is not necessarily a quantifier, but this - has been tested above. */ - - case CHAR_LEFT_CURLY_BRACKET: - if (!is_quantifier) goto NORMAL_CHAR; - ptr = read_repeat_counts(ptr+1, &repeat_min, &repeat_max, errorcodeptr); - if (*errorcodeptr != 0) goto FAILED; - goto REPEAT; - - case CHAR_ASTERISK: - repeat_min = 0; - repeat_max = -1; - goto REPEAT; - - case CHAR_PLUS: - repeat_min = 1; - repeat_max = -1; - goto REPEAT; - - case CHAR_QUESTION_MARK: - repeat_min = 0; - repeat_max = 1; - - REPEAT: - if (previous == NULL) - { - *errorcodeptr = ERR9; - goto FAILED; - } - - if (repeat_min == 0) - { - firstchar = zerofirstchar; /* Adjust for zero repeat */ - firstcharflags = zerofirstcharflags; - reqchar = zeroreqchar; /* Ditto */ - reqcharflags = zeroreqcharflags; - } - - /* Remember whether this is a variable length repeat */ - - reqvary = (repeat_min == repeat_max)? 0 : REQ_VARY; - - op_type = 0; /* Default single-char op codes */ - possessive_quantifier = FALSE; /* Default not possessive quantifier */ - - /* Save start of previous item, in case we have to move it up in order to - insert something before it. */ - - tempcode = previous; - - /* Before checking for a possessive quantifier, we must skip over - whitespace and comments in extended mode because Perl allows white space at - this point. */ - - if ((options & PCRE_EXTENDED) != 0) - { - const pcre_uchar *p = ptr + 1; - for (;;) - { - while (MAX_255(*p) && (cd->ctypes[*p] & ctype_space) != 0) p++; - if (*p != CHAR_NUMBER_SIGN) break; - p++; - while (*p != CHAR_NULL) - { - if (IS_NEWLINE(p)) /* For non-fixed-length newline cases, */ - { /* IS_NEWLINE sets cd->nllen. */ - p += cd->nllen; - break; - } - p++; -#ifdef SUPPORT_UTF - if (utf) FORWARDCHAR(p); -#endif - } /* Loop for comment characters */ - } /* Loop for multiple comments */ - ptr = p - 1; /* Character before the next significant one. */ - } - - /* If the next character is '+', we have a possessive quantifier. This - implies greediness, whatever the setting of the PCRE_UNGREEDY option. - If the next character is '?' this is a minimizing repeat, by default, - but if PCRE_UNGREEDY is set, it works the other way round. We change the - repeat type to the non-default. */ - - if (ptr[1] == CHAR_PLUS) - { - repeat_type = 0; /* Force greedy */ - possessive_quantifier = TRUE; - ptr++; - } - else if (ptr[1] == CHAR_QUESTION_MARK) - { - repeat_type = greedy_non_default; - ptr++; - } - else repeat_type = greedy_default; - - /* If previous was a recursion call, wrap it in atomic brackets so that - previous becomes the atomic group. All recursions were so wrapped in the - past, but it no longer happens for non-repeated recursions. In fact, the - repeated ones could be re-implemented independently so as not to need this, - but for the moment we rely on the code for repeating groups. */ - - if (*previous == OP_RECURSE) - { - memmove(previous + 1 + LINK_SIZE, previous, IN_UCHARS(1 + LINK_SIZE)); - *previous = OP_ONCE; - PUT(previous, 1, 2 + 2*LINK_SIZE); - previous[2 + 2*LINK_SIZE] = OP_KET; - PUT(previous, 3 + 2*LINK_SIZE, 2 + 2*LINK_SIZE); - code += 2 + 2 * LINK_SIZE; - length_prevgroup = 3 + 3*LINK_SIZE; - - /* When actually compiling, we need to check whether this was a forward - reference, and if so, adjust the offset. */ - - if (lengthptr == NULL && cd->hwm >= cd->start_workspace + LINK_SIZE) - { - int offset = GET(cd->hwm, -LINK_SIZE); - if (offset == previous + 1 - cd->start_code) - PUT(cd->hwm, -LINK_SIZE, offset + 1 + LINK_SIZE); - } - } - - /* Now handle repetition for the different types of item. */ - - /* If previous was a character or negated character match, abolish the item - and generate a repeat item instead. If a char item has a minimum of more - than one, ensure that it is set in reqchar - it might not be if a sequence - such as x{3} is the first thing in a branch because the x will have gone - into firstchar instead. */ - - if (*previous == OP_CHAR || *previous == OP_CHARI - || *previous == OP_NOT || *previous == OP_NOTI) - { - switch (*previous) - { - default: /* Make compiler happy. */ - case OP_CHAR: op_type = OP_STAR - OP_STAR; break; - case OP_CHARI: op_type = OP_STARI - OP_STAR; break; - case OP_NOT: op_type = OP_NOTSTAR - OP_STAR; break; - case OP_NOTI: op_type = OP_NOTSTARI - OP_STAR; break; - } - - /* Deal with UTF characters that take up more than one character. It's - easier to write this out separately than try to macrify it. Use c to - hold the length of the character in bytes, plus UTF_LENGTH to flag that - it's a length rather than a small character. */ - -#if defined SUPPORT_UTF && !defined COMPILE_PCRE32 - if (utf && NOT_FIRSTCHAR(code[-1])) - { - pcre_uchar *lastchar = code - 1; - BACKCHAR(lastchar); - c = (int)(code - lastchar); /* Length of UTF-8 character */ - memcpy(utf_chars, lastchar, IN_UCHARS(c)); /* Save the char */ - c |= UTF_LENGTH; /* Flag c as a length */ - } - else -#endif /* SUPPORT_UTF */ - - /* Handle the case of a single charater - either with no UTF support, or - with UTF disabled, or for a single character UTF character. */ - { - c = code[-1]; - if (*previous <= OP_CHARI && repeat_min > 1) - { - reqchar = c; - reqcharflags = req_caseopt | cd->req_varyopt; - } - } - - goto OUTPUT_SINGLE_REPEAT; /* Code shared with single character types */ - } - - /* If previous was a character type match (\d or similar), abolish it and - create a suitable repeat item. The code is shared with single-character - repeats by setting op_type to add a suitable offset into repeat_type. Note - the the Unicode property types will be present only when SUPPORT_UCP is - defined, but we don't wrap the little bits of code here because it just - makes it horribly messy. */ - - else if (*previous < OP_EODN) - { - pcre_uchar *oldcode; - int prop_type, prop_value; - op_type = OP_TYPESTAR - OP_STAR; /* Use type opcodes */ - c = *previous; - - OUTPUT_SINGLE_REPEAT: - if (*previous == OP_PROP || *previous == OP_NOTPROP) - { - prop_type = previous[1]; - prop_value = previous[2]; - } - else prop_type = prop_value = -1; - - oldcode = code; - code = previous; /* Usually overwrite previous item */ - - /* If the maximum is zero then the minimum must also be zero; Perl allows - this case, so we do too - by simply omitting the item altogether. */ - - if (repeat_max == 0) goto END_REPEAT; - - /* Combine the op_type with the repeat_type */ - - repeat_type += op_type; - - /* A minimum of zero is handled either as the special case * or ?, or as - an UPTO, with the maximum given. */ - - if (repeat_min == 0) - { - if (repeat_max == -1) *code++ = OP_STAR + repeat_type; - else if (repeat_max == 1) *code++ = OP_QUERY + repeat_type; - else - { - *code++ = OP_UPTO + repeat_type; - PUT2INC(code, 0, repeat_max); - } - } - - /* A repeat minimum of 1 is optimized into some special cases. If the - maximum is unlimited, we use OP_PLUS. Otherwise, the original item is - left in place and, if the maximum is greater than 1, we use OP_UPTO with - one less than the maximum. */ - - else if (repeat_min == 1) - { - if (repeat_max == -1) - *code++ = OP_PLUS + repeat_type; - else - { - code = oldcode; /* leave previous item in place */ - if (repeat_max == 1) goto END_REPEAT; - *code++ = OP_UPTO + repeat_type; - PUT2INC(code, 0, repeat_max - 1); - } - } - - /* The case {n,n} is just an EXACT, while the general case {n,m} is - handled as an EXACT followed by an UPTO. */ - - else - { - *code++ = OP_EXACT + op_type; /* NB EXACT doesn't have repeat_type */ - PUT2INC(code, 0, repeat_min); - - /* If the maximum is unlimited, insert an OP_STAR. Before doing so, - we have to insert the character for the previous code. For a repeated - Unicode property match, there are two extra bytes that define the - required property. In UTF-8 mode, long characters have their length in - c, with the UTF_LENGTH bit as a flag. */ - - if (repeat_max < 0) - { -#if defined SUPPORT_UTF && !defined COMPILE_PCRE32 - if (utf && (c & UTF_LENGTH) != 0) - { - memcpy(code, utf_chars, IN_UCHARS(c & 7)); - code += c & 7; - } - else -#endif - { - *code++ = c; - if (prop_type >= 0) - { - *code++ = prop_type; - *code++ = prop_value; - } - } - *code++ = OP_STAR + repeat_type; - } - - /* Else insert an UPTO if the max is greater than the min, again - preceded by the character, for the previously inserted code. If the - UPTO is just for 1 instance, we can use QUERY instead. */ - - else if (repeat_max != repeat_min) - { -#if defined SUPPORT_UTF && !defined COMPILE_PCRE32 - if (utf && (c & UTF_LENGTH) != 0) - { - memcpy(code, utf_chars, IN_UCHARS(c & 7)); - code += c & 7; - } - else -#endif - *code++ = c; - if (prop_type >= 0) - { - *code++ = prop_type; - *code++ = prop_value; - } - repeat_max -= repeat_min; - - if (repeat_max == 1) - { - *code++ = OP_QUERY + repeat_type; - } - else - { - *code++ = OP_UPTO + repeat_type; - PUT2INC(code, 0, repeat_max); - } - } - } - - /* The character or character type itself comes last in all cases. */ - -#if defined SUPPORT_UTF && !defined COMPILE_PCRE32 - if (utf && (c & UTF_LENGTH) != 0) - { - memcpy(code, utf_chars, IN_UCHARS(c & 7)); - code += c & 7; - } - else -#endif - *code++ = c; - - /* For a repeated Unicode property match, there are two extra bytes that - define the required property. */ - -#ifdef SUPPORT_UCP - if (prop_type >= 0) - { - *code++ = prop_type; - *code++ = prop_value; - } -#endif - } - - /* If previous was a character class or a back reference, we put the repeat - stuff after it, but just skip the item if the repeat was {0,0}. */ - - else if (*previous == OP_CLASS || *previous == OP_NCLASS || -#if defined SUPPORT_UTF || !defined COMPILE_PCRE8 - *previous == OP_XCLASS || -#endif - *previous == OP_REF || *previous == OP_REFI || - *previous == OP_DNREF || *previous == OP_DNREFI) - { - if (repeat_max == 0) - { - code = previous; - goto END_REPEAT; - } - - if (repeat_min == 0 && repeat_max == -1) - *code++ = OP_CRSTAR + repeat_type; - else if (repeat_min == 1 && repeat_max == -1) - *code++ = OP_CRPLUS + repeat_type; - else if (repeat_min == 0 && repeat_max == 1) - *code++ = OP_CRQUERY + repeat_type; - else - { - *code++ = OP_CRRANGE + repeat_type; - PUT2INC(code, 0, repeat_min); - if (repeat_max == -1) repeat_max = 0; /* 2-byte encoding for max */ - PUT2INC(code, 0, repeat_max); - } - } - - /* If previous was a bracket group, we may have to replicate it in certain - cases. Note that at this point we can encounter only the "basic" bracket - opcodes such as BRA and CBRA, as this is the place where they get converted - into the more special varieties such as BRAPOS and SBRA. A test for >= - OP_ASSERT and <= OP_COND includes ASSERT, ASSERT_NOT, ASSERTBACK, - ASSERTBACK_NOT, ONCE, ONCE_NC, BRA, BRAPOS, CBRA, CBRAPOS, and COND. - Originally, PCRE did not allow repetition of assertions, but now it does, - for Perl compatibility. */ - - else if (*previous >= OP_ASSERT && *previous <= OP_COND) - { - register int i; - int len = (int)(code - previous); - size_t base_hwm_offset = item_hwm_offset; - pcre_uchar *bralink = NULL; - pcre_uchar *brazeroptr = NULL; - - /* Repeating a DEFINE group is pointless, but Perl allows the syntax, so - we just ignore the repeat. */ - - if (*previous == OP_COND && previous[LINK_SIZE+1] == OP_DEF) - goto END_REPEAT; - - /* There is no sense in actually repeating assertions. The only potential - use of repetition is in cases when the assertion is optional. Therefore, - if the minimum is greater than zero, just ignore the repeat. If the - maximum is not zero or one, set it to 1. */ - - if (*previous < OP_ONCE) /* Assertion */ - { - if (repeat_min > 0) goto END_REPEAT; - if (repeat_max < 0 || repeat_max > 1) repeat_max = 1; - } - - /* The case of a zero minimum is special because of the need to stick - OP_BRAZERO in front of it, and because the group appears once in the - data, whereas in other cases it appears the minimum number of times. For - this reason, it is simplest to treat this case separately, as otherwise - the code gets far too messy. There are several special subcases when the - minimum is zero. */ - - if (repeat_min == 0) - { - /* If the maximum is also zero, we used to just omit the group from the - output altogether, like this: - - ** if (repeat_max == 0) - ** { - ** code = previous; - ** goto END_REPEAT; - ** } - - However, that fails when a group or a subgroup within it is referenced - as a subroutine from elsewhere in the pattern, so now we stick in - OP_SKIPZERO in front of it so that it is skipped on execution. As we - don't have a list of which groups are referenced, we cannot do this - selectively. - - If the maximum is 1 or unlimited, we just have to stick in the BRAZERO - and do no more at this point. However, we do need to adjust any - OP_RECURSE calls inside the group that refer to the group itself or any - internal or forward referenced group, because the offset is from the - start of the whole regex. Temporarily terminate the pattern while doing - this. */ - - if (repeat_max <= 1) /* Covers 0, 1, and unlimited */ - { - *code = OP_END; - adjust_recurse(previous, 1, utf, cd, item_hwm_offset); - memmove(previous + 1, previous, IN_UCHARS(len)); - code++; - if (repeat_max == 0) - { - *previous++ = OP_SKIPZERO; - goto END_REPEAT; - } - brazeroptr = previous; /* Save for possessive optimizing */ - *previous++ = OP_BRAZERO + repeat_type; - } - - /* If the maximum is greater than 1 and limited, we have to replicate - in a nested fashion, sticking OP_BRAZERO before each set of brackets. - The first one has to be handled carefully because it's the original - copy, which has to be moved up. The remainder can be handled by code - that is common with the non-zero minimum case below. We have to - adjust the value or repeat_max, since one less copy is required. Once - again, we may have to adjust any OP_RECURSE calls inside the group. */ - - else - { - int offset; - *code = OP_END; - adjust_recurse(previous, 2 + LINK_SIZE, utf, cd, item_hwm_offset); - memmove(previous + 2 + LINK_SIZE, previous, IN_UCHARS(len)); - code += 2 + LINK_SIZE; - *previous++ = OP_BRAZERO + repeat_type; - *previous++ = OP_BRA; - - /* We chain together the bracket offset fields that have to be - filled in later when the ends of the brackets are reached. */ - - offset = (bralink == NULL)? 0 : (int)(previous - bralink); - bralink = previous; - PUTINC(previous, 0, offset); - } - - repeat_max--; - } - - /* If the minimum is greater than zero, replicate the group as many - times as necessary, and adjust the maximum to the number of subsequent - copies that we need. If we set a first char from the group, and didn't - set a required char, copy the latter from the former. If there are any - forward reference subroutine calls in the group, there will be entries on - the workspace list; replicate these with an appropriate increment. */ - - else - { - if (repeat_min > 1) - { - /* In the pre-compile phase, we don't actually do the replication. We - just adjust the length as if we had. Do some paranoid checks for - potential integer overflow. The INT64_OR_DOUBLE type is a 64-bit - integer type when available, otherwise double. */ - - if (lengthptr != NULL) - { - int delta = (repeat_min - 1)*length_prevgroup; - if ((INT64_OR_DOUBLE)(repeat_min - 1)* - (INT64_OR_DOUBLE)length_prevgroup > - (INT64_OR_DOUBLE)INT_MAX || - OFLOW_MAX - *lengthptr < delta) - { - *errorcodeptr = ERR20; - goto FAILED; - } - *lengthptr += delta; - } - - /* This is compiling for real. If there is a set first byte for - the group, and we have not yet set a "required byte", set it. Make - sure there is enough workspace for copying forward references before - doing the copy. */ - - else - { - if (groupsetfirstchar && reqcharflags < 0) - { - reqchar = firstchar; - reqcharflags = firstcharflags; - } - - for (i = 1; i < repeat_min; i++) - { - pcre_uchar *hc; - size_t this_hwm_offset = cd->hwm - cd->start_workspace; - memcpy(code, previous, IN_UCHARS(len)); - - while (cd->hwm > cd->start_workspace + cd->workspace_size - - WORK_SIZE_SAFETY_MARGIN - - (this_hwm_offset - base_hwm_offset)) - { - *errorcodeptr = expand_workspace(cd); - if (*errorcodeptr != 0) goto FAILED; - } - - for (hc = (pcre_uchar *)cd->start_workspace + base_hwm_offset; - hc < (pcre_uchar *)cd->start_workspace + this_hwm_offset; - hc += LINK_SIZE) - { - PUT(cd->hwm, 0, GET(hc, 0) + len); - cd->hwm += LINK_SIZE; - } - base_hwm_offset = this_hwm_offset; - code += len; - } - } - } - - if (repeat_max > 0) repeat_max -= repeat_min; - } - - /* This code is common to both the zero and non-zero minimum cases. If - the maximum is limited, it replicates the group in a nested fashion, - remembering the bracket starts on a stack. In the case of a zero minimum, - the first one was set up above. In all cases the repeat_max now specifies - the number of additional copies needed. Again, we must remember to - replicate entries on the forward reference list. */ - - if (repeat_max >= 0) - { - /* In the pre-compile phase, we don't actually do the replication. We - just adjust the length as if we had. For each repetition we must add 1 - to the length for BRAZERO and for all but the last repetition we must - add 2 + 2*LINKSIZE to allow for the nesting that occurs. Do some - paranoid checks to avoid integer overflow. The INT64_OR_DOUBLE type is - a 64-bit integer type when available, otherwise double. */ - - if (lengthptr != NULL && repeat_max > 0) - { - int delta = repeat_max * (length_prevgroup + 1 + 2 + 2*LINK_SIZE) - - 2 - 2*LINK_SIZE; /* Last one doesn't nest */ - if ((INT64_OR_DOUBLE)repeat_max * - (INT64_OR_DOUBLE)(length_prevgroup + 1 + 2 + 2*LINK_SIZE) - > (INT64_OR_DOUBLE)INT_MAX || - OFLOW_MAX - *lengthptr < delta) - { - *errorcodeptr = ERR20; - goto FAILED; - } - *lengthptr += delta; - } - - /* This is compiling for real */ - - else for (i = repeat_max - 1; i >= 0; i--) - { - pcre_uchar *hc; - size_t this_hwm_offset = cd->hwm - cd->start_workspace; - - *code++ = OP_BRAZERO + repeat_type; - - /* All but the final copy start a new nesting, maintaining the - chain of brackets outstanding. */ - - if (i != 0) - { - int offset; - *code++ = OP_BRA; - offset = (bralink == NULL)? 0 : (int)(code - bralink); - bralink = code; - PUTINC(code, 0, offset); - } - - memcpy(code, previous, IN_UCHARS(len)); - - /* Ensure there is enough workspace for forward references before - copying them. */ - - while (cd->hwm > cd->start_workspace + cd->workspace_size - - WORK_SIZE_SAFETY_MARGIN - - (this_hwm_offset - base_hwm_offset)) - { - *errorcodeptr = expand_workspace(cd); - if (*errorcodeptr != 0) goto FAILED; - } - - for (hc = (pcre_uchar *)cd->start_workspace + base_hwm_offset; - hc < (pcre_uchar *)cd->start_workspace + this_hwm_offset; - hc += LINK_SIZE) - { - PUT(cd->hwm, 0, GET(hc, 0) + len + ((i != 0)? 2+LINK_SIZE : 1)); - cd->hwm += LINK_SIZE; - } - base_hwm_offset = this_hwm_offset; - code += len; - } - - /* Now chain through the pending brackets, and fill in their length - fields (which are holding the chain links pro tem). */ - - while (bralink != NULL) - { - int oldlinkoffset; - int offset = (int)(code - bralink + 1); - pcre_uchar *bra = code - offset; - oldlinkoffset = GET(bra, 1); - bralink = (oldlinkoffset == 0)? NULL : bralink - oldlinkoffset; - *code++ = OP_KET; - PUTINC(code, 0, offset); - PUT(bra, 1, offset); - } - } - - /* If the maximum is unlimited, set a repeater in the final copy. For - ONCE brackets, that's all we need to do. However, possessively repeated - ONCE brackets can be converted into non-capturing brackets, as the - behaviour of (?:xx)++ is the same as (?>xx)++ and this saves having to - deal with possessive ONCEs specially. - - Otherwise, when we are doing the actual compile phase, check to see - whether this group is one that could match an empty string. If so, - convert the initial operator to the S form (e.g. OP_BRA -> OP_SBRA) so - that runtime checking can be done. [This check is also applied to ONCE - groups at runtime, but in a different way.] - - Then, if the quantifier was possessive and the bracket is not a - conditional, we convert the BRA code to the POS form, and the KET code to - KETRPOS. (It turns out to be convenient at runtime to detect this kind of - subpattern at both the start and at the end.) The use of special opcodes - makes it possible to reduce greatly the stack usage in pcre_exec(). If - the group is preceded by OP_BRAZERO, convert this to OP_BRAPOSZERO. - - Then, if the minimum number of matches is 1 or 0, cancel the possessive - flag so that the default action below, of wrapping everything inside - atomic brackets, does not happen. When the minimum is greater than 1, - there will be earlier copies of the group, and so we still have to wrap - the whole thing. */ - - else - { - pcre_uchar *ketcode = code - 1 - LINK_SIZE; - pcre_uchar *bracode = ketcode - GET(ketcode, 1); - - /* Convert possessive ONCE brackets to non-capturing */ - - if ((*bracode == OP_ONCE || *bracode == OP_ONCE_NC) && - possessive_quantifier) *bracode = OP_BRA; - - /* For non-possessive ONCE brackets, all we need to do is to - set the KET. */ - - if (*bracode == OP_ONCE || *bracode == OP_ONCE_NC) - *ketcode = OP_KETRMAX + repeat_type; - - /* Handle non-ONCE brackets and possessive ONCEs (which have been - converted to non-capturing above). */ - - else - { - /* In the compile phase, check for empty string matching. */ - - if (lengthptr == NULL) - { - pcre_uchar *scode = bracode; - do - { - if (could_be_empty_branch(scode, ketcode, utf, cd, NULL)) - { - *bracode += OP_SBRA - OP_BRA; - break; - } - scode += GET(scode, 1); - } - while (*scode == OP_ALT); - } - - /* A conditional group with only one branch has an implicit empty - alternative branch. */ - - if (*bracode == OP_COND && bracode[GET(bracode,1)] != OP_ALT) - *bracode = OP_SCOND; - - /* Handle possessive quantifiers. */ - - if (possessive_quantifier) - { - /* For COND brackets, we wrap the whole thing in a possessively - repeated non-capturing bracket, because we have not invented POS - versions of the COND opcodes. Because we are moving code along, we - must ensure that any pending recursive references are updated. */ - - if (*bracode == OP_COND || *bracode == OP_SCOND) - { - int nlen = (int)(code - bracode); - *code = OP_END; - adjust_recurse(bracode, 1 + LINK_SIZE, utf, cd, item_hwm_offset); - memmove(bracode + 1 + LINK_SIZE, bracode, IN_UCHARS(nlen)); - code += 1 + LINK_SIZE; - nlen += 1 + LINK_SIZE; - *bracode = (*bracode == OP_COND)? OP_BRAPOS : OP_SBRAPOS; - *code++ = OP_KETRPOS; - PUTINC(code, 0, nlen); - PUT(bracode, 1, nlen); - } - - /* For non-COND brackets, we modify the BRA code and use KETRPOS. */ - - else - { - *bracode += 1; /* Switch to xxxPOS opcodes */ - *ketcode = OP_KETRPOS; - } - - /* If the minimum is zero, mark it as possessive, then unset the - possessive flag when the minimum is 0 or 1. */ - - if (brazeroptr != NULL) *brazeroptr = OP_BRAPOSZERO; - if (repeat_min < 2) possessive_quantifier = FALSE; - } - - /* Non-possessive quantifier */ - - else *ketcode = OP_KETRMAX + repeat_type; - } - } - } - - /* If previous is OP_FAIL, it was generated by an empty class [] in - JavaScript mode. The other ways in which OP_FAIL can be generated, that is - by (*FAIL) or (?!) set previous to NULL, which gives a "nothing to repeat" - error above. We can just ignore the repeat in JS case. */ - - else if (*previous == OP_FAIL) goto END_REPEAT; - - /* Else there's some kind of shambles */ - - else - { - *errorcodeptr = ERR11; - goto FAILED; - } - - /* If the character following a repeat is '+', possessive_quantifier is - TRUE. For some opcodes, there are special alternative opcodes for this - case. For anything else, we wrap the entire repeated item inside OP_ONCE - brackets. Logically, the '+' notation is just syntactic sugar, taken from - Sun's Java package, but the special opcodes can optimize it. - - Some (but not all) possessively repeated subpatterns have already been - completely handled in the code just above. For them, possessive_quantifier - is always FALSE at this stage. Note that the repeated item starts at - tempcode, not at previous, which might be the first part of a string whose - (former) last char we repeated. */ - - if (possessive_quantifier) - { - int len; - - /* Possessifying an EXACT quantifier has no effect, so we can ignore it. - However, QUERY, STAR, or UPTO may follow (for quantifiers such as {5,6}, - {5,}, or {5,10}). We skip over an EXACT item; if the length of what - remains is greater than zero, there's a further opcode that can be - handled. If not, do nothing, leaving the EXACT alone. */ - - switch(*tempcode) - { - case OP_TYPEEXACT: - tempcode += PRIV(OP_lengths)[*tempcode] + - ((tempcode[1 + IMM2_SIZE] == OP_PROP - || tempcode[1 + IMM2_SIZE] == OP_NOTPROP)? 2 : 0); - break; - - /* CHAR opcodes are used for exacts whose count is 1. */ - - case OP_CHAR: - case OP_CHARI: - case OP_NOT: - case OP_NOTI: - case OP_EXACT: - case OP_EXACTI: - case OP_NOTEXACT: - case OP_NOTEXACTI: - tempcode += PRIV(OP_lengths)[*tempcode]; -#ifdef SUPPORT_UTF - if (utf && HAS_EXTRALEN(tempcode[-1])) - tempcode += GET_EXTRALEN(tempcode[-1]); -#endif - break; - - /* For the class opcodes, the repeat operator appears at the end; - adjust tempcode to point to it. */ - - case OP_CLASS: - case OP_NCLASS: - tempcode += 1 + 32/sizeof(pcre_uchar); - break; - -#if defined SUPPORT_UTF || !defined COMPILE_PCRE8 - case OP_XCLASS: - tempcode += GET(tempcode, 1); - break; -#endif - } - - /* If tempcode is equal to code (which points to the end of the repeated - item), it means we have skipped an EXACT item but there is no following - QUERY, STAR, or UPTO; the value of len will be 0, and we do nothing. In - all other cases, tempcode will be pointing to the repeat opcode, and will - be less than code, so the value of len will be greater than 0. */ - - len = (int)(code - tempcode); - if (len > 0) - { - unsigned int repcode = *tempcode; - - /* There is a table for possessifying opcodes, all of which are less - than OP_CALLOUT. A zero entry means there is no possessified version. - */ - - if (repcode < OP_CALLOUT && opcode_possessify[repcode] > 0) - *tempcode = opcode_possessify[repcode]; - - /* For opcode without a special possessified version, wrap the item in - ONCE brackets. Because we are moving code along, we must ensure that any - pending recursive references are updated. */ - - else - { - *code = OP_END; - adjust_recurse(tempcode, 1 + LINK_SIZE, utf, cd, item_hwm_offset); - memmove(tempcode + 1 + LINK_SIZE, tempcode, IN_UCHARS(len)); - code += 1 + LINK_SIZE; - len += 1 + LINK_SIZE; - tempcode[0] = OP_ONCE; - *code++ = OP_KET; - PUTINC(code, 0, len); - PUT(tempcode, 1, len); - } - } - -#ifdef NEVER - if (len > 0) switch (*tempcode) - { - case OP_STAR: *tempcode = OP_POSSTAR; break; - case OP_PLUS: *tempcode = OP_POSPLUS; break; - case OP_QUERY: *tempcode = OP_POSQUERY; break; - case OP_UPTO: *tempcode = OP_POSUPTO; break; - - case OP_STARI: *tempcode = OP_POSSTARI; break; - case OP_PLUSI: *tempcode = OP_POSPLUSI; break; - case OP_QUERYI: *tempcode = OP_POSQUERYI; break; - case OP_UPTOI: *tempcode = OP_POSUPTOI; break; - - case OP_NOTSTAR: *tempcode = OP_NOTPOSSTAR; break; - case OP_NOTPLUS: *tempcode = OP_NOTPOSPLUS; break; - case OP_NOTQUERY: *tempcode = OP_NOTPOSQUERY; break; - case OP_NOTUPTO: *tempcode = OP_NOTPOSUPTO; break; - - case OP_NOTSTARI: *tempcode = OP_NOTPOSSTARI; break; - case OP_NOTPLUSI: *tempcode = OP_NOTPOSPLUSI; break; - case OP_NOTQUERYI: *tempcode = OP_NOTPOSQUERYI; break; - case OP_NOTUPTOI: *tempcode = OP_NOTPOSUPTOI; break; - - case OP_TYPESTAR: *tempcode = OP_TYPEPOSSTAR; break; - case OP_TYPEPLUS: *tempcode = OP_TYPEPOSPLUS; break; - case OP_TYPEQUERY: *tempcode = OP_TYPEPOSQUERY; break; - case OP_TYPEUPTO: *tempcode = OP_TYPEPOSUPTO; break; - - case OP_CRSTAR: *tempcode = OP_CRPOSSTAR; break; - case OP_CRPLUS: *tempcode = OP_CRPOSPLUS; break; - case OP_CRQUERY: *tempcode = OP_CRPOSQUERY; break; - case OP_CRRANGE: *tempcode = OP_CRPOSRANGE; break; - - /* Because we are moving code along, we must ensure that any - pending recursive references are updated. */ - - default: - *code = OP_END; - adjust_recurse(tempcode, 1 + LINK_SIZE, utf, cd, item_hwm_offset); - memmove(tempcode + 1 + LINK_SIZE, tempcode, IN_UCHARS(len)); - code += 1 + LINK_SIZE; - len += 1 + LINK_SIZE; - tempcode[0] = OP_ONCE; - *code++ = OP_KET; - PUTINC(code, 0, len); - PUT(tempcode, 1, len); - break; - } -#endif - } - - /* In all case we no longer have a previous item. We also set the - "follows varying string" flag for subsequently encountered reqchars if - it isn't already set and we have just passed a varying length item. */ - - END_REPEAT: - previous = NULL; - cd->req_varyopt |= reqvary; - break; - - - /* ===================================================================*/ - /* Start of nested parenthesized sub-expression, or comment or lookahead or - lookbehind or option setting or condition or all the other extended - parenthesis forms. */ - - case CHAR_LEFT_PARENTHESIS: - ptr++; - - /* First deal with comments. Putting this code right at the start ensures - that comments have no bad side effects. */ - - if (ptr[0] == CHAR_QUESTION_MARK && ptr[1] == CHAR_NUMBER_SIGN) - { - ptr += 2; - while (*ptr != CHAR_NULL && *ptr != CHAR_RIGHT_PARENTHESIS) ptr++; - if (*ptr == CHAR_NULL) - { - *errorcodeptr = ERR18; - goto FAILED; - } - continue; - } - - /* Now deal with various "verbs" that can be introduced by '*'. */ - - if (ptr[0] == CHAR_ASTERISK && (ptr[1] == ':' - || (MAX_255(ptr[1]) && ((cd->ctypes[ptr[1]] & ctype_letter) != 0)))) - { - int i, namelen; - int arglen = 0; - const char *vn = verbnames; - const pcre_uchar *name = ptr + 1; - const pcre_uchar *arg = NULL; - previous = NULL; - ptr++; - while (MAX_255(*ptr) && (cd->ctypes[*ptr] & ctype_letter) != 0) ptr++; - namelen = (int)(ptr - name); - - /* It appears that Perl allows any characters whatsoever, other than - a closing parenthesis, to appear in arguments, so we no longer insist on - letters, digits, and underscores. */ - - if (*ptr == CHAR_COLON) - { - arg = ++ptr; - while (*ptr != CHAR_NULL && *ptr != CHAR_RIGHT_PARENTHESIS) ptr++; - arglen = (int)(ptr - arg); - if ((unsigned int)arglen > MAX_MARK) - { - *errorcodeptr = ERR75; - goto FAILED; - } - } - - if (*ptr != CHAR_RIGHT_PARENTHESIS) - { - *errorcodeptr = ERR60; - goto FAILED; - } - - /* Scan the table of verb names */ - - for (i = 0; i < verbcount; i++) - { - if (namelen == verbs[i].len && - STRNCMP_UC_C8(name, vn, namelen) == 0) - { - int setverb; - - /* Check for open captures before ACCEPT and convert it to - ASSERT_ACCEPT if in an assertion. */ - - if (verbs[i].op == OP_ACCEPT) - { - open_capitem *oc; - if (arglen != 0) - { - *errorcodeptr = ERR59; - goto FAILED; - } - cd->had_accept = TRUE; - for (oc = cd->open_caps; oc != NULL; oc = oc->next) - { - *code++ = OP_CLOSE; - PUT2INC(code, 0, oc->number); - } - setverb = *code++ = - (cd->assert_depth > 0)? OP_ASSERT_ACCEPT : OP_ACCEPT; - - /* Do not set firstchar after *ACCEPT */ - if (firstcharflags == REQ_UNSET) firstcharflags = REQ_NONE; - } - - /* Handle other cases with/without an argument */ - - else if (arglen == 0) - { - if (verbs[i].op < 0) /* Argument is mandatory */ - { - *errorcodeptr = ERR66; - goto FAILED; - } - setverb = *code++ = verbs[i].op; - } - - else - { - if (verbs[i].op_arg < 0) /* Argument is forbidden */ - { - *errorcodeptr = ERR59; - goto FAILED; - } - setverb = *code++ = verbs[i].op_arg; - if (lengthptr != NULL) /* In pass 1 just add in the length */ - { /* to avoid potential workspace */ - *lengthptr += arglen; /* overflow. */ - *code++ = 0; - } - else - { - *code++ = arglen; - memcpy(code, arg, IN_UCHARS(arglen)); - code += arglen; - } - *code++ = 0; - } - - switch (setverb) - { - case OP_THEN: - case OP_THEN_ARG: - cd->external_flags |= PCRE_HASTHEN; - break; - - case OP_PRUNE: - case OP_PRUNE_ARG: - case OP_SKIP: - case OP_SKIP_ARG: - cd->had_pruneorskip = TRUE; - break; - } - - break; /* Found verb, exit loop */ - } - - vn += verbs[i].len + 1; - } - - if (i < verbcount) continue; /* Successfully handled a verb */ - *errorcodeptr = ERR60; /* Verb not recognized */ - goto FAILED; - } - - /* Initialize for "real" parentheses */ - - newoptions = options; - skipbytes = 0; - bravalue = OP_CBRA; - item_hwm_offset = cd->hwm - cd->start_workspace; - reset_bracount = FALSE; - - /* Deal with the extended parentheses; all are introduced by '?', and the - appearance of any of them means that this is not a capturing group. */ - - if (*ptr == CHAR_QUESTION_MARK) - { - int i, set, unset, namelen; - int *optset; - const pcre_uchar *name; - pcre_uchar *slot; - - switch (*(++ptr)) - { - /* ------------------------------------------------------------ */ - case CHAR_VERTICAL_LINE: /* Reset capture count for each branch */ - reset_bracount = TRUE; - cd->dupgroups = TRUE; /* Record (?| encountered */ - /* Fall through */ - - /* ------------------------------------------------------------ */ - case CHAR_COLON: /* Non-capturing bracket */ - bravalue = OP_BRA; - ptr++; - break; - - - /* ------------------------------------------------------------ */ - case CHAR_LEFT_PARENTHESIS: - bravalue = OP_COND; /* Conditional group */ - tempptr = ptr; - - /* A condition can be an assertion, a number (referring to a numbered - group's having been set), a name (referring to a named group), or 'R', - referring to recursion. R<digits> and R&name are also permitted for - recursion tests. - - There are ways of testing a named group: (?(name)) is used by Python; - Perl 5.10 onwards uses (?(<name>) or (?('name')). - - There is one unfortunate ambiguity, caused by history. 'R' can be the - recursive thing or the name 'R' (and similarly for 'R' followed by - digits). We look for a name first; if not found, we try the other case. - - For compatibility with auto-callouts, we allow a callout to be - specified before a condition that is an assertion. First, check for the - syntax of a callout; if found, adjust the temporary pointer that is - used to check for an assertion condition. That's all that is needed! */ - - if (ptr[1] == CHAR_QUESTION_MARK && ptr[2] == CHAR_C) - { - for (i = 3;; i++) if (!IS_DIGIT(ptr[i])) break; - if (ptr[i] == CHAR_RIGHT_PARENTHESIS) - tempptr += i + 1; - } - - /* For conditions that are assertions, check the syntax, and then exit - the switch. This will take control down to where bracketed groups, - including assertions, are processed. */ - - if (tempptr[1] == CHAR_QUESTION_MARK && - (tempptr[2] == CHAR_EQUALS_SIGN || - tempptr[2] == CHAR_EXCLAMATION_MARK || - (tempptr[2] == CHAR_LESS_THAN_SIGN && - (tempptr[3] == CHAR_EQUALS_SIGN || - tempptr[3] == CHAR_EXCLAMATION_MARK)))) - { - cd->iscondassert = TRUE; - break; - } - - /* Other conditions use OP_CREF/OP_DNCREF/OP_RREF/OP_DNRREF, and all - need to skip at least 1+IMM2_SIZE bytes at the start of the group. */ - - code[1+LINK_SIZE] = OP_CREF; - skipbytes = 1+IMM2_SIZE; - refsign = -1; /* => not a number */ - namelen = -1; /* => not a name; must set to avoid warning */ - name = NULL; /* Always set to avoid warning */ - recno = 0; /* Always set to avoid warning */ - - /* Check for a test for recursion in a named group. */ - - ptr++; - if (*ptr == CHAR_R && ptr[1] == CHAR_AMPERSAND) - { - terminator = -1; - ptr += 2; - code[1+LINK_SIZE] = OP_RREF; /* Change the type of test */ - } - - /* Check for a test for a named group's having been set, using the Perl - syntax (?(<name>) or (?('name'), and also allow for the original PCRE - syntax of (?(name) or for (?(+n), (?(-n), and just (?(n). */ - - else if (*ptr == CHAR_LESS_THAN_SIGN) - { - terminator = CHAR_GREATER_THAN_SIGN; - ptr++; - } - else if (*ptr == CHAR_APOSTROPHE) - { - terminator = CHAR_APOSTROPHE; - ptr++; - } - else - { - terminator = CHAR_NULL; - if (*ptr == CHAR_MINUS || *ptr == CHAR_PLUS) refsign = *ptr++; - else if (IS_DIGIT(*ptr)) refsign = 0; - } - - /* Handle a number */ - - if (refsign >= 0) - { - while (IS_DIGIT(*ptr)) - { - if (recno > INT_MAX / 10 - 1) /* Integer overflow */ - { - while (IS_DIGIT(*ptr)) ptr++; - *errorcodeptr = ERR61; - goto FAILED; - } - recno = recno * 10 + (int)(*ptr - CHAR_0); - ptr++; - } - } - - /* Otherwise we expect to read a name; anything else is an error. When - a name is one of a number of duplicates, a different opcode is used and - it needs more memory. Unfortunately we cannot tell whether a name is a - duplicate in the first pass, so we have to allow for more memory. */ - - else - { - if (IS_DIGIT(*ptr)) - { - *errorcodeptr = ERR84; - goto FAILED; - } - if (!MAX_255(*ptr) || (cd->ctypes[*ptr] & ctype_word) == 0) - { - *errorcodeptr = ERR28; /* Assertion expected */ - goto FAILED; - } - name = ptr++; - while (MAX_255(*ptr) && (cd->ctypes[*ptr] & ctype_word) != 0) - { - ptr++; - } - namelen = (int)(ptr - name); - if (lengthptr != NULL) skipbytes += IMM2_SIZE; - } - - /* Check the terminator */ - - if ((terminator > 0 && *ptr++ != (pcre_uchar)terminator) || - *ptr++ != CHAR_RIGHT_PARENTHESIS) - { - ptr--; /* Error offset */ - *errorcodeptr = ERR26; /* Malformed number or name */ - goto FAILED; - } - - /* Do no further checking in the pre-compile phase. */ - - if (lengthptr != NULL) break; - - /* In the real compile we do the work of looking for the actual - reference. If refsign is not negative, it means we have a number in - recno. */ - - if (refsign >= 0) - { - if (recno <= 0) - { - *errorcodeptr = ERR35; - goto FAILED; - } - if (refsign != 0) recno = (refsign == CHAR_MINUS)? - cd->bracount - recno + 1 : recno + cd->bracount; - if (recno <= 0 || recno > cd->final_bracount) - { - *errorcodeptr = ERR15; - goto FAILED; - } - PUT2(code, 2+LINK_SIZE, recno); - if (recno > cd->top_backref) cd->top_backref = recno; - break; - } - - /* Otherwise look for the name. */ - - slot = cd->name_table; - for (i = 0; i < cd->names_found; i++) - { - if (STRNCMP_UC_UC(name, slot+IMM2_SIZE, namelen) == 0) break; - slot += cd->name_entry_size; - } - - /* Found the named subpattern. If the name is duplicated, add one to - the opcode to change CREF/RREF into DNCREF/DNRREF and insert - appropriate data values. Otherwise, just insert the unique subpattern - number. */ - - if (i < cd->names_found) - { - int offset = i++; - int count = 1; - recno = GET2(slot, 0); /* Number from first found */ - if (recno > cd->top_backref) cd->top_backref = recno; - for (; i < cd->names_found; i++) - { - slot += cd->name_entry_size; - if (STRNCMP_UC_UC(name, slot+IMM2_SIZE, namelen) != 0 || - (slot+IMM2_SIZE)[namelen] != 0) break; - count++; - } - - if (count > 1) - { - PUT2(code, 2+LINK_SIZE, offset); - PUT2(code, 2+LINK_SIZE+IMM2_SIZE, count); - skipbytes += IMM2_SIZE; - code[1+LINK_SIZE]++; - } - else /* Not a duplicated name */ - { - PUT2(code, 2+LINK_SIZE, recno); - } - } - - /* If terminator == CHAR_NULL it means that the name followed directly - after the opening parenthesis [e.g. (?(abc)...] and in this case there - are some further alternatives to try. For the cases where terminator != - CHAR_NULL [things like (?(<name>... or (?('name')... or (?(R&name)... ] - we have now checked all the possibilities, so give an error. */ - - else if (terminator != CHAR_NULL) - { - *errorcodeptr = ERR15; - goto FAILED; - } - - /* Check for (?(R) for recursion. Allow digits after R to specify a - specific group number. */ - - else if (*name == CHAR_R) - { - recno = 0; - for (i = 1; i < namelen; i++) - { - if (!IS_DIGIT(name[i])) - { - *errorcodeptr = ERR15; - goto FAILED; - } - if (recno > INT_MAX / 10 - 1) /* Integer overflow */ - { - *errorcodeptr = ERR61; - goto FAILED; - } - recno = recno * 10 + name[i] - CHAR_0; - } - if (recno == 0) recno = RREF_ANY; - code[1+LINK_SIZE] = OP_RREF; /* Change test type */ - PUT2(code, 2+LINK_SIZE, recno); - } - - /* Similarly, check for the (?(DEFINE) "condition", which is always - false. */ - - else if (namelen == 6 && STRNCMP_UC_C8(name, STRING_DEFINE, 6) == 0) - { - code[1+LINK_SIZE] = OP_DEF; - skipbytes = 1; - } - - /* Reference to an unidentified subpattern. */ - - else - { - *errorcodeptr = ERR15; - goto FAILED; - } - break; - - - /* ------------------------------------------------------------ */ - case CHAR_EQUALS_SIGN: /* Positive lookahead */ - bravalue = OP_ASSERT; - cd->assert_depth += 1; - ptr++; - break; - - /* Optimize (?!) to (*FAIL) unless it is quantified - which is a weird - thing to do, but Perl allows all assertions to be quantified, and when - they contain capturing parentheses there may be a potential use for - this feature. Not that that applies to a quantified (?!) but we allow - it for uniformity. */ - - /* ------------------------------------------------------------ */ - case CHAR_EXCLAMATION_MARK: /* Negative lookahead */ - ptr++; - if (*ptr == CHAR_RIGHT_PARENTHESIS && ptr[1] != CHAR_ASTERISK && - ptr[1] != CHAR_PLUS && ptr[1] != CHAR_QUESTION_MARK && - (ptr[1] != CHAR_LEFT_CURLY_BRACKET || !is_counted_repeat(ptr+2))) - { - *code++ = OP_FAIL; - previous = NULL; - continue; - } - bravalue = OP_ASSERT_NOT; - cd->assert_depth += 1; - break; - - - /* ------------------------------------------------------------ */ - case CHAR_LESS_THAN_SIGN: /* Lookbehind or named define */ - switch (ptr[1]) - { - case CHAR_EQUALS_SIGN: /* Positive lookbehind */ - bravalue = OP_ASSERTBACK; - cd->assert_depth += 1; - ptr += 2; - break; - - case CHAR_EXCLAMATION_MARK: /* Negative lookbehind */ - bravalue = OP_ASSERTBACK_NOT; - cd->assert_depth += 1; - ptr += 2; - break; - - default: /* Could be name define, else bad */ - if (MAX_255(ptr[1]) && (cd->ctypes[ptr[1]] & ctype_word) != 0) - goto DEFINE_NAME; - ptr++; /* Correct offset for error */ - *errorcodeptr = ERR24; - goto FAILED; - } - break; - - - /* ------------------------------------------------------------ */ - case CHAR_GREATER_THAN_SIGN: /* One-time brackets */ - bravalue = OP_ONCE; - ptr++; - break; - - - /* ------------------------------------------------------------ */ - case CHAR_C: /* Callout - may be followed by digits; */ - previous_callout = code; /* Save for later completion */ - after_manual_callout = 1; /* Skip one item before completing */ - *code++ = OP_CALLOUT; - { - int n = 0; - ptr++; - while(IS_DIGIT(*ptr)) - n = n * 10 + *ptr++ - CHAR_0; - if (*ptr != CHAR_RIGHT_PARENTHESIS) - { - *errorcodeptr = ERR39; - goto FAILED; - } - if (n > 255) - { - *errorcodeptr = ERR38; - goto FAILED; - } - *code++ = n; - PUT(code, 0, (int)(ptr - cd->start_pattern + 1)); /* Pattern offset */ - PUT(code, LINK_SIZE, 0); /* Default length */ - code += 2 * LINK_SIZE; - } - previous = NULL; - continue; - - - /* ------------------------------------------------------------ */ - case CHAR_P: /* Python-style named subpattern handling */ - if (*(++ptr) == CHAR_EQUALS_SIGN || - *ptr == CHAR_GREATER_THAN_SIGN) /* Reference or recursion */ - { - is_recurse = *ptr == CHAR_GREATER_THAN_SIGN; - terminator = CHAR_RIGHT_PARENTHESIS; - goto NAMED_REF_OR_RECURSE; - } - else if (*ptr != CHAR_LESS_THAN_SIGN) /* Test for Python-style defn */ - { - *errorcodeptr = ERR41; - goto FAILED; - } - /* Fall through to handle (?P< as (?< is handled */ - - - /* ------------------------------------------------------------ */ - DEFINE_NAME: /* Come here from (?< handling */ - case CHAR_APOSTROPHE: - terminator = (*ptr == CHAR_LESS_THAN_SIGN)? - CHAR_GREATER_THAN_SIGN : CHAR_APOSTROPHE; - name = ++ptr; - if (IS_DIGIT(*ptr)) - { - *errorcodeptr = ERR84; /* Group name must start with non-digit */ - goto FAILED; - } - while (MAX_255(*ptr) && (cd->ctypes[*ptr] & ctype_word) != 0) ptr++; - namelen = (int)(ptr - name); - - /* In the pre-compile phase, do a syntax check, remember the longest - name, and then remember the group in a vector, expanding it if - necessary. Duplicates for the same number are skipped; other duplicates - are checked for validity. In the actual compile, there is nothing to - do. */ - - if (lengthptr != NULL) - { - named_group *ng; - pcre_uint32 number = cd->bracount + 1; - - if (*ptr != (pcre_uchar)terminator) - { - *errorcodeptr = ERR42; - goto FAILED; - } - - if (cd->names_found >= MAX_NAME_COUNT) - { - *errorcodeptr = ERR49; - goto FAILED; - } - - if (namelen + IMM2_SIZE + 1 > cd->name_entry_size) - { - cd->name_entry_size = namelen + IMM2_SIZE + 1; - if (namelen > MAX_NAME_SIZE) - { - *errorcodeptr = ERR48; - goto FAILED; - } - } - - /* Scan the list to check for duplicates. For duplicate names, if the - number is the same, break the loop, which causes the name to be - discarded; otherwise, if DUPNAMES is not set, give an error. - If it is set, allow the name with a different number, but continue - scanning in case this is a duplicate with the same number. For - non-duplicate names, give an error if the number is duplicated. */ - - ng = cd->named_groups; - for (i = 0; i < cd->names_found; i++, ng++) - { - if (namelen == ng->length && - STRNCMP_UC_UC(name, ng->name, namelen) == 0) - { - if (ng->number == number) break; - if ((options & PCRE_DUPNAMES) == 0) - { - *errorcodeptr = ERR43; - goto FAILED; - } - cd->dupnames = TRUE; /* Duplicate names exist */ - } - else if (ng->number == number) - { - *errorcodeptr = ERR65; - goto FAILED; - } - } - - if (i >= cd->names_found) /* Not a duplicate with same number */ - { - /* Increase the list size if necessary */ - - if (cd->names_found >= cd->named_group_list_size) - { - int newsize = cd->named_group_list_size * 2; - named_group *newspace = (PUBL(malloc)) - (newsize * sizeof(named_group)); - - if (newspace == NULL) - { - *errorcodeptr = ERR21; - goto FAILED; - } - - memcpy(newspace, cd->named_groups, - cd->named_group_list_size * sizeof(named_group)); - if (cd->named_group_list_size > NAMED_GROUP_LIST_SIZE) - (PUBL(free))((void *)cd->named_groups); - cd->named_groups = newspace; - cd->named_group_list_size = newsize; - } - - cd->named_groups[cd->names_found].name = name; - cd->named_groups[cd->names_found].length = namelen; - cd->named_groups[cd->names_found].number = number; - cd->names_found++; - } - } - - ptr++; /* Move past > or ' in both passes. */ - goto NUMBERED_GROUP; - - - /* ------------------------------------------------------------ */ - case CHAR_AMPERSAND: /* Perl recursion/subroutine syntax */ - terminator = CHAR_RIGHT_PARENTHESIS; - is_recurse = TRUE; - /* Fall through */ - - /* We come here from the Python syntax above that handles both - references (?P=name) and recursion (?P>name), as well as falling - through from the Perl recursion syntax (?&name). We also come here from - the Perl \k<name> or \k'name' back reference syntax and the \k{name} - .NET syntax, and the Oniguruma \g<...> and \g'...' subroutine syntax. */ - - NAMED_REF_OR_RECURSE: - name = ++ptr; - if (IS_DIGIT(*ptr)) - { - *errorcodeptr = ERR84; /* Group name must start with non-digit */ - goto FAILED; - } - while (MAX_255(*ptr) && (cd->ctypes[*ptr] & ctype_word) != 0) ptr++; - namelen = (int)(ptr - name); - - /* In the pre-compile phase, do a syntax check. We used to just set - a dummy reference number, because it was not used in the first pass. - However, with the change of recursive back references to be atomic, - we have to look for the number so that this state can be identified, as - otherwise the incorrect length is computed. If it's not a backwards - reference, the dummy number will do. */ - - if (lengthptr != NULL) - { - named_group *ng; - recno = 0; - - if (namelen == 0) - { - *errorcodeptr = ERR62; - goto FAILED; - } - if (*ptr != (pcre_uchar)terminator) - { - *errorcodeptr = ERR42; - goto FAILED; - } - if (namelen > MAX_NAME_SIZE) - { - *errorcodeptr = ERR48; - goto FAILED; - } - - /* Count named back references. */ - - if (!is_recurse) cd->namedrefcount++; - - /* We have to allow for a named reference to a duplicated name (this - cannot be determined until the second pass). This needs an extra - 16-bit data item. */ - - *lengthptr += IMM2_SIZE; - - /* If this is a forward reference and we are within a (?|...) group, - the reference may end up as the number of a group which we are - currently inside, that is, it could be a recursive reference. In the - real compile this will be picked up and the reference wrapped with - OP_ONCE to make it atomic, so we must space in case this occurs. */ - - /* In fact, this can happen for a non-forward reference because - another group with the same number might be created later. This - issue is fixed "properly" in PCRE2. As PCRE1 is now in maintenance - only mode, we finesse the bug by allowing more memory always. */ - - *lengthptr += 2 + 2*LINK_SIZE; - - /* It is even worse than that. The current reference may be to an - existing named group with a different number (so apparently not - recursive) but which later on is also attached to a group with the - current number. This can only happen if $(| has been previous - encountered. In that case, we allow yet more memory, just in case. - (Again, this is fixed "properly" in PCRE2. */ - - if (cd->dupgroups) *lengthptr += 4 + 4*LINK_SIZE; - - /* Otherwise, check for recursion here. The name table does not exist - in the first pass; instead we must scan the list of names encountered - so far in order to get the number. If the name is not found, leave - the value of recno as 0 for a forward reference. */ - - else - { - ng = cd->named_groups; - for (i = 0; i < cd->names_found; i++, ng++) - { - if (namelen == ng->length && - STRNCMP_UC_UC(name, ng->name, namelen) == 0) - { - open_capitem *oc; - recno = ng->number; - if (is_recurse) break; - for (oc = cd->open_caps; oc != NULL; oc = oc->next) - { - if (oc->number == recno) - { - oc->flag = TRUE; - break; - } - } - } - } - } - } - - /* In the real compile, search the name table. We check the name - first, and then check that we have reached the end of the name in the - table. That way, if the name is longer than any in the table, the - comparison will fail without reading beyond the table entry. */ - - else - { - slot = cd->name_table; - for (i = 0; i < cd->names_found; i++) - { - if (STRNCMP_UC_UC(name, slot+IMM2_SIZE, namelen) == 0 && - slot[IMM2_SIZE+namelen] == 0) - break; - slot += cd->name_entry_size; - } - - if (i < cd->names_found) - { - recno = GET2(slot, 0); - } - else - { - *errorcodeptr = ERR15; - goto FAILED; - } - } - - /* In both phases, for recursions, we can now go to the code than - handles numerical recursion. */ - - if (is_recurse) goto HANDLE_RECURSION; - - /* In the second pass we must see if the name is duplicated. If so, we - generate a different opcode. */ - - if (lengthptr == NULL && cd->dupnames) - { - int count = 1; - unsigned int index = i; - pcre_uchar *cslot = slot + cd->name_entry_size; - - for (i++; i < cd->names_found; i++) - { - if (STRCMP_UC_UC(slot + IMM2_SIZE, cslot + IMM2_SIZE) != 0) break; - count++; - cslot += cd->name_entry_size; - } - - if (count > 1) - { - if (firstcharflags == REQ_UNSET) firstcharflags = REQ_NONE; - previous = code; - item_hwm_offset = cd->hwm - cd->start_workspace; - *code++ = ((options & PCRE_CASELESS) != 0)? OP_DNREFI : OP_DNREF; - PUT2INC(code, 0, index); - PUT2INC(code, 0, count); - - /* Process each potentially referenced group. */ - - for (; slot < cslot; slot += cd->name_entry_size) - { - open_capitem *oc; - recno = GET2(slot, 0); - cd->backref_map |= (recno < 32)? (1 << recno) : 1; - if (recno > cd->top_backref) cd->top_backref = recno; - - /* Check to see if this back reference is recursive, that it, it - is inside the group that it references. A flag is set so that the - group can be made atomic. */ - - for (oc = cd->open_caps; oc != NULL; oc = oc->next) - { - if (oc->number == recno) - { - oc->flag = TRUE; - break; - } - } - } - - continue; /* End of back ref handling */ - } - } - - /* First pass, or a non-duplicated name. */ - - goto HANDLE_REFERENCE; - - - /* ------------------------------------------------------------ */ - case CHAR_R: /* Recursion, same as (?0) */ - recno = 0; - if (*(++ptr) != CHAR_RIGHT_PARENTHESIS) - { - *errorcodeptr = ERR29; - goto FAILED; - } - goto HANDLE_RECURSION; - - - /* ------------------------------------------------------------ */ - case CHAR_MINUS: case CHAR_PLUS: /* Recursion or subroutine */ - case CHAR_0: case CHAR_1: case CHAR_2: case CHAR_3: case CHAR_4: - case CHAR_5: case CHAR_6: case CHAR_7: case CHAR_8: case CHAR_9: - { - const pcre_uchar *called; - terminator = CHAR_RIGHT_PARENTHESIS; - - /* Come here from the \g<...> and \g'...' code (Oniguruma - compatibility). However, the syntax has been checked to ensure that - the ... are a (signed) number, so that neither ERR63 nor ERR29 will - be called on this path, nor with the jump to OTHER_CHAR_AFTER_QUERY - ever be taken. */ - - HANDLE_NUMERICAL_RECURSION: - - if ((refsign = *ptr) == CHAR_PLUS) - { - ptr++; - if (!IS_DIGIT(*ptr)) - { - *errorcodeptr = ERR63; - goto FAILED; - } - } - else if (refsign == CHAR_MINUS) - { - if (!IS_DIGIT(ptr[1])) - goto OTHER_CHAR_AFTER_QUERY; - ptr++; - } - - recno = 0; - while(IS_DIGIT(*ptr)) - { - if (recno > INT_MAX / 10 - 1) /* Integer overflow */ - { - while (IS_DIGIT(*ptr)) ptr++; - *errorcodeptr = ERR61; - goto FAILED; - } - recno = recno * 10 + *ptr++ - CHAR_0; - } - - if (*ptr != (pcre_uchar)terminator) - { - *errorcodeptr = ERR29; - goto FAILED; - } - - if (refsign == CHAR_MINUS) - { - if (recno == 0) - { - *errorcodeptr = ERR58; - goto FAILED; - } - recno = cd->bracount - recno + 1; - if (recno <= 0) - { - *errorcodeptr = ERR15; - goto FAILED; - } - } - else if (refsign == CHAR_PLUS) - { - if (recno == 0) - { - *errorcodeptr = ERR58; - goto FAILED; - } - recno += cd->bracount; - } - - /* Come here from code above that handles a named recursion */ - - HANDLE_RECURSION: - - previous = code; - item_hwm_offset = cd->hwm - cd->start_workspace; - called = cd->start_code; - - /* When we are actually compiling, find the bracket that is being - referenced. Temporarily end the regex in case it doesn't exist before - this point. If we end up with a forward reference, first check that - the bracket does occur later so we can give the error (and position) - now. Then remember this forward reference in the workspace so it can - be filled in at the end. */ - - if (lengthptr == NULL) - { - *code = OP_END; - if (recno != 0) - called = PRIV(find_bracket)(cd->start_code, utf, recno); - - /* Forward reference */ - - if (called == NULL) - { - if (recno > cd->final_bracount) - { - *errorcodeptr = ERR15; - goto FAILED; - } - - /* Fudge the value of "called" so that when it is inserted as an - offset below, what it actually inserted is the reference number - of the group. Then remember the forward reference. */ - - called = cd->start_code + recno; - if (cd->hwm >= cd->start_workspace + cd->workspace_size - - WORK_SIZE_SAFETY_MARGIN) - { - *errorcodeptr = expand_workspace(cd); - if (*errorcodeptr != 0) goto FAILED; - } - PUTINC(cd->hwm, 0, (int)(code + 1 - cd->start_code)); - } - - /* If not a forward reference, and the subpattern is still open, - this is a recursive call. We check to see if this is a left - recursion that could loop for ever, and diagnose that case. We - must not, however, do this check if we are in a conditional - subpattern because the condition might be testing for recursion in - a pattern such as /(?(R)a+|(?R)b)/, which is perfectly valid. - Forever loops are also detected at runtime, so those that occur in - conditional subpatterns will be picked up then. */ - - else if (GET(called, 1) == 0 && cond_depth <= 0 && - could_be_empty(called, code, bcptr, utf, cd)) - { - *errorcodeptr = ERR40; - goto FAILED; - } - } - - /* Insert the recursion/subroutine item. It does not have a set first - character (relevant if it is repeated, because it will then be - wrapped with ONCE brackets). */ - - *code = OP_RECURSE; - PUT(code, 1, (int)(called - cd->start_code)); - code += 1 + LINK_SIZE; - groupsetfirstchar = FALSE; - } - - /* Can't determine a first byte now */ - - if (firstcharflags == REQ_UNSET) firstcharflags = REQ_NONE; - continue; - - - /* ------------------------------------------------------------ */ - default: /* Other characters: check option setting */ - OTHER_CHAR_AFTER_QUERY: - set = unset = 0; - optset = &set; - - while (*ptr != CHAR_RIGHT_PARENTHESIS && *ptr != CHAR_COLON) - { - switch (*ptr++) - { - case CHAR_MINUS: optset = &unset; break; - - case CHAR_J: /* Record that it changed in the external options */ - *optset |= PCRE_DUPNAMES; - cd->external_flags |= PCRE_JCHANGED; - break; - - case CHAR_i: *optset |= PCRE_CASELESS; break; - case CHAR_m: *optset |= PCRE_MULTILINE; break; - case CHAR_s: *optset |= PCRE_DOTALL; break; - case CHAR_x: *optset |= PCRE_EXTENDED; break; - case CHAR_U: *optset |= PCRE_UNGREEDY; break; - case CHAR_X: *optset |= PCRE_EXTRA; break; - - default: *errorcodeptr = ERR12; - ptr--; /* Correct the offset */ - goto FAILED; - } - } - - /* Set up the changed option bits, but don't change anything yet. */ - - newoptions = (options | set) & (~unset); - - /* If the options ended with ')' this is not the start of a nested - group with option changes, so the options change at this level. If this - item is right at the start of the pattern, the options can be - abstracted and made external in the pre-compile phase, and ignored in - the compile phase. This can be helpful when matching -- for instance in - caseless checking of required bytes. - - If the code pointer is not (cd->start_code + 1 + LINK_SIZE), we are - definitely *not* at the start of the pattern because something has been - compiled. In the pre-compile phase, however, the code pointer can have - that value after the start, because it gets reset as code is discarded - during the pre-compile. However, this can happen only at top level - if - we are within parentheses, the starting BRA will still be present. At - any parenthesis level, the length value can be used to test if anything - has been compiled at that level. Thus, a test for both these conditions - is necessary to ensure we correctly detect the start of the pattern in - both phases. - - If we are not at the pattern start, reset the greedy defaults and the - case value for firstchar and reqchar. */ - - if (*ptr == CHAR_RIGHT_PARENTHESIS) - { - if (code == cd->start_code + 1 + LINK_SIZE && - (lengthptr == NULL || *lengthptr == 2 + 2*LINK_SIZE)) - { - cd->external_options = newoptions; - } - else - { - greedy_default = ((newoptions & PCRE_UNGREEDY) != 0); - greedy_non_default = greedy_default ^ 1; - req_caseopt = ((newoptions & PCRE_CASELESS) != 0)? REQ_CASELESS:0; - } - - /* Change options at this level, and pass them back for use - in subsequent branches. */ - - *optionsptr = options = newoptions; - previous = NULL; /* This item can't be repeated */ - continue; /* It is complete */ - } - - /* If the options ended with ':' we are heading into a nested group - with possible change of options. Such groups are non-capturing and are - not assertions of any kind. All we need to do is skip over the ':'; - the newoptions value is handled below. */ - - bravalue = OP_BRA; - ptr++; - } /* End of switch for character following (? */ - } /* End of (? handling */ - - /* Opening parenthesis not followed by '*' or '?'. If PCRE_NO_AUTO_CAPTURE - is set, all unadorned brackets become non-capturing and behave like (?:...) - brackets. */ - - else if ((options & PCRE_NO_AUTO_CAPTURE) != 0) - { - bravalue = OP_BRA; - } - - /* Else we have a capturing group. */ - - else - { - NUMBERED_GROUP: - cd->bracount += 1; - PUT2(code, 1+LINK_SIZE, cd->bracount); - skipbytes = IMM2_SIZE; - } - - /* Process nested bracketed regex. First check for parentheses nested too - deeply. */ - - if ((cd->parens_depth += 1) > PARENS_NEST_LIMIT) - { - *errorcodeptr = ERR82; - goto FAILED; - } - - /* All assertions used not to be repeatable, but this was changed for Perl - compatibility. All kinds can now be repeated except for assertions that are - conditions (Perl also forbids these to be repeated). We copy code into a - non-register variable (tempcode) in order to be able to pass its address - because some compilers complain otherwise. At the start of a conditional - group whose condition is an assertion, cd->iscondassert is set. We unset it - here so as to allow assertions later in the group to be quantified. */ - - if (bravalue >= OP_ASSERT && bravalue <= OP_ASSERTBACK_NOT && - cd->iscondassert) - { - previous = NULL; - cd->iscondassert = FALSE; - } - else - { - previous = code; - item_hwm_offset = cd->hwm - cd->start_workspace; - } - - *code = bravalue; - tempcode = code; - tempreqvary = cd->req_varyopt; /* Save value before bracket */ - tempbracount = cd->bracount; /* Save value before bracket */ - length_prevgroup = 0; /* Initialize for pre-compile phase */ - - if (!compile_regex( - newoptions, /* The complete new option state */ - &tempcode, /* Where to put code (updated) */ - &ptr, /* Input pointer (updated) */ - errorcodeptr, /* Where to put an error message */ - (bravalue == OP_ASSERTBACK || - bravalue == OP_ASSERTBACK_NOT), /* TRUE if back assert */ - reset_bracount, /* True if (?| group */ - skipbytes, /* Skip over bracket number */ - cond_depth + - ((bravalue == OP_COND)?1:0), /* Depth of condition subpatterns */ - &subfirstchar, /* For possible first char */ - &subfirstcharflags, - &subreqchar, /* For possible last char */ - &subreqcharflags, - bcptr, /* Current branch chain */ - cd, /* Tables block */ - (lengthptr == NULL)? NULL : /* Actual compile phase */ - &length_prevgroup /* Pre-compile phase */ - )) - goto FAILED; - - cd->parens_depth -= 1; - - /* If this was an atomic group and there are no capturing groups within it, - generate OP_ONCE_NC instead of OP_ONCE. */ - - if (bravalue == OP_ONCE && cd->bracount <= tempbracount) - *code = OP_ONCE_NC; - - if (bravalue >= OP_ASSERT && bravalue <= OP_ASSERTBACK_NOT) - cd->assert_depth -= 1; - - /* At the end of compiling, code is still pointing to the start of the - group, while tempcode has been updated to point past the end of the group. - The pattern pointer (ptr) is on the bracket. - - If this is a conditional bracket, check that there are no more than - two branches in the group, or just one if it's a DEFINE group. We do this - in the real compile phase, not in the pre-pass, where the whole group may - not be available. */ - - if (bravalue == OP_COND && lengthptr == NULL) - { - pcre_uchar *tc = code; - int condcount = 0; - - do { - condcount++; - tc += GET(tc,1); - } - while (*tc != OP_KET); - - /* A DEFINE group is never obeyed inline (the "condition" is always - false). It must have only one branch. */ - - if (code[LINK_SIZE+1] == OP_DEF) - { - if (condcount > 1) - { - *errorcodeptr = ERR54; - goto FAILED; - } - bravalue = OP_DEF; /* Just a flag to suppress char handling below */ - } - - /* A "normal" conditional group. If there is just one branch, we must not - make use of its firstchar or reqchar, because this is equivalent to an - empty second branch. */ - - else - { - if (condcount > 2) - { - *errorcodeptr = ERR27; - goto FAILED; - } - if (condcount == 1) subfirstcharflags = subreqcharflags = REQ_NONE; - } - } - - /* Error if hit end of pattern */ - - if (*ptr != CHAR_RIGHT_PARENTHESIS) - { - *errorcodeptr = ERR14; - goto FAILED; - } - - /* In the pre-compile phase, update the length by the length of the group, - less the brackets at either end. Then reduce the compiled code to just a - set of non-capturing brackets so that it doesn't use much memory if it is - duplicated by a quantifier.*/ - - if (lengthptr != NULL) - { - if (OFLOW_MAX - *lengthptr < length_prevgroup - 2 - 2*LINK_SIZE) - { - *errorcodeptr = ERR20; - goto FAILED; - } - *lengthptr += length_prevgroup - 2 - 2*LINK_SIZE; - code++; /* This already contains bravalue */ - PUTINC(code, 0, 1 + LINK_SIZE); - *code++ = OP_KET; - PUTINC(code, 0, 1 + LINK_SIZE); - break; /* No need to waste time with special character handling */ - } - - /* Otherwise update the main code pointer to the end of the group. */ - - code = tempcode; - - /* For a DEFINE group, required and first character settings are not - relevant. */ - - if (bravalue == OP_DEF) break; - - /* Handle updating of the required and first characters for other types of - group. Update for normal brackets of all kinds, and conditions with two - branches (see code above). If the bracket is followed by a quantifier with - zero repeat, we have to back off. Hence the definition of zeroreqchar and - zerofirstchar outside the main loop so that they can be accessed for the - back off. */ - - zeroreqchar = reqchar; - zeroreqcharflags = reqcharflags; - zerofirstchar = firstchar; - zerofirstcharflags = firstcharflags; - groupsetfirstchar = FALSE; - - if (bravalue >= OP_ONCE) - { - /* If we have not yet set a firstchar in this branch, take it from the - subpattern, remembering that it was set here so that a repeat of more - than one can replicate it as reqchar if necessary. If the subpattern has - no firstchar, set "none" for the whole branch. In both cases, a zero - repeat forces firstchar to "none". */ - - if (firstcharflags == REQ_UNSET) - { - if (subfirstcharflags >= 0) - { - firstchar = subfirstchar; - firstcharflags = subfirstcharflags; - groupsetfirstchar = TRUE; - } - else firstcharflags = REQ_NONE; - zerofirstcharflags = REQ_NONE; - } - - /* If firstchar was previously set, convert the subpattern's firstchar - into reqchar if there wasn't one, using the vary flag that was in - existence beforehand. */ - - else if (subfirstcharflags >= 0 && subreqcharflags < 0) - { - subreqchar = subfirstchar; - subreqcharflags = subfirstcharflags | tempreqvary; - } - - /* If the subpattern set a required byte (or set a first byte that isn't - really the first byte - see above), set it. */ - - if (subreqcharflags >= 0) - { - reqchar = subreqchar; - reqcharflags = subreqcharflags; - } - } - - /* For a forward assertion, we take the reqchar, if set. This can be - helpful if the pattern that follows the assertion doesn't set a different - char. For example, it's useful for /(?=abcde).+/. We can't set firstchar - for an assertion, however because it leads to incorrect effect for patterns - such as /(?=a)a.+/ when the "real" "a" would then become a reqchar instead - of a firstchar. This is overcome by a scan at the end if there's no - firstchar, looking for an asserted first char. */ - - else if (bravalue == OP_ASSERT && subreqcharflags >= 0) - { - reqchar = subreqchar; - reqcharflags = subreqcharflags; - } - break; /* End of processing '(' */ - - - /* ===================================================================*/ - /* Handle metasequences introduced by \. For ones like \d, the ESC_ values - are arranged to be the negation of the corresponding OP_values in the - default case when PCRE_UCP is not set. For the back references, the values - are negative the reference number. Only back references and those types - that consume a character may be repeated. We can test for values between - ESC_b and ESC_Z for the latter; this may have to change if any new ones are - ever created. */ - - case CHAR_BACKSLASH: - tempptr = ptr; - escape = check_escape(&ptr, &ec, errorcodeptr, cd->bracount, options, FALSE); - if (*errorcodeptr != 0) goto FAILED; - - if (escape == 0) /* The escape coded a single character */ - c = ec; - else - { - if (escape == ESC_Q) /* Handle start of quoted string */ - { - if (ptr[1] == CHAR_BACKSLASH && ptr[2] == CHAR_E) - ptr += 2; /* avoid empty string */ - else inescq = TRUE; - continue; - } - - if (escape == ESC_E) continue; /* Perl ignores an orphan \E */ - - /* For metasequences that actually match a character, we disable the - setting of a first character if it hasn't already been set. */ - - if (firstcharflags == REQ_UNSET && escape > ESC_b && escape < ESC_Z) - firstcharflags = REQ_NONE; - - /* Set values to reset to if this is followed by a zero repeat. */ - - zerofirstchar = firstchar; - zerofirstcharflags = firstcharflags; - zeroreqchar = reqchar; - zeroreqcharflags = reqcharflags; - - /* \g<name> or \g'name' is a subroutine call by name and \g<n> or \g'n' - is a subroutine call by number (Oniguruma syntax). In fact, the value - ESC_g is returned only for these cases. So we don't need to check for < - or ' if the value is ESC_g. For the Perl syntax \g{n} the value is - -n, and for the Perl syntax \g{name} the result is ESC_k (as - that is a synonym for a named back reference). */ - - if (escape == ESC_g) - { - const pcre_uchar *p; - pcre_uint32 cf; - - item_hwm_offset = cd->hwm - cd->start_workspace; /* Normally this is set when '(' is read */ - terminator = (*(++ptr) == CHAR_LESS_THAN_SIGN)? - CHAR_GREATER_THAN_SIGN : CHAR_APOSTROPHE; - - /* These two statements stop the compiler for warning about possibly - unset variables caused by the jump to HANDLE_NUMERICAL_RECURSION. In - fact, because we do the check for a number below, the paths that - would actually be in error are never taken. */ - - skipbytes = 0; - reset_bracount = FALSE; - - /* If it's not a signed or unsigned number, treat it as a name. */ - - cf = ptr[1]; - if (cf != CHAR_PLUS && cf != CHAR_MINUS && !IS_DIGIT(cf)) - { - is_recurse = TRUE; - goto NAMED_REF_OR_RECURSE; - } - - /* Signed or unsigned number (cf = ptr[1]) is known to be plus or minus - or a digit. */ - - p = ptr + 2; - while (IS_DIGIT(*p)) p++; - if (*p != (pcre_uchar)terminator) - { - *errorcodeptr = ERR57; - goto FAILED; - } - ptr++; - goto HANDLE_NUMERICAL_RECURSION; - } - - /* \k<name> or \k'name' is a back reference by name (Perl syntax). - We also support \k{name} (.NET syntax). */ - - if (escape == ESC_k) - { - if ((ptr[1] != CHAR_LESS_THAN_SIGN && - ptr[1] != CHAR_APOSTROPHE && ptr[1] != CHAR_LEFT_CURLY_BRACKET)) - { - *errorcodeptr = ERR69; - goto FAILED; - } - is_recurse = FALSE; - terminator = (*(++ptr) == CHAR_LESS_THAN_SIGN)? - CHAR_GREATER_THAN_SIGN : (*ptr == CHAR_APOSTROPHE)? - CHAR_APOSTROPHE : CHAR_RIGHT_CURLY_BRACKET; - goto NAMED_REF_OR_RECURSE; - } - - /* Back references are handled specially; must disable firstchar if - not set to cope with cases like (?=(\w+))\1: which would otherwise set - ':' later. */ - - if (escape < 0) - { - open_capitem *oc; - recno = -escape; - - /* Come here from named backref handling when the reference is to a - single group (i.e. not to a duplicated name. */ - - HANDLE_REFERENCE: - if (firstcharflags == REQ_UNSET) firstcharflags = REQ_NONE; - previous = code; - item_hwm_offset = cd->hwm - cd->start_workspace; - *code++ = ((options & PCRE_CASELESS) != 0)? OP_REFI : OP_REF; - PUT2INC(code, 0, recno); - cd->backref_map |= (recno < 32)? (1 << recno) : 1; - if (recno > cd->top_backref) cd->top_backref = recno; - - /* Check to see if this back reference is recursive, that it, it - is inside the group that it references. A flag is set so that the - group can be made atomic. */ - - for (oc = cd->open_caps; oc != NULL; oc = oc->next) - { - if (oc->number == recno) - { - oc->flag = TRUE; - break; - } - } - } - - /* So are Unicode property matches, if supported. */ - -#ifdef SUPPORT_UCP - else if (escape == ESC_P || escape == ESC_p) - { - BOOL negated; - unsigned int ptype = 0, pdata = 0; - if (!get_ucp(&ptr, &negated, &ptype, &pdata, errorcodeptr)) - goto FAILED; - previous = code; - item_hwm_offset = cd->hwm - cd->start_workspace; - *code++ = ((escape == ESC_p) != negated)? OP_PROP : OP_NOTPROP; - *code++ = ptype; - *code++ = pdata; - } -#else - - /* If Unicode properties are not supported, \X, \P, and \p are not - allowed. */ - - else if (escape == ESC_X || escape == ESC_P || escape == ESC_p) - { - *errorcodeptr = ERR45; - goto FAILED; - } -#endif - - /* For the rest (including \X when Unicode properties are supported), we - can obtain the OP value by negating the escape value in the default - situation when PCRE_UCP is not set. When it *is* set, we substitute - Unicode property tests. Note that \b and \B do a one-character - lookbehind, and \A also behaves as if it does. */ - - else - { - if ((escape == ESC_b || escape == ESC_B || escape == ESC_A) && - cd->max_lookbehind == 0) - cd->max_lookbehind = 1; -#ifdef SUPPORT_UCP - if (escape >= ESC_DU && escape <= ESC_wu) - { - nestptr = ptr + 1; /* Where to resume */ - ptr = substitutes[escape - ESC_DU] - 1; /* Just before substitute */ - } - else -#endif - /* In non-UTF-8 mode, we turn \C into OP_ALLANY instead of OP_ANYBYTE - so that it works in DFA mode and in lookbehinds. */ - - { - previous = (escape > ESC_b && escape < ESC_Z)? code : NULL; - item_hwm_offset = cd->hwm - cd->start_workspace; - *code++ = (!utf && escape == ESC_C)? OP_ALLANY : escape; - } - } - continue; - } - - /* We have a data character whose value is in c. In UTF-8 mode it may have - a value > 127. We set its representation in the length/buffer, and then - handle it as a data character. */ - -#if defined SUPPORT_UTF && !defined COMPILE_PCRE32 - if (utf && c > MAX_VALUE_FOR_SINGLE_CHAR) - mclength = PRIV(ord2utf)(c, mcbuffer); - else -#endif - - { - mcbuffer[0] = c; - mclength = 1; - } - goto ONE_CHAR; - - - /* ===================================================================*/ - /* Handle a literal character. It is guaranteed not to be whitespace or # - when the extended flag is set. If we are in a UTF mode, it may be a - multi-unit literal character. */ - - default: - NORMAL_CHAR: - mclength = 1; - mcbuffer[0] = c; - -#ifdef SUPPORT_UTF - if (utf && HAS_EXTRALEN(c)) - ACROSSCHAR(TRUE, ptr[1], mcbuffer[mclength++] = *(++ptr)); -#endif - - /* At this point we have the character's bytes in mcbuffer, and the length - in mclength. When not in UTF-8 mode, the length is always 1. */ - - ONE_CHAR: - previous = code; - item_hwm_offset = cd->hwm - cd->start_workspace; - - /* For caseless UTF-8 mode when UCP support is available, check whether - this character has more than one other case. If so, generate a special - OP_PROP item instead of OP_CHARI. */ - -#ifdef SUPPORT_UCP - if (utf && (options & PCRE_CASELESS) != 0) - { - GETCHAR(c, mcbuffer); - if ((c = UCD_CASESET(c)) != 0) - { - *code++ = OP_PROP; - *code++ = PT_CLIST; - *code++ = c; - if (firstcharflags == REQ_UNSET) - firstcharflags = zerofirstcharflags = REQ_NONE; - break; - } - } -#endif - - /* Caseful matches, or not one of the multicase characters. */ - - *code++ = ((options & PCRE_CASELESS) != 0)? OP_CHARI : OP_CHAR; - for (c = 0; c < mclength; c++) *code++ = mcbuffer[c]; - - /* Remember if \r or \n were seen */ - - if (mcbuffer[0] == CHAR_CR || mcbuffer[0] == CHAR_NL) - cd->external_flags |= PCRE_HASCRORLF; - - /* Set the first and required bytes appropriately. If no previous first - byte, set it from this character, but revert to none on a zero repeat. - Otherwise, leave the firstchar value alone, and don't change it on a zero - repeat. */ - - if (firstcharflags == REQ_UNSET) - { - zerofirstcharflags = REQ_NONE; - zeroreqchar = reqchar; - zeroreqcharflags = reqcharflags; - - /* If the character is more than one byte long, we can set firstchar - only if it is not to be matched caselessly. */ - - if (mclength == 1 || req_caseopt == 0) - { - firstchar = mcbuffer[0] | req_caseopt; - firstchar = mcbuffer[0]; - firstcharflags = req_caseopt; - - if (mclength != 1) - { - reqchar = code[-1]; - reqcharflags = cd->req_varyopt; - } - } - else firstcharflags = reqcharflags = REQ_NONE; - } - - /* firstchar was previously set; we can set reqchar only if the length is - 1 or the matching is caseful. */ - - else - { - zerofirstchar = firstchar; - zerofirstcharflags = firstcharflags; - zeroreqchar = reqchar; - zeroreqcharflags = reqcharflags; - if (mclength == 1 || req_caseopt == 0) - { - reqchar = code[-1]; - reqcharflags = req_caseopt | cd->req_varyopt; - } - } - - break; /* End of literal character handling */ - } - } /* end of big loop */ - - -/* Control never reaches here by falling through, only by a goto for all the -error states. Pass back the position in the pattern so that it can be displayed -to the user for diagnosing the error. */ - -FAILED: -*ptrptr = ptr; -return FALSE; -} - - - -/************************************************* -* Compile sequence of alternatives * -*************************************************/ - -/* On entry, ptr is pointing past the bracket character, but on return it -points to the closing bracket, or vertical bar, or end of string. The code -variable is pointing at the byte into which the BRA operator has been stored. -This function is used during the pre-compile phase when we are trying to find -out the amount of memory needed, as well as during the real compile phase. The -value of lengthptr distinguishes the two phases. - -Arguments: - options option bits, including any changes for this subpattern - codeptr -> the address of the current code pointer - ptrptr -> the address of the current pattern pointer - errorcodeptr -> pointer to error code variable - lookbehind TRUE if this is a lookbehind assertion - reset_bracount TRUE to reset the count for each branch - skipbytes skip this many bytes at start (for brackets and OP_COND) - cond_depth depth of nesting for conditional subpatterns - firstcharptr place to put the first required character - firstcharflagsptr place to put the first character flags, or a negative number - reqcharptr place to put the last required character - reqcharflagsptr place to put the last required character flags, or a negative number - bcptr pointer to the chain of currently open branches - cd points to the data block with tables pointers etc. - lengthptr NULL during the real compile phase - points to length accumulator during pre-compile phase - -Returns: TRUE on success -*/ - -static BOOL -compile_regex(int options, pcre_uchar **codeptr, const pcre_uchar **ptrptr, - int *errorcodeptr, BOOL lookbehind, BOOL reset_bracount, int skipbytes, - int cond_depth, - pcre_uint32 *firstcharptr, pcre_int32 *firstcharflagsptr, - pcre_uint32 *reqcharptr, pcre_int32 *reqcharflagsptr, - branch_chain *bcptr, compile_data *cd, int *lengthptr) -{ -const pcre_uchar *ptr = *ptrptr; -pcre_uchar *code = *codeptr; -pcre_uchar *last_branch = code; -pcre_uchar *start_bracket = code; -pcre_uchar *reverse_count = NULL; -open_capitem capitem; -int capnumber = 0; -pcre_uint32 firstchar, reqchar; -pcre_int32 firstcharflags, reqcharflags; -pcre_uint32 branchfirstchar, branchreqchar; -pcre_int32 branchfirstcharflags, branchreqcharflags; -int length; -unsigned int orig_bracount; -unsigned int max_bracount; -branch_chain bc; -size_t save_hwm_offset; - -/* If set, call the external function that checks for stack availability. */ - -if (PUBL(stack_guard) != NULL && PUBL(stack_guard)()) - { - *errorcodeptr= ERR85; - return FALSE; - } - -/* Miscellaneous initialization */ - -bc.outer = bcptr; -bc.current_branch = code; - -firstchar = reqchar = 0; -firstcharflags = reqcharflags = REQ_UNSET; - -save_hwm_offset = cd->hwm - cd->start_workspace; - -/* Accumulate the length for use in the pre-compile phase. Start with the -length of the BRA and KET and any extra bytes that are required at the -beginning. We accumulate in a local variable to save frequent testing of -lenthptr for NULL. We cannot do this by looking at the value of code at the -start and end of each alternative, because compiled items are discarded during -the pre-compile phase so that the work space is not exceeded. */ - -length = 2 + 2*LINK_SIZE + skipbytes; - -/* WARNING: If the above line is changed for any reason, you must also change -the code that abstracts option settings at the start of the pattern and makes -them global. It tests the value of length for (2 + 2*LINK_SIZE) in the -pre-compile phase to find out whether anything has yet been compiled or not. */ - -/* If this is a capturing subpattern, add to the chain of open capturing items -so that we can detect them if (*ACCEPT) is encountered. This is also used to -detect groups that contain recursive back references to themselves. Note that -only OP_CBRA need be tested here; changing this opcode to one of its variants, -e.g. OP_SCBRAPOS, happens later, after the group has been compiled. */ - -if (*code == OP_CBRA) - { - capnumber = GET2(code, 1 + LINK_SIZE); - capitem.number = capnumber; - capitem.next = cd->open_caps; - capitem.flag = FALSE; - cd->open_caps = &capitem; - } - -/* Offset is set zero to mark that this bracket is still open */ - -PUT(code, 1, 0); -code += 1 + LINK_SIZE + skipbytes; - -/* Loop for each alternative branch */ - -orig_bracount = max_bracount = cd->bracount; -for (;;) - { - /* For a (?| group, reset the capturing bracket count so that each branch - uses the same numbers. */ - - if (reset_bracount) cd->bracount = orig_bracount; - - /* Set up dummy OP_REVERSE if lookbehind assertion */ - - if (lookbehind) - { - *code++ = OP_REVERSE; - reverse_count = code; - PUTINC(code, 0, 0); - length += 1 + LINK_SIZE; - } - - /* Now compile the branch; in the pre-compile phase its length gets added - into the length. */ - - if (!compile_branch(&options, &code, &ptr, errorcodeptr, &branchfirstchar, - &branchfirstcharflags, &branchreqchar, &branchreqcharflags, &bc, - cond_depth, cd, (lengthptr == NULL)? NULL : &length)) - { - *ptrptr = ptr; - return FALSE; - } - - /* Keep the highest bracket count in case (?| was used and some branch - has fewer than the rest. */ - - if (cd->bracount > max_bracount) max_bracount = cd->bracount; - - /* In the real compile phase, there is some post-processing to be done. */ - - if (lengthptr == NULL) - { - /* If this is the first branch, the firstchar and reqchar values for the - branch become the values for the regex. */ - - if (*last_branch != OP_ALT) - { - firstchar = branchfirstchar; - firstcharflags = branchfirstcharflags; - reqchar = branchreqchar; - reqcharflags = branchreqcharflags; - } - - /* If this is not the first branch, the first char and reqchar have to - match the values from all the previous branches, except that if the - previous value for reqchar didn't have REQ_VARY set, it can still match, - and we set REQ_VARY for the regex. */ - - else - { - /* If we previously had a firstchar, but it doesn't match the new branch, - we have to abandon the firstchar for the regex, but if there was - previously no reqchar, it takes on the value of the old firstchar. */ - - if (firstcharflags >= 0 && - (firstcharflags != branchfirstcharflags || firstchar != branchfirstchar)) - { - if (reqcharflags < 0) - { - reqchar = firstchar; - reqcharflags = firstcharflags; - } - firstcharflags = REQ_NONE; - } - - /* If we (now or from before) have no firstchar, a firstchar from the - branch becomes a reqchar if there isn't a branch reqchar. */ - - if (firstcharflags < 0 && branchfirstcharflags >= 0 && branchreqcharflags < 0) - { - branchreqchar = branchfirstchar; - branchreqcharflags = branchfirstcharflags; - } - - /* Now ensure that the reqchars match */ - - if (((reqcharflags & ~REQ_VARY) != (branchreqcharflags & ~REQ_VARY)) || - reqchar != branchreqchar) - reqcharflags = REQ_NONE; - else - { - reqchar = branchreqchar; - reqcharflags |= branchreqcharflags; /* To "or" REQ_VARY */ - } - } - - /* If lookbehind, check that this branch matches a fixed-length string, and - put the length into the OP_REVERSE item. Temporarily mark the end of the - branch with OP_END. If the branch contains OP_RECURSE, the result is -3 - because there may be forward references that we can't check here. Set a - flag to cause another lookbehind check at the end. Why not do it all at the - end? Because common, erroneous checks are picked up here and the offset of - the problem can be shown. */ - - if (lookbehind) - { - int fixed_length; - *code = OP_END; - fixed_length = find_fixedlength(last_branch, (options & PCRE_UTF8) != 0, - FALSE, cd, NULL); - DPRINTF(("fixed length = %d\n", fixed_length)); - if (fixed_length == -3) - { - cd->check_lookbehind = TRUE; - } - else if (fixed_length < 0) - { - *errorcodeptr = (fixed_length == -2)? ERR36 : - (fixed_length == -4)? ERR70: ERR25; - *ptrptr = ptr; - return FALSE; - } - else - { - if (fixed_length > cd->max_lookbehind) - cd->max_lookbehind = fixed_length; - PUT(reverse_count, 0, fixed_length); - } - } - } - - /* Reached end of expression, either ')' or end of pattern. In the real - compile phase, go back through the alternative branches and reverse the chain - of offsets, with the field in the BRA item now becoming an offset to the - first alternative. If there are no alternatives, it points to the end of the - group. The length in the terminating ket is always the length of the whole - bracketed item. Return leaving the pointer at the terminating char. */ - - if (*ptr != CHAR_VERTICAL_LINE) - { - if (lengthptr == NULL) - { - int branch_length = (int)(code - last_branch); - do - { - int prev_length = GET(last_branch, 1); - PUT(last_branch, 1, branch_length); - branch_length = prev_length; - last_branch -= branch_length; - } - while (branch_length > 0); - } - - /* Fill in the ket */ - - *code = OP_KET; - PUT(code, 1, (int)(code - start_bracket)); - code += 1 + LINK_SIZE; - - /* If it was a capturing subpattern, check to see if it contained any - recursive back references. If so, we must wrap it in atomic brackets. - Because we are moving code along, we must ensure that any pending recursive - references are updated. In any event, remove the block from the chain. */ - - if (capnumber > 0) - { - if (cd->open_caps->flag) - { - *code = OP_END; - adjust_recurse(start_bracket, 1 + LINK_SIZE, - (options & PCRE_UTF8) != 0, cd, save_hwm_offset); - memmove(start_bracket + 1 + LINK_SIZE, start_bracket, - IN_UCHARS(code - start_bracket)); - *start_bracket = OP_ONCE; - code += 1 + LINK_SIZE; - PUT(start_bracket, 1, (int)(code - start_bracket)); - *code = OP_KET; - PUT(code, 1, (int)(code - start_bracket)); - code += 1 + LINK_SIZE; - length += 2 + 2*LINK_SIZE; - } - cd->open_caps = cd->open_caps->next; - } - - /* Retain the highest bracket number, in case resetting was used. */ - - cd->bracount = max_bracount; - - /* Set values to pass back */ - - *codeptr = code; - *ptrptr = ptr; - *firstcharptr = firstchar; - *firstcharflagsptr = firstcharflags; - *reqcharptr = reqchar; - *reqcharflagsptr = reqcharflags; - if (lengthptr != NULL) - { - if (OFLOW_MAX - *lengthptr < length) - { - *errorcodeptr = ERR20; - return FALSE; - } - *lengthptr += length; - } - return TRUE; - } - - /* Another branch follows. In the pre-compile phase, we can move the code - pointer back to where it was for the start of the first branch. (That is, - pretend that each branch is the only one.) - - In the real compile phase, insert an ALT node. Its length field points back - to the previous branch while the bracket remains open. At the end the chain - is reversed. It's done like this so that the start of the bracket has a - zero offset until it is closed, making it possible to detect recursion. */ - - if (lengthptr != NULL) - { - code = *codeptr + 1 + LINK_SIZE + skipbytes; - length += 1 + LINK_SIZE; - } - else - { - *code = OP_ALT; - PUT(code, 1, (int)(code - last_branch)); - bc.current_branch = last_branch = code; - code += 1 + LINK_SIZE; - } - - ptr++; - } -/* Control never reaches here */ -} - - - - -/************************************************* -* Check for anchored expression * -*************************************************/ - -/* Try to find out if this is an anchored regular expression. Consider each -alternative branch. If they all start with OP_SOD or OP_CIRC, or with a bracket -all of whose alternatives start with OP_SOD or OP_CIRC (recurse ad lib), then -it's anchored. However, if this is a multiline pattern, then only OP_SOD will -be found, because ^ generates OP_CIRCM in that mode. - -We can also consider a regex to be anchored if OP_SOM starts all its branches. -This is the code for \G, which means "match at start of match position, taking -into account the match offset". - -A branch is also implicitly anchored if it starts with .* and DOTALL is set, -because that will try the rest of the pattern at all possible matching points, -so there is no point trying again.... er .... - -.... except when the .* appears inside capturing parentheses, and there is a -subsequent back reference to those parentheses. We haven't enough information -to catch that case precisely. - -At first, the best we could do was to detect when .* was in capturing brackets -and the highest back reference was greater than or equal to that level. -However, by keeping a bitmap of the first 31 back references, we can catch some -of the more common cases more precisely. - -... A second exception is when the .* appears inside an atomic group, because -this prevents the number of characters it matches from being adjusted. - -Arguments: - code points to start of expression (the bracket) - bracket_map a bitmap of which brackets we are inside while testing; this - handles up to substring 31; after that we just have to take - the less precise approach - cd points to the compile data block - atomcount atomic group level - -Returns: TRUE or FALSE -*/ - -static BOOL -is_anchored(register const pcre_uchar *code, unsigned int bracket_map, - compile_data *cd, int atomcount) -{ -do { - const pcre_uchar *scode = first_significant_code( - code + PRIV(OP_lengths)[*code], FALSE); - register int op = *scode; - - /* Non-capturing brackets */ - - if (op == OP_BRA || op == OP_BRAPOS || - op == OP_SBRA || op == OP_SBRAPOS) - { - if (!is_anchored(scode, bracket_map, cd, atomcount)) return FALSE; - } - - /* Capturing brackets */ - - else if (op == OP_CBRA || op == OP_CBRAPOS || - op == OP_SCBRA || op == OP_SCBRAPOS) - { - int n = GET2(scode, 1+LINK_SIZE); - int new_map = bracket_map | ((n < 32)? (1 << n) : 1); - if (!is_anchored(scode, new_map, cd, atomcount)) return FALSE; - } - - /* Positive forward assertions and conditions */ - - else if (op == OP_ASSERT || op == OP_COND) - { - if (!is_anchored(scode, bracket_map, cd, atomcount)) return FALSE; - } - - /* Atomic groups */ - - else if (op == OP_ONCE || op == OP_ONCE_NC) - { - if (!is_anchored(scode, bracket_map, cd, atomcount + 1)) - return FALSE; - } - - /* .* is not anchored unless DOTALL is set (which generates OP_ALLANY) and - it isn't in brackets that are or may be referenced or inside an atomic - group. */ - - else if ((op == OP_TYPESTAR || op == OP_TYPEMINSTAR || - op == OP_TYPEPOSSTAR)) - { - if (scode[1] != OP_ALLANY || (bracket_map & cd->backref_map) != 0 || - atomcount > 0 || cd->had_pruneorskip) - return FALSE; - } - - /* Check for explicit anchoring */ - - else if (op != OP_SOD && op != OP_SOM && op != OP_CIRC) return FALSE; - - code += GET(code, 1); - } -while (*code == OP_ALT); /* Loop for each alternative */ -return TRUE; -} - - - -/************************************************* -* Check for starting with ^ or .* * -*************************************************/ - -/* This is called to find out if every branch starts with ^ or .* so that -"first char" processing can be done to speed things up in multiline -matching and for non-DOTALL patterns that start with .* (which must start at -the beginning or after \n). As in the case of is_anchored() (see above), we -have to take account of back references to capturing brackets that contain .* -because in that case we can't make the assumption. Also, the appearance of .* -inside atomic brackets or in a pattern that contains *PRUNE or *SKIP does not -count, because once again the assumption no longer holds. - -Arguments: - code points to start of expression (the bracket) - bracket_map a bitmap of which brackets we are inside while testing; this - handles up to substring 31; after that we just have to take - the less precise approach - cd points to the compile data - atomcount atomic group level - -Returns: TRUE or FALSE -*/ - -static BOOL -is_startline(const pcre_uchar *code, unsigned int bracket_map, - compile_data *cd, int atomcount) -{ -do { - const pcre_uchar *scode = first_significant_code( - code + PRIV(OP_lengths)[*code], FALSE); - register int op = *scode; - - /* If we are at the start of a conditional assertion group, *both* the - conditional assertion *and* what follows the condition must satisfy the test - for start of line. Other kinds of condition fail. Note that there may be an - auto-callout at the start of a condition. */ - - if (op == OP_COND) - { - scode += 1 + LINK_SIZE; - if (*scode == OP_CALLOUT) scode += PRIV(OP_lengths)[OP_CALLOUT]; - switch (*scode) - { - case OP_CREF: - case OP_DNCREF: - case OP_RREF: - case OP_DNRREF: - case OP_DEF: - case OP_FAIL: - return FALSE; - - default: /* Assertion */ - if (!is_startline(scode, bracket_map, cd, atomcount)) return FALSE; - do scode += GET(scode, 1); while (*scode == OP_ALT); - scode += 1 + LINK_SIZE; - break; - } - scode = first_significant_code(scode, FALSE); - op = *scode; - } - - /* Non-capturing brackets */ - - if (op == OP_BRA || op == OP_BRAPOS || - op == OP_SBRA || op == OP_SBRAPOS) - { - if (!is_startline(scode, bracket_map, cd, atomcount)) return FALSE; - } - - /* Capturing brackets */ - - else if (op == OP_CBRA || op == OP_CBRAPOS || - op == OP_SCBRA || op == OP_SCBRAPOS) - { - int n = GET2(scode, 1+LINK_SIZE); - int new_map = bracket_map | ((n < 32)? (1 << n) : 1); - if (!is_startline(scode, new_map, cd, atomcount)) return FALSE; - } - - /* Positive forward assertions */ - - else if (op == OP_ASSERT) - { - if (!is_startline(scode, bracket_map, cd, atomcount)) return FALSE; - } - - /* Atomic brackets */ - - else if (op == OP_ONCE || op == OP_ONCE_NC) - { - if (!is_startline(scode, bracket_map, cd, atomcount + 1)) return FALSE; - } - - /* .* means "start at start or after \n" if it isn't in atomic brackets or - brackets that may be referenced, as long as the pattern does not contain - *PRUNE or *SKIP, because these break the feature. Consider, for example, - /.*?a(*PRUNE)b/ with the subject "aab", which matches "ab", i.e. not at the - start of a line. */ - - else if (op == OP_TYPESTAR || op == OP_TYPEMINSTAR || op == OP_TYPEPOSSTAR) - { - if (scode[1] != OP_ANY || (bracket_map & cd->backref_map) != 0 || - atomcount > 0 || cd->had_pruneorskip) - return FALSE; - } - - /* Check for explicit circumflex; anything else gives a FALSE result. Note - in particular that this includes atomic brackets OP_ONCE and OP_ONCE_NC - because the number of characters matched by .* cannot be adjusted inside - them. */ - - else if (op != OP_CIRC && op != OP_CIRCM) return FALSE; - - /* Move on to the next alternative */ - - code += GET(code, 1); - } -while (*code == OP_ALT); /* Loop for each alternative */ -return TRUE; -} - - - -/************************************************* -* Check for asserted fixed first char * -*************************************************/ - -/* During compilation, the "first char" settings from forward assertions are -discarded, because they can cause conflicts with actual literals that follow. -However, if we end up without a first char setting for an unanchored pattern, -it is worth scanning the regex to see if there is an initial asserted first -char. If all branches start with the same asserted char, or with a -non-conditional bracket all of whose alternatives start with the same asserted -char (recurse ad lib), then we return that char, with the flags set to zero or -REQ_CASELESS; otherwise return zero with REQ_NONE in the flags. - -Arguments: - code points to start of expression (the bracket) - flags points to the first char flags, or to REQ_NONE - inassert TRUE if in an assertion - -Returns: the fixed first char, or 0 with REQ_NONE in flags -*/ - -static pcre_uint32 -find_firstassertedchar(const pcre_uchar *code, pcre_int32 *flags, - BOOL inassert) -{ -register pcre_uint32 c = 0; -int cflags = REQ_NONE; - -*flags = REQ_NONE; -do { - pcre_uint32 d; - int dflags; - int xl = (*code == OP_CBRA || *code == OP_SCBRA || - *code == OP_CBRAPOS || *code == OP_SCBRAPOS)? IMM2_SIZE:0; - const pcre_uchar *scode = first_significant_code(code + 1+LINK_SIZE + xl, - TRUE); - register pcre_uchar op = *scode; - - switch(op) - { - default: - return 0; - - case OP_BRA: - case OP_BRAPOS: - case OP_CBRA: - case OP_SCBRA: - case OP_CBRAPOS: - case OP_SCBRAPOS: - case OP_ASSERT: - case OP_ONCE: - case OP_ONCE_NC: - d = find_firstassertedchar(scode, &dflags, op == OP_ASSERT); - if (dflags < 0) - return 0; - if (cflags < 0) { c = d; cflags = dflags; } else if (c != d || cflags != dflags) return 0; - break; - - case OP_EXACT: - scode += IMM2_SIZE; - /* Fall through */ - - case OP_CHAR: - case OP_PLUS: - case OP_MINPLUS: - case OP_POSPLUS: - if (!inassert) return 0; - if (cflags < 0) { c = scode[1]; cflags = 0; } - else if (c != scode[1]) return 0; - break; - - case OP_EXACTI: - scode += IMM2_SIZE; - /* Fall through */ - - case OP_CHARI: - case OP_PLUSI: - case OP_MINPLUSI: - case OP_POSPLUSI: - if (!inassert) return 0; - if (cflags < 0) { c = scode[1]; cflags = REQ_CASELESS; } - else if (c != scode[1]) return 0; - break; - } - - code += GET(code, 1); - } -while (*code == OP_ALT); - -*flags = cflags; -return c; -} - - - -/************************************************* -* Add an entry to the name/number table * -*************************************************/ - -/* This function is called between compiling passes to add an entry to the -name/number table, maintaining alphabetical order. Checking for permitted -and forbidden duplicates has already been done. - -Arguments: - cd the compile data block - name the name to add - length the length of the name - groupno the group number - -Returns: nothing -*/ - -static void -add_name(compile_data *cd, const pcre_uchar *name, int length, - unsigned int groupno) -{ -int i; -pcre_uchar *slot = cd->name_table; - -for (i = 0; i < cd->names_found; i++) - { - int crc = memcmp(name, slot+IMM2_SIZE, IN_UCHARS(length)); - if (crc == 0 && slot[IMM2_SIZE+length] != 0) - crc = -1; /* Current name is a substring */ - - /* Make space in the table and break the loop for an earlier name. For a - duplicate or later name, carry on. We do this for duplicates so that in the - simple case (when ?(| is not used) they are in order of their numbers. In all - cases they are in the order in which they appear in the pattern. */ - - if (crc < 0) - { - memmove(slot + cd->name_entry_size, slot, - IN_UCHARS((cd->names_found - i) * cd->name_entry_size)); - break; - } - - /* Continue the loop for a later or duplicate name */ - - slot += cd->name_entry_size; - } - -PUT2(slot, 0, groupno); -memcpy(slot + IMM2_SIZE, name, IN_UCHARS(length)); -slot[IMM2_SIZE + length] = 0; -cd->names_found++; -} - - - -/************************************************* -* Compile a Regular Expression * -*************************************************/ - -/* This function takes a string and returns a pointer to a block of store -holding a compiled version of the expression. The original API for this -function had no error code return variable; it is retained for backwards -compatibility. The new function is given a new name. - -Arguments: - pattern the regular expression - options various option bits - errorcodeptr pointer to error code variable (pcre_compile2() only) - can be NULL if you don't want a code value - errorptr pointer to pointer to error text - erroroffset ptr offset in pattern where error was detected - tables pointer to character tables or NULL - -Returns: pointer to compiled data block, or NULL on error, - with errorptr and erroroffset set -*/ - -#if defined COMPILE_PCRE8 -PCRE_EXP_DEFN pcre * PCRE_CALL_CONVENTION -pcre_compile(const char *pattern, int options, const char **errorptr, - int *erroroffset, const unsigned char *tables) -#elif defined COMPILE_PCRE16 -PCRE_EXP_DEFN pcre16 * PCRE_CALL_CONVENTION -pcre16_compile(PCRE_SPTR16 pattern, int options, const char **errorptr, - int *erroroffset, const unsigned char *tables) -#elif defined COMPILE_PCRE32 -PCRE_EXP_DEFN pcre32 * PCRE_CALL_CONVENTION -pcre32_compile(PCRE_SPTR32 pattern, int options, const char **errorptr, - int *erroroffset, const unsigned char *tables) -#endif -{ -#if defined COMPILE_PCRE8 -return pcre_compile2(pattern, options, NULL, errorptr, erroroffset, tables); -#elif defined COMPILE_PCRE16 -return pcre16_compile2(pattern, options, NULL, errorptr, erroroffset, tables); -#elif defined COMPILE_PCRE32 -return pcre32_compile2(pattern, options, NULL, errorptr, erroroffset, tables); -#endif -} - - -#if defined COMPILE_PCRE8 -PCRE_EXP_DEFN pcre * PCRE_CALL_CONVENTION -pcre_compile2(const char *pattern, int options, int *errorcodeptr, - const char **errorptr, int *erroroffset, const unsigned char *tables) -#elif defined COMPILE_PCRE16 -PCRE_EXP_DEFN pcre16 * PCRE_CALL_CONVENTION -pcre16_compile2(PCRE_SPTR16 pattern, int options, int *errorcodeptr, - const char **errorptr, int *erroroffset, const unsigned char *tables) -#elif defined COMPILE_PCRE32 -PCRE_EXP_DEFN pcre32 * PCRE_CALL_CONVENTION -pcre32_compile2(PCRE_SPTR32 pattern, int options, int *errorcodeptr, - const char **errorptr, int *erroroffset, const unsigned char *tables) -#endif -{ -REAL_PCRE *re; -int length = 1; /* For final END opcode */ -pcre_int32 firstcharflags, reqcharflags; -pcre_uint32 firstchar, reqchar; -pcre_uint32 limit_match = PCRE_UINT32_MAX; -pcre_uint32 limit_recursion = PCRE_UINT32_MAX; -int newline; -int errorcode = 0; -int skipatstart = 0; -BOOL utf; -BOOL never_utf = FALSE; -size_t size; -pcre_uchar *code; -const pcre_uchar *codestart; -const pcre_uchar *ptr; -compile_data compile_block; -compile_data *cd = &compile_block; - -/* This space is used for "compiling" into during the first phase, when we are -computing the amount of memory that is needed. Compiled items are thrown away -as soon as possible, so that a fairly large buffer should be sufficient for -this purpose. The same space is used in the second phase for remembering where -to fill in forward references to subpatterns. That may overflow, in which case -new memory is obtained from malloc(). */ - -pcre_uchar cworkspace[COMPILE_WORK_SIZE]; - -/* This vector is used for remembering name groups during the pre-compile. In a -similar way to cworkspace, it can be expanded using malloc() if necessary. */ - -named_group named_groups[NAMED_GROUP_LIST_SIZE]; - -/* Set this early so that early errors get offset 0. */ - -ptr = (const pcre_uchar *)pattern; - -/* We can't pass back an error message if errorptr is NULL; I guess the best we -can do is just return NULL, but we can set a code value if there is a code -pointer. */ - -if (errorptr == NULL) - { - if (errorcodeptr != NULL) *errorcodeptr = 99; - return NULL; - } - -*errorptr = NULL; -if (errorcodeptr != NULL) *errorcodeptr = ERR0; - -/* However, we can give a message for this error */ - -if (erroroffset == NULL) - { - errorcode = ERR16; - goto PCRE_EARLY_ERROR_RETURN2; - } - -*erroroffset = 0; - -/* Set up pointers to the individual character tables */ - -if (tables == NULL) tables = PRIV(default_tables); -cd->lcc = tables + lcc_offset; -cd->fcc = tables + fcc_offset; -cd->cbits = tables + cbits_offset; -cd->ctypes = tables + ctypes_offset; - -/* Check that all undefined public option bits are zero */ - -if ((options & ~PUBLIC_COMPILE_OPTIONS) != 0) - { - errorcode = ERR17; - goto PCRE_EARLY_ERROR_RETURN; - } - -/* If PCRE_NEVER_UTF is set, remember it. */ - -if ((options & PCRE_NEVER_UTF) != 0) never_utf = TRUE; - -/* Check for global one-time settings at the start of the pattern, and remember -the offset for later. */ - -cd->external_flags = 0; /* Initialize here for LIMIT_MATCH/RECURSION */ - -while (ptr[skipatstart] == CHAR_LEFT_PARENTHESIS && - ptr[skipatstart+1] == CHAR_ASTERISK) - { - int newnl = 0; - int newbsr = 0; - -/* For completeness and backward compatibility, (*UTFn) is supported in the -relevant libraries, but (*UTF) is generic and always supported. Note that -PCRE_UTF8 == PCRE_UTF16 == PCRE_UTF32. */ - -#ifdef COMPILE_PCRE8 - if (STRNCMP_UC_C8(ptr+skipatstart+2, STRING_UTF8_RIGHTPAR, 5) == 0) - { skipatstart += 7; options |= PCRE_UTF8; continue; } -#endif -#ifdef COMPILE_PCRE16 - if (STRNCMP_UC_C8(ptr+skipatstart+2, STRING_UTF16_RIGHTPAR, 6) == 0) - { skipatstart += 8; options |= PCRE_UTF16; continue; } -#endif -#ifdef COMPILE_PCRE32 - if (STRNCMP_UC_C8(ptr+skipatstart+2, STRING_UTF32_RIGHTPAR, 6) == 0) - { skipatstart += 8; options |= PCRE_UTF32; continue; } -#endif - - else if (STRNCMP_UC_C8(ptr+skipatstart+2, STRING_UTF_RIGHTPAR, 4) == 0) - { skipatstart += 6; options |= PCRE_UTF8; continue; } - else if (STRNCMP_UC_C8(ptr+skipatstart+2, STRING_UCP_RIGHTPAR, 4) == 0) - { skipatstart += 6; options |= PCRE_UCP; continue; } - else if (STRNCMP_UC_C8(ptr+skipatstart+2, STRING_NO_AUTO_POSSESS_RIGHTPAR, 16) == 0) - { skipatstart += 18; options |= PCRE_NO_AUTO_POSSESS; continue; } - else if (STRNCMP_UC_C8(ptr+skipatstart+2, STRING_NO_START_OPT_RIGHTPAR, 13) == 0) - { skipatstart += 15; options |= PCRE_NO_START_OPTIMIZE; continue; } - - else if (STRNCMP_UC_C8(ptr+skipatstart+2, STRING_LIMIT_MATCH_EQ, 12) == 0) - { - pcre_uint32 c = 0; - int p = skipatstart + 14; - while (isdigit(ptr[p])) - { - if (c > PCRE_UINT32_MAX / 10 - 1) break; /* Integer overflow */ - c = c*10 + ptr[p++] - CHAR_0; - } - if (ptr[p++] != CHAR_RIGHT_PARENTHESIS) break; - if (c < limit_match) - { - limit_match = c; - cd->external_flags |= PCRE_MLSET; - } - skipatstart = p; - continue; - } - - else if (STRNCMP_UC_C8(ptr+skipatstart+2, STRING_LIMIT_RECURSION_EQ, 16) == 0) - { - pcre_uint32 c = 0; - int p = skipatstart + 18; - while (isdigit(ptr[p])) - { - if (c > PCRE_UINT32_MAX / 10 - 1) break; /* Integer overflow check */ - c = c*10 + ptr[p++] - CHAR_0; - } - if (ptr[p++] != CHAR_RIGHT_PARENTHESIS) break; - if (c < limit_recursion) - { - limit_recursion = c; - cd->external_flags |= PCRE_RLSET; - } - skipatstart = p; - continue; - } - - if (STRNCMP_UC_C8(ptr+skipatstart+2, STRING_CR_RIGHTPAR, 3) == 0) - { skipatstart += 5; newnl = PCRE_NEWLINE_CR; } - else if (STRNCMP_UC_C8(ptr+skipatstart+2, STRING_LF_RIGHTPAR, 3) == 0) - { skipatstart += 5; newnl = PCRE_NEWLINE_LF; } - else if (STRNCMP_UC_C8(ptr+skipatstart+2, STRING_CRLF_RIGHTPAR, 5) == 0) - { skipatstart += 7; newnl = PCRE_NEWLINE_CR + PCRE_NEWLINE_LF; } - else if (STRNCMP_UC_C8(ptr+skipatstart+2, STRING_ANY_RIGHTPAR, 4) == 0) - { skipatstart += 6; newnl = PCRE_NEWLINE_ANY; } - else if (STRNCMP_UC_C8(ptr+skipatstart+2, STRING_ANYCRLF_RIGHTPAR, 8) == 0) - { skipatstart += 10; newnl = PCRE_NEWLINE_ANYCRLF; } - - else if (STRNCMP_UC_C8(ptr+skipatstart+2, STRING_BSR_ANYCRLF_RIGHTPAR, 12) == 0) - { skipatstart += 14; newbsr = PCRE_BSR_ANYCRLF; } - else if (STRNCMP_UC_C8(ptr+skipatstart+2, STRING_BSR_UNICODE_RIGHTPAR, 12) == 0) - { skipatstart += 14; newbsr = PCRE_BSR_UNICODE; } - - if (newnl != 0) - options = (options & ~PCRE_NEWLINE_BITS) | newnl; - else if (newbsr != 0) - options = (options & ~(PCRE_BSR_ANYCRLF|PCRE_BSR_UNICODE)) | newbsr; - else break; - } - -/* PCRE_UTF(16|32) have the same value as PCRE_UTF8. */ -utf = (options & PCRE_UTF8) != 0; -if (utf && never_utf) - { - errorcode = ERR78; - goto PCRE_EARLY_ERROR_RETURN2; - } - -/* Can't support UTF unless PCRE has been compiled to include the code. The -return of an error code from PRIV(valid_utf)() is a new feature, introduced in -release 8.13. It is passed back from pcre_[dfa_]exec(), but at the moment is -not used here. */ - -#ifdef SUPPORT_UTF -if (utf && (options & PCRE_NO_UTF8_CHECK) == 0 && - (errorcode = PRIV(valid_utf)((PCRE_PUCHAR)pattern, -1, erroroffset)) != 0) - { -#if defined COMPILE_PCRE8 - errorcode = ERR44; -#elif defined COMPILE_PCRE16 - errorcode = ERR74; -#elif defined COMPILE_PCRE32 - errorcode = ERR77; -#endif - goto PCRE_EARLY_ERROR_RETURN2; - } -#else -if (utf) - { - errorcode = ERR32; - goto PCRE_EARLY_ERROR_RETURN; - } -#endif - -/* Can't support UCP unless PCRE has been compiled to include the code. */ - -#ifndef SUPPORT_UCP -if ((options & PCRE_UCP) != 0) - { - errorcode = ERR67; - goto PCRE_EARLY_ERROR_RETURN; - } -#endif - -/* Check validity of \R options. */ - -if ((options & (PCRE_BSR_ANYCRLF|PCRE_BSR_UNICODE)) == - (PCRE_BSR_ANYCRLF|PCRE_BSR_UNICODE)) - { - errorcode = ERR56; - goto PCRE_EARLY_ERROR_RETURN; - } - -/* Handle different types of newline. The three bits give seven cases. The -current code allows for fixed one- or two-byte sequences, plus "any" and -"anycrlf". */ - -switch (options & PCRE_NEWLINE_BITS) - { - case 0: newline = NEWLINE; break; /* Build-time default */ - case PCRE_NEWLINE_CR: newline = CHAR_CR; break; - case PCRE_NEWLINE_LF: newline = CHAR_NL; break; - case PCRE_NEWLINE_CR+ - PCRE_NEWLINE_LF: newline = (CHAR_CR << 8) | CHAR_NL; break; - case PCRE_NEWLINE_ANY: newline = -1; break; - case PCRE_NEWLINE_ANYCRLF: newline = -2; break; - default: errorcode = ERR56; goto PCRE_EARLY_ERROR_RETURN; - } - -if (newline == -2) - { - cd->nltype = NLTYPE_ANYCRLF; - } -else if (newline < 0) - { - cd->nltype = NLTYPE_ANY; - } -else - { - cd->nltype = NLTYPE_FIXED; - if (newline > 255) - { - cd->nllen = 2; - cd->nl[0] = (newline >> 8) & 255; - cd->nl[1] = newline & 255; - } - else - { - cd->nllen = 1; - cd->nl[0] = newline; - } - } - -/* Maximum back reference and backref bitmap. The bitmap records up to 31 back -references to help in deciding whether (.*) can be treated as anchored or not. -*/ - -cd->top_backref = 0; -cd->backref_map = 0; - -/* Reflect pattern for debugging output */ - -DPRINTF(("------------------------------------------------------------------\n")); -#ifdef PCRE_DEBUG -print_puchar(stdout, (PCRE_PUCHAR)pattern); -#endif -DPRINTF(("\n")); - -/* Pretend to compile the pattern while actually just accumulating the length -of memory required. This behaviour is triggered by passing a non-NULL final -argument to compile_regex(). We pass a block of workspace (cworkspace) for it -to compile parts of the pattern into; the compiled code is discarded when it is -no longer needed, so hopefully this workspace will never overflow, though there -is a test for its doing so. */ - -cd->bracount = cd->final_bracount = 0; -cd->names_found = 0; -cd->name_entry_size = 0; -cd->name_table = NULL; -cd->dupnames = FALSE; -cd->dupgroups = FALSE; -cd->namedrefcount = 0; -cd->start_code = cworkspace; -cd->hwm = cworkspace; -cd->iscondassert = FALSE; -cd->start_workspace = cworkspace; -cd->workspace_size = COMPILE_WORK_SIZE; -cd->named_groups = named_groups; -cd->named_group_list_size = NAMED_GROUP_LIST_SIZE; -cd->start_pattern = (const pcre_uchar *)pattern; -cd->end_pattern = (const pcre_uchar *)(pattern + STRLEN_UC((const pcre_uchar *)pattern)); -cd->req_varyopt = 0; -cd->parens_depth = 0; -cd->assert_depth = 0; -cd->max_lookbehind = 0; -cd->external_options = options; -cd->open_caps = NULL; - -/* Now do the pre-compile. On error, errorcode will be set non-zero, so we -don't need to look at the result of the function here. The initial options have -been put into the cd block so that they can be changed if an option setting is -found within the regex right at the beginning. Bringing initial option settings -outside can help speed up starting point checks. */ - -ptr += skipatstart; -code = cworkspace; -*code = OP_BRA; - -(void)compile_regex(cd->external_options, &code, &ptr, &errorcode, FALSE, - FALSE, 0, 0, &firstchar, &firstcharflags, &reqchar, &reqcharflags, NULL, - cd, &length); -if (errorcode != 0) goto PCRE_EARLY_ERROR_RETURN; - -DPRINTF(("end pre-compile: length=%d workspace=%d\n", length, - (int)(cd->hwm - cworkspace))); - -if (length > MAX_PATTERN_SIZE) - { - errorcode = ERR20; - goto PCRE_EARLY_ERROR_RETURN; - } - -/* Compute the size of the data block for storing the compiled pattern. Integer -overflow should no longer be possible because nowadays we limit the maximum -value of cd->names_found and cd->name_entry_size. */ - -size = sizeof(REAL_PCRE) + - (length + cd->names_found * cd->name_entry_size) * sizeof(pcre_uchar); - -/* Get the memory. */ - -re = (REAL_PCRE *)(PUBL(malloc))(size); -if (re == NULL) - { - errorcode = ERR21; - goto PCRE_EARLY_ERROR_RETURN; - } - -/* Put in the magic number, and save the sizes, initial options, internal -flags, and character table pointer. NULL is used for the default character -tables. The nullpad field is at the end; it's there to help in the case when a -regex compiled on a system with 4-byte pointers is run on another with 8-byte -pointers. */ - -re->magic_number = MAGIC_NUMBER; -re->size = (int)size; -re->options = cd->external_options; -re->flags = cd->external_flags; -re->limit_match = limit_match; -re->limit_recursion = limit_recursion; -re->first_char = 0; -re->req_char = 0; -re->name_table_offset = sizeof(REAL_PCRE) / sizeof(pcre_uchar); -re->name_entry_size = cd->name_entry_size; -re->name_count = cd->names_found; -re->ref_count = 0; -re->tables = (tables == PRIV(default_tables))? NULL : tables; -re->nullpad = NULL; -#ifdef COMPILE_PCRE32 -re->dummy = 0; -#else -re->dummy1 = re->dummy2 = re->dummy3 = 0; -#endif - -/* The starting points of the name/number translation table and of the code are -passed around in the compile data block. The start/end pattern and initial -options are already set from the pre-compile phase, as is the name_entry_size -field. Reset the bracket count and the names_found field. Also reset the hwm -field; this time it's used for remembering forward references to subpatterns. -*/ - -cd->final_bracount = cd->bracount; /* Save for checking forward references */ -cd->parens_depth = 0; -cd->assert_depth = 0; -cd->bracount = 0; -cd->max_lookbehind = 0; -cd->name_table = (pcre_uchar *)re + re->name_table_offset; -codestart = cd->name_table + re->name_entry_size * re->name_count; -cd->start_code = codestart; -cd->hwm = (pcre_uchar *)(cd->start_workspace); -cd->iscondassert = FALSE; -cd->req_varyopt = 0; -cd->had_accept = FALSE; -cd->had_pruneorskip = FALSE; -cd->check_lookbehind = FALSE; -cd->open_caps = NULL; - -/* If any named groups were found, create the name/number table from the list -created in the first pass. */ - -if (cd->names_found > 0) - { - int i = cd->names_found; - named_group *ng = cd->named_groups; - cd->names_found = 0; - for (; i > 0; i--, ng++) - add_name(cd, ng->name, ng->length, ng->number); - if (cd->named_group_list_size > NAMED_GROUP_LIST_SIZE) - (PUBL(free))((void *)cd->named_groups); - } - -/* Set up a starting, non-extracting bracket, then compile the expression. On -error, errorcode will be set non-zero, so we don't need to look at the result -of the function here. */ - -ptr = (const pcre_uchar *)pattern + skipatstart; -code = (pcre_uchar *)codestart; -*code = OP_BRA; -(void)compile_regex(re->options, &code, &ptr, &errorcode, FALSE, FALSE, 0, 0, - &firstchar, &firstcharflags, &reqchar, &reqcharflags, NULL, cd, NULL); -re->top_bracket = cd->bracount; -re->top_backref = cd->top_backref; -re->max_lookbehind = cd->max_lookbehind; -re->flags = cd->external_flags | PCRE_MODE; - -if (cd->had_accept) - { - reqchar = 0; /* Must disable after (*ACCEPT) */ - reqcharflags = REQ_NONE; - } - -/* If not reached end of pattern on success, there's an excess bracket. */ - -if (errorcode == 0 && *ptr != CHAR_NULL) errorcode = ERR22; - -/* Fill in the terminating state and check for disastrous overflow, but -if debugging, leave the test till after things are printed out. */ - -*code++ = OP_END; - -#ifndef PCRE_DEBUG -if (code - codestart > length) errorcode = ERR23; -#endif - -#ifdef SUPPORT_VALGRIND -/* If the estimated length exceeds the really used length, mark the extra -allocated memory as unaddressable, so that any out-of-bound reads can be -detected. */ -VALGRIND_MAKE_MEM_NOACCESS(code, (length - (code - codestart)) * sizeof(pcre_uchar)); -#endif - -/* Fill in any forward references that are required. There may be repeated -references; optimize for them, as searching a large regex takes time. */ - -if (cd->hwm > cd->start_workspace) - { - int prev_recno = -1; - const pcre_uchar *groupptr = NULL; - while (errorcode == 0 && cd->hwm > cd->start_workspace) - { - int offset, recno; - cd->hwm -= LINK_SIZE; - offset = GET(cd->hwm, 0); - - /* Check that the hwm handling hasn't gone wrong. This whole area is - rewritten in PCRE2 because there are some obscure cases. */ - - if (offset == 0 || codestart[offset-1] != OP_RECURSE) - { - errorcode = ERR10; - break; - } - - recno = GET(codestart, offset); - if (recno != prev_recno) - { - groupptr = PRIV(find_bracket)(codestart, utf, recno); - prev_recno = recno; - } - if (groupptr == NULL) errorcode = ERR53; - else PUT(((pcre_uchar *)codestart), offset, (int)(groupptr - codestart)); - } - } - -/* If the workspace had to be expanded, free the new memory. Set the pointer to -NULL to indicate that forward references have been filled in. */ - -if (cd->workspace_size > COMPILE_WORK_SIZE) - (PUBL(free))((void *)cd->start_workspace); -cd->start_workspace = NULL; - -/* Give an error if there's back reference to a non-existent capturing -subpattern. */ - -if (errorcode == 0 && re->top_backref > re->top_bracket) errorcode = ERR15; - -/* Unless disabled, check whether any single character iterators can be -auto-possessified. The function overwrites the appropriate opcode values, so -the type of the pointer must be cast. NOTE: the intermediate variable "temp" is -used in this code because at least one compiler gives a warning about loss of -"const" attribute if the cast (pcre_uchar *)codestart is used directly in the -function call. */ - -if (errorcode == 0 && (options & PCRE_NO_AUTO_POSSESS) == 0) - { - pcre_uchar *temp = (pcre_uchar *)codestart; - auto_possessify(temp, utf, cd); - } - -/* If there were any lookbehind assertions that contained OP_RECURSE -(recursions or subroutine calls), a flag is set for them to be checked here, -because they may contain forward references. Actual recursions cannot be fixed -length, but subroutine calls can. It is done like this so that those without -OP_RECURSE that are not fixed length get a diagnosic with a useful offset. The -exceptional ones forgo this. We scan the pattern to check that they are fixed -length, and set their lengths. */ - -if (errorcode == 0 && cd->check_lookbehind) - { - pcre_uchar *cc = (pcre_uchar *)codestart; - - /* Loop, searching for OP_REVERSE items, and process those that do not have - their length set. (Actually, it will also re-process any that have a length - of zero, but that is a pathological case, and it does no harm.) When we find - one, we temporarily terminate the branch it is in while we scan it. */ - - for (cc = (pcre_uchar *)PRIV(find_bracket)(codestart, utf, -1); - cc != NULL; - cc = (pcre_uchar *)PRIV(find_bracket)(cc, utf, -1)) - { - if (GET(cc, 1) == 0) - { - int fixed_length; - pcre_uchar *be = cc - 1 - LINK_SIZE + GET(cc, -LINK_SIZE); - int end_op = *be; - *be = OP_END; - fixed_length = find_fixedlength(cc, (re->options & PCRE_UTF8) != 0, TRUE, - cd, NULL); - *be = end_op; - DPRINTF(("fixed length = %d\n", fixed_length)); - if (fixed_length < 0) - { - errorcode = (fixed_length == -2)? ERR36 : - (fixed_length == -4)? ERR70 : ERR25; - break; - } - if (fixed_length > cd->max_lookbehind) cd->max_lookbehind = fixed_length; - PUT(cc, 1, fixed_length); - } - cc += 1 + LINK_SIZE; - } - } - -/* Failed to compile, or error while post-processing */ - -if (errorcode != 0) - { - (PUBL(free))(re); - PCRE_EARLY_ERROR_RETURN: - *erroroffset = (int)(ptr - (const pcre_uchar *)pattern); - PCRE_EARLY_ERROR_RETURN2: - *errorptr = find_error_text(errorcode); - if (errorcodeptr != NULL) *errorcodeptr = errorcode; - return NULL; - } - -/* If the anchored option was not passed, set the flag if we can determine that -the pattern is anchored by virtue of ^ characters or \A or anything else, such -as starting with non-atomic .* when DOTALL is set and there are no occurrences -of *PRUNE or *SKIP. - -Otherwise, if we know what the first byte has to be, save it, because that -speeds up unanchored matches no end. If not, see if we can set the -PCRE_STARTLINE flag. This is helpful for multiline matches when all branches -start with ^. and also when all branches start with non-atomic .* for -non-DOTALL matches when *PRUNE and SKIP are not present. */ - -if ((re->options & PCRE_ANCHORED) == 0) - { - if (is_anchored(codestart, 0, cd, 0)) re->options |= PCRE_ANCHORED; - else - { - if (firstcharflags < 0) - firstchar = find_firstassertedchar(codestart, &firstcharflags, FALSE); - if (firstcharflags >= 0) /* Remove caseless flag for non-caseable chars */ - { -#if defined COMPILE_PCRE8 - re->first_char = firstchar & 0xff; -#elif defined COMPILE_PCRE16 - re->first_char = firstchar & 0xffff; -#elif defined COMPILE_PCRE32 - re->first_char = firstchar; -#endif - if ((firstcharflags & REQ_CASELESS) != 0) - { -#if defined SUPPORT_UCP && !(defined COMPILE_PCRE8) - /* We ignore non-ASCII first chars in 8 bit mode. */ - if (utf) - { - if (re->first_char < 128) - { - if (cd->fcc[re->first_char] != re->first_char) - re->flags |= PCRE_FCH_CASELESS; - } - else if (UCD_OTHERCASE(re->first_char) != re->first_char) - re->flags |= PCRE_FCH_CASELESS; - } - else -#endif - if (MAX_255(re->first_char) - && cd->fcc[re->first_char] != re->first_char) - re->flags |= PCRE_FCH_CASELESS; - } - - re->flags |= PCRE_FIRSTSET; - } - - else if (is_startline(codestart, 0, cd, 0)) re->flags |= PCRE_STARTLINE; - } - } - -/* For an anchored pattern, we use the "required byte" only if it follows a -variable length item in the regex. Remove the caseless flag for non-caseable -bytes. */ - -if (reqcharflags >= 0 && - ((re->options & PCRE_ANCHORED) == 0 || (reqcharflags & REQ_VARY) != 0)) - { -#if defined COMPILE_PCRE8 - re->req_char = reqchar & 0xff; -#elif defined COMPILE_PCRE16 - re->req_char = reqchar & 0xffff; -#elif defined COMPILE_PCRE32 - re->req_char = reqchar; -#endif - if ((reqcharflags & REQ_CASELESS) != 0) - { -#if defined SUPPORT_UCP && !(defined COMPILE_PCRE8) - /* We ignore non-ASCII first chars in 8 bit mode. */ - if (utf) - { - if (re->req_char < 128) - { - if (cd->fcc[re->req_char] != re->req_char) - re->flags |= PCRE_RCH_CASELESS; - } - else if (UCD_OTHERCASE(re->req_char) != re->req_char) - re->flags |= PCRE_RCH_CASELESS; - } - else -#endif - if (MAX_255(re->req_char) && cd->fcc[re->req_char] != re->req_char) - re->flags |= PCRE_RCH_CASELESS; - } - - re->flags |= PCRE_REQCHSET; - } - -/* Print out the compiled data if debugging is enabled. This is never the -case when building a production library. */ - -#ifdef PCRE_DEBUG -printf("Length = %d top_bracket = %d top_backref = %d\n", - length, re->top_bracket, re->top_backref); - -printf("Options=%08x\n", re->options); - -if ((re->flags & PCRE_FIRSTSET) != 0) - { - pcre_uchar ch = re->first_char; - const char *caseless = - ((re->flags & PCRE_FCH_CASELESS) == 0)? "" : " (caseless)"; - if (PRINTABLE(ch)) printf("First char = %c%s\n", ch, caseless); - else printf("First char = \\x%02x%s\n", ch, caseless); - } - -if ((re->flags & PCRE_REQCHSET) != 0) - { - pcre_uchar ch = re->req_char; - const char *caseless = - ((re->flags & PCRE_RCH_CASELESS) == 0)? "" : " (caseless)"; - if (PRINTABLE(ch)) printf("Req char = %c%s\n", ch, caseless); - else printf("Req char = \\x%02x%s\n", ch, caseless); - } - -#if defined COMPILE_PCRE8 -pcre_printint((pcre *)re, stdout, TRUE); -#elif defined COMPILE_PCRE16 -pcre16_printint((pcre *)re, stdout, TRUE); -#elif defined COMPILE_PCRE32 -pcre32_printint((pcre *)re, stdout, TRUE); -#endif - -/* This check is done here in the debugging case so that the code that -was compiled can be seen. */ - -if (code - codestart > length) - { - (PUBL(free))(re); - *errorptr = find_error_text(ERR23); - *erroroffset = ptr - (pcre_uchar *)pattern; - if (errorcodeptr != NULL) *errorcodeptr = ERR23; - return NULL; - } -#endif /* PCRE_DEBUG */ - -/* Check for a pattern than can match an empty string, so that this information -can be provided to applications. */ - -do - { - if (could_be_empty_branch(codestart, code, utf, cd, NULL)) - { - re->flags |= PCRE_MATCH_EMPTY; - break; - } - codestart += GET(codestart, 1); - } -while (*codestart == OP_ALT); - -#if defined COMPILE_PCRE8 -return (pcre *)re; -#elif defined COMPILE_PCRE16 -return (pcre16 *)re; -#elif defined COMPILE_PCRE32 -return (pcre32 *)re; -#endif -} - -/* End of pcre_compile.c */ diff --git a/src/third_party/pcre-8.38/pcre_config.c b/src/third_party/pcre-8.38/pcre_config.c deleted file mode 100644 index 1cbdd9c960c..00000000000 --- a/src/third_party/pcre-8.38/pcre_config.c +++ /dev/null @@ -1,190 +0,0 @@ -/************************************************* -* Perl-Compatible Regular Expressions * -*************************************************/ - -/* PCRE is a library of functions to support regular expressions whose syntax -and semantics are as close as possible to those of the Perl 5 language. - - Written by Philip Hazel - Copyright (c) 1997-2012 University of Cambridge - ------------------------------------------------------------------------------ -Redistribution and use in source and binary forms, with or without -modification, are permitted provided that the following conditions are met: - - * Redistributions of source code must retain the above copyright notice, - this list of conditions and the following disclaimer. - - * Redistributions in binary form must reproduce the above copyright - notice, this list of conditions and the following disclaimer in the - documentation and/or other materials provided with the distribution. - - * Neither the name of the University of Cambridge nor the names of its - contributors may be used to endorse or promote products derived from - this software without specific prior written permission. - -THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS" -AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE -IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE -ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR CONTRIBUTORS BE -LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR -CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF -SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS -INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN -CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) -ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE -POSSIBILITY OF SUCH DAMAGE. ------------------------------------------------------------------------------ -*/ - - -/* This module contains the external function pcre_config(). */ - - -#ifdef HAVE_CONFIG_H -#include "config.h" -#endif - -/* Keep the original link size. */ -static int real_link_size = LINK_SIZE; - -#include "pcre_internal.h" - - -/************************************************* -* Return info about what features are configured * -*************************************************/ - -/* This function has an extensible interface so that additional items can be -added compatibly. - -Arguments: - what what information is required - where where to put the information - -Returns: 0 if data returned, negative on error -*/ - -#if defined COMPILE_PCRE8 -PCRE_EXP_DEFN int PCRE_CALL_CONVENTION -pcre_config(int what, void *where) -#elif defined COMPILE_PCRE16 -PCRE_EXP_DEFN int PCRE_CALL_CONVENTION -pcre16_config(int what, void *where) -#elif defined COMPILE_PCRE32 -PCRE_EXP_DEFN int PCRE_CALL_CONVENTION -pcre32_config(int what, void *where) -#endif -{ -switch (what) - { - case PCRE_CONFIG_UTF8: -#if defined COMPILE_PCRE16 || defined COMPILE_PCRE32 - *((int *)where) = 0; - return PCRE_ERROR_BADOPTION; -#else -#if defined SUPPORT_UTF - *((int *)where) = 1; -#else - *((int *)where) = 0; -#endif - break; -#endif - - case PCRE_CONFIG_UTF16: -#if defined COMPILE_PCRE8 || defined COMPILE_PCRE32 - *((int *)where) = 0; - return PCRE_ERROR_BADOPTION; -#else -#if defined SUPPORT_UTF - *((int *)where) = 1; -#else - *((int *)where) = 0; -#endif - break; -#endif - - case PCRE_CONFIG_UTF32: -#if defined COMPILE_PCRE8 || defined COMPILE_PCRE16 - *((int *)where) = 0; - return PCRE_ERROR_BADOPTION; -#else -#if defined SUPPORT_UTF - *((int *)where) = 1; -#else - *((int *)where) = 0; -#endif - break; -#endif - - case PCRE_CONFIG_UNICODE_PROPERTIES: -#ifdef SUPPORT_UCP - *((int *)where) = 1; -#else - *((int *)where) = 0; -#endif - break; - - case PCRE_CONFIG_JIT: -#ifdef SUPPORT_JIT - *((int *)where) = 1; -#else - *((int *)where) = 0; -#endif - break; - - case PCRE_CONFIG_JITTARGET: -#ifdef SUPPORT_JIT - *((const char **)where) = PRIV(jit_get_target)(); -#else - *((const char **)where) = NULL; -#endif - break; - - case PCRE_CONFIG_NEWLINE: - *((int *)where) = NEWLINE; - break; - - case PCRE_CONFIG_BSR: -#ifdef BSR_ANYCRLF - *((int *)where) = 1; -#else - *((int *)where) = 0; -#endif - break; - - case PCRE_CONFIG_LINK_SIZE: - *((int *)where) = real_link_size; - break; - - case PCRE_CONFIG_POSIX_MALLOC_THRESHOLD: - *((int *)where) = POSIX_MALLOC_THRESHOLD; - break; - - case PCRE_CONFIG_PARENS_LIMIT: - *((unsigned long int *)where) = PARENS_NEST_LIMIT; - break; - - case PCRE_CONFIG_MATCH_LIMIT: - *((unsigned long int *)where) = MATCH_LIMIT; - break; - - case PCRE_CONFIG_MATCH_LIMIT_RECURSION: - *((unsigned long int *)where) = MATCH_LIMIT_RECURSION; - break; - - case PCRE_CONFIG_STACKRECURSE: -#ifdef NO_RECURSE - *((int *)where) = 0; -#else - *((int *)where) = 1; -#endif - break; - - default: return PCRE_ERROR_BADOPTION; - } - -return 0; -} - -/* End of pcre_config.c */ diff --git a/src/third_party/pcre-8.38/pcre_dfa_exec.c b/src/third_party/pcre-8.38/pcre_dfa_exec.c deleted file mode 100644 index 170ce6a0016..00000000000 --- a/src/third_party/pcre-8.38/pcre_dfa_exec.c +++ /dev/null @@ -1,3674 +0,0 @@ -/************************************************* -* Perl-Compatible Regular Expressions * -*************************************************/ - -/* PCRE is a library of functions to support regular expressions whose syntax -and semantics are as close as possible to those of the Perl 5 language (but see -below for why this module is different). - - Written by Philip Hazel - Copyright (c) 1997-2014 University of Cambridge - ------------------------------------------------------------------------------ -Redistribution and use in source and binary forms, with or without -modification, are permitted provided that the following conditions are met: - - * Redistributions of source code must retain the above copyright notice, - this list of conditions and the following disclaimer. - - * Redistributions in binary form must reproduce the above copyright - notice, this list of conditions and the following disclaimer in the - documentation and/or other materials provided with the distribution. - - * Neither the name of the University of Cambridge nor the names of its - contributors may be used to endorse or promote products derived from - this software without specific prior written permission. - -THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS" -AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE -IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE -ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR CONTRIBUTORS BE -LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR -CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF -SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS -INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN -CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) -ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE -POSSIBILITY OF SUCH DAMAGE. ------------------------------------------------------------------------------ -*/ - -/* This module contains the external function pcre_dfa_exec(), which is an -alternative matching function that uses a sort of DFA algorithm (not a true -FSM). This is NOT Perl-compatible, but it has advantages in certain -applications. */ - - -/* NOTE ABOUT PERFORMANCE: A user of this function sent some code that improved -the performance of his patterns greatly. I could not use it as it stood, as it -was not thread safe, and made assumptions about pattern sizes. Also, it caused -test 7 to loop, and test 9 to crash with a segfault. - -The issue is the check for duplicate states, which is done by a simple linear -search up the state list. (Grep for "duplicate" below to find the code.) For -many patterns, there will never be many states active at one time, so a simple -linear search is fine. In patterns that have many active states, it might be a -bottleneck. The suggested code used an indexing scheme to remember which states -had previously been used for each character, and avoided the linear search when -it knew there was no chance of a duplicate. This was implemented when adding -states to the state lists. - -I wrote some thread-safe, not-limited code to try something similar at the time -of checking for duplicates (instead of when adding states), using index vectors -on the stack. It did give a 13% improvement with one specially constructed -pattern for certain subject strings, but on other strings and on many of the -simpler patterns in the test suite it did worse. The major problem, I think, -was the extra time to initialize the index. This had to be done for each call -of internal_dfa_exec(). (The supplied patch used a static vector, initialized -only once - I suspect this was the cause of the problems with the tests.) - -Overall, I concluded that the gains in some cases did not outweigh the losses -in others, so I abandoned this code. */ - - - -#ifdef HAVE_CONFIG_H -#include "config.h" -#endif - -#define NLBLOCK md /* Block containing newline information */ -#define PSSTART start_subject /* Field containing processed string start */ -#define PSEND end_subject /* Field containing processed string end */ - -#include "pcre_internal.h" - - -/* For use to indent debugging output */ - -#define SP " " - - -/************************************************* -* Code parameters and static tables * -*************************************************/ - -/* These are offsets that are used to turn the OP_TYPESTAR and friends opcodes -into others, under special conditions. A gap of 20 between the blocks should be -enough. The resulting opcodes don't have to be less than 256 because they are -never stored, so we push them well clear of the normal opcodes. */ - -#define OP_PROP_EXTRA 300 -#define OP_EXTUNI_EXTRA 320 -#define OP_ANYNL_EXTRA 340 -#define OP_HSPACE_EXTRA 360 -#define OP_VSPACE_EXTRA 380 - - -/* This table identifies those opcodes that are followed immediately by a -character that is to be tested in some way. This makes it possible to -centralize the loading of these characters. In the case of Type * etc, the -"character" is the opcode for \D, \d, \S, \s, \W, or \w, which will always be a -small value. Non-zero values in the table are the offsets from the opcode where -the character is to be found. ***NOTE*** If the start of this table is -modified, the three tables that follow must also be modified. */ - -static const pcre_uint8 coptable[] = { - 0, /* End */ - 0, 0, 0, 0, 0, /* \A, \G, \K, \B, \b */ - 0, 0, 0, 0, 0, 0, /* \D, \d, \S, \s, \W, \w */ - 0, 0, 0, /* Any, AllAny, Anybyte */ - 0, 0, /* \P, \p */ - 0, 0, 0, 0, 0, /* \R, \H, \h, \V, \v */ - 0, /* \X */ - 0, 0, 0, 0, 0, 0, /* \Z, \z, $, $M, ^, ^M */ - 1, /* Char */ - 1, /* Chari */ - 1, /* not */ - 1, /* noti */ - /* Positive single-char repeats */ - 1, 1, 1, 1, 1, 1, /* *, *?, +, +?, ?, ?? */ - 1+IMM2_SIZE, 1+IMM2_SIZE, /* upto, minupto */ - 1+IMM2_SIZE, /* exact */ - 1, 1, 1, 1+IMM2_SIZE, /* *+, ++, ?+, upto+ */ - 1, 1, 1, 1, 1, 1, /* *I, *?I, +I, +?I, ?I, ??I */ - 1+IMM2_SIZE, 1+IMM2_SIZE, /* upto I, minupto I */ - 1+IMM2_SIZE, /* exact I */ - 1, 1, 1, 1+IMM2_SIZE, /* *+I, ++I, ?+I, upto+I */ - /* Negative single-char repeats - only for chars < 256 */ - 1, 1, 1, 1, 1, 1, /* NOT *, *?, +, +?, ?, ?? */ - 1+IMM2_SIZE, 1+IMM2_SIZE, /* NOT upto, minupto */ - 1+IMM2_SIZE, /* NOT exact */ - 1, 1, 1, 1+IMM2_SIZE, /* NOT *+, ++, ?+, upto+ */ - 1, 1, 1, 1, 1, 1, /* NOT *I, *?I, +I, +?I, ?I, ??I */ - 1+IMM2_SIZE, 1+IMM2_SIZE, /* NOT upto I, minupto I */ - 1+IMM2_SIZE, /* NOT exact I */ - 1, 1, 1, 1+IMM2_SIZE, /* NOT *+I, ++I, ?+I, upto+I */ - /* Positive type repeats */ - 1, 1, 1, 1, 1, 1, /* Type *, *?, +, +?, ?, ?? */ - 1+IMM2_SIZE, 1+IMM2_SIZE, /* Type upto, minupto */ - 1+IMM2_SIZE, /* Type exact */ - 1, 1, 1, 1+IMM2_SIZE, /* Type *+, ++, ?+, upto+ */ - /* Character class & ref repeats */ - 0, 0, 0, 0, 0, 0, /* *, *?, +, +?, ?, ?? */ - 0, 0, /* CRRANGE, CRMINRANGE */ - 0, 0, 0, 0, /* Possessive *+, ++, ?+, CRPOSRANGE */ - 0, /* CLASS */ - 0, /* NCLASS */ - 0, /* XCLASS - variable length */ - 0, /* REF */ - 0, /* REFI */ - 0, /* DNREF */ - 0, /* DNREFI */ - 0, /* RECURSE */ - 0, /* CALLOUT */ - 0, /* Alt */ - 0, /* Ket */ - 0, /* KetRmax */ - 0, /* KetRmin */ - 0, /* KetRpos */ - 0, /* Reverse */ - 0, /* Assert */ - 0, /* Assert not */ - 0, /* Assert behind */ - 0, /* Assert behind not */ - 0, 0, /* ONCE, ONCE_NC */ - 0, 0, 0, 0, 0, /* BRA, BRAPOS, CBRA, CBRAPOS, COND */ - 0, 0, 0, 0, 0, /* SBRA, SBRAPOS, SCBRA, SCBRAPOS, SCOND */ - 0, 0, /* CREF, DNCREF */ - 0, 0, /* RREF, DNRREF */ - 0, /* DEF */ - 0, 0, 0, /* BRAZERO, BRAMINZERO, BRAPOSZERO */ - 0, 0, 0, /* MARK, PRUNE, PRUNE_ARG */ - 0, 0, 0, 0, /* SKIP, SKIP_ARG, THEN, THEN_ARG */ - 0, 0, 0, 0, /* COMMIT, FAIL, ACCEPT, ASSERT_ACCEPT */ - 0, 0 /* CLOSE, SKIPZERO */ -}; - -/* This table identifies those opcodes that inspect a character. It is used to -remember the fact that a character could have been inspected when the end of -the subject is reached. ***NOTE*** If the start of this table is modified, the -two tables that follow must also be modified. */ - -static const pcre_uint8 poptable[] = { - 0, /* End */ - 0, 0, 0, 1, 1, /* \A, \G, \K, \B, \b */ - 1, 1, 1, 1, 1, 1, /* \D, \d, \S, \s, \W, \w */ - 1, 1, 1, /* Any, AllAny, Anybyte */ - 1, 1, /* \P, \p */ - 1, 1, 1, 1, 1, /* \R, \H, \h, \V, \v */ - 1, /* \X */ - 0, 0, 0, 0, 0, 0, /* \Z, \z, $, $M, ^, ^M */ - 1, /* Char */ - 1, /* Chari */ - 1, /* not */ - 1, /* noti */ - /* Positive single-char repeats */ - 1, 1, 1, 1, 1, 1, /* *, *?, +, +?, ?, ?? */ - 1, 1, 1, /* upto, minupto, exact */ - 1, 1, 1, 1, /* *+, ++, ?+, upto+ */ - 1, 1, 1, 1, 1, 1, /* *I, *?I, +I, +?I, ?I, ??I */ - 1, 1, 1, /* upto I, minupto I, exact I */ - 1, 1, 1, 1, /* *+I, ++I, ?+I, upto+I */ - /* Negative single-char repeats - only for chars < 256 */ - 1, 1, 1, 1, 1, 1, /* NOT *, *?, +, +?, ?, ?? */ - 1, 1, 1, /* NOT upto, minupto, exact */ - 1, 1, 1, 1, /* NOT *+, ++, ?+, upto+ */ - 1, 1, 1, 1, 1, 1, /* NOT *I, *?I, +I, +?I, ?I, ??I */ - 1, 1, 1, /* NOT upto I, minupto I, exact I */ - 1, 1, 1, 1, /* NOT *+I, ++I, ?+I, upto+I */ - /* Positive type repeats */ - 1, 1, 1, 1, 1, 1, /* Type *, *?, +, +?, ?, ?? */ - 1, 1, 1, /* Type upto, minupto, exact */ - 1, 1, 1, 1, /* Type *+, ++, ?+, upto+ */ - /* Character class & ref repeats */ - 1, 1, 1, 1, 1, 1, /* *, *?, +, +?, ?, ?? */ - 1, 1, /* CRRANGE, CRMINRANGE */ - 1, 1, 1, 1, /* Possessive *+, ++, ?+, CRPOSRANGE */ - 1, /* CLASS */ - 1, /* NCLASS */ - 1, /* XCLASS - variable length */ - 0, /* REF */ - 0, /* REFI */ - 0, /* DNREF */ - 0, /* DNREFI */ - 0, /* RECURSE */ - 0, /* CALLOUT */ - 0, /* Alt */ - 0, /* Ket */ - 0, /* KetRmax */ - 0, /* KetRmin */ - 0, /* KetRpos */ - 0, /* Reverse */ - 0, /* Assert */ - 0, /* Assert not */ - 0, /* Assert behind */ - 0, /* Assert behind not */ - 0, 0, /* ONCE, ONCE_NC */ - 0, 0, 0, 0, 0, /* BRA, BRAPOS, CBRA, CBRAPOS, COND */ - 0, 0, 0, 0, 0, /* SBRA, SBRAPOS, SCBRA, SCBRAPOS, SCOND */ - 0, 0, /* CREF, DNCREF */ - 0, 0, /* RREF, DNRREF */ - 0, /* DEF */ - 0, 0, 0, /* BRAZERO, BRAMINZERO, BRAPOSZERO */ - 0, 0, 0, /* MARK, PRUNE, PRUNE_ARG */ - 0, 0, 0, 0, /* SKIP, SKIP_ARG, THEN, THEN_ARG */ - 0, 0, 0, 0, /* COMMIT, FAIL, ACCEPT, ASSERT_ACCEPT */ - 0, 0 /* CLOSE, SKIPZERO */ -}; - -/* These 2 tables allow for compact code for testing for \D, \d, \S, \s, \W, -and \w */ - -static const pcre_uint8 toptable1[] = { - 0, 0, 0, 0, 0, 0, - ctype_digit, ctype_digit, - ctype_space, ctype_space, - ctype_word, ctype_word, - 0, 0 /* OP_ANY, OP_ALLANY */ -}; - -static const pcre_uint8 toptable2[] = { - 0, 0, 0, 0, 0, 0, - ctype_digit, 0, - ctype_space, 0, - ctype_word, 0, - 1, 1 /* OP_ANY, OP_ALLANY */ -}; - - -/* Structure for holding data about a particular state, which is in effect the -current data for an active path through the match tree. It must consist -entirely of ints because the working vector we are passed, and which we put -these structures in, is a vector of ints. */ - -typedef struct stateblock { - int offset; /* Offset to opcode */ - int count; /* Count for repeats */ - int data; /* Some use extra data */ -} stateblock; - -#define INTS_PER_STATEBLOCK (int)(sizeof(stateblock)/sizeof(int)) - - -#ifdef PCRE_DEBUG -/************************************************* -* Print character string * -*************************************************/ - -/* Character string printing function for debugging. - -Arguments: - p points to string - length number of bytes - f where to print - -Returns: nothing -*/ - -static void -pchars(const pcre_uchar *p, int length, FILE *f) -{ -pcre_uint32 c; -while (length-- > 0) - { - if (isprint(c = *(p++))) - fprintf(f, "%c", c); - else - fprintf(f, "\\x{%02x}", c); - } -} -#endif - - - -/************************************************* -* Execute a Regular Expression - DFA engine * -*************************************************/ - -/* This internal function applies a compiled pattern to a subject string, -starting at a given point, using a DFA engine. This function is called from the -external one, possibly multiple times if the pattern is not anchored. The -function calls itself recursively for some kinds of subpattern. - -Arguments: - md the match_data block with fixed information - this_start_code the opening bracket of this subexpression's code - current_subject where we currently are in the subject string - start_offset start offset in the subject string - offsets vector to contain the matching string offsets - offsetcount size of same - workspace vector of workspace - wscount size of same - rlevel function call recursion level - -Returns: > 0 => number of match offset pairs placed in offsets - = 0 => offsets overflowed; longest matches are present - -1 => failed to match - < -1 => some kind of unexpected problem - -The following macros are used for adding states to the two state vectors (one -for the current character, one for the following character). */ - -#define ADD_ACTIVE(x,y) \ - if (active_count++ < wscount) \ - { \ - next_active_state->offset = (x); \ - next_active_state->count = (y); \ - next_active_state++; \ - DPRINTF(("%.*sADD_ACTIVE(%d,%d)\n", rlevel*2-2, SP, (x), (y))); \ - } \ - else return PCRE_ERROR_DFA_WSSIZE - -#define ADD_ACTIVE_DATA(x,y,z) \ - if (active_count++ < wscount) \ - { \ - next_active_state->offset = (x); \ - next_active_state->count = (y); \ - next_active_state->data = (z); \ - next_active_state++; \ - DPRINTF(("%.*sADD_ACTIVE_DATA(%d,%d,%d)\n", rlevel*2-2, SP, (x), (y), (z))); \ - } \ - else return PCRE_ERROR_DFA_WSSIZE - -#define ADD_NEW(x,y) \ - if (new_count++ < wscount) \ - { \ - next_new_state->offset = (x); \ - next_new_state->count = (y); \ - next_new_state++; \ - DPRINTF(("%.*sADD_NEW(%d,%d)\n", rlevel*2-2, SP, (x), (y))); \ - } \ - else return PCRE_ERROR_DFA_WSSIZE - -#define ADD_NEW_DATA(x,y,z) \ - if (new_count++ < wscount) \ - { \ - next_new_state->offset = (x); \ - next_new_state->count = (y); \ - next_new_state->data = (z); \ - next_new_state++; \ - DPRINTF(("%.*sADD_NEW_DATA(%d,%d,%d) line %d\n", rlevel*2-2, SP, \ - (x), (y), (z), __LINE__)); \ - } \ - else return PCRE_ERROR_DFA_WSSIZE - -/* And now, here is the code */ - -static int -internal_dfa_exec( - dfa_match_data *md, - const pcre_uchar *this_start_code, - const pcre_uchar *current_subject, - int start_offset, - int *offsets, - int offsetcount, - int *workspace, - int wscount, - int rlevel) -{ -stateblock *active_states, *new_states, *temp_states; -stateblock *next_active_state, *next_new_state; - -const pcre_uint8 *ctypes, *lcc, *fcc; -const pcre_uchar *ptr; -const pcre_uchar *end_code, *first_op; - -dfa_recursion_info new_recursive; - -int active_count, new_count, match_count; - -/* Some fields in the md block are frequently referenced, so we load them into -independent variables in the hope that this will perform better. */ - -const pcre_uchar *start_subject = md->start_subject; -const pcre_uchar *end_subject = md->end_subject; -const pcre_uchar *start_code = md->start_code; - -#ifdef SUPPORT_UTF -BOOL utf = (md->poptions & PCRE_UTF8) != 0; -#else -BOOL utf = FALSE; -#endif - -BOOL reset_could_continue = FALSE; - -rlevel++; -offsetcount &= (-2); - -wscount -= 2; -wscount = (wscount - (wscount % (INTS_PER_STATEBLOCK * 2))) / - (2 * INTS_PER_STATEBLOCK); - -DPRINTF(("\n%.*s---------------------\n" - "%.*sCall to internal_dfa_exec f=%d\n", - rlevel*2-2, SP, rlevel*2-2, SP, rlevel)); - -ctypes = md->tables + ctypes_offset; -lcc = md->tables + lcc_offset; -fcc = md->tables + fcc_offset; - -match_count = PCRE_ERROR_NOMATCH; /* A negative number */ - -active_states = (stateblock *)(workspace + 2); -next_new_state = new_states = active_states + wscount; -new_count = 0; - -first_op = this_start_code + 1 + LINK_SIZE + - ((*this_start_code == OP_CBRA || *this_start_code == OP_SCBRA || - *this_start_code == OP_CBRAPOS || *this_start_code == OP_SCBRAPOS) - ? IMM2_SIZE:0); - -/* The first thing in any (sub) pattern is a bracket of some sort. Push all -the alternative states onto the list, and find out where the end is. This -makes is possible to use this function recursively, when we want to stop at a -matching internal ket rather than at the end. - -If the first opcode in the first alternative is OP_REVERSE, we are dealing with -a backward assertion. In that case, we have to find out the maximum amount to -move back, and set up each alternative appropriately. */ - -if (*first_op == OP_REVERSE) - { - int max_back = 0; - int gone_back; - - end_code = this_start_code; - do - { - int back = GET(end_code, 2+LINK_SIZE); - if (back > max_back) max_back = back; - end_code += GET(end_code, 1); - } - while (*end_code == OP_ALT); - - /* If we can't go back the amount required for the longest lookbehind - pattern, go back as far as we can; some alternatives may still be viable. */ - -#ifdef SUPPORT_UTF - /* In character mode we have to step back character by character */ - - if (utf) - { - for (gone_back = 0; gone_back < max_back; gone_back++) - { - if (current_subject <= start_subject) break; - current_subject--; - ACROSSCHAR(current_subject > start_subject, *current_subject, current_subject--); - } - } - else -#endif - - /* In byte-mode we can do this quickly. */ - - { - gone_back = (current_subject - max_back < start_subject)? - (int)(current_subject - start_subject) : max_back; - current_subject -= gone_back; - } - - /* Save the earliest consulted character */ - - if (current_subject < md->start_used_ptr) - md->start_used_ptr = current_subject; - - /* Now we can process the individual branches. */ - - end_code = this_start_code; - do - { - int back = GET(end_code, 2+LINK_SIZE); - if (back <= gone_back) - { - int bstate = (int)(end_code - start_code + 2 + 2*LINK_SIZE); - ADD_NEW_DATA(-bstate, 0, gone_back - back); - } - end_code += GET(end_code, 1); - } - while (*end_code == OP_ALT); - } - -/* This is the code for a "normal" subpattern (not a backward assertion). The -start of a whole pattern is always one of these. If we are at the top level, -we may be asked to restart matching from the same point that we reached for a -previous partial match. We still have to scan through the top-level branches to -find the end state. */ - -else - { - end_code = this_start_code; - - /* Restarting */ - - if (rlevel == 1 && (md->moptions & PCRE_DFA_RESTART) != 0) - { - do { end_code += GET(end_code, 1); } while (*end_code == OP_ALT); - new_count = workspace[1]; - if (!workspace[0]) - memcpy(new_states, active_states, new_count * sizeof(stateblock)); - } - - /* Not restarting */ - - else - { - int length = 1 + LINK_SIZE + - ((*this_start_code == OP_CBRA || *this_start_code == OP_SCBRA || - *this_start_code == OP_CBRAPOS || *this_start_code == OP_SCBRAPOS) - ? IMM2_SIZE:0); - do - { - ADD_NEW((int)(end_code - start_code + length), 0); - end_code += GET(end_code, 1); - length = 1 + LINK_SIZE; - } - while (*end_code == OP_ALT); - } - } - -workspace[0] = 0; /* Bit indicating which vector is current */ - -DPRINTF(("%.*sEnd state = %d\n", rlevel*2-2, SP, (int)(end_code - start_code))); - -/* Loop for scanning the subject */ - -ptr = current_subject; -for (;;) - { - int i, j; - int clen, dlen; - pcre_uint32 c, d; - int forced_fail = 0; - BOOL partial_newline = FALSE; - BOOL could_continue = reset_could_continue; - reset_could_continue = FALSE; - - /* Make the new state list into the active state list and empty the - new state list. */ - - temp_states = active_states; - active_states = new_states; - new_states = temp_states; - active_count = new_count; - new_count = 0; - - workspace[0] ^= 1; /* Remember for the restarting feature */ - workspace[1] = active_count; - -#ifdef PCRE_DEBUG - printf("%.*sNext character: rest of subject = \"", rlevel*2-2, SP); - pchars(ptr, STRLEN_UC(ptr), stdout); - printf("\"\n"); - - printf("%.*sActive states: ", rlevel*2-2, SP); - for (i = 0; i < active_count; i++) - printf("%d/%d ", active_states[i].offset, active_states[i].count); - printf("\n"); -#endif - - /* Set the pointers for adding new states */ - - next_active_state = active_states + active_count; - next_new_state = new_states; - - /* Load the current character from the subject outside the loop, as many - different states may want to look at it, and we assume that at least one - will. */ - - if (ptr < end_subject) - { - clen = 1; /* Number of data items in the character */ -#ifdef SUPPORT_UTF - GETCHARLENTEST(c, ptr, clen); -#else - c = *ptr; -#endif /* SUPPORT_UTF */ - } - else - { - clen = 0; /* This indicates the end of the subject */ - c = NOTACHAR; /* This value should never actually be used */ - } - - /* Scan up the active states and act on each one. The result of an action - may be to add more states to the currently active list (e.g. on hitting a - parenthesis) or it may be to put states on the new list, for considering - when we move the character pointer on. */ - - for (i = 0; i < active_count; i++) - { - stateblock *current_state = active_states + i; - BOOL caseless = FALSE; - const pcre_uchar *code; - int state_offset = current_state->offset; - int codevalue, rrc; - int count; - -#ifdef PCRE_DEBUG - printf ("%.*sProcessing state %d c=", rlevel*2-2, SP, state_offset); - if (clen == 0) printf("EOL\n"); - else if (c > 32 && c < 127) printf("'%c'\n", c); - else printf("0x%02x\n", c); -#endif - - /* A negative offset is a special case meaning "hold off going to this - (negated) state until the number of characters in the data field have - been skipped". If the could_continue flag was passed over from a previous - state, arrange for it to passed on. */ - - if (state_offset < 0) - { - if (current_state->data > 0) - { - DPRINTF(("%.*sSkipping this character\n", rlevel*2-2, SP)); - ADD_NEW_DATA(state_offset, current_state->count, - current_state->data - 1); - if (could_continue) reset_could_continue = TRUE; - continue; - } - else - { - current_state->offset = state_offset = -state_offset; - } - } - - /* Check for a duplicate state with the same count, and skip if found. - See the note at the head of this module about the possibility of improving - performance here. */ - - for (j = 0; j < i; j++) - { - if (active_states[j].offset == state_offset && - active_states[j].count == current_state->count) - { - DPRINTF(("%.*sDuplicate state: skipped\n", rlevel*2-2, SP)); - goto NEXT_ACTIVE_STATE; - } - } - - /* The state offset is the offset to the opcode */ - - code = start_code + state_offset; - codevalue = *code; - - /* If this opcode inspects a character, but we are at the end of the - subject, remember the fact for use when testing for a partial match. */ - - if (clen == 0 && poptable[codevalue] != 0) - could_continue = TRUE; - - /* If this opcode is followed by an inline character, load it. It is - tempting to test for the presence of a subject character here, but that - is wrong, because sometimes zero repetitions of the subject are - permitted. - - We also use this mechanism for opcodes such as OP_TYPEPLUS that take an - argument that is not a data character - but is always one byte long because - the values are small. We have to take special action to deal with \P, \p, - \H, \h, \V, \v and \X in this case. To keep the other cases fast, convert - these ones to new opcodes. */ - - if (coptable[codevalue] > 0) - { - dlen = 1; -#ifdef SUPPORT_UTF - if (utf) { GETCHARLEN(d, (code + coptable[codevalue]), dlen); } else -#endif /* SUPPORT_UTF */ - d = code[coptable[codevalue]]; - if (codevalue >= OP_TYPESTAR) - { - switch(d) - { - case OP_ANYBYTE: return PCRE_ERROR_DFA_UITEM; - case OP_NOTPROP: - case OP_PROP: codevalue += OP_PROP_EXTRA; break; - case OP_ANYNL: codevalue += OP_ANYNL_EXTRA; break; - case OP_EXTUNI: codevalue += OP_EXTUNI_EXTRA; break; - case OP_NOT_HSPACE: - case OP_HSPACE: codevalue += OP_HSPACE_EXTRA; break; - case OP_NOT_VSPACE: - case OP_VSPACE: codevalue += OP_VSPACE_EXTRA; break; - default: break; - } - } - } - else - { - dlen = 0; /* Not strictly necessary, but compilers moan */ - d = NOTACHAR; /* if these variables are not set. */ - } - - - /* Now process the individual opcodes */ - - switch (codevalue) - { -/* ========================================================================== */ - /* These cases are never obeyed. This is a fudge that causes a compile- - time error if the vectors coptable or poptable, which are indexed by - opcode, are not the correct length. It seems to be the only way to do - such a check at compile time, as the sizeof() operator does not work - in the C preprocessor. */ - - case OP_TABLE_LENGTH: - case OP_TABLE_LENGTH + - ((sizeof(coptable) == OP_TABLE_LENGTH) && - (sizeof(poptable) == OP_TABLE_LENGTH)): - break; - -/* ========================================================================== */ - /* Reached a closing bracket. If not at the end of the pattern, carry - on with the next opcode. For repeating opcodes, also add the repeat - state. Note that KETRPOS will always be encountered at the end of the - subpattern, because the possessive subpattern repeats are always handled - using recursive calls. Thus, it never adds any new states. - - At the end of the (sub)pattern, unless we have an empty string and - PCRE_NOTEMPTY is set, or PCRE_NOTEMPTY_ATSTART is set and we are at the - start of the subject, save the match data, shifting up all previous - matches so we always have the longest first. */ - - case OP_KET: - case OP_KETRMIN: - case OP_KETRMAX: - case OP_KETRPOS: - if (code != end_code) - { - ADD_ACTIVE(state_offset + 1 + LINK_SIZE, 0); - if (codevalue != OP_KET) - { - ADD_ACTIVE(state_offset - GET(code, 1), 0); - } - } - else - { - if (ptr > current_subject || - ((md->moptions & PCRE_NOTEMPTY) == 0 && - ((md->moptions & PCRE_NOTEMPTY_ATSTART) == 0 || - current_subject > start_subject + md->start_offset))) - { - if (match_count < 0) match_count = (offsetcount >= 2)? 1 : 0; - else if (match_count > 0 && ++match_count * 2 > offsetcount) - match_count = 0; - count = ((match_count == 0)? offsetcount : match_count * 2) - 2; - if (count > 0) memmove(offsets + 2, offsets, count * sizeof(int)); - if (offsetcount >= 2) - { - offsets[0] = (int)(current_subject - start_subject); - offsets[1] = (int)(ptr - start_subject); - DPRINTF(("%.*sSet matched string = \"%.*s\"\n", rlevel*2-2, SP, - offsets[1] - offsets[0], (char *)current_subject)); - } - if ((md->moptions & PCRE_DFA_SHORTEST) != 0) - { - DPRINTF(("%.*sEnd of internal_dfa_exec %d: returning %d\n" - "%.*s---------------------\n\n", rlevel*2-2, SP, rlevel, - match_count, rlevel*2-2, SP)); - return match_count; - } - } - } - break; - -/* ========================================================================== */ - /* These opcodes add to the current list of states without looking - at the current character. */ - - /*-----------------------------------------------------------------*/ - case OP_ALT: - do { code += GET(code, 1); } while (*code == OP_ALT); - ADD_ACTIVE((int)(code - start_code), 0); - break; - - /*-----------------------------------------------------------------*/ - case OP_BRA: - case OP_SBRA: - do - { - ADD_ACTIVE((int)(code - start_code + 1 + LINK_SIZE), 0); - code += GET(code, 1); - } - while (*code == OP_ALT); - break; - - /*-----------------------------------------------------------------*/ - case OP_CBRA: - case OP_SCBRA: - ADD_ACTIVE((int)(code - start_code + 1 + LINK_SIZE + IMM2_SIZE), 0); - code += GET(code, 1); - while (*code == OP_ALT) - { - ADD_ACTIVE((int)(code - start_code + 1 + LINK_SIZE), 0); - code += GET(code, 1); - } - break; - - /*-----------------------------------------------------------------*/ - case OP_BRAZERO: - case OP_BRAMINZERO: - ADD_ACTIVE(state_offset + 1, 0); - code += 1 + GET(code, 2); - while (*code == OP_ALT) code += GET(code, 1); - ADD_ACTIVE((int)(code - start_code + 1 + LINK_SIZE), 0); - break; - - /*-----------------------------------------------------------------*/ - case OP_SKIPZERO: - code += 1 + GET(code, 2); - while (*code == OP_ALT) code += GET(code, 1); - ADD_ACTIVE((int)(code - start_code + 1 + LINK_SIZE), 0); - break; - - /*-----------------------------------------------------------------*/ - case OP_CIRC: - if (ptr == start_subject && (md->moptions & PCRE_NOTBOL) == 0) - { ADD_ACTIVE(state_offset + 1, 0); } - break; - - /*-----------------------------------------------------------------*/ - case OP_CIRCM: - if ((ptr == start_subject && (md->moptions & PCRE_NOTBOL) == 0) || - (ptr != end_subject && WAS_NEWLINE(ptr))) - { ADD_ACTIVE(state_offset + 1, 0); } - break; - - /*-----------------------------------------------------------------*/ - case OP_EOD: - if (ptr >= end_subject) - { - if ((md->moptions & PCRE_PARTIAL_HARD) != 0) - could_continue = TRUE; - else { ADD_ACTIVE(state_offset + 1, 0); } - } - break; - - /*-----------------------------------------------------------------*/ - case OP_SOD: - if (ptr == start_subject) { ADD_ACTIVE(state_offset + 1, 0); } - break; - - /*-----------------------------------------------------------------*/ - case OP_SOM: - if (ptr == start_subject + start_offset) { ADD_ACTIVE(state_offset + 1, 0); } - break; - - -/* ========================================================================== */ - /* These opcodes inspect the next subject character, and sometimes - the previous one as well, but do not have an argument. The variable - clen contains the length of the current character and is zero if we are - at the end of the subject. */ - - /*-----------------------------------------------------------------*/ - case OP_ANY: - if (clen > 0 && !IS_NEWLINE(ptr)) - { - if (ptr + 1 >= md->end_subject && - (md->moptions & (PCRE_PARTIAL_HARD)) != 0 && - NLBLOCK->nltype == NLTYPE_FIXED && - NLBLOCK->nllen == 2 && - c == NLBLOCK->nl[0]) - { - could_continue = partial_newline = TRUE; - } - else - { - ADD_NEW(state_offset + 1, 0); - } - } - break; - - /*-----------------------------------------------------------------*/ - case OP_ALLANY: - if (clen > 0) - { ADD_NEW(state_offset + 1, 0); } - break; - - /*-----------------------------------------------------------------*/ - case OP_EODN: - if (clen == 0 && (md->moptions & PCRE_PARTIAL_HARD) != 0) - could_continue = TRUE; - else if (clen == 0 || (IS_NEWLINE(ptr) && ptr == end_subject - md->nllen)) - { ADD_ACTIVE(state_offset + 1, 0); } - break; - - /*-----------------------------------------------------------------*/ - case OP_DOLL: - if ((md->moptions & PCRE_NOTEOL) == 0) - { - if (clen == 0 && (md->moptions & PCRE_PARTIAL_HARD) != 0) - could_continue = TRUE; - else if (clen == 0 || - ((md->poptions & PCRE_DOLLAR_ENDONLY) == 0 && IS_NEWLINE(ptr) && - (ptr == end_subject - md->nllen) - )) - { ADD_ACTIVE(state_offset + 1, 0); } - else if (ptr + 1 >= md->end_subject && - (md->moptions & (PCRE_PARTIAL_HARD|PCRE_PARTIAL_SOFT)) != 0 && - NLBLOCK->nltype == NLTYPE_FIXED && - NLBLOCK->nllen == 2 && - c == NLBLOCK->nl[0]) - { - if ((md->moptions & PCRE_PARTIAL_HARD) != 0) - { - reset_could_continue = TRUE; - ADD_NEW_DATA(-(state_offset + 1), 0, 1); - } - else could_continue = partial_newline = TRUE; - } - } - break; - - /*-----------------------------------------------------------------*/ - case OP_DOLLM: - if ((md->moptions & PCRE_NOTEOL) == 0) - { - if (clen == 0 && (md->moptions & PCRE_PARTIAL_HARD) != 0) - could_continue = TRUE; - else if (clen == 0 || - ((md->poptions & PCRE_DOLLAR_ENDONLY) == 0 && IS_NEWLINE(ptr))) - { ADD_ACTIVE(state_offset + 1, 0); } - else if (ptr + 1 >= md->end_subject && - (md->moptions & (PCRE_PARTIAL_HARD|PCRE_PARTIAL_SOFT)) != 0 && - NLBLOCK->nltype == NLTYPE_FIXED && - NLBLOCK->nllen == 2 && - c == NLBLOCK->nl[0]) - { - if ((md->moptions & PCRE_PARTIAL_HARD) != 0) - { - reset_could_continue = TRUE; - ADD_NEW_DATA(-(state_offset + 1), 0, 1); - } - else could_continue = partial_newline = TRUE; - } - } - else if (IS_NEWLINE(ptr)) - { ADD_ACTIVE(state_offset + 1, 0); } - break; - - /*-----------------------------------------------------------------*/ - - case OP_DIGIT: - case OP_WHITESPACE: - case OP_WORDCHAR: - if (clen > 0 && c < 256 && - ((ctypes[c] & toptable1[codevalue]) ^ toptable2[codevalue]) != 0) - { ADD_NEW(state_offset + 1, 0); } - break; - - /*-----------------------------------------------------------------*/ - case OP_NOT_DIGIT: - case OP_NOT_WHITESPACE: - case OP_NOT_WORDCHAR: - if (clen > 0 && (c >= 256 || - ((ctypes[c] & toptable1[codevalue]) ^ toptable2[codevalue]) != 0)) - { ADD_NEW(state_offset + 1, 0); } - break; - - /*-----------------------------------------------------------------*/ - case OP_WORD_BOUNDARY: - case OP_NOT_WORD_BOUNDARY: - { - int left_word, right_word; - - if (ptr > start_subject) - { - const pcre_uchar *temp = ptr - 1; - if (temp < md->start_used_ptr) md->start_used_ptr = temp; -#if defined SUPPORT_UTF && !defined COMPILE_PCRE32 - if (utf) { BACKCHAR(temp); } -#endif - GETCHARTEST(d, temp); -#ifdef SUPPORT_UCP - if ((md->poptions & PCRE_UCP) != 0) - { - if (d == '_') left_word = TRUE; else - { - int cat = UCD_CATEGORY(d); - left_word = (cat == ucp_L || cat == ucp_N); - } - } - else -#endif - left_word = d < 256 && (ctypes[d] & ctype_word) != 0; - } - else left_word = FALSE; - - if (clen > 0) - { -#ifdef SUPPORT_UCP - if ((md->poptions & PCRE_UCP) != 0) - { - if (c == '_') right_word = TRUE; else - { - int cat = UCD_CATEGORY(c); - right_word = (cat == ucp_L || cat == ucp_N); - } - } - else -#endif - right_word = c < 256 && (ctypes[c] & ctype_word) != 0; - } - else right_word = FALSE; - - if ((left_word == right_word) == (codevalue == OP_NOT_WORD_BOUNDARY)) - { ADD_ACTIVE(state_offset + 1, 0); } - } - break; - - - /*-----------------------------------------------------------------*/ - /* Check the next character by Unicode property. We will get here only - if the support is in the binary; otherwise a compile-time error occurs. - */ - -#ifdef SUPPORT_UCP - case OP_PROP: - case OP_NOTPROP: - if (clen > 0) - { - BOOL OK; - const pcre_uint32 *cp; - const ucd_record * prop = GET_UCD(c); - switch(code[1]) - { - case PT_ANY: - OK = TRUE; - break; - - case PT_LAMP: - OK = prop->chartype == ucp_Lu || prop->chartype == ucp_Ll || - prop->chartype == ucp_Lt; - break; - - case PT_GC: - OK = PRIV(ucp_gentype)[prop->chartype] == code[2]; - break; - - case PT_PC: - OK = prop->chartype == code[2]; - break; - - case PT_SC: - OK = prop->script == code[2]; - break; - - /* These are specials for combination cases. */ - - case PT_ALNUM: - OK = PRIV(ucp_gentype)[prop->chartype] == ucp_L || - PRIV(ucp_gentype)[prop->chartype] == ucp_N; - break; - - /* Perl space used to exclude VT, but from Perl 5.18 it is included, - which means that Perl space and POSIX space are now identical. PCRE - was changed at release 8.34. */ - - case PT_SPACE: /* Perl space */ - case PT_PXSPACE: /* POSIX space */ - switch(c) - { - HSPACE_CASES: - VSPACE_CASES: - OK = TRUE; - break; - - default: - OK = PRIV(ucp_gentype)[prop->chartype] == ucp_Z; - break; - } - break; - - case PT_WORD: - OK = PRIV(ucp_gentype)[prop->chartype] == ucp_L || - PRIV(ucp_gentype)[prop->chartype] == ucp_N || - c == CHAR_UNDERSCORE; - break; - - case PT_CLIST: - cp = PRIV(ucd_caseless_sets) + code[2]; - for (;;) - { - if (c < *cp) { OK = FALSE; break; } - if (c == *cp++) { OK = TRUE; break; } - } - break; - - case PT_UCNC: - OK = c == CHAR_DOLLAR_SIGN || c == CHAR_COMMERCIAL_AT || - c == CHAR_GRAVE_ACCENT || (c >= 0xa0 && c <= 0xd7ff) || - c >= 0xe000; - break; - - /* Should never occur, but keep compilers from grumbling. */ - - default: - OK = codevalue != OP_PROP; - break; - } - - if (OK == (codevalue == OP_PROP)) { ADD_NEW(state_offset + 3, 0); } - } - break; -#endif - - - -/* ========================================================================== */ - /* These opcodes likewise inspect the subject character, but have an - argument that is not a data character. It is one of these opcodes: - OP_ANY, OP_ALLANY, OP_DIGIT, OP_NOT_DIGIT, OP_WHITESPACE, OP_NOT_SPACE, - OP_WORDCHAR, OP_NOT_WORDCHAR. The value is loaded into d. */ - - case OP_TYPEPLUS: - case OP_TYPEMINPLUS: - case OP_TYPEPOSPLUS: - count = current_state->count; /* Already matched */ - if (count > 0) { ADD_ACTIVE(state_offset + 2, 0); } - if (clen > 0) - { - if (d == OP_ANY && ptr + 1 >= md->end_subject && - (md->moptions & (PCRE_PARTIAL_HARD)) != 0 && - NLBLOCK->nltype == NLTYPE_FIXED && - NLBLOCK->nllen == 2 && - c == NLBLOCK->nl[0]) - { - could_continue = partial_newline = TRUE; - } - else if ((c >= 256 && d != OP_DIGIT && d != OP_WHITESPACE && d != OP_WORDCHAR) || - (c < 256 && - (d != OP_ANY || !IS_NEWLINE(ptr)) && - ((ctypes[c] & toptable1[d]) ^ toptable2[d]) != 0)) - { - if (count > 0 && codevalue == OP_TYPEPOSPLUS) - { - active_count--; /* Remove non-match possibility */ - next_active_state--; - } - count++; - ADD_NEW(state_offset, count); - } - } - break; - - /*-----------------------------------------------------------------*/ - case OP_TYPEQUERY: - case OP_TYPEMINQUERY: - case OP_TYPEPOSQUERY: - ADD_ACTIVE(state_offset + 2, 0); - if (clen > 0) - { - if (d == OP_ANY && ptr + 1 >= md->end_subject && - (md->moptions & (PCRE_PARTIAL_HARD)) != 0 && - NLBLOCK->nltype == NLTYPE_FIXED && - NLBLOCK->nllen == 2 && - c == NLBLOCK->nl[0]) - { - could_continue = partial_newline = TRUE; - } - else if ((c >= 256 && d != OP_DIGIT && d != OP_WHITESPACE && d != OP_WORDCHAR) || - (c < 256 && - (d != OP_ANY || !IS_NEWLINE(ptr)) && - ((ctypes[c] & toptable1[d]) ^ toptable2[d]) != 0)) - { - if (codevalue == OP_TYPEPOSQUERY) - { - active_count--; /* Remove non-match possibility */ - next_active_state--; - } - ADD_NEW(state_offset + 2, 0); - } - } - break; - - /*-----------------------------------------------------------------*/ - case OP_TYPESTAR: - case OP_TYPEMINSTAR: - case OP_TYPEPOSSTAR: - ADD_ACTIVE(state_offset + 2, 0); - if (clen > 0) - { - if (d == OP_ANY && ptr + 1 >= md->end_subject && - (md->moptions & (PCRE_PARTIAL_HARD)) != 0 && - NLBLOCK->nltype == NLTYPE_FIXED && - NLBLOCK->nllen == 2 && - c == NLBLOCK->nl[0]) - { - could_continue = partial_newline = TRUE; - } - else if ((c >= 256 && d != OP_DIGIT && d != OP_WHITESPACE && d != OP_WORDCHAR) || - (c < 256 && - (d != OP_ANY || !IS_NEWLINE(ptr)) && - ((ctypes[c] & toptable1[d]) ^ toptable2[d]) != 0)) - { - if (codevalue == OP_TYPEPOSSTAR) - { - active_count--; /* Remove non-match possibility */ - next_active_state--; - } - ADD_NEW(state_offset, 0); - } - } - break; - - /*-----------------------------------------------------------------*/ - case OP_TYPEEXACT: - count = current_state->count; /* Number already matched */ - if (clen > 0) - { - if (d == OP_ANY && ptr + 1 >= md->end_subject && - (md->moptions & (PCRE_PARTIAL_HARD)) != 0 && - NLBLOCK->nltype == NLTYPE_FIXED && - NLBLOCK->nllen == 2 && - c == NLBLOCK->nl[0]) - { - could_continue = partial_newline = TRUE; - } - else if ((c >= 256 && d != OP_DIGIT && d != OP_WHITESPACE && d != OP_WORDCHAR) || - (c < 256 && - (d != OP_ANY || !IS_NEWLINE(ptr)) && - ((ctypes[c] & toptable1[d]) ^ toptable2[d]) != 0)) - { - if (++count >= (int)GET2(code, 1)) - { ADD_NEW(state_offset + 1 + IMM2_SIZE + 1, 0); } - else - { ADD_NEW(state_offset, count); } - } - } - break; - - /*-----------------------------------------------------------------*/ - case OP_TYPEUPTO: - case OP_TYPEMINUPTO: - case OP_TYPEPOSUPTO: - ADD_ACTIVE(state_offset + 2 + IMM2_SIZE, 0); - count = current_state->count; /* Number already matched */ - if (clen > 0) - { - if (d == OP_ANY && ptr + 1 >= md->end_subject && - (md->moptions & (PCRE_PARTIAL_HARD)) != 0 && - NLBLOCK->nltype == NLTYPE_FIXED && - NLBLOCK->nllen == 2 && - c == NLBLOCK->nl[0]) - { - could_continue = partial_newline = TRUE; - } - else if ((c >= 256 && d != OP_DIGIT && d != OP_WHITESPACE && d != OP_WORDCHAR) || - (c < 256 && - (d != OP_ANY || !IS_NEWLINE(ptr)) && - ((ctypes[c] & toptable1[d]) ^ toptable2[d]) != 0)) - { - if (codevalue == OP_TYPEPOSUPTO) - { - active_count--; /* Remove non-match possibility */ - next_active_state--; - } - if (++count >= (int)GET2(code, 1)) - { ADD_NEW(state_offset + 2 + IMM2_SIZE, 0); } - else - { ADD_NEW(state_offset, count); } - } - } - break; - -/* ========================================================================== */ - /* These are virtual opcodes that are used when something like - OP_TYPEPLUS has OP_PROP, OP_NOTPROP, OP_ANYNL, or OP_EXTUNI as its - argument. It keeps the code above fast for the other cases. The argument - is in the d variable. */ - -#ifdef SUPPORT_UCP - case OP_PROP_EXTRA + OP_TYPEPLUS: - case OP_PROP_EXTRA + OP_TYPEMINPLUS: - case OP_PROP_EXTRA + OP_TYPEPOSPLUS: - count = current_state->count; /* Already matched */ - if (count > 0) { ADD_ACTIVE(state_offset + 4, 0); } - if (clen > 0) - { - BOOL OK; - const pcre_uint32 *cp; - const ucd_record * prop = GET_UCD(c); - switch(code[2]) - { - case PT_ANY: - OK = TRUE; - break; - - case PT_LAMP: - OK = prop->chartype == ucp_Lu || prop->chartype == ucp_Ll || - prop->chartype == ucp_Lt; - break; - - case PT_GC: - OK = PRIV(ucp_gentype)[prop->chartype] == code[3]; - break; - - case PT_PC: - OK = prop->chartype == code[3]; - break; - - case PT_SC: - OK = prop->script == code[3]; - break; - - /* These are specials for combination cases. */ - - case PT_ALNUM: - OK = PRIV(ucp_gentype)[prop->chartype] == ucp_L || - PRIV(ucp_gentype)[prop->chartype] == ucp_N; - break; - - /* Perl space used to exclude VT, but from Perl 5.18 it is included, - which means that Perl space and POSIX space are now identical. PCRE - was changed at release 8.34. */ - - case PT_SPACE: /* Perl space */ - case PT_PXSPACE: /* POSIX space */ - switch(c) - { - HSPACE_CASES: - VSPACE_CASES: - OK = TRUE; - break; - - default: - OK = PRIV(ucp_gentype)[prop->chartype] == ucp_Z; - break; - } - break; - - case PT_WORD: - OK = PRIV(ucp_gentype)[prop->chartype] == ucp_L || - PRIV(ucp_gentype)[prop->chartype] == ucp_N || - c == CHAR_UNDERSCORE; - break; - - case PT_CLIST: - cp = PRIV(ucd_caseless_sets) + code[3]; - for (;;) - { - if (c < *cp) { OK = FALSE; break; } - if (c == *cp++) { OK = TRUE; break; } - } - break; - - case PT_UCNC: - OK = c == CHAR_DOLLAR_SIGN || c == CHAR_COMMERCIAL_AT || - c == CHAR_GRAVE_ACCENT || (c >= 0xa0 && c <= 0xd7ff) || - c >= 0xe000; - break; - - /* Should never occur, but keep compilers from grumbling. */ - - default: - OK = codevalue != OP_PROP; - break; - } - - if (OK == (d == OP_PROP)) - { - if (count > 0 && codevalue == OP_PROP_EXTRA + OP_TYPEPOSPLUS) - { - active_count--; /* Remove non-match possibility */ - next_active_state--; - } - count++; - ADD_NEW(state_offset, count); - } - } - break; - - /*-----------------------------------------------------------------*/ - case OP_EXTUNI_EXTRA + OP_TYPEPLUS: - case OP_EXTUNI_EXTRA + OP_TYPEMINPLUS: - case OP_EXTUNI_EXTRA + OP_TYPEPOSPLUS: - count = current_state->count; /* Already matched */ - if (count > 0) { ADD_ACTIVE(state_offset + 2, 0); } - if (clen > 0) - { - int lgb, rgb; - const pcre_uchar *nptr = ptr + clen; - int ncount = 0; - if (count > 0 && codevalue == OP_EXTUNI_EXTRA + OP_TYPEPOSPLUS) - { - active_count--; /* Remove non-match possibility */ - next_active_state--; - } - lgb = UCD_GRAPHBREAK(c); - while (nptr < end_subject) - { - dlen = 1; - if (!utf) d = *nptr; else { GETCHARLEN(d, nptr, dlen); } - rgb = UCD_GRAPHBREAK(d); - if ((PRIV(ucp_gbtable)[lgb] & (1 << rgb)) == 0) break; - ncount++; - lgb = rgb; - nptr += dlen; - } - count++; - ADD_NEW_DATA(-state_offset, count, ncount); - } - break; -#endif - - /*-----------------------------------------------------------------*/ - case OP_ANYNL_EXTRA + OP_TYPEPLUS: - case OP_ANYNL_EXTRA + OP_TYPEMINPLUS: - case OP_ANYNL_EXTRA + OP_TYPEPOSPLUS: - count = current_state->count; /* Already matched */ - if (count > 0) { ADD_ACTIVE(state_offset + 2, 0); } - if (clen > 0) - { - int ncount = 0; - switch (c) - { - case CHAR_VT: - case CHAR_FF: - case CHAR_NEL: -#ifndef EBCDIC - case 0x2028: - case 0x2029: -#endif /* Not EBCDIC */ - if ((md->moptions & PCRE_BSR_ANYCRLF) != 0) break; - goto ANYNL01; - - case CHAR_CR: - if (ptr + 1 < end_subject && UCHAR21TEST(ptr + 1) == CHAR_LF) ncount = 1; - /* Fall through */ - - ANYNL01: - case CHAR_LF: - if (count > 0 && codevalue == OP_ANYNL_EXTRA + OP_TYPEPOSPLUS) - { - active_count--; /* Remove non-match possibility */ - next_active_state--; - } - count++; - ADD_NEW_DATA(-state_offset, count, ncount); - break; - - default: - break; - } - } - break; - - /*-----------------------------------------------------------------*/ - case OP_VSPACE_EXTRA + OP_TYPEPLUS: - case OP_VSPACE_EXTRA + OP_TYPEMINPLUS: - case OP_VSPACE_EXTRA + OP_TYPEPOSPLUS: - count = current_state->count; /* Already matched */ - if (count > 0) { ADD_ACTIVE(state_offset + 2, 0); } - if (clen > 0) - { - BOOL OK; - switch (c) - { - VSPACE_CASES: - OK = TRUE; - break; - - default: - OK = FALSE; - break; - } - - if (OK == (d == OP_VSPACE)) - { - if (count > 0 && codevalue == OP_VSPACE_EXTRA + OP_TYPEPOSPLUS) - { - active_count--; /* Remove non-match possibility */ - next_active_state--; - } - count++; - ADD_NEW_DATA(-state_offset, count, 0); - } - } - break; - - /*-----------------------------------------------------------------*/ - case OP_HSPACE_EXTRA + OP_TYPEPLUS: - case OP_HSPACE_EXTRA + OP_TYPEMINPLUS: - case OP_HSPACE_EXTRA + OP_TYPEPOSPLUS: - count = current_state->count; /* Already matched */ - if (count > 0) { ADD_ACTIVE(state_offset + 2, 0); } - if (clen > 0) - { - BOOL OK; - switch (c) - { - HSPACE_CASES: - OK = TRUE; - break; - - default: - OK = FALSE; - break; - } - - if (OK == (d == OP_HSPACE)) - { - if (count > 0 && codevalue == OP_HSPACE_EXTRA + OP_TYPEPOSPLUS) - { - active_count--; /* Remove non-match possibility */ - next_active_state--; - } - count++; - ADD_NEW_DATA(-state_offset, count, 0); - } - } - break; - - /*-----------------------------------------------------------------*/ -#ifdef SUPPORT_UCP - case OP_PROP_EXTRA + OP_TYPEQUERY: - case OP_PROP_EXTRA + OP_TYPEMINQUERY: - case OP_PROP_EXTRA + OP_TYPEPOSQUERY: - count = 4; - goto QS1; - - case OP_PROP_EXTRA + OP_TYPESTAR: - case OP_PROP_EXTRA + OP_TYPEMINSTAR: - case OP_PROP_EXTRA + OP_TYPEPOSSTAR: - count = 0; - - QS1: - - ADD_ACTIVE(state_offset + 4, 0); - if (clen > 0) - { - BOOL OK; - const pcre_uint32 *cp; - const ucd_record * prop = GET_UCD(c); - switch(code[2]) - { - case PT_ANY: - OK = TRUE; - break; - - case PT_LAMP: - OK = prop->chartype == ucp_Lu || prop->chartype == ucp_Ll || - prop->chartype == ucp_Lt; - break; - - case PT_GC: - OK = PRIV(ucp_gentype)[prop->chartype] == code[3]; - break; - - case PT_PC: - OK = prop->chartype == code[3]; - break; - - case PT_SC: - OK = prop->script == code[3]; - break; - - /* These are specials for combination cases. */ - - case PT_ALNUM: - OK = PRIV(ucp_gentype)[prop->chartype] == ucp_L || - PRIV(ucp_gentype)[prop->chartype] == ucp_N; - break; - - /* Perl space used to exclude VT, but from Perl 5.18 it is included, - which means that Perl space and POSIX space are now identical. PCRE - was changed at release 8.34. */ - - case PT_SPACE: /* Perl space */ - case PT_PXSPACE: /* POSIX space */ - switch(c) - { - HSPACE_CASES: - VSPACE_CASES: - OK = TRUE; - break; - - default: - OK = PRIV(ucp_gentype)[prop->chartype] == ucp_Z; - break; - } - break; - - case PT_WORD: - OK = PRIV(ucp_gentype)[prop->chartype] == ucp_L || - PRIV(ucp_gentype)[prop->chartype] == ucp_N || - c == CHAR_UNDERSCORE; - break; - - case PT_CLIST: - cp = PRIV(ucd_caseless_sets) + code[3]; - for (;;) - { - if (c < *cp) { OK = FALSE; break; } - if (c == *cp++) { OK = TRUE; break; } - } - break; - - case PT_UCNC: - OK = c == CHAR_DOLLAR_SIGN || c == CHAR_COMMERCIAL_AT || - c == CHAR_GRAVE_ACCENT || (c >= 0xa0 && c <= 0xd7ff) || - c >= 0xe000; - break; - - /* Should never occur, but keep compilers from grumbling. */ - - default: - OK = codevalue != OP_PROP; - break; - } - - if (OK == (d == OP_PROP)) - { - if (codevalue == OP_PROP_EXTRA + OP_TYPEPOSSTAR || - codevalue == OP_PROP_EXTRA + OP_TYPEPOSQUERY) - { - active_count--; /* Remove non-match possibility */ - next_active_state--; - } - ADD_NEW(state_offset + count, 0); - } - } - break; - - /*-----------------------------------------------------------------*/ - case OP_EXTUNI_EXTRA + OP_TYPEQUERY: - case OP_EXTUNI_EXTRA + OP_TYPEMINQUERY: - case OP_EXTUNI_EXTRA + OP_TYPEPOSQUERY: - count = 2; - goto QS2; - - case OP_EXTUNI_EXTRA + OP_TYPESTAR: - case OP_EXTUNI_EXTRA + OP_TYPEMINSTAR: - case OP_EXTUNI_EXTRA + OP_TYPEPOSSTAR: - count = 0; - - QS2: - - ADD_ACTIVE(state_offset + 2, 0); - if (clen > 0) - { - int lgb, rgb; - const pcre_uchar *nptr = ptr + clen; - int ncount = 0; - if (codevalue == OP_EXTUNI_EXTRA + OP_TYPEPOSSTAR || - codevalue == OP_EXTUNI_EXTRA + OP_TYPEPOSQUERY) - { - active_count--; /* Remove non-match possibility */ - next_active_state--; - } - lgb = UCD_GRAPHBREAK(c); - while (nptr < end_subject) - { - dlen = 1; - if (!utf) d = *nptr; else { GETCHARLEN(d, nptr, dlen); } - rgb = UCD_GRAPHBREAK(d); - if ((PRIV(ucp_gbtable)[lgb] & (1 << rgb)) == 0) break; - ncount++; - lgb = rgb; - nptr += dlen; - } - ADD_NEW_DATA(-(state_offset + count), 0, ncount); - } - break; -#endif - - /*-----------------------------------------------------------------*/ - case OP_ANYNL_EXTRA + OP_TYPEQUERY: - case OP_ANYNL_EXTRA + OP_TYPEMINQUERY: - case OP_ANYNL_EXTRA + OP_TYPEPOSQUERY: - count = 2; - goto QS3; - - case OP_ANYNL_EXTRA + OP_TYPESTAR: - case OP_ANYNL_EXTRA + OP_TYPEMINSTAR: - case OP_ANYNL_EXTRA + OP_TYPEPOSSTAR: - count = 0; - - QS3: - ADD_ACTIVE(state_offset + 2, 0); - if (clen > 0) - { - int ncount = 0; - switch (c) - { - case CHAR_VT: - case CHAR_FF: - case CHAR_NEL: -#ifndef EBCDIC - case 0x2028: - case 0x2029: -#endif /* Not EBCDIC */ - if ((md->moptions & PCRE_BSR_ANYCRLF) != 0) break; - goto ANYNL02; - - case CHAR_CR: - if (ptr + 1 < end_subject && UCHAR21TEST(ptr + 1) == CHAR_LF) ncount = 1; - /* Fall through */ - - ANYNL02: - case CHAR_LF: - if (codevalue == OP_ANYNL_EXTRA + OP_TYPEPOSSTAR || - codevalue == OP_ANYNL_EXTRA + OP_TYPEPOSQUERY) - { - active_count--; /* Remove non-match possibility */ - next_active_state--; - } - ADD_NEW_DATA(-(state_offset + (int)count), 0, ncount); - break; - - default: - break; - } - } - break; - - /*-----------------------------------------------------------------*/ - case OP_VSPACE_EXTRA + OP_TYPEQUERY: - case OP_VSPACE_EXTRA + OP_TYPEMINQUERY: - case OP_VSPACE_EXTRA + OP_TYPEPOSQUERY: - count = 2; - goto QS4; - - case OP_VSPACE_EXTRA + OP_TYPESTAR: - case OP_VSPACE_EXTRA + OP_TYPEMINSTAR: - case OP_VSPACE_EXTRA + OP_TYPEPOSSTAR: - count = 0; - - QS4: - ADD_ACTIVE(state_offset + 2, 0); - if (clen > 0) - { - BOOL OK; - switch (c) - { - VSPACE_CASES: - OK = TRUE; - break; - - default: - OK = FALSE; - break; - } - if (OK == (d == OP_VSPACE)) - { - if (codevalue == OP_VSPACE_EXTRA + OP_TYPEPOSSTAR || - codevalue == OP_VSPACE_EXTRA + OP_TYPEPOSQUERY) - { - active_count--; /* Remove non-match possibility */ - next_active_state--; - } - ADD_NEW_DATA(-(state_offset + (int)count), 0, 0); - } - } - break; - - /*-----------------------------------------------------------------*/ - case OP_HSPACE_EXTRA + OP_TYPEQUERY: - case OP_HSPACE_EXTRA + OP_TYPEMINQUERY: - case OP_HSPACE_EXTRA + OP_TYPEPOSQUERY: - count = 2; - goto QS5; - - case OP_HSPACE_EXTRA + OP_TYPESTAR: - case OP_HSPACE_EXTRA + OP_TYPEMINSTAR: - case OP_HSPACE_EXTRA + OP_TYPEPOSSTAR: - count = 0; - - QS5: - ADD_ACTIVE(state_offset + 2, 0); - if (clen > 0) - { - BOOL OK; - switch (c) - { - HSPACE_CASES: - OK = TRUE; - break; - - default: - OK = FALSE; - break; - } - - if (OK == (d == OP_HSPACE)) - { - if (codevalue == OP_HSPACE_EXTRA + OP_TYPEPOSSTAR || - codevalue == OP_HSPACE_EXTRA + OP_TYPEPOSQUERY) - { - active_count--; /* Remove non-match possibility */ - next_active_state--; - } - ADD_NEW_DATA(-(state_offset + (int)count), 0, 0); - } - } - break; - - /*-----------------------------------------------------------------*/ -#ifdef SUPPORT_UCP - case OP_PROP_EXTRA + OP_TYPEEXACT: - case OP_PROP_EXTRA + OP_TYPEUPTO: - case OP_PROP_EXTRA + OP_TYPEMINUPTO: - case OP_PROP_EXTRA + OP_TYPEPOSUPTO: - if (codevalue != OP_PROP_EXTRA + OP_TYPEEXACT) - { ADD_ACTIVE(state_offset + 1 + IMM2_SIZE + 3, 0); } - count = current_state->count; /* Number already matched */ - if (clen > 0) - { - BOOL OK; - const pcre_uint32 *cp; - const ucd_record * prop = GET_UCD(c); - switch(code[1 + IMM2_SIZE + 1]) - { - case PT_ANY: - OK = TRUE; - break; - - case PT_LAMP: - OK = prop->chartype == ucp_Lu || prop->chartype == ucp_Ll || - prop->chartype == ucp_Lt; - break; - - case PT_GC: - OK = PRIV(ucp_gentype)[prop->chartype] == code[1 + IMM2_SIZE + 2]; - break; - - case PT_PC: - OK = prop->chartype == code[1 + IMM2_SIZE + 2]; - break; - - case PT_SC: - OK = prop->script == code[1 + IMM2_SIZE + 2]; - break; - - /* These are specials for combination cases. */ - - case PT_ALNUM: - OK = PRIV(ucp_gentype)[prop->chartype] == ucp_L || - PRIV(ucp_gentype)[prop->chartype] == ucp_N; - break; - - /* Perl space used to exclude VT, but from Perl 5.18 it is included, - which means that Perl space and POSIX space are now identical. PCRE - was changed at release 8.34. */ - - case PT_SPACE: /* Perl space */ - case PT_PXSPACE: /* POSIX space */ - switch(c) - { - HSPACE_CASES: - VSPACE_CASES: - OK = TRUE; - break; - - default: - OK = PRIV(ucp_gentype)[prop->chartype] == ucp_Z; - break; - } - break; - - case PT_WORD: - OK = PRIV(ucp_gentype)[prop->chartype] == ucp_L || - PRIV(ucp_gentype)[prop->chartype] == ucp_N || - c == CHAR_UNDERSCORE; - break; - - case PT_CLIST: - cp = PRIV(ucd_caseless_sets) + code[1 + IMM2_SIZE + 2]; - for (;;) - { - if (c < *cp) { OK = FALSE; break; } - if (c == *cp++) { OK = TRUE; break; } - } - break; - - case PT_UCNC: - OK = c == CHAR_DOLLAR_SIGN || c == CHAR_COMMERCIAL_AT || - c == CHAR_GRAVE_ACCENT || (c >= 0xa0 && c <= 0xd7ff) || - c >= 0xe000; - break; - - /* Should never occur, but keep compilers from grumbling. */ - - default: - OK = codevalue != OP_PROP; - break; - } - - if (OK == (d == OP_PROP)) - { - if (codevalue == OP_PROP_EXTRA + OP_TYPEPOSUPTO) - { - active_count--; /* Remove non-match possibility */ - next_active_state--; - } - if (++count >= (int)GET2(code, 1)) - { ADD_NEW(state_offset + 1 + IMM2_SIZE + 3, 0); } - else - { ADD_NEW(state_offset, count); } - } - } - break; - - /*-----------------------------------------------------------------*/ - case OP_EXTUNI_EXTRA + OP_TYPEEXACT: - case OP_EXTUNI_EXTRA + OP_TYPEUPTO: - case OP_EXTUNI_EXTRA + OP_TYPEMINUPTO: - case OP_EXTUNI_EXTRA + OP_TYPEPOSUPTO: - if (codevalue != OP_EXTUNI_EXTRA + OP_TYPEEXACT) - { ADD_ACTIVE(state_offset + 2 + IMM2_SIZE, 0); } - count = current_state->count; /* Number already matched */ - if (clen > 0) - { - int lgb, rgb; - const pcre_uchar *nptr = ptr + clen; - int ncount = 0; - if (codevalue == OP_EXTUNI_EXTRA + OP_TYPEPOSUPTO) - { - active_count--; /* Remove non-match possibility */ - next_active_state--; - } - lgb = UCD_GRAPHBREAK(c); - while (nptr < end_subject) - { - dlen = 1; - if (!utf) d = *nptr; else { GETCHARLEN(d, nptr, dlen); } - rgb = UCD_GRAPHBREAK(d); - if ((PRIV(ucp_gbtable)[lgb] & (1 << rgb)) == 0) break; - ncount++; - lgb = rgb; - nptr += dlen; - } - if (nptr >= end_subject && (md->moptions & PCRE_PARTIAL_HARD) != 0) - reset_could_continue = TRUE; - if (++count >= (int)GET2(code, 1)) - { ADD_NEW_DATA(-(state_offset + 2 + IMM2_SIZE), 0, ncount); } - else - { ADD_NEW_DATA(-state_offset, count, ncount); } - } - break; -#endif - - /*-----------------------------------------------------------------*/ - case OP_ANYNL_EXTRA + OP_TYPEEXACT: - case OP_ANYNL_EXTRA + OP_TYPEUPTO: - case OP_ANYNL_EXTRA + OP_TYPEMINUPTO: - case OP_ANYNL_EXTRA + OP_TYPEPOSUPTO: - if (codevalue != OP_ANYNL_EXTRA + OP_TYPEEXACT) - { ADD_ACTIVE(state_offset + 2 + IMM2_SIZE, 0); } - count = current_state->count; /* Number already matched */ - if (clen > 0) - { - int ncount = 0; - switch (c) - { - case CHAR_VT: - case CHAR_FF: - case CHAR_NEL: -#ifndef EBCDIC - case 0x2028: - case 0x2029: -#endif /* Not EBCDIC */ - if ((md->moptions & PCRE_BSR_ANYCRLF) != 0) break; - goto ANYNL03; - - case CHAR_CR: - if (ptr + 1 < end_subject && UCHAR21TEST(ptr + 1) == CHAR_LF) ncount = 1; - /* Fall through */ - - ANYNL03: - case CHAR_LF: - if (codevalue == OP_ANYNL_EXTRA + OP_TYPEPOSUPTO) - { - active_count--; /* Remove non-match possibility */ - next_active_state--; - } - if (++count >= (int)GET2(code, 1)) - { ADD_NEW_DATA(-(state_offset + 2 + IMM2_SIZE), 0, ncount); } - else - { ADD_NEW_DATA(-state_offset, count, ncount); } - break; - - default: - break; - } - } - break; - - /*-----------------------------------------------------------------*/ - case OP_VSPACE_EXTRA + OP_TYPEEXACT: - case OP_VSPACE_EXTRA + OP_TYPEUPTO: - case OP_VSPACE_EXTRA + OP_TYPEMINUPTO: - case OP_VSPACE_EXTRA + OP_TYPEPOSUPTO: - if (codevalue != OP_VSPACE_EXTRA + OP_TYPEEXACT) - { ADD_ACTIVE(state_offset + 2 + IMM2_SIZE, 0); } - count = current_state->count; /* Number already matched */ - if (clen > 0) - { - BOOL OK; - switch (c) - { - VSPACE_CASES: - OK = TRUE; - break; - - default: - OK = FALSE; - } - - if (OK == (d == OP_VSPACE)) - { - if (codevalue == OP_VSPACE_EXTRA + OP_TYPEPOSUPTO) - { - active_count--; /* Remove non-match possibility */ - next_active_state--; - } - if (++count >= (int)GET2(code, 1)) - { ADD_NEW_DATA(-(state_offset + 2 + IMM2_SIZE), 0, 0); } - else - { ADD_NEW_DATA(-state_offset, count, 0); } - } - } - break; - - /*-----------------------------------------------------------------*/ - case OP_HSPACE_EXTRA + OP_TYPEEXACT: - case OP_HSPACE_EXTRA + OP_TYPEUPTO: - case OP_HSPACE_EXTRA + OP_TYPEMINUPTO: - case OP_HSPACE_EXTRA + OP_TYPEPOSUPTO: - if (codevalue != OP_HSPACE_EXTRA + OP_TYPEEXACT) - { ADD_ACTIVE(state_offset + 2 + IMM2_SIZE, 0); } - count = current_state->count; /* Number already matched */ - if (clen > 0) - { - BOOL OK; - switch (c) - { - HSPACE_CASES: - OK = TRUE; - break; - - default: - OK = FALSE; - break; - } - - if (OK == (d == OP_HSPACE)) - { - if (codevalue == OP_HSPACE_EXTRA + OP_TYPEPOSUPTO) - { - active_count--; /* Remove non-match possibility */ - next_active_state--; - } - if (++count >= (int)GET2(code, 1)) - { ADD_NEW_DATA(-(state_offset + 2 + IMM2_SIZE), 0, 0); } - else - { ADD_NEW_DATA(-state_offset, count, 0); } - } - } - break; - -/* ========================================================================== */ - /* These opcodes are followed by a character that is usually compared - to the current subject character; it is loaded into d. We still get - here even if there is no subject character, because in some cases zero - repetitions are permitted. */ - - /*-----------------------------------------------------------------*/ - case OP_CHAR: - if (clen > 0 && c == d) { ADD_NEW(state_offset + dlen + 1, 0); } - break; - - /*-----------------------------------------------------------------*/ - case OP_CHARI: - if (clen == 0) break; - -#ifdef SUPPORT_UTF - if (utf) - { - if (c == d) { ADD_NEW(state_offset + dlen + 1, 0); } else - { - unsigned int othercase; - if (c < 128) - othercase = fcc[c]; - else - /* If we have Unicode property support, we can use it to test the - other case of the character. */ -#ifdef SUPPORT_UCP - othercase = UCD_OTHERCASE(c); -#else - othercase = NOTACHAR; -#endif - - if (d == othercase) { ADD_NEW(state_offset + dlen + 1, 0); } - } - } - else -#endif /* SUPPORT_UTF */ - /* Not UTF mode */ - { - if (TABLE_GET(c, lcc, c) == TABLE_GET(d, lcc, d)) - { ADD_NEW(state_offset + 2, 0); } - } - break; - - -#ifdef SUPPORT_UCP - /*-----------------------------------------------------------------*/ - /* This is a tricky one because it can match more than one character. - Find out how many characters to skip, and then set up a negative state - to wait for them to pass before continuing. */ - - case OP_EXTUNI: - if (clen > 0) - { - int lgb, rgb; - const pcre_uchar *nptr = ptr + clen; - int ncount = 0; - lgb = UCD_GRAPHBREAK(c); - while (nptr < end_subject) - { - dlen = 1; - if (!utf) d = *nptr; else { GETCHARLEN(d, nptr, dlen); } - rgb = UCD_GRAPHBREAK(d); - if ((PRIV(ucp_gbtable)[lgb] & (1 << rgb)) == 0) break; - ncount++; - lgb = rgb; - nptr += dlen; - } - if (nptr >= end_subject && (md->moptions & PCRE_PARTIAL_HARD) != 0) - reset_could_continue = TRUE; - ADD_NEW_DATA(-(state_offset + 1), 0, ncount); - } - break; -#endif - - /*-----------------------------------------------------------------*/ - /* This is a tricky like EXTUNI because it too can match more than one - character (when CR is followed by LF). In this case, set up a negative - state to wait for one character to pass before continuing. */ - - case OP_ANYNL: - if (clen > 0) switch(c) - { - case CHAR_VT: - case CHAR_FF: - case CHAR_NEL: -#ifndef EBCDIC - case 0x2028: - case 0x2029: -#endif /* Not EBCDIC */ - if ((md->moptions & PCRE_BSR_ANYCRLF) != 0) break; - - case CHAR_LF: - ADD_NEW(state_offset + 1, 0); - break; - - case CHAR_CR: - if (ptr + 1 >= end_subject) - { - ADD_NEW(state_offset + 1, 0); - if ((md->moptions & PCRE_PARTIAL_HARD) != 0) - reset_could_continue = TRUE; - } - else if (UCHAR21TEST(ptr + 1) == CHAR_LF) - { - ADD_NEW_DATA(-(state_offset + 1), 0, 1); - } - else - { - ADD_NEW(state_offset + 1, 0); - } - break; - } - break; - - /*-----------------------------------------------------------------*/ - case OP_NOT_VSPACE: - if (clen > 0) switch(c) - { - VSPACE_CASES: - break; - - default: - ADD_NEW(state_offset + 1, 0); - break; - } - break; - - /*-----------------------------------------------------------------*/ - case OP_VSPACE: - if (clen > 0) switch(c) - { - VSPACE_CASES: - ADD_NEW(state_offset + 1, 0); - break; - - default: - break; - } - break; - - /*-----------------------------------------------------------------*/ - case OP_NOT_HSPACE: - if (clen > 0) switch(c) - { - HSPACE_CASES: - break; - - default: - ADD_NEW(state_offset + 1, 0); - break; - } - break; - - /*-----------------------------------------------------------------*/ - case OP_HSPACE: - if (clen > 0) switch(c) - { - HSPACE_CASES: - ADD_NEW(state_offset + 1, 0); - break; - - default: - break; - } - break; - - /*-----------------------------------------------------------------*/ - /* Match a negated single character casefully. */ - - case OP_NOT: - if (clen > 0 && c != d) { ADD_NEW(state_offset + dlen + 1, 0); } - break; - - /*-----------------------------------------------------------------*/ - /* Match a negated single character caselessly. */ - - case OP_NOTI: - if (clen > 0) - { - unsigned int otherd; -#ifdef SUPPORT_UTF - if (utf && d >= 128) - { -#ifdef SUPPORT_UCP - otherd = UCD_OTHERCASE(d); -#endif /* SUPPORT_UCP */ - } - else -#endif /* SUPPORT_UTF */ - otherd = TABLE_GET(d, fcc, d); - if (c != d && c != otherd) - { ADD_NEW(state_offset + dlen + 1, 0); } - } - break; - - /*-----------------------------------------------------------------*/ - case OP_PLUSI: - case OP_MINPLUSI: - case OP_POSPLUSI: - case OP_NOTPLUSI: - case OP_NOTMINPLUSI: - case OP_NOTPOSPLUSI: - caseless = TRUE; - codevalue -= OP_STARI - OP_STAR; - - /* Fall through */ - case OP_PLUS: - case OP_MINPLUS: - case OP_POSPLUS: - case OP_NOTPLUS: - case OP_NOTMINPLUS: - case OP_NOTPOSPLUS: - count = current_state->count; /* Already matched */ - if (count > 0) { ADD_ACTIVE(state_offset + dlen + 1, 0); } - if (clen > 0) - { - pcre_uint32 otherd = NOTACHAR; - if (caseless) - { -#ifdef SUPPORT_UTF - if (utf && d >= 128) - { -#ifdef SUPPORT_UCP - otherd = UCD_OTHERCASE(d); -#endif /* SUPPORT_UCP */ - } - else -#endif /* SUPPORT_UTF */ - otherd = TABLE_GET(d, fcc, d); - } - if ((c == d || c == otherd) == (codevalue < OP_NOTSTAR)) - { - if (count > 0 && - (codevalue == OP_POSPLUS || codevalue == OP_NOTPOSPLUS)) - { - active_count--; /* Remove non-match possibility */ - next_active_state--; - } - count++; - ADD_NEW(state_offset, count); - } - } - break; - - /*-----------------------------------------------------------------*/ - case OP_QUERYI: - case OP_MINQUERYI: - case OP_POSQUERYI: - case OP_NOTQUERYI: - case OP_NOTMINQUERYI: - case OP_NOTPOSQUERYI: - caseless = TRUE; - codevalue -= OP_STARI - OP_STAR; - /* Fall through */ - case OP_QUERY: - case OP_MINQUERY: - case OP_POSQUERY: - case OP_NOTQUERY: - case OP_NOTMINQUERY: - case OP_NOTPOSQUERY: - ADD_ACTIVE(state_offset + dlen + 1, 0); - if (clen > 0) - { - pcre_uint32 otherd = NOTACHAR; - if (caseless) - { -#ifdef SUPPORT_UTF - if (utf && d >= 128) - { -#ifdef SUPPORT_UCP - otherd = UCD_OTHERCASE(d); -#endif /* SUPPORT_UCP */ - } - else -#endif /* SUPPORT_UTF */ - otherd = TABLE_GET(d, fcc, d); - } - if ((c == d || c == otherd) == (codevalue < OP_NOTSTAR)) - { - if (codevalue == OP_POSQUERY || codevalue == OP_NOTPOSQUERY) - { - active_count--; /* Remove non-match possibility */ - next_active_state--; - } - ADD_NEW(state_offset + dlen + 1, 0); - } - } - break; - - /*-----------------------------------------------------------------*/ - case OP_STARI: - case OP_MINSTARI: - case OP_POSSTARI: - case OP_NOTSTARI: - case OP_NOTMINSTARI: - case OP_NOTPOSSTARI: - caseless = TRUE; - codevalue -= OP_STARI - OP_STAR; - /* Fall through */ - case OP_STAR: - case OP_MINSTAR: - case OP_POSSTAR: - case OP_NOTSTAR: - case OP_NOTMINSTAR: - case OP_NOTPOSSTAR: - ADD_ACTIVE(state_offset + dlen + 1, 0); - if (clen > 0) - { - pcre_uint32 otherd = NOTACHAR; - if (caseless) - { -#ifdef SUPPORT_UTF - if (utf && d >= 128) - { -#ifdef SUPPORT_UCP - otherd = UCD_OTHERCASE(d); -#endif /* SUPPORT_UCP */ - } - else -#endif /* SUPPORT_UTF */ - otherd = TABLE_GET(d, fcc, d); - } - if ((c == d || c == otherd) == (codevalue < OP_NOTSTAR)) - { - if (codevalue == OP_POSSTAR || codevalue == OP_NOTPOSSTAR) - { - active_count--; /* Remove non-match possibility */ - next_active_state--; - } - ADD_NEW(state_offset, 0); - } - } - break; - - /*-----------------------------------------------------------------*/ - case OP_EXACTI: - case OP_NOTEXACTI: - caseless = TRUE; - codevalue -= OP_STARI - OP_STAR; - /* Fall through */ - case OP_EXACT: - case OP_NOTEXACT: - count = current_state->count; /* Number already matched */ - if (clen > 0) - { - pcre_uint32 otherd = NOTACHAR; - if (caseless) - { -#ifdef SUPPORT_UTF - if (utf && d >= 128) - { -#ifdef SUPPORT_UCP - otherd = UCD_OTHERCASE(d); -#endif /* SUPPORT_UCP */ - } - else -#endif /* SUPPORT_UTF */ - otherd = TABLE_GET(d, fcc, d); - } - if ((c == d || c == otherd) == (codevalue < OP_NOTSTAR)) - { - if (++count >= (int)GET2(code, 1)) - { ADD_NEW(state_offset + dlen + 1 + IMM2_SIZE, 0); } - else - { ADD_NEW(state_offset, count); } - } - } - break; - - /*-----------------------------------------------------------------*/ - case OP_UPTOI: - case OP_MINUPTOI: - case OP_POSUPTOI: - case OP_NOTUPTOI: - case OP_NOTMINUPTOI: - case OP_NOTPOSUPTOI: - caseless = TRUE; - codevalue -= OP_STARI - OP_STAR; - /* Fall through */ - case OP_UPTO: - case OP_MINUPTO: - case OP_POSUPTO: - case OP_NOTUPTO: - case OP_NOTMINUPTO: - case OP_NOTPOSUPTO: - ADD_ACTIVE(state_offset + dlen + 1 + IMM2_SIZE, 0); - count = current_state->count; /* Number already matched */ - if (clen > 0) - { - pcre_uint32 otherd = NOTACHAR; - if (caseless) - { -#ifdef SUPPORT_UTF - if (utf && d >= 128) - { -#ifdef SUPPORT_UCP - otherd = UCD_OTHERCASE(d); -#endif /* SUPPORT_UCP */ - } - else -#endif /* SUPPORT_UTF */ - otherd = TABLE_GET(d, fcc, d); - } - if ((c == d || c == otherd) == (codevalue < OP_NOTSTAR)) - { - if (codevalue == OP_POSUPTO || codevalue == OP_NOTPOSUPTO) - { - active_count--; /* Remove non-match possibility */ - next_active_state--; - } - if (++count >= (int)GET2(code, 1)) - { ADD_NEW(state_offset + dlen + 1 + IMM2_SIZE, 0); } - else - { ADD_NEW(state_offset, count); } - } - } - break; - - -/* ========================================================================== */ - /* These are the class-handling opcodes */ - - case OP_CLASS: - case OP_NCLASS: - case OP_XCLASS: - { - BOOL isinclass = FALSE; - int next_state_offset; - const pcre_uchar *ecode; - - /* For a simple class, there is always just a 32-byte table, and we - can set isinclass from it. */ - - if (codevalue != OP_XCLASS) - { - ecode = code + 1 + (32 / sizeof(pcre_uchar)); - if (clen > 0) - { - isinclass = (c > 255)? (codevalue == OP_NCLASS) : - ((((pcre_uint8 *)(code + 1))[c/8] & (1 << (c&7))) != 0); - } - } - - /* An extended class may have a table or a list of single characters, - ranges, or both, and it may be positive or negative. There's a - function that sorts all this out. */ - - else - { - ecode = code + GET(code, 1); - if (clen > 0) isinclass = PRIV(xclass)(c, code + 1 + LINK_SIZE, utf); - } - - /* At this point, isinclass is set for all kinds of class, and ecode - points to the byte after the end of the class. If there is a - quantifier, this is where it will be. */ - - next_state_offset = (int)(ecode - start_code); - - switch (*ecode) - { - case OP_CRSTAR: - case OP_CRMINSTAR: - case OP_CRPOSSTAR: - ADD_ACTIVE(next_state_offset + 1, 0); - if (isinclass) - { - if (*ecode == OP_CRPOSSTAR) - { - active_count--; /* Remove non-match possibility */ - next_active_state--; - } - ADD_NEW(state_offset, 0); - } - break; - - case OP_CRPLUS: - case OP_CRMINPLUS: - case OP_CRPOSPLUS: - count = current_state->count; /* Already matched */ - if (count > 0) { ADD_ACTIVE(next_state_offset + 1, 0); } - if (isinclass) - { - if (count > 0 && *ecode == OP_CRPOSPLUS) - { - active_count--; /* Remove non-match possibility */ - next_active_state--; - } - count++; - ADD_NEW(state_offset, count); - } - break; - - case OP_CRQUERY: - case OP_CRMINQUERY: - case OP_CRPOSQUERY: - ADD_ACTIVE(next_state_offset + 1, 0); - if (isinclass) - { - if (*ecode == OP_CRPOSQUERY) - { - active_count--; /* Remove non-match possibility */ - next_active_state--; - } - ADD_NEW(next_state_offset + 1, 0); - } - break; - - case OP_CRRANGE: - case OP_CRMINRANGE: - case OP_CRPOSRANGE: - count = current_state->count; /* Already matched */ - if (count >= (int)GET2(ecode, 1)) - { ADD_ACTIVE(next_state_offset + 1 + 2 * IMM2_SIZE, 0); } - if (isinclass) - { - int max = (int)GET2(ecode, 1 + IMM2_SIZE); - if (*ecode == OP_CRPOSRANGE) - { - active_count--; /* Remove non-match possibility */ - next_active_state--; - } - if (++count >= max && max != 0) /* Max 0 => no limit */ - { ADD_NEW(next_state_offset + 1 + 2 * IMM2_SIZE, 0); } - else - { ADD_NEW(state_offset, count); } - } - break; - - default: - if (isinclass) { ADD_NEW(next_state_offset, 0); } - break; - } - } - break; - -/* ========================================================================== */ - /* These are the opcodes for fancy brackets of various kinds. We have - to use recursion in order to handle them. The "always failing" assertion - (?!) is optimised to OP_FAIL when compiling, so we have to support that, - though the other "backtracking verbs" are not supported. */ - - case OP_FAIL: - forced_fail++; /* Count FAILs for multiple states */ - break; - - case OP_ASSERT: - case OP_ASSERT_NOT: - case OP_ASSERTBACK: - case OP_ASSERTBACK_NOT: - { - int rc; - int local_offsets[2]; - int local_workspace[1000]; - const pcre_uchar *endasscode = code + GET(code, 1); - - while (*endasscode == OP_ALT) endasscode += GET(endasscode, 1); - - rc = internal_dfa_exec( - md, /* static match data */ - code, /* this subexpression's code */ - ptr, /* where we currently are */ - (int)(ptr - start_subject), /* start offset */ - local_offsets, /* offset vector */ - sizeof(local_offsets)/sizeof(int), /* size of same */ - local_workspace, /* workspace vector */ - sizeof(local_workspace)/sizeof(int), /* size of same */ - rlevel); /* function recursion level */ - - if (rc == PCRE_ERROR_DFA_UITEM) return rc; - if ((rc >= 0) == (codevalue == OP_ASSERT || codevalue == OP_ASSERTBACK)) - { ADD_ACTIVE((int)(endasscode + LINK_SIZE + 1 - start_code), 0); } - } - break; - - /*-----------------------------------------------------------------*/ - case OP_COND: - case OP_SCOND: - { - int local_offsets[1000]; - int local_workspace[1000]; - int codelink = GET(code, 1); - int condcode; - - /* Because of the way auto-callout works during compile, a callout item - is inserted between OP_COND and an assertion condition. This does not - happen for the other conditions. */ - - if (code[LINK_SIZE+1] == OP_CALLOUT) - { - rrc = 0; - if (PUBL(callout) != NULL) - { - PUBL(callout_block) cb; - cb.version = 1; /* Version 1 of the callout block */ - cb.callout_number = code[LINK_SIZE+2]; - cb.offset_vector = offsets; -#if defined COMPILE_PCRE8 - cb.subject = (PCRE_SPTR)start_subject; -#elif defined COMPILE_PCRE16 - cb.subject = (PCRE_SPTR16)start_subject; -#elif defined COMPILE_PCRE32 - cb.subject = (PCRE_SPTR32)start_subject; -#endif - cb.subject_length = (int)(end_subject - start_subject); - cb.start_match = (int)(current_subject - start_subject); - cb.current_position = (int)(ptr - start_subject); - cb.pattern_position = GET(code, LINK_SIZE + 3); - cb.next_item_length = GET(code, 3 + 2*LINK_SIZE); - cb.capture_top = 1; - cb.capture_last = -1; - cb.callout_data = md->callout_data; - cb.mark = NULL; /* No (*MARK) support */ - if ((rrc = (*PUBL(callout))(&cb)) < 0) return rrc; /* Abandon */ - } - if (rrc > 0) break; /* Fail this thread */ - code += PRIV(OP_lengths)[OP_CALLOUT]; /* Skip callout data */ - } - - condcode = code[LINK_SIZE+1]; - - /* Back reference conditions and duplicate named recursion conditions - are not supported */ - - if (condcode == OP_CREF || condcode == OP_DNCREF || - condcode == OP_DNRREF) - return PCRE_ERROR_DFA_UCOND; - - /* The DEFINE condition is always false, and the assertion (?!) is - converted to OP_FAIL. */ - - if (condcode == OP_DEF || condcode == OP_FAIL) - { ADD_ACTIVE(state_offset + codelink + LINK_SIZE + 1, 0); } - - /* The only supported version of OP_RREF is for the value RREF_ANY, - which means "test if in any recursion". We can't test for specifically - recursed groups. */ - - else if (condcode == OP_RREF) - { - int value = GET2(code, LINK_SIZE + 2); - if (value != RREF_ANY) return PCRE_ERROR_DFA_UCOND; - if (md->recursive != NULL) - { ADD_ACTIVE(state_offset + LINK_SIZE + 2 + IMM2_SIZE, 0); } - else { ADD_ACTIVE(state_offset + codelink + LINK_SIZE + 1, 0); } - } - - /* Otherwise, the condition is an assertion */ - - else - { - int rc; - const pcre_uchar *asscode = code + LINK_SIZE + 1; - const pcre_uchar *endasscode = asscode + GET(asscode, 1); - - while (*endasscode == OP_ALT) endasscode += GET(endasscode, 1); - - rc = internal_dfa_exec( - md, /* fixed match data */ - asscode, /* this subexpression's code */ - ptr, /* where we currently are */ - (int)(ptr - start_subject), /* start offset */ - local_offsets, /* offset vector */ - sizeof(local_offsets)/sizeof(int), /* size of same */ - local_workspace, /* workspace vector */ - sizeof(local_workspace)/sizeof(int), /* size of same */ - rlevel); /* function recursion level */ - - if (rc == PCRE_ERROR_DFA_UITEM) return rc; - if ((rc >= 0) == - (condcode == OP_ASSERT || condcode == OP_ASSERTBACK)) - { ADD_ACTIVE((int)(endasscode + LINK_SIZE + 1 - start_code), 0); } - else - { ADD_ACTIVE(state_offset + codelink + LINK_SIZE + 1, 0); } - } - } - break; - - /*-----------------------------------------------------------------*/ - case OP_RECURSE: - { - dfa_recursion_info *ri; - int local_offsets[1000]; - int local_workspace[1000]; - const pcre_uchar *callpat = start_code + GET(code, 1); - int recno = (callpat == md->start_code)? 0 : - GET2(callpat, 1 + LINK_SIZE); - int rc; - - DPRINTF(("%.*sStarting regex recursion\n", rlevel*2-2, SP)); - - /* Check for repeating a recursion without advancing the subject - pointer. This should catch convoluted mutual recursions. (Some simple - cases are caught at compile time.) */ - - for (ri = md->recursive; ri != NULL; ri = ri->prevrec) - if (recno == ri->group_num && ptr == ri->subject_position) - return PCRE_ERROR_RECURSELOOP; - - /* Remember this recursion and where we started it so as to - catch infinite loops. */ - - new_recursive.group_num = recno; - new_recursive.subject_position = ptr; - new_recursive.prevrec = md->recursive; - md->recursive = &new_recursive; - - rc = internal_dfa_exec( - md, /* fixed match data */ - callpat, /* this subexpression's code */ - ptr, /* where we currently are */ - (int)(ptr - start_subject), /* start offset */ - local_offsets, /* offset vector */ - sizeof(local_offsets)/sizeof(int), /* size of same */ - local_workspace, /* workspace vector */ - sizeof(local_workspace)/sizeof(int), /* size of same */ - rlevel); /* function recursion level */ - - md->recursive = new_recursive.prevrec; /* Done this recursion */ - - DPRINTF(("%.*sReturn from regex recursion: rc=%d\n", rlevel*2-2, SP, - rc)); - - /* Ran out of internal offsets */ - - if (rc == 0) return PCRE_ERROR_DFA_RECURSE; - - /* For each successful matched substring, set up the next state with a - count of characters to skip before trying it. Note that the count is in - characters, not bytes. */ - - if (rc > 0) - { - for (rc = rc*2 - 2; rc >= 0; rc -= 2) - { - int charcount = local_offsets[rc+1] - local_offsets[rc]; -#if defined SUPPORT_UTF && !defined COMPILE_PCRE32 - if (utf) - { - const pcre_uchar *p = start_subject + local_offsets[rc]; - const pcre_uchar *pp = start_subject + local_offsets[rc+1]; - while (p < pp) if (NOT_FIRSTCHAR(*p++)) charcount--; - } -#endif - if (charcount > 0) - { - ADD_NEW_DATA(-(state_offset + LINK_SIZE + 1), 0, (charcount - 1)); - } - else - { - ADD_ACTIVE(state_offset + LINK_SIZE + 1, 0); - } - } - } - else if (rc != PCRE_ERROR_NOMATCH) return rc; - } - break; - - /*-----------------------------------------------------------------*/ - case OP_BRAPOS: - case OP_SBRAPOS: - case OP_CBRAPOS: - case OP_SCBRAPOS: - case OP_BRAPOSZERO: - { - int charcount, matched_count; - const pcre_uchar *local_ptr = ptr; - BOOL allow_zero; - - if (codevalue == OP_BRAPOSZERO) - { - allow_zero = TRUE; - codevalue = *(++code); /* Codevalue will be one of above BRAs */ - } - else allow_zero = FALSE; - - /* Loop to match the subpattern as many times as possible as if it were - a complete pattern. */ - - for (matched_count = 0;; matched_count++) - { - int local_offsets[2]; - int local_workspace[1000]; - - int rc = internal_dfa_exec( - md, /* fixed match data */ - code, /* this subexpression's code */ - local_ptr, /* where we currently are */ - (int)(ptr - start_subject), /* start offset */ - local_offsets, /* offset vector */ - sizeof(local_offsets)/sizeof(int), /* size of same */ - local_workspace, /* workspace vector */ - sizeof(local_workspace)/sizeof(int), /* size of same */ - rlevel); /* function recursion level */ - - /* Failed to match */ - - if (rc < 0) - { - if (rc != PCRE_ERROR_NOMATCH) return rc; - break; - } - - /* Matched: break the loop if zero characters matched. */ - - charcount = local_offsets[1] - local_offsets[0]; - if (charcount == 0) break; - local_ptr += charcount; /* Advance temporary position ptr */ - } - - /* At this point we have matched the subpattern matched_count - times, and local_ptr is pointing to the character after the end of the - last match. */ - - if (matched_count > 0 || allow_zero) - { - const pcre_uchar *end_subpattern = code; - int next_state_offset; - - do { end_subpattern += GET(end_subpattern, 1); } - while (*end_subpattern == OP_ALT); - next_state_offset = - (int)(end_subpattern - start_code + LINK_SIZE + 1); - - /* Optimization: if there are no more active states, and there - are no new states yet set up, then skip over the subject string - right here, to save looping. Otherwise, set up the new state to swing - into action when the end of the matched substring is reached. */ - - if (i + 1 >= active_count && new_count == 0) - { - ptr = local_ptr; - clen = 0; - ADD_NEW(next_state_offset, 0); - } - else - { - const pcre_uchar *p = ptr; - const pcre_uchar *pp = local_ptr; - charcount = (int)(pp - p); -#if defined SUPPORT_UTF && !defined COMPILE_PCRE32 - if (utf) while (p < pp) if (NOT_FIRSTCHAR(*p++)) charcount--; -#endif - ADD_NEW_DATA(-next_state_offset, 0, (charcount - 1)); - } - } - } - break; - - /*-----------------------------------------------------------------*/ - case OP_ONCE: - case OP_ONCE_NC: - { - int local_offsets[2]; - int local_workspace[1000]; - - int rc = internal_dfa_exec( - md, /* fixed match data */ - code, /* this subexpression's code */ - ptr, /* where we currently are */ - (int)(ptr - start_subject), /* start offset */ - local_offsets, /* offset vector */ - sizeof(local_offsets)/sizeof(int), /* size of same */ - local_workspace, /* workspace vector */ - sizeof(local_workspace)/sizeof(int), /* size of same */ - rlevel); /* function recursion level */ - - if (rc >= 0) - { - const pcre_uchar *end_subpattern = code; - int charcount = local_offsets[1] - local_offsets[0]; - int next_state_offset, repeat_state_offset; - - do { end_subpattern += GET(end_subpattern, 1); } - while (*end_subpattern == OP_ALT); - next_state_offset = - (int)(end_subpattern - start_code + LINK_SIZE + 1); - - /* If the end of this subpattern is KETRMAX or KETRMIN, we must - arrange for the repeat state also to be added to the relevant list. - Calculate the offset, or set -1 for no repeat. */ - - repeat_state_offset = (*end_subpattern == OP_KETRMAX || - *end_subpattern == OP_KETRMIN)? - (int)(end_subpattern - start_code - GET(end_subpattern, 1)) : -1; - - /* If we have matched an empty string, add the next state at the - current character pointer. This is important so that the duplicate - checking kicks in, which is what breaks infinite loops that match an - empty string. */ - - if (charcount == 0) - { - ADD_ACTIVE(next_state_offset, 0); - } - - /* Optimization: if there are no more active states, and there - are no new states yet set up, then skip over the subject string - right here, to save looping. Otherwise, set up the new state to swing - into action when the end of the matched substring is reached. */ - - else if (i + 1 >= active_count && new_count == 0) - { - ptr += charcount; - clen = 0; - ADD_NEW(next_state_offset, 0); - - /* If we are adding a repeat state at the new character position, - we must fudge things so that it is the only current state. - Otherwise, it might be a duplicate of one we processed before, and - that would cause it to be skipped. */ - - if (repeat_state_offset >= 0) - { - next_active_state = active_states; - active_count = 0; - i = -1; - ADD_ACTIVE(repeat_state_offset, 0); - } - } - else - { -#if defined SUPPORT_UTF && !defined COMPILE_PCRE32 - if (utf) - { - const pcre_uchar *p = start_subject + local_offsets[0]; - const pcre_uchar *pp = start_subject + local_offsets[1]; - while (p < pp) if (NOT_FIRSTCHAR(*p++)) charcount--; - } -#endif - ADD_NEW_DATA(-next_state_offset, 0, (charcount - 1)); - if (repeat_state_offset >= 0) - { ADD_NEW_DATA(-repeat_state_offset, 0, (charcount - 1)); } - } - } - else if (rc != PCRE_ERROR_NOMATCH) return rc; - } - break; - - -/* ========================================================================== */ - /* Handle callouts */ - - case OP_CALLOUT: - rrc = 0; - if (PUBL(callout) != NULL) - { - PUBL(callout_block) cb; - cb.version = 1; /* Version 1 of the callout block */ - cb.callout_number = code[1]; - cb.offset_vector = offsets; -#if defined COMPILE_PCRE8 - cb.subject = (PCRE_SPTR)start_subject; -#elif defined COMPILE_PCRE16 - cb.subject = (PCRE_SPTR16)start_subject; -#elif defined COMPILE_PCRE32 - cb.subject = (PCRE_SPTR32)start_subject; -#endif - cb.subject_length = (int)(end_subject - start_subject); - cb.start_match = (int)(current_subject - start_subject); - cb.current_position = (int)(ptr - start_subject); - cb.pattern_position = GET(code, 2); - cb.next_item_length = GET(code, 2 + LINK_SIZE); - cb.capture_top = 1; - cb.capture_last = -1; - cb.callout_data = md->callout_data; - cb.mark = NULL; /* No (*MARK) support */ - if ((rrc = (*PUBL(callout))(&cb)) < 0) return rrc; /* Abandon */ - } - if (rrc == 0) - { ADD_ACTIVE(state_offset + PRIV(OP_lengths)[OP_CALLOUT], 0); } - break; - - -/* ========================================================================== */ - default: /* Unsupported opcode */ - return PCRE_ERROR_DFA_UITEM; - } - - NEXT_ACTIVE_STATE: continue; - - } /* End of loop scanning active states */ - - /* We have finished the processing at the current subject character. If no - new states have been set for the next character, we have found all the - matches that we are going to find. If we are at the top level and partial - matching has been requested, check for appropriate conditions. - - The "forced_ fail" variable counts the number of (*F) encountered for the - character. If it is equal to the original active_count (saved in - workspace[1]) it means that (*F) was found on every active state. In this - case we don't want to give a partial match. - - The "could_continue" variable is true if a state could have continued but - for the fact that the end of the subject was reached. */ - - if (new_count <= 0) - { - if (rlevel == 1 && /* Top level, and */ - could_continue && /* Some could go on, and */ - forced_fail != workspace[1] && /* Not all forced fail & */ - ( /* either... */ - (md->moptions & PCRE_PARTIAL_HARD) != 0 /* Hard partial */ - || /* or... */ - ((md->moptions & PCRE_PARTIAL_SOFT) != 0 && /* Soft partial and */ - match_count < 0) /* no matches */ - ) && /* And... */ - ( - partial_newline || /* Either partial NL */ - ( /* or ... */ - ptr >= end_subject && /* End of subject and */ - ptr > md->start_used_ptr) /* Inspected non-empty string */ - ) - ) - match_count = PCRE_ERROR_PARTIAL; - DPRINTF(("%.*sEnd of internal_dfa_exec %d: returning %d\n" - "%.*s---------------------\n\n", rlevel*2-2, SP, rlevel, match_count, - rlevel*2-2, SP)); - break; /* In effect, "return", but see the comment below */ - } - - /* One or more states are active for the next character. */ - - ptr += clen; /* Advance to next subject character */ - } /* Loop to move along the subject string */ - -/* Control gets here from "break" a few lines above. We do it this way because -if we use "return" above, we have compiler trouble. Some compilers warn if -there's nothing here because they think the function doesn't return a value. On -the other hand, if we put a dummy statement here, some more clever compilers -complain that it can't be reached. Sigh. */ - -return match_count; -} - - - - -/************************************************* -* Execute a Regular Expression - DFA engine * -*************************************************/ - -/* This external function applies a compiled re to a subject string using a DFA -engine. This function calls the internal function multiple times if the pattern -is not anchored. - -Arguments: - argument_re points to the compiled expression - extra_data points to extra data or is NULL - subject points to the subject string - length length of subject string (may contain binary zeros) - start_offset where to start in the subject string - options option bits - offsets vector of match offsets - offsetcount size of same - workspace workspace vector - wscount size of same - -Returns: > 0 => number of match offset pairs placed in offsets - = 0 => offsets overflowed; longest matches are present - -1 => failed to match - < -1 => some kind of unexpected problem -*/ - -#if defined COMPILE_PCRE8 -PCRE_EXP_DEFN int PCRE_CALL_CONVENTION -pcre_dfa_exec(const pcre *argument_re, const pcre_extra *extra_data, - const char *subject, int length, int start_offset, int options, int *offsets, - int offsetcount, int *workspace, int wscount) -#elif defined COMPILE_PCRE16 -PCRE_EXP_DEFN int PCRE_CALL_CONVENTION -pcre16_dfa_exec(const pcre16 *argument_re, const pcre16_extra *extra_data, - PCRE_SPTR16 subject, int length, int start_offset, int options, int *offsets, - int offsetcount, int *workspace, int wscount) -#elif defined COMPILE_PCRE32 -PCRE_EXP_DEFN int PCRE_CALL_CONVENTION -pcre32_dfa_exec(const pcre32 *argument_re, const pcre32_extra *extra_data, - PCRE_SPTR32 subject, int length, int start_offset, int options, int *offsets, - int offsetcount, int *workspace, int wscount) -#endif -{ -REAL_PCRE *re = (REAL_PCRE *)argument_re; -dfa_match_data match_block; -dfa_match_data *md = &match_block; -BOOL utf, anchored, startline, firstline; -const pcre_uchar *current_subject, *end_subject; -const pcre_study_data *study = NULL; - -const pcre_uchar *req_char_ptr; -const pcre_uint8 *start_bits = NULL; -BOOL has_first_char = FALSE; -BOOL has_req_char = FALSE; -pcre_uchar first_char = 0; -pcre_uchar first_char2 = 0; -pcre_uchar req_char = 0; -pcre_uchar req_char2 = 0; -int newline; - -/* Plausibility checks */ - -if ((options & ~PUBLIC_DFA_EXEC_OPTIONS) != 0) return PCRE_ERROR_BADOPTION; -if (re == NULL || subject == NULL || workspace == NULL || - (offsets == NULL && offsetcount > 0)) return PCRE_ERROR_NULL; -if (offsetcount < 0) return PCRE_ERROR_BADCOUNT; -if (wscount < 20) return PCRE_ERROR_DFA_WSSIZE; -if (length < 0) return PCRE_ERROR_BADLENGTH; -if (start_offset < 0 || start_offset > length) return PCRE_ERROR_BADOFFSET; - -/* Check that the first field in the block is the magic number. If it is not, -return with PCRE_ERROR_BADMAGIC. However, if the magic number is equal to -REVERSED_MAGIC_NUMBER we return with PCRE_ERROR_BADENDIANNESS, which -means that the pattern is likely compiled with different endianness. */ - -if (re->magic_number != MAGIC_NUMBER) - return re->magic_number == REVERSED_MAGIC_NUMBER? - PCRE_ERROR_BADENDIANNESS:PCRE_ERROR_BADMAGIC; -if ((re->flags & PCRE_MODE) == 0) return PCRE_ERROR_BADMODE; - -/* If restarting after a partial match, do some sanity checks on the contents -of the workspace. */ - -if ((options & PCRE_DFA_RESTART) != 0) - { - if ((workspace[0] & (-2)) != 0 || workspace[1] < 1 || - workspace[1] > (wscount - 2)/INTS_PER_STATEBLOCK) - return PCRE_ERROR_DFA_BADRESTART; - } - -/* Set up study, callout, and table data */ - -md->tables = re->tables; -md->callout_data = NULL; - -if (extra_data != NULL) - { - unsigned long int flags = extra_data->flags; - if ((flags & PCRE_EXTRA_STUDY_DATA) != 0) - study = (const pcre_study_data *)extra_data->study_data; - if ((flags & PCRE_EXTRA_MATCH_LIMIT) != 0) return PCRE_ERROR_DFA_UMLIMIT; - if ((flags & PCRE_EXTRA_MATCH_LIMIT_RECURSION) != 0) - return PCRE_ERROR_DFA_UMLIMIT; - if ((flags & PCRE_EXTRA_CALLOUT_DATA) != 0) - md->callout_data = extra_data->callout_data; - if ((flags & PCRE_EXTRA_TABLES) != 0) - md->tables = extra_data->tables; - } - -/* Set some local values */ - -current_subject = (const pcre_uchar *)subject + start_offset; -end_subject = (const pcre_uchar *)subject + length; -req_char_ptr = current_subject - 1; - -#ifdef SUPPORT_UTF -/* PCRE_UTF(16|32) have the same value as PCRE_UTF8. */ -utf = (re->options & PCRE_UTF8) != 0; -#else -utf = FALSE; -#endif - -anchored = (options & (PCRE_ANCHORED|PCRE_DFA_RESTART)) != 0 || - (re->options & PCRE_ANCHORED) != 0; - -/* The remaining fixed data for passing around. */ - -md->start_code = (const pcre_uchar *)argument_re + - re->name_table_offset + re->name_count * re->name_entry_size; -md->start_subject = (const pcre_uchar *)subject; -md->end_subject = end_subject; -md->start_offset = start_offset; -md->moptions = options; -md->poptions = re->options; - -/* If the BSR option is not set at match time, copy what was set -at compile time. */ - -if ((md->moptions & (PCRE_BSR_ANYCRLF|PCRE_BSR_UNICODE)) == 0) - { - if ((re->options & (PCRE_BSR_ANYCRLF|PCRE_BSR_UNICODE)) != 0) - md->moptions |= re->options & (PCRE_BSR_ANYCRLF|PCRE_BSR_UNICODE); -#ifdef BSR_ANYCRLF - else md->moptions |= PCRE_BSR_ANYCRLF; -#endif - } - -/* Handle different types of newline. The three bits give eight cases. If -nothing is set at run time, whatever was used at compile time applies. */ - -switch ((((options & PCRE_NEWLINE_BITS) == 0)? re->options : (pcre_uint32)options) & - PCRE_NEWLINE_BITS) - { - case 0: newline = NEWLINE; break; /* Compile-time default */ - case PCRE_NEWLINE_CR: newline = CHAR_CR; break; - case PCRE_NEWLINE_LF: newline = CHAR_NL; break; - case PCRE_NEWLINE_CR+ - PCRE_NEWLINE_LF: newline = (CHAR_CR << 8) | CHAR_NL; break; - case PCRE_NEWLINE_ANY: newline = -1; break; - case PCRE_NEWLINE_ANYCRLF: newline = -2; break; - default: return PCRE_ERROR_BADNEWLINE; - } - -if (newline == -2) - { - md->nltype = NLTYPE_ANYCRLF; - } -else if (newline < 0) - { - md->nltype = NLTYPE_ANY; - } -else - { - md->nltype = NLTYPE_FIXED; - if (newline > 255) - { - md->nllen = 2; - md->nl[0] = (newline >> 8) & 255; - md->nl[1] = newline & 255; - } - else - { - md->nllen = 1; - md->nl[0] = newline; - } - } - -/* Check a UTF-8 string if required. Unfortunately there's no way of passing -back the character offset. */ - -#ifdef SUPPORT_UTF -if (utf && (options & PCRE_NO_UTF8_CHECK) == 0) - { - int erroroffset; - int errorcode = PRIV(valid_utf)((pcre_uchar *)subject, length, &erroroffset); - if (errorcode != 0) - { - if (offsetcount >= 2) - { - offsets[0] = erroroffset; - offsets[1] = errorcode; - } -#if defined COMPILE_PCRE8 - return (errorcode <= PCRE_UTF8_ERR5 && (options & PCRE_PARTIAL_HARD) != 0) ? - PCRE_ERROR_SHORTUTF8 : PCRE_ERROR_BADUTF8; -#elif defined COMPILE_PCRE16 - return (errorcode <= PCRE_UTF16_ERR1 && (options & PCRE_PARTIAL_HARD) != 0) ? - PCRE_ERROR_SHORTUTF16 : PCRE_ERROR_BADUTF16; -#elif defined COMPILE_PCRE32 - return PCRE_ERROR_BADUTF32; -#endif - } -#if defined COMPILE_PCRE8 || defined COMPILE_PCRE16 - if (start_offset > 0 && start_offset < length && - NOT_FIRSTCHAR(((PCRE_PUCHAR)subject)[start_offset])) - return PCRE_ERROR_BADUTF8_OFFSET; -#endif - } -#endif - -/* If the exec call supplied NULL for tables, use the inbuilt ones. This -is a feature that makes it possible to save compiled regex and re-use them -in other programs later. */ - -if (md->tables == NULL) md->tables = PRIV(default_tables); - -/* The "must be at the start of a line" flags are used in a loop when finding -where to start. */ - -startline = (re->flags & PCRE_STARTLINE) != 0; -firstline = (re->options & PCRE_FIRSTLINE) != 0; - -/* Set up the first character to match, if available. The first_byte value is -never set for an anchored regular expression, but the anchoring may be forced -at run time, so we have to test for anchoring. The first char may be unset for -an unanchored pattern, of course. If there's no first char and the pattern was -studied, there may be a bitmap of possible first characters. */ - -if (!anchored) - { - if ((re->flags & PCRE_FIRSTSET) != 0) - { - has_first_char = TRUE; - first_char = first_char2 = (pcre_uchar)(re->first_char); - if ((re->flags & PCRE_FCH_CASELESS) != 0) - { - first_char2 = TABLE_GET(first_char, md->tables + fcc_offset, first_char); -#if defined SUPPORT_UCP && !(defined COMPILE_PCRE8) - if (utf && first_char > 127) - first_char2 = UCD_OTHERCASE(first_char); -#endif - } - } - else - { - if (!startline && study != NULL && - (study->flags & PCRE_STUDY_MAPPED) != 0) - start_bits = study->start_bits; - } - } - -/* For anchored or unanchored matches, there may be a "last known required -character" set. */ - -if ((re->flags & PCRE_REQCHSET) != 0) - { - has_req_char = TRUE; - req_char = req_char2 = (pcre_uchar)(re->req_char); - if ((re->flags & PCRE_RCH_CASELESS) != 0) - { - req_char2 = TABLE_GET(req_char, md->tables + fcc_offset, req_char); -#if defined SUPPORT_UCP && !(defined COMPILE_PCRE8) - if (utf && req_char > 127) - req_char2 = UCD_OTHERCASE(req_char); -#endif - } - } - -/* Call the main matching function, looping for a non-anchored regex after a -failed match. If not restarting, perform certain optimizations at the start of -a match. */ - -for (;;) - { - int rc; - - if ((options & PCRE_DFA_RESTART) == 0) - { - const pcre_uchar *save_end_subject = end_subject; - - /* If firstline is TRUE, the start of the match is constrained to the first - line of a multiline string. Implement this by temporarily adjusting - end_subject so that we stop scanning at a newline. If the match fails at - the newline, later code breaks this loop. */ - - if (firstline) - { - PCRE_PUCHAR t = current_subject; -#ifdef SUPPORT_UTF - if (utf) - { - while (t < md->end_subject && !IS_NEWLINE(t)) - { - t++; - ACROSSCHAR(t < end_subject, *t, t++); - } - } - else -#endif - while (t < md->end_subject && !IS_NEWLINE(t)) t++; - end_subject = t; - } - - /* There are some optimizations that avoid running the match if a known - starting point is not found. However, there is an option that disables - these, for testing and for ensuring that all callouts do actually occur. - The option can be set in the regex by (*NO_START_OPT) or passed in - match-time options. */ - - if (((options | re->options) & PCRE_NO_START_OPTIMIZE) == 0) - { - /* Advance to a known first pcre_uchar (i.e. data item) */ - - if (has_first_char) - { - if (first_char != first_char2) - { - pcre_uchar csc; - while (current_subject < end_subject && - (csc = UCHAR21TEST(current_subject)) != first_char && csc != first_char2) - current_subject++; - } - else - while (current_subject < end_subject && - UCHAR21TEST(current_subject) != first_char) - current_subject++; - } - - /* Or to just after a linebreak for a multiline match if possible */ - - else if (startline) - { - if (current_subject > md->start_subject + start_offset) - { -#ifdef SUPPORT_UTF - if (utf) - { - while (current_subject < end_subject && - !WAS_NEWLINE(current_subject)) - { - current_subject++; - ACROSSCHAR(current_subject < end_subject, *current_subject, - current_subject++); - } - } - else -#endif - while (current_subject < end_subject && !WAS_NEWLINE(current_subject)) - current_subject++; - - /* If we have just passed a CR and the newline option is ANY or - ANYCRLF, and we are now at a LF, advance the match position by one - more character. */ - - if (UCHAR21TEST(current_subject - 1) == CHAR_CR && - (md->nltype == NLTYPE_ANY || md->nltype == NLTYPE_ANYCRLF) && - current_subject < end_subject && - UCHAR21TEST(current_subject) == CHAR_NL) - current_subject++; - } - } - - /* Advance to a non-unique first pcre_uchar after study */ - - else if (start_bits != NULL) - { - while (current_subject < end_subject) - { - register pcre_uint32 c = UCHAR21TEST(current_subject); -#ifndef COMPILE_PCRE8 - if (c > 255) c = 255; -#endif - if ((start_bits[c/8] & (1 << (c&7))) != 0) break; - current_subject++; - } - } - } - - /* Restore fudged end_subject */ - - end_subject = save_end_subject; - - /* The following two optimizations are disabled for partial matching or if - disabling is explicitly requested (and of course, by the test above, this - code is not obeyed when restarting after a partial match). */ - - if (((options | re->options) & PCRE_NO_START_OPTIMIZE) == 0 && - (options & (PCRE_PARTIAL_HARD|PCRE_PARTIAL_SOFT)) == 0) - { - /* If the pattern was studied, a minimum subject length may be set. This - is a lower bound; no actual string of that length may actually match the - pattern. Although the value is, strictly, in characters, we treat it as - in pcre_uchar units to avoid spending too much time in this optimization. - */ - - if (study != NULL && (study->flags & PCRE_STUDY_MINLEN) != 0 && - (pcre_uint32)(end_subject - current_subject) < study->minlength) - return PCRE_ERROR_NOMATCH; - - /* If req_char is set, we know that that pcre_uchar must appear in the - subject for the match to succeed. If the first pcre_uchar is set, - req_char must be later in the subject; otherwise the test starts at the - match point. This optimization can save a huge amount of work in patterns - with nested unlimited repeats that aren't going to match. Writing - separate code for cased/caseless versions makes it go faster, as does - using an autoincrement and backing off on a match. - - HOWEVER: when the subject string is very, very long, searching to its end - can take a long time, and give bad performance on quite ordinary - patterns. This showed up when somebody was matching /^C/ on a 32-megabyte - string... so we don't do this when the string is sufficiently long. */ - - if (has_req_char && end_subject - current_subject < REQ_BYTE_MAX) - { - register PCRE_PUCHAR p = current_subject + (has_first_char? 1:0); - - /* We don't need to repeat the search if we haven't yet reached the - place we found it at last time. */ - - if (p > req_char_ptr) - { - if (req_char != req_char2) - { - while (p < end_subject) - { - register pcre_uint32 pp = UCHAR21INCTEST(p); - if (pp == req_char || pp == req_char2) { p--; break; } - } - } - else - { - while (p < end_subject) - { - if (UCHAR21INCTEST(p) == req_char) { p--; break; } - } - } - - /* If we can't find the required pcre_uchar, break the matching loop, - which will cause a return or PCRE_ERROR_NOMATCH. */ - - if (p >= end_subject) break; - - /* If we have found the required pcre_uchar, save the point where we - found it, so that we don't search again next time round the loop if - the start hasn't passed this point yet. */ - - req_char_ptr = p; - } - } - } - } /* End of optimizations that are done when not restarting */ - - /* OK, now we can do the business */ - - md->start_used_ptr = current_subject; - md->recursive = NULL; - - rc = internal_dfa_exec( - md, /* fixed match data */ - md->start_code, /* this subexpression's code */ - current_subject, /* where we currently are */ - start_offset, /* start offset in subject */ - offsets, /* offset vector */ - offsetcount, /* size of same */ - workspace, /* workspace vector */ - wscount, /* size of same */ - 0); /* function recurse level */ - - /* Anything other than "no match" means we are done, always; otherwise, carry - on only if not anchored. */ - - if (rc != PCRE_ERROR_NOMATCH || anchored) - { - if (rc == PCRE_ERROR_PARTIAL && offsetcount >= 2) - { - offsets[0] = (int)(md->start_used_ptr - (PCRE_PUCHAR)subject); - offsets[1] = (int)(end_subject - (PCRE_PUCHAR)subject); - if (offsetcount > 2) - offsets[2] = (int)(current_subject - (PCRE_PUCHAR)subject); - } - return rc; - } - - /* Advance to the next subject character unless we are at the end of a line - and firstline is set. */ - - if (firstline && IS_NEWLINE(current_subject)) break; - current_subject++; -#ifdef SUPPORT_UTF - if (utf) - { - ACROSSCHAR(current_subject < end_subject, *current_subject, - current_subject++); - } -#endif - if (current_subject > end_subject) break; - - /* If we have just passed a CR and we are now at a LF, and the pattern does - not contain any explicit matches for \r or \n, and the newline option is CRLF - or ANY or ANYCRLF, advance the match position by one more character. */ - - if (UCHAR21TEST(current_subject - 1) == CHAR_CR && - current_subject < end_subject && - UCHAR21TEST(current_subject) == CHAR_NL && - (re->flags & PCRE_HASCRORLF) == 0 && - (md->nltype == NLTYPE_ANY || - md->nltype == NLTYPE_ANYCRLF || - md->nllen == 2)) - current_subject++; - - } /* "Bumpalong" loop */ - -return PCRE_ERROR_NOMATCH; -} - -/* End of pcre_dfa_exec.c */ diff --git a/src/third_party/pcre-8.38/pcre_exec.c b/src/third_party/pcre-8.38/pcre_exec.c deleted file mode 100644 index 24b23ca2864..00000000000 --- a/src/third_party/pcre-8.38/pcre_exec.c +++ /dev/null @@ -1,7173 +0,0 @@ -/************************************************* -* Perl-Compatible Regular Expressions * -*************************************************/ - -/* PCRE is a library of functions to support regular expressions whose syntax -and semantics are as close as possible to those of the Perl 5 language. - - Written by Philip Hazel - Copyright (c) 1997-2014 University of Cambridge - ------------------------------------------------------------------------------ -Redistribution and use in source and binary forms, with or without -modification, are permitted provided that the following conditions are met: - - * Redistributions of source code must retain the above copyright notice, - this list of conditions and the following disclaimer. - - * Redistributions in binary form must reproduce the above copyright - notice, this list of conditions and the following disclaimer in the - documentation and/or other materials provided with the distribution. - - * Neither the name of the University of Cambridge nor the names of its - contributors may be used to endorse or promote products derived from - this software without specific prior written permission. - -THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS" -AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE -IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE -ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR CONTRIBUTORS BE -LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR -CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF -SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS -INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN -CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) -ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE -POSSIBILITY OF SUCH DAMAGE. ------------------------------------------------------------------------------ -*/ - -/* This module contains pcre_exec(), the externally visible function that does -pattern matching using an NFA algorithm, trying to mimic Perl as closely as -possible. There are also some static supporting functions. */ - -#ifdef HAVE_CONFIG_H -#include "config.h" -#endif - -#define NLBLOCK md /* Block containing newline information */ -#define PSSTART start_subject /* Field containing processed string start */ -#define PSEND end_subject /* Field containing processed string end */ - -#include "pcre_internal.h" - -/* Undefine some potentially clashing cpp symbols */ - -#undef min -#undef max - -/* The md->capture_last field uses the lower 16 bits for the last captured -substring (which can never be greater than 65535) and a bit in the top half -to mean "capture vector overflowed". This odd way of doing things was -implemented when it was realized that preserving and restoring the overflow bit -whenever the last capture number was saved/restored made for a neater -interface, and doing it this way saved on (a) another variable, which would -have increased the stack frame size (a big NO-NO in PCRE) and (b) another -separate set of save/restore instructions. The following defines are used in -implementing this. */ - -#define CAPLMASK 0x0000ffff /* The bits used for last_capture */ -#define OVFLMASK 0xffff0000 /* The bits used for the overflow flag */ -#define OVFLBIT 0x00010000 /* The bit that is set for overflow */ - -/* Values for setting in md->match_function_type to indicate two special types -of call to match(). We do it this way to save on using another stack variable, -as stack usage is to be discouraged. */ - -#define MATCH_CONDASSERT 1 /* Called to check a condition assertion */ -#define MATCH_CBEGROUP 2 /* Could-be-empty unlimited repeat group */ - -/* Non-error returns from the match() function. Error returns are externally -defined PCRE_ERROR_xxx codes, which are all negative. */ - -#define MATCH_MATCH 1 -#define MATCH_NOMATCH 0 - -/* Special internal returns from the match() function. Make them sufficiently -negative to avoid the external error codes. */ - -#define MATCH_ACCEPT (-999) -#define MATCH_KETRPOS (-998) -#define MATCH_ONCE (-997) -/* The next 5 must be kept together and in sequence so that a test that checks -for any one of them can use a range. */ -#define MATCH_COMMIT (-996) -#define MATCH_PRUNE (-995) -#define MATCH_SKIP (-994) -#define MATCH_SKIP_ARG (-993) -#define MATCH_THEN (-992) -#define MATCH_BACKTRACK_MAX MATCH_THEN -#define MATCH_BACKTRACK_MIN MATCH_COMMIT - -/* Maximum number of ints of offset to save on the stack for recursive calls. -If the offset vector is bigger, malloc is used. This should be a multiple of 3, -because the offset vector is always a multiple of 3 long. */ - -#define REC_STACK_SAVE_MAX 30 - -/* Min and max values for the common repeats; for the maxima, 0 => infinity */ - -static const char rep_min[] = { 0, 0, 1, 1, 0, 0, 0, 0, 0, 1, 0, }; -static const char rep_max[] = { 0, 0, 0, 0, 1, 1, 0, 0, 0, 0, 1, }; - -#ifdef PCRE_DEBUG -/************************************************* -* Debugging function to print chars * -*************************************************/ - -/* Print a sequence of chars in printable format, stopping at the end of the -subject if the requested. - -Arguments: - p points to characters - length number to print - is_subject TRUE if printing from within md->start_subject - md pointer to matching data block, if is_subject is TRUE - -Returns: nothing -*/ - -static void -pchars(const pcre_uchar *p, int length, BOOL is_subject, match_data *md) -{ -pcre_uint32 c; -BOOL utf = md->utf; -if (is_subject && length > md->end_subject - p) length = md->end_subject - p; -while (length-- > 0) - if (isprint(c = UCHAR21INCTEST(p))) printf("%c", (char)c); else printf("\\x{%02x}", c); -} -#endif - - - -/************************************************* -* Match a back-reference * -*************************************************/ - -/* Normally, if a back reference hasn't been set, the length that is passed is -negative, so the match always fails. However, in JavaScript compatibility mode, -the length passed is zero. Note that in caseless UTF-8 mode, the number of -subject bytes matched may be different to the number of reference bytes. - -Arguments: - offset index into the offset vector - eptr pointer into the subject - length length of reference to be matched (number of bytes) - md points to match data block - caseless TRUE if caseless - -Returns: >= 0 the number of subject bytes matched - -1 no match - -2 partial match; always given if at end subject -*/ - -static int -match_ref(int offset, register PCRE_PUCHAR eptr, int length, match_data *md, - BOOL caseless) -{ -PCRE_PUCHAR eptr_start = eptr; -register PCRE_PUCHAR p = md->start_subject + md->offset_vector[offset]; -#if defined SUPPORT_UTF && defined SUPPORT_UCP -BOOL utf = md->utf; -#endif - -#ifdef PCRE_DEBUG -if (eptr >= md->end_subject) - printf("matching subject <null>"); -else - { - printf("matching subject "); - pchars(eptr, length, TRUE, md); - } -printf(" against backref "); -pchars(p, length, FALSE, md); -printf("\n"); -#endif - -/* Always fail if reference not set (and not JavaScript compatible - in that -case the length is passed as zero). */ - -if (length < 0) return -1; - -/* Separate the caseless case for speed. In UTF-8 mode we can only do this -properly if Unicode properties are supported. Otherwise, we can check only -ASCII characters. */ - -if (caseless) - { -#if defined SUPPORT_UTF && defined SUPPORT_UCP - if (utf) - { - /* Match characters up to the end of the reference. NOTE: the number of - data units matched may differ, because in UTF-8 there are some characters - whose upper and lower case versions code have different numbers of bytes. - For example, U+023A (2 bytes in UTF-8) is the upper case version of U+2C65 - (3 bytes in UTF-8); a sequence of 3 of the former uses 6 bytes, as does a - sequence of two of the latter. It is important, therefore, to check the - length along the reference, not along the subject (earlier code did this - wrong). */ - - PCRE_PUCHAR endptr = p + length; - while (p < endptr) - { - pcre_uint32 c, d; - const ucd_record *ur; - if (eptr >= md->end_subject) return -2; /* Partial match */ - GETCHARINC(c, eptr); - GETCHARINC(d, p); - ur = GET_UCD(d); - if (c != d && c != d + ur->other_case) - { - const pcre_uint32 *pp = PRIV(ucd_caseless_sets) + ur->caseset; - for (;;) - { - if (c < *pp) return -1; - if (c == *pp++) break; - } - } - } - } - else -#endif - - /* The same code works when not in UTF-8 mode and in UTF-8 mode when there - is no UCP support. */ - { - while (length-- > 0) - { - pcre_uint32 cc, cp; - if (eptr >= md->end_subject) return -2; /* Partial match */ - cc = UCHAR21TEST(eptr); - cp = UCHAR21TEST(p); - if (TABLE_GET(cp, md->lcc, cp) != TABLE_GET(cc, md->lcc, cc)) return -1; - p++; - eptr++; - } - } - } - -/* In the caseful case, we can just compare the bytes, whether or not we -are in UTF-8 mode. */ - -else - { - while (length-- > 0) - { - if (eptr >= md->end_subject) return -2; /* Partial match */ - if (UCHAR21INCTEST(p) != UCHAR21INCTEST(eptr)) return -1; - } - } - -return (int)(eptr - eptr_start); -} - - - -/*************************************************************************** -**************************************************************************** - RECURSION IN THE match() FUNCTION - -The match() function is highly recursive, though not every recursive call -increases the recursive depth. Nevertheless, some regular expressions can cause -it to recurse to a great depth. I was writing for Unix, so I just let it call -itself recursively. This uses the stack for saving everything that has to be -saved for a recursive call. On Unix, the stack can be large, and this works -fine. - -It turns out that on some non-Unix-like systems there are problems with -programs that use a lot of stack. (This despite the fact that every last chip -has oodles of memory these days, and techniques for extending the stack have -been known for decades.) So.... - -There is a fudge, triggered by defining NO_RECURSE, which avoids recursive -calls by keeping local variables that need to be preserved in blocks of memory -obtained from malloc() instead instead of on the stack. Macros are used to -achieve this so that the actual code doesn't look very different to what it -always used to. - -The original heap-recursive code used longjmp(). However, it seems that this -can be very slow on some operating systems. Following a suggestion from Stan -Switzer, the use of longjmp() has been abolished, at the cost of having to -provide a unique number for each call to RMATCH. There is no way of generating -a sequence of numbers at compile time in C. I have given them names, to make -them stand out more clearly. - -Crude tests on x86 Linux show a small speedup of around 5-8%. However, on -FreeBSD, avoiding longjmp() more than halves the time taken to run the standard -tests. Furthermore, not using longjmp() means that local dynamic variables -don't have indeterminate values; this has meant that the frame size can be -reduced because the result can be "passed back" by straight setting of the -variable instead of being passed in the frame. -**************************************************************************** -***************************************************************************/ - -/* Numbers for RMATCH calls. When this list is changed, the code at HEAP_RETURN -below must be updated in sync. */ - -enum { RM1=1, RM2, RM3, RM4, RM5, RM6, RM7, RM8, RM9, RM10, - RM11, RM12, RM13, RM14, RM15, RM16, RM17, RM18, RM19, RM20, - RM21, RM22, RM23, RM24, RM25, RM26, RM27, RM28, RM29, RM30, - RM31, RM32, RM33, RM34, RM35, RM36, RM37, RM38, RM39, RM40, - RM41, RM42, RM43, RM44, RM45, RM46, RM47, RM48, RM49, RM50, - RM51, RM52, RM53, RM54, RM55, RM56, RM57, RM58, RM59, RM60, - RM61, RM62, RM63, RM64, RM65, RM66, RM67 }; - -/* These versions of the macros use the stack, as normal. There are debugging -versions and production versions. Note that the "rw" argument of RMATCH isn't -actually used in this definition. */ - -#ifndef NO_RECURSE -#define REGISTER register - -#ifdef PCRE_DEBUG -#define RMATCH(ra,rb,rc,rd,re,rw) \ - { \ - printf("match() called in line %d\n", __LINE__); \ - rrc = match(ra,rb,mstart,rc,rd,re,rdepth+1); \ - printf("to line %d\n", __LINE__); \ - } -#define RRETURN(ra) \ - { \ - printf("match() returned %d from line %d\n", ra, __LINE__); \ - return ra; \ - } -#else -#define RMATCH(ra,rb,rc,rd,re,rw) \ - rrc = match(ra,rb,mstart,rc,rd,re,rdepth+1) -#define RRETURN(ra) return ra -#endif - -#else - - -/* These versions of the macros manage a private stack on the heap. Note that -the "rd" argument of RMATCH isn't actually used in this definition. It's the md -argument of match(), which never changes. */ - -#define REGISTER - -#define RMATCH(ra,rb,rc,rd,re,rw)\ - {\ - heapframe *newframe = frame->Xnextframe;\ - if (newframe == NULL)\ - {\ - newframe = (heapframe *)(PUBL(stack_malloc))(sizeof(heapframe));\ - if (newframe == NULL) RRETURN(PCRE_ERROR_NOMEMORY);\ - newframe->Xnextframe = NULL;\ - frame->Xnextframe = newframe;\ - }\ - frame->Xwhere = rw;\ - newframe->Xeptr = ra;\ - newframe->Xecode = rb;\ - newframe->Xmstart = mstart;\ - newframe->Xoffset_top = rc;\ - newframe->Xeptrb = re;\ - newframe->Xrdepth = frame->Xrdepth + 1;\ - newframe->Xprevframe = frame;\ - frame = newframe;\ - DPRINTF(("restarting from line %d\n", __LINE__));\ - goto HEAP_RECURSE;\ - L_##rw:\ - DPRINTF(("jumped back to line %d\n", __LINE__));\ - } - -#define RRETURN(ra)\ - {\ - heapframe *oldframe = frame;\ - frame = oldframe->Xprevframe;\ - if (frame != NULL)\ - {\ - rrc = ra;\ - goto HEAP_RETURN;\ - }\ - return ra;\ - } - - -/* Structure for remembering the local variables in a private frame */ - -typedef struct heapframe { - struct heapframe *Xprevframe; - struct heapframe *Xnextframe; - - /* Function arguments that may change */ - - PCRE_PUCHAR Xeptr; - const pcre_uchar *Xecode; - PCRE_PUCHAR Xmstart; - int Xoffset_top; - eptrblock *Xeptrb; - unsigned int Xrdepth; - - /* Function local variables */ - - PCRE_PUCHAR Xcallpat; -#ifdef SUPPORT_UTF - PCRE_PUCHAR Xcharptr; -#endif - PCRE_PUCHAR Xdata; - PCRE_PUCHAR Xnext; - PCRE_PUCHAR Xpp; - PCRE_PUCHAR Xprev; - PCRE_PUCHAR Xsaved_eptr; - - recursion_info Xnew_recursive; - - BOOL Xcur_is_word; - BOOL Xcondition; - BOOL Xprev_is_word; - -#ifdef SUPPORT_UCP - int Xprop_type; - unsigned int Xprop_value; - int Xprop_fail_result; - int Xoclength; - pcre_uchar Xocchars[6]; -#endif - - int Xcodelink; - int Xctype; - unsigned int Xfc; - int Xfi; - int Xlength; - int Xmax; - int Xmin; - unsigned int Xnumber; - int Xoffset; - unsigned int Xop; - pcre_int32 Xsave_capture_last; - int Xsave_offset1, Xsave_offset2, Xsave_offset3; - int Xstacksave[REC_STACK_SAVE_MAX]; - - eptrblock Xnewptrb; - - /* Where to jump back to */ - - int Xwhere; - -} heapframe; - -#endif - - -/*************************************************************************** -***************************************************************************/ - - - -/************************************************* -* Match from current position * -*************************************************/ - -/* This function is called recursively in many circumstances. Whenever it -returns a negative (error) response, the outer incarnation must also return the -same response. */ - -/* These macros pack up tests that are used for partial matching, and which -appear several times in the code. We set the "hit end" flag if the pointer is -at the end of the subject and also past the start of the subject (i.e. -something has been matched). For hard partial matching, we then return -immediately. The second one is used when we already know we are past the end of -the subject. */ - -#define CHECK_PARTIAL()\ - if (md->partial != 0 && eptr >= md->end_subject && \ - eptr > md->start_used_ptr) \ - { \ - md->hitend = TRUE; \ - if (md->partial > 1) RRETURN(PCRE_ERROR_PARTIAL); \ - } - -#define SCHECK_PARTIAL()\ - if (md->partial != 0 && eptr > md->start_used_ptr) \ - { \ - md->hitend = TRUE; \ - if (md->partial > 1) RRETURN(PCRE_ERROR_PARTIAL); \ - } - - -/* Performance note: It might be tempting to extract commonly used fields from -the md structure (e.g. utf, end_subject) into individual variables to improve -performance. Tests using gcc on a SPARC disproved this; in the first case, it -made performance worse. - -Arguments: - eptr pointer to current character in subject - ecode pointer to current position in compiled code - mstart pointer to the current match start position (can be modified - by encountering \K) - offset_top current top pointer - md pointer to "static" info for the match - eptrb pointer to chain of blocks containing eptr at start of - brackets - for testing for empty matches - rdepth the recursion depth - -Returns: MATCH_MATCH if matched ) these values are >= 0 - MATCH_NOMATCH if failed to match ) - a negative MATCH_xxx value for PRUNE, SKIP, etc - a negative PCRE_ERROR_xxx value if aborted by an error condition - (e.g. stopped by repeated call or recursion limit) -*/ - -static int -match(REGISTER PCRE_PUCHAR eptr, REGISTER const pcre_uchar *ecode, - PCRE_PUCHAR mstart, int offset_top, match_data *md, eptrblock *eptrb, - unsigned int rdepth) -{ -/* These variables do not need to be preserved over recursion in this function, -so they can be ordinary variables in all cases. Mark some of them with -"register" because they are used a lot in loops. */ - -register int rrc; /* Returns from recursive calls */ -register int i; /* Used for loops not involving calls to RMATCH() */ -register pcre_uint32 c; /* Character values not kept over RMATCH() calls */ -register BOOL utf; /* Local copy of UTF flag for speed */ - -BOOL minimize, possessive; /* Quantifier options */ -BOOL caseless; -int condcode; - -/* When recursion is not being used, all "local" variables that have to be -preserved over calls to RMATCH() are part of a "frame". We set up the top-level -frame on the stack here; subsequent instantiations are obtained from the heap -whenever RMATCH() does a "recursion". See the macro definitions above. Putting -the top-level on the stack rather than malloc-ing them all gives a performance -boost in many cases where there is not much "recursion". */ - -#ifdef NO_RECURSE -heapframe *frame = (heapframe *)md->match_frames_base; - -/* Copy in the original argument variables */ - -frame->Xeptr = eptr; -frame->Xecode = ecode; -frame->Xmstart = mstart; -frame->Xoffset_top = offset_top; -frame->Xeptrb = eptrb; -frame->Xrdepth = rdepth; - -/* This is where control jumps back to to effect "recursion" */ - -HEAP_RECURSE: - -/* Macros make the argument variables come from the current frame */ - -#define eptr frame->Xeptr -#define ecode frame->Xecode -#define mstart frame->Xmstart -#define offset_top frame->Xoffset_top -#define eptrb frame->Xeptrb -#define rdepth frame->Xrdepth - -/* Ditto for the local variables */ - -#ifdef SUPPORT_UTF -#define charptr frame->Xcharptr -#endif -#define callpat frame->Xcallpat -#define codelink frame->Xcodelink -#define data frame->Xdata -#define next frame->Xnext -#define pp frame->Xpp -#define prev frame->Xprev -#define saved_eptr frame->Xsaved_eptr - -#define new_recursive frame->Xnew_recursive - -#define cur_is_word frame->Xcur_is_word -#define condition frame->Xcondition -#define prev_is_word frame->Xprev_is_word - -#ifdef SUPPORT_UCP -#define prop_type frame->Xprop_type -#define prop_value frame->Xprop_value -#define prop_fail_result frame->Xprop_fail_result -#define oclength frame->Xoclength -#define occhars frame->Xocchars -#endif - -#define ctype frame->Xctype -#define fc frame->Xfc -#define fi frame->Xfi -#define length frame->Xlength -#define max frame->Xmax -#define min frame->Xmin -#define number frame->Xnumber -#define offset frame->Xoffset -#define op frame->Xop -#define save_capture_last frame->Xsave_capture_last -#define save_offset1 frame->Xsave_offset1 -#define save_offset2 frame->Xsave_offset2 -#define save_offset3 frame->Xsave_offset3 -#define stacksave frame->Xstacksave - -#define newptrb frame->Xnewptrb - -/* When recursion is being used, local variables are allocated on the stack and -get preserved during recursion in the normal way. In this environment, fi and -i, and fc and c, can be the same variables. */ - -#else /* NO_RECURSE not defined */ -#define fi i -#define fc c - -/* Many of the following variables are used only in small blocks of the code. -My normal style of coding would have declared them within each of those blocks. -However, in order to accommodate the version of this code that uses an external -"stack" implemented on the heap, it is easier to declare them all here, so the -declarations can be cut out in a block. The only declarations within blocks -below are for variables that do not have to be preserved over a recursive call -to RMATCH(). */ - -#ifdef SUPPORT_UTF -const pcre_uchar *charptr; -#endif -const pcre_uchar *callpat; -const pcre_uchar *data; -const pcre_uchar *next; -PCRE_PUCHAR pp; -const pcre_uchar *prev; -PCRE_PUCHAR saved_eptr; - -recursion_info new_recursive; - -BOOL cur_is_word; -BOOL condition; -BOOL prev_is_word; - -#ifdef SUPPORT_UCP -int prop_type; -unsigned int prop_value; -int prop_fail_result; -int oclength; -pcre_uchar occhars[6]; -#endif - -int codelink; -int ctype; -int length; -int max; -int min; -unsigned int number; -int offset; -unsigned int op; -pcre_int32 save_capture_last; -int save_offset1, save_offset2, save_offset3; -int stacksave[REC_STACK_SAVE_MAX]; - -eptrblock newptrb; - -/* There is a special fudge for calling match() in a way that causes it to -measure the size of its basic stack frame when the stack is being used for -recursion. The second argument (ecode) being NULL triggers this behaviour. It -cannot normally ever be NULL. The return is the negated value of the frame -size. */ - -if (ecode == NULL) - { - if (rdepth == 0) - return match((PCRE_PUCHAR)&rdepth, NULL, NULL, 0, NULL, NULL, 1); - else - { - int len = (char *)&rdepth - (char *)eptr; - return (len > 0)? -len : len; - } - } -#endif /* NO_RECURSE */ - -/* To save space on the stack and in the heap frame, I have doubled up on some -of the local variables that are used only in localised parts of the code, but -still need to be preserved over recursive calls of match(). These macros define -the alternative names that are used. */ - -#define allow_zero cur_is_word -#define cbegroup condition -#define code_offset codelink -#define condassert condition -#define matched_once prev_is_word -#define foc number -#define save_mark data - -/* These statements are here to stop the compiler complaining about unitialized -variables. */ - -#ifdef SUPPORT_UCP -prop_value = 0; -prop_fail_result = 0; -#endif - - -/* This label is used for tail recursion, which is used in a few cases even -when NO_RECURSE is not defined, in order to reduce the amount of stack that is -used. Thanks to Ian Taylor for noticing this possibility and sending the -original patch. */ - -TAIL_RECURSE: - -/* OK, now we can get on with the real code of the function. Recursive calls -are specified by the macro RMATCH and RRETURN is used to return. When -NO_RECURSE is *not* defined, these just turn into a recursive call to match() -and a "return", respectively (possibly with some debugging if PCRE_DEBUG is -defined). However, RMATCH isn't like a function call because it's quite a -complicated macro. It has to be used in one particular way. This shouldn't, -however, impact performance when true recursion is being used. */ - -#ifdef SUPPORT_UTF -utf = md->utf; /* Local copy of the flag */ -#else -utf = FALSE; -#endif - -/* First check that we haven't called match() too many times, or that we -haven't exceeded the recursive call limit. */ - -if (md->match_call_count++ >= md->match_limit) RRETURN(PCRE_ERROR_MATCHLIMIT); -if (rdepth >= md->match_limit_recursion) RRETURN(PCRE_ERROR_RECURSIONLIMIT); - -/* At the start of a group with an unlimited repeat that may match an empty -string, the variable md->match_function_type is set to MATCH_CBEGROUP. It is -done this way to save having to use another function argument, which would take -up space on the stack. See also MATCH_CONDASSERT below. - -When MATCH_CBEGROUP is set, add the current subject pointer to the chain of -such remembered pointers, to be checked when we hit the closing ket, in order -to break infinite loops that match no characters. When match() is called in -other circumstances, don't add to the chain. The MATCH_CBEGROUP feature must -NOT be used with tail recursion, because the memory block that is used is on -the stack, so a new one may be required for each match(). */ - -if (md->match_function_type == MATCH_CBEGROUP) - { - newptrb.epb_saved_eptr = eptr; - newptrb.epb_prev = eptrb; - eptrb = &newptrb; - md->match_function_type = 0; - } - -/* Now start processing the opcodes. */ - -for (;;) - { - minimize = possessive = FALSE; - op = *ecode; - - switch(op) - { - case OP_MARK: - md->nomatch_mark = ecode + 2; - md->mark = NULL; /* In case previously set by assertion */ - RMATCH(eptr, ecode + PRIV(OP_lengths)[*ecode] + ecode[1], offset_top, md, - eptrb, RM55); - if ((rrc == MATCH_MATCH || rrc == MATCH_ACCEPT) && - md->mark == NULL) md->mark = ecode + 2; - - /* A return of MATCH_SKIP_ARG means that matching failed at SKIP with an - argument, and we must check whether that argument matches this MARK's - argument. It is passed back in md->start_match_ptr (an overloading of that - variable). If it does match, we reset that variable to the current subject - position and return MATCH_SKIP. Otherwise, pass back the return code - unaltered. */ - - else if (rrc == MATCH_SKIP_ARG && - STRCMP_UC_UC_TEST(ecode + 2, md->start_match_ptr) == 0) - { - md->start_match_ptr = eptr; - RRETURN(MATCH_SKIP); - } - RRETURN(rrc); - - case OP_FAIL: - RRETURN(MATCH_NOMATCH); - - case OP_COMMIT: - RMATCH(eptr, ecode + PRIV(OP_lengths)[*ecode], offset_top, md, - eptrb, RM52); - if (rrc != MATCH_NOMATCH) RRETURN(rrc); - RRETURN(MATCH_COMMIT); - - case OP_PRUNE: - RMATCH(eptr, ecode + PRIV(OP_lengths)[*ecode], offset_top, md, - eptrb, RM51); - if (rrc != MATCH_NOMATCH) RRETURN(rrc); - RRETURN(MATCH_PRUNE); - - case OP_PRUNE_ARG: - md->nomatch_mark = ecode + 2; - md->mark = NULL; /* In case previously set by assertion */ - RMATCH(eptr, ecode + PRIV(OP_lengths)[*ecode] + ecode[1], offset_top, md, - eptrb, RM56); - if ((rrc == MATCH_MATCH || rrc == MATCH_ACCEPT) && - md->mark == NULL) md->mark = ecode + 2; - if (rrc != MATCH_NOMATCH) RRETURN(rrc); - RRETURN(MATCH_PRUNE); - - case OP_SKIP: - RMATCH(eptr, ecode + PRIV(OP_lengths)[*ecode], offset_top, md, - eptrb, RM53); - if (rrc != MATCH_NOMATCH) RRETURN(rrc); - md->start_match_ptr = eptr; /* Pass back current position */ - RRETURN(MATCH_SKIP); - - /* Note that, for Perl compatibility, SKIP with an argument does NOT set - nomatch_mark. When a pattern match ends with a SKIP_ARG for which there was - not a matching mark, we have to re-run the match, ignoring the SKIP_ARG - that failed and any that precede it (either they also failed, or were not - triggered). To do this, we maintain a count of executed SKIP_ARGs. If a - SKIP_ARG gets to top level, the match is re-run with md->ignore_skip_arg - set to the count of the one that failed. */ - - case OP_SKIP_ARG: - md->skip_arg_count++; - if (md->skip_arg_count <= md->ignore_skip_arg) - { - ecode += PRIV(OP_lengths)[*ecode] + ecode[1]; - break; - } - RMATCH(eptr, ecode + PRIV(OP_lengths)[*ecode] + ecode[1], offset_top, md, - eptrb, RM57); - if (rrc != MATCH_NOMATCH) RRETURN(rrc); - - /* Pass back the current skip name by overloading md->start_match_ptr and - returning the special MATCH_SKIP_ARG return code. This will either be - caught by a matching MARK, or get to the top, where it causes a rematch - with md->ignore_skip_arg set to the value of md->skip_arg_count. */ - - md->start_match_ptr = ecode + 2; - RRETURN(MATCH_SKIP_ARG); - - /* For THEN (and THEN_ARG) we pass back the address of the opcode, so that - the branch in which it occurs can be determined. Overload the start of - match pointer to do this. */ - - case OP_THEN: - RMATCH(eptr, ecode + PRIV(OP_lengths)[*ecode], offset_top, md, - eptrb, RM54); - if (rrc != MATCH_NOMATCH) RRETURN(rrc); - md->start_match_ptr = ecode; - RRETURN(MATCH_THEN); - - case OP_THEN_ARG: - md->nomatch_mark = ecode + 2; - md->mark = NULL; /* In case previously set by assertion */ - RMATCH(eptr, ecode + PRIV(OP_lengths)[*ecode] + ecode[1], offset_top, - md, eptrb, RM58); - if ((rrc == MATCH_MATCH || rrc == MATCH_ACCEPT) && - md->mark == NULL) md->mark = ecode + 2; - if (rrc != MATCH_NOMATCH) RRETURN(rrc); - md->start_match_ptr = ecode; - RRETURN(MATCH_THEN); - - /* Handle an atomic group that does not contain any capturing parentheses. - This can be handled like an assertion. Prior to 8.13, all atomic groups - were handled this way. In 8.13, the code was changed as below for ONCE, so - that backups pass through the group and thereby reset captured values. - However, this uses a lot more stack, so in 8.20, atomic groups that do not - contain any captures generate OP_ONCE_NC, which can be handled in the old, - less stack intensive way. - - Check the alternative branches in turn - the matching won't pass the KET - for this kind of subpattern. If any one branch matches, we carry on as at - the end of a normal bracket, leaving the subject pointer, but resetting - the start-of-match value in case it was changed by \K. */ - - case OP_ONCE_NC: - prev = ecode; - saved_eptr = eptr; - save_mark = md->mark; - do - { - RMATCH(eptr, ecode + 1 + LINK_SIZE, offset_top, md, eptrb, RM64); - if (rrc == MATCH_MATCH) /* Note: _not_ MATCH_ACCEPT */ - { - mstart = md->start_match_ptr; - break; - } - if (rrc == MATCH_THEN) - { - next = ecode + GET(ecode,1); - if (md->start_match_ptr < next && - (*ecode == OP_ALT || *next == OP_ALT)) - rrc = MATCH_NOMATCH; - } - - if (rrc != MATCH_NOMATCH) RRETURN(rrc); - ecode += GET(ecode,1); - md->mark = save_mark; - } - while (*ecode == OP_ALT); - - /* If hit the end of the group (which could be repeated), fail */ - - if (*ecode != OP_ONCE_NC && *ecode != OP_ALT) RRETURN(MATCH_NOMATCH); - - /* Continue as from after the group, updating the offsets high water - mark, since extracts may have been taken. */ - - do ecode += GET(ecode, 1); while (*ecode == OP_ALT); - - offset_top = md->end_offset_top; - eptr = md->end_match_ptr; - - /* For a non-repeating ket, just continue at this level. This also - happens for a repeating ket if no characters were matched in the group. - This is the forcible breaking of infinite loops as implemented in Perl - 5.005. */ - - if (*ecode == OP_KET || eptr == saved_eptr) - { - ecode += 1+LINK_SIZE; - break; - } - - /* The repeating kets try the rest of the pattern or restart from the - preceding bracket, in the appropriate order. The second "call" of match() - uses tail recursion, to avoid using another stack frame. */ - - if (*ecode == OP_KETRMIN) - { - RMATCH(eptr, ecode + 1 + LINK_SIZE, offset_top, md, eptrb, RM65); - if (rrc != MATCH_NOMATCH) RRETURN(rrc); - ecode = prev; - goto TAIL_RECURSE; - } - else /* OP_KETRMAX */ - { - RMATCH(eptr, prev, offset_top, md, eptrb, RM66); - if (rrc != MATCH_NOMATCH) RRETURN(rrc); - ecode += 1 + LINK_SIZE; - goto TAIL_RECURSE; - } - /* Control never gets here */ - - /* Handle a capturing bracket, other than those that are possessive with an - unlimited repeat. If there is space in the offset vector, save the current - subject position in the working slot at the top of the vector. We mustn't - change the current values of the data slot, because they may be set from a - previous iteration of this group, and be referred to by a reference inside - the group. A failure to match might occur after the group has succeeded, - if something later on doesn't match. For this reason, we need to restore - the working value and also the values of the final offsets, in case they - were set by a previous iteration of the same bracket. - - If there isn't enough space in the offset vector, treat this as if it were - a non-capturing bracket. Don't worry about setting the flag for the error - case here; that is handled in the code for KET. */ - - case OP_CBRA: - case OP_SCBRA: - number = GET2(ecode, 1+LINK_SIZE); - offset = number << 1; - -#ifdef PCRE_DEBUG - printf("start bracket %d\n", number); - printf("subject="); - pchars(eptr, 16, TRUE, md); - printf("\n"); -#endif - - if (offset < md->offset_max) - { - save_offset1 = md->offset_vector[offset]; - save_offset2 = md->offset_vector[offset+1]; - save_offset3 = md->offset_vector[md->offset_end - number]; - save_capture_last = md->capture_last; - save_mark = md->mark; - - DPRINTF(("saving %d %d %d\n", save_offset1, save_offset2, save_offset3)); - md->offset_vector[md->offset_end - number] = - (int)(eptr - md->start_subject); - - for (;;) - { - if (op >= OP_SBRA) md->match_function_type = MATCH_CBEGROUP; - RMATCH(eptr, ecode + PRIV(OP_lengths)[*ecode], offset_top, md, - eptrb, RM1); - if (rrc == MATCH_ONCE) break; /* Backing up through an atomic group */ - - /* If we backed up to a THEN, check whether it is within the current - branch by comparing the address of the THEN that is passed back with - the end of the branch. If it is within the current branch, and the - branch is one of two or more alternatives (it either starts or ends - with OP_ALT), we have reached the limit of THEN's action, so convert - the return code to NOMATCH, which will cause normal backtracking to - happen from now on. Otherwise, THEN is passed back to an outer - alternative. This implements Perl's treatment of parenthesized groups, - where a group not containing | does not affect the current alternative, - that is, (X) is NOT the same as (X|(*F)). */ - - if (rrc == MATCH_THEN) - { - next = ecode + GET(ecode,1); - if (md->start_match_ptr < next && - (*ecode == OP_ALT || *next == OP_ALT)) - rrc = MATCH_NOMATCH; - } - - /* Anything other than NOMATCH is passed back. */ - - if (rrc != MATCH_NOMATCH) RRETURN(rrc); - md->capture_last = save_capture_last; - ecode += GET(ecode, 1); - md->mark = save_mark; - if (*ecode != OP_ALT) break; - } - - DPRINTF(("bracket %d failed\n", number)); - md->offset_vector[offset] = save_offset1; - md->offset_vector[offset+1] = save_offset2; - md->offset_vector[md->offset_end - number] = save_offset3; - - /* At this point, rrc will be one of MATCH_ONCE or MATCH_NOMATCH. */ - - RRETURN(rrc); - } - - /* FALL THROUGH ... Insufficient room for saving captured contents. Treat - as a non-capturing bracket. */ - - /* VVVVVVVVVVVVVVVVVVVVVVVVV */ - /* VVVVVVVVVVVVVVVVVVVVVVVVV */ - - DPRINTF(("insufficient capture room: treat as non-capturing\n")); - - /* VVVVVVVVVVVVVVVVVVVVVVVVV */ - /* VVVVVVVVVVVVVVVVVVVVVVVVV */ - - /* Non-capturing or atomic group, except for possessive with unlimited - repeat and ONCE group with no captures. Loop for all the alternatives. - - When we get to the final alternative within the brackets, we used to return - the result of a recursive call to match() whatever happened so it was - possible to reduce stack usage by turning this into a tail recursion, - except in the case of a possibly empty group. However, now that there is - the possiblity of (*THEN) occurring in the final alternative, this - optimization is no longer always possible. - - We can optimize if we know there are no (*THEN)s in the pattern; at present - this is the best that can be done. - - MATCH_ONCE is returned when the end of an atomic group is successfully - reached, but subsequent matching fails. It passes back up the tree (causing - captured values to be reset) until the original atomic group level is - reached. This is tested by comparing md->once_target with the start of the - group. At this point, the return is converted into MATCH_NOMATCH so that - previous backup points can be taken. */ - - case OP_ONCE: - case OP_BRA: - case OP_SBRA: - DPRINTF(("start non-capturing bracket\n")); - - for (;;) - { - if (op >= OP_SBRA || op == OP_ONCE) - md->match_function_type = MATCH_CBEGROUP; - - /* If this is not a possibly empty group, and there are no (*THEN)s in - the pattern, and this is the final alternative, optimize as described - above. */ - - else if (!md->hasthen && ecode[GET(ecode, 1)] != OP_ALT) - { - ecode += PRIV(OP_lengths)[*ecode]; - goto TAIL_RECURSE; - } - - /* In all other cases, we have to make another call to match(). */ - - save_mark = md->mark; - save_capture_last = md->capture_last; - RMATCH(eptr, ecode + PRIV(OP_lengths)[*ecode], offset_top, md, eptrb, - RM2); - - /* See comment in the code for capturing groups above about handling - THEN. */ - - if (rrc == MATCH_THEN) - { - next = ecode + GET(ecode,1); - if (md->start_match_ptr < next && - (*ecode == OP_ALT || *next == OP_ALT)) - rrc = MATCH_NOMATCH; - } - - if (rrc != MATCH_NOMATCH) - { - if (rrc == MATCH_ONCE) - { - const pcre_uchar *scode = ecode; - if (*scode != OP_ONCE) /* If not at start, find it */ - { - while (*scode == OP_ALT) scode += GET(scode, 1); - scode -= GET(scode, 1); - } - if (md->once_target == scode) rrc = MATCH_NOMATCH; - } - RRETURN(rrc); - } - ecode += GET(ecode, 1); - md->mark = save_mark; - if (*ecode != OP_ALT) break; - md->capture_last = save_capture_last; - } - - RRETURN(MATCH_NOMATCH); - - /* Handle possessive capturing brackets with an unlimited repeat. We come - here from BRAZERO with allow_zero set TRUE. The offset_vector values are - handled similarly to the normal case above. However, the matching is - different. The end of these brackets will always be OP_KETRPOS, which - returns MATCH_KETRPOS without going further in the pattern. By this means - we can handle the group by iteration rather than recursion, thereby - reducing the amount of stack needed. */ - - case OP_CBRAPOS: - case OP_SCBRAPOS: - allow_zero = FALSE; - - POSSESSIVE_CAPTURE: - number = GET2(ecode, 1+LINK_SIZE); - offset = number << 1; - -#ifdef PCRE_DEBUG - printf("start possessive bracket %d\n", number); - printf("subject="); - pchars(eptr, 16, TRUE, md); - printf("\n"); -#endif - - if (offset >= md->offset_max) goto POSSESSIVE_NON_CAPTURE; - - matched_once = FALSE; - code_offset = (int)(ecode - md->start_code); - - save_offset1 = md->offset_vector[offset]; - save_offset2 = md->offset_vector[offset+1]; - save_offset3 = md->offset_vector[md->offset_end - number]; - save_capture_last = md->capture_last; - - DPRINTF(("saving %d %d %d\n", save_offset1, save_offset2, save_offset3)); - - /* Each time round the loop, save the current subject position for use - when the group matches. For MATCH_MATCH, the group has matched, so we - restart it with a new subject starting position, remembering that we had - at least one match. For MATCH_NOMATCH, carry on with the alternatives, as - usual. If we haven't matched any alternatives in any iteration, check to - see if a previous iteration matched. If so, the group has matched; - continue from afterwards. Otherwise it has failed; restore the previous - capture values before returning NOMATCH. */ - - for (;;) - { - md->offset_vector[md->offset_end - number] = - (int)(eptr - md->start_subject); - if (op >= OP_SBRA) md->match_function_type = MATCH_CBEGROUP; - RMATCH(eptr, ecode + PRIV(OP_lengths)[*ecode], offset_top, md, - eptrb, RM63); - if (rrc == MATCH_KETRPOS) - { - offset_top = md->end_offset_top; - ecode = md->start_code + code_offset; - save_capture_last = md->capture_last; - matched_once = TRUE; - mstart = md->start_match_ptr; /* In case \K changed it */ - if (eptr == md->end_match_ptr) /* Matched an empty string */ - { - do ecode += GET(ecode, 1); while (*ecode == OP_ALT); - break; - } - eptr = md->end_match_ptr; - continue; - } - - /* See comment in the code for capturing groups above about handling - THEN. */ - - if (rrc == MATCH_THEN) - { - next = ecode + GET(ecode,1); - if (md->start_match_ptr < next && - (*ecode == OP_ALT || *next == OP_ALT)) - rrc = MATCH_NOMATCH; - } - - if (rrc != MATCH_NOMATCH) RRETURN(rrc); - md->capture_last = save_capture_last; - ecode += GET(ecode, 1); - if (*ecode != OP_ALT) break; - } - - if (!matched_once) - { - md->offset_vector[offset] = save_offset1; - md->offset_vector[offset+1] = save_offset2; - md->offset_vector[md->offset_end - number] = save_offset3; - } - - if (allow_zero || matched_once) - { - ecode += 1 + LINK_SIZE; - break; - } - - RRETURN(MATCH_NOMATCH); - - /* Non-capturing possessive bracket with unlimited repeat. We come here - from BRAZERO with allow_zero = TRUE. The code is similar to the above, - without the capturing complication. It is written out separately for speed - and cleanliness. */ - - case OP_BRAPOS: - case OP_SBRAPOS: - allow_zero = FALSE; - - POSSESSIVE_NON_CAPTURE: - matched_once = FALSE; - code_offset = (int)(ecode - md->start_code); - save_capture_last = md->capture_last; - - for (;;) - { - if (op >= OP_SBRA) md->match_function_type = MATCH_CBEGROUP; - RMATCH(eptr, ecode + PRIV(OP_lengths)[*ecode], offset_top, md, - eptrb, RM48); - if (rrc == MATCH_KETRPOS) - { - offset_top = md->end_offset_top; - ecode = md->start_code + code_offset; - matched_once = TRUE; - mstart = md->start_match_ptr; /* In case \K reset it */ - if (eptr == md->end_match_ptr) /* Matched an empty string */ - { - do ecode += GET(ecode, 1); while (*ecode == OP_ALT); - break; - } - eptr = md->end_match_ptr; - continue; - } - - /* See comment in the code for capturing groups above about handling - THEN. */ - - if (rrc == MATCH_THEN) - { - next = ecode + GET(ecode,1); - if (md->start_match_ptr < next && - (*ecode == OP_ALT || *next == OP_ALT)) - rrc = MATCH_NOMATCH; - } - - if (rrc != MATCH_NOMATCH) RRETURN(rrc); - ecode += GET(ecode, 1); - if (*ecode != OP_ALT) break; - md->capture_last = save_capture_last; - } - - if (matched_once || allow_zero) - { - ecode += 1 + LINK_SIZE; - break; - } - RRETURN(MATCH_NOMATCH); - - /* Control never reaches here. */ - - /* Conditional group: compilation checked that there are no more than two - branches. If the condition is false, skipping the first branch takes us - past the end of the item if there is only one branch, but that's exactly - what we want. */ - - case OP_COND: - case OP_SCOND: - - /* The variable codelink will be added to ecode when the condition is - false, to get to the second branch. Setting it to the offset to the ALT - or KET, then incrementing ecode achieves this effect. We now have ecode - pointing to the condition or callout. */ - - codelink = GET(ecode, 1); /* Offset to the second branch */ - ecode += 1 + LINK_SIZE; /* From this opcode */ - - /* Because of the way auto-callout works during compile, a callout item is - inserted between OP_COND and an assertion condition. */ - - if (*ecode == OP_CALLOUT) - { - if (PUBL(callout) != NULL) - { - PUBL(callout_block) cb; - cb.version = 2; /* Version 1 of the callout block */ - cb.callout_number = ecode[1]; - cb.offset_vector = md->offset_vector; -#if defined COMPILE_PCRE8 - cb.subject = (PCRE_SPTR)md->start_subject; -#elif defined COMPILE_PCRE16 - cb.subject = (PCRE_SPTR16)md->start_subject; -#elif defined COMPILE_PCRE32 - cb.subject = (PCRE_SPTR32)md->start_subject; -#endif - cb.subject_length = (int)(md->end_subject - md->start_subject); - cb.start_match = (int)(mstart - md->start_subject); - cb.current_position = (int)(eptr - md->start_subject); - cb.pattern_position = GET(ecode, 2); - cb.next_item_length = GET(ecode, 2 + LINK_SIZE); - cb.capture_top = offset_top/2; - cb.capture_last = md->capture_last & CAPLMASK; - /* Internal change requires this for API compatibility. */ - if (cb.capture_last == 0) cb.capture_last = -1; - cb.callout_data = md->callout_data; - cb.mark = md->nomatch_mark; - if ((rrc = (*PUBL(callout))(&cb)) > 0) RRETURN(MATCH_NOMATCH); - if (rrc < 0) RRETURN(rrc); - } - - /* Advance ecode past the callout, so it now points to the condition. We - must adjust codelink so that the value of ecode+codelink is unchanged. */ - - ecode += PRIV(OP_lengths)[OP_CALLOUT]; - codelink -= PRIV(OP_lengths)[OP_CALLOUT]; - } - - /* Test the various possible conditions */ - - condition = FALSE; - switch(condcode = *ecode) - { - case OP_RREF: /* Numbered group recursion test */ - if (md->recursive != NULL) /* Not recursing => FALSE */ - { - unsigned int recno = GET2(ecode, 1); /* Recursion group number*/ - condition = (recno == RREF_ANY || recno == md->recursive->group_num); - } - break; - - case OP_DNRREF: /* Duplicate named group recursion test */ - if (md->recursive != NULL) - { - int count = GET2(ecode, 1 + IMM2_SIZE); - pcre_uchar *slot = md->name_table + GET2(ecode, 1) * md->name_entry_size; - while (count-- > 0) - { - unsigned int recno = GET2(slot, 0); - condition = recno == md->recursive->group_num; - if (condition) break; - slot += md->name_entry_size; - } - } - break; - - case OP_CREF: /* Numbered group used test */ - offset = GET2(ecode, 1) << 1; /* Doubled ref number */ - condition = offset < offset_top && md->offset_vector[offset] >= 0; - break; - - case OP_DNCREF: /* Duplicate named group used test */ - { - int count = GET2(ecode, 1 + IMM2_SIZE); - pcre_uchar *slot = md->name_table + GET2(ecode, 1) * md->name_entry_size; - while (count-- > 0) - { - offset = GET2(slot, 0) << 1; - condition = offset < offset_top && md->offset_vector[offset] >= 0; - if (condition) break; - slot += md->name_entry_size; - } - } - break; - - case OP_DEF: /* DEFINE - always false */ - case OP_FAIL: /* From optimized (?!) condition */ - break; - - /* The condition is an assertion. Call match() to evaluate it - setting - md->match_function_type to MATCH_CONDASSERT causes it to stop at the end - of an assertion. */ - - default: - md->match_function_type = MATCH_CONDASSERT; - RMATCH(eptr, ecode, offset_top, md, NULL, RM3); - if (rrc == MATCH_MATCH) - { - if (md->end_offset_top > offset_top) - offset_top = md->end_offset_top; /* Captures may have happened */ - condition = TRUE; - - /* Advance ecode past the assertion to the start of the first branch, - but adjust it so that the general choosing code below works. If the - assertion has a quantifier that allows zero repeats we must skip over - the BRAZERO. This is a lunatic thing to do, but somebody did! */ - - if (*ecode == OP_BRAZERO) ecode++; - ecode += GET(ecode, 1); - while (*ecode == OP_ALT) ecode += GET(ecode, 1); - ecode += 1 + LINK_SIZE - PRIV(OP_lengths)[condcode]; - } - - /* PCRE doesn't allow the effect of (*THEN) to escape beyond an - assertion; it is therefore treated as NOMATCH. Any other return is an - error. */ - - else if (rrc != MATCH_NOMATCH && rrc != MATCH_THEN) - { - RRETURN(rrc); /* Need braces because of following else */ - } - break; - } - - /* Choose branch according to the condition */ - - ecode += condition? PRIV(OP_lengths)[condcode] : codelink; - - /* We are now at the branch that is to be obeyed. As there is only one, we - can use tail recursion to avoid using another stack frame, except when - there is unlimited repeat of a possibly empty group. In the latter case, a - recursive call to match() is always required, unless the second alternative - doesn't exist, in which case we can just plough on. Note that, for - compatibility with Perl, the | in a conditional group is NOT treated as - creating two alternatives. If a THEN is encountered in the branch, it - propagates out to the enclosing alternative (unless nested in a deeper set - of alternatives, of course). */ - - if (condition || ecode[-(1+LINK_SIZE)] == OP_ALT) - { - if (op != OP_SCOND) - { - goto TAIL_RECURSE; - } - - md->match_function_type = MATCH_CBEGROUP; - RMATCH(eptr, ecode, offset_top, md, eptrb, RM49); - RRETURN(rrc); - } - - /* Condition false & no alternative; continue after the group. */ - - else - { - } - break; - - - /* Before OP_ACCEPT there may be any number of OP_CLOSE opcodes, - to close any currently open capturing brackets. */ - - case OP_CLOSE: - number = GET2(ecode, 1); /* Must be less than 65536 */ - offset = number << 1; - -#ifdef PCRE_DEBUG - printf("end bracket %d at *ACCEPT", number); - printf("\n"); -#endif - - md->capture_last = (md->capture_last & OVFLMASK) | number; - if (offset >= md->offset_max) md->capture_last |= OVFLBIT; else - { - md->offset_vector[offset] = - md->offset_vector[md->offset_end - number]; - md->offset_vector[offset+1] = (int)(eptr - md->start_subject); - - /* If this group is at or above the current highwater mark, ensure that - any groups between the current high water mark and this group are marked - unset and then update the high water mark. */ - - if (offset >= offset_top) - { - register int *iptr = md->offset_vector + offset_top; - register int *iend = md->offset_vector + offset; - while (iptr < iend) *iptr++ = -1; - offset_top = offset + 2; - } - } - ecode += 1 + IMM2_SIZE; - break; - - - /* End of the pattern, either real or forced. */ - - case OP_END: - case OP_ACCEPT: - case OP_ASSERT_ACCEPT: - - /* If we have matched an empty string, fail if not in an assertion and not - in a recursion if either PCRE_NOTEMPTY is set, or if PCRE_NOTEMPTY_ATSTART - is set and we have matched at the start of the subject. In both cases, - backtracking will then try other alternatives, if any. */ - - if (eptr == mstart && op != OP_ASSERT_ACCEPT && - md->recursive == NULL && - (md->notempty || - (md->notempty_atstart && - mstart == md->start_subject + md->start_offset))) - RRETURN(MATCH_NOMATCH); - - /* Otherwise, we have a match. */ - - md->end_match_ptr = eptr; /* Record where we ended */ - md->end_offset_top = offset_top; /* and how many extracts were taken */ - md->start_match_ptr = mstart; /* and the start (\K can modify) */ - - /* For some reason, the macros don't work properly if an expression is - given as the argument to RRETURN when the heap is in use. */ - - rrc = (op == OP_END)? MATCH_MATCH : MATCH_ACCEPT; - RRETURN(rrc); - - /* Assertion brackets. Check the alternative branches in turn - the - matching won't pass the KET for an assertion. If any one branch matches, - the assertion is true. Lookbehind assertions have an OP_REVERSE item at the - start of each branch to move the current point backwards, so the code at - this level is identical to the lookahead case. When the assertion is part - of a condition, we want to return immediately afterwards. The caller of - this incarnation of the match() function will have set MATCH_CONDASSERT in - md->match_function type, and one of these opcodes will be the first opcode - that is processed. We use a local variable that is preserved over calls to - match() to remember this case. */ - - case OP_ASSERT: - case OP_ASSERTBACK: - save_mark = md->mark; - if (md->match_function_type == MATCH_CONDASSERT) - { - condassert = TRUE; - md->match_function_type = 0; - } - else condassert = FALSE; - - /* Loop for each branch */ - - do - { - RMATCH(eptr, ecode + 1 + LINK_SIZE, offset_top, md, NULL, RM4); - - /* A match means that the assertion is true; break out of the loop - that matches its alternatives. */ - - if (rrc == MATCH_MATCH || rrc == MATCH_ACCEPT) - { - mstart = md->start_match_ptr; /* In case \K reset it */ - break; - } - - /* If not matched, restore the previous mark setting. */ - - md->mark = save_mark; - - /* See comment in the code for capturing groups above about handling - THEN. */ - - if (rrc == MATCH_THEN) - { - next = ecode + GET(ecode,1); - if (md->start_match_ptr < next && - (*ecode == OP_ALT || *next == OP_ALT)) - rrc = MATCH_NOMATCH; - } - - /* Anything other than NOMATCH causes the entire assertion to fail, - passing back the return code. This includes COMMIT, SKIP, PRUNE and an - uncaptured THEN, which means they take their normal effect. This - consistent approach does not always have exactly the same effect as in - Perl. */ - - if (rrc != MATCH_NOMATCH) RRETURN(rrc); - ecode += GET(ecode, 1); - } - while (*ecode == OP_ALT); /* Continue for next alternative */ - - /* If we have tried all the alternative branches, the assertion has - failed. If not, we broke out after a match. */ - - if (*ecode == OP_KET) RRETURN(MATCH_NOMATCH); - - /* If checking an assertion for a condition, return MATCH_MATCH. */ - - if (condassert) RRETURN(MATCH_MATCH); - - /* Continue from after a successful assertion, updating the offsets high - water mark, since extracts may have been taken during the assertion. */ - - do ecode += GET(ecode,1); while (*ecode == OP_ALT); - ecode += 1 + LINK_SIZE; - offset_top = md->end_offset_top; - continue; - - /* Negative assertion: all branches must fail to match for the assertion to - succeed. */ - - case OP_ASSERT_NOT: - case OP_ASSERTBACK_NOT: - save_mark = md->mark; - if (md->match_function_type == MATCH_CONDASSERT) - { - condassert = TRUE; - md->match_function_type = 0; - } - else condassert = FALSE; - - /* Loop for each alternative branch. */ - - do - { - RMATCH(eptr, ecode + 1 + LINK_SIZE, offset_top, md, NULL, RM5); - md->mark = save_mark; /* Always restore the mark setting */ - - switch(rrc) - { - case MATCH_MATCH: /* A successful match means */ - case MATCH_ACCEPT: /* the assertion has failed. */ - RRETURN(MATCH_NOMATCH); - - case MATCH_NOMATCH: /* Carry on with next branch */ - break; - - /* See comment in the code for capturing groups above about handling - THEN. */ - - case MATCH_THEN: - next = ecode + GET(ecode,1); - if (md->start_match_ptr < next && - (*ecode == OP_ALT || *next == OP_ALT)) - { - rrc = MATCH_NOMATCH; - break; - } - /* Otherwise fall through. */ - - /* COMMIT, SKIP, PRUNE, and an uncaptured THEN cause the whole - assertion to fail to match, without considering any more alternatives. - Failing to match means the assertion is true. This is a consistent - approach, but does not always have the same effect as in Perl. */ - - case MATCH_COMMIT: - case MATCH_SKIP: - case MATCH_SKIP_ARG: - case MATCH_PRUNE: - do ecode += GET(ecode,1); while (*ecode == OP_ALT); - goto NEG_ASSERT_TRUE; /* Break out of alternation loop */ - - /* Anything else is an error */ - - default: - RRETURN(rrc); - } - - /* Continue with next branch */ - - ecode += GET(ecode,1); - } - while (*ecode == OP_ALT); - - /* All branches in the assertion failed to match. */ - - NEG_ASSERT_TRUE: - if (condassert) RRETURN(MATCH_MATCH); /* Condition assertion */ - ecode += 1 + LINK_SIZE; /* Continue with current branch */ - continue; - - /* Move the subject pointer back. This occurs only at the start of - each branch of a lookbehind assertion. If we are too close to the start to - move back, this match function fails. When working with UTF-8 we move - back a number of characters, not bytes. */ - - case OP_REVERSE: -#ifdef SUPPORT_UTF - if (utf) - { - i = GET(ecode, 1); - while (i-- > 0) - { - eptr--; - if (eptr < md->start_subject) RRETURN(MATCH_NOMATCH); - BACKCHAR(eptr); - } - } - else -#endif - - /* No UTF-8 support, or not in UTF-8 mode: count is byte count */ - - { - eptr -= GET(ecode, 1); - if (eptr < md->start_subject) RRETURN(MATCH_NOMATCH); - } - - /* Save the earliest consulted character, then skip to next op code */ - - if (eptr < md->start_used_ptr) md->start_used_ptr = eptr; - ecode += 1 + LINK_SIZE; - break; - - /* The callout item calls an external function, if one is provided, passing - details of the match so far. This is mainly for debugging, though the - function is able to force a failure. */ - - case OP_CALLOUT: - if (PUBL(callout) != NULL) - { - PUBL(callout_block) cb; - cb.version = 2; /* Version 1 of the callout block */ - cb.callout_number = ecode[1]; - cb.offset_vector = md->offset_vector; -#if defined COMPILE_PCRE8 - cb.subject = (PCRE_SPTR)md->start_subject; -#elif defined COMPILE_PCRE16 - cb.subject = (PCRE_SPTR16)md->start_subject; -#elif defined COMPILE_PCRE32 - cb.subject = (PCRE_SPTR32)md->start_subject; -#endif - cb.subject_length = (int)(md->end_subject - md->start_subject); - cb.start_match = (int)(mstart - md->start_subject); - cb.current_position = (int)(eptr - md->start_subject); - cb.pattern_position = GET(ecode, 2); - cb.next_item_length = GET(ecode, 2 + LINK_SIZE); - cb.capture_top = offset_top/2; - cb.capture_last = md->capture_last & CAPLMASK; - /* Internal change requires this for API compatibility. */ - if (cb.capture_last == 0) cb.capture_last = -1; - cb.callout_data = md->callout_data; - cb.mark = md->nomatch_mark; - if ((rrc = (*PUBL(callout))(&cb)) > 0) RRETURN(MATCH_NOMATCH); - if (rrc < 0) RRETURN(rrc); - } - ecode += 2 + 2*LINK_SIZE; - break; - - /* Recursion either matches the current regex, or some subexpression. The - offset data is the offset to the starting bracket from the start of the - whole pattern. (This is so that it works from duplicated subpatterns.) - - The state of the capturing groups is preserved over recursion, and - re-instated afterwards. We don't know how many are started and not yet - finished (offset_top records the completed total) so we just have to save - all the potential data. There may be up to 65535 such values, which is too - large to put on the stack, but using malloc for small numbers seems - expensive. As a compromise, the stack is used when there are no more than - REC_STACK_SAVE_MAX values to store; otherwise malloc is used. - - There are also other values that have to be saved. We use a chained - sequence of blocks that actually live on the stack. Thanks to Robin Houston - for the original version of this logic. It has, however, been hacked around - a lot, so he is not to blame for the current way it works. */ - - case OP_RECURSE: - { - recursion_info *ri; - unsigned int recno; - - callpat = md->start_code + GET(ecode, 1); - recno = (callpat == md->start_code)? 0 : - GET2(callpat, 1 + LINK_SIZE); - - /* Check for repeating a recursion without advancing the subject pointer. - This should catch convoluted mutual recursions. (Some simple cases are - caught at compile time.) */ - - for (ri = md->recursive; ri != NULL; ri = ri->prevrec) - if (recno == ri->group_num && eptr == ri->subject_position) - RRETURN(PCRE_ERROR_RECURSELOOP); - - /* Add to "recursing stack" */ - - new_recursive.group_num = recno; - new_recursive.saved_capture_last = md->capture_last; - new_recursive.subject_position = eptr; - new_recursive.prevrec = md->recursive; - md->recursive = &new_recursive; - - /* Where to continue from afterwards */ - - ecode += 1 + LINK_SIZE; - - /* Now save the offset data */ - - new_recursive.saved_max = md->offset_end; - if (new_recursive.saved_max <= REC_STACK_SAVE_MAX) - new_recursive.offset_save = stacksave; - else - { - new_recursive.offset_save = - (int *)(PUBL(malloc))(new_recursive.saved_max * sizeof(int)); - if (new_recursive.offset_save == NULL) RRETURN(PCRE_ERROR_NOMEMORY); - } - memcpy(new_recursive.offset_save, md->offset_vector, - new_recursive.saved_max * sizeof(int)); - - /* OK, now we can do the recursion. After processing each alternative, - restore the offset data and the last captured value. If there were nested - recursions, md->recursive might be changed, so reset it before looping. - */ - - DPRINTF(("Recursing into group %d\n", new_recursive.group_num)); - cbegroup = (*callpat >= OP_SBRA); - do - { - if (cbegroup) md->match_function_type = MATCH_CBEGROUP; - RMATCH(eptr, callpat + PRIV(OP_lengths)[*callpat], offset_top, - md, eptrb, RM6); - memcpy(md->offset_vector, new_recursive.offset_save, - new_recursive.saved_max * sizeof(int)); - md->capture_last = new_recursive.saved_capture_last; - md->recursive = new_recursive.prevrec; - if (rrc == MATCH_MATCH || rrc == MATCH_ACCEPT) - { - DPRINTF(("Recursion matched\n")); - if (new_recursive.offset_save != stacksave) - (PUBL(free))(new_recursive.offset_save); - - /* Set where we got to in the subject, and reset the start in case - it was changed by \K. This *is* propagated back out of a recursion, - for Perl compatibility. */ - - eptr = md->end_match_ptr; - mstart = md->start_match_ptr; - goto RECURSION_MATCHED; /* Exit loop; end processing */ - } - - /* PCRE does not allow THEN, SKIP, PRUNE or COMMIT to escape beyond a - recursion; they cause a NOMATCH for the entire recursion. These codes - are defined in a range that can be tested for. */ - - if (rrc >= MATCH_BACKTRACK_MIN && rrc <= MATCH_BACKTRACK_MAX) - { - if (new_recursive.offset_save != stacksave) - (PUBL(free))(new_recursive.offset_save); - RRETURN(MATCH_NOMATCH); - } - - /* Any return code other than NOMATCH is an error. */ - - if (rrc != MATCH_NOMATCH) - { - DPRINTF(("Recursion gave error %d\n", rrc)); - if (new_recursive.offset_save != stacksave) - (PUBL(free))(new_recursive.offset_save); - RRETURN(rrc); - } - - md->recursive = &new_recursive; - callpat += GET(callpat, 1); - } - while (*callpat == OP_ALT); - - DPRINTF(("Recursion didn't match\n")); - md->recursive = new_recursive.prevrec; - if (new_recursive.offset_save != stacksave) - (PUBL(free))(new_recursive.offset_save); - RRETURN(MATCH_NOMATCH); - } - - RECURSION_MATCHED: - break; - - /* An alternation is the end of a branch; scan along to find the end of the - bracketed group and go to there. */ - - case OP_ALT: - do ecode += GET(ecode,1); while (*ecode == OP_ALT); - break; - - /* BRAZERO, BRAMINZERO and SKIPZERO occur just before a bracket group, - indicating that it may occur zero times. It may repeat infinitely, or not - at all - i.e. it could be ()* or ()? or even (){0} in the pattern. Brackets - with fixed upper repeat limits are compiled as a number of copies, with the - optional ones preceded by BRAZERO or BRAMINZERO. */ - - case OP_BRAZERO: - next = ecode + 1; - RMATCH(eptr, next, offset_top, md, eptrb, RM10); - if (rrc != MATCH_NOMATCH) RRETURN(rrc); - do next += GET(next, 1); while (*next == OP_ALT); - ecode = next + 1 + LINK_SIZE; - break; - - case OP_BRAMINZERO: - next = ecode + 1; - do next += GET(next, 1); while (*next == OP_ALT); - RMATCH(eptr, next + 1+LINK_SIZE, offset_top, md, eptrb, RM11); - if (rrc != MATCH_NOMATCH) RRETURN(rrc); - ecode++; - break; - - case OP_SKIPZERO: - next = ecode+1; - do next += GET(next,1); while (*next == OP_ALT); - ecode = next + 1 + LINK_SIZE; - break; - - /* BRAPOSZERO occurs before a possessive bracket group. Don't do anything - here; just jump to the group, with allow_zero set TRUE. */ - - case OP_BRAPOSZERO: - op = *(++ecode); - allow_zero = TRUE; - if (op == OP_CBRAPOS || op == OP_SCBRAPOS) goto POSSESSIVE_CAPTURE; - goto POSSESSIVE_NON_CAPTURE; - - /* End of a group, repeated or non-repeating. */ - - case OP_KET: - case OP_KETRMIN: - case OP_KETRMAX: - case OP_KETRPOS: - prev = ecode - GET(ecode, 1); - - /* If this was a group that remembered the subject start, in order to break - infinite repeats of empty string matches, retrieve the subject start from - the chain. Otherwise, set it NULL. */ - - if (*prev >= OP_SBRA || *prev == OP_ONCE) - { - saved_eptr = eptrb->epb_saved_eptr; /* Value at start of group */ - eptrb = eptrb->epb_prev; /* Backup to previous group */ - } - else saved_eptr = NULL; - - /* If we are at the end of an assertion group or a non-capturing atomic - group, stop matching and return MATCH_MATCH, but record the current high - water mark for use by positive assertions. We also need to record the match - start in case it was changed by \K. */ - - if ((*prev >= OP_ASSERT && *prev <= OP_ASSERTBACK_NOT) || - *prev == OP_ONCE_NC) - { - md->end_match_ptr = eptr; /* For ONCE_NC */ - md->end_offset_top = offset_top; - md->start_match_ptr = mstart; - RRETURN(MATCH_MATCH); /* Sets md->mark */ - } - - /* For capturing groups we have to check the group number back at the start - and if necessary complete handling an extraction by setting the offsets and - bumping the high water mark. Whole-pattern recursion is coded as a recurse - into group 0, so it won't be picked up here. Instead, we catch it when the - OP_END is reached. Other recursion is handled here. We just have to record - the current subject position and start match pointer and give a MATCH - return. */ - - if (*prev == OP_CBRA || *prev == OP_SCBRA || - *prev == OP_CBRAPOS || *prev == OP_SCBRAPOS) - { - number = GET2(prev, 1+LINK_SIZE); - offset = number << 1; - -#ifdef PCRE_DEBUG - printf("end bracket %d", number); - printf("\n"); -#endif - - /* Handle a recursively called group. */ - - if (md->recursive != NULL && md->recursive->group_num == number) - { - md->end_match_ptr = eptr; - md->start_match_ptr = mstart; - RRETURN(MATCH_MATCH); - } - - /* Deal with capturing */ - - md->capture_last = (md->capture_last & OVFLMASK) | number; - if (offset >= md->offset_max) md->capture_last |= OVFLBIT; else - { - /* If offset is greater than offset_top, it means that we are - "skipping" a capturing group, and that group's offsets must be marked - unset. In earlier versions of PCRE, all the offsets were unset at the - start of matching, but this doesn't work because atomic groups and - assertions can cause a value to be set that should later be unset. - Example: matching /(?>(a))b|(a)c/ against "ac". This sets group 1 as - part of the atomic group, but this is not on the final matching path, - so must be unset when 2 is set. (If there is no group 2, there is no - problem, because offset_top will then be 2, indicating no capture.) */ - - if (offset > offset_top) - { - register int *iptr = md->offset_vector + offset_top; - register int *iend = md->offset_vector + offset; - while (iptr < iend) *iptr++ = -1; - } - - /* Now make the extraction */ - - md->offset_vector[offset] = - md->offset_vector[md->offset_end - number]; - md->offset_vector[offset+1] = (int)(eptr - md->start_subject); - if (offset_top <= offset) offset_top = offset + 2; - } - } - - /* OP_KETRPOS is a possessive repeating ket. Remember the current position, - and return the MATCH_KETRPOS. This makes it possible to do the repeats one - at a time from the outer level, thus saving stack. This must precede the - empty string test - in this case that test is done at the outer level. */ - - if (*ecode == OP_KETRPOS) - { - md->start_match_ptr = mstart; /* In case \K reset it */ - md->end_match_ptr = eptr; - md->end_offset_top = offset_top; - RRETURN(MATCH_KETRPOS); - } - - /* For an ordinary non-repeating ket, just continue at this level. This - also happens for a repeating ket if no characters were matched in the - group. This is the forcible breaking of infinite loops as implemented in - Perl 5.005. For a non-repeating atomic group that includes captures, - establish a backup point by processing the rest of the pattern at a lower - level. If this results in a NOMATCH return, pass MATCH_ONCE back to the - original OP_ONCE level, thereby bypassing intermediate backup points, but - resetting any captures that happened along the way. */ - - if (*ecode == OP_KET || eptr == saved_eptr) - { - if (*prev == OP_ONCE) - { - RMATCH(eptr, ecode + 1 + LINK_SIZE, offset_top, md, eptrb, RM12); - if (rrc != MATCH_NOMATCH) RRETURN(rrc); - md->once_target = prev; /* Level at which to change to MATCH_NOMATCH */ - RRETURN(MATCH_ONCE); - } - ecode += 1 + LINK_SIZE; /* Carry on at this level */ - break; - } - - /* The normal repeating kets try the rest of the pattern or restart from - the preceding bracket, in the appropriate order. In the second case, we can - use tail recursion to avoid using another stack frame, unless we have an - an atomic group or an unlimited repeat of a group that can match an empty - string. */ - - if (*ecode == OP_KETRMIN) - { - RMATCH(eptr, ecode + 1 + LINK_SIZE, offset_top, md, eptrb, RM7); - if (rrc != MATCH_NOMATCH) RRETURN(rrc); - if (*prev == OP_ONCE) - { - RMATCH(eptr, prev, offset_top, md, eptrb, RM8); - if (rrc != MATCH_NOMATCH) RRETURN(rrc); - md->once_target = prev; /* Level at which to change to MATCH_NOMATCH */ - RRETURN(MATCH_ONCE); - } - if (*prev >= OP_SBRA) /* Could match an empty string */ - { - RMATCH(eptr, prev, offset_top, md, eptrb, RM50); - RRETURN(rrc); - } - ecode = prev; - goto TAIL_RECURSE; - } - else /* OP_KETRMAX */ - { - RMATCH(eptr, prev, offset_top, md, eptrb, RM13); - if (rrc == MATCH_ONCE && md->once_target == prev) rrc = MATCH_NOMATCH; - if (rrc != MATCH_NOMATCH) RRETURN(rrc); - if (*prev == OP_ONCE) - { - RMATCH(eptr, ecode + 1 + LINK_SIZE, offset_top, md, eptrb, RM9); - if (rrc != MATCH_NOMATCH) RRETURN(rrc); - md->once_target = prev; - RRETURN(MATCH_ONCE); - } - ecode += 1 + LINK_SIZE; - goto TAIL_RECURSE; - } - /* Control never gets here */ - - /* Not multiline mode: start of subject assertion, unless notbol. */ - - case OP_CIRC: - if (md->notbol && eptr == md->start_subject) RRETURN(MATCH_NOMATCH); - - /* Start of subject assertion */ - - case OP_SOD: - if (eptr != md->start_subject) RRETURN(MATCH_NOMATCH); - ecode++; - break; - - /* Multiline mode: start of subject unless notbol, or after any newline. */ - - case OP_CIRCM: - if (md->notbol && eptr == md->start_subject) RRETURN(MATCH_NOMATCH); - if (eptr != md->start_subject && - (eptr == md->end_subject || !WAS_NEWLINE(eptr))) - RRETURN(MATCH_NOMATCH); - ecode++; - break; - - /* Start of match assertion */ - - case OP_SOM: - if (eptr != md->start_subject + md->start_offset) RRETURN(MATCH_NOMATCH); - ecode++; - break; - - /* Reset the start of match point */ - - case OP_SET_SOM: - mstart = eptr; - ecode++; - break; - - /* Multiline mode: assert before any newline, or before end of subject - unless noteol is set. */ - - case OP_DOLLM: - if (eptr < md->end_subject) - { - if (!IS_NEWLINE(eptr)) - { - if (md->partial != 0 && - eptr + 1 >= md->end_subject && - NLBLOCK->nltype == NLTYPE_FIXED && - NLBLOCK->nllen == 2 && - UCHAR21TEST(eptr) == NLBLOCK->nl[0]) - { - md->hitend = TRUE; - if (md->partial > 1) RRETURN(PCRE_ERROR_PARTIAL); - } - RRETURN(MATCH_NOMATCH); - } - } - else - { - if (md->noteol) RRETURN(MATCH_NOMATCH); - SCHECK_PARTIAL(); - } - ecode++; - break; - - /* Not multiline mode: assert before a terminating newline or before end of - subject unless noteol is set. */ - - case OP_DOLL: - if (md->noteol) RRETURN(MATCH_NOMATCH); - if (!md->endonly) goto ASSERT_NL_OR_EOS; - - /* ... else fall through for endonly */ - - /* End of subject assertion (\z) */ - - case OP_EOD: - if (eptr < md->end_subject) RRETURN(MATCH_NOMATCH); - SCHECK_PARTIAL(); - ecode++; - break; - - /* End of subject or ending \n assertion (\Z) */ - - case OP_EODN: - ASSERT_NL_OR_EOS: - if (eptr < md->end_subject && - (!IS_NEWLINE(eptr) || eptr != md->end_subject - md->nllen)) - { - if (md->partial != 0 && - eptr + 1 >= md->end_subject && - NLBLOCK->nltype == NLTYPE_FIXED && - NLBLOCK->nllen == 2 && - UCHAR21TEST(eptr) == NLBLOCK->nl[0]) - { - md->hitend = TRUE; - if (md->partial > 1) RRETURN(PCRE_ERROR_PARTIAL); - } - RRETURN(MATCH_NOMATCH); - } - - /* Either at end of string or \n before end. */ - - SCHECK_PARTIAL(); - ecode++; - break; - - /* Word boundary assertions */ - - case OP_NOT_WORD_BOUNDARY: - case OP_WORD_BOUNDARY: - { - - /* Find out if the previous and current characters are "word" characters. - It takes a bit more work in UTF-8 mode. Characters > 255 are assumed to - be "non-word" characters. Remember the earliest consulted character for - partial matching. */ - -#ifdef SUPPORT_UTF - if (utf) - { - /* Get status of previous character */ - - if (eptr == md->start_subject) prev_is_word = FALSE; else - { - PCRE_PUCHAR lastptr = eptr - 1; - BACKCHAR(lastptr); - if (lastptr < md->start_used_ptr) md->start_used_ptr = lastptr; - GETCHAR(c, lastptr); -#ifdef SUPPORT_UCP - if (md->use_ucp) - { - if (c == '_') prev_is_word = TRUE; else - { - int cat = UCD_CATEGORY(c); - prev_is_word = (cat == ucp_L || cat == ucp_N); - } - } - else -#endif - prev_is_word = c < 256 && (md->ctypes[c] & ctype_word) != 0; - } - - /* Get status of next character */ - - if (eptr >= md->end_subject) - { - SCHECK_PARTIAL(); - cur_is_word = FALSE; - } - else - { - GETCHAR(c, eptr); -#ifdef SUPPORT_UCP - if (md->use_ucp) - { - if (c == '_') cur_is_word = TRUE; else - { - int cat = UCD_CATEGORY(c); - cur_is_word = (cat == ucp_L || cat == ucp_N); - } - } - else -#endif - cur_is_word = c < 256 && (md->ctypes[c] & ctype_word) != 0; - } - } - else -#endif - - /* Not in UTF-8 mode, but we may still have PCRE_UCP set, and for - consistency with the behaviour of \w we do use it in this case. */ - - { - /* Get status of previous character */ - - if (eptr == md->start_subject) prev_is_word = FALSE; else - { - if (eptr <= md->start_used_ptr) md->start_used_ptr = eptr - 1; -#ifdef SUPPORT_UCP - if (md->use_ucp) - { - c = eptr[-1]; - if (c == '_') prev_is_word = TRUE; else - { - int cat = UCD_CATEGORY(c); - prev_is_word = (cat == ucp_L || cat == ucp_N); - } - } - else -#endif - prev_is_word = MAX_255(eptr[-1]) - && ((md->ctypes[eptr[-1]] & ctype_word) != 0); - } - - /* Get status of next character */ - - if (eptr >= md->end_subject) - { - SCHECK_PARTIAL(); - cur_is_word = FALSE; - } - else -#ifdef SUPPORT_UCP - if (md->use_ucp) - { - c = *eptr; - if (c == '_') cur_is_word = TRUE; else - { - int cat = UCD_CATEGORY(c); - cur_is_word = (cat == ucp_L || cat == ucp_N); - } - } - else -#endif - cur_is_word = MAX_255(*eptr) - && ((md->ctypes[*eptr] & ctype_word) != 0); - } - - /* Now see if the situation is what we want */ - - if ((*ecode++ == OP_WORD_BOUNDARY)? - cur_is_word == prev_is_word : cur_is_word != prev_is_word) - RRETURN(MATCH_NOMATCH); - } - break; - - /* Match any single character type except newline; have to take care with - CRLF newlines and partial matching. */ - - case OP_ANY: - if (IS_NEWLINE(eptr)) RRETURN(MATCH_NOMATCH); - if (md->partial != 0 && - eptr + 1 >= md->end_subject && - NLBLOCK->nltype == NLTYPE_FIXED && - NLBLOCK->nllen == 2 && - UCHAR21TEST(eptr) == NLBLOCK->nl[0]) - { - md->hitend = TRUE; - if (md->partial > 1) RRETURN(PCRE_ERROR_PARTIAL); - } - - /* Fall through */ - - /* Match any single character whatsoever. */ - - case OP_ALLANY: - if (eptr >= md->end_subject) /* DO NOT merge the eptr++ here; it must */ - { /* not be updated before SCHECK_PARTIAL. */ - SCHECK_PARTIAL(); - RRETURN(MATCH_NOMATCH); - } - eptr++; -#ifdef SUPPORT_UTF - if (utf) ACROSSCHAR(eptr < md->end_subject, *eptr, eptr++); -#endif - ecode++; - break; - - /* Match a single byte, even in UTF-8 mode. This opcode really does match - any byte, even newline, independent of the setting of PCRE_DOTALL. */ - - case OP_ANYBYTE: - if (eptr >= md->end_subject) /* DO NOT merge the eptr++ here; it must */ - { /* not be updated before SCHECK_PARTIAL. */ - SCHECK_PARTIAL(); - RRETURN(MATCH_NOMATCH); - } - eptr++; - ecode++; - break; - - case OP_NOT_DIGIT: - if (eptr >= md->end_subject) - { - SCHECK_PARTIAL(); - RRETURN(MATCH_NOMATCH); - } - GETCHARINCTEST(c, eptr); - if ( -#if defined SUPPORT_UTF || !(defined COMPILE_PCRE8) - c < 256 && -#endif - (md->ctypes[c] & ctype_digit) != 0 - ) - RRETURN(MATCH_NOMATCH); - ecode++; - break; - - case OP_DIGIT: - if (eptr >= md->end_subject) - { - SCHECK_PARTIAL(); - RRETURN(MATCH_NOMATCH); - } - GETCHARINCTEST(c, eptr); - if ( -#if defined SUPPORT_UTF || !(defined COMPILE_PCRE8) - c > 255 || -#endif - (md->ctypes[c] & ctype_digit) == 0 - ) - RRETURN(MATCH_NOMATCH); - ecode++; - break; - - case OP_NOT_WHITESPACE: - if (eptr >= md->end_subject) - { - SCHECK_PARTIAL(); - RRETURN(MATCH_NOMATCH); - } - GETCHARINCTEST(c, eptr); - if ( -#if defined SUPPORT_UTF || !(defined COMPILE_PCRE8) - c < 256 && -#endif - (md->ctypes[c] & ctype_space) != 0 - ) - RRETURN(MATCH_NOMATCH); - ecode++; - break; - - case OP_WHITESPACE: - if (eptr >= md->end_subject) - { - SCHECK_PARTIAL(); - RRETURN(MATCH_NOMATCH); - } - GETCHARINCTEST(c, eptr); - if ( -#if defined SUPPORT_UTF || !(defined COMPILE_PCRE8) - c > 255 || -#endif - (md->ctypes[c] & ctype_space) == 0 - ) - RRETURN(MATCH_NOMATCH); - ecode++; - break; - - case OP_NOT_WORDCHAR: - if (eptr >= md->end_subject) - { - SCHECK_PARTIAL(); - RRETURN(MATCH_NOMATCH); - } - GETCHARINCTEST(c, eptr); - if ( -#if defined SUPPORT_UTF || !(defined COMPILE_PCRE8) - c < 256 && -#endif - (md->ctypes[c] & ctype_word) != 0 - ) - RRETURN(MATCH_NOMATCH); - ecode++; - break; - - case OP_WORDCHAR: - if (eptr >= md->end_subject) - { - SCHECK_PARTIAL(); - RRETURN(MATCH_NOMATCH); - } - GETCHARINCTEST(c, eptr); - if ( -#if defined SUPPORT_UTF || !(defined COMPILE_PCRE8) - c > 255 || -#endif - (md->ctypes[c] & ctype_word) == 0 - ) - RRETURN(MATCH_NOMATCH); - ecode++; - break; - - case OP_ANYNL: - if (eptr >= md->end_subject) - { - SCHECK_PARTIAL(); - RRETURN(MATCH_NOMATCH); - } - GETCHARINCTEST(c, eptr); - switch(c) - { - default: RRETURN(MATCH_NOMATCH); - - case CHAR_CR: - if (eptr >= md->end_subject) - { - SCHECK_PARTIAL(); - } - else if (UCHAR21TEST(eptr) == CHAR_LF) eptr++; - break; - - case CHAR_LF: - break; - - case CHAR_VT: - case CHAR_FF: - case CHAR_NEL: -#ifndef EBCDIC - case 0x2028: - case 0x2029: -#endif /* Not EBCDIC */ - if (md->bsr_anycrlf) RRETURN(MATCH_NOMATCH); - break; - } - ecode++; - break; - - case OP_NOT_HSPACE: - if (eptr >= md->end_subject) - { - SCHECK_PARTIAL(); - RRETURN(MATCH_NOMATCH); - } - GETCHARINCTEST(c, eptr); - switch(c) - { - HSPACE_CASES: RRETURN(MATCH_NOMATCH); /* Byte and multibyte cases */ - default: break; - } - ecode++; - break; - - case OP_HSPACE: - if (eptr >= md->end_subject) - { - SCHECK_PARTIAL(); - RRETURN(MATCH_NOMATCH); - } - GETCHARINCTEST(c, eptr); - switch(c) - { - HSPACE_CASES: break; /* Byte and multibyte cases */ - default: RRETURN(MATCH_NOMATCH); - } - ecode++; - break; - - case OP_NOT_VSPACE: - if (eptr >= md->end_subject) - { - SCHECK_PARTIAL(); - RRETURN(MATCH_NOMATCH); - } - GETCHARINCTEST(c, eptr); - switch(c) - { - VSPACE_CASES: RRETURN(MATCH_NOMATCH); - default: break; - } - ecode++; - break; - - case OP_VSPACE: - if (eptr >= md->end_subject) - { - SCHECK_PARTIAL(); - RRETURN(MATCH_NOMATCH); - } - GETCHARINCTEST(c, eptr); - switch(c) - { - VSPACE_CASES: break; - default: RRETURN(MATCH_NOMATCH); - } - ecode++; - break; - -#ifdef SUPPORT_UCP - /* Check the next character by Unicode property. We will get here only - if the support is in the binary; otherwise a compile-time error occurs. */ - - case OP_PROP: - case OP_NOTPROP: - if (eptr >= md->end_subject) - { - SCHECK_PARTIAL(); - RRETURN(MATCH_NOMATCH); - } - GETCHARINCTEST(c, eptr); - { - const pcre_uint32 *cp; - const ucd_record *prop = GET_UCD(c); - - switch(ecode[1]) - { - case PT_ANY: - if (op == OP_NOTPROP) RRETURN(MATCH_NOMATCH); - break; - - case PT_LAMP: - if ((prop->chartype == ucp_Lu || - prop->chartype == ucp_Ll || - prop->chartype == ucp_Lt) == (op == OP_NOTPROP)) - RRETURN(MATCH_NOMATCH); - break; - - case PT_GC: - if ((ecode[2] != PRIV(ucp_gentype)[prop->chartype]) == (op == OP_PROP)) - RRETURN(MATCH_NOMATCH); - break; - - case PT_PC: - if ((ecode[2] != prop->chartype) == (op == OP_PROP)) - RRETURN(MATCH_NOMATCH); - break; - - case PT_SC: - if ((ecode[2] != prop->script) == (op == OP_PROP)) - RRETURN(MATCH_NOMATCH); - break; - - /* These are specials */ - - case PT_ALNUM: - if ((PRIV(ucp_gentype)[prop->chartype] == ucp_L || - PRIV(ucp_gentype)[prop->chartype] == ucp_N) == (op == OP_NOTPROP)) - RRETURN(MATCH_NOMATCH); - break; - - /* Perl space used to exclude VT, but from Perl 5.18 it is included, - which means that Perl space and POSIX space are now identical. PCRE - was changed at release 8.34. */ - - case PT_SPACE: /* Perl space */ - case PT_PXSPACE: /* POSIX space */ - switch(c) - { - HSPACE_CASES: - VSPACE_CASES: - if (op == OP_NOTPROP) RRETURN(MATCH_NOMATCH); - break; - - default: - if ((PRIV(ucp_gentype)[prop->chartype] == ucp_Z) == - (op == OP_NOTPROP)) RRETURN(MATCH_NOMATCH); - break; - } - break; - - case PT_WORD: - if ((PRIV(ucp_gentype)[prop->chartype] == ucp_L || - PRIV(ucp_gentype)[prop->chartype] == ucp_N || - c == CHAR_UNDERSCORE) == (op == OP_NOTPROP)) - RRETURN(MATCH_NOMATCH); - break; - - case PT_CLIST: - cp = PRIV(ucd_caseless_sets) + ecode[2]; - for (;;) - { - if (c < *cp) - { if (op == OP_PROP) { RRETURN(MATCH_NOMATCH); } else break; } - if (c == *cp++) - { if (op == OP_PROP) break; else { RRETURN(MATCH_NOMATCH); } } - } - break; - - case PT_UCNC: - if ((c == CHAR_DOLLAR_SIGN || c == CHAR_COMMERCIAL_AT || - c == CHAR_GRAVE_ACCENT || (c >= 0xa0 && c <= 0xd7ff) || - c >= 0xe000) == (op == OP_NOTPROP)) - RRETURN(MATCH_NOMATCH); - break; - - /* This should never occur */ - - default: - RRETURN(PCRE_ERROR_INTERNAL); - } - - ecode += 3; - } - break; - - /* Match an extended Unicode sequence. We will get here only if the support - is in the binary; otherwise a compile-time error occurs. */ - - case OP_EXTUNI: - if (eptr >= md->end_subject) - { - SCHECK_PARTIAL(); - RRETURN(MATCH_NOMATCH); - } - else - { - int lgb, rgb; - GETCHARINCTEST(c, eptr); - lgb = UCD_GRAPHBREAK(c); - while (eptr < md->end_subject) - { - int len = 1; - if (!utf) c = *eptr; else { GETCHARLEN(c, eptr, len); } - rgb = UCD_GRAPHBREAK(c); - if ((PRIV(ucp_gbtable)[lgb] & (1 << rgb)) == 0) break; - lgb = rgb; - eptr += len; - } - } - CHECK_PARTIAL(); - ecode++; - break; -#endif /* SUPPORT_UCP */ - - - /* Match a back reference, possibly repeatedly. Look past the end of the - item to see if there is repeat information following. The code is similar - to that for character classes, but repeated for efficiency. Then obey - similar code to character type repeats - written out again for speed. - However, if the referenced string is the empty string, always treat - it as matched, any number of times (otherwise there could be infinite - loops). If the reference is unset, there are two possibilities: - - (a) In the default, Perl-compatible state, set the length negative; - this ensures that every attempt at a match fails. We can't just fail - here, because of the possibility of quantifiers with zero minima. - - (b) If the JavaScript compatibility flag is set, set the length to zero - so that the back reference matches an empty string. - - Otherwise, set the length to the length of what was matched by the - referenced subpattern. - - The OP_REF and OP_REFI opcodes are used for a reference to a numbered group - or to a non-duplicated named group. For a duplicated named group, OP_DNREF - and OP_DNREFI are used. In this case we must scan the list of groups to - which the name refers, and use the first one that is set. */ - - case OP_DNREF: - case OP_DNREFI: - caseless = op == OP_DNREFI; - { - int count = GET2(ecode, 1+IMM2_SIZE); - pcre_uchar *slot = md->name_table + GET2(ecode, 1) * md->name_entry_size; - ecode += 1 + 2*IMM2_SIZE; - - /* Setting the default length first and initializing 'offset' avoids - compiler warnings in the REF_REPEAT code. */ - - length = (md->jscript_compat)? 0 : -1; - offset = 0; - - while (count-- > 0) - { - offset = GET2(slot, 0) << 1; - if (offset < offset_top && md->offset_vector[offset] >= 0) - { - length = md->offset_vector[offset+1] - md->offset_vector[offset]; - break; - } - slot += md->name_entry_size; - } - } - goto REF_REPEAT; - - case OP_REF: - case OP_REFI: - caseless = op == OP_REFI; - offset = GET2(ecode, 1) << 1; /* Doubled ref number */ - ecode += 1 + IMM2_SIZE; - if (offset >= offset_top || md->offset_vector[offset] < 0) - length = (md->jscript_compat)? 0 : -1; - else - length = md->offset_vector[offset+1] - md->offset_vector[offset]; - - /* Set up for repetition, or handle the non-repeated case */ - - REF_REPEAT: - switch (*ecode) - { - case OP_CRSTAR: - case OP_CRMINSTAR: - case OP_CRPLUS: - case OP_CRMINPLUS: - case OP_CRQUERY: - case OP_CRMINQUERY: - c = *ecode++ - OP_CRSTAR; - minimize = (c & 1) != 0; - min = rep_min[c]; /* Pick up values from tables; */ - max = rep_max[c]; /* zero for max => infinity */ - if (max == 0) max = INT_MAX; - break; - - case OP_CRRANGE: - case OP_CRMINRANGE: - minimize = (*ecode == OP_CRMINRANGE); - min = GET2(ecode, 1); - max = GET2(ecode, 1 + IMM2_SIZE); - if (max == 0) max = INT_MAX; - ecode += 1 + 2 * IMM2_SIZE; - break; - - default: /* No repeat follows */ - if ((length = match_ref(offset, eptr, length, md, caseless)) < 0) - { - if (length == -2) eptr = md->end_subject; /* Partial match */ - CHECK_PARTIAL(); - RRETURN(MATCH_NOMATCH); - } - eptr += length; - continue; /* With the main loop */ - } - - /* Handle repeated back references. If the length of the reference is - zero, just continue with the main loop. If the length is negative, it - means the reference is unset in non-Java-compatible mode. If the minimum is - zero, we can continue at the same level without recursion. For any other - minimum, carrying on will result in NOMATCH. */ - - if (length == 0) continue; - if (length < 0 && min == 0) continue; - - /* First, ensure the minimum number of matches are present. We get back - the length of the reference string explicitly rather than passing the - address of eptr, so that eptr can be a register variable. */ - - for (i = 1; i <= min; i++) - { - int slength; - if ((slength = match_ref(offset, eptr, length, md, caseless)) < 0) - { - if (slength == -2) eptr = md->end_subject; /* Partial match */ - CHECK_PARTIAL(); - RRETURN(MATCH_NOMATCH); - } - eptr += slength; - } - - /* If min = max, continue at the same level without recursion. - They are not both allowed to be zero. */ - - if (min == max) continue; - - /* If minimizing, keep trying and advancing the pointer */ - - if (minimize) - { - for (fi = min;; fi++) - { - int slength; - RMATCH(eptr, ecode, offset_top, md, eptrb, RM14); - if (rrc != MATCH_NOMATCH) RRETURN(rrc); - if (fi >= max) RRETURN(MATCH_NOMATCH); - if ((slength = match_ref(offset, eptr, length, md, caseless)) < 0) - { - if (slength == -2) eptr = md->end_subject; /* Partial match */ - CHECK_PARTIAL(); - RRETURN(MATCH_NOMATCH); - } - eptr += slength; - } - /* Control never gets here */ - } - - /* If maximizing, find the longest string and work backwards */ - - else - { - pp = eptr; - for (i = min; i < max; i++) - { - int slength; - if ((slength = match_ref(offset, eptr, length, md, caseless)) < 0) - { - /* Can't use CHECK_PARTIAL because we don't want to update eptr in - the soft partial matching case. */ - - if (slength == -2 && md->partial != 0 && - md->end_subject > md->start_used_ptr) - { - md->hitend = TRUE; - if (md->partial > 1) RRETURN(PCRE_ERROR_PARTIAL); - } - break; - } - eptr += slength; - } - - while (eptr >= pp) - { - RMATCH(eptr, ecode, offset_top, md, eptrb, RM15); - if (rrc != MATCH_NOMATCH) RRETURN(rrc); - eptr -= length; - } - RRETURN(MATCH_NOMATCH); - } - /* Control never gets here */ - - /* Match a bit-mapped character class, possibly repeatedly. This op code is - used when all the characters in the class have values in the range 0-255, - and either the matching is caseful, or the characters are in the range - 0-127 when UTF-8 processing is enabled. The only difference between - OP_CLASS and OP_NCLASS occurs when a data character outside the range is - encountered. - - First, look past the end of the item to see if there is repeat information - following. Then obey similar code to character type repeats - written out - again for speed. */ - - case OP_NCLASS: - case OP_CLASS: - { - /* The data variable is saved across frames, so the byte map needs to - be stored there. */ -#define BYTE_MAP ((pcre_uint8 *)data) - data = ecode + 1; /* Save for matching */ - ecode += 1 + (32 / sizeof(pcre_uchar)); /* Advance past the item */ - - switch (*ecode) - { - case OP_CRSTAR: - case OP_CRMINSTAR: - case OP_CRPLUS: - case OP_CRMINPLUS: - case OP_CRQUERY: - case OP_CRMINQUERY: - case OP_CRPOSSTAR: - case OP_CRPOSPLUS: - case OP_CRPOSQUERY: - c = *ecode++ - OP_CRSTAR; - if (c < OP_CRPOSSTAR - OP_CRSTAR) minimize = (c & 1) != 0; - else possessive = TRUE; - min = rep_min[c]; /* Pick up values from tables; */ - max = rep_max[c]; /* zero for max => infinity */ - if (max == 0) max = INT_MAX; - break; - - case OP_CRRANGE: - case OP_CRMINRANGE: - case OP_CRPOSRANGE: - minimize = (*ecode == OP_CRMINRANGE); - possessive = (*ecode == OP_CRPOSRANGE); - min = GET2(ecode, 1); - max = GET2(ecode, 1 + IMM2_SIZE); - if (max == 0) max = INT_MAX; - ecode += 1 + 2 * IMM2_SIZE; - break; - - default: /* No repeat follows */ - min = max = 1; - break; - } - - /* First, ensure the minimum number of matches are present. */ - -#ifdef SUPPORT_UTF - if (utf) - { - for (i = 1; i <= min; i++) - { - if (eptr >= md->end_subject) - { - SCHECK_PARTIAL(); - RRETURN(MATCH_NOMATCH); - } - GETCHARINC(c, eptr); - if (c > 255) - { - if (op == OP_CLASS) RRETURN(MATCH_NOMATCH); - } - else - if ((BYTE_MAP[c/8] & (1 << (c&7))) == 0) RRETURN(MATCH_NOMATCH); - } - } - else -#endif - /* Not UTF mode */ - { - for (i = 1; i <= min; i++) - { - if (eptr >= md->end_subject) - { - SCHECK_PARTIAL(); - RRETURN(MATCH_NOMATCH); - } - c = *eptr++; -#ifndef COMPILE_PCRE8 - if (c > 255) - { - if (op == OP_CLASS) RRETURN(MATCH_NOMATCH); - } - else -#endif - if ((BYTE_MAP[c/8] & (1 << (c&7))) == 0) RRETURN(MATCH_NOMATCH); - } - } - - /* If max == min we can continue with the main loop without the - need to recurse. */ - - if (min == max) continue; - - /* If minimizing, keep testing the rest of the expression and advancing - the pointer while it matches the class. */ - - if (minimize) - { -#ifdef SUPPORT_UTF - if (utf) - { - for (fi = min;; fi++) - { - RMATCH(eptr, ecode, offset_top, md, eptrb, RM16); - if (rrc != MATCH_NOMATCH) RRETURN(rrc); - if (fi >= max) RRETURN(MATCH_NOMATCH); - if (eptr >= md->end_subject) - { - SCHECK_PARTIAL(); - RRETURN(MATCH_NOMATCH); - } - GETCHARINC(c, eptr); - if (c > 255) - { - if (op == OP_CLASS) RRETURN(MATCH_NOMATCH); - } - else - if ((BYTE_MAP[c/8] & (1 << (c&7))) == 0) RRETURN(MATCH_NOMATCH); - } - } - else -#endif - /* Not UTF mode */ - { - for (fi = min;; fi++) - { - RMATCH(eptr, ecode, offset_top, md, eptrb, RM17); - if (rrc != MATCH_NOMATCH) RRETURN(rrc); - if (fi >= max) RRETURN(MATCH_NOMATCH); - if (eptr >= md->end_subject) - { - SCHECK_PARTIAL(); - RRETURN(MATCH_NOMATCH); - } - c = *eptr++; -#ifndef COMPILE_PCRE8 - if (c > 255) - { - if (op == OP_CLASS) RRETURN(MATCH_NOMATCH); - } - else -#endif - if ((BYTE_MAP[c/8] & (1 << (c&7))) == 0) RRETURN(MATCH_NOMATCH); - } - } - /* Control never gets here */ - } - - /* If maximizing, find the longest possible run, then work backwards. */ - - else - { - pp = eptr; - -#ifdef SUPPORT_UTF - if (utf) - { - for (i = min; i < max; i++) - { - int len = 1; - if (eptr >= md->end_subject) - { - SCHECK_PARTIAL(); - break; - } - GETCHARLEN(c, eptr, len); - if (c > 255) - { - if (op == OP_CLASS) break; - } - else - if ((BYTE_MAP[c/8] & (1 << (c&7))) == 0) break; - eptr += len; - } - - if (possessive) continue; /* No backtracking */ - - for (;;) - { - RMATCH(eptr, ecode, offset_top, md, eptrb, RM18); - if (rrc != MATCH_NOMATCH) RRETURN(rrc); - if (eptr-- == pp) break; /* Stop if tried at original pos */ - BACKCHAR(eptr); - } - } - else -#endif - /* Not UTF mode */ - { - for (i = min; i < max; i++) - { - if (eptr >= md->end_subject) - { - SCHECK_PARTIAL(); - break; - } - c = *eptr; -#ifndef COMPILE_PCRE8 - if (c > 255) - { - if (op == OP_CLASS) break; - } - else -#endif - if ((BYTE_MAP[c/8] & (1 << (c&7))) == 0) break; - eptr++; - } - - if (possessive) continue; /* No backtracking */ - - while (eptr >= pp) - { - RMATCH(eptr, ecode, offset_top, md, eptrb, RM19); - if (rrc != MATCH_NOMATCH) RRETURN(rrc); - eptr--; - } - } - - RRETURN(MATCH_NOMATCH); - } -#undef BYTE_MAP - } - /* Control never gets here */ - - - /* Match an extended character class. In the 8-bit library, this opcode is - encountered only when UTF-8 mode mode is supported. In the 16-bit and - 32-bit libraries, codepoints greater than 255 may be encountered even when - UTF is not supported. */ - -#if defined SUPPORT_UTF || !defined COMPILE_PCRE8 - case OP_XCLASS: - { - data = ecode + 1 + LINK_SIZE; /* Save for matching */ - ecode += GET(ecode, 1); /* Advance past the item */ - - switch (*ecode) - { - case OP_CRSTAR: - case OP_CRMINSTAR: - case OP_CRPLUS: - case OP_CRMINPLUS: - case OP_CRQUERY: - case OP_CRMINQUERY: - case OP_CRPOSSTAR: - case OP_CRPOSPLUS: - case OP_CRPOSQUERY: - c = *ecode++ - OP_CRSTAR; - if (c < OP_CRPOSSTAR - OP_CRSTAR) minimize = (c & 1) != 0; - else possessive = TRUE; - min = rep_min[c]; /* Pick up values from tables; */ - max = rep_max[c]; /* zero for max => infinity */ - if (max == 0) max = INT_MAX; - break; - - case OP_CRRANGE: - case OP_CRMINRANGE: - case OP_CRPOSRANGE: - minimize = (*ecode == OP_CRMINRANGE); - possessive = (*ecode == OP_CRPOSRANGE); - min = GET2(ecode, 1); - max = GET2(ecode, 1 + IMM2_SIZE); - if (max == 0) max = INT_MAX; - ecode += 1 + 2 * IMM2_SIZE; - break; - - default: /* No repeat follows */ - min = max = 1; - break; - } - - /* First, ensure the minimum number of matches are present. */ - - for (i = 1; i <= min; i++) - { - if (eptr >= md->end_subject) - { - SCHECK_PARTIAL(); - RRETURN(MATCH_NOMATCH); - } - GETCHARINCTEST(c, eptr); - if (!PRIV(xclass)(c, data, utf)) RRETURN(MATCH_NOMATCH); - } - - /* If max == min we can continue with the main loop without the - need to recurse. */ - - if (min == max) continue; - - /* If minimizing, keep testing the rest of the expression and advancing - the pointer while it matches the class. */ - - if (minimize) - { - for (fi = min;; fi++) - { - RMATCH(eptr, ecode, offset_top, md, eptrb, RM20); - if (rrc != MATCH_NOMATCH) RRETURN(rrc); - if (fi >= max) RRETURN(MATCH_NOMATCH); - if (eptr >= md->end_subject) - { - SCHECK_PARTIAL(); - RRETURN(MATCH_NOMATCH); - } - GETCHARINCTEST(c, eptr); - if (!PRIV(xclass)(c, data, utf)) RRETURN(MATCH_NOMATCH); - } - /* Control never gets here */ - } - - /* If maximizing, find the longest possible run, then work backwards. */ - - else - { - pp = eptr; - for (i = min; i < max; i++) - { - int len = 1; - if (eptr >= md->end_subject) - { - SCHECK_PARTIAL(); - break; - } -#ifdef SUPPORT_UTF - GETCHARLENTEST(c, eptr, len); -#else - c = *eptr; -#endif - if (!PRIV(xclass)(c, data, utf)) break; - eptr += len; - } - - if (possessive) continue; /* No backtracking */ - - for(;;) - { - RMATCH(eptr, ecode, offset_top, md, eptrb, RM21); - if (rrc != MATCH_NOMATCH) RRETURN(rrc); - if (eptr-- == pp) break; /* Stop if tried at original pos */ -#ifdef SUPPORT_UTF - if (utf) BACKCHAR(eptr); -#endif - } - RRETURN(MATCH_NOMATCH); - } - - /* Control never gets here */ - } -#endif /* End of XCLASS */ - - /* Match a single character, casefully */ - - case OP_CHAR: -#ifdef SUPPORT_UTF - if (utf) - { - length = 1; - ecode++; - GETCHARLEN(fc, ecode, length); - if (length > md->end_subject - eptr) - { - CHECK_PARTIAL(); /* Not SCHECK_PARTIAL() */ - RRETURN(MATCH_NOMATCH); - } - while (length-- > 0) if (*ecode++ != UCHAR21INC(eptr)) RRETURN(MATCH_NOMATCH); - } - else -#endif - /* Not UTF mode */ - { - if (md->end_subject - eptr < 1) - { - SCHECK_PARTIAL(); /* This one can use SCHECK_PARTIAL() */ - RRETURN(MATCH_NOMATCH); - } - if (ecode[1] != *eptr++) RRETURN(MATCH_NOMATCH); - ecode += 2; - } - break; - - /* Match a single character, caselessly. If we are at the end of the - subject, give up immediately. */ - - case OP_CHARI: - if (eptr >= md->end_subject) - { - SCHECK_PARTIAL(); - RRETURN(MATCH_NOMATCH); - } - -#ifdef SUPPORT_UTF - if (utf) - { - length = 1; - ecode++; - GETCHARLEN(fc, ecode, length); - - /* If the pattern character's value is < 128, we have only one byte, and - we know that its other case must also be one byte long, so we can use the - fast lookup table. We know that there is at least one byte left in the - subject. */ - - if (fc < 128) - { - pcre_uint32 cc = UCHAR21(eptr); - if (md->lcc[fc] != TABLE_GET(cc, md->lcc, cc)) RRETURN(MATCH_NOMATCH); - ecode++; - eptr++; - } - - /* Otherwise we must pick up the subject character. Note that we cannot - use the value of "length" to check for sufficient bytes left, because the - other case of the character may have more or fewer bytes. */ - - else - { - pcre_uint32 dc; - GETCHARINC(dc, eptr); - ecode += length; - - /* If we have Unicode property support, we can use it to test the other - case of the character, if there is one. */ - - if (fc != dc) - { -#ifdef SUPPORT_UCP - if (dc != UCD_OTHERCASE(fc)) -#endif - RRETURN(MATCH_NOMATCH); - } - } - } - else -#endif /* SUPPORT_UTF */ - - /* Not UTF mode */ - { - if (TABLE_GET(ecode[1], md->lcc, ecode[1]) - != TABLE_GET(*eptr, md->lcc, *eptr)) RRETURN(MATCH_NOMATCH); - eptr++; - ecode += 2; - } - break; - - /* Match a single character repeatedly. */ - - case OP_EXACT: - case OP_EXACTI: - min = max = GET2(ecode, 1); - ecode += 1 + IMM2_SIZE; - goto REPEATCHAR; - - case OP_POSUPTO: - case OP_POSUPTOI: - possessive = TRUE; - /* Fall through */ - - case OP_UPTO: - case OP_UPTOI: - case OP_MINUPTO: - case OP_MINUPTOI: - min = 0; - max = GET2(ecode, 1); - minimize = *ecode == OP_MINUPTO || *ecode == OP_MINUPTOI; - ecode += 1 + IMM2_SIZE; - goto REPEATCHAR; - - case OP_POSSTAR: - case OP_POSSTARI: - possessive = TRUE; - min = 0; - max = INT_MAX; - ecode++; - goto REPEATCHAR; - - case OP_POSPLUS: - case OP_POSPLUSI: - possessive = TRUE; - min = 1; - max = INT_MAX; - ecode++; - goto REPEATCHAR; - - case OP_POSQUERY: - case OP_POSQUERYI: - possessive = TRUE; - min = 0; - max = 1; - ecode++; - goto REPEATCHAR; - - case OP_STAR: - case OP_STARI: - case OP_MINSTAR: - case OP_MINSTARI: - case OP_PLUS: - case OP_PLUSI: - case OP_MINPLUS: - case OP_MINPLUSI: - case OP_QUERY: - case OP_QUERYI: - case OP_MINQUERY: - case OP_MINQUERYI: - c = *ecode++ - ((op < OP_STARI)? OP_STAR : OP_STARI); - minimize = (c & 1) != 0; - min = rep_min[c]; /* Pick up values from tables; */ - max = rep_max[c]; /* zero for max => infinity */ - if (max == 0) max = INT_MAX; - - /* Common code for all repeated single-character matches. We first check - for the minimum number of characters. If the minimum equals the maximum, we - are done. Otherwise, if minimizing, check the rest of the pattern for a - match; if there isn't one, advance up to the maximum, one character at a - time. - - If maximizing, advance up to the maximum number of matching characters, - until eptr is past the end of the maximum run. If possessive, we are - then done (no backing up). Otherwise, match at this position; anything - other than no match is immediately returned. For nomatch, back up one - character, unless we are matching \R and the last thing matched was - \r\n, in which case, back up two bytes. When we reach the first optional - character position, we can save stack by doing a tail recurse. - - The various UTF/non-UTF and caseful/caseless cases are handled separately, - for speed. */ - - REPEATCHAR: -#ifdef SUPPORT_UTF - if (utf) - { - length = 1; - charptr = ecode; - GETCHARLEN(fc, ecode, length); - ecode += length; - - /* Handle multibyte character matching specially here. There is - support for caseless matching if UCP support is present. */ - - if (length > 1) - { -#ifdef SUPPORT_UCP - pcre_uint32 othercase; - if (op >= OP_STARI && /* Caseless */ - (othercase = UCD_OTHERCASE(fc)) != fc) - oclength = PRIV(ord2utf)(othercase, occhars); - else oclength = 0; -#endif /* SUPPORT_UCP */ - - for (i = 1; i <= min; i++) - { - if (eptr <= md->end_subject - length && - memcmp(eptr, charptr, IN_UCHARS(length)) == 0) eptr += length; -#ifdef SUPPORT_UCP - else if (oclength > 0 && - eptr <= md->end_subject - oclength && - memcmp(eptr, occhars, IN_UCHARS(oclength)) == 0) eptr += oclength; -#endif /* SUPPORT_UCP */ - else - { - CHECK_PARTIAL(); - RRETURN(MATCH_NOMATCH); - } - } - - if (min == max) continue; - - if (minimize) - { - for (fi = min;; fi++) - { - RMATCH(eptr, ecode, offset_top, md, eptrb, RM22); - if (rrc != MATCH_NOMATCH) RRETURN(rrc); - if (fi >= max) RRETURN(MATCH_NOMATCH); - if (eptr <= md->end_subject - length && - memcmp(eptr, charptr, IN_UCHARS(length)) == 0) eptr += length; -#ifdef SUPPORT_UCP - else if (oclength > 0 && - eptr <= md->end_subject - oclength && - memcmp(eptr, occhars, IN_UCHARS(oclength)) == 0) eptr += oclength; -#endif /* SUPPORT_UCP */ - else - { - CHECK_PARTIAL(); - RRETURN(MATCH_NOMATCH); - } - } - /* Control never gets here */ - } - - else /* Maximize */ - { - pp = eptr; - for (i = min; i < max; i++) - { - if (eptr <= md->end_subject - length && - memcmp(eptr, charptr, IN_UCHARS(length)) == 0) eptr += length; -#ifdef SUPPORT_UCP - else if (oclength > 0 && - eptr <= md->end_subject - oclength && - memcmp(eptr, occhars, IN_UCHARS(oclength)) == 0) eptr += oclength; -#endif /* SUPPORT_UCP */ - else - { - CHECK_PARTIAL(); - break; - } - } - - if (possessive) continue; /* No backtracking */ - for(;;) - { - if (eptr <= pp) goto TAIL_RECURSE; - RMATCH(eptr, ecode, offset_top, md, eptrb, RM23); - if (rrc != MATCH_NOMATCH) RRETURN(rrc); -#ifdef SUPPORT_UCP - eptr--; - BACKCHAR(eptr); -#else /* without SUPPORT_UCP */ - eptr -= length; -#endif /* SUPPORT_UCP */ - } - } - /* Control never gets here */ - } - - /* If the length of a UTF-8 character is 1, we fall through here, and - obey the code as for non-UTF-8 characters below, though in this case the - value of fc will always be < 128. */ - } - else -#endif /* SUPPORT_UTF */ - /* When not in UTF-8 mode, load a single-byte character. */ - fc = *ecode++; - - /* The value of fc at this point is always one character, though we may - or may not be in UTF mode. The code is duplicated for the caseless and - caseful cases, for speed, since matching characters is likely to be quite - common. First, ensure the minimum number of matches are present. If min = - max, continue at the same level without recursing. Otherwise, if - minimizing, keep trying the rest of the expression and advancing one - matching character if failing, up to the maximum. Alternatively, if - maximizing, find the maximum number of characters and work backwards. */ - - DPRINTF(("matching %c{%d,%d} against subject %.*s\n", fc, min, max, - max, (char *)eptr)); - - if (op >= OP_STARI) /* Caseless */ - { -#ifdef COMPILE_PCRE8 - /* fc must be < 128 if UTF is enabled. */ - foc = md->fcc[fc]; -#else -#ifdef SUPPORT_UTF -#ifdef SUPPORT_UCP - if (utf && fc > 127) - foc = UCD_OTHERCASE(fc); -#else - if (utf && fc > 127) - foc = fc; -#endif /* SUPPORT_UCP */ - else -#endif /* SUPPORT_UTF */ - foc = TABLE_GET(fc, md->fcc, fc); -#endif /* COMPILE_PCRE8 */ - - for (i = 1; i <= min; i++) - { - pcre_uint32 cc; /* Faster than pcre_uchar */ - if (eptr >= md->end_subject) - { - SCHECK_PARTIAL(); - RRETURN(MATCH_NOMATCH); - } - cc = UCHAR21TEST(eptr); - if (fc != cc && foc != cc) RRETURN(MATCH_NOMATCH); - eptr++; - } - if (min == max) continue; - if (minimize) - { - for (fi = min;; fi++) - { - pcre_uint32 cc; /* Faster than pcre_uchar */ - RMATCH(eptr, ecode, offset_top, md, eptrb, RM24); - if (rrc != MATCH_NOMATCH) RRETURN(rrc); - if (fi >= max) RRETURN(MATCH_NOMATCH); - if (eptr >= md->end_subject) - { - SCHECK_PARTIAL(); - RRETURN(MATCH_NOMATCH); - } - cc = UCHAR21TEST(eptr); - if (fc != cc && foc != cc) RRETURN(MATCH_NOMATCH); - eptr++; - } - /* Control never gets here */ - } - else /* Maximize */ - { - pp = eptr; - for (i = min; i < max; i++) - { - pcre_uint32 cc; /* Faster than pcre_uchar */ - if (eptr >= md->end_subject) - { - SCHECK_PARTIAL(); - break; - } - cc = UCHAR21TEST(eptr); - if (fc != cc && foc != cc) break; - eptr++; - } - if (possessive) continue; /* No backtracking */ - for (;;) - { - if (eptr == pp) goto TAIL_RECURSE; - RMATCH(eptr, ecode, offset_top, md, eptrb, RM25); - eptr--; - if (rrc != MATCH_NOMATCH) RRETURN(rrc); - } - /* Control never gets here */ - } - } - - /* Caseful comparisons (includes all multi-byte characters) */ - - else - { - for (i = 1; i <= min; i++) - { - if (eptr >= md->end_subject) - { - SCHECK_PARTIAL(); - RRETURN(MATCH_NOMATCH); - } - if (fc != UCHAR21INCTEST(eptr)) RRETURN(MATCH_NOMATCH); - } - - if (min == max) continue; - - if (minimize) - { - for (fi = min;; fi++) - { - RMATCH(eptr, ecode, offset_top, md, eptrb, RM26); - if (rrc != MATCH_NOMATCH) RRETURN(rrc); - if (fi >= max) RRETURN(MATCH_NOMATCH); - if (eptr >= md->end_subject) - { - SCHECK_PARTIAL(); - RRETURN(MATCH_NOMATCH); - } - if (fc != UCHAR21INCTEST(eptr)) RRETURN(MATCH_NOMATCH); - } - /* Control never gets here */ - } - else /* Maximize */ - { - pp = eptr; - for (i = min; i < max; i++) - { - if (eptr >= md->end_subject) - { - SCHECK_PARTIAL(); - break; - } - if (fc != UCHAR21TEST(eptr)) break; - eptr++; - } - if (possessive) continue; /* No backtracking */ - for (;;) - { - if (eptr == pp) goto TAIL_RECURSE; - RMATCH(eptr, ecode, offset_top, md, eptrb, RM27); - eptr--; - if (rrc != MATCH_NOMATCH) RRETURN(rrc); - } - /* Control never gets here */ - } - } - /* Control never gets here */ - - /* Match a negated single one-byte character. The character we are - checking can be multibyte. */ - - case OP_NOT: - case OP_NOTI: - if (eptr >= md->end_subject) - { - SCHECK_PARTIAL(); - RRETURN(MATCH_NOMATCH); - } -#ifdef SUPPORT_UTF - if (utf) - { - register pcre_uint32 ch, och; - - ecode++; - GETCHARINC(ch, ecode); - GETCHARINC(c, eptr); - - if (op == OP_NOT) - { - if (ch == c) RRETURN(MATCH_NOMATCH); - } - else - { -#ifdef SUPPORT_UCP - if (ch > 127) - och = UCD_OTHERCASE(ch); -#else - if (ch > 127) - och = ch; -#endif /* SUPPORT_UCP */ - else - och = TABLE_GET(ch, md->fcc, ch); - if (ch == c || och == c) RRETURN(MATCH_NOMATCH); - } - } - else -#endif - { - register pcre_uint32 ch = ecode[1]; - c = *eptr++; - if (ch == c || (op == OP_NOTI && TABLE_GET(ch, md->fcc, ch) == c)) - RRETURN(MATCH_NOMATCH); - ecode += 2; - } - break; - - /* Match a negated single one-byte character repeatedly. This is almost a - repeat of the code for a repeated single character, but I haven't found a - nice way of commoning these up that doesn't require a test of the - positive/negative option for each character match. Maybe that wouldn't add - very much to the time taken, but character matching *is* what this is all - about... */ - - case OP_NOTEXACT: - case OP_NOTEXACTI: - min = max = GET2(ecode, 1); - ecode += 1 + IMM2_SIZE; - goto REPEATNOTCHAR; - - case OP_NOTUPTO: - case OP_NOTUPTOI: - case OP_NOTMINUPTO: - case OP_NOTMINUPTOI: - min = 0; - max = GET2(ecode, 1); - minimize = *ecode == OP_NOTMINUPTO || *ecode == OP_NOTMINUPTOI; - ecode += 1 + IMM2_SIZE; - goto REPEATNOTCHAR; - - case OP_NOTPOSSTAR: - case OP_NOTPOSSTARI: - possessive = TRUE; - min = 0; - max = INT_MAX; - ecode++; - goto REPEATNOTCHAR; - - case OP_NOTPOSPLUS: - case OP_NOTPOSPLUSI: - possessive = TRUE; - min = 1; - max = INT_MAX; - ecode++; - goto REPEATNOTCHAR; - - case OP_NOTPOSQUERY: - case OP_NOTPOSQUERYI: - possessive = TRUE; - min = 0; - max = 1; - ecode++; - goto REPEATNOTCHAR; - - case OP_NOTPOSUPTO: - case OP_NOTPOSUPTOI: - possessive = TRUE; - min = 0; - max = GET2(ecode, 1); - ecode += 1 + IMM2_SIZE; - goto REPEATNOTCHAR; - - case OP_NOTSTAR: - case OP_NOTSTARI: - case OP_NOTMINSTAR: - case OP_NOTMINSTARI: - case OP_NOTPLUS: - case OP_NOTPLUSI: - case OP_NOTMINPLUS: - case OP_NOTMINPLUSI: - case OP_NOTQUERY: - case OP_NOTQUERYI: - case OP_NOTMINQUERY: - case OP_NOTMINQUERYI: - c = *ecode++ - ((op >= OP_NOTSTARI)? OP_NOTSTARI: OP_NOTSTAR); - minimize = (c & 1) != 0; - min = rep_min[c]; /* Pick up values from tables; */ - max = rep_max[c]; /* zero for max => infinity */ - if (max == 0) max = INT_MAX; - - /* Common code for all repeated single-byte matches. */ - - REPEATNOTCHAR: - GETCHARINCTEST(fc, ecode); - - /* The code is duplicated for the caseless and caseful cases, for speed, - since matching characters is likely to be quite common. First, ensure the - minimum number of matches are present. If min = max, continue at the same - level without recursing. Otherwise, if minimizing, keep trying the rest of - the expression and advancing one matching character if failing, up to the - maximum. Alternatively, if maximizing, find the maximum number of - characters and work backwards. */ - - DPRINTF(("negative matching %c{%d,%d} against subject %.*s\n", fc, min, max, - max, (char *)eptr)); - - if (op >= OP_NOTSTARI) /* Caseless */ - { -#ifdef SUPPORT_UTF -#ifdef SUPPORT_UCP - if (utf && fc > 127) - foc = UCD_OTHERCASE(fc); -#else - if (utf && fc > 127) - foc = fc; -#endif /* SUPPORT_UCP */ - else -#endif /* SUPPORT_UTF */ - foc = TABLE_GET(fc, md->fcc, fc); - -#ifdef SUPPORT_UTF - if (utf) - { - register pcre_uint32 d; - for (i = 1; i <= min; i++) - { - if (eptr >= md->end_subject) - { - SCHECK_PARTIAL(); - RRETURN(MATCH_NOMATCH); - } - GETCHARINC(d, eptr); - if (fc == d || (unsigned int)foc == d) RRETURN(MATCH_NOMATCH); - } - } - else -#endif /* SUPPORT_UTF */ - /* Not UTF mode */ - { - for (i = 1; i <= min; i++) - { - if (eptr >= md->end_subject) - { - SCHECK_PARTIAL(); - RRETURN(MATCH_NOMATCH); - } - if (fc == *eptr || foc == *eptr) RRETURN(MATCH_NOMATCH); - eptr++; - } - } - - if (min == max) continue; - - if (minimize) - { -#ifdef SUPPORT_UTF - if (utf) - { - register pcre_uint32 d; - for (fi = min;; fi++) - { - RMATCH(eptr, ecode, offset_top, md, eptrb, RM28); - if (rrc != MATCH_NOMATCH) RRETURN(rrc); - if (fi >= max) RRETURN(MATCH_NOMATCH); - if (eptr >= md->end_subject) - { - SCHECK_PARTIAL(); - RRETURN(MATCH_NOMATCH); - } - GETCHARINC(d, eptr); - if (fc == d || (unsigned int)foc == d) RRETURN(MATCH_NOMATCH); - } - } - else -#endif /*SUPPORT_UTF */ - /* Not UTF mode */ - { - for (fi = min;; fi++) - { - RMATCH(eptr, ecode, offset_top, md, eptrb, RM29); - if (rrc != MATCH_NOMATCH) RRETURN(rrc); - if (fi >= max) RRETURN(MATCH_NOMATCH); - if (eptr >= md->end_subject) - { - SCHECK_PARTIAL(); - RRETURN(MATCH_NOMATCH); - } - if (fc == *eptr || foc == *eptr) RRETURN(MATCH_NOMATCH); - eptr++; - } - } - /* Control never gets here */ - } - - /* Maximize case */ - - else - { - pp = eptr; - -#ifdef SUPPORT_UTF - if (utf) - { - register pcre_uint32 d; - for (i = min; i < max; i++) - { - int len = 1; - if (eptr >= md->end_subject) - { - SCHECK_PARTIAL(); - break; - } - GETCHARLEN(d, eptr, len); - if (fc == d || (unsigned int)foc == d) break; - eptr += len; - } - if (possessive) continue; /* No backtracking */ - for(;;) - { - if (eptr <= pp) goto TAIL_RECURSE; - RMATCH(eptr, ecode, offset_top, md, eptrb, RM30); - if (rrc != MATCH_NOMATCH) RRETURN(rrc); - eptr--; - BACKCHAR(eptr); - } - } - else -#endif /* SUPPORT_UTF */ - /* Not UTF mode */ - { - for (i = min; i < max; i++) - { - if (eptr >= md->end_subject) - { - SCHECK_PARTIAL(); - break; - } - if (fc == *eptr || foc == *eptr) break; - eptr++; - } - if (possessive) continue; /* No backtracking */ - for (;;) - { - if (eptr == pp) goto TAIL_RECURSE; - RMATCH(eptr, ecode, offset_top, md, eptrb, RM31); - if (rrc != MATCH_NOMATCH) RRETURN(rrc); - eptr--; - } - } - /* Control never gets here */ - } - } - - /* Caseful comparisons */ - - else - { -#ifdef SUPPORT_UTF - if (utf) - { - register pcre_uint32 d; - for (i = 1; i <= min; i++) - { - if (eptr >= md->end_subject) - { - SCHECK_PARTIAL(); - RRETURN(MATCH_NOMATCH); - } - GETCHARINC(d, eptr); - if (fc == d) RRETURN(MATCH_NOMATCH); - } - } - else -#endif - /* Not UTF mode */ - { - for (i = 1; i <= min; i++) - { - if (eptr >= md->end_subject) - { - SCHECK_PARTIAL(); - RRETURN(MATCH_NOMATCH); - } - if (fc == *eptr++) RRETURN(MATCH_NOMATCH); - } - } - - if (min == max) continue; - - if (minimize) - { -#ifdef SUPPORT_UTF - if (utf) - { - register pcre_uint32 d; - for (fi = min;; fi++) - { - RMATCH(eptr, ecode, offset_top, md, eptrb, RM32); - if (rrc != MATCH_NOMATCH) RRETURN(rrc); - if (fi >= max) RRETURN(MATCH_NOMATCH); - if (eptr >= md->end_subject) - { - SCHECK_PARTIAL(); - RRETURN(MATCH_NOMATCH); - } - GETCHARINC(d, eptr); - if (fc == d) RRETURN(MATCH_NOMATCH); - } - } - else -#endif - /* Not UTF mode */ - { - for (fi = min;; fi++) - { - RMATCH(eptr, ecode, offset_top, md, eptrb, RM33); - if (rrc != MATCH_NOMATCH) RRETURN(rrc); - if (fi >= max) RRETURN(MATCH_NOMATCH); - if (eptr >= md->end_subject) - { - SCHECK_PARTIAL(); - RRETURN(MATCH_NOMATCH); - } - if (fc == *eptr++) RRETURN(MATCH_NOMATCH); - } - } - /* Control never gets here */ - } - - /* Maximize case */ - - else - { - pp = eptr; - -#ifdef SUPPORT_UTF - if (utf) - { - register pcre_uint32 d; - for (i = min; i < max; i++) - { - int len = 1; - if (eptr >= md->end_subject) - { - SCHECK_PARTIAL(); - break; - } - GETCHARLEN(d, eptr, len); - if (fc == d) break; - eptr += len; - } - if (possessive) continue; /* No backtracking */ - for(;;) - { - if (eptr <= pp) goto TAIL_RECURSE; - RMATCH(eptr, ecode, offset_top, md, eptrb, RM34); - if (rrc != MATCH_NOMATCH) RRETURN(rrc); - eptr--; - BACKCHAR(eptr); - } - } - else -#endif - /* Not UTF mode */ - { - for (i = min; i < max; i++) - { - if (eptr >= md->end_subject) - { - SCHECK_PARTIAL(); - break; - } - if (fc == *eptr) break; - eptr++; - } - if (possessive) continue; /* No backtracking */ - for (;;) - { - if (eptr == pp) goto TAIL_RECURSE; - RMATCH(eptr, ecode, offset_top, md, eptrb, RM35); - if (rrc != MATCH_NOMATCH) RRETURN(rrc); - eptr--; - } - } - /* Control never gets here */ - } - } - /* Control never gets here */ - - /* Match a single character type repeatedly; several different opcodes - share code. This is very similar to the code for single characters, but we - repeat it in the interests of efficiency. */ - - case OP_TYPEEXACT: - min = max = GET2(ecode, 1); - minimize = TRUE; - ecode += 1 + IMM2_SIZE; - goto REPEATTYPE; - - case OP_TYPEUPTO: - case OP_TYPEMINUPTO: - min = 0; - max = GET2(ecode, 1); - minimize = *ecode == OP_TYPEMINUPTO; - ecode += 1 + IMM2_SIZE; - goto REPEATTYPE; - - case OP_TYPEPOSSTAR: - possessive = TRUE; - min = 0; - max = INT_MAX; - ecode++; - goto REPEATTYPE; - - case OP_TYPEPOSPLUS: - possessive = TRUE; - min = 1; - max = INT_MAX; - ecode++; - goto REPEATTYPE; - - case OP_TYPEPOSQUERY: - possessive = TRUE; - min = 0; - max = 1; - ecode++; - goto REPEATTYPE; - - case OP_TYPEPOSUPTO: - possessive = TRUE; - min = 0; - max = GET2(ecode, 1); - ecode += 1 + IMM2_SIZE; - goto REPEATTYPE; - - case OP_TYPESTAR: - case OP_TYPEMINSTAR: - case OP_TYPEPLUS: - case OP_TYPEMINPLUS: - case OP_TYPEQUERY: - case OP_TYPEMINQUERY: - c = *ecode++ - OP_TYPESTAR; - minimize = (c & 1) != 0; - min = rep_min[c]; /* Pick up values from tables; */ - max = rep_max[c]; /* zero for max => infinity */ - if (max == 0) max = INT_MAX; - - /* Common code for all repeated single character type matches. Note that - in UTF-8 mode, '.' matches a character of any length, but for the other - character types, the valid characters are all one-byte long. */ - - REPEATTYPE: - ctype = *ecode++; /* Code for the character type */ - -#ifdef SUPPORT_UCP - if (ctype == OP_PROP || ctype == OP_NOTPROP) - { - prop_fail_result = ctype == OP_NOTPROP; - prop_type = *ecode++; - prop_value = *ecode++; - } - else prop_type = -1; -#endif - - /* First, ensure the minimum number of matches are present. Use inline - code for maximizing the speed, and do the type test once at the start - (i.e. keep it out of the loop). Separate the UTF-8 code completely as that - is tidier. Also separate the UCP code, which can be the same for both UTF-8 - and single-bytes. */ - - if (min > 0) - { -#ifdef SUPPORT_UCP - if (prop_type >= 0) - { - switch(prop_type) - { - case PT_ANY: - if (prop_fail_result) RRETURN(MATCH_NOMATCH); - for (i = 1; i <= min; i++) - { - if (eptr >= md->end_subject) - { - SCHECK_PARTIAL(); - RRETURN(MATCH_NOMATCH); - } - GETCHARINCTEST(c, eptr); - } - break; - - case PT_LAMP: - for (i = 1; i <= min; i++) - { - int chartype; - if (eptr >= md->end_subject) - { - SCHECK_PARTIAL(); - RRETURN(MATCH_NOMATCH); - } - GETCHARINCTEST(c, eptr); - chartype = UCD_CHARTYPE(c); - if ((chartype == ucp_Lu || - chartype == ucp_Ll || - chartype == ucp_Lt) == prop_fail_result) - RRETURN(MATCH_NOMATCH); - } - break; - - case PT_GC: - for (i = 1; i <= min; i++) - { - if (eptr >= md->end_subject) - { - SCHECK_PARTIAL(); - RRETURN(MATCH_NOMATCH); - } - GETCHARINCTEST(c, eptr); - if ((UCD_CATEGORY(c) == prop_value) == prop_fail_result) - RRETURN(MATCH_NOMATCH); - } - break; - - case PT_PC: - for (i = 1; i <= min; i++) - { - if (eptr >= md->end_subject) - { - SCHECK_PARTIAL(); - RRETURN(MATCH_NOMATCH); - } - GETCHARINCTEST(c, eptr); - if ((UCD_CHARTYPE(c) == prop_value) == prop_fail_result) - RRETURN(MATCH_NOMATCH); - } - break; - - case PT_SC: - for (i = 1; i <= min; i++) - { - if (eptr >= md->end_subject) - { - SCHECK_PARTIAL(); - RRETURN(MATCH_NOMATCH); - } - GETCHARINCTEST(c, eptr); - if ((UCD_SCRIPT(c) == prop_value) == prop_fail_result) - RRETURN(MATCH_NOMATCH); - } - break; - - case PT_ALNUM: - for (i = 1; i <= min; i++) - { - int category; - if (eptr >= md->end_subject) - { - SCHECK_PARTIAL(); - RRETURN(MATCH_NOMATCH); - } - GETCHARINCTEST(c, eptr); - category = UCD_CATEGORY(c); - if ((category == ucp_L || category == ucp_N) == prop_fail_result) - RRETURN(MATCH_NOMATCH); - } - break; - - /* Perl space used to exclude VT, but from Perl 5.18 it is included, - which means that Perl space and POSIX space are now identical. PCRE - was changed at release 8.34. */ - - case PT_SPACE: /* Perl space */ - case PT_PXSPACE: /* POSIX space */ - for (i = 1; i <= min; i++) - { - if (eptr >= md->end_subject) - { - SCHECK_PARTIAL(); - RRETURN(MATCH_NOMATCH); - } - GETCHARINCTEST(c, eptr); - switch(c) - { - HSPACE_CASES: - VSPACE_CASES: - if (prop_fail_result) RRETURN(MATCH_NOMATCH); - break; - - default: - if ((UCD_CATEGORY(c) == ucp_Z) == prop_fail_result) - RRETURN(MATCH_NOMATCH); - break; - } - } - break; - - case PT_WORD: - for (i = 1; i <= min; i++) - { - int category; - if (eptr >= md->end_subject) - { - SCHECK_PARTIAL(); - RRETURN(MATCH_NOMATCH); - } - GETCHARINCTEST(c, eptr); - category = UCD_CATEGORY(c); - if ((category == ucp_L || category == ucp_N || c == CHAR_UNDERSCORE) - == prop_fail_result) - RRETURN(MATCH_NOMATCH); - } - break; - - case PT_CLIST: - for (i = 1; i <= min; i++) - { - const pcre_uint32 *cp; - if (eptr >= md->end_subject) - { - SCHECK_PARTIAL(); - RRETURN(MATCH_NOMATCH); - } - GETCHARINCTEST(c, eptr); - cp = PRIV(ucd_caseless_sets) + prop_value; - for (;;) - { - if (c < *cp) - { if (prop_fail_result) break; else { RRETURN(MATCH_NOMATCH); } } - if (c == *cp++) - { if (prop_fail_result) { RRETURN(MATCH_NOMATCH); } else break; } - } - } - break; - - case PT_UCNC: - for (i = 1; i <= min; i++) - { - if (eptr >= md->end_subject) - { - SCHECK_PARTIAL(); - RRETURN(MATCH_NOMATCH); - } - GETCHARINCTEST(c, eptr); - if ((c == CHAR_DOLLAR_SIGN || c == CHAR_COMMERCIAL_AT || - c == CHAR_GRAVE_ACCENT || (c >= 0xa0 && c <= 0xd7ff) || - c >= 0xe000) == prop_fail_result) - RRETURN(MATCH_NOMATCH); - } - break; - - /* This should not occur */ - - default: - RRETURN(PCRE_ERROR_INTERNAL); - } - } - - /* Match extended Unicode sequences. We will get here only if the - support is in the binary; otherwise a compile-time error occurs. */ - - else if (ctype == OP_EXTUNI) - { - for (i = 1; i <= min; i++) - { - if (eptr >= md->end_subject) - { - SCHECK_PARTIAL(); - RRETURN(MATCH_NOMATCH); - } - else - { - int lgb, rgb; - GETCHARINCTEST(c, eptr); - lgb = UCD_GRAPHBREAK(c); - while (eptr < md->end_subject) - { - int len = 1; - if (!utf) c = *eptr; else { GETCHARLEN(c, eptr, len); } - rgb = UCD_GRAPHBREAK(c); - if ((PRIV(ucp_gbtable)[lgb] & (1 << rgb)) == 0) break; - lgb = rgb; - eptr += len; - } - } - CHECK_PARTIAL(); - } - } - - else -#endif /* SUPPORT_UCP */ - -/* Handle all other cases when the coding is UTF-8 */ - -#ifdef SUPPORT_UTF - if (utf) switch(ctype) - { - case OP_ANY: - for (i = 1; i <= min; i++) - { - if (eptr >= md->end_subject) - { - SCHECK_PARTIAL(); - RRETURN(MATCH_NOMATCH); - } - if (IS_NEWLINE(eptr)) RRETURN(MATCH_NOMATCH); - if (md->partial != 0 && - eptr + 1 >= md->end_subject && - NLBLOCK->nltype == NLTYPE_FIXED && - NLBLOCK->nllen == 2 && - UCHAR21(eptr) == NLBLOCK->nl[0]) - { - md->hitend = TRUE; - if (md->partial > 1) RRETURN(PCRE_ERROR_PARTIAL); - } - eptr++; - ACROSSCHAR(eptr < md->end_subject, *eptr, eptr++); - } - break; - - case OP_ALLANY: - for (i = 1; i <= min; i++) - { - if (eptr >= md->end_subject) - { - SCHECK_PARTIAL(); - RRETURN(MATCH_NOMATCH); - } - eptr++; - ACROSSCHAR(eptr < md->end_subject, *eptr, eptr++); - } - break; - - case OP_ANYBYTE: - if (eptr > md->end_subject - min) RRETURN(MATCH_NOMATCH); - eptr += min; - break; - - case OP_ANYNL: - for (i = 1; i <= min; i++) - { - if (eptr >= md->end_subject) - { - SCHECK_PARTIAL(); - RRETURN(MATCH_NOMATCH); - } - GETCHARINC(c, eptr); - switch(c) - { - default: RRETURN(MATCH_NOMATCH); - - case CHAR_CR: - if (eptr < md->end_subject && UCHAR21(eptr) == CHAR_LF) eptr++; - break; - - case CHAR_LF: - break; - - case CHAR_VT: - case CHAR_FF: - case CHAR_NEL: -#ifndef EBCDIC - case 0x2028: - case 0x2029: -#endif /* Not EBCDIC */ - if (md->bsr_anycrlf) RRETURN(MATCH_NOMATCH); - break; - } - } - break; - - case OP_NOT_HSPACE: - for (i = 1; i <= min; i++) - { - if (eptr >= md->end_subject) - { - SCHECK_PARTIAL(); - RRETURN(MATCH_NOMATCH); - } - GETCHARINC(c, eptr); - switch(c) - { - HSPACE_CASES: RRETURN(MATCH_NOMATCH); /* Byte and multibyte cases */ - default: break; - } - } - break; - - case OP_HSPACE: - for (i = 1; i <= min; i++) - { - if (eptr >= md->end_subject) - { - SCHECK_PARTIAL(); - RRETURN(MATCH_NOMATCH); - } - GETCHARINC(c, eptr); - switch(c) - { - HSPACE_CASES: break; /* Byte and multibyte cases */ - default: RRETURN(MATCH_NOMATCH); - } - } - break; - - case OP_NOT_VSPACE: - for (i = 1; i <= min; i++) - { - if (eptr >= md->end_subject) - { - SCHECK_PARTIAL(); - RRETURN(MATCH_NOMATCH); - } - GETCHARINC(c, eptr); - switch(c) - { - VSPACE_CASES: RRETURN(MATCH_NOMATCH); - default: break; - } - } - break; - - case OP_VSPACE: - for (i = 1; i <= min; i++) - { - if (eptr >= md->end_subject) - { - SCHECK_PARTIAL(); - RRETURN(MATCH_NOMATCH); - } - GETCHARINC(c, eptr); - switch(c) - { - VSPACE_CASES: break; - default: RRETURN(MATCH_NOMATCH); - } - } - break; - - case OP_NOT_DIGIT: - for (i = 1; i <= min; i++) - { - if (eptr >= md->end_subject) - { - SCHECK_PARTIAL(); - RRETURN(MATCH_NOMATCH); - } - GETCHARINC(c, eptr); - if (c < 128 && (md->ctypes[c] & ctype_digit) != 0) - RRETURN(MATCH_NOMATCH); - } - break; - - case OP_DIGIT: - for (i = 1; i <= min; i++) - { - pcre_uint32 cc; - if (eptr >= md->end_subject) - { - SCHECK_PARTIAL(); - RRETURN(MATCH_NOMATCH); - } - cc = UCHAR21(eptr); - if (cc >= 128 || (md->ctypes[cc] & ctype_digit) == 0) - RRETURN(MATCH_NOMATCH); - eptr++; - /* No need to skip more bytes - we know it's a 1-byte character */ - } - break; - - case OP_NOT_WHITESPACE: - for (i = 1; i <= min; i++) - { - pcre_uint32 cc; - if (eptr >= md->end_subject) - { - SCHECK_PARTIAL(); - RRETURN(MATCH_NOMATCH); - } - cc = UCHAR21(eptr); - if (cc < 128 && (md->ctypes[cc] & ctype_space) != 0) - RRETURN(MATCH_NOMATCH); - eptr++; - ACROSSCHAR(eptr < md->end_subject, *eptr, eptr++); - } - break; - - case OP_WHITESPACE: - for (i = 1; i <= min; i++) - { - pcre_uint32 cc; - if (eptr >= md->end_subject) - { - SCHECK_PARTIAL(); - RRETURN(MATCH_NOMATCH); - } - cc = UCHAR21(eptr); - if (cc >= 128 || (md->ctypes[cc] & ctype_space) == 0) - RRETURN(MATCH_NOMATCH); - eptr++; - /* No need to skip more bytes - we know it's a 1-byte character */ - } - break; - - case OP_NOT_WORDCHAR: - for (i = 1; i <= min; i++) - { - pcre_uint32 cc; - if (eptr >= md->end_subject) - { - SCHECK_PARTIAL(); - RRETURN(MATCH_NOMATCH); - } - cc = UCHAR21(eptr); - if (cc < 128 && (md->ctypes[cc] & ctype_word) != 0) - RRETURN(MATCH_NOMATCH); - eptr++; - ACROSSCHAR(eptr < md->end_subject, *eptr, eptr++); - } - break; - - case OP_WORDCHAR: - for (i = 1; i <= min; i++) - { - pcre_uint32 cc; - if (eptr >= md->end_subject) - { - SCHECK_PARTIAL(); - RRETURN(MATCH_NOMATCH); - } - cc = UCHAR21(eptr); - if (cc >= 128 || (md->ctypes[cc] & ctype_word) == 0) - RRETURN(MATCH_NOMATCH); - eptr++; - /* No need to skip more bytes - we know it's a 1-byte character */ - } - break; - - default: - RRETURN(PCRE_ERROR_INTERNAL); - } /* End switch(ctype) */ - - else -#endif /* SUPPORT_UTF */ - - /* Code for the non-UTF-8 case for minimum matching of operators other - than OP_PROP and OP_NOTPROP. */ - - switch(ctype) - { - case OP_ANY: - for (i = 1; i <= min; i++) - { - if (eptr >= md->end_subject) - { - SCHECK_PARTIAL(); - RRETURN(MATCH_NOMATCH); - } - if (IS_NEWLINE(eptr)) RRETURN(MATCH_NOMATCH); - if (md->partial != 0 && - eptr + 1 >= md->end_subject && - NLBLOCK->nltype == NLTYPE_FIXED && - NLBLOCK->nllen == 2 && - *eptr == NLBLOCK->nl[0]) - { - md->hitend = TRUE; - if (md->partial > 1) RRETURN(PCRE_ERROR_PARTIAL); - } - eptr++; - } - break; - - case OP_ALLANY: - if (eptr > md->end_subject - min) - { - SCHECK_PARTIAL(); - RRETURN(MATCH_NOMATCH); - } - eptr += min; - break; - - case OP_ANYBYTE: - if (eptr > md->end_subject - min) - { - SCHECK_PARTIAL(); - RRETURN(MATCH_NOMATCH); - } - eptr += min; - break; - - case OP_ANYNL: - for (i = 1; i <= min; i++) - { - if (eptr >= md->end_subject) - { - SCHECK_PARTIAL(); - RRETURN(MATCH_NOMATCH); - } - switch(*eptr++) - { - default: RRETURN(MATCH_NOMATCH); - - case CHAR_CR: - if (eptr < md->end_subject && *eptr == CHAR_LF) eptr++; - break; - - case CHAR_LF: - break; - - case CHAR_VT: - case CHAR_FF: - case CHAR_NEL: -#if defined COMPILE_PCRE16 || defined COMPILE_PCRE32 - case 0x2028: - case 0x2029: -#endif - if (md->bsr_anycrlf) RRETURN(MATCH_NOMATCH); - break; - } - } - break; - - case OP_NOT_HSPACE: - for (i = 1; i <= min; i++) - { - if (eptr >= md->end_subject) - { - SCHECK_PARTIAL(); - RRETURN(MATCH_NOMATCH); - } - switch(*eptr++) - { - default: break; - HSPACE_BYTE_CASES: -#if defined COMPILE_PCRE16 || defined COMPILE_PCRE32 - HSPACE_MULTIBYTE_CASES: -#endif - RRETURN(MATCH_NOMATCH); - } - } - break; - - case OP_HSPACE: - for (i = 1; i <= min; i++) - { - if (eptr >= md->end_subject) - { - SCHECK_PARTIAL(); - RRETURN(MATCH_NOMATCH); - } - switch(*eptr++) - { - default: RRETURN(MATCH_NOMATCH); - HSPACE_BYTE_CASES: -#if defined COMPILE_PCRE16 || defined COMPILE_PCRE32 - HSPACE_MULTIBYTE_CASES: -#endif - break; - } - } - break; - - case OP_NOT_VSPACE: - for (i = 1; i <= min; i++) - { - if (eptr >= md->end_subject) - { - SCHECK_PARTIAL(); - RRETURN(MATCH_NOMATCH); - } - switch(*eptr++) - { - VSPACE_BYTE_CASES: -#if defined COMPILE_PCRE16 || defined COMPILE_PCRE32 - VSPACE_MULTIBYTE_CASES: -#endif - RRETURN(MATCH_NOMATCH); - default: break; - } - } - break; - - case OP_VSPACE: - for (i = 1; i <= min; i++) - { - if (eptr >= md->end_subject) - { - SCHECK_PARTIAL(); - RRETURN(MATCH_NOMATCH); - } - switch(*eptr++) - { - default: RRETURN(MATCH_NOMATCH); - VSPACE_BYTE_CASES: -#if defined COMPILE_PCRE16 || defined COMPILE_PCRE32 - VSPACE_MULTIBYTE_CASES: -#endif - break; - } - } - break; - - case OP_NOT_DIGIT: - for (i = 1; i <= min; i++) - { - if (eptr >= md->end_subject) - { - SCHECK_PARTIAL(); - RRETURN(MATCH_NOMATCH); - } - if (MAX_255(*eptr) && (md->ctypes[*eptr] & ctype_digit) != 0) - RRETURN(MATCH_NOMATCH); - eptr++; - } - break; - - case OP_DIGIT: - for (i = 1; i <= min; i++) - { - if (eptr >= md->end_subject) - { - SCHECK_PARTIAL(); - RRETURN(MATCH_NOMATCH); - } - if (!MAX_255(*eptr) || (md->ctypes[*eptr] & ctype_digit) == 0) - RRETURN(MATCH_NOMATCH); - eptr++; - } - break; - - case OP_NOT_WHITESPACE: - for (i = 1; i <= min; i++) - { - if (eptr >= md->end_subject) - { - SCHECK_PARTIAL(); - RRETURN(MATCH_NOMATCH); - } - if (MAX_255(*eptr) && (md->ctypes[*eptr] & ctype_space) != 0) - RRETURN(MATCH_NOMATCH); - eptr++; - } - break; - - case OP_WHITESPACE: - for (i = 1; i <= min; i++) - { - if (eptr >= md->end_subject) - { - SCHECK_PARTIAL(); - RRETURN(MATCH_NOMATCH); - } - if (!MAX_255(*eptr) || (md->ctypes[*eptr] & ctype_space) == 0) - RRETURN(MATCH_NOMATCH); - eptr++; - } - break; - - case OP_NOT_WORDCHAR: - for (i = 1; i <= min; i++) - { - if (eptr >= md->end_subject) - { - SCHECK_PARTIAL(); - RRETURN(MATCH_NOMATCH); - } - if (MAX_255(*eptr) && (md->ctypes[*eptr] & ctype_word) != 0) - RRETURN(MATCH_NOMATCH); - eptr++; - } - break; - - case OP_WORDCHAR: - for (i = 1; i <= min; i++) - { - if (eptr >= md->end_subject) - { - SCHECK_PARTIAL(); - RRETURN(MATCH_NOMATCH); - } - if (!MAX_255(*eptr) || (md->ctypes[*eptr] & ctype_word) == 0) - RRETURN(MATCH_NOMATCH); - eptr++; - } - break; - - default: - RRETURN(PCRE_ERROR_INTERNAL); - } - } - - /* If min = max, continue at the same level without recursing */ - - if (min == max) continue; - - /* If minimizing, we have to test the rest of the pattern before each - subsequent match. Again, separate the UTF-8 case for speed, and also - separate the UCP cases. */ - - if (minimize) - { -#ifdef SUPPORT_UCP - if (prop_type >= 0) - { - switch(prop_type) - { - case PT_ANY: - for (fi = min;; fi++) - { - RMATCH(eptr, ecode, offset_top, md, eptrb, RM36); - if (rrc != MATCH_NOMATCH) RRETURN(rrc); - if (fi >= max) RRETURN(MATCH_NOMATCH); - if (eptr >= md->end_subject) - { - SCHECK_PARTIAL(); - RRETURN(MATCH_NOMATCH); - } - GETCHARINCTEST(c, eptr); - if (prop_fail_result) RRETURN(MATCH_NOMATCH); - } - /* Control never gets here */ - - case PT_LAMP: - for (fi = min;; fi++) - { - int chartype; - RMATCH(eptr, ecode, offset_top, md, eptrb, RM37); - if (rrc != MATCH_NOMATCH) RRETURN(rrc); - if (fi >= max) RRETURN(MATCH_NOMATCH); - if (eptr >= md->end_subject) - { - SCHECK_PARTIAL(); - RRETURN(MATCH_NOMATCH); - } - GETCHARINCTEST(c, eptr); - chartype = UCD_CHARTYPE(c); - if ((chartype == ucp_Lu || - chartype == ucp_Ll || - chartype == ucp_Lt) == prop_fail_result) - RRETURN(MATCH_NOMATCH); - } - /* Control never gets here */ - - case PT_GC: - for (fi = min;; fi++) - { - RMATCH(eptr, ecode, offset_top, md, eptrb, RM38); - if (rrc != MATCH_NOMATCH) RRETURN(rrc); - if (fi >= max) RRETURN(MATCH_NOMATCH); - if (eptr >= md->end_subject) - { - SCHECK_PARTIAL(); - RRETURN(MATCH_NOMATCH); - } - GETCHARINCTEST(c, eptr); - if ((UCD_CATEGORY(c) == prop_value) == prop_fail_result) - RRETURN(MATCH_NOMATCH); - } - /* Control never gets here */ - - case PT_PC: - for (fi = min;; fi++) - { - RMATCH(eptr, ecode, offset_top, md, eptrb, RM39); - if (rrc != MATCH_NOMATCH) RRETURN(rrc); - if (fi >= max) RRETURN(MATCH_NOMATCH); - if (eptr >= md->end_subject) - { - SCHECK_PARTIAL(); - RRETURN(MATCH_NOMATCH); - } - GETCHARINCTEST(c, eptr); - if ((UCD_CHARTYPE(c) == prop_value) == prop_fail_result) - RRETURN(MATCH_NOMATCH); - } - /* Control never gets here */ - - case PT_SC: - for (fi = min;; fi++) - { - RMATCH(eptr, ecode, offset_top, md, eptrb, RM40); - if (rrc != MATCH_NOMATCH) RRETURN(rrc); - if (fi >= max) RRETURN(MATCH_NOMATCH); - if (eptr >= md->end_subject) - { - SCHECK_PARTIAL(); - RRETURN(MATCH_NOMATCH); - } - GETCHARINCTEST(c, eptr); - if ((UCD_SCRIPT(c) == prop_value) == prop_fail_result) - RRETURN(MATCH_NOMATCH); - } - /* Control never gets here */ - - case PT_ALNUM: - for (fi = min;; fi++) - { - int category; - RMATCH(eptr, ecode, offset_top, md, eptrb, RM59); - if (rrc != MATCH_NOMATCH) RRETURN(rrc); - if (fi >= max) RRETURN(MATCH_NOMATCH); - if (eptr >= md->end_subject) - { - SCHECK_PARTIAL(); - RRETURN(MATCH_NOMATCH); - } - GETCHARINCTEST(c, eptr); - category = UCD_CATEGORY(c); - if ((category == ucp_L || category == ucp_N) == prop_fail_result) - RRETURN(MATCH_NOMATCH); - } - /* Control never gets here */ - - /* Perl space used to exclude VT, but from Perl 5.18 it is included, - which means that Perl space and POSIX space are now identical. PCRE - was changed at release 8.34. */ - - case PT_SPACE: /* Perl space */ - case PT_PXSPACE: /* POSIX space */ - for (fi = min;; fi++) - { - RMATCH(eptr, ecode, offset_top, md, eptrb, RM61); - if (rrc != MATCH_NOMATCH) RRETURN(rrc); - if (fi >= max) RRETURN(MATCH_NOMATCH); - if (eptr >= md->end_subject) - { - SCHECK_PARTIAL(); - RRETURN(MATCH_NOMATCH); - } - GETCHARINCTEST(c, eptr); - switch(c) - { - HSPACE_CASES: - VSPACE_CASES: - if (prop_fail_result) RRETURN(MATCH_NOMATCH); - break; - - default: - if ((UCD_CATEGORY(c) == ucp_Z) == prop_fail_result) - RRETURN(MATCH_NOMATCH); - break; - } - } - /* Control never gets here */ - - case PT_WORD: - for (fi = min;; fi++) - { - int category; - RMATCH(eptr, ecode, offset_top, md, eptrb, RM62); - if (rrc != MATCH_NOMATCH) RRETURN(rrc); - if (fi >= max) RRETURN(MATCH_NOMATCH); - if (eptr >= md->end_subject) - { - SCHECK_PARTIAL(); - RRETURN(MATCH_NOMATCH); - } - GETCHARINCTEST(c, eptr); - category = UCD_CATEGORY(c); - if ((category == ucp_L || - category == ucp_N || - c == CHAR_UNDERSCORE) - == prop_fail_result) - RRETURN(MATCH_NOMATCH); - } - /* Control never gets here */ - - case PT_CLIST: - for (fi = min;; fi++) - { - const pcre_uint32 *cp; - RMATCH(eptr, ecode, offset_top, md, eptrb, RM67); - if (rrc != MATCH_NOMATCH) RRETURN(rrc); - if (fi >= max) RRETURN(MATCH_NOMATCH); - if (eptr >= md->end_subject) - { - SCHECK_PARTIAL(); - RRETURN(MATCH_NOMATCH); - } - GETCHARINCTEST(c, eptr); - cp = PRIV(ucd_caseless_sets) + prop_value; - for (;;) - { - if (c < *cp) - { if (prop_fail_result) break; else { RRETURN(MATCH_NOMATCH); } } - if (c == *cp++) - { if (prop_fail_result) { RRETURN(MATCH_NOMATCH); } else break; } - } - } - /* Control never gets here */ - - case PT_UCNC: - for (fi = min;; fi++) - { - RMATCH(eptr, ecode, offset_top, md, eptrb, RM60); - if (rrc != MATCH_NOMATCH) RRETURN(rrc); - if (fi >= max) RRETURN(MATCH_NOMATCH); - if (eptr >= md->end_subject) - { - SCHECK_PARTIAL(); - RRETURN(MATCH_NOMATCH); - } - GETCHARINCTEST(c, eptr); - if ((c == CHAR_DOLLAR_SIGN || c == CHAR_COMMERCIAL_AT || - c == CHAR_GRAVE_ACCENT || (c >= 0xa0 && c <= 0xd7ff) || - c >= 0xe000) == prop_fail_result) - RRETURN(MATCH_NOMATCH); - } - /* Control never gets here */ - - /* This should never occur */ - default: - RRETURN(PCRE_ERROR_INTERNAL); - } - } - - /* Match extended Unicode sequences. We will get here only if the - support is in the binary; otherwise a compile-time error occurs. */ - - else if (ctype == OP_EXTUNI) - { - for (fi = min;; fi++) - { - RMATCH(eptr, ecode, offset_top, md, eptrb, RM41); - if (rrc != MATCH_NOMATCH) RRETURN(rrc); - if (fi >= max) RRETURN(MATCH_NOMATCH); - if (eptr >= md->end_subject) - { - SCHECK_PARTIAL(); - RRETURN(MATCH_NOMATCH); - } - else - { - int lgb, rgb; - GETCHARINCTEST(c, eptr); - lgb = UCD_GRAPHBREAK(c); - while (eptr < md->end_subject) - { - int len = 1; - if (!utf) c = *eptr; else { GETCHARLEN(c, eptr, len); } - rgb = UCD_GRAPHBREAK(c); - if ((PRIV(ucp_gbtable)[lgb] & (1 << rgb)) == 0) break; - lgb = rgb; - eptr += len; - } - } - CHECK_PARTIAL(); - } - } - else -#endif /* SUPPORT_UCP */ - -#ifdef SUPPORT_UTF - if (utf) - { - for (fi = min;; fi++) - { - RMATCH(eptr, ecode, offset_top, md, eptrb, RM42); - if (rrc != MATCH_NOMATCH) RRETURN(rrc); - if (fi >= max) RRETURN(MATCH_NOMATCH); - if (eptr >= md->end_subject) - { - SCHECK_PARTIAL(); - RRETURN(MATCH_NOMATCH); - } - if (ctype == OP_ANY && IS_NEWLINE(eptr)) - RRETURN(MATCH_NOMATCH); - GETCHARINC(c, eptr); - switch(ctype) - { - case OP_ANY: /* This is the non-NL case */ - if (md->partial != 0 && /* Take care with CRLF partial */ - eptr >= md->end_subject && - NLBLOCK->nltype == NLTYPE_FIXED && - NLBLOCK->nllen == 2 && - c == NLBLOCK->nl[0]) - { - md->hitend = TRUE; - if (md->partial > 1) RRETURN(PCRE_ERROR_PARTIAL); - } - break; - - case OP_ALLANY: - case OP_ANYBYTE: - break; - - case OP_ANYNL: - switch(c) - { - default: RRETURN(MATCH_NOMATCH); - case CHAR_CR: - if (eptr < md->end_subject && UCHAR21(eptr) == CHAR_LF) eptr++; - break; - - case CHAR_LF: - break; - - case CHAR_VT: - case CHAR_FF: - case CHAR_NEL: -#ifndef EBCDIC - case 0x2028: - case 0x2029: -#endif /* Not EBCDIC */ - if (md->bsr_anycrlf) RRETURN(MATCH_NOMATCH); - break; - } - break; - - case OP_NOT_HSPACE: - switch(c) - { - HSPACE_CASES: RRETURN(MATCH_NOMATCH); - default: break; - } - break; - - case OP_HSPACE: - switch(c) - { - HSPACE_CASES: break; - default: RRETURN(MATCH_NOMATCH); - } - break; - - case OP_NOT_VSPACE: - switch(c) - { - VSPACE_CASES: RRETURN(MATCH_NOMATCH); - default: break; - } - break; - - case OP_VSPACE: - switch(c) - { - VSPACE_CASES: break; - default: RRETURN(MATCH_NOMATCH); - } - break; - - case OP_NOT_DIGIT: - if (c < 256 && (md->ctypes[c] & ctype_digit) != 0) - RRETURN(MATCH_NOMATCH); - break; - - case OP_DIGIT: - if (c >= 256 || (md->ctypes[c] & ctype_digit) == 0) - RRETURN(MATCH_NOMATCH); - break; - - case OP_NOT_WHITESPACE: - if (c < 256 && (md->ctypes[c] & ctype_space) != 0) - RRETURN(MATCH_NOMATCH); - break; - - case OP_WHITESPACE: - if (c >= 256 || (md->ctypes[c] & ctype_space) == 0) - RRETURN(MATCH_NOMATCH); - break; - - case OP_NOT_WORDCHAR: - if (c < 256 && (md->ctypes[c] & ctype_word) != 0) - RRETURN(MATCH_NOMATCH); - break; - - case OP_WORDCHAR: - if (c >= 256 || (md->ctypes[c] & ctype_word) == 0) - RRETURN(MATCH_NOMATCH); - break; - - default: - RRETURN(PCRE_ERROR_INTERNAL); - } - } - } - else -#endif - /* Not UTF mode */ - { - for (fi = min;; fi++) - { - RMATCH(eptr, ecode, offset_top, md, eptrb, RM43); - if (rrc != MATCH_NOMATCH) RRETURN(rrc); - if (fi >= max) RRETURN(MATCH_NOMATCH); - if (eptr >= md->end_subject) - { - SCHECK_PARTIAL(); - RRETURN(MATCH_NOMATCH); - } - if (ctype == OP_ANY && IS_NEWLINE(eptr)) - RRETURN(MATCH_NOMATCH); - c = *eptr++; - switch(ctype) - { - case OP_ANY: /* This is the non-NL case */ - if (md->partial != 0 && /* Take care with CRLF partial */ - eptr >= md->end_subject && - NLBLOCK->nltype == NLTYPE_FIXED && - NLBLOCK->nllen == 2 && - c == NLBLOCK->nl[0]) - { - md->hitend = TRUE; - if (md->partial > 1) RRETURN(PCRE_ERROR_PARTIAL); - } - break; - - case OP_ALLANY: - case OP_ANYBYTE: - break; - - case OP_ANYNL: - switch(c) - { - default: RRETURN(MATCH_NOMATCH); - case CHAR_CR: - if (eptr < md->end_subject && *eptr == CHAR_LF) eptr++; - break; - - case CHAR_LF: - break; - - case CHAR_VT: - case CHAR_FF: - case CHAR_NEL: -#if defined COMPILE_PCRE16 || defined COMPILE_PCRE32 - case 0x2028: - case 0x2029: -#endif - if (md->bsr_anycrlf) RRETURN(MATCH_NOMATCH); - break; - } - break; - - case OP_NOT_HSPACE: - switch(c) - { - default: break; - HSPACE_BYTE_CASES: -#if defined COMPILE_PCRE16 || defined COMPILE_PCRE32 - HSPACE_MULTIBYTE_CASES: -#endif - RRETURN(MATCH_NOMATCH); - } - break; - - case OP_HSPACE: - switch(c) - { - default: RRETURN(MATCH_NOMATCH); - HSPACE_BYTE_CASES: -#if defined COMPILE_PCRE16 || defined COMPILE_PCRE32 - HSPACE_MULTIBYTE_CASES: -#endif - break; - } - break; - - case OP_NOT_VSPACE: - switch(c) - { - default: break; - VSPACE_BYTE_CASES: -#if defined COMPILE_PCRE16 || defined COMPILE_PCRE32 - VSPACE_MULTIBYTE_CASES: -#endif - RRETURN(MATCH_NOMATCH); - } - break; - - case OP_VSPACE: - switch(c) - { - default: RRETURN(MATCH_NOMATCH); - VSPACE_BYTE_CASES: -#if defined COMPILE_PCRE16 || defined COMPILE_PCRE32 - VSPACE_MULTIBYTE_CASES: -#endif - break; - } - break; - - case OP_NOT_DIGIT: - if (MAX_255(c) && (md->ctypes[c] & ctype_digit) != 0) RRETURN(MATCH_NOMATCH); - break; - - case OP_DIGIT: - if (!MAX_255(c) || (md->ctypes[c] & ctype_digit) == 0) RRETURN(MATCH_NOMATCH); - break; - - case OP_NOT_WHITESPACE: - if (MAX_255(c) && (md->ctypes[c] & ctype_space) != 0) RRETURN(MATCH_NOMATCH); - break; - - case OP_WHITESPACE: - if (!MAX_255(c) || (md->ctypes[c] & ctype_space) == 0) RRETURN(MATCH_NOMATCH); - break; - - case OP_NOT_WORDCHAR: - if (MAX_255(c) && (md->ctypes[c] & ctype_word) != 0) RRETURN(MATCH_NOMATCH); - break; - - case OP_WORDCHAR: - if (!MAX_255(c) || (md->ctypes[c] & ctype_word) == 0) RRETURN(MATCH_NOMATCH); - break; - - default: - RRETURN(PCRE_ERROR_INTERNAL); - } - } - } - /* Control never gets here */ - } - - /* If maximizing, it is worth using inline code for speed, doing the type - test once at the start (i.e. keep it out of the loop). Again, keep the - UTF-8 and UCP stuff separate. */ - - else - { - pp = eptr; /* Remember where we started */ - -#ifdef SUPPORT_UCP - if (prop_type >= 0) - { - switch(prop_type) - { - case PT_ANY: - for (i = min; i < max; i++) - { - int len = 1; - if (eptr >= md->end_subject) - { - SCHECK_PARTIAL(); - break; - } - GETCHARLENTEST(c, eptr, len); - if (prop_fail_result) break; - eptr+= len; - } - break; - - case PT_LAMP: - for (i = min; i < max; i++) - { - int chartype; - int len = 1; - if (eptr >= md->end_subject) - { - SCHECK_PARTIAL(); - break; - } - GETCHARLENTEST(c, eptr, len); - chartype = UCD_CHARTYPE(c); - if ((chartype == ucp_Lu || - chartype == ucp_Ll || - chartype == ucp_Lt) == prop_fail_result) - break; - eptr+= len; - } - break; - - case PT_GC: - for (i = min; i < max; i++) - { - int len = 1; - if (eptr >= md->end_subject) - { - SCHECK_PARTIAL(); - break; - } - GETCHARLENTEST(c, eptr, len); - if ((UCD_CATEGORY(c) == prop_value) == prop_fail_result) break; - eptr+= len; - } - break; - - case PT_PC: - for (i = min; i < max; i++) - { - int len = 1; - if (eptr >= md->end_subject) - { - SCHECK_PARTIAL(); - break; - } - GETCHARLENTEST(c, eptr, len); - if ((UCD_CHARTYPE(c) == prop_value) == prop_fail_result) break; - eptr+= len; - } - break; - - case PT_SC: - for (i = min; i < max; i++) - { - int len = 1; - if (eptr >= md->end_subject) - { - SCHECK_PARTIAL(); - break; - } - GETCHARLENTEST(c, eptr, len); - if ((UCD_SCRIPT(c) == prop_value) == prop_fail_result) break; - eptr+= len; - } - break; - - case PT_ALNUM: - for (i = min; i < max; i++) - { - int category; - int len = 1; - if (eptr >= md->end_subject) - { - SCHECK_PARTIAL(); - break; - } - GETCHARLENTEST(c, eptr, len); - category = UCD_CATEGORY(c); - if ((category == ucp_L || category == ucp_N) == prop_fail_result) - break; - eptr+= len; - } - break; - - /* Perl space used to exclude VT, but from Perl 5.18 it is included, - which means that Perl space and POSIX space are now identical. PCRE - was changed at release 8.34. */ - - case PT_SPACE: /* Perl space */ - case PT_PXSPACE: /* POSIX space */ - for (i = min; i < max; i++) - { - int len = 1; - if (eptr >= md->end_subject) - { - SCHECK_PARTIAL(); - break; - } - GETCHARLENTEST(c, eptr, len); - switch(c) - { - HSPACE_CASES: - VSPACE_CASES: - if (prop_fail_result) goto ENDLOOP99; /* Break the loop */ - break; - - default: - if ((UCD_CATEGORY(c) == ucp_Z) == prop_fail_result) - goto ENDLOOP99; /* Break the loop */ - break; - } - eptr+= len; - } - ENDLOOP99: - break; - - case PT_WORD: - for (i = min; i < max; i++) - { - int category; - int len = 1; - if (eptr >= md->end_subject) - { - SCHECK_PARTIAL(); - break; - } - GETCHARLENTEST(c, eptr, len); - category = UCD_CATEGORY(c); - if ((category == ucp_L || category == ucp_N || - c == CHAR_UNDERSCORE) == prop_fail_result) - break; - eptr+= len; - } - break; - - case PT_CLIST: - for (i = min; i < max; i++) - { - const pcre_uint32 *cp; - int len = 1; - if (eptr >= md->end_subject) - { - SCHECK_PARTIAL(); - break; - } - GETCHARLENTEST(c, eptr, len); - cp = PRIV(ucd_caseless_sets) + prop_value; - for (;;) - { - if (c < *cp) - { if (prop_fail_result) break; else goto GOT_MAX; } - if (c == *cp++) - { if (prop_fail_result) goto GOT_MAX; else break; } - } - eptr += len; - } - GOT_MAX: - break; - - case PT_UCNC: - for (i = min; i < max; i++) - { - int len = 1; - if (eptr >= md->end_subject) - { - SCHECK_PARTIAL(); - break; - } - GETCHARLENTEST(c, eptr, len); - if ((c == CHAR_DOLLAR_SIGN || c == CHAR_COMMERCIAL_AT || - c == CHAR_GRAVE_ACCENT || (c >= 0xa0 && c <= 0xd7ff) || - c >= 0xe000) == prop_fail_result) - break; - eptr += len; - } - break; - - default: - RRETURN(PCRE_ERROR_INTERNAL); - } - - /* eptr is now past the end of the maximum run */ - - if (possessive) continue; /* No backtracking */ - for(;;) - { - if (eptr <= pp) goto TAIL_RECURSE; - RMATCH(eptr, ecode, offset_top, md, eptrb, RM44); - if (rrc != MATCH_NOMATCH) RRETURN(rrc); - eptr--; - if (utf) BACKCHAR(eptr); - } - } - - /* Match extended Unicode grapheme clusters. We will get here only if the - support is in the binary; otherwise a compile-time error occurs. */ - - else if (ctype == OP_EXTUNI) - { - for (i = min; i < max; i++) - { - if (eptr >= md->end_subject) - { - SCHECK_PARTIAL(); - break; - } - else - { - int lgb, rgb; - GETCHARINCTEST(c, eptr); - lgb = UCD_GRAPHBREAK(c); - while (eptr < md->end_subject) - { - int len = 1; - if (!utf) c = *eptr; else { GETCHARLEN(c, eptr, len); } - rgb = UCD_GRAPHBREAK(c); - if ((PRIV(ucp_gbtable)[lgb] & (1 << rgb)) == 0) break; - lgb = rgb; - eptr += len; - } - } - CHECK_PARTIAL(); - } - - /* eptr is now past the end of the maximum run */ - - if (possessive) continue; /* No backtracking */ - - /* We use <= pp rather than == pp to detect the start of the run while - backtracking because the use of \C in UTF mode can cause BACKCHAR to - move back past pp. This is just palliative; the use of \C in UTF mode - is fraught with danger. */ - - for(;;) - { - int lgb, rgb; - PCRE_PUCHAR fptr; - - if (eptr <= pp) goto TAIL_RECURSE; /* At start of char run */ - RMATCH(eptr, ecode, offset_top, md, eptrb, RM45); - if (rrc != MATCH_NOMATCH) RRETURN(rrc); - - /* Backtracking over an extended grapheme cluster involves inspecting - the previous two characters (if present) to see if a break is - permitted between them. */ - - eptr--; - if (!utf) c = *eptr; else - { - BACKCHAR(eptr); - GETCHAR(c, eptr); - } - rgb = UCD_GRAPHBREAK(c); - - for (;;) - { - if (eptr <= pp) goto TAIL_RECURSE; /* At start of char run */ - fptr = eptr - 1; - if (!utf) c = *fptr; else - { - BACKCHAR(fptr); - GETCHAR(c, fptr); - } - lgb = UCD_GRAPHBREAK(c); - if ((PRIV(ucp_gbtable)[lgb] & (1 << rgb)) == 0) break; - eptr = fptr; - rgb = lgb; - } - } - } - - else -#endif /* SUPPORT_UCP */ - -#ifdef SUPPORT_UTF - if (utf) - { - switch(ctype) - { - case OP_ANY: - for (i = min; i < max; i++) - { - if (eptr >= md->end_subject) - { - SCHECK_PARTIAL(); - break; - } - if (IS_NEWLINE(eptr)) break; - if (md->partial != 0 && /* Take care with CRLF partial */ - eptr + 1 >= md->end_subject && - NLBLOCK->nltype == NLTYPE_FIXED && - NLBLOCK->nllen == 2 && - UCHAR21(eptr) == NLBLOCK->nl[0]) - { - md->hitend = TRUE; - if (md->partial > 1) RRETURN(PCRE_ERROR_PARTIAL); - } - eptr++; - ACROSSCHAR(eptr < md->end_subject, *eptr, eptr++); - } - break; - - case OP_ALLANY: - if (max < INT_MAX) - { - for (i = min; i < max; i++) - { - if (eptr >= md->end_subject) - { - SCHECK_PARTIAL(); - break; - } - eptr++; - ACROSSCHAR(eptr < md->end_subject, *eptr, eptr++); - } - } - else - { - eptr = md->end_subject; /* Unlimited UTF-8 repeat */ - SCHECK_PARTIAL(); - } - break; - - /* The byte case is the same as non-UTF8 */ - - case OP_ANYBYTE: - c = max - min; - if (c > (unsigned int)(md->end_subject - eptr)) - { - eptr = md->end_subject; - SCHECK_PARTIAL(); - } - else eptr += c; - break; - - case OP_ANYNL: - for (i = min; i < max; i++) - { - int len = 1; - if (eptr >= md->end_subject) - { - SCHECK_PARTIAL(); - break; - } - GETCHARLEN(c, eptr, len); - if (c == CHAR_CR) - { - if (++eptr >= md->end_subject) break; - if (UCHAR21(eptr) == CHAR_LF) eptr++; - } - else - { - if (c != CHAR_LF && - (md->bsr_anycrlf || - (c != CHAR_VT && c != CHAR_FF && c != CHAR_NEL -#ifndef EBCDIC - && c != 0x2028 && c != 0x2029 -#endif /* Not EBCDIC */ - ))) - break; - eptr += len; - } - } - break; - - case OP_NOT_HSPACE: - case OP_HSPACE: - for (i = min; i < max; i++) - { - BOOL gotspace; - int len = 1; - if (eptr >= md->end_subject) - { - SCHECK_PARTIAL(); - break; - } - GETCHARLEN(c, eptr, len); - switch(c) - { - HSPACE_CASES: gotspace = TRUE; break; - default: gotspace = FALSE; break; - } - if (gotspace == (ctype == OP_NOT_HSPACE)) break; - eptr += len; - } - break; - - case OP_NOT_VSPACE: - case OP_VSPACE: - for (i = min; i < max; i++) - { - BOOL gotspace; - int len = 1; - if (eptr >= md->end_subject) - { - SCHECK_PARTIAL(); - break; - } - GETCHARLEN(c, eptr, len); - switch(c) - { - VSPACE_CASES: gotspace = TRUE; break; - default: gotspace = FALSE; break; - } - if (gotspace == (ctype == OP_NOT_VSPACE)) break; - eptr += len; - } - break; - - case OP_NOT_DIGIT: - for (i = min; i < max; i++) - { - int len = 1; - if (eptr >= md->end_subject) - { - SCHECK_PARTIAL(); - break; - } - GETCHARLEN(c, eptr, len); - if (c < 256 && (md->ctypes[c] & ctype_digit) != 0) break; - eptr+= len; - } - break; - - case OP_DIGIT: - for (i = min; i < max; i++) - { - int len = 1; - if (eptr >= md->end_subject) - { - SCHECK_PARTIAL(); - break; - } - GETCHARLEN(c, eptr, len); - if (c >= 256 ||(md->ctypes[c] & ctype_digit) == 0) break; - eptr+= len; - } - break; - - case OP_NOT_WHITESPACE: - for (i = min; i < max; i++) - { - int len = 1; - if (eptr >= md->end_subject) - { - SCHECK_PARTIAL(); - break; - } - GETCHARLEN(c, eptr, len); - if (c < 256 && (md->ctypes[c] & ctype_space) != 0) break; - eptr+= len; - } - break; - - case OP_WHITESPACE: - for (i = min; i < max; i++) - { - int len = 1; - if (eptr >= md->end_subject) - { - SCHECK_PARTIAL(); - break; - } - GETCHARLEN(c, eptr, len); - if (c >= 256 ||(md->ctypes[c] & ctype_space) == 0) break; - eptr+= len; - } - break; - - case OP_NOT_WORDCHAR: - for (i = min; i < max; i++) - { - int len = 1; - if (eptr >= md->end_subject) - { - SCHECK_PARTIAL(); - break; - } - GETCHARLEN(c, eptr, len); - if (c < 256 && (md->ctypes[c] & ctype_word) != 0) break; - eptr+= len; - } - break; - - case OP_WORDCHAR: - for (i = min; i < max; i++) - { - int len = 1; - if (eptr >= md->end_subject) - { - SCHECK_PARTIAL(); - break; - } - GETCHARLEN(c, eptr, len); - if (c >= 256 || (md->ctypes[c] & ctype_word) == 0) break; - eptr+= len; - } - break; - - default: - RRETURN(PCRE_ERROR_INTERNAL); - } - - if (possessive) continue; /* No backtracking */ - for(;;) - { - if (eptr <= pp) goto TAIL_RECURSE; - RMATCH(eptr, ecode, offset_top, md, eptrb, RM46); - if (rrc != MATCH_NOMATCH) RRETURN(rrc); - eptr--; - BACKCHAR(eptr); - if (ctype == OP_ANYNL && eptr > pp && UCHAR21(eptr) == CHAR_NL && - UCHAR21(eptr - 1) == CHAR_CR) eptr--; - } - } - else -#endif /* SUPPORT_UTF */ - /* Not UTF mode */ - { - switch(ctype) - { - case OP_ANY: - for (i = min; i < max; i++) - { - if (eptr >= md->end_subject) - { - SCHECK_PARTIAL(); - break; - } - if (IS_NEWLINE(eptr)) break; - if (md->partial != 0 && /* Take care with CRLF partial */ - eptr + 1 >= md->end_subject && - NLBLOCK->nltype == NLTYPE_FIXED && - NLBLOCK->nllen == 2 && - *eptr == NLBLOCK->nl[0]) - { - md->hitend = TRUE; - if (md->partial > 1) RRETURN(PCRE_ERROR_PARTIAL); - } - eptr++; - } - break; - - case OP_ALLANY: - case OP_ANYBYTE: - c = max - min; - if (c > (unsigned int)(md->end_subject - eptr)) - { - eptr = md->end_subject; - SCHECK_PARTIAL(); - } - else eptr += c; - break; - - case OP_ANYNL: - for (i = min; i < max; i++) - { - if (eptr >= md->end_subject) - { - SCHECK_PARTIAL(); - break; - } - c = *eptr; - if (c == CHAR_CR) - { - if (++eptr >= md->end_subject) break; - if (*eptr == CHAR_LF) eptr++; - } - else - { - if (c != CHAR_LF && (md->bsr_anycrlf || - (c != CHAR_VT && c != CHAR_FF && c != CHAR_NEL -#if defined COMPILE_PCRE16 || defined COMPILE_PCRE32 - && c != 0x2028 && c != 0x2029 -#endif - ))) break; - eptr++; - } - } - break; - - case OP_NOT_HSPACE: - for (i = min; i < max; i++) - { - if (eptr >= md->end_subject) - { - SCHECK_PARTIAL(); - break; - } - switch(*eptr) - { - default: eptr++; break; - HSPACE_BYTE_CASES: -#if defined COMPILE_PCRE16 || defined COMPILE_PCRE32 - HSPACE_MULTIBYTE_CASES: -#endif - goto ENDLOOP00; - } - } - ENDLOOP00: - break; - - case OP_HSPACE: - for (i = min; i < max; i++) - { - if (eptr >= md->end_subject) - { - SCHECK_PARTIAL(); - break; - } - switch(*eptr) - { - default: goto ENDLOOP01; - HSPACE_BYTE_CASES: -#if defined COMPILE_PCRE16 || defined COMPILE_PCRE32 - HSPACE_MULTIBYTE_CASES: -#endif - eptr++; break; - } - } - ENDLOOP01: - break; - - case OP_NOT_VSPACE: - for (i = min; i < max; i++) - { - if (eptr >= md->end_subject) - { - SCHECK_PARTIAL(); - break; - } - switch(*eptr) - { - default: eptr++; break; - VSPACE_BYTE_CASES: -#if defined COMPILE_PCRE16 || defined COMPILE_PCRE32 - VSPACE_MULTIBYTE_CASES: -#endif - goto ENDLOOP02; - } - } - ENDLOOP02: - break; - - case OP_VSPACE: - for (i = min; i < max; i++) - { - if (eptr >= md->end_subject) - { - SCHECK_PARTIAL(); - break; - } - switch(*eptr) - { - default: goto ENDLOOP03; - VSPACE_BYTE_CASES: -#if defined COMPILE_PCRE16 || defined COMPILE_PCRE32 - VSPACE_MULTIBYTE_CASES: -#endif - eptr++; break; - } - } - ENDLOOP03: - break; - - case OP_NOT_DIGIT: - for (i = min; i < max; i++) - { - if (eptr >= md->end_subject) - { - SCHECK_PARTIAL(); - break; - } - if (MAX_255(*eptr) && (md->ctypes[*eptr] & ctype_digit) != 0) break; - eptr++; - } - break; - - case OP_DIGIT: - for (i = min; i < max; i++) - { - if (eptr >= md->end_subject) - { - SCHECK_PARTIAL(); - break; - } - if (!MAX_255(*eptr) || (md->ctypes[*eptr] & ctype_digit) == 0) break; - eptr++; - } - break; - - case OP_NOT_WHITESPACE: - for (i = min; i < max; i++) - { - if (eptr >= md->end_subject) - { - SCHECK_PARTIAL(); - break; - } - if (MAX_255(*eptr) && (md->ctypes[*eptr] & ctype_space) != 0) break; - eptr++; - } - break; - - case OP_WHITESPACE: - for (i = min; i < max; i++) - { - if (eptr >= md->end_subject) - { - SCHECK_PARTIAL(); - break; - } - if (!MAX_255(*eptr) || (md->ctypes[*eptr] & ctype_space) == 0) break; - eptr++; - } - break; - - case OP_NOT_WORDCHAR: - for (i = min; i < max; i++) - { - if (eptr >= md->end_subject) - { - SCHECK_PARTIAL(); - break; - } - if (MAX_255(*eptr) && (md->ctypes[*eptr] & ctype_word) != 0) break; - eptr++; - } - break; - - case OP_WORDCHAR: - for (i = min; i < max; i++) - { - if (eptr >= md->end_subject) - { - SCHECK_PARTIAL(); - break; - } - if (!MAX_255(*eptr) || (md->ctypes[*eptr] & ctype_word) == 0) break; - eptr++; - } - break; - - default: - RRETURN(PCRE_ERROR_INTERNAL); - } - - if (possessive) continue; /* No backtracking */ - for (;;) - { - if (eptr == pp) goto TAIL_RECURSE; - RMATCH(eptr, ecode, offset_top, md, eptrb, RM47); - if (rrc != MATCH_NOMATCH) RRETURN(rrc); - eptr--; - if (ctype == OP_ANYNL && eptr > pp && *eptr == CHAR_LF && - eptr[-1] == CHAR_CR) eptr--; - } - } - - /* Control never gets here */ - } - - /* There's been some horrible disaster. Arrival here can only mean there is - something seriously wrong in the code above or the OP_xxx definitions. */ - - default: - DPRINTF(("Unknown opcode %d\n", *ecode)); - RRETURN(PCRE_ERROR_UNKNOWN_OPCODE); - } - - /* Do not stick any code in here without much thought; it is assumed - that "continue" in the code above comes out to here to repeat the main - loop. */ - - } /* End of main loop */ -/* Control never reaches here */ - - -/* When compiling to use the heap rather than the stack for recursive calls to -match(), the RRETURN() macro jumps here. The number that is saved in -frame->Xwhere indicates which label we actually want to return to. */ - -#ifdef NO_RECURSE -#define LBL(val) case val: goto L_RM##val; -HEAP_RETURN: -switch (frame->Xwhere) - { - LBL( 1) LBL( 2) LBL( 3) LBL( 4) LBL( 5) LBL( 6) LBL( 7) LBL( 8) - LBL( 9) LBL(10) LBL(11) LBL(12) LBL(13) LBL(14) LBL(15) LBL(17) - LBL(19) LBL(24) LBL(25) LBL(26) LBL(27) LBL(29) LBL(31) LBL(33) - LBL(35) LBL(43) LBL(47) LBL(48) LBL(49) LBL(50) LBL(51) LBL(52) - LBL(53) LBL(54) LBL(55) LBL(56) LBL(57) LBL(58) LBL(63) LBL(64) - LBL(65) LBL(66) -#if defined SUPPORT_UTF || !defined COMPILE_PCRE8 - LBL(20) LBL(21) -#endif -#ifdef SUPPORT_UTF - LBL(16) LBL(18) - LBL(22) LBL(23) LBL(28) LBL(30) - LBL(32) LBL(34) LBL(42) LBL(46) -#ifdef SUPPORT_UCP - LBL(36) LBL(37) LBL(38) LBL(39) LBL(40) LBL(41) LBL(44) LBL(45) - LBL(59) LBL(60) LBL(61) LBL(62) LBL(67) -#endif /* SUPPORT_UCP */ -#endif /* SUPPORT_UTF */ - default: - DPRINTF(("jump error in pcre match: label %d non-existent\n", frame->Xwhere)); - return PCRE_ERROR_INTERNAL; - } -#undef LBL -#endif /* NO_RECURSE */ -} - - -/*************************************************************************** -**************************************************************************** - RECURSION IN THE match() FUNCTION - -Undefine all the macros that were defined above to handle this. */ - -#ifdef NO_RECURSE -#undef eptr -#undef ecode -#undef mstart -#undef offset_top -#undef eptrb -#undef flags - -#undef callpat -#undef charptr -#undef data -#undef next -#undef pp -#undef prev -#undef saved_eptr - -#undef new_recursive - -#undef cur_is_word -#undef condition -#undef prev_is_word - -#undef ctype -#undef length -#undef max -#undef min -#undef number -#undef offset -#undef op -#undef save_capture_last -#undef save_offset1 -#undef save_offset2 -#undef save_offset3 -#undef stacksave - -#undef newptrb - -#endif - -/* These two are defined as macros in both cases */ - -#undef fc -#undef fi - -/*************************************************************************** -***************************************************************************/ - - -#ifdef NO_RECURSE -/************************************************* -* Release allocated heap frames * -*************************************************/ - -/* This function releases all the allocated frames. The base frame is on the -machine stack, and so must not be freed. - -Argument: the address of the base frame -Returns: nothing -*/ - -static void -release_match_heapframes (heapframe *frame_base) -{ -heapframe *nextframe = frame_base->Xnextframe; -while (nextframe != NULL) - { - heapframe *oldframe = nextframe; - nextframe = nextframe->Xnextframe; - (PUBL(stack_free))(oldframe); - } -} -#endif - - -/************************************************* -* Execute a Regular Expression * -*************************************************/ - -/* This function applies a compiled re to a subject string and picks out -portions of the string if it matches. Two elements in the vector are set for -each substring: the offsets to the start and end of the substring. - -Arguments: - argument_re points to the compiled expression - extra_data points to extra data or is NULL - subject points to the subject string - length length of subject string (may contain binary zeros) - start_offset where to start in the subject string - options option bits - offsets points to a vector of ints to be filled in with offsets - offsetcount the number of elements in the vector - -Returns: > 0 => success; value is the number of elements filled in - = 0 => success, but offsets is not big enough - -1 => failed to match - < -1 => some kind of unexpected problem -*/ - -#if defined COMPILE_PCRE8 -PCRE_EXP_DEFN int PCRE_CALL_CONVENTION -pcre_exec(const pcre *argument_re, const pcre_extra *extra_data, - PCRE_SPTR subject, int length, int start_offset, int options, int *offsets, - int offsetcount) -#elif defined COMPILE_PCRE16 -PCRE_EXP_DEFN int PCRE_CALL_CONVENTION -pcre16_exec(const pcre16 *argument_re, const pcre16_extra *extra_data, - PCRE_SPTR16 subject, int length, int start_offset, int options, int *offsets, - int offsetcount) -#elif defined COMPILE_PCRE32 -PCRE_EXP_DEFN int PCRE_CALL_CONVENTION -pcre32_exec(const pcre32 *argument_re, const pcre32_extra *extra_data, - PCRE_SPTR32 subject, int length, int start_offset, int options, int *offsets, - int offsetcount) -#endif -{ -int rc, ocount, arg_offset_max; -int newline; -BOOL using_temporary_offsets = FALSE; -BOOL anchored; -BOOL startline; -BOOL firstline; -BOOL utf; -BOOL has_first_char = FALSE; -BOOL has_req_char = FALSE; -pcre_uchar first_char = 0; -pcre_uchar first_char2 = 0; -pcre_uchar req_char = 0; -pcre_uchar req_char2 = 0; -match_data match_block; -match_data *md = &match_block; -const pcre_uint8 *tables; -const pcre_uint8 *start_bits = NULL; -PCRE_PUCHAR start_match = (PCRE_PUCHAR)subject + start_offset; -PCRE_PUCHAR end_subject; -PCRE_PUCHAR start_partial = NULL; -PCRE_PUCHAR match_partial = NULL; -PCRE_PUCHAR req_char_ptr = start_match - 1; - -const pcre_study_data *study; -const REAL_PCRE *re = (const REAL_PCRE *)argument_re; - -#ifdef NO_RECURSE -heapframe frame_zero; -frame_zero.Xprevframe = NULL; /* Marks the top level */ -frame_zero.Xnextframe = NULL; /* None are allocated yet */ -md->match_frames_base = &frame_zero; -#endif - -/* Check for the special magic call that measures the size of the stack used -per recursive call of match(). Without the funny casting for sizeof, a Windows -compiler gave this error: "unary minus operator applied to unsigned type, -result still unsigned". Hopefully the cast fixes that. */ - -if (re == NULL && extra_data == NULL && subject == NULL && length == -999 && - start_offset == -999) -#ifdef NO_RECURSE - return -((int)sizeof(heapframe)); -#else - return match(NULL, NULL, NULL, 0, NULL, NULL, 0); -#endif - -/* Plausibility checks */ - -if ((options & ~PUBLIC_EXEC_OPTIONS) != 0) return PCRE_ERROR_BADOPTION; -if (re == NULL || subject == NULL || (offsets == NULL && offsetcount > 0)) - return PCRE_ERROR_NULL; -if (offsetcount < 0) return PCRE_ERROR_BADCOUNT; -if (length < 0) return PCRE_ERROR_BADLENGTH; -if (start_offset < 0 || start_offset > length) return PCRE_ERROR_BADOFFSET; - -/* Check that the first field in the block is the magic number. If it is not, -return with PCRE_ERROR_BADMAGIC. However, if the magic number is equal to -REVERSED_MAGIC_NUMBER we return with PCRE_ERROR_BADENDIANNESS, which -means that the pattern is likely compiled with different endianness. */ - -if (re->magic_number != MAGIC_NUMBER) - return re->magic_number == REVERSED_MAGIC_NUMBER? - PCRE_ERROR_BADENDIANNESS:PCRE_ERROR_BADMAGIC; -if ((re->flags & PCRE_MODE) == 0) return PCRE_ERROR_BADMODE; - -/* These two settings are used in the code for checking a UTF-8 string that -follows immediately afterwards. Other values in the md block are used only -during "normal" pcre_exec() processing, not when the JIT support is in use, -so they are set up later. */ - -/* PCRE_UTF16 has the same value as PCRE_UTF8. */ -utf = md->utf = (re->options & PCRE_UTF8) != 0; -md->partial = ((options & PCRE_PARTIAL_HARD) != 0)? 2 : - ((options & PCRE_PARTIAL_SOFT) != 0)? 1 : 0; - -/* Check a UTF-8 string if required. Pass back the character offset and error -code for an invalid string if a results vector is available. */ - -#ifdef SUPPORT_UTF -if (utf && (options & PCRE_NO_UTF8_CHECK) == 0) - { - int erroroffset; - int errorcode = PRIV(valid_utf)((PCRE_PUCHAR)subject, length, &erroroffset); - if (errorcode != 0) - { - if (offsetcount >= 2) - { - offsets[0] = erroroffset; - offsets[1] = errorcode; - } -#if defined COMPILE_PCRE8 - return (errorcode <= PCRE_UTF8_ERR5 && md->partial > 1)? - PCRE_ERROR_SHORTUTF8 : PCRE_ERROR_BADUTF8; -#elif defined COMPILE_PCRE16 - return (errorcode <= PCRE_UTF16_ERR1 && md->partial > 1)? - PCRE_ERROR_SHORTUTF16 : PCRE_ERROR_BADUTF16; -#elif defined COMPILE_PCRE32 - return PCRE_ERROR_BADUTF32; -#endif - } -#if defined COMPILE_PCRE8 || defined COMPILE_PCRE16 - /* Check that a start_offset points to the start of a UTF character. */ - if (start_offset > 0 && start_offset < length && - NOT_FIRSTCHAR(((PCRE_PUCHAR)subject)[start_offset])) - return PCRE_ERROR_BADUTF8_OFFSET; -#endif - } -#endif - -/* If the pattern was successfully studied with JIT support, run the JIT -executable instead of the rest of this function. Most options must be set at -compile time for the JIT code to be usable. Fallback to the normal code path if -an unsupported flag is set. */ - -#ifdef SUPPORT_JIT -if (extra_data != NULL - && (extra_data->flags & (PCRE_EXTRA_EXECUTABLE_JIT | - PCRE_EXTRA_TABLES)) == PCRE_EXTRA_EXECUTABLE_JIT - && extra_data->executable_jit != NULL - && (options & ~PUBLIC_JIT_EXEC_OPTIONS) == 0) - { - rc = PRIV(jit_exec)(extra_data, (const pcre_uchar *)subject, length, - start_offset, options, offsets, offsetcount); - - /* PCRE_ERROR_NULL means that the selected normal or partial matching - mode is not compiled. In this case we simply fallback to interpreter. */ - - if (rc != PCRE_ERROR_JIT_BADOPTION) return rc; - } -#endif - -/* Carry on with non-JIT matching. This information is for finding all the -numbers associated with a given name, for condition testing. */ - -md->name_table = (pcre_uchar *)re + re->name_table_offset; -md->name_count = re->name_count; -md->name_entry_size = re->name_entry_size; - -/* Fish out the optional data from the extra_data structure, first setting -the default values. */ - -study = NULL; -md->match_limit = MATCH_LIMIT; -md->match_limit_recursion = MATCH_LIMIT_RECURSION; -md->callout_data = NULL; - -/* The table pointer is always in native byte order. */ - -tables = re->tables; - -/* The two limit values override the defaults, whatever their value. */ - -if (extra_data != NULL) - { - unsigned long int flags = extra_data->flags; - if ((flags & PCRE_EXTRA_STUDY_DATA) != 0) - study = (const pcre_study_data *)extra_data->study_data; - if ((flags & PCRE_EXTRA_MATCH_LIMIT) != 0) - md->match_limit = extra_data->match_limit; - if ((flags & PCRE_EXTRA_MATCH_LIMIT_RECURSION) != 0) - md->match_limit_recursion = extra_data->match_limit_recursion; - if ((flags & PCRE_EXTRA_CALLOUT_DATA) != 0) - md->callout_data = extra_data->callout_data; - if ((flags & PCRE_EXTRA_TABLES) != 0) tables = extra_data->tables; - } - -/* Limits in the regex override only if they are smaller. */ - -if ((re->flags & PCRE_MLSET) != 0 && re->limit_match < md->match_limit) - md->match_limit = re->limit_match; - -if ((re->flags & PCRE_RLSET) != 0 && - re->limit_recursion < md->match_limit_recursion) - md->match_limit_recursion = re->limit_recursion; - -/* If the exec call supplied NULL for tables, use the inbuilt ones. This -is a feature that makes it possible to save compiled regex and re-use them -in other programs later. */ - -if (tables == NULL) tables = PRIV(default_tables); - -/* Set up other data */ - -anchored = ((re->options | options) & PCRE_ANCHORED) != 0; -startline = (re->flags & PCRE_STARTLINE) != 0; -firstline = (re->options & PCRE_FIRSTLINE) != 0; - -/* The code starts after the real_pcre block and the capture name table. */ - -md->start_code = (const pcre_uchar *)re + re->name_table_offset + - re->name_count * re->name_entry_size; - -md->start_subject = (PCRE_PUCHAR)subject; -md->start_offset = start_offset; -md->end_subject = md->start_subject + length; -end_subject = md->end_subject; - -md->endonly = (re->options & PCRE_DOLLAR_ENDONLY) != 0; -md->use_ucp = (re->options & PCRE_UCP) != 0; -md->jscript_compat = (re->options & PCRE_JAVASCRIPT_COMPAT) != 0; -md->ignore_skip_arg = 0; - -/* Some options are unpacked into BOOL variables in the hope that testing -them will be faster than individual option bits. */ - -md->notbol = (options & PCRE_NOTBOL) != 0; -md->noteol = (options & PCRE_NOTEOL) != 0; -md->notempty = (options & PCRE_NOTEMPTY) != 0; -md->notempty_atstart = (options & PCRE_NOTEMPTY_ATSTART) != 0; - -md->hitend = FALSE; -md->mark = md->nomatch_mark = NULL; /* In case never set */ - -md->recursive = NULL; /* No recursion at top level */ -md->hasthen = (re->flags & PCRE_HASTHEN) != 0; - -md->lcc = tables + lcc_offset; -md->fcc = tables + fcc_offset; -md->ctypes = tables + ctypes_offset; - -/* Handle different \R options. */ - -switch (options & (PCRE_BSR_ANYCRLF|PCRE_BSR_UNICODE)) - { - case 0: - if ((re->options & (PCRE_BSR_ANYCRLF|PCRE_BSR_UNICODE)) != 0) - md->bsr_anycrlf = (re->options & PCRE_BSR_ANYCRLF) != 0; - else -#ifdef BSR_ANYCRLF - md->bsr_anycrlf = TRUE; -#else - md->bsr_anycrlf = FALSE; -#endif - break; - - case PCRE_BSR_ANYCRLF: - md->bsr_anycrlf = TRUE; - break; - - case PCRE_BSR_UNICODE: - md->bsr_anycrlf = FALSE; - break; - - default: return PCRE_ERROR_BADNEWLINE; - } - -/* Handle different types of newline. The three bits give eight cases. If -nothing is set at run time, whatever was used at compile time applies. */ - -switch ((((options & PCRE_NEWLINE_BITS) == 0)? re->options : - (pcre_uint32)options) & PCRE_NEWLINE_BITS) - { - case 0: newline = NEWLINE; break; /* Compile-time default */ - case PCRE_NEWLINE_CR: newline = CHAR_CR; break; - case PCRE_NEWLINE_LF: newline = CHAR_NL; break; - case PCRE_NEWLINE_CR+ - PCRE_NEWLINE_LF: newline = (CHAR_CR << 8) | CHAR_NL; break; - case PCRE_NEWLINE_ANY: newline = -1; break; - case PCRE_NEWLINE_ANYCRLF: newline = -2; break; - default: return PCRE_ERROR_BADNEWLINE; - } - -if (newline == -2) - { - md->nltype = NLTYPE_ANYCRLF; - } -else if (newline < 0) - { - md->nltype = NLTYPE_ANY; - } -else - { - md->nltype = NLTYPE_FIXED; - if (newline > 255) - { - md->nllen = 2; - md->nl[0] = (newline >> 8) & 255; - md->nl[1] = newline & 255; - } - else - { - md->nllen = 1; - md->nl[0] = newline; - } - } - -/* Partial matching was originally supported only for a restricted set of -regexes; from release 8.00 there are no restrictions, but the bits are still -defined (though never set). So there's no harm in leaving this code. */ - -if (md->partial && (re->flags & PCRE_NOPARTIAL) != 0) - return PCRE_ERROR_BADPARTIAL; - -/* If the expression has got more back references than the offsets supplied can -hold, we get a temporary chunk of working store to use during the matching. -Otherwise, we can use the vector supplied, rounding down its size to a multiple -of 3. */ - -ocount = offsetcount - (offsetcount % 3); -arg_offset_max = (2*ocount)/3; - -if (re->top_backref > 0 && re->top_backref >= ocount/3) - { - ocount = re->top_backref * 3 + 3; - md->offset_vector = (int *)(PUBL(malloc))(ocount * sizeof(int)); - if (md->offset_vector == NULL) return PCRE_ERROR_NOMEMORY; - using_temporary_offsets = TRUE; - DPRINTF(("Got memory to hold back references\n")); - } -else md->offset_vector = offsets; -md->offset_end = ocount; -md->offset_max = (2*ocount)/3; -md->capture_last = 0; - -/* Reset the working variable associated with each extraction. These should -never be used unless previously set, but they get saved and restored, and so we -initialize them to avoid reading uninitialized locations. Also, unset the -offsets for the matched string. This is really just for tidiness with callouts, -in case they inspect these fields. */ - -if (md->offset_vector != NULL) - { - register int *iptr = md->offset_vector + ocount; - register int *iend = iptr - re->top_bracket; - if (iend < md->offset_vector + 2) iend = md->offset_vector + 2; - while (--iptr >= iend) *iptr = -1; - if (offsetcount > 0) md->offset_vector[0] = -1; - if (offsetcount > 1) md->offset_vector[1] = -1; - } - -/* Set up the first character to match, if available. The first_char value is -never set for an anchored regular expression, but the anchoring may be forced -at run time, so we have to test for anchoring. The first char may be unset for -an unanchored pattern, of course. If there's no first char and the pattern was -studied, there may be a bitmap of possible first characters. */ - -if (!anchored) - { - if ((re->flags & PCRE_FIRSTSET) != 0) - { - has_first_char = TRUE; - first_char = first_char2 = (pcre_uchar)(re->first_char); - if ((re->flags & PCRE_FCH_CASELESS) != 0) - { - first_char2 = TABLE_GET(first_char, md->fcc, first_char); -#if defined SUPPORT_UCP && !(defined COMPILE_PCRE8) - if (utf && first_char > 127) - first_char2 = UCD_OTHERCASE(first_char); -#endif - } - } - else - if (!startline && study != NULL && - (study->flags & PCRE_STUDY_MAPPED) != 0) - start_bits = study->start_bits; - } - -/* For anchored or unanchored matches, there may be a "last known required -character" set. */ - -if ((re->flags & PCRE_REQCHSET) != 0) - { - has_req_char = TRUE; - req_char = req_char2 = (pcre_uchar)(re->req_char); - if ((re->flags & PCRE_RCH_CASELESS) != 0) - { - req_char2 = TABLE_GET(req_char, md->fcc, req_char); -#if defined SUPPORT_UCP && !(defined COMPILE_PCRE8) - if (utf && req_char > 127) - req_char2 = UCD_OTHERCASE(req_char); -#endif - } - } - - -/* ==========================================================================*/ - -/* Loop for handling unanchored repeated matching attempts; for anchored regexs -the loop runs just once. */ - -for(;;) - { - PCRE_PUCHAR save_end_subject = end_subject; - PCRE_PUCHAR new_start_match; - - /* If firstline is TRUE, the start of the match is constrained to the first - line of a multiline string. That is, the match must be before or at the first - newline. Implement this by temporarily adjusting end_subject so that we stop - scanning at a newline. If the match fails at the newline, later code breaks - this loop. */ - - if (firstline) - { - PCRE_PUCHAR t = start_match; -#ifdef SUPPORT_UTF - if (utf) - { - while (t < md->end_subject && !IS_NEWLINE(t)) - { - t++; - ACROSSCHAR(t < end_subject, *t, t++); - } - } - else -#endif - while (t < md->end_subject && !IS_NEWLINE(t)) t++; - end_subject = t; - } - - /* There are some optimizations that avoid running the match if a known - starting point is not found, or if a known later character is not present. - However, there is an option that disables these, for testing and for ensuring - that all callouts do actually occur. The option can be set in the regex by - (*NO_START_OPT) or passed in match-time options. */ - - if (((options | re->options) & PCRE_NO_START_OPTIMIZE) == 0) - { - /* Advance to a unique first char if there is one. */ - - if (has_first_char) - { - pcre_uchar smc; - - if (first_char != first_char2) - while (start_match < end_subject && - (smc = UCHAR21TEST(start_match)) != first_char && smc != first_char2) - start_match++; - else - while (start_match < end_subject && UCHAR21TEST(start_match) != first_char) - start_match++; - } - - /* Or to just after a linebreak for a multiline match */ - - else if (startline) - { - if (start_match > md->start_subject + start_offset) - { -#ifdef SUPPORT_UTF - if (utf) - { - while (start_match < end_subject && !WAS_NEWLINE(start_match)) - { - start_match++; - ACROSSCHAR(start_match < end_subject, *start_match, - start_match++); - } - } - else -#endif - while (start_match < end_subject && !WAS_NEWLINE(start_match)) - start_match++; - - /* If we have just passed a CR and the newline option is ANY or ANYCRLF, - and we are now at a LF, advance the match position by one more character. - */ - - if (start_match[-1] == CHAR_CR && - (md->nltype == NLTYPE_ANY || md->nltype == NLTYPE_ANYCRLF) && - start_match < end_subject && - UCHAR21TEST(start_match) == CHAR_NL) - start_match++; - } - } - - /* Or to a non-unique first byte after study */ - - else if (start_bits != NULL) - { - while (start_match < end_subject) - { - register pcre_uint32 c = UCHAR21TEST(start_match); -#ifndef COMPILE_PCRE8 - if (c > 255) c = 255; -#endif - if ((start_bits[c/8] & (1 << (c&7))) != 0) break; - start_match++; - } - } - } /* Starting optimizations */ - - /* Restore fudged end_subject */ - - end_subject = save_end_subject; - - /* The following two optimizations are disabled for partial matching or if - disabling is explicitly requested. */ - - if (((options | re->options) & PCRE_NO_START_OPTIMIZE) == 0 && !md->partial) - { - /* If the pattern was studied, a minimum subject length may be set. This is - a lower bound; no actual string of that length may actually match the - pattern. Although the value is, strictly, in characters, we treat it as - bytes to avoid spending too much time in this optimization. */ - - if (study != NULL && (study->flags & PCRE_STUDY_MINLEN) != 0 && - (pcre_uint32)(end_subject - start_match) < study->minlength) - { - rc = MATCH_NOMATCH; - break; - } - - /* If req_char is set, we know that that character must appear in the - subject for the match to succeed. If the first character is set, req_char - must be later in the subject; otherwise the test starts at the match point. - This optimization can save a huge amount of backtracking in patterns with - nested unlimited repeats that aren't going to match. Writing separate code - for cased/caseless versions makes it go faster, as does using an - autoincrement and backing off on a match. - - HOWEVER: when the subject string is very, very long, searching to its end - can take a long time, and give bad performance on quite ordinary patterns. - This showed up when somebody was matching something like /^\d+C/ on a - 32-megabyte string... so we don't do this when the string is sufficiently - long. */ - - if (has_req_char && end_subject - start_match < REQ_BYTE_MAX) - { - register PCRE_PUCHAR p = start_match + (has_first_char? 1:0); - - /* We don't need to repeat the search if we haven't yet reached the - place we found it at last time. */ - - if (p > req_char_ptr) - { - if (req_char != req_char2) - { - while (p < end_subject) - { - register pcre_uint32 pp = UCHAR21INCTEST(p); - if (pp == req_char || pp == req_char2) { p--; break; } - } - } - else - { - while (p < end_subject) - { - if (UCHAR21INCTEST(p) == req_char) { p--; break; } - } - } - - /* If we can't find the required character, break the matching loop, - forcing a match failure. */ - - if (p >= end_subject) - { - rc = MATCH_NOMATCH; - break; - } - - /* If we have found the required character, save the point where we - found it, so that we don't search again next time round the loop if - the start hasn't passed this character yet. */ - - req_char_ptr = p; - } - } - } - -#ifdef PCRE_DEBUG /* Sigh. Some compilers never learn. */ - printf(">>>> Match against: "); - pchars(start_match, end_subject - start_match, TRUE, md); - printf("\n"); -#endif - - /* OK, we can now run the match. If "hitend" is set afterwards, remember the - first starting point for which a partial match was found. */ - - md->start_match_ptr = start_match; - md->start_used_ptr = start_match; - md->match_call_count = 0; - md->match_function_type = 0; - md->end_offset_top = 0; - md->skip_arg_count = 0; - rc = match(start_match, md->start_code, start_match, 2, md, NULL, 0); - if (md->hitend && start_partial == NULL) - { - start_partial = md->start_used_ptr; - match_partial = start_match; - } - - switch(rc) - { - /* If MATCH_SKIP_ARG reaches this level it means that a MARK that matched - the SKIP's arg was not found. In this circumstance, Perl ignores the SKIP - entirely. The only way we can do that is to re-do the match at the same - point, with a flag to force SKIP with an argument to be ignored. Just - treating this case as NOMATCH does not work because it does not check other - alternatives in patterns such as A(*SKIP:A)B|AC when the subject is AC. */ - - case MATCH_SKIP_ARG: - new_start_match = start_match; - md->ignore_skip_arg = md->skip_arg_count; - break; - - /* SKIP passes back the next starting point explicitly, but if it is no - greater than the match we have just done, treat it as NOMATCH. */ - - case MATCH_SKIP: - if (md->start_match_ptr > start_match) - { - new_start_match = md->start_match_ptr; - break; - } - /* Fall through */ - - /* NOMATCH and PRUNE advance by one character. THEN at this level acts - exactly like PRUNE. Unset ignore SKIP-with-argument. */ - - case MATCH_NOMATCH: - case MATCH_PRUNE: - case MATCH_THEN: - md->ignore_skip_arg = 0; - new_start_match = start_match + 1; -#ifdef SUPPORT_UTF - if (utf) - ACROSSCHAR(new_start_match < end_subject, *new_start_match, - new_start_match++); -#endif - break; - - /* COMMIT disables the bumpalong, but otherwise behaves as NOMATCH. */ - - case MATCH_COMMIT: - rc = MATCH_NOMATCH; - goto ENDLOOP; - - /* Any other return is either a match, or some kind of error. */ - - default: - goto ENDLOOP; - } - - /* Control reaches here for the various types of "no match at this point" - result. Reset the code to MATCH_NOMATCH for subsequent checking. */ - - rc = MATCH_NOMATCH; - - /* If PCRE_FIRSTLINE is set, the match must happen before or at the first - newline in the subject (though it may continue over the newline). Therefore, - if we have just failed to match, starting at a newline, do not continue. */ - - if (firstline && IS_NEWLINE(start_match)) break; - - /* Advance to new matching position */ - - start_match = new_start_match; - - /* Break the loop if the pattern is anchored or if we have passed the end of - the subject. */ - - if (anchored || start_match > end_subject) break; - - /* If we have just passed a CR and we are now at a LF, and the pattern does - not contain any explicit matches for \r or \n, and the newline option is CRLF - or ANY or ANYCRLF, advance the match position by one more character. In - normal matching start_match will aways be greater than the first position at - this stage, but a failed *SKIP can cause a return at the same point, which is - why the first test exists. */ - - if (start_match > (PCRE_PUCHAR)subject + start_offset && - start_match[-1] == CHAR_CR && - start_match < end_subject && - *start_match == CHAR_NL && - (re->flags & PCRE_HASCRORLF) == 0 && - (md->nltype == NLTYPE_ANY || - md->nltype == NLTYPE_ANYCRLF || - md->nllen == 2)) - start_match++; - - md->mark = NULL; /* Reset for start of next match attempt */ - } /* End of for(;;) "bumpalong" loop */ - -/* ==========================================================================*/ - -/* We reach here when rc is not MATCH_NOMATCH, or if one of the stopping -conditions is true: - -(1) The pattern is anchored or the match was failed by (*COMMIT); - -(2) We are past the end of the subject; - -(3) PCRE_FIRSTLINE is set and we have failed to match at a newline, because - this option requests that a match occur at or before the first newline in - the subject. - -When we have a match and the offset vector is big enough to deal with any -backreferences, captured substring offsets will already be set up. In the case -where we had to get some local store to hold offsets for backreference -processing, copy those that we can. In this case there need not be overflow if -certain parts of the pattern were not used, even though there are more -capturing parentheses than vector slots. */ - -ENDLOOP: - -if (rc == MATCH_MATCH || rc == MATCH_ACCEPT) - { - if (using_temporary_offsets) - { - if (arg_offset_max >= 4) - { - memcpy(offsets + 2, md->offset_vector + 2, - (arg_offset_max - 2) * sizeof(int)); - DPRINTF(("Copied offsets from temporary memory\n")); - } - if (md->end_offset_top > arg_offset_max) md->capture_last |= OVFLBIT; - DPRINTF(("Freeing temporary memory\n")); - (PUBL(free))(md->offset_vector); - } - - /* Set the return code to the number of captured strings, or 0 if there were - too many to fit into the vector. */ - - rc = ((md->capture_last & OVFLBIT) != 0 && - md->end_offset_top >= arg_offset_max)? - 0 : md->end_offset_top/2; - - /* If there is space in the offset vector, set any unused pairs at the end of - the pattern to -1 for backwards compatibility. It is documented that this - happens. In earlier versions, the whole set of potential capturing offsets - was set to -1 each time round the loop, but this is handled differently now. - "Gaps" are set to -1 dynamically instead (this fixes a bug). Thus, it is only - those at the end that need unsetting here. We can't just unset them all at - the start of the whole thing because they may get set in one branch that is - not the final matching branch. */ - - if (md->end_offset_top/2 <= re->top_bracket && offsets != NULL) - { - register int *iptr, *iend; - int resetcount = 2 + re->top_bracket * 2; - if (resetcount > offsetcount) resetcount = offsetcount; - iptr = offsets + md->end_offset_top; - iend = offsets + resetcount; - while (iptr < iend) *iptr++ = -1; - } - - /* If there is space, set up the whole thing as substring 0. The value of - md->start_match_ptr might be modified if \K was encountered on the success - matching path. */ - - if (offsetcount < 2) rc = 0; else - { - offsets[0] = (int)(md->start_match_ptr - md->start_subject); - offsets[1] = (int)(md->end_match_ptr - md->start_subject); - } - - /* Return MARK data if requested */ - - if (extra_data != NULL && (extra_data->flags & PCRE_EXTRA_MARK) != 0) - *(extra_data->mark) = (pcre_uchar *)md->mark; - DPRINTF((">>>> returning %d\n", rc)); -#ifdef NO_RECURSE - release_match_heapframes(&frame_zero); -#endif - return rc; - } - -/* Control gets here if there has been an error, or if the overall match -attempt has failed at all permitted starting positions. */ - -if (using_temporary_offsets) - { - DPRINTF(("Freeing temporary memory\n")); - (PUBL(free))(md->offset_vector); - } - -/* For anything other than nomatch or partial match, just return the code. */ - -if (rc != MATCH_NOMATCH && rc != PCRE_ERROR_PARTIAL) - { - DPRINTF((">>>> error: returning %d\n", rc)); -#ifdef NO_RECURSE - release_match_heapframes(&frame_zero); -#endif - return rc; - } - -/* Handle partial matches - disable any mark data */ - -if (match_partial != NULL) - { - DPRINTF((">>>> returning PCRE_ERROR_PARTIAL\n")); - md->mark = NULL; - if (offsetcount > 1) - { - offsets[0] = (int)(start_partial - (PCRE_PUCHAR)subject); - offsets[1] = (int)(end_subject - (PCRE_PUCHAR)subject); - if (offsetcount > 2) - offsets[2] = (int)(match_partial - (PCRE_PUCHAR)subject); - } - rc = PCRE_ERROR_PARTIAL; - } - -/* This is the classic nomatch case */ - -else - { - DPRINTF((">>>> returning PCRE_ERROR_NOMATCH\n")); - rc = PCRE_ERROR_NOMATCH; - } - -/* Return the MARK data if it has been requested. */ - -if (extra_data != NULL && (extra_data->flags & PCRE_EXTRA_MARK) != 0) - *(extra_data->mark) = (pcre_uchar *)md->nomatch_mark; -#ifdef NO_RECURSE - release_match_heapframes(&frame_zero); -#endif -return rc; -} - -/* End of pcre_exec.c */ diff --git a/src/third_party/pcre-8.38/pcre_fullinfo.c b/src/third_party/pcre-8.38/pcre_fullinfo.c deleted file mode 100644 index a6c2ece6ca5..00000000000 --- a/src/third_party/pcre-8.38/pcre_fullinfo.c +++ /dev/null @@ -1,245 +0,0 @@ -/************************************************* -* Perl-Compatible Regular Expressions * -*************************************************/ - -/* PCRE is a library of functions to support regular expressions whose syntax -and semantics are as close as possible to those of the Perl 5 language. - - Written by Philip Hazel - Copyright (c) 1997-2013 University of Cambridge - ------------------------------------------------------------------------------ -Redistribution and use in source and binary forms, with or without -modification, are permitted provided that the following conditions are met: - - * Redistributions of source code must retain the above copyright notice, - this list of conditions and the following disclaimer. - - * Redistributions in binary form must reproduce the above copyright - notice, this list of conditions and the following disclaimer in the - documentation and/or other materials provided with the distribution. - - * Neither the name of the University of Cambridge nor the names of its - contributors may be used to endorse or promote products derived from - this software without specific prior written permission. - -THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS" -AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE -IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE -ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR CONTRIBUTORS BE -LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR -CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF -SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS -INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN -CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) -ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE -POSSIBILITY OF SUCH DAMAGE. ------------------------------------------------------------------------------ -*/ - - -/* This module contains the external function pcre_fullinfo(), which returns -information about a compiled pattern. */ - - -#ifdef HAVE_CONFIG_H -#include "config.h" -#endif - -#include "pcre_internal.h" - - -/************************************************* -* Return info about compiled pattern * -*************************************************/ - -/* This is a newer "info" function which has an extensible interface so -that additional items can be added compatibly. - -Arguments: - argument_re points to compiled code - extra_data points extra data, or NULL - what what information is required - where where to put the information - -Returns: 0 if data returned, negative on error -*/ - -#if defined COMPILE_PCRE8 -PCRE_EXP_DEFN int PCRE_CALL_CONVENTION -pcre_fullinfo(const pcre *argument_re, const pcre_extra *extra_data, - int what, void *where) -#elif defined COMPILE_PCRE16 -PCRE_EXP_DEFN int PCRE_CALL_CONVENTION -pcre16_fullinfo(const pcre16 *argument_re, const pcre16_extra *extra_data, - int what, void *where) -#elif defined COMPILE_PCRE32 -PCRE_EXP_DEFN int PCRE_CALL_CONVENTION -pcre32_fullinfo(const pcre32 *argument_re, const pcre32_extra *extra_data, - int what, void *where) -#endif -{ -const REAL_PCRE *re = (const REAL_PCRE *)argument_re; -const pcre_study_data *study = NULL; - -if (re == NULL || where == NULL) return PCRE_ERROR_NULL; - -if (extra_data != NULL && (extra_data->flags & PCRE_EXTRA_STUDY_DATA) != 0) - study = (const pcre_study_data *)extra_data->study_data; - -/* Check that the first field in the block is the magic number. If it is not, -return with PCRE_ERROR_BADMAGIC. However, if the magic number is equal to -REVERSED_MAGIC_NUMBER we return with PCRE_ERROR_BADENDIANNESS, which -means that the pattern is likely compiled with different endianness. */ - -if (re->magic_number != MAGIC_NUMBER) - return re->magic_number == REVERSED_MAGIC_NUMBER? - PCRE_ERROR_BADENDIANNESS:PCRE_ERROR_BADMAGIC; - -/* Check that this pattern was compiled in the correct bit mode */ - -if ((re->flags & PCRE_MODE) == 0) return PCRE_ERROR_BADMODE; - -switch (what) - { - case PCRE_INFO_OPTIONS: - *((unsigned long int *)where) = re->options & PUBLIC_COMPILE_OPTIONS; - break; - - case PCRE_INFO_SIZE: - *((size_t *)where) = re->size; - break; - - case PCRE_INFO_STUDYSIZE: - *((size_t *)where) = (study == NULL)? 0 : study->size; - break; - - case PCRE_INFO_JITSIZE: -#ifdef SUPPORT_JIT - *((size_t *)where) = - (extra_data != NULL && - (extra_data->flags & PCRE_EXTRA_EXECUTABLE_JIT) != 0 && - extra_data->executable_jit != NULL)? - PRIV(jit_get_size)(extra_data->executable_jit) : 0; -#else - *((size_t *)where) = 0; -#endif - break; - - case PCRE_INFO_CAPTURECOUNT: - *((int *)where) = re->top_bracket; - break; - - case PCRE_INFO_BACKREFMAX: - *((int *)where) = re->top_backref; - break; - - case PCRE_INFO_FIRSTBYTE: - *((int *)where) = - ((re->flags & PCRE_FIRSTSET) != 0)? (int)re->first_char : - ((re->flags & PCRE_STARTLINE) != 0)? -1 : -2; - break; - - case PCRE_INFO_FIRSTCHARACTER: - *((pcre_uint32 *)where) = - (re->flags & PCRE_FIRSTSET) != 0 ? re->first_char : 0; - break; - - case PCRE_INFO_FIRSTCHARACTERFLAGS: - *((int *)where) = - ((re->flags & PCRE_FIRSTSET) != 0) ? 1 : - ((re->flags & PCRE_STARTLINE) != 0) ? 2 : 0; - break; - - /* Make sure we pass back the pointer to the bit vector in the external - block, not the internal copy (with flipped integer fields). */ - - case PCRE_INFO_FIRSTTABLE: - *((const pcre_uint8 **)where) = - (study != NULL && (study->flags & PCRE_STUDY_MAPPED) != 0)? - ((const pcre_study_data *)extra_data->study_data)->start_bits : NULL; - break; - - case PCRE_INFO_MINLENGTH: - *((int *)where) = - (study != NULL && (study->flags & PCRE_STUDY_MINLEN) != 0)? - (int)(study->minlength) : -1; - break; - - case PCRE_INFO_JIT: - *((int *)where) = extra_data != NULL && - (extra_data->flags & PCRE_EXTRA_EXECUTABLE_JIT) != 0 && - extra_data->executable_jit != NULL; - break; - - case PCRE_INFO_LASTLITERAL: - *((int *)where) = - ((re->flags & PCRE_REQCHSET) != 0)? (int)re->req_char : -1; - break; - - case PCRE_INFO_REQUIREDCHAR: - *((pcre_uint32 *)where) = - ((re->flags & PCRE_REQCHSET) != 0) ? re->req_char : 0; - break; - - case PCRE_INFO_REQUIREDCHARFLAGS: - *((int *)where) = - ((re->flags & PCRE_REQCHSET) != 0); - break; - - case PCRE_INFO_NAMEENTRYSIZE: - *((int *)where) = re->name_entry_size; - break; - - case PCRE_INFO_NAMECOUNT: - *((int *)where) = re->name_count; - break; - - case PCRE_INFO_NAMETABLE: - *((const pcre_uchar **)where) = (const pcre_uchar *)re + re->name_table_offset; - break; - - case PCRE_INFO_DEFAULT_TABLES: - *((const pcre_uint8 **)where) = (const pcre_uint8 *)(PRIV(default_tables)); - break; - - /* From release 8.00 this will always return TRUE because NOPARTIAL is - no longer ever set (the restrictions have been removed). */ - - case PCRE_INFO_OKPARTIAL: - *((int *)where) = (re->flags & PCRE_NOPARTIAL) == 0; - break; - - case PCRE_INFO_JCHANGED: - *((int *)where) = (re->flags & PCRE_JCHANGED) != 0; - break; - - case PCRE_INFO_HASCRORLF: - *((int *)where) = (re->flags & PCRE_HASCRORLF) != 0; - break; - - case PCRE_INFO_MAXLOOKBEHIND: - *((int *)where) = re->max_lookbehind; - break; - - case PCRE_INFO_MATCHLIMIT: - if ((re->flags & PCRE_MLSET) == 0) return PCRE_ERROR_UNSET; - *((pcre_uint32 *)where) = re->limit_match; - break; - - case PCRE_INFO_RECURSIONLIMIT: - if ((re->flags & PCRE_RLSET) == 0) return PCRE_ERROR_UNSET; - *((pcre_uint32 *)where) = re->limit_recursion; - break; - - case PCRE_INFO_MATCH_EMPTY: - *((int *)where) = (re->flags & PCRE_MATCH_EMPTY) != 0; - break; - - default: return PCRE_ERROR_BADOPTION; - } - -return 0; -} - -/* End of pcre_fullinfo.c */ diff --git a/src/third_party/pcre-8.38/pcre_get.c b/src/third_party/pcre-8.38/pcre_get.c deleted file mode 100644 index 8094b34bbfb..00000000000 --- a/src/third_party/pcre-8.38/pcre_get.c +++ /dev/null @@ -1,662 +0,0 @@ -/************************************************* -* Perl-Compatible Regular Expressions * -*************************************************/ - -/* PCRE is a library of functions to support regular expressions whose syntax -and semantics are as close as possible to those of the Perl 5 language. - - Written by Philip Hazel - Copyright (c) 1997-2012 University of Cambridge - ------------------------------------------------------------------------------ -Redistribution and use in source and binary forms, with or without -modification, are permitted provided that the following conditions are met: - - * Redistributions of source code must retain the above copyright notice, - this list of conditions and the following disclaimer. - - * Redistributions in binary form must reproduce the above copyright - notice, this list of conditions and the following disclaimer in the - documentation and/or other materials provided with the distribution. - - * Neither the name of the University of Cambridge nor the names of its - contributors may be used to endorse or promote products derived from - this software without specific prior written permission. - -THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS" -AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE -IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE -ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR CONTRIBUTORS BE -LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR -CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF -SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS -INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN -CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) -ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE -POSSIBILITY OF SUCH DAMAGE. ------------------------------------------------------------------------------ -*/ - - -/* This module contains some convenience functions for extracting substrings -from the subject string after a regex match has succeeded. The original idea -for these functions came from Scott Wimer. */ - - -#ifdef HAVE_CONFIG_H -#include "config.h" -#endif - -#include "pcre_internal.h" - - -/************************************************* -* Find number for named string * -*************************************************/ - -/* This function is used by the get_first_set() function below, as well -as being generally available. It assumes that names are unique. - -Arguments: - code the compiled regex - stringname the name whose number is required - -Returns: the number of the named parentheses, or a negative number - (PCRE_ERROR_NOSUBSTRING) if not found -*/ - -#if defined COMPILE_PCRE8 -PCRE_EXP_DEFN int PCRE_CALL_CONVENTION -pcre_get_stringnumber(const pcre *code, const char *stringname) -#elif defined COMPILE_PCRE16 -PCRE_EXP_DEFN int PCRE_CALL_CONVENTION -pcre16_get_stringnumber(const pcre16 *code, PCRE_SPTR16 stringname) -#elif defined COMPILE_PCRE32 -PCRE_EXP_DEFN int PCRE_CALL_CONVENTION -pcre32_get_stringnumber(const pcre32 *code, PCRE_SPTR32 stringname) -#endif -{ -int rc; -int entrysize; -int top, bot; -pcre_uchar *nametable; - -#ifdef COMPILE_PCRE8 -if ((rc = pcre_fullinfo(code, NULL, PCRE_INFO_NAMECOUNT, &top)) != 0) - return rc; -if (top <= 0) return PCRE_ERROR_NOSUBSTRING; - -if ((rc = pcre_fullinfo(code, NULL, PCRE_INFO_NAMEENTRYSIZE, &entrysize)) != 0) - return rc; -if ((rc = pcre_fullinfo(code, NULL, PCRE_INFO_NAMETABLE, &nametable)) != 0) - return rc; -#endif -#ifdef COMPILE_PCRE16 -if ((rc = pcre16_fullinfo(code, NULL, PCRE_INFO_NAMECOUNT, &top)) != 0) - return rc; -if (top <= 0) return PCRE_ERROR_NOSUBSTRING; - -if ((rc = pcre16_fullinfo(code, NULL, PCRE_INFO_NAMEENTRYSIZE, &entrysize)) != 0) - return rc; -if ((rc = pcre16_fullinfo(code, NULL, PCRE_INFO_NAMETABLE, &nametable)) != 0) - return rc; -#endif -#ifdef COMPILE_PCRE32 -if ((rc = pcre32_fullinfo(code, NULL, PCRE_INFO_NAMECOUNT, &top)) != 0) - return rc; -if (top <= 0) return PCRE_ERROR_NOSUBSTRING; - -if ((rc = pcre32_fullinfo(code, NULL, PCRE_INFO_NAMEENTRYSIZE, &entrysize)) != 0) - return rc; -if ((rc = pcre32_fullinfo(code, NULL, PCRE_INFO_NAMETABLE, &nametable)) != 0) - return rc; -#endif - -bot = 0; -while (top > bot) - { - int mid = (top + bot) / 2; - pcre_uchar *entry = nametable + entrysize*mid; - int c = STRCMP_UC_UC((pcre_uchar *)stringname, - (pcre_uchar *)(entry + IMM2_SIZE)); - if (c == 0) return GET2(entry, 0); - if (c > 0) bot = mid + 1; else top = mid; - } - -return PCRE_ERROR_NOSUBSTRING; -} - - - -/************************************************* -* Find (multiple) entries for named string * -*************************************************/ - -/* This is used by the get_first_set() function below, as well as being -generally available. It is used when duplicated names are permitted. - -Arguments: - code the compiled regex - stringname the name whose entries required - firstptr where to put the pointer to the first entry - lastptr where to put the pointer to the last entry - -Returns: the length of each entry, or a negative number - (PCRE_ERROR_NOSUBSTRING) if not found -*/ - -#if defined COMPILE_PCRE8 -PCRE_EXP_DEFN int PCRE_CALL_CONVENTION -pcre_get_stringtable_entries(const pcre *code, const char *stringname, - char **firstptr, char **lastptr) -#elif defined COMPILE_PCRE16 -PCRE_EXP_DEFN int PCRE_CALL_CONVENTION -pcre16_get_stringtable_entries(const pcre16 *code, PCRE_SPTR16 stringname, - PCRE_UCHAR16 **firstptr, PCRE_UCHAR16 **lastptr) -#elif defined COMPILE_PCRE32 -PCRE_EXP_DEFN int PCRE_CALL_CONVENTION -pcre32_get_stringtable_entries(const pcre32 *code, PCRE_SPTR32 stringname, - PCRE_UCHAR32 **firstptr, PCRE_UCHAR32 **lastptr) -#endif -{ -int rc; -int entrysize; -int top, bot; -pcre_uchar *nametable, *lastentry; - -#ifdef COMPILE_PCRE8 -if ((rc = pcre_fullinfo(code, NULL, PCRE_INFO_NAMECOUNT, &top)) != 0) - return rc; -if (top <= 0) return PCRE_ERROR_NOSUBSTRING; - -if ((rc = pcre_fullinfo(code, NULL, PCRE_INFO_NAMEENTRYSIZE, &entrysize)) != 0) - return rc; -if ((rc = pcre_fullinfo(code, NULL, PCRE_INFO_NAMETABLE, &nametable)) != 0) - return rc; -#endif -#ifdef COMPILE_PCRE16 -if ((rc = pcre16_fullinfo(code, NULL, PCRE_INFO_NAMECOUNT, &top)) != 0) - return rc; -if (top <= 0) return PCRE_ERROR_NOSUBSTRING; - -if ((rc = pcre16_fullinfo(code, NULL, PCRE_INFO_NAMEENTRYSIZE, &entrysize)) != 0) - return rc; -if ((rc = pcre16_fullinfo(code, NULL, PCRE_INFO_NAMETABLE, &nametable)) != 0) - return rc; -#endif -#ifdef COMPILE_PCRE32 -if ((rc = pcre32_fullinfo(code, NULL, PCRE_INFO_NAMECOUNT, &top)) != 0) - return rc; -if (top <= 0) return PCRE_ERROR_NOSUBSTRING; - -if ((rc = pcre32_fullinfo(code, NULL, PCRE_INFO_NAMEENTRYSIZE, &entrysize)) != 0) - return rc; -if ((rc = pcre32_fullinfo(code, NULL, PCRE_INFO_NAMETABLE, &nametable)) != 0) - return rc; -#endif - -lastentry = nametable + entrysize * (top - 1); -bot = 0; -while (top > bot) - { - int mid = (top + bot) / 2; - pcre_uchar *entry = nametable + entrysize*mid; - int c = STRCMP_UC_UC((pcre_uchar *)stringname, - (pcre_uchar *)(entry + IMM2_SIZE)); - if (c == 0) - { - pcre_uchar *first = entry; - pcre_uchar *last = entry; - while (first > nametable) - { - if (STRCMP_UC_UC((pcre_uchar *)stringname, - (pcre_uchar *)(first - entrysize + IMM2_SIZE)) != 0) break; - first -= entrysize; - } - while (last < lastentry) - { - if (STRCMP_UC_UC((pcre_uchar *)stringname, - (pcre_uchar *)(last + entrysize + IMM2_SIZE)) != 0) break; - last += entrysize; - } -#if defined COMPILE_PCRE8 - *firstptr = (char *)first; - *lastptr = (char *)last; -#elif defined COMPILE_PCRE16 - *firstptr = (PCRE_UCHAR16 *)first; - *lastptr = (PCRE_UCHAR16 *)last; -#elif defined COMPILE_PCRE32 - *firstptr = (PCRE_UCHAR32 *)first; - *lastptr = (PCRE_UCHAR32 *)last; -#endif - return entrysize; - } - if (c > 0) bot = mid + 1; else top = mid; - } - -return PCRE_ERROR_NOSUBSTRING; -} - - - -/************************************************* -* Find first set of multiple named strings * -*************************************************/ - -/* This function allows for duplicate names in the table of named substrings. -It returns the number of the first one that was set in a pattern match. - -Arguments: - code the compiled regex - stringname the name of the capturing substring - ovector the vector of matched substrings - -Returns: the number of the first that is set, - or the number of the last one if none are set, - or a negative number on error -*/ - -#if defined COMPILE_PCRE8 -static int -get_first_set(const pcre *code, const char *stringname, int *ovector) -#elif defined COMPILE_PCRE16 -static int -get_first_set(const pcre16 *code, PCRE_SPTR16 stringname, int *ovector) -#elif defined COMPILE_PCRE32 -static int -get_first_set(const pcre32 *code, PCRE_SPTR32 stringname, int *ovector) -#endif -{ -const REAL_PCRE *re = (const REAL_PCRE *)code; -int entrysize; -pcre_uchar *entry; -#if defined COMPILE_PCRE8 -char *first, *last; -#elif defined COMPILE_PCRE16 -PCRE_UCHAR16 *first, *last; -#elif defined COMPILE_PCRE32 -PCRE_UCHAR32 *first, *last; -#endif - -#if defined COMPILE_PCRE8 -if ((re->options & PCRE_DUPNAMES) == 0 && (re->flags & PCRE_JCHANGED) == 0) - return pcre_get_stringnumber(code, stringname); -entrysize = pcre_get_stringtable_entries(code, stringname, &first, &last); -#elif defined COMPILE_PCRE16 -if ((re->options & PCRE_DUPNAMES) == 0 && (re->flags & PCRE_JCHANGED) == 0) - return pcre16_get_stringnumber(code, stringname); -entrysize = pcre16_get_stringtable_entries(code, stringname, &first, &last); -#elif defined COMPILE_PCRE32 -if ((re->options & PCRE_DUPNAMES) == 0 && (re->flags & PCRE_JCHANGED) == 0) - return pcre32_get_stringnumber(code, stringname); -entrysize = pcre32_get_stringtable_entries(code, stringname, &first, &last); -#endif -if (entrysize <= 0) return entrysize; -for (entry = (pcre_uchar *)first; entry <= (pcre_uchar *)last; entry += entrysize) - { - int n = GET2(entry, 0); - if (ovector[n*2] >= 0) return n; - } -return GET2(entry, 0); -} - - - - -/************************************************* -* Copy captured string to given buffer * -*************************************************/ - -/* This function copies a single captured substring into a given buffer. -Note that we use memcpy() rather than strncpy() in case there are binary zeros -in the string. - -Arguments: - subject the subject string that was matched - ovector pointer to the offsets table - stringcount the number of substrings that were captured - (i.e. the yield of the pcre_exec call, unless - that was zero, in which case it should be 1/3 - of the offset table size) - stringnumber the number of the required substring - buffer where to put the substring - size the size of the buffer - -Returns: if successful: - the length of the copied string, not including the zero - that is put on the end; can be zero - if not successful: - PCRE_ERROR_NOMEMORY (-6) buffer too small - PCRE_ERROR_NOSUBSTRING (-7) no such captured substring -*/ - -#if defined COMPILE_PCRE8 -PCRE_EXP_DEFN int PCRE_CALL_CONVENTION -pcre_copy_substring(const char *subject, int *ovector, int stringcount, - int stringnumber, char *buffer, int size) -#elif defined COMPILE_PCRE16 -PCRE_EXP_DEFN int PCRE_CALL_CONVENTION -pcre16_copy_substring(PCRE_SPTR16 subject, int *ovector, int stringcount, - int stringnumber, PCRE_UCHAR16 *buffer, int size) -#elif defined COMPILE_PCRE32 -PCRE_EXP_DEFN int PCRE_CALL_CONVENTION -pcre32_copy_substring(PCRE_SPTR32 subject, int *ovector, int stringcount, - int stringnumber, PCRE_UCHAR32 *buffer, int size) -#endif -{ -int yield; -if (stringnumber < 0 || stringnumber >= stringcount) - return PCRE_ERROR_NOSUBSTRING; -stringnumber *= 2; -yield = ovector[stringnumber+1] - ovector[stringnumber]; -if (size < yield + 1) return PCRE_ERROR_NOMEMORY; -memcpy(buffer, subject + ovector[stringnumber], IN_UCHARS(yield)); -buffer[yield] = 0; -return yield; -} - - - -/************************************************* -* Copy named captured string to given buffer * -*************************************************/ - -/* This function copies a single captured substring into a given buffer, -identifying it by name. If the regex permits duplicate names, the first -substring that is set is chosen. - -Arguments: - code the compiled regex - subject the subject string that was matched - ovector pointer to the offsets table - stringcount the number of substrings that were captured - (i.e. the yield of the pcre_exec call, unless - that was zero, in which case it should be 1/3 - of the offset table size) - stringname the name of the required substring - buffer where to put the substring - size the size of the buffer - -Returns: if successful: - the length of the copied string, not including the zero - that is put on the end; can be zero - if not successful: - PCRE_ERROR_NOMEMORY (-6) buffer too small - PCRE_ERROR_NOSUBSTRING (-7) no such captured substring -*/ - -#if defined COMPILE_PCRE8 -PCRE_EXP_DEFN int PCRE_CALL_CONVENTION -pcre_copy_named_substring(const pcre *code, const char *subject, - int *ovector, int stringcount, const char *stringname, - char *buffer, int size) -#elif defined COMPILE_PCRE16 -PCRE_EXP_DEFN int PCRE_CALL_CONVENTION -pcre16_copy_named_substring(const pcre16 *code, PCRE_SPTR16 subject, - int *ovector, int stringcount, PCRE_SPTR16 stringname, - PCRE_UCHAR16 *buffer, int size) -#elif defined COMPILE_PCRE32 -PCRE_EXP_DEFN int PCRE_CALL_CONVENTION -pcre32_copy_named_substring(const pcre32 *code, PCRE_SPTR32 subject, - int *ovector, int stringcount, PCRE_SPTR32 stringname, - PCRE_UCHAR32 *buffer, int size) -#endif -{ -int n = get_first_set(code, stringname, ovector); -if (n <= 0) return n; -#if defined COMPILE_PCRE8 -return pcre_copy_substring(subject, ovector, stringcount, n, buffer, size); -#elif defined COMPILE_PCRE16 -return pcre16_copy_substring(subject, ovector, stringcount, n, buffer, size); -#elif defined COMPILE_PCRE32 -return pcre32_copy_substring(subject, ovector, stringcount, n, buffer, size); -#endif -} - - - -/************************************************* -* Copy all captured strings to new store * -*************************************************/ - -/* This function gets one chunk of store and builds a list of pointers and all -of the captured substrings in it. A NULL pointer is put on the end of the list. - -Arguments: - subject the subject string that was matched - ovector pointer to the offsets table - stringcount the number of substrings that were captured - (i.e. the yield of the pcre_exec call, unless - that was zero, in which case it should be 1/3 - of the offset table size) - listptr set to point to the list of pointers - -Returns: if successful: 0 - if not successful: - PCRE_ERROR_NOMEMORY (-6) failed to get store -*/ - -#if defined COMPILE_PCRE8 -PCRE_EXP_DEFN int PCRE_CALL_CONVENTION -pcre_get_substring_list(const char *subject, int *ovector, int stringcount, - const char ***listptr) -#elif defined COMPILE_PCRE16 -PCRE_EXP_DEFN int PCRE_CALL_CONVENTION -pcre16_get_substring_list(PCRE_SPTR16 subject, int *ovector, int stringcount, - PCRE_SPTR16 **listptr) -#elif defined COMPILE_PCRE32 -PCRE_EXP_DEFN int PCRE_CALL_CONVENTION -pcre32_get_substring_list(PCRE_SPTR32 subject, int *ovector, int stringcount, - PCRE_SPTR32 **listptr) -#endif -{ -int i; -int size = sizeof(pcre_uchar *); -int double_count = stringcount * 2; -pcre_uchar **stringlist; -pcre_uchar *p; - -for (i = 0; i < double_count; i += 2) - size += sizeof(pcre_uchar *) + IN_UCHARS(ovector[i+1] - ovector[i] + 1); - -stringlist = (pcre_uchar **)(PUBL(malloc))(size); -if (stringlist == NULL) return PCRE_ERROR_NOMEMORY; - -#if defined COMPILE_PCRE8 -*listptr = (const char **)stringlist; -#elif defined COMPILE_PCRE16 -*listptr = (PCRE_SPTR16 *)stringlist; -#elif defined COMPILE_PCRE32 -*listptr = (PCRE_SPTR32 *)stringlist; -#endif -p = (pcre_uchar *)(stringlist + stringcount + 1); - -for (i = 0; i < double_count; i += 2) - { - int len = ovector[i+1] - ovector[i]; - memcpy(p, subject + ovector[i], IN_UCHARS(len)); - *stringlist++ = p; - p += len; - *p++ = 0; - } - -*stringlist = NULL; -return 0; -} - - - -/************************************************* -* Free store obtained by get_substring_list * -*************************************************/ - -/* This function exists for the benefit of people calling PCRE from non-C -programs that can call its functions, but not free() or (PUBL(free))() -directly. - -Argument: the result of a previous pcre_get_substring_list() -Returns: nothing -*/ - -#if defined COMPILE_PCRE8 -PCRE_EXP_DEFN void PCRE_CALL_CONVENTION -pcre_free_substring_list(const char **pointer) -#elif defined COMPILE_PCRE16 -PCRE_EXP_DEFN void PCRE_CALL_CONVENTION -pcre16_free_substring_list(PCRE_SPTR16 *pointer) -#elif defined COMPILE_PCRE32 -PCRE_EXP_DEFN void PCRE_CALL_CONVENTION -pcre32_free_substring_list(PCRE_SPTR32 *pointer) -#endif -{ -(PUBL(free))((void *)pointer); -} - - - -/************************************************* -* Copy captured string to new store * -*************************************************/ - -/* This function copies a single captured substring into a piece of new -store - -Arguments: - subject the subject string that was matched - ovector pointer to the offsets table - stringcount the number of substrings that were captured - (i.e. the yield of the pcre_exec call, unless - that was zero, in which case it should be 1/3 - of the offset table size) - stringnumber the number of the required substring - stringptr where to put a pointer to the substring - -Returns: if successful: - the length of the string, not including the zero that - is put on the end; can be zero - if not successful: - PCRE_ERROR_NOMEMORY (-6) failed to get store - PCRE_ERROR_NOSUBSTRING (-7) substring not present -*/ - -#if defined COMPILE_PCRE8 -PCRE_EXP_DEFN int PCRE_CALL_CONVENTION -pcre_get_substring(const char *subject, int *ovector, int stringcount, - int stringnumber, const char **stringptr) -#elif defined COMPILE_PCRE16 -PCRE_EXP_DEFN int PCRE_CALL_CONVENTION -pcre16_get_substring(PCRE_SPTR16 subject, int *ovector, int stringcount, - int stringnumber, PCRE_SPTR16 *stringptr) -#elif defined COMPILE_PCRE32 -PCRE_EXP_DEFN int PCRE_CALL_CONVENTION -pcre32_get_substring(PCRE_SPTR32 subject, int *ovector, int stringcount, - int stringnumber, PCRE_SPTR32 *stringptr) -#endif -{ -int yield; -pcre_uchar *substring; -if (stringnumber < 0 || stringnumber >= stringcount) - return PCRE_ERROR_NOSUBSTRING; -stringnumber *= 2; -yield = ovector[stringnumber+1] - ovector[stringnumber]; -substring = (pcre_uchar *)(PUBL(malloc))(IN_UCHARS(yield + 1)); -if (substring == NULL) return PCRE_ERROR_NOMEMORY; -memcpy(substring, subject + ovector[stringnumber], IN_UCHARS(yield)); -substring[yield] = 0; -#if defined COMPILE_PCRE8 -*stringptr = (const char *)substring; -#elif defined COMPILE_PCRE16 -*stringptr = (PCRE_SPTR16)substring; -#elif defined COMPILE_PCRE32 -*stringptr = (PCRE_SPTR32)substring; -#endif -return yield; -} - - - -/************************************************* -* Copy named captured string to new store * -*************************************************/ - -/* This function copies a single captured substring, identified by name, into -new store. If the regex permits duplicate names, the first substring that is -set is chosen. - -Arguments: - code the compiled regex - subject the subject string that was matched - ovector pointer to the offsets table - stringcount the number of substrings that were captured - (i.e. the yield of the pcre_exec call, unless - that was zero, in which case it should be 1/3 - of the offset table size) - stringname the name of the required substring - stringptr where to put the pointer - -Returns: if successful: - the length of the copied string, not including the zero - that is put on the end; can be zero - if not successful: - PCRE_ERROR_NOMEMORY (-6) couldn't get memory - PCRE_ERROR_NOSUBSTRING (-7) no such captured substring -*/ - -#if defined COMPILE_PCRE8 -PCRE_EXP_DEFN int PCRE_CALL_CONVENTION -pcre_get_named_substring(const pcre *code, const char *subject, - int *ovector, int stringcount, const char *stringname, - const char **stringptr) -#elif defined COMPILE_PCRE16 -PCRE_EXP_DEFN int PCRE_CALL_CONVENTION -pcre16_get_named_substring(const pcre16 *code, PCRE_SPTR16 subject, - int *ovector, int stringcount, PCRE_SPTR16 stringname, - PCRE_SPTR16 *stringptr) -#elif defined COMPILE_PCRE32 -PCRE_EXP_DEFN int PCRE_CALL_CONVENTION -pcre32_get_named_substring(const pcre32 *code, PCRE_SPTR32 subject, - int *ovector, int stringcount, PCRE_SPTR32 stringname, - PCRE_SPTR32 *stringptr) -#endif -{ -int n = get_first_set(code, stringname, ovector); -if (n <= 0) return n; -#if defined COMPILE_PCRE8 -return pcre_get_substring(subject, ovector, stringcount, n, stringptr); -#elif defined COMPILE_PCRE16 -return pcre16_get_substring(subject, ovector, stringcount, n, stringptr); -#elif defined COMPILE_PCRE32 -return pcre32_get_substring(subject, ovector, stringcount, n, stringptr); -#endif -} - - - - -/************************************************* -* Free store obtained by get_substring * -*************************************************/ - -/* This function exists for the benefit of people calling PCRE from non-C -programs that can call its functions, but not free() or (PUBL(free))() -directly. - -Argument: the result of a previous pcre_get_substring() -Returns: nothing -*/ - -#if defined COMPILE_PCRE8 -PCRE_EXP_DEFN void PCRE_CALL_CONVENTION -pcre_free_substring(const char *pointer) -#elif defined COMPILE_PCRE16 -PCRE_EXP_DEFN void PCRE_CALL_CONVENTION -pcre16_free_substring(PCRE_SPTR16 pointer) -#elif defined COMPILE_PCRE32 -PCRE_EXP_DEFN void PCRE_CALL_CONVENTION -pcre32_free_substring(PCRE_SPTR32 pointer) -#endif -{ -(PUBL(free))((void *)pointer); -} - -/* End of pcre_get.c */ diff --git a/src/third_party/pcre-8.38/pcre_globals.c b/src/third_party/pcre-8.38/pcre_globals.c deleted file mode 100644 index 0f106aa9013..00000000000 --- a/src/third_party/pcre-8.38/pcre_globals.c +++ /dev/null @@ -1,86 +0,0 @@ -/************************************************* -* Perl-Compatible Regular Expressions * -*************************************************/ - -/* PCRE is a library of functions to support regular expressions whose syntax -and semantics are as close as possible to those of the Perl 5 language. - - Written by Philip Hazel - Copyright (c) 1997-2014 University of Cambridge - ------------------------------------------------------------------------------ -Redistribution and use in source and binary forms, with or without -modification, are permitted provided that the following conditions are met: - - * Redistributions of source code must retain the above copyright notice, - this list of conditions and the following disclaimer. - - * Redistributions in binary form must reproduce the above copyright - notice, this list of conditions and the following disclaimer in the - documentation and/or other materials provided with the distribution. - - * Neither the name of the University of Cambridge nor the names of its - contributors may be used to endorse or promote products derived from - this software without specific prior written permission. - -THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS" -AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE -IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE -ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR CONTRIBUTORS BE -LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR -CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF -SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS -INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN -CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) -ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE -POSSIBILITY OF SUCH DAMAGE. ------------------------------------------------------------------------------ -*/ - - -/* This module contains global variables that are exported by the PCRE library. -PCRE is thread-clean and doesn't use any global variables in the normal sense. -However, it calls memory allocation and freeing functions via the four -indirections below, and it can optionally do callouts, using the fifth -indirection. These values can be changed by the caller, but are shared between -all threads. - -For MS Visual Studio and Symbian OS, there are problems in initializing these -variables to non-local functions. In these cases, therefore, an indirection via -a local function is used. - -Also, when compiling for Virtual Pascal, things are done differently, and -global variables are not used. */ - -#ifdef HAVE_CONFIG_H -#include "config.h" -#endif - -#include "pcre_internal.h" - -#if defined _MSC_VER || defined __SYMBIAN32__ -static void* LocalPcreMalloc(size_t aSize) - { - return malloc(aSize); - } -static void LocalPcreFree(void* aPtr) - { - free(aPtr); - } -PCRE_EXP_DATA_DEFN void *(*PUBL(malloc))(size_t) = LocalPcreMalloc; -PCRE_EXP_DATA_DEFN void (*PUBL(free))(void *) = LocalPcreFree; -PCRE_EXP_DATA_DEFN void *(*PUBL(stack_malloc))(size_t) = LocalPcreMalloc; -PCRE_EXP_DATA_DEFN void (*PUBL(stack_free))(void *) = LocalPcreFree; -PCRE_EXP_DATA_DEFN int (*PUBL(callout))(PUBL(callout_block) *) = NULL; -PCRE_EXP_DATA_DEFN int (*PUBL(stack_guard))(void) = NULL; - -#elif !defined VPCOMPAT -PCRE_EXP_DATA_DEFN void *(*PUBL(malloc))(size_t) = malloc; -PCRE_EXP_DATA_DEFN void (*PUBL(free))(void *) = free; -PCRE_EXP_DATA_DEFN void *(*PUBL(stack_malloc))(size_t) = malloc; -PCRE_EXP_DATA_DEFN void (*PUBL(stack_free))(void *) = free; -PCRE_EXP_DATA_DEFN int (*PUBL(callout))(PUBL(callout_block) *) = NULL; -PCRE_EXP_DATA_DEFN int (*PUBL(stack_guard))(void) = NULL; -#endif - -/* End of pcre_globals.c */ diff --git a/src/third_party/pcre-8.38/pcre_internal.h b/src/third_party/pcre-8.38/pcre_internal.h deleted file mode 100644 index f7a5ee7aa6f..00000000000 --- a/src/third_party/pcre-8.38/pcre_internal.h +++ /dev/null @@ -1,2798 +0,0 @@ -/************************************************* -* Perl-Compatible Regular Expressions * -*************************************************/ - - -/* PCRE is a library of functions to support regular expressions whose syntax -and semantics are as close as possible to those of the Perl 5 language. - - Written by Philip Hazel - Copyright (c) 1997-2014 University of Cambridge - ------------------------------------------------------------------------------ -Redistribution and use in source and binary forms, with or without -modification, are permitted provided that the following conditions are met: - - * Redistributions of source code must retain the above copyright notice, - this list of conditions and the following disclaimer. - - * Redistributions in binary form must reproduce the above copyright - notice, this list of conditions and the following disclaimer in the - documentation and/or other materials provided with the distribution. - - * Neither the name of the University of Cambridge nor the names of its - contributors may be used to endorse or promote products derived from - this software without specific prior written permission. - -THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS" -AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE -IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE -ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR CONTRIBUTORS BE -LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR -CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF -SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS -INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN -CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) -ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE -POSSIBILITY OF SUCH DAMAGE. ------------------------------------------------------------------------------ -*/ - -/* This header contains definitions that are shared between the different -modules, but which are not relevant to the exported API. This includes some -functions whose names all begin with "_pcre_", "_pcre16_" or "_pcre32_" -depending on the PRIV macro. */ - -#ifndef PCRE_INTERNAL_H -#define PCRE_INTERNAL_H - -/* Define PCRE_DEBUG to get debugging output on stdout. */ - -#if 0 -#define PCRE_DEBUG -#endif - -/* PCRE is compiled as an 8 bit library if it is not requested otherwise. */ - -#if !defined COMPILE_PCRE16 && !defined COMPILE_PCRE32 -#define COMPILE_PCRE8 -#endif - -/* If SUPPORT_UCP is defined, SUPPORT_UTF must also be defined. The -"configure" script ensures this, but not everybody uses "configure". */ - -#if defined SUPPORT_UCP && !(defined SUPPORT_UTF) -#define SUPPORT_UTF 1 -#endif - -/* We define SUPPORT_UTF if SUPPORT_UTF8 is enabled for compatibility -reasons with existing code. */ - -#if defined SUPPORT_UTF8 && !(defined SUPPORT_UTF) -#define SUPPORT_UTF 1 -#endif - -/* Fixme: SUPPORT_UTF8 should be eventually disappear from the code. -Until then we define it if SUPPORT_UTF is defined. */ - -#if defined SUPPORT_UTF && !(defined SUPPORT_UTF8) -#define SUPPORT_UTF8 1 -#endif - -/* We do not support both EBCDIC and UTF-8/16/32 at the same time. The "configure" -script prevents both being selected, but not everybody uses "configure". */ - -#if defined EBCDIC && defined SUPPORT_UTF -#error The use of both EBCDIC and SUPPORT_UTF is not supported. -#endif - -/* Use a macro for debugging printing, 'cause that eliminates the use of #ifdef -inline, and there are *still* stupid compilers about that don't like indented -pre-processor statements, or at least there were when I first wrote this. After -all, it had only been about 10 years then... - -It turns out that the Mac Debugging.h header also defines the macro DPRINTF, so -be absolutely sure we get our version. */ - -#undef DPRINTF -#ifdef PCRE_DEBUG -#define DPRINTF(p) printf p -#else -#define DPRINTF(p) /* Nothing */ -#endif - - -/* Standard C headers plus the external interface definition. The only time -setjmp and stdarg are used is when NO_RECURSE is set. */ - -#include <ctype.h> -#include <limits.h> -#include <stddef.h> -#include <stdio.h> -#include <stdlib.h> -#include <string.h> - -/* Valgrind (memcheck) support */ - -#ifdef SUPPORT_VALGRIND -#include <valgrind/memcheck.h> -#endif - -/* When compiling a DLL for Windows, the exported symbols have to be declared -using some MS magic. I found some useful information on this web page: -http://msdn2.microsoft.com/en-us/library/y4h7bcy6(VS.80).aspx. According to the -information there, using __declspec(dllexport) without "extern" we have a -definition; with "extern" we have a declaration. The settings here override the -setting in pcre.h (which is included below); it defines only PCRE_EXP_DECL, -which is all that is needed for applications (they just import the symbols). We -use: - - PCRE_EXP_DECL for declarations - PCRE_EXP_DEFN for definitions of exported functions - PCRE_EXP_DATA_DEFN for definitions of exported variables - -The reason for the two DEFN macros is that in non-Windows environments, one -does not want to have "extern" before variable definitions because it leads to -compiler warnings. So we distinguish between functions and variables. In -Windows, the two should always be the same. - -The reason for wrapping this in #ifndef PCRE_EXP_DECL is so that pcretest, -which is an application, but needs to import this file in order to "peek" at -internals, can #include pcre.h first to get an application's-eye view. - -In principle, people compiling for non-Windows, non-Unix-like (i.e. uncommon, -special-purpose environments) might want to stick other stuff in front of -exported symbols. That's why, in the non-Windows case, we set PCRE_EXP_DEFN and -PCRE_EXP_DATA_DEFN only if they are not already set. */ - -#ifndef PCRE_EXP_DECL -# ifdef _WIN32 -# ifndef PCRE_STATIC -# define PCRE_EXP_DECL extern __declspec(dllexport) -# define PCRE_EXP_DEFN __declspec(dllexport) -# define PCRE_EXP_DATA_DEFN __declspec(dllexport) -# else -# define PCRE_EXP_DECL extern -# define PCRE_EXP_DEFN -# define PCRE_EXP_DATA_DEFN -# endif -# else -# ifdef __cplusplus -# define PCRE_EXP_DECL extern "C" -# else -# define PCRE_EXP_DECL extern -# endif -# ifndef PCRE_EXP_DEFN -# define PCRE_EXP_DEFN PCRE_EXP_DECL -# endif -# ifndef PCRE_EXP_DATA_DEFN -# define PCRE_EXP_DATA_DEFN -# endif -# endif -#endif - -/* When compiling with the MSVC compiler, it is sometimes necessary to include -a "calling convention" before exported function names. (This is secondhand -information; I know nothing about MSVC myself). For example, something like - - void __cdecl function(....) - -might be needed. In order so make this easy, all the exported functions have -PCRE_CALL_CONVENTION just before their names. It is rarely needed; if not -set, we ensure here that it has no effect. */ - -#ifndef PCRE_CALL_CONVENTION -#define PCRE_CALL_CONVENTION -#endif - -/* We need to have types that specify unsigned 8, 16 and 32-bit integers. We -cannot determine these outside the compilation (e.g. by running a program as -part of "configure") because PCRE is often cross-compiled for use on other -systems. Instead we make use of the maximum sizes that are available at -preprocessor time in standard C environments. */ - -typedef unsigned char pcre_uint8; - -#if USHRT_MAX == 65535 -typedef unsigned short pcre_uint16; -typedef short pcre_int16; -#define PCRE_UINT16_MAX USHRT_MAX -#define PCRE_INT16_MAX SHRT_MAX -#elif UINT_MAX == 65535 -typedef unsigned int pcre_uint16; -typedef int pcre_int16; -#define PCRE_UINT16_MAX UINT_MAX -#define PCRE_INT16_MAX INT_MAX -#else -#error Cannot determine a type for 16-bit integers -#endif - -#if UINT_MAX == 4294967295U -typedef unsigned int pcre_uint32; -typedef int pcre_int32; -#define PCRE_UINT32_MAX UINT_MAX -#define PCRE_INT32_MAX INT_MAX -#elif ULONG_MAX == 4294967295UL -typedef unsigned long int pcre_uint32; -typedef long int pcre_int32; -#define PCRE_UINT32_MAX ULONG_MAX -#define PCRE_INT32_MAX LONG_MAX -#else -#error Cannot determine a type for 32-bit integers -#endif - -/* When checking for integer overflow in pcre_compile(), we need to handle -large integers. If a 64-bit integer type is available, we can use that. -Otherwise we have to cast to double, which of course requires floating point -arithmetic. Handle this by defining a macro for the appropriate type. If -stdint.h is available, include it; it may define INT64_MAX. Systems that do not -have stdint.h (e.g. Solaris) may have inttypes.h. The macro int64_t may be set -by "configure". */ - -#if defined HAVE_STDINT_H -#include <stdint.h> -#elif defined HAVE_INTTYPES_H -#include <inttypes.h> -#endif - -#if defined INT64_MAX || defined int64_t -#define INT64_OR_DOUBLE int64_t -#else -#define INT64_OR_DOUBLE double -#endif - -/* All character handling must be done as unsigned characters. Otherwise there -are problems with top-bit-set characters and functions such as isspace(). -However, we leave the interface to the outside world as char * or short *, -because that should make things easier for callers. This character type is -called pcre_uchar. - -The IN_UCHARS macro multiply its argument with the byte size of the current -pcre_uchar type. Useful for memcpy and such operations, whose require the -byte size of their input/output buffers. - -The MAX_255 macro checks whether its pcre_uchar input is less than 256. - -The TABLE_GET macro is designed for accessing elements of tables whose contain -exactly 256 items. When the character is able to contain more than 256 -items, some check is needed before accessing these tables. -*/ - -#if defined COMPILE_PCRE8 - -typedef unsigned char pcre_uchar; -#define IN_UCHARS(x) (x) -#define MAX_255(c) 1 -#define TABLE_GET(c, table, default) ((table)[c]) - -#elif defined COMPILE_PCRE16 - -#if USHRT_MAX != 65535 -/* This is a warning message. Change PCRE_UCHAR16 to a 16 bit data type in -pcre.h(.in) and disable (comment out) this message. */ -#error Warning: PCRE_UCHAR16 is not a 16 bit data type. -#endif - -typedef pcre_uint16 pcre_uchar; -#define UCHAR_SHIFT (1) -#define IN_UCHARS(x) ((x) << UCHAR_SHIFT) -#define MAX_255(c) ((c) <= 255u) -#define TABLE_GET(c, table, default) (MAX_255(c)? ((table)[c]):(default)) - -#elif defined COMPILE_PCRE32 - -typedef pcre_uint32 pcre_uchar; -#define UCHAR_SHIFT (2) -#define IN_UCHARS(x) ((x) << UCHAR_SHIFT) -#define MAX_255(c) ((c) <= 255u) -#define TABLE_GET(c, table, default) (MAX_255(c)? ((table)[c]):(default)) - -#else -#error Unsupported compiling mode -#endif /* COMPILE_PCRE[8|16|32] */ - -/* This is an unsigned int value that no character can ever have. UTF-8 -characters only go up to 0x7fffffff (though Unicode doesn't go beyond -0x0010ffff). */ - -#define NOTACHAR 0xffffffff - -/* PCRE is able to support several different kinds of newline (CR, LF, CRLF, -"any" and "anycrlf" at present). The following macros are used to package up -testing for newlines. NLBLOCK, PSSTART, and PSEND are defined in the various -modules to indicate in which datablock the parameters exist, and what the -start/end of string field names are. */ - -#define NLTYPE_FIXED 0 /* Newline is a fixed length string */ -#define NLTYPE_ANY 1 /* Newline is any Unicode line ending */ -#define NLTYPE_ANYCRLF 2 /* Newline is CR, LF, or CRLF */ - -/* This macro checks for a newline at the given position */ - -#define IS_NEWLINE(p) \ - ((NLBLOCK->nltype != NLTYPE_FIXED)? \ - ((p) < NLBLOCK->PSEND && \ - PRIV(is_newline)((p), NLBLOCK->nltype, NLBLOCK->PSEND, \ - &(NLBLOCK->nllen), utf)) \ - : \ - ((p) <= NLBLOCK->PSEND - NLBLOCK->nllen && \ - UCHAR21TEST(p) == NLBLOCK->nl[0] && \ - (NLBLOCK->nllen == 1 || UCHAR21TEST(p+1) == NLBLOCK->nl[1]) \ - ) \ - ) - -/* This macro checks for a newline immediately preceding the given position */ - -#define WAS_NEWLINE(p) \ - ((NLBLOCK->nltype != NLTYPE_FIXED)? \ - ((p) > NLBLOCK->PSSTART && \ - PRIV(was_newline)((p), NLBLOCK->nltype, NLBLOCK->PSSTART, \ - &(NLBLOCK->nllen), utf)) \ - : \ - ((p) >= NLBLOCK->PSSTART + NLBLOCK->nllen && \ - UCHAR21TEST(p - NLBLOCK->nllen) == NLBLOCK->nl[0] && \ - (NLBLOCK->nllen == 1 || UCHAR21TEST(p - NLBLOCK->nllen + 1) == NLBLOCK->nl[1]) \ - ) \ - ) - -/* When PCRE is compiled as a C++ library, the subject pointer can be replaced -with a custom type. This makes it possible, for example, to allow pcre_exec() -to process subject strings that are discontinuous by using a smart pointer -class. It must always be possible to inspect all of the subject string in -pcre_exec() because of the way it backtracks. Two macros are required in the -normal case, for sign-unspecified and unsigned char pointers. The former is -used for the external interface and appears in pcre.h, which is why its name -must begin with PCRE_. */ - -#ifdef CUSTOM_SUBJECT_PTR -#define PCRE_PUCHAR CUSTOM_SUBJECT_PTR -#else -#define PCRE_PUCHAR const pcre_uchar * -#endif - -/* Include the public PCRE header and the definitions of UCP character property -values. */ - -#include "pcre.h" -#include "ucp.h" - -#ifdef COMPILE_PCRE32 -/* Assert that the public PCRE_UCHAR32 is a 32-bit type */ -typedef int __assert_pcre_uchar32_size[sizeof(PCRE_UCHAR32) == 4 ? 1 : -1]; -#endif - -/* When compiling for use with the Virtual Pascal compiler, these functions -need to have their names changed. PCRE must be compiled with the -DVPCOMPAT -option on the command line. */ - -#ifdef VPCOMPAT -#define strlen(s) _strlen(s) -#define strncmp(s1,s2,m) _strncmp(s1,s2,m) -#define memcmp(s,c,n) _memcmp(s,c,n) -#define memcpy(d,s,n) _memcpy(d,s,n) -#define memmove(d,s,n) _memmove(d,s,n) -#define memset(s,c,n) _memset(s,c,n) -#else /* VPCOMPAT */ - -/* To cope with SunOS4 and other systems that lack memmove() but have bcopy(), -define a macro for memmove() if HAVE_MEMMOVE is false, provided that HAVE_BCOPY -is set. Otherwise, include an emulating function for those systems that have -neither (there some non-Unix environments where this is the case). */ - -#ifndef HAVE_MEMMOVE -#undef memmove /* some systems may have a macro */ -#ifdef HAVE_BCOPY -#define memmove(a, b, c) bcopy(b, a, c) -#else /* HAVE_BCOPY */ -static void * -pcre_memmove(void *d, const void *s, size_t n) -{ -size_t i; -unsigned char *dest = (unsigned char *)d; -const unsigned char *src = (const unsigned char *)s; -if (dest > src) - { - dest += n; - src += n; - for (i = 0; i < n; ++i) *(--dest) = *(--src); - return (void *)dest; - } -else - { - for (i = 0; i < n; ++i) *dest++ = *src++; - return (void *)(dest - n); - } -} -#define memmove(a, b, c) pcre_memmove(a, b, c) -#endif /* not HAVE_BCOPY */ -#endif /* not HAVE_MEMMOVE */ -#endif /* not VPCOMPAT */ - - -/* PCRE keeps offsets in its compiled code as 2-byte quantities (always stored -in big-endian order) by default. These are used, for example, to link from the -start of a subpattern to its alternatives and its end. The use of 2 bytes per -offset limits the size of the compiled regex to around 64K, which is big enough -for almost everybody. However, I received a request for an even bigger limit. -For this reason, and also to make the code easier to maintain, the storing and -loading of offsets from the byte string is now handled by the macros that are -defined here. - -The macros are controlled by the value of LINK_SIZE. This defaults to 2 in -the config.h file, but can be overridden by using -D on the command line. This -is automated on Unix systems via the "configure" command. */ - -#if defined COMPILE_PCRE8 - -#if LINK_SIZE == 2 - -#define PUT(a,n,d) \ - (a[n] = (d) >> 8), \ - (a[(n)+1] = (d) & 255) - -#define GET(a,n) \ - (((a)[n] << 8) | (a)[(n)+1]) - -#define MAX_PATTERN_SIZE (1 << 16) - - -#elif LINK_SIZE == 3 - -#define PUT(a,n,d) \ - (a[n] = (d) >> 16), \ - (a[(n)+1] = (d) >> 8), \ - (a[(n)+2] = (d) & 255) - -#define GET(a,n) \ - (((a)[n] << 16) | ((a)[(n)+1] << 8) | (a)[(n)+2]) - -#define MAX_PATTERN_SIZE (1 << 24) - - -#elif LINK_SIZE == 4 - -#define PUT(a,n,d) \ - (a[n] = (d) >> 24), \ - (a[(n)+1] = (d) >> 16), \ - (a[(n)+2] = (d) >> 8), \ - (a[(n)+3] = (d) & 255) - -#define GET(a,n) \ - (((a)[n] << 24) | ((a)[(n)+1] << 16) | ((a)[(n)+2] << 8) | (a)[(n)+3]) - -/* Keep it positive */ -#define MAX_PATTERN_SIZE (1 << 30) - -#else -#error LINK_SIZE must be either 2, 3, or 4 -#endif - -#elif defined COMPILE_PCRE16 - -#if LINK_SIZE == 2 - -/* Redefine LINK_SIZE as a multiple of sizeof(pcre_uchar) */ -#undef LINK_SIZE -#define LINK_SIZE 1 - -#define PUT(a,n,d) \ - (a[n] = (d)) - -#define GET(a,n) \ - (a[n]) - -#define MAX_PATTERN_SIZE (1 << 16) - -#elif LINK_SIZE == 3 || LINK_SIZE == 4 - -/* Redefine LINK_SIZE as a multiple of sizeof(pcre_uchar) */ -#undef LINK_SIZE -#define LINK_SIZE 2 - -#define PUT(a,n,d) \ - (a[n] = (d) >> 16), \ - (a[(n)+1] = (d) & 65535) - -#define GET(a,n) \ - (((a)[n] << 16) | (a)[(n)+1]) - -/* Keep it positive */ -#define MAX_PATTERN_SIZE (1 << 30) - -#else -#error LINK_SIZE must be either 2, 3, or 4 -#endif - -#elif defined COMPILE_PCRE32 - -/* Only supported LINK_SIZE is 4 */ -/* Redefine LINK_SIZE as a multiple of sizeof(pcre_uchar) */ -#undef LINK_SIZE -#define LINK_SIZE 1 - -#define PUT(a,n,d) \ - (a[n] = (d)) - -#define GET(a,n) \ - (a[n]) - -/* Keep it positive */ -#define MAX_PATTERN_SIZE (1 << 30) - -#else -#error Unsupported compiling mode -#endif /* COMPILE_PCRE[8|16|32] */ - -/* Convenience macro defined in terms of the others */ - -#define PUTINC(a,n,d) PUT(a,n,d), a += LINK_SIZE - - -/* PCRE uses some other 2-byte quantities that do not change when the size of -offsets changes. There are used for repeat counts and for other things such as -capturing parenthesis numbers in back references. */ - -#if defined COMPILE_PCRE8 - -#define IMM2_SIZE 2 - -#define PUT2(a,n,d) \ - a[n] = (d) >> 8; \ - a[(n)+1] = (d) & 255 - -/* For reasons that I do not understand, the expression in this GET2 macro is -treated by gcc as a signed expression, even when a is declared as unsigned. It -seems that any kind of arithmetic results in a signed value. */ - -#define GET2(a,n) \ - (unsigned int)(((a)[n] << 8) | (a)[(n)+1]) - -#elif defined COMPILE_PCRE16 - -#define IMM2_SIZE 1 - -#define PUT2(a,n,d) \ - a[n] = d - -#define GET2(a,n) \ - a[n] - -#elif defined COMPILE_PCRE32 - -#define IMM2_SIZE 1 - -#define PUT2(a,n,d) \ - a[n] = d - -#define GET2(a,n) \ - a[n] - -#else -#error Unsupported compiling mode -#endif /* COMPILE_PCRE[8|16|32] */ - -#define PUT2INC(a,n,d) PUT2(a,n,d), a += IMM2_SIZE - -/* The maximum length of a MARK name is currently one data unit; it may be -changed in future to be a fixed number of bytes or to depend on LINK_SIZE. */ - -#if defined COMPILE_PCRE16 || defined COMPILE_PCRE32 -#define MAX_MARK ((1u << 16) - 1) -#else -#define MAX_MARK ((1u << 8) - 1) -#endif - -/* There is a proposed future special "UTF-21" mode, in which only the lowest -21 bits of a 32-bit character are interpreted as UTF, with the remaining 11 -high-order bits available to the application for other uses. In preparation for -the future implementation of this mode, there are macros that load a data item -and, if in this special mode, mask it to 21 bits. These macros all have names -starting with UCHAR21. In all other modes, including the normal 32-bit -library, the macros all have the same simple definitions. When the new mode is -implemented, it is expected that these definitions will be varied appropriately -using #ifdef when compiling the library that supports the special mode. */ - -#define UCHAR21(eptr) (*(eptr)) -#define UCHAR21TEST(eptr) (*(eptr)) -#define UCHAR21INC(eptr) (*(eptr)++) -#define UCHAR21INCTEST(eptr) (*(eptr)++) - -/* When UTF encoding is being used, a character is no longer just a single -byte in 8-bit mode or a single short in 16-bit mode. The macros for character -handling generate simple sequences when used in the basic mode, and more -complicated ones for UTF characters. GETCHARLENTEST and other macros are not -used when UTF is not supported. To make sure they can never even appear when -UTF support is omitted, we don't even define them. */ - -#ifndef SUPPORT_UTF - -/* #define MAX_VALUE_FOR_SINGLE_CHAR */ -/* #define HAS_EXTRALEN(c) */ -/* #define GET_EXTRALEN(c) */ -/* #define NOT_FIRSTCHAR(c) */ -#define GETCHAR(c, eptr) c = *eptr; -#define GETCHARTEST(c, eptr) c = *eptr; -#define GETCHARINC(c, eptr) c = *eptr++; -#define GETCHARINCTEST(c, eptr) c = *eptr++; -#define GETCHARLEN(c, eptr, len) c = *eptr; -/* #define GETCHARLENTEST(c, eptr, len) */ -/* #define BACKCHAR(eptr) */ -/* #define FORWARDCHAR(eptr) */ -/* #define ACROSSCHAR(condition, eptr, action) */ - -#else /* SUPPORT_UTF */ - -/* Tests whether the code point needs extra characters to decode. */ - -#define HASUTF8EXTRALEN(c) ((c) >= 0xc0) - -/* Base macro to pick up the remaining bytes of a UTF-8 character, not -advancing the pointer. */ - -#define GETUTF8(c, eptr) \ - { \ - if ((c & 0x20) == 0) \ - c = ((c & 0x1f) << 6) | (eptr[1] & 0x3f); \ - else if ((c & 0x10) == 0) \ - c = ((c & 0x0f) << 12) | ((eptr[1] & 0x3f) << 6) | (eptr[2] & 0x3f); \ - else if ((c & 0x08) == 0) \ - c = ((c & 0x07) << 18) | ((eptr[1] & 0x3f) << 12) | \ - ((eptr[2] & 0x3f) << 6) | (eptr[3] & 0x3f); \ - else if ((c & 0x04) == 0) \ - c = ((c & 0x03) << 24) | ((eptr[1] & 0x3f) << 18) | \ - ((eptr[2] & 0x3f) << 12) | ((eptr[3] & 0x3f) << 6) | \ - (eptr[4] & 0x3f); \ - else \ - c = ((c & 0x01) << 30) | ((eptr[1] & 0x3f) << 24) | \ - ((eptr[2] & 0x3f) << 18) | ((eptr[3] & 0x3f) << 12) | \ - ((eptr[4] & 0x3f) << 6) | (eptr[5] & 0x3f); \ - } - -/* Base macro to pick up the remaining bytes of a UTF-8 character, advancing -the pointer. */ - -#define GETUTF8INC(c, eptr) \ - { \ - if ((c & 0x20) == 0) \ - c = ((c & 0x1f) << 6) | (*eptr++ & 0x3f); \ - else if ((c & 0x10) == 0) \ - { \ - c = ((c & 0x0f) << 12) | ((*eptr & 0x3f) << 6) | (eptr[1] & 0x3f); \ - eptr += 2; \ - } \ - else if ((c & 0x08) == 0) \ - { \ - c = ((c & 0x07) << 18) | ((*eptr & 0x3f) << 12) | \ - ((eptr[1] & 0x3f) << 6) | (eptr[2] & 0x3f); \ - eptr += 3; \ - } \ - else if ((c & 0x04) == 0) \ - { \ - c = ((c & 0x03) << 24) | ((*eptr & 0x3f) << 18) | \ - ((eptr[1] & 0x3f) << 12) | ((eptr[2] & 0x3f) << 6) | \ - (eptr[3] & 0x3f); \ - eptr += 4; \ - } \ - else \ - { \ - c = ((c & 0x01) << 30) | ((*eptr & 0x3f) << 24) | \ - ((eptr[1] & 0x3f) << 18) | ((eptr[2] & 0x3f) << 12) | \ - ((eptr[3] & 0x3f) << 6) | (eptr[4] & 0x3f); \ - eptr += 5; \ - } \ - } - -#if defined COMPILE_PCRE8 - -/* These macros were originally written in the form of loops that used data -from the tables whose names start with PRIV(utf8_table). They were rewritten by -a user so as not to use loops, because in some environments this gives a -significant performance advantage, and it seems never to do any harm. */ - -/* Tells the biggest code point which can be encoded as a single character. */ - -#define MAX_VALUE_FOR_SINGLE_CHAR 127 - -/* Tests whether the code point needs extra characters to decode. */ - -#define HAS_EXTRALEN(c) ((c) >= 0xc0) - -/* Returns with the additional number of characters if IS_MULTICHAR(c) is TRUE. -Otherwise it has an undefined behaviour. */ - -#define GET_EXTRALEN(c) (PRIV(utf8_table4)[(c) & 0x3f]) - -/* Returns TRUE, if the given character is not the first character -of a UTF sequence. */ - -#define NOT_FIRSTCHAR(c) (((c) & 0xc0) == 0x80) - -/* Get the next UTF-8 character, not advancing the pointer. This is called when -we know we are in UTF-8 mode. */ - -#define GETCHAR(c, eptr) \ - c = *eptr; \ - if (c >= 0xc0) GETUTF8(c, eptr); - -/* Get the next UTF-8 character, testing for UTF-8 mode, and not advancing the -pointer. */ - -#define GETCHARTEST(c, eptr) \ - c = *eptr; \ - if (utf && c >= 0xc0) GETUTF8(c, eptr); - -/* Get the next UTF-8 character, advancing the pointer. This is called when we -know we are in UTF-8 mode. */ - -#define GETCHARINC(c, eptr) \ - c = *eptr++; \ - if (c >= 0xc0) GETUTF8INC(c, eptr); - -/* Get the next character, testing for UTF-8 mode, and advancing the pointer. -This is called when we don't know if we are in UTF-8 mode. */ - -#define GETCHARINCTEST(c, eptr) \ - c = *eptr++; \ - if (utf && c >= 0xc0) GETUTF8INC(c, eptr); - -/* Base macro to pick up the remaining bytes of a UTF-8 character, not -advancing the pointer, incrementing the length. */ - -#define GETUTF8LEN(c, eptr, len) \ - { \ - if ((c & 0x20) == 0) \ - { \ - c = ((c & 0x1f) << 6) | (eptr[1] & 0x3f); \ - len++; \ - } \ - else if ((c & 0x10) == 0) \ - { \ - c = ((c & 0x0f) << 12) | ((eptr[1] & 0x3f) << 6) | (eptr[2] & 0x3f); \ - len += 2; \ - } \ - else if ((c & 0x08) == 0) \ - {\ - c = ((c & 0x07) << 18) | ((eptr[1] & 0x3f) << 12) | \ - ((eptr[2] & 0x3f) << 6) | (eptr[3] & 0x3f); \ - len += 3; \ - } \ - else if ((c & 0x04) == 0) \ - { \ - c = ((c & 0x03) << 24) | ((eptr[1] & 0x3f) << 18) | \ - ((eptr[2] & 0x3f) << 12) | ((eptr[3] & 0x3f) << 6) | \ - (eptr[4] & 0x3f); \ - len += 4; \ - } \ - else \ - {\ - c = ((c & 0x01) << 30) | ((eptr[1] & 0x3f) << 24) | \ - ((eptr[2] & 0x3f) << 18) | ((eptr[3] & 0x3f) << 12) | \ - ((eptr[4] & 0x3f) << 6) | (eptr[5] & 0x3f); \ - len += 5; \ - } \ - } - -/* Get the next UTF-8 character, not advancing the pointer, incrementing length -if there are extra bytes. This is called when we know we are in UTF-8 mode. */ - -#define GETCHARLEN(c, eptr, len) \ - c = *eptr; \ - if (c >= 0xc0) GETUTF8LEN(c, eptr, len); - -/* Get the next UTF-8 character, testing for UTF-8 mode, not advancing the -pointer, incrementing length if there are extra bytes. This is called when we -do not know if we are in UTF-8 mode. */ - -#define GETCHARLENTEST(c, eptr, len) \ - c = *eptr; \ - if (utf && c >= 0xc0) GETUTF8LEN(c, eptr, len); - -/* If the pointer is not at the start of a character, move it back until -it is. This is called only in UTF-8 mode - we don't put a test within the macro -because almost all calls are already within a block of UTF-8 only code. */ - -#define BACKCHAR(eptr) while((*eptr & 0xc0) == 0x80) eptr-- - -/* Same as above, just in the other direction. */ -#define FORWARDCHAR(eptr) while((*eptr & 0xc0) == 0x80) eptr++ - -/* Same as above, but it allows a fully customizable form. */ -#define ACROSSCHAR(condition, eptr, action) \ - while((condition) && ((eptr) & 0xc0) == 0x80) action - -#elif defined COMPILE_PCRE16 - -/* Tells the biggest code point which can be encoded as a single character. */ - -#define MAX_VALUE_FOR_SINGLE_CHAR 65535 - -/* Tests whether the code point needs extra characters to decode. */ - -#define HAS_EXTRALEN(c) (((c) & 0xfc00) == 0xd800) - -/* Returns with the additional number of characters if IS_MULTICHAR(c) is TRUE. -Otherwise it has an undefined behaviour. */ - -#define GET_EXTRALEN(c) 1 - -/* Returns TRUE, if the given character is not the first character -of a UTF sequence. */ - -#define NOT_FIRSTCHAR(c) (((c) & 0xfc00) == 0xdc00) - -/* Base macro to pick up the low surrogate of a UTF-16 character, not -advancing the pointer. */ - -#define GETUTF16(c, eptr) \ - { c = (((c & 0x3ff) << 10) | (eptr[1] & 0x3ff)) + 0x10000; } - -/* Get the next UTF-16 character, not advancing the pointer. This is called when -we know we are in UTF-16 mode. */ - -#define GETCHAR(c, eptr) \ - c = *eptr; \ - if ((c & 0xfc00) == 0xd800) GETUTF16(c, eptr); - -/* Get the next UTF-16 character, testing for UTF-16 mode, and not advancing the -pointer. */ - -#define GETCHARTEST(c, eptr) \ - c = *eptr; \ - if (utf && (c & 0xfc00) == 0xd800) GETUTF16(c, eptr); - -/* Base macro to pick up the low surrogate of a UTF-16 character, advancing -the pointer. */ - -#define GETUTF16INC(c, eptr) \ - { c = (((c & 0x3ff) << 10) | (*eptr++ & 0x3ff)) + 0x10000; } - -/* Get the next UTF-16 character, advancing the pointer. This is called when we -know we are in UTF-16 mode. */ - -#define GETCHARINC(c, eptr) \ - c = *eptr++; \ - if ((c & 0xfc00) == 0xd800) GETUTF16INC(c, eptr); - -/* Get the next character, testing for UTF-16 mode, and advancing the pointer. -This is called when we don't know if we are in UTF-16 mode. */ - -#define GETCHARINCTEST(c, eptr) \ - c = *eptr++; \ - if (utf && (c & 0xfc00) == 0xd800) GETUTF16INC(c, eptr); - -/* Base macro to pick up the low surrogate of a UTF-16 character, not -advancing the pointer, incrementing the length. */ - -#define GETUTF16LEN(c, eptr, len) \ - { c = (((c & 0x3ff) << 10) | (eptr[1] & 0x3ff)) + 0x10000; len++; } - -/* Get the next UTF-16 character, not advancing the pointer, incrementing -length if there is a low surrogate. This is called when we know we are in -UTF-16 mode. */ - -#define GETCHARLEN(c, eptr, len) \ - c = *eptr; \ - if ((c & 0xfc00) == 0xd800) GETUTF16LEN(c, eptr, len); - -/* Get the next UTF-816character, testing for UTF-16 mode, not advancing the -pointer, incrementing length if there is a low surrogate. This is called when -we do not know if we are in UTF-16 mode. */ - -#define GETCHARLENTEST(c, eptr, len) \ - c = *eptr; \ - if (utf && (c & 0xfc00) == 0xd800) GETUTF16LEN(c, eptr, len); - -/* If the pointer is not at the start of a character, move it back until -it is. This is called only in UTF-16 mode - we don't put a test within the -macro because almost all calls are already within a block of UTF-16 only -code. */ - -#define BACKCHAR(eptr) if ((*eptr & 0xfc00) == 0xdc00) eptr-- - -/* Same as above, just in the other direction. */ -#define FORWARDCHAR(eptr) if ((*eptr & 0xfc00) == 0xdc00) eptr++ - -/* Same as above, but it allows a fully customizable form. */ -#define ACROSSCHAR(condition, eptr, action) \ - if ((condition) && ((eptr) & 0xfc00) == 0xdc00) action - -#elif defined COMPILE_PCRE32 - -/* These are trivial for the 32-bit library, since all UTF-32 characters fit -into one pcre_uchar unit. */ -#define MAX_VALUE_FOR_SINGLE_CHAR (0x10ffffu) -#define HAS_EXTRALEN(c) (0) -#define GET_EXTRALEN(c) (0) -#define NOT_FIRSTCHAR(c) (0) - -/* Get the next UTF-32 character, not advancing the pointer. This is called when -we know we are in UTF-32 mode. */ - -#define GETCHAR(c, eptr) \ - c = *(eptr); - -/* Get the next UTF-32 character, testing for UTF-32 mode, and not advancing the -pointer. */ - -#define GETCHARTEST(c, eptr) \ - c = *(eptr); - -/* Get the next UTF-32 character, advancing the pointer. This is called when we -know we are in UTF-32 mode. */ - -#define GETCHARINC(c, eptr) \ - c = *((eptr)++); - -/* Get the next character, testing for UTF-32 mode, and advancing the pointer. -This is called when we don't know if we are in UTF-32 mode. */ - -#define GETCHARINCTEST(c, eptr) \ - c = *((eptr)++); - -/* Get the next UTF-32 character, not advancing the pointer, not incrementing -length (since all UTF-32 is of length 1). This is called when we know we are in -UTF-32 mode. */ - -#define GETCHARLEN(c, eptr, len) \ - GETCHAR(c, eptr) - -/* Get the next UTF-32character, testing for UTF-32 mode, not advancing the -pointer, not incrementing the length (since all UTF-32 is of length 1). -This is called when we do not know if we are in UTF-32 mode. */ - -#define GETCHARLENTEST(c, eptr, len) \ - GETCHARTEST(c, eptr) - -/* If the pointer is not at the start of a character, move it back until -it is. This is called only in UTF-32 mode - we don't put a test within the -macro because almost all calls are already within a block of UTF-32 only -code. -These are all no-ops since all UTF-32 characters fit into one pcre_uchar. */ - -#define BACKCHAR(eptr) do { } while (0) - -/* Same as above, just in the other direction. */ -#define FORWARDCHAR(eptr) do { } while (0) - -/* Same as above, but it allows a fully customizable form. */ -#define ACROSSCHAR(condition, eptr, action) do { } while (0) - -#else -#error Unsupported compiling mode -#endif /* COMPILE_PCRE[8|16|32] */ - -#endif /* SUPPORT_UTF */ - -/* Tests for Unicode horizontal and vertical whitespace characters must check a -number of different values. Using a switch statement for this generates the -fastest code (no loop, no memory access), and there are several places in the -interpreter code where this happens. In order to ensure that all the case lists -remain in step, we use macros so that there is only one place where the lists -are defined. - -These values are also required as lists in pcre_compile.c when processing \h, -\H, \v and \V in a character class. The lists are defined in pcre_tables.c, but -macros that define the values are here so that all the definitions are -together. The lists must be in ascending character order, terminated by -NOTACHAR (which is 0xffffffff). - -Any changes should ensure that the various macros are kept in step with each -other. NOTE: The values also appear in pcre_jit_compile.c. */ - -/* ------ ASCII/Unicode environments ------ */ - -#ifndef EBCDIC - -#define HSPACE_LIST \ - CHAR_HT, CHAR_SPACE, CHAR_NBSP, \ - 0x1680, 0x180e, 0x2000, 0x2001, 0x2002, 0x2003, 0x2004, 0x2005, \ - 0x2006, 0x2007, 0x2008, 0x2009, 0x200A, 0x202f, 0x205f, 0x3000, \ - NOTACHAR - -#define HSPACE_MULTIBYTE_CASES \ - case 0x1680: /* OGHAM SPACE MARK */ \ - case 0x180e: /* MONGOLIAN VOWEL SEPARATOR */ \ - case 0x2000: /* EN QUAD */ \ - case 0x2001: /* EM QUAD */ \ - case 0x2002: /* EN SPACE */ \ - case 0x2003: /* EM SPACE */ \ - case 0x2004: /* THREE-PER-EM SPACE */ \ - case 0x2005: /* FOUR-PER-EM SPACE */ \ - case 0x2006: /* SIX-PER-EM SPACE */ \ - case 0x2007: /* FIGURE SPACE */ \ - case 0x2008: /* PUNCTUATION SPACE */ \ - case 0x2009: /* THIN SPACE */ \ - case 0x200A: /* HAIR SPACE */ \ - case 0x202f: /* NARROW NO-BREAK SPACE */ \ - case 0x205f: /* MEDIUM MATHEMATICAL SPACE */ \ - case 0x3000 /* IDEOGRAPHIC SPACE */ - -#define HSPACE_BYTE_CASES \ - case CHAR_HT: \ - case CHAR_SPACE: \ - case CHAR_NBSP - -#define HSPACE_CASES \ - HSPACE_BYTE_CASES: \ - HSPACE_MULTIBYTE_CASES - -#define VSPACE_LIST \ - CHAR_LF, CHAR_VT, CHAR_FF, CHAR_CR, CHAR_NEL, 0x2028, 0x2029, NOTACHAR - -#define VSPACE_MULTIBYTE_CASES \ - case 0x2028: /* LINE SEPARATOR */ \ - case 0x2029 /* PARAGRAPH SEPARATOR */ - -#define VSPACE_BYTE_CASES \ - case CHAR_LF: \ - case CHAR_VT: \ - case CHAR_FF: \ - case CHAR_CR: \ - case CHAR_NEL - -#define VSPACE_CASES \ - VSPACE_BYTE_CASES: \ - VSPACE_MULTIBYTE_CASES - -/* ------ EBCDIC environments ------ */ - -#else -#define HSPACE_LIST CHAR_HT, CHAR_SPACE, CHAR_NBSP, NOTACHAR - -#define HSPACE_BYTE_CASES \ - case CHAR_HT: \ - case CHAR_SPACE: \ - case CHAR_NBSP - -#define HSPACE_CASES HSPACE_BYTE_CASES - -#ifdef EBCDIC_NL25 -#define VSPACE_LIST \ - CHAR_VT, CHAR_FF, CHAR_CR, CHAR_NEL, CHAR_LF, NOTACHAR -#else -#define VSPACE_LIST \ - CHAR_VT, CHAR_FF, CHAR_CR, CHAR_LF, CHAR_NEL, NOTACHAR -#endif - -#define VSPACE_BYTE_CASES \ - case CHAR_LF: \ - case CHAR_VT: \ - case CHAR_FF: \ - case CHAR_CR: \ - case CHAR_NEL - -#define VSPACE_CASES VSPACE_BYTE_CASES -#endif /* EBCDIC */ - -/* ------ End of whitespace macros ------ */ - - - -/* Private flags containing information about the compiled regex. They used to -live at the top end of the options word, but that got almost full, so they were -moved to a 16-bit flags word - which got almost full, so now they are in a -32-bit flags word. From release 8.00, PCRE_NOPARTIAL is unused, as the -restrictions on partial matching have been lifted. It remains for backwards -compatibility. */ - -#define PCRE_MODE8 0x00000001 /* compiled in 8 bit mode */ -#define PCRE_MODE16 0x00000002 /* compiled in 16 bit mode */ -#define PCRE_MODE32 0x00000004 /* compiled in 32 bit mode */ -#define PCRE_FIRSTSET 0x00000010 /* first_char is set */ -#define PCRE_FCH_CASELESS 0x00000020 /* caseless first char */ -#define PCRE_REQCHSET 0x00000040 /* req_byte is set */ -#define PCRE_RCH_CASELESS 0x00000080 /* caseless requested char */ -#define PCRE_STARTLINE 0x00000100 /* start after \n for multiline */ -#define PCRE_NOPARTIAL 0x00000200 /* can't use partial with this regex */ -#define PCRE_JCHANGED 0x00000400 /* j option used in regex */ -#define PCRE_HASCRORLF 0x00000800 /* explicit \r or \n in pattern */ -#define PCRE_HASTHEN 0x00001000 /* pattern contains (*THEN) */ -#define PCRE_MLSET 0x00002000 /* match limit set by regex */ -#define PCRE_RLSET 0x00004000 /* recursion limit set by regex */ -#define PCRE_MATCH_EMPTY 0x00008000 /* pattern can match empty string */ - -#if defined COMPILE_PCRE8 -#define PCRE_MODE PCRE_MODE8 -#elif defined COMPILE_PCRE16 -#define PCRE_MODE PCRE_MODE16 -#elif defined COMPILE_PCRE32 -#define PCRE_MODE PCRE_MODE32 -#endif -#define PCRE_MODE_MASK (PCRE_MODE8 | PCRE_MODE16 | PCRE_MODE32) - -/* Flags for the "extra" block produced by pcre_study(). */ - -#define PCRE_STUDY_MAPPED 0x0001 /* a map of starting chars exists */ -#define PCRE_STUDY_MINLEN 0x0002 /* a minimum length field exists */ - -/* Masks for identifying the public options that are permitted at compile -time, run time, or study time, respectively. */ - -#define PCRE_NEWLINE_BITS (PCRE_NEWLINE_CR|PCRE_NEWLINE_LF|PCRE_NEWLINE_ANY| \ - PCRE_NEWLINE_ANYCRLF) - -#define PUBLIC_COMPILE_OPTIONS \ - (PCRE_CASELESS|PCRE_EXTENDED|PCRE_ANCHORED|PCRE_MULTILINE| \ - PCRE_DOTALL|PCRE_DOLLAR_ENDONLY|PCRE_EXTRA|PCRE_UNGREEDY|PCRE_UTF8| \ - PCRE_NO_AUTO_CAPTURE|PCRE_NO_AUTO_POSSESS| \ - PCRE_NO_UTF8_CHECK|PCRE_AUTO_CALLOUT|PCRE_FIRSTLINE| \ - PCRE_DUPNAMES|PCRE_NEWLINE_BITS|PCRE_BSR_ANYCRLF|PCRE_BSR_UNICODE| \ - PCRE_JAVASCRIPT_COMPAT|PCRE_UCP|PCRE_NO_START_OPTIMIZE|PCRE_NEVER_UTF) - -#define PUBLIC_EXEC_OPTIONS \ - (PCRE_ANCHORED|PCRE_NOTBOL|PCRE_NOTEOL|PCRE_NOTEMPTY|PCRE_NOTEMPTY_ATSTART| \ - PCRE_NO_UTF8_CHECK|PCRE_PARTIAL_HARD|PCRE_PARTIAL_SOFT|PCRE_NEWLINE_BITS| \ - PCRE_BSR_ANYCRLF|PCRE_BSR_UNICODE|PCRE_NO_START_OPTIMIZE) - -#define PUBLIC_DFA_EXEC_OPTIONS \ - (PCRE_ANCHORED|PCRE_NOTBOL|PCRE_NOTEOL|PCRE_NOTEMPTY|PCRE_NOTEMPTY_ATSTART| \ - PCRE_NO_UTF8_CHECK|PCRE_PARTIAL_HARD|PCRE_PARTIAL_SOFT|PCRE_DFA_SHORTEST| \ - PCRE_DFA_RESTART|PCRE_NEWLINE_BITS|PCRE_BSR_ANYCRLF|PCRE_BSR_UNICODE| \ - PCRE_NO_START_OPTIMIZE) - -#define PUBLIC_STUDY_OPTIONS \ - (PCRE_STUDY_JIT_COMPILE|PCRE_STUDY_JIT_PARTIAL_SOFT_COMPILE| \ - PCRE_STUDY_JIT_PARTIAL_HARD_COMPILE|PCRE_STUDY_EXTRA_NEEDED) - -#define PUBLIC_JIT_EXEC_OPTIONS \ - (PCRE_NO_UTF8_CHECK|PCRE_NOTBOL|PCRE_NOTEOL|PCRE_NOTEMPTY|\ - PCRE_NOTEMPTY_ATSTART|PCRE_PARTIAL_SOFT|PCRE_PARTIAL_HARD) - -/* Magic number to provide a small check against being handed junk. */ - -#define MAGIC_NUMBER 0x50435245UL /* 'PCRE' */ - -/* This variable is used to detect a loaded regular expression -in different endianness. */ - -#define REVERSED_MAGIC_NUMBER 0x45524350UL /* 'ERCP' */ - -/* The maximum remaining length of subject we are prepared to search for a -req_byte match. */ - -#define REQ_BYTE_MAX 1000 - -/* Miscellaneous definitions. The #ifndef is to pacify compiler warnings in -environments where these macros are defined elsewhere. Unfortunately, there -is no way to do the same for the typedef. */ - -typedef int BOOL; - -#ifndef FALSE -#define FALSE 0 -#define TRUE 1 -#endif - -/* If PCRE is to support UTF-8 on EBCDIC platforms, we cannot use normal -character constants like '*' because the compiler would emit their EBCDIC code, -which is different from their ASCII/UTF-8 code. Instead we define macros for -the characters so that they always use the ASCII/UTF-8 code when UTF-8 support -is enabled. When UTF-8 support is not enabled, the definitions use character -literals. Both character and string versions of each character are needed, and -there are some longer strings as well. - -This means that, on EBCDIC platforms, the PCRE library can handle either -EBCDIC, or UTF-8, but not both. To support both in the same compiled library -would need different lookups depending on whether PCRE_UTF8 was set or not. -This would make it impossible to use characters in switch/case statements, -which would reduce performance. For a theoretical use (which nobody has asked -for) in a minority area (EBCDIC platforms), this is not sensible. Any -application that did need both could compile two versions of the library, using -macros to give the functions distinct names. */ - -#ifndef SUPPORT_UTF - -/* UTF-8 support is not enabled; use the platform-dependent character literals -so that PCRE works in both ASCII and EBCDIC environments, but only in non-UTF -mode. Newline characters are problematic in EBCDIC. Though it has CR and LF -characters, a common practice has been to use its NL (0x15) character as the -line terminator in C-like processing environments. However, sometimes the LF -(0x25) character is used instead, according to this Unicode document: - -http://unicode.org/standard/reports/tr13/tr13-5.html - -PCRE defaults EBCDIC NL to 0x15, but has a build-time option to select 0x25 -instead. Whichever is *not* chosen is defined as NEL. - -In both ASCII and EBCDIC environments, CHAR_NL and CHAR_LF are synonyms for the -same code point. */ - -#ifdef EBCDIC - -#ifndef EBCDIC_NL25 -#define CHAR_NL '\x15' -#define CHAR_NEL '\x25' -#define STR_NL "\x15" -#define STR_NEL "\x25" -#else -#define CHAR_NL '\x25' -#define CHAR_NEL '\x15' -#define STR_NL "\x25" -#define STR_NEL "\x15" -#endif - -#define CHAR_LF CHAR_NL -#define STR_LF STR_NL - -#define CHAR_ESC '\047' -#define CHAR_DEL '\007' -#define CHAR_NBSP '\x41' -#define STR_ESC "\047" -#define STR_DEL "\007" - -#else /* Not EBCDIC */ - -/* In ASCII/Unicode, linefeed is '\n' and we equate this to NL for -compatibility. NEL is the Unicode newline character; make sure it is -a positive value. */ - -#define CHAR_LF '\n' -#define CHAR_NL CHAR_LF -#define CHAR_NEL ((unsigned char)'\x85') -#define CHAR_ESC '\033' -#define CHAR_DEL '\177' -#define CHAR_NBSP ((unsigned char)'\xa0') - -#define STR_LF "\n" -#define STR_NL STR_LF -#define STR_NEL "\x85" -#define STR_ESC "\033" -#define STR_DEL "\177" - -#endif /* EBCDIC */ - -/* The remaining definitions work in both environments. */ - -#define CHAR_NULL '\0' -#define CHAR_HT '\t' -#define CHAR_VT '\v' -#define CHAR_FF '\f' -#define CHAR_CR '\r' -#define CHAR_BS '\b' -#define CHAR_BEL '\a' - -#define CHAR_SPACE ' ' -#define CHAR_EXCLAMATION_MARK '!' -#define CHAR_QUOTATION_MARK '"' -#define CHAR_NUMBER_SIGN '#' -#define CHAR_DOLLAR_SIGN '$' -#define CHAR_PERCENT_SIGN '%' -#define CHAR_AMPERSAND '&' -#define CHAR_APOSTROPHE '\'' -#define CHAR_LEFT_PARENTHESIS '(' -#define CHAR_RIGHT_PARENTHESIS ')' -#define CHAR_ASTERISK '*' -#define CHAR_PLUS '+' -#define CHAR_COMMA ',' -#define CHAR_MINUS '-' -#define CHAR_DOT '.' -#define CHAR_SLASH '/' -#define CHAR_0 '0' -#define CHAR_1 '1' -#define CHAR_2 '2' -#define CHAR_3 '3' -#define CHAR_4 '4' -#define CHAR_5 '5' -#define CHAR_6 '6' -#define CHAR_7 '7' -#define CHAR_8 '8' -#define CHAR_9 '9' -#define CHAR_COLON ':' -#define CHAR_SEMICOLON ';' -#define CHAR_LESS_THAN_SIGN '<' -#define CHAR_EQUALS_SIGN '=' -#define CHAR_GREATER_THAN_SIGN '>' -#define CHAR_QUESTION_MARK '?' -#define CHAR_COMMERCIAL_AT '@' -#define CHAR_A 'A' -#define CHAR_B 'B' -#define CHAR_C 'C' -#define CHAR_D 'D' -#define CHAR_E 'E' -#define CHAR_F 'F' -#define CHAR_G 'G' -#define CHAR_H 'H' -#define CHAR_I 'I' -#define CHAR_J 'J' -#define CHAR_K 'K' -#define CHAR_L 'L' -#define CHAR_M 'M' -#define CHAR_N 'N' -#define CHAR_O 'O' -#define CHAR_P 'P' -#define CHAR_Q 'Q' -#define CHAR_R 'R' -#define CHAR_S 'S' -#define CHAR_T 'T' -#define CHAR_U 'U' -#define CHAR_V 'V' -#define CHAR_W 'W' -#define CHAR_X 'X' -#define CHAR_Y 'Y' -#define CHAR_Z 'Z' -#define CHAR_LEFT_SQUARE_BRACKET '[' -#define CHAR_BACKSLASH '\\' -#define CHAR_RIGHT_SQUARE_BRACKET ']' -#define CHAR_CIRCUMFLEX_ACCENT '^' -#define CHAR_UNDERSCORE '_' -#define CHAR_GRAVE_ACCENT '`' -#define CHAR_a 'a' -#define CHAR_b 'b' -#define CHAR_c 'c' -#define CHAR_d 'd' -#define CHAR_e 'e' -#define CHAR_f 'f' -#define CHAR_g 'g' -#define CHAR_h 'h' -#define CHAR_i 'i' -#define CHAR_j 'j' -#define CHAR_k 'k' -#define CHAR_l 'l' -#define CHAR_m 'm' -#define CHAR_n 'n' -#define CHAR_o 'o' -#define CHAR_p 'p' -#define CHAR_q 'q' -#define CHAR_r 'r' -#define CHAR_s 's' -#define CHAR_t 't' -#define CHAR_u 'u' -#define CHAR_v 'v' -#define CHAR_w 'w' -#define CHAR_x 'x' -#define CHAR_y 'y' -#define CHAR_z 'z' -#define CHAR_LEFT_CURLY_BRACKET '{' -#define CHAR_VERTICAL_LINE '|' -#define CHAR_RIGHT_CURLY_BRACKET '}' -#define CHAR_TILDE '~' - -#define STR_HT "\t" -#define STR_VT "\v" -#define STR_FF "\f" -#define STR_CR "\r" -#define STR_BS "\b" -#define STR_BEL "\a" - -#define STR_SPACE " " -#define STR_EXCLAMATION_MARK "!" -#define STR_QUOTATION_MARK "\"" -#define STR_NUMBER_SIGN "#" -#define STR_DOLLAR_SIGN "$" -#define STR_PERCENT_SIGN "%" -#define STR_AMPERSAND "&" -#define STR_APOSTROPHE "'" -#define STR_LEFT_PARENTHESIS "(" -#define STR_RIGHT_PARENTHESIS ")" -#define STR_ASTERISK "*" -#define STR_PLUS "+" -#define STR_COMMA "," -#define STR_MINUS "-" -#define STR_DOT "." -#define STR_SLASH "/" -#define STR_0 "0" -#define STR_1 "1" -#define STR_2 "2" -#define STR_3 "3" -#define STR_4 "4" -#define STR_5 "5" -#define STR_6 "6" -#define STR_7 "7" -#define STR_8 "8" -#define STR_9 "9" -#define STR_COLON ":" -#define STR_SEMICOLON ";" -#define STR_LESS_THAN_SIGN "<" -#define STR_EQUALS_SIGN "=" -#define STR_GREATER_THAN_SIGN ">" -#define STR_QUESTION_MARK "?" -#define STR_COMMERCIAL_AT "@" -#define STR_A "A" -#define STR_B "B" -#define STR_C "C" -#define STR_D "D" -#define STR_E "E" -#define STR_F "F" -#define STR_G "G" -#define STR_H "H" -#define STR_I "I" -#define STR_J "J" -#define STR_K "K" -#define STR_L "L" -#define STR_M "M" -#define STR_N "N" -#define STR_O "O" -#define STR_P "P" -#define STR_Q "Q" -#define STR_R "R" -#define STR_S "S" -#define STR_T "T" -#define STR_U "U" -#define STR_V "V" -#define STR_W "W" -#define STR_X "X" -#define STR_Y "Y" -#define STR_Z "Z" -#define STR_LEFT_SQUARE_BRACKET "[" -#define STR_BACKSLASH "\\" -#define STR_RIGHT_SQUARE_BRACKET "]" -#define STR_CIRCUMFLEX_ACCENT "^" -#define STR_UNDERSCORE "_" -#define STR_GRAVE_ACCENT "`" -#define STR_a "a" -#define STR_b "b" -#define STR_c "c" -#define STR_d "d" -#define STR_e "e" -#define STR_f "f" -#define STR_g "g" -#define STR_h "h" -#define STR_i "i" -#define STR_j "j" -#define STR_k "k" -#define STR_l "l" -#define STR_m "m" -#define STR_n "n" -#define STR_o "o" -#define STR_p "p" -#define STR_q "q" -#define STR_r "r" -#define STR_s "s" -#define STR_t "t" -#define STR_u "u" -#define STR_v "v" -#define STR_w "w" -#define STR_x "x" -#define STR_y "y" -#define STR_z "z" -#define STR_LEFT_CURLY_BRACKET "{" -#define STR_VERTICAL_LINE "|" -#define STR_RIGHT_CURLY_BRACKET "}" -#define STR_TILDE "~" - -#define STRING_ACCEPT0 "ACCEPT\0" -#define STRING_COMMIT0 "COMMIT\0" -#define STRING_F0 "F\0" -#define STRING_FAIL0 "FAIL\0" -#define STRING_MARK0 "MARK\0" -#define STRING_PRUNE0 "PRUNE\0" -#define STRING_SKIP0 "SKIP\0" -#define STRING_THEN "THEN" - -#define STRING_alpha0 "alpha\0" -#define STRING_lower0 "lower\0" -#define STRING_upper0 "upper\0" -#define STRING_alnum0 "alnum\0" -#define STRING_ascii0 "ascii\0" -#define STRING_blank0 "blank\0" -#define STRING_cntrl0 "cntrl\0" -#define STRING_digit0 "digit\0" -#define STRING_graph0 "graph\0" -#define STRING_print0 "print\0" -#define STRING_punct0 "punct\0" -#define STRING_space0 "space\0" -#define STRING_word0 "word\0" -#define STRING_xdigit "xdigit" - -#define STRING_DEFINE "DEFINE" -#define STRING_WEIRD_STARTWORD "[:<:]]" -#define STRING_WEIRD_ENDWORD "[:>:]]" - -#define STRING_CR_RIGHTPAR "CR)" -#define STRING_LF_RIGHTPAR "LF)" -#define STRING_CRLF_RIGHTPAR "CRLF)" -#define STRING_ANY_RIGHTPAR "ANY)" -#define STRING_ANYCRLF_RIGHTPAR "ANYCRLF)" -#define STRING_BSR_ANYCRLF_RIGHTPAR "BSR_ANYCRLF)" -#define STRING_BSR_UNICODE_RIGHTPAR "BSR_UNICODE)" -#define STRING_UTF8_RIGHTPAR "UTF8)" -#define STRING_UTF16_RIGHTPAR "UTF16)" -#define STRING_UTF32_RIGHTPAR "UTF32)" -#define STRING_UTF_RIGHTPAR "UTF)" -#define STRING_UCP_RIGHTPAR "UCP)" -#define STRING_NO_AUTO_POSSESS_RIGHTPAR "NO_AUTO_POSSESS)" -#define STRING_NO_START_OPT_RIGHTPAR "NO_START_OPT)" -#define STRING_LIMIT_MATCH_EQ "LIMIT_MATCH=" -#define STRING_LIMIT_RECURSION_EQ "LIMIT_RECURSION=" - -#else /* SUPPORT_UTF */ - -/* UTF-8 support is enabled; always use UTF-8 (=ASCII) character codes. This -works in both modes non-EBCDIC platforms, and on EBCDIC platforms in UTF-8 mode -only. */ - -#define CHAR_HT '\011' -#define CHAR_VT '\013' -#define CHAR_FF '\014' -#define CHAR_CR '\015' -#define CHAR_LF '\012' -#define CHAR_NL CHAR_LF -#define CHAR_NEL ((unsigned char)'\x85') -#define CHAR_BS '\010' -#define CHAR_BEL '\007' -#define CHAR_ESC '\033' -#define CHAR_DEL '\177' - -#define CHAR_NULL '\0' -#define CHAR_SPACE '\040' -#define CHAR_EXCLAMATION_MARK '\041' -#define CHAR_QUOTATION_MARK '\042' -#define CHAR_NUMBER_SIGN '\043' -#define CHAR_DOLLAR_SIGN '\044' -#define CHAR_PERCENT_SIGN '\045' -#define CHAR_AMPERSAND '\046' -#define CHAR_APOSTROPHE '\047' -#define CHAR_LEFT_PARENTHESIS '\050' -#define CHAR_RIGHT_PARENTHESIS '\051' -#define CHAR_ASTERISK '\052' -#define CHAR_PLUS '\053' -#define CHAR_COMMA '\054' -#define CHAR_MINUS '\055' -#define CHAR_DOT '\056' -#define CHAR_SLASH '\057' -#define CHAR_0 '\060' -#define CHAR_1 '\061' -#define CHAR_2 '\062' -#define CHAR_3 '\063' -#define CHAR_4 '\064' -#define CHAR_5 '\065' -#define CHAR_6 '\066' -#define CHAR_7 '\067' -#define CHAR_8 '\070' -#define CHAR_9 '\071' -#define CHAR_COLON '\072' -#define CHAR_SEMICOLON '\073' -#define CHAR_LESS_THAN_SIGN '\074' -#define CHAR_EQUALS_SIGN '\075' -#define CHAR_GREATER_THAN_SIGN '\076' -#define CHAR_QUESTION_MARK '\077' -#define CHAR_COMMERCIAL_AT '\100' -#define CHAR_A '\101' -#define CHAR_B '\102' -#define CHAR_C '\103' -#define CHAR_D '\104' -#define CHAR_E '\105' -#define CHAR_F '\106' -#define CHAR_G '\107' -#define CHAR_H '\110' -#define CHAR_I '\111' -#define CHAR_J '\112' -#define CHAR_K '\113' -#define CHAR_L '\114' -#define CHAR_M '\115' -#define CHAR_N '\116' -#define CHAR_O '\117' -#define CHAR_P '\120' -#define CHAR_Q '\121' -#define CHAR_R '\122' -#define CHAR_S '\123' -#define CHAR_T '\124' -#define CHAR_U '\125' -#define CHAR_V '\126' -#define CHAR_W '\127' -#define CHAR_X '\130' -#define CHAR_Y '\131' -#define CHAR_Z '\132' -#define CHAR_LEFT_SQUARE_BRACKET '\133' -#define CHAR_BACKSLASH '\134' -#define CHAR_RIGHT_SQUARE_BRACKET '\135' -#define CHAR_CIRCUMFLEX_ACCENT '\136' -#define CHAR_UNDERSCORE '\137' -#define CHAR_GRAVE_ACCENT '\140' -#define CHAR_a '\141' -#define CHAR_b '\142' -#define CHAR_c '\143' -#define CHAR_d '\144' -#define CHAR_e '\145' -#define CHAR_f '\146' -#define CHAR_g '\147' -#define CHAR_h '\150' -#define CHAR_i '\151' -#define CHAR_j '\152' -#define CHAR_k '\153' -#define CHAR_l '\154' -#define CHAR_m '\155' -#define CHAR_n '\156' -#define CHAR_o '\157' -#define CHAR_p '\160' -#define CHAR_q '\161' -#define CHAR_r '\162' -#define CHAR_s '\163' -#define CHAR_t '\164' -#define CHAR_u '\165' -#define CHAR_v '\166' -#define CHAR_w '\167' -#define CHAR_x '\170' -#define CHAR_y '\171' -#define CHAR_z '\172' -#define CHAR_LEFT_CURLY_BRACKET '\173' -#define CHAR_VERTICAL_LINE '\174' -#define CHAR_RIGHT_CURLY_BRACKET '\175' -#define CHAR_TILDE '\176' -#define CHAR_NBSP ((unsigned char)'\xa0') - -#define STR_HT "\011" -#define STR_VT "\013" -#define STR_FF "\014" -#define STR_CR "\015" -#define STR_NL "\012" -#define STR_BS "\010" -#define STR_BEL "\007" -#define STR_ESC "\033" -#define STR_DEL "\177" - -#define STR_SPACE "\040" -#define STR_EXCLAMATION_MARK "\041" -#define STR_QUOTATION_MARK "\042" -#define STR_NUMBER_SIGN "\043" -#define STR_DOLLAR_SIGN "\044" -#define STR_PERCENT_SIGN "\045" -#define STR_AMPERSAND "\046" -#define STR_APOSTROPHE "\047" -#define STR_LEFT_PARENTHESIS "\050" -#define STR_RIGHT_PARENTHESIS "\051" -#define STR_ASTERISK "\052" -#define STR_PLUS "\053" -#define STR_COMMA "\054" -#define STR_MINUS "\055" -#define STR_DOT "\056" -#define STR_SLASH "\057" -#define STR_0 "\060" -#define STR_1 "\061" -#define STR_2 "\062" -#define STR_3 "\063" -#define STR_4 "\064" -#define STR_5 "\065" -#define STR_6 "\066" -#define STR_7 "\067" -#define STR_8 "\070" -#define STR_9 "\071" -#define STR_COLON "\072" -#define STR_SEMICOLON "\073" -#define STR_LESS_THAN_SIGN "\074" -#define STR_EQUALS_SIGN "\075" -#define STR_GREATER_THAN_SIGN "\076" -#define STR_QUESTION_MARK "\077" -#define STR_COMMERCIAL_AT "\100" -#define STR_A "\101" -#define STR_B "\102" -#define STR_C "\103" -#define STR_D "\104" -#define STR_E "\105" -#define STR_F "\106" -#define STR_G "\107" -#define STR_H "\110" -#define STR_I "\111" -#define STR_J "\112" -#define STR_K "\113" -#define STR_L "\114" -#define STR_M "\115" -#define STR_N "\116" -#define STR_O "\117" -#define STR_P "\120" -#define STR_Q "\121" -#define STR_R "\122" -#define STR_S "\123" -#define STR_T "\124" -#define STR_U "\125" -#define STR_V "\126" -#define STR_W "\127" -#define STR_X "\130" -#define STR_Y "\131" -#define STR_Z "\132" -#define STR_LEFT_SQUARE_BRACKET "\133" -#define STR_BACKSLASH "\134" -#define STR_RIGHT_SQUARE_BRACKET "\135" -#define STR_CIRCUMFLEX_ACCENT "\136" -#define STR_UNDERSCORE "\137" -#define STR_GRAVE_ACCENT "\140" -#define STR_a "\141" -#define STR_b "\142" -#define STR_c "\143" -#define STR_d "\144" -#define STR_e "\145" -#define STR_f "\146" -#define STR_g "\147" -#define STR_h "\150" -#define STR_i "\151" -#define STR_j "\152" -#define STR_k "\153" -#define STR_l "\154" -#define STR_m "\155" -#define STR_n "\156" -#define STR_o "\157" -#define STR_p "\160" -#define STR_q "\161" -#define STR_r "\162" -#define STR_s "\163" -#define STR_t "\164" -#define STR_u "\165" -#define STR_v "\166" -#define STR_w "\167" -#define STR_x "\170" -#define STR_y "\171" -#define STR_z "\172" -#define STR_LEFT_CURLY_BRACKET "\173" -#define STR_VERTICAL_LINE "\174" -#define STR_RIGHT_CURLY_BRACKET "\175" -#define STR_TILDE "\176" - -#define STRING_ACCEPT0 STR_A STR_C STR_C STR_E STR_P STR_T "\0" -#define STRING_COMMIT0 STR_C STR_O STR_M STR_M STR_I STR_T "\0" -#define STRING_F0 STR_F "\0" -#define STRING_FAIL0 STR_F STR_A STR_I STR_L "\0" -#define STRING_MARK0 STR_M STR_A STR_R STR_K "\0" -#define STRING_PRUNE0 STR_P STR_R STR_U STR_N STR_E "\0" -#define STRING_SKIP0 STR_S STR_K STR_I STR_P "\0" -#define STRING_THEN STR_T STR_H STR_E STR_N - -#define STRING_alpha0 STR_a STR_l STR_p STR_h STR_a "\0" -#define STRING_lower0 STR_l STR_o STR_w STR_e STR_r "\0" -#define STRING_upper0 STR_u STR_p STR_p STR_e STR_r "\0" -#define STRING_alnum0 STR_a STR_l STR_n STR_u STR_m "\0" -#define STRING_ascii0 STR_a STR_s STR_c STR_i STR_i "\0" -#define STRING_blank0 STR_b STR_l STR_a STR_n STR_k "\0" -#define STRING_cntrl0 STR_c STR_n STR_t STR_r STR_l "\0" -#define STRING_digit0 STR_d STR_i STR_g STR_i STR_t "\0" -#define STRING_graph0 STR_g STR_r STR_a STR_p STR_h "\0" -#define STRING_print0 STR_p STR_r STR_i STR_n STR_t "\0" -#define STRING_punct0 STR_p STR_u STR_n STR_c STR_t "\0" -#define STRING_space0 STR_s STR_p STR_a STR_c STR_e "\0" -#define STRING_word0 STR_w STR_o STR_r STR_d "\0" -#define STRING_xdigit STR_x STR_d STR_i STR_g STR_i STR_t - -#define STRING_DEFINE STR_D STR_E STR_F STR_I STR_N STR_E -#define STRING_WEIRD_STARTWORD STR_LEFT_SQUARE_BRACKET STR_COLON STR_LESS_THAN_SIGN STR_COLON STR_RIGHT_SQUARE_BRACKET STR_RIGHT_SQUARE_BRACKET -#define STRING_WEIRD_ENDWORD STR_LEFT_SQUARE_BRACKET STR_COLON STR_GREATER_THAN_SIGN STR_COLON STR_RIGHT_SQUARE_BRACKET STR_RIGHT_SQUARE_BRACKET - -#define STRING_CR_RIGHTPAR STR_C STR_R STR_RIGHT_PARENTHESIS -#define STRING_LF_RIGHTPAR STR_L STR_F STR_RIGHT_PARENTHESIS -#define STRING_CRLF_RIGHTPAR STR_C STR_R STR_L STR_F STR_RIGHT_PARENTHESIS -#define STRING_ANY_RIGHTPAR STR_A STR_N STR_Y STR_RIGHT_PARENTHESIS -#define STRING_ANYCRLF_RIGHTPAR STR_A STR_N STR_Y STR_C STR_R STR_L STR_F STR_RIGHT_PARENTHESIS -#define STRING_BSR_ANYCRLF_RIGHTPAR STR_B STR_S STR_R STR_UNDERSCORE STR_A STR_N STR_Y STR_C STR_R STR_L STR_F STR_RIGHT_PARENTHESIS -#define STRING_BSR_UNICODE_RIGHTPAR STR_B STR_S STR_R STR_UNDERSCORE STR_U STR_N STR_I STR_C STR_O STR_D STR_E STR_RIGHT_PARENTHESIS -#define STRING_UTF8_RIGHTPAR STR_U STR_T STR_F STR_8 STR_RIGHT_PARENTHESIS -#define STRING_UTF16_RIGHTPAR STR_U STR_T STR_F STR_1 STR_6 STR_RIGHT_PARENTHESIS -#define STRING_UTF32_RIGHTPAR STR_U STR_T STR_F STR_3 STR_2 STR_RIGHT_PARENTHESIS -#define STRING_UTF_RIGHTPAR STR_U STR_T STR_F STR_RIGHT_PARENTHESIS -#define STRING_UCP_RIGHTPAR STR_U STR_C STR_P STR_RIGHT_PARENTHESIS -#define STRING_NO_AUTO_POSSESS_RIGHTPAR STR_N STR_O STR_UNDERSCORE STR_A STR_U STR_T STR_O STR_UNDERSCORE STR_P STR_O STR_S STR_S STR_E STR_S STR_S STR_RIGHT_PARENTHESIS -#define STRING_NO_START_OPT_RIGHTPAR STR_N STR_O STR_UNDERSCORE STR_S STR_T STR_A STR_R STR_T STR_UNDERSCORE STR_O STR_P STR_T STR_RIGHT_PARENTHESIS -#define STRING_LIMIT_MATCH_EQ STR_L STR_I STR_M STR_I STR_T STR_UNDERSCORE STR_M STR_A STR_T STR_C STR_H STR_EQUALS_SIGN -#define STRING_LIMIT_RECURSION_EQ STR_L STR_I STR_M STR_I STR_T STR_UNDERSCORE STR_R STR_E STR_C STR_U STR_R STR_S STR_I STR_O STR_N STR_EQUALS_SIGN - -#endif /* SUPPORT_UTF */ - -/* Escape items that are just an encoding of a particular data value. */ - -#ifndef ESC_a -#define ESC_a CHAR_BEL -#endif - -#ifndef ESC_e -#define ESC_e CHAR_ESC -#endif - -#ifndef ESC_f -#define ESC_f CHAR_FF -#endif - -#ifndef ESC_n -#define ESC_n CHAR_LF -#endif - -#ifndef ESC_r -#define ESC_r CHAR_CR -#endif - -/* We can't officially use ESC_t because it is a POSIX reserved identifier -(presumably because of all the others like size_t). */ - -#ifndef ESC_tee -#define ESC_tee CHAR_HT -#endif - -/* Codes for different types of Unicode property */ - -#define PT_ANY 0 /* Any property - matches all chars */ -#define PT_LAMP 1 /* L& - the union of Lu, Ll, Lt */ -#define PT_GC 2 /* Specified general characteristic (e.g. L) */ -#define PT_PC 3 /* Specified particular characteristic (e.g. Lu) */ -#define PT_SC 4 /* Script (e.g. Han) */ -#define PT_ALNUM 5 /* Alphanumeric - the union of L and N */ -#define PT_SPACE 6 /* Perl space - Z plus 9,10,12,13 */ -#define PT_PXSPACE 7 /* POSIX space - Z plus 9,10,11,12,13 */ -#define PT_WORD 8 /* Word - L plus N plus underscore */ -#define PT_CLIST 9 /* Pseudo-property: match character list */ -#define PT_UCNC 10 /* Universal Character nameable character */ -#define PT_TABSIZE 11 /* Size of square table for autopossessify tests */ - -/* The following special properties are used only in XCLASS items, when POSIX -classes are specified and PCRE_UCP is set - in other words, for Unicode -handling of these classes. They are not available via the \p or \P escapes like -those in the above list, and so they do not take part in the autopossessifying -table. */ - -#define PT_PXGRAPH 11 /* [:graph:] - characters that mark the paper */ -#define PT_PXPRINT 12 /* [:print:] - [:graph:] plus non-control spaces */ -#define PT_PXPUNCT 13 /* [:punct:] - punctuation characters */ - -/* Flag bits and data types for the extended class (OP_XCLASS) for classes that -contain characters with values greater than 255. */ - -#define XCL_NOT 0x01 /* Flag: this is a negative class */ -#define XCL_MAP 0x02 /* Flag: a 32-byte map is present */ -#define XCL_HASPROP 0x04 /* Flag: property checks are present. */ - -#define XCL_END 0 /* Marks end of individual items */ -#define XCL_SINGLE 1 /* Single item (one multibyte char) follows */ -#define XCL_RANGE 2 /* A range (two multibyte chars) follows */ -#define XCL_PROP 3 /* Unicode property (2-byte property code follows) */ -#define XCL_NOTPROP 4 /* Unicode inverted property (ditto) */ - -/* These are escaped items that aren't just an encoding of a particular data -value such as \n. They must have non-zero values, as check_escape() returns 0 -for a data character. Also, they must appear in the same order as in the -opcode definitions below, up to ESC_z. There's a dummy for OP_ALLANY because it -corresponds to "." in DOTALL mode rather than an escape sequence. It is also -used for [^] in JavaScript compatibility mode, and for \C in non-utf mode. In -non-DOTALL mode, "." behaves like \N. - -The special values ESC_DU, ESC_du, etc. are used instead of ESC_D, ESC_d, etc. -when PCRE_UCP is set and replacement of \d etc by \p sequences is required. -They must be contiguous, and remain in order so that the replacements can be -looked up from a table. - -Negative numbers are used to encode a backreference (\1, \2, \3, etc.) in -check_escape(). There are two tests in the code for an escape -greater than ESC_b and less than ESC_Z to detect the types that may be -repeated. These are the types that consume characters. If any new escapes are -put in between that don't consume a character, that code will have to change. -*/ - -enum { ESC_A = 1, ESC_G, ESC_K, ESC_B, ESC_b, ESC_D, ESC_d, ESC_S, ESC_s, - ESC_W, ESC_w, ESC_N, ESC_dum, ESC_C, ESC_P, ESC_p, ESC_R, ESC_H, - ESC_h, ESC_V, ESC_v, ESC_X, ESC_Z, ESC_z, - ESC_E, ESC_Q, ESC_g, ESC_k, - ESC_DU, ESC_du, ESC_SU, ESC_su, ESC_WU, ESC_wu }; - - -/********************** Opcode definitions ******************/ - -/****** NOTE NOTE NOTE ****** - -Starting from 1 (i.e. after OP_END), the values up to OP_EOD must correspond in -order to the list of escapes immediately above. Furthermore, values up to -OP_DOLLM must not be changed without adjusting the table called autoposstab in -pcre_compile.c - -Whenever this list is updated, the two macro definitions that follow must be -updated to match. The possessification table called "opcode_possessify" in -pcre_compile.c must also be updated, and also the tables called "coptable" -and "poptable" in pcre_dfa_exec.c. - -****** NOTE NOTE NOTE ******/ - - -/* The values between FIRST_AUTOTAB_OP and LAST_AUTOTAB_RIGHT_OP, inclusive, -are used in a table for deciding whether a repeated character type can be -auto-possessified. */ - -#define FIRST_AUTOTAB_OP OP_NOT_DIGIT -#define LAST_AUTOTAB_LEFT_OP OP_EXTUNI -#define LAST_AUTOTAB_RIGHT_OP OP_DOLLM - -enum { - OP_END, /* 0 End of pattern */ - - /* Values corresponding to backslashed metacharacters */ - - OP_SOD, /* 1 Start of data: \A */ - OP_SOM, /* 2 Start of match (subject + offset): \G */ - OP_SET_SOM, /* 3 Set start of match (\K) */ - OP_NOT_WORD_BOUNDARY, /* 4 \B */ - OP_WORD_BOUNDARY, /* 5 \b */ - OP_NOT_DIGIT, /* 6 \D */ - OP_DIGIT, /* 7 \d */ - OP_NOT_WHITESPACE, /* 8 \S */ - OP_WHITESPACE, /* 9 \s */ - OP_NOT_WORDCHAR, /* 10 \W */ - OP_WORDCHAR, /* 11 \w */ - - OP_ANY, /* 12 Match any character except newline (\N) */ - OP_ALLANY, /* 13 Match any character */ - OP_ANYBYTE, /* 14 Match any byte (\C); different to OP_ANY for UTF-8 */ - OP_NOTPROP, /* 15 \P (not Unicode property) */ - OP_PROP, /* 16 \p (Unicode property) */ - OP_ANYNL, /* 17 \R (any newline sequence) */ - OP_NOT_HSPACE, /* 18 \H (not horizontal whitespace) */ - OP_HSPACE, /* 19 \h (horizontal whitespace) */ - OP_NOT_VSPACE, /* 20 \V (not vertical whitespace) */ - OP_VSPACE, /* 21 \v (vertical whitespace) */ - OP_EXTUNI, /* 22 \X (extended Unicode sequence */ - OP_EODN, /* 23 End of data or \n at end of data (\Z) */ - OP_EOD, /* 24 End of data (\z) */ - - /* Line end assertions */ - - OP_DOLL, /* 25 End of line - not multiline */ - OP_DOLLM, /* 26 End of line - multiline */ - OP_CIRC, /* 27 Start of line - not multiline */ - OP_CIRCM, /* 28 Start of line - multiline */ - - /* Single characters; caseful must precede the caseless ones */ - - OP_CHAR, /* 29 Match one character, casefully */ - OP_CHARI, /* 30 Match one character, caselessly */ - OP_NOT, /* 31 Match one character, not the given one, casefully */ - OP_NOTI, /* 32 Match one character, not the given one, caselessly */ - - /* The following sets of 13 opcodes must always be kept in step because - the offset from the first one is used to generate the others. */ - - /* Repeated characters; caseful must precede the caseless ones */ - - OP_STAR, /* 33 The maximizing and minimizing versions of */ - OP_MINSTAR, /* 34 these six opcodes must come in pairs, with */ - OP_PLUS, /* 35 the minimizing one second. */ - OP_MINPLUS, /* 36 */ - OP_QUERY, /* 37 */ - OP_MINQUERY, /* 38 */ - - OP_UPTO, /* 39 From 0 to n matches of one character, caseful*/ - OP_MINUPTO, /* 40 */ - OP_EXACT, /* 41 Exactly n matches */ - - OP_POSSTAR, /* 42 Possessified star, caseful */ - OP_POSPLUS, /* 43 Possessified plus, caseful */ - OP_POSQUERY, /* 44 Posesssified query, caseful */ - OP_POSUPTO, /* 45 Possessified upto, caseful */ - - /* Repeated characters; caseless must follow the caseful ones */ - - OP_STARI, /* 46 */ - OP_MINSTARI, /* 47 */ - OP_PLUSI, /* 48 */ - OP_MINPLUSI, /* 49 */ - OP_QUERYI, /* 50 */ - OP_MINQUERYI, /* 51 */ - - OP_UPTOI, /* 52 From 0 to n matches of one character, caseless */ - OP_MINUPTOI, /* 53 */ - OP_EXACTI, /* 54 */ - - OP_POSSTARI, /* 55 Possessified star, caseless */ - OP_POSPLUSI, /* 56 Possessified plus, caseless */ - OP_POSQUERYI, /* 57 Posesssified query, caseless */ - OP_POSUPTOI, /* 58 Possessified upto, caseless */ - - /* The negated ones must follow the non-negated ones, and match them */ - /* Negated repeated character, caseful; must precede the caseless ones */ - - OP_NOTSTAR, /* 59 The maximizing and minimizing versions of */ - OP_NOTMINSTAR, /* 60 these six opcodes must come in pairs, with */ - OP_NOTPLUS, /* 61 the minimizing one second. They must be in */ - OP_NOTMINPLUS, /* 62 exactly the same order as those above. */ - OP_NOTQUERY, /* 63 */ - OP_NOTMINQUERY, /* 64 */ - - OP_NOTUPTO, /* 65 From 0 to n matches, caseful */ - OP_NOTMINUPTO, /* 66 */ - OP_NOTEXACT, /* 67 Exactly n matches */ - - OP_NOTPOSSTAR, /* 68 Possessified versions, caseful */ - OP_NOTPOSPLUS, /* 69 */ - OP_NOTPOSQUERY, /* 70 */ - OP_NOTPOSUPTO, /* 71 */ - - /* Negated repeated character, caseless; must follow the caseful ones */ - - OP_NOTSTARI, /* 72 */ - OP_NOTMINSTARI, /* 73 */ - OP_NOTPLUSI, /* 74 */ - OP_NOTMINPLUSI, /* 75 */ - OP_NOTQUERYI, /* 76 */ - OP_NOTMINQUERYI, /* 77 */ - - OP_NOTUPTOI, /* 78 From 0 to n matches, caseless */ - OP_NOTMINUPTOI, /* 79 */ - OP_NOTEXACTI, /* 80 Exactly n matches */ - - OP_NOTPOSSTARI, /* 81 Possessified versions, caseless */ - OP_NOTPOSPLUSI, /* 82 */ - OP_NOTPOSQUERYI, /* 83 */ - OP_NOTPOSUPTOI, /* 84 */ - - /* Character types */ - - OP_TYPESTAR, /* 85 The maximizing and minimizing versions of */ - OP_TYPEMINSTAR, /* 86 these six opcodes must come in pairs, with */ - OP_TYPEPLUS, /* 87 the minimizing one second. These codes must */ - OP_TYPEMINPLUS, /* 88 be in exactly the same order as those above. */ - OP_TYPEQUERY, /* 89 */ - OP_TYPEMINQUERY, /* 90 */ - - OP_TYPEUPTO, /* 91 From 0 to n matches */ - OP_TYPEMINUPTO, /* 92 */ - OP_TYPEEXACT, /* 93 Exactly n matches */ - - OP_TYPEPOSSTAR, /* 94 Possessified versions */ - OP_TYPEPOSPLUS, /* 95 */ - OP_TYPEPOSQUERY, /* 96 */ - OP_TYPEPOSUPTO, /* 97 */ - - /* These are used for character classes and back references; only the - first six are the same as the sets above. */ - - OP_CRSTAR, /* 98 The maximizing and minimizing versions of */ - OP_CRMINSTAR, /* 99 all these opcodes must come in pairs, with */ - OP_CRPLUS, /* 100 the minimizing one second. These codes must */ - OP_CRMINPLUS, /* 101 be in exactly the same order as those above. */ - OP_CRQUERY, /* 102 */ - OP_CRMINQUERY, /* 103 */ - - OP_CRRANGE, /* 104 These are different to the three sets above. */ - OP_CRMINRANGE, /* 105 */ - - OP_CRPOSSTAR, /* 106 Possessified versions */ - OP_CRPOSPLUS, /* 107 */ - OP_CRPOSQUERY, /* 108 */ - OP_CRPOSRANGE, /* 109 */ - - /* End of quantifier opcodes */ - - OP_CLASS, /* 110 Match a character class, chars < 256 only */ - OP_NCLASS, /* 111 Same, but the bitmap was created from a negative - class - the difference is relevant only when a - character > 255 is encountered. */ - OP_XCLASS, /* 112 Extended class for handling > 255 chars within the - class. This does both positive and negative. */ - OP_REF, /* 113 Match a back reference, casefully */ - OP_REFI, /* 114 Match a back reference, caselessly */ - OP_DNREF, /* 115 Match a duplicate name backref, casefully */ - OP_DNREFI, /* 116 Match a duplicate name backref, caselessly */ - OP_RECURSE, /* 117 Match a numbered subpattern (possibly recursive) */ - OP_CALLOUT, /* 118 Call out to external function if provided */ - - OP_ALT, /* 119 Start of alternation */ - OP_KET, /* 120 End of group that doesn't have an unbounded repeat */ - OP_KETRMAX, /* 121 These two must remain together and in this */ - OP_KETRMIN, /* 122 order. They are for groups the repeat for ever. */ - OP_KETRPOS, /* 123 Possessive unlimited repeat. */ - - /* The assertions must come before BRA, CBRA, ONCE, and COND, and the four - asserts must remain in order. */ - - OP_REVERSE, /* 124 Move pointer back - used in lookbehind assertions */ - OP_ASSERT, /* 125 Positive lookahead */ - OP_ASSERT_NOT, /* 126 Negative lookahead */ - OP_ASSERTBACK, /* 127 Positive lookbehind */ - OP_ASSERTBACK_NOT, /* 128 Negative lookbehind */ - - /* ONCE, ONCE_NC, BRA, BRAPOS, CBRA, CBRAPOS, and COND must come immediately - after the assertions, with ONCE first, as there's a test for >= ONCE for a - subpattern that isn't an assertion. The POS versions must immediately follow - the non-POS versions in each case. */ - - OP_ONCE, /* 129 Atomic group, contains captures */ - OP_ONCE_NC, /* 130 Atomic group containing no captures */ - OP_BRA, /* 131 Start of non-capturing bracket */ - OP_BRAPOS, /* 132 Ditto, with unlimited, possessive repeat */ - OP_CBRA, /* 133 Start of capturing bracket */ - OP_CBRAPOS, /* 134 Ditto, with unlimited, possessive repeat */ - OP_COND, /* 135 Conditional group */ - - /* These five must follow the previous five, in the same order. There's a - check for >= SBRA to distinguish the two sets. */ - - OP_SBRA, /* 136 Start of non-capturing bracket, check empty */ - OP_SBRAPOS, /* 137 Ditto, with unlimited, possessive repeat */ - OP_SCBRA, /* 138 Start of capturing bracket, check empty */ - OP_SCBRAPOS, /* 139 Ditto, with unlimited, possessive repeat */ - OP_SCOND, /* 140 Conditional group, check empty */ - - /* The next two pairs must (respectively) be kept together. */ - - OP_CREF, /* 141 Used to hold a capture number as condition */ - OP_DNCREF, /* 142 Used to point to duplicate names as a condition */ - OP_RREF, /* 143 Used to hold a recursion number as condition */ - OP_DNRREF, /* 144 Used to point to duplicate names as a condition */ - OP_DEF, /* 145 The DEFINE condition */ - - OP_BRAZERO, /* 146 These two must remain together and in this */ - OP_BRAMINZERO, /* 147 order. */ - OP_BRAPOSZERO, /* 148 */ - - /* These are backtracking control verbs */ - - OP_MARK, /* 149 always has an argument */ - OP_PRUNE, /* 150 */ - OP_PRUNE_ARG, /* 151 same, but with argument */ - OP_SKIP, /* 152 */ - OP_SKIP_ARG, /* 153 same, but with argument */ - OP_THEN, /* 154 */ - OP_THEN_ARG, /* 155 same, but with argument */ - OP_COMMIT, /* 156 */ - - /* These are forced failure and success verbs */ - - OP_FAIL, /* 157 */ - OP_ACCEPT, /* 158 */ - OP_ASSERT_ACCEPT, /* 159 Used inside assertions */ - OP_CLOSE, /* 160 Used before OP_ACCEPT to close open captures */ - - /* This is used to skip a subpattern with a {0} quantifier */ - - OP_SKIPZERO, /* 161 */ - - /* This is not an opcode, but is used to check that tables indexed by opcode - are the correct length, in order to catch updating errors - there have been - some in the past. */ - - OP_TABLE_LENGTH -}; - -/* *** NOTE NOTE NOTE *** Whenever the list above is updated, the two macro -definitions that follow must also be updated to match. There are also tables -called "opcode_possessify" in pcre_compile.c and "coptable" and "poptable" in -pcre_dfa_exec.c that must be updated. */ - - -/* This macro defines textual names for all the opcodes. These are used only -for debugging, and some of them are only partial names. The macro is referenced -only in pcre_printint.c, which fills out the full names in many cases (and in -some cases doesn't actually use these names at all). */ - -#define OP_NAME_LIST \ - "End", "\\A", "\\G", "\\K", "\\B", "\\b", "\\D", "\\d", \ - "\\S", "\\s", "\\W", "\\w", "Any", "AllAny", "Anybyte", \ - "notprop", "prop", "\\R", "\\H", "\\h", "\\V", "\\v", \ - "extuni", "\\Z", "\\z", \ - "$", "$", "^", "^", "char", "chari", "not", "noti", \ - "*", "*?", "+", "+?", "?", "??", \ - "{", "{", "{", \ - "*+","++", "?+", "{", \ - "*", "*?", "+", "+?", "?", "??", \ - "{", "{", "{", \ - "*+","++", "?+", "{", \ - "*", "*?", "+", "+?", "?", "??", \ - "{", "{", "{", \ - "*+","++", "?+", "{", \ - "*", "*?", "+", "+?", "?", "??", \ - "{", "{", "{", \ - "*+","++", "?+", "{", \ - "*", "*?", "+", "+?", "?", "??", "{", "{", "{", \ - "*+","++", "?+", "{", \ - "*", "*?", "+", "+?", "?", "??", "{", "{", \ - "*+","++", "?+", "{", \ - "class", "nclass", "xclass", "Ref", "Refi", "DnRef", "DnRefi", \ - "Recurse", "Callout", \ - "Alt", "Ket", "KetRmax", "KetRmin", "KetRpos", \ - "Reverse", "Assert", "Assert not", "AssertB", "AssertB not", \ - "Once", "Once_NC", \ - "Bra", "BraPos", "CBra", "CBraPos", \ - "Cond", \ - "SBra", "SBraPos", "SCBra", "SCBraPos", \ - "SCond", \ - "Cond ref", "Cond dnref", "Cond rec", "Cond dnrec", "Cond def", \ - "Brazero", "Braminzero", "Braposzero", \ - "*MARK", "*PRUNE", "*PRUNE", "*SKIP", "*SKIP", \ - "*THEN", "*THEN", "*COMMIT", "*FAIL", \ - "*ACCEPT", "*ASSERT_ACCEPT", \ - "Close", "Skip zero" - - -/* This macro defines the length of fixed length operations in the compiled -regex. The lengths are used when searching for specific things, and also in the -debugging printing of a compiled regex. We use a macro so that it can be -defined close to the definitions of the opcodes themselves. - -As things have been extended, some of these are no longer fixed lenths, but are -minima instead. For example, the length of a single-character repeat may vary -in UTF-8 mode. The code that uses this table must know about such things. */ - -#define OP_LENGTHS \ - 1, /* End */ \ - 1, 1, 1, 1, 1, /* \A, \G, \K, \B, \b */ \ - 1, 1, 1, 1, 1, 1, /* \D, \d, \S, \s, \W, \w */ \ - 1, 1, 1, /* Any, AllAny, Anybyte */ \ - 3, 3, /* \P, \p */ \ - 1, 1, 1, 1, 1, /* \R, \H, \h, \V, \v */ \ - 1, /* \X */ \ - 1, 1, 1, 1, 1, 1, /* \Z, \z, $, $M ^, ^M */ \ - 2, /* Char - the minimum length */ \ - 2, /* Chari - the minimum length */ \ - 2, /* not */ \ - 2, /* noti */ \ - /* Positive single-char repeats ** These are */ \ - 2, 2, 2, 2, 2, 2, /* *, *?, +, +?, ?, ?? ** minima in */ \ - 2+IMM2_SIZE, 2+IMM2_SIZE, /* upto, minupto ** mode */ \ - 2+IMM2_SIZE, /* exact */ \ - 2, 2, 2, 2+IMM2_SIZE, /* *+, ++, ?+, upto+ */ \ - 2, 2, 2, 2, 2, 2, /* *I, *?I, +I, +?I, ?I, ??I ** UTF-8 */ \ - 2+IMM2_SIZE, 2+IMM2_SIZE, /* upto I, minupto I */ \ - 2+IMM2_SIZE, /* exact I */ \ - 2, 2, 2, 2+IMM2_SIZE, /* *+I, ++I, ?+I, upto+I */ \ - /* Negative single-char repeats - only for chars < 256 */ \ - 2, 2, 2, 2, 2, 2, /* NOT *, *?, +, +?, ?, ?? */ \ - 2+IMM2_SIZE, 2+IMM2_SIZE, /* NOT upto, minupto */ \ - 2+IMM2_SIZE, /* NOT exact */ \ - 2, 2, 2, 2+IMM2_SIZE, /* Possessive NOT *, +, ?, upto */ \ - 2, 2, 2, 2, 2, 2, /* NOT *I, *?I, +I, +?I, ?I, ??I */ \ - 2+IMM2_SIZE, 2+IMM2_SIZE, /* NOT upto I, minupto I */ \ - 2+IMM2_SIZE, /* NOT exact I */ \ - 2, 2, 2, 2+IMM2_SIZE, /* Possessive NOT *I, +I, ?I, upto I */ \ - /* Positive type repeats */ \ - 2, 2, 2, 2, 2, 2, /* Type *, *?, +, +?, ?, ?? */ \ - 2+IMM2_SIZE, 2+IMM2_SIZE, /* Type upto, minupto */ \ - 2+IMM2_SIZE, /* Type exact */ \ - 2, 2, 2, 2+IMM2_SIZE, /* Possessive *+, ++, ?+, upto+ */ \ - /* Character class & ref repeats */ \ - 1, 1, 1, 1, 1, 1, /* *, *?, +, +?, ?, ?? */ \ - 1+2*IMM2_SIZE, 1+2*IMM2_SIZE, /* CRRANGE, CRMINRANGE */ \ - 1, 1, 1, 1+2*IMM2_SIZE, /* Possessive *+, ++, ?+, CRPOSRANGE */ \ - 1+(32/sizeof(pcre_uchar)), /* CLASS */ \ - 1+(32/sizeof(pcre_uchar)), /* NCLASS */ \ - 0, /* XCLASS - variable length */ \ - 1+IMM2_SIZE, /* REF */ \ - 1+IMM2_SIZE, /* REFI */ \ - 1+2*IMM2_SIZE, /* DNREF */ \ - 1+2*IMM2_SIZE, /* DNREFI */ \ - 1+LINK_SIZE, /* RECURSE */ \ - 2+2*LINK_SIZE, /* CALLOUT */ \ - 1+LINK_SIZE, /* Alt */ \ - 1+LINK_SIZE, /* Ket */ \ - 1+LINK_SIZE, /* KetRmax */ \ - 1+LINK_SIZE, /* KetRmin */ \ - 1+LINK_SIZE, /* KetRpos */ \ - 1+LINK_SIZE, /* Reverse */ \ - 1+LINK_SIZE, /* Assert */ \ - 1+LINK_SIZE, /* Assert not */ \ - 1+LINK_SIZE, /* Assert behind */ \ - 1+LINK_SIZE, /* Assert behind not */ \ - 1+LINK_SIZE, /* ONCE */ \ - 1+LINK_SIZE, /* ONCE_NC */ \ - 1+LINK_SIZE, /* BRA */ \ - 1+LINK_SIZE, /* BRAPOS */ \ - 1+LINK_SIZE+IMM2_SIZE, /* CBRA */ \ - 1+LINK_SIZE+IMM2_SIZE, /* CBRAPOS */ \ - 1+LINK_SIZE, /* COND */ \ - 1+LINK_SIZE, /* SBRA */ \ - 1+LINK_SIZE, /* SBRAPOS */ \ - 1+LINK_SIZE+IMM2_SIZE, /* SCBRA */ \ - 1+LINK_SIZE+IMM2_SIZE, /* SCBRAPOS */ \ - 1+LINK_SIZE, /* SCOND */ \ - 1+IMM2_SIZE, 1+2*IMM2_SIZE, /* CREF, DNCREF */ \ - 1+IMM2_SIZE, 1+2*IMM2_SIZE, /* RREF, DNRREF */ \ - 1, /* DEF */ \ - 1, 1, 1, /* BRAZERO, BRAMINZERO, BRAPOSZERO */ \ - 3, 1, 3, /* MARK, PRUNE, PRUNE_ARG */ \ - 1, 3, /* SKIP, SKIP_ARG */ \ - 1, 3, /* THEN, THEN_ARG */ \ - 1, 1, 1, 1, /* COMMIT, FAIL, ACCEPT, ASSERT_ACCEPT */ \ - 1+IMM2_SIZE, 1 /* CLOSE, SKIPZERO */ - -/* A magic value for OP_RREF to indicate the "any recursion" condition. */ - -#define RREF_ANY 0xffff - -/* Compile time error code numbers. They are given names so that they can more -easily be tracked. When a new number is added, the table called eint in -pcreposix.c must be updated. */ - -enum { ERR0, ERR1, ERR2, ERR3, ERR4, ERR5, ERR6, ERR7, ERR8, ERR9, - ERR10, ERR11, ERR12, ERR13, ERR14, ERR15, ERR16, ERR17, ERR18, ERR19, - ERR20, ERR21, ERR22, ERR23, ERR24, ERR25, ERR26, ERR27, ERR28, ERR29, - ERR30, ERR31, ERR32, ERR33, ERR34, ERR35, ERR36, ERR37, ERR38, ERR39, - ERR40, ERR41, ERR42, ERR43, ERR44, ERR45, ERR46, ERR47, ERR48, ERR49, - ERR50, ERR51, ERR52, ERR53, ERR54, ERR55, ERR56, ERR57, ERR58, ERR59, - ERR60, ERR61, ERR62, ERR63, ERR64, ERR65, ERR66, ERR67, ERR68, ERR69, - ERR70, ERR71, ERR72, ERR73, ERR74, ERR75, ERR76, ERR77, ERR78, ERR79, - ERR80, ERR81, ERR82, ERR83, ERR84, ERR85, ERR86, ERRCOUNT }; - -/* JIT compiling modes. The function list is indexed by them. */ - -enum { JIT_COMPILE, JIT_PARTIAL_SOFT_COMPILE, JIT_PARTIAL_HARD_COMPILE, - JIT_NUMBER_OF_COMPILE_MODES }; - -/* The real format of the start of the pcre block; the index of names and the -code vector run on as long as necessary after the end. We store an explicit -offset to the name table so that if a regex is compiled on one host, saved, and -then run on another where the size of pointers is different, all might still -be well. - -The size of the structure must be a multiple of 8 bytes. For the case of -compiled-on-4 and run-on-8, we include an extra pointer that is always NULL so -that there are an even number of pointers which therefore are a multiple of 8 -bytes. - -It is necessary to fork the struct for the 32 bit library, since it needs to -use pcre_uint32 for first_char and req_char. We can't put an ifdef inside the -typedef because pcretest needs access to the struct of the 8-, 16- and 32-bit -variants. - -*** WARNING *** -When new fields are added to these structures, remember to adjust the code in -pcre_byte_order.c that is concerned with swapping the byte order of the fields -when a compiled regex is reloaded on a host with different endianness. -*** WARNING *** -There is also similar byte-flipping code in pcretest.c, which is used for -testing the byte-flipping features. It must also be kept in step. -*** WARNING *** -*/ - -typedef struct real_pcre8_or_16 { - pcre_uint32 magic_number; - pcre_uint32 size; /* Total that was malloced */ - pcre_uint32 options; /* Public options */ - pcre_uint32 flags; /* Private flags */ - pcre_uint32 limit_match; /* Limit set from regex */ - pcre_uint32 limit_recursion; /* Limit set from regex */ - pcre_uint16 first_char; /* Starting character */ - pcre_uint16 req_char; /* This character must be seen */ - pcre_uint16 max_lookbehind; /* Longest lookbehind (characters) */ - pcre_uint16 top_bracket; /* Highest numbered group */ - pcre_uint16 top_backref; /* Highest numbered back reference */ - pcre_uint16 name_table_offset; /* Offset to name table that follows */ - pcre_uint16 name_entry_size; /* Size of any name items */ - pcre_uint16 name_count; /* Number of name items */ - pcre_uint16 ref_count; /* Reference count */ - pcre_uint16 dummy1; /* To ensure size is a multiple of 8 */ - pcre_uint16 dummy2; /* To ensure size is a multiple of 8 */ - pcre_uint16 dummy3; /* To ensure size is a multiple of 8 */ - const pcre_uint8 *tables; /* Pointer to tables or NULL for std */ - void *nullpad; /* NULL padding */ -} real_pcre8_or_16; - -typedef struct real_pcre8_or_16 real_pcre; -typedef struct real_pcre8_or_16 real_pcre16; - -typedef struct real_pcre32 { - pcre_uint32 magic_number; - pcre_uint32 size; /* Total that was malloced */ - pcre_uint32 options; /* Public options */ - pcre_uint32 flags; /* Private flags */ - pcre_uint32 limit_match; /* Limit set from regex */ - pcre_uint32 limit_recursion; /* Limit set from regex */ - pcre_uint32 first_char; /* Starting character */ - pcre_uint32 req_char; /* This character must be seen */ - pcre_uint16 max_lookbehind; /* Longest lookbehind (characters) */ - pcre_uint16 top_bracket; /* Highest numbered group */ - pcre_uint16 top_backref; /* Highest numbered back reference */ - pcre_uint16 name_table_offset; /* Offset to name table that follows */ - pcre_uint16 name_entry_size; /* Size of any name items */ - pcre_uint16 name_count; /* Number of name items */ - pcre_uint16 ref_count; /* Reference count */ - pcre_uint16 dummy; /* To ensure size is a multiple of 8 */ - const pcre_uint8 *tables; /* Pointer to tables or NULL for std */ - void *nullpad; /* NULL padding */ -} real_pcre32; - -#if defined COMPILE_PCRE8 -#define REAL_PCRE real_pcre -#elif defined COMPILE_PCRE16 -#define REAL_PCRE real_pcre16 -#elif defined COMPILE_PCRE32 -#define REAL_PCRE real_pcre32 -#endif - -/* Assert that the size of REAL_PCRE is divisible by 8 */ -typedef int __assert_real_pcre_size_divisible_8[(sizeof(REAL_PCRE) % 8) == 0 ? 1 : -1]; - -/* Needed in pcretest to access some fields in the real_pcre* structures - * directly. They're unified for 8/16/32 bits since the structs only differ - * after these fields; if that ever changes, need to fork those defines into - * 8/16 and 32 bit versions. */ -#define REAL_PCRE_MAGIC(re) (((REAL_PCRE*)re)->magic_number) -#define REAL_PCRE_SIZE(re) (((REAL_PCRE*)re)->size) -#define REAL_PCRE_OPTIONS(re) (((REAL_PCRE*)re)->options) -#define REAL_PCRE_FLAGS(re) (((REAL_PCRE*)re)->flags) - -/* The format of the block used to store data from pcre_study(). The same -remark (see NOTE above) about extending this structure applies. */ - -typedef struct pcre_study_data { - pcre_uint32 size; /* Total that was malloced */ - pcre_uint32 flags; /* Private flags */ - pcre_uint8 start_bits[32]; /* Starting char bits */ - pcre_uint32 minlength; /* Minimum subject length */ -} pcre_study_data; - -/* Structure for building a chain of open capturing subpatterns during -compiling, so that instructions to close them can be compiled when (*ACCEPT) is -encountered. This is also used to identify subpatterns that contain recursive -back references to themselves, so that they can be made atomic. */ - -typedef struct open_capitem { - struct open_capitem *next; /* Chain link */ - pcre_uint16 number; /* Capture number */ - pcre_uint16 flag; /* Set TRUE if recursive back ref */ -} open_capitem; - -/* Structure for building a list of named groups during the first pass of -compiling. */ - -typedef struct named_group { - const pcre_uchar *name; /* Points to the name in the pattern */ - int length; /* Length of the name */ - pcre_uint32 number; /* Group number */ -} named_group; - -/* Structure for passing "static" information around between the functions -doing the compiling, so that they are thread-safe. */ - -typedef struct compile_data { - const pcre_uint8 *lcc; /* Points to lower casing table */ - const pcre_uint8 *fcc; /* Points to case-flipping table */ - const pcre_uint8 *cbits; /* Points to character type table */ - const pcre_uint8 *ctypes; /* Points to table of type maps */ - const pcre_uchar *start_workspace;/* The start of working space */ - const pcre_uchar *start_code; /* The start of the compiled code */ - const pcre_uchar *start_pattern; /* The start of the pattern */ - const pcre_uchar *end_pattern; /* The end of the pattern */ - pcre_uchar *hwm; /* High watermark of workspace */ - open_capitem *open_caps; /* Chain of open capture items */ - named_group *named_groups; /* Points to vector in pre-compile */ - pcre_uchar *name_table; /* The name/number table */ - int names_found; /* Number of entries so far */ - int name_entry_size; /* Size of each entry */ - int named_group_list_size; /* Number of entries in the list */ - int workspace_size; /* Size of workspace */ - unsigned int bracount; /* Count of capturing parens as we compile */ - int final_bracount; /* Saved value after first pass */ - int max_lookbehind; /* Maximum lookbehind (characters) */ - int top_backref; /* Maximum back reference */ - unsigned int backref_map; /* Bitmap of low back refs */ - unsigned int namedrefcount; /* Number of backreferences by name */ - int parens_depth; /* Depth of nested parentheses */ - int assert_depth; /* Depth of nested assertions */ - pcre_uint32 external_options; /* External (initial) options */ - pcre_uint32 external_flags; /* External flag bits to be set */ - int req_varyopt; /* "After variable item" flag for reqbyte */ - BOOL had_accept; /* (*ACCEPT) encountered */ - BOOL had_pruneorskip; /* (*PRUNE) or (*SKIP) encountered */ - BOOL check_lookbehind; /* Lookbehinds need later checking */ - BOOL dupnames; /* Duplicate names exist */ - BOOL dupgroups; /* Duplicate groups exist: (?| found */ - BOOL iscondassert; /* Next assert is a condition */ - int nltype; /* Newline type */ - int nllen; /* Newline string length */ - pcre_uchar nl[4]; /* Newline string when fixed length */ -} compile_data; - -/* Structure for maintaining a chain of pointers to the currently incomplete -branches, for testing for left recursion while compiling. */ - -typedef struct branch_chain { - struct branch_chain *outer; - pcre_uchar *current_branch; -} branch_chain; - -/* Structure for mutual recursion detection. */ - -typedef struct recurse_check { - struct recurse_check *prev; - const pcre_uchar *group; -} recurse_check; - -/* Structure for items in a linked list that represents an explicit recursive -call within the pattern; used by pcre_exec(). */ - -typedef struct recursion_info { - struct recursion_info *prevrec; /* Previous recursion record (or NULL) */ - unsigned int group_num; /* Number of group that was called */ - int *offset_save; /* Pointer to start of saved offsets */ - int saved_max; /* Number of saved offsets */ - int saved_capture_last; /* Last capture number */ - PCRE_PUCHAR subject_position; /* Position at start of recursion */ -} recursion_info; - -/* A similar structure for pcre_dfa_exec(). */ - -typedef struct dfa_recursion_info { - struct dfa_recursion_info *prevrec; - int group_num; - PCRE_PUCHAR subject_position; -} dfa_recursion_info; - -/* Structure for building a chain of data for holding the values of the subject -pointer at the start of each subpattern, so as to detect when an empty string -has been matched by a subpattern - to break infinite loops; used by -pcre_exec(). */ - -typedef struct eptrblock { - struct eptrblock *epb_prev; - PCRE_PUCHAR epb_saved_eptr; -} eptrblock; - - -/* Structure for passing "static" information around between the functions -doing traditional NFA matching, so that they are thread-safe. */ - -typedef struct match_data { - unsigned long int match_call_count; /* As it says */ - unsigned long int match_limit; /* As it says */ - unsigned long int match_limit_recursion; /* As it says */ - int *offset_vector; /* Offset vector */ - int offset_end; /* One past the end */ - int offset_max; /* The maximum usable for return data */ - int nltype; /* Newline type */ - int nllen; /* Newline string length */ - int name_count; /* Number of names in name table */ - int name_entry_size; /* Size of entry in names table */ - unsigned int skip_arg_count; /* For counting SKIP_ARGs */ - unsigned int ignore_skip_arg; /* For re-run when SKIP arg name not found */ - pcre_uchar *name_table; /* Table of names */ - pcre_uchar nl[4]; /* Newline string when fixed */ - const pcre_uint8 *lcc; /* Points to lower casing table */ - const pcre_uint8 *fcc; /* Points to case-flipping table */ - const pcre_uint8 *ctypes; /* Points to table of type maps */ - BOOL notbol; /* NOTBOL flag */ - BOOL noteol; /* NOTEOL flag */ - BOOL utf; /* UTF-8 / UTF-16 flag */ - BOOL jscript_compat; /* JAVASCRIPT_COMPAT flag */ - BOOL use_ucp; /* PCRE_UCP flag */ - BOOL endonly; /* Dollar not before final \n */ - BOOL notempty; /* Empty string match not wanted */ - BOOL notempty_atstart; /* Empty string match at start not wanted */ - BOOL hitend; /* Hit the end of the subject at some point */ - BOOL bsr_anycrlf; /* \R is just any CRLF, not full Unicode */ - BOOL hasthen; /* Pattern contains (*THEN) */ - const pcre_uchar *start_code; /* For use when recursing */ - PCRE_PUCHAR start_subject; /* Start of the subject string */ - PCRE_PUCHAR end_subject; /* End of the subject string */ - PCRE_PUCHAR start_match_ptr; /* Start of matched string */ - PCRE_PUCHAR end_match_ptr; /* Subject position at end match */ - PCRE_PUCHAR start_used_ptr; /* Earliest consulted character */ - int partial; /* PARTIAL options */ - int end_offset_top; /* Highwater mark at end of match */ - pcre_int32 capture_last; /* Most recent capture number + overflow flag */ - int start_offset; /* The start offset value */ - int match_function_type; /* Set for certain special calls of MATCH() */ - eptrblock *eptrchain; /* Chain of eptrblocks for tail recursions */ - int eptrn; /* Next free eptrblock */ - recursion_info *recursive; /* Linked list of recursion data */ - void *callout_data; /* To pass back to callouts */ - const pcre_uchar *mark; /* Mark pointer to pass back on success */ - const pcre_uchar *nomatch_mark;/* Mark pointer to pass back on failure */ - const pcre_uchar *once_target; /* Where to back up to for atomic groups */ -#ifdef NO_RECURSE - void *match_frames_base; /* For remembering malloc'd frames */ -#endif -} match_data; - -/* A similar structure is used for the same purpose by the DFA matching -functions. */ - -typedef struct dfa_match_data { - const pcre_uchar *start_code; /* Start of the compiled pattern */ - const pcre_uchar *start_subject ; /* Start of the subject string */ - const pcre_uchar *end_subject; /* End of subject string */ - const pcre_uchar *start_used_ptr; /* Earliest consulted character */ - const pcre_uint8 *tables; /* Character tables */ - int start_offset; /* The start offset value */ - int moptions; /* Match options */ - int poptions; /* Pattern options */ - int nltype; /* Newline type */ - int nllen; /* Newline string length */ - pcre_uchar nl[4]; /* Newline string when fixed */ - void *callout_data; /* To pass back to callouts */ - dfa_recursion_info *recursive; /* Linked list of recursion data */ -} dfa_match_data; - -/* Bit definitions for entries in the pcre_ctypes table. */ - -#define ctype_space 0x01 -#define ctype_letter 0x02 -#define ctype_digit 0x04 -#define ctype_xdigit 0x08 -#define ctype_word 0x10 /* alphanumeric or '_' */ -#define ctype_meta 0x80 /* regexp meta char or zero (end pattern) */ - -/* Offsets for the bitmap tables in pcre_cbits. Each table contains a set -of bits for a class map. Some classes are built by combining these tables. */ - -#define cbit_space 0 /* [:space:] or \s */ -#define cbit_xdigit 32 /* [:xdigit:] */ -#define cbit_digit 64 /* [:digit:] or \d */ -#define cbit_upper 96 /* [:upper:] */ -#define cbit_lower 128 /* [:lower:] */ -#define cbit_word 160 /* [:word:] or \w */ -#define cbit_graph 192 /* [:graph:] */ -#define cbit_print 224 /* [:print:] */ -#define cbit_punct 256 /* [:punct:] */ -#define cbit_cntrl 288 /* [:cntrl:] */ -#define cbit_length 320 /* Length of the cbits table */ - -/* Offsets of the various tables from the base tables pointer, and -total length. */ - -#define lcc_offset 0 -#define fcc_offset 256 -#define cbits_offset 512 -#define ctypes_offset (cbits_offset + cbit_length) -#define tables_length (ctypes_offset + 256) - -/* Internal function and data prefixes. */ - -#if defined COMPILE_PCRE8 -#ifndef PUBL -#define PUBL(name) pcre_##name -#endif -#ifndef PRIV -#define PRIV(name) _pcre_##name -#endif -#elif defined COMPILE_PCRE16 -#ifndef PUBL -#define PUBL(name) pcre16_##name -#endif -#ifndef PRIV -#define PRIV(name) _pcre16_##name -#endif -#elif defined COMPILE_PCRE32 -#ifndef PUBL -#define PUBL(name) pcre32_##name -#endif -#ifndef PRIV -#define PRIV(name) _pcre32_##name -#endif -#else -#error Unsupported compiling mode -#endif /* COMPILE_PCRE[8|16|32] */ - -/* Layout of the UCP type table that translates property names into types and -codes. Each entry used to point directly to a name, but to reduce the number of -relocations in shared libraries, it now has an offset into a single string -instead. */ - -typedef struct { - pcre_uint16 name_offset; - pcre_uint16 type; - pcre_uint16 value; -} ucp_type_table; - - -/* Internal shared data tables. These are tables that are used by more than one -of the exported public functions. They have to be "external" in the C sense, -but are not part of the PCRE public API. The data for these tables is in the -pcre_tables.c module. */ - -#ifdef COMPILE_PCRE8 -extern const int PRIV(utf8_table1)[]; -extern const int PRIV(utf8_table1_size); -extern const int PRIV(utf8_table2)[]; -extern const int PRIV(utf8_table3)[]; -extern const pcre_uint8 PRIV(utf8_table4)[]; -#endif /* COMPILE_PCRE8 */ - -extern const char PRIV(utt_names)[]; -extern const ucp_type_table PRIV(utt)[]; -extern const int PRIV(utt_size); - -extern const pcre_uint8 PRIV(OP_lengths)[]; -extern const pcre_uint8 PRIV(default_tables)[]; - -extern const pcre_uint32 PRIV(hspace_list)[]; -extern const pcre_uint32 PRIV(vspace_list)[]; - - -/* Internal shared functions. These are functions that are used by more than -one of the exported public functions. They have to be "external" in the C -sense, but are not part of the PCRE public API. */ - -/* String comparison functions. */ -#if defined COMPILE_PCRE8 - -#define STRCMP_UC_UC(str1, str2) \ - strcmp((char *)(str1), (char *)(str2)) -#define STRCMP_UC_C8(str1, str2) \ - strcmp((char *)(str1), (str2)) -#define STRNCMP_UC_UC(str1, str2, num) \ - strncmp((char *)(str1), (char *)(str2), (num)) -#define STRNCMP_UC_C8(str1, str2, num) \ - strncmp((char *)(str1), (str2), (num)) -#define STRLEN_UC(str) strlen((const char *)str) - -#elif defined COMPILE_PCRE16 || defined COMPILE_PCRE32 - -extern int PRIV(strcmp_uc_uc)(const pcre_uchar *, - const pcre_uchar *); -extern int PRIV(strcmp_uc_c8)(const pcre_uchar *, - const char *); -extern int PRIV(strncmp_uc_uc)(const pcre_uchar *, - const pcre_uchar *, unsigned int num); -extern int PRIV(strncmp_uc_c8)(const pcre_uchar *, - const char *, unsigned int num); -extern unsigned int PRIV(strlen_uc)(const pcre_uchar *str); - -#define STRCMP_UC_UC(str1, str2) \ - PRIV(strcmp_uc_uc)((str1), (str2)) -#define STRCMP_UC_C8(str1, str2) \ - PRIV(strcmp_uc_c8)((str1), (str2)) -#define STRNCMP_UC_UC(str1, str2, num) \ - PRIV(strncmp_uc_uc)((str1), (str2), (num)) -#define STRNCMP_UC_C8(str1, str2, num) \ - PRIV(strncmp_uc_c8)((str1), (str2), (num)) -#define STRLEN_UC(str) PRIV(strlen_uc)(str) - -#endif /* COMPILE_PCRE[8|16|32] */ - -#if defined COMPILE_PCRE8 || defined COMPILE_PCRE16 - -#define STRCMP_UC_UC_TEST(str1, str2) STRCMP_UC_UC(str1, str2) -#define STRCMP_UC_C8_TEST(str1, str2) STRCMP_UC_C8(str1, str2) - -#elif defined COMPILE_PCRE32 - -extern int PRIV(strcmp_uc_uc_utf)(const pcre_uchar *, - const pcre_uchar *); -extern int PRIV(strcmp_uc_c8_utf)(const pcre_uchar *, - const char *); - -#define STRCMP_UC_UC_TEST(str1, str2) \ - (utf ? PRIV(strcmp_uc_uc_utf)((str1), (str2)) : PRIV(strcmp_uc_uc)((str1), (str2))) -#define STRCMP_UC_C8_TEST(str1, str2) \ - (utf ? PRIV(strcmp_uc_c8_utf)((str1), (str2)) : PRIV(strcmp_uc_c8)((str1), (str2))) - -#endif /* COMPILE_PCRE[8|16|32] */ - -extern const pcre_uchar *PRIV(find_bracket)(const pcre_uchar *, BOOL, int); -extern BOOL PRIV(is_newline)(PCRE_PUCHAR, int, PCRE_PUCHAR, - int *, BOOL); -extern unsigned int PRIV(ord2utf)(pcre_uint32, pcre_uchar *); -extern int PRIV(valid_utf)(PCRE_PUCHAR, int, int *); -extern BOOL PRIV(was_newline)(PCRE_PUCHAR, int, PCRE_PUCHAR, - int *, BOOL); -extern BOOL PRIV(xclass)(pcre_uint32, const pcre_uchar *, BOOL); - -#ifdef SUPPORT_JIT -extern void PRIV(jit_compile)(const REAL_PCRE *, - PUBL(extra) *, int); -extern int PRIV(jit_exec)(const PUBL(extra) *, - const pcre_uchar *, int, int, int, int *, int); -extern void PRIV(jit_free)(void *); -extern int PRIV(jit_get_size)(void *); -extern const char* PRIV(jit_get_target)(void); -#endif - -/* Unicode character database (UCD) */ - -typedef struct { - pcre_uint8 script; /* ucp_Arabic, etc. */ - pcre_uint8 chartype; /* ucp_Cc, etc. (general categories) */ - pcre_uint8 gbprop; /* ucp_gbControl, etc. (grapheme break property) */ - pcre_uint8 caseset; /* offset to multichar other cases or zero */ - pcre_int32 other_case; /* offset to other case, or zero if none */ -} ucd_record; - -extern const pcre_uint32 PRIV(ucd_caseless_sets)[]; -extern const ucd_record PRIV(ucd_records)[]; -extern const pcre_uint8 PRIV(ucd_stage1)[]; -extern const pcre_uint16 PRIV(ucd_stage2)[]; -extern const pcre_uint32 PRIV(ucp_gentype)[]; -extern const pcre_uint32 PRIV(ucp_gbtable)[]; -#ifdef SUPPORT_JIT -extern const int PRIV(ucp_typerange)[]; -#endif - -#ifdef SUPPORT_UCP -/* UCD access macros */ - -#define UCD_BLOCK_SIZE 128 -#define GET_UCD(ch) (PRIV(ucd_records) + \ - PRIV(ucd_stage2)[PRIV(ucd_stage1)[(int)(ch) / UCD_BLOCK_SIZE] * \ - UCD_BLOCK_SIZE + (int)(ch) % UCD_BLOCK_SIZE]) - -#define UCD_CHARTYPE(ch) GET_UCD(ch)->chartype -#define UCD_SCRIPT(ch) GET_UCD(ch)->script -#define UCD_CATEGORY(ch) PRIV(ucp_gentype)[UCD_CHARTYPE(ch)] -#define UCD_GRAPHBREAK(ch) GET_UCD(ch)->gbprop -#define UCD_CASESET(ch) GET_UCD(ch)->caseset -#define UCD_OTHERCASE(ch) ((pcre_uint32)((int)ch + (int)(GET_UCD(ch)->other_case))) - -#endif /* SUPPORT_UCP */ - -#endif - -/* End of pcre_internal.h */ diff --git a/src/third_party/pcre-8.38/pcre_jit_compile.c b/src/third_party/pcre-8.38/pcre_jit_compile.c deleted file mode 100644 index 445de0cbefe..00000000000 --- a/src/third_party/pcre-8.38/pcre_jit_compile.c +++ /dev/null @@ -1,10733 +0,0 @@ -/************************************************* -* Perl-Compatible Regular Expressions * -*************************************************/ - -/* PCRE is a library of functions to support regular expressions whose syntax -and semantics are as close as possible to those of the Perl 5 language. - - Written by Philip Hazel - Copyright (c) 1997-2013 University of Cambridge - - The machine code generator part (this module) was written by Zoltan Herczeg - Copyright (c) 2010-2013 - ------------------------------------------------------------------------------ -Redistribution and use in source and binary forms, with or without -modification, are permitted provided that the following conditions are met: - - * Redistributions of source code must retain the above copyright notice, - this list of conditions and the following disclaimer. - - * Redistributions in binary form must reproduce the above copyright - notice, this list of conditions and the following disclaimer in the - documentation and/or other materials provided with the distribution. - - * Neither the name of the University of Cambridge nor the names of its - contributors may be used to endorse or promote products derived from - this software without specific prior written permission. - -THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS" -AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE -IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE -ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR CONTRIBUTORS BE -LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR -CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF -SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS -INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN -CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) -ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE -POSSIBILITY OF SUCH DAMAGE. ------------------------------------------------------------------------------ -*/ - -#ifdef HAVE_CONFIG_H -#include "config.h" -#endif - -#include "pcre_internal.h" - -#if defined SUPPORT_JIT - -/* All-in-one: Since we use the JIT compiler only from here, -we just include it. This way we don't need to touch the build -system files. */ - -#define SLJIT_MALLOC(size, allocator_data) (PUBL(malloc))(size) -#define SLJIT_FREE(ptr, allocator_data) (PUBL(free))(ptr) -#define SLJIT_CONFIG_AUTO 1 -#define SLJIT_CONFIG_STATIC 1 -#define SLJIT_VERBOSE 0 -#define SLJIT_DEBUG 0 - -#include "sljit/sljitLir.c" - -#if defined SLJIT_CONFIG_UNSUPPORTED && SLJIT_CONFIG_UNSUPPORTED -#error Unsupported architecture -#endif - -/* Defines for debugging purposes. */ - -/* 1 - Use unoptimized capturing brackets. - 2 - Enable capture_last_ptr (includes option 1). */ -/* #define DEBUG_FORCE_UNOPTIMIZED_CBRAS 2 */ - -/* 1 - Always have a control head. */ -/* #define DEBUG_FORCE_CONTROL_HEAD 1 */ - -/* Allocate memory for the regex stack on the real machine stack. -Fast, but limited size. */ -#define MACHINE_STACK_SIZE 32768 - -/* Growth rate for stack allocated by the OS. Should be the multiply -of page size. */ -#define STACK_GROWTH_RATE 8192 - -/* Enable to check that the allocation could destroy temporaries. */ -#if defined SLJIT_DEBUG && SLJIT_DEBUG -#define DESTROY_REGISTERS 1 -#endif - -/* -Short summary about the backtracking mechanism empolyed by the jit code generator: - -The code generator follows the recursive nature of the PERL compatible regular -expressions. The basic blocks of regular expressions are condition checkers -whose execute different commands depending on the result of the condition check. -The relationship between the operators can be horizontal (concatenation) and -vertical (sub-expression) (See struct backtrack_common for more details). - - 'ab' - 'a' and 'b' regexps are concatenated - 'a+' - 'a' is the sub-expression of the '+' operator - -The condition checkers are boolean (true/false) checkers. Machine code is generated -for the checker itself and for the actions depending on the result of the checker. -The 'true' case is called as the matching path (expected path), and the other is called as -the 'backtrack' path. Branch instructions are expesive for all CPUs, so we avoid taken -branches on the matching path. - - Greedy star operator (*) : - Matching path: match happens. - Backtrack path: match failed. - Non-greedy star operator (*?) : - Matching path: no need to perform a match. - Backtrack path: match is required. - -The following example shows how the code generated for a capturing bracket -with two alternatives. Let A, B, C, D are arbirary regular expressions, and -we have the following regular expression: - - A(B|C)D - -The generated code will be the following: - - A matching path - '(' matching path (pushing arguments to the stack) - B matching path - ')' matching path (pushing arguments to the stack) - D matching path - return with successful match - - D backtrack path - ')' backtrack path (If we arrived from "C" jump to the backtrack of "C") - B backtrack path - C expected path - jump to D matching path - C backtrack path - A backtrack path - - Notice, that the order of backtrack code paths are the opposite of the fast - code paths. In this way the topmost value on the stack is always belong - to the current backtrack code path. The backtrack path must check - whether there is a next alternative. If so, it needs to jump back to - the matching path eventually. Otherwise it needs to clear out its own stack - frame and continue the execution on the backtrack code paths. -*/ - -/* -Saved stack frames: - -Atomic blocks and asserts require reloading the values of private data -when the backtrack mechanism performed. Because of OP_RECURSE, the data -are not necessarly known in compile time, thus we need a dynamic restore -mechanism. - -The stack frames are stored in a chain list, and have the following format: -([ capturing bracket offset ][ start value ][ end value ])+ ... [ 0 ] [ previous head ] - -Thus we can restore the private data to a particular point in the stack. -*/ - -typedef struct jit_arguments { - /* Pointers first. */ - struct sljit_stack *stack; - const pcre_uchar *str; - const pcre_uchar *begin; - const pcre_uchar *end; - int *offsets; - pcre_uchar *uchar_ptr; - pcre_uchar *mark_ptr; - void *callout_data; - /* Everything else after. */ - pcre_uint32 limit_match; - int real_offset_count; - int offset_count; - pcre_uint8 notbol; - pcre_uint8 noteol; - pcre_uint8 notempty; - pcre_uint8 notempty_atstart; -} jit_arguments; - -typedef struct executable_functions { - void *executable_funcs[JIT_NUMBER_OF_COMPILE_MODES]; - void *read_only_data_heads[JIT_NUMBER_OF_COMPILE_MODES]; - sljit_uw executable_sizes[JIT_NUMBER_OF_COMPILE_MODES]; - PUBL(jit_callback) callback; - void *userdata; - pcre_uint32 top_bracket; - pcre_uint32 limit_match; -} executable_functions; - -typedef struct jump_list { - struct sljit_jump *jump; - struct jump_list *next; -} jump_list; - -typedef struct stub_list { - struct sljit_jump *start; - struct sljit_label *quit; - struct stub_list *next; -} stub_list; - -typedef struct label_addr_list { - struct sljit_label *label; - sljit_uw *update_addr; - struct label_addr_list *next; -} label_addr_list; - -enum frame_types { - no_frame = -1, - no_stack = -2 -}; - -enum control_types { - type_mark = 0, - type_then_trap = 1 -}; - -typedef int (SLJIT_CALL *jit_function)(jit_arguments *args); - -/* The following structure is the key data type for the recursive -code generator. It is allocated by compile_matchingpath, and contains -the arguments for compile_backtrackingpath. Must be the first member -of its descendants. */ -typedef struct backtrack_common { - /* Concatenation stack. */ - struct backtrack_common *prev; - jump_list *nextbacktracks; - /* Internal stack (for component operators). */ - struct backtrack_common *top; - jump_list *topbacktracks; - /* Opcode pointer. */ - pcre_uchar *cc; -} backtrack_common; - -typedef struct assert_backtrack { - backtrack_common common; - jump_list *condfailed; - /* Less than 0 if a frame is not needed. */ - int framesize; - /* Points to our private memory word on the stack. */ - int private_data_ptr; - /* For iterators. */ - struct sljit_label *matchingpath; -} assert_backtrack; - -typedef struct bracket_backtrack { - backtrack_common common; - /* Where to coninue if an alternative is successfully matched. */ - struct sljit_label *alternative_matchingpath; - /* For rmin and rmax iterators. */ - struct sljit_label *recursive_matchingpath; - /* For greedy ? operator. */ - struct sljit_label *zero_matchingpath; - /* Contains the branches of a failed condition. */ - union { - /* Both for OP_COND, OP_SCOND. */ - jump_list *condfailed; - assert_backtrack *assert; - /* For OP_ONCE. Less than 0 if not needed. */ - int framesize; - } u; - /* Points to our private memory word on the stack. */ - int private_data_ptr; -} bracket_backtrack; - -typedef struct bracketpos_backtrack { - backtrack_common common; - /* Points to our private memory word on the stack. */ - int private_data_ptr; - /* Reverting stack is needed. */ - int framesize; - /* Allocated stack size. */ - int stacksize; -} bracketpos_backtrack; - -typedef struct braminzero_backtrack { - backtrack_common common; - struct sljit_label *matchingpath; -} braminzero_backtrack; - -typedef struct iterator_backtrack { - backtrack_common common; - /* Next iteration. */ - struct sljit_label *matchingpath; -} iterator_backtrack; - -typedef struct recurse_entry { - struct recurse_entry *next; - /* Contains the function entry. */ - struct sljit_label *entry; - /* Collects the calls until the function is not created. */ - jump_list *calls; - /* Points to the starting opcode. */ - sljit_sw start; -} recurse_entry; - -typedef struct recurse_backtrack { - backtrack_common common; - BOOL inlined_pattern; -} recurse_backtrack; - -#define OP_THEN_TRAP OP_TABLE_LENGTH - -typedef struct then_trap_backtrack { - backtrack_common common; - /* If then_trap is not NULL, this structure contains the real - then_trap for the backtracking path. */ - struct then_trap_backtrack *then_trap; - /* Points to the starting opcode. */ - sljit_sw start; - /* Exit point for the then opcodes of this alternative. */ - jump_list *quit; - /* Frame size of the current alternative. */ - int framesize; -} then_trap_backtrack; - -#define MAX_RANGE_SIZE 4 - -typedef struct compiler_common { - /* The sljit ceneric compiler. */ - struct sljit_compiler *compiler; - /* First byte code. */ - pcre_uchar *start; - /* Maps private data offset to each opcode. */ - sljit_si *private_data_ptrs; - /* Chain list of read-only data ptrs. */ - void *read_only_data_head; - /* Tells whether the capturing bracket is optimized. */ - pcre_uint8 *optimized_cbracket; - /* Tells whether the starting offset is a target of then. */ - pcre_uint8 *then_offsets; - /* Current position where a THEN must jump. */ - then_trap_backtrack *then_trap; - /* Starting offset of private data for capturing brackets. */ - int cbra_ptr; - /* Output vector starting point. Must be divisible by 2. */ - int ovector_start; - /* Last known position of the requested byte. */ - int req_char_ptr; - /* Head of the last recursion. */ - int recursive_head_ptr; - /* First inspected character for partial matching. */ - int start_used_ptr; - /* Starting pointer for partial soft matches. */ - int hit_start; - /* End pointer of the first line. */ - int first_line_end; - /* Points to the marked string. */ - int mark_ptr; - /* Recursive control verb management chain. */ - int control_head_ptr; - /* Points to the last matched capture block index. */ - int capture_last_ptr; - /* Points to the starting position of the current match. */ - int start_ptr; - - /* Flipped and lower case tables. */ - const pcre_uint8 *fcc; - sljit_sw lcc; - /* Mode can be PCRE_STUDY_JIT_COMPILE and others. */ - int mode; - /* TRUE, when minlength is greater than 0. */ - BOOL might_be_empty; - /* \K is found in the pattern. */ - BOOL has_set_som; - /* (*SKIP:arg) is found in the pattern. */ - BOOL has_skip_arg; - /* (*THEN) is found in the pattern. */ - BOOL has_then; - /* Needs to know the start position anytime. */ - BOOL needs_start_ptr; - /* Currently in recurse or negative assert. */ - BOOL local_exit; - /* Currently in a positive assert. */ - BOOL positive_assert; - /* Newline control. */ - int nltype; - pcre_uint32 nlmax; - pcre_uint32 nlmin; - int newline; - int bsr_nltype; - pcre_uint32 bsr_nlmax; - pcre_uint32 bsr_nlmin; - /* Dollar endonly. */ - int endonly; - /* Tables. */ - sljit_sw ctypes; - /* Named capturing brackets. */ - pcre_uchar *name_table; - sljit_sw name_count; - sljit_sw name_entry_size; - - /* Labels and jump lists. */ - struct sljit_label *partialmatchlabel; - struct sljit_label *quit_label; - struct sljit_label *forced_quit_label; - struct sljit_label *accept_label; - struct sljit_label *ff_newline_shortcut; - stub_list *stubs; - label_addr_list *label_addrs; - recurse_entry *entries; - recurse_entry *currententry; - jump_list *partialmatch; - jump_list *quit; - jump_list *positive_assert_quit; - jump_list *forced_quit; - jump_list *accept; - jump_list *calllimit; - jump_list *stackalloc; - jump_list *revertframes; - jump_list *wordboundary; - jump_list *anynewline; - jump_list *hspace; - jump_list *vspace; - jump_list *casefulcmp; - jump_list *caselesscmp; - jump_list *reset_match; - BOOL jscript_compat; -#ifdef SUPPORT_UTF - BOOL utf; -#ifdef SUPPORT_UCP - BOOL use_ucp; -#endif -#ifdef COMPILE_PCRE8 - jump_list *utfreadchar; - jump_list *utfreadchar16; - jump_list *utfreadtype8; -#endif -#endif /* SUPPORT_UTF */ -#ifdef SUPPORT_UCP - jump_list *getucd; -#endif -} compiler_common; - -/* For byte_sequence_compare. */ - -typedef struct compare_context { - int length; - int sourcereg; -#if defined SLJIT_UNALIGNED && SLJIT_UNALIGNED - int ucharptr; - union { - sljit_si asint; - sljit_uh asushort; -#if defined COMPILE_PCRE8 - sljit_ub asbyte; - sljit_ub asuchars[4]; -#elif defined COMPILE_PCRE16 - sljit_uh asuchars[2]; -#elif defined COMPILE_PCRE32 - sljit_ui asuchars[1]; -#endif - } c; - union { - sljit_si asint; - sljit_uh asushort; -#if defined COMPILE_PCRE8 - sljit_ub asbyte; - sljit_ub asuchars[4]; -#elif defined COMPILE_PCRE16 - sljit_uh asuchars[2]; -#elif defined COMPILE_PCRE32 - sljit_ui asuchars[1]; -#endif - } oc; -#endif -} compare_context; - -/* Undefine sljit macros. */ -#undef CMP - -/* Used for accessing the elements of the stack. */ -#define STACK(i) ((-(i) - 1) * (int)sizeof(sljit_sw)) - -#define TMP1 SLJIT_R0 -#define TMP2 SLJIT_R2 -#define TMP3 SLJIT_R3 -#define STR_PTR SLJIT_S0 -#define STR_END SLJIT_S1 -#define STACK_TOP SLJIT_R1 -#define STACK_LIMIT SLJIT_S2 -#define COUNT_MATCH SLJIT_S3 -#define ARGUMENTS SLJIT_S4 -#define RETURN_ADDR SLJIT_R4 - -/* Local space layout. */ -/* These two locals can be used by the current opcode. */ -#define LOCALS0 (0 * sizeof(sljit_sw)) -#define LOCALS1 (1 * sizeof(sljit_sw)) -/* Two local variables for possessive quantifiers (char1 cannot use them). */ -#define POSSESSIVE0 (2 * sizeof(sljit_sw)) -#define POSSESSIVE1 (3 * sizeof(sljit_sw)) -/* Max limit of recursions. */ -#define LIMIT_MATCH (4 * sizeof(sljit_sw)) -/* The output vector is stored on the stack, and contains pointers -to characters. The vector data is divided into two groups: the first -group contains the start / end character pointers, and the second is -the start pointers when the end of the capturing group has not yet reached. */ -#define OVECTOR_START (common->ovector_start) -#define OVECTOR(i) (OVECTOR_START + (i) * (sljit_sw)sizeof(sljit_sw)) -#define OVECTOR_PRIV(i) (common->cbra_ptr + (i) * (sljit_sw)sizeof(sljit_sw)) -#define PRIVATE_DATA(cc) (common->private_data_ptrs[(cc) - common->start]) - -#if defined COMPILE_PCRE8 -#define MOV_UCHAR SLJIT_MOV_UB -#define MOVU_UCHAR SLJIT_MOVU_UB -#elif defined COMPILE_PCRE16 -#define MOV_UCHAR SLJIT_MOV_UH -#define MOVU_UCHAR SLJIT_MOVU_UH -#elif defined COMPILE_PCRE32 -#define MOV_UCHAR SLJIT_MOV_UI -#define MOVU_UCHAR SLJIT_MOVU_UI -#else -#error Unsupported compiling mode -#endif - -/* Shortcuts. */ -#define DEFINE_COMPILER \ - struct sljit_compiler *compiler = common->compiler -#define OP1(op, dst, dstw, src, srcw) \ - sljit_emit_op1(compiler, (op), (dst), (dstw), (src), (srcw)) -#define OP2(op, dst, dstw, src1, src1w, src2, src2w) \ - sljit_emit_op2(compiler, (op), (dst), (dstw), (src1), (src1w), (src2), (src2w)) -#define LABEL() \ - sljit_emit_label(compiler) -#define JUMP(type) \ - sljit_emit_jump(compiler, (type)) -#define JUMPTO(type, label) \ - sljit_set_label(sljit_emit_jump(compiler, (type)), (label)) -#define JUMPHERE(jump) \ - sljit_set_label((jump), sljit_emit_label(compiler)) -#define SET_LABEL(jump, label) \ - sljit_set_label((jump), (label)) -#define CMP(type, src1, src1w, src2, src2w) \ - sljit_emit_cmp(compiler, (type), (src1), (src1w), (src2), (src2w)) -#define CMPTO(type, src1, src1w, src2, src2w, label) \ - sljit_set_label(sljit_emit_cmp(compiler, (type), (src1), (src1w), (src2), (src2w)), (label)) -#define OP_FLAGS(op, dst, dstw, src, srcw, type) \ - sljit_emit_op_flags(compiler, (op), (dst), (dstw), (src), (srcw), (type)) -#define GET_LOCAL_BASE(dst, dstw, offset) \ - sljit_get_local_base(compiler, (dst), (dstw), (offset)) - -#define READ_CHAR_MAX 0x7fffffff - -static pcre_uchar *bracketend(pcre_uchar *cc) -{ -SLJIT_ASSERT((*cc >= OP_ASSERT && *cc <= OP_ASSERTBACK_NOT) || (*cc >= OP_ONCE && *cc <= OP_SCOND)); -do cc += GET(cc, 1); while (*cc == OP_ALT); -SLJIT_ASSERT(*cc >= OP_KET && *cc <= OP_KETRPOS); -cc += 1 + LINK_SIZE; -return cc; -} - -static int no_alternatives(pcre_uchar *cc) -{ -int count = 0; -SLJIT_ASSERT((*cc >= OP_ASSERT && *cc <= OP_ASSERTBACK_NOT) || (*cc >= OP_ONCE && *cc <= OP_SCOND)); -do - { - cc += GET(cc, 1); - count++; - } -while (*cc == OP_ALT); -SLJIT_ASSERT(*cc >= OP_KET && *cc <= OP_KETRPOS); -return count; -} - -static int ones_in_half_byte[16] = { - /* 0 */ 0, 1, 1, 2, /* 4 */ 1, 2, 2, 3, - /* 8 */ 1, 2, 2, 3, /* 12 */ 2, 3, 3, 4 -}; - -/* Functions whose might need modification for all new supported opcodes: - next_opcode - check_opcode_types - set_private_data_ptrs - get_framesize - init_frame - get_private_data_copy_length - copy_private_data - compile_matchingpath - compile_backtrackingpath -*/ - -static pcre_uchar *next_opcode(compiler_common *common, pcre_uchar *cc) -{ -SLJIT_UNUSED_ARG(common); -switch(*cc) - { - case OP_SOD: - case OP_SOM: - case OP_SET_SOM: - case OP_NOT_WORD_BOUNDARY: - case OP_WORD_BOUNDARY: - case OP_NOT_DIGIT: - case OP_DIGIT: - case OP_NOT_WHITESPACE: - case OP_WHITESPACE: - case OP_NOT_WORDCHAR: - case OP_WORDCHAR: - case OP_ANY: - case OP_ALLANY: - case OP_NOTPROP: - case OP_PROP: - case OP_ANYNL: - case OP_NOT_HSPACE: - case OP_HSPACE: - case OP_NOT_VSPACE: - case OP_VSPACE: - case OP_EXTUNI: - case OP_EODN: - case OP_EOD: - case OP_CIRC: - case OP_CIRCM: - case OP_DOLL: - case OP_DOLLM: - case OP_CRSTAR: - case OP_CRMINSTAR: - case OP_CRPLUS: - case OP_CRMINPLUS: - case OP_CRQUERY: - case OP_CRMINQUERY: - case OP_CRRANGE: - case OP_CRMINRANGE: - case OP_CRPOSSTAR: - case OP_CRPOSPLUS: - case OP_CRPOSQUERY: - case OP_CRPOSRANGE: - case OP_CLASS: - case OP_NCLASS: - case OP_REF: - case OP_REFI: - case OP_DNREF: - case OP_DNREFI: - case OP_RECURSE: - case OP_CALLOUT: - case OP_ALT: - case OP_KET: - case OP_KETRMAX: - case OP_KETRMIN: - case OP_KETRPOS: - case OP_REVERSE: - case OP_ASSERT: - case OP_ASSERT_NOT: - case OP_ASSERTBACK: - case OP_ASSERTBACK_NOT: - case OP_ONCE: - case OP_ONCE_NC: - case OP_BRA: - case OP_BRAPOS: - case OP_CBRA: - case OP_CBRAPOS: - case OP_COND: - case OP_SBRA: - case OP_SBRAPOS: - case OP_SCBRA: - case OP_SCBRAPOS: - case OP_SCOND: - case OP_CREF: - case OP_DNCREF: - case OP_RREF: - case OP_DNRREF: - case OP_DEF: - case OP_BRAZERO: - case OP_BRAMINZERO: - case OP_BRAPOSZERO: - case OP_PRUNE: - case OP_SKIP: - case OP_THEN: - case OP_COMMIT: - case OP_FAIL: - case OP_ACCEPT: - case OP_ASSERT_ACCEPT: - case OP_CLOSE: - case OP_SKIPZERO: - return cc + PRIV(OP_lengths)[*cc]; - - case OP_CHAR: - case OP_CHARI: - case OP_NOT: - case OP_NOTI: - case OP_STAR: - case OP_MINSTAR: - case OP_PLUS: - case OP_MINPLUS: - case OP_QUERY: - case OP_MINQUERY: - case OP_UPTO: - case OP_MINUPTO: - case OP_EXACT: - case OP_POSSTAR: - case OP_POSPLUS: - case OP_POSQUERY: - case OP_POSUPTO: - case OP_STARI: - case OP_MINSTARI: - case OP_PLUSI: - case OP_MINPLUSI: - case OP_QUERYI: - case OP_MINQUERYI: - case OP_UPTOI: - case OP_MINUPTOI: - case OP_EXACTI: - case OP_POSSTARI: - case OP_POSPLUSI: - case OP_POSQUERYI: - case OP_POSUPTOI: - case OP_NOTSTAR: - case OP_NOTMINSTAR: - case OP_NOTPLUS: - case OP_NOTMINPLUS: - case OP_NOTQUERY: - case OP_NOTMINQUERY: - case OP_NOTUPTO: - case OP_NOTMINUPTO: - case OP_NOTEXACT: - case OP_NOTPOSSTAR: - case OP_NOTPOSPLUS: - case OP_NOTPOSQUERY: - case OP_NOTPOSUPTO: - case OP_NOTSTARI: - case OP_NOTMINSTARI: - case OP_NOTPLUSI: - case OP_NOTMINPLUSI: - case OP_NOTQUERYI: - case OP_NOTMINQUERYI: - case OP_NOTUPTOI: - case OP_NOTMINUPTOI: - case OP_NOTEXACTI: - case OP_NOTPOSSTARI: - case OP_NOTPOSPLUSI: - case OP_NOTPOSQUERYI: - case OP_NOTPOSUPTOI: - cc += PRIV(OP_lengths)[*cc]; -#ifdef SUPPORT_UTF - if (common->utf && HAS_EXTRALEN(cc[-1])) cc += GET_EXTRALEN(cc[-1]); -#endif - return cc; - - /* Special cases. */ - case OP_TYPESTAR: - case OP_TYPEMINSTAR: - case OP_TYPEPLUS: - case OP_TYPEMINPLUS: - case OP_TYPEQUERY: - case OP_TYPEMINQUERY: - case OP_TYPEUPTO: - case OP_TYPEMINUPTO: - case OP_TYPEEXACT: - case OP_TYPEPOSSTAR: - case OP_TYPEPOSPLUS: - case OP_TYPEPOSQUERY: - case OP_TYPEPOSUPTO: - return cc + PRIV(OP_lengths)[*cc] - 1; - - case OP_ANYBYTE: -#ifdef SUPPORT_UTF - if (common->utf) return NULL; -#endif - return cc + 1; - -#if defined SUPPORT_UTF || !defined COMPILE_PCRE8 - case OP_XCLASS: - return cc + GET(cc, 1); -#endif - - case OP_MARK: - case OP_PRUNE_ARG: - case OP_SKIP_ARG: - case OP_THEN_ARG: - return cc + 1 + 2 + cc[1]; - - default: - /* All opcodes are supported now! */ - SLJIT_ASSERT_STOP(); - return NULL; - } -} - -static BOOL check_opcode_types(compiler_common *common, pcre_uchar *cc, pcre_uchar *ccend) -{ -int count; -pcre_uchar *slot; - -/* Calculate important variables (like stack size) and checks whether all opcodes are supported. */ -while (cc < ccend) - { - switch(*cc) - { - case OP_SET_SOM: - common->has_set_som = TRUE; - common->might_be_empty = TRUE; - cc += 1; - break; - - case OP_REF: - case OP_REFI: - common->optimized_cbracket[GET2(cc, 1)] = 0; - cc += 1 + IMM2_SIZE; - break; - - case OP_CBRAPOS: - case OP_SCBRAPOS: - common->optimized_cbracket[GET2(cc, 1 + LINK_SIZE)] = 0; - cc += 1 + LINK_SIZE + IMM2_SIZE; - break; - - case OP_COND: - case OP_SCOND: - /* Only AUTO_CALLOUT can insert this opcode. We do - not intend to support this case. */ - if (cc[1 + LINK_SIZE] == OP_CALLOUT) - return FALSE; - cc += 1 + LINK_SIZE; - break; - - case OP_CREF: - common->optimized_cbracket[GET2(cc, 1)] = 0; - cc += 1 + IMM2_SIZE; - break; - - case OP_DNREF: - case OP_DNREFI: - case OP_DNCREF: - count = GET2(cc, 1 + IMM2_SIZE); - slot = common->name_table + GET2(cc, 1) * common->name_entry_size; - while (count-- > 0) - { - common->optimized_cbracket[GET2(slot, 0)] = 0; - slot += common->name_entry_size; - } - cc += 1 + 2 * IMM2_SIZE; - break; - - case OP_RECURSE: - /* Set its value only once. */ - if (common->recursive_head_ptr == 0) - { - common->recursive_head_ptr = common->ovector_start; - common->ovector_start += sizeof(sljit_sw); - } - cc += 1 + LINK_SIZE; - break; - - case OP_CALLOUT: - if (common->capture_last_ptr == 0) - { - common->capture_last_ptr = common->ovector_start; - common->ovector_start += sizeof(sljit_sw); - } - cc += 2 + 2 * LINK_SIZE; - break; - - case OP_THEN_ARG: - common->has_then = TRUE; - common->control_head_ptr = 1; - /* Fall through. */ - - case OP_PRUNE_ARG: - common->needs_start_ptr = TRUE; - /* Fall through. */ - - case OP_MARK: - if (common->mark_ptr == 0) - { - common->mark_ptr = common->ovector_start; - common->ovector_start += sizeof(sljit_sw); - } - cc += 1 + 2 + cc[1]; - break; - - case OP_THEN: - common->has_then = TRUE; - common->control_head_ptr = 1; - /* Fall through. */ - - case OP_PRUNE: - case OP_SKIP: - common->needs_start_ptr = TRUE; - cc += 1; - break; - - case OP_SKIP_ARG: - common->control_head_ptr = 1; - common->has_skip_arg = TRUE; - cc += 1 + 2 + cc[1]; - break; - - default: - cc = next_opcode(common, cc); - if (cc == NULL) - return FALSE; - break; - } - } -return TRUE; -} - -static int get_class_iterator_size(pcre_uchar *cc) -{ -switch(*cc) - { - case OP_CRSTAR: - case OP_CRPLUS: - return 2; - - case OP_CRMINSTAR: - case OP_CRMINPLUS: - case OP_CRQUERY: - case OP_CRMINQUERY: - return 1; - - case OP_CRRANGE: - case OP_CRMINRANGE: - if (GET2(cc, 1) == GET2(cc, 1 + IMM2_SIZE)) - return 0; - return 2; - - default: - return 0; - } -} - -static BOOL detect_repeat(compiler_common *common, pcre_uchar *begin) -{ -pcre_uchar *end = bracketend(begin); -pcre_uchar *next; -pcre_uchar *next_end; -pcre_uchar *max_end; -pcre_uchar type; -sljit_sw length = end - begin; -int min, max, i; - -/* Detect fixed iterations first. */ -if (end[-(1 + LINK_SIZE)] != OP_KET) - return FALSE; - -/* Already detected repeat. */ -if (common->private_data_ptrs[end - common->start - LINK_SIZE] != 0) - return TRUE; - -next = end; -min = 1; -while (1) - { - if (*next != *begin) - break; - next_end = bracketend(next); - if (next_end - next != length || memcmp(begin, next, IN_UCHARS(length)) != 0) - break; - next = next_end; - min++; - } - -if (min == 2) - return FALSE; - -max = 0; -max_end = next; -if (*next == OP_BRAZERO || *next == OP_BRAMINZERO) - { - type = *next; - while (1) - { - if (next[0] != type || next[1] != OP_BRA || next[2 + LINK_SIZE] != *begin) - break; - next_end = bracketend(next + 2 + LINK_SIZE); - if (next_end - next != (length + 2 + LINK_SIZE) || memcmp(begin, next + 2 + LINK_SIZE, IN_UCHARS(length)) != 0) - break; - next = next_end; - max++; - } - - if (next[0] == type && next[1] == *begin && max >= 1) - { - next_end = bracketend(next + 1); - if (next_end - next == (length + 1) && memcmp(begin, next + 1, IN_UCHARS(length)) == 0) - { - for (i = 0; i < max; i++, next_end += 1 + LINK_SIZE) - if (*next_end != OP_KET) - break; - - if (i == max) - { - common->private_data_ptrs[max_end - common->start - LINK_SIZE] = next_end - max_end; - common->private_data_ptrs[max_end - common->start - LINK_SIZE + 1] = (type == OP_BRAZERO) ? OP_UPTO : OP_MINUPTO; - /* +2 the original and the last. */ - common->private_data_ptrs[max_end - common->start - LINK_SIZE + 2] = max + 2; - if (min == 1) - return TRUE; - min--; - max_end -= (1 + LINK_SIZE) + GET(max_end, -LINK_SIZE); - } - } - } - } - -if (min >= 3) - { - common->private_data_ptrs[end - common->start - LINK_SIZE] = max_end - end; - common->private_data_ptrs[end - common->start - LINK_SIZE + 1] = OP_EXACT; - common->private_data_ptrs[end - common->start - LINK_SIZE + 2] = min; - return TRUE; - } - -return FALSE; -} - -#define CASE_ITERATOR_PRIVATE_DATA_1 \ - case OP_MINSTAR: \ - case OP_MINPLUS: \ - case OP_QUERY: \ - case OP_MINQUERY: \ - case OP_MINSTARI: \ - case OP_MINPLUSI: \ - case OP_QUERYI: \ - case OP_MINQUERYI: \ - case OP_NOTMINSTAR: \ - case OP_NOTMINPLUS: \ - case OP_NOTQUERY: \ - case OP_NOTMINQUERY: \ - case OP_NOTMINSTARI: \ - case OP_NOTMINPLUSI: \ - case OP_NOTQUERYI: \ - case OP_NOTMINQUERYI: - -#define CASE_ITERATOR_PRIVATE_DATA_2A \ - case OP_STAR: \ - case OP_PLUS: \ - case OP_STARI: \ - case OP_PLUSI: \ - case OP_NOTSTAR: \ - case OP_NOTPLUS: \ - case OP_NOTSTARI: \ - case OP_NOTPLUSI: - -#define CASE_ITERATOR_PRIVATE_DATA_2B \ - case OP_UPTO: \ - case OP_MINUPTO: \ - case OP_UPTOI: \ - case OP_MINUPTOI: \ - case OP_NOTUPTO: \ - case OP_NOTMINUPTO: \ - case OP_NOTUPTOI: \ - case OP_NOTMINUPTOI: - -#define CASE_ITERATOR_TYPE_PRIVATE_DATA_1 \ - case OP_TYPEMINSTAR: \ - case OP_TYPEMINPLUS: \ - case OP_TYPEQUERY: \ - case OP_TYPEMINQUERY: - -#define CASE_ITERATOR_TYPE_PRIVATE_DATA_2A \ - case OP_TYPESTAR: \ - case OP_TYPEPLUS: - -#define CASE_ITERATOR_TYPE_PRIVATE_DATA_2B \ - case OP_TYPEUPTO: \ - case OP_TYPEMINUPTO: - -static void set_private_data_ptrs(compiler_common *common, int *private_data_start, pcre_uchar *ccend) -{ -pcre_uchar *cc = common->start; -pcre_uchar *alternative; -pcre_uchar *end = NULL; -int private_data_ptr = *private_data_start; -int space, size, bracketlen; -BOOL repeat_check = TRUE; - -while (cc < ccend) - { - space = 0; - size = 0; - bracketlen = 0; - if (private_data_ptr > SLJIT_MAX_LOCAL_SIZE) - break; - - if (repeat_check && (*cc == OP_ONCE || *cc == OP_ONCE_NC || *cc == OP_BRA || *cc == OP_CBRA || *cc == OP_COND)) - { - if (detect_repeat(common, cc)) - { - /* These brackets are converted to repeats, so no global - based single character repeat is allowed. */ - if (cc >= end) - end = bracketend(cc); - } - } - repeat_check = TRUE; - - switch(*cc) - { - case OP_KET: - if (common->private_data_ptrs[cc + 1 - common->start] != 0) - { - common->private_data_ptrs[cc - common->start] = private_data_ptr; - private_data_ptr += sizeof(sljit_sw); - cc += common->private_data_ptrs[cc + 1 - common->start]; - } - cc += 1 + LINK_SIZE; - break; - - case OP_ASSERT: - case OP_ASSERT_NOT: - case OP_ASSERTBACK: - case OP_ASSERTBACK_NOT: - case OP_ONCE: - case OP_ONCE_NC: - case OP_BRAPOS: - case OP_SBRA: - case OP_SBRAPOS: - case OP_SCOND: - common->private_data_ptrs[cc - common->start] = private_data_ptr; - private_data_ptr += sizeof(sljit_sw); - bracketlen = 1 + LINK_SIZE; - break; - - case OP_CBRAPOS: - case OP_SCBRAPOS: - common->private_data_ptrs[cc - common->start] = private_data_ptr; - private_data_ptr += sizeof(sljit_sw); - bracketlen = 1 + LINK_SIZE + IMM2_SIZE; - break; - - case OP_COND: - /* Might be a hidden SCOND. */ - alternative = cc + GET(cc, 1); - if (*alternative == OP_KETRMAX || *alternative == OP_KETRMIN) - { - common->private_data_ptrs[cc - common->start] = private_data_ptr; - private_data_ptr += sizeof(sljit_sw); - } - bracketlen = 1 + LINK_SIZE; - break; - - case OP_BRA: - bracketlen = 1 + LINK_SIZE; - break; - - case OP_CBRA: - case OP_SCBRA: - bracketlen = 1 + LINK_SIZE + IMM2_SIZE; - break; - - case OP_BRAZERO: - case OP_BRAMINZERO: - case OP_BRAPOSZERO: - repeat_check = FALSE; - size = 1; - break; - - CASE_ITERATOR_PRIVATE_DATA_1 - space = 1; - size = -2; - break; - - CASE_ITERATOR_PRIVATE_DATA_2A - space = 2; - size = -2; - break; - - CASE_ITERATOR_PRIVATE_DATA_2B - space = 2; - size = -(2 + IMM2_SIZE); - break; - - CASE_ITERATOR_TYPE_PRIVATE_DATA_1 - space = 1; - size = 1; - break; - - CASE_ITERATOR_TYPE_PRIVATE_DATA_2A - if (cc[1] != OP_ANYNL && cc[1] != OP_EXTUNI) - space = 2; - size = 1; - break; - - case OP_TYPEUPTO: - if (cc[1 + IMM2_SIZE] != OP_ANYNL && cc[1 + IMM2_SIZE] != OP_EXTUNI) - space = 2; - size = 1 + IMM2_SIZE; - break; - - case OP_TYPEMINUPTO: - space = 2; - size = 1 + IMM2_SIZE; - break; - - case OP_CLASS: - case OP_NCLASS: - size += 1 + 32 / sizeof(pcre_uchar); - space = get_class_iterator_size(cc + size); - break; - -#if defined SUPPORT_UTF || !defined COMPILE_PCRE8 - case OP_XCLASS: - size = GET(cc, 1); - space = get_class_iterator_size(cc + size); - break; -#endif - - default: - cc = next_opcode(common, cc); - SLJIT_ASSERT(cc != NULL); - break; - } - - /* Character iterators, which are not inside a repeated bracket, - gets a private slot instead of allocating it on the stack. */ - if (space > 0 && cc >= end) - { - common->private_data_ptrs[cc - common->start] = private_data_ptr; - private_data_ptr += sizeof(sljit_sw) * space; - } - - if (size != 0) - { - if (size < 0) - { - cc += -size; -#ifdef SUPPORT_UTF - if (common->utf && HAS_EXTRALEN(cc[-1])) cc += GET_EXTRALEN(cc[-1]); -#endif - } - else - cc += size; - } - - if (bracketlen > 0) - { - if (cc >= end) - { - end = bracketend(cc); - if (end[-1 - LINK_SIZE] == OP_KET) - end = NULL; - } - cc += bracketlen; - } - } -*private_data_start = private_data_ptr; -} - -/* Returns with a frame_types (always < 0) if no need for frame. */ -static int get_framesize(compiler_common *common, pcre_uchar *cc, pcre_uchar *ccend, BOOL recursive, BOOL *needs_control_head) -{ -int length = 0; -int possessive = 0; -BOOL stack_restore = FALSE; -BOOL setsom_found = recursive; -BOOL setmark_found = recursive; -/* The last capture is a local variable even for recursions. */ -BOOL capture_last_found = FALSE; - -#if defined DEBUG_FORCE_CONTROL_HEAD && DEBUG_FORCE_CONTROL_HEAD -SLJIT_ASSERT(common->control_head_ptr != 0); -*needs_control_head = TRUE; -#else -*needs_control_head = FALSE; -#endif - -if (ccend == NULL) - { - ccend = bracketend(cc) - (1 + LINK_SIZE); - if (!recursive && (*cc == OP_CBRAPOS || *cc == OP_SCBRAPOS)) - { - possessive = length = (common->capture_last_ptr != 0) ? 5 : 3; - /* This is correct regardless of common->capture_last_ptr. */ - capture_last_found = TRUE; - } - cc = next_opcode(common, cc); - } - -SLJIT_ASSERT(cc != NULL); -while (cc < ccend) - switch(*cc) - { - case OP_SET_SOM: - SLJIT_ASSERT(common->has_set_som); - stack_restore = TRUE; - if (!setsom_found) - { - length += 2; - setsom_found = TRUE; - } - cc += 1; - break; - - case OP_MARK: - case OP_PRUNE_ARG: - case OP_THEN_ARG: - SLJIT_ASSERT(common->mark_ptr != 0); - stack_restore = TRUE; - if (!setmark_found) - { - length += 2; - setmark_found = TRUE; - } - if (common->control_head_ptr != 0) - *needs_control_head = TRUE; - cc += 1 + 2 + cc[1]; - break; - - case OP_RECURSE: - stack_restore = TRUE; - if (common->has_set_som && !setsom_found) - { - length += 2; - setsom_found = TRUE; - } - if (common->mark_ptr != 0 && !setmark_found) - { - length += 2; - setmark_found = TRUE; - } - if (common->capture_last_ptr != 0 && !capture_last_found) - { - length += 2; - capture_last_found = TRUE; - } - cc += 1 + LINK_SIZE; - break; - - case OP_CBRA: - case OP_CBRAPOS: - case OP_SCBRA: - case OP_SCBRAPOS: - stack_restore = TRUE; - if (common->capture_last_ptr != 0 && !capture_last_found) - { - length += 2; - capture_last_found = TRUE; - } - length += 3; - cc += 1 + LINK_SIZE + IMM2_SIZE; - break; - - case OP_THEN: - stack_restore = TRUE; - if (common->control_head_ptr != 0) - *needs_control_head = TRUE; - cc ++; - break; - - default: - stack_restore = TRUE; - /* Fall through. */ - - case OP_NOT_WORD_BOUNDARY: - case OP_WORD_BOUNDARY: - case OP_NOT_DIGIT: - case OP_DIGIT: - case OP_NOT_WHITESPACE: - case OP_WHITESPACE: - case OP_NOT_WORDCHAR: - case OP_WORDCHAR: - case OP_ANY: - case OP_ALLANY: - case OP_ANYBYTE: - case OP_NOTPROP: - case OP_PROP: - case OP_ANYNL: - case OP_NOT_HSPACE: - case OP_HSPACE: - case OP_NOT_VSPACE: - case OP_VSPACE: - case OP_EXTUNI: - case OP_EODN: - case OP_EOD: - case OP_CIRC: - case OP_CIRCM: - case OP_DOLL: - case OP_DOLLM: - case OP_CHAR: - case OP_CHARI: - case OP_NOT: - case OP_NOTI: - - case OP_EXACT: - case OP_POSSTAR: - case OP_POSPLUS: - case OP_POSQUERY: - case OP_POSUPTO: - - case OP_EXACTI: - case OP_POSSTARI: - case OP_POSPLUSI: - case OP_POSQUERYI: - case OP_POSUPTOI: - - case OP_NOTEXACT: - case OP_NOTPOSSTAR: - case OP_NOTPOSPLUS: - case OP_NOTPOSQUERY: - case OP_NOTPOSUPTO: - - case OP_NOTEXACTI: - case OP_NOTPOSSTARI: - case OP_NOTPOSPLUSI: - case OP_NOTPOSQUERYI: - case OP_NOTPOSUPTOI: - - case OP_TYPEEXACT: - case OP_TYPEPOSSTAR: - case OP_TYPEPOSPLUS: - case OP_TYPEPOSQUERY: - case OP_TYPEPOSUPTO: - - case OP_CLASS: - case OP_NCLASS: - case OP_XCLASS: - - cc = next_opcode(common, cc); - SLJIT_ASSERT(cc != NULL); - break; - } - -/* Possessive quantifiers can use a special case. */ -if (SLJIT_UNLIKELY(possessive == length)) - return stack_restore ? no_frame : no_stack; - -if (length > 0) - return length + 1; -return stack_restore ? no_frame : no_stack; -} - -static void init_frame(compiler_common *common, pcre_uchar *cc, pcre_uchar *ccend, int stackpos, int stacktop, BOOL recursive) -{ -DEFINE_COMPILER; -BOOL setsom_found = recursive; -BOOL setmark_found = recursive; -/* The last capture is a local variable even for recursions. */ -BOOL capture_last_found = FALSE; -int offset; - -/* >= 1 + shortest item size (2) */ -SLJIT_UNUSED_ARG(stacktop); -SLJIT_ASSERT(stackpos >= stacktop + 2); - -stackpos = STACK(stackpos); -if (ccend == NULL) - { - ccend = bracketend(cc) - (1 + LINK_SIZE); - if (recursive || (*cc != OP_CBRAPOS && *cc != OP_SCBRAPOS)) - cc = next_opcode(common, cc); - } - -SLJIT_ASSERT(cc != NULL); -while (cc < ccend) - switch(*cc) - { - case OP_SET_SOM: - SLJIT_ASSERT(common->has_set_som); - if (!setsom_found) - { - OP1(SLJIT_MOV, TMP1, 0, SLJIT_MEM1(SLJIT_SP), OVECTOR(0)); - OP1(SLJIT_MOV, SLJIT_MEM1(STACK_TOP), stackpos, SLJIT_IMM, -OVECTOR(0)); - stackpos += (int)sizeof(sljit_sw); - OP1(SLJIT_MOV, SLJIT_MEM1(STACK_TOP), stackpos, TMP1, 0); - stackpos += (int)sizeof(sljit_sw); - setsom_found = TRUE; - } - cc += 1; - break; - - case OP_MARK: - case OP_PRUNE_ARG: - case OP_THEN_ARG: - SLJIT_ASSERT(common->mark_ptr != 0); - if (!setmark_found) - { - OP1(SLJIT_MOV, TMP1, 0, SLJIT_MEM1(SLJIT_SP), common->mark_ptr); - OP1(SLJIT_MOV, SLJIT_MEM1(STACK_TOP), stackpos, SLJIT_IMM, -common->mark_ptr); - stackpos += (int)sizeof(sljit_sw); - OP1(SLJIT_MOV, SLJIT_MEM1(STACK_TOP), stackpos, TMP1, 0); - stackpos += (int)sizeof(sljit_sw); - setmark_found = TRUE; - } - cc += 1 + 2 + cc[1]; - break; - - case OP_RECURSE: - if (common->has_set_som && !setsom_found) - { - OP1(SLJIT_MOV, TMP1, 0, SLJIT_MEM1(SLJIT_SP), OVECTOR(0)); - OP1(SLJIT_MOV, SLJIT_MEM1(STACK_TOP), stackpos, SLJIT_IMM, -OVECTOR(0)); - stackpos += (int)sizeof(sljit_sw); - OP1(SLJIT_MOV, SLJIT_MEM1(STACK_TOP), stackpos, TMP1, 0); - stackpos += (int)sizeof(sljit_sw); - setsom_found = TRUE; - } - if (common->mark_ptr != 0 && !setmark_found) - { - OP1(SLJIT_MOV, TMP1, 0, SLJIT_MEM1(SLJIT_SP), common->mark_ptr); - OP1(SLJIT_MOV, SLJIT_MEM1(STACK_TOP), stackpos, SLJIT_IMM, -common->mark_ptr); - stackpos += (int)sizeof(sljit_sw); - OP1(SLJIT_MOV, SLJIT_MEM1(STACK_TOP), stackpos, TMP1, 0); - stackpos += (int)sizeof(sljit_sw); - setmark_found = TRUE; - } - if (common->capture_last_ptr != 0 && !capture_last_found) - { - OP1(SLJIT_MOV, TMP1, 0, SLJIT_MEM1(SLJIT_SP), common->capture_last_ptr); - OP1(SLJIT_MOV, SLJIT_MEM1(STACK_TOP), stackpos, SLJIT_IMM, -common->capture_last_ptr); - stackpos += (int)sizeof(sljit_sw); - OP1(SLJIT_MOV, SLJIT_MEM1(STACK_TOP), stackpos, TMP1, 0); - stackpos += (int)sizeof(sljit_sw); - capture_last_found = TRUE; - } - cc += 1 + LINK_SIZE; - break; - - case OP_CBRA: - case OP_CBRAPOS: - case OP_SCBRA: - case OP_SCBRAPOS: - if (common->capture_last_ptr != 0 && !capture_last_found) - { - OP1(SLJIT_MOV, TMP1, 0, SLJIT_MEM1(SLJIT_SP), common->capture_last_ptr); - OP1(SLJIT_MOV, SLJIT_MEM1(STACK_TOP), stackpos, SLJIT_IMM, -common->capture_last_ptr); - stackpos += (int)sizeof(sljit_sw); - OP1(SLJIT_MOV, SLJIT_MEM1(STACK_TOP), stackpos, TMP1, 0); - stackpos += (int)sizeof(sljit_sw); - capture_last_found = TRUE; - } - offset = (GET2(cc, 1 + LINK_SIZE)) << 1; - OP1(SLJIT_MOV, SLJIT_MEM1(STACK_TOP), stackpos, SLJIT_IMM, OVECTOR(offset)); - stackpos += (int)sizeof(sljit_sw); - OP1(SLJIT_MOV, TMP1, 0, SLJIT_MEM1(SLJIT_SP), OVECTOR(offset)); - OP1(SLJIT_MOV, TMP2, 0, SLJIT_MEM1(SLJIT_SP), OVECTOR(offset + 1)); - OP1(SLJIT_MOV, SLJIT_MEM1(STACK_TOP), stackpos, TMP1, 0); - stackpos += (int)sizeof(sljit_sw); - OP1(SLJIT_MOV, SLJIT_MEM1(STACK_TOP), stackpos, TMP2, 0); - stackpos += (int)sizeof(sljit_sw); - - cc += 1 + LINK_SIZE + IMM2_SIZE; - break; - - default: - cc = next_opcode(common, cc); - SLJIT_ASSERT(cc != NULL); - break; - } - -OP1(SLJIT_MOV, SLJIT_MEM1(STACK_TOP), stackpos, SLJIT_IMM, 0); -SLJIT_ASSERT(stackpos == STACK(stacktop)); -} - -static SLJIT_INLINE int get_private_data_copy_length(compiler_common *common, pcre_uchar *cc, pcre_uchar *ccend, BOOL needs_control_head) -{ -int private_data_length = needs_control_head ? 3 : 2; -int size; -pcre_uchar *alternative; -/* Calculate the sum of the private machine words. */ -while (cc < ccend) - { - size = 0; - switch(*cc) - { - case OP_KET: - if (PRIVATE_DATA(cc) != 0) - { - private_data_length++; - SLJIT_ASSERT(PRIVATE_DATA(cc + 1) != 0); - cc += PRIVATE_DATA(cc + 1); - } - cc += 1 + LINK_SIZE; - break; - - case OP_ASSERT: - case OP_ASSERT_NOT: - case OP_ASSERTBACK: - case OP_ASSERTBACK_NOT: - case OP_ONCE: - case OP_ONCE_NC: - case OP_BRAPOS: - case OP_SBRA: - case OP_SBRAPOS: - case OP_SCOND: - private_data_length++; - SLJIT_ASSERT(PRIVATE_DATA(cc) != 0); - cc += 1 + LINK_SIZE; - break; - - case OP_CBRA: - case OP_SCBRA: - if (common->optimized_cbracket[GET2(cc, 1 + LINK_SIZE)] == 0) - private_data_length++; - cc += 1 + LINK_SIZE + IMM2_SIZE; - break; - - case OP_CBRAPOS: - case OP_SCBRAPOS: - private_data_length += 2; - cc += 1 + LINK_SIZE + IMM2_SIZE; - break; - - case OP_COND: - /* Might be a hidden SCOND. */ - alternative = cc + GET(cc, 1); - if (*alternative == OP_KETRMAX || *alternative == OP_KETRMIN) - private_data_length++; - cc += 1 + LINK_SIZE; - break; - - CASE_ITERATOR_PRIVATE_DATA_1 - if (PRIVATE_DATA(cc)) - private_data_length++; - cc += 2; -#ifdef SUPPORT_UTF - if (common->utf && HAS_EXTRALEN(cc[-1])) cc += GET_EXTRALEN(cc[-1]); -#endif - break; - - CASE_ITERATOR_PRIVATE_DATA_2A - if (PRIVATE_DATA(cc)) - private_data_length += 2; - cc += 2; -#ifdef SUPPORT_UTF - if (common->utf && HAS_EXTRALEN(cc[-1])) cc += GET_EXTRALEN(cc[-1]); -#endif - break; - - CASE_ITERATOR_PRIVATE_DATA_2B - if (PRIVATE_DATA(cc)) - private_data_length += 2; - cc += 2 + IMM2_SIZE; -#ifdef SUPPORT_UTF - if (common->utf && HAS_EXTRALEN(cc[-1])) cc += GET_EXTRALEN(cc[-1]); -#endif - break; - - CASE_ITERATOR_TYPE_PRIVATE_DATA_1 - if (PRIVATE_DATA(cc)) - private_data_length++; - cc += 1; - break; - - CASE_ITERATOR_TYPE_PRIVATE_DATA_2A - if (PRIVATE_DATA(cc)) - private_data_length += 2; - cc += 1; - break; - - CASE_ITERATOR_TYPE_PRIVATE_DATA_2B - if (PRIVATE_DATA(cc)) - private_data_length += 2; - cc += 1 + IMM2_SIZE; - break; - - case OP_CLASS: - case OP_NCLASS: -#if defined SUPPORT_UTF || !defined COMPILE_PCRE8 - case OP_XCLASS: - size = (*cc == OP_XCLASS) ? GET(cc, 1) : 1 + 32 / (int)sizeof(pcre_uchar); -#else - size = 1 + 32 / (int)sizeof(pcre_uchar); -#endif - if (PRIVATE_DATA(cc)) - private_data_length += get_class_iterator_size(cc + size); - cc += size; - break; - - default: - cc = next_opcode(common, cc); - SLJIT_ASSERT(cc != NULL); - break; - } - } -SLJIT_ASSERT(cc == ccend); -return private_data_length; -} - -static void copy_private_data(compiler_common *common, pcre_uchar *cc, pcre_uchar *ccend, - BOOL save, int stackptr, int stacktop, BOOL needs_control_head) -{ -DEFINE_COMPILER; -int srcw[2]; -int count, size; -BOOL tmp1next = TRUE; -BOOL tmp1empty = TRUE; -BOOL tmp2empty = TRUE; -pcre_uchar *alternative; -enum { - start, - loop, - end -} status; - -status = save ? start : loop; -stackptr = STACK(stackptr - 2); -stacktop = STACK(stacktop - 1); - -if (!save) - { - stackptr += (needs_control_head ? 2 : 1) * sizeof(sljit_sw); - if (stackptr < stacktop) - { - OP1(SLJIT_MOV, TMP1, 0, SLJIT_MEM1(STACK_TOP), stackptr); - stackptr += sizeof(sljit_sw); - tmp1empty = FALSE; - } - if (stackptr < stacktop) - { - OP1(SLJIT_MOV, TMP2, 0, SLJIT_MEM1(STACK_TOP), stackptr); - stackptr += sizeof(sljit_sw); - tmp2empty = FALSE; - } - /* The tmp1next must be TRUE in either way. */ - } - -do - { - count = 0; - switch(status) - { - case start: - SLJIT_ASSERT(save && common->recursive_head_ptr != 0); - count = 1; - srcw[0] = common->recursive_head_ptr; - if (needs_control_head) - { - SLJIT_ASSERT(common->control_head_ptr != 0); - count = 2; - srcw[1] = common->control_head_ptr; - } - status = loop; - break; - - case loop: - if (cc >= ccend) - { - status = end; - break; - } - - switch(*cc) - { - case OP_KET: - if (PRIVATE_DATA(cc) != 0) - { - count = 1; - srcw[0] = PRIVATE_DATA(cc); - SLJIT_ASSERT(PRIVATE_DATA(cc + 1) != 0); - cc += PRIVATE_DATA(cc + 1); - } - cc += 1 + LINK_SIZE; - break; - - case OP_ASSERT: - case OP_ASSERT_NOT: - case OP_ASSERTBACK: - case OP_ASSERTBACK_NOT: - case OP_ONCE: - case OP_ONCE_NC: - case OP_BRAPOS: - case OP_SBRA: - case OP_SBRAPOS: - case OP_SCOND: - count = 1; - srcw[0] = PRIVATE_DATA(cc); - SLJIT_ASSERT(srcw[0] != 0); - cc += 1 + LINK_SIZE; - break; - - case OP_CBRA: - case OP_SCBRA: - if (common->optimized_cbracket[GET2(cc, 1 + LINK_SIZE)] == 0) - { - count = 1; - srcw[0] = OVECTOR_PRIV(GET2(cc, 1 + LINK_SIZE)); - } - cc += 1 + LINK_SIZE + IMM2_SIZE; - break; - - case OP_CBRAPOS: - case OP_SCBRAPOS: - count = 2; - srcw[0] = PRIVATE_DATA(cc); - srcw[1] = OVECTOR_PRIV(GET2(cc, 1 + LINK_SIZE)); - SLJIT_ASSERT(srcw[0] != 0 && srcw[1] != 0); - cc += 1 + LINK_SIZE + IMM2_SIZE; - break; - - case OP_COND: - /* Might be a hidden SCOND. */ - alternative = cc + GET(cc, 1); - if (*alternative == OP_KETRMAX || *alternative == OP_KETRMIN) - { - count = 1; - srcw[0] = PRIVATE_DATA(cc); - SLJIT_ASSERT(srcw[0] != 0); - } - cc += 1 + LINK_SIZE; - break; - - CASE_ITERATOR_PRIVATE_DATA_1 - if (PRIVATE_DATA(cc)) - { - count = 1; - srcw[0] = PRIVATE_DATA(cc); - } - cc += 2; -#ifdef SUPPORT_UTF - if (common->utf && HAS_EXTRALEN(cc[-1])) cc += GET_EXTRALEN(cc[-1]); -#endif - break; - - CASE_ITERATOR_PRIVATE_DATA_2A - if (PRIVATE_DATA(cc)) - { - count = 2; - srcw[0] = PRIVATE_DATA(cc); - srcw[1] = PRIVATE_DATA(cc) + sizeof(sljit_sw); - } - cc += 2; -#ifdef SUPPORT_UTF - if (common->utf && HAS_EXTRALEN(cc[-1])) cc += GET_EXTRALEN(cc[-1]); -#endif - break; - - CASE_ITERATOR_PRIVATE_DATA_2B - if (PRIVATE_DATA(cc)) - { - count = 2; - srcw[0] = PRIVATE_DATA(cc); - srcw[1] = PRIVATE_DATA(cc) + sizeof(sljit_sw); - } - cc += 2 + IMM2_SIZE; -#ifdef SUPPORT_UTF - if (common->utf && HAS_EXTRALEN(cc[-1])) cc += GET_EXTRALEN(cc[-1]); -#endif - break; - - CASE_ITERATOR_TYPE_PRIVATE_DATA_1 - if (PRIVATE_DATA(cc)) - { - count = 1; - srcw[0] = PRIVATE_DATA(cc); - } - cc += 1; - break; - - CASE_ITERATOR_TYPE_PRIVATE_DATA_2A - if (PRIVATE_DATA(cc)) - { - count = 2; - srcw[0] = PRIVATE_DATA(cc); - srcw[1] = srcw[0] + sizeof(sljit_sw); - } - cc += 1; - break; - - CASE_ITERATOR_TYPE_PRIVATE_DATA_2B - if (PRIVATE_DATA(cc)) - { - count = 2; - srcw[0] = PRIVATE_DATA(cc); - srcw[1] = srcw[0] + sizeof(sljit_sw); - } - cc += 1 + IMM2_SIZE; - break; - - case OP_CLASS: - case OP_NCLASS: -#if defined SUPPORT_UTF || !defined COMPILE_PCRE8 - case OP_XCLASS: - size = (*cc == OP_XCLASS) ? GET(cc, 1) : 1 + 32 / (int)sizeof(pcre_uchar); -#else - size = 1 + 32 / (int)sizeof(pcre_uchar); -#endif - if (PRIVATE_DATA(cc)) - switch(get_class_iterator_size(cc + size)) - { - case 1: - count = 1; - srcw[0] = PRIVATE_DATA(cc); - break; - - case 2: - count = 2; - srcw[0] = PRIVATE_DATA(cc); - srcw[1] = srcw[0] + sizeof(sljit_sw); - break; - - default: - SLJIT_ASSERT_STOP(); - break; - } - cc += size; - break; - - default: - cc = next_opcode(common, cc); - SLJIT_ASSERT(cc != NULL); - break; - } - break; - - case end: - SLJIT_ASSERT_STOP(); - break; - } - - while (count > 0) - { - count--; - if (save) - { - if (tmp1next) - { - if (!tmp1empty) - { - OP1(SLJIT_MOV, SLJIT_MEM1(STACK_TOP), stackptr, TMP1, 0); - stackptr += sizeof(sljit_sw); - } - OP1(SLJIT_MOV, TMP1, 0, SLJIT_MEM1(SLJIT_SP), srcw[count]); - tmp1empty = FALSE; - tmp1next = FALSE; - } - else - { - if (!tmp2empty) - { - OP1(SLJIT_MOV, SLJIT_MEM1(STACK_TOP), stackptr, TMP2, 0); - stackptr += sizeof(sljit_sw); - } - OP1(SLJIT_MOV, TMP2, 0, SLJIT_MEM1(SLJIT_SP), srcw[count]); - tmp2empty = FALSE; - tmp1next = TRUE; - } - } - else - { - if (tmp1next) - { - SLJIT_ASSERT(!tmp1empty); - OP1(SLJIT_MOV, SLJIT_MEM1(SLJIT_SP), srcw[count], TMP1, 0); - tmp1empty = stackptr >= stacktop; - if (!tmp1empty) - { - OP1(SLJIT_MOV, TMP1, 0, SLJIT_MEM1(STACK_TOP), stackptr); - stackptr += sizeof(sljit_sw); - } - tmp1next = FALSE; - } - else - { - SLJIT_ASSERT(!tmp2empty); - OP1(SLJIT_MOV, SLJIT_MEM1(SLJIT_SP), srcw[count], TMP2, 0); - tmp2empty = stackptr >= stacktop; - if (!tmp2empty) - { - OP1(SLJIT_MOV, TMP2, 0, SLJIT_MEM1(STACK_TOP), stackptr); - stackptr += sizeof(sljit_sw); - } - tmp1next = TRUE; - } - } - } - } -while (status != end); - -if (save) - { - if (tmp1next) - { - if (!tmp1empty) - { - OP1(SLJIT_MOV, SLJIT_MEM1(STACK_TOP), stackptr, TMP1, 0); - stackptr += sizeof(sljit_sw); - } - if (!tmp2empty) - { - OP1(SLJIT_MOV, SLJIT_MEM1(STACK_TOP), stackptr, TMP2, 0); - stackptr += sizeof(sljit_sw); - } - } - else - { - if (!tmp2empty) - { - OP1(SLJIT_MOV, SLJIT_MEM1(STACK_TOP), stackptr, TMP2, 0); - stackptr += sizeof(sljit_sw); - } - if (!tmp1empty) - { - OP1(SLJIT_MOV, SLJIT_MEM1(STACK_TOP), stackptr, TMP1, 0); - stackptr += sizeof(sljit_sw); - } - } - } -SLJIT_ASSERT(cc == ccend && stackptr == stacktop && (save || (tmp1empty && tmp2empty))); -} - -static SLJIT_INLINE pcre_uchar *set_then_offsets(compiler_common *common, pcre_uchar *cc, pcre_uint8 *current_offset) -{ -pcre_uchar *end = bracketend(cc); -BOOL has_alternatives = cc[GET(cc, 1)] == OP_ALT; - -/* Assert captures then. */ -if (*cc >= OP_ASSERT && *cc <= OP_ASSERTBACK_NOT) - current_offset = NULL; -/* Conditional block does not. */ -if (*cc == OP_COND || *cc == OP_SCOND) - has_alternatives = FALSE; - -cc = next_opcode(common, cc); -if (has_alternatives) - current_offset = common->then_offsets + (cc - common->start); - -while (cc < end) - { - if ((*cc >= OP_ASSERT && *cc <= OP_ASSERTBACK_NOT) || (*cc >= OP_ONCE && *cc <= OP_SCOND)) - cc = set_then_offsets(common, cc, current_offset); - else - { - if (*cc == OP_ALT && has_alternatives) - current_offset = common->then_offsets + (cc + 1 + LINK_SIZE - common->start); - if (*cc >= OP_THEN && *cc <= OP_THEN_ARG && current_offset != NULL) - *current_offset = 1; - cc = next_opcode(common, cc); - } - } - -return end; -} - -#undef CASE_ITERATOR_PRIVATE_DATA_1 -#undef CASE_ITERATOR_PRIVATE_DATA_2A -#undef CASE_ITERATOR_PRIVATE_DATA_2B -#undef CASE_ITERATOR_TYPE_PRIVATE_DATA_1 -#undef CASE_ITERATOR_TYPE_PRIVATE_DATA_2A -#undef CASE_ITERATOR_TYPE_PRIVATE_DATA_2B - -static SLJIT_INLINE BOOL is_powerof2(unsigned int value) -{ -return (value & (value - 1)) == 0; -} - -static SLJIT_INLINE void set_jumps(jump_list *list, struct sljit_label *label) -{ -while (list) - { - /* sljit_set_label is clever enough to do nothing - if either the jump or the label is NULL. */ - SET_LABEL(list->jump, label); - list = list->next; - } -} - -static SLJIT_INLINE void add_jump(struct sljit_compiler *compiler, jump_list **list, struct sljit_jump *jump) -{ -jump_list *list_item = sljit_alloc_memory(compiler, sizeof(jump_list)); -if (list_item) - { - list_item->next = *list; - list_item->jump = jump; - *list = list_item; - } -} - -static void add_stub(compiler_common *common, struct sljit_jump *start) -{ -DEFINE_COMPILER; -stub_list *list_item = sljit_alloc_memory(compiler, sizeof(stub_list)); - -if (list_item) - { - list_item->start = start; - list_item->quit = LABEL(); - list_item->next = common->stubs; - common->stubs = list_item; - } -} - -static void flush_stubs(compiler_common *common) -{ -DEFINE_COMPILER; -stub_list *list_item = common->stubs; - -while (list_item) - { - JUMPHERE(list_item->start); - add_jump(compiler, &common->stackalloc, JUMP(SLJIT_FAST_CALL)); - JUMPTO(SLJIT_JUMP, list_item->quit); - list_item = list_item->next; - } -common->stubs = NULL; -} - -static void add_label_addr(compiler_common *common, sljit_uw *update_addr) -{ -DEFINE_COMPILER; -label_addr_list *label_addr; - -label_addr = sljit_alloc_memory(compiler, sizeof(label_addr_list)); -if (label_addr == NULL) - return; -label_addr->label = LABEL(); -label_addr->update_addr = update_addr; -label_addr->next = common->label_addrs; -common->label_addrs = label_addr; -} - -static SLJIT_INLINE void count_match(compiler_common *common) -{ -DEFINE_COMPILER; - -OP2(SLJIT_SUB | SLJIT_SET_E, COUNT_MATCH, 0, COUNT_MATCH, 0, SLJIT_IMM, 1); -add_jump(compiler, &common->calllimit, JUMP(SLJIT_ZERO)); -} - -static SLJIT_INLINE void allocate_stack(compiler_common *common, int size) -{ -/* May destroy all locals and registers except TMP2. */ -DEFINE_COMPILER; - -OP2(SLJIT_ADD, STACK_TOP, 0, STACK_TOP, 0, SLJIT_IMM, size * sizeof(sljit_sw)); -#ifdef DESTROY_REGISTERS -OP1(SLJIT_MOV, TMP1, 0, SLJIT_IMM, 12345); -OP1(SLJIT_MOV, TMP3, 0, TMP1, 0); -OP1(SLJIT_MOV, RETURN_ADDR, 0, TMP1, 0); -OP1(SLJIT_MOV, SLJIT_MEM1(SLJIT_SP), LOCALS0, TMP1, 0); -OP1(SLJIT_MOV, SLJIT_MEM1(SLJIT_SP), LOCALS1, TMP1, 0); -#endif -add_stub(common, CMP(SLJIT_GREATER, STACK_TOP, 0, STACK_LIMIT, 0)); -} - -static SLJIT_INLINE void free_stack(compiler_common *common, int size) -{ -DEFINE_COMPILER; -OP2(SLJIT_SUB, STACK_TOP, 0, STACK_TOP, 0, SLJIT_IMM, size * sizeof(sljit_sw)); -} - -static sljit_uw * allocate_read_only_data(compiler_common *common, sljit_uw size) -{ -DEFINE_COMPILER; -sljit_uw *result; - -if (SLJIT_UNLIKELY(sljit_get_compiler_error(compiler))) - return NULL; - -result = (sljit_uw *)SLJIT_MALLOC(size + sizeof(sljit_uw), compiler->allocator_data); -if (SLJIT_UNLIKELY(result == NULL)) - { - sljit_set_compiler_memory_error(compiler); - return NULL; - } - -*(void**)result = common->read_only_data_head; -common->read_only_data_head = (void *)result; -return result + 1; -} - -static void free_read_only_data(void *current, void *allocator_data) -{ -void *next; - -SLJIT_UNUSED_ARG(allocator_data); - -while (current != NULL) - { - next = *(void**)current; - SLJIT_FREE(current, allocator_data); - current = next; - } -} - -static SLJIT_INLINE void reset_ovector(compiler_common *common, int length) -{ -DEFINE_COMPILER; -struct sljit_label *loop; -int i; - -/* At this point we can freely use all temporary registers. */ -SLJIT_ASSERT(length > 1); -/* TMP1 returns with begin - 1. */ -OP2(SLJIT_SUB, SLJIT_R0, 0, SLJIT_MEM1(SLJIT_S0), SLJIT_OFFSETOF(jit_arguments, begin), SLJIT_IMM, IN_UCHARS(1)); -if (length < 8) - { - for (i = 1; i < length; i++) - OP1(SLJIT_MOV, SLJIT_MEM1(SLJIT_SP), OVECTOR(i), SLJIT_R0, 0); - } -else - { - GET_LOCAL_BASE(SLJIT_R1, 0, OVECTOR_START); - OP1(SLJIT_MOV, SLJIT_R2, 0, SLJIT_IMM, length - 1); - loop = LABEL(); - OP1(SLJIT_MOVU, SLJIT_MEM1(SLJIT_R1), sizeof(sljit_sw), SLJIT_R0, 0); - OP2(SLJIT_SUB | SLJIT_SET_E, SLJIT_R2, 0, SLJIT_R2, 0, SLJIT_IMM, 1); - JUMPTO(SLJIT_NOT_ZERO, loop); - } -} - -static SLJIT_INLINE void do_reset_match(compiler_common *common, int length) -{ -DEFINE_COMPILER; -struct sljit_label *loop; -int i; - -SLJIT_ASSERT(length > 1); -/* OVECTOR(1) contains the "string begin - 1" constant. */ -if (length > 2) - OP1(SLJIT_MOV, TMP1, 0, SLJIT_MEM1(SLJIT_SP), OVECTOR(1)); -if (length < 8) - { - for (i = 2; i < length; i++) - OP1(SLJIT_MOV, SLJIT_MEM1(SLJIT_SP), OVECTOR(i), TMP1, 0); - } -else - { - GET_LOCAL_BASE(TMP2, 0, OVECTOR_START + sizeof(sljit_sw)); - OP1(SLJIT_MOV, STACK_TOP, 0, SLJIT_IMM, length - 2); - loop = LABEL(); - OP1(SLJIT_MOVU, SLJIT_MEM1(TMP2), sizeof(sljit_sw), TMP1, 0); - OP2(SLJIT_SUB | SLJIT_SET_E, STACK_TOP, 0, STACK_TOP, 0, SLJIT_IMM, 1); - JUMPTO(SLJIT_NOT_ZERO, loop); - } - -OP1(SLJIT_MOV, STACK_TOP, 0, ARGUMENTS, 0); -if (common->mark_ptr != 0) - OP1(SLJIT_MOV, SLJIT_MEM1(SLJIT_SP), common->mark_ptr, SLJIT_IMM, 0); -if (common->control_head_ptr != 0) - OP1(SLJIT_MOV, SLJIT_MEM1(SLJIT_SP), common->control_head_ptr, SLJIT_IMM, 0); -OP1(SLJIT_MOV, STACK_TOP, 0, SLJIT_MEM1(STACK_TOP), SLJIT_OFFSETOF(jit_arguments, stack)); -OP1(SLJIT_MOV, TMP1, 0, SLJIT_MEM1(SLJIT_SP), common->start_ptr); -OP1(SLJIT_MOV, STACK_TOP, 0, SLJIT_MEM1(STACK_TOP), SLJIT_OFFSETOF(struct sljit_stack, base)); -} - -static sljit_sw SLJIT_CALL do_search_mark(sljit_sw *current, const pcre_uchar *skip_arg) -{ -while (current != NULL) - { - switch (current[-2]) - { - case type_then_trap: - break; - - case type_mark: - if (STRCMP_UC_UC(skip_arg, (pcre_uchar *)current[-3]) == 0) - return current[-4]; - break; - - default: - SLJIT_ASSERT_STOP(); - break; - } - SLJIT_ASSERT(current > (sljit_sw*)current[-1]); - current = (sljit_sw*)current[-1]; - } -return -1; -} - -static SLJIT_INLINE void copy_ovector(compiler_common *common, int topbracket) -{ -DEFINE_COMPILER; -struct sljit_label *loop; -struct sljit_jump *early_quit; - -/* At this point we can freely use all registers. */ -OP1(SLJIT_MOV, SLJIT_S2, 0, SLJIT_MEM1(SLJIT_SP), OVECTOR(1)); -OP1(SLJIT_MOV, SLJIT_MEM1(SLJIT_SP), OVECTOR(1), STR_PTR, 0); - -OP1(SLJIT_MOV, SLJIT_R0, 0, ARGUMENTS, 0); -if (common->mark_ptr != 0) - OP1(SLJIT_MOV, SLJIT_R2, 0, SLJIT_MEM1(SLJIT_SP), common->mark_ptr); -OP1(SLJIT_MOV_SI, SLJIT_R1, 0, SLJIT_MEM1(SLJIT_R0), SLJIT_OFFSETOF(jit_arguments, offset_count)); -if (common->mark_ptr != 0) - OP1(SLJIT_MOV, SLJIT_MEM1(SLJIT_R0), SLJIT_OFFSETOF(jit_arguments, mark_ptr), SLJIT_R2, 0); -OP2(SLJIT_SUB, SLJIT_R2, 0, SLJIT_MEM1(SLJIT_R0), SLJIT_OFFSETOF(jit_arguments, offsets), SLJIT_IMM, sizeof(int)); -OP1(SLJIT_MOV, SLJIT_R0, 0, SLJIT_MEM1(SLJIT_R0), SLJIT_OFFSETOF(jit_arguments, begin)); -GET_LOCAL_BASE(SLJIT_S0, 0, OVECTOR_START); -/* Unlikely, but possible */ -early_quit = CMP(SLJIT_EQUAL, SLJIT_R1, 0, SLJIT_IMM, 0); -loop = LABEL(); -OP2(SLJIT_SUB, SLJIT_S1, 0, SLJIT_MEM1(SLJIT_S0), 0, SLJIT_R0, 0); -OP2(SLJIT_ADD, SLJIT_S0, 0, SLJIT_S0, 0, SLJIT_IMM, sizeof(sljit_sw)); -/* Copy the integer value to the output buffer */ -#if defined COMPILE_PCRE16 || defined COMPILE_PCRE32 -OP2(SLJIT_ASHR, SLJIT_S1, 0, SLJIT_S1, 0, SLJIT_IMM, UCHAR_SHIFT); -#endif -OP1(SLJIT_MOVU_SI, SLJIT_MEM1(SLJIT_R2), sizeof(int), SLJIT_S1, 0); -OP2(SLJIT_SUB | SLJIT_SET_E, SLJIT_R1, 0, SLJIT_R1, 0, SLJIT_IMM, 1); -JUMPTO(SLJIT_NOT_ZERO, loop); -JUMPHERE(early_quit); - -/* Calculate the return value, which is the maximum ovector value. */ -if (topbracket > 1) - { - GET_LOCAL_BASE(SLJIT_R0, 0, OVECTOR_START + topbracket * 2 * sizeof(sljit_sw)); - OP1(SLJIT_MOV, SLJIT_R1, 0, SLJIT_IMM, topbracket + 1); - - /* OVECTOR(0) is never equal to SLJIT_S2. */ - loop = LABEL(); - OP1(SLJIT_MOVU, SLJIT_R2, 0, SLJIT_MEM1(SLJIT_R0), -(2 * (sljit_sw)sizeof(sljit_sw))); - OP2(SLJIT_SUB, SLJIT_R1, 0, SLJIT_R1, 0, SLJIT_IMM, 1); - CMPTO(SLJIT_EQUAL, SLJIT_R2, 0, SLJIT_S2, 0, loop); - OP1(SLJIT_MOV, SLJIT_RETURN_REG, 0, SLJIT_R1, 0); - } -else - OP1(SLJIT_MOV, SLJIT_RETURN_REG, 0, SLJIT_IMM, 1); -} - -static SLJIT_INLINE void return_with_partial_match(compiler_common *common, struct sljit_label *quit) -{ -DEFINE_COMPILER; -struct sljit_jump *jump; - -SLJIT_COMPILE_ASSERT(STR_END == SLJIT_S1, str_end_must_be_saved_reg2); -SLJIT_ASSERT(common->start_used_ptr != 0 && common->start_ptr != 0 - && (common->mode == JIT_PARTIAL_SOFT_COMPILE ? common->hit_start != 0 : common->hit_start == 0)); - -OP1(SLJIT_MOV, SLJIT_R1, 0, ARGUMENTS, 0); -OP1(SLJIT_MOV, SLJIT_RETURN_REG, 0, SLJIT_IMM, PCRE_ERROR_PARTIAL); -OP1(SLJIT_MOV_SI, SLJIT_R2, 0, SLJIT_MEM1(SLJIT_R1), SLJIT_OFFSETOF(jit_arguments, real_offset_count)); -CMPTO(SLJIT_SIG_LESS, SLJIT_R2, 0, SLJIT_IMM, 2, quit); - -/* Store match begin and end. */ -OP1(SLJIT_MOV, SLJIT_S0, 0, SLJIT_MEM1(SLJIT_R1), SLJIT_OFFSETOF(jit_arguments, begin)); -OP1(SLJIT_MOV, SLJIT_R1, 0, SLJIT_MEM1(SLJIT_R1), SLJIT_OFFSETOF(jit_arguments, offsets)); - -jump = CMP(SLJIT_SIG_LESS, SLJIT_R2, 0, SLJIT_IMM, 3); -OP2(SLJIT_SUB, SLJIT_R2, 0, SLJIT_MEM1(SLJIT_SP), common->mode == JIT_PARTIAL_HARD_COMPILE ? common->start_ptr : (common->hit_start + (int)sizeof(sljit_sw)), SLJIT_S0, 0); -#if defined COMPILE_PCRE16 || defined COMPILE_PCRE32 -OP2(SLJIT_ASHR, SLJIT_R2, 0, SLJIT_R2, 0, SLJIT_IMM, UCHAR_SHIFT); -#endif -OP1(SLJIT_MOV_SI, SLJIT_MEM1(SLJIT_R1), 2 * sizeof(int), SLJIT_R2, 0); -JUMPHERE(jump); - -OP1(SLJIT_MOV, SLJIT_R2, 0, SLJIT_MEM1(SLJIT_SP), common->mode == JIT_PARTIAL_HARD_COMPILE ? common->start_used_ptr : common->hit_start); -OP2(SLJIT_SUB, SLJIT_S1, 0, STR_END, 0, SLJIT_S0, 0); -#if defined COMPILE_PCRE16 || defined COMPILE_PCRE32 -OP2(SLJIT_ASHR, SLJIT_S1, 0, SLJIT_S1, 0, SLJIT_IMM, UCHAR_SHIFT); -#endif -OP1(SLJIT_MOV_SI, SLJIT_MEM1(SLJIT_R1), sizeof(int), SLJIT_S1, 0); - -OP2(SLJIT_SUB, SLJIT_R2, 0, SLJIT_R2, 0, SLJIT_S0, 0); -#if defined COMPILE_PCRE16 || defined COMPILE_PCRE32 -OP2(SLJIT_ASHR, SLJIT_R2, 0, SLJIT_R2, 0, SLJIT_IMM, UCHAR_SHIFT); -#endif -OP1(SLJIT_MOV_SI, SLJIT_MEM1(SLJIT_R1), 0, SLJIT_R2, 0); - -JUMPTO(SLJIT_JUMP, quit); -} - -static SLJIT_INLINE void check_start_used_ptr(compiler_common *common) -{ -/* May destroy TMP1. */ -DEFINE_COMPILER; -struct sljit_jump *jump; - -if (common->mode == JIT_PARTIAL_SOFT_COMPILE) - { - /* The value of -1 must be kept for start_used_ptr! */ - OP2(SLJIT_ADD, TMP1, 0, SLJIT_MEM1(SLJIT_SP), common->start_used_ptr, SLJIT_IMM, 1); - /* Jumps if start_used_ptr < STR_PTR, or start_used_ptr == -1. Although overwriting - is not necessary if start_used_ptr == STR_PTR, it does not hurt as well. */ - jump = CMP(SLJIT_LESS_EQUAL, TMP1, 0, STR_PTR, 0); - OP1(SLJIT_MOV, SLJIT_MEM1(SLJIT_SP), common->start_used_ptr, STR_PTR, 0); - JUMPHERE(jump); - } -else if (common->mode == JIT_PARTIAL_HARD_COMPILE) - { - jump = CMP(SLJIT_LESS_EQUAL, SLJIT_MEM1(SLJIT_SP), common->start_used_ptr, STR_PTR, 0); - OP1(SLJIT_MOV, SLJIT_MEM1(SLJIT_SP), common->start_used_ptr, STR_PTR, 0); - JUMPHERE(jump); - } -} - -static SLJIT_INLINE BOOL char_has_othercase(compiler_common *common, pcre_uchar *cc) -{ -/* Detects if the character has an othercase. */ -unsigned int c; - -#ifdef SUPPORT_UTF -if (common->utf) - { - GETCHAR(c, cc); - if (c > 127) - { -#ifdef SUPPORT_UCP - return c != UCD_OTHERCASE(c); -#else - return FALSE; -#endif - } -#ifndef COMPILE_PCRE8 - return common->fcc[c] != c; -#endif - } -else -#endif - c = *cc; -return MAX_255(c) ? common->fcc[c] != c : FALSE; -} - -static SLJIT_INLINE unsigned int char_othercase(compiler_common *common, unsigned int c) -{ -/* Returns with the othercase. */ -#ifdef SUPPORT_UTF -if (common->utf && c > 127) - { -#ifdef SUPPORT_UCP - return UCD_OTHERCASE(c); -#else - return c; -#endif - } -#endif -return TABLE_GET(c, common->fcc, c); -} - -static unsigned int char_get_othercase_bit(compiler_common *common, pcre_uchar *cc) -{ -/* Detects if the character and its othercase has only 1 bit difference. */ -unsigned int c, oc, bit; -#if defined SUPPORT_UTF && defined COMPILE_PCRE8 -int n; -#endif - -#ifdef SUPPORT_UTF -if (common->utf) - { - GETCHAR(c, cc); - if (c <= 127) - oc = common->fcc[c]; - else - { -#ifdef SUPPORT_UCP - oc = UCD_OTHERCASE(c); -#else - oc = c; -#endif - } - } -else - { - c = *cc; - oc = TABLE_GET(c, common->fcc, c); - } -#else -c = *cc; -oc = TABLE_GET(c, common->fcc, c); -#endif - -SLJIT_ASSERT(c != oc); - -bit = c ^ oc; -/* Optimized for English alphabet. */ -if (c <= 127 && bit == 0x20) - return (0 << 8) | 0x20; - -/* Since c != oc, they must have at least 1 bit difference. */ -if (!is_powerof2(bit)) - return 0; - -#if defined COMPILE_PCRE8 - -#ifdef SUPPORT_UTF -if (common->utf && c > 127) - { - n = GET_EXTRALEN(*cc); - while ((bit & 0x3f) == 0) - { - n--; - bit >>= 6; - } - return (n << 8) | bit; - } -#endif /* SUPPORT_UTF */ -return (0 << 8) | bit; - -#elif defined COMPILE_PCRE16 || defined COMPILE_PCRE32 - -#ifdef SUPPORT_UTF -if (common->utf && c > 65535) - { - if (bit >= (1 << 10)) - bit >>= 10; - else - return (bit < 256) ? ((2 << 8) | bit) : ((3 << 8) | (bit >> 8)); - } -#endif /* SUPPORT_UTF */ -return (bit < 256) ? ((0 << 8) | bit) : ((1 << 8) | (bit >> 8)); - -#endif /* COMPILE_PCRE[8|16|32] */ -} - -static void check_partial(compiler_common *common, BOOL force) -{ -/* Checks whether a partial matching is occurred. Does not modify registers. */ -DEFINE_COMPILER; -struct sljit_jump *jump = NULL; - -SLJIT_ASSERT(!force || common->mode != JIT_COMPILE); - -if (common->mode == JIT_COMPILE) - return; - -if (!force) - jump = CMP(SLJIT_GREATER_EQUAL, SLJIT_MEM1(SLJIT_SP), common->start_used_ptr, STR_PTR, 0); -else if (common->mode == JIT_PARTIAL_SOFT_COMPILE) - jump = CMP(SLJIT_EQUAL, SLJIT_MEM1(SLJIT_SP), common->start_used_ptr, SLJIT_IMM, -1); - -if (common->mode == JIT_PARTIAL_SOFT_COMPILE) - OP1(SLJIT_MOV, SLJIT_MEM1(SLJIT_SP), common->hit_start, SLJIT_IMM, 0); -else - { - if (common->partialmatchlabel != NULL) - JUMPTO(SLJIT_JUMP, common->partialmatchlabel); - else - add_jump(compiler, &common->partialmatch, JUMP(SLJIT_JUMP)); - } - -if (jump != NULL) - JUMPHERE(jump); -} - -static void check_str_end(compiler_common *common, jump_list **end_reached) -{ -/* Does not affect registers. Usually used in a tight spot. */ -DEFINE_COMPILER; -struct sljit_jump *jump; - -if (common->mode == JIT_COMPILE) - { - add_jump(compiler, end_reached, CMP(SLJIT_GREATER_EQUAL, STR_PTR, 0, STR_END, 0)); - return; - } - -jump = CMP(SLJIT_LESS, STR_PTR, 0, STR_END, 0); -if (common->mode == JIT_PARTIAL_SOFT_COMPILE) - { - add_jump(compiler, end_reached, CMP(SLJIT_GREATER_EQUAL, SLJIT_MEM1(SLJIT_SP), common->start_used_ptr, STR_PTR, 0)); - OP1(SLJIT_MOV, SLJIT_MEM1(SLJIT_SP), common->hit_start, SLJIT_IMM, 0); - add_jump(compiler, end_reached, JUMP(SLJIT_JUMP)); - } -else - { - add_jump(compiler, end_reached, CMP(SLJIT_GREATER_EQUAL, SLJIT_MEM1(SLJIT_SP), common->start_used_ptr, STR_PTR, 0)); - if (common->partialmatchlabel != NULL) - JUMPTO(SLJIT_JUMP, common->partialmatchlabel); - else - add_jump(compiler, &common->partialmatch, JUMP(SLJIT_JUMP)); - } -JUMPHERE(jump); -} - -static void detect_partial_match(compiler_common *common, jump_list **backtracks) -{ -DEFINE_COMPILER; -struct sljit_jump *jump; - -if (common->mode == JIT_COMPILE) - { - add_jump(compiler, backtracks, CMP(SLJIT_GREATER_EQUAL, STR_PTR, 0, STR_END, 0)); - return; - } - -/* Partial matching mode. */ -jump = CMP(SLJIT_LESS, STR_PTR, 0, STR_END, 0); -add_jump(compiler, backtracks, CMP(SLJIT_GREATER_EQUAL, SLJIT_MEM1(SLJIT_SP), common->start_used_ptr, STR_PTR, 0)); -if (common->mode == JIT_PARTIAL_SOFT_COMPILE) - { - OP1(SLJIT_MOV, SLJIT_MEM1(SLJIT_SP), common->hit_start, SLJIT_IMM, 0); - add_jump(compiler, backtracks, JUMP(SLJIT_JUMP)); - } -else - { - if (common->partialmatchlabel != NULL) - JUMPTO(SLJIT_JUMP, common->partialmatchlabel); - else - add_jump(compiler, &common->partialmatch, JUMP(SLJIT_JUMP)); - } -JUMPHERE(jump); -} - -static void peek_char(compiler_common *common, pcre_uint32 max) -{ -/* Reads the character into TMP1, keeps STR_PTR. -Does not check STR_END. TMP2 Destroyed. */ -DEFINE_COMPILER; -#if defined SUPPORT_UTF && !defined COMPILE_PCRE32 -struct sljit_jump *jump; -#endif - -SLJIT_UNUSED_ARG(max); - -OP1(MOV_UCHAR, TMP1, 0, SLJIT_MEM1(STR_PTR), 0); -#if defined SUPPORT_UTF && defined COMPILE_PCRE8 -if (common->utf) - { - if (max < 128) return; - - jump = CMP(SLJIT_LESS, TMP1, 0, SLJIT_IMM, 0xc0); - OP2(SLJIT_ADD, STR_PTR, 0, STR_PTR, 0, SLJIT_IMM, IN_UCHARS(1)); - add_jump(compiler, &common->utfreadchar, JUMP(SLJIT_FAST_CALL)); - OP2(SLJIT_SUB, STR_PTR, 0, STR_PTR, 0, TMP2, 0); - JUMPHERE(jump); - } -#endif /* SUPPORT_UTF && !COMPILE_PCRE32 */ - -#if defined SUPPORT_UTF && defined COMPILE_PCRE16 -if (common->utf) - { - if (max < 0xd800) return; - - OP2(SLJIT_SUB, TMP2, 0, TMP1, 0, SLJIT_IMM, 0xd800); - jump = CMP(SLJIT_GREATER, TMP2, 0, SLJIT_IMM, 0xdc00 - 0xd800 - 1); - /* TMP2 contains the high surrogate. */ - OP1(MOV_UCHAR, TMP1, 0, SLJIT_MEM1(STR_PTR), IN_UCHARS(0)); - OP2(SLJIT_ADD, TMP2, 0, TMP2, 0, SLJIT_IMM, 0x40); - OP2(SLJIT_SHL, TMP2, 0, TMP2, 0, SLJIT_IMM, 10); - OP2(SLJIT_AND, TMP1, 0, TMP1, 0, SLJIT_IMM, 0x3ff); - OP2(SLJIT_OR, TMP1, 0, TMP1, 0, TMP2, 0); - JUMPHERE(jump); - } -#endif -} - -#if defined SUPPORT_UTF && defined COMPILE_PCRE8 - -static BOOL is_char7_bitset(const pcre_uint8 *bitset, BOOL nclass) -{ -/* Tells whether the character codes below 128 are enough -to determine a match. */ -const pcre_uint8 value = nclass ? 0xff : 0; -const pcre_uint8 *end = bitset + 32; - -bitset += 16; -do - { - if (*bitset++ != value) - return FALSE; - } -while (bitset < end); -return TRUE; -} - -static void read_char7_type(compiler_common *common, BOOL full_read) -{ -/* Reads the precise character type of a character into TMP1, if the character -is less than 128. Otherwise it returns with zero. Does not check STR_END. The -full_read argument tells whether characters above max are accepted or not. */ -DEFINE_COMPILER; -struct sljit_jump *jump; - -SLJIT_ASSERT(common->utf); - -OP1(MOV_UCHAR, TMP2, 0, SLJIT_MEM1(STR_PTR), 0); -OP2(SLJIT_ADD, STR_PTR, 0, STR_PTR, 0, SLJIT_IMM, IN_UCHARS(1)); - -OP1(SLJIT_MOV_UB, TMP1, 0, SLJIT_MEM1(TMP2), common->ctypes); - -if (full_read) - { - jump = CMP(SLJIT_LESS, TMP2, 0, SLJIT_IMM, 0xc0); - OP1(SLJIT_MOV_UB, TMP2, 0, SLJIT_MEM1(TMP2), (sljit_sw)PRIV(utf8_table4) - 0xc0); - OP2(SLJIT_ADD, STR_PTR, 0, STR_PTR, 0, TMP2, 0); - JUMPHERE(jump); - } -} - -#endif /* SUPPORT_UTF && COMPILE_PCRE8 */ - -static void read_char_range(compiler_common *common, pcre_uint32 min, pcre_uint32 max, BOOL update_str_ptr) -{ -/* Reads the precise value of a character into TMP1, if the character is -between min and max (c >= min && c <= max). Otherwise it returns with a value -outside the range. Does not check STR_END. */ -DEFINE_COMPILER; -#if defined SUPPORT_UTF && !defined COMPILE_PCRE32 -struct sljit_jump *jump; -#endif -#if defined SUPPORT_UTF && defined COMPILE_PCRE8 -struct sljit_jump *jump2; -#endif - -SLJIT_UNUSED_ARG(update_str_ptr); -SLJIT_UNUSED_ARG(min); -SLJIT_UNUSED_ARG(max); -SLJIT_ASSERT(min <= max); - -OP1(MOV_UCHAR, TMP1, 0, SLJIT_MEM1(STR_PTR), IN_UCHARS(0)); -OP2(SLJIT_ADD, STR_PTR, 0, STR_PTR, 0, SLJIT_IMM, IN_UCHARS(1)); - -#if defined SUPPORT_UTF && defined COMPILE_PCRE8 -if (common->utf) - { - if (max < 128 && !update_str_ptr) return; - - jump = CMP(SLJIT_LESS, TMP1, 0, SLJIT_IMM, 0xc0); - if (min >= 0x10000) - { - OP2(SLJIT_SUB, TMP2, 0, TMP1, 0, SLJIT_IMM, 0xf0); - if (update_str_ptr) - OP1(SLJIT_MOV_UB, RETURN_ADDR, 0, SLJIT_MEM1(TMP1), (sljit_sw)PRIV(utf8_table4) - 0xc0); - OP1(MOV_UCHAR, TMP1, 0, SLJIT_MEM1(STR_PTR), IN_UCHARS(0)); - jump2 = CMP(SLJIT_GREATER, TMP2, 0, SLJIT_IMM, 0x7); - OP2(SLJIT_SHL, TMP2, 0, TMP2, 0, SLJIT_IMM, 6); - OP2(SLJIT_AND, TMP1, 0, TMP1, 0, SLJIT_IMM, 0x3f); - OP2(SLJIT_OR, TMP1, 0, TMP1, 0, TMP2, 0); - OP1(MOV_UCHAR, TMP2, 0, SLJIT_MEM1(STR_PTR), IN_UCHARS(1)); - OP2(SLJIT_SHL, TMP1, 0, TMP1, 0, SLJIT_IMM, 6); - OP2(SLJIT_AND, TMP2, 0, TMP2, 0, SLJIT_IMM, 0x3f); - OP2(SLJIT_OR, TMP1, 0, TMP1, 0, TMP2, 0); - OP1(MOV_UCHAR, TMP2, 0, SLJIT_MEM1(STR_PTR), IN_UCHARS(2)); - if (!update_str_ptr) - OP2(SLJIT_ADD, STR_PTR, 0, STR_PTR, 0, SLJIT_IMM, IN_UCHARS(3)); - OP2(SLJIT_SHL, TMP1, 0, TMP1, 0, SLJIT_IMM, 6); - OP2(SLJIT_AND, TMP2, 0, TMP2, 0, SLJIT_IMM, 0x3f); - OP2(SLJIT_OR, TMP1, 0, TMP1, 0, TMP2, 0); - JUMPHERE(jump2); - if (update_str_ptr) - OP2(SLJIT_ADD, STR_PTR, 0, STR_PTR, 0, RETURN_ADDR, 0); - } - else if (min >= 0x800 && max <= 0xffff) - { - OP2(SLJIT_SUB, TMP2, 0, TMP1, 0, SLJIT_IMM, 0xe0); - if (update_str_ptr) - OP1(SLJIT_MOV_UB, RETURN_ADDR, 0, SLJIT_MEM1(TMP1), (sljit_sw)PRIV(utf8_table4) - 0xc0); - OP1(MOV_UCHAR, TMP1, 0, SLJIT_MEM1(STR_PTR), IN_UCHARS(0)); - jump2 = CMP(SLJIT_GREATER, TMP2, 0, SLJIT_IMM, 0xf); - OP2(SLJIT_SHL, TMP2, 0, TMP2, 0, SLJIT_IMM, 6); - OP2(SLJIT_AND, TMP1, 0, TMP1, 0, SLJIT_IMM, 0x3f); - OP2(SLJIT_OR, TMP1, 0, TMP1, 0, TMP2, 0); - OP1(MOV_UCHAR, TMP2, 0, SLJIT_MEM1(STR_PTR), IN_UCHARS(1)); - if (!update_str_ptr) - OP2(SLJIT_ADD, STR_PTR, 0, STR_PTR, 0, SLJIT_IMM, IN_UCHARS(2)); - OP2(SLJIT_SHL, TMP1, 0, TMP1, 0, SLJIT_IMM, 6); - OP2(SLJIT_AND, TMP2, 0, TMP2, 0, SLJIT_IMM, 0x3f); - OP2(SLJIT_OR, TMP1, 0, TMP1, 0, TMP2, 0); - JUMPHERE(jump2); - if (update_str_ptr) - OP2(SLJIT_ADD, STR_PTR, 0, STR_PTR, 0, RETURN_ADDR, 0); - } - else if (max >= 0x800) - add_jump(compiler, (max < 0x10000) ? &common->utfreadchar16 : &common->utfreadchar, JUMP(SLJIT_FAST_CALL)); - else if (max < 128) - { - OP1(SLJIT_MOV_UB, TMP2, 0, SLJIT_MEM1(TMP1), (sljit_sw)PRIV(utf8_table4) - 0xc0); - OP2(SLJIT_ADD, STR_PTR, 0, STR_PTR, 0, TMP2, 0); - } - else - { - OP1(MOV_UCHAR, TMP2, 0, SLJIT_MEM1(STR_PTR), IN_UCHARS(0)); - if (!update_str_ptr) - OP2(SLJIT_ADD, STR_PTR, 0, STR_PTR, 0, SLJIT_IMM, IN_UCHARS(1)); - else - OP1(SLJIT_MOV_UB, RETURN_ADDR, 0, SLJIT_MEM1(TMP1), (sljit_sw)PRIV(utf8_table4) - 0xc0); - OP2(SLJIT_AND, TMP1, 0, TMP1, 0, SLJIT_IMM, 0x3f); - OP2(SLJIT_SHL, TMP1, 0, TMP1, 0, SLJIT_IMM, 6); - OP2(SLJIT_AND, TMP2, 0, TMP2, 0, SLJIT_IMM, 0x3f); - OP2(SLJIT_OR, TMP1, 0, TMP1, 0, TMP2, 0); - if (update_str_ptr) - OP2(SLJIT_ADD, STR_PTR, 0, STR_PTR, 0, RETURN_ADDR, 0); - } - JUMPHERE(jump); - } -#endif - -#if defined SUPPORT_UTF && defined COMPILE_PCRE16 -if (common->utf) - { - if (max >= 0x10000) - { - OP2(SLJIT_SUB, TMP2, 0, TMP1, 0, SLJIT_IMM, 0xd800); - jump = CMP(SLJIT_GREATER, TMP2, 0, SLJIT_IMM, 0xdc00 - 0xd800 - 1); - /* TMP2 contains the high surrogate. */ - OP1(MOV_UCHAR, TMP1, 0, SLJIT_MEM1(STR_PTR), IN_UCHARS(0)); - OP2(SLJIT_ADD, TMP2, 0, TMP2, 0, SLJIT_IMM, 0x40); - OP2(SLJIT_SHL, TMP2, 0, TMP2, 0, SLJIT_IMM, 10); - OP2(SLJIT_ADD, STR_PTR, 0, STR_PTR, 0, SLJIT_IMM, IN_UCHARS(1)); - OP2(SLJIT_AND, TMP1, 0, TMP1, 0, SLJIT_IMM, 0x3ff); - OP2(SLJIT_OR, TMP1, 0, TMP1, 0, TMP2, 0); - JUMPHERE(jump); - return; - } - - if (max < 0xd800 && !update_str_ptr) return; - - /* Skip low surrogate if necessary. */ - OP2(SLJIT_SUB, TMP2, 0, TMP1, 0, SLJIT_IMM, 0xd800); - jump = CMP(SLJIT_GREATER, TMP2, 0, SLJIT_IMM, 0xdc00 - 0xd800 - 1); - if (update_str_ptr) - OP2(SLJIT_ADD, STR_PTR, 0, STR_PTR, 0, SLJIT_IMM, IN_UCHARS(1)); - if (max >= 0xd800) - OP1(SLJIT_MOV, TMP1, 0, SLJIT_IMM, 0x10000); - JUMPHERE(jump); - } -#endif -} - -static SLJIT_INLINE void read_char(compiler_common *common) -{ -read_char_range(common, 0, READ_CHAR_MAX, TRUE); -} - -static void read_char8_type(compiler_common *common, BOOL update_str_ptr) -{ -/* Reads the character type into TMP1, updates STR_PTR. Does not check STR_END. */ -DEFINE_COMPILER; -#if defined SUPPORT_UTF || !defined COMPILE_PCRE8 -struct sljit_jump *jump; -#endif -#if defined SUPPORT_UTF && defined COMPILE_PCRE8 -struct sljit_jump *jump2; -#endif - -SLJIT_UNUSED_ARG(update_str_ptr); - -OP1(MOV_UCHAR, TMP2, 0, SLJIT_MEM1(STR_PTR), 0); -OP2(SLJIT_ADD, STR_PTR, 0, STR_PTR, 0, SLJIT_IMM, IN_UCHARS(1)); - -#if defined SUPPORT_UTF && defined COMPILE_PCRE8 -if (common->utf) - { - /* This can be an extra read in some situations, but hopefully - it is needed in most cases. */ - OP1(SLJIT_MOV_UB, TMP1, 0, SLJIT_MEM1(TMP2), common->ctypes); - jump = CMP(SLJIT_LESS, TMP2, 0, SLJIT_IMM, 0xc0); - if (!update_str_ptr) - { - OP1(MOV_UCHAR, TMP1, 0, SLJIT_MEM1(STR_PTR), IN_UCHARS(0)); - OP2(SLJIT_ADD, STR_PTR, 0, STR_PTR, 0, SLJIT_IMM, IN_UCHARS(1)); - OP2(SLJIT_AND, TMP2, 0, TMP2, 0, SLJIT_IMM, 0x3f); - OP2(SLJIT_SHL, TMP2, 0, TMP2, 0, SLJIT_IMM, 6); - OP2(SLJIT_AND, TMP1, 0, TMP1, 0, SLJIT_IMM, 0x3f); - OP2(SLJIT_OR, TMP2, 0, TMP2, 0, TMP1, 0); - OP1(SLJIT_MOV, TMP1, 0, SLJIT_IMM, 0); - jump2 = CMP(SLJIT_GREATER, TMP2, 0, SLJIT_IMM, 255); - OP1(SLJIT_MOV_UB, TMP1, 0, SLJIT_MEM1(TMP2), common->ctypes); - JUMPHERE(jump2); - } - else - add_jump(compiler, &common->utfreadtype8, JUMP(SLJIT_FAST_CALL)); - JUMPHERE(jump); - return; - } -#endif /* SUPPORT_UTF && COMPILE_PCRE8 */ - -#if !defined COMPILE_PCRE8 -/* The ctypes array contains only 256 values. */ -OP1(SLJIT_MOV, TMP1, 0, SLJIT_IMM, 0); -jump = CMP(SLJIT_GREATER, TMP2, 0, SLJIT_IMM, 255); -#endif -OP1(SLJIT_MOV_UB, TMP1, 0, SLJIT_MEM1(TMP2), common->ctypes); -#if !defined COMPILE_PCRE8 -JUMPHERE(jump); -#endif - -#if defined SUPPORT_UTF && defined COMPILE_PCRE16 -if (common->utf && update_str_ptr) - { - /* Skip low surrogate if necessary. */ - OP2(SLJIT_SUB, TMP2, 0, TMP2, 0, SLJIT_IMM, 0xd800); - jump = CMP(SLJIT_GREATER, TMP2, 0, SLJIT_IMM, 0xdc00 - 0xd800 - 1); - OP2(SLJIT_ADD, STR_PTR, 0, STR_PTR, 0, SLJIT_IMM, IN_UCHARS(1)); - JUMPHERE(jump); - } -#endif /* SUPPORT_UTF && COMPILE_PCRE16 */ -} - -static void skip_char_back(compiler_common *common) -{ -/* Goes one character back. Affects STR_PTR and TMP1. Does not check begin. */ -DEFINE_COMPILER; -#if defined SUPPORT_UTF && !defined COMPILE_PCRE32 -#if defined COMPILE_PCRE8 -struct sljit_label *label; - -if (common->utf) - { - label = LABEL(); - OP1(MOV_UCHAR, TMP1, 0, SLJIT_MEM1(STR_PTR), -IN_UCHARS(1)); - OP2(SLJIT_SUB, STR_PTR, 0, STR_PTR, 0, SLJIT_IMM, IN_UCHARS(1)); - OP2(SLJIT_AND, TMP1, 0, TMP1, 0, SLJIT_IMM, 0xc0); - CMPTO(SLJIT_EQUAL, TMP1, 0, SLJIT_IMM, 0x80, label); - return; - } -#elif defined COMPILE_PCRE16 -if (common->utf) - { - OP1(MOV_UCHAR, TMP1, 0, SLJIT_MEM1(STR_PTR), -IN_UCHARS(1)); - OP2(SLJIT_SUB, STR_PTR, 0, STR_PTR, 0, SLJIT_IMM, IN_UCHARS(1)); - /* Skip low surrogate if necessary. */ - OP2(SLJIT_AND, TMP1, 0, TMP1, 0, SLJIT_IMM, 0xfc00); - OP2(SLJIT_SUB | SLJIT_SET_E, SLJIT_UNUSED, 0, TMP1, 0, SLJIT_IMM, 0xdc00); - OP_FLAGS(SLJIT_MOV, TMP1, 0, SLJIT_UNUSED, 0, SLJIT_EQUAL); - OP2(SLJIT_SHL, TMP1, 0, TMP1, 0, SLJIT_IMM, 1); - OP2(SLJIT_SUB, STR_PTR, 0, STR_PTR, 0, TMP1, 0); - return; - } -#endif /* COMPILE_PCRE[8|16] */ -#endif /* SUPPORT_UTF && !COMPILE_PCRE32 */ -OP2(SLJIT_SUB, STR_PTR, 0, STR_PTR, 0, SLJIT_IMM, IN_UCHARS(1)); -} - -static void check_newlinechar(compiler_common *common, int nltype, jump_list **backtracks, BOOL jumpifmatch) -{ -/* Character comes in TMP1. Checks if it is a newline. TMP2 may be destroyed. */ -DEFINE_COMPILER; -struct sljit_jump *jump; - -if (nltype == NLTYPE_ANY) - { - add_jump(compiler, &common->anynewline, JUMP(SLJIT_FAST_CALL)); - add_jump(compiler, backtracks, JUMP(jumpifmatch ? SLJIT_NOT_ZERO : SLJIT_ZERO)); - } -else if (nltype == NLTYPE_ANYCRLF) - { - if (jumpifmatch) - { - add_jump(compiler, backtracks, CMP(SLJIT_EQUAL, TMP1, 0, SLJIT_IMM, CHAR_CR)); - add_jump(compiler, backtracks, CMP(SLJIT_EQUAL, TMP1, 0, SLJIT_IMM, CHAR_NL)); - } - else - { - jump = CMP(SLJIT_EQUAL, TMP1, 0, SLJIT_IMM, CHAR_CR); - add_jump(compiler, backtracks, CMP(SLJIT_NOT_EQUAL, TMP1, 0, SLJIT_IMM, CHAR_NL)); - JUMPHERE(jump); - } - } -else - { - SLJIT_ASSERT(nltype == NLTYPE_FIXED && common->newline < 256); - add_jump(compiler, backtracks, CMP(jumpifmatch ? SLJIT_EQUAL : SLJIT_NOT_EQUAL, TMP1, 0, SLJIT_IMM, common->newline)); - } -} - -#ifdef SUPPORT_UTF - -#if defined COMPILE_PCRE8 -static void do_utfreadchar(compiler_common *common) -{ -/* Fast decoding a UTF-8 character. TMP1 contains the first byte -of the character (>= 0xc0). Return char value in TMP1, length in TMP2. */ -DEFINE_COMPILER; -struct sljit_jump *jump; - -sljit_emit_fast_enter(compiler, RETURN_ADDR, 0); -OP1(MOV_UCHAR, TMP2, 0, SLJIT_MEM1(STR_PTR), IN_UCHARS(0)); -OP2(SLJIT_AND, TMP1, 0, TMP1, 0, SLJIT_IMM, 0x3f); -OP2(SLJIT_SHL, TMP1, 0, TMP1, 0, SLJIT_IMM, 6); -OP2(SLJIT_AND, TMP2, 0, TMP2, 0, SLJIT_IMM, 0x3f); -OP2(SLJIT_OR, TMP1, 0, TMP1, 0, TMP2, 0); - -/* Searching for the first zero. */ -OP2(SLJIT_AND | SLJIT_SET_E, SLJIT_UNUSED, 0, TMP1, 0, SLJIT_IMM, 0x800); -jump = JUMP(SLJIT_NOT_ZERO); -/* Two byte sequence. */ -OP2(SLJIT_ADD, STR_PTR, 0, STR_PTR, 0, SLJIT_IMM, IN_UCHARS(1)); -OP1(SLJIT_MOV, TMP2, 0, SLJIT_IMM, IN_UCHARS(2)); -sljit_emit_fast_return(compiler, RETURN_ADDR, 0); - -JUMPHERE(jump); -OP1(MOV_UCHAR, TMP2, 0, SLJIT_MEM1(STR_PTR), IN_UCHARS(1)); -OP2(SLJIT_XOR, TMP1, 0, TMP1, 0, SLJIT_IMM, 0x800); -OP2(SLJIT_SHL, TMP1, 0, TMP1, 0, SLJIT_IMM, 6); -OP2(SLJIT_AND, TMP2, 0, TMP2, 0, SLJIT_IMM, 0x3f); -OP2(SLJIT_OR, TMP1, 0, TMP1, 0, TMP2, 0); - -OP2(SLJIT_AND | SLJIT_SET_E, SLJIT_UNUSED, 0, TMP1, 0, SLJIT_IMM, 0x10000); -jump = JUMP(SLJIT_NOT_ZERO); -/* Three byte sequence. */ -OP2(SLJIT_ADD, STR_PTR, 0, STR_PTR, 0, SLJIT_IMM, IN_UCHARS(2)); -OP1(SLJIT_MOV, TMP2, 0, SLJIT_IMM, IN_UCHARS(3)); -sljit_emit_fast_return(compiler, RETURN_ADDR, 0); - -/* Four byte sequence. */ -JUMPHERE(jump); -OP1(MOV_UCHAR, TMP2, 0, SLJIT_MEM1(STR_PTR), IN_UCHARS(2)); -OP2(SLJIT_XOR, TMP1, 0, TMP1, 0, SLJIT_IMM, 0x10000); -OP2(SLJIT_SHL, TMP1, 0, TMP1, 0, SLJIT_IMM, 6); -OP2(SLJIT_ADD, STR_PTR, 0, STR_PTR, 0, SLJIT_IMM, IN_UCHARS(3)); -OP2(SLJIT_AND, TMP2, 0, TMP2, 0, SLJIT_IMM, 0x3f); -OP2(SLJIT_OR, TMP1, 0, TMP1, 0, TMP2, 0); -OP1(SLJIT_MOV, TMP2, 0, SLJIT_IMM, IN_UCHARS(4)); -sljit_emit_fast_return(compiler, RETURN_ADDR, 0); -} - -static void do_utfreadchar16(compiler_common *common) -{ -/* Fast decoding a UTF-8 character. TMP1 contains the first byte -of the character (>= 0xc0). Return value in TMP1. */ -DEFINE_COMPILER; -struct sljit_jump *jump; - -sljit_emit_fast_enter(compiler, RETURN_ADDR, 0); -OP1(MOV_UCHAR, TMP2, 0, SLJIT_MEM1(STR_PTR), IN_UCHARS(0)); -OP2(SLJIT_AND, TMP1, 0, TMP1, 0, SLJIT_IMM, 0x3f); -OP2(SLJIT_SHL, TMP1, 0, TMP1, 0, SLJIT_IMM, 6); -OP2(SLJIT_AND, TMP2, 0, TMP2, 0, SLJIT_IMM, 0x3f); -OP2(SLJIT_OR, TMP1, 0, TMP1, 0, TMP2, 0); - -/* Searching for the first zero. */ -OP2(SLJIT_AND | SLJIT_SET_E, SLJIT_UNUSED, 0, TMP1, 0, SLJIT_IMM, 0x800); -jump = JUMP(SLJIT_NOT_ZERO); -/* Two byte sequence. */ -OP2(SLJIT_ADD, STR_PTR, 0, STR_PTR, 0, SLJIT_IMM, IN_UCHARS(1)); -sljit_emit_fast_return(compiler, RETURN_ADDR, 0); - -JUMPHERE(jump); -OP2(SLJIT_AND | SLJIT_SET_E, SLJIT_UNUSED, 0, TMP1, 0, SLJIT_IMM, 0x400); -OP_FLAGS(SLJIT_MOV, TMP2, 0, SLJIT_UNUSED, 0, SLJIT_NOT_ZERO); -/* This code runs only in 8 bit mode. No need to shift the value. */ -OP2(SLJIT_ADD, STR_PTR, 0, STR_PTR, 0, TMP2, 0); -OP1(MOV_UCHAR, TMP2, 0, SLJIT_MEM1(STR_PTR), IN_UCHARS(1)); -OP2(SLJIT_XOR, TMP1, 0, TMP1, 0, SLJIT_IMM, 0x800); -OP2(SLJIT_SHL, TMP1, 0, TMP1, 0, SLJIT_IMM, 6); -OP2(SLJIT_AND, TMP2, 0, TMP2, 0, SLJIT_IMM, 0x3f); -OP2(SLJIT_OR, TMP1, 0, TMP1, 0, TMP2, 0); -/* Three byte sequence. */ -OP2(SLJIT_ADD, STR_PTR, 0, STR_PTR, 0, SLJIT_IMM, IN_UCHARS(2)); -sljit_emit_fast_return(compiler, RETURN_ADDR, 0); -} - -static void do_utfreadtype8(compiler_common *common) -{ -/* Fast decoding a UTF-8 character type. TMP2 contains the first byte -of the character (>= 0xc0). Return value in TMP1. */ -DEFINE_COMPILER; -struct sljit_jump *jump; -struct sljit_jump *compare; - -sljit_emit_fast_enter(compiler, RETURN_ADDR, 0); - -OP2(SLJIT_AND | SLJIT_SET_E, SLJIT_UNUSED, 0, TMP2, 0, SLJIT_IMM, 0x20); -jump = JUMP(SLJIT_NOT_ZERO); -/* Two byte sequence. */ -OP1(MOV_UCHAR, TMP1, 0, SLJIT_MEM1(STR_PTR), IN_UCHARS(0)); -OP2(SLJIT_ADD, STR_PTR, 0, STR_PTR, 0, SLJIT_IMM, IN_UCHARS(1)); -OP2(SLJIT_AND, TMP2, 0, TMP2, 0, SLJIT_IMM, 0x1f); -/* The upper 5 bits are known at this point. */ -compare = CMP(SLJIT_GREATER, TMP2, 0, SLJIT_IMM, 0x3); -OP2(SLJIT_SHL, TMP2, 0, TMP2, 0, SLJIT_IMM, 6); -OP2(SLJIT_AND, TMP1, 0, TMP1, 0, SLJIT_IMM, 0x3f); -OP2(SLJIT_OR, TMP2, 0, TMP2, 0, TMP1, 0); -OP1(SLJIT_MOV_UB, TMP1, 0, SLJIT_MEM1(TMP2), common->ctypes); -sljit_emit_fast_return(compiler, RETURN_ADDR, 0); - -JUMPHERE(compare); -OP1(SLJIT_MOV, TMP1, 0, SLJIT_IMM, 0); -sljit_emit_fast_return(compiler, RETURN_ADDR, 0); - -/* We only have types for characters less than 256. */ -JUMPHERE(jump); -OP1(SLJIT_MOV_UB, TMP2, 0, SLJIT_MEM1(TMP2), (sljit_sw)PRIV(utf8_table4) - 0xc0); -OP1(SLJIT_MOV, TMP1, 0, SLJIT_IMM, 0); -OP2(SLJIT_ADD, STR_PTR, 0, STR_PTR, 0, TMP2, 0); -sljit_emit_fast_return(compiler, RETURN_ADDR, 0); -} - -#endif /* COMPILE_PCRE8 */ - -#endif /* SUPPORT_UTF */ - -#ifdef SUPPORT_UCP - -/* UCD_BLOCK_SIZE must be 128 (see the assert below). */ -#define UCD_BLOCK_MASK 127 -#define UCD_BLOCK_SHIFT 7 - -static void do_getucd(compiler_common *common) -{ -/* Search the UCD record for the character comes in TMP1. -Returns chartype in TMP1 and UCD offset in TMP2. */ -DEFINE_COMPILER; - -SLJIT_ASSERT(UCD_BLOCK_SIZE == 128 && sizeof(ucd_record) == 8); - -sljit_emit_fast_enter(compiler, RETURN_ADDR, 0); -OP2(SLJIT_LSHR, TMP2, 0, TMP1, 0, SLJIT_IMM, UCD_BLOCK_SHIFT); -OP1(SLJIT_MOV_UB, TMP2, 0, SLJIT_MEM1(TMP2), (sljit_sw)PRIV(ucd_stage1)); -OP2(SLJIT_AND, TMP1, 0, TMP1, 0, SLJIT_IMM, UCD_BLOCK_MASK); -OP2(SLJIT_SHL, TMP2, 0, TMP2, 0, SLJIT_IMM, UCD_BLOCK_SHIFT); -OP2(SLJIT_ADD, TMP1, 0, TMP1, 0, TMP2, 0); -OP1(SLJIT_MOV, TMP2, 0, SLJIT_IMM, (sljit_sw)PRIV(ucd_stage2)); -OP1(SLJIT_MOV_UH, TMP2, 0, SLJIT_MEM2(TMP2, TMP1), 1); -OP1(SLJIT_MOV, TMP1, 0, SLJIT_IMM, (sljit_sw)PRIV(ucd_records) + SLJIT_OFFSETOF(ucd_record, chartype)); -OP1(SLJIT_MOV_UB, TMP1, 0, SLJIT_MEM2(TMP1, TMP2), 3); -sljit_emit_fast_return(compiler, RETURN_ADDR, 0); -} -#endif - -static SLJIT_INLINE struct sljit_label *mainloop_entry(compiler_common *common, BOOL hascrorlf, BOOL firstline) -{ -DEFINE_COMPILER; -struct sljit_label *mainloop; -struct sljit_label *newlinelabel = NULL; -struct sljit_jump *start; -struct sljit_jump *end = NULL; -struct sljit_jump *nl = NULL; -#if defined SUPPORT_UTF && !defined COMPILE_PCRE32 -struct sljit_jump *singlechar; -#endif -jump_list *newline = NULL; -BOOL newlinecheck = FALSE; -BOOL readuchar = FALSE; - -if (!(hascrorlf || firstline) && (common->nltype == NLTYPE_ANY || - common->nltype == NLTYPE_ANYCRLF || common->newline > 255)) - newlinecheck = TRUE; - -if (firstline) - { - /* Search for the end of the first line. */ - SLJIT_ASSERT(common->first_line_end != 0); - OP1(SLJIT_MOV, TMP3, 0, STR_PTR, 0); - - if (common->nltype == NLTYPE_FIXED && common->newline > 255) - { - mainloop = LABEL(); - OP2(SLJIT_ADD, STR_PTR, 0, STR_PTR, 0, SLJIT_IMM, IN_UCHARS(1)); - end = CMP(SLJIT_GREATER_EQUAL, STR_PTR, 0, STR_END, 0); - OP1(MOV_UCHAR, TMP1, 0, SLJIT_MEM1(STR_PTR), IN_UCHARS(-1)); - OP1(MOV_UCHAR, TMP2, 0, SLJIT_MEM1(STR_PTR), IN_UCHARS(0)); - CMPTO(SLJIT_NOT_EQUAL, TMP1, 0, SLJIT_IMM, (common->newline >> 8) & 0xff, mainloop); - CMPTO(SLJIT_NOT_EQUAL, TMP2, 0, SLJIT_IMM, common->newline & 0xff, mainloop); - JUMPHERE(end); - OP2(SLJIT_SUB, SLJIT_MEM1(SLJIT_SP), common->first_line_end, STR_PTR, 0, SLJIT_IMM, IN_UCHARS(1)); - } - else - { - end = CMP(SLJIT_GREATER_EQUAL, STR_PTR, 0, STR_END, 0); - mainloop = LABEL(); - /* Continual stores does not cause data dependency. */ - OP1(SLJIT_MOV, SLJIT_MEM1(SLJIT_SP), common->first_line_end, STR_PTR, 0); - read_char_range(common, common->nlmin, common->nlmax, TRUE); - check_newlinechar(common, common->nltype, &newline, TRUE); - CMPTO(SLJIT_LESS, STR_PTR, 0, STR_END, 0, mainloop); - JUMPHERE(end); - OP1(SLJIT_MOV, SLJIT_MEM1(SLJIT_SP), common->first_line_end, STR_PTR, 0); - set_jumps(newline, LABEL()); - } - - OP1(SLJIT_MOV, STR_PTR, 0, TMP3, 0); - } - -start = JUMP(SLJIT_JUMP); - -if (newlinecheck) - { - newlinelabel = LABEL(); - OP2(SLJIT_ADD, STR_PTR, 0, STR_PTR, 0, SLJIT_IMM, IN_UCHARS(1)); - end = CMP(SLJIT_GREATER_EQUAL, STR_PTR, 0, STR_END, 0); - OP1(MOV_UCHAR, TMP1, 0, SLJIT_MEM1(STR_PTR), 0); - OP2(SLJIT_SUB | SLJIT_SET_E, SLJIT_UNUSED, 0, TMP1, 0, SLJIT_IMM, common->newline & 0xff); - OP_FLAGS(SLJIT_MOV, TMP1, 0, SLJIT_UNUSED, 0, SLJIT_EQUAL); -#if defined COMPILE_PCRE16 || defined COMPILE_PCRE32 - OP2(SLJIT_SHL, TMP1, 0, TMP1, 0, SLJIT_IMM, UCHAR_SHIFT); -#endif - OP2(SLJIT_ADD, STR_PTR, 0, STR_PTR, 0, TMP1, 0); - nl = JUMP(SLJIT_JUMP); - } - -mainloop = LABEL(); - -/* Increasing the STR_PTR here requires one less jump in the most common case. */ -#ifdef SUPPORT_UTF -if (common->utf) readuchar = TRUE; -#endif -if (newlinecheck) readuchar = TRUE; - -if (readuchar) - OP1(MOV_UCHAR, TMP1, 0, SLJIT_MEM1(STR_PTR), 0); - -if (newlinecheck) - CMPTO(SLJIT_EQUAL, TMP1, 0, SLJIT_IMM, (common->newline >> 8) & 0xff, newlinelabel); - -OP2(SLJIT_ADD, STR_PTR, 0, STR_PTR, 0, SLJIT_IMM, IN_UCHARS(1)); -#if defined SUPPORT_UTF && !defined COMPILE_PCRE32 -#if defined COMPILE_PCRE8 -if (common->utf) - { - singlechar = CMP(SLJIT_LESS, TMP1, 0, SLJIT_IMM, 0xc0); - OP1(SLJIT_MOV_UB, TMP1, 0, SLJIT_MEM1(TMP1), (sljit_sw)PRIV(utf8_table4) - 0xc0); - OP2(SLJIT_ADD, STR_PTR, 0, STR_PTR, 0, TMP1, 0); - JUMPHERE(singlechar); - } -#elif defined COMPILE_PCRE16 -if (common->utf) - { - singlechar = CMP(SLJIT_LESS, TMP1, 0, SLJIT_IMM, 0xd800); - OP2(SLJIT_AND, TMP1, 0, TMP1, 0, SLJIT_IMM, 0xfc00); - OP2(SLJIT_SUB | SLJIT_SET_E, SLJIT_UNUSED, 0, TMP1, 0, SLJIT_IMM, 0xd800); - OP_FLAGS(SLJIT_MOV, TMP1, 0, SLJIT_UNUSED, 0, SLJIT_EQUAL); - OP2(SLJIT_SHL, TMP1, 0, TMP1, 0, SLJIT_IMM, 1); - OP2(SLJIT_ADD, STR_PTR, 0, STR_PTR, 0, TMP1, 0); - JUMPHERE(singlechar); - } -#endif /* COMPILE_PCRE[8|16] */ -#endif /* SUPPORT_UTF && !COMPILE_PCRE32 */ -JUMPHERE(start); - -if (newlinecheck) - { - JUMPHERE(end); - JUMPHERE(nl); - } - -return mainloop; -} - -#define MAX_N_CHARS 16 -#define MAX_N_BYTES 8 - -static SLJIT_INLINE void add_prefix_byte(pcre_uint8 byte, pcre_uint8 *bytes) -{ -pcre_uint8 len = bytes[0]; -int i; - -if (len == 255) - return; - -if (len == 0) - { - bytes[0] = 1; - bytes[1] = byte; - return; - } - -for (i = len; i > 0; i--) - if (bytes[i] == byte) - return; - -if (len >= MAX_N_BYTES - 1) - { - bytes[0] = 255; - return; - } - -len++; -bytes[len] = byte; -bytes[0] = len; -} - -static int scan_prefix(compiler_common *common, pcre_uchar *cc, pcre_uint32 *chars, pcre_uint8 *bytes, int max_chars, pcre_uint32 *rec_count) -{ -/* Recursive function, which scans prefix literals. */ -BOOL last, any, caseless; -int len, repeat, len_save, consumed = 0; -pcre_uint32 chr, mask; -pcre_uchar *alternative, *cc_save, *oc; -#if defined SUPPORT_UTF && defined COMPILE_PCRE8 -pcre_uchar othercase[8]; -#elif defined SUPPORT_UTF && defined COMPILE_PCRE16 -pcre_uchar othercase[2]; -#else -pcre_uchar othercase[1]; -#endif - -repeat = 1; -while (TRUE) - { - if (*rec_count == 0) - return 0; - (*rec_count)--; - - last = TRUE; - any = FALSE; - caseless = FALSE; - - switch (*cc) - { - case OP_CHARI: - caseless = TRUE; - case OP_CHAR: - last = FALSE; - cc++; - break; - - case OP_SOD: - case OP_SOM: - case OP_SET_SOM: - case OP_NOT_WORD_BOUNDARY: - case OP_WORD_BOUNDARY: - case OP_EODN: - case OP_EOD: - case OP_CIRC: - case OP_CIRCM: - case OP_DOLL: - case OP_DOLLM: - /* Zero width assertions. */ - cc++; - continue; - - case OP_ASSERT: - case OP_ASSERT_NOT: - case OP_ASSERTBACK: - case OP_ASSERTBACK_NOT: - cc = bracketend(cc); - continue; - - case OP_PLUSI: - case OP_MINPLUSI: - case OP_POSPLUSI: - caseless = TRUE; - case OP_PLUS: - case OP_MINPLUS: - case OP_POSPLUS: - cc++; - break; - - case OP_EXACTI: - caseless = TRUE; - case OP_EXACT: - repeat = GET2(cc, 1); - last = FALSE; - cc += 1 + IMM2_SIZE; - break; - - case OP_QUERYI: - case OP_MINQUERYI: - case OP_POSQUERYI: - caseless = TRUE; - case OP_QUERY: - case OP_MINQUERY: - case OP_POSQUERY: - len = 1; - cc++; -#ifdef SUPPORT_UTF - if (common->utf && HAS_EXTRALEN(*cc)) len += GET_EXTRALEN(*cc); -#endif - max_chars = scan_prefix(common, cc + len, chars, bytes, max_chars, rec_count); - if (max_chars == 0) - return consumed; - last = FALSE; - break; - - case OP_KET: - cc += 1 + LINK_SIZE; - continue; - - case OP_ALT: - cc += GET(cc, 1); - continue; - - case OP_ONCE: - case OP_ONCE_NC: - case OP_BRA: - case OP_BRAPOS: - case OP_CBRA: - case OP_CBRAPOS: - alternative = cc + GET(cc, 1); - while (*alternative == OP_ALT) - { - max_chars = scan_prefix(common, alternative + 1 + LINK_SIZE, chars, bytes, max_chars, rec_count); - if (max_chars == 0) - return consumed; - alternative += GET(alternative, 1); - } - - if (*cc == OP_CBRA || *cc == OP_CBRAPOS) - cc += IMM2_SIZE; - cc += 1 + LINK_SIZE; - continue; - - case OP_CLASS: -#if defined SUPPORT_UTF && defined COMPILE_PCRE8 - if (common->utf && !is_char7_bitset((const pcre_uint8 *)(cc + 1), FALSE)) return consumed; -#endif - any = TRUE; - cc += 1 + 32 / sizeof(pcre_uchar); - break; - - case OP_NCLASS: -#if defined SUPPORT_UTF && !defined COMPILE_PCRE32 - if (common->utf) return consumed; -#endif - any = TRUE; - cc += 1 + 32 / sizeof(pcre_uchar); - break; - -#if defined SUPPORT_UTF || !defined COMPILE_PCRE8 - case OP_XCLASS: -#if defined SUPPORT_UTF && !defined COMPILE_PCRE32 - if (common->utf) return consumed; -#endif - any = TRUE; - cc += GET(cc, 1); - break; -#endif - - case OP_DIGIT: -#if defined SUPPORT_UTF && defined COMPILE_PCRE8 - if (common->utf && !is_char7_bitset((const pcre_uint8 *)common->ctypes - cbit_length + cbit_digit, FALSE)) - return consumed; -#endif - any = TRUE; - cc++; - break; - - case OP_WHITESPACE: -#if defined SUPPORT_UTF && defined COMPILE_PCRE8 - if (common->utf && !is_char7_bitset((const pcre_uint8 *)common->ctypes - cbit_length + cbit_space, FALSE)) - return consumed; -#endif - any = TRUE; - cc++; - break; - - case OP_WORDCHAR: -#if defined SUPPORT_UTF && defined COMPILE_PCRE8 - if (common->utf && !is_char7_bitset((const pcre_uint8 *)common->ctypes - cbit_length + cbit_word, FALSE)) - return consumed; -#endif - any = TRUE; - cc++; - break; - - case OP_NOT: - case OP_NOTI: - cc++; - /* Fall through. */ - case OP_NOT_DIGIT: - case OP_NOT_WHITESPACE: - case OP_NOT_WORDCHAR: - case OP_ANY: - case OP_ALLANY: -#if defined SUPPORT_UTF && !defined COMPILE_PCRE32 - if (common->utf) return consumed; -#endif - any = TRUE; - cc++; - break; - -#ifdef SUPPORT_UCP - case OP_NOTPROP: - case OP_PROP: -#if defined SUPPORT_UTF && !defined COMPILE_PCRE32 - if (common->utf) return consumed; -#endif - any = TRUE; - cc += 1 + 2; - break; -#endif - - case OP_TYPEEXACT: - repeat = GET2(cc, 1); - cc += 1 + IMM2_SIZE; - continue; - - case OP_NOTEXACT: - case OP_NOTEXACTI: -#if defined SUPPORT_UTF && !defined COMPILE_PCRE32 - if (common->utf) return consumed; -#endif - any = TRUE; - repeat = GET2(cc, 1); - cc += 1 + IMM2_SIZE + 1; - break; - - default: - return consumed; - } - - if (any) - { -#if defined COMPILE_PCRE8 - mask = 0xff; -#elif defined COMPILE_PCRE16 - mask = 0xffff; -#elif defined COMPILE_PCRE32 - mask = 0xffffffff; -#else - SLJIT_ASSERT_STOP(); -#endif - - do - { - chars[0] = mask; - chars[1] = mask; - bytes[0] = 255; - - consumed++; - if (--max_chars == 0) - return consumed; - chars += 2; - bytes += MAX_N_BYTES; - } - while (--repeat > 0); - - repeat = 1; - continue; - } - - len = 1; -#ifdef SUPPORT_UTF - if (common->utf && HAS_EXTRALEN(*cc)) len += GET_EXTRALEN(*cc); -#endif - - if (caseless && char_has_othercase(common, cc)) - { -#ifdef SUPPORT_UTF - if (common->utf) - { - GETCHAR(chr, cc); - if ((int)PRIV(ord2utf)(char_othercase(common, chr), othercase) != len) - return consumed; - } - else -#endif - { - chr = *cc; - othercase[0] = TABLE_GET(chr, common->fcc, chr); - } - } - else - caseless = FALSE; - - len_save = len; - cc_save = cc; - while (TRUE) - { - oc = othercase; - do - { - chr = *cc; -#ifdef COMPILE_PCRE32 - if (SLJIT_UNLIKELY(chr == NOTACHAR)) - return consumed; -#endif - add_prefix_byte((pcre_uint8)chr, bytes); - - mask = 0; - if (caseless) - { - add_prefix_byte((pcre_uint8)*oc, bytes); - mask = *cc ^ *oc; - chr |= mask; - } - -#ifdef COMPILE_PCRE32 - if (chars[0] == NOTACHAR && chars[1] == 0) -#else - if (chars[0] == NOTACHAR) -#endif - { - chars[0] = chr; - chars[1] = mask; - } - else - { - mask |= chars[0] ^ chr; - chr |= mask; - chars[0] = chr; - chars[1] |= mask; - } - - len--; - consumed++; - if (--max_chars == 0) - return consumed; - chars += 2; - bytes += MAX_N_BYTES; - cc++; - oc++; - } - while (len > 0); - - if (--repeat == 0) - break; - - len = len_save; - cc = cc_save; - } - - repeat = 1; - if (last) - return consumed; - } -} - -static SLJIT_INLINE BOOL fast_forward_first_n_chars(compiler_common *common, BOOL firstline) -{ -DEFINE_COMPILER; -struct sljit_label *start; -struct sljit_jump *quit; -pcre_uint32 chars[MAX_N_CHARS * 2]; -pcre_uint8 bytes[MAX_N_CHARS * MAX_N_BYTES]; -pcre_uint8 ones[MAX_N_CHARS]; -int offsets[3]; -pcre_uint32 mask; -pcre_uint8 *byte_set, *byte_set_end; -int i, max, from; -int range_right = -1, range_len = 3 - 1; -sljit_ub *update_table = NULL; -BOOL in_range; -pcre_uint32 rec_count; - -for (i = 0; i < MAX_N_CHARS; i++) - { - chars[i << 1] = NOTACHAR; - chars[(i << 1) + 1] = 0; - bytes[i * MAX_N_BYTES] = 0; - } - -rec_count = 10000; -max = scan_prefix(common, common->start, chars, bytes, MAX_N_CHARS, &rec_count); - -if (max <= 1) - return FALSE; - -for (i = 0; i < max; i++) - { - mask = chars[(i << 1) + 1]; - ones[i] = ones_in_half_byte[mask & 0xf]; - mask >>= 4; - while (mask != 0) - { - ones[i] += ones_in_half_byte[mask & 0xf]; - mask >>= 4; - } - } - -in_range = FALSE; -from = 0; /* Prevent compiler "uninitialized" warning */ -for (i = 0; i <= max; i++) - { - if (in_range && (i - from) > range_len && (bytes[(i - 1) * MAX_N_BYTES] <= 4)) - { - range_len = i - from; - range_right = i - 1; - } - - if (i < max && bytes[i * MAX_N_BYTES] < 255) - { - if (!in_range) - { - in_range = TRUE; - from = i; - } - } - else if (in_range) - in_range = FALSE; - } - -if (range_right >= 0) - { - update_table = (sljit_ub *)allocate_read_only_data(common, 256); - if (update_table == NULL) - return TRUE; - memset(update_table, IN_UCHARS(range_len), 256); - - for (i = 0; i < range_len; i++) - { - byte_set = bytes + ((range_right - i) * MAX_N_BYTES); - SLJIT_ASSERT(byte_set[0] > 0 && byte_set[0] < 255); - byte_set_end = byte_set + byte_set[0]; - byte_set++; - while (byte_set <= byte_set_end) - { - if (update_table[*byte_set] > IN_UCHARS(i)) - update_table[*byte_set] = IN_UCHARS(i); - byte_set++; - } - } - } - -offsets[0] = -1; -/* Scan forward. */ -for (i = 0; i < max; i++) - if (ones[i] <= 2) { - offsets[0] = i; - break; - } - -if (offsets[0] < 0 && range_right < 0) - return FALSE; - -if (offsets[0] >= 0) - { - /* Scan backward. */ - offsets[1] = -1; - for (i = max - 1; i > offsets[0]; i--) - if (ones[i] <= 2 && i != range_right) - { - offsets[1] = i; - break; - } - - /* This case is handled better by fast_forward_first_char. */ - if (offsets[1] == -1 && offsets[0] == 0 && range_right < 0) - return FALSE; - - offsets[2] = -1; - /* We only search for a middle character if there is no range check. */ - if (offsets[1] >= 0 && range_right == -1) - { - /* Scan from middle. */ - for (i = (offsets[0] + offsets[1]) / 2 + 1; i < offsets[1]; i++) - if (ones[i] <= 2) - { - offsets[2] = i; - break; - } - - if (offsets[2] == -1) - { - for (i = (offsets[0] + offsets[1]) / 2; i > offsets[0]; i--) - if (ones[i] <= 2) - { - offsets[2] = i; - break; - } - } - } - - SLJIT_ASSERT(offsets[1] == -1 || (offsets[0] < offsets[1])); - SLJIT_ASSERT(offsets[2] == -1 || (offsets[0] < offsets[2] && offsets[1] > offsets[2])); - - chars[0] = chars[offsets[0] << 1]; - chars[1] = chars[(offsets[0] << 1) + 1]; - if (offsets[2] >= 0) - { - chars[2] = chars[offsets[2] << 1]; - chars[3] = chars[(offsets[2] << 1) + 1]; - } - if (offsets[1] >= 0) - { - chars[4] = chars[offsets[1] << 1]; - chars[5] = chars[(offsets[1] << 1) + 1]; - } - } - -max -= 1; -if (firstline) - { - SLJIT_ASSERT(common->first_line_end != 0); - OP1(SLJIT_MOV, TMP1, 0, SLJIT_MEM1(SLJIT_SP), common->first_line_end); - OP1(SLJIT_MOV, TMP3, 0, STR_END, 0); - OP2(SLJIT_SUB, STR_END, 0, STR_END, 0, SLJIT_IMM, IN_UCHARS(max)); - quit = CMP(SLJIT_LESS_EQUAL, STR_END, 0, TMP1, 0); - OP1(SLJIT_MOV, STR_END, 0, TMP1, 0); - JUMPHERE(quit); - } -else - OP2(SLJIT_SUB, STR_END, 0, STR_END, 0, SLJIT_IMM, IN_UCHARS(max)); - -#if !(defined SLJIT_CONFIG_X86_32 && SLJIT_CONFIG_X86_32) -if (range_right >= 0) - OP1(SLJIT_MOV, RETURN_ADDR, 0, SLJIT_IMM, (sljit_sw)update_table); -#endif - -start = LABEL(); -quit = CMP(SLJIT_GREATER_EQUAL, STR_PTR, 0, STR_END, 0); - -SLJIT_ASSERT(range_right >= 0 || offsets[0] >= 0); - -if (range_right >= 0) - { -#if defined COMPILE_PCRE8 || (defined SLJIT_LITTLE_ENDIAN && SLJIT_LITTLE_ENDIAN) - OP1(SLJIT_MOV_UB, TMP1, 0, SLJIT_MEM1(STR_PTR), IN_UCHARS(range_right)); -#else - OP1(SLJIT_MOV_UB, TMP1, 0, SLJIT_MEM1(STR_PTR), IN_UCHARS(range_right + 1) - 1); -#endif - -#if !(defined SLJIT_CONFIG_X86_32 && SLJIT_CONFIG_X86_32) - OP1(SLJIT_MOV_UB, TMP1, 0, SLJIT_MEM2(RETURN_ADDR, TMP1), 0); -#else - OP1(SLJIT_MOV_UB, TMP1, 0, SLJIT_MEM1(TMP1), (sljit_sw)update_table); -#endif - OP2(SLJIT_ADD, STR_PTR, 0, STR_PTR, 0, TMP1, 0); - CMPTO(SLJIT_NOT_EQUAL, TMP1, 0, SLJIT_IMM, 0, start); - } - -if (offsets[0] >= 0) - { - OP1(MOV_UCHAR, TMP1, 0, SLJIT_MEM1(STR_PTR), IN_UCHARS(offsets[0])); - if (offsets[1] >= 0) - OP1(MOV_UCHAR, TMP2, 0, SLJIT_MEM1(STR_PTR), IN_UCHARS(offsets[1])); - OP2(SLJIT_ADD, STR_PTR, 0, STR_PTR, 0, SLJIT_IMM, IN_UCHARS(1)); - - if (chars[1] != 0) - OP2(SLJIT_OR, TMP1, 0, TMP1, 0, SLJIT_IMM, chars[1]); - CMPTO(SLJIT_NOT_EQUAL, TMP1, 0, SLJIT_IMM, chars[0], start); - if (offsets[2] >= 0) - OP1(MOV_UCHAR, TMP1, 0, SLJIT_MEM1(STR_PTR), IN_UCHARS(offsets[2] - 1)); - - if (offsets[1] >= 0) - { - if (chars[5] != 0) - OP2(SLJIT_OR, TMP2, 0, TMP2, 0, SLJIT_IMM, chars[5]); - CMPTO(SLJIT_NOT_EQUAL, TMP2, 0, SLJIT_IMM, chars[4], start); - } - - if (offsets[2] >= 0) - { - if (chars[3] != 0) - OP2(SLJIT_OR, TMP1, 0, TMP1, 0, SLJIT_IMM, chars[3]); - CMPTO(SLJIT_NOT_EQUAL, TMP1, 0, SLJIT_IMM, chars[2], start); - } - OP2(SLJIT_SUB, STR_PTR, 0, STR_PTR, 0, SLJIT_IMM, IN_UCHARS(1)); - } - -JUMPHERE(quit); - -if (firstline) - { - if (range_right >= 0) - OP1(SLJIT_MOV, TMP1, 0, SLJIT_MEM1(SLJIT_SP), common->first_line_end); - OP1(SLJIT_MOV, STR_END, 0, TMP3, 0); - if (range_right >= 0) - { - quit = CMP(SLJIT_LESS_EQUAL, STR_PTR, 0, TMP1, 0); - OP1(SLJIT_MOV, STR_PTR, 0, TMP1, 0); - JUMPHERE(quit); - } - } -else - OP2(SLJIT_ADD, STR_END, 0, STR_END, 0, SLJIT_IMM, IN_UCHARS(max)); -return TRUE; -} - -#undef MAX_N_CHARS -#undef MAX_N_BYTES - -static SLJIT_INLINE void fast_forward_first_char(compiler_common *common, pcre_uchar first_char, BOOL caseless, BOOL firstline) -{ -DEFINE_COMPILER; -struct sljit_label *start; -struct sljit_jump *quit; -struct sljit_jump *found; -pcre_uchar oc, bit; - -if (firstline) - { - SLJIT_ASSERT(common->first_line_end != 0); - OP1(SLJIT_MOV, TMP3, 0, STR_END, 0); - OP1(SLJIT_MOV, STR_END, 0, SLJIT_MEM1(SLJIT_SP), common->first_line_end); - } - -start = LABEL(); -quit = CMP(SLJIT_GREATER_EQUAL, STR_PTR, 0, STR_END, 0); -OP1(MOV_UCHAR, TMP1, 0, SLJIT_MEM1(STR_PTR), 0); - -oc = first_char; -if (caseless) - { - oc = TABLE_GET(first_char, common->fcc, first_char); -#if defined SUPPORT_UCP && !(defined COMPILE_PCRE8) - if (first_char > 127 && common->utf) - oc = UCD_OTHERCASE(first_char); -#endif - } -if (first_char == oc) - found = CMP(SLJIT_EQUAL, TMP1, 0, SLJIT_IMM, first_char); -else - { - bit = first_char ^ oc; - if (is_powerof2(bit)) - { - OP2(SLJIT_OR, TMP2, 0, TMP1, 0, SLJIT_IMM, bit); - found = CMP(SLJIT_EQUAL, TMP2, 0, SLJIT_IMM, first_char | bit); - } - else - { - OP2(SLJIT_SUB | SLJIT_SET_E, SLJIT_UNUSED, 0, TMP1, 0, SLJIT_IMM, first_char); - OP_FLAGS(SLJIT_MOV, TMP2, 0, SLJIT_UNUSED, 0, SLJIT_EQUAL); - OP2(SLJIT_SUB | SLJIT_SET_E, SLJIT_UNUSED, 0, TMP1, 0, SLJIT_IMM, oc); - OP_FLAGS(SLJIT_OR | SLJIT_SET_E, TMP2, 0, TMP2, 0, SLJIT_EQUAL); - found = JUMP(SLJIT_NOT_ZERO); - } - } - -OP2(SLJIT_ADD, STR_PTR, 0, STR_PTR, 0, SLJIT_IMM, IN_UCHARS(1)); -JUMPTO(SLJIT_JUMP, start); -JUMPHERE(found); -JUMPHERE(quit); - -if (firstline) - OP1(SLJIT_MOV, STR_END, 0, TMP3, 0); -} - -static SLJIT_INLINE void fast_forward_newline(compiler_common *common, BOOL firstline) -{ -DEFINE_COMPILER; -struct sljit_label *loop; -struct sljit_jump *lastchar; -struct sljit_jump *firstchar; -struct sljit_jump *quit; -struct sljit_jump *foundcr = NULL; -struct sljit_jump *notfoundnl; -jump_list *newline = NULL; - -if (firstline) - { - SLJIT_ASSERT(common->first_line_end != 0); - OP1(SLJIT_MOV, TMP3, 0, STR_END, 0); - OP1(SLJIT_MOV, STR_END, 0, SLJIT_MEM1(SLJIT_SP), common->first_line_end); - } - -if (common->nltype == NLTYPE_FIXED && common->newline > 255) - { - lastchar = CMP(SLJIT_GREATER_EQUAL, STR_PTR, 0, STR_END, 0); - OP1(SLJIT_MOV, TMP1, 0, ARGUMENTS, 0); - OP1(SLJIT_MOV, TMP2, 0, SLJIT_MEM1(TMP1), SLJIT_OFFSETOF(jit_arguments, str)); - OP1(SLJIT_MOV, TMP1, 0, SLJIT_MEM1(TMP1), SLJIT_OFFSETOF(jit_arguments, begin)); - firstchar = CMP(SLJIT_LESS_EQUAL, STR_PTR, 0, TMP2, 0); - - OP2(SLJIT_ADD, TMP1, 0, TMP1, 0, SLJIT_IMM, IN_UCHARS(2)); - OP2(SLJIT_SUB | SLJIT_SET_U, SLJIT_UNUSED, 0, STR_PTR, 0, TMP1, 0); - OP_FLAGS(SLJIT_MOV, TMP2, 0, SLJIT_UNUSED, 0, SLJIT_GREATER_EQUAL); -#if defined COMPILE_PCRE16 || defined COMPILE_PCRE32 - OP2(SLJIT_SHL, TMP2, 0, TMP2, 0, SLJIT_IMM, UCHAR_SHIFT); -#endif - OP2(SLJIT_SUB, STR_PTR, 0, STR_PTR, 0, TMP2, 0); - - loop = LABEL(); - OP2(SLJIT_ADD, STR_PTR, 0, STR_PTR, 0, SLJIT_IMM, IN_UCHARS(1)); - quit = CMP(SLJIT_GREATER_EQUAL, STR_PTR, 0, STR_END, 0); - OP1(MOV_UCHAR, TMP1, 0, SLJIT_MEM1(STR_PTR), IN_UCHARS(-2)); - OP1(MOV_UCHAR, TMP2, 0, SLJIT_MEM1(STR_PTR), IN_UCHARS(-1)); - CMPTO(SLJIT_NOT_EQUAL, TMP1, 0, SLJIT_IMM, (common->newline >> 8) & 0xff, loop); - CMPTO(SLJIT_NOT_EQUAL, TMP2, 0, SLJIT_IMM, common->newline & 0xff, loop); - - JUMPHERE(quit); - JUMPHERE(firstchar); - JUMPHERE(lastchar); - - if (firstline) - OP1(SLJIT_MOV, STR_END, 0, TMP3, 0); - return; - } - -OP1(SLJIT_MOV, TMP1, 0, ARGUMENTS, 0); -OP1(SLJIT_MOV, TMP2, 0, SLJIT_MEM1(TMP1), SLJIT_OFFSETOF(jit_arguments, str)); -firstchar = CMP(SLJIT_LESS_EQUAL, STR_PTR, 0, TMP2, 0); -skip_char_back(common); - -loop = LABEL(); -common->ff_newline_shortcut = loop; - -read_char_range(common, common->nlmin, common->nlmax, TRUE); -lastchar = CMP(SLJIT_GREATER_EQUAL, STR_PTR, 0, STR_END, 0); -if (common->nltype == NLTYPE_ANY || common->nltype == NLTYPE_ANYCRLF) - foundcr = CMP(SLJIT_EQUAL, TMP1, 0, SLJIT_IMM, CHAR_CR); -check_newlinechar(common, common->nltype, &newline, FALSE); -set_jumps(newline, loop); - -if (common->nltype == NLTYPE_ANY || common->nltype == NLTYPE_ANYCRLF) - { - quit = JUMP(SLJIT_JUMP); - JUMPHERE(foundcr); - notfoundnl = CMP(SLJIT_GREATER_EQUAL, STR_PTR, 0, STR_END, 0); - OP1(MOV_UCHAR, TMP1, 0, SLJIT_MEM1(STR_PTR), 0); - OP2(SLJIT_SUB | SLJIT_SET_E, SLJIT_UNUSED, 0, TMP1, 0, SLJIT_IMM, CHAR_NL); - OP_FLAGS(SLJIT_MOV, TMP1, 0, SLJIT_UNUSED, 0, SLJIT_EQUAL); -#if defined COMPILE_PCRE16 || defined COMPILE_PCRE32 - OP2(SLJIT_SHL, TMP1, 0, TMP1, 0, SLJIT_IMM, UCHAR_SHIFT); -#endif - OP2(SLJIT_ADD, STR_PTR, 0, STR_PTR, 0, TMP1, 0); - JUMPHERE(notfoundnl); - JUMPHERE(quit); - } -JUMPHERE(lastchar); -JUMPHERE(firstchar); - -if (firstline) - OP1(SLJIT_MOV, STR_END, 0, TMP3, 0); -} - -static BOOL check_class_ranges(compiler_common *common, const pcre_uint8 *bits, BOOL nclass, BOOL invert, jump_list **backtracks); - -static SLJIT_INLINE void fast_forward_start_bits(compiler_common *common, pcre_uint8 *start_bits, BOOL firstline) -{ -DEFINE_COMPILER; -struct sljit_label *start; -struct sljit_jump *quit; -struct sljit_jump *found = NULL; -jump_list *matches = NULL; -#ifndef COMPILE_PCRE8 -struct sljit_jump *jump; -#endif - -if (firstline) - { - SLJIT_ASSERT(common->first_line_end != 0); - OP1(SLJIT_MOV, RETURN_ADDR, 0, STR_END, 0); - OP1(SLJIT_MOV, STR_END, 0, SLJIT_MEM1(SLJIT_SP), common->first_line_end); - } - -start = LABEL(); -quit = CMP(SLJIT_GREATER_EQUAL, STR_PTR, 0, STR_END, 0); -OP1(MOV_UCHAR, TMP1, 0, SLJIT_MEM1(STR_PTR), 0); -#ifdef SUPPORT_UTF -if (common->utf) - OP1(SLJIT_MOV, TMP3, 0, TMP1, 0); -#endif - -if (!check_class_ranges(common, start_bits, (start_bits[31] & 0x80) != 0, TRUE, &matches)) - { -#ifndef COMPILE_PCRE8 - jump = CMP(SLJIT_LESS, TMP1, 0, SLJIT_IMM, 255); - OP1(SLJIT_MOV, TMP1, 0, SLJIT_IMM, 255); - JUMPHERE(jump); -#endif - OP2(SLJIT_AND, TMP2, 0, TMP1, 0, SLJIT_IMM, 0x7); - OP2(SLJIT_LSHR, TMP1, 0, TMP1, 0, SLJIT_IMM, 3); - OP1(SLJIT_MOV_UB, TMP1, 0, SLJIT_MEM1(TMP1), (sljit_sw)start_bits); - OP2(SLJIT_SHL, TMP2, 0, SLJIT_IMM, 1, TMP2, 0); - OP2(SLJIT_AND | SLJIT_SET_E, SLJIT_UNUSED, 0, TMP1, 0, TMP2, 0); - found = JUMP(SLJIT_NOT_ZERO); - } - -#ifdef SUPPORT_UTF -if (common->utf) - OP1(SLJIT_MOV, TMP1, 0, TMP3, 0); -#endif -OP2(SLJIT_ADD, STR_PTR, 0, STR_PTR, 0, SLJIT_IMM, IN_UCHARS(1)); -#ifdef SUPPORT_UTF -#if defined COMPILE_PCRE8 -if (common->utf) - { - CMPTO(SLJIT_LESS, TMP1, 0, SLJIT_IMM, 0xc0, start); - OP1(SLJIT_MOV_UB, TMP1, 0, SLJIT_MEM1(TMP1), (sljit_sw)PRIV(utf8_table4) - 0xc0); - OP2(SLJIT_ADD, STR_PTR, 0, STR_PTR, 0, TMP1, 0); - } -#elif defined COMPILE_PCRE16 -if (common->utf) - { - CMPTO(SLJIT_LESS, TMP1, 0, SLJIT_IMM, 0xd800, start); - OP2(SLJIT_AND, TMP1, 0, TMP1, 0, SLJIT_IMM, 0xfc00); - OP2(SLJIT_SUB | SLJIT_SET_E, SLJIT_UNUSED, 0, TMP1, 0, SLJIT_IMM, 0xd800); - OP_FLAGS(SLJIT_MOV, TMP1, 0, SLJIT_UNUSED, 0, SLJIT_EQUAL); - OP2(SLJIT_SHL, TMP1, 0, TMP1, 0, SLJIT_IMM, 1); - OP2(SLJIT_ADD, STR_PTR, 0, STR_PTR, 0, TMP1, 0); - } -#endif /* COMPILE_PCRE[8|16] */ -#endif /* SUPPORT_UTF */ -JUMPTO(SLJIT_JUMP, start); -if (found != NULL) - JUMPHERE(found); -if (matches != NULL) - set_jumps(matches, LABEL()); -JUMPHERE(quit); - -if (firstline) - OP1(SLJIT_MOV, STR_END, 0, RETURN_ADDR, 0); -} - -static SLJIT_INLINE struct sljit_jump *search_requested_char(compiler_common *common, pcre_uchar req_char, BOOL caseless, BOOL has_firstchar) -{ -DEFINE_COMPILER; -struct sljit_label *loop; -struct sljit_jump *toolong; -struct sljit_jump *alreadyfound; -struct sljit_jump *found; -struct sljit_jump *foundoc = NULL; -struct sljit_jump *notfound; -pcre_uint32 oc, bit; - -SLJIT_ASSERT(common->req_char_ptr != 0); -OP1(SLJIT_MOV, TMP2, 0, SLJIT_MEM1(SLJIT_SP), common->req_char_ptr); -OP2(SLJIT_ADD, TMP1, 0, STR_PTR, 0, SLJIT_IMM, REQ_BYTE_MAX); -toolong = CMP(SLJIT_LESS, TMP1, 0, STR_END, 0); -alreadyfound = CMP(SLJIT_LESS, STR_PTR, 0, TMP2, 0); - -if (has_firstchar) - OP2(SLJIT_ADD, TMP1, 0, STR_PTR, 0, SLJIT_IMM, IN_UCHARS(1)); -else - OP1(SLJIT_MOV, TMP1, 0, STR_PTR, 0); - -loop = LABEL(); -notfound = CMP(SLJIT_GREATER_EQUAL, TMP1, 0, STR_END, 0); - -OP1(MOV_UCHAR, TMP2, 0, SLJIT_MEM1(TMP1), 0); -oc = req_char; -if (caseless) - { - oc = TABLE_GET(req_char, common->fcc, req_char); -#if defined SUPPORT_UCP && !(defined COMPILE_PCRE8) - if (req_char > 127 && common->utf) - oc = UCD_OTHERCASE(req_char); -#endif - } -if (req_char == oc) - found = CMP(SLJIT_EQUAL, TMP2, 0, SLJIT_IMM, req_char); -else - { - bit = req_char ^ oc; - if (is_powerof2(bit)) - { - OP2(SLJIT_OR, TMP2, 0, TMP2, 0, SLJIT_IMM, bit); - found = CMP(SLJIT_EQUAL, TMP2, 0, SLJIT_IMM, req_char | bit); - } - else - { - found = CMP(SLJIT_EQUAL, TMP2, 0, SLJIT_IMM, req_char); - foundoc = CMP(SLJIT_EQUAL, TMP2, 0, SLJIT_IMM, oc); - } - } -OP2(SLJIT_ADD, TMP1, 0, TMP1, 0, SLJIT_IMM, IN_UCHARS(1)); -JUMPTO(SLJIT_JUMP, loop); - -JUMPHERE(found); -if (foundoc) - JUMPHERE(foundoc); -OP1(SLJIT_MOV, SLJIT_MEM1(SLJIT_SP), common->req_char_ptr, TMP1, 0); -JUMPHERE(alreadyfound); -JUMPHERE(toolong); -return notfound; -} - -static void do_revertframes(compiler_common *common) -{ -DEFINE_COMPILER; -struct sljit_jump *jump; -struct sljit_label *mainloop; - -sljit_emit_fast_enter(compiler, RETURN_ADDR, 0); -OP1(SLJIT_MOV, TMP1, 0, STACK_TOP, 0); -GET_LOCAL_BASE(TMP3, 0, 0); - -/* Drop frames until we reach STACK_TOP. */ -mainloop = LABEL(); -OP1(SLJIT_MOV, TMP2, 0, SLJIT_MEM1(TMP1), 0); -OP2(SLJIT_SUB | SLJIT_SET_S, SLJIT_UNUSED, 0, TMP2, 0, SLJIT_IMM, 0); -jump = JUMP(SLJIT_SIG_LESS_EQUAL); - -OP2(SLJIT_ADD, TMP2, 0, TMP2, 0, TMP3, 0); -OP1(SLJIT_MOV, SLJIT_MEM1(TMP2), 0, SLJIT_MEM1(TMP1), sizeof(sljit_sw)); -OP1(SLJIT_MOV, SLJIT_MEM1(TMP2), sizeof(sljit_sw), SLJIT_MEM1(TMP1), 2 * sizeof(sljit_sw)); -OP2(SLJIT_ADD, TMP1, 0, TMP1, 0, SLJIT_IMM, 3 * sizeof(sljit_sw)); -JUMPTO(SLJIT_JUMP, mainloop); - -JUMPHERE(jump); -jump = JUMP(SLJIT_SIG_LESS); -/* End of dropping frames. */ -sljit_emit_fast_return(compiler, RETURN_ADDR, 0); - -JUMPHERE(jump); -OP1(SLJIT_NEG, TMP2, 0, TMP2, 0); -OP2(SLJIT_ADD, TMP2, 0, TMP2, 0, TMP3, 0); -OP1(SLJIT_MOV, SLJIT_MEM1(TMP2), 0, SLJIT_MEM1(TMP1), sizeof(sljit_sw)); -OP2(SLJIT_ADD, TMP1, 0, TMP1, 0, SLJIT_IMM, 2 * sizeof(sljit_sw)); -JUMPTO(SLJIT_JUMP, mainloop); -} - -static void check_wordboundary(compiler_common *common) -{ -DEFINE_COMPILER; -struct sljit_jump *skipread; -jump_list *skipread_list = NULL; -#if !(defined COMPILE_PCRE8) || defined SUPPORT_UTF -struct sljit_jump *jump; -#endif - -SLJIT_COMPILE_ASSERT(ctype_word == 0x10, ctype_word_must_be_16); - -sljit_emit_fast_enter(compiler, SLJIT_MEM1(SLJIT_SP), LOCALS0); -/* Get type of the previous char, and put it to LOCALS1. */ -OP1(SLJIT_MOV, TMP1, 0, ARGUMENTS, 0); -OP1(SLJIT_MOV, TMP1, 0, SLJIT_MEM1(TMP1), SLJIT_OFFSETOF(jit_arguments, begin)); -OP1(SLJIT_MOV, SLJIT_MEM1(SLJIT_SP), LOCALS1, SLJIT_IMM, 0); -skipread = CMP(SLJIT_LESS_EQUAL, STR_PTR, 0, TMP1, 0); -skip_char_back(common); -check_start_used_ptr(common); -read_char(common); - -/* Testing char type. */ -#ifdef SUPPORT_UCP -if (common->use_ucp) - { - OP1(SLJIT_MOV, TMP2, 0, SLJIT_IMM, 1); - jump = CMP(SLJIT_EQUAL, TMP1, 0, SLJIT_IMM, CHAR_UNDERSCORE); - add_jump(compiler, &common->getucd, JUMP(SLJIT_FAST_CALL)); - OP2(SLJIT_SUB, TMP1, 0, TMP1, 0, SLJIT_IMM, ucp_Ll); - OP2(SLJIT_SUB | SLJIT_SET_U, SLJIT_UNUSED, 0, TMP1, 0, SLJIT_IMM, ucp_Lu - ucp_Ll); - OP_FLAGS(SLJIT_MOV, TMP2, 0, SLJIT_UNUSED, 0, SLJIT_LESS_EQUAL); - OP2(SLJIT_SUB, TMP1, 0, TMP1, 0, SLJIT_IMM, ucp_Nd - ucp_Ll); - OP2(SLJIT_SUB | SLJIT_SET_U, SLJIT_UNUSED, 0, TMP1, 0, SLJIT_IMM, ucp_No - ucp_Nd); - OP_FLAGS(SLJIT_OR, TMP2, 0, TMP2, 0, SLJIT_LESS_EQUAL); - JUMPHERE(jump); - OP1(SLJIT_MOV, SLJIT_MEM1(SLJIT_SP), LOCALS1, TMP2, 0); - } -else -#endif - { -#ifndef COMPILE_PCRE8 - jump = CMP(SLJIT_GREATER, TMP1, 0, SLJIT_IMM, 255); -#elif defined SUPPORT_UTF - /* Here LOCALS1 has already been zeroed. */ - jump = NULL; - if (common->utf) - jump = CMP(SLJIT_GREATER, TMP1, 0, SLJIT_IMM, 255); -#endif /* COMPILE_PCRE8 */ - OP1(SLJIT_MOV_UB, TMP1, 0, SLJIT_MEM1(TMP1), common->ctypes); - OP2(SLJIT_LSHR, TMP1, 0, TMP1, 0, SLJIT_IMM, 4 /* ctype_word */); - OP2(SLJIT_AND, TMP1, 0, TMP1, 0, SLJIT_IMM, 1); - OP1(SLJIT_MOV, SLJIT_MEM1(SLJIT_SP), LOCALS1, TMP1, 0); -#ifndef COMPILE_PCRE8 - JUMPHERE(jump); -#elif defined SUPPORT_UTF - if (jump != NULL) - JUMPHERE(jump); -#endif /* COMPILE_PCRE8 */ - } -JUMPHERE(skipread); - -OP1(SLJIT_MOV, TMP2, 0, SLJIT_IMM, 0); -check_str_end(common, &skipread_list); -peek_char(common, READ_CHAR_MAX); - -/* Testing char type. This is a code duplication. */ -#ifdef SUPPORT_UCP -if (common->use_ucp) - { - OP1(SLJIT_MOV, TMP2, 0, SLJIT_IMM, 1); - jump = CMP(SLJIT_EQUAL, TMP1, 0, SLJIT_IMM, CHAR_UNDERSCORE); - add_jump(compiler, &common->getucd, JUMP(SLJIT_FAST_CALL)); - OP2(SLJIT_SUB, TMP1, 0, TMP1, 0, SLJIT_IMM, ucp_Ll); - OP2(SLJIT_SUB | SLJIT_SET_U, SLJIT_UNUSED, 0, TMP1, 0, SLJIT_IMM, ucp_Lu - ucp_Ll); - OP_FLAGS(SLJIT_MOV, TMP2, 0, SLJIT_UNUSED, 0, SLJIT_LESS_EQUAL); - OP2(SLJIT_SUB, TMP1, 0, TMP1, 0, SLJIT_IMM, ucp_Nd - ucp_Ll); - OP2(SLJIT_SUB | SLJIT_SET_U, SLJIT_UNUSED, 0, TMP1, 0, SLJIT_IMM, ucp_No - ucp_Nd); - OP_FLAGS(SLJIT_OR, TMP2, 0, TMP2, 0, SLJIT_LESS_EQUAL); - JUMPHERE(jump); - } -else -#endif - { -#ifndef COMPILE_PCRE8 - /* TMP2 may be destroyed by peek_char. */ - OP1(SLJIT_MOV, TMP2, 0, SLJIT_IMM, 0); - jump = CMP(SLJIT_GREATER, TMP1, 0, SLJIT_IMM, 255); -#elif defined SUPPORT_UTF - OP1(SLJIT_MOV, TMP2, 0, SLJIT_IMM, 0); - jump = NULL; - if (common->utf) - jump = CMP(SLJIT_GREATER, TMP1, 0, SLJIT_IMM, 255); -#endif - OP1(SLJIT_MOV_UB, TMP2, 0, SLJIT_MEM1(TMP1), common->ctypes); - OP2(SLJIT_LSHR, TMP2, 0, TMP2, 0, SLJIT_IMM, 4 /* ctype_word */); - OP2(SLJIT_AND, TMP2, 0, TMP2, 0, SLJIT_IMM, 1); -#ifndef COMPILE_PCRE8 - JUMPHERE(jump); -#elif defined SUPPORT_UTF - if (jump != NULL) - JUMPHERE(jump); -#endif /* COMPILE_PCRE8 */ - } -set_jumps(skipread_list, LABEL()); - -OP2(SLJIT_XOR | SLJIT_SET_E, SLJIT_UNUSED, 0, TMP2, 0, SLJIT_MEM1(SLJIT_SP), LOCALS1); -sljit_emit_fast_return(compiler, SLJIT_MEM1(SLJIT_SP), LOCALS0); -} - -static BOOL check_class_ranges(compiler_common *common, const pcre_uint8 *bits, BOOL nclass, BOOL invert, jump_list **backtracks) -{ -DEFINE_COMPILER; -int ranges[MAX_RANGE_SIZE]; -pcre_uint8 bit, cbit, all; -int i, byte, length = 0; - -bit = bits[0] & 0x1; -/* All bits will be zero or one (since bit is zero or one). */ -all = -bit; - -for (i = 0; i < 256; ) - { - byte = i >> 3; - if ((i & 0x7) == 0 && bits[byte] == all) - i += 8; - else - { - cbit = (bits[byte] >> (i & 0x7)) & 0x1; - if (cbit != bit) - { - if (length >= MAX_RANGE_SIZE) - return FALSE; - ranges[length] = i; - length++; - bit = cbit; - all = -cbit; - } - i++; - } - } - -if (((bit == 0) && nclass) || ((bit == 1) && !nclass)) - { - if (length >= MAX_RANGE_SIZE) - return FALSE; - ranges[length] = 256; - length++; - } - -if (length < 0 || length > 4) - return FALSE; - -bit = bits[0] & 0x1; -if (invert) bit ^= 0x1; - -/* No character is accepted. */ -if (length == 0 && bit == 0) - add_jump(compiler, backtracks, JUMP(SLJIT_JUMP)); - -switch(length) - { - case 0: - /* When bit != 0, all characters are accepted. */ - return TRUE; - - case 1: - add_jump(compiler, backtracks, CMP(bit == 0 ? SLJIT_LESS : SLJIT_GREATER_EQUAL, TMP1, 0, SLJIT_IMM, ranges[0])); - return TRUE; - - case 2: - if (ranges[0] + 1 != ranges[1]) - { - OP2(SLJIT_SUB, TMP1, 0, TMP1, 0, SLJIT_IMM, ranges[0]); - add_jump(compiler, backtracks, CMP(bit != 0 ? SLJIT_LESS : SLJIT_GREATER_EQUAL, TMP1, 0, SLJIT_IMM, ranges[1] - ranges[0])); - } - else - add_jump(compiler, backtracks, CMP(bit != 0 ? SLJIT_EQUAL : SLJIT_NOT_EQUAL, TMP1, 0, SLJIT_IMM, ranges[0])); - return TRUE; - - case 3: - if (bit != 0) - { - add_jump(compiler, backtracks, CMP(SLJIT_GREATER_EQUAL, TMP1, 0, SLJIT_IMM, ranges[2])); - if (ranges[0] + 1 != ranges[1]) - { - OP2(SLJIT_SUB, TMP1, 0, TMP1, 0, SLJIT_IMM, ranges[0]); - add_jump(compiler, backtracks, CMP(SLJIT_LESS, TMP1, 0, SLJIT_IMM, ranges[1] - ranges[0])); - } - else - add_jump(compiler, backtracks, CMP(SLJIT_EQUAL, TMP1, 0, SLJIT_IMM, ranges[0])); - return TRUE; - } - - add_jump(compiler, backtracks, CMP(SLJIT_LESS, TMP1, 0, SLJIT_IMM, ranges[0])); - if (ranges[1] + 1 != ranges[2]) - { - OP2(SLJIT_SUB, TMP1, 0, TMP1, 0, SLJIT_IMM, ranges[1]); - add_jump(compiler, backtracks, CMP(SLJIT_LESS, TMP1, 0, SLJIT_IMM, ranges[2] - ranges[1])); - } - else - add_jump(compiler, backtracks, CMP(SLJIT_EQUAL, TMP1, 0, SLJIT_IMM, ranges[1])); - return TRUE; - - case 4: - if ((ranges[1] - ranges[0]) == (ranges[3] - ranges[2]) - && (ranges[0] | (ranges[2] - ranges[0])) == ranges[2] - && (ranges[1] & (ranges[2] - ranges[0])) == 0 - && is_powerof2(ranges[2] - ranges[0])) - { - SLJIT_ASSERT((ranges[0] & (ranges[2] - ranges[0])) == 0 && (ranges[2] & ranges[3] & (ranges[2] - ranges[0])) != 0); - OP2(SLJIT_OR, TMP1, 0, TMP1, 0, SLJIT_IMM, ranges[2] - ranges[0]); - if (ranges[2] + 1 != ranges[3]) - { - OP2(SLJIT_SUB, TMP1, 0, TMP1, 0, SLJIT_IMM, ranges[2]); - add_jump(compiler, backtracks, CMP(bit != 0 ? SLJIT_LESS : SLJIT_GREATER_EQUAL, TMP1, 0, SLJIT_IMM, ranges[3] - ranges[2])); - } - else - add_jump(compiler, backtracks, CMP(bit != 0 ? SLJIT_EQUAL : SLJIT_NOT_EQUAL, TMP1, 0, SLJIT_IMM, ranges[2])); - return TRUE; - } - - if (bit != 0) - { - i = 0; - if (ranges[0] + 1 != ranges[1]) - { - OP2(SLJIT_SUB, TMP1, 0, TMP1, 0, SLJIT_IMM, ranges[0]); - add_jump(compiler, backtracks, CMP(SLJIT_LESS, TMP1, 0, SLJIT_IMM, ranges[1] - ranges[0])); - i = ranges[0]; - } - else - add_jump(compiler, backtracks, CMP(SLJIT_EQUAL, TMP1, 0, SLJIT_IMM, ranges[0])); - - if (ranges[2] + 1 != ranges[3]) - { - OP2(SLJIT_SUB, TMP1, 0, TMP1, 0, SLJIT_IMM, ranges[2] - i); - add_jump(compiler, backtracks, CMP(SLJIT_LESS, TMP1, 0, SLJIT_IMM, ranges[3] - ranges[2])); - } - else - add_jump(compiler, backtracks, CMP(SLJIT_EQUAL, TMP1, 0, SLJIT_IMM, ranges[2] - i)); - return TRUE; - } - - OP2(SLJIT_SUB, TMP1, 0, TMP1, 0, SLJIT_IMM, ranges[0]); - add_jump(compiler, backtracks, CMP(SLJIT_GREATER_EQUAL, TMP1, 0, SLJIT_IMM, ranges[3] - ranges[0])); - if (ranges[1] + 1 != ranges[2]) - { - OP2(SLJIT_SUB, TMP1, 0, TMP1, 0, SLJIT_IMM, ranges[1] - ranges[0]); - add_jump(compiler, backtracks, CMP(SLJIT_LESS, TMP1, 0, SLJIT_IMM, ranges[2] - ranges[1])); - } - else - add_jump(compiler, backtracks, CMP(SLJIT_EQUAL, TMP1, 0, SLJIT_IMM, ranges[1] - ranges[0])); - return TRUE; - - default: - SLJIT_ASSERT_STOP(); - return FALSE; - } -} - -static void check_anynewline(compiler_common *common) -{ -/* Check whether TMP1 contains a newline character. TMP2 destroyed. */ -DEFINE_COMPILER; - -sljit_emit_fast_enter(compiler, RETURN_ADDR, 0); - -OP2(SLJIT_SUB, TMP1, 0, TMP1, 0, SLJIT_IMM, 0x0a); -OP2(SLJIT_SUB | SLJIT_SET_U, SLJIT_UNUSED, 0, TMP1, 0, SLJIT_IMM, 0x0d - 0x0a); -OP_FLAGS(SLJIT_MOV, TMP2, 0, SLJIT_UNUSED, 0, SLJIT_LESS_EQUAL); -OP2(SLJIT_SUB | SLJIT_SET_E, SLJIT_UNUSED, 0, TMP1, 0, SLJIT_IMM, 0x85 - 0x0a); -#if defined SUPPORT_UTF || defined COMPILE_PCRE16 || defined COMPILE_PCRE32 -#ifdef COMPILE_PCRE8 -if (common->utf) - { -#endif - OP_FLAGS(SLJIT_OR, TMP2, 0, TMP2, 0, SLJIT_EQUAL); - OP2(SLJIT_OR, TMP1, 0, TMP1, 0, SLJIT_IMM, 0x1); - OP2(SLJIT_SUB | SLJIT_SET_E, SLJIT_UNUSED, 0, TMP1, 0, SLJIT_IMM, 0x2029 - 0x0a); -#ifdef COMPILE_PCRE8 - } -#endif -#endif /* SUPPORT_UTF || COMPILE_PCRE16 || COMPILE_PCRE32 */ -OP_FLAGS(SLJIT_OR | SLJIT_SET_E, TMP2, 0, TMP2, 0, SLJIT_EQUAL); -sljit_emit_fast_return(compiler, RETURN_ADDR, 0); -} - -static void check_hspace(compiler_common *common) -{ -/* Check whether TMP1 contains a newline character. TMP2 destroyed. */ -DEFINE_COMPILER; - -sljit_emit_fast_enter(compiler, RETURN_ADDR, 0); - -OP2(SLJIT_SUB | SLJIT_SET_E, SLJIT_UNUSED, 0, TMP1, 0, SLJIT_IMM, 0x09); -OP_FLAGS(SLJIT_MOV, TMP2, 0, SLJIT_UNUSED, 0, SLJIT_EQUAL); -OP2(SLJIT_SUB | SLJIT_SET_E, SLJIT_UNUSED, 0, TMP1, 0, SLJIT_IMM, 0x20); -OP_FLAGS(SLJIT_OR, TMP2, 0, TMP2, 0, SLJIT_EQUAL); -OP2(SLJIT_SUB | SLJIT_SET_E, SLJIT_UNUSED, 0, TMP1, 0, SLJIT_IMM, 0xa0); -#if defined SUPPORT_UTF || defined COMPILE_PCRE16 || defined COMPILE_PCRE32 -#ifdef COMPILE_PCRE8 -if (common->utf) - { -#endif - OP_FLAGS(SLJIT_OR, TMP2, 0, TMP2, 0, SLJIT_EQUAL); - OP2(SLJIT_SUB | SLJIT_SET_E, SLJIT_UNUSED, 0, TMP1, 0, SLJIT_IMM, 0x1680); - OP_FLAGS(SLJIT_OR, TMP2, 0, TMP2, 0, SLJIT_EQUAL); - OP2(SLJIT_SUB | SLJIT_SET_E, SLJIT_UNUSED, 0, TMP1, 0, SLJIT_IMM, 0x180e); - OP_FLAGS(SLJIT_OR, TMP2, 0, TMP2, 0, SLJIT_EQUAL); - OP2(SLJIT_SUB, TMP1, 0, TMP1, 0, SLJIT_IMM, 0x2000); - OP2(SLJIT_SUB | SLJIT_SET_U, SLJIT_UNUSED, 0, TMP1, 0, SLJIT_IMM, 0x200A - 0x2000); - OP_FLAGS(SLJIT_OR, TMP2, 0, TMP2, 0, SLJIT_LESS_EQUAL); - OP2(SLJIT_SUB | SLJIT_SET_E, SLJIT_UNUSED, 0, TMP1, 0, SLJIT_IMM, 0x202f - 0x2000); - OP_FLAGS(SLJIT_OR, TMP2, 0, TMP2, 0, SLJIT_EQUAL); - OP2(SLJIT_SUB | SLJIT_SET_E, SLJIT_UNUSED, 0, TMP1, 0, SLJIT_IMM, 0x205f - 0x2000); - OP_FLAGS(SLJIT_OR, TMP2, 0, TMP2, 0, SLJIT_EQUAL); - OP2(SLJIT_SUB | SLJIT_SET_E, SLJIT_UNUSED, 0, TMP1, 0, SLJIT_IMM, 0x3000 - 0x2000); -#ifdef COMPILE_PCRE8 - } -#endif -#endif /* SUPPORT_UTF || COMPILE_PCRE16 || COMPILE_PCRE32 */ -OP_FLAGS(SLJIT_OR | SLJIT_SET_E, TMP2, 0, TMP2, 0, SLJIT_EQUAL); - -sljit_emit_fast_return(compiler, RETURN_ADDR, 0); -} - -static void check_vspace(compiler_common *common) -{ -/* Check whether TMP1 contains a newline character. TMP2 destroyed. */ -DEFINE_COMPILER; - -sljit_emit_fast_enter(compiler, RETURN_ADDR, 0); - -OP2(SLJIT_SUB, TMP1, 0, TMP1, 0, SLJIT_IMM, 0x0a); -OP2(SLJIT_SUB | SLJIT_SET_U, SLJIT_UNUSED, 0, TMP1, 0, SLJIT_IMM, 0x0d - 0x0a); -OP_FLAGS(SLJIT_MOV, TMP2, 0, SLJIT_UNUSED, 0, SLJIT_LESS_EQUAL); -OP2(SLJIT_SUB | SLJIT_SET_E, SLJIT_UNUSED, 0, TMP1, 0, SLJIT_IMM, 0x85 - 0x0a); -#if defined SUPPORT_UTF || defined COMPILE_PCRE16 || defined COMPILE_PCRE32 -#ifdef COMPILE_PCRE8 -if (common->utf) - { -#endif - OP_FLAGS(SLJIT_OR | SLJIT_SET_E, TMP2, 0, TMP2, 0, SLJIT_EQUAL); - OP2(SLJIT_OR, TMP1, 0, TMP1, 0, SLJIT_IMM, 0x1); - OP2(SLJIT_SUB | SLJIT_SET_E, SLJIT_UNUSED, 0, TMP1, 0, SLJIT_IMM, 0x2029 - 0x0a); -#ifdef COMPILE_PCRE8 - } -#endif -#endif /* SUPPORT_UTF || COMPILE_PCRE16 || COMPILE_PCRE32 */ -OP_FLAGS(SLJIT_OR | SLJIT_SET_E, TMP2, 0, TMP2, 0, SLJIT_EQUAL); - -sljit_emit_fast_return(compiler, RETURN_ADDR, 0); -} - -#define CHAR1 STR_END -#define CHAR2 STACK_TOP - -static void do_casefulcmp(compiler_common *common) -{ -DEFINE_COMPILER; -struct sljit_jump *jump; -struct sljit_label *label; - -sljit_emit_fast_enter(compiler, RETURN_ADDR, 0); -OP2(SLJIT_SUB, STR_PTR, 0, STR_PTR, 0, TMP2, 0); -OP1(SLJIT_MOV, TMP3, 0, CHAR1, 0); -OP1(SLJIT_MOV, SLJIT_MEM1(SLJIT_SP), LOCALS0, CHAR2, 0); -OP2(SLJIT_SUB, TMP1, 0, TMP1, 0, SLJIT_IMM, IN_UCHARS(1)); -OP2(SLJIT_SUB, STR_PTR, 0, STR_PTR, 0, SLJIT_IMM, IN_UCHARS(1)); - -label = LABEL(); -OP1(MOVU_UCHAR, CHAR1, 0, SLJIT_MEM1(TMP1), IN_UCHARS(1)); -OP1(MOVU_UCHAR, CHAR2, 0, SLJIT_MEM1(STR_PTR), IN_UCHARS(1)); -jump = CMP(SLJIT_NOT_EQUAL, CHAR1, 0, CHAR2, 0); -OP2(SLJIT_SUB | SLJIT_SET_E, TMP2, 0, TMP2, 0, SLJIT_IMM, IN_UCHARS(1)); -JUMPTO(SLJIT_NOT_ZERO, label); - -JUMPHERE(jump); -OP2(SLJIT_ADD, STR_PTR, 0, STR_PTR, 0, SLJIT_IMM, IN_UCHARS(1)); -OP1(SLJIT_MOV, CHAR1, 0, TMP3, 0); -OP1(SLJIT_MOV, CHAR2, 0, SLJIT_MEM1(SLJIT_SP), LOCALS0); -sljit_emit_fast_return(compiler, RETURN_ADDR, 0); -} - -#define LCC_TABLE STACK_LIMIT - -static void do_caselesscmp(compiler_common *common) -{ -DEFINE_COMPILER; -struct sljit_jump *jump; -struct sljit_label *label; - -sljit_emit_fast_enter(compiler, RETURN_ADDR, 0); -OP2(SLJIT_SUB, STR_PTR, 0, STR_PTR, 0, TMP2, 0); - -OP1(SLJIT_MOV, TMP3, 0, LCC_TABLE, 0); -OP1(SLJIT_MOV, SLJIT_MEM1(SLJIT_SP), LOCALS0, CHAR1, 0); -OP1(SLJIT_MOV, SLJIT_MEM1(SLJIT_SP), LOCALS1, CHAR2, 0); -OP1(SLJIT_MOV, LCC_TABLE, 0, SLJIT_IMM, common->lcc); -OP2(SLJIT_SUB, TMP1, 0, TMP1, 0, SLJIT_IMM, IN_UCHARS(1)); -OP2(SLJIT_SUB, STR_PTR, 0, STR_PTR, 0, SLJIT_IMM, IN_UCHARS(1)); - -label = LABEL(); -OP1(MOVU_UCHAR, CHAR1, 0, SLJIT_MEM1(TMP1), IN_UCHARS(1)); -OP1(MOVU_UCHAR, CHAR2, 0, SLJIT_MEM1(STR_PTR), IN_UCHARS(1)); -#ifndef COMPILE_PCRE8 -jump = CMP(SLJIT_GREATER, CHAR1, 0, SLJIT_IMM, 255); -#endif -OP1(SLJIT_MOV_UB, CHAR1, 0, SLJIT_MEM2(LCC_TABLE, CHAR1), 0); -#ifndef COMPILE_PCRE8 -JUMPHERE(jump); -jump = CMP(SLJIT_GREATER, CHAR2, 0, SLJIT_IMM, 255); -#endif -OP1(SLJIT_MOV_UB, CHAR2, 0, SLJIT_MEM2(LCC_TABLE, CHAR2), 0); -#ifndef COMPILE_PCRE8 -JUMPHERE(jump); -#endif -jump = CMP(SLJIT_NOT_EQUAL, CHAR1, 0, CHAR2, 0); -OP2(SLJIT_SUB | SLJIT_SET_E, TMP2, 0, TMP2, 0, SLJIT_IMM, IN_UCHARS(1)); -JUMPTO(SLJIT_NOT_ZERO, label); - -JUMPHERE(jump); -OP2(SLJIT_ADD, STR_PTR, 0, STR_PTR, 0, SLJIT_IMM, IN_UCHARS(1)); -OP1(SLJIT_MOV, LCC_TABLE, 0, TMP3, 0); -OP1(SLJIT_MOV, CHAR1, 0, SLJIT_MEM1(SLJIT_SP), LOCALS0); -OP1(SLJIT_MOV, CHAR2, 0, SLJIT_MEM1(SLJIT_SP), LOCALS1); -sljit_emit_fast_return(compiler, RETURN_ADDR, 0); -} - -#undef LCC_TABLE -#undef CHAR1 -#undef CHAR2 - -#if defined SUPPORT_UTF && defined SUPPORT_UCP - -static const pcre_uchar * SLJIT_CALL do_utf_caselesscmp(pcre_uchar *src1, jit_arguments *args, pcre_uchar *end1) -{ -/* This function would be ineffective to do in JIT level. */ -pcre_uint32 c1, c2; -const pcre_uchar *src2 = args->uchar_ptr; -const pcre_uchar *end2 = args->end; -const ucd_record *ur; -const pcre_uint32 *pp; - -while (src1 < end1) - { - if (src2 >= end2) - return (pcre_uchar*)1; - GETCHARINC(c1, src1); - GETCHARINC(c2, src2); - ur = GET_UCD(c2); - if (c1 != c2 && c1 != c2 + ur->other_case) - { - pp = PRIV(ucd_caseless_sets) + ur->caseset; - for (;;) - { - if (c1 < *pp) return NULL; - if (c1 == *pp++) break; - } - } - } -return src2; -} - -#endif /* SUPPORT_UTF && SUPPORT_UCP */ - -static pcre_uchar *byte_sequence_compare(compiler_common *common, BOOL caseless, pcre_uchar *cc, - compare_context *context, jump_list **backtracks) -{ -DEFINE_COMPILER; -unsigned int othercasebit = 0; -pcre_uchar *othercasechar = NULL; -#ifdef SUPPORT_UTF -int utflength; -#endif - -if (caseless && char_has_othercase(common, cc)) - { - othercasebit = char_get_othercase_bit(common, cc); - SLJIT_ASSERT(othercasebit); - /* Extracting bit difference info. */ -#if defined COMPILE_PCRE8 - othercasechar = cc + (othercasebit >> 8); - othercasebit &= 0xff; -#elif defined COMPILE_PCRE16 || defined COMPILE_PCRE32 - /* Note that this code only handles characters in the BMP. If there - ever are characters outside the BMP whose othercase differs in only one - bit from itself (there currently are none), this code will need to be - revised for COMPILE_PCRE32. */ - othercasechar = cc + (othercasebit >> 9); - if ((othercasebit & 0x100) != 0) - othercasebit = (othercasebit & 0xff) << 8; - else - othercasebit &= 0xff; -#endif /* COMPILE_PCRE[8|16|32] */ - } - -if (context->sourcereg == -1) - { -#if defined COMPILE_PCRE8 -#if defined SLJIT_UNALIGNED && SLJIT_UNALIGNED - if (context->length >= 4) - OP1(SLJIT_MOV_SI, TMP1, 0, SLJIT_MEM1(STR_PTR), -context->length); - else if (context->length >= 2) - OP1(SLJIT_MOV_UH, TMP1, 0, SLJIT_MEM1(STR_PTR), -context->length); - else -#endif - OP1(SLJIT_MOV_UB, TMP1, 0, SLJIT_MEM1(STR_PTR), -context->length); -#elif defined COMPILE_PCRE16 -#if defined SLJIT_UNALIGNED && SLJIT_UNALIGNED - if (context->length >= 4) - OP1(SLJIT_MOV_SI, TMP1, 0, SLJIT_MEM1(STR_PTR), -context->length); - else -#endif - OP1(MOV_UCHAR, TMP1, 0, SLJIT_MEM1(STR_PTR), -context->length); -#elif defined COMPILE_PCRE32 - OP1(MOV_UCHAR, TMP1, 0, SLJIT_MEM1(STR_PTR), -context->length); -#endif /* COMPILE_PCRE[8|16|32] */ - context->sourcereg = TMP2; - } - -#ifdef SUPPORT_UTF -utflength = 1; -if (common->utf && HAS_EXTRALEN(*cc)) - utflength += GET_EXTRALEN(*cc); - -do - { -#endif - - context->length -= IN_UCHARS(1); -#if (defined SLJIT_UNALIGNED && SLJIT_UNALIGNED) && (defined COMPILE_PCRE8 || defined COMPILE_PCRE16) - - /* Unaligned read is supported. */ - if (othercasebit != 0 && othercasechar == cc) - { - context->c.asuchars[context->ucharptr] = *cc | othercasebit; - context->oc.asuchars[context->ucharptr] = othercasebit; - } - else - { - context->c.asuchars[context->ucharptr] = *cc; - context->oc.asuchars[context->ucharptr] = 0; - } - context->ucharptr++; - -#if defined COMPILE_PCRE8 - if (context->ucharptr >= 4 || context->length == 0 || (context->ucharptr == 2 && context->length == 1)) -#else - if (context->ucharptr >= 2 || context->length == 0) -#endif - { - if (context->length >= 4) - OP1(SLJIT_MOV_SI, context->sourcereg, 0, SLJIT_MEM1(STR_PTR), -context->length); - else if (context->length >= 2) - OP1(SLJIT_MOV_UH, context->sourcereg, 0, SLJIT_MEM1(STR_PTR), -context->length); -#if defined COMPILE_PCRE8 - else if (context->length >= 1) - OP1(SLJIT_MOV_UB, context->sourcereg, 0, SLJIT_MEM1(STR_PTR), -context->length); -#endif /* COMPILE_PCRE8 */ - context->sourcereg = context->sourcereg == TMP1 ? TMP2 : TMP1; - - switch(context->ucharptr) - { - case 4 / sizeof(pcre_uchar): - if (context->oc.asint != 0) - OP2(SLJIT_OR, context->sourcereg, 0, context->sourcereg, 0, SLJIT_IMM, context->oc.asint); - add_jump(compiler, backtracks, CMP(SLJIT_NOT_EQUAL, context->sourcereg, 0, SLJIT_IMM, context->c.asint | context->oc.asint)); - break; - - case 2 / sizeof(pcre_uchar): - if (context->oc.asushort != 0) - OP2(SLJIT_OR, context->sourcereg, 0, context->sourcereg, 0, SLJIT_IMM, context->oc.asushort); - add_jump(compiler, backtracks, CMP(SLJIT_NOT_EQUAL, context->sourcereg, 0, SLJIT_IMM, context->c.asushort | context->oc.asushort)); - break; - -#ifdef COMPILE_PCRE8 - case 1: - if (context->oc.asbyte != 0) - OP2(SLJIT_OR, context->sourcereg, 0, context->sourcereg, 0, SLJIT_IMM, context->oc.asbyte); - add_jump(compiler, backtracks, CMP(SLJIT_NOT_EQUAL, context->sourcereg, 0, SLJIT_IMM, context->c.asbyte | context->oc.asbyte)); - break; -#endif - - default: - SLJIT_ASSERT_STOP(); - break; - } - context->ucharptr = 0; - } - -#else - - /* Unaligned read is unsupported or in 32 bit mode. */ - if (context->length >= 1) - OP1(MOV_UCHAR, context->sourcereg, 0, SLJIT_MEM1(STR_PTR), -context->length); - - context->sourcereg = context->sourcereg == TMP1 ? TMP2 : TMP1; - - if (othercasebit != 0 && othercasechar == cc) - { - OP2(SLJIT_OR, context->sourcereg, 0, context->sourcereg, 0, SLJIT_IMM, othercasebit); - add_jump(compiler, backtracks, CMP(SLJIT_NOT_EQUAL, context->sourcereg, 0, SLJIT_IMM, *cc | othercasebit)); - } - else - add_jump(compiler, backtracks, CMP(SLJIT_NOT_EQUAL, context->sourcereg, 0, SLJIT_IMM, *cc)); - -#endif - - cc++; -#ifdef SUPPORT_UTF - utflength--; - } -while (utflength > 0); -#endif - -return cc; -} - -#if defined SUPPORT_UTF || !defined COMPILE_PCRE8 - -#define SET_TYPE_OFFSET(value) \ - if ((value) != typeoffset) \ - { \ - if ((value) < typeoffset) \ - OP2(SLJIT_ADD, typereg, 0, typereg, 0, SLJIT_IMM, typeoffset - (value)); \ - else \ - OP2(SLJIT_SUB, typereg, 0, typereg, 0, SLJIT_IMM, (value) - typeoffset); \ - } \ - typeoffset = (value); - -#define SET_CHAR_OFFSET(value) \ - if ((value) != charoffset) \ - { \ - if ((value) < charoffset) \ - OP2(SLJIT_ADD, TMP1, 0, TMP1, 0, SLJIT_IMM, (sljit_sw)(charoffset - (value))); \ - else \ - OP2(SLJIT_SUB, TMP1, 0, TMP1, 0, SLJIT_IMM, (sljit_sw)((value) - charoffset)); \ - } \ - charoffset = (value); - -static void compile_xclass_matchingpath(compiler_common *common, pcre_uchar *cc, jump_list **backtracks) -{ -DEFINE_COMPILER; -jump_list *found = NULL; -jump_list **list = (cc[0] & XCL_NOT) == 0 ? &found : backtracks; -sljit_uw c, charoffset, max = 256, min = READ_CHAR_MAX; -struct sljit_jump *jump = NULL; -pcre_uchar *ccbegin; -int compares, invertcmp, numberofcmps; -#if defined SUPPORT_UTF && (defined COMPILE_PCRE8 || defined COMPILE_PCRE16) -BOOL utf = common->utf; -#endif - -#ifdef SUPPORT_UCP -BOOL needstype = FALSE, needsscript = FALSE, needschar = FALSE; -BOOL charsaved = FALSE; -int typereg = TMP1, scriptreg = TMP1; -const pcre_uint32 *other_cases; -sljit_uw typeoffset; -#endif - -/* Scanning the necessary info. */ -cc++; -ccbegin = cc; -compares = 0; -if (cc[-1] & XCL_MAP) - { - min = 0; - cc += 32 / sizeof(pcre_uchar); - } - -while (*cc != XCL_END) - { - compares++; - if (*cc == XCL_SINGLE) - { - cc ++; - GETCHARINCTEST(c, cc); - if (c > max) max = c; - if (c < min) min = c; -#ifdef SUPPORT_UCP - needschar = TRUE; -#endif - } - else if (*cc == XCL_RANGE) - { - cc ++; - GETCHARINCTEST(c, cc); - if (c < min) min = c; - GETCHARINCTEST(c, cc); - if (c > max) max = c; -#ifdef SUPPORT_UCP - needschar = TRUE; -#endif - } -#ifdef SUPPORT_UCP - else - { - SLJIT_ASSERT(*cc == XCL_PROP || *cc == XCL_NOTPROP); - cc++; - if (*cc == PT_CLIST) - { - other_cases = PRIV(ucd_caseless_sets) + cc[1]; - while (*other_cases != NOTACHAR) - { - if (*other_cases > max) max = *other_cases; - if (*other_cases < min) min = *other_cases; - other_cases++; - } - } - else - { - max = READ_CHAR_MAX; - min = 0; - } - - switch(*cc) - { - case PT_ANY: - break; - - case PT_LAMP: - case PT_GC: - case PT_PC: - case PT_ALNUM: - needstype = TRUE; - break; - - case PT_SC: - needsscript = TRUE; - break; - - case PT_SPACE: - case PT_PXSPACE: - case PT_WORD: - case PT_PXGRAPH: - case PT_PXPRINT: - case PT_PXPUNCT: - needstype = TRUE; - needschar = TRUE; - break; - - case PT_CLIST: - case PT_UCNC: - needschar = TRUE; - break; - - default: - SLJIT_ASSERT_STOP(); - break; - } - cc += 2; - } -#endif - } - -/* We are not necessary in utf mode even in 8 bit mode. */ -cc = ccbegin; -detect_partial_match(common, backtracks); -read_char_range(common, min, max, (cc[-1] & XCL_NOT) != 0); - -if ((cc[-1] & XCL_HASPROP) == 0) - { - if ((cc[-1] & XCL_MAP) != 0) - { - jump = CMP(SLJIT_GREATER, TMP1, 0, SLJIT_IMM, 255); - if (!check_class_ranges(common, (const pcre_uint8 *)cc, (((const pcre_uint8 *)cc)[31] & 0x80) != 0, TRUE, &found)) - { - OP2(SLJIT_AND, TMP2, 0, TMP1, 0, SLJIT_IMM, 0x7); - OP2(SLJIT_LSHR, TMP1, 0, TMP1, 0, SLJIT_IMM, 3); - OP1(SLJIT_MOV_UB, TMP1, 0, SLJIT_MEM1(TMP1), (sljit_sw)cc); - OP2(SLJIT_SHL, TMP2, 0, SLJIT_IMM, 1, TMP2, 0); - OP2(SLJIT_AND | SLJIT_SET_E, SLJIT_UNUSED, 0, TMP1, 0, TMP2, 0); - add_jump(compiler, &found, JUMP(SLJIT_NOT_ZERO)); - } - - add_jump(compiler, backtracks, JUMP(SLJIT_JUMP)); - JUMPHERE(jump); - - cc += 32 / sizeof(pcre_uchar); - } - else - { - OP2(SLJIT_SUB, TMP2, 0, TMP1, 0, SLJIT_IMM, min); - add_jump(compiler, (cc[-1] & XCL_NOT) == 0 ? backtracks : &found, CMP(SLJIT_GREATER, TMP2, 0, SLJIT_IMM, max - min)); - } - } -else if ((cc[-1] & XCL_MAP) != 0) - { - OP1(SLJIT_MOV, TMP3, 0, TMP1, 0); -#ifdef SUPPORT_UCP - charsaved = TRUE; -#endif - if (!check_class_ranges(common, (const pcre_uint8 *)cc, FALSE, TRUE, list)) - { -#ifdef COMPILE_PCRE8 - jump = NULL; - if (common->utf) -#endif - jump = CMP(SLJIT_GREATER, TMP1, 0, SLJIT_IMM, 255); - - OP2(SLJIT_AND, TMP2, 0, TMP1, 0, SLJIT_IMM, 0x7); - OP2(SLJIT_LSHR, TMP1, 0, TMP1, 0, SLJIT_IMM, 3); - OP1(SLJIT_MOV_UB, TMP1, 0, SLJIT_MEM1(TMP1), (sljit_sw)cc); - OP2(SLJIT_SHL, TMP2, 0, SLJIT_IMM, 1, TMP2, 0); - OP2(SLJIT_AND | SLJIT_SET_E, SLJIT_UNUSED, 0, TMP1, 0, TMP2, 0); - add_jump(compiler, list, JUMP(SLJIT_NOT_ZERO)); - -#ifdef COMPILE_PCRE8 - if (common->utf) -#endif - JUMPHERE(jump); - } - - OP1(SLJIT_MOV, TMP1, 0, TMP3, 0); - cc += 32 / sizeof(pcre_uchar); - } - -#ifdef SUPPORT_UCP -/* Simple register allocation. TMP1 is preferred if possible. */ -if (needstype || needsscript) - { - if (needschar && !charsaved) - OP1(SLJIT_MOV, TMP3, 0, TMP1, 0); - add_jump(compiler, &common->getucd, JUMP(SLJIT_FAST_CALL)); - if (needschar) - { - if (needstype) - { - OP1(SLJIT_MOV, RETURN_ADDR, 0, TMP1, 0); - typereg = RETURN_ADDR; - } - - if (needsscript) - scriptreg = TMP3; - OP1(SLJIT_MOV, TMP1, 0, TMP3, 0); - } - else if (needstype && needsscript) - scriptreg = TMP3; - /* In all other cases only one of them was specified, and that can goes to TMP1. */ - - if (needsscript) - { - if (scriptreg == TMP1) - { - OP1(SLJIT_MOV, scriptreg, 0, SLJIT_IMM, (sljit_sw)PRIV(ucd_records) + SLJIT_OFFSETOF(ucd_record, script)); - OP1(SLJIT_MOV_UB, scriptreg, 0, SLJIT_MEM2(scriptreg, TMP2), 3); - } - else - { - OP2(SLJIT_SHL, TMP2, 0, TMP2, 0, SLJIT_IMM, 3); - OP2(SLJIT_ADD, TMP2, 0, TMP2, 0, SLJIT_IMM, (sljit_sw)PRIV(ucd_records) + SLJIT_OFFSETOF(ucd_record, script)); - OP1(SLJIT_MOV_UB, scriptreg, 0, SLJIT_MEM1(TMP2), 0); - } - } - } -#endif - -/* Generating code. */ -charoffset = 0; -numberofcmps = 0; -#ifdef SUPPORT_UCP -typeoffset = 0; -#endif - -while (*cc != XCL_END) - { - compares--; - invertcmp = (compares == 0 && list != backtracks); - jump = NULL; - - if (*cc == XCL_SINGLE) - { - cc ++; - GETCHARINCTEST(c, cc); - - if (numberofcmps < 3 && (*cc == XCL_SINGLE || *cc == XCL_RANGE)) - { - OP2(SLJIT_SUB | SLJIT_SET_E, SLJIT_UNUSED, 0, TMP1, 0, SLJIT_IMM, (sljit_sw)(c - charoffset)); - OP_FLAGS(numberofcmps == 0 ? SLJIT_MOV : SLJIT_OR, TMP2, 0, numberofcmps == 0 ? SLJIT_UNUSED : TMP2, 0, SLJIT_EQUAL); - numberofcmps++; - } - else if (numberofcmps > 0) - { - OP2(SLJIT_SUB | SLJIT_SET_E, SLJIT_UNUSED, 0, TMP1, 0, SLJIT_IMM, (sljit_sw)(c - charoffset)); - OP_FLAGS(SLJIT_OR | SLJIT_SET_E, TMP2, 0, TMP2, 0, SLJIT_EQUAL); - jump = JUMP(SLJIT_NOT_ZERO ^ invertcmp); - numberofcmps = 0; - } - else - { - jump = CMP(SLJIT_EQUAL ^ invertcmp, TMP1, 0, SLJIT_IMM, (sljit_sw)(c - charoffset)); - numberofcmps = 0; - } - } - else if (*cc == XCL_RANGE) - { - cc ++; - GETCHARINCTEST(c, cc); - SET_CHAR_OFFSET(c); - GETCHARINCTEST(c, cc); - - if (numberofcmps < 3 && (*cc == XCL_SINGLE || *cc == XCL_RANGE)) - { - OP2(SLJIT_SUB | SLJIT_SET_U, SLJIT_UNUSED, 0, TMP1, 0, SLJIT_IMM, (sljit_sw)(c - charoffset)); - OP_FLAGS(numberofcmps == 0 ? SLJIT_MOV : SLJIT_OR, TMP2, 0, numberofcmps == 0 ? SLJIT_UNUSED : TMP2, 0, SLJIT_LESS_EQUAL); - numberofcmps++; - } - else if (numberofcmps > 0) - { - OP2(SLJIT_SUB | SLJIT_SET_U, SLJIT_UNUSED, 0, TMP1, 0, SLJIT_IMM, (sljit_sw)(c - charoffset)); - OP_FLAGS(SLJIT_OR | SLJIT_SET_E, TMP2, 0, TMP2, 0, SLJIT_LESS_EQUAL); - jump = JUMP(SLJIT_NOT_ZERO ^ invertcmp); - numberofcmps = 0; - } - else - { - jump = CMP(SLJIT_LESS_EQUAL ^ invertcmp, TMP1, 0, SLJIT_IMM, (sljit_sw)(c - charoffset)); - numberofcmps = 0; - } - } -#ifdef SUPPORT_UCP - else - { - if (*cc == XCL_NOTPROP) - invertcmp ^= 0x1; - cc++; - switch(*cc) - { - case PT_ANY: - if (list != backtracks) - { - if ((cc[-1] == XCL_NOTPROP && compares > 0) || (cc[-1] == XCL_PROP && compares == 0)) - continue; - } - else if (cc[-1] == XCL_NOTPROP) - continue; - jump = JUMP(SLJIT_JUMP); - break; - - case PT_LAMP: - OP2(SLJIT_SUB | SLJIT_SET_E, SLJIT_UNUSED, 0, typereg, 0, SLJIT_IMM, ucp_Lu - typeoffset); - OP_FLAGS(SLJIT_MOV, TMP2, 0, SLJIT_UNUSED, 0, SLJIT_EQUAL); - OP2(SLJIT_SUB | SLJIT_SET_E, SLJIT_UNUSED, 0, typereg, 0, SLJIT_IMM, ucp_Ll - typeoffset); - OP_FLAGS(SLJIT_OR, TMP2, 0, TMP2, 0, SLJIT_EQUAL); - OP2(SLJIT_SUB | SLJIT_SET_E, SLJIT_UNUSED, 0, typereg, 0, SLJIT_IMM, ucp_Lt - typeoffset); - OP_FLAGS(SLJIT_OR | SLJIT_SET_E, TMP2, 0, TMP2, 0, SLJIT_EQUAL); - jump = JUMP(SLJIT_NOT_ZERO ^ invertcmp); - break; - - case PT_GC: - c = PRIV(ucp_typerange)[(int)cc[1] * 2]; - SET_TYPE_OFFSET(c); - jump = CMP(SLJIT_LESS_EQUAL ^ invertcmp, typereg, 0, SLJIT_IMM, PRIV(ucp_typerange)[(int)cc[1] * 2 + 1] - c); - break; - - case PT_PC: - jump = CMP(SLJIT_EQUAL ^ invertcmp, typereg, 0, SLJIT_IMM, (int)cc[1] - typeoffset); - break; - - case PT_SC: - jump = CMP(SLJIT_EQUAL ^ invertcmp, scriptreg, 0, SLJIT_IMM, (int)cc[1]); - break; - - case PT_SPACE: - case PT_PXSPACE: - SET_CHAR_OFFSET(9); - OP2(SLJIT_SUB | SLJIT_SET_U, SLJIT_UNUSED, 0, TMP1, 0, SLJIT_IMM, 0xd - 0x9); - OP_FLAGS(SLJIT_MOV, TMP2, 0, SLJIT_UNUSED, 0, SLJIT_LESS_EQUAL); - - OP2(SLJIT_SUB | SLJIT_SET_E, SLJIT_UNUSED, 0, TMP1, 0, SLJIT_IMM, 0x85 - 0x9); - OP_FLAGS(SLJIT_OR | SLJIT_SET_E, TMP2, 0, TMP2, 0, SLJIT_EQUAL); - - OP2(SLJIT_SUB | SLJIT_SET_E, SLJIT_UNUSED, 0, TMP1, 0, SLJIT_IMM, 0x180e - 0x9); - OP_FLAGS(SLJIT_OR | SLJIT_SET_E, TMP2, 0, TMP2, 0, SLJIT_EQUAL); - - SET_TYPE_OFFSET(ucp_Zl); - OP2(SLJIT_SUB | SLJIT_SET_U, SLJIT_UNUSED, 0, typereg, 0, SLJIT_IMM, ucp_Zs - ucp_Zl); - OP_FLAGS(SLJIT_OR | SLJIT_SET_E, TMP2, 0, TMP2, 0, SLJIT_LESS_EQUAL); - jump = JUMP(SLJIT_NOT_ZERO ^ invertcmp); - break; - - case PT_WORD: - OP2(SLJIT_SUB | SLJIT_SET_E, SLJIT_UNUSED, 0, TMP1, 0, SLJIT_IMM, (sljit_sw)(CHAR_UNDERSCORE - charoffset)); - OP_FLAGS(SLJIT_MOV, TMP2, 0, SLJIT_UNUSED, 0, SLJIT_EQUAL); - /* Fall through. */ - - case PT_ALNUM: - SET_TYPE_OFFSET(ucp_Ll); - OP2(SLJIT_SUB | SLJIT_SET_U, SLJIT_UNUSED, 0, typereg, 0, SLJIT_IMM, ucp_Lu - ucp_Ll); - OP_FLAGS((*cc == PT_ALNUM) ? SLJIT_MOV : SLJIT_OR, TMP2, 0, (*cc == PT_ALNUM) ? SLJIT_UNUSED : TMP2, 0, SLJIT_LESS_EQUAL); - SET_TYPE_OFFSET(ucp_Nd); - OP2(SLJIT_SUB | SLJIT_SET_U, SLJIT_UNUSED, 0, typereg, 0, SLJIT_IMM, ucp_No - ucp_Nd); - OP_FLAGS(SLJIT_OR | SLJIT_SET_E, TMP2, 0, TMP2, 0, SLJIT_LESS_EQUAL); - jump = JUMP(SLJIT_NOT_ZERO ^ invertcmp); - break; - - case PT_CLIST: - other_cases = PRIV(ucd_caseless_sets) + cc[1]; - - /* At least three characters are required. - Otherwise this case would be handled by the normal code path. */ - SLJIT_ASSERT(other_cases[0] != NOTACHAR && other_cases[1] != NOTACHAR && other_cases[2] != NOTACHAR); - SLJIT_ASSERT(other_cases[0] < other_cases[1] && other_cases[1] < other_cases[2]); - - /* Optimizing character pairs, if their difference is power of 2. */ - if (is_powerof2(other_cases[1] ^ other_cases[0])) - { - if (charoffset == 0) - OP2(SLJIT_OR, TMP2, 0, TMP1, 0, SLJIT_IMM, other_cases[1] ^ other_cases[0]); - else - { - OP2(SLJIT_ADD, TMP2, 0, TMP1, 0, SLJIT_IMM, (sljit_sw)charoffset); - OP2(SLJIT_OR, TMP2, 0, TMP2, 0, SLJIT_IMM, other_cases[1] ^ other_cases[0]); - } - OP2(SLJIT_SUB | SLJIT_SET_E, SLJIT_UNUSED, 0, TMP2, 0, SLJIT_IMM, other_cases[1]); - OP_FLAGS(SLJIT_MOV, TMP2, 0, SLJIT_UNUSED, 0, SLJIT_EQUAL); - other_cases += 2; - } - else if (is_powerof2(other_cases[2] ^ other_cases[1])) - { - if (charoffset == 0) - OP2(SLJIT_OR, TMP2, 0, TMP1, 0, SLJIT_IMM, other_cases[2] ^ other_cases[1]); - else - { - OP2(SLJIT_ADD, TMP2, 0, TMP1, 0, SLJIT_IMM, (sljit_sw)charoffset); - OP2(SLJIT_OR, TMP2, 0, TMP2, 0, SLJIT_IMM, other_cases[1] ^ other_cases[0]); - } - OP2(SLJIT_SUB | SLJIT_SET_E, SLJIT_UNUSED, 0, TMP2, 0, SLJIT_IMM, other_cases[2]); - OP_FLAGS(SLJIT_MOV, TMP2, 0, SLJIT_UNUSED, 0, SLJIT_EQUAL); - - OP2(SLJIT_SUB | SLJIT_SET_E, SLJIT_UNUSED, 0, TMP1, 0, SLJIT_IMM, (sljit_sw)(other_cases[0] - charoffset)); - OP_FLAGS(SLJIT_OR | ((other_cases[3] == NOTACHAR) ? SLJIT_SET_E : 0), TMP2, 0, TMP2, 0, SLJIT_EQUAL); - - other_cases += 3; - } - else - { - OP2(SLJIT_SUB | SLJIT_SET_E, SLJIT_UNUSED, 0, TMP1, 0, SLJIT_IMM, (sljit_sw)(*other_cases++ - charoffset)); - OP_FLAGS(SLJIT_MOV, TMP2, 0, SLJIT_UNUSED, 0, SLJIT_EQUAL); - } - - while (*other_cases != NOTACHAR) - { - OP2(SLJIT_SUB | SLJIT_SET_E, SLJIT_UNUSED, 0, TMP1, 0, SLJIT_IMM, (sljit_sw)(*other_cases++ - charoffset)); - OP_FLAGS(SLJIT_OR | ((*other_cases == NOTACHAR) ? SLJIT_SET_E : 0), TMP2, 0, TMP2, 0, SLJIT_EQUAL); - } - jump = JUMP(SLJIT_NOT_ZERO ^ invertcmp); - break; - - case PT_UCNC: - OP2(SLJIT_SUB | SLJIT_SET_E, SLJIT_UNUSED, 0, TMP1, 0, SLJIT_IMM, (sljit_sw)(CHAR_DOLLAR_SIGN - charoffset)); - OP_FLAGS(SLJIT_MOV, TMP2, 0, SLJIT_UNUSED, 0, SLJIT_EQUAL); - OP2(SLJIT_SUB | SLJIT_SET_E, SLJIT_UNUSED, 0, TMP1, 0, SLJIT_IMM, (sljit_sw)(CHAR_COMMERCIAL_AT - charoffset)); - OP_FLAGS(SLJIT_OR, TMP2, 0, TMP2, 0, SLJIT_EQUAL); - OP2(SLJIT_SUB | SLJIT_SET_E, SLJIT_UNUSED, 0, TMP1, 0, SLJIT_IMM, (sljit_sw)(CHAR_GRAVE_ACCENT - charoffset)); - OP_FLAGS(SLJIT_OR, TMP2, 0, TMP2, 0, SLJIT_EQUAL); - - SET_CHAR_OFFSET(0xa0); - OP2(SLJIT_SUB | SLJIT_SET_U, SLJIT_UNUSED, 0, TMP1, 0, SLJIT_IMM, (sljit_sw)(0xd7ff - charoffset)); - OP_FLAGS(SLJIT_OR, TMP2, 0, TMP2, 0, SLJIT_LESS_EQUAL); - SET_CHAR_OFFSET(0); - OP2(SLJIT_SUB | SLJIT_SET_U, SLJIT_UNUSED, 0, TMP1, 0, SLJIT_IMM, 0xe000 - 0); - OP_FLAGS(SLJIT_OR | SLJIT_SET_E, TMP2, 0, TMP2, 0, SLJIT_GREATER_EQUAL); - jump = JUMP(SLJIT_NOT_ZERO ^ invertcmp); - break; - - case PT_PXGRAPH: - /* C and Z groups are the farthest two groups. */ - SET_TYPE_OFFSET(ucp_Ll); - OP2(SLJIT_SUB | SLJIT_SET_U, SLJIT_UNUSED, 0, typereg, 0, SLJIT_IMM, ucp_So - ucp_Ll); - OP_FLAGS(SLJIT_MOV, TMP2, 0, SLJIT_UNUSED, 0, SLJIT_GREATER); - - jump = CMP(SLJIT_NOT_EQUAL, typereg, 0, SLJIT_IMM, ucp_Cf - ucp_Ll); - - /* In case of ucp_Cf, we overwrite the result. */ - SET_CHAR_OFFSET(0x2066); - OP2(SLJIT_SUB | SLJIT_SET_U, SLJIT_UNUSED, 0, TMP1, 0, SLJIT_IMM, 0x2069 - 0x2066); - OP_FLAGS(SLJIT_MOV, TMP2, 0, SLJIT_UNUSED, 0, SLJIT_LESS_EQUAL); - - OP2(SLJIT_SUB | SLJIT_SET_E, SLJIT_UNUSED, 0, TMP1, 0, SLJIT_IMM, 0x061c - 0x2066); - OP_FLAGS(SLJIT_OR, TMP2, 0, TMP2, 0, SLJIT_EQUAL); - - OP2(SLJIT_SUB | SLJIT_SET_E, SLJIT_UNUSED, 0, TMP1, 0, SLJIT_IMM, 0x180e - 0x2066); - OP_FLAGS(SLJIT_OR, TMP2, 0, TMP2, 0, SLJIT_EQUAL); - - JUMPHERE(jump); - jump = CMP(SLJIT_ZERO ^ invertcmp, TMP2, 0, SLJIT_IMM, 0); - break; - - case PT_PXPRINT: - /* C and Z groups are the farthest two groups. */ - SET_TYPE_OFFSET(ucp_Ll); - OP2(SLJIT_SUB | SLJIT_SET_U, SLJIT_UNUSED, 0, typereg, 0, SLJIT_IMM, ucp_So - ucp_Ll); - OP_FLAGS(SLJIT_MOV, TMP2, 0, SLJIT_UNUSED, 0, SLJIT_GREATER); - - OP2(SLJIT_SUB | SLJIT_SET_E, SLJIT_UNUSED, 0, typereg, 0, SLJIT_IMM, ucp_Zs - ucp_Ll); - OP_FLAGS(SLJIT_AND, TMP2, 0, TMP2, 0, SLJIT_NOT_EQUAL); - - jump = CMP(SLJIT_NOT_EQUAL, typereg, 0, SLJIT_IMM, ucp_Cf - ucp_Ll); - - /* In case of ucp_Cf, we overwrite the result. */ - SET_CHAR_OFFSET(0x2066); - OP2(SLJIT_SUB | SLJIT_SET_U, SLJIT_UNUSED, 0, TMP1, 0, SLJIT_IMM, 0x2069 - 0x2066); - OP_FLAGS(SLJIT_MOV, TMP2, 0, SLJIT_UNUSED, 0, SLJIT_LESS_EQUAL); - - OP2(SLJIT_SUB | SLJIT_SET_E, SLJIT_UNUSED, 0, TMP1, 0, SLJIT_IMM, 0x061c - 0x2066); - OP_FLAGS(SLJIT_OR, TMP2, 0, TMP2, 0, SLJIT_EQUAL); - - JUMPHERE(jump); - jump = CMP(SLJIT_ZERO ^ invertcmp, TMP2, 0, SLJIT_IMM, 0); - break; - - case PT_PXPUNCT: - SET_TYPE_OFFSET(ucp_Sc); - OP2(SLJIT_SUB | SLJIT_SET_U, SLJIT_UNUSED, 0, typereg, 0, SLJIT_IMM, ucp_So - ucp_Sc); - OP_FLAGS(SLJIT_MOV, TMP2, 0, SLJIT_UNUSED, 0, SLJIT_LESS_EQUAL); - - SET_CHAR_OFFSET(0); - OP2(SLJIT_SUB | SLJIT_SET_U, SLJIT_UNUSED, 0, TMP1, 0, SLJIT_IMM, 0x7f); - OP_FLAGS(SLJIT_AND, TMP2, 0, TMP2, 0, SLJIT_LESS_EQUAL); - - SET_TYPE_OFFSET(ucp_Pc); - OP2(SLJIT_SUB | SLJIT_SET_U, SLJIT_UNUSED, 0, typereg, 0, SLJIT_IMM, ucp_Ps - ucp_Pc); - OP_FLAGS(SLJIT_OR | SLJIT_SET_E, TMP2, 0, TMP2, 0, SLJIT_LESS_EQUAL); - jump = JUMP(SLJIT_NOT_ZERO ^ invertcmp); - break; - } - cc += 2; - } -#endif - - if (jump != NULL) - add_jump(compiler, compares > 0 ? list : backtracks, jump); - } - -if (found != NULL) - set_jumps(found, LABEL()); -} - -#undef SET_TYPE_OFFSET -#undef SET_CHAR_OFFSET - -#endif - -static pcre_uchar *compile_char1_matchingpath(compiler_common *common, pcre_uchar type, pcre_uchar *cc, jump_list **backtracks) -{ -DEFINE_COMPILER; -int length; -unsigned int c, oc, bit; -compare_context context; -struct sljit_jump *jump[4]; -jump_list *end_list; -#ifdef SUPPORT_UTF -struct sljit_label *label; -#ifdef SUPPORT_UCP -pcre_uchar propdata[5]; -#endif -#endif /* SUPPORT_UTF */ - -switch(type) - { - case OP_SOD: - OP1(SLJIT_MOV, TMP1, 0, ARGUMENTS, 0); - OP1(SLJIT_MOV, TMP1, 0, SLJIT_MEM1(TMP1), SLJIT_OFFSETOF(jit_arguments, begin)); - add_jump(compiler, backtracks, CMP(SLJIT_NOT_EQUAL, STR_PTR, 0, TMP1, 0)); - return cc; - - case OP_SOM: - OP1(SLJIT_MOV, TMP1, 0, ARGUMENTS, 0); - OP1(SLJIT_MOV, TMP1, 0, SLJIT_MEM1(TMP1), SLJIT_OFFSETOF(jit_arguments, str)); - add_jump(compiler, backtracks, CMP(SLJIT_NOT_EQUAL, STR_PTR, 0, TMP1, 0)); - return cc; - - case OP_NOT_WORD_BOUNDARY: - case OP_WORD_BOUNDARY: - add_jump(compiler, &common->wordboundary, JUMP(SLJIT_FAST_CALL)); - add_jump(compiler, backtracks, JUMP(type == OP_NOT_WORD_BOUNDARY ? SLJIT_NOT_ZERO : SLJIT_ZERO)); - return cc; - - case OP_NOT_DIGIT: - case OP_DIGIT: - /* Digits are usually 0-9, so it is worth to optimize them. */ - detect_partial_match(common, backtracks); -#if defined SUPPORT_UTF && defined COMPILE_PCRE8 - if (common->utf && is_char7_bitset((const pcre_uint8*)common->ctypes - cbit_length + cbit_digit, FALSE)) - read_char7_type(common, type == OP_NOT_DIGIT); - else -#endif - read_char8_type(common, type == OP_NOT_DIGIT); - /* Flip the starting bit in the negative case. */ - OP2(SLJIT_AND | SLJIT_SET_E, SLJIT_UNUSED, 0, TMP1, 0, SLJIT_IMM, ctype_digit); - add_jump(compiler, backtracks, JUMP(type == OP_DIGIT ? SLJIT_ZERO : SLJIT_NOT_ZERO)); - return cc; - - case OP_NOT_WHITESPACE: - case OP_WHITESPACE: - detect_partial_match(common, backtracks); -#if defined SUPPORT_UTF && defined COMPILE_PCRE8 - if (common->utf && is_char7_bitset((const pcre_uint8*)common->ctypes - cbit_length + cbit_space, FALSE)) - read_char7_type(common, type == OP_NOT_WHITESPACE); - else -#endif - read_char8_type(common, type == OP_NOT_WHITESPACE); - OP2(SLJIT_AND | SLJIT_SET_E, SLJIT_UNUSED, 0, TMP1, 0, SLJIT_IMM, ctype_space); - add_jump(compiler, backtracks, JUMP(type == OP_WHITESPACE ? SLJIT_ZERO : SLJIT_NOT_ZERO)); - return cc; - - case OP_NOT_WORDCHAR: - case OP_WORDCHAR: - detect_partial_match(common, backtracks); -#if defined SUPPORT_UTF && defined COMPILE_PCRE8 - if (common->utf && is_char7_bitset((const pcre_uint8*)common->ctypes - cbit_length + cbit_word, FALSE)) - read_char7_type(common, type == OP_NOT_WORDCHAR); - else -#endif - read_char8_type(common, type == OP_NOT_WORDCHAR); - OP2(SLJIT_AND | SLJIT_SET_E, SLJIT_UNUSED, 0, TMP1, 0, SLJIT_IMM, ctype_word); - add_jump(compiler, backtracks, JUMP(type == OP_WORDCHAR ? SLJIT_ZERO : SLJIT_NOT_ZERO)); - return cc; - - case OP_ANY: - detect_partial_match(common, backtracks); - read_char_range(common, common->nlmin, common->nlmax, TRUE); - if (common->nltype == NLTYPE_FIXED && common->newline > 255) - { - jump[0] = CMP(SLJIT_NOT_EQUAL, TMP1, 0, SLJIT_IMM, (common->newline >> 8) & 0xff); - end_list = NULL; - if (common->mode != JIT_PARTIAL_HARD_COMPILE) - add_jump(compiler, &end_list, CMP(SLJIT_GREATER_EQUAL, STR_PTR, 0, STR_END, 0)); - else - check_str_end(common, &end_list); - - OP1(MOV_UCHAR, TMP1, 0, SLJIT_MEM1(STR_PTR), 0); - add_jump(compiler, backtracks, CMP(SLJIT_EQUAL, TMP1, 0, SLJIT_IMM, common->newline & 0xff)); - set_jumps(end_list, LABEL()); - JUMPHERE(jump[0]); - } - else - check_newlinechar(common, common->nltype, backtracks, TRUE); - return cc; - - case OP_ALLANY: - detect_partial_match(common, backtracks); -#ifdef SUPPORT_UTF - if (common->utf) - { - OP1(MOV_UCHAR, TMP1, 0, SLJIT_MEM1(STR_PTR), 0); - OP2(SLJIT_ADD, STR_PTR, 0, STR_PTR, 0, SLJIT_IMM, IN_UCHARS(1)); -#if defined COMPILE_PCRE8 || defined COMPILE_PCRE16 -#if defined COMPILE_PCRE8 - jump[0] = CMP(SLJIT_LESS, TMP1, 0, SLJIT_IMM, 0xc0); - OP1(SLJIT_MOV_UB, TMP1, 0, SLJIT_MEM1(TMP1), (sljit_sw)PRIV(utf8_table4) - 0xc0); - OP2(SLJIT_ADD, STR_PTR, 0, STR_PTR, 0, TMP1, 0); -#elif defined COMPILE_PCRE16 - jump[0] = CMP(SLJIT_LESS, TMP1, 0, SLJIT_IMM, 0xd800); - OP2(SLJIT_AND, TMP1, 0, TMP1, 0, SLJIT_IMM, 0xfc00); - OP2(SLJIT_SUB | SLJIT_SET_E, SLJIT_UNUSED, 0, TMP1, 0, SLJIT_IMM, 0xd800); - OP_FLAGS(SLJIT_MOV, TMP1, 0, SLJIT_UNUSED, 0, SLJIT_EQUAL); - OP2(SLJIT_SHL, TMP1, 0, TMP1, 0, SLJIT_IMM, 1); - OP2(SLJIT_ADD, STR_PTR, 0, STR_PTR, 0, TMP1, 0); -#endif - JUMPHERE(jump[0]); -#endif /* COMPILE_PCRE[8|16] */ - return cc; - } -#endif - OP2(SLJIT_ADD, STR_PTR, 0, STR_PTR, 0, SLJIT_IMM, IN_UCHARS(1)); - return cc; - - case OP_ANYBYTE: - detect_partial_match(common, backtracks); - OP2(SLJIT_ADD, STR_PTR, 0, STR_PTR, 0, SLJIT_IMM, IN_UCHARS(1)); - return cc; - -#ifdef SUPPORT_UTF -#ifdef SUPPORT_UCP - case OP_NOTPROP: - case OP_PROP: - propdata[0] = XCL_HASPROP; - propdata[1] = type == OP_NOTPROP ? XCL_NOTPROP : XCL_PROP; - propdata[2] = cc[0]; - propdata[3] = cc[1]; - propdata[4] = XCL_END; - compile_xclass_matchingpath(common, propdata, backtracks); - return cc + 2; -#endif -#endif - - case OP_ANYNL: - detect_partial_match(common, backtracks); - read_char_range(common, common->bsr_nlmin, common->bsr_nlmax, FALSE); - jump[0] = CMP(SLJIT_NOT_EQUAL, TMP1, 0, SLJIT_IMM, CHAR_CR); - /* We don't need to handle soft partial matching case. */ - end_list = NULL; - if (common->mode != JIT_PARTIAL_HARD_COMPILE) - add_jump(compiler, &end_list, CMP(SLJIT_GREATER_EQUAL, STR_PTR, 0, STR_END, 0)); - else - check_str_end(common, &end_list); - OP1(MOV_UCHAR, TMP1, 0, SLJIT_MEM1(STR_PTR), 0); - jump[1] = CMP(SLJIT_NOT_EQUAL, TMP1, 0, SLJIT_IMM, CHAR_NL); - OP2(SLJIT_ADD, STR_PTR, 0, STR_PTR, 0, SLJIT_IMM, IN_UCHARS(1)); - jump[2] = JUMP(SLJIT_JUMP); - JUMPHERE(jump[0]); - check_newlinechar(common, common->bsr_nltype, backtracks, FALSE); - set_jumps(end_list, LABEL()); - JUMPHERE(jump[1]); - JUMPHERE(jump[2]); - return cc; - - case OP_NOT_HSPACE: - case OP_HSPACE: - detect_partial_match(common, backtracks); - read_char_range(common, 0x9, 0x3000, type == OP_NOT_HSPACE); - add_jump(compiler, &common->hspace, JUMP(SLJIT_FAST_CALL)); - add_jump(compiler, backtracks, JUMP(type == OP_NOT_HSPACE ? SLJIT_NOT_ZERO : SLJIT_ZERO)); - return cc; - - case OP_NOT_VSPACE: - case OP_VSPACE: - detect_partial_match(common, backtracks); - read_char_range(common, 0xa, 0x2029, type == OP_NOT_VSPACE); - add_jump(compiler, &common->vspace, JUMP(SLJIT_FAST_CALL)); - add_jump(compiler, backtracks, JUMP(type == OP_NOT_VSPACE ? SLJIT_NOT_ZERO : SLJIT_ZERO)); - return cc; - -#ifdef SUPPORT_UCP - case OP_EXTUNI: - detect_partial_match(common, backtracks); - read_char(common); - add_jump(compiler, &common->getucd, JUMP(SLJIT_FAST_CALL)); - OP1(SLJIT_MOV, TMP1, 0, SLJIT_IMM, (sljit_sw)PRIV(ucd_records) + SLJIT_OFFSETOF(ucd_record, gbprop)); - /* Optimize register allocation: use a real register. */ - OP1(SLJIT_MOV, SLJIT_MEM1(SLJIT_SP), LOCALS0, STACK_TOP, 0); - OP1(SLJIT_MOV_UB, STACK_TOP, 0, SLJIT_MEM2(TMP1, TMP2), 3); - - label = LABEL(); - jump[0] = CMP(SLJIT_GREATER_EQUAL, STR_PTR, 0, STR_END, 0); - OP1(SLJIT_MOV, TMP3, 0, STR_PTR, 0); - read_char(common); - add_jump(compiler, &common->getucd, JUMP(SLJIT_FAST_CALL)); - OP1(SLJIT_MOV, TMP1, 0, SLJIT_IMM, (sljit_sw)PRIV(ucd_records) + SLJIT_OFFSETOF(ucd_record, gbprop)); - OP1(SLJIT_MOV_UB, TMP2, 0, SLJIT_MEM2(TMP1, TMP2), 3); - - OP2(SLJIT_SHL, STACK_TOP, 0, STACK_TOP, 0, SLJIT_IMM, 2); - OP1(SLJIT_MOV_UI, TMP1, 0, SLJIT_MEM1(STACK_TOP), (sljit_sw)PRIV(ucp_gbtable)); - OP1(SLJIT_MOV, STACK_TOP, 0, TMP2, 0); - OP2(SLJIT_SHL, TMP2, 0, SLJIT_IMM, 1, TMP2, 0); - OP2(SLJIT_AND | SLJIT_SET_E, SLJIT_UNUSED, 0, TMP1, 0, TMP2, 0); - JUMPTO(SLJIT_NOT_ZERO, label); - - OP1(SLJIT_MOV, STR_PTR, 0, TMP3, 0); - JUMPHERE(jump[0]); - OP1(SLJIT_MOV, STACK_TOP, 0, SLJIT_MEM1(SLJIT_SP), LOCALS0); - - if (common->mode == JIT_PARTIAL_HARD_COMPILE) - { - jump[0] = CMP(SLJIT_LESS, STR_PTR, 0, STR_END, 0); - /* Since we successfully read a char above, partial matching must occure. */ - check_partial(common, TRUE); - JUMPHERE(jump[0]); - } - return cc; -#endif - - case OP_EODN: - /* Requires rather complex checks. */ - jump[0] = CMP(SLJIT_GREATER_EQUAL, STR_PTR, 0, STR_END, 0); - if (common->nltype == NLTYPE_FIXED && common->newline > 255) - { - OP2(SLJIT_ADD, TMP2, 0, STR_PTR, 0, SLJIT_IMM, IN_UCHARS(2)); - OP1(MOV_UCHAR, TMP1, 0, SLJIT_MEM1(STR_PTR), IN_UCHARS(0)); - if (common->mode == JIT_COMPILE) - add_jump(compiler, backtracks, CMP(SLJIT_NOT_EQUAL, TMP2, 0, STR_END, 0)); - else - { - jump[1] = CMP(SLJIT_EQUAL, TMP2, 0, STR_END, 0); - OP2(SLJIT_SUB | SLJIT_SET_U, SLJIT_UNUSED, 0, TMP2, 0, STR_END, 0); - OP_FLAGS(SLJIT_MOV, TMP2, 0, SLJIT_UNUSED, 0, SLJIT_LESS); - OP2(SLJIT_SUB | SLJIT_SET_E, SLJIT_UNUSED, 0, TMP1, 0, SLJIT_IMM, (common->newline >> 8) & 0xff); - OP_FLAGS(SLJIT_OR | SLJIT_SET_E, TMP2, 0, TMP2, 0, SLJIT_NOT_EQUAL); - add_jump(compiler, backtracks, JUMP(SLJIT_NOT_EQUAL)); - check_partial(common, TRUE); - add_jump(compiler, backtracks, JUMP(SLJIT_JUMP)); - JUMPHERE(jump[1]); - } - OP1(MOV_UCHAR, TMP2, 0, SLJIT_MEM1(STR_PTR), IN_UCHARS(1)); - add_jump(compiler, backtracks, CMP(SLJIT_NOT_EQUAL, TMP1, 0, SLJIT_IMM, (common->newline >> 8) & 0xff)); - add_jump(compiler, backtracks, CMP(SLJIT_NOT_EQUAL, TMP2, 0, SLJIT_IMM, common->newline & 0xff)); - } - else if (common->nltype == NLTYPE_FIXED) - { - OP2(SLJIT_ADD, TMP2, 0, STR_PTR, 0, SLJIT_IMM, IN_UCHARS(1)); - OP1(MOV_UCHAR, TMP1, 0, SLJIT_MEM1(STR_PTR), IN_UCHARS(0)); - add_jump(compiler, backtracks, CMP(SLJIT_NOT_EQUAL, TMP2, 0, STR_END, 0)); - add_jump(compiler, backtracks, CMP(SLJIT_NOT_EQUAL, TMP1, 0, SLJIT_IMM, common->newline)); - } - else - { - OP1(MOV_UCHAR, TMP1, 0, SLJIT_MEM1(STR_PTR), IN_UCHARS(0)); - jump[1] = CMP(SLJIT_NOT_EQUAL, TMP1, 0, SLJIT_IMM, CHAR_CR); - OP2(SLJIT_ADD, TMP2, 0, STR_PTR, 0, SLJIT_IMM, IN_UCHARS(2)); - OP2(SLJIT_SUB | SLJIT_SET_U, SLJIT_UNUSED, 0, TMP2, 0, STR_END, 0); - jump[2] = JUMP(SLJIT_GREATER); - add_jump(compiler, backtracks, JUMP(SLJIT_LESS)); - /* Equal. */ - OP1(MOV_UCHAR, TMP1, 0, SLJIT_MEM1(STR_PTR), IN_UCHARS(1)); - jump[3] = CMP(SLJIT_EQUAL, TMP1, 0, SLJIT_IMM, CHAR_NL); - add_jump(compiler, backtracks, JUMP(SLJIT_JUMP)); - - JUMPHERE(jump[1]); - if (common->nltype == NLTYPE_ANYCRLF) - { - OP2(SLJIT_ADD, TMP2, 0, STR_PTR, 0, SLJIT_IMM, IN_UCHARS(1)); - add_jump(compiler, backtracks, CMP(SLJIT_LESS, TMP2, 0, STR_END, 0)); - add_jump(compiler, backtracks, CMP(SLJIT_NOT_EQUAL, TMP1, 0, SLJIT_IMM, CHAR_NL)); - } - else - { - OP1(SLJIT_MOV, SLJIT_MEM1(SLJIT_SP), LOCALS1, STR_PTR, 0); - read_char_range(common, common->nlmin, common->nlmax, TRUE); - add_jump(compiler, backtracks, CMP(SLJIT_NOT_EQUAL, STR_PTR, 0, STR_END, 0)); - add_jump(compiler, &common->anynewline, JUMP(SLJIT_FAST_CALL)); - add_jump(compiler, backtracks, JUMP(SLJIT_ZERO)); - OP1(SLJIT_MOV, STR_PTR, 0, SLJIT_MEM1(SLJIT_SP), LOCALS1); - } - JUMPHERE(jump[2]); - JUMPHERE(jump[3]); - } - JUMPHERE(jump[0]); - check_partial(common, FALSE); - return cc; - - case OP_EOD: - add_jump(compiler, backtracks, CMP(SLJIT_LESS, STR_PTR, 0, STR_END, 0)); - check_partial(common, FALSE); - return cc; - - case OP_CIRC: - OP1(SLJIT_MOV, TMP2, 0, ARGUMENTS, 0); - OP1(SLJIT_MOV, TMP1, 0, SLJIT_MEM1(TMP2), SLJIT_OFFSETOF(jit_arguments, begin)); - add_jump(compiler, backtracks, CMP(SLJIT_GREATER, STR_PTR, 0, TMP1, 0)); - OP1(SLJIT_MOV_UB, TMP2, 0, SLJIT_MEM1(TMP2), SLJIT_OFFSETOF(jit_arguments, notbol)); - add_jump(compiler, backtracks, CMP(SLJIT_NOT_EQUAL, TMP2, 0, SLJIT_IMM, 0)); - return cc; - - case OP_CIRCM: - OP1(SLJIT_MOV, TMP2, 0, ARGUMENTS, 0); - OP1(SLJIT_MOV, TMP1, 0, SLJIT_MEM1(TMP2), SLJIT_OFFSETOF(jit_arguments, begin)); - jump[1] = CMP(SLJIT_GREATER, STR_PTR, 0, TMP1, 0); - OP1(SLJIT_MOV_UB, TMP2, 0, SLJIT_MEM1(TMP2), SLJIT_OFFSETOF(jit_arguments, notbol)); - add_jump(compiler, backtracks, CMP(SLJIT_NOT_EQUAL, TMP2, 0, SLJIT_IMM, 0)); - jump[0] = JUMP(SLJIT_JUMP); - JUMPHERE(jump[1]); - - add_jump(compiler, backtracks, CMP(SLJIT_GREATER_EQUAL, STR_PTR, 0, STR_END, 0)); - if (common->nltype == NLTYPE_FIXED && common->newline > 255) - { - OP2(SLJIT_SUB, TMP2, 0, STR_PTR, 0, SLJIT_IMM, IN_UCHARS(2)); - add_jump(compiler, backtracks, CMP(SLJIT_LESS, TMP2, 0, TMP1, 0)); - OP1(MOV_UCHAR, TMP1, 0, SLJIT_MEM1(STR_PTR), IN_UCHARS(-2)); - OP1(MOV_UCHAR, TMP2, 0, SLJIT_MEM1(STR_PTR), IN_UCHARS(-1)); - add_jump(compiler, backtracks, CMP(SLJIT_NOT_EQUAL, TMP1, 0, SLJIT_IMM, (common->newline >> 8) & 0xff)); - add_jump(compiler, backtracks, CMP(SLJIT_NOT_EQUAL, TMP2, 0, SLJIT_IMM, common->newline & 0xff)); - } - else - { - skip_char_back(common); - read_char_range(common, common->nlmin, common->nlmax, TRUE); - check_newlinechar(common, common->nltype, backtracks, FALSE); - } - JUMPHERE(jump[0]); - return cc; - - case OP_DOLL: - OP1(SLJIT_MOV, TMP2, 0, ARGUMENTS, 0); - OP1(SLJIT_MOV_UB, TMP2, 0, SLJIT_MEM1(TMP2), SLJIT_OFFSETOF(jit_arguments, noteol)); - add_jump(compiler, backtracks, CMP(SLJIT_NOT_EQUAL, TMP2, 0, SLJIT_IMM, 0)); - - if (!common->endonly) - compile_char1_matchingpath(common, OP_EODN, cc, backtracks); - else - { - add_jump(compiler, backtracks, CMP(SLJIT_LESS, STR_PTR, 0, STR_END, 0)); - check_partial(common, FALSE); - } - return cc; - - case OP_DOLLM: - jump[1] = CMP(SLJIT_LESS, STR_PTR, 0, STR_END, 0); - OP1(SLJIT_MOV, TMP2, 0, ARGUMENTS, 0); - OP1(SLJIT_MOV_UB, TMP2, 0, SLJIT_MEM1(TMP2), SLJIT_OFFSETOF(jit_arguments, noteol)); - add_jump(compiler, backtracks, CMP(SLJIT_NOT_EQUAL, TMP2, 0, SLJIT_IMM, 0)); - check_partial(common, FALSE); - jump[0] = JUMP(SLJIT_JUMP); - JUMPHERE(jump[1]); - - if (common->nltype == NLTYPE_FIXED && common->newline > 255) - { - OP2(SLJIT_ADD, TMP2, 0, STR_PTR, 0, SLJIT_IMM, IN_UCHARS(2)); - OP1(MOV_UCHAR, TMP1, 0, SLJIT_MEM1(STR_PTR), IN_UCHARS(0)); - if (common->mode == JIT_COMPILE) - add_jump(compiler, backtracks, CMP(SLJIT_GREATER, TMP2, 0, STR_END, 0)); - else - { - jump[1] = CMP(SLJIT_LESS_EQUAL, TMP2, 0, STR_END, 0); - /* STR_PTR = STR_END - IN_UCHARS(1) */ - add_jump(compiler, backtracks, CMP(SLJIT_NOT_EQUAL, TMP1, 0, SLJIT_IMM, (common->newline >> 8) & 0xff)); - check_partial(common, TRUE); - add_jump(compiler, backtracks, JUMP(SLJIT_JUMP)); - JUMPHERE(jump[1]); - } - - OP1(MOV_UCHAR, TMP2, 0, SLJIT_MEM1(STR_PTR), IN_UCHARS(1)); - add_jump(compiler, backtracks, CMP(SLJIT_NOT_EQUAL, TMP1, 0, SLJIT_IMM, (common->newline >> 8) & 0xff)); - add_jump(compiler, backtracks, CMP(SLJIT_NOT_EQUAL, TMP2, 0, SLJIT_IMM, common->newline & 0xff)); - } - else - { - peek_char(common, common->nlmax); - check_newlinechar(common, common->nltype, backtracks, FALSE); - } - JUMPHERE(jump[0]); - return cc; - - case OP_CHAR: - case OP_CHARI: - length = 1; -#ifdef SUPPORT_UTF - if (common->utf && HAS_EXTRALEN(*cc)) length += GET_EXTRALEN(*cc); -#endif - if (common->mode == JIT_COMPILE && (type == OP_CHAR || !char_has_othercase(common, cc) || char_get_othercase_bit(common, cc) != 0)) - { - OP2(SLJIT_ADD, STR_PTR, 0, STR_PTR, 0, SLJIT_IMM, IN_UCHARS(length)); - add_jump(compiler, backtracks, CMP(SLJIT_GREATER, STR_PTR, 0, STR_END, 0)); - - context.length = IN_UCHARS(length); - context.sourcereg = -1; -#if defined SLJIT_UNALIGNED && SLJIT_UNALIGNED - context.ucharptr = 0; -#endif - return byte_sequence_compare(common, type == OP_CHARI, cc, &context, backtracks); - } - - detect_partial_match(common, backtracks); -#ifdef SUPPORT_UTF - if (common->utf) - { - GETCHAR(c, cc); - } - else -#endif - c = *cc; - - if (type == OP_CHAR || !char_has_othercase(common, cc)) - { - read_char_range(common, c, c, FALSE); - add_jump(compiler, backtracks, CMP(SLJIT_NOT_EQUAL, TMP1, 0, SLJIT_IMM, c)); - return cc + length; - } - oc = char_othercase(common, c); - read_char_range(common, c < oc ? c : oc, c > oc ? c : oc, FALSE); - bit = c ^ oc; - if (is_powerof2(bit)) - { - OP2(SLJIT_OR, TMP1, 0, TMP1, 0, SLJIT_IMM, bit); - add_jump(compiler, backtracks, CMP(SLJIT_NOT_EQUAL, TMP1, 0, SLJIT_IMM, c | bit)); - return cc + length; - } - jump[0] = CMP(SLJIT_EQUAL, TMP1, 0, SLJIT_IMM, c); - add_jump(compiler, backtracks, CMP(SLJIT_NOT_EQUAL, TMP1, 0, SLJIT_IMM, oc)); - JUMPHERE(jump[0]); - return cc + length; - - case OP_NOT: - case OP_NOTI: - detect_partial_match(common, backtracks); - length = 1; -#ifdef SUPPORT_UTF - if (common->utf) - { -#ifdef COMPILE_PCRE8 - c = *cc; - if (c < 128) - { - OP1(SLJIT_MOV_UB, TMP1, 0, SLJIT_MEM1(STR_PTR), 0); - if (type == OP_NOT || !char_has_othercase(common, cc)) - add_jump(compiler, backtracks, CMP(SLJIT_EQUAL, TMP1, 0, SLJIT_IMM, c)); - else - { - /* Since UTF8 code page is fixed, we know that c is in [a-z] or [A-Z] range. */ - OP2(SLJIT_OR, TMP2, 0, TMP1, 0, SLJIT_IMM, 0x20); - add_jump(compiler, backtracks, CMP(SLJIT_EQUAL, TMP2, 0, SLJIT_IMM, c | 0x20)); - } - /* Skip the variable-length character. */ - OP2(SLJIT_ADD, STR_PTR, 0, STR_PTR, 0, SLJIT_IMM, IN_UCHARS(1)); - jump[0] = CMP(SLJIT_LESS, TMP1, 0, SLJIT_IMM, 0xc0); - OP1(MOV_UCHAR, TMP1, 0, SLJIT_MEM1(TMP1), (sljit_sw)PRIV(utf8_table4) - 0xc0); - OP2(SLJIT_ADD, STR_PTR, 0, STR_PTR, 0, TMP1, 0); - JUMPHERE(jump[0]); - return cc + 1; - } - else -#endif /* COMPILE_PCRE8 */ - { - GETCHARLEN(c, cc, length); - } - } - else -#endif /* SUPPORT_UTF */ - c = *cc; - - if (type == OP_NOT || !char_has_othercase(common, cc)) - { - read_char_range(common, c, c, TRUE); - add_jump(compiler, backtracks, CMP(SLJIT_EQUAL, TMP1, 0, SLJIT_IMM, c)); - } - else - { - oc = char_othercase(common, c); - read_char_range(common, c < oc ? c : oc, c > oc ? c : oc, TRUE); - bit = c ^ oc; - if (is_powerof2(bit)) - { - OP2(SLJIT_OR, TMP1, 0, TMP1, 0, SLJIT_IMM, bit); - add_jump(compiler, backtracks, CMP(SLJIT_EQUAL, TMP1, 0, SLJIT_IMM, c | bit)); - } - else - { - add_jump(compiler, backtracks, CMP(SLJIT_EQUAL, TMP1, 0, SLJIT_IMM, c)); - add_jump(compiler, backtracks, CMP(SLJIT_EQUAL, TMP1, 0, SLJIT_IMM, oc)); - } - } - return cc + length; - - case OP_CLASS: - case OP_NCLASS: - detect_partial_match(common, backtracks); - -#if defined SUPPORT_UTF && defined COMPILE_PCRE8 - bit = (common->utf && is_char7_bitset((const pcre_uint8 *)cc, type == OP_NCLASS)) ? 127 : 255; - read_char_range(common, 0, bit, type == OP_NCLASS); -#else - read_char_range(common, 0, 255, type == OP_NCLASS); -#endif - - if (check_class_ranges(common, (const pcre_uint8 *)cc, type == OP_NCLASS, FALSE, backtracks)) - return cc + 32 / sizeof(pcre_uchar); - -#if defined SUPPORT_UTF && defined COMPILE_PCRE8 - jump[0] = NULL; - if (common->utf) - { - jump[0] = CMP(SLJIT_GREATER, TMP1, 0, SLJIT_IMM, bit); - if (type == OP_CLASS) - { - add_jump(compiler, backtracks, jump[0]); - jump[0] = NULL; - } - } -#elif !defined COMPILE_PCRE8 - jump[0] = CMP(SLJIT_GREATER, TMP1, 0, SLJIT_IMM, 255); - if (type == OP_CLASS) - { - add_jump(compiler, backtracks, jump[0]); - jump[0] = NULL; - } -#endif /* SUPPORT_UTF && COMPILE_PCRE8 */ - - OP2(SLJIT_AND, TMP2, 0, TMP1, 0, SLJIT_IMM, 0x7); - OP2(SLJIT_LSHR, TMP1, 0, TMP1, 0, SLJIT_IMM, 3); - OP1(SLJIT_MOV_UB, TMP1, 0, SLJIT_MEM1(TMP1), (sljit_sw)cc); - OP2(SLJIT_SHL, TMP2, 0, SLJIT_IMM, 1, TMP2, 0); - OP2(SLJIT_AND | SLJIT_SET_E, SLJIT_UNUSED, 0, TMP1, 0, TMP2, 0); - add_jump(compiler, backtracks, JUMP(SLJIT_ZERO)); - -#if defined SUPPORT_UTF || !defined COMPILE_PCRE8 - if (jump[0] != NULL) - JUMPHERE(jump[0]); -#endif - - return cc + 32 / sizeof(pcre_uchar); - -#if defined SUPPORT_UTF || defined COMPILE_PCRE16 || defined COMPILE_PCRE32 - case OP_XCLASS: - compile_xclass_matchingpath(common, cc + LINK_SIZE, backtracks); - return cc + GET(cc, 0) - 1; -#endif - - case OP_REVERSE: - length = GET(cc, 0); - if (length == 0) - return cc + LINK_SIZE; - OP1(SLJIT_MOV, TMP1, 0, ARGUMENTS, 0); -#ifdef SUPPORT_UTF - if (common->utf) - { - OP1(SLJIT_MOV, TMP3, 0, SLJIT_MEM1(TMP1), SLJIT_OFFSETOF(jit_arguments, begin)); - OP1(SLJIT_MOV, TMP2, 0, SLJIT_IMM, length); - label = LABEL(); - add_jump(compiler, backtracks, CMP(SLJIT_LESS_EQUAL, STR_PTR, 0, TMP3, 0)); - skip_char_back(common); - OP2(SLJIT_SUB | SLJIT_SET_E, TMP2, 0, TMP2, 0, SLJIT_IMM, 1); - JUMPTO(SLJIT_NOT_ZERO, label); - } - else -#endif - { - OP1(SLJIT_MOV, TMP1, 0, SLJIT_MEM1(TMP1), SLJIT_OFFSETOF(jit_arguments, begin)); - OP2(SLJIT_SUB, STR_PTR, 0, STR_PTR, 0, SLJIT_IMM, IN_UCHARS(length)); - add_jump(compiler, backtracks, CMP(SLJIT_LESS, STR_PTR, 0, TMP1, 0)); - } - check_start_used_ptr(common); - return cc + LINK_SIZE; - } -SLJIT_ASSERT_STOP(); -return cc; -} - -static SLJIT_INLINE pcre_uchar *compile_charn_matchingpath(compiler_common *common, pcre_uchar *cc, pcre_uchar *ccend, jump_list **backtracks) -{ -/* This function consumes at least one input character. */ -/* To decrease the number of length checks, we try to concatenate the fixed length character sequences. */ -DEFINE_COMPILER; -pcre_uchar *ccbegin = cc; -compare_context context; -int size; - -context.length = 0; -do - { - if (cc >= ccend) - break; - - if (*cc == OP_CHAR) - { - size = 1; -#ifdef SUPPORT_UTF - if (common->utf && HAS_EXTRALEN(cc[1])) - size += GET_EXTRALEN(cc[1]); -#endif - } - else if (*cc == OP_CHARI) - { - size = 1; -#ifdef SUPPORT_UTF - if (common->utf) - { - if (char_has_othercase(common, cc + 1) && char_get_othercase_bit(common, cc + 1) == 0) - size = 0; - else if (HAS_EXTRALEN(cc[1])) - size += GET_EXTRALEN(cc[1]); - } - else -#endif - if (char_has_othercase(common, cc + 1) && char_get_othercase_bit(common, cc + 1) == 0) - size = 0; - } - else - size = 0; - - cc += 1 + size; - context.length += IN_UCHARS(size); - } -while (size > 0 && context.length <= 128); - -cc = ccbegin; -if (context.length > 0) - { - /* We have a fixed-length byte sequence. */ - OP2(SLJIT_ADD, STR_PTR, 0, STR_PTR, 0, SLJIT_IMM, context.length); - add_jump(compiler, backtracks, CMP(SLJIT_GREATER, STR_PTR, 0, STR_END, 0)); - - context.sourcereg = -1; -#if defined SLJIT_UNALIGNED && SLJIT_UNALIGNED - context.ucharptr = 0; -#endif - do cc = byte_sequence_compare(common, *cc == OP_CHARI, cc + 1, &context, backtracks); while (context.length > 0); - return cc; - } - -/* A non-fixed length character will be checked if length == 0. */ -return compile_char1_matchingpath(common, *cc, cc + 1, backtracks); -} - -/* Forward definitions. */ -static void compile_matchingpath(compiler_common *, pcre_uchar *, pcre_uchar *, backtrack_common *); -static void compile_backtrackingpath(compiler_common *, struct backtrack_common *); - -#define PUSH_BACKTRACK(size, ccstart, error) \ - do \ - { \ - backtrack = sljit_alloc_memory(compiler, (size)); \ - if (SLJIT_UNLIKELY(sljit_get_compiler_error(compiler))) \ - return error; \ - memset(backtrack, 0, size); \ - backtrack->prev = parent->top; \ - backtrack->cc = (ccstart); \ - parent->top = backtrack; \ - } \ - while (0) - -#define PUSH_BACKTRACK_NOVALUE(size, ccstart) \ - do \ - { \ - backtrack = sljit_alloc_memory(compiler, (size)); \ - if (SLJIT_UNLIKELY(sljit_get_compiler_error(compiler))) \ - return; \ - memset(backtrack, 0, size); \ - backtrack->prev = parent->top; \ - backtrack->cc = (ccstart); \ - parent->top = backtrack; \ - } \ - while (0) - -#define BACKTRACK_AS(type) ((type *)backtrack) - -static void compile_dnref_search(compiler_common *common, pcre_uchar *cc, jump_list **backtracks) -{ -/* The OVECTOR offset goes to TMP2. */ -DEFINE_COMPILER; -int count = GET2(cc, 1 + IMM2_SIZE); -pcre_uchar *slot = common->name_table + GET2(cc, 1) * common->name_entry_size; -unsigned int offset; -jump_list *found = NULL; - -SLJIT_ASSERT(*cc == OP_DNREF || *cc == OP_DNREFI); - -OP1(SLJIT_MOV, TMP1, 0, SLJIT_MEM1(SLJIT_SP), OVECTOR(1)); - -count--; -while (count-- > 0) - { - offset = GET2(slot, 0) << 1; - GET_LOCAL_BASE(TMP2, 0, OVECTOR(offset)); - add_jump(compiler, &found, CMP(SLJIT_NOT_EQUAL, SLJIT_MEM1(SLJIT_SP), OVECTOR(offset), TMP1, 0)); - slot += common->name_entry_size; - } - -offset = GET2(slot, 0) << 1; -GET_LOCAL_BASE(TMP2, 0, OVECTOR(offset)); -if (backtracks != NULL && !common->jscript_compat) - add_jump(compiler, backtracks, CMP(SLJIT_EQUAL, SLJIT_MEM1(SLJIT_SP), OVECTOR(offset), TMP1, 0)); - -set_jumps(found, LABEL()); -} - -static void compile_ref_matchingpath(compiler_common *common, pcre_uchar *cc, jump_list **backtracks, BOOL withchecks, BOOL emptyfail) -{ -DEFINE_COMPILER; -BOOL ref = (*cc == OP_REF || *cc == OP_REFI); -int offset = 0; -struct sljit_jump *jump = NULL; -struct sljit_jump *partial; -struct sljit_jump *nopartial; - -if (ref) - { - offset = GET2(cc, 1) << 1; - OP1(SLJIT_MOV, TMP1, 0, SLJIT_MEM1(SLJIT_SP), OVECTOR(offset)); - /* OVECTOR(1) contains the "string begin - 1" constant. */ - if (withchecks && !common->jscript_compat) - add_jump(compiler, backtracks, CMP(SLJIT_EQUAL, TMP1, 0, SLJIT_MEM1(SLJIT_SP), OVECTOR(1))); - } -else - OP1(SLJIT_MOV, TMP1, 0, SLJIT_MEM1(TMP2), 0); - -#if defined SUPPORT_UTF && defined SUPPORT_UCP -if (common->utf && *cc == OP_REFI) - { - SLJIT_ASSERT(TMP1 == SLJIT_R0 && STACK_TOP == SLJIT_R1 && TMP2 == SLJIT_R2); - if (ref) - OP1(SLJIT_MOV, TMP2, 0, SLJIT_MEM1(SLJIT_SP), OVECTOR(offset + 1)); - else - OP1(SLJIT_MOV, TMP2, 0, SLJIT_MEM1(TMP2), sizeof(sljit_sw)); - - if (withchecks) - jump = CMP(SLJIT_EQUAL, TMP1, 0, TMP2, 0); - - /* Needed to save important temporary registers. */ - OP1(SLJIT_MOV, SLJIT_MEM1(SLJIT_SP), LOCALS0, STACK_TOP, 0); - OP1(SLJIT_MOV, SLJIT_R1, 0, ARGUMENTS, 0); - OP1(SLJIT_MOV, SLJIT_MEM1(SLJIT_R1), SLJIT_OFFSETOF(jit_arguments, uchar_ptr), STR_PTR, 0); - sljit_emit_ijump(compiler, SLJIT_CALL3, SLJIT_IMM, SLJIT_FUNC_OFFSET(do_utf_caselesscmp)); - OP1(SLJIT_MOV, STACK_TOP, 0, SLJIT_MEM1(SLJIT_SP), LOCALS0); - if (common->mode == JIT_COMPILE) - add_jump(compiler, backtracks, CMP(SLJIT_LESS_EQUAL, SLJIT_RETURN_REG, 0, SLJIT_IMM, 1)); - else - { - add_jump(compiler, backtracks, CMP(SLJIT_EQUAL, SLJIT_RETURN_REG, 0, SLJIT_IMM, 0)); - nopartial = CMP(SLJIT_NOT_EQUAL, SLJIT_RETURN_REG, 0, SLJIT_IMM, 1); - check_partial(common, FALSE); - add_jump(compiler, backtracks, JUMP(SLJIT_JUMP)); - JUMPHERE(nopartial); - } - OP1(SLJIT_MOV, STR_PTR, 0, SLJIT_RETURN_REG, 0); - } -else -#endif /* SUPPORT_UTF && SUPPORT_UCP */ - { - if (ref) - OP2(SLJIT_SUB | SLJIT_SET_E, TMP2, 0, SLJIT_MEM1(SLJIT_SP), OVECTOR(offset + 1), TMP1, 0); - else - OP2(SLJIT_SUB | SLJIT_SET_E, TMP2, 0, SLJIT_MEM1(TMP2), sizeof(sljit_sw), TMP1, 0); - - if (withchecks) - jump = JUMP(SLJIT_ZERO); - - OP2(SLJIT_ADD, STR_PTR, 0, STR_PTR, 0, TMP2, 0); - partial = CMP(SLJIT_GREATER, STR_PTR, 0, STR_END, 0); - if (common->mode == JIT_COMPILE) - add_jump(compiler, backtracks, partial); - - add_jump(compiler, *cc == OP_REF ? &common->casefulcmp : &common->caselesscmp, JUMP(SLJIT_FAST_CALL)); - add_jump(compiler, backtracks, CMP(SLJIT_NOT_EQUAL, TMP2, 0, SLJIT_IMM, 0)); - - if (common->mode != JIT_COMPILE) - { - nopartial = JUMP(SLJIT_JUMP); - JUMPHERE(partial); - /* TMP2 -= STR_END - STR_PTR */ - OP2(SLJIT_SUB, TMP2, 0, TMP2, 0, STR_PTR, 0); - OP2(SLJIT_ADD, TMP2, 0, TMP2, 0, STR_END, 0); - partial = CMP(SLJIT_EQUAL, TMP2, 0, SLJIT_IMM, 0); - OP1(SLJIT_MOV, STR_PTR, 0, STR_END, 0); - add_jump(compiler, *cc == OP_REF ? &common->casefulcmp : &common->caselesscmp, JUMP(SLJIT_FAST_CALL)); - add_jump(compiler, backtracks, CMP(SLJIT_NOT_EQUAL, TMP2, 0, SLJIT_IMM, 0)); - JUMPHERE(partial); - check_partial(common, FALSE); - add_jump(compiler, backtracks, JUMP(SLJIT_JUMP)); - JUMPHERE(nopartial); - } - } - -if (jump != NULL) - { - if (emptyfail) - add_jump(compiler, backtracks, jump); - else - JUMPHERE(jump); - } -} - -static SLJIT_INLINE pcre_uchar *compile_ref_iterator_matchingpath(compiler_common *common, pcre_uchar *cc, backtrack_common *parent) -{ -DEFINE_COMPILER; -BOOL ref = (*cc == OP_REF || *cc == OP_REFI); -backtrack_common *backtrack; -pcre_uchar type; -int offset = 0; -struct sljit_label *label; -struct sljit_jump *zerolength; -struct sljit_jump *jump = NULL; -pcre_uchar *ccbegin = cc; -int min = 0, max = 0; -BOOL minimize; - -PUSH_BACKTRACK(sizeof(iterator_backtrack), cc, NULL); - -if (ref) - offset = GET2(cc, 1) << 1; -else - cc += IMM2_SIZE; -type = cc[1 + IMM2_SIZE]; - -SLJIT_COMPILE_ASSERT((OP_CRSTAR & 0x1) == 0, crstar_opcode_must_be_even); -minimize = (type & 0x1) != 0; -switch(type) - { - case OP_CRSTAR: - case OP_CRMINSTAR: - min = 0; - max = 0; - cc += 1 + IMM2_SIZE + 1; - break; - case OP_CRPLUS: - case OP_CRMINPLUS: - min = 1; - max = 0; - cc += 1 + IMM2_SIZE + 1; - break; - case OP_CRQUERY: - case OP_CRMINQUERY: - min = 0; - max = 1; - cc += 1 + IMM2_SIZE + 1; - break; - case OP_CRRANGE: - case OP_CRMINRANGE: - min = GET2(cc, 1 + IMM2_SIZE + 1); - max = GET2(cc, 1 + IMM2_SIZE + 1 + IMM2_SIZE); - cc += 1 + IMM2_SIZE + 1 + 2 * IMM2_SIZE; - break; - default: - SLJIT_ASSERT_STOP(); - break; - } - -if (!minimize) - { - if (min == 0) - { - allocate_stack(common, 2); - if (ref) - OP1(SLJIT_MOV, TMP1, 0, SLJIT_MEM1(SLJIT_SP), OVECTOR(offset)); - OP1(SLJIT_MOV, SLJIT_MEM1(STACK_TOP), STACK(0), STR_PTR, 0); - OP1(SLJIT_MOV, SLJIT_MEM1(STACK_TOP), STACK(1), SLJIT_IMM, 0); - /* Temporary release of STR_PTR. */ - OP2(SLJIT_SUB, STACK_TOP, 0, STACK_TOP, 0, SLJIT_IMM, sizeof(sljit_sw)); - /* Handles both invalid and empty cases. Since the minimum repeat, - is zero the invalid case is basically the same as an empty case. */ - if (ref) - zerolength = CMP(SLJIT_EQUAL, TMP1, 0, SLJIT_MEM1(SLJIT_SP), OVECTOR(offset + 1)); - else - { - compile_dnref_search(common, ccbegin, NULL); - OP1(SLJIT_MOV, TMP1, 0, SLJIT_MEM1(TMP2), 0); - OP1(SLJIT_MOV, SLJIT_MEM1(SLJIT_SP), POSSESSIVE1, TMP2, 0); - zerolength = CMP(SLJIT_EQUAL, TMP1, 0, SLJIT_MEM1(TMP2), sizeof(sljit_sw)); - } - /* Restore if not zero length. */ - OP2(SLJIT_ADD, STACK_TOP, 0, STACK_TOP, 0, SLJIT_IMM, sizeof(sljit_sw)); - } - else - { - allocate_stack(common, 1); - if (ref) - OP1(SLJIT_MOV, TMP1, 0, SLJIT_MEM1(SLJIT_SP), OVECTOR(offset)); - OP1(SLJIT_MOV, SLJIT_MEM1(STACK_TOP), STACK(0), SLJIT_IMM, 0); - if (ref) - { - add_jump(compiler, &backtrack->topbacktracks, CMP(SLJIT_EQUAL, TMP1, 0, SLJIT_MEM1(SLJIT_SP), OVECTOR(1))); - zerolength = CMP(SLJIT_EQUAL, TMP1, 0, SLJIT_MEM1(SLJIT_SP), OVECTOR(offset + 1)); - } - else - { - compile_dnref_search(common, ccbegin, &backtrack->topbacktracks); - OP1(SLJIT_MOV, TMP1, 0, SLJIT_MEM1(TMP2), 0); - OP1(SLJIT_MOV, SLJIT_MEM1(SLJIT_SP), POSSESSIVE1, TMP2, 0); - zerolength = CMP(SLJIT_EQUAL, TMP1, 0, SLJIT_MEM1(TMP2), sizeof(sljit_sw)); - } - } - - if (min > 1 || max > 1) - OP1(SLJIT_MOV, SLJIT_MEM1(SLJIT_SP), POSSESSIVE0, SLJIT_IMM, 0); - - label = LABEL(); - if (!ref) - OP1(SLJIT_MOV, TMP2, 0, SLJIT_MEM1(SLJIT_SP), POSSESSIVE1); - compile_ref_matchingpath(common, ccbegin, &backtrack->topbacktracks, FALSE, FALSE); - - if (min > 1 || max > 1) - { - OP1(SLJIT_MOV, TMP1, 0, SLJIT_MEM1(SLJIT_SP), POSSESSIVE0); - OP2(SLJIT_ADD, TMP1, 0, TMP1, 0, SLJIT_IMM, 1); - OP1(SLJIT_MOV, SLJIT_MEM1(SLJIT_SP), POSSESSIVE0, TMP1, 0); - if (min > 1) - CMPTO(SLJIT_LESS, TMP1, 0, SLJIT_IMM, min, label); - if (max > 1) - { - jump = CMP(SLJIT_GREATER_EQUAL, TMP1, 0, SLJIT_IMM, max); - allocate_stack(common, 1); - OP1(SLJIT_MOV, SLJIT_MEM1(STACK_TOP), STACK(0), STR_PTR, 0); - JUMPTO(SLJIT_JUMP, label); - JUMPHERE(jump); - } - } - - if (max == 0) - { - /* Includes min > 1 case as well. */ - allocate_stack(common, 1); - OP1(SLJIT_MOV, SLJIT_MEM1(STACK_TOP), STACK(0), STR_PTR, 0); - JUMPTO(SLJIT_JUMP, label); - } - - JUMPHERE(zerolength); - BACKTRACK_AS(iterator_backtrack)->matchingpath = LABEL(); - - count_match(common); - return cc; - } - -allocate_stack(common, ref ? 2 : 3); -if (ref) - OP1(SLJIT_MOV, TMP1, 0, SLJIT_MEM1(SLJIT_SP), OVECTOR(offset)); -OP1(SLJIT_MOV, SLJIT_MEM1(STACK_TOP), STACK(0), SLJIT_IMM, 0); -if (type != OP_CRMINSTAR) - OP1(SLJIT_MOV, SLJIT_MEM1(STACK_TOP), STACK(1), SLJIT_IMM, 0); - -if (min == 0) - { - /* Handles both invalid and empty cases. Since the minimum repeat, - is zero the invalid case is basically the same as an empty case. */ - if (ref) - zerolength = CMP(SLJIT_EQUAL, TMP1, 0, SLJIT_MEM1(SLJIT_SP), OVECTOR(offset + 1)); - else - { - compile_dnref_search(common, ccbegin, NULL); - OP1(SLJIT_MOV, TMP1, 0, SLJIT_MEM1(TMP2), 0); - OP1(SLJIT_MOV, SLJIT_MEM1(STACK_TOP), STACK(2), TMP2, 0); - zerolength = CMP(SLJIT_EQUAL, TMP1, 0, SLJIT_MEM1(TMP2), sizeof(sljit_sw)); - } - /* Length is non-zero, we can match real repeats. */ - OP1(SLJIT_MOV, SLJIT_MEM1(STACK_TOP), STACK(0), STR_PTR, 0); - jump = JUMP(SLJIT_JUMP); - } -else - { - if (ref) - { - add_jump(compiler, &backtrack->topbacktracks, CMP(SLJIT_EQUAL, TMP1, 0, SLJIT_MEM1(SLJIT_SP), OVECTOR(1))); - zerolength = CMP(SLJIT_EQUAL, TMP1, 0, SLJIT_MEM1(SLJIT_SP), OVECTOR(offset + 1)); - } - else - { - compile_dnref_search(common, ccbegin, &backtrack->topbacktracks); - OP1(SLJIT_MOV, TMP1, 0, SLJIT_MEM1(TMP2), 0); - OP1(SLJIT_MOV, SLJIT_MEM1(STACK_TOP), STACK(2), TMP2, 0); - zerolength = CMP(SLJIT_EQUAL, TMP1, 0, SLJIT_MEM1(TMP2), sizeof(sljit_sw)); - } - } - -BACKTRACK_AS(iterator_backtrack)->matchingpath = LABEL(); -if (max > 0) - add_jump(compiler, &backtrack->topbacktracks, CMP(SLJIT_GREATER_EQUAL, SLJIT_MEM1(STACK_TOP), STACK(1), SLJIT_IMM, max)); - -if (!ref) - OP1(SLJIT_MOV, TMP2, 0, SLJIT_MEM1(STACK_TOP), STACK(2)); -compile_ref_matchingpath(common, ccbegin, &backtrack->topbacktracks, TRUE, TRUE); -OP1(SLJIT_MOV, SLJIT_MEM1(STACK_TOP), STACK(0), STR_PTR, 0); - -if (min > 1) - { - OP1(SLJIT_MOV, TMP1, 0, SLJIT_MEM1(STACK_TOP), STACK(1)); - OP2(SLJIT_ADD, TMP1, 0, TMP1, 0, SLJIT_IMM, 1); - OP1(SLJIT_MOV, SLJIT_MEM1(STACK_TOP), STACK(1), TMP1, 0); - CMPTO(SLJIT_LESS, TMP1, 0, SLJIT_IMM, min, BACKTRACK_AS(iterator_backtrack)->matchingpath); - } -else if (max > 0) - OP2(SLJIT_ADD, SLJIT_MEM1(STACK_TOP), STACK(1), SLJIT_MEM1(STACK_TOP), STACK(1), SLJIT_IMM, 1); - -if (jump != NULL) - JUMPHERE(jump); -JUMPHERE(zerolength); - -count_match(common); -return cc; -} - -static SLJIT_INLINE pcre_uchar *compile_recurse_matchingpath(compiler_common *common, pcre_uchar *cc, backtrack_common *parent) -{ -DEFINE_COMPILER; -backtrack_common *backtrack; -recurse_entry *entry = common->entries; -recurse_entry *prev = NULL; -sljit_sw start = GET(cc, 1); -pcre_uchar *start_cc; -BOOL needs_control_head; - -PUSH_BACKTRACK(sizeof(recurse_backtrack), cc, NULL); - -/* Inlining simple patterns. */ -if (get_framesize(common, common->start + start, NULL, TRUE, &needs_control_head) == no_stack) - { - start_cc = common->start + start; - compile_matchingpath(common, next_opcode(common, start_cc), bracketend(start_cc) - (1 + LINK_SIZE), backtrack); - BACKTRACK_AS(recurse_backtrack)->inlined_pattern = TRUE; - return cc + 1 + LINK_SIZE; - } - -while (entry != NULL) - { - if (entry->start == start) - break; - prev = entry; - entry = entry->next; - } - -if (entry == NULL) - { - entry = sljit_alloc_memory(compiler, sizeof(recurse_entry)); - if (SLJIT_UNLIKELY(sljit_get_compiler_error(compiler))) - return NULL; - entry->next = NULL; - entry->entry = NULL; - entry->calls = NULL; - entry->start = start; - - if (prev != NULL) - prev->next = entry; - else - common->entries = entry; - } - -if (common->has_set_som && common->mark_ptr != 0) - { - OP1(SLJIT_MOV, TMP2, 0, SLJIT_MEM1(SLJIT_SP), OVECTOR(0)); - allocate_stack(common, 2); - OP1(SLJIT_MOV, TMP1, 0, SLJIT_MEM1(SLJIT_SP), common->mark_ptr); - OP1(SLJIT_MOV, SLJIT_MEM1(STACK_TOP), STACK(0), TMP2, 0); - OP1(SLJIT_MOV, SLJIT_MEM1(STACK_TOP), STACK(1), TMP1, 0); - } -else if (common->has_set_som || common->mark_ptr != 0) - { - OP1(SLJIT_MOV, TMP2, 0, SLJIT_MEM1(SLJIT_SP), common->has_set_som ? (int)(OVECTOR(0)) : common->mark_ptr); - allocate_stack(common, 1); - OP1(SLJIT_MOV, SLJIT_MEM1(STACK_TOP), STACK(0), TMP2, 0); - } - -if (entry->entry == NULL) - add_jump(compiler, &entry->calls, JUMP(SLJIT_FAST_CALL)); -else - JUMPTO(SLJIT_FAST_CALL, entry->entry); -/* Leave if the match is failed. */ -add_jump(compiler, &backtrack->topbacktracks, CMP(SLJIT_EQUAL, TMP1, 0, SLJIT_IMM, 0)); -return cc + 1 + LINK_SIZE; -} - -static int SLJIT_CALL do_callout(struct jit_arguments *arguments, PUBL(callout_block) *callout_block, pcre_uchar **jit_ovector) -{ -const pcre_uchar *begin = arguments->begin; -int *offset_vector = arguments->offsets; -int offset_count = arguments->offset_count; -int i; - -if (PUBL(callout) == NULL) - return 0; - -callout_block->version = 2; -callout_block->callout_data = arguments->callout_data; - -/* Offsets in subject. */ -callout_block->subject_length = arguments->end - arguments->begin; -callout_block->start_match = (pcre_uchar*)callout_block->subject - arguments->begin; -callout_block->current_position = (pcre_uchar*)callout_block->offset_vector - arguments->begin; -#if defined COMPILE_PCRE8 -callout_block->subject = (PCRE_SPTR)begin; -#elif defined COMPILE_PCRE16 -callout_block->subject = (PCRE_SPTR16)begin; -#elif defined COMPILE_PCRE32 -callout_block->subject = (PCRE_SPTR32)begin; -#endif - -/* Convert and copy the JIT offset vector to the offset_vector array. */ -callout_block->capture_top = 0; -callout_block->offset_vector = offset_vector; -for (i = 2; i < offset_count; i += 2) - { - offset_vector[i] = jit_ovector[i] - begin; - offset_vector[i + 1] = jit_ovector[i + 1] - begin; - if (jit_ovector[i] >= begin) - callout_block->capture_top = i; - } - -callout_block->capture_top = (callout_block->capture_top >> 1) + 1; -if (offset_count > 0) - offset_vector[0] = -1; -if (offset_count > 1) - offset_vector[1] = -1; -return (*PUBL(callout))(callout_block); -} - -/* Aligning to 8 byte. */ -#define CALLOUT_ARG_SIZE \ - (((int)sizeof(PUBL(callout_block)) + 7) & ~7) - -#define CALLOUT_ARG_OFFSET(arg) \ - (-CALLOUT_ARG_SIZE + SLJIT_OFFSETOF(PUBL(callout_block), arg)) - -static SLJIT_INLINE pcre_uchar *compile_callout_matchingpath(compiler_common *common, pcre_uchar *cc, backtrack_common *parent) -{ -DEFINE_COMPILER; -backtrack_common *backtrack; - -PUSH_BACKTRACK(sizeof(backtrack_common), cc, NULL); - -allocate_stack(common, CALLOUT_ARG_SIZE / sizeof(sljit_sw)); - -SLJIT_ASSERT(common->capture_last_ptr != 0); -OP1(SLJIT_MOV, TMP2, 0, SLJIT_MEM1(SLJIT_SP), common->capture_last_ptr); -OP1(SLJIT_MOV, TMP1, 0, ARGUMENTS, 0); -OP1(SLJIT_MOV_SI, SLJIT_MEM1(STACK_TOP), CALLOUT_ARG_OFFSET(callout_number), SLJIT_IMM, cc[1]); -OP1(SLJIT_MOV_SI, SLJIT_MEM1(STACK_TOP), CALLOUT_ARG_OFFSET(capture_last), TMP2, 0); - -/* These pointer sized fields temporarly stores internal variables. */ -OP1(SLJIT_MOV, TMP2, 0, SLJIT_MEM1(SLJIT_SP), OVECTOR(0)); -OP1(SLJIT_MOV, SLJIT_MEM1(STACK_TOP), CALLOUT_ARG_OFFSET(offset_vector), STR_PTR, 0); -OP1(SLJIT_MOV, SLJIT_MEM1(STACK_TOP), CALLOUT_ARG_OFFSET(subject), TMP2, 0); - -if (common->mark_ptr != 0) - OP1(SLJIT_MOV, TMP2, 0, SLJIT_MEM1(TMP1), SLJIT_OFFSETOF(jit_arguments, mark_ptr)); -OP1(SLJIT_MOV_SI, SLJIT_MEM1(STACK_TOP), CALLOUT_ARG_OFFSET(pattern_position), SLJIT_IMM, GET(cc, 2)); -OP1(SLJIT_MOV_SI, SLJIT_MEM1(STACK_TOP), CALLOUT_ARG_OFFSET(next_item_length), SLJIT_IMM, GET(cc, 2 + LINK_SIZE)); -OP1(SLJIT_MOV, SLJIT_MEM1(STACK_TOP), CALLOUT_ARG_OFFSET(mark), (common->mark_ptr != 0) ? TMP2 : SLJIT_IMM, 0); - -/* Needed to save important temporary registers. */ -OP1(SLJIT_MOV, SLJIT_MEM1(SLJIT_SP), LOCALS0, STACK_TOP, 0); -OP2(SLJIT_SUB, SLJIT_R1, 0, STACK_TOP, 0, SLJIT_IMM, CALLOUT_ARG_SIZE); -GET_LOCAL_BASE(SLJIT_R2, 0, OVECTOR_START); -sljit_emit_ijump(compiler, SLJIT_CALL3, SLJIT_IMM, SLJIT_FUNC_OFFSET(do_callout)); -OP1(SLJIT_MOV_SI, SLJIT_RETURN_REG, 0, SLJIT_RETURN_REG, 0); -OP1(SLJIT_MOV, STACK_TOP, 0, SLJIT_MEM1(SLJIT_SP), LOCALS0); -free_stack(common, CALLOUT_ARG_SIZE / sizeof(sljit_sw)); - -/* Check return value. */ -OP2(SLJIT_SUB | SLJIT_SET_S, SLJIT_UNUSED, 0, SLJIT_RETURN_REG, 0, SLJIT_IMM, 0); -add_jump(compiler, &backtrack->topbacktracks, JUMP(SLJIT_SIG_GREATER)); -if (common->forced_quit_label == NULL) - add_jump(compiler, &common->forced_quit, JUMP(SLJIT_SIG_LESS)); -else - JUMPTO(SLJIT_SIG_LESS, common->forced_quit_label); -return cc + 2 + 2 * LINK_SIZE; -} - -#undef CALLOUT_ARG_SIZE -#undef CALLOUT_ARG_OFFSET - -static pcre_uchar *compile_assert_matchingpath(compiler_common *common, pcre_uchar *cc, assert_backtrack *backtrack, BOOL conditional) -{ -DEFINE_COMPILER; -int framesize; -int extrasize; -BOOL needs_control_head; -int private_data_ptr; -backtrack_common altbacktrack; -pcre_uchar *ccbegin; -pcre_uchar opcode; -pcre_uchar bra = OP_BRA; -jump_list *tmp = NULL; -jump_list **target = (conditional) ? &backtrack->condfailed : &backtrack->common.topbacktracks; -jump_list **found; -/* Saving previous accept variables. */ -BOOL save_local_exit = common->local_exit; -BOOL save_positive_assert = common->positive_assert; -then_trap_backtrack *save_then_trap = common->then_trap; -struct sljit_label *save_quit_label = common->quit_label; -struct sljit_label *save_accept_label = common->accept_label; -jump_list *save_quit = common->quit; -jump_list *save_positive_assert_quit = common->positive_assert_quit; -jump_list *save_accept = common->accept; -struct sljit_jump *jump; -struct sljit_jump *brajump = NULL; - -/* Assert captures then. */ -common->then_trap = NULL; - -if (*cc == OP_BRAZERO || *cc == OP_BRAMINZERO) - { - SLJIT_ASSERT(!conditional); - bra = *cc; - cc++; - } -private_data_ptr = PRIVATE_DATA(cc); -SLJIT_ASSERT(private_data_ptr != 0); -framesize = get_framesize(common, cc, NULL, FALSE, &needs_control_head); -backtrack->framesize = framesize; -backtrack->private_data_ptr = private_data_ptr; -opcode = *cc; -SLJIT_ASSERT(opcode >= OP_ASSERT && opcode <= OP_ASSERTBACK_NOT); -found = (opcode == OP_ASSERT || opcode == OP_ASSERTBACK) ? &tmp : target; -ccbegin = cc; -cc += GET(cc, 1); - -if (bra == OP_BRAMINZERO) - { - /* This is a braminzero backtrack path. */ - OP1(SLJIT_MOV, STR_PTR, 0, SLJIT_MEM1(STACK_TOP), STACK(0)); - free_stack(common, 1); - brajump = CMP(SLJIT_EQUAL, STR_PTR, 0, SLJIT_IMM, 0); - } - -if (framesize < 0) - { - extrasize = needs_control_head ? 2 : 1; - if (framesize == no_frame) - OP1(SLJIT_MOV, SLJIT_MEM1(SLJIT_SP), private_data_ptr, STACK_TOP, 0); - allocate_stack(common, extrasize); - if (needs_control_head) - OP1(SLJIT_MOV, TMP1, 0, SLJIT_MEM1(SLJIT_SP), common->control_head_ptr); - OP1(SLJIT_MOV, SLJIT_MEM1(STACK_TOP), STACK(0), STR_PTR, 0); - if (needs_control_head) - { - OP1(SLJIT_MOV, SLJIT_MEM1(SLJIT_SP), common->control_head_ptr, SLJIT_IMM, 0); - OP1(SLJIT_MOV, SLJIT_MEM1(STACK_TOP), STACK(1), TMP1, 0); - } - } -else - { - extrasize = needs_control_head ? 3 : 2; - allocate_stack(common, framesize + extrasize); - OP1(SLJIT_MOV, TMP1, 0, SLJIT_MEM1(SLJIT_SP), private_data_ptr); - OP2(SLJIT_SUB, TMP2, 0, STACK_TOP, 0, SLJIT_IMM, (framesize + extrasize) * sizeof(sljit_sw)); - OP1(SLJIT_MOV, SLJIT_MEM1(SLJIT_SP), private_data_ptr, TMP2, 0); - if (needs_control_head) - OP1(SLJIT_MOV, TMP2, 0, SLJIT_MEM1(SLJIT_SP), common->control_head_ptr); - OP1(SLJIT_MOV, SLJIT_MEM1(STACK_TOP), STACK(0), STR_PTR, 0); - if (needs_control_head) - { - OP1(SLJIT_MOV, SLJIT_MEM1(STACK_TOP), STACK(2), TMP1, 0); - OP1(SLJIT_MOV, SLJIT_MEM1(STACK_TOP), STACK(1), TMP2, 0); - OP1(SLJIT_MOV, SLJIT_MEM1(SLJIT_SP), common->control_head_ptr, SLJIT_IMM, 0); - } - else - OP1(SLJIT_MOV, SLJIT_MEM1(STACK_TOP), STACK(1), TMP1, 0); - init_frame(common, ccbegin, NULL, framesize + extrasize - 1, extrasize, FALSE); - } - -memset(&altbacktrack, 0, sizeof(backtrack_common)); -if (opcode == OP_ASSERT_NOT || opcode == OP_ASSERTBACK_NOT) - { - /* Negative assert is stronger than positive assert. */ - common->local_exit = TRUE; - common->quit_label = NULL; - common->quit = NULL; - common->positive_assert = FALSE; - } -else - common->positive_assert = TRUE; -common->positive_assert_quit = NULL; - -while (1) - { - common->accept_label = NULL; - common->accept = NULL; - altbacktrack.top = NULL; - altbacktrack.topbacktracks = NULL; - - if (*ccbegin == OP_ALT) - OP1(SLJIT_MOV, STR_PTR, 0, SLJIT_MEM1(STACK_TOP), STACK(0)); - - altbacktrack.cc = ccbegin; - compile_matchingpath(common, ccbegin + 1 + LINK_SIZE, cc, &altbacktrack); - if (SLJIT_UNLIKELY(sljit_get_compiler_error(compiler))) - { - if (opcode == OP_ASSERT_NOT || opcode == OP_ASSERTBACK_NOT) - { - common->local_exit = save_local_exit; - common->quit_label = save_quit_label; - common->quit = save_quit; - } - common->positive_assert = save_positive_assert; - common->then_trap = save_then_trap; - common->accept_label = save_accept_label; - common->positive_assert_quit = save_positive_assert_quit; - common->accept = save_accept; - return NULL; - } - common->accept_label = LABEL(); - if (common->accept != NULL) - set_jumps(common->accept, common->accept_label); - - /* Reset stack. */ - if (framesize < 0) - { - if (framesize == no_frame) - OP1(SLJIT_MOV, STACK_TOP, 0, SLJIT_MEM1(SLJIT_SP), private_data_ptr); - else - free_stack(common, extrasize); - if (needs_control_head) - OP1(SLJIT_MOV, SLJIT_MEM1(SLJIT_SP), common->control_head_ptr, SLJIT_MEM1(STACK_TOP), 0); - } - else - { - if ((opcode != OP_ASSERT_NOT && opcode != OP_ASSERTBACK_NOT) || conditional) - { - /* We don't need to keep the STR_PTR, only the previous private_data_ptr. */ - OP2(SLJIT_ADD, STACK_TOP, 0, SLJIT_MEM1(SLJIT_SP), private_data_ptr, SLJIT_IMM, (framesize + 1) * sizeof(sljit_sw)); - if (needs_control_head) - OP1(SLJIT_MOV, SLJIT_MEM1(SLJIT_SP), common->control_head_ptr, SLJIT_MEM1(STACK_TOP), 0); - } - else - { - OP1(SLJIT_MOV, STACK_TOP, 0, SLJIT_MEM1(SLJIT_SP), private_data_ptr); - if (needs_control_head) - OP1(SLJIT_MOV, SLJIT_MEM1(SLJIT_SP), common->control_head_ptr, SLJIT_MEM1(STACK_TOP), (framesize + 1) * sizeof(sljit_sw)); - add_jump(compiler, &common->revertframes, JUMP(SLJIT_FAST_CALL)); - } - } - - if (opcode == OP_ASSERT_NOT || opcode == OP_ASSERTBACK_NOT) - { - /* We know that STR_PTR was stored on the top of the stack. */ - if (conditional) - OP1(SLJIT_MOV, STR_PTR, 0, SLJIT_MEM1(STACK_TOP), needs_control_head ? sizeof(sljit_sw) : 0); - else if (bra == OP_BRAZERO) - { - if (framesize < 0) - OP1(SLJIT_MOV, STR_PTR, 0, SLJIT_MEM1(STACK_TOP), (extrasize - 1) * sizeof(sljit_sw)); - else - { - OP1(SLJIT_MOV, TMP1, 0, SLJIT_MEM1(STACK_TOP), framesize * sizeof(sljit_sw)); - OP1(SLJIT_MOV, STR_PTR, 0, SLJIT_MEM1(STACK_TOP), (framesize + extrasize - 1) * sizeof(sljit_sw)); - OP1(SLJIT_MOV, SLJIT_MEM1(SLJIT_SP), private_data_ptr, TMP1, 0); - } - OP2(SLJIT_ADD, STACK_TOP, 0, STACK_TOP, 0, SLJIT_IMM, sizeof(sljit_sw)); - OP1(SLJIT_MOV, SLJIT_MEM1(STACK_TOP), STACK(0), SLJIT_IMM, 0); - } - else if (framesize >= 0) - { - /* For OP_BRA and OP_BRAMINZERO. */ - OP1(SLJIT_MOV, SLJIT_MEM1(SLJIT_SP), private_data_ptr, SLJIT_MEM1(STACK_TOP), framesize * sizeof(sljit_sw)); - } - } - add_jump(compiler, found, JUMP(SLJIT_JUMP)); - - compile_backtrackingpath(common, altbacktrack.top); - if (SLJIT_UNLIKELY(sljit_get_compiler_error(compiler))) - { - if (opcode == OP_ASSERT_NOT || opcode == OP_ASSERTBACK_NOT) - { - common->local_exit = save_local_exit; - common->quit_label = save_quit_label; - common->quit = save_quit; - } - common->positive_assert = save_positive_assert; - common->then_trap = save_then_trap; - common->accept_label = save_accept_label; - common->positive_assert_quit = save_positive_assert_quit; - common->accept = save_accept; - return NULL; - } - set_jumps(altbacktrack.topbacktracks, LABEL()); - - if (*cc != OP_ALT) - break; - - ccbegin = cc; - cc += GET(cc, 1); - } - -if (opcode == OP_ASSERT_NOT || opcode == OP_ASSERTBACK_NOT) - { - SLJIT_ASSERT(common->positive_assert_quit == NULL); - /* Makes the check less complicated below. */ - common->positive_assert_quit = common->quit; - } - -/* None of them matched. */ -if (common->positive_assert_quit != NULL) - { - jump = JUMP(SLJIT_JUMP); - set_jumps(common->positive_assert_quit, LABEL()); - SLJIT_ASSERT(framesize != no_stack); - if (framesize < 0) - OP2(SLJIT_ADD, STACK_TOP, 0, SLJIT_MEM1(SLJIT_SP), private_data_ptr, SLJIT_IMM, extrasize * sizeof(sljit_sw)); - else - { - OP1(SLJIT_MOV, STACK_TOP, 0, SLJIT_MEM1(SLJIT_SP), private_data_ptr); - add_jump(compiler, &common->revertframes, JUMP(SLJIT_FAST_CALL)); - OP2(SLJIT_ADD, STACK_TOP, 0, STACK_TOP, 0, SLJIT_IMM, (framesize + extrasize) * sizeof(sljit_sw)); - } - JUMPHERE(jump); - } - -if (needs_control_head) - OP1(SLJIT_MOV, SLJIT_MEM1(SLJIT_SP), common->control_head_ptr, SLJIT_MEM1(STACK_TOP), STACK(1)); - -if (opcode == OP_ASSERT || opcode == OP_ASSERTBACK) - { - /* Assert is failed. */ - if (conditional || bra == OP_BRAZERO) - OP1(SLJIT_MOV, STR_PTR, 0, SLJIT_MEM1(STACK_TOP), STACK(0)); - - if (framesize < 0) - { - /* The topmost item should be 0. */ - if (bra == OP_BRAZERO) - { - if (extrasize == 2) - free_stack(common, 1); - OP1(SLJIT_MOV, SLJIT_MEM1(STACK_TOP), STACK(0), SLJIT_IMM, 0); - } - else - free_stack(common, extrasize); - } - else - { - OP1(SLJIT_MOV, TMP1, 0, SLJIT_MEM1(STACK_TOP), STACK(extrasize - 1)); - /* The topmost item should be 0. */ - if (bra == OP_BRAZERO) - { - free_stack(common, framesize + extrasize - 1); - OP1(SLJIT_MOV, SLJIT_MEM1(STACK_TOP), STACK(0), SLJIT_IMM, 0); - } - else - free_stack(common, framesize + extrasize); - OP1(SLJIT_MOV, SLJIT_MEM1(SLJIT_SP), private_data_ptr, TMP1, 0); - } - jump = JUMP(SLJIT_JUMP); - if (bra != OP_BRAZERO) - add_jump(compiler, target, jump); - - /* Assert is successful. */ - set_jumps(tmp, LABEL()); - if (framesize < 0) - { - /* We know that STR_PTR was stored on the top of the stack. */ - OP1(SLJIT_MOV, STR_PTR, 0, SLJIT_MEM1(STACK_TOP), (extrasize - 1) * sizeof(sljit_sw)); - /* Keep the STR_PTR on the top of the stack. */ - if (bra == OP_BRAZERO) - { - OP2(SLJIT_ADD, STACK_TOP, 0, STACK_TOP, 0, SLJIT_IMM, sizeof(sljit_sw)); - if (extrasize == 2) - OP1(SLJIT_MOV, SLJIT_MEM1(STACK_TOP), STACK(0), STR_PTR, 0); - } - else if (bra == OP_BRAMINZERO) - { - OP2(SLJIT_ADD, STACK_TOP, 0, STACK_TOP, 0, SLJIT_IMM, sizeof(sljit_sw)); - OP1(SLJIT_MOV, SLJIT_MEM1(STACK_TOP), STACK(0), SLJIT_IMM, 0); - } - } - else - { - if (bra == OP_BRA) - { - /* We don't need to keep the STR_PTR, only the previous private_data_ptr. */ - OP2(SLJIT_ADD, STACK_TOP, 0, SLJIT_MEM1(SLJIT_SP), private_data_ptr, SLJIT_IMM, (framesize + 1) * sizeof(sljit_sw)); - OP1(SLJIT_MOV, STR_PTR, 0, SLJIT_MEM1(STACK_TOP), (extrasize - 2) * sizeof(sljit_sw)); - } - else - { - /* We don't need to keep the STR_PTR, only the previous private_data_ptr. */ - OP2(SLJIT_ADD, STACK_TOP, 0, SLJIT_MEM1(SLJIT_SP), private_data_ptr, SLJIT_IMM, (framesize + 2) * sizeof(sljit_sw)); - if (extrasize == 2) - { - OP1(SLJIT_MOV, STR_PTR, 0, SLJIT_MEM1(STACK_TOP), STACK(0)); - if (bra == OP_BRAMINZERO) - OP1(SLJIT_MOV, SLJIT_MEM1(STACK_TOP), STACK(0), SLJIT_IMM, 0); - } - else - { - OP1(SLJIT_MOV, STR_PTR, 0, SLJIT_MEM1(STACK_TOP), 0); - OP1(SLJIT_MOV, SLJIT_MEM1(STACK_TOP), STACK(0), bra == OP_BRAZERO ? STR_PTR : SLJIT_IMM, 0); - } - } - } - - if (bra == OP_BRAZERO) - { - backtrack->matchingpath = LABEL(); - SET_LABEL(jump, backtrack->matchingpath); - } - else if (bra == OP_BRAMINZERO) - { - JUMPTO(SLJIT_JUMP, backtrack->matchingpath); - JUMPHERE(brajump); - if (framesize >= 0) - { - OP1(SLJIT_MOV, STACK_TOP, 0, SLJIT_MEM1(SLJIT_SP), private_data_ptr); - add_jump(compiler, &common->revertframes, JUMP(SLJIT_FAST_CALL)); - OP1(SLJIT_MOV, SLJIT_MEM1(SLJIT_SP), private_data_ptr, SLJIT_MEM1(STACK_TOP), framesize * sizeof(sljit_sw)); - } - set_jumps(backtrack->common.topbacktracks, LABEL()); - } - } -else - { - /* AssertNot is successful. */ - if (framesize < 0) - { - OP1(SLJIT_MOV, STR_PTR, 0, SLJIT_MEM1(STACK_TOP), STACK(0)); - if (bra != OP_BRA) - { - if (extrasize == 2) - free_stack(common, 1); - OP1(SLJIT_MOV, SLJIT_MEM1(STACK_TOP), STACK(0), SLJIT_IMM, 0); - } - else - free_stack(common, extrasize); - } - else - { - OP1(SLJIT_MOV, STR_PTR, 0, SLJIT_MEM1(STACK_TOP), STACK(0)); - OP1(SLJIT_MOV, TMP1, 0, SLJIT_MEM1(STACK_TOP), STACK(extrasize - 1)); - /* The topmost item should be 0. */ - if (bra != OP_BRA) - { - free_stack(common, framesize + extrasize - 1); - OP1(SLJIT_MOV, SLJIT_MEM1(STACK_TOP), STACK(0), SLJIT_IMM, 0); - } - else - free_stack(common, framesize + extrasize); - OP1(SLJIT_MOV, SLJIT_MEM1(SLJIT_SP), private_data_ptr, TMP1, 0); - } - - if (bra == OP_BRAZERO) - backtrack->matchingpath = LABEL(); - else if (bra == OP_BRAMINZERO) - { - JUMPTO(SLJIT_JUMP, backtrack->matchingpath); - JUMPHERE(brajump); - } - - if (bra != OP_BRA) - { - SLJIT_ASSERT(found == &backtrack->common.topbacktracks); - set_jumps(backtrack->common.topbacktracks, LABEL()); - backtrack->common.topbacktracks = NULL; - } - } - -if (opcode == OP_ASSERT_NOT || opcode == OP_ASSERTBACK_NOT) - { - common->local_exit = save_local_exit; - common->quit_label = save_quit_label; - common->quit = save_quit; - } -common->positive_assert = save_positive_assert; -common->then_trap = save_then_trap; -common->accept_label = save_accept_label; -common->positive_assert_quit = save_positive_assert_quit; -common->accept = save_accept; -return cc + 1 + LINK_SIZE; -} - -static SLJIT_INLINE void match_once_common(compiler_common *common, pcre_uchar ket, int framesize, int private_data_ptr, BOOL has_alternatives, BOOL needs_control_head) -{ -DEFINE_COMPILER; -int stacksize; - -if (framesize < 0) - { - if (framesize == no_frame) - OP1(SLJIT_MOV, STACK_TOP, 0, SLJIT_MEM1(SLJIT_SP), private_data_ptr); - else - { - stacksize = needs_control_head ? 1 : 0; - if (ket != OP_KET || has_alternatives) - stacksize++; - free_stack(common, stacksize); - } - - if (needs_control_head) - OP1(SLJIT_MOV, TMP1, 0, SLJIT_MEM1(STACK_TOP), (ket != OP_KET || has_alternatives) ? sizeof(sljit_sw) : 0); - - /* TMP2 which is set here used by OP_KETRMAX below. */ - if (ket == OP_KETRMAX) - OP1(SLJIT_MOV, TMP2, 0, SLJIT_MEM1(STACK_TOP), 0); - else if (ket == OP_KETRMIN) - { - /* Move the STR_PTR to the private_data_ptr. */ - OP1(SLJIT_MOV, SLJIT_MEM1(SLJIT_SP), private_data_ptr, SLJIT_MEM1(STACK_TOP), 0); - } - } -else - { - stacksize = (ket != OP_KET || has_alternatives) ? 2 : 1; - OP2(SLJIT_ADD, STACK_TOP, 0, SLJIT_MEM1(SLJIT_SP), private_data_ptr, SLJIT_IMM, (framesize + stacksize) * sizeof(sljit_sw)); - if (needs_control_head) - OP1(SLJIT_MOV, TMP1, 0, SLJIT_MEM1(STACK_TOP), 0); - - if (ket == OP_KETRMAX) - { - /* TMP2 which is set here used by OP_KETRMAX below. */ - OP1(SLJIT_MOV, TMP2, 0, SLJIT_MEM1(STACK_TOP), STACK(0)); - } - } -if (needs_control_head) - OP1(SLJIT_MOV, SLJIT_MEM1(SLJIT_SP), common->control_head_ptr, TMP1, 0); -} - -static SLJIT_INLINE int match_capture_common(compiler_common *common, int stacksize, int offset, int private_data_ptr) -{ -DEFINE_COMPILER; - -if (common->capture_last_ptr != 0) - { - OP1(SLJIT_MOV, TMP1, 0, SLJIT_MEM1(SLJIT_SP), common->capture_last_ptr); - OP1(SLJIT_MOV, SLJIT_MEM1(SLJIT_SP), common->capture_last_ptr, SLJIT_IMM, offset >> 1); - OP1(SLJIT_MOV, SLJIT_MEM1(STACK_TOP), STACK(stacksize), TMP1, 0); - stacksize++; - } -if (common->optimized_cbracket[offset >> 1] == 0) - { - OP1(SLJIT_MOV, TMP1, 0, SLJIT_MEM1(SLJIT_SP), OVECTOR(offset)); - OP1(SLJIT_MOV, TMP2, 0, SLJIT_MEM1(SLJIT_SP), OVECTOR(offset + 1)); - OP1(SLJIT_MOV, SLJIT_MEM1(STACK_TOP), STACK(stacksize), TMP1, 0); - OP1(SLJIT_MOV, TMP1, 0, SLJIT_MEM1(SLJIT_SP), private_data_ptr); - OP1(SLJIT_MOV, SLJIT_MEM1(STACK_TOP), STACK(stacksize + 1), TMP2, 0); - OP1(SLJIT_MOV, SLJIT_MEM1(SLJIT_SP), OVECTOR(offset + 1), STR_PTR, 0); - OP1(SLJIT_MOV, SLJIT_MEM1(SLJIT_SP), OVECTOR(offset), TMP1, 0); - stacksize += 2; - } -return stacksize; -} - -/* - Handling bracketed expressions is probably the most complex part. - - Stack layout naming characters: - S - Push the current STR_PTR - 0 - Push a 0 (NULL) - A - Push the current STR_PTR. Needed for restoring the STR_PTR - before the next alternative. Not pushed if there are no alternatives. - M - Any values pushed by the current alternative. Can be empty, or anything. - C - Push the previous OVECTOR(i), OVECTOR(i+1) and OVECTOR_PRIV(i) to the stack. - L - Push the previous local (pointed by localptr) to the stack - () - opional values stored on the stack - ()* - optonal, can be stored multiple times - - The following list shows the regular expression templates, their PCRE byte codes - and stack layout supported by pcre-sljit. - - (?:) OP_BRA | OP_KET A M - () OP_CBRA | OP_KET C M - (?:)+ OP_BRA | OP_KETRMAX 0 A M S ( A M S )* - OP_SBRA | OP_KETRMAX 0 L M S ( L M S )* - (?:)+? OP_BRA | OP_KETRMIN 0 A M S ( A M S )* - OP_SBRA | OP_KETRMIN 0 L M S ( L M S )* - ()+ OP_CBRA | OP_KETRMAX 0 C M S ( C M S )* - OP_SCBRA | OP_KETRMAX 0 C M S ( C M S )* - ()+? OP_CBRA | OP_KETRMIN 0 C M S ( C M S )* - OP_SCBRA | OP_KETRMIN 0 C M S ( C M S )* - (?:)? OP_BRAZERO | OP_BRA | OP_KET S ( A M 0 ) - (?:)?? OP_BRAMINZERO | OP_BRA | OP_KET S ( A M 0 ) - ()? OP_BRAZERO | OP_CBRA | OP_KET S ( C M 0 ) - ()?? OP_BRAMINZERO | OP_CBRA | OP_KET S ( C M 0 ) - (?:)* OP_BRAZERO | OP_BRA | OP_KETRMAX S 0 ( A M S )* - OP_BRAZERO | OP_SBRA | OP_KETRMAX S 0 ( L M S )* - (?:)*? OP_BRAMINZERO | OP_BRA | OP_KETRMIN S 0 ( A M S )* - OP_BRAMINZERO | OP_SBRA | OP_KETRMIN S 0 ( L M S )* - ()* OP_BRAZERO | OP_CBRA | OP_KETRMAX S 0 ( C M S )* - OP_BRAZERO | OP_SCBRA | OP_KETRMAX S 0 ( C M S )* - ()*? OP_BRAMINZERO | OP_CBRA | OP_KETRMIN S 0 ( C M S )* - OP_BRAMINZERO | OP_SCBRA | OP_KETRMIN S 0 ( C M S )* - - - Stack layout naming characters: - A - Push the alternative index (starting from 0) on the stack. - Not pushed if there is no alternatives. - M - Any values pushed by the current alternative. Can be empty, or anything. - - The next list shows the possible content of a bracket: - (|) OP_*BRA | OP_ALT ... M A - (?()|) OP_*COND | OP_ALT M A - (?>|) OP_ONCE | OP_ALT ... [stack trace] M A - (?>|) OP_ONCE_NC | OP_ALT ... [stack trace] M A - Or nothing, if trace is unnecessary -*/ - -static pcre_uchar *compile_bracket_matchingpath(compiler_common *common, pcre_uchar *cc, backtrack_common *parent) -{ -DEFINE_COMPILER; -backtrack_common *backtrack; -pcre_uchar opcode; -int private_data_ptr = 0; -int offset = 0; -int i, stacksize; -int repeat_ptr = 0, repeat_length = 0; -int repeat_type = 0, repeat_count = 0; -pcre_uchar *ccbegin; -pcre_uchar *matchingpath; -pcre_uchar *slot; -pcre_uchar bra = OP_BRA; -pcre_uchar ket; -assert_backtrack *assert; -BOOL has_alternatives; -BOOL needs_control_head = FALSE; -struct sljit_jump *jump; -struct sljit_jump *skip; -struct sljit_label *rmax_label = NULL; -struct sljit_jump *braminzero = NULL; - -PUSH_BACKTRACK(sizeof(bracket_backtrack), cc, NULL); - -if (*cc == OP_BRAZERO || *cc == OP_BRAMINZERO) - { - bra = *cc; - cc++; - opcode = *cc; - } - -opcode = *cc; -ccbegin = cc; -matchingpath = bracketend(cc) - 1 - LINK_SIZE; -ket = *matchingpath; -if (ket == OP_KET && PRIVATE_DATA(matchingpath) != 0) - { - repeat_ptr = PRIVATE_DATA(matchingpath); - repeat_length = PRIVATE_DATA(matchingpath + 1); - repeat_type = PRIVATE_DATA(matchingpath + 2); - repeat_count = PRIVATE_DATA(matchingpath + 3); - SLJIT_ASSERT(repeat_length != 0 && repeat_type != 0 && repeat_count != 0); - if (repeat_type == OP_UPTO) - ket = OP_KETRMAX; - if (repeat_type == OP_MINUPTO) - ket = OP_KETRMIN; - } - -if ((opcode == OP_COND || opcode == OP_SCOND) && cc[1 + LINK_SIZE] == OP_DEF) - { - /* Drop this bracket_backtrack. */ - parent->top = backtrack->prev; - return matchingpath + 1 + LINK_SIZE + repeat_length; - } - -matchingpath = ccbegin + 1 + LINK_SIZE; -SLJIT_ASSERT(ket == OP_KET || ket == OP_KETRMAX || ket == OP_KETRMIN); -SLJIT_ASSERT(!((bra == OP_BRAZERO && ket == OP_KETRMIN) || (bra == OP_BRAMINZERO && ket == OP_KETRMAX))); -cc += GET(cc, 1); - -has_alternatives = *cc == OP_ALT; -if (SLJIT_UNLIKELY(opcode == OP_COND || opcode == OP_SCOND)) - has_alternatives = (*matchingpath == OP_RREF || *matchingpath == OP_DNRREF || *matchingpath == OP_FAIL) ? FALSE : TRUE; - -if (SLJIT_UNLIKELY(opcode == OP_COND) && (*cc == OP_KETRMAX || *cc == OP_KETRMIN)) - opcode = OP_SCOND; -if (SLJIT_UNLIKELY(opcode == OP_ONCE_NC)) - opcode = OP_ONCE; - -if (opcode == OP_CBRA || opcode == OP_SCBRA) - { - /* Capturing brackets has a pre-allocated space. */ - offset = GET2(ccbegin, 1 + LINK_SIZE); - if (common->optimized_cbracket[offset] == 0) - { - private_data_ptr = OVECTOR_PRIV(offset); - offset <<= 1; - } - else - { - offset <<= 1; - private_data_ptr = OVECTOR(offset); - } - BACKTRACK_AS(bracket_backtrack)->private_data_ptr = private_data_ptr; - matchingpath += IMM2_SIZE; - } -else if (opcode == OP_ONCE || opcode == OP_SBRA || opcode == OP_SCOND) - { - /* Other brackets simply allocate the next entry. */ - private_data_ptr = PRIVATE_DATA(ccbegin); - SLJIT_ASSERT(private_data_ptr != 0); - BACKTRACK_AS(bracket_backtrack)->private_data_ptr = private_data_ptr; - if (opcode == OP_ONCE) - BACKTRACK_AS(bracket_backtrack)->u.framesize = get_framesize(common, ccbegin, NULL, FALSE, &needs_control_head); - } - -/* Instructions before the first alternative. */ -stacksize = 0; -if (ket == OP_KETRMAX || (ket == OP_KETRMIN && bra != OP_BRAMINZERO)) - stacksize++; -if (bra == OP_BRAZERO) - stacksize++; - -if (stacksize > 0) - allocate_stack(common, stacksize); - -stacksize = 0; -if (ket == OP_KETRMAX || (ket == OP_KETRMIN && bra != OP_BRAMINZERO)) - { - OP1(SLJIT_MOV, SLJIT_MEM1(STACK_TOP), STACK(stacksize), SLJIT_IMM, 0); - stacksize++; - } - -if (bra == OP_BRAZERO) - OP1(SLJIT_MOV, SLJIT_MEM1(STACK_TOP), STACK(stacksize), STR_PTR, 0); - -if (bra == OP_BRAMINZERO) - { - /* This is a backtrack path! (Since the try-path of OP_BRAMINZERO matches to the empty string) */ - OP1(SLJIT_MOV, STR_PTR, 0, SLJIT_MEM1(STACK_TOP), STACK(0)); - if (ket != OP_KETRMIN) - { - free_stack(common, 1); - braminzero = CMP(SLJIT_EQUAL, STR_PTR, 0, SLJIT_IMM, 0); - } - else - { - if (opcode == OP_ONCE || opcode >= OP_SBRA) - { - jump = CMP(SLJIT_NOT_EQUAL, STR_PTR, 0, SLJIT_IMM, 0); - OP1(SLJIT_MOV, STR_PTR, 0, SLJIT_MEM1(STACK_TOP), STACK(1)); - /* Nothing stored during the first run. */ - skip = JUMP(SLJIT_JUMP); - JUMPHERE(jump); - /* Checking zero-length iteration. */ - if (opcode != OP_ONCE || BACKTRACK_AS(bracket_backtrack)->u.framesize < 0) - { - /* When we come from outside, private_data_ptr contains the previous STR_PTR. */ - braminzero = CMP(SLJIT_EQUAL, STR_PTR, 0, SLJIT_MEM1(SLJIT_SP), private_data_ptr); - } - else - { - /* Except when the whole stack frame must be saved. */ - OP1(SLJIT_MOV, TMP1, 0, SLJIT_MEM1(SLJIT_SP), private_data_ptr); - braminzero = CMP(SLJIT_EQUAL, STR_PTR, 0, SLJIT_MEM1(TMP1), (BACKTRACK_AS(bracket_backtrack)->u.framesize + 1) * sizeof(sljit_sw)); - } - JUMPHERE(skip); - } - else - { - jump = CMP(SLJIT_NOT_EQUAL, STR_PTR, 0, SLJIT_IMM, 0); - OP1(SLJIT_MOV, STR_PTR, 0, SLJIT_MEM1(STACK_TOP), STACK(1)); - JUMPHERE(jump); - } - } - } - -if (repeat_type != 0) - { - OP1(SLJIT_MOV, SLJIT_MEM1(SLJIT_SP), repeat_ptr, SLJIT_IMM, repeat_count); - if (repeat_type == OP_EXACT) - rmax_label = LABEL(); - } - -if (ket == OP_KETRMIN) - BACKTRACK_AS(bracket_backtrack)->recursive_matchingpath = LABEL(); - -if (ket == OP_KETRMAX) - { - rmax_label = LABEL(); - if (has_alternatives && opcode != OP_ONCE && opcode < OP_SBRA && repeat_type == 0) - BACKTRACK_AS(bracket_backtrack)->alternative_matchingpath = rmax_label; - } - -/* Handling capturing brackets and alternatives. */ -if (opcode == OP_ONCE) - { - stacksize = 0; - if (needs_control_head) - { - OP1(SLJIT_MOV, TMP2, 0, SLJIT_MEM1(SLJIT_SP), common->control_head_ptr); - stacksize++; - } - - if (BACKTRACK_AS(bracket_backtrack)->u.framesize < 0) - { - /* Neither capturing brackets nor recursions are found in the block. */ - if (ket == OP_KETRMIN) - { - stacksize += 2; - if (!needs_control_head) - OP1(SLJIT_MOV, TMP2, 0, SLJIT_MEM1(SLJIT_SP), private_data_ptr); - } - else - { - if (BACKTRACK_AS(bracket_backtrack)->u.framesize == no_frame) - OP1(SLJIT_MOV, SLJIT_MEM1(SLJIT_SP), private_data_ptr, STACK_TOP, 0); - if (ket == OP_KETRMAX || has_alternatives) - stacksize++; - } - - if (stacksize > 0) - allocate_stack(common, stacksize); - - stacksize = 0; - if (needs_control_head) - { - stacksize++; - OP1(SLJIT_MOV, SLJIT_MEM1(STACK_TOP), STACK(0), TMP2, 0); - } - - if (ket == OP_KETRMIN) - { - if (needs_control_head) - OP1(SLJIT_MOV, TMP2, 0, SLJIT_MEM1(SLJIT_SP), private_data_ptr); - OP1(SLJIT_MOV, SLJIT_MEM1(STACK_TOP), STACK(stacksize), STR_PTR, 0); - if (BACKTRACK_AS(bracket_backtrack)->u.framesize == no_frame) - OP2(SLJIT_SUB, SLJIT_MEM1(SLJIT_SP), private_data_ptr, STACK_TOP, 0, SLJIT_IMM, needs_control_head ? (2 * sizeof(sljit_sw)) : sizeof(sljit_sw)); - OP1(SLJIT_MOV, SLJIT_MEM1(STACK_TOP), STACK(stacksize + 1), TMP2, 0); - } - else if (ket == OP_KETRMAX || has_alternatives) - OP1(SLJIT_MOV, SLJIT_MEM1(STACK_TOP), STACK(stacksize), STR_PTR, 0); - } - else - { - if (ket != OP_KET || has_alternatives) - stacksize++; - - stacksize += BACKTRACK_AS(bracket_backtrack)->u.framesize + 1; - allocate_stack(common, stacksize); - - if (needs_control_head) - OP1(SLJIT_MOV, SLJIT_MEM1(STACK_TOP), STACK(0), TMP2, 0); - - OP1(SLJIT_MOV, TMP1, 0, SLJIT_MEM1(SLJIT_SP), private_data_ptr); - OP2(SLJIT_SUB, TMP2, 0, STACK_TOP, 0, SLJIT_IMM, stacksize * sizeof(sljit_sw)); - - stacksize = needs_control_head ? 1 : 0; - if (ket != OP_KET || has_alternatives) - { - OP1(SLJIT_MOV, SLJIT_MEM1(STACK_TOP), STACK(stacksize), STR_PTR, 0); - OP1(SLJIT_MOV, SLJIT_MEM1(SLJIT_SP), private_data_ptr, TMP2, 0); - stacksize++; - OP1(SLJIT_MOV, SLJIT_MEM1(STACK_TOP), STACK(stacksize), TMP1, 0); - } - else - { - OP1(SLJIT_MOV, SLJIT_MEM1(SLJIT_SP), private_data_ptr, TMP2, 0); - OP1(SLJIT_MOV, SLJIT_MEM1(STACK_TOP), STACK(stacksize), TMP1, 0); - } - init_frame(common, ccbegin, NULL, BACKTRACK_AS(bracket_backtrack)->u.framesize + stacksize, stacksize + 1, FALSE); - } - } -else if (opcode == OP_CBRA || opcode == OP_SCBRA) - { - /* Saving the previous values. */ - if (common->optimized_cbracket[offset >> 1] != 0) - { - SLJIT_ASSERT(private_data_ptr == OVECTOR(offset)); - allocate_stack(common, 2); - OP1(SLJIT_MOV, TMP1, 0, SLJIT_MEM1(SLJIT_SP), private_data_ptr); - OP1(SLJIT_MOV, TMP2, 0, SLJIT_MEM1(SLJIT_SP), private_data_ptr + sizeof(sljit_sw)); - OP1(SLJIT_MOV, SLJIT_MEM1(SLJIT_SP), private_data_ptr, STR_PTR, 0); - OP1(SLJIT_MOV, SLJIT_MEM1(STACK_TOP), STACK(0), TMP1, 0); - OP1(SLJIT_MOV, SLJIT_MEM1(STACK_TOP), STACK(1), TMP2, 0); - } - else - { - OP1(SLJIT_MOV, TMP2, 0, SLJIT_MEM1(SLJIT_SP), private_data_ptr); - allocate_stack(common, 1); - OP1(SLJIT_MOV, SLJIT_MEM1(SLJIT_SP), private_data_ptr, STR_PTR, 0); - OP1(SLJIT_MOV, SLJIT_MEM1(STACK_TOP), STACK(0), TMP2, 0); - } - } -else if (opcode == OP_SBRA || opcode == OP_SCOND) - { - /* Saving the previous value. */ - OP1(SLJIT_MOV, TMP2, 0, SLJIT_MEM1(SLJIT_SP), private_data_ptr); - allocate_stack(common, 1); - OP1(SLJIT_MOV, SLJIT_MEM1(SLJIT_SP), private_data_ptr, STR_PTR, 0); - OP1(SLJIT_MOV, SLJIT_MEM1(STACK_TOP), STACK(0), TMP2, 0); - } -else if (has_alternatives) - { - /* Pushing the starting string pointer. */ - allocate_stack(common, 1); - OP1(SLJIT_MOV, SLJIT_MEM1(STACK_TOP), STACK(0), STR_PTR, 0); - } - -/* Generating code for the first alternative. */ -if (opcode == OP_COND || opcode == OP_SCOND) - { - if (*matchingpath == OP_CREF) - { - SLJIT_ASSERT(has_alternatives); - add_jump(compiler, &(BACKTRACK_AS(bracket_backtrack)->u.condfailed), - CMP(SLJIT_EQUAL, SLJIT_MEM1(SLJIT_SP), OVECTOR(GET2(matchingpath, 1) << 1), SLJIT_MEM1(SLJIT_SP), OVECTOR(1))); - matchingpath += 1 + IMM2_SIZE; - } - else if (*matchingpath == OP_DNCREF) - { - SLJIT_ASSERT(has_alternatives); - - i = GET2(matchingpath, 1 + IMM2_SIZE); - slot = common->name_table + GET2(matchingpath, 1) * common->name_entry_size; - OP1(SLJIT_MOV, TMP3, 0, STR_PTR, 0); - OP1(SLJIT_MOV, TMP1, 0, SLJIT_MEM1(SLJIT_SP), OVECTOR(1)); - OP2(SLJIT_SUB | SLJIT_SET_E, TMP2, 0, SLJIT_MEM1(SLJIT_SP), OVECTOR(GET2(slot, 0) << 1), TMP1, 0); - slot += common->name_entry_size; - i--; - while (i-- > 0) - { - OP2(SLJIT_SUB, STR_PTR, 0, SLJIT_MEM1(SLJIT_SP), OVECTOR(GET2(slot, 0) << 1), TMP1, 0); - OP2(SLJIT_OR | SLJIT_SET_E, TMP2, 0, TMP2, 0, STR_PTR, 0); - slot += common->name_entry_size; - } - OP1(SLJIT_MOV, STR_PTR, 0, TMP3, 0); - add_jump(compiler, &(BACKTRACK_AS(bracket_backtrack)->u.condfailed), JUMP(SLJIT_ZERO)); - matchingpath += 1 + 2 * IMM2_SIZE; - } - else if (*matchingpath == OP_RREF || *matchingpath == OP_DNRREF || *matchingpath == OP_FAIL) - { - /* Never has other case. */ - BACKTRACK_AS(bracket_backtrack)->u.condfailed = NULL; - SLJIT_ASSERT(!has_alternatives); - - if (*matchingpath == OP_FAIL) - stacksize = 0; - if (*matchingpath == OP_RREF) - { - stacksize = GET2(matchingpath, 1); - if (common->currententry == NULL) - stacksize = 0; - else if (stacksize == RREF_ANY) - stacksize = 1; - else if (common->currententry->start == 0) - stacksize = stacksize == 0; - else - stacksize = stacksize == (int)GET2(common->start, common->currententry->start + 1 + LINK_SIZE); - - if (stacksize != 0) - matchingpath += 1 + IMM2_SIZE; - } - else - { - if (common->currententry == NULL || common->currententry->start == 0) - stacksize = 0; - else - { - stacksize = GET2(matchingpath, 1 + IMM2_SIZE); - slot = common->name_table + GET2(matchingpath, 1) * common->name_entry_size; - i = (int)GET2(common->start, common->currententry->start + 1 + LINK_SIZE); - while (stacksize > 0) - { - if ((int)GET2(slot, 0) == i) - break; - slot += common->name_entry_size; - stacksize--; - } - } - - if (stacksize != 0) - matchingpath += 1 + 2 * IMM2_SIZE; - } - - /* The stacksize == 0 is a common "else" case. */ - if (stacksize == 0) - { - if (*cc == OP_ALT) - { - matchingpath = cc + 1 + LINK_SIZE; - cc += GET(cc, 1); - } - else - matchingpath = cc; - } - } - else - { - SLJIT_ASSERT(has_alternatives && *matchingpath >= OP_ASSERT && *matchingpath <= OP_ASSERTBACK_NOT); - /* Similar code as PUSH_BACKTRACK macro. */ - assert = sljit_alloc_memory(compiler, sizeof(assert_backtrack)); - if (SLJIT_UNLIKELY(sljit_get_compiler_error(compiler))) - return NULL; - memset(assert, 0, sizeof(assert_backtrack)); - assert->common.cc = matchingpath; - BACKTRACK_AS(bracket_backtrack)->u.assert = assert; - matchingpath = compile_assert_matchingpath(common, matchingpath, assert, TRUE); - } - } - -compile_matchingpath(common, matchingpath, cc, backtrack); -if (SLJIT_UNLIKELY(sljit_get_compiler_error(compiler))) - return NULL; - -if (opcode == OP_ONCE) - match_once_common(common, ket, BACKTRACK_AS(bracket_backtrack)->u.framesize, private_data_ptr, has_alternatives, needs_control_head); - -stacksize = 0; -if (repeat_type == OP_MINUPTO) - { - /* We need to preserve the counter. TMP2 will be used below. */ - OP1(SLJIT_MOV, TMP2, 0, SLJIT_MEM1(SLJIT_SP), repeat_ptr); - stacksize++; - } -if (ket != OP_KET || bra != OP_BRA) - stacksize++; -if (offset != 0) - { - if (common->capture_last_ptr != 0) - stacksize++; - if (common->optimized_cbracket[offset >> 1] == 0) - stacksize += 2; - } -if (has_alternatives && opcode != OP_ONCE) - stacksize++; - -if (stacksize > 0) - allocate_stack(common, stacksize); - -stacksize = 0; -if (repeat_type == OP_MINUPTO) - { - /* TMP2 was set above. */ - OP2(SLJIT_SUB, SLJIT_MEM1(STACK_TOP), STACK(stacksize), TMP2, 0, SLJIT_IMM, 1); - stacksize++; - } - -if (ket != OP_KET || bra != OP_BRA) - { - if (ket != OP_KET) - OP1(SLJIT_MOV, SLJIT_MEM1(STACK_TOP), STACK(stacksize), STR_PTR, 0); - else - OP1(SLJIT_MOV, SLJIT_MEM1(STACK_TOP), STACK(stacksize), SLJIT_IMM, 0); - stacksize++; - } - -if (offset != 0) - stacksize = match_capture_common(common, stacksize, offset, private_data_ptr); - -if (has_alternatives) - { - if (opcode != OP_ONCE) - OP1(SLJIT_MOV, SLJIT_MEM1(STACK_TOP), STACK(stacksize), SLJIT_IMM, 0); - if (ket != OP_KETRMAX) - BACKTRACK_AS(bracket_backtrack)->alternative_matchingpath = LABEL(); - } - -/* Must be after the matchingpath label. */ -if (offset != 0 && common->optimized_cbracket[offset >> 1] != 0) - { - SLJIT_ASSERT(private_data_ptr == OVECTOR(offset + 0)); - OP1(SLJIT_MOV, SLJIT_MEM1(SLJIT_SP), OVECTOR(offset + 1), STR_PTR, 0); - } - -if (ket == OP_KETRMAX) - { - if (repeat_type != 0) - { - if (has_alternatives) - BACKTRACK_AS(bracket_backtrack)->alternative_matchingpath = LABEL(); - OP2(SLJIT_SUB | SLJIT_SET_E, SLJIT_MEM1(SLJIT_SP), repeat_ptr, SLJIT_MEM1(SLJIT_SP), repeat_ptr, SLJIT_IMM, 1); - JUMPTO(SLJIT_NOT_ZERO, rmax_label); - /* Drop STR_PTR for greedy plus quantifier. */ - if (opcode != OP_ONCE) - free_stack(common, 1); - } - else if (opcode == OP_ONCE || opcode >= OP_SBRA) - { - if (has_alternatives) - BACKTRACK_AS(bracket_backtrack)->alternative_matchingpath = LABEL(); - /* Checking zero-length iteration. */ - if (opcode != OP_ONCE) - { - CMPTO(SLJIT_NOT_EQUAL, SLJIT_MEM1(SLJIT_SP), private_data_ptr, STR_PTR, 0, rmax_label); - /* Drop STR_PTR for greedy plus quantifier. */ - if (bra != OP_BRAZERO) - free_stack(common, 1); - } - else - /* TMP2 must contain the starting STR_PTR. */ - CMPTO(SLJIT_NOT_EQUAL, TMP2, 0, STR_PTR, 0, rmax_label); - } - else - JUMPTO(SLJIT_JUMP, rmax_label); - BACKTRACK_AS(bracket_backtrack)->recursive_matchingpath = LABEL(); - } - -if (repeat_type == OP_EXACT) - { - count_match(common); - OP2(SLJIT_SUB | SLJIT_SET_E, SLJIT_MEM1(SLJIT_SP), repeat_ptr, SLJIT_MEM1(SLJIT_SP), repeat_ptr, SLJIT_IMM, 1); - JUMPTO(SLJIT_NOT_ZERO, rmax_label); - } -else if (repeat_type == OP_UPTO) - { - /* We need to preserve the counter. */ - OP1(SLJIT_MOV, TMP2, 0, SLJIT_MEM1(SLJIT_SP), repeat_ptr); - allocate_stack(common, 1); - OP1(SLJIT_MOV, SLJIT_MEM1(STACK_TOP), STACK(0), TMP2, 0); - } - -if (bra == OP_BRAZERO) - BACKTRACK_AS(bracket_backtrack)->zero_matchingpath = LABEL(); - -if (bra == OP_BRAMINZERO) - { - /* This is a backtrack path! (From the viewpoint of OP_BRAMINZERO) */ - JUMPTO(SLJIT_JUMP, ((braminzero_backtrack *)parent)->matchingpath); - if (braminzero != NULL) - { - JUMPHERE(braminzero); - /* We need to release the end pointer to perform the - backtrack for the zero-length iteration. When - framesize is < 0, OP_ONCE will do the release itself. */ - if (opcode == OP_ONCE && BACKTRACK_AS(bracket_backtrack)->u.framesize >= 0) - { - OP1(SLJIT_MOV, STACK_TOP, 0, SLJIT_MEM1(SLJIT_SP), private_data_ptr); - add_jump(compiler, &common->revertframes, JUMP(SLJIT_FAST_CALL)); - } - else if (ket == OP_KETRMIN && opcode != OP_ONCE) - free_stack(common, 1); - } - /* Continue to the normal backtrack. */ - } - -if ((ket != OP_KET && bra != OP_BRAMINZERO) || bra == OP_BRAZERO) - count_match(common); - -/* Skip the other alternatives. */ -while (*cc == OP_ALT) - cc += GET(cc, 1); -cc += 1 + LINK_SIZE; - -/* Temporarily encoding the needs_control_head in framesize. */ -if (opcode == OP_ONCE) - BACKTRACK_AS(bracket_backtrack)->u.framesize = (BACKTRACK_AS(bracket_backtrack)->u.framesize << 1) | (needs_control_head ? 1 : 0); -return cc + repeat_length; -} - -static pcre_uchar *compile_bracketpos_matchingpath(compiler_common *common, pcre_uchar *cc, backtrack_common *parent) -{ -DEFINE_COMPILER; -backtrack_common *backtrack; -pcre_uchar opcode; -int private_data_ptr; -int cbraprivptr = 0; -BOOL needs_control_head; -int framesize; -int stacksize; -int offset = 0; -BOOL zero = FALSE; -pcre_uchar *ccbegin = NULL; -int stack; /* Also contains the offset of control head. */ -struct sljit_label *loop = NULL; -struct jump_list *emptymatch = NULL; - -PUSH_BACKTRACK(sizeof(bracketpos_backtrack), cc, NULL); -if (*cc == OP_BRAPOSZERO) - { - zero = TRUE; - cc++; - } - -opcode = *cc; -private_data_ptr = PRIVATE_DATA(cc); -SLJIT_ASSERT(private_data_ptr != 0); -BACKTRACK_AS(bracketpos_backtrack)->private_data_ptr = private_data_ptr; -switch(opcode) - { - case OP_BRAPOS: - case OP_SBRAPOS: - ccbegin = cc + 1 + LINK_SIZE; - break; - - case OP_CBRAPOS: - case OP_SCBRAPOS: - offset = GET2(cc, 1 + LINK_SIZE); - /* This case cannot be optimized in the same was as - normal capturing brackets. */ - SLJIT_ASSERT(common->optimized_cbracket[offset] == 0); - cbraprivptr = OVECTOR_PRIV(offset); - offset <<= 1; - ccbegin = cc + 1 + LINK_SIZE + IMM2_SIZE; - break; - - default: - SLJIT_ASSERT_STOP(); - break; - } - -framesize = get_framesize(common, cc, NULL, FALSE, &needs_control_head); -BACKTRACK_AS(bracketpos_backtrack)->framesize = framesize; -if (framesize < 0) - { - if (offset != 0) - { - stacksize = 2; - if (common->capture_last_ptr != 0) - stacksize++; - } - else - stacksize = 1; - - if (needs_control_head) - stacksize++; - if (!zero) - stacksize++; - - BACKTRACK_AS(bracketpos_backtrack)->stacksize = stacksize; - allocate_stack(common, stacksize); - if (framesize == no_frame) - OP1(SLJIT_MOV, SLJIT_MEM1(SLJIT_SP), private_data_ptr, STACK_TOP, 0); - - stack = 0; - if (offset != 0) - { - stack = 2; - OP1(SLJIT_MOV, TMP1, 0, SLJIT_MEM1(SLJIT_SP), OVECTOR(offset)); - OP1(SLJIT_MOV, TMP2, 0, SLJIT_MEM1(SLJIT_SP), OVECTOR(offset + 1)); - OP1(SLJIT_MOV, SLJIT_MEM1(STACK_TOP), STACK(0), TMP1, 0); - if (common->capture_last_ptr != 0) - OP1(SLJIT_MOV, TMP1, 0, SLJIT_MEM1(SLJIT_SP), common->capture_last_ptr); - OP1(SLJIT_MOV, SLJIT_MEM1(STACK_TOP), STACK(1), TMP2, 0); - if (needs_control_head) - OP1(SLJIT_MOV, TMP2, 0, SLJIT_MEM1(SLJIT_SP), common->control_head_ptr); - if (common->capture_last_ptr != 0) - { - OP1(SLJIT_MOV, SLJIT_MEM1(STACK_TOP), STACK(2), TMP1, 0); - stack = 3; - } - } - else - { - if (needs_control_head) - OP1(SLJIT_MOV, TMP2, 0, SLJIT_MEM1(SLJIT_SP), common->control_head_ptr); - OP1(SLJIT_MOV, SLJIT_MEM1(STACK_TOP), STACK(0), STR_PTR, 0); - stack = 1; - } - - if (needs_control_head) - stack++; - if (!zero) - OP1(SLJIT_MOV, SLJIT_MEM1(STACK_TOP), STACK(stack), SLJIT_IMM, 1); - if (needs_control_head) - { - stack--; - OP1(SLJIT_MOV, SLJIT_MEM1(STACK_TOP), STACK(stack), TMP2, 0); - } - } -else - { - stacksize = framesize + 1; - if (!zero) - stacksize++; - if (needs_control_head) - stacksize++; - if (offset == 0) - stacksize++; - BACKTRACK_AS(bracketpos_backtrack)->stacksize = stacksize; - - allocate_stack(common, stacksize); - OP1(SLJIT_MOV, TMP1, 0, SLJIT_MEM1(SLJIT_SP), private_data_ptr); - if (needs_control_head) - OP1(SLJIT_MOV, TMP2, 0, SLJIT_MEM1(SLJIT_SP), common->control_head_ptr); - OP2(SLJIT_SUB, SLJIT_MEM1(SLJIT_SP), private_data_ptr, STACK_TOP, 0, SLJIT_IMM, -STACK(stacksize - 1)); - - stack = 0; - if (!zero) - { - OP1(SLJIT_MOV, SLJIT_MEM1(STACK_TOP), STACK(0), SLJIT_IMM, 1); - stack = 1; - } - if (needs_control_head) - { - OP1(SLJIT_MOV, SLJIT_MEM1(STACK_TOP), STACK(stack), TMP2, 0); - stack++; - } - if (offset == 0) - { - OP1(SLJIT_MOV, SLJIT_MEM1(STACK_TOP), STACK(stack), STR_PTR, 0); - stack++; - } - OP1(SLJIT_MOV, SLJIT_MEM1(STACK_TOP), STACK(stack), TMP1, 0); - init_frame(common, cc, NULL, stacksize - 1, stacksize - framesize, FALSE); - stack -= 1 + (offset == 0); - } - -if (offset != 0) - OP1(SLJIT_MOV, SLJIT_MEM1(SLJIT_SP), cbraprivptr, STR_PTR, 0); - -loop = LABEL(); -while (*cc != OP_KETRPOS) - { - backtrack->top = NULL; - backtrack->topbacktracks = NULL; - cc += GET(cc, 1); - - compile_matchingpath(common, ccbegin, cc, backtrack); - if (SLJIT_UNLIKELY(sljit_get_compiler_error(compiler))) - return NULL; - - if (framesize < 0) - { - if (framesize == no_frame) - OP1(SLJIT_MOV, STACK_TOP, 0, SLJIT_MEM1(SLJIT_SP), private_data_ptr); - - if (offset != 0) - { - OP1(SLJIT_MOV, TMP1, 0, SLJIT_MEM1(SLJIT_SP), cbraprivptr); - OP1(SLJIT_MOV, SLJIT_MEM1(SLJIT_SP), OVECTOR(offset + 1), STR_PTR, 0); - OP1(SLJIT_MOV, SLJIT_MEM1(SLJIT_SP), cbraprivptr, STR_PTR, 0); - if (common->capture_last_ptr != 0) - OP1(SLJIT_MOV, SLJIT_MEM1(SLJIT_SP), common->capture_last_ptr, SLJIT_IMM, offset >> 1); - OP1(SLJIT_MOV, SLJIT_MEM1(SLJIT_SP), OVECTOR(offset), TMP1, 0); - } - else - { - if (opcode == OP_SBRAPOS) - OP1(SLJIT_MOV, TMP1, 0, SLJIT_MEM1(STACK_TOP), STACK(0)); - OP1(SLJIT_MOV, SLJIT_MEM1(STACK_TOP), STACK(0), STR_PTR, 0); - } - - /* Even if the match is empty, we need to reset the control head. */ - if (needs_control_head) - OP1(SLJIT_MOV, SLJIT_MEM1(SLJIT_SP), common->control_head_ptr, SLJIT_MEM1(STACK_TOP), STACK(stack)); - - if (opcode == OP_SBRAPOS || opcode == OP_SCBRAPOS) - add_jump(compiler, &emptymatch, CMP(SLJIT_EQUAL, TMP1, 0, STR_PTR, 0)); - - if (!zero) - OP1(SLJIT_MOV, SLJIT_MEM1(STACK_TOP), STACK(stacksize - 1), SLJIT_IMM, 0); - } - else - { - if (offset != 0) - { - OP2(SLJIT_ADD, STACK_TOP, 0, SLJIT_MEM1(SLJIT_SP), private_data_ptr, SLJIT_IMM, stacksize * sizeof(sljit_sw)); - OP1(SLJIT_MOV, TMP1, 0, SLJIT_MEM1(SLJIT_SP), cbraprivptr); - OP1(SLJIT_MOV, SLJIT_MEM1(SLJIT_SP), OVECTOR(offset + 1), STR_PTR, 0); - OP1(SLJIT_MOV, SLJIT_MEM1(SLJIT_SP), cbraprivptr, STR_PTR, 0); - if (common->capture_last_ptr != 0) - OP1(SLJIT_MOV, SLJIT_MEM1(SLJIT_SP), common->capture_last_ptr, SLJIT_IMM, offset >> 1); - OP1(SLJIT_MOV, SLJIT_MEM1(SLJIT_SP), OVECTOR(offset), TMP1, 0); - } - else - { - OP1(SLJIT_MOV, TMP2, 0, SLJIT_MEM1(SLJIT_SP), private_data_ptr); - OP2(SLJIT_ADD, STACK_TOP, 0, TMP2, 0, SLJIT_IMM, stacksize * sizeof(sljit_sw)); - if (opcode == OP_SBRAPOS) - OP1(SLJIT_MOV, TMP1, 0, SLJIT_MEM1(TMP2), (framesize + 1) * sizeof(sljit_sw)); - OP1(SLJIT_MOV, SLJIT_MEM1(TMP2), (framesize + 1) * sizeof(sljit_sw), STR_PTR, 0); - } - - /* Even if the match is empty, we need to reset the control head. */ - if (needs_control_head) - OP1(SLJIT_MOV, SLJIT_MEM1(SLJIT_SP), common->control_head_ptr, SLJIT_MEM1(STACK_TOP), STACK(stack)); - - if (opcode == OP_SBRAPOS || opcode == OP_SCBRAPOS) - add_jump(compiler, &emptymatch, CMP(SLJIT_EQUAL, TMP1, 0, STR_PTR, 0)); - - if (!zero) - { - if (framesize < 0) - OP1(SLJIT_MOV, SLJIT_MEM1(STACK_TOP), STACK(stacksize - 1), SLJIT_IMM, 0); - else - OP1(SLJIT_MOV, SLJIT_MEM1(STACK_TOP), STACK(0), SLJIT_IMM, 0); - } - } - - JUMPTO(SLJIT_JUMP, loop); - flush_stubs(common); - - compile_backtrackingpath(common, backtrack->top); - if (SLJIT_UNLIKELY(sljit_get_compiler_error(compiler))) - return NULL; - set_jumps(backtrack->topbacktracks, LABEL()); - - if (framesize < 0) - { - if (offset != 0) - OP1(SLJIT_MOV, STR_PTR, 0, SLJIT_MEM1(SLJIT_SP), cbraprivptr); - else - OP1(SLJIT_MOV, STR_PTR, 0, SLJIT_MEM1(STACK_TOP), STACK(0)); - } - else - { - if (offset != 0) - { - /* Last alternative. */ - if (*cc == OP_KETRPOS) - OP1(SLJIT_MOV, TMP2, 0, SLJIT_MEM1(SLJIT_SP), private_data_ptr); - OP1(SLJIT_MOV, STR_PTR, 0, SLJIT_MEM1(SLJIT_SP), cbraprivptr); - } - else - { - OP1(SLJIT_MOV, TMP2, 0, SLJIT_MEM1(SLJIT_SP), private_data_ptr); - OP1(SLJIT_MOV, STR_PTR, 0, SLJIT_MEM1(TMP2), (framesize + 1) * sizeof(sljit_sw)); - } - } - - if (*cc == OP_KETRPOS) - break; - ccbegin = cc + 1 + LINK_SIZE; - } - -/* We don't have to restore the control head in case of a failed match. */ - -backtrack->topbacktracks = NULL; -if (!zero) - { - if (framesize < 0) - add_jump(compiler, &backtrack->topbacktracks, CMP(SLJIT_NOT_EQUAL, SLJIT_MEM1(STACK_TOP), STACK(stacksize - 1), SLJIT_IMM, 0)); - else /* TMP2 is set to [private_data_ptr] above. */ - add_jump(compiler, &backtrack->topbacktracks, CMP(SLJIT_NOT_EQUAL, SLJIT_MEM1(TMP2), (stacksize - 1) * sizeof(sljit_sw), SLJIT_IMM, 0)); - } - -/* None of them matched. */ -set_jumps(emptymatch, LABEL()); -count_match(common); -return cc + 1 + LINK_SIZE; -} - -static SLJIT_INLINE pcre_uchar *get_iterator_parameters(compiler_common *common, pcre_uchar *cc, pcre_uchar *opcode, pcre_uchar *type, int *max, int *min, pcre_uchar **end) -{ -int class_len; - -*opcode = *cc; -if (*opcode >= OP_STAR && *opcode <= OP_POSUPTO) - { - cc++; - *type = OP_CHAR; - } -else if (*opcode >= OP_STARI && *opcode <= OP_POSUPTOI) - { - cc++; - *type = OP_CHARI; - *opcode -= OP_STARI - OP_STAR; - } -else if (*opcode >= OP_NOTSTAR && *opcode <= OP_NOTPOSUPTO) - { - cc++; - *type = OP_NOT; - *opcode -= OP_NOTSTAR - OP_STAR; - } -else if (*opcode >= OP_NOTSTARI && *opcode <= OP_NOTPOSUPTOI) - { - cc++; - *type = OP_NOTI; - *opcode -= OP_NOTSTARI - OP_STAR; - } -else if (*opcode >= OP_TYPESTAR && *opcode <= OP_TYPEPOSUPTO) - { - cc++; - *opcode -= OP_TYPESTAR - OP_STAR; - *type = 0; - } -else - { - SLJIT_ASSERT(*opcode == OP_CLASS || *opcode == OP_NCLASS || *opcode == OP_XCLASS); - *type = *opcode; - cc++; - class_len = (*type < OP_XCLASS) ? (int)(1 + (32 / sizeof(pcre_uchar))) : GET(cc, 0); - *opcode = cc[class_len - 1]; - if (*opcode >= OP_CRSTAR && *opcode <= OP_CRMINQUERY) - { - *opcode -= OP_CRSTAR - OP_STAR; - if (end != NULL) - *end = cc + class_len; - } - else if (*opcode >= OP_CRPOSSTAR && *opcode <= OP_CRPOSQUERY) - { - *opcode -= OP_CRPOSSTAR - OP_POSSTAR; - if (end != NULL) - *end = cc + class_len; - } - else - { - SLJIT_ASSERT(*opcode == OP_CRRANGE || *opcode == OP_CRMINRANGE || *opcode == OP_CRPOSRANGE); - *max = GET2(cc, (class_len + IMM2_SIZE)); - *min = GET2(cc, class_len); - - if (*min == 0) - { - SLJIT_ASSERT(*max != 0); - *opcode = (*opcode == OP_CRRANGE) ? OP_UPTO : (*opcode == OP_CRMINRANGE ? OP_MINUPTO : OP_POSUPTO); - } - if (*max == *min) - *opcode = OP_EXACT; - - if (end != NULL) - *end = cc + class_len + 2 * IMM2_SIZE; - } - return cc; - } - -if (*opcode == OP_UPTO || *opcode == OP_MINUPTO || *opcode == OP_EXACT || *opcode == OP_POSUPTO) - { - *max = GET2(cc, 0); - cc += IMM2_SIZE; - } - -if (*type == 0) - { - *type = *cc; - if (end != NULL) - *end = next_opcode(common, cc); - cc++; - return cc; - } - -if (end != NULL) - { - *end = cc + 1; -#ifdef SUPPORT_UTF - if (common->utf && HAS_EXTRALEN(*cc)) *end += GET_EXTRALEN(*cc); -#endif - } -return cc; -} - -static pcre_uchar *compile_iterator_matchingpath(compiler_common *common, pcre_uchar *cc, backtrack_common *parent) -{ -DEFINE_COMPILER; -backtrack_common *backtrack; -pcre_uchar opcode; -pcre_uchar type; -int max = -1, min = -1; -pcre_uchar *end; -jump_list *nomatch = NULL; -struct sljit_jump *jump = NULL; -struct sljit_label *label; -int private_data_ptr = PRIVATE_DATA(cc); -int base = (private_data_ptr == 0) ? SLJIT_MEM1(STACK_TOP) : SLJIT_MEM1(SLJIT_SP); -int offset0 = (private_data_ptr == 0) ? STACK(0) : private_data_ptr; -int offset1 = (private_data_ptr == 0) ? STACK(1) : private_data_ptr + (int)sizeof(sljit_sw); -int tmp_base, tmp_offset; - -PUSH_BACKTRACK(sizeof(iterator_backtrack), cc, NULL); - -cc = get_iterator_parameters(common, cc, &opcode, &type, &max, &min, &end); - -switch(type) - { - case OP_NOT_DIGIT: - case OP_DIGIT: - case OP_NOT_WHITESPACE: - case OP_WHITESPACE: - case OP_NOT_WORDCHAR: - case OP_WORDCHAR: - case OP_ANY: - case OP_ALLANY: - case OP_ANYBYTE: - case OP_ANYNL: - case OP_NOT_HSPACE: - case OP_HSPACE: - case OP_NOT_VSPACE: - case OP_VSPACE: - case OP_CHAR: - case OP_CHARI: - case OP_NOT: - case OP_NOTI: - case OP_CLASS: - case OP_NCLASS: - tmp_base = TMP3; - tmp_offset = 0; - break; - - default: - SLJIT_ASSERT_STOP(); - /* Fall through. */ - - case OP_EXTUNI: - case OP_XCLASS: - case OP_NOTPROP: - case OP_PROP: - tmp_base = SLJIT_MEM1(SLJIT_SP); - tmp_offset = POSSESSIVE0; - break; - } - -switch(opcode) - { - case OP_STAR: - case OP_PLUS: - case OP_UPTO: - case OP_CRRANGE: - if (type == OP_ANYNL || type == OP_EXTUNI) - { - SLJIT_ASSERT(private_data_ptr == 0); - if (opcode == OP_STAR || opcode == OP_UPTO) - { - allocate_stack(common, 2); - OP1(SLJIT_MOV, SLJIT_MEM1(STACK_TOP), STACK(0), STR_PTR, 0); - OP1(SLJIT_MOV, SLJIT_MEM1(STACK_TOP), STACK(1), SLJIT_IMM, 0); - } - else - { - allocate_stack(common, 1); - OP1(SLJIT_MOV, SLJIT_MEM1(STACK_TOP), STACK(0), SLJIT_IMM, 0); - } - - if (opcode == OP_UPTO || opcode == OP_CRRANGE) - OP1(SLJIT_MOV, SLJIT_MEM1(SLJIT_SP), POSSESSIVE0, SLJIT_IMM, 0); - - label = LABEL(); - compile_char1_matchingpath(common, type, cc, &backtrack->topbacktracks); - if (opcode == OP_UPTO || opcode == OP_CRRANGE) - { - OP1(SLJIT_MOV, TMP1, 0, SLJIT_MEM1(SLJIT_SP), POSSESSIVE0); - OP2(SLJIT_ADD, TMP1, 0, TMP1, 0, SLJIT_IMM, 1); - if (opcode == OP_CRRANGE && min > 0) - CMPTO(SLJIT_LESS, TMP1, 0, SLJIT_IMM, min, label); - if (opcode == OP_UPTO || (opcode == OP_CRRANGE && max > 0)) - jump = CMP(SLJIT_GREATER_EQUAL, TMP1, 0, SLJIT_IMM, max); - OP1(SLJIT_MOV, SLJIT_MEM1(SLJIT_SP), POSSESSIVE0, TMP1, 0); - } - - /* We cannot use TMP3 because of this allocate_stack. */ - allocate_stack(common, 1); - OP1(SLJIT_MOV, SLJIT_MEM1(STACK_TOP), STACK(0), STR_PTR, 0); - JUMPTO(SLJIT_JUMP, label); - if (jump != NULL) - JUMPHERE(jump); - } - else - { - if (opcode == OP_PLUS) - compile_char1_matchingpath(common, type, cc, &backtrack->topbacktracks); - if (private_data_ptr == 0) - allocate_stack(common, 2); - OP1(SLJIT_MOV, base, offset0, STR_PTR, 0); - if (opcode <= OP_PLUS) - OP1(SLJIT_MOV, base, offset1, STR_PTR, 0); - else - OP1(SLJIT_MOV, base, offset1, SLJIT_IMM, 1); - label = LABEL(); - compile_char1_matchingpath(common, type, cc, &nomatch); - OP1(SLJIT_MOV, base, offset0, STR_PTR, 0); - if (opcode <= OP_PLUS) - JUMPTO(SLJIT_JUMP, label); - else if (opcode == OP_CRRANGE && max == 0) - { - OP2(SLJIT_ADD, base, offset1, base, offset1, SLJIT_IMM, 1); - JUMPTO(SLJIT_JUMP, label); - } - else - { - OP1(SLJIT_MOV, TMP1, 0, base, offset1); - OP2(SLJIT_ADD, TMP1, 0, TMP1, 0, SLJIT_IMM, 1); - OP1(SLJIT_MOV, base, offset1, TMP1, 0); - CMPTO(SLJIT_LESS, TMP1, 0, SLJIT_IMM, max + 1, label); - } - set_jumps(nomatch, LABEL()); - if (opcode == OP_CRRANGE) - add_jump(compiler, &backtrack->topbacktracks, CMP(SLJIT_LESS, base, offset1, SLJIT_IMM, min + 1)); - OP1(SLJIT_MOV, STR_PTR, 0, base, offset0); - } - BACKTRACK_AS(iterator_backtrack)->matchingpath = LABEL(); - break; - - case OP_MINSTAR: - case OP_MINPLUS: - if (opcode == OP_MINPLUS) - compile_char1_matchingpath(common, type, cc, &backtrack->topbacktracks); - if (private_data_ptr == 0) - allocate_stack(common, 1); - OP1(SLJIT_MOV, base, offset0, STR_PTR, 0); - BACKTRACK_AS(iterator_backtrack)->matchingpath = LABEL(); - break; - - case OP_MINUPTO: - case OP_CRMINRANGE: - if (private_data_ptr == 0) - allocate_stack(common, 2); - OP1(SLJIT_MOV, base, offset0, STR_PTR, 0); - OP1(SLJIT_MOV, base, offset1, SLJIT_IMM, 1); - if (opcode == OP_CRMINRANGE) - add_jump(compiler, &backtrack->topbacktracks, JUMP(SLJIT_JUMP)); - BACKTRACK_AS(iterator_backtrack)->matchingpath = LABEL(); - break; - - case OP_QUERY: - case OP_MINQUERY: - if (private_data_ptr == 0) - allocate_stack(common, 1); - OP1(SLJIT_MOV, base, offset0, STR_PTR, 0); - if (opcode == OP_QUERY) - compile_char1_matchingpath(common, type, cc, &backtrack->topbacktracks); - BACKTRACK_AS(iterator_backtrack)->matchingpath = LABEL(); - break; - - case OP_EXACT: - OP1(SLJIT_MOV, tmp_base, tmp_offset, SLJIT_IMM, max); - label = LABEL(); - compile_char1_matchingpath(common, type, cc, &backtrack->topbacktracks); - OP2(SLJIT_SUB | SLJIT_SET_E, tmp_base, tmp_offset, tmp_base, tmp_offset, SLJIT_IMM, 1); - JUMPTO(SLJIT_NOT_ZERO, label); - break; - - case OP_POSSTAR: - case OP_POSPLUS: - case OP_POSUPTO: - if (opcode == OP_POSPLUS) - compile_char1_matchingpath(common, type, cc, &backtrack->topbacktracks); - if (opcode == OP_POSUPTO) - OP1(SLJIT_MOV, SLJIT_MEM1(SLJIT_SP), POSSESSIVE1, SLJIT_IMM, max); - OP1(SLJIT_MOV, tmp_base, tmp_offset, STR_PTR, 0); - label = LABEL(); - compile_char1_matchingpath(common, type, cc, &nomatch); - OP1(SLJIT_MOV, tmp_base, tmp_offset, STR_PTR, 0); - if (opcode != OP_POSUPTO) - JUMPTO(SLJIT_JUMP, label); - else - { - OP2(SLJIT_SUB | SLJIT_SET_E, SLJIT_MEM1(SLJIT_SP), POSSESSIVE1, SLJIT_MEM1(SLJIT_SP), POSSESSIVE1, SLJIT_IMM, 1); - JUMPTO(SLJIT_NOT_ZERO, label); - } - set_jumps(nomatch, LABEL()); - OP1(SLJIT_MOV, STR_PTR, 0, tmp_base, tmp_offset); - break; - - case OP_POSQUERY: - OP1(SLJIT_MOV, tmp_base, tmp_offset, STR_PTR, 0); - compile_char1_matchingpath(common, type, cc, &nomatch); - OP1(SLJIT_MOV, tmp_base, tmp_offset, STR_PTR, 0); - set_jumps(nomatch, LABEL()); - OP1(SLJIT_MOV, STR_PTR, 0, tmp_base, tmp_offset); - break; - - case OP_CRPOSRANGE: - /* Combination of OP_EXACT and OP_POSSTAR or OP_POSUPTO */ - OP1(SLJIT_MOV, tmp_base, tmp_offset, SLJIT_IMM, min); - label = LABEL(); - compile_char1_matchingpath(common, type, cc, &backtrack->topbacktracks); - OP2(SLJIT_SUB | SLJIT_SET_E, tmp_base, tmp_offset, tmp_base, tmp_offset, SLJIT_IMM, 1); - JUMPTO(SLJIT_NOT_ZERO, label); - - if (max != 0) - { - SLJIT_ASSERT(max - min > 0); - OP1(SLJIT_MOV, SLJIT_MEM1(SLJIT_SP), POSSESSIVE1, SLJIT_IMM, max - min); - } - OP1(SLJIT_MOV, tmp_base, tmp_offset, STR_PTR, 0); - label = LABEL(); - compile_char1_matchingpath(common, type, cc, &nomatch); - OP1(SLJIT_MOV, tmp_base, tmp_offset, STR_PTR, 0); - if (max == 0) - JUMPTO(SLJIT_JUMP, label); - else - { - OP2(SLJIT_SUB | SLJIT_SET_E, SLJIT_MEM1(SLJIT_SP), POSSESSIVE1, SLJIT_MEM1(SLJIT_SP), POSSESSIVE1, SLJIT_IMM, 1); - JUMPTO(SLJIT_NOT_ZERO, label); - } - set_jumps(nomatch, LABEL()); - OP1(SLJIT_MOV, STR_PTR, 0, tmp_base, tmp_offset); - break; - - default: - SLJIT_ASSERT_STOP(); - break; - } - -count_match(common); -return end; -} - -static SLJIT_INLINE pcre_uchar *compile_fail_accept_matchingpath(compiler_common *common, pcre_uchar *cc, backtrack_common *parent) -{ -DEFINE_COMPILER; -backtrack_common *backtrack; - -PUSH_BACKTRACK(sizeof(backtrack_common), cc, NULL); - -if (*cc == OP_FAIL) - { - add_jump(compiler, &backtrack->topbacktracks, JUMP(SLJIT_JUMP)); - return cc + 1; - } - -if (*cc == OP_ASSERT_ACCEPT || common->currententry != NULL || !common->might_be_empty) - { - /* No need to check notempty conditions. */ - if (common->accept_label == NULL) - add_jump(compiler, &common->accept, JUMP(SLJIT_JUMP)); - else - JUMPTO(SLJIT_JUMP, common->accept_label); - return cc + 1; - } - -if (common->accept_label == NULL) - add_jump(compiler, &common->accept, CMP(SLJIT_NOT_EQUAL, STR_PTR, 0, SLJIT_MEM1(SLJIT_SP), OVECTOR(0))); -else - CMPTO(SLJIT_NOT_EQUAL, STR_PTR, 0, SLJIT_MEM1(SLJIT_SP), OVECTOR(0), common->accept_label); -OP1(SLJIT_MOV, TMP1, 0, ARGUMENTS, 0); -OP1(SLJIT_MOV_UB, TMP2, 0, SLJIT_MEM1(TMP1), SLJIT_OFFSETOF(jit_arguments, notempty)); -add_jump(compiler, &backtrack->topbacktracks, CMP(SLJIT_NOT_EQUAL, TMP2, 0, SLJIT_IMM, 0)); -OP1(SLJIT_MOV_UB, TMP2, 0, SLJIT_MEM1(TMP1), SLJIT_OFFSETOF(jit_arguments, notempty_atstart)); -if (common->accept_label == NULL) - add_jump(compiler, &common->accept, CMP(SLJIT_EQUAL, TMP2, 0, SLJIT_IMM, 0)); -else - CMPTO(SLJIT_EQUAL, TMP2, 0, SLJIT_IMM, 0, common->accept_label); -OP1(SLJIT_MOV, TMP2, 0, SLJIT_MEM1(TMP1), SLJIT_OFFSETOF(jit_arguments, str)); -if (common->accept_label == NULL) - add_jump(compiler, &common->accept, CMP(SLJIT_NOT_EQUAL, TMP2, 0, STR_PTR, 0)); -else - CMPTO(SLJIT_NOT_EQUAL, TMP2, 0, STR_PTR, 0, common->accept_label); -add_jump(compiler, &backtrack->topbacktracks, JUMP(SLJIT_JUMP)); -return cc + 1; -} - -static SLJIT_INLINE pcre_uchar *compile_close_matchingpath(compiler_common *common, pcre_uchar *cc) -{ -DEFINE_COMPILER; -int offset = GET2(cc, 1); -BOOL optimized_cbracket = common->optimized_cbracket[offset] != 0; - -/* Data will be discarded anyway... */ -if (common->currententry != NULL) - return cc + 1 + IMM2_SIZE; - -if (!optimized_cbracket) - OP1(SLJIT_MOV, TMP1, 0, SLJIT_MEM1(SLJIT_SP), OVECTOR_PRIV(offset)); -offset <<= 1; -OP1(SLJIT_MOV, SLJIT_MEM1(SLJIT_SP), OVECTOR(offset + 1), STR_PTR, 0); -if (!optimized_cbracket) - OP1(SLJIT_MOV, SLJIT_MEM1(SLJIT_SP), OVECTOR(offset), TMP1, 0); -return cc + 1 + IMM2_SIZE; -} - -static SLJIT_INLINE pcre_uchar *compile_control_verb_matchingpath(compiler_common *common, pcre_uchar *cc, backtrack_common *parent) -{ -DEFINE_COMPILER; -backtrack_common *backtrack; -pcre_uchar opcode = *cc; -pcre_uchar *ccend = cc + 1; - -if (opcode == OP_PRUNE_ARG || opcode == OP_SKIP_ARG || opcode == OP_THEN_ARG) - ccend += 2 + cc[1]; - -PUSH_BACKTRACK(sizeof(backtrack_common), cc, NULL); - -if (opcode == OP_SKIP) - { - allocate_stack(common, 1); - OP1(SLJIT_MOV, SLJIT_MEM1(STACK_TOP), STACK(0), STR_PTR, 0); - return ccend; - } - -if (opcode == OP_PRUNE_ARG || opcode == OP_THEN_ARG) - { - OP1(SLJIT_MOV, TMP1, 0, ARGUMENTS, 0); - OP1(SLJIT_MOV, TMP2, 0, SLJIT_IMM, (sljit_sw)(cc + 2)); - OP1(SLJIT_MOV, SLJIT_MEM1(SLJIT_SP), common->mark_ptr, TMP2, 0); - OP1(SLJIT_MOV, SLJIT_MEM1(TMP1), SLJIT_OFFSETOF(jit_arguments, mark_ptr), TMP2, 0); - } - -return ccend; -} - -static pcre_uchar then_trap_opcode[1] = { OP_THEN_TRAP }; - -static SLJIT_INLINE void compile_then_trap_matchingpath(compiler_common *common, pcre_uchar *cc, pcre_uchar *ccend, backtrack_common *parent) -{ -DEFINE_COMPILER; -backtrack_common *backtrack; -BOOL needs_control_head; -int size; - -PUSH_BACKTRACK_NOVALUE(sizeof(then_trap_backtrack), cc); -common->then_trap = BACKTRACK_AS(then_trap_backtrack); -BACKTRACK_AS(then_trap_backtrack)->common.cc = then_trap_opcode; -BACKTRACK_AS(then_trap_backtrack)->start = (sljit_sw)(cc - common->start); -BACKTRACK_AS(then_trap_backtrack)->framesize = get_framesize(common, cc, ccend, FALSE, &needs_control_head); - -size = BACKTRACK_AS(then_trap_backtrack)->framesize; -size = 3 + (size < 0 ? 0 : size); - -OP1(SLJIT_MOV, TMP2, 0, SLJIT_MEM1(SLJIT_SP), common->control_head_ptr); -allocate_stack(common, size); -if (size > 3) - OP2(SLJIT_SUB, SLJIT_MEM1(SLJIT_SP), common->control_head_ptr, STACK_TOP, 0, SLJIT_IMM, (size - 3) * sizeof(sljit_sw)); -else - OP1(SLJIT_MOV, SLJIT_MEM1(SLJIT_SP), common->control_head_ptr, STACK_TOP, 0); -OP1(SLJIT_MOV, SLJIT_MEM1(STACK_TOP), STACK(size - 1), SLJIT_IMM, BACKTRACK_AS(then_trap_backtrack)->start); -OP1(SLJIT_MOV, SLJIT_MEM1(STACK_TOP), STACK(size - 2), SLJIT_IMM, type_then_trap); -OP1(SLJIT_MOV, SLJIT_MEM1(STACK_TOP), STACK(size - 3), TMP2, 0); - -size = BACKTRACK_AS(then_trap_backtrack)->framesize; -if (size >= 0) - init_frame(common, cc, ccend, size - 1, 0, FALSE); -} - -static void compile_matchingpath(compiler_common *common, pcre_uchar *cc, pcre_uchar *ccend, backtrack_common *parent) -{ -DEFINE_COMPILER; -backtrack_common *backtrack; -BOOL has_then_trap = FALSE; -then_trap_backtrack *save_then_trap = NULL; - -SLJIT_ASSERT(*ccend == OP_END || (*ccend >= OP_ALT && *ccend <= OP_KETRPOS)); - -if (common->has_then && common->then_offsets[cc - common->start] != 0) - { - SLJIT_ASSERT(*ccend != OP_END && common->control_head_ptr != 0); - has_then_trap = TRUE; - save_then_trap = common->then_trap; - /* Tail item on backtrack. */ - compile_then_trap_matchingpath(common, cc, ccend, parent); - } - -while (cc < ccend) - { - switch(*cc) - { - case OP_SOD: - case OP_SOM: - case OP_NOT_WORD_BOUNDARY: - case OP_WORD_BOUNDARY: - case OP_NOT_DIGIT: - case OP_DIGIT: - case OP_NOT_WHITESPACE: - case OP_WHITESPACE: - case OP_NOT_WORDCHAR: - case OP_WORDCHAR: - case OP_ANY: - case OP_ALLANY: - case OP_ANYBYTE: - case OP_NOTPROP: - case OP_PROP: - case OP_ANYNL: - case OP_NOT_HSPACE: - case OP_HSPACE: - case OP_NOT_VSPACE: - case OP_VSPACE: - case OP_EXTUNI: - case OP_EODN: - case OP_EOD: - case OP_CIRC: - case OP_CIRCM: - case OP_DOLL: - case OP_DOLLM: - case OP_NOT: - case OP_NOTI: - case OP_REVERSE: - cc = compile_char1_matchingpath(common, *cc, cc + 1, parent->top != NULL ? &parent->top->nextbacktracks : &parent->topbacktracks); - break; - - case OP_SET_SOM: - PUSH_BACKTRACK_NOVALUE(sizeof(backtrack_common), cc); - OP1(SLJIT_MOV, TMP2, 0, SLJIT_MEM1(SLJIT_SP), OVECTOR(0)); - allocate_stack(common, 1); - OP1(SLJIT_MOV, SLJIT_MEM1(SLJIT_SP), OVECTOR(0), STR_PTR, 0); - OP1(SLJIT_MOV, SLJIT_MEM1(STACK_TOP), STACK(0), TMP2, 0); - cc++; - break; - - case OP_CHAR: - case OP_CHARI: - if (common->mode == JIT_COMPILE) - cc = compile_charn_matchingpath(common, cc, ccend, parent->top != NULL ? &parent->top->nextbacktracks : &parent->topbacktracks); - else - cc = compile_char1_matchingpath(common, *cc, cc + 1, parent->top != NULL ? &parent->top->nextbacktracks : &parent->topbacktracks); - break; - - case OP_STAR: - case OP_MINSTAR: - case OP_PLUS: - case OP_MINPLUS: - case OP_QUERY: - case OP_MINQUERY: - case OP_UPTO: - case OP_MINUPTO: - case OP_EXACT: - case OP_POSSTAR: - case OP_POSPLUS: - case OP_POSQUERY: - case OP_POSUPTO: - case OP_STARI: - case OP_MINSTARI: - case OP_PLUSI: - case OP_MINPLUSI: - case OP_QUERYI: - case OP_MINQUERYI: - case OP_UPTOI: - case OP_MINUPTOI: - case OP_EXACTI: - case OP_POSSTARI: - case OP_POSPLUSI: - case OP_POSQUERYI: - case OP_POSUPTOI: - case OP_NOTSTAR: - case OP_NOTMINSTAR: - case OP_NOTPLUS: - case OP_NOTMINPLUS: - case OP_NOTQUERY: - case OP_NOTMINQUERY: - case OP_NOTUPTO: - case OP_NOTMINUPTO: - case OP_NOTEXACT: - case OP_NOTPOSSTAR: - case OP_NOTPOSPLUS: - case OP_NOTPOSQUERY: - case OP_NOTPOSUPTO: - case OP_NOTSTARI: - case OP_NOTMINSTARI: - case OP_NOTPLUSI: - case OP_NOTMINPLUSI: - case OP_NOTQUERYI: - case OP_NOTMINQUERYI: - case OP_NOTUPTOI: - case OP_NOTMINUPTOI: - case OP_NOTEXACTI: - case OP_NOTPOSSTARI: - case OP_NOTPOSPLUSI: - case OP_NOTPOSQUERYI: - case OP_NOTPOSUPTOI: - case OP_TYPESTAR: - case OP_TYPEMINSTAR: - case OP_TYPEPLUS: - case OP_TYPEMINPLUS: - case OP_TYPEQUERY: - case OP_TYPEMINQUERY: - case OP_TYPEUPTO: - case OP_TYPEMINUPTO: - case OP_TYPEEXACT: - case OP_TYPEPOSSTAR: - case OP_TYPEPOSPLUS: - case OP_TYPEPOSQUERY: - case OP_TYPEPOSUPTO: - cc = compile_iterator_matchingpath(common, cc, parent); - break; - - case OP_CLASS: - case OP_NCLASS: - if (cc[1 + (32 / sizeof(pcre_uchar))] >= OP_CRSTAR && cc[1 + (32 / sizeof(pcre_uchar))] <= OP_CRPOSRANGE) - cc = compile_iterator_matchingpath(common, cc, parent); - else - cc = compile_char1_matchingpath(common, *cc, cc + 1, parent->top != NULL ? &parent->top->nextbacktracks : &parent->topbacktracks); - break; - -#if defined SUPPORT_UTF || defined COMPILE_PCRE16 || defined COMPILE_PCRE32 - case OP_XCLASS: - if (*(cc + GET(cc, 1)) >= OP_CRSTAR && *(cc + GET(cc, 1)) <= OP_CRPOSRANGE) - cc = compile_iterator_matchingpath(common, cc, parent); - else - cc = compile_char1_matchingpath(common, *cc, cc + 1, parent->top != NULL ? &parent->top->nextbacktracks : &parent->topbacktracks); - break; -#endif - - case OP_REF: - case OP_REFI: - if (cc[1 + IMM2_SIZE] >= OP_CRSTAR && cc[1 + IMM2_SIZE] <= OP_CRPOSRANGE) - cc = compile_ref_iterator_matchingpath(common, cc, parent); - else - { - compile_ref_matchingpath(common, cc, parent->top != NULL ? &parent->top->nextbacktracks : &parent->topbacktracks, TRUE, FALSE); - cc += 1 + IMM2_SIZE; - } - break; - - case OP_DNREF: - case OP_DNREFI: - if (cc[1 + 2 * IMM2_SIZE] >= OP_CRSTAR && cc[1 + 2 * IMM2_SIZE] <= OP_CRPOSRANGE) - cc = compile_ref_iterator_matchingpath(common, cc, parent); - else - { - compile_dnref_search(common, cc, parent->top != NULL ? &parent->top->nextbacktracks : &parent->topbacktracks); - compile_ref_matchingpath(common, cc, parent->top != NULL ? &parent->top->nextbacktracks : &parent->topbacktracks, TRUE, FALSE); - cc += 1 + 2 * IMM2_SIZE; - } - break; - - case OP_RECURSE: - cc = compile_recurse_matchingpath(common, cc, parent); - break; - - case OP_CALLOUT: - cc = compile_callout_matchingpath(common, cc, parent); - break; - - case OP_ASSERT: - case OP_ASSERT_NOT: - case OP_ASSERTBACK: - case OP_ASSERTBACK_NOT: - PUSH_BACKTRACK_NOVALUE(sizeof(assert_backtrack), cc); - cc = compile_assert_matchingpath(common, cc, BACKTRACK_AS(assert_backtrack), FALSE); - break; - - case OP_BRAMINZERO: - PUSH_BACKTRACK_NOVALUE(sizeof(braminzero_backtrack), cc); - cc = bracketend(cc + 1); - if (*(cc - 1 - LINK_SIZE) != OP_KETRMIN) - { - allocate_stack(common, 1); - OP1(SLJIT_MOV, SLJIT_MEM1(STACK_TOP), STACK(0), STR_PTR, 0); - } - else - { - allocate_stack(common, 2); - OP1(SLJIT_MOV, SLJIT_MEM1(STACK_TOP), STACK(0), SLJIT_IMM, 0); - OP1(SLJIT_MOV, SLJIT_MEM1(STACK_TOP), STACK(1), STR_PTR, 0); - } - BACKTRACK_AS(braminzero_backtrack)->matchingpath = LABEL(); - count_match(common); - break; - - case OP_ONCE: - case OP_ONCE_NC: - case OP_BRA: - case OP_CBRA: - case OP_COND: - case OP_SBRA: - case OP_SCBRA: - case OP_SCOND: - cc = compile_bracket_matchingpath(common, cc, parent); - break; - - case OP_BRAZERO: - if (cc[1] > OP_ASSERTBACK_NOT) - cc = compile_bracket_matchingpath(common, cc, parent); - else - { - PUSH_BACKTRACK_NOVALUE(sizeof(assert_backtrack), cc); - cc = compile_assert_matchingpath(common, cc, BACKTRACK_AS(assert_backtrack), FALSE); - } - break; - - case OP_BRAPOS: - case OP_CBRAPOS: - case OP_SBRAPOS: - case OP_SCBRAPOS: - case OP_BRAPOSZERO: - cc = compile_bracketpos_matchingpath(common, cc, parent); - break; - - case OP_MARK: - PUSH_BACKTRACK_NOVALUE(sizeof(backtrack_common), cc); - SLJIT_ASSERT(common->mark_ptr != 0); - OP1(SLJIT_MOV, TMP2, 0, SLJIT_MEM1(SLJIT_SP), common->mark_ptr); - allocate_stack(common, common->has_skip_arg ? 5 : 1); - OP1(SLJIT_MOV, TMP1, 0, ARGUMENTS, 0); - OP1(SLJIT_MOV, SLJIT_MEM1(STACK_TOP), STACK(common->has_skip_arg ? 4 : 0), TMP2, 0); - OP1(SLJIT_MOV, TMP2, 0, SLJIT_IMM, (sljit_sw)(cc + 2)); - OP1(SLJIT_MOV, SLJIT_MEM1(SLJIT_SP), common->mark_ptr, TMP2, 0); - OP1(SLJIT_MOV, SLJIT_MEM1(TMP1), SLJIT_OFFSETOF(jit_arguments, mark_ptr), TMP2, 0); - if (common->has_skip_arg) - { - OP1(SLJIT_MOV, TMP1, 0, SLJIT_MEM1(SLJIT_SP), common->control_head_ptr); - OP1(SLJIT_MOV, SLJIT_MEM1(SLJIT_SP), common->control_head_ptr, STACK_TOP, 0); - OP1(SLJIT_MOV, SLJIT_MEM1(STACK_TOP), STACK(1), SLJIT_IMM, type_mark); - OP1(SLJIT_MOV, SLJIT_MEM1(STACK_TOP), STACK(2), SLJIT_IMM, (sljit_sw)(cc + 2)); - OP1(SLJIT_MOV, SLJIT_MEM1(STACK_TOP), STACK(3), STR_PTR, 0); - OP1(SLJIT_MOV, SLJIT_MEM1(STACK_TOP), STACK(0), TMP1, 0); - } - cc += 1 + 2 + cc[1]; - break; - - case OP_PRUNE: - case OP_PRUNE_ARG: - case OP_SKIP: - case OP_SKIP_ARG: - case OP_THEN: - case OP_THEN_ARG: - case OP_COMMIT: - cc = compile_control_verb_matchingpath(common, cc, parent); - break; - - case OP_FAIL: - case OP_ACCEPT: - case OP_ASSERT_ACCEPT: - cc = compile_fail_accept_matchingpath(common, cc, parent); - break; - - case OP_CLOSE: - cc = compile_close_matchingpath(common, cc); - break; - - case OP_SKIPZERO: - cc = bracketend(cc + 1); - break; - - default: - SLJIT_ASSERT_STOP(); - return; - } - if (cc == NULL) - return; - } - -if (has_then_trap) - { - /* Head item on backtrack. */ - PUSH_BACKTRACK_NOVALUE(sizeof(then_trap_backtrack), cc); - BACKTRACK_AS(then_trap_backtrack)->common.cc = then_trap_opcode; - BACKTRACK_AS(then_trap_backtrack)->then_trap = common->then_trap; - common->then_trap = save_then_trap; - } -SLJIT_ASSERT(cc == ccend); -} - -#undef PUSH_BACKTRACK -#undef PUSH_BACKTRACK_NOVALUE -#undef BACKTRACK_AS - -#define COMPILE_BACKTRACKINGPATH(current) \ - do \ - { \ - compile_backtrackingpath(common, (current)); \ - if (SLJIT_UNLIKELY(sljit_get_compiler_error(compiler))) \ - return; \ - } \ - while (0) - -#define CURRENT_AS(type) ((type *)current) - -static void compile_iterator_backtrackingpath(compiler_common *common, struct backtrack_common *current) -{ -DEFINE_COMPILER; -pcre_uchar *cc = current->cc; -pcre_uchar opcode; -pcre_uchar type; -int max = -1, min = -1; -struct sljit_label *label = NULL; -struct sljit_jump *jump = NULL; -jump_list *jumplist = NULL; -int private_data_ptr = PRIVATE_DATA(cc); -int base = (private_data_ptr == 0) ? SLJIT_MEM1(STACK_TOP) : SLJIT_MEM1(SLJIT_SP); -int offset0 = (private_data_ptr == 0) ? STACK(0) : private_data_ptr; -int offset1 = (private_data_ptr == 0) ? STACK(1) : private_data_ptr + (int)sizeof(sljit_sw); - -cc = get_iterator_parameters(common, cc, &opcode, &type, &max, &min, NULL); - -switch(opcode) - { - case OP_STAR: - case OP_PLUS: - case OP_UPTO: - case OP_CRRANGE: - if (type == OP_ANYNL || type == OP_EXTUNI) - { - SLJIT_ASSERT(private_data_ptr == 0); - set_jumps(current->topbacktracks, LABEL()); - OP1(SLJIT_MOV, STR_PTR, 0, SLJIT_MEM1(STACK_TOP), STACK(0)); - free_stack(common, 1); - CMPTO(SLJIT_NOT_EQUAL, STR_PTR, 0, SLJIT_IMM, 0, CURRENT_AS(iterator_backtrack)->matchingpath); - } - else - { - if (opcode == OP_UPTO) - min = 0; - if (opcode <= OP_PLUS) - { - OP1(SLJIT_MOV, STR_PTR, 0, base, offset0); - jump = CMP(SLJIT_LESS_EQUAL, STR_PTR, 0, base, offset1); - } - else - { - OP1(SLJIT_MOV, TMP1, 0, base, offset1); - OP1(SLJIT_MOV, STR_PTR, 0, base, offset0); - jump = CMP(SLJIT_LESS_EQUAL, TMP1, 0, SLJIT_IMM, min + 1); - OP2(SLJIT_SUB, base, offset1, TMP1, 0, SLJIT_IMM, 1); - } - skip_char_back(common); - OP1(SLJIT_MOV, base, offset0, STR_PTR, 0); - JUMPTO(SLJIT_JUMP, CURRENT_AS(iterator_backtrack)->matchingpath); - if (opcode == OP_CRRANGE) - set_jumps(current->topbacktracks, LABEL()); - JUMPHERE(jump); - if (private_data_ptr == 0) - free_stack(common, 2); - if (opcode == OP_PLUS) - set_jumps(current->topbacktracks, LABEL()); - } - break; - - case OP_MINSTAR: - case OP_MINPLUS: - OP1(SLJIT_MOV, STR_PTR, 0, base, offset0); - compile_char1_matchingpath(common, type, cc, &jumplist); - OP1(SLJIT_MOV, base, offset0, STR_PTR, 0); - JUMPTO(SLJIT_JUMP, CURRENT_AS(iterator_backtrack)->matchingpath); - set_jumps(jumplist, LABEL()); - if (private_data_ptr == 0) - free_stack(common, 1); - if (opcode == OP_MINPLUS) - set_jumps(current->topbacktracks, LABEL()); - break; - - case OP_MINUPTO: - case OP_CRMINRANGE: - if (opcode == OP_CRMINRANGE) - { - label = LABEL(); - set_jumps(current->topbacktracks, label); - } - OP1(SLJIT_MOV, STR_PTR, 0, base, offset0); - compile_char1_matchingpath(common, type, cc, &jumplist); - - OP1(SLJIT_MOV, TMP1, 0, base, offset1); - OP1(SLJIT_MOV, base, offset0, STR_PTR, 0); - OP2(SLJIT_ADD, TMP1, 0, TMP1, 0, SLJIT_IMM, 1); - OP1(SLJIT_MOV, base, offset1, TMP1, 0); - - if (opcode == OP_CRMINRANGE) - CMPTO(SLJIT_LESS, TMP1, 0, SLJIT_IMM, min + 1, label); - - if (opcode == OP_CRMINRANGE && max == 0) - JUMPTO(SLJIT_JUMP, CURRENT_AS(iterator_backtrack)->matchingpath); - else - CMPTO(SLJIT_LESS, TMP1, 0, SLJIT_IMM, max + 2, CURRENT_AS(iterator_backtrack)->matchingpath); - - set_jumps(jumplist, LABEL()); - if (private_data_ptr == 0) - free_stack(common, 2); - break; - - case OP_QUERY: - OP1(SLJIT_MOV, STR_PTR, 0, base, offset0); - OP1(SLJIT_MOV, base, offset0, SLJIT_IMM, 0); - CMPTO(SLJIT_NOT_EQUAL, STR_PTR, 0, SLJIT_IMM, 0, CURRENT_AS(iterator_backtrack)->matchingpath); - jump = JUMP(SLJIT_JUMP); - set_jumps(current->topbacktracks, LABEL()); - OP1(SLJIT_MOV, STR_PTR, 0, base, offset0); - OP1(SLJIT_MOV, base, offset0, SLJIT_IMM, 0); - JUMPTO(SLJIT_JUMP, CURRENT_AS(iterator_backtrack)->matchingpath); - JUMPHERE(jump); - if (private_data_ptr == 0) - free_stack(common, 1); - break; - - case OP_MINQUERY: - OP1(SLJIT_MOV, STR_PTR, 0, base, offset0); - OP1(SLJIT_MOV, base, offset0, SLJIT_IMM, 0); - jump = CMP(SLJIT_EQUAL, STR_PTR, 0, SLJIT_IMM, 0); - compile_char1_matchingpath(common, type, cc, &jumplist); - JUMPTO(SLJIT_JUMP, CURRENT_AS(iterator_backtrack)->matchingpath); - set_jumps(jumplist, LABEL()); - JUMPHERE(jump); - if (private_data_ptr == 0) - free_stack(common, 1); - break; - - case OP_EXACT: - case OP_POSPLUS: - case OP_CRPOSRANGE: - set_jumps(current->topbacktracks, LABEL()); - break; - - case OP_POSSTAR: - case OP_POSQUERY: - case OP_POSUPTO: - break; - - default: - SLJIT_ASSERT_STOP(); - break; - } -} - -static SLJIT_INLINE void compile_ref_iterator_backtrackingpath(compiler_common *common, struct backtrack_common *current) -{ -DEFINE_COMPILER; -pcre_uchar *cc = current->cc; -BOOL ref = (*cc == OP_REF || *cc == OP_REFI); -pcre_uchar type; - -type = cc[ref ? 1 + IMM2_SIZE : 1 + 2 * IMM2_SIZE]; - -if ((type & 0x1) == 0) - { - /* Maximize case. */ - set_jumps(current->topbacktracks, LABEL()); - OP1(SLJIT_MOV, STR_PTR, 0, SLJIT_MEM1(STACK_TOP), STACK(0)); - free_stack(common, 1); - CMPTO(SLJIT_NOT_EQUAL, STR_PTR, 0, SLJIT_IMM, 0, CURRENT_AS(iterator_backtrack)->matchingpath); - return; - } - -OP1(SLJIT_MOV, STR_PTR, 0, SLJIT_MEM1(STACK_TOP), STACK(0)); -CMPTO(SLJIT_NOT_EQUAL, STR_PTR, 0, SLJIT_IMM, 0, CURRENT_AS(iterator_backtrack)->matchingpath); -set_jumps(current->topbacktracks, LABEL()); -free_stack(common, ref ? 2 : 3); -} - -static SLJIT_INLINE void compile_recurse_backtrackingpath(compiler_common *common, struct backtrack_common *current) -{ -DEFINE_COMPILER; - -if (CURRENT_AS(recurse_backtrack)->inlined_pattern) - compile_backtrackingpath(common, current->top); -set_jumps(current->topbacktracks, LABEL()); -if (CURRENT_AS(recurse_backtrack)->inlined_pattern) - return; - -if (common->has_set_som && common->mark_ptr != 0) - { - OP1(SLJIT_MOV, TMP2, 0, SLJIT_MEM1(STACK_TOP), STACK(0)); - OP1(SLJIT_MOV, TMP1, 0, SLJIT_MEM1(STACK_TOP), STACK(1)); - free_stack(common, 2); - OP1(SLJIT_MOV, SLJIT_MEM1(SLJIT_SP), OVECTOR(0), TMP2, 0); - OP1(SLJIT_MOV, SLJIT_MEM1(SLJIT_SP), common->mark_ptr, TMP1, 0); - } -else if (common->has_set_som || common->mark_ptr != 0) - { - OP1(SLJIT_MOV, TMP2, 0, SLJIT_MEM1(STACK_TOP), STACK(0)); - free_stack(common, 1); - OP1(SLJIT_MOV, SLJIT_MEM1(SLJIT_SP), common->has_set_som ? (int)(OVECTOR(0)) : common->mark_ptr, TMP2, 0); - } -} - -static void compile_assert_backtrackingpath(compiler_common *common, struct backtrack_common *current) -{ -DEFINE_COMPILER; -pcre_uchar *cc = current->cc; -pcre_uchar bra = OP_BRA; -struct sljit_jump *brajump = NULL; - -SLJIT_ASSERT(*cc != OP_BRAMINZERO); -if (*cc == OP_BRAZERO) - { - bra = *cc; - cc++; - } - -if (bra == OP_BRAZERO) - { - SLJIT_ASSERT(current->topbacktracks == NULL); - OP1(SLJIT_MOV, STR_PTR, 0, SLJIT_MEM1(STACK_TOP), STACK(0)); - } - -if (CURRENT_AS(assert_backtrack)->framesize < 0) - { - set_jumps(current->topbacktracks, LABEL()); - - if (bra == OP_BRAZERO) - { - OP1(SLJIT_MOV, SLJIT_MEM1(STACK_TOP), STACK(0), SLJIT_IMM, 0); - CMPTO(SLJIT_NOT_EQUAL, STR_PTR, 0, SLJIT_IMM, 0, CURRENT_AS(assert_backtrack)->matchingpath); - free_stack(common, 1); - } - return; - } - -if (bra == OP_BRAZERO) - { - if (*cc == OP_ASSERT_NOT || *cc == OP_ASSERTBACK_NOT) - { - OP1(SLJIT_MOV, SLJIT_MEM1(STACK_TOP), STACK(0), SLJIT_IMM, 0); - CMPTO(SLJIT_NOT_EQUAL, STR_PTR, 0, SLJIT_IMM, 0, CURRENT_AS(assert_backtrack)->matchingpath); - free_stack(common, 1); - return; - } - free_stack(common, 1); - brajump = CMP(SLJIT_EQUAL, STR_PTR, 0, SLJIT_IMM, 0); - } - -if (*cc == OP_ASSERT || *cc == OP_ASSERTBACK) - { - OP1(SLJIT_MOV, STACK_TOP, 0, SLJIT_MEM1(SLJIT_SP), CURRENT_AS(assert_backtrack)->private_data_ptr); - add_jump(compiler, &common->revertframes, JUMP(SLJIT_FAST_CALL)); - OP1(SLJIT_MOV, SLJIT_MEM1(SLJIT_SP), CURRENT_AS(assert_backtrack)->private_data_ptr, SLJIT_MEM1(STACK_TOP), CURRENT_AS(assert_backtrack)->framesize * sizeof(sljit_sw)); - - set_jumps(current->topbacktracks, LABEL()); - } -else - set_jumps(current->topbacktracks, LABEL()); - -if (bra == OP_BRAZERO) - { - /* We know there is enough place on the stack. */ - OP2(SLJIT_ADD, STACK_TOP, 0, STACK_TOP, 0, SLJIT_IMM, sizeof(sljit_sw)); - OP1(SLJIT_MOV, SLJIT_MEM1(STACK_TOP), STACK(0), SLJIT_IMM, 0); - JUMPTO(SLJIT_JUMP, CURRENT_AS(assert_backtrack)->matchingpath); - JUMPHERE(brajump); - } -} - -static void compile_bracket_backtrackingpath(compiler_common *common, struct backtrack_common *current) -{ -DEFINE_COMPILER; -int opcode, stacksize, alt_count, alt_max; -int offset = 0; -int private_data_ptr = CURRENT_AS(bracket_backtrack)->private_data_ptr; -int repeat_ptr = 0, repeat_type = 0, repeat_count = 0; -pcre_uchar *cc = current->cc; -pcre_uchar *ccbegin; -pcre_uchar *ccprev; -pcre_uchar bra = OP_BRA; -pcre_uchar ket; -assert_backtrack *assert; -sljit_uw *next_update_addr = NULL; -BOOL has_alternatives; -BOOL needs_control_head = FALSE; -struct sljit_jump *brazero = NULL; -struct sljit_jump *alt1 = NULL; -struct sljit_jump *alt2 = NULL; -struct sljit_jump *once = NULL; -struct sljit_jump *cond = NULL; -struct sljit_label *rmin_label = NULL; -struct sljit_label *exact_label = NULL; - -if (*cc == OP_BRAZERO || *cc == OP_BRAMINZERO) - { - bra = *cc; - cc++; - } - -opcode = *cc; -ccbegin = bracketend(cc) - 1 - LINK_SIZE; -ket = *ccbegin; -if (ket == OP_KET && PRIVATE_DATA(ccbegin) != 0) - { - repeat_ptr = PRIVATE_DATA(ccbegin); - repeat_type = PRIVATE_DATA(ccbegin + 2); - repeat_count = PRIVATE_DATA(ccbegin + 3); - SLJIT_ASSERT(repeat_type != 0 && repeat_count != 0); - if (repeat_type == OP_UPTO) - ket = OP_KETRMAX; - if (repeat_type == OP_MINUPTO) - ket = OP_KETRMIN; - } -ccbegin = cc; -cc += GET(cc, 1); -has_alternatives = *cc == OP_ALT; -if (SLJIT_UNLIKELY(opcode == OP_COND) || SLJIT_UNLIKELY(opcode == OP_SCOND)) - has_alternatives = (ccbegin[1 + LINK_SIZE] >= OP_ASSERT && ccbegin[1 + LINK_SIZE] <= OP_ASSERTBACK_NOT) || CURRENT_AS(bracket_backtrack)->u.condfailed != NULL; -if (opcode == OP_CBRA || opcode == OP_SCBRA) - offset = (GET2(ccbegin, 1 + LINK_SIZE)) << 1; -if (SLJIT_UNLIKELY(opcode == OP_COND) && (*cc == OP_KETRMAX || *cc == OP_KETRMIN)) - opcode = OP_SCOND; -if (SLJIT_UNLIKELY(opcode == OP_ONCE_NC)) - opcode = OP_ONCE; - -alt_max = has_alternatives ? no_alternatives(ccbegin) : 0; - -/* Decoding the needs_control_head in framesize. */ -if (opcode == OP_ONCE) - { - needs_control_head = (CURRENT_AS(bracket_backtrack)->u.framesize & 0x1) != 0; - CURRENT_AS(bracket_backtrack)->u.framesize >>= 1; - } - -if (ket != OP_KET && repeat_type != 0) - { - /* TMP1 is used in OP_KETRMIN below. */ - OP1(SLJIT_MOV, TMP1, 0, SLJIT_MEM1(STACK_TOP), STACK(0)); - free_stack(common, 1); - if (repeat_type == OP_UPTO) - OP2(SLJIT_ADD, SLJIT_MEM1(SLJIT_SP), repeat_ptr, TMP1, 0, SLJIT_IMM, 1); - else - OP1(SLJIT_MOV, SLJIT_MEM1(SLJIT_SP), repeat_ptr, TMP1, 0); - } - -if (ket == OP_KETRMAX) - { - if (bra == OP_BRAZERO) - { - OP1(SLJIT_MOV, TMP1, 0, SLJIT_MEM1(STACK_TOP), STACK(0)); - free_stack(common, 1); - brazero = CMP(SLJIT_EQUAL, TMP1, 0, SLJIT_IMM, 0); - } - } -else if (ket == OP_KETRMIN) - { - if (bra != OP_BRAMINZERO) - { - OP1(SLJIT_MOV, STR_PTR, 0, SLJIT_MEM1(STACK_TOP), STACK(0)); - if (repeat_type != 0) - { - /* TMP1 was set a few lines above. */ - CMPTO(SLJIT_NOT_EQUAL, TMP1, 0, SLJIT_IMM, 0, CURRENT_AS(bracket_backtrack)->recursive_matchingpath); - /* Drop STR_PTR for non-greedy plus quantifier. */ - if (opcode != OP_ONCE) - free_stack(common, 1); - } - else if (opcode >= OP_SBRA || opcode == OP_ONCE) - { - /* Checking zero-length iteration. */ - if (opcode != OP_ONCE || CURRENT_AS(bracket_backtrack)->u.framesize < 0) - CMPTO(SLJIT_NOT_EQUAL, STR_PTR, 0, SLJIT_MEM1(SLJIT_SP), private_data_ptr, CURRENT_AS(bracket_backtrack)->recursive_matchingpath); - else - { - OP1(SLJIT_MOV, TMP1, 0, SLJIT_MEM1(SLJIT_SP), private_data_ptr); - CMPTO(SLJIT_NOT_EQUAL, STR_PTR, 0, SLJIT_MEM1(TMP1), (CURRENT_AS(bracket_backtrack)->u.framesize + 1) * sizeof(sljit_sw), CURRENT_AS(bracket_backtrack)->recursive_matchingpath); - } - /* Drop STR_PTR for non-greedy plus quantifier. */ - if (opcode != OP_ONCE) - free_stack(common, 1); - } - else - JUMPTO(SLJIT_JUMP, CURRENT_AS(bracket_backtrack)->recursive_matchingpath); - } - rmin_label = LABEL(); - if (repeat_type != 0) - OP2(SLJIT_ADD, SLJIT_MEM1(SLJIT_SP), repeat_ptr, SLJIT_MEM1(SLJIT_SP), repeat_ptr, SLJIT_IMM, 1); - } -else if (bra == OP_BRAZERO) - { - OP1(SLJIT_MOV, TMP1, 0, SLJIT_MEM1(STACK_TOP), STACK(0)); - free_stack(common, 1); - brazero = CMP(SLJIT_NOT_EQUAL, TMP1, 0, SLJIT_IMM, 0); - } -else if (repeat_type == OP_EXACT) - { - OP1(SLJIT_MOV, SLJIT_MEM1(SLJIT_SP), repeat_ptr, SLJIT_IMM, 1); - exact_label = LABEL(); - } - -if (offset != 0) - { - if (common->capture_last_ptr != 0) - { - SLJIT_ASSERT(common->optimized_cbracket[offset >> 1] == 0); - OP1(SLJIT_MOV, TMP1, 0, SLJIT_MEM1(STACK_TOP), STACK(0)); - OP1(SLJIT_MOV, TMP2, 0, SLJIT_MEM1(STACK_TOP), STACK(1)); - OP1(SLJIT_MOV, SLJIT_MEM1(SLJIT_SP), common->capture_last_ptr, TMP1, 0); - OP1(SLJIT_MOV, TMP1, 0, SLJIT_MEM1(STACK_TOP), STACK(2)); - free_stack(common, 3); - OP1(SLJIT_MOV, SLJIT_MEM1(SLJIT_SP), OVECTOR(offset), TMP2, 0); - OP1(SLJIT_MOV, SLJIT_MEM1(SLJIT_SP), OVECTOR(offset + 1), TMP1, 0); - } - else if (common->optimized_cbracket[offset >> 1] == 0) - { - OP1(SLJIT_MOV, TMP1, 0, SLJIT_MEM1(STACK_TOP), STACK(0)); - OP1(SLJIT_MOV, TMP2, 0, SLJIT_MEM1(STACK_TOP), STACK(1)); - free_stack(common, 2); - OP1(SLJIT_MOV, SLJIT_MEM1(SLJIT_SP), OVECTOR(offset), TMP1, 0); - OP1(SLJIT_MOV, SLJIT_MEM1(SLJIT_SP), OVECTOR(offset + 1), TMP2, 0); - } - } - -if (SLJIT_UNLIKELY(opcode == OP_ONCE)) - { - if (CURRENT_AS(bracket_backtrack)->u.framesize >= 0) - { - OP1(SLJIT_MOV, STACK_TOP, 0, SLJIT_MEM1(SLJIT_SP), private_data_ptr); - add_jump(compiler, &common->revertframes, JUMP(SLJIT_FAST_CALL)); - } - once = JUMP(SLJIT_JUMP); - } -else if (SLJIT_UNLIKELY(opcode == OP_COND) || SLJIT_UNLIKELY(opcode == OP_SCOND)) - { - if (has_alternatives) - { - /* Always exactly one alternative. */ - OP1(SLJIT_MOV, TMP1, 0, SLJIT_MEM1(STACK_TOP), STACK(0)); - free_stack(common, 1); - - alt_max = 2; - alt1 = CMP(SLJIT_EQUAL, TMP1, 0, SLJIT_IMM, sizeof(sljit_uw)); - } - } -else if (has_alternatives) - { - OP1(SLJIT_MOV, TMP1, 0, SLJIT_MEM1(STACK_TOP), STACK(0)); - free_stack(common, 1); - - if (alt_max > 4) - { - /* Table jump if alt_max is greater than 4. */ - next_update_addr = allocate_read_only_data(common, alt_max * sizeof(sljit_uw)); - if (SLJIT_UNLIKELY(next_update_addr == NULL)) - return; - sljit_emit_ijump(compiler, SLJIT_JUMP, SLJIT_MEM1(TMP1), (sljit_sw)next_update_addr); - add_label_addr(common, next_update_addr++); - } - else - { - if (alt_max == 4) - alt2 = CMP(SLJIT_GREATER_EQUAL, TMP1, 0, SLJIT_IMM, 2 * sizeof(sljit_uw)); - alt1 = CMP(SLJIT_GREATER_EQUAL, TMP1, 0, SLJIT_IMM, sizeof(sljit_uw)); - } - } - -COMPILE_BACKTRACKINGPATH(current->top); -if (current->topbacktracks) - set_jumps(current->topbacktracks, LABEL()); - -if (SLJIT_UNLIKELY(opcode == OP_COND) || SLJIT_UNLIKELY(opcode == OP_SCOND)) - { - /* Conditional block always has at most one alternative. */ - if (ccbegin[1 + LINK_SIZE] >= OP_ASSERT && ccbegin[1 + LINK_SIZE] <= OP_ASSERTBACK_NOT) - { - SLJIT_ASSERT(has_alternatives); - assert = CURRENT_AS(bracket_backtrack)->u.assert; - if (assert->framesize >= 0 && (ccbegin[1 + LINK_SIZE] == OP_ASSERT || ccbegin[1 + LINK_SIZE] == OP_ASSERTBACK)) - { - OP1(SLJIT_MOV, STACK_TOP, 0, SLJIT_MEM1(SLJIT_SP), assert->private_data_ptr); - add_jump(compiler, &common->revertframes, JUMP(SLJIT_FAST_CALL)); - OP1(SLJIT_MOV, SLJIT_MEM1(SLJIT_SP), assert->private_data_ptr, SLJIT_MEM1(STACK_TOP), assert->framesize * sizeof(sljit_sw)); - } - cond = JUMP(SLJIT_JUMP); - set_jumps(CURRENT_AS(bracket_backtrack)->u.assert->condfailed, LABEL()); - } - else if (CURRENT_AS(bracket_backtrack)->u.condfailed != NULL) - { - SLJIT_ASSERT(has_alternatives); - cond = JUMP(SLJIT_JUMP); - set_jumps(CURRENT_AS(bracket_backtrack)->u.condfailed, LABEL()); - } - else - SLJIT_ASSERT(!has_alternatives); - } - -if (has_alternatives) - { - alt_count = sizeof(sljit_uw); - do - { - current->top = NULL; - current->topbacktracks = NULL; - current->nextbacktracks = NULL; - /* Conditional blocks always have an additional alternative, even if it is empty. */ - if (*cc == OP_ALT) - { - ccprev = cc + 1 + LINK_SIZE; - cc += GET(cc, 1); - if (opcode != OP_COND && opcode != OP_SCOND) - { - if (opcode != OP_ONCE) - { - if (private_data_ptr != 0) - OP1(SLJIT_MOV, STR_PTR, 0, SLJIT_MEM1(SLJIT_SP), private_data_ptr); - else - OP1(SLJIT_MOV, STR_PTR, 0, SLJIT_MEM1(STACK_TOP), STACK(0)); - } - else - OP1(SLJIT_MOV, STR_PTR, 0, SLJIT_MEM1(STACK_TOP), STACK(needs_control_head ? 1 : 0)); - } - compile_matchingpath(common, ccprev, cc, current); - if (SLJIT_UNLIKELY(sljit_get_compiler_error(compiler))) - return; - } - - /* Instructions after the current alternative is successfully matched. */ - /* There is a similar code in compile_bracket_matchingpath. */ - if (opcode == OP_ONCE) - match_once_common(common, ket, CURRENT_AS(bracket_backtrack)->u.framesize, private_data_ptr, has_alternatives, needs_control_head); - - stacksize = 0; - if (repeat_type == OP_MINUPTO) - { - /* We need to preserve the counter. TMP2 will be used below. */ - OP1(SLJIT_MOV, TMP2, 0, SLJIT_MEM1(SLJIT_SP), repeat_ptr); - stacksize++; - } - if (ket != OP_KET || bra != OP_BRA) - stacksize++; - if (offset != 0) - { - if (common->capture_last_ptr != 0) - stacksize++; - if (common->optimized_cbracket[offset >> 1] == 0) - stacksize += 2; - } - if (opcode != OP_ONCE) - stacksize++; - - if (stacksize > 0) - allocate_stack(common, stacksize); - - stacksize = 0; - if (repeat_type == OP_MINUPTO) - { - /* TMP2 was set above. */ - OP2(SLJIT_SUB, SLJIT_MEM1(STACK_TOP), STACK(stacksize), TMP2, 0, SLJIT_IMM, 1); - stacksize++; - } - - if (ket != OP_KET || bra != OP_BRA) - { - if (ket != OP_KET) - OP1(SLJIT_MOV, SLJIT_MEM1(STACK_TOP), STACK(stacksize), STR_PTR, 0); - else - OP1(SLJIT_MOV, SLJIT_MEM1(STACK_TOP), STACK(stacksize), SLJIT_IMM, 0); - stacksize++; - } - - if (offset != 0) - stacksize = match_capture_common(common, stacksize, offset, private_data_ptr); - - if (opcode != OP_ONCE) - OP1(SLJIT_MOV, SLJIT_MEM1(STACK_TOP), STACK(stacksize), SLJIT_IMM, alt_count); - - if (offset != 0 && ket == OP_KETRMAX && common->optimized_cbracket[offset >> 1] != 0) - { - /* If ket is not OP_KETRMAX, this code path is executed after the jump to alternative_matchingpath. */ - SLJIT_ASSERT(private_data_ptr == OVECTOR(offset + 0)); - OP1(SLJIT_MOV, SLJIT_MEM1(SLJIT_SP), OVECTOR(offset + 1), STR_PTR, 0); - } - - JUMPTO(SLJIT_JUMP, CURRENT_AS(bracket_backtrack)->alternative_matchingpath); - - if (opcode != OP_ONCE) - { - if (alt_max > 4) - add_label_addr(common, next_update_addr++); - else - { - if (alt_count != 2 * sizeof(sljit_uw)) - { - JUMPHERE(alt1); - if (alt_max == 3 && alt_count == sizeof(sljit_uw)) - alt2 = CMP(SLJIT_GREATER_EQUAL, TMP1, 0, SLJIT_IMM, 2 * sizeof(sljit_uw)); - } - else - { - JUMPHERE(alt2); - if (alt_max == 4) - alt1 = CMP(SLJIT_GREATER_EQUAL, TMP1, 0, SLJIT_IMM, 3 * sizeof(sljit_uw)); - } - } - alt_count += sizeof(sljit_uw); - } - - COMPILE_BACKTRACKINGPATH(current->top); - if (current->topbacktracks) - set_jumps(current->topbacktracks, LABEL()); - SLJIT_ASSERT(!current->nextbacktracks); - } - while (*cc == OP_ALT); - - if (cond != NULL) - { - SLJIT_ASSERT(opcode == OP_COND || opcode == OP_SCOND); - assert = CURRENT_AS(bracket_backtrack)->u.assert; - if ((ccbegin[1 + LINK_SIZE] == OP_ASSERT_NOT || ccbegin[1 + LINK_SIZE] == OP_ASSERTBACK_NOT) && assert->framesize >= 0) - { - OP1(SLJIT_MOV, STACK_TOP, 0, SLJIT_MEM1(SLJIT_SP), assert->private_data_ptr); - add_jump(compiler, &common->revertframes, JUMP(SLJIT_FAST_CALL)); - OP1(SLJIT_MOV, SLJIT_MEM1(SLJIT_SP), assert->private_data_ptr, SLJIT_MEM1(STACK_TOP), assert->framesize * sizeof(sljit_sw)); - } - JUMPHERE(cond); - } - - /* Free the STR_PTR. */ - if (private_data_ptr == 0) - free_stack(common, 1); - } - -if (offset != 0) - { - /* Using both tmp register is better for instruction scheduling. */ - if (common->optimized_cbracket[offset >> 1] != 0) - { - OP1(SLJIT_MOV, TMP1, 0, SLJIT_MEM1(STACK_TOP), STACK(0)); - OP1(SLJIT_MOV, TMP2, 0, SLJIT_MEM1(STACK_TOP), STACK(1)); - free_stack(common, 2); - OP1(SLJIT_MOV, SLJIT_MEM1(SLJIT_SP), OVECTOR(offset), TMP1, 0); - OP1(SLJIT_MOV, SLJIT_MEM1(SLJIT_SP), OVECTOR(offset + 1), TMP2, 0); - } - else - { - OP1(SLJIT_MOV, TMP1, 0, SLJIT_MEM1(STACK_TOP), STACK(0)); - free_stack(common, 1); - OP1(SLJIT_MOV, SLJIT_MEM1(SLJIT_SP), private_data_ptr, TMP1, 0); - } - } -else if (opcode == OP_SBRA || opcode == OP_SCOND) - { - OP1(SLJIT_MOV, SLJIT_MEM1(SLJIT_SP), private_data_ptr, SLJIT_MEM1(STACK_TOP), STACK(0)); - free_stack(common, 1); - } -else if (opcode == OP_ONCE) - { - cc = ccbegin + GET(ccbegin, 1); - stacksize = needs_control_head ? 1 : 0; - - if (CURRENT_AS(bracket_backtrack)->u.framesize >= 0) - { - /* Reset head and drop saved frame. */ - stacksize += CURRENT_AS(bracket_backtrack)->u.framesize + ((ket != OP_KET || *cc == OP_ALT) ? 2 : 1); - } - else if (ket == OP_KETRMAX || (*cc == OP_ALT && ket != OP_KETRMIN)) - { - /* The STR_PTR must be released. */ - stacksize++; - } - free_stack(common, stacksize); - - JUMPHERE(once); - /* Restore previous private_data_ptr */ - if (CURRENT_AS(bracket_backtrack)->u.framesize >= 0) - OP1(SLJIT_MOV, SLJIT_MEM1(SLJIT_SP), private_data_ptr, SLJIT_MEM1(STACK_TOP), CURRENT_AS(bracket_backtrack)->u.framesize * sizeof(sljit_sw)); - else if (ket == OP_KETRMIN) - { - OP1(SLJIT_MOV, TMP1, 0, SLJIT_MEM1(STACK_TOP), STACK(1)); - /* See the comment below. */ - free_stack(common, 2); - OP1(SLJIT_MOV, SLJIT_MEM1(SLJIT_SP), private_data_ptr, TMP1, 0); - } - } - -if (repeat_type == OP_EXACT) - { - OP2(SLJIT_ADD, TMP1, 0, SLJIT_MEM1(SLJIT_SP), repeat_ptr, SLJIT_IMM, 1); - OP1(SLJIT_MOV, SLJIT_MEM1(SLJIT_SP), repeat_ptr, TMP1, 0); - CMPTO(SLJIT_LESS_EQUAL, TMP1, 0, SLJIT_IMM, repeat_count, exact_label); - } -else if (ket == OP_KETRMAX) - { - OP1(SLJIT_MOV, STR_PTR, 0, SLJIT_MEM1(STACK_TOP), STACK(0)); - if (bra != OP_BRAZERO) - free_stack(common, 1); - - CMPTO(SLJIT_NOT_EQUAL, STR_PTR, 0, SLJIT_IMM, 0, CURRENT_AS(bracket_backtrack)->recursive_matchingpath); - if (bra == OP_BRAZERO) - { - OP1(SLJIT_MOV, STR_PTR, 0, SLJIT_MEM1(STACK_TOP), STACK(1)); - JUMPTO(SLJIT_JUMP, CURRENT_AS(bracket_backtrack)->zero_matchingpath); - JUMPHERE(brazero); - free_stack(common, 1); - } - } -else if (ket == OP_KETRMIN) - { - OP1(SLJIT_MOV, TMP1, 0, SLJIT_MEM1(STACK_TOP), STACK(0)); - - /* OP_ONCE removes everything in case of a backtrack, so we don't - need to explicitly release the STR_PTR. The extra release would - affect badly the free_stack(2) above. */ - if (opcode != OP_ONCE) - free_stack(common, 1); - CMPTO(SLJIT_NOT_EQUAL, TMP1, 0, SLJIT_IMM, 0, rmin_label); - if (opcode == OP_ONCE) - free_stack(common, bra == OP_BRAMINZERO ? 2 : 1); - else if (bra == OP_BRAMINZERO) - free_stack(common, 1); - } -else if (bra == OP_BRAZERO) - { - OP1(SLJIT_MOV, STR_PTR, 0, SLJIT_MEM1(STACK_TOP), STACK(0)); - JUMPTO(SLJIT_JUMP, CURRENT_AS(bracket_backtrack)->zero_matchingpath); - JUMPHERE(brazero); - } -} - -static SLJIT_INLINE void compile_bracketpos_backtrackingpath(compiler_common *common, struct backtrack_common *current) -{ -DEFINE_COMPILER; -int offset; -struct sljit_jump *jump; - -if (CURRENT_AS(bracketpos_backtrack)->framesize < 0) - { - if (*current->cc == OP_CBRAPOS || *current->cc == OP_SCBRAPOS) - { - offset = (GET2(current->cc, 1 + LINK_SIZE)) << 1; - OP1(SLJIT_MOV, TMP1, 0, SLJIT_MEM1(STACK_TOP), STACK(0)); - OP1(SLJIT_MOV, TMP2, 0, SLJIT_MEM1(STACK_TOP), STACK(1)); - OP1(SLJIT_MOV, SLJIT_MEM1(SLJIT_SP), OVECTOR(offset), TMP1, 0); - if (common->capture_last_ptr != 0) - OP1(SLJIT_MOV, TMP1, 0, SLJIT_MEM1(STACK_TOP), STACK(2)); - OP1(SLJIT_MOV, SLJIT_MEM1(SLJIT_SP), OVECTOR(offset + 1), TMP2, 0); - if (common->capture_last_ptr != 0) - OP1(SLJIT_MOV, SLJIT_MEM1(SLJIT_SP), common->capture_last_ptr, TMP1, 0); - } - set_jumps(current->topbacktracks, LABEL()); - free_stack(common, CURRENT_AS(bracketpos_backtrack)->stacksize); - return; - } - -OP1(SLJIT_MOV, STACK_TOP, 0, SLJIT_MEM1(SLJIT_SP), CURRENT_AS(bracketpos_backtrack)->private_data_ptr); -add_jump(compiler, &common->revertframes, JUMP(SLJIT_FAST_CALL)); - -if (current->topbacktracks) - { - jump = JUMP(SLJIT_JUMP); - set_jumps(current->topbacktracks, LABEL()); - /* Drop the stack frame. */ - free_stack(common, CURRENT_AS(bracketpos_backtrack)->stacksize); - JUMPHERE(jump); - } -OP1(SLJIT_MOV, SLJIT_MEM1(SLJIT_SP), CURRENT_AS(bracketpos_backtrack)->private_data_ptr, SLJIT_MEM1(STACK_TOP), CURRENT_AS(bracketpos_backtrack)->framesize * sizeof(sljit_sw)); -} - -static SLJIT_INLINE void compile_braminzero_backtrackingpath(compiler_common *common, struct backtrack_common *current) -{ -assert_backtrack backtrack; - -current->top = NULL; -current->topbacktracks = NULL; -current->nextbacktracks = NULL; -if (current->cc[1] > OP_ASSERTBACK_NOT) - { - /* Manual call of compile_bracket_matchingpath and compile_bracket_backtrackingpath. */ - compile_bracket_matchingpath(common, current->cc, current); - compile_bracket_backtrackingpath(common, current->top); - } -else - { - memset(&backtrack, 0, sizeof(backtrack)); - backtrack.common.cc = current->cc; - backtrack.matchingpath = CURRENT_AS(braminzero_backtrack)->matchingpath; - /* Manual call of compile_assert_matchingpath. */ - compile_assert_matchingpath(common, current->cc, &backtrack, FALSE); - } -SLJIT_ASSERT(!current->nextbacktracks && !current->topbacktracks); -} - -static SLJIT_INLINE void compile_control_verb_backtrackingpath(compiler_common *common, struct backtrack_common *current) -{ -DEFINE_COMPILER; -pcre_uchar opcode = *current->cc; -struct sljit_label *loop; -struct sljit_jump *jump; - -if (opcode == OP_THEN || opcode == OP_THEN_ARG) - { - if (common->then_trap != NULL) - { - SLJIT_ASSERT(common->control_head_ptr != 0); - - OP1(SLJIT_MOV, STACK_TOP, 0, SLJIT_MEM1(SLJIT_SP), common->control_head_ptr); - OP1(SLJIT_MOV, TMP1, 0, SLJIT_IMM, type_then_trap); - OP1(SLJIT_MOV, TMP2, 0, SLJIT_IMM, common->then_trap->start); - jump = JUMP(SLJIT_JUMP); - - loop = LABEL(); - OP1(SLJIT_MOV, STACK_TOP, 0, SLJIT_MEM1(STACK_TOP), -(int)sizeof(sljit_sw)); - JUMPHERE(jump); - CMPTO(SLJIT_NOT_EQUAL, SLJIT_MEM1(STACK_TOP), -(int)(2 * sizeof(sljit_sw)), TMP1, 0, loop); - CMPTO(SLJIT_NOT_EQUAL, SLJIT_MEM1(STACK_TOP), -(int)(3 * sizeof(sljit_sw)), TMP2, 0, loop); - add_jump(compiler, &common->then_trap->quit, JUMP(SLJIT_JUMP)); - return; - } - else if (common->positive_assert) - { - add_jump(compiler, &common->positive_assert_quit, JUMP(SLJIT_JUMP)); - return; - } - } - -if (common->local_exit) - { - if (common->quit_label == NULL) - add_jump(compiler, &common->quit, JUMP(SLJIT_JUMP)); - else - JUMPTO(SLJIT_JUMP, common->quit_label); - return; - } - -if (opcode == OP_SKIP_ARG) - { - SLJIT_ASSERT(common->control_head_ptr != 0); - OP1(SLJIT_MOV, TMP1, 0, SLJIT_MEM1(SLJIT_SP), common->control_head_ptr); - OP1(SLJIT_MOV, SLJIT_MEM1(SLJIT_SP), LOCALS0, STACK_TOP, 0); - OP1(SLJIT_MOV, STACK_TOP, 0, SLJIT_IMM, (sljit_sw)(current->cc + 2)); - sljit_emit_ijump(compiler, SLJIT_CALL2, SLJIT_IMM, SLJIT_FUNC_OFFSET(do_search_mark)); - OP1(SLJIT_MOV, STACK_TOP, 0, SLJIT_MEM1(SLJIT_SP), LOCALS0); - - OP1(SLJIT_MOV, STR_PTR, 0, TMP1, 0); - add_jump(compiler, &common->reset_match, CMP(SLJIT_NOT_EQUAL, STR_PTR, 0, SLJIT_IMM, -1)); - return; - } - -if (opcode == OP_SKIP) - OP1(SLJIT_MOV, STR_PTR, 0, SLJIT_MEM1(STACK_TOP), STACK(0)); -else - OP1(SLJIT_MOV, STR_PTR, 0, SLJIT_IMM, 0); -add_jump(compiler, &common->reset_match, JUMP(SLJIT_JUMP)); -} - -static SLJIT_INLINE void compile_then_trap_backtrackingpath(compiler_common *common, struct backtrack_common *current) -{ -DEFINE_COMPILER; -struct sljit_jump *jump; -int size; - -if (CURRENT_AS(then_trap_backtrack)->then_trap) - { - common->then_trap = CURRENT_AS(then_trap_backtrack)->then_trap; - return; - } - -size = CURRENT_AS(then_trap_backtrack)->framesize; -size = 3 + (size < 0 ? 0 : size); - -OP1(SLJIT_MOV, TMP1, 0, SLJIT_MEM1(STACK_TOP), STACK(size - 3)); -free_stack(common, size); -jump = JUMP(SLJIT_JUMP); - -set_jumps(CURRENT_AS(then_trap_backtrack)->quit, LABEL()); -/* STACK_TOP is set by THEN. */ -if (CURRENT_AS(then_trap_backtrack)->framesize >= 0) - add_jump(compiler, &common->revertframes, JUMP(SLJIT_FAST_CALL)); -OP1(SLJIT_MOV, TMP1, 0, SLJIT_MEM1(STACK_TOP), STACK(0)); -free_stack(common, 3); - -JUMPHERE(jump); -OP1(SLJIT_MOV, SLJIT_MEM1(SLJIT_SP), common->control_head_ptr, TMP1, 0); -} - -static void compile_backtrackingpath(compiler_common *common, struct backtrack_common *current) -{ -DEFINE_COMPILER; -then_trap_backtrack *save_then_trap = common->then_trap; - -while (current) - { - if (current->nextbacktracks != NULL) - set_jumps(current->nextbacktracks, LABEL()); - switch(*current->cc) - { - case OP_SET_SOM: - OP1(SLJIT_MOV, TMP1, 0, SLJIT_MEM1(STACK_TOP), STACK(0)); - free_stack(common, 1); - OP1(SLJIT_MOV, SLJIT_MEM1(SLJIT_SP), OVECTOR(0), TMP1, 0); - break; - - case OP_STAR: - case OP_MINSTAR: - case OP_PLUS: - case OP_MINPLUS: - case OP_QUERY: - case OP_MINQUERY: - case OP_UPTO: - case OP_MINUPTO: - case OP_EXACT: - case OP_POSSTAR: - case OP_POSPLUS: - case OP_POSQUERY: - case OP_POSUPTO: - case OP_STARI: - case OP_MINSTARI: - case OP_PLUSI: - case OP_MINPLUSI: - case OP_QUERYI: - case OP_MINQUERYI: - case OP_UPTOI: - case OP_MINUPTOI: - case OP_EXACTI: - case OP_POSSTARI: - case OP_POSPLUSI: - case OP_POSQUERYI: - case OP_POSUPTOI: - case OP_NOTSTAR: - case OP_NOTMINSTAR: - case OP_NOTPLUS: - case OP_NOTMINPLUS: - case OP_NOTQUERY: - case OP_NOTMINQUERY: - case OP_NOTUPTO: - case OP_NOTMINUPTO: - case OP_NOTEXACT: - case OP_NOTPOSSTAR: - case OP_NOTPOSPLUS: - case OP_NOTPOSQUERY: - case OP_NOTPOSUPTO: - case OP_NOTSTARI: - case OP_NOTMINSTARI: - case OP_NOTPLUSI: - case OP_NOTMINPLUSI: - case OP_NOTQUERYI: - case OP_NOTMINQUERYI: - case OP_NOTUPTOI: - case OP_NOTMINUPTOI: - case OP_NOTEXACTI: - case OP_NOTPOSSTARI: - case OP_NOTPOSPLUSI: - case OP_NOTPOSQUERYI: - case OP_NOTPOSUPTOI: - case OP_TYPESTAR: - case OP_TYPEMINSTAR: - case OP_TYPEPLUS: - case OP_TYPEMINPLUS: - case OP_TYPEQUERY: - case OP_TYPEMINQUERY: - case OP_TYPEUPTO: - case OP_TYPEMINUPTO: - case OP_TYPEEXACT: - case OP_TYPEPOSSTAR: - case OP_TYPEPOSPLUS: - case OP_TYPEPOSQUERY: - case OP_TYPEPOSUPTO: - case OP_CLASS: - case OP_NCLASS: -#if defined SUPPORT_UTF || !defined COMPILE_PCRE8 - case OP_XCLASS: -#endif - compile_iterator_backtrackingpath(common, current); - break; - - case OP_REF: - case OP_REFI: - case OP_DNREF: - case OP_DNREFI: - compile_ref_iterator_backtrackingpath(common, current); - break; - - case OP_RECURSE: - compile_recurse_backtrackingpath(common, current); - break; - - case OP_ASSERT: - case OP_ASSERT_NOT: - case OP_ASSERTBACK: - case OP_ASSERTBACK_NOT: - compile_assert_backtrackingpath(common, current); - break; - - case OP_ONCE: - case OP_ONCE_NC: - case OP_BRA: - case OP_CBRA: - case OP_COND: - case OP_SBRA: - case OP_SCBRA: - case OP_SCOND: - compile_bracket_backtrackingpath(common, current); - break; - - case OP_BRAZERO: - if (current->cc[1] > OP_ASSERTBACK_NOT) - compile_bracket_backtrackingpath(common, current); - else - compile_assert_backtrackingpath(common, current); - break; - - case OP_BRAPOS: - case OP_CBRAPOS: - case OP_SBRAPOS: - case OP_SCBRAPOS: - case OP_BRAPOSZERO: - compile_bracketpos_backtrackingpath(common, current); - break; - - case OP_BRAMINZERO: - compile_braminzero_backtrackingpath(common, current); - break; - - case OP_MARK: - OP1(SLJIT_MOV, TMP1, 0, SLJIT_MEM1(STACK_TOP), STACK(common->has_skip_arg ? 4 : 0)); - if (common->has_skip_arg) - OP1(SLJIT_MOV, TMP2, 0, SLJIT_MEM1(STACK_TOP), STACK(0)); - free_stack(common, common->has_skip_arg ? 5 : 1); - OP1(SLJIT_MOV, SLJIT_MEM1(SLJIT_SP), common->mark_ptr, TMP1, 0); - if (common->has_skip_arg) - OP1(SLJIT_MOV, SLJIT_MEM1(SLJIT_SP), common->control_head_ptr, TMP2, 0); - break; - - case OP_THEN: - case OP_THEN_ARG: - case OP_PRUNE: - case OP_PRUNE_ARG: - case OP_SKIP: - case OP_SKIP_ARG: - compile_control_verb_backtrackingpath(common, current); - break; - - case OP_COMMIT: - if (!common->local_exit) - OP1(SLJIT_MOV, SLJIT_RETURN_REG, 0, SLJIT_IMM, PCRE_ERROR_NOMATCH); - if (common->quit_label == NULL) - add_jump(compiler, &common->quit, JUMP(SLJIT_JUMP)); - else - JUMPTO(SLJIT_JUMP, common->quit_label); - break; - - case OP_CALLOUT: - case OP_FAIL: - case OP_ACCEPT: - case OP_ASSERT_ACCEPT: - set_jumps(current->topbacktracks, LABEL()); - break; - - case OP_THEN_TRAP: - /* A virtual opcode for then traps. */ - compile_then_trap_backtrackingpath(common, current); - break; - - default: - SLJIT_ASSERT_STOP(); - break; - } - current = current->prev; - } -common->then_trap = save_then_trap; -} - -static SLJIT_INLINE void compile_recurse(compiler_common *common) -{ -DEFINE_COMPILER; -pcre_uchar *cc = common->start + common->currententry->start; -pcre_uchar *ccbegin = cc + 1 + LINK_SIZE + (*cc == OP_BRA ? 0 : IMM2_SIZE); -pcre_uchar *ccend = bracketend(cc) - (1 + LINK_SIZE); -BOOL needs_control_head; -int framesize = get_framesize(common, cc, NULL, TRUE, &needs_control_head); -int private_data_size = get_private_data_copy_length(common, ccbegin, ccend, needs_control_head); -int alternativesize; -BOOL needs_frame; -backtrack_common altbacktrack; -struct sljit_jump *jump; - -/* Recurse captures then. */ -common->then_trap = NULL; - -SLJIT_ASSERT(*cc == OP_BRA || *cc == OP_CBRA || *cc == OP_CBRAPOS || *cc == OP_SCBRA || *cc == OP_SCBRAPOS); -needs_frame = framesize >= 0; -if (!needs_frame) - framesize = 0; -alternativesize = *(cc + GET(cc, 1)) == OP_ALT ? 1 : 0; - -SLJIT_ASSERT(common->currententry->entry == NULL && common->recursive_head_ptr != 0); -common->currententry->entry = LABEL(); -set_jumps(common->currententry->calls, common->currententry->entry); - -sljit_emit_fast_enter(compiler, TMP2, 0); -allocate_stack(common, private_data_size + framesize + alternativesize); -count_match(common); -OP1(SLJIT_MOV, SLJIT_MEM1(STACK_TOP), STACK(private_data_size + framesize + alternativesize - 1), TMP2, 0); -copy_private_data(common, ccbegin, ccend, TRUE, private_data_size + framesize + alternativesize, framesize + alternativesize, needs_control_head); -if (needs_control_head) - OP1(SLJIT_MOV, SLJIT_MEM1(SLJIT_SP), common->control_head_ptr, SLJIT_IMM, 0); -OP1(SLJIT_MOV, SLJIT_MEM1(SLJIT_SP), common->recursive_head_ptr, STACK_TOP, 0); -if (needs_frame) - init_frame(common, cc, NULL, framesize + alternativesize - 1, alternativesize, TRUE); - -if (alternativesize > 0) - OP1(SLJIT_MOV, SLJIT_MEM1(STACK_TOP), STACK(0), STR_PTR, 0); - -memset(&altbacktrack, 0, sizeof(backtrack_common)); -common->quit_label = NULL; -common->accept_label = NULL; -common->quit = NULL; -common->accept = NULL; -altbacktrack.cc = ccbegin; -cc += GET(cc, 1); -while (1) - { - altbacktrack.top = NULL; - altbacktrack.topbacktracks = NULL; - - if (altbacktrack.cc != ccbegin) - OP1(SLJIT_MOV, STR_PTR, 0, SLJIT_MEM1(STACK_TOP), STACK(0)); - - compile_matchingpath(common, altbacktrack.cc, cc, &altbacktrack); - if (SLJIT_UNLIKELY(sljit_get_compiler_error(compiler))) - return; - - add_jump(compiler, &common->accept, JUMP(SLJIT_JUMP)); - - compile_backtrackingpath(common, altbacktrack.top); - if (SLJIT_UNLIKELY(sljit_get_compiler_error(compiler))) - return; - set_jumps(altbacktrack.topbacktracks, LABEL()); - - if (*cc != OP_ALT) - break; - - altbacktrack.cc = cc + 1 + LINK_SIZE; - cc += GET(cc, 1); - } - -/* None of them matched. */ -OP1(SLJIT_MOV, TMP3, 0, SLJIT_IMM, 0); -jump = JUMP(SLJIT_JUMP); - -if (common->quit != NULL) - { - set_jumps(common->quit, LABEL()); - OP1(SLJIT_MOV, STACK_TOP, 0, SLJIT_MEM1(SLJIT_SP), common->recursive_head_ptr); - if (needs_frame) - { - OP2(SLJIT_SUB, STACK_TOP, 0, STACK_TOP, 0, SLJIT_IMM, (framesize + alternativesize) * sizeof(sljit_sw)); - add_jump(compiler, &common->revertframes, JUMP(SLJIT_FAST_CALL)); - OP2(SLJIT_ADD, STACK_TOP, 0, STACK_TOP, 0, SLJIT_IMM, (framesize + alternativesize) * sizeof(sljit_sw)); - } - OP1(SLJIT_MOV, TMP3, 0, SLJIT_IMM, 0); - common->quit = NULL; - add_jump(compiler, &common->quit, JUMP(SLJIT_JUMP)); - } - -set_jumps(common->accept, LABEL()); -OP1(SLJIT_MOV, STACK_TOP, 0, SLJIT_MEM1(SLJIT_SP), common->recursive_head_ptr); -if (needs_frame) - { - OP2(SLJIT_SUB, STACK_TOP, 0, STACK_TOP, 0, SLJIT_IMM, (framesize + alternativesize) * sizeof(sljit_sw)); - add_jump(compiler, &common->revertframes, JUMP(SLJIT_FAST_CALL)); - OP2(SLJIT_ADD, STACK_TOP, 0, STACK_TOP, 0, SLJIT_IMM, (framesize + alternativesize) * sizeof(sljit_sw)); - } -OP1(SLJIT_MOV, TMP3, 0, SLJIT_IMM, 1); - -JUMPHERE(jump); -if (common->quit != NULL) - set_jumps(common->quit, LABEL()); -copy_private_data(common, ccbegin, ccend, FALSE, private_data_size + framesize + alternativesize, framesize + alternativesize, needs_control_head); -free_stack(common, private_data_size + framesize + alternativesize); -if (needs_control_head) - { - OP1(SLJIT_MOV, TMP1, 0, SLJIT_MEM1(STACK_TOP), 2 * sizeof(sljit_sw)); - OP1(SLJIT_MOV, TMP2, 0, SLJIT_MEM1(STACK_TOP), sizeof(sljit_sw)); - OP1(SLJIT_MOV, SLJIT_MEM1(SLJIT_SP), common->recursive_head_ptr, TMP1, 0); - OP1(SLJIT_MOV, TMP1, 0, TMP3, 0); - OP1(SLJIT_MOV, SLJIT_MEM1(SLJIT_SP), common->control_head_ptr, TMP2, 0); - } -else - { - OP1(SLJIT_MOV, TMP2, 0, SLJIT_MEM1(STACK_TOP), sizeof(sljit_sw)); - OP1(SLJIT_MOV, TMP1, 0, TMP3, 0); - OP1(SLJIT_MOV, SLJIT_MEM1(SLJIT_SP), common->recursive_head_ptr, TMP2, 0); - } -sljit_emit_fast_return(compiler, SLJIT_MEM1(STACK_TOP), 0); -} - -#undef COMPILE_BACKTRACKINGPATH -#undef CURRENT_AS - -void -PRIV(jit_compile)(const REAL_PCRE *re, PUBL(extra) *extra, int mode) -{ -struct sljit_compiler *compiler; -backtrack_common rootbacktrack; -compiler_common common_data; -compiler_common *common = &common_data; -const pcre_uint8 *tables = re->tables; -pcre_study_data *study; -int private_data_size; -pcre_uchar *ccend; -executable_functions *functions; -void *executable_func; -sljit_uw executable_size; -sljit_uw total_length; -label_addr_list *label_addr; -struct sljit_label *mainloop_label = NULL; -struct sljit_label *continue_match_label; -struct sljit_label *empty_match_found_label = NULL; -struct sljit_label *empty_match_backtrack_label = NULL; -struct sljit_label *reset_match_label; -struct sljit_label *quit_label; -struct sljit_jump *jump; -struct sljit_jump *minlength_check_failed = NULL; -struct sljit_jump *reqbyte_notfound = NULL; -struct sljit_jump *empty_match = NULL; - -SLJIT_ASSERT((extra->flags & PCRE_EXTRA_STUDY_DATA) != 0); -study = extra->study_data; - -if (!tables) - tables = PRIV(default_tables); - -memset(&rootbacktrack, 0, sizeof(backtrack_common)); -memset(common, 0, sizeof(compiler_common)); -rootbacktrack.cc = (pcre_uchar *)re + re->name_table_offset + re->name_count * re->name_entry_size; - -common->start = rootbacktrack.cc; -common->read_only_data_head = NULL; -common->fcc = tables + fcc_offset; -common->lcc = (sljit_sw)(tables + lcc_offset); -common->mode = mode; -common->might_be_empty = study->minlength == 0; -common->nltype = NLTYPE_FIXED; -switch(re->options & PCRE_NEWLINE_BITS) - { - case 0: - /* Compile-time default */ - switch(NEWLINE) - { - case -1: common->newline = (CHAR_CR << 8) | CHAR_NL; common->nltype = NLTYPE_ANY; break; - case -2: common->newline = (CHAR_CR << 8) | CHAR_NL; common->nltype = NLTYPE_ANYCRLF; break; - default: common->newline = NEWLINE; break; - } - break; - case PCRE_NEWLINE_CR: common->newline = CHAR_CR; break; - case PCRE_NEWLINE_LF: common->newline = CHAR_NL; break; - case PCRE_NEWLINE_CR+ - PCRE_NEWLINE_LF: common->newline = (CHAR_CR << 8) | CHAR_NL; break; - case PCRE_NEWLINE_ANY: common->newline = (CHAR_CR << 8) | CHAR_NL; common->nltype = NLTYPE_ANY; break; - case PCRE_NEWLINE_ANYCRLF: common->newline = (CHAR_CR << 8) | CHAR_NL; common->nltype = NLTYPE_ANYCRLF; break; - default: return; - } -common->nlmax = READ_CHAR_MAX; -common->nlmin = 0; -if ((re->options & PCRE_BSR_ANYCRLF) != 0) - common->bsr_nltype = NLTYPE_ANYCRLF; -else if ((re->options & PCRE_BSR_UNICODE) != 0) - common->bsr_nltype = NLTYPE_ANY; -else - { -#ifdef BSR_ANYCRLF - common->bsr_nltype = NLTYPE_ANYCRLF; -#else - common->bsr_nltype = NLTYPE_ANY; -#endif - } -common->bsr_nlmax = READ_CHAR_MAX; -common->bsr_nlmin = 0; -common->endonly = (re->options & PCRE_DOLLAR_ENDONLY) != 0; -common->ctypes = (sljit_sw)(tables + ctypes_offset); -common->name_table = ((pcre_uchar *)re) + re->name_table_offset; -common->name_count = re->name_count; -common->name_entry_size = re->name_entry_size; -common->jscript_compat = (re->options & PCRE_JAVASCRIPT_COMPAT) != 0; -#ifdef SUPPORT_UTF -/* PCRE_UTF[16|32] have the same value as PCRE_UTF8. */ -common->utf = (re->options & PCRE_UTF8) != 0; -#ifdef SUPPORT_UCP -common->use_ucp = (re->options & PCRE_UCP) != 0; -#endif -if (common->utf) - { - if (common->nltype == NLTYPE_ANY) - common->nlmax = 0x2029; - else if (common->nltype == NLTYPE_ANYCRLF) - common->nlmax = (CHAR_CR > CHAR_NL) ? CHAR_CR : CHAR_NL; - else - { - /* We only care about the first newline character. */ - common->nlmax = common->newline & 0xff; - } - - if (common->nltype == NLTYPE_FIXED) - common->nlmin = common->newline & 0xff; - else - common->nlmin = (CHAR_CR < CHAR_NL) ? CHAR_CR : CHAR_NL; - - if (common->bsr_nltype == NLTYPE_ANY) - common->bsr_nlmax = 0x2029; - else - common->bsr_nlmax = (CHAR_CR > CHAR_NL) ? CHAR_CR : CHAR_NL; - common->bsr_nlmin = (CHAR_CR < CHAR_NL) ? CHAR_CR : CHAR_NL; - } -#endif /* SUPPORT_UTF */ -ccend = bracketend(common->start); - -/* Calculate the local space size on the stack. */ -common->ovector_start = LIMIT_MATCH + sizeof(sljit_sw); -common->optimized_cbracket = (pcre_uint8 *)SLJIT_MALLOC(re->top_bracket + 1, compiler->allocator_data); -if (!common->optimized_cbracket) - return; -#if defined DEBUG_FORCE_UNOPTIMIZED_CBRAS && DEBUG_FORCE_UNOPTIMIZED_CBRAS == 1 -memset(common->optimized_cbracket, 0, re->top_bracket + 1); -#else -memset(common->optimized_cbracket, 1, re->top_bracket + 1); -#endif - -SLJIT_ASSERT(*common->start == OP_BRA && ccend[-(1 + LINK_SIZE)] == OP_KET); -#if defined DEBUG_FORCE_UNOPTIMIZED_CBRAS && DEBUG_FORCE_UNOPTIMIZED_CBRAS == 2 -common->capture_last_ptr = common->ovector_start; -common->ovector_start += sizeof(sljit_sw); -#endif -if (!check_opcode_types(common, common->start, ccend)) - { - SLJIT_FREE(common->optimized_cbracket, compiler->allocator_data); - return; - } - -/* Checking flags and updating ovector_start. */ -if (mode == JIT_COMPILE && (re->flags & PCRE_REQCHSET) != 0 && (re->options & PCRE_NO_START_OPTIMIZE) == 0) - { - common->req_char_ptr = common->ovector_start; - common->ovector_start += sizeof(sljit_sw); - } -if (mode != JIT_COMPILE) - { - common->start_used_ptr = common->ovector_start; - common->ovector_start += sizeof(sljit_sw); - if (mode == JIT_PARTIAL_SOFT_COMPILE) - { - common->hit_start = common->ovector_start; - common->ovector_start += 2 * sizeof(sljit_sw); - } - else - { - SLJIT_ASSERT(mode == JIT_PARTIAL_HARD_COMPILE); - common->needs_start_ptr = TRUE; - } - } -if ((re->options & PCRE_FIRSTLINE) != 0) - { - common->first_line_end = common->ovector_start; - common->ovector_start += sizeof(sljit_sw); - } -#if defined DEBUG_FORCE_CONTROL_HEAD && DEBUG_FORCE_CONTROL_HEAD -common->control_head_ptr = 1; -#endif -if (common->control_head_ptr != 0) - { - common->control_head_ptr = common->ovector_start; - common->ovector_start += sizeof(sljit_sw); - } -if (common->needs_start_ptr && common->has_set_som) - { - /* Saving the real start pointer is necessary. */ - common->start_ptr = common->ovector_start; - common->ovector_start += sizeof(sljit_sw); - } -else - common->needs_start_ptr = FALSE; - -/* Aligning ovector to even number of sljit words. */ -if ((common->ovector_start & sizeof(sljit_sw)) != 0) - common->ovector_start += sizeof(sljit_sw); - -if (common->start_ptr == 0) - common->start_ptr = OVECTOR(0); - -/* Capturing brackets cannot be optimized if callouts are allowed. */ -if (common->capture_last_ptr != 0) - memset(common->optimized_cbracket, 0, re->top_bracket + 1); - -SLJIT_ASSERT(!(common->req_char_ptr != 0 && common->start_used_ptr != 0)); -common->cbra_ptr = OVECTOR_START + (re->top_bracket + 1) * 2 * sizeof(sljit_sw); - -total_length = ccend - common->start; -common->private_data_ptrs = (sljit_si *)SLJIT_MALLOC(total_length * (sizeof(sljit_si) + (common->has_then ? 1 : 0)), compiler->allocator_data); -if (!common->private_data_ptrs) - { - SLJIT_FREE(common->optimized_cbracket, compiler->allocator_data); - return; - } -memset(common->private_data_ptrs, 0, total_length * sizeof(sljit_si)); - -private_data_size = common->cbra_ptr + (re->top_bracket + 1) * sizeof(sljit_sw); -set_private_data_ptrs(common, &private_data_size, ccend); -if (private_data_size > SLJIT_MAX_LOCAL_SIZE) - { - SLJIT_FREE(common->private_data_ptrs, compiler->allocator_data); - SLJIT_FREE(common->optimized_cbracket, compiler->allocator_data); - return; - } - -if (common->has_then) - { - common->then_offsets = (pcre_uint8 *)(common->private_data_ptrs + total_length); - memset(common->then_offsets, 0, total_length); - set_then_offsets(common, common->start, NULL); - } - -compiler = sljit_create_compiler(NULL); -if (!compiler) - { - SLJIT_FREE(common->optimized_cbracket, compiler->allocator_data); - SLJIT_FREE(common->private_data_ptrs, compiler->allocator_data); - return; - } -common->compiler = compiler; - -/* Main pcre_jit_exec entry. */ -sljit_emit_enter(compiler, 0, 1, 5, 5, 0, 0, private_data_size); - -/* Register init. */ -reset_ovector(common, (re->top_bracket + 1) * 2); -if (common->req_char_ptr != 0) - OP1(SLJIT_MOV, SLJIT_MEM1(SLJIT_SP), common->req_char_ptr, SLJIT_R0, 0); - -OP1(SLJIT_MOV, ARGUMENTS, 0, SLJIT_S0, 0); -OP1(SLJIT_MOV, TMP1, 0, SLJIT_S0, 0); -OP1(SLJIT_MOV, STR_PTR, 0, SLJIT_MEM1(TMP1), SLJIT_OFFSETOF(jit_arguments, str)); -OP1(SLJIT_MOV, STR_END, 0, SLJIT_MEM1(TMP1), SLJIT_OFFSETOF(jit_arguments, end)); -OP1(SLJIT_MOV, TMP2, 0, SLJIT_MEM1(TMP1), SLJIT_OFFSETOF(jit_arguments, stack)); -OP1(SLJIT_MOV_UI, TMP1, 0, SLJIT_MEM1(TMP1), SLJIT_OFFSETOF(jit_arguments, limit_match)); -OP1(SLJIT_MOV, STACK_TOP, 0, SLJIT_MEM1(TMP2), SLJIT_OFFSETOF(struct sljit_stack, base)); -OP1(SLJIT_MOV, STACK_LIMIT, 0, SLJIT_MEM1(TMP2), SLJIT_OFFSETOF(struct sljit_stack, limit)); -OP2(SLJIT_ADD, TMP1, 0, TMP1, 0, SLJIT_IMM, 1); -OP1(SLJIT_MOV, SLJIT_MEM1(SLJIT_SP), LIMIT_MATCH, TMP1, 0); - -if (mode == JIT_PARTIAL_SOFT_COMPILE) - OP1(SLJIT_MOV, SLJIT_MEM1(SLJIT_SP), common->hit_start, SLJIT_IMM, -1); -if (common->mark_ptr != 0) - OP1(SLJIT_MOV, SLJIT_MEM1(SLJIT_SP), common->mark_ptr, SLJIT_IMM, 0); -if (common->control_head_ptr != 0) - OP1(SLJIT_MOV, SLJIT_MEM1(SLJIT_SP), common->control_head_ptr, SLJIT_IMM, 0); - -/* Main part of the matching */ -if ((re->options & PCRE_ANCHORED) == 0) - { - mainloop_label = mainloop_entry(common, (re->flags & PCRE_HASCRORLF) != 0, (re->options & PCRE_FIRSTLINE) != 0); - continue_match_label = LABEL(); - /* Forward search if possible. */ - if ((re->options & PCRE_NO_START_OPTIMIZE) == 0) - { - if (mode == JIT_COMPILE && fast_forward_first_n_chars(common, (re->options & PCRE_FIRSTLINE) != 0)) - ; - else if ((re->flags & PCRE_FIRSTSET) != 0) - fast_forward_first_char(common, (pcre_uchar)re->first_char, (re->flags & PCRE_FCH_CASELESS) != 0, (re->options & PCRE_FIRSTLINE) != 0); - else if ((re->flags & PCRE_STARTLINE) != 0) - fast_forward_newline(common, (re->options & PCRE_FIRSTLINE) != 0); - else if (study != NULL && (study->flags & PCRE_STUDY_MAPPED) != 0) - fast_forward_start_bits(common, study->start_bits, (re->options & PCRE_FIRSTLINE) != 0); - } - } -else - continue_match_label = LABEL(); - -if (mode == JIT_COMPILE && study->minlength > 0 && (re->options & PCRE_NO_START_OPTIMIZE) == 0) - { - OP1(SLJIT_MOV, SLJIT_RETURN_REG, 0, SLJIT_IMM, PCRE_ERROR_NOMATCH); - OP2(SLJIT_ADD, TMP2, 0, STR_PTR, 0, SLJIT_IMM, IN_UCHARS(study->minlength)); - minlength_check_failed = CMP(SLJIT_GREATER, TMP2, 0, STR_END, 0); - } -if (common->req_char_ptr != 0) - reqbyte_notfound = search_requested_char(common, (pcre_uchar)re->req_char, (re->flags & PCRE_RCH_CASELESS) != 0, (re->flags & PCRE_FIRSTSET) != 0); - -/* Store the current STR_PTR in OVECTOR(0). */ -OP1(SLJIT_MOV, SLJIT_MEM1(SLJIT_SP), OVECTOR(0), STR_PTR, 0); -/* Copy the limit of allowed recursions. */ -OP1(SLJIT_MOV, COUNT_MATCH, 0, SLJIT_MEM1(SLJIT_SP), LIMIT_MATCH); -if (common->capture_last_ptr != 0) - OP1(SLJIT_MOV, SLJIT_MEM1(SLJIT_SP), common->capture_last_ptr, SLJIT_IMM, -1); - -if (common->needs_start_ptr) - { - SLJIT_ASSERT(common->start_ptr != OVECTOR(0)); - OP1(SLJIT_MOV, SLJIT_MEM1(SLJIT_SP), common->start_ptr, STR_PTR, 0); - } -else - SLJIT_ASSERT(common->start_ptr == OVECTOR(0)); - -/* Copy the beginning of the string. */ -if (mode == JIT_PARTIAL_SOFT_COMPILE) - { - jump = CMP(SLJIT_NOT_EQUAL, SLJIT_MEM1(SLJIT_SP), common->hit_start, SLJIT_IMM, -1); - OP1(SLJIT_MOV, SLJIT_MEM1(SLJIT_SP), common->start_used_ptr, STR_PTR, 0); - OP1(SLJIT_MOV, SLJIT_MEM1(SLJIT_SP), common->hit_start + sizeof(sljit_sw), STR_PTR, 0); - JUMPHERE(jump); - } -else if (mode == JIT_PARTIAL_HARD_COMPILE) - OP1(SLJIT_MOV, SLJIT_MEM1(SLJIT_SP), common->start_used_ptr, STR_PTR, 0); - -compile_matchingpath(common, common->start, ccend, &rootbacktrack); -if (SLJIT_UNLIKELY(sljit_get_compiler_error(compiler))) - { - sljit_free_compiler(compiler); - SLJIT_FREE(common->optimized_cbracket, compiler->allocator_data); - SLJIT_FREE(common->private_data_ptrs, compiler->allocator_data); - free_read_only_data(common->read_only_data_head, compiler->allocator_data); - return; - } - -if (common->might_be_empty) - { - empty_match = CMP(SLJIT_EQUAL, STR_PTR, 0, SLJIT_MEM1(SLJIT_SP), OVECTOR(0)); - empty_match_found_label = LABEL(); - } - -common->accept_label = LABEL(); -if (common->accept != NULL) - set_jumps(common->accept, common->accept_label); - -/* This means we have a match. Update the ovector. */ -copy_ovector(common, re->top_bracket + 1); -common->quit_label = common->forced_quit_label = LABEL(); -if (common->quit != NULL) - set_jumps(common->quit, common->quit_label); -if (common->forced_quit != NULL) - set_jumps(common->forced_quit, common->forced_quit_label); -if (minlength_check_failed != NULL) - SET_LABEL(minlength_check_failed, common->forced_quit_label); -sljit_emit_return(compiler, SLJIT_MOV, SLJIT_RETURN_REG, 0); - -if (mode != JIT_COMPILE) - { - common->partialmatchlabel = LABEL(); - set_jumps(common->partialmatch, common->partialmatchlabel); - return_with_partial_match(common, common->quit_label); - } - -if (common->might_be_empty) - empty_match_backtrack_label = LABEL(); -compile_backtrackingpath(common, rootbacktrack.top); -if (SLJIT_UNLIKELY(sljit_get_compiler_error(compiler))) - { - sljit_free_compiler(compiler); - SLJIT_FREE(common->optimized_cbracket, compiler->allocator_data); - SLJIT_FREE(common->private_data_ptrs, compiler->allocator_data); - free_read_only_data(common->read_only_data_head, compiler->allocator_data); - return; - } - -SLJIT_ASSERT(rootbacktrack.prev == NULL); -reset_match_label = LABEL(); - -if (mode == JIT_PARTIAL_SOFT_COMPILE) - { - /* Update hit_start only in the first time. */ - jump = CMP(SLJIT_NOT_EQUAL, SLJIT_MEM1(SLJIT_SP), common->hit_start, SLJIT_IMM, 0); - OP1(SLJIT_MOV, TMP1, 0, SLJIT_MEM1(SLJIT_SP), common->start_used_ptr); - OP1(SLJIT_MOV, SLJIT_MEM1(SLJIT_SP), common->start_used_ptr, SLJIT_IMM, -1); - OP1(SLJIT_MOV, SLJIT_MEM1(SLJIT_SP), common->hit_start, TMP1, 0); - JUMPHERE(jump); - } - -/* Check we have remaining characters. */ -if ((re->options & PCRE_ANCHORED) == 0 && (re->options & PCRE_FIRSTLINE) != 0) - { - SLJIT_ASSERT(common->first_line_end != 0); - OP1(SLJIT_MOV, TMP1, 0, SLJIT_MEM1(SLJIT_SP), common->first_line_end); - } - -OP1(SLJIT_MOV, STR_PTR, 0, SLJIT_MEM1(SLJIT_SP), common->start_ptr); - -if ((re->options & PCRE_ANCHORED) == 0) - { - if (common->ff_newline_shortcut != NULL) - { - if ((re->options & PCRE_FIRSTLINE) == 0) - CMPTO(SLJIT_LESS, STR_PTR, 0, STR_END, 0, common->ff_newline_shortcut); - /* There cannot be more newlines here. */ - } - else - { - if ((re->options & PCRE_FIRSTLINE) == 0) - CMPTO(SLJIT_LESS, STR_PTR, 0, STR_END, 0, mainloop_label); - else - CMPTO(SLJIT_LESS, STR_PTR, 0, TMP1, 0, mainloop_label); - } - } - -/* No more remaining characters. */ -if (reqbyte_notfound != NULL) - JUMPHERE(reqbyte_notfound); - -if (mode == JIT_PARTIAL_SOFT_COMPILE) - CMPTO(SLJIT_NOT_EQUAL, SLJIT_MEM1(SLJIT_SP), common->hit_start, SLJIT_IMM, -1, common->partialmatchlabel); - -OP1(SLJIT_MOV, SLJIT_RETURN_REG, 0, SLJIT_IMM, PCRE_ERROR_NOMATCH); -JUMPTO(SLJIT_JUMP, common->quit_label); - -flush_stubs(common); - -if (common->might_be_empty) - { - JUMPHERE(empty_match); - OP1(SLJIT_MOV, TMP1, 0, ARGUMENTS, 0); - OP1(SLJIT_MOV_UB, TMP2, 0, SLJIT_MEM1(TMP1), SLJIT_OFFSETOF(jit_arguments, notempty)); - CMPTO(SLJIT_NOT_EQUAL, TMP2, 0, SLJIT_IMM, 0, empty_match_backtrack_label); - OP1(SLJIT_MOV_UB, TMP2, 0, SLJIT_MEM1(TMP1), SLJIT_OFFSETOF(jit_arguments, notempty_atstart)); - CMPTO(SLJIT_EQUAL, TMP2, 0, SLJIT_IMM, 0, empty_match_found_label); - OP1(SLJIT_MOV, TMP2, 0, SLJIT_MEM1(TMP1), SLJIT_OFFSETOF(jit_arguments, str)); - CMPTO(SLJIT_NOT_EQUAL, TMP2, 0, STR_PTR, 0, empty_match_found_label); - JUMPTO(SLJIT_JUMP, empty_match_backtrack_label); - } - -common->currententry = common->entries; -common->local_exit = TRUE; -quit_label = common->quit_label; -while (common->currententry != NULL) - { - /* Might add new entries. */ - compile_recurse(common); - if (SLJIT_UNLIKELY(sljit_get_compiler_error(compiler))) - { - sljit_free_compiler(compiler); - SLJIT_FREE(common->optimized_cbracket, compiler->allocator_data); - SLJIT_FREE(common->private_data_ptrs, compiler->allocator_data); - free_read_only_data(common->read_only_data_head, compiler->allocator_data); - return; - } - flush_stubs(common); - common->currententry = common->currententry->next; - } -common->local_exit = FALSE; -common->quit_label = quit_label; - -/* Allocating stack, returns with PCRE_ERROR_JIT_STACKLIMIT if fails. */ -/* This is a (really) rare case. */ -set_jumps(common->stackalloc, LABEL()); -/* RETURN_ADDR is not a saved register. */ -sljit_emit_fast_enter(compiler, SLJIT_MEM1(SLJIT_SP), LOCALS0); -OP1(SLJIT_MOV, SLJIT_MEM1(SLJIT_SP), LOCALS1, TMP2, 0); -OP1(SLJIT_MOV, TMP1, 0, ARGUMENTS, 0); -OP1(SLJIT_MOV, TMP1, 0, SLJIT_MEM1(TMP1), SLJIT_OFFSETOF(jit_arguments, stack)); -OP1(SLJIT_MOV, SLJIT_MEM1(TMP1), SLJIT_OFFSETOF(struct sljit_stack, top), STACK_TOP, 0); -OP2(SLJIT_ADD, TMP2, 0, SLJIT_MEM1(TMP1), SLJIT_OFFSETOF(struct sljit_stack, limit), SLJIT_IMM, STACK_GROWTH_RATE); - -sljit_emit_ijump(compiler, SLJIT_CALL2, SLJIT_IMM, SLJIT_FUNC_OFFSET(sljit_stack_resize)); -jump = CMP(SLJIT_NOT_EQUAL, SLJIT_RETURN_REG, 0, SLJIT_IMM, 0); -OP1(SLJIT_MOV, TMP1, 0, ARGUMENTS, 0); -OP1(SLJIT_MOV, TMP1, 0, SLJIT_MEM1(TMP1), SLJIT_OFFSETOF(jit_arguments, stack)); -OP1(SLJIT_MOV, STACK_TOP, 0, SLJIT_MEM1(TMP1), SLJIT_OFFSETOF(struct sljit_stack, top)); -OP1(SLJIT_MOV, STACK_LIMIT, 0, SLJIT_MEM1(TMP1), SLJIT_OFFSETOF(struct sljit_stack, limit)); -OP1(SLJIT_MOV, TMP2, 0, SLJIT_MEM1(SLJIT_SP), LOCALS1); -sljit_emit_fast_return(compiler, SLJIT_MEM1(SLJIT_SP), LOCALS0); - -/* Allocation failed. */ -JUMPHERE(jump); -/* We break the return address cache here, but this is a really rare case. */ -OP1(SLJIT_MOV, SLJIT_RETURN_REG, 0, SLJIT_IMM, PCRE_ERROR_JIT_STACKLIMIT); -JUMPTO(SLJIT_JUMP, common->quit_label); - -/* Call limit reached. */ -set_jumps(common->calllimit, LABEL()); -OP1(SLJIT_MOV, SLJIT_RETURN_REG, 0, SLJIT_IMM, PCRE_ERROR_MATCHLIMIT); -JUMPTO(SLJIT_JUMP, common->quit_label); - -if (common->revertframes != NULL) - { - set_jumps(common->revertframes, LABEL()); - do_revertframes(common); - } -if (common->wordboundary != NULL) - { - set_jumps(common->wordboundary, LABEL()); - check_wordboundary(common); - } -if (common->anynewline != NULL) - { - set_jumps(common->anynewline, LABEL()); - check_anynewline(common); - } -if (common->hspace != NULL) - { - set_jumps(common->hspace, LABEL()); - check_hspace(common); - } -if (common->vspace != NULL) - { - set_jumps(common->vspace, LABEL()); - check_vspace(common); - } -if (common->casefulcmp != NULL) - { - set_jumps(common->casefulcmp, LABEL()); - do_casefulcmp(common); - } -if (common->caselesscmp != NULL) - { - set_jumps(common->caselesscmp, LABEL()); - do_caselesscmp(common); - } -if (common->reset_match != NULL) - { - set_jumps(common->reset_match, LABEL()); - do_reset_match(common, (re->top_bracket + 1) * 2); - CMPTO(SLJIT_GREATER, STR_PTR, 0, TMP1, 0, continue_match_label); - OP1(SLJIT_MOV, STR_PTR, 0, TMP1, 0); - JUMPTO(SLJIT_JUMP, reset_match_label); - } -#ifdef SUPPORT_UTF -#ifdef COMPILE_PCRE8 -if (common->utfreadchar != NULL) - { - set_jumps(common->utfreadchar, LABEL()); - do_utfreadchar(common); - } -if (common->utfreadchar16 != NULL) - { - set_jumps(common->utfreadchar16, LABEL()); - do_utfreadchar16(common); - } -if (common->utfreadtype8 != NULL) - { - set_jumps(common->utfreadtype8, LABEL()); - do_utfreadtype8(common); - } -#endif /* COMPILE_PCRE8 */ -#endif /* SUPPORT_UTF */ -#ifdef SUPPORT_UCP -if (common->getucd != NULL) - { - set_jumps(common->getucd, LABEL()); - do_getucd(common); - } -#endif - -SLJIT_FREE(common->optimized_cbracket, compiler->allocator_data); -SLJIT_FREE(common->private_data_ptrs, compiler->allocator_data); - -executable_func = sljit_generate_code(compiler); -executable_size = sljit_get_generated_code_size(compiler); -label_addr = common->label_addrs; -while (label_addr != NULL) - { - *label_addr->update_addr = sljit_get_label_addr(label_addr->label); - label_addr = label_addr->next; - } -sljit_free_compiler(compiler); -if (executable_func == NULL) - { - free_read_only_data(common->read_only_data_head, compiler->allocator_data); - return; - } - -/* Reuse the function descriptor if possible. */ -if ((extra->flags & PCRE_EXTRA_EXECUTABLE_JIT) != 0 && extra->executable_jit != NULL) - functions = (executable_functions *)extra->executable_jit; -else - { - /* Note: If your memory-checker has flagged the allocation below as a - * memory leak, it is probably because you either forgot to call - * pcre_free_study() (or pcre16_free_study()) on the pcre_extra (or - * pcre16_extra) object, or you called said function after having - * cleared the PCRE_EXTRA_EXECUTABLE_JIT bit from the "flags" field - * of the object. (The function will only free the JIT data if the - * bit remains set, as the bit indicates that the pointer to the data - * is valid.) - */ - functions = SLJIT_MALLOC(sizeof(executable_functions), compiler->allocator_data); - if (functions == NULL) - { - /* This case is highly unlikely since we just recently - freed a lot of memory. Not impossible though. */ - sljit_free_code(executable_func); - free_read_only_data(common->read_only_data_head, compiler->allocator_data); - return; - } - memset(functions, 0, sizeof(executable_functions)); - functions->top_bracket = (re->top_bracket + 1) * 2; - functions->limit_match = (re->flags & PCRE_MLSET) != 0 ? re->limit_match : 0; - extra->executable_jit = functions; - extra->flags |= PCRE_EXTRA_EXECUTABLE_JIT; - } - -functions->executable_funcs[mode] = executable_func; -functions->read_only_data_heads[mode] = common->read_only_data_head; -functions->executable_sizes[mode] = executable_size; -} - -static SLJIT_NOINLINE int jit_machine_stack_exec(jit_arguments *arguments, void *executable_func) -{ -union { - void *executable_func; - jit_function call_executable_func; -} convert_executable_func; -pcre_uint8 local_space[MACHINE_STACK_SIZE]; -struct sljit_stack local_stack; - -local_stack.top = (sljit_sw)&local_space; -local_stack.base = local_stack.top; -local_stack.limit = local_stack.base + MACHINE_STACK_SIZE; -local_stack.max_limit = local_stack.limit; -arguments->stack = &local_stack; -convert_executable_func.executable_func = executable_func; -return convert_executable_func.call_executable_func(arguments); -} - -int -PRIV(jit_exec)(const PUBL(extra) *extra_data, const pcre_uchar *subject, - int length, int start_offset, int options, int *offsets, int offset_count) -{ -executable_functions *functions = (executable_functions *)extra_data->executable_jit; -union { - void *executable_func; - jit_function call_executable_func; -} convert_executable_func; -jit_arguments arguments; -int max_offset_count; -int retval; -int mode = JIT_COMPILE; - -if ((options & PCRE_PARTIAL_HARD) != 0) - mode = JIT_PARTIAL_HARD_COMPILE; -else if ((options & PCRE_PARTIAL_SOFT) != 0) - mode = JIT_PARTIAL_SOFT_COMPILE; - -if (functions->executable_funcs[mode] == NULL) - return PCRE_ERROR_JIT_BADOPTION; - -/* Sanity checks should be handled by pcre_exec. */ -arguments.str = subject + start_offset; -arguments.begin = subject; -arguments.end = subject + length; -arguments.mark_ptr = NULL; -/* JIT decreases this value less frequently than the interpreter. */ -arguments.limit_match = ((extra_data->flags & PCRE_EXTRA_MATCH_LIMIT) == 0) ? MATCH_LIMIT : (pcre_uint32)(extra_data->match_limit); -if (functions->limit_match != 0 && functions->limit_match < arguments.limit_match) - arguments.limit_match = functions->limit_match; -arguments.notbol = (options & PCRE_NOTBOL) != 0; -arguments.noteol = (options & PCRE_NOTEOL) != 0; -arguments.notempty = (options & PCRE_NOTEMPTY) != 0; -arguments.notempty_atstart = (options & PCRE_NOTEMPTY_ATSTART) != 0; -arguments.offsets = offsets; -arguments.callout_data = (extra_data->flags & PCRE_EXTRA_CALLOUT_DATA) != 0 ? extra_data->callout_data : NULL; -arguments.real_offset_count = offset_count; - -/* pcre_exec() rounds offset_count to a multiple of 3, and then uses only 2/3 of -the output vector for storing captured strings, with the remainder used as -workspace. We don't need the workspace here. For compatibility, we limit the -number of captured strings in the same way as pcre_exec(), so that the user -gets the same result with and without JIT. */ - -if (offset_count != 2) - offset_count = ((offset_count - (offset_count % 3)) * 2) / 3; -max_offset_count = functions->top_bracket; -if (offset_count > max_offset_count) - offset_count = max_offset_count; -arguments.offset_count = offset_count; - -if (functions->callback) - arguments.stack = (struct sljit_stack *)functions->callback(functions->userdata); -else - arguments.stack = (struct sljit_stack *)functions->userdata; - -if (arguments.stack == NULL) - retval = jit_machine_stack_exec(&arguments, functions->executable_funcs[mode]); -else - { - convert_executable_func.executable_func = functions->executable_funcs[mode]; - retval = convert_executable_func.call_executable_func(&arguments); - } - -if (retval * 2 > offset_count) - retval = 0; -if ((extra_data->flags & PCRE_EXTRA_MARK) != 0) - *(extra_data->mark) = arguments.mark_ptr; - -return retval; -} - -#if defined COMPILE_PCRE8 -PCRE_EXP_DEFN int PCRE_CALL_CONVENTION -pcre_jit_exec(const pcre *argument_re, const pcre_extra *extra_data, - PCRE_SPTR subject, int length, int start_offset, int options, - int *offsets, int offset_count, pcre_jit_stack *stack) -#elif defined COMPILE_PCRE16 -PCRE_EXP_DEFN int PCRE_CALL_CONVENTION -pcre16_jit_exec(const pcre16 *argument_re, const pcre16_extra *extra_data, - PCRE_SPTR16 subject, int length, int start_offset, int options, - int *offsets, int offset_count, pcre16_jit_stack *stack) -#elif defined COMPILE_PCRE32 -PCRE_EXP_DEFN int PCRE_CALL_CONVENTION -pcre32_jit_exec(const pcre32 *argument_re, const pcre32_extra *extra_data, - PCRE_SPTR32 subject, int length, int start_offset, int options, - int *offsets, int offset_count, pcre32_jit_stack *stack) -#endif -{ -pcre_uchar *subject_ptr = (pcre_uchar *)subject; -executable_functions *functions = (executable_functions *)extra_data->executable_jit; -union { - void *executable_func; - jit_function call_executable_func; -} convert_executable_func; -jit_arguments arguments; -int max_offset_count; -int retval; -int mode = JIT_COMPILE; - -SLJIT_UNUSED_ARG(argument_re); - -/* Plausibility checks */ -if ((options & ~PUBLIC_JIT_EXEC_OPTIONS) != 0) return PCRE_ERROR_JIT_BADOPTION; - -if ((options & PCRE_PARTIAL_HARD) != 0) - mode = JIT_PARTIAL_HARD_COMPILE; -else if ((options & PCRE_PARTIAL_SOFT) != 0) - mode = JIT_PARTIAL_SOFT_COMPILE; - -if (functions->executable_funcs[mode] == NULL) - return PCRE_ERROR_JIT_BADOPTION; - -/* Sanity checks should be handled by pcre_exec. */ -arguments.stack = (struct sljit_stack *)stack; -arguments.str = subject_ptr + start_offset; -arguments.begin = subject_ptr; -arguments.end = subject_ptr + length; -arguments.mark_ptr = NULL; -/* JIT decreases this value less frequently than the interpreter. */ -arguments.limit_match = ((extra_data->flags & PCRE_EXTRA_MATCH_LIMIT) == 0) ? MATCH_LIMIT : (pcre_uint32)(extra_data->match_limit); -if (functions->limit_match != 0 && functions->limit_match < arguments.limit_match) - arguments.limit_match = functions->limit_match; -arguments.notbol = (options & PCRE_NOTBOL) != 0; -arguments.noteol = (options & PCRE_NOTEOL) != 0; -arguments.notempty = (options & PCRE_NOTEMPTY) != 0; -arguments.notempty_atstart = (options & PCRE_NOTEMPTY_ATSTART) != 0; -arguments.offsets = offsets; -arguments.callout_data = (extra_data->flags & PCRE_EXTRA_CALLOUT_DATA) != 0 ? extra_data->callout_data : NULL; -arguments.real_offset_count = offset_count; - -/* pcre_exec() rounds offset_count to a multiple of 3, and then uses only 2/3 of -the output vector for storing captured strings, with the remainder used as -workspace. We don't need the workspace here. For compatibility, we limit the -number of captured strings in the same way as pcre_exec(), so that the user -gets the same result with and without JIT. */ - -if (offset_count != 2) - offset_count = ((offset_count - (offset_count % 3)) * 2) / 3; -max_offset_count = functions->top_bracket; -if (offset_count > max_offset_count) - offset_count = max_offset_count; -arguments.offset_count = offset_count; - -convert_executable_func.executable_func = functions->executable_funcs[mode]; -retval = convert_executable_func.call_executable_func(&arguments); - -if (retval * 2 > offset_count) - retval = 0; -if ((extra_data->flags & PCRE_EXTRA_MARK) != 0) - *(extra_data->mark) = arguments.mark_ptr; - -return retval; -} - -void -PRIV(jit_free)(void *executable_funcs) -{ -int i; -executable_functions *functions = (executable_functions *)executable_funcs; -for (i = 0; i < JIT_NUMBER_OF_COMPILE_MODES; i++) - { - if (functions->executable_funcs[i] != NULL) - sljit_free_code(functions->executable_funcs[i]); - free_read_only_data(functions->read_only_data_heads[i], NULL); - } -SLJIT_FREE(functions, compiler->allocator_data); -} - -int -PRIV(jit_get_size)(void *executable_funcs) -{ -int i; -sljit_uw size = 0; -sljit_uw *executable_sizes = ((executable_functions *)executable_funcs)->executable_sizes; -for (i = 0; i < JIT_NUMBER_OF_COMPILE_MODES; i++) - size += executable_sizes[i]; -return (int)size; -} - -const char* -PRIV(jit_get_target)(void) -{ -return sljit_get_platform_name(); -} - -#if defined COMPILE_PCRE8 -PCRE_EXP_DECL pcre_jit_stack * -pcre_jit_stack_alloc(int startsize, int maxsize) -#elif defined COMPILE_PCRE16 -PCRE_EXP_DECL pcre16_jit_stack * -pcre16_jit_stack_alloc(int startsize, int maxsize) -#elif defined COMPILE_PCRE32 -PCRE_EXP_DECL pcre32_jit_stack * -pcre32_jit_stack_alloc(int startsize, int maxsize) -#endif -{ -if (startsize < 1 || maxsize < 1) - return NULL; -if (startsize > maxsize) - startsize = maxsize; -startsize = (startsize + STACK_GROWTH_RATE - 1) & ~(STACK_GROWTH_RATE - 1); -maxsize = (maxsize + STACK_GROWTH_RATE - 1) & ~(STACK_GROWTH_RATE - 1); -return (PUBL(jit_stack)*)sljit_allocate_stack(startsize, maxsize, NULL); -} - -#if defined COMPILE_PCRE8 -PCRE_EXP_DECL void -pcre_jit_stack_free(pcre_jit_stack *stack) -#elif defined COMPILE_PCRE16 -PCRE_EXP_DECL void -pcre16_jit_stack_free(pcre16_jit_stack *stack) -#elif defined COMPILE_PCRE32 -PCRE_EXP_DECL void -pcre32_jit_stack_free(pcre32_jit_stack *stack) -#endif -{ -sljit_free_stack((struct sljit_stack *)stack, NULL); -} - -#if defined COMPILE_PCRE8 -PCRE_EXP_DECL void -pcre_assign_jit_stack(pcre_extra *extra, pcre_jit_callback callback, void *userdata) -#elif defined COMPILE_PCRE16 -PCRE_EXP_DECL void -pcre16_assign_jit_stack(pcre16_extra *extra, pcre16_jit_callback callback, void *userdata) -#elif defined COMPILE_PCRE32 -PCRE_EXP_DECL void -pcre32_assign_jit_stack(pcre32_extra *extra, pcre32_jit_callback callback, void *userdata) -#endif -{ -executable_functions *functions; -if (extra != NULL && - (extra->flags & PCRE_EXTRA_EXECUTABLE_JIT) != 0 && - extra->executable_jit != NULL) - { - functions = (executable_functions *)extra->executable_jit; - functions->callback = callback; - functions->userdata = userdata; - } -} - -#if defined COMPILE_PCRE8 -PCRE_EXP_DECL void -pcre_jit_free_unused_memory(void) -#elif defined COMPILE_PCRE16 -PCRE_EXP_DECL void -pcre16_jit_free_unused_memory(void) -#elif defined COMPILE_PCRE32 -PCRE_EXP_DECL void -pcre32_jit_free_unused_memory(void) -#endif -{ -sljit_free_unused_memory_exec(); -} - -#else /* SUPPORT_JIT */ - -/* These are dummy functions to avoid linking errors when JIT support is not -being compiled. */ - -#if defined COMPILE_PCRE8 -PCRE_EXP_DECL pcre_jit_stack * -pcre_jit_stack_alloc(int startsize, int maxsize) -#elif defined COMPILE_PCRE16 -PCRE_EXP_DECL pcre16_jit_stack * -pcre16_jit_stack_alloc(int startsize, int maxsize) -#elif defined COMPILE_PCRE32 -PCRE_EXP_DECL pcre32_jit_stack * -pcre32_jit_stack_alloc(int startsize, int maxsize) -#endif -{ -(void)startsize; -(void)maxsize; -return NULL; -} - -#if defined COMPILE_PCRE8 -PCRE_EXP_DECL void -pcre_jit_stack_free(pcre_jit_stack *stack) -#elif defined COMPILE_PCRE16 -PCRE_EXP_DECL void -pcre16_jit_stack_free(pcre16_jit_stack *stack) -#elif defined COMPILE_PCRE32 -PCRE_EXP_DECL void -pcre32_jit_stack_free(pcre32_jit_stack *stack) -#endif -{ -(void)stack; -} - -#if defined COMPILE_PCRE8 -PCRE_EXP_DECL void -pcre_assign_jit_stack(pcre_extra *extra, pcre_jit_callback callback, void *userdata) -#elif defined COMPILE_PCRE16 -PCRE_EXP_DECL void -pcre16_assign_jit_stack(pcre16_extra *extra, pcre16_jit_callback callback, void *userdata) -#elif defined COMPILE_PCRE32 -PCRE_EXP_DECL void -pcre32_assign_jit_stack(pcre32_extra *extra, pcre32_jit_callback callback, void *userdata) -#endif -{ -(void)extra; -(void)callback; -(void)userdata; -} - -#if defined COMPILE_PCRE8 -PCRE_EXP_DECL void -pcre_jit_free_unused_memory(void) -#elif defined COMPILE_PCRE16 -PCRE_EXP_DECL void -pcre16_jit_free_unused_memory(void) -#elif defined COMPILE_PCRE32 -PCRE_EXP_DECL void -pcre32_jit_free_unused_memory(void) -#endif -{ -} - -#endif - -/* End of pcre_jit_compile.c */ diff --git a/src/third_party/pcre-8.38/pcre_jit_test.c b/src/third_party/pcre-8.38/pcre_jit_test.c deleted file mode 100644 index 17378957d62..00000000000 --- a/src/third_party/pcre-8.38/pcre_jit_test.c +++ /dev/null @@ -1,1738 +0,0 @@ -/************************************************* -* Perl-Compatible Regular Expressions * -*************************************************/ - -/* PCRE is a library of functions to support regular expressions whose syntax -and semantics are as close as possible to those of the Perl 5 language. - - Main Library written by Philip Hazel - Copyright (c) 1997-2012 University of Cambridge - - This JIT compiler regression test program was written by Zoltan Herczeg - Copyright (c) 2010-2012 - ------------------------------------------------------------------------------ -Redistribution and use in source and binary forms, with or without -modification, are permitted provided that the following conditions are met: - - * Redistributions of source code must retain the above copyright notice, - this list of conditions and the following disclaimer. - - * Redistributions in binary form must reproduce the above copyright - notice, this list of conditions and the following disclaimer in the - documentation and/or other materials provided with the distribution. - - * Neither the name of the University of Cambridge nor the names of its - contributors may be used to endorse or promote products derived from - this software without specific prior written permission. - -THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS" -AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE -IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE -ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR CONTRIBUTORS BE -LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR -CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF -SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS -INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN -CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) -ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE -POSSIBILITY OF SUCH DAMAGE. ------------------------------------------------------------------------------ -*/ - -#ifdef HAVE_CONFIG_H -#include "config.h" -#endif - -#include <stdio.h> -#include <string.h> -#include "pcre.h" - - -#include "pcre_internal.h" - -/* - Letter characters: - \xe6\x92\xad = 0x64ad = 25773 (kanji) - Non-letter characters: - \xc2\xa1 = 0xa1 = (Inverted Exclamation Mark) - \xf3\xa9\xb7\x80 = 0xe9dc0 = 957888 - \xed\xa0\x80 = 55296 = 0xd800 (Invalid UTF character) - \xed\xb0\x80 = 56320 = 0xdc00 (Invalid UTF character) - Newlines: - \xc2\x85 = 0x85 = 133 (NExt Line = NEL) - \xe2\x80\xa8 = 0x2028 = 8232 (Line Separator) - Othercase pairs: - \xc3\xa9 = 0xe9 = 233 (e') - \xc3\x89 = 0xc9 = 201 (E') - \xc3\xa1 = 0xe1 = 225 (a') - \xc3\x81 = 0xc1 = 193 (A') - \x53 = 0x53 = S - \x73 = 0x73 = s - \xc5\xbf = 0x17f = 383 (long S) - \xc8\xba = 0x23a = 570 - \xe2\xb1\xa5 = 0x2c65 = 11365 - \xe1\xbd\xb8 = 0x1f78 = 8056 - \xe1\xbf\xb8 = 0x1ff8 = 8184 - \xf0\x90\x90\x80 = 0x10400 = 66560 - \xf0\x90\x90\xa8 = 0x10428 = 66600 - \xc7\x84 = 0x1c4 = 452 - \xc7\x85 = 0x1c5 = 453 - \xc7\x86 = 0x1c6 = 454 - Caseless sets: - ucp_Armenian - \x{531}-\x{556} -> \x{561}-\x{586} - ucp_Coptic - \x{2c80}-\x{2ce3} -> caseless: XOR 0x1 - ucp_Latin - \x{ff21}-\x{ff3a} -> \x{ff41]-\x{ff5a} - - Mark property: - \xcc\x8d = 0x30d = 781 - Special: - \xc2\x80 = 0x80 = 128 (lowest 2 byte character) - \xdf\xbf = 0x7ff = 2047 (highest 2 byte character) - \xe0\xa0\x80 = 0x800 = 2048 (lowest 2 byte character) - \xef\xbf\xbf = 0xffff = 65535 (highest 3 byte character) - \xf0\x90\x80\x80 = 0x10000 = 65536 (lowest 4 byte character) - \xf4\x8f\xbf\xbf = 0x10ffff = 1114111 (highest allowed utf character) -*/ - -static int regression_tests(void); - -int main(void) -{ - int jit = 0; -#if defined SUPPORT_PCRE8 - pcre_config(PCRE_CONFIG_JIT, &jit); -#elif defined SUPPORT_PCRE16 - pcre16_config(PCRE_CONFIG_JIT, &jit); -#elif defined SUPPORT_PCRE32 - pcre32_config(PCRE_CONFIG_JIT, &jit); -#endif - if (!jit) { - printf("JIT must be enabled to run pcre_jit_test\n"); - return 1; - } - return regression_tests(); -} - -/* --------------------------------------------------------------------------------------- */ - -#if !(defined SUPPORT_PCRE8) && !(defined SUPPORT_PCRE16) && !(defined SUPPORT_PCRE32) -#error SUPPORT_PCRE8 or SUPPORT_PCRE16 or SUPPORT_PCRE32 must be defined -#endif - -#define MUA (PCRE_MULTILINE | PCRE_UTF8 | PCRE_NEWLINE_ANYCRLF) -#define MUAP (PCRE_MULTILINE | PCRE_UTF8 | PCRE_NEWLINE_ANYCRLF | PCRE_UCP) -#define CMUA (PCRE_CASELESS | PCRE_MULTILINE | PCRE_UTF8 | PCRE_NEWLINE_ANYCRLF) -#define CMUAP (PCRE_CASELESS | PCRE_MULTILINE | PCRE_UTF8 | PCRE_NEWLINE_ANYCRLF | PCRE_UCP) -#define MA (PCRE_MULTILINE | PCRE_NEWLINE_ANYCRLF) -#define MAP (PCRE_MULTILINE | PCRE_NEWLINE_ANYCRLF | PCRE_UCP) -#define CMA (PCRE_CASELESS | PCRE_MULTILINE | PCRE_NEWLINE_ANYCRLF) - -#define OFFSET_MASK 0x00ffff -#define F_NO8 0x010000 -#define F_NO16 0x020000 -#define F_NO32 0x020000 -#define F_NOMATCH 0x040000 -#define F_DIFF 0x080000 -#define F_FORCECONV 0x100000 -#define F_PROPERTY 0x200000 -#define F_STUDY 0x400000 - -struct regression_test_case { - int flags; - int start_offset; - const char *pattern; - const char *input; -}; - -static struct regression_test_case regression_test_cases[] = { - /* Constant strings. */ - { MUA, 0, "AbC", "AbAbC" }, - { MUA, 0, "ACCEPT", "AACACCACCEACCEPACCEPTACCEPTT" }, - { CMUA, 0, "aA#\xc3\xa9\xc3\x81", "aA#Aa#\xc3\x89\xc3\xa1" }, - { MA, 0, "[^a]", "aAbB" }, - { CMA, 0, "[^m]", "mMnN" }, - { MA, 0, "a[^b][^#]", "abacd" }, - { CMA, 0, "A[^B][^E]", "abacd" }, - { CMUA, 0, "[^x][^#]", "XxBll" }, - { MUA, 0, "[^a]", "aaa\xc3\xa1#Ab" }, - { CMUA, 0, "[^A]", "aA\xe6\x92\xad" }, - { MUA, 0, "\\W(\\W)?\\w", "\r\n+bc" }, - { MUA, 0, "\\W(\\W)?\\w", "\n\r+bc" }, - { MUA, 0, "\\W(\\W)?\\w", "\r\r+bc" }, - { MUA, 0, "\\W(\\W)?\\w", "\n\n+bc" }, - { MUA, 0, "[axd]", "sAXd" }, - { CMUA, 0, "[axd]", "sAXd" }, - { CMUA, 0 | F_NOMATCH, "[^axd]", "DxA" }, - { MUA, 0, "[a-dA-C]", "\xe6\x92\xad\xc3\xa9.B" }, - { MUA, 0, "[^a-dA-C]", "\xe6\x92\xad\xc3\xa9" }, - { CMUA, 0, "[^\xc3\xa9]", "\xc3\xa9\xc3\x89." }, - { MUA, 0, "[^\xc3\xa9]", "\xc3\xa9\xc3\x89." }, - { MUA, 0, "[^a]", "\xc2\x80[]" }, - { CMUA, 0, "\xf0\x90\x90\xa7", "\xf0\x90\x91\x8f" }, - { CMA, 0, "1a2b3c4", "1a2B3c51A2B3C4" }, - { PCRE_CASELESS, 0, "\xff#a", "\xff#\xff\xfe##\xff#A" }, - { PCRE_CASELESS, 0, "\xfe", "\xff\xfc#\xfe\xfe" }, - { PCRE_CASELESS, 0, "a1", "Aa1" }, - { MA, 0, "\\Ca", "cda" }, - { CMA, 0, "\\Ca", "CDA" }, - { MA, 0 | F_NOMATCH, "\\Cx", "cda" }, - { CMA, 0 | F_NOMATCH, "\\Cx", "CDA" }, - { CMUAP, 0, "\xf0\x90\x90\x80\xf0\x90\x90\xa8", "\xf0\x90\x90\xa8\xf0\x90\x90\x80" }, - { CMUAP, 0, "\xf0\x90\x90\x80{2}", "\xf0\x90\x90\x80#\xf0\x90\x90\xa8\xf0\x90\x90\x80" }, - { CMUAP, 0, "\xf0\x90\x90\xa8{2}", "\xf0\x90\x90\x80#\xf0\x90\x90\xa8\xf0\x90\x90\x80" }, - { CMUAP, 0, "\xe1\xbd\xb8\xe1\xbf\xb8", "\xe1\xbf\xb8\xe1\xbd\xb8" }, - { MA, 0, "[3-57-9]", "5" }, - - /* Assertions. */ - { MUA, 0, "\\b[^A]", "A_B#" }, - { MA, 0 | F_NOMATCH, "\\b\\W", "\n*" }, - { MUA, 0, "\\B[^,]\\b[^s]\\b", "#X" }, - { MAP, 0, "\\B", "_\xa1" }, - { MAP, 0, "\\b_\\b[,A]\\B", "_," }, - { MUAP, 0, "\\b", "\xe6\x92\xad!" }, - { MUAP, 0, "\\B", "_\xc2\xa1\xc3\xa1\xc2\x85" }, - { MUAP, 0, "\\b[^A]\\B[^c]\\b[^_]\\B", "_\xc3\xa1\xe2\x80\xa8" }, - { MUAP, 0, "\\b\\w+\\B", "\xc3\x89\xc2\xa1\xe6\x92\xad\xc3\x81\xc3\xa1" }, - { MUA, 0 | F_NOMATCH, "\\b.", "\xcd\xbe" }, - { CMUAP, 0, "\\By", "\xf0\x90\x90\xa8y" }, - { MA, 0 | F_NOMATCH, "\\R^", "\n" }, - { MA, 1 | F_NOMATCH, "^", "\n" }, - { 0, 0, "^ab", "ab" }, - { 0, 0 | F_NOMATCH, "^ab", "aab" }, - { PCRE_MULTILINE | PCRE_NEWLINE_CRLF, 0, "^a", "\r\raa\n\naa\r\naa" }, - { PCRE_MULTILINE | PCRE_UTF8 | PCRE_NEWLINE_ANYCRLF, 0, "^-", "\xe2\x80\xa8--\xc2\x85-\r\n-" }, - { PCRE_MULTILINE | PCRE_NEWLINE_ANY, 0, "^-", "a--b--\x85--" }, - { PCRE_MULTILINE | PCRE_UTF8 | PCRE_NEWLINE_ANY, 0, "^-", "a--\xe2\x80\xa8--" }, - { PCRE_MULTILINE | PCRE_UTF8 | PCRE_NEWLINE_ANY, 0, "^-", "a--\xc2\x85--" }, - { 0, 0, "ab$", "ab" }, - { 0, 0 | F_NOMATCH, "ab$", "abab\n\n" }, - { PCRE_DOLLAR_ENDONLY, 0 | F_NOMATCH, "ab$", "abab\r\n" }, - { PCRE_MULTILINE | PCRE_NEWLINE_CRLF, 0, "a$", "\r\raa\n\naa\r\naa" }, - { PCRE_MULTILINE | PCRE_NEWLINE_ANY, 0, "a$", "aaa" }, - { PCRE_MULTILINE | PCRE_UTF8 | PCRE_NEWLINE_ANYCRLF, 0, "#$", "#\xc2\x85###\r#" }, - { PCRE_MULTILINE | PCRE_UTF8 | PCRE_NEWLINE_ANY, 0, "#$", "#\xe2\x80\xa9" }, - { PCRE_NOTBOL | PCRE_NEWLINE_ANY, 0 | F_NOMATCH, "^a", "aa\naa" }, - { PCRE_NOTBOL | PCRE_MULTILINE | PCRE_NEWLINE_ANY, 0, "^a", "aa\naa" }, - { PCRE_NOTEOL | PCRE_NEWLINE_ANY, 0 | F_NOMATCH, "a$", "aa\naa" }, - { PCRE_NOTEOL | PCRE_NEWLINE_ANY, 0 | F_NOMATCH, "a$", "aa\r\n" }, - { PCRE_UTF8 | PCRE_DOLLAR_ENDONLY | PCRE_NEWLINE_ANY, 0 | F_PROPERTY, "\\p{Any}{2,}$", "aa\r\n" }, - { PCRE_NOTEOL | PCRE_MULTILINE | PCRE_NEWLINE_ANY, 0, "a$", "aa\naa" }, - { PCRE_NEWLINE_CR, 0, ".\\Z", "aaa" }, - { PCRE_NEWLINE_CR | PCRE_UTF8, 0, "a\\Z", "aaa\r" }, - { PCRE_NEWLINE_CR, 0, ".\\Z", "aaa\n" }, - { PCRE_NEWLINE_CRLF, 0, ".\\Z", "aaa\r" }, - { PCRE_NEWLINE_CRLF | PCRE_UTF8, 0, ".\\Z", "aaa\n" }, - { PCRE_NEWLINE_CRLF, 0, ".\\Z", "aaa\r\n" }, - { PCRE_NEWLINE_ANYCRLF | PCRE_UTF8, 0, ".\\Z", "aaa" }, - { PCRE_NEWLINE_ANYCRLF | PCRE_UTF8, 0, ".\\Z", "aaa\r" }, - { PCRE_NEWLINE_ANYCRLF | PCRE_UTF8, 0, ".\\Z", "aaa\n" }, - { PCRE_NEWLINE_ANYCRLF | PCRE_UTF8, 0, ".\\Z", "aaa\r\n" }, - { PCRE_NEWLINE_ANYCRLF | PCRE_UTF8, 0, ".\\Z", "aaa\xe2\x80\xa8" }, - { PCRE_NEWLINE_ANYCRLF | PCRE_UTF8, 0, ".\\Z", "aaa" }, - { PCRE_NEWLINE_ANYCRLF | PCRE_UTF8, 0, ".\\Z", "aaa\r" }, - { PCRE_NEWLINE_ANYCRLF | PCRE_UTF8, 0, ".\\Z", "aaa\n" }, - { PCRE_NEWLINE_ANYCRLF | PCRE_UTF8, 0, ".\\Z", "aaa\r\n" }, - { PCRE_NEWLINE_ANY | PCRE_UTF8, 0, ".\\Z", "aaa\xc2\x85" }, - { PCRE_NEWLINE_ANY | PCRE_UTF8, 0, ".\\Z", "aaa\xe2\x80\xa8" }, - { MA, 0, "\\Aa", "aaa" }, - { MA, 1 | F_NOMATCH, "\\Aa", "aaa" }, - { MA, 1, "\\Ga", "aaa" }, - { MA, 1 | F_NOMATCH, "\\Ga", "aba" }, - { MA, 0, "a\\z", "aaa" }, - { MA, 0 | F_NOMATCH, "a\\z", "aab" }, - - /* Brackets. */ - { MUA, 0, "(ab|bb|cd)", "bacde" }, - { MUA, 0, "(?:ab|a)(bc|c)", "ababc" }, - { MUA, 0, "((ab|(cc))|(bb)|(?:cd|efg))", "abac" }, - { CMUA, 0, "((aB|(Cc))|(bB)|(?:cd|EFg))", "AcCe" }, - { MUA, 0, "((ab|(cc))|(bb)|(?:cd|ebg))", "acebebg" }, - { MUA, 0, "(?:(a)|(?:b))(cc|(?:d|e))(a|b)k", "accabdbbccbk" }, - - /* Greedy and non-greedy ? operators. */ - { MUA, 0, "(?:a)?a", "laab" }, - { CMUA, 0, "(A)?A", "llaab" }, - { MUA, 0, "(a)?\?a", "aab" }, /* ?? is the prefix of trygraphs in GCC. */ - { MUA, 0, "(a)?a", "manm" }, - { CMUA, 0, "(a|b)?\?d((?:e)?)", "ABABdx" }, - { MUA, 0, "(a|b)?\?d((?:e)?)", "abcde" }, - { MUA, 0, "((?:ab)?\?g|b(?:g(nn|d)?\?)?)?\?(?:n)?m", "abgnbgnnbgdnmm" }, - - /* Greedy and non-greedy + operators */ - { MUA, 0, "(aa)+aa", "aaaaaaa" }, - { MUA, 0, "(aa)+?aa", "aaaaaaa" }, - { MUA, 0, "(?:aba|ab|a)+l", "ababamababal" }, - { MUA, 0, "(?:aba|ab|a)+?l", "ababamababal" }, - { MUA, 0, "(a(?:bc|cb|b|c)+?|ss)+e", "accssabccbcacbccbbXaccssabccbcacbccbbe" }, - { MUA, 0, "(a(?:bc|cb|b|c)+|ss)+?e", "accssabccbcacbccbbXaccssabccbcacbccbbe" }, - { MUA, 0, "(?:(b(c)+?)+)?\?(?:(bc)+|(cb)+)+(?:m)+", "bccbcccbcbccbcbPbccbcccbcbccbcbmmn" }, - - /* Greedy and non-greedy * operators */ - { CMUA, 0, "(?:AA)*AB", "aaaaaaamaaaaaaab" }, - { MUA, 0, "(?:aa)*?ab", "aaaaaaamaaaaaaab" }, - { MUA, 0, "(aa|ab)*ab", "aaabaaab" }, - { CMUA, 0, "(aa|Ab)*?aB", "aaabaaab" }, - { MUA, 0, "(a|b)*(?:a)*(?:b)*m", "abbbaaababanabbbaaababamm" }, - { MUA, 0, "(a|b)*?(?:a)*?(?:b)*?m", "abbbaaababanabbbaaababamm" }, - { MA, 0, "a(a(\\1*)a|(b)b+){0}a", "aa" }, - { MA, 0, "((?:a|)*){0}a", "a" }, - - /* Combining ? + * operators */ - { MUA, 0, "((bm)+)?\?(?:a)*(bm)+n|((am)+?)?(?:a)+(am)*n", "bmbmabmamaaamambmaman" }, - { MUA, 0, "(((ab)?cd)*ef)+g", "abcdcdefcdefefmabcdcdefcdefefgg" }, - { MUA, 0, "(((ab)?\?cd)*?ef)+?g", "abcdcdefcdefefmabcdcdefcdefefgg" }, - { MUA, 0, "(?:(ab)?c|(?:ab)+?d)*g", "ababcdccababddg" }, - { MUA, 0, "(?:(?:ab)?\?c|(ab)+d)*?g", "ababcdccababddg" }, - - /* Single character iterators. */ - { MUA, 0, "(a+aab)+aaaab", "aaaabcaaaabaabcaabcaaabaaaab" }, - { MUA, 0, "(a*a*aab)+x", "aaaaabaabaaabmaabx" }, - { MUA, 0, "(a*?(b|ab)a*?)+x", "aaaabcxbbaabaacbaaabaabax" }, - { MUA, 0, "(a+(ab|ad)a+)+x", "aaabaaaadaabaaabaaaadaaax" }, - { MUA, 0, "(a?(a)a?)+(aaa)", "abaaabaaaaaaaa" }, - { MUA, 0, "(a?\?(a)a?\?)+(b)", "aaaacaaacaacacbaaab" }, - { MUA, 0, "(a{0,4}(b))+d", "aaaaaabaabcaaaaabaaaaabd" }, - { MUA, 0, "(a{0,4}?[^b])+d+(a{0,4}[^b])d+", "aaaaadaaaacaadddaaddd" }, - { MUA, 0, "(ba{2})+c", "baabaaabacbaabaac" }, - { MUA, 0, "(a*+bc++)+", "aaabbcaaabcccab" }, - { MUA, 0, "(a?+[^b])+", "babaacacb" }, - { MUA, 0, "(a{0,3}+b)(a{0,3}+b)(a{0,3}+)[^c]", "abaabaaacbaabaaaac" }, - { CMUA, 0, "([a-c]+[d-f]+?)+?g", "aBdacdehAbDaFgA" }, - { CMUA, 0, "[c-f]+k", "DemmFke" }, - { MUA, 0, "([DGH]{0,4}M)+", "GGDGHDGMMHMDHHGHM" }, - { MUA, 0, "([a-c]{4,}s)+", "abasabbasbbaabsbba" }, - { CMUA, 0, "[ace]{3,7}", "AcbDAcEEcEd" }, - { CMUA, 0, "[ace]{3,7}?", "AcbDAcEEcEd" }, - { CMUA, 0, "[ace]{3,}", "AcbDAcEEcEd" }, - { CMUA, 0, "[ace]{3,}?", "AcbDAcEEcEd" }, - { MUA, 0, "[ckl]{2,}?g", "cdkkmlglglkcg" }, - { CMUA, 0, "[ace]{5}?", "AcCebDAcEEcEd" }, - { MUA, 0, "([AbC]{3,5}?d)+", "BACaAbbAEAACCbdCCbdCCAAbb" }, - { MUA, 0, "([^ab]{0,}s){2}", "abaabcdsABamsDDs" }, - { MUA, 0, "\\b\\w+\\B", "x,a_cd" }, - { MUAP, 0, "\\b[^\xc2\xa1]+\\B", "\xc3\x89\xc2\xa1\xe6\x92\xad\xc3\x81\xc3\xa1" }, - { CMUA, 0, "[^b]+(a*)([^c]?d{3})", "aaaaddd" }, - { CMUAP, 0, "\xe1\xbd\xb8{2}", "\xe1\xbf\xb8#\xe1\xbf\xb8\xe1\xbd\xb8" }, - { CMUA, 0, "[^\xf0\x90\x90\x80]{2,4}@", "\xf0\x90\x90\xa8\xf0\x90\x90\x80###\xf0\x90\x90\x80@@@" }, - { CMUA, 0, "[^\xe1\xbd\xb8][^\xc3\xa9]", "\xe1\xbd\xb8\xe1\xbf\xb8\xc3\xa9\xc3\x89#" }, - { MUA, 0, "[^\xe1\xbd\xb8][^\xc3\xa9]", "\xe1\xbd\xb8\xe1\xbf\xb8\xc3\xa9\xc3\x89#" }, - { MUA, 0, "[^\xe1\xbd\xb8]{3,}?", "##\xe1\xbd\xb8#\xe1\xbd\xb8#\xc3\x89#\xe1\xbd\xb8" }, - - /* Bracket repeats with limit. */ - { MUA, 0, "(?:(ab){2}){5}M", "abababababababababababM" }, - { MUA, 0, "(?:ab|abab){1,5}M", "abababababababababababM" }, - { MUA, 0, "(?>ab|abab){1,5}M", "abababababababababababM" }, - { MUA, 0, "(?:ab|abab){1,5}?M", "abababababababababababM" }, - { MUA, 0, "(?>ab|abab){1,5}?M", "abababababababababababM" }, - { MUA, 0, "(?:(ab){1,4}?){1,3}?M", "abababababababababababababM" }, - { MUA, 0, "(?:(ab){1,4}){1,3}abababababababababababM", "ababababababababababababM" }, - { MUA, 0 | F_NOMATCH, "(?:(ab){1,4}){1,3}abababababababababababM", "abababababababababababM" }, - { MUA, 0, "(ab){4,6}?M", "abababababababM" }, - - /* Basic character sets. */ - { MUA, 0, "(?:\\s)+(?:\\S)+", "ab \t\xc3\xa9\xe6\x92\xad " }, - { MUA, 0, "(\\w)*(k)(\\W)?\?", "abcdef abck11" }, - { MUA, 0, "\\((\\d)+\\)\\D", "a() (83 (8)2 (9)ab" }, - { MUA, 0, "\\w(\\s|(?:\\d)*,)+\\w\\wb", "a 5, 4,, bb 5, 4,, aab" }, - { MUA, 0, "(\\v+)(\\V+)", "\x0e\xc2\x85\xe2\x80\xa8\x0b\x09\xe2\x80\xa9" }, - { MUA, 0, "(\\h+)(\\H+)", "\xe2\x80\xa8\xe2\x80\x80\x20\xe2\x80\x8a\xe2\x81\x9f\xe3\x80\x80\x09\x20\xc2\xa0\x0a" }, - { MUA, 0, "x[bcef]+", "xaxdxecbfg" }, - { MUA, 0, "x[bcdghij]+", "xaxexfxdgbjk" }, - { MUA, 0, "x[^befg]+", "xbxexacdhg" }, - { MUA, 0, "x[^bcdl]+", "xlxbxaekmd" }, - { MUA, 0, "x[^bcdghi]+", "xbxdxgxaefji" }, - { MUA, 0, "x[B-Fb-f]+", "xaxAxgxbfBFG" }, - { CMUA, 0, "\\x{e9}+", "#\xf0\x90\x90\xa8\xc3\xa8\xc3\xa9\xc3\x89\xc3\x88" }, - { CMUA, 0, "[^\\x{e9}]+", "\xc3\xa9#\xf0\x90\x90\xa8\xc3\xa8\xc3\x88\xc3\x89" }, - { MUA, 0, "[\\x02\\x7e]+", "\xc3\x81\xe1\xbf\xb8\xf0\x90\x90\xa8\x01\x02\x7e\x7f" }, - { MUA, 0, "[^\\x02\\x7e]+", "\x02\xc3\x81\xe1\xbf\xb8\xf0\x90\x90\xa8\x01\x7f\x7e" }, - { MUA, 0, "[\\x{81}-\\x{7fe}]+", "#\xe1\xbf\xb8\xf0\x90\x90\xa8\xc2\x80\xc2\x81\xdf\xbe\xdf\xbf" }, - { MUA, 0, "[^\\x{81}-\\x{7fe}]+", "\xc2\x81#\xe1\xbf\xb8\xf0\x90\x90\xa8\xc2\x80\xdf\xbf\xdf\xbe" }, - { MUA, 0, "[\\x{801}-\\x{fffe}]+", "#\xc3\xa9\xf0\x90\x90\x80\xe0\xa0\x80\xe0\xa0\x81\xef\xbf\xbe\xef\xbf\xbf" }, - { MUA, 0, "[^\\x{801}-\\x{fffe}]+", "\xe0\xa0\x81#\xc3\xa9\xf0\x90\x90\x80\xe0\xa0\x80\xef\xbf\xbf\xef\xbf\xbe" }, - { MUA, 0, "[\\x{10001}-\\x{10fffe}]+", "#\xc3\xa9\xe2\xb1\xa5\xf0\x90\x80\x80\xf0\x90\x80\x81\xf4\x8f\xbf\xbe\xf4\x8f\xbf\xbf" }, - { MUA, 0, "[^\\x{10001}-\\x{10fffe}]+", "\xf0\x90\x80\x81#\xc3\xa9\xe2\xb1\xa5\xf0\x90\x80\x80\xf4\x8f\xbf\xbf\xf4\x8f\xbf\xbe" }, - - /* Unicode properties. */ - { MUAP, 0, "[1-5\xc3\xa9\\w]", "\xc3\xa1_" }, - { MUAP, 0 | F_PROPERTY, "[\xc3\x81\\p{Ll}]", "A_\xc3\x89\xc3\xa1" }, - { MUAP, 0, "[\\Wd-h_x-z]+", "a\xc2\xa1#_yhzdxi" }, - { MUAP, 0 | F_NOMATCH | F_PROPERTY, "[\\P{Any}]", "abc" }, - { MUAP, 0 | F_NOMATCH | F_PROPERTY, "[^\\p{Any}]", "abc" }, - { MUAP, 0 | F_NOMATCH | F_PROPERTY, "[\\P{Any}\xc3\xa1-\xc3\xa8]", "abc" }, - { MUAP, 0 | F_NOMATCH | F_PROPERTY, "[^\\p{Any}\xc3\xa1-\xc3\xa8]", "abc" }, - { MUAP, 0 | F_NOMATCH | F_PROPERTY, "[\xc3\xa1-\xc3\xa8\\P{Any}]", "abc" }, - { MUAP, 0 | F_NOMATCH | F_PROPERTY, "[^\xc3\xa1-\xc3\xa8\\p{Any}]", "abc" }, - { MUAP, 0 | F_PROPERTY, "[\xc3\xa1-\xc3\xa8\\p{Any}]", "abc" }, - { MUAP, 0 | F_PROPERTY, "[^\xc3\xa1-\xc3\xa8\\P{Any}]", "abc" }, - { MUAP, 0, "[b-\xc3\xa9\\s]", "a\xc\xe6\x92\xad" }, - { CMUAP, 0, "[\xc2\x85-\xc2\x89\xc3\x89]", "\xc2\x84\xc3\xa9" }, - { MUAP, 0, "[^b-d^&\\s]{3,}", "db^ !a\xe2\x80\xa8_ae" }, - { MUAP, 0 | F_PROPERTY, "[^\\S\\P{Any}][\\sN]{1,3}[\\P{N}]{4}", "\xe2\x80\xaa\xa N\x9\xc3\xa9_0" }, - { MUA, 0 | F_PROPERTY, "[^\\P{L}\x9!D-F\xa]{2,3}", "\x9,.DF\xa.CG\xc3\x81" }, - { CMUAP, 0, "[\xc3\xa1-\xc3\xa9_\xe2\x80\xa0-\xe2\x80\xaf]{1,5}[^\xe2\x80\xa0-\xe2\x80\xaf]", "\xc2\xa1\xc3\x89\xc3\x89\xe2\x80\xaf_\xe2\x80\xa0" }, - { MUAP, 0 | F_PROPERTY, "[\xc3\xa2-\xc3\xa6\xc3\x81-\xc3\x84\xe2\x80\xa8-\xe2\x80\xa9\xe6\x92\xad\\p{Zs}]{2,}", "\xe2\x80\xa7\xe2\x80\xa9\xe6\x92\xad \xe6\x92\xae" }, - { MUAP, 0 | F_PROPERTY, "[\\P{L&}]{2}[^\xc2\x85-\xc2\x89\\p{Ll}\\p{Lu}]{2}", "\xc3\xa9\xe6\x92\xad.a\xe6\x92\xad|\xc2\x8a#" }, - { PCRE_UCP, 0, "[a-b\\s]{2,5}[^a]", "AB baaa" }, - - /* Possible empty brackets. */ - { MUA, 0, "(?:|ab||bc|a)+d", "abcxabcabd" }, - { MUA, 0, "(|ab||bc|a)+d", "abcxabcabd" }, - { MUA, 0, "(?:|ab||bc|a)*d", "abcxabcabd" }, - { MUA, 0, "(|ab||bc|a)*d", "abcxabcabd" }, - { MUA, 0, "(?:|ab||bc|a)+?d", "abcxabcabd" }, - { MUA, 0, "(|ab||bc|a)+?d", "abcxabcabd" }, - { MUA, 0, "(?:|ab||bc|a)*?d", "abcxabcabd" }, - { MUA, 0, "(|ab||bc|a)*?d", "abcxabcabd" }, - { MUA, 0, "(((a)*?|(?:ba)+)+?|(?:|c|ca)*)*m", "abaacaccabacabalabaacaccabacabamm" }, - { MUA, 0, "(?:((?:a)*|(ba)+?)+|(|c|ca)*?)*?m", "abaacaccabacabalabaacaccabacabamm" }, - - /* Start offset. */ - { MUA, 3, "(\\d|(?:\\w)*\\w)+", "0ac01Hb" }, - { MUA, 4 | F_NOMATCH, "(\\w\\W\\w)+", "ab#d" }, - { MUA, 2 | F_NOMATCH, "(\\w\\W\\w)+", "ab#d" }, - { MUA, 1, "(\\w\\W\\w)+", "ab#d" }, - - /* Newline. */ - { PCRE_MULTILINE | PCRE_NEWLINE_CRLF, 0, "\\W{0,2}[^#]{3}", "\r\n#....." }, - { PCRE_MULTILINE | PCRE_NEWLINE_CR, 0, "\\W{0,2}[^#]{3}", "\r\n#....." }, - { PCRE_MULTILINE | PCRE_NEWLINE_CRLF, 0, "\\W{1,3}[^#]", "\r\n##...." }, - { MUA | PCRE_NO_UTF8_CHECK, 1, "^.a", "\n\x80\nxa" }, - { MUA, 1, "^", "\r\n" }, - { PCRE_MULTILINE | PCRE_NEWLINE_CRLF, 1 | F_NOMATCH, "^", "\r\n" }, - { PCRE_MULTILINE | PCRE_NEWLINE_CRLF, 1, "^", "\r\na" }, - - /* Any character except newline or any newline. */ - { PCRE_NEWLINE_CRLF, 0, ".", "\r" }, - { PCRE_NEWLINE_CRLF | PCRE_UTF8, 0, ".(.).", "a\xc3\xa1\r\n\n\r\r" }, - { PCRE_NEWLINE_ANYCRLF, 0, ".(.)", "a\rb\nc\r\n\xc2\x85\xe2\x80\xa8" }, - { PCRE_NEWLINE_ANYCRLF | PCRE_UTF8, 0, ".(.)", "a\rb\nc\r\n\xc2\x85\xe2\x80\xa8" }, - { PCRE_NEWLINE_ANY | PCRE_UTF8, 0, "(.).", "a\rb\nc\r\n\xc2\x85\xe2\x80\xa9$de" }, - { PCRE_NEWLINE_ANYCRLF | PCRE_UTF8, 0 | F_NOMATCH, ".(.).", "\xe2\x80\xa8\nb\r" }, - { PCRE_NEWLINE_ANY, 0, "(.)(.)", "#\x85#\r#\n#\r\n#\x84" }, - { PCRE_NEWLINE_ANY | PCRE_UTF8, 0, "(.+)#", "#\rMn\xc2\x85#\n###" }, - { PCRE_BSR_ANYCRLF, 0, "\\R", "\r" }, - { PCRE_BSR_ANYCRLF, 0, "\\R", "\x85#\r\n#" }, - { PCRE_BSR_UNICODE | PCRE_UTF8, 0, "\\R", "ab\xe2\x80\xa8#c" }, - { PCRE_BSR_UNICODE | PCRE_UTF8, 0, "\\R", "ab\r\nc" }, - { PCRE_NEWLINE_CRLF | PCRE_BSR_UNICODE | PCRE_UTF8, 0, "(\\R.)+", "\xc2\x85\r\n#\xe2\x80\xa8\n\r\n\r" }, - { MUA, 0 | F_NOMATCH, "\\R+", "ab" }, - { MUA, 0, "\\R+", "ab\r\n\r" }, - { MUA, 0, "\\R*", "ab\r\n\r" }, - { MUA, 0, "\\R*", "\r\n\r" }, - { MUA, 0, "\\R{2,4}", "\r\nab\r\r" }, - { MUA, 0, "\\R{2,4}", "\r\nab\n\n\n\r\r\r" }, - { MUA, 0, "\\R{2,}", "\r\nab\n\n\n\r\r\r" }, - { MUA, 0, "\\R{0,3}", "\r\n\r\n\r\n\r\n\r\n" }, - { MUA, 0 | F_NOMATCH, "\\R+\\R\\R", "\r\n\r\n" }, - { MUA, 0, "\\R+\\R\\R", "\r\r\r" }, - { MUA, 0, "\\R*\\R\\R", "\n\r" }, - { MUA, 0 | F_NOMATCH, "\\R{2,4}\\R\\R", "\r\r\r" }, - { MUA, 0, "\\R{2,4}\\R\\R", "\r\r\r\r" }, - - /* Atomic groups (no fallback from "next" direction). */ - { MUA, 0 | F_NOMATCH, "(?>ab)ab", "bab" }, - { MUA, 0 | F_NOMATCH, "(?>(ab))ab", "bab" }, - { MUA, 0, "(?>ab)+abc(?>de)*def(?>gh)?ghe(?>ij)+?k(?>lm)*?n(?>op)?\?op", - "bababcdedefgheijijklmlmnop" }, - { MUA, 0, "(?>a(b)+a|(ab)?\?(b))an", "abban" }, - { MUA, 0, "(?>ab+a|(?:ab)?\?b)an", "abban" }, - { MUA, 0, "((?>ab|ad|)*?)(?>|c)*abad", "abababcababad" }, - { MUA, 0, "(?>(aa|b|)*+(?>(##)|###)*d|(aa)(?>(baa)?)m)", "aabaa#####da" }, - { MUA, 0, "((?>a|)+?)b", "aaacaaab" }, - { MUA, 0, "(?>x|)*$", "aaa" }, - { MUA, 0, "(?>(x)|)*$", "aaa" }, - { MUA, 0, "(?>x|())*$", "aaa" }, - { MUA, 0, "((?>[cxy]a|[a-d])*?)b", "aaa+ aaab" }, - { MUA, 0, "((?>[cxy](a)|[a-d])*?)b", "aaa+ aaab" }, - { MUA, 0, "(?>((?>(a+))))bab|(?>((?>(a+))))bb", "aaaabaaabaabab" }, - { MUA, 0, "(?>(?>a+))bab|(?>(?>a+))bb", "aaaabaaabaabab" }, - { MUA, 0, "(?>(a)c|(?>(c)|(a))a)b*?bab", "aaaabaaabaabab" }, - { MUA, 0, "(?>ac|(?>c|a)a)b*?bab", "aaaabaaabaabab" }, - { MUA, 0, "(?>(b)b|(a))*b(?>(c)|d)?x", "ababcaaabdbx" }, - { MUA, 0, "(?>bb|a)*b(?>c|d)?x", "ababcaaabdbx" }, - { MUA, 0, "(?>(bb)|a)*b(?>c|(d))?x", "ababcaaabdbx" }, - { MUA, 0, "(?>(a))*?(?>(a))+?(?>(a))??x", "aaaaaacccaaaaabax" }, - { MUA, 0, "(?>a)*?(?>a)+?(?>a)??x", "aaaaaacccaaaaabax" }, - { MUA, 0, "(?>(a)|)*?(?>(a)|)+?(?>(a)|)??x", "aaaaaacccaaaaabax" }, - { MUA, 0, "(?>a|)*?(?>a|)+?(?>a|)??x", "aaaaaacccaaaaabax" }, - { MUA, 0, "(?>a(?>(a{0,2}))*?b|aac)+b", "aaaaaaacaaaabaaaaacaaaabaacaaabb" }, - { CMA, 0, "(?>((?>a{32}|b+|(a*))?(?>c+|d*)?\?)+e)+?f", "aaccebbdde bbdaaaccebbdee bbdaaaccebbdeef" }, - { MUA, 0, "(?>(?:(?>aa|a||x)+?b|(?>aa|a||(x))+?c)?(?>[ad]{0,2})*?d)+d", "aaacdbaabdcabdbaaacd aacaabdbdcdcaaaadaabcbaadd" }, - { MUA, 0, "(?>(?:(?>aa|a||(x))+?b|(?>aa|a||x)+?c)?(?>[ad]{0,2})*?d)+d", "aaacdbaabdcabdbaaacd aacaabdbdcdcaaaadaabcbaadd" }, - { MUA, 0 | F_PROPERTY, "\\X", "\xcc\x8d\xcc\x8d" }, - { MUA, 0 | F_PROPERTY, "\\X", "\xcc\x8d\xcc\x8d#\xcc\x8d\xcc\x8d" }, - { MUA, 0 | F_PROPERTY, "\\X+..", "\xcc\x8d#\xcc\x8d#\xcc\x8d\xcc\x8d" }, - { MUA, 0 | F_PROPERTY, "\\X{2,4}", "abcdef" }, - { MUA, 0 | F_PROPERTY, "\\X{2,4}?", "abcdef" }, - { MUA, 0 | F_NOMATCH | F_PROPERTY, "\\X{2,4}..", "#\xcc\x8d##" }, - { MUA, 0 | F_PROPERTY, "\\X{2,4}..", "#\xcc\x8d#\xcc\x8d##" }, - { MUA, 0, "(c(ab)?+ab)+", "cabcababcab" }, - { MUA, 0, "(?>(a+)b)+aabab", "aaaabaaabaabab" }, - - /* Possessive quantifiers. */ - { MUA, 0, "(?:a|b)++m", "mababbaaxababbaam" }, - { MUA, 0, "(?:a|b)*+m", "mababbaaxababbaam" }, - { MUA, 0, "(?:a|b)*+m", "ababbaaxababbaam" }, - { MUA, 0, "(a|b)++m", "mababbaaxababbaam" }, - { MUA, 0, "(a|b)*+m", "mababbaaxababbaam" }, - { MUA, 0, "(a|b)*+m", "ababbaaxababbaam" }, - { MUA, 0, "(a|b(*ACCEPT))++m", "maaxab" }, - { MUA, 0, "(?:b*)++m", "bxbbxbbbxm" }, - { MUA, 0, "(?:b*)++m", "bxbbxbbbxbbm" }, - { MUA, 0, "(?:b*)*+m", "bxbbxbbbxm" }, - { MUA, 0, "(?:b*)*+m", "bxbbxbbbxbbm" }, - { MUA, 0, "(b*)++m", "bxbbxbbbxm" }, - { MUA, 0, "(b*)++m", "bxbbxbbbxbbm" }, - { MUA, 0, "(b*)*+m", "bxbbxbbbxm" }, - { MUA, 0, "(b*)*+m", "bxbbxbbbxbbm" }, - { MUA, 0, "(?:a|(b))++m", "mababbaaxababbaam" }, - { MUA, 0, "(?:(a)|b)*+m", "mababbaaxababbaam" }, - { MUA, 0, "(?:(a)|(b))*+m", "ababbaaxababbaam" }, - { MUA, 0, "(a|(b))++m", "mababbaaxababbaam" }, - { MUA, 0, "((a)|b)*+m", "mababbaaxababbaam" }, - { MUA, 0, "((a)|(b))*+m", "ababbaaxababbaam" }, - { MUA, 0, "(a|(b)(*ACCEPT))++m", "maaxab" }, - { MUA, 0, "(?:(b*))++m", "bxbbxbbbxm" }, - { MUA, 0, "(?:(b*))++m", "bxbbxbbbxbbm" }, - { MUA, 0, "(?:(b*))*+m", "bxbbxbbbxm" }, - { MUA, 0, "(?:(b*))*+m", "bxbbxbbbxbbm" }, - { MUA, 0, "((b*))++m", "bxbbxbbbxm" }, - { MUA, 0, "((b*))++m", "bxbbxbbbxbbm" }, - { MUA, 0, "((b*))*+m", "bxbbxbbbxm" }, - { MUA, 0, "((b*))*+m", "bxbbxbbbxbbm" }, - { MUA, 0 | F_NOMATCH, "(?>(b{2,4}))(?:(?:(aa|c))++m|(?:(aa|c))+n)", "bbaacaaccaaaacxbbbmbn" }, - { MUA, 0, "((?:b)++a)+(cd)*+m", "bbababbacdcdnbbababbacdcdm" }, - { MUA, 0, "((?:(b))++a)+((c)d)*+m", "bbababbacdcdnbbababbacdcdm" }, - { MUA, 0, "(?:(?:(?:ab)*+k)++(?:n(?:cd)++)*+)*+m", "ababkkXababkkabkncXababkkabkncdcdncdXababkkabkncdcdncdkkabkncdXababkkabkncdcdncdkkabkncdm" }, - { MUA, 0, "(?:((ab)*+(k))++(n(?:c(d))++)*+)*+m", "ababkkXababkkabkncXababkkabkncdcdncdXababkkabkncdcdncdkkabkncdXababkkabkncdcdncdkkabkncdm" }, - - /* Back references. */ - { MUA, 0, "(aa|bb)(\\1*)(ll|)(\\3*)bbbbbbc", "aaaaaabbbbbbbbc" }, - { CMUA, 0, "(aa|bb)(\\1+)(ll|)(\\3+)bbbbbbc", "bBbbBbCbBbbbBbbcbbBbbbBBbbC" }, - { CMA, 0, "(a{2,4})\\1", "AaAaaAaA" }, - { MUA, 0, "(aa|bb)(\\1?)aa(\\1?)(ll|)(\\4+)bbc", "aaaaaaaabbaabbbbaabbbbc" }, - { MUA, 0, "(aa|bb)(\\1{0,5})(ll|)(\\3{0,5})cc", "bbxxbbbbxxaaaaaaaaaaaaaaaacc" }, - { MUA, 0, "(aa|bb)(\\1{3,5})(ll|)(\\3{3,5})cc", "bbbbbbbbbbbbaaaaaaccbbbbbbbbbbbbbbcc" }, - { MUA, 0, "(aa|bb)(\\1{3,})(ll|)(\\3{3,})cc", "bbbbbbbbbbbbaaaaaaccbbbbbbbbbbbbbbcc" }, - { MUA, 0, "(\\w+)b(\\1+)c", "GabGaGaDbGaDGaDc" }, - { MUA, 0, "(?:(aa)|b)\\1?b", "bb" }, - { CMUA, 0, "(aa|bb)(\\1*?)aa(\\1+?)", "bBBbaaAAaaAAaa" }, - { MUA, 0, "(aa|bb)(\\1*?)(dd|)cc(\\3+?)", "aaaaaccdd" }, - { CMUA, 0, "(?:(aa|bb)(\\1?\?)cc){2}(\\1?\?)", "aAaABBbbAAaAcCaAcCaA" }, - { MUA, 0, "(?:(aa|bb)(\\1{3,5}?)){2}(dd|)(\\3{3,5}?)", "aaaaaabbbbbbbbbbaaaaaaaaaaaaaa" }, - { CMA, 0, "(?:(aa|bb)(\\1{3,}?)){2}(dd|)(\\3{3,}?)", "aaaaaabbbbbbbbbbaaaaaaaaaaaaaa" }, - { MUA, 0, "(?:(aa|bb)(\\1{0,3}?)){2}(dd|)(\\3{0,3}?)b(\\1{0,3}?)(\\1{0,3})", "aaaaaaaaaaaaaaabaaaaa" }, - { MUA, 0, "(a(?:\\1|)a){3}b", "aaaaaaaaaaab" }, - { MA, 0, "(a?)b(\\1\\1*\\1+\\1?\\1*?\\1+?\\1??\\1*+\\1++\\1?+\\1{4}\\1{3,5}\\1{4,}\\1{0,5}\\1{3,5}?\\1{4,}?\\1{0,5}?\\1{3,5}+\\1{4,}+\\1{0,5}+#){2}d", "bb#b##d" }, - { MUAP, 0 | F_PROPERTY, "(\\P{N})\\1{2,}", ".www." }, - { MUAP, 0 | F_PROPERTY, "(\\P{N})\\1{0,2}", "wwwww." }, - { MUAP, 0 | F_PROPERTY, "(\\P{N})\\1{1,2}ww", "wwww" }, - { MUAP, 0 | F_PROPERTY, "(\\P{N})\\1{1,2}ww", "wwwww" }, - { PCRE_UCP, 0 | F_PROPERTY, "(\\P{N})\\1{2,}", ".www." }, - { CMUAP, 0, "(\xf0\x90\x90\x80)\\1", "\xf0\x90\x90\xa8\xf0\x90\x90\xa8" }, - { MUA | PCRE_DUPNAMES, 0 | F_NOMATCH, "\\k<A>{1,3}(?<A>aa)(?<A>bb)", "aabb" }, - { MUA | PCRE_DUPNAMES | PCRE_JAVASCRIPT_COMPAT, 0, "\\k<A>{1,3}(?<A>aa)(?<A>bb)", "aabb" }, - { MUA | PCRE_DUPNAMES | PCRE_JAVASCRIPT_COMPAT, 0, "\\k<A>*(?<A>aa)(?<A>bb)", "aabb" }, - { MUA | PCRE_DUPNAMES, 0, "(?<A>aa)(?<A>bb)\\k<A>{0,3}aaaaaa", "aabbaaaaaa" }, - { MUA | PCRE_DUPNAMES, 0, "(?<A>aa)(?<A>bb)\\k<A>{2,5}bb", "aabbaaaabb" }, - { MUA | PCRE_DUPNAMES, 0, "(?:(?<A>aa)|(?<A>bb))\\k<A>{0,3}m", "aaaaaaaabbbbaabbbbm" }, - { MUA | PCRE_DUPNAMES, 0 | F_NOMATCH, "\\k<A>{1,3}?(?<A>aa)(?<A>bb)", "aabb" }, - { MUA | PCRE_DUPNAMES | PCRE_JAVASCRIPT_COMPAT, 0, "\\k<A>{1,3}?(?<A>aa)(?<A>bb)", "aabb" }, - { MUA | PCRE_DUPNAMES, 0, "\\k<A>*?(?<A>aa)(?<A>bb)", "aabb" }, - { MUA | PCRE_DUPNAMES, 0, "(?:(?<A>aa)|(?<A>bb))\\k<A>{0,3}?m", "aaaaaabbbbbbaabbbbbbbbbbm" }, - { MUA | PCRE_DUPNAMES, 0, "(?:(?<A>aa)|(?<A>bb))\\k<A>*?m", "aaaaaabbbbbbaabbbbbbbbbbm" }, - { MUA | PCRE_DUPNAMES, 0, "(?:(?<A>aa)|(?<A>bb))\\k<A>{2,3}?", "aaaabbbbaaaabbbbbbbbbb" }, - { CMUA | PCRE_DUPNAMES, 0, "(?:(?<A>AA)|(?<A>BB))\\k<A>{0,3}M", "aaaaaaaabbbbaabbbbm" }, - { CMUA | PCRE_DUPNAMES, 0, "(?:(?<A>AA)|(?<A>BB))\\k<A>{1,3}M", "aaaaaaaabbbbaabbbbm" }, - { CMUA | PCRE_DUPNAMES, 0, "(?:(?<A>AA)|(?<A>BB))\\k<A>{0,3}?M", "aaaaaabbbbbbaabbbbbbbbbbm" }, - { CMUA | PCRE_DUPNAMES, 0, "(?:(?<A>AA)|(?<A>BB))\\k<A>{2,3}?", "aaaabbbbaaaabbbbbbbbbb" }, - - /* Assertions. */ - { MUA, 0, "(?=xx|yy|zz)\\w{4}", "abczzdefg" }, - { MUA, 0, "(?=((\\w+)b){3}|ab)", "dbbbb ab" }, - { MUA, 0, "(?!ab|bc|cd)[a-z]{2}", "Xabcdef" }, - { MUA, 0, "(?<=aaa|aa|a)a", "aaa" }, - { MUA, 2, "(?<=aaa|aa|a)a", "aaa" }, - { MA, 0, "(?<=aaa|aa|a)a", "aaa" }, - { MA, 2, "(?<=aaa|aa|a)a", "aaa" }, - { MUA, 0, "(\\d{2})(?!\\w+c|(((\\w?)m){2}n)+|\\1)", "x5656" }, - { MUA, 0, "((?=((\\d{2,6}\\w){2,}))\\w{5,20}K){2,}", "567v09708K12l00M00 567v09708K12l00M00K45K" }, - { MUA, 0, "(?=(?:(?=\\S+a)\\w*(b)){3})\\w+\\d", "bba bbab nbbkba nbbkba0kl" }, - { MUA, 0, "(?>a(?>(b+))a(?=(..)))*?k", "acabbcabbaabacabaabbakk" }, - { MUA, 0, "((?(?=(a))a)+k)", "bbak" }, - { MUA, 0, "((?(?=a)a)+k)", "bbak" }, - { MUA, 0 | F_NOMATCH, "(?=(?>(a))m)amk", "a k" }, - { MUA, 0 | F_NOMATCH, "(?!(?>(a))m)amk", "a k" }, - { MUA, 0 | F_NOMATCH, "(?>(?=(a))am)amk", "a k" }, - { MUA, 0, "(?=(?>a|(?=(?>(b+))a|c)[a-c]+)*?m)[a-cm]+k", "aaam bbam baaambaam abbabba baaambaamk" }, - { MUA, 0, "(?> ?\?\\b(?(?=\\w{1,4}(a))m)\\w{0,8}bc){2,}?", "bca ssbc mabd ssbc mabc" }, - { MUA, 0, "(?:(?=ab)?[^n][^n])+m", "ababcdabcdcdabnababcdabcdcdabm" }, - { MUA, 0, "(?:(?=a(b))?[^n][^n])+m", "ababcdabcdcdabnababcdabcdcdabm" }, - { MUA, 0, "(?:(?=.(.))??\\1.)+m", "aabbbcbacccanaabbbcbacccam" }, - { MUA, 0, "(?:(?=.)??[a-c])+m", "abacdcbacacdcaccam" }, - { MUA, 0, "((?!a)?(?!([^a]))?)+$", "acbab" }, - { MUA, 0, "((?!a)?\?(?!([^a]))?\?)+$", "acbab" }, - - /* Not empty, ACCEPT, FAIL */ - { MUA | PCRE_NOTEMPTY, 0 | F_NOMATCH, "a*", "bcx" }, - { MUA | PCRE_NOTEMPTY, 0, "a*", "bcaad" }, - { MUA | PCRE_NOTEMPTY, 0, "a*?", "bcaad" }, - { MUA | PCRE_NOTEMPTY_ATSTART, 0, "a*", "bcaad" }, - { MUA, 0, "a(*ACCEPT)b", "ab" }, - { MUA | PCRE_NOTEMPTY, 0 | F_NOMATCH, "a*(*ACCEPT)b", "bcx" }, - { MUA | PCRE_NOTEMPTY, 0, "a*(*ACCEPT)b", "bcaad" }, - { MUA | PCRE_NOTEMPTY, 0, "a*?(*ACCEPT)b", "bcaad" }, - { MUA | PCRE_NOTEMPTY, 0 | F_NOMATCH, "(?:z|a*(*ACCEPT)b)", "bcx" }, - { MUA | PCRE_NOTEMPTY, 0, "(?:z|a*(*ACCEPT)b)", "bcaad" }, - { MUA | PCRE_NOTEMPTY, 0, "(?:z|a*?(*ACCEPT)b)", "bcaad" }, - { MUA | PCRE_NOTEMPTY_ATSTART, 0, "a*(*ACCEPT)b", "bcx" }, - { MUA | PCRE_NOTEMPTY_ATSTART, 0 | F_NOMATCH, "a*(*ACCEPT)b", "" }, - { MUA, 0, "((a(*ACCEPT)b))", "ab" }, - { MUA, 0, "(a(*FAIL)a|a)", "aaa" }, - { MUA, 0, "(?=ab(*ACCEPT)b)a", "ab" }, - { MUA, 0, "(?=(?:x|ab(*ACCEPT)b))", "ab" }, - { MUA, 0, "(?=(a(b(*ACCEPT)b)))a", "ab" }, - { MUA | PCRE_NOTEMPTY, 0, "(?=a*(*ACCEPT))c", "c" }, - - /* Conditional blocks. */ - { MUA, 0, "(?(?=(a))a|b)+k", "ababbalbbadabak" }, - { MUA, 0, "(?(?!(b))a|b)+k", "ababbalbbadabak" }, - { MUA, 0, "(?(?=a)a|b)+k", "ababbalbbadabak" }, - { MUA, 0, "(?(?!b)a|b)+k", "ababbalbbadabak" }, - { MUA, 0, "(?(?=(a))a*|b*)+k", "ababbalbbadabak" }, - { MUA, 0, "(?(?!(b))a*|b*)+k", "ababbalbbadabak" }, - { MUA, 0, "(?(?!(b))(?:aaaaaa|a)|(?:bbbbbb|b))+aaaak", "aaaaaaaaaaaaaa bbbbbbbbbbbbbbb aaaaaaak" }, - { MUA, 0, "(?(?!b)(?:aaaaaa|a)|(?:bbbbbb|b))+aaaak", "aaaaaaaaaaaaaa bbbbbbbbbbbbbbb aaaaaaak" }, - { MUA, 0 | F_DIFF, "(?(?!(b))(?:aaaaaa|a)|(?:bbbbbb|b))+bbbbk", "aaaaaaaaaaaaaa bbbbbbbbbbbbbbb bbbbbbbk" }, - { MUA, 0, "(?(?!b)(?:aaaaaa|a)|(?:bbbbbb|b))+bbbbk", "aaaaaaaaaaaaaa bbbbbbbbbbbbbbb bbbbbbbk" }, - { MUA, 0, "(?(?=a)a*|b*)+k", "ababbalbbadabak" }, - { MUA, 0, "(?(?!b)a*|b*)+k", "ababbalbbadabak" }, - { MUA, 0, "(?(?=a)ab)", "a" }, - { MUA, 0, "(?(?<!b)c)", "b" }, - { MUA, 0, "(?(DEFINE)a(b))", "a" }, - { MUA, 0, "a(?(DEFINE)(?:b|(?:c?)+)*)", "a" }, - { MUA, 0, "(?(?=.[a-c])[k-l]|[A-D])", "kdB" }, - { MUA, 0, "(?(?!.{0,4}[cd])(aa|bb)|(cc|dd))+", "aabbccddaa" }, - { MUA, 0, "(?(?=[^#@]*@)(aaab|aa|aba)|(aba|aab)){3,}", "aaabaaaba#aaabaaaba#aaabaaaba@" }, - { MUA, 0, "((?=\\w{5})\\w(?(?=\\w*k)\\d|[a-f_])*\\w\\s)+", "mol m10kk m088k _f_a_ mbkkl" }, - { MUA, 0, "(c)?\?(?(1)a|b)", "cdcaa" }, - { MUA, 0, "(c)?\?(?(1)a|b)", "cbb" }, - { MUA, 0 | F_DIFF, "(?(?=(a))(aaaa|a?))+aak", "aaaaab aaaaak" }, - { MUA, 0, "(?(?=a)(aaaa|a?))+aak", "aaaaab aaaaak" }, - { MUA, 0, "(?(?!(b))(aaaa|a?))+aak", "aaaaab aaaaak" }, - { MUA, 0, "(?(?!b)(aaaa|a?))+aak", "aaaaab aaaaak" }, - { MUA, 0 | F_DIFF, "(?(?=(a))a*)+aak", "aaaaab aaaaak" }, - { MUA, 0, "(?(?=a)a*)+aak", "aaaaab aaaaak" }, - { MUA, 0, "(?(?!(b))a*)+aak", "aaaaab aaaaak" }, - { MUA, 0, "(?(?!b)a*)+aak", "aaaaab aaaaak" }, - { MUA, 0, "(?(?=(?=(?!(x))a)aa)aaa|(?(?=(?!y)bb)bbb))*k", "abaabbaaabbbaaabbb abaabbaaabbbaaabbbk" }, - { MUA, 0, "(?P<Name>a)?(?P<Name2>b)?(?(Name)c|d)*l", "bc ddd abccabccl" }, - { MUA, 0, "(?P<Name>a)?(?P<Name2>b)?(?(Name)c|d)+?dd", "bcabcacdb bdddd" }, - { MUA, 0, "(?P<Name>a)?(?P<Name2>b)?(?(Name)c|d)+l", "ababccddabdbccd abcccl" }, - { MUA, 0, "((?:a|aa)(?(1)aaa))x", "aax" }, - { MUA, 0, "(?(?!)a|b)", "ab" }, - { MUA, 0, "(?(?!)a)", "ab" }, - { MUA, 0 | F_NOMATCH, "(?(?!)a|b)", "ac" }, - - /* Set start of match. */ - { MUA, 0, "(?:\\Ka)*aaaab", "aaaaaaaa aaaaaaabb" }, - { MUA, 0, "(?>\\Ka\\Ka)*aaaab", "aaaaaaaa aaaaaaaaaabb" }, - { MUA, 0, "a+\\K(?<=\\Gaa)a", "aaaaaa" }, - { MUA | PCRE_NOTEMPTY, 0 | F_NOMATCH, "a\\K(*ACCEPT)b", "aa" }, - { MUA | PCRE_NOTEMPTY_ATSTART, 0, "a\\K(*ACCEPT)b", "aa" }, - - /* First line. */ - { MUA | PCRE_FIRSTLINE, 0 | F_PROPERTY, "\\p{Any}a", "bb\naaa" }, - { MUA | PCRE_FIRSTLINE, 0 | F_NOMATCH | F_PROPERTY, "\\p{Any}a", "bb\r\naaa" }, - { MUA | PCRE_FIRSTLINE, 0, "(?<=a)", "a" }, - { MUA | PCRE_FIRSTLINE, 0 | F_NOMATCH, "[^a][^b]", "ab" }, - { MUA | PCRE_FIRSTLINE, 0 | F_NOMATCH, "a", "\na" }, - { MUA | PCRE_FIRSTLINE, 0 | F_NOMATCH, "[abc]", "\na" }, - { MUA | PCRE_FIRSTLINE, 0 | F_NOMATCH, "^a", "\na" }, - { MUA | PCRE_FIRSTLINE, 0 | F_NOMATCH, "^(?<=\n)", "\na" }, - { MUA | PCRE_FIRSTLINE, 0, "\xf0\x90\x90\x80", "\xf0\x90\x90\x80" }, - { PCRE_MULTILINE | PCRE_UTF8 | PCRE_NEWLINE_ANY | PCRE_FIRSTLINE, 0 | F_NOMATCH, "#", "\xc2\x85#" }, - { PCRE_MULTILINE | PCRE_NEWLINE_ANY | PCRE_FIRSTLINE, 0 | F_NOMATCH, "#", "\x85#" }, - { PCRE_MULTILINE | PCRE_UTF8 | PCRE_NEWLINE_ANY | PCRE_FIRSTLINE, 0 | F_NOMATCH, "^#", "\xe2\x80\xa8#" }, - { PCRE_MULTILINE | PCRE_UTF8 | PCRE_NEWLINE_CRLF | PCRE_FIRSTLINE, 0 | F_PROPERTY, "\\p{Any}", "\r\na" }, - { PCRE_MULTILINE | PCRE_UTF8 | PCRE_NEWLINE_CRLF | PCRE_FIRSTLINE, 0, ".", "\r" }, - { PCRE_MULTILINE | PCRE_UTF8 | PCRE_NEWLINE_CRLF | PCRE_FIRSTLINE, 0, "a", "\ra" }, - { PCRE_MULTILINE | PCRE_UTF8 | PCRE_NEWLINE_CRLF | PCRE_FIRSTLINE, 0 | F_NOMATCH, "ba", "bbb\r\nba" }, - { PCRE_MULTILINE | PCRE_UTF8 | PCRE_NEWLINE_CRLF | PCRE_FIRSTLINE, 0 | F_NOMATCH | F_PROPERTY, "\\p{Any}{4}|a", "\r\na" }, - { PCRE_MULTILINE | PCRE_UTF8 | PCRE_NEWLINE_CRLF | PCRE_FIRSTLINE, 1, ".", "\r\n" }, - { PCRE_FIRSTLINE | PCRE_NEWLINE_LF | PCRE_DOTALL, 0 | F_NOMATCH, "ab.", "ab" }, - { MUA | PCRE_FIRSTLINE, 1 | F_NOMATCH, "^[a-d0-9]", "\nxx\nd" }, - - /* Recurse. */ - { MUA, 0, "(a)(?1)", "aa" }, - { MUA, 0, "((a))(?1)", "aa" }, - { MUA, 0, "(b|a)(?1)", "aa" }, - { MUA, 0, "(b|(a))(?1)", "aa" }, - { MUA, 0 | F_NOMATCH, "((a)(b)(?:a*))(?1)", "aba" }, - { MUA, 0, "((a)(b)(?:a*))(?1)", "abab" }, - { MUA, 0, "((a+)c(?2))b(?1)", "aacaabaca" }, - { MUA, 0, "((?2)b|(a)){2}(?1)", "aabab" }, - { MUA, 0, "(?1)(a)*+(?2)(b(?1))", "aababa" }, - { MUA, 0, "(?1)(((a(*ACCEPT)))b)", "axaa" }, - { MUA, 0, "(?1)(?(DEFINE) (((ac(*ACCEPT)))b) )", "akaac" }, - { MUA, 0, "(a+)b(?1)b\\1", "abaaabaaaaa" }, - { MUA, 0 | F_NOMATCH, "(?(DEFINE)(aa|a))(?1)ab", "aab" }, - { MUA, 0, "(?(DEFINE)(a\\Kb))(?1)+ababc", "abababxabababc" }, - { MUA, 0, "(a\\Kb)(?1)+ababc", "abababxababababc" }, - { MUA, 0 | F_NOMATCH, "(a\\Kb)(?1)+ababc", "abababxababababxc" }, - { MUA, 0, "b|<(?R)*>", "<<b>" }, - { MUA, 0, "(a\\K){0}(?:(?1)b|ac)", "ac" }, - { MUA, 0, "(?(DEFINE)(a(?2)|b)(b(?1)|(a)))(?:(?1)|(?2))m", "ababababnababababaam" }, - { MUA, 0, "(a)((?(R)a|b))(?2)", "aabbabaa" }, - { MUA, 0, "(a)((?(R2)a|b))(?2)", "aabbabaa" }, - { MUA, 0, "(a)((?(R1)a|b))(?2)", "ababba" }, - { MUA, 0, "(?(R0)aa|bb(?R))", "abba aabb bbaa" }, - { MUA, 0, "((?(R)(?:aaaa|a)|(?:(aaaa)|(a)))+)(?1)$", "aaaaaaaaaa aaaa" }, - { MUA, 0, "(?P<Name>a(?(R&Name)a|b))(?1)", "aab abb abaa" }, - { MUA, 0, "((?(R)a|(?1)){3})", "XaaaaaaaaaX" }, - { MUA, 0, "((?:(?(R)a|(?1))){3})", "XaaaaaaaaaX" }, - { MUA, 0, "((?(R)a|(?1)){1,3})aaaaaa", "aaaaaaaaXaaaaaaaaa" }, - { MUA, 0, "((?(R)a|(?1)){1,3}?)M", "aaaM" }, - - /* 16 bit specific tests. */ - { CMA, 0 | F_FORCECONV, "\xc3\xa1", "\xc3\x81\xc3\xa1" }, - { CMA, 0 | F_FORCECONV, "\xe1\xbd\xb8", "\xe1\xbf\xb8\xe1\xbd\xb8" }, - { CMA, 0 | F_FORCECONV, "[\xc3\xa1]", "\xc3\x81\xc3\xa1" }, - { CMA, 0 | F_FORCECONV, "[\xe1\xbd\xb8]", "\xe1\xbf\xb8\xe1\xbd\xb8" }, - { CMA, 0 | F_FORCECONV, "[a-\xed\xb0\x80]", "A" }, - { CMA, 0 | F_NO8 | F_FORCECONV, "[a-\\x{dc00}]", "B" }, - { CMA, 0 | F_NO8 | F_NOMATCH | F_FORCECONV, "[b-\\x{dc00}]", "a" }, - { CMA, 0 | F_NO8 | F_FORCECONV, "\xed\xa0\x80\\x{d800}\xed\xb0\x80\\x{dc00}", "\xed\xa0\x80\xed\xa0\x80\xed\xb0\x80\xed\xb0\x80" }, - { CMA, 0 | F_NO8 | F_FORCECONV, "[\xed\xa0\x80\\x{d800}]{1,2}?[\xed\xb0\x80\\x{dc00}]{1,2}?#", "\xed\xa0\x80\xed\xa0\x80\xed\xb0\x80\xed\xb0\x80#" }, - { CMA, 0 | F_FORCECONV, "[\xed\xa0\x80\xed\xb0\x80#]{0,3}(?<=\xed\xb0\x80.)", "\xed\xa0\x80#\xed\xa0\x80##\xed\xb0\x80\xed\xa0\x80" }, - { CMA, 0 | F_FORCECONV, "[\xed\xa0\x80-\xed\xb3\xbf]", "\xed\x9f\xbf\xed\xa0\x83" }, - { CMA, 0 | F_FORCECONV, "[\xed\xa0\x80-\xed\xb3\xbf]", "\xed\xb4\x80\xed\xb3\xb0" }, - { CMA, 0 | F_NO8 | F_FORCECONV, "[\\x{d800}-\\x{dcff}]", "\xed\x9f\xbf\xed\xa0\x83" }, - { CMA, 0 | F_NO8 | F_FORCECONV, "[\\x{d800}-\\x{dcff}]", "\xed\xb4\x80\xed\xb3\xb0" }, - { CMA, 0 | F_FORCECONV, "[\xed\xa0\x80-\xef\xbf\xbf]+[\x1-\xed\xb0\x80]+#", "\xed\xa0\x85\xc3\x81\xed\xa0\x85\xef\xbf\xb0\xc2\x85\xed\xa9\x89#" }, - { CMA, 0 | F_FORCECONV, "[\xed\xa0\x80][\xed\xb0\x80]{2,}", "\xed\xa0\x80\xed\xb0\x80\xed\xa0\x80\xed\xb0\x80\xed\xb0\x80\xed\xb0\x80" }, - { MA, 0 | F_FORCECONV, "[^\xed\xb0\x80]{3,}?", "##\xed\xb0\x80#\xed\xb0\x80#\xc3\x89#\xed\xb0\x80" }, - { MA, 0 | F_NO8 | F_FORCECONV, "[^\\x{dc00}]{3,}?", "##\xed\xb0\x80#\xed\xb0\x80#\xc3\x89#\xed\xb0\x80" }, - { CMA, 0 | F_FORCECONV, ".\\B.", "\xed\xa0\x80\xed\xb0\x80" }, - { CMA, 0 | F_FORCECONV, "\\D+(?:\\d+|.)\\S+(?:\\s+|.)\\W+(?:\\w+|.)\xed\xa0\x80\xed\xa0\x80", "\xed\xa0\x80\xed\xa0\x80\xed\xa0\x80\xed\xa0\x80\xed\xa0\x80\xed\xa0\x80\xed\xa0\x80\xed\xa0\x80" }, - { CMA, 0 | F_FORCECONV, "\\d*\\s*\\w*\xed\xa0\x80\xed\xa0\x80", "\xed\xa0\x80\xed\xa0\x80" }, - { CMA, 0 | F_FORCECONV | F_NOMATCH, "\\d*?\\D*?\\s*?\\S*?\\w*?\\W*?##", "\xed\xa0\x80\xed\xa0\x80\xed\xa0\x80\xed\xa0\x80#" }, - { CMA | PCRE_EXTENDED, 0 | F_FORCECONV, "\xed\xa0\x80 \xed\xb0\x80 !", "\xed\xa0\x80\xed\xb0\x80!" }, - { CMA, 0 | F_FORCECONV, "\xed\xa0\x80+#[^#]+\xed\xa0\x80", "\xed\xa0\x80#a\xed\xa0\x80" }, - { CMA, 0 | F_FORCECONV, "(\xed\xa0\x80+)#\\1", "\xed\xa0\x80\xed\xa0\x80#\xed\xa0\x80\xed\xa0\x80" }, - { PCRE_MULTILINE | PCRE_NEWLINE_ANY, 0 | F_NO8 | F_FORCECONV, "^-", "a--\xe2\x80\xa8--" }, - { PCRE_BSR_UNICODE, 0 | F_NO8 | F_FORCECONV, "\\R", "ab\xe2\x80\xa8" }, - { 0, 0 | F_NO8 | F_FORCECONV, "\\v", "ab\xe2\x80\xa9" }, - { 0, 0 | F_NO8 | F_FORCECONV, "\\h", "ab\xe1\xa0\x8e" }, - { 0, 0 | F_NO8 | F_FORCECONV, "\\v+?\\V+?#", "\xe2\x80\xa9\xe2\x80\xa9\xef\xbf\xbf\xef\xbf\xbf#" }, - { 0, 0 | F_NO8 | F_FORCECONV, "\\h+?\\H+?#", "\xe1\xa0\x8e\xe1\xa0\x8e\xef\xbf\xbf\xef\xbf\xbf#" }, - - /* Partial matching. */ - { MUA | PCRE_PARTIAL_SOFT, 0, "ab", "a" }, - { MUA | PCRE_PARTIAL_SOFT, 0, "ab|a", "a" }, - { MUA | PCRE_PARTIAL_HARD, 0, "ab|a", "a" }, - { MUA | PCRE_PARTIAL_SOFT, 0, "\\b#", "a" }, - { MUA | PCRE_PARTIAL_SOFT, 0, "(?<=a)b", "a" }, - { MUA | PCRE_PARTIAL_SOFT, 0, "abc|(?<=xxa)bc", "xxab" }, - { MUA | PCRE_PARTIAL_SOFT, 0, "a\\B", "a" }, - { MUA | PCRE_PARTIAL_HARD, 0, "a\\b", "a" }, - - /* (*MARK) verb. */ - { MUA, 0, "a(*MARK:aa)a", "ababaa" }, - { MUA, 0 | F_NOMATCH, "a(*:aa)a", "abab" }, - { MUA, 0, "a(*:aa)(b(*:bb)b|bc)", "abc" }, - { MUA, 0 | F_NOMATCH, "a(*:1)x|b(*:2)y", "abc" }, - { MUA, 0, "(?>a(*:aa))b|ac", "ac" }, - { MUA, 0, "(?(DEFINE)(a(*:aa)))(?1)", "a" }, - { MUA, 0 | F_NOMATCH, "(?(DEFINE)((a)(*:aa)))(?1)b", "aa" }, - { MUA, 0, "(?(DEFINE)(a(*:aa)))a(?1)b|aac", "aac" }, - { MUA, 0, "(a(*:aa)){0}(?:b(?1)b|c)+c", "babbab cc" }, - { MUA, 0, "(a(*:aa)){0}(?:b(?1)b)+", "babba" }, - { MUA, 0 | F_NOMATCH | F_STUDY, "(a(*:aa)){0}(?:b(?1)b)+", "ba" }, - { MUA, 0, "(a\\K(*:aa)){0}(?:b(?1)b|c)+c", "babbab cc" }, - { MUA, 0, "(a\\K(*:aa)){0}(?:b(?1)b)+", "babba" }, - { MUA, 0 | F_NOMATCH | F_STUDY, "(a\\K(*:aa)){0}(?:b(?1)b)+", "ba" }, - { MUA, 0 | F_NOMATCH | F_STUDY, "(*:mark)m", "a" }, - - /* (*COMMIT) verb. */ - { MUA, 0 | F_NOMATCH, "a(*COMMIT)b", "ac" }, - { MUA, 0, "aa(*COMMIT)b", "xaxaab" }, - { MUA, 0 | F_NOMATCH, "a(*COMMIT)(*:msg)b|ac", "ac" }, - { MUA, 0 | F_NOMATCH, "(a(*COMMIT)b)++", "abac" }, - { MUA, 0 | F_NOMATCH, "((a)(*COMMIT)b)++", "abac" }, - { MUA, 0 | F_NOMATCH, "(?=a(*COMMIT)b)ab|ad", "ad" }, - - /* (*PRUNE) verb. */ - { MUA, 0, "aa\\K(*PRUNE)b", "aaab" }, - { MUA, 0, "aa(*PRUNE:bb)b|a", "aa" }, - { MUA, 0, "(a)(a)(*PRUNE)b|(a)", "aa" }, - { MUA, 0, "(a)(a)(a)(a)(a)(a)(a)(a)(*PRUNE)b|(a)", "aaaaaaaa" }, - { MUA | PCRE_PARTIAL_SOFT, 0, "a(*PRUNE)a|", "a" }, - { MUA | PCRE_PARTIAL_SOFT, 0, "a(*PRUNE)a|m", "a" }, - { MUA, 0 | F_NOMATCH, "(?=a(*PRUNE)b)ab|ad", "ad" }, - { MUA, 0, "a(*COMMIT)(*PRUNE)d|bc", "abc" }, - { MUA, 0, "(?=a(*COMMIT)b)a(*PRUNE)c|bc", "abc" }, - { MUA, 0 | F_NOMATCH, "(*COMMIT)(?=a(*COMMIT)b)a(*PRUNE)c|bc", "abc" }, - { MUA, 0, "(?=(a)(*COMMIT)b)a(*PRUNE)c|bc", "abc" }, - { MUA, 0 | F_NOMATCH, "(*COMMIT)(?=(a)(*COMMIT)b)a(*PRUNE)c|bc", "abc" }, - { MUA, 0, "(a(*COMMIT)b){0}a(?1)(*PRUNE)c|bc", "abc" }, - { MUA, 0 | F_NOMATCH, "(a(*COMMIT)b){0}a(*COMMIT)(?1)(*PRUNE)c|bc", "abc" }, - { MUA, 0, "(a(*COMMIT)b)++(*PRUNE)d|c", "ababc" }, - { MUA, 0 | F_NOMATCH, "(*COMMIT)(a(*COMMIT)b)++(*PRUNE)d|c", "ababc" }, - { MUA, 0, "((a)(*COMMIT)b)++(*PRUNE)d|c", "ababc" }, - { MUA, 0 | F_NOMATCH, "(*COMMIT)((a)(*COMMIT)b)++(*PRUNE)d|c", "ababc" }, - { MUA, 0, "(?>a(*COMMIT)b)*abab(*PRUNE)d|ba", "ababab" }, - { MUA, 0 | F_NOMATCH, "(*COMMIT)(?>a(*COMMIT)b)*abab(*PRUNE)d|ba", "ababab" }, - { MUA, 0, "(?>a(*COMMIT)b)+abab(*PRUNE)d|ba", "ababab" }, - { MUA, 0 | F_NOMATCH, "(*COMMIT)(?>a(*COMMIT)b)+abab(*PRUNE)d|ba", "ababab" }, - { MUA, 0, "(?>a(*COMMIT)b)?ab(*PRUNE)d|ba", "aba" }, - { MUA, 0 | F_NOMATCH, "(*COMMIT)(?>a(*COMMIT)b)?ab(*PRUNE)d|ba", "aba" }, - { MUA, 0, "(?>a(*COMMIT)b)*?n(*PRUNE)d|ba", "abababn" }, - { MUA, 0 | F_NOMATCH, "(*COMMIT)(?>a(*COMMIT)b)*?n(*PRUNE)d|ba", "abababn" }, - { MUA, 0, "(?>a(*COMMIT)b)+?n(*PRUNE)d|ba", "abababn" }, - { MUA, 0 | F_NOMATCH, "(*COMMIT)(?>a(*COMMIT)b)+?n(*PRUNE)d|ba", "abababn" }, - { MUA, 0, "(?>a(*COMMIT)b)??n(*PRUNE)d|bn", "abn" }, - { MUA, 0 | F_NOMATCH, "(*COMMIT)(?>a(*COMMIT)b)??n(*PRUNE)d|bn", "abn" }, - - /* (*SKIP) verb. */ - { MUA, 0 | F_NOMATCH, "(?=a(*SKIP)b)ab|ad", "ad" }, - - /* (*THEN) verb. */ - { MUA, 0, "((?:a(*THEN)|aab)(*THEN)c|a+)+m", "aabcaabcaabcaabcnacm" }, - { MUA, 0 | F_NOMATCH, "((?:a(*THEN)|aab)(*THEN)c|a+)+m", "aabcm" }, - { MUA, 0, "((?:a(*THEN)|aab)c|a+)+m", "aabcaabcnmaabcaabcm" }, - { MUA, 0, "((?:a|aab)(*THEN)c|a+)+m", "aam" }, - { MUA, 0, "((?:a(*COMMIT)|aab)(*THEN)c|a+)+m", "aam" }, - { MUA, 0, "(?(?=a(*THEN)b)ab|ad)", "ad" }, - { MUA, 0, "(?(?!a(*THEN)b)ad|add)", "add" }, - { MUA, 0 | F_NOMATCH, "(?(?=a)a(*THEN)b|ad)", "ad" }, - { MUA, 0, "(?!(?(?=a)ab|b(*THEN)d))bn|bnn", "bnn" }, - - /* Deep recursion. */ - { MUA, 0, "((((?:(?:(?:\\w)+)?)*|(?>\\w)+?)+|(?>\\w)?\?)*)?\\s", "aaaaa+ " }, - { MUA, 0, "(?:((?:(?:(?:\\w*?)+)??|(?>\\w)?|\\w*+)*)+)+?\\s", "aa+ " }, - { MUA, 0, "((a?)+)+b", "aaaaaaaaaaaa b" }, - - /* Deep recursion: Stack limit reached. */ - { MA, 0 | F_NOMATCH, "a?a?a?a?a?a?a?a?a?a?a?a?a?a?a?a?a?a?a?a?a?a?a?aaaaaaaaaaaaaaaaaaaaaaa", "aaaaaaaaaaaaaaaaaaaaaaa" }, - { MA, 0 | F_NOMATCH, "(?:a+)+b", "aaaaaaaaaaaaaaaaaaaaaaaa b" }, - { MA, 0 | F_NOMATCH, "(?:a+?)+?b", "aaaaaaaaaaaaaaaaaaaaaaaa b" }, - { MA, 0 | F_NOMATCH, "(?:a*)*b", "aaaaaaaaaaaaaaaaaaaaaaaa b" }, - { MA, 0 | F_NOMATCH, "(?:a*?)*?b", "aaaaaaaaaaaaaaaaaaaaaaaa b" }, - - { 0, 0, NULL, NULL } -}; - -static const unsigned char *tables(int mode) -{ - /* The purpose of this function to allow valgrind - for reporting invalid reads and writes. */ - static unsigned char *tables_copy; - const char *errorptr; - int erroroffset; - unsigned char *default_tables; -#if defined SUPPORT_PCRE8 - pcre *regex; - char null_str[1] = { 0 }; -#elif defined SUPPORT_PCRE16 - pcre16 *regex; - PCRE_UCHAR16 null_str[1] = { 0 }; -#elif defined SUPPORT_PCRE32 - pcre32 *regex; - PCRE_UCHAR32 null_str[1] = { 0 }; -#endif - - if (mode) { - if (tables_copy) - free(tables_copy); - tables_copy = NULL; - return NULL; - } - - if (tables_copy) - return tables_copy; - - default_tables = NULL; -#if defined SUPPORT_PCRE8 - regex = pcre_compile(null_str, 0, &errorptr, &erroroffset, NULL); - if (regex) { - pcre_fullinfo(regex, NULL, PCRE_INFO_DEFAULT_TABLES, &default_tables); - pcre_free(regex); - } -#elif defined SUPPORT_PCRE16 - regex = pcre16_compile(null_str, 0, &errorptr, &erroroffset, NULL); - if (regex) { - pcre16_fullinfo(regex, NULL, PCRE_INFO_DEFAULT_TABLES, &default_tables); - pcre16_free(regex); - } -#elif defined SUPPORT_PCRE32 - regex = pcre32_compile(null_str, 0, &errorptr, &erroroffset, NULL); - if (regex) { - pcre32_fullinfo(regex, NULL, PCRE_INFO_DEFAULT_TABLES, &default_tables); - pcre32_free(regex); - } -#endif - /* Shouldn't ever happen. */ - if (!default_tables) - return NULL; - - /* Unfortunately this value cannot get from pcre_fullinfo. - Since this is a test program, this is acceptable at the moment. */ - tables_copy = (unsigned char *)malloc(1088); - if (!tables_copy) - return NULL; - - memcpy(tables_copy, default_tables, 1088); - return tables_copy; -} - -#ifdef SUPPORT_PCRE8 -static pcre_jit_stack* callback8(void *arg) -{ - return (pcre_jit_stack *)arg; -} -#endif - -#ifdef SUPPORT_PCRE16 -static pcre16_jit_stack* callback16(void *arg) -{ - return (pcre16_jit_stack *)arg; -} -#endif - -#ifdef SUPPORT_PCRE32 -static pcre32_jit_stack* callback32(void *arg) -{ - return (pcre32_jit_stack *)arg; -} -#endif - -#ifdef SUPPORT_PCRE8 -static pcre_jit_stack *stack8; - -static pcre_jit_stack *getstack8(void) -{ - if (!stack8) - stack8 = pcre_jit_stack_alloc(1, 1024 * 1024); - return stack8; -} - -static void setstack8(pcre_extra *extra) -{ - if (!extra) { - if (stack8) - pcre_jit_stack_free(stack8); - stack8 = NULL; - return; - } - - pcre_assign_jit_stack(extra, callback8, getstack8()); -} -#endif /* SUPPORT_PCRE8 */ - -#ifdef SUPPORT_PCRE16 -static pcre16_jit_stack *stack16; - -static pcre16_jit_stack *getstack16(void) -{ - if (!stack16) - stack16 = pcre16_jit_stack_alloc(1, 1024 * 1024); - return stack16; -} - -static void setstack16(pcre16_extra *extra) -{ - if (!extra) { - if (stack16) - pcre16_jit_stack_free(stack16); - stack16 = NULL; - return; - } - - pcre16_assign_jit_stack(extra, callback16, getstack16()); -} -#endif /* SUPPORT_PCRE16 */ - -#ifdef SUPPORT_PCRE32 -static pcre32_jit_stack *stack32; - -static pcre32_jit_stack *getstack32(void) -{ - if (!stack32) - stack32 = pcre32_jit_stack_alloc(1, 1024 * 1024); - return stack32; -} - -static void setstack32(pcre32_extra *extra) -{ - if (!extra) { - if (stack32) - pcre32_jit_stack_free(stack32); - stack32 = NULL; - return; - } - - pcre32_assign_jit_stack(extra, callback32, getstack32()); -} -#endif /* SUPPORT_PCRE32 */ - -#ifdef SUPPORT_PCRE16 - -static int convert_utf8_to_utf16(const char *input, PCRE_UCHAR16 *output, int *offsetmap, int max_length) -{ - unsigned char *iptr = (unsigned char*)input; - PCRE_UCHAR16 *optr = output; - unsigned int c; - - if (max_length == 0) - return 0; - - while (*iptr && max_length > 1) { - c = 0; - if (offsetmap) - *offsetmap++ = (int)(iptr - (unsigned char*)input); - - if (*iptr < 0xc0) - c = *iptr++; - else if (!(*iptr & 0x20)) { - c = ((iptr[0] & 0x1f) << 6) | (iptr[1] & 0x3f); - iptr += 2; - } else if (!(*iptr & 0x10)) { - c = ((iptr[0] & 0x0f) << 12) | ((iptr[1] & 0x3f) << 6) | (iptr[2] & 0x3f); - iptr += 3; - } else if (!(*iptr & 0x08)) { - c = ((iptr[0] & 0x07) << 18) | ((iptr[1] & 0x3f) << 12) | ((iptr[2] & 0x3f) << 6) | (iptr[3] & 0x3f); - iptr += 4; - } - - if (c < 65536) { - *optr++ = c; - max_length--; - } else if (max_length <= 2) { - *optr = '\0'; - return (int)(optr - output); - } else { - c -= 0x10000; - *optr++ = 0xd800 | ((c >> 10) & 0x3ff); - *optr++ = 0xdc00 | (c & 0x3ff); - max_length -= 2; - if (offsetmap) - offsetmap++; - } - } - if (offsetmap) - *offsetmap = (int)(iptr - (unsigned char*)input); - *optr = '\0'; - return (int)(optr - output); -} - -static int copy_char8_to_char16(const char *input, PCRE_UCHAR16 *output, int max_length) -{ - unsigned char *iptr = (unsigned char*)input; - PCRE_UCHAR16 *optr = output; - - if (max_length == 0) - return 0; - - while (*iptr && max_length > 1) { - *optr++ = *iptr++; - max_length--; - } - *optr = '\0'; - return (int)(optr - output); -} - -#define REGTEST_MAX_LENGTH16 4096 -static PCRE_UCHAR16 regtest_buf16[REGTEST_MAX_LENGTH16]; -static int regtest_offsetmap16[REGTEST_MAX_LENGTH16]; - -#endif /* SUPPORT_PCRE16 */ - -#ifdef SUPPORT_PCRE32 - -static int convert_utf8_to_utf32(const char *input, PCRE_UCHAR32 *output, int *offsetmap, int max_length) -{ - unsigned char *iptr = (unsigned char*)input; - PCRE_UCHAR32 *optr = output; - unsigned int c; - - if (max_length == 0) - return 0; - - while (*iptr && max_length > 1) { - c = 0; - if (offsetmap) - *offsetmap++ = (int)(iptr - (unsigned char*)input); - - if (*iptr < 0xc0) - c = *iptr++; - else if (!(*iptr & 0x20)) { - c = ((iptr[0] & 0x1f) << 6) | (iptr[1] & 0x3f); - iptr += 2; - } else if (!(*iptr & 0x10)) { - c = ((iptr[0] & 0x0f) << 12) | ((iptr[1] & 0x3f) << 6) | (iptr[2] & 0x3f); - iptr += 3; - } else if (!(*iptr & 0x08)) { - c = ((iptr[0] & 0x07) << 18) | ((iptr[1] & 0x3f) << 12) | ((iptr[2] & 0x3f) << 6) | (iptr[3] & 0x3f); - iptr += 4; - } - - *optr++ = c; - max_length--; - } - if (offsetmap) - *offsetmap = (int)(iptr - (unsigned char*)input); - *optr = 0; - return (int)(optr - output); -} - -static int copy_char8_to_char32(const char *input, PCRE_UCHAR32 *output, int max_length) -{ - unsigned char *iptr = (unsigned char*)input; - PCRE_UCHAR32 *optr = output; - - if (max_length == 0) - return 0; - - while (*iptr && max_length > 1) { - *optr++ = *iptr++; - max_length--; - } - *optr = '\0'; - return (int)(optr - output); -} - -#define REGTEST_MAX_LENGTH32 4096 -static PCRE_UCHAR32 regtest_buf32[REGTEST_MAX_LENGTH32]; -static int regtest_offsetmap32[REGTEST_MAX_LENGTH32]; - -#endif /* SUPPORT_PCRE32 */ - -static int check_ascii(const char *input) -{ - const unsigned char *ptr = (unsigned char *)input; - while (*ptr) { - if (*ptr > 127) - return 0; - ptr++; - } - return 1; -} - -static int regression_tests(void) -{ - struct regression_test_case *current = regression_test_cases; - const char *error; - char *cpu_info; - int i, err_offs; - int is_successful, is_ascii; - int total = 0; - int successful = 0; - int successful_row = 0; - int counter = 0; - int study_mode; - int utf = 0, ucp = 0; - int disabled_flags = 0; -#ifdef SUPPORT_PCRE8 - pcre *re8; - pcre_extra *extra8; - pcre_extra dummy_extra8; - int ovector8_1[32]; - int ovector8_2[32]; - int return_value8[2]; - unsigned char *mark8_1, *mark8_2; -#endif -#ifdef SUPPORT_PCRE16 - pcre16 *re16; - pcre16_extra *extra16; - pcre16_extra dummy_extra16; - int ovector16_1[32]; - int ovector16_2[32]; - int return_value16[2]; - PCRE_UCHAR16 *mark16_1, *mark16_2; - int length16; -#endif -#ifdef SUPPORT_PCRE32 - pcre32 *re32; - pcre32_extra *extra32; - pcre32_extra dummy_extra32; - int ovector32_1[32]; - int ovector32_2[32]; - int return_value32[2]; - PCRE_UCHAR32 *mark32_1, *mark32_2; - int length32; -#endif - - /* This test compares the behaviour of interpreter and JIT. Although disabling - utf or ucp may make tests fail, if the pcre_exec result is the SAME, it is - still considered successful from pcre_jit_test point of view. */ - -#if defined SUPPORT_PCRE8 - pcre_config(PCRE_CONFIG_JITTARGET, &cpu_info); -#elif defined SUPPORT_PCRE16 - pcre16_config(PCRE_CONFIG_JITTARGET, &cpu_info); -#elif defined SUPPORT_PCRE32 - pcre32_config(PCRE_CONFIG_JITTARGET, &cpu_info); -#endif - - printf("Running JIT regression tests\n"); - printf(" target CPU of SLJIT compiler: %s\n", cpu_info); - -#if defined SUPPORT_PCRE8 - pcre_config(PCRE_CONFIG_UTF8, &utf); - pcre_config(PCRE_CONFIG_UNICODE_PROPERTIES, &ucp); -#elif defined SUPPORT_PCRE16 - pcre16_config(PCRE_CONFIG_UTF16, &utf); - pcre16_config(PCRE_CONFIG_UNICODE_PROPERTIES, &ucp); -#elif defined SUPPORT_PCRE32 - pcre32_config(PCRE_CONFIG_UTF32, &utf); - pcre32_config(PCRE_CONFIG_UNICODE_PROPERTIES, &ucp); -#endif - - if (!utf) - disabled_flags |= PCRE_UTF8 | PCRE_UTF16 | PCRE_UTF32; - if (!ucp) - disabled_flags |= PCRE_UCP; -#ifdef SUPPORT_PCRE8 - printf(" in 8 bit mode with UTF-8 %s and ucp %s:\n", utf ? "enabled" : "disabled", ucp ? "enabled" : "disabled"); -#endif -#ifdef SUPPORT_PCRE16 - printf(" in 16 bit mode with UTF-16 %s and ucp %s:\n", utf ? "enabled" : "disabled", ucp ? "enabled" : "disabled"); -#endif -#ifdef SUPPORT_PCRE32 - printf(" in 32 bit mode with UTF-32 %s and ucp %s:\n", utf ? "enabled" : "disabled", ucp ? "enabled" : "disabled"); -#endif - - while (current->pattern) { - /* printf("\nPattern: %s :\n", current->pattern); */ - total++; - is_ascii = 0; - if (!(current->start_offset & F_PROPERTY)) - is_ascii = check_ascii(current->pattern) && check_ascii(current->input); - - if (current->flags & PCRE_PARTIAL_SOFT) - study_mode = PCRE_STUDY_JIT_PARTIAL_SOFT_COMPILE; - else if (current->flags & PCRE_PARTIAL_HARD) - study_mode = PCRE_STUDY_JIT_PARTIAL_HARD_COMPILE; - else - study_mode = PCRE_STUDY_JIT_COMPILE; - error = NULL; -#ifdef SUPPORT_PCRE8 - re8 = NULL; - if (!(current->start_offset & F_NO8)) - re8 = pcre_compile(current->pattern, - current->flags & ~(PCRE_NOTBOL | PCRE_NOTEOL | PCRE_NOTEMPTY | PCRE_NOTEMPTY_ATSTART | PCRE_PARTIAL_SOFT | PCRE_PARTIAL_HARD | disabled_flags), - &error, &err_offs, tables(0)); - - extra8 = NULL; - if (re8) { - error = NULL; - extra8 = pcre_study(re8, study_mode, &error); - if (!extra8) { - printf("\n8 bit: Cannot study pattern: %s\n", current->pattern); - pcre_free(re8); - re8 = NULL; - } - else if (!(extra8->flags & PCRE_EXTRA_EXECUTABLE_JIT)) { - printf("\n8 bit: JIT compiler does not support: %s\n", current->pattern); - pcre_free_study(extra8); - pcre_free(re8); - re8 = NULL; - } - extra8->flags |= PCRE_EXTRA_MARK; - } else if (((utf && ucp) || is_ascii) && !(current->start_offset & F_NO8)) - printf("\n8 bit: Cannot compile pattern \"%s\": %s\n", current->pattern, error); -#endif -#ifdef SUPPORT_PCRE16 - if ((current->flags & PCRE_UTF16) || (current->start_offset & F_FORCECONV)) - convert_utf8_to_utf16(current->pattern, regtest_buf16, NULL, REGTEST_MAX_LENGTH16); - else - copy_char8_to_char16(current->pattern, regtest_buf16, REGTEST_MAX_LENGTH16); - - re16 = NULL; - if (!(current->start_offset & F_NO16)) - re16 = pcre16_compile(regtest_buf16, - current->flags & ~(PCRE_NOTBOL | PCRE_NOTEOL | PCRE_NOTEMPTY | PCRE_NOTEMPTY_ATSTART | PCRE_PARTIAL_SOFT | PCRE_PARTIAL_HARD | disabled_flags), - &error, &err_offs, tables(0)); - - extra16 = NULL; - if (re16) { - error = NULL; - extra16 = pcre16_study(re16, study_mode, &error); - if (!extra16) { - printf("\n16 bit: Cannot study pattern: %s\n", current->pattern); - pcre16_free(re16); - re16 = NULL; - } - else if (!(extra16->flags & PCRE_EXTRA_EXECUTABLE_JIT)) { - printf("\n16 bit: JIT compiler does not support: %s\n", current->pattern); - pcre16_free_study(extra16); - pcre16_free(re16); - re16 = NULL; - } - extra16->flags |= PCRE_EXTRA_MARK; - } else if (((utf && ucp) || is_ascii) && !(current->start_offset & F_NO16)) - printf("\n16 bit: Cannot compile pattern \"%s\": %s\n", current->pattern, error); -#endif -#ifdef SUPPORT_PCRE32 - if ((current->flags & PCRE_UTF32) || (current->start_offset & F_FORCECONV)) - convert_utf8_to_utf32(current->pattern, regtest_buf32, NULL, REGTEST_MAX_LENGTH32); - else - copy_char8_to_char32(current->pattern, regtest_buf32, REGTEST_MAX_LENGTH32); - - re32 = NULL; - if (!(current->start_offset & F_NO32)) - re32 = pcre32_compile(regtest_buf32, - current->flags & ~(PCRE_NOTBOL | PCRE_NOTEOL | PCRE_NOTEMPTY | PCRE_NOTEMPTY_ATSTART | PCRE_PARTIAL_SOFT | PCRE_PARTIAL_HARD | disabled_flags), - &error, &err_offs, tables(0)); - - extra32 = NULL; - if (re32) { - error = NULL; - extra32 = pcre32_study(re32, study_mode, &error); - if (!extra32) { - printf("\n32 bit: Cannot study pattern: %s\n", current->pattern); - pcre32_free(re32); - re32 = NULL; - } - if (!(extra32->flags & PCRE_EXTRA_EXECUTABLE_JIT)) { - printf("\n32 bit: JIT compiler does not support: %s\n", current->pattern); - pcre32_free_study(extra32); - pcre32_free(re32); - re32 = NULL; - } - extra32->flags |= PCRE_EXTRA_MARK; - } else if (((utf && ucp) || is_ascii) && !(current->start_offset & F_NO32)) - printf("\n32 bit: Cannot compile pattern \"%s\": %s\n", current->pattern, error); -#endif - - counter++; - if ((counter & 0x3) != 0) { -#ifdef SUPPORT_PCRE8 - setstack8(NULL); -#endif -#ifdef SUPPORT_PCRE16 - setstack16(NULL); -#endif -#ifdef SUPPORT_PCRE32 - setstack32(NULL); -#endif - } - -#ifdef SUPPORT_PCRE8 - return_value8[0] = -1000; - return_value8[1] = -1000; - for (i = 0; i < 32; ++i) - ovector8_1[i] = -2; - for (i = 0; i < 32; ++i) - ovector8_2[i] = -2; - if (re8) { - mark8_1 = NULL; - mark8_2 = NULL; - extra8->mark = &mark8_1; - - if ((counter & 0x1) != 0) { - setstack8(extra8); - return_value8[0] = pcre_exec(re8, extra8, current->input, strlen(current->input), current->start_offset & OFFSET_MASK, - current->flags & (PCRE_NOTBOL | PCRE_NOTEOL | PCRE_NOTEMPTY | PCRE_NOTEMPTY_ATSTART | PCRE_PARTIAL_SOFT | PCRE_PARTIAL_HARD | PCRE_NO_UTF8_CHECK), ovector8_1, 32); - } else - return_value8[0] = pcre_jit_exec(re8, extra8, current->input, strlen(current->input), current->start_offset & OFFSET_MASK, - current->flags & (PCRE_NOTBOL | PCRE_NOTEOL | PCRE_NOTEMPTY | PCRE_NOTEMPTY_ATSTART | PCRE_PARTIAL_SOFT | PCRE_PARTIAL_HARD | PCRE_NO_UTF8_CHECK), ovector8_1, 32, getstack8()); - memset(&dummy_extra8, 0, sizeof(pcre_extra)); - dummy_extra8.flags = PCRE_EXTRA_MARK; - if (current->start_offset & F_STUDY) { - dummy_extra8.flags |= PCRE_EXTRA_STUDY_DATA; - dummy_extra8.study_data = extra8->study_data; - } - dummy_extra8.mark = &mark8_2; - return_value8[1] = pcre_exec(re8, &dummy_extra8, current->input, strlen(current->input), current->start_offset & OFFSET_MASK, - current->flags & (PCRE_NOTBOL | PCRE_NOTEOL | PCRE_NOTEMPTY | PCRE_NOTEMPTY_ATSTART | PCRE_PARTIAL_SOFT | PCRE_PARTIAL_HARD | PCRE_NO_UTF8_CHECK), ovector8_2, 32); - } -#endif - -#ifdef SUPPORT_PCRE16 - return_value16[0] = -1000; - return_value16[1] = -1000; - for (i = 0; i < 32; ++i) - ovector16_1[i] = -2; - for (i = 0; i < 32; ++i) - ovector16_2[i] = -2; - if (re16) { - mark16_1 = NULL; - mark16_2 = NULL; - if ((current->flags & PCRE_UTF16) || (current->start_offset & F_FORCECONV)) - length16 = convert_utf8_to_utf16(current->input, regtest_buf16, regtest_offsetmap16, REGTEST_MAX_LENGTH16); - else - length16 = copy_char8_to_char16(current->input, regtest_buf16, REGTEST_MAX_LENGTH16); - extra16->mark = &mark16_1; - if ((counter & 0x1) != 0) { - setstack16(extra16); - return_value16[0] = pcre16_exec(re16, extra16, regtest_buf16, length16, current->start_offset & OFFSET_MASK, - current->flags & (PCRE_NOTBOL | PCRE_NOTEOL | PCRE_NOTEMPTY | PCRE_NOTEMPTY_ATSTART | PCRE_PARTIAL_SOFT | PCRE_PARTIAL_HARD | PCRE_NO_UTF8_CHECK), ovector16_1, 32); - } else - return_value16[0] = pcre16_jit_exec(re16, extra16, regtest_buf16, length16, current->start_offset & OFFSET_MASK, - current->flags & (PCRE_NOTBOL | PCRE_NOTEOL | PCRE_NOTEMPTY | PCRE_NOTEMPTY_ATSTART | PCRE_PARTIAL_SOFT | PCRE_PARTIAL_HARD | PCRE_NO_UTF8_CHECK), ovector16_1, 32, getstack16()); - memset(&dummy_extra16, 0, sizeof(pcre16_extra)); - dummy_extra16.flags = PCRE_EXTRA_MARK; - if (current->start_offset & F_STUDY) { - dummy_extra16.flags |= PCRE_EXTRA_STUDY_DATA; - dummy_extra16.study_data = extra16->study_data; - } - dummy_extra16.mark = &mark16_2; - return_value16[1] = pcre16_exec(re16, &dummy_extra16, regtest_buf16, length16, current->start_offset & OFFSET_MASK, - current->flags & (PCRE_NOTBOL | PCRE_NOTEOL | PCRE_NOTEMPTY | PCRE_NOTEMPTY_ATSTART | PCRE_PARTIAL_SOFT | PCRE_PARTIAL_HARD | PCRE_NO_UTF8_CHECK), ovector16_2, 32); - } -#endif - -#ifdef SUPPORT_PCRE32 - return_value32[0] = -1000; - return_value32[1] = -1000; - for (i = 0; i < 32; ++i) - ovector32_1[i] = -2; - for (i = 0; i < 32; ++i) - ovector32_2[i] = -2; - if (re32) { - mark32_1 = NULL; - mark32_2 = NULL; - if ((current->flags & PCRE_UTF32) || (current->start_offset & F_FORCECONV)) - length32 = convert_utf8_to_utf32(current->input, regtest_buf32, regtest_offsetmap32, REGTEST_MAX_LENGTH32); - else - length32 = copy_char8_to_char32(current->input, regtest_buf32, REGTEST_MAX_LENGTH32); - extra32->mark = &mark32_1; - if ((counter & 0x1) != 0) { - setstack32(extra32); - return_value32[0] = pcre32_exec(re32, extra32, regtest_buf32, length32, current->start_offset & OFFSET_MASK, - current->flags & (PCRE_NOTBOL | PCRE_NOTEOL | PCRE_NOTEMPTY | PCRE_NOTEMPTY_ATSTART | PCRE_PARTIAL_SOFT | PCRE_PARTIAL_HARD | PCRE_NO_UTF8_CHECK), ovector32_1, 32); - } else - return_value32[0] = pcre32_jit_exec(re32, extra32, regtest_buf32, length32, current->start_offset & OFFSET_MASK, - current->flags & (PCRE_NOTBOL | PCRE_NOTEOL | PCRE_NOTEMPTY | PCRE_NOTEMPTY_ATSTART | PCRE_PARTIAL_SOFT | PCRE_PARTIAL_HARD | PCRE_NO_UTF8_CHECK), ovector32_1, 32, getstack32()); - memset(&dummy_extra32, 0, sizeof(pcre32_extra)); - dummy_extra32.flags = PCRE_EXTRA_MARK; - if (current->start_offset & F_STUDY) { - dummy_extra32.flags |= PCRE_EXTRA_STUDY_DATA; - dummy_extra32.study_data = extra32->study_data; - } - dummy_extra32.mark = &mark32_2; - return_value32[1] = pcre32_exec(re32, &dummy_extra32, regtest_buf32, length32, current->start_offset & OFFSET_MASK, - current->flags & (PCRE_NOTBOL | PCRE_NOTEOL | PCRE_NOTEMPTY | PCRE_NOTEMPTY_ATSTART | PCRE_PARTIAL_SOFT | PCRE_PARTIAL_HARD | PCRE_NO_UTF8_CHECK), ovector32_2, 32); - } -#endif - - /* printf("[%d-%d-%d|%d-%d|%d-%d|%d-%d]%s", - return_value8[0], return_value16[0], return_value32[0], - ovector8_1[0], ovector8_1[1], - ovector16_1[0], ovector16_1[1], - ovector32_1[0], ovector32_1[1], - (current->flags & PCRE_CASELESS) ? "C" : ""); */ - - /* If F_DIFF is set, just run the test, but do not compare the results. - Segfaults can still be captured. */ - - is_successful = 1; - if (!(current->start_offset & F_DIFF)) { -#if defined SUPPORT_UTF && ((defined(SUPPORT_PCRE8) + defined(SUPPORT_PCRE16) + defined(SUPPORT_PCRE32)) >= 2) - if (!(current->start_offset & F_FORCECONV)) { - int return_value; - - /* All results must be the same. */ -#ifdef SUPPORT_PCRE8 - if ((return_value = return_value8[0]) != return_value8[1]) { - printf("\n8 bit: Return value differs(J8:%d,I8:%d): [%d] '%s' @ '%s'\n", - return_value8[0], return_value8[1], total, current->pattern, current->input); - is_successful = 0; - } else -#endif -#ifdef SUPPORT_PCRE16 - if ((return_value = return_value16[0]) != return_value16[1]) { - printf("\n16 bit: Return value differs(J16:%d,I16:%d): [%d] '%s' @ '%s'\n", - return_value16[0], return_value16[1], total, current->pattern, current->input); - is_successful = 0; - } else -#endif -#ifdef SUPPORT_PCRE32 - if ((return_value = return_value32[0]) != return_value32[1]) { - printf("\n32 bit: Return value differs(J32:%d,I32:%d): [%d] '%s' @ '%s'\n", - return_value32[0], return_value32[1], total, current->pattern, current->input); - is_successful = 0; - } else -#endif -#if defined SUPPORT_PCRE8 && defined SUPPORT_PCRE16 - if (return_value8[0] != return_value16[0]) { - printf("\n8 and 16 bit: Return value differs(J8:%d,J16:%d): [%d] '%s' @ '%s'\n", - return_value8[0], return_value16[0], - total, current->pattern, current->input); - is_successful = 0; - } else -#endif -#if defined SUPPORT_PCRE8 && defined SUPPORT_PCRE32 - if (return_value8[0] != return_value32[0]) { - printf("\n8 and 32 bit: Return value differs(J8:%d,J32:%d): [%d] '%s' @ '%s'\n", - return_value8[0], return_value32[0], - total, current->pattern, current->input); - is_successful = 0; - } else -#endif -#if defined SUPPORT_PCRE16 && defined SUPPORT_PCRE32 - if (return_value16[0] != return_value32[0]) { - printf("\n16 and 32 bit: Return value differs(J16:%d,J32:%d): [%d] '%s' @ '%s'\n", - return_value16[0], return_value32[0], - total, current->pattern, current->input); - is_successful = 0; - } else -#endif - if (return_value >= 0 || return_value == PCRE_ERROR_PARTIAL) { - if (return_value == PCRE_ERROR_PARTIAL) { - return_value = 2; - } else { - return_value *= 2; - } -#ifdef SUPPORT_PCRE8 - return_value8[0] = return_value; -#endif -#ifdef SUPPORT_PCRE16 - return_value16[0] = return_value; -#endif -#ifdef SUPPORT_PCRE32 - return_value32[0] = return_value; -#endif - /* Transform back the results. */ - if (current->flags & PCRE_UTF8) { -#ifdef SUPPORT_PCRE16 - for (i = 0; i < return_value; ++i) { - if (ovector16_1[i] >= 0) - ovector16_1[i] = regtest_offsetmap16[ovector16_1[i]]; - if (ovector16_2[i] >= 0) - ovector16_2[i] = regtest_offsetmap16[ovector16_2[i]]; - } -#endif -#ifdef SUPPORT_PCRE32 - for (i = 0; i < return_value; ++i) { - if (ovector32_1[i] >= 0) - ovector32_1[i] = regtest_offsetmap32[ovector32_1[i]]; - if (ovector32_2[i] >= 0) - ovector32_2[i] = regtest_offsetmap32[ovector32_2[i]]; - } -#endif - } - - for (i = 0; i < return_value; ++i) { -#if defined SUPPORT_PCRE8 && defined SUPPORT_PCRE16 - if (ovector8_1[i] != ovector8_2[i] || ovector8_1[i] != ovector16_1[i] || ovector8_1[i] != ovector16_2[i]) { - printf("\n8 and 16 bit: Ovector[%d] value differs(J8:%d,I8:%d,J16:%d,I16:%d): [%d] '%s' @ '%s' \n", - i, ovector8_1[i], ovector8_2[i], ovector16_1[i], ovector16_2[i], - total, current->pattern, current->input); - is_successful = 0; - } -#endif -#if defined SUPPORT_PCRE8 && defined SUPPORT_PCRE32 - if (ovector8_1[i] != ovector8_2[i] || ovector8_1[i] != ovector32_1[i] || ovector8_1[i] != ovector32_2[i]) { - printf("\n8 and 32 bit: Ovector[%d] value differs(J8:%d,I8:%d,J32:%d,I32:%d): [%d] '%s' @ '%s' \n", - i, ovector8_1[i], ovector8_2[i], ovector32_1[i], ovector32_2[i], - total, current->pattern, current->input); - is_successful = 0; - } -#endif -#if defined SUPPORT_PCRE16 && defined SUPPORT_PCRE16 - if (ovector16_1[i] != ovector16_2[i] || ovector16_1[i] != ovector16_1[i] || ovector16_1[i] != ovector16_2[i]) { - printf("\n16 and 16 bit: Ovector[%d] value differs(J16:%d,I16:%d,J32:%d,I32:%d): [%d] '%s' @ '%s' \n", - i, ovector16_1[i], ovector16_2[i], ovector16_1[i], ovector16_2[i], - total, current->pattern, current->input); - is_successful = 0; - } -#endif - } - } - } else -#endif /* more than one of SUPPORT_PCRE8, SUPPORT_PCRE16 and SUPPORT_PCRE32 */ - { - /* Only the 8 bit and 16 bit results must be equal. */ -#ifdef SUPPORT_PCRE8 - if (return_value8[0] != return_value8[1]) { - printf("\n8 bit: Return value differs(%d:%d): [%d] '%s' @ '%s'\n", - return_value8[0], return_value8[1], total, current->pattern, current->input); - is_successful = 0; - } else if (return_value8[0] >= 0 || return_value8[0] == PCRE_ERROR_PARTIAL) { - if (return_value8[0] == PCRE_ERROR_PARTIAL) - return_value8[0] = 2; - else - return_value8[0] *= 2; - - for (i = 0; i < return_value8[0]; ++i) - if (ovector8_1[i] != ovector8_2[i]) { - printf("\n8 bit: Ovector[%d] value differs(%d:%d): [%d] '%s' @ '%s'\n", - i, ovector8_1[i], ovector8_2[i], total, current->pattern, current->input); - is_successful = 0; - } - } -#endif - -#ifdef SUPPORT_PCRE16 - if (return_value16[0] != return_value16[1]) { - printf("\n16 bit: Return value differs(%d:%d): [%d] '%s' @ '%s'\n", - return_value16[0], return_value16[1], total, current->pattern, current->input); - is_successful = 0; - } else if (return_value16[0] >= 0 || return_value16[0] == PCRE_ERROR_PARTIAL) { - if (return_value16[0] == PCRE_ERROR_PARTIAL) - return_value16[0] = 2; - else - return_value16[0] *= 2; - - for (i = 0; i < return_value16[0]; ++i) - if (ovector16_1[i] != ovector16_2[i]) { - printf("\n16 bit: Ovector[%d] value differs(%d:%d): [%d] '%s' @ '%s'\n", - i, ovector16_1[i], ovector16_2[i], total, current->pattern, current->input); - is_successful = 0; - } - } -#endif - -#ifdef SUPPORT_PCRE32 - if (return_value32[0] != return_value32[1]) { - printf("\n32 bit: Return value differs(%d:%d): [%d] '%s' @ '%s'\n", - return_value32[0], return_value32[1], total, current->pattern, current->input); - is_successful = 0; - } else if (return_value32[0] >= 0 || return_value32[0] == PCRE_ERROR_PARTIAL) { - if (return_value32[0] == PCRE_ERROR_PARTIAL) - return_value32[0] = 2; - else - return_value32[0] *= 2; - - for (i = 0; i < return_value32[0]; ++i) - if (ovector32_1[i] != ovector32_2[i]) { - printf("\n32 bit: Ovector[%d] value differs(%d:%d): [%d] '%s' @ '%s'\n", - i, ovector32_1[i], ovector32_2[i], total, current->pattern, current->input); - is_successful = 0; - } - } -#endif - } - } - - if (is_successful) { -#ifdef SUPPORT_PCRE8 - if (!(current->start_offset & F_NO8) && ((utf && ucp) || is_ascii)) { - if (return_value8[0] < 0 && !(current->start_offset & F_NOMATCH)) { - printf("8 bit: Test should match: [%d] '%s' @ '%s'\n", - total, current->pattern, current->input); - is_successful = 0; - } - - if (return_value8[0] >= 0 && (current->start_offset & F_NOMATCH)) { - printf("8 bit: Test should not match: [%d] '%s' @ '%s'\n", - total, current->pattern, current->input); - is_successful = 0; - } - } -#endif -#ifdef SUPPORT_PCRE16 - if (!(current->start_offset & F_NO16) && ((utf && ucp) || is_ascii)) { - if (return_value16[0] < 0 && !(current->start_offset & F_NOMATCH)) { - printf("16 bit: Test should match: [%d] '%s' @ '%s'\n", - total, current->pattern, current->input); - is_successful = 0; - } - - if (return_value16[0] >= 0 && (current->start_offset & F_NOMATCH)) { - printf("16 bit: Test should not match: [%d] '%s' @ '%s'\n", - total, current->pattern, current->input); - is_successful = 0; - } - } -#endif -#ifdef SUPPORT_PCRE32 - if (!(current->start_offset & F_NO32) && ((utf && ucp) || is_ascii)) { - if (return_value32[0] < 0 && !(current->start_offset & F_NOMATCH)) { - printf("32 bit: Test should match: [%d] '%s' @ '%s'\n", - total, current->pattern, current->input); - is_successful = 0; - } - - if (return_value32[0] >= 0 && (current->start_offset & F_NOMATCH)) { - printf("32 bit: Test should not match: [%d] '%s' @ '%s'\n", - total, current->pattern, current->input); - is_successful = 0; - } - } -#endif - } - - if (is_successful) { -#ifdef SUPPORT_PCRE8 - if (mark8_1 != mark8_2) { - printf("8 bit: Mark value mismatch: [%d] '%s' @ '%s'\n", - total, current->pattern, current->input); - is_successful = 0; - } -#endif -#ifdef SUPPORT_PCRE16 - if (mark16_1 != mark16_2) { - printf("16 bit: Mark value mismatch: [%d] '%s' @ '%s'\n", - total, current->pattern, current->input); - is_successful = 0; - } -#endif -#ifdef SUPPORT_PCRE32 - if (mark32_1 != mark32_2) { - printf("32 bit: Mark value mismatch: [%d] '%s' @ '%s'\n", - total, current->pattern, current->input); - is_successful = 0; - } -#endif - } - -#ifdef SUPPORT_PCRE8 - if (re8) { - pcre_free_study(extra8); - pcre_free(re8); - } -#endif -#ifdef SUPPORT_PCRE16 - if (re16) { - pcre16_free_study(extra16); - pcre16_free(re16); - } -#endif -#ifdef SUPPORT_PCRE32 - if (re32) { - pcre32_free_study(extra32); - pcre32_free(re32); - } -#endif - - if (is_successful) { - successful++; - successful_row++; - printf("."); - if (successful_row >= 60) { - successful_row = 0; - printf("\n"); - } - } else - successful_row = 0; - - fflush(stdout); - current++; - } - tables(1); -#ifdef SUPPORT_PCRE8 - setstack8(NULL); -#endif -#ifdef SUPPORT_PCRE16 - setstack16(NULL); -#endif -#ifdef SUPPORT_PCRE32 - setstack32(NULL); -#endif - - if (total == successful) { - printf("\nAll JIT regression tests are successfully passed.\n"); - return 0; - } else { - printf("\nSuccessful test ratio: %d%% (%d failed)\n", successful * 100 / total, total - successful); - return 1; - } -} - -/* End of pcre_jit_test.c */ diff --git a/src/third_party/pcre-8.38/pcre_maketables.c b/src/third_party/pcre-8.38/pcre_maketables.c deleted file mode 100644 index a44a6eaa905..00000000000 --- a/src/third_party/pcre-8.38/pcre_maketables.c +++ /dev/null @@ -1,156 +0,0 @@ -/************************************************* -* Perl-Compatible Regular Expressions * -*************************************************/ - -/* PCRE is a library of functions to support regular expressions whose syntax -and semantics are as close as possible to those of the Perl 5 language. - - Written by Philip Hazel - Copyright (c) 1997-2012 University of Cambridge - ------------------------------------------------------------------------------ -Redistribution and use in source and binary forms, with or without -modification, are permitted provided that the following conditions are met: - - * Redistributions of source code must retain the above copyright notice, - this list of conditions and the following disclaimer. - - * Redistributions in binary form must reproduce the above copyright - notice, this list of conditions and the following disclaimer in the - documentation and/or other materials provided with the distribution. - - * Neither the name of the University of Cambridge nor the names of its - contributors may be used to endorse or promote products derived from - this software without specific prior written permission. - -THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS" -AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE -IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE -ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR CONTRIBUTORS BE -LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR -CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF -SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS -INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN -CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) -ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE -POSSIBILITY OF SUCH DAMAGE. ------------------------------------------------------------------------------ -*/ - - -/* This module contains the external function pcre_maketables(), which builds -character tables for PCRE in the current locale. The file is compiled on its -own as part of the PCRE library. However, it is also included in the -compilation of dftables.c, in which case the macro DFTABLES is defined. */ - - -#ifndef DFTABLES -# ifdef HAVE_CONFIG_H -# include "config.h" -# endif -# include "pcre_internal.h" -#endif - - -/************************************************* -* Create PCRE character tables * -*************************************************/ - -/* This function builds a set of character tables for use by PCRE and returns -a pointer to them. They are build using the ctype functions, and consequently -their contents will depend upon the current locale setting. When compiled as -part of the library, the store is obtained via PUBL(malloc)(), but when -compiled inside dftables, use malloc(). - -Arguments: none -Returns: pointer to the contiguous block of data -*/ - -#if defined COMPILE_PCRE8 -const unsigned char * -pcre_maketables(void) -#elif defined COMPILE_PCRE16 -const unsigned char * -pcre16_maketables(void) -#elif defined COMPILE_PCRE32 -const unsigned char * -pcre32_maketables(void) -#endif -{ -unsigned char *yield, *p; -int i; - -#ifndef DFTABLES -yield = (unsigned char*)(PUBL(malloc))(tables_length); -#else -yield = (unsigned char*)malloc(tables_length); -#endif - -if (yield == NULL) return NULL; -p = yield; - -/* First comes the lower casing table */ - -for (i = 0; i < 256; i++) *p++ = tolower(i); - -/* Next the case-flipping table */ - -for (i = 0; i < 256; i++) *p++ = islower(i)? toupper(i) : tolower(i); - -/* Then the character class tables. Don't try to be clever and save effort on -exclusive ones - in some locales things may be different. - -Note that the table for "space" includes everything "isspace" gives, including -VT in the default locale. This makes it work for the POSIX class [:space:]. -From release 8.34 is is also correct for Perl space, because Perl added VT at -release 5.18. - -Note also that it is possible for a character to be alnum or alpha without -being lower or upper, such as "male and female ordinals" (\xAA and \xBA) in the -fr_FR locale (at least under Debian Linux's locales as of 12/2005). So we must -test for alnum specially. */ - -memset(p, 0, cbit_length); -for (i = 0; i < 256; i++) - { - if (isdigit(i)) p[cbit_digit + i/8] |= 1 << (i&7); - if (isupper(i)) p[cbit_upper + i/8] |= 1 << (i&7); - if (islower(i)) p[cbit_lower + i/8] |= 1 << (i&7); - if (isalnum(i)) p[cbit_word + i/8] |= 1 << (i&7); - if (i == '_') p[cbit_word + i/8] |= 1 << (i&7); - if (isspace(i)) p[cbit_space + i/8] |= 1 << (i&7); - if (isxdigit(i))p[cbit_xdigit + i/8] |= 1 << (i&7); - if (isgraph(i)) p[cbit_graph + i/8] |= 1 << (i&7); - if (isprint(i)) p[cbit_print + i/8] |= 1 << (i&7); - if (ispunct(i)) p[cbit_punct + i/8] |= 1 << (i&7); - if (iscntrl(i)) p[cbit_cntrl + i/8] |= 1 << (i&7); - } -p += cbit_length; - -/* Finally, the character type table. In this, we used to exclude VT from the -white space chars, because Perl didn't recognize it as such for \s and for -comments within regexes. However, Perl changed at release 5.18, so PCRE changed -at release 8.34. */ - -for (i = 0; i < 256; i++) - { - int x = 0; - if (isspace(i)) x += ctype_space; - if (isalpha(i)) x += ctype_letter; - if (isdigit(i)) x += ctype_digit; - if (isxdigit(i)) x += ctype_xdigit; - if (isalnum(i) || i == '_') x += ctype_word; - - /* Note: strchr includes the terminating zero in the characters it considers. - In this instance, that is ok because we want binary zero to be flagged as a - meta-character, which in this sense is any character that terminates a run - of data characters. */ - - if (strchr("\\*+?{^.$|()[", i) != 0) x += ctype_meta; - *p++ = x; - } - -return yield; -} - -/* End of pcre_maketables.c */ diff --git a/src/third_party/pcre-8.38/pcre_newline.c b/src/third_party/pcre-8.38/pcre_newline.c deleted file mode 100644 index b8f5a4de19c..00000000000 --- a/src/third_party/pcre-8.38/pcre_newline.c +++ /dev/null @@ -1,210 +0,0 @@ -/************************************************* -* Perl-Compatible Regular Expressions * -*************************************************/ - -/* PCRE is a library of functions to support regular expressions whose syntax -and semantics are as close as possible to those of the Perl 5 language. - - Written by Philip Hazel - Copyright (c) 1997-2012 University of Cambridge - ------------------------------------------------------------------------------ -Redistribution and use in source and binary forms, with or without -modification, are permitted provided that the following conditions are met: - - * Redistributions of source code must retain the above copyright notice, - this list of conditions and the following disclaimer. - - * Redistributions in binary form must reproduce the above copyright - notice, this list of conditions and the following disclaimer in the - documentation and/or other materials provided with the distribution. - - * Neither the name of the University of Cambridge nor the names of its - contributors may be used to endorse or promote products derived from - this software without specific prior written permission. - -THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS" -AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE -IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE -ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR CONTRIBUTORS BE -LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR -CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF -SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS -INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN -CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) -ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE -POSSIBILITY OF SUCH DAMAGE. ------------------------------------------------------------------------------ -*/ - - -/* This module contains internal functions for testing newlines when more than -one kind of newline is to be recognized. When a newline is found, its length is -returned. In principle, we could implement several newline "types", each -referring to a different set of newline characters. At present, PCRE supports -only NLTYPE_FIXED, which gets handled without these functions, NLTYPE_ANYCRLF, -and NLTYPE_ANY. The full list of Unicode newline characters is taken from -http://unicode.org/unicode/reports/tr18/. */ - - -#ifdef HAVE_CONFIG_H -#include "config.h" -#endif - -#include "pcre_internal.h" - - - -/************************************************* -* Check for newline at given position * -*************************************************/ - -/* It is guaranteed that the initial value of ptr is less than the end of the -string that is being processed. - -Arguments: - ptr pointer to possible newline - type the newline type - endptr pointer to the end of the string - lenptr where to return the length - utf TRUE if in utf mode - -Returns: TRUE or FALSE -*/ - -BOOL -PRIV(is_newline)(PCRE_PUCHAR ptr, int type, PCRE_PUCHAR endptr, int *lenptr, - BOOL utf) -{ -pcre_uint32 c; -(void)utf; -#ifdef SUPPORT_UTF -if (utf) - { - GETCHAR(c, ptr); - } -else -#endif /* SUPPORT_UTF */ - c = *ptr; - -/* Note that this function is called only for ANY or ANYCRLF. */ - -if (type == NLTYPE_ANYCRLF) switch(c) - { - case CHAR_LF: *lenptr = 1; return TRUE; - case CHAR_CR: *lenptr = (ptr < endptr - 1 && ptr[1] == CHAR_LF)? 2 : 1; - return TRUE; - default: return FALSE; - } - -/* NLTYPE_ANY */ - -else switch(c) - { -#ifdef EBCDIC - case CHAR_NEL: -#endif - case CHAR_LF: - case CHAR_VT: - case CHAR_FF: *lenptr = 1; return TRUE; - - case CHAR_CR: - *lenptr = (ptr < endptr - 1 && ptr[1] == CHAR_LF)? 2 : 1; - return TRUE; - -#ifndef EBCDIC -#ifdef COMPILE_PCRE8 - case CHAR_NEL: *lenptr = utf? 2 : 1; return TRUE; - case 0x2028: /* LS */ - case 0x2029: *lenptr = 3; return TRUE; /* PS */ -#else /* COMPILE_PCRE16 || COMPILE_PCRE32 */ - case CHAR_NEL: - case 0x2028: /* LS */ - case 0x2029: *lenptr = 1; return TRUE; /* PS */ -#endif /* COMPILE_PCRE8 */ -#endif /* Not EBCDIC */ - - default: return FALSE; - } -} - - - -/************************************************* -* Check for newline at previous position * -*************************************************/ - -/* It is guaranteed that the initial value of ptr is greater than the start of -the string that is being processed. - -Arguments: - ptr pointer to possible newline - type the newline type - startptr pointer to the start of the string - lenptr where to return the length - utf TRUE if in utf mode - -Returns: TRUE or FALSE -*/ - -BOOL -PRIV(was_newline)(PCRE_PUCHAR ptr, int type, PCRE_PUCHAR startptr, int *lenptr, - BOOL utf) -{ -pcre_uint32 c; -(void)utf; -ptr--; -#ifdef SUPPORT_UTF -if (utf) - { - BACKCHAR(ptr); - GETCHAR(c, ptr); - } -else -#endif /* SUPPORT_UTF */ - c = *ptr; - -/* Note that this function is called only for ANY or ANYCRLF. */ - -if (type == NLTYPE_ANYCRLF) switch(c) - { - case CHAR_LF: - *lenptr = (ptr > startptr && ptr[-1] == CHAR_CR)? 2 : 1; - return TRUE; - - case CHAR_CR: *lenptr = 1; return TRUE; - default: return FALSE; - } - -/* NLTYPE_ANY */ - -else switch(c) - { - case CHAR_LF: - *lenptr = (ptr > startptr && ptr[-1] == CHAR_CR)? 2 : 1; - return TRUE; - -#ifdef EBCDIC - case CHAR_NEL: -#endif - case CHAR_VT: - case CHAR_FF: - case CHAR_CR: *lenptr = 1; return TRUE; - -#ifndef EBCDIC -#ifdef COMPILE_PCRE8 - case CHAR_NEL: *lenptr = utf? 2 : 1; return TRUE; - case 0x2028: /* LS */ - case 0x2029: *lenptr = 3; return TRUE; /* PS */ -#else /* COMPILE_PCRE16 || COMPILE_PCRE32 */ - case CHAR_NEL: - case 0x2028: /* LS */ - case 0x2029: *lenptr = 1; return TRUE; /* PS */ -#endif /* COMPILE_PCRE8 */ -#endif /* NotEBCDIC */ - - default: return FALSE; - } -} - -/* End of pcre_newline.c */ diff --git a/src/third_party/pcre-8.38/pcre_ord2utf8.c b/src/third_party/pcre-8.38/pcre_ord2utf8.c deleted file mode 100644 index 95f1beb963e..00000000000 --- a/src/third_party/pcre-8.38/pcre_ord2utf8.c +++ /dev/null @@ -1,94 +0,0 @@ -/************************************************* -* Perl-Compatible Regular Expressions * -*************************************************/ - -/* PCRE is a library of functions to support regular expressions whose syntax -and semantics are as close as possible to those of the Perl 5 language. - - Written by Philip Hazel - Copyright (c) 1997-2012 University of Cambridge - ------------------------------------------------------------------------------ -Redistribution and use in source and binary forms, with or without -modification, are permitted provided that the following conditions are met: - - * Redistributions of source code must retain the above copyright notice, - this list of conditions and the following disclaimer. - - * Redistributions in binary form must reproduce the above copyright - notice, this list of conditions and the following disclaimer in the - documentation and/or other materials provided with the distribution. - - * Neither the name of the University of Cambridge nor the names of its - contributors may be used to endorse or promote products derived from - this software without specific prior written permission. - -THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS" -AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE -IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE -ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR CONTRIBUTORS BE -LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR -CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF -SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS -INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN -CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) -ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE -POSSIBILITY OF SUCH DAMAGE. ------------------------------------------------------------------------------ -*/ - - -/* This file contains a private PCRE function that converts an ordinal -character value into a UTF8 string. */ - -#ifdef HAVE_CONFIG_H -#include "config.h" -#endif - -#define COMPILE_PCRE8 - -#include "pcre_internal.h" - -/************************************************* -* Convert character value to UTF-8 * -*************************************************/ - -/* This function takes an integer value in the range 0 - 0x10ffff -and encodes it as a UTF-8 character in 1 to 4 pcre_uchars. - -Arguments: - cvalue the character value - buffer pointer to buffer for result - at least 6 pcre_uchars long - -Returns: number of characters placed in the buffer -*/ - -unsigned -int -PRIV(ord2utf)(pcre_uint32 cvalue, pcre_uchar *buffer) -{ -#ifdef SUPPORT_UTF - -register int i, j; - -for (i = 0; i < PRIV(utf8_table1_size); i++) - if ((int)cvalue <= PRIV(utf8_table1)[i]) break; -buffer += i; -for (j = i; j > 0; j--) - { - *buffer-- = 0x80 | (cvalue & 0x3f); - cvalue >>= 6; - } -*buffer = PRIV(utf8_table2)[i] | cvalue; -return i + 1; - -#else - -(void)(cvalue); /* Keep compiler happy; this function won't ever be */ -(void)(buffer); /* called when SUPPORT_UTF is not defined. */ -return 0; - -#endif -} - -/* End of pcre_ord2utf8.c */ diff --git a/src/third_party/pcre-8.38/pcre_printint.c b/src/third_party/pcre-8.38/pcre_printint.c deleted file mode 100644 index 60dcb55efbf..00000000000 --- a/src/third_party/pcre-8.38/pcre_printint.c +++ /dev/null @@ -1,834 +0,0 @@ -/************************************************* -* Perl-Compatible Regular Expressions * -*************************************************/ - -/* PCRE is a library of functions to support regular expressions whose syntax -and semantics are as close as possible to those of the Perl 5 language. - - Written by Philip Hazel - Copyright (c) 1997-2012 University of Cambridge - ------------------------------------------------------------------------------ -Redistribution and use in source and binary forms, with or without -modification, are permitted provided that the following conditions are met: - - * Redistributions of source code must retain the above copyright notice, - this list of conditions and the following disclaimer. - - * Redistributions in binary form must reproduce the above copyright - notice, this list of conditions and the following disclaimer in the - documentation and/or other materials provided with the distribution. - - * Neither the name of the University of Cambridge nor the names of its - contributors may be used to endorse or promote products derived from - this software without specific prior written permission. - -THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS" -AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE -IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE -ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR CONTRIBUTORS BE -LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR -CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF -SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS -INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN -CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) -ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE -POSSIBILITY OF SUCH DAMAGE. ------------------------------------------------------------------------------ -*/ - - -/* This module contains a PCRE private debugging function for printing out the -internal form of a compiled regular expression, along with some supporting -local functions. This source file is used in two places: - -(1) It is #included by pcre_compile.c when it is compiled in debugging mode -(PCRE_DEBUG defined in pcre_internal.h). It is not included in production -compiles. In this case PCRE_INCLUDED is defined. - -(2) It is also compiled separately and linked with pcretest.c, which can be -asked to print out a compiled regex for debugging purposes. */ - -#ifndef PCRE_INCLUDED - -#ifdef HAVE_CONFIG_H -#include "config.h" -#endif - -/* For pcretest program. */ -#define PRIV(name) name - -/* We have to include pcre_internal.h because we need the internal info for -displaying the results of pcre_study() and we also need to know about the -internal macros, structures, and other internal data values; pcretest has -"inside information" compared to a program that strictly follows the PCRE API. - -Although pcre_internal.h does itself include pcre.h, we explicitly include it -here before pcre_internal.h so that the PCRE_EXP_xxx macros get set -appropriately for an application, not for building PCRE. */ - -#include "pcre.h" -#include "pcre_internal.h" - -/* These are the funtions that are contained within. It doesn't seem worth -having a separate .h file just for this. */ - -#endif /* PCRE_INCLUDED */ - -#ifdef PCRE_INCLUDED -static /* Keep the following function as private. */ -#endif - -#if defined COMPILE_PCRE8 -void pcre_printint(pcre *external_re, FILE *f, BOOL print_lengths); -#elif defined COMPILE_PCRE16 -void pcre16_printint(pcre *external_re, FILE *f, BOOL print_lengths); -#elif defined COMPILE_PCRE32 -void pcre32_printint(pcre *external_re, FILE *f, BOOL print_lengths); -#endif - -/* Macro that decides whether a character should be output as a literal or in -hexadecimal. We don't use isprint() because that can vary from system to system -(even without the use of locales) and we want the output always to be the same, -for testing purposes. */ - -#ifdef EBCDIC -#define PRINTABLE(c) ((c) >= 64 && (c) < 255) -#else -#define PRINTABLE(c) ((c) >= 32 && (c) < 127) -#endif - -/* The table of operator names. */ - -static const char *priv_OP_names[] = { OP_NAME_LIST }; - -/* This table of operator lengths is not actually used by the working code, -but its size is needed for a check that ensures it is the correct size for the -number of opcodes (thus catching update omissions). */ - -static const pcre_uint8 priv_OP_lengths[] = { OP_LENGTHS }; - - - -/************************************************* -* Print single- or multi-byte character * -*************************************************/ - -static unsigned int -print_char(FILE *f, pcre_uchar *ptr, BOOL utf) -{ -pcre_uint32 c = *ptr; - -#ifndef SUPPORT_UTF - -(void)utf; /* Avoid compiler warning */ -if (PRINTABLE(c)) fprintf(f, "%c", (char)c); -else if (c <= 0x80) fprintf(f, "\\x%02x", c); -else fprintf(f, "\\x{%x}", c); -return 0; - -#else - -#if defined COMPILE_PCRE8 - -if (!utf || (c & 0xc0) != 0xc0) - { - if (PRINTABLE(c)) fprintf(f, "%c", (char)c); - else if (c < 0x80) fprintf(f, "\\x%02x", c); - else fprintf(f, "\\x{%02x}", c); - return 0; - } -else - { - int i; - int a = PRIV(utf8_table4)[c & 0x3f]; /* Number of additional bytes */ - int s = 6*a; - c = (c & PRIV(utf8_table3)[a]) << s; - for (i = 1; i <= a; i++) - { - /* This is a check for malformed UTF-8; it should only occur if the sanity - check has been turned off. Rather than swallow random bytes, just stop if - we hit a bad one. Print it with \X instead of \x as an indication. */ - - if ((ptr[i] & 0xc0) != 0x80) - { - fprintf(f, "\\X{%x}", c); - return i - 1; - } - - /* The byte is OK */ - - s -= 6; - c |= (ptr[i] & 0x3f) << s; - } - fprintf(f, "\\x{%x}", c); - return a; - } - -#elif defined COMPILE_PCRE16 - -if (!utf || (c & 0xfc00) != 0xd800) - { - if (PRINTABLE(c)) fprintf(f, "%c", (char)c); - else if (c <= 0x80) fprintf(f, "\\x%02x", c); - else fprintf(f, "\\x{%02x}", c); - return 0; - } -else - { - /* This is a check for malformed UTF-16; it should only occur if the sanity - check has been turned off. Rather than swallow a low surrogate, just stop if - we hit a bad one. Print it with \X instead of \x as an indication. */ - - if ((ptr[1] & 0xfc00) != 0xdc00) - { - fprintf(f, "\\X{%x}", c); - return 0; - } - - c = (((c & 0x3ff) << 10) | (ptr[1] & 0x3ff)) + 0x10000; - fprintf(f, "\\x{%x}", c); - return 1; - } - -#elif defined COMPILE_PCRE32 - -if (!utf || (c & 0xfffff800u) != 0xd800u) - { - if (PRINTABLE(c)) fprintf(f, "%c", (char)c); - else if (c <= 0x80) fprintf(f, "\\x%02x", c); - else fprintf(f, "\\x{%x}", c); - return 0; - } -else - { - /* This is a check for malformed UTF-32; it should only occur if the sanity - check has been turned off. Rather than swallow a surrogate, just stop if - we hit one. Print it with \X instead of \x as an indication. */ - fprintf(f, "\\X{%x}", c); - return 0; - } - -#endif /* COMPILE_PCRE[8|16|32] */ - -#endif /* SUPPORT_UTF */ -} - -/************************************************* -* Print uchar string (regardless of utf) * -*************************************************/ - -static void -print_puchar(FILE *f, PCRE_PUCHAR ptr) -{ -while (*ptr != '\0') - { - register pcre_uint32 c = *ptr++; - if (PRINTABLE(c)) fprintf(f, "%c", c); else fprintf(f, "\\x{%x}", c); - } -} - -/************************************************* -* Find Unicode property name * -*************************************************/ - -static const char * -get_ucpname(unsigned int ptype, unsigned int pvalue) -{ -#ifdef SUPPORT_UCP -int i; -for (i = PRIV(utt_size) - 1; i >= 0; i--) - { - if (ptype == PRIV(utt)[i].type && pvalue == PRIV(utt)[i].value) break; - } -return (i >= 0)? PRIV(utt_names) + PRIV(utt)[i].name_offset : "??"; -#else -/* It gets harder and harder to shut off unwanted compiler warnings. */ -ptype = ptype * pvalue; -return (ptype == pvalue)? "??" : "??"; -#endif -} - - -/************************************************* -* Print Unicode property value * -*************************************************/ - -/* "Normal" properties can be printed from tables. The PT_CLIST property is a -pseudo-property that contains a pointer to a list of case-equivalent -characters. This is used only when UCP support is available and UTF mode is -selected. It should never occur otherwise, but just in case it does, have -something ready to print. */ - -static void -print_prop(FILE *f, pcre_uchar *code, const char *before, const char *after) -{ -if (code[1] != PT_CLIST) - { - fprintf(f, "%s%s %s%s", before, priv_OP_names[*code], get_ucpname(code[1], - code[2]), after); - } -else - { - const char *not = (*code == OP_PROP)? "" : "not "; -#ifndef SUPPORT_UCP - fprintf(f, "%s%sclist %d%s", before, not, code[2], after); -#else - const pcre_uint32 *p = PRIV(ucd_caseless_sets) + code[2]; - fprintf (f, "%s%sclist", before, not); - while (*p < NOTACHAR) fprintf(f, " %04x", *p++); - fprintf(f, "%s", after); -#endif - } -} - - - - -/************************************************* -* Print compiled regex * -*************************************************/ - -/* Make this function work for a regex with integers either byte order. -However, we assume that what we are passed is a compiled regex. The -print_lengths flag controls whether offsets and lengths of items are printed. -They can be turned off from pcretest so that automatic tests on bytecode can be -written that do not depend on the value of LINK_SIZE. */ - -#ifdef PCRE_INCLUDED -static /* Keep the following function as private. */ -#endif -#if defined COMPILE_PCRE8 -void -pcre_printint(pcre *external_re, FILE *f, BOOL print_lengths) -#elif defined COMPILE_PCRE16 -void -pcre16_printint(pcre *external_re, FILE *f, BOOL print_lengths) -#elif defined COMPILE_PCRE32 -void -pcre32_printint(pcre *external_re, FILE *f, BOOL print_lengths) -#endif -{ -REAL_PCRE *re = (REAL_PCRE *)external_re; -pcre_uchar *codestart, *code; -BOOL utf; - -unsigned int options = re->options; -int offset = re->name_table_offset; -int count = re->name_count; -int size = re->name_entry_size; - -if (re->magic_number != MAGIC_NUMBER) - { - offset = ((offset << 8) & 0xff00) | ((offset >> 8) & 0xff); - count = ((count << 8) & 0xff00) | ((count >> 8) & 0xff); - size = ((size << 8) & 0xff00) | ((size >> 8) & 0xff); - options = ((options << 24) & 0xff000000) | - ((options << 8) & 0x00ff0000) | - ((options >> 8) & 0x0000ff00) | - ((options >> 24) & 0x000000ff); - } - -code = codestart = (pcre_uchar *)re + offset + count * size; -/* PCRE_UTF(16|32) have the same value as PCRE_UTF8. */ -utf = (options & PCRE_UTF8) != 0; - -for(;;) - { - pcre_uchar *ccode; - const char *flag = " "; - pcre_uint32 c; - unsigned int extra = 0; - - if (print_lengths) - fprintf(f, "%3d ", (int)(code - codestart)); - else - fprintf(f, " "); - - switch(*code) - { -/* ========================================================================== */ - /* These cases are never obeyed. This is a fudge that causes a compile- - time error if the vectors OP_names or OP_lengths, which are indexed - by opcode, are not the correct length. It seems to be the only way to do - such a check at compile time, as the sizeof() operator does not work in - the C preprocessor. */ - - case OP_TABLE_LENGTH: - case OP_TABLE_LENGTH + - ((sizeof(priv_OP_names)/sizeof(const char *) == OP_TABLE_LENGTH) && - (sizeof(priv_OP_lengths) == OP_TABLE_LENGTH)): - break; -/* ========================================================================== */ - - case OP_END: - fprintf(f, " %s\n", priv_OP_names[*code]); - fprintf(f, "------------------------------------------------------------------\n"); - return; - - case OP_CHAR: - fprintf(f, " "); - do - { - code++; - code += 1 + print_char(f, code, utf); - } - while (*code == OP_CHAR); - fprintf(f, "\n"); - continue; - - case OP_CHARI: - fprintf(f, " /i "); - do - { - code++; - code += 1 + print_char(f, code, utf); - } - while (*code == OP_CHARI); - fprintf(f, "\n"); - continue; - - case OP_CBRA: - case OP_CBRAPOS: - case OP_SCBRA: - case OP_SCBRAPOS: - if (print_lengths) fprintf(f, "%3d ", GET(code, 1)); - else fprintf(f, " "); - fprintf(f, "%s %d", priv_OP_names[*code], GET2(code, 1+LINK_SIZE)); - break; - - case OP_BRA: - case OP_BRAPOS: - case OP_SBRA: - case OP_SBRAPOS: - case OP_KETRMAX: - case OP_KETRMIN: - case OP_KETRPOS: - case OP_ALT: - case OP_KET: - case OP_ASSERT: - case OP_ASSERT_NOT: - case OP_ASSERTBACK: - case OP_ASSERTBACK_NOT: - case OP_ONCE: - case OP_ONCE_NC: - case OP_COND: - case OP_SCOND: - case OP_REVERSE: - if (print_lengths) fprintf(f, "%3d ", GET(code, 1)); - else fprintf(f, " "); - fprintf(f, "%s", priv_OP_names[*code]); - break; - - case OP_CLOSE: - fprintf(f, " %s %d", priv_OP_names[*code], GET2(code, 1)); - break; - - case OP_CREF: - fprintf(f, "%3d %s", GET2(code,1), priv_OP_names[*code]); - break; - - case OP_DNCREF: - { - pcre_uchar *entry = (pcre_uchar *)re + offset + (GET2(code, 1) * size) + - IMM2_SIZE; - fprintf(f, " %s Cond ref <", flag); - print_puchar(f, entry); - fprintf(f, ">%d", GET2(code, 1 + IMM2_SIZE)); - } - break; - - case OP_RREF: - c = GET2(code, 1); - if (c == RREF_ANY) - fprintf(f, " Cond recurse any"); - else - fprintf(f, " Cond recurse %d", c); - break; - - case OP_DNRREF: - { - pcre_uchar *entry = (pcre_uchar *)re + offset + (GET2(code, 1) * size) + - IMM2_SIZE; - fprintf(f, " %s Cond recurse <", flag); - print_puchar(f, entry); - fprintf(f, ">%d", GET2(code, 1 + IMM2_SIZE)); - } - break; - - case OP_DEF: - fprintf(f, " Cond def"); - break; - - case OP_STARI: - case OP_MINSTARI: - case OP_POSSTARI: - case OP_PLUSI: - case OP_MINPLUSI: - case OP_POSPLUSI: - case OP_QUERYI: - case OP_MINQUERYI: - case OP_POSQUERYI: - flag = "/i"; - /* Fall through */ - case OP_STAR: - case OP_MINSTAR: - case OP_POSSTAR: - case OP_PLUS: - case OP_MINPLUS: - case OP_POSPLUS: - case OP_QUERY: - case OP_MINQUERY: - case OP_POSQUERY: - case OP_TYPESTAR: - case OP_TYPEMINSTAR: - case OP_TYPEPOSSTAR: - case OP_TYPEPLUS: - case OP_TYPEMINPLUS: - case OP_TYPEPOSPLUS: - case OP_TYPEQUERY: - case OP_TYPEMINQUERY: - case OP_TYPEPOSQUERY: - fprintf(f, " %s ", flag); - if (*code >= OP_TYPESTAR) - { - if (code[1] == OP_PROP || code[1] == OP_NOTPROP) - { - print_prop(f, code + 1, "", " "); - extra = 2; - } - else fprintf(f, "%s", priv_OP_names[code[1]]); - } - else extra = print_char(f, code+1, utf); - fprintf(f, "%s", priv_OP_names[*code]); - break; - - case OP_EXACTI: - case OP_UPTOI: - case OP_MINUPTOI: - case OP_POSUPTOI: - flag = "/i"; - /* Fall through */ - case OP_EXACT: - case OP_UPTO: - case OP_MINUPTO: - case OP_POSUPTO: - fprintf(f, " %s ", flag); - extra = print_char(f, code + 1 + IMM2_SIZE, utf); - fprintf(f, "{"); - if (*code != OP_EXACT && *code != OP_EXACTI) fprintf(f, "0,"); - fprintf(f, "%d}", GET2(code,1)); - if (*code == OP_MINUPTO || *code == OP_MINUPTOI) fprintf(f, "?"); - else if (*code == OP_POSUPTO || *code == OP_POSUPTOI) fprintf(f, "+"); - break; - - case OP_TYPEEXACT: - case OP_TYPEUPTO: - case OP_TYPEMINUPTO: - case OP_TYPEPOSUPTO: - if (code[1 + IMM2_SIZE] == OP_PROP || code[1 + IMM2_SIZE] == OP_NOTPROP) - { - print_prop(f, code + IMM2_SIZE + 1, " ", " "); - extra = 2; - } - else fprintf(f, " %s", priv_OP_names[code[1 + IMM2_SIZE]]); - fprintf(f, "{"); - if (*code != OP_TYPEEXACT) fprintf(f, "0,"); - fprintf(f, "%d}", GET2(code,1)); - if (*code == OP_TYPEMINUPTO) fprintf(f, "?"); - else if (*code == OP_TYPEPOSUPTO) fprintf(f, "+"); - break; - - case OP_NOTI: - flag = "/i"; - /* Fall through */ - case OP_NOT: - fprintf(f, " %s [^", flag); - extra = print_char(f, code + 1, utf); - fprintf(f, "]"); - break; - - case OP_NOTSTARI: - case OP_NOTMINSTARI: - case OP_NOTPOSSTARI: - case OP_NOTPLUSI: - case OP_NOTMINPLUSI: - case OP_NOTPOSPLUSI: - case OP_NOTQUERYI: - case OP_NOTMINQUERYI: - case OP_NOTPOSQUERYI: - flag = "/i"; - /* Fall through */ - - case OP_NOTSTAR: - case OP_NOTMINSTAR: - case OP_NOTPOSSTAR: - case OP_NOTPLUS: - case OP_NOTMINPLUS: - case OP_NOTPOSPLUS: - case OP_NOTQUERY: - case OP_NOTMINQUERY: - case OP_NOTPOSQUERY: - fprintf(f, " %s [^", flag); - extra = print_char(f, code + 1, utf); - fprintf(f, "]%s", priv_OP_names[*code]); - break; - - case OP_NOTEXACTI: - case OP_NOTUPTOI: - case OP_NOTMINUPTOI: - case OP_NOTPOSUPTOI: - flag = "/i"; - /* Fall through */ - - case OP_NOTEXACT: - case OP_NOTUPTO: - case OP_NOTMINUPTO: - case OP_NOTPOSUPTO: - fprintf(f, " %s [^", flag); - extra = print_char(f, code + 1 + IMM2_SIZE, utf); - fprintf(f, "]{"); - if (*code != OP_NOTEXACT && *code != OP_NOTEXACTI) fprintf(f, "0,"); - fprintf(f, "%d}", GET2(code,1)); - if (*code == OP_NOTMINUPTO || *code == OP_NOTMINUPTOI) fprintf(f, "?"); - else - if (*code == OP_NOTPOSUPTO || *code == OP_NOTPOSUPTOI) fprintf(f, "+"); - break; - - case OP_RECURSE: - if (print_lengths) fprintf(f, "%3d ", GET(code, 1)); - else fprintf(f, " "); - fprintf(f, "%s", priv_OP_names[*code]); - break; - - case OP_REFI: - flag = "/i"; - /* Fall through */ - case OP_REF: - fprintf(f, " %s \\%d", flag, GET2(code,1)); - ccode = code + priv_OP_lengths[*code]; - goto CLASS_REF_REPEAT; - - case OP_DNREFI: - flag = "/i"; - /* Fall through */ - case OP_DNREF: - { - pcre_uchar *entry = (pcre_uchar *)re + offset + (GET2(code, 1) * size) + - IMM2_SIZE; - fprintf(f, " %s \\k<", flag); - print_puchar(f, entry); - fprintf(f, ">%d", GET2(code, 1 + IMM2_SIZE)); - } - ccode = code + priv_OP_lengths[*code]; - goto CLASS_REF_REPEAT; - - case OP_CALLOUT: - fprintf(f, " %s %d %d %d", priv_OP_names[*code], code[1], GET(code,2), - GET(code, 2 + LINK_SIZE)); - break; - - case OP_PROP: - case OP_NOTPROP: - print_prop(f, code, " ", ""); - break; - - /* OP_XCLASS cannot occur in 8-bit, non-UTF mode. However, there's no harm - in having this code always here, and it makes it less messy without all - those #ifdefs. */ - - case OP_CLASS: - case OP_NCLASS: - case OP_XCLASS: - { - int i; - unsigned int min, max; - BOOL printmap; - BOOL invertmap = FALSE; - pcre_uint8 *map; - pcre_uint8 inverted_map[32]; - - fprintf(f, " ["); - - if (*code == OP_XCLASS) - { - extra = GET(code, 1); - ccode = code + LINK_SIZE + 1; - printmap = (*ccode & XCL_MAP) != 0; - if ((*ccode & XCL_NOT) != 0) - { - invertmap = (*ccode & XCL_HASPROP) == 0; - fprintf(f, "^"); - } - ccode++; - } - else - { - printmap = TRUE; - ccode = code + 1; - } - - /* Print a bit map */ - - if (printmap) - { - map = (pcre_uint8 *)ccode; - if (invertmap) - { - for (i = 0; i < 32; i++) inverted_map[i] = ~map[i]; - map = inverted_map; - } - - for (i = 0; i < 256; i++) - { - if ((map[i/8] & (1 << (i&7))) != 0) - { - int j; - for (j = i+1; j < 256; j++) - if ((map[j/8] & (1 << (j&7))) == 0) break; - if (i == '-' || i == ']') fprintf(f, "\\"); - if (PRINTABLE(i)) fprintf(f, "%c", i); - else fprintf(f, "\\x%02x", i); - if (--j > i) - { - if (j != i + 1) fprintf(f, "-"); - if (j == '-' || j == ']') fprintf(f, "\\"); - if (PRINTABLE(j)) fprintf(f, "%c", j); - else fprintf(f, "\\x%02x", j); - } - i = j; - } - } - ccode += 32 / sizeof(pcre_uchar); - } - - /* For an XCLASS there is always some additional data */ - - if (*code == OP_XCLASS) - { - pcre_uchar ch; - while ((ch = *ccode++) != XCL_END) - { - BOOL not = FALSE; - const char *notch = ""; - - switch(ch) - { - case XCL_NOTPROP: - not = TRUE; - notch = "^"; - /* Fall through */ - - case XCL_PROP: - { - unsigned int ptype = *ccode++; - unsigned int pvalue = *ccode++; - - switch(ptype) - { - case PT_PXGRAPH: - fprintf(f, "[:%sgraph:]", notch); - break; - - case PT_PXPRINT: - fprintf(f, "[:%sprint:]", notch); - break; - - case PT_PXPUNCT: - fprintf(f, "[:%spunct:]", notch); - break; - - default: - fprintf(f, "\\%c{%s}", (not? 'P':'p'), - get_ucpname(ptype, pvalue)); - break; - } - } - break; - - default: - ccode += 1 + print_char(f, ccode, utf); - if (ch == XCL_RANGE) - { - fprintf(f, "-"); - ccode += 1 + print_char(f, ccode, utf); - } - break; - } - } - } - - /* Indicate a non-UTF class which was created by negation */ - - fprintf(f, "]%s", (*code == OP_NCLASS)? " (neg)" : ""); - - /* Handle repeats after a class or a back reference */ - - CLASS_REF_REPEAT: - switch(*ccode) - { - case OP_CRSTAR: - case OP_CRMINSTAR: - case OP_CRPLUS: - case OP_CRMINPLUS: - case OP_CRQUERY: - case OP_CRMINQUERY: - case OP_CRPOSSTAR: - case OP_CRPOSPLUS: - case OP_CRPOSQUERY: - fprintf(f, "%s", priv_OP_names[*ccode]); - extra += priv_OP_lengths[*ccode]; - break; - - case OP_CRRANGE: - case OP_CRMINRANGE: - case OP_CRPOSRANGE: - min = GET2(ccode,1); - max = GET2(ccode,1 + IMM2_SIZE); - if (max == 0) fprintf(f, "{%u,}", min); - else fprintf(f, "{%u,%u}", min, max); - if (*ccode == OP_CRMINRANGE) fprintf(f, "?"); - else if (*ccode == OP_CRPOSRANGE) fprintf(f, "+"); - extra += priv_OP_lengths[*ccode]; - break; - - /* Do nothing if it's not a repeat; this code stops picky compilers - warning about the lack of a default code path. */ - - default: - break; - } - } - break; - - case OP_MARK: - case OP_PRUNE_ARG: - case OP_SKIP_ARG: - case OP_THEN_ARG: - fprintf(f, " %s ", priv_OP_names[*code]); - print_puchar(f, code + 2); - extra += code[1]; - break; - - case OP_THEN: - fprintf(f, " %s", priv_OP_names[*code]); - break; - - case OP_CIRCM: - case OP_DOLLM: - flag = "/m"; - /* Fall through */ - - /* Anything else is just an item with no data, but possibly a flag. */ - - default: - fprintf(f, " %s %s", flag, priv_OP_names[*code]); - break; - } - - code += priv_OP_lengths[*code] + extra; - fprintf(f, "\n"); - } -} - -/* End of pcre_printint.src */ diff --git a/src/third_party/pcre-8.38/pcre_refcount.c b/src/third_party/pcre-8.38/pcre_refcount.c deleted file mode 100644 index 79efa90f216..00000000000 --- a/src/third_party/pcre-8.38/pcre_refcount.c +++ /dev/null @@ -1,92 +0,0 @@ -/************************************************* -* Perl-Compatible Regular Expressions * -*************************************************/ - -/* PCRE is a library of functions to support regular expressions whose syntax -and semantics are as close as possible to those of the Perl 5 language. - - Written by Philip Hazel - Copyright (c) 1997-2012 University of Cambridge - ------------------------------------------------------------------------------ -Redistribution and use in source and binary forms, with or without -modification, are permitted provided that the following conditions are met: - - * Redistributions of source code must retain the above copyright notice, - this list of conditions and the following disclaimer. - - * Redistributions in binary form must reproduce the above copyright - notice, this list of conditions and the following disclaimer in the - documentation and/or other materials provided with the distribution. - - * Neither the name of the University of Cambridge nor the names of its - contributors may be used to endorse or promote products derived from - this software without specific prior written permission. - -THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS" -AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE -IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE -ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR CONTRIBUTORS BE -LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR -CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF -SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS -INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN -CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) -ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE -POSSIBILITY OF SUCH DAMAGE. ------------------------------------------------------------------------------ -*/ - - -/* This module contains the external function pcre_refcount(), which is an -auxiliary function that can be used to maintain a reference count in a compiled -pattern data block. This might be helpful in applications where the block is -shared by different users. */ - - -#ifdef HAVE_CONFIG_H -#include "config.h" -#endif - -#include "pcre_internal.h" - - -/************************************************* -* Maintain reference count * -*************************************************/ - -/* The reference count is a 16-bit field, initialized to zero. It is not -possible to transfer a non-zero count from one host to a different host that -has a different byte order - though I can't see why anyone in their right mind -would ever want to do that! - -Arguments: - argument_re points to compiled code - adjust value to add to the count - -Returns: the (possibly updated) count value (a non-negative number), or - a negative error number -*/ - -#if defined COMPILE_PCRE8 -PCRE_EXP_DEFN int PCRE_CALL_CONVENTION -pcre_refcount(pcre *argument_re, int adjust) -#elif defined COMPILE_PCRE16 -PCRE_EXP_DEFN int PCRE_CALL_CONVENTION -pcre16_refcount(pcre16 *argument_re, int adjust) -#elif defined COMPILE_PCRE32 -PCRE_EXP_DEFN int PCRE_CALL_CONVENTION -pcre32_refcount(pcre32 *argument_re, int adjust) -#endif -{ -REAL_PCRE *re = (REAL_PCRE *)argument_re; -if (re == NULL) return PCRE_ERROR_NULL; -if (re->magic_number != MAGIC_NUMBER) return PCRE_ERROR_BADMAGIC; -if ((re->flags & PCRE_MODE) == 0) return PCRE_ERROR_BADMODE; -re->ref_count = (-adjust > re->ref_count)? 0 : - (adjust + re->ref_count > 65535)? 65535 : - re->ref_count + adjust; -return re->ref_count; -} - -/* End of pcre_refcount.c */ diff --git a/src/third_party/pcre-8.38/pcre_scanner.cc b/src/third_party/pcre-8.38/pcre_scanner.cc deleted file mode 100644 index 6be2be6829b..00000000000 --- a/src/third_party/pcre-8.38/pcre_scanner.cc +++ /dev/null @@ -1,199 +0,0 @@ -// Copyright (c) 2005, Google Inc. -// All rights reserved. -// -// Redistribution and use in source and binary forms, with or without -// modification, are permitted provided that the following conditions are -// met: -// -// * Redistributions of source code must retain the above copyright -// notice, this list of conditions and the following disclaimer. -// * Redistributions in binary form must reproduce the above -// copyright notice, this list of conditions and the following disclaimer -// in the documentation and/or other materials provided with the -// distribution. -// * Neither the name of Google Inc. nor the names of its -// contributors may be used to endorse or promote products derived from -// this software without specific prior written permission. -// -// THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS -// "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT -// LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR -// A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT -// OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, -// SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT -// LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, -// DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY -// THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT -// (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE -// OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE. -// -// Author: Sanjay Ghemawat - -#ifdef HAVE_CONFIG_H -#include "config.h" -#endif - -#include <vector> -#include <assert.h> - -#include "pcrecpp_internal.h" -#include "pcre_scanner.h" - -using std::vector; - -namespace pcrecpp { - -Scanner::Scanner() - : data_(), - input_(data_), - skip_(NULL), - should_skip_(false), - skip_repeat_(false), - save_comments_(false), - comments_(NULL), - comments_offset_(0) { -} - -Scanner::Scanner(const string& in) - : data_(in), - input_(data_), - skip_(NULL), - should_skip_(false), - skip_repeat_(false), - save_comments_(false), - comments_(NULL), - comments_offset_(0) { -} - -Scanner::~Scanner() { - delete skip_; - delete comments_; -} - -void Scanner::SetSkipExpression(const char* re) { - delete skip_; - if (re != NULL) { - skip_ = new RE(re); - should_skip_ = true; - skip_repeat_ = true; - ConsumeSkip(); - } else { - skip_ = NULL; - should_skip_ = false; - skip_repeat_ = false; - } -} - -void Scanner::Skip(const char* re) { - delete skip_; - if (re != NULL) { - skip_ = new RE(re); - should_skip_ = true; - skip_repeat_ = false; - ConsumeSkip(); - } else { - skip_ = NULL; - should_skip_ = false; - skip_repeat_ = false; - } -} - -void Scanner::DisableSkip() { - assert(skip_ != NULL); - should_skip_ = false; -} - -void Scanner::EnableSkip() { - assert(skip_ != NULL); - should_skip_ = true; - ConsumeSkip(); -} - -int Scanner::LineNumber() const { - // TODO: Make it more efficient by keeping track of the last point - // where we computed line numbers and counting newlines since then. - // We could use std:count, but not all systems have it. :-( - int count = 1; - for (const char* p = data_.data(); p < input_.data(); ++p) - if (*p == '\n') - ++count; - return count; -} - -int Scanner::Offset() const { - return (int)(input_.data() - data_.c_str()); -} - -bool Scanner::LookingAt(const RE& re) const { - int consumed; - return re.DoMatch(input_, RE::ANCHOR_START, &consumed, 0, 0); -} - - -bool Scanner::Consume(const RE& re, - const Arg& arg0, - const Arg& arg1, - const Arg& arg2) { - const bool result = re.Consume(&input_, arg0, arg1, arg2); - if (result && should_skip_) ConsumeSkip(); - return result; -} - -// helper function to consume *skip_ and honour save_comments_ -void Scanner::ConsumeSkip() { - const char* start_data = input_.data(); - while (skip_->Consume(&input_)) { - if (!skip_repeat_) { - // Only one skip allowed. - break; - } - } - if (save_comments_) { - if (comments_ == NULL) { - comments_ = new vector<StringPiece>; - } - // already pointing one past end, so no need to +1 - int length = (int)(input_.data() - start_data); - if (length > 0) { - comments_->push_back(StringPiece(start_data, length)); - } - } -} - - -void Scanner::GetComments(int start, int end, vector<StringPiece> *ranges) { - // short circuit out if we've not yet initialized comments_ - // (e.g., when save_comments is false) - if (!comments_) { - return; - } - // TODO: if we guarantee that comments_ will contain StringPieces - // that are ordered by their start, then we can do a binary search - // for the first StringPiece at or past start and then scan for the - // ones contained in the range, quit early (use equal_range or - // lower_bound) - for (vector<StringPiece>::const_iterator it = comments_->begin(); - it != comments_->end(); ++it) { - if ((it->data() >= data_.c_str() + start && - it->data() + it->size() <= data_.c_str() + end)) { - ranges->push_back(*it); - } - } -} - - -void Scanner::GetNextComments(vector<StringPiece> *ranges) { - // short circuit out if we've not yet initialized comments_ - // (e.g., when save_comments is false) - if (!comments_) { - return; - } - for (vector<StringPiece>::const_iterator it = - comments_->begin() + comments_offset_; - it != comments_->end(); ++it) { - ranges->push_back(*it); - ++comments_offset_; - } -} - -} // namespace pcrecpp diff --git a/src/third_party/pcre-8.38/pcre_scanner.h b/src/third_party/pcre-8.38/pcre_scanner.h deleted file mode 100644 index 5617e4515cb..00000000000 --- a/src/third_party/pcre-8.38/pcre_scanner.h +++ /dev/null @@ -1,172 +0,0 @@ -// Copyright (c) 2005, Google Inc. -// All rights reserved. -// -// Redistribution and use in source and binary forms, with or without -// modification, are permitted provided that the following conditions are -// met: -// -// * Redistributions of source code must retain the above copyright -// notice, this list of conditions and the following disclaimer. -// * Redistributions in binary form must reproduce the above -// copyright notice, this list of conditions and the following disclaimer -// in the documentation and/or other materials provided with the -// distribution. -// * Neither the name of Google Inc. nor the names of its -// contributors may be used to endorse or promote products derived from -// this software without specific prior written permission. -// -// THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS -// "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT -// LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR -// A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT -// OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, -// SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT -// LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, -// DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY -// THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT -// (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE -// OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE. -// -// Author: Sanjay Ghemawat -// -// Regular-expression based scanner for parsing an input stream. -// -// Example 1: parse a sequence of "var = number" entries from input: -// -// Scanner scanner(input); -// string var; -// int number; -// scanner.SetSkipExpression("\\s+"); // Skip any white space we encounter -// while (scanner.Consume("(\\w+) = (\\d+)", &var, &number)) { -// ...; -// } - -#ifndef _PCRE_SCANNER_H -#define _PCRE_SCANNER_H - -#include <assert.h> -#include <string> -#include <vector> - -#include <pcrecpp.h> -#include <pcre_stringpiece.h> - -namespace pcrecpp { - -class PCRECPP_EXP_DEFN Scanner { - public: - Scanner(); - explicit Scanner(const std::string& input); - ~Scanner(); - - // Return current line number. The returned line-number is - // one-based. I.e. it returns 1 + the number of consumed newlines. - // - // Note: this method may be slow. It may take time proportional to - // the size of the input. - int LineNumber() const; - - // Return the byte-offset that the scanner is looking in the - // input data; - int Offset() const; - - // Return true iff the start of the remaining input matches "re" - bool LookingAt(const RE& re) const; - - // Return true iff all of the following are true - // a. the start of the remaining input matches "re", - // b. if any arguments are supplied, matched sub-patterns can be - // parsed and stored into the arguments. - // If it returns true, it skips over the matched input and any - // following input that matches the "skip" regular expression. - bool Consume(const RE& re, - const Arg& arg0 = RE::no_arg, - const Arg& arg1 = RE::no_arg, - const Arg& arg2 = RE::no_arg - // TODO: Allow more arguments? - ); - - // Set the "skip" regular expression. If after consuming some data, - // a prefix of the input matches this RE, it is automatically - // skipped. For example, a programming language scanner would use - // a skip RE that matches white space and comments. - // - // scanner.SetSkipExpression("\\s+|//.*|/[*](.|\n)*?[*]/"); - // - // Skipping repeats as long as it succeeds. We used to let people do - // this by writing "(...)*" in the regular expression, but that added - // up to lots of recursive calls within the pcre library, so now we - // control repetition explicitly via the function call API. - // - // You can pass NULL for "re" if you do not want any data to be skipped. - void Skip(const char* re); // DEPRECATED; does *not* repeat - void SetSkipExpression(const char* re); - - // Temporarily pause "skip"ing. This - // Skip("Foo"); code ; DisableSkip(); code; EnableSkip() - // is similar to - // Skip("Foo"); code ; Skip(NULL); code ; Skip("Foo"); - // but avoids creating/deleting new RE objects. - void DisableSkip(); - - // Reenable previously paused skipping. Any prefix of the input - // that matches the skip pattern is immediately dropped. - void EnableSkip(); - - /***** Special wrappers around SetSkip() for some common idioms *****/ - - // Arranges to skip whitespace, C comments, C++ comments. - // The overall RE is a disjunction of the following REs: - // \\s whitespace - // //.*\n C++ comment - // /[*](.|\n)*?[*]/ C comment (x*? means minimal repetitions of x) - // We get repetition via the semantics of SetSkipExpression, not by using * - void SkipCXXComments() { - SetSkipExpression("\\s|//.*\n|/[*](?:\n|.)*?[*]/"); - } - - void set_save_comments(bool comments) { - save_comments_ = comments; - } - - bool save_comments() { - return save_comments_; - } - - // Append to vector ranges the comments found in the - // byte range [start,end] (inclusive) of the input data. - // Only comments that were extracted entirely within that - // range are returned: no range splitting of atomically-extracted - // comments is performed. - void GetComments(int start, int end, std::vector<StringPiece> *ranges); - - // Append to vector ranges the comments added - // since the last time this was called. This - // functionality is provided for efficiency when - // interleaving scanning with parsing. - void GetNextComments(std::vector<StringPiece> *ranges); - - private: - std::string data_; // All the input data - StringPiece input_; // Unprocessed input - RE* skip_; // If non-NULL, RE for skipping input - bool should_skip_; // If true, use skip_ - bool skip_repeat_; // If true, repeat skip_ as long as it works - bool save_comments_; // If true, aggregate the skip expression - - // the skipped comments - // TODO: later consider requiring that the StringPieces be added - // in order by their start position - std::vector<StringPiece> *comments_; - - // the offset into comments_ that has been returned by GetNextComments - int comments_offset_; - - // helper function to consume *skip_ and honour - // save_comments_ - void ConsumeSkip(); -}; - -} // namespace pcrecpp - -#endif /* _PCRE_SCANNER_H */ diff --git a/src/third_party/pcre-8.38/pcre_scanner_unittest.cc b/src/third_party/pcre-8.38/pcre_scanner_unittest.cc deleted file mode 100644 index c00312c4f63..00000000000 --- a/src/third_party/pcre-8.38/pcre_scanner_unittest.cc +++ /dev/null @@ -1,161 +0,0 @@ -// Copyright (c) 2005, Google Inc. -// All rights reserved. -// -// Redistribution and use in source and binary forms, with or without -// modification, are permitted provided that the following conditions are -// met: -// -// * Redistributions of source code must retain the above copyright -// notice, this list of conditions and the following disclaimer. -// * Redistributions in binary form must reproduce the above -// copyright notice, this list of conditions and the following disclaimer -// in the documentation and/or other materials provided with the -// distribution. -// * Neither the name of Google Inc. nor the names of its -// contributors may be used to endorse or promote products derived from -// this software without specific prior written permission. -// -// THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS -// "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT -// LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR -// A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT -// OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, -// SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT -// LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, -// DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY -// THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT -// (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE -// OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE. -// -// Author: Greg J. Badros -// -// Unittest for scanner, especially GetNextComments and GetComments() -// functionality. - -#ifdef HAVE_CONFIG_H -#include "config.h" -#endif - -#include <stdio.h> -#include <string.h> /* for strchr */ -#include <string> -#include <vector> - -#include "pcrecpp.h" -#include "pcre_stringpiece.h" -#include "pcre_scanner.h" - -#define FLAGS_unittest_stack_size 49152 - -// Dies with a fatal error if the two values are not equal. -#define CHECK_EQ(a, b) do { \ - if ( (a) != (b) ) { \ - fprintf(stderr, "%s:%d: Check failed because %s != %s\n", \ - __FILE__, __LINE__, #a, #b); \ - exit(1); \ - } \ -} while (0) - -using std::vector; -using pcrecpp::StringPiece; -using pcrecpp::Scanner; - -static void TestScanner() { - const char input[] = "\n" - "alpha = 1; // this sets alpha\n" - "bravo = 2; // bravo is set here\n" - "gamma = 33; /* and here is gamma */\n"; - - const char *re = "(\\w+) = (\\d+);"; - - Scanner s(input); - string var; - int number; - s.SkipCXXComments(); - s.set_save_comments(true); - vector<StringPiece> comments; - - s.Consume(re, &var, &number); - CHECK_EQ(var, "alpha"); - CHECK_EQ(number, 1); - CHECK_EQ(s.LineNumber(), 3); - s.GetNextComments(&comments); - CHECK_EQ(comments.size(), 1); - CHECK_EQ(comments[0].as_string(), " // this sets alpha\n"); - comments.resize(0); - - s.Consume(re, &var, &number); - CHECK_EQ(var, "bravo"); - CHECK_EQ(number, 2); - s.GetNextComments(&comments); - CHECK_EQ(comments.size(), 1); - CHECK_EQ(comments[0].as_string(), " // bravo is set here\n"); - comments.resize(0); - - s.Consume(re, &var, &number); - CHECK_EQ(var, "gamma"); - CHECK_EQ(number, 33); - s.GetNextComments(&comments); - CHECK_EQ(comments.size(), 1); - CHECK_EQ(comments[0].as_string(), " /* and here is gamma */\n"); - comments.resize(0); - - s.GetComments(0, sizeof(input), &comments); - CHECK_EQ(comments.size(), 3); - CHECK_EQ(comments[0].as_string(), " // this sets alpha\n"); - CHECK_EQ(comments[1].as_string(), " // bravo is set here\n"); - CHECK_EQ(comments[2].as_string(), " /* and here is gamma */\n"); - comments.resize(0); - - s.GetComments(0, (int)(strchr(input, '/') - input), &comments); - CHECK_EQ(comments.size(), 0); - comments.resize(0); - - s.GetComments((int)(strchr(input, '/') - input - 1), sizeof(input), - &comments); - CHECK_EQ(comments.size(), 3); - CHECK_EQ(comments[0].as_string(), " // this sets alpha\n"); - CHECK_EQ(comments[1].as_string(), " // bravo is set here\n"); - CHECK_EQ(comments[2].as_string(), " /* and here is gamma */\n"); - comments.resize(0); - - s.GetComments((int)(strchr(input, '/') - input - 1), - (int)(strchr(input + 1, '\n') - input + 1), &comments); - CHECK_EQ(comments.size(), 1); - CHECK_EQ(comments[0].as_string(), " // this sets alpha\n"); - comments.resize(0); -} - -static void TestBigComment() { - string input; - for (int i = 0; i < 1024; ++i) { - char buf[1024]; // definitely big enough - sprintf(buf, " # Comment %d\n", i); - input += buf; - } - input += "name = value;\n"; - - Scanner s(input.c_str()); - s.SetSkipExpression("\\s+|#.*\n"); - - string name; - string value; - s.Consume("(\\w+) = (\\w+);", &name, &value); - CHECK_EQ(name, "name"); - CHECK_EQ(value, "value"); -} - -// TODO: also test scanner and big-comment in a thread with a -// small stack size - -int main(int argc, char** argv) { - (void)argc; - (void)argv; - TestScanner(); - TestBigComment(); - - // Done - printf("OK\n"); - - return 0; -} diff --git a/src/third_party/pcre-8.38/pcre_string_utils.c b/src/third_party/pcre-8.38/pcre_string_utils.c deleted file mode 100644 index 25eacc85073..00000000000 --- a/src/third_party/pcre-8.38/pcre_string_utils.c +++ /dev/null @@ -1,211 +0,0 @@ -/************************************************* -* Perl-Compatible Regular Expressions * -*************************************************/ - -/* PCRE is a library of functions to support regular expressions whose syntax -and semantics are as close as possible to those of the Perl 5 language. - - Written by Philip Hazel - Copyright (c) 1997-2014 University of Cambridge - ------------------------------------------------------------------------------ -Redistribution and use in source and binary forms, with or without -modification, are permitted provided that the following conditions are met: - - * Redistributions of source code must retain the above copyright notice, - this list of conditions and the following disclaimer. - - * Redistributions in binary form must reproduce the above copyright - notice, this list of conditions and the following disclaimer in the - documentation and/or other materials provided with the distribution. - - * Neither the name of the University of Cambridge nor the names of its - contributors may be used to endorse or promote products derived from - this software without specific prior written permission. - -THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS" -AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE -IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE -ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR CONTRIBUTORS BE -LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR -CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF -SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS -INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN -CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) -ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE -POSSIBILITY OF SUCH DAMAGE. ------------------------------------------------------------------------------ -*/ - - -/* This module contains internal functions for comparing and finding the length -of strings for different data item sizes. */ - - -#ifdef HAVE_CONFIG_H -#include "config.h" -#endif - -#include "pcre_internal.h" - -#ifndef COMPILE_PCRE8 - -/************************************************* -* Compare string utilities * -*************************************************/ - -/* The following two functions compares two strings. Basically a strcmp -for non 8 bit characters. - -Arguments: - str1 first string - str2 second string - -Returns: 0 if both string are equal (like strcmp), 1 otherwise -*/ - -int -PRIV(strcmp_uc_uc)(const pcre_uchar *str1, const pcre_uchar *str2) -{ -pcre_uchar c1; -pcre_uchar c2; - -while (*str1 != '\0' || *str2 != '\0') - { - c1 = *str1++; - c2 = *str2++; - if (c1 != c2) - return ((c1 > c2) << 1) - 1; - } -/* Both length and characters must be equal. */ -return 0; -} - -#ifdef COMPILE_PCRE32 - -int -PRIV(strcmp_uc_uc_utf)(const pcre_uchar *str1, const pcre_uchar *str2) -{ -pcre_uchar c1; -pcre_uchar c2; - -while (*str1 != '\0' || *str2 != '\0') - { - c1 = UCHAR21INC(str1); - c2 = UCHAR21INC(str2); - if (c1 != c2) - return ((c1 > c2) << 1) - 1; - } -/* Both length and characters must be equal. */ -return 0; -} - -#endif /* COMPILE_PCRE32 */ - -int -PRIV(strcmp_uc_c8)(const pcre_uchar *str1, const char *str2) -{ -const pcre_uint8 *ustr2 = (pcre_uint8 *)str2; -pcre_uchar c1; -pcre_uchar c2; - -while (*str1 != '\0' || *ustr2 != '\0') - { - c1 = *str1++; - c2 = (pcre_uchar)*ustr2++; - if (c1 != c2) - return ((c1 > c2) << 1) - 1; - } -/* Both length and characters must be equal. */ -return 0; -} - -#ifdef COMPILE_PCRE32 - -int -PRIV(strcmp_uc_c8_utf)(const pcre_uchar *str1, const char *str2) -{ -const pcre_uint8 *ustr2 = (pcre_uint8 *)str2; -pcre_uchar c1; -pcre_uchar c2; - -while (*str1 != '\0' || *ustr2 != '\0') - { - c1 = UCHAR21INC(str1); - c2 = (pcre_uchar)*ustr2++; - if (c1 != c2) - return ((c1 > c2) << 1) - 1; - } -/* Both length and characters must be equal. */ -return 0; -} - -#endif /* COMPILE_PCRE32 */ - -/* The following two functions compares two, fixed length -strings. Basically an strncmp for non 8 bit characters. - -Arguments: - str1 first string - str2 second string - num size of the string - -Returns: 0 if both string are equal (like strcmp), 1 otherwise -*/ - -int -PRIV(strncmp_uc_uc)(const pcre_uchar *str1, const pcre_uchar *str2, unsigned int num) -{ -pcre_uchar c1; -pcre_uchar c2; - -while (num-- > 0) - { - c1 = *str1++; - c2 = *str2++; - if (c1 != c2) - return ((c1 > c2) << 1) - 1; - } -/* Both length and characters must be equal. */ -return 0; -} - -int -PRIV(strncmp_uc_c8)(const pcre_uchar *str1, const char *str2, unsigned int num) -{ -const pcre_uint8 *ustr2 = (pcre_uint8 *)str2; -pcre_uchar c1; -pcre_uchar c2; - -while (num-- > 0) - { - c1 = *str1++; - c2 = (pcre_uchar)*ustr2++; - if (c1 != c2) - return ((c1 > c2) << 1) - 1; - } -/* Both length and characters must be equal. */ -return 0; -} - -/* The following function returns with the length of -a zero terminated string. Basically an strlen for non 8 bit characters. - -Arguments: - str string - -Returns: length of the string -*/ - -unsigned int -PRIV(strlen_uc)(const pcre_uchar *str) -{ -unsigned int len = 0; -while (*str++ != 0) - len++; -return len; -} - -#endif /* !COMPILE_PCRE8 */ - -/* End of pcre_string_utils.c */ diff --git a/src/third_party/pcre-8.38/pcre_stringpiece.cc b/src/third_party/pcre-8.38/pcre_stringpiece.cc deleted file mode 100644 index 67c0f1fc0e5..00000000000 --- a/src/third_party/pcre-8.38/pcre_stringpiece.cc +++ /dev/null @@ -1,43 +0,0 @@ -// Copyright (c) 2005, Google Inc. -// All rights reserved. -// -// Redistribution and use in source and binary forms, with or without -// modification, are permitted provided that the following conditions are -// met: -// -// * Redistributions of source code must retain the above copyright -// notice, this list of conditions and the following disclaimer. -// * Redistributions in binary form must reproduce the above -// copyright notice, this list of conditions and the following disclaimer -// in the documentation and/or other materials provided with the -// distribution. -// * Neither the name of Google Inc. nor the names of its -// contributors may be used to endorse or promote products derived from -// this software without specific prior written permission. -// -// THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS -// "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT -// LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR -// A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT -// OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, -// SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT -// LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, -// DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY -// THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT -// (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE -// OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE. -// -// Author: wilsonh@google.com (Wilson Hsieh) -// - -#ifdef HAVE_CONFIG_H -#include "config.h" -#endif - -#include <iostream> -#include "pcrecpp_internal.h" -#include "pcre_stringpiece.h" - -std::ostream& operator<<(std::ostream& o, const pcrecpp::StringPiece& piece) { - return (o << piece.as_string()); -} diff --git a/src/third_party/pcre-8.38/pcre_stringpiece.h b/src/third_party/pcre-8.38/pcre_stringpiece.h deleted file mode 100644 index cc3dc42963a..00000000000 --- a/src/third_party/pcre-8.38/pcre_stringpiece.h +++ /dev/null @@ -1,180 +0,0 @@ -// Copyright (c) 2005, Google Inc. -// All rights reserved. -// -// Redistribution and use in source and binary forms, with or without -// modification, are permitted provided that the following conditions are -// met: -// -// * Redistributions of source code must retain the above copyright -// notice, this list of conditions and the following disclaimer. -// * Redistributions in binary form must reproduce the above -// copyright notice, this list of conditions and the following disclaimer -// in the documentation and/or other materials provided with the -// distribution. -// * Neither the name of Google Inc. nor the names of its -// contributors may be used to endorse or promote products derived from -// this software without specific prior written permission. -// -// THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS -// "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT -// LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR -// A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT -// OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, -// SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT -// LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, -// DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY -// THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT -// (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE -// OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE. -// -// Author: Sanjay Ghemawat -// -// A string like object that points into another piece of memory. -// Useful for providing an interface that allows clients to easily -// pass in either a "const char*" or a "string". -// -// Arghh! I wish C++ literals were automatically of type "string". - -#ifndef _PCRE_STRINGPIECE_H -#define _PCRE_STRINGPIECE_H - -#include <cstring> -#include <string> -#include <iosfwd> // for ostream forward-declaration - -#if 0 -#define HAVE_TYPE_TRAITS -#include <type_traits.h> -#elif 0 -#define HAVE_TYPE_TRAITS -#include <bits/type_traits.h> -#endif - -#include <pcre.h> - -using std::memcmp; -using std::strlen; -using std::string; - -namespace pcrecpp { - -class PCRECPP_EXP_DEFN StringPiece { - private: - const char* ptr_; - int length_; - - public: - // We provide non-explicit singleton constructors so users can pass - // in a "const char*" or a "string" wherever a "StringPiece" is - // expected. - StringPiece() - : ptr_(NULL), length_(0) { } - StringPiece(const char* str) - : ptr_(str), length_(static_cast<int>(strlen(ptr_))) { } - StringPiece(const unsigned char* str) - : ptr_(reinterpret_cast<const char*>(str)), - length_(static_cast<int>(strlen(ptr_))) { } - StringPiece(const string& str) - : ptr_(str.data()), length_(static_cast<int>(str.size())) { } - StringPiece(const char* offset, int len) - : ptr_(offset), length_(len) { } - - // data() may return a pointer to a buffer with embedded NULs, and the - // returned buffer may or may not be null terminated. Therefore it is - // typically a mistake to pass data() to a routine that expects a NUL - // terminated string. Use "as_string().c_str()" if you really need to do - // this. Or better yet, change your routine so it does not rely on NUL - // termination. - const char* data() const { return ptr_; } - int size() const { return length_; } - bool empty() const { return length_ == 0; } - - void clear() { ptr_ = NULL; length_ = 0; } - void set(const char* buffer, int len) { ptr_ = buffer; length_ = len; } - void set(const char* str) { - ptr_ = str; - length_ = static_cast<int>(strlen(str)); - } - void set(const void* buffer, int len) { - ptr_ = reinterpret_cast<const char*>(buffer); - length_ = len; - } - - char operator[](int i) const { return ptr_[i]; } - - void remove_prefix(int n) { - ptr_ += n; - length_ -= n; - } - - void remove_suffix(int n) { - length_ -= n; - } - - bool operator==(const StringPiece& x) const { - return ((length_ == x.length_) && - (memcmp(ptr_, x.ptr_, length_) == 0)); - } - bool operator!=(const StringPiece& x) const { - return !(*this == x); - } - -#define STRINGPIECE_BINARY_PREDICATE(cmp,auxcmp) \ - bool operator cmp (const StringPiece& x) const { \ - int r = memcmp(ptr_, x.ptr_, length_ < x.length_ ? length_ : x.length_); \ - return ((r auxcmp 0) || ((r == 0) && (length_ cmp x.length_))); \ - } - STRINGPIECE_BINARY_PREDICATE(<, <); - STRINGPIECE_BINARY_PREDICATE(<=, <); - STRINGPIECE_BINARY_PREDICATE(>=, >); - STRINGPIECE_BINARY_PREDICATE(>, >); -#undef STRINGPIECE_BINARY_PREDICATE - - int compare(const StringPiece& x) const { - int r = memcmp(ptr_, x.ptr_, length_ < x.length_ ? length_ : x.length_); - if (r == 0) { - if (length_ < x.length_) r = -1; - else if (length_ > x.length_) r = +1; - } - return r; - } - - string as_string() const { - return string(data(), size()); - } - - void CopyToString(string* target) const { - target->assign(ptr_, length_); - } - - // Does "this" start with "x" - bool starts_with(const StringPiece& x) const { - return ((length_ >= x.length_) && (memcmp(ptr_, x.ptr_, x.length_) == 0)); - } -}; - -} // namespace pcrecpp - -// ------------------------------------------------------------------ -// Functions used to create STL containers that use StringPiece -// Remember that a StringPiece's lifetime had better be less than -// that of the underlying string or char*. If it is not, then you -// cannot safely store a StringPiece into an STL container -// ------------------------------------------------------------------ - -#ifdef HAVE_TYPE_TRAITS -// This makes vector<StringPiece> really fast for some STL implementations -template<> struct __type_traits<pcrecpp::StringPiece> { - typedef __true_type has_trivial_default_constructor; - typedef __true_type has_trivial_copy_constructor; - typedef __true_type has_trivial_assignment_operator; - typedef __true_type has_trivial_destructor; - typedef __true_type is_POD_type; -}; -#endif - -// allow StringPiece to be logged -PCRECPP_EXP_DECL std::ostream& operator<<(std::ostream& o, - const pcrecpp::StringPiece& piece); - -#endif /* _PCRE_STRINGPIECE_H */ diff --git a/src/third_party/pcre-8.38/pcre_stringpiece.h.in b/src/third_party/pcre-8.38/pcre_stringpiece.h.in deleted file mode 100644 index eb25826b453..00000000000 --- a/src/third_party/pcre-8.38/pcre_stringpiece.h.in +++ /dev/null @@ -1,180 +0,0 @@ -// Copyright (c) 2005, Google Inc. -// All rights reserved. -// -// Redistribution and use in source and binary forms, with or without -// modification, are permitted provided that the following conditions are -// met: -// -// * Redistributions of source code must retain the above copyright -// notice, this list of conditions and the following disclaimer. -// * Redistributions in binary form must reproduce the above -// copyright notice, this list of conditions and the following disclaimer -// in the documentation and/or other materials provided with the -// distribution. -// * Neither the name of Google Inc. nor the names of its -// contributors may be used to endorse or promote products derived from -// this software without specific prior written permission. -// -// THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS -// "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT -// LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR -// A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT -// OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, -// SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT -// LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, -// DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY -// THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT -// (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE -// OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE. -// -// Author: Sanjay Ghemawat -// -// A string like object that points into another piece of memory. -// Useful for providing an interface that allows clients to easily -// pass in either a "const char*" or a "string". -// -// Arghh! I wish C++ literals were automatically of type "string". - -#ifndef _PCRE_STRINGPIECE_H -#define _PCRE_STRINGPIECE_H - -#include <cstring> -#include <string> -#include <iosfwd> // for ostream forward-declaration - -#if @pcre_have_type_traits@ -#define HAVE_TYPE_TRAITS -#include <type_traits.h> -#elif @pcre_have_bits_type_traits@ -#define HAVE_TYPE_TRAITS -#include <bits/type_traits.h> -#endif - -#include <pcre.h> - -using std::memcmp; -using std::strlen; -using std::string; - -namespace pcrecpp { - -class PCRECPP_EXP_DEFN StringPiece { - private: - const char* ptr_; - int length_; - - public: - // We provide non-explicit singleton constructors so users can pass - // in a "const char*" or a "string" wherever a "StringPiece" is - // expected. - StringPiece() - : ptr_(NULL), length_(0) { } - StringPiece(const char* str) - : ptr_(str), length_(static_cast<int>(strlen(ptr_))) { } - StringPiece(const unsigned char* str) - : ptr_(reinterpret_cast<const char*>(str)), - length_(static_cast<int>(strlen(ptr_))) { } - StringPiece(const string& str) - : ptr_(str.data()), length_(static_cast<int>(str.size())) { } - StringPiece(const char* offset, int len) - : ptr_(offset), length_(len) { } - - // data() may return a pointer to a buffer with embedded NULs, and the - // returned buffer may or may not be null terminated. Therefore it is - // typically a mistake to pass data() to a routine that expects a NUL - // terminated string. Use "as_string().c_str()" if you really need to do - // this. Or better yet, change your routine so it does not rely on NUL - // termination. - const char* data() const { return ptr_; } - int size() const { return length_; } - bool empty() const { return length_ == 0; } - - void clear() { ptr_ = NULL; length_ = 0; } - void set(const char* buffer, int len) { ptr_ = buffer; length_ = len; } - void set(const char* str) { - ptr_ = str; - length_ = static_cast<int>(strlen(str)); - } - void set(const void* buffer, int len) { - ptr_ = reinterpret_cast<const char*>(buffer); - length_ = len; - } - - char operator[](int i) const { return ptr_[i]; } - - void remove_prefix(int n) { - ptr_ += n; - length_ -= n; - } - - void remove_suffix(int n) { - length_ -= n; - } - - bool operator==(const StringPiece& x) const { - return ((length_ == x.length_) && - (memcmp(ptr_, x.ptr_, length_) == 0)); - } - bool operator!=(const StringPiece& x) const { - return !(*this == x); - } - -#define STRINGPIECE_BINARY_PREDICATE(cmp,auxcmp) \ - bool operator cmp (const StringPiece& x) const { \ - int r = memcmp(ptr_, x.ptr_, length_ < x.length_ ? length_ : x.length_); \ - return ((r auxcmp 0) || ((r == 0) && (length_ cmp x.length_))); \ - } - STRINGPIECE_BINARY_PREDICATE(<, <); - STRINGPIECE_BINARY_PREDICATE(<=, <); - STRINGPIECE_BINARY_PREDICATE(>=, >); - STRINGPIECE_BINARY_PREDICATE(>, >); -#undef STRINGPIECE_BINARY_PREDICATE - - int compare(const StringPiece& x) const { - int r = memcmp(ptr_, x.ptr_, length_ < x.length_ ? length_ : x.length_); - if (r == 0) { - if (length_ < x.length_) r = -1; - else if (length_ > x.length_) r = +1; - } - return r; - } - - string as_string() const { - return string(data(), size()); - } - - void CopyToString(string* target) const { - target->assign(ptr_, length_); - } - - // Does "this" start with "x" - bool starts_with(const StringPiece& x) const { - return ((length_ >= x.length_) && (memcmp(ptr_, x.ptr_, x.length_) == 0)); - } -}; - -} // namespace pcrecpp - -// ------------------------------------------------------------------ -// Functions used to create STL containers that use StringPiece -// Remember that a StringPiece's lifetime had better be less than -// that of the underlying string or char*. If it is not, then you -// cannot safely store a StringPiece into an STL container -// ------------------------------------------------------------------ - -#ifdef HAVE_TYPE_TRAITS -// This makes vector<StringPiece> really fast for some STL implementations -template<> struct __type_traits<pcrecpp::StringPiece> { - typedef __true_type has_trivial_default_constructor; - typedef __true_type has_trivial_copy_constructor; - typedef __true_type has_trivial_assignment_operator; - typedef __true_type has_trivial_destructor; - typedef __true_type is_POD_type; -}; -#endif - -// allow StringPiece to be logged -PCRECPP_EXP_DECL std::ostream& operator<<(std::ostream& o, - const pcrecpp::StringPiece& piece); - -#endif /* _PCRE_STRINGPIECE_H */ diff --git a/src/third_party/pcre-8.38/pcre_stringpiece_unittest.cc b/src/third_party/pcre-8.38/pcre_stringpiece_unittest.cc deleted file mode 100644 index 1c4759da3b0..00000000000 --- a/src/third_party/pcre-8.38/pcre_stringpiece_unittest.cc +++ /dev/null @@ -1,152 +0,0 @@ -// Copyright 2003 and onwards Google Inc. -// Author: Sanjay Ghemawat - -#ifdef HAVE_CONFIG_H -#include "config.h" -#endif - -#include <stdio.h> -#include <map> -#include <algorithm> // for make_pair - -#include "pcrecpp.h" -#include "pcre_stringpiece.h" - -// CHECK dies with a fatal error if condition is not true. It is *not* -// controlled by NDEBUG, so the check will be executed regardless of -// compilation mode. Therefore, it is safe to do things like: -// CHECK(fp->Write(x) == 4) -#define CHECK(condition) do { \ - if (!(condition)) { \ - fprintf(stderr, "%s:%d: Check failed: %s\n", \ - __FILE__, __LINE__, #condition); \ - exit(1); \ - } \ -} while (0) - -using pcrecpp::StringPiece; - -static void CheckSTLComparator() { - string s1("foo"); - string s2("bar"); - string s3("baz"); - - StringPiece p1(s1); - StringPiece p2(s2); - StringPiece p3(s3); - - typedef std::map<StringPiece, int> TestMap; - TestMap map; - - map.insert(std::make_pair(p1, 0)); - map.insert(std::make_pair(p2, 1)); - map.insert(std::make_pair(p3, 2)); - - CHECK(map.size() == 3); - - TestMap::const_iterator iter = map.begin(); - CHECK(iter->second == 1); - ++iter; - CHECK(iter->second == 2); - ++iter; - CHECK(iter->second == 0); - ++iter; - CHECK(iter == map.end()); - - TestMap::iterator new_iter = map.find("zot"); - CHECK(new_iter == map.end()); - - new_iter = map.find("bar"); - CHECK(new_iter != map.end()); - - map.erase(new_iter); - CHECK(map.size() == 2); - - iter = map.begin(); - CHECK(iter->second == 2); - ++iter; - CHECK(iter->second == 0); - ++iter; - CHECK(iter == map.end()); -} - -static void CheckComparisonOperators() { -#define CMP_Y(op, x, y) \ - CHECK( (StringPiece((x)) op StringPiece((y)))); \ - CHECK( (StringPiece((x)).compare(StringPiece((y))) op 0)) - -#define CMP_N(op, x, y) \ - CHECK(!(StringPiece((x)) op StringPiece((y)))); \ - CHECK(!(StringPiece((x)).compare(StringPiece((y))) op 0)) - - CMP_Y(==, "", ""); - CMP_Y(==, "a", "a"); - CMP_Y(==, "aa", "aa"); - CMP_N(==, "a", ""); - CMP_N(==, "", "a"); - CMP_N(==, "a", "b"); - CMP_N(==, "a", "aa"); - CMP_N(==, "aa", "a"); - - CMP_N(!=, "", ""); - CMP_N(!=, "a", "a"); - CMP_N(!=, "aa", "aa"); - CMP_Y(!=, "a", ""); - CMP_Y(!=, "", "a"); - CMP_Y(!=, "a", "b"); - CMP_Y(!=, "a", "aa"); - CMP_Y(!=, "aa", "a"); - - CMP_Y(<, "a", "b"); - CMP_Y(<, "a", "aa"); - CMP_Y(<, "aa", "b"); - CMP_Y(<, "aa", "bb"); - CMP_N(<, "a", "a"); - CMP_N(<, "b", "a"); - CMP_N(<, "aa", "a"); - CMP_N(<, "b", "aa"); - CMP_N(<, "bb", "aa"); - - CMP_Y(<=, "a", "a"); - CMP_Y(<=, "a", "b"); - CMP_Y(<=, "a", "aa"); - CMP_Y(<=, "aa", "b"); - CMP_Y(<=, "aa", "bb"); - CMP_N(<=, "b", "a"); - CMP_N(<=, "aa", "a"); - CMP_N(<=, "b", "aa"); - CMP_N(<=, "bb", "aa"); - - CMP_N(>=, "a", "b"); - CMP_N(>=, "a", "aa"); - CMP_N(>=, "aa", "b"); - CMP_N(>=, "aa", "bb"); - CMP_Y(>=, "a", "a"); - CMP_Y(>=, "b", "a"); - CMP_Y(>=, "aa", "a"); - CMP_Y(>=, "b", "aa"); - CMP_Y(>=, "bb", "aa"); - - CMP_N(>, "a", "a"); - CMP_N(>, "a", "b"); - CMP_N(>, "a", "aa"); - CMP_N(>, "aa", "b"); - CMP_N(>, "aa", "bb"); - CMP_Y(>, "b", "a"); - CMP_Y(>, "aa", "a"); - CMP_Y(>, "b", "aa"); - CMP_Y(>, "bb", "aa"); - -#undef CMP_Y -#undef CMP_N -} - -int main(int argc, char** argv) { - (void)argc; - (void)argv; - CheckComparisonOperators(); - CheckSTLComparator(); - - printf("OK\n"); - return 0; -} diff --git a/src/third_party/pcre-8.38/pcre_study.c b/src/third_party/pcre-8.38/pcre_study.c deleted file mode 100644 index 7fd0ba0b3d8..00000000000 --- a/src/third_party/pcre-8.38/pcre_study.c +++ /dev/null @@ -1,1686 +0,0 @@ -/************************************************* -* Perl-Compatible Regular Expressions * -*************************************************/ - -/* PCRE is a library of functions to support regular expressions whose syntax -and semantics are as close as possible to those of the Perl 5 language. - - Written by Philip Hazel - Copyright (c) 1997-2012 University of Cambridge - ------------------------------------------------------------------------------ -Redistribution and use in source and binary forms, with or without -modification, are permitted provided that the following conditions are met: - - * Redistributions of source code must retain the above copyright notice, - this list of conditions and the following disclaimer. - - * Redistributions in binary form must reproduce the above copyright - notice, this list of conditions and the following disclaimer in the - documentation and/or other materials provided with the distribution. - - * Neither the name of the University of Cambridge nor the names of its - contributors may be used to endorse or promote products derived from - this software without specific prior written permission. - -THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS" -AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE -IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE -ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR CONTRIBUTORS BE -LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR -CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF -SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS -INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN -CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) -ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE -POSSIBILITY OF SUCH DAMAGE. ------------------------------------------------------------------------------ -*/ - - -/* This module contains the external function pcre_study(), along with local -supporting functions. */ - - -#ifdef HAVE_CONFIG_H -#include "config.h" -#endif - -#include "pcre_internal.h" - -#define SET_BIT(c) start_bits[c/8] |= (1 << (c&7)) - -/* Returns from set_start_bits() */ - -enum { SSB_FAIL, SSB_DONE, SSB_CONTINUE, SSB_UNKNOWN }; - - - -/************************************************* -* Find the minimum subject length for a group * -*************************************************/ - -/* Scan a parenthesized group and compute the minimum length of subject that -is needed to match it. This is a lower bound; it does not mean there is a -string of that length that matches. In UTF8 mode, the result is in characters -rather than bytes. - -Arguments: - re compiled pattern block - code pointer to start of group (the bracket) - startcode pointer to start of the whole pattern's code - options the compiling options - recurses chain of recurse_check to catch mutual recursion - countptr pointer to call count (to catch over complexity) - -Returns: the minimum length - -1 if \C in UTF-8 mode or (*ACCEPT) was encountered - -2 internal error (missing capturing bracket) - -3 internal error (opcode not listed) -*/ - -static int -find_minlength(const REAL_PCRE *re, const pcre_uchar *code, - const pcre_uchar *startcode, int options, recurse_check *recurses, - int *countptr) -{ -int length = -1; -/* PCRE_UTF16 has the same value as PCRE_UTF8. */ -BOOL utf = (options & PCRE_UTF8) != 0; -BOOL had_recurse = FALSE; -recurse_check this_recurse; -register int branchlength = 0; -register pcre_uchar *cc = (pcre_uchar *)code + 1 + LINK_SIZE; - -if ((*countptr)++ > 1000) return -1; /* too complex */ - -if (*code == OP_CBRA || *code == OP_SCBRA || - *code == OP_CBRAPOS || *code == OP_SCBRAPOS) cc += IMM2_SIZE; - -/* Scan along the opcodes for this branch. If we get to the end of the -branch, check the length against that of the other branches. */ - -for (;;) - { - int d, min; - pcre_uchar *cs, *ce; - register pcre_uchar op = *cc; - - switch (op) - { - case OP_COND: - case OP_SCOND: - - /* If there is only one branch in a condition, the implied branch has zero - length, so we don't add anything. This covers the DEFINE "condition" - automatically. */ - - cs = cc + GET(cc, 1); - if (*cs != OP_ALT) - { - cc = cs + 1 + LINK_SIZE; - break; - } - - /* Otherwise we can fall through and treat it the same as any other - subpattern. */ - - case OP_CBRA: - case OP_SCBRA: - case OP_BRA: - case OP_SBRA: - case OP_CBRAPOS: - case OP_SCBRAPOS: - case OP_BRAPOS: - case OP_SBRAPOS: - case OP_ONCE: - case OP_ONCE_NC: - d = find_minlength(re, cc, startcode, options, recurses, countptr); - if (d < 0) return d; - branchlength += d; - do cc += GET(cc, 1); while (*cc == OP_ALT); - cc += 1 + LINK_SIZE; - break; - - /* ACCEPT makes things far too complicated; we have to give up. */ - - case OP_ACCEPT: - case OP_ASSERT_ACCEPT: - return -1; - - /* Reached end of a branch; if it's a ket it is the end of a nested - call. If it's ALT it is an alternation in a nested call. If it is END it's - the end of the outer call. All can be handled by the same code. If an - ACCEPT was previously encountered, use the length that was in force at that - time, and pass back the shortest ACCEPT length. */ - - case OP_ALT: - case OP_KET: - case OP_KETRMAX: - case OP_KETRMIN: - case OP_KETRPOS: - case OP_END: - if (length < 0 || (!had_recurse && branchlength < length)) - length = branchlength; - if (op != OP_ALT) return length; - cc += 1 + LINK_SIZE; - branchlength = 0; - had_recurse = FALSE; - break; - - /* Skip over assertive subpatterns */ - - case OP_ASSERT: - case OP_ASSERT_NOT: - case OP_ASSERTBACK: - case OP_ASSERTBACK_NOT: - do cc += GET(cc, 1); while (*cc == OP_ALT); - /* Fall through */ - - /* Skip over things that don't match chars */ - - case OP_REVERSE: - case OP_CREF: - case OP_DNCREF: - case OP_RREF: - case OP_DNRREF: - case OP_DEF: - case OP_CALLOUT: - case OP_SOD: - case OP_SOM: - case OP_EOD: - case OP_EODN: - case OP_CIRC: - case OP_CIRCM: - case OP_DOLL: - case OP_DOLLM: - case OP_NOT_WORD_BOUNDARY: - case OP_WORD_BOUNDARY: - cc += PRIV(OP_lengths)[*cc]; - break; - - /* Skip over a subpattern that has a {0} or {0,x} quantifier */ - - case OP_BRAZERO: - case OP_BRAMINZERO: - case OP_BRAPOSZERO: - case OP_SKIPZERO: - cc += PRIV(OP_lengths)[*cc]; - do cc += GET(cc, 1); while (*cc == OP_ALT); - cc += 1 + LINK_SIZE; - break; - - /* Handle literal characters and + repetitions */ - - case OP_CHAR: - case OP_CHARI: - case OP_NOT: - case OP_NOTI: - case OP_PLUS: - case OP_PLUSI: - case OP_MINPLUS: - case OP_MINPLUSI: - case OP_POSPLUS: - case OP_POSPLUSI: - case OP_NOTPLUS: - case OP_NOTPLUSI: - case OP_NOTMINPLUS: - case OP_NOTMINPLUSI: - case OP_NOTPOSPLUS: - case OP_NOTPOSPLUSI: - branchlength++; - cc += 2; -#ifdef SUPPORT_UTF - if (utf && HAS_EXTRALEN(cc[-1])) cc += GET_EXTRALEN(cc[-1]); -#endif - break; - - case OP_TYPEPLUS: - case OP_TYPEMINPLUS: - case OP_TYPEPOSPLUS: - branchlength++; - cc += (cc[1] == OP_PROP || cc[1] == OP_NOTPROP)? 4 : 2; - break; - - /* Handle exact repetitions. The count is already in characters, but we - need to skip over a multibyte character in UTF8 mode. */ - - case OP_EXACT: - case OP_EXACTI: - case OP_NOTEXACT: - case OP_NOTEXACTI: - branchlength += GET2(cc,1); - cc += 2 + IMM2_SIZE; -#ifdef SUPPORT_UTF - if (utf && HAS_EXTRALEN(cc[-1])) cc += GET_EXTRALEN(cc[-1]); -#endif - break; - - case OP_TYPEEXACT: - branchlength += GET2(cc,1); - cc += 2 + IMM2_SIZE + ((cc[1 + IMM2_SIZE] == OP_PROP - || cc[1 + IMM2_SIZE] == OP_NOTPROP)? 2 : 0); - break; - - /* Handle single-char non-literal matchers */ - - case OP_PROP: - case OP_NOTPROP: - cc += 2; - /* Fall through */ - - case OP_NOT_DIGIT: - case OP_DIGIT: - case OP_NOT_WHITESPACE: - case OP_WHITESPACE: - case OP_NOT_WORDCHAR: - case OP_WORDCHAR: - case OP_ANY: - case OP_ALLANY: - case OP_EXTUNI: - case OP_HSPACE: - case OP_NOT_HSPACE: - case OP_VSPACE: - case OP_NOT_VSPACE: - branchlength++; - cc++; - break; - - /* "Any newline" might match two characters, but it also might match just - one. */ - - case OP_ANYNL: - branchlength += 1; - cc++; - break; - - /* The single-byte matcher means we can't proceed in UTF-8 mode. (In - non-UTF-8 mode \C will actually be turned into OP_ALLANY, so won't ever - appear, but leave the code, just in case.) */ - - case OP_ANYBYTE: -#ifdef SUPPORT_UTF - if (utf) return -1; -#endif - branchlength++; - cc++; - break; - - /* For repeated character types, we have to test for \p and \P, which have - an extra two bytes of parameters. */ - - case OP_TYPESTAR: - case OP_TYPEMINSTAR: - case OP_TYPEQUERY: - case OP_TYPEMINQUERY: - case OP_TYPEPOSSTAR: - case OP_TYPEPOSQUERY: - if (cc[1] == OP_PROP || cc[1] == OP_NOTPROP) cc += 2; - cc += PRIV(OP_lengths)[op]; - break; - - case OP_TYPEUPTO: - case OP_TYPEMINUPTO: - case OP_TYPEPOSUPTO: - if (cc[1 + IMM2_SIZE] == OP_PROP - || cc[1 + IMM2_SIZE] == OP_NOTPROP) cc += 2; - cc += PRIV(OP_lengths)[op]; - break; - - /* Check a class for variable quantification */ - - case OP_CLASS: - case OP_NCLASS: -#if defined SUPPORT_UTF || defined COMPILE_PCRE16 || defined COMPILE_PCRE32 - case OP_XCLASS: - /* The original code caused an unsigned overflow in 64 bit systems, - so now we use a conditional statement. */ - if (op == OP_XCLASS) - cc += GET(cc, 1); - else - cc += PRIV(OP_lengths)[OP_CLASS]; -#else - cc += PRIV(OP_lengths)[OP_CLASS]; -#endif - - switch (*cc) - { - case OP_CRPLUS: - case OP_CRMINPLUS: - case OP_CRPOSPLUS: - branchlength++; - /* Fall through */ - - case OP_CRSTAR: - case OP_CRMINSTAR: - case OP_CRQUERY: - case OP_CRMINQUERY: - case OP_CRPOSSTAR: - case OP_CRPOSQUERY: - cc++; - break; - - case OP_CRRANGE: - case OP_CRMINRANGE: - case OP_CRPOSRANGE: - branchlength += GET2(cc,1); - cc += 1 + 2 * IMM2_SIZE; - break; - - default: - branchlength++; - break; - } - break; - - /* Backreferences and subroutine calls are treated in the same way: we find - the minimum length for the subpattern. A recursion, however, causes an - a flag to be set that causes the length of this branch to be ignored. The - logic is that a recursion can only make sense if there is another - alternation that stops the recursing. That will provide the minimum length - (when no recursion happens). A backreference within the group that it is - referencing behaves in the same way. - - If PCRE_JAVASCRIPT_COMPAT is set, a backreference to an unset bracket - matches an empty string (by default it causes a matching failure), so in - that case we must set the minimum length to zero. */ - - case OP_DNREF: /* Duplicate named pattern back reference */ - case OP_DNREFI: - if ((options & PCRE_JAVASCRIPT_COMPAT) == 0) - { - int count = GET2(cc, 1+IMM2_SIZE); - pcre_uchar *slot = (pcre_uchar *)re + - re->name_table_offset + GET2(cc, 1) * re->name_entry_size; - d = INT_MAX; - while (count-- > 0) - { - ce = cs = (pcre_uchar *)PRIV(find_bracket)(startcode, utf, GET2(slot, 0)); - if (cs == NULL) return -2; - do ce += GET(ce, 1); while (*ce == OP_ALT); - if (cc > cs && cc < ce) /* Simple recursion */ - { - d = 0; - had_recurse = TRUE; - break; - } - else - { - recurse_check *r = recurses; - for (r = recurses; r != NULL; r = r->prev) if (r->group == cs) break; - if (r != NULL) /* Mutual recursion */ - { - d = 0; - had_recurse = TRUE; - break; - } - else - { - int dd; - this_recurse.prev = recurses; - this_recurse.group = cs; - dd = find_minlength(re, cs, startcode, options, &this_recurse, - countptr); - if (dd < d) d = dd; - } - } - slot += re->name_entry_size; - } - } - else d = 0; - cc += 1 + 2*IMM2_SIZE; - goto REPEAT_BACK_REFERENCE; - - case OP_REF: /* Single back reference */ - case OP_REFI: - if ((options & PCRE_JAVASCRIPT_COMPAT) == 0) - { - ce = cs = (pcre_uchar *)PRIV(find_bracket)(startcode, utf, GET2(cc, 1)); - if (cs == NULL) return -2; - do ce += GET(ce, 1); while (*ce == OP_ALT); - if (cc > cs && cc < ce) /* Simple recursion */ - { - d = 0; - had_recurse = TRUE; - } - else - { - recurse_check *r = recurses; - for (r = recurses; r != NULL; r = r->prev) if (r->group == cs) break; - if (r != NULL) /* Mutual recursion */ - { - d = 0; - had_recurse = TRUE; - } - else - { - this_recurse.prev = recurses; - this_recurse.group = cs; - d = find_minlength(re, cs, startcode, options, &this_recurse, - countptr); - } - } - } - else d = 0; - cc += 1 + IMM2_SIZE; - - /* Handle repeated back references */ - - REPEAT_BACK_REFERENCE: - switch (*cc) - { - case OP_CRSTAR: - case OP_CRMINSTAR: - case OP_CRQUERY: - case OP_CRMINQUERY: - case OP_CRPOSSTAR: - case OP_CRPOSQUERY: - min = 0; - cc++; - break; - - case OP_CRPLUS: - case OP_CRMINPLUS: - case OP_CRPOSPLUS: - min = 1; - cc++; - break; - - case OP_CRRANGE: - case OP_CRMINRANGE: - case OP_CRPOSRANGE: - min = GET2(cc, 1); - cc += 1 + 2 * IMM2_SIZE; - break; - - default: - min = 1; - break; - } - - branchlength += min * d; - break; - - /* We can easily detect direct recursion, but not mutual recursion. This is - caught by a recursion depth count. */ - - case OP_RECURSE: - cs = ce = (pcre_uchar *)startcode + GET(cc, 1); - do ce += GET(ce, 1); while (*ce == OP_ALT); - if (cc > cs && cc < ce) /* Simple recursion */ - had_recurse = TRUE; - else - { - recurse_check *r = recurses; - for (r = recurses; r != NULL; r = r->prev) if (r->group == cs) break; - if (r != NULL) /* Mutual recursion */ - had_recurse = TRUE; - else - { - this_recurse.prev = recurses; - this_recurse.group = cs; - branchlength += find_minlength(re, cs, startcode, options, - &this_recurse, countptr); - } - } - cc += 1 + LINK_SIZE; - break; - - /* Anything else does not or need not match a character. We can get the - item's length from the table, but for those that can match zero occurrences - of a character, we must take special action for UTF-8 characters. As it - happens, the "NOT" versions of these opcodes are used at present only for - ASCII characters, so they could be omitted from this list. However, in - future that may change, so we include them here so as not to leave a - gotcha for a future maintainer. */ - - case OP_UPTO: - case OP_UPTOI: - case OP_NOTUPTO: - case OP_NOTUPTOI: - case OP_MINUPTO: - case OP_MINUPTOI: - case OP_NOTMINUPTO: - case OP_NOTMINUPTOI: - case OP_POSUPTO: - case OP_POSUPTOI: - case OP_NOTPOSUPTO: - case OP_NOTPOSUPTOI: - - case OP_STAR: - case OP_STARI: - case OP_NOTSTAR: - case OP_NOTSTARI: - case OP_MINSTAR: - case OP_MINSTARI: - case OP_NOTMINSTAR: - case OP_NOTMINSTARI: - case OP_POSSTAR: - case OP_POSSTARI: - case OP_NOTPOSSTAR: - case OP_NOTPOSSTARI: - - case OP_QUERY: - case OP_QUERYI: - case OP_NOTQUERY: - case OP_NOTQUERYI: - case OP_MINQUERY: - case OP_MINQUERYI: - case OP_NOTMINQUERY: - case OP_NOTMINQUERYI: - case OP_POSQUERY: - case OP_POSQUERYI: - case OP_NOTPOSQUERY: - case OP_NOTPOSQUERYI: - - cc += PRIV(OP_lengths)[op]; -#ifdef SUPPORT_UTF - if (utf && HAS_EXTRALEN(cc[-1])) cc += GET_EXTRALEN(cc[-1]); -#endif - break; - - /* Skip these, but we need to add in the name length. */ - - case OP_MARK: - case OP_PRUNE_ARG: - case OP_SKIP_ARG: - case OP_THEN_ARG: - cc += PRIV(OP_lengths)[op] + cc[1]; - break; - - /* The remaining opcodes are just skipped over. */ - - case OP_CLOSE: - case OP_COMMIT: - case OP_FAIL: - case OP_PRUNE: - case OP_SET_SOM: - case OP_SKIP: - case OP_THEN: - cc += PRIV(OP_lengths)[op]; - break; - - /* This should not occur: we list all opcodes explicitly so that when - new ones get added they are properly considered. */ - - default: - return -3; - } - } -/* Control never gets here */ -} - - - -/************************************************* -* Set a bit and maybe its alternate case * -*************************************************/ - -/* Given a character, set its first byte's bit in the table, and also the -corresponding bit for the other version of a letter if we are caseless. In -UTF-8 mode, for characters greater than 127, we can only do the caseless thing -when Unicode property support is available. - -Arguments: - start_bits points to the bit map - p points to the character - caseless the caseless flag - cd the block with char table pointers - utf TRUE for UTF-8 / UTF-16 / UTF-32 mode - -Returns: pointer after the character -*/ - -static const pcre_uchar * -set_table_bit(pcre_uint8 *start_bits, const pcre_uchar *p, BOOL caseless, - compile_data *cd, BOOL utf) -{ -pcre_uint32 c = *p; - -#ifdef COMPILE_PCRE8 -SET_BIT(c); - -#ifdef SUPPORT_UTF -if (utf && c > 127) - { - GETCHARINC(c, p); -#ifdef SUPPORT_UCP - if (caseless) - { - pcre_uchar buff[6]; - c = UCD_OTHERCASE(c); - (void)PRIV(ord2utf)(c, buff); - SET_BIT(buff[0]); - } -#endif /* Not SUPPORT_UCP */ - return p; - } -#else /* Not SUPPORT_UTF */ -(void)(utf); /* Stops warning for unused parameter */ -#endif /* SUPPORT_UTF */ - -/* Not UTF-8 mode, or character is less than 127. */ - -if (caseless && (cd->ctypes[c] & ctype_letter) != 0) SET_BIT(cd->fcc[c]); -return p + 1; -#endif /* COMPILE_PCRE8 */ - -#if defined COMPILE_PCRE16 || defined COMPILE_PCRE32 -if (c > 0xff) - { - c = 0xff; - caseless = FALSE; - } -SET_BIT(c); - -#ifdef SUPPORT_UTF -if (utf && c > 127) - { - GETCHARINC(c, p); -#ifdef SUPPORT_UCP - if (caseless) - { - c = UCD_OTHERCASE(c); - if (c > 0xff) - c = 0xff; - SET_BIT(c); - } -#endif /* SUPPORT_UCP */ - return p; - } -#else /* Not SUPPORT_UTF */ -(void)(utf); /* Stops warning for unused parameter */ -#endif /* SUPPORT_UTF */ - -if (caseless && (cd->ctypes[c] & ctype_letter) != 0) SET_BIT(cd->fcc[c]); -return p + 1; -#endif -} - - - -/************************************************* -* Set bits for a positive character type * -*************************************************/ - -/* This function sets starting bits for a character type. In UTF-8 mode, we can -only do a direct setting for bytes less than 128, as otherwise there can be -confusion with bytes in the middle of UTF-8 characters. In a "traditional" -environment, the tables will only recognize ASCII characters anyway, but in at -least one Windows environment, some higher bytes bits were set in the tables. -So we deal with that case by considering the UTF-8 encoding. - -Arguments: - start_bits the starting bitmap - cbit type the type of character wanted - table_limit 32 for non-UTF-8; 16 for UTF-8 - cd the block with char table pointers - -Returns: nothing -*/ - -static void -set_type_bits(pcre_uint8 *start_bits, int cbit_type, unsigned int table_limit, - compile_data *cd) -{ -register pcre_uint32 c; -for (c = 0; c < table_limit; c++) start_bits[c] |= cd->cbits[c+cbit_type]; -#if defined SUPPORT_UTF && defined COMPILE_PCRE8 -if (table_limit == 32) return; -for (c = 128; c < 256; c++) - { - if ((cd->cbits[c/8] & (1 << (c&7))) != 0) - { - pcre_uchar buff[6]; - (void)PRIV(ord2utf)(c, buff); - SET_BIT(buff[0]); - } - } -#endif -} - - -/************************************************* -* Set bits for a negative character type * -*************************************************/ - -/* This function sets starting bits for a negative character type such as \D. -In UTF-8 mode, we can only do a direct setting for bytes less than 128, as -otherwise there can be confusion with bytes in the middle of UTF-8 characters. -Unlike in the positive case, where we can set appropriate starting bits for -specific high-valued UTF-8 characters, in this case we have to set the bits for -all high-valued characters. The lowest is 0xc2, but we overkill by starting at -0xc0 (192) for simplicity. - -Arguments: - start_bits the starting bitmap - cbit type the type of character wanted - table_limit 32 for non-UTF-8; 16 for UTF-8 - cd the block with char table pointers - -Returns: nothing -*/ - -static void -set_nottype_bits(pcre_uint8 *start_bits, int cbit_type, unsigned int table_limit, - compile_data *cd) -{ -register pcre_uint32 c; -for (c = 0; c < table_limit; c++) start_bits[c] |= ~cd->cbits[c+cbit_type]; -#if defined SUPPORT_UTF && defined COMPILE_PCRE8 -if (table_limit != 32) for (c = 24; c < 32; c++) start_bits[c] = 0xff; -#endif -} - - - -/************************************************* -* Create bitmap of starting bytes * -*************************************************/ - -/* This function scans a compiled unanchored expression recursively and -attempts to build a bitmap of the set of possible starting bytes. As time goes -by, we may be able to get more clever at doing this. The SSB_CONTINUE return is -useful for parenthesized groups in patterns such as (a*)b where the group -provides some optional starting bytes but scanning must continue at the outer -level to find at least one mandatory byte. At the outermost level, this -function fails unless the result is SSB_DONE. - -Arguments: - code points to an expression - start_bits points to a 32-byte table, initialized to 0 - utf TRUE if in UTF-8 / UTF-16 / UTF-32 mode - cd the block with char table pointers - -Returns: SSB_FAIL => Failed to find any starting bytes - SSB_DONE => Found mandatory starting bytes - SSB_CONTINUE => Found optional starting bytes - SSB_UNKNOWN => Hit an unrecognized opcode -*/ - -static int -set_start_bits(const pcre_uchar *code, pcre_uint8 *start_bits, BOOL utf, - compile_data *cd) -{ -register pcre_uint32 c; -int yield = SSB_DONE; -#if defined SUPPORT_UTF && defined COMPILE_PCRE8 -int table_limit = utf? 16:32; -#else -int table_limit = 32; -#endif - -#if 0 -/* ========================================================================= */ -/* The following comment and code was inserted in January 1999. In May 2006, -when it was observed to cause compiler warnings about unused values, I took it -out again. If anybody is still using OS/2, they will have to put it back -manually. */ - -/* This next statement and the later reference to dummy are here in order to -trick the optimizer of the IBM C compiler for OS/2 into generating correct -code. Apparently IBM isn't going to fix the problem, and we would rather not -disable optimization (in this module it actually makes a big difference, and -the pcre module can use all the optimization it can get). */ - -volatile int dummy; -/* ========================================================================= */ -#endif - -do - { - BOOL try_next = TRUE; - const pcre_uchar *tcode = code + 1 + LINK_SIZE; - - if (*code == OP_CBRA || *code == OP_SCBRA || - *code == OP_CBRAPOS || *code == OP_SCBRAPOS) tcode += IMM2_SIZE; - - while (try_next) /* Loop for items in this branch */ - { - int rc; - - switch(*tcode) - { - /* If we reach something we don't understand, it means a new opcode has - been created that hasn't been added to this code. Hopefully this problem - will be discovered during testing. */ - - default: - return SSB_UNKNOWN; - - /* Fail for a valid opcode that implies no starting bits. */ - - case OP_ACCEPT: - case OP_ASSERT_ACCEPT: - case OP_ALLANY: - case OP_ANY: - case OP_ANYBYTE: - case OP_CIRC: - case OP_CIRCM: - case OP_CLOSE: - case OP_COMMIT: - case OP_COND: - case OP_CREF: - case OP_DEF: - case OP_DNCREF: - case OP_DNREF: - case OP_DNREFI: - case OP_DNRREF: - case OP_DOLL: - case OP_DOLLM: - case OP_END: - case OP_EOD: - case OP_EODN: - case OP_EXTUNI: - case OP_FAIL: - case OP_MARK: - case OP_NOT: - case OP_NOTEXACT: - case OP_NOTEXACTI: - case OP_NOTI: - case OP_NOTMINPLUS: - case OP_NOTMINPLUSI: - case OP_NOTMINQUERY: - case OP_NOTMINQUERYI: - case OP_NOTMINSTAR: - case OP_NOTMINSTARI: - case OP_NOTMINUPTO: - case OP_NOTMINUPTOI: - case OP_NOTPLUS: - case OP_NOTPLUSI: - case OP_NOTPOSPLUS: - case OP_NOTPOSPLUSI: - case OP_NOTPOSQUERY: - case OP_NOTPOSQUERYI: - case OP_NOTPOSSTAR: - case OP_NOTPOSSTARI: - case OP_NOTPOSUPTO: - case OP_NOTPOSUPTOI: - case OP_NOTPROP: - case OP_NOTQUERY: - case OP_NOTQUERYI: - case OP_NOTSTAR: - case OP_NOTSTARI: - case OP_NOTUPTO: - case OP_NOTUPTOI: - case OP_NOT_HSPACE: - case OP_NOT_VSPACE: - case OP_PRUNE: - case OP_PRUNE_ARG: - case OP_RECURSE: - case OP_REF: - case OP_REFI: - case OP_REVERSE: - case OP_RREF: - case OP_SCOND: - case OP_SET_SOM: - case OP_SKIP: - case OP_SKIP_ARG: - case OP_SOD: - case OP_SOM: - case OP_THEN: - case OP_THEN_ARG: - return SSB_FAIL; - - /* A "real" property test implies no starting bits, but the fake property - PT_CLIST identifies a list of characters. These lists are short, as they - are used for characters with more than one "other case", so there is no - point in recognizing them for OP_NOTPROP. */ - - case OP_PROP: - if (tcode[1] != PT_CLIST) return SSB_FAIL; - { - const pcre_uint32 *p = PRIV(ucd_caseless_sets) + tcode[2]; - while ((c = *p++) < NOTACHAR) - { -#if defined SUPPORT_UTF && defined COMPILE_PCRE8 - if (utf) - { - pcre_uchar buff[6]; - (void)PRIV(ord2utf)(c, buff); - c = buff[0]; - } -#endif - if (c > 0xff) SET_BIT(0xff); else SET_BIT(c); - } - } - try_next = FALSE; - break; - - /* We can ignore word boundary tests. */ - - case OP_WORD_BOUNDARY: - case OP_NOT_WORD_BOUNDARY: - tcode++; - break; - - /* If we hit a bracket or a positive lookahead assertion, recurse to set - bits from within the subpattern. If it can't find anything, we have to - give up. If it finds some mandatory character(s), we are done for this - branch. Otherwise, carry on scanning after the subpattern. */ - - case OP_BRA: - case OP_SBRA: - case OP_CBRA: - case OP_SCBRA: - case OP_BRAPOS: - case OP_SBRAPOS: - case OP_CBRAPOS: - case OP_SCBRAPOS: - case OP_ONCE: - case OP_ONCE_NC: - case OP_ASSERT: - rc = set_start_bits(tcode, start_bits, utf, cd); - if (rc == SSB_FAIL || rc == SSB_UNKNOWN) return rc; - if (rc == SSB_DONE) try_next = FALSE; else - { - do tcode += GET(tcode, 1); while (*tcode == OP_ALT); - tcode += 1 + LINK_SIZE; - } - break; - - /* If we hit ALT or KET, it means we haven't found anything mandatory in - this branch, though we might have found something optional. For ALT, we - continue with the next alternative, but we have to arrange that the final - result from subpattern is SSB_CONTINUE rather than SSB_DONE. For KET, - return SSB_CONTINUE: if this is the top level, that indicates failure, - but after a nested subpattern, it causes scanning to continue. */ - - case OP_ALT: - yield = SSB_CONTINUE; - try_next = FALSE; - break; - - case OP_KET: - case OP_KETRMAX: - case OP_KETRMIN: - case OP_KETRPOS: - return SSB_CONTINUE; - - /* Skip over callout */ - - case OP_CALLOUT: - tcode += 2 + 2*LINK_SIZE; - break; - - /* Skip over lookbehind and negative lookahead assertions */ - - case OP_ASSERT_NOT: - case OP_ASSERTBACK: - case OP_ASSERTBACK_NOT: - do tcode += GET(tcode, 1); while (*tcode == OP_ALT); - tcode += 1 + LINK_SIZE; - break; - - /* BRAZERO does the bracket, but carries on. */ - - case OP_BRAZERO: - case OP_BRAMINZERO: - case OP_BRAPOSZERO: - rc = set_start_bits(++tcode, start_bits, utf, cd); - if (rc == SSB_FAIL || rc == SSB_UNKNOWN) return rc; -/* ========================================================================= - See the comment at the head of this function concerning the next line, - which was an old fudge for the benefit of OS/2. - dummy = 1; - ========================================================================= */ - do tcode += GET(tcode,1); while (*tcode == OP_ALT); - tcode += 1 + LINK_SIZE; - break; - - /* SKIPZERO skips the bracket. */ - - case OP_SKIPZERO: - tcode++; - do tcode += GET(tcode,1); while (*tcode == OP_ALT); - tcode += 1 + LINK_SIZE; - break; - - /* Single-char * or ? sets the bit and tries the next item */ - - case OP_STAR: - case OP_MINSTAR: - case OP_POSSTAR: - case OP_QUERY: - case OP_MINQUERY: - case OP_POSQUERY: - tcode = set_table_bit(start_bits, tcode + 1, FALSE, cd, utf); - break; - - case OP_STARI: - case OP_MINSTARI: - case OP_POSSTARI: - case OP_QUERYI: - case OP_MINQUERYI: - case OP_POSQUERYI: - tcode = set_table_bit(start_bits, tcode + 1, TRUE, cd, utf); - break; - - /* Single-char upto sets the bit and tries the next */ - - case OP_UPTO: - case OP_MINUPTO: - case OP_POSUPTO: - tcode = set_table_bit(start_bits, tcode + 1 + IMM2_SIZE, FALSE, cd, utf); - break; - - case OP_UPTOI: - case OP_MINUPTOI: - case OP_POSUPTOI: - tcode = set_table_bit(start_bits, tcode + 1 + IMM2_SIZE, TRUE, cd, utf); - break; - - /* At least one single char sets the bit and stops */ - - case OP_EXACT: - tcode += IMM2_SIZE; - /* Fall through */ - case OP_CHAR: - case OP_PLUS: - case OP_MINPLUS: - case OP_POSPLUS: - (void)set_table_bit(start_bits, tcode + 1, FALSE, cd, utf); - try_next = FALSE; - break; - - case OP_EXACTI: - tcode += IMM2_SIZE; - /* Fall through */ - case OP_CHARI: - case OP_PLUSI: - case OP_MINPLUSI: - case OP_POSPLUSI: - (void)set_table_bit(start_bits, tcode + 1, TRUE, cd, utf); - try_next = FALSE; - break; - - /* Special spacing and line-terminating items. These recognize specific - lists of characters. The difference between VSPACE and ANYNL is that the - latter can match the two-character CRLF sequence, but that is not - relevant for finding the first character, so their code here is - identical. */ - - case OP_HSPACE: - SET_BIT(CHAR_HT); - SET_BIT(CHAR_SPACE); -#ifdef SUPPORT_UTF - if (utf) - { -#ifdef COMPILE_PCRE8 - SET_BIT(0xC2); /* For U+00A0 */ - SET_BIT(0xE1); /* For U+1680, U+180E */ - SET_BIT(0xE2); /* For U+2000 - U+200A, U+202F, U+205F */ - SET_BIT(0xE3); /* For U+3000 */ -#elif defined COMPILE_PCRE16 || defined COMPILE_PCRE32 - SET_BIT(0xA0); - SET_BIT(0xFF); /* For characters > 255 */ -#endif /* COMPILE_PCRE[8|16|32] */ - } - else -#endif /* SUPPORT_UTF */ - { -#ifndef EBCDIC - SET_BIT(0xA0); -#endif /* Not EBCDIC */ -#if defined COMPILE_PCRE16 || defined COMPILE_PCRE32 - SET_BIT(0xFF); /* For characters > 255 */ -#endif /* COMPILE_PCRE[16|32] */ - } - try_next = FALSE; - break; - - case OP_ANYNL: - case OP_VSPACE: - SET_BIT(CHAR_LF); - SET_BIT(CHAR_VT); - SET_BIT(CHAR_FF); - SET_BIT(CHAR_CR); -#ifdef SUPPORT_UTF - if (utf) - { -#ifdef COMPILE_PCRE8 - SET_BIT(0xC2); /* For U+0085 */ - SET_BIT(0xE2); /* For U+2028, U+2029 */ -#elif defined COMPILE_PCRE16 || defined COMPILE_PCRE32 - SET_BIT(CHAR_NEL); - SET_BIT(0xFF); /* For characters > 255 */ -#endif /* COMPILE_PCRE[8|16|32] */ - } - else -#endif /* SUPPORT_UTF */ - { - SET_BIT(CHAR_NEL); -#if defined COMPILE_PCRE16 || defined COMPILE_PCRE32 - SET_BIT(0xFF); /* For characters > 255 */ -#endif - } - try_next = FALSE; - break; - - /* Single character types set the bits and stop. Note that if PCRE_UCP - is set, we do not see these op codes because \d etc are converted to - properties. Therefore, these apply in the case when only characters less - than 256 are recognized to match the types. */ - - case OP_NOT_DIGIT: - set_nottype_bits(start_bits, cbit_digit, table_limit, cd); - try_next = FALSE; - break; - - case OP_DIGIT: - set_type_bits(start_bits, cbit_digit, table_limit, cd); - try_next = FALSE; - break; - - /* The cbit_space table has vertical tab as whitespace; we no longer - have to play fancy tricks because Perl added VT to its whitespace at - release 5.18. PCRE added it at release 8.34. */ - - case OP_NOT_WHITESPACE: - set_nottype_bits(start_bits, cbit_space, table_limit, cd); - try_next = FALSE; - break; - - case OP_WHITESPACE: - set_type_bits(start_bits, cbit_space, table_limit, cd); - try_next = FALSE; - break; - - case OP_NOT_WORDCHAR: - set_nottype_bits(start_bits, cbit_word, table_limit, cd); - try_next = FALSE; - break; - - case OP_WORDCHAR: - set_type_bits(start_bits, cbit_word, table_limit, cd); - try_next = FALSE; - break; - - /* One or more character type fudges the pointer and restarts, knowing - it will hit a single character type and stop there. */ - - case OP_TYPEPLUS: - case OP_TYPEMINPLUS: - case OP_TYPEPOSPLUS: - tcode++; - break; - - case OP_TYPEEXACT: - tcode += 1 + IMM2_SIZE; - break; - - /* Zero or more repeats of character types set the bits and then - try again. */ - - case OP_TYPEUPTO: - case OP_TYPEMINUPTO: - case OP_TYPEPOSUPTO: - tcode += IMM2_SIZE; /* Fall through */ - - case OP_TYPESTAR: - case OP_TYPEMINSTAR: - case OP_TYPEPOSSTAR: - case OP_TYPEQUERY: - case OP_TYPEMINQUERY: - case OP_TYPEPOSQUERY: - switch(tcode[1]) - { - default: - case OP_ANY: - case OP_ALLANY: - return SSB_FAIL; - - case OP_HSPACE: - SET_BIT(CHAR_HT); - SET_BIT(CHAR_SPACE); -#ifdef SUPPORT_UTF - if (utf) - { -#ifdef COMPILE_PCRE8 - SET_BIT(0xC2); /* For U+00A0 */ - SET_BIT(0xE1); /* For U+1680, U+180E */ - SET_BIT(0xE2); /* For U+2000 - U+200A, U+202F, U+205F */ - SET_BIT(0xE3); /* For U+3000 */ -#elif defined COMPILE_PCRE16 || defined COMPILE_PCRE32 - SET_BIT(0xA0); - SET_BIT(0xFF); /* For characters > 255 */ -#endif /* COMPILE_PCRE[8|16|32] */ - } - else -#endif /* SUPPORT_UTF */ -#ifndef EBCDIC - SET_BIT(0xA0); -#endif /* Not EBCDIC */ - break; - - case OP_ANYNL: - case OP_VSPACE: - SET_BIT(CHAR_LF); - SET_BIT(CHAR_VT); - SET_BIT(CHAR_FF); - SET_BIT(CHAR_CR); -#ifdef SUPPORT_UTF - if (utf) - { -#ifdef COMPILE_PCRE8 - SET_BIT(0xC2); /* For U+0085 */ - SET_BIT(0xE2); /* For U+2028, U+2029 */ -#elif defined COMPILE_PCRE16 || defined COMPILE_PCRE32 - SET_BIT(CHAR_NEL); - SET_BIT(0xFF); /* For characters > 255 */ -#endif /* COMPILE_PCRE16 */ - } - else -#endif /* SUPPORT_UTF */ - SET_BIT(CHAR_NEL); - break; - - case OP_NOT_DIGIT: - set_nottype_bits(start_bits, cbit_digit, table_limit, cd); - break; - - case OP_DIGIT: - set_type_bits(start_bits, cbit_digit, table_limit, cd); - break; - - /* The cbit_space table has vertical tab as whitespace; we no longer - have to play fancy tricks because Perl added VT to its whitespace at - release 5.18. PCRE added it at release 8.34. */ - - case OP_NOT_WHITESPACE: - set_nottype_bits(start_bits, cbit_space, table_limit, cd); - break; - - case OP_WHITESPACE: - set_type_bits(start_bits, cbit_space, table_limit, cd); - break; - - case OP_NOT_WORDCHAR: - set_nottype_bits(start_bits, cbit_word, table_limit, cd); - break; - - case OP_WORDCHAR: - set_type_bits(start_bits, cbit_word, table_limit, cd); - break; - } - - tcode += 2; - break; - - /* Character class where all the information is in a bit map: set the - bits and either carry on or not, according to the repeat count. If it was - a negative class, and we are operating with UTF-8 characters, any byte - with a value >= 0xc4 is a potentially valid starter because it starts a - character with a value > 255. */ - -#if defined SUPPORT_UTF || !defined COMPILE_PCRE8 - case OP_XCLASS: - if ((tcode[1 + LINK_SIZE] & XCL_HASPROP) != 0) - return SSB_FAIL; - /* All bits are set. */ - if ((tcode[1 + LINK_SIZE] & XCL_MAP) == 0 && (tcode[1 + LINK_SIZE] & XCL_NOT) != 0) - return SSB_FAIL; -#endif - /* Fall through */ - - case OP_NCLASS: -#if defined SUPPORT_UTF && defined COMPILE_PCRE8 - if (utf) - { - start_bits[24] |= 0xf0; /* Bits for 0xc4 - 0xc8 */ - memset(start_bits+25, 0xff, 7); /* Bits for 0xc9 - 0xff */ - } -#endif -#if defined COMPILE_PCRE16 || defined COMPILE_PCRE32 - SET_BIT(0xFF); /* For characters > 255 */ -#endif - /* Fall through */ - - case OP_CLASS: - { - pcre_uint8 *map; -#if defined SUPPORT_UTF || !defined COMPILE_PCRE8 - map = NULL; - if (*tcode == OP_XCLASS) - { - if ((tcode[1 + LINK_SIZE] & XCL_MAP) != 0) - map = (pcre_uint8 *)(tcode + 1 + LINK_SIZE + 1); - tcode += GET(tcode, 1); - } - else -#endif - { - tcode++; - map = (pcre_uint8 *)tcode; - tcode += 32 / sizeof(pcre_uchar); - } - - /* In UTF-8 mode, the bits in a bit map correspond to character - values, not to byte values. However, the bit map we are constructing is - for byte values. So we have to do a conversion for characters whose - value is > 127. In fact, there are only two possible starting bytes for - characters in the range 128 - 255. */ - -#if defined SUPPORT_UTF || !defined COMPILE_PCRE8 - if (map != NULL) -#endif - { -#if defined SUPPORT_UTF && defined COMPILE_PCRE8 - if (utf) - { - for (c = 0; c < 16; c++) start_bits[c] |= map[c]; - for (c = 128; c < 256; c++) - { - if ((map[c/8] && (1 << (c&7))) != 0) - { - int d = (c >> 6) | 0xc0; /* Set bit for this starter */ - start_bits[d/8] |= (1 << (d&7)); /* and then skip on to the */ - c = (c & 0xc0) + 0x40 - 1; /* next relevant character. */ - } - } - } - else -#endif - { - /* In non-UTF-8 mode, the two bit maps are completely compatible. */ - for (c = 0; c < 32; c++) start_bits[c] |= map[c]; - } - } - - /* Advance past the bit map, and act on what follows. For a zero - minimum repeat, continue; otherwise stop processing. */ - - switch (*tcode) - { - case OP_CRSTAR: - case OP_CRMINSTAR: - case OP_CRQUERY: - case OP_CRMINQUERY: - case OP_CRPOSSTAR: - case OP_CRPOSQUERY: - tcode++; - break; - - case OP_CRRANGE: - case OP_CRMINRANGE: - case OP_CRPOSRANGE: - if (GET2(tcode, 1) == 0) tcode += 1 + 2 * IMM2_SIZE; - else try_next = FALSE; - break; - - default: - try_next = FALSE; - break; - } - } - break; /* End of bitmap class handling */ - - } /* End of switch */ - } /* End of try_next loop */ - - code += GET(code, 1); /* Advance to next branch */ - } -while (*code == OP_ALT); -return yield; -} - - - - - -/************************************************* -* Study a compiled expression * -*************************************************/ - -/* This function is handed a compiled expression that it must study to produce -information that will speed up the matching. It returns a pcre[16]_extra block -which then gets handed back to pcre_exec(). - -Arguments: - re points to the compiled expression - options contains option bits - errorptr points to where to place error messages; - set NULL unless error - -Returns: pointer to a pcre[16]_extra block, with study_data filled in and - the appropriate flags set; - NULL on error or if no optimization possible -*/ - -#if defined COMPILE_PCRE8 -PCRE_EXP_DEFN pcre_extra * PCRE_CALL_CONVENTION -pcre_study(const pcre *external_re, int options, const char **errorptr) -#elif defined COMPILE_PCRE16 -PCRE_EXP_DEFN pcre16_extra * PCRE_CALL_CONVENTION -pcre16_study(const pcre16 *external_re, int options, const char **errorptr) -#elif defined COMPILE_PCRE32 -PCRE_EXP_DEFN pcre32_extra * PCRE_CALL_CONVENTION -pcre32_study(const pcre32 *external_re, int options, const char **errorptr) -#endif -{ -int min; -int count = 0; -BOOL bits_set = FALSE; -pcre_uint8 start_bits[32]; -PUBL(extra) *extra = NULL; -pcre_study_data *study; -const pcre_uint8 *tables; -pcre_uchar *code; -compile_data compile_block; -const REAL_PCRE *re = (const REAL_PCRE *)external_re; - - -*errorptr = NULL; - -if (re == NULL || re->magic_number != MAGIC_NUMBER) - { - *errorptr = "argument is not a compiled regular expression"; - return NULL; - } - -if ((re->flags & PCRE_MODE) == 0) - { -#if defined COMPILE_PCRE8 - *errorptr = "argument not compiled in 8 bit mode"; -#elif defined COMPILE_PCRE16 - *errorptr = "argument not compiled in 16 bit mode"; -#elif defined COMPILE_PCRE32 - *errorptr = "argument not compiled in 32 bit mode"; -#endif - return NULL; - } - -if ((options & ~PUBLIC_STUDY_OPTIONS) != 0) - { - *errorptr = "unknown or incorrect option bit(s) set"; - return NULL; - } - -code = (pcre_uchar *)re + re->name_table_offset + - (re->name_count * re->name_entry_size); - -/* For an anchored pattern, or an unanchored pattern that has a first char, or -a multiline pattern that matches only at "line starts", there is no point in -seeking a list of starting bytes. */ - -if ((re->options & PCRE_ANCHORED) == 0 && - (re->flags & (PCRE_FIRSTSET|PCRE_STARTLINE)) == 0) - { - int rc; - - /* Set the character tables in the block that is passed around */ - - tables = re->tables; - -#if defined COMPILE_PCRE8 - if (tables == NULL) - (void)pcre_fullinfo(external_re, NULL, PCRE_INFO_DEFAULT_TABLES, - (void *)(&tables)); -#elif defined COMPILE_PCRE16 - if (tables == NULL) - (void)pcre16_fullinfo(external_re, NULL, PCRE_INFO_DEFAULT_TABLES, - (void *)(&tables)); -#elif defined COMPILE_PCRE32 - if (tables == NULL) - (void)pcre32_fullinfo(external_re, NULL, PCRE_INFO_DEFAULT_TABLES, - (void *)(&tables)); -#endif - - compile_block.lcc = tables + lcc_offset; - compile_block.fcc = tables + fcc_offset; - compile_block.cbits = tables + cbits_offset; - compile_block.ctypes = tables + ctypes_offset; - - /* See if we can find a fixed set of initial characters for the pattern. */ - - memset(start_bits, 0, 32 * sizeof(pcre_uint8)); - rc = set_start_bits(code, start_bits, (re->options & PCRE_UTF8) != 0, - &compile_block); - bits_set = rc == SSB_DONE; - if (rc == SSB_UNKNOWN) - { - *errorptr = "internal error: opcode not recognized"; - return NULL; - } - } - -/* Find the minimum length of subject string. */ - -switch(min = find_minlength(re, code, code, re->options, NULL, &count)) - { - case -2: *errorptr = "internal error: missing capturing bracket"; return NULL; - case -3: *errorptr = "internal error: opcode not recognized"; return NULL; - default: break; - } - -/* If a set of starting bytes has been identified, or if the minimum length is -greater than zero, or if JIT optimization has been requested, or if -PCRE_STUDY_EXTRA_NEEDED is set, get a pcre[16]_extra block and a -pcre_study_data block. The study data is put in the latter, which is pointed to -by the former, which may also get additional data set later by the calling -program. At the moment, the size of pcre_study_data is fixed. We nevertheless -save it in a field for returning via the pcre_fullinfo() function so that if it -becomes variable in the future, we don't have to change that code. */ - -if (bits_set || min > 0 || (options & ( -#ifdef SUPPORT_JIT - PCRE_STUDY_JIT_COMPILE | PCRE_STUDY_JIT_PARTIAL_SOFT_COMPILE | - PCRE_STUDY_JIT_PARTIAL_HARD_COMPILE | -#endif - PCRE_STUDY_EXTRA_NEEDED)) != 0) - { - extra = (PUBL(extra) *)(PUBL(malloc)) - (sizeof(PUBL(extra)) + sizeof(pcre_study_data)); - if (extra == NULL) - { - *errorptr = "failed to get memory"; - return NULL; - } - - study = (pcre_study_data *)((char *)extra + sizeof(PUBL(extra))); - extra->flags = PCRE_EXTRA_STUDY_DATA; - extra->study_data = study; - - study->size = sizeof(pcre_study_data); - study->flags = 0; - - /* Set the start bits always, to avoid unset memory errors if the - study data is written to a file, but set the flag only if any of the bits - are set, to save time looking when none are. */ - - if (bits_set) - { - study->flags |= PCRE_STUDY_MAPPED; - memcpy(study->start_bits, start_bits, sizeof(start_bits)); - } - else memset(study->start_bits, 0, 32 * sizeof(pcre_uint8)); - -#ifdef PCRE_DEBUG - if (bits_set) - { - pcre_uint8 *ptr = start_bits; - int i; - - printf("Start bits:\n"); - for (i = 0; i < 32; i++) - printf("%3d: %02x%s", i * 8, *ptr++, ((i + 1) & 0x7) != 0? " " : "\n"); - } -#endif - - /* Always set the minlength value in the block, because the JIT compiler - makes use of it. However, don't set the bit unless the length is greater than - zero - the interpretive pcre_exec() and pcre_dfa_exec() needn't waste time - checking the zero case. */ - - if (min > 0) - { - study->flags |= PCRE_STUDY_MINLEN; - study->minlength = min; - } - else study->minlength = 0; - - /* If JIT support was compiled and requested, attempt the JIT compilation. - If no starting bytes were found, and the minimum length is zero, and JIT - compilation fails, abandon the extra block and return NULL, unless - PCRE_STUDY_EXTRA_NEEDED is set. */ - -#ifdef SUPPORT_JIT - extra->executable_jit = NULL; - if ((options & PCRE_STUDY_JIT_COMPILE) != 0) - PRIV(jit_compile)(re, extra, JIT_COMPILE); - if ((options & PCRE_STUDY_JIT_PARTIAL_SOFT_COMPILE) != 0) - PRIV(jit_compile)(re, extra, JIT_PARTIAL_SOFT_COMPILE); - if ((options & PCRE_STUDY_JIT_PARTIAL_HARD_COMPILE) != 0) - PRIV(jit_compile)(re, extra, JIT_PARTIAL_HARD_COMPILE); - - if (study->flags == 0 && (extra->flags & PCRE_EXTRA_EXECUTABLE_JIT) == 0 && - (options & PCRE_STUDY_EXTRA_NEEDED) == 0) - { -#if defined COMPILE_PCRE8 - pcre_free_study(extra); -#elif defined COMPILE_PCRE16 - pcre16_free_study(extra); -#elif defined COMPILE_PCRE32 - pcre32_free_study(extra); -#endif - extra = NULL; - } -#endif - } - -return extra; -} - - -/************************************************* -* Free the study data * -*************************************************/ - -/* This function frees the memory that was obtained by pcre_study(). - -Argument: a pointer to the pcre[16]_extra block -Returns: nothing -*/ - -#if defined COMPILE_PCRE8 -PCRE_EXP_DEFN void -pcre_free_study(pcre_extra *extra) -#elif defined COMPILE_PCRE16 -PCRE_EXP_DEFN void -pcre16_free_study(pcre16_extra *extra) -#elif defined COMPILE_PCRE32 -PCRE_EXP_DEFN void -pcre32_free_study(pcre32_extra *extra) -#endif -{ -if (extra == NULL) - return; -#ifdef SUPPORT_JIT -if ((extra->flags & PCRE_EXTRA_EXECUTABLE_JIT) != 0 && - extra->executable_jit != NULL) - PRIV(jit_free)(extra->executable_jit); -#endif -PUBL(free)(extra); -} - -/* End of pcre_study.c */ diff --git a/src/third_party/pcre-8.38/pcre_tables.c b/src/third_party/pcre-8.38/pcre_tables.c deleted file mode 100644 index 4960af57c4d..00000000000 --- a/src/third_party/pcre-8.38/pcre_tables.c +++ /dev/null @@ -1,727 +0,0 @@ -/************************************************* -* Perl-Compatible Regular Expressions * -*************************************************/ - -/* PCRE is a library of functions to support regular expressions whose syntax -and semantics are as close as possible to those of the Perl 5 language. - - Written by Philip Hazel - Copyright (c) 1997-2012 University of Cambridge - ------------------------------------------------------------------------------ -Redistribution and use in source and binary forms, with or without -modification, are permitted provided that the following conditions are met: - - * Redistributions of source code must retain the above copyright notice, - this list of conditions and the following disclaimer. - - * Redistributions in binary form must reproduce the above copyright - notice, this list of conditions and the following disclaimer in the - documentation and/or other materials provided with the distribution. - - * Neither the name of the University of Cambridge nor the names of its - contributors may be used to endorse or promote products derived from - this software without specific prior written permission. - -THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS" -AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE -IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE -ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR CONTRIBUTORS BE -LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR -CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF -SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS -INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN -CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) -ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE -POSSIBILITY OF SUCH DAMAGE. ------------------------------------------------------------------------------ -*/ - -#ifndef PCRE_INCLUDED - -/* This module contains some fixed tables that are used by more than one of the -PCRE code modules. The tables are also #included by the pcretest program, which -uses macros to change their names from _pcre_xxx to xxxx, thereby avoiding name -clashes with the library. */ - - -#ifdef HAVE_CONFIG_H -#include "config.h" -#endif - -#include "pcre_internal.h" - -#endif /* PCRE_INCLUDED */ - -/* Table of sizes for the fixed-length opcodes. It's defined in a macro so that -the definition is next to the definition of the opcodes in pcre_internal.h. */ - -const pcre_uint8 PRIV(OP_lengths)[] = { OP_LENGTHS }; - -/* Tables of horizontal and vertical whitespace characters, suitable for -adding to classes. */ - -const pcre_uint32 PRIV(hspace_list)[] = { HSPACE_LIST }; -const pcre_uint32 PRIV(vspace_list)[] = { VSPACE_LIST }; - - - -/************************************************* -* Tables for UTF-8 support * -*************************************************/ - -/* These are the breakpoints for different numbers of bytes in a UTF-8 -character. */ - -#if (defined SUPPORT_UTF && defined COMPILE_PCRE8) \ - || (defined PCRE_INCLUDED && (defined SUPPORT_PCRE16 || defined SUPPORT_PCRE32)) - -/* These tables are also required by pcretest in 16- or 32-bit mode. */ - -const int PRIV(utf8_table1)[] = - { 0x7f, 0x7ff, 0xffff, 0x1fffff, 0x3ffffff, 0x7fffffff}; - -const int PRIV(utf8_table1_size) = sizeof(PRIV(utf8_table1)) / sizeof(int); - -/* These are the indicator bits and the mask for the data bits to set in the -first byte of a character, indexed by the number of additional bytes. */ - -const int PRIV(utf8_table2)[] = { 0, 0xc0, 0xe0, 0xf0, 0xf8, 0xfc}; -const int PRIV(utf8_table3)[] = { 0xff, 0x1f, 0x0f, 0x07, 0x03, 0x01}; - -/* Table of the number of extra bytes, indexed by the first byte masked with -0x3f. The highest number for a valid UTF-8 first byte is in fact 0x3d. */ - -const pcre_uint8 PRIV(utf8_table4)[] = { - 1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1, - 1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1, - 2,2,2,2,2,2,2,2,2,2,2,2,2,2,2,2, - 3,3,3,3,3,3,3,3,4,4,4,4,5,5,5,5 }; - -#endif /* (SUPPORT_UTF && COMPILE_PCRE8) || (PCRE_INCLUDED && SUPPORT_PCRE[16|32])*/ - -#ifdef SUPPORT_UTF - -/* Table to translate from particular type value to the general value. */ - -const pcre_uint32 PRIV(ucp_gentype)[] = { - ucp_C, ucp_C, ucp_C, ucp_C, ucp_C, /* Cc, Cf, Cn, Co, Cs */ - ucp_L, ucp_L, ucp_L, ucp_L, ucp_L, /* Ll, Lu, Lm, Lo, Lt */ - ucp_M, ucp_M, ucp_M, /* Mc, Me, Mn */ - ucp_N, ucp_N, ucp_N, /* Nd, Nl, No */ - ucp_P, ucp_P, ucp_P, ucp_P, ucp_P, /* Pc, Pd, Pe, Pf, Pi */ - ucp_P, ucp_P, /* Ps, Po */ - ucp_S, ucp_S, ucp_S, ucp_S, /* Sc, Sk, Sm, So */ - ucp_Z, ucp_Z, ucp_Z /* Zl, Zp, Zs */ -}; - -/* This table encodes the rules for finding the end of an extended grapheme -cluster. Every code point has a grapheme break property which is one of the -ucp_gbXX values defined in ucp.h. The 2-dimensional table is indexed by the -properties of two adjacent code points. The left property selects a word from -the table, and the right property selects a bit from that word like this: - - ucp_gbtable[left-property] & (1 << right-property) - -The value is non-zero if a grapheme break is NOT permitted between the relevant -two code points. The breaking rules are as follows: - -1. Break at the start and end of text (pretty obviously). - -2. Do not break between a CR and LF; otherwise, break before and after - controls. - -3. Do not break Hangul syllable sequences, the rules for which are: - - L may be followed by L, V, LV or LVT - LV or V may be followed by V or T - LVT or T may be followed by T - -4. Do not break before extending characters. - -The next two rules are only for extended grapheme clusters (but that's what we -are implementing). - -5. Do not break before SpacingMarks. - -6. Do not break after Prepend characters. - -7. Otherwise, break everywhere. -*/ - -const pcre_uint32 PRIV(ucp_gbtable[]) = { - (1<<ucp_gbLF), /* 0 CR */ - 0, /* 1 LF */ - 0, /* 2 Control */ - (1<<ucp_gbExtend)|(1<<ucp_gbSpacingMark), /* 3 Extend */ - (1<<ucp_gbExtend)|(1<<ucp_gbPrepend)| /* 4 Prepend */ - (1<<ucp_gbSpacingMark)|(1<<ucp_gbL)| - (1<<ucp_gbV)|(1<<ucp_gbT)|(1<<ucp_gbLV)| - (1<<ucp_gbLVT)|(1<<ucp_gbOther), - - (1<<ucp_gbExtend)|(1<<ucp_gbSpacingMark), /* 5 SpacingMark */ - (1<<ucp_gbExtend)|(1<<ucp_gbSpacingMark)|(1<<ucp_gbL)| /* 6 L */ - (1<<ucp_gbL)|(1<<ucp_gbV)|(1<<ucp_gbLV)|(1<<ucp_gbLVT), - - (1<<ucp_gbExtend)|(1<<ucp_gbSpacingMark)|(1<<ucp_gbV)| /* 7 V */ - (1<<ucp_gbT), - - (1<<ucp_gbExtend)|(1<<ucp_gbSpacingMark)|(1<<ucp_gbT), /* 8 T */ - (1<<ucp_gbExtend)|(1<<ucp_gbSpacingMark)|(1<<ucp_gbV)| /* 9 LV */ - (1<<ucp_gbT), - - (1<<ucp_gbExtend)|(1<<ucp_gbSpacingMark)|(1<<ucp_gbT), /* 10 LVT */ - (1<<ucp_gbRegionalIndicator), /* 11 RegionalIndicator */ - (1<<ucp_gbExtend)|(1<<ucp_gbSpacingMark) /* 12 Other */ -}; - -#ifdef SUPPORT_JIT -/* This table reverses PRIV(ucp_gentype). We can save the cost -of a memory load. */ - -const int PRIV(ucp_typerange)[] = { - ucp_Cc, ucp_Cs, - ucp_Ll, ucp_Lu, - ucp_Mc, ucp_Mn, - ucp_Nd, ucp_No, - ucp_Pc, ucp_Ps, - ucp_Sc, ucp_So, - ucp_Zl, ucp_Zs, -}; -#endif /* SUPPORT_JIT */ - -/* The pcre_utt[] table below translates Unicode property names into type and -code values. It is searched by binary chop, so must be in collating sequence of -name. Originally, the table contained pointers to the name strings in the first -field of each entry. However, that leads to a large number of relocations when -a shared library is dynamically loaded. A significant reduction is made by -putting all the names into a single, large string and then using offsets in the -table itself. Maintenance is more error-prone, but frequent changes to this -data are unlikely. - -July 2008: There is now a script called maint/GenerateUtt.py that can be used -to generate this data automatically instead of maintaining it by hand. - -The script was updated in March 2009 to generate a new EBCDIC-compliant -version. Like all other character and string literals that are compared against -the regular expression pattern, we must use STR_ macros instead of literal -strings to make sure that UTF-8 support works on EBCDIC platforms. */ - -#define STRING_Any0 STR_A STR_n STR_y "\0" -#define STRING_Arabic0 STR_A STR_r STR_a STR_b STR_i STR_c "\0" -#define STRING_Armenian0 STR_A STR_r STR_m STR_e STR_n STR_i STR_a STR_n "\0" -#define STRING_Avestan0 STR_A STR_v STR_e STR_s STR_t STR_a STR_n "\0" -#define STRING_Balinese0 STR_B STR_a STR_l STR_i STR_n STR_e STR_s STR_e "\0" -#define STRING_Bamum0 STR_B STR_a STR_m STR_u STR_m "\0" -#define STRING_Bassa_Vah0 STR_B STR_a STR_s STR_s STR_a STR_UNDERSCORE STR_V STR_a STR_h "\0" -#define STRING_Batak0 STR_B STR_a STR_t STR_a STR_k "\0" -#define STRING_Bengali0 STR_B STR_e STR_n STR_g STR_a STR_l STR_i "\0" -#define STRING_Bopomofo0 STR_B STR_o STR_p STR_o STR_m STR_o STR_f STR_o "\0" -#define STRING_Brahmi0 STR_B STR_r STR_a STR_h STR_m STR_i "\0" -#define STRING_Braille0 STR_B STR_r STR_a STR_i STR_l STR_l STR_e "\0" -#define STRING_Buginese0 STR_B STR_u STR_g STR_i STR_n STR_e STR_s STR_e "\0" -#define STRING_Buhid0 STR_B STR_u STR_h STR_i STR_d "\0" -#define STRING_C0 STR_C "\0" -#define STRING_Canadian_Aboriginal0 STR_C STR_a STR_n STR_a STR_d STR_i STR_a STR_n STR_UNDERSCORE STR_A STR_b STR_o STR_r STR_i STR_g STR_i STR_n STR_a STR_l "\0" -#define STRING_Carian0 STR_C STR_a STR_r STR_i STR_a STR_n "\0" -#define STRING_Caucasian_Albanian0 STR_C STR_a STR_u STR_c STR_a STR_s STR_i STR_a STR_n STR_UNDERSCORE STR_A STR_l STR_b STR_a STR_n STR_i STR_a STR_n "\0" -#define STRING_Cc0 STR_C STR_c "\0" -#define STRING_Cf0 STR_C STR_f "\0" -#define STRING_Chakma0 STR_C STR_h STR_a STR_k STR_m STR_a "\0" -#define STRING_Cham0 STR_C STR_h STR_a STR_m "\0" -#define STRING_Cherokee0 STR_C STR_h STR_e STR_r STR_o STR_k STR_e STR_e "\0" -#define STRING_Cn0 STR_C STR_n "\0" -#define STRING_Co0 STR_C STR_o "\0" -#define STRING_Common0 STR_C STR_o STR_m STR_m STR_o STR_n "\0" -#define STRING_Coptic0 STR_C STR_o STR_p STR_t STR_i STR_c "\0" -#define STRING_Cs0 STR_C STR_s "\0" -#define STRING_Cuneiform0 STR_C STR_u STR_n STR_e STR_i STR_f STR_o STR_r STR_m "\0" -#define STRING_Cypriot0 STR_C STR_y STR_p STR_r STR_i STR_o STR_t "\0" -#define STRING_Cyrillic0 STR_C STR_y STR_r STR_i STR_l STR_l STR_i STR_c "\0" -#define STRING_Deseret0 STR_D STR_e STR_s STR_e STR_r STR_e STR_t "\0" -#define STRING_Devanagari0 STR_D STR_e STR_v STR_a STR_n STR_a STR_g STR_a STR_r STR_i "\0" -#define STRING_Duployan0 STR_D STR_u STR_p STR_l STR_o STR_y STR_a STR_n "\0" -#define STRING_Egyptian_Hieroglyphs0 STR_E STR_g STR_y STR_p STR_t STR_i STR_a STR_n STR_UNDERSCORE STR_H STR_i STR_e STR_r STR_o STR_g STR_l STR_y STR_p STR_h STR_s "\0" -#define STRING_Elbasan0 STR_E STR_l STR_b STR_a STR_s STR_a STR_n "\0" -#define STRING_Ethiopic0 STR_E STR_t STR_h STR_i STR_o STR_p STR_i STR_c "\0" -#define STRING_Georgian0 STR_G STR_e STR_o STR_r STR_g STR_i STR_a STR_n "\0" -#define STRING_Glagolitic0 STR_G STR_l STR_a STR_g STR_o STR_l STR_i STR_t STR_i STR_c "\0" -#define STRING_Gothic0 STR_G STR_o STR_t STR_h STR_i STR_c "\0" -#define STRING_Grantha0 STR_G STR_r STR_a STR_n STR_t STR_h STR_a "\0" -#define STRING_Greek0 STR_G STR_r STR_e STR_e STR_k "\0" -#define STRING_Gujarati0 STR_G STR_u STR_j STR_a STR_r STR_a STR_t STR_i "\0" -#define STRING_Gurmukhi0 STR_G STR_u STR_r STR_m STR_u STR_k STR_h STR_i "\0" -#define STRING_Han0 STR_H STR_a STR_n "\0" -#define STRING_Hangul0 STR_H STR_a STR_n STR_g STR_u STR_l "\0" -#define STRING_Hanunoo0 STR_H STR_a STR_n STR_u STR_n STR_o STR_o "\0" -#define STRING_Hebrew0 STR_H STR_e STR_b STR_r STR_e STR_w "\0" -#define STRING_Hiragana0 STR_H STR_i STR_r STR_a STR_g STR_a STR_n STR_a "\0" -#define STRING_Imperial_Aramaic0 STR_I STR_m STR_p STR_e STR_r STR_i STR_a STR_l STR_UNDERSCORE STR_A STR_r STR_a STR_m STR_a STR_i STR_c "\0" -#define STRING_Inherited0 STR_I STR_n STR_h STR_e STR_r STR_i STR_t STR_e STR_d "\0" -#define STRING_Inscriptional_Pahlavi0 STR_I STR_n STR_s STR_c STR_r STR_i STR_p STR_t STR_i STR_o STR_n STR_a STR_l STR_UNDERSCORE STR_P STR_a STR_h STR_l STR_a STR_v STR_i "\0" -#define STRING_Inscriptional_Parthian0 STR_I STR_n STR_s STR_c STR_r STR_i STR_p STR_t STR_i STR_o STR_n STR_a STR_l STR_UNDERSCORE STR_P STR_a STR_r STR_t STR_h STR_i STR_a STR_n "\0" -#define STRING_Javanese0 STR_J STR_a STR_v STR_a STR_n STR_e STR_s STR_e "\0" -#define STRING_Kaithi0 STR_K STR_a STR_i STR_t STR_h STR_i "\0" -#define STRING_Kannada0 STR_K STR_a STR_n STR_n STR_a STR_d STR_a "\0" -#define STRING_Katakana0 STR_K STR_a STR_t STR_a STR_k STR_a STR_n STR_a "\0" -#define STRING_Kayah_Li0 STR_K STR_a STR_y STR_a STR_h STR_UNDERSCORE STR_L STR_i "\0" -#define STRING_Kharoshthi0 STR_K STR_h STR_a STR_r STR_o STR_s STR_h STR_t STR_h STR_i "\0" -#define STRING_Khmer0 STR_K STR_h STR_m STR_e STR_r "\0" -#define STRING_Khojki0 STR_K STR_h STR_o STR_j STR_k STR_i "\0" -#define STRING_Khudawadi0 STR_K STR_h STR_u STR_d STR_a STR_w STR_a STR_d STR_i "\0" -#define STRING_L0 STR_L "\0" -#define STRING_L_AMPERSAND0 STR_L STR_AMPERSAND "\0" -#define STRING_Lao0 STR_L STR_a STR_o "\0" -#define STRING_Latin0 STR_L STR_a STR_t STR_i STR_n "\0" -#define STRING_Lepcha0 STR_L STR_e STR_p STR_c STR_h STR_a "\0" -#define STRING_Limbu0 STR_L STR_i STR_m STR_b STR_u "\0" -#define STRING_Linear_A0 STR_L STR_i STR_n STR_e STR_a STR_r STR_UNDERSCORE STR_A "\0" -#define STRING_Linear_B0 STR_L STR_i STR_n STR_e STR_a STR_r STR_UNDERSCORE STR_B "\0" -#define STRING_Lisu0 STR_L STR_i STR_s STR_u "\0" -#define STRING_Ll0 STR_L STR_l "\0" -#define STRING_Lm0 STR_L STR_m "\0" -#define STRING_Lo0 STR_L STR_o "\0" -#define STRING_Lt0 STR_L STR_t "\0" -#define STRING_Lu0 STR_L STR_u "\0" -#define STRING_Lycian0 STR_L STR_y STR_c STR_i STR_a STR_n "\0" -#define STRING_Lydian0 STR_L STR_y STR_d STR_i STR_a STR_n "\0" -#define STRING_M0 STR_M "\0" -#define STRING_Mahajani0 STR_M STR_a STR_h STR_a STR_j STR_a STR_n STR_i "\0" -#define STRING_Malayalam0 STR_M STR_a STR_l STR_a STR_y STR_a STR_l STR_a STR_m "\0" -#define STRING_Mandaic0 STR_M STR_a STR_n STR_d STR_a STR_i STR_c "\0" -#define STRING_Manichaean0 STR_M STR_a STR_n STR_i STR_c STR_h STR_a STR_e STR_a STR_n "\0" -#define STRING_Mc0 STR_M STR_c "\0" -#define STRING_Me0 STR_M STR_e "\0" -#define STRING_Meetei_Mayek0 STR_M STR_e STR_e STR_t STR_e STR_i STR_UNDERSCORE STR_M STR_a STR_y STR_e STR_k "\0" -#define STRING_Mende_Kikakui0 STR_M STR_e STR_n STR_d STR_e STR_UNDERSCORE STR_K STR_i STR_k STR_a STR_k STR_u STR_i "\0" -#define STRING_Meroitic_Cursive0 STR_M STR_e STR_r STR_o STR_i STR_t STR_i STR_c STR_UNDERSCORE STR_C STR_u STR_r STR_s STR_i STR_v STR_e "\0" -#define STRING_Meroitic_Hieroglyphs0 STR_M STR_e STR_r STR_o STR_i STR_t STR_i STR_c STR_UNDERSCORE STR_H STR_i STR_e STR_r STR_o STR_g STR_l STR_y STR_p STR_h STR_s "\0" -#define STRING_Miao0 STR_M STR_i STR_a STR_o "\0" -#define STRING_Mn0 STR_M STR_n "\0" -#define STRING_Modi0 STR_M STR_o STR_d STR_i "\0" -#define STRING_Mongolian0 STR_M STR_o STR_n STR_g STR_o STR_l STR_i STR_a STR_n "\0" -#define STRING_Mro0 STR_M STR_r STR_o "\0" -#define STRING_Myanmar0 STR_M STR_y STR_a STR_n STR_m STR_a STR_r "\0" -#define STRING_N0 STR_N "\0" -#define STRING_Nabataean0 STR_N STR_a STR_b STR_a STR_t STR_a STR_e STR_a STR_n "\0" -#define STRING_Nd0 STR_N STR_d "\0" -#define STRING_New_Tai_Lue0 STR_N STR_e STR_w STR_UNDERSCORE STR_T STR_a STR_i STR_UNDERSCORE STR_L STR_u STR_e "\0" -#define STRING_Nko0 STR_N STR_k STR_o "\0" -#define STRING_Nl0 STR_N STR_l "\0" -#define STRING_No0 STR_N STR_o "\0" -#define STRING_Ogham0 STR_O STR_g STR_h STR_a STR_m "\0" -#define STRING_Ol_Chiki0 STR_O STR_l STR_UNDERSCORE STR_C STR_h STR_i STR_k STR_i "\0" -#define STRING_Old_Italic0 STR_O STR_l STR_d STR_UNDERSCORE STR_I STR_t STR_a STR_l STR_i STR_c "\0" -#define STRING_Old_North_Arabian0 STR_O STR_l STR_d STR_UNDERSCORE STR_N STR_o STR_r STR_t STR_h STR_UNDERSCORE STR_A STR_r STR_a STR_b STR_i STR_a STR_n "\0" -#define STRING_Old_Permic0 STR_O STR_l STR_d STR_UNDERSCORE STR_P STR_e STR_r STR_m STR_i STR_c "\0" -#define STRING_Old_Persian0 STR_O STR_l STR_d STR_UNDERSCORE STR_P STR_e STR_r STR_s STR_i STR_a STR_n "\0" -#define STRING_Old_South_Arabian0 STR_O STR_l STR_d STR_UNDERSCORE STR_S STR_o STR_u STR_t STR_h STR_UNDERSCORE STR_A STR_r STR_a STR_b STR_i STR_a STR_n "\0" -#define STRING_Old_Turkic0 STR_O STR_l STR_d STR_UNDERSCORE STR_T STR_u STR_r STR_k STR_i STR_c "\0" -#define STRING_Oriya0 STR_O STR_r STR_i STR_y STR_a "\0" -#define STRING_Osmanya0 STR_O STR_s STR_m STR_a STR_n STR_y STR_a "\0" -#define STRING_P0 STR_P "\0" -#define STRING_Pahawh_Hmong0 STR_P STR_a STR_h STR_a STR_w STR_h STR_UNDERSCORE STR_H STR_m STR_o STR_n STR_g "\0" -#define STRING_Palmyrene0 STR_P STR_a STR_l STR_m STR_y STR_r STR_e STR_n STR_e "\0" -#define STRING_Pau_Cin_Hau0 STR_P STR_a STR_u STR_UNDERSCORE STR_C STR_i STR_n STR_UNDERSCORE STR_H STR_a STR_u "\0" -#define STRING_Pc0 STR_P STR_c "\0" -#define STRING_Pd0 STR_P STR_d "\0" -#define STRING_Pe0 STR_P STR_e "\0" -#define STRING_Pf0 STR_P STR_f "\0" -#define STRING_Phags_Pa0 STR_P STR_h STR_a STR_g STR_s STR_UNDERSCORE STR_P STR_a "\0" -#define STRING_Phoenician0 STR_P STR_h STR_o STR_e STR_n STR_i STR_c STR_i STR_a STR_n "\0" -#define STRING_Pi0 STR_P STR_i "\0" -#define STRING_Po0 STR_P STR_o "\0" -#define STRING_Ps0 STR_P STR_s "\0" -#define STRING_Psalter_Pahlavi0 STR_P STR_s STR_a STR_l STR_t STR_e STR_r STR_UNDERSCORE STR_P STR_a STR_h STR_l STR_a STR_v STR_i "\0" -#define STRING_Rejang0 STR_R STR_e STR_j STR_a STR_n STR_g "\0" -#define STRING_Runic0 STR_R STR_u STR_n STR_i STR_c "\0" -#define STRING_S0 STR_S "\0" -#define STRING_Samaritan0 STR_S STR_a STR_m STR_a STR_r STR_i STR_t STR_a STR_n "\0" -#define STRING_Saurashtra0 STR_S STR_a STR_u STR_r STR_a STR_s STR_h STR_t STR_r STR_a "\0" -#define STRING_Sc0 STR_S STR_c "\0" -#define STRING_Sharada0 STR_S STR_h STR_a STR_r STR_a STR_d STR_a "\0" -#define STRING_Shavian0 STR_S STR_h STR_a STR_v STR_i STR_a STR_n "\0" -#define STRING_Siddham0 STR_S STR_i STR_d STR_d STR_h STR_a STR_m "\0" -#define STRING_Sinhala0 STR_S STR_i STR_n STR_h STR_a STR_l STR_a "\0" -#define STRING_Sk0 STR_S STR_k "\0" -#define STRING_Sm0 STR_S STR_m "\0" -#define STRING_So0 STR_S STR_o "\0" -#define STRING_Sora_Sompeng0 STR_S STR_o STR_r STR_a STR_UNDERSCORE STR_S STR_o STR_m STR_p STR_e STR_n STR_g "\0" -#define STRING_Sundanese0 STR_S STR_u STR_n STR_d STR_a STR_n STR_e STR_s STR_e "\0" -#define STRING_Syloti_Nagri0 STR_S STR_y STR_l STR_o STR_t STR_i STR_UNDERSCORE STR_N STR_a STR_g STR_r STR_i "\0" -#define STRING_Syriac0 STR_S STR_y STR_r STR_i STR_a STR_c "\0" -#define STRING_Tagalog0 STR_T STR_a STR_g STR_a STR_l STR_o STR_g "\0" -#define STRING_Tagbanwa0 STR_T STR_a STR_g STR_b STR_a STR_n STR_w STR_a "\0" -#define STRING_Tai_Le0 STR_T STR_a STR_i STR_UNDERSCORE STR_L STR_e "\0" -#define STRING_Tai_Tham0 STR_T STR_a STR_i STR_UNDERSCORE STR_T STR_h STR_a STR_m "\0" -#define STRING_Tai_Viet0 STR_T STR_a STR_i STR_UNDERSCORE STR_V STR_i STR_e STR_t "\0" -#define STRING_Takri0 STR_T STR_a STR_k STR_r STR_i "\0" -#define STRING_Tamil0 STR_T STR_a STR_m STR_i STR_l "\0" -#define STRING_Telugu0 STR_T STR_e STR_l STR_u STR_g STR_u "\0" -#define STRING_Thaana0 STR_T STR_h STR_a STR_a STR_n STR_a "\0" -#define STRING_Thai0 STR_T STR_h STR_a STR_i "\0" -#define STRING_Tibetan0 STR_T STR_i STR_b STR_e STR_t STR_a STR_n "\0" -#define STRING_Tifinagh0 STR_T STR_i STR_f STR_i STR_n STR_a STR_g STR_h "\0" -#define STRING_Tirhuta0 STR_T STR_i STR_r STR_h STR_u STR_t STR_a "\0" -#define STRING_Ugaritic0 STR_U STR_g STR_a STR_r STR_i STR_t STR_i STR_c "\0" -#define STRING_Vai0 STR_V STR_a STR_i "\0" -#define STRING_Warang_Citi0 STR_W STR_a STR_r STR_a STR_n STR_g STR_UNDERSCORE STR_C STR_i STR_t STR_i "\0" -#define STRING_Xan0 STR_X STR_a STR_n "\0" -#define STRING_Xps0 STR_X STR_p STR_s "\0" -#define STRING_Xsp0 STR_X STR_s STR_p "\0" -#define STRING_Xuc0 STR_X STR_u STR_c "\0" -#define STRING_Xwd0 STR_X STR_w STR_d "\0" -#define STRING_Yi0 STR_Y STR_i "\0" -#define STRING_Z0 STR_Z "\0" -#define STRING_Zl0 STR_Z STR_l "\0" -#define STRING_Zp0 STR_Z STR_p "\0" -#define STRING_Zs0 STR_Z STR_s "\0" - -const char PRIV(utt_names)[] = - STRING_Any0 - STRING_Arabic0 - STRING_Armenian0 - STRING_Avestan0 - STRING_Balinese0 - STRING_Bamum0 - STRING_Bassa_Vah0 - STRING_Batak0 - STRING_Bengali0 - STRING_Bopomofo0 - STRING_Brahmi0 - STRING_Braille0 - STRING_Buginese0 - STRING_Buhid0 - STRING_C0 - STRING_Canadian_Aboriginal0 - STRING_Carian0 - STRING_Caucasian_Albanian0 - STRING_Cc0 - STRING_Cf0 - STRING_Chakma0 - STRING_Cham0 - STRING_Cherokee0 - STRING_Cn0 - STRING_Co0 - STRING_Common0 - STRING_Coptic0 - STRING_Cs0 - STRING_Cuneiform0 - STRING_Cypriot0 - STRING_Cyrillic0 - STRING_Deseret0 - STRING_Devanagari0 - STRING_Duployan0 - STRING_Egyptian_Hieroglyphs0 - STRING_Elbasan0 - STRING_Ethiopic0 - STRING_Georgian0 - STRING_Glagolitic0 - STRING_Gothic0 - STRING_Grantha0 - STRING_Greek0 - STRING_Gujarati0 - STRING_Gurmukhi0 - STRING_Han0 - STRING_Hangul0 - STRING_Hanunoo0 - STRING_Hebrew0 - STRING_Hiragana0 - STRING_Imperial_Aramaic0 - STRING_Inherited0 - STRING_Inscriptional_Pahlavi0 - STRING_Inscriptional_Parthian0 - STRING_Javanese0 - STRING_Kaithi0 - STRING_Kannada0 - STRING_Katakana0 - STRING_Kayah_Li0 - STRING_Kharoshthi0 - STRING_Khmer0 - STRING_Khojki0 - STRING_Khudawadi0 - STRING_L0 - STRING_L_AMPERSAND0 - STRING_Lao0 - STRING_Latin0 - STRING_Lepcha0 - STRING_Limbu0 - STRING_Linear_A0 - STRING_Linear_B0 - STRING_Lisu0 - STRING_Ll0 - STRING_Lm0 - STRING_Lo0 - STRING_Lt0 - STRING_Lu0 - STRING_Lycian0 - STRING_Lydian0 - STRING_M0 - STRING_Mahajani0 - STRING_Malayalam0 - STRING_Mandaic0 - STRING_Manichaean0 - STRING_Mc0 - STRING_Me0 - STRING_Meetei_Mayek0 - STRING_Mende_Kikakui0 - STRING_Meroitic_Cursive0 - STRING_Meroitic_Hieroglyphs0 - STRING_Miao0 - STRING_Mn0 - STRING_Modi0 - STRING_Mongolian0 - STRING_Mro0 - STRING_Myanmar0 - STRING_N0 - STRING_Nabataean0 - STRING_Nd0 - STRING_New_Tai_Lue0 - STRING_Nko0 - STRING_Nl0 - STRING_No0 - STRING_Ogham0 - STRING_Ol_Chiki0 - STRING_Old_Italic0 - STRING_Old_North_Arabian0 - STRING_Old_Permic0 - STRING_Old_Persian0 - STRING_Old_South_Arabian0 - STRING_Old_Turkic0 - STRING_Oriya0 - STRING_Osmanya0 - STRING_P0 - STRING_Pahawh_Hmong0 - STRING_Palmyrene0 - STRING_Pau_Cin_Hau0 - STRING_Pc0 - STRING_Pd0 - STRING_Pe0 - STRING_Pf0 - STRING_Phags_Pa0 - STRING_Phoenician0 - STRING_Pi0 - STRING_Po0 - STRING_Ps0 - STRING_Psalter_Pahlavi0 - STRING_Rejang0 - STRING_Runic0 - STRING_S0 - STRING_Samaritan0 - STRING_Saurashtra0 - STRING_Sc0 - STRING_Sharada0 - STRING_Shavian0 - STRING_Siddham0 - STRING_Sinhala0 - STRING_Sk0 - STRING_Sm0 - STRING_So0 - STRING_Sora_Sompeng0 - STRING_Sundanese0 - STRING_Syloti_Nagri0 - STRING_Syriac0 - STRING_Tagalog0 - STRING_Tagbanwa0 - STRING_Tai_Le0 - STRING_Tai_Tham0 - STRING_Tai_Viet0 - STRING_Takri0 - STRING_Tamil0 - STRING_Telugu0 - STRING_Thaana0 - STRING_Thai0 - STRING_Tibetan0 - STRING_Tifinagh0 - STRING_Tirhuta0 - STRING_Ugaritic0 - STRING_Vai0 - STRING_Warang_Citi0 - STRING_Xan0 - STRING_Xps0 - STRING_Xsp0 - STRING_Xuc0 - STRING_Xwd0 - STRING_Yi0 - STRING_Z0 - STRING_Zl0 - STRING_Zp0 - STRING_Zs0; - -const ucp_type_table PRIV(utt)[] = { - { 0, PT_ANY, 0 }, - { 4, PT_SC, ucp_Arabic }, - { 11, PT_SC, ucp_Armenian }, - { 20, PT_SC, ucp_Avestan }, - { 28, PT_SC, ucp_Balinese }, - { 37, PT_SC, ucp_Bamum }, - { 43, PT_SC, ucp_Bassa_Vah }, - { 53, PT_SC, ucp_Batak }, - { 59, PT_SC, ucp_Bengali }, - { 67, PT_SC, ucp_Bopomofo }, - { 76, PT_SC, ucp_Brahmi }, - { 83, PT_SC, ucp_Braille }, - { 91, PT_SC, ucp_Buginese }, - { 100, PT_SC, ucp_Buhid }, - { 106, PT_GC, ucp_C }, - { 108, PT_SC, ucp_Canadian_Aboriginal }, - { 128, PT_SC, ucp_Carian }, - { 135, PT_SC, ucp_Caucasian_Albanian }, - { 154, PT_PC, ucp_Cc }, - { 157, PT_PC, ucp_Cf }, - { 160, PT_SC, ucp_Chakma }, - { 167, PT_SC, ucp_Cham }, - { 172, PT_SC, ucp_Cherokee }, - { 181, PT_PC, ucp_Cn }, - { 184, PT_PC, ucp_Co }, - { 187, PT_SC, ucp_Common }, - { 194, PT_SC, ucp_Coptic }, - { 201, PT_PC, ucp_Cs }, - { 204, PT_SC, ucp_Cuneiform }, - { 214, PT_SC, ucp_Cypriot }, - { 222, PT_SC, ucp_Cyrillic }, - { 231, PT_SC, ucp_Deseret }, - { 239, PT_SC, ucp_Devanagari }, - { 250, PT_SC, ucp_Duployan }, - { 259, PT_SC, ucp_Egyptian_Hieroglyphs }, - { 280, PT_SC, ucp_Elbasan }, - { 288, PT_SC, ucp_Ethiopic }, - { 297, PT_SC, ucp_Georgian }, - { 306, PT_SC, ucp_Glagolitic }, - { 317, PT_SC, ucp_Gothic }, - { 324, PT_SC, ucp_Grantha }, - { 332, PT_SC, ucp_Greek }, - { 338, PT_SC, ucp_Gujarati }, - { 347, PT_SC, ucp_Gurmukhi }, - { 356, PT_SC, ucp_Han }, - { 360, PT_SC, ucp_Hangul }, - { 367, PT_SC, ucp_Hanunoo }, - { 375, PT_SC, ucp_Hebrew }, - { 382, PT_SC, ucp_Hiragana }, - { 391, PT_SC, ucp_Imperial_Aramaic }, - { 408, PT_SC, ucp_Inherited }, - { 418, PT_SC, ucp_Inscriptional_Pahlavi }, - { 440, PT_SC, ucp_Inscriptional_Parthian }, - { 463, PT_SC, ucp_Javanese }, - { 472, PT_SC, ucp_Kaithi }, - { 479, PT_SC, ucp_Kannada }, - { 487, PT_SC, ucp_Katakana }, - { 496, PT_SC, ucp_Kayah_Li }, - { 505, PT_SC, ucp_Kharoshthi }, - { 516, PT_SC, ucp_Khmer }, - { 522, PT_SC, ucp_Khojki }, - { 529, PT_SC, ucp_Khudawadi }, - { 539, PT_GC, ucp_L }, - { 541, PT_LAMP, 0 }, - { 544, PT_SC, ucp_Lao }, - { 548, PT_SC, ucp_Latin }, - { 554, PT_SC, ucp_Lepcha }, - { 561, PT_SC, ucp_Limbu }, - { 567, PT_SC, ucp_Linear_A }, - { 576, PT_SC, ucp_Linear_B }, - { 585, PT_SC, ucp_Lisu }, - { 590, PT_PC, ucp_Ll }, - { 593, PT_PC, ucp_Lm }, - { 596, PT_PC, ucp_Lo }, - { 599, PT_PC, ucp_Lt }, - { 602, PT_PC, ucp_Lu }, - { 605, PT_SC, ucp_Lycian }, - { 612, PT_SC, ucp_Lydian }, - { 619, PT_GC, ucp_M }, - { 621, PT_SC, ucp_Mahajani }, - { 630, PT_SC, ucp_Malayalam }, - { 640, PT_SC, ucp_Mandaic }, - { 648, PT_SC, ucp_Manichaean }, - { 659, PT_PC, ucp_Mc }, - { 662, PT_PC, ucp_Me }, - { 665, PT_SC, ucp_Meetei_Mayek }, - { 678, PT_SC, ucp_Mende_Kikakui }, - { 692, PT_SC, ucp_Meroitic_Cursive }, - { 709, PT_SC, ucp_Meroitic_Hieroglyphs }, - { 730, PT_SC, ucp_Miao }, - { 735, PT_PC, ucp_Mn }, - { 738, PT_SC, ucp_Modi }, - { 743, PT_SC, ucp_Mongolian }, - { 753, PT_SC, ucp_Mro }, - { 757, PT_SC, ucp_Myanmar }, - { 765, PT_GC, ucp_N }, - { 767, PT_SC, ucp_Nabataean }, - { 777, PT_PC, ucp_Nd }, - { 780, PT_SC, ucp_New_Tai_Lue }, - { 792, PT_SC, ucp_Nko }, - { 796, PT_PC, ucp_Nl }, - { 799, PT_PC, ucp_No }, - { 802, PT_SC, ucp_Ogham }, - { 808, PT_SC, ucp_Ol_Chiki }, - { 817, PT_SC, ucp_Old_Italic }, - { 828, PT_SC, ucp_Old_North_Arabian }, - { 846, PT_SC, ucp_Old_Permic }, - { 857, PT_SC, ucp_Old_Persian }, - { 869, PT_SC, ucp_Old_South_Arabian }, - { 887, PT_SC, ucp_Old_Turkic }, - { 898, PT_SC, ucp_Oriya }, - { 904, PT_SC, ucp_Osmanya }, - { 912, PT_GC, ucp_P }, - { 914, PT_SC, ucp_Pahawh_Hmong }, - { 927, PT_SC, ucp_Palmyrene }, - { 937, PT_SC, ucp_Pau_Cin_Hau }, - { 949, PT_PC, ucp_Pc }, - { 952, PT_PC, ucp_Pd }, - { 955, PT_PC, ucp_Pe }, - { 958, PT_PC, ucp_Pf }, - { 961, PT_SC, ucp_Phags_Pa }, - { 970, PT_SC, ucp_Phoenician }, - { 981, PT_PC, ucp_Pi }, - { 984, PT_PC, ucp_Po }, - { 987, PT_PC, ucp_Ps }, - { 990, PT_SC, ucp_Psalter_Pahlavi }, - { 1006, PT_SC, ucp_Rejang }, - { 1013, PT_SC, ucp_Runic }, - { 1019, PT_GC, ucp_S }, - { 1021, PT_SC, ucp_Samaritan }, - { 1031, PT_SC, ucp_Saurashtra }, - { 1042, PT_PC, ucp_Sc }, - { 1045, PT_SC, ucp_Sharada }, - { 1053, PT_SC, ucp_Shavian }, - { 1061, PT_SC, ucp_Siddham }, - { 1069, PT_SC, ucp_Sinhala }, - { 1077, PT_PC, ucp_Sk }, - { 1080, PT_PC, ucp_Sm }, - { 1083, PT_PC, ucp_So }, - { 1086, PT_SC, ucp_Sora_Sompeng }, - { 1099, PT_SC, ucp_Sundanese }, - { 1109, PT_SC, ucp_Syloti_Nagri }, - { 1122, PT_SC, ucp_Syriac }, - { 1129, PT_SC, ucp_Tagalog }, - { 1137, PT_SC, ucp_Tagbanwa }, - { 1146, PT_SC, ucp_Tai_Le }, - { 1153, PT_SC, ucp_Tai_Tham }, - { 1162, PT_SC, ucp_Tai_Viet }, - { 1171, PT_SC, ucp_Takri }, - { 1177, PT_SC, ucp_Tamil }, - { 1183, PT_SC, ucp_Telugu }, - { 1190, PT_SC, ucp_Thaana }, - { 1197, PT_SC, ucp_Thai }, - { 1202, PT_SC, ucp_Tibetan }, - { 1210, PT_SC, ucp_Tifinagh }, - { 1219, PT_SC, ucp_Tirhuta }, - { 1227, PT_SC, ucp_Ugaritic }, - { 1236, PT_SC, ucp_Vai }, - { 1240, PT_SC, ucp_Warang_Citi }, - { 1252, PT_ALNUM, 0 }, - { 1256, PT_PXSPACE, 0 }, - { 1260, PT_SPACE, 0 }, - { 1264, PT_UCNC, 0 }, - { 1268, PT_WORD, 0 }, - { 1272, PT_SC, ucp_Yi }, - { 1275, PT_GC, ucp_Z }, - { 1277, PT_PC, ucp_Zl }, - { 1280, PT_PC, ucp_Zp }, - { 1283, PT_PC, ucp_Zs } -}; - -const int PRIV(utt_size) = sizeof(PRIV(utt)) / sizeof(ucp_type_table); - -#endif /* SUPPORT_UTF */ - -/* End of pcre_tables.c */ diff --git a/src/third_party/pcre-8.38/pcre_ucd.c b/src/third_party/pcre-8.38/pcre_ucd.c deleted file mode 100644 index 69c4fd42c34..00000000000 --- a/src/third_party/pcre-8.38/pcre_ucd.c +++ /dev/null @@ -1,3630 +0,0 @@ -/* This module is generated by the maint/MultiStage2.py script. -Do not modify it by hand. Instead modify the script and run it -to regenerate this code. - -As well as being part of the PCRE library, this module is #included -by the pcretest program, which redefines the PRIV macro to change -table names from _pcre_xxx to xxxx, thereby avoiding name clashes -with the library. At present, just one of these tables is actually -needed. */ - -#ifndef PCRE_INCLUDED - -#ifdef HAVE_CONFIG_H -#include "config.h" -#endif - -#include "pcre_internal.h" - -#endif /* PCRE_INCLUDED */ - -/* Unicode character database. */ -/* This file was autogenerated by the MultiStage2.py script. */ -/* Total size: 72576 bytes, block size: 128. */ - -/* The tables herein are needed only when UCP support is built -into PCRE. This module should not be referenced otherwise, so -it should not matter whether it is compiled or not. However -a comment was received about space saving - maybe the guy linked -all the modules rather than using a library - so we include a -condition to cut out the tables when not needed. But don't leave -a totally empty module because some compilers barf at that. -Instead, just supply small dummy tables. */ - -#ifndef SUPPORT_UCP -const ucd_record PRIV(ucd_records)[] = {{0,0,0,0,0 }}; -const pcre_uint8 PRIV(ucd_stage1)[] = {0}; -const pcre_uint16 PRIV(ucd_stage2)[] = {0}; -const pcre_uint32 PRIV(ucd_caseless_sets)[] = {0}; -#else - -/* When recompiling tables with a new Unicode version, please check the -types in this structure definition from pcre_internal.h (the actual -field names will be different): - -typedef struct { -pcre_uint8 property_0; -pcre_uint8 property_1; -pcre_uint8 property_2; -pcre_uint8 property_3; -pcre_int32 property_4; -} ucd_record; -*/ - - -const pcre_uint32 PRIV(ucd_caseless_sets)[] = { - NOTACHAR, - 0x0053, 0x0073, 0x017f, NOTACHAR, - 0x01c4, 0x01c5, 0x01c6, NOTACHAR, - 0x01c7, 0x01c8, 0x01c9, NOTACHAR, - 0x01ca, 0x01cb, 0x01cc, NOTACHAR, - 0x01f1, 0x01f2, 0x01f3, NOTACHAR, - 0x0345, 0x0399, 0x03b9, 0x1fbe, NOTACHAR, - 0x00b5, 0x039c, 0x03bc, NOTACHAR, - 0x03a3, 0x03c2, 0x03c3, NOTACHAR, - 0x0392, 0x03b2, 0x03d0, NOTACHAR, - 0x0398, 0x03b8, 0x03d1, 0x03f4, NOTACHAR, - 0x03a6, 0x03c6, 0x03d5, NOTACHAR, - 0x03a0, 0x03c0, 0x03d6, NOTACHAR, - 0x039a, 0x03ba, 0x03f0, NOTACHAR, - 0x03a1, 0x03c1, 0x03f1, NOTACHAR, - 0x0395, 0x03b5, 0x03f5, NOTACHAR, - 0x1e60, 0x1e61, 0x1e9b, NOTACHAR, - 0x03a9, 0x03c9, 0x2126, NOTACHAR, - 0x004b, 0x006b, 0x212a, NOTACHAR, - 0x00c5, 0x00e5, 0x212b, NOTACHAR, -}; - -/* When #included in pcretest, we don't need this large table. */ - -#ifndef PCRE_INCLUDED - -const ucd_record PRIV(ucd_records)[] = { /* 5760 bytes, record size 8 */ - { 9, 0, 2, 0, 0, }, /* 0 */ - { 9, 0, 1, 0, 0, }, /* 1 */ - { 9, 0, 0, 0, 0, }, /* 2 */ - { 9, 29, 12, 0, 0, }, /* 3 */ - { 9, 21, 12, 0, 0, }, /* 4 */ - { 9, 23, 12, 0, 0, }, /* 5 */ - { 9, 22, 12, 0, 0, }, /* 6 */ - { 9, 18, 12, 0, 0, }, /* 7 */ - { 9, 25, 12, 0, 0, }, /* 8 */ - { 9, 17, 12, 0, 0, }, /* 9 */ - { 9, 13, 12, 0, 0, }, /* 10 */ - { 33, 9, 12, 0, 32, }, /* 11 */ - { 33, 9, 12, 71, 32, }, /* 12 */ - { 33, 9, 12, 1, 32, }, /* 13 */ - { 9, 24, 12, 0, 0, }, /* 14 */ - { 9, 16, 12, 0, 0, }, /* 15 */ - { 33, 5, 12, 0, -32, }, /* 16 */ - { 33, 5, 12, 71, -32, }, /* 17 */ - { 33, 5, 12, 1, -32, }, /* 18 */ - { 9, 26, 12, 0, 0, }, /* 19 */ - { 33, 7, 12, 0, 0, }, /* 20 */ - { 9, 20, 12, 0, 0, }, /* 21 */ - { 9, 1, 2, 0, 0, }, /* 22 */ - { 9, 15, 12, 0, 0, }, /* 23 */ - { 9, 5, 12, 26, 775, }, /* 24 */ - { 9, 19, 12, 0, 0, }, /* 25 */ - { 33, 9, 12, 75, 32, }, /* 26 */ - { 33, 5, 12, 0, 7615, }, /* 27 */ - { 33, 5, 12, 75, -32, }, /* 28 */ - { 33, 5, 12, 0, 121, }, /* 29 */ - { 33, 9, 12, 0, 1, }, /* 30 */ - { 33, 5, 12, 0, -1, }, /* 31 */ - { 33, 9, 12, 0, 0, }, /* 32 */ - { 33, 5, 12, 0, 0, }, /* 33 */ - { 33, 9, 12, 0, -121, }, /* 34 */ - { 33, 5, 12, 1, -268, }, /* 35 */ - { 33, 5, 12, 0, 195, }, /* 36 */ - { 33, 9, 12, 0, 210, }, /* 37 */ - { 33, 9, 12, 0, 206, }, /* 38 */ - { 33, 9, 12, 0, 205, }, /* 39 */ - { 33, 9, 12, 0, 79, }, /* 40 */ - { 33, 9, 12, 0, 202, }, /* 41 */ - { 33, 9, 12, 0, 203, }, /* 42 */ - { 33, 9, 12, 0, 207, }, /* 43 */ - { 33, 5, 12, 0, 97, }, /* 44 */ - { 33, 9, 12, 0, 211, }, /* 45 */ - { 33, 9, 12, 0, 209, }, /* 46 */ - { 33, 5, 12, 0, 163, }, /* 47 */ - { 33, 9, 12, 0, 213, }, /* 48 */ - { 33, 5, 12, 0, 130, }, /* 49 */ - { 33, 9, 12, 0, 214, }, /* 50 */ - { 33, 9, 12, 0, 218, }, /* 51 */ - { 33, 9, 12, 0, 217, }, /* 52 */ - { 33, 9, 12, 0, 219, }, /* 53 */ - { 33, 5, 12, 0, 56, }, /* 54 */ - { 33, 9, 12, 5, 2, }, /* 55 */ - { 33, 8, 12, 5, 1, }, /* 56 */ - { 33, 5, 12, 5, -2, }, /* 57 */ - { 33, 9, 12, 9, 2, }, /* 58 */ - { 33, 8, 12, 9, 1, }, /* 59 */ - { 33, 5, 12, 9, -2, }, /* 60 */ - { 33, 9, 12, 13, 2, }, /* 61 */ - { 33, 8, 12, 13, 1, }, /* 62 */ - { 33, 5, 12, 13, -2, }, /* 63 */ - { 33, 5, 12, 0, -79, }, /* 64 */ - { 33, 9, 12, 17, 2, }, /* 65 */ - { 33, 8, 12, 17, 1, }, /* 66 */ - { 33, 5, 12, 17, -2, }, /* 67 */ - { 33, 9, 12, 0, -97, }, /* 68 */ - { 33, 9, 12, 0, -56, }, /* 69 */ - { 33, 9, 12, 0, -130, }, /* 70 */ - { 33, 9, 12, 0, 10795, }, /* 71 */ - { 33, 9, 12, 0, -163, }, /* 72 */ - { 33, 9, 12, 0, 10792, }, /* 73 */ - { 33, 5, 12, 0, 10815, }, /* 74 */ - { 33, 9, 12, 0, -195, }, /* 75 */ - { 33, 9, 12, 0, 69, }, /* 76 */ - { 33, 9, 12, 0, 71, }, /* 77 */ - { 33, 5, 12, 0, 10783, }, /* 78 */ - { 33, 5, 12, 0, 10780, }, /* 79 */ - { 33, 5, 12, 0, 10782, }, /* 80 */ - { 33, 5, 12, 0, -210, }, /* 81 */ - { 33, 5, 12, 0, -206, }, /* 82 */ - { 33, 5, 12, 0, -205, }, /* 83 */ - { 33, 5, 12, 0, -202, }, /* 84 */ - { 33, 5, 12, 0, -203, }, /* 85 */ - { 33, 5, 12, 0, 42319, }, /* 86 */ - { 33, 5, 12, 0, 42315, }, /* 87 */ - { 33, 5, 12, 0, -207, }, /* 88 */ - { 33, 5, 12, 0, 42280, }, /* 89 */ - { 33, 5, 12, 0, 42308, }, /* 90 */ - { 33, 5, 12, 0, -209, }, /* 91 */ - { 33, 5, 12, 0, -211, }, /* 92 */ - { 33, 5, 12, 0, 10743, }, /* 93 */ - { 33, 5, 12, 0, 42305, }, /* 94 */ - { 33, 5, 12, 0, 10749, }, /* 95 */ - { 33, 5, 12, 0, -213, }, /* 96 */ - { 33, 5, 12, 0, -214, }, /* 97 */ - { 33, 5, 12, 0, 10727, }, /* 98 */ - { 33, 5, 12, 0, -218, }, /* 99 */ - { 33, 5, 12, 0, 42282, }, /* 100 */ - { 33, 5, 12, 0, -69, }, /* 101 */ - { 33, 5, 12, 0, -217, }, /* 102 */ - { 33, 5, 12, 0, -71, }, /* 103 */ - { 33, 5, 12, 0, -219, }, /* 104 */ - { 33, 5, 12, 0, 42258, }, /* 105 */ - { 33, 6, 12, 0, 0, }, /* 106 */ - { 9, 6, 12, 0, 0, }, /* 107 */ - { 3, 24, 12, 0, 0, }, /* 108 */ - { 27, 12, 3, 0, 0, }, /* 109 */ - { 27, 12, 3, 21, 116, }, /* 110 */ - { 19, 9, 12, 0, 1, }, /* 111 */ - { 19, 5, 12, 0, -1, }, /* 112 */ - { 19, 24, 12, 0, 0, }, /* 113 */ - { 9, 2, 12, 0, 0, }, /* 114 */ - { 19, 6, 12, 0, 0, }, /* 115 */ - { 19, 5, 12, 0, 130, }, /* 116 */ - { 19, 9, 12, 0, 116, }, /* 117 */ - { 19, 9, 12, 0, 38, }, /* 118 */ - { 19, 9, 12, 0, 37, }, /* 119 */ - { 19, 9, 12, 0, 64, }, /* 120 */ - { 19, 9, 12, 0, 63, }, /* 121 */ - { 19, 5, 12, 0, 0, }, /* 122 */ - { 19, 9, 12, 0, 32, }, /* 123 */ - { 19, 9, 12, 34, 32, }, /* 124 */ - { 19, 9, 12, 59, 32, }, /* 125 */ - { 19, 9, 12, 38, 32, }, /* 126 */ - { 19, 9, 12, 21, 32, }, /* 127 */ - { 19, 9, 12, 51, 32, }, /* 128 */ - { 19, 9, 12, 26, 32, }, /* 129 */ - { 19, 9, 12, 47, 32, }, /* 130 */ - { 19, 9, 12, 55, 32, }, /* 131 */ - { 19, 9, 12, 30, 32, }, /* 132 */ - { 19, 9, 12, 43, 32, }, /* 133 */ - { 19, 9, 12, 67, 32, }, /* 134 */ - { 19, 5, 12, 0, -38, }, /* 135 */ - { 19, 5, 12, 0, -37, }, /* 136 */ - { 19, 5, 12, 0, -32, }, /* 137 */ - { 19, 5, 12, 34, -32, }, /* 138 */ - { 19, 5, 12, 59, -32, }, /* 139 */ - { 19, 5, 12, 38, -32, }, /* 140 */ - { 19, 5, 12, 21, -116, }, /* 141 */ - { 19, 5, 12, 51, -32, }, /* 142 */ - { 19, 5, 12, 26, -775, }, /* 143 */ - { 19, 5, 12, 47, -32, }, /* 144 */ - { 19, 5, 12, 55, -32, }, /* 145 */ - { 19, 5, 12, 30, 1, }, /* 146 */ - { 19, 5, 12, 30, -32, }, /* 147 */ - { 19, 5, 12, 43, -32, }, /* 148 */ - { 19, 5, 12, 67, -32, }, /* 149 */ - { 19, 5, 12, 0, -64, }, /* 150 */ - { 19, 5, 12, 0, -63, }, /* 151 */ - { 19, 9, 12, 0, 8, }, /* 152 */ - { 19, 5, 12, 34, -30, }, /* 153 */ - { 19, 5, 12, 38, -25, }, /* 154 */ - { 19, 9, 12, 0, 0, }, /* 155 */ - { 19, 5, 12, 43, -15, }, /* 156 */ - { 19, 5, 12, 47, -22, }, /* 157 */ - { 19, 5, 12, 0, -8, }, /* 158 */ - { 10, 9, 12, 0, 1, }, /* 159 */ - { 10, 5, 12, 0, -1, }, /* 160 */ - { 19, 5, 12, 51, -54, }, /* 161 */ - { 19, 5, 12, 55, -48, }, /* 162 */ - { 19, 5, 12, 0, 7, }, /* 163 */ - { 19, 5, 12, 0, -116, }, /* 164 */ - { 19, 9, 12, 38, -60, }, /* 165 */ - { 19, 5, 12, 59, -64, }, /* 166 */ - { 19, 25, 12, 0, 0, }, /* 167 */ - { 19, 9, 12, 0, -7, }, /* 168 */ - { 19, 9, 12, 0, -130, }, /* 169 */ - { 12, 9, 12, 0, 80, }, /* 170 */ - { 12, 9, 12, 0, 32, }, /* 171 */ - { 12, 5, 12, 0, -32, }, /* 172 */ - { 12, 5, 12, 0, -80, }, /* 173 */ - { 12, 9, 12, 0, 1, }, /* 174 */ - { 12, 5, 12, 0, -1, }, /* 175 */ - { 12, 26, 12, 0, 0, }, /* 176 */ - { 12, 12, 3, 0, 0, }, /* 177 */ - { 12, 11, 3, 0, 0, }, /* 178 */ - { 12, 9, 12, 0, 15, }, /* 179 */ - { 12, 5, 12, 0, -15, }, /* 180 */ - { 1, 9, 12, 0, 48, }, /* 181 */ - { 1, 6, 12, 0, 0, }, /* 182 */ - { 1, 21, 12, 0, 0, }, /* 183 */ - { 1, 5, 12, 0, -48, }, /* 184 */ - { 1, 5, 12, 0, 0, }, /* 185 */ - { 1, 17, 12, 0, 0, }, /* 186 */ - { 1, 26, 12, 0, 0, }, /* 187 */ - { 1, 23, 12, 0, 0, }, /* 188 */ - { 25, 12, 3, 0, 0, }, /* 189 */ - { 25, 17, 12, 0, 0, }, /* 190 */ - { 25, 21, 12, 0, 0, }, /* 191 */ - { 25, 7, 12, 0, 0, }, /* 192 */ - { 0, 1, 2, 0, 0, }, /* 193 */ - { 0, 25, 12, 0, 0, }, /* 194 */ - { 0, 21, 12, 0, 0, }, /* 195 */ - { 0, 23, 12, 0, 0, }, /* 196 */ - { 0, 26, 12, 0, 0, }, /* 197 */ - { 0, 12, 3, 0, 0, }, /* 198 */ - { 0, 7, 12, 0, 0, }, /* 199 */ - { 0, 6, 12, 0, 0, }, /* 200 */ - { 0, 13, 12, 0, 0, }, /* 201 */ - { 49, 21, 12, 0, 0, }, /* 202 */ - { 49, 1, 2, 0, 0, }, /* 203 */ - { 49, 7, 12, 0, 0, }, /* 204 */ - { 49, 12, 3, 0, 0, }, /* 205 */ - { 55, 7, 12, 0, 0, }, /* 206 */ - { 55, 12, 3, 0, 0, }, /* 207 */ - { 63, 13, 12, 0, 0, }, /* 208 */ - { 63, 7, 12, 0, 0, }, /* 209 */ - { 63, 12, 3, 0, 0, }, /* 210 */ - { 63, 6, 12, 0, 0, }, /* 211 */ - { 63, 26, 12, 0, 0, }, /* 212 */ - { 63, 21, 12, 0, 0, }, /* 213 */ - { 89, 7, 12, 0, 0, }, /* 214 */ - { 89, 12, 3, 0, 0, }, /* 215 */ - { 89, 6, 12, 0, 0, }, /* 216 */ - { 89, 21, 12, 0, 0, }, /* 217 */ - { 94, 7, 12, 0, 0, }, /* 218 */ - { 94, 12, 3, 0, 0, }, /* 219 */ - { 94, 21, 12, 0, 0, }, /* 220 */ - { 14, 12, 3, 0, 0, }, /* 221 */ - { 14, 10, 5, 0, 0, }, /* 222 */ - { 14, 7, 12, 0, 0, }, /* 223 */ - { 14, 13, 12, 0, 0, }, /* 224 */ - { 14, 21, 12, 0, 0, }, /* 225 */ - { 14, 6, 12, 0, 0, }, /* 226 */ - { 2, 7, 12, 0, 0, }, /* 227 */ - { 2, 12, 3, 0, 0, }, /* 228 */ - { 2, 10, 5, 0, 0, }, /* 229 */ - { 2, 10, 3, 0, 0, }, /* 230 */ - { 2, 13, 12, 0, 0, }, /* 231 */ - { 2, 23, 12, 0, 0, }, /* 232 */ - { 2, 15, 12, 0, 0, }, /* 233 */ - { 2, 26, 12, 0, 0, }, /* 234 */ - { 21, 12, 3, 0, 0, }, /* 235 */ - { 21, 10, 5, 0, 0, }, /* 236 */ - { 21, 7, 12, 0, 0, }, /* 237 */ - { 21, 13, 12, 0, 0, }, /* 238 */ - { 20, 12, 3, 0, 0, }, /* 239 */ - { 20, 10, 5, 0, 0, }, /* 240 */ - { 20, 7, 12, 0, 0, }, /* 241 */ - { 20, 13, 12, 0, 0, }, /* 242 */ - { 20, 21, 12, 0, 0, }, /* 243 */ - { 20, 23, 12, 0, 0, }, /* 244 */ - { 43, 12, 3, 0, 0, }, /* 245 */ - { 43, 10, 5, 0, 0, }, /* 246 */ - { 43, 7, 12, 0, 0, }, /* 247 */ - { 43, 10, 3, 0, 0, }, /* 248 */ - { 43, 13, 12, 0, 0, }, /* 249 */ - { 43, 26, 12, 0, 0, }, /* 250 */ - { 43, 15, 12, 0, 0, }, /* 251 */ - { 53, 12, 3, 0, 0, }, /* 252 */ - { 53, 7, 12, 0, 0, }, /* 253 */ - { 53, 10, 3, 0, 0, }, /* 254 */ - { 53, 10, 5, 0, 0, }, /* 255 */ - { 53, 13, 12, 0, 0, }, /* 256 */ - { 53, 15, 12, 0, 0, }, /* 257 */ - { 53, 26, 12, 0, 0, }, /* 258 */ - { 53, 23, 12, 0, 0, }, /* 259 */ - { 54, 12, 3, 0, 0, }, /* 260 */ - { 54, 10, 5, 0, 0, }, /* 261 */ - { 54, 7, 12, 0, 0, }, /* 262 */ - { 54, 13, 12, 0, 0, }, /* 263 */ - { 54, 15, 12, 0, 0, }, /* 264 */ - { 54, 26, 12, 0, 0, }, /* 265 */ - { 28, 12, 3, 0, 0, }, /* 266 */ - { 28, 10, 5, 0, 0, }, /* 267 */ - { 28, 7, 12, 0, 0, }, /* 268 */ - { 28, 10, 3, 0, 0, }, /* 269 */ - { 28, 13, 12, 0, 0, }, /* 270 */ - { 36, 12, 3, 0, 0, }, /* 271 */ - { 36, 10, 5, 0, 0, }, /* 272 */ - { 36, 7, 12, 0, 0, }, /* 273 */ - { 36, 10, 3, 0, 0, }, /* 274 */ - { 36, 13, 12, 0, 0, }, /* 275 */ - { 36, 15, 12, 0, 0, }, /* 276 */ - { 36, 26, 12, 0, 0, }, /* 277 */ - { 47, 10, 5, 0, 0, }, /* 278 */ - { 47, 7, 12, 0, 0, }, /* 279 */ - { 47, 12, 3, 0, 0, }, /* 280 */ - { 47, 10, 3, 0, 0, }, /* 281 */ - { 47, 13, 12, 0, 0, }, /* 282 */ - { 47, 21, 12, 0, 0, }, /* 283 */ - { 56, 7, 12, 0, 0, }, /* 284 */ - { 56, 12, 3, 0, 0, }, /* 285 */ - { 56, 7, 5, 0, 0, }, /* 286 */ - { 56, 6, 12, 0, 0, }, /* 287 */ - { 56, 21, 12, 0, 0, }, /* 288 */ - { 56, 13, 12, 0, 0, }, /* 289 */ - { 32, 7, 12, 0, 0, }, /* 290 */ - { 32, 12, 3, 0, 0, }, /* 291 */ - { 32, 7, 5, 0, 0, }, /* 292 */ - { 32, 6, 12, 0, 0, }, /* 293 */ - { 32, 13, 12, 0, 0, }, /* 294 */ - { 57, 7, 12, 0, 0, }, /* 295 */ - { 57, 26, 12, 0, 0, }, /* 296 */ - { 57, 21, 12, 0, 0, }, /* 297 */ - { 57, 12, 3, 0, 0, }, /* 298 */ - { 57, 13, 12, 0, 0, }, /* 299 */ - { 57, 15, 12, 0, 0, }, /* 300 */ - { 57, 22, 12, 0, 0, }, /* 301 */ - { 57, 18, 12, 0, 0, }, /* 302 */ - { 57, 10, 5, 0, 0, }, /* 303 */ - { 38, 7, 12, 0, 0, }, /* 304 */ - { 38, 10, 12, 0, 0, }, /* 305 */ - { 38, 12, 3, 0, 0, }, /* 306 */ - { 38, 10, 5, 0, 0, }, /* 307 */ - { 38, 13, 12, 0, 0, }, /* 308 */ - { 38, 21, 12, 0, 0, }, /* 309 */ - { 38, 26, 12, 0, 0, }, /* 310 */ - { 16, 9, 12, 0, 7264, }, /* 311 */ - { 16, 7, 12, 0, 0, }, /* 312 */ - { 16, 6, 12, 0, 0, }, /* 313 */ - { 23, 7, 6, 0, 0, }, /* 314 */ - { 23, 7, 7, 0, 0, }, /* 315 */ - { 23, 7, 8, 0, 0, }, /* 316 */ - { 15, 7, 12, 0, 0, }, /* 317 */ - { 15, 12, 3, 0, 0, }, /* 318 */ - { 15, 21, 12, 0, 0, }, /* 319 */ - { 15, 15, 12, 0, 0, }, /* 320 */ - { 15, 26, 12, 0, 0, }, /* 321 */ - { 8, 7, 12, 0, 0, }, /* 322 */ - { 7, 17, 12, 0, 0, }, /* 323 */ - { 7, 7, 12, 0, 0, }, /* 324 */ - { 7, 21, 12, 0, 0, }, /* 325 */ - { 40, 29, 12, 0, 0, }, /* 326 */ - { 40, 7, 12, 0, 0, }, /* 327 */ - { 40, 22, 12, 0, 0, }, /* 328 */ - { 40, 18, 12, 0, 0, }, /* 329 */ - { 45, 7, 12, 0, 0, }, /* 330 */ - { 45, 14, 12, 0, 0, }, /* 331 */ - { 50, 7, 12, 0, 0, }, /* 332 */ - { 50, 12, 3, 0, 0, }, /* 333 */ - { 24, 7, 12, 0, 0, }, /* 334 */ - { 24, 12, 3, 0, 0, }, /* 335 */ - { 6, 7, 12, 0, 0, }, /* 336 */ - { 6, 12, 3, 0, 0, }, /* 337 */ - { 51, 7, 12, 0, 0, }, /* 338 */ - { 51, 12, 3, 0, 0, }, /* 339 */ - { 31, 7, 12, 0, 0, }, /* 340 */ - { 31, 12, 3, 0, 0, }, /* 341 */ - { 31, 10, 5, 0, 0, }, /* 342 */ - { 31, 21, 12, 0, 0, }, /* 343 */ - { 31, 6, 12, 0, 0, }, /* 344 */ - { 31, 23, 12, 0, 0, }, /* 345 */ - { 31, 13, 12, 0, 0, }, /* 346 */ - { 31, 15, 12, 0, 0, }, /* 347 */ - { 37, 21, 12, 0, 0, }, /* 348 */ - { 37, 17, 12, 0, 0, }, /* 349 */ - { 37, 12, 3, 0, 0, }, /* 350 */ - { 37, 1, 2, 0, 0, }, /* 351 */ - { 37, 13, 12, 0, 0, }, /* 352 */ - { 37, 7, 12, 0, 0, }, /* 353 */ - { 37, 6, 12, 0, 0, }, /* 354 */ - { 34, 7, 12, 0, 0, }, /* 355 */ - { 34, 12, 3, 0, 0, }, /* 356 */ - { 34, 10, 5, 0, 0, }, /* 357 */ - { 34, 26, 12, 0, 0, }, /* 358 */ - { 34, 21, 12, 0, 0, }, /* 359 */ - { 34, 13, 12, 0, 0, }, /* 360 */ - { 52, 7, 12, 0, 0, }, /* 361 */ - { 39, 7, 12, 0, 0, }, /* 362 */ - { 39, 10, 12, 0, 0, }, /* 363 */ - { 39, 10, 5, 0, 0, }, /* 364 */ - { 39, 13, 12, 0, 0, }, /* 365 */ - { 39, 15, 12, 0, 0, }, /* 366 */ - { 39, 26, 12, 0, 0, }, /* 367 */ - { 31, 26, 12, 0, 0, }, /* 368 */ - { 5, 7, 12, 0, 0, }, /* 369 */ - { 5, 12, 3, 0, 0, }, /* 370 */ - { 5, 10, 5, 0, 0, }, /* 371 */ - { 5, 21, 12, 0, 0, }, /* 372 */ - { 90, 7, 12, 0, 0, }, /* 373 */ - { 90, 10, 5, 0, 0, }, /* 374 */ - { 90, 12, 3, 0, 0, }, /* 375 */ - { 90, 10, 12, 0, 0, }, /* 376 */ - { 90, 13, 12, 0, 0, }, /* 377 */ - { 90, 21, 12, 0, 0, }, /* 378 */ - { 90, 6, 12, 0, 0, }, /* 379 */ - { 27, 11, 3, 0, 0, }, /* 380 */ - { 61, 12, 3, 0, 0, }, /* 381 */ - { 61, 10, 5, 0, 0, }, /* 382 */ - { 61, 7, 12, 0, 0, }, /* 383 */ - { 61, 13, 12, 0, 0, }, /* 384 */ - { 61, 21, 12, 0, 0, }, /* 385 */ - { 61, 26, 12, 0, 0, }, /* 386 */ - { 75, 12, 3, 0, 0, }, /* 387 */ - { 75, 10, 5, 0, 0, }, /* 388 */ - { 75, 7, 12, 0, 0, }, /* 389 */ - { 75, 13, 12, 0, 0, }, /* 390 */ - { 92, 7, 12, 0, 0, }, /* 391 */ - { 92, 12, 3, 0, 0, }, /* 392 */ - { 92, 10, 5, 0, 0, }, /* 393 */ - { 92, 21, 12, 0, 0, }, /* 394 */ - { 69, 7, 12, 0, 0, }, /* 395 */ - { 69, 10, 5, 0, 0, }, /* 396 */ - { 69, 12, 3, 0, 0, }, /* 397 */ - { 69, 21, 12, 0, 0, }, /* 398 */ - { 69, 13, 12, 0, 0, }, /* 399 */ - { 72, 13, 12, 0, 0, }, /* 400 */ - { 72, 7, 12, 0, 0, }, /* 401 */ - { 72, 6, 12, 0, 0, }, /* 402 */ - { 72, 21, 12, 0, 0, }, /* 403 */ - { 75, 21, 12, 0, 0, }, /* 404 */ - { 9, 10, 5, 0, 0, }, /* 405 */ - { 9, 7, 12, 0, 0, }, /* 406 */ - { 12, 5, 12, 0, 0, }, /* 407 */ - { 12, 6, 12, 0, 0, }, /* 408 */ - { 33, 5, 12, 0, 35332, }, /* 409 */ - { 33, 5, 12, 0, 3814, }, /* 410 */ - { 33, 9, 12, 63, 1, }, /* 411 */ - { 33, 5, 12, 63, -1, }, /* 412 */ - { 33, 5, 12, 63, -58, }, /* 413 */ - { 33, 9, 12, 0, -7615, }, /* 414 */ - { 19, 5, 12, 0, 8, }, /* 415 */ - { 19, 9, 12, 0, -8, }, /* 416 */ - { 19, 5, 12, 0, 74, }, /* 417 */ - { 19, 5, 12, 0, 86, }, /* 418 */ - { 19, 5, 12, 0, 100, }, /* 419 */ - { 19, 5, 12, 0, 128, }, /* 420 */ - { 19, 5, 12, 0, 112, }, /* 421 */ - { 19, 5, 12, 0, 126, }, /* 422 */ - { 19, 8, 12, 0, -8, }, /* 423 */ - { 19, 5, 12, 0, 9, }, /* 424 */ - { 19, 9, 12, 0, -74, }, /* 425 */ - { 19, 8, 12, 0, -9, }, /* 426 */ - { 19, 5, 12, 21, -7173, }, /* 427 */ - { 19, 9, 12, 0, -86, }, /* 428 */ - { 19, 9, 12, 0, -100, }, /* 429 */ - { 19, 9, 12, 0, -112, }, /* 430 */ - { 19, 9, 12, 0, -128, }, /* 431 */ - { 19, 9, 12, 0, -126, }, /* 432 */ - { 27, 1, 3, 0, 0, }, /* 433 */ - { 9, 27, 2, 0, 0, }, /* 434 */ - { 9, 28, 2, 0, 0, }, /* 435 */ - { 9, 2, 2, 0, 0, }, /* 436 */ - { 9, 9, 12, 0, 0, }, /* 437 */ - { 9, 5, 12, 0, 0, }, /* 438 */ - { 19, 9, 12, 67, -7517, }, /* 439 */ - { 33, 9, 12, 71, -8383, }, /* 440 */ - { 33, 9, 12, 75, -8262, }, /* 441 */ - { 33, 9, 12, 0, 28, }, /* 442 */ - { 33, 5, 12, 0, -28, }, /* 443 */ - { 33, 14, 12, 0, 16, }, /* 444 */ - { 33, 14, 12, 0, -16, }, /* 445 */ - { 33, 14, 12, 0, 0, }, /* 446 */ - { 9, 26, 12, 0, 26, }, /* 447 */ - { 9, 26, 12, 0, -26, }, /* 448 */ - { 4, 26, 12, 0, 0, }, /* 449 */ - { 17, 9, 12, 0, 48, }, /* 450 */ - { 17, 5, 12, 0, -48, }, /* 451 */ - { 33, 9, 12, 0, -10743, }, /* 452 */ - { 33, 9, 12, 0, -3814, }, /* 453 */ - { 33, 9, 12, 0, -10727, }, /* 454 */ - { 33, 5, 12, 0, -10795, }, /* 455 */ - { 33, 5, 12, 0, -10792, }, /* 456 */ - { 33, 9, 12, 0, -10780, }, /* 457 */ - { 33, 9, 12, 0, -10749, }, /* 458 */ - { 33, 9, 12, 0, -10783, }, /* 459 */ - { 33, 9, 12, 0, -10782, }, /* 460 */ - { 33, 9, 12, 0, -10815, }, /* 461 */ - { 10, 5, 12, 0, 0, }, /* 462 */ - { 10, 26, 12, 0, 0, }, /* 463 */ - { 10, 12, 3, 0, 0, }, /* 464 */ - { 10, 21, 12, 0, 0, }, /* 465 */ - { 10, 15, 12, 0, 0, }, /* 466 */ - { 16, 5, 12, 0, -7264, }, /* 467 */ - { 58, 7, 12, 0, 0, }, /* 468 */ - { 58, 6, 12, 0, 0, }, /* 469 */ - { 58, 21, 12, 0, 0, }, /* 470 */ - { 58, 12, 3, 0, 0, }, /* 471 */ - { 22, 26, 12, 0, 0, }, /* 472 */ - { 22, 6, 12, 0, 0, }, /* 473 */ - { 22, 14, 12, 0, 0, }, /* 474 */ - { 23, 10, 3, 0, 0, }, /* 475 */ - { 26, 7, 12, 0, 0, }, /* 476 */ - { 26, 6, 12, 0, 0, }, /* 477 */ - { 29, 7, 12, 0, 0, }, /* 478 */ - { 29, 6, 12, 0, 0, }, /* 479 */ - { 3, 7, 12, 0, 0, }, /* 480 */ - { 23, 7, 12, 0, 0, }, /* 481 */ - { 23, 26, 12, 0, 0, }, /* 482 */ - { 29, 26, 12, 0, 0, }, /* 483 */ - { 22, 7, 12, 0, 0, }, /* 484 */ - { 60, 7, 12, 0, 0, }, /* 485 */ - { 60, 6, 12, 0, 0, }, /* 486 */ - { 60, 26, 12, 0, 0, }, /* 487 */ - { 85, 7, 12, 0, 0, }, /* 488 */ - { 85, 6, 12, 0, 0, }, /* 489 */ - { 85, 21, 12, 0, 0, }, /* 490 */ - { 76, 7, 12, 0, 0, }, /* 491 */ - { 76, 6, 12, 0, 0, }, /* 492 */ - { 76, 21, 12, 0, 0, }, /* 493 */ - { 76, 13, 12, 0, 0, }, /* 494 */ - { 12, 7, 12, 0, 0, }, /* 495 */ - { 12, 21, 12, 0, 0, }, /* 496 */ - { 78, 7, 12, 0, 0, }, /* 497 */ - { 78, 14, 12, 0, 0, }, /* 498 */ - { 78, 12, 3, 0, 0, }, /* 499 */ - { 78, 21, 12, 0, 0, }, /* 500 */ - { 33, 9, 12, 0, -35332, }, /* 501 */ - { 33, 9, 12, 0, -42280, }, /* 502 */ - { 33, 9, 12, 0, -42308, }, /* 503 */ - { 33, 9, 12, 0, -42319, }, /* 504 */ - { 33, 9, 12, 0, -42315, }, /* 505 */ - { 33, 9, 12, 0, -42305, }, /* 506 */ - { 33, 9, 12, 0, -42258, }, /* 507 */ - { 33, 9, 12, 0, -42282, }, /* 508 */ - { 48, 7, 12, 0, 0, }, /* 509 */ - { 48, 12, 3, 0, 0, }, /* 510 */ - { 48, 10, 5, 0, 0, }, /* 511 */ - { 48, 26, 12, 0, 0, }, /* 512 */ - { 64, 7, 12, 0, 0, }, /* 513 */ - { 64, 21, 12, 0, 0, }, /* 514 */ - { 74, 10, 5, 0, 0, }, /* 515 */ - { 74, 7, 12, 0, 0, }, /* 516 */ - { 74, 12, 3, 0, 0, }, /* 517 */ - { 74, 21, 12, 0, 0, }, /* 518 */ - { 74, 13, 12, 0, 0, }, /* 519 */ - { 68, 13, 12, 0, 0, }, /* 520 */ - { 68, 7, 12, 0, 0, }, /* 521 */ - { 68, 12, 3, 0, 0, }, /* 522 */ - { 68, 21, 12, 0, 0, }, /* 523 */ - { 73, 7, 12, 0, 0, }, /* 524 */ - { 73, 12, 3, 0, 0, }, /* 525 */ - { 73, 10, 5, 0, 0, }, /* 526 */ - { 73, 21, 12, 0, 0, }, /* 527 */ - { 83, 12, 3, 0, 0, }, /* 528 */ - { 83, 10, 5, 0, 0, }, /* 529 */ - { 83, 7, 12, 0, 0, }, /* 530 */ - { 83, 21, 12, 0, 0, }, /* 531 */ - { 83, 13, 12, 0, 0, }, /* 532 */ - { 38, 6, 12, 0, 0, }, /* 533 */ - { 67, 7, 12, 0, 0, }, /* 534 */ - { 67, 12, 3, 0, 0, }, /* 535 */ - { 67, 10, 5, 0, 0, }, /* 536 */ - { 67, 13, 12, 0, 0, }, /* 537 */ - { 67, 21, 12, 0, 0, }, /* 538 */ - { 91, 7, 12, 0, 0, }, /* 539 */ - { 91, 12, 3, 0, 0, }, /* 540 */ - { 91, 6, 12, 0, 0, }, /* 541 */ - { 91, 21, 12, 0, 0, }, /* 542 */ - { 86, 7, 12, 0, 0, }, /* 543 */ - { 86, 10, 5, 0, 0, }, /* 544 */ - { 86, 12, 3, 0, 0, }, /* 545 */ - { 86, 21, 12, 0, 0, }, /* 546 */ - { 86, 6, 12, 0, 0, }, /* 547 */ - { 86, 13, 12, 0, 0, }, /* 548 */ - { 23, 7, 9, 0, 0, }, /* 549 */ - { 23, 7, 10, 0, 0, }, /* 550 */ - { 9, 4, 2, 0, 0, }, /* 551 */ - { 9, 3, 12, 0, 0, }, /* 552 */ - { 25, 25, 12, 0, 0, }, /* 553 */ - { 0, 24, 12, 0, 0, }, /* 554 */ - { 9, 6, 3, 0, 0, }, /* 555 */ - { 35, 7, 12, 0, 0, }, /* 556 */ - { 19, 14, 12, 0, 0, }, /* 557 */ - { 19, 15, 12, 0, 0, }, /* 558 */ - { 19, 26, 12, 0, 0, }, /* 559 */ - { 70, 7, 12, 0, 0, }, /* 560 */ - { 66, 7, 12, 0, 0, }, /* 561 */ - { 41, 7, 12, 0, 0, }, /* 562 */ - { 41, 15, 12, 0, 0, }, /* 563 */ - { 18, 7, 12, 0, 0, }, /* 564 */ - { 18, 14, 12, 0, 0, }, /* 565 */ - { 117, 7, 12, 0, 0, }, /* 566 */ - { 117, 12, 3, 0, 0, }, /* 567 */ - { 59, 7, 12, 0, 0, }, /* 568 */ - { 59, 21, 12, 0, 0, }, /* 569 */ - { 42, 7, 12, 0, 0, }, /* 570 */ - { 42, 21, 12, 0, 0, }, /* 571 */ - { 42, 14, 12, 0, 0, }, /* 572 */ - { 13, 9, 12, 0, 40, }, /* 573 */ - { 13, 5, 12, 0, -40, }, /* 574 */ - { 46, 7, 12, 0, 0, }, /* 575 */ - { 44, 7, 12, 0, 0, }, /* 576 */ - { 44, 13, 12, 0, 0, }, /* 577 */ - { 105, 7, 12, 0, 0, }, /* 578 */ - { 103, 7, 12, 0, 0, }, /* 579 */ - { 103, 21, 12, 0, 0, }, /* 580 */ - { 109, 7, 12, 0, 0, }, /* 581 */ - { 11, 7, 12, 0, 0, }, /* 582 */ - { 80, 7, 12, 0, 0, }, /* 583 */ - { 80, 21, 12, 0, 0, }, /* 584 */ - { 80, 15, 12, 0, 0, }, /* 585 */ - { 119, 7, 12, 0, 0, }, /* 586 */ - { 119, 26, 12, 0, 0, }, /* 587 */ - { 119, 15, 12, 0, 0, }, /* 588 */ - { 115, 7, 12, 0, 0, }, /* 589 */ - { 115, 15, 12, 0, 0, }, /* 590 */ - { 65, 7, 12, 0, 0, }, /* 591 */ - { 65, 15, 12, 0, 0, }, /* 592 */ - { 65, 21, 12, 0, 0, }, /* 593 */ - { 71, 7, 12, 0, 0, }, /* 594 */ - { 71, 21, 12, 0, 0, }, /* 595 */ - { 97, 7, 12, 0, 0, }, /* 596 */ - { 96, 7, 12, 0, 0, }, /* 597 */ - { 30, 7, 12, 0, 0, }, /* 598 */ - { 30, 12, 3, 0, 0, }, /* 599 */ - { 30, 15, 12, 0, 0, }, /* 600 */ - { 30, 21, 12, 0, 0, }, /* 601 */ - { 87, 7, 12, 0, 0, }, /* 602 */ - { 87, 15, 12, 0, 0, }, /* 603 */ - { 87, 21, 12, 0, 0, }, /* 604 */ - { 116, 7, 12, 0, 0, }, /* 605 */ - { 116, 15, 12, 0, 0, }, /* 606 */ - { 111, 7, 12, 0, 0, }, /* 607 */ - { 111, 26, 12, 0, 0, }, /* 608 */ - { 111, 12, 3, 0, 0, }, /* 609 */ - { 111, 15, 12, 0, 0, }, /* 610 */ - { 111, 21, 12, 0, 0, }, /* 611 */ - { 77, 7, 12, 0, 0, }, /* 612 */ - { 77, 21, 12, 0, 0, }, /* 613 */ - { 82, 7, 12, 0, 0, }, /* 614 */ - { 82, 15, 12, 0, 0, }, /* 615 */ - { 81, 7, 12, 0, 0, }, /* 616 */ - { 81, 15, 12, 0, 0, }, /* 617 */ - { 120, 7, 12, 0, 0, }, /* 618 */ - { 120, 21, 12, 0, 0, }, /* 619 */ - { 120, 15, 12, 0, 0, }, /* 620 */ - { 88, 7, 12, 0, 0, }, /* 621 */ - { 0, 15, 12, 0, 0, }, /* 622 */ - { 93, 10, 5, 0, 0, }, /* 623 */ - { 93, 12, 3, 0, 0, }, /* 624 */ - { 93, 7, 12, 0, 0, }, /* 625 */ - { 93, 21, 12, 0, 0, }, /* 626 */ - { 93, 15, 12, 0, 0, }, /* 627 */ - { 93, 13, 12, 0, 0, }, /* 628 */ - { 84, 12, 3, 0, 0, }, /* 629 */ - { 84, 10, 5, 0, 0, }, /* 630 */ - { 84, 7, 12, 0, 0, }, /* 631 */ - { 84, 21, 12, 0, 0, }, /* 632 */ - { 84, 1, 2, 0, 0, }, /* 633 */ - { 100, 7, 12, 0, 0, }, /* 634 */ - { 100, 13, 12, 0, 0, }, /* 635 */ - { 95, 12, 3, 0, 0, }, /* 636 */ - { 95, 7, 12, 0, 0, }, /* 637 */ - { 95, 10, 5, 0, 0, }, /* 638 */ - { 95, 13, 12, 0, 0, }, /* 639 */ - { 95, 21, 12, 0, 0, }, /* 640 */ - { 110, 7, 12, 0, 0, }, /* 641 */ - { 110, 12, 3, 0, 0, }, /* 642 */ - { 110, 21, 12, 0, 0, }, /* 643 */ - { 99, 12, 3, 0, 0, }, /* 644 */ - { 99, 10, 5, 0, 0, }, /* 645 */ - { 99, 7, 12, 0, 0, }, /* 646 */ - { 99, 21, 12, 0, 0, }, /* 647 */ - { 99, 13, 12, 0, 0, }, /* 648 */ - { 47, 15, 12, 0, 0, }, /* 649 */ - { 107, 7, 12, 0, 0, }, /* 650 */ - { 107, 10, 5, 0, 0, }, /* 651 */ - { 107, 12, 3, 0, 0, }, /* 652 */ - { 107, 21, 12, 0, 0, }, /* 653 */ - { 108, 7, 12, 0, 0, }, /* 654 */ - { 108, 12, 3, 0, 0, }, /* 655 */ - { 108, 10, 5, 0, 0, }, /* 656 */ - { 108, 13, 12, 0, 0, }, /* 657 */ - { 106, 12, 3, 0, 0, }, /* 658 */ - { 106, 10, 5, 0, 0, }, /* 659 */ - { 106, 7, 12, 0, 0, }, /* 660 */ - { 106, 10, 3, 0, 0, }, /* 661 */ - { 123, 7, 12, 0, 0, }, /* 662 */ - { 123, 10, 3, 0, 0, }, /* 663 */ - { 123, 10, 5, 0, 0, }, /* 664 */ - { 123, 12, 3, 0, 0, }, /* 665 */ - { 123, 21, 12, 0, 0, }, /* 666 */ - { 123, 13, 12, 0, 0, }, /* 667 */ - { 122, 7, 12, 0, 0, }, /* 668 */ - { 122, 10, 3, 0, 0, }, /* 669 */ - { 122, 10, 5, 0, 0, }, /* 670 */ - { 122, 12, 3, 0, 0, }, /* 671 */ - { 122, 21, 12, 0, 0, }, /* 672 */ - { 113, 7, 12, 0, 0, }, /* 673 */ - { 113, 10, 5, 0, 0, }, /* 674 */ - { 113, 12, 3, 0, 0, }, /* 675 */ - { 113, 21, 12, 0, 0, }, /* 676 */ - { 113, 13, 12, 0, 0, }, /* 677 */ - { 101, 7, 12, 0, 0, }, /* 678 */ - { 101, 12, 3, 0, 0, }, /* 679 */ - { 101, 10, 5, 0, 0, }, /* 680 */ - { 101, 13, 12, 0, 0, }, /* 681 */ - { 124, 9, 12, 0, 32, }, /* 682 */ - { 124, 5, 12, 0, -32, }, /* 683 */ - { 124, 13, 12, 0, 0, }, /* 684 */ - { 124, 15, 12, 0, 0, }, /* 685 */ - { 124, 7, 12, 0, 0, }, /* 686 */ - { 121, 7, 12, 0, 0, }, /* 687 */ - { 62, 7, 12, 0, 0, }, /* 688 */ - { 62, 14, 12, 0, 0, }, /* 689 */ - { 62, 21, 12, 0, 0, }, /* 690 */ - { 79, 7, 12, 0, 0, }, /* 691 */ - { 114, 7, 12, 0, 0, }, /* 692 */ - { 114, 13, 12, 0, 0, }, /* 693 */ - { 114, 21, 12, 0, 0, }, /* 694 */ - { 102, 7, 12, 0, 0, }, /* 695 */ - { 102, 12, 3, 0, 0, }, /* 696 */ - { 102, 21, 12, 0, 0, }, /* 697 */ - { 118, 7, 12, 0, 0, }, /* 698 */ - { 118, 12, 3, 0, 0, }, /* 699 */ - { 118, 21, 12, 0, 0, }, /* 700 */ - { 118, 26, 12, 0, 0, }, /* 701 */ - { 118, 6, 12, 0, 0, }, /* 702 */ - { 118, 13, 12, 0, 0, }, /* 703 */ - { 118, 15, 12, 0, 0, }, /* 704 */ - { 98, 7, 12, 0, 0, }, /* 705 */ - { 98, 10, 5, 0, 0, }, /* 706 */ - { 98, 12, 3, 0, 0, }, /* 707 */ - { 98, 6, 12, 0, 0, }, /* 708 */ - { 104, 7, 12, 0, 0, }, /* 709 */ - { 104, 26, 12, 0, 0, }, /* 710 */ - { 104, 12, 3, 0, 0, }, /* 711 */ - { 104, 21, 12, 0, 0, }, /* 712 */ - { 9, 10, 3, 0, 0, }, /* 713 */ - { 19, 12, 3, 0, 0, }, /* 714 */ - { 112, 7, 12, 0, 0, }, /* 715 */ - { 112, 15, 12, 0, 0, }, /* 716 */ - { 112, 12, 3, 0, 0, }, /* 717 */ - { 9, 26, 11, 0, 0, }, /* 718 */ - { 26, 26, 12, 0, 0, }, /* 719 */ -}; - -const pcre_uint8 PRIV(ucd_stage1)[] = { /* 8704 bytes */ - 0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15, /* U+0000 */ - 16, 17, 18, 19, 20, 21, 22, 23, 24, 25, 26, 27, 28, 29, 30, 31, /* U+0800 */ - 32, 33, 34, 35, 36, 37, 38, 39, 40, 41, 41, 41, 42, 43, 44, 45, /* U+1000 */ - 46, 47, 48, 49, 50, 51, 52, 53, 54, 55, 56, 57, 58, 59, 60, 61, /* U+1800 */ - 62, 63, 64, 65, 66, 66, 67, 68, 69, 70, 71, 72, 73, 71, 74, 75, /* U+2000 */ - 76, 76, 66, 77, 66, 66, 78, 79, 80, 81, 82, 83, 84, 85, 86, 87, /* U+2800 */ - 88, 89, 90, 91, 92, 93, 94, 71, 95, 95, 95, 95, 95, 95, 95, 95, /* U+3000 */ - 95, 95, 95, 95, 95, 95, 95, 95, 95, 95, 95, 95, 95, 95, 95, 95, /* U+3800 */ - 95, 95, 95, 95, 95, 95, 95, 95, 95, 95, 95, 95, 95, 95, 95, 95, /* U+4000 */ - 95, 95, 95, 95, 95, 95, 95, 95, 95, 95, 95, 96, 95, 95, 95, 95, /* U+4800 */ - 95, 95, 95, 95, 95, 95, 95, 95, 95, 95, 95, 95, 95, 95, 95, 95, /* U+5000 */ - 95, 95, 95, 95, 95, 95, 95, 95, 95, 95, 95, 95, 95, 95, 95, 95, /* U+5800 */ - 95, 95, 95, 95, 95, 95, 95, 95, 95, 95, 95, 95, 95, 95, 95, 95, /* U+6000 */ - 95, 95, 95, 95, 95, 95, 95, 95, 95, 95, 95, 95, 95, 95, 95, 95, /* U+6800 */ - 95, 95, 95, 95, 95, 95, 95, 95, 95, 95, 95, 95, 95, 95, 95, 95, /* U+7000 */ - 95, 95, 95, 95, 95, 95, 95, 95, 95, 95, 95, 95, 95, 95, 95, 95, /* U+7800 */ - 95, 95, 95, 95, 95, 95, 95, 95, 95, 95, 95, 95, 95, 95, 95, 95, /* U+8000 */ - 95, 95, 95, 95, 95, 95, 95, 95, 95, 95, 95, 95, 95, 95, 95, 95, /* U+8800 */ - 95, 95, 95, 95, 95, 95, 95, 95, 95, 95, 95, 95, 95, 95, 95, 95, /* U+9000 */ - 95, 95, 95, 95, 95, 95, 95, 95, 95, 95, 95, 95, 95, 95, 95, 97, /* U+9800 */ - 98, 99, 99, 99, 99, 99, 99, 99, 99,100,101,101,102,103,104,105, /* U+A000 */ -106,107,108,109,110,111,112,113,114,115,116,117,118,119,120,114, /* U+A800 */ -115,116,117,118,119,120,114,115,116,117,118,119,120,114,115,116, /* U+B000 */ -117,118,119,120,114,115,116,117,118,119,120,114,115,116,117,118, /* U+B800 */ -119,120,114,115,116,117,118,119,120,114,115,116,117,118,119,120, /* U+C000 */ -114,115,116,117,118,119,120,114,115,116,117,118,119,120,114,115, /* U+C800 */ -116,117,118,119,120,114,115,116,117,118,119,120,114,115,116,121, /* U+D000 */ -122,122,122,122,122,122,122,122,122,122,122,122,122,122,122,122, /* U+D800 */ -123,123,123,123,123,123,123,123,123,123,123,123,123,123,123,123, /* U+E000 */ -123,123,123,123,123,123,123,123,123,123,123,123,123,123,123,123, /* U+E800 */ -123,123,123,123,123,123,123,123,123,123,123,123,123,123,123,123, /* U+F000 */ -123,123, 95, 95,124,125,126,127,128,128,129,130,131,132,133,134, /* U+F800 */ -135,136,137,138,139,140,141,142,143,144,145,139,146,146,147,139, /* U+10000 */ -148,149,150,151,152,153,154,155,156,139,139,139,157,139,139,139, /* U+10800 */ -158,159,160,161,162,163,164,139,139,165,139,166,167,168,139,139, /* U+11000 */ -139,169,139,139,139,170,139,139,139,139,139,139,139,139,139,139, /* U+11800 */ -171,171,171,171,171,171,171,172,173,139,139,139,139,139,139,139, /* U+12000 */ -139,139,139,139,139,139,139,139,139,139,139,139,139,139,139,139, /* U+12800 */ -174,174,174,174,174,174,174,174,175,139,139,139,139,139,139,139, /* U+13000 */ -139,139,139,139,139,139,139,139,139,139,139,139,139,139,139,139, /* U+13800 */ -139,139,139,139,139,139,139,139,139,139,139,139,139,139,139,139, /* U+14000 */ -139,139,139,139,139,139,139,139,139,139,139,139,139,139,139,139, /* U+14800 */ -139,139,139,139,139,139,139,139,139,139,139,139,139,139,139,139, /* U+15000 */ -139,139,139,139,139,139,139,139,139,139,139,139,139,139,139,139, /* U+15800 */ -139,139,139,139,139,139,139,139,139,139,139,139,139,139,139,139, /* U+16000 */ -176,176,176,176,177,178,179,180,139,139,139,139,139,139,181,182, /* U+16800 */ -139,139,139,139,139,139,139,139,139,139,139,139,139,139,139,139, /* U+17000 */ -139,139,139,139,139,139,139,139,139,139,139,139,139,139,139,139, /* U+17800 */ -139,139,139,139,139,139,139,139,139,139,139,139,139,139,139,139, /* U+18000 */ -139,139,139,139,139,139,139,139,139,139,139,139,139,139,139,139, /* U+18800 */ -139,139,139,139,139,139,139,139,139,139,139,139,139,139,139,139, /* U+19000 */ -139,139,139,139,139,139,139,139,139,139,139,139,139,139,139,139, /* U+19800 */ -139,139,139,139,139,139,139,139,139,139,139,139,139,139,139,139, /* U+1A000 */ -139,139,139,139,139,139,139,139,139,139,139,139,139,139,139,139, /* U+1A800 */ -183,139,139,139,139,139,139,139,139,139,139,139,139,139,139,139, /* U+1B000 */ -139,139,139,139,139,139,139,139,184,185,139,139,139,139,139,139, /* U+1B800 */ -139,139,139,139,139,139,139,139,139,139,139,139,139,139,139,139, /* U+1C000 */ -139,139,139,139,139,139,139,139,139,139,139,139,139,139,139,139, /* U+1C800 */ - 71,186,187,188,189,139,190,139,191,192,193,194,195,196,197,198, /* U+1D000 */ -139,139,139,139,139,139,139,139,139,139,139,139,139,139,139,139, /* U+1D800 */ -139,139,139,139,139,139,139,139,139,139,139,139,139,139,139,139, /* U+1E000 */ -199,200,139,139,139,139,139,139,139,139,139,139,201,202,139,139, /* U+1E800 */ -203,204,205,206,207,139,208,209, 71,210,211,212,213,214,215,216, /* U+1F000 */ -217,218,139,139,139,139,139,139,139,139,139,139,139,139,139,139, /* U+1F800 */ - 95, 95, 95, 95, 95, 95, 95, 95, 95, 95, 95, 95, 95, 95, 95, 95, /* U+20000 */ - 95, 95, 95, 95, 95, 95, 95, 95, 95, 95, 95, 95, 95, 95, 95, 95, /* U+20800 */ - 95, 95, 95, 95, 95, 95, 95, 95, 95, 95, 95, 95, 95, 95, 95, 95, /* U+21000 */ - 95, 95, 95, 95, 95, 95, 95, 95, 95, 95, 95, 95, 95, 95, 95, 95, /* U+21800 */ - 95, 95, 95, 95, 95, 95, 95, 95, 95, 95, 95, 95, 95, 95, 95, 95, /* U+22000 */ - 95, 95, 95, 95, 95, 95, 95, 95, 95, 95, 95, 95, 95, 95, 95, 95, /* U+22800 */ - 95, 95, 95, 95, 95, 95, 95, 95, 95, 95, 95, 95, 95, 95, 95, 95, /* U+23000 */ - 95, 95, 95, 95, 95, 95, 95, 95, 95, 95, 95, 95, 95, 95, 95, 95, /* U+23800 */ - 95, 95, 95, 95, 95, 95, 95, 95, 95, 95, 95, 95, 95, 95, 95, 95, /* U+24000 */ - 95, 95, 95, 95, 95, 95, 95, 95, 95, 95, 95, 95, 95, 95, 95, 95, /* U+24800 */ - 95, 95, 95, 95, 95, 95, 95, 95, 95, 95, 95, 95, 95, 95, 95, 95, /* U+25000 */ - 95, 95, 95, 95, 95, 95, 95, 95, 95, 95, 95, 95, 95, 95, 95, 95, /* U+25800 */ - 95, 95, 95, 95, 95, 95, 95, 95, 95, 95, 95, 95, 95, 95, 95, 95, /* U+26000 */ - 95, 95, 95, 95, 95, 95, 95, 95, 95, 95, 95, 95, 95, 95, 95, 95, /* U+26800 */ - 95, 95, 95, 95, 95, 95, 95, 95, 95, 95, 95, 95, 95, 95, 95, 95, /* U+27000 */ - 95, 95, 95, 95, 95, 95, 95, 95, 95, 95, 95, 95, 95, 95, 95, 95, /* U+27800 */ - 95, 95, 95, 95, 95, 95, 95, 95, 95, 95, 95, 95, 95, 95, 95, 95, /* U+28000 */ - 95, 95, 95, 95, 95, 95, 95, 95, 95, 95, 95, 95, 95, 95, 95, 95, /* U+28800 */ - 95, 95, 95, 95, 95, 95, 95, 95, 95, 95, 95, 95, 95, 95, 95, 95, /* U+29000 */ - 95, 95, 95, 95, 95, 95, 95, 95, 95, 95, 95, 95, 95, 95, 95, 95, /* U+29800 */ - 95, 95, 95, 95, 95, 95, 95, 95, 95, 95, 95, 95, 95,219, 95, 95, /* U+2A000 */ - 95, 95, 95, 95, 95, 95, 95, 95, 95, 95, 95, 95, 95, 95, 95, 95, /* U+2A800 */ - 95, 95, 95, 95, 95, 95, 95, 95, 95, 95, 95, 95, 95, 95,220, 95, /* U+2B000 */ -221,139,139,139,139,139,139,139,139,139,139,139,139,139,139,139, /* U+2B800 */ -139,139,139,139,139,139,139,139,139,139,139,139,139,139,139,139, /* U+2C000 */ -139,139,139,139,139,139,139,139,139,139,139,139,139,139,139,139, /* U+2C800 */ -139,139,139,139,139,139,139,139,139,139,139,139,139,139,139,139, /* U+2D000 */ -139,139,139,139,139,139,139,139,139,139,139,139,139,139,139,139, /* U+2D800 */ -139,139,139,139,139,139,139,139,139,139,139,139,139,139,139,139, /* U+2E000 */ -139,139,139,139,139,139,139,139,139,139,139,139,139,139,139,139, /* U+2E800 */ -139,139,139,139,139,139,139,139,139,139,139,139,139,139,139,139, /* U+2F000 */ - 95, 95, 95, 95,221,139,139,139,139,139,139,139,139,139,139,139, /* U+2F800 */ -139,139,139,139,139,139,139,139,139,139,139,139,139,139,139,139, /* U+30000 */ -139,139,139,139,139,139,139,139,139,139,139,139,139,139,139,139, /* U+30800 */ -139,139,139,139,139,139,139,139,139,139,139,139,139,139,139,139, /* U+31000 */ -139,139,139,139,139,139,139,139,139,139,139,139,139,139,139,139, /* U+31800 */ -139,139,139,139,139,139,139,139,139,139,139,139,139,139,139,139, /* U+32000 */ -139,139,139,139,139,139,139,139,139,139,139,139,139,139,139,139, /* U+32800 */ -139,139,139,139,139,139,139,139,139,139,139,139,139,139,139,139, /* U+33000 */ -139,139,139,139,139,139,139,139,139,139,139,139,139,139,139,139, /* U+33800 */ -139,139,139,139,139,139,139,139,139,139,139,139,139,139,139,139, /* U+34000 */ -139,139,139,139,139,139,139,139,139,139,139,139,139,139,139,139, /* U+34800 */ -139,139,139,139,139,139,139,139,139,139,139,139,139,139,139,139, /* U+35000 */ -139,139,139,139,139,139,139,139,139,139,139,139,139,139,139,139, /* U+35800 */ -139,139,139,139,139,139,139,139,139,139,139,139,139,139,139,139, /* U+36000 */ -139,139,139,139,139,139,139,139,139,139,139,139,139,139,139,139, /* U+36800 */ -139,139,139,139,139,139,139,139,139,139,139,139,139,139,139,139, /* U+37000 */ -139,139,139,139,139,139,139,139,139,139,139,139,139,139,139,139, /* U+37800 */ -139,139,139,139,139,139,139,139,139,139,139,139,139,139,139,139, /* U+38000 */ -139,139,139,139,139,139,139,139,139,139,139,139,139,139,139,139, /* U+38800 */ -139,139,139,139,139,139,139,139,139,139,139,139,139,139,139,139, /* U+39000 */ -139,139,139,139,139,139,139,139,139,139,139,139,139,139,139,139, /* U+39800 */ -139,139,139,139,139,139,139,139,139,139,139,139,139,139,139,139, /* U+3A000 */ -139,139,139,139,139,139,139,139,139,139,139,139,139,139,139,139, /* U+3A800 */ -139,139,139,139,139,139,139,139,139,139,139,139,139,139,139,139, /* U+3B000 */ -139,139,139,139,139,139,139,139,139,139,139,139,139,139,139,139, /* U+3B800 */ -139,139,139,139,139,139,139,139,139,139,139,139,139,139,139,139, /* U+3C000 */ -139,139,139,139,139,139,139,139,139,139,139,139,139,139,139,139, /* U+3C800 */ -139,139,139,139,139,139,139,139,139,139,139,139,139,139,139,139, /* U+3D000 */ -139,139,139,139,139,139,139,139,139,139,139,139,139,139,139,139, /* U+3D800 */ -139,139,139,139,139,139,139,139,139,139,139,139,139,139,139,139, /* U+3E000 */ -139,139,139,139,139,139,139,139,139,139,139,139,139,139,139,139, /* U+3E800 */ -139,139,139,139,139,139,139,139,139,139,139,139,139,139,139,139, /* U+3F000 */ -139,139,139,139,139,139,139,139,139,139,139,139,139,139,139,139, /* U+3F800 */ -139,139,139,139,139,139,139,139,139,139,139,139,139,139,139,139, /* U+40000 */ -139,139,139,139,139,139,139,139,139,139,139,139,139,139,139,139, /* U+40800 */ -139,139,139,139,139,139,139,139,139,139,139,139,139,139,139,139, /* U+41000 */ -139,139,139,139,139,139,139,139,139,139,139,139,139,139,139,139, /* U+41800 */ -139,139,139,139,139,139,139,139,139,139,139,139,139,139,139,139, /* U+42000 */ -139,139,139,139,139,139,139,139,139,139,139,139,139,139,139,139, /* U+42800 */ -139,139,139,139,139,139,139,139,139,139,139,139,139,139,139,139, /* U+43000 */ -139,139,139,139,139,139,139,139,139,139,139,139,139,139,139,139, /* U+43800 */ -139,139,139,139,139,139,139,139,139,139,139,139,139,139,139,139, /* U+44000 */ -139,139,139,139,139,139,139,139,139,139,139,139,139,139,139,139, /* U+44800 */ -139,139,139,139,139,139,139,139,139,139,139,139,139,139,139,139, /* U+45000 */ -139,139,139,139,139,139,139,139,139,139,139,139,139,139,139,139, /* U+45800 */ -139,139,139,139,139,139,139,139,139,139,139,139,139,139,139,139, /* U+46000 */ -139,139,139,139,139,139,139,139,139,139,139,139,139,139,139,139, /* U+46800 */ -139,139,139,139,139,139,139,139,139,139,139,139,139,139,139,139, /* U+47000 */ -139,139,139,139,139,139,139,139,139,139,139,139,139,139,139,139, /* U+47800 */ -139,139,139,139,139,139,139,139,139,139,139,139,139,139,139,139, /* U+48000 */ -139,139,139,139,139,139,139,139,139,139,139,139,139,139,139,139, /* U+48800 */ -139,139,139,139,139,139,139,139,139,139,139,139,139,139,139,139, /* U+49000 */ -139,139,139,139,139,139,139,139,139,139,139,139,139,139,139,139, /* U+49800 */ -139,139,139,139,139,139,139,139,139,139,139,139,139,139,139,139, /* U+4A000 */ -139,139,139,139,139,139,139,139,139,139,139,139,139,139,139,139, /* U+4A800 */ -139,139,139,139,139,139,139,139,139,139,139,139,139,139,139,139, /* U+4B000 */ -139,139,139,139,139,139,139,139,139,139,139,139,139,139,139,139, /* U+4B800 */ -139,139,139,139,139,139,139,139,139,139,139,139,139,139,139,139, /* U+4C000 */ -139,139,139,139,139,139,139,139,139,139,139,139,139,139,139,139, /* U+4C800 */ -139,139,139,139,139,139,139,139,139,139,139,139,139,139,139,139, /* U+4D000 */ -139,139,139,139,139,139,139,139,139,139,139,139,139,139,139,139, /* U+4D800 */ -139,139,139,139,139,139,139,139,139,139,139,139,139,139,139,139, /* U+4E000 */ -139,139,139,139,139,139,139,139,139,139,139,139,139,139,139,139, /* U+4E800 */ -139,139,139,139,139,139,139,139,139,139,139,139,139,139,139,139, /* U+4F000 */ -139,139,139,139,139,139,139,139,139,139,139,139,139,139,139,139, /* U+4F800 */ -139,139,139,139,139,139,139,139,139,139,139,139,139,139,139,139, /* U+50000 */ -139,139,139,139,139,139,139,139,139,139,139,139,139,139,139,139, /* U+50800 */ -139,139,139,139,139,139,139,139,139,139,139,139,139,139,139,139, /* U+51000 */ -139,139,139,139,139,139,139,139,139,139,139,139,139,139,139,139, /* U+51800 */ -139,139,139,139,139,139,139,139,139,139,139,139,139,139,139,139, /* U+52000 */ -139,139,139,139,139,139,139,139,139,139,139,139,139,139,139,139, /* U+52800 */ -139,139,139,139,139,139,139,139,139,139,139,139,139,139,139,139, /* U+53000 */ -139,139,139,139,139,139,139,139,139,139,139,139,139,139,139,139, /* U+53800 */ -139,139,139,139,139,139,139,139,139,139,139,139,139,139,139,139, /* U+54000 */ -139,139,139,139,139,139,139,139,139,139,139,139,139,139,139,139, /* U+54800 */ -139,139,139,139,139,139,139,139,139,139,139,139,139,139,139,139, /* U+55000 */ -139,139,139,139,139,139,139,139,139,139,139,139,139,139,139,139, /* U+55800 */ -139,139,139,139,139,139,139,139,139,139,139,139,139,139,139,139, /* U+56000 */ -139,139,139,139,139,139,139,139,139,139,139,139,139,139,139,139, /* U+56800 */ -139,139,139,139,139,139,139,139,139,139,139,139,139,139,139,139, /* U+57000 */ -139,139,139,139,139,139,139,139,139,139,139,139,139,139,139,139, /* U+57800 */ -139,139,139,139,139,139,139,139,139,139,139,139,139,139,139,139, /* U+58000 */ -139,139,139,139,139,139,139,139,139,139,139,139,139,139,139,139, /* U+58800 */ -139,139,139,139,139,139,139,139,139,139,139,139,139,139,139,139, /* U+59000 */ -139,139,139,139,139,139,139,139,139,139,139,139,139,139,139,139, /* U+59800 */ -139,139,139,139,139,139,139,139,139,139,139,139,139,139,139,139, /* U+5A000 */ -139,139,139,139,139,139,139,139,139,139,139,139,139,139,139,139, /* U+5A800 */ -139,139,139,139,139,139,139,139,139,139,139,139,139,139,139,139, /* U+5B000 */ -139,139,139,139,139,139,139,139,139,139,139,139,139,139,139,139, /* U+5B800 */ -139,139,139,139,139,139,139,139,139,139,139,139,139,139,139,139, /* U+5C000 */ -139,139,139,139,139,139,139,139,139,139,139,139,139,139,139,139, /* U+5C800 */ -139,139,139,139,139,139,139,139,139,139,139,139,139,139,139,139, /* U+5D000 */ -139,139,139,139,139,139,139,139,139,139,139,139,139,139,139,139, /* U+5D800 */ -139,139,139,139,139,139,139,139,139,139,139,139,139,139,139,139, /* U+5E000 */ -139,139,139,139,139,139,139,139,139,139,139,139,139,139,139,139, /* U+5E800 */ -139,139,139,139,139,139,139,139,139,139,139,139,139,139,139,139, /* U+5F000 */ -139,139,139,139,139,139,139,139,139,139,139,139,139,139,139,139, /* U+5F800 */ -139,139,139,139,139,139,139,139,139,139,139,139,139,139,139,139, /* U+60000 */ -139,139,139,139,139,139,139,139,139,139,139,139,139,139,139,139, /* U+60800 */ -139,139,139,139,139,139,139,139,139,139,139,139,139,139,139,139, /* U+61000 */ -139,139,139,139,139,139,139,139,139,139,139,139,139,139,139,139, /* U+61800 */ -139,139,139,139,139,139,139,139,139,139,139,139,139,139,139,139, /* U+62000 */ -139,139,139,139,139,139,139,139,139,139,139,139,139,139,139,139, /* U+62800 */ -139,139,139,139,139,139,139,139,139,139,139,139,139,139,139,139, /* U+63000 */ -139,139,139,139,139,139,139,139,139,139,139,139,139,139,139,139, /* U+63800 */ -139,139,139,139,139,139,139,139,139,139,139,139,139,139,139,139, /* U+64000 */ -139,139,139,139,139,139,139,139,139,139,139,139,139,139,139,139, /* U+64800 */ -139,139,139,139,139,139,139,139,139,139,139,139,139,139,139,139, /* U+65000 */ -139,139,139,139,139,139,139,139,139,139,139,139,139,139,139,139, /* U+65800 */ -139,139,139,139,139,139,139,139,139,139,139,139,139,139,139,139, /* U+66000 */ -139,139,139,139,139,139,139,139,139,139,139,139,139,139,139,139, /* U+66800 */ -139,139,139,139,139,139,139,139,139,139,139,139,139,139,139,139, /* U+67000 */ -139,139,139,139,139,139,139,139,139,139,139,139,139,139,139,139, /* U+67800 */ -139,139,139,139,139,139,139,139,139,139,139,139,139,139,139,139, /* U+68000 */ -139,139,139,139,139,139,139,139,139,139,139,139,139,139,139,139, /* U+68800 */ -139,139,139,139,139,139,139,139,139,139,139,139,139,139,139,139, /* U+69000 */ -139,139,139,139,139,139,139,139,139,139,139,139,139,139,139,139, /* U+69800 */ -139,139,139,139,139,139,139,139,139,139,139,139,139,139,139,139, /* U+6A000 */ -139,139,139,139,139,139,139,139,139,139,139,139,139,139,139,139, /* U+6A800 */ -139,139,139,139,139,139,139,139,139,139,139,139,139,139,139,139, /* U+6B000 */ -139,139,139,139,139,139,139,139,139,139,139,139,139,139,139,139, /* U+6B800 */ -139,139,139,139,139,139,139,139,139,139,139,139,139,139,139,139, /* U+6C000 */ -139,139,139,139,139,139,139,139,139,139,139,139,139,139,139,139, /* U+6C800 */ -139,139,139,139,139,139,139,139,139,139,139,139,139,139,139,139, /* U+6D000 */ -139,139,139,139,139,139,139,139,139,139,139,139,139,139,139,139, /* U+6D800 */ -139,139,139,139,139,139,139,139,139,139,139,139,139,139,139,139, /* U+6E000 */ -139,139,139,139,139,139,139,139,139,139,139,139,139,139,139,139, /* U+6E800 */ -139,139,139,139,139,139,139,139,139,139,139,139,139,139,139,139, /* U+6F000 */ -139,139,139,139,139,139,139,139,139,139,139,139,139,139,139,139, /* U+6F800 */ -139,139,139,139,139,139,139,139,139,139,139,139,139,139,139,139, /* U+70000 */ -139,139,139,139,139,139,139,139,139,139,139,139,139,139,139,139, /* U+70800 */ -139,139,139,139,139,139,139,139,139,139,139,139,139,139,139,139, /* U+71000 */ -139,139,139,139,139,139,139,139,139,139,139,139,139,139,139,139, /* U+71800 */ -139,139,139,139,139,139,139,139,139,139,139,139,139,139,139,139, /* U+72000 */ -139,139,139,139,139,139,139,139,139,139,139,139,139,139,139,139, /* U+72800 */ -139,139,139,139,139,139,139,139,139,139,139,139,139,139,139,139, /* U+73000 */ -139,139,139,139,139,139,139,139,139,139,139,139,139,139,139,139, /* U+73800 */ -139,139,139,139,139,139,139,139,139,139,139,139,139,139,139,139, /* U+74000 */ -139,139,139,139,139,139,139,139,139,139,139,139,139,139,139,139, /* U+74800 */ -139,139,139,139,139,139,139,139,139,139,139,139,139,139,139,139, /* U+75000 */ -139,139,139,139,139,139,139,139,139,139,139,139,139,139,139,139, /* U+75800 */ -139,139,139,139,139,139,139,139,139,139,139,139,139,139,139,139, /* U+76000 */ -139,139,139,139,139,139,139,139,139,139,139,139,139,139,139,139, /* U+76800 */ -139,139,139,139,139,139,139,139,139,139,139,139,139,139,139,139, /* U+77000 */ -139,139,139,139,139,139,139,139,139,139,139,139,139,139,139,139, /* U+77800 */ -139,139,139,139,139,139,139,139,139,139,139,139,139,139,139,139, /* U+78000 */ -139,139,139,139,139,139,139,139,139,139,139,139,139,139,139,139, /* U+78800 */ -139,139,139,139,139,139,139,139,139,139,139,139,139,139,139,139, /* U+79000 */ -139,139,139,139,139,139,139,139,139,139,139,139,139,139,139,139, /* U+79800 */ -139,139,139,139,139,139,139,139,139,139,139,139,139,139,139,139, /* U+7A000 */ -139,139,139,139,139,139,139,139,139,139,139,139,139,139,139,139, /* U+7A800 */ -139,139,139,139,139,139,139,139,139,139,139,139,139,139,139,139, /* U+7B000 */ -139,139,139,139,139,139,139,139,139,139,139,139,139,139,139,139, /* U+7B800 */ -139,139,139,139,139,139,139,139,139,139,139,139,139,139,139,139, /* U+7C000 */ -139,139,139,139,139,139,139,139,139,139,139,139,139,139,139,139, /* U+7C800 */ -139,139,139,139,139,139,139,139,139,139,139,139,139,139,139,139, /* U+7D000 */ -139,139,139,139,139,139,139,139,139,139,139,139,139,139,139,139, /* U+7D800 */ -139,139,139,139,139,139,139,139,139,139,139,139,139,139,139,139, /* U+7E000 */ -139,139,139,139,139,139,139,139,139,139,139,139,139,139,139,139, /* U+7E800 */ -139,139,139,139,139,139,139,139,139,139,139,139,139,139,139,139, /* U+7F000 */ -139,139,139,139,139,139,139,139,139,139,139,139,139,139,139,139, /* U+7F800 */ -139,139,139,139,139,139,139,139,139,139,139,139,139,139,139,139, /* U+80000 */ -139,139,139,139,139,139,139,139,139,139,139,139,139,139,139,139, /* U+80800 */ -139,139,139,139,139,139,139,139,139,139,139,139,139,139,139,139, /* U+81000 */ -139,139,139,139,139,139,139,139,139,139,139,139,139,139,139,139, /* U+81800 */ -139,139,139,139,139,139,139,139,139,139,139,139,139,139,139,139, /* U+82000 */ -139,139,139,139,139,139,139,139,139,139,139,139,139,139,139,139, /* U+82800 */ -139,139,139,139,139,139,139,139,139,139,139,139,139,139,139,139, /* U+83000 */ -139,139,139,139,139,139,139,139,139,139,139,139,139,139,139,139, /* U+83800 */ -139,139,139,139,139,139,139,139,139,139,139,139,139,139,139,139, /* U+84000 */ -139,139,139,139,139,139,139,139,139,139,139,139,139,139,139,139, /* U+84800 */ -139,139,139,139,139,139,139,139,139,139,139,139,139,139,139,139, /* U+85000 */ -139,139,139,139,139,139,139,139,139,139,139,139,139,139,139,139, /* U+85800 */ -139,139,139,139,139,139,139,139,139,139,139,139,139,139,139,139, /* U+86000 */ -139,139,139,139,139,139,139,139,139,139,139,139,139,139,139,139, /* U+86800 */ -139,139,139,139,139,139,139,139,139,139,139,139,139,139,139,139, /* U+87000 */ -139,139,139,139,139,139,139,139,139,139,139,139,139,139,139,139, /* U+87800 */ -139,139,139,139,139,139,139,139,139,139,139,139,139,139,139,139, /* U+88000 */ -139,139,139,139,139,139,139,139,139,139,139,139,139,139,139,139, /* U+88800 */ -139,139,139,139,139,139,139,139,139,139,139,139,139,139,139,139, /* U+89000 */ -139,139,139,139,139,139,139,139,139,139,139,139,139,139,139,139, /* U+89800 */ -139,139,139,139,139,139,139,139,139,139,139,139,139,139,139,139, /* U+8A000 */ -139,139,139,139,139,139,139,139,139,139,139,139,139,139,139,139, /* U+8A800 */ -139,139,139,139,139,139,139,139,139,139,139,139,139,139,139,139, /* U+8B000 */ -139,139,139,139,139,139,139,139,139,139,139,139,139,139,139,139, /* U+8B800 */ -139,139,139,139,139,139,139,139,139,139,139,139,139,139,139,139, /* U+8C000 */ -139,139,139,139,139,139,139,139,139,139,139,139,139,139,139,139, /* U+8C800 */ -139,139,139,139,139,139,139,139,139,139,139,139,139,139,139,139, /* U+8D000 */ -139,139,139,139,139,139,139,139,139,139,139,139,139,139,139,139, /* U+8D800 */ -139,139,139,139,139,139,139,139,139,139,139,139,139,139,139,139, /* U+8E000 */ -139,139,139,139,139,139,139,139,139,139,139,139,139,139,139,139, /* U+8E800 */ -139,139,139,139,139,139,139,139,139,139,139,139,139,139,139,139, /* U+8F000 */ -139,139,139,139,139,139,139,139,139,139,139,139,139,139,139,139, /* U+8F800 */ -139,139,139,139,139,139,139,139,139,139,139,139,139,139,139,139, /* U+90000 */ -139,139,139,139,139,139,139,139,139,139,139,139,139,139,139,139, /* U+90800 */ -139,139,139,139,139,139,139,139,139,139,139,139,139,139,139,139, /* U+91000 */ -139,139,139,139,139,139,139,139,139,139,139,139,139,139,139,139, /* U+91800 */ -139,139,139,139,139,139,139,139,139,139,139,139,139,139,139,139, /* U+92000 */ -139,139,139,139,139,139,139,139,139,139,139,139,139,139,139,139, /* U+92800 */ -139,139,139,139,139,139,139,139,139,139,139,139,139,139,139,139, /* U+93000 */ -139,139,139,139,139,139,139,139,139,139,139,139,139,139,139,139, /* U+93800 */ -139,139,139,139,139,139,139,139,139,139,139,139,139,139,139,139, /* U+94000 */ -139,139,139,139,139,139,139,139,139,139,139,139,139,139,139,139, /* U+94800 */ -139,139,139,139,139,139,139,139,139,139,139,139,139,139,139,139, /* U+95000 */ -139,139,139,139,139,139,139,139,139,139,139,139,139,139,139,139, /* U+95800 */ -139,139,139,139,139,139,139,139,139,139,139,139,139,139,139,139, /* U+96000 */ -139,139,139,139,139,139,139,139,139,139,139,139,139,139,139,139, /* U+96800 */ -139,139,139,139,139,139,139,139,139,139,139,139,139,139,139,139, /* U+97000 */ -139,139,139,139,139,139,139,139,139,139,139,139,139,139,139,139, /* U+97800 */ -139,139,139,139,139,139,139,139,139,139,139,139,139,139,139,139, /* U+98000 */ -139,139,139,139,139,139,139,139,139,139,139,139,139,139,139,139, /* U+98800 */ -139,139,139,139,139,139,139,139,139,139,139,139,139,139,139,139, /* U+99000 */ -139,139,139,139,139,139,139,139,139,139,139,139,139,139,139,139, /* U+99800 */ -139,139,139,139,139,139,139,139,139,139,139,139,139,139,139,139, /* U+9A000 */ -139,139,139,139,139,139,139,139,139,139,139,139,139,139,139,139, /* U+9A800 */ -139,139,139,139,139,139,139,139,139,139,139,139,139,139,139,139, /* U+9B000 */ -139,139,139,139,139,139,139,139,139,139,139,139,139,139,139,139, /* U+9B800 */ -139,139,139,139,139,139,139,139,139,139,139,139,139,139,139,139, /* U+9C000 */ -139,139,139,139,139,139,139,139,139,139,139,139,139,139,139,139, /* U+9C800 */ -139,139,139,139,139,139,139,139,139,139,139,139,139,139,139,139, /* U+9D000 */ -139,139,139,139,139,139,139,139,139,139,139,139,139,139,139,139, /* U+9D800 */ -139,139,139,139,139,139,139,139,139,139,139,139,139,139,139,139, /* U+9E000 */ -139,139,139,139,139,139,139,139,139,139,139,139,139,139,139,139, /* U+9E800 */ -139,139,139,139,139,139,139,139,139,139,139,139,139,139,139,139, /* U+9F000 */ -139,139,139,139,139,139,139,139,139,139,139,139,139,139,139,139, /* U+9F800 */ -139,139,139,139,139,139,139,139,139,139,139,139,139,139,139,139, /* U+A0000 */ -139,139,139,139,139,139,139,139,139,139,139,139,139,139,139,139, /* U+A0800 */ -139,139,139,139,139,139,139,139,139,139,139,139,139,139,139,139, /* U+A1000 */ -139,139,139,139,139,139,139,139,139,139,139,139,139,139,139,139, /* U+A1800 */ -139,139,139,139,139,139,139,139,139,139,139,139,139,139,139,139, /* U+A2000 */ -139,139,139,139,139,139,139,139,139,139,139,139,139,139,139,139, /* U+A2800 */ -139,139,139,139,139,139,139,139,139,139,139,139,139,139,139,139, /* U+A3000 */ -139,139,139,139,139,139,139,139,139,139,139,139,139,139,139,139, /* U+A3800 */ -139,139,139,139,139,139,139,139,139,139,139,139,139,139,139,139, /* U+A4000 */ -139,139,139,139,139,139,139,139,139,139,139,139,139,139,139,139, /* U+A4800 */ -139,139,139,139,139,139,139,139,139,139,139,139,139,139,139,139, /* U+A5000 */ -139,139,139,139,139,139,139,139,139,139,139,139,139,139,139,139, /* U+A5800 */ -139,139,139,139,139,139,139,139,139,139,139,139,139,139,139,139, /* U+A6000 */ -139,139,139,139,139,139,139,139,139,139,139,139,139,139,139,139, /* U+A6800 */ -139,139,139,139,139,139,139,139,139,139,139,139,139,139,139,139, /* U+A7000 */ -139,139,139,139,139,139,139,139,139,139,139,139,139,139,139,139, /* U+A7800 */ -139,139,139,139,139,139,139,139,139,139,139,139,139,139,139,139, /* U+A8000 */ -139,139,139,139,139,139,139,139,139,139,139,139,139,139,139,139, /* U+A8800 */ -139,139,139,139,139,139,139,139,139,139,139,139,139,139,139,139, /* U+A9000 */ -139,139,139,139,139,139,139,139,139,139,139,139,139,139,139,139, /* U+A9800 */ -139,139,139,139,139,139,139,139,139,139,139,139,139,139,139,139, /* U+AA000 */ -139,139,139,139,139,139,139,139,139,139,139,139,139,139,139,139, /* U+AA800 */ -139,139,139,139,139,139,139,139,139,139,139,139,139,139,139,139, /* U+AB000 */ -139,139,139,139,139,139,139,139,139,139,139,139,139,139,139,139, /* U+AB800 */ -139,139,139,139,139,139,139,139,139,139,139,139,139,139,139,139, /* U+AC000 */ -139,139,139,139,139,139,139,139,139,139,139,139,139,139,139,139, /* U+AC800 */ -139,139,139,139,139,139,139,139,139,139,139,139,139,139,139,139, /* U+AD000 */ -139,139,139,139,139,139,139,139,139,139,139,139,139,139,139,139, /* U+AD800 */ -139,139,139,139,139,139,139,139,139,139,139,139,139,139,139,139, /* U+AE000 */ -139,139,139,139,139,139,139,139,139,139,139,139,139,139,139,139, /* U+AE800 */ -139,139,139,139,139,139,139,139,139,139,139,139,139,139,139,139, /* U+AF000 */ -139,139,139,139,139,139,139,139,139,139,139,139,139,139,139,139, /* U+AF800 */ -139,139,139,139,139,139,139,139,139,139,139,139,139,139,139,139, /* U+B0000 */ -139,139,139,139,139,139,139,139,139,139,139,139,139,139,139,139, /* U+B0800 */ -139,139,139,139,139,139,139,139,139,139,139,139,139,139,139,139, /* U+B1000 */ -139,139,139,139,139,139,139,139,139,139,139,139,139,139,139,139, /* U+B1800 */ -139,139,139,139,139,139,139,139,139,139,139,139,139,139,139,139, /* U+B2000 */ -139,139,139,139,139,139,139,139,139,139,139,139,139,139,139,139, /* U+B2800 */ -139,139,139,139,139,139,139,139,139,139,139,139,139,139,139,139, /* U+B3000 */ -139,139,139,139,139,139,139,139,139,139,139,139,139,139,139,139, /* U+B3800 */ -139,139,139,139,139,139,139,139,139,139,139,139,139,139,139,139, /* U+B4000 */ -139,139,139,139,139,139,139,139,139,139,139,139,139,139,139,139, /* U+B4800 */ -139,139,139,139,139,139,139,139,139,139,139,139,139,139,139,139, /* U+B5000 */ -139,139,139,139,139,139,139,139,139,139,139,139,139,139,139,139, /* U+B5800 */ -139,139,139,139,139,139,139,139,139,139,139,139,139,139,139,139, /* U+B6000 */ -139,139,139,139,139,139,139,139,139,139,139,139,139,139,139,139, /* U+B6800 */ -139,139,139,139,139,139,139,139,139,139,139,139,139,139,139,139, /* U+B7000 */ -139,139,139,139,139,139,139,139,139,139,139,139,139,139,139,139, /* U+B7800 */ -139,139,139,139,139,139,139,139,139,139,139,139,139,139,139,139, /* U+B8000 */ -139,139,139,139,139,139,139,139,139,139,139,139,139,139,139,139, /* U+B8800 */ -139,139,139,139,139,139,139,139,139,139,139,139,139,139,139,139, /* U+B9000 */ -139,139,139,139,139,139,139,139,139,139,139,139,139,139,139,139, /* U+B9800 */ -139,139,139,139,139,139,139,139,139,139,139,139,139,139,139,139, /* U+BA000 */ -139,139,139,139,139,139,139,139,139,139,139,139,139,139,139,139, /* U+BA800 */ -139,139,139,139,139,139,139,139,139,139,139,139,139,139,139,139, /* U+BB000 */ -139,139,139,139,139,139,139,139,139,139,139,139,139,139,139,139, /* U+BB800 */ -139,139,139,139,139,139,139,139,139,139,139,139,139,139,139,139, /* U+BC000 */ -139,139,139,139,139,139,139,139,139,139,139,139,139,139,139,139, /* U+BC800 */ -139,139,139,139,139,139,139,139,139,139,139,139,139,139,139,139, /* U+BD000 */ -139,139,139,139,139,139,139,139,139,139,139,139,139,139,139,139, /* U+BD800 */ -139,139,139,139,139,139,139,139,139,139,139,139,139,139,139,139, /* U+BE000 */ -139,139,139,139,139,139,139,139,139,139,139,139,139,139,139,139, /* U+BE800 */ -139,139,139,139,139,139,139,139,139,139,139,139,139,139,139,139, /* U+BF000 */ -139,139,139,139,139,139,139,139,139,139,139,139,139,139,139,139, /* U+BF800 */ -139,139,139,139,139,139,139,139,139,139,139,139,139,139,139,139, /* U+C0000 */ -139,139,139,139,139,139,139,139,139,139,139,139,139,139,139,139, /* U+C0800 */ -139,139,139,139,139,139,139,139,139,139,139,139,139,139,139,139, /* U+C1000 */ -139,139,139,139,139,139,139,139,139,139,139,139,139,139,139,139, /* U+C1800 */ -139,139,139,139,139,139,139,139,139,139,139,139,139,139,139,139, /* U+C2000 */ -139,139,139,139,139,139,139,139,139,139,139,139,139,139,139,139, /* U+C2800 */ -139,139,139,139,139,139,139,139,139,139,139,139,139,139,139,139, /* U+C3000 */ -139,139,139,139,139,139,139,139,139,139,139,139,139,139,139,139, /* U+C3800 */ -139,139,139,139,139,139,139,139,139,139,139,139,139,139,139,139, /* U+C4000 */ -139,139,139,139,139,139,139,139,139,139,139,139,139,139,139,139, /* U+C4800 */ -139,139,139,139,139,139,139,139,139,139,139,139,139,139,139,139, /* U+C5000 */ -139,139,139,139,139,139,139,139,139,139,139,139,139,139,139,139, /* U+C5800 */ -139,139,139,139,139,139,139,139,139,139,139,139,139,139,139,139, /* U+C6000 */ -139,139,139,139,139,139,139,139,139,139,139,139,139,139,139,139, /* U+C6800 */ -139,139,139,139,139,139,139,139,139,139,139,139,139,139,139,139, /* U+C7000 */ -139,139,139,139,139,139,139,139,139,139,139,139,139,139,139,139, /* U+C7800 */ -139,139,139,139,139,139,139,139,139,139,139,139,139,139,139,139, /* U+C8000 */ -139,139,139,139,139,139,139,139,139,139,139,139,139,139,139,139, /* U+C8800 */ -139,139,139,139,139,139,139,139,139,139,139,139,139,139,139,139, /* U+C9000 */ -139,139,139,139,139,139,139,139,139,139,139,139,139,139,139,139, /* U+C9800 */ -139,139,139,139,139,139,139,139,139,139,139,139,139,139,139,139, /* U+CA000 */ -139,139,139,139,139,139,139,139,139,139,139,139,139,139,139,139, /* U+CA800 */ -139,139,139,139,139,139,139,139,139,139,139,139,139,139,139,139, /* U+CB000 */ -139,139,139,139,139,139,139,139,139,139,139,139,139,139,139,139, /* U+CB800 */ -139,139,139,139,139,139,139,139,139,139,139,139,139,139,139,139, /* U+CC000 */ -139,139,139,139,139,139,139,139,139,139,139,139,139,139,139,139, /* U+CC800 */ -139,139,139,139,139,139,139,139,139,139,139,139,139,139,139,139, /* U+CD000 */ -139,139,139,139,139,139,139,139,139,139,139,139,139,139,139,139, /* U+CD800 */ -139,139,139,139,139,139,139,139,139,139,139,139,139,139,139,139, /* U+CE000 */ -139,139,139,139,139,139,139,139,139,139,139,139,139,139,139,139, /* U+CE800 */ -139,139,139,139,139,139,139,139,139,139,139,139,139,139,139,139, /* U+CF000 */ -139,139,139,139,139,139,139,139,139,139,139,139,139,139,139,139, /* U+CF800 */ -139,139,139,139,139,139,139,139,139,139,139,139,139,139,139,139, /* U+D0000 */ -139,139,139,139,139,139,139,139,139,139,139,139,139,139,139,139, /* U+D0800 */ -139,139,139,139,139,139,139,139,139,139,139,139,139,139,139,139, /* U+D1000 */ -139,139,139,139,139,139,139,139,139,139,139,139,139,139,139,139, /* U+D1800 */ -139,139,139,139,139,139,139,139,139,139,139,139,139,139,139,139, /* U+D2000 */ -139,139,139,139,139,139,139,139,139,139,139,139,139,139,139,139, /* U+D2800 */ -139,139,139,139,139,139,139,139,139,139,139,139,139,139,139,139, /* U+D3000 */ -139,139,139,139,139,139,139,139,139,139,139,139,139,139,139,139, /* U+D3800 */ -139,139,139,139,139,139,139,139,139,139,139,139,139,139,139,139, /* U+D4000 */ -139,139,139,139,139,139,139,139,139,139,139,139,139,139,139,139, /* U+D4800 */ -139,139,139,139,139,139,139,139,139,139,139,139,139,139,139,139, /* U+D5000 */ -139,139,139,139,139,139,139,139,139,139,139,139,139,139,139,139, /* U+D5800 */ -139,139,139,139,139,139,139,139,139,139,139,139,139,139,139,139, /* U+D6000 */ -139,139,139,139,139,139,139,139,139,139,139,139,139,139,139,139, /* U+D6800 */ -139,139,139,139,139,139,139,139,139,139,139,139,139,139,139,139, /* U+D7000 */ -139,139,139,139,139,139,139,139,139,139,139,139,139,139,139,139, /* U+D7800 */ -139,139,139,139,139,139,139,139,139,139,139,139,139,139,139,139, /* U+D8000 */ -139,139,139,139,139,139,139,139,139,139,139,139,139,139,139,139, /* U+D8800 */ -139,139,139,139,139,139,139,139,139,139,139,139,139,139,139,139, /* U+D9000 */ -139,139,139,139,139,139,139,139,139,139,139,139,139,139,139,139, /* U+D9800 */ -139,139,139,139,139,139,139,139,139,139,139,139,139,139,139,139, /* U+DA000 */ -139,139,139,139,139,139,139,139,139,139,139,139,139,139,139,139, /* U+DA800 */ -139,139,139,139,139,139,139,139,139,139,139,139,139,139,139,139, /* U+DB000 */ -139,139,139,139,139,139,139,139,139,139,139,139,139,139,139,139, /* U+DB800 */ -139,139,139,139,139,139,139,139,139,139,139,139,139,139,139,139, /* U+DC000 */ -139,139,139,139,139,139,139,139,139,139,139,139,139,139,139,139, /* U+DC800 */ -139,139,139,139,139,139,139,139,139,139,139,139,139,139,139,139, /* U+DD000 */ -139,139,139,139,139,139,139,139,139,139,139,139,139,139,139,139, /* U+DD800 */ -139,139,139,139,139,139,139,139,139,139,139,139,139,139,139,139, /* U+DE000 */ -139,139,139,139,139,139,139,139,139,139,139,139,139,139,139,139, /* U+DE800 */ -139,139,139,139,139,139,139,139,139,139,139,139,139,139,139,139, /* U+DF000 */ -139,139,139,139,139,139,139,139,139,139,139,139,139,139,139,139, /* U+DF800 */ -222,223,224,225,223,223,223,223,223,223,223,223,223,223,223,223, /* U+E0000 */ -223,223,223,223,223,223,223,223,223,223,223,223,223,223,223,223, /* U+E0800 */ -139,139,139,139,139,139,139,139,139,139,139,139,139,139,139,139, /* U+E1000 */ -139,139,139,139,139,139,139,139,139,139,139,139,139,139,139,139, /* U+E1800 */ -139,139,139,139,139,139,139,139,139,139,139,139,139,139,139,139, /* U+E2000 */ -139,139,139,139,139,139,139,139,139,139,139,139,139,139,139,139, /* U+E2800 */ -139,139,139,139,139,139,139,139,139,139,139,139,139,139,139,139, /* U+E3000 */ -139,139,139,139,139,139,139,139,139,139,139,139,139,139,139,139, /* U+E3800 */ -139,139,139,139,139,139,139,139,139,139,139,139,139,139,139,139, /* U+E4000 */ -139,139,139,139,139,139,139,139,139,139,139,139,139,139,139,139, /* U+E4800 */ -139,139,139,139,139,139,139,139,139,139,139,139,139,139,139,139, /* U+E5000 */ -139,139,139,139,139,139,139,139,139,139,139,139,139,139,139,139, /* U+E5800 */ -139,139,139,139,139,139,139,139,139,139,139,139,139,139,139,139, /* U+E6000 */ -139,139,139,139,139,139,139,139,139,139,139,139,139,139,139,139, /* U+E6800 */ -139,139,139,139,139,139,139,139,139,139,139,139,139,139,139,139, /* U+E7000 */ -139,139,139,139,139,139,139,139,139,139,139,139,139,139,139,139, /* U+E7800 */ -139,139,139,139,139,139,139,139,139,139,139,139,139,139,139,139, /* U+E8000 */ -139,139,139,139,139,139,139,139,139,139,139,139,139,139,139,139, /* U+E8800 */ -139,139,139,139,139,139,139,139,139,139,139,139,139,139,139,139, /* U+E9000 */ -139,139,139,139,139,139,139,139,139,139,139,139,139,139,139,139, /* U+E9800 */ -139,139,139,139,139,139,139,139,139,139,139,139,139,139,139,139, /* U+EA000 */ -139,139,139,139,139,139,139,139,139,139,139,139,139,139,139,139, /* U+EA800 */ -139,139,139,139,139,139,139,139,139,139,139,139,139,139,139,139, /* U+EB000 */ -139,139,139,139,139,139,139,139,139,139,139,139,139,139,139,139, /* U+EB800 */ -139,139,139,139,139,139,139,139,139,139,139,139,139,139,139,139, /* U+EC000 */ -139,139,139,139,139,139,139,139,139,139,139,139,139,139,139,139, /* U+EC800 */ -139,139,139,139,139,139,139,139,139,139,139,139,139,139,139,139, /* U+ED000 */ -139,139,139,139,139,139,139,139,139,139,139,139,139,139,139,139, /* U+ED800 */ -139,139,139,139,139,139,139,139,139,139,139,139,139,139,139,139, /* U+EE000 */ -139,139,139,139,139,139,139,139,139,139,139,139,139,139,139,139, /* U+EE800 */ -139,139,139,139,139,139,139,139,139,139,139,139,139,139,139,139, /* U+EF000 */ -139,139,139,139,139,139,139,139,139,139,139,139,139,139,139,139, /* U+EF800 */ -123,123,123,123,123,123,123,123,123,123,123,123,123,123,123,123, /* U+F0000 */ -123,123,123,123,123,123,123,123,123,123,123,123,123,123,123,123, /* U+F0800 */ -123,123,123,123,123,123,123,123,123,123,123,123,123,123,123,123, /* U+F1000 */ -123,123,123,123,123,123,123,123,123,123,123,123,123,123,123,123, /* U+F1800 */ -123,123,123,123,123,123,123,123,123,123,123,123,123,123,123,123, /* U+F2000 */ -123,123,123,123,123,123,123,123,123,123,123,123,123,123,123,123, /* U+F2800 */ -123,123,123,123,123,123,123,123,123,123,123,123,123,123,123,123, /* U+F3000 */ -123,123,123,123,123,123,123,123,123,123,123,123,123,123,123,123, /* U+F3800 */ -123,123,123,123,123,123,123,123,123,123,123,123,123,123,123,123, /* U+F4000 */ -123,123,123,123,123,123,123,123,123,123,123,123,123,123,123,123, /* U+F4800 */ -123,123,123,123,123,123,123,123,123,123,123,123,123,123,123,123, /* U+F5000 */ -123,123,123,123,123,123,123,123,123,123,123,123,123,123,123,123, /* U+F5800 */ -123,123,123,123,123,123,123,123,123,123,123,123,123,123,123,123, /* U+F6000 */ -123,123,123,123,123,123,123,123,123,123,123,123,123,123,123,123, /* U+F6800 */ -123,123,123,123,123,123,123,123,123,123,123,123,123,123,123,123, /* U+F7000 */ -123,123,123,123,123,123,123,123,123,123,123,123,123,123,123,123, /* U+F7800 */ -123,123,123,123,123,123,123,123,123,123,123,123,123,123,123,123, /* U+F8000 */ -123,123,123,123,123,123,123,123,123,123,123,123,123,123,123,123, /* U+F8800 */ -123,123,123,123,123,123,123,123,123,123,123,123,123,123,123,123, /* U+F9000 */ -123,123,123,123,123,123,123,123,123,123,123,123,123,123,123,123, /* U+F9800 */ -123,123,123,123,123,123,123,123,123,123,123,123,123,123,123,123, /* U+FA000 */ -123,123,123,123,123,123,123,123,123,123,123,123,123,123,123,123, /* U+FA800 */ -123,123,123,123,123,123,123,123,123,123,123,123,123,123,123,123, /* U+FB000 */ -123,123,123,123,123,123,123,123,123,123,123,123,123,123,123,123, /* U+FB800 */ -123,123,123,123,123,123,123,123,123,123,123,123,123,123,123,123, /* U+FC000 */ -123,123,123,123,123,123,123,123,123,123,123,123,123,123,123,123, /* U+FC800 */ -123,123,123,123,123,123,123,123,123,123,123,123,123,123,123,123, /* U+FD000 */ -123,123,123,123,123,123,123,123,123,123,123,123,123,123,123,123, /* U+FD800 */ -123,123,123,123,123,123,123,123,123,123,123,123,123,123,123,123, /* U+FE000 */ -123,123,123,123,123,123,123,123,123,123,123,123,123,123,123,123, /* U+FE800 */ -123,123,123,123,123,123,123,123,123,123,123,123,123,123,123,123, /* U+FF000 */ -123,123,123,123,123,123,123,123,123,123,123,123,123,123,123,226, /* U+FF800 */ -123,123,123,123,123,123,123,123,123,123,123,123,123,123,123,123, /* U+100000 */ -123,123,123,123,123,123,123,123,123,123,123,123,123,123,123,123, /* U+100800 */ -123,123,123,123,123,123,123,123,123,123,123,123,123,123,123,123, /* U+101000 */ -123,123,123,123,123,123,123,123,123,123,123,123,123,123,123,123, /* U+101800 */ -123,123,123,123,123,123,123,123,123,123,123,123,123,123,123,123, /* U+102000 */ -123,123,123,123,123,123,123,123,123,123,123,123,123,123,123,123, /* U+102800 */ -123,123,123,123,123,123,123,123,123,123,123,123,123,123,123,123, /* U+103000 */ -123,123,123,123,123,123,123,123,123,123,123,123,123,123,123,123, /* U+103800 */ -123,123,123,123,123,123,123,123,123,123,123,123,123,123,123,123, /* U+104000 */ -123,123,123,123,123,123,123,123,123,123,123,123,123,123,123,123, /* U+104800 */ -123,123,123,123,123,123,123,123,123,123,123,123,123,123,123,123, /* U+105000 */ -123,123,123,123,123,123,123,123,123,123,123,123,123,123,123,123, /* U+105800 */ -123,123,123,123,123,123,123,123,123,123,123,123,123,123,123,123, /* U+106000 */ -123,123,123,123,123,123,123,123,123,123,123,123,123,123,123,123, /* U+106800 */ -123,123,123,123,123,123,123,123,123,123,123,123,123,123,123,123, /* U+107000 */ -123,123,123,123,123,123,123,123,123,123,123,123,123,123,123,123, /* U+107800 */ -123,123,123,123,123,123,123,123,123,123,123,123,123,123,123,123, /* U+108000 */ -123,123,123,123,123,123,123,123,123,123,123,123,123,123,123,123, /* U+108800 */ -123,123,123,123,123,123,123,123,123,123,123,123,123,123,123,123, /* U+109000 */ -123,123,123,123,123,123,123,123,123,123,123,123,123,123,123,123, /* U+109800 */ -123,123,123,123,123,123,123,123,123,123,123,123,123,123,123,123, /* U+10A000 */ -123,123,123,123,123,123,123,123,123,123,123,123,123,123,123,123, /* U+10A800 */ -123,123,123,123,123,123,123,123,123,123,123,123,123,123,123,123, /* U+10B000 */ -123,123,123,123,123,123,123,123,123,123,123,123,123,123,123,123, /* U+10B800 */ -123,123,123,123,123,123,123,123,123,123,123,123,123,123,123,123, /* U+10C000 */ -123,123,123,123,123,123,123,123,123,123,123,123,123,123,123,123, /* U+10C800 */ -123,123,123,123,123,123,123,123,123,123,123,123,123,123,123,123, /* U+10D000 */ -123,123,123,123,123,123,123,123,123,123,123,123,123,123,123,123, /* U+10D800 */ -123,123,123,123,123,123,123,123,123,123,123,123,123,123,123,123, /* U+10E000 */ -123,123,123,123,123,123,123,123,123,123,123,123,123,123,123,123, /* U+10E800 */ -123,123,123,123,123,123,123,123,123,123,123,123,123,123,123,123, /* U+10F000 */ -123,123,123,123,123,123,123,123,123,123,123,123,123,123,123,226, /* U+10F800 */ -}; - -const pcre_uint16 PRIV(ucd_stage2)[] = { /* 58112 bytes, block = 128 */ -/* block 0 */ - 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 1, 0, 0, 2, 0, 0, - 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, - 3, 4, 4, 4, 5, 4, 4, 4, 6, 7, 4, 8, 4, 9, 4, 4, - 10, 10, 10, 10, 10, 10, 10, 10, 10, 10, 4, 4, 8, 8, 8, 4, - 4, 11, 11, 11, 11, 11, 11, 11, 11, 11, 11, 12, 11, 11, 11, 11, - 11, 11, 11, 13, 11, 11, 11, 11, 11, 11, 11, 6, 4, 7, 14, 15, - 14, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 17, 16, 16, 16, 16, - 16, 16, 16, 18, 16, 16, 16, 16, 16, 16, 16, 6, 8, 7, 8, 0, - -/* block 1 */ - 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, - 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, - 3, 4, 5, 5, 5, 5, 19, 4, 14, 19, 20, 21, 8, 22, 19, 14, - 19, 8, 23, 23, 14, 24, 4, 4, 14, 23, 20, 25, 23, 23, 23, 4, - 11, 11, 11, 11, 11, 26, 11, 11, 11, 11, 11, 11, 11, 11, 11, 11, - 11, 11, 11, 11, 11, 11, 11, 8, 11, 11, 11, 11, 11, 11, 11, 27, - 16, 16, 16, 16, 16, 28, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, - 16, 16, 16, 16, 16, 16, 16, 8, 16, 16, 16, 16, 16, 16, 16, 29, - -/* block 2 */ - 30, 31, 30, 31, 30, 31, 30, 31, 30, 31, 30, 31, 30, 31, 30, 31, - 30, 31, 30, 31, 30, 31, 30, 31, 30, 31, 30, 31, 30, 31, 30, 31, - 30, 31, 30, 31, 30, 31, 30, 31, 30, 31, 30, 31, 30, 31, 30, 31, - 32, 33, 30, 31, 30, 31, 30, 31, 33, 30, 31, 30, 31, 30, 31, 30, - 31, 30, 31, 30, 31, 30, 31, 30, 31, 33, 30, 31, 30, 31, 30, 31, - 30, 31, 30, 31, 30, 31, 30, 31, 30, 31, 30, 31, 30, 31, 30, 31, - 30, 31, 30, 31, 30, 31, 30, 31, 30, 31, 30, 31, 30, 31, 30, 31, - 30, 31, 30, 31, 30, 31, 30, 31, 34, 30, 31, 30, 31, 30, 31, 35, - -/* block 3 */ - 36, 37, 30, 31, 30, 31, 38, 30, 31, 39, 39, 30, 31, 33, 40, 41, - 42, 30, 31, 39, 43, 44, 45, 46, 30, 31, 47, 33, 45, 48, 49, 50, - 30, 31, 30, 31, 30, 31, 51, 30, 31, 51, 33, 33, 30, 31, 51, 30, - 31, 52, 52, 30, 31, 30, 31, 53, 30, 31, 33, 20, 30, 31, 33, 54, - 20, 20, 20, 20, 55, 56, 57, 58, 59, 60, 61, 62, 63, 30, 31, 30, - 31, 30, 31, 30, 31, 30, 31, 30, 31, 30, 31, 30, 31, 64, 30, 31, - 30, 31, 30, 31, 30, 31, 30, 31, 30, 31, 30, 31, 30, 31, 30, 31, - 33, 65, 66, 67, 30, 31, 68, 69, 30, 31, 30, 31, 30, 31, 30, 31, - -/* block 4 */ - 30, 31, 30, 31, 30, 31, 30, 31, 30, 31, 30, 31, 30, 31, 30, 31, - 30, 31, 30, 31, 30, 31, 30, 31, 30, 31, 30, 31, 30, 31, 30, 31, - 70, 33, 30, 31, 30, 31, 30, 31, 30, 31, 30, 31, 30, 31, 30, 31, - 30, 31, 30, 31, 33, 33, 33, 33, 33, 33, 71, 30, 31, 72, 73, 74, - 74, 30, 31, 75, 76, 77, 30, 31, 30, 31, 30, 31, 30, 31, 30, 31, - 78, 79, 80, 81, 82, 33, 83, 83, 33, 84, 33, 85, 86, 33, 33, 33, - 83, 87, 33, 88, 33, 89, 90, 33, 91, 92, 33, 93, 94, 33, 33, 92, - 33, 95, 96, 33, 33, 97, 33, 33, 33, 33, 33, 33, 33, 98, 33, 33, - -/* block 5 */ - 99, 33, 33, 99, 33, 33, 33,100, 99,101,102,102,103, 33, 33, 33, - 33, 33,104, 33, 20, 33, 33, 33, 33, 33, 33, 33, 33, 33,105, 33, - 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, -106,106,106,106,106,106,106,106,106,107,107,107,107,107,107,107, -107,107, 14, 14, 14, 14,107,107,107,107,107,107,107,107,107,107, -107,107, 14, 14, 14, 14, 14, 14, 14, 14, 14, 14, 14, 14, 14, 14, -106,106,106,106,106, 14, 14, 14, 14, 14,108,108,107, 14,107, 14, - 14, 14, 14, 14, 14, 14, 14, 14, 14, 14, 14, 14, 14, 14, 14, 14, - -/* block 6 */ -109,109,109,109,109,109,109,109,109,109,109,109,109,109,109,109, -109,109,109,109,109,109,109,109,109,109,109,109,109,109,109,109, -109,109,109,109,109,109,109,109,109,109,109,109,109,109,109,109, -109,109,109,109,109,109,109,109,109,109,109,109,109,109,109,109, -109,109,109,109,109,110,109,109,109,109,109,109,109,109,109,109, -109,109,109,109,109,109,109,109,109,109,109,109,109,109,109,109, -109,109,109,109,109,109,109,109,109,109,109,109,109,109,109,109, -111,112,111,112,107,113,111,112,114,114,115,116,116,116, 4,117, - -/* block 7 */ -114,114,114,114,113, 14,118, 4,119,119,119,114,120,114,121,121, -122,123,124,123,123,125,123,123,126,127,128,123,129,123,123,123, -130,131,114,132,123,123,133,123,123,134,123,123,135,136,136,136, -122,137,138,137,137,139,137,137,140,141,142,137,143,137,137,137, -144,145,146,147,137,137,148,137,137,149,137,137,150,151,151,152, -153,154,155,155,155,156,157,158,111,112,111,112,111,112,111,112, -111,112,159,160,159,160,159,160,159,160,159,160,159,160,159,160, -161,162,163,164,165,166,167,111,112,168,111,112,122,169,169,169, - -/* block 8 */ -170,170,170,170,170,170,170,170,170,170,170,170,170,170,170,170, -171,171,171,171,171,171,171,171,171,171,171,171,171,171,171,171, -171,171,171,171,171,171,171,171,171,171,171,171,171,171,171,171, -172,172,172,172,172,172,172,172,172,172,172,172,172,172,172,172, -172,172,172,172,172,172,172,172,172,172,172,172,172,172,172,172, -173,173,173,173,173,173,173,173,173,173,173,173,173,173,173,173, -174,175,174,175,174,175,174,175,174,175,174,175,174,175,174,175, -174,175,174,175,174,175,174,175,174,175,174,175,174,175,174,175, - -/* block 9 */ -174,175,176,177,177,109,109,177,178,178,174,175,174,175,174,175, -174,175,174,175,174,175,174,175,174,175,174,175,174,175,174,175, -174,175,174,175,174,175,174,175,174,175,174,175,174,175,174,175, -174,175,174,175,174,175,174,175,174,175,174,175,174,175,174,175, -179,174,175,174,175,174,175,174,175,174,175,174,175,174,175,180, -174,175,174,175,174,175,174,175,174,175,174,175,174,175,174,175, -174,175,174,175,174,175,174,175,174,175,174,175,174,175,174,175, -174,175,174,175,174,175,174,175,174,175,174,175,174,175,174,175, - -/* block 10 */ -174,175,174,175,174,175,174,175,174,175,174,175,174,175,174,175, -174,175,174,175,174,175,174,175,174,175,174,175,174,175,174,175, -174,175,174,175,174,175,174,175,174,175,174,175,174,175,174,175, -114,181,181,181,181,181,181,181,181,181,181,181,181,181,181,181, -181,181,181,181,181,181,181,181,181,181,181,181,181,181,181,181, -181,181,181,181,181,181,181,114,114,182,183,183,183,183,183,183, -114,184,184,184,184,184,184,184,184,184,184,184,184,184,184,184, -184,184,184,184,184,184,184,184,184,184,184,184,184,184,184,184, - -/* block 11 */ -184,184,184,184,184,184,184,185,114, 4,186,114,114,187,187,188, -114,189,189,189,189,189,189,189,189,189,189,189,189,189,189,189, -189,189,189,189,189,189,189,189,189,189,189,189,189,189,189,189, -189,189,189,189,189,189,189,189,189,189,189,189,189,189,190,189, -191,189,189,191,189,189,191,189,114,114,114,114,114,114,114,114, -192,192,192,192,192,192,192,192,192,192,192,192,192,192,192,192, -192,192,192,192,192,192,192,192,192,192,192,114,114,114,114,114, -192,192,192,191,191,114,114,114,114,114,114,114,114,114,114,114, - -/* block 12 */ -193,193,193,193,193, 22,194,194,194,195,195,196, 4,195,197,197, -198,198,198,198,198,198,198,198,198,198,198, 4, 22,114,195, 4, -199,199,199,199,199,199,199,199,199,199,199,199,199,199,199,199, -199,199,199,199,199,199,199,199,199,199,199,199,199,199,199,199, -107,199,199,199,199,199,199,199,199,199,199,109,109,109,109,109, -109,109,109,109,109,109,198,198,198,198,198,198,198,198,198,198, - 10, 10, 10, 10, 10, 10, 10, 10, 10, 10,195,195,195,195,199,199, -109,199,199,199,199,199,199,199,199,199,199,199,199,199,199,199, - -/* block 13 */ -199,199,199,199,199,199,199,199,199,199,199,199,199,199,199,199, -199,199,199,199,199,199,199,199,199,199,199,199,199,199,199,199, -199,199,199,199,199,199,199,199,199,199,199,199,199,199,199,199, -199,199,199,199,199,199,199,199,199,199,199,199,199,199,199,199, -199,199,199,199,199,199,199,199,199,199,199,199,199,199,199,199, -199,199,199,199,195,199,198,198,198,198,198,198,198, 22,197,198, -198,198,198,198,198,200,200,198,198,197,198,198,198,198,199,199, -201,201,201,201,201,201,201,201,201,201,199,199,199,197,197,199, - -/* block 14 */ -202,202,202,202,202,202,202,202,202,202,202,202,202,202,114,203, -204,205,204,204,204,204,204,204,204,204,204,204,204,204,204,204, -204,204,204,204,204,204,204,204,204,204,204,204,204,204,204,204, -205,205,205,205,205,205,205,205,205,205,205,205,205,205,205,205, -205,205,205,205,205,205,205,205,205,205,205,114,114,204,204,204, -199,199,199,199,199,199,199,199,199,199,199,199,199,199,199,199, -199,199,199,199,199,199,199,199,199,199,199,199,199,199,199,199, -199,199,199,199,199,199,199,199,199,199,199,199,199,199,199,199, - -/* block 15 */ -206,206,206,206,206,206,206,206,206,206,206,206,206,206,206,206, -206,206,206,206,206,206,206,206,206,206,206,206,206,206,206,206, -206,206,206,206,206,206,207,207,207,207,207,207,207,207,207,207, -207,206,114,114,114,114,114,114,114,114,114,114,114,114,114,114, -208,208,208,208,208,208,208,208,208,208,209,209,209,209,209,209, -209,209,209,209,209,209,209,209,209,209,209,209,209,209,209,209, -209,209,209,209,209,209,209,209,209,209,209,210,210,210,210,210, -210,210,210,210,211,211,212,213,213,213,211,114,114,114,114,114, - -/* block 16 */ -214,214,214,214,214,214,214,214,214,214,214,214,214,214,214,214, -214,214,214,214,214,214,215,215,215,215,216,215,215,215,215,215, -215,215,215,215,216,215,215,215,216,215,215,215,215,215,114,114, -217,217,217,217,217,217,217,217,217,217,217,217,217,217,217,114, -218,218,218,218,218,218,218,218,218,218,218,218,218,218,218,218, -218,218,218,218,218,218,218,218,218,219,219,219,114,114,220,114, -114,114,114,114,114,114,114,114,114,114,114,114,114,114,114,114, -114,114,114,114,114,114,114,114,114,114,114,114,114,114,114,114, - -/* block 17 */ -114,114,114,114,114,114,114,114,114,114,114,114,114,114,114,114, -114,114,114,114,114,114,114,114,114,114,114,114,114,114,114,114, -199,199,199,199,199,199,199,199,199,199,199,199,199,199,199,199, -199,199,199,114,114,114,114,114,114,114,114,114,114,114,114,114, -114,114,114,114,114,114,114,114,114,114,114,114,114,114,114,114, -114,114,114,114,114,114,114,114,114,114,114,114,114,114,114,114, -114,114,114,114,198,198,198,198,198,198,198,198,198,198,198,198, -198,198,198,198,198,198,198,198,198,198,198,198,198,198,198,198, - -/* block 18 */ -221,221,221,222,223,223,223,223,223,223,223,223,223,223,223,223, -223,223,223,223,223,223,223,223,223,223,223,223,223,223,223,223, -223,223,223,223,223,223,223,223,223,223,223,223,223,223,223,223, -223,223,223,223,223,223,223,223,223,223,221,222,221,223,222,222, -222,221,221,221,221,221,221,221,221,222,222,222,222,221,222,222, -223,109,109,221,221,221,221,221,223,223,223,223,223,223,223,223, -223,223,221,221, 4, 4,224,224,224,224,224,224,224,224,224,224, -225,226,223,223,223,223,223,223,223,223,223,223,223,223,223,223, - -/* block 19 */ -227,228,229,229,114,227,227,227,227,227,227,227,227,114,114,227, -227,114,114,227,227,227,227,227,227,227,227,227,227,227,227,227, -227,227,227,227,227,227,227,227,227,114,227,227,227,227,227,227, -227,114,227,114,114,114,227,227,227,227,114,114,228,227,230,229, -229,228,228,228,228,114,114,229,229,114,114,229,229,228,227,114, -114,114,114,114,114,114,114,230,114,114,114,114,227,227,114,227, -227,227,228,228,114,114,231,231,231,231,231,231,231,231,231,231, -227,227,232,232,233,233,233,233,233,233,234,232,114,114,114,114, - -/* block 20 */ -114,235,235,236,114,237,237,237,237,237,237,114,114,114,114,237, -237,114,114,237,237,237,237,237,237,237,237,237,237,237,237,237, -237,237,237,237,237,237,237,237,237,114,237,237,237,237,237,237, -237,114,237,237,114,237,237,114,237,237,114,114,235,114,236,236, -236,235,235,114,114,114,114,235,235,114,114,235,235,235,114,114, -114,235,114,114,114,114,114,114,114,237,237,237,237,114,237,114, -114,114,114,114,114,114,238,238,238,238,238,238,238,238,238,238, -235,235,237,237,237,235,114,114,114,114,114,114,114,114,114,114, - -/* block 21 */ -114,239,239,240,114,241,241,241,241,241,241,241,241,241,114,241, -241,241,114,241,241,241,241,241,241,241,241,241,241,241,241,241, -241,241,241,241,241,241,241,241,241,114,241,241,241,241,241,241, -241,114,241,241,114,241,241,241,241,241,114,114,239,241,240,240, -240,239,239,239,239,239,114,239,239,240,114,240,240,239,114,114, -241,114,114,114,114,114,114,114,114,114,114,114,114,114,114,114, -241,241,239,239,114,114,242,242,242,242,242,242,242,242,242,242, -243,244,114,114,114,114,114,114,114,114,114,114,114,114,114,114, - -/* block 22 */ -114,245,246,246,114,247,247,247,247,247,247,247,247,114,114,247, -247,114,114,247,247,247,247,247,247,247,247,247,247,247,247,247, -247,247,247,247,247,247,247,247,247,114,247,247,247,247,247,247, -247,114,247,247,114,247,247,247,247,247,114,114,245,247,248,245, -246,245,245,245,245,114,114,246,246,114,114,246,246,245,114,114, -114,114,114,114,114,114,245,248,114,114,114,114,247,247,114,247, -247,247,245,245,114,114,249,249,249,249,249,249,249,249,249,249, -250,247,251,251,251,251,251,251,114,114,114,114,114,114,114,114, - -/* block 23 */ -114,114,252,253,114,253,253,253,253,253,253,114,114,114,253,253, -253,114,253,253,253,253,114,114,114,253,253,114,253,114,253,253, -114,114,114,253,253,114,114,114,253,253,253,114,114,114,253,253, -253,253,253,253,253,253,253,253,253,253,114,114,114,114,254,255, -252,255,255,114,114,114,255,255,255,114,255,255,255,252,114,114, -253,114,114,114,114,114,114,254,114,114,114,114,114,114,114,114, -114,114,114,114,114,114,256,256,256,256,256,256,256,256,256,256, -257,257,257,258,258,258,258,258,258,259,258,114,114,114,114,114, - -/* block 24 */ -260,261,261,261,114,262,262,262,262,262,262,262,262,114,262,262, -262,114,262,262,262,262,262,262,262,262,262,262,262,262,262,262, -262,262,262,262,262,262,262,262,262,114,262,262,262,262,262,262, -262,262,262,262,262,262,262,262,262,262,114,114,114,262,260,260, -260,261,261,261,261,114,260,260,260,114,260,260,260,260,114,114, -114,114,114,114,114,260,260,114,262,262,114,114,114,114,114,114, -262,262,260,260,114,114,263,263,263,263,263,263,263,263,263,263, -114,114,114,114,114,114,114,114,264,264,264,264,264,264,264,265, - -/* block 25 */ -114,266,267,267,114,268,268,268,268,268,268,268,268,114,268,268, -268,114,268,268,268,268,268,268,268,268,268,268,268,268,268,268, -268,268,268,268,268,268,268,268,268,114,268,268,268,268,268,268, -268,268,268,268,114,268,268,268,268,268,114,114,266,268,267,266, -267,267,269,267,267,114,266,267,267,114,267,267,266,266,114,114, -114,114,114,114,114,269,269,114,114,114,114,114,114,114,268,114, -268,268,266,266,114,114,270,270,270,270,270,270,270,270,270,270, -114,268,268,114,114,114,114,114,114,114,114,114,114,114,114,114, - -/* block 26 */ -114,271,272,272,114,273,273,273,273,273,273,273,273,114,273,273, -273,114,273,273,273,273,273,273,273,273,273,273,273,273,273,273, -273,273,273,273,273,273,273,273,273,273,273,273,273,273,273,273, -273,273,273,273,273,273,273,273,273,273,273,114,114,273,274,272, -272,271,271,271,271,114,272,272,272,114,272,272,272,271,273,114, -114,114,114,114,114,114,114,274,114,114,114,114,114,114,114,114, -273,273,271,271,114,114,275,275,275,275,275,275,275,275,275,275, -276,276,276,276,276,276,114,114,114,277,273,273,273,273,273,273, - -/* block 27 */ -114,114,278,278,114,279,279,279,279,279,279,279,279,279,279,279, -279,279,279,279,279,279,279,114,114,114,279,279,279,279,279,279, -279,279,279,279,279,279,279,279,279,279,279,279,279,279,279,279, -279,279,114,279,279,279,279,279,279,279,279,279,114,279,114,114, -279,279,279,279,279,279,279,114,114,114,280,114,114,114,114,281, -278,278,280,280,280,114,280,114,278,278,278,278,278,278,278,281, -114,114,114,114,114,114,282,282,282,282,282,282,282,282,282,282, -114,114,278,278,283,114,114,114,114,114,114,114,114,114,114,114, - -/* block 28 */ -114,284,284,284,284,284,284,284,284,284,284,284,284,284,284,284, -284,284,284,284,284,284,284,284,284,284,284,284,284,284,284,284, -284,284,284,284,284,284,284,284,284,284,284,284,284,284,284,284, -284,285,284,286,285,285,285,285,285,285,285,114,114,114,114, 5, -284,284,284,284,284,284,287,285,285,285,285,285,285,285,285,288, -289,289,289,289,289,289,289,289,289,289,288,288,114,114,114,114, -114,114,114,114,114,114,114,114,114,114,114,114,114,114,114,114, -114,114,114,114,114,114,114,114,114,114,114,114,114,114,114,114, - -/* block 29 */ -114,290,290,114,290,114,114,290,290,114,290,114,114,290,114,114, -114,114,114,114,290,290,290,290,114,290,290,290,290,290,290,290, -114,290,290,290,114,290,114,290,114,114,290,290,114,290,290,290, -290,291,290,292,291,291,291,291,291,291,114,291,291,290,114,114, -290,290,290,290,290,114,293,114,291,291,291,291,291,291,114,114, -294,294,294,294,294,294,294,294,294,294,114,114,290,290,290,290, -114,114,114,114,114,114,114,114,114,114,114,114,114,114,114,114, -114,114,114,114,114,114,114,114,114,114,114,114,114,114,114,114, - -/* block 30 */ -295,296,296,296,297,297,297,297,297,297,297,297,297,297,297,297, -297,297,297,296,297,296,296,296,298,298,296,296,296,296,296,296, -299,299,299,299,299,299,299,299,299,299,300,300,300,300,300,300, -300,300,300,300,296,298,296,298,296,298,301,302,301,302,303,303, -295,295,295,295,295,295,295,295,114,295,295,295,295,295,295,295, -295,295,295,295,295,295,295,295,295,295,295,295,295,295,295,295, -295,295,295,295,295,295,295,295,295,295,295,295,295,114,114,114, -114,298,298,298,298,298,298,298,298,298,298,298,298,298,298,303, - -/* block 31 */ -298,298,298,298,298,297,298,298,295,295,295,295,295,298,298,298, -298,298,298,298,298,298,298,298,114,298,298,298,298,298,298,298, -298,298,298,298,298,298,298,298,298,298,298,298,298,298,298,298, -298,298,298,298,298,298,298,298,298,298,298,298,298,114,296,296, -296,296,296,296,296,296,298,296,296,296,296,296,296,114,296,296, -297,297,297,297,297, 19, 19, 19, 19,297,297,114,114,114,114,114, -114,114,114,114,114,114,114,114,114,114,114,114,114,114,114,114, -114,114,114,114,114,114,114,114,114,114,114,114,114,114,114,114, - -/* block 32 */ -304,304,304,304,304,304,304,304,304,304,304,304,304,304,304,304, -304,304,304,304,304,304,304,304,304,304,304,304,304,304,304,304, -304,304,304,304,304,304,304,304,304,304,304,305,305,306,306,306, -306,307,306,306,306,306,306,306,305,306,306,307,307,306,306,304, -308,308,308,308,308,308,308,308,308,308,309,309,309,309,309,309, -304,304,304,304,304,304,307,307,306,306,304,304,304,304,306,306, -306,304,305,305,305,304,304,305,305,305,305,305,305,305,304,304, -304,306,306,306,306,304,304,304,304,304,304,304,304,304,304,304, - -/* block 33 */ -304,304,306,305,307,306,306,305,305,305,305,305,305,306,304,305, -308,308,308,308,308,308,308,308,308,308,305,305,305,306,310,310, -311,311,311,311,311,311,311,311,311,311,311,311,311,311,311,311, -311,311,311,311,311,311,311,311,311,311,311,311,311,311,311,311, -311,311,311,311,311,311,114,311,114,114,114,114,114,311,114,114, -312,312,312,312,312,312,312,312,312,312,312,312,312,312,312,312, -312,312,312,312,312,312,312,312,312,312,312,312,312,312,312,312, -312,312,312,312,312,312,312,312,312,312,312, 4,313,312,312,312, - -/* block 34 */ -314,314,314,314,314,314,314,314,314,314,314,314,314,314,314,314, -314,314,314,314,314,314,314,314,314,314,314,314,314,314,314,314, -314,314,314,314,314,314,314,314,314,314,314,314,314,314,314,314, -314,314,314,314,314,314,314,314,314,314,314,314,314,314,314,314, -314,314,314,314,314,314,314,314,314,314,314,314,314,314,314,314, -314,314,314,314,314,314,314,314,314,314,314,314,314,314,314,314, -315,315,315,315,315,315,315,315,315,315,315,315,315,315,315,315, -315,315,315,315,315,315,315,315,315,315,315,315,315,315,315,315, - -/* block 35 */ -315,315,315,315,315,315,315,315,315,315,315,315,315,315,315,315, -315,315,315,315,315,315,315,315,315,315,315,315,315,315,315,315, -315,315,315,315,315,315,315,315,316,316,316,316,316,316,316,316, -316,316,316,316,316,316,316,316,316,316,316,316,316,316,316,316, -316,316,316,316,316,316,316,316,316,316,316,316,316,316,316,316, -316,316,316,316,316,316,316,316,316,316,316,316,316,316,316,316, -316,316,316,316,316,316,316,316,316,316,316,316,316,316,316,316, -316,316,316,316,316,316,316,316,316,316,316,316,316,316,316,316, - -/* block 36 */ -317,317,317,317,317,317,317,317,317,317,317,317,317,317,317,317, -317,317,317,317,317,317,317,317,317,317,317,317,317,317,317,317, -317,317,317,317,317,317,317,317,317,317,317,317,317,317,317,317, -317,317,317,317,317,317,317,317,317,317,317,317,317,317,317,317, -317,317,317,317,317,317,317,317,317,114,317,317,317,317,114,114, -317,317,317,317,317,317,317,114,317,114,317,317,317,317,114,114, -317,317,317,317,317,317,317,317,317,317,317,317,317,317,317,317, -317,317,317,317,317,317,317,317,317,317,317,317,317,317,317,317, - -/* block 37 */ -317,317,317,317,317,317,317,317,317,114,317,317,317,317,114,114, -317,317,317,317,317,317,317,317,317,317,317,317,317,317,317,317, -317,317,317,317,317,317,317,317,317,317,317,317,317,317,317,317, -317,114,317,317,317,317,114,114,317,317,317,317,317,317,317,114, -317,114,317,317,317,317,114,114,317,317,317,317,317,317,317,317, -317,317,317,317,317,317,317,114,317,317,317,317,317,317,317,317, -317,317,317,317,317,317,317,317,317,317,317,317,317,317,317,317, -317,317,317,317,317,317,317,317,317,317,317,317,317,317,317,317, - -/* block 38 */ -317,317,317,317,317,317,317,317,317,317,317,317,317,317,317,317, -317,114,317,317,317,317,114,114,317,317,317,317,317,317,317,317, -317,317,317,317,317,317,317,317,317,317,317,317,317,317,317,317, -317,317,317,317,317,317,317,317,317,317,317,317,317,317,317,317, -317,317,317,317,317,317,317,317,317,317,317,317,317,317,317,317, -317,317,317,317,317,317,317,317,317,317,317,114,114,318,318,318, -319,319,319,319,319,319,319,319,319,320,320,320,320,320,320,320, -320,320,320,320,320,320,320,320,320,320,320,320,320,114,114,114, - -/* block 39 */ -317,317,317,317,317,317,317,317,317,317,317,317,317,317,317,317, -321,321,321,321,321,321,321,321,321,321,114,114,114,114,114,114, -322,322,322,322,322,322,322,322,322,322,322,322,322,322,322,322, -322,322,322,322,322,322,322,322,322,322,322,322,322,322,322,322, -322,322,322,322,322,322,322,322,322,322,322,322,322,322,322,322, -322,322,322,322,322,322,322,322,322,322,322,322,322,322,322,322, -322,322,322,322,322,322,322,322,322,322,322,322,322,322,322,322, -322,322,322,322,322,114,114,114,114,114,114,114,114,114,114,114, - -/* block 40 */ -323,324,324,324,324,324,324,324,324,324,324,324,324,324,324,324, -324,324,324,324,324,324,324,324,324,324,324,324,324,324,324,324, -324,324,324,324,324,324,324,324,324,324,324,324,324,324,324,324, -324,324,324,324,324,324,324,324,324,324,324,324,324,324,324,324, -324,324,324,324,324,324,324,324,324,324,324,324,324,324,324,324, -324,324,324,324,324,324,324,324,324,324,324,324,324,324,324,324, -324,324,324,324,324,324,324,324,324,324,324,324,324,324,324,324, -324,324,324,324,324,324,324,324,324,324,324,324,324,324,324,324, - -/* block 41 */ -324,324,324,324,324,324,324,324,324,324,324,324,324,324,324,324, -324,324,324,324,324,324,324,324,324,324,324,324,324,324,324,324, -324,324,324,324,324,324,324,324,324,324,324,324,324,324,324,324, -324,324,324,324,324,324,324,324,324,324,324,324,324,324,324,324, -324,324,324,324,324,324,324,324,324,324,324,324,324,324,324,324, -324,324,324,324,324,324,324,324,324,324,324,324,324,324,324,324, -324,324,324,324,324,324,324,324,324,324,324,324,324,324,324,324, -324,324,324,324,324,324,324,324,324,324,324,324,324,324,324,324, - -/* block 42 */ -324,324,324,324,324,324,324,324,324,324,324,324,324,324,324,324, -324,324,324,324,324,324,324,324,324,324,324,324,324,324,324,324, -324,324,324,324,324,324,324,324,324,324,324,324,324,324,324,324, -324,324,324,324,324,324,324,324,324,324,324,324,324,324,324,324, -324,324,324,324,324,324,324,324,324,324,324,324,324,324,324,324, -324,324,324,324,324,324,324,324,324,324,324,324,324,324,324,324, -324,324,324,324,324,324,324,324,324,324,324,324,324,325,325,324, -324,324,324,324,324,324,324,324,324,324,324,324,324,324,324,324, - -/* block 43 */ -326,327,327,327,327,327,327,327,327,327,327,327,327,327,327,327, -327,327,327,327,327,327,327,327,327,327,327,328,329,114,114,114, -330,330,330,330,330,330,330,330,330,330,330,330,330,330,330,330, -330,330,330,330,330,330,330,330,330,330,330,330,330,330,330,330, -330,330,330,330,330,330,330,330,330,330,330,330,330,330,330,330, -330,330,330,330,330,330,330,330,330,330,330,330,330,330,330,330, -330,330,330,330,330,330,330,330,330,330,330, 4, 4, 4,331,331, -331,330,330,330,330,330,330,330,330,114,114,114,114,114,114,114, - -/* block 44 */ -332,332,332,332,332,332,332,332,332,332,332,332,332,114,332,332, -332,332,333,333,333,114,114,114,114,114,114,114,114,114,114,114, -334,334,334,334,334,334,334,334,334,334,334,334,334,334,334,334, -334,334,335,335,335, 4, 4,114,114,114,114,114,114,114,114,114, -336,336,336,336,336,336,336,336,336,336,336,336,336,336,336,336, -336,336,337,337,114,114,114,114,114,114,114,114,114,114,114,114, -338,338,338,338,338,338,338,338,338,338,338,338,338,114,338,338, -338,114,339,339,114,114,114,114,114,114,114,114,114,114,114,114, - -/* block 45 */ -340,340,340,340,340,340,340,340,340,340,340,340,340,340,340,340, -340,340,340,340,340,340,340,340,340,340,340,340,340,340,340,340, -340,340,340,340,340,340,340,340,340,340,340,340,340,340,340,340, -340,340,340,340,341,341,342,341,341,341,341,341,341,341,342,342, -342,342,342,342,342,342,341,342,342,341,341,341,341,341,341,341, -341,341,341,341,343,343,343,344,343,343,343,345,340,341,114,114, -346,346,346,346,346,346,346,346,346,346,114,114,114,114,114,114, -347,347,347,347,347,347,347,347,347,347,114,114,114,114,114,114, - -/* block 46 */ -348,348, 4, 4,348, 4,349,348,348,348,348,350,350,350,351,114, -352,352,352,352,352,352,352,352,352,352,114,114,114,114,114,114, -353,353,353,353,353,353,353,353,353,353,353,353,353,353,353,353, -353,353,353,353,353,353,353,353,353,353,353,353,353,353,353,353, -353,353,353,354,353,353,353,353,353,353,353,353,353,353,353,353, -353,353,353,353,353,353,353,353,353,353,353,353,353,353,353,353, -353,353,353,353,353,353,353,353,353,353,353,353,353,353,353,353, -353,353,353,353,353,353,353,353,114,114,114,114,114,114,114,114, - -/* block 47 */ -353,353,353,353,353,353,353,353,353,353,353,353,353,353,353,353, -353,353,353,353,353,353,353,353,353,353,353,353,353,353,353,353, -353,353,353,353,353,353,353,353,353,350,353,114,114,114,114,114, -324,324,324,324,324,324,324,324,324,324,324,324,324,324,324,324, -324,324,324,324,324,324,324,324,324,324,324,324,324,324,324,324, -324,324,324,324,324,324,324,324,324,324,324,324,324,324,324,324, -324,324,324,324,324,324,324,324,324,324,324,324,324,324,324,324, -324,324,324,324,324,324,114,114,114,114,114,114,114,114,114,114, - -/* block 48 */ -355,355,355,355,355,355,355,355,355,355,355,355,355,355,355,355, -355,355,355,355,355,355,355,355,355,355,355,355,355,355,355,114, -356,356,356,357,357,357,357,356,356,357,357,357,114,114,114,114, -357,357,356,357,357,357,357,357,357,356,356,356,114,114,114,114, -358,114,114,114,359,359,360,360,360,360,360,360,360,360,360,360, -361,361,361,361,361,361,361,361,361,361,361,361,361,361,361,361, -361,361,361,361,361,361,361,361,361,361,361,361,361,361,114,114, -361,361,361,361,361,114,114,114,114,114,114,114,114,114,114,114, - -/* block 49 */ -362,362,362,362,362,362,362,362,362,362,362,362,362,362,362,362, -362,362,362,362,362,362,362,362,362,362,362,362,362,362,362,362, -362,362,362,362,362,362,362,362,362,362,362,362,114,114,114,114, -363,363,363,363,363,364,364,364,363,363,364,363,363,363,363,363, -363,362,362,362,362,362,362,362,363,363,114,114,114,114,114,114, -365,365,365,365,365,365,365,365,365,365,366,114,114,114,367,367, -368,368,368,368,368,368,368,368,368,368,368,368,368,368,368,368, -368,368,368,368,368,368,368,368,368,368,368,368,368,368,368,368, - -/* block 50 */ -369,369,369,369,369,369,369,369,369,369,369,369,369,369,369,369, -369,369,369,369,369,369,369,370,370,371,371,370,114,114,372,372, -373,373,373,373,373,373,373,373,373,373,373,373,373,373,373,373, -373,373,373,373,373,373,373,373,373,373,373,373,373,373,373,373, -373,373,373,373,373,373,373,373,373,373,373,373,373,373,373,373, -373,373,373,373,373,374,375,374,375,375,375,375,375,375,375,114, -375,376,375,376,376,375,375,375,375,375,375,375,375,374,374,374, -374,374,374,375,375,375,375,375,375,375,375,375,375,114,114,375, - -/* block 51 */ -377,377,377,377,377,377,377,377,377,377,114,114,114,114,114,114, -377,377,377,377,377,377,377,377,377,377,114,114,114,114,114,114, -378,378,378,378,378,378,378,379,378,378,378,378,378,378,114,114, -109,109,109,109,109,109,109,109,109,109,109,109,109,109,380,114, -114,114,114,114,114,114,114,114,114,114,114,114,114,114,114,114, -114,114,114,114,114,114,114,114,114,114,114,114,114,114,114,114, -114,114,114,114,114,114,114,114,114,114,114,114,114,114,114,114, -114,114,114,114,114,114,114,114,114,114,114,114,114,114,114,114, - -/* block 52 */ -381,381,381,381,382,383,383,383,383,383,383,383,383,383,383,383, -383,383,383,383,383,383,383,383,383,383,383,383,383,383,383,383, -383,383,383,383,383,383,383,383,383,383,383,383,383,383,383,383, -383,383,383,383,381,382,381,381,381,381,381,382,381,382,382,382, -382,382,381,382,382,383,383,383,383,383,383,383,114,114,114,114, -384,384,384,384,384,384,384,384,384,384,385,385,385,385,385,385, -385,386,386,386,386,386,386,386,386,386,386,381,381,381,381,381, -381,381,381,381,386,386,386,386,386,386,386,386,386,114,114,114, - -/* block 53 */ -387,387,388,389,389,389,389,389,389,389,389,389,389,389,389,389, -389,389,389,389,389,389,389,389,389,389,389,389,389,389,389,389, -389,388,387,387,387,387,388,388,387,387,388,387,387,387,389,389, -390,390,390,390,390,390,390,390,390,390,389,389,389,389,389,389, -391,391,391,391,391,391,391,391,391,391,391,391,391,391,391,391, -391,391,391,391,391,391,391,391,391,391,391,391,391,391,391,391, -391,391,391,391,391,391,392,393,392,392,393,393,393,392,393,392, -392,392,393,393,114,114,114,114,114,114,114,114,394,394,394,394, - -/* block 54 */ -395,395,395,395,395,395,395,395,395,395,395,395,395,395,395,395, -395,395,395,395,395,395,395,395,395,395,395,395,395,395,395,395, -395,395,395,395,396,396,396,396,396,396,396,396,397,397,397,397, -397,397,397,397,396,396,397,397,114,114,114,398,398,398,398,398, -399,399,399,399,399,399,399,399,399,399,114,114,114,395,395,395, -400,400,400,400,400,400,400,400,400,400,401,401,401,401,401,401, -401,401,401,401,401,401,401,401,401,401,401,401,401,401,401,401, -401,401,401,401,401,401,401,401,402,402,402,402,402,402,403,403, - -/* block 55 */ -114,114,114,114,114,114,114,114,114,114,114,114,114,114,114,114, -114,114,114,114,114,114,114,114,114,114,114,114,114,114,114,114, -114,114,114,114,114,114,114,114,114,114,114,114,114,114,114,114, -114,114,114,114,114,114,114,114,114,114,114,114,114,114,114,114, -404,404,404,404,404,404,404,404,114,114,114,114,114,114,114,114, -109,109,109, 4,109,109,109,109,109,109,109,109,109,109,109,109, -109,405,109,109,109,109,109,109,109,406,406,406,406,109,406,406, -406,406,405,405,109,406,406,114,109,109,114,114,114,114,114,114, - -/* block 56 */ - 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, - 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, - 33, 33, 33, 33, 33, 33,122,122,122,122,122,407,106,106,106,106, -106,106,106,106,106,106,106,106,106,106,106,106,106,106,106,106, -106,106,106,106,106,106,106,106,106,106,106,106,106,106,106,106, -106,106,106,106,106,106,106,106,106,106,106,106,106,115,115,115, -115,115,106,106,106,106,115,115,115,115,115, 33, 33, 33, 33, 33, - 33, 33, 33, 33, 33, 33, 33, 33,408,409, 33, 33, 33,410, 33, 33, - -/* block 57 */ - 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, - 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,106,106,106,106,106, -106,106,106,106,106,106,106,106,106,106,106,106,106,106,106,106, -106,106,106,106,106,106,106,106,106,106,106,106,106,106,106,115, -109,109,109,109,109,109,109,109,109,109,109,109,109,109,109,109, -109,109,109,109,109,109,109,109,109,109,109,109,109,109,109,109, -109,109,109,109,109,109,109,109,109,109,109,109,109,109,109,109, -109,109,109,109,109,109,114,114,114,114,114,114,109,109,109,109, - -/* block 58 */ - 30, 31, 30, 31, 30, 31, 30, 31, 30, 31, 30, 31, 30, 31, 30, 31, - 30, 31, 30, 31, 30, 31, 30, 31, 30, 31, 30, 31, 30, 31, 30, 31, - 30, 31, 30, 31, 30, 31, 30, 31, 30, 31, 30, 31, 30, 31, 30, 31, - 30, 31, 30, 31, 30, 31, 30, 31, 30, 31, 30, 31, 30, 31, 30, 31, - 30, 31, 30, 31, 30, 31, 30, 31, 30, 31, 30, 31, 30, 31, 30, 31, - 30, 31, 30, 31, 30, 31, 30, 31, 30, 31, 30, 31, 30, 31, 30, 31, -411,412, 30, 31, 30, 31, 30, 31, 30, 31, 30, 31, 30, 31, 30, 31, - 30, 31, 30, 31, 30, 31, 30, 31, 30, 31, 30, 31, 30, 31, 30, 31, - -/* block 59 */ - 30, 31, 30, 31, 30, 31, 30, 31, 30, 31, 30, 31, 30, 31, 30, 31, - 30, 31, 30, 31, 30, 31, 33, 33, 33, 33, 33,413, 33, 33,414, 33, - 30, 31, 30, 31, 30, 31, 30, 31, 30, 31, 30, 31, 30, 31, 30, 31, - 30, 31, 30, 31, 30, 31, 30, 31, 30, 31, 30, 31, 30, 31, 30, 31, - 30, 31, 30, 31, 30, 31, 30, 31, 30, 31, 30, 31, 30, 31, 30, 31, - 30, 31, 30, 31, 30, 31, 30, 31, 30, 31, 30, 31, 30, 31, 30, 31, - 30, 31, 30, 31, 30, 31, 30, 31, 30, 31, 30, 31, 30, 31, 30, 31, - 30, 31, 30, 31, 30, 31, 30, 31, 30, 31, 30, 31, 30, 31, 30, 31, - -/* block 60 */ -415,415,415,415,415,415,415,415,416,416,416,416,416,416,416,416, -415,415,415,415,415,415,114,114,416,416,416,416,416,416,114,114, -415,415,415,415,415,415,415,415,416,416,416,416,416,416,416,416, -415,415,415,415,415,415,415,415,416,416,416,416,416,416,416,416, -415,415,415,415,415,415,114,114,416,416,416,416,416,416,114,114, -122,415,122,415,122,415,122,415,114,416,114,416,114,416,114,416, -415,415,415,415,415,415,415,415,416,416,416,416,416,416,416,416, -417,417,418,418,418,418,419,419,420,420,421,421,422,422,114,114, - -/* block 61 */ -415,415,415,415,415,415,415,415,423,423,423,423,423,423,423,423, -415,415,415,415,415,415,415,415,423,423,423,423,423,423,423,423, -415,415,415,415,415,415,415,415,423,423,423,423,423,423,423,423, -415,415,122,424,122,114,122,122,416,416,425,425,426,113,427,113, -113,113,122,424,122,114,122,122,428,428,428,428,426,113,113,113, -415,415,122,122,114,114,122,122,416,416,429,429,114,113,113,113, -415,415,122,122,122,163,122,122,416,416,430,430,168,113,113,113, -114,114,122,424,122,114,122,122,431,431,432,432,426,113,113,114, - -/* block 62 */ - 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 22,433,433, 22, 22, - 9, 9, 9, 9, 9, 9, 4, 4, 21, 25, 6, 21, 21, 25, 6, 21, - 4, 4, 4, 4, 4, 4, 4, 4,434,435, 22, 22, 22, 22, 22, 3, - 4, 4, 4, 4, 4, 4, 4, 4, 4, 21, 25, 4, 4, 4, 4, 15, - 15, 4, 4, 4, 8, 6, 7, 4, 4, 4, 4, 4, 4, 4, 4, 4, - 4, 4, 8, 4, 15, 4, 4, 4, 4, 4, 4, 4, 4, 4, 4, 3, - 22, 22, 22, 22, 22,436, 22, 22, 22, 22, 22, 22, 22, 22, 22, 22, - 23,106,114,114, 23, 23, 23, 23, 23, 23, 8, 8, 8, 6, 7,106, - -/* block 63 */ - 23, 23, 23, 23, 23, 23, 23, 23, 23, 23, 8, 8, 8, 6, 7,114, -106,106,106,106,106,106,106,106,106,106,106,106,106,114,114,114, - 5, 5, 5, 5, 5, 5, 5, 5, 5, 5, 5, 5, 5, 5, 5, 5, - 5, 5, 5, 5, 5, 5, 5, 5, 5, 5, 5, 5, 5, 5,114,114, -114,114,114,114,114,114,114,114,114,114,114,114,114,114,114,114, -109,109,109,109,109,109,109,109,109,109,109,109,109,380,380,380, -380,109,380,380,380,109,109,109,109,109,109,109,109,109,109,109, -109,114,114,114,114,114,114,114,114,114,114,114,114,114,114,114, - -/* block 64 */ - 19, 19,437, 19, 19, 19, 19,437, 19, 19,438,437,437,437,438,438, -437,437,437,438, 19,437, 19, 19, 8,437,437,437,437,437, 19, 19, - 19, 19, 19, 19,437, 19,439, 19,437, 19,440,441,437,437, 19,438, -437,437,442,437,438,406,406,406,406,438, 19, 19,438,438,437,437, - 8, 8, 8, 8, 8,437,438,438,438,438, 19, 8, 19, 19,443, 19, - 23, 23, 23, 23, 23, 23, 23, 23, 23, 23, 23, 23, 23, 23, 23, 23, -444,444,444,444,444,444,444,444,444,444,444,444,444,444,444,444, -445,445,445,445,445,445,445,445,445,445,445,445,445,445,445,445, - -/* block 65 */ -446,446,446, 30, 31,446,446,446,446, 23,114,114,114,114,114,114, - 8, 8, 8, 8, 8, 19, 19, 19, 19, 19, 8, 8, 19, 19, 19, 19, - 8, 19, 19, 8, 19, 19, 8, 19, 19, 19, 19, 19, 19, 19, 8, 19, - 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, - 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 8, 8, - 19, 19, 8, 19, 8, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, - 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, - 19, 19, 19, 19, 8, 8, 8, 8, 8, 8, 8, 8, 8, 8, 8, 8, - -/* block 66 */ - 8, 8, 8, 8, 8, 8, 8, 8, 8, 8, 8, 8, 8, 8, 8, 8, - 8, 8, 8, 8, 8, 8, 8, 8, 8, 8, 8, 8, 8, 8, 8, 8, - 8, 8, 8, 8, 8, 8, 8, 8, 8, 8, 8, 8, 8, 8, 8, 8, - 8, 8, 8, 8, 8, 8, 8, 8, 8, 8, 8, 8, 8, 8, 8, 8, - 8, 8, 8, 8, 8, 8, 8, 8, 8, 8, 8, 8, 8, 8, 8, 8, - 8, 8, 8, 8, 8, 8, 8, 8, 8, 8, 8, 8, 8, 8, 8, 8, - 8, 8, 8, 8, 8, 8, 8, 8, 8, 8, 8, 8, 8, 8, 8, 8, - 8, 8, 8, 8, 8, 8, 8, 8, 8, 8, 8, 8, 8, 8, 8, 8, - -/* block 67 */ - 19, 19, 19, 19, 19, 19, 19, 19, 6, 7, 6, 7, 19, 19, 19, 19, - 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, - 8, 8, 19, 19, 19, 19, 19, 19, 19, 6, 7, 19, 19, 19, 19, 19, - 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, - 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, - 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, - 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, - 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 8, 19, 19, 19, - -/* block 68 */ - 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, - 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 8, 8, 8, 8, 8, - 8, 8, 8, 8, 8, 8, 8, 8, 8, 8, 8, 8, 8, 8, 8, 8, - 8, 8, 8, 8, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, - 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, - 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 8, 8, 8, 8, - 8, 8, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, - 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19,114,114,114,114,114, - -/* block 69 */ - 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, - 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, - 19, 19, 19, 19, 19, 19, 19,114,114,114,114,114,114,114,114,114, -114,114,114,114,114,114,114,114,114,114,114,114,114,114,114,114, - 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19,114,114,114,114,114, -114,114,114,114,114,114,114,114,114,114,114,114,114,114,114,114, - 23, 23, 23, 23, 23, 23, 23, 23, 23, 23, 23, 23, 23, 23, 23, 23, - 23, 23, 23, 23, 23, 23, 23, 23, 23, 23, 23, 23, 23, 23, 23, 23, - -/* block 70 */ - 23, 23, 23, 23, 23, 23, 23, 23, 23, 23, 23, 23, 23, 23, 23, 23, - 23, 23, 23, 23, 23, 23, 23, 23, 23, 23, 23, 23, 19, 19, 19, 19, - 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, - 19, 19, 19, 19, 19, 19,447,447,447,447,447,447,447,447,447,447, -447,447,447,447,447,447,447,447,447,447,447,447,447,447,447,447, -448,448,448,448,448,448,448,448,448,448,448,448,448,448,448,448, -448,448,448,448,448,448,448,448,448,448, 23, 23, 23, 23, 23, 23, - 23, 23, 23, 23, 23, 23, 23, 23, 23, 23, 23, 23, 23, 23, 23, 23, - -/* block 71 */ - 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, - 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, - 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, - 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, - 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, - 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, - 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, - 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, - -/* block 72 */ - 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, - 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, - 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, - 19, 19, 19, 19, 19, 19, 19, 8, 19, 19, 19, 19, 19, 19, 19, 19, - 19, 8, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, - 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, - 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, - 19, 19, 19, 19, 19, 19, 19, 19, 8, 8, 8, 8, 8, 8, 8, 8, - -/* block 73 */ - 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, - 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, - 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, - 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, - 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, - 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, - 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 8, - 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, - -/* block 74 */ - 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, - 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, - 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, - 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, - 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, - 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, - 19, 19, 19, 19, 19, 19, 19, 19, 6, 7, 6, 7, 6, 7, 6, 7, - 6, 7, 6, 7, 6, 7, 23, 23, 23, 23, 23, 23, 23, 23, 23, 23, - -/* block 75 */ - 23, 23, 23, 23, 23, 23, 23, 23, 23, 23, 23, 23, 23, 23, 23, 23, - 23, 23, 23, 23, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, - 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, - 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, - 8, 8, 8, 8, 8, 6, 7, 8, 8, 8, 8, 8, 8, 8, 8, 8, - 8, 8, 8, 8, 8, 8, 8, 8, 8, 8, 8, 8, 8, 8, 8, 8, - 8, 8, 8, 8, 8, 8, 6, 7, 6, 7, 6, 7, 6, 7, 6, 7, - 8, 8, 8, 8, 8, 8, 8, 8, 8, 8, 8, 8, 8, 8, 8, 8, - -/* block 76 */ -449,449,449,449,449,449,449,449,449,449,449,449,449,449,449,449, -449,449,449,449,449,449,449,449,449,449,449,449,449,449,449,449, -449,449,449,449,449,449,449,449,449,449,449,449,449,449,449,449, -449,449,449,449,449,449,449,449,449,449,449,449,449,449,449,449, -449,449,449,449,449,449,449,449,449,449,449,449,449,449,449,449, -449,449,449,449,449,449,449,449,449,449,449,449,449,449,449,449, -449,449,449,449,449,449,449,449,449,449,449,449,449,449,449,449, -449,449,449,449,449,449,449,449,449,449,449,449,449,449,449,449, - -/* block 77 */ - 8, 8, 8, 6, 7, 6, 7, 6, 7, 6, 7, 6, 7, 6, 7, 6, - 7, 6, 7, 6, 7, 6, 7, 6, 7, 8, 8, 8, 8, 8, 8, 8, - 8, 8, 8, 8, 8, 8, 8, 8, 8, 8, 8, 8, 8, 8, 8, 8, - 8, 8, 8, 8, 8, 8, 8, 8, 8, 8, 8, 8, 8, 8, 8, 8, - 8, 8, 8, 8, 8, 8, 8, 8, 8, 8, 8, 8, 8, 8, 8, 8, - 8, 8, 8, 8, 8, 8, 8, 8, 6, 7, 6, 7, 8, 8, 8, 8, - 8, 8, 8, 8, 8, 8, 8, 8, 8, 8, 8, 8, 8, 8, 8, 8, - 8, 8, 8, 8, 8, 8, 8, 8, 8, 8, 8, 8, 6, 7, 8, 8, - -/* block 78 */ - 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, - 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, - 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, - 8, 8, 8, 8, 8, 8, 8, 8, 8, 8, 8, 8, 8, 8, 8, 8, - 8, 8, 8, 8, 8, 19, 19, 8, 8, 8, 8, 8, 8, 19, 19, 19, - 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, - 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, - 19, 19, 19, 19,114,114, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, - -/* block 79 */ - 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, - 19, 19, 19, 19, 19, 19,114,114, 19, 19, 19, 19, 19, 19, 19, 19, - 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, - 19, 19, 19, 19, 19, 19, 19, 19, 19, 19,114,114,114, 19, 19, 19, - 19, 19, 19, 19, 19, 19, 19, 19, 19,114, 19, 19, 19, 19, 19, 19, - 19, 19,114,114,114,114,114,114,114,114,114,114,114,114,114,114, -114,114,114,114,114,114,114,114,114,114,114,114,114,114,114,114, -114,114,114,114,114,114,114,114,114,114,114,114,114,114,114,114, - -/* block 80 */ -450,450,450,450,450,450,450,450,450,450,450,450,450,450,450,450, -450,450,450,450,450,450,450,450,450,450,450,450,450,450,450,450, -450,450,450,450,450,450,450,450,450,450,450,450,450,450,450,114, -451,451,451,451,451,451,451,451,451,451,451,451,451,451,451,451, -451,451,451,451,451,451,451,451,451,451,451,451,451,451,451,451, -451,451,451,451,451,451,451,451,451,451,451,451,451,451,451,114, - 30, 31,452,453,454,455,456, 30, 31, 30, 31, 30, 31,457,458,459, -460, 33, 30, 31, 33, 30, 31, 33, 33, 33, 33, 33,106,106,461,461, - -/* block 81 */ -159,160,159,160,159,160,159,160,159,160,159,160,159,160,159,160, -159,160,159,160,159,160,159,160,159,160,159,160,159,160,159,160, -159,160,159,160,159,160,159,160,159,160,159,160,159,160,159,160, -159,160,159,160,159,160,159,160,159,160,159,160,159,160,159,160, -159,160,159,160,159,160,159,160,159,160,159,160,159,160,159,160, -159,160,159,160,159,160,159,160,159,160,159,160,159,160,159,160, -159,160,159,160,462,463,463,463,463,463,463,159,160,159,160,464, -464,464,159,160,114,114,114,114,114,465,465,465,465,466,465,465, - -/* block 82 */ -467,467,467,467,467,467,467,467,467,467,467,467,467,467,467,467, -467,467,467,467,467,467,467,467,467,467,467,467,467,467,467,467, -467,467,467,467,467,467,114,467,114,114,114,114,114,467,114,114, -468,468,468,468,468,468,468,468,468,468,468,468,468,468,468,468, -468,468,468,468,468,468,468,468,468,468,468,468,468,468,468,468, -468,468,468,468,468,468,468,468,468,468,468,468,468,468,468,468, -468,468,468,468,468,468,468,468,114,114,114,114,114,114,114,469, -470,114,114,114,114,114,114,114,114,114,114,114,114,114,114,471, - -/* block 83 */ -317,317,317,317,317,317,317,317,317,317,317,317,317,317,317,317, -317,317,317,317,317,317,317,114,114,114,114,114,114,114,114,114, -317,317,317,317,317,317,317,114,317,317,317,317,317,317,317,114, -317,317,317,317,317,317,317,114,317,317,317,317,317,317,317,114, -317,317,317,317,317,317,317,114,317,317,317,317,317,317,317,114, -317,317,317,317,317,317,317,114,317,317,317,317,317,317,317,114, -177,177,177,177,177,177,177,177,177,177,177,177,177,177,177,177, -177,177,177,177,177,177,177,177,177,177,177,177,177,177,177,177, - -/* block 84 */ - 4, 4, 21, 25, 21, 25, 4, 4, 4, 21, 25, 4, 21, 25, 4, 4, - 4, 4, 4, 4, 4, 4, 4, 9, 4, 4, 9, 4, 21, 25, 4, 4, - 21, 25, 6, 7, 6, 7, 6, 7, 6, 7, 4, 4, 4, 4, 4,107, - 4, 4, 4, 4, 4, 4, 4, 4, 4, 4, 9, 9, 4, 4, 4, 4, - 9, 4, 6,114,114,114,114,114,114,114,114,114,114,114,114,114, -114,114,114,114,114,114,114,114,114,114,114,114,114,114,114,114, -114,114,114,114,114,114,114,114,114,114,114,114,114,114,114,114, -114,114,114,114,114,114,114,114,114,114,114,114,114,114,114,114, - -/* block 85 */ -472,472,472,472,472,472,472,472,472,472,472,472,472,472,472,472, -472,472,472,472,472,472,472,472,472,472,114,472,472,472,472,472, -472,472,472,472,472,472,472,472,472,472,472,472,472,472,472,472, -472,472,472,472,472,472,472,472,472,472,472,472,472,472,472,472, -472,472,472,472,472,472,472,472,472,472,472,472,472,472,472,472, -472,472,472,472,472,472,472,472,472,472,472,472,472,472,472,472, -472,472,472,472,472,472,472,472,472,472,472,472,472,472,472,472, -472,472,472,472,114,114,114,114,114,114,114,114,114,114,114,114, - -/* block 86 */ -472,472,472,472,472,472,472,472,472,472,472,472,472,472,472,472, -472,472,472,472,472,472,472,472,472,472,472,472,472,472,472,472, -472,472,472,472,472,472,472,472,472,472,472,472,472,472,472,472, -472,472,472,472,472,472,472,472,472,472,472,472,472,472,472,472, -472,472,472,472,472,472,472,472,472,472,472,472,472,472,472,472, -472,472,472,472,472,472,472,472,472,472,472,472,472,472,472,472, -472,472,472,472,472,472,472,472,472,472,472,472,472,472,472,472, -472,472,472,472,472,472,472,472,472,472,472,472,472,472,472,472, - -/* block 87 */ -472,472,472,472,472,472,472,472,472,472,472,472,472,472,472,472, -472,472,472,472,472,472,472,472,472,472,472,472,472,472,472,472, -472,472,472,472,472,472,472,472,472,472,472,472,472,472,472,472, -472,472,472,472,472,472,472,472,472,472,472,472,472,472,472,472, -472,472,472,472,472,472,472,472,472,472,472,472,472,472,472,472, -472,472,472,472,472,472,114,114,114,114,114,114,114,114,114,114, -114,114,114,114,114,114,114,114,114,114,114,114,114,114,114,114, - 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19,114,114,114,114, - -/* block 88 */ - 3, 4, 4, 4, 19,473,406,474, 6, 7, 6, 7, 6, 7, 6, 7, - 6, 7, 19, 19, 6, 7, 6, 7, 6, 7, 6, 7, 9, 6, 7, 7, - 19,474,474,474,474,474,474,474,474,474,109,109,109,109,475,475, - 9,107,107,107,107,107, 19, 19,474,474,474,473,406, 4, 19, 19, -114,476,476,476,476,476,476,476,476,476,476,476,476,476,476,476, -476,476,476,476,476,476,476,476,476,476,476,476,476,476,476,476, -476,476,476,476,476,476,476,476,476,476,476,476,476,476,476,476, -476,476,476,476,476,476,476,476,476,476,476,476,476,476,476,476, - -/* block 89 */ -476,476,476,476,476,476,476,476,476,476,476,476,476,476,476,476, -476,476,476,476,476,476,476,114,114,109,109, 14, 14,477,477,476, - 9,478,478,478,478,478,478,478,478,478,478,478,478,478,478,478, -478,478,478,478,478,478,478,478,478,478,478,478,478,478,478,478, -478,478,478,478,478,478,478,478,478,478,478,478,478,478,478,478, -478,478,478,478,478,478,478,478,478,478,478,478,478,478,478,478, -478,478,478,478,478,478,478,478,478,478,478,478,478,478,478,478, -478,478,478,478,478,478,478,478,478,478,478, 4,107,479,479,478, - -/* block 90 */ -114,114,114,114,114,480,480,480,480,480,480,480,480,480,480,480, -480,480,480,480,480,480,480,480,480,480,480,480,480,480,480,480, -480,480,480,480,480,480,480,480,480,480,480,480,480,480,114,114, -114,481,481,481,481,481,481,481,481,481,481,481,481,481,481,481, -481,481,481,481,481,481,481,481,481,481,481,481,481,481,481,481, -481,481,481,481,481,481,481,481,481,481,481,481,481,481,481,481, -481,481,481,481,481,481,481,481,481,481,481,481,481,481,481,481, -481,481,481,481,481,481,481,481,481,481,481,481,481,481,481,481, - -/* block 91 */ -481,481,481,481,481,481,481,481,481,481,481,481,481,481,481,114, - 19, 19, 23, 23, 23, 23, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, -480,480,480,480,480,480,480,480,480,480,480,480,480,480,480,480, -480,480,480,480,480,480,480,480,480,480,480,114,114,114,114,114, - 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, - 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, - 19, 19, 19, 19,114,114,114,114,114,114,114,114,114,114,114,114, -478,478,478,478,478,478,478,478,478,478,478,478,478,478,478,478, - -/* block 92 */ -482,482,482,482,482,482,482,482,482,482,482,482,482,482,482,482, -482,482,482,482,482,482,482,482,482,482,482,482,482,482,482,114, - 23, 23, 23, 23, 23, 23, 23, 23, 23, 23, 19, 19, 19, 19, 19, 19, - 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, - 19, 19, 19, 19, 19, 19, 19, 19, 23, 23, 23, 23, 23, 23, 23, 23, - 19, 23, 23, 23, 23, 23, 23, 23, 23, 23, 23, 23, 23, 23, 23, 23, -482,482,482,482,482,482,482,482,482,482,482,482,482,482,482,482, -482,482,482,482,482,482,482,482,482,482,482,482,482,482,482, 19, - -/* block 93 */ - 23, 23, 23, 23, 23, 23, 23, 23, 23, 23, 19, 19, 19, 19, 19, 19, - 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, - 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, - 19, 23, 23, 23, 23, 23, 23, 23, 23, 23, 23, 23, 23, 23, 23, 23, - 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, -483,483,483,483,483,483,483,483,483,483,483,483,483,483,483,483, -483,483,483,483,483,483,483,483,483,483,483,483,483,483,483,483, -483,483,483,483,483,483,483,483,483,483,483,483,483,483,483,114, - -/* block 94 */ -483,483,483,483,483,483,483,483,483,483,483,483,483,483,483,483, -483,483,483,483,483,483,483,483,483,483,483,483,483,483,483,483, -483,483,483,483,483,483,483,483,483,483,483,483,483,483,483,483, -483,483,483,483,483,483,483,483,483,483,483,483,483,483,483,483, -483,483,483,483,483,483,483,483,483,483,483,483,483,483,483,483, -483,483,483,483,483,483,483,483, 19, 19, 19, 19, 19, 19, 19, 19, - 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, - 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, - -/* block 95 */ -484,484,484,484,484,484,484,484,484,484,484,484,484,484,484,484, -484,484,484,484,484,484,484,484,484,484,484,484,484,484,484,484, -484,484,484,484,484,484,484,484,484,484,484,484,484,484,484,484, -484,484,484,484,484,484,484,484,484,484,484,484,484,484,484,484, -484,484,484,484,484,484,484,484,484,484,484,484,484,484,484,484, -484,484,484,484,484,484,484,484,484,484,484,484,484,484,484,484, -484,484,484,484,484,484,484,484,484,484,484,484,484,484,484,484, -484,484,484,484,484,484,484,484,484,484,484,484,484,484,484,484, - -/* block 96 */ -484,484,484,484,484,484,484,484,484,484,484,484,484,484,484,484, -484,484,484,484,484,484,484,484,484,484,484,484,484,484,484,484, -484,484,484,484,484,484,484,484,484,484,484,484,484,484,484,484, -484,484,484,484,484,484,114,114,114,114,114,114,114,114,114,114, - 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, - 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, - 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, - 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, - -/* block 97 */ -484,484,484,484,484,484,484,484,484,484,484,484,484,484,484,484, -484,484,484,484,484,484,484,484,484,484,484,484,484,484,484,484, -484,484,484,484,484,484,484,484,484,484,484,484,484,484,484,484, -484,484,484,484,484,484,484,484,484,484,484,484,484,484,484,484, -484,484,484,484,484,484,484,484,484,484,484,484,484,114,114,114, -114,114,114,114,114,114,114,114,114,114,114,114,114,114,114,114, -114,114,114,114,114,114,114,114,114,114,114,114,114,114,114,114, -114,114,114,114,114,114,114,114,114,114,114,114,114,114,114,114, - -/* block 98 */ -485,485,485,485,485,485,485,485,485,485,485,485,485,485,485,485, -485,485,485,485,485,486,485,485,485,485,485,485,485,485,485,485, -485,485,485,485,485,485,485,485,485,485,485,485,485,485,485,485, -485,485,485,485,485,485,485,485,485,485,485,485,485,485,485,485, -485,485,485,485,485,485,485,485,485,485,485,485,485,485,485,485, -485,485,485,485,485,485,485,485,485,485,485,485,485,485,485,485, -485,485,485,485,485,485,485,485,485,485,485,485,485,485,485,485, -485,485,485,485,485,485,485,485,485,485,485,485,485,485,485,485, - -/* block 99 */ -485,485,485,485,485,485,485,485,485,485,485,485,485,485,485,485, -485,485,485,485,485,485,485,485,485,485,485,485,485,485,485,485, -485,485,485,485,485,485,485,485,485,485,485,485,485,485,485,485, -485,485,485,485,485,485,485,485,485,485,485,485,485,485,485,485, -485,485,485,485,485,485,485,485,485,485,485,485,485,485,485,485, -485,485,485,485,485,485,485,485,485,485,485,485,485,485,485,485, -485,485,485,485,485,485,485,485,485,485,485,485,485,485,485,485, -485,485,485,485,485,485,485,485,485,485,485,485,485,485,485,485, - -/* block 100 */ -485,485,485,485,485,485,485,485,485,485,485,485,485,114,114,114, -487,487,487,487,487,487,487,487,487,487,487,487,487,487,487,487, -487,487,487,487,487,487,487,487,487,487,487,487,487,487,487,487, -487,487,487,487,487,487,487,487,487,487,487,487,487,487,487,487, -487,487,487,487,487,487,487,114,114,114,114,114,114,114,114,114, -488,488,488,488,488,488,488,488,488,488,488,488,488,488,488,488, -488,488,488,488,488,488,488,488,488,488,488,488,488,488,488,488, -488,488,488,488,488,488,488,488,489,489,489,489,489,489,490,490, - -/* block 101 */ -491,491,491,491,491,491,491,491,491,491,491,491,491,491,491,491, -491,491,491,491,491,491,491,491,491,491,491,491,491,491,491,491, -491,491,491,491,491,491,491,491,491,491,491,491,491,491,491,491, -491,491,491,491,491,491,491,491,491,491,491,491,491,491,491,491, -491,491,491,491,491,491,491,491,491,491,491,491,491,491,491,491, -491,491,491,491,491,491,491,491,491,491,491,491,491,491,491,491, -491,491,491,491,491,491,491,491,491,491,491,491,491,491,491,491, -491,491,491,491,491,491,491,491,491,491,491,491,491,491,491,491, - -/* block 102 */ -491,491,491,491,491,491,491,491,491,491,491,491,492,493,493,493, -491,491,491,491,491,491,491,491,491,491,491,491,491,491,491,491, -494,494,494,494,494,494,494,494,494,494,491,491,114,114,114,114, -114,114,114,114,114,114,114,114,114,114,114,114,114,114,114,114, -174,175,174,175,174,175,174,175,174,175,174,175,174,175,174,175, -174,175,174,175,174,175,174,175,174,175,174,175,174,175,174,175, -174,175,174,175,174,175,174,175,174,175,174,175,174,175,495,177, -178,178,178,496,177,177,177,177,177,177,177,177,177,177,496,408, - -/* block 103 */ -174,175,174,175,174,175,174,175,174,175,174,175,174,175,174,175, -174,175,174,175,174,175,174,175,174,175,174,175,408,408,114,177, -497,497,497,497,497,497,497,497,497,497,497,497,497,497,497,497, -497,497,497,497,497,497,497,497,497,497,497,497,497,497,497,497, -497,497,497,497,497,497,497,497,497,497,497,497,497,497,497,497, -497,497,497,497,497,497,497,497,497,497,497,497,497,497,497,497, -497,497,497,497,497,497,498,498,498,498,498,498,498,498,498,498, -499,499,500,500,500,500,500,500,114,114,114,114,114,114,114,114, - -/* block 104 */ - 14, 14, 14, 14, 14, 14, 14, 14, 14, 14, 14, 14, 14, 14, 14, 14, - 14, 14, 14, 14, 14, 14, 14,107,107,107,107,107,107,107,107,107, - 14, 14, 30, 31, 30, 31, 30, 31, 30, 31, 30, 31, 30, 31, 30, 31, - 33, 33, 30, 31, 30, 31, 30, 31, 30, 31, 30, 31, 30, 31, 30, 31, - 30, 31, 30, 31, 30, 31, 30, 31, 30, 31, 30, 31, 30, 31, 30, 31, - 30, 31, 30, 31, 30, 31, 30, 31, 30, 31, 30, 31, 30, 31, 30, 31, - 30, 31, 30, 31, 30, 31, 30, 31, 30, 31, 30, 31, 30, 31, 30, 31, -106, 33, 33, 33, 33, 33, 33, 33, 33, 30, 31, 30, 31,501, 30, 31, - -/* block 105 */ - 30, 31, 30, 31, 30, 31, 30, 31,107, 14, 14, 30, 31,502, 33,114, - 30, 31, 30, 31, 33, 33, 30, 31, 30, 31, 30, 31, 30, 31, 30, 31, - 30, 31, 30, 31, 30, 31, 30, 31, 30, 31,503,504,505,506,114,114, -507,508,114,114,114,114,114,114,114,114,114,114,114,114,114,114, -114,114,114,114,114,114,114,114,114,114,114,114,114,114,114,114, -114,114,114,114,114,114,114,114,114,114,114,114,114,114,114,114, -114,114,114,114,114,114,114,114,114,114,114,114,114,114,114,114, -114,114,114,114,114,114,114, 20,106,106, 33, 20, 20, 20, 20, 20, - -/* block 106 */ -509,509,510,509,509,509,510,509,509,509,509,510,509,509,509,509, -509,509,509,509,509,509,509,509,509,509,509,509,509,509,509,509, -509,509,509,511,511,510,510,511,512,512,512,512,114,114,114,114, - 23, 23, 23, 23, 23, 23, 19, 19, 5, 19,114,114,114,114,114,114, -513,513,513,513,513,513,513,513,513,513,513,513,513,513,513,513, -513,513,513,513,513,513,513,513,513,513,513,513,513,513,513,513, -513,513,513,513,513,513,513,513,513,513,513,513,513,513,513,513, -513,513,513,513,514,514,514,514,114,114,114,114,114,114,114,114, - -/* block 107 */ -515,515,516,516,516,516,516,516,516,516,516,516,516,516,516,516, -516,516,516,516,516,516,516,516,516,516,516,516,516,516,516,516, -516,516,516,516,516,516,516,516,516,516,516,516,516,516,516,516, -516,516,516,516,515,515,515,515,515,515,515,515,515,515,515,515, -515,515,515,515,517,114,114,114,114,114,114,114,114,114,518,518, -519,519,519,519,519,519,519,519,519,519,114,114,114,114,114,114, -221,221,221,221,221,221,221,221,221,221,221,221,221,221,221,221, -221,221,223,223,223,223,223,223,225,225,225,223,114,114,114,114, - -/* block 108 */ -520,520,520,520,520,520,520,520,520,520,521,521,521,521,521,521, -521,521,521,521,521,521,521,521,521,521,521,521,521,521,521,521, -521,521,521,521,521,521,522,522,522,522,522,522,522,522, 4,523, -524,524,524,524,524,524,524,524,524,524,524,524,524,524,524,524, -524,524,524,524,524,524,524,525,525,525,525,525,525,525,525,525, -525,525,526,526,114,114,114,114,114,114,114,114,114,114,114,527, -314,314,314,314,314,314,314,314,314,314,314,314,314,314,314,314, -314,314,314,314,314,314,314,314,314,314,314,314,314,114,114,114, - -/* block 109 */ -528,528,528,529,530,530,530,530,530,530,530,530,530,530,530,530, -530,530,530,530,530,530,530,530,530,530,530,530,530,530,530,530, -530,530,530,530,530,530,530,530,530,530,530,530,530,530,530,530, -530,530,530,528,529,529,528,528,528,528,529,529,528,529,529,529, -529,531,531,531,531,531,531,531,531,531,531,531,531,531,114,107, -532,532,532,532,532,532,532,532,532,532,114,114,114,114,531,531, -304,304,304,304,304,306,533,304,304,304,304,304,304,304,304,304, -308,308,308,308,308,308,308,308,308,308,304,304,304,304,304,114, - -/* block 110 */ -534,534,534,534,534,534,534,534,534,534,534,534,534,534,534,534, -534,534,534,534,534,534,534,534,534,534,534,534,534,534,534,534, -534,534,534,534,534,534,534,534,534,535,535,535,535,535,535,536, -536,535,535,536,536,535,535,114,114,114,114,114,114,114,114,114, -534,534,534,535,534,534,534,534,534,534,534,534,535,536,114,114, -537,537,537,537,537,537,537,537,537,537,114,114,538,538,538,538, -304,304,304,304,304,304,304,304,304,304,304,304,304,304,304,304, -533,304,304,304,304,304,304,310,310,310,304,305,306,305,304,304, - -/* block 111 */ -539,539,539,539,539,539,539,539,539,539,539,539,539,539,539,539, -539,539,539,539,539,539,539,539,539,539,539,539,539,539,539,539, -539,539,539,539,539,539,539,539,539,539,539,539,539,539,539,539, -540,539,540,540,540,539,539,540,540,539,539,539,539,539,540,540, -539,540,539,114,114,114,114,114,114,114,114,114,114,114,114,114, -114,114,114,114,114,114,114,114,114,114,114,539,539,541,542,542, -543,543,543,543,543,543,543,543,543,543,543,544,545,545,544,544, -546,546,543,547,547,544,545,114,114,114,114,114,114,114,114,114, - -/* block 112 */ -114,317,317,317,317,317,317,114,114,317,317,317,317,317,317,114, -114,317,317,317,317,317,317,114,114,114,114,114,114,114,114,114, -317,317,317,317,317,317,317,114,317,317,317,317,317,317,317,114, - 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, - 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, - 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 14,106,106,106,106, -114,114,114,114, 33,122,114,114,114,114,114,114,114,114,114,114, -114,114,114,114,114,114,114,114,114,114,114,114,114,114,114,114, - -/* block 113 */ -114,114,114,114,114,114,114,114,114,114,114,114,114,114,114,114, -114,114,114,114,114,114,114,114,114,114,114,114,114,114,114,114, -114,114,114,114,114,114,114,114,114,114,114,114,114,114,114,114, -114,114,114,114,114,114,114,114,114,114,114,114,114,114,114,114, -543,543,543,543,543,543,543,543,543,543,543,543,543,543,543,543, -543,543,543,543,543,543,543,543,543,543,543,543,543,543,543,543, -543,543,543,544,544,545,544,544,545,544,544,546,544,545,114,114, -548,548,548,548,548,548,548,548,548,548,114,114,114,114,114,114, - -/* block 114 */ -549,550,550,550,550,550,550,550,550,550,550,550,550,550,550,550, -550,550,550,550,550,550,550,550,550,550,550,550,549,550,550,550, -550,550,550,550,550,550,550,550,550,550,550,550,550,550,550,550, -550,550,550,550,550,550,550,550,549,550,550,550,550,550,550,550, -550,550,550,550,550,550,550,550,550,550,550,550,550,550,550,550, -550,550,550,550,549,550,550,550,550,550,550,550,550,550,550,550, -550,550,550,550,550,550,550,550,550,550,550,550,550,550,550,550, -549,550,550,550,550,550,550,550,550,550,550,550,550,550,550,550, - -/* block 115 */ -550,550,550,550,550,550,550,550,550,550,550,550,549,550,550,550, -550,550,550,550,550,550,550,550,550,550,550,550,550,550,550,550, -550,550,550,550,550,550,550,550,549,550,550,550,550,550,550,550, -550,550,550,550,550,550,550,550,550,550,550,550,550,550,550,550, -550,550,550,550,549,550,550,550,550,550,550,550,550,550,550,550, -550,550,550,550,550,550,550,550,550,550,550,550,550,550,550,550, -549,550,550,550,550,550,550,550,550,550,550,550,550,550,550,550, -550,550,550,550,550,550,550,550,550,550,550,550,549,550,550,550, - -/* block 116 */ -550,550,550,550,550,550,550,550,550,550,550,550,550,550,550,550, -550,550,550,550,550,550,550,550,549,550,550,550,550,550,550,550, -550,550,550,550,550,550,550,550,550,550,550,550,550,550,550,550, -550,550,550,550,549,550,550,550,550,550,550,550,550,550,550,550, -550,550,550,550,550,550,550,550,550,550,550,550,550,550,550,550, -549,550,550,550,550,550,550,550,550,550,550,550,550,550,550,550, -550,550,550,550,550,550,550,550,550,550,550,550,549,550,550,550, -550,550,550,550,550,550,550,550,550,550,550,550,550,550,550,550, - -/* block 117 */ -550,550,550,550,550,550,550,550,549,550,550,550,550,550,550,550, -550,550,550,550,550,550,550,550,550,550,550,550,550,550,550,550, -550,550,550,550,549,550,550,550,550,550,550,550,550,550,550,550, -550,550,550,550,550,550,550,550,550,550,550,550,550,550,550,550, -549,550,550,550,550,550,550,550,550,550,550,550,550,550,550,550, -550,550,550,550,550,550,550,550,550,550,550,550,549,550,550,550, -550,550,550,550,550,550,550,550,550,550,550,550,550,550,550,550, -550,550,550,550,550,550,550,550,549,550,550,550,550,550,550,550, - -/* block 118 */ -550,550,550,550,550,550,550,550,550,550,550,550,550,550,550,550, -550,550,550,550,549,550,550,550,550,550,550,550,550,550,550,550, -550,550,550,550,550,550,550,550,550,550,550,550,550,550,550,550, -549,550,550,550,550,550,550,550,550,550,550,550,550,550,550,550, -550,550,550,550,550,550,550,550,550,550,550,550,549,550,550,550, -550,550,550,550,550,550,550,550,550,550,550,550,550,550,550,550, -550,550,550,550,550,550,550,550,549,550,550,550,550,550,550,550, -550,550,550,550,550,550,550,550,550,550,550,550,550,550,550,550, - -/* block 119 */ -550,550,550,550,549,550,550,550,550,550,550,550,550,550,550,550, -550,550,550,550,550,550,550,550,550,550,550,550,550,550,550,550, -549,550,550,550,550,550,550,550,550,550,550,550,550,550,550,550, -550,550,550,550,550,550,550,550,550,550,550,550,549,550,550,550, -550,550,550,550,550,550,550,550,550,550,550,550,550,550,550,550, -550,550,550,550,550,550,550,550,549,550,550,550,550,550,550,550, -550,550,550,550,550,550,550,550,550,550,550,550,550,550,550,550, -550,550,550,550,549,550,550,550,550,550,550,550,550,550,550,550, - -/* block 120 */ -550,550,550,550,550,550,550,550,550,550,550,550,550,550,550,550, -549,550,550,550,550,550,550,550,550,550,550,550,550,550,550,550, -550,550,550,550,550,550,550,550,550,550,550,550,549,550,550,550, -550,550,550,550,550,550,550,550,550,550,550,550,550,550,550,550, -550,550,550,550,550,550,550,550,549,550,550,550,550,550,550,550, -550,550,550,550,550,550,550,550,550,550,550,550,550,550,550,550, -550,550,550,550,549,550,550,550,550,550,550,550,550,550,550,550, -550,550,550,550,550,550,550,550,550,550,550,550,550,550,550,550, - -/* block 121 */ -550,550,550,550,550,550,550,550,549,550,550,550,550,550,550,550, -550,550,550,550,550,550,550,550,550,550,550,550,550,550,550,550, -550,550,550,550,114,114,114,114,114,114,114,114,114,114,114,114, -315,315,315,315,315,315,315,315,315,315,315,315,315,315,315,315, -315,315,315,315,315,315,315,114,114,114,114,316,316,316,316,316, -316,316,316,316,316,316,316,316,316,316,316,316,316,316,316,316, -316,316,316,316,316,316,316,316,316,316,316,316,316,316,316,316, -316,316,316,316,316,316,316,316,316,316,316,316,114,114,114,114, - -/* block 122 */ -551,551,551,551,551,551,551,551,551,551,551,551,551,551,551,551, -551,551,551,551,551,551,551,551,551,551,551,551,551,551,551,551, -551,551,551,551,551,551,551,551,551,551,551,551,551,551,551,551, -551,551,551,551,551,551,551,551,551,551,551,551,551,551,551,551, -551,551,551,551,551,551,551,551,551,551,551,551,551,551,551,551, -551,551,551,551,551,551,551,551,551,551,551,551,551,551,551,551, -551,551,551,551,551,551,551,551,551,551,551,551,551,551,551,551, -551,551,551,551,551,551,551,551,551,551,551,551,551,551,551,551, - -/* block 123 */ -552,552,552,552,552,552,552,552,552,552,552,552,552,552,552,552, -552,552,552,552,552,552,552,552,552,552,552,552,552,552,552,552, -552,552,552,552,552,552,552,552,552,552,552,552,552,552,552,552, -552,552,552,552,552,552,552,552,552,552,552,552,552,552,552,552, -552,552,552,552,552,552,552,552,552,552,552,552,552,552,552,552, -552,552,552,552,552,552,552,552,552,552,552,552,552,552,552,552, -552,552,552,552,552,552,552,552,552,552,552,552,552,552,552,552, -552,552,552,552,552,552,552,552,552,552,552,552,552,552,552,552, - -/* block 124 */ -484,484,484,484,484,484,484,484,484,484,484,484,484,484,484,484, -484,484,484,484,484,484,484,484,484,484,484,484,484,484,484,484, -484,484,484,484,484,484,484,484,484,484,484,484,484,484,484,484, -484,484,484,484,484,484,484,484,484,484,484,484,484,484,484,484, -484,484,484,484,484,484,484,484,484,484,484,484,484,484,484,484, -484,484,484,484,484,484,484,484,484,484,484,484,484,484,484,484, -484,484,484,484,484,484,484,484,484,484,484,484,484,484,114,114, -484,484,484,484,484,484,484,484,484,484,484,484,484,484,484,484, - -/* block 125 */ -484,484,484,484,484,484,484,484,484,484,484,484,484,484,484,484, -484,484,484,484,484,484,484,484,484,484,484,484,484,484,484,484, -484,484,484,484,484,484,484,484,484,484,484,484,484,484,484,484, -484,484,484,484,484,484,484,484,484,484,484,484,484,484,484,484, -484,484,484,484,484,484,484,484,484,484,484,484,484,484,484,484, -484,484,484,484,484,484,484,484,484,484,114,114,114,114,114,114, -114,114,114,114,114,114,114,114,114,114,114,114,114,114,114,114, -114,114,114,114,114,114,114,114,114,114,114,114,114,114,114,114, - -/* block 126 */ - 33, 33, 33, 33, 33, 33, 33,114,114,114,114,114,114,114,114,114, -114,114,114,185,185,185,185,185,114,114,114,114,114,192,189,192, -192,192,192,192,192,192,192,192,192,553,192,192,192,192,192,192, -192,192,192,192,192,192,192,114,192,192,192,192,192,114,192,114, -192,192,114,192,192,114,192,192,192,192,192,192,192,192,192,192, -199,199,199,199,199,199,199,199,199,199,199,199,199,199,199,199, -199,199,199,199,199,199,199,199,199,199,199,199,199,199,199,199, -199,199,199,199,199,199,199,199,199,199,199,199,199,199,199,199, - -/* block 127 */ -199,199,199,199,199,199,199,199,199,199,199,199,199,199,199,199, -199,199,199,199,199,199,199,199,199,199,199,199,199,199,199,199, -199,199,199,199,199,199,199,199,199,199,199,199,199,199,199,199, -199,199,554,554,554,554,554,554,554,554,554,554,554,554,554,554, -554,554,114,114,114,114,114,114,114,114,114,114,114,114,114,114, -114,114,114,199,199,199,199,199,199,199,199,199,199,199,199,199, -199,199,199,199,199,199,199,199,199,199,199,199,199,199,199,199, -199,199,199,199,199,199,199,199,199,199,199,199,199,199,199,199, - -/* block 128 */ -199,199,199,199,199,199,199,199,199,199,199,199,199,199,199,199, -199,199,199,199,199,199,199,199,199,199,199,199,199,199,199,199, -199,199,199,199,199,199,199,199,199,199,199,199,199,199,199,199, -199,199,199,199,199,199,199,199,199,199,199,199,199,199,199,199, -199,199,199,199,199,199,199,199,199,199,199,199,199,199,199,199, -199,199,199,199,199,199,199,199,199,199,199,199,199,199,199,199, -199,199,199,199,199,199,199,199,199,199,199,199,199,199,199,199, -199,199,199,199,199,199,199,199,199,199,199,199,199,199,199,199, - -/* block 129 */ -199,199,199,199,199,199,199,199,199,199,199,199,199,199,199,199, -199,199,199,199,199,199,199,199,199,199,199,199,199,199,199,199, -199,199,199,199,199,199,199,199,199,199,199,199,199,199,199,199, -199,199,199,199,199,199,199,199,199,199,199,199,199,199, 7, 6, -114,114,114,114,114,114,114,114,114,114,114,114,114,114,114,114, -199,199,199,199,199,199,199,199,199,199,199,199,199,199,199,199, -199,199,199,199,199,199,199,199,199,199,199,199,199,199,199,199, -199,199,199,199,199,199,199,199,199,199,199,199,199,199,199,199, - -/* block 130 */ -199,199,199,199,199,199,199,199,199,199,199,199,199,199,199,199, -114,114,199,199,199,199,199,199,199,199,199,199,199,199,199,199, -199,199,199,199,199,199,199,199,199,199,199,199,199,199,199,199, -199,199,199,199,199,199,199,199,199,199,199,199,199,199,199,199, -199,199,199,199,199,199,199,199,114,114,114,114,114,114,114,114, -114,114,114,114,114,114,114,114,114,114,114,114,114,114,114,114, -114,114,114,114,114,114,114,114,114,114,114,114,114,114,114,114, -199,199,199,199,199,199,199,199,199,199,199,199,196,197,114,114, - -/* block 131 */ -109,109,109,109,109,109,109,109,109,109,109,109,109,109,109,109, - 4, 4, 4, 4, 4, 4, 4, 6, 7, 4,114,114,114,114,114,114, -109,109,109,109,109,109,109,109,109,109,109,109,109,109,114,114, - 4, 9, 9, 15, 15, 6, 7, 6, 7, 6, 7, 6, 7, 6, 7, 6, - 7, 6, 7, 6, 7, 4, 4, 6, 7, 4, 4, 4, 4, 15, 15, 15, - 4, 4, 4,114, 4, 4, 4, 4, 9, 6, 7, 6, 7, 6, 7, 4, - 4, 4, 8, 9, 8, 8, 8,114, 4, 5, 4, 4,114,114,114,114, -199,199,199,199,199,114,199,199,199,199,199,199,199,199,199,199, - -/* block 132 */ -199,199,199,199,199,199,199,199,199,199,199,199,199,199,199,199, -199,199,199,199,199,199,199,199,199,199,199,199,199,199,199,199, -199,199,199,199,199,199,199,199,199,199,199,199,199,199,199,199, -199,199,199,199,199,199,199,199,199,199,199,199,199,199,199,199, -199,199,199,199,199,199,199,199,199,199,199,199,199,199,199,199, -199,199,199,199,199,199,199,199,199,199,199,199,199,199,199,199, -199,199,199,199,199,199,199,199,199,199,199,199,199,199,199,199, -199,199,199,199,199,199,199,199,199,199,199,199,199,114,114, 22, - -/* block 133 */ -114, 4, 4, 4, 5, 4, 4, 4, 6, 7, 4, 8, 4, 9, 4, 4, - 10, 10, 10, 10, 10, 10, 10, 10, 10, 10, 4, 4, 8, 8, 8, 4, - 4, 11, 11, 11, 11, 11, 11, 11, 11, 11, 11, 11, 11, 11, 11, 11, - 11, 11, 11, 11, 11, 11, 11, 11, 11, 11, 11, 6, 4, 7, 14, 15, - 14, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, - 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 6, 8, 7, 8, 6, - 7, 4, 6, 7, 4, 4,478,478,478,478,478,478,478,478,478,478, -107,478,478,478,478,478,478,478,478,478,478,478,478,478,478,478, - -/* block 134 */ -478,478,478,478,478,478,478,478,478,478,478,478,478,478,478,478, -478,478,478,478,478,478,478,478,478,478,478,478,478,478,555,555, -481,481,481,481,481,481,481,481,481,481,481,481,481,481,481,481, -481,481,481,481,481,481,481,481,481,481,481,481,481,481,481,114, -114,114,481,481,481,481,481,481,114,114,481,481,481,481,481,481, -114,114,481,481,481,481,481,481,114,114,481,481,481,114,114,114, - 5, 5, 8, 14, 19, 5, 5,114, 19, 8, 8, 8, 8, 19, 19,114, -436,436,436,436,436,436,436,436,436, 22, 22, 22, 19, 19,114,114, - -/* block 135 */ -556,556,556,556,556,556,556,556,556,556,556,556,114,556,556,556, -556,556,556,556,556,556,556,556,556,556,556,556,556,556,556,556, -556,556,556,556,556,556,556,114,556,556,556,556,556,556,556,556, -556,556,556,556,556,556,556,556,556,556,556,114,556,556,114,556, -556,556,556,556,556,556,556,556,556,556,556,556,556,556,114,114, -556,556,556,556,556,556,556,556,556,556,556,556,556,556,114,114, -114,114,114,114,114,114,114,114,114,114,114,114,114,114,114,114, -114,114,114,114,114,114,114,114,114,114,114,114,114,114,114,114, - -/* block 136 */ -556,556,556,556,556,556,556,556,556,556,556,556,556,556,556,556, -556,556,556,556,556,556,556,556,556,556,556,556,556,556,556,556, -556,556,556,556,556,556,556,556,556,556,556,556,556,556,556,556, -556,556,556,556,556,556,556,556,556,556,556,556,556,556,556,556, -556,556,556,556,556,556,556,556,556,556,556,556,556,556,556,556, -556,556,556,556,556,556,556,556,556,556,556,556,556,556,556,556, -556,556,556,556,556,556,556,556,556,556,556,556,556,556,556,556, -556,556,556,556,556,556,556,556,556,556,556,114,114,114,114,114, - -/* block 137 */ - 4, 4, 4,114,114,114,114, 23, 23, 23, 23, 23, 23, 23, 23, 23, - 23, 23, 23, 23, 23, 23, 23, 23, 23, 23, 23, 23, 23, 23, 23, 23, - 23, 23, 23, 23, 23, 23, 23, 23, 23, 23, 23, 23, 23, 23, 23, 23, - 23, 23, 23, 23,114,114,114, 19, 19, 19, 19, 19, 19, 19, 19, 19, -557,557,557,557,557,557,557,557,557,557,557,557,557,557,557,557, -557,557,557,557,557,557,557,557,557,557,557,557,557,557,557,557, -557,557,557,557,557,557,557,557,557,557,557,557,557,557,557,557, -557,557,557,557,557,558,558,558,558,559,559,559,559,559,559,559, - -/* block 138 */ -559,559,559,559,559,559,559,559,559,559,558,558,559,114,114,114, - 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19,114,114,114,114, -559,114,114,114,114,114,114,114,114,114,114,114,114,114,114,114, -114,114,114,114,114,114,114,114,114,114,114,114,114,114,114,114, -114,114,114,114,114,114,114,114,114,114,114,114,114,114,114,114, - 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, - 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, - 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19,109,114,114, - -/* block 139 */ -114,114,114,114,114,114,114,114,114,114,114,114,114,114,114,114, -114,114,114,114,114,114,114,114,114,114,114,114,114,114,114,114, -114,114,114,114,114,114,114,114,114,114,114,114,114,114,114,114, -114,114,114,114,114,114,114,114,114,114,114,114,114,114,114,114, -114,114,114,114,114,114,114,114,114,114,114,114,114,114,114,114, -114,114,114,114,114,114,114,114,114,114,114,114,114,114,114,114, -114,114,114,114,114,114,114,114,114,114,114,114,114,114,114,114, -114,114,114,114,114,114,114,114,114,114,114,114,114,114,114,114, - -/* block 140 */ -560,560,560,560,560,560,560,560,560,560,560,560,560,560,560,560, -560,560,560,560,560,560,560,560,560,560,560,560,560,114,114,114, -561,561,561,561,561,561,561,561,561,561,561,561,561,561,561,561, -561,561,561,561,561,561,561,561,561,561,561,561,561,561,561,561, -561,561,561,561,561,561,561,561,561,561,561,561,561,561,561,561, -561,114,114,114,114,114,114,114,114,114,114,114,114,114,114,114, -109, 23, 23, 23, 23, 23, 23, 23, 23, 23, 23, 23, 23, 23, 23, 23, - 23, 23, 23, 23, 23, 23, 23, 23, 23, 23, 23, 23,114,114,114,114, - -/* block 141 */ -562,562,562,562,562,562,562,562,562,562,562,562,562,562,562,562, -562,562,562,562,562,562,562,562,562,562,562,562,562,562,562,562, -563,563,563,563,114,114,114,114,114,114,114,114,114,114,114,114, -564,564,564,564,564,564,564,564,564,564,564,564,564,564,564,564, -564,565,564,564,564,564,564,564,564,564,565,114,114,114,114,114, -566,566,566,566,566,566,566,566,566,566,566,566,566,566,566,566, -566,566,566,566,566,566,566,566,566,566,566,566,566,566,566,566, -566,566,566,566,566,566,567,567,567,567,567,114,114,114,114,114, - -/* block 142 */ -568,568,568,568,568,568,568,568,568,568,568,568,568,568,568,568, -568,568,568,568,568,568,568,568,568,568,568,568,568,568,114,569, -570,570,570,570,570,570,570,570,570,570,570,570,570,570,570,570, -570,570,570,570,570,570,570,570,570,570,570,570,570,570,570,570, -570,570,570,570,114,114,114,114,570,570,570,570,570,570,570,570, -571,572,572,572,572,572,114,114,114,114,114,114,114,114,114,114, -114,114,114,114,114,114,114,114,114,114,114,114,114,114,114,114, -114,114,114,114,114,114,114,114,114,114,114,114,114,114,114,114, - -/* block 143 */ -573,573,573,573,573,573,573,573,573,573,573,573,573,573,573,573, -573,573,573,573,573,573,573,573,573,573,573,573,573,573,573,573, -573,573,573,573,573,573,573,573,574,574,574,574,574,574,574,574, -574,574,574,574,574,574,574,574,574,574,574,574,574,574,574,574, -574,574,574,574,574,574,574,574,574,574,574,574,574,574,574,574, -575,575,575,575,575,575,575,575,575,575,575,575,575,575,575,575, -575,575,575,575,575,575,575,575,575,575,575,575,575,575,575,575, -575,575,575,575,575,575,575,575,575,575,575,575,575,575,575,575, - -/* block 144 */ -576,576,576,576,576,576,576,576,576,576,576,576,576,576,576,576, -576,576,576,576,576,576,576,576,576,576,576,576,576,576,114,114, -577,577,577,577,577,577,577,577,577,577,114,114,114,114,114,114, -114,114,114,114,114,114,114,114,114,114,114,114,114,114,114,114, -114,114,114,114,114,114,114,114,114,114,114,114,114,114,114,114, -114,114,114,114,114,114,114,114,114,114,114,114,114,114,114,114, -114,114,114,114,114,114,114,114,114,114,114,114,114,114,114,114, -114,114,114,114,114,114,114,114,114,114,114,114,114,114,114,114, - -/* block 145 */ -578,578,578,578,578,578,578,578,578,578,578,578,578,578,578,578, -578,578,578,578,578,578,578,578,578,578,578,578,578,578,578,578, -578,578,578,578,578,578,578,578,114,114,114,114,114,114,114,114, -579,579,579,579,579,579,579,579,579,579,579,579,579,579,579,579, -579,579,579,579,579,579,579,579,579,579,579,579,579,579,579,579, -579,579,579,579,579,579,579,579,579,579,579,579,579,579,579,579, -579,579,579,579,114,114,114,114,114,114,114,114,114,114,114,580, -114,114,114,114,114,114,114,114,114,114,114,114,114,114,114,114, - -/* block 146 */ -581,581,581,581,581,581,581,581,581,581,581,581,581,581,581,581, -581,581,581,581,581,581,581,581,581,581,581,581,581,581,581,581, -581,581,581,581,581,581,581,581,581,581,581,581,581,581,581,581, -581,581,581,581,581,581,581,581,581,581,581,581,581,581,581,581, -581,581,581,581,581,581,581,581,581,581,581,581,581,581,581,581, -581,581,581,581,581,581,581,581,581,581,581,581,581,581,581,581, -581,581,581,581,581,581,581,581,581,581,581,581,581,581,581,581, -581,581,581,581,581,581,581,581,581,581,581,581,581,581,581,581, - -/* block 147 */ -581,581,581,581,581,581,581,581,581,581,581,581,581,581,581,581, -581,581,581,581,581,581,581,581,581,581,581,581,581,581,581,581, -581,581,581,581,581,581,581,581,581,581,581,581,581,581,581,581, -581,581,581,581,581,581,581,114,114,114,114,114,114,114,114,114, -581,581,581,581,581,581,581,581,581,581,581,581,581,581,581,581, -581,581,581,581,581,581,114,114,114,114,114,114,114,114,114,114, -581,581,581,581,581,581,581,581,114,114,114,114,114,114,114,114, -114,114,114,114,114,114,114,114,114,114,114,114,114,114,114,114, - -/* block 148 */ -582,582,582,582,582,582,114,114,582,114,582,582,582,582,582,582, -582,582,582,582,582,582,582,582,582,582,582,582,582,582,582,582, -582,582,582,582,582,582,582,582,582,582,582,582,582,582,582,582, -582,582,582,582,582,582,114,582,582,114,114,114,582,114,114,582, -583,583,583,583,583,583,583,583,583,583,583,583,583,583,583,583, -583,583,583,583,583,583,114,584,585,585,585,585,585,585,585,585, -586,586,586,586,586,586,586,586,586,586,586,586,586,586,586,586, -586,586,586,586,586,586,586,587,587,588,588,588,588,588,588,588, - -/* block 149 */ -589,589,589,589,589,589,589,589,589,589,589,589,589,589,589,589, -589,589,589,589,589,589,589,589,589,589,589,589,589,589,589,114, -114,114,114,114,114,114,114,590,590,590,590,590,590,590,590,590, -114,114,114,114,114,114,114,114,114,114,114,114,114,114,114,114, -114,114,114,114,114,114,114,114,114,114,114,114,114,114,114,114, -114,114,114,114,114,114,114,114,114,114,114,114,114,114,114,114, -114,114,114,114,114,114,114,114,114,114,114,114,114,114,114,114, -114,114,114,114,114,114,114,114,114,114,114,114,114,114,114,114, - -/* block 150 */ -591,591,591,591,591,591,591,591,591,591,591,591,591,591,591,591, -591,591,591,591,591,591,592,592,592,592,592,592,114,114,114,593, -594,594,594,594,594,594,594,594,594,594,594,594,594,594,594,594, -594,594,594,594,594,594,594,594,594,594,114,114,114,114,114,595, -114,114,114,114,114,114,114,114,114,114,114,114,114,114,114,114, -114,114,114,114,114,114,114,114,114,114,114,114,114,114,114,114, -114,114,114,114,114,114,114,114,114,114,114,114,114,114,114,114, -114,114,114,114,114,114,114,114,114,114,114,114,114,114,114,114, - -/* block 151 */ -596,596,596,596,596,596,596,596,596,596,596,596,596,596,596,596, -596,596,596,596,596,596,596,596,596,596,596,596,596,596,596,596, -597,597,597,597,597,597,597,597,597,597,597,597,597,597,597,597, -597,597,597,597,597,597,597,597,114,114,114,114,114,114,597,597, -114,114,114,114,114,114,114,114,114,114,114,114,114,114,114,114, -114,114,114,114,114,114,114,114,114,114,114,114,114,114,114,114, -114,114,114,114,114,114,114,114,114,114,114,114,114,114,114,114, -114,114,114,114,114,114,114,114,114,114,114,114,114,114,114,114, - -/* block 152 */ -598,599,599,599,114,599,599,114,114,114,114,114,599,599,599,599, -598,598,598,598,114,598,598,598,114,598,598,598,598,598,598,598, -598,598,598,598,598,598,598,598,598,598,598,598,598,598,598,598, -598,598,598,598,114,114,114,114,599,599,599,114,114,114,114,599, -600,600,600,600,600,600,600,600,114,114,114,114,114,114,114,114, -601,601,601,601,601,601,601,601,601,114,114,114,114,114,114,114, -602,602,602,602,602,602,602,602,602,602,602,602,602,602,602,602, -602,602,602,602,602,602,602,602,602,602,602,602,602,603,603,604, - -/* block 153 */ -605,605,605,605,605,605,605,605,605,605,605,605,605,605,605,605, -605,605,605,605,605,605,605,605,605,605,605,605,605,606,606,606, -114,114,114,114,114,114,114,114,114,114,114,114,114,114,114,114, -114,114,114,114,114,114,114,114,114,114,114,114,114,114,114,114, -607,607,607,607,607,607,607,607,608,607,607,607,607,607,607,607, -607,607,607,607,607,607,607,607,607,607,607,607,607,607,607,607, -607,607,607,607,607,609,609,114,114,114,114,610,610,610,610,610, -611,611,611,611,611,611,611,114,114,114,114,114,114,114,114,114, - -/* block 154 */ -612,612,612,612,612,612,612,612,612,612,612,612,612,612,612,612, -612,612,612,612,612,612,612,612,612,612,612,612,612,612,612,612, -612,612,612,612,612,612,612,612,612,612,612,612,612,612,612,612, -612,612,612,612,612,612,114,114,114,613,613,613,613,613,613,613, -614,614,614,614,614,614,614,614,614,614,614,614,614,614,614,614, -614,614,614,614,614,614,114,114,615,615,615,615,615,615,615,615, -616,616,616,616,616,616,616,616,616,616,616,616,616,616,616,616, -616,616,616,114,114,114,114,114,617,617,617,617,617,617,617,617, - -/* block 155 */ -618,618,618,618,618,618,618,618,618,618,618,618,618,618,618,618, -618,618,114,114,114,114,114,114,114,619,619,619,619,114,114,114, -114,114,114,114,114,114,114,114,114,620,620,620,620,620,620,620, -114,114,114,114,114,114,114,114,114,114,114,114,114,114,114,114, -114,114,114,114,114,114,114,114,114,114,114,114,114,114,114,114, -114,114,114,114,114,114,114,114,114,114,114,114,114,114,114,114, -114,114,114,114,114,114,114,114,114,114,114,114,114,114,114,114, -114,114,114,114,114,114,114,114,114,114,114,114,114,114,114,114, - -/* block 156 */ -621,621,621,621,621,621,621,621,621,621,621,621,621,621,621,621, -621,621,621,621,621,621,621,621,621,621,621,621,621,621,621,621, -621,621,621,621,621,621,621,621,621,621,621,621,621,621,621,621, -621,621,621,621,621,621,621,621,621,621,621,621,621,621,621,621, -621,621,621,621,621,621,621,621,621,114,114,114,114,114,114,114, -114,114,114,114,114,114,114,114,114,114,114,114,114,114,114,114, -114,114,114,114,114,114,114,114,114,114,114,114,114,114,114,114, -114,114,114,114,114,114,114,114,114,114,114,114,114,114,114,114, - -/* block 157 */ -114,114,114,114,114,114,114,114,114,114,114,114,114,114,114,114, -114,114,114,114,114,114,114,114,114,114,114,114,114,114,114,114, -114,114,114,114,114,114,114,114,114,114,114,114,114,114,114,114, -114,114,114,114,114,114,114,114,114,114,114,114,114,114,114,114, -114,114,114,114,114,114,114,114,114,114,114,114,114,114,114,114, -114,114,114,114,114,114,114,114,114,114,114,114,114,114,114,114, -622,622,622,622,622,622,622,622,622,622,622,622,622,622,622,622, -622,622,622,622,622,622,622,622,622,622,622,622,622,622,622,114, - -/* block 158 */ -623,624,623,625,625,625,625,625,625,625,625,625,625,625,625,625, -625,625,625,625,625,625,625,625,625,625,625,625,625,625,625,625, -625,625,625,625,625,625,625,625,625,625,625,625,625,625,625,625, -625,625,625,625,625,625,625,625,624,624,624,624,624,624,624,624, -624,624,624,624,624,624,624,626,626,626,626,626,626,626,114,114, -114,114,627,627,627,627,627,627,627,627,627,627,627,627,627,627, -627,627,627,627,627,627,628,628,628,628,628,628,628,628,628,628, -114,114,114,114,114,114,114,114,114,114,114,114,114,114,114,624, - -/* block 159 */ -629,629,630,631,631,631,631,631,631,631,631,631,631,631,631,631, -631,631,631,631,631,631,631,631,631,631,631,631,631,631,631,631, -631,631,631,631,631,631,631,631,631,631,631,631,631,631,631,631, -630,630,630,629,629,629,629,630,630,629,629,632,632,633,632,632, -632,632,114,114,114,114,114,114,114,114,114,114,114,114,114,114, -634,634,634,634,634,634,634,634,634,634,634,634,634,634,634,634, -634,634,634,634,634,634,634,634,634,114,114,114,114,114,114,114, -635,635,635,635,635,635,635,635,635,635,114,114,114,114,114,114, - -/* block 160 */ -636,636,636,637,637,637,637,637,637,637,637,637,637,637,637,637, -637,637,637,637,637,637,637,637,637,637,637,637,637,637,637,637, -637,637,637,637,637,637,637,636,636,636,636,636,638,636,636,636, -636,636,636,636,636,114,639,639,639,639,639,639,639,639,639,639, -640,640,640,640,114,114,114,114,114,114,114,114,114,114,114,114, -641,641,641,641,641,641,641,641,641,641,641,641,641,641,641,641, -641,641,641,641,641,641,641,641,641,641,641,641,641,641,641,641, -641,641,641,642,643,643,641,114,114,114,114,114,114,114,114,114, - -/* block 161 */ -644,644,645,646,646,646,646,646,646,646,646,646,646,646,646,646, -646,646,646,646,646,646,646,646,646,646,646,646,646,646,646,646, -646,646,646,646,646,646,646,646,646,646,646,646,646,646,646,646, -646,646,646,645,645,645,644,644,644,644,644,644,644,644,644,645, -645,646,646,646,646,647,647,647,647,114,114,114,114,647,114,114, -648,648,648,648,648,648,648,648,648,648,646,114,114,114,114,114, -114,649,649,649,649,649,649,649,649,649,649,649,649,649,649,649, -649,649,649,649,649,114,114,114,114,114,114,114,114,114,114,114, - -/* block 162 */ -650,650,650,650,650,650,650,650,650,650,650,650,650,650,650,650, -650,650,114,650,650,650,650,650,650,650,650,650,650,650,650,650, -650,650,650,650,650,650,650,650,650,650,650,650,651,651,651,652, -652,652,651,651,652,651,652,652,653,653,653,653,653,653,114,114, -114,114,114,114,114,114,114,114,114,114,114,114,114,114,114,114, -114,114,114,114,114,114,114,114,114,114,114,114,114,114,114,114, -114,114,114,114,114,114,114,114,114,114,114,114,114,114,114,114, -114,114,114,114,114,114,114,114,114,114,114,114,114,114,114,114, - -/* block 163 */ -114,114,114,114,114,114,114,114,114,114,114,114,114,114,114,114, -114,114,114,114,114,114,114,114,114,114,114,114,114,114,114,114, -114,114,114,114,114,114,114,114,114,114,114,114,114,114,114,114, -654,654,654,654,654,654,654,654,654,654,654,654,654,654,654,654, -654,654,654,654,654,654,654,654,654,654,654,654,654,654,654,654, -654,654,654,654,654,654,654,654,654,654,654,654,654,654,654,655, -656,656,656,655,655,655,655,655,655,655,655,114,114,114,114,114, -657,657,657,657,657,657,657,657,657,657,114,114,114,114,114,114, - -/* block 164 */ -114,658,659,659,114,660,660,660,660,660,660,660,660,114,114,660, -660,114,114,660,660,660,660,660,660,660,660,660,660,660,660,660, -660,660,660,660,660,660,660,660,660,114,660,660,660,660,660,660, -660,114,660,660,114,660,660,660,660,660,114,114,658,660,661,659, -658,659,659,659,659,114,114,659,659,114,114,659,659,659,114,114, -114,114,114,114,114,114,114,661,114,114,114,114,114,660,660,660, -660,660,659,659,114,114,658,658,658,658,658,658,658,114,114,114, -658,658,658,658,658,114,114,114,114,114,114,114,114,114,114,114, - -/* block 165 */ -662,662,662,662,662,662,662,662,662,662,662,662,662,662,662,662, -662,662,662,662,662,662,662,662,662,662,662,662,662,662,662,662, -662,662,662,662,662,662,662,662,662,662,662,662,662,662,662,662, -663,664,664,665,665,665,665,665,665,664,665,664,664,663,664,665, -665,664,665,665,662,662,666,662,114,114,114,114,114,114,114,114, -667,667,667,667,667,667,667,667,667,667,114,114,114,114,114,114, -114,114,114,114,114,114,114,114,114,114,114,114,114,114,114,114, -114,114,114,114,114,114,114,114,114,114,114,114,114,114,114,114, - -/* block 166 */ -668,668,668,668,668,668,668,668,668,668,668,668,668,668,668,668, -668,668,668,668,668,668,668,668,668,668,668,668,668,668,668,668, -668,668,668,668,668,668,668,668,668,668,668,668,668,668,668,669, -670,670,671,671,671,671,114,114,670,670,670,670,671,671,670,671, -671,672,672,672,672,672,672,672,672,672,114,114,114,114,114,114, -114,114,114,114,114,114,114,114,114,114,114,114,114,114,114,114, -114,114,114,114,114,114,114,114,114,114,114,114,114,114,114,114, -114,114,114,114,114,114,114,114,114,114,114,114,114,114,114,114, - -/* block 167 */ -673,673,673,673,673,673,673,673,673,673,673,673,673,673,673,673, -673,673,673,673,673,673,673,673,673,673,673,673,673,673,673,673, -673,673,673,673,673,673,673,673,673,673,673,673,673,673,673,673, -674,674,674,675,675,675,675,675,675,675,675,674,674,675,674,675, -675,676,676,676,673,114,114,114,114,114,114,114,114,114,114,114, -677,677,677,677,677,677,677,677,677,677,114,114,114,114,114,114, -114,114,114,114,114,114,114,114,114,114,114,114,114,114,114,114, -114,114,114,114,114,114,114,114,114,114,114,114,114,114,114,114, - -/* block 168 */ -678,678,678,678,678,678,678,678,678,678,678,678,678,678,678,678, -678,678,678,678,678,678,678,678,678,678,678,678,678,678,678,678, -678,678,678,678,678,678,678,678,678,678,678,679,680,679,680,680, -679,679,679,679,679,679,680,679,114,114,114,114,114,114,114,114, -681,681,681,681,681,681,681,681,681,681,114,114,114,114,114,114, -114,114,114,114,114,114,114,114,114,114,114,114,114,114,114,114, -114,114,114,114,114,114,114,114,114,114,114,114,114,114,114,114, -114,114,114,114,114,114,114,114,114,114,114,114,114,114,114,114, - -/* block 169 */ -114,114,114,114,114,114,114,114,114,114,114,114,114,114,114,114, -114,114,114,114,114,114,114,114,114,114,114,114,114,114,114,114, -682,682,682,682,682,682,682,682,682,682,682,682,682,682,682,682, -682,682,682,682,682,682,682,682,682,682,682,682,682,682,682,682, -683,683,683,683,683,683,683,683,683,683,683,683,683,683,683,683, -683,683,683,683,683,683,683,683,683,683,683,683,683,683,683,683, -684,684,684,684,684,684,684,684,684,684,685,685,685,685,685,685, -685,685,685,114,114,114,114,114,114,114,114,114,114,114,114,686, - -/* block 170 */ -114,114,114,114,114,114,114,114,114,114,114,114,114,114,114,114, -114,114,114,114,114,114,114,114,114,114,114,114,114,114,114,114, -114,114,114,114,114,114,114,114,114,114,114,114,114,114,114,114, -114,114,114,114,114,114,114,114,114,114,114,114,114,114,114,114, -687,687,687,687,687,687,687,687,687,687,687,687,687,687,687,687, -687,687,687,687,687,687,687,687,687,687,687,687,687,687,687,687, -687,687,687,687,687,687,687,687,687,687,687,687,687,687,687,687, -687,687,687,687,687,687,687,687,687,114,114,114,114,114,114,114, - -/* block 171 */ -688,688,688,688,688,688,688,688,688,688,688,688,688,688,688,688, -688,688,688,688,688,688,688,688,688,688,688,688,688,688,688,688, -688,688,688,688,688,688,688,688,688,688,688,688,688,688,688,688, -688,688,688,688,688,688,688,688,688,688,688,688,688,688,688,688, -688,688,688,688,688,688,688,688,688,688,688,688,688,688,688,688, -688,688,688,688,688,688,688,688,688,688,688,688,688,688,688,688, -688,688,688,688,688,688,688,688,688,688,688,688,688,688,688,688, -688,688,688,688,688,688,688,688,688,688,688,688,688,688,688,688, - -/* block 172 */ -688,688,688,688,688,688,688,688,688,688,688,688,688,688,688,688, -688,688,688,688,688,688,688,688,688,114,114,114,114,114,114,114, -114,114,114,114,114,114,114,114,114,114,114,114,114,114,114,114, -114,114,114,114,114,114,114,114,114,114,114,114,114,114,114,114, -114,114,114,114,114,114,114,114,114,114,114,114,114,114,114,114, -114,114,114,114,114,114,114,114,114,114,114,114,114,114,114,114, -114,114,114,114,114,114,114,114,114,114,114,114,114,114,114,114, -114,114,114,114,114,114,114,114,114,114,114,114,114,114,114,114, - -/* block 173 */ -689,689,689,689,689,689,689,689,689,689,689,689,689,689,689,689, -689,689,689,689,689,689,689,689,689,689,689,689,689,689,689,689, -689,689,689,689,689,689,689,689,689,689,689,689,689,689,689,689, -689,689,689,689,689,689,689,689,689,689,689,689,689,689,689,689, -689,689,689,689,689,689,689,689,689,689,689,689,689,689,689,689, -689,689,689,689,689,689,689,689,689,689,689,689,689,689,689,689, -689,689,689,689,689,689,689,689,689,689,689,689,689,689,689,114, -690,690,690,690,690,114,114,114,114,114,114,114,114,114,114,114, - -/* block 174 */ -691,691,691,691,691,691,691,691,691,691,691,691,691,691,691,691, -691,691,691,691,691,691,691,691,691,691,691,691,691,691,691,691, -691,691,691,691,691,691,691,691,691,691,691,691,691,691,691,691, -691,691,691,691,691,691,691,691,691,691,691,691,691,691,691,691, -691,691,691,691,691,691,691,691,691,691,691,691,691,691,691,691, -691,691,691,691,691,691,691,691,691,691,691,691,691,691,691,691, -691,691,691,691,691,691,691,691,691,691,691,691,691,691,691,691, -691,691,691,691,691,691,691,691,691,691,691,691,691,691,691,691, - -/* block 175 */ -691,691,691,691,691,691,691,691,691,691,691,691,691,691,691,691, -691,691,691,691,691,691,691,691,691,691,691,691,691,691,691,691, -691,691,691,691,691,691,691,691,691,691,691,691,691,691,691,114, -114,114,114,114,114,114,114,114,114,114,114,114,114,114,114,114, -114,114,114,114,114,114,114,114,114,114,114,114,114,114,114,114, -114,114,114,114,114,114,114,114,114,114,114,114,114,114,114,114, -114,114,114,114,114,114,114,114,114,114,114,114,114,114,114,114, -114,114,114,114,114,114,114,114,114,114,114,114,114,114,114,114, - -/* block 176 */ -497,497,497,497,497,497,497,497,497,497,497,497,497,497,497,497, -497,497,497,497,497,497,497,497,497,497,497,497,497,497,497,497, -497,497,497,497,497,497,497,497,497,497,497,497,497,497,497,497, -497,497,497,497,497,497,497,497,497,497,497,497,497,497,497,497, -497,497,497,497,497,497,497,497,497,497,497,497,497,497,497,497, -497,497,497,497,497,497,497,497,497,497,497,497,497,497,497,497, -497,497,497,497,497,497,497,497,497,497,497,497,497,497,497,497, -497,497,497,497,497,497,497,497,497,497,497,497,497,497,497,497, - -/* block 177 */ -497,497,497,497,497,497,497,497,497,497,497,497,497,497,497,497, -497,497,497,497,497,497,497,497,497,497,497,497,497,497,497,497, -497,497,497,497,497,497,497,497,497,497,497,497,497,497,497,497, -497,497,497,497,497,497,497,497,497,114,114,114,114,114,114,114, -692,692,692,692,692,692,692,692,692,692,692,692,692,692,692,692, -692,692,692,692,692,692,692,692,692,692,692,692,692,692,692,114, -693,693,693,693,693,693,693,693,693,693,114,114,114,114,694,694, -114,114,114,114,114,114,114,114,114,114,114,114,114,114,114,114, - -/* block 178 */ -114,114,114,114,114,114,114,114,114,114,114,114,114,114,114,114, -114,114,114,114,114,114,114,114,114,114,114,114,114,114,114,114, -114,114,114,114,114,114,114,114,114,114,114,114,114,114,114,114, -114,114,114,114,114,114,114,114,114,114,114,114,114,114,114,114, -114,114,114,114,114,114,114,114,114,114,114,114,114,114,114,114, -695,695,695,695,695,695,695,695,695,695,695,695,695,695,695,695, -695,695,695,695,695,695,695,695,695,695,695,695,695,695,114,114, -696,696,696,696,696,697,114,114,114,114,114,114,114,114,114,114, - -/* block 179 */ -698,698,698,698,698,698,698,698,698,698,698,698,698,698,698,698, -698,698,698,698,698,698,698,698,698,698,698,698,698,698,698,698, -698,698,698,698,698,698,698,698,698,698,698,698,698,698,698,698, -699,699,699,699,699,699,699,700,700,700,700,700,701,701,701,701, -702,702,702,702,700,701,114,114,114,114,114,114,114,114,114,114, -703,703,703,703,703,703,703,703,703,703,114,704,704,704,704,704, -704,704,114,698,698,698,698,698,698,698,698,698,698,698,698,698, -698,698,698,698,698,698,698,698,114,114,114,114,114,698,698,698, - -/* block 180 */ -698,698,698,698,698,698,698,698,698,698,698,698,698,698,698,698, -114,114,114,114,114,114,114,114,114,114,114,114,114,114,114,114, -114,114,114,114,114,114,114,114,114,114,114,114,114,114,114,114, -114,114,114,114,114,114,114,114,114,114,114,114,114,114,114,114, -114,114,114,114,114,114,114,114,114,114,114,114,114,114,114,114, -114,114,114,114,114,114,114,114,114,114,114,114,114,114,114,114, -114,114,114,114,114,114,114,114,114,114,114,114,114,114,114,114, -114,114,114,114,114,114,114,114,114,114,114,114,114,114,114,114, - -/* block 181 */ -705,705,705,705,705,705,705,705,705,705,705,705,705,705,705,705, -705,705,705,705,705,705,705,705,705,705,705,705,705,705,705,705, -705,705,705,705,705,705,705,705,705,705,705,705,705,705,705,705, -705,705,705,705,705,705,705,705,705,705,705,705,705,705,705,705, -705,705,705,705,705,114,114,114,114,114,114,114,114,114,114,114, -705,706,706,706,706,706,706,706,706,706,706,706,706,706,706,706, -706,706,706,706,706,706,706,706,706,706,706,706,706,706,706,706, -706,706,706,706,706,706,706,706,706,706,706,706,706,706,706,114, - -/* block 182 */ -114,114,114,114,114,114,114,114,114,114,114,114,114,114,114,707, -707,707,707,708,708,708,708,708,708,708,708,708,708,708,708,708, -114,114,114,114,114,114,114,114,114,114,114,114,114,114,114,114, -114,114,114,114,114,114,114,114,114,114,114,114,114,114,114,114, -114,114,114,114,114,114,114,114,114,114,114,114,114,114,114,114, -114,114,114,114,114,114,114,114,114,114,114,114,114,114,114,114, -114,114,114,114,114,114,114,114,114,114,114,114,114,114,114,114, -114,114,114,114,114,114,114,114,114,114,114,114,114,114,114,114, - -/* block 183 */ -478,476,114,114,114,114,114,114,114,114,114,114,114,114,114,114, -114,114,114,114,114,114,114,114,114,114,114,114,114,114,114,114, -114,114,114,114,114,114,114,114,114,114,114,114,114,114,114,114, -114,114,114,114,114,114,114,114,114,114,114,114,114,114,114,114, -114,114,114,114,114,114,114,114,114,114,114,114,114,114,114,114, -114,114,114,114,114,114,114,114,114,114,114,114,114,114,114,114, -114,114,114,114,114,114,114,114,114,114,114,114,114,114,114,114, -114,114,114,114,114,114,114,114,114,114,114,114,114,114,114,114, - -/* block 184 */ -709,709,709,709,709,709,709,709,709,709,709,709,709,709,709,709, -709,709,709,709,709,709,709,709,709,709,709,709,709,709,709,709, -709,709,709,709,709,709,709,709,709,709,709,709,709,709,709,709, -709,709,709,709,709,709,709,709,709,709,709,709,709,709,709,709, -709,709,709,709,709,709,709,709,709,709,709,709,709,709,709,709, -709,709,709,709,709,709,709,709,709,709,709,709,709,709,709,709, -709,709,709,709,709,709,709,709,709,709,709,114,114,114,114,114, -709,709,709,709,709,709,709,709,709,709,709,709,709,114,114,114, - -/* block 185 */ -709,709,709,709,709,709,709,709,709,114,114,114,114,114,114,114, -709,709,709,709,709,709,709,709,709,709,114,114,710,711,711,712, - 22, 22, 22, 22,114,114,114,114,114,114,114,114,114,114,114,114, -114,114,114,114,114,114,114,114,114,114,114,114,114,114,114,114, -114,114,114,114,114,114,114,114,114,114,114,114,114,114,114,114, -114,114,114,114,114,114,114,114,114,114,114,114,114,114,114,114, -114,114,114,114,114,114,114,114,114,114,114,114,114,114,114,114, -114,114,114,114,114,114,114,114,114,114,114,114,114,114,114,114, - -/* block 186 */ - 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, - 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, - 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, - 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, - 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, - 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, - 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, - 19, 19, 19, 19, 19, 19,114,114,114,114,114,114,114,114,114,114, - -/* block 187 */ - 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, - 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, - 19, 19, 19, 19, 19, 19, 19,114,114, 19, 19, 19, 19, 19, 19, 19, - 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, - 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, - 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, - 19, 19, 19, 19, 19,713,405,109,109,109, 19, 19, 19,405,713,713, -713,713,713, 22, 22, 22, 22, 22, 22, 22, 22,109,109,109,109,109, - -/* block 188 */ -109,109,109, 19, 19,109,109,109,109,109,109,109, 19, 19, 19, 19, - 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, - 19, 19, 19, 19, 19, 19, 19, 19, 19, 19,109,109,109,109, 19, 19, - 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, - 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, - 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19,114,114, -114,114,114,114,114,114,114,114,114,114,114,114,114,114,114,114, -114,114,114,114,114,114,114,114,114,114,114,114,114,114,114,114, - -/* block 189 */ -559,559,559,559,559,559,559,559,559,559,559,559,559,559,559,559, -559,559,559,559,559,559,559,559,559,559,559,559,559,559,559,559, -559,559,559,559,559,559,559,559,559,559,559,559,559,559,559,559, -559,559,559,559,559,559,559,559,559,559,559,559,559,559,559,559, -559,559,714,714,714,559,114,114,114,114,114,114,114,114,114,114, -114,114,114,114,114,114,114,114,114,114,114,114,114,114,114,114, -114,114,114,114,114,114,114,114,114,114,114,114,114,114,114,114, -114,114,114,114,114,114,114,114,114,114,114,114,114,114,114,114, - -/* block 190 */ - 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, - 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, - 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, - 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, - 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, - 19, 19, 19, 19, 19, 19, 19,114,114,114,114,114,114,114,114,114, - 23, 23, 23, 23, 23, 23, 23, 23, 23, 23, 23, 23, 23, 23, 23, 23, - 23, 23,114,114,114,114,114,114,114,114,114,114,114,114,114,114, - -/* block 191 */ -437,437,437,437,437,437,437,437,437,437,437,437,437,437,437,437, -437,437,437,437,437,437,437,437,437,437,438,438,438,438,438,438, -438,438,438,438,438,438,438,438,438,438,438,438,438,438,438,438, -438,438,438,438,437,437,437,437,437,437,437,437,437,437,437,437, -437,437,437,437,437,437,437,437,437,437,437,437,437,437,438,438, -438,438,438,438,438,114,438,438,438,438,438,438,438,438,438,438, -438,438,438,438,438,438,438,438,437,437,437,437,437,437,437,437, -437,437,437,437,437,437,437,437,437,437,437,437,437,437,437,437, - -/* block 192 */ -437,437,438,438,438,438,438,438,438,438,438,438,438,438,438,438, -438,438,438,438,438,438,438,438,438,438,438,438,437,114,437,437, -114,114,437,114,114,437,437,114,114,437,437,437,437,114,437,437, -437,437,437,437,437,437,438,438,438,438,114,438,114,438,438,438, -438,438,438,438,114,438,438,438,438,438,438,438,438,438,438,438, -437,437,437,437,437,437,437,437,437,437,437,437,437,437,437,437, -437,437,437,437,437,437,437,437,437,437,438,438,438,438,438,438, -438,438,438,438,438,438,438,438,438,438,438,438,438,438,438,438, - -/* block 193 */ -438,438,438,438,437,437,114,437,437,437,437,114,114,437,437,437, -437,437,437,437,437,114,437,437,437,437,437,437,437,114,438,438, -438,438,438,438,438,438,438,438,438,438,438,438,438,438,438,438, -438,438,438,438,438,438,438,438,437,437,114,437,437,437,437,114, -437,437,437,437,437,114,437,114,114,114,437,437,437,437,437,437, -437,114,438,438,438,438,438,438,438,438,438,438,438,438,438,438, -438,438,438,438,438,438,438,438,438,438,438,438,437,437,437,437, -437,437,437,437,437,437,437,437,437,437,437,437,437,437,437,437, - -/* block 194 */ -437,437,437,437,437,437,438,438,438,438,438,438,438,438,438,438, -438,438,438,438,438,438,438,438,438,438,438,438,438,438,438,438, -437,437,437,437,437,437,437,437,437,437,437,437,437,437,437,437, -437,437,437,437,437,437,437,437,437,437,438,438,438,438,438,438, -438,438,438,438,438,438,438,438,438,438,438,438,438,438,438,438, -438,438,438,438,437,437,437,437,437,437,437,437,437,437,437,437, -437,437,437,437,437,437,437,437,437,437,437,437,437,437,438,438, -438,438,438,438,438,438,438,438,438,438,438,438,438,438,438,438, - -/* block 195 */ -438,438,438,438,438,438,438,438,437,437,437,437,437,437,437,437, -437,437,437,437,437,437,437,437,437,437,437,437,437,437,437,437, -437,437,438,438,438,438,438,438,438,438,438,438,438,438,438,438, -438,438,438,438,438,438,438,438,438,438,438,438,437,437,437,437, -437,437,437,437,437,437,437,437,437,437,437,437,437,437,437,437, -437,437,437,437,437,437,438,438,438,438,438,438,438,438,438,438, -438,438,438,438,438,438,438,438,438,438,438,438,438,438,438,438, -437,437,437,437,437,437,437,437,437,437,437,437,437,437,437,437, - -/* block 196 */ -437,437,437,437,437,437,437,437,437,437,438,438,438,438,438,438, -438,438,438,438,438,438,438,438,438,438,438,438,438,438,438,438, -438,438,438,438,438,438,114,114,437,437,437,437,437,437,437,437, -437,437,437,437,437,437,437,437,437,437,437,437,437,437,437,437, -437, 8,438,438,438,438,438,438,438,438,438,438,438,438,438,438, -438,438,438,438,438,438,438,438,438,438,438, 8,438,438,438,438, -438,438,437,437,437,437,437,437,437,437,437,437,437,437,437,437, -437,437,437,437,437,437,437,437,437,437,437, 8,438,438,438,438, - -/* block 197 */ -438,438,438,438,438,438,438,438,438,438,438,438,438,438,438,438, -438,438,438,438,438, 8,438,438,438,438,438,438,437,437,437,437, -437,437,437,437,437,437,437,437,437,437,437,437,437,437,437,437, -437,437,437,437,437, 8,438,438,438,438,438,438,438,438,438,438, -438,438,438,438,438,438,438,438,438,438,438,438,438,438,438, 8, -438,438,438,438,438,438,437,437,437,437,437,437,437,437,437,437, -437,437,437,437,437,437,437,437,437,437,437,437,437,437,437, 8, -438,438,438,438,438,438,438,438,438,438,438,438,438,438,438,438, - -/* block 198 */ -438,438,438,438,438,438,438,438,438, 8,438,438,438,438,438,438, -437,437,437,437,437,437,437,437,437,437,437,437,437,437,437,437, -437,437,437,437,437,437,437,437,437, 8,438,438,438,438,438,438, -438,438,438,438,438,438,438,438,438,438,438,438,438,438,438,438, -438,438,438, 8,438,438,438,438,438,438,437,438,114,114, 10, 10, - 10, 10, 10, 10, 10, 10, 10, 10, 10, 10, 10, 10, 10, 10, 10, 10, - 10, 10, 10, 10, 10, 10, 10, 10, 10, 10, 10, 10, 10, 10, 10, 10, - 10, 10, 10, 10, 10, 10, 10, 10, 10, 10, 10, 10, 10, 10, 10, 10, - -/* block 199 */ -715,715,715,715,715,715,715,715,715,715,715,715,715,715,715,715, -715,715,715,715,715,715,715,715,715,715,715,715,715,715,715,715, -715,715,715,715,715,715,715,715,715,715,715,715,715,715,715,715, -715,715,715,715,715,715,715,715,715,715,715,715,715,715,715,715, -715,715,715,715,715,715,715,715,715,715,715,715,715,715,715,715, -715,715,715,715,715,715,715,715,715,715,715,715,715,715,715,715, -715,715,715,715,715,715,715,715,715,715,715,715,715,715,715,715, -715,715,715,715,715,715,715,715,715,715,715,715,715,715,715,715, - -/* block 200 */ -715,715,715,715,715,715,715,715,715,715,715,715,715,715,715,715, -715,715,715,715,715,715,715,715,715,715,715,715,715,715,715,715, -715,715,715,715,715,715,715,715,715,715,715,715,715,715,715,715, -715,715,715,715,715,715,715,715,715,715,715,715,715,715,715,715, -715,715,715,715,715,114,114,716,716,716,716,716,716,716,716,716, -717,717,717,717,717,717,717,114,114,114,114,114,114,114,114,114, -114,114,114,114,114,114,114,114,114,114,114,114,114,114,114,114, -114,114,114,114,114,114,114,114,114,114,114,114,114,114,114,114, - -/* block 201 */ -199,199,199,199,114,199,199,199,199,199,199,199,199,199,199,199, -199,199,199,199,199,199,199,199,199,199,199,199,199,199,199,199, -114,199,199,114,199,114,114,199,114,199,199,199,199,199,199,199, -199,199,199,114,199,199,199,199,114,199,114,199,114,114,114,114, -114,114,199,114,114,114,114,199,114,199,114,199,114,199,199,199, -114,199,199,114,199,114,114,199,114,199,114,199,114,199,114,199, -114,199,199,114,199,114,114,199,199,199,199,114,199,199,199,199, -199,199,199,114,199,199,199,199,114,199,199,199,199,114,199,114, - -/* block 202 */ -199,199,199,199,199,199,199,199,199,199,114,199,199,199,199,199, -199,199,199,199,199,199,199,199,199,199,199,199,114,114,114,114, -114,199,199,199,114,199,199,199,199,199,114,199,199,199,199,199, -199,199,199,199,199,199,199,199,199,199,199,199,114,114,114,114, -114,114,114,114,114,114,114,114,114,114,114,114,114,114,114,114, -114,114,114,114,114,114,114,114,114,114,114,114,114,114,114,114, -114,114,114,114,114,114,114,114,114,114,114,114,114,114,114,114, -194,194,114,114,114,114,114,114,114,114,114,114,114,114,114,114, - -/* block 203 */ - 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, - 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, - 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19,114,114,114,114, - 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, - 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, - 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, - 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, - 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, - -/* block 204 */ - 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, - 19, 19, 19, 19,114,114,114,114,114,114,114,114,114,114,114,114, - 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19,114, -114, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, -114, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, -114, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, - 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, - 19, 19, 19, 19, 19, 19,114,114,114,114,114,114,114,114,114,114, - -/* block 205 */ - 23, 23, 23, 23, 23, 23, 23, 23, 23, 23, 23, 23, 23,114,114,114, - 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, - 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19,114, - 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, - 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, - 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, - 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19,114,114,114,114, - 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, - -/* block 206 */ - 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, - 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19,114,114,114,114,114, -114,114,114,114,114,114,114,114,114,114,114,114,114,114,114,114, -114,114,114,114,114,114,114,114,114,114,114,114,114,114,114,114, -114,114,114,114,114,114,114,114,114,114,114,114,114,114,114,114, -114,114,114,114,114,114,114,114,114,114,114,114,114,114,114,114, -114,114,114,114,114,114,718,718,718,718,718,718,718,718,718,718, -718,718,718,718,718,718,718,718,718,718,718,718,718,718,718,718, - -/* block 207 */ -719, 19, 19,114,114,114,114,114,114,114,114,114,114,114,114,114, - 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, - 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, - 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19,114,114,114,114,114, - 19, 19, 19, 19, 19, 19, 19, 19, 19,114,114,114,114,114,114,114, - 19, 19,114,114,114,114,114,114,114,114,114,114,114,114,114,114, -114,114,114,114,114,114,114,114,114,114,114,114,114,114,114,114, -114,114,114,114,114,114,114,114,114,114,114,114,114,114,114,114, - -/* block 208 */ - 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, - 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, - 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19,114,114,114, - 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, - 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, - 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, - 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, - 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19,114,114, - -/* block 209 */ - 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, - 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, - 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, - 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, - 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19,114, -114,114,114,114, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, - 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, - 19, 19, 19, 19, 19, 19, 19, 19,114,114,114,114,114,114,114,114, - -/* block 210 */ - 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, - 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, - 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, - 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, - 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, - 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, - 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, - 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19,114, - -/* block 211 */ - 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, - 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, - 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, - 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, - 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19,114,114,114,114,114, - 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, - 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, - 19, 19, 19, 19, 19, 19, 19, 19, 19, 19,114, 19, 19, 19, 19, 19, - -/* block 212 */ - 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, - 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, - 19, 19, 19, 19,114, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, - 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, - 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, - 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, - 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, - 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, - -/* block 213 */ - 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, - 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, - 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, - 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, - 19, 19, 19,114,114, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, - 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, - 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, - 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, - -/* block 214 */ - 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, - 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, - 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, - 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, - 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, -114,114,114,114,114,114,114,114,114,114,114,114,114,114,114,114, - 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19,114,114,114, - 19, 19, 19, 19,114,114,114,114,114,114,114,114,114,114,114,114, - -/* block 215 */ - 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, - 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, - 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, - 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, - 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, - 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, - 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, - 19, 19, 19, 19,114,114,114,114,114,114,114,114,114,114,114,114, - -/* block 216 */ - 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, - 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, - 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, - 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, - 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, - 19, 19, 19, 19, 19,114,114,114,114,114,114,114,114,114,114,114, -114,114,114,114,114,114,114,114,114,114,114,114,114,114,114,114, -114,114,114,114,114,114,114,114,114,114,114,114,114,114,114,114, - -/* block 217 */ - 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19,114,114,114,114, - 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, - 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, - 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, - 19, 19, 19, 19, 19, 19, 19, 19,114,114,114,114,114,114,114,114, - 19, 19, 19, 19, 19, 19, 19, 19, 19, 19,114,114,114,114,114,114, - 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, - 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, - -/* block 218 */ - 19, 19, 19, 19, 19, 19, 19, 19,114,114,114,114,114,114,114,114, - 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, - 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19,114,114, -114,114,114,114,114,114,114,114,114,114,114,114,114,114,114,114, -114,114,114,114,114,114,114,114,114,114,114,114,114,114,114,114, -114,114,114,114,114,114,114,114,114,114,114,114,114,114,114,114, -114,114,114,114,114,114,114,114,114,114,114,114,114,114,114,114, -114,114,114,114,114,114,114,114,114,114,114,114,114,114,114,114, - -/* block 219 */ -484,484,484,484,484,484,484,484,484,484,484,484,484,484,484,484, -484,484,484,484,484,484,484,484,484,484,484,484,484,484,484,484, -484,484,484,484,484,484,484,484,484,484,484,484,484,484,484,484, -484,484,484,484,484,484,484,484,484,484,484,484,484,484,484,484, -484,484,484,484,484,484,484,484,484,484,484,484,484,484,484,484, -484,484,484,484,484,484,484,114,114,114,114,114,114,114,114,114, -114,114,114,114,114,114,114,114,114,114,114,114,114,114,114,114, -114,114,114,114,114,114,114,114,114,114,114,114,114,114,114,114, - -/* block 220 */ -484,484,484,484,484,484,484,484,484,484,484,484,484,484,484,484, -484,484,484,484,484,484,484,484,484,484,484,484,484,484,484,484, -484,484,484,484,484,484,484,484,484,484,484,484,484,484,484,484, -484,484,484,484,484,114,114,114,114,114,114,114,114,114,114,114, -484,484,484,484,484,484,484,484,484,484,484,484,484,484,484,484, -484,484,484,484,484,484,484,484,484,484,484,484,484,484,484,484, -484,484,484,484,484,484,484,484,484,484,484,484,484,484,484,484, -484,484,484,484,484,484,484,484,484,484,484,484,484,484,484,484, - -/* block 221 */ -484,484,484,484,484,484,484,484,484,484,484,484,484,484,484,484, -484,484,484,484,484,484,484,484,484,484,484,484,484,484,114,114, -114,114,114,114,114,114,114,114,114,114,114,114,114,114,114,114, -114,114,114,114,114,114,114,114,114,114,114,114,114,114,114,114, -114,114,114,114,114,114,114,114,114,114,114,114,114,114,114,114, -114,114,114,114,114,114,114,114,114,114,114,114,114,114,114,114, -114,114,114,114,114,114,114,114,114,114,114,114,114,114,114,114, -114,114,114,114,114,114,114,114,114,114,114,114,114,114,114,114, - -/* block 222 */ -436, 22,436,436,436,436,436,436,436,436,436,436,436,436,436,436, -436,436,436,436,436,436,436,436,436,436,436,436,436,436,436,436, - 22, 22, 22, 22, 22, 22, 22, 22, 22, 22, 22, 22, 22, 22, 22, 22, - 22, 22, 22, 22, 22, 22, 22, 22, 22, 22, 22, 22, 22, 22, 22, 22, - 22, 22, 22, 22, 22, 22, 22, 22, 22, 22, 22, 22, 22, 22, 22, 22, - 22, 22, 22, 22, 22, 22, 22, 22, 22, 22, 22, 22, 22, 22, 22, 22, - 22, 22, 22, 22, 22, 22, 22, 22, 22, 22, 22, 22, 22, 22, 22, 22, - 22, 22, 22, 22, 22, 22, 22, 22, 22, 22, 22, 22, 22, 22, 22, 22, - -/* block 223 */ -436,436,436,436,436,436,436,436,436,436,436,436,436,436,436,436, -436,436,436,436,436,436,436,436,436,436,436,436,436,436,436,436, -436,436,436,436,436,436,436,436,436,436,436,436,436,436,436,436, -436,436,436,436,436,436,436,436,436,436,436,436,436,436,436,436, -436,436,436,436,436,436,436,436,436,436,436,436,436,436,436,436, -436,436,436,436,436,436,436,436,436,436,436,436,436,436,436,436, -436,436,436,436,436,436,436,436,436,436,436,436,436,436,436,436, -436,436,436,436,436,436,436,436,436,436,436,436,436,436,436,436, - -/* block 224 */ -109,109,109,109,109,109,109,109,109,109,109,109,109,109,109,109, -109,109,109,109,109,109,109,109,109,109,109,109,109,109,109,109, -109,109,109,109,109,109,109,109,109,109,109,109,109,109,109,109, -109,109,109,109,109,109,109,109,109,109,109,109,109,109,109,109, -109,109,109,109,109,109,109,109,109,109,109,109,109,109,109,109, -109,109,109,109,109,109,109,109,109,109,109,109,109,109,109,109, -109,109,109,109,109,109,109,109,109,109,109,109,109,109,109,109, -109,109,109,109,109,109,109,109,109,109,109,109,109,109,109,109, - -/* block 225 */ -109,109,109,109,109,109,109,109,109,109,109,109,109,109,109,109, -109,109,109,109,109,109,109,109,109,109,109,109,109,109,109,109, -109,109,109,109,109,109,109,109,109,109,109,109,109,109,109,109, -109,109,109,109,109,109,109,109,109,109,109,109,109,109,109,109, -109,109,109,109,109,109,109,109,109,109,109,109,109,109,109,109, -109,109,109,109,109,109,109,109,109,109,109,109,109,109,109,109, -109,109,109,109,109,109,109,109,109,109,109,109,109,109,109,109, -436,436,436,436,436,436,436,436,436,436,436,436,436,436,436,436, - -/* block 226 */ -552,552,552,552,552,552,552,552,552,552,552,552,552,552,552,552, -552,552,552,552,552,552,552,552,552,552,552,552,552,552,552,552, -552,552,552,552,552,552,552,552,552,552,552,552,552,552,552,552, -552,552,552,552,552,552,552,552,552,552,552,552,552,552,552,552, -552,552,552,552,552,552,552,552,552,552,552,552,552,552,552,552, -552,552,552,552,552,552,552,552,552,552,552,552,552,552,552,552, -552,552,552,552,552,552,552,552,552,552,552,552,552,552,552,552, -552,552,552,552,552,552,552,552,552,552,552,552,552,552,114,114, - -}; - -#if UCD_BLOCK_SIZE != 128 -#error Please correct UCD_BLOCK_SIZE in pcre_internal.h -#endif -#endif /* SUPPORT_UCP */ - -#endif /* PCRE_INCLUDED */ diff --git a/src/third_party/pcre-8.38/pcre_valid_utf8.c b/src/third_party/pcre-8.38/pcre_valid_utf8.c deleted file mode 100644 index 3b0f6464a35..00000000000 --- a/src/third_party/pcre-8.38/pcre_valid_utf8.c +++ /dev/null @@ -1,301 +0,0 @@ -/************************************************* -* Perl-Compatible Regular Expressions * -*************************************************/ - -/* PCRE is a library of functions to support regular expressions whose syntax -and semantics are as close as possible to those of the Perl 5 language. - - Written by Philip Hazel - Copyright (c) 1997-2013 University of Cambridge - ------------------------------------------------------------------------------ -Redistribution and use in source and binary forms, with or without -modification, are permitted provided that the following conditions are met: - - * Redistributions of source code must retain the above copyright notice, - this list of conditions and the following disclaimer. - - * Redistributions in binary form must reproduce the above copyright - notice, this list of conditions and the following disclaimer in the - documentation and/or other materials provided with the distribution. - - * Neither the name of the University of Cambridge nor the names of its - contributors may be used to endorse or promote products derived from - this software without specific prior written permission. - -THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS" -AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE -IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE -ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR CONTRIBUTORS BE -LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR -CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF -SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS -INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN -CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) -ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE -POSSIBILITY OF SUCH DAMAGE. ------------------------------------------------------------------------------ -*/ - - -/* This module contains an internal function for validating UTF-8 character -strings. */ - - -#ifdef HAVE_CONFIG_H -#include "config.h" -#endif - -#include "pcre_internal.h" - - -/************************************************* -* Validate a UTF-8 string * -*************************************************/ - -/* This function is called (optionally) at the start of compile or match, to -check that a supposed UTF-8 string is actually valid. The early check means -that subsequent code can assume it is dealing with a valid string. The check -can be turned off for maximum performance, but the consequences of supplying an -invalid string are then undefined. - -Originally, this function checked according to RFC 2279, allowing for values in -the range 0 to 0x7fffffff, up to 6 bytes long, but ensuring that they were in -the canonical format. Once somebody had pointed out RFC 3629 to me (it -obsoletes 2279), additional restrictions were applied. The values are now -limited to be between 0 and 0x0010ffff, no more than 4 bytes long, and the -subrange 0xd000 to 0xdfff is excluded. However, the format of 5-byte and 6-byte -characters is still checked. - -From release 8.13 more information about the details of the error are passed -back in the returned value: - -PCRE_UTF8_ERR0 No error -PCRE_UTF8_ERR1 Missing 1 byte at the end of the string -PCRE_UTF8_ERR2 Missing 2 bytes at the end of the string -PCRE_UTF8_ERR3 Missing 3 bytes at the end of the string -PCRE_UTF8_ERR4 Missing 4 bytes at the end of the string -PCRE_UTF8_ERR5 Missing 5 bytes at the end of the string -PCRE_UTF8_ERR6 2nd-byte's two top bits are not 0x80 -PCRE_UTF8_ERR7 3rd-byte's two top bits are not 0x80 -PCRE_UTF8_ERR8 4th-byte's two top bits are not 0x80 -PCRE_UTF8_ERR9 5th-byte's two top bits are not 0x80 -PCRE_UTF8_ERR10 6th-byte's two top bits are not 0x80 -PCRE_UTF8_ERR11 5-byte character is not permitted by RFC 3629 -PCRE_UTF8_ERR12 6-byte character is not permitted by RFC 3629 -PCRE_UTF8_ERR13 4-byte character with value > 0x10ffff is not permitted -PCRE_UTF8_ERR14 3-byte character with value 0xd000-0xdfff is not permitted -PCRE_UTF8_ERR15 Overlong 2-byte sequence -PCRE_UTF8_ERR16 Overlong 3-byte sequence -PCRE_UTF8_ERR17 Overlong 4-byte sequence -PCRE_UTF8_ERR18 Overlong 5-byte sequence (won't ever occur) -PCRE_UTF8_ERR19 Overlong 6-byte sequence (won't ever occur) -PCRE_UTF8_ERR20 Isolated 0x80 byte (not within UTF-8 character) -PCRE_UTF8_ERR21 Byte with the illegal value 0xfe or 0xff -PCRE_UTF8_ERR22 Unused (was non-character) - -Arguments: - string points to the string - length length of string, or -1 if the string is zero-terminated - errp pointer to an error position offset variable - -Returns: = 0 if the string is a valid UTF-8 string - > 0 otherwise, setting the offset of the bad character -*/ - -int -PRIV(valid_utf)(PCRE_PUCHAR string, int length, int *erroroffset) -{ -#ifdef SUPPORT_UTF -register PCRE_PUCHAR p; - -if (length < 0) - { - for (p = string; *p != 0; p++); - length = (int)(p - string); - } - -for (p = string; length-- > 0; p++) - { - register pcre_uchar ab, c, d; - - c = *p; - if (c < 128) continue; /* ASCII character */ - - if (c < 0xc0) /* Isolated 10xx xxxx byte */ - { - *erroroffset = (int)(p - string); - return PCRE_UTF8_ERR20; - } - - if (c >= 0xfe) /* Invalid 0xfe or 0xff bytes */ - { - *erroroffset = (int)(p - string); - return PCRE_UTF8_ERR21; - } - - ab = PRIV(utf8_table4)[c & 0x3f]; /* Number of additional bytes */ - if (length < ab) - { - *erroroffset = (int)(p - string); /* Missing bytes */ - return ab - length; /* Codes ERR1 to ERR5 */ - } - length -= ab; /* Length remaining */ - - /* Check top bits in the second byte */ - - if (((d = *(++p)) & 0xc0) != 0x80) - { - *erroroffset = (int)(p - string) - 1; - return PCRE_UTF8_ERR6; - } - - /* For each length, check that the remaining bytes start with the 0x80 bit - set and not the 0x40 bit. Then check for an overlong sequence, and for the - excluded range 0xd800 to 0xdfff. */ - - switch (ab) - { - /* 2-byte character. No further bytes to check for 0x80. Check first byte - for for xx00 000x (overlong sequence). */ - - case 1: if ((c & 0x3e) == 0) - { - *erroroffset = (int)(p - string) - 1; - return PCRE_UTF8_ERR15; - } - break; - - /* 3-byte character. Check third byte for 0x80. Then check first 2 bytes - for 1110 0000, xx0x xxxx (overlong sequence) or - 1110 1101, 1010 xxxx (0xd800 - 0xdfff) */ - - case 2: - if ((*(++p) & 0xc0) != 0x80) /* Third byte */ - { - *erroroffset = (int)(p - string) - 2; - return PCRE_UTF8_ERR7; - } - if (c == 0xe0 && (d & 0x20) == 0) - { - *erroroffset = (int)(p - string) - 2; - return PCRE_UTF8_ERR16; - } - if (c == 0xed && d >= 0xa0) - { - *erroroffset = (int)(p - string) - 2; - return PCRE_UTF8_ERR14; - } - break; - - /* 4-byte character. Check 3rd and 4th bytes for 0x80. Then check first 2 - bytes for for 1111 0000, xx00 xxxx (overlong sequence), then check for a - character greater than 0x0010ffff (f4 8f bf bf) */ - - case 3: - if ((*(++p) & 0xc0) != 0x80) /* Third byte */ - { - *erroroffset = (int)(p - string) - 2; - return PCRE_UTF8_ERR7; - } - if ((*(++p) & 0xc0) != 0x80) /* Fourth byte */ - { - *erroroffset = (int)(p - string) - 3; - return PCRE_UTF8_ERR8; - } - if (c == 0xf0 && (d & 0x30) == 0) - { - *erroroffset = (int)(p - string) - 3; - return PCRE_UTF8_ERR17; - } - if (c > 0xf4 || (c == 0xf4 && d > 0x8f)) - { - *erroroffset = (int)(p - string) - 3; - return PCRE_UTF8_ERR13; - } - break; - - /* 5-byte and 6-byte characters are not allowed by RFC 3629, and will be - rejected by the length test below. However, we do the appropriate tests - here so that overlong sequences get diagnosed, and also in case there is - ever an option for handling these larger code points. */ - - /* 5-byte character. Check 3rd, 4th, and 5th bytes for 0x80. Then check for - 1111 1000, xx00 0xxx */ - - case 4: - if ((*(++p) & 0xc0) != 0x80) /* Third byte */ - { - *erroroffset = (int)(p - string) - 2; - return PCRE_UTF8_ERR7; - } - if ((*(++p) & 0xc0) != 0x80) /* Fourth byte */ - { - *erroroffset = (int)(p - string) - 3; - return PCRE_UTF8_ERR8; - } - if ((*(++p) & 0xc0) != 0x80) /* Fifth byte */ - { - *erroroffset = (int)(p - string) - 4; - return PCRE_UTF8_ERR9; - } - if (c == 0xf8 && (d & 0x38) == 0) - { - *erroroffset = (int)(p - string) - 4; - return PCRE_UTF8_ERR18; - } - break; - - /* 6-byte character. Check 3rd-6th bytes for 0x80. Then check for - 1111 1100, xx00 00xx. */ - - case 5: - if ((*(++p) & 0xc0) != 0x80) /* Third byte */ - { - *erroroffset = (int)(p - string) - 2; - return PCRE_UTF8_ERR7; - } - if ((*(++p) & 0xc0) != 0x80) /* Fourth byte */ - { - *erroroffset = (int)(p - string) - 3; - return PCRE_UTF8_ERR8; - } - if ((*(++p) & 0xc0) != 0x80) /* Fifth byte */ - { - *erroroffset = (int)(p - string) - 4; - return PCRE_UTF8_ERR9; - } - if ((*(++p) & 0xc0) != 0x80) /* Sixth byte */ - { - *erroroffset = (int)(p - string) - 5; - return PCRE_UTF8_ERR10; - } - if (c == 0xfc && (d & 0x3c) == 0) - { - *erroroffset = (int)(p - string) - 5; - return PCRE_UTF8_ERR19; - } - break; - } - - /* Character is valid under RFC 2279, but 4-byte and 5-byte characters are - excluded by RFC 3629. The pointer p is currently at the last byte of the - character. */ - - if (ab > 3) - { - *erroroffset = (int)(p - string) - ab; - return (ab == 4)? PCRE_UTF8_ERR11 : PCRE_UTF8_ERR12; - } - } - -#else /* Not SUPPORT_UTF */ -(void)(string); /* Keep picky compilers happy */ -(void)(length); -(void)(erroroffset); -#endif - -return PCRE_UTF8_ERR0; /* This indicates success */ -} - -/* End of pcre_valid_utf8.c */ diff --git a/src/third_party/pcre-8.38/pcre_version.c b/src/third_party/pcre-8.38/pcre_version.c deleted file mode 100644 index ae86ff28bc8..00000000000 --- a/src/third_party/pcre-8.38/pcre_version.c +++ /dev/null @@ -1,98 +0,0 @@ -/************************************************* -* Perl-Compatible Regular Expressions * -*************************************************/ - -/* PCRE is a library of functions to support regular expressions whose syntax -and semantics are as close as possible to those of the Perl 5 language. - - Written by Philip Hazel - Copyright (c) 1997-2012 University of Cambridge - ------------------------------------------------------------------------------ -Redistribution and use in source and binary forms, with or without -modification, are permitted provided that the following conditions are met: - - * Redistributions of source code must retain the above copyright notice, - this list of conditions and the following disclaimer. - - * Redistributions in binary form must reproduce the above copyright - notice, this list of conditions and the following disclaimer in the - documentation and/or other materials provided with the distribution. - - * Neither the name of the University of Cambridge nor the names of its - contributors may be used to endorse or promote products derived from - this software without specific prior written permission. - -THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS" -AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE -IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE -ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR CONTRIBUTORS BE -LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR -CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF -SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS -INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN -CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) -ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE -POSSIBILITY OF SUCH DAMAGE. ------------------------------------------------------------------------------ -*/ - - -/* This module contains the external function pcre_version(), which returns a -string that identifies the PCRE version that is in use. */ - - -#ifdef HAVE_CONFIG_H -#include "config.h" -#endif - -#include "pcre_internal.h" - - -/************************************************* -* Return version string * -*************************************************/ - -/* These macros are the standard way of turning unquoted text into C strings. -They allow macros like PCRE_MAJOR to be defined without quotes, which is -convenient for user programs that want to test its value. */ - -#define STRING(a) # a -#define XSTRING(s) STRING(s) - -/* A problem turned up with PCRE_PRERELEASE, which is defined empty for -production releases. Originally, it was used naively in this code: - - return XSTRING(PCRE_MAJOR) - "." XSTRING(PCRE_MINOR) - XSTRING(PCRE_PRERELEASE) - " " XSTRING(PCRE_DATE); - -However, when PCRE_PRERELEASE is empty, this leads to an attempted expansion of -STRING(). The C standard states: "If (before argument substitution) any -argument consists of no preprocessing tokens, the behavior is undefined." It -turns out the gcc treats this case as a single empty string - which is what we -really want - but Visual C grumbles about the lack of an argument for the -macro. Unfortunately, both are within their rights. To cope with both ways of -handling this, I had resort to some messy hackery that does a test at run time. -I could find no way of detecting that a macro is defined as an empty string at -pre-processor time. This hack uses a standard trick for avoiding calling -the STRING macro with an empty argument when doing the test. */ - -#if defined COMPILE_PCRE8 -PCRE_EXP_DEFN const char * PCRE_CALL_CONVENTION -pcre_version(void) -#elif defined COMPILE_PCRE16 -PCRE_EXP_DEFN const char * PCRE_CALL_CONVENTION -pcre16_version(void) -#elif defined COMPILE_PCRE32 -PCRE_EXP_DEFN const char * PCRE_CALL_CONVENTION -pcre32_version(void) -#endif -{ -return (XSTRING(Z PCRE_PRERELEASE)[1] == 0)? - XSTRING(PCRE_MAJOR.PCRE_MINOR PCRE_DATE) : - XSTRING(PCRE_MAJOR.PCRE_MINOR) XSTRING(PCRE_PRERELEASE PCRE_DATE); -} - -/* End of pcre_version.c */ diff --git a/src/third_party/pcre-8.38/pcre_xclass.c b/src/third_party/pcre-8.38/pcre_xclass.c deleted file mode 100644 index ef759a589a6..00000000000 --- a/src/third_party/pcre-8.38/pcre_xclass.c +++ /dev/null @@ -1,268 +0,0 @@ -/************************************************* -* Perl-Compatible Regular Expressions * -*************************************************/ - -/* PCRE is a library of functions to support regular expressions whose syntax -and semantics are as close as possible to those of the Perl 5 language. - - Written by Philip Hazel - Copyright (c) 1997-2013 University of Cambridge - ------------------------------------------------------------------------------ -Redistribution and use in source and binary forms, with or without -modification, are permitted provided that the following conditions are met: - - * Redistributions of source code must retain the above copyright notice, - this list of conditions and the following disclaimer. - - * Redistributions in binary form must reproduce the above copyright - notice, this list of conditions and the following disclaimer in the - documentation and/or other materials provided with the distribution. - - * Neither the name of the University of Cambridge nor the names of its - contributors may be used to endorse or promote products derived from - this software without specific prior written permission. - -THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS" -AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE -IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE -ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR CONTRIBUTORS BE -LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR -CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF -SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS -INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN -CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) -ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE -POSSIBILITY OF SUCH DAMAGE. ------------------------------------------------------------------------------ -*/ - - -/* This module contains an internal function that is used to match an extended -class. It is used by both pcre_exec() and pcre_def_exec(). */ - - -#ifdef HAVE_CONFIG_H -#include "config.h" -#endif - -#include "pcre_internal.h" - - -/************************************************* -* Match character against an XCLASS * -*************************************************/ - -/* This function is called to match a character against an extended class that -might contain values > 255 and/or Unicode properties. - -Arguments: - c the character - data points to the flag byte of the XCLASS data - -Returns: TRUE if character matches, else FALSE -*/ - -BOOL -PRIV(xclass)(pcre_uint32 c, const pcre_uchar *data, BOOL utf) -{ -pcre_uchar t; -BOOL negated = (*data & XCL_NOT) != 0; - -(void)utf; -#ifdef COMPILE_PCRE8 -/* In 8 bit mode, this must always be TRUE. Help the compiler to know that. */ -utf = TRUE; -#endif - -/* Character values < 256 are matched against a bitmap, if one is present. If -not, we still carry on, because there may be ranges that start below 256 in the -additional data. */ - -if (c < 256) - { - if ((*data & XCL_HASPROP) == 0) - { - if ((*data & XCL_MAP) == 0) return negated; - return (((pcre_uint8 *)(data + 1))[c/8] & (1 << (c&7))) != 0; - } - if ((*data & XCL_MAP) != 0 && - (((pcre_uint8 *)(data + 1))[c/8] & (1 << (c&7))) != 0) - return !negated; /* char found */ - } - -/* First skip the bit map if present. Then match against the list of Unicode -properties or large chars or ranges that end with a large char. We won't ever -encounter XCL_PROP or XCL_NOTPROP when UCP support is not compiled. */ - -if ((*data++ & XCL_MAP) != 0) data += 32 / sizeof(pcre_uchar); - -while ((t = *data++) != XCL_END) - { - pcre_uint32 x, y; - if (t == XCL_SINGLE) - { -#ifdef SUPPORT_UTF - if (utf) - { - GETCHARINC(x, data); /* macro generates multiple statements */ - } - else -#endif - x = *data++; - if (c == x) return !negated; - } - else if (t == XCL_RANGE) - { -#ifdef SUPPORT_UTF - if (utf) - { - GETCHARINC(x, data); /* macro generates multiple statements */ - GETCHARINC(y, data); /* macro generates multiple statements */ - } - else -#endif - { - x = *data++; - y = *data++; - } - if (c >= x && c <= y) return !negated; - } - -#ifdef SUPPORT_UCP - else /* XCL_PROP & XCL_NOTPROP */ - { - const ucd_record *prop = GET_UCD(c); - BOOL isprop = t == XCL_PROP; - - switch(*data) - { - case PT_ANY: - if (isprop) return !negated; - break; - - case PT_LAMP: - if ((prop->chartype == ucp_Lu || prop->chartype == ucp_Ll || - prop->chartype == ucp_Lt) == isprop) return !negated; - break; - - case PT_GC: - if ((data[1] == PRIV(ucp_gentype)[prop->chartype]) == isprop) - return !negated; - break; - - case PT_PC: - if ((data[1] == prop->chartype) == isprop) return !negated; - break; - - case PT_SC: - if ((data[1] == prop->script) == isprop) return !negated; - break; - - case PT_ALNUM: - if ((PRIV(ucp_gentype)[prop->chartype] == ucp_L || - PRIV(ucp_gentype)[prop->chartype] == ucp_N) == isprop) - return !negated; - break; - - /* Perl space used to exclude VT, but from Perl 5.18 it is included, - which means that Perl space and POSIX space are now identical. PCRE - was changed at release 8.34. */ - - case PT_SPACE: /* Perl space */ - case PT_PXSPACE: /* POSIX space */ - switch(c) - { - HSPACE_CASES: - VSPACE_CASES: - if (isprop) return !negated; - break; - - default: - if ((PRIV(ucp_gentype)[prop->chartype] == ucp_Z) == isprop) - return !negated; - break; - } - break; - - case PT_WORD: - if ((PRIV(ucp_gentype)[prop->chartype] == ucp_L || - PRIV(ucp_gentype)[prop->chartype] == ucp_N || c == CHAR_UNDERSCORE) - == isprop) - return !negated; - break; - - case PT_UCNC: - if (c < 0xa0) - { - if ((c == CHAR_DOLLAR_SIGN || c == CHAR_COMMERCIAL_AT || - c == CHAR_GRAVE_ACCENT) == isprop) - return !negated; - } - else - { - if ((c < 0xd800 || c > 0xdfff) == isprop) - return !negated; - } - break; - - /* The following three properties can occur only in an XCLASS, as there - is no \p or \P coding for them. */ - - /* Graphic character. Implement this as not Z (space or separator) and - not C (other), except for Cf (format) with a few exceptions. This seems - to be what Perl does. The exceptional characters are: - - U+061C Arabic Letter Mark - U+180E Mongolian Vowel Separator - U+2066 - U+2069 Various "isolate"s - */ - - case PT_PXGRAPH: - if ((PRIV(ucp_gentype)[prop->chartype] != ucp_Z && - (PRIV(ucp_gentype)[prop->chartype] != ucp_C || - (prop->chartype == ucp_Cf && - c != 0x061c && c != 0x180e && (c < 0x2066 || c > 0x2069)) - )) == isprop) - return !negated; - break; - - /* Printable character: same as graphic, with the addition of Zs, i.e. - not Zl and not Zp, and U+180E. */ - - case PT_PXPRINT: - if ((prop->chartype != ucp_Zl && - prop->chartype != ucp_Zp && - (PRIV(ucp_gentype)[prop->chartype] != ucp_C || - (prop->chartype == ucp_Cf && - c != 0x061c && (c < 0x2066 || c > 0x2069)) - )) == isprop) - return !negated; - break; - - /* Punctuation: all Unicode punctuation, plus ASCII characters that - Unicode treats as symbols rather than punctuation, for Perl - compatibility (these are $+<=>^`|~). */ - - case PT_PXPUNCT: - if ((PRIV(ucp_gentype)[prop->chartype] == ucp_P || - (c < 128 && PRIV(ucp_gentype)[prop->chartype] == ucp_S)) == isprop) - return !negated; - break; - - /* This should never occur, but compilers may mutter if there is no - default. */ - - default: - return FALSE; - } - - data += 2; - } -#endif /* SUPPORT_UCP */ - } - -return negated; /* char did not match */ -} - -/* End of pcre_xclass.c */ diff --git a/src/third_party/pcre-8.38/pcrecpp.cc b/src/third_party/pcre-8.38/pcrecpp.cc deleted file mode 100644 index c595cbcab5c..00000000000 --- a/src/third_party/pcre-8.38/pcrecpp.cc +++ /dev/null @@ -1,924 +0,0 @@ -// Copyright (c) 2010, Google Inc. -// All rights reserved. -// -// Redistribution and use in source and binary forms, with or without -// modification, are permitted provided that the following conditions are -// met: -// -// * Redistributions of source code must retain the above copyright -// notice, this list of conditions and the following disclaimer. -// * Redistributions in binary form must reproduce the above -// copyright notice, this list of conditions and the following disclaimer -// in the documentation and/or other materials provided with the -// distribution. -// * Neither the name of Google Inc. nor the names of its -// contributors may be used to endorse or promote products derived from -// this software without specific prior written permission. -// -// THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS -// "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT -// LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR -// A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT -// OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, -// SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT -// LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, -// DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY -// THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT -// (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE -// OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE. -// -// Author: Sanjay Ghemawat - -#ifdef HAVE_CONFIG_H -#include "config.h" -#endif - -#include <stdlib.h> -#include <stdio.h> -#include <ctype.h> -#include <limits.h> /* for SHRT_MIN, USHRT_MAX, etc */ -#include <string.h> /* for memcpy */ -#include <assert.h> -#include <errno.h> -#include <string> -#include <algorithm> - -#include "pcrecpp_internal.h" -#include "pcre.h" -#include "pcrecpp.h" -#include "pcre_stringpiece.h" - - -namespace pcrecpp { - -// Maximum number of args we can set -static const int kMaxArgs = 16; -static const int kVecSize = (1 + kMaxArgs) * 3; // results + PCRE workspace - -// Special object that stands-in for no argument -Arg RE::no_arg((void*)NULL); - -// This is for ABI compatibility with old versions of pcre (pre-7.6), -// which defined a global no_arg variable instead of putting it in the -// RE class. This works on GCC >= 3, at least. It definitely works -// for ELF, but may not for other object formats (Mach-O, for -// instance, does not support aliases.) We could probably have a more -// inclusive test if we ever needed it. (Note that not only the -// __attribute__ syntax, but also __USER_LABEL_PREFIX__, are -// gnu-specific.) -#if defined(__GNUC__) && __GNUC__ >= 3 && defined(__ELF__) -# define ULP_AS_STRING(x) ULP_AS_STRING_INTERNAL(x) -# define ULP_AS_STRING_INTERNAL(x) #x -# define USER_LABEL_PREFIX_STR ULP_AS_STRING(__USER_LABEL_PREFIX__) -extern Arg no_arg - __attribute__((alias(USER_LABEL_PREFIX_STR "_ZN7pcrecpp2RE6no_argE"))); -#endif - -// If a regular expression has no error, its error_ field points here -static const string empty_string; - -// If the user doesn't ask for any options, we just use this one -static RE_Options default_options; - -void RE::Init(const string& pat, const RE_Options* options) { - pattern_ = pat; - if (options == NULL) { - options_ = default_options; - } else { - options_ = *options; - } - error_ = &empty_string; - re_full_ = NULL; - re_partial_ = NULL; - - re_partial_ = Compile(UNANCHORED); - if (re_partial_ != NULL) { - re_full_ = Compile(ANCHOR_BOTH); - } -} - -void RE::Cleanup() { - if (re_full_ != NULL) (*pcre_free)(re_full_); - if (re_partial_ != NULL) (*pcre_free)(re_partial_); - if (error_ != &empty_string) delete error_; -} - - -RE::~RE() { - Cleanup(); -} - - -pcre* RE::Compile(Anchor anchor) { - // First, convert RE_Options into pcre options - int pcre_options = 0; - pcre_options = options_.all_options(); - - // Special treatment for anchoring. This is needed because at - // runtime pcre only provides an option for anchoring at the - // beginning of a string (unless you use offset). - // - // There are three types of anchoring we want: - // UNANCHORED Compile the original pattern, and use - // a pcre unanchored match. - // ANCHOR_START Compile the original pattern, and use - // a pcre anchored match. - // ANCHOR_BOTH Tack a "\z" to the end of the original pattern - // and use a pcre anchored match. - - const char* compile_error; - int eoffset; - pcre* re; - if (anchor != ANCHOR_BOTH) { - re = pcre_compile(pattern_.c_str(), pcre_options, - &compile_error, &eoffset, NULL); - } else { - // Tack a '\z' at the end of RE. Parenthesize it first so that - // the '\z' applies to all top-level alternatives in the regexp. - string wrapped = "(?:"; // A non-counting grouping operator - wrapped += pattern_; - wrapped += ")\\z"; - re = pcre_compile(wrapped.c_str(), pcre_options, - &compile_error, &eoffset, NULL); - } - if (re == NULL) { - if (error_ == &empty_string) error_ = new string(compile_error); - } - return re; -} - -/***** Matching interfaces *****/ - -bool RE::FullMatch(const StringPiece& text, - const Arg& ptr1, - const Arg& ptr2, - const Arg& ptr3, - const Arg& ptr4, - const Arg& ptr5, - const Arg& ptr6, - const Arg& ptr7, - const Arg& ptr8, - const Arg& ptr9, - const Arg& ptr10, - const Arg& ptr11, - const Arg& ptr12, - const Arg& ptr13, - const Arg& ptr14, - const Arg& ptr15, - const Arg& ptr16) const { - const Arg* args[kMaxArgs]; - int n = 0; - if (&ptr1 == &no_arg) goto done; args[n++] = &ptr1; - if (&ptr2 == &no_arg) goto done; args[n++] = &ptr2; - if (&ptr3 == &no_arg) goto done; args[n++] = &ptr3; - if (&ptr4 == &no_arg) goto done; args[n++] = &ptr4; - if (&ptr5 == &no_arg) goto done; args[n++] = &ptr5; - if (&ptr6 == &no_arg) goto done; args[n++] = &ptr6; - if (&ptr7 == &no_arg) goto done; args[n++] = &ptr7; - if (&ptr8 == &no_arg) goto done; args[n++] = &ptr8; - if (&ptr9 == &no_arg) goto done; args[n++] = &ptr9; - if (&ptr10 == &no_arg) goto done; args[n++] = &ptr10; - if (&ptr11 == &no_arg) goto done; args[n++] = &ptr11; - if (&ptr12 == &no_arg) goto done; args[n++] = &ptr12; - if (&ptr13 == &no_arg) goto done; args[n++] = &ptr13; - if (&ptr14 == &no_arg) goto done; args[n++] = &ptr14; - if (&ptr15 == &no_arg) goto done; args[n++] = &ptr15; - if (&ptr16 == &no_arg) goto done; args[n++] = &ptr16; - done: - - int consumed; - int vec[kVecSize]; - return DoMatchImpl(text, ANCHOR_BOTH, &consumed, args, n, vec, kVecSize); -} - -bool RE::PartialMatch(const StringPiece& text, - const Arg& ptr1, - const Arg& ptr2, - const Arg& ptr3, - const Arg& ptr4, - const Arg& ptr5, - const Arg& ptr6, - const Arg& ptr7, - const Arg& ptr8, - const Arg& ptr9, - const Arg& ptr10, - const Arg& ptr11, - const Arg& ptr12, - const Arg& ptr13, - const Arg& ptr14, - const Arg& ptr15, - const Arg& ptr16) const { - const Arg* args[kMaxArgs]; - int n = 0; - if (&ptr1 == &no_arg) goto done; args[n++] = &ptr1; - if (&ptr2 == &no_arg) goto done; args[n++] = &ptr2; - if (&ptr3 == &no_arg) goto done; args[n++] = &ptr3; - if (&ptr4 == &no_arg) goto done; args[n++] = &ptr4; - if (&ptr5 == &no_arg) goto done; args[n++] = &ptr5; - if (&ptr6 == &no_arg) goto done; args[n++] = &ptr6; - if (&ptr7 == &no_arg) goto done; args[n++] = &ptr7; - if (&ptr8 == &no_arg) goto done; args[n++] = &ptr8; - if (&ptr9 == &no_arg) goto done; args[n++] = &ptr9; - if (&ptr10 == &no_arg) goto done; args[n++] = &ptr10; - if (&ptr11 == &no_arg) goto done; args[n++] = &ptr11; - if (&ptr12 == &no_arg) goto done; args[n++] = &ptr12; - if (&ptr13 == &no_arg) goto done; args[n++] = &ptr13; - if (&ptr14 == &no_arg) goto done; args[n++] = &ptr14; - if (&ptr15 == &no_arg) goto done; args[n++] = &ptr15; - if (&ptr16 == &no_arg) goto done; args[n++] = &ptr16; - done: - - int consumed; - int vec[kVecSize]; - return DoMatchImpl(text, UNANCHORED, &consumed, args, n, vec, kVecSize); -} - -bool RE::Consume(StringPiece* input, - const Arg& ptr1, - const Arg& ptr2, - const Arg& ptr3, - const Arg& ptr4, - const Arg& ptr5, - const Arg& ptr6, - const Arg& ptr7, - const Arg& ptr8, - const Arg& ptr9, - const Arg& ptr10, - const Arg& ptr11, - const Arg& ptr12, - const Arg& ptr13, - const Arg& ptr14, - const Arg& ptr15, - const Arg& ptr16) const { - const Arg* args[kMaxArgs]; - int n = 0; - if (&ptr1 == &no_arg) goto done; args[n++] = &ptr1; - if (&ptr2 == &no_arg) goto done; args[n++] = &ptr2; - if (&ptr3 == &no_arg) goto done; args[n++] = &ptr3; - if (&ptr4 == &no_arg) goto done; args[n++] = &ptr4; - if (&ptr5 == &no_arg) goto done; args[n++] = &ptr5; - if (&ptr6 == &no_arg) goto done; args[n++] = &ptr6; - if (&ptr7 == &no_arg) goto done; args[n++] = &ptr7; - if (&ptr8 == &no_arg) goto done; args[n++] = &ptr8; - if (&ptr9 == &no_arg) goto done; args[n++] = &ptr9; - if (&ptr10 == &no_arg) goto done; args[n++] = &ptr10; - if (&ptr11 == &no_arg) goto done; args[n++] = &ptr11; - if (&ptr12 == &no_arg) goto done; args[n++] = &ptr12; - if (&ptr13 == &no_arg) goto done; args[n++] = &ptr13; - if (&ptr14 == &no_arg) goto done; args[n++] = &ptr14; - if (&ptr15 == &no_arg) goto done; args[n++] = &ptr15; - if (&ptr16 == &no_arg) goto done; args[n++] = &ptr16; - done: - - int consumed; - int vec[kVecSize]; - if (DoMatchImpl(*input, ANCHOR_START, &consumed, - args, n, vec, kVecSize)) { - input->remove_prefix(consumed); - return true; - } else { - return false; - } -} - -bool RE::FindAndConsume(StringPiece* input, - const Arg& ptr1, - const Arg& ptr2, - const Arg& ptr3, - const Arg& ptr4, - const Arg& ptr5, - const Arg& ptr6, - const Arg& ptr7, - const Arg& ptr8, - const Arg& ptr9, - const Arg& ptr10, - const Arg& ptr11, - const Arg& ptr12, - const Arg& ptr13, - const Arg& ptr14, - const Arg& ptr15, - const Arg& ptr16) const { - const Arg* args[kMaxArgs]; - int n = 0; - if (&ptr1 == &no_arg) goto done; args[n++] = &ptr1; - if (&ptr2 == &no_arg) goto done; args[n++] = &ptr2; - if (&ptr3 == &no_arg) goto done; args[n++] = &ptr3; - if (&ptr4 == &no_arg) goto done; args[n++] = &ptr4; - if (&ptr5 == &no_arg) goto done; args[n++] = &ptr5; - if (&ptr6 == &no_arg) goto done; args[n++] = &ptr6; - if (&ptr7 == &no_arg) goto done; args[n++] = &ptr7; - if (&ptr8 == &no_arg) goto done; args[n++] = &ptr8; - if (&ptr9 == &no_arg) goto done; args[n++] = &ptr9; - if (&ptr10 == &no_arg) goto done; args[n++] = &ptr10; - if (&ptr11 == &no_arg) goto done; args[n++] = &ptr11; - if (&ptr12 == &no_arg) goto done; args[n++] = &ptr12; - if (&ptr13 == &no_arg) goto done; args[n++] = &ptr13; - if (&ptr14 == &no_arg) goto done; args[n++] = &ptr14; - if (&ptr15 == &no_arg) goto done; args[n++] = &ptr15; - if (&ptr16 == &no_arg) goto done; args[n++] = &ptr16; - done: - - int consumed; - int vec[kVecSize]; - if (DoMatchImpl(*input, UNANCHORED, &consumed, - args, n, vec, kVecSize)) { - input->remove_prefix(consumed); - return true; - } else { - return false; - } -} - -bool RE::Replace(const StringPiece& rewrite, - string *str) const { - int vec[kVecSize]; - int matches = TryMatch(*str, 0, UNANCHORED, true, vec, kVecSize); - if (matches == 0) - return false; - - string s; - if (!Rewrite(&s, rewrite, *str, vec, matches)) - return false; - - assert(vec[0] >= 0); - assert(vec[1] >= 0); - str->replace(vec[0], vec[1] - vec[0], s); - return true; -} - -// Returns PCRE_NEWLINE_CRLF, PCRE_NEWLINE_CR, or PCRE_NEWLINE_LF. -// Note that PCRE_NEWLINE_CRLF is defined to be P_N_CR | P_N_LF. -// Modified by PH to add PCRE_NEWLINE_ANY and PCRE_NEWLINE_ANYCRLF. - -static int NewlineMode(int pcre_options) { - // TODO: if we can make it threadsafe, cache this var - int newline_mode = 0; - /* if (newline_mode) return newline_mode; */ // do this once it's cached - if (pcre_options & (PCRE_NEWLINE_CRLF|PCRE_NEWLINE_CR|PCRE_NEWLINE_LF| - PCRE_NEWLINE_ANY|PCRE_NEWLINE_ANYCRLF)) { - newline_mode = (pcre_options & - (PCRE_NEWLINE_CRLF|PCRE_NEWLINE_CR|PCRE_NEWLINE_LF| - PCRE_NEWLINE_ANY|PCRE_NEWLINE_ANYCRLF)); - } else { - int newline; - pcre_config(PCRE_CONFIG_NEWLINE, &newline); - if (newline == 10) - newline_mode = PCRE_NEWLINE_LF; - else if (newline == 13) - newline_mode = PCRE_NEWLINE_CR; - else if (newline == 3338) - newline_mode = PCRE_NEWLINE_CRLF; - else if (newline == -1) - newline_mode = PCRE_NEWLINE_ANY; - else if (newline == -2) - newline_mode = PCRE_NEWLINE_ANYCRLF; - else - assert(NULL == "Unexpected return value from pcre_config(NEWLINE)"); - } - return newline_mode; -} - -int RE::GlobalReplace(const StringPiece& rewrite, - string *str) const { - int count = 0; - int vec[kVecSize]; - string out; - int start = 0; - bool last_match_was_empty_string = false; - - while (start <= static_cast<int>(str->length())) { - // If the previous match was for the empty string, we shouldn't - // just match again: we'll match in the same way and get an - // infinite loop. Instead, we do the match in a special way: - // anchored -- to force another try at the same position -- - // and with a flag saying that this time, ignore empty matches. - // If this special match returns, that means there's a non-empty - // match at this position as well, and we can continue. If not, - // we do what perl does, and just advance by one. - // Notice that perl prints '@@@' for this; - // perl -le '$_ = "aa"; s/b*|aa/@/g; print' - int matches; - if (last_match_was_empty_string) { - matches = TryMatch(*str, start, ANCHOR_START, false, vec, kVecSize); - if (matches <= 0) { - int matchend = start + 1; // advance one character. - // If the current char is CR and we're in CRLF mode, skip LF too. - // Note it's better to call pcre_fullinfo() than to examine - // all_options(), since options_ could have changed bewteen - // compile-time and now, but this is simpler and safe enough. - // Modified by PH to add ANY and ANYCRLF. - if (matchend < static_cast<int>(str->length()) && - (*str)[start] == '\r' && (*str)[matchend] == '\n' && - (NewlineMode(options_.all_options()) == PCRE_NEWLINE_CRLF || - NewlineMode(options_.all_options()) == PCRE_NEWLINE_ANY || - NewlineMode(options_.all_options()) == PCRE_NEWLINE_ANYCRLF)) { - matchend++; - } - // We also need to advance more than one char if we're in utf8 mode. -#ifdef SUPPORT_UTF8 - if (options_.utf8()) { - while (matchend < static_cast<int>(str->length()) && - ((*str)[matchend] & 0xc0) == 0x80) - matchend++; - } -#endif - if (start < static_cast<int>(str->length())) - out.append(*str, start, matchend - start); - start = matchend; - last_match_was_empty_string = false; - continue; - } - } else { - matches = TryMatch(*str, start, UNANCHORED, true, vec, kVecSize); - if (matches <= 0) - break; - } - int matchstart = vec[0], matchend = vec[1]; - assert(matchstart >= start); - assert(matchend >= matchstart); - out.append(*str, start, matchstart - start); - Rewrite(&out, rewrite, *str, vec, matches); - start = matchend; - count++; - last_match_was_empty_string = (matchstart == matchend); - } - - if (count == 0) - return 0; - - if (start < static_cast<int>(str->length())) - out.append(*str, start, str->length() - start); - swap(out, *str); - return count; -} - -bool RE::Extract(const StringPiece& rewrite, - const StringPiece& text, - string *out) const { - int vec[kVecSize]; - int matches = TryMatch(text, 0, UNANCHORED, true, vec, kVecSize); - if (matches == 0) - return false; - out->erase(); - return Rewrite(out, rewrite, text, vec, matches); -} - -/*static*/ string RE::QuoteMeta(const StringPiece& unquoted) { - string result; - - // Escape any ascii character not in [A-Za-z_0-9]. - // - // Note that it's legal to escape a character even if it has no - // special meaning in a regular expression -- so this function does - // that. (This also makes it identical to the perl function of the - // same name; see `perldoc -f quotemeta`.) The one exception is - // escaping NUL: rather than doing backslash + NUL, like perl does, - // we do '\0', because pcre itself doesn't take embedded NUL chars. - for (int ii = 0; ii < unquoted.size(); ++ii) { - // Note that using 'isalnum' here raises the benchmark time from - // 32ns to 58ns: - if (unquoted[ii] == '\0') { - result += "\\0"; - } else if ((unquoted[ii] < 'a' || unquoted[ii] > 'z') && - (unquoted[ii] < 'A' || unquoted[ii] > 'Z') && - (unquoted[ii] < '0' || unquoted[ii] > '9') && - unquoted[ii] != '_' && - // If this is the part of a UTF8 or Latin1 character, we need - // to copy this byte without escaping. Experimentally this is - // what works correctly with the regexp library. - !(unquoted[ii] & 128)) { - result += '\\'; - result += unquoted[ii]; - } else { - result += unquoted[ii]; - } - } - - return result; -} - -/***** Actual matching and rewriting code *****/ - -int RE::TryMatch(const StringPiece& text, - int startpos, - Anchor anchor, - bool empty_ok, - int *vec, - int vecsize) const { - pcre* re = (anchor == ANCHOR_BOTH) ? re_full_ : re_partial_; - if (re == NULL) { - //fprintf(stderr, "Matching against invalid re: %s\n", error_->c_str()); - return 0; - } - - pcre_extra extra = { 0, 0, 0, 0, 0, 0, 0, 0 }; - if (options_.match_limit() > 0) { - extra.flags |= PCRE_EXTRA_MATCH_LIMIT; - extra.match_limit = options_.match_limit(); - } - if (options_.match_limit_recursion() > 0) { - extra.flags |= PCRE_EXTRA_MATCH_LIMIT_RECURSION; - extra.match_limit_recursion = options_.match_limit_recursion(); - } - - // int options = 0; - // Changed by PH as a result of bugzilla #1288 - int options = (options_.all_options() & PCRE_NO_UTF8_CHECK); - - if (anchor != UNANCHORED) - options |= PCRE_ANCHORED; - if (!empty_ok) - options |= PCRE_NOTEMPTY; - - int rc = pcre_exec(re, // The regular expression object - &extra, - (text.data() == NULL) ? "" : text.data(), - text.size(), - startpos, - options, - vec, - vecsize); - - // Handle errors - if (rc == PCRE_ERROR_NOMATCH) { - return 0; - } else if (rc < 0) { - //fprintf(stderr, "Unexpected return code: %d when matching '%s'\n", - // re, pattern_.c_str()); - return 0; - } else if (rc == 0) { - // pcre_exec() returns 0 as a special case when the number of - // capturing subpatterns exceeds the size of the vector. - // When this happens, there is a match and the output vector - // is filled, but we miss out on the positions of the extra subpatterns. - rc = vecsize / 2; - } - - return rc; -} - -bool RE::DoMatchImpl(const StringPiece& text, - Anchor anchor, - int* consumed, - const Arg* const* args, - int n, - int* vec, - int vecsize) const { - assert((1 + n) * 3 <= vecsize); // results + PCRE workspace - int matches = TryMatch(text, 0, anchor, true, vec, vecsize); - assert(matches >= 0); // TryMatch never returns negatives - if (matches == 0) - return false; - - *consumed = vec[1]; - - if (n == 0 || args == NULL) { - // We are not interested in results - return true; - } - - if (NumberOfCapturingGroups() < n) { - // RE has fewer capturing groups than number of arg pointers passed in - return false; - } - - // If we got here, we must have matched the whole pattern. - // We do not need (can not do) any more checks on the value of 'matches' here - // -- see the comment for TryMatch. - for (int i = 0; i < n; i++) { - const int start = vec[2*(i+1)]; - const int limit = vec[2*(i+1)+1]; - if (!args[i]->Parse(text.data() + start, limit-start)) { - // TODO: Should we indicate what the error was? - return false; - } - } - - return true; -} - -bool RE::DoMatch(const StringPiece& text, - Anchor anchor, - int* consumed, - const Arg* const args[], - int n) const { - assert(n >= 0); - size_t const vecsize = (1 + n) * 3; // results + PCRE workspace - // (as for kVecSize) - int space[21]; // use stack allocation for small vecsize (common case) - int* vec = vecsize <= 21 ? space : new int[vecsize]; - bool retval = DoMatchImpl(text, anchor, consumed, args, n, vec, (int)vecsize); - if (vec != space) delete [] vec; - return retval; -} - -bool RE::Rewrite(string *out, const StringPiece &rewrite, - const StringPiece &text, int *vec, int veclen) const { - for (const char *s = rewrite.data(), *end = s + rewrite.size(); - s < end; s++) { - int c = *s; - if (c == '\\') { - c = *++s; - if (isdigit(c)) { - int n = (c - '0'); - if (n >= veclen) { - //fprintf(stderr, requested group %d in regexp %.*s\n", - // n, rewrite.size(), rewrite.data()); - return false; - } - int start = vec[2 * n]; - if (start >= 0) - out->append(text.data() + start, vec[2 * n + 1] - start); - } else if (c == '\\') { - *out += '\\'; - } else { - //fprintf(stderr, "invalid rewrite pattern: %.*s\n", - // rewrite.size(), rewrite.data()); - return false; - } - } else { - *out += c; - } - } - return true; -} - -// Return the number of capturing subpatterns, or -1 if the -// regexp wasn't valid on construction. -int RE::NumberOfCapturingGroups() const { - if (re_partial_ == NULL) return -1; - - int result; - int pcre_retval = pcre_fullinfo(re_partial_, // The regular expression object - NULL, // We did not study the pattern - PCRE_INFO_CAPTURECOUNT, - &result); - assert(pcre_retval == 0); - return result; -} - -/***** Parsers for various types *****/ - -bool Arg::parse_null(const char* str, int n, void* dest) { - (void)str; - (void)n; - // We fail if somebody asked us to store into a non-NULL void* pointer - return (dest == NULL); -} - -bool Arg::parse_string(const char* str, int n, void* dest) { - if (dest == NULL) return true; - reinterpret_cast<string*>(dest)->assign(str, n); - return true; -} - -bool Arg::parse_stringpiece(const char* str, int n, void* dest) { - if (dest == NULL) return true; - reinterpret_cast<StringPiece*>(dest)->set(str, n); - return true; -} - -bool Arg::parse_char(const char* str, int n, void* dest) { - if (n != 1) return false; - if (dest == NULL) return true; - *(reinterpret_cast<char*>(dest)) = str[0]; - return true; -} - -bool Arg::parse_uchar(const char* str, int n, void* dest) { - if (n != 1) return false; - if (dest == NULL) return true; - *(reinterpret_cast<unsigned char*>(dest)) = str[0]; - return true; -} - -// Largest number spec that we are willing to parse -static const int kMaxNumberLength = 32; - -// REQUIRES "buf" must have length at least kMaxNumberLength+1 -// REQUIRES "n > 0" -// Copies "str" into "buf" and null-terminates if necessary. -// Returns one of: -// a. "str" if no termination is needed -// b. "buf" if the string was copied and null-terminated -// c. "" if the input was invalid and has no hope of being parsed -static const char* TerminateNumber(char* buf, const char* str, int n) { - if ((n > 0) && isspace(*str)) { - // We are less forgiving than the strtoxxx() routines and do not - // allow leading spaces. - return ""; - } - - // See if the character right after the input text may potentially - // look like a digit. - if (isdigit(str[n]) || - ((str[n] >= 'a') && (str[n] <= 'f')) || - ((str[n] >= 'A') && (str[n] <= 'F'))) { - if (n > kMaxNumberLength) return ""; // Input too big to be a valid number - memcpy(buf, str, n); - buf[n] = '\0'; - return buf; - } else { - // We can parse right out of the supplied string, so return it. - return str; - } -} - -bool Arg::parse_long_radix(const char* str, - int n, - void* dest, - int radix) { - if (n == 0) return false; - char buf[kMaxNumberLength+1]; - str = TerminateNumber(buf, str, n); - char* end; - errno = 0; - long r = strtol(str, &end, radix); - if (end != str + n) return false; // Leftover junk - if (errno) return false; - if (dest == NULL) return true; - *(reinterpret_cast<long*>(dest)) = r; - return true; -} - -bool Arg::parse_ulong_radix(const char* str, - int n, - void* dest, - int radix) { - if (n == 0) return false; - char buf[kMaxNumberLength+1]; - str = TerminateNumber(buf, str, n); - if (str[0] == '-') return false; // strtoul() on a negative number?! - char* end; - errno = 0; - unsigned long r = strtoul(str, &end, radix); - if (end != str + n) return false; // Leftover junk - if (errno) return false; - if (dest == NULL) return true; - *(reinterpret_cast<unsigned long*>(dest)) = r; - return true; -} - -bool Arg::parse_short_radix(const char* str, - int n, - void* dest, - int radix) { - long r; - if (!parse_long_radix(str, n, &r, radix)) return false; // Could not parse - if (r < SHRT_MIN || r > SHRT_MAX) return false; // Out of range - if (dest == NULL) return true; - *(reinterpret_cast<short*>(dest)) = static_cast<short>(r); - return true; -} - -bool Arg::parse_ushort_radix(const char* str, - int n, - void* dest, - int radix) { - unsigned long r; - if (!parse_ulong_radix(str, n, &r, radix)) return false; // Could not parse - if (r > USHRT_MAX) return false; // Out of range - if (dest == NULL) return true; - *(reinterpret_cast<unsigned short*>(dest)) = static_cast<unsigned short>(r); - return true; -} - -bool Arg::parse_int_radix(const char* str, - int n, - void* dest, - int radix) { - long r; - if (!parse_long_radix(str, n, &r, radix)) return false; // Could not parse - if (r < INT_MIN || r > INT_MAX) return false; // Out of range - if (dest == NULL) return true; - *(reinterpret_cast<int*>(dest)) = r; - return true; -} - -bool Arg::parse_uint_radix(const char* str, - int n, - void* dest, - int radix) { - unsigned long r; - if (!parse_ulong_radix(str, n, &r, radix)) return false; // Could not parse - if (r > UINT_MAX) return false; // Out of range - if (dest == NULL) return true; - *(reinterpret_cast<unsigned int*>(dest)) = r; - return true; -} - -bool Arg::parse_longlong_radix(const char* str, - int n, - void* dest, - int radix) { -#ifndef HAVE_LONG_LONG - return false; -#else - if (n == 0) return false; - char buf[kMaxNumberLength+1]; - str = TerminateNumber(buf, str, n); - char* end; - errno = 0; -#if defined HAVE_STRTOQ - long long r = strtoq(str, &end, radix); -#elif defined HAVE_STRTOLL - long long r = strtoll(str, &end, radix); -#elif defined HAVE__STRTOI64 - long long r = _strtoi64(str, &end, radix); -#elif defined HAVE_STRTOIMAX - long long r = strtoimax(str, &end, radix); -#else -#error parse_longlong_radix: cannot convert input to a long-long -#endif - if (end != str + n) return false; // Leftover junk - if (errno) return false; - if (dest == NULL) return true; - *(reinterpret_cast<long long*>(dest)) = r; - return true; -#endif /* HAVE_LONG_LONG */ -} - -bool Arg::parse_ulonglong_radix(const char* str, - int n, - void* dest, - int radix) { -#ifndef HAVE_UNSIGNED_LONG_LONG - return false; -#else - if (n == 0) return false; - char buf[kMaxNumberLength+1]; - str = TerminateNumber(buf, str, n); - if (str[0] == '-') return false; // strtoull() on a negative number?! - char* end; - errno = 0; -#if defined HAVE_STRTOQ - unsigned long long r = strtouq(str, &end, radix); -#elif defined HAVE_STRTOLL - unsigned long long r = strtoull(str, &end, radix); -#elif defined HAVE__STRTOI64 - unsigned long long r = _strtoui64(str, &end, radix); -#elif defined HAVE_STRTOIMAX - unsigned long long r = strtoumax(str, &end, radix); -#else -#error parse_ulonglong_radix: cannot convert input to a long-long -#endif - if (end != str + n) return false; // Leftover junk - if (errno) return false; - if (dest == NULL) return true; - *(reinterpret_cast<unsigned long long*>(dest)) = r; - return true; -#endif /* HAVE_UNSIGNED_LONG_LONG */ -} - -bool Arg::parse_double(const char* str, int n, void* dest) { - if (n == 0) return false; - static const int kMaxLength = 200; - char buf[kMaxLength]; - if (n >= kMaxLength) return false; - memcpy(buf, str, n); - buf[n] = '\0'; - errno = 0; - char* end; - double r = strtod(buf, &end); - if (end != buf + n) return false; // Leftover junk - if (errno) return false; - if (dest == NULL) return true; - *(reinterpret_cast<double*>(dest)) = r; - return true; -} - -bool Arg::parse_float(const char* str, int n, void* dest) { - double r; - if (!parse_double(str, n, &r)) return false; - if (dest == NULL) return true; - *(reinterpret_cast<float*>(dest)) = static_cast<float>(r); - return true; -} - - -#define DEFINE_INTEGER_PARSERS(name) \ - bool Arg::parse_##name(const char* str, int n, void* dest) { \ - return parse_##name##_radix(str, n, dest, 10); \ - } \ - bool Arg::parse_##name##_hex(const char* str, int n, void* dest) { \ - return parse_##name##_radix(str, n, dest, 16); \ - } \ - bool Arg::parse_##name##_octal(const char* str, int n, void* dest) { \ - return parse_##name##_radix(str, n, dest, 8); \ - } \ - bool Arg::parse_##name##_cradix(const char* str, int n, void* dest) { \ - return parse_##name##_radix(str, n, dest, 0); \ - } - -DEFINE_INTEGER_PARSERS(short) /* */ -DEFINE_INTEGER_PARSERS(ushort) /* */ -DEFINE_INTEGER_PARSERS(int) /* Don't use semicolons after these */ -DEFINE_INTEGER_PARSERS(uint) /* statements because they can cause */ -DEFINE_INTEGER_PARSERS(long) /* compiler warnings if the checking */ -DEFINE_INTEGER_PARSERS(ulong) /* level is turned up high enough. */ -DEFINE_INTEGER_PARSERS(longlong) /* */ -DEFINE_INTEGER_PARSERS(ulonglong) /* */ - -#undef DEFINE_INTEGER_PARSERS - -} // namespace pcrecpp diff --git a/src/third_party/pcre-8.38/pcrecpp.h b/src/third_party/pcre-8.38/pcrecpp.h deleted file mode 100644 index 3e594b0d439..00000000000 --- a/src/third_party/pcre-8.38/pcrecpp.h +++ /dev/null @@ -1,710 +0,0 @@ -// Copyright (c) 2005, Google Inc. -// All rights reserved. -// -// Redistribution and use in source and binary forms, with or without -// modification, are permitted provided that the following conditions are -// met: -// -// * Redistributions of source code must retain the above copyright -// notice, this list of conditions and the following disclaimer. -// * Redistributions in binary form must reproduce the above -// copyright notice, this list of conditions and the following disclaimer -// in the documentation and/or other materials provided with the -// distribution. -// * Neither the name of Google Inc. nor the names of its -// contributors may be used to endorse or promote products derived from -// this software without specific prior written permission. -// -// THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS -// "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT -// LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR -// A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT -// OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, -// SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT -// LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, -// DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY -// THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT -// (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE -// OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE. -// -// Author: Sanjay Ghemawat -// Support for PCRE_XXX modifiers added by Giuseppe Maxia, July 2005 - -#ifndef _PCRECPP_H -#define _PCRECPP_H - -// C++ interface to the pcre regular-expression library. RE supports -// Perl-style regular expressions (with extensions like \d, \w, \s, -// ...). -// -// ----------------------------------------------------------------------- -// REGEXP SYNTAX: -// -// This module is part of the pcre library and hence supports its syntax -// for regular expressions. -// -// The syntax is pretty similar to Perl's. For those not familiar -// with Perl's regular expressions, here are some examples of the most -// commonly used extensions: -// -// "hello (\\w+) world" -- \w matches a "word" character -// "version (\\d+)" -- \d matches a digit -// "hello\\s+world" -- \s matches any whitespace character -// "\\b(\\w+)\\b" -- \b matches empty string at a word boundary -// "(?i)hello" -- (?i) turns on case-insensitive matching -// "/\\*(.*?)\\*/" -- .*? matches . minimum no. of times possible -// -// ----------------------------------------------------------------------- -// MATCHING INTERFACE: -// -// The "FullMatch" operation checks that supplied text matches a -// supplied pattern exactly. -// -// Example: successful match -// pcrecpp::RE re("h.*o"); -// re.FullMatch("hello"); -// -// Example: unsuccessful match (requires full match): -// pcrecpp::RE re("e"); -// !re.FullMatch("hello"); -// -// Example: creating a temporary RE object: -// pcrecpp::RE("h.*o").FullMatch("hello"); -// -// You can pass in a "const char*" or a "string" for "text". The -// examples below tend to use a const char*. -// -// You can, as in the different examples above, store the RE object -// explicitly in a variable or use a temporary RE object. The -// examples below use one mode or the other arbitrarily. Either -// could correctly be used for any of these examples. -// -// ----------------------------------------------------------------------- -// MATCHING WITH SUB-STRING EXTRACTION: -// -// You can supply extra pointer arguments to extract matched subpieces. -// -// Example: extracts "ruby" into "s" and 1234 into "i" -// int i; -// string s; -// pcrecpp::RE re("(\\w+):(\\d+)"); -// re.FullMatch("ruby:1234", &s, &i); -// -// Example: does not try to extract any extra sub-patterns -// re.FullMatch("ruby:1234", &s); -// -// Example: does not try to extract into NULL -// re.FullMatch("ruby:1234", NULL, &i); -// -// Example: integer overflow causes failure -// !re.FullMatch("ruby:1234567891234", NULL, &i); -// -// Example: fails because there aren't enough sub-patterns: -// !pcrecpp::RE("\\w+:\\d+").FullMatch("ruby:1234", &s); -// -// Example: fails because string cannot be stored in integer -// !pcrecpp::RE("(.*)").FullMatch("ruby", &i); -// -// The provided pointer arguments can be pointers to any scalar numeric -// type, or one of -// string (matched piece is copied to string) -// StringPiece (StringPiece is mutated to point to matched piece) -// T (where "bool T::ParseFrom(const char*, int)" exists) -// NULL (the corresponding matched sub-pattern is not copied) -// -// CAVEAT: An optional sub-pattern that does not exist in the matched -// string is assigned the empty string. Therefore, the following will -// return false (because the empty string is not a valid number): -// int number; -// pcrecpp::RE::FullMatch("abc", "[a-z]+(\\d+)?", &number); -// -// ----------------------------------------------------------------------- -// DO_MATCH -// -// The matching interface supports at most 16 arguments per call. -// If you need more, consider using the more general interface -// pcrecpp::RE::DoMatch(). See pcrecpp.h for the signature for DoMatch. -// -// ----------------------------------------------------------------------- -// PARTIAL MATCHES -// -// You can use the "PartialMatch" operation when you want the pattern -// to match any substring of the text. -// -// Example: simple search for a string: -// pcrecpp::RE("ell").PartialMatch("hello"); -// -// Example: find first number in a string: -// int number; -// pcrecpp::RE re("(\\d+)"); -// re.PartialMatch("x*100 + 20", &number); -// assert(number == 100); -// -// ----------------------------------------------------------------------- -// UTF-8 AND THE MATCHING INTERFACE: -// -// By default, pattern and text are plain text, one byte per character. -// The UTF8 flag, passed to the constructor, causes both pattern -// and string to be treated as UTF-8 text, still a byte stream but -// potentially multiple bytes per character. In practice, the text -// is likelier to be UTF-8 than the pattern, but the match returned -// may depend on the UTF8 flag, so always use it when matching -// UTF8 text. E.g., "." will match one byte normally but with UTF8 -// set may match up to three bytes of a multi-byte character. -// -// Example: -// pcrecpp::RE_Options options; -// options.set_utf8(); -// pcrecpp::RE re(utf8_pattern, options); -// re.FullMatch(utf8_string); -// -// Example: using the convenience function UTF8(): -// pcrecpp::RE re(utf8_pattern, pcrecpp::UTF8()); -// re.FullMatch(utf8_string); -// -// NOTE: The UTF8 option is ignored if pcre was not configured with the -// --enable-utf8 flag. -// -// ----------------------------------------------------------------------- -// PASSING MODIFIERS TO THE REGULAR EXPRESSION ENGINE -// -// PCRE defines some modifiers to change the behavior of the regular -// expression engine. -// The C++ wrapper defines an auxiliary class, RE_Options, as a vehicle -// to pass such modifiers to a RE class. -// -// Currently, the following modifiers are supported -// -// modifier description Perl corresponding -// -// PCRE_CASELESS case insensitive match /i -// PCRE_MULTILINE multiple lines match /m -// PCRE_DOTALL dot matches newlines /s -// PCRE_DOLLAR_ENDONLY $ matches only at end N/A -// PCRE_EXTRA strict escape parsing N/A -// PCRE_EXTENDED ignore whitespaces /x -// PCRE_UTF8 handles UTF8 chars built-in -// PCRE_UNGREEDY reverses * and *? N/A -// PCRE_NO_AUTO_CAPTURE disables matching parens N/A (*) -// -// (For a full account on how each modifier works, please check the -// PCRE API reference manual). -// -// (*) Both Perl and PCRE allow non matching parentheses by means of the -// "?:" modifier within the pattern itself. e.g. (?:ab|cd) does not -// capture, while (ab|cd) does. -// -// For each modifier, there are two member functions whose name is made -// out of the modifier in lowercase, without the "PCRE_" prefix. For -// instance, PCRE_CASELESS is handled by -// bool caseless(), -// which returns true if the modifier is set, and -// RE_Options & set_caseless(bool), -// which sets or unsets the modifier. -// -// Moreover, PCRE_EXTRA_MATCH_LIMIT can be accessed through the -// set_match_limit() and match_limit() member functions. -// Setting match_limit to a non-zero value will limit the executation of -// pcre to keep it from doing bad things like blowing the stack or taking -// an eternity to return a result. A value of 5000 is good enough to stop -// stack blowup in a 2MB thread stack. Setting match_limit to zero will -// disable match limiting. Alternately, you can set match_limit_recursion() -// which uses PCRE_EXTRA_MATCH_LIMIT_RECURSION to limit how much pcre -// recurses. match_limit() caps the number of matches pcre does; -// match_limit_recrusion() caps the depth of recursion. -// -// Normally, to pass one or more modifiers to a RE class, you declare -// a RE_Options object, set the appropriate options, and pass this -// object to a RE constructor. Example: -// -// RE_options opt; -// opt.set_caseless(true); -// -// if (RE("HELLO", opt).PartialMatch("hello world")) ... -// -// RE_options has two constructors. The default constructor takes no -// arguments and creates a set of flags that are off by default. -// -// The optional parameter 'option_flags' is to facilitate transfer -// of legacy code from C programs. This lets you do -// RE(pattern, RE_Options(PCRE_CASELESS|PCRE_MULTILINE)).PartialMatch(str); -// -// But new code is better off doing -// RE(pattern, -// RE_Options().set_caseless(true).set_multiline(true)).PartialMatch(str); -// (See below) -// -// If you are going to pass one of the most used modifiers, there are some -// convenience functions that return a RE_Options class with the -// appropriate modifier already set: -// CASELESS(), UTF8(), MULTILINE(), DOTALL(), EXTENDED() -// -// If you need to set several options at once, and you don't want to go -// through the pains of declaring a RE_Options object and setting several -// options, there is a parallel method that give you such ability on the -// fly. You can concatenate several set_xxxxx member functions, since each -// of them returns a reference to its class object. e.g.: to pass -// PCRE_CASELESS, PCRE_EXTENDED, and PCRE_MULTILINE to a RE with one -// statement, you may write -// -// RE(" ^ xyz \\s+ .* blah$", RE_Options() -// .set_caseless(true) -// .set_extended(true) -// .set_multiline(true)).PartialMatch(sometext); -// -// ----------------------------------------------------------------------- -// SCANNING TEXT INCREMENTALLY -// -// The "Consume" operation may be useful if you want to repeatedly -// match regular expressions at the front of a string and skip over -// them as they match. This requires use of the "StringPiece" type, -// which represents a sub-range of a real string. Like RE, StringPiece -// is defined in the pcrecpp namespace. -// -// Example: read lines of the form "var = value" from a string. -// string contents = ...; // Fill string somehow -// pcrecpp::StringPiece input(contents); // Wrap in a StringPiece -// -// string var; -// int value; -// pcrecpp::RE re("(\\w+) = (\\d+)\n"); -// while (re.Consume(&input, &var, &value)) { -// ...; -// } -// -// Each successful call to "Consume" will set "var/value", and also -// advance "input" so it points past the matched text. -// -// The "FindAndConsume" operation is similar to "Consume" but does not -// anchor your match at the beginning of the string. For example, you -// could extract all words from a string by repeatedly calling -// pcrecpp::RE("(\\w+)").FindAndConsume(&input, &word) -// -// ----------------------------------------------------------------------- -// PARSING HEX/OCTAL/C-RADIX NUMBERS -// -// By default, if you pass a pointer to a numeric value, the -// corresponding text is interpreted as a base-10 number. You can -// instead wrap the pointer with a call to one of the operators Hex(), -// Octal(), or CRadix() to interpret the text in another base. The -// CRadix operator interprets C-style "0" (base-8) and "0x" (base-16) -// prefixes, but defaults to base-10. -// -// Example: -// int a, b, c, d; -// pcrecpp::RE re("(.*) (.*) (.*) (.*)"); -// re.FullMatch("100 40 0100 0x40", -// pcrecpp::Octal(&a), pcrecpp::Hex(&b), -// pcrecpp::CRadix(&c), pcrecpp::CRadix(&d)); -// will leave 64 in a, b, c, and d. -// -// ----------------------------------------------------------------------- -// REPLACING PARTS OF STRINGS -// -// You can replace the first match of "pattern" in "str" with -// "rewrite". Within "rewrite", backslash-escaped digits (\1 to \9) -// can be used to insert text matching corresponding parenthesized -// group from the pattern. \0 in "rewrite" refers to the entire -// matching text. E.g., -// -// string s = "yabba dabba doo"; -// pcrecpp::RE("b+").Replace("d", &s); -// -// will leave "s" containing "yada dabba doo". The result is true if -// the pattern matches and a replacement occurs, or false otherwise. -// -// GlobalReplace() is like Replace(), except that it replaces all -// occurrences of the pattern in the string with the rewrite. -// Replacements are not subject to re-matching. E.g., -// -// string s = "yabba dabba doo"; -// pcrecpp::RE("b+").GlobalReplace("d", &s); -// -// will leave "s" containing "yada dada doo". It returns the number -// of replacements made. -// -// Extract() is like Replace(), except that if the pattern matches, -// "rewrite" is copied into "out" (an additional argument) with -// substitutions. The non-matching portions of "text" are ignored. -// Returns true iff a match occurred and the extraction happened -// successfully. If no match occurs, the string is left unaffected. - - -#include <string> -#include <pcre.h> -#include <pcrecpparg.h> // defines the Arg class -// This isn't technically needed here, but we include it -// anyway so folks who include pcrecpp.h don't have to. -#include <pcre_stringpiece.h> - -namespace pcrecpp { - -#define PCRE_SET_OR_CLEAR(b, o) \ - if (b) all_options_ |= (o); else all_options_ &= ~(o); \ - return *this - -#define PCRE_IS_SET(o) \ - (all_options_ & o) == o - -/***** Compiling regular expressions: the RE class *****/ - -// RE_Options allow you to set options to be passed along to pcre, -// along with other options we put on top of pcre. -// Only 9 modifiers, plus match_limit and match_limit_recursion, -// are supported now. -class PCRECPP_EXP_DEFN RE_Options { - public: - // constructor - RE_Options() : match_limit_(0), match_limit_recursion_(0), all_options_(0) {} - - // alternative constructor. - // To facilitate transfer of legacy code from C programs - // - // This lets you do - // RE(pattern, RE_Options(PCRE_CASELESS|PCRE_MULTILINE)).PartialMatch(str); - // But new code is better off doing - // RE(pattern, - // RE_Options().set_caseless(true).set_multiline(true)).PartialMatch(str); - RE_Options(int option_flags) : match_limit_(0), match_limit_recursion_(0), - all_options_(option_flags) {} - // we're fine with the default destructor, copy constructor, etc. - - // accessors and mutators - int match_limit() const { return match_limit_; }; - RE_Options &set_match_limit(int limit) { - match_limit_ = limit; - return *this; - } - - int match_limit_recursion() const { return match_limit_recursion_; }; - RE_Options &set_match_limit_recursion(int limit) { - match_limit_recursion_ = limit; - return *this; - } - - bool caseless() const { - return PCRE_IS_SET(PCRE_CASELESS); - } - RE_Options &set_caseless(bool x) { - PCRE_SET_OR_CLEAR(x, PCRE_CASELESS); - } - - bool multiline() const { - return PCRE_IS_SET(PCRE_MULTILINE); - } - RE_Options &set_multiline(bool x) { - PCRE_SET_OR_CLEAR(x, PCRE_MULTILINE); - } - - bool dotall() const { - return PCRE_IS_SET(PCRE_DOTALL); - } - RE_Options &set_dotall(bool x) { - PCRE_SET_OR_CLEAR(x, PCRE_DOTALL); - } - - bool extended() const { - return PCRE_IS_SET(PCRE_EXTENDED); - } - RE_Options &set_extended(bool x) { - PCRE_SET_OR_CLEAR(x, PCRE_EXTENDED); - } - - bool dollar_endonly() const { - return PCRE_IS_SET(PCRE_DOLLAR_ENDONLY); - } - RE_Options &set_dollar_endonly(bool x) { - PCRE_SET_OR_CLEAR(x, PCRE_DOLLAR_ENDONLY); - } - - bool extra() const { - return PCRE_IS_SET(PCRE_EXTRA); - } - RE_Options &set_extra(bool x) { - PCRE_SET_OR_CLEAR(x, PCRE_EXTRA); - } - - bool ungreedy() const { - return PCRE_IS_SET(PCRE_UNGREEDY); - } - RE_Options &set_ungreedy(bool x) { - PCRE_SET_OR_CLEAR(x, PCRE_UNGREEDY); - } - - bool utf8() const { - return PCRE_IS_SET(PCRE_UTF8); - } - RE_Options &set_utf8(bool x) { - PCRE_SET_OR_CLEAR(x, PCRE_UTF8); - } - - bool no_auto_capture() const { - return PCRE_IS_SET(PCRE_NO_AUTO_CAPTURE); - } - RE_Options &set_no_auto_capture(bool x) { - PCRE_SET_OR_CLEAR(x, PCRE_NO_AUTO_CAPTURE); - } - - RE_Options &set_all_options(int opt) { - all_options_ = opt; - return *this; - } - int all_options() const { - return all_options_ ; - } - - // TODO: add other pcre flags - - private: - int match_limit_; - int match_limit_recursion_; - int all_options_; -}; - -// These functions return some common RE_Options -static inline RE_Options UTF8() { - return RE_Options().set_utf8(true); -} - -static inline RE_Options CASELESS() { - return RE_Options().set_caseless(true); -} -static inline RE_Options MULTILINE() { - return RE_Options().set_multiline(true); -} - -static inline RE_Options DOTALL() { - return RE_Options().set_dotall(true); -} - -static inline RE_Options EXTENDED() { - return RE_Options().set_extended(true); -} - -// Interface for regular expression matching. Also corresponds to a -// pre-compiled regular expression. An "RE" object is safe for -// concurrent use by multiple threads. -class PCRECPP_EXP_DEFN RE { - public: - // We provide implicit conversions from strings so that users can - // pass in a string or a "const char*" wherever an "RE" is expected. - RE(const string& pat) { Init(pat, NULL); } - RE(const string& pat, const RE_Options& option) { Init(pat, &option); } - RE(const char* pat) { Init(pat, NULL); } - RE(const char* pat, const RE_Options& option) { Init(pat, &option); } - RE(const unsigned char* pat) { - Init(reinterpret_cast<const char*>(pat), NULL); - } - RE(const unsigned char* pat, const RE_Options& option) { - Init(reinterpret_cast<const char*>(pat), &option); - } - - // Copy constructor & assignment - note that these are expensive - // because they recompile the expression. - RE(const RE& re) { Init(re.pattern_, &re.options_); } - const RE& operator=(const RE& re) { - if (this != &re) { - Cleanup(); - - // This is the code that originally came from Google - // Init(re.pattern_.c_str(), &re.options_); - - // This is the replacement from Ari Pollak - Init(re.pattern_, &re.options_); - } - return *this; - } - - - ~RE(); - - // The string specification for this RE. E.g. - // RE re("ab*c?d+"); - // re.pattern(); // "ab*c?d+" - const string& pattern() const { return pattern_; } - - // If RE could not be created properly, returns an error string. - // Else returns the empty string. - const string& error() const { return *error_; } - - /***** The useful part: the matching interface *****/ - - // This is provided so one can do pattern.ReplaceAll() just as - // easily as ReplaceAll(pattern-text, ....) - - bool FullMatch(const StringPiece& text, - const Arg& ptr1 = no_arg, - const Arg& ptr2 = no_arg, - const Arg& ptr3 = no_arg, - const Arg& ptr4 = no_arg, - const Arg& ptr5 = no_arg, - const Arg& ptr6 = no_arg, - const Arg& ptr7 = no_arg, - const Arg& ptr8 = no_arg, - const Arg& ptr9 = no_arg, - const Arg& ptr10 = no_arg, - const Arg& ptr11 = no_arg, - const Arg& ptr12 = no_arg, - const Arg& ptr13 = no_arg, - const Arg& ptr14 = no_arg, - const Arg& ptr15 = no_arg, - const Arg& ptr16 = no_arg) const; - - bool PartialMatch(const StringPiece& text, - const Arg& ptr1 = no_arg, - const Arg& ptr2 = no_arg, - const Arg& ptr3 = no_arg, - const Arg& ptr4 = no_arg, - const Arg& ptr5 = no_arg, - const Arg& ptr6 = no_arg, - const Arg& ptr7 = no_arg, - const Arg& ptr8 = no_arg, - const Arg& ptr9 = no_arg, - const Arg& ptr10 = no_arg, - const Arg& ptr11 = no_arg, - const Arg& ptr12 = no_arg, - const Arg& ptr13 = no_arg, - const Arg& ptr14 = no_arg, - const Arg& ptr15 = no_arg, - const Arg& ptr16 = no_arg) const; - - bool Consume(StringPiece* input, - const Arg& ptr1 = no_arg, - const Arg& ptr2 = no_arg, - const Arg& ptr3 = no_arg, - const Arg& ptr4 = no_arg, - const Arg& ptr5 = no_arg, - const Arg& ptr6 = no_arg, - const Arg& ptr7 = no_arg, - const Arg& ptr8 = no_arg, - const Arg& ptr9 = no_arg, - const Arg& ptr10 = no_arg, - const Arg& ptr11 = no_arg, - const Arg& ptr12 = no_arg, - const Arg& ptr13 = no_arg, - const Arg& ptr14 = no_arg, - const Arg& ptr15 = no_arg, - const Arg& ptr16 = no_arg) const; - - bool FindAndConsume(StringPiece* input, - const Arg& ptr1 = no_arg, - const Arg& ptr2 = no_arg, - const Arg& ptr3 = no_arg, - const Arg& ptr4 = no_arg, - const Arg& ptr5 = no_arg, - const Arg& ptr6 = no_arg, - const Arg& ptr7 = no_arg, - const Arg& ptr8 = no_arg, - const Arg& ptr9 = no_arg, - const Arg& ptr10 = no_arg, - const Arg& ptr11 = no_arg, - const Arg& ptr12 = no_arg, - const Arg& ptr13 = no_arg, - const Arg& ptr14 = no_arg, - const Arg& ptr15 = no_arg, - const Arg& ptr16 = no_arg) const; - - bool Replace(const StringPiece& rewrite, - string *str) const; - - int GlobalReplace(const StringPiece& rewrite, - string *str) const; - - bool Extract(const StringPiece &rewrite, - const StringPiece &text, - string *out) const; - - // Escapes all potentially meaningful regexp characters in - // 'unquoted'. The returned string, used as a regular expression, - // will exactly match the original string. For example, - // 1.5-2.0? - // may become: - // 1\.5\-2\.0\? - // Note QuoteMeta behaves the same as perl's QuoteMeta function, - // *except* that it escapes the NUL character (\0) as backslash + 0, - // rather than backslash + NUL. - static string QuoteMeta(const StringPiece& unquoted); - - - /***** Generic matching interface *****/ - - // Type of match (TODO: Should be restructured as part of RE_Options) - enum Anchor { - UNANCHORED, // No anchoring - ANCHOR_START, // Anchor at start only - ANCHOR_BOTH // Anchor at start and end - }; - - // General matching routine. Stores the length of the match in - // "*consumed" if successful. - bool DoMatch(const StringPiece& text, - Anchor anchor, - int* consumed, - const Arg* const* args, int n) const; - - // Return the number of capturing subpatterns, or -1 if the - // regexp wasn't valid on construction. - int NumberOfCapturingGroups() const; - - // The default value for an argument, to indicate the end of the argument - // list. This must be used only in optional argument defaults. It should NOT - // be passed explicitly. Some people have tried to use it like this: - // - // FullMatch(x, y, &z, no_arg, &w); - // - // This is a mistake, and will not work. - static Arg no_arg; - - private: - - void Init(const string& pattern, const RE_Options* options); - void Cleanup(); - - // Match against "text", filling in "vec" (up to "vecsize" * 2/3) with - // pairs of integers for the beginning and end positions of matched - // text. The first pair corresponds to the entire matched text; - // subsequent pairs correspond, in order, to parentheses-captured - // matches. Returns the number of pairs (one more than the number of - // the last subpattern with a match) if matching was successful - // and zero if the match failed. - // I.e. for RE("(foo)|(bar)|(baz)") it will return 2, 3, and 4 when matching - // against "foo", "bar", and "baz" respectively. - // When matching RE("(foo)|hello") against "hello", it will return 1. - // But the values for all subpattern are filled in into "vec". - int TryMatch(const StringPiece& text, - int startpos, - Anchor anchor, - bool empty_ok, - int *vec, - int vecsize) const; - - // Append the "rewrite" string, with backslash subsitutions from "text" - // and "vec", to string "out". - bool Rewrite(string *out, - const StringPiece& rewrite, - const StringPiece& text, - int *vec, - int veclen) const; - - // internal implementation for DoMatch - bool DoMatchImpl(const StringPiece& text, - Anchor anchor, - int* consumed, - const Arg* const args[], - int n, - int* vec, - int vecsize) const; - - // Compile the regexp for the specified anchoring mode - pcre* Compile(Anchor anchor); - - string pattern_; - RE_Options options_; - pcre* re_full_; // For full matches - pcre* re_partial_; // For partial matches - const string* error_; // Error indicator (or points to empty string) -}; - -} // namespace pcrecpp - -#endif /* _PCRECPP_H */ diff --git a/src/third_party/pcre-8.38/pcrecpp_internal.h b/src/third_party/pcre-8.38/pcrecpp_internal.h deleted file mode 100644 index 827f9e04e2a..00000000000 --- a/src/third_party/pcre-8.38/pcrecpp_internal.h +++ /dev/null @@ -1,71 +0,0 @@ -/************************************************* -* Perl-Compatible Regular Expressions * -*************************************************/ - -/* -Copyright (c) 2005, Google Inc. -All rights reserved. - ------------------------------------------------------------------------------ -Redistribution and use in source and binary forms, with or without -modification, are permitted provided that the following conditions are met: - - * Redistributions of source code must retain the above copyright notice, - this list of conditions and the following disclaimer. - - * Redistributions in binary form must reproduce the above copyright - notice, this list of conditions and the following disclaimer in the - documentation and/or other materials provided with the distribution. - - * Neither the name of the University of Cambridge nor the names of its - contributors may be used to endorse or promote products derived from - this software without specific prior written permission. - -THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS" -AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE -IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE -ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR CONTRIBUTORS BE -LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR -CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF -SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS -INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN -CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) -ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE -POSSIBILITY OF SUCH DAMAGE. ------------------------------------------------------------------------------ -*/ - - -#ifndef PCRECPP_INTERNAL_H -#define PCRECPP_INTERNAL_H - -/* When compiling a DLL for Windows, the exported symbols have to be declared -using some MS magic. I found some useful information on this web page: -http://msdn2.microsoft.com/en-us/library/y4h7bcy6(VS.80).aspx. According to the -information there, using __declspec(dllexport) without "extern" we have a -definition; with "extern" we have a declaration. The settings here override the -setting in pcre.h. We use: - - PCRECPP_EXP_DECL for declarations - PCRECPP_EXP_DEFN for definitions of exported functions - -*/ - -#ifndef PCRECPP_EXP_DECL -# ifdef _WIN32 -# ifndef PCRE_STATIC -# define PCRECPP_EXP_DECL extern __declspec(dllexport) -# define PCRECPP_EXP_DEFN __declspec(dllexport) -# else -# define PCRECPP_EXP_DECL extern -# define PCRECPP_EXP_DEFN -# endif -# else -# define PCRECPP_EXP_DECL extern -# define PCRECPP_EXP_DEFN -# endif -#endif - -#endif /* PCRECPP_INTERNAL_H */ - -/* End of pcrecpp_internal.h */ diff --git a/src/third_party/pcre-8.38/pcrecpp_unittest.cc b/src/third_party/pcre-8.38/pcrecpp_unittest.cc deleted file mode 100644 index 92cae8fbea5..00000000000 --- a/src/third_party/pcre-8.38/pcrecpp_unittest.cc +++ /dev/null @@ -1,1291 +0,0 @@ -// -*- coding: utf-8 -*- -// -// Copyright (c) 2005 - 2010, Google Inc. -// All rights reserved. -// -// Redistribution and use in source and binary forms, with or without -// modification, are permitted provided that the following conditions are -// met: -// -// * Redistributions of source code must retain the above copyright -// notice, this list of conditions and the following disclaimer. -// * Redistributions in binary form must reproduce the above -// copyright notice, this list of conditions and the following disclaimer -// in the documentation and/or other materials provided with the -// distribution. -// * Neither the name of Google Inc. nor the names of its -// contributors may be used to endorse or promote products derived from -// this software without specific prior written permission. -// -// THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS -// "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT -// LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR -// A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT -// OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, -// SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT -// LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, -// DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY -// THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT -// (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE -// OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE. -// -// Author: Sanjay Ghemawat -// -// TODO: Test extractions for PartialMatch/Consume - -#ifdef HAVE_CONFIG_H -#include "config.h" -#endif - -#include <stdio.h> -#include <string.h> /* for memset and strcmp */ -#include <cassert> -#include <vector> -#include "pcrecpp.h" - -using pcrecpp::StringPiece; -using pcrecpp::RE; -using pcrecpp::RE_Options; -using pcrecpp::Hex; -using pcrecpp::Octal; -using pcrecpp::CRadix; - -static bool VERBOSE_TEST = false; - -// CHECK dies with a fatal error if condition is not true. It is *not* -// controlled by NDEBUG, so the check will be executed regardless of -// compilation mode. Therefore, it is safe to do things like: -// CHECK_EQ(fp->Write(x), 4) -#define CHECK(condition) do { \ - if (!(condition)) { \ - fprintf(stderr, "%s:%d: Check failed: %s\n", \ - __FILE__, __LINE__, #condition); \ - exit(1); \ - } \ -} while (0) - -#define CHECK_EQ(a, b) CHECK(a == b) - -static void Timing1(int num_iters) { - // Same pattern lots of times - RE pattern("ruby:\\d+"); - StringPiece p("ruby:1234"); - for (int j = num_iters; j > 0; j--) { - CHECK(pattern.FullMatch(p)); - } -} - -static void Timing2(int num_iters) { - // Same pattern lots of times - RE pattern("ruby:(\\d+)"); - int i; - for (int j = num_iters; j > 0; j--) { - CHECK(pattern.FullMatch("ruby:1234", &i)); - CHECK_EQ(i, 1234); - } -} - -static void Timing3(int num_iters) { - string text_string; - for (int j = num_iters; j > 0; j--) { - text_string += "this is another line\n"; - } - - RE line_matcher(".*\n"); - string line; - StringPiece text(text_string); - int counter = 0; - while (line_matcher.Consume(&text)) { - counter++; - } - printf("Matched %d lines\n", counter); -} - -#if 0 // uncomment this if you have a way of defining VirtualProcessSize() - -static void LeakTest() { - // Check for memory leaks - unsigned long long initial_size = 0; - for (int i = 0; i < 100000; i++) { - if (i == 50000) { - initial_size = VirtualProcessSize(); - printf("Size after 50000: %llu\n", initial_size); - } - char buf[100]; // definitely big enough - sprintf(buf, "pat%09d", i); - RE newre(buf); - } - uint64 final_size = VirtualProcessSize(); - printf("Size after 100000: %llu\n", final_size); - const double growth = double(final_size - initial_size) / final_size; - printf("Growth: %0.2f%%", growth * 100); - CHECK(growth < 0.02); // Allow < 2% growth -} - -#endif - -static void RadixTests() { - printf("Testing hex\n"); - -#define CHECK_HEX(type, value) \ - do { \ - type v; \ - CHECK(RE("([0-9a-fA-F]+)[uUlL]*").FullMatch(#value, Hex(&v))); \ - CHECK_EQ(v, 0x ## value); \ - CHECK(RE("([0-9a-fA-FxX]+)[uUlL]*").FullMatch("0x" #value, CRadix(&v))); \ - CHECK_EQ(v, 0x ## value); \ - } while(0) - - CHECK_HEX(short, 2bad); - CHECK_HEX(unsigned short, 2badU); - CHECK_HEX(int, dead); - CHECK_HEX(unsigned int, deadU); - CHECK_HEX(long, 7eadbeefL); - CHECK_HEX(unsigned long, deadbeefUL); -#ifdef HAVE_LONG_LONG - CHECK_HEX(long long, 12345678deadbeefLL); -#endif -#ifdef HAVE_UNSIGNED_LONG_LONG - CHECK_HEX(unsigned long long, cafebabedeadbeefULL); -#endif - -#undef CHECK_HEX - - printf("Testing octal\n"); - -#define CHECK_OCTAL(type, value) \ - do { \ - type v; \ - CHECK(RE("([0-7]+)[uUlL]*").FullMatch(#value, Octal(&v))); \ - CHECK_EQ(v, 0 ## value); \ - CHECK(RE("([0-9a-fA-FxX]+)[uUlL]*").FullMatch("0" #value, CRadix(&v))); \ - CHECK_EQ(v, 0 ## value); \ - } while(0) - - CHECK_OCTAL(short, 77777); - CHECK_OCTAL(unsigned short, 177777U); - CHECK_OCTAL(int, 17777777777); - CHECK_OCTAL(unsigned int, 37777777777U); - CHECK_OCTAL(long, 17777777777L); - CHECK_OCTAL(unsigned long, 37777777777UL); -#ifdef HAVE_LONG_LONG - CHECK_OCTAL(long long, 777777777777777777777LL); -#endif -#ifdef HAVE_UNSIGNED_LONG_LONG - CHECK_OCTAL(unsigned long long, 1777777777777777777777ULL); -#endif - -#undef CHECK_OCTAL - - printf("Testing decimal\n"); - -#define CHECK_DECIMAL(type, value) \ - do { \ - type v; \ - CHECK(RE("(-?[0-9]+)[uUlL]*").FullMatch(#value, &v)); \ - CHECK_EQ(v, value); \ - CHECK(RE("(-?[0-9a-fA-FxX]+)[uUlL]*").FullMatch(#value, CRadix(&v))); \ - CHECK_EQ(v, value); \ - } while(0) - - CHECK_DECIMAL(short, -1); - CHECK_DECIMAL(unsigned short, 9999); - CHECK_DECIMAL(int, -1000); - CHECK_DECIMAL(unsigned int, 12345U); - CHECK_DECIMAL(long, -10000000L); - CHECK_DECIMAL(unsigned long, 3083324652U); -#ifdef HAVE_LONG_LONG - CHECK_DECIMAL(long long, -100000000000000LL); -#endif -#ifdef HAVE_UNSIGNED_LONG_LONG - CHECK_DECIMAL(unsigned long long, 1234567890987654321ULL); -#endif - -#undef CHECK_DECIMAL - -} - -static void TestReplace() { - printf("Testing Replace\n"); - - struct ReplaceTest { - const char *regexp; - const char *rewrite; - const char *original; - const char *single; - const char *global; - int global_count; // the expected return value from ReplaceAll - }; - static const ReplaceTest tests[] = { - { "(qu|[b-df-hj-np-tv-z]*)([a-z]+)", - "\\2\\1ay", - "the quick brown fox jumps over the lazy dogs.", - "ethay quick brown fox jumps over the lazy dogs.", - "ethay ickquay ownbray oxfay umpsjay overay ethay azylay ogsday.", - 9 }, - { "\\w+", - "\\0-NOSPAM", - "paul.haahr@google.com", - "paul-NOSPAM.haahr@google.com", - "paul-NOSPAM.haahr-NOSPAM@google-NOSPAM.com-NOSPAM", - 4 }, - { "^", - "(START)", - "foo", - "(START)foo", - "(START)foo", - 1 }, - { "^", - "(START)", - "", - "(START)", - "(START)", - 1 }, - { "$", - "(END)", - "", - "(END)", - "(END)", - 1 }, - { "b", - "bb", - "ababababab", - "abbabababab", - "abbabbabbabbabb", - 5 }, - { "b", - "bb", - "bbbbbb", - "bbbbbbb", - "bbbbbbbbbbbb", - 6 }, - { "b+", - "bb", - "bbbbbb", - "bb", - "bb", - 1 }, - { "b*", - "bb", - "bbbbbb", - "bb", - "bbbb", - 2 }, - { "b*", - "bb", - "aaaaa", - "bbaaaaa", - "bbabbabbabbabbabb", - 6 }, - { "b*", - "bb", - "aa\naa\n", - "bbaa\naa\n", - "bbabbabb\nbbabbabb\nbb", - 7 }, - { "b*", - "bb", - "aa\raa\r", - "bbaa\raa\r", - "bbabbabb\rbbabbabb\rbb", - 7 }, - { "b*", - "bb", - "aa\r\naa\r\n", - "bbaa\r\naa\r\n", - "bbabbabb\r\nbbabbabb\r\nbb", - 7 }, - // Check empty-string matching (it's tricky!) - { "aa|b*", - "@", - "aa", - "@", - "@@", - 2 }, - { "b*|aa", - "@", - "aa", - "@aa", - "@@@", - 3 }, -#ifdef SUPPORT_UTF8 - { "b*", - "bb", - "\xE3\x83\x9B\xE3\x83\xBC\xE3\x83\xA0\xE3\x81\xB8", // utf8 - "bb\xE3\x83\x9B\xE3\x83\xBC\xE3\x83\xA0\xE3\x81\xB8", - "bb\xE3\x83\x9B""bb""\xE3\x83\xBC""bb""\xE3\x83\xA0""bb""\xE3\x81\xB8""bb", - 5 }, - { "b*", - "bb", - "\xE3\x83\x9B\r\n\xE3\x83\xBC\r\xE3\x83\xA0\n\xE3\x81\xB8\r\n", // utf8 - "bb\xE3\x83\x9B\r\n\xE3\x83\xBC\r\xE3\x83\xA0\n\xE3\x81\xB8\r\n", - ("bb\xE3\x83\x9B""bb\r\nbb""\xE3\x83\xBC""bb\rbb""\xE3\x83\xA0" - "bb\nbb""\xE3\x81\xB8""bb\r\nbb"), - 9 }, -#endif - { "", NULL, NULL, NULL, NULL, 0 } - }; - -#ifdef SUPPORT_UTF8 - const bool support_utf8 = true; -#else - const bool support_utf8 = false; -#endif - - for (const ReplaceTest *t = tests; t->original != NULL; ++t) { - RE re(t->regexp, RE_Options(PCRE_NEWLINE_CRLF).set_utf8(support_utf8)); - assert(re.error().empty()); - string one(t->original); - CHECK(re.Replace(t->rewrite, &one)); - CHECK_EQ(one, t->single); - string all(t->original); - const int replace_count = re.GlobalReplace(t->rewrite, &all); - CHECK_EQ(all, t->global); - CHECK_EQ(replace_count, t->global_count); - } - - // One final test: test \r\n replacement when we're not in CRLF mode - { - RE re("b*", RE_Options(PCRE_NEWLINE_CR).set_utf8(support_utf8)); - assert(re.error().empty()); - string all("aa\r\naa\r\n"); - CHECK_EQ(re.GlobalReplace("bb", &all), 9); - CHECK_EQ(all, string("bbabbabb\rbb\nbbabbabb\rbb\nbb")); - } - { - RE re("b*", RE_Options(PCRE_NEWLINE_LF).set_utf8(support_utf8)); - assert(re.error().empty()); - string all("aa\r\naa\r\n"); - CHECK_EQ(re.GlobalReplace("bb", &all), 9); - CHECK_EQ(all, string("bbabbabb\rbb\nbbabbabb\rbb\nbb")); - } - // TODO: test what happens when no PCRE_NEWLINE_* flag is set. - // Alas, the answer depends on how pcre was compiled. -} - -static void TestExtract() { - printf("Testing Extract\n"); - - string s; - - CHECK(RE("(.*)@([^.]*)").Extract("\\2!\\1", "boris@kremvax.ru", &s)); - CHECK_EQ(s, "kremvax!boris"); - - // check the RE interface as well - CHECK(RE(".*").Extract("'\\0'", "foo", &s)); - CHECK_EQ(s, "'foo'"); - CHECK(!RE("bar").Extract("'\\0'", "baz", &s)); - CHECK_EQ(s, "'foo'"); -} - -static void TestConsume() { - printf("Testing Consume\n"); - - string word; - - string s(" aaa b!@#$@#$cccc"); - StringPiece input(s); - - RE r("\\s*(\\w+)"); // matches a word, possibly proceeded by whitespace - CHECK(r.Consume(&input, &word)); - CHECK_EQ(word, "aaa"); - CHECK(r.Consume(&input, &word)); - CHECK_EQ(word, "b"); - CHECK(! r.Consume(&input, &word)); -} - -static void TestFindAndConsume() { - printf("Testing FindAndConsume\n"); - - string word; - - string s(" aaa b!@#$@#$cccc"); - StringPiece input(s); - - RE r("(\\w+)"); // matches a word - CHECK(r.FindAndConsume(&input, &word)); - CHECK_EQ(word, "aaa"); - CHECK(r.FindAndConsume(&input, &word)); - CHECK_EQ(word, "b"); - CHECK(r.FindAndConsume(&input, &word)); - CHECK_EQ(word, "cccc"); - CHECK(! r.FindAndConsume(&input, &word)); -} - -static void TestMatchNumberPeculiarity() { - printf("Testing match-number peculiarity\n"); - - string word1; - string word2; - string word3; - - RE r("(foo)|(bar)|(baz)"); - CHECK(r.PartialMatch("foo", &word1, &word2, &word3)); - CHECK_EQ(word1, "foo"); - CHECK_EQ(word2, ""); - CHECK_EQ(word3, ""); - CHECK(r.PartialMatch("bar", &word1, &word2, &word3)); - CHECK_EQ(word1, ""); - CHECK_EQ(word2, "bar"); - CHECK_EQ(word3, ""); - CHECK(r.PartialMatch("baz", &word1, &word2, &word3)); - CHECK_EQ(word1, ""); - CHECK_EQ(word2, ""); - CHECK_EQ(word3, "baz"); - CHECK(!r.PartialMatch("f", &word1, &word2, &word3)); - - string a; - CHECK(RE("(foo)|hello").FullMatch("hello", &a)); - CHECK_EQ(a, ""); -} - -static void TestRecursion() { - printf("Testing recursion\n"); - - // Get one string that passes (sometimes), one that never does. - string text_good("abcdefghijk"); - string text_bad("acdefghijkl"); - - // According to pcretest, matching text_good against (\w+)*b - // requires match_limit of at least 8192, and match_recursion_limit - // of at least 37. - - RE_Options options_ml; - options_ml.set_match_limit(8192); - RE re("(\\w+)*b", options_ml); - CHECK(re.PartialMatch(text_good) == true); - CHECK(re.PartialMatch(text_bad) == false); - CHECK(re.FullMatch(text_good) == false); - CHECK(re.FullMatch(text_bad) == false); - - options_ml.set_match_limit(1024); - RE re2("(\\w+)*b", options_ml); - CHECK(re2.PartialMatch(text_good) == false); // because of match_limit - CHECK(re2.PartialMatch(text_bad) == false); - CHECK(re2.FullMatch(text_good) == false); - CHECK(re2.FullMatch(text_bad) == false); - - RE_Options options_mlr; - options_mlr.set_match_limit_recursion(50); - RE re3("(\\w+)*b", options_mlr); - CHECK(re3.PartialMatch(text_good) == true); - CHECK(re3.PartialMatch(text_bad) == false); - CHECK(re3.FullMatch(text_good) == false); - CHECK(re3.FullMatch(text_bad) == false); - - options_mlr.set_match_limit_recursion(10); - RE re4("(\\w+)*b", options_mlr); - CHECK(re4.PartialMatch(text_good) == false); - CHECK(re4.PartialMatch(text_bad) == false); - CHECK(re4.FullMatch(text_good) == false); - CHECK(re4.FullMatch(text_bad) == false); -} - -// A meta-quoted string, interpreted as a pattern, should always match -// the original unquoted string. -static void TestQuoteMeta(string unquoted, RE_Options options = RE_Options()) { - string quoted = RE::QuoteMeta(unquoted); - RE re(quoted, options); - CHECK(re.FullMatch(unquoted)); -} - -// A string containing meaningful regexp characters, which is then meta- -// quoted, should not generally match a string the unquoted string does. -static void NegativeTestQuoteMeta(string unquoted, string should_not_match, - RE_Options options = RE_Options()) { - string quoted = RE::QuoteMeta(unquoted); - RE re(quoted, options); - CHECK(!re.FullMatch(should_not_match)); -} - -// Tests that quoted meta characters match their original strings, -// and that a few things that shouldn't match indeed do not. -static void TestQuotaMetaSimple() { - TestQuoteMeta("foo"); - TestQuoteMeta("foo.bar"); - TestQuoteMeta("foo\\.bar"); - TestQuoteMeta("[1-9]"); - TestQuoteMeta("1.5-2.0?"); - TestQuoteMeta("\\d"); - TestQuoteMeta("Who doesn't like ice cream?"); - TestQuoteMeta("((a|b)c?d*e+[f-h]i)"); - TestQuoteMeta("((?!)xxx).*yyy"); - TestQuoteMeta("(["); - TestQuoteMeta(string("foo\0bar", 7)); -} - -static void TestQuoteMetaSimpleNegative() { - NegativeTestQuoteMeta("foo", "bar"); - NegativeTestQuoteMeta("...", "bar"); - NegativeTestQuoteMeta("\\.", "."); - NegativeTestQuoteMeta("\\.", ".."); - NegativeTestQuoteMeta("(a)", "a"); - NegativeTestQuoteMeta("(a|b)", "a"); - NegativeTestQuoteMeta("(a|b)", "(a)"); - NegativeTestQuoteMeta("(a|b)", "a|b"); - NegativeTestQuoteMeta("[0-9]", "0"); - NegativeTestQuoteMeta("[0-9]", "0-9"); - NegativeTestQuoteMeta("[0-9]", "[9]"); - NegativeTestQuoteMeta("((?!)xxx)", "xxx"); -} - -static void TestQuoteMetaLatin1() { - TestQuoteMeta("3\xb2 = 9"); -} - -static void TestQuoteMetaUtf8() { -#ifdef SUPPORT_UTF8 - TestQuoteMeta("Pl\xc3\xa1\x63ido Domingo", pcrecpp::UTF8()); - TestQuoteMeta("xyz", pcrecpp::UTF8()); // No fancy utf8 - TestQuoteMeta("\xc2\xb0", pcrecpp::UTF8()); // 2-byte utf8 (degree symbol) - TestQuoteMeta("27\xc2\xb0 degrees", pcrecpp::UTF8()); // As a middle character - TestQuoteMeta("\xe2\x80\xb3", pcrecpp::UTF8()); // 3-byte utf8 (double prime) - TestQuoteMeta("\xf0\x9d\x85\x9f", pcrecpp::UTF8()); // 4-byte utf8 (music note) - TestQuoteMeta("27\xc2\xb0"); // Interpreted as Latin-1, but should still work - NegativeTestQuoteMeta("27\xc2\xb0", // 2-byte utf (degree symbol) - "27\\\xc2\\\xb0", - pcrecpp::UTF8()); -#endif -} - -static void TestQuoteMetaAll() { - printf("Testing QuoteMeta\n"); - TestQuotaMetaSimple(); - TestQuoteMetaSimpleNegative(); - TestQuoteMetaLatin1(); - TestQuoteMetaUtf8(); -} - -// -// Options tests contributed by -// Giuseppe Maxia, CTO, Stardata s.r.l. -// July 2005 -// -static void GetOneOptionResult( - const char *option_name, - const char *regex, - const char *str, - RE_Options options, - bool full, - string expected) { - - printf("Testing Option <%s>\n", option_name); - if(VERBOSE_TEST) - printf("/%s/ finds \"%s\" within \"%s\" \n", - regex, - expected.c_str(), - str); - string captured(""); - if (full) - RE(regex,options).FullMatch(str, &captured); - else - RE(regex,options).PartialMatch(str, &captured); - CHECK_EQ(captured, expected); -} - -static void TestOneOption( - const char *option_name, - const char *regex, - const char *str, - RE_Options options, - bool full, - bool assertive = true) { - - printf("Testing Option <%s>\n", option_name); - if (VERBOSE_TEST) - printf("'%s' %s /%s/ \n", - str, - (assertive? "matches" : "doesn't match"), - regex); - if (assertive) { - if (full) - CHECK(RE(regex,options).FullMatch(str)); - else - CHECK(RE(regex,options).PartialMatch(str)); - } else { - if (full) - CHECK(!RE(regex,options).FullMatch(str)); - else - CHECK(!RE(regex,options).PartialMatch(str)); - } -} - -static void Test_CASELESS() { - RE_Options options; - RE_Options options2; - - options.set_caseless(true); - TestOneOption("CASELESS (class)", "HELLO", "hello", options, false); - TestOneOption("CASELESS (class2)", "HELLO", "hello", options2.set_caseless(true), false); - TestOneOption("CASELESS (class)", "^[A-Z]+$", "Hello", options, false); - - TestOneOption("CASELESS (function)", "HELLO", "hello", pcrecpp::CASELESS(), false); - TestOneOption("CASELESS (function)", "^[A-Z]+$", "Hello", pcrecpp::CASELESS(), false); - options.set_caseless(false); - TestOneOption("no CASELESS", "HELLO", "hello", options, false, false); -} - -static void Test_MULTILINE() { - RE_Options options; - RE_Options options2; - const char *str = "HELLO\n" "cruel\n" "world\n"; - - options.set_multiline(true); - TestOneOption("MULTILINE (class)", "^cruel$", str, options, false); - TestOneOption("MULTILINE (class2)", "^cruel$", str, options2.set_multiline(true), false); - TestOneOption("MULTILINE (function)", "^cruel$", str, pcrecpp::MULTILINE(), false); - options.set_multiline(false); - TestOneOption("no MULTILINE", "^cruel$", str, options, false, false); -} - -static void Test_DOTALL() { - RE_Options options; - RE_Options options2; - const char *str = "HELLO\n" "cruel\n" "world"; - - options.set_dotall(true); - TestOneOption("DOTALL (class)", "HELLO.*world", str, options, true); - TestOneOption("DOTALL (class2)", "HELLO.*world", str, options2.set_dotall(true), true); - TestOneOption("DOTALL (function)", "HELLO.*world", str, pcrecpp::DOTALL(), true); - options.set_dotall(false); - TestOneOption("no DOTALL", "HELLO.*world", str, options, true, false); -} - -static void Test_DOLLAR_ENDONLY() { - RE_Options options; - RE_Options options2; - const char *str = "HELLO world\n"; - - TestOneOption("no DOLLAR_ENDONLY", "world$", str, options, false); - options.set_dollar_endonly(true); - TestOneOption("DOLLAR_ENDONLY 1", "world$", str, options, false, false); - TestOneOption("DOLLAR_ENDONLY 2", "world$", str, options2.set_dollar_endonly(true), false, false); -} - -static void Test_EXTRA() { - RE_Options options; - const char *str = "HELLO"; - - options.set_extra(true); - TestOneOption("EXTRA 1", "\\HELL\\O", str, options, true, false ); - TestOneOption("EXTRA 2", "\\HELL\\O", str, RE_Options().set_extra(true), true, false ); - options.set_extra(false); - TestOneOption("no EXTRA", "\\HELL\\O", str, options, true ); -} - -static void Test_EXTENDED() { - RE_Options options; - RE_Options options2; - const char *str = "HELLO world"; - - options.set_extended(true); - TestOneOption("EXTENDED (class)", "HELLO world", str, options, false, false); - TestOneOption("EXTENDED (class2)", "HELLO world", str, options2.set_extended(true), false, false); - TestOneOption("EXTENDED (class)", - "^ HE L{2} O " - "\\s+ " - "\\w+ $ ", - str, - options, - false); - - TestOneOption("EXTENDED (function)", "HELLO world", str, pcrecpp::EXTENDED(), false, false); - TestOneOption("EXTENDED (function)", - "^ HE L{2} O " - "\\s+ " - "\\w+ $ ", - str, - pcrecpp::EXTENDED(), - false); - - options.set_extended(false); - TestOneOption("no EXTENDED", "HELLO world", str, options, false); -} - -static void Test_NO_AUTO_CAPTURE() { - RE_Options options; - const char *str = "HELLO world"; - string captured; - - printf("Testing Option <no NO_AUTO_CAPTURE>\n"); - if (VERBOSE_TEST) - printf("parentheses capture text\n"); - RE re("(world|universe)$", options); - CHECK(re.Extract("\\1", str , &captured)); - CHECK_EQ(captured, "world"); - options.set_no_auto_capture(true); - printf("testing Option <NO_AUTO_CAPTURE>\n"); - if (VERBOSE_TEST) - printf("parentheses do not capture text\n"); - re.Extract("\\1",str, &captured ); - CHECK_EQ(captured, "world"); -} - -static void Test_UNGREEDY() { - RE_Options options; - const char *str = "HELLO, 'this' is the 'world'"; - - options.set_ungreedy(true); - GetOneOptionResult("UNGREEDY 1", "('.*')", str, options, false, "'this'" ); - GetOneOptionResult("UNGREEDY 2", "('.*')", str, RE_Options().set_ungreedy(true), false, "'this'" ); - GetOneOptionResult("UNGREEDY", "('.*?')", str, options, false, "'this' is the 'world'" ); - - options.set_ungreedy(false); - GetOneOptionResult("no UNGREEDY", "('.*')", str, options, false, "'this' is the 'world'" ); - GetOneOptionResult("no UNGREEDY", "('.*?')", str, options, false, "'this'" ); -} - -static void Test_all_options() { - const char *str = "HELLO\n" "cruel\n" "world"; - RE_Options options; - options.set_all_options(PCRE_CASELESS | PCRE_DOTALL); - - TestOneOption("all_options (CASELESS|DOTALL)", "^hello.*WORLD", str , options, false); - options.set_all_options(0); - TestOneOption("all_options (0)", "^hello.*WORLD", str , options, false, false); - options.set_all_options(PCRE_MULTILINE | PCRE_EXTENDED); - - TestOneOption("all_options (MULTILINE|EXTENDED)", " ^ c r u e l $ ", str, options, false); - TestOneOption("all_options (MULTILINE|EXTENDED) with constructor", - " ^ c r u e l $ ", - str, - RE_Options(PCRE_MULTILINE | PCRE_EXTENDED), - false); - - TestOneOption("all_options (MULTILINE|EXTENDED) with concatenation", - " ^ c r u e l $ ", - str, - RE_Options() - .set_multiline(true) - .set_extended(true), - false); - - options.set_all_options(0); - TestOneOption("all_options (0)", "^ c r u e l $", str, options, false, false); - -} - -static void TestOptions() { - printf("Testing Options\n"); - Test_CASELESS(); - Test_MULTILINE(); - Test_DOTALL(); - Test_DOLLAR_ENDONLY(); - Test_EXTENDED(); - Test_NO_AUTO_CAPTURE(); - Test_UNGREEDY(); - Test_EXTRA(); - Test_all_options(); -} - -static void TestConstructors() { - printf("Testing constructors\n"); - - RE_Options options; - options.set_dotall(true); - const char *str = "HELLO\n" "cruel\n" "world"; - - RE orig("HELLO.*world", options); - CHECK(orig.FullMatch(str)); - - RE copy1(orig); - CHECK(copy1.FullMatch(str)); - - RE copy2("not a match"); - CHECK(!copy2.FullMatch(str)); - copy2 = copy1; - CHECK(copy2.FullMatch(str)); - copy2 = orig; - CHECK(copy2.FullMatch(str)); - - // Make sure when we assign to ourselves, nothing bad happens - orig = orig; - copy1 = copy1; - copy2 = copy2; - CHECK(orig.FullMatch(str)); - CHECK(copy1.FullMatch(str)); - CHECK(copy2.FullMatch(str)); -} - -int main(int argc, char** argv) { - // Treat any flag as --help - if (argc > 1 && argv[1][0] == '-') { - printf("Usage: %s [timing1|timing2|timing3 num-iters]\n" - " If 'timingX ###' is specified, run the given timing test\n" - " with the given number of iterations, rather than running\n" - " the default corectness test.\n", argv[0]); - return 0; - } - - if (argc > 1) { - if ( argc == 2 || atoi(argv[2]) == 0) { - printf("timing mode needs a num-iters argument\n"); - return 1; - } - if (!strcmp(argv[1], "timing1")) - Timing1(atoi(argv[2])); - else if (!strcmp(argv[1], "timing2")) - Timing2(atoi(argv[2])); - else if (!strcmp(argv[1], "timing3")) - Timing3(atoi(argv[2])); - else - printf("Unknown argument '%s'\n", argv[1]); - return 0; - } - - printf("PCRE C++ wrapper tests\n"); - printf("Testing FullMatch\n"); - - int i; - string s; - - /***** FullMatch with no args *****/ - - CHECK(RE("h.*o").FullMatch("hello")); - CHECK(!RE("h.*o").FullMatch("othello")); // Must be anchored at front - CHECK(!RE("h.*o").FullMatch("hello!")); // Must be anchored at end - CHECK(RE("a*").FullMatch("aaaa")); // Fullmatch with normal op - CHECK(RE("a*?").FullMatch("aaaa")); // Fullmatch with nongreedy op - CHECK(RE("a*?\\z").FullMatch("aaaa")); // Two unusual ops - - /***** FullMatch with args *****/ - - // Zero-arg - CHECK(RE("\\d+").FullMatch("1001")); - - // Single-arg - CHECK(RE("(\\d+)").FullMatch("1001", &i)); - CHECK_EQ(i, 1001); - CHECK(RE("(-?\\d+)").FullMatch("-123", &i)); - CHECK_EQ(i, -123); - CHECK(!RE("()\\d+").FullMatch("10", &i)); - CHECK(!RE("(\\d+)").FullMatch("1234567890123456789012345678901234567890", - &i)); - - // Digits surrounding integer-arg - CHECK(RE("1(\\d*)4").FullMatch("1234", &i)); - CHECK_EQ(i, 23); - CHECK(RE("(\\d)\\d+").FullMatch("1234", &i)); - CHECK_EQ(i, 1); - CHECK(RE("(-\\d)\\d+").FullMatch("-1234", &i)); - CHECK_EQ(i, -1); - CHECK(RE("(\\d)").PartialMatch("1234", &i)); - CHECK_EQ(i, 1); - CHECK(RE("(-\\d)").PartialMatch("-1234", &i)); - CHECK_EQ(i, -1); - - // String-arg - CHECK(RE("h(.*)o").FullMatch("hello", &s)); - CHECK_EQ(s, string("ell")); - - // StringPiece-arg - StringPiece sp; - CHECK(RE("(\\w+):(\\d+)").FullMatch("ruby:1234", &sp, &i)); - CHECK_EQ(sp.size(), 4); - CHECK(memcmp(sp.data(), "ruby", 4) == 0); - CHECK_EQ(i, 1234); - - // Multi-arg - CHECK(RE("(\\w+):(\\d+)").FullMatch("ruby:1234", &s, &i)); - CHECK_EQ(s, string("ruby")); - CHECK_EQ(i, 1234); - - // Ignore non-void* NULL arg - CHECK(RE("he(.*)lo").FullMatch("hello", (char*)NULL)); - CHECK(RE("h(.*)o").FullMatch("hello", (string*)NULL)); - CHECK(RE("h(.*)o").FullMatch("hello", (StringPiece*)NULL)); - CHECK(RE("(.*)").FullMatch("1234", (int*)NULL)); -#ifdef HAVE_LONG_LONG - CHECK(RE("(.*)").FullMatch("1234567890123456", (long long*)NULL)); -#endif - CHECK(RE("(.*)").FullMatch("123.4567890123456", (double*)NULL)); - CHECK(RE("(.*)").FullMatch("123.4567890123456", (float*)NULL)); - - // Fail on non-void* NULL arg if the match doesn't parse for the given type. - CHECK(!RE("h(.*)lo").FullMatch("hello", &s, (char*)NULL)); - CHECK(!RE("(.*)").FullMatch("hello", (int*)NULL)); - CHECK(!RE("(.*)").FullMatch("1234567890123456", (int*)NULL)); - CHECK(!RE("(.*)").FullMatch("hello", (double*)NULL)); - CHECK(!RE("(.*)").FullMatch("hello", (float*)NULL)); - - // Ignored arg - CHECK(RE("(\\w+)(:)(\\d+)").FullMatch("ruby:1234", &s, (void*)NULL, &i)); - CHECK_EQ(s, string("ruby")); - CHECK_EQ(i, 1234); - - // Type tests - { - char c; - CHECK(RE("(H)ello").FullMatch("Hello", &c)); - CHECK_EQ(c, 'H'); - } - { - unsigned char c; - CHECK(RE("(H)ello").FullMatch("Hello", &c)); - CHECK_EQ(c, static_cast<unsigned char>('H')); - } - { - short v; - CHECK(RE("(-?\\d+)").FullMatch("100", &v)); CHECK_EQ(v, 100); - CHECK(RE("(-?\\d+)").FullMatch("-100", &v)); CHECK_EQ(v, -100); - CHECK(RE("(-?\\d+)").FullMatch("32767", &v)); CHECK_EQ(v, 32767); - CHECK(RE("(-?\\d+)").FullMatch("-32768", &v)); CHECK_EQ(v, -32768); - CHECK(!RE("(-?\\d+)").FullMatch("-32769", &v)); - CHECK(!RE("(-?\\d+)").FullMatch("32768", &v)); - } - { - unsigned short v; - CHECK(RE("(\\d+)").FullMatch("100", &v)); CHECK_EQ(v, 100); - CHECK(RE("(\\d+)").FullMatch("32767", &v)); CHECK_EQ(v, 32767); - CHECK(RE("(\\d+)").FullMatch("65535", &v)); CHECK_EQ(v, 65535); - CHECK(!RE("(\\d+)").FullMatch("65536", &v)); - } - { - int v; - static const int max_value = 0x7fffffff; - static const int min_value = -max_value - 1; - CHECK(RE("(-?\\d+)").FullMatch("100", &v)); CHECK_EQ(v, 100); - CHECK(RE("(-?\\d+)").FullMatch("-100", &v)); CHECK_EQ(v, -100); - CHECK(RE("(-?\\d+)").FullMatch("2147483647", &v)); CHECK_EQ(v, max_value); - CHECK(RE("(-?\\d+)").FullMatch("-2147483648", &v)); CHECK_EQ(v, min_value); - CHECK(!RE("(-?\\d+)").FullMatch("-2147483649", &v)); - CHECK(!RE("(-?\\d+)").FullMatch("2147483648", &v)); - } - { - unsigned int v; - static const unsigned int max_value = 0xfffffffful; - CHECK(RE("(\\d+)").FullMatch("100", &v)); CHECK_EQ(v, 100); - CHECK(RE("(\\d+)").FullMatch("4294967295", &v)); CHECK_EQ(v, max_value); - CHECK(!RE("(\\d+)").FullMatch("4294967296", &v)); - } -#ifdef HAVE_LONG_LONG -# if defined(__MINGW__) || defined(__MINGW32__) -# define LLD "%I64d" -# define LLU "%I64u" -# else -# define LLD "%lld" -# define LLU "%llu" -# endif - { - long long v; - static const long long max_value = 0x7fffffffffffffffLL; - static const long long min_value = -max_value - 1; - char buf[32]; // definitely big enough for a long long - - CHECK(RE("(-?\\d+)").FullMatch("100", &v)); CHECK_EQ(v, 100); - CHECK(RE("(-?\\d+)").FullMatch("-100",&v)); CHECK_EQ(v, -100); - - sprintf(buf, LLD, max_value); - CHECK(RE("(-?\\d+)").FullMatch(buf,&v)); CHECK_EQ(v, max_value); - - sprintf(buf, LLD, min_value); - CHECK(RE("(-?\\d+)").FullMatch(buf,&v)); CHECK_EQ(v, min_value); - - sprintf(buf, LLD, max_value); - assert(buf[strlen(buf)-1] != '9'); - buf[strlen(buf)-1]++; - CHECK(!RE("(-?\\d+)").FullMatch(buf, &v)); - - sprintf(buf, LLD, min_value); - assert(buf[strlen(buf)-1] != '9'); - buf[strlen(buf)-1]++; - CHECK(!RE("(-?\\d+)").FullMatch(buf, &v)); - } -#endif -#if defined HAVE_UNSIGNED_LONG_LONG && defined HAVE_LONG_LONG - { - unsigned long long v; - long long v2; - static const unsigned long long max_value = 0xffffffffffffffffULL; - char buf[32]; // definitely big enough for a unsigned long long - - CHECK(RE("(-?\\d+)").FullMatch("100",&v)); CHECK_EQ(v, 100); - CHECK(RE("(-?\\d+)").FullMatch("-100",&v2)); CHECK_EQ(v2, -100); - - sprintf(buf, LLU, max_value); - CHECK(RE("(-?\\d+)").FullMatch(buf,&v)); CHECK_EQ(v, max_value); - - assert(buf[strlen(buf)-1] != '9'); - buf[strlen(buf)-1]++; - CHECK(!RE("(-?\\d+)").FullMatch(buf, &v)); - } -#endif - { - float v; - CHECK(RE("(.*)").FullMatch("100", &v)); - CHECK(RE("(.*)").FullMatch("-100.", &v)); - CHECK(RE("(.*)").FullMatch("1e23", &v)); - } - { - double v; - CHECK(RE("(.*)").FullMatch("100", &v)); - CHECK(RE("(.*)").FullMatch("-100.", &v)); - CHECK(RE("(.*)").FullMatch("1e23", &v)); - } - - // Check that matching is fully anchored - CHECK(!RE("(\\d+)").FullMatch("x1001", &i)); - CHECK(!RE("(\\d+)").FullMatch("1001x", &i)); - CHECK(RE("x(\\d+)").FullMatch("x1001", &i)); CHECK_EQ(i, 1001); - CHECK(RE("(\\d+)x").FullMatch("1001x", &i)); CHECK_EQ(i, 1001); - - // Braces - CHECK(RE("[0-9a-f+.-]{5,}").FullMatch("0abcd")); - CHECK(RE("[0-9a-f+.-]{5,}").FullMatch("0abcde")); - CHECK(!RE("[0-9a-f+.-]{5,}").FullMatch("0abc")); - - // Complicated RE - CHECK(RE("foo|bar|[A-Z]").FullMatch("foo")); - CHECK(RE("foo|bar|[A-Z]").FullMatch("bar")); - CHECK(RE("foo|bar|[A-Z]").FullMatch("X")); - CHECK(!RE("foo|bar|[A-Z]").FullMatch("XY")); - - // Check full-match handling (needs '$' tacked on internally) - CHECK(RE("fo|foo").FullMatch("fo")); - CHECK(RE("fo|foo").FullMatch("foo")); - CHECK(RE("fo|foo$").FullMatch("fo")); - CHECK(RE("fo|foo$").FullMatch("foo")); - CHECK(RE("foo$").FullMatch("foo")); - CHECK(!RE("foo\\$").FullMatch("foo$bar")); - CHECK(!RE("fo|bar").FullMatch("fox")); - - // Uncomment the following if we change the handling of '$' to - // prevent it from matching a trailing newline - if (false) { - // Check that we don't get bitten by pcre's special handling of a - // '\n' at the end of the string matching '$' - CHECK(!RE("foo$").PartialMatch("foo\n")); - } - - // Number of args - int a[16]; - CHECK(RE("").FullMatch("")); - - memset(a, 0, sizeof(0)); - CHECK(RE("(\\d){1}").FullMatch("1", - &a[0])); - CHECK_EQ(a[0], 1); - - memset(a, 0, sizeof(0)); - CHECK(RE("(\\d)(\\d)").FullMatch("12", - &a[0], &a[1])); - CHECK_EQ(a[0], 1); - CHECK_EQ(a[1], 2); - - memset(a, 0, sizeof(0)); - CHECK(RE("(\\d)(\\d)(\\d)").FullMatch("123", - &a[0], &a[1], &a[2])); - CHECK_EQ(a[0], 1); - CHECK_EQ(a[1], 2); - CHECK_EQ(a[2], 3); - - memset(a, 0, sizeof(0)); - CHECK(RE("(\\d)(\\d)(\\d)(\\d)").FullMatch("1234", - &a[0], &a[1], &a[2], &a[3])); - CHECK_EQ(a[0], 1); - CHECK_EQ(a[1], 2); - CHECK_EQ(a[2], 3); - CHECK_EQ(a[3], 4); - - memset(a, 0, sizeof(0)); - CHECK(RE("(\\d)(\\d)(\\d)(\\d)(\\d)").FullMatch("12345", - &a[0], &a[1], &a[2], - &a[3], &a[4])); - CHECK_EQ(a[0], 1); - CHECK_EQ(a[1], 2); - CHECK_EQ(a[2], 3); - CHECK_EQ(a[3], 4); - CHECK_EQ(a[4], 5); - - memset(a, 0, sizeof(0)); - CHECK(RE("(\\d)(\\d)(\\d)(\\d)(\\d)(\\d)").FullMatch("123456", - &a[0], &a[1], &a[2], - &a[3], &a[4], &a[5])); - CHECK_EQ(a[0], 1); - CHECK_EQ(a[1], 2); - CHECK_EQ(a[2], 3); - CHECK_EQ(a[3], 4); - CHECK_EQ(a[4], 5); - CHECK_EQ(a[5], 6); - - memset(a, 0, sizeof(0)); - CHECK(RE("(\\d)(\\d)(\\d)(\\d)(\\d)(\\d)(\\d)").FullMatch("1234567", - &a[0], &a[1], &a[2], &a[3], - &a[4], &a[5], &a[6])); - CHECK_EQ(a[0], 1); - CHECK_EQ(a[1], 2); - CHECK_EQ(a[2], 3); - CHECK_EQ(a[3], 4); - CHECK_EQ(a[4], 5); - CHECK_EQ(a[5], 6); - CHECK_EQ(a[6], 7); - - memset(a, 0, sizeof(0)); - CHECK(RE("(\\d)(\\d)(\\d)(\\d)(\\d)(\\d)(\\d)(\\d)" - "(\\d)(\\d)(\\d)(\\d)(\\d)(\\d)(\\d)(\\d)").FullMatch( - "1234567890123456", - &a[0], &a[1], &a[2], &a[3], - &a[4], &a[5], &a[6], &a[7], - &a[8], &a[9], &a[10], &a[11], - &a[12], &a[13], &a[14], &a[15])); - CHECK_EQ(a[0], 1); - CHECK_EQ(a[1], 2); - CHECK_EQ(a[2], 3); - CHECK_EQ(a[3], 4); - CHECK_EQ(a[4], 5); - CHECK_EQ(a[5], 6); - CHECK_EQ(a[6], 7); - CHECK_EQ(a[7], 8); - CHECK_EQ(a[8], 9); - CHECK_EQ(a[9], 0); - CHECK_EQ(a[10], 1); - CHECK_EQ(a[11], 2); - CHECK_EQ(a[12], 3); - CHECK_EQ(a[13], 4); - CHECK_EQ(a[14], 5); - CHECK_EQ(a[15], 6); - - /***** PartialMatch *****/ - - printf("Testing PartialMatch\n"); - - CHECK(RE("h.*o").PartialMatch("hello")); - CHECK(RE("h.*o").PartialMatch("othello")); - CHECK(RE("h.*o").PartialMatch("hello!")); - CHECK(RE("((((((((((((((((((((x))))))))))))))))))))").PartialMatch("x")); - - /***** other tests *****/ - - RadixTests(); - TestReplace(); - TestExtract(); - TestConsume(); - TestFindAndConsume(); - TestQuoteMetaAll(); - TestMatchNumberPeculiarity(); - - // Check the pattern() accessor - { - const string kPattern = "http://([^/]+)/.*"; - const RE re(kPattern); - CHECK_EQ(kPattern, re.pattern()); - } - - // Check RE error field. - { - RE re("foo"); - CHECK(re.error().empty()); // Must have no error - } - -#ifdef SUPPORT_UTF8 - // Check UTF-8 handling - { - printf("Testing UTF-8 handling\n"); - - // Three Japanese characters (nihongo) - const unsigned char utf8_string[] = { - 0xe6, 0x97, 0xa5, // 65e5 - 0xe6, 0x9c, 0xac, // 627c - 0xe8, 0xaa, 0x9e, // 8a9e - 0 - }; - const unsigned char utf8_pattern[] = { - '.', - 0xe6, 0x9c, 0xac, // 627c - '.', - 0 - }; - - // Both should match in either mode, bytes or UTF-8 - RE re_test1("........."); - CHECK(re_test1.FullMatch(utf8_string)); - RE re_test2("...", pcrecpp::UTF8()); - CHECK(re_test2.FullMatch(utf8_string)); - - // Check that '.' matches one byte or UTF-8 character - // according to the mode. - string ss; - RE re_test3("(.)"); - CHECK(re_test3.PartialMatch(utf8_string, &ss)); - CHECK_EQ(ss, string("\xe6")); - RE re_test4("(.)", pcrecpp::UTF8()); - CHECK(re_test4.PartialMatch(utf8_string, &ss)); - CHECK_EQ(ss, string("\xe6\x97\xa5")); - - // Check that string matches itself in either mode - RE re_test5(utf8_string); - CHECK(re_test5.FullMatch(utf8_string)); - RE re_test6(utf8_string, pcrecpp::UTF8()); - CHECK(re_test6.FullMatch(utf8_string)); - - // Check that pattern matches string only in UTF8 mode - RE re_test7(utf8_pattern); - CHECK(!re_test7.FullMatch(utf8_string)); - RE re_test8(utf8_pattern, pcrecpp::UTF8()); - CHECK(re_test8.FullMatch(utf8_string)); - } - - // Check that ungreedy, UTF8 regular expressions don't match when they - // oughtn't -- see bug 82246. - { - // This code always worked. - const char* pattern = "\\w+X"; - const string target = "a aX"; - RE match_sentence(pattern); - RE match_sentence_re(pattern, pcrecpp::UTF8()); - - CHECK(!match_sentence.FullMatch(target)); - CHECK(!match_sentence_re.FullMatch(target)); - } - - { - const char* pattern = "(?U)\\w+X"; - const string target = "a aX"; - RE match_sentence(pattern); - RE match_sentence_re(pattern, pcrecpp::UTF8()); - - CHECK(!match_sentence.FullMatch(target)); - CHECK(!match_sentence_re.FullMatch(target)); - } -#endif /* def SUPPORT_UTF8 */ - - printf("Testing error reporting\n"); - - { RE re("a\\1"); CHECK(!re.error().empty()); } - { - RE re("a[x"); - CHECK(!re.error().empty()); - } - { - RE re("a[z-a]"); - CHECK(!re.error().empty()); - } - { - RE re("a[[:foobar:]]"); - CHECK(!re.error().empty()); - } - { - RE re("a(b"); - CHECK(!re.error().empty()); - } - { - RE re("a\\"); - CHECK(!re.error().empty()); - } - - // Test that recursion is stopped - TestRecursion(); - - // Test Options - if (getenv("VERBOSE_TEST") != NULL) - VERBOSE_TEST = true; - TestOptions(); - - // Test the constructors - TestConstructors(); - - // Done - printf("OK\n"); - - return 0; -} diff --git a/src/third_party/pcre-8.38/pcrecpparg.h b/src/third_party/pcre-8.38/pcrecpparg.h deleted file mode 100644 index b4f9c3f4989..00000000000 --- a/src/third_party/pcre-8.38/pcrecpparg.h +++ /dev/null @@ -1,174 +0,0 @@ -// Copyright (c) 2005, Google Inc. -// All rights reserved. -// -// Redistribution and use in source and binary forms, with or without -// modification, are permitted provided that the following conditions are -// met: -// -// * Redistributions of source code must retain the above copyright -// notice, this list of conditions and the following disclaimer. -// * Redistributions in binary form must reproduce the above -// copyright notice, this list of conditions and the following disclaimer -// in the documentation and/or other materials provided with the -// distribution. -// * Neither the name of Google Inc. nor the names of its -// contributors may be used to endorse or promote products derived from -// this software without specific prior written permission. -// -// THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS -// "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT -// LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR -// A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT -// OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, -// SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT -// LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, -// DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY -// THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT -// (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE -// OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE. -// -// Author: Sanjay Ghemawat - -#ifndef _PCRECPPARG_H -#define _PCRECPPARG_H - -#include <stdlib.h> // for NULL -#include <string> - -#include <pcre.h> - -namespace pcrecpp { - -class StringPiece; - -// Hex/Octal/Binary? - -// Special class for parsing into objects that define a ParseFrom() method -template <class T> -class _RE_MatchObject { - public: - static inline bool Parse(const char* str, int n, void* dest) { - if (dest == NULL) return true; - T* object = reinterpret_cast<T*>(dest); - return object->ParseFrom(str, n); - } -}; - -class PCRECPP_EXP_DEFN Arg { - public: - // Empty constructor so we can declare arrays of Arg - Arg(); - - // Constructor specially designed for NULL arguments - Arg(void*); - - typedef bool (*Parser)(const char* str, int n, void* dest); - -// Type-specific parsers -#define PCRE_MAKE_PARSER(type,name) \ - Arg(type* p) : arg_(p), parser_(name) { } \ - Arg(type* p, Parser parser) : arg_(p), parser_(parser) { } - - - PCRE_MAKE_PARSER(char, parse_char); - PCRE_MAKE_PARSER(unsigned char, parse_uchar); - PCRE_MAKE_PARSER(short, parse_short); - PCRE_MAKE_PARSER(unsigned short, parse_ushort); - PCRE_MAKE_PARSER(int, parse_int); - PCRE_MAKE_PARSER(unsigned int, parse_uint); - PCRE_MAKE_PARSER(long, parse_long); - PCRE_MAKE_PARSER(unsigned long, parse_ulong); -#if 1 - PCRE_MAKE_PARSER(long long, parse_longlong); -#endif -#if 1 - PCRE_MAKE_PARSER(unsigned long long, parse_ulonglong); -#endif - PCRE_MAKE_PARSER(float, parse_float); - PCRE_MAKE_PARSER(double, parse_double); - PCRE_MAKE_PARSER(std::string, parse_string); - PCRE_MAKE_PARSER(StringPiece, parse_stringpiece); - -#undef PCRE_MAKE_PARSER - - // Generic constructor - template <class T> Arg(T*, Parser parser); - // Generic constructor template - template <class T> Arg(T* p) - : arg_(p), parser_(_RE_MatchObject<T>::Parse) { - } - - // Parse the data - bool Parse(const char* str, int n) const; - - private: - void* arg_; - Parser parser_; - - static bool parse_null (const char* str, int n, void* dest); - static bool parse_char (const char* str, int n, void* dest); - static bool parse_uchar (const char* str, int n, void* dest); - static bool parse_float (const char* str, int n, void* dest); - static bool parse_double (const char* str, int n, void* dest); - static bool parse_string (const char* str, int n, void* dest); - static bool parse_stringpiece (const char* str, int n, void* dest); - -#define PCRE_DECLARE_INTEGER_PARSER(name) \ - private: \ - static bool parse_ ## name(const char* str, int n, void* dest); \ - static bool parse_ ## name ## _radix( \ - const char* str, int n, void* dest, int radix); \ - public: \ - static bool parse_ ## name ## _hex(const char* str, int n, void* dest); \ - static bool parse_ ## name ## _octal(const char* str, int n, void* dest); \ - static bool parse_ ## name ## _cradix(const char* str, int n, void* dest) - - PCRE_DECLARE_INTEGER_PARSER(short); - PCRE_DECLARE_INTEGER_PARSER(ushort); - PCRE_DECLARE_INTEGER_PARSER(int); - PCRE_DECLARE_INTEGER_PARSER(uint); - PCRE_DECLARE_INTEGER_PARSER(long); - PCRE_DECLARE_INTEGER_PARSER(ulong); - PCRE_DECLARE_INTEGER_PARSER(longlong); - PCRE_DECLARE_INTEGER_PARSER(ulonglong); - -#undef PCRE_DECLARE_INTEGER_PARSER -}; - -inline Arg::Arg() : arg_(NULL), parser_(parse_null) { } -inline Arg::Arg(void* p) : arg_(p), parser_(parse_null) { } - -inline bool Arg::Parse(const char* str, int n) const { - return (*parser_)(str, n, arg_); -} - -// This part of the parser, appropriate only for ints, deals with bases -#define MAKE_INTEGER_PARSER(type, name) \ - inline Arg Hex(type* ptr) { \ - return Arg(ptr, Arg::parse_ ## name ## _hex); } \ - inline Arg Octal(type* ptr) { \ - return Arg(ptr, Arg::parse_ ## name ## _octal); } \ - inline Arg CRadix(type* ptr) { \ - return Arg(ptr, Arg::parse_ ## name ## _cradix); } - -MAKE_INTEGER_PARSER(short, short) /* */ -MAKE_INTEGER_PARSER(unsigned short, ushort) /* */ -MAKE_INTEGER_PARSER(int, int) /* Don't use semicolons */ -MAKE_INTEGER_PARSER(unsigned int, uint) /* after these statement */ -MAKE_INTEGER_PARSER(long, long) /* because they can cause */ -MAKE_INTEGER_PARSER(unsigned long, ulong) /* compiler warnings if */ -#if 1 /* the checking level is */ -MAKE_INTEGER_PARSER(long long, longlong) /* turned up high enough. */ -#endif /* */ -#if 1 /* */ -MAKE_INTEGER_PARSER(unsigned long long, ulonglong) /* */ -#endif - -#undef PCRE_IS_SET -#undef PCRE_SET_OR_CLEAR -#undef MAKE_INTEGER_PARSER - -} // namespace pcrecpp - - -#endif /* _PCRECPPARG_H */ diff --git a/src/third_party/pcre-8.38/pcrecpparg.h.in b/src/third_party/pcre-8.38/pcrecpparg.h.in deleted file mode 100644 index 61bcab5402c..00000000000 --- a/src/third_party/pcre-8.38/pcrecpparg.h.in +++ /dev/null @@ -1,174 +0,0 @@ -// Copyright (c) 2005, Google Inc. -// All rights reserved. -// -// Redistribution and use in source and binary forms, with or without -// modification, are permitted provided that the following conditions are -// met: -// -// * Redistributions of source code must retain the above copyright -// notice, this list of conditions and the following disclaimer. -// * Redistributions in binary form must reproduce the above -// copyright notice, this list of conditions and the following disclaimer -// in the documentation and/or other materials provided with the -// distribution. -// * Neither the name of Google Inc. nor the names of its -// contributors may be used to endorse or promote products derived from -// this software without specific prior written permission. -// -// THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS -// "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT -// LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR -// A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT -// OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, -// SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT -// LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, -// DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY -// THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT -// (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE -// OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE. -// -// Author: Sanjay Ghemawat - -#ifndef _PCRECPPARG_H -#define _PCRECPPARG_H - -#include <stdlib.h> // for NULL -#include <string> - -#include <pcre.h> - -namespace pcrecpp { - -class StringPiece; - -// Hex/Octal/Binary? - -// Special class for parsing into objects that define a ParseFrom() method -template <class T> -class _RE_MatchObject { - public: - static inline bool Parse(const char* str, int n, void* dest) { - if (dest == NULL) return true; - T* object = reinterpret_cast<T*>(dest); - return object->ParseFrom(str, n); - } -}; - -class PCRECPP_EXP_DEFN Arg { - public: - // Empty constructor so we can declare arrays of Arg - Arg(); - - // Constructor specially designed for NULL arguments - Arg(void*); - - typedef bool (*Parser)(const char* str, int n, void* dest); - -// Type-specific parsers -#define PCRE_MAKE_PARSER(type,name) \ - Arg(type* p) : arg_(p), parser_(name) { } \ - Arg(type* p, Parser parser) : arg_(p), parser_(parser) { } - - - PCRE_MAKE_PARSER(char, parse_char); - PCRE_MAKE_PARSER(unsigned char, parse_uchar); - PCRE_MAKE_PARSER(short, parse_short); - PCRE_MAKE_PARSER(unsigned short, parse_ushort); - PCRE_MAKE_PARSER(int, parse_int); - PCRE_MAKE_PARSER(unsigned int, parse_uint); - PCRE_MAKE_PARSER(long, parse_long); - PCRE_MAKE_PARSER(unsigned long, parse_ulong); -#if @pcre_have_long_long@ - PCRE_MAKE_PARSER(long long, parse_longlong); -#endif -#if @pcre_have_ulong_long@ - PCRE_MAKE_PARSER(unsigned long long, parse_ulonglong); -#endif - PCRE_MAKE_PARSER(float, parse_float); - PCRE_MAKE_PARSER(double, parse_double); - PCRE_MAKE_PARSER(std::string, parse_string); - PCRE_MAKE_PARSER(StringPiece, parse_stringpiece); - -#undef PCRE_MAKE_PARSER - - // Generic constructor - template <class T> Arg(T*, Parser parser); - // Generic constructor template - template <class T> Arg(T* p) - : arg_(p), parser_(_RE_MatchObject<T>::Parse) { - } - - // Parse the data - bool Parse(const char* str, int n) const; - - private: - void* arg_; - Parser parser_; - - static bool parse_null (const char* str, int n, void* dest); - static bool parse_char (const char* str, int n, void* dest); - static bool parse_uchar (const char* str, int n, void* dest); - static bool parse_float (const char* str, int n, void* dest); - static bool parse_double (const char* str, int n, void* dest); - static bool parse_string (const char* str, int n, void* dest); - static bool parse_stringpiece (const char* str, int n, void* dest); - -#define PCRE_DECLARE_INTEGER_PARSER(name) \ - private: \ - static bool parse_ ## name(const char* str, int n, void* dest); \ - static bool parse_ ## name ## _radix( \ - const char* str, int n, void* dest, int radix); \ - public: \ - static bool parse_ ## name ## _hex(const char* str, int n, void* dest); \ - static bool parse_ ## name ## _octal(const char* str, int n, void* dest); \ - static bool parse_ ## name ## _cradix(const char* str, int n, void* dest) - - PCRE_DECLARE_INTEGER_PARSER(short); - PCRE_DECLARE_INTEGER_PARSER(ushort); - PCRE_DECLARE_INTEGER_PARSER(int); - PCRE_DECLARE_INTEGER_PARSER(uint); - PCRE_DECLARE_INTEGER_PARSER(long); - PCRE_DECLARE_INTEGER_PARSER(ulong); - PCRE_DECLARE_INTEGER_PARSER(longlong); - PCRE_DECLARE_INTEGER_PARSER(ulonglong); - -#undef PCRE_DECLARE_INTEGER_PARSER -}; - -inline Arg::Arg() : arg_(NULL), parser_(parse_null) { } -inline Arg::Arg(void* p) : arg_(p), parser_(parse_null) { } - -inline bool Arg::Parse(const char* str, int n) const { - return (*parser_)(str, n, arg_); -} - -// This part of the parser, appropriate only for ints, deals with bases -#define MAKE_INTEGER_PARSER(type, name) \ - inline Arg Hex(type* ptr) { \ - return Arg(ptr, Arg::parse_ ## name ## _hex); } \ - inline Arg Octal(type* ptr) { \ - return Arg(ptr, Arg::parse_ ## name ## _octal); } \ - inline Arg CRadix(type* ptr) { \ - return Arg(ptr, Arg::parse_ ## name ## _cradix); } - -MAKE_INTEGER_PARSER(short, short) /* */ -MAKE_INTEGER_PARSER(unsigned short, ushort) /* */ -MAKE_INTEGER_PARSER(int, int) /* Don't use semicolons */ -MAKE_INTEGER_PARSER(unsigned int, uint) /* after these statement */ -MAKE_INTEGER_PARSER(long, long) /* because they can cause */ -MAKE_INTEGER_PARSER(unsigned long, ulong) /* compiler warnings if */ -#if @pcre_have_long_long@ /* the checking level is */ -MAKE_INTEGER_PARSER(long long, longlong) /* turned up high enough. */ -#endif /* */ -#if @pcre_have_ulong_long@ /* */ -MAKE_INTEGER_PARSER(unsigned long long, ulonglong) /* */ -#endif - -#undef PCRE_IS_SET -#undef PCRE_SET_OR_CLEAR -#undef MAKE_INTEGER_PARSER - -} // namespace pcrecpp - - -#endif /* _PCRECPPARG_H */ diff --git a/src/third_party/pcre-8.38/pcredemo.c b/src/third_party/pcre-8.38/pcredemo.c deleted file mode 100644 index 946aba45cdc..00000000000 --- a/src/third_party/pcre-8.38/pcredemo.c +++ /dev/null @@ -1,406 +0,0 @@ -/************************************************* -* PCRE DEMONSTRATION PROGRAM * -*************************************************/ - -/* This is a demonstration program to illustrate the most straightforward ways -of calling the PCRE regular expression library from a C program. See the -pcresample documentation for a short discussion ("man pcresample" if you have -the PCRE man pages installed). - -In Unix-like environments, if PCRE is installed in your standard system -libraries, you should be able to compile this program using this command: - -gcc -Wall pcredemo.c -lpcre -o pcredemo - -If PCRE is not installed in a standard place, it is likely to be installed with -support for the pkg-config mechanism. If you have pkg-config, you can compile -this program using this command: - -gcc -Wall pcredemo.c `pkg-config --cflags --libs libpcre` -o pcredemo - -If you do not have pkg-config, you may have to use this: - -gcc -Wall pcredemo.c -I/usr/local/include -L/usr/local/lib \ - -R/usr/local/lib -lpcre -o pcredemo - -Replace "/usr/local/include" and "/usr/local/lib" with wherever the include and -library files for PCRE are installed on your system. Only some operating -systems (e.g. Solaris) use the -R option. - -Building under Windows: - -If you want to statically link this program against a non-dll .a file, you must -define PCRE_STATIC before including pcre.h, otherwise the pcre_malloc() and -pcre_free() exported functions will be declared __declspec(dllimport), with -unwanted results. So in this environment, uncomment the following line. */ - -/* #define PCRE_STATIC */ - -#include <stdio.h> -#include <string.h> -#include <pcre.h> - -#define OVECCOUNT 30 /* should be a multiple of 3 */ - - -int main(int argc, char **argv) -{ -pcre *re; -const char *error; -char *pattern; -char *subject; -unsigned char *name_table; -unsigned int option_bits; -int erroffset; -int find_all; -int crlf_is_newline; -int namecount; -int name_entry_size; -int ovector[OVECCOUNT]; -int subject_length; -int rc, i; -int utf8; - - -/************************************************************************** -* First, sort out the command line. There is only one possible option at * -* the moment, "-g" to request repeated matching to find all occurrences, * -* like Perl's /g option. We set the variable find_all to a non-zero value * -* if the -g option is present. Apart from that, there must be exactly two * -* arguments. * -**************************************************************************/ - -find_all = 0; -for (i = 1; i < argc; i++) - { - if (strcmp(argv[i], "-g") == 0) find_all = 1; - else break; - } - -/* After the options, we require exactly two arguments, which are the pattern, -and the subject string. */ - -if (argc - i != 2) - { - printf("Two arguments required: a regex and a subject string\n"); - return 1; - } - -pattern = argv[i]; -subject = argv[i+1]; -subject_length = (int)strlen(subject); - - -/************************************************************************* -* Now we are going to compile the regular expression pattern, and handle * -* and errors that are detected. * -*************************************************************************/ - -re = pcre_compile( - pattern, /* the pattern */ - 0, /* default options */ - &error, /* for error message */ - &erroffset, /* for error offset */ - NULL); /* use default character tables */ - -/* Compilation failed: print the error message and exit */ - -if (re == NULL) - { - printf("PCRE compilation failed at offset %d: %s\n", erroffset, error); - return 1; - } - - -/************************************************************************* -* If the compilation succeeded, we call PCRE again, in order to do a * -* pattern match against the subject string. This does just ONE match. If * -* further matching is needed, it will be done below. * -*************************************************************************/ - -rc = pcre_exec( - re, /* the compiled pattern */ - NULL, /* no extra data - we didn't study the pattern */ - subject, /* the subject string */ - subject_length, /* the length of the subject */ - 0, /* start at offset 0 in the subject */ - 0, /* default options */ - ovector, /* output vector for substring information */ - OVECCOUNT); /* number of elements in the output vector */ - -/* Matching failed: handle error cases */ - -if (rc < 0) - { - switch(rc) - { - case PCRE_ERROR_NOMATCH: printf("No match\n"); break; - /* - Handle other special cases if you like - */ - default: printf("Matching error %d\n", rc); break; - } - pcre_free(re); /* Release memory used for the compiled pattern */ - return 1; - } - -/* Match succeded */ - -printf("\nMatch succeeded at offset %d\n", ovector[0]); - - -/************************************************************************* -* We have found the first match within the subject string. If the output * -* vector wasn't big enough, say so. Then output any substrings that were * -* captured. * -*************************************************************************/ - -/* The output vector wasn't big enough */ - -if (rc == 0) - { - rc = OVECCOUNT/3; - printf("ovector only has room for %d captured substrings\n", rc - 1); - } - -/* Show substrings stored in the output vector by number. Obviously, in a real -application you might want to do things other than print them. */ - -for (i = 0; i < rc; i++) - { - char *substring_start = subject + ovector[2*i]; - int substring_length = ovector[2*i+1] - ovector[2*i]; - printf("%2d: %.*s\n", i, substring_length, substring_start); - } - - -/************************************************************************** -* That concludes the basic part of this demonstration program. We have * -* compiled a pattern, and performed a single match. The code that follows * -* shows first how to access named substrings, and then how to code for * -* repeated matches on the same subject. * -**************************************************************************/ - -/* See if there are any named substrings, and if so, show them by name. First -we have to extract the count of named parentheses from the pattern. */ - -(void)pcre_fullinfo( - re, /* the compiled pattern */ - NULL, /* no extra data - we didn't study the pattern */ - PCRE_INFO_NAMECOUNT, /* number of named substrings */ - &namecount); /* where to put the answer */ - -if (namecount <= 0) printf("No named substrings\n"); else - { - unsigned char *tabptr; - printf("Named substrings\n"); - - /* Before we can access the substrings, we must extract the table for - translating names to numbers, and the size of each entry in the table. */ - - (void)pcre_fullinfo( - re, /* the compiled pattern */ - NULL, /* no extra data - we didn't study the pattern */ - PCRE_INFO_NAMETABLE, /* address of the table */ - &name_table); /* where to put the answer */ - - (void)pcre_fullinfo( - re, /* the compiled pattern */ - NULL, /* no extra data - we didn't study the pattern */ - PCRE_INFO_NAMEENTRYSIZE, /* size of each entry in the table */ - &name_entry_size); /* where to put the answer */ - - /* Now we can scan the table and, for each entry, print the number, the name, - and the substring itself. */ - - tabptr = name_table; - for (i = 0; i < namecount; i++) - { - int n = (tabptr[0] << 8) | tabptr[1]; - printf("(%d) %*s: %.*s\n", n, name_entry_size - 3, tabptr + 2, - ovector[2*n+1] - ovector[2*n], subject + ovector[2*n]); - tabptr += name_entry_size; - } - } - - -/************************************************************************* -* If the "-g" option was given on the command line, we want to continue * -* to search for additional matches in the subject string, in a similar * -* way to the /g option in Perl. This turns out to be trickier than you * -* might think because of the possibility of matching an empty string. * -* What happens is as follows: * -* * -* If the previous match was NOT for an empty string, we can just start * -* the next match at the end of the previous one. * -* * -* If the previous match WAS for an empty string, we can't do that, as it * -* would lead to an infinite loop. Instead, a special call of pcre_exec() * -* is made with the PCRE_NOTEMPTY_ATSTART and PCRE_ANCHORED flags set. * -* The first of these tells PCRE that an empty string at the start of the * -* subject is not a valid match; other possibilities must be tried. The * -* second flag restricts PCRE to one match attempt at the initial string * -* position. If this match succeeds, an alternative to the empty string * -* match has been found, and we can print it and proceed round the loop, * -* advancing by the length of whatever was found. If this match does not * -* succeed, we still stay in the loop, advancing by just one character. * -* In UTF-8 mode, which can be set by (*UTF8) in the pattern, this may be * -* more than one byte. * -* * -* However, there is a complication concerned with newlines. When the * -* newline convention is such that CRLF is a valid newline, we must * -* advance by two characters rather than one. The newline convention can * -* be set in the regex by (*CR), etc.; if not, we must find the default. * -*************************************************************************/ - -if (!find_all) /* Check for -g */ - { - pcre_free(re); /* Release the memory used for the compiled pattern */ - return 0; /* Finish unless -g was given */ - } - -/* Before running the loop, check for UTF-8 and whether CRLF is a valid newline -sequence. First, find the options with which the regex was compiled; extract -the UTF-8 state, and mask off all but the newline options. */ - -(void)pcre_fullinfo(re, NULL, PCRE_INFO_OPTIONS, &option_bits); -utf8 = option_bits & PCRE_UTF8; -option_bits &= PCRE_NEWLINE_CR|PCRE_NEWLINE_LF|PCRE_NEWLINE_CRLF| - PCRE_NEWLINE_ANY|PCRE_NEWLINE_ANYCRLF; - -/* If no newline options were set, find the default newline convention from the -build configuration. */ - -if (option_bits == 0) - { - int d; - (void)pcre_config(PCRE_CONFIG_NEWLINE, &d); - /* Note that these values are always the ASCII ones, even in - EBCDIC environments. CR = 13, NL = 10. */ - option_bits = (d == 13)? PCRE_NEWLINE_CR : - (d == 10)? PCRE_NEWLINE_LF : - (d == (13<<8 | 10))? PCRE_NEWLINE_CRLF : - (d == -2)? PCRE_NEWLINE_ANYCRLF : - (d == -1)? PCRE_NEWLINE_ANY : 0; - } - -/* See if CRLF is a valid newline sequence. */ - -crlf_is_newline = - option_bits == PCRE_NEWLINE_ANY || - option_bits == PCRE_NEWLINE_CRLF || - option_bits == PCRE_NEWLINE_ANYCRLF; - -/* Loop for second and subsequent matches */ - -for (;;) - { - int options = 0; /* Normally no options */ - int start_offset = ovector[1]; /* Start at end of previous match */ - - /* If the previous match was for an empty string, we are finished if we are - at the end of the subject. Otherwise, arrange to run another match at the - same point to see if a non-empty match can be found. */ - - if (ovector[0] == ovector[1]) - { - if (ovector[0] == subject_length) break; - options = PCRE_NOTEMPTY_ATSTART | PCRE_ANCHORED; - } - - /* Run the next matching operation */ - - rc = pcre_exec( - re, /* the compiled pattern */ - NULL, /* no extra data - we didn't study the pattern */ - subject, /* the subject string */ - subject_length, /* the length of the subject */ - start_offset, /* starting offset in the subject */ - options, /* options */ - ovector, /* output vector for substring information */ - OVECCOUNT); /* number of elements in the output vector */ - - /* This time, a result of NOMATCH isn't an error. If the value in "options" - is zero, it just means we have found all possible matches, so the loop ends. - Otherwise, it means we have failed to find a non-empty-string match at a - point where there was a previous empty-string match. In this case, we do what - Perl does: advance the matching position by one character, and continue. We - do this by setting the "end of previous match" offset, because that is picked - up at the top of the loop as the point at which to start again. - - There are two complications: (a) When CRLF is a valid newline sequence, and - the current position is just before it, advance by an extra byte. (b) - Otherwise we must ensure that we skip an entire UTF-8 character if we are in - UTF-8 mode. */ - - if (rc == PCRE_ERROR_NOMATCH) - { - if (options == 0) break; /* All matches found */ - ovector[1] = start_offset + 1; /* Advance one byte */ - if (crlf_is_newline && /* If CRLF is newline & */ - start_offset < subject_length - 1 && /* we are at CRLF, */ - subject[start_offset] == '\r' && - subject[start_offset + 1] == '\n') - ovector[1] += 1; /* Advance by one more. */ - else if (utf8) /* Otherwise, ensure we */ - { /* advance a whole UTF-8 */ - while (ovector[1] < subject_length) /* character. */ - { - if ((subject[ovector[1]] & 0xc0) != 0x80) break; - ovector[1] += 1; - } - } - continue; /* Go round the loop again */ - } - - /* Other matching errors are not recoverable. */ - - if (rc < 0) - { - printf("Matching error %d\n", rc); - pcre_free(re); /* Release memory used for the compiled pattern */ - return 1; - } - - /* Match succeded */ - - printf("\nMatch succeeded again at offset %d\n", ovector[0]); - - /* The match succeeded, but the output vector wasn't big enough. */ - - if (rc == 0) - { - rc = OVECCOUNT/3; - printf("ovector only has room for %d captured substrings\n", rc - 1); - } - - /* As before, show substrings stored in the output vector by number, and then - also any named substrings. */ - - for (i = 0; i < rc; i++) - { - char *substring_start = subject + ovector[2*i]; - int substring_length = ovector[2*i+1] - ovector[2*i]; - printf("%2d: %.*s\n", i, substring_length, substring_start); - } - - if (namecount <= 0) printf("No named substrings\n"); else - { - unsigned char *tabptr = name_table; - printf("Named substrings\n"); - for (i = 0; i < namecount; i++) - { - int n = (tabptr[0] << 8) | tabptr[1]; - printf("(%d) %*s: %.*s\n", n, name_entry_size - 3, tabptr + 2, - ovector[2*n+1] - ovector[2*n], subject + ovector[2*n]); - tabptr += name_entry_size; - } - } - } /* End of loop to find second and subsequent matches */ - -printf("\n"); -pcre_free(re); /* Release memory used for the compiled pattern */ -return 0; -} - -/* End of pcredemo.c */ diff --git a/src/third_party/pcre-8.38/pcregexp.pas b/src/third_party/pcre-8.38/pcregexp.pas deleted file mode 100644 index bb2b3da8f3d..00000000000 --- a/src/third_party/pcre-8.38/pcregexp.pas +++ /dev/null @@ -1,845 +0,0 @@ -{
- pcRegExp - Perl compatible regular expressions for Virtual Pascal
- (c) 2001 Peter S. Voronov aka Chem O'Dun <petervrn@yahoo.com>
-
- Based on PCRE library interface unit for Virtual Pascal.
- (c) 2001 Alexander Tokarev <dwalin@dwalin.ru>
-
- The current PCRE version is: 3.7
-
- This software may be distributed under the terms of the modified BSD license
- Copyright (c) 2001, Alexander Tokarev
- All rights reserved.
-
- Redistribution and use in source and binary forms, with or without
- modification, are permitted provided that the following conditions are met:
-
- * Redistributions of source code must retain the above copyright notice,
- this list of conditions and the following disclaimer.
- * Redistributions in binary form must reproduce the above copyright notice,
- this list of conditions and the following disclaimer in the documentation
- and/or other materials provided with the distribution.
- * Neither the name of the <ORGANIZATION> nor the names of its contributors
- may be used to endorse or promote products derived from this software without
- specific prior written permission.
-
- THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS" AND
- ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE IMPLIED
- WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE ARE
- DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT HOLDER OR CONTRIBUTORS BE LIABLE
- FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL
- DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR
- SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER
- CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY,
- OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE
- OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
-
- The PCRE library is written by: Philip Hazel <ph10@cam.ac.uk>
- Copyright (c) 1997-2004 University of Cambridge
-
- AngelsHolocaust 4-11-04 updated to use version v5.0
- (INFO: this is regex-directed, NFA)
- AH: 9-11-04 - pcre_free: removed var, pcre already gives the ptr, now
- everything works as it should (no more crashes)
- -> removed CheckRegExp because pcre handles errors perfectly
- 10-11-04 - added pcError (errorhandling), pcInit
- 13-11-04 - removed the ErrorPos = 0 check -> always print erroroffset
- 17-10-05 - support for \1-\9 backreferences in TpcRegExp.GetReplStr
- 17-02-06 - added RunTimeOptions: caller can set options while searching
- 19-02-06 - added SearchOfs(): let PCRE use the complete string and offset
- into the string itself
- 20-12-06 - support for version 7.0
- 27.08.08 - support for v7.7
-}
-
-{$H+} {$DEFINE PCRE_3_7} {$DEFINE PCRE_5_0} {$DEFINE PCRE_7_0} {$DEFINE PCRE_7_7}
-
-Unit pcregexp;
-
-Interface
-
-uses objects;
-
-Type
- PpcRegExp = ^TpcRegExp;
-// TpcRegExp = object
- TpcRegExp = object(TObject)
- MatchesCount: integer;
- RegExpC, RegExpExt : Pointer;
- Matches:Pointer;
- RegExp: shortstring;
- SourceLen: integer;
- PartialMatch : boolean;
- Error : boolean;
- ErrorMsg : Pchar;
- ErrorPos : integer;
- RunTimeOptions: Integer; // options which can be set by the caller
- constructor Init(const ARegExp : shortstring; AOptions : integer; ALocale : Pointer);
- function Search(AStr: Pchar; ALen : longint) : boolean; virtual;
- function SearchNext( AStr: Pchar; ALen : longint) : boolean; virtual;
- function SearchOfs ( AStr: Pchar; ALen, AOfs : longint) : boolean; virtual;
- function MatchSub(ANom: integer; var Pos, Len : longint) : boolean; virtual;
- function MatchFull(var Pos, Len : longint) : boolean; virtual;
- function GetSubStr(ANom: integer; AStr: Pchar) : string; virtual;
- function GetFullStr(AStr: Pchar) : string; virtual;
- function GetReplStr(AStr: Pchar; const ARepl: string) : string; virtual;
- function GetPreSubStr(AStr: Pchar) : string; virtual;
- function GetPostSubStr(AStr: Pchar) : string; virtual;
- function ErrorStr : string; virtual;
- destructor Done; virtual;
- end;
-
- function pcGrepMatch(WildCard, aStr: string; AOptions:integer; ALocale : Pointer): Boolean;
- function pcGrepSub(WildCard, aStr, aRepl: string; AOptions:integer; ALocale : Pointer): string;
-
- function pcFastGrepMatch(WildCard, aStr: string): Boolean;
- function pcFastGrepSub(WildCard, aStr, aRepl: string): string;
-
-{$IFDEF PCRE_5_0}
- function pcGetVersion : pchar;
-{$ENDIF}
-
- function pcError (var pRegExp : Pointer) : Boolean;
- function pcInit (const Pattern: Shortstring; CaseSens: Boolean) : Pointer;
-
-Const { Options }
- PCRE_CASELESS = $0001;
- PCRE_MULTILINE = $0002;
- PCRE_DOTALL = $0004;
- PCRE_EXTENDED = $0008;
- PCRE_ANCHORED = $0010;
- PCRE_DOLLAR_ENDONLY = $0020;
- PCRE_EXTRA = $0040;
- PCRE_NOTBOL = $0080;
- PCRE_NOTEOL = $0100;
- PCRE_UNGREEDY = $0200;
- PCRE_NOTEMPTY = $0400;
-{$IFDEF PCRE_5_0}
- PCRE_UTF8 = $0800;
- PCRE_NO_AUTO_CAPTURE = $1000;
- PCRE_NO_UTF8_CHECK = $2000;
- PCRE_AUTO_CALLOUT = $4000;
- PCRE_PARTIAL = $8000;
-{$ENDIF}
-{$IFDEF PCRE_7_0}
- PCRE_DFA_SHORTEST = $00010000;
- PCRE_DFA_RESTART = $00020000;
- PCRE_FIRSTLINE = $00040000;
- PCRE_DUPNAMES = $00080000;
- PCRE_NEWLINE_CR = $00100000;
- PCRE_NEWLINE_LF = $00200000;
- PCRE_NEWLINE_CRLF = $00300000;
- PCRE_NEWLINE_ANY = $00400000;
- PCRE_NEWLINE_ANYCRLF = $00500000;
-
- PCRE_NEWLINE_BITS = PCRE_NEWLINE_CR or PCRE_NEWLINE_LF or PCRE_NEWLINE_ANY;
-
-{$ENDIF}
-{$IFDEF PCRE_7_7}
- PCRE_BSR_ANYCRLF = $00800000;
- PCRE_BSR_UNICODE = $01000000;
- PCRE_JAVASCRIPT_COMPAT= $02000000;
-{$ENDIF}
-
- PCRE_COMPILE_ALLOWED_OPTIONS = PCRE_ANCHORED + PCRE_AUTO_CALLOUT + PCRE_CASELESS +
- PCRE_DOLLAR_ENDONLY + PCRE_DOTALL + PCRE_EXTENDED +
- PCRE_EXTRA + PCRE_MULTILINE + PCRE_NO_AUTO_CAPTURE +
- PCRE_UNGREEDY + PCRE_UTF8 + PCRE_NO_UTF8_CHECK
- {$IFDEF PCRE_7_0}
- + PCRE_DUPNAMES + PCRE_FIRSTLINE + PCRE_NEWLINE_BITS
- {$ENDIF}
- {$IFDEF PCRE_7_7}
- + PCRE_BSR_ANYCRLF + PCRE_BSR_UNICODE + PCRE_JAVASCRIPT_COMPAT
- {$ENDIF}
- ;
-
- PCRE_EXEC_ALLOWED_OPTIONS = PCRE_ANCHORED + PCRE_NOTBOL + PCRE_NOTEOL +
- PCRE_NOTEMPTY + PCRE_NO_UTF8_CHECK + PCRE_PARTIAL
- {$IFDEF PCRE_7_0}
- + PCRE_NEWLINE_BITS
- {$ENDIF}
- {$IFDEF PCRE_7_7}
- + PCRE_BSR_ANYCRLF + PCRE_BSR_UNICODE
- {$ENDIF}
- ;
-
-{$IFDEF PCRE_7_0}
- PCRE_DFA_EXEC_ALLOWED_OPTIONS = PCRE_ANCHORED + PCRE_NOTBOL + PCRE_NOTEOL +
- PCRE_NOTEMPTY + PCRE_NO_UTF8_CHECK + PCRE_PARTIAL +
- PCRE_DFA_SHORTEST + PCRE_DFA_RESTART +
- PCRE_NEWLINE_BITS
- {$IFDEF PCRE_7_7}
- + PCRE_BSR_ANYCRLF + PCRE_BSR_UNICODE
- {$ENDIF}
- ;
-{$ENDIF}
-
-{ Exec-time and get/set-time error codes }
- PCRE_ERROR_NOMATCH = -1;
- PCRE_ERROR_NULL = -2;
- PCRE_ERROR_BADOPTION = -3;
- PCRE_ERROR_BADMAGIC = -4;
- PCRE_ERROR_UNKNOWN_MODE = -5;
- PCRE_ERROR_NOMEMORY = -6;
- PCRE_ERROR_NOSUBSTRING = -7;
-{$IFDEF PCRE_5_0}
- PCRE_ERROR_MATCHLIMIT = -8;
- PCRE_ERROR_CALLOUT = -9; { Never used by PCRE itself }
- PCRE_ERROR_BADUTF8 = -10;
- PCRE_ERROR_BADUTF8_OFFSET = -11;
- PCRE_ERROR_PARTIAL = -12;
- PCRE_ERROR_BADPARTIAL = -13;
- PCRE_ERROR_INTERNAL = -14;
- PCRE_ERROR_BADCOUNT = -15;
-{$ENDIF}
-{$IFDEF PCRE_7_0}
- PCRE_ERROR_DFA_UITEM = -16;
- PCRE_ERROR_DFA_UCOND = -17;
- PCRE_ERROR_DFA_UMLIMIT = -18;
- PCRE_ERROR_DFA_WSSIZE = -19;
- PCRE_ERROR_DFA_RECURSE = -20;
- PCRE_ERROR_RECURSIONLIMIT = -21;
- PCRE_ERROR_NULLWSLIMIT = -22;
- PCRE_ERROR_BADNEWLINE = -23;
-{$ENDIF}
-
-{ Request types for pcre_fullinfo() }
-
- PCRE_INFO_OPTIONS = 0;
- PCRE_INFO_SIZE = 1;
- PCRE_INFO_CAPTURECOUNT = 2;
- PCRE_INFO_BACKREFMAX = 3;
- PCRE_INFO_FIRSTBYTE = 4;
- PCRE_INFO_FIRSTCHAR = 4; { For backwards compatibility }
- PCRE_INFO_FIRSTTABLE = 5;
-{$IFDEF PCRE_5_0}
- PCRE_INFO_LASTLITERAL = 6;
- PCRE_INFO_NAMEENTRYSIZE = 7;
- PCRE_INFO_NAMECOUNT = 8;
- PCRE_INFO_NAMETABLE = 9;
- PCRE_INFO_STUDYSIZE = 10;
- PCRE_INFO_DEFAULT_TABLES = 11;
-{$ENDIF PCRE_5_0}
-{$IFDEF PCRE_7_7}
- PCRE_INFO_OKPARTIAL = 12;
- PCRE_INFO_JCHANGED = 13;
- PCRE_INFO_HASCRORLF = 14;
-{$ENDIF}
-
-{ Request types for pcre_config() }
-{$IFDEF PCRE_5_0}
- PCRE_CONFIG_UTF8 = 0;
- PCRE_CONFIG_NEWLINE = 1;
- PCRE_CONFIG_LINK_SIZE = 2;
- PCRE_CONFIG_POSIX_MALLOC_THRESHOLD = 3;
- PCRE_CONFIG_MATCH_LIMIT = 4;
- PCRE_CONFIG_STACKRECURSE = 5;
- PCRE_CONFIG_UNICODE_PROPERTIES = 6;
-{$ENDIF PCRE_5_0}
-{$IFDEF PCRE_7_0}
- PCRE_CONFIG_MATCH_LIMIT_RECURSION = 7;
-{$ENDIF}
-{$IFDEF PCRE_7_7}
- PCRE_CONFIG_BSR = 8;
-{$ENDIF}
-
-{ Bit flags for the pcre_extra structure }
-{$IFDEF PCRE_5_0}
- PCRE_EXTRA_STUDY_DATA = $0001;
- PCRE_EXTRA_MATCH_LIMIT = $0002;
- PCRE_EXTRA_CALLOUT_DATA = $0004;
- PCRE_EXTRA_TABLES = $0008;
-{$ENDIF PCRE_5_0}
-{$IFDEF PCRE_7_0}
- PCRE_EXTRA_MATCH_LIMIT_RECURSION = $0010;
-{$ENDIF}
-
-Const
-// DefaultOptions : integer = 0;
- DefaultLocaleTable : pointer = nil;
-
-{$IFDEF PCRE_5_0}
-{ The structure for passing additional data to pcre_exec(). This is defined in
-such as way as to be extensible. Always add new fields at the end, in order to
-remain compatible. }
-
-type ppcre_extra = ^tpcre_extra;
- tpcre_extra = record
- flags : longint; { Bits for which fields are set }
- study_data : pointer; { Opaque data from pcre_study() }
- match_limit : longint; { Maximum number of calls to match() }
- callout_data : pointer; { Data passed back in callouts }
- tables : pointer; { Pointer to character tables }
- match_limit_recursion: longint; { Max recursive calls to match() }
- end;
-
-type ppcre_callout_block = ^pcre_callout_block;
- pcre_callout_block = record
- version,
- (* ------------------------ Version 0 ------------------------------- *)
- callout_number : integer;
- offset_vector : pointer;
- subject : pchar;
- subject_length, start_match, current_position, capture_top,
- capture_last : integer;
- callout_data : pointer;
- (* ------------------- Added for Version 1 -------------------------- *)
- pattern_position, next_item_length : integer;
- end;
-{$ENDIF PCRE_5_0}
-
-{$OrgName+}
-{$IFDEF VIRTUALPASCAL} {&Cdecl+} {$ENDIF VIRTUALPASCAL}
-
- { local replacement of external pcre memory management functions }
- function pcre_malloc( size : integer ) : pointer;
- procedure pcre_free( {var} p : pointer );
-{$IFDEF PCRE_5_0}
- const pcre_stack_malloc: function ( size : integer ): pointer = pcre_malloc;
- pcre_stack_free: procedure ( {var} p : pointer ) = pcre_free;
- function pcre_callout(var p : ppcre_callout_block) : integer;
-{$ENDIF PCRE_5_0}
-{$IFDEF VIRTUALPASCAL} {&Cdecl-} {$ENDIF VIRTUALPASCAL}
-
-Implementation
-
-Uses strings, collect, messages, dnapp, commands, advance0, stringsx
- {$IFDEF VIRTUALPASCAL} ,vpsyslow {$ENDIF VIRTUALPASCAL};
-
-Const
- MAGIC_NUMBER = $50435245; { 'PCRE' }
- MAX_MATCHES = 90; { changed in 3.5 version; should be divisible by 3, was 64}
-
-Type
- PMatchArray = ^TMatchArray;
- TMatchArray = array[0..( MAX_MATCHES * 3 )] of integer;
-
- PRegExpCollection = ^TRegExpCollection;
- TRegExpCollection = object(TSortedCollection)
- MaxRegExp : integer;
- SearchRegExp : shortstring;
- CompareModeInsert : boolean;
- constructor Init(AMaxRegExp:integer);
- procedure FreeItem(P: Pointer); virtual;
- function Compare(P1, P2: Pointer): Integer; virtual;
- function Find(ARegExp:shortstring;var P: PpcRegExp):boolean; virtual;
- function CheckNew(ARegExp:shortstring):PpcRegExp;virtual;
- end;
-
-Var
- PRegExpCache : PRegExpCollection;
-
-
-{$IFDEF VIRTUALPASCAL} {&Cdecl+} {$ENDIF VIRTUALPASCAL}
-
- { imported original pcre functions }
-
- function pcre_compile( const pattern : PChar; options : integer;
- var errorptr : PChar; var erroroffset : integer;
- const tables : PChar ) : pointer {pcre}; external;
-{$IFDEF PCRE_7_0}
- function pcre_compile2( const pattern : PChar; options : integer;
- var errorcodeptr : Integer;
- var errorptr : PChar; var erroroffset : integer;
- const tables : PChar ) : pointer {pcre}; external;
-{$ENDIF}
-{$IFDEF PCRE_5_0}
- function pcre_config( what : integer; where : pointer) : integer; external;
- function pcre_copy_named_substring( const code : pointer {pcre};
- const subject : pchar;
- var ovector : integer;
- stringcount : integer;
- const stringname : pchar;
- var buffer : pchar;
- size : integer) : integer; external;
- function pcre_copy_substring( const subject : pchar; var ovector : integer;
- stringcount, stringnumber : integer;
- var buffer : pchar; size : integer )
- : integer; external;
- function pcre_exec( const argument_re : pointer {pcre};
- const extra_data : pointer {pcre_extra};
-{$ELSE}
- function pcre_exec( const external_re : pointer;
- const external_extra : pointer;
-{$ENDIF}
- const subject : PChar;
- length, start_offset, options : integer;
- offsets : pointer;
- offsetcount : integer ) : integer; external;
-{$IFDEF PCRE_7_0}
- function pcre_dfa_exec( const argument_re : pointer {pcre};
- const extra_data : pointer {pcre_extra};
- const subject : pchar;
- length, start_offset, options : integer;
- offsets : pointer;
- offsetcount : integer;
- workspace : pointer;
- wscount : integer ) : integer; external;
-{$ENDIF}
-{$IFDEF PCRE_5_0}
- procedure pcre_free_substring( const p : pchar ); external;
- procedure pcre_free_substring_list( var p : pchar ); external;
- function pcre_fullinfo( const argument_re : pointer {pcre};
- const extra_data : pointer {pcre_extra};
- what : integer;
- where : pointer ) : integer; external;
- function pcre_get_named_substring( const code : pointer {pcre};
- const subject : pchar;
- var ovector : integer;
- stringcount : integer;
- const stringname : pchar;
- var stringptr : pchar ) : integer; external;
- function pcre_get_stringnumber( const code : pointer {pcre};
- const stringname : pchar ) : integer; external;
- function pcre_get_stringtable_entries( const code : pointer {pcre};
- const stringname : pchar;
- var firstptr,
- lastptr : pchar ) : integer; external;
- function pcre_get_substring( const subject : pchar; var ovector : integer;
- stringcount, stringnumber : integer;
- var stringptr : pchar ) : integer; external;
- function pcre_get_substring_list( const subject : pchar; var ovector : integer;
- stringcount : integer;
- listptr : pointer {const char ***listptr}) : integer; external;
- function pcre_info( const argument_re : pointer {pcre};
- var optptr : integer;
- var first_byte : integer ) : integer; external;
- function pcre_maketables : pchar; external;
-{$ENDIF}
-{$IFDEF PCRE_7_0}
- function pcre_refcount( const argument_re : pointer {pcre};
- adjust : integer ) : pchar; external;
-{$ENDIF}
- function pcre_study( const external_re : pointer {pcre};
- options : integer;
- var errorptr : PChar ) : pointer {pcre_extra}; external;
-{$IFDEF PCRE_5_0}
- function pcre_version : pchar; external;
-{$ENDIF}
-
- function pcre_malloc( size : integer ) : pointer;
- begin
- GetMem( result, size );
- end;
-
- procedure pcre_free( {var} p : pointer );
- begin
- if (p <> nil) then
- FreeMem( p, 0 );
- {@p := nil;}
- end;
-
-{$IFDEF PCRE_5_0}
-(* Called from PCRE as a result of the (?C) item. We print out where we are in
-the match. Yield zero unless more callouts than the fail count, or the callout
-data is not zero. *)
-
- function pcre_callout;
- begin
- end;
-{$ENDIF}
-
-{$IFDEF VIRTUALPASCAL} {&Cdecl-} {$ENDIF VIRTUALPASCAL}
-
-// Always include the newest version of the library
-{$IFDEF PCRE_7_7}
- {$L pcre77.lib}
-{$ELSE}
- {$IFDEF PCRE_7_0}
- {$L pcre70.lib}
- {$ELSE}
- {$IFDEF PCRE_5_0}
- {$L pcre50.lib}
- {$ELSE}
- {$IFDEF PCRE_3_7}
- {$L pcre37.lib}
- {$ENDIF PCRE_3_7}
- {$ENDIF PCRE_5_0}
- {$ENDIF PCRE_7_0}
-{$ENDIF PCRE_7_7}
-
-{TpcRegExp}
-
- constructor TpcRegExp.Init(const ARegExp:shortstring; AOptions:integer; ALocale : Pointer);
- var
- pRegExp : PChar;
- begin
- RegExp:=ARegExp;
- RegExpC:=nil;
- RegExpExt:=nil;
- Matches:=nil;
- MatchesCount:=0;
- Error:=true;
- ErrorMsg:=nil;
- ErrorPos:=0;
- RunTimeOptions := 0;
- if length(RegExp) < 255 then
- begin
- RegExp[length(RegExp)+1]:=#0;
- pRegExp:=@RegExp[1];
- end
- else
- begin
- GetMem(pRegExp,length(RegExp)+1);
- pRegExp:=strpcopy(pRegExp,RegExp);
- end;
- RegExpC := pcre_compile( pRegExp,
- AOptions and PCRE_COMPILE_ALLOWED_OPTIONS,
- ErrorMsg, ErrorPos, ALocale);
- if length(RegExp) = 255 then
- StrDispose(pRegExp);
- if RegExpC = nil then
- exit;
- ErrorMsg:=nil;
- RegExpExt := pcre_study( RegExpC, 0, ErrorMsg );
- if (RegExpExt = nil) and (ErrorMsg <> nil) then
- begin
- pcre_free(RegExpC);
- exit;
- end;
- GetMem(Matches,SizeOf(TMatchArray));
- Error:=false;
- end;
-
- destructor TpcRegExp.Done;
- begin
- if RegExpC <> nil then
- pcre_free(RegExpC);
- if RegExpExt <> nil then
- pcre_free(RegExpExt);
- if Matches <> nil then
- FreeMem(Matches,SizeOf(TMatchArray));
- end;
-
- function TpcRegExp.SearchNext( AStr: Pchar; ALen : longint ) : boolean;
- var Options: Integer;
- begin // must handle PCRE_ERROR_PARTIAL here
- Options := (RunTimeOptions or startup.MiscMultiData.cfgRegEx.DefaultOptions) and
- PCRE_EXEC_ALLOWED_OPTIONS;
- if MatchesCount > 0 then
- MatchesCount:=pcre_exec( RegExpC, RegExpExt, AStr, ALen, PMatchArray(Matches)^[1],
- Options, Matches, MAX_MATCHES ) else
- MatchesCount:=pcre_exec( RegExpC, RegExpExt, AStr, ALen, 0,
- Options, Matches, MAX_MATCHES );
-{ if MatchesCount = 0 then
- MatchesCount := MatchesCount div 3;}
- PartialMatch := MatchesCount = PCRE_ERROR_PARTIAL;
- SearchNext := MatchesCount > 0;
- end;
-
- function TpcRegExp.Search( AStr: Pchar; ALen : longint):boolean;
- begin
- MatchesCount:=0;
- Search:=SearchNext(AStr,ALen);
- SourceLen:=ALen;
- end;
-
- function TpcRegExp.SearchOfs( AStr: Pchar; ALen, AOfs: longint ) : boolean;
- var Options: Integer;
- begin
- MatchesCount:=0;
- Options := (RunTimeOptions or startup.MiscMultiData.cfgRegEx.DefaultOptions) and
- PCRE_EXEC_ALLOWED_OPTIONS;
- MatchesCount:=pcre_exec( RegExpC, RegExpExt, AStr, ALen, AOfs,
- Options, Matches, MAX_MATCHES );
- PartialMatch := MatchesCount = PCRE_ERROR_PARTIAL;
- SearchOfs := MatchesCount > 0;
- SourceLen := ALen-AOfs;
- end;
-
- function TpcRegExp.MatchSub(ANom:integer; var Pos,Len:longint):boolean;
- begin
- if (MatchesCount > 0) and (ANom <= (MatchesCount-1)) then
- begin
- ANom:=ANom*2;
- Pos:=PMatchArray(Matches)^[ANom];
- Len:=PMatchArray(Matches)^[ANom+1]-Pos;
- MatchSub:=true;
- end
- else
- MatchSub:=false;
- end;
-
- function TpcRegExp.MatchFull(var Pos,Len:longint):boolean;
- begin
- MatchFull:=MatchSub(0,Pos,Len);
- end;
-
- function TpcRegExp.GetSubStr(ANom: integer; AStr: Pchar):string;
- var
- s: ansistring;
- pos,len: longint;
- begin
- s:='';
- if MatchSub(ANom, pos, len) then
- begin
- setlength(s, len);
- Move(AStr[pos], s[1], len);
- end;
- GetSubStr:=s;
- end;
-
- function TpcRegExp.GetPreSubStr(AStr: Pchar):string;
- var
- s: ansistring;
- l: longint;
- begin
- s:='';
- if (MatchesCount > 0) then
- begin
- l:=PMatchArray(Matches)^[0]-1;
- if l > 0 then
- begin
- setlength(s,l);
- Move(AStr[1],s[1],l);
- end;
- end;
- GetPreSubStr:=s;
- end;
-
- function TpcRegExp.GetPostSubStr(AStr: Pchar):string;
- var
- s: ansistring;
- l: longint;
- ANom: integer;
- begin
- s:='';
- if (MatchesCount > 0) then
- begin
- ANom:=(MatchesCount-1){*2} shl 1;
- l:=SourceLen-PMatchArray(Matches)^[ANom+1]+1;
- if l > 0 then
- begin
- setlength(s,l);
- Move(AStr[PMatchArray(Matches)^[ANom+1]],s[1],l);
- end;
- end;
- GetPostSubStr:=s;
- end;
-
-
- function TpcRegExp.GetFullStr(AStr: Pchar):string;
- var
- s: ansistring;
- l: longint;
- begin
- GetFullStr:=GetSubStr(0,AStr);
- end;
-
- function TpcRegExp.GetReplStr(AStr: Pchar; const ARepl: string):string;
- var
- s: ansistring;
- l,i,lasti: longint;
- begin
- l:=length(ARepl);
- i:=1;
- lasti:=1;
- s:='';
- while i <= l do
- begin
- case ARepl[i] of
- '\' :
- begin
- if i < l then
- begin
- s:=s+copy(ARepl,lasti,i-lasti){+ARepl[i+1]};
- {AH 17-10-05 support for POSIX \1-\9 backreferences}
- case ARepl[i+1] of
- '0' : s:=s+GetFullStr(AStr);
- '1'..'9' : s:=s+GetSubStr(ord(ARepl[i+1])-ord('0'),AStr);
- else s:=s+ARepl[i+1]; // copy the escaped character
- end;
- end;
- inc(i);
- lasti:=i+1;
- end;
- '$' :
- begin
- if i < l then
- begin
- s:=s+copy(ARepl,lasti,i-lasti);
- case ARepl[i+1] of
- '&' : s:=s+GetFullStr(AStr);
- '1'..'9' : s:=s+GetSubStr(ord(ARepl[i+1])-ord('0'),AStr);
- '`' : s:=s+GetPreSubStr(AStr);
- #39 : s:=s+GetPostSubStr(AStr);
- end;
- end;
- inc(i);
- lasti:=i+1;
- end;
- end;
- inc(i);
- end;
- if lasti <= {AH 25-10-2004 added =, else l==1 won't work} l then
- s:=s+copy(ARepl,lasti,l-lasti+1);
- GetReplStr:=s;
- end;
-
- function TpcRegExp.ErrorStr:string;
- begin
- ErrorStr:=StrPas(ErrorMsg);
- end;
-
-{TRegExpCollection}
-
-constructor TRegExpCollection.Init(AMaxRegExp: integer);
-begin
- Inherited Init(1,1);
- MaxRegExp:=AMaxRegExp;
- CompareModeInsert:=true;
-end;
-
-procedure TRegExpCollection.FreeItem(P: Pointer);
-begin
- if P <> nil then
- begin
- Dispose(PpcRegExp(P),Done);
- end;
-end;
-
-function TRegExpCollection.Compare(P1, P2: Pointer): Integer;
-//var
-// l,l1,l2,i : byte;
-//// wPos: pchar;
-begin
- if CompareModeInsert then
- begin
-// l1:=length(PpcRegExp(P1)^.RegExp);
-// l2:=length(PpcRegExp(P2)^.RegExp);
-// if l1 > l2 then l:=l2 else
-// l:=l1;
-// for i:=1 to l do
-// if PpcRegExp(P1).RegExp[i] <> PpcRegExp(P2).RegExp[i] then break;
-// if i <=l then
-// Compare:=ord(PpcRegExp(P1).RegExp[i])-ord(PpcRegExp(P2).RegExp[i]) else
-// Compare:=l1-l2;
- Compare := stringsx.PasStrCmp(PpcRegExp(P1).RegExp, PpcRegExp(P2).RegExp, False);
- end
- else
- begin
-// l1:=length(PpcRegExp(P1)^.RegExp);
-// l2:=length(SearchRegExp);
-// if l1 > l2 then l:=l2 else
-// l:=l1;
-// for i:=1 to l do
-// if PpcRegExp(P1).RegExp[i] <> SearchRegExp[i] then
-// begin
-// Compare:=ord(PpcRegExp(P1).RegExp[i])-ord(SearchRegExp[i]);
-// break;
-// end;
-// if i > l then Compare:=l1-l2;
- Compare := stringsx.PasStrCmp(PpcRegExp(P1).RegExp, SearchRegExp, False);
- end;
-end;
-
-function TRegExpCollection.Find(ARegExp:shortstring;var P: PpcRegExp):boolean;
-var I : integer;
-begin
- CompareModeInsert:=false;
- SearchRegExp:=ARegExp;
- if Search(nil,I) then
- begin
- P:=PpcRegExp(At(I));
- Find:=true;
- end
- else
- begin
- P:=nil;
- Find:=false;
- end;
- CompareModeInsert:=true;
-end;
-
-function TRegExpCollection.CheckNew(ARegExp:shortstring):PpcRegExp;
-var
- P : PpcRegExp;
-begin
- if not Find(ARegExp,P) then
- begin
- if Count = MaxRegExp then
- AtFree(0);
- P:=New(ppcRegExp,Init(ARegExp,PCRE_CASELESS,nil));
- Insert(P);
- end;
- CheckNew:=P;
-end;
-
-function pcGrepMatch(WildCard, aStr: string; AOptions:integer; ALocale : Pointer): Boolean;
-var
- PpcRE:PpcRegExp;
-begin
- PpcRE:=New(ppcRegExp,Init(WildCard,AOptions,Alocale));
- pcGrepMatch:=PpcRE^.Search(pchar(AStr),Length(AStr));
- Dispose(PpcRE,Done);
-end;
-
-function pcGrepSub(WildCard, aStr, aRepl: string; AOptions:integer; ALocale : Pointer): string;
-var
- PpcRE:PpcRegExp;
-begin
- PpcRE:=New(ppcRegExp,Init(WildCard,AOptions,Alocale));
- if PpcRE^.Search(pchar(AStr),Length(AStr)) then
- pcGrepSub:=PpcRE^.GetReplStr(pchar(AStr),ARepl)
- else
- pcGrepSub:='';
- Dispose(PpcRE,Done);
-end;
-
-function pcFastGrepMatch(WildCard, aStr: string): Boolean;
-var
- PpcRE:PpcRegExp;
-begin
- PpcRE:=PRegExpCache^.CheckNew(WildCard);
- pcFastGrepMatch:=PpcRE^.Search(pchar(AStr),Length(AStr));
-end;
-
-function pcFastGrepSub(WildCard, aStr, aRepl: string): string;
-var
- PpcRE:PpcRegExp;
-begin
- PpcRE:=PRegExpCache^.CheckNew(WildCard);
- if PpcRE^.Search(pchar(AStr),Length(AStr)) then
- pcFastGrepSub:=PpcRE^.GetReplStr(pchar(AStr),ARepl)
- else
- pcFastGrepSub:='';
-end;
-
-{$IFDEF PCRE_5_0}
-function pcGetVersion : pchar; assembler; {$FRAME-}{$USES none}
-asm
- call pcre_version
-end;
-{$ENDIF PCRE_5_0}
-
-function pcError;
-var P: ppcRegExp absolute pRegExp;
-begin
- Result := (P = nil) or P^.Error;
- If Result and (P <> nil) then
- begin
-{ if P^.ErrorPos = 0 then
- MessageBox(GetString(erRegExpCompile)+'"'+P^.ErrorStr+'"', nil,mfConfirmation+mfOkButton)
- else}
- MessageBox(GetString(erRegExpCompile)+'"'+P^.ErrorStr+'"'+GetString(erRegExpCompPos),
- @P^.ErrorPos,mfConfirmation+mfOkButton);
- Dispose(P, Done);
- P:=nil;
- end;
-end;
-
-function pcInit;
-var Options : Integer;
-begin
- If CaseSens then Options := 0 else Options := PCRE_CASELESS;
- Result := New( PpcRegExp, Init( Pattern,
- {DefaultOptions}
- startup.MiscMultiData.cfgRegEx.DefaultOptions or Options,
- DefaultLocaleTable) );
-end;
-
-Initialization
- PRegExpCache:=New(PRegExpCollection,Init(64));
-Finalization
- Dispose(PRegExpCache,Done);
-End.
diff --git a/src/third_party/pcre-8.38/pcregrep.c b/src/third_party/pcre-8.38/pcregrep.c deleted file mode 100644 index 64986b016e6..00000000000 --- a/src/third_party/pcre-8.38/pcregrep.c +++ /dev/null @@ -1,3325 +0,0 @@ -/************************************************* -* pcregrep program * -*************************************************/ - -/* This is a grep program that uses the PCRE regular expression library to do -its pattern matching. On Unix-like, Windows, and native z/OS systems it can -recurse into directories, and in z/OS it can handle PDS files. - -Note that for native z/OS, in addition to defining the NATIVE_ZOS macro, an -additional header is required. That header is not included in the main PCRE -distribution because other apparatus is needed to compile pcregrep for z/OS. -The header can be found in the special z/OS distribution, which is available -from www.zaconsultants.net or from www.cbttape.org. - - Copyright (c) 1997-2014 University of Cambridge - ------------------------------------------------------------------------------ -Redistribution and use in source and binary forms, with or without -modification, are permitted provided that the following conditions are met: - - * Redistributions of source code must retain the above copyright notice, - this list of conditions and the following disclaimer. - - * Redistributions in binary form must reproduce the above copyright - notice, this list of conditions and the following disclaimer in the - documentation and/or other materials provided with the distribution. - - * Neither the name of the University of Cambridge nor the names of its - contributors may be used to endorse or promote products derived from - this software without specific prior written permission. - -THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS" -AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE -IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE -ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR CONTRIBUTORS BE -LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR -CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF -SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS -INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN -CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) -ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE -POSSIBILITY OF SUCH DAMAGE. ------------------------------------------------------------------------------ -*/ - -#ifdef HAVE_CONFIG_H -#include "config.h" -#endif - -#include <ctype.h> -#include <locale.h> -#include <stdio.h> -#include <string.h> -#include <stdlib.h> -#include <errno.h> - -#include <sys/types.h> -#include <sys/stat.h> - -#ifdef HAVE_UNISTD_H -#include <unistd.h> -#endif - -#ifdef SUPPORT_LIBZ -#include <zlib.h> -#endif - -#ifdef SUPPORT_LIBBZ2 -#include <bzlib.h> -#endif - -#include "pcre.h" - -#define FALSE 0 -#define TRUE 1 - -typedef int BOOL; - -#define OFFSET_SIZE 99 - -#if BUFSIZ > 8192 -#define MAXPATLEN BUFSIZ -#else -#define MAXPATLEN 8192 -#endif - -#define PATBUFSIZE (MAXPATLEN + 10) /* Allows for prefix+suffix */ - -/* Values for the "filenames" variable, which specifies options for file name -output. The order is important; it is assumed that a file name is wanted for -all values greater than FN_DEFAULT. */ - -enum { FN_NONE, FN_DEFAULT, FN_MATCH_ONLY, FN_NOMATCH_ONLY, FN_FORCE }; - -/* File reading styles */ - -enum { FR_PLAIN, FR_LIBZ, FR_LIBBZ2 }; - -/* Actions for the -d and -D options */ - -enum { dee_READ, dee_SKIP, dee_RECURSE }; -enum { DEE_READ, DEE_SKIP }; - -/* Actions for special processing options (flag bits) */ - -#define PO_WORD_MATCH 0x0001 -#define PO_LINE_MATCH 0x0002 -#define PO_FIXED_STRINGS 0x0004 - -/* Line ending types */ - -enum { EL_LF, EL_CR, EL_CRLF, EL_ANY, EL_ANYCRLF }; - -/* Binary file options */ - -enum { BIN_BINARY, BIN_NOMATCH, BIN_TEXT }; - -/* In newer versions of gcc, with FORTIFY_SOURCE set (the default in some -environments), a warning is issued if the value of fwrite() is ignored. -Unfortunately, casting to (void) does not suppress the warning. To get round -this, we use a macro that compiles a fudge. Oddly, this does not also seem to -apply to fprintf(). */ - -#define FWRITE(a,b,c,d) if (fwrite(a,b,c,d)) {} - - - -/************************************************* -* Global variables * -*************************************************/ - -/* Jeffrey Friedl has some debugging requirements that are not part of the -regular code. */ - -#ifdef JFRIEDL_DEBUG -static int S_arg = -1; -static unsigned int jfriedl_XR = 0; /* repeat regex attempt this many times */ -static unsigned int jfriedl_XT = 0; /* replicate text this many times */ -static const char *jfriedl_prefix = ""; -static const char *jfriedl_postfix = ""; -#endif - -static int endlinetype; - -static char *colour_string = (char *)"1;31"; -static char *colour_option = NULL; -static char *dee_option = NULL; -static char *DEE_option = NULL; -static char *locale = NULL; -static char *main_buffer = NULL; -static char *newline = NULL; -static char *om_separator = (char *)""; -static char *stdin_name = (char *)"(standard input)"; - -static const unsigned char *pcretables = NULL; - -static int after_context = 0; -static int before_context = 0; -static int binary_files = BIN_BINARY; -static int both_context = 0; -static int bufthird = PCREGREP_BUFSIZE; -static int bufsize = 3*PCREGREP_BUFSIZE; - -#if defined HAVE_WINDOWS_H && HAVE_WINDOWS_H -static int dee_action = dee_SKIP; -#else -static int dee_action = dee_READ; -#endif - -static int DEE_action = DEE_READ; -static int error_count = 0; -static int filenames = FN_DEFAULT; -static int pcre_options = 0; -static int process_options = 0; - -#ifdef SUPPORT_PCREGREP_JIT -static int study_options = PCRE_STUDY_JIT_COMPILE; -#else -static int study_options = 0; -#endif - -static unsigned long int match_limit = 0; -static unsigned long int match_limit_recursion = 0; - -static BOOL count_only = FALSE; -static BOOL do_colour = FALSE; -static BOOL file_offsets = FALSE; -static BOOL hyphenpending = FALSE; -static BOOL invert = FALSE; -static BOOL line_buffered = FALSE; -static BOOL line_offsets = FALSE; -static BOOL multiline = FALSE; -static BOOL number = FALSE; -static BOOL omit_zero_count = FALSE; -static BOOL resource_error = FALSE; -static BOOL quiet = FALSE; -static BOOL show_only_matching = FALSE; -static BOOL silent = FALSE; -static BOOL utf8 = FALSE; - -/* Structure for list of --only-matching capturing numbers. */ - -typedef struct omstr { - struct omstr *next; - int groupnum; -} omstr; - -static omstr *only_matching = NULL; -static omstr *only_matching_last = NULL; - -/* Structure for holding the two variables that describe a number chain. */ - -typedef struct omdatastr { - omstr **anchor; - omstr **lastptr; -} omdatastr; - -static omdatastr only_matching_data = { &only_matching, &only_matching_last }; - -/* Structure for list of file names (for -f and --{in,ex}clude-from) */ - -typedef struct fnstr { - struct fnstr *next; - char *name; -} fnstr; - -static fnstr *exclude_from = NULL; -static fnstr *exclude_from_last = NULL; -static fnstr *include_from = NULL; -static fnstr *include_from_last = NULL; - -static fnstr *file_lists = NULL; -static fnstr *file_lists_last = NULL; -static fnstr *pattern_files = NULL; -static fnstr *pattern_files_last = NULL; - -/* Structure for holding the two variables that describe a file name chain. */ - -typedef struct fndatastr { - fnstr **anchor; - fnstr **lastptr; -} fndatastr; - -static fndatastr exclude_from_data = { &exclude_from, &exclude_from_last }; -static fndatastr include_from_data = { &include_from, &include_from_last }; -static fndatastr file_lists_data = { &file_lists, &file_lists_last }; -static fndatastr pattern_files_data = { &pattern_files, &pattern_files_last }; - -/* Structure for pattern and its compiled form; used for matching patterns and -also for include/exclude patterns. */ - -typedef struct patstr { - struct patstr *next; - char *string; - pcre *compiled; - pcre_extra *hint; -} patstr; - -static patstr *patterns = NULL; -static patstr *patterns_last = NULL; -static patstr *include_patterns = NULL; -static patstr *include_patterns_last = NULL; -static patstr *exclude_patterns = NULL; -static patstr *exclude_patterns_last = NULL; -static patstr *include_dir_patterns = NULL; -static patstr *include_dir_patterns_last = NULL; -static patstr *exclude_dir_patterns = NULL; -static patstr *exclude_dir_patterns_last = NULL; - -/* Structure holding the two variables that describe a pattern chain. A pointer -to such structures is used for each appropriate option. */ - -typedef struct patdatastr { - patstr **anchor; - patstr **lastptr; -} patdatastr; - -static patdatastr match_patdata = { &patterns, &patterns_last }; -static patdatastr include_patdata = { &include_patterns, &include_patterns_last }; -static patdatastr exclude_patdata = { &exclude_patterns, &exclude_patterns_last }; -static patdatastr include_dir_patdata = { &include_dir_patterns, &include_dir_patterns_last }; -static patdatastr exclude_dir_patdata = { &exclude_dir_patterns, &exclude_dir_patterns_last }; - -static patstr **incexlist[4] = { &include_patterns, &exclude_patterns, - &include_dir_patterns, &exclude_dir_patterns }; - -static const char *incexname[4] = { "--include", "--exclude", - "--include-dir", "--exclude-dir" }; - -/* Structure for options and list of them */ - -enum { OP_NODATA, OP_STRING, OP_OP_STRING, OP_NUMBER, OP_LONGNUMBER, - OP_OP_NUMBER, OP_OP_NUMBERS, OP_PATLIST, OP_FILELIST, OP_BINFILES }; - -typedef struct option_item { - int type; - int one_char; - void *dataptr; - const char *long_name; - const char *help_text; -} option_item; - -/* Options without a single-letter equivalent get a negative value. This can be -used to identify them. */ - -#define N_COLOUR (-1) -#define N_EXCLUDE (-2) -#define N_EXCLUDE_DIR (-3) -#define N_HELP (-4) -#define N_INCLUDE (-5) -#define N_INCLUDE_DIR (-6) -#define N_LABEL (-7) -#define N_LOCALE (-8) -#define N_NULL (-9) -#define N_LOFFSETS (-10) -#define N_FOFFSETS (-11) -#define N_LBUFFER (-12) -#define N_M_LIMIT (-13) -#define N_M_LIMIT_REC (-14) -#define N_BUFSIZE (-15) -#define N_NOJIT (-16) -#define N_FILE_LIST (-17) -#define N_BINARY_FILES (-18) -#define N_EXCLUDE_FROM (-19) -#define N_INCLUDE_FROM (-20) -#define N_OM_SEPARATOR (-21) - -static option_item optionlist[] = { - { OP_NODATA, N_NULL, NULL, "", "terminate options" }, - { OP_NODATA, N_HELP, NULL, "help", "display this help and exit" }, - { OP_NUMBER, 'A', &after_context, "after-context=number", "set number of following context lines" }, - { OP_NODATA, 'a', NULL, "text", "treat binary files as text" }, - { OP_NUMBER, 'B', &before_context, "before-context=number", "set number of prior context lines" }, - { OP_BINFILES, N_BINARY_FILES, NULL, "binary-files=word", "set treatment of binary files" }, - { OP_NUMBER, N_BUFSIZE,&bufthird, "buffer-size=number", "set processing buffer size parameter" }, - { OP_OP_STRING, N_COLOUR, &colour_option, "color=option", "matched text color option" }, - { OP_OP_STRING, N_COLOUR, &colour_option, "colour=option", "matched text colour option" }, - { OP_NUMBER, 'C', &both_context, "context=number", "set number of context lines, before & after" }, - { OP_NODATA, 'c', NULL, "count", "print only a count of matching lines per FILE" }, - { OP_STRING, 'D', &DEE_option, "devices=action","how to handle devices, FIFOs, and sockets" }, - { OP_STRING, 'd', &dee_option, "directories=action", "how to handle directories" }, - { OP_PATLIST, 'e', &match_patdata, "regex(p)=pattern", "specify pattern (may be used more than once)" }, - { OP_NODATA, 'F', NULL, "fixed-strings", "patterns are sets of newline-separated strings" }, - { OP_FILELIST, 'f', &pattern_files_data, "file=path", "read patterns from file" }, - { OP_FILELIST, N_FILE_LIST, &file_lists_data, "file-list=path","read files to search from file" }, - { OP_NODATA, N_FOFFSETS, NULL, "file-offsets", "output file offsets, not text" }, - { OP_NODATA, 'H', NULL, "with-filename", "force the prefixing filename on output" }, - { OP_NODATA, 'h', NULL, "no-filename", "suppress the prefixing filename on output" }, - { OP_NODATA, 'I', NULL, "", "treat binary files as not matching (ignore)" }, - { OP_NODATA, 'i', NULL, "ignore-case", "ignore case distinctions" }, -#ifdef SUPPORT_PCREGREP_JIT - { OP_NODATA, N_NOJIT, NULL, "no-jit", "do not use just-in-time compiler optimization" }, -#else - { OP_NODATA, N_NOJIT, NULL, "no-jit", "ignored: this pcregrep does not support JIT" }, -#endif - { OP_NODATA, 'l', NULL, "files-with-matches", "print only FILE names containing matches" }, - { OP_NODATA, 'L', NULL, "files-without-match","print only FILE names not containing matches" }, - { OP_STRING, N_LABEL, &stdin_name, "label=name", "set name for standard input" }, - { OP_NODATA, N_LBUFFER, NULL, "line-buffered", "use line buffering" }, - { OP_NODATA, N_LOFFSETS, NULL, "line-offsets", "output line numbers and offsets, not text" }, - { OP_STRING, N_LOCALE, &locale, "locale=locale", "use the named locale" }, - { OP_LONGNUMBER, N_M_LIMIT, &match_limit, "match-limit=number", "set PCRE match limit option" }, - { OP_LONGNUMBER, N_M_LIMIT_REC, &match_limit_recursion, "recursion-limit=number", "set PCRE match recursion limit option" }, - { OP_NODATA, 'M', NULL, "multiline", "run in multiline mode" }, - { OP_STRING, 'N', &newline, "newline=type", "set newline type (CR, LF, CRLF, ANYCRLF or ANY)" }, - { OP_NODATA, 'n', NULL, "line-number", "print line number with output lines" }, - { OP_OP_NUMBERS, 'o', &only_matching_data, "only-matching=n", "show only the part of the line that matched" }, - { OP_STRING, N_OM_SEPARATOR, &om_separator, "om-separator=text", "set separator for multiple -o output" }, - { OP_NODATA, 'q', NULL, "quiet", "suppress output, just set return code" }, - { OP_NODATA, 'r', NULL, "recursive", "recursively scan sub-directories" }, - { OP_PATLIST, N_EXCLUDE,&exclude_patdata, "exclude=pattern","exclude matching files when recursing" }, - { OP_PATLIST, N_INCLUDE,&include_patdata, "include=pattern","include matching files when recursing" }, - { OP_PATLIST, N_EXCLUDE_DIR,&exclude_dir_patdata, "exclude-dir=pattern","exclude matching directories when recursing" }, - { OP_PATLIST, N_INCLUDE_DIR,&include_dir_patdata, "include-dir=pattern","include matching directories when recursing" }, - { OP_FILELIST, N_EXCLUDE_FROM,&exclude_from_data, "exclude-from=path", "read exclude list from file" }, - { OP_FILELIST, N_INCLUDE_FROM,&include_from_data, "include-from=path", "read include list from file" }, - - /* These two were accidentally implemented with underscores instead of - hyphens in the option names. As this was not discovered for several releases, - the incorrect versions are left in the table for compatibility. However, the - --help function misses out any option that has an underscore in its name. */ - - { OP_PATLIST, N_EXCLUDE_DIR,&exclude_dir_patdata, "exclude_dir=pattern","exclude matching directories when recursing" }, - { OP_PATLIST, N_INCLUDE_DIR,&include_dir_patdata, "include_dir=pattern","include matching directories when recursing" }, - -#ifdef JFRIEDL_DEBUG - { OP_OP_NUMBER, 'S', &S_arg, "jeffS", "replace matched (sub)string with X" }, -#endif - { OP_NODATA, 's', NULL, "no-messages", "suppress error messages" }, - { OP_NODATA, 'u', NULL, "utf-8", "use UTF-8 mode" }, - { OP_NODATA, 'V', NULL, "version", "print version information and exit" }, - { OP_NODATA, 'v', NULL, "invert-match", "select non-matching lines" }, - { OP_NODATA, 'w', NULL, "word-regex(p)", "force patterns to match only as words" }, - { OP_NODATA, 'x', NULL, "line-regex(p)", "force patterns to match only whole lines" }, - { OP_NODATA, 0, NULL, NULL, NULL } -}; - -/* Tables for prefixing and suffixing patterns, according to the -w, -x, and -F -options. These set the 1, 2, and 4 bits in process_options, respectively. Note -that the combination of -w and -x has the same effect as -x on its own, so we -can treat them as the same. Note that the MAXPATLEN macro assumes the longest -prefix+suffix is 10 characters; if anything longer is added, it must be -adjusted. */ - -static const char *prefix[] = { - "", "\\b", "^(?:", "^(?:", "\\Q", "\\b\\Q", "^(?:\\Q", "^(?:\\Q" }; - -static const char *suffix[] = { - "", "\\b", ")$", ")$", "\\E", "\\E\\b", "\\E)$", "\\E)$" }; - -/* UTF-8 tables - used only when the newline setting is "any". */ - -const int utf8_table3[] = { 0xff, 0x1f, 0x0f, 0x07, 0x03, 0x01}; - -const char utf8_table4[] = { - 1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1, - 1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1, - 2,2,2,2,2,2,2,2,2,2,2,2,2,2,2,2, - 3,3,3,3,3,3,3,3,4,4,4,4,5,5,5,5 }; - - - -/************************************************* -* Exit from the program * -*************************************************/ - -/* If there has been a resource error, give a suitable message. - -Argument: the return code -Returns: does not return -*/ - -static void -pcregrep_exit(int rc) -{ -if (resource_error) - { - fprintf(stderr, "pcregrep: Error %d, %d or %d means that a resource limit " - "was exceeded.\n", PCRE_ERROR_MATCHLIMIT, PCRE_ERROR_RECURSIONLIMIT, - PCRE_ERROR_JIT_STACKLIMIT); - fprintf(stderr, "pcregrep: Check your regex for nested unlimited loops.\n"); - } -exit(rc); -} - - -/************************************************* -* Add item to chain of patterns * -*************************************************/ - -/* Used to add an item onto a chain, or just return an unconnected item if the -"after" argument is NULL. - -Arguments: - s pattern string to add - after if not NULL points to item to insert after - -Returns: new pattern block or NULL on error -*/ - -static patstr * -add_pattern(char *s, patstr *after) -{ -patstr *p = (patstr *)malloc(sizeof(patstr)); -if (p == NULL) - { - fprintf(stderr, "pcregrep: malloc failed\n"); - pcregrep_exit(2); - } -if (strlen(s) > MAXPATLEN) - { - fprintf(stderr, "pcregrep: pattern is too long (limit is %d bytes)\n", - MAXPATLEN); - free(p); - return NULL; - } -p->next = NULL; -p->string = s; -p->compiled = NULL; -p->hint = NULL; - -if (after != NULL) - { - p->next = after->next; - after->next = p; - } -return p; -} - - -/************************************************* -* Free chain of patterns * -*************************************************/ - -/* Used for several chains of patterns. - -Argument: pointer to start of chain -Returns: nothing -*/ - -static void -free_pattern_chain(patstr *pc) -{ -while (pc != NULL) - { - patstr *p = pc; - pc = p->next; - if (p->hint != NULL) pcre_free_study(p->hint); - if (p->compiled != NULL) pcre_free(p->compiled); - free(p); - } -} - - -/************************************************* -* Free chain of file names * -*************************************************/ - -/* -Argument: pointer to start of chain -Returns: nothing -*/ - -static void -free_file_chain(fnstr *fn) -{ -while (fn != NULL) - { - fnstr *f = fn; - fn = f->next; - free(f); - } -} - - -/************************************************* -* OS-specific functions * -*************************************************/ - -/* These functions are defined so that they can be made system specific. -At present there are versions for Unix-style environments, Windows, native -z/OS, and "no support". */ - - -/************* Directory scanning Unix-style and z/OS ***********/ - -#if (defined HAVE_SYS_STAT_H && defined HAVE_DIRENT_H && defined HAVE_SYS_TYPES_H) || defined NATIVE_ZOS -#include <sys/types.h> -#include <sys/stat.h> -#include <dirent.h> - -#if defined NATIVE_ZOS -/************* Directory and PDS/E scanning for z/OS ***********/ -/************* z/OS looks mostly like Unix with USS ************/ -/* However, z/OS needs the #include statements in this header */ -#include "pcrzosfs.h" -/* That header is not included in the main PCRE distribution because - other apparatus is needed to compile pcregrep for z/OS. The header - can be found in the special z/OS distribution, which is available - from www.zaconsultants.net or from www.cbttape.org. */ -#endif - -typedef DIR directory_type; -#define FILESEP '/' - -static int -isdirectory(char *filename) -{ -struct stat statbuf; -if (stat(filename, &statbuf) < 0) - return 0; /* In the expectation that opening as a file will fail */ -return (statbuf.st_mode & S_IFMT) == S_IFDIR; -} - -static directory_type * -opendirectory(char *filename) -{ -return opendir(filename); -} - -static char * -readdirectory(directory_type *dir) -{ -for (;;) - { - struct dirent *dent = readdir(dir); - if (dent == NULL) return NULL; - if (strcmp(dent->d_name, ".") != 0 && strcmp(dent->d_name, "..") != 0) - return dent->d_name; - } -/* Control never reaches here */ -} - -static void -closedirectory(directory_type *dir) -{ -closedir(dir); -} - - -/************* Test for regular file, Unix-style **********/ - -static int -isregfile(char *filename) -{ -struct stat statbuf; -if (stat(filename, &statbuf) < 0) - return 1; /* In the expectation that opening as a file will fail */ -return (statbuf.st_mode & S_IFMT) == S_IFREG; -} - - -#if defined NATIVE_ZOS -/************* Test for a terminal in z/OS **********/ -/* isatty() does not work in a TSO environment, so always give FALSE.*/ - -static BOOL -is_stdout_tty(void) -{ -return FALSE; -} - -static BOOL -is_file_tty(FILE *f) -{ -return FALSE; -} - - -/************* Test for a terminal, Unix-style **********/ - -#else -static BOOL -is_stdout_tty(void) -{ -return isatty(fileno(stdout)); -} - -static BOOL -is_file_tty(FILE *f) -{ -return isatty(fileno(f)); -} -#endif - -/* End of Unix-style or native z/OS environment functions. */ - - -/************* Directory scanning in Windows ***********/ - -/* I (Philip Hazel) have no means of testing this code. It was contributed by -Lionel Fourquaux. David Burgess added a patch to define INVALID_FILE_ATTRIBUTES -when it did not exist. David Byron added a patch that moved the #include of -<windows.h> to before the INVALID_FILE_ATTRIBUTES definition rather than after. -The double test below stops gcc 4.4.4 grumbling that HAVE_WINDOWS_H is -undefined when it is indeed undefined. */ - -#elif defined HAVE_WINDOWS_H && HAVE_WINDOWS_H - -#ifndef STRICT -# define STRICT -#endif -#ifndef WIN32_LEAN_AND_MEAN -# define WIN32_LEAN_AND_MEAN -#endif - -#include <windows.h> - -#ifndef INVALID_FILE_ATTRIBUTES -#define INVALID_FILE_ATTRIBUTES 0xFFFFFFFF -#endif - -typedef struct directory_type -{ -HANDLE handle; -BOOL first; -WIN32_FIND_DATA data; -} directory_type; - -#define FILESEP '/' - -int -isdirectory(char *filename) -{ -DWORD attr = GetFileAttributes(filename); -if (attr == INVALID_FILE_ATTRIBUTES) - return 0; -return (attr & FILE_ATTRIBUTE_DIRECTORY) != 0; -} - -directory_type * -opendirectory(char *filename) -{ -size_t len; -char *pattern; -directory_type *dir; -DWORD err; -len = strlen(filename); -pattern = (char *)malloc(len + 3); -dir = (directory_type *)malloc(sizeof(*dir)); -if ((pattern == NULL) || (dir == NULL)) - { - fprintf(stderr, "pcregrep: malloc failed\n"); - pcregrep_exit(2); - } -memcpy(pattern, filename, len); -memcpy(&(pattern[len]), "\\*", 3); -dir->handle = FindFirstFile(pattern, &(dir->data)); -if (dir->handle != INVALID_HANDLE_VALUE) - { - free(pattern); - dir->first = TRUE; - return dir; - } -err = GetLastError(); -free(pattern); -free(dir); -errno = (err == ERROR_ACCESS_DENIED) ? EACCES : ENOENT; -return NULL; -} - -char * -readdirectory(directory_type *dir) -{ -for (;;) - { - if (!dir->first) - { - if (!FindNextFile(dir->handle, &(dir->data))) - return NULL; - } - else - { - dir->first = FALSE; - } - if (strcmp(dir->data.cFileName, ".") != 0 && strcmp(dir->data.cFileName, "..") != 0) - return dir->data.cFileName; - } -#ifndef _MSC_VER -return NULL; /* Keep compiler happy; never executed */ -#endif -} - -void -closedirectory(directory_type *dir) -{ -FindClose(dir->handle); -free(dir); -} - - -/************* Test for regular file in Windows **********/ - -/* I don't know how to do this, or if it can be done; assume all paths are -regular if they are not directories. */ - -int isregfile(char *filename) -{ -return !isdirectory(filename); -} - - -/************* Test for a terminal in Windows **********/ - -/* I don't know how to do this; assume never */ - -static BOOL -is_stdout_tty(void) -{ -return FALSE; -} - -static BOOL -is_file_tty(FILE *f) -{ -return FALSE; -} - -/* End of Windows functions */ - - -/************* Directory scanning when we can't do it ***********/ - -/* The type is void, and apart from isdirectory(), the functions do nothing. */ - -#else - -#define FILESEP 0 -typedef void directory_type; - -int isdirectory(char *filename) { return 0; } -directory_type * opendirectory(char *filename) { return (directory_type*)0;} -char *readdirectory(directory_type *dir) { return (char*)0;} -void closedirectory(directory_type *dir) {} - - -/************* Test for regular file when we can't do it **********/ - -/* Assume all files are regular. */ - -int isregfile(char *filename) { return 1; } - - -/************* Test for a terminal when we can't do it **********/ - -static BOOL -is_stdout_tty(void) -{ -return FALSE; -} - -static BOOL -is_file_tty(FILE *f) -{ -return FALSE; -} - -#endif /* End of system-specific functions */ - - - -#ifndef HAVE_STRERROR -/************************************************* -* Provide strerror() for non-ANSI libraries * -*************************************************/ - -/* Some old-fashioned systems still around (e.g. SunOS4) don't have strerror() -in their libraries, but can provide the same facility by this simple -alternative function. */ - -extern int sys_nerr; -extern char *sys_errlist[]; - -char * -strerror(int n) -{ -if (n < 0 || n >= sys_nerr) return "unknown error number"; -return sys_errlist[n]; -} -#endif /* HAVE_STRERROR */ - - - -/************************************************* -* Usage function * -*************************************************/ - -static int -usage(int rc) -{ -option_item *op; -fprintf(stderr, "Usage: pcregrep [-"); -for (op = optionlist; op->one_char != 0; op++) - { - if (op->one_char > 0) fprintf(stderr, "%c", op->one_char); - } -fprintf(stderr, "] [long options] [pattern] [files]\n"); -fprintf(stderr, "Type `pcregrep --help' for more information and the long " - "options.\n"); -return rc; -} - - - -/************************************************* -* Help function * -*************************************************/ - -static void -help(void) -{ -option_item *op; - -printf("Usage: pcregrep [OPTION]... [PATTERN] [FILE1 FILE2 ...]\n"); -printf("Search for PATTERN in each FILE or standard input.\n"); -printf("PATTERN must be present if neither -e nor -f is used.\n"); -printf("\"-\" can be used as a file name to mean STDIN.\n"); - -#ifdef SUPPORT_LIBZ -printf("Files whose names end in .gz are read using zlib.\n"); -#endif - -#ifdef SUPPORT_LIBBZ2 -printf("Files whose names end in .bz2 are read using bzlib2.\n"); -#endif - -#if defined SUPPORT_LIBZ || defined SUPPORT_LIBBZ2 -printf("Other files and the standard input are read as plain files.\n\n"); -#else -printf("All files are read as plain files, without any interpretation.\n\n"); -#endif - -printf("Example: pcregrep -i 'hello.*world' menu.h main.c\n\n"); -printf("Options:\n"); - -for (op = optionlist; op->one_char != 0; op++) - { - int n; - char s[4]; - - /* Two options were accidentally implemented and documented with underscores - instead of hyphens in their names, something that was not noticed for quite a - few releases. When fixing this, I left the underscored versions in the list - in case people were using them. However, we don't want to display them in the - help data. There are no other options that contain underscores, and we do not - expect ever to implement such options. Therefore, just omit any option that - contains an underscore. */ - - if (strchr(op->long_name, '_') != NULL) continue; - - if (op->one_char > 0 && (op->long_name)[0] == 0) - n = 31 - printf(" -%c", op->one_char); - else - { - if (op->one_char > 0) sprintf(s, "-%c,", op->one_char); - else strcpy(s, " "); - n = 31 - printf(" %s --%s", s, op->long_name); - } - - if (n < 1) n = 1; - printf("%.*s%s\n", n, " ", op->help_text); - } - -printf("\nNumbers may be followed by K or M, e.g. --buffer-size=100K.\n"); -printf("The default value for --buffer-size is %d.\n", PCREGREP_BUFSIZE); -printf("When reading patterns or file names from a file, trailing white\n"); -printf("space is removed and blank lines are ignored.\n"); -printf("The maximum size of any pattern is %d bytes.\n", MAXPATLEN); - -printf("\nWith no FILEs, read standard input. If fewer than two FILEs given, assume -h.\n"); -printf("Exit status is 0 if any matches, 1 if no matches, and 2 if trouble.\n"); -} - - - -/************************************************* -* Test exclude/includes * -*************************************************/ - -/* If any exclude pattern matches, the path is excluded. Otherwise, unless -there are no includes, the path must match an include pattern. - -Arguments: - path the path to be matched - ip the chain of include patterns - ep the chain of exclude patterns - -Returns: TRUE if the path is not excluded -*/ - -static BOOL -test_incexc(char *path, patstr *ip, patstr *ep) -{ -int plen = strlen(path); - -for (; ep != NULL; ep = ep->next) - { - if (pcre_exec(ep->compiled, NULL, path, plen, 0, 0, NULL, 0) >= 0) - return FALSE; - } - -if (ip == NULL) return TRUE; - -for (; ip != NULL; ip = ip->next) - { - if (pcre_exec(ip->compiled, NULL, path, plen, 0, 0, NULL, 0) >= 0) - return TRUE; - } - -return FALSE; -} - - - -/************************************************* -* Decode integer argument value * -*************************************************/ - -/* Integer arguments can be followed by K or M. Avoid the use of strtoul() -because SunOS4 doesn't have it. This is used only for unpicking arguments, so -just keep it simple. - -Arguments: - option_data the option data string - op the option item (for error messages) - longop TRUE if option given in long form - -Returns: a long integer -*/ - -static long int -decode_number(char *option_data, option_item *op, BOOL longop) -{ -unsigned long int n = 0; -char *endptr = option_data; -while (*endptr != 0 && isspace((unsigned char)(*endptr))) endptr++; -while (isdigit((unsigned char)(*endptr))) - n = n * 10 + (int)(*endptr++ - '0'); -if (toupper(*endptr) == 'K') - { - n *= 1024; - endptr++; - } -else if (toupper(*endptr) == 'M') - { - n *= 1024*1024; - endptr++; - } - -if (*endptr != 0) /* Error */ - { - if (longop) - { - char *equals = strchr(op->long_name, '='); - int nlen = (equals == NULL)? (int)strlen(op->long_name) : - (int)(equals - op->long_name); - fprintf(stderr, "pcregrep: Malformed number \"%s\" after --%.*s\n", - option_data, nlen, op->long_name); - } - else - fprintf(stderr, "pcregrep: Malformed number \"%s\" after -%c\n", - option_data, op->one_char); - pcregrep_exit(usage(2)); - } - -return n; -} - - - -/************************************************* -* Add item to a chain of numbers * -*************************************************/ - -/* Used to add an item onto a chain, or just return an unconnected item if the -"after" argument is NULL. - -Arguments: - n the number to add - after if not NULL points to item to insert after - -Returns: new number block -*/ - -static omstr * -add_number(int n, omstr *after) -{ -omstr *om = (omstr *)malloc(sizeof(omstr)); - -if (om == NULL) - { - fprintf(stderr, "pcregrep: malloc failed\n"); - pcregrep_exit(2); - } -om->next = NULL; -om->groupnum = n; - -if (after != NULL) - { - om->next = after->next; - after->next = om; - } -return om; -} - - - -/************************************************* -* Read one line of input * -*************************************************/ - -/* Normally, input is read using fread() into a large buffer, so many lines may -be read at once. However, doing this for tty input means that no output appears -until a lot of input has been typed. Instead, tty input is handled line by -line. We cannot use fgets() for this, because it does not stop at a binary -zero, and therefore there is no way of telling how many characters it has read, -because there may be binary zeros embedded in the data. - -Arguments: - buffer the buffer to read into - length the maximum number of characters to read - f the file - -Returns: the number of characters read, zero at end of file -*/ - -static unsigned int -read_one_line(char *buffer, int length, FILE *f) -{ -int c; -int yield = 0; -while ((c = fgetc(f)) != EOF) - { - buffer[yield++] = c; - if (c == '\n' || yield >= length) break; - } -return yield; -} - - - -/************************************************* -* Find end of line * -*************************************************/ - -/* The length of the endline sequence that is found is set via lenptr. This may -be zero at the very end of the file if there is no line-ending sequence there. - -Arguments: - p current position in line - endptr end of available data - lenptr where to put the length of the eol sequence - -Returns: pointer after the last byte of the line, - including the newline byte(s) -*/ - -static char * -end_of_line(char *p, char *endptr, int *lenptr) -{ -switch(endlinetype) - { - default: /* Just in case */ - case EL_LF: - while (p < endptr && *p != '\n') p++; - if (p < endptr) - { - *lenptr = 1; - return p + 1; - } - *lenptr = 0; - return endptr; - - case EL_CR: - while (p < endptr && *p != '\r') p++; - if (p < endptr) - { - *lenptr = 1; - return p + 1; - } - *lenptr = 0; - return endptr; - - case EL_CRLF: - for (;;) - { - while (p < endptr && *p != '\r') p++; - if (++p >= endptr) - { - *lenptr = 0; - return endptr; - } - if (*p == '\n') - { - *lenptr = 2; - return p + 1; - } - } - break; - - case EL_ANYCRLF: - while (p < endptr) - { - int extra = 0; - register int c = *((unsigned char *)p); - - if (utf8 && c >= 0xc0) - { - int gcii, gcss; - extra = utf8_table4[c & 0x3f]; /* Number of additional bytes */ - gcss = 6*extra; - c = (c & utf8_table3[extra]) << gcss; - for (gcii = 1; gcii <= extra; gcii++) - { - gcss -= 6; - c |= (p[gcii] & 0x3f) << gcss; - } - } - - p += 1 + extra; - - switch (c) - { - case '\n': - *lenptr = 1; - return p; - - case '\r': - if (p < endptr && *p == '\n') - { - *lenptr = 2; - p++; - } - else *lenptr = 1; - return p; - - default: - break; - } - } /* End of loop for ANYCRLF case */ - - *lenptr = 0; /* Must have hit the end */ - return endptr; - - case EL_ANY: - while (p < endptr) - { - int extra = 0; - register int c = *((unsigned char *)p); - - if (utf8 && c >= 0xc0) - { - int gcii, gcss; - extra = utf8_table4[c & 0x3f]; /* Number of additional bytes */ - gcss = 6*extra; - c = (c & utf8_table3[extra]) << gcss; - for (gcii = 1; gcii <= extra; gcii++) - { - gcss -= 6; - c |= (p[gcii] & 0x3f) << gcss; - } - } - - p += 1 + extra; - - switch (c) - { - case '\n': /* LF */ - case '\v': /* VT */ - case '\f': /* FF */ - *lenptr = 1; - return p; - - case '\r': /* CR */ - if (p < endptr && *p == '\n') - { - *lenptr = 2; - p++; - } - else *lenptr = 1; - return p; - -#ifndef EBCDIC - case 0x85: /* Unicode NEL */ - *lenptr = utf8? 2 : 1; - return p; - - case 0x2028: /* Unicode LS */ - case 0x2029: /* Unicode PS */ - *lenptr = 3; - return p; -#endif /* Not EBCDIC */ - - default: - break; - } - } /* End of loop for ANY case */ - - *lenptr = 0; /* Must have hit the end */ - return endptr; - } /* End of overall switch */ -} - - - -/************************************************* -* Find start of previous line * -*************************************************/ - -/* This is called when looking back for before lines to print. - -Arguments: - p start of the subsequent line - startptr start of available data - -Returns: pointer to the start of the previous line -*/ - -static char * -previous_line(char *p, char *startptr) -{ -switch(endlinetype) - { - default: /* Just in case */ - case EL_LF: - p--; - while (p > startptr && p[-1] != '\n') p--; - return p; - - case EL_CR: - p--; - while (p > startptr && p[-1] != '\n') p--; - return p; - - case EL_CRLF: - for (;;) - { - p -= 2; - while (p > startptr && p[-1] != '\n') p--; - if (p <= startptr + 1 || p[-2] == '\r') return p; - } - /* Control can never get here */ - - case EL_ANY: - case EL_ANYCRLF: - if (*(--p) == '\n' && p > startptr && p[-1] == '\r') p--; - if (utf8) while ((*p & 0xc0) == 0x80) p--; - - while (p > startptr) - { - register unsigned int c; - char *pp = p - 1; - - if (utf8) - { - int extra = 0; - while ((*pp & 0xc0) == 0x80) pp--; - c = *((unsigned char *)pp); - if (c >= 0xc0) - { - int gcii, gcss; - extra = utf8_table4[c & 0x3f]; /* Number of additional bytes */ - gcss = 6*extra; - c = (c & utf8_table3[extra]) << gcss; - for (gcii = 1; gcii <= extra; gcii++) - { - gcss -= 6; - c |= (pp[gcii] & 0x3f) << gcss; - } - } - } - else c = *((unsigned char *)pp); - - if (endlinetype == EL_ANYCRLF) switch (c) - { - case '\n': /* LF */ - case '\r': /* CR */ - return p; - - default: - break; - } - - else switch (c) - { - case '\n': /* LF */ - case '\v': /* VT */ - case '\f': /* FF */ - case '\r': /* CR */ -#ifndef EBCDIE - case 0x85: /* Unicode NEL */ - case 0x2028: /* Unicode LS */ - case 0x2029: /* Unicode PS */ -#endif /* Not EBCDIC */ - return p; - - default: - break; - } - - p = pp; /* Back one character */ - } /* End of loop for ANY case */ - - return startptr; /* Hit start of data */ - } /* End of overall switch */ -} - - - - - -/************************************************* -* Print the previous "after" lines * -*************************************************/ - -/* This is called if we are about to lose said lines because of buffer filling, -and at the end of the file. The data in the line is written using fwrite() so -that a binary zero does not terminate it. - -Arguments: - lastmatchnumber the number of the last matching line, plus one - lastmatchrestart where we restarted after the last match - endptr end of available data - printname filename for printing - -Returns: nothing -*/ - -static void -do_after_lines(int lastmatchnumber, char *lastmatchrestart, char *endptr, - char *printname) -{ -if (after_context > 0 && lastmatchnumber > 0) - { - int count = 0; - while (lastmatchrestart < endptr && count++ < after_context) - { - int ellength; - char *pp = lastmatchrestart; - if (printname != NULL) fprintf(stdout, "%s-", printname); - if (number) fprintf(stdout, "%d-", lastmatchnumber++); - pp = end_of_line(pp, endptr, &ellength); - FWRITE(lastmatchrestart, 1, pp - lastmatchrestart, stdout); - lastmatchrestart = pp; - } - hyphenpending = TRUE; - } -} - - - -/************************************************* -* Apply patterns to subject till one matches * -*************************************************/ - -/* This function is called to run through all patterns, looking for a match. It -is used multiple times for the same subject when colouring is enabled, in order -to find all possible matches. - -Arguments: - matchptr the start of the subject - length the length of the subject to match - options options for pcre_exec - startoffset where to start matching - offsets the offets vector to fill in - mrc address of where to put the result of pcre_exec() - -Returns: TRUE if there was a match - FALSE if there was no match - invert if there was a non-fatal error -*/ - -static BOOL -match_patterns(char *matchptr, size_t length, unsigned int options, - int startoffset, int *offsets, int *mrc) -{ -int i; -size_t slen = length; -patstr *p = patterns; -const char *msg = "this text:\n\n"; - -if (slen > 200) - { - slen = 200; - msg = "text that starts:\n\n"; - } -for (i = 1; p != NULL; p = p->next, i++) - { - *mrc = pcre_exec(p->compiled, p->hint, matchptr, (int)length, - startoffset, options, offsets, OFFSET_SIZE); - if (*mrc >= 0) return TRUE; - if (*mrc == PCRE_ERROR_NOMATCH) continue; - fprintf(stderr, "pcregrep: pcre_exec() gave error %d while matching ", *mrc); - if (patterns->next != NULL) fprintf(stderr, "pattern number %d to ", i); - fprintf(stderr, "%s", msg); - FWRITE(matchptr, 1, slen, stderr); /* In case binary zero included */ - fprintf(stderr, "\n\n"); - if (*mrc == PCRE_ERROR_MATCHLIMIT || *mrc == PCRE_ERROR_RECURSIONLIMIT || - *mrc == PCRE_ERROR_JIT_STACKLIMIT) - resource_error = TRUE; - if (error_count++ > 20) - { - fprintf(stderr, "pcregrep: Too many errors - abandoned.\n"); - pcregrep_exit(2); - } - return invert; /* No more matching; don't show the line again */ - } - -return FALSE; /* No match, no errors */ -} - - - -/************************************************* -* Grep an individual file * -*************************************************/ - -/* This is called from grep_or_recurse() below. It uses a buffer that is three -times the value of bufthird. The matching point is never allowed to stray into -the top third of the buffer, thus keeping more of the file available for -context printing or for multiline scanning. For large files, the pointer will -be in the middle third most of the time, so the bottom third is available for -"before" context printing. - -Arguments: - handle the fopened FILE stream for a normal file - the gzFile pointer when reading is via libz - the BZFILE pointer when reading is via libbz2 - frtype FR_PLAIN, FR_LIBZ, or FR_LIBBZ2 - filename the file name or NULL (for errors) - printname the file name if it is to be printed for each match - or NULL if the file name is not to be printed - it cannot be NULL if filenames[_nomatch]_only is set - -Returns: 0 if there was at least one match - 1 otherwise (no matches) - 2 if an overlong line is encountered - 3 if there is a read error on a .bz2 file -*/ - -static int -pcregrep(void *handle, int frtype, char *filename, char *printname) -{ -int rc = 1; -int linenumber = 1; -int lastmatchnumber = 0; -int count = 0; -int filepos = 0; -int offsets[OFFSET_SIZE]; -char *lastmatchrestart = NULL; -char *ptr = main_buffer; -char *endptr; -size_t bufflength; -BOOL binary = FALSE; -BOOL endhyphenpending = FALSE; -BOOL input_line_buffered = line_buffered; -FILE *in = NULL; /* Ensure initialized */ - -#ifdef SUPPORT_LIBZ -gzFile ingz = NULL; -#endif - -#ifdef SUPPORT_LIBBZ2 -BZFILE *inbz2 = NULL; -#endif - - -/* Do the first read into the start of the buffer and set up the pointer to end -of what we have. In the case of libz, a non-zipped .gz file will be read as a -plain file. However, if a .bz2 file isn't actually bzipped, the first read will -fail. */ - -(void)frtype; - -#ifdef SUPPORT_LIBZ -if (frtype == FR_LIBZ) - { - ingz = (gzFile)handle; - bufflength = gzread (ingz, main_buffer, bufsize); - } -else -#endif - -#ifdef SUPPORT_LIBBZ2 -if (frtype == FR_LIBBZ2) - { - inbz2 = (BZFILE *)handle; - bufflength = BZ2_bzread(inbz2, main_buffer, bufsize); - if ((int)bufflength < 0) return 2; /* Gotcha: bufflength is size_t; */ - } /* without the cast it is unsigned. */ -else -#endif - - { - in = (FILE *)handle; - if (is_file_tty(in)) input_line_buffered = TRUE; - bufflength = input_line_buffered? - read_one_line(main_buffer, bufsize, in) : - fread(main_buffer, 1, bufsize, in); - } - -endptr = main_buffer + bufflength; - -/* Unless binary-files=text, see if we have a binary file. This uses the same -rule as GNU grep, namely, a search for a binary zero byte near the start of the -file. */ - -if (binary_files != BIN_TEXT) - { - binary = - memchr(main_buffer, 0, (bufflength > 1024)? 1024 : bufflength) != NULL; - if (binary && binary_files == BIN_NOMATCH) return 1; - } - -/* Loop while the current pointer is not at the end of the file. For large -files, endptr will be at the end of the buffer when we are in the middle of the -file, but ptr will never get there, because as soon as it gets over 2/3 of the -way, the buffer is shifted left and re-filled. */ - -while (ptr < endptr) - { - int endlinelength; - int mrc = 0; - int startoffset = 0; - int prevoffsets[2]; - unsigned int options = 0; - BOOL match; - char *matchptr = ptr; - char *t = ptr; - size_t length, linelength; - - prevoffsets[0] = prevoffsets[1] = -1; - - /* At this point, ptr is at the start of a line. We need to find the length - of the subject string to pass to pcre_exec(). In multiline mode, it is the - length remainder of the data in the buffer. Otherwise, it is the length of - the next line, excluding the terminating newline. After matching, we always - advance by the length of the next line. In multiline mode the PCRE_FIRSTLINE - option is used for compiling, so that any match is constrained to be in the - first line. */ - - t = end_of_line(t, endptr, &endlinelength); - linelength = t - ptr - endlinelength; - length = multiline? (size_t)(endptr - ptr) : linelength; - - /* Check to see if the line we are looking at extends right to the very end - of the buffer without a line terminator. This means the line is too long to - handle. */ - - if (endlinelength == 0 && t == main_buffer + bufsize) - { - fprintf(stderr, "pcregrep: line %d%s%s is too long for the internal buffer\n" - "pcregrep: check the --buffer-size option\n", - linenumber, - (filename == NULL)? "" : " of file ", - (filename == NULL)? "" : filename); - return 2; - } - - /* Extra processing for Jeffrey Friedl's debugging. */ - -#ifdef JFRIEDL_DEBUG - if (jfriedl_XT || jfriedl_XR) - { -# include <sys/time.h> -# include <time.h> - struct timeval start_time, end_time; - struct timezone dummy; - int i; - - if (jfriedl_XT) - { - unsigned long newlen = length * jfriedl_XT + strlen(jfriedl_prefix) + strlen(jfriedl_postfix); - const char *orig = ptr; - ptr = malloc(newlen + 1); - if (!ptr) { - printf("out of memory"); - pcregrep_exit(2); - } - endptr = ptr; - strcpy(endptr, jfriedl_prefix); endptr += strlen(jfriedl_prefix); - for (i = 0; i < jfriedl_XT; i++) { - strncpy(endptr, orig, length); - endptr += length; - } - strcpy(endptr, jfriedl_postfix); endptr += strlen(jfriedl_postfix); - length = newlen; - } - - if (gettimeofday(&start_time, &dummy) != 0) - perror("bad gettimeofday"); - - - for (i = 0; i < jfriedl_XR; i++) - match = (pcre_exec(patterns->compiled, patterns->hint, ptr, length, 0, - PCRE_NOTEMPTY, offsets, OFFSET_SIZE) >= 0); - - if (gettimeofday(&end_time, &dummy) != 0) - perror("bad gettimeofday"); - - double delta = ((end_time.tv_sec + (end_time.tv_usec / 1000000.0)) - - - (start_time.tv_sec + (start_time.tv_usec / 1000000.0))); - - printf("%s TIMER[%.4f]\n", match ? "MATCH" : "FAIL", delta); - return 0; - } -#endif - - /* We come back here after a match when show_only_matching is set, in order - to find any further matches in the same line. This applies to - --only-matching, --file-offsets, and --line-offsets. */ - - ONLY_MATCHING_RESTART: - - /* Run through all the patterns until one matches or there is an error other - than NOMATCH. This code is in a subroutine so that it can be re-used for - finding subsequent matches when colouring matched lines. After finding one - match, set PCRE_NOTEMPTY to disable any further matches of null strings in - this line. */ - - match = match_patterns(matchptr, length, options, startoffset, offsets, &mrc); - options = PCRE_NOTEMPTY; - - /* If it's a match or a not-match (as required), do what's wanted. */ - - if (match != invert) - { - BOOL hyphenprinted = FALSE; - - /* We've failed if we want a file that doesn't have any matches. */ - - if (filenames == FN_NOMATCH_ONLY) return 1; - - /* If all we want is a yes/no answer, stop now. */ - - if (quiet) return 0; - - /* Just count if just counting is wanted. */ - - else if (count_only) count++; - - /* When handling a binary file and binary-files==binary, the "binary" - variable will be set true (it's false in all other cases). In this - situation we just want to output the file name. No need to scan further. */ - - else if (binary) - { - fprintf(stdout, "Binary file %s matches\n", filename); - return 0; - } - - /* If all we want is a file name, there is no need to scan any more lines - in the file. */ - - else if (filenames == FN_MATCH_ONLY) - { - fprintf(stdout, "%s\n", printname); - return 0; - } - - /* The --only-matching option prints just the substring that matched, - and/or one or more captured portions of it, as long as these strings are - not empty. The --file-offsets and --line-offsets options output offsets for - the matching substring (all three set show_only_matching). None of these - mutually exclusive options prints any context. Afterwards, adjust the start - and then jump back to look for further matches in the same line. If we are - in invert mode, however, nothing is printed and we do not restart - this - could still be useful because the return code is set. */ - - else if (show_only_matching) - { - if (!invert) - { - int oldstartoffset = startoffset; - - /* It is possible, when a lookbehind assertion contains \K, for the - same string to be found again. The code below advances startoffset, but - until it is past the "bumpalong" offset that gave the match, the same - substring will be returned. The PCRE1 library does not return the - bumpalong offset, so all we can do is ignore repeated strings. (PCRE2 - does this better.) */ - - if (prevoffsets[0] != offsets[0] || prevoffsets[1] != offsets[1]) - { - prevoffsets[0] = offsets[0]; - prevoffsets[1] = offsets[1]; - - if (printname != NULL) fprintf(stdout, "%s:", printname); - if (number) fprintf(stdout, "%d:", linenumber); - - /* Handle --line-offsets */ - - if (line_offsets) - fprintf(stdout, "%d,%d\n", (int)(matchptr + offsets[0] - ptr), - offsets[1] - offsets[0]); - - /* Handle --file-offsets */ - - else if (file_offsets) - fprintf(stdout, "%d,%d\n", - (int)(filepos + matchptr + offsets[0] - ptr), - offsets[1] - offsets[0]); - - /* Handle --only-matching, which may occur many times */ - - else - { - BOOL printed = FALSE; - omstr *om; - - for (om = only_matching; om != NULL; om = om->next) - { - int n = om->groupnum; - if (n < mrc) - { - int plen = offsets[2*n + 1] - offsets[2*n]; - if (plen > 0) - { - if (printed) fprintf(stdout, "%s", om_separator); - if (do_colour) fprintf(stdout, "%c[%sm", 0x1b, colour_string); - FWRITE(matchptr + offsets[n*2], 1, plen, stdout); - if (do_colour) fprintf(stdout, "%c[00m", 0x1b); - printed = TRUE; - } - } - } - - if (printed || printname != NULL || number) fprintf(stdout, "\n"); - } - } - - /* Prepare to repeat to find the next match. If the patterned contained - a lookbehind tht included \K, it is possible that the end of the match - might be at or before the actual strting offset we have just used. We - need to start one character further on. Unfortunately, for unanchored - patterns, the actual start offset can be greater that the one that was - set as a result of "bumpalong". PCRE1 does not return the actual start - offset, so we have to check against the original start offset. This may - lead to duplicates - we we need the fudge above to avoid printing them. - (PCRE2 does this better.) */ - - match = FALSE; - if (line_buffered) fflush(stdout); - rc = 0; /* Had some success */ - startoffset = offsets[1]; /* Restart after the match */ - if (startoffset <= oldstartoffset) - { - if ((size_t)startoffset >= length) - goto END_ONE_MATCH; /* We were at the end */ - startoffset = oldstartoffset + 1; - if (utf8) - while ((matchptr[startoffset] & 0xc0) == 0x80) startoffset++; - } - goto ONLY_MATCHING_RESTART; - } - } - - /* This is the default case when none of the above options is set. We print - the matching lines(s), possibly preceded and/or followed by other lines of - context. */ - - else - { - /* See if there is a requirement to print some "after" lines from a - previous match. We never print any overlaps. */ - - if (after_context > 0 && lastmatchnumber > 0) - { - int ellength; - int linecount = 0; - char *p = lastmatchrestart; - - while (p < ptr && linecount < after_context) - { - p = end_of_line(p, ptr, &ellength); - linecount++; - } - - /* It is important to advance lastmatchrestart during this printing so - that it interacts correctly with any "before" printing below. Print - each line's data using fwrite() in case there are binary zeroes. */ - - while (lastmatchrestart < p) - { - char *pp = lastmatchrestart; - if (printname != NULL) fprintf(stdout, "%s-", printname); - if (number) fprintf(stdout, "%d-", lastmatchnumber++); - pp = end_of_line(pp, endptr, &ellength); - FWRITE(lastmatchrestart, 1, pp - lastmatchrestart, stdout); - lastmatchrestart = pp; - } - if (lastmatchrestart != ptr) hyphenpending = TRUE; - } - - /* If there were non-contiguous lines printed above, insert hyphens. */ - - if (hyphenpending) - { - fprintf(stdout, "--\n"); - hyphenpending = FALSE; - hyphenprinted = TRUE; - } - - /* See if there is a requirement to print some "before" lines for this - match. Again, don't print overlaps. */ - - if (before_context > 0) - { - int linecount = 0; - char *p = ptr; - - while (p > main_buffer && (lastmatchnumber == 0 || p > lastmatchrestart) && - linecount < before_context) - { - linecount++; - p = previous_line(p, main_buffer); - } - - if (lastmatchnumber > 0 && p > lastmatchrestart && !hyphenprinted) - fprintf(stdout, "--\n"); - - while (p < ptr) - { - int ellength; - char *pp = p; - if (printname != NULL) fprintf(stdout, "%s-", printname); - if (number) fprintf(stdout, "%d-", linenumber - linecount--); - pp = end_of_line(pp, endptr, &ellength); - FWRITE(p, 1, pp - p, stdout); - p = pp; - } - } - - /* Now print the matching line(s); ensure we set hyphenpending at the end - of the file if any context lines are being output. */ - - if (after_context > 0 || before_context > 0) - endhyphenpending = TRUE; - - if (printname != NULL) fprintf(stdout, "%s:", printname); - if (number) fprintf(stdout, "%d:", linenumber); - - /* In multiline mode, we want to print to the end of the line in which - the end of the matched string is found, so we adjust linelength and the - line number appropriately, but only when there actually was a match - (invert not set). Because the PCRE_FIRSTLINE option is set, the start of - the match will always be before the first newline sequence. */ - - if (multiline & !invert) - { - char *endmatch = ptr + offsets[1]; - t = ptr; - while (t <= endmatch) - { - t = end_of_line(t, endptr, &endlinelength); - if (t < endmatch) linenumber++; else break; - } - linelength = t - ptr - endlinelength; - } - - /*** NOTE: Use only fwrite() to output the data line, so that binary - zeroes are treated as just another data character. */ - - /* This extra option, for Jeffrey Friedl's debugging requirements, - replaces the matched string, or a specific captured string if it exists, - with X. When this happens, colouring is ignored. */ - -#ifdef JFRIEDL_DEBUG - if (S_arg >= 0 && S_arg < mrc) - { - int first = S_arg * 2; - int last = first + 1; - FWRITE(ptr, 1, offsets[first], stdout); - fprintf(stdout, "X"); - FWRITE(ptr + offsets[last], 1, linelength - offsets[last], stdout); - } - else -#endif - - /* We have to split the line(s) up if colouring, and search for further - matches, but not of course if the line is a non-match. */ - - if (do_colour && !invert) - { - int plength; - FWRITE(ptr, 1, offsets[0], stdout); - fprintf(stdout, "%c[%sm", 0x1b, colour_string); - FWRITE(ptr + offsets[0], 1, offsets[1] - offsets[0], stdout); - fprintf(stdout, "%c[00m", 0x1b); - for (;;) - { - startoffset = offsets[1]; - if (startoffset >= (int)linelength + endlinelength || - !match_patterns(matchptr, length, options, startoffset, offsets, - &mrc)) - break; - FWRITE(matchptr + startoffset, 1, offsets[0] - startoffset, stdout); - fprintf(stdout, "%c[%sm", 0x1b, colour_string); - FWRITE(matchptr + offsets[0], 1, offsets[1] - offsets[0], stdout); - fprintf(stdout, "%c[00m", 0x1b); - } - - /* In multiline mode, we may have already printed the complete line - and its line-ending characters (if they matched the pattern), so there - may be no more to print. */ - - plength = (int)((linelength + endlinelength) - startoffset); - if (plength > 0) FWRITE(ptr + startoffset, 1, plength, stdout); - } - - /* Not colouring; no need to search for further matches */ - - else FWRITE(ptr, 1, linelength + endlinelength, stdout); - } - - /* End of doing what has to be done for a match. If --line-buffered was - given, flush the output. */ - - if (line_buffered) fflush(stdout); - rc = 0; /* Had some success */ - - /* Remember where the last match happened for after_context. We remember - where we are about to restart, and that line's number. */ - - lastmatchrestart = ptr + linelength + endlinelength; - lastmatchnumber = linenumber + 1; - } - - /* For a match in multiline inverted mode (which of course did not cause - anything to be printed), we have to move on to the end of the match before - proceeding. */ - - if (multiline && invert && match) - { - int ellength; - char *endmatch = ptr + offsets[1]; - t = ptr; - while (t < endmatch) - { - t = end_of_line(t, endptr, &ellength); - if (t <= endmatch) linenumber++; else break; - } - endmatch = end_of_line(endmatch, endptr, &ellength); - linelength = endmatch - ptr - ellength; - } - - /* Advance to after the newline and increment the line number. The file - offset to the current line is maintained in filepos. */ - - END_ONE_MATCH: - ptr += linelength + endlinelength; - filepos += (int)(linelength + endlinelength); - linenumber++; - - /* If input is line buffered, and the buffer is not yet full, read another - line and add it into the buffer. */ - - if (input_line_buffered && bufflength < (size_t)bufsize) - { - int add = read_one_line(ptr, bufsize - (int)(ptr - main_buffer), in); - bufflength += add; - endptr += add; - } - - /* If we haven't yet reached the end of the file (the buffer is full), and - the current point is in the top 1/3 of the buffer, slide the buffer down by - 1/3 and refill it. Before we do this, if some unprinted "after" lines are - about to be lost, print them. */ - - if (bufflength >= (size_t)bufsize && ptr > main_buffer + 2*bufthird) - { - if (after_context > 0 && - lastmatchnumber > 0 && - lastmatchrestart < main_buffer + bufthird) - { - do_after_lines(lastmatchnumber, lastmatchrestart, endptr, printname); - lastmatchnumber = 0; - } - - /* Now do the shuffle */ - - memmove(main_buffer, main_buffer + bufthird, 2*bufthird); - ptr -= bufthird; - -#ifdef SUPPORT_LIBZ - if (frtype == FR_LIBZ) - bufflength = 2*bufthird + - gzread (ingz, main_buffer + 2*bufthird, bufthird); - else -#endif - -#ifdef SUPPORT_LIBBZ2 - if (frtype == FR_LIBBZ2) - bufflength = 2*bufthird + - BZ2_bzread(inbz2, main_buffer + 2*bufthird, bufthird); - else -#endif - - bufflength = 2*bufthird + - (input_line_buffered? - read_one_line(main_buffer + 2*bufthird, bufthird, in) : - fread(main_buffer + 2*bufthird, 1, bufthird, in)); - endptr = main_buffer + bufflength; - - /* Adjust any last match point */ - - if (lastmatchnumber > 0) lastmatchrestart -= bufthird; - } - } /* Loop through the whole file */ - -/* End of file; print final "after" lines if wanted; do_after_lines sets -hyphenpending if it prints something. */ - -if (!show_only_matching && !count_only) - { - do_after_lines(lastmatchnumber, lastmatchrestart, endptr, printname); - hyphenpending |= endhyphenpending; - } - -/* Print the file name if we are looking for those without matches and there -were none. If we found a match, we won't have got this far. */ - -if (filenames == FN_NOMATCH_ONLY) - { - fprintf(stdout, "%s\n", printname); - return 0; - } - -/* Print the match count if wanted */ - -if (count_only && !quiet) - { - if (count > 0 || !omit_zero_count) - { - if (printname != NULL && filenames != FN_NONE) - fprintf(stdout, "%s:", printname); - fprintf(stdout, "%d\n", count); - } - } - -return rc; -} - - - -/************************************************* -* Grep a file or recurse into a directory * -*************************************************/ - -/* Given a path name, if it's a directory, scan all the files if we are -recursing; if it's a file, grep it. - -Arguments: - pathname the path to investigate - dir_recurse TRUE if recursing is wanted (-r or -drecurse) - only_one_at_top TRUE if the path is the only one at toplevel - -Returns: -1 the file/directory was skipped - 0 if there was at least one match - 1 if there were no matches - 2 there was some kind of error - -However, file opening failures are suppressed if "silent" is set. -*/ - -static int -grep_or_recurse(char *pathname, BOOL dir_recurse, BOOL only_one_at_top) -{ -int rc = 1; -int frtype; -void *handle; -char *lastcomp; -FILE *in = NULL; /* Ensure initialized */ - -#ifdef SUPPORT_LIBZ -gzFile ingz = NULL; -#endif - -#ifdef SUPPORT_LIBBZ2 -BZFILE *inbz2 = NULL; -#endif - -#if defined SUPPORT_LIBZ || defined SUPPORT_LIBBZ2 -int pathlen; -#endif - -#if defined NATIVE_ZOS -int zos_type; -FILE *zos_test_file; -#endif - -/* If the file name is "-" we scan stdin */ - -if (strcmp(pathname, "-") == 0) - { - return pcregrep(stdin, FR_PLAIN, stdin_name, - (filenames > FN_DEFAULT || (filenames == FN_DEFAULT && !only_one_at_top))? - stdin_name : NULL); - } - -/* Inclusion and exclusion: --include-dir and --exclude-dir apply only to -directories, whereas --include and --exclude apply to everything else. The test -is against the final component of the path. */ - -lastcomp = strrchr(pathname, FILESEP); -lastcomp = (lastcomp == NULL)? pathname : lastcomp + 1; - -/* If the file is a directory, skip if not recursing or if explicitly excluded. -Otherwise, scan the directory and recurse for each path within it. The scanning -code is localized so it can be made system-specific. */ - - -/* For z/OS, determine the file type. */ - -#if defined NATIVE_ZOS -zos_test_file = fopen(pathname,"rb"); - -if (zos_test_file == NULL) - { - if (!silent) fprintf(stderr, "pcregrep: failed to test next file %s\n", - pathname, strerror(errno)); - return -1; - } -zos_type = identifyzosfiletype (zos_test_file); -fclose (zos_test_file); - -/* Handle a PDS in separate code */ - -if (zos_type == __ZOS_PDS || zos_type == __ZOS_PDSE) - { - return travelonpdsdir (pathname, only_one_at_top); - } - -/* Deal with regular files in the normal way below. These types are: - zos_type == __ZOS_PDS_MEMBER - zos_type == __ZOS_PS - zos_type == __ZOS_VSAM_KSDS - zos_type == __ZOS_VSAM_ESDS - zos_type == __ZOS_VSAM_RRDS -*/ - -/* Handle a z/OS directory using common code. */ - -else if (zos_type == __ZOS_HFS) - { -#endif /* NATIVE_ZOS */ - - -/* Handle directories: common code for all OS */ - -if (isdirectory(pathname)) - { - if (dee_action == dee_SKIP || - !test_incexc(lastcomp, include_dir_patterns, exclude_dir_patterns)) - return -1; - - if (dee_action == dee_RECURSE) - { - char buffer[1024]; - char *nextfile; - directory_type *dir = opendirectory(pathname); - - if (dir == NULL) - { - if (!silent) - fprintf(stderr, "pcregrep: Failed to open directory %s: %s\n", pathname, - strerror(errno)); - return 2; - } - - while ((nextfile = readdirectory(dir)) != NULL) - { - int frc; - sprintf(buffer, "%.512s%c%.128s", pathname, FILESEP, nextfile); - frc = grep_or_recurse(buffer, dir_recurse, FALSE); - if (frc > 1) rc = frc; - else if (frc == 0 && rc == 1) rc = 0; - } - - closedirectory(dir); - return rc; - } - } - -#if defined NATIVE_ZOS - } -#endif - -/* If the file is not a directory, check for a regular file, and if it is not, -skip it if that's been requested. Otherwise, check for an explicit inclusion or -exclusion. */ - -else if ( -#if defined NATIVE_ZOS - (zos_type == __ZOS_NOFILE && DEE_action == DEE_SKIP) || -#else /* all other OS */ - (!isregfile(pathname) && DEE_action == DEE_SKIP) || -#endif - !test_incexc(lastcomp, include_patterns, exclude_patterns)) - return -1; /* File skipped */ - -/* Control reaches here if we have a regular file, or if we have a directory -and recursion or skipping was not requested, or if we have anything else and -skipping was not requested. The scan proceeds. If this is the first and only -argument at top level, we don't show the file name, unless we are only showing -the file name, or the filename was forced (-H). */ - -#if defined SUPPORT_LIBZ || defined SUPPORT_LIBBZ2 -pathlen = (int)(strlen(pathname)); -#endif - -/* Open using zlib if it is supported and the file name ends with .gz. */ - -#ifdef SUPPORT_LIBZ -if (pathlen > 3 && strcmp(pathname + pathlen - 3, ".gz") == 0) - { - ingz = gzopen(pathname, "rb"); - if (ingz == NULL) - { - if (!silent) - fprintf(stderr, "pcregrep: Failed to open %s: %s\n", pathname, - strerror(errno)); - return 2; - } - handle = (void *)ingz; - frtype = FR_LIBZ; - } -else -#endif - -/* Otherwise open with bz2lib if it is supported and the name ends with .bz2. */ - -#ifdef SUPPORT_LIBBZ2 -if (pathlen > 4 && strcmp(pathname + pathlen - 4, ".bz2") == 0) - { - inbz2 = BZ2_bzopen(pathname, "rb"); - handle = (void *)inbz2; - frtype = FR_LIBBZ2; - } -else -#endif - -/* Otherwise use plain fopen(). The label is so that we can come back here if -an attempt to read a .bz2 file indicates that it really is a plain file. */ - -#ifdef SUPPORT_LIBBZ2 -PLAIN_FILE: -#endif - { - in = fopen(pathname, "rb"); - handle = (void *)in; - frtype = FR_PLAIN; - } - -/* All the opening methods return errno when they fail. */ - -if (handle == NULL) - { - if (!silent) - fprintf(stderr, "pcregrep: Failed to open %s: %s\n", pathname, - strerror(errno)); - return 2; - } - -/* Now grep the file */ - -rc = pcregrep(handle, frtype, pathname, (filenames > FN_DEFAULT || - (filenames == FN_DEFAULT && !only_one_at_top))? pathname : NULL); - -/* Close in an appropriate manner. */ - -#ifdef SUPPORT_LIBZ -if (frtype == FR_LIBZ) - gzclose(ingz); -else -#endif - -/* If it is a .bz2 file and the result is 3, it means that the first attempt to -read failed. If the error indicates that the file isn't in fact bzipped, try -again as a normal file. */ - -#ifdef SUPPORT_LIBBZ2 -if (frtype == FR_LIBBZ2) - { - if (rc == 3) - { - int errnum; - const char *err = BZ2_bzerror(inbz2, &errnum); - if (errnum == BZ_DATA_ERROR_MAGIC) - { - BZ2_bzclose(inbz2); - goto PLAIN_FILE; - } - else if (!silent) - fprintf(stderr, "pcregrep: Failed to read %s using bzlib: %s\n", - pathname, err); - rc = 2; /* The normal "something went wrong" code */ - } - BZ2_bzclose(inbz2); - } -else -#endif - -/* Normal file close */ - -fclose(in); - -/* Pass back the yield from pcregrep(). */ - -return rc; -} - - - -/************************************************* -* Handle a single-letter, no data option * -*************************************************/ - -static int -handle_option(int letter, int options) -{ -switch(letter) - { - case N_FOFFSETS: file_offsets = TRUE; break; - case N_HELP: help(); pcregrep_exit(0); - case N_LBUFFER: line_buffered = TRUE; break; - case N_LOFFSETS: line_offsets = number = TRUE; break; - case N_NOJIT: study_options &= ~PCRE_STUDY_JIT_COMPILE; break; - case 'a': binary_files = BIN_TEXT; break; - case 'c': count_only = TRUE; break; - case 'F': process_options |= PO_FIXED_STRINGS; break; - case 'H': filenames = FN_FORCE; break; - case 'I': binary_files = BIN_NOMATCH; break; - case 'h': filenames = FN_NONE; break; - case 'i': options |= PCRE_CASELESS; break; - case 'l': omit_zero_count = TRUE; filenames = FN_MATCH_ONLY; break; - case 'L': filenames = FN_NOMATCH_ONLY; break; - case 'M': multiline = TRUE; options |= PCRE_MULTILINE|PCRE_FIRSTLINE; break; - case 'n': number = TRUE; break; - - case 'o': - only_matching_last = add_number(0, only_matching_last); - if (only_matching == NULL) only_matching = only_matching_last; - break; - - case 'q': quiet = TRUE; break; - case 'r': dee_action = dee_RECURSE; break; - case 's': silent = TRUE; break; - case 'u': options |= PCRE_UTF8; utf8 = TRUE; break; - case 'v': invert = TRUE; break; - case 'w': process_options |= PO_WORD_MATCH; break; - case 'x': process_options |= PO_LINE_MATCH; break; - - case 'V': - fprintf(stdout, "pcregrep version %s\n", pcre_version()); - pcregrep_exit(0); - break; - - default: - fprintf(stderr, "pcregrep: Unknown option -%c\n", letter); - pcregrep_exit(usage(2)); - } - -return options; -} - - - - -/************************************************* -* Construct printed ordinal * -*************************************************/ - -/* This turns a number into "1st", "3rd", etc. */ - -static char * -ordin(int n) -{ -static char buffer[8]; -char *p = buffer; -sprintf(p, "%d", n); -while (*p != 0) p++; -switch (n%10) - { - case 1: strcpy(p, "st"); break; - case 2: strcpy(p, "nd"); break; - case 3: strcpy(p, "rd"); break; - default: strcpy(p, "th"); break; - } -return buffer; -} - - - -/************************************************* -* Compile a single pattern * -*************************************************/ - -/* Do nothing if the pattern has already been compiled. This is the case for -include/exclude patterns read from a file. - -When the -F option has been used, each "pattern" may be a list of strings, -separated by line breaks. They will be matched literally. We split such a -string and compile the first substring, inserting an additional block into the -pattern chain. - -Arguments: - p points to the pattern block - options the PCRE options - popts the processing options - fromfile TRUE if the pattern was read from a file - fromtext file name or identifying text (e.g. "include") - count 0 if this is the only command line pattern, or - number of the command line pattern, or - linenumber for a pattern from a file - -Returns: TRUE on success, FALSE after an error -*/ - -static BOOL -compile_pattern(patstr *p, int options, int popts, int fromfile, - const char *fromtext, int count) -{ -char buffer[PATBUFSIZE]; -const char *error; -char *ps = p->string; -int patlen = strlen(ps); -int errptr; - -if (p->compiled != NULL) return TRUE; - -if ((popts & PO_FIXED_STRINGS) != 0) - { - int ellength; - char *eop = ps + patlen; - char *pe = end_of_line(ps, eop, &ellength); - - if (ellength != 0) - { - if (add_pattern(pe, p) == NULL) return FALSE; - patlen = (int)(pe - ps - ellength); - } - } - -sprintf(buffer, "%s%.*s%s", prefix[popts], patlen, ps, suffix[popts]); -p->compiled = pcre_compile(buffer, options, &error, &errptr, pcretables); -if (p->compiled != NULL) return TRUE; - -/* Handle compile errors */ - -errptr -= (int)strlen(prefix[popts]); -if (errptr > patlen) errptr = patlen; - -if (fromfile) - { - fprintf(stderr, "pcregrep: Error in regex in line %d of %s " - "at offset %d: %s\n", count, fromtext, errptr, error); - } -else - { - if (count == 0) - fprintf(stderr, "pcregrep: Error in %s regex at offset %d: %s\n", - fromtext, errptr, error); - else - fprintf(stderr, "pcregrep: Error in %s %s regex at offset %d: %s\n", - ordin(count), fromtext, errptr, error); - } - -return FALSE; -} - - - -/************************************************* -* Read and compile a file of patterns * -*************************************************/ - -/* This is used for --filelist, --include-from, and --exclude-from. - -Arguments: - name the name of the file; "-" is stdin - patptr pointer to the pattern chain anchor - patlastptr pointer to the last pattern pointer - popts the process options to pass to pattern_compile() - -Returns: TRUE if all went well -*/ - -static BOOL -read_pattern_file(char *name, patstr **patptr, patstr **patlastptr, int popts) -{ -int linenumber = 0; -FILE *f; -char *filename; -char buffer[PATBUFSIZE]; - -if (strcmp(name, "-") == 0) - { - f = stdin; - filename = stdin_name; - } -else - { - f = fopen(name, "r"); - if (f == NULL) - { - fprintf(stderr, "pcregrep: Failed to open %s: %s\n", name, strerror(errno)); - return FALSE; - } - filename = name; - } - -while (fgets(buffer, PATBUFSIZE, f) != NULL) - { - char *s = buffer + (int)strlen(buffer); - while (s > buffer && isspace((unsigned char)(s[-1]))) s--; - *s = 0; - linenumber++; - if (buffer[0] == 0) continue; /* Skip blank lines */ - - /* Note: this call to add_pattern() puts a pointer to the local variable - "buffer" into the pattern chain. However, that pointer is used only when - compiling the pattern, which happens immediately below, so we flatten it - afterwards, as a precaution against any later code trying to use it. */ - - *patlastptr = add_pattern(buffer, *patlastptr); - if (*patlastptr == NULL) - { - if (f != stdin) fclose(f); - return FALSE; - } - if (*patptr == NULL) *patptr = *patlastptr; - - /* This loop is needed because compiling a "pattern" when -F is set may add - on additional literal patterns if the original contains a newline. In the - common case, it never will, because fgets() stops at a newline. However, - the -N option can be used to give pcregrep a different newline setting. */ - - for(;;) - { - if (!compile_pattern(*patlastptr, pcre_options, popts, TRUE, filename, - linenumber)) - { - if (f != stdin) fclose(f); - return FALSE; - } - (*patlastptr)->string = NULL; /* Insurance */ - if ((*patlastptr)->next == NULL) break; - *patlastptr = (*patlastptr)->next; - } - } - -if (f != stdin) fclose(f); -return TRUE; -} - - - -/************************************************* -* Main program * -*************************************************/ - -/* Returns 0 if something matched, 1 if nothing matched, 2 after an error. */ - -int -main(int argc, char **argv) -{ -int i, j; -int rc = 1; -BOOL only_one_at_top; -patstr *cp; -fnstr *fn; -const char *locale_from = "--locale"; -const char *error; - -#ifdef SUPPORT_PCREGREP_JIT -pcre_jit_stack *jit_stack = NULL; -#endif - -/* Set the default line ending value from the default in the PCRE library; -"lf", "cr", "crlf", and "any" are supported. Anything else is treated as "lf". -Note that the return values from pcre_config(), though derived from the ASCII -codes, are the same in EBCDIC environments, so we must use the actual values -rather than escapes such as as '\r'. */ - -(void)pcre_config(PCRE_CONFIG_NEWLINE, &i); -switch(i) - { - default: newline = (char *)"lf"; break; - case 13: newline = (char *)"cr"; break; - case (13 << 8) | 10: newline = (char *)"crlf"; break; - case -1: newline = (char *)"any"; break; - case -2: newline = (char *)"anycrlf"; break; - } - -/* Process the options */ - -for (i = 1; i < argc; i++) - { - option_item *op = NULL; - char *option_data = (char *)""; /* default to keep compiler happy */ - BOOL longop; - BOOL longopwasequals = FALSE; - - if (argv[i][0] != '-') break; - - /* If we hit an argument that is just "-", it may be a reference to STDIN, - but only if we have previously had -e or -f to define the patterns. */ - - if (argv[i][1] == 0) - { - if (pattern_files != NULL || patterns != NULL) break; - else pcregrep_exit(usage(2)); - } - - /* Handle a long name option, or -- to terminate the options */ - - if (argv[i][1] == '-') - { - char *arg = argv[i] + 2; - char *argequals = strchr(arg, '='); - - if (*arg == 0) /* -- terminates options */ - { - i++; - break; /* out of the options-handling loop */ - } - - longop = TRUE; - - /* Some long options have data that follows after =, for example file=name. - Some options have variations in the long name spelling: specifically, we - allow "regexp" because GNU grep allows it, though I personally go along - with Jeffrey Friedl and Larry Wall in preferring "regex" without the "p". - These options are entered in the table as "regex(p)". Options can be in - both these categories. */ - - for (op = optionlist; op->one_char != 0; op++) - { - char *opbra = strchr(op->long_name, '('); - char *equals = strchr(op->long_name, '='); - - /* Handle options with only one spelling of the name */ - - if (opbra == NULL) /* Does not contain '(' */ - { - if (equals == NULL) /* Not thing=data case */ - { - if (strcmp(arg, op->long_name) == 0) break; - } - else /* Special case xxx=data */ - { - int oplen = (int)(equals - op->long_name); - int arglen = (argequals == NULL)? - (int)strlen(arg) : (int)(argequals - arg); - if (oplen == arglen && strncmp(arg, op->long_name, oplen) == 0) - { - option_data = arg + arglen; - if (*option_data == '=') - { - option_data++; - longopwasequals = TRUE; - } - break; - } - } - } - - /* Handle options with an alternate spelling of the name */ - - else - { - char buff1[24]; - char buff2[24]; - - int baselen = (int)(opbra - op->long_name); - int fulllen = (int)(strchr(op->long_name, ')') - op->long_name + 1); - int arglen = (argequals == NULL || equals == NULL)? - (int)strlen(arg) : (int)(argequals - arg); - - sprintf(buff1, "%.*s", baselen, op->long_name); - sprintf(buff2, "%s%.*s", buff1, fulllen - baselen - 2, opbra + 1); - - if (strncmp(arg, buff1, arglen) == 0 || - strncmp(arg, buff2, arglen) == 0) - { - if (equals != NULL && argequals != NULL) - { - option_data = argequals; - if (*option_data == '=') - { - option_data++; - longopwasequals = TRUE; - } - } - break; - } - } - } - - if (op->one_char == 0) - { - fprintf(stderr, "pcregrep: Unknown option %s\n", argv[i]); - pcregrep_exit(usage(2)); - } - } - - /* Jeffrey Friedl's debugging harness uses these additional options which - are not in the right form for putting in the option table because they use - only one hyphen, yet are more than one character long. By putting them - separately here, they will not get displayed as part of the help() output, - but I don't think Jeffrey will care about that. */ - -#ifdef JFRIEDL_DEBUG - else if (strcmp(argv[i], "-pre") == 0) { - jfriedl_prefix = argv[++i]; - continue; - } else if (strcmp(argv[i], "-post") == 0) { - jfriedl_postfix = argv[++i]; - continue; - } else if (strcmp(argv[i], "-XT") == 0) { - sscanf(argv[++i], "%d", &jfriedl_XT); - continue; - } else if (strcmp(argv[i], "-XR") == 0) { - sscanf(argv[++i], "%d", &jfriedl_XR); - continue; - } -#endif - - - /* One-char options; many that have no data may be in a single argument; we - continue till we hit the last one or one that needs data. */ - - else - { - char *s = argv[i] + 1; - longop = FALSE; - - while (*s != 0) - { - for (op = optionlist; op->one_char != 0; op++) - { - if (*s == op->one_char) break; - } - if (op->one_char == 0) - { - fprintf(stderr, "pcregrep: Unknown option letter '%c' in \"%s\"\n", - *s, argv[i]); - pcregrep_exit(usage(2)); - } - - option_data = s+1; - - /* Break out if this is the last character in the string; it's handled - below like a single multi-char option. */ - - if (*option_data == 0) break; - - /* Check for a single-character option that has data: OP_OP_NUMBER(S) - are used for ones that either have a numerical number or defaults, i.e. - the data is optional. If a digit follows, there is data; if not, carry on - with other single-character options in the same string. */ - - if (op->type == OP_OP_NUMBER || op->type == OP_OP_NUMBERS) - { - if (isdigit((unsigned char)s[1])) break; - } - else /* Check for an option with data */ - { - if (op->type != OP_NODATA) break; - } - - /* Handle a single-character option with no data, then loop for the - next character in the string. */ - - pcre_options = handle_option(*s++, pcre_options); - } - } - - /* At this point we should have op pointing to a matched option. If the type - is NO_DATA, it means that there is no data, and the option might set - something in the PCRE options. */ - - if (op->type == OP_NODATA) - { - pcre_options = handle_option(op->one_char, pcre_options); - continue; - } - - /* If the option type is OP_OP_STRING or OP_OP_NUMBER(S), it's an option that - either has a value or defaults to something. It cannot have data in a - separate item. At the moment, the only such options are "colo(u)r", - "only-matching", and Jeffrey Friedl's special -S debugging option. */ - - if (*option_data == 0 && - (op->type == OP_OP_STRING || op->type == OP_OP_NUMBER || - op->type == OP_OP_NUMBERS)) - { - switch (op->one_char) - { - case N_COLOUR: - colour_option = (char *)"auto"; - break; - - case 'o': - only_matching_last = add_number(0, only_matching_last); - if (only_matching == NULL) only_matching = only_matching_last; - break; - -#ifdef JFRIEDL_DEBUG - case 'S': - S_arg = 0; - break; -#endif - } - continue; - } - - /* Otherwise, find the data string for the option. */ - - if (*option_data == 0) - { - if (i >= argc - 1 || longopwasequals) - { - fprintf(stderr, "pcregrep: Data missing after %s\n", argv[i]); - pcregrep_exit(usage(2)); - } - option_data = argv[++i]; - } - - /* If the option type is OP_OP_NUMBERS, the value is a number that is to be - added to a chain of numbers. */ - - if (op->type == OP_OP_NUMBERS) - { - unsigned long int n = decode_number(option_data, op, longop); - omdatastr *omd = (omdatastr *)op->dataptr; - *(omd->lastptr) = add_number((int)n, *(omd->lastptr)); - if (*(omd->anchor) == NULL) *(omd->anchor) = *(omd->lastptr); - } - - /* If the option type is OP_PATLIST, it's the -e option, or one of the - include/exclude options, which can be called multiple times to create lists - of patterns. */ - - else if (op->type == OP_PATLIST) - { - patdatastr *pd = (patdatastr *)op->dataptr; - *(pd->lastptr) = add_pattern(option_data, *(pd->lastptr)); - if (*(pd->lastptr) == NULL) goto EXIT2; - if (*(pd->anchor) == NULL) *(pd->anchor) = *(pd->lastptr); - } - - /* If the option type is OP_FILELIST, it's one of the options that names a - file. */ - - else if (op->type == OP_FILELIST) - { - fndatastr *fd = (fndatastr *)op->dataptr; - fn = (fnstr *)malloc(sizeof(fnstr)); - if (fn == NULL) - { - fprintf(stderr, "pcregrep: malloc failed\n"); - goto EXIT2; - } - fn->next = NULL; - fn->name = option_data; - if (*(fd->anchor) == NULL) - *(fd->anchor) = fn; - else - (*(fd->lastptr))->next = fn; - *(fd->lastptr) = fn; - } - - /* Handle OP_BINARY_FILES */ - - else if (op->type == OP_BINFILES) - { - if (strcmp(option_data, "binary") == 0) - binary_files = BIN_BINARY; - else if (strcmp(option_data, "without-match") == 0) - binary_files = BIN_NOMATCH; - else if (strcmp(option_data, "text") == 0) - binary_files = BIN_TEXT; - else - { - fprintf(stderr, "pcregrep: unknown value \"%s\" for binary-files\n", - option_data); - pcregrep_exit(usage(2)); - } - } - - /* Otherwise, deal with a single string or numeric data value. */ - - else if (op->type != OP_NUMBER && op->type != OP_LONGNUMBER && - op->type != OP_OP_NUMBER) - { - *((char **)op->dataptr) = option_data; - } - else - { - unsigned long int n = decode_number(option_data, op, longop); - if (op->type == OP_LONGNUMBER) *((unsigned long int *)op->dataptr) = n; - else *((int *)op->dataptr) = n; - } - } - -/* Options have been decoded. If -C was used, its value is used as a default -for -A and -B. */ - -if (both_context > 0) - { - if (after_context == 0) after_context = both_context; - if (before_context == 0) before_context = both_context; - } - -/* Only one of --only-matching, --file-offsets, or --line-offsets is permitted. -However, all three set show_only_matching because they display, each in their -own way, only the data that has matched. */ - -if ((only_matching != NULL && (file_offsets || line_offsets)) || - (file_offsets && line_offsets)) - { - fprintf(stderr, "pcregrep: Cannot mix --only-matching, --file-offsets " - "and/or --line-offsets\n"); - pcregrep_exit(usage(2)); - } - -if (only_matching != NULL || file_offsets || line_offsets) - show_only_matching = TRUE; - -/* If a locale has not been provided as an option, see if the LC_CTYPE or -LC_ALL environment variable is set, and if so, use it. */ - -if (locale == NULL) - { - locale = getenv("LC_ALL"); - locale_from = "LCC_ALL"; - } - -if (locale == NULL) - { - locale = getenv("LC_CTYPE"); - locale_from = "LC_CTYPE"; - } - -/* If a locale is set, use it to generate the tables the PCRE needs. Otherwise, -pcretables==NULL, which causes the use of default tables. */ - -if (locale != NULL) - { - if (setlocale(LC_CTYPE, locale) == NULL) - { - fprintf(stderr, "pcregrep: Failed to set locale %s (obtained from %s)\n", - locale, locale_from); - goto EXIT2; - } - pcretables = pcre_maketables(); - } - -/* Sort out colouring */ - -if (colour_option != NULL && strcmp(colour_option, "never") != 0) - { - if (strcmp(colour_option, "always") == 0) do_colour = TRUE; - else if (strcmp(colour_option, "auto") == 0) do_colour = is_stdout_tty(); - else - { - fprintf(stderr, "pcregrep: Unknown colour setting \"%s\"\n", - colour_option); - goto EXIT2; - } - if (do_colour) - { - char *cs = getenv("PCREGREP_COLOUR"); - if (cs == NULL) cs = getenv("PCREGREP_COLOR"); - if (cs != NULL) colour_string = cs; - } - } - -/* Interpret the newline type; the default settings are Unix-like. */ - -if (strcmp(newline, "cr") == 0 || strcmp(newline, "CR") == 0) - { - pcre_options |= PCRE_NEWLINE_CR; - endlinetype = EL_CR; - } -else if (strcmp(newline, "lf") == 0 || strcmp(newline, "LF") == 0) - { - pcre_options |= PCRE_NEWLINE_LF; - endlinetype = EL_LF; - } -else if (strcmp(newline, "crlf") == 0 || strcmp(newline, "CRLF") == 0) - { - pcre_options |= PCRE_NEWLINE_CRLF; - endlinetype = EL_CRLF; - } -else if (strcmp(newline, "any") == 0 || strcmp(newline, "ANY") == 0) - { - pcre_options |= PCRE_NEWLINE_ANY; - endlinetype = EL_ANY; - } -else if (strcmp(newline, "anycrlf") == 0 || strcmp(newline, "ANYCRLF") == 0) - { - pcre_options |= PCRE_NEWLINE_ANYCRLF; - endlinetype = EL_ANYCRLF; - } -else - { - fprintf(stderr, "pcregrep: Invalid newline specifier \"%s\"\n", newline); - goto EXIT2; - } - -/* Interpret the text values for -d and -D */ - -if (dee_option != NULL) - { - if (strcmp(dee_option, "read") == 0) dee_action = dee_READ; - else if (strcmp(dee_option, "recurse") == 0) dee_action = dee_RECURSE; - else if (strcmp(dee_option, "skip") == 0) dee_action = dee_SKIP; - else - { - fprintf(stderr, "pcregrep: Invalid value \"%s\" for -d\n", dee_option); - goto EXIT2; - } - } - -if (DEE_option != NULL) - { - if (strcmp(DEE_option, "read") == 0) DEE_action = DEE_READ; - else if (strcmp(DEE_option, "skip") == 0) DEE_action = DEE_SKIP; - else - { - fprintf(stderr, "pcregrep: Invalid value \"%s\" for -D\n", DEE_option); - goto EXIT2; - } - } - -/* Check the values for Jeffrey Friedl's debugging options. */ - -#ifdef JFRIEDL_DEBUG -if (S_arg > 9) - { - fprintf(stderr, "pcregrep: bad value for -S option\n"); - return 2; - } -if (jfriedl_XT != 0 || jfriedl_XR != 0) - { - if (jfriedl_XT == 0) jfriedl_XT = 1; - if (jfriedl_XR == 0) jfriedl_XR = 1; - } -#endif - -/* Get memory for the main buffer. */ - -bufsize = 3*bufthird; -main_buffer = (char *)malloc(bufsize); - -if (main_buffer == NULL) - { - fprintf(stderr, "pcregrep: malloc failed\n"); - goto EXIT2; - } - -/* If no patterns were provided by -e, and there are no files provided by -f, -the first argument is the one and only pattern, and it must exist. */ - -if (patterns == NULL && pattern_files == NULL) - { - if (i >= argc) return usage(2); - patterns = patterns_last = add_pattern(argv[i++], NULL); - if (patterns == NULL) goto EXIT2; - } - -/* Compile the patterns that were provided on the command line, either by -multiple uses of -e or as a single unkeyed pattern. We cannot do this until -after all the command-line options are read so that we know which PCRE options -to use. When -F is used, compile_pattern() may add another block into the -chain, so we must not access the next pointer till after the compile. */ - -for (j = 1, cp = patterns; cp != NULL; j++, cp = cp->next) - { - if (!compile_pattern(cp, pcre_options, process_options, FALSE, "command-line", - (j == 1 && patterns->next == NULL)? 0 : j)) - goto EXIT2; - } - -/* Read and compile the regular expressions that are provided in files. */ - -for (fn = pattern_files; fn != NULL; fn = fn->next) - { - if (!read_pattern_file(fn->name, &patterns, &patterns_last, process_options)) - goto EXIT2; - } - -/* Study the regular expressions, as we will be running them many times. If an -extra block is needed for a limit, set PCRE_STUDY_EXTRA_NEEDED so that one is -returned, even if studying produces no data. */ - -if (match_limit > 0 || match_limit_recursion > 0) - study_options |= PCRE_STUDY_EXTRA_NEEDED; - -/* Unless JIT has been explicitly disabled, arrange a stack for it to use. */ - -#ifdef SUPPORT_PCREGREP_JIT -if ((study_options & PCRE_STUDY_JIT_COMPILE) != 0) - jit_stack = pcre_jit_stack_alloc(32*1024, 1024*1024); -#endif - -for (j = 1, cp = patterns; cp != NULL; j++, cp = cp->next) - { - cp->hint = pcre_study(cp->compiled, study_options, &error); - if (error != NULL) - { - char s[16]; - if (patterns->next == NULL) s[0] = 0; else sprintf(s, " number %d", j); - fprintf(stderr, "pcregrep: Error while studying regex%s: %s\n", s, error); - goto EXIT2; - } -#ifdef SUPPORT_PCREGREP_JIT - if (jit_stack != NULL && cp->hint != NULL) - pcre_assign_jit_stack(cp->hint, NULL, jit_stack); -#endif - } - -/* If --match-limit or --recursion-limit was set, put the value(s) into the -pcre_extra block for each pattern. There will always be an extra block because -of the use of PCRE_STUDY_EXTRA_NEEDED above. */ - -for (cp = patterns; cp != NULL; cp = cp->next) - { - if (match_limit > 0) - { - cp->hint->flags |= PCRE_EXTRA_MATCH_LIMIT; - cp->hint->match_limit = match_limit; - } - - if (match_limit_recursion > 0) - { - cp->hint->flags |= PCRE_EXTRA_MATCH_LIMIT_RECURSION; - cp->hint->match_limit_recursion = match_limit_recursion; - } - } - -/* If there are include or exclude patterns read from the command line, compile -them. -F, -w, and -x do not apply, so the third argument of compile_pattern is -0. */ - -for (j = 0; j < 4; j++) - { - int k; - for (k = 1, cp = *(incexlist[j]); cp != NULL; k++, cp = cp->next) - { - if (!compile_pattern(cp, pcre_options, 0, FALSE, incexname[j], - (k == 1 && cp->next == NULL)? 0 : k)) - goto EXIT2; - } - } - -/* Read and compile include/exclude patterns from files. */ - -for (fn = include_from; fn != NULL; fn = fn->next) - { - if (!read_pattern_file(fn->name, &include_patterns, &include_patterns_last, 0)) - goto EXIT2; - } - -for (fn = exclude_from; fn != NULL; fn = fn->next) - { - if (!read_pattern_file(fn->name, &exclude_patterns, &exclude_patterns_last, 0)) - goto EXIT2; - } - -/* If there are no files that contain lists of files to search, and there are -no file arguments, search stdin, and then exit. */ - -if (file_lists == NULL && i >= argc) - { - rc = pcregrep(stdin, FR_PLAIN, stdin_name, - (filenames > FN_DEFAULT)? stdin_name : NULL); - goto EXIT; - } - -/* If any files that contains a list of files to search have been specified, -read them line by line and search the given files. */ - -for (fn = file_lists; fn != NULL; fn = fn->next) - { - char buffer[PATBUFSIZE]; - FILE *fl; - if (strcmp(fn->name, "-") == 0) fl = stdin; else - { - fl = fopen(fn->name, "rb"); - if (fl == NULL) - { - fprintf(stderr, "pcregrep: Failed to open %s: %s\n", fn->name, - strerror(errno)); - goto EXIT2; - } - } - while (fgets(buffer, PATBUFSIZE, fl) != NULL) - { - int frc; - char *end = buffer + (int)strlen(buffer); - while (end > buffer && isspace(end[-1])) end--; - *end = 0; - if (*buffer != 0) - { - frc = grep_or_recurse(buffer, dee_action == dee_RECURSE, FALSE); - if (frc > 1) rc = frc; - else if (frc == 0 && rc == 1) rc = 0; - } - } - if (fl != stdin) fclose(fl); - } - -/* After handling file-list, work through remaining arguments. Pass in the fact -that there is only one argument at top level - this suppresses the file name if -the argument is not a directory and filenames are not otherwise forced. */ - -only_one_at_top = i == argc - 1 && file_lists == NULL; - -for (; i < argc; i++) - { - int frc = grep_or_recurse(argv[i], dee_action == dee_RECURSE, - only_one_at_top); - if (frc > 1) rc = frc; - else if (frc == 0 && rc == 1) rc = 0; - } - -EXIT: -#ifdef SUPPORT_PCREGREP_JIT -if (jit_stack != NULL) pcre_jit_stack_free(jit_stack); -#endif - -free(main_buffer); -free((void *)pcretables); - -free_pattern_chain(patterns); -free_pattern_chain(include_patterns); -free_pattern_chain(include_dir_patterns); -free_pattern_chain(exclude_patterns); -free_pattern_chain(exclude_dir_patterns); - -free_file_chain(exclude_from); -free_file_chain(include_from); -free_file_chain(pattern_files); -free_file_chain(file_lists); - -while (only_matching != NULL) - { - omstr *this = only_matching; - only_matching = this->next; - free(this); - } - -pcregrep_exit(rc); - -EXIT2: -rc = 2; -goto EXIT; -} - -/* End of pcregrep */ diff --git a/src/third_party/pcre-8.38/pcreposix.c b/src/third_party/pcre-8.38/pcreposix.c deleted file mode 100644 index f024423b634..00000000000 --- a/src/third_party/pcre-8.38/pcreposix.c +++ /dev/null @@ -1,430 +0,0 @@ -/************************************************* -* Perl-Compatible Regular Expressions * -*************************************************/ - -/* PCRE is a library of functions to support regular expressions whose syntax -and semantics are as close as possible to those of the Perl 5 language. - - Written by Philip Hazel - Copyright (c) 1997-2014 University of Cambridge - ------------------------------------------------------------------------------ -Redistribution and use in source and binary forms, with or without -modification, are permitted provided that the following conditions are met: - - * Redistributions of source code must retain the above copyright notice, - this list of conditions and the following disclaimer. - - * Redistributions in binary form must reproduce the above copyright - notice, this list of conditions and the following disclaimer in the - documentation and/or other materials provided with the distribution. - - * Neither the name of the University of Cambridge nor the names of its - contributors may be used to endorse or promote products derived from - this software without specific prior written permission. - -THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS" -AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE -IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE -ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR CONTRIBUTORS BE -LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR -CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF -SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS -INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN -CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) -ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE -POSSIBILITY OF SUCH DAMAGE. ------------------------------------------------------------------------------ -*/ - - -/* This module is a wrapper that provides a POSIX API to the underlying PCRE -functions. */ - - -#ifdef HAVE_CONFIG_H -#include "config.h" -#endif - - -/* Ensure that the PCREPOSIX_EXP_xxx macros are set appropriately for -compiling these functions. This must come before including pcreposix.h, where -they are set for an application (using these functions) if they have not -previously been set. */ - -#if defined(_WIN32) && !defined(PCRE_STATIC) -# define PCREPOSIX_EXP_DECL extern __declspec(dllexport) -# define PCREPOSIX_EXP_DEFN __declspec(dllexport) -#endif - -/* We include pcre.h before pcre_internal.h so that the PCRE library functions -are declared as "import" for Windows by defining PCRE_EXP_DECL as "import". -This is needed even though pcre_internal.h itself includes pcre.h, because it -does so after it has set PCRE_EXP_DECL to "export" if it is not already set. */ - -#include "pcre.h" -#include "pcre_internal.h" -#include "pcreposix.h" - - -/* Table to translate PCRE compile time error codes into POSIX error codes. */ - -static const int eint[] = { - 0, /* no error */ - REG_EESCAPE, /* \ at end of pattern */ - REG_EESCAPE, /* \c at end of pattern */ - REG_EESCAPE, /* unrecognized character follows \ */ - REG_BADBR, /* numbers out of order in {} quantifier */ - /* 5 */ - REG_BADBR, /* number too big in {} quantifier */ - REG_EBRACK, /* missing terminating ] for character class */ - REG_ECTYPE, /* invalid escape sequence in character class */ - REG_ERANGE, /* range out of order in character class */ - REG_BADRPT, /* nothing to repeat */ - /* 10 */ - REG_BADRPT, /* operand of unlimited repeat could match the empty string */ - REG_ASSERT, /* internal error: unexpected repeat */ - REG_BADPAT, /* unrecognized character after (? */ - REG_BADPAT, /* POSIX named classes are supported only within a class */ - REG_EPAREN, /* missing ) */ - /* 15 */ - REG_ESUBREG, /* reference to non-existent subpattern */ - REG_INVARG, /* erroffset passed as NULL */ - REG_INVARG, /* unknown option bit(s) set */ - REG_EPAREN, /* missing ) after comment */ - REG_ESIZE, /* parentheses nested too deeply */ - /* 20 */ - REG_ESIZE, /* regular expression too large */ - REG_ESPACE, /* failed to get memory */ - REG_EPAREN, /* unmatched parentheses */ - REG_ASSERT, /* internal error: code overflow */ - REG_BADPAT, /* unrecognized character after (?< */ - /* 25 */ - REG_BADPAT, /* lookbehind assertion is not fixed length */ - REG_BADPAT, /* malformed number or name after (?( */ - REG_BADPAT, /* conditional group contains more than two branches */ - REG_BADPAT, /* assertion expected after (?( */ - REG_BADPAT, /* (?R or (?[+-]digits must be followed by ) */ - /* 30 */ - REG_ECTYPE, /* unknown POSIX class name */ - REG_BADPAT, /* POSIX collating elements are not supported */ - REG_INVARG, /* this version of PCRE is not compiled with PCRE_UTF8 support */ - REG_BADPAT, /* spare error */ - REG_BADPAT, /* character value in \x{} or \o{} is too large */ - /* 35 */ - REG_BADPAT, /* invalid condition (?(0) */ - REG_BADPAT, /* \C not allowed in lookbehind assertion */ - REG_EESCAPE, /* PCRE does not support \L, \l, \N, \U, or \u */ - REG_BADPAT, /* number after (?C is > 255 */ - REG_BADPAT, /* closing ) for (?C expected */ - /* 40 */ - REG_BADPAT, /* recursive call could loop indefinitely */ - REG_BADPAT, /* unrecognized character after (?P */ - REG_BADPAT, /* syntax error in subpattern name (missing terminator) */ - REG_BADPAT, /* two named subpatterns have the same name */ - REG_BADPAT, /* invalid UTF-8 string */ - /* 45 */ - REG_BADPAT, /* support for \P, \p, and \X has not been compiled */ - REG_BADPAT, /* malformed \P or \p sequence */ - REG_BADPAT, /* unknown property name after \P or \p */ - REG_BADPAT, /* subpattern name is too long (maximum 32 characters) */ - REG_BADPAT, /* too many named subpatterns (maximum 10,000) */ - /* 50 */ - REG_BADPAT, /* repeated subpattern is too long */ - REG_BADPAT, /* octal value is greater than \377 (not in UTF-8 mode) */ - REG_BADPAT, /* internal error: overran compiling workspace */ - REG_BADPAT, /* internal error: previously-checked referenced subpattern not found */ - REG_BADPAT, /* DEFINE group contains more than one branch */ - /* 55 */ - REG_BADPAT, /* repeating a DEFINE group is not allowed */ - REG_INVARG, /* inconsistent NEWLINE options */ - REG_BADPAT, /* \g is not followed followed by an (optionally braced) non-zero number */ - REG_BADPAT, /* a numbered reference must not be zero */ - REG_BADPAT, /* an argument is not allowed for (*ACCEPT), (*FAIL), or (*COMMIT) */ - /* 60 */ - REG_BADPAT, /* (*VERB) not recognized */ - REG_BADPAT, /* number is too big */ - REG_BADPAT, /* subpattern name expected */ - REG_BADPAT, /* digit expected after (?+ */ - REG_BADPAT, /* ] is an invalid data character in JavaScript compatibility mode */ - /* 65 */ - REG_BADPAT, /* different names for subpatterns of the same number are not allowed */ - REG_BADPAT, /* (*MARK) must have an argument */ - REG_INVARG, /* this version of PCRE is not compiled with PCRE_UCP support */ - REG_BADPAT, /* \c must be followed by an ASCII character */ - REG_BADPAT, /* \k is not followed by a braced, angle-bracketed, or quoted name */ - /* 70 */ - REG_BADPAT, /* internal error: unknown opcode in find_fixedlength() */ - REG_BADPAT, /* \N is not supported in a class */ - REG_BADPAT, /* too many forward references */ - REG_BADPAT, /* disallowed UTF-8/16/32 code point (>= 0xd800 && <= 0xdfff) */ - REG_BADPAT, /* invalid UTF-16 string (should not occur) */ - /* 75 */ - REG_BADPAT, /* overlong MARK name */ - REG_BADPAT, /* character value in \u.... sequence is too large */ - REG_BADPAT, /* invalid UTF-32 string (should not occur) */ - REG_BADPAT, /* setting UTF is disabled by the application */ - REG_BADPAT, /* non-hex character in \\x{} (closing brace missing?) */ - /* 80 */ - REG_BADPAT, /* non-octal character in \o{} (closing brace missing?) */ - REG_BADPAT, /* missing opening brace after \o */ - REG_BADPAT, /* parentheses too deeply nested */ - REG_BADPAT, /* invalid range in character class */ - REG_BADPAT, /* group name must start with a non-digit */ - /* 85 */ - REG_BADPAT, /* parentheses too deeply nested (stack check) */ - REG_BADPAT /* missing digits in \x{} or \o{} */ -}; - -/* Table of texts corresponding to POSIX error codes */ - -static const char *const pstring[] = { - "", /* Dummy for value 0 */ - "internal error", /* REG_ASSERT */ - "invalid repeat counts in {}", /* BADBR */ - "pattern error", /* BADPAT */ - "? * + invalid", /* BADRPT */ - "unbalanced {}", /* EBRACE */ - "unbalanced []", /* EBRACK */ - "collation error - not relevant", /* ECOLLATE */ - "bad class", /* ECTYPE */ - "bad escape sequence", /* EESCAPE */ - "empty expression", /* EMPTY */ - "unbalanced ()", /* EPAREN */ - "bad range inside []", /* ERANGE */ - "expression too big", /* ESIZE */ - "failed to get memory", /* ESPACE */ - "bad back reference", /* ESUBREG */ - "bad argument", /* INVARG */ - "match failed" /* NOMATCH */ -}; - - - - -/************************************************* -* Translate error code to string * -*************************************************/ - -PCREPOSIX_EXP_DEFN size_t PCRE_CALL_CONVENTION -regerror(int errcode, const regex_t *preg, char *errbuf, size_t errbuf_size) -{ -const char *message, *addmessage; -size_t length, addlength; - -message = (errcode >= (int)(sizeof(pstring)/sizeof(char *)))? - "unknown error code" : pstring[errcode]; -length = strlen(message) + 1; - -addmessage = " at offset "; -addlength = (preg != NULL && (int)preg->re_erroffset != -1)? - strlen(addmessage) + 6 : 0; - -if (errbuf_size > 0) - { - if (addlength > 0 && errbuf_size >= length + addlength) - sprintf(errbuf, "%s%s%-6d", message, addmessage, (int)preg->re_erroffset); - else - { - strncpy(errbuf, message, errbuf_size - 1); - errbuf[errbuf_size-1] = 0; - } - } - -return length + addlength; -} - - - - -/************************************************* -* Free store held by a regex * -*************************************************/ - -PCREPOSIX_EXP_DEFN void PCRE_CALL_CONVENTION -regfree(regex_t *preg) -{ -(PUBL(free))(preg->re_pcre); -} - - - - -/************************************************* -* Compile a regular expression * -*************************************************/ - -/* -Arguments: - preg points to a structure for recording the compiled expression - pattern the pattern to compile - cflags compilation flags - -Returns: 0 on success - various non-zero codes on failure -*/ - -PCREPOSIX_EXP_DEFN int PCRE_CALL_CONVENTION -regcomp(regex_t *preg, const char *pattern, int cflags) -{ -const char *errorptr; -int erroffset; -int errorcode; -int options = 0; -int re_nsub = 0; - -if ((cflags & REG_ICASE) != 0) options |= PCRE_CASELESS; -if ((cflags & REG_NEWLINE) != 0) options |= PCRE_MULTILINE; -if ((cflags & REG_DOTALL) != 0) options |= PCRE_DOTALL; -if ((cflags & REG_NOSUB) != 0) options |= PCRE_NO_AUTO_CAPTURE; -if ((cflags & REG_UTF8) != 0) options |= PCRE_UTF8; -if ((cflags & REG_UCP) != 0) options |= PCRE_UCP; -if ((cflags & REG_UNGREEDY) != 0) options |= PCRE_UNGREEDY; - -preg->re_pcre = pcre_compile2(pattern, options, &errorcode, &errorptr, - &erroffset, NULL); -preg->re_erroffset = erroffset; - -/* Safety: if the error code is too big for the translation vector (which -should not happen, but we all make mistakes), return REG_BADPAT. */ - -if (preg->re_pcre == NULL) - { - return (errorcode < (int)(sizeof(eint)/sizeof(const int)))? - eint[errorcode] : REG_BADPAT; - } - -(void)pcre_fullinfo((const pcre *)preg->re_pcre, NULL, PCRE_INFO_CAPTURECOUNT, - &re_nsub); -preg->re_nsub = (size_t)re_nsub; -return 0; -} - - - - -/************************************************* -* Match a regular expression * -*************************************************/ - -/* Unfortunately, PCRE requires 3 ints of working space for each captured -substring, so we have to get and release working store instead of just using -the POSIX structures as was done in earlier releases when PCRE needed only 2 -ints. However, if the number of possible capturing brackets is small, use a -block of store on the stack, to reduce the use of malloc/free. The threshold is -in a macro that can be changed at configure time. - -If REG_NOSUB was specified at compile time, the PCRE_NO_AUTO_CAPTURE flag will -be set. When this is the case, the nmatch and pmatch arguments are ignored, and -the only result is yes/no/error. */ - -PCREPOSIX_EXP_DEFN int PCRE_CALL_CONVENTION -regexec(const regex_t *preg, const char *string, size_t nmatch, - regmatch_t pmatch[], int eflags) -{ -int rc, so, eo; -int options = 0; -int *ovector = NULL; -int small_ovector[POSIX_MALLOC_THRESHOLD * 3]; -BOOL allocated_ovector = FALSE; -BOOL nosub = - (REAL_PCRE_OPTIONS((const pcre *)preg->re_pcre) & PCRE_NO_AUTO_CAPTURE) != 0; - -if ((eflags & REG_NOTBOL) != 0) options |= PCRE_NOTBOL; -if ((eflags & REG_NOTEOL) != 0) options |= PCRE_NOTEOL; -if ((eflags & REG_NOTEMPTY) != 0) options |= PCRE_NOTEMPTY; - -((regex_t *)preg)->re_erroffset = (size_t)(-1); /* Only has meaning after compile */ - -/* When no string data is being returned, or no vector has been passed in which -to put it, ensure that nmatch is zero. Otherwise, ensure the vector for holding -the return data is large enough. */ - -if (nosub || pmatch == NULL) nmatch = 0; - -else if (nmatch > 0) - { - if (nmatch <= POSIX_MALLOC_THRESHOLD) - { - ovector = &(small_ovector[0]); - } - else - { - if (nmatch > INT_MAX/(sizeof(int) * 3)) return REG_ESPACE; - ovector = (int *)malloc(sizeof(int) * nmatch * 3); - if (ovector == NULL) return REG_ESPACE; - allocated_ovector = TRUE; - } - } - -/* REG_STARTEND is a BSD extension, to allow for non-NUL-terminated strings. -The man page from OS X says "REG_STARTEND affects only the location of the -string, not how it is matched". That is why the "so" value is used to bump the -start location rather than being passed as a PCRE "starting offset". */ - -if ((eflags & REG_STARTEND) != 0) - { - so = pmatch[0].rm_so; - eo = pmatch[0].rm_eo; - } -else - { - so = 0; - eo = (int)strlen(string); - } - -rc = pcre_exec((const pcre *)preg->re_pcre, NULL, string + so, (eo - so), - 0, options, ovector, (int)(nmatch * 3)); - -if (rc == 0) rc = (int)nmatch; /* All captured slots were filled in */ - -/* Successful match */ - -if (rc >= 0) - { - size_t i; - if (!nosub) - { - for (i = 0; i < (size_t)rc; i++) - { - pmatch[i].rm_so = ovector[i*2]; - pmatch[i].rm_eo = ovector[i*2+1]; - } - if (allocated_ovector) free(ovector); - for (; i < nmatch; i++) pmatch[i].rm_so = pmatch[i].rm_eo = -1; - } - return 0; - } - -/* Unsuccessful match */ - -if (allocated_ovector) free(ovector); -switch(rc) - { -/* ========================================================================== */ - /* These cases are never obeyed. This is a fudge that causes a compile-time - error if the vector eint, which is indexed by compile-time error number, is - not the correct length. It seems to be the only way to do such a check at - compile time, as the sizeof() operator does not work in the C preprocessor. - As all the PCRE_ERROR_xxx values are negative, we can use 0 and 1. */ - - case 0: - case (sizeof(eint)/sizeof(int) == ERRCOUNT): - return REG_ASSERT; -/* ========================================================================== */ - - case PCRE_ERROR_NOMATCH: return REG_NOMATCH; - case PCRE_ERROR_NULL: return REG_INVARG; - case PCRE_ERROR_BADOPTION: return REG_INVARG; - case PCRE_ERROR_BADMAGIC: return REG_INVARG; - case PCRE_ERROR_UNKNOWN_NODE: return REG_ASSERT; - case PCRE_ERROR_NOMEMORY: return REG_ESPACE; - case PCRE_ERROR_MATCHLIMIT: return REG_ESPACE; - case PCRE_ERROR_BADUTF8: return REG_INVARG; - case PCRE_ERROR_BADUTF8_OFFSET: return REG_INVARG; - case PCRE_ERROR_BADMODE: return REG_INVARG; - default: return REG_ASSERT; - } -} - -/* End of pcreposix.c */ diff --git a/src/third_party/pcre-8.38/pcreposix.h b/src/third_party/pcre-8.38/pcreposix.h deleted file mode 100644 index c77c0b0523c..00000000000 --- a/src/third_party/pcre-8.38/pcreposix.h +++ /dev/null @@ -1,146 +0,0 @@ -/************************************************* -* Perl-Compatible Regular Expressions * -*************************************************/ - -#ifndef _PCREPOSIX_H -#define _PCREPOSIX_H - -/* This is the header for the POSIX wrapper interface to the PCRE Perl- -Compatible Regular Expression library. It defines the things POSIX says should -be there. I hope. - - Copyright (c) 1997-2012 University of Cambridge - ------------------------------------------------------------------------------ -Redistribution and use in source and binary forms, with or without -modification, are permitted provided that the following conditions are met: - - * Redistributions of source code must retain the above copyright notice, - this list of conditions and the following disclaimer. - - * Redistributions in binary form must reproduce the above copyright - notice, this list of conditions and the following disclaimer in the - documentation and/or other materials provided with the distribution. - - * Neither the name of the University of Cambridge nor the names of its - contributors may be used to endorse or promote products derived from - this software without specific prior written permission. - -THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS" -AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE -IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE -ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR CONTRIBUTORS BE -LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR -CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF -SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS -INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN -CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) -ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE -POSSIBILITY OF SUCH DAMAGE. ------------------------------------------------------------------------------ -*/ - -/* Have to include stdlib.h in order to ensure that size_t is defined. */ - -#include <stdlib.h> - -/* Allow for C++ users */ - -#ifdef __cplusplus -extern "C" { -#endif - -/* Options, mostly defined by POSIX, but with some extras. */ - -#define REG_ICASE 0x0001 /* Maps to PCRE_CASELESS */ -#define REG_NEWLINE 0x0002 /* Maps to PCRE_MULTILINE */ -#define REG_NOTBOL 0x0004 /* Maps to PCRE_NOTBOL */ -#define REG_NOTEOL 0x0008 /* Maps to PCRE_NOTEOL */ -#define REG_DOTALL 0x0010 /* NOT defined by POSIX; maps to PCRE_DOTALL */ -#define REG_NOSUB 0x0020 /* Maps to PCRE_NO_AUTO_CAPTURE */ -#define REG_UTF8 0x0040 /* NOT defined by POSIX; maps to PCRE_UTF8 */ -#define REG_STARTEND 0x0080 /* BSD feature: pass subject string by so,eo */ -#define REG_NOTEMPTY 0x0100 /* NOT defined by POSIX; maps to PCRE_NOTEMPTY */ -#define REG_UNGREEDY 0x0200 /* NOT defined by POSIX; maps to PCRE_UNGREEDY */ -#define REG_UCP 0x0400 /* NOT defined by POSIX; maps to PCRE_UCP */ - -/* This is not used by PCRE, but by defining it we make it easier -to slot PCRE into existing programs that make POSIX calls. */ - -#define REG_EXTENDED 0 - -/* Error values. Not all these are relevant or used by the wrapper. */ - -enum { - REG_ASSERT = 1, /* internal error ? */ - REG_BADBR, /* invalid repeat counts in {} */ - REG_BADPAT, /* pattern error */ - REG_BADRPT, /* ? * + invalid */ - REG_EBRACE, /* unbalanced {} */ - REG_EBRACK, /* unbalanced [] */ - REG_ECOLLATE, /* collation error - not relevant */ - REG_ECTYPE, /* bad class */ - REG_EESCAPE, /* bad escape sequence */ - REG_EMPTY, /* empty expression */ - REG_EPAREN, /* unbalanced () */ - REG_ERANGE, /* bad range inside [] */ - REG_ESIZE, /* expression too big */ - REG_ESPACE, /* failed to get memory */ - REG_ESUBREG, /* bad back reference */ - REG_INVARG, /* bad argument */ - REG_NOMATCH /* match failed */ -}; - - -/* The structure representing a compiled regular expression. */ - -typedef struct { - void *re_pcre; - size_t re_nsub; - size_t re_erroffset; -} regex_t; - -/* The structure in which a captured offset is returned. */ - -typedef int regoff_t; - -typedef struct { - regoff_t rm_so; - regoff_t rm_eo; -} regmatch_t; - -/* When an application links to a PCRE DLL in Windows, the symbols that are -imported have to be identified as such. When building PCRE, the appropriate -export settings are needed, and are set in pcreposix.c before including this -file. */ - -#if defined(_WIN32) && !defined(PCRE_STATIC) && !defined(PCREPOSIX_EXP_DECL) -# define PCREPOSIX_EXP_DECL extern __declspec(dllimport) -# define PCREPOSIX_EXP_DEFN __declspec(dllimport) -#endif - -/* By default, we use the standard "extern" declarations. */ - -#ifndef PCREPOSIX_EXP_DECL -# ifdef __cplusplus -# define PCREPOSIX_EXP_DECL extern "C" -# define PCREPOSIX_EXP_DEFN extern "C" -# else -# define PCREPOSIX_EXP_DECL extern -# define PCREPOSIX_EXP_DEFN extern -# endif -#endif - -/* The functions */ - -PCREPOSIX_EXP_DECL int regcomp(regex_t *, const char *, int); -PCREPOSIX_EXP_DECL int regexec(const regex_t *, const char *, size_t, - regmatch_t *, int); -PCREPOSIX_EXP_DECL size_t regerror(int, const regex_t *, char *, size_t); -PCREPOSIX_EXP_DECL void regfree(regex_t *); - -#ifdef __cplusplus -} /* extern "C" */ -#endif - -#endif /* End of pcreposix.h */ diff --git a/src/third_party/pcre-8.38/pcretest.c b/src/third_party/pcre-8.38/pcretest.c deleted file mode 100644 index 488e419462e..00000000000 --- a/src/third_party/pcre-8.38/pcretest.c +++ /dev/null @@ -1,5742 +0,0 @@ -/************************************************* -* PCRE testing program * -*************************************************/ - -/* This program was hacked up as a tester for PCRE. I really should have -written it more tidily in the first place. Will I ever learn? It has grown and -been extended and consequently is now rather, er, *very* untidy in places. The -addition of 16-bit support has made it even worse. :-( - ------------------------------------------------------------------------------ -Redistribution and use in source and binary forms, with or without -modification, are permitted provided that the following conditions are met: - - * Redistributions of source code must retain the above copyright notice, - this list of conditions and the following disclaimer. - - * Redistributions in binary form must reproduce the above copyright - notice, this list of conditions and the following disclaimer in the - documentation and/or other materials provided with the distribution. - - * Neither the name of the University of Cambridge nor the names of its - contributors may be used to endorse or promote products derived from - this software without specific prior written permission. - -THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS" -AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE -IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE -ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR CONTRIBUTORS BE -LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR -CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF -SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS -INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN -CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) -ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE -POSSIBILITY OF SUCH DAMAGE. ------------------------------------------------------------------------------ -*/ - -/* This program now supports the testing of all of the 8-bit, 16-bit, and -32-bit PCRE libraries in a single program. This is different from the modules -such as pcre_compile.c in the library itself, which are compiled separately for -each mode. If two modes are enabled, for example, pcre_compile.c is compiled -twice. By contrast, pcretest.c is compiled only once. Therefore, it must not -make use of any of the macros from pcre_internal.h that depend on -COMPILE_PCRE8, COMPILE_PCRE16, or COMPILE_PCRE32. It does, however, make use of -SUPPORT_PCRE8, SUPPORT_PCRE16, and SUPPORT_PCRE32 to ensure that it calls only -supported library functions. */ - -#ifdef HAVE_CONFIG_H -#include "config.h" -#endif - -#include <ctype.h> -#include <stdio.h> -#include <string.h> -#include <stdlib.h> -#include <time.h> -#include <locale.h> -#include <errno.h> - -/* Both libreadline and libedit are optionally supported. The user-supplied -original patch uses readline/readline.h for libedit, but in at least one system -it is installed as editline/readline.h, so the configuration code now looks for -that first, falling back to readline/readline.h. */ - -#if defined(SUPPORT_LIBREADLINE) || defined(SUPPORT_LIBEDIT) -#ifdef HAVE_UNISTD_H -#include <unistd.h> -#endif -#if defined(SUPPORT_LIBREADLINE) -#include <readline/readline.h> -#include <readline/history.h> -#else -#if defined(HAVE_EDITLINE_READLINE_H) -#include <editline/readline.h> -#else -#include <readline/readline.h> -#endif -#endif -#endif - -/* A number of things vary for Windows builds. Originally, pcretest opened its -input and output without "b"; then I was told that "b" was needed in some -environments, so it was added for release 5.0 to both the input and output. (It -makes no difference on Unix-like systems.) Later I was told that it is wrong -for the input on Windows. I've now abstracted the modes into two macros that -are set here, to make it easier to fiddle with them, and removed "b" from the -input mode under Windows. */ - -#if defined(_WIN32) || defined(WIN32) -#include <io.h> /* For _setmode() */ -#include <fcntl.h> /* For _O_BINARY */ -#define INPUT_MODE "r" -#define OUTPUT_MODE "wb" - -#ifndef isatty -#define isatty _isatty /* This is what Windows calls them, I'm told, */ -#endif /* though in some environments they seem to */ - /* be already defined, hence the #ifndefs. */ -#ifndef fileno -#define fileno _fileno -#endif - -/* A user sent this fix for Borland Builder 5 under Windows. */ - -#ifdef __BORLANDC__ -#define _setmode(handle, mode) setmode(handle, mode) -#endif - -/* Not Windows */ - -#else -#include <sys/time.h> /* These two includes are needed */ -#include <sys/resource.h> /* for setrlimit(). */ -#if defined NATIVE_ZOS /* z/OS uses non-binary I/O */ -#define INPUT_MODE "r" -#define OUTPUT_MODE "w" -#else -#define INPUT_MODE "rb" -#define OUTPUT_MODE "wb" -#endif -#endif - -#ifdef __VMS -#include <ssdef.h> -void vms_setsymbol( char *, char *, int ); -#endif - - -#define PRIV(name) name - -/* We have to include pcre_internal.h because we need the internal info for -displaying the results of pcre_study() and we also need to know about the -internal macros, structures, and other internal data values; pcretest has -"inside information" compared to a program that strictly follows the PCRE API. - -Although pcre_internal.h does itself include pcre.h, we explicitly include it -here before pcre_internal.h so that the PCRE_EXP_xxx macros get set -appropriately for an application, not for building PCRE. */ - -#include "pcre.h" -#include "pcre_internal.h" - -/* The pcre_printint() function, which prints the internal form of a compiled -regex, is held in a separate file so that (a) it can be compiled in either -8-, 16- or 32-bit mode, and (b) it can be #included directly in pcre_compile.c -when that is compiled in debug mode. */ - -#ifdef SUPPORT_PCRE8 -void pcre_printint(pcre *external_re, FILE *f, BOOL print_lengths); -#endif -#ifdef SUPPORT_PCRE16 -void pcre16_printint(pcre *external_re, FILE *f, BOOL print_lengths); -#endif -#ifdef SUPPORT_PCRE32 -void pcre32_printint(pcre *external_re, FILE *f, BOOL print_lengths); -#endif - -/* We need access to some of the data tables that PCRE uses. So as not to have -to keep two copies, we include the source files here, changing the names of the -external symbols to prevent clashes. */ - -#define PCRE_INCLUDED - -#include "pcre_tables.c" -#include "pcre_ucd.c" - -/* The definition of the macro PRINTABLE, which determines whether to print an -output character as-is or as a hex value when showing compiled patterns, is -the same as in the printint.src file. We uses it here in cases when the locale -has not been explicitly changed, so as to get consistent output from systems -that differ in their output from isprint() even in the "C" locale. */ - -#ifdef EBCDIC -#define PRINTABLE(c) ((c) >= 64 && (c) < 255) -#else -#define PRINTABLE(c) ((c) >= 32 && (c) < 127) -#endif - -#define PRINTOK(c) (locale_set? isprint(c) : PRINTABLE(c)) - -/* Posix support is disabled in 16 or 32 bit only mode. */ -#if !defined SUPPORT_PCRE8 && !defined NOPOSIX -#define NOPOSIX -#endif - -/* It is possible to compile this test program without including support for -testing the POSIX interface, though this is not available via the standard -Makefile. */ - -#if !defined NOPOSIX -#include "pcreposix.h" -#endif - -/* It is also possible, originally for the benefit of a version that was -imported into Exim, to build pcretest without support for UTF8 or UTF16 (define -NOUTF), without the interface to the DFA matcher (NODFA). In fact, we -automatically cut out the UTF support if PCRE is built without it. */ - -#ifndef SUPPORT_UTF -#ifndef NOUTF -#define NOUTF -#endif -#endif - -/* To make the code a bit tidier for 8/16/32-bit support, we define macros -for all the pcre[16]_xxx functions (except pcre16_fullinfo, which is called -only from one place and is handled differently). I couldn't dream up any way of -using a single macro to do this in a generic way, because of the many different -argument requirements. We know that at least one of SUPPORT_PCRE8 and -SUPPORT_PCRE16 must be set. First define macros for each individual mode; then -use these in the definitions of generic macros. - -**** Special note about the PCHARSxxx macros: the address of the string to be -printed is always given as two arguments: a base address followed by an offset. -The base address is cast to the correct data size for 8 or 16 bit data; the -offset is in units of this size. If the string were given as base+offset in one -argument, the casting might be incorrectly applied. */ - -#ifdef SUPPORT_PCRE8 - -#define PCHARS8(lv, p, offset, len, f) \ - lv = pchars((pcre_uint8 *)(p) + offset, len, f) - -#define PCHARSV8(p, offset, len, f) \ - (void)pchars((pcre_uint8 *)(p) + offset, len, f) - -#define READ_CAPTURE_NAME8(p, cn8, cn16, cn32, re) \ - p = read_capture_name8(p, cn8, re) - -#define STRLEN8(p) ((int)strlen((char *)p)) - -#define SET_PCRE_CALLOUT8(callout) \ - pcre_callout = callout - -#define SET_PCRE_STACK_GUARD8(stack_guard) \ - pcre_stack_guard = stack_guard - -#define PCRE_ASSIGN_JIT_STACK8(extra, callback, userdata) \ - pcre_assign_jit_stack(extra, callback, userdata) - -#define PCRE_COMPILE8(re, pat, options, error, erroffset, tables) \ - re = pcre_compile((char *)pat, options, error, erroffset, tables) - -#define PCRE_COPY_NAMED_SUBSTRING8(rc, re, bptr, offsets, count, \ - namesptr, cbuffer, size) \ - rc = pcre_copy_named_substring(re, (char *)bptr, offsets, count, \ - (char *)namesptr, cbuffer, size) - -#define PCRE_COPY_SUBSTRING8(rc, bptr, offsets, count, i, cbuffer, size) \ - rc = pcre_copy_substring((char *)bptr, offsets, count, i, cbuffer, size) - -#define PCRE_DFA_EXEC8(count, re, extra, bptr, len, start_offset, options, \ - offsets, size_offsets, workspace, size_workspace) \ - count = pcre_dfa_exec(re, extra, (char *)bptr, len, start_offset, options, \ - offsets, size_offsets, workspace, size_workspace) - -#define PCRE_EXEC8(count, re, extra, bptr, len, start_offset, options, \ - offsets, size_offsets) \ - count = pcre_exec(re, extra, (char *)bptr, len, start_offset, options, \ - offsets, size_offsets) - -#define PCRE_FREE_STUDY8(extra) \ - pcre_free_study(extra) - -#define PCRE_FREE_SUBSTRING8(substring) \ - pcre_free_substring(substring) - -#define PCRE_FREE_SUBSTRING_LIST8(listptr) \ - pcre_free_substring_list(listptr) - -#define PCRE_GET_NAMED_SUBSTRING8(rc, re, bptr, offsets, count, \ - getnamesptr, subsptr) \ - rc = pcre_get_named_substring(re, (char *)bptr, offsets, count, \ - (char *)getnamesptr, subsptr) - -#define PCRE_GET_STRINGNUMBER8(n, rc, ptr) \ - n = pcre_get_stringnumber(re, (char *)ptr) - -#define PCRE_GET_SUBSTRING8(rc, bptr, offsets, count, i, subsptr) \ - rc = pcre_get_substring((char *)bptr, offsets, count, i, subsptr) - -#define PCRE_GET_SUBSTRING_LIST8(rc, bptr, offsets, count, listptr) \ - rc = pcre_get_substring_list((const char *)bptr, offsets, count, listptr) - -#define PCRE_PATTERN_TO_HOST_BYTE_ORDER8(rc, re, extra, tables) \ - rc = pcre_pattern_to_host_byte_order(re, extra, tables) - -#define PCRE_PRINTINT8(re, outfile, debug_lengths) \ - pcre_printint(re, outfile, debug_lengths) - -#define PCRE_STUDY8(extra, re, options, error) \ - extra = pcre_study(re, options, error) - -#define PCRE_JIT_STACK_ALLOC8(startsize, maxsize) \ - pcre_jit_stack_alloc(startsize, maxsize) - -#define PCRE_JIT_STACK_FREE8(stack) \ - pcre_jit_stack_free(stack) - -#define pcre8_maketables pcre_maketables - -#endif /* SUPPORT_PCRE8 */ - -/* -----------------------------------------------------------*/ - -#ifdef SUPPORT_PCRE16 - -#define PCHARS16(lv, p, offset, len, f) \ - lv = pchars16((PCRE_SPTR16)(p) + offset, len, f) - -#define PCHARSV16(p, offset, len, f) \ - (void)pchars16((PCRE_SPTR16)(p) + offset, len, f) - -#define READ_CAPTURE_NAME16(p, cn8, cn16, cn32, re) \ - p = read_capture_name16(p, cn16, re) - -#define STRLEN16(p) ((int)strlen16((PCRE_SPTR16)p)) - -#define SET_PCRE_CALLOUT16(callout) \ - pcre16_callout = (int (*)(pcre16_callout_block *))callout - -#define SET_PCRE_STACK_GUARD16(stack_guard) \ - pcre16_stack_guard = (int (*)(void))stack_guard - -#define PCRE_ASSIGN_JIT_STACK16(extra, callback, userdata) \ - pcre16_assign_jit_stack((pcre16_extra *)extra, \ - (pcre16_jit_callback)callback, userdata) - -#define PCRE_COMPILE16(re, pat, options, error, erroffset, tables) \ - re = (pcre *)pcre16_compile((PCRE_SPTR16)pat, options, error, erroffset, \ - tables) - -#define PCRE_COPY_NAMED_SUBSTRING16(rc, re, bptr, offsets, count, \ - namesptr, cbuffer, size) \ - rc = pcre16_copy_named_substring((pcre16 *)re, (PCRE_SPTR16)bptr, offsets, \ - count, (PCRE_SPTR16)namesptr, (PCRE_UCHAR16 *)cbuffer, size/2) - -#define PCRE_COPY_SUBSTRING16(rc, bptr, offsets, count, i, cbuffer, size) \ - rc = pcre16_copy_substring((PCRE_SPTR16)bptr, offsets, count, i, \ - (PCRE_UCHAR16 *)cbuffer, size/2) - -#define PCRE_DFA_EXEC16(count, re, extra, bptr, len, start_offset, options, \ - offsets, size_offsets, workspace, size_workspace) \ - count = pcre16_dfa_exec((pcre16 *)re, (pcre16_extra *)extra, \ - (PCRE_SPTR16)bptr, len, start_offset, options, offsets, size_offsets, \ - workspace, size_workspace) - -#define PCRE_EXEC16(count, re, extra, bptr, len, start_offset, options, \ - offsets, size_offsets) \ - count = pcre16_exec((pcre16 *)re, (pcre16_extra *)extra, (PCRE_SPTR16)bptr, \ - len, start_offset, options, offsets, size_offsets) - -#define PCRE_FREE_STUDY16(extra) \ - pcre16_free_study((pcre16_extra *)extra) - -#define PCRE_FREE_SUBSTRING16(substring) \ - pcre16_free_substring((PCRE_SPTR16)substring) - -#define PCRE_FREE_SUBSTRING_LIST16(listptr) \ - pcre16_free_substring_list((PCRE_SPTR16 *)listptr) - -#define PCRE_GET_NAMED_SUBSTRING16(rc, re, bptr, offsets, count, \ - getnamesptr, subsptr) \ - rc = pcre16_get_named_substring((pcre16 *)re, (PCRE_SPTR16)bptr, offsets, \ - count, (PCRE_SPTR16)getnamesptr, (PCRE_SPTR16 *)(void*)subsptr) - -#define PCRE_GET_STRINGNUMBER16(n, rc, ptr) \ - n = pcre16_get_stringnumber(re, (PCRE_SPTR16)ptr) - -#define PCRE_GET_SUBSTRING16(rc, bptr, offsets, count, i, subsptr) \ - rc = pcre16_get_substring((PCRE_SPTR16)bptr, offsets, count, i, \ - (PCRE_SPTR16 *)(void*)subsptr) - -#define PCRE_GET_SUBSTRING_LIST16(rc, bptr, offsets, count, listptr) \ - rc = pcre16_get_substring_list((PCRE_SPTR16)bptr, offsets, count, \ - (PCRE_SPTR16 **)(void*)listptr) - -#define PCRE_PATTERN_TO_HOST_BYTE_ORDER16(rc, re, extra, tables) \ - rc = pcre16_pattern_to_host_byte_order((pcre16 *)re, (pcre16_extra *)extra, \ - tables) - -#define PCRE_PRINTINT16(re, outfile, debug_lengths) \ - pcre16_printint(re, outfile, debug_lengths) - -#define PCRE_STUDY16(extra, re, options, error) \ - extra = (pcre_extra *)pcre16_study((pcre16 *)re, options, error) - -#define PCRE_JIT_STACK_ALLOC16(startsize, maxsize) \ - (pcre_jit_stack *)pcre16_jit_stack_alloc(startsize, maxsize) - -#define PCRE_JIT_STACK_FREE16(stack) \ - pcre16_jit_stack_free((pcre16_jit_stack *)stack) - -#endif /* SUPPORT_PCRE16 */ - -/* -----------------------------------------------------------*/ - -#ifdef SUPPORT_PCRE32 - -#define PCHARS32(lv, p, offset, len, f) \ - lv = pchars32((PCRE_SPTR32)(p) + offset, len, use_utf, f) - -#define PCHARSV32(p, offset, len, f) \ - (void)pchars32((PCRE_SPTR32)(p) + offset, len, use_utf, f) - -#define READ_CAPTURE_NAME32(p, cn8, cn16, cn32, re) \ - p = read_capture_name32(p, cn32, re) - -#define STRLEN32(p) ((int)strlen32((PCRE_SPTR32)p)) - -#define SET_PCRE_CALLOUT32(callout) \ - pcre32_callout = (int (*)(pcre32_callout_block *))callout - -#define SET_PCRE_STACK_GUARD32(stack_guard) \ - pcre32_stack_guard = (int (*)(void))stack_guard - -#define PCRE_ASSIGN_JIT_STACK32(extra, callback, userdata) \ - pcre32_assign_jit_stack((pcre32_extra *)extra, \ - (pcre32_jit_callback)callback, userdata) - -#define PCRE_COMPILE32(re, pat, options, error, erroffset, tables) \ - re = (pcre *)pcre32_compile((PCRE_SPTR32)pat, options, error, erroffset, \ - tables) - -#define PCRE_COPY_NAMED_SUBSTRING32(rc, re, bptr, offsets, count, \ - namesptr, cbuffer, size) \ - rc = pcre32_copy_named_substring((pcre32 *)re, (PCRE_SPTR32)bptr, offsets, \ - count, (PCRE_SPTR32)namesptr, (PCRE_UCHAR32 *)cbuffer, size/2) - -#define PCRE_COPY_SUBSTRING32(rc, bptr, offsets, count, i, cbuffer, size) \ - rc = pcre32_copy_substring((PCRE_SPTR32)bptr, offsets, count, i, \ - (PCRE_UCHAR32 *)cbuffer, size/2) - -#define PCRE_DFA_EXEC32(count, re, extra, bptr, len, start_offset, options, \ - offsets, size_offsets, workspace, size_workspace) \ - count = pcre32_dfa_exec((pcre32 *)re, (pcre32_extra *)extra, \ - (PCRE_SPTR32)bptr, len, start_offset, options, offsets, size_offsets, \ - workspace, size_workspace) - -#define PCRE_EXEC32(count, re, extra, bptr, len, start_offset, options, \ - offsets, size_offsets) \ - count = pcre32_exec((pcre32 *)re, (pcre32_extra *)extra, (PCRE_SPTR32)bptr, \ - len, start_offset, options, offsets, size_offsets) - -#define PCRE_FREE_STUDY32(extra) \ - pcre32_free_study((pcre32_extra *)extra) - -#define PCRE_FREE_SUBSTRING32(substring) \ - pcre32_free_substring((PCRE_SPTR32)substring) - -#define PCRE_FREE_SUBSTRING_LIST32(listptr) \ - pcre32_free_substring_list((PCRE_SPTR32 *)listptr) - -#define PCRE_GET_NAMED_SUBSTRING32(rc, re, bptr, offsets, count, \ - getnamesptr, subsptr) \ - rc = pcre32_get_named_substring((pcre32 *)re, (PCRE_SPTR32)bptr, offsets, \ - count, (PCRE_SPTR32)getnamesptr, (PCRE_SPTR32 *)(void*)subsptr) - -#define PCRE_GET_STRINGNUMBER32(n, rc, ptr) \ - n = pcre32_get_stringnumber(re, (PCRE_SPTR32)ptr) - -#define PCRE_GET_SUBSTRING32(rc, bptr, offsets, count, i, subsptr) \ - rc = pcre32_get_substring((PCRE_SPTR32)bptr, offsets, count, i, \ - (PCRE_SPTR32 *)(void*)subsptr) - -#define PCRE_GET_SUBSTRING_LIST32(rc, bptr, offsets, count, listptr) \ - rc = pcre32_get_substring_list((PCRE_SPTR32)bptr, offsets, count, \ - (PCRE_SPTR32 **)(void*)listptr) - -#define PCRE_PATTERN_TO_HOST_BYTE_ORDER32(rc, re, extra, tables) \ - rc = pcre32_pattern_to_host_byte_order((pcre32 *)re, (pcre32_extra *)extra, \ - tables) - -#define PCRE_PRINTINT32(re, outfile, debug_lengths) \ - pcre32_printint(re, outfile, debug_lengths) - -#define PCRE_STUDY32(extra, re, options, error) \ - extra = (pcre_extra *)pcre32_study((pcre32 *)re, options, error) - -#define PCRE_JIT_STACK_ALLOC32(startsize, maxsize) \ - (pcre_jit_stack *)pcre32_jit_stack_alloc(startsize, maxsize) - -#define PCRE_JIT_STACK_FREE32(stack) \ - pcre32_jit_stack_free((pcre32_jit_stack *)stack) - -#endif /* SUPPORT_PCRE32 */ - - -/* ----- More than one mode is supported; a runtime test is needed, except for -pcre_config(), and the JIT stack functions, when it doesn't matter which -available version is called. ----- */ - -enum { - PCRE8_MODE, - PCRE16_MODE, - PCRE32_MODE -}; - -#if (defined (SUPPORT_PCRE8) + defined (SUPPORT_PCRE16) + \ - defined (SUPPORT_PCRE32)) >= 2 - -#define CHAR_SIZE (1 << pcre_mode) - -/* There doesn't seem to be an easy way of writing these macros that can cope -with the 3 pairs of bit sizes plus all three bit sizes. So just handle all the -cases separately. */ - -/* ----- All three modes supported ----- */ - -#if defined(SUPPORT_PCRE8) && defined(SUPPORT_PCRE16) && defined(SUPPORT_PCRE32) - -#define PCHARS(lv, p, offset, len, f) \ - if (pcre_mode == PCRE32_MODE) \ - PCHARS32(lv, p, offset, len, f); \ - else if (pcre_mode == PCRE16_MODE) \ - PCHARS16(lv, p, offset, len, f); \ - else \ - PCHARS8(lv, p, offset, len, f) - -#define PCHARSV(p, offset, len, f) \ - if (pcre_mode == PCRE32_MODE) \ - PCHARSV32(p, offset, len, f); \ - else if (pcre_mode == PCRE16_MODE) \ - PCHARSV16(p, offset, len, f); \ - else \ - PCHARSV8(p, offset, len, f) - -#define READ_CAPTURE_NAME(p, cn8, cn16, cn32, re) \ - if (pcre_mode == PCRE32_MODE) \ - READ_CAPTURE_NAME32(p, cn8, cn16, cn32, re); \ - else if (pcre_mode == PCRE16_MODE) \ - READ_CAPTURE_NAME16(p, cn8, cn16, cn32, re); \ - else \ - READ_CAPTURE_NAME8(p, cn8, cn16, cn32, re) - -#define SET_PCRE_CALLOUT(callout) \ - if (pcre_mode == PCRE32_MODE) \ - SET_PCRE_CALLOUT32(callout); \ - else if (pcre_mode == PCRE16_MODE) \ - SET_PCRE_CALLOUT16(callout); \ - else \ - SET_PCRE_CALLOUT8(callout) - -#define SET_PCRE_STACK_GUARD(stack_guard) \ - if (pcre_mode == PCRE32_MODE) \ - SET_PCRE_STACK_GUARD32(stack_guard); \ - else if (pcre_mode == PCRE16_MODE) \ - SET_PCRE_STACK_GUARD16(stack_guard); \ - else \ - SET_PCRE_STACK_GUARD8(stack_guard) - -#define STRLEN(p) (pcre_mode == PCRE32_MODE ? STRLEN32(p) : pcre_mode == PCRE16_MODE ? STRLEN16(p) : STRLEN8(p)) - -#define PCRE_ASSIGN_JIT_STACK(extra, callback, userdata) \ - if (pcre_mode == PCRE32_MODE) \ - PCRE_ASSIGN_JIT_STACK32(extra, callback, userdata); \ - else if (pcre_mode == PCRE16_MODE) \ - PCRE_ASSIGN_JIT_STACK16(extra, callback, userdata); \ - else \ - PCRE_ASSIGN_JIT_STACK8(extra, callback, userdata) - -#define PCRE_COMPILE(re, pat, options, error, erroffset, tables) \ - if (pcre_mode == PCRE32_MODE) \ - PCRE_COMPILE32(re, pat, options, error, erroffset, tables); \ - else if (pcre_mode == PCRE16_MODE) \ - PCRE_COMPILE16(re, pat, options, error, erroffset, tables); \ - else \ - PCRE_COMPILE8(re, pat, options, error, erroffset, tables) - -#define PCRE_CONFIG pcre_config - -#define PCRE_COPY_NAMED_SUBSTRING(rc, re, bptr, offsets, count, \ - namesptr, cbuffer, size) \ - if (pcre_mode == PCRE32_MODE) \ - PCRE_COPY_NAMED_SUBSTRING32(rc, re, bptr, offsets, count, \ - namesptr, cbuffer, size); \ - else if (pcre_mode == PCRE16_MODE) \ - PCRE_COPY_NAMED_SUBSTRING16(rc, re, bptr, offsets, count, \ - namesptr, cbuffer, size); \ - else \ - PCRE_COPY_NAMED_SUBSTRING8(rc, re, bptr, offsets, count, \ - namesptr, cbuffer, size) - -#define PCRE_COPY_SUBSTRING(rc, bptr, offsets, count, i, cbuffer, size) \ - if (pcre_mode == PCRE32_MODE) \ - PCRE_COPY_SUBSTRING32(rc, bptr, offsets, count, i, cbuffer, size); \ - else if (pcre_mode == PCRE16_MODE) \ - PCRE_COPY_SUBSTRING16(rc, bptr, offsets, count, i, cbuffer, size); \ - else \ - PCRE_COPY_SUBSTRING8(rc, bptr, offsets, count, i, cbuffer, size) - -#define PCRE_DFA_EXEC(count, re, extra, bptr, len, start_offset, options, \ - offsets, size_offsets, workspace, size_workspace) \ - if (pcre_mode == PCRE32_MODE) \ - PCRE_DFA_EXEC32(count, re, extra, bptr, len, start_offset, options, \ - offsets, size_offsets, workspace, size_workspace); \ - else if (pcre_mode == PCRE16_MODE) \ - PCRE_DFA_EXEC16(count, re, extra, bptr, len, start_offset, options, \ - offsets, size_offsets, workspace, size_workspace); \ - else \ - PCRE_DFA_EXEC8(count, re, extra, bptr, len, start_offset, options, \ - offsets, size_offsets, workspace, size_workspace) - -#define PCRE_EXEC(count, re, extra, bptr, len, start_offset, options, \ - offsets, size_offsets) \ - if (pcre_mode == PCRE32_MODE) \ - PCRE_EXEC32(count, re, extra, bptr, len, start_offset, options, \ - offsets, size_offsets); \ - else if (pcre_mode == PCRE16_MODE) \ - PCRE_EXEC16(count, re, extra, bptr, len, start_offset, options, \ - offsets, size_offsets); \ - else \ - PCRE_EXEC8(count, re, extra, bptr, len, start_offset, options, \ - offsets, size_offsets) - -#define PCRE_FREE_STUDY(extra) \ - if (pcre_mode == PCRE32_MODE) \ - PCRE_FREE_STUDY32(extra); \ - else if (pcre_mode == PCRE16_MODE) \ - PCRE_FREE_STUDY16(extra); \ - else \ - PCRE_FREE_STUDY8(extra) - -#define PCRE_FREE_SUBSTRING(substring) \ - if (pcre_mode == PCRE32_MODE) \ - PCRE_FREE_SUBSTRING32(substring); \ - else if (pcre_mode == PCRE16_MODE) \ - PCRE_FREE_SUBSTRING16(substring); \ - else \ - PCRE_FREE_SUBSTRING8(substring) - -#define PCRE_FREE_SUBSTRING_LIST(listptr) \ - if (pcre_mode == PCRE32_MODE) \ - PCRE_FREE_SUBSTRING_LIST32(listptr); \ - else if (pcre_mode == PCRE16_MODE) \ - PCRE_FREE_SUBSTRING_LIST16(listptr); \ - else \ - PCRE_FREE_SUBSTRING_LIST8(listptr) - -#define PCRE_GET_NAMED_SUBSTRING(rc, re, bptr, offsets, count, \ - getnamesptr, subsptr) \ - if (pcre_mode == PCRE32_MODE) \ - PCRE_GET_NAMED_SUBSTRING32(rc, re, bptr, offsets, count, \ - getnamesptr, subsptr); \ - else if (pcre_mode == PCRE16_MODE) \ - PCRE_GET_NAMED_SUBSTRING16(rc, re, bptr, offsets, count, \ - getnamesptr, subsptr); \ - else \ - PCRE_GET_NAMED_SUBSTRING8(rc, re, bptr, offsets, count, \ - getnamesptr, subsptr) - -#define PCRE_GET_STRINGNUMBER(n, rc, ptr) \ - if (pcre_mode == PCRE32_MODE) \ - PCRE_GET_STRINGNUMBER32(n, rc, ptr); \ - else if (pcre_mode == PCRE16_MODE) \ - PCRE_GET_STRINGNUMBER16(n, rc, ptr); \ - else \ - PCRE_GET_STRINGNUMBER8(n, rc, ptr) - -#define PCRE_GET_SUBSTRING(rc, bptr, use_offsets, count, i, subsptr) \ - if (pcre_mode == PCRE32_MODE) \ - PCRE_GET_SUBSTRING32(rc, bptr, use_offsets, count, i, subsptr); \ - else if (pcre_mode == PCRE16_MODE) \ - PCRE_GET_SUBSTRING16(rc, bptr, use_offsets, count, i, subsptr); \ - else \ - PCRE_GET_SUBSTRING8(rc, bptr, use_offsets, count, i, subsptr) - -#define PCRE_GET_SUBSTRING_LIST(rc, bptr, offsets, count, listptr) \ - if (pcre_mode == PCRE32_MODE) \ - PCRE_GET_SUBSTRING_LIST32(rc, bptr, offsets, count, listptr); \ - else if (pcre_mode == PCRE16_MODE) \ - PCRE_GET_SUBSTRING_LIST16(rc, bptr, offsets, count, listptr); \ - else \ - PCRE_GET_SUBSTRING_LIST8(rc, bptr, offsets, count, listptr) - -#define PCRE_JIT_STACK_ALLOC(startsize, maxsize) \ - (pcre_mode == PCRE32_MODE ? \ - PCRE_JIT_STACK_ALLOC32(startsize, maxsize) \ - : pcre_mode == PCRE16_MODE ? \ - PCRE_JIT_STACK_ALLOC16(startsize, maxsize) \ - : PCRE_JIT_STACK_ALLOC8(startsize, maxsize)) - -#define PCRE_JIT_STACK_FREE(stack) \ - if (pcre_mode == PCRE32_MODE) \ - PCRE_JIT_STACK_FREE32(stack); \ - else if (pcre_mode == PCRE16_MODE) \ - PCRE_JIT_STACK_FREE16(stack); \ - else \ - PCRE_JIT_STACK_FREE8(stack) - -#define PCRE_MAKETABLES \ - (pcre_mode == PCRE32_MODE ? pcre32_maketables() : pcre_mode == PCRE16_MODE ? pcre16_maketables() : pcre_maketables()) - -#define PCRE_PATTERN_TO_HOST_BYTE_ORDER(rc, re, extra, tables) \ - if (pcre_mode == PCRE32_MODE) \ - PCRE_PATTERN_TO_HOST_BYTE_ORDER32(rc, re, extra, tables); \ - else if (pcre_mode == PCRE16_MODE) \ - PCRE_PATTERN_TO_HOST_BYTE_ORDER16(rc, re, extra, tables); \ - else \ - PCRE_PATTERN_TO_HOST_BYTE_ORDER8(rc, re, extra, tables) - -#define PCRE_PRINTINT(re, outfile, debug_lengths) \ - if (pcre_mode == PCRE32_MODE) \ - PCRE_PRINTINT32(re, outfile, debug_lengths); \ - else if (pcre_mode == PCRE16_MODE) \ - PCRE_PRINTINT16(re, outfile, debug_lengths); \ - else \ - PCRE_PRINTINT8(re, outfile, debug_lengths) - -#define PCRE_STUDY(extra, re, options, error) \ - if (pcre_mode == PCRE32_MODE) \ - PCRE_STUDY32(extra, re, options, error); \ - else if (pcre_mode == PCRE16_MODE) \ - PCRE_STUDY16(extra, re, options, error); \ - else \ - PCRE_STUDY8(extra, re, options, error) - - -/* ----- Two out of three modes are supported ----- */ - -#else - -/* We can use some macro trickery to make a single set of definitions work in -the three different cases. */ - -/* ----- 32-bit and 16-bit but not 8-bit supported ----- */ - -#if defined(SUPPORT_PCRE32) && defined(SUPPORT_PCRE16) -#define BITONE 32 -#define BITTWO 16 - -/* ----- 32-bit and 8-bit but not 16-bit supported ----- */ - -#elif defined(SUPPORT_PCRE32) && defined(SUPPORT_PCRE8) -#define BITONE 32 -#define BITTWO 8 - -/* ----- 16-bit and 8-bit but not 32-bit supported ----- */ - -#else -#define BITONE 16 -#define BITTWO 8 -#endif - -#define glue(a,b) a##b -#define G(a,b) glue(a,b) - - -/* ----- Common macros for two-mode cases ----- */ - -#define PCHARS(lv, p, offset, len, f) \ - if (pcre_mode == G(G(PCRE,BITONE),_MODE)) \ - G(PCHARS,BITONE)(lv, p, offset, len, f); \ - else \ - G(PCHARS,BITTWO)(lv, p, offset, len, f) - -#define PCHARSV(p, offset, len, f) \ - if (pcre_mode == G(G(PCRE,BITONE),_MODE)) \ - G(PCHARSV,BITONE)(p, offset, len, f); \ - else \ - G(PCHARSV,BITTWO)(p, offset, len, f) - -#define READ_CAPTURE_NAME(p, cn8, cn16, cn32, re) \ - if (pcre_mode == G(G(PCRE,BITONE),_MODE)) \ - G(READ_CAPTURE_NAME,BITONE)(p, cn8, cn16, cn32, re); \ - else \ - G(READ_CAPTURE_NAME,BITTWO)(p, cn8, cn16, cn32, re) - -#define SET_PCRE_CALLOUT(callout) \ - if (pcre_mode == G(G(PCRE,BITONE),_MODE)) \ - G(SET_PCRE_CALLOUT,BITONE)(callout); \ - else \ - G(SET_PCRE_CALLOUT,BITTWO)(callout) - -#define SET_PCRE_STACK_GUARD(stack_guard) \ - if (pcre_mode == G(G(PCRE,BITONE),_MODE)) \ - G(SET_PCRE_STACK_GUARD,BITONE)(stack_guard); \ - else \ - G(SET_PCRE_STACK_GUARD,BITTWO)(stack_guard) - -#define STRLEN(p) ((pcre_mode == G(G(PCRE,BITONE),_MODE)) ? \ - G(STRLEN,BITONE)(p) : G(STRLEN,BITTWO)(p)) - -#define PCRE_ASSIGN_JIT_STACK(extra, callback, userdata) \ - if (pcre_mode == G(G(PCRE,BITONE),_MODE)) \ - G(PCRE_ASSIGN_JIT_STACK,BITONE)(extra, callback, userdata); \ - else \ - G(PCRE_ASSIGN_JIT_STACK,BITTWO)(extra, callback, userdata) - -#define PCRE_COMPILE(re, pat, options, error, erroffset, tables) \ - if (pcre_mode == G(G(PCRE,BITONE),_MODE)) \ - G(PCRE_COMPILE,BITONE)(re, pat, options, error, erroffset, tables); \ - else \ - G(PCRE_COMPILE,BITTWO)(re, pat, options, error, erroffset, tables) - -#define PCRE_CONFIG G(G(pcre,BITONE),_config) - -#define PCRE_COPY_NAMED_SUBSTRING(rc, re, bptr, offsets, count, \ - namesptr, cbuffer, size) \ - if (pcre_mode == G(G(PCRE,BITONE),_MODE)) \ - G(PCRE_COPY_NAMED_SUBSTRING,BITONE)(rc, re, bptr, offsets, count, \ - namesptr, cbuffer, size); \ - else \ - G(PCRE_COPY_NAMED_SUBSTRING,BITTWO)(rc, re, bptr, offsets, count, \ - namesptr, cbuffer, size) - -#define PCRE_COPY_SUBSTRING(rc, bptr, offsets, count, i, cbuffer, size) \ - if (pcre_mode == G(G(PCRE,BITONE),_MODE)) \ - G(PCRE_COPY_SUBSTRING,BITONE)(rc, bptr, offsets, count, i, cbuffer, size); \ - else \ - G(PCRE_COPY_SUBSTRING,BITTWO)(rc, bptr, offsets, count, i, cbuffer, size) - -#define PCRE_DFA_EXEC(count, re, extra, bptr, len, start_offset, options, \ - offsets, size_offsets, workspace, size_workspace) \ - if (pcre_mode == G(G(PCRE,BITONE),_MODE)) \ - G(PCRE_DFA_EXEC,BITONE)(count, re, extra, bptr, len, start_offset, options, \ - offsets, size_offsets, workspace, size_workspace); \ - else \ - G(PCRE_DFA_EXEC,BITTWO)(count, re, extra, bptr, len, start_offset, options, \ - offsets, size_offsets, workspace, size_workspace) - -#define PCRE_EXEC(count, re, extra, bptr, len, start_offset, options, \ - offsets, size_offsets) \ - if (pcre_mode == G(G(PCRE,BITONE),_MODE)) \ - G(PCRE_EXEC,BITONE)(count, re, extra, bptr, len, start_offset, options, \ - offsets, size_offsets); \ - else \ - G(PCRE_EXEC,BITTWO)(count, re, extra, bptr, len, start_offset, options, \ - offsets, size_offsets) - -#define PCRE_FREE_STUDY(extra) \ - if (pcre_mode == G(G(PCRE,BITONE),_MODE)) \ - G(PCRE_FREE_STUDY,BITONE)(extra); \ - else \ - G(PCRE_FREE_STUDY,BITTWO)(extra) - -#define PCRE_FREE_SUBSTRING(substring) \ - if (pcre_mode == G(G(PCRE,BITONE),_MODE)) \ - G(PCRE_FREE_SUBSTRING,BITONE)(substring); \ - else \ - G(PCRE_FREE_SUBSTRING,BITTWO)(substring) - -#define PCRE_FREE_SUBSTRING_LIST(listptr) \ - if (pcre_mode == G(G(PCRE,BITONE),_MODE)) \ - G(PCRE_FREE_SUBSTRING_LIST,BITONE)(listptr); \ - else \ - G(PCRE_FREE_SUBSTRING_LIST,BITTWO)(listptr) - -#define PCRE_GET_NAMED_SUBSTRING(rc, re, bptr, offsets, count, \ - getnamesptr, subsptr) \ - if (pcre_mode == G(G(PCRE,BITONE),_MODE)) \ - G(PCRE_GET_NAMED_SUBSTRING,BITONE)(rc, re, bptr, offsets, count, \ - getnamesptr, subsptr); \ - else \ - G(PCRE_GET_NAMED_SUBSTRING,BITTWO)(rc, re, bptr, offsets, count, \ - getnamesptr, subsptr) - -#define PCRE_GET_STRINGNUMBER(n, rc, ptr) \ - if (pcre_mode == G(G(PCRE,BITONE),_MODE)) \ - G(PCRE_GET_STRINGNUMBER,BITONE)(n, rc, ptr); \ - else \ - G(PCRE_GET_STRINGNUMBER,BITTWO)(n, rc, ptr) - -#define PCRE_GET_SUBSTRING(rc, bptr, use_offsets, count, i, subsptr) \ - if (pcre_mode == G(G(PCRE,BITONE),_MODE)) \ - G(PCRE_GET_SUBSTRING,BITONE)(rc, bptr, use_offsets, count, i, subsptr); \ - else \ - G(PCRE_GET_SUBSTRING,BITTWO)(rc, bptr, use_offsets, count, i, subsptr) - -#define PCRE_GET_SUBSTRING_LIST(rc, bptr, offsets, count, listptr) \ - if (pcre_mode == G(G(PCRE,BITONE),_MODE)) \ - G(PCRE_GET_SUBSTRING_LIST,BITONE)(rc, bptr, offsets, count, listptr); \ - else \ - G(PCRE_GET_SUBSTRING_LIST,BITTWO)(rc, bptr, offsets, count, listptr) - -#define PCRE_JIT_STACK_ALLOC(startsize, maxsize) \ - (pcre_mode == G(G(PCRE,BITONE),_MODE)) ? \ - G(PCRE_JIT_STACK_ALLOC,BITONE)(startsize, maxsize) \ - : G(PCRE_JIT_STACK_ALLOC,BITTWO)(startsize, maxsize) - -#define PCRE_JIT_STACK_FREE(stack) \ - if (pcre_mode == G(G(PCRE,BITONE),_MODE)) \ - G(PCRE_JIT_STACK_FREE,BITONE)(stack); \ - else \ - G(PCRE_JIT_STACK_FREE,BITTWO)(stack) - -#define PCRE_MAKETABLES \ - (pcre_mode == G(G(PCRE,BITONE),_MODE)) ? \ - G(G(pcre,BITONE),_maketables)() : G(G(pcre,BITTWO),_maketables)() - -#define PCRE_PATTERN_TO_HOST_BYTE_ORDER(rc, re, extra, tables) \ - if (pcre_mode == G(G(PCRE,BITONE),_MODE)) \ - G(PCRE_PATTERN_TO_HOST_BYTE_ORDER,BITONE)(rc, re, extra, tables); \ - else \ - G(PCRE_PATTERN_TO_HOST_BYTE_ORDER,BITTWO)(rc, re, extra, tables) - -#define PCRE_PRINTINT(re, outfile, debug_lengths) \ - if (pcre_mode == G(G(PCRE,BITONE),_MODE)) \ - G(PCRE_PRINTINT,BITONE)(re, outfile, debug_lengths); \ - else \ - G(PCRE_PRINTINT,BITTWO)(re, outfile, debug_lengths) - -#define PCRE_STUDY(extra, re, options, error) \ - if (pcre_mode == G(G(PCRE,BITONE),_MODE)) \ - G(PCRE_STUDY,BITONE)(extra, re, options, error); \ - else \ - G(PCRE_STUDY,BITTWO)(extra, re, options, error) - -#endif /* Two out of three modes */ - -/* ----- End of cases where more than one mode is supported ----- */ - - -/* ----- Only 8-bit mode is supported ----- */ - -#elif defined SUPPORT_PCRE8 -#define CHAR_SIZE 1 -#define PCHARS PCHARS8 -#define PCHARSV PCHARSV8 -#define READ_CAPTURE_NAME READ_CAPTURE_NAME8 -#define SET_PCRE_CALLOUT SET_PCRE_CALLOUT8 -#define SET_PCRE_STACK_GUARD SET_PCRE_STACK_GUARD8 -#define STRLEN STRLEN8 -#define PCRE_ASSIGN_JIT_STACK PCRE_ASSIGN_JIT_STACK8 -#define PCRE_COMPILE PCRE_COMPILE8 -#define PCRE_CONFIG pcre_config -#define PCRE_COPY_NAMED_SUBSTRING PCRE_COPY_NAMED_SUBSTRING8 -#define PCRE_COPY_SUBSTRING PCRE_COPY_SUBSTRING8 -#define PCRE_DFA_EXEC PCRE_DFA_EXEC8 -#define PCRE_EXEC PCRE_EXEC8 -#define PCRE_FREE_STUDY PCRE_FREE_STUDY8 -#define PCRE_FREE_SUBSTRING PCRE_FREE_SUBSTRING8 -#define PCRE_FREE_SUBSTRING_LIST PCRE_FREE_SUBSTRING_LIST8 -#define PCRE_GET_NAMED_SUBSTRING PCRE_GET_NAMED_SUBSTRING8 -#define PCRE_GET_STRINGNUMBER PCRE_GET_STRINGNUMBER8 -#define PCRE_GET_SUBSTRING PCRE_GET_SUBSTRING8 -#define PCRE_GET_SUBSTRING_LIST PCRE_GET_SUBSTRING_LIST8 -#define PCRE_JIT_STACK_ALLOC PCRE_JIT_STACK_ALLOC8 -#define PCRE_JIT_STACK_FREE PCRE_JIT_STACK_FREE8 -#define PCRE_MAKETABLES pcre_maketables() -#define PCRE_PATTERN_TO_HOST_BYTE_ORDER PCRE_PATTERN_TO_HOST_BYTE_ORDER8 -#define PCRE_PRINTINT PCRE_PRINTINT8 -#define PCRE_STUDY PCRE_STUDY8 - -/* ----- Only 16-bit mode is supported ----- */ - -#elif defined SUPPORT_PCRE16 -#define CHAR_SIZE 2 -#define PCHARS PCHARS16 -#define PCHARSV PCHARSV16 -#define READ_CAPTURE_NAME READ_CAPTURE_NAME16 -#define SET_PCRE_CALLOUT SET_PCRE_CALLOUT16 -#define SET_PCRE_STACK_GUARD SET_PCRE_STACK_GUARD16 -#define STRLEN STRLEN16 -#define PCRE_ASSIGN_JIT_STACK PCRE_ASSIGN_JIT_STACK16 -#define PCRE_COMPILE PCRE_COMPILE16 -#define PCRE_CONFIG pcre16_config -#define PCRE_COPY_NAMED_SUBSTRING PCRE_COPY_NAMED_SUBSTRING16 -#define PCRE_COPY_SUBSTRING PCRE_COPY_SUBSTRING16 -#define PCRE_DFA_EXEC PCRE_DFA_EXEC16 -#define PCRE_EXEC PCRE_EXEC16 -#define PCRE_FREE_STUDY PCRE_FREE_STUDY16 -#define PCRE_FREE_SUBSTRING PCRE_FREE_SUBSTRING16 -#define PCRE_FREE_SUBSTRING_LIST PCRE_FREE_SUBSTRING_LIST16 -#define PCRE_GET_NAMED_SUBSTRING PCRE_GET_NAMED_SUBSTRING16 -#define PCRE_GET_STRINGNUMBER PCRE_GET_STRINGNUMBER16 -#define PCRE_GET_SUBSTRING PCRE_GET_SUBSTRING16 -#define PCRE_GET_SUBSTRING_LIST PCRE_GET_SUBSTRING_LIST16 -#define PCRE_JIT_STACK_ALLOC PCRE_JIT_STACK_ALLOC16 -#define PCRE_JIT_STACK_FREE PCRE_JIT_STACK_FREE16 -#define PCRE_MAKETABLES pcre16_maketables() -#define PCRE_PATTERN_TO_HOST_BYTE_ORDER PCRE_PATTERN_TO_HOST_BYTE_ORDER16 -#define PCRE_PRINTINT PCRE_PRINTINT16 -#define PCRE_STUDY PCRE_STUDY16 - -/* ----- Only 32-bit mode is supported ----- */ - -#elif defined SUPPORT_PCRE32 -#define CHAR_SIZE 4 -#define PCHARS PCHARS32 -#define PCHARSV PCHARSV32 -#define READ_CAPTURE_NAME READ_CAPTURE_NAME32 -#define SET_PCRE_CALLOUT SET_PCRE_CALLOUT32 -#define SET_PCRE_STACK_GUARD SET_PCRE_STACK_GUARD32 -#define STRLEN STRLEN32 -#define PCRE_ASSIGN_JIT_STACK PCRE_ASSIGN_JIT_STACK32 -#define PCRE_COMPILE PCRE_COMPILE32 -#define PCRE_CONFIG pcre32_config -#define PCRE_COPY_NAMED_SUBSTRING PCRE_COPY_NAMED_SUBSTRING32 -#define PCRE_COPY_SUBSTRING PCRE_COPY_SUBSTRING32 -#define PCRE_DFA_EXEC PCRE_DFA_EXEC32 -#define PCRE_EXEC PCRE_EXEC32 -#define PCRE_FREE_STUDY PCRE_FREE_STUDY32 -#define PCRE_FREE_SUBSTRING PCRE_FREE_SUBSTRING32 -#define PCRE_FREE_SUBSTRING_LIST PCRE_FREE_SUBSTRING_LIST32 -#define PCRE_GET_NAMED_SUBSTRING PCRE_GET_NAMED_SUBSTRING32 -#define PCRE_GET_STRINGNUMBER PCRE_GET_STRINGNUMBER32 -#define PCRE_GET_SUBSTRING PCRE_GET_SUBSTRING32 -#define PCRE_GET_SUBSTRING_LIST PCRE_GET_SUBSTRING_LIST32 -#define PCRE_JIT_STACK_ALLOC PCRE_JIT_STACK_ALLOC32 -#define PCRE_JIT_STACK_FREE PCRE_JIT_STACK_FREE32 -#define PCRE_MAKETABLES pcre32_maketables() -#define PCRE_PATTERN_TO_HOST_BYTE_ORDER PCRE_PATTERN_TO_HOST_BYTE_ORDER32 -#define PCRE_PRINTINT PCRE_PRINTINT32 -#define PCRE_STUDY PCRE_STUDY32 - -#endif - -/* ----- End of mode-specific function call macros ----- */ - - -/* Other parameters */ - -#ifndef CLOCKS_PER_SEC -#ifdef CLK_TCK -#define CLOCKS_PER_SEC CLK_TCK -#else -#define CLOCKS_PER_SEC 100 -#endif -#endif - -#if !defined NODFA -#define DFA_WS_DIMENSION 1000 -#endif - -/* This is the default loop count for timing. */ - -#define LOOPREPEAT 500000 - -/* Static variables */ - -static FILE *outfile; -static int log_store = 0; -static int callout_count; -static int callout_extra; -static int callout_fail_count; -static int callout_fail_id; -static int debug_lengths; -static int first_callout; -static int jit_was_used; -static int locale_set = 0; -static int show_malloc; -static int stack_guard_return; -static int use_utf; -static const unsigned char *last_callout_mark = NULL; - -/* The buffers grow automatically if very long input lines are encountered. */ - -static int buffer_size = 50000; -static pcre_uint8 *buffer = NULL; -static pcre_uint8 *pbuffer = NULL; - -/* Just as a safety check, make sure that COMPILE_PCRE[16|32] are *not* set. */ - -#ifdef COMPILE_PCRE16 -#error COMPILE_PCRE16 must not be set when compiling pcretest.c -#endif - -#ifdef COMPILE_PCRE32 -#error COMPILE_PCRE32 must not be set when compiling pcretest.c -#endif - -/* We need buffers for building 16/32-bit strings, and the tables of operator -lengths that are used for 16/32-bit compiling, in order to swap bytes in a -pattern for saving/reloading testing. Luckily, the data for these tables is -defined as a macro. However, we must ensure that LINK_SIZE and IMM2_SIZE (which -are used in the tables) are adjusted appropriately for the 16/32-bit world. -LINK_SIZE is also used later in this program. */ - -#ifdef SUPPORT_PCRE16 -#undef IMM2_SIZE -#define IMM2_SIZE 1 - -#if LINK_SIZE == 2 -#undef LINK_SIZE -#define LINK_SIZE 1 -#elif LINK_SIZE == 3 || LINK_SIZE == 4 -#undef LINK_SIZE -#define LINK_SIZE 2 -#else -#error LINK_SIZE must be either 2, 3, or 4 -#endif - -static int buffer16_size = 0; -static pcre_uint16 *buffer16 = NULL; -static const pcre_uint16 OP_lengths16[] = { OP_LENGTHS }; -#endif /* SUPPORT_PCRE16 */ - -#ifdef SUPPORT_PCRE32 -#undef IMM2_SIZE -#define IMM2_SIZE 1 -#undef LINK_SIZE -#define LINK_SIZE 1 - -static int buffer32_size = 0; -static pcre_uint32 *buffer32 = NULL; -static const pcre_uint32 OP_lengths32[] = { OP_LENGTHS }; -#endif /* SUPPORT_PCRE32 */ - -/* If we have 8-bit support, default to it; if there is also 16-or 32-bit -support, it can be changed by an option. If there is no 8-bit support, there -must be 16-or 32-bit support, so default it to 1. */ - -#if defined SUPPORT_PCRE8 -static int pcre_mode = PCRE8_MODE; -#elif defined SUPPORT_PCRE16 -static int pcre_mode = PCRE16_MODE; -#elif defined SUPPORT_PCRE32 -static int pcre_mode = PCRE32_MODE; -#endif - -/* JIT study options for -s+n and /S+n where '1' <= n <= '7'. */ - -static int jit_study_bits[] = - { - PCRE_STUDY_JIT_COMPILE, - PCRE_STUDY_JIT_PARTIAL_SOFT_COMPILE, - PCRE_STUDY_JIT_COMPILE + PCRE_STUDY_JIT_PARTIAL_SOFT_COMPILE, - PCRE_STUDY_JIT_PARTIAL_HARD_COMPILE, - PCRE_STUDY_JIT_COMPILE + PCRE_STUDY_JIT_PARTIAL_HARD_COMPILE, - PCRE_STUDY_JIT_PARTIAL_SOFT_COMPILE + PCRE_STUDY_JIT_PARTIAL_HARD_COMPILE, - PCRE_STUDY_JIT_COMPILE + PCRE_STUDY_JIT_PARTIAL_SOFT_COMPILE + - PCRE_STUDY_JIT_PARTIAL_HARD_COMPILE -}; - -#define PCRE_STUDY_ALLJIT (PCRE_STUDY_JIT_COMPILE | \ - PCRE_STUDY_JIT_PARTIAL_SOFT_COMPILE | PCRE_STUDY_JIT_PARTIAL_HARD_COMPILE) - -/* Textual explanations for runtime error codes */ - -static const char *errtexts[] = { - NULL, /* 0 is no error */ - NULL, /* NOMATCH is handled specially */ - "NULL argument passed", - "bad option value", - "magic number missing", - "unknown opcode - pattern overwritten?", - "no more memory", - NULL, /* never returned by pcre_exec() or pcre_dfa_exec() */ - "match limit exceeded", - "callout error code", - NULL, /* BADUTF8/16 is handled specially */ - NULL, /* BADUTF8/16 offset is handled specially */ - NULL, /* PARTIAL is handled specially */ - "not used - internal error", - "internal error - pattern overwritten?", - "bad count value", - "item unsupported for DFA matching", - "backreference condition or recursion test not supported for DFA matching", - "match limit not supported for DFA matching", - "workspace size exceeded in DFA matching", - "too much recursion for DFA matching", - "recursion limit exceeded", - "not used - internal error", - "invalid combination of newline options", - "bad offset value", - NULL, /* SHORTUTF8/16 is handled specially */ - "nested recursion at the same subject position", - "JIT stack limit reached", - "pattern compiled in wrong mode: 8-bit/16-bit error", - "pattern compiled with other endianness", - "invalid data in workspace for DFA restart", - "bad JIT option", - "bad length" -}; - - -/************************************************* -* Alternate character tables * -*************************************************/ - -/* By default, the "tables" pointer when calling PCRE is set to NULL, thereby -using the default tables of the library. However, the T option can be used to -select alternate sets of tables, for different kinds of testing. Note also that -the L (locale) option also adjusts the tables. */ - -/* This is the set of tables distributed as default with PCRE. It recognizes -only ASCII characters. */ - -static const pcre_uint8 tables0[] = { - -/* This table is a lower casing table. */ - - 0, 1, 2, 3, 4, 5, 6, 7, - 8, 9, 10, 11, 12, 13, 14, 15, - 16, 17, 18, 19, 20, 21, 22, 23, - 24, 25, 26, 27, 28, 29, 30, 31, - 32, 33, 34, 35, 36, 37, 38, 39, - 40, 41, 42, 43, 44, 45, 46, 47, - 48, 49, 50, 51, 52, 53, 54, 55, - 56, 57, 58, 59, 60, 61, 62, 63, - 64, 97, 98, 99,100,101,102,103, - 104,105,106,107,108,109,110,111, - 112,113,114,115,116,117,118,119, - 120,121,122, 91, 92, 93, 94, 95, - 96, 97, 98, 99,100,101,102,103, - 104,105,106,107,108,109,110,111, - 112,113,114,115,116,117,118,119, - 120,121,122,123,124,125,126,127, - 128,129,130,131,132,133,134,135, - 136,137,138,139,140,141,142,143, - 144,145,146,147,148,149,150,151, - 152,153,154,155,156,157,158,159, - 160,161,162,163,164,165,166,167, - 168,169,170,171,172,173,174,175, - 176,177,178,179,180,181,182,183, - 184,185,186,187,188,189,190,191, - 192,193,194,195,196,197,198,199, - 200,201,202,203,204,205,206,207, - 208,209,210,211,212,213,214,215, - 216,217,218,219,220,221,222,223, - 224,225,226,227,228,229,230,231, - 232,233,234,235,236,237,238,239, - 240,241,242,243,244,245,246,247, - 248,249,250,251,252,253,254,255, - -/* This table is a case flipping table. */ - - 0, 1, 2, 3, 4, 5, 6, 7, - 8, 9, 10, 11, 12, 13, 14, 15, - 16, 17, 18, 19, 20, 21, 22, 23, - 24, 25, 26, 27, 28, 29, 30, 31, - 32, 33, 34, 35, 36, 37, 38, 39, - 40, 41, 42, 43, 44, 45, 46, 47, - 48, 49, 50, 51, 52, 53, 54, 55, - 56, 57, 58, 59, 60, 61, 62, 63, - 64, 97, 98, 99,100,101,102,103, - 104,105,106,107,108,109,110,111, - 112,113,114,115,116,117,118,119, - 120,121,122, 91, 92, 93, 94, 95, - 96, 65, 66, 67, 68, 69, 70, 71, - 72, 73, 74, 75, 76, 77, 78, 79, - 80, 81, 82, 83, 84, 85, 86, 87, - 88, 89, 90,123,124,125,126,127, - 128,129,130,131,132,133,134,135, - 136,137,138,139,140,141,142,143, - 144,145,146,147,148,149,150,151, - 152,153,154,155,156,157,158,159, - 160,161,162,163,164,165,166,167, - 168,169,170,171,172,173,174,175, - 176,177,178,179,180,181,182,183, - 184,185,186,187,188,189,190,191, - 192,193,194,195,196,197,198,199, - 200,201,202,203,204,205,206,207, - 208,209,210,211,212,213,214,215, - 216,217,218,219,220,221,222,223, - 224,225,226,227,228,229,230,231, - 232,233,234,235,236,237,238,239, - 240,241,242,243,244,245,246,247, - 248,249,250,251,252,253,254,255, - -/* This table contains bit maps for various character classes. Each map is 32 -bytes long and the bits run from the least significant end of each byte. The -classes that have their own maps are: space, xdigit, digit, upper, lower, word, -graph, print, punct, and cntrl. Other classes are built from combinations. */ - - 0x00,0x3e,0x00,0x00,0x01,0x00,0x00,0x00, - 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, - 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, - 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, - - 0x00,0x00,0x00,0x00,0x00,0x00,0xff,0x03, - 0x7e,0x00,0x00,0x00,0x7e,0x00,0x00,0x00, - 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, - 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, - - 0x00,0x00,0x00,0x00,0x00,0x00,0xff,0x03, - 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, - 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, - 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, - - 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, - 0xfe,0xff,0xff,0x07,0x00,0x00,0x00,0x00, - 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, - 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, - - 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, - 0x00,0x00,0x00,0x00,0xfe,0xff,0xff,0x07, - 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, - 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, - - 0x00,0x00,0x00,0x00,0x00,0x00,0xff,0x03, - 0xfe,0xff,0xff,0x87,0xfe,0xff,0xff,0x07, - 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, - 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, - - 0x00,0x00,0x00,0x00,0xfe,0xff,0xff,0xff, - 0xff,0xff,0xff,0xff,0xff,0xff,0xff,0x7f, - 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, - 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, - - 0x00,0x00,0x00,0x00,0xff,0xff,0xff,0xff, - 0xff,0xff,0xff,0xff,0xff,0xff,0xff,0x7f, - 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, - 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, - - 0x00,0x00,0x00,0x00,0xfe,0xff,0x00,0xfc, - 0x01,0x00,0x00,0xf8,0x01,0x00,0x00,0x78, - 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, - 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, - - 0xff,0xff,0xff,0xff,0x00,0x00,0x00,0x00, - 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x80, - 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, - 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, - -/* This table identifies various classes of character by individual bits: - 0x01 white space character - 0x02 letter - 0x04 decimal digit - 0x08 hexadecimal digit - 0x10 alphanumeric or '_' - 0x80 regular expression metacharacter or binary zero -*/ - - 0x80,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /* 0- 7 */ - 0x00,0x01,0x01,0x01,0x01,0x01,0x00,0x00, /* 8- 15 */ - 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /* 16- 23 */ - 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /* 24- 31 */ - 0x01,0x00,0x00,0x00,0x80,0x00,0x00,0x00, /* - ' */ - 0x80,0x80,0x80,0x80,0x00,0x00,0x80,0x00, /* ( - / */ - 0x1c,0x1c,0x1c,0x1c,0x1c,0x1c,0x1c,0x1c, /* 0 - 7 */ - 0x1c,0x1c,0x00,0x00,0x00,0x00,0x00,0x80, /* 8 - ? */ - 0x00,0x1a,0x1a,0x1a,0x1a,0x1a,0x1a,0x12, /* @ - G */ - 0x12,0x12,0x12,0x12,0x12,0x12,0x12,0x12, /* H - O */ - 0x12,0x12,0x12,0x12,0x12,0x12,0x12,0x12, /* P - W */ - 0x12,0x12,0x12,0x80,0x80,0x00,0x80,0x10, /* X - _ */ - 0x00,0x1a,0x1a,0x1a,0x1a,0x1a,0x1a,0x12, /* ` - g */ - 0x12,0x12,0x12,0x12,0x12,0x12,0x12,0x12, /* h - o */ - 0x12,0x12,0x12,0x12,0x12,0x12,0x12,0x12, /* p - w */ - 0x12,0x12,0x12,0x80,0x80,0x00,0x00,0x00, /* x -127 */ - 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /* 128-135 */ - 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /* 136-143 */ - 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /* 144-151 */ - 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /* 152-159 */ - 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /* 160-167 */ - 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /* 168-175 */ - 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /* 176-183 */ - 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /* 184-191 */ - 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /* 192-199 */ - 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /* 200-207 */ - 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /* 208-215 */ - 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /* 216-223 */ - 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /* 224-231 */ - 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /* 232-239 */ - 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /* 240-247 */ - 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00};/* 248-255 */ - -/* This is a set of tables that came originally from a Windows user. It seems -to be at least an approximation of ISO 8859. In particular, there are -characters greater than 128 that are marked as spaces, letters, etc. */ - -static const pcre_uint8 tables1[] = { -0,1,2,3,4,5,6,7, -8,9,10,11,12,13,14,15, -16,17,18,19,20,21,22,23, -24,25,26,27,28,29,30,31, -32,33,34,35,36,37,38,39, -40,41,42,43,44,45,46,47, -48,49,50,51,52,53,54,55, -56,57,58,59,60,61,62,63, -64,97,98,99,100,101,102,103, -104,105,106,107,108,109,110,111, -112,113,114,115,116,117,118,119, -120,121,122,91,92,93,94,95, -96,97,98,99,100,101,102,103, -104,105,106,107,108,109,110,111, -112,113,114,115,116,117,118,119, -120,121,122,123,124,125,126,127, -128,129,130,131,132,133,134,135, -136,137,138,139,140,141,142,143, -144,145,146,147,148,149,150,151, -152,153,154,155,156,157,158,159, -160,161,162,163,164,165,166,167, -168,169,170,171,172,173,174,175, -176,177,178,179,180,181,182,183, -184,185,186,187,188,189,190,191, -224,225,226,227,228,229,230,231, -232,233,234,235,236,237,238,239, -240,241,242,243,244,245,246,215, -248,249,250,251,252,253,254,223, -224,225,226,227,228,229,230,231, -232,233,234,235,236,237,238,239, -240,241,242,243,244,245,246,247, -248,249,250,251,252,253,254,255, -0,1,2,3,4,5,6,7, -8,9,10,11,12,13,14,15, -16,17,18,19,20,21,22,23, -24,25,26,27,28,29,30,31, -32,33,34,35,36,37,38,39, -40,41,42,43,44,45,46,47, -48,49,50,51,52,53,54,55, -56,57,58,59,60,61,62,63, -64,97,98,99,100,101,102,103, -104,105,106,107,108,109,110,111, -112,113,114,115,116,117,118,119, -120,121,122,91,92,93,94,95, -96,65,66,67,68,69,70,71, -72,73,74,75,76,77,78,79, -80,81,82,83,84,85,86,87, -88,89,90,123,124,125,126,127, -128,129,130,131,132,133,134,135, -136,137,138,139,140,141,142,143, -144,145,146,147,148,149,150,151, -152,153,154,155,156,157,158,159, -160,161,162,163,164,165,166,167, -168,169,170,171,172,173,174,175, -176,177,178,179,180,181,182,183, -184,185,186,187,188,189,190,191, -224,225,226,227,228,229,230,231, -232,233,234,235,236,237,238,239, -240,241,242,243,244,245,246,215, -248,249,250,251,252,253,254,223, -192,193,194,195,196,197,198,199, -200,201,202,203,204,205,206,207, -208,209,210,211,212,213,214,247, -216,217,218,219,220,221,222,255, -0,62,0,0,1,0,0,0, -0,0,0,0,0,0,0,0, -32,0,0,0,1,0,0,0, -0,0,0,0,0,0,0,0, -0,0,0,0,0,0,255,3, -126,0,0,0,126,0,0,0, -0,0,0,0,0,0,0,0, -0,0,0,0,0,0,0,0, -0,0,0,0,0,0,255,3, -0,0,0,0,0,0,0,0, -0,0,0,0,0,0,12,2, -0,0,0,0,0,0,0,0, -0,0,0,0,0,0,0,0, -254,255,255,7,0,0,0,0, -0,0,0,0,0,0,0,0, -255,255,127,127,0,0,0,0, -0,0,0,0,0,0,0,0, -0,0,0,0,254,255,255,7, -0,0,0,0,0,4,32,4, -0,0,0,128,255,255,127,255, -0,0,0,0,0,0,255,3, -254,255,255,135,254,255,255,7, -0,0,0,0,0,4,44,6, -255,255,127,255,255,255,127,255, -0,0,0,0,254,255,255,255, -255,255,255,255,255,255,255,127, -0,0,0,0,254,255,255,255, -255,255,255,255,255,255,255,255, -0,2,0,0,255,255,255,255, -255,255,255,255,255,255,255,127, -0,0,0,0,255,255,255,255, -255,255,255,255,255,255,255,255, -0,0,0,0,254,255,0,252, -1,0,0,248,1,0,0,120, -0,0,0,0,254,255,255,255, -0,0,128,0,0,0,128,0, -255,255,255,255,0,0,0,0, -0,0,0,0,0,0,0,128, -255,255,255,255,0,0,0,0, -0,0,0,0,0,0,0,0, -128,0,0,0,0,0,0,0, -0,1,1,0,1,1,0,0, -0,0,0,0,0,0,0,0, -0,0,0,0,0,0,0,0, -1,0,0,0,128,0,0,0, -128,128,128,128,0,0,128,0, -28,28,28,28,28,28,28,28, -28,28,0,0,0,0,0,128, -0,26,26,26,26,26,26,18, -18,18,18,18,18,18,18,18, -18,18,18,18,18,18,18,18, -18,18,18,128,128,0,128,16, -0,26,26,26,26,26,26,18, -18,18,18,18,18,18,18,18, -18,18,18,18,18,18,18,18, -18,18,18,128,128,0,0,0, -0,0,0,0,0,1,0,0, -0,0,0,0,0,0,0,0, -0,0,0,0,0,0,0,0, -0,0,0,0,0,0,0,0, -1,0,0,0,0,0,0,0, -0,0,18,0,0,0,0,0, -0,0,20,20,0,18,0,0, -0,20,18,0,0,0,0,0, -18,18,18,18,18,18,18,18, -18,18,18,18,18,18,18,18, -18,18,18,18,18,18,18,0, -18,18,18,18,18,18,18,18, -18,18,18,18,18,18,18,18, -18,18,18,18,18,18,18,18, -18,18,18,18,18,18,18,0, -18,18,18,18,18,18,18,18 -}; - - - - -#ifndef HAVE_STRERROR -/************************************************* -* Provide strerror() for non-ANSI libraries * -*************************************************/ - -/* Some old-fashioned systems still around (e.g. SunOS4) don't have strerror() -in their libraries, but can provide the same facility by this simple -alternative function. */ - -extern int sys_nerr; -extern char *sys_errlist[]; - -char * -strerror(int n) -{ -if (n < 0 || n >= sys_nerr) return "unknown error number"; -return sys_errlist[n]; -} -#endif /* HAVE_STRERROR */ - - - -/************************************************* -* Print newline configuration * -*************************************************/ - -/* -Arguments: - rc the return code from PCRE_CONFIG_NEWLINE - isc TRUE if called from "-C newline" -Returns: nothing -*/ - -static void -print_newline_config(int rc, BOOL isc) -{ -const char *s = NULL; -if (!isc) printf(" Newline sequence is "); -switch(rc) - { - case CHAR_CR: s = "CR"; break; - case CHAR_LF: s = "LF"; break; - case (CHAR_CR<<8 | CHAR_LF): s = "CRLF"; break; - case -1: s = "ANY"; break; - case -2: s = "ANYCRLF"; break; - - default: - printf("a non-standard value: 0x%04x\n", rc); - return; - } - -printf("%s\n", s); -} - - - -/************************************************* -* JIT memory callback * -*************************************************/ - -static pcre_jit_stack* jit_callback(void *arg) -{ -jit_was_used = TRUE; -return (pcre_jit_stack *)arg; -} - - -#if !defined NOUTF || defined SUPPORT_PCRE16 || defined SUPPORT_PCRE32 -/************************************************* -* Convert UTF-8 string to value * -*************************************************/ - -/* This function takes one or more bytes that represents a UTF-8 character, -and returns the value of the character. - -Argument: - utf8bytes a pointer to the byte vector - vptr a pointer to an int to receive the value - -Returns: > 0 => the number of bytes consumed - -6 to 0 => malformed UTF-8 character at offset = (-return) -*/ - -static int -utf82ord(pcre_uint8 *utf8bytes, pcre_uint32 *vptr) -{ -pcre_uint32 c = *utf8bytes++; -pcre_uint32 d = c; -int i, j, s; - -for (i = -1; i < 6; i++) /* i is number of additional bytes */ - { - if ((d & 0x80) == 0) break; - d <<= 1; - } - -if (i == -1) { *vptr = c; return 1; } /* ascii character */ -if (i == 0 || i == 6) return 0; /* invalid UTF-8 */ - -/* i now has a value in the range 1-5 */ - -s = 6*i; -d = (c & utf8_table3[i]) << s; - -for (j = 0; j < i; j++) - { - c = *utf8bytes++; - if ((c & 0xc0) != 0x80) return -(j+1); - s -= 6; - d |= (c & 0x3f) << s; - } - -/* Check that encoding was the correct unique one */ - -for (j = 0; j < utf8_table1_size; j++) - if (d <= (pcre_uint32)utf8_table1[j]) break; -if (j != i) return -(i+1); - -/* Valid value */ - -*vptr = d; -return i+1; -} -#endif /* NOUTF || SUPPORT_PCRE16 */ - - - -#if defined SUPPORT_PCRE8 && !defined NOUTF -/************************************************* -* Convert character value to UTF-8 * -*************************************************/ - -/* This function takes an integer value in the range 0 - 0x7fffffff -and encodes it as a UTF-8 character in 0 to 6 bytes. - -Arguments: - cvalue the character value - utf8bytes pointer to buffer for result - at least 6 bytes long - -Returns: number of characters placed in the buffer -*/ - -static int -ord2utf8(pcre_uint32 cvalue, pcre_uint8 *utf8bytes) -{ -register int i, j; -if (cvalue > 0x7fffffffu) - return -1; -for (i = 0; i < utf8_table1_size; i++) - if (cvalue <= (pcre_uint32)utf8_table1[i]) break; -utf8bytes += i; -for (j = i; j > 0; j--) - { - *utf8bytes-- = 0x80 | (cvalue & 0x3f); - cvalue >>= 6; - } -*utf8bytes = utf8_table2[i] | cvalue; -return i + 1; -} -#endif - - -#ifdef SUPPORT_PCRE16 -/************************************************* -* Convert a string to 16-bit * -*************************************************/ - -/* In non-UTF mode, the space needed for a 16-bit string is exactly double the -8-bit size. For a UTF-8 string, the size needed for UTF-16 is no more than -double, because up to 0xffff uses no more than 3 bytes in UTF-8 but possibly 4 -in UTF-16. Higher values use 4 bytes in UTF-8 and up to 4 bytes in UTF-16. The -result is always left in buffer16. - -Note that this function does not object to surrogate values. This is -deliberate; it makes it possible to construct UTF-16 strings that are invalid, -for the purpose of testing that they are correctly faulted. - -Patterns to be converted are either plain ASCII or UTF-8; data lines are always -in UTF-8 so that values greater than 255 can be handled. - -Arguments: - data TRUE if converting a data line; FALSE for a regex - p points to a byte string - utf true if UTF-8 (to be converted to UTF-16) - len number of bytes in the string (excluding trailing zero) - -Returns: number of 16-bit data items used (excluding trailing zero) - OR -1 if a UTF-8 string is malformed - OR -2 if a value > 0x10ffff is encountered - OR -3 if a value > 0xffff is encountered when not in UTF mode -*/ - -static int -to16(int data, pcre_uint8 *p, int utf, int len) -{ -pcre_uint16 *pp; - -if (buffer16_size < 2*len + 2) - { - if (buffer16 != NULL) free(buffer16); - buffer16_size = 2*len + 2; - buffer16 = (pcre_uint16 *)malloc(buffer16_size); - if (buffer16 == NULL) - { - fprintf(stderr, "pcretest: malloc(%d) failed for buffer16\n", buffer16_size); - exit(1); - } - } - -pp = buffer16; - -if (!utf && !data) - { - while (len-- > 0) *pp++ = *p++; - } - -else - { - pcre_uint32 c = 0; - while (len > 0) - { - int chlen = utf82ord(p, &c); - if (chlen <= 0) return -1; - if (c > 0x10ffff) return -2; - p += chlen; - len -= chlen; - if (c < 0x10000) *pp++ = c; else - { - if (!utf) return -3; - c -= 0x10000; - *pp++ = 0xD800 | (c >> 10); - *pp++ = 0xDC00 | (c & 0x3ff); - } - } - } - -*pp = 0; -return pp - buffer16; -} -#endif - -#ifdef SUPPORT_PCRE32 -/************************************************* -* Convert a string to 32-bit * -*************************************************/ - -/* In non-UTF mode, the space needed for a 32-bit string is exactly four times the -8-bit size. For a UTF-8 string, the size needed for UTF-32 is no more than four -times, because up to 0xffff uses no more than 3 bytes in UTF-8 but possibly 4 -in UTF-32. Higher values use 4 bytes in UTF-8 and up to 4 bytes in UTF-32. The -result is always left in buffer32. - -Note that this function does not object to surrogate values. This is -deliberate; it makes it possible to construct UTF-32 strings that are invalid, -for the purpose of testing that they are correctly faulted. - -Patterns to be converted are either plain ASCII or UTF-8; data lines are always -in UTF-8 so that values greater than 255 can be handled. - -Arguments: - data TRUE if converting a data line; FALSE for a regex - p points to a byte string - utf true if UTF-8 (to be converted to UTF-32) - len number of bytes in the string (excluding trailing zero) - -Returns: number of 32-bit data items used (excluding trailing zero) - OR -1 if a UTF-8 string is malformed - OR -2 if a value > 0x10ffff is encountered - OR -3 if an ill-formed value is encountered (i.e. a surrogate) -*/ - -static int -to32(int data, pcre_uint8 *p, int utf, int len) -{ -pcre_uint32 *pp; - -if (buffer32_size < 4*len + 4) - { - if (buffer32 != NULL) free(buffer32); - buffer32_size = 4*len + 4; - buffer32 = (pcre_uint32 *)malloc(buffer32_size); - if (buffer32 == NULL) - { - fprintf(stderr, "pcretest: malloc(%d) failed for buffer32\n", buffer32_size); - exit(1); - } - } - -pp = buffer32; - -if (!utf && !data) - { - while (len-- > 0) *pp++ = *p++; - } - -else - { - pcre_uint32 c = 0; - while (len > 0) - { - int chlen = utf82ord(p, &c); - if (chlen <= 0) return -1; - if (utf) - { - if (c > 0x10ffff) return -2; - if (!data && (c & 0xfffff800u) == 0xd800u) return -3; - } - - p += chlen; - len -= chlen; - *pp++ = c; - } - } - -*pp = 0; -return pp - buffer32; -} - -/* Check that a 32-bit character string is valid UTF-32. - -Arguments: - string points to the string - length length of string, or -1 if the string is zero-terminated - -Returns: TRUE if the string is a valid UTF-32 string - FALSE otherwise -*/ - -#ifdef NEVER /* Not used */ -#ifdef SUPPORT_UTF -static BOOL -valid_utf32(pcre_uint32 *string, int length) -{ -register pcre_uint32 *p; -register pcre_uint32 c; - -for (p = string; length-- > 0; p++) - { - c = *p; - if (c > 0x10ffffu) return FALSE; /* Too big */ - if ((c & 0xfffff800u) == 0xd800u) return FALSE; /* Surrogate */ - } - -return TRUE; -} -#endif /* SUPPORT_UTF */ -#endif /* NEVER */ -#endif /* SUPPORT_PCRE32 */ - - -/************************************************* -* Read or extend an input line * -*************************************************/ - -/* Input lines are read into buffer, but both patterns and data lines can be -continued over multiple input lines. In addition, if the buffer fills up, we -want to automatically expand it so as to be able to handle extremely large -lines that are needed for certain stress tests. When the input buffer is -expanded, the other two buffers must also be expanded likewise, and the -contents of pbuffer, which are a copy of the input for callouts, must be -preserved (for when expansion happens for a data line). This is not the most -optimal way of handling this, but hey, this is just a test program! - -Arguments: - f the file to read - start where in buffer to start (this *must* be within buffer) - prompt for stdin or readline() - -Returns: pointer to the start of new data - could be a copy of start, or could be moved - NULL if no data read and EOF reached -*/ - -static pcre_uint8 * -extend_inputline(FILE *f, pcre_uint8 *start, const char *prompt) -{ -pcre_uint8 *here = start; - -for (;;) - { - size_t rlen = (size_t)(buffer_size - (here - buffer)); - - if (rlen > 1000) - { - int dlen; - - /* If libreadline or libedit support is required, use readline() to read a - line if the input is a terminal. Note that readline() removes the trailing - newline, so we must put it back again, to be compatible with fgets(). */ - -#if defined(SUPPORT_LIBREADLINE) || defined(SUPPORT_LIBEDIT) - if (isatty(fileno(f))) - { - size_t len; - char *s = readline(prompt); - if (s == NULL) return (here == start)? NULL : start; - len = strlen(s); - if (len > 0) add_history(s); - if (len > rlen - 1) len = rlen - 1; - memcpy(here, s, len); - here[len] = '\n'; - here[len+1] = 0; - free(s); - } - else -#endif - - /* Read the next line by normal means, prompting if the file is stdin. */ - - { - if (f == stdin) printf("%s", prompt); - if (fgets((char *)here, rlen, f) == NULL) - return (here == start)? NULL : start; - } - - dlen = (int)strlen((char *)here); - if (dlen > 0 && here[dlen - 1] == '\n') return start; - here += dlen; - } - - else - { - int new_buffer_size = 2*buffer_size; - pcre_uint8 *new_buffer = (pcre_uint8 *)malloc(new_buffer_size); - pcre_uint8 *new_pbuffer = (pcre_uint8 *)malloc(new_buffer_size); - - if (new_buffer == NULL || new_pbuffer == NULL) - { - fprintf(stderr, "pcretest: malloc(%d) failed\n", new_buffer_size); - exit(1); - } - - memcpy(new_buffer, buffer, buffer_size); - memcpy(new_pbuffer, pbuffer, buffer_size); - - buffer_size = new_buffer_size; - - start = new_buffer + (start - buffer); - here = new_buffer + (here - buffer); - - free(buffer); - free(pbuffer); - - buffer = new_buffer; - pbuffer = new_pbuffer; - } - } - -/* Control never gets here */ -} - - - -/************************************************* -* Read number from string * -*************************************************/ - -/* We don't use strtoul() because SunOS4 doesn't have it. Rather than mess -around with conditional compilation, just do the job by hand. It is only used -for unpicking arguments, so just keep it simple. - -Arguments: - str string to be converted - endptr where to put the end pointer - -Returns: the unsigned long -*/ - -static int -get_value(pcre_uint8 *str, pcre_uint8 **endptr) -{ -int result = 0; -while(*str != 0 && isspace(*str)) str++; -while (isdigit(*str)) result = result * 10 + (int)(*str++ - '0'); -*endptr = str; -return(result); -} - - - -/************************************************* -* Print one character * -*************************************************/ - -/* Print a single character either literally, or as a hex escape. */ - -static int pchar(pcre_uint32 c, FILE *f) -{ -int n = 0; -if (PRINTOK(c)) - { - if (f != NULL) fprintf(f, "%c", c); - return 1; - } - -if (c < 0x100) - { - if (use_utf) - { - if (f != NULL) fprintf(f, "\\x{%02x}", c); - return 6; - } - else - { - if (f != NULL) fprintf(f, "\\x%02x", c); - return 4; - } - } - -if (f != NULL) n = fprintf(f, "\\x{%02x}", c); -return n >= 0 ? n : 0; -} - - - -#ifdef SUPPORT_PCRE8 -/************************************************* -* Print 8-bit character string * -*************************************************/ - -/* Must handle UTF-8 strings in utf8 mode. Yields number of characters printed. -If handed a NULL file, just counts chars without printing. */ - -static int pchars(pcre_uint8 *p, int length, FILE *f) -{ -pcre_uint32 c = 0; -int yield = 0; - -if (length < 0) - length = strlen((char *)p); - -while (length-- > 0) - { -#if !defined NOUTF - if (use_utf) - { - int rc = utf82ord(p, &c); - if (rc > 0 && rc <= length + 1) /* Mustn't run over the end */ - { - length -= rc - 1; - p += rc; - yield += pchar(c, f); - continue; - } - } -#endif - c = *p++; - yield += pchar(c, f); - } - -return yield; -} -#endif - - - -#ifdef SUPPORT_PCRE16 -/************************************************* -* Find length of 0-terminated 16-bit string * -*************************************************/ - -static int strlen16(PCRE_SPTR16 p) -{ -PCRE_SPTR16 pp = p; -while (*pp != 0) pp++; -return (int)(pp - p); -} -#endif /* SUPPORT_PCRE16 */ - - - -#ifdef SUPPORT_PCRE32 -/************************************************* -* Find length of 0-terminated 32-bit string * -*************************************************/ - -static int strlen32(PCRE_SPTR32 p) -{ -PCRE_SPTR32 pp = p; -while (*pp != 0) pp++; -return (int)(pp - p); -} -#endif /* SUPPORT_PCRE32 */ - - - -#ifdef SUPPORT_PCRE16 -/************************************************* -* Print 16-bit character string * -*************************************************/ - -/* Must handle UTF-16 strings in utf mode. Yields number of characters printed. -If handed a NULL file, just counts chars without printing. */ - -static int pchars16(PCRE_SPTR16 p, int length, FILE *f) -{ -int yield = 0; - -if (length < 0) - length = strlen16(p); - -while (length-- > 0) - { - pcre_uint32 c = *p++ & 0xffff; -#if !defined NOUTF - if (use_utf && c >= 0xD800 && c < 0xDC00 && length > 0) - { - int d = *p & 0xffff; - if (d >= 0xDC00 && d <= 0xDFFF) - { - c = ((c & 0x3ff) << 10) + (d & 0x3ff) + 0x10000; - length--; - p++; - } - } -#endif - yield += pchar(c, f); - } - -return yield; -} -#endif /* SUPPORT_PCRE16 */ - - - -#ifdef SUPPORT_PCRE32 -/************************************************* -* Print 32-bit character string * -*************************************************/ - -/* Must handle UTF-32 strings in utf mode. Yields number of characters printed. -If handed a NULL file, just counts chars without printing. */ - -static int pchars32(PCRE_SPTR32 p, int length, BOOL utf, FILE *f) -{ -int yield = 0; - -(void)(utf); /* Avoid compiler warning */ - -if (length < 0) - length = strlen32(p); - -while (length-- > 0) - { - pcre_uint32 c = *p++; - yield += pchar(c, f); - } - -return yield; -} -#endif /* SUPPORT_PCRE32 */ - - - -#ifdef SUPPORT_PCRE8 -/************************************************* -* Read a capture name (8-bit) and check it * -*************************************************/ - -static pcre_uint8 * -read_capture_name8(pcre_uint8 *p, pcre_uint8 **pp, pcre *re) -{ -pcre_uint8 *npp = *pp; -while (isalnum(*p)) *npp++ = *p++; -*npp++ = 0; -*npp = 0; -if (pcre_get_stringnumber(re, (char *)(*pp)) < 0) - { - fprintf(outfile, "no parentheses with name \""); - PCHARSV(*pp, 0, -1, outfile); - fprintf(outfile, "\"\n"); - } - -*pp = npp; -return p; -} -#endif /* SUPPORT_PCRE8 */ - - - -#ifdef SUPPORT_PCRE16 -/************************************************* -* Read a capture name (16-bit) and check it * -*************************************************/ - -/* Note that the text being read is 8-bit. */ - -static pcre_uint8 * -read_capture_name16(pcre_uint8 *p, pcre_uint16 **pp, pcre *re) -{ -pcre_uint16 *npp = *pp; -while (isalnum(*p)) *npp++ = *p++; -*npp++ = 0; -*npp = 0; -if (pcre16_get_stringnumber((pcre16 *)re, (PCRE_SPTR16)(*pp)) < 0) - { - fprintf(outfile, "no parentheses with name \""); - PCHARSV(*pp, 0, -1, outfile); - fprintf(outfile, "\"\n"); - } -*pp = npp; -return p; -} -#endif /* SUPPORT_PCRE16 */ - - - -#ifdef SUPPORT_PCRE32 -/************************************************* -* Read a capture name (32-bit) and check it * -*************************************************/ - -/* Note that the text being read is 8-bit. */ - -static pcre_uint8 * -read_capture_name32(pcre_uint8 *p, pcre_uint32 **pp, pcre *re) -{ -pcre_uint32 *npp = *pp; -while (isalnum(*p)) *npp++ = *p++; -*npp++ = 0; -*npp = 0; -if (pcre32_get_stringnumber((pcre32 *)re, (PCRE_SPTR32)(*pp)) < 0) - { - fprintf(outfile, "no parentheses with name \""); - PCHARSV(*pp, 0, -1, outfile); - fprintf(outfile, "\"\n"); - } -*pp = npp; -return p; -} -#endif /* SUPPORT_PCRE32 */ - - - -/************************************************* -* Stack guard function * -*************************************************/ - -/* Called from PCRE when set in pcre_stack_guard. We give an error (non-zero) -return when a count overflows. */ - -static int stack_guard(void) -{ -return stack_guard_return; -} - -/************************************************* -* Callout function * -*************************************************/ - -/* Called from PCRE as a result of the (?C) item. We print out where we are in -the match. Yield zero unless more callouts than the fail count, or the callout -data is not zero. */ - -static int callout(pcre_callout_block *cb) -{ -FILE *f = (first_callout | callout_extra)? outfile : NULL; -int i, pre_start, post_start, subject_length; - -if (callout_extra) - { - fprintf(f, "Callout %d: last capture = %d\n", - cb->callout_number, cb->capture_last); - - if (cb->offset_vector != NULL) - { - for (i = 0; i < cb->capture_top * 2; i += 2) - { - if (cb->offset_vector[i] < 0) - fprintf(f, "%2d: <unset>\n", i/2); - else - { - fprintf(f, "%2d: ", i/2); - PCHARSV(cb->subject, cb->offset_vector[i], - cb->offset_vector[i+1] - cb->offset_vector[i], f); - fprintf(f, "\n"); - } - } - } - } - -/* Re-print the subject in canonical form, the first time or if giving full -datails. On subsequent calls in the same match, we use pchars just to find the -printed lengths of the substrings. */ - -if (f != NULL) fprintf(f, "--->"); - -PCHARS(pre_start, cb->subject, 0, cb->start_match, f); -PCHARS(post_start, cb->subject, cb->start_match, - cb->current_position - cb->start_match, f); - -PCHARS(subject_length, cb->subject, 0, cb->subject_length, NULL); - -PCHARSV(cb->subject, cb->current_position, - cb->subject_length - cb->current_position, f); - -if (f != NULL) fprintf(f, "\n"); - -/* Always print appropriate indicators, with callout number if not already -shown. For automatic callouts, show the pattern offset. */ - -if (cb->callout_number == 255) - { - fprintf(outfile, "%+3d ", cb->pattern_position); - if (cb->pattern_position > 99) fprintf(outfile, "\n "); - } -else - { - if (callout_extra) fprintf(outfile, " "); - else fprintf(outfile, "%3d ", cb->callout_number); - } - -for (i = 0; i < pre_start; i++) fprintf(outfile, " "); -fprintf(outfile, "^"); - -if (post_start > 0) - { - for (i = 0; i < post_start - 1; i++) fprintf(outfile, " "); - fprintf(outfile, "^"); - } - -for (i = 0; i < subject_length - pre_start - post_start + 4; i++) - fprintf(outfile, " "); - -fprintf(outfile, "%.*s", (cb->next_item_length == 0)? 1 : cb->next_item_length, - pbuffer + cb->pattern_position); - -fprintf(outfile, "\n"); -first_callout = 0; - -if (cb->mark != last_callout_mark) - { - if (cb->mark == NULL) - fprintf(outfile, "Latest Mark: <unset>\n"); - else - { - fprintf(outfile, "Latest Mark: "); - PCHARSV(cb->mark, 0, -1, outfile); - putc('\n', outfile); - } - last_callout_mark = cb->mark; - } - -if (cb->callout_data != NULL) - { - int callout_data = *((int *)(cb->callout_data)); - if (callout_data != 0) - { - fprintf(outfile, "Callout data = %d\n", callout_data); - return callout_data; - } - } - -return (cb->callout_number != callout_fail_id)? 0 : - (++callout_count >= callout_fail_count)? 1 : 0; -} - - -/************************************************* -* Local malloc functions * -*************************************************/ - -/* Alternative malloc function, to test functionality and save the size of a -compiled re, which is the first store request that pcre_compile() makes. The -show_malloc variable is set only during matching. */ - -static void *new_malloc(size_t size) -{ -void *block = malloc(size); -if (show_malloc) - fprintf(outfile, "malloc %3d %p\n", (int)size, block); -return block; -} - -static void new_free(void *block) -{ -if (show_malloc) - fprintf(outfile, "free %p\n", block); -free(block); -} - -/* For recursion malloc/free, to test stacking calls */ - -static void *stack_malloc(size_t size) -{ -void *block = malloc(size); -if (show_malloc) - fprintf(outfile, "stack_malloc %3d %p\n", (int)size, block); -return block; -} - -static void stack_free(void *block) -{ -if (show_malloc) - fprintf(outfile, "stack_free %p\n", block); -free(block); -} - - -/************************************************* -* Call pcre_fullinfo() * -*************************************************/ - -/* Get one piece of information from the pcre_fullinfo() function. When only -one of 8-, 16- or 32-bit is supported, pcre_mode should always have the correct -value, but the code is defensive. - -Arguments: - re compiled regex - study study data - option PCRE_INFO_xxx option - ptr where to put the data - -Returns: 0 when OK, < 0 on error -*/ - -static int -new_info(pcre *re, pcre_extra *study, int option, void *ptr) -{ -int rc; - -if (pcre_mode == PCRE32_MODE) -#ifdef SUPPORT_PCRE32 - rc = pcre32_fullinfo((pcre32 *)re, (pcre32_extra *)study, option, ptr); -#else - rc = PCRE_ERROR_BADMODE; -#endif -else if (pcre_mode == PCRE16_MODE) -#ifdef SUPPORT_PCRE16 - rc = pcre16_fullinfo((pcre16 *)re, (pcre16_extra *)study, option, ptr); -#else - rc = PCRE_ERROR_BADMODE; -#endif -else -#ifdef SUPPORT_PCRE8 - rc = pcre_fullinfo(re, study, option, ptr); -#else - rc = PCRE_ERROR_BADMODE; -#endif - -if (rc < 0 && rc != PCRE_ERROR_UNSET) - { - fprintf(outfile, "Error %d from pcre%s_fullinfo(%d)\n", rc, - pcre_mode == PCRE32_MODE ? "32" : pcre_mode == PCRE16_MODE ? "16" : "", option); - if (rc == PCRE_ERROR_BADMODE) - fprintf(outfile, "Running in %d-bit mode but pattern was compiled in " - "%d-bit mode\n", 8 * CHAR_SIZE, - 8 * (REAL_PCRE_FLAGS(re) & PCRE_MODE_MASK)); - } - -return rc; -} - - - -/************************************************* -* Swap byte functions * -*************************************************/ - -/* The following functions swap the bytes of a pcre_uint16 and pcre_uint32 -value, respectively. - -Arguments: - value any number - -Returns: the byte swapped value -*/ - -static pcre_uint32 -swap_uint32(pcre_uint32 value) -{ -return ((value & 0x000000ff) << 24) | - ((value & 0x0000ff00) << 8) | - ((value & 0x00ff0000) >> 8) | - (value >> 24); -} - -static pcre_uint16 -swap_uint16(pcre_uint16 value) -{ -return (value >> 8) | (value << 8); -} - - - -/************************************************* -* Flip bytes in a compiled pattern * -*************************************************/ - -/* This function is called if the 'F' option was present on a pattern that is -to be written to a file. We flip the bytes of all the integer fields in the -regex data block and the study block. In 16-bit mode this also flips relevant -bytes in the pattern itself. This is to make it possible to test PCRE's -ability to reload byte-flipped patterns, e.g. those compiled on a different -architecture. */ - -#if defined SUPPORT_PCRE8 || defined SUPPORT_PCRE16 -static void -regexflip8_or_16(pcre *ere, pcre_extra *extra) -{ -real_pcre8_or_16 *re = (real_pcre8_or_16 *)ere; -#ifdef SUPPORT_PCRE16 -int op; -pcre_uint16 *ptr = (pcre_uint16 *)re + re->name_table_offset; -int length = re->name_count * re->name_entry_size; -#ifdef SUPPORT_UTF -BOOL utf = (re->options & PCRE_UTF16) != 0; -BOOL utf16_char = FALSE; -#endif /* SUPPORT_UTF */ -#endif /* SUPPORT_PCRE16 */ - -/* Always flip the bytes in the main data block and study blocks. */ - -re->magic_number = REVERSED_MAGIC_NUMBER; -re->size = swap_uint32(re->size); -re->options = swap_uint32(re->options); -re->flags = swap_uint32(re->flags); -re->limit_match = swap_uint32(re->limit_match); -re->limit_recursion = swap_uint32(re->limit_recursion); -re->first_char = swap_uint16(re->first_char); -re->req_char = swap_uint16(re->req_char); -re->max_lookbehind = swap_uint16(re->max_lookbehind); -re->top_bracket = swap_uint16(re->top_bracket); -re->top_backref = swap_uint16(re->top_backref); -re->name_table_offset = swap_uint16(re->name_table_offset); -re->name_entry_size = swap_uint16(re->name_entry_size); -re->name_count = swap_uint16(re->name_count); -re->ref_count = swap_uint16(re->ref_count); - -if (extra != NULL && (extra->flags & PCRE_EXTRA_STUDY_DATA) != 0) - { - pcre_study_data *rsd = (pcre_study_data *)(extra->study_data); - rsd->size = swap_uint32(rsd->size); - rsd->flags = swap_uint32(rsd->flags); - rsd->minlength = swap_uint32(rsd->minlength); - } - -/* In 8-bit mode, that is all we need to do. In 16-bit mode we must swap bytes -in the name table, if present, and then in the pattern itself. */ - -#ifdef SUPPORT_PCRE16 -if (pcre_mode != PCRE16_MODE) return; - -while(TRUE) - { - /* Swap previous characters. */ - while (length-- > 0) - { - *ptr = swap_uint16(*ptr); - ptr++; - } -#ifdef SUPPORT_UTF - if (utf16_char) - { - if ((ptr[-1] & 0xfc00) == 0xd800) - { - /* We know that there is only one extra character in UTF-16. */ - *ptr = swap_uint16(*ptr); - ptr++; - } - } - utf16_char = FALSE; -#endif /* SUPPORT_UTF */ - - /* Get next opcode. */ - - length = 0; - op = *ptr; - *ptr++ = swap_uint16(op); - - switch (op) - { - case OP_END: - return; - -#ifdef SUPPORT_UTF - case OP_CHAR: - case OP_CHARI: - case OP_NOT: - case OP_NOTI: - case OP_STAR: - case OP_MINSTAR: - case OP_PLUS: - case OP_MINPLUS: - case OP_QUERY: - case OP_MINQUERY: - case OP_UPTO: - case OP_MINUPTO: - case OP_EXACT: - case OP_POSSTAR: - case OP_POSPLUS: - case OP_POSQUERY: - case OP_POSUPTO: - case OP_STARI: - case OP_MINSTARI: - case OP_PLUSI: - case OP_MINPLUSI: - case OP_QUERYI: - case OP_MINQUERYI: - case OP_UPTOI: - case OP_MINUPTOI: - case OP_EXACTI: - case OP_POSSTARI: - case OP_POSPLUSI: - case OP_POSQUERYI: - case OP_POSUPTOI: - case OP_NOTSTAR: - case OP_NOTMINSTAR: - case OP_NOTPLUS: - case OP_NOTMINPLUS: - case OP_NOTQUERY: - case OP_NOTMINQUERY: - case OP_NOTUPTO: - case OP_NOTMINUPTO: - case OP_NOTEXACT: - case OP_NOTPOSSTAR: - case OP_NOTPOSPLUS: - case OP_NOTPOSQUERY: - case OP_NOTPOSUPTO: - case OP_NOTSTARI: - case OP_NOTMINSTARI: - case OP_NOTPLUSI: - case OP_NOTMINPLUSI: - case OP_NOTQUERYI: - case OP_NOTMINQUERYI: - case OP_NOTUPTOI: - case OP_NOTMINUPTOI: - case OP_NOTEXACTI: - case OP_NOTPOSSTARI: - case OP_NOTPOSPLUSI: - case OP_NOTPOSQUERYI: - case OP_NOTPOSUPTOI: - if (utf) utf16_char = TRUE; -#endif - /* Fall through. */ - - default: - length = OP_lengths16[op] - 1; - break; - - case OP_CLASS: - case OP_NCLASS: - /* Skip the character bit map. */ - ptr += 32/sizeof(pcre_uint16); - length = 0; - break; - - case OP_XCLASS: - /* LINK_SIZE can be 1 or 2 in 16 bit mode. */ - if (LINK_SIZE > 1) - length = (int)((((unsigned int)(ptr[0]) << 16) | (unsigned int)(ptr[1])) - - (1 + LINK_SIZE + 1)); - else - length = (int)((unsigned int)(ptr[0]) - (1 + LINK_SIZE + 1)); - - /* Reverse the size of the XCLASS instance. */ - *ptr = swap_uint16(*ptr); - ptr++; - if (LINK_SIZE > 1) - { - *ptr = swap_uint16(*ptr); - ptr++; - } - - op = *ptr; - *ptr = swap_uint16(op); - ptr++; - if ((op & XCL_MAP) != 0) - { - /* Skip the character bit map. */ - ptr += 32/sizeof(pcre_uint16); - length -= 32/sizeof(pcre_uint16); - } - break; - } - } -/* Control should never reach here in 16 bit mode. */ -#endif /* SUPPORT_PCRE16 */ -} -#endif /* SUPPORT_PCRE[8|16] */ - - - -#if defined SUPPORT_PCRE32 -static void -regexflip_32(pcre *ere, pcre_extra *extra) -{ -real_pcre32 *re = (real_pcre32 *)ere; -int op; -pcre_uint32 *ptr = (pcre_uint32 *)re + re->name_table_offset; -int length = re->name_count * re->name_entry_size; - -/* Always flip the bytes in the main data block and study blocks. */ - -re->magic_number = REVERSED_MAGIC_NUMBER; -re->size = swap_uint32(re->size); -re->options = swap_uint32(re->options); -re->flags = swap_uint32(re->flags); -re->limit_match = swap_uint32(re->limit_match); -re->limit_recursion = swap_uint32(re->limit_recursion); -re->first_char = swap_uint32(re->first_char); -re->req_char = swap_uint32(re->req_char); -re->max_lookbehind = swap_uint16(re->max_lookbehind); -re->top_bracket = swap_uint16(re->top_bracket); -re->top_backref = swap_uint16(re->top_backref); -re->name_table_offset = swap_uint16(re->name_table_offset); -re->name_entry_size = swap_uint16(re->name_entry_size); -re->name_count = swap_uint16(re->name_count); -re->ref_count = swap_uint16(re->ref_count); - -if (extra != NULL && (extra->flags & PCRE_EXTRA_STUDY_DATA) != 0) - { - pcre_study_data *rsd = (pcre_study_data *)(extra->study_data); - rsd->size = swap_uint32(rsd->size); - rsd->flags = swap_uint32(rsd->flags); - rsd->minlength = swap_uint32(rsd->minlength); - } - -/* In 32-bit mode we must swap bytes in the name table, if present, and then in -the pattern itself. */ - -while(TRUE) - { - /* Swap previous characters. */ - while (length-- > 0) - { - *ptr = swap_uint32(*ptr); - ptr++; - } - - /* Get next opcode. */ - - length = 0; - op = *ptr; - *ptr++ = swap_uint32(op); - - switch (op) - { - case OP_END: - return; - - default: - length = OP_lengths32[op] - 1; - break; - - case OP_CLASS: - case OP_NCLASS: - /* Skip the character bit map. */ - ptr += 32/sizeof(pcre_uint32); - length = 0; - break; - - case OP_XCLASS: - /* LINK_SIZE can only be 1 in 32-bit mode. */ - length = (int)((unsigned int)(ptr[0]) - (1 + LINK_SIZE + 1)); - - /* Reverse the size of the XCLASS instance. */ - *ptr = swap_uint32(*ptr); - ptr++; - - op = *ptr; - *ptr = swap_uint32(op); - ptr++; - if ((op & XCL_MAP) != 0) - { - /* Skip the character bit map. */ - ptr += 32/sizeof(pcre_uint32); - length -= 32/sizeof(pcre_uint32); - } - break; - } - } -/* Control should never reach here in 32 bit mode. */ -} - -#endif /* SUPPORT_PCRE32 */ - - - -static void -regexflip(pcre *ere, pcre_extra *extra) -{ -#if defined SUPPORT_PCRE32 - if (REAL_PCRE_FLAGS(ere) & PCRE_MODE32) - regexflip_32(ere, extra); -#endif -#if defined SUPPORT_PCRE8 || defined SUPPORT_PCRE16 - if (REAL_PCRE_FLAGS(ere) & (PCRE_MODE8 | PCRE_MODE16)) - regexflip8_or_16(ere, extra); -#endif -} - - - -/************************************************* -* Check match or recursion limit * -*************************************************/ - -static int -check_match_limit(pcre *re, pcre_extra *extra, pcre_uint8 *bptr, int len, - int start_offset, int options, int *use_offsets, int use_size_offsets, - int flag, unsigned long int *limit, int errnumber, const char *msg) -{ -int count; -int min = 0; -int mid = 64; -int max = -1; - -extra->flags |= flag; - -for (;;) - { - *limit = mid; - - PCRE_EXEC(count, re, extra, bptr, len, start_offset, options, - use_offsets, use_size_offsets); - - if (count == errnumber) - { - /* fprintf(outfile, "Testing %s limit = %d\n", msg, mid); */ - min = mid; - mid = (mid == max - 1)? max : (max > 0)? (min + max)/2 : mid*2; - } - - else if (count >= 0 || count == PCRE_ERROR_NOMATCH || - count == PCRE_ERROR_PARTIAL) - { - if (mid == min + 1) - { - fprintf(outfile, "Minimum %s limit = %d\n", msg, mid); - break; - } - /* fprintf(outfile, "Testing %s limit = %d\n", msg, mid); */ - max = mid; - mid = (min + mid)/2; - } - else break; /* Some other error */ - } - -extra->flags &= ~flag; -return count; -} - - - -/************************************************* -* Case-independent strncmp() function * -*************************************************/ - -/* -Arguments: - s first string - t second string - n number of characters to compare - -Returns: < 0, = 0, or > 0, according to the comparison -*/ - -static int -strncmpic(pcre_uint8 *s, pcre_uint8 *t, int n) -{ -while (n--) - { - int c = tolower(*s++) - tolower(*t++); - if (c) return c; - } -return 0; -} - - - -/************************************************* -* Check multicharacter option * -*************************************************/ - -/* This is used both at compile and run-time to check for <xxx> escapes. Print -a message and return 0 if there is no match. - -Arguments: - p points after the leading '<' - f file for error message - nl TRUE to check only for newline settings - stype "modifier" or "escape sequence" - -Returns: appropriate PCRE_NEWLINE_xxx flags, or 0 -*/ - -static int -check_mc_option(pcre_uint8 *p, FILE *f, BOOL nl, const char *stype) -{ -if (strncmpic(p, (pcre_uint8 *)"cr>", 3) == 0) return PCRE_NEWLINE_CR; -if (strncmpic(p, (pcre_uint8 *)"lf>", 3) == 0) return PCRE_NEWLINE_LF; -if (strncmpic(p, (pcre_uint8 *)"crlf>", 5) == 0) return PCRE_NEWLINE_CRLF; -if (strncmpic(p, (pcre_uint8 *)"anycrlf>", 8) == 0) return PCRE_NEWLINE_ANYCRLF; -if (strncmpic(p, (pcre_uint8 *)"any>", 4) == 0) return PCRE_NEWLINE_ANY; -if (strncmpic(p, (pcre_uint8 *)"bsr_anycrlf>", 12) == 0) return PCRE_BSR_ANYCRLF; -if (strncmpic(p, (pcre_uint8 *)"bsr_unicode>", 12) == 0) return PCRE_BSR_UNICODE; - -if (!nl) - { - if (strncmpic(p, (pcre_uint8 *)"JS>", 3) == 0) return PCRE_JAVASCRIPT_COMPAT; - } - -fprintf(f, "Unknown %s at: <%s\n", stype, p); -return 0; -} - - - -/************************************************* -* Usage function * -*************************************************/ - -static void -usage(void) -{ -printf("Usage: pcretest [options] [<input file> [<output file>]]\n\n"); -printf("Input and output default to stdin and stdout.\n"); -#if defined(SUPPORT_LIBREADLINE) || defined(SUPPORT_LIBEDIT) -printf("If input is a terminal, readline() is used to read from it.\n"); -#else -printf("This version of pcretest is not linked with readline().\n"); -#endif -printf("\nOptions:\n"); -#ifdef SUPPORT_PCRE16 -printf(" -16 use the 16-bit library\n"); -#endif -#ifdef SUPPORT_PCRE32 -printf(" -32 use the 32-bit library\n"); -#endif -printf(" -b show compiled code\n"); -printf(" -C show PCRE compile-time options and exit\n"); -printf(" -C arg show a specific compile-time option and exit\n"); -printf(" with its value if numeric (else 0). The arg can be:\n"); -printf(" linksize internal link size [2, 3, 4]\n"); -printf(" pcre8 8 bit library support enabled [0, 1]\n"); -printf(" pcre16 16 bit library support enabled [0, 1]\n"); -printf(" pcre32 32 bit library support enabled [0, 1]\n"); -printf(" utf Unicode Transformation Format supported [0, 1]\n"); -printf(" ucp Unicode Properties supported [0, 1]\n"); -printf(" jit Just-in-time compiler supported [0, 1]\n"); -printf(" newline Newline type [CR, LF, CRLF, ANYCRLF, ANY]\n"); -printf(" bsr \\R type [ANYCRLF, ANY]\n"); -printf(" -d debug: show compiled code and information (-b and -i)\n"); -#if !defined NODFA -printf(" -dfa force DFA matching for all subjects\n"); -#endif -printf(" -help show usage information\n"); -printf(" -i show information about compiled patterns\n" - " -M find MATCH_LIMIT minimum for each subject\n" - " -m output memory used information\n" - " -O set PCRE_NO_AUTO_POSSESS on each pattern\n" - " -o <n> set size of offsets vector to <n>\n"); -#if !defined NOPOSIX -printf(" -p use POSIX interface\n"); -#endif -printf(" -q quiet: do not output PCRE version number at start\n"); -printf(" -S <n> set stack size to <n> megabytes\n"); -printf(" -s force each pattern to be studied at basic level\n" - " -s+ force each pattern to be studied, using JIT if available\n" - " -s++ ditto, verifying when JIT was actually used\n" - " -s+n force each pattern to be studied, using JIT if available,\n" - " where 1 <= n <= 7 selects JIT options\n" - " -s++n ditto, verifying when JIT was actually used\n" - " -t time compilation and execution\n"); -printf(" -t <n> time compilation and execution, repeating <n> times\n"); -printf(" -tm time execution (matching) only\n"); -printf(" -tm <n> time execution (matching) only, repeating <n> times\n"); -printf(" -T same as -t, but show total times at the end\n"); -printf(" -TM same as -tm, but show total time at the end\n"); -} - - - -/************************************************* -* Main Program * -*************************************************/ - -/* Read lines from named file or stdin and write to named file or stdout; lines -consist of a regular expression, in delimiters and optionally followed by -options, followed by a set of test data, terminated by an empty line. */ - -int main(int argc, char **argv) -{ -FILE *infile = stdin; -const char *version; -int options = 0; -int study_options = 0; -int default_find_match_limit = FALSE; -pcre_uint32 default_options = 0; -int op = 1; -int timeit = 0; -int timeitm = 0; -int showtotaltimes = 0; -int showinfo = 0; -int showstore = 0; -int force_study = -1; -int force_study_options = 0; -int quiet = 0; -int size_offsets = 45; -int size_offsets_max; -int *offsets = NULL; -int debug = 0; -int done = 0; -int all_use_dfa = 0; -int verify_jit = 0; -int yield = 0; -int stack_size; -pcre_uint8 *dbuffer = NULL; -pcre_uint8 lockout[24] = { 0 }; -size_t dbuffer_size = 1u << 14; -clock_t total_compile_time = 0; -clock_t total_study_time = 0; -clock_t total_match_time = 0; - -#if !defined NOPOSIX -int posix = 0; -#endif -#if !defined NODFA -int *dfa_workspace = NULL; -#endif - -pcre_jit_stack *jit_stack = NULL; - -/* These vectors store, end-to-end, a list of zero-terminated captured -substring names, each list itself being terminated by an empty name. Assume -that 1024 is plenty long enough for the few names we'll be testing. It is -easiest to keep separate 8-, 16- and 32-bit versions, using the 32-bit version -for the actual memory, to ensure alignment. */ - -pcre_uint32 copynames[1024]; -pcre_uint32 getnames[1024]; - -#ifdef SUPPORT_PCRE32 -pcre_uint32 *cn32ptr; -pcre_uint32 *gn32ptr; -#endif - -#ifdef SUPPORT_PCRE16 -pcre_uint16 *copynames16 = (pcre_uint16 *)copynames; -pcre_uint16 *getnames16 = (pcre_uint16 *)getnames; -pcre_uint16 *cn16ptr; -pcre_uint16 *gn16ptr; -#endif - -#ifdef SUPPORT_PCRE8 -pcre_uint8 *copynames8 = (pcre_uint8 *)copynames; -pcre_uint8 *getnames8 = (pcre_uint8 *)getnames; -pcre_uint8 *cn8ptr; -pcre_uint8 *gn8ptr; -#endif - -/* Get buffers from malloc() so that valgrind will check their misuse when -debugging. They grow automatically when very long lines are read. The 16- -and 32-bit buffers (buffer16, buffer32) are obtained only if needed. */ - -buffer = (pcre_uint8 *)malloc(buffer_size); -pbuffer = (pcre_uint8 *)malloc(buffer_size); - -/* The outfile variable is static so that new_malloc can use it. */ - -outfile = stdout; - -/* The following _setmode() stuff is some Windows magic that tells its runtime -library to translate CRLF into a single LF character. At least, that's what -I've been told: never having used Windows I take this all on trust. Originally -it set 0x8000, but then I was advised that _O_BINARY was better. */ - -#if defined(_WIN32) || defined(WIN32) -_setmode( _fileno( stdout ), _O_BINARY ); -#endif - -/* Get the version number: both pcre_version() and pcre16_version() give the -same answer. We just need to ensure that we call one that is available. */ - -#if defined SUPPORT_PCRE8 -version = pcre_version(); -#elif defined SUPPORT_PCRE16 -version = pcre16_version(); -#elif defined SUPPORT_PCRE32 -version = pcre32_version(); -#endif - -/* Scan options */ - -while (argc > 1 && argv[op][0] == '-') - { - pcre_uint8 *endptr; - char *arg = argv[op]; - - if (strcmp(arg, "-m") == 0) showstore = 1; - else if (strcmp(arg, "-s") == 0) force_study = 0; - - else if (strncmp(arg, "-s+", 3) == 0) - { - arg += 3; - if (*arg == '+') { arg++; verify_jit = TRUE; } - force_study = 1; - if (*arg == 0) - force_study_options = jit_study_bits[6]; - else if (*arg >= '1' && *arg <= '7') - force_study_options = jit_study_bits[*arg - '1']; - else goto BAD_ARG; - } - else if (strcmp(arg, "-8") == 0) - { -#ifdef SUPPORT_PCRE8 - pcre_mode = PCRE8_MODE; -#else - printf("** This version of PCRE was built without 8-bit support\n"); - exit(1); -#endif - } - else if (strcmp(arg, "-16") == 0) - { -#ifdef SUPPORT_PCRE16 - pcre_mode = PCRE16_MODE; -#else - printf("** This version of PCRE was built without 16-bit support\n"); - exit(1); -#endif - } - else if (strcmp(arg, "-32") == 0) - { -#ifdef SUPPORT_PCRE32 - pcre_mode = PCRE32_MODE; -#else - printf("** This version of PCRE was built without 32-bit support\n"); - exit(1); -#endif - } - else if (strcmp(arg, "-q") == 0) quiet = 1; - else if (strcmp(arg, "-b") == 0) debug = 1; - else if (strcmp(arg, "-i") == 0) showinfo = 1; - else if (strcmp(arg, "-d") == 0) showinfo = debug = 1; - else if (strcmp(arg, "-M") == 0) default_find_match_limit = TRUE; - else if (strcmp(arg, "-O") == 0) default_options |= PCRE_NO_AUTO_POSSESS; -#if !defined NODFA - else if (strcmp(arg, "-dfa") == 0) all_use_dfa = 1; -#endif - else if (strcmp(arg, "-o") == 0 && argc > 2 && - ((size_offsets = get_value((pcre_uint8 *)argv[op+1], &endptr)), - *endptr == 0)) - { - op++; - argc--; - } - else if (strcmp(arg, "-t") == 0 || strcmp(arg, "-tm") == 0 || - strcmp(arg, "-T") == 0 || strcmp(arg, "-TM") == 0) - { - int temp; - int both = arg[2] == 0; - showtotaltimes = arg[1] == 'T'; - if (argc > 2 && (temp = get_value((pcre_uint8 *)argv[op+1], &endptr), - *endptr == 0)) - { - timeitm = temp; - op++; - argc--; - } - else timeitm = LOOPREPEAT; - if (both) timeit = timeitm; - } - else if (strcmp(arg, "-S") == 0 && argc > 2 && - ((stack_size = get_value((pcre_uint8 *)argv[op+1], &endptr)), - *endptr == 0)) - { -#if defined(_WIN32) || defined(WIN32) || defined(__minix) || defined(NATIVE_ZOS) || defined(__VMS) - printf("PCRE: -S not supported on this OS\n"); - exit(1); -#else - int rc; - struct rlimit rlim; - getrlimit(RLIMIT_STACK, &rlim); - rlim.rlim_cur = stack_size * 1024 * 1024; - rc = setrlimit(RLIMIT_STACK, &rlim); - if (rc != 0) - { - printf("PCRE: setrlimit() failed with error %d\n", rc); - exit(1); - } - op++; - argc--; -#endif - } -#if !defined NOPOSIX - else if (strcmp(arg, "-p") == 0) posix = 1; -#endif - else if (strcmp(arg, "-C") == 0) - { - int rc; - unsigned long int lrc; - - if (argc > 2) - { - if (strcmp(argv[op + 1], "linksize") == 0) - { - (void)PCRE_CONFIG(PCRE_CONFIG_LINK_SIZE, &rc); - printf("%d\n", rc); - yield = rc; - -#ifdef __VMS - vms_setsymbol("LINKSIZE",0,yield ); -#endif - } - else if (strcmp(argv[op + 1], "pcre8") == 0) - { -#ifdef SUPPORT_PCRE8 - printf("1\n"); - yield = 1; -#else - printf("0\n"); - yield = 0; -#endif -#ifdef __VMS - vms_setsymbol("PCRE8",0,yield ); -#endif - } - else if (strcmp(argv[op + 1], "pcre16") == 0) - { -#ifdef SUPPORT_PCRE16 - printf("1\n"); - yield = 1; -#else - printf("0\n"); - yield = 0; -#endif -#ifdef __VMS - vms_setsymbol("PCRE16",0,yield ); -#endif - } - else if (strcmp(argv[op + 1], "pcre32") == 0) - { -#ifdef SUPPORT_PCRE32 - printf("1\n"); - yield = 1; -#else - printf("0\n"); - yield = 0; -#endif -#ifdef __VMS - vms_setsymbol("PCRE32",0,yield ); -#endif - } - else if (strcmp(argv[op + 1], "utf") == 0) - { -#ifdef SUPPORT_PCRE8 - if (pcre_mode == PCRE8_MODE) - (void)pcre_config(PCRE_CONFIG_UTF8, &rc); -#endif -#ifdef SUPPORT_PCRE16 - if (pcre_mode == PCRE16_MODE) - (void)pcre16_config(PCRE_CONFIG_UTF16, &rc); -#endif -#ifdef SUPPORT_PCRE32 - if (pcre_mode == PCRE32_MODE) - (void)pcre32_config(PCRE_CONFIG_UTF32, &rc); -#endif - printf("%d\n", rc); - yield = rc; -#ifdef __VMS - vms_setsymbol("UTF",0,yield ); -#endif - } - else if (strcmp(argv[op + 1], "ucp") == 0) - { - (void)PCRE_CONFIG(PCRE_CONFIG_UNICODE_PROPERTIES, &rc); - printf("%d\n", rc); - yield = rc; - } - else if (strcmp(argv[op + 1], "jit") == 0) - { - (void)PCRE_CONFIG(PCRE_CONFIG_JIT, &rc); - printf("%d\n", rc); - yield = rc; - } - else if (strcmp(argv[op + 1], "newline") == 0) - { - (void)PCRE_CONFIG(PCRE_CONFIG_NEWLINE, &rc); - print_newline_config(rc, TRUE); - } - else if (strcmp(argv[op + 1], "bsr") == 0) - { - (void)PCRE_CONFIG(PCRE_CONFIG_BSR, &rc); - printf("%s\n", rc? "ANYCRLF" : "ANY"); - } - else if (strcmp(argv[op + 1], "ebcdic") == 0) - { -#ifdef EBCDIC - printf("1\n"); - yield = 1; -#else - printf("0\n"); -#endif - } - else if (strcmp(argv[op + 1], "ebcdic-nl") == 0) - { -#ifdef EBCDIC - printf("0x%02x\n", CHAR_LF); -#else - printf("0\n"); -#endif - } - else - { - printf("Unknown -C option: %s\n", argv[op + 1]); - } - goto EXIT; - } - - /* No argument for -C: output all configuration information. */ - - printf("PCRE version %s\n", version); - printf("Compiled with\n"); - -#ifdef EBCDIC - printf(" EBCDIC code support: LF is 0x%02x\n", CHAR_LF); -#endif - -/* At least one of SUPPORT_PCRE8 and SUPPORT_PCRE16 will be set. If both -are set, either both UTFs are supported or both are not supported. */ - -#ifdef SUPPORT_PCRE8 - printf(" 8-bit support\n"); - (void)pcre_config(PCRE_CONFIG_UTF8, &rc); - printf (" %sUTF-8 support\n", rc ? "" : "No "); -#endif -#ifdef SUPPORT_PCRE16 - printf(" 16-bit support\n"); - (void)pcre16_config(PCRE_CONFIG_UTF16, &rc); - printf (" %sUTF-16 support\n", rc ? "" : "No "); -#endif -#ifdef SUPPORT_PCRE32 - printf(" 32-bit support\n"); - (void)pcre32_config(PCRE_CONFIG_UTF32, &rc); - printf (" %sUTF-32 support\n", rc ? "" : "No "); -#endif - - (void)PCRE_CONFIG(PCRE_CONFIG_UNICODE_PROPERTIES, &rc); - printf(" %sUnicode properties support\n", rc? "" : "No "); - (void)PCRE_CONFIG(PCRE_CONFIG_JIT, &rc); - if (rc) - { - const char *arch; - (void)PCRE_CONFIG(PCRE_CONFIG_JITTARGET, (void *)(&arch)); - printf(" Just-in-time compiler support: %s\n", arch); - } - else - printf(" No just-in-time compiler support\n"); - (void)PCRE_CONFIG(PCRE_CONFIG_NEWLINE, &rc); - print_newline_config(rc, FALSE); - (void)PCRE_CONFIG(PCRE_CONFIG_BSR, &rc); - printf(" \\R matches %s\n", rc? "CR, LF, or CRLF only" : - "all Unicode newlines"); - (void)PCRE_CONFIG(PCRE_CONFIG_LINK_SIZE, &rc); - printf(" Internal link size = %d\n", rc); - (void)PCRE_CONFIG(PCRE_CONFIG_POSIX_MALLOC_THRESHOLD, &rc); - printf(" POSIX malloc threshold = %d\n", rc); - (void)PCRE_CONFIG(PCRE_CONFIG_PARENS_LIMIT, &lrc); - printf(" Parentheses nest limit = %ld\n", lrc); - (void)PCRE_CONFIG(PCRE_CONFIG_MATCH_LIMIT, &lrc); - printf(" Default match limit = %ld\n", lrc); - (void)PCRE_CONFIG(PCRE_CONFIG_MATCH_LIMIT_RECURSION, &lrc); - printf(" Default recursion depth limit = %ld\n", lrc); - (void)PCRE_CONFIG(PCRE_CONFIG_STACKRECURSE, &rc); - printf(" Match recursion uses %s", rc? "stack" : "heap"); - if (showstore) - { - PCRE_EXEC(stack_size, NULL, NULL, NULL, -999, -999, 0, NULL, 0); - printf(": %sframe size = %d bytes", rc? "approximate " : "", -stack_size); - } - printf("\n"); - goto EXIT; - } - else if (strcmp(arg, "-help") == 0 || - strcmp(arg, "--help") == 0) - { - usage(); - goto EXIT; - } - else - { - BAD_ARG: - printf("** Unknown or malformed option %s\n", arg); - usage(); - yield = 1; - goto EXIT; - } - op++; - argc--; - } - -/* Get the store for the offsets vector, and remember what it was */ - -size_offsets_max = size_offsets; -offsets = (int *)malloc(size_offsets_max * sizeof(int)); -if (offsets == NULL) - { - printf("** Failed to get %d bytes of memory for offsets vector\n", - (int)(size_offsets_max * sizeof(int))); - yield = 1; - goto EXIT; - } - -/* Sort out the input and output files */ - -if (argc > 1) - { - infile = fopen(argv[op], INPUT_MODE); - if (infile == NULL) - { - printf("** Failed to open %s\n", argv[op]); - yield = 1; - goto EXIT; - } - } - -if (argc > 2) - { - outfile = fopen(argv[op+1], OUTPUT_MODE); - if (outfile == NULL) - { - printf("** Failed to open %s\n", argv[op+1]); - yield = 1; - goto EXIT; - } - } - -/* Set alternative malloc function */ - -#ifdef SUPPORT_PCRE8 -pcre_malloc = new_malloc; -pcre_free = new_free; -pcre_stack_malloc = stack_malloc; -pcre_stack_free = stack_free; -#endif - -#ifdef SUPPORT_PCRE16 -pcre16_malloc = new_malloc; -pcre16_free = new_free; -pcre16_stack_malloc = stack_malloc; -pcre16_stack_free = stack_free; -#endif - -#ifdef SUPPORT_PCRE32 -pcre32_malloc = new_malloc; -pcre32_free = new_free; -pcre32_stack_malloc = stack_malloc; -pcre32_stack_free = stack_free; -#endif - -/* Heading line unless quiet */ - -if (!quiet) fprintf(outfile, "PCRE version %s\n\n", version); - -/* Main loop */ - -while (!done) - { - pcre *re = NULL; - pcre_extra *extra = NULL; - -#if !defined NOPOSIX /* There are still compilers that require no indent */ - regex_t preg = { NULL, 0, 0} ; - int do_posix = 0; -#endif - - const char *error; - pcre_uint8 *markptr; - pcre_uint8 *p, *pp, *ppp; - pcre_uint8 *to_file = NULL; - const pcre_uint8 *tables = NULL; - unsigned long int get_options; - unsigned long int true_size, true_study_size = 0; - size_t size; - int do_allcaps = 0; - int do_mark = 0; - int do_study = 0; - int no_force_study = 0; - int do_debug = debug; - int do_G = 0; - int do_g = 0; - int do_showinfo = showinfo; - int do_showrest = 0; - int do_showcaprest = 0; - int do_flip = 0; - int erroroffset, len, delimiter, poffset; - -#if !defined NODFA - int dfa_matched = 0; -#endif - - use_utf = 0; - debug_lengths = 1; - SET_PCRE_STACK_GUARD(NULL); - - if (extend_inputline(infile, buffer, " re> ") == NULL) break; - if (infile != stdin) fprintf(outfile, "%s", (char *)buffer); - fflush(outfile); - - p = buffer; - while (isspace(*p)) p++; - if (*p == 0) continue; - - /* Handle option lock-out setting */ - - if (*p == '<' && p[1] == ' ') - { - p += 2; - while (isspace(*p)) p++; - if (strncmp((char *)p, "forbid ", 7) == 0) - { - p += 7; - while (isspace(*p)) p++; - pp = lockout; - while (!isspace(*p) && pp < lockout + sizeof(lockout) - 1) - *pp++ = *p++; - *pp = 0; - } - else - { - printf("** Unrecognized special command '%s'\n", p); - yield = 1; - goto EXIT; - } - continue; - } - - /* See if the pattern is to be loaded pre-compiled from a file. */ - - if (*p == '<' && strchr((char *)(p+1), '<') == NULL) - { - pcre_uint32 magic; - pcre_uint8 sbuf[8]; - FILE *f; - - p++; - if (*p == '!') - { - do_debug = TRUE; - do_showinfo = TRUE; - p++; - } - - pp = p + (int)strlen((char *)p); - while (isspace(pp[-1])) pp--; - *pp = 0; - - f = fopen((char *)p, "rb"); - if (f == NULL) - { - fprintf(outfile, "Failed to open %s: %s\n", p, strerror(errno)); - continue; - } - if (fread(sbuf, 1, 8, f) != 8) goto FAIL_READ; - - true_size = - (sbuf[0] << 24) | (sbuf[1] << 16) | (sbuf[2] << 8) | sbuf[3]; - true_study_size = - (sbuf[4] << 24) | (sbuf[5] << 16) | (sbuf[6] << 8) | sbuf[7]; - - re = (pcre *)new_malloc(true_size); - if (re == NULL) - { - printf("** Failed to get %d bytes of memory for pcre object\n", - (int)true_size); - yield = 1; - goto EXIT; - } - if (fread(re, 1, true_size, f) != true_size) goto FAIL_READ; - - magic = REAL_PCRE_MAGIC(re); - if (magic != MAGIC_NUMBER) - { - if (swap_uint32(magic) == MAGIC_NUMBER) - { - do_flip = 1; - } - else - { - fprintf(outfile, "Data in %s is not a compiled PCRE regex\n", p); - new_free(re); - fclose(f); - continue; - } - } - - /* We hide the byte-invert info for little and big endian tests. */ - fprintf(outfile, "Compiled pattern%s loaded from %s\n", - do_flip && (p[-1] == '<') ? " (byte-inverted)" : "", p); - - /* Now see if there is any following study data. */ - - if (true_study_size != 0) - { - pcre_study_data *psd; - - extra = (pcre_extra *)new_malloc(sizeof(pcre_extra) + true_study_size); - extra->flags = PCRE_EXTRA_STUDY_DATA; - - psd = (pcre_study_data *)(((char *)extra) + sizeof(pcre_extra)); - extra->study_data = psd; - - if (fread(psd, 1, true_study_size, f) != true_study_size) - { - FAIL_READ: - fprintf(outfile, "Failed to read data from %s\n", p); - if (extra != NULL) - { - PCRE_FREE_STUDY(extra); - } - new_free(re); - fclose(f); - continue; - } - fprintf(outfile, "Study data loaded from %s\n", p); - do_study = 1; /* To get the data output if requested */ - } - else fprintf(outfile, "No study data\n"); - - /* Flip the necessary bytes. */ - if (do_flip) - { - int rc; - PCRE_PATTERN_TO_HOST_BYTE_ORDER(rc, re, extra, NULL); - if (rc == PCRE_ERROR_BADMODE) - { - pcre_uint32 flags_in_host_byte_order; - if (REAL_PCRE_MAGIC(re) == MAGIC_NUMBER) - flags_in_host_byte_order = REAL_PCRE_FLAGS(re); - else - flags_in_host_byte_order = swap_uint32(REAL_PCRE_FLAGS(re)); - /* Simulate the result of the function call below. */ - fprintf(outfile, "Error %d from pcre%s_fullinfo(%d)\n", rc, - pcre_mode == PCRE32_MODE ? "32" : pcre_mode == PCRE16_MODE ? "16" : "", - PCRE_INFO_OPTIONS); - fprintf(outfile, "Running in %d-bit mode but pattern was compiled in " - "%d-bit mode\n", 8 * CHAR_SIZE, 8 * (flags_in_host_byte_order & PCRE_MODE_MASK)); - new_free(re); - fclose(f); - continue; - } - } - - /* Need to know if UTF-8 for printing data strings. */ - - if (new_info(re, NULL, PCRE_INFO_OPTIONS, &get_options) < 0) - { - new_free(re); - fclose(f); - continue; - } - use_utf = (get_options & PCRE_UTF8) != 0; - - fclose(f); - goto SHOW_INFO; - } - - /* In-line pattern (the usual case). Get the delimiter and seek the end of - the pattern; if it isn't complete, read more. */ - - delimiter = *p++; - - if (isalnum(delimiter) || delimiter == '\\') - { - fprintf(outfile, "** Delimiter must not be alphanumeric or \\\n"); - goto SKIP_DATA; - } - - pp = p; - poffset = (int)(p - buffer); - - for(;;) - { - while (*pp != 0) - { - if (*pp == '\\' && pp[1] != 0) pp++; - else if (*pp == delimiter) break; - pp++; - } - if (*pp != 0) break; - if ((pp = extend_inputline(infile, pp, " > ")) == NULL) - { - fprintf(outfile, "** Unexpected EOF\n"); - done = 1; - goto CONTINUE; - } - if (infile != stdin) fprintf(outfile, "%s", (char *)pp); - } - - /* The buffer may have moved while being extended; reset the start of data - pointer to the correct relative point in the buffer. */ - - p = buffer + poffset; - - /* If the first character after the delimiter is backslash, make - the pattern end with backslash. This is purely to provide a way - of testing for the error message when a pattern ends with backslash. */ - - if (pp[1] == '\\') *pp++ = '\\'; - - /* Terminate the pattern at the delimiter, and save a copy of the pattern - for callouts. */ - - *pp++ = 0; - strcpy((char *)pbuffer, (char *)p); - - /* Look for modifiers and options after the final delimiter. */ - - options = default_options; - study_options = force_study_options; - log_store = showstore; /* default from command line */ - - while (*pp != 0) - { - /* Check to see whether this modifier has been locked out for this file. - This is complicated for the multi-character options that begin with '<'. - If there is no '>' in the lockout string, all multi-character modifiers are - locked out. */ - - if (strchr((char *)lockout, *pp) != NULL) - { - if (*pp == '<' && strchr((char *)lockout, '>') != NULL) - { - int x = check_mc_option(pp+1, outfile, FALSE, "modifier"); - if (x == 0) goto SKIP_DATA; - - for (ppp = lockout; *ppp != 0; ppp++) - { - if (*ppp == '<') - { - int y = check_mc_option(ppp+1, outfile, FALSE, "modifier"); - if (y == 0) - { - printf("** Error in modifier forbid data - giving up.\n"); - yield = 1; - goto EXIT; - } - if (x == y) - { - ppp = pp; - while (*ppp != '>') ppp++; - printf("** The %.*s modifier is locked out - giving up.\n", - (int)(ppp - pp + 1), pp); - yield = 1; - goto EXIT; - } - } - } - } - - /* The single-character modifiers are straightforward. */ - - else - { - printf("** The /%c modifier is locked out - giving up.\n", *pp); - yield = 1; - goto EXIT; - } - } - - /* The modifier is not locked out; handle it. */ - - switch (*pp++) - { - case 'f': options |= PCRE_FIRSTLINE; break; - case 'g': do_g = 1; break; - case 'i': options |= PCRE_CASELESS; break; - case 'm': options |= PCRE_MULTILINE; break; - case 's': options |= PCRE_DOTALL; break; - case 'x': options |= PCRE_EXTENDED; break; - - case '+': - if (do_showrest) do_showcaprest = 1; else do_showrest = 1; - break; - - case '=': do_allcaps = 1; break; - case 'A': options |= PCRE_ANCHORED; break; - case 'B': do_debug = 1; break; - case 'C': options |= PCRE_AUTO_CALLOUT; break; - case 'D': do_debug = do_showinfo = 1; break; - case 'E': options |= PCRE_DOLLAR_ENDONLY; break; - case 'F': do_flip = 1; break; - case 'G': do_G = 1; break; - case 'I': do_showinfo = 1; break; - case 'J': options |= PCRE_DUPNAMES; break; - case 'K': do_mark = 1; break; - case 'M': log_store = 1; break; - case 'N': options |= PCRE_NO_AUTO_CAPTURE; break; - case 'O': options |= PCRE_NO_AUTO_POSSESS; break; - -#if !defined NOPOSIX - case 'P': do_posix = 1; break; -#endif - - case 'Q': - switch (*pp) - { - case '0': - case '1': - stack_guard_return = *pp++ - '0'; - break; - - default: - fprintf(outfile, "** Missing 0 or 1 after /Q\n"); - goto SKIP_DATA; - } - SET_PCRE_STACK_GUARD(stack_guard); - break; - - case 'S': - do_study = 1; - for (;;) - { - switch (*pp++) - { - case 'S': - do_study = 0; - no_force_study = 1; - break; - - case '!': - study_options |= PCRE_STUDY_EXTRA_NEEDED; - break; - - case '+': - if (*pp == '+') - { - verify_jit = TRUE; - pp++; - } - if (*pp >= '1' && *pp <= '7') - study_options |= jit_study_bits[*pp++ - '1']; - else - study_options |= jit_study_bits[6]; - break; - - case '-': - study_options &= ~PCRE_STUDY_ALLJIT; - break; - - default: - pp--; - goto ENDLOOP; - } - } - ENDLOOP: - break; - - case 'U': options |= PCRE_UNGREEDY; break; - case 'W': options |= PCRE_UCP; break; - case 'X': options |= PCRE_EXTRA; break; - case 'Y': options |= PCRE_NO_START_OPTIMISE; break; - case 'Z': debug_lengths = 0; break; - case '8': options |= PCRE_UTF8; use_utf = 1; break; - case '9': options |= PCRE_NEVER_UTF; break; - case '?': options |= PCRE_NO_UTF8_CHECK; break; - - case 'T': - switch (*pp++) - { - case '0': tables = tables0; break; - case '1': tables = tables1; break; - - case '\r': - case '\n': - case ' ': - case 0: - fprintf(outfile, "** Missing table number after /T\n"); - goto SKIP_DATA; - - default: - fprintf(outfile, "** Bad table number \"%c\" after /T\n", pp[-1]); - goto SKIP_DATA; - } - break; - - case 'L': - ppp = pp; - /* The '\r' test here is so that it works on Windows. */ - /* The '0' test is just in case this is an unterminated line. */ - while (*ppp != 0 && *ppp != '\n' && *ppp != '\r' && *ppp != ' ') ppp++; - *ppp = 0; - if (setlocale(LC_CTYPE, (const char *)pp) == NULL) - { - fprintf(outfile, "** Failed to set locale \"%s\"\n", pp); - goto SKIP_DATA; - } - locale_set = 1; - tables = PCRE_MAKETABLES; - pp = ppp; - break; - - case '>': - to_file = pp; - while (*pp != 0) pp++; - while (isspace(pp[-1])) pp--; - *pp = 0; - break; - - case '<': - { - int x = check_mc_option(pp, outfile, FALSE, "modifier"); - if (x == 0) goto SKIP_DATA; - options |= x; - while (*pp++ != '>'); - } - break; - - case '\r': /* So that it works in Windows */ - case '\n': - case ' ': - break; - - default: - fprintf(outfile, "** Unknown modifier '%c'\n", pp[-1]); - goto SKIP_DATA; - } - } - - /* Handle compiling via the POSIX interface, which doesn't support the - timing, showing, or debugging options, nor the ability to pass over - local character tables. Neither does it have 16-bit support. */ - -#if !defined NOPOSIX - if (posix || do_posix) - { - int rc; - int cflags = 0; - - if ((options & PCRE_CASELESS) != 0) cflags |= REG_ICASE; - if ((options & PCRE_MULTILINE) != 0) cflags |= REG_NEWLINE; - if ((options & PCRE_DOTALL) != 0) cflags |= REG_DOTALL; - if ((options & PCRE_NO_AUTO_CAPTURE) != 0) cflags |= REG_NOSUB; - if ((options & PCRE_UTF8) != 0) cflags |= REG_UTF8; - if ((options & PCRE_UCP) != 0) cflags |= REG_UCP; - if ((options & PCRE_UNGREEDY) != 0) cflags |= REG_UNGREEDY; - - rc = regcomp(&preg, (char *)p, cflags); - - /* Compilation failed; go back for another re, skipping to blank line - if non-interactive. */ - - if (rc != 0) - { - (void)regerror(rc, &preg, (char *)buffer, buffer_size); - fprintf(outfile, "Failed: POSIX code %d: %s\n", rc, buffer); - goto SKIP_DATA; - } - } - - /* Handle compiling via the native interface */ - - else -#endif /* !defined NOPOSIX */ - - { - /* In 16- or 32-bit mode, convert the input. */ - -#ifdef SUPPORT_PCRE16 - if (pcre_mode == PCRE16_MODE) - { - switch(to16(FALSE, p, options & PCRE_UTF8, (int)strlen((char *)p))) - { - case -1: - fprintf(outfile, "**Failed: invalid UTF-8 string cannot be " - "converted to UTF-16\n"); - goto SKIP_DATA; - - case -2: - fprintf(outfile, "**Failed: character value greater than 0x10ffff " - "cannot be converted to UTF-16\n"); - goto SKIP_DATA; - - case -3: /* "Impossible error" when to16 is called arg1 FALSE */ - fprintf(outfile, "**Failed: character value greater than 0xffff " - "cannot be converted to 16-bit in non-UTF mode\n"); - goto SKIP_DATA; - - default: - break; - } - p = (pcre_uint8 *)buffer16; - } -#endif - -#ifdef SUPPORT_PCRE32 - if (pcre_mode == PCRE32_MODE) - { - switch(to32(FALSE, p, options & PCRE_UTF32, (int)strlen((char *)p))) - { - case -1: - fprintf(outfile, "**Failed: invalid UTF-8 string cannot be " - "converted to UTF-32\n"); - goto SKIP_DATA; - - case -2: - fprintf(outfile, "**Failed: character value greater than 0x10ffff " - "cannot be converted to UTF-32\n"); - goto SKIP_DATA; - - case -3: - fprintf(outfile, "**Failed: character value is ill-formed UTF-32\n"); - goto SKIP_DATA; - - default: - break; - } - p = (pcre_uint8 *)buffer32; - } -#endif - - /* Compile many times when timing */ - - if (timeit > 0) - { - register int i; - clock_t time_taken; - clock_t start_time = clock(); - for (i = 0; i < timeit; i++) - { - PCRE_COMPILE(re, p, options, &error, &erroroffset, tables); - if (re != NULL) free(re); - } - total_compile_time += (time_taken = clock() - start_time); - fprintf(outfile, "Compile time %.4f milliseconds\n", - (((double)time_taken * 1000.0) / (double)timeit) / - (double)CLOCKS_PER_SEC); - } - - PCRE_COMPILE(re, p, options, &error, &erroroffset, tables); - - /* Compilation failed; go back for another re, skipping to blank line - if non-interactive. */ - - if (re == NULL) - { - fprintf(outfile, "Failed: %s at offset %d\n", error, erroroffset); - SKIP_DATA: - if (infile != stdin) - { - for (;;) - { - if (extend_inputline(infile, buffer, NULL) == NULL) - { - done = 1; - goto CONTINUE; - } - len = (int)strlen((char *)buffer); - while (len > 0 && isspace(buffer[len-1])) len--; - if (len == 0) break; - } - fprintf(outfile, "\n"); - } - goto CONTINUE; - } - - /* Compilation succeeded. It is now possible to set the UTF-8 option from - within the regex; check for this so that we know how to process the data - lines. */ - - if (new_info(re, NULL, PCRE_INFO_OPTIONS, &get_options) < 0) - goto SKIP_DATA; - if ((get_options & PCRE_UTF8) != 0) use_utf = 1; - - /* Extract the size for possible writing before possibly flipping it, - and remember the store that was got. */ - - true_size = REAL_PCRE_SIZE(re); - - /* Output code size information if requested */ - - if (log_store) - { - int name_count, name_entry_size, real_pcre_size; - - new_info(re, NULL, PCRE_INFO_NAMECOUNT, &name_count); - new_info(re, NULL, PCRE_INFO_NAMEENTRYSIZE, &name_entry_size); - real_pcre_size = 0; -#ifdef SUPPORT_PCRE8 - if (REAL_PCRE_FLAGS(re) & PCRE_MODE8) - real_pcre_size = sizeof(real_pcre); -#endif -#ifdef SUPPORT_PCRE16 - if (REAL_PCRE_FLAGS(re) & PCRE_MODE16) - real_pcre_size = sizeof(real_pcre16); -#endif -#ifdef SUPPORT_PCRE32 - if (REAL_PCRE_FLAGS(re) & PCRE_MODE32) - real_pcre_size = sizeof(real_pcre32); -#endif - new_info(re, NULL, PCRE_INFO_SIZE, &size); - fprintf(outfile, "Memory allocation (code space): %d\n", - (int)(size - real_pcre_size - name_count * name_entry_size)); - } - - /* If -s or /S was present, study the regex to generate additional info to - help with the matching, unless the pattern has the SS option, which - suppresses the effect of /S (used for a few test patterns where studying is - never sensible). */ - - if (do_study || (force_study >= 0 && !no_force_study)) - { - if (timeit > 0) - { - register int i; - clock_t time_taken; - clock_t start_time = clock(); - for (i = 0; i < timeit; i++) - { - PCRE_STUDY(extra, re, study_options, &error); - } - total_study_time = (time_taken = clock() - start_time); - if (extra != NULL) - { - PCRE_FREE_STUDY(extra); - } - fprintf(outfile, " Study time %.4f milliseconds\n", - (((double)time_taken * 1000.0) / (double)timeit) / - (double)CLOCKS_PER_SEC); - } - PCRE_STUDY(extra, re, study_options, &error); - if (error != NULL) - fprintf(outfile, "Failed to study: %s\n", error); - else if (extra != NULL) - { - true_study_size = ((pcre_study_data *)(extra->study_data))->size; - if (log_store) - { - size_t jitsize; - if (new_info(re, extra, PCRE_INFO_JITSIZE, &jitsize) == 0 && - jitsize != 0) - fprintf(outfile, "Memory allocation (JIT code): %d\n", (int)jitsize); - } - } - } - - /* If /K was present, we set up for handling MARK data. */ - - if (do_mark) - { - if (extra == NULL) - { - extra = (pcre_extra *)malloc(sizeof(pcre_extra)); - extra->flags = 0; - } - extra->mark = &markptr; - extra->flags |= PCRE_EXTRA_MARK; - } - - /* Extract and display information from the compiled data if required. */ - - SHOW_INFO: - - if (do_debug) - { - fprintf(outfile, "------------------------------------------------------------------\n"); - PCRE_PRINTINT(re, outfile, debug_lengths); - } - - /* We already have the options in get_options (see above) */ - - if (do_showinfo) - { - unsigned long int all_options; - pcre_uint32 first_char, need_char; - pcre_uint32 match_limit, recursion_limit; - int count, backrefmax, first_char_set, need_char_set, okpartial, jchanged, - hascrorlf, maxlookbehind, match_empty; - int nameentrysize, namecount; - const pcre_uint8 *nametable; - - if (new_info(re, NULL, PCRE_INFO_CAPTURECOUNT, &count) + - new_info(re, NULL, PCRE_INFO_BACKREFMAX, &backrefmax) + - new_info(re, NULL, PCRE_INFO_FIRSTCHARACTER, &first_char) + - new_info(re, NULL, PCRE_INFO_FIRSTCHARACTERFLAGS, &first_char_set) + - new_info(re, NULL, PCRE_INFO_REQUIREDCHAR, &need_char) + - new_info(re, NULL, PCRE_INFO_REQUIREDCHARFLAGS, &need_char_set) + - new_info(re, NULL, PCRE_INFO_NAMEENTRYSIZE, &nameentrysize) + - new_info(re, NULL, PCRE_INFO_NAMECOUNT, &namecount) + - new_info(re, NULL, PCRE_INFO_NAMETABLE, (void *)&nametable) + - new_info(re, NULL, PCRE_INFO_OKPARTIAL, &okpartial) + - new_info(re, NULL, PCRE_INFO_JCHANGED, &jchanged) + - new_info(re, NULL, PCRE_INFO_HASCRORLF, &hascrorlf) + - new_info(re, NULL, PCRE_INFO_MATCH_EMPTY, &match_empty) + - new_info(re, NULL, PCRE_INFO_MAXLOOKBEHIND, &maxlookbehind) - != 0) - goto SKIP_DATA; - - fprintf(outfile, "Capturing subpattern count = %d\n", count); - - if (backrefmax > 0) - fprintf(outfile, "Max back reference = %d\n", backrefmax); - - if (maxlookbehind > 0) - fprintf(outfile, "Max lookbehind = %d\n", maxlookbehind); - - if (new_info(re, NULL, PCRE_INFO_MATCHLIMIT, &match_limit) == 0) - fprintf(outfile, "Match limit = %u\n", match_limit); - - if (new_info(re, NULL, PCRE_INFO_RECURSIONLIMIT, &recursion_limit) == 0) - fprintf(outfile, "Recursion limit = %u\n", recursion_limit); - - if (namecount > 0) - { - fprintf(outfile, "Named capturing subpatterns:\n"); - while (namecount-- > 0) - { - int imm2_size = pcre_mode == PCRE8_MODE ? 2 : 1; - int length = (int)STRLEN(nametable + imm2_size); - fprintf(outfile, " "); - PCHARSV(nametable, imm2_size, length, outfile); - while (length++ < nameentrysize - imm2_size) putc(' ', outfile); -#ifdef SUPPORT_PCRE32 - if (pcre_mode == PCRE32_MODE) - fprintf(outfile, "%3d\n", (int)(((PCRE_SPTR32)nametable)[0])); -#endif -#ifdef SUPPORT_PCRE16 - if (pcre_mode == PCRE16_MODE) - fprintf(outfile, "%3d\n", (int)(((PCRE_SPTR16)nametable)[0])); -#endif -#ifdef SUPPORT_PCRE8 - if (pcre_mode == PCRE8_MODE) - fprintf(outfile, "%3d\n", ((int)nametable[0] << 8) | (int)nametable[1]); -#endif - nametable += nameentrysize * CHAR_SIZE; - } - } - - if (!okpartial) fprintf(outfile, "Partial matching not supported\n"); - if (hascrorlf) fprintf(outfile, "Contains explicit CR or LF match\n"); - if (match_empty) fprintf(outfile, "May match empty string\n"); - - all_options = REAL_PCRE_OPTIONS(re); - if (do_flip) all_options = swap_uint32(all_options); - - if (get_options == 0) fprintf(outfile, "No options\n"); - else fprintf(outfile, "Options:%s%s%s%s%s%s%s%s%s%s%s%s%s%s%s%s%s%s%s\n", - ((get_options & PCRE_ANCHORED) != 0)? " anchored" : "", - ((get_options & PCRE_CASELESS) != 0)? " caseless" : "", - ((get_options & PCRE_EXTENDED) != 0)? " extended" : "", - ((get_options & PCRE_MULTILINE) != 0)? " multiline" : "", - ((get_options & PCRE_FIRSTLINE) != 0)? " firstline" : "", - ((get_options & PCRE_DOTALL) != 0)? " dotall" : "", - ((get_options & PCRE_BSR_ANYCRLF) != 0)? " bsr_anycrlf" : "", - ((get_options & PCRE_BSR_UNICODE) != 0)? " bsr_unicode" : "", - ((get_options & PCRE_DOLLAR_ENDONLY) != 0)? " dollar_endonly" : "", - ((get_options & PCRE_EXTRA) != 0)? " extra" : "", - ((get_options & PCRE_UNGREEDY) != 0)? " ungreedy" : "", - ((get_options & PCRE_NO_AUTO_CAPTURE) != 0)? " no_auto_capture" : "", - ((get_options & PCRE_NO_AUTO_POSSESS) != 0)? " no_auto_possessify" : "", - ((get_options & PCRE_UTF8) != 0)? " utf" : "", - ((get_options & PCRE_UCP) != 0)? " ucp" : "", - ((get_options & PCRE_NO_UTF8_CHECK) != 0)? " no_utf_check" : "", - ((get_options & PCRE_NO_START_OPTIMIZE) != 0)? " no_start_optimize" : "", - ((get_options & PCRE_DUPNAMES) != 0)? " dupnames" : "", - ((get_options & PCRE_NEVER_UTF) != 0)? " never_utf" : ""); - - if (jchanged) fprintf(outfile, "Duplicate name status changes\n"); - - switch (get_options & PCRE_NEWLINE_BITS) - { - case PCRE_NEWLINE_CR: - fprintf(outfile, "Forced newline sequence: CR\n"); - break; - - case PCRE_NEWLINE_LF: - fprintf(outfile, "Forced newline sequence: LF\n"); - break; - - case PCRE_NEWLINE_CRLF: - fprintf(outfile, "Forced newline sequence: CRLF\n"); - break; - - case PCRE_NEWLINE_ANYCRLF: - fprintf(outfile, "Forced newline sequence: ANYCRLF\n"); - break; - - case PCRE_NEWLINE_ANY: - fprintf(outfile, "Forced newline sequence: ANY\n"); - break; - - default: - break; - } - - if (first_char_set == 2) - { - fprintf(outfile, "First char at start or follows newline\n"); - } - else if (first_char_set == 1) - { - const char *caseless = - ((REAL_PCRE_FLAGS(re) & PCRE_FCH_CASELESS) == 0)? - "" : " (caseless)"; - - if (PRINTOK(first_char)) - fprintf(outfile, "First char = \'%c\'%s\n", first_char, caseless); - else - { - fprintf(outfile, "First char = "); - pchar(first_char, outfile); - fprintf(outfile, "%s\n", caseless); - } - } - else - { - fprintf(outfile, "No first char\n"); - } - - if (need_char_set == 0) - { - fprintf(outfile, "No need char\n"); - } - else - { - const char *caseless = - ((REAL_PCRE_FLAGS(re) & PCRE_RCH_CASELESS) == 0)? - "" : " (caseless)"; - - if (PRINTOK(need_char)) - fprintf(outfile, "Need char = \'%c\'%s\n", need_char, caseless); - else - { - fprintf(outfile, "Need char = "); - pchar(need_char, outfile); - fprintf(outfile, "%s\n", caseless); - } - } - - /* Don't output study size; at present it is in any case a fixed - value, but it varies, depending on the computer architecture, and - so messes up the test suite. (And with the /F option, it might be - flipped.) If study was forced by an external -s, don't show this - information unless -i or -d was also present. This means that, except - when auto-callouts are involved, the output from runs with and without - -s should be identical. */ - - if (do_study || (force_study >= 0 && showinfo && !no_force_study)) - { - if (extra == NULL) - fprintf(outfile, "Study returned NULL\n"); - else - { - pcre_uint8 *start_bits = NULL; - int minlength; - - if (new_info(re, extra, PCRE_INFO_MINLENGTH, &minlength) == 0) - fprintf(outfile, "Subject length lower bound = %d\n", minlength); - - if (new_info(re, extra, PCRE_INFO_FIRSTTABLE, &start_bits) == 0) - { - if (start_bits == NULL) - fprintf(outfile, "No starting char list\n"); - else - { - int i; - int c = 24; - fprintf(outfile, "Starting chars: "); - for (i = 0; i < 256; i++) - { - if ((start_bits[i/8] & (1<<(i&7))) != 0) - { - if (c > 75) - { - fprintf(outfile, "\n "); - c = 2; - } - if (PRINTOK(i) && i != ' ') - { - fprintf(outfile, "%c ", i); - c += 2; - } - else - { - fprintf(outfile, "\\x%02x ", i); - c += 5; - } - } - } - fprintf(outfile, "\n"); - } - } - } - - /* Show this only if the JIT was set by /S, not by -s. */ - - if ((study_options & PCRE_STUDY_ALLJIT) != 0 && - (force_study_options & PCRE_STUDY_ALLJIT) == 0) - { - int jit; - if (new_info(re, extra, PCRE_INFO_JIT, &jit) == 0) - { - if (jit) - fprintf(outfile, "JIT study was successful\n"); - else -#ifdef SUPPORT_JIT - fprintf(outfile, "JIT study was not successful\n"); -#else - fprintf(outfile, "JIT support is not available in this version of PCRE\n"); -#endif - } - } - } - } - - /* If the '>' option was present, we write out the regex to a file, and - that is all. The first 8 bytes of the file are the regex length and then - the study length, in big-endian order. */ - - if (to_file != NULL) - { - FILE *f = fopen((char *)to_file, "wb"); - if (f == NULL) - { - fprintf(outfile, "Unable to open %s: %s\n", to_file, strerror(errno)); - } - else - { - pcre_uint8 sbuf[8]; - - if (do_flip) regexflip(re, extra); - sbuf[0] = (pcre_uint8)((true_size >> 24) & 255); - sbuf[1] = (pcre_uint8)((true_size >> 16) & 255); - sbuf[2] = (pcre_uint8)((true_size >> 8) & 255); - sbuf[3] = (pcre_uint8)((true_size) & 255); - sbuf[4] = (pcre_uint8)((true_study_size >> 24) & 255); - sbuf[5] = (pcre_uint8)((true_study_size >> 16) & 255); - sbuf[6] = (pcre_uint8)((true_study_size >> 8) & 255); - sbuf[7] = (pcre_uint8)((true_study_size) & 255); - - if (fwrite(sbuf, 1, 8, f) < 8 || - fwrite(re, 1, true_size, f) < true_size) - { - fprintf(outfile, "Write error on %s: %s\n", to_file, strerror(errno)); - } - else - { - fprintf(outfile, "Compiled pattern written to %s\n", to_file); - - /* If there is study data, write it. */ - - if (extra != NULL) - { - if (fwrite(extra->study_data, 1, true_study_size, f) < - true_study_size) - { - fprintf(outfile, "Write error on %s: %s\n", to_file, - strerror(errno)); - } - else fprintf(outfile, "Study data written to %s\n", to_file); - } - } - fclose(f); - } - - new_free(re); - if (extra != NULL) - { - PCRE_FREE_STUDY(extra); - } - if (locale_set) - { - new_free((void *)tables); - setlocale(LC_CTYPE, "C"); - locale_set = 0; - } - continue; /* With next regex */ - } - } /* End of non-POSIX compile */ - - /* Read data lines and test them */ - - for (;;) - { -#ifdef SUPPORT_PCRE8 - pcre_uint8 *q8; -#endif -#ifdef SUPPORT_PCRE16 - pcre_uint16 *q16; -#endif -#ifdef SUPPORT_PCRE32 - pcre_uint32 *q32; -#endif - pcre_uint8 *bptr; - int *use_offsets = offsets; - int use_size_offsets = size_offsets; - int callout_data = 0; - int callout_data_set = 0; - int count; - pcre_uint32 c; - int copystrings = 0; - int find_match_limit = default_find_match_limit; - int getstrings = 0; - int getlist = 0; - int gmatched = 0; - int start_offset = 0; - int start_offset_sign = 1; - int g_notempty = 0; - int use_dfa = 0; - - *copynames = 0; - *getnames = 0; - -#ifdef SUPPORT_PCRE32 - cn32ptr = copynames; - gn32ptr = getnames; -#endif -#ifdef SUPPORT_PCRE16 - cn16ptr = copynames16; - gn16ptr = getnames16; -#endif -#ifdef SUPPORT_PCRE8 - cn8ptr = copynames8; - gn8ptr = getnames8; -#endif - - SET_PCRE_CALLOUT(callout); - first_callout = 1; - last_callout_mark = NULL; - callout_extra = 0; - callout_count = 0; - callout_fail_count = 999999; - callout_fail_id = -1; - show_malloc = 0; - options = 0; - - if (extra != NULL) extra->flags &= - ~(PCRE_EXTRA_MATCH_LIMIT|PCRE_EXTRA_MATCH_LIMIT_RECURSION); - - len = 0; - for (;;) - { - if (extend_inputline(infile, buffer + len, "data> ") == NULL) - { - if (len > 0) /* Reached EOF without hitting a newline */ - { - fprintf(outfile, "\n"); - break; - } - done = 1; - goto CONTINUE; - } - if (infile != stdin) fprintf(outfile, "%s", (char *)buffer); - len = (int)strlen((char *)buffer); - if (buffer[len-1] == '\n') break; - } - - while (len > 0 && isspace(buffer[len-1])) len--; - buffer[len] = 0; - if (len == 0) break; - - p = buffer; - while (isspace(*p)) p++; - -#ifndef NOUTF - /* Check that the data is well-formed UTF-8 if we're in UTF mode. To create - invalid input to pcre_exec, you must use \x?? or \x{} sequences. */ - - if (use_utf) - { - pcre_uint8 *q; - pcre_uint32 cc; - int n = 1; - - for (q = p; n > 0 && *q; q += n) n = utf82ord(q, &cc); - if (n <= 0) - { - fprintf(outfile, "**Failed: invalid UTF-8 string cannot be used as input in UTF mode\n"); - goto NEXT_DATA; - } - } -#endif - -#ifdef SUPPORT_VALGRIND - /* Mark the dbuffer as addressable but undefined again. */ - - if (dbuffer != NULL) - { - VALGRIND_MAKE_MEM_UNDEFINED(dbuffer, dbuffer_size * CHAR_SIZE); - } -#endif - - /* Allocate a buffer to hold the data line; len+1 is an upper bound on - the number of pcre_uchar units that will be needed. */ - - while (dbuffer == NULL || (size_t)len >= dbuffer_size) - { - dbuffer_size *= 2; - dbuffer = (pcre_uint8 *)realloc(dbuffer, dbuffer_size * CHAR_SIZE); - if (dbuffer == NULL) - { - fprintf(stderr, "pcretest: realloc(%d) failed\n", (int)dbuffer_size); - exit(1); - } - } - -#ifdef SUPPORT_PCRE8 - q8 = (pcre_uint8 *) dbuffer; -#endif -#ifdef SUPPORT_PCRE16 - q16 = (pcre_uint16 *) dbuffer; -#endif -#ifdef SUPPORT_PCRE32 - q32 = (pcre_uint32 *) dbuffer; -#endif - - while ((c = *p++) != 0) - { - int i = 0; - int n = 0; - - /* In UTF mode, input can be UTF-8, so just copy all non-backslash bytes. - In non-UTF mode, allow the value of the byte to fall through to later, - where values greater than 127 are turned into UTF-8 when running in - 16-bit or 32-bit mode. */ - - if (c != '\\') - { -#ifndef NOUTF - if (use_utf && HASUTF8EXTRALEN(c)) { GETUTF8INC(c, p); } -#endif - } - - /* Handle backslash escapes */ - - else switch ((c = *p++)) - { - case 'a': c = CHAR_BEL; break; - case 'b': c = '\b'; break; - case 'e': c = CHAR_ESC; break; - case 'f': c = '\f'; break; - case 'n': c = '\n'; break; - case 'r': c = '\r'; break; - case 't': c = '\t'; break; - case 'v': c = '\v'; break; - - case '0': case '1': case '2': case '3': - case '4': case '5': case '6': case '7': - c -= '0'; - while (i++ < 2 && isdigit(*p) && *p != '8' && *p != '9') - c = c * 8 + *p++ - '0'; - break; - - case 'o': - if (*p == '{') - { - pcre_uint8 *pt = p; - c = 0; - for (pt++; isdigit(*pt) && *pt != '8' && *pt != '9'; pt++) - { - if (++i == 12) - fprintf(outfile, "** Too many octal digits in \\o{...} item; " - "using only the first twelve.\n"); - else c = c * 8 + *pt - '0'; - } - if (*pt == '}') p = pt + 1; - else fprintf(outfile, "** Missing } after \\o{ (assumed)\n"); - } - break; - - case 'x': - if (*p == '{') - { - pcre_uint8 *pt = p; - c = 0; - - /* We used to have "while (isxdigit(*(++pt)))" here, but it fails - when isxdigit() is a macro that refers to its argument more than - once. This is banned by the C Standard, but apparently happens in at - least one MacOS environment. */ - - for (pt++; isxdigit(*pt); pt++) - { - if (++i == 9) - fprintf(outfile, "** Too many hex digits in \\x{...} item; " - "using only the first eight.\n"); - else c = c * 16 + tolower(*pt) - ((isdigit(*pt))? '0' : 'a' - 10); - } - if (*pt == '}') - { - p = pt + 1; - break; - } - /* Not correct form for \x{...}; fall through */ - } - - /* \x without {} always defines just one byte in 8-bit mode. This - allows UTF-8 characters to be constructed byte by byte, and also allows - invalid UTF-8 sequences to be made. Just copy the byte in UTF mode. - Otherwise, pass it down to later code so that it can be turned into - UTF-8 when running in 16/32-bit mode. */ - - c = 0; - while (i++ < 2 && isxdigit(*p)) - { - c = c * 16 + tolower(*p) - ((isdigit(*p))? '0' : 'a' - 10); - p++; - } -#if !defined NOUTF && defined SUPPORT_PCRE8 - if (use_utf && (pcre_mode == PCRE8_MODE)) - { - *q8++ = c; - continue; - } -#endif - break; - - case 0: /* \ followed by EOF allows for an empty line */ - p--; - continue; - - case '>': - if (*p == '-') - { - start_offset_sign = -1; - p++; - } - while(isdigit(*p)) start_offset = start_offset * 10 + *p++ - '0'; - start_offset *= start_offset_sign; - continue; - - case 'A': /* Option setting */ - options |= PCRE_ANCHORED; - continue; - - case 'B': - options |= PCRE_NOTBOL; - continue; - - case 'C': - if (isdigit(*p)) /* Set copy string */ - { - while(isdigit(*p)) n = n * 10 + *p++ - '0'; - copystrings |= 1 << n; - } - else if (isalnum(*p)) - { - READ_CAPTURE_NAME(p, &cn8ptr, &cn16ptr, &cn32ptr, re); - } - else if (*p == '+') - { - callout_extra = 1; - p++; - } - else if (*p == '-') - { - SET_PCRE_CALLOUT(NULL); - p++; - } - else if (*p == '!') - { - callout_fail_id = 0; - p++; - while(isdigit(*p)) - callout_fail_id = callout_fail_id * 10 + *p++ - '0'; - callout_fail_count = 0; - if (*p == '!') - { - p++; - while(isdigit(*p)) - callout_fail_count = callout_fail_count * 10 + *p++ - '0'; - } - } - else if (*p == '*') - { - int sign = 1; - callout_data = 0; - if (*(++p) == '-') { sign = -1; p++; } - while(isdigit(*p)) - callout_data = callout_data * 10 + *p++ - '0'; - callout_data *= sign; - callout_data_set = 1; - } - continue; - -#if !defined NODFA - case 'D': -#if !defined NOPOSIX - if (posix || do_posix) - printf("** Can't use dfa matching in POSIX mode: \\D ignored\n"); - else -#endif - use_dfa = 1; - continue; -#endif - -#if !defined NODFA - case 'F': - options |= PCRE_DFA_SHORTEST; - continue; -#endif - - case 'G': - if (isdigit(*p)) - { - while(isdigit(*p)) n = n * 10 + *p++ - '0'; - getstrings |= 1 << n; - } - else if (isalnum(*p)) - { - READ_CAPTURE_NAME(p, &gn8ptr, &gn16ptr, &gn32ptr, re); - } - continue; - - case 'J': - while(isdigit(*p)) n = n * 10 + *p++ - '0'; - if (extra != NULL - && (extra->flags & PCRE_EXTRA_EXECUTABLE_JIT) != 0 - && extra->executable_jit != NULL) - { - if (jit_stack != NULL) { PCRE_JIT_STACK_FREE(jit_stack); } - jit_stack = PCRE_JIT_STACK_ALLOC(1, n * 1024); - PCRE_ASSIGN_JIT_STACK(extra, jit_callback, jit_stack); - } - continue; - - case 'L': - getlist = 1; - continue; - - case 'M': - find_match_limit = 1; - continue; - - case 'N': - if ((options & PCRE_NOTEMPTY) != 0) - options = (options & ~PCRE_NOTEMPTY) | PCRE_NOTEMPTY_ATSTART; - else - options |= PCRE_NOTEMPTY; - continue; - - case 'O': - while(isdigit(*p)) n = n * 10 + *p++ - '0'; - if (n > size_offsets_max) - { - size_offsets_max = n; - free(offsets); - use_offsets = offsets = (int *)malloc(size_offsets_max * sizeof(int)); - if (offsets == NULL) - { - printf("** Failed to get %d bytes of memory for offsets vector\n", - (int)(size_offsets_max * sizeof(int))); - yield = 1; - goto EXIT; - } - } - use_size_offsets = n; - if (n == 0) use_offsets = NULL; /* Ensures it can't write to it */ - else use_offsets = offsets + size_offsets_max - n; /* To catch overruns */ - continue; - - case 'P': - options |= ((options & PCRE_PARTIAL_SOFT) == 0)? - PCRE_PARTIAL_SOFT : PCRE_PARTIAL_HARD; - continue; - - case 'Q': - while(isdigit(*p)) n = n * 10 + *p++ - '0'; - if (extra == NULL) - { - extra = (pcre_extra *)malloc(sizeof(pcre_extra)); - extra->flags = 0; - } - extra->flags |= PCRE_EXTRA_MATCH_LIMIT_RECURSION; - extra->match_limit_recursion = n; - continue; - - case 'q': - while(isdigit(*p)) n = n * 10 + *p++ - '0'; - if (extra == NULL) - { - extra = (pcre_extra *)malloc(sizeof(pcre_extra)); - extra->flags = 0; - } - extra->flags |= PCRE_EXTRA_MATCH_LIMIT; - extra->match_limit = n; - continue; - -#if !defined NODFA - case 'R': - options |= PCRE_DFA_RESTART; - continue; -#endif - - case 'S': - show_malloc = 1; - continue; - - case 'Y': - options |= PCRE_NO_START_OPTIMIZE; - continue; - - case 'Z': - options |= PCRE_NOTEOL; - continue; - - case '?': - options |= PCRE_NO_UTF8_CHECK; - continue; - - case '<': - { - int x = check_mc_option(p, outfile, TRUE, "escape sequence"); - if (x == 0) goto NEXT_DATA; - options |= x; - while (*p++ != '>'); - } - continue; - } - - /* We now have a character value in c that may be greater than 255. - In 8-bit mode we convert to UTF-8 if we are in UTF mode. Values greater - than 127 in UTF mode must have come from \x{...} or octal constructs - because values from \x.. get this far only in non-UTF mode. */ - -#ifdef SUPPORT_PCRE8 - if (pcre_mode == PCRE8_MODE) - { -#ifndef NOUTF - if (use_utf) - { - if (c > 0x7fffffff) - { - fprintf(outfile, "** Character \\x{%x} is greater than 0x7fffffff " - "and so cannot be converted to UTF-8\n", c); - goto NEXT_DATA; - } - q8 += ord2utf8(c, q8); - } - else -#endif - { - if (c > 0xffu) - { - fprintf(outfile, "** Character \\x{%x} is greater than 255 " - "and UTF-8 mode is not enabled.\n", c); - fprintf(outfile, "** Truncation will probably give the wrong " - "result.\n"); - } - *q8++ = c; - } - } -#endif -#ifdef SUPPORT_PCRE16 - if (pcre_mode == PCRE16_MODE) - { -#ifndef NOUTF - if (use_utf) - { - if (c > 0x10ffffu) - { - fprintf(outfile, "** Failed: character \\x{%x} is greater than " - "0x10ffff and so cannot be converted to UTF-16\n", c); - goto NEXT_DATA; - } - else if (c >= 0x10000u) - { - c-= 0x10000u; - *q16++ = 0xD800 | (c >> 10); - *q16++ = 0xDC00 | (c & 0x3ff); - } - else - *q16++ = c; - } - else -#endif - { - if (c > 0xffffu) - { - fprintf(outfile, "** Character \\x{%x} is greater than 0xffff " - "and UTF-16 mode is not enabled.\n", c); - fprintf(outfile, "** Truncation will probably give the wrong " - "result.\n"); - } - - *q16++ = c; - } - } -#endif -#ifdef SUPPORT_PCRE32 - if (pcre_mode == PCRE32_MODE) - { - *q32++ = c; - } -#endif - - } - - /* Reached end of subject string */ - -#ifdef SUPPORT_PCRE8 - if (pcre_mode == PCRE8_MODE) - { - *q8 = 0; - len = (int)(q8 - (pcre_uint8 *)dbuffer); - } -#endif -#ifdef SUPPORT_PCRE16 - if (pcre_mode == PCRE16_MODE) - { - *q16 = 0; - len = (int)(q16 - (pcre_uint16 *)dbuffer); - } -#endif -#ifdef SUPPORT_PCRE32 - if (pcre_mode == PCRE32_MODE) - { - *q32 = 0; - len = (int)(q32 - (pcre_uint32 *)dbuffer); - } -#endif - - /* If we're compiling with explicit valgrind support, Mark the data from after - its end to the end of the buffer as unaddressable, so that a read over the end - of the buffer will be seen by valgrind, even if it doesn't cause a crash. - If we're not building with valgrind support, at least move the data to the end - of the buffer so that it might at least cause a crash. - If we are using the POSIX interface, we must include the terminating zero. */ - - bptr = dbuffer; - -#if !defined NOPOSIX - if (posix || do_posix) - { -#ifdef SUPPORT_VALGRIND - VALGRIND_MAKE_MEM_NOACCESS(dbuffer + len + 1, dbuffer_size - (len + 1)); -#else - memmove(bptr + dbuffer_size - len - 1, bptr, len + 1); - bptr += dbuffer_size - len - 1; -#endif - } - else -#endif - { -#ifdef SUPPORT_VALGRIND - VALGRIND_MAKE_MEM_NOACCESS(dbuffer + len * CHAR_SIZE, (dbuffer_size - len) * CHAR_SIZE); -#else - bptr = memmove(bptr + (dbuffer_size - len) * CHAR_SIZE, bptr, len * CHAR_SIZE); -#endif - } - - if ((all_use_dfa || use_dfa) && find_match_limit) - { - printf("**Match limit not relevant for DFA matching: ignored\n"); - find_match_limit = 0; - } - - /* Handle matching via the POSIX interface, which does not - support timing or playing with the match limit or callout data. */ - -#if !defined NOPOSIX - if (posix || do_posix) - { - int rc; - int eflags = 0; - regmatch_t *pmatch = NULL; - if (use_size_offsets > 0) - pmatch = (regmatch_t *)malloc(sizeof(regmatch_t) * use_size_offsets); - if ((options & PCRE_NOTBOL) != 0) eflags |= REG_NOTBOL; - if ((options & PCRE_NOTEOL) != 0) eflags |= REG_NOTEOL; - if ((options & PCRE_NOTEMPTY) != 0) eflags |= REG_NOTEMPTY; - - rc = regexec(&preg, (const char *)bptr, use_size_offsets, pmatch, eflags); - - if (rc != 0) - { - (void)regerror(rc, &preg, (char *)buffer, buffer_size); - fprintf(outfile, "No match: POSIX code %d: %s\n", rc, buffer); - } - else if ((REAL_PCRE_OPTIONS(preg.re_pcre) & PCRE_NO_AUTO_CAPTURE) != 0) - { - fprintf(outfile, "Matched with REG_NOSUB\n"); - } - else - { - size_t i; - for (i = 0; i < (size_t)use_size_offsets; i++) - { - if (pmatch[i].rm_so >= 0) - { - fprintf(outfile, "%2d: ", (int)i); - PCHARSV(dbuffer, pmatch[i].rm_so, - pmatch[i].rm_eo - pmatch[i].rm_so, outfile); - fprintf(outfile, "\n"); - if (do_showcaprest || (i == 0 && do_showrest)) - { - fprintf(outfile, "%2d+ ", (int)i); - PCHARSV(dbuffer, pmatch[i].rm_eo, len - pmatch[i].rm_eo, - outfile); - fprintf(outfile, "\n"); - } - } - } - } - free(pmatch); - goto NEXT_DATA; - } - -#endif /* !defined NOPOSIX */ - - /* Handle matching via the native interface - repeats for /g and /G */ - - /* Ensure that there is a JIT callback if we want to verify that JIT was - actually used. If jit_stack == NULL, no stack has yet been assigned. */ - - if (verify_jit && jit_stack == NULL && extra != NULL) - { PCRE_ASSIGN_JIT_STACK(extra, jit_callback, jit_stack); } - - for (;; gmatched++) /* Loop for /g or /G */ - { - markptr = NULL; - jit_was_used = FALSE; - - if (timeitm > 0) - { - register int i; - clock_t time_taken; - clock_t start_time = clock(); - -#if !defined NODFA - if (all_use_dfa || use_dfa) - { - if ((options & PCRE_DFA_RESTART) != 0) - { - fprintf(outfile, "Timing DFA restarts is not supported\n"); - break; - } - if (dfa_workspace == NULL) - dfa_workspace = (int *)malloc(DFA_WS_DIMENSION*sizeof(int)); - for (i = 0; i < timeitm; i++) - { - PCRE_DFA_EXEC(count, re, extra, bptr, len, start_offset, - (options | g_notempty), use_offsets, use_size_offsets, - dfa_workspace, DFA_WS_DIMENSION); - } - } - else -#endif - - for (i = 0; i < timeitm; i++) - { - PCRE_EXEC(count, re, extra, bptr, len, start_offset, - (options | g_notempty), use_offsets, use_size_offsets); - } - total_match_time += (time_taken = clock() - start_time); - fprintf(outfile, "Execute time %.4f milliseconds\n", - (((double)time_taken * 1000.0) / (double)timeitm) / - (double)CLOCKS_PER_SEC); - } - - /* If find_match_limit is set, we want to do repeated matches with - varying limits in order to find the minimum value for the match limit and - for the recursion limit. The match limits are relevant only to the normal - running of pcre_exec(), so disable the JIT optimization. This makes it - possible to run the same set of tests with and without JIT externally - requested. */ - - if (find_match_limit) - { - if (extra != NULL) { PCRE_FREE_STUDY(extra); } - extra = (pcre_extra *)malloc(sizeof(pcre_extra)); - extra->flags = 0; - - (void)check_match_limit(re, extra, bptr, len, start_offset, - options|g_notempty, use_offsets, use_size_offsets, - PCRE_EXTRA_MATCH_LIMIT, &(extra->match_limit), - PCRE_ERROR_MATCHLIMIT, "match()"); - - count = check_match_limit(re, extra, bptr, len, start_offset, - options|g_notempty, use_offsets, use_size_offsets, - PCRE_EXTRA_MATCH_LIMIT_RECURSION, &(extra->match_limit_recursion), - PCRE_ERROR_RECURSIONLIMIT, "match() recursion"); - } - - /* If callout_data is set, use the interface with additional data */ - - else if (callout_data_set) - { - if (extra == NULL) - { - extra = (pcre_extra *)malloc(sizeof(pcre_extra)); - extra->flags = 0; - } - extra->flags |= PCRE_EXTRA_CALLOUT_DATA; - extra->callout_data = &callout_data; - PCRE_EXEC(count, re, extra, bptr, len, start_offset, - options | g_notempty, use_offsets, use_size_offsets); - extra->flags &= ~PCRE_EXTRA_CALLOUT_DATA; - } - - /* The normal case is just to do the match once, with the default - value of match_limit. */ - -#if !defined NODFA - else if (all_use_dfa || use_dfa) - { - if (dfa_workspace == NULL) - dfa_workspace = (int *)malloc(DFA_WS_DIMENSION*sizeof(int)); - if (dfa_matched++ == 0) - dfa_workspace[0] = -1; /* To catch bad restart */ - PCRE_DFA_EXEC(count, re, extra, bptr, len, start_offset, - (options | g_notempty), use_offsets, use_size_offsets, dfa_workspace, - DFA_WS_DIMENSION); - if (count == 0) - { - fprintf(outfile, "Matched, but offsets vector is too small to show all matches\n"); - count = use_size_offsets/2; - } - } -#endif - - else - { - PCRE_EXEC(count, re, extra, bptr, len, start_offset, - options | g_notempty, use_offsets, use_size_offsets); - if (count == 0) - { - fprintf(outfile, "Matched, but too many substrings\n"); - /* 2 is a special case; match can be returned */ - count = (use_size_offsets == 2)? 1 : use_size_offsets/3; - } - } - - /* Matched */ - - if (count >= 0) - { - int i, maxcount; - void *cnptr, *gnptr; - -#if !defined NODFA - if (all_use_dfa || use_dfa) maxcount = use_size_offsets/2; else -#endif - /* 2 is a special case; match can be returned */ - maxcount = (use_size_offsets == 2)? 1 : use_size_offsets/3; - - /* This is a check against a lunatic return value. */ - - if (count > maxcount) - { - fprintf(outfile, - "** PCRE error: returned count %d is too big for offset size %d\n", - count, use_size_offsets); - count = use_size_offsets/3; - if (do_g || do_G) - { - fprintf(outfile, "** /%c loop abandoned\n", do_g? 'g' : 'G'); - do_g = do_G = FALSE; /* Break g/G loop */ - } - } - - /* do_allcaps requests showing of all captures in the pattern, to check - unset ones at the end. */ - - if (do_allcaps) - { - if (new_info(re, NULL, PCRE_INFO_CAPTURECOUNT, &count) < 0) - goto SKIP_DATA; - count++; /* Allow for full match */ - if (count * 2 > use_size_offsets) count = use_size_offsets/2; - } - - /* Output the captured substrings. Note that, for the matched string, - the use of \K in an assertion can make the start later than the end. */ - - for (i = 0; i < count * 2; i += 2) - { - if (use_offsets[i] < 0) - { - if (use_offsets[i] != -1) - fprintf(outfile, "ERROR: bad negative value %d for offset %d\n", - use_offsets[i], i); - if (use_offsets[i+1] != -1) - fprintf(outfile, "ERROR: bad negative value %d for offset %d\n", - use_offsets[i+1], i+1); - fprintf(outfile, "%2d: <unset>\n", i/2); - } - else - { - int start = use_offsets[i]; - int end = use_offsets[i+1]; - - if (start > end) - { - start = use_offsets[i+1]; - end = use_offsets[i]; - fprintf(outfile, "Start of matched string is beyond its end - " - "displaying from end to start.\n"); - } - - fprintf(outfile, "%2d: ", i/2); - PCHARSV(bptr, start, end - start, outfile); - if (verify_jit && jit_was_used) fprintf(outfile, " (JIT)"); - fprintf(outfile, "\n"); - - /* Note: don't use the start/end variables here because we want to - show the text from what is reported as the end. */ - - if (do_showcaprest || (i == 0 && do_showrest)) - { - fprintf(outfile, "%2d+ ", i/2); - PCHARSV(bptr, use_offsets[i+1], len - use_offsets[i+1], - outfile); - fprintf(outfile, "\n"); - } - } - } - - if (markptr != NULL) - { - fprintf(outfile, "MK: "); - PCHARSV(markptr, 0, -1, outfile); - fprintf(outfile, "\n"); - } - - for (i = 0; i < 32; i++) - { - if ((copystrings & (1 << i)) != 0) - { - int rc; - char copybuffer[256]; - PCRE_COPY_SUBSTRING(rc, bptr, use_offsets, count, i, - copybuffer, sizeof(copybuffer)); - if (rc < 0) - fprintf(outfile, "copy substring %d failed %d\n", i, rc); - else - { - fprintf(outfile, "%2dC ", i); - PCHARSV(copybuffer, 0, rc, outfile); - fprintf(outfile, " (%d)\n", rc); - } - } - } - - cnptr = copynames; - for (;;) - { - int rc; - char copybuffer[256]; - -#ifdef SUPPORT_PCRE32 - if (pcre_mode == PCRE32_MODE) - { - if (*(pcre_uint32 *)cnptr == 0) break; - } -#endif -#ifdef SUPPORT_PCRE16 - if (pcre_mode == PCRE16_MODE) - { - if (*(pcre_uint16 *)cnptr == 0) break; - } -#endif -#ifdef SUPPORT_PCRE8 - if (pcre_mode == PCRE8_MODE) - { - if (*(pcre_uint8 *)cnptr == 0) break; - } -#endif - - PCRE_COPY_NAMED_SUBSTRING(rc, re, bptr, use_offsets, count, - cnptr, copybuffer, sizeof(copybuffer)); - - if (rc < 0) - { - fprintf(outfile, "copy substring "); - PCHARSV(cnptr, 0, -1, outfile); - fprintf(outfile, " failed %d\n", rc); - } - else - { - fprintf(outfile, " C "); - PCHARSV(copybuffer, 0, rc, outfile); - fprintf(outfile, " (%d) ", rc); - PCHARSV(cnptr, 0, -1, outfile); - putc('\n', outfile); - } - - cnptr = (char *)cnptr + (STRLEN(cnptr) + 1) * CHAR_SIZE; - } - - for (i = 0; i < 32; i++) - { - if ((getstrings & (1 << i)) != 0) - { - int rc; - const char *substring; - PCRE_GET_SUBSTRING(rc, bptr, use_offsets, count, i, &substring); - if (rc < 0) - fprintf(outfile, "get substring %d failed %d\n", i, rc); - else - { - fprintf(outfile, "%2dG ", i); - PCHARSV(substring, 0, rc, outfile); - fprintf(outfile, " (%d)\n", rc); - PCRE_FREE_SUBSTRING(substring); - } - } - } - - gnptr = getnames; - for (;;) - { - int rc; - const char *substring; - -#ifdef SUPPORT_PCRE32 - if (pcre_mode == PCRE32_MODE) - { - if (*(pcre_uint32 *)gnptr == 0) break; - } -#endif -#ifdef SUPPORT_PCRE16 - if (pcre_mode == PCRE16_MODE) - { - if (*(pcre_uint16 *)gnptr == 0) break; - } -#endif -#ifdef SUPPORT_PCRE8 - if (pcre_mode == PCRE8_MODE) - { - if (*(pcre_uint8 *)gnptr == 0) break; - } -#endif - - PCRE_GET_NAMED_SUBSTRING(rc, re, bptr, use_offsets, count, - gnptr, &substring); - if (rc < 0) - { - fprintf(outfile, "get substring "); - PCHARSV(gnptr, 0, -1, outfile); - fprintf(outfile, " failed %d\n", rc); - } - else - { - fprintf(outfile, " G "); - PCHARSV(substring, 0, rc, outfile); - fprintf(outfile, " (%d) ", rc); - PCHARSV(gnptr, 0, -1, outfile); - PCRE_FREE_SUBSTRING(substring); - putc('\n', outfile); - } - - gnptr = (char *)gnptr + (STRLEN(gnptr) + 1) * CHAR_SIZE; - } - - if (getlist) - { - int rc; - const char **stringlist; - PCRE_GET_SUBSTRING_LIST(rc, bptr, use_offsets, count, &stringlist); - if (rc < 0) - fprintf(outfile, "get substring list failed %d\n", rc); - else - { - for (i = 0; i < count; i++) - { - fprintf(outfile, "%2dL ", i); - PCHARSV(stringlist[i], 0, -1, outfile); - putc('\n', outfile); - } - if (stringlist[i] != NULL) - fprintf(outfile, "string list not terminated by NULL\n"); - PCRE_FREE_SUBSTRING_LIST(stringlist); - } - } - } - - /* There was a partial match. If the bumpalong point is not the same as - the first inspected character, show the offset explicitly. */ - - else if (count == PCRE_ERROR_PARTIAL) - { - fprintf(outfile, "Partial match"); - if (use_size_offsets > 2 && use_offsets[0] != use_offsets[2]) - fprintf(outfile, " at offset %d", use_offsets[2]); - if (markptr != NULL) - { - fprintf(outfile, ", mark="); - PCHARSV(markptr, 0, -1, outfile); - } - if (use_size_offsets > 1) - { - fprintf(outfile, ": "); - PCHARSV(bptr, use_offsets[0], use_offsets[1] - use_offsets[0], - outfile); - } - if (verify_jit && jit_was_used) fprintf(outfile, " (JIT)"); - fprintf(outfile, "\n"); - break; /* Out of the /g loop */ - } - - /* Failed to match. If this is a /g or /G loop and we previously set - g_notempty after a null match, this is not necessarily the end. We want - to advance the start offset, and continue. We won't be at the end of the - string - that was checked before setting g_notempty. - - Complication arises in the case when the newline convention is "any", - "crlf", or "anycrlf". If the previous match was at the end of a line - terminated by CRLF, an advance of one character just passes the \r, - whereas we should prefer the longer newline sequence, as does the code in - pcre_exec(). Fudge the offset value to achieve this. We check for a - newline setting in the pattern; if none was set, use PCRE_CONFIG() to - find the default. - - Otherwise, in the case of UTF-8 matching, the advance must be one - character, not one byte. */ - - else - { - if (g_notempty != 0) - { - int onechar = 1; - unsigned int obits = REAL_PCRE_OPTIONS(re); - use_offsets[0] = start_offset; - if ((obits & PCRE_NEWLINE_BITS) == 0) - { - int d; - (void)PCRE_CONFIG(PCRE_CONFIG_NEWLINE, &d); - /* Note that these values are always the ASCII ones, even in - EBCDIC environments. CR = 13, NL = 10. */ - obits = (d == 13)? PCRE_NEWLINE_CR : - (d == 10)? PCRE_NEWLINE_LF : - (d == (13<<8 | 10))? PCRE_NEWLINE_CRLF : - (d == -2)? PCRE_NEWLINE_ANYCRLF : - (d == -1)? PCRE_NEWLINE_ANY : 0; - } - if (((obits & PCRE_NEWLINE_BITS) == PCRE_NEWLINE_ANY || - (obits & PCRE_NEWLINE_BITS) == PCRE_NEWLINE_CRLF || - (obits & PCRE_NEWLINE_BITS) == PCRE_NEWLINE_ANYCRLF) - && - start_offset < len - 1 && ( -#ifdef SUPPORT_PCRE8 - (pcre_mode == PCRE8_MODE && - bptr[start_offset] == '\r' && - bptr[start_offset + 1] == '\n') || -#endif -#ifdef SUPPORT_PCRE16 - (pcre_mode == PCRE16_MODE && - ((PCRE_SPTR16)bptr)[start_offset] == '\r' && - ((PCRE_SPTR16)bptr)[start_offset + 1] == '\n') || -#endif -#ifdef SUPPORT_PCRE32 - (pcre_mode == PCRE32_MODE && - ((PCRE_SPTR32)bptr)[start_offset] == '\r' && - ((PCRE_SPTR32)bptr)[start_offset + 1] == '\n') || -#endif - 0)) - onechar++; - else if (use_utf) - { - while (start_offset + onechar < len) - { - if ((bptr[start_offset+onechar] & 0xc0) != 0x80) break; - onechar++; - } - } - use_offsets[1] = start_offset + onechar; - } - else - { - switch(count) - { - case PCRE_ERROR_NOMATCH: - if (gmatched == 0) - { - if (markptr == NULL) - { - fprintf(outfile, "No match"); - } - else - { - fprintf(outfile, "No match, mark = "); - PCHARSV(markptr, 0, -1, outfile); - } - if (verify_jit && jit_was_used) fprintf(outfile, " (JIT)"); - putc('\n', outfile); - } - break; - - case PCRE_ERROR_BADUTF8: - case PCRE_ERROR_SHORTUTF8: - fprintf(outfile, "Error %d (%s UTF-%d string)", count, - (count == PCRE_ERROR_BADUTF8)? "bad" : "short", - 8 * CHAR_SIZE); - if (use_size_offsets >= 2) - fprintf(outfile, " offset=%d reason=%d", use_offsets[0], - use_offsets[1]); - fprintf(outfile, "\n"); - break; - - case PCRE_ERROR_BADUTF8_OFFSET: - fprintf(outfile, "Error %d (bad UTF-%d offset)\n", count, - 8 * CHAR_SIZE); - break; - - default: - if (count < 0 && - (-count) < (int)(sizeof(errtexts)/sizeof(const char *))) - fprintf(outfile, "Error %d (%s)\n", count, errtexts[-count]); - else - fprintf(outfile, "Error %d (Unexpected value)\n", count); - break; - } - - break; /* Out of the /g loop */ - } - } - - /* If not /g or /G we are done */ - - if (!do_g && !do_G) break; - - if (use_offsets == NULL) - { - fprintf(outfile, "Cannot do global matching without an ovector\n"); - break; - } - - /* If we have matched an empty string, first check to see if we are at - the end of the subject. If so, the /g loop is over. Otherwise, mimic what - Perl's /g options does. This turns out to be rather cunning. First we set - PCRE_NOTEMPTY_ATSTART and PCRE_ANCHORED and try the match again at the - same point. If this fails (picked up above) we advance to the next - character. */ - - g_notempty = 0; - - if (use_offsets[0] == use_offsets[1]) - { - if (use_offsets[0] == len) break; - g_notempty = PCRE_NOTEMPTY_ATSTART | PCRE_ANCHORED; - } - - /* For /g, update the start offset, leaving the rest alone. There is a - tricky case when \K is used in a positive lookbehind assertion. This can - cause the end of the match to be less than or equal to the start offset. - In this case we restart at one past the start offset. This may return the - same match if the original start offset was bumped along during the - match, but eventually the new start offset will hit the actual start - offset. (In PCRE2 the true start offset is available, and this can be - done better. It is not worth doing more than making sure we do not loop - at this stage in the life of PCRE1.) */ - - if (do_g) - { - if (g_notempty == 0 && use_offsets[1] <= start_offset) - { - if (start_offset >= len) break; /* End of subject */ - start_offset++; - if (use_utf) - { - while (start_offset < len) - { - if ((bptr[start_offset] & 0xc0) != 0x80) break; - start_offset++; - } - } - } - else start_offset = use_offsets[1]; - } - - /* For /G, update the pointer and length */ - - else - { - bptr += use_offsets[1] * CHAR_SIZE; - len -= use_offsets[1]; - } - } /* End of loop for /g and /G */ - - NEXT_DATA: continue; - } /* End of loop for data lines */ - - CONTINUE: - -#if !defined NOPOSIX - if ((posix || do_posix) && preg.re_pcre != 0) regfree(&preg); -#endif - - if (re != NULL) new_free(re); - if (extra != NULL) - { - PCRE_FREE_STUDY(extra); - } - if (locale_set) - { - new_free((void *)tables); - setlocale(LC_CTYPE, "C"); - locale_set = 0; - } - if (jit_stack != NULL) - { - PCRE_JIT_STACK_FREE(jit_stack); - jit_stack = NULL; - } - } - -if (infile == stdin) fprintf(outfile, "\n"); - -if (showtotaltimes) - { - fprintf(outfile, "--------------------------------------\n"); - if (timeit > 0) - { - fprintf(outfile, "Total compile time %.4f milliseconds\n", - (((double)total_compile_time * 1000.0) / (double)timeit) / - (double)CLOCKS_PER_SEC); - fprintf(outfile, "Total study time %.4f milliseconds\n", - (((double)total_study_time * 1000.0) / (double)timeit) / - (double)CLOCKS_PER_SEC); - } - fprintf(outfile, "Total execute time %.4f milliseconds\n", - (((double)total_match_time * 1000.0) / (double)timeitm) / - (double)CLOCKS_PER_SEC); - } - -EXIT: - -if (infile != NULL && infile != stdin) fclose(infile); -if (outfile != NULL && outfile != stdout) fclose(outfile); - -free(buffer); -free(dbuffer); -free(pbuffer); -free(offsets); - -#ifdef SUPPORT_PCRE16 -if (buffer16 != NULL) free(buffer16); -#endif -#ifdef SUPPORT_PCRE32 -if (buffer32 != NULL) free(buffer32); -#endif - -#if !defined NODFA -if (dfa_workspace != NULL) - free(dfa_workspace); -#endif - -#if defined(__VMS) - yield = SS$_NORMAL; /* Return values via DCL symbols */ -#endif - -return yield; -} - -/* End of pcretest.c */ diff --git a/src/third_party/pcre-8.38/perltest.pl b/src/third_party/pcre-8.38/perltest.pl deleted file mode 100755 index 29b808b5293..00000000000 --- a/src/third_party/pcre-8.38/perltest.pl +++ /dev/null @@ -1,242 +0,0 @@ -#! /usr/bin/env perl - -# Program for testing regular expressions with perl to check that PCRE handles -# them the same. This version needs to have "use utf8" at the start for running -# the UTF-8 tests, but *not* for the other tests. The only way I've found for -# doing this is to cat this line in explicitly in the RunPerlTest script. I've -# also used this method to supply "require Encode" for the UTF-8 tests, so that -# the main test will still run where Encode is not installed. - -#use utf8; -#require Encode; - -# Function for turning a string into a string of printing chars. - -sub pchars { -my($t) = ""; - -if ($utf8) - { - @p = unpack('U*', $_[0]); - foreach $c (@p) - { - if ($c >= 32 && $c < 127) { $t .= chr $c; } - else { $t .= sprintf("\\x{%02x}", $c); - } - } - } -else - { - foreach $c (split(//, $_[0])) - { - if (ord $c >= 32 && ord $c < 127) { $t .= $c; } - else { $t .= sprintf("\\x%02x", ord $c); } - } - } - -$t; -} - - -# Read lines from named file or stdin and write to named file or stdout; lines -# consist of a regular expression, in delimiters and optionally followed by -# options, followed by a set of test data, terminated by an empty line. - -# Sort out the input and output files - -if (@ARGV > 0) - { - open(INFILE, "<$ARGV[0]") || die "Failed to open $ARGV[0]\n"; - $infile = "INFILE"; - } -else { $infile = "STDIN"; } - -if (@ARGV > 1) - { - open(OUTFILE, ">$ARGV[1]") || die "Failed to open $ARGV[1]\n"; - $outfile = "OUTFILE"; - } -else { $outfile = "STDOUT"; } - -printf($outfile "Perl $] Regular Expressions\n\n"); - -# Main loop - -NEXT_RE: -for (;;) - { - printf " re> " if $infile eq "STDIN"; - last if ! ($_ = <$infile>); - printf $outfile "$_" if $infile ne "STDIN"; - next if ($_ =~ /^\s*$/ || $_ =~ /^< forbid/); - - $pattern = $_; - - while ($pattern !~ /^\s*(.).*\1/s) - { - printf " > " if $infile eq "STDIN"; - last if ! ($_ = <$infile>); - printf $outfile "$_" if $infile ne "STDIN"; - $pattern .= $_; - } - - chomp($pattern); - $pattern =~ s/\s+$//; - - # The private /+ modifier means "print $' afterwards". - - $showrest = ($pattern =~ s/\+(?=[a-zA-Z]*$)//); - - # A doubled version is used by pcretest to print remainders after captures - - $pattern =~ s/\+(?=[a-zA-Z]*$)//; - - # Remove /8 from a UTF-8 pattern. - - $utf8 = $pattern =~ s/8(?=[a-zA-Z]*$)//; - - # Remove /J from a pattern with duplicate names. - - $pattern =~ s/J(?=[a-zA-Z]*$)//; - - # Remove /K from a pattern (asks pcretest to check MARK data) */ - - $pattern =~ s/K(?=[a-zA-Z]*$)//; - - # /W asks pcretest to set PCRE_UCP; change this to /u for Perl - - $pattern =~ s/W(?=[a-zA-Z]*$)/u/; - - # Remove /S or /SS from a pattern (asks pcretest to study or not to study) - - $pattern =~ s/S(?=[a-zA-Z]*$)//g; - - # Remove /Y and /O from a pattern (disable PCRE optimizations) - - $pattern =~ s/[YO](?=[a-zA-Z]*$)//; - - # Check that the pattern is valid - - eval "\$_ =~ ${pattern}"; - if ($@) - { - printf $outfile "Error: $@"; - if ($infile != "STDIN") - { - for (;;) - { - last if ! ($_ = <$infile>); - last if $_ =~ /^\s*$/; - } - } - next NEXT_RE; - } - - # If the /g modifier is present, we want to put a loop round the matching; - # otherwise just a single "if". - - $cmd = ($pattern =~ /g[a-z]*$/)? "while" : "if"; - - # If the pattern is actually the null string, Perl uses the most recently - # executed (and successfully compiled) regex is used instead. This is a - # nasty trap for the unwary! The PCRE test suite does contain null strings - # in places - if they are allowed through here all sorts of weird and - # unexpected effects happen. To avoid this, we replace such patterns with - # a non-null pattern that has the same effect. - - $pattern = "/(?#)/$2" if ($pattern =~ /^(.)\1(.*)$/); - - # Read data lines and test them - - for (;;) - { - printf "data> " if $infile eq "STDIN"; - last NEXT_RE if ! ($_ = <$infile>); - chomp; - printf $outfile "$_\n" if $infile ne "STDIN"; - - s/\s+$//; # Remove trailing space - s/^\s+//; # Remove leading space - s/\\Y//g; # Remove \Y (pcretest flag to set PCRE_NO_START_OPTIMIZE) - - last if ($_ eq ""); - $x = eval "\"$_\""; # To get escapes processed - - # Empty array for holding results, ensure $REGERROR and $REGMARK are - # unset, then do the matching. - - @subs = (); - - $pushes = "push \@subs,\$&;" . - "push \@subs,\$1;" . - "push \@subs,\$2;" . - "push \@subs,\$3;" . - "push \@subs,\$4;" . - "push \@subs,\$5;" . - "push \@subs,\$6;" . - "push \@subs,\$7;" . - "push \@subs,\$8;" . - "push \@subs,\$9;" . - "push \@subs,\$10;" . - "push \@subs,\$11;" . - "push \@subs,\$12;" . - "push \@subs,\$13;" . - "push \@subs,\$14;" . - "push \@subs,\$15;" . - "push \@subs,\$16;" . - "push \@subs,\$'; }"; - - undef $REGERROR; - undef $REGMARK; - - eval "${cmd} (\$x =~ ${pattern}) {" . $pushes; - - if ($@) - { - printf $outfile "Error: $@\n"; - next NEXT_RE; - } - elsif (scalar(@subs) == 0) - { - printf $outfile "No match"; - if (defined $REGERROR && $REGERROR != 1) - { printf $outfile (", mark = %s", &pchars($REGERROR)); } - printf $outfile "\n"; - } - else - { - while (scalar(@subs) != 0) - { - printf $outfile (" 0: %s\n", &pchars($subs[0])); - printf $outfile (" 0+ %s\n", &pchars($subs[17])) if $showrest; - $last_printed = 0; - for ($i = 1; $i <= 16; $i++) - { - if (defined $subs[$i]) - { - while ($last_printed++ < $i-1) - { printf $outfile ("%2d: <unset>\n", $last_printed); } - printf $outfile ("%2d: %s\n", $i, &pchars($subs[$i])); - $last_printed = $i; - } - } - splice(@subs, 0, 18); - } - - # It seems that $REGMARK is not marked as UTF-8 even when use utf8 is - # set and the input pattern was a UTF-8 string. We can, however, force - # it to be so marked. - - if (defined $REGMARK && $REGMARK != 1) - { - $xx = $REGMARK; - $xx = Encode::decode_utf8($xx) if $utf8; - printf $outfile ("MK: %s\n", &pchars($xx)); - } - } - } - } - -# printf $outfile "\n"; - -# End diff --git a/src/third_party/pcre-8.38/ucp.h b/src/third_party/pcre-8.38/ucp.h deleted file mode 100644 index 2fa00296e42..00000000000 --- a/src/third_party/pcre-8.38/ucp.h +++ /dev/null @@ -1,224 +0,0 @@ -/************************************************* -* Unicode Property Table handler * -*************************************************/ - -#ifndef _UCP_H -#define _UCP_H - -/* This file contains definitions of the property values that are returned by -the UCD access macros. New values that are added for new releases of Unicode -should always be at the end of each enum, for backwards compatibility. - -IMPORTANT: Note also that the specific numeric values of the enums have to be -the same as the values that are generated by the maint/MultiStage2.py script, -where the equivalent property descriptive names are listed in vectors. - -ALSO: The specific values of the first two enums are assumed for the table -called catposstab in pcre_compile.c. */ - -/* These are the general character categories. */ - -enum { - ucp_C, /* Other */ - ucp_L, /* Letter */ - ucp_M, /* Mark */ - ucp_N, /* Number */ - ucp_P, /* Punctuation */ - ucp_S, /* Symbol */ - ucp_Z /* Separator */ -}; - -/* These are the particular character categories. */ - -enum { - ucp_Cc, /* Control */ - ucp_Cf, /* Format */ - ucp_Cn, /* Unassigned */ - ucp_Co, /* Private use */ - ucp_Cs, /* Surrogate */ - ucp_Ll, /* Lower case letter */ - ucp_Lm, /* Modifier letter */ - ucp_Lo, /* Other letter */ - ucp_Lt, /* Title case letter */ - ucp_Lu, /* Upper case letter */ - ucp_Mc, /* Spacing mark */ - ucp_Me, /* Enclosing mark */ - ucp_Mn, /* Non-spacing mark */ - ucp_Nd, /* Decimal number */ - ucp_Nl, /* Letter number */ - ucp_No, /* Other number */ - ucp_Pc, /* Connector punctuation */ - ucp_Pd, /* Dash punctuation */ - ucp_Pe, /* Close punctuation */ - ucp_Pf, /* Final punctuation */ - ucp_Pi, /* Initial punctuation */ - ucp_Po, /* Other punctuation */ - ucp_Ps, /* Open punctuation */ - ucp_Sc, /* Currency symbol */ - ucp_Sk, /* Modifier symbol */ - ucp_Sm, /* Mathematical symbol */ - ucp_So, /* Other symbol */ - ucp_Zl, /* Line separator */ - ucp_Zp, /* Paragraph separator */ - ucp_Zs /* Space separator */ -}; - -/* These are grapheme break properties. Note that the code for processing them -assumes that the values are less than 16. If more values are added that take -the number to 16 or more, the code will have to be rewritten. */ - -enum { - ucp_gbCR, /* 0 */ - ucp_gbLF, /* 1 */ - ucp_gbControl, /* 2 */ - ucp_gbExtend, /* 3 */ - ucp_gbPrepend, /* 4 */ - ucp_gbSpacingMark, /* 5 */ - ucp_gbL, /* 6 Hangul syllable type L */ - ucp_gbV, /* 7 Hangul syllable type V */ - ucp_gbT, /* 8 Hangul syllable type T */ - ucp_gbLV, /* 9 Hangul syllable type LV */ - ucp_gbLVT, /* 10 Hangul syllable type LVT */ - ucp_gbRegionalIndicator, /* 11 */ - ucp_gbOther /* 12 */ -}; - -/* These are the script identifications. */ - -enum { - ucp_Arabic, - ucp_Armenian, - ucp_Bengali, - ucp_Bopomofo, - ucp_Braille, - ucp_Buginese, - ucp_Buhid, - ucp_Canadian_Aboriginal, - ucp_Cherokee, - ucp_Common, - ucp_Coptic, - ucp_Cypriot, - ucp_Cyrillic, - ucp_Deseret, - ucp_Devanagari, - ucp_Ethiopic, - ucp_Georgian, - ucp_Glagolitic, - ucp_Gothic, - ucp_Greek, - ucp_Gujarati, - ucp_Gurmukhi, - ucp_Han, - ucp_Hangul, - ucp_Hanunoo, - ucp_Hebrew, - ucp_Hiragana, - ucp_Inherited, - ucp_Kannada, - ucp_Katakana, - ucp_Kharoshthi, - ucp_Khmer, - ucp_Lao, - ucp_Latin, - ucp_Limbu, - ucp_Linear_B, - ucp_Malayalam, - ucp_Mongolian, - ucp_Myanmar, - ucp_New_Tai_Lue, - ucp_Ogham, - ucp_Old_Italic, - ucp_Old_Persian, - ucp_Oriya, - ucp_Osmanya, - ucp_Runic, - ucp_Shavian, - ucp_Sinhala, - ucp_Syloti_Nagri, - ucp_Syriac, - ucp_Tagalog, - ucp_Tagbanwa, - ucp_Tai_Le, - ucp_Tamil, - ucp_Telugu, - ucp_Thaana, - ucp_Thai, - ucp_Tibetan, - ucp_Tifinagh, - ucp_Ugaritic, - ucp_Yi, - /* New for Unicode 5.0: */ - ucp_Balinese, - ucp_Cuneiform, - ucp_Nko, - ucp_Phags_Pa, - ucp_Phoenician, - /* New for Unicode 5.1: */ - ucp_Carian, - ucp_Cham, - ucp_Kayah_Li, - ucp_Lepcha, - ucp_Lycian, - ucp_Lydian, - ucp_Ol_Chiki, - ucp_Rejang, - ucp_Saurashtra, - ucp_Sundanese, - ucp_Vai, - /* New for Unicode 5.2: */ - ucp_Avestan, - ucp_Bamum, - ucp_Egyptian_Hieroglyphs, - ucp_Imperial_Aramaic, - ucp_Inscriptional_Pahlavi, - ucp_Inscriptional_Parthian, - ucp_Javanese, - ucp_Kaithi, - ucp_Lisu, - ucp_Meetei_Mayek, - ucp_Old_South_Arabian, - ucp_Old_Turkic, - ucp_Samaritan, - ucp_Tai_Tham, - ucp_Tai_Viet, - /* New for Unicode 6.0.0: */ - ucp_Batak, - ucp_Brahmi, - ucp_Mandaic, - /* New for Unicode 6.1.0: */ - ucp_Chakma, - ucp_Meroitic_Cursive, - ucp_Meroitic_Hieroglyphs, - ucp_Miao, - ucp_Sharada, - ucp_Sora_Sompeng, - ucp_Takri, - /* New for Unicode 7.0.0: */ - ucp_Bassa_Vah, - ucp_Caucasian_Albanian, - ucp_Duployan, - ucp_Elbasan, - ucp_Grantha, - ucp_Khojki, - ucp_Khudawadi, - ucp_Linear_A, - ucp_Mahajani, - ucp_Manichaean, - ucp_Mende_Kikakui, - ucp_Modi, - ucp_Mro, - ucp_Nabataean, - ucp_Old_North_Arabian, - ucp_Old_Permic, - ucp_Pahawh_Hmong, - ucp_Palmyrene, - ucp_Psalter_Pahlavi, - ucp_Pau_Cin_Hau, - ucp_Siddham, - ucp_Tirhuta, - ucp_Warang_Citi -}; - -#endif - -/* End of ucp.h */ |