diff options
| author | ph10 <ph10@2f5784b3-3f2a-0410-8824-cb99058d5e15> | 2014-03-04 10:45:15 +0000 |
|---|---|---|
| committer | ph10 <ph10@2f5784b3-3f2a-0410-8824-cb99058d5e15> | 2014-03-04 10:45:15 +0000 |
| commit | f2f9b30e2aa29fff14f7b46a6bd1da4e7a8fb272 (patch) | |
| tree | 5285c4aed81c9848fbdc1aa8a4cb0cf01aa2d37d | |
| parent | 5af167ddb0bba1ec2ace7e31de5d1105b345cde0 (diff) | |
| download | pcre-f2f9b30e2aa29fff14f7b46a6bd1da4e7a8fb272.tar.gz | |
Preparations for next release.
git-svn-id: svn://vcs.exim.org/pcre/code/trunk@1459 2f5784b3-3f2a-0410-8824-cb99058d5e15
| -rw-r--r-- | AUTHORS | 6 | ||||
| -rw-r--r-- | ChangeLog | 84 | ||||
| -rw-r--r-- | LICENCE | 6 | ||||
| -rw-r--r-- | NEWS | 10 | ||||
| -rw-r--r-- | README | 2 | ||||
| -rwxr-xr-x | RunTest | 12 | ||||
| -rw-r--r-- | configure.ac | 14 | ||||
| -rw-r--r-- | doc/html/README.txt | 21 | ||||
| -rw-r--r-- | doc/html/pcre.html | 15 | ||||
| -rw-r--r-- | doc/html/pcreapi.html | 114 | ||||
| -rw-r--r-- | doc/html/pcrepattern.html | 25 | ||||
| -rw-r--r-- | doc/html/pcresyntax.html | 79 | ||||
| -rw-r--r-- | doc/html/pcretest.html | 21 | ||||
| -rw-r--r-- | doc/pcre.3 | 2 | ||||
| -rw-r--r-- | doc/pcre.txt | 1323 | ||||
| -rw-r--r-- | doc/pcreapi.3 | 20 | ||||
| -rw-r--r-- | doc/pcrepattern.3 | 2 | ||||
| -rw-r--r-- | doc/pcresyntax.3 | 4 | ||||
| -rw-r--r-- | doc/pcretest.1 | 18 | ||||
| -rw-r--r-- | doc/pcretest.txt | 375 | ||||
| -rwxr-xr-x | maint/ManyConfigTests | 4 | ||||
| -rw-r--r-- | pcre_compile.c | 20 | ||||
| -rw-r--r-- | pcre_exec.c | 4 | ||||
| -rw-r--r-- | pcre_internal.h | 6 | ||||
| -rw-r--r-- | pcretest.c | 4 |
25 files changed, 1140 insertions, 1051 deletions
@@ -8,7 +8,7 @@ Email domain: cam.ac.uk University of Cambridge Computing Service, Cambridge, England. -Copyright (c) 1997-2013 University of Cambridge +Copyright (c) 1997-2014 University of Cambridge All rights reserved @@ -19,7 +19,7 @@ Written by: Zoltan Herczeg Email local part: hzmester Emain domain: freemail.hu -Copyright(c) 2010-2013 Zoltan Herczeg +Copyright(c) 2010-2014 Zoltan Herczeg All rights reserved. @@ -30,7 +30,7 @@ Written by: Zoltan Herczeg Email local part: hzmester Emain domain: freemail.hu -Copyright(c) 2009-2013 Zoltan Herczeg +Copyright(c) 2009-2014 Zoltan Herczeg All rights reserved. @@ -1,8 +1,8 @@ ChangeLog for PCRE ------------------ -Version 8.35-RC1 xx-xxxx-201x ------------------------------ +Version 8.35-RC1 04-March-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 @@ -30,22 +30,22 @@ Version 8.35-RC1 xx-xxxx-201x above a certain treshold (e.g: 256). The only limitation is that the value must be bigger than the treshold as well. This function is useful, when the characters above the treshold 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. - + +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. + 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 @@ -54,57 +54,57 @@ Version 8.35-RC1 xx-xxxx-201x 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 + +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 + 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 + 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 + 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. + +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. + 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. Version 8.34 15-December-2013 @@ -24,7 +24,7 @@ Email domain: cam.ac.uk University of Cambridge Computing Service, Cambridge, England. -Copyright (c) 1997-2013 University of Cambridge +Copyright (c) 1997-2014 University of Cambridge All rights reserved. @@ -35,7 +35,7 @@ Written by: Zoltan Herczeg Email local part: hzmester Emain domain: freemail.hu -Copyright(c) 2010-2013 Zoltan Herczeg +Copyright(c) 2010-2014 Zoltan Herczeg All rights reserved. @@ -46,7 +46,7 @@ Written by: Zoltan Herczeg Email local part: hzmester Emain domain: freemail.hu -Copyright(c) 2009-2013 Zoltan Herczeg +Copyright(c) 2009-2014 Zoltan Herczeg All rights reserved. @@ -1,6 +1,16 @@ News about PCRE releases ------------------------ +Release 8.35 04-March-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. + + Release 8.34 15-December-2013 ----------------------------- @@ -373,7 +373,7 @@ library. They are also documented in the pcrebuild man page. 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 +. The default size (in bytes) of the internal buffer used by pcregrep can be set by, for example: --with-pcregrep-bufsize=51200 @@ -32,7 +32,7 @@ # 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 +# 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. # @@ -473,13 +473,13 @@ if [ $do3 = yes ] ; then locale=fr_FR infile=$testdata/testinput3 outfile=$testdata/testoutput3 - outfile2=$testdata/testoutput3A - outfile3=$testdata/testoutput3B + outfile2=$testdata/testoutput3A + outfile3=$testdata/testoutput3B else infile=test3input outfile=test3output - outfile2=test3outputA - outfile3=test3outputB + outfile2=test3outputA + outfile3=test3outputB locale -a | grep '^french$' >/dev/null if [ $? -eq 0 ] ; then locale=french @@ -508,7 +508,7 @@ if [ $do3 = yes ] ; then if [ $? = 0 ] ; then if $cf $outfile testtry >teststdout || \ $cf $outfile2 testtry >teststdout || \ - $cf $outfile3 testtry >teststdout + $cf $outfile3 testtry >teststdout then if [ "$opt" = "-s" ] ; then echo " OK with study" elif [ "$opt" = "-s+" ] ; then echo " OK with JIT study" diff --git a/configure.ac b/configure.ac index 40703f0..d8fd6d5 100644 --- a/configure.ac +++ b/configure.ac @@ -11,15 +11,15 @@ dnl be defined as -RC2, for example. For real releases, it should be empty. m4_define(pcre_major, [8]) m4_define(pcre_minor, [35]) m4_define(pcre_prerelease, [-RC1]) -m4_define(pcre_date, [2013-12-23]) +m4_define(pcre_date, [2014-03-04]) # NOTE: The CMakeLists.txt file searches for the above variables in the first # 50 lines of this file. Please update that if the variables above are moved. # Libtool shared library interface versions (current:revision:age) -m4_define(libpcre_version, [3:2:2]) -m4_define(libpcre16_version, [2:2:2]) -m4_define(libpcre32_version, [0:2:0]) +m4_define(libpcre_version, [3:3:2]) +m4_define(libpcre16_version, [2:3:2]) +m4_define(libpcre32_version, [0:3:0]) m4_define(libpcreposix_version, [0:2:0]) m4_define(libpcrecpp_version, [0:0:0]) @@ -695,7 +695,7 @@ if test "$enable_jit" = "yes"; then CC="$PTHREAD_CC" CFLAGS="$PTHREAD_CFLAGS $CFLAGS" LIBS="$PTHREAD_LIBS $LIBS" - fi + fi AC_DEFINE([SUPPORT_JIT], [], [ Define to any value to enable support for Just-In-Time compiling.]) else @@ -748,8 +748,8 @@ if test $with_pcregrep_bufsize -lt 8192 ; then with_pcregrep_bufsize="8192" else if test $? -gt 1 ; then - AC_MSG_ERROR([Bad value for --with-pcregrep-bufsize]) - fi + AC_MSG_ERROR([Bad value for --with-pcregrep-bufsize]) + fi fi AC_DEFINE_UNQUOTED([PCREGREP_BUFSIZE], [$with_pcregrep_bufsize], [ diff --git a/doc/html/README.txt b/doc/html/README.txt index 51197df..88f2dfd 100644 --- a/doc/html/README.txt +++ b/doc/html/README.txt @@ -85,11 +85,12 @@ 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 - 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). + 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 @@ -372,12 +373,12 @@ library. They are also documented in the pcrebuild man page. Of course, the relevant libraries must be installed on your system. -. The default size of internal buffer used by pcregrep can be set by, for - example: +. The default size (in bytes) of the internal buffer used by pcregrep can be + set by, for example: - --with-pcregrep-bufsize=50K + --with-pcregrep-bufsize=51200 - The default value is 20K. + 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, @@ -987,4 +988,4 @@ pcre_xxx, one with the name pcre16_xx, and a third with the name pcre32_xxx. Philip Hazel Email local part: ph10 Email domain: cam.ac.uk -Last updated: 05 November 2013 +Last updated: 17 January 2014 diff --git a/doc/html/pcre.html b/doc/html/pcre.html index 93b129e..c2b29aa 100644 --- a/doc/html/pcre.html +++ b/doc/html/pcre.html @@ -154,8 +154,11 @@ page. The user documentation for PCRE comprises a number of different sections. In the "man" format, each of these is a separate "man page". In the HTML format, each is a separate page, linked from the index page. In the plain text format, -all the sections, except the <b>pcredemo</b> section, are concatenated, for ease -of searching. The sections are as follows: +the descriptions of the <b>pcregrep</b> and <b>pcretest</b> programs are in files +called <b>pcregrep.txt</b> and <b>pcretest.txt</b>, respectively. The remaining +sections, except for the <b>pcredemo</b> section (which is a program listing), +are concatenated in <b>pcre.txt</b>, for ease of searching. The sections are as +follows: <pre> pcre this document pcre-config show PCRE installation configuration information @@ -182,8 +185,8 @@ of searching. The sections are as follows: pcretest description of the <b>pcretest</b> testing command pcreunicode discussion of Unicode and UTF-8/16/32 support </pre> -In addition, in the "man" and HTML formats, there is a short page for each -C library function, listing its arguments and results. +In the "man" and HTML formats, there is also a short page for each C library +function, listing its arguments and results. </P> <br><a name="SEC4" href="#TOC1">AUTHOR</a><br> <P> @@ -201,9 +204,9 @@ two digits 10, at the domain cam.ac.uk. </P> <br><a name="SEC5" href="#TOC1">REVISION</a><br> <P> -Last updated: 13 May 2013 +Last updated: 08 January 2014 <br> -Copyright © 1997-2013 University of Cambridge. +Copyright © 1997-2014 University of Cambridge. <br> <p> Return to the <a href="index.html">PCRE index page</a>. diff --git a/doc/html/pcreapi.html b/doc/html/pcreapi.html index abc3d26..b401ecc 100644 --- a/doc/html/pcreapi.html +++ b/doc/html/pcreapi.html @@ -166,6 +166,9 @@ man page, in case the conversion went wrong. <br> <br> <b>int (*pcre_callout)(pcre_callout_block *);</b> +<br> +<br> +<b>int (*pcre_stack_guard)(void);</b> </P> <br><a name="SEC5" href="#TOC1">PCRE 8-BIT, 16-BIT, AND 32-BIT LIBRARIES</a><br> <P> @@ -324,6 +327,15 @@ by the caller to a "callout" function, which PCRE will then call at specified points during a matching operation. Details are given in the <a href="pcrecallout.html"><b>pcrecallout</b></a> documentation. +</P> +<P> +The global variable <b>pcre_stack_guard</b> initially contains NULL. It can be +set by the caller to a function that is called by PCRE whenever it starts +to compile a parenthesized part of a pattern. When parentheses are nested, PCRE +uses recursive function calls, which use up the system stack. This function is +provided so that applications with restricted stacks can force a compilation +error if the stack runs out. The function should return zero if all is well, or +non-zero to force an error. <a name="newlines"></a></P> <br><a name="SEC7" href="#TOC1">NEWLINES</a><br> <P> @@ -369,7 +381,8 @@ controlled in a similar way, but by separate options. The PCRE functions can be used in multi-threading applications, with the proviso that the memory management functions pointed to by <b>pcre_malloc</b>, <b>pcre_free</b>, <b>pcre_stack_malloc</b>, and <b>pcre_stack_free</b>, and the -callout function pointed to by <b>pcre_callout</b>, are shared by all threads. +callout and stack-checking functions pointed to by <b>pcre_callout</b> and +<b>pcre_stack_guard</b>, are shared by all threads. </P> <P> The compiled form of a regular expression is not altered during matching, so @@ -489,7 +502,10 @@ documentation. The output is a long integer that gives the maximum depth of nesting of parentheses (of any kind) in a pattern. This limit is imposed to cap the amount of system stack used when a pattern is compiled. It is specified when PCRE is -built; the default is 250. +built; the default is 250. This limit does not take into account the stack that +may already be used by the calling application. For finer control over +compilation stack usage, you can set a pointer to an external checking function +in <b>pcre_stack_guard</b>. <pre> PCRE_CONFIG_MATCH_LIMIT </pre> @@ -1008,6 +1024,8 @@ have fallen out of use. To avoid confusion, they have not been re-used. 81 missing opening brace after \o 82 parentheses are too deeply nested 83 invalid range in character class + 84 group name must start with a non-digit + 85 parentheses are too deeply nested (stack check) </pre> The numbers 32 and 10000 in errors 48 and 49 are defaults; different values may be used if the limits were changed when PCRE was built. @@ -1265,12 +1283,15 @@ information call is provided for internal use by the <b>pcre_study()</b> function. External callers can cause PCRE to use its internal tables by passing a NULL table pointer. <pre> - PCRE_INFO_FIRSTBYTE + PCRE_INFO_FIRSTBYTE (deprecated) </pre> Return information about the first data unit of any matched string, for a -non-anchored pattern. (The name of this option refers to the 8-bit library, -where data units are bytes.) The fourth argument should point to an <b>int</b> -variable. +non-anchored pattern. The name of this option refers to the 8-bit library, +where data units are bytes. The fourth argument should point to an <b>int</b> +variable. Negative values are used for special cases. However, this means that +when the 32-bit library is in non-UTF-32 mode, the full 32-bit range of +characters cannot be returned. For this reason, this value is deprecated; use +PCRE_INFO_FIRSTCHARACTERFLAGS and PCRE_INFO_FIRSTCHARACTER instead. </P> <P> If there is a fixed first value, for example, the letter "c" from a pattern @@ -1293,12 +1314,43 @@ starts with "^", or -1 is returned, indicating that the pattern matches only at the start of a subject string or after any newline within the string. Otherwise -2 is returned. For anchored patterns, -2 is returned. +<pre> + PCRE_INFO_FIRSTCHARACTER +</pre> +Return the value of the first data unit (non-UTF character) of any matched +string in the situation where PCRE_INFO_FIRSTCHARACTERFLAGS returns 1; +otherwise return 0. The fourth argument should point to an <b>uint_t</b> +variable. </P> <P> -Since for the 32-bit library using the non-UTF-32 mode, this function is unable -to return the full 32-bit range of the character, this value is deprecated; -instead the PCRE_INFO_FIRSTCHARACTERFLAGS and PCRE_INFO_FIRSTCHARACTER values -should be used. +In the 8-bit library, the value is always less than 256. In the 16-bit library +the value can be up to 0xffff. In the 32-bit library in UTF-32 mode the value +can be up to 0x10ffff, and up to 0xffffffff when not using UTF-32 mode. +<pre> + PCRE_INFO_FIRSTCHARACTERFLAGS +</pre> +Return information about the first data unit of any matched string, for a +non-anchored pattern. The fourth argument should point to an <b>int</b> +variable. +</P> +<P> +If there is a fixed first value, for example, the letter "c" from a pattern +such as (cat|cow|coyote), 1 is returned, and the character value can be +retrieved using PCRE_INFO_FIRSTCHARACTER. If there is no fixed first value, and +if either +<br> +<br> +(a) the pattern was compiled with the PCRE_MULTILINE option, and every branch +starts with "^", or +<br> +<br> +(b) every branch of the pattern starts with ".*" and PCRE_DOTALL is not set +(if it were set, the pattern would be anchored), +<br> +<br> +2 is returned, indicating that the pattern matches only at the start of a +subject string or after any newline within the string. Otherwise 0 is +returned. For anchored patterns, 0 is returned. <pre> PCRE_INFO_FIRSTTABLE </pre> @@ -1509,44 +1561,6 @@ is made available via this option so that it can be saved and restored (see the <a href="pcreprecompile.html"><b>pcreprecompile</b></a> documentation for details). <pre> - PCRE_INFO_FIRSTCHARACTERFLAGS -</pre> -Return information about the first data unit of any matched string, for a -non-anchored pattern. The fourth argument should point to an <b>int</b> -variable. -</P> -<P> -If there is a fixed first value, for example, the letter "c" from a pattern -such as (cat|cow|coyote), 1 is returned, and the character value can be -retrieved using PCRE_INFO_FIRSTCHARACTER. -</P> -<P> -If there is no fixed first value, and if either -<br> -<br> -(a) the pattern was compiled with the PCRE_MULTILINE option, and every branch -starts with "^", or -<br> -<br> -(b) every branch of the pattern starts with ".*" and PCRE_DOTALL is not set -(if it were set, the pattern would be anchored), -<br> -<br> -2 is returned, indicating that the pattern matches only at the start of a -subject string or after any newline within the string. Otherwise 0 is -returned. For anchored patterns, 0 is returned. -<pre> - PCRE_INFO_FIRSTCHARACTER -</pre> -Return the fixed first character value in the situation where -PCRE_INFO_FIRSTCHARACTERFLAGS returns 1; otherwise return 0. The fourth -argument should point to an <b>uint_t</b> variable. -</P> -<P> -In the 8-bit library, the value is always less than 256. In the 16-bit library -the value can be up to 0xffff. In the 32-bit library in UTF-32 mode the value -can be up to 0x10ffff, and up to 0xffffffff when not using UTF-32 mode. -<pre> PCRE_INFO_REQUIREDCHARFLAGS </pre> Returns 1 if there is a rightmost literal data unit that must exist in any @@ -2899,9 +2913,9 @@ Cambridge CB2 3QH, England. </P> <br><a name="SEC26" href="#TOC1">REVISION</a><br> <P> -Last updated: 12 November 2013 +Last updated: 09 February 2014 <br> -Copyright © 1997-2013 University of Cambridge. +Copyright © 1997-2014 University of Cambridge. <br> <p> Return to the <a href="index.html">PCRE index page</a>. diff --git a/doc/html/pcrepattern.html b/doc/html/pcrepattern.html index 624cb44..c06d1e0 100644 --- a/doc/html/pcrepattern.html +++ b/doc/html/pcrepattern.html @@ -1003,7 +1003,9 @@ matches "foobar", the first substring is still set to "foo". <P> Perl documents that the use of \K within assertions is "not well defined". In PCRE, \K is acted upon when it occurs inside positive assertions, but is -ignored in negative assertions. +ignored in negative assertions. Note that when a pattern such as (?=ab\K) +matches, the reported start of the match can be greater than the end of the +match. <a name="smallassertions"></a></P> <br><b> Simple assertions @@ -2990,19 +2992,22 @@ match does not always guarantee that a match must be at this starting point. <P> Note that (*COMMIT) at the start of a pattern is not the same as an anchor, unless PCRE's start-of-match optimizations are turned off, as shown in this -<b>pcretest</b> example: +output from <b>pcretest</b>: <pre> re> /(*COMMIT)abc/ data> xyzabc 0: abc - xyzabc\Y + data> xyzabc\Y No match </pre> -PCRE knows that any match must start with "a", so the optimization skips along -the subject to "a" before running the first match attempt, which succeeds. When -the optimization is disabled by the \Y escape in the second subject, the match -starts at "x" and so the (*COMMIT) causes it to fail without trying any other -starting points. +For this pattern, PCRE knows that any match must start with "a", so the +optimization skips along the subject to "a" before applying the pattern to the +first set of data. The match attempt then succeeds. In the second set of data, +the escape sequence \Y is interpreted by the <b>pcretest</b> program. It causes +the PCRE_NO_START_OPTIMIZE option to be set when <b>pcre_exec()</b> is called. +This disables the optimization that skips along to the first character. The +pattern is now applied starting at "x", and so the (*COMMIT) causes the match +to fail without trying any other starting points. <pre> (*PRUNE) or (*PRUNE:NAME) </pre> @@ -3221,9 +3226,9 @@ Cambridge CB2 3QH, England. </P> <br><a name="SEC30" href="#TOC1">REVISION</a><br> <P> -Last updated: 03 December 2013 +Last updated: 08 January 2014 <br> -Copyright © 1997-2013 University of Cambridge. +Copyright © 1997-2014 University of Cambridge. <br> <p> Return to the <a href="index.html">PCRE index page</a>. diff --git a/doc/html/pcresyntax.html b/doc/html/pcresyntax.html index 0764a33..89f3573 100644 --- a/doc/html/pcresyntax.html +++ b/doc/html/pcresyntax.html @@ -29,13 +29,13 @@ man page, in case the conversion went wrong. <li><a name="TOC14" href="#SEC14">ATOMIC GROUPS</a> <li><a name="TOC15" href="#SEC15">COMMENT</a> <li><a name="TOC16" href="#SEC16">OPTION SETTING</a> -<li><a name="TOC17" href="#SEC17">LOOKAHEAD AND LOOKBEHIND ASSERTIONS</a> -<li><a name="TOC18" href="#SEC18">BACKREFERENCES</a> -<li><a name="TOC19" href="#SEC19">SUBROUTINE REFERENCES (POSSIBLY RECURSIVE)</a> -<li><a name="TOC20" href="#SEC20">CONDITIONAL PATTERNS</a> -<li><a name="TOC21" href="#SEC21">BACKTRACKING CONTROL</a> -<li><a name="TOC22" href="#SEC22">NEWLINE CONVENTIONS</a> -<li><a name="TOC23" href="#SEC23">WHAT \R MATCHES</a> +<li><a name="TOC17" href="#SEC17">NEWLINE CONVENTION</a> +<li><a name="TOC18" href="#SEC18">WHAT \R MATCHES</a> +<li><a name="TOC19" href="#SEC19">LOOKAHEAD AND LOOKBEHIND ASSERTIONS</a> +<li><a name="TOC20" href="#SEC20">BACKREFERENCES</a> +<li><a name="TOC21" href="#SEC21">SUBROUTINE REFERENCES (POSSIBLY RECURSIVE)</a> +<li><a name="TOC22" href="#SEC22">CONDITIONAL PATTERNS</a> +<li><a name="TOC23" href="#SEC23">BACKTRACKING CONTROL</a> <li><a name="TOC24" href="#SEC24">CALLOUTS</a> <li><a name="TOC25" href="#SEC25">SEE ALSO</a> <li><a name="TOC26" href="#SEC26">AUTHOR</a> @@ -339,7 +339,8 @@ but some of them use Unicode properties if PCRE_UCP is set. You can use <P> <pre> \K reset start of match -</PRE> +</pre> +\K is honoured in positive assertions, but ignored in negative ones. </P> <br><a name="SEC12" href="#TOC1">ALTERNATION</a><br> <P> @@ -382,11 +383,13 @@ but some of them use Unicode properties if PCRE_UCP is set. You can use (?x) extended (ignore white space) (?-...) unset option(s) </pre> -The following are recognized only at the start of a pattern or after one of the -newline-setting options with similar syntax: +The following are recognized only at the very start of a pattern or after one +of the newline or \R options with similar syntax. More than one of them may +appear. <pre> (*LIMIT_MATCH=d) set the match limit to d (decimal number) (*LIMIT_RECURSION=d) set the recursion limit to d (decimal number) + (*NO_AUTO_POSSESS) no auto-possessification (PCRE_NO_AUTO_POSSESS) (*NO_START_OPT) no start-match optimization (PCRE_NO_START_OPTIMIZE) (*UTF8) set UTF-8 mode: 8-bit library (PCRE_UTF8) (*UTF16) set UTF-16 mode: 16-bit library (PCRE_UTF16) @@ -397,7 +400,28 @@ newline-setting options with similar syntax: Note that LIMIT_MATCH and LIMIT_RECURSION can only reduce the value of the limits set by the caller of pcre_exec(), not increase them. </P> -<br><a name="SEC17" href="#TOC1">LOOKAHEAD AND LOOKBEHIND ASSERTIONS</a><br> +<br><a name="SEC17" href="#TOC1">NEWLINE CONVENTION</a><br> +<P> +These are recognized only at the very start of the pattern or after option +settings with a similar syntax. +<pre> + (*CR) carriage return only + (*LF) linefeed only + (*CRLF) carriage return followed by linefeed + (*ANYCRLF) all three of the above + (*ANY) any Unicode newline sequence +</PRE> +</P> +<br><a name="SEC18" href="#TOC1">WHAT \R MATCHES</a><br> +<P> +These are recognized only at the very start of the pattern or after option +setting with a similar syntax. +<pre> + (*BSR_ANYCRLF) CR, LF, or CRLF + (*BSR_UNICODE) any Unicode newline sequence +</PRE> +</P> +<br><a name="SEC19" href="#TOC1">LOOKAHEAD AND LOOKBEHIND ASSERTIONS</a><br> <P> <pre> (?=...) positive look ahead @@ -407,7 +431,7 @@ limits set by the caller of pcre_exec(), not increase them. </pre> Each top-level branch of a look behind must be of a fixed length. </P> -<br><a name="SEC18" href="#TOC1">BACKREFERENCES</a><br> +<br><a name="SEC20" href="#TOC1">BACKREFERENCES</a><br> <P> <pre> \n reference by number (can be ambiguous) @@ -421,7 +445,7 @@ Each top-level branch of a look behind must be of a fixed length. (?P=name) reference by name (Python) </PRE> </P> -<br><a name="SEC19" href="#TOC1">SUBROUTINE REFERENCES (POSSIBLY RECURSIVE)</a><br> +<br><a name="SEC21" href="#TOC1">SUBROUTINE REFERENCES (POSSIBLY RECURSIVE)</a><br> <P> <pre> (?R) recurse whole pattern @@ -440,7 +464,7 @@ Each top-level branch of a look behind must be of a fixed length. \g'-n' call subpattern by relative number (PCRE extension) </PRE> </P> -<br><a name="SEC20" href="#TOC1">CONDITIONAL PATTERNS</a><br> +<br><a name="SEC22" href="#TOC1">CONDITIONAL PATTERNS</a><br> <P> <pre> (?(condition)yes-pattern) @@ -459,7 +483,7 @@ Each top-level branch of a look behind must be of a fixed length. (?(assert)... assertion condition </PRE> </P> -<br><a name="SEC21" href="#TOC1">BACKTRACKING CONTROL</a><br> +<br><a name="SEC23" href="#TOC1">BACKTRACKING CONTROL</a><br> <P> The following act immediately they are reached: <pre> @@ -482,27 +506,6 @@ pattern is not anchored. (*THEN:NAME) equivalent to (*MARK:NAME)(*THEN) </PRE> </P> -<br><a name="SEC22" href="#TOC1">NEWLINE CONVENTIONS</a><br> -<P> -These are recognized only at the very start of the pattern or after a -(*BSR_...), (*UTF8), (*UTF16), (*UTF32) or (*UCP) option. -<pre> - (*CR) carriage return only - (*LF) linefeed only - (*CRLF) carriage return followed by linefeed - (*ANYCRLF) all three of the above - (*ANY) any Unicode newline sequence -</PRE> -</P> -<br><a name="SEC23" href="#TOC1">WHAT \R MATCHES</a><br> -<P> -These are recognized only at the very start of the pattern or after a -(*...) option that sets the newline convention or a UTF or UCP mode. -<pre> - (*BSR_ANYCRLF) CR, LF, or CRLF - (*BSR_UNICODE) any Unicode newline sequence -</PRE> -</P> <br><a name="SEC24" href="#TOC1">CALLOUTS</a><br> <P> <pre> @@ -526,9 +529,9 @@ Cambridge CB2 3QH, England. </P> <br><a name="SEC27" href="#TOC1">REVISION</a><br> <P> -Last updated: 12 November 2013 +Last updated: 08 January 2014 <br> -Copyright © 1997-2013 University of Cambridge. +Copyright © 1997-2014 University of Cambridge. <br> <p> Return to the <a href="index.html">PCRE index page</a>. diff --git a/doc/html/pcretest.html b/doc/html/pcretest.html index 4ed1dfd..839fabf 100644 --- a/doc/html/pcretest.html +++ b/doc/html/pcretest.html @@ -138,6 +138,9 @@ following options output the value and set the exit code as indicated: newline the default newline setting: CR, LF, CRLF, ANYCRLF, or ANY exit code is always 0 + bsr the default setting for what \R matches: + ANYCRLF or ANY + exit code is always 0 </pre> The following options output 1 for true or 0 for false, and set the exit code to the same value: @@ -373,6 +376,7 @@ sections. <b>/N</b> set PCRE_NO_AUTO_CAPTURE <b>/O</b> set PCRE_NO_AUTO_POSSESS <b>/P</b> use the POSIX wrapper + <b>/Q</b> test external stack check function <b>/S</b> study the pattern after compilation <b>/s</b> set PCRE_DOTALL <b>/T</b> select character tables @@ -534,7 +538,10 @@ below. The <b>/I</b> modifier requests that <b>pcretest</b> output information about the compiled pattern (whether it is anchored, has a fixed first character, and so on). It does this by calling <b>pcre[16|32]_fullinfo()</b> after compiling a -pattern. If the pattern is studied, the results of that are also output. +pattern. If the pattern is studied, the results of that are also output. In +this output, the word "char" means a non-UTF character, that is, the value of a +single data item (8-bit, 16-bit, or 32-bit, depending on the library that is +being tested). </P> <P> The <b>/K</b> modifier requests <b>pcretest</b> to show names from backtracking @@ -568,6 +575,14 @@ successfully studied with the PCRE_STUDY_JIT_COMPILE option, the size of the JIT compiled code is also output. </P> <P> +The <b>/Q</b> modifier is used to test the use of <b>pcre_stack_guard</b>. It +must be followed by '0' or '1', specifying the return code to be given from an +external function that is passed to PCRE and used for stack checking during +compilation (see the +<a href="pcreapi.html"><b>pcreapi</b></a> +documentation for details). +</P> +<P> The <b>/S</b> modifier causes <b>pcre[16|32]_study()</b> to be called after the expression has been compiled, and the results used when the expression is matched. There are a number of qualifying characters that may follow <b>/S</b>. @@ -1134,9 +1149,9 @@ Cambridge CB2 3QH, England. </P> <br><a name="SEC17" href="#TOC1">REVISION</a><br> <P> -Last updated: 12 November 2013 +Last updated: 09 February 2014 <br> -Copyright © 1997-2013 University of Cambridge. +Copyright © 1997-2014 University of Cambridge. <br> <p> Return to the <a href="index.html">PCRE index page</a>. @@ -158,7 +158,7 @@ page. The user documentation for PCRE comprises a number of different sections. In the "man" format, each of these is a separate "man page". In the HTML format, each is a separate page, linked from the index page. In the plain text format, -the descriptions of the \fBpcregrep\fP and \fBpcretest\fP programs are in files +the descriptions of the \fBpcregrep\fP and \fBpcretest\fP programs are in files called \fBpcregrep.txt\fP and \fBpcretest.txt\fP, respectively. The remaining sections, except for the \fBpcredemo\fP section (which is a program listing), are concatenated in \fBpcre.txt\fP, for ease of searching. The sections are as diff --git a/doc/pcre.txt b/doc/pcre.txt index 9d69515..14cbb8b 100644 --- a/doc/pcre.txt +++ b/doc/pcre.txt @@ -130,9 +130,11 @@ USER DOCUMENTATION The user documentation for PCRE comprises a number of different sec- tions. In the "man" format, each of these is a separate "man page". In the HTML format, each is a separate page, linked from the index page. - In the plain text format, all the sections, except the pcredemo sec- - tion, are concatenated, for ease of searching. The sections are as fol- - lows: + In the plain text format, the descriptions of the pcregrep and pcretest + programs are in files called pcregrep.txt and pcretest.txt, respec- + tively. The remaining sections, except for the pcredemo section (which + is a program listing), are concatenated in pcre.txt, for ease of + searching. The sections are as follows: pcre this document pcre-config show PCRE installation configuration information @@ -160,8 +162,8 @@ USER DOCUMENTATION pcretest description of the pcretest testing command pcreunicode discussion of Unicode and UTF-8/16/32 support - In addition, in the "man" and HTML formats, there is a short page for - each C library function, listing its arguments and results. + In the "man" and HTML formats, there is also a short page for each C + library function, listing its arguments and results. AUTHOR @@ -177,8 +179,8 @@ AUTHOR REVISION - Last updated: 13 May 2013 - Copyright (c) 1997-2013 University of Cambridge. + Last updated: 08 January 2014 + Copyright (c) 1997-2014 University of Cambridge. ------------------------------------------------------------------------------ @@ -1674,6 +1676,8 @@ PCRE NATIVE API INDIRECTED FUNCTIONS int (*pcre_callout)(pcre_callout_block *); + int (*pcre_stack_guard)(void); + PCRE 8-BIT, 16-BIT, AND 32-BIT LIBRARIES @@ -1809,6 +1813,14 @@ PCRE API OVERVIEW specified points during a matching operation. Details are given in the pcrecallout documentation. + The global variable pcre_stack_guard initially contains NULL. It can be + set by the caller to a function that is called by PCRE whenever it + starts to compile a parenthesized part of a pattern. When parentheses + are nested, PCRE uses recursive function calls, which use up the system + stack. This function is provided so that applications with restricted + stacks can force a compilation error if the stack runs out. The func- + tion should return zero if all is well, or non-zero to force an error. + NEWLINES @@ -1849,25 +1861,26 @@ MULTITHREADING The PCRE functions can be used in multi-threading applications, with the proviso that the memory management functions pointed to by pcre_malloc, pcre_free, pcre_stack_malloc, and pcre_stack_free, and the - callout function pointed to by pcre_callout, are shared by all threads. + callout and stack-checking functions pointed to by pcre_callout and + pcre_stack_guard, are shared by all threads. - The compiled form of a regular expression is not altered during match- + The compiled form of a regular expression is not altered during match- ing, so the same compiled pattern can safely be used by several threads at once. - If the just-in-time optimization feature is being used, it needs sepa- - rate memory stack areas for each thread. See the pcrejit documentation + If the just-in-time optimization feature is being used, it needs sepa- + rate memory stack areas for each thread. See the pcrejit documentation for more details. SAVING PRECOMPILED PATTERNS FOR LATER USE The compiled form of a regular expression can be saved and re-used at a - later time, possibly by a different program, and even on a host other - than the one on which it was compiled. Details are given in the - pcreprecompile documentation, which includes a description of the - pcre_pattern_to_host_byte_order() function. However, compiling a regu- - lar expression with one version of PCRE for use with a different ver- + later time, possibly by a different program, and even on a host other + than the one on which it was compiled. Details are given in the + pcreprecompile documentation, which includes a description of the + pcre_pattern_to_host_byte_order() function. However, compiling a regu- + lar expression with one version of PCRE for use with a different ver- sion is not guaranteed to work and may cause crashes. @@ -1875,45 +1888,45 @@ CHECKING BUILD-TIME OPTIONS int pcre_config(int what, void *where); - The function pcre_config() makes it possible for a PCRE client to dis- + The function pcre_config() makes it possible for a PCRE client to dis- cover which optional features have been compiled into the PCRE library. - The pcrebuild documentation has more details about these optional fea- + The pcrebuild documentation has more details about these optional fea- tures. - The first argument for pcre_config() is an integer, specifying which + The first argument for pcre_config() is an integer, specifying which information is required; the second argument is a pointer to a variable - into which the information is placed. The returned value is zero on - success, or the negative error code PCRE_ERROR_BADOPTION if the value - in the first argument is not recognized. The following information is + into which the information is placed. The returned value is zero on + success, or the negative error code PCRE_ERROR_BADOPTION if the value + in the first argument is not recognized. The following information is available: PCRE_CONFIG_UTF8 - The output is an integer that is set to one if UTF-8 support is avail- - able; otherwise it is set to zero. This value should normally be given + The output is an integer that is set to one if UTF-8 support is avail- + able; otherwise it is set to zero. This value should normally be given to the 8-bit version of this function, pcre_config(). If it is given to - the 16-bit or 32-bit version of this function, the result is + the 16-bit or 32-bit version of this function, the result is PCRE_ERROR_BADOPTION. PCRE_CONFIG_UTF16 The output is an integer that is set to one if UTF-16 support is avail- - able; otherwise it is set to zero. This value should normally be given + able; otherwise it is set to zero. This value should normally be given to the 16-bit version of this function, pcre16_config(). If it is given - to the 8-bit or 32-bit version of this function, the result is + to the 8-bit or 32-bit version of this function, the result is PCRE_ERROR_BADOPTION. PCRE_CONFIG_UTF32 The output is an integer that is set to one if UTF-32 support is avail- - able; otherwise it is set to zero. This value should normally be given + able; otherwise it is set to zero. This value should normally be given to the 32-bit version of this function, pcre32_config(). If it is given - to the 8-bit or 16-bit version of this function, the result is + to the 8-bit or 16-bit version of this function, the result is PCRE_ERROR_BADOPTION. PCRE_CONFIG_UNICODE_PROPERTIES - The output is an integer that is set to one if support for Unicode + The output is an integer that is set to one if support for Unicode character properties is available; otherwise it is set to zero. PCRE_CONFIG_JIT @@ -1923,55 +1936,58 @@ CHECKING BUILD-TIME OPTIONS PCRE_CONFIG_JITTARGET - The output is a pointer to a zero-terminated "const char *" string. If + The output is a pointer to a zero-terminated "const char *" string. If JIT support is available, the string contains the name of the architec- - ture for which the JIT compiler is configured, for example "x86 32bit - (little endian + unaligned)". If JIT support is not available, the + ture for which the JIT compiler is configured, for example "x86 32bit + (little endian + unaligned)". If JIT support is not available, the result is NULL. PCRE_CONFIG_NEWLINE - The output is an integer whose value specifies the default character - sequence that is recognized as meaning "newline". The values that are + The output is an integer whose value specifies the default character + sequence that is recognized as meaning "newline". The values that are supported in ASCII/Unicode environments are: 10 for LF, 13 for CR, 3338 - for CRLF, -2 for ANYCRLF, and -1 for ANY. In EBCDIC environments, CR, - ANYCRLF, and ANY yield the same values. However, the value for LF is - normally 21, though some EBCDIC environments use 37. The corresponding - values for CRLF are 3349 and 3365. The default should normally corre- + for CRLF, -2 for ANYCRLF, and -1 for ANY. In EBCDIC environments, CR, + ANYCRLF, and ANY yield the same values. However, the value for LF is + normally 21, though some EBCDIC environments use 37. The corresponding + values for CRLF are 3349 and 3365. The default should normally corre- spond to the standard sequence for your operating system. PCRE_CONFIG_BSR The output is an integer whose value indicates what character sequences - the \R escape sequence matches by default. A value of 0 means that \R - matches any Unicode line ending sequence; a value of 1 means that \R + the \R escape sequence matches by default. A value of 0 means that \R + matches any Unicode line ending sequence; a value of 1 means that \R matches only CR, LF, or CRLF. The default can be overridden when a pat- tern is compiled or matched. PCRE_CONFIG_LINK_SIZE - The output is an integer that contains the number of bytes used for + The output is an integer that contains the number of bytes used for internal linkage in compiled regular expressions. For the 8-bit library, the value can be 2, 3, or 4. For the 16-bit library, the value - is either 2 or 4 and is still a number of bytes. For the 32-bit + is either 2 or 4 and is still a number of bytes. For the 32-bit library, the value is either 2 or 4 and is still a number of bytes. The default value of 2 is sufficient for all but the most massive patterns, - since it allows the compiled pattern to be up to 64K in size. Larger - values allow larger regular expressions to be compiled, at the expense + since it allows the compiled pattern to be up to 64K in size. Larger + values allow larger regular expressions to be compiled, at the expense of slower matching. PCRE_CONFIG_POSIX_MALLOC_THRESHOLD - The output is an integer that contains the threshold above which the - POSIX interface uses malloc() for output vectors. Further details are + The output is an integer that contains the threshold above which the + POSIX interface uses malloc() for output vectors. Further details are given in the pcreposix documentation. PCRE_CONFIG_PARENS_LIMIT The output is a long integer that gives the maximum depth of nesting of - parentheses (of any kind) in a pattern. This limit is imposed to cap + parentheses (of any kind) in a pattern. This limit is imposed to cap the amount of system stack used when a pattern is compiled. It is spec- - ified when PCRE is built; the default is 250. + ified when PCRE is built; the default is 250. This limit does not take + into account the stack that may already be used by the calling applica- + tion. For finer control over compilation stack usage, you can set a + pointer to an external checking function in pcre_stack_guard. PCRE_CONFIG_MATCH_LIMIT @@ -2474,6 +2490,8 @@ COMPILATION ERROR CODES 81 missing opening brace after \o 82 parentheses are too deeply nested 83 invalid range in character class + 84 group name must start with a non-digit + 85 parentheses are too deeply nested (stack check) The numbers 32 and 10000 in errors 48 and 49 are defaults; different values may be used if the limits were changed when PCRE was built. @@ -2714,12 +2732,16 @@ INFORMATION ABOUT A PATTERN tion. External callers can cause PCRE to use its internal tables by passing a NULL table pointer. - PCRE_INFO_FIRSTBYTE + PCRE_INFO_FIRSTBYTE (deprecated) Return information about the first data unit of any matched string, for - a non-anchored pattern. (The name of this option refers to the 8-bit - library, where data units are bytes.) The fourth argument should point - to an int variable. + a non-anchored pattern. The name of this option refers to the 8-bit + library, where data units are bytes. The fourth argument should point + to an int variable. Negative values are used for special cases. How- + ever, this means that when the 32-bit library is in non-UTF-32 mode, + the full 32-bit range of characters cannot be returned. For this rea- + son, this value is deprecated; use PCRE_INFO_FIRSTCHARACTERFLAGS and + PCRE_INFO_FIRSTCHARACTER instead. If there is a fixed first value, for example, the letter "c" from a pattern such as (cat|cow|coyote), its value is returned. In the 8-bit @@ -2739,10 +2761,38 @@ INFORMATION ABOUT A PATTERN of a subject string or after any newline within the string. Otherwise -2 is returned. For anchored patterns, -2 is returned. - Since for the 32-bit library using the non-UTF-32 mode, this function - is unable to return the full 32-bit range of the character, this value - is deprecated; instead the PCRE_INFO_FIRSTCHARACTERFLAGS and - PCRE_INFO_FIRSTCHARACTER values should be used. + PCRE_INFO_FIRSTCHARACTER + + Return the value of the first data unit (non-UTF character) of any + matched string in the situation where PCRE_INFO_FIRSTCHARACTERFLAGS + returns 1; otherwise return 0. The fourth argument should point to an + uint_t variable. + + In the 8-bit library, the value is always less than 256. In the 16-bit + library the value can be up to 0xffff. In the 32-bit library in UTF-32 + mode the value can be up to 0x10ffff, and up to 0xffffffff when not + using UTF-32 mode. + + PCRE_INFO_FIRSTCHARACTERFLAGS + + Return information about the first data unit of any matched string, for + a non-anchored pattern. The fourth argument should point to an int + variable. + + If there is a fixed first value, for example, the letter "c" from a + pattern such as (cat|cow|coyote), 1 is returned, and the character + value can be retrieved using PCRE_INFO_FIRSTCHARACTER. If there is no + fixed first value, and if either + + (a) the pattern was compiled with the PCRE_MULTILINE option, and every + branch starts with "^", or + + (b) every branch of the pattern starts with ".*" and PCRE_DOTALL is not + set (if it were set, the pattern would be anchored), + + 2 is returned, indicating that the pattern matches only at the start of + a subject string or after any newline within the string. Otherwise 0 is + returned. For anchored patterns, 0 is returned. PCRE_INFO_FIRSTTABLE @@ -2954,57 +3004,24 @@ INFORMATION ABOUT A PATTERN option so that it can be saved and restored (see the pcreprecompile documentation for details). - PCRE_INFO_FIRSTCHARACTERFLAGS - - Return information about the first data unit of any matched string, for - a non-anchored pattern. The fourth argument should point to an int - variable. - - If there is a fixed first value, for example, the letter "c" from a - pattern such as (cat|cow|coyote), 1 is returned, and the character - value can be retrieved using PCRE_INFO_FIRSTCHARACTER. - - If there is no fixed first value, and if either - - (a) the pattern was compiled with the PCRE_MULTILINE option, and every - branch starts with "^", or - - (b) every branch of the pattern starts with ".*" and PCRE_DOTALL is not - set (if it were set, the pattern would be anchored), - - 2 is returned, indicating that the pattern matches only at the start of - a subject string or after any newline within the string. Otherwise 0 is - returned. For anchored patterns, 0 is returned. - - PCRE_INFO_FIRSTCHARACTER - - Return the fixed first character value in the situation where - PCRE_INFO_FIRSTCHARACTERFLAGS returns 1; otherwise return 0. The fourth - argument should point to an uint_t variable. - - In the 8-bit library, the value is always less than 256. In the 16-bit - library the value can be up to 0xffff. In the 32-bit library in UTF-32 - mode the value can be up to 0x10ffff, and up to 0xffffffff when not - using UTF-32 mode. - PCRE_INFO_REQUIREDCHARFLAGS - Returns 1 if there is a rightmost literal data unit that must exist in + Returns 1 if there is a rightmost literal data unit that must exist in any matched string, other than at its start. The fourth argument should - point to an int variable. If there is no such value, 0 is returned. If + point to an int variable. If there is no such value, 0 is returned. If returning 1, the character value itself can be retrieved using PCRE_INFO_REQUIREDCHAR. For anchored patterns, a last literal value is recorded only if it fol- - lows something of variable length. For example, for the pattern - /^a\d+z\d+/ the returned value 1 (with "z" returned from + lows something of variable length. For example, for the pattern + /^a\d+z\d+/ the returned value 1 (with "z" returned from PCRE_INFO_REQUIREDCHAR), but for /^a\dz\d/ the returned value is 0. PCRE_INFO_REQUIREDCHAR - Return the value of the rightmost literal data unit that must exist in - any matched string, other than at its start, if such a value has been - recorded. The fourth argument should point to an uint32_t variable. If + Return the value of the rightmost literal data unit that must exist in + any matched string, other than at its start, if such a value has been + recorded. The fourth argument should point to an uint32_t variable. If there is no such value, 0 is returned. @@ -3012,21 +3029,21 @@ REFERENCE COUNTS int pcre_refcount(pcre *code, int adjust); - The pcre_refcount() function is used to maintain a reference count in + The pcre_refcount() function is used to maintain a reference count in the data block that contains a compiled pattern. It is provided for the - benefit of applications that operate in an object-oriented manner, + benefit of applications that operate in an object-oriented manner, where different parts of the application may be using the same compiled pattern, but you want to free the block when they are all done. When a pattern is compiled, the reference count field is initialized to - zero. It is changed only by calling this function, whose action is to - add the adjust value (which may be positive or negative) to it. The + zero. It is changed only by calling this function, whose action is to + add the adjust value (which may be positive or negative) to it. The yield of the function is the new value. However, the value of the count - is constrained to lie between 0 and 65535, inclusive. If the new value + is constrained to lie between 0 and 65535, inclusive. If the new value is outside these limits, it is forced to the appropriate limit value. - Except when it is zero, the reference count is not correctly preserved - if a pattern is compiled on one host and then transferred to a host + Except when it is zero, the reference count is not correctly preserved + if a pattern is compiled on one host and then transferred to a host whose byte-order is different. (This seems a highly unlikely scenario.) @@ -3036,22 +3053,22 @@ MATCHING A PATTERN: THE TRADITIONAL FUNCTION const char *subject, int length, int startoffset, int options, int *ovector, int ovecsize); - The function pcre_exec() is called to match a subject string against a - compiled pattern, which is passed in the code argument. If the pattern - was studied, the result of the study should be passed in the extra - argument. You can call pcre_exec() with the same code and extra argu- - ments as many times as you like, in order to match different subject + The function pcre_exec() is called to match a subject string against a + compiled pattern, which is passed in the code argument. If the pattern + was studied, the result of the study should be passed in the extra + argument. You can call pcre_exec() with the same code and extra argu- + ments as many times as you like, in order to match different subject strings with the same pattern. - This function is the main matching facility of the library, and it - operates in a Perl-like manner. For specialist use there is also an - alternative matching function, which is described below in the section + This function is the main matching facility of the library, and it + operates in a Perl-like manner. For specialist use there is also an + alternative matching function, which is described below in the section about the pcre_dfa_exec() function. - In most applications, the pattern will have been compiled (and option- - ally studied) in the same process that calls pcre_exec(). However, it + In most applications, the pattern will have been compiled (and option- + ally studied) in the same process that calls pcre_exec(). However, it is possible to save compiled patterns and study data, and then use them - later in different processes, possibly even on different hosts. For a + later in different processes, possibly even on different hosts. For a discussion about this, see the pcreprecompile documentation. Here is an example of a simple call to pcre_exec(): @@ -3070,10 +3087,10 @@ MATCHING A PATTERN: THE TRADITIONAL FUNCTION Extra data for pcre_exec() - If the extra argument is not NULL, it must point to a pcre_extra data - block. The pcre_study() function returns such a block (when it doesn't - return NULL), but you can also create one for yourself, and pass addi- - tional information in it. The pcre_extra block contains the following + If the extra argument is not NULL, it must point to a pcre_extra data + block. The pcre_study() function returns such a block (when it doesn't + return NULL), but you can also create one for yourself, and pass addi- + tional information in it. The pcre_extra block contains the following fields (not necessarily in this order): unsigned long int flags; @@ -3085,13 +3102,13 @@ MATCHING A PATTERN: THE TRADITIONAL FUNCTION const unsigned char *tables; unsigned char **mark; - In the 16-bit version of this structure, the mark field has type + In the 16-bit version of this structure, the mark field has type "PCRE_UCHAR16 **". - In the 32-bit version of this structure, the mark field has type + In the 32-bit version of this structure, the mark field has type "PCRE_UCHAR32 **". - The flags field is used to specify which of the other fields are set. + The flags field is used to specify which of the other fields are set. The flag bits are: PCRE_EXTRA_CALLOUT_DATA @@ -3102,134 +3119,134 @@ MATCHING A PATTERN: THE TRADITIONAL FUNCTION PCRE_EXTRA_STUDY_DATA PCRE_EXTRA_TABLES - Other flag bits should be set to zero. The study_data field and some- - times the executable_jit field are set in the pcre_extra block that is - returned by pcre_study(), together with the appropriate flag bits. You - should not set these yourself, but you may add to the block by setting + Other flag bits should be set to zero. The study_data field and some- + times the executable_jit field are set in the pcre_extra block that is + returned by pcre_study(), together with the appropriate flag bits. You + should not set these yourself, but you may add to the block by setting other fields and their corresponding flag bits. The match_limit field provides a means of preventing PCRE from using up - a vast amount of resources when running patterns that are not going to - match, but which have a very large number of possibilities in their - search trees. The classic example is a pattern that uses nested unlim- + a vast amount of resources when running patterns that are not going to + match, but which have a very large number of possibilities in their + search trees. The classic example is a pattern that uses nested unlim- ited repeats. - Internally, pcre_exec() uses a function called match(), which it calls - repeatedly (sometimes recursively). The limit set by match_limit is - imposed on the number of times this function is called during a match, - which has the effect of limiting the amount of backtracking that can + Internally, pcre_exec() uses a function called match(), which it calls + repeatedly (sometimes recursively). The limit set by match_limit is + imposed on the number of times this function is called during a match, + which has the effect of limiting the amount of backtracking that can take place. For patterns that are not anchored, the count restarts from zero for each position in the subject string. When pcre_exec() is called with a pattern that was successfully studied - with a JIT option, the way that the matching is executed is entirely + with a JIT option, the way that the matching is executed is entirely different. However, there is still the possibility of runaway matching that goes on for a very long time, and so the match_limit value is also used in this case (but in a different way) to limit how long the match- ing can continue. - The default value for the limit can be set when PCRE is built; the - default default is 10 million, which handles all but the most extreme - cases. You can override the default by suppling pcre_exec() with a - pcre_extra block in which match_limit is set, and - PCRE_EXTRA_MATCH_LIMIT is set in the flags field. If the limit is + The default value for the limit can be set when PCRE is built; the + default default is 10 million, which handles all but the most extreme + cases. You can override the default by suppling pcre_exec() with a + pcre_extra block in which match_limit is set, and + PCRE_EXTRA_MATCH_LIMIT is set in the flags field. If the limit is exceeded, pcre_exec() returns PCRE_ERROR_MATCHLIMIT. - A value for the match limit may also be supplied by an item at the + A value for the match limit may also be supplied by an item at the start of a pattern of the form (*LIMIT_MATCH=d) - where d is a decimal number. However, such a setting is ignored unless - d is less than the limit set by the caller of pcre_exec() or, if no + where d is a decimal number. However, such a setting is ignored unless + d is less than the limit set by the caller of pcre_exec() or, if no such limit is set, less than the default. - The match_limit_recursion field is similar to match_limit, but instead + The match_limit_recursion field is similar to match_limit, but instead of limiting the total number of times that match() is called, it limits - the depth of recursion. The recursion depth is a smaller number than - the total number of calls, because not all calls to match() are recur- + the depth of recursion. The recursion depth is a smaller number than + the total number of calls, because not all calls to match() are recur- sive. This limit is of use only if it is set smaller than match_limit. - Limiting the recursion depth limits the amount of machine stack that - can be used, or, when PCRE has been compiled to use memory on the heap - instead of the stack, the amount of heap memory that can be used. This - limit is not relevant, and is ignored, when matching is done using JIT + Limiting the recursion depth limits the amount of machine stack that + can be used, or, when PCRE has been compiled to use memory on the heap + instead of the stack, the amount of heap memory that can be used. This + limit is not relevant, and is ignored, when matching is done using JIT compiled code. - The default value for match_limit_recursion can be set when PCRE is - built; the default default is the same value as the default for - match_limit. You can override the default by suppling pcre_exec() with - a pcre_extra block in which match_limit_recursion is set, and - PCRE_EXTRA_MATCH_LIMIT_RECURSION is set in the flags field. If the + The default value for match_limit_recursion can be set when PCRE is + built; the default default is the same value as the default for + match_limit. You can override the default by suppling pcre_exec() with + a pcre_extra block in which match_limit_recursion is set, and + PCRE_EXTRA_MATCH_LIMIT_RECURSION is set in the flags field. If the limit is exceeded, pcre_exec() returns PCRE_ERROR_RECURSIONLIMIT. - A value for the recursion limit may also be supplied by an item at the + A value for the recursion limit may also be supplied by an item at the start of a pattern of the form (*LIMIT_RECURSION=d) - where d is a decimal number. However, such a setting is ignored unless - d is less than the limit set by the caller of pcre_exec() or, if no + where d is a decimal number. However, such a setting is ignored unless + d is less than the limit set by the caller of pcre_exec() or, if no such limit is set, less than the default. - The callout_data field is used in conjunction with the "callout" fea- + The callout_data field is used in conjunction with the "callout" fea- ture, and is described in the pcrecallout documentation. - The tables field is provided for use with patterns that have been pre- + The tables field is provided for use with patterns that have been pre- compiled using custom character tables, saved to disc or elsewhere, and - then reloaded, because the tables that were used to compile a pattern - are not saved with it. See the pcreprecompile documentation for a dis- - cussion of saving compiled patterns for later use. If NULL is passed + then reloaded, because the tables that were used to compile a pattern + are not saved with it. See the pcreprecompile documentation for a dis- + cussion of saving compiled patterns for later use. If NULL is passed using this mechanism, it forces PCRE's internal tables to be used. - Warning: The tables that pcre_exec() uses must be the same as those - that were used when the pattern was compiled. If this is not the case, + Warning: The tables that pcre_exec() uses must be the same as those + that were used when the pattern was compiled. If this is not the case, the behaviour of pcre_exec() is undefined. Therefore, when a pattern is - compiled and matched in the same process, this field should never be + compiled and matched in the same process, this field should never be set. In this (the most common) case, the correct table pointer is auto- - matically passed with the compiled pattern from pcre_compile() to + matically passed with the compiled pattern from pcre_compile() to pcre_exec(). - If PCRE_EXTRA_MARK is set in the flags field, the mark field must be - set to point to a suitable variable. If the pattern contains any back- - tracking control verbs such as (*MARK:NAME), and the execution ends up - with a name to pass back, a pointer to the name string (zero termi- - nated) is placed in the variable pointed to by the mark field. The - names are within the compiled pattern; if you wish to retain such a - name you must copy it before freeing the memory of a compiled pattern. - If there is no name to pass back, the variable pointed to by the mark - field is set to NULL. For details of the backtracking control verbs, + If PCRE_EXTRA_MARK is set in the flags field, the mark field must be + set to point to a suitable variable. If the pattern contains any back- + tracking control verbs such as (*MARK:NAME), and the execution ends up + with a name to pass back, a pointer to the name string (zero termi- + nated) is placed in the variable pointed to by the mark field. The + names are within the compiled pattern; if you wish to retain such a + name you must copy it before freeing the memory of a compiled pattern. + If there is no name to pass back, the variable pointed to by the mark + field is set to NULL. For details of the backtracking control verbs, see the section entitled "Backtracking control" in the pcrepattern doc- umentation. Option bits for pcre_exec() - The unused bits of the options argument for pcre_exec() must be zero. - The only bits that may be set are PCRE_ANCHORED, PCRE_NEWLINE_xxx, - PCRE_NOTBOL, PCRE_NOTEOL, PCRE_NOTEMPTY, PCRE_NOTEMPTY_ATSTART, - PCRE_NO_START_OPTIMIZE, PCRE_NO_UTF8_CHECK, PCRE_PARTIAL_HARD, and + The unused bits of the options argument for pcre_exec() must be zero. + The only bits that may be set are PCRE_ANCHORED, PCRE_NEWLINE_xxx, + PCRE_NOTBOL, PCRE_NOTEOL, PCRE_NOTEMPTY, PCRE_NOTEMPTY_ATSTART, + PCRE_NO_START_OPTIMIZE, PCRE_NO_UTF8_CHECK, PCRE_PARTIAL_HARD, and PCRE_PARTIAL_SOFT. - If the pattern was successfully studied with one of the just-in-time + If the pattern was successfully studied with one of the just-in-time (JIT) compile options, the only supported options for JIT execution are - PCRE_NO_UTF8_CHECK, PCRE_NOTBOL, PCRE_NOTEOL, PCRE_NOTEMPTY, - PCRE_NOTEMPTY_ATSTART, PCRE_PARTIAL_HARD, and PCRE_PARTIAL_SOFT. If an - unsupported option is used, JIT execution is disabled and the normal + PCRE_NO_UTF8_CHECK, PCRE_NOTBOL, PCRE_NOTEOL, PCRE_NOTEMPTY, + PCRE_NOTEMPTY_ATSTART, PCRE_PARTIAL_HARD, and PCRE_PARTIAL_SOFT. If an + unsupported option is used, JIT execution is disabled and the normal interpretive code in pcre_exec() is run. PCRE_ANCHORED - The PCRE_ANCHORED option limits pcre_exec() to matching at the first - matching position. If a pattern was compiled with PCRE_ANCHORED, or - turned out to be anchored by virtue of its contents, it cannot be made + The PCRE_ANCHORED option limits pcre_exec() to matching at the first + matching position. If a pattern was compiled with PCRE_ANCHORED, or + turned out to be anchored by virtue of its contents, it cannot be made unachored at matching time. PCRE_BSR_ANYCRLF PCRE_BSR_UNICODE These options (which are mutually exclusive) control what the \R escape - sequence matches. The choice is either to match only CR, LF, or CRLF, - or to match any Unicode newline sequence. These options override the + sequence matches. The choice is either to match only CR, LF, or CRLF, + or to match any Unicode newline sequence. These options override the choice that was made or defaulted when the pattern was compiled. PCRE_NEWLINE_CR @@ -3238,345 +3255,345 @@ MATCHING A PATTERN: THE TRADITIONAL FUNCTION PCRE_NEWLINE_ANYCRLF PCRE_NEWLINE_ANY - These options override the newline definition that was chosen or - defaulted when the pattern was compiled. For details, see the descrip- - tion of pcre_compile() above. During matching, the newline choice - affects the behaviour of the dot, circumflex, and dollar metacharac- - ters. It may also alter the way the match position is advanced after a + These options override the newline definition that was chosen or + defaulted when the pattern was compiled. For details, see the descrip- + tion of pcre_compile() above. During matching, the newline choice + affects the behaviour of the dot, circumflex, and dollar metacharac- + ters. It may also alter the way the match position is advanced after a match failure for an unanchored pattern. - When PCRE_NEWLINE_CRLF, PCRE_NEWLINE_ANYCRLF, or PCRE_NEWLINE_ANY is - set, and a match attempt for an unanchored pattern fails when the cur- - rent position is at a CRLF sequence, and the pattern contains no - explicit matches for CR or LF characters, the match position is + When PCRE_NEWLINE_CRLF, PCRE_NEWLINE_ANYCRLF, or PCRE_NEWLINE_ANY is + set, and a match attempt for an unanchored pattern fails when the cur- + rent position is at a CRLF sequence, and the pattern contains no + explicit matches for CR or LF characters, the match position is advanced by two characters instead of one, in other words, to after the CRLF. The above rule is a compromise that makes the most common cases work as - expected. For example, if the pattern is .+A (and the PCRE_DOTALL + expected. For example, if the pattern is .+A (and the PCRE_DOTALL option is not set), it does not match the string "\r\nA" because, after - failing at the start, it skips both the CR and the LF before retrying. - However, the pattern [\r\n]A does match that string, because it con- + failing at the start, it skips both the CR and the LF before retrying. + However, the pattern [\r\n]A does match that string, because it con- tains an explicit CR or LF reference, and so advances only by one char- acter after the first failure. An explicit match for CR of LF is either a literal appearance of one of - those characters, or one of the \r or \n escape sequences. Implicit - matches such as [^X] do not count, nor does \s (which includes CR and + those characters, or one of the \r or \n escape sequences. Implicit + matches such as [^X] do not count, nor does \s (which includes CR and LF in the characters that it matches). - Notwithstanding the above, anomalous effects may still occur when CRLF + Notwithstanding the above, anomalous effects may still occur when CRLF is a valid newline sequence and explicit \r or \n escapes appear in the pattern. PCRE_NOTBOL This option specifies that first character of the subject string is not - the beginning of a line, so the circumflex metacharacter should not - match before it. Setting this without PCRE_MULTILINE (at compile time) - causes circumflex never to match. This option affects only the behav- + the beginning of a line, so the circumflex metacharacter should not + match before it. Setting this without PCRE_MULTILINE (at compile time) + causes circumflex never to match. This option affects only the behav- iour of the circumflex metacharacter. It does not affect \A. PCRE_NOTEOL This option specifies that the end of the subject string is not the end - of a line, so the dollar metacharacter should not match it nor (except - in multiline mode) a newline immediately before it. Setting this with- + of a line, so the dollar metacharacter should not match it nor (except + in multiline mode) a newline immediately before it. Setting this with- out PCRE_MULTILINE (at compile time) causes dollar never to match. This - option affects only the behaviour of the dollar metacharacter. It does + option affects only the behaviour of the dollar metacharacter. It does not affect \Z or \z. PCRE_NOTEMPTY An empty string is not considered to be a valid match if this option is - set. If there are alternatives in the pattern, they are tried. If all - the alternatives match the empty string, the entire match fails. For + set. If there are alternatives in the pattern, they are tried. If all + the alternatives match the empty string, the entire match fails. For example, if the pattern a?b? - is applied to a string not beginning with "a" or "b", it matches an - empty string at the start of the subject. With PCRE_NOTEMPTY set, this + is applied to a string not beginning with "a" or "b", it matches an + empty string at the start of the subject. With PCRE_NOTEMPTY set, this match is not valid, so PCRE searches further into the string for occur- rences of "a" or "b". PCRE_NOTEMPTY_ATSTART - This is like PCRE_NOTEMPTY, except that an empty string match that is - not at the start of the subject is permitted. If the pattern is + This is like PCRE_NOTEMPTY, except that an empty string match that is + not at the start of the subject is permitted. If the pattern is anchored, such a match can occur only if the pattern contains \K. - Perl has no direct equivalent of PCRE_NOTEMPTY or - PCRE_NOTEMPTY_ATSTART, but it does make a special case of a pattern - match of the empty string within its split() function, and when using - the /g modifier. It is possible to emulate Perl's behaviour after + Perl has no direct equivalent of PCRE_NOTEMPTY or + PCRE_NOTEMPTY_ATSTART, but it does make a special case of a pattern + match of the empty string within its split() function, and when using + the /g modifier. It is possible to emulate Perl's behaviour after matching a null string by first trying the match again at the same off- - set with PCRE_NOTEMPTY_ATSTART and PCRE_ANCHORED, and then if that + set with PCRE_NOTEMPTY_ATSTART and PCRE_ANCHORED, and then if that fails, by advancing the starting offset (see below) and trying an ordi- - nary match again. There is some code that demonstrates how to do this - in the pcredemo sample program. In the most general case, you have to - check to see if the newline convention recognizes CRLF as a newline, - and if so, and the current character is CR followed by LF, advance the + nary match again. There is some code that demonstrates how to do this + in the pcredemo sample program. In the most general case, you have to + check to see if the newline convention recognizes CRLF as a newline, + and if so, and the current character is CR followed by LF, advance the starting offset by two characters instead of one. PCRE_NO_START_OPTIMIZE - There are a number of optimizations that pcre_exec() uses at the start - of a match, in order to speed up the process. For example, if it is + There are a number of optimizations that pcre_exec() uses at the start + of a match, in order to speed up the process. For example, if it is known that an unanchored match must start with a specific character, it - searches the subject for that character, and fails immediately if it - cannot find it, without actually running the main matching function. + searches the subject for that character, and fails immediately if it + cannot find it, without actually running the main matching function. This means that a special item such as (*COMMIT) at the start of a pat- - tern is not considered until after a suitable starting point for the - match has been found. Also, when callouts or (*MARK) items are in use, + tern is not considered until after a suitable starting point for the + match has been found. Also, when callouts or (*MARK) items are in use, these "start-up" optimizations can cause them to be skipped if the pat- tern is never actually used. The start-up optimizations are in effect a pre-scan of the subject that takes place before the pattern is run. - The PCRE_NO_START_OPTIMIZE option disables the start-up optimizations, - possibly causing performance to suffer, but ensuring that in cases - where the result is "no match", the callouts do occur, and that items + The PCRE_NO_START_OPTIMIZE option disables the start-up optimizations, + possibly causing performance to suffer, but ensuring that in cases + where the result is "no match", the callouts do occur, and that items such as (*COMMIT) and (*MARK) are considered at every possible starting - position in the subject string. If PCRE_NO_START_OPTIMIZE is set at - compile time, it cannot be unset at matching time. The use of + position in the subject string. If PCRE_NO_START_OPTIMIZE is set at + compile time, it cannot be unset at matching time. The use of PCRE_NO_START_OPTIMIZE at matching time (that is, passing it to - pcre_exec()) disables JIT execution; in this situation, matching is + pcre_exec()) disables JIT execution; in this situation, matching is always done using interpretively. - Setting PCRE_NO_START_OPTIMIZE can change the outcome of a matching + Setting PCRE_NO_START_OPTIMIZE can change the outcome of a matching operation. Consider the pattern (*COMMIT)ABC - When this is compiled, PCRE records the fact that a match must start - with the character "A". Suppose the subject string is "DEFABC". The - start-up optimization scans along the subject, finds "A" and runs the - first match attempt from there. The (*COMMIT) item means that the pat- - tern must match the current starting position, which in this case, it - does. However, if the same match is run with PCRE_NO_START_OPTIMIZE - set, the initial scan along the subject string does not happen. The - first match attempt is run starting from "D" and when this fails, - (*COMMIT) prevents any further matches being tried, so the overall - result is "no match". If the pattern is studied, more start-up opti- - mizations may be used. For example, a minimum length for the subject + When this is compiled, PCRE records the fact that a match must start + with the character "A". Suppose the subject string is "DEFABC". The + start-up optimization scans along the subject, finds "A" and runs the + first match attempt from there. The (*COMMIT) item means that the pat- + tern must match the current starting position, which in this case, it + does. However, if the same match is run with PCRE_NO_START_OPTIMIZE + set, the initial scan along the subject string does not happen. The + first match attempt is run starting from "D" and when this fails, + (*COMMIT) prevents any further matches being tried, so the overall + result is "no match". If the pattern is studied, more start-up opti- + mizations may be used. For example, a minimum length for the subject may be recorded. Consider the pattern (*MARK:A)(X|Y) - The minimum length for a match is one character. If the subject is - "ABC", there will be attempts to match "ABC", "BC", "C", and then - finally an empty string. If the pattern is studied, the final attempt - does not take place, because PCRE knows that the subject is too short, - and so the (*MARK) is never encountered. In this case, studying the - pattern does not affect the overall match result, which is still "no + The minimum length for a match is one character. If the subject is + "ABC", there will be attempts to match "ABC", "BC", "C", and then + finally an empty string. If the pattern is studied, the final attempt + does not take place, because PCRE knows that the subject is too short, + and so the (*MARK) is never encountered. In this case, studying the + pattern does not affect the overall match result, which is still "no match", but it does affect the auxiliary information that is returned. PCRE_NO_UTF8_CHECK When PCRE_UTF8 is set at compile time, the validity of the subject as a - UTF-8 string is automatically checked when pcre_exec() is subsequently + UTF-8 string is automatically checked when pcre_exec() is subsequently called. The entire string is checked before any other processing takes - place. The value of startoffset is also checked to ensure that it - points to the start of a UTF-8 character. There is a discussion about - the validity of UTF-8 strings in the pcreunicode page. If an invalid - sequence of bytes is found, pcre_exec() returns the error + place. The value of startoffset is also checked to ensure that it + points to the start of a UTF-8 character. There is a discussion about + the validity of UTF-8 strings in the pcreunicode page. If an invalid + sequence of bytes is found, pcre_exec() returns the error PCRE_ERROR_BADUTF8 or, if PCRE_PARTIAL_HARD is set and the problem is a truncated character at the end of the subject, PCRE_ERROR_SHORTUTF8. In - both cases, information about the precise nature of the error may also - be returned (see the descriptions of these errors in the section enti- - tled Error return values from pcre_exec() below). If startoffset con- + both cases, information about the precise nature of the error may also + be returned (see the descriptions of these errors in the section enti- + tled Error return values from pcre_exec() below). If startoffset con- tains a value that does not point to the start of a UTF-8 character (or to the end of the subject), PCRE_ERROR_BADUTF8_OFFSET is returned. - If you already know that your subject is valid, and you want to skip - these checks for performance reasons, you can set the - PCRE_NO_UTF8_CHECK option when calling pcre_exec(). You might want to - do this for the second and subsequent calls to pcre_exec() if you are - making repeated calls to find all the matches in a single subject - string. However, you should be sure that the value of startoffset - points to the start of a character (or the end of the subject). When + If you already know that your subject is valid, and you want to skip + these checks for performance reasons, you can set the + PCRE_NO_UTF8_CHECK option when calling pcre_exec(). You might want to + do this for the second and subsequent calls to pcre_exec() if you are + making repeated calls to find all the matches in a single subject + string. However, you should be sure that the value of startoffset + points to the start of a character (or the end of the subject). When PCRE_NO_UTF8_CHECK is set, the effect of passing an invalid string as a - subject or an invalid value of startoffset is undefined. Your program + subject or an invalid value of startoffset is undefined. Your program may crash or loop. PCRE_PARTIAL_HARD PCRE_PARTIAL_SOFT - These options turn on the partial matching feature. For backwards com- - patibility, PCRE_PARTIAL is a synonym for PCRE_PARTIAL_SOFT. A partial - match occurs if the end of the subject string is reached successfully, - but there are not enough subject characters to complete the match. If + These options turn on the partial matching feature. For backwards com- + patibility, PCRE_PARTIAL is a synonym for PCRE_PARTIAL_SOFT. A partial + match occurs if the end of the subject string is reached successfully, + but there are not enough subject characters to complete the match. If this happens when PCRE_PARTIAL_SOFT (but not PCRE_PARTIAL_HARD) is set, - matching continues by testing any remaining alternatives. Only if no - complete match can be found is PCRE_ERROR_PARTIAL returned instead of - PCRE_ERROR_NOMATCH. In other words, PCRE_PARTIAL_SOFT says that the - caller is prepared to handle a partial match, but only if no complete + matching continues by testing any remaining alternatives. Only if no + complete match can be found is PCRE_ERROR_PARTIAL returned instead of + PCRE_ERROR_NOMATCH. In other words, PCRE_PARTIAL_SOFT says that the + caller is prepared to handle a partial match, but only if no complete match can be found. - If PCRE_PARTIAL_HARD is set, it overrides PCRE_PARTIAL_SOFT. In this - case, if a partial match is found, pcre_exec() immediately returns - PCRE_ERROR_PARTIAL, without considering any other alternatives. In - other words, when PCRE_PARTIAL_HARD is set, a partial match is consid- + If PCRE_PARTIAL_HARD is set, it overrides PCRE_PARTIAL_SOFT. In this + case, if a partial match is found, pcre_exec() immediately returns + PCRE_ERROR_PARTIAL, without considering any other alternatives. In + other words, when PCRE_PARTIAL_HARD is set, a partial match is consid- ered to be more important that an alternative complete match. - In both cases, the portion of the string that was inspected when the + In both cases, the portion of the string that was inspected when the partial match was found is set as the first matching string. There is a - more detailed discussion of partial and multi-segment matching, with + more detailed discussion of partial and multi-segment matching, with examples, in the pcrepartial documentation. The string to be matched by pcre_exec() - The subject string is passed to pcre_exec() as a pointer in subject, a - length in length, and a starting offset in startoffset. The units for - length and startoffset are bytes for the 8-bit library, 16-bit data - items for the 16-bit library, and 32-bit data items for the 32-bit + The subject string is passed to pcre_exec() as a pointer in subject, a + length in length, and a starting offset in startoffset. The units for + length and startoffset are bytes for the 8-bit library, 16-bit data + items for the 16-bit library, and 32-bit data items for the 32-bit library. - If startoffset is negative or greater than the length of the subject, - pcre_exec() returns PCRE_ERROR_BADOFFSET. When the starting offset is - zero, the search for a match starts at the beginning of the subject, - and this is by far the most common case. In UTF-8 or UTF-16 mode, the - offset must point to the start of a character, or the end of the sub- - ject (in UTF-32 mode, one data unit equals one character, so all off- - sets are valid). Unlike the pattern string, the subject may contain + If startoffset is negative or greater than the length of the subject, + pcre_exec() returns PCRE_ERROR_BADOFFSET. When the starting offset is + zero, the search for a match starts at the beginning of the subject, + and this is by far the most common case. In UTF-8 or UTF-16 mode, the + offset must point to the start of a character, or the end of the sub- + ject (in UTF-32 mode, one data unit equals one character, so all off- + sets are valid). Unlike the pattern string, the subject may contain binary zeroes. - A non-zero starting offset is useful when searching for another match - in the same subject by calling pcre_exec() again after a previous suc- - cess. Setting startoffset differs from just passing over a shortened - string and setting PCRE_NOTBOL in the case of a pattern that begins + A non-zero starting offset is useful when searching for another match + in the same subject by calling pcre_exec() again after a previous suc- + cess. Setting startoffset differs from just passing over a shortened + string and setting PCRE_NOTBOL in the case of a pattern that begins with any kind of lookbehind. For example, consider the pattern \Biss\B - which finds occurrences of "iss" in the middle of words. (\B matches - only if the current position in the subject is not a word boundary.) - When applied to the string "Mississipi" the first call to pcre_exec() - finds the first occurrence. If pcre_exec() is called again with just - the remainder of the subject, namely "issipi", it does not match, + which finds occurrences of "iss" in the middle of words. (\B matches + only if the current position in the subject is not a word boundary.) + When applied to the string "Mississipi" the first call to pcre_exec() + finds the first occurrence. If pcre_exec() is called again with just + the remainder of the subject, namely "issipi", it does not match, because \B is always false at the start of the subject, which is deemed - to be a word boundary. However, if pcre_exec() is passed the entire + to be a word boundary. However, if pcre_exec() is passed the entire string again, but with startoffset set to 4, it finds the second occur- - rence of "iss" because it is able to look behind the starting point to + rence of "iss" because it is able to look behind the starting point to discover that it is preceded by a letter. - Finding all the matches in a subject is tricky when the pattern can + Finding all the matches in a subject is tricky when the pattern can match an empty string. It is possible to emulate Perl's /g behaviour by - first trying the match again at the same offset, with the - PCRE_NOTEMPTY_ATSTART and PCRE_ANCHORED options, and then if that - fails, advancing the starting offset and trying an ordinary match + first trying the match again at the same offset, with the + PCRE_NOTEMPTY_ATSTART and PCRE_ANCHORED options, and then if that + fails, advancing the starting offset and trying an ordinary match again. There is some code that demonstrates how to do this in the pcre- demo sample program. In the most general case, you have to check to see - if the newline convention recognizes CRLF as a newline, and if so, and + if the newline convention recognizes CRLF as a newline, and if so, and the current character is CR followed by LF, advance the starting offset by two characters instead of one. - If a non-zero starting offset is passed when the pattern is anchored, + If a non-zero starting offset is passed when the pattern is anchored, one attempt to match at the given offset is made. This can only succeed - if the pattern does not require the match to be at the start of the + if the pattern does not require the match to be at the start of the subject. How pcre_exec() returns captured substrings - In general, a pattern matches a certain portion of the subject, and in - addition, further substrings from the subject may be picked out by - parts of the pattern. Following the usage in Jeffrey Friedl's book, - this is called "capturing" in what follows, and the phrase "capturing - subpattern" is used for a fragment of a pattern that picks out a sub- - string. PCRE supports several other kinds of parenthesized subpattern + In general, a pattern matches a certain portion of the subject, and in + addition, further substrings from the subject may be picked out by + parts of the pattern. Following the usage in Jeffrey Friedl's book, + this is called "capturing" in what follows, and the phrase "capturing + subpattern" is used for a fragment of a pattern that picks out a sub- + string. PCRE supports several other kinds of parenthesized subpattern that do not cause substrings to be captured. Captured substrings are returned to the caller via a vector of integers - whose address is passed in ovector. The number of elements in the vec- - tor is passed in ovecsize, which must be a non-negative number. Note: + whose address is passed in ovector. The number of elements in the vec- + tor is passed in ovecsize, which must be a non-negative number. Note: this argument is NOT the size of ovector in bytes. - The first two-thirds of the vector is used to pass back captured sub- - strings, each substring using a pair of integers. The remaining third - of the vector is used as workspace by pcre_exec() while matching cap- - turing subpatterns, and is not available for passing back information. - The number passed in ovecsize should always be a multiple of three. If + The first two-thirds of the vector is used to pass back captured sub- + strings, each substring using a pair of integers. The remaining third + of the vector is used as workspace by pcre_exec() while matching cap- + turing subpatterns, and is not available for passing back information. + The number passed in ovecsize should always be a multiple of three. If it is not, it is rounded down. - When a match is successful, information about captured substrings is - returned in pairs of integers, starting at the beginning of ovector, - and continuing up to two-thirds of its length at the most. The first - element of each pair is set to the offset of the first character in a - substring, and the second is set to the offset of the first character - after the end of a substring. These values are always data unit off- - sets, even in UTF mode. They are byte offsets in the 8-bit library, - 16-bit data item offsets in the 16-bit library, and 32-bit data item + When a match is successful, information about captured substrings is + returned in pairs of integers, starting at the beginning of ovector, + and continuing up to two-thirds of its length at the most. The first + element of each pair is set to the offset of the first character in a + substring, and the second is set to the offset of the first character + after the end of a substring. These values are always data unit off- + sets, even in UTF mode. They are byte offsets in the 8-bit library, + 16-bit data item offsets in the 16-bit library, and 32-bit data item offsets in the 32-bit library. Note: they are not character counts. - The first pair of integers, ovector[0] and ovector[1], identify the - portion of the subject string matched by the entire pattern. The next - pair is used for the first capturing subpattern, and so on. The value + The first pair of integers, ovector[0] and ovector[1], identify the + portion of the subject string matched by the entire pattern. The next + pair is used for the first capturing subpattern, and so on. The value returned by pcre_exec() is one more than the highest numbered pair that - has been set. For example, if two substrings have been captured, the - returned value is 3. If there are no capturing subpatterns, the return + has been set. For example, if two substrings have been captured, the + returned value is 3. If there are no capturing subpatterns, the return value from a successful match is 1, indicating that just the first pair of offsets has been set. If a capturing subpattern is matched repeatedly, it is the last portion of the string that it matched that is returned. - If the vector is too small to hold all the captured substring offsets, + If the vector is too small to hold all the captured substring offsets, it is used as far as possible (up to two-thirds of its length), and the - function returns a value of zero. If neither the actual string matched - nor any captured substrings are of interest, pcre_exec() may be called - with ovector passed as NULL and ovecsize as zero. However, if the pat- - tern contains back references and the ovector is not big enough to - remember the related substrings, PCRE has to get additional memory for - use during matching. Thus it is usually advisable to supply an ovector + function returns a value of zero. If neither the actual string matched + nor any captured substrings are of interest, pcre_exec() may be called + with ovector passed as NULL and ovecsize as zero. However, if the pat- + tern contains back references and the ovector is not big enough to + remember the related substrings, PCRE has to get additional memory for + use during matching. Thus it is usually advisable to supply an ovector of reasonable size. - There are some cases where zero is returned (indicating vector over- - flow) when in fact the vector is exactly the right size for the final + There are some cases where zero is returned (indicating vector over- + flow) when in fact the vector is exactly the right size for the final match. For example, consider the pattern (a)(?:(b)c|bd) - If a vector of 6 elements (allowing for only 1 captured substring) is + If a vector of 6 elements (allowing for only 1 captured substring) is given with subject string "abd", pcre_exec() will try to set the second captured string, thereby recording a vector overflow, before failing to - match "c" and backing up to try the second alternative. The zero - return, however, does correctly indicate that the maximum number of + match "c" and backing up to try the second alternative. The zero + return, however, does correctly indicate that the maximum number of slots (namely 2) have been filled. In similar cases where there is tem- - porary overflow, but the final number of used slots is actually less + porary overflow, but the final number of used slots is actually less than the maximum, a non-zero value is returned. The pcre_fullinfo() function can be used to find out how many capturing - subpatterns there are in a compiled pattern. The smallest size for - ovector that will allow for n captured substrings, in addition to the + subpatterns there are in a compiled pattern. The smallest size for + ovector that will allow for n captured substrings, in addition to the offsets of the substring matched by the whole pattern, is (n+1)*3. - It is possible for capturing subpattern number n+1 to match some part + It is possible for capturing subpattern number n+1 to match some part of the subject when subpattern n has not been used at all. For example, - if the string "abc" is matched against the pattern (a|(z))(bc) the + if the string "abc" is matched against the pattern (a|(z))(bc) the return from the function is 4, and subpatterns 1 and 3 are matched, but - 2 is not. When this happens, both values in the offset pairs corre- + 2 is not. When this happens, both values in the offset pairs corre- sponding to unused subpatterns are set to -1. - Offset values that correspond to unused subpatterns at the end of the - expression are also set to -1. For example, if the string "abc" is - matched against the pattern (abc)(x(yz)?)? subpatterns 2 and 3 are not - matched. The return from the function is 2, because the highest used - capturing subpattern number is 1, and the offsets for for the second - and third capturing subpatterns (assuming the vector is large enough, + Offset values that correspond to unused subpatterns at the end of the + expression are also set to -1. For example, if the string "abc" is + matched against the pattern (abc)(x(yz)?)? subpatterns 2 and 3 are not + matched. The return from the function is 2, because the highest used + capturing subpattern number is 1, and the offsets for for the second + and third capturing subpatterns (assuming the vector is large enough, of course) are set to -1. - Note: Elements in the first two-thirds of ovector that do not corre- - spond to capturing parentheses in the pattern are never changed. That - is, if a pattern contains n capturing parentheses, no more than ovec- - tor[0] to ovector[2n+1] are set by pcre_exec(). The other elements (in + Note: Elements in the first two-thirds of ovector that do not corre- + spond to capturing parentheses in the pattern are never changed. That + is, if a pattern contains n capturing parentheses, no more than ovec- + tor[0] to ovector[2n+1] are set by pcre_exec(). The other elements (in the first two-thirds) retain whatever values they previously had. - Some convenience functions are provided for extracting the captured + Some convenience functions are provided for extracting the captured substrings as separate strings. These are described below. Error return values from pcre_exec() - If pcre_exec() fails, it returns a negative number. The following are + If pcre_exec() fails, it returns a negative number. The following are defined in the header file: PCRE_ERROR_NOMATCH (-1) @@ -3585,7 +3602,7 @@ MATCHING A PATTERN: THE TRADITIONAL FUNCTION PCRE_ERROR_NULL (-2) - Either code or subject was passed as NULL, or ovector was NULL and + Either code or subject was passed as NULL, or ovector was NULL and ovecsize was not zero. PCRE_ERROR_BADOPTION (-3) @@ -3594,82 +3611,82 @@ MATCHING A PATTERN: THE TRADITIONAL FUNCTION PCRE_ERROR_BADMAGIC (-4) - PCRE stores a 4-byte "magic number" at the start of the compiled code, + PCRE stores a 4-byte "magic number" at the start of the compiled code, to catch the case when it is passed a junk pointer and to detect when a pattern that was compiled in an environment of one endianness is run in - an environment with the other endianness. This is the error that PCRE + an environment with the other endianness. This is the error that PCRE gives when the magic number is not present. PCRE_ERROR_UNKNOWN_OPCODE (-5) While running the pattern match, an unknown item was encountered in the - compiled pattern. This error could be caused by a bug in PCRE or by + compiled pattern. This error could be caused by a bug in PCRE or by overwriting of the compiled pattern. PCRE_ERROR_NOMEMORY (-6) - If a pattern contains back references, but the ovector that is passed + If a pattern contains back references, but the ovector that is passed to pcre_exec() is not big enough to remember the referenced substrings, - PCRE gets a block of memory at the start of matching to use for this - purpose. If the call via pcre_malloc() fails, this error is given. The + PCRE gets a block of memory at the start of matching to use for this + purpose. If the call via pcre_malloc() fails, this error is given. The memory is automatically freed at the end of matching. - This error is also given if pcre_stack_malloc() fails in pcre_exec(). - This can happen only when PCRE has been compiled with --disable-stack- + This error is also given if pcre_stack_malloc() fails in pcre_exec(). + This can happen only when PCRE has been compiled with --disable-stack- for-recursion. PCRE_ERROR_NOSUBSTRING (-7) - This error is used by the pcre_copy_substring(), pcre_get_substring(), + This error is used by the pcre_copy_substring(), pcre_get_substring(), and pcre_get_substring_list() functions (see below). It is never returned by pcre_exec(). PCRE_ERROR_MATCHLIMIT (-8) - The backtracking limit, as specified by the match_limit field in a - pcre_extra structure (or defaulted) was reached. See the description + The backtracking limit, as specified by the match_limit field in a + pcre_extra structure (or defaulted) was reached. See the description above. PCRE_ERROR_CALLOUT (-9) This error is never generated by pcre_exec() itself. It is provided for - use by callout functions that want to yield a distinctive error code. + use by callout functions that want to yield a distinctive error code. See the pcrecallout documentation for details. PCRE_ERROR_BADUTF8 (-10) - A string that contains an invalid UTF-8 byte sequence was passed as a - subject, and the PCRE_NO_UTF8_CHECK option was not set. If the size of - the output vector (ovecsize) is at least 2, the byte offset to the - start of the the invalid UTF-8 character is placed in the first ele- - ment, and a reason code is placed in the second element. The reason + A string that contains an invalid UTF-8 byte sequence was passed as a + subject, and the PCRE_NO_UTF8_CHECK option was not set. If the size of + the output vector (ovecsize) is at least 2, the byte offset to the + start of the the invalid UTF-8 character is placed in the first ele- + ment, and a reason code is placed in the second element. The reason codes are listed in the following section. For backward compatibility, - if PCRE_PARTIAL_HARD is set and the problem is a truncated UTF-8 char- - acter at the end of the subject (reason codes 1 to 5), + if PCRE_PARTIAL_HARD is set and the problem is a truncated UTF-8 char- + acter at the end of the subject (reason codes 1 to 5), PCRE_ERROR_SHORTUTF8 is returned instead of PCRE_ERROR_BADUTF8. PCRE_ERROR_BADUTF8_OFFSET (-11) - The UTF-8 byte sequence that was passed as a subject was checked and - found to be valid (the PCRE_NO_UTF8_CHECK option was not set), but the - value of startoffset did not point to the beginning of a UTF-8 charac- + The UTF-8 byte sequence that was passed as a subject was checked and + found to be valid (the PCRE_NO_UTF8_CHECK option was not set), but the + value of startoffset did not point to the beginning of a UTF-8 charac- ter or the end of the subject. PCRE_ERROR_PARTIAL (-12) - The subject string did not match, but it did match partially. See the + The subject string did not match, but it did match partially. See the pcrepartial documentation for details of partial matching. PCRE_ERROR_BADPARTIAL (-13) - This code is no longer in use. It was formerly returned when the - PCRE_PARTIAL option was used with a compiled pattern containing items - that were not supported for partial matching. From release 8.00 + This code is no longer in use. It was formerly returned when the + PCRE_PARTIAL option was used with a compiled pattern containing items + that were not supported for partial matching. From release 8.00 onwards, there are no restrictions on partial matching. PCRE_ERROR_INTERNAL (-14) - An unexpected internal error has occurred. This error could be caused + An unexpected internal error has occurred. This error could be caused by a bug in PCRE or by overwriting of the compiled pattern. PCRE_ERROR_BADCOUNT (-15) @@ -3679,7 +3696,7 @@ MATCHING A PATTERN: THE TRADITIONAL FUNCTION PCRE_ERROR_RECURSIONLIMIT (-21) The internal recursion limit, as specified by the match_limit_recursion - field in a pcre_extra structure (or defaulted) was reached. See the + field in a pcre_extra structure (or defaulted) was reached. See the description above. PCRE_ERROR_BADNEWLINE (-23) @@ -3693,29 +3710,29 @@ MATCHING A PATTERN: THE TRADITIONAL FUNCTION PCRE_ERROR_SHORTUTF8 (-25) - This error is returned instead of PCRE_ERROR_BADUTF8 when the subject - string ends with a truncated UTF-8 character and the PCRE_PARTIAL_HARD - option is set. Information about the failure is returned as for - PCRE_ERROR_BADUTF8. It is in fact sufficient to detect this case, but - this special error code for PCRE_PARTIAL_HARD precedes the implementa- - tion of returned information; it is retained for backwards compatibil- + This error is returned instead of PCRE_ERROR_BADUTF8 when the subject + string ends with a truncated UTF-8 character and the PCRE_PARTIAL_HARD + option is set. Information about the failure is returned as for + PCRE_ERROR_BADUTF8. It is in fact sufficient to detect this case, but + this special error code for PCRE_PARTIAL_HARD precedes the implementa- + tion of returned information; it is retained for backwards compatibil- ity. PCRE_ERROR_RECURSELOOP (-26) This error is returned when pcre_exec() detects a recursion loop within - the pattern. Specifically, it means that either the whole pattern or a - subpattern has been called recursively for the second time at the same + the pattern. Specifically, it means that either the whole pattern or a + subpattern has been called recursively for the second time at the same position in the subject string. Some simple patterns that might do this - are detected and faulted at compile time, but more complicated cases, + are detected and faulted at compile time, but more complicated cases, in particular mutual recursions between two different subpatterns, can- not be detected until run time. PCRE_ERROR_JIT_STACKLIMIT (-27) - This error is returned when a pattern that was successfully studied - using a JIT compile option is being matched, but the memory available - for the just-in-time processing stack is not large enough. See the + This error is returned when a pattern that was successfully studied + using a JIT compile option is being matched, but the memory available + for the just-in-time processing stack is not large enough. See the pcrejit documentation for more details. PCRE_ERROR_BADMODE (-28) @@ -3725,38 +3742,38 @@ MATCHING A PATTERN: THE TRADITIONAL FUNCTION PCRE_ERROR_BADENDIANNESS (-29) - This error is given if a pattern that was compiled and saved is - reloaded on a host with different endianness. The utility function + This error is given if a pattern that was compiled and saved is + reloaded on a host with different endianness. The utility function pcre_pattern_to_host_byte_order() can be used to convert such a pattern so that it runs on the new host. PCRE_ERROR_JIT_BADOPTION - This error is returned when a pattern that was successfully studied - using a JIT compile option is being matched, but the matching mode - (partial or complete match) does not correspond to any JIT compilation - mode. When the JIT fast path function is used, this error may be also - given for invalid options. See the pcrejit documentation for more + This error is returned when a pattern that was successfully studied + using a JIT compile option is being matched, but the matching mode + (partial or complete match) does not correspond to any JIT compilation + mode. When the JIT fast path function is used, this error may be also + given for invalid options. See the pcrejit documentation for more details. PCRE_ERROR_BADLENGTH (-32) - This error is given if pcre_exec() is called with a negative value for + This error is given if pcre_exec() is called with a negative value for the length argument. Error numbers -16 to -20, -22, and 30 are not used by pcre_exec(). Reason codes for invalid UTF-8 strings - This section applies only to the 8-bit library. The corresponding - information for the 16-bit and 32-bit libraries is given in the pcre16 + This section applies only to the 8-bit library. The corresponding + information for the 16-bit and 32-bit libraries is given in the pcre16 and pcre32 pages. When pcre_exec() returns either PCRE_ERROR_BADUTF8 or PCRE_ERROR_SHORT- - UTF8, and the size of the output vector (ovecsize) is at least 2, the - offset of the start of the invalid UTF-8 character is placed in the + UTF8, and the size of the output vector (ovecsize) is at least 2, the + offset of the start of the invalid UTF-8 character is placed in the first output vector element (ovector[0]) and a reason code is placed in - the second element (ovector[1]). The reason codes are given names in + the second element (ovector[1]). The reason codes are given names in the pcre.h header file: PCRE_UTF8_ERR1 @@ -3765,10 +3782,10 @@ MATCHING A PATTERN: THE TRADITIONAL FUNCTION PCRE_UTF8_ERR4 PCRE_UTF8_ERR5 - The string ends with a truncated UTF-8 character; the code specifies - how many bytes are missing (1 to 5). Although RFC 3629 restricts UTF-8 - characters to be no longer than 4 bytes, the encoding scheme (origi- - nally defined by RFC 2279) allows for up to 6 bytes, and this is + The string ends with a truncated UTF-8 character; the code specifies + how many bytes are missing (1 to 5). Although RFC 3629 restricts UTF-8 + characters to be no longer than 4 bytes, the encoding scheme (origi- + nally defined by RFC 2279) allows for up to 6 bytes, and this is checked first; hence the possibility of 4 or 5 missing bytes. PCRE_UTF8_ERR6 @@ -3778,24 +3795,24 @@ MATCHING A PATTERN: THE TRADITIONAL FUNCTION PCRE_UTF8_ERR10 The two most significant bits of the 2nd, 3rd, 4th, 5th, or 6th byte of - the character do not have the binary value 0b10 (that is, either the + the character do not have the binary value 0b10 (that is, either the most significant bit is 0, or the next bit is 1). PCRE_UTF8_ERR11 PCRE_UTF8_ERR12 - A character that is valid by the RFC 2279 rules is either 5 or 6 bytes + A character that is valid by the RFC 2279 rules is either 5 or 6 bytes long; these code points are excluded by RFC 3629. PCRE_UTF8_ERR13 - A 4-byte character has a value greater than 0x10fff; these code points + A 4-byte character has a value greater than 0x10fff; these code points are excluded by RFC 3629. PCRE_UTF8_ERR14 - A 3-byte character has a value in the range 0xd800 to 0xdfff; this - range of code points are reserved by RFC 3629 for use with UTF-16, and + A 3-byte character has a value in the range 0xd800 to 0xdfff; this + range of code points are reserved by RFC 3629 for use with UTF-16, and so are excluded from UTF-8. PCRE_UTF8_ERR15 @@ -3804,28 +3821,28 @@ MATCHING A PATTERN: THE TRADITIONAL FUNCTION PCRE_UTF8_ERR18 PCRE_UTF8_ERR19 - A 2-, 3-, 4-, 5-, or 6-byte character is "overlong", that is, it codes - for a value that can be represented by fewer bytes, which is invalid. - For example, the two bytes 0xc0, 0xae give the value 0x2e, whose cor- + A 2-, 3-, 4-, 5-, or 6-byte character is "overlong", that is, it codes + for a value that can be represented by fewer bytes, which is invalid. + For example, the two bytes 0xc0, 0xae give the value 0x2e, whose cor- rect coding uses just one byte. PCRE_UTF8_ERR20 The two most significant bits of the first byte of a character have the - binary value 0b10 (that is, the most significant bit is 1 and the sec- - ond is 0). Such a byte can only validly occur as the second or subse- + binary value 0b10 (that is, the most significant bit is 1 and the sec- + ond is 0). Such a byte can only validly occur as the second or subse- quent byte of a multi-byte character. PCRE_UTF8_ERR21 - The first byte of a character has the value 0xfe or 0xff. These values + The first byte of a character has the value 0xfe or 0xff. These values can never occur in a valid UTF-8 string. PCRE_UTF8_ERR22 - This error code was formerly used when the presence of a so-called - "non-character" caused an error. Unicode corrigendum #9 makes it clear - that such characters should not cause a string to be rejected, and so + This error code was formerly used when the presence of a so-called + "non-character" caused an error. Unicode corrigendum #9 makes it clear + that such characters should not cause a string to be rejected, and so this code is no longer in use and is never returned. @@ -3842,78 +3859,78 @@ EXTRACTING CAPTURED SUBSTRINGS BY NUMBER int pcre_get_substring_list(const char *subject, int *ovector, int stringcount, const char ***listptr); - Captured substrings can be accessed directly by using the offsets - returned by pcre_exec() in ovector. For convenience, the functions + Captured substrings can be accessed directly by using the offsets + returned by pcre_exec() in ovector. For convenience, the functions pcre_copy_substring(), pcre_get_substring(), and pcre_get_sub- - string_list() are provided for extracting captured substrings as new, - separate, zero-terminated strings. These functions identify substrings - by number. The next section describes functions for extracting named + string_list() are provided for extracting captured substrings as new, + separate, zero-terminated strings. These functions identify substrings + by number. The next section describes functions for extracting named substrings. - A substring that contains a binary zero is correctly extracted and has - a further zero added on the end, but the result is not, of course, a C - string. However, you can process such a string by referring to the - length that is returned by pcre_copy_substring() and pcre_get_sub- + A substring that contains a binary zero is correctly extracted and has + a further zero added on the end, but the result is not, of course, a C + string. However, you can process such a string by referring to the + length that is returned by pcre_copy_substring() and pcre_get_sub- string(). Unfortunately, the interface to pcre_get_substring_list() is - not adequate for handling strings containing binary zeros, because the + not adequate for handling strings containing binary zeros, because the end of the final string is not independently indicated. - The first three arguments are the same for all three of these func- - tions: subject is the subject string that has just been successfully + The first three arguments are the same for all three of these func- + tions: subject is the subject string that has just been successfully matched, ovector is a pointer to the vector of integer offsets that was passed to pcre_exec(), and stringcount is the number of substrings that - were captured by the match, including the substring that matched the + were captured by the match, including the substring that matched the entire regular expression. This is the value returned by pcre_exec() if - it is greater than zero. If pcre_exec() returned zero, indicating that - it ran out of space in ovector, the value passed as stringcount should + it is greater than zero. If pcre_exec() returned zero, indicating that + it ran out of space in ovector, the value passed as stringcount should be the number of elements in the vector divided by three. - The functions pcre_copy_substring() and pcre_get_substring() extract a - single substring, whose number is given as stringnumber. A value of - zero extracts the substring that matched the entire pattern, whereas - higher values extract the captured substrings. For pcre_copy_sub- - string(), the string is placed in buffer, whose length is given by - buffersize, while for pcre_get_substring() a new block of memory is - obtained via pcre_malloc, and its address is returned via stringptr. - The yield of the function is the length of the string, not including + The functions pcre_copy_substring() and pcre_get_substring() extract a + single substring, whose number is given as stringnumber. A value of + zero extracts the substring that matched the entire pattern, whereas + higher values extract the captured substrings. For pcre_copy_sub- + string(), the string is placed in buffer, whose length is given by + buffersize, while for pcre_get_substring() a new block of memory is + obtained via pcre_malloc, and its address is returned via stringptr. + The yield of the function is the length of the string, not including the terminating zero, or one of these error codes: PCRE_ERROR_NOMEMORY (-6) - The buffer was too small for pcre_copy_substring(), or the attempt to + The buffer was too small for pcre_copy_substring(), or the attempt to get memory failed for pcre_get_substring(). PCRE_ERROR_NOSUBSTRING (-7) There is no substring whose number is stringnumber. - The pcre_get_substring_list() function extracts all available sub- - strings and builds a list of pointers to them. All this is done in a + The pcre_get_substring_list() function extracts all available sub- + strings and builds a list of pointers to them. All this is done in a single block of memory that is obtained via pcre_malloc. The address of - the memory block is returned via listptr, which is also the start of - the list of string pointers. The end of the list is marked by a NULL - pointer. The yield of the function is zero if all went well, or the + the memory block is returned via listptr, which is also the start of + the list of string pointers. The end of the list is marked by a NULL + pointer. The yield of the function is zero if all went well, or the error code PCRE_ERROR_NOMEMORY (-6) if the attempt to get the memory block failed. - When any of these functions encounter a substring that is unset, which - can happen when capturing subpattern number n+1 matches some part of - the subject, but subpattern n has not been used at all, they return an + When any of these functions encounter a substring that is unset, which + can happen when capturing subpattern number n+1 matches some part of + the subject, but subpattern n has not been used at all, they return an empty string. This can be distinguished from a genuine zero-length sub- - string by inspecting the appropriate offset in ovector, which is nega- + string by inspecting the appropriate offset in ovector, which is nega- tive for unset substrings. - The two convenience functions pcre_free_substring() and pcre_free_sub- - string_list() can be used to free the memory returned by a previous + The two convenience functions pcre_free_substring() and pcre_free_sub- + string_list() can be used to free the memory returned by a previous call of pcre_get_substring() or pcre_get_substring_list(), respec- - tively. They do nothing more than call the function pointed to by - pcre_free, which of course could be called directly from a C program. - However, PCRE is used in some situations where it is linked via a spe- - cial interface to another programming language that cannot use - pcre_free directly; it is for these cases that the functions are pro- + tively. They do nothing more than call the function pointed to by + pcre_free, which of course could be called directly from a C program. + However, PCRE is used in some situations where it is linked via a spe- + cial interface to another programming language that cannot use + pcre_free directly; it is for these cases that the functions are pro- vided. @@ -3932,7 +3949,7 @@ EXTRACTING CAPTURED SUBSTRINGS BY NAME int stringcount, const char *stringname, const char **stringptr); - To extract a substring by name, you first have to find associated num- + To extract a substring by name, you first have to find associated num- ber. For example, for this pattern (a+)b(?<xxx>\d+)... @@ -3941,35 +3958,35 @@ EXTRACTING CAPTURED SUBSTRINGS BY NAME be unique (PCRE_DUPNAMES was not set), you can find the number from the name by calling pcre_get_stringnumber(). The first argument is the com- piled pattern, and the second is the name. The yield of the function is - the subpattern number, or PCRE_ERROR_NOSUBSTRING (-7) if there is no + the subpattern number, or PCRE_ERROR_NOSUBSTRING (-7) if there is no subpattern of that name. Given the number, you can extract the substring directly, or use one of the functions described in the previous section. For convenience, there are also two functions that do the whole job. - Most of the arguments of pcre_copy_named_substring() and - pcre_get_named_substring() are the same as those for the similarly - named functions that extract by number. As these are described in the - previous section, they are not re-described here. There are just two + Most of the arguments of pcre_copy_named_substring() and + pcre_get_named_substring() are the same as those for the similarly + named functions that extract by number. As these are described in the + previous section, they are not re-described here. There are just two differences: - First, instead of a substring number, a substring name is given. Sec- + First, instead of a substring number, a substring name is given. Sec- ond, there is an extra argument, given at the start, which is a pointer - to the compiled pattern. This is needed in order to gain access to the + to the compiled pattern. This is needed in order to gain access to the name-to-number translation table. - These functions call pcre_get_stringnumber(), and if it succeeds, they - then call pcre_copy_substring() or pcre_get_substring(), as appropri- - ate. NOTE: If PCRE_DUPNAMES is set and there are duplicate names, the + These functions call pcre_get_stringnumber(), and if it succeeds, they + then call pcre_copy_substring() or pcre_get_substring(), as appropri- + ate. NOTE: If PCRE_DUPNAMES is set and there are duplicate names, the behaviour may not be what you want (see the next section). Warning: If the pattern uses the (?| feature to set up multiple subpat- - terns with the same number, as described in the section on duplicate - subpattern numbers in the pcrepattern page, you cannot use names to - distinguish the different subpatterns, because names are not included - in the compiled code. The matching process uses only numbers. For this - reason, the use of different names for subpatterns of the same number + terns with the same number, as described in the section on duplicate + subpattern numbers in the pcrepattern page, you cannot use names to + distinguish the different subpatterns, because names are not included + in the compiled code. The matching process uses only numbers. For this + reason, the use of different names for subpatterns of the same number causes an error at compile time. @@ -3978,76 +3995,76 @@ DUPLICATE SUBPATTERN NAMES int pcre_get_stringtable_entries(const pcre *code, const char *name, char **first, char **last); - When a pattern is compiled with the PCRE_DUPNAMES option, names for - subpatterns are not required to be unique. (Duplicate names are always - allowed for subpatterns with the same number, created by using the (?| - feature. Indeed, if such subpatterns are named, they are required to + When a pattern is compiled with the PCRE_DUPNAMES option, names for + subpatterns are not required to be unique. (Duplicate names are always + allowed for subpatterns with the same number, created by using the (?| + feature. Indeed, if such subpatterns are named, they are required to use the same names.) Normally, patterns with duplicate names are such that in any one match, - only one of the named subpatterns participates. An example is shown in + only one of the named subpatterns participates. An example is shown in the pcrepattern documentation. - When duplicates are present, pcre_copy_named_substring() and - pcre_get_named_substring() return the first substring corresponding to - the given name that is set. If none are set, PCRE_ERROR_NOSUBSTRING - (-7) is returned; no data is returned. The pcre_get_stringnumber() - function returns one of the numbers that are associated with the name, + When duplicates are present, pcre_copy_named_substring() and + pcre_get_named_substring() return the first substring corresponding to + the given name that is set. If none are set, PCRE_ERROR_NOSUBSTRING + (-7) is returned; no data is returned. The pcre_get_stringnumber() + function returns one of the numbers that are associated with the name, but it is not defined which it is. - If you want to get full details of all captured substrings for a given - name, you must use the pcre_get_stringtable_entries() function. The + If you want to get full details of all captured substrings for a given + name, you must use the pcre_get_stringtable_entries() function. The first argument is the compiled pattern, and the second is the name. The - third and fourth are pointers to variables which are updated by the + third and fourth are pointers to variables which are updated by the function. After it has run, they point to the first and last entries in - the name-to-number table for the given name. The function itself - returns the length of each entry, or PCRE_ERROR_NOSUBSTRING (-7) if - there are none. The format of the table is described above in the sec- - tion entitled Information about a pattern above. Given all the rele- - vant entries for the name, you can extract each of their numbers, and + the name-to-number table for the given name. The function itself + returns the length of each entry, or PCRE_ERROR_NOSUBSTRING (-7) if + there are none. The format of the table is described above in the sec- + tion entitled Information about a pattern above. Given all the rele- + vant entries for the name, you can extract each of their numbers, and hence the captured data, if any. FINDING ALL POSSIBLE MATCHES - The traditional matching function uses a similar algorithm to Perl, + The traditional matching function uses a similar algorithm to Perl, which stops when it finds the first match, starting at a given point in - the subject. If you want to find all possible matches, or the longest - possible match, consider using the alternative matching function (see - below) instead. If you cannot use the alternative function, but still - need to find all possible matches, you can kludge it up by making use + the subject. If you want to find all possible matches, or the longest + possible match, consider using the alternative matching function (see + below) instead. If you cannot use the alternative function, but still + need to find all possible matches, you can kludge it up by making use of the callout facility, which is described in the pcrecallout documen- tation. What you have to do is to insert a callout right at the end of the pat- - tern. When your callout function is called, extract and save the cur- - rent matched substring. Then return 1, which forces pcre_exec() to - backtrack and try other alternatives. Ultimately, when it runs out of + tern. When your callout function is called, extract and save the cur- + rent matched substring. Then return 1, which forces pcre_exec() to + backtrack and try other alternatives. Ultimately, when it runs out of matches, pcre_exec() will yield PCRE_ERROR_NOMATCH. OBTAINING AN ESTIMATE OF STACK USAGE - Matching certain patterns using pcre_exec() can use a lot of process - stack, which in certain environments can be rather limited in size. - Some users find it helpful to have an estimate of the amount of stack - that is used by pcre_exec(), to help them set recursion limits, as - described in the pcrestack documentation. The estimate that is output + Matching certain patterns using pcre_exec() can use a lot of process + stack, which in certain environments can be rather limited in size. + Some users find it helpful to have an estimate of the amount of stack + that is used by pcre_exec(), to help them set recursion limits, as + described in the pcrestack documentation. The estimate that is output by pcretest when called with the -m and -C options is obtained by call- - ing pcre_exec with the values NULL, NULL, NULL, -999, and -999 for its + ing pcre_exec with the values NULL, NULL, NULL, -999, and -999 for its first five arguments. - Normally, if its first argument is NULL, pcre_exec() immediately - returns the negative error code PCRE_ERROR_NULL, but with this special - combination of arguments, it returns instead a negative number whose - absolute value is the approximate stack frame size in bytes. (A nega- - tive number is used so that it is clear that no match has happened.) - The value is approximate because in some cases, recursive calls to + Normally, if its first argument is NULL, pcre_exec() immediately + returns the negative error code PCRE_ERROR_NULL, but with this special + combination of arguments, it returns instead a negative number whose + absolute value is the approximate stack frame size in bytes. (A nega- + tive number is used so that it is clear that no match has happened.) + The value is approximate because in some cases, recursive calls to pcre_exec() occur when there are one or two additional variables on the stack. - If PCRE has been compiled to use the heap instead of the stack for - recursion, the value returned is the size of each block that is + If PCRE has been compiled to use the heap instead of the stack for + recursion, the value returned is the size of each block that is obtained from the heap. @@ -4058,26 +4075,26 @@ MATCHING A PATTERN: THE ALTERNATIVE FUNCTION int options, int *ovector, int ovecsize, int *workspace, int wscount); - The function pcre_dfa_exec() is called to match a subject string - against a compiled pattern, using a matching algorithm that scans the - subject string just once, and does not backtrack. This has different - characteristics to the normal algorithm, and is not compatible with - Perl. Some of the features of PCRE patterns are not supported. Never- - theless, there are times when this kind of matching can be useful. For - a discussion of the two matching algorithms, and a list of features - that pcre_dfa_exec() does not support, see the pcrematching documenta- + The function pcre_dfa_exec() is called to match a subject string + against a compiled pattern, using a matching algorithm that scans the + subject string just once, and does not backtrack. This has different + characteristics to the normal algorithm, and is not compatible with + Perl. Some of the features of PCRE patterns are not supported. Never- + theless, there are times when this kind of matching can be useful. For + a discussion of the two matching algorithms, and a list of features + that pcre_dfa_exec() does not support, see the pcrematching documenta- tion. - The arguments for the pcre_dfa_exec() function are the same as for + The arguments for the pcre_dfa_exec() function are the same as for pcre_exec(), plus two extras. The ovector argument is used in a differ- - ent way, and this is described below. The other common arguments are - used in the same way as for pcre_exec(), so their description is not + ent way, and this is described below. The other common arguments are + used in the same way as for pcre_exec(), so their description is not repeated here. - The two additional arguments provide workspace for the function. The - workspace vector should contain at least 20 elements. It is used for + The two additional arguments provide workspace for the function. The + workspace vector should contain at least 20 elements. It is used for keeping track of multiple paths through the pattern tree. More - workspace will be needed for patterns and subjects where there are a + workspace will be needed for patterns and subjects where there are a lot of potential matches. Here is an example of a simple call to pcre_dfa_exec(): @@ -4099,55 +4116,55 @@ MATCHING A PATTERN: THE ALTERNATIVE FUNCTION Option bits for pcre_dfa_exec() - The unused bits of the options argument for pcre_dfa_exec() must be - zero. The only bits that may be set are PCRE_ANCHORED, PCRE_NEW- + The unused bits of the options argument for pcre_dfa_exec() must be + zero. The only bits that may be set are PCRE_ANCHORED, PCRE_NEW- LINE_xxx, PCRE_NOTBOL, PCRE_NOTEOL, PCRE_NOTEMPTY, - PCRE_NOTEMPTY_ATSTART, PCRE_NO_UTF8_CHECK, PCRE_BSR_ANYCRLF, - PCRE_BSR_UNICODE, PCRE_NO_START_OPTIMIZE, PCRE_PARTIAL_HARD, PCRE_PAR- - TIAL_SOFT, PCRE_DFA_SHORTEST, and PCRE_DFA_RESTART. All but the last - four of these are exactly the same as for pcre_exec(), so their + PCRE_NOTEMPTY_ATSTART, PCRE_NO_UTF8_CHECK, PCRE_BSR_ANYCRLF, + PCRE_BSR_UNICODE, PCRE_NO_START_OPTIMIZE, PCRE_PARTIAL_HARD, PCRE_PAR- + TIAL_SOFT, PCRE_DFA_SHORTEST, and PCRE_DFA_RESTART. All but the last + four of these are exactly the same as for pcre_exec(), so their description is not repeated here. PCRE_PARTIAL_HARD PCRE_PARTIAL_SOFT - These have the same general effect as they do for pcre_exec(), but the - details are slightly different. When PCRE_PARTIAL_HARD is set for - pcre_dfa_exec(), it returns PCRE_ERROR_PARTIAL if the end of the sub- - ject is reached and there is still at least one matching possibility + These have the same general effect as they do for pcre_exec(), but the + details are slightly different. When PCRE_PARTIAL_HARD is set for + pcre_dfa_exec(), it returns PCRE_ERROR_PARTIAL if the end of the sub- + ject is reached and there is still at least one matching possibility that requires additional characters. This happens even if some complete matches have also been found. When PCRE_PARTIAL_SOFT is set, the return code PCRE_ERROR_NOMATCH is converted into PCRE_ERROR_PARTIAL if the end - of the subject is reached, there have been no complete matches, but - there is still at least one matching possibility. The portion of the - string that was inspected when the longest partial match was found is - set as the first matching string in both cases. There is a more - detailed discussion of partial and multi-segment matching, with exam- + of the subject is reached, there have been no complete matches, but + there is still at least one matching possibility. The portion of the + string that was inspected when the longest partial match was found is + set as the first matching string in both cases. There is a more + detailed discussion of partial and multi-segment matching, with exam- ples, in the pcrepartial documentation. PCRE_DFA_SHORTEST - Setting the PCRE_DFA_SHORTEST option causes the matching algorithm to + Setting the PCRE_DFA_SHORTEST option causes the matching algorithm to stop as soon as it has found one match. Because of the way the alterna- - tive algorithm works, this is necessarily the shortest possible match + tive algorithm works, this is necessarily the shortest possible match at the first possible matching point in the subject string. PCRE_DFA_RESTART When pcre_dfa_exec() returns a partial match, it is possible to call it - again, with additional subject characters, and have it continue with - the same match. The PCRE_DFA_RESTART option requests this action; when - it is set, the workspace and wscount options must reference the same - vector as before because data about the match so far is left in them + again, with additional subject characters, and have it continue with + the same match. The PCRE_DFA_RESTART option requests this action; when + it is set, the workspace and wscount options must reference the same + vector as before because data about the match so far is left in them after a partial match. There is more discussion of this facility in the pcrepartial documentation. Successful returns from pcre_dfa_exec() - When pcre_dfa_exec() succeeds, it may have matched more than one sub- + When pcre_dfa_exec() succeeds, it may have matched more than one sub- string in the subject. Note, however, that all the matches from one run - of the function start at the same point in the subject. The shorter - matches are all initial substrings of the longer matches. For example, + of the function start at the same point in the subject. The shorter + matches are all initial substrings of the longer matches. For example, if the pattern <.*> @@ -4162,79 +4179,79 @@ MATCHING A PATTERN: THE ALTERNATIVE FUNCTION <something> <something else> <something> <something else> <something further> - On success, the yield of the function is a number greater than zero, - which is the number of matched substrings. The substrings themselves - are returned in ovector. Each string uses two elements; the first is - the offset to the start, and the second is the offset to the end. In - fact, all the strings have the same start offset. (Space could have - been saved by giving this only once, but it was decided to retain some - compatibility with the way pcre_exec() returns data, even though the + On success, the yield of the function is a number greater than zero, + which is the number of matched substrings. The substrings themselves + are returned in ovector. Each string uses two elements; the first is + the offset to the start, and the second is the offset to the end. In + fact, all the strings have the same start offset. (Space could have + been saved by giving this only once, but it was decided to retain some + compatibility with the way pcre_exec() returns data, even though the meaning of the strings is different.) The strings are returned in reverse order of length; that is, the long- - est matching string is given first. If there were too many matches to - fit into ovector, the yield of the function is zero, and the vector is - filled with the longest matches. Unlike pcre_exec(), pcre_dfa_exec() + est matching string is given first. If there were too many matches to + fit into ovector, the yield of the function is zero, and the vector is + filled with the longest matches. Unlike pcre_exec(), pcre_dfa_exec() can use the entire ovector for returning matched strings. - NOTE: PCRE's "auto-possessification" optimization usually applies to - character repeats at the end of a pattern (as well as internally). For - example, the pattern "a\d+" is compiled as if it were "a\d++" because + NOTE: PCRE's "auto-possessification" optimization usually applies to + character repeats at the end of a pattern (as well as internally). For + example, the pattern "a\d+" is compiled as if it were "a\d++" because there is no point even considering the possibility of backtracking into - the repeated digits. For DFA matching, this means that only one possi- - ble match is found. If you really do want multiple matches in such - cases, either use an ungreedy repeat ("a\d+?") or set the + the repeated digits. For DFA matching, this means that only one possi- + ble match is found. If you really do want multiple matches in such + cases, either use an ungreedy repeat ("a\d+?") or set the PCRE_NO_AUTO_POSSESS option when compiling. Error returns from pcre_dfa_exec() - The pcre_dfa_exec() function returns a negative number when it fails. - Many of the errors are the same as for pcre_exec(), and these are - described above. There are in addition the following errors that are + The pcre_dfa_exec() function returns a negative number when it fails. + Many of the errors are the same as for pcre_exec(), and these are + described above. There are in addition the following errors that are specific to pcre_dfa_exec(): PCRE_ERROR_DFA_UITEM (-16) - This return is given if pcre_dfa_exec() encounters an item in the pat- - tern that it does not support, for instance, the use of \C or a back + This return is given if pcre_dfa_exec() encounters an item in the pat- + tern that it does not support, for instance, the use of \C or a back reference. PCRE_ERROR_DFA_UCOND (-17) - This return is given if pcre_dfa_exec() encounters a condition item - that uses a back reference for the condition, or a test for recursion + This return is given if pcre_dfa_exec() encounters a condition item + that uses a back reference for the condition, or a test for recursion in a specific group. These are not supported. PCRE_ERROR_DFA_UMLIMIT (-18) - This return is given if pcre_dfa_exec() is called with an extra block - that contains a setting of the match_limit or match_limit_recursion - fields. This is not supported (these fields are meaningless for DFA + This return is given if pcre_dfa_exec() is called with an extra block + that contains a setting of the match_limit or match_limit_recursion + fields. This is not supported (these fields are meaningless for DFA matching). PCRE_ERROR_DFA_WSSIZE (-19) - This return is given if pcre_dfa_exec() runs out of space in the + This return is given if pcre_dfa_exec() runs out of space in the workspace vector. PCRE_ERROR_DFA_RECURSE (-20) - When a recursive subpattern is processed, the matching function calls - itself recursively, using private vectors for ovector and workspace. - This error is given if the output vector is not large enough. This + When a recursive subpattern is processed, the matching function calls + itself recursively, using private vectors for ovector and workspace. + This error is given if the output vector is not large enough. This should be extremely rare, as a vector of size 1000 is used. PCRE_ERROR_DFA_BADRESTART (-30) - When pcre_dfa_exec() is called with the PCRE_DFA_RESTART option, some - plausibility checks are made on the contents of the workspace, which - should contain data about the previous partial match. If any of these + When pcre_dfa_exec() is called with the PCRE_DFA_RESTART option, some + plausibility checks are made on the contents of the workspace, which + should contain data about the previous partial match. If any of these checks fail, this error is given. SEE ALSO - pcre16(3), pcre32(3), pcrebuild(3), pcrecallout(3), pcrecpp(3)(3), + pcre16(3), pcre32(3), pcrebuild(3), pcrecallout(3), pcrecpp(3)(3), pcrematching(3), pcrepartial(3), pcreposix(3), pcreprecompile(3), pcre- sample(3), pcrestack(3). @@ -4248,8 +4265,8 @@ AUTHOR REVISION - Last updated: 12 November 2013 - Copyright (c) 1997-2013 University of Cambridge. + Last updated: 09 February 2014 + Copyright (c) 1997-2014 University of Cambridge. ------------------------------------------------------------------------------ @@ -5510,7 +5527,9 @@ BACKSLASH Perl documents that the use of \K within assertions is "not well defined". In PCRE, \K is acted upon when it occurs inside positive - assertions, but is ignored in negative assertions. + assertions, but is ignored in negative assertions. Note that when a + pattern such as (?=ab\K) matches, the reported start of the match can + be greater than the end of the match. Simple assertions @@ -7399,19 +7418,23 @@ BACKTRACKING CONTROL Note that (*COMMIT) at the start of a pattern is not the same as an anchor, unless PCRE's start-of-match optimizations are turned off, as - shown in this pcretest example: + shown in this output from pcretest: re> /(*COMMIT)abc/ data> xyzabc 0: abc - xyzabc\Y + data> xyzabc\Y No match - PCRE knows that any match must start with "a", so the optimization - skips along the subject to "a" before running the first match attempt, - which succeeds. When the optimization is disabled by the \Y escape in - the second subject, the match starts at "x" and so the (*COMMIT) causes - it to fail without trying any other starting points. + For this pattern, PCRE knows that any match must start with "a", so the + optimization skips along the subject to "a" before applying the pattern + to the first set of data. The match attempt then succeeds. In the sec- + ond set of data, the escape sequence \Y is interpreted by the pcretest + program. It causes the PCRE_NO_START_OPTIMIZE option to be set when + pcre_exec() is called. This disables the optimization that skips along + to the first character. The pattern is now applied starting at "x", and + so the (*COMMIT) causes the match to fail without trying any other + starting points. (*PRUNE) or (*PRUNE:NAME) @@ -7618,8 +7641,8 @@ AUTHOR REVISION - Last updated: 03 December 2013 - Copyright (c) 1997-2013 University of Cambridge. + Last updated: 08 January 2014 + Copyright (c) 1997-2014 University of Cambridge. ------------------------------------------------------------------------------ @@ -7840,6 +7863,8 @@ MATCH POINT RESET \K reset start of match + \K is honoured in positive assertions, but ignored in negative ones. + ALTERNATION @@ -7877,11 +7902,13 @@ OPTION SETTING (?x) extended (ignore white space) (?-...) unset option(s) - The following are recognized only at the start of a pattern or after - one of the newline-setting options with similar syntax: + The following are recognized only at the very start of a pattern or + after one of the newline or \R options with similar syntax. More than + one of them may appear. (*LIMIT_MATCH=d) set the match limit to d (decimal number) (*LIMIT_RECURSION=d) set the recursion limit to d (decimal number) + (*NO_AUTO_POSSESS) no auto-possessification (PCRE_NO_AUTO_POSSESS) (*NO_START_OPT) no start-match optimization (PCRE_NO_START_OPTIMIZE) (*UTF8) set UTF-8 mode: 8-bit library (PCRE_UTF8) (*UTF16) set UTF-16 mode: 16-bit library (PCRE_UTF16) @@ -7889,10 +7916,31 @@ OPTION SETTING (*UTF) set appropriate UTF mode for the library in use (*UCP) set PCRE_UCP (use Unicode properties for \d etc) - Note that LIMIT_MATCH and LIMIT_RECURSION can only reduce the value of + Note that LIMIT_MATCH and LIMIT_RECURSION can only reduce the value of the limits set by the caller of pcre_exec(), not increase them. +NEWLINE CONVENTION + + These are recognized only at the very start of the pattern or after + option settings with a similar syntax. + + (*CR) carriage return only + (*LF) linefeed only + (*CRLF) carriage return followed by linefeed + (*ANYCRLF) all three of the above + (*ANY) any Unicode newline sequence + + +WHAT \R MATCHES + + These are recognized only at the very start of the pattern or after + option setting with a similar syntax. + + (*BSR_ANYCRLF) CR, LF, or CRLF + (*BSR_UNICODE) any Unicode newline sequence + + LOOKAHEAD AND LOOKBEHIND ASSERTIONS (?=...) positive look ahead @@ -7960,7 +8008,7 @@ BACKTRACKING CONTROL (*FAIL) force backtrack; synonym (*F) (*MARK:NAME) set name to be passed back; synonym (*:NAME) - The following act only when a subsequent match failure causes a back- + The following act only when a subsequent match failure causes a back- track to reach them. They all force a match failure, but they differ in what happens afterwards. Those that advance the start-of-match point do so only if the pattern is not anchored. @@ -7975,27 +8023,6 @@ BACKTRACKING CONTROL (*THEN:NAME) equivalent to (*MARK:NAME)(*THEN) -NEWLINE CONVENTIONS - - These are recognized only at the very start of the pattern or after a - (*BSR_...), (*UTF8), (*UTF16), (*UTF32) or (*UCP) option. - - (*CR) carriage return only - (*LF) linefeed only - (*CRLF) carriage return followed by linefeed - (*ANYCRLF) all three of the above - (*ANY) any Unicode newline sequence - - -WHAT \R MATCHES - - These are recognized only at the very start of the pattern or after a - (*...) option that sets the newline convention or a UTF or UCP mode. - - (*BSR_ANYCRLF) CR, LF, or CRLF - (*BSR_UNICODE) any Unicode newline sequence - - CALLOUTS (?C) callout @@ -8016,8 +8043,8 @@ AUTHOR REVISION - Last updated: 12 November 2013 - Copyright (c) 1997-2013 University of Cambridge. + Last updated: 08 January 2014 + Copyright (c) 1997-2014 University of Cambridge. ------------------------------------------------------------------------------ diff --git a/doc/pcreapi.3 b/doc/pcreapi.3 index 8ffa9b7..ab3eaa0 100644 --- a/doc/pcreapi.3 +++ b/doc/pcreapi.3 @@ -289,12 +289,12 @@ points during a matching operation. Details are given in the .\" documentation. .P -The global variable \fBpcre_stack_guard\fP initially contains NULL. It can be -set by the caller to a function that is called by PCRE whenever it starts -to compile a parenthesized part of a pattern. When parentheses are nested, PCRE -uses recursive function calls, which use up the system stack. This function is -provided so that applications with restricted stacks can force a compilation -error if the stack runs out. The function should return zero if all is well, or +The global variable \fBpcre_stack_guard\fP initially contains NULL. It can be +set by the caller to a function that is called by PCRE whenever it starts +to compile a parenthesized part of a pattern. When parentheses are nested, PCRE +uses recursive function calls, which use up the system stack. This function is +provided so that applications with restricted stacks can force a compilation +error if the stack runs out. The function should return zero if all is well, or non-zero to force an error. . . @@ -347,7 +347,7 @@ controlled in a similar way, but by separate options. The PCRE functions can be used in multi-threading applications, with the proviso that the memory management functions pointed to by \fBpcre_malloc\fP, \fBpcre_free\fP, \fBpcre_stack_malloc\fP, and \fBpcre_stack_free\fP, and the -callout and stack-checking functions pointed to by \fBpcre_callout\fP and +callout and stack-checking functions pointed to by \fBpcre_callout\fP and \fBpcre_stack_guard\fP, are shared by all threads. .P The compiled form of a regular expression is not altered during matching, so @@ -476,8 +476,8 @@ documentation. The output is a long integer that gives the maximum depth of nesting of parentheses (of any kind) in a pattern. This limit is imposed to cap the amount of system stack used when a pattern is compiled. It is specified when PCRE is -built; the default is 250. This limit does not take into account the stack that -may already be used by the calling application. For finer control over +built; the default is 250. This limit does not take into account the stack that +may already be used by the calling application. For finer control over compilation stack usage, you can set a pointer to an external checking function in \fBpcre_stack_guard\fP. .sp @@ -1006,7 +1006,7 @@ have fallen out of use. To avoid confusion, they have not been re-used. 82 parentheses are too deeply nested 83 invalid range in character class 84 group name must start with a non-digit - 85 parentheses are too deeply nested (stack check) + 85 parentheses are too deeply nested (stack check) .sp The numbers 32 and 10000 in errors 48 and 49 are defaults; different values may be used if the limits were changed when PCRE was built. diff --git a/doc/pcrepattern.3 b/doc/pcrepattern.3 index 17b65f5..f1c45cd 100644 --- a/doc/pcrepattern.3 +++ b/doc/pcrepattern.3 @@ -1005,7 +1005,7 @@ matches "foobar", the first substring is still set to "foo". Perl documents that the use of \eK within assertions is "not well defined". In PCRE, \eK is acted upon when it occurs inside positive assertions, but is ignored in negative assertions. Note that when a pattern such as (?=ab\eK) -matches, the reported start of the match can be greater than the end of the +matches, the reported start of the match can be greater than the end of the match. . . diff --git a/doc/pcresyntax.3 b/doc/pcresyntax.3 index c35800b..fd878da 100644 --- a/doc/pcresyntax.3 +++ b/doc/pcresyntax.3 @@ -310,7 +310,7 @@ but some of them use Unicode properties if PCRE_UCP is set. You can use .sp \eK reset start of match .sp -\eK is honoured in positive assertions, but ignored in negative ones. +\eK is honoured in positive assertions, but ignored in negative ones. . . .SH "ALTERNATION" @@ -362,7 +362,7 @@ appear. .sp (*LIMIT_MATCH=d) set the match limit to d (decimal number) (*LIMIT_RECURSION=d) set the recursion limit to d (decimal number) - (*NO_AUTO_POSSESS) no auto-possessification (PCRE_NO_AUTO_POSSESS) + (*NO_AUTO_POSSESS) no auto-possessification (PCRE_NO_AUTO_POSSESS) (*NO_START_OPT) no start-match optimization (PCRE_NO_START_OPTIMIZE) (*UTF8) set UTF-8 mode: 8-bit library (PCRE_UTF8) (*UTF16) set UTF-16 mode: 16-bit library (PCRE_UTF16) diff --git a/doc/pcretest.1 b/doc/pcretest.1 index 733fc6f..92640da 100644 --- a/doc/pcretest.1 +++ b/doc/pcretest.1 @@ -115,7 +115,7 @@ following options output the value and set the exit code as indicated: exit code is always 0 bsr the default setting for what \eR matches: ANYCRLF or ANY - exit code is always 0 + exit code is always 0 .sp The following options output 1 for true or 0 for false, and set the exit code to the same value: @@ -333,7 +333,7 @@ sections. \fB/N\fP set PCRE_NO_AUTO_CAPTURE \fB/O\fP set PCRE_NO_AUTO_POSSESS \fB/P\fP use the POSIX wrapper - \fB/Q\fP test external stack check function + \fB/Q\fP test external stack check function \fB/S\fP study the pattern after compilation \fB/s\fP set PCRE_DOTALL \fB/T\fP select character tables @@ -487,9 +487,9 @@ below. The \fB/I\fP modifier requests that \fBpcretest\fP output information about the compiled pattern (whether it is anchored, has a fixed first character, and so on). It does this by calling \fBpcre[16|32]_fullinfo()\fP after compiling a -pattern. If the pattern is studied, the results of that are also output. In -this output, the word "char" means a non-UTF character, that is, the value of a -single data item (8-bit, 16-bit, or 32-bit, depending on the library that is +pattern. If the pattern is studied, the results of that are also output. In +this output, the word "char" means a non-UTF character, that is, the value of a +single data item (8-bit, 16-bit, or 32-bit, depending on the library that is being tested). .P The \fB/K\fP modifier requests \fBpcretest\fP to show names from backtracking @@ -520,14 +520,14 @@ the compiled pattern to be output. This does not include the size of the successfully studied with the PCRE_STUDY_JIT_COMPILE option, the size of the JIT compiled code is also output. .P -The \fB/Q\fP modifier is used to test the use of \fBpcre_stack_guard\fP. It -must be followed by '0' or '1', specifying the return code to be given from an -external function that is passed to PCRE and used for stack checking during +The \fB/Q\fP modifier is used to test the use of \fBpcre_stack_guard\fP. It +must be followed by '0' or '1', specifying the return code to be given from an +external function that is passed to PCRE and used for stack checking during compilation (see the .\" HREF \fBpcreapi\fP .\" -documentation for details). +documentation for details). .P The \fB/S\fP modifier causes \fBpcre[16|32]_study()\fP to be called after the expression has been compiled, and the results used when the expression is diff --git a/doc/pcretest.txt b/doc/pcretest.txt index f060993..55de502 100644 --- a/doc/pcretest.txt +++ b/doc/pcretest.txt @@ -99,6 +99,9 @@ COMMAND LINE OPTIONS newline the default newline setting: CR, LF, CRLF, ANYCRLF, or ANY exit code is always 0 + bsr the default setting for what \R matches: + ANYCRLF or ANY + exit code is always 0 The following options output 1 for true or 0 for false, and set the exit code to the same value: @@ -316,6 +319,7 @@ PATTERN MODIFIERS /N set PCRE_NO_AUTO_CAPTURE /O set PCRE_NO_AUTO_POSSESS /P use the POSIX wrapper + /Q test external stack check function /S study the pattern after compilation /s set PCRE_DOTALL /T select character tables @@ -462,7 +466,9 @@ PATTERN MODIFIERS compiled pattern (whether it is anchored, has a fixed first character, and so on). It does this by calling pcre[16|32]_fullinfo() after com- piling a pattern. If the pattern is studied, the results of that are - also output. + also output. In this output, the word "char" means a non-UTF character, + that is, the value of a single data item (8-bit, 16-bit, or 32-bit, + depending on the library that is being tested). The /K modifier requests pcretest to show names from backtracking con- trol verbs that are returned from calls to pcre[16|32]_exec(). It @@ -493,26 +499,31 @@ PATTERN MODIFIERS pattern is successfully studied with the PCRE_STUDY_JIT_COMPILE option, the size of the JIT compiled code is also output. - The /S modifier causes pcre[16|32]_study() to be called after the - expression has been compiled, and the results used when the expression + The /Q modifier is used to test the use of pcre_stack_guard. It must be + followed by '0' or '1', specifying the return code to be given from an + external function that is passed to PCRE and used for stack checking + during compilation (see the pcreapi documentation for details). + + The /S modifier causes pcre[16|32]_study() to be called after the + expression has been compiled, and the results used when the expression is matched. There are a number of qualifying characters that may follow /S. They may appear in any order. If /S is followed by an exclamation mark, pcre[16|32]_study() is called - with the PCRE_STUDY_EXTRA_NEEDED option, causing it always to return a + with the PCRE_STUDY_EXTRA_NEEDED option, causing it always to return a pcre_extra block, even when studying discovers no useful information. If /S is followed by a second S character, it suppresses studying, even - if it was requested externally by the -s command line option. This - makes it possible to specify that certain patterns are always studied, + if it was requested externally by the -s command line option. This + makes it possible to specify that certain patterns are always studied, and others are never studied, independently of -s. This feature is used in the test files in a few cases where the output is different when the pattern is studied. - If the /S modifier is followed by a + character, the call to - pcre[16|32]_study() is made with all the JIT study options, requesting - just-in-time optimization support if it is available, for both normal - and partial matching. If you want to restrict the JIT compiling modes, + If the /S modifier is followed by a + character, the call to + pcre[16|32]_study() is made with all the JIT study options, requesting + just-in-time optimization support if it is available, for both normal + and partial matching. If you want to restrict the JIT compiling modes, you can follow /S+ with a digit in the range 1 to 7: 1 normal match only @@ -523,40 +534,40 @@ PATTERN MODIFIERS 7 all three modes (default) If /S++ is used instead of /S+ (with or without a following digit), the - text "(JIT)" is added to the first output line after a match or no + text "(JIT)" is added to the first output line after a match or no match when JIT-compiled code was actually used. - Note that there is also an independent /+ modifier; it must not be + Note that there is also an independent /+ modifier; it must not be given immediately after /S or /S+ because this will be misinterpreted. If JIT studying is successful, the compiled JIT code will automatically - be used when pcre[16|32]_exec() is run, except when incompatible run- - time options are specified. For more details, see the pcrejit documen- - tation. See also the \J escape sequence below for a way of setting the + be used when pcre[16|32]_exec() is run, except when incompatible run- + time options are specified. For more details, see the pcrejit documen- + tation. See also the \J escape sequence below for a way of setting the size of the JIT stack. - Finally, if /S is followed by a minus character, JIT compilation is - suppressed, even if it was requested externally by the -s command line - option. This makes it possible to specify that JIT is never to be used + Finally, if /S is followed by a minus character, JIT compilation is + suppressed, even if it was requested externally by the -s command line + option. This makes it possible to specify that JIT is never to be used for certain patterns. - The /T modifier must be followed by a single digit. It causes a spe- + The /T modifier must be followed by a single digit. It causes a spe- cific set of built-in character tables to be passed to pcre[16|32]_com- - pile(). It is used in the standard PCRE tests to check behaviour with + pile(). It is used in the standard PCRE tests to check behaviour with different character tables. The digit specifies the tables as follows: 0 the default ASCII tables, as distributed in pcre_chartables.c.dist 1 a set of tables defining ISO 8859 characters - In table 1, some characters whose codes are greater than 128 are iden- + In table 1, some characters whose codes are greater than 128 are iden- tified as letters, digits, spaces, etc. Using the POSIX wrapper API - The /P modifier causes pcretest to call PCRE via the POSIX wrapper API - rather than its native API. This supports only the 8-bit library. When - /P is set, the following modifiers set options for the regcomp() func- + The /P modifier causes pcretest to call PCRE via the POSIX wrapper API + rather than its native API. This supports only the 8-bit library. When + /P is set, the following modifiers set options for the regcomp() func- tion: /i REG_ICASE @@ -567,48 +578,48 @@ PATTERN MODIFIERS /W REG_UCP ) the POSIX standard /8 REG_UTF8 ) - The /+ modifier works as described above. All other modifiers are + The /+ modifier works as described above. All other modifiers are ignored. Locking out certain modifiers - PCRE can be compiled with or without support for certain features such - as UTF-8/16/32 or Unicode properties. Accordingly, the standard tests - are split up into a number of different files that are selected for - running depending on which features are available. When updating the + PCRE can be compiled with or without support for certain features such + as UTF-8/16/32 or Unicode properties. Accordingly, the standard tests + are split up into a number of different files that are selected for + running depending on which features are available. When updating the tests, it is all too easy to put a new test into the wrong file by mis- - take; for example, to put a test that requires UTF support into a file - that is used when it is not available. To help detect such mistakes as - early as possible, there is a facility for locking out specific modi- + take; for example, to put a test that requires UTF support into a file + that is used when it is not available. To help detect such mistakes as + early as possible, there is a facility for locking out specific modi- fiers. If an input line for pcretest starts with the string "< forbid " - the following sequence of characters is taken as a list of forbidden + the following sequence of characters is taken as a list of forbidden modifiers. For example, in the test files that must not use UTF or Uni- code property support, this line appears: < forbid 8W - This locks out the /8 and /W modifiers. An immediate error is given if - they are subsequently encountered. If the character string contains < - but not >, all the multi-character modifiers that begin with < are - locked out. Otherwise, such modifiers must be explicitly listed, for + This locks out the /8 and /W modifiers. An immediate error is given if + they are subsequently encountered. If the character string contains < + but not >, all the multi-character modifiers that begin with < are + locked out. Otherwise, such modifiers must be explicitly listed, for example: < forbid <JS><cr> There must be a single space between < and "forbid" for this feature to - be recognised. If there is not, the line is interpreted either as a - request to re-load a pre-compiled pattern (see "SAVING AND RELOADING - COMPILED PATTERNS" below) or, if there is a another < character, as a + be recognised. If there is not, the line is interpreted either as a + request to re-load a pre-compiled pattern (see "SAVING AND RELOADING + COMPILED PATTERNS" below) or, if there is a another < character, as a pattern that uses < as its delimiter. DATA LINES - Before each data line is passed to pcre[16|32]_exec(), leading and - trailing white space is removed, and it is then scanned for \ escapes. - Some of these are pretty esoteric features, intended for checking out - some of the more complicated features of PCRE. If you are just testing - "ordinary" regular expressions, you probably don't need any of these. + Before each data line is passed to pcre[16|32]_exec(), leading and + trailing white space is removed, and it is then scanned for \ escapes. + Some of these are pretty esoteric features, intended for checking out + some of the more complicated features of PCRE. If you are just testing + "ordinary" regular expressions, you probably don't need any of these. The following escapes are recognized: \a alarm (BEL, \x07) @@ -669,7 +680,7 @@ DATA LINES (any number of digits) \R pass the PCRE_DFA_RESTART option to pcre[16|32]_dfa_exec() \S output details of memory get/free calls during matching - \Y pass the PCRE_NO_START_OPTIMIZE option to + \Y pass the PCRE_NO_START_OPTIMIZE option to pcre[16|32]_exec() or pcre[16|32]_dfa_exec() \Z pass the PCRE_NOTEOL option to pcre[16|32]_exec() @@ -678,7 +689,7 @@ DATA LINES pcre[16|32]_exec() or pcre[16|32]_dfa_exec() \>dd start the match at offset dd (optional "-"; then any number of digits); this sets the startoffset - argument for pcre[16|32]_exec() or + argument for pcre[16|32]_exec() or pcre[16|32]_dfa_exec() \<cr> pass the PCRE_NEWLINE_CR option to pcre[16|32]_exec() or pcre[16|32]_dfa_exec() @@ -691,102 +702,102 @@ DATA LINES \<any> pass the PCRE_NEWLINE_ANY option to pcre[16|32]_exec() or pcre[16|32]_dfa_exec() - The use of \x{hh...} is not dependent on the use of the /8 modifier on - the pattern. It is recognized always. There may be any number of hexa- - decimal digits inside the braces; invalid values provoke error mes- + The use of \x{hh...} is not dependent on the use of the /8 modifier on + the pattern. It is recognized always. There may be any number of hexa- + decimal digits inside the braces; invalid values provoke error mes- sages. - Note that \xhh specifies one byte rather than one character in UTF-8 - mode; this makes it possible to construct invalid UTF-8 sequences for - testing purposes. On the other hand, \x{hh} is interpreted as a UTF-8 - character in UTF-8 mode, generating more than one byte if the value is - greater than 127. When testing the 8-bit library not in UTF-8 mode, + Note that \xhh specifies one byte rather than one character in UTF-8 + mode; this makes it possible to construct invalid UTF-8 sequences for + testing purposes. On the other hand, \x{hh} is interpreted as a UTF-8 + character in UTF-8 mode, generating more than one byte if the value is + greater than 127. When testing the 8-bit library not in UTF-8 mode, \x{hh} generates one byte for values less than 256, and causes an error for greater values. In UTF-16 mode, all 4-digit \x{hhhh} values are accepted. This makes it possible to construct invalid UTF-16 sequences for testing purposes. - In UTF-32 mode, all 4- to 8-digit \x{...} values are accepted. This - makes it possible to construct invalid UTF-32 sequences for testing + In UTF-32 mode, all 4- to 8-digit \x{...} values are accepted. This + makes it possible to construct invalid UTF-32 sequences for testing purposes. - The escapes that specify line ending sequences are literal strings, + The escapes that specify line ending sequences are literal strings, exactly as shown. No more than one newline setting should be present in any data line. - A backslash followed by anything else just escapes the anything else. - If the very last character is a backslash, it is ignored. This gives a - way of passing an empty line as data, since a real empty line termi- + A backslash followed by anything else just escapes the anything else. + If the very last character is a backslash, it is ignored. This gives a + way of passing an empty line as data, since a real empty line termi- nates the data input. - The \J escape provides a way of setting the maximum stack size that is - used by the just-in-time optimization code. It is ignored if JIT opti- - mization is not being used. Providing a stack that is larger than the + The \J escape provides a way of setting the maximum stack size that is + used by the just-in-time optimization code. It is ignored if JIT opti- + mization is not being used. Providing a stack that is larger than the default 32K is necessary only for very complicated patterns. If \M is present, pcretest calls pcre[16|32]_exec() several times, with different values in the match_limit and match_limit_recursion fields of - the pcre[16|32]_extra data structure, until it finds the minimum num- + the pcre[16|32]_extra data structure, until it finds the minimum num- bers for each parameter that allow pcre[16|32]_exec() to complete with- - out error. Because this is testing a specific feature of the normal + out error. Because this is testing a specific feature of the normal interpretive pcre[16|32]_exec() execution, the use of any JIT optimiza- - tion that might have been set up by the /S+ qualifier of -s+ option is + tion that might have been set up by the /S+ qualifier of -s+ option is disabled. - The match_limit number is a measure of the amount of backtracking that - takes place, and checking it out can be instructive. For most simple - matches, the number is quite small, but for patterns with very large - numbers of matching possibilities, it can become large very quickly - with increasing length of subject string. The match_limit_recursion - number is a measure of how much stack (or, if PCRE is compiled with - NO_RECURSE, how much heap) memory is needed to complete the match + The match_limit number is a measure of the amount of backtracking that + takes place, and checking it out can be instructive. For most simple + matches, the number is quite small, but for patterns with very large + numbers of matching possibilities, it can become large very quickly + with increasing length of subject string. The match_limit_recursion + number is a measure of how much stack (or, if PCRE is compiled with + NO_RECURSE, how much heap) memory is needed to complete the match attempt. - When \O is used, the value specified may be higher or lower than the + When \O is used, the value specified may be higher or lower than the size set by the -O command line option (or defaulted to 45); \O applies - only to the call of pcre[16|32]_exec() for the line in which it + only to the call of pcre[16|32]_exec() for the line in which it appears. - If the /P modifier was present on the pattern, causing the POSIX wrap- - per API to be used, the only option-setting sequences that have any - effect are \B, \N, and \Z, causing REG_NOTBOL, REG_NOTEMPTY, and + If the /P modifier was present on the pattern, causing the POSIX wrap- + per API to be used, the only option-setting sequences that have any + effect are \B, \N, and \Z, causing REG_NOTBOL, REG_NOTEMPTY, and REG_NOTEOL, respectively, to be passed to regexec(). THE ALTERNATIVE MATCHING FUNCTION - By default, pcretest uses the standard PCRE matching function, - pcre[16|32]_exec() to match each data line. PCRE also supports an - alternative matching function, pcre[16|32]_dfa_test(), which operates - in a different way, and has some restrictions. The differences between + By default, pcretest uses the standard PCRE matching function, + pcre[16|32]_exec() to match each data line. PCRE also supports an + alternative matching function, pcre[16|32]_dfa_test(), which operates + in a different way, and has some restrictions. The differences between the two functions are described in the pcrematching documentation. - If a data line contains the \D escape sequence, or if the command line - contains the -dfa option, the alternative matching function is used. + If a data line contains the \D escape sequence, or if the command line + contains the -dfa option, the alternative matching function is used. This function finds all possible matches at a given point. If, however, - the \F escape sequence is present in the data line, it stops after the + the \F escape sequence is present in the data line, it stops after the first match is found. This is always the shortest possible match. DEFAULT OUTPUT FROM PCRETEST - This section describes the output when the normal matching function, + This section describes the output when the normal matching function, pcre[16|32]_exec(), is being used. When a match succeeds, pcretest outputs the list of captured substrings - that pcre[16|32]_exec() returns, starting with number 0 for the string - that matched the whole pattern. Otherwise, it outputs "No match" when - the return is PCRE_ERROR_NOMATCH, and "Partial match:" followed by the - partially matching substring when pcre[16|32]_exec() returns - PCRE_ERROR_PARTIAL. (Note that this is the entire substring that was - inspected during the partial match; it may include characters before - the actual match start if a lookbehind assertion, \K, \b, or \B was - involved.) For any other return, pcretest outputs the PCRE negative - error number and a short descriptive phrase. If the error is a failed - UTF string check, the offset of the start of the failing character and - the reason code are also output, provided that the size of the output - vector is at least two. Here is an example of an interactive pcretest + that pcre[16|32]_exec() returns, starting with number 0 for the string + that matched the whole pattern. Otherwise, it outputs "No match" when + the return is PCRE_ERROR_NOMATCH, and "Partial match:" followed by the + partially matching substring when pcre[16|32]_exec() returns + PCRE_ERROR_PARTIAL. (Note that this is the entire substring that was + inspected during the partial match; it may include characters before + the actual match start if a lookbehind assertion, \K, \b, or \B was + involved.) For any other return, pcretest outputs the PCRE negative + error number and a short descriptive phrase. If the error is a failed + UTF string check, the offset of the start of the failing character and + the reason code are also output, provided that the size of the output + vector is at least two. Here is an example of an interactive pcretest run. $ pcretest @@ -800,10 +811,10 @@ DEFAULT OUTPUT FROM PCRETEST No match Unset capturing substrings that are not followed by one that is set are - not returned by pcre[16|32]_exec(), and are not shown by pcretest. In + not returned by pcre[16|32]_exec(), and are not shown by pcretest. In the following example, there are two capturing substrings, but when the - first data line is matched, the second, unset substring is not shown. - An "internal" unset substring is shown as "<unset>", as for the second + first data line is matched, the second, unset substring is not shown. + An "internal" unset substring is shown as "<unset>", as for the second data line. re> /(a)|(b)/ @@ -815,11 +826,11 @@ DEFAULT OUTPUT FROM PCRETEST 1: <unset> 2: b - If the strings contain any non-printing characters, they are output as - \xhh escapes if the value is less than 256 and UTF mode is not set. + If the strings contain any non-printing characters, they are output as + \xhh escapes if the value is less than 256 and UTF mode is not set. Otherwise they are output as \x{hh...} escapes. See below for the defi- - nition of non-printing characters. If the pattern has the /+ modifier, - the output for substring 0 is followed by the the rest of the subject + nition of non-printing characters. If the pattern has the /+ modifier, + the output for substring 0 is followed by the the rest of the subject string, identified by "0+" like this: re> /cat/+ @@ -827,7 +838,7 @@ DEFAULT OUTPUT FROM PCRETEST 0: cat 0+ aract - If the pattern has the /g or /G modifier, the results of successive + If the pattern has the /g or /G modifier, the results of successive matching attempts are output in sequence, like this: re> /\Bi(\w\w)/g @@ -839,32 +850,32 @@ DEFAULT OUTPUT FROM PCRETEST 0: ipp 1: pp - "No match" is output only if the first match attempt fails. Here is an - example of a failure message (the offset 4 that is specified by \>4 is + "No match" is output only if the first match attempt fails. Here is an + example of a failure message (the offset 4 that is specified by \>4 is past the end of the subject string): re> /xyz/ data> xyz\>4 Error -24 (bad offset value) - If any of the sequences \C, \G, or \L are present in a data line that - is successfully matched, the substrings extracted by the convenience + If any of the sequences \C, \G, or \L are present in a data line that + is successfully matched, the substrings extracted by the convenience functions are output with C, G, or L after the string number instead of a colon. This is in addition to the normal full list. The string length - (that is, the return from the extraction function) is given in paren- + (that is, the return from the extraction function) is given in paren- theses after each string for \C and \G. Note that whereas patterns can be continued over several lines (a plain ">" prompt is used for continuations), data lines may not. However new- - lines can be included in data by means of the \n escape (or \r, \r\n, + lines can be included in data by means of the \n escape (or \r, \r\n, etc., depending on the newline sequence setting). OUTPUT FROM THE ALTERNATIVE MATCHING FUNCTION When the alternative matching function, pcre[16|32]_dfa_exec(), is used - (by means of the \D escape sequence or the -dfa command line option), - the output consists of a list of all the matches that start at the + (by means of the \D escape sequence or the -dfa command line option), + the output consists of a list of all the matches that start at the first point in the subject where there is at least one match. For exam- ple: @@ -874,11 +885,11 @@ OUTPUT FROM THE ALTERNATIVE MATCHING FUNCTION 1: tang 2: tan - (Using the normal matching function on this data finds only "tang".) - The longest matching string is always given first (and numbered zero). + (Using the normal matching function on this data finds only "tang".) + The longest matching string is always given first (and numbered zero). After a PCRE_ERROR_PARTIAL return, the output is "Partial match:", fol- - lowed by the partially matching substring. (Note that this is the - entire substring that was inspected during the partial match; it may + lowed by the partially matching substring. (Note that this is the + entire substring that was inspected during the partial match; it may include characters before the actual match start if a lookbehind asser- tion, \K, \b, or \B was involved.) @@ -894,16 +905,16 @@ OUTPUT FROM THE ALTERNATIVE MATCHING FUNCTION 1: tan 0: tan - Since the matching function does not support substring capture, the - escape sequences that are concerned with captured substrings are not + Since the matching function does not support substring capture, the + escape sequences that are concerned with captured substrings are not relevant. RESTARTING AFTER A PARTIAL MATCH When the alternative matching function has given the PCRE_ERROR_PARTIAL - return, indicating that the subject partially matched the pattern, you - can restart the match with additional subject data by means of the \R + return, indicating that the subject partially matched the pattern, you + can restart the match with additional subject data by means of the \R escape sequence. For example: re> /^\d?\d(jan|feb|mar|apr|may|jun|jul|aug|sep|oct|nov|dec)\d\d$/ @@ -912,30 +923,30 @@ RESTARTING AFTER A PARTIAL MATCH data> n05\R\D 0: n05 - For further information about partial matching, see the pcrepartial + For further information about partial matching, see the pcrepartial documentation. CALLOUTS - If the pattern contains any callout requests, pcretest's callout func- - tion is called during matching. This works with both matching func- + If the pattern contains any callout requests, pcretest's callout func- + tion is called during matching. This works with both matching func- tions. By default, the called function displays the callout number, the - start and current positions in the text at the callout time, and the + start and current positions in the text at the callout time, and the next pattern item to be tested. For example: --->pqrabcdef 0 ^ ^ \d - This output indicates that callout number 0 occurred for a match - attempt starting at the fourth character of the subject string, when + This output indicates that callout number 0 occurred for a match + attempt starting at the fourth character of the subject string, when the pointer was at the seventh character of the data, and when the next - pattern item was \d. Just one circumflex is output if the start and + pattern item was \d. Just one circumflex is output if the start and current positions are the same. Callouts numbered 255 are assumed to be automatic callouts, inserted as - a result of the /C pattern modifier. In this case, instead of showing - the callout number, the offset in the pattern, preceded by a plus, is + a result of the /C pattern modifier. In this case, instead of showing + the callout number, the offset in the pattern, preceded by a plus, is output. For example: re> /\d?[A-E]\*/C @@ -948,7 +959,7 @@ CALLOUTS 0: E* If a pattern contains (*MARK) items, an additional line is output when- - ever a change of latest mark is passed to the callout function. For + ever a change of latest mark is passed to the callout function. For example: re> /a(*MARK:X)bc/C @@ -962,104 +973,104 @@ CALLOUTS +12 ^ ^ 0: abc - The mark changes between matching "a" and "b", but stays the same for - the rest of the match, so nothing more is output. If, as a result of - backtracking, the mark reverts to being unset, the text "<unset>" is + The mark changes between matching "a" and "b", but stays the same for + the rest of the match, so nothing more is output. If, as a result of + backtracking, the mark reverts to being unset, the text "<unset>" is output. - The callout function in pcretest returns zero (carry on matching) by - default, but you can use a \C item in a data line (as described above) + The callout function in pcretest returns zero (carry on matching) by + default, but you can use a \C item in a data line (as described above) to change this and other parameters of the callout. - Inserting callouts can be helpful when using pcretest to check compli- - cated regular expressions. For further information about callouts, see + Inserting callouts can be helpful when using pcretest to check compli- + cated regular expressions. For further information about callouts, see the pcrecallout documentation. NON-PRINTING CHARACTERS - When pcretest is outputting text in the compiled version of a pattern, - bytes other than 32-126 are always treated as non-printing characters + When pcretest is outputting text in the compiled version of a pattern, + bytes other than 32-126 are always treated as non-printing characters are are therefore shown as hex escapes. - When pcretest is outputting text that is a matched part of a subject - string, it behaves in the same way, unless a different locale has been - set for the pattern (using the /L modifier). In this case, the + When pcretest is outputting text that is a matched part of a subject + string, it behaves in the same way, unless a different locale has been + set for the pattern (using the /L modifier). In this case, the isprint() function to distinguish printing and non-printing characters. SAVING AND RELOADING COMPILED PATTERNS - The facilities described in this section are not available when the - POSIX interface to PCRE is being used, that is, when the /P pattern + The facilities described in this section are not available when the + POSIX interface to PCRE is being used, that is, when the /P pattern modifier is specified. When the POSIX interface is not in use, you can cause pcretest to write - a compiled pattern to a file, by following the modifiers with > and a + a compiled pattern to a file, by following the modifiers with > and a file name. For example: /pattern/im >/some/file - See the pcreprecompile documentation for a discussion about saving and - re-using compiled patterns. Note that if the pattern was successfully + See the pcreprecompile documentation for a discussion about saving and + re-using compiled patterns. Note that if the pattern was successfully studied with JIT optimization, the JIT data cannot be saved. - The data that is written is binary. The first eight bytes are the - length of the compiled pattern data followed by the length of the - optional study data, each written as four bytes in big-endian order - (most significant byte first). If there is no study data (either the + The data that is written is binary. The first eight bytes are the + length of the compiled pattern data followed by the length of the + optional study data, each written as four bytes in big-endian order + (most significant byte first). If there is no study data (either the pattern was not studied, or studying did not return any data), the sec- - ond length is zero. The lengths are followed by an exact copy of the - compiled pattern. If there is additional study data, this (excluding - any JIT data) follows immediately after the compiled pattern. After + ond length is zero. The lengths are followed by an exact copy of the + compiled pattern. If there is additional study data, this (excluding + any JIT data) follows immediately after the compiled pattern. After writing the file, pcretest expects to read a new pattern. - A saved pattern can be reloaded into pcretest by specifying < and a - file name instead of a pattern. There must be no space between < and - the file name, which must not contain a < character, as otherwise - pcretest will interpret the line as a pattern delimited by < charac- + A saved pattern can be reloaded into pcretest by specifying < and a + file name instead of a pattern. There must be no space between < and + the file name, which must not contain a < character, as otherwise + pcretest will interpret the line as a pattern delimited by < charac- ters. For example: re> </some/file Compiled pattern loaded from /some/file No study data - If the pattern was previously studied with the JIT optimization, the - JIT information cannot be saved and restored, and so is lost. When the - pattern has been loaded, pcretest proceeds to read data lines in the + If the pattern was previously studied with the JIT optimization, the + JIT information cannot be saved and restored, and so is lost. When the + pattern has been loaded, pcretest proceeds to read data lines in the usual way. - You can copy a file written by pcretest to a different host and reload - it there, even if the new host has opposite endianness to the one on - which the pattern was compiled. For example, you can compile on an i86 - machine and run on a SPARC machine. When a pattern is reloaded on a + You can copy a file written by pcretest to a different host and reload + it there, even if the new host has opposite endianness to the one on + which the pattern was compiled. For example, you can compile on an i86 + machine and run on a SPARC machine. When a pattern is reloaded on a host with different endianness, the confirmation message is changed to: Compiled pattern (byte-inverted) loaded from /some/file The test suite contains some saved pre-compiled patterns with different - endianness. These are reloaded using "<!" instead of just "<". This + endianness. These are reloaded using "<!" instead of just "<". This suppresses the "(byte-inverted)" text so that the output is the same on - all hosts. It also forces debugging output once the pattern has been + all hosts. It also forces debugging output once the pattern has been reloaded. - File names for saving and reloading can be absolute or relative, but - note that the shell facility of expanding a file name that starts with + File names for saving and reloading can be absolute or relative, but + note that the shell facility of expanding a file name that starts with a tilde (~) is not available. - The ability to save and reload files in pcretest is intended for test- - ing and experimentation. It is not intended for production use because - only a single pattern can be written to a file. Furthermore, there is - no facility for supplying custom character tables for use with a - reloaded pattern. If the original pattern was compiled with custom - tables, an attempt to match a subject string using a reloaded pattern - is likely to cause pcretest to crash. Finally, if you attempt to load + The ability to save and reload files in pcretest is intended for test- + ing and experimentation. It is not intended for production use because + only a single pattern can be written to a file. Furthermore, there is + no facility for supplying custom character tables for use with a + reloaded pattern. If the original pattern was compiled with custom + tables, an attempt to match a subject string using a reloaded pattern + is likely to cause pcretest to crash. Finally, if you attempt to load a file that is not in the correct format, the result is undefined. SEE ALSO - pcre(3), pcre16(3), pcre32(3), pcreapi(3), pcrecallout(3), pcrejit, + pcre(3), pcre16(3), pcre32(3), pcreapi(3), pcrecallout(3), pcrejit, pcrematching(3), pcrepartial(d), pcrepattern(3), pcreprecompile(3). @@ -1072,5 +1083,5 @@ AUTHOR REVISION - Last updated: 12 November 2013 - Copyright (c) 1997-2013 University of Cambridge. + Last updated: 09 February 2014 + Copyright (c) 1997-2014 University of Cambridge. diff --git a/maint/ManyConfigTests b/maint/ManyConfigTests index d9c3ae0..42e31f2 100755 --- a/maint/ManyConfigTests +++ b/maint/ManyConfigTests @@ -79,7 +79,7 @@ function runtest() fi echo "Making" - make >/dev/null 2>teststderr + make -j >/dev/null 2>teststderr if [ $? -ne 0 -o -s teststderr ]; then echo " " echo "**** Errors or warnings while making ****" @@ -166,7 +166,7 @@ function runtest() # Update the total count whenever a new test is added; it is used to show # progess as each test is run. -testtotal=42 +testtotal=43 testcount=0 # This set of tests builds PCRE and runs the tests with a variety of configure diff --git a/pcre_compile.c b/pcre_compile.c index e220799..180a46c 100644 --- a/pcre_compile.c +++ b/pcre_compile.c @@ -548,7 +548,7 @@ static const char error_texts[] = "invalid range in character class\0" "group name must start with a non-digit\0" /* 85 */ - "parentheses are too deeply nested (stack check)\0" + "parentheses are too deeply nested (stack check)\0" ; /* Table to identify digits and hex digits. This is used when compiling @@ -4081,8 +4081,8 @@ for (c = *cptr; c <= d; c++) 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 +/* 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; @@ -4146,7 +4146,7 @@ if ((options & PCRE_CASELESS) != 0) 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. */ @@ -4209,7 +4209,7 @@ for (c = start; c <= classbits_end; c++) #if defined SUPPORT_UTF || !defined COMPILE_PCRE8 if (start <= 0xff) start = 0xff + 1; -if (end >= start) +if (end >= start) { pcre_uchar *uchardata = *uchardptr; #ifdef SUPPORT_UTF @@ -6620,9 +6620,9 @@ for (;; ptr++) 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 */ + 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. */ @@ -8042,8 +8042,8 @@ if (PUBL(stack_guard) != NULL && PUBL(stack_guard)()) *errorcodeptr= ERR85; return FALSE; } - -/* Miscellaneous initialization */ + +/* Miscellaneous initialization */ bc.outer = bcptr; bc.current_branch = code; diff --git a/pcre_exec.c b/pcre_exec.c index 7a59dbe..5dec992 100644 --- a/pcre_exec.c +++ b/pcre_exec.c @@ -2700,11 +2700,11 @@ for (;;) while (count-- > 0) { offset = GET2(slot, 0) << 1; - if (offset < offset_top && md->offset_vector[offset] >= 0) + 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; } } diff --git a/pcre_internal.h b/pcre_internal.h index 2c7f5f8..6e915a0 100644 --- a/pcre_internal.h +++ b/pcre_internal.h @@ -582,9 +582,9 @@ changed in future to be a fixed number of bytes or to depend on LINK_SIZE. */ #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 +/* 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 @@ -3788,10 +3788,10 @@ while (!done) case 'Q': switch (*pp) { - case '0': + case '0': case '1': stack_guard_return = *pp++ - '0'; - break; + break; default: fprintf(outfile, "** Missing 0 or 1 after /Q\n"); |