diff options
| author | ph10 <ph10@6239d852-aaf2-0410-a92c-79f79f948069> | 2015-12-17 18:44:06 +0000 |
|---|---|---|
| committer | ph10 <ph10@6239d852-aaf2-0410-a92c-79f79f948069> | 2015-12-17 18:44:06 +0000 |
| commit | 9a29fc883ba431ef060e80308d5e4b813b70388d (patch) | |
| tree | e0b4084519b7d988fe46e528b8e428a3a48f9204 | |
| parent | 9f663b990467cfd5f173147c3b648cf195f606bd (diff) | |
| download | pcre2-9a29fc883ba431ef060e80308d5e4b813b70388d.tar.gz | |
File tidies, version updates, etc. for 10.21-RC1
git-svn-id: svn://vcs.exim.org/pcre2/code/trunk@471 6239d852-aaf2-0410-a92c-79f79f948069
48 files changed, 1730 insertions, 1361 deletions
diff --git a/CMakeLists.txt b/CMakeLists.txt index 0ec4402..2c84b05 100644 --- a/CMakeLists.txt +++ b/CMakeLists.txt @@ -258,7 +258,7 @@ ENDIF(PCRE2_SUPPORT_BSR_ANYCRLF) IF(PCRE2_NEVER_BACKSLASH_C) SET(NEVER_BACKSLASH_C 1) -ENDIF(PCRE2_NEVER_BACKSLASH_C) +ENDIF(PCRE2_NEVER_BACKSLASH_C) IF(PCRE2_SUPPORT_UNICODE) SET(SUPPORT_UNICODE 1) @@ -400,7 +400,7 @@ SET(PCRE2_SOURCES src/pcre2_context.c src/pcre2_dfa_match.c src/pcre2_error.c - src/pcre2_find_bracket.c + src/pcre2_find_bracket.c src/pcre2_jit_compile.c src/pcre2_maketables.c src/pcre2_match.c @@ -268,18 +268,18 @@ size of patterns that they are prepared to handle. 78. (*NO_AUTO_POSSESS) was not working. -79. Adding group information caching improves the speed of compiling when -checking whether a group has a fixed length and/or could match an empty string, -especially when recursion or subroutine calls are involved. However, this -cannot be used when (?| is present in the pattern because the same number may -be used for groups of different sizes. To catch runaway patterns in this -situation, counts have been introduced to the functions that scan for empty +79. Adding group information caching improves the speed of compiling when +checking whether a group has a fixed length and/or could match an empty string, +especially when recursion or subroutine calls are involved. However, this +cannot be used when (?| is present in the pattern because the same number may +be used for groups of different sizes. To catch runaway patterns in this +situation, counts have been introduced to the functions that scan for empty branches or compute fixed lengths. 80. Allow for the possibility of the size of the nest_save structure not being a factor of the size of the compiling workspace (it currently is). -81. Check for integer overflow in minimum length calculation and cap it at +81. Check for integer overflow in minimum length calculation and cap it at 65535. 82. Small optimizations in code for finding the minimum matching length. @@ -290,72 +290,72 @@ a factor of the size of the compiling workspace (it currently is). 85. Check for too many replacements (more than INT_MAX) in pcre2_substitute(). -86. Avoid the possibility of computing with an out-of-bounds pointer (though +86. Avoid the possibility of computing with an out-of-bounds pointer (though not dereferencing it) while handling lookbehind assertions. -87. Failure to get memory for the match data in regcomp() is now given as a +87. Failure to get memory for the match data in regcomp() is now given as a regcomp() error instead of waiting for regexec() to pick it up. -88. In pcre2_substitute(), ensure that CRLF is not split when it is a valid +88. In pcre2_substitute(), ensure that CRLF is not split when it is a valid newline sequence. 89. Paranoid check in regcomp() for bad error code from pcre2_compile(). -90. Run test 8 (internal offsets and code sizes) for link sizes 3 and 4 as well +90. Run test 8 (internal offsets and code sizes) for link sizes 3 and 4 as well as for link size 2. -91. Document that JIT has a limit on pattern size, and give more information +91. Document that JIT has a limit on pattern size, and give more information about JIT compile failures in pcre2test. 92. Implement PCRE2_INFO_HASBACKSLASHC. -93. Re-arrange valgrind support code in pcre2test to avoid spurious reports +93. Re-arrange valgrind support code in pcre2test to avoid spurious reports with JIT (possibly caused by SSE2?). 94. Support offset_limit in JIT. -95. A sequence such as [[:punct:]b] that is, a POSIX character class followed -by a single ASCII character in a class item, was incorrectly compiled in UCP +95. A sequence such as [[:punct:]b] that is, a POSIX character class followed +by a single ASCII character in a class item, was incorrectly compiled in UCP mode. The POSIX class got lost, but only if the single character followed it. -96. [:punct:] in UCP mode was matching some characters in the range 128-255 +96. [:punct:] in UCP mode was matching some characters in the range 128-255 that should not have been matched. -97. If [:^ascii:] or [:^xdigit:] are present in a non-negated class, all -characters with code points greater than 255 are in the class. When a Unicode -property was also in the class (if PCRE2_UCP is set, escapes such as \w are -turned into Unicode properties), wide characters were not correctly handled, +97. If [:^ascii:] or [:^xdigit:] are present in a non-negated class, all +characters with code points greater than 255 are in the class. When a Unicode +property was also in the class (if PCRE2_UCP is set, escapes such as \w are +turned into Unicode properties), wide characters were not correctly handled, and could fail to match. -98. In pcre2test, make the "startoffset" modifier a synonym of "offset", +98. In pcre2test, make the "startoffset" modifier a synonym of "offset", because it sets the "startoffset" parameter for pcre2_match(). -99. If PCRE2_AUTO_CALLOUT was set on a pattern that had a (?# comment between -an item and its qualifier (for example, A(?#comment)?B) pcre2_compile() +99. If PCRE2_AUTO_CALLOUT was set on a pattern that had a (?# comment between +an item and its qualifier (for example, A(?#comment)?B) pcre2_compile() misbehaved. This bug was found by the LLVM fuzzer. -100. The error for an invalid UTF pattern string always gave the code unit +100. The error for an invalid UTF pattern string always gave the code unit offset as zero instead of where the invalidity was found. -101. Further to 97 above, negated classes such as [^[:^ascii:]\d] were also not +101. Further to 97 above, negated classes such as [^[:^ascii:]\d] were also not working correctly in UCP mode. -102. Similar to 99 above, if an isolated \E was present between an item and its +102. Similar to 99 above, if an isolated \E was present between an item and its qualifier when PCRE2_AUTO_CALLOUT was set, pcre2_compile() misbehaved. This bug was found by the LLVM fuzzer. -103. The POSIX wrapper function regexec() crashed if the option REG_STARTEND +103. The POSIX wrapper function regexec() crashed if the option REG_STARTEND was set when the pmatch argument was NULL. It now returns REG_INVARG. 104. Allow for up to 32-bit numbers in the ordin() function in pcre2grep. -105. An empty \Q\E sequence between an item and its qualifier caused +105. An empty \Q\E sequence between an item and its qualifier caused pcre2_compile() to misbehave when auto callouts were enabled. This bug was found by the LLVM fuzzer. -106. If both PCRE2_ALT_VERBNAMES and PCRE2_EXTENDED were set, and a (*MARK) or -other verb "name" ended with whitespace immediately before the closing -parenthesis, pcre2_compile() misbehaved. Example: /(*:abc )/, but only when +106. If both PCRE2_ALT_VERBNAMES and PCRE2_EXTENDED were set, and a (*MARK) or +other verb "name" ended with whitespace immediately before the closing +parenthesis, pcre2_compile() misbehaved. Example: /(*:abc )/, but only when both those options were set. 107. In a number of places pcre2_compile() was not handling NULL characters @@ -363,27 +363,27 @@ correctly, and pcre2test with the "bincode" modifier was not always correctly displaying fields containing NULLS: (a) Within /x extended #-comments - (b) Within the "name" part of (*MARK) and other *verbs - (c) Within the text argument of a callout - -108. If a pattern that was compiled with PCRE2_EXTENDED started with white -space or a #-type comment that was followed by (?-x), which turns off + (b) Within the "name" part of (*MARK) and other *verbs + (c) Within the text argument of a callout + +108. If a pattern that was compiled with PCRE2_EXTENDED started with white +space or a #-type comment that was followed by (?-x), which turns off PCRE2_EXTENDED, and there was no subsequent (?x) to turn it on again, pcre2_compile() assumed that (?-x) applied to the whole pattern and -consequently mis-compiled it. This bug was found by the LLVM fuzzer. The fix -for this bug means that a setting of any of the (?imsxU) options at the start -of a pattern is no longer transferred to the options that are returned by -PCRE2_INFO_ALLOPTIONS. In fact, this was an anachronism that should have +consequently mis-compiled it. This bug was found by the LLVM fuzzer. The fix +for this bug means that a setting of any of the (?imsxU) options at the start +of a pattern is no longer transferred to the options that are returned by +PCRE2_INFO_ALLOPTIONS. In fact, this was an anachronism that should have changed when the effects of those options were all moved to compile time. -109. An escaped closing parenthesis in the "name" part of a (*verb) when +109. An escaped closing parenthesis in the "name" part of a (*verb) when PCRE2_ALT_VERBNAMES was set caused pcre2_compile() to malfunction. This bug was found by the LLVM fuzzer. -110. Implemented PCRE2_SUBSTITUTE_UNSET_EMPTY, and updated pcre2test to make it +110. Implemented PCRE2_SUBSTITUTE_UNSET_EMPTY, and updated pcre2test to make it possible to test it. -111. "Harden" pcre2test against ridiculously large values in modifiers and +111. "Harden" pcre2test against ridiculously large values in modifiers and command line arguments. 112. Implemented PCRE2_SUBSTITUTE_UNKNOWN_UNSET and PCRE2_SUBSTITUTE_OVERFLOW_ @@ -1,6 +1,47 @@ News about PCRE2 releases ------------------------- +Version 10.21 15-December-2015 +------------------------------ + +1. Many bugs have been fixed. A large number of them were provoked only by very +strange pattern input, and were discovered by fuzzers. Some others were +discovered by code auditing. See ChangeLog for details. + +2. The Unicode tables have been updated to Unicode version 8.0.0. + +3. For Perl compatibility in EBCDIC environments, ranges such as a-z in a +class, where both values are literal letters in the same case, omit the +non-letter EBCDIC code points within the range. + +4. There have been a number of enhancements to the pcre2_substitute() function, +giving more flexibility to replacement facilities. It is now also possible to +cause the function to return the needed buffer size if the one given is too +small. + +5. The PCRE2_ALT_VERBNAMES option causes the "name" parts of special verbs such +as (*THEN:name) to be processed for backslashes and to take note of +PCRE2_EXTENDED. + +6. PCRE2_INFO_HASBACKSLASHC makes it possible for a client to find out if a +pattern uses \C, and --never-backslash-C makes it possible to compile a version +PCRE2 in which the use of \C is always forbidden. + +7. A limit to the length of pattern that can be handled can now be set by +calling pcre2_set_max_pattern_length(). + +8. When matching an unanchored pattern, a match can be required to begin within +a given number of code units after the start of the subject by calling +pcre2_set_offset_limit(). + +9. The pcre2test program has been extended to test new facilities, and it can +now run the tests when LF on its own is not a valid newline sequence. + +10. The RunTest script has also been updated to enable more tests to be run. + +11. There have been some minor performance enhancements. + + Version 10.20 30-June-2015 -------------------------- diff --git a/NON-AUTOTOOLS-BUILD b/NON-AUTOTOOLS-BUILD index bdbff78..ceb9245 100644 --- a/NON-AUTOTOOLS-BUILD +++ b/NON-AUTOTOOLS-BUILD @@ -97,7 +97,7 @@ can skip ahead to the CMake section. pcre2_context.c pcre2_dfa_match.c pcre2_error.c - pcre2_find_bracket.c + pcre2_find_bracket.c pcre2_jit_compile.c pcre2_maketables.c pcre2_match.c @@ -219,13 +219,13 @@ library. They are also documented in the pcre2build man page. to be the end of a line (see above). However, the caller of PCRE2 can restrict \R to match only CR, LF, or CRLF. You can make this the default by adding --enable-bsr-anycrlf to the "configure" command (bsr = "backslash R"). - -. In a pattern, the escape sequence \C matches a single code unit, even in a - UTF mode. This can be dangerous because it breaks up multi-code-unit + +. In a pattern, the escape sequence \C matches a single code unit, even in a + UTF mode. This can be dangerous because it breaks up multi-code-unit characters. You can build PCRE2 with the use of \C permanently locked out by - adding --enable-never-backslash-C (note the upper case C) to the "configure" - command. When \C is allowed by the library, individual applications can lock - it out by calling pcre2_compile() with the PCRE2_NEVER_BACKSLASH_C option. + adding --enable-never-backslash-C (note the upper case C) to the "configure" + command. When \C is allowed by the library, individual applications can lock + it out by calling pcre2_compile() with the PCRE2_NEVER_BACKSLASH_C option. . PCRE2 has a counter that limits the depth of nesting of parentheses in a pattern. This limits the amount of system stack that a pattern uses when it @@ -731,7 +731,7 @@ The distribution should contain the files listed below. src/pcre2_context.c ) src/pcre2_dfa_match.c ) src/pcre2_error.c ) - src/pcre2_find_bracket.c ) + src/pcre2_find_bracket.c ) src/pcre2_jit_compile.c ) src/pcre2_jit_match.c ) sources for the functions in the library, src/pcre2_jit_misc.c ) and some internal functions that they use diff --git a/RunGrepTest b/RunGrepTest index bdbb40b..67d672b 100755 --- a/RunGrepTest +++ b/RunGrepTest @@ -82,7 +82,7 @@ utf8=$? nl=`$pcre2test -C newline` if [ "$nl" != "LF" -a "$nl" != "ANY" -a "$nl" != "ANYCRLF" ]; then pcre2grep="$pcre2grep -N LF" - echo "Default newline setting forced to LF" + echo "Default newline setting forced to LF" fi # ------ Function to run and check a special pcre2grep arguments test ------- @@ -406,7 +406,7 @@ if [ $jit -ne 0 -a "$nojit" != "yes" ] ; then jitopt=-jit if [ "$valgrind" != "" ] ; then vjs="--suppressions=$testdata/valgrind-jit.supp" - fi + fi fi # If no specific tests were requested, select all. Those that are not @@ -439,10 +439,10 @@ if [ $do0 = no -a $do1 = no -a $do2 = no -a $do3 = no -a \ do17=yes do18=yes do19=yes - do20=yes - do21=yes - do22=yes - do23=yes + do20=yes + do21=yes + do22=yes + do23=yes fi # Handle any explicit skips at this stage, so that an argument list may consist @@ -720,7 +720,7 @@ for bmode in "$test8" "$test16" "$test32"; do checkresult $? 13 "" fi fi - + # Tests for DFA UTF and UCP features. Output is different for the different widths. if [ $do14 = yes ] ; then @@ -730,7 +730,7 @@ for bmode in "$test8" "$test16" "$test32"; do else $sim $valgrind ./pcre2test -q $defaultstack $bmode $opt $testdata/testinput14 testtry checkresult $? 14-$bits "" - fi + fi fi # Test non-JIT match and recursion limits @@ -798,7 +798,7 @@ for bmode in "$test8" "$test16" "$test32"; do $sim $valgrind ./pcre2test -q $defaultstack $bmode $testdata/testinput20 testtry checkresult $? 20 "" fi - + # \C tests without UTF - DFA matching is supported if [ "$do21" = yes ] ; then @@ -814,7 +814,7 @@ for bmode in "$test8" "$test16" "$test32"; do fi # \C tests with UTF - DFA matching is not supported for \C in UTF mode - + if [ "$do22" = yes ] ; then echo $title22 if [ $supportBSC -eq 0 ] ; then @@ -830,7 +830,7 @@ for bmode in "$test8" "$test16" "$test32"; do fi # Test when \C is disabled - + if [ "$do23" = yes ] ; then echo $title23 if [ $supportBSC -ne 0 ] ; then diff --git a/configure.ac b/configure.ac index ae064fd..8717c01 100644 --- a/configure.ac +++ b/configure.ac @@ -11,16 +11,16 @@ dnl be defined as -RC2, for example. For real releases, it should be empty. m4_define(pcre2_major, [10]) m4_define(pcre2_minor, [21]) m4_define(pcre2_prerelease, [-RC1]) -m4_define(pcre2_date, [2015-07-06]) +m4_define(pcre2_date, [2015-12-15]) # NOTE: The CMakeLists.txt file searches for the above variables in the first # 50 lines of this file. Please update that if the variables above are moved. # Libtool shared library interface versions (current:revision:age) -m4_define(libpcre2_8_version, [2:0:2]) -m4_define(libpcre2_16_version, [2:0:2]) -m4_define(libpcre2_32_version, [2:0:2]) -m4_define(libpcre2_posix_version, [0:0:0]) +m4_define(libpcre2_8_version, [3:0:3]) +m4_define(libpcre2_16_version, [3:0:3]) +m4_define(libpcre2_32_version, [3:0:3]) +m4_define(libpcre2_posix_version, [0:1:0]) AC_PREREQ(2.57) AC_INIT(PCRE2, pcre2_major.pcre2_minor[]pcre2_prerelease, , pcre2) @@ -189,12 +189,12 @@ AC_ARG_ENABLE(bsr-anycrlf, AS_HELP_STRING([--enable-bsr-anycrlf], [\R matches only CR, LF, CRLF by default]), , enable_bsr_anycrlf=no) - + # Handle --enable-never-backslash-C AC_ARG_ENABLE(never-backslash-C, AS_HELP_STRING([--enable-never-backslash-C], [use of \C causes an error]), - , enable_never_backslash_C=no) + , enable_never_backslash_C=no) # Handle --enable-ebcdic AC_ARG_ENABLE(ebcdic, @@ -348,7 +348,7 @@ if test "x$enable_ebcdic" = "xyes"; then AC_MSG_ERROR([support for EBCDIC and Unicode cannot be enabled at the same time]) fi if test "x$enable_pcre2_16" = "xyes" -o "x$enable_pcre2_32" = "xyes"; then - AC_MSG_ERROR([EBCDIC support is available only for the 8-bit library]) + AC_MSG_ERROR([EBCDIC support is available only for the 8-bit library]) fi fi @@ -617,7 +617,7 @@ fi if test "$enable_never_backslash_C" = "yes"; then AC_DEFINE([NEVER_BACKSLASH_C], [], [ Defining NEVER_BACKSLASH_C locks out the use of \C in all patterns.]) -fi +fi AC_DEFINE_UNQUOTED([LINK_SIZE], [$with_link_size], [ The value of LINK_SIZE determines the number of bytes used to store @@ -896,7 +896,7 @@ $PACKAGE-$VERSION configuration summary: Enable Unicode support .......... : ${enable_unicode} Newline char/sequence ........... : ${enable_newline} \R matches only ANYCRLF ......... : ${enable_bsr_anycrlf} - \C is disabled .................. : ${enable_never_backslash_C} + \C is disabled .................. : ${enable_never_backslash_C} EBCDIC coding ................... : ${enable_ebcdic} EBCDIC code for NL .............. : ${ebcdic_nl_code} Rebuild char tables ............. : ${enable_rebuild_chartables} diff --git a/doc/html/NON-AUTOTOOLS-BUILD.txt b/doc/html/NON-AUTOTOOLS-BUILD.txt index bdbff78..ceb9245 100644 --- a/doc/html/NON-AUTOTOOLS-BUILD.txt +++ b/doc/html/NON-AUTOTOOLS-BUILD.txt @@ -97,7 +97,7 @@ can skip ahead to the CMake section. pcre2_context.c pcre2_dfa_match.c pcre2_error.c - pcre2_find_bracket.c + pcre2_find_bracket.c pcre2_jit_compile.c pcre2_maketables.c pcre2_match.c diff --git a/doc/html/README.txt b/doc/html/README.txt index 49eaaf6..48d2ffd 100644 --- a/doc/html/README.txt +++ b/doc/html/README.txt @@ -219,13 +219,13 @@ library. They are also documented in the pcre2build man page. to be the end of a line (see above). However, the caller of PCRE2 can restrict \R to match only CR, LF, or CRLF. You can make this the default by adding --enable-bsr-anycrlf to the "configure" command (bsr = "backslash R"). - -. In a pattern, the escape sequence \C matches a single code unit, even in a - UTF mode. This can be dangerous because it breaks up multi-code-unit + +. In a pattern, the escape sequence \C matches a single code unit, even in a + UTF mode. This can be dangerous because it breaks up multi-code-unit characters. You can build PCRE2 with the use of \C permanently locked out by - adding --enable-never-backslash-C (note the upper case C) to the "configure" - command. When \C is allowed by the library, individual applications can lock - it out by calling pcre2_compile() with the PCRE2_NEVER_BACKSLASH_C option. + adding --enable-never-backslash-C (note the upper case C) to the "configure" + command. When \C is allowed by the library, individual applications can lock + it out by calling pcre2_compile() with the PCRE2_NEVER_BACKSLASH_C option. . PCRE2 has a counter that limits the depth of nesting of parentheses in a pattern. This limits the amount of system stack that a pattern uses when it @@ -731,7 +731,7 @@ The distribution should contain the files listed below. src/pcre2_context.c ) src/pcre2_dfa_match.c ) src/pcre2_error.c ) - src/pcre2_find_bracket.c ) + src/pcre2_find_bracket.c ) src/pcre2_jit_compile.c ) src/pcre2_jit_match.c ) sources for the functions in the library, src/pcre2_jit_misc.c ) and some internal functions that they use diff --git a/doc/html/pcre2.html b/doc/html/pcre2.html index 2cf5810..07ab8e9 100644 --- a/doc/html/pcre2.html +++ b/doc/html/pcre2.html @@ -126,9 +126,9 @@ running redundant checks. <P> The use of the \C escape sequence in a UTF-8 or UTF-16 pattern can lead to problems, because it may leave the current matching point in the middle of a -multi-code-unit character. The PCRE2_NEVER_BACKSLASH_C option can be used by an +multi-code-unit character. The PCRE2_NEVER_BACKSLASH_C option can be used by an application to lock out the use of \C, causing a compile-time error if it is -encountered. It is also possible to build PCRE2 with the use of \C permanently +encountered. It is also possible to build PCRE2 with the use of \C permanently disabled. </P> <P> diff --git a/doc/html/pcre2_pattern_info.html b/doc/html/pcre2_pattern_info.html index 4e007ee..b4cd6f5 100644 --- a/doc/html/pcre2_pattern_info.html +++ b/doc/html/pcre2_pattern_info.html @@ -42,19 +42,20 @@ request are as follows: PCRE2_BSR_ANYCRLF: CR, LF, or CRLF only PCRE2_INFO_CAPTURECOUNT Number of capturing subpatterns PCRE2_INFO_FIRSTBITMAP Bitmap of first code units, or NULL - PCRE2_INFO_FIRSTCODEUNIT First code unit when type is 1 PCRE2_INFO_FIRSTCODETYPE Type of start-of-match information 0 nothing set 1 first code unit is set 2 start of string or after newline + PCRE2_INFO_FIRSTCODEUNIT First code unit when type is 1 + PCRE2_INFO_HASBACKSLASHC Return 1 if pattern contains \C PCRE2_INFO_HASCRORLF Return 1 if explicit CR or LF matches exist in the pattern PCRE2_INFO_JCHANGED Return 1 if (?J) or (?-J) was used PCRE2_INFO_JITSIZE Size of JIT compiled code, or 0 - PCRE2_INFO_LASTCODEUNIT Last code unit when type is 1 PCRE2_INFO_LASTCODETYPE Type of must-be-present information 0 nothing set 1 code unit is set + PCRE2_INFO_LASTCODEUNIT Last code unit when type is 1 PCRE2_INFO_MATCHEMPTY 1 if the pattern can match an empty string, 0 otherwise PCRE2_INFO_MATCHLIMIT Match limit if set, @@ -62,8 +63,8 @@ request are as follows: PCRE2_INFO_MAXLOOKBEHIND Length (in characters) of the longest lookbehind assertion PCRE2_INFO_MINLENGTH Lower bound length of matching strings - PCRE2_INFO_NAMEENTRYSIZE Size of name table entries PCRE2_INFO_NAMECOUNT Number of named subpatterns + PCRE2_INFO_NAMEENTRYSIZE Size of name table entries PCRE2_INFO_NAMETABLE Pointer to name table PCRE2_CONFIG_NEWLINE Code for the newline sequence: PCRE2_NEWLINE_CR diff --git a/doc/html/pcre2_set_max_pattern_length.html b/doc/html/pcre2_set_max_pattern_length.html index f3537bb..055d1ec 100644 --- a/doc/html/pcre2_set_max_pattern_length.html +++ b/doc/html/pcre2_set_max_pattern_length.html @@ -26,7 +26,7 @@ SYNOPSIS DESCRIPTION </b><br> <P> -This function sets, in a compile context, the maximum length (in code units) of +This function sets, in a compile context, the maximum length (in code units) of the pattern that can be compiled. The result is always zero. </P> <P> diff --git a/doc/html/pcre2_substitute.html b/doc/html/pcre2_substitute.html index fbae80d..2dfd094 100644 --- a/doc/html/pcre2_substitute.html +++ b/doc/html/pcre2_substitute.html @@ -70,6 +70,9 @@ The options are: PCRE2_UTF was set at compile time) PCRE2_SUBSTITUTE_EXTENDED Do extended replacement processing PCRE2_SUBSTITUTE_GLOBAL Replace all occurrences in the subject + PCRE2_SUBSTITUTE_OVERFLOW_LENGTH If overflow, compute needed length + PCRE2_SUBSTITUTE_UNKNOWN_UNSET Treat unknown group as unset + PCRE2_SUBSTITUTE_UNSET_EMPTY Simple unset insert = empty string </pre> The function returns the number of substitutions, which may be zero if there were no matches. The result can be greater than one only when diff --git a/doc/html/pcre2api.html b/doc/html/pcre2api.html index e298e8f..bf1dd8e 100644 --- a/doc/html/pcre2api.html +++ b/doc/html/pcre2api.html @@ -618,7 +618,7 @@ of the following compile-time parameters: PCRE2's character tables The newline character sequence The compile time nested parentheses limit - The maximum length of the pattern string + The maximum length of the pattern string An external function for stack checking </pre> A compile context is also required if you are using custom memory management. @@ -661,10 +661,10 @@ in the current locale. <b> PCRE2_SIZE <i>value</i>);</b> <br> <br> -This sets a maximum length, in code units, for the pattern string that is to be -compiled. If the pattern is longer, an error is generated. This facility is -provided so that applications that accept patterns from external sources can -limit their size. The default is the largest number that a PCRE2_SIZE variable +This sets a maximum length, in code units, for the pattern string that is to be +compiled. If the pattern is longer, an error is generated. This facility is +provided so that applications that accept patterns from external sources can +limit their size. The default is the largest number that a PCRE2_SIZE variable can hold, which is effectively unlimited. <b>int pcre2_set_newline(pcre2_compile_context *<i>ccontext</i>,</b> <b> uint32_t <i>value</i>);</b> @@ -716,8 +716,8 @@ of the following match-time parameters: <pre> A callout function The offset limit for matching an unanchored pattern - The limit for calling <i>match()</i> - The limit for calling <i>match()</i> recursively + The limit for calling <b>match()</b> (see below) + The limit for calling <b>match()</b> recursively </pre> A match context is also required if you are using custom memory management. If none of these apply, just pass NULL as the context argument of @@ -771,7 +771,9 @@ PCRE2_USE_OFFSET_LIMIT is not set, an error is generated. <P> The offset limit facility can be used to track progress when searching large subject strings. See also the PCRE2_FIRSTLINE option, which requires a match to -start within the first line of the subject. +start within the first line of the subject. If this is set with an offset +limit, a match must occur in the first line and also within the offset limit. +In other words, whichever limit comes first is used. <b>int pcre2_set_match_limit(pcre2_match_context *<i>mcontext</i>,</b> <b> uint32_t <i>value</i>);</b> <br> @@ -1212,7 +1214,9 @@ built. If this option is set, an unanchored pattern is required to match before or at the first newline in the subject string, though the matched text may continue over the newline. See also PCRE2_USE_OFFSET_LIMIT, which provides a more -general limiting facility. +general limiting facility. If PCRE2_FIRSTLINE is set with an offset limit, a +match must occur in the first line and also within the offset limit. In other +words, whichever limit comes first is used. <pre> PCRE2_MATCH_UNSET_BACKREF </pre> @@ -1251,7 +1255,7 @@ This option locks out the use of \C in the pattern that is being compiled. This escape can cause unpredictable behaviour in UTF-8 or UTF-16 modes, because it may leave the current matching point in the middle of a multi-code-unit character. This option may be useful in applications that process patterns from -external sources. Note that there is also a build-time option that permanently +external sources. Note that there is also a build-time option that permanently locks out the use of \C. <pre> PCRE2_NEVER_UCP @@ -1563,11 +1567,10 @@ are as follows: Return a copy of the pattern's options. The third argument should point to a <b>uint32_t</b> variable. PCRE2_INFO_ARGOPTIONS returns exactly the options that were passed to <b>pcre2_compile()</b>, whereas PCRE2_INFO_ALLOPTIONS returns -the compile options as modified by any top-level option settings at the start -of the pattern itself. In other words, they are the options that will be in -force when matching starts. For example, if the pattern /(?im)abc(?-i)d/ is -compiled with the PCRE2_EXTENDED option, the result is PCRE2_CASELESS, -PCRE2_MULTILINE, and PCRE2_EXTENDED. +the compile options as modified by any top-level option settings such as (*UTF) +at the start of the pattern itself. For example, if the pattern /(*UTF)abc/ is +compiled with the PCRE2_EXTENDED option, the result is PCRE2_EXTENDED and +PCRE2_UTF. </P> <P> A pattern compiled without PCRE2_ANCHORED is automatically anchored by PCRE2 if @@ -1609,18 +1612,27 @@ matches only CR, LF, or CRLF. <pre> PCRE2_INFO_CAPTURECOUNT </pre> -Return the number of capturing subpatterns in the pattern. The third argument -should point to an <b>uint32_t</b> variable. +Return the highest capturing subpattern number in the pattern. In patterns +where (?| is not used, this is also the total number of capturing subpatterns. +The third argument should point to an <b>uint32_t</b> variable. +<pre> + PCRE2_INFO_FIRSTBITMAP +</pre> +In the absence of a single first code unit for a non-anchored pattern, +<b>pcre2_compile()</b> may construct a 256-bit table that defines a fixed set of +values for the first code unit in any match. For example, a pattern that starts +with [abc] results in a table with three bits set. When code unit values +greater than 255 are supported, the flag bit for 255 means "any code unit of +value 255 or above". If such a table was constructed, a pointer to it is +returned. Otherwise NULL is returned. The third argument should point to an +<b>const uint8_t *</b> variable. <pre> PCRE2_INFO_FIRSTCODETYPE </pre> Return information about the first code unit of any matched string, for a non-anchored pattern. The third argument should point to an <b>uint32_t</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 +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 PCRE2_INFO_FIRSTCODEUNIT. If there is no fixed first value, but it is known that a match can occur only at the start of the subject or following a newline in the subject, 2 is returned. Otherwise, and for anchored @@ -1635,16 +1647,10 @@ 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> - PCRE2_INFO_FIRSTBITMAP + PCRE2_INFO_HASBACKSLASHC </pre> -In the absence of a single first code unit for a non-anchored pattern, -<b>pcre2_compile()</b> may construct a 256-bit table that defines a fixed set of -values for the first code unit in any match. For example, a pattern that starts -with [abc] results in a table with three bits set. When code unit values -greater than 255 are supported, the flag bit for 255 means "any code unit of -value 255 or above". If such a table was constructed, a pointer to it is -returned. Otherwise NULL is returned. The third argument should point to an -<b>const uint8_t *</b> variable. +Return 1 if the pattern contains any instances of \C, otherwise 0. The third +argument should point to an <b>uint32_t</b> variable. <pre> PCRE2_INFO_HASCRORLF </pre> @@ -1670,13 +1676,10 @@ Returns 1 if there is a rightmost literal code unit that must exist in any matched string, other than at its start. The third argument should point to an <b>uint32_t</b> variable. If there is no such value, 0 is returned. When 1 is returned, the code unit value itself can be retrieved using -PCRE2_INFO_LASTCODEUNIT. -</P> -<P> -For anchored patterns, a last literal value is recorded only if it follows -something of variable length. For example, for the pattern /^a\d+z\d+/ the -returned value is 1 (with "z" returned from PCRE2_INFO_LASTCODEUNIT), but for -/^a\dz\d/ the returned value is 0. +PCRE2_INFO_LASTCODEUNIT. For anchored patterns, a last literal value is +recorded only if it follows something of variable length. For example, for the +pattern /^a\d+z\d+/ the returned value is 1 (with "z" returned from +PCRE2_INFO_LASTCODEUNIT), but for /^a\dz\d/ the returned value is 0. <pre> PCRE2_INFO_LASTCODEUNIT </pre> @@ -1687,8 +1690,11 @@ value, 0 is returned. <pre> PCRE2_INFO_MATCHEMPTY </pre> -Return 1 if the pattern can match an empty string, otherwise 0. The third -argument should point to an <b>uint32_t</b> variable. +Return 1 if the pattern might match an empty string, otherwise 0. The third +argument should point to an <b>uint32_t</b> variable. When a pattern contains +recursive subroutine calls it is not always possible to determine whether or +not it can match an empty string. PCRE2 takes a cautious approach and returns 1 +in such cases. <pre> PCRE2_INFO_MATCHLIMIT </pre> @@ -2142,8 +2148,13 @@ documentation. When PCRE2 is built, a default newline convention is set; this is usually the standard convention for the operating system. The default can be overridden in a -<a href="#compilecontext">compile context.</a> -During matching, the newline choice affects the behaviour of the dot, +<a href="#compilecontext">compile context</a> +by calling <b>pcre2_set_newline()</b>. It can also be overridden by starting a +pattern string with, for example, (*CRLF), as described in the +<a href="pcre2pattern.html#newlines">section on newline conventions</a> +in the +<a href="pcre2pattern.html"><b>pcre2pattern</b></a> +page. During matching, the newline choice affects the behaviour of the dot, circumflex, and dollar metacharacters. It may also alter the way the match starting position is advanced after a match failure for an unanchored pattern. </P> @@ -2191,19 +2202,20 @@ function can be used to find out how many capturing subpatterns there are in a compiled pattern. </P> <P> -A successful match returns the overall matched string and any captured -substrings to the caller via a vector of PCRE2_SIZE values. This is called the -<b>ovector</b>, and is contained within the -<a href="#matchdatablock">match data block.</a> -You can obtain direct access to the ovector by calling -<b>pcre2_get_ovector_pointer()</b> to find its address, and -<b>pcre2_get_ovector_count()</b> to find the number of pairs of values it -contains. Alternatively, you can use the auxiliary functions for accessing -captured substrings +You can use auxiliary functions for accessing captured substrings <a href="#extractbynumber">by number</a> or -<a href="#extractbyname">by name</a> -(see below). +<a href="#extractbyname">by name,</a> +as described in sections below. +</P> +<P> +Alternatively, you can make direct use of the vector of PCRE2_SIZE values, +called the <b>ovector</b>, which contains the offsets of captured strings. It is +part of the +<a href="#matchdatablock">match data block.</a> +The function <b>pcre2_get_ovector_pointer()</b> returns the address of the +ovector, and <b>pcre2_get_ovector_count()</b> returns the number of pairs of +values it contains. </P> <P> Within the ovector, the first in each pair of values is set to the offset of @@ -2292,7 +2304,13 @@ After a successful match, a partial match (PCRE2_ERROR_PARTIAL), or a failure to match (PCRE2_ERROR_NOMATCH), a (*MARK) name may be available, and <b>pcre2_get_mark()</b> can be called. It returns a pointer to the zero-terminated name, which is within the compiled pattern. Otherwise NULL is -returned. After a successful match, the (*MARK) name that is returned is the +returned. The length of the (*MARK) name (excluding the terminating zero) is +stored in the code unit that preceeds the name. You should use this instead of +relying on the terminating zero if the (*MARK) name might contain a binary +zero. +</P> +<P> +After a successful match, the (*MARK) name that is returned is the last one encountered on the matching path through the pattern. After a "no match" or a partial match, the last encountered (*MARK) name is returned. For example, consider this pattern: @@ -2313,7 +2331,7 @@ escape sequence. After a partial match, however, this value is always the same as <i>ovector[0]</i> because \K does not affect the result of a partial match. </P> <P> -After a UTF check failure, \fBpcre2_get_startchar()\fB can be used to obtain +After a UTF check failure, <b>pcre2_get_startchar()</b> can be used to obtain the code unit offset of the invalid UTF character. Details are given in the <a href="pcre2unicode.html"><b>pcre2unicode</b></a> page. @@ -2636,7 +2654,7 @@ same number causes an error at compile time. This function calls <b>pcre2_match()</b> and then makes a copy of the subject string in <i>outputbuffer</i>, replacing the part that was matched with the <i>replacement</i> string, whose length is supplied in <b>rlength</b>. This can -be given as PCRE2_ZERO_TERMINATED for a zero-terminated string. Matches in +be given as PCRE2_ZERO_TERMINATED for a zero-terminated string. Matches in which a \K item in a lookahead in the pattern causes the match to end before it starts are not supported, and give rise to an error return. </P> @@ -2650,12 +2668,21 @@ allocate memory for the compiled code. </P> <P> The <i>outlengthptr</i> argument must point to a variable that contains the -length, in code units, of the output buffer. If the function is successful, -the value is updated to contain the length of the new string, excluding the -trailing zero that is automatically added. If the function is not successful, -the value is set to PCRE2_UNSET for general errors (such as output buffer too -small). For syntax errors in the replacement string, the value is set to the -offset in the replacement string where the error was detected. +length, in code units, of the output buffer. If the function is successful, the +value is updated to contain the length of the new string, excluding the +trailing zero that is automatically added. +</P> +<P> +If the function is not successful, the value set via <i>outlengthptr</i> depends +on the type of error. For syntax errors in the replacement string, the value is +the offset in the replacement string where the error was detected. For other +errors, the value is PCRE2_UNSET by default. This includes the case of the +output buffer being too small, unless PCRE2_SUBSTITUTE_OVERFLOW_LENGTH is set +(see below), in which case the value is the minimum length needed, including +space for the trailing zero. Note that in order to compute the required length, +<b>pcre2_substitute()</b> has to simulate all the matching and copying, instead +of giving an error return as soon as the buffer overflows. Note also that the +length is in code units, not bytes. </P> <P> In the replacement string, which is interpreted as a UTF string in UTF mode, @@ -2682,15 +2709,53 @@ simultaneous substitutions, as this <b>pcre2test</b> example shows: apple lemon 2: pear orange </pre> -There is an additional option, PCRE2_SUBSTITUTE_GLOBAL, which causes the -function to iterate over the subject string, replacing every matching -substring. If this is not set, only the first matching substring is replaced. +As well as the usual options for <b>pcre2_match()</b>, a number of additional +options can be set in the <i>options</i> argument. +</P> +<P> +PCRE2_SUBSTITUTE_GLOBAL causes the function to iterate over the subject string, +replacing every matching substring. If this is not set, only the first matching +substring is replaced. If any matched substring has zero length, after the +substitution has happened, an attempt to find a non-empty match at the same +position is performed. If this is not successful, the current position is +advanced by one character except when CRLF is a valid newline sequence and the +next two characters are CR, LF. In this case, the current position is advanced +by two characters. +</P> +<P> +PCRE2_SUBSTITUTE_OVERFLOW_LENGTH changes what happens when the output buffer is +too small. The default action is to return PCRE2_ERROR_NOMEMORY immediately. If +this option is set, however, <b>pcre2_substitute()</b> continues to go through +the motions of matching and substituting (without, of course, writing anything) +in order to compute the size of buffer that is needed. This value is passed +back via the <i>outlengthptr</i> variable, with the result of the function still +being PCRE2_ERROR_NOMEMORY. +</P> +<P> +Passing a buffer size of zero is a permitted way of finding out how much memory +is needed for given substitution. However, this does mean that the entire +operation is carried out twice. Depending on the application, it may be more +efficient to allocate a large buffer and free the excess afterwards, instead of +using PCRE2_SUBSTITUTE_OVERFLOW_LENGTH. +</P> +<P> +PCRE2_SUBSTITUTE_UNKNOWN_UNSET causes references to capturing groups that do +not appear in the pattern to be treated as unset groups. This option should be +used with care, because it means that a typo in a group name or number no +longer causes the PCRE2_ERROR_NOSUBSTRING error. </P> <P> -A second additional option, PCRE2_SUBSTITUTE_EXTENDED, causes extra processing -to be applied to the replacement string. Without this option, only the dollar -character is special, and only the group insertion forms listed above are -valid. When PCRE2_SUBSTITUTE_EXTENDED is set, two things change: +PCRE2_SUBSTITUTE_UNSET_EMPTY causes unset capturing groups (including unknown +groups when PCRE2_SUBSTITUTE_UNKNOWN_UNSET is set) to be treated as empty +strings when inserted as described above. If this option is not set, an attempt +to insert an unset group causes the PCRE2_ERROR_UNSET error. This option does +not influence the extended substitution syntax described below. +</P> +<P> +PCRE2_SUBSTITUTE_EXTENDED causes extra processing to be applied to the +replacement string. Without this option, only the dollar character is special, +and only the group insertion forms listed above are valid. When +PCRE2_SUBSTITUTE_EXTENDED is set, two things change: </P> <P> Firstly, backslash in a replacement string is interpreted as an escape @@ -2740,22 +2805,46 @@ string remains in force afterwards, as shown in this <b>pcre2test</b> example: somebody 1: HELLO </pre> -If successful, the function returns the number of replacements that were made. -This may be zero if no matches were found, and is never greater than 1 unless -PCRE2_SUBSTITUTE_GLOBAL is set. +The PCRE2_SUBSTITUTE_UNSET_EMPTY option does not affect these extended +substitutions. However, PCRE2_SUBSTITUTE_UNKNOWN_UNSET does cause unknown +groups in the extended syntax forms to be treated as unset. +</P> +<P> +If successful, <b>pcre2_substitute()</b> returns the number of replacements that +were made. This may be zero if no matches were found, and is never greater than +1 unless PCRE2_SUBSTITUTE_GLOBAL is set. </P> <P> In the event of an error, a negative error code is returned. Except for PCRE2_ERROR_NOMATCH (which is never returned), errors from <b>pcre2_match()</b> -are passed straight back. PCRE2_ERROR_NOMEMORY is returned if the output buffer -is not big enough. PCRE2_ERROR_BADREPLACEMENT is used for miscellaneous syntax -errors in the replacement string, with more particular errors being -PCRE2_ERROR_BADREPESCAPE (invalid escape sequence), -PCRE2_ERROR_REPMISSING_BRACE (closing curly bracket not found), -PCRE2_BADSUBSTITUTION (syntax error in extended group substitution), and -PCRE2_BADSUBPATTERN (the pattern match ended before it started). As for all -PCRE2 errors, a text message that describes the error can be obtained by -calling <b>pcre2_get_error_message()</b>. +are passed straight back. +</P> +<P> +PCRE2_ERROR_NOSUBSTRING is returned for a non-existent substring insertion, +unless PCRE2_SUBSTITUTE_UNKNOWN_UNSET is set. +</P> +<P> +PCRE2_ERROR_UNSET is returned for an unset substring insertion (including an +unknown substring when PCRE2_SUBSTITUTE_UNKNOWN_UNSET is set) when the simple +(non-extended) syntax is used and PCRE2_SUBSTITUTE_UNSET_EMPTY is not set. +</P> +<P> +PCRE2_ERROR_NOMEMORY is returned if the output buffer is not big enough. If the +PCRE2_SUBSTITUTE_OVERFLOW_LENGTH option is set, the size of buffer that is +needed is returned via <i>outlengthptr</i>. Note that this does not happen by +default. +</P> +<P> +PCRE2_ERROR_BADREPLACEMENT is used for miscellaneous syntax errors in the +replacement string, with more particular errors being PCRE2_ERROR_BADREPESCAPE +(invalid escape sequence), PCRE2_ERROR_REPMISSING_BRACE (closing curly bracket +not found), PCRE2_BADSUBSTITUTION (syntax error in extended group +substitution), and PCRE2_BADSUBPATTERN (the pattern match ended before it +started, which can happen if \K is used in an assertion). +</P> +<P> +As for all PCRE2 errors, a text message that describes the error can be +obtained by calling <b>pcre2_get_error_message()</b>. </P> <br><a name="SEC35" href="#TOC1">DUPLICATE SUBPATTERN NAMES</a><br> <P> @@ -2796,11 +2885,11 @@ function returns the length of each entry in code units. In both cases, PCRE2_ERROR_NOSUBSTRING is returned if there are no entries for the given name. </P> <P> -The format of the name table is described above in the section entitled -<i>Information about a pattern</i> -<a href="#infoaboutpattern">above.</a> -Given all the relevant entries for the name, you can extract each of their -numbers, and hence the captured data. +The format of the name table is described +<a href="#infoaboutpattern">above</a> +in the section entitled <i>Information about a pattern</i>. Given all the +relevant entries for the name, you can extract each of their numbers, and hence +the captured data. </P> <br><a name="SEC36" href="#TOC1">FINDING ALL POSSIBLE MATCHES AT ONE POSITION</a><br> <P> @@ -3032,7 +3121,7 @@ Cambridge, England. </P> <br><a name="SEC40" href="#TOC1">REVISION</a><br> <P> -Last updated: 05 November 2015 +Last updated: 16 December 2015 <br> Copyright © 1997-2015 University of Cambridge. <br> diff --git a/doc/html/pcre2jit.html b/doc/html/pcre2jit.html index 887650d..48ee122 100644 --- a/doc/html/pcre2jit.html +++ b/doc/html/pcre2jit.html @@ -86,6 +86,13 @@ results. The returned value from <b>pcre2_jit_compile()</b> is zero on success, or a negative error code. </P> <P> +There is a limit to the size of pattern that JIT supports, imposed by the size +of machine stack that it uses. The exact rules are not documented because they +may change at any time, in particular, when new optimizations are introduced. +If a pattern is too big, a call to \fBpcre2_jit_compile()\fB returns +PCRE2_ERROR_NOMEMORY. +</P> +<P> PCRE2_JIT_COMPLETE requests the JIT compiler to generate code for complete matches. If you want to run partial matches using the PCRE2_PARTIAL_HARD or PCRE2_PARTIAL_SOFT options of <b>pcre2_match()</b>, you should set one or both @@ -425,7 +432,7 @@ Cambridge, England. </P> <br><a name="SEC13" href="#TOC1">REVISION</a><br> <P> -Last updated: 28 July 2015 +Last updated: 14 November 2015 <br> Copyright © 1997-2015 University of Cambridge. <br> diff --git a/doc/html/pcre2limits.html b/doc/html/pcre2limits.html index 35ebc11..e227a30 100644 --- a/doc/html/pcre2limits.html +++ b/doc/html/pcre2limits.html @@ -32,8 +32,8 @@ However, the speed of execution is slower. In the 32-bit library, the internal linkage size is always 4. </P> <P> -The maximum length of a source pattern string is essentially unlimited; it is -the largest number a PCRE2_SIZE variable can hold. However, the program that +The maximum length of a source pattern string is essentially unlimited; it is +the largest number a PCRE2_SIZE variable can hold. However, the program that calls <b>pcre2_compile()</b> can specify a smaller limit. </P> <P> diff --git a/doc/html/pcre2pattern.html b/doc/html/pcre2pattern.html index 0daddaf..c88e931 100644 --- a/doc/html/pcre2pattern.html +++ b/doc/html/pcre2pattern.html @@ -669,8 +669,8 @@ This is an example of an "atomic group", details of which are given This particular group matches either the two-character sequence CR followed by LF, or one of the single characters LF (linefeed, U+000A), VT (vertical tab, U+000B), FF (form feed, U+000C), CR (carriage return, U+000D), or NEL (next -line, U+0085). The two-character sequence is treated as a single unit that -cannot be split. +line, U+0085). Because this is an atomic group, the two-character sequence is +treated as a single unit that cannot be split. </P> <P> In other modes, two additional characters whose codepoints are greater than 255 @@ -1186,6 +1186,16 @@ when the <i>startoffset</i> argument of <b>pcre2_match()</b> is non-zero. The PCRE2_DOLLAR_ENDONLY option is ignored if PCRE2_MULTILINE is set. </P> <P> +When the newline convention (see +<a href="#newlines">"Newline conventions"</a> +below) recognizes the two-character sequence CRLF as a newline, this is +preferred, even if the single characters CR and LF are also recognized as +newlines. For example, if the newline convention is "any", a multiline mode +circumflex matches before "xyz" in the string "abc\r\nxyz" rather than after +CR, even though CR on its own is a valid newline. (It also matches at the very +start of the string, of course.) +</P> +<P> Note that the sequences \A, \Z, and \z can be used to match the start and end of the subject in both modes, and if all branches of a pattern start with \A it is always anchored, whether or not PCRE2_MULTILINE is set. @@ -1236,7 +1246,7 @@ with \C in UTF-8 or UTF-16 mode means that the rest of the string may start with a malformed UTF character. This has undefined results, because PCRE2 assumes that it is matching character by character in a valid UTF string (by default it checks the subject string's validity at the start of processing -unless the PCRE2_NO_UTF_CHECK option is used). +unless the PCRE2_NO_UTF_CHECK option is used). </P> <P> An application can lock out the use of \C by setting the @@ -1247,9 +1257,9 @@ build PCRE2 with the use of \C permanently disabled. PCRE2 does not allow \C to appear in lookbehind assertions <a href="#lookbehind">(described below)</a> in a UTF mode, because this would make it impossible to calculate the length of -the lookbehind. Neither the alternative matching function -<b>pcre2_dfa_match()</b> not the JIT optimizer support \C in a UTF mode. The -former gives a match-time error; the latter fails to optimize and so the match +the lookbehind. Neither the alternative matching function +<b>pcre2_dfa_match()</b> not the JIT optimizer support \C in a UTF mode. The +former gives a match-time error; the latter fails to optimize and so the match is always run using the interpreter. </P> <P> @@ -1341,11 +1351,11 @@ example [\000-\037]. Ranges can include any characters that are valid for the current mode. </P> <P> -There is a special case in EBCDIC environments for ranges whose end points are -both specified as literal letters in the same case. For compatibility with -Perl, EBCDIC code points within the range that are not letters are omitted. For -example, [h-k] matches only four characters, even though the codes for h and k -are 0x88 and 0x92, a range of 11 code points. However, if the range is +There is a special case in EBCDIC environments for ranges whose end points are +both specified as literal letters in the same case. For compatibility with +Perl, EBCDIC code points within the range that are not letters are omitted. For +example, [h-k] matches only four characters, even though the codes for h and k +are 0x88 and 0x92, a range of 11 code points. However, if the range is specified numerically, for example, [\x88-\x92] or [h-\x92], all code points are included. </P> @@ -1672,6 +1682,10 @@ first one in the pattern with the given number. The following pattern matches <pre> /(?|(abc)|(def))(?1)/ </pre> +A relative reference such as (?-1) is no different: it is just a convenient way +of computing an absolute group number. +</P> +<P> If a <a href="#conditions">condition test</a> for a subpattern's having matched refers to a non-unique number, the test is @@ -2512,7 +2526,7 @@ For example: (?(VERSION>=10.4)yes|no) </pre> This pattern matches "yes" if the PCRE2 version is greater or equal to 10.4, or -"no" otherwise. The fractional part of the version number may not contain more +"no" otherwise. The fractional part of the version number may not contain more than two digits. </P> <br><b> @@ -2626,6 +2640,21 @@ parentheses preceding the recursion. In other words, a negative number counts capturing parentheses leftwards from the point at which it is encountered. </P> <P> +Be aware however, that if +<a href="#dupsubpatternnumber">duplicate subpattern numbers</a> +are in use, relative references refer to the earliest subpattern with the +appropriate number. Consider, for example: +<pre> + (?|(a)|(b)) (c) (?-2) +</pre> +The first two capturing groups (a) and (b) are both numbered 1, and group (c) +is number 2. When the reference (?-2) is encountered, the second most recently +opened parentheses has the number 1, but it is the first such group (the (a) +group) to which the recursion refers. This would be the same if an absolute +reference (?1) was used. In other words, relative references are just a +shorthand for computing a group number. +</P> +<P> It is also possible to refer to subsequently opened parentheses, by writing references such as (?+2). However, these cannot be recursive because the reference is not inside the parentheses that are referenced. They are always @@ -2929,13 +2958,13 @@ depending on whether or not a name is present. </P> <P> By default, for compatibility with Perl, a name is any sequence of characters -that does not include a closing parenthesis. The name is not processed in +that does not include a closing parenthesis. The name is not processed in any way, and it is not possible to include a closing parenthesis in the name. -However, if the PCRE2_ALT_VERBNAMES option is set, normal backslash processing -is applied to verb names and only an unescaped closing parenthesis terminates -the name. A closing parenthesis can be included in a name either as \) or -between \Q and \E. If the PCRE2_EXTENDED option is set, unescaped whitespace -in verb names is skipped and #-comments are recognized, exactly as in the rest +However, if the PCRE2_ALT_VERBNAMES option is set, normal backslash processing +is applied to verb names and only an unescaped closing parenthesis terminates +the name. A closing parenthesis can be included in a name either as \) or +between \Q and \E. If the PCRE2_EXTENDED option is set, unescaped whitespace +in verb names is skipped and #-comments are recognized, exactly as in the rest of the pattern. </P> <P> @@ -3359,7 +3388,7 @@ Cambridge, England. </P> <br><a name="SEC30" href="#TOC1">REVISION</a><br> <P> -Last updated: 01 November 2015 +Last updated: 13 November 2015 <br> Copyright © 1997-2015 University of Cambridge. <br> diff --git a/doc/html/pcre2posix.html b/doc/html/pcre2posix.html index 7496325..e16a4c3 100644 --- a/doc/html/pcre2posix.html +++ b/doc/html/pcre2posix.html @@ -200,7 +200,7 @@ Default POSIX newline handling can be obtained by setting PCRE2_DOTALL and PCRE2_DOLLAR_ENDONLY when calling <b>pcre2_compile()</b> directly, but there is no way to make PCRE2 behave exactly as for the REG_NEWLINE action. When using the POSIX API, passing REG_NEWLINE to PCRE2's <b>regcomp()</b> function -causes PCRE2_MULTILINE to be passed to <b>pcre2_compile()</b>, and REG_DOTALL +causes PCRE2_MULTILINE to be passed to <b>pcre2_compile()</b>, and REG_DOTALL passes PCRE2_DOTALL. There is no way to pass PCRE2_DOLLAR_ENDONLY. </P> <br><a name="SEC5" href="#TOC1">MATCHING A PATTERN</a><br> @@ -235,7 +235,8 @@ to have a terminating NUL located at <i>string</i> + <i>pmatch[0].rm_eo</i> IEEE Standard 1003.2 (POSIX.2), and should be used with caution in software intended to be portable to other systems. Note that a non-zero <i>rm_so</i> does not imply REG_NOTBOL; REG_STARTEND affects only the location of the string, not -how it is matched. +how it is matched. Setting REG_STARTEND and passing <i>pmatch</i> as NULL are +mutually exclusive; the error REG_INVARG is returned. </P> <P> If the pattern was compiled with the REG_NOSUB flag, no data about any matched @@ -289,7 +290,7 @@ Cambridge, England. </P> <br><a name="SEC9" href="#TOC1">REVISION</a><br> <P> -Last updated: 30 October 2015 +Last updated: 29 November 2015 <br> Copyright © 1997-2015 University of Cambridge. <br> diff --git a/doc/html/pcre2serialize.html b/doc/html/pcre2serialize.html index 7f5336b..3747c0a 100644 --- a/doc/html/pcre2serialize.html +++ b/doc/html/pcre2serialize.html @@ -154,13 +154,13 @@ on a system with different endianness. <P> Decoded patterns can be used for matching in the usual way, and must be freed by calling <b>pcre2_code_free()</b>. However, be aware that there is a potential -race issue if you are using multiple patterns that were decoded from a single +race issue if you are using multiple patterns that were decoded from a single byte stream in a multithreaded application. A single copy of the character tables is used by all the decoded patterns and a reference count is used to arrange for its memory to be automatically freed when the last pattern is freed, but there is no locking on this reference count. Therefore, if you want to call <b>pcre2_code_free()</b> for these patterns in different threads, you -must arrange your own locking, and ensure that <b>pcre2_code_free()</b> cannot +must arrange your own locking, and ensure that <b>pcre2_code_free()</b> cannot be called by two threads at the same time. </P> <P> diff --git a/doc/html/pcre2syntax.html b/doc/html/pcre2syntax.html index e9bc896..7fdc0dc 100644 --- a/doc/html/pcre2syntax.html +++ b/doc/html/pcre2syntax.html @@ -113,7 +113,7 @@ it matches a literal "u". </pre> \C is dangerous because it may leave the current matching point in the middle of a UTF-8 or UTF-16 character. The application can lock out the use of \C by -setting the PCRE2_NEVER_BACKSLASH_C option. It is also possible to build PCRE2 +setting the PCRE2_NEVER_BACKSLASH_C option. It is also possible to build PCRE2 with the use of \C permanently disabled. </P> <P> diff --git a/doc/html/pcre2test.html b/doc/html/pcre2test.html index 6097f02..537985d 100644 --- a/doc/html/pcre2test.html +++ b/doc/html/pcre2test.html @@ -486,7 +486,7 @@ the start of a modifier list. For example: <pre> abc\=notbol,notempty </pre> -If the subject string is empty and \= is followed by whitespace, the line is +If the subject string is empty and \= is followed by whitespace, the line is treated as a comment line, and is not used for matching. For example: <pre> \= This is a comment. @@ -538,7 +538,7 @@ for a description of their effects. no_utf_check set PCRE2_NO_UTF_CHECK ucp set PCRE2_UCP ungreedy set PCRE2_UNGREEDY - use_offset_limit set PCRE2_USE_OFFSET_LIMIT + use_offset_limit set PCRE2_USE_OFFSET_LIMIT utf set PCRE2_UTF </pre> As well as turning on the PCRE2_UTF option, the <b>utf</b> modifier causes all @@ -564,7 +564,7 @@ about the pattern: jitfast use JIT fast path jitverify verify JIT use locale=<name> use this locale - max_pattern_length=<n> set the maximum pattern length + max_pattern_length=<n> set the maximum pattern length memory show memory used newline=<type> set newline type null_context compile with a NULL context @@ -649,9 +649,9 @@ by the item that follows it in the pattern. Passing a NULL context </b><br> <P> -Normally, <b>pcre2test</b> passes a context block to <b>pcre2_compile()</b>. If -the <b>null_context</b> modifier is set, however, NULL is passed. This is for -testing that <b>pcre2_compile()</b> behaves correctly in this case (it uses +Normally, <b>pcre2test</b> passes a context block to <b>pcre2_compile()</b>. If +the <b>null_context</b> modifier is set, however, NULL is passed. This is for +testing that <b>pcre2_compile()</b> behaves correctly in this case (it uses default values). </P> <br><b> @@ -675,9 +675,9 @@ Generating long repetitive patterns </b><br> <P> Some tests use long patterns that are very repetitive. Instead of creating a -very long input line for such a pattern, you can use a special repetition -feature, similar to the one described for subject lines above. If the -<b>expand</b> modifier is present on a pattern, parts of the pattern that have +very long input line for such a pattern, you can use a special repetition +feature, similar to the one described for subject lines above. If the +<b>expand</b> modifier is present on a pattern, parts of the pattern that have the form <pre> \[<characters>]{<count>} @@ -689,13 +689,13 @@ by decimal digits and "}" is found later in the pattern. If not, the characters remain in the pattern unaltered. </P> <P> -If part of an expanded pattern looks like an expansion, but is really part of -the actual pattern, unwanted expansion can be avoided by giving two values in -the quantifier. For example, \[AB]{6000,6000} is not recognized as an +If part of an expanded pattern looks like an expansion, but is really part of +the actual pattern, unwanted expansion can be avoided by giving two values in +the quantifier. For example, \[AB]{6000,6000} is not recognized as an expansion item. </P> <P> -If the <b>info</b> modifier is set on an expanded pattern, the result of the +If the <b>info</b> modifier is set on an expanded pattern, the result of the expansion is included in the information that is output. </P> <br><b> @@ -812,9 +812,9 @@ suite. Limiting the pattern length </b><br> <P> -The <b>max_pattern_length</b> modifier sets a limit, in code units, to the -length of pattern that <b>pcre2_compile()</b> will accept. Breaching the limit -causes a compilation error. The default is the largest number a PCRE2_SIZE +The <b>max_pattern_length</b> modifier sets a limit, in code units, to the +length of pattern that <b>pcre2_compile()</b> will accept. Breaching the limit +causes a compilation error. The default is the largest number a PCRE2_SIZE variable can hold (essentially unlimited). </P> <br><b> @@ -836,13 +836,13 @@ modifiers set options for the <b>regcomp()</b> function: ucp REG_UCP ) the POSIX standard utf REG_UTF8 ) </pre> -The <b>regerror_buffsize</b> modifier specifies a size for the error buffer that +The <b>regerror_buffsize</b> modifier specifies a size for the error buffer that is passed to <b>regerror()</b> in the event of a compilation error. For example: <pre> /abc/posix,regerror_buffsize=20 </pre> -This provides a means of testing the behaviour of <b>regerror()</b> when the -buffer is too small for the error message. If this modifier has not been set, a +This provides a means of testing the behaviour of <b>regerror()</b> when the +buffer is too small for the error message. If this modifier has not been set, a large buffer is used. </P> <P> @@ -892,14 +892,18 @@ are applied to every subject line that is processed with that pattern. They may not appear in <b>#pattern</b> commands. These modifiers do not affect the compilation process. <pre> - aftertext show text after match - allaftertext show text after captures - allcaptures show all captures - allusedtext show all consulted text - /g global global matching - mark show mark values - replace=<string> specify a replacement string - startchar show starting character when relevant + aftertext show text after match + allaftertext show text after captures + allcaptures show all captures + allusedtext show all consulted text + /g global global matching + mark show mark values + replace=<string> specify a replacement string + startchar show starting character when relevant + substitute_extended use PCRE2_SUBSTITUTE_EXTENDED + substitute_overflow_length use PCRE2_SUBSTITUTE_OVERFLOW_LENGTH + substitute_unknown_unset use PCRE2_SUBSTITUTE_UNKNOWN_UNSET + substitute_unset_empty use PCRE2_SUBSTITUTE_UNSET_EMPTY </pre> These modifiers may not appear in a <b>#pattern</b> command. If you want them as defaults, set them in a <b>#subject</b> command. @@ -964,33 +968,38 @@ information. Some of them may also be specified on a pattern line (see above), in which case they apply to every subject line that is matched against that pattern. <pre> - aftertext show text after match - allaftertext show text after captures - allcaptures show all captures - allusedtext show all consulted text (non-JIT only) - altglobal alternative global matching - callout_capture show captures at callout time - callout_data=<n> set a value to pass via callouts - callout_fail=<n>[:<m>] control callout failure - callout_none do not supply a callout function - copy=<number or name> copy captured substring - dfa use <b>pcre2_dfa_match()</b> - find_limits find match and recursion limits - get=<number or name> extract captured substring - getall extract all captured substrings - /g global global matching - jitstack=<n> set size of JIT stack - mark show mark values - match_limit=<n> set a match limit - memory show memory usage - null_context match with a NULL context - offset=<n> set starting offset - offset_limit=<n> set offset limit - ovector=<n> set size of output vector - recursion_limit=<n> set a recursion limit - replace=<string> specify a replacement string - startchar show startchar when relevant - zero_terminate pass the subject as zero-terminated + aftertext show text after match + allaftertext show text after captures + allcaptures show all captures + allusedtext show all consulted text (non-JIT only) + altglobal alternative global matching + callout_capture show captures at callout time + callout_data=<n> set a value to pass via callouts + callout_fail=<n>[:<m>] control callout failure + callout_none do not supply a callout function + copy=<number or name> copy captured substring + dfa use <b>pcre2_dfa_match()</b> + find_limits find match and recursion limits + get=<number or name> extract captured substring + getall extract all captured substrings + /g global global matching + jitstack=<n> set size of JIT stack + mark show mark values + match_limit=<n> set a match limit + memory show memory usage + null_context match with a NULL context + offset=<n> set starting offset + offset_limit=<n> set offset limit + ovector=<n> set size of output vector + recursion_limit=<n> set a recursion limit + replace=<string> specify a replacement string + startchar show startchar when relevant + startoffset=<n> same as offset=<n> + substitute_extedded use PCRE2_SUBSTITUTE_EXTENDED + substitute_overflow_length use PCRE2_SUBSTITUTE_OVERFLOW_LENGTH + substitute_unknown_unset use PCRE2_SUBSTITUTE_UNKNOWN_UNSET + substitute_unset_empty use PCRE2_SUBSTITUTE_UNSET_EMPTY + zero_terminate pass the subject as zero-terminated </pre> The effects of these modifiers are described in the following sections. </P> @@ -1129,19 +1138,34 @@ Testing the substitution function </b><br> <P> If the <b>replace</b> modifier is set, the <b>pcre2_substitute()</b> function is -called instead of one of the matching functions. Unlike subject strings, -<b>pcre2test</b> does not process replacement strings for escape sequences. In -UTF mode, a replacement string is checked to see if it is a valid UTF-8 string. -If so, it is correctly converted to a UTF string of the appropriate code unit -width. If it is not a valid UTF-8 string, the individual code units are copied -directly. This provides a means of passing an invalid UTF-8 string for testing -purposes. -</P> -<P> -If the <b>global</b> modifier is set, PCRE2_SUBSTITUTE_GLOBAL is passed to -<b>pcre2_substitute()</b>. After a successful substitution, the modified string -is output, preceded by the number of replacements. This may be zero if there -were no matches. Here is a simple example of a substitution test: +called instead of one of the matching functions. Note that replacement strings +cannot contain commas, because a comma signifies the end of a modifier. This is +not thought to be an issue in a test program. +</P> +<P> +Unlike subject strings, <b>pcre2test</b> does not process replacement strings +for escape sequences. In UTF mode, a replacement string is checked to see if it +is a valid UTF-8 string. If so, it is correctly converted to a UTF string of +the appropriate code unit width. If it is not a valid UTF-8 string, the +individual code units are copied directly. This provides a means of passing an +invalid UTF-8 string for testing purposes. +</P> +<P> +The following modifiers set options (in additional to the normal match options) +for <b>pcre2_substitute()</b>: +<pre> + global PCRE2_SUBSTITUTE_GLOBAL + substitute_extended PCRE2_SUBSTITUTE_EXTENDED + substitute_overflow_length PCRE2_SUBSTITUTE_OVERFLOW_LENGTH + substitute_unknown_unset PCRE2_SUBSTITUTE_UNKNOWN_UNSET + substitute_unset_empty PCRE2_SUBSTITUTE_UNSET_EMPTY + +</PRE> +</P> +<P> +After a successful substitution, the modified string is output, preceded by the +number of replacements. This may be zero if there were no matches. Here is a +simple example of a substitution test: <pre> /abc/replace=xxx =abc=abc= @@ -1149,12 +1173,12 @@ were no matches. Here is a simple example of a substitution test: =abc=abc=\=global 2: =xxx=xxx= </pre> -Subject and replacement strings should be kept relatively short for -substitution tests, as fixed-size buffers are used. To make it easy to test for -buffer overflow, if the replacement string starts with a number in square -brackets, that number is passed to <b>pcre2_substitute()</b> as the size of the -output buffer, with the replacement string starting at the next character. Here -is an example that tests the edge case: +Subject and replacement strings should be kept relatively short (fewer than 256 +characters) for substitution tests, as fixed-size buffers are used. To make it +easy to test for buffer overflow, if the replacement string starts with a +number in square brackets, that number is passed to <b>pcre2_substitute()</b> as +the size of the output buffer, with the replacement string starting at the next +character. Here is an example that tests the edge case: <pre> /abc/ 123abc123\=replace=[10]XYZ @@ -1162,6 +1186,19 @@ is an example that tests the edge case: 123abc123\=replace=[9]XYZ Failed: error -47: no more memory </pre> +The default action of <b>pcre2_substitute()</b> is to return +PCRE2_ERROR_NOMEMORY when the output buffer is too small. However, if the +PCRE2_SUBSTITUTE_OVERFLOW_LENGTH option is set (by using the +<b>substitute_overflow_length</b> modifier), <b>pcre2_substitute()</b> continues +to go through the motions of matching and substituting, in order to compute the +size of buffer that is required. When this happens, <b>pcre2test</b> shows the +required buffer length (which includes space for the trailing zero) as part of +the error message. For example: +<pre> + /abc/substitute_overflow_length + 123abc123\=replace=[9]XYZ + Failed: error -47: no more memory: 10 code units are needed +</pre> A replacement string is ignored with POSIX and DFA matching. Specifying partial matching provokes an error return ("bad option value") from <b>pcre2_substitute()</b>. @@ -1236,10 +1273,10 @@ matching starts. Its value is a number of code units, not characters. Setting an offset limit </b><br> <P> -The <b>offset_limit</b> modifier sets a limit for unanchored matches. If a match -cannot be found starting at or before this offset in the subject, a "no match" -return is given. The data value is a number of code units, not characters. When -this modifier is used, the <b>use_offset_limit</b> modifier must have been set +The <b>offset_limit</b> modifier sets a limit for unanchored matches. If a match +cannot be found starting at or before this offset in the subject, a "no match" +return is given. The data value is a number of code units, not characters. When +this modifier is used, the <b>use_offset_limit</b> modifier must have been set for the pattern; if not, an error is generated. </P> <br><b> @@ -1281,8 +1318,8 @@ Passing a NULL context Normally, <b>pcre2test</b> passes a context block to <b>pcre2_match()</b>, <b>pcre2_dfa_match()</b> or <b>pcre2_jit_match()</b>. If the <b>null_context</b> modifier is set, however, NULL is passed. This is for testing that the matching -functions behave correctly in this case (they use default values). This -modifier cannot be used with the <b>find_limits</b> modifier or when testing the +functions behave correctly in this case (they use default values). This +modifier cannot be used with the <b>find_limits</b> modifier or when testing the substitution function. </P> <br><a name="SEC12" href="#TOC1">THE ALTERNATIVE MATCHING FUNCTION</a><br> @@ -1623,7 +1660,7 @@ Cambridge, England. </P> <br><a name="SEC21" href="#TOC1">REVISION</a><br> <P> -Last updated: 05 November 2015 +Last updated: 12 December 2015 <br> Copyright © 1997-2015 University of Cambridge. <br> diff --git a/doc/html/pcre2unicode.html b/doc/html/pcre2unicode.html index c7d1dd2..7af55c3 100644 --- a/doc/html/pcre2unicode.html +++ b/doc/html/pcre2unicode.html @@ -127,8 +127,8 @@ as a byte-order mark (BOM). The PCRE2 functions do not handle this, expecting strings to be in host byte order. </P> <P> -A UTF string is checked before any other processing takes place. In the case of -<b>pcre2_match()</b> and <b>pcre2_dfa_match()</b> calls with a non-zero starting +A UTF string is checked before any other processing takes place. In the case of +<b>pcre2_match()</b> and <b>pcre2_dfa_match()</b> calls with a non-zero starting offset, the check is applied only to that part of the subject that could be inspected during matching, and there is a check that the starting offset points to the first code unit of a character or to the end of the subject. If there diff --git a/doc/pcre2.3 b/doc/pcre2.3 index eb45de4..9a84ce3 100644 --- a/doc/pcre2.3 +++ b/doc/pcre2.3 @@ -118,9 +118,9 @@ running redundant checks. .P The use of the \eC escape sequence in a UTF-8 or UTF-16 pattern can lead to problems, because it may leave the current matching point in the middle of a -multi-code-unit character. The PCRE2_NEVER_BACKSLASH_C option can be used by an +multi-code-unit character. The PCRE2_NEVER_BACKSLASH_C option can be used by an application to lock out the use of \eC, causing a compile-time error if it is -encountered. It is also possible to build PCRE2 with the use of \eC permanently +encountered. It is also possible to build PCRE2 with the use of \eC permanently disabled. .P Another way that performance can be hit is by running a pattern that has a very diff --git a/doc/pcre2.txt b/doc/pcre2.txt index cc8ca64..9df2d47 100644 --- a/doc/pcre2.txt +++ b/doc/pcre2.txt @@ -169,8 +169,8 @@ REVISION Last updated: 16 October 2015 Copyright (c) 1997-2015 University of Cambridge. ------------------------------------------------------------------------------ - - + + PCRE2API(3) Library Functions Manual PCRE2API(3) @@ -774,7 +774,7 @@ PCRE2 CONTEXTS A callout function The offset limit for matching an unanchored pattern - The limit for calling match() + The limit for calling match() (see below) The limit for calling match() recursively A match context is also required if you are using custom memory manage- @@ -824,69 +824,72 @@ PCRE2 CONTEXTS The offset limit facility can be used to track progress when searching large subject strings. See also the PCRE2_FIRSTLINE option, which - requires a match to start within the first line of the subject. + requires a match to start within the first line of the subject. If this + is set with an offset limit, a match must occur in the first line and + also within the offset limit. In other words, whichever limit comes + first is used. int pcre2_set_match_limit(pcre2_match_context *mcontext, uint32_t value); - The match_limit parameter provides a means of preventing PCRE2 from + The match_limit parameter provides a means of preventing PCRE2 from using up too many resources when processing 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- + 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, pcre2_match() 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 + Internally, pcre2_match() 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. This limit is not + can take place. For patterns that are not anchored, the count restarts + from zero for each position in the subject string. This limit is not relevant to pcre2_dfa_match(), which ignores it. - When pcre2_match() is called with a pattern that was successfully pro- + When pcre2_match() is called with a pattern that was successfully pro- cessed by pcre2_jit_compile(), the way in which 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 + 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 matching can continue. - The default value for the limit can be set when PCRE2 is built; the - default default is 10 million, which handles all but the most extreme - cases. If the limit is exceeded, pcre2_match() returns - PCRE2_ERROR_MATCHLIMIT. A value for the match limit may also be sup- + The default value for the limit can be set when PCRE2 is built; the + default default is 10 million, which handles all but the most extreme + cases. If the limit is exceeded, pcre2_match() returns + PCRE2_ERROR_MATCHLIMIT. A value for the match limit may also be sup- plied by an item at the start of a pattern of the form (*LIMIT_MATCH=ddd) - where ddd is a decimal number. However, such a setting is ignored - unless ddd is less than the limit set by the caller of pcre2_match() + where ddd is a decimal number. However, such a setting is ignored + unless ddd is less than the limit set by the caller of pcre2_match() or, if no such limit is set, less than the default. int pcre2_set_recursion_limit(pcre2_match_context *mcontext, uint32_t value); The recursion_limit parameter 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- + 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- sive. This limit is of use only if it is set smaller than match_limit. Limiting the recursion depth limits the amount of system stack that can - be used, or, when PCRE2 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 + be used, or, when PCRE2 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 or by the pcre2_dfa_match() function. - The default value for recursion_limit can be set when PCRE2 is built; - the default default is the same value as the default for match_limit. - If the limit is exceeded, pcre2_match() returns PCRE2_ERROR_RECURSION- - LIMIT. A value for the recursion limit may also be supplied by an item + The default value for recursion_limit can be set when PCRE2 is built; + the default default is the same value as the default for match_limit. + If the limit is exceeded, pcre2_match() returns PCRE2_ERROR_RECURSION- + LIMIT. A value for the recursion limit may also be supplied by an item at the start of a pattern of the form (*LIMIT_RECURSION=ddd) - where ddd is a decimal number. However, such a setting is ignored - unless ddd is less than the limit set by the caller of pcre2_match() + where ddd is a decimal number. However, such a setting is ignored + unless ddd is less than the limit set by the caller of pcre2_match() or, if no such limit is set, less than the default. int pcre2_set_recursion_memory_management( @@ -895,21 +898,21 @@ PCRE2 CONTEXTS void (*private_free)(void *, void *), void *memory_data); This function sets up two additional custom memory management functions - for use by pcre2_match() when PCRE2 is compiled to use the heap for + for use by pcre2_match() when PCRE2 is compiled to use the heap for remembering backtracking data, instead of recursive function calls that - use the system stack. There is a discussion about PCRE2's stack usage - in the pcre2stack documentation. See the pcre2build documentation for + use the system stack. There is a discussion about PCRE2's stack usage + in the pcre2stack documentation. See the pcre2build documentation for details of how to build PCRE2. - Using the heap for recursion is a non-standard way of building PCRE2, - for use in environments that have limited stacks. Because of the + Using the heap for recursion is a non-standard way of building PCRE2, + for use in environments that have limited stacks. Because of the greater use of memory management, pcre2_match() runs more slowly. Func- - tions that are different to the general custom memory functions are - provided so that special-purpose external code can be used for this - case, because the memory blocks are all the same size. The blocks are + tions that are different to the general custom memory functions are + provided so that special-purpose external code can be used for this + case, because the memory blocks are all the same size. The blocks are retained by pcre2_match() until it is about to exit so that they can be - re-used when possible during the match. In the absence of these func- - tions, the normal custom memory management functions are used, if sup- + re-used when possible during the match. In the absence of these func- + tions, the normal custom memory management functions are used, if sup- plied, otherwise the system functions. @@ -917,75 +920,75 @@ CHECKING BUILD-TIME OPTIONS int pcre2_config(uint32_t what, void *where); - The function pcre2_config() makes it possible for a PCRE2 client to - discover which optional features have been compiled into the PCRE2 - library. The pcre2build documentation has more details about these + The function pcre2_config() makes it possible for a PCRE2 client to + discover which optional features have been compiled into the PCRE2 + library. The pcre2build documentation has more details about these optional features. - The first argument for pcre2_config() specifies which information is - required. The second argument is a pointer to memory into which the - information is placed. If NULL is passed, the function returns the - amount of memory that is needed for the requested information. For - calls that return numerical values, the value is in bytes; when - requesting these values, where should point to appropriately aligned - memory. For calls that return strings, the required length is given in + The first argument for pcre2_config() specifies which information is + required. The second argument is a pointer to memory into which the + information is placed. If NULL is passed, the function returns the + amount of memory that is needed for the requested information. For + calls that return numerical values, the value is in bytes; when + requesting these values, where should point to appropriately aligned + memory. For calls that return strings, the required length is given in code units, not counting the terminating zero. - When requesting information, the returned value from pcre2_config() is - non-negative on success, or the negative error code PCRE2_ERROR_BADOP- - TION if the value in the first argument is not recognized. The follow- + When requesting information, the returned value from pcre2_config() is + non-negative on success, or the negative error code PCRE2_ERROR_BADOP- + TION if the value in the first argument is not recognized. The follow- ing information is available: PCRE2_CONFIG_BSR - The output is a uint32_t integer whose value indicates what character - sequences the \R escape sequence matches by default. A value of + The output is a uint32_t integer whose value indicates what character + sequences the \R escape sequence matches by default. A value of PCRE2_BSR_UNICODE means that \R matches any Unicode line ending - sequence; a value of PCRE2_BSR_ANYCRLF means that \R matches only CR, + sequence; a value of PCRE2_BSR_ANYCRLF means that \R matches only CR, LF, or CRLF. The default can be overridden when a pattern is compiled. PCRE2_CONFIG_JIT - The output is a uint32_t integer that is set to one if support for + The output is a uint32_t integer that is set to one if support for just-in-time compiling is available; otherwise it is set to zero. PCRE2_CONFIG_JITTARGET - The where argument should point to a buffer that is at least 48 code - units long. (The exact length required can be found by calling - pcre2_config() with where set to NULL.) The buffer is filled with a - string that contains the name of the architecture for which the JIT - compiler is configured, for example "x86 32bit (little endian + - unaligned)". If JIT support is not available, PCRE2_ERROR_BADOPTION is - returned, otherwise the number of code units used is returned. This is + The where argument should point to a buffer that is at least 48 code + units long. (The exact length required can be found by calling + pcre2_config() with where set to NULL.) The buffer is filled with a + string that contains the name of the architecture for which the JIT + compiler is configured, for example "x86 32bit (little endian + + unaligned)". If JIT support is not available, PCRE2_ERROR_BADOPTION is + returned, otherwise the number of code units used is returned. This is the length of the string, plus one unit for the terminating zero. PCRE2_CONFIG_LINKSIZE The output is a uint32_t integer that contains the number of bytes used - for internal linkage in compiled regular expressions. When PCRE2 is - configured, the value can be set to 2, 3, or 4, with the default being - 2. This is the value that is returned by pcre2_config(). However, when - the 16-bit library is compiled, a value of 3 is rounded up to 4, and - when the 32-bit library is compiled, internal linkages always use 4 + for internal linkage in compiled regular expressions. When PCRE2 is + configured, the value can be set to 2, 3, or 4, with the default being + 2. This is the value that is returned by pcre2_config(). However, when + the 16-bit library is compiled, a value of 3 is rounded up to 4, and + when the 32-bit library is compiled, internal linkages always use 4 bytes, so the configured value is not relevant. The default value of 2 for the 8-bit and 16-bit libraries is sufficient - for all but the most massive patterns, since it allows the size of the + for all but the most massive patterns, since it allows the size of the compiled pattern to be up to 64K code units. Larger values allow larger - regular expressions to be compiled by those two libraries, but at the + regular expressions to be compiled by those two libraries, but at the expense of slower matching. PCRE2_CONFIG_MATCHLIMIT - The output is a uint32_t integer that gives the default limit for the - number of internal matching function calls in a pcre2_match() execu- + The output is a uint32_t integer that gives the default limit for the + number of internal matching function calls in a pcre2_match() execu- tion. Further details are given with pcre2_match() below. PCRE2_CONFIG_NEWLINE - The output is a uint32_t integer whose value specifies the default - character sequence that is recognized as meaning "newline". The values + The output is a uint32_t integer whose value specifies the default + character sequence that is recognized as meaning "newline". The values are: PCRE2_NEWLINE_CR Carriage return (CR) @@ -994,56 +997,56 @@ CHECKING BUILD-TIME OPTIONS PCRE2_NEWLINE_ANY Any Unicode line ending PCRE2_NEWLINE_ANYCRLF Any of CR, LF, or CRLF - The default should normally correspond to the standard sequence for + The default should normally correspond to the standard sequence for your operating system. PCRE2_CONFIG_PARENSLIMIT - The output is a uint32_t integer that gives the maximum depth of nest- + The output is a uint32_t integer that gives the maximum depth of nest- ing 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 PCRE2 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 compilation stack usage, see + cap the amount of system stack used when a pattern is compiled. It is + specified when PCRE2 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 compilation stack usage, see pcre2_set_compile_recursion_guard(). PCRE2_CONFIG_RECURSIONLIMIT - The output is a uint32_t integer that gives the default limit for the - depth of recursion when calling the internal matching function in a - pcre2_match() execution. Further details are given with pcre2_match() + The output is a uint32_t integer that gives the default limit for the + depth of recursion when calling the internal matching function in a + pcre2_match() execution. Further details are given with pcre2_match() below. PCRE2_CONFIG_STACKRECURSE - The output is a uint32_t integer that is set to one if internal recur- - sion when running pcre2_match() is implemented by recursive function - calls that use the system stack to remember their state. This is the - usual way that PCRE2 is compiled. The output is zero if PCRE2 was com- - piled to use blocks of data on the heap instead of recursive function + The output is a uint32_t integer that is set to one if internal recur- + sion when running pcre2_match() is implemented by recursive function + calls that use the system stack to remember their state. This is the + usual way that PCRE2 is compiled. The output is zero if PCRE2 was com- + piled to use blocks of data on the heap instead of recursive function calls. PCRE2_CONFIG_UNICODE_VERSION - The where argument should point to a buffer that is at least 24 code - units long. (The exact length required can be found by calling - pcre2_config() with where set to NULL.) If PCRE2 has been compiled - without Unicode support, the buffer is filled with the text "Unicode - not supported". Otherwise, the Unicode version string (for example, - "8.0.0") is inserted. The number of code units used is returned. This + The where argument should point to a buffer that is at least 24 code + units long. (The exact length required can be found by calling + pcre2_config() with where set to NULL.) If PCRE2 has been compiled + without Unicode support, the buffer is filled with the text "Unicode + not supported". Otherwise, the Unicode version string (for example, + "8.0.0") is inserted. The number of code units used is returned. This is the length of the string plus one unit for the terminating zero. PCRE2_CONFIG_UNICODE - The output is a uint32_t integer that is set to one if Unicode support - is available; otherwise it is set to zero. Unicode support implies UTF + The output is a uint32_t integer that is set to one if Unicode support + is available; otherwise it is set to zero. Unicode support implies UTF support. PCRE2_CONFIG_VERSION - The where argument should point to a buffer that is at least 12 code - units long. (The exact length required can be found by calling - pcre2_config() with where set to NULL.) The buffer is filled with the + The where argument should point to a buffer that is at least 12 code + units long. (The exact length required can be found by calling + pcre2_config() with where set to NULL.) The buffer is filled with the PCRE2 version string, zero-terminated. The number of code units used is returned. This is the length of the string plus one unit for the termi- nating zero. @@ -1057,58 +1060,58 @@ COMPILING A PATTERN void pcre2_code_free(pcre2_code *code); - The pcre2_compile() function compiles a pattern into an internal form. - The pattern is defined by a pointer to a string of code units and a - length, If the pattern is zero-terminated, the length can be specified - as PCRE2_ZERO_TERMINATED. The function returns a pointer to a block of - memory that contains the compiled pattern and related data. The caller - must free the memory by calling pcre2_code_free() when it is no longer + The pcre2_compile() function compiles a pattern into an internal form. + The pattern is defined by a pointer to a string of code units and a + length, If the pattern is zero-terminated, the length can be specified + as PCRE2_ZERO_TERMINATED. The function returns a pointer to a block of + memory that contains the compiled pattern and related data. The caller + must free the memory by calling pcre2_code_free() when it is no longer needed. - NOTE: When one of the matching functions is called, pointers to the + NOTE: When one of the matching functions is called, pointers to the compiled pattern and the subject string are set in the match data block - so that they can be referenced by the extraction functions. After run- - ning a match, you must not free a compiled pattern (or a subject - string) until after all operations on the match data block have taken + so that they can be referenced by the extraction functions. After run- + ning a match, you must not free a compiled pattern (or a subject + string) until after all operations on the match data block have taken place. - If the compile context argument ccontext is NULL, memory for the com- - piled pattern is obtained by calling malloc(). Otherwise, it is - obtained from the same memory function that was used for the compile + If the compile context argument ccontext is NULL, memory for the com- + piled pattern is obtained by calling malloc(). Otherwise, it is + obtained from the same memory function that was used for the compile context. The options argument contains various bit settings that affect the com- - pilation. It should be zero if no options are required. The available - options are described below. Some of them (in particular, those that - are compatible with Perl, but some others as well) can also be set and - unset from within the pattern (see the detailed description in the + pilation. It should be zero if no options are required. The available + options are described below. Some of them (in particular, those that + are compatible with Perl, but some others as well) can also be set and + unset from within the pattern (see the detailed description in the pcre2pattern documentation). - For those options that can be different in different parts of the pat- - tern, the contents of the options argument specifies their settings at - the start of compilation. The PCRE2_ANCHORED and PCRE2_NO_UTF_CHECK + For those options that can be different in different parts of the pat- + tern, the contents of the options argument specifies their settings at + the start of compilation. The PCRE2_ANCHORED and PCRE2_NO_UTF_CHECK options can be set at the time of matching as well as at compile time. - Other, less frequently required compile-time parameters (for example, + Other, less frequently required compile-time parameters (for example, the newline setting) can be provided in a compile context (as described above). If errorcode or erroroffset is NULL, pcre2_compile() returns NULL imme- - diately. Otherwise, if compilation of a pattern fails, pcre2_compile() + diately. Otherwise, if compilation of a pattern fails, pcre2_compile() returns NULL, having set these variables to an error code and an offset - (number of code units) within the pattern, respectively. The - pcre2_get_error_message() function provides a textual message for each + (number of code units) within the pattern, respectively. The + pcre2_get_error_message() function provides a textual message for each error code. Compilation errors are positive numbers, but UTF formatting errors are negative numbers. For an invalid UTF-8 or UTF-16 string, the offset is that of the first code unit of the failing character. - Some errors are not detected until the whole pattern has been scanned; - in these cases, the offset passed back is the length of the pattern. - Note that the offset is in code units, not characters, even in a UTF + Some errors are not detected until the whole pattern has been scanned; + in these cases, the offset passed back is the length of the pattern. + Note that the offset is in code units, not characters, even in a UTF mode. It may sometimes point into the middle of a UTF-8 or UTF-16 char- acter. - This code fragment shows a typical straightforward call to pcre2_com- + This code fragment shows a typical straightforward call to pcre2_com- pile(): pcre2_code *re; @@ -1122,136 +1125,139 @@ COMPILING A PATTERN &erroffset, /* for error offset */ NULL); /* no compile context */ - The following names for option bits are defined in the pcre2.h header + The following names for option bits are defined in the pcre2.h header file: PCRE2_ANCHORED If this bit is set, the pattern is forced to be "anchored", that is, it - is constrained to match only at the first matching point in the string - that is being searched (the "subject string"). This effect can also be - achieved by appropriate constructs in the pattern itself, which is the + is constrained to match only at the first matching point in the string + that is being searched (the "subject string"). This effect can also be + achieved by appropriate constructs in the pattern itself, which is the only way to do it in Perl. PCRE2_ALLOW_EMPTY_CLASS - By default, for compatibility with Perl, a closing square bracket that - immediately follows an opening one is treated as a data character for - the class. When PCRE2_ALLOW_EMPTY_CLASS is set, it terminates the + By default, for compatibility with Perl, a closing square bracket that + immediately follows an opening one is treated as a data character for + the class. When PCRE2_ALLOW_EMPTY_CLASS is set, it terminates the class, which therefore contains no characters and so can never match. PCRE2_ALT_BSUX - This option request alternative handling of three escape sequences, - which makes PCRE2's behaviour more like ECMAscript (aka JavaScript). + This option request alternative handling of three escape sequences, + which makes PCRE2's behaviour more like ECMAscript (aka JavaScript). When it is set: (1) \U matches an upper case "U" character; by default \U causes a com- pile time error (Perl uses \U to upper case subsequent characters). (2) \u matches a lower case "u" character unless it is followed by four - hexadecimal digits, in which case the hexadecimal number defines the - code point to match. By default, \u causes a compile time error (Perl + hexadecimal digits, in which case the hexadecimal number defines the + code point to match. By default, \u causes a compile time error (Perl uses it to upper case the following character). - (3) \x matches a lower case "x" character unless it is followed by two - hexadecimal digits, in which case the hexadecimal number defines the - code point to match. By default, as in Perl, a hexadecimal number is + (3) \x matches a lower case "x" character unless it is followed by two + hexadecimal digits, in which case the hexadecimal number defines the + code point to match. By default, as in Perl, a hexadecimal number is always expected after \x, but it may have zero, one, or two digits (so, for example, \xz matches a binary zero character followed by z). PCRE2_ALT_CIRCUMFLEX In multiline mode (when PCRE2_MULTILINE is set), the circumflex - metacharacter matches at the start of the subject (unless PCRE2_NOTBOL - is set), and also after any internal newline. However, it does not + metacharacter matches at the start of the subject (unless PCRE2_NOTBOL + is set), and also after any internal newline. However, it does not match after a newline at the end of the subject, for compatibility with - Perl. If you want a multiline circumflex also to match after a termi- + Perl. If you want a multiline circumflex also to match after a termi- nating newline, you must set PCRE2_ALT_CIRCUMFLEX. PCRE2_ALT_VERBNAMES - By default, for compatibility with Perl, the name in any verb sequence - such as (*MARK:NAME) is any sequence of characters that does not - include a closing parenthesis. The name is not processed in any way, - and it is not possible to include a closing parenthesis in the name. - However, if the PCRE2_ALT_VERBNAMES option is set, normal backslash - processing is applied to verb names and only an unescaped closing - parenthesis terminates the name. A closing parenthesis can be included - in a name either as \) or between \Q and \E. If the PCRE2_EXTENDED + By default, for compatibility with Perl, the name in any verb sequence + such as (*MARK:NAME) is any sequence of characters that does not + include a closing parenthesis. The name is not processed in any way, + and it is not possible to include a closing parenthesis in the name. + However, if the PCRE2_ALT_VERBNAMES option is set, normal backslash + processing is applied to verb names and only an unescaped closing + parenthesis terminates the name. A closing parenthesis can be included + in a name either as \) or between \Q and \E. If the PCRE2_EXTENDED option is set, unescaped whitespace in verb names is skipped and #-com- ments are recognized, exactly as in the rest of the pattern. PCRE2_AUTO_CALLOUT - If this bit is set, pcre2_compile() automatically inserts callout + If this bit is set, pcre2_compile() automatically inserts callout items, all with number 255, before each pattern item. For discussion of the callout facility, see the pcre2callout documentation. PCRE2_CASELESS - If this bit is set, letters in the pattern match both upper and lower - case letters in the subject. It is equivalent to Perl's /i option, and + If this bit is set, letters in the pattern match both upper and lower + case letters in the subject. It is equivalent to Perl's /i option, and it can be changed within a pattern by a (?i) option setting. PCRE2_DOLLAR_ENDONLY - If this bit is set, a dollar metacharacter in the pattern matches only - at the end of the subject string. Without this option, a dollar also - matches immediately before a newline at the end of the string (but not - before any other newlines). The PCRE2_DOLLAR_ENDONLY option is ignored - if PCRE2_MULTILINE is set. There is no equivalent to this option in + If this bit is set, a dollar metacharacter in the pattern matches only + at the end of the subject string. Without this option, a dollar also + matches immediately before a newline at the end of the string (but not + before any other newlines). The PCRE2_DOLLAR_ENDONLY option is ignored + if PCRE2_MULTILINE is set. There is no equivalent to this option in Perl, and no way to set it within a pattern. PCRE2_DOTALL - If this bit is set, a dot metacharacter in the pattern matches any - character, including one that indicates a newline. However, it only + If this bit is set, a dot metacharacter in the pattern matches any + character, including one that indicates a newline. However, it only ever matches one character, even if newlines are coded as CRLF. Without this option, a dot does not match when the current position in the sub- - ject is at a newline. This option is equivalent to Perl's /s option, + ject is at a newline. This option is equivalent to Perl's /s option, and it can be changed within a pattern by a (?s) option setting. A neg- ative class such as [^a] always matches newline characters, independent of the setting of this option. PCRE2_DUPNAMES - If this bit is set, names used to identify capturing subpatterns need + If this bit is set, names used to identify capturing subpatterns need not be unique. This can be helpful for certain types of pattern when it - is known that only one instance of the named subpattern can ever be - matched. There are more details of named subpatterns below; see also + is known that only one instance of the named subpattern can ever be + matched. There are more details of named subpatterns below; see also the pcre2pattern documentation. PCRE2_EXTENDED - If this bit is set, most white space characters in the pattern are - totally ignored except when escaped or inside a character class. How- - ever, white space is not allowed within sequences such as (?> that + If this bit is set, most white space characters in the pattern are + totally ignored except when escaped or inside a character class. How- + ever, white space is not allowed within sequences such as (?> that introduce various parenthesized subpatterns, nor within numerical quan- - tifiers such as {1,3}. Ignorable white space is permitted between an - item and a following quantifier and between a quantifier and a follow- + tifiers such as {1,3}. Ignorable white space is permitted between an + item and a following quantifier and between a quantifier and a follow- ing + that indicates possessiveness. - PCRE2_EXTENDED also causes characters between an unescaped # outside a - character class and the next newline, inclusive, to be ignored, which + PCRE2_EXTENDED also causes characters between an unescaped # outside a + character class and the next newline, inclusive, to be ignored, which makes it possible to include comments inside complicated patterns. Note - that the end of this type of comment is a literal newline sequence in + that the end of this type of comment is a literal newline sequence in the pattern; escape sequences that happen to represent a newline do not - count. PCRE2_EXTENDED is equivalent to Perl's /x option, and it can be + count. PCRE2_EXTENDED is equivalent to Perl's /x option, and it can be changed within a pattern by a (?x) option setting. Which characters are interpreted as newlines can be specified by a set- - ting in the compile context that is passed to pcre2_compile() or by a - special sequence at the start of the pattern, as described in the sec- - tion entitled "Newline conventions" in the pcre2pattern documentation. + ting in the compile context that is passed to pcre2_compile() or by a + special sequence at the start of the pattern, as described in the sec- + tion entitled "Newline conventions" in the pcre2pattern documentation. A default is defined when PCRE2 is built. PCRE2_FIRSTLINE - If this option is set, an unanchored pattern is required to match - before or at the first newline in the subject string, though the - matched text may continue over the newline. See also PCRE2_USE_OFF- - SET_LIMIT, which provides a more general limiting facility. + If this option is set, an unanchored pattern is required to match + before or at the first newline in the subject string, though the + matched text may continue over the newline. See also PCRE2_USE_OFF- + SET_LIMIT, which provides a more general limiting facility. If + PCRE2_FIRSTLINE is set with an offset limit, a match must occur in the + first line and also within the offset limit. In other words, whichever + limit comes first is used. PCRE2_MATCH_UNSET_BACKREF @@ -1590,11 +1596,9 @@ INFORMATION ABOUT A COMPILED PATTERN to a uint32_t variable. PCRE2_INFO_ARGOPTIONS returns exactly the options that were passed to pcre2_compile(), whereas PCRE2_INFO_ALLOP- TIONS returns the compile options as modified by any top-level option - settings at the start of the pattern itself. In other words, they are - the options that will be in force when matching starts. For example, if - the pattern /(?im)abc(?-i)d/ is compiled with the PCRE2_EXTENDED - option, the result is PCRE2_CASELESS, PCRE2_MULTILINE, and - PCRE2_EXTENDED. + settings such as (*UTF) at the start of the pattern itself. For exam- + ple, if the pattern /(*UTF)abc/ is compiled with the PCRE2_EXTENDED + option, the result is PCRE2_EXTENDED and PCRE2_UTF. A pattern compiled without PCRE2_ANCHORED is automatically anchored by PCRE2 if the first significant item in every top-level branch is one of @@ -1638,20 +1642,30 @@ INFORMATION ABOUT A COMPILED PATTERN PCRE2_INFO_CAPTURECOUNT - Return the number of capturing subpatterns in the pattern. The third - argument should point to an uint32_t variable. + Return the highest capturing subpattern number in the pattern. In pat- + terns where (?| is not used, this is also the total number of capturing + subpatterns. The third argument should point to an uint32_t variable. + + PCRE2_INFO_FIRSTBITMAP + + In the absence of a single first code unit for a non-anchored pattern, + pcre2_compile() may construct a 256-bit table that defines a fixed set + of values for the first code unit in any match. For example, a pattern + that starts with [abc] results in a table with three bits set. When + code unit values greater than 255 are supported, the flag bit for 255 + means "any code unit of value 255 or above". If such a table was con- + structed, a pointer to it is returned. Otherwise NULL is returned. The + third argument should point to an const uint8_t * variable. PCRE2_INFO_FIRSTCODETYPE Return information about the first code unit of any matched string, for a non-anchored pattern. The third argument should point to an uint32_t - 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 PCRE2_INFO_FIRSTCODEUNIT. If there is no - fixed first value, but it is known that a match can occur only at the - start of the subject or following a newline in the subject, 2 is + 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 charac- + ter value can be retrieved using PCRE2_INFO_FIRSTCODEUNIT. If there is + no fixed first value, but it is known that a match can occur only at + the start of the subject or following a newline in the subject, 2 is returned. Otherwise, and for anchored patterns, 0 is returned. PCRE2_INFO_FIRSTCODEUNIT @@ -1664,16 +1678,10 @@ INFORMATION ABOUT A COMPILED PATTERN value can be up to 0x10ffff, and up to 0xffffffff when not using UTF-32 mode. - PCRE2_INFO_FIRSTBITMAP + PCRE2_INFO_HASBACKSLASHC - In the absence of a single first code unit for a non-anchored pattern, - pcre2_compile() may construct a 256-bit table that defines a fixed set - of values for the first code unit in any match. For example, a pattern - that starts with [abc] results in a table with three bits set. When - code unit values greater than 255 are supported, the flag bit for 255 - means "any code unit of value 255 or above". If such a table was con- - structed, a pointer to it is returned. Otherwise NULL is returned. The - third argument should point to an const uint8_t * variable. + Return 1 if the pattern contains any instances of \C, otherwise 0. The + third argument should point to an uint32_t variable. PCRE2_INFO_HASCRORLF @@ -1701,24 +1709,26 @@ INFORMATION ABOUT A COMPILED PATTERN any matched string, other than at its start. The third argument should point to an uint32_t variable. If there is no such value, 0 is returned. When 1 is returned, the code unit value itself can be - retrieved using PCRE2_INFO_LASTCODEUNIT. - - 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 is 1 (with "z" returned from - PCRE2_INFO_LASTCODEUNIT), but for /^a\dz\d/ the returned value is 0. + retrieved using PCRE2_INFO_LASTCODEUNIT. For anchored patterns, a last + literal value is recorded only if it follows something of variable + length. For example, for the pattern /^a\d+z\d+/ the returned value is + 1 (with "z" returned from PCRE2_INFO_LASTCODEUNIT), but for /^a\dz\d/ + the returned value is 0. PCRE2_INFO_LASTCODEUNIT - 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 third 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 third argument should point to an uint32_t variable. If there is no such value, 0 is returned. PCRE2_INFO_MATCHEMPTY - Return 1 if the pattern can match an empty string, otherwise 0. The - third argument should point to an uint32_t variable. + Return 1 if the pattern might match an empty string, otherwise 0. The + third argument should point to an uint32_t variable. When a pattern + contains recursive subroutine calls it is not always possible to deter- + mine whether or not it can match an empty string. PCRE2 takes a cau- + tious approach and returns 1 in such cases. PCRE2_INFO_MATCHLIMIT @@ -2142,32 +2152,35 @@ NEWLINE HANDLING WHEN MATCHING When PCRE2 is built, a default newline convention is set; this is usu- ally the standard convention for the operating system. The default can - be overridden in a compile context. During matching, the newline - choice affects the behaviour of the dot, circumflex, and dollar - metacharacters. It may also alter the way the match starting position - is advanced after a match failure for an unanchored pattern. + be overridden in a compile context by calling pcre2_set_newline(). It + can also be overridden by starting a pattern string with, for example, + (*CRLF), as described in the section on newline conventions in the + pcre2pattern page. During matching, the newline choice affects the be- + haviour of the dot, circumflex, and dollar metacharacters. It may also + alter the way the match starting position is advanced after a match + failure for an unanchored pattern. When PCRE2_NEWLINE_CRLF, PCRE2_NEWLINE_ANYCRLF, or PCRE2_NEWLINE_ANY is - set as the newline convention, and a match attempt for an unanchored + set as the newline convention, and a match attempt for an unanchored pattern fails when the current starting 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 + 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 PCRE2_DOTALL + expected. For example, if the pattern is .+A (and the PCRE2_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 in the pattern, or one of the \r or \n escape - sequences. Implicit matches such as [^X] do not count, nor does \s, + those characters in the pattern, or one of the \r or \n escape + sequences. Implicit matches such as [^X] do not count, nor does \s, even though it 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. @@ -2178,24 +2191,25 @@ HOW PCRE2_MATCH() RETURNS A STRING AND CAPTURED SUBSTRINGS PCRE2_SIZE *pcre2_get_ovector_pointer(pcre2_match_data *match_data); - In general, a pattern matches a certain portion of the subject, and in - addition, further substrings from the subject may be picked out by - parenthesized parts of the pattern. Following the usage in Jeffrey - Friedl's book, this is called "capturing" in what follows, and the - phrase "capturing subpattern" or "capturing group" is used for a frag- - ment of a pattern that picks out a substring. PCRE2 supports several + In general, a pattern matches a certain portion of the subject, and in + addition, further substrings from the subject may be picked out by + parenthesized parts of the pattern. Following the usage in Jeffrey + Friedl's book, this is called "capturing" in what follows, and the + phrase "capturing subpattern" or "capturing group" is used for a frag- + ment of a pattern that picks out a substring. PCRE2 supports several other kinds of parenthesized subpattern that do not cause substrings to - be captured. The pcre2_pattern_info() function can be used to find out + be captured. The pcre2_pattern_info() function can be used to find out how many capturing subpatterns there are in a compiled pattern. - A successful match returns the overall matched string and any captured - substrings to the caller via a vector of PCRE2_SIZE values. This is - called the ovector, and is contained within the match data block. You - can obtain direct access to the ovector by calling pcre2_get_ovec- - tor_pointer() to find its address, and pcre2_get_ovector_count() to - find the number of pairs of values it contains. Alternatively, you can - use the auxiliary functions for accessing captured substrings by number - or by name (see below). + You can use auxiliary functions for accessing captured substrings by + number or by name, as described in sections below. + + Alternatively, you can make direct use of the vector of PCRE2_SIZE val- + ues, called the ovector, which contains the offsets of captured + strings. It is part of the match data block. The function + pcre2_get_ovector_pointer() returns the address of the ovector, and + pcre2_get_ovector_count() returns the number of pairs of values it con- + tains. Within the ovector, the first in each pair of values is set to the off- set of the first code unit of a substring, and the second is set to the @@ -2274,40 +2288,45 @@ OTHER INFORMATION ABOUT A MATCH failure to match (PCRE2_ERROR_NOMATCH), a (*MARK) name may be avail- able, and pcre2_get_mark() can be called. It returns a pointer to the zero-terminated name, which is within the compiled pattern. Otherwise - NULL is returned. After a successful match, the (*MARK) name that is - returned is the last one encountered on the matching path through the - pattern. After a "no match" or a partial match, the last encountered - (*MARK) name is returned. For example, consider this pattern: + NULL is returned. The length of the (*MARK) name (excluding the termi- + nating zero) is stored in the code unit that preceeds the name. You + should use this instead of relying on the terminating zero if the + (*MARK) name might contain a binary zero. + + After a successful match, the (*MARK) name that is returned is the last + one encountered on the matching path through the pattern. After a "no + match" or a partial match, the last encountered (*MARK) name is + returned. For example, consider this pattern: ^(*MARK:A)((*MARK:B)a|b)c - When it matches "bc", the returned mark is A. The B mark is "seen" in - the first branch of the group, but it is not on the matching path. On - the other hand, when this pattern fails to match "bx", the returned + When it matches "bc", the returned mark is A. The B mark is "seen" in + the first branch of the group, but it is not on the matching path. On + the other hand, when this pattern fails to match "bx", the returned mark is B. - After a successful match, a partial match, or one of the invalid UTF - errors (for example, PCRE2_ERROR_UTF8_ERR5), pcre2_get_startchar() can + After a successful match, a partial match, or one of the invalid UTF + errors (for example, PCRE2_ERROR_UTF8_ERR5), pcre2_get_startchar() can be called. After a successful or partial match it returns the code unit - offset of the character at which the match started. For a non-partial - match, this can be different to the value of ovector[0] if the pattern - contains the \K escape sequence. After a partial match, however, this - value is always the same as ovector[0] because \K does not affect the + offset of the character at which the match started. For a non-partial + match, this can be different to the value of ovector[0] if the pattern + contains the \K escape sequence. After a partial match, however, this + value is always the same as ovector[0] because \K does not affect the result of a partial match. - After a UTF check failure, pcre2_get_startchar() can be used to obtain + After a UTF check failure, pcre2_get_startchar() can be used to obtain the code unit offset of the invalid UTF character. Details are given in the pcre2unicode page. ERROR RETURNS FROM pcre2_match() - If pcre2_match() fails, it returns a negative number. This can be con- - verted to a text string by calling pcre2_get_error_message(). Negative - error codes are also returned by other functions, and are documented + If pcre2_match() fails, it returns a negative number. This can be con- + verted to a text string by calling pcre2_get_error_message(). Negative + error codes are also returned by other functions, and are documented with them. The codes are given names in the header file. If UTF check- ing is in force and an invalid UTF subject string is detected, one of a - number of UTF-specific negative error codes is returned. Details are + number of UTF-specific negative error codes is returned. Details are given in the pcre2unicode page. The following are the other errors that may be returned by pcre2_match(): @@ -2317,19 +2336,19 @@ ERROR RETURNS FROM pcre2_match() PCRE2_ERROR_PARTIAL - 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 pcre2partial documentation for details of partial matching. PCRE2_ERROR_BADMAGIC PCRE2 stores a 4-byte "magic number" at the start of the compiled code, - to catch the case when it is passed a junk pointer. This is the error + to catch the case when it is passed a junk pointer. This is the error that is returned when the magic number is not present. PCRE2_ERROR_BADMODE - This error is given when a pattern that was compiled by the 8-bit - library is passed to a 16-bit or 32-bit library function, or vice + This error is given when a pattern that was compiled by the 8-bit + library is passed to a 16-bit or 32-bit library function, or vice versa. PCRE2_ERROR_BADOFFSET @@ -2343,35 +2362,35 @@ ERROR RETURNS FROM pcre2_match() PCRE2_ERROR_BADUTFOFFSET The UTF code unit sequence that was passed as a subject was checked and - found to be valid (the PCRE2_NO_UTF_CHECK option was not set), but the - value of startoffset did not point to the beginning of a UTF character + found to be valid (the PCRE2_NO_UTF_CHECK option was not set), but the + value of startoffset did not point to the beginning of a UTF character or the end of the subject. PCRE2_ERROR_CALLOUT - This error is never generated by pcre2_match() itself. It is provided - for use by callout functions that want to cause pcre2_match() or - pcre2_callout_enumerate() to return a distinctive error code. See the + This error is never generated by pcre2_match() itself. It is provided + for use by callout functions that want to cause pcre2_match() or + pcre2_callout_enumerate() to return a distinctive error code. See the pcre2callout documentation for details. PCRE2_ERROR_INTERNAL - 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 PCRE2 or by overwriting of the compiled pattern. PCRE2_ERROR_JIT_BADOPTION - This error is returned when a pattern that was successfully studied - using JIT 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 + This error is returned when a pattern that was successfully studied + using JIT 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 pcre2jit documentation for more details. PCRE2_ERROR_JIT_STACKLIMIT - This error is returned when a pattern that was successfully studied - using JIT is being matched, but the memory available for the just-in- - time processing stack is not large enough. See the pcre2jit documenta- + This error is returned when a pattern that was successfully studied + using JIT is being matched, but the memory available for the just-in- + time processing stack is not large enough. See the pcre2jit documenta- tion for more details. PCRE2_ERROR_MATCHLIMIT @@ -2380,10 +2399,10 @@ ERROR RETURNS FROM pcre2_match() PCRE2_ERROR_NOMEMORY - If a pattern contains back references, but the ovector is not big - enough to remember the referenced substrings, PCRE2 gets a block of + If a pattern contains back references, but the ovector is not big + enough to remember the referenced substrings, PCRE2 gets a block of memory at the start of matching to use for this purpose. There are some - other special cases where extra memory is needed during matching. This + other special cases where extra memory is needed during matching. This error is given when memory cannot be obtained. PCRE2_ERROR_NULL @@ -2392,12 +2411,12 @@ ERROR RETURNS FROM pcre2_match() PCRE2_ERROR_RECURSELOOP - This error is returned when pcre2_match() detects a recursion loop - within the pattern. Specifically, it means that either the whole pat- + This error is returned when pcre2_match() detects a recursion loop + within the pattern. Specifically, it means that either the whole pat- tern 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 com- - plicated cases, in particular mutual recursions between two different + the same position in the subject string. Some simple patterns that + might do this are detected and faulted at compile time, but more com- + plicated cases, in particular mutual recursions between two different subpatterns, cannot be detected until matching is attempted. PCRE2_ERROR_RECURSIONLIMIT @@ -2420,39 +2439,39 @@ EXTRACTING CAPTURED SUBSTRINGS BY NUMBER void pcre2_substring_free(PCRE2_UCHAR *buffer); - Captured substrings can be accessed directly by using the ovector as + Captured substrings can be accessed directly by using the ovector as described above. For convenience, auxiliary functions are provided for - extracting captured substrings as new, separate, zero-terminated + extracting captured substrings as new, separate, zero-terminated strings. 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 + and has a further zero added on the end, but the result is not, of course, a C string. The functions in this section identify substrings by number. The number zero refers to the entire matched substring, with higher numbers refer- - ring to substrings captured by parenthesized groups. After a partial - match, only substring zero is available. An attempt to extract any - other substring gives the error PCRE2_ERROR_PARTIAL. The next section + ring to substrings captured by parenthesized groups. After a partial + match, only substring zero is available. An attempt to extract any + other substring gives the error PCRE2_ERROR_PARTIAL. The next section describes similar functions for extracting captured substrings by name. - If a pattern uses the \K escape sequence within a positive assertion, + If a pattern uses the \K escape sequence within a positive assertion, the reported start of a successful match can be greater than the end of - the match. For example, if the pattern (?=ab\K) is matched against - "ab", the start and end offset values for the match are 2 and 0. In - this situation, calling these functions with a zero substring number + the match. For example, if the pattern (?=ab\K) is matched against + "ab", the start and end offset values for the match are 2 and 0. In + this situation, calling these functions with a zero substring number extracts a zero-length empty string. - You can find the length in code units of a captured substring without - extracting it by calling pcre2_substring_length_bynumber(). The first - argument is a pointer to the match data block, the second is the group - number, and the third is a pointer to a variable into which the length - is placed. If you just want to know whether or not the substring has + You can find the length in code units of a captured substring without + extracting it by calling pcre2_substring_length_bynumber(). The first + argument is a pointer to the match data block, the second is the group + number, and the third is a pointer to a variable into which the length + is placed. If you just want to know whether or not the substring has been captured, you can pass the third argument as NULL. - The pcre2_substring_copy_bynumber() function copies a captured sub- - string into a supplied buffer, whereas pcre2_substring_get_bynumber() - copies it into new memory, obtained using the same memory allocation - function that was used for the match data block. The first two argu- - ments of these functions are a pointer to the match data block and a + The pcre2_substring_copy_bynumber() function copies a captured sub- + string into a supplied buffer, whereas pcre2_substring_get_bynumber() + copies it into new memory, obtained using the same memory allocation + function that was used for the match data block. The first two argu- + ments of these functions are a pointer to the match data block and a capturing group number. The final arguments of pcre2_substring_copy_bynumber() are a pointer to @@ -2461,25 +2480,25 @@ EXTRACTING CAPTURED SUBSTRINGS BY NUMBER for the extracted substring, excluding the terminating zero. For pcre2_substring_get_bynumber() the third and fourth arguments point - to variables that are updated with a pointer to the new memory and the - number of code units that comprise the substring, again excluding the - terminating zero. When the substring is no longer needed, the memory + to variables that are updated with a pointer to the new memory and the + number of code units that comprise the substring, again excluding the + terminating zero. When the substring is no longer needed, the memory should be freed by calling pcre2_substring_free(). - The return value from all these functions is zero for success, or a - negative error code. If the pattern match failed, the match failure - code is returned. If a substring number greater than zero is used - after a partial match, PCRE2_ERROR_PARTIAL is returned. Other possible + The return value from all these functions is zero for success, or a + negative error code. If the pattern match failed, the match failure + code is returned. If a substring number greater than zero is used + after a partial match, PCRE2_ERROR_PARTIAL is returned. Other possible error codes are: PCRE2_ERROR_NOMEMORY - The buffer was too small for pcre2_substring_copy_bynumber(), or the + The buffer was too small for pcre2_substring_copy_bynumber(), or the attempt to get memory failed for pcre2_substring_get_bynumber(). PCRE2_ERROR_NOSUBSTRING - There is no substring with that number in the pattern, that is, the + There is no substring with that number in the pattern, that is, the number is greater than the number of capturing parentheses. PCRE2_ERROR_UNAVAILABLE @@ -2490,8 +2509,8 @@ EXTRACTING CAPTURED SUBSTRINGS BY NUMBER PCRE2_ERROR_UNSET - The substring did not participate in the match. For example, if the - pattern is (abc)|(def) and the subject is "def", and the ovector con- + The substring did not participate in the match. For example, if the + pattern is (abc)|(def) and the subject is "def", and the ovector con- tains at least two capturing slots, substring number 1 is unset. @@ -2502,32 +2521,32 @@ EXTRACTING A LIST OF ALL CAPTURED SUBSTRINGS void pcre2_substring_list_free(PCRE2_SPTR *list); - The pcre2_substring_list_get() function extracts all available sub- - strings and builds a list of pointers to them. It also (optionally) - builds a second list that contains their lengths (in code units), + The pcre2_substring_list_get() function extracts all available sub- + strings and builds a list of pointers to them. It also (optionally) + builds a second list that contains their lengths (in code units), excluding a terminating zero that is added to each of them. All this is done in a single block of memory that is obtained using the same memory allocation function that was used to get the match data block. - This function must be called only after a successful match. If called + This function must be called only after a successful match. If called after a partial match, the error code PCRE2_ERROR_PARTIAL is returned. - The address of the memory block is returned via listptr, which is also + 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 address of the list of lengths is returned via - lengthsptr. If your strings do not contain binary zeros and you do not + by a NULL pointer. The address of the list of lengths is returned via + lengthsptr. If your strings do not contain binary zeros and you do not therefore need the lengths, you may supply NULL as the lengthsptr argu- - ment to disable the creation of a list of lengths. The yield of the - function is zero if all went well, or PCRE2_ERROR_NOMEMORY if the mem- - ory block could not be obtained. When the list is no longer needed, it + ment to disable the creation of a list of lengths. The yield of the + function is zero if all went well, or PCRE2_ERROR_NOMEMORY if the mem- + ory block could not be obtained. When the list is no longer needed, it should be freed by calling pcre2_substring_list_free(). If this function encounters 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, it returns an empty string. - This can be distinguished from a genuine zero-length substring by + when capturing subpattern number n+1 matches some part of the subject, + but subpattern n has not been used at all, it returns an empty string. + This can be distinguished from a genuine zero-length substring by inspecting the appropriate offset in the ovector, which contain - PCRE2_UNSET for unset substrings, or by calling pcre2_sub- + PCRE2_UNSET for unset substrings, or by calling pcre2_sub- string_length_bynumber(). @@ -2547,39 +2566,39 @@ EXTRACTING CAPTURED SUBSTRINGS BY NAME void pcre2_substring_free(PCRE2_UCHAR *buffer); - 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+)... the number of the subpattern called "xxx" is 2. If the name is known to - be unique (PCRE2_DUPNAMES was not set), you can find the number from + be unique (PCRE2_DUPNAMES was not set), you can find the number from the name by calling pcre2_substring_number_from_name(). The first argu- - ment is the compiled pattern, and the second is the name. The yield of + ment is the compiled pattern, and the second is the name. The yield of the function is the subpattern number, PCRE2_ERROR_NOSUBSTRING if there - is no subpattern of that name, or PCRE2_ERROR_NOUNIQUESUBSTRING if - there is more than one subpattern of that name. Given the number, you - can extract the substring directly, or use one of the functions + is no subpattern of that name, or PCRE2_ERROR_NOUNIQUESUBSTRING if + there is more than one subpattern of that name. Given the number, you + can extract the substring directly, or use one of the functions described above. - For convenience, there are also "byname" functions that correspond to - the "bynumber" functions, the only difference being that the second - argument is a name instead of a number. If PCRE2_DUPNAMES is set and + For convenience, there are also "byname" functions that correspond to + the "bynumber" functions, the only difference being that the second + argument is a name instead of a number. If PCRE2_DUPNAMES is set and there are duplicate names, these functions scan all the groups with the given name, and return the first named string that is set. - If there are no groups with the given name, PCRE2_ERROR_NOSUBSTRING is - returned. If all groups with the name have numbers that are greater - than the number of slots in the ovector, PCRE2_ERROR_UNAVAILABLE is - returned. If there is at least one group with a slot in the ovector, + If there are no groups with the given name, PCRE2_ERROR_NOSUBSTRING is + returned. If all groups with the name have numbers that are greater + than the number of slots in the ovector, PCRE2_ERROR_UNAVAILABLE is + returned. If there is at least one group with a slot in the ovector, but no group is found to be set, PCRE2_ERROR_UNSET is returned. 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 pcre2pattern 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 pcre2pattern 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. @@ -2592,44 +2611,52 @@ CREATING A NEW STRING WITH SUBSTITUTIONS PCRE2_SIZE rlength, PCRE2_UCHAR *outputbufferP, PCRE2_SIZE *outlengthptr); - This function calls pcre2_match() and then makes a copy of the subject - string in outputbuffer, replacing the part that was matched with the - replacement string, whose length is supplied in rlength. This can be + This function calls pcre2_match() and then makes a copy of the subject + string in outputbuffer, replacing the part that was matched with the + replacement string, whose length is supplied in rlength. This can be given as PCRE2_ZERO_TERMINATED for a zero-terminated string. Matches in - which a \K item in a lookahead in the pattern causes the match to end + which a \K item in a lookahead in the pattern causes the match to end before it starts are not supported, and give rise to an error return. - The first seven arguments of pcre2_substitute() are the same as for + The first seven arguments of pcre2_substitute() are the same as for pcre2_match(), except that the partial matching options are not permit- - ted, and match_data may be passed as NULL, in which case a match data - block is obtained and freed within this function, using memory manage- - ment functions from the match context, if provided, or else those that + ted, and match_data may be passed as NULL, in which case a match data + block is obtained and freed within this function, using memory manage- + ment functions from the match context, if provided, or else those that were used to allocate memory for the compiled code. - The outlengthptr argument must point to a variable that contains the - length, in code units, of the output buffer. If the function is suc- - cessful, the value is updated to contain the length of the new string, - excluding the trailing zero that is automatically added. If the func- - tion is not successful, the value is set to PCRE2_UNSET for general - errors (such as output buffer too small). For syntax errors in the - replacement string, the value is set to the offset in the replacement - string where the error was detected. - - In the replacement string, which is interpreted as a UTF string in UTF - mode, and is checked for UTF validity unless the PCRE2_NO_UTF_CHECK + The outlengthptr argument must point to a variable that contains the + length, in code units, of the output buffer. If the function is suc- + cessful, the value is updated to contain the length of the new string, + excluding the trailing zero that is automatically added. + + If the function is not successful, the value set via outlengthptr + depends on the type of error. For syntax errors in the replacement + string, the value is the offset in the replacement string where the + error was detected. For other errors, the value is PCRE2_UNSET by + default. This includes the case of the output buffer being too small, + unless PCRE2_SUBSTITUTE_OVERFLOW_LENGTH is set (see below), in which + case the value is the minimum length needed, including space for the + trailing zero. Note that in order to compute the required length, + pcre2_substitute() has to simulate all the matching and copying, + instead of giving an error return as soon as the buffer overflows. Note + also that the length is in code units, not bytes. + + In the replacement string, which is interpreted as a UTF string in UTF + mode, and is checked for UTF validity unless the PCRE2_NO_UTF_CHECK option is set, a dollar character is an escape character that can spec- - ify the insertion of characters from capturing groups or (*MARK) items + ify the insertion of characters from capturing groups or (*MARK) items in the pattern. The following forms are always recognized: $$ insert a dollar character $<n> or ${<n>} insert the contents of group <n> $*MARK or ${*MARK} insert the name of the last (*MARK) encountered - Either a group number or a group name can be given for <n>. Curly - brackets are required only if the following character would be inter- + Either a group number or a group name can be given for <n>. Curly + brackets are required only if the following character would be inter- preted as part of the number or name. The number may be zero to include - the entire matched string. For example, if the pattern a(b)c is - matched with "=abc=" and the replacement string "+$1$0$1+", the result + the entire matched string. For example, if the pattern a(b)c is + matched with "=abc=" and the replacement string "+$1$0$1+", the result is "=+babcb+=". The facility for inserting a (*MARK) name can be used to perform simple @@ -2639,16 +2666,51 @@ CREATING A NEW STRING WITH SUBSTITUTIONS apple lemon 2: pear orange - There is an additional option, PCRE2_SUBSTITUTE_GLOBAL, which causes - the function to iterate over the subject string, replacing every match- - ing substring. If this is not set, only the first matching substring is - replaced. + As well as the usual options for pcre2_match(), a number of additional + options can be set in the options argument. + + PCRE2_SUBSTITUTE_GLOBAL causes the function to iterate over the subject + string, replacing every matching substring. If this is not set, only + the first matching substring is replaced. If any matched substring has + zero length, after the substitution has happened, an attempt to find a + non-empty match at the same position is performed. If this is not suc- + cessful, the current position is advanced by one character except when + CRLF is a valid newline sequence and the next two characters are CR, + LF. In this case, the current position is advanced by two characters. + + PCRE2_SUBSTITUTE_OVERFLOW_LENGTH changes what happens when the output + buffer is too small. The default action is to return PCRE2_ERROR_NOMEM- + ORY immediately. If this option is set, however, pcre2_substitute() + continues to go through the motions of matching and substituting (with- + out, of course, writing anything) in order to compute the size of buf- + fer that is needed. This value is passed back via the outlengthptr + variable, with the result of the function still being + PCRE2_ERROR_NOMEMORY. + + Passing a buffer size of zero is a permitted way of finding out how + much memory is needed for given substitution. However, this does mean + that the entire operation is carried out twice. Depending on the appli- + cation, it may be more efficient to allocate a large buffer and free + the excess afterwards, instead of using PCRE2_SUBSTITUTE_OVER- + FLOW_LENGTH. + + PCRE2_SUBSTITUTE_UNKNOWN_UNSET causes references to capturing groups + that do not appear in the pattern to be treated as unset groups. This + option should be used with care, because it means that a typo in a + group name or number no longer causes the PCRE2_ERROR_NOSUBSTRING + error. + + PCRE2_SUBSTITUTE_UNSET_EMPTY causes unset capturing groups (including + unknown groups when PCRE2_SUBSTITUTE_UNKNOWN_UNSET is set) to be + treated as empty strings when inserted as described above. If this + option is not set, an attempt to insert an unset group causes the + PCRE2_ERROR_UNSET error. This option does not influence the extended + substitution syntax described below. - A second additional option, PCRE2_SUBSTITUTE_EXTENDED, causes extra - processing to be applied to the replacement string. Without this - option, only the dollar character is special, and only the group inser- - tion forms listed above are valid. When PCRE2_SUBSTITUTE_EXTENDED is - set, two things change: + PCRE2_SUBSTITUTE_EXTENDED causes extra processing to be applied to the + replacement string. Without this option, only the dollar character is + special, and only the group insertion forms listed above are valid. + When PCRE2_SUBSTITUTE_EXTENDED is set, two things change: Firstly, backslash in a replacement string is interpreted as an escape character. The usual forms such as \n or \x{ddd} can be used to specify @@ -2698,22 +2760,41 @@ CREATING A NEW STRING WITH SUBSTITUTIONS somebody 1: HELLO - If successful, the function returns the number of replacements that - were made. This may be zero if no matches were found, and is never + The PCRE2_SUBSTITUTE_UNSET_EMPTY option does not affect these extended + substitutions. However, PCRE2_SUBSTITUTE_UNKNOWN_UNSET does cause + unknown groups in the extended syntax forms to be treated as unset. + + If successful, pcre2_substitute() returns the number of replacements + that were made. This may be zero if no matches were found, and is never greater than 1 unless PCRE2_SUBSTITUTE_GLOBAL is set. In the event of an error, a negative error code is returned. Except for PCRE2_ERROR_NOMATCH (which is never returned), errors from - pcre2_match() are passed straight back. PCRE2_ERROR_NOMEMORY is - returned if the output buffer is not big enough. - PCRE2_ERROR_BADREPLACEMENT is used for miscellaneous syntax errors in + pcre2_match() are passed straight back. + + PCRE2_ERROR_NOSUBSTRING is returned for a non-existent substring inser- + tion, unless PCRE2_SUBSTITUTE_UNKNOWN_UNSET is set. + + PCRE2_ERROR_UNSET is returned for an unset substring insertion (includ- + ing an unknown substring when PCRE2_SUBSTITUTE_UNKNOWN_UNSET is set) + when the simple (non-extended) syntax is used and PCRE2_SUBSTI- + TUTE_UNSET_EMPTY is not set. + + PCRE2_ERROR_NOMEMORY is returned if the output buffer is not big + enough. If the PCRE2_SUBSTITUTE_OVERFLOW_LENGTH option is set, the size + of buffer that is needed is returned via outlengthptr. Note that this + does not happen by default. + + PCRE2_ERROR_BADREPLACEMENT is used for miscellaneous syntax errors in the replacement string, with more particular errors being - PCRE2_ERROR_BADREPESCAPE (invalid escape sequence), PCRE2_ERROR_REP- - MISSING_BRACE (closing curly bracket not found), PCRE2_BADSUBSTITUTION - (syntax error in extended group substitution), and PCRE2_BADSUBPATTERN - (the pattern match ended before it started). As for all PCRE2 errors, a - text message that describes the error can be obtained by calling - pcre2_get_error_message(). + PCRE2_ERROR_BADREPESCAPE (invalid escape sequence), PCRE2_ERROR_REP- + MISSING_BRACE (closing curly bracket not found), PCRE2_BADSUBSTITUTION + (syntax error in extended group substitution), and PCRE2_BADSUBPATTERN + (the pattern match ended before it started, which can happen if \K is + used in an assertion). + + As for all PCRE2 errors, a text message that describes the error can be + obtained by calling pcre2_get_error_message(). DUPLICATE SUBPATTERN NAMES @@ -2721,56 +2802,56 @@ DUPLICATE SUBPATTERN NAMES int pcre2_substring_nametable_scan(const pcre2_code *code, PCRE2_SPTR name, PCRE2_SPTR *first, PCRE2_SPTR *last); - When a pattern is compiled with the PCRE2_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 PCRE2_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 pcre2pattern documentation. - When duplicates are present, pcre2_substring_copy_byname() and - pcre2_substring_get_byname() return the first substring corresponding - to the given name that is set. Only if none are set is - PCRE2_ERROR_UNSET is returned. The pcre2_substring_number_from_name() + When duplicates are present, pcre2_substring_copy_byname() and + pcre2_substring_get_byname() return the first substring corresponding + to the given name that is set. Only if none are set is + PCRE2_ERROR_UNSET is returned. The pcre2_substring_number_from_name() function returns the error PCRE2_ERROR_NOUNIQUESUBSTRING when there are duplicate names. - If you want to get full details of all captured substrings for a given - name, you must use the pcre2_substring_nametable_scan() function. The - first argument is the compiled pattern, and the second is the name. If - the third and fourth arguments are NULL, the function returns a group + If you want to get full details of all captured substrings for a given + name, you must use the pcre2_substring_nametable_scan() function. The + first argument is the compiled pattern, and the second is the name. If + the third and fourth arguments are NULL, the function returns a group number for a unique name, or PCRE2_ERROR_NOUNIQUESUBSTRING otherwise. When the third and fourth arguments are not NULL, they must be pointers - to variables that are updated by the function. After it has run, they + to variables that 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, and the function returns the length of each entry in code - units. In both cases, PCRE2_ERROR_NOSUBSTRING is returned if there are + given name, and the function returns the length of each entry in code + units. In both cases, PCRE2_ERROR_NOSUBSTRING is returned if there are no entries for the given name. The format of the name table is described above in the section entitled - Information about a pattern above. Given all the relevant entries for - the name, you can extract each of their numbers, and hence the captured + Information about a pattern. Given all the relevant entries for the + name, you can extract each of their numbers, and hence the captured data. FINDING ALL POSSIBLE MATCHES AT ONE POSITION - The traditional matching function uses a similar algorithm to Perl, - which stops when it finds the first match at a given point in the sub- + The traditional matching function uses a similar algorithm to Perl, + which stops when it finds the first match at a given point in the sub- ject. If you want to find all possible matches, or the longest possible - match at a given position, consider using the alternative matching - function (see below) instead. If you cannot use the alternative func- + match at a given position, consider using the alternative matching + function (see below) instead. If you cannot use the alternative func- tion, you can kludge it up by making use of the callout facility, which is described in the pcre2callout documentation. 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 pcre2_match() 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 pcre2_match() to + backtrack and try other alternatives. Ultimately, when it runs out of matches, pcre2_match() will yield PCRE2_ERROR_NOMATCH. @@ -2782,26 +2863,26 @@ MATCHING A PATTERN: THE ALTERNATIVE FUNCTION pcre2_match_context *mcontext, int *workspace, PCRE2_SIZE wscount); - The function pcre2_dfa_match() 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 PCRE2 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 + The function pcre2_dfa_match() 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 PCRE2 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 pcre2_dfa_match() does not support, see the pcre2matching documen- tation. - The arguments for the pcre2_dfa_match() function are the same as for + The arguments for the pcre2_dfa_match() function are the same as for pcre2_match(), plus two extras. The ovector within the match data block is used in a different way, and this is described below. The other com- - mon arguments are used in the same way as for pcre2_match(), so their + mon arguments are used in the same way as for pcre2_match(), 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 is needed for patterns and subjects where there are a lot of + workspace is needed for patterns and subjects where there are a lot of potential matches. Here is an example of a simple call to pcre2_dfa_match(): @@ -2821,45 +2902,45 @@ MATCHING A PATTERN: THE ALTERNATIVE FUNCTION Option bits for pcre_dfa_match() - The unused bits of the options argument for pcre2_dfa_match() must be - zero. The only bits that may be set are PCRE2_ANCHORED, PCRE2_NOTBOL, + The unused bits of the options argument for pcre2_dfa_match() must be + zero. The only bits that may be set are PCRE2_ANCHORED, PCRE2_NOTBOL, PCRE2_NOTEOL, PCRE2_NOTEMPTY, PCRE2_NOTEMPTY_ATSTART, PCRE2_NO_UTF_CHECK, PCRE2_PARTIAL_HARD, PCRE2_PARTIAL_SOFT, - PCRE2_DFA_SHORTEST, and PCRE2_DFA_RESTART. All but the last four of - these are exactly the same as for pcre2_match(), so their description + PCRE2_DFA_SHORTEST, and PCRE2_DFA_RESTART. All but the last four of + these are exactly the same as for pcre2_match(), so their description is not repeated here. PCRE2_PARTIAL_HARD PCRE2_PARTIAL_SOFT - These have the same general effect as they do for pcre2_match(), but - the details are slightly different. When PCRE2_PARTIAL_HARD is set for - pcre2_dfa_match(), it returns PCRE2_ERROR_PARTIAL if the end of the + These have the same general effect as they do for pcre2_match(), but + the details are slightly different. When PCRE2_PARTIAL_HARD is set for + pcre2_dfa_match(), it returns PCRE2_ERROR_PARTIAL if the end of the subject is reached and there is still at least one matching possibility that requires additional characters. This happens even if some complete - matches have already been found. When PCRE2_PARTIAL_SOFT is set, the - return code PCRE2_ERROR_NOMATCH is converted into PCRE2_ERROR_PARTIAL - if the end of the subject is reached, there have been no complete + matches have already been found. When PCRE2_PARTIAL_SOFT is set, the + return code PCRE2_ERROR_NOMATCH is converted into PCRE2_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 por- - tion of the string that was inspected when the longest partial match + tion 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 + more detailed discussion of partial and multi-segment matching, with examples, in the pcre2partial documentation. PCRE2_DFA_SHORTEST - Setting the PCRE2_DFA_SHORTEST option causes the matching algorithm to + Setting the PCRE2_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. PCRE2_DFA_RESTART - When pcre2_dfa_match() returns a partial match, it is possible to call + When pcre2_dfa_match() returns a partial match, it is possible to call it again, with additional subject characters, and have it continue with the same match. The PCRE2_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 + 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 pcre2partial documentation. @@ -2867,8 +2948,8 @@ MATCHING A PATTERN: THE ALTERNATIVE FUNCTION When pcre2_dfa_match() 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 <.*> @@ -2883,17 +2964,17 @@ MATCHING A PATTERN: THE ALTERNATIVE FUNCTION <something> <something else> <something> - On success, the yield of the function is a number greater than zero, - which is the number of matched substrings. The offsets of the sub- - strings are returned in the ovector, and can be extracted by number in - the same way as for pcre2_match(), but the numbers bear no relation to - any capturing groups that may exist in the pattern, because DFA match- + On success, the yield of the function is a number greater than zero, + which is the number of matched substrings. The offsets of the sub- + strings are returned in the ovector, and can be extracted by number in + the same way as for pcre2_match(), but the numbers bear no relation to + any capturing groups that may exist in the pattern, because DFA match- ing does not support group capture. - Calls to the convenience functions that extract substrings by name - return the error PCRE2_ERROR_DFA_UFUNC (unsupported function) if used + Calls to the convenience functions that extract substrings by name + return the error PCRE2_ERROR_DFA_UFUNC (unsupported function) if used after a DFA match. The convenience functions that extract substrings by - number never return PCRE2_ERROR_NOSUBSTRING, and the meanings of some + number never return PCRE2_ERROR_NOSUBSTRING, and the meanings of some other errors are slightly different: PCRE2_ERROR_UNAVAILABLE @@ -2903,64 +2984,64 @@ MATCHING A PATTERN: THE ALTERNATIVE FUNCTION PCRE2_ERROR_UNSET - There is a slot in the ovector for this substring, but there were + There is a slot in the ovector for this substring, but there were insufficient matches to fill it. - The matched strings are stored in the ovector in reverse order of - length; that is, the longest matching string is first. If there were - too many matches to fit into the ovector, the yield of the function is + The matched strings are stored in the ovector in reverse order of + length; that is, the longest matching string is first. If there were + too many matches to fit into the ovector, the yield of the function is zero, and the vector is filled with the longest matches. - NOTE: PCRE2'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++". For DFA - matching, this means that only one possible match is found. If you - really do want multiple matches in such cases, either use an ungreedy - repeat auch as "a\d+?" or set the PCRE2_NO_AUTO_POSSESS option when + NOTE: PCRE2'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++". For DFA + matching, this means that only one possible match is found. If you + really do want multiple matches in such cases, either use an ungreedy + repeat auch as "a\d+?" or set the PCRE2_NO_AUTO_POSSESS option when compiling. Error returns from pcre2_dfa_match() The pcre2_dfa_match() function returns a negative number when it fails. - Many of the errors are the same as for pcre2_match(), as described + Many of the errors are the same as for pcre2_match(), as described above. There are in addition the following errors that are specific to pcre2_dfa_match(): PCRE2_ERROR_DFA_UITEM - This return is given if pcre2_dfa_match() encounters an item in the - pattern that it does not support, for instance, the use of \C in a UTF + This return is given if pcre2_dfa_match() encounters an item in the + pattern that it does not support, for instance, the use of \C in a UTF mode or a back reference. PCRE2_ERROR_DFA_UCOND - This return is given if pcre2_dfa_match() encounters a condition item - that uses a back reference for the condition, or a test for recursion + This return is given if pcre2_dfa_match() 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. PCRE2_ERROR_DFA_WSSIZE - This return is given if pcre2_dfa_match() runs out of space in the + This return is given if pcre2_dfa_match() runs out of space in the workspace vector. PCRE2_ERROR_DFA_RECURSE - When a recursive subpattern is processed, the matching function calls + When a recursive subpattern is processed, the matching function calls itself recursively, using private memory for the ovector and workspace. - This error is given if the internal ovector is not large enough. This + This error is given if the internal ovector is not large enough. This should be extremely rare, as a vector of size 1000 is used. PCRE2_ERROR_DFA_BADRESTART - When pcre2_dfa_match() is called with the PCRE2_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 + When pcre2_dfa_match() is called with the PCRE2_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 - pcre2build(3), pcre2callout(3), pcre2demo(3), pcre2matching(3), + pcre2build(3), pcre2callout(3), pcre2demo(3), pcre2matching(3), pcre2partial(3), pcre2posix(3), pcre2sample(3), pcre2stack(3), pcre2unicode(3). @@ -2974,11 +3055,11 @@ AUTHOR REVISION - Last updated: 05 November 2015 + Last updated: 16 December 2015 Copyright (c) 1997-2015 University of Cambridge. ------------------------------------------------------------------------------ - - + + PCRE2BUILD(3) Library Functions Manual PCRE2BUILD(3) @@ -3461,8 +3542,8 @@ REVISION Last updated: 16 October 2015 Copyright (c) 1997-2015 University of Cambridge. ------------------------------------------------------------------------------ - - + + PCRE2CALLOUT(3) Library Functions Manual PCRE2CALLOUT(3) @@ -3825,8 +3906,8 @@ REVISION Last updated: 23 March 2015 Copyright (c) 1997-2015 University of Cambridge. ------------------------------------------------------------------------------ - - + + PCRE2COMPAT(3) Library Functions Manual PCRE2COMPAT(3) @@ -4010,8 +4091,8 @@ REVISION Last updated: 15 March 2015 Copyright (c) 1997-2015 University of Cambridge. ------------------------------------------------------------------------------ - - + + PCRE2JIT(3) Library Functions Manual PCRE2JIT(3) @@ -4078,6 +4159,12 @@ SIMPLE USE OF JIT exactly the same results. The returned value from pcre2_jit_compile() is zero on success, or a negative error code. + There is a limit to the size of pattern that JIT supports, imposed by + the size of machine stack that it uses. The exact rules are not docu- + mented because they may change at any time, in particular, when new + optimizations are introduced. If a pattern is too big, a call to + pcre2_jit_compile() returns PCRE2_ERROR_NOMEMORY. + PCRE2_JIT_COMPLETE requests the JIT compiler to generate code for com- plete matches. If you want to run partial matches using the PCRE2_PAR- TIAL_HARD or PCRE2_PARTIAL_SOFT options of pcre2_match(), you should @@ -4394,11 +4481,11 @@ AUTHOR REVISION - Last updated: 28 July 2015 + Last updated: 14 November 2015 Copyright (c) 1997-2015 University of Cambridge. ------------------------------------------------------------------------------ - - + + PCRE2LIMITS(3) Library Functions Manual PCRE2LIMITS(3) @@ -4475,8 +4562,8 @@ REVISION Last updated: 05 November 2015 Copyright (c) 1997-2015 University of Cambridge. ------------------------------------------------------------------------------ - - + + PCRE2MATCHING(3) Library Functions Manual PCRE2MATCHING(3) @@ -4694,8 +4781,8 @@ REVISION Last updated: 29 September 2014 Copyright (c) 1997-2014 University of Cambridge. ------------------------------------------------------------------------------ - - + + PCRE2PARTIAL(3) Library Functions Manual PCRE2PARTIAL(3) @@ -5134,8 +5221,8 @@ REVISION Last updated: 22 December 2014 Copyright (c) 1997-2014 University of Cambridge. ------------------------------------------------------------------------------ - - + + PCRE2PATTERN(3) Library Functions Manual PCRE2PATTERN(3) @@ -5706,20 +5793,21 @@ BACKSLASH below. This particular group matches either the two-character sequence CR followed by LF, or one of the single characters LF (linefeed, U+000A), VT (vertical tab, U+000B), FF (form feed, U+000C), CR (car- - riage return, U+000D), or NEL (next line, U+0085). The two-character - sequence is treated as a single unit that cannot be split. + riage return, U+000D), or NEL (next line, U+0085). Because this is an + atomic group, the two-character sequence is treated as a single unit + that cannot be split. - In other modes, two additional characters whose codepoints are greater + In other modes, two additional characters whose codepoints are greater than 255 are added: LS (line separator, U+2028) and PS (paragraph sepa- - rator, U+2029). Unicode support is not needed for these characters to + rator, U+2029). Unicode support is not needed for these characters to be recognized. It is possible to restrict \R to match only CR, LF, or CRLF (instead of - the complete set of Unicode line endings) by setting the option - PCRE2_BSR_ANYCRLF at compile time. (BSR is an abbrevation for "back- + the complete set of Unicode line endings) by setting the option + PCRE2_BSR_ANYCRLF at compile time. (BSR is an abbrevation for "back- slash R".) This can be made the default when PCRE2 is built; if this is - the case, the other behaviour can be requested via the PCRE2_BSR_UNI- - CODE option. It is also possible to specify these settings by starting + the case, the other behaviour can be requested via the PCRE2_BSR_UNI- + CODE option. It is also possible to specify these settings by starting a pattern string with one of the following sequences: (*BSR_ANYCRLF) CR, LF, or CRLF only @@ -5727,76 +5815,76 @@ BACKSLASH These override the default and the options given to the compiling func- tion. Note that these special settings, which are not Perl-compatible, - are recognized only at the very start of a pattern, and that they must - be in upper case. If more than one of them is present, the last one is - used. They can be combined with a change of newline convention; for + are recognized only at the very start of a pattern, and that they must + be in upper case. If more than one of them is present, the last one is + used. They can be combined with a change of newline convention; for example, a pattern can start with: (*ANY)(*BSR_ANYCRLF) - They can also be combined with the (*UTF) or (*UCP) special sequences. - Inside a character class, \R is treated as an unrecognized escape + They can also be combined with the (*UTF) or (*UCP) special sequences. + Inside a character class, \R is treated as an unrecognized escape sequence, and causes an error. Unicode character properties - When PCRE2 is built with Unicode support (the default), three addi- - tional escape sequences that match characters with specific properties - are available. In 8-bit non-UTF-8 mode, these sequences are of course - limited to testing characters whose codepoints are less than 256, but + When PCRE2 is built with Unicode support (the default), three addi- + tional escape sequences that match characters with specific properties + are available. In 8-bit non-UTF-8 mode, these sequences are of course + limited to testing characters whose codepoints are less than 256, but they do work in this mode. The extra escape sequences are: \p{xx} a character with the xx property \P{xx} a character without the xx property \X a Unicode extended grapheme cluster - The property names represented by xx above are limited to the Unicode + The property names represented by xx above are limited to the Unicode script names, the general category properties, "Any", which matches any character (including newline), and some special PCRE2 properties - (described in the next section). Other Perl properties such as "InMu- - sicalSymbols" are not supported by PCRE2. Note that \P{Any} does not + (described in the next section). Other Perl properties such as "InMu- + sicalSymbols" are not supported by PCRE2. Note that \P{Any} does not match any characters, so always causes a match failure. Sets of Unicode characters are defined as belonging to certain scripts. - A character from one of these sets can be matched using a script name. + A character from one of these sets can be matched using a script name. For example: \p{Greek} \P{Han} - Those that are not part of an identified script are lumped together as + Those that are not part of an identified script are lumped together as "Common". The current list of scripts is: - Ahom, Anatolian_Hieroglyphs, Arabic, Armenian, Avestan, Balinese, - Bamum, Bassa_Vah, Batak, Bengali, Bopomofo, Brahmi, Braille, Buginese, - Buhid, Canadian_Aboriginal, Carian, Caucasian_Albanian, Chakma, Cham, - Cherokee, Common, Coptic, Cuneiform, Cypriot, Cyrillic, Deseret, - Devanagari, Duployan, Egyptian_Hieroglyphs, Elbasan, Ethiopic, Geor- - gian, Glagolitic, Gothic, Grantha, Greek, Gujarati, Gurmukhi, Han, + Ahom, Anatolian_Hieroglyphs, Arabic, Armenian, Avestan, Balinese, + Bamum, Bassa_Vah, Batak, Bengali, Bopomofo, Brahmi, Braille, Buginese, + Buhid, Canadian_Aboriginal, Carian, Caucasian_Albanian, Chakma, Cham, + Cherokee, Common, Coptic, Cuneiform, Cypriot, Cyrillic, Deseret, + Devanagari, Duployan, Egyptian_Hieroglyphs, Elbasan, Ethiopic, Geor- + gian, Glagolitic, Gothic, Grantha, Greek, Gujarati, Gurmukhi, Han, Hangul, Hanunoo, Hatran, Hebrew, Hiragana, Imperial_Aramaic, Inherited, - Inscriptional_Pahlavi, Inscriptional_Parthian, Javanese, Kaithi, Kan- - nada, Katakana, Kayah_Li, Kharoshthi, Khmer, Khojki, Khudawadi, Lao, - Latin, Lepcha, Limbu, Linear_A, Linear_B, Lisu, Lycian, Lydian, Maha- + Inscriptional_Pahlavi, Inscriptional_Parthian, Javanese, Kaithi, Kan- + nada, Katakana, Kayah_Li, Kharoshthi, Khmer, Khojki, Khudawadi, Lao, + Latin, Lepcha, Limbu, Linear_A, Linear_B, Lisu, Lycian, Lydian, Maha- jani, Malayalam, Mandaic, Manichaean, Meetei_Mayek, Mende_Kikakui, - Meroitic_Cursive, Meroitic_Hieroglyphs, Miao, Modi, Mongolian, Mro, - Multani, Myanmar, Nabataean, New_Tai_Lue, Nko, Ogham, Ol_Chiki, - Old_Hungarian, Old_Italic, Old_North_Arabian, Old_Permic, Old_Persian, + Meroitic_Cursive, Meroitic_Hieroglyphs, Miao, Modi, Mongolian, Mro, + Multani, Myanmar, Nabataean, New_Tai_Lue, Nko, Ogham, Ol_Chiki, + Old_Hungarian, Old_Italic, Old_North_Arabian, Old_Permic, Old_Persian, Old_South_Arabian, Old_Turkic, Oriya, Osmanya, Pahawh_Hmong, Palmyrene, Pau_Cin_Hau, Phags_Pa, Phoenician, Psalter_Pahlavi, Rejang, Runic, Samaritan, Saurashtra, Sharada, Shavian, Siddham, SignWriting, Sinhala, - Sora_Sompeng, Sundanese, Syloti_Nagri, Syriac, Tagalog, Tagbanwa, - Tai_Le, Tai_Tham, Tai_Viet, Takri, Tamil, Telugu, Thaana, Thai, + Sora_Sompeng, Sundanese, Syloti_Nagri, Syriac, Tagalog, Tagbanwa, + Tai_Le, Tai_Tham, Tai_Viet, Takri, Tamil, Telugu, Thaana, Thai, Tibetan, Tifinagh, Tirhuta, Ugaritic, Vai, Warang_Citi, Yi. Each character has exactly one Unicode general category property, spec- - ified by a two-letter abbreviation. For compatibility with Perl, nega- - tion can be specified by including a circumflex between the opening - brace and the property name. For example, \p{^Lu} is the same as + ified by a two-letter abbreviation. For compatibility with Perl, nega- + tion can be specified by including a circumflex between the opening + brace and the property name. For example, \p{^Lu} is the same as \P{Lu}. If only one letter is specified with \p or \P, it includes all the gen- - eral category properties that start with that letter. In this case, in - the absence of negation, the curly brackets in the escape sequence are + eral category properties that start with that letter. In this case, in + the absence of negation, the curly brackets in the escape sequence are optional; these two examples have the same effect: \p{L} @@ -5848,59 +5936,59 @@ BACKSLASH Zp Paragraph separator Zs Space separator - The special property L& is also supported: it matches a character that - has the Lu, Ll, or Lt property, in other words, a letter that is not + The special property L& is also supported: it matches a character that + has the Lu, Ll, or Lt property, in other words, a letter that is not classified as a modifier or "other". - The Cs (Surrogate) property applies only to characters in the range - U+D800 to U+DFFF. Such characters are not valid in Unicode strings and - so cannot be tested by PCRE2, unless UTF validity checking has been - turned off (see the discussion of PCRE2_NO_UTF_CHECK in the pcre2api + The Cs (Surrogate) property applies only to characters in the range + U+D800 to U+DFFF. Such characters are not valid in Unicode strings and + so cannot be tested by PCRE2, unless UTF validity checking has been + turned off (see the discussion of PCRE2_NO_UTF_CHECK in the pcre2api page). Perl does not support the Cs property. - The long synonyms for property names that Perl supports (such as - \p{Letter}) are not supported by PCRE2, nor is it permitted to prefix + The long synonyms for property names that Perl supports (such as + \p{Letter}) are not supported by PCRE2, nor is it permitted to prefix any of these properties with "Is". No character that is in the Unicode table has the Cn (unassigned) prop- erty. Instead, this property is assumed for any code point that is not in the Unicode table. - Specifying caseless matching does not affect these escape sequences. - For example, \p{Lu} always matches only upper case letters. This is + Specifying caseless matching does not affect these escape sequences. + For example, \p{Lu} always matches only upper case letters. This is different from the behaviour of current versions of Perl. - Matching characters by Unicode property is not fast, because PCRE2 has - to do a multistage table lookup in order to find a character's prop- + Matching characters by Unicode property is not fast, because PCRE2 has + to do a multistage table lookup in order to find a character's prop- erty. That is why the traditional escape sequences such as \d and \w do - not use Unicode properties in PCRE2 by default, though you can make - them do so by setting the PCRE2_UCP option or by starting the pattern + not use Unicode properties in PCRE2 by default, though you can make + them do so by setting the PCRE2_UCP option or by starting the pattern with (*UCP). Extended grapheme clusters - The \X escape matches any number of Unicode characters that form an + The \X escape matches any number of Unicode characters that form an "extended grapheme cluster", and treats the sequence as an atomic group - (see below). Unicode supports various kinds of composite character by - giving each character a grapheme breaking property, and having rules + (see below). Unicode supports various kinds of composite character by + giving each character a grapheme breaking property, and having rules that use these properties to define the boundaries of extended grapheme - clusters. \X always matches at least one character. Then it decides - whether to add additional characters according to the following rules + clusters. \X always matches at least one character. Then it decides + whether to add additional characters according to the following rules for ending a cluster: 1. End at the end of the subject string. - 2. Do not end between CR and LF; otherwise end after any control char- + 2. Do not end between CR and LF; otherwise end after any control char- acter. - 3. Do not break Hangul (a Korean script) syllable sequences. Hangul - characters are of five types: L, V, T, LV, and LVT. An L character may - be followed by an L, V, LV, or LVT character; an LV or V character may + 3. Do not break Hangul (a Korean script) syllable sequences. Hangul + characters are of five types: L, V, T, LV, and LVT. An L character may + be followed by an L, V, LV, or LVT character; an LV or V character may be followed by a V or T character; an LVT or T character may be follwed only by a T character. - 4. Do not end before extending characters or spacing marks. Characters - with the "mark" property always have the "extend" grapheme breaking + 4. Do not end before extending characters or spacing marks. Characters + with the "mark" property always have the "extend" grapheme breaking property. 5. Do not end after prepend characters. @@ -5909,10 +5997,10 @@ BACKSLASH PCRE2's additional properties - As well as the standard Unicode properties described above, PCRE2 sup- - ports four more that make it possible to convert traditional escape + As well as the standard Unicode properties described above, PCRE2 sup- + ports four more that make it possible to convert traditional escape sequences such as \w and \s to use Unicode properties. PCRE2 uses these - non-standard, non-Perl properties internally when PCRE2_UCP is set. + non-standard, non-Perl properties internally when PCRE2_UCP is set. However, they may also be used explicitly. These properties are: Xan Any alphanumeric character @@ -5920,53 +6008,53 @@ BACKSLASH Xsp Any Perl space character Xwd Any Perl "word" character - Xan matches characters that have either the L (letter) or the N (num- - ber) property. Xps matches the characters tab, linefeed, vertical tab, - form feed, or carriage return, and any other character that has the Z - (separator) property. Xsp is the same as Xps; in PCRE1 it used to - exclude vertical tab, for Perl compatibility, but Perl changed. Xwd + Xan matches characters that have either the L (letter) or the N (num- + ber) property. Xps matches the characters tab, linefeed, vertical tab, + form feed, or carriage return, and any other character that has the Z + (separator) property. Xsp is the same as Xps; in PCRE1 it used to + exclude vertical tab, for Perl compatibility, but Perl changed. Xwd matches the same characters as Xan, plus underscore. - There is another non-standard property, Xuc, which matches any charac- - ter that can be represented by a Universal Character Name in C++ and - other programming languages. These are the characters $, @, ` (grave - accent), and all characters with Unicode code points greater than or - equal to U+00A0, except for the surrogates U+D800 to U+DFFF. Note that - most base (ASCII) characters are excluded. (Universal Character Names - are of the form \uHHHH or \UHHHHHHHH where H is a hexadecimal digit. + There is another non-standard property, Xuc, which matches any charac- + ter that can be represented by a Universal Character Name in C++ and + other programming languages. These are the characters $, @, ` (grave + accent), and all characters with Unicode code points greater than or + equal to U+00A0, except for the surrogates U+D800 to U+DFFF. Note that + most base (ASCII) characters are excluded. (Universal Character Names + are of the form \uHHHH or \UHHHHHHHH where H is a hexadecimal digit. Note that the Xuc property does not match these sequences but the char- acters that they represent.) Resetting the match start - The escape sequence \K causes any previously matched characters not to + The escape sequence \K causes any previously matched characters not to be included in the final matched sequence. For example, the pattern: foo\Kbar - matches "foobar", but reports that it has matched "bar". This feature - is similar to a lookbehind assertion (described below). However, in - this case, the part of the subject before the real match does not have - to be of fixed length, as lookbehind assertions do. The use of \K does - not interfere with the setting of captured substrings. For example, + matches "foobar", but reports that it has matched "bar". This feature + is similar to a lookbehind assertion (described below). However, in + this case, the part of the subject before the real match does not have + to be of fixed length, as lookbehind assertions do. The use of \K does + not interfere with the setting of captured substrings. For example, when the pattern (foo)\Kbar matches "foobar", the first substring is still set to "foo". - Perl documents that the use of \K within assertions is "not well - defined". In PCRE2, \K is acted upon when it occurs inside positive - assertions, but is ignored in negative assertions. Note that when a - pattern such as (?=ab\K) matches, the reported start of the match can + Perl documents that the use of \K within assertions is "not well + defined". In PCRE2, \K is acted upon when it occurs inside positive + 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 - The final use of backslash is for certain simple assertions. An asser- - tion specifies a condition that has to be met at a particular point in - a match, without consuming any characters from the subject string. The - use of subpatterns for more complicated assertions is described below. + The final use of backslash is for certain simple assertions. An asser- + tion specifies a condition that has to be met at a particular point in + a match, without consuming any characters from the subject string. The + use of subpatterns for more complicated assertions is described below. The backslashed assertions are: \b matches at a word boundary @@ -5977,172 +6065,180 @@ BACKSLASH \z matches only at the end of the subject \G matches at the first matching position in the subject - Inside a character class, \b has a different meaning; it matches the - backspace character. If any other of these assertions appears in a + Inside a character class, \b has a different meaning; it matches the + backspace character. If any other of these assertions appears in a character class, an "invalid escape sequence" error is generated. - A word boundary is a position in the subject string where the current - character and the previous character do not both match \w or \W (i.e. - one matches \w and the other matches \W), or the start or end of the - string if the first or last character matches \w, respectively. In a - UTF mode, the meanings of \w and \W can be changed by setting the + A word boundary is a position in the subject string where the current + character and the previous character do not both match \w or \W (i.e. + one matches \w and the other matches \W), or the start or end of the + string if the first or last character matches \w, respectively. In a + UTF mode, the meanings of \w and \W can be changed by setting the PCRE2_UCP option. When this is done, it also affects \b and \B. Neither - PCRE2 nor Perl has a separate "start of word" or "end of word" metase- - quence. However, whatever follows \b normally determines which it is. + PCRE2 nor Perl has a separate "start of word" or "end of word" metase- + quence. However, whatever follows \b normally determines which it is. For example, the fragment \ba matches "a" at the start of a word. - The \A, \Z, and \z assertions differ from the traditional circumflex + The \A, \Z, and \z assertions differ from the traditional circumflex and dollar (described in the next section) in that they only ever match - at the very start and end of the subject string, whatever options are - set. Thus, they are independent of multiline mode. These three asser- - tions are not affected by the PCRE2_NOTBOL or PCRE2_NOTEOL options, - which affect only the behaviour of the circumflex and dollar metachar- - acters. However, if the startoffset argument of pcre2_match() is non- - zero, indicating that matching is to start at a point other than the - beginning of the subject, \A can never match. The difference between - \Z and \z is that \Z matches before a newline at the end of the string + at the very start and end of the subject string, whatever options are + set. Thus, they are independent of multiline mode. These three asser- + tions are not affected by the PCRE2_NOTBOL or PCRE2_NOTEOL options, + which affect only the behaviour of the circumflex and dollar metachar- + acters. However, if the startoffset argument of pcre2_match() is non- + zero, indicating that matching is to start at a point other than the + beginning of the subject, \A can never match. The difference between + \Z and \z is that \Z matches before a newline at the end of the string as well as at the very end, whereas \z matches only at the end. - The \G assertion is true only when the current matching position is at - the start point of the match, as specified by the startoffset argument - of pcre2_match(). It differs from \A when the value of startoffset is - non-zero. By calling pcre2_match() multiple times with appropriate - arguments, you can mimic Perl's /g option, and it is in this kind of + The \G assertion is true only when the current matching position is at + the start point of the match, as specified by the startoffset argument + of pcre2_match(). It differs from \A when the value of startoffset is + non-zero. By calling pcre2_match() multiple times with appropriate + arguments, you can mimic Perl's /g option, and it is in this kind of implementation where \G can be useful. - Note, however, that PCRE2's interpretation of \G, as the start of the + Note, however, that PCRE2's interpretation of \G, as the start of the current match, is subtly different from Perl's, which defines it as the - end of the previous match. In Perl, these can be different when the - previously matched string was empty. Because PCRE2 does just one match + end of the previous match. In Perl, these can be different when the + previously matched string was empty. Because PCRE2 does just one match at a time, it cannot reproduce this behaviour. - If all the alternatives of a pattern begin with \G, the expression is + If all the alternatives of a pattern begin with \G, the expression is anchored to the starting match position, and the "anchored" flag is set in the compiled regular expression. CIRCUMFLEX AND DOLLAR - The circumflex and dollar metacharacters are zero-width assertions. - That is, they test for a particular condition being true without con- + The circumflex and dollar metacharacters are zero-width assertions. + That is, they test for a particular condition being true without con- suming any characters from the subject string. These two metacharacters - are concerned with matching the starts and ends of lines. If the new- - line convention is set so that only the two-character sequence CRLF is - recognized as a newline, isolated CR and LF characters are treated as + are concerned with matching the starts and ends of lines. If the new- + line convention is set so that only the two-character sequence CRLF is + recognized as a newline, isolated CR and LF characters are treated as ordinary data characters, and are not recognized as newlines. Outside a character class, in the default matching mode, the circumflex - character is an assertion that is true only if the current matching - point is at the start of the subject string. If the startoffset argu- - ment of pcre2_match() is non-zero, or if PCRE2_NOTBOL is set, circum- - flex can never match if the PCRE2_MULTILINE option is unset. Inside a - character class, circumflex has an entirely different meaning (see + character is an assertion that is true only if the current matching + point is at the start of the subject string. If the startoffset argu- + ment of pcre2_match() is non-zero, or if PCRE2_NOTBOL is set, circum- + flex can never match if the PCRE2_MULTILINE option is unset. Inside a + character class, circumflex has an entirely different meaning (see below). - Circumflex need not be the first character of the pattern if a number - of alternatives are involved, but it should be the first thing in each - alternative in which it appears if the pattern is ever to match that - branch. If all possible alternatives start with a circumflex, that is, - if the pattern is constrained to match only at the start of the sub- - ject, it is said to be an "anchored" pattern. (There are also other + Circumflex need not be the first character of the pattern if a number + of alternatives are involved, but it should be the first thing in each + alternative in which it appears if the pattern is ever to match that + branch. If all possible alternatives start with a circumflex, that is, + if the pattern is constrained to match only at the start of the sub- + ject, it is said to be an "anchored" pattern. (There are also other constructs that can cause a pattern to be anchored.) - The dollar character is an assertion that is true only if the current - matching point is at the end of the subject string, or immediately - before a newline at the end of the string (by default), unless + The dollar character is an assertion that is true only if the current + matching point is at the end of the subject string, or immediately + before a newline at the end of the string (by default), unless PCRE2_NOTEOL is set. Note, however, that it does not actually match the newline. Dollar need not be the last character of the pattern if a num- ber of alternatives are involved, but it should be the last item in any - branch in which it appears. Dollar has no special meaning in a charac- + branch in which it appears. Dollar has no special meaning in a charac- ter class. - The meaning of dollar can be changed so that it matches only at the - very end of the string, by setting the PCRE2_DOLLAR_ENDONLY option at + The meaning of dollar can be changed so that it matches only at the + very end of the string, by setting the PCRE2_DOLLAR_ENDONLY option at compile time. This does not affect the \Z assertion. The meanings of the circumflex and dollar metacharacters are changed if - the PCRE2_MULTILINE option is set. When this is the case, a dollar - character matches before any newlines in the string, as well as at the - very end, and a circumflex matches immediately after internal newlines - as well as at the start of the subject string. It does not match after - a newline that ends the string, for compatibility with Perl. However, + the PCRE2_MULTILINE option is set. When this is the case, a dollar + character matches before any newlines in the string, as well as at the + very end, and a circumflex matches immediately after internal newlines + as well as at the start of the subject string. It does not match after + a newline that ends the string, for compatibility with Perl. However, this can be changed by setting the PCRE2_ALT_CIRCUMFLEX option. - For example, the pattern /^abc$/ matches the subject string "def\nabc" - (where \n represents a newline) in multiline mode, but not otherwise. - Consequently, patterns that are anchored in single line mode because - all branches start with ^ are not anchored in multiline mode, and a - match for circumflex is possible when the startoffset argument of - pcre2_match() is non-zero. The PCRE2_DOLLAR_ENDONLY option is ignored + For example, the pattern /^abc$/ matches the subject string "def\nabc" + (where \n represents a newline) in multiline mode, but not otherwise. + Consequently, patterns that are anchored in single line mode because + all branches start with ^ are not anchored in multiline mode, and a + match for circumflex is possible when the startoffset argument of + pcre2_match() is non-zero. The PCRE2_DOLLAR_ENDONLY option is ignored if PCRE2_MULTILINE is set. - Note that the sequences \A, \Z, and \z can be used to match the start - and end of the subject in both modes, and if all branches of a pattern - start with \A it is always anchored, whether or not PCRE2_MULTILINE is + When the newline convention (see "Newline conventions" below) recog- + nizes the two-character sequence CRLF as a newline, this is preferred, + even if the single characters CR and LF are also recognized as new- + lines. For example, if the newline convention is "any", a multiline + mode circumflex matches before "xyz" in the string "abc\r\nxyz" rather + than after CR, even though CR on its own is a valid newline. (It also + matches at the very start of the string, of course.) + + Note that the sequences \A, \Z, and \z can be used to match the start + and end of the subject in both modes, and if all branches of a pattern + start with \A it is always anchored, whether or not PCRE2_MULTILINE is set. FULL STOP (PERIOD, DOT) AND \N Outside a character class, a dot in the pattern matches any one charac- - ter in the subject string except (by default) a character that signi- + ter in the subject string except (by default) a character that signi- fies the end of a line. - When a line ending is defined as a single character, dot never matches - that character; when the two-character sequence CRLF is used, dot does - not match CR if it is immediately followed by LF, but otherwise it - matches all characters (including isolated CRs and LFs). When any Uni- - code line endings are being recognized, dot does not match CR or LF or + When a line ending is defined as a single character, dot never matches + that character; when the two-character sequence CRLF is used, dot does + not match CR if it is immediately followed by LF, but otherwise it + matches all characters (including isolated CRs and LFs). When any Uni- + code line endings are being recognized, dot does not match CR or LF or any of the other line ending characters. - The behaviour of dot with regard to newlines can be changed. If the - PCRE2_DOTALL option is set, a dot matches any one character, without - exception. If the two-character sequence CRLF is present in the sub- + The behaviour of dot with regard to newlines can be changed. If the + PCRE2_DOTALL option is set, a dot matches any one character, without + exception. If the two-character sequence CRLF is present in the sub- ject string, it takes two dots to match it. - The handling of dot is entirely independent of the handling of circum- - flex and dollar, the only relationship being that they both involve + The handling of dot is entirely independent of the handling of circum- + flex and dollar, the only relationship being that they both involve newlines. Dot has no special meaning in a character class. - The escape sequence \N behaves like a dot, except that it is not - affected by the PCRE2_DOTALL option. In other words, it matches any - character except one that signifies the end of a line. Perl also uses + The escape sequence \N behaves like a dot, except that it is not + affected by the PCRE2_DOTALL option. In other words, it matches any + character except one that signifies the end of a line. Perl also uses \N to match characters by name; PCRE2 does not support this. MATCHING A SINGLE CODE UNIT - Outside a character class, the escape sequence \C matches any one code - unit, whether or not a UTF mode is set. In the 8-bit library, one code - unit is one byte; in the 16-bit library it is a 16-bit unit; in the - 32-bit library it is a 32-bit unit. Unlike a dot, \C always matches - line-ending characters. The feature is provided in Perl in order to + Outside a character class, the escape sequence \C matches any one code + unit, whether or not a UTF mode is set. In the 8-bit library, one code + unit is one byte; in the 16-bit library it is a 16-bit unit; in the + 32-bit library it is a 32-bit unit. Unlike a dot, \C always matches + line-ending characters. The feature is provided in Perl in order to match individual bytes in UTF-8 mode, but it is unclear how it can use- fully be used. - Because \C breaks up characters into individual code units, matching - one unit with \C in UTF-8 or UTF-16 mode means that the rest of the - string may start with a malformed UTF character. This has undefined + Because \C breaks up characters into individual code units, matching + one unit with \C in UTF-8 or UTF-16 mode means that the rest of the + string may start with a malformed UTF character. This has undefined results, because PCRE2 assumes that it is matching character by charac- - ter in a valid UTF string (by default it checks the subject string's - validity at the start of processing unless the PCRE2_NO_UTF_CHECK + ter in a valid UTF string (by default it checks the subject string's + validity at the start of processing unless the PCRE2_NO_UTF_CHECK option is used). - An application can lock out the use of \C by setting the - PCRE2_NEVER_BACKSLASH_C option when compiling a pattern. It is also + An application can lock out the use of \C by setting the + PCRE2_NEVER_BACKSLASH_C option when compiling a pattern. It is also possible to build PCRE2 with the use of \C permanently disabled. - PCRE2 does not allow \C to appear in lookbehind assertions (described - below) in a UTF mode, because this would make it impossible to calcu- - late the length of the lookbehind. Neither the alternative matching - function pcre2_dfa_match() not the JIT optimizer support \C in a UTF + PCRE2 does not allow \C to appear in lookbehind assertions (described + below) in a UTF mode, because this would make it impossible to calcu- + late the length of the lookbehind. Neither the alternative matching + function pcre2_dfa_match() not the JIT optimizer support \C in a UTF mode. The former gives a match-time error; the latter fails to optimize and so the match is always run using the interpreter. In general, the \C escape sequence is best avoided. However, one way of - using it that avoids the problem of malformed UTF characters is to use - a lookahead to check the length of the next character, as in this pat- - tern, which could be used with a UTF-8 string (ignore white space and + using it that avoids the problem of malformed UTF characters is to use + a lookahead to check the length of the next character, as in this pat- + tern, which could be used with a UTF-8 string (ignore white space and line breaks): (?| (?=[\x00-\x7f])(\C) | @@ -6150,10 +6246,10 @@ MATCHING A SINGLE CODE UNIT (?=[\x{800}-\x{ffff}])(\C)(\C)(\C) | (?=[\x{10000}-\x{1fffff}])(\C)(\C)(\C)(\C)) - In this example, a group that starts with (?| resets the capturing + In this example, a group that starts with (?| resets the capturing parentheses numbers in each alternative (see "Duplicate Subpattern Num- bers" below). The assertions at the start of each branch check the next - UTF-8 character for values whose encoding uses 1, 2, 3, or 4 bytes, + UTF-8 character for values whose encoding uses 1, 2, 3, or 4 bytes, respectively. The character's individual bytes are then captured by the appropriate number of \C groups. @@ -6162,105 +6258,105 @@ SQUARE BRACKETS AND CHARACTER CLASSES An opening square bracket introduces a character class, terminated by a closing square bracket. A closing square bracket on its own is not spe- - cial by default. If a closing square bracket is required as a member + cial by default. If a closing square bracket is required as a member of the class, it should be the first data character in the class (after - an initial circumflex, if present) or escaped with a backslash. This - means that, by default, an empty class cannot be defined. However, if - the PCRE2_ALLOW_EMPTY_CLASS option is set, a closing square bracket at + an initial circumflex, if present) or escaped with a backslash. This + means that, by default, an empty class cannot be defined. However, if + the PCRE2_ALLOW_EMPTY_CLASS option is set, a closing square bracket at the start does end the (empty) class. - A character class matches a single character in the subject. A matched + A character class matches a single character in the subject. A matched character must be in the set of characters defined by the class, unless - the first character in the class definition is a circumflex, in which + the first character in the class definition is a circumflex, in which case the subject character must not be in the set defined by the class. - If a circumflex is actually required as a member of the class, ensure + If a circumflex is actually required as a member of the class, ensure it is not the first character, or escape it with a backslash. - For example, the character class [aeiou] matches any lower case vowel, - while [^aeiou] matches any character that is not a lower case vowel. + For example, the character class [aeiou] matches any lower case vowel, + while [^aeiou] matches any character that is not a lower case vowel. Note that a circumflex is just a convenient notation for specifying the - characters that are in the class by enumerating those that are not. A - class that starts with a circumflex is not an assertion; it still con- - sumes a character from the subject string, and therefore it fails if + characters that are in the class by enumerating those that are not. A + class that starts with a circumflex is not an assertion; it still con- + sumes a character from the subject string, and therefore it fails if the current pointer is at the end of the string. - When caseless matching is set, any letters in a class represent both - their upper case and lower case versions, so for example, a caseless - [aeiou] matches "A" as well as "a", and a caseless [^aeiou] does not + When caseless matching is set, any letters in a class represent both + their upper case and lower case versions, so for example, a caseless + [aeiou] matches "A" as well as "a", and a caseless [^aeiou] does not match "A", whereas a caseful version would. - Characters that might indicate line breaks are never treated in any - special way when matching character classes, whatever line-ending - sequence is in use, and whatever setting of the PCRE2_DOTALL and - PCRE2_MULTILINE options is used. A class such as [^a] always matches + Characters that might indicate line breaks are never treated in any + special way when matching character classes, whatever line-ending + sequence is in use, and whatever setting of the PCRE2_DOTALL and + PCRE2_MULTILINE options is used. A class such as [^a] always matches one of these characters. - The minus (hyphen) character can be used to specify a range of charac- - ters in a character class. For example, [d-m] matches any letter - between d and m, inclusive. If a minus character is required in a - class, it must be escaped with a backslash or appear in a position - where it cannot be interpreted as indicating a range, typically as the + The minus (hyphen) character can be used to specify a range of charac- + ters in a character class. For example, [d-m] matches any letter + between d and m, inclusive. If a minus character is required in a + class, it must be escaped with a backslash or appear in a position + where it cannot be interpreted as indicating a range, typically as the first or last character in the class, or immediately after a range. For - example, [b-d-z] matches letters in the range b to d, a hyphen charac- + example, [b-d-z] matches letters in the range b to d, a hyphen charac- ter, or z. It is not possible to have the literal character "]" as the end charac- - ter of a range. A pattern such as [W-]46] is interpreted as a class of - two characters ("W" and "-") followed by a literal string "46]", so it - would match "W46]" or "-46]". However, if the "]" is escaped with a - backslash it is interpreted as the end of range, so [W-\]46] is inter- - preted as a class containing a range followed by two other characters. - The octal or hexadecimal representation of "]" can also be used to end + ter of a range. A pattern such as [W-]46] is interpreted as a class of + two characters ("W" and "-") followed by a literal string "46]", so it + would match "W46]" or "-46]". However, if the "]" is escaped with a + backslash it is interpreted as the end of range, so [W-\]46] is inter- + preted as a class containing a range followed by two other characters. + The octal or hexadecimal representation of "]" can also be used to end a range. - An error is generated if a POSIX character class (see below) or an - escape sequence other than one that defines a single character appears - at a point where a range ending character is expected. For example, + An error is generated if a POSIX character class (see below) or an + escape sequence other than one that defines a single character appears + at a point where a range ending character is expected. For example, [z-\xff] is valid, but [A-\d] and [A-[:digit:]] are not. Ranges normally include all code points between the start and end char- - acters, inclusive. They can also be used for code points specified + acters, inclusive. They can also be used for code points specified numerically, for example [\000-\037]. Ranges can include any characters that are valid for the current mode. - There is a special case in EBCDIC environments for ranges whose end + There is a special case in EBCDIC environments for ranges whose end points are both specified as literal letters in the same case. For com- - patibility with Perl, EBCDIC code points within the range that are not - letters are omitted. For example, [h-k] matches only four characters, + patibility with Perl, EBCDIC code points within the range that are not + letters are omitted. For example, [h-k] matches only four characters, even though the codes for h and k are 0x88 and 0x92, a range of 11 code - points. However, if the range is specified numerically, for example, + points. However, if the range is specified numerically, for example, [\x88-\x92] or [h-\x92], all code points are included. If a range that includes letters is used when caseless matching is set, it matches the letters in either case. For example, [W-c] is equivalent - to [][\\^_`wxyzabc], matched caselessly, and in a non-UTF mode, if - character tables for a French locale are in use, [\xc8-\xcb] matches + to [][\\^_`wxyzabc], matched caselessly, and in a non-UTF mode, if + character tables for a French locale are in use, [\xc8-\xcb] matches accented E characters in both cases. - The character escape sequences \d, \D, \h, \H, \p, \P, \s, \S, \v, \V, + The character escape sequences \d, \D, \h, \H, \p, \P, \s, \S, \v, \V, \w, and \W may appear in a character class, and add the characters that - they match to the class. For example, [\dABCDEF] matches any hexadeci- - mal digit. In UTF modes, the PCRE2_UCP option affects the meanings of - \d, \s, \w and their upper case partners, just as it does when they - appear outside a character class, as described in the section entitled + they match to the class. For example, [\dABCDEF] matches any hexadeci- + mal digit. In UTF modes, the PCRE2_UCP option affects the meanings of + \d, \s, \w and their upper case partners, just as it does when they + appear outside a character class, as described in the section entitled "Generic character types" above. The escape sequence \b has a different - meaning inside a character class; it matches the backspace character. - The sequences \B, \N, \R, and \X are not special inside a character - class. Like any other unrecognized escape sequences, they cause an + meaning inside a character class; it matches the backspace character. + The sequences \B, \N, \R, and \X are not special inside a character + class. Like any other unrecognized escape sequences, they cause an error. - A circumflex can conveniently be used with the upper case character - types to specify a more restricted set of characters than the matching - lower case type. For example, the class [^\W_] matches any letter or + A circumflex can conveniently be used with the upper case character + types to specify a more restricted set of characters than the matching + lower case type. For example, the class [^\W_] matches any letter or digit, but not underscore, whereas [\w] includes underscore. A positive character class should be read as "something OR something OR ..." and a negative class as "NOT something AND NOT something AND NOT ...". - The only metacharacters that are recognized in character classes are - backslash, hyphen (only where it can be interpreted as specifying a - range), circumflex (only at the start), opening square bracket (only - when it can be interpreted as introducing a POSIX class name, or for a - special compatibility feature - see the next two sections), and the + The only metacharacters that are recognized in character classes are + backslash, hyphen (only where it can be interpreted as specifying a + range), circumflex (only at the start), opening square bracket (only + when it can be interpreted as introducing a POSIX class name, or for a + special compatibility feature - see the next two sections), and the terminating closing square bracket. However, escaping other non- alphanumeric characters does no harm. @@ -6268,7 +6364,7 @@ SQUARE BRACKETS AND CHARACTER CLASSES POSIX CHARACTER CLASSES Perl supports the POSIX notation for character classes. This uses names - enclosed by [: and :] within the enclosing square brackets. PCRE2 also + enclosed by [: and :] within the enclosing square brackets. PCRE2 also supports this notation. For example, [01[:alpha:]%] @@ -6291,13 +6387,13 @@ POSIX CHARACTER CLASSES word "word" characters (same as \w) xdigit hexadecimal digits - The default "space" characters are HT (9), LF (10), VT (11), FF (12), - CR (13), and space (32). If locale-specific matching is taking place, - the list of space characters may be different; there may be fewer or + The default "space" characters are HT (9), LF (10), VT (11), FF (12), + CR (13), and space (32). If locale-specific matching is taking place, + the list of space characters may be different; there may be fewer or more of them. "Space" and \s match the same set of characters. - The name "word" is a Perl extension, and "blank" is a GNU extension - from Perl 5.8. Another Perl extension is negation, which is indicated + The name "word" is a Perl extension, and "blank" is a GNU extension + from Perl 5.8. Another Perl extension is negation, which is indicated by a ^ character after the colon. For example, [12[:^digit:]] @@ -6308,9 +6404,9 @@ POSIX CHARACTER CLASSES By default, characters with values greater than 127 do not match any of the POSIX character classes, although this may be different for charac- - ters in the range 128-255 when locale-specific matching is happening. - However, if the PCRE2_UCP option is passed to pcre2_compile(), some of - the classes are changed so that Unicode character properties are used. + ters in the range 128-255 when locale-specific matching is happening. + However, if the PCRE2_UCP option is passed to pcre2_compile(), some of + the classes are changed so that Unicode character properties are used. This is achieved by replacing certain POSIX classes with other sequences, as follows: @@ -6324,10 +6420,10 @@ POSIX CHARACTER CLASSES [:upper:] becomes \p{Lu} [:word:] becomes \p{Xwd} - Negated versions, such as [:^alpha:] use \P instead of \p. Three other + Negated versions, such as [:^alpha:] use \P instead of \p. Three other POSIX classes are handled specially in UCP mode: - [:graph:] This matches characters that have glyphs that mark the page + [:graph:] This matches characters that have glyphs that mark the page when printed. In Unicode property terms, it matches all char- acters with the L, M, N, P, S, or Cf properties, except for: @@ -6336,58 +6432,58 @@ POSIX CHARACTER CLASSES U+2066 - U+2069 Various "isolate"s - [:print:] This matches the same characters as [:graph:] plus space - characters that are not controls, that is, characters with + [:print:] This matches the same characters as [:graph:] plus space + characters that are not controls, that is, characters with the Zs property. [:punct:] This matches all characters that have the Unicode P (punctua- - tion) property, plus those characters with code points less + tion) property, plus those characters with code points less than 256 that have the S (Symbol) property. - The other POSIX classes are unchanged, and match only characters with + The other POSIX classes are unchanged, and match only characters with code points less than 256. COMPATIBILITY FEATURE FOR WORD BOUNDARIES - In the POSIX.2 compliant library that was included in 4.4BSD Unix, the - ugly syntax [[:<:]] and [[:>:]] is used for matching "start of word" + In the POSIX.2 compliant library that was included in 4.4BSD Unix, the + ugly syntax [[:<:]] and [[:>:]] is used for matching "start of word" and "end of word". PCRE2 treats these items as follows: [[:<:]] is converted to \b(?=\w) [[:>:]] is converted to \b(?<=\w) Only these exact character sequences are recognized. A sequence such as - [a[:<:]b] provokes error for an unrecognized POSIX class name. This - support is not compatible with Perl. It is provided to help migrations + [a[:<:]b] provokes error for an unrecognized POSIX class name. This + support is not compatible with Perl. It is provided to help migrations from other environments, and is best not used in any new patterns. Note - that \b matches at the start and the end of a word (see "Simple asser- - tions" above), and in a Perl-style pattern the preceding or following - character normally shows which is wanted, without the need for the - assertions that are used above in order to give exactly the POSIX be- + that \b matches at the start and the end of a word (see "Simple asser- + tions" above), and in a Perl-style pattern the preceding or following + character normally shows which is wanted, without the need for the + assertions that are used above in order to give exactly the POSIX be- haviour. VERTICAL BAR - Vertical bar characters are used to separate alternative patterns. For + Vertical bar characters are used to separate alternative patterns. For example, the pattern gilbert|sullivan - matches either "gilbert" or "sullivan". Any number of alternatives may - appear, and an empty alternative is permitted (matching the empty + matches either "gilbert" or "sullivan". Any number of alternatives may + appear, and an empty alternative is permitted (matching the empty string). The matching process tries each alternative in turn, from left - to right, and the first one that succeeds is used. If the alternatives - are within a subpattern (defined below), "succeeds" means matching the + to right, and the first one that succeeds is used. If the alternatives + are within a subpattern (defined below), "succeeds" means matching the rest of the main pattern as well as the alternative in the subpattern. INTERNAL OPTION SETTING - The settings of the PCRE2_CASELESS, PCRE2_MULTILINE, PCRE2_DOTALL, and - PCRE2_EXTENDED options (which are Perl-compatible) can be changed from - within the pattern by a sequence of Perl option letters enclosed + The settings of the PCRE2_CASELESS, PCRE2_MULTILINE, PCRE2_DOTALL, and + PCRE2_EXTENDED options (which are Perl-compatible) can be changed from + within the pattern by a sequence of Perl option letters enclosed between "(?" and ")". The option letters are i for PCRE2_CASELESS @@ -6398,43 +6494,43 @@ INTERNAL OPTION SETTING For example, (?im) sets caseless, multiline matching. It is also possi- ble to unset these options by preceding the letter with a hyphen, and a combined setting and unsetting such as (?im-sx), which sets PCRE2_CASE- - LESS and PCRE2_MULTILINE while unsetting PCRE2_DOTALL and - PCRE2_EXTENDED, is also permitted. If a letter appears both before and - after the hyphen, the option is unset. An empty options setting "(?)" + LESS and PCRE2_MULTILINE while unsetting PCRE2_DOTALL and + PCRE2_EXTENDED, is also permitted. If a letter appears both before and + after the hyphen, the option is unset. An empty options setting "(?)" is allowed. Needless to say, it has no effect. - The PCRE2-specific options PCRE2_DUPNAMES and PCRE2_UNGREEDY can be - changed in the same way as the Perl-compatible options by using the + The PCRE2-specific options PCRE2_DUPNAMES and PCRE2_UNGREEDY can be + changed in the same way as the Perl-compatible options by using the characters J and U respectively. - When one of these option changes occurs at top level (that is, not - inside subpattern parentheses), the change applies to the remainder of + When one of these option changes occurs at top level (that is, not + inside subpattern parentheses), the change applies to the remainder of the pattern that follows. If the change is placed right at the start of - a pattern, PCRE2 extracts it into the global options (and it will - therefore show up in data extracted by the pcre2_pattern_info() func- + a pattern, PCRE2 extracts it into the global options (and it will + therefore show up in data extracted by the pcre2_pattern_info() func- tion). - An option change within a subpattern (see below for a description of - subpatterns) affects only that part of the subpattern that follows it, + An option change within a subpattern (see below for a description of + subpatterns) affects only that part of the subpattern that follows it, so (a(?i)b)c - matches abc and aBc and no other strings (assuming PCRE2_CASELESS is - not used). By this means, options can be made to have different set- + matches abc and aBc and no other strings (assuming PCRE2_CASELESS is + not used). By this means, options can be made to have different set- tings in different parts of the pattern. Any changes made in one alter- native do carry on into subsequent branches within the same subpattern. For example, (a(?i)b|c) - matches "ab", "aB", "c", and "C", even though when matching "C" the - first branch is abandoned before the option setting. This is because - the effects of option settings happen at compile time. There would be + matches "ab", "aB", "c", and "C", even though when matching "C" the + first branch is abandoned before the option setting. This is because + the effects of option settings happen at compile time. There would be some very weird behaviour otherwise. - As a convenient shorthand, if any option settings are required at the - start of a non-capturing subpattern (see the next section), the option + As a convenient shorthand, if any option settings are required at the + start of a non-capturing subpattern (see the next section), the option letters may appear between the "?" and the ":". Thus the two patterns (?i:saturday|sunday) @@ -6442,14 +6538,14 @@ INTERNAL OPTION SETTING match exactly the same set of strings. - Note: There are other PCRE2-specific options that can be set by the + Note: There are other PCRE2-specific options that can be set by the application when the compiling function is called. The pattern can con- - tain special leading sequences such as (*CRLF) to override what the - application has set or what has been defaulted. Details are given in - the section entitled "Newline sequences" above. There are also the - (*UTF) and (*UCP) leading sequences that can be used to set UTF and - Unicode property modes; they are equivalent to setting the PCRE2_UTF - and PCRE2_UCP options, respectively. However, the application can set + tain special leading sequences such as (*CRLF) to override what the + application has set or what has been defaulted. Details are given in + the section entitled "Newline sequences" above. There are also the + (*UTF) and (*UCP) leading sequences that can be used to set UTF and + Unicode property modes; they are equivalent to setting the PCRE2_UTF + and PCRE2_UCP options, respectively. However, the application can set the PCRE2_NEVER_UTF and PCRE2_NEVER_UCP options, which lock out the use of the (*UTF) and (*UCP) sequences. @@ -6463,18 +6559,18 @@ SUBPATTERNS cat(aract|erpillar|) - matches "cataract", "caterpillar", or "cat". Without the parentheses, + matches "cataract", "caterpillar", or "cat". Without the parentheses, it would match "cataract", "erpillar" or an empty string. - 2. It sets up the subpattern as a capturing subpattern. This means + 2. It sets up the subpattern as a capturing subpattern. This means that, when the whole pattern matches, the portion of the subject string - that matched the subpattern is passed back to the caller, separately - from the portion that matched the whole pattern. (This applies only to - the traditional matching function; the DFA matching function does not + that matched the subpattern is passed back to the caller, separately + from the portion that matched the whole pattern. (This applies only to + the traditional matching function; the DFA matching function does not support capturing.) Opening parentheses are counted from left to right (starting from 1) to - obtain numbers for the capturing subpatterns. For example, if the + obtain numbers for the capturing subpatterns. For example, if the string "the red king" is matched against the pattern the ((red|white) (king|queen)) @@ -6482,12 +6578,12 @@ SUBPATTERNS the captured substrings are "red king", "red", and "king", and are num- bered 1, 2, and 3, respectively. - The fact that plain parentheses fulfil two functions is not always - helpful. There are often times when a grouping subpattern is required - without a capturing requirement. If an opening parenthesis is followed - by a question mark and a colon, the subpattern does not do any captur- - ing, and is not counted when computing the number of any subsequent - capturing subpatterns. For example, if the string "the white queen" is + The fact that plain parentheses fulfil two functions is not always + helpful. There are often times when a grouping subpattern is required + without a capturing requirement. If an opening parenthesis is followed + by a question mark and a colon, the subpattern does not do any captur- + ing, and is not counted when computing the number of any subsequent + capturing subpatterns. For example, if the string "the white queen" is matched against the pattern the ((?:red|white) (king|queen)) @@ -6495,37 +6591,37 @@ SUBPATTERNS the captured substrings are "white queen" and "queen", and are numbered 1 and 2. The maximum number of capturing subpatterns is 65535. - As a convenient shorthand, if any option settings are required at the - start of a non-capturing subpattern, the option letters may appear + As a convenient shorthand, if any option settings are required at the + start of a non-capturing subpattern, the option letters may appear between the "?" and the ":". Thus the two patterns (?i:saturday|sunday) (?:(?i)saturday|sunday) match exactly the same set of strings. Because alternative branches are - tried from left to right, and options are not reset until the end of - the subpattern is reached, an option setting in one branch does affect - subsequent branches, so the above patterns match "SUNDAY" as well as + tried from left to right, and options are not reset until the end of + the subpattern is reached, an option setting in one branch does affect + subsequent branches, so the above patterns match "SUNDAY" as well as "Saturday". DUPLICATE SUBPATTERN NUMBERS Perl 5.10 introduced a feature whereby each alternative in a subpattern - uses the same numbers for its capturing parentheses. Such a subpattern - starts with (?| and is itself a non-capturing subpattern. For example, + uses the same numbers for its capturing parentheses. Such a subpattern + starts with (?| and is itself a non-capturing subpattern. For example, consider this pattern: (?|(Sat)ur|(Sun))day - Because the two alternatives are inside a (?| group, both sets of cap- - turing parentheses are numbered one. Thus, when the pattern matches, - you can look at captured substring number one, whichever alternative - matched. This construct is useful when you want to capture part, but + Because the two alternatives are inside a (?| group, both sets of cap- + turing parentheses are numbered one. Thus, when the pattern matches, + you can look at captured substring number one, whichever alternative + matched. This construct is useful when you want to capture part, but not all, of one of a number of alternatives. Inside a (?| group, paren- - theses are numbered as usual, but the number is reset at the start of - each branch. The numbers of any capturing parentheses that follow the - subpattern start after the highest number used in any branch. The fol- + theses are numbered as usual, but the number is reset at the start of + each branch. The numbers of any capturing parentheses that follow the + subpattern start after the highest number used in any branch. The fol- lowing example is taken from the Perl documentation. The numbers under- neath show in which buffer the captured content will be stored. @@ -6533,18 +6629,21 @@ DUPLICATE SUBPATTERN NUMBERS / ( a ) (?| x ( y ) z | (p (q) r) | (t) u (v) ) ( z ) /x # 1 2 2 3 2 3 4 - A back reference to a numbered subpattern uses the most recent value - that is set for that number by any subpattern. The following pattern + A back reference to a numbered subpattern uses the most recent value + that is set for that number by any subpattern. The following pattern matches "abcabc" or "defdef": /(?|(abc)|(def))\1/ - In contrast, a subroutine call to a numbered subpattern always refers - to the first one in the pattern with the given number. The following + In contrast, a subroutine call to a numbered subpattern always refers + to the first one in the pattern with the given number. The following pattern matches "abcabc" or "defabc": /(?|(abc)|(def))(?1)/ + A relative reference such as (?-1) is no different: it is just a conve- + nient way of computing an absolute group number. + If a condition test for a subpattern's having matched refers to a non- unique number, the test is true if any of the subpatterns of that num- ber have matched. @@ -7444,6 +7543,20 @@ RECURSIVE PATTERNS words, a negative number counts capturing parentheses leftwards from the point at which it is encountered. + Be aware however, that if duplicate subpattern numbers are in use, rel- + ative references refer to the earliest subpattern with the appropriate + number. Consider, for example: + + (?|(a)|(b)) (c) (?-2) + + The first two capturing groups (a) and (b) are both numbered 1, and + group (c) is number 2. When the reference (?-2) is encountered, the + second most recently opened parentheses has the number 1, but it is the + first such group (the (a) group) to which the recursion refers. This + would be the same if an absolute reference (?1) was used. In other + words, relative references are just a shorthand for computing a group + number. + It is also possible to refer to subsequently opened parentheses, by writing references such as (?+2). However, these cannot be recursive because the reference is not inside the parentheses that are refer- @@ -8141,11 +8254,11 @@ AUTHOR REVISION - Last updated: 01 November 2015 + Last updated: 13 November 2015 Copyright (c) 1997-2015 University of Cambridge. ------------------------------------------------------------------------------ - - + + PCRE2PERFORM(3) Library Functions Manual PCRE2PERFORM(3) @@ -8317,8 +8430,8 @@ REVISION Last updated: 02 January 2015 Copyright (c) 1997-2015 University of Cambridge. ------------------------------------------------------------------------------ - - + + PCRE2POSIX(3) Library Functions Manual PCRE2POSIX(3) @@ -8534,7 +8647,9 @@ MATCHING A PATTERN IEEE Standard 1003.2 (POSIX.2), and should be used with caution in software intended to be portable to other systems. Note that a non-zero rm_so does not imply REG_NOTBOL; REG_STARTEND affects only the location - of the string, not how it is matched. + of the string, not how it is matched. Setting REG_STARTEND and passing + pmatch as NULL are mutually exclusive; the error REG_INVARG is + returned. If the pattern was compiled with the REG_NOSUB flag, no data about any matched strings is returned. The nmatch and pmatch arguments of @@ -8587,11 +8702,11 @@ AUTHOR REVISION - Last updated: 30 October 2015 + Last updated: 29 November 2015 Copyright (c) 1997-2015 University of Cambridge. ------------------------------------------------------------------------------ - - + + PCRE2SAMPLE(3) Library Functions Manual PCRE2SAMPLE(3) @@ -8839,8 +8954,8 @@ REVISION Last updated: 03 November 2015 Copyright (c) 1997-2015 University of Cambridge. ------------------------------------------------------------------------------ - - + + PCRE2STACK(3) Library Functions Manual PCRE2STACK(3) @@ -9005,8 +9120,8 @@ REVISION Last updated: 21 November 2014 Copyright (c) 1997-2014 University of Cambridge. ------------------------------------------------------------------------------ - - + + PCRE2SYNTAX(3) Library Functions Manual PCRE2SYNTAX(3) @@ -9441,8 +9556,8 @@ REVISION Last updated: 16 October 2015 Copyright (c) 1997-2015 University of Cambridge. ------------------------------------------------------------------------------ - - + + PCRE2UNICODE(3) Library Functions Manual PCRE2UNICODE(3) @@ -9680,5 +9795,5 @@ REVISION Last updated: 16 October 2015 Copyright (c) 1997-2015 University of Cambridge. ------------------------------------------------------------------------------ - - + + diff --git a/doc/pcre2_set_max_pattern_length.3 b/doc/pcre2_set_max_pattern_length.3 index af4f58c..1367b96 100644 --- a/doc/pcre2_set_max_pattern_length.3 +++ b/doc/pcre2_set_max_pattern_length.3 @@ -14,7 +14,7 @@ PCRE2 - Perl-compatible regular expressions (revised API) .SH DESCRIPTION .rs .sp -This function sets, in a compile context, the maximum length (in code units) of +This function sets, in a compile context, the maximum length (in code units) of the pattern that can be compiled. The result is always zero. .P There is a complete description of the PCRE2 native API in the diff --git a/doc/pcre2_substitute.3 b/doc/pcre2_substitute.3 index 74b5849..e69e0cc 100644 --- a/doc/pcre2_substitute.3 +++ b/doc/pcre2_substitute.3 @@ -58,9 +58,9 @@ The options are: PCRE2_UTF was set at compile time) PCRE2_SUBSTITUTE_EXTENDED Do extended replacement processing PCRE2_SUBSTITUTE_GLOBAL Replace all occurrences in the subject - PCRE2_SUBSTITUTE_OVERFLOW_LENGTH If overflow, compute needed length - PCRE2_SUBSTITUTE_UNKNOWN_UNSET Treat unknown group as unset - PCRE2_SUBSTITUTE_UNSET_EMPTY Simple unset insert = empty string + PCRE2_SUBSTITUTE_OVERFLOW_LENGTH If overflow, compute needed length + PCRE2_SUBSTITUTE_UNKNOWN_UNSET Treat unknown group as unset + PCRE2_SUBSTITUTE_UNSET_EMPTY Simple unset insert = empty string .sp The function returns the number of substitutions, which may be zero if there were no matches. The result can be greater than one only when diff --git a/doc/pcre2api.3 b/doc/pcre2api.3 index f1de15d..b29f7b0 100644 --- a/doc/pcre2api.3 +++ b/doc/pcre2api.3 @@ -1,4 +1,4 @@ -.TH PCRE2API 3 "12 December 2015" "PCRE2 10.21" +.TH PCRE2API 3 "16 December 2015" "PCRE2 10.21" .SH NAME PCRE2 - Perl-compatible regular expressions (revised API) .sp @@ -570,7 +570,7 @@ of the following compile-time parameters: PCRE2's character tables The newline character sequence The compile time nested parentheses limit - The maximum length of the pattern string + The maximum length of the pattern string An external function for stack checking .sp A compile context is also required if you are using custom memory management. @@ -618,10 +618,10 @@ in the current locale. .B " PCRE2_SIZE \fIvalue\fP);" .fi .sp -This sets a maximum length, in code units, for the pattern string that is to be -compiled. If the pattern is longer, an error is generated. This facility is -provided so that applications that accept patterns from external sources can -limit their size. The default is the largest number that a PCRE2_SIZE variable +This sets a maximum length, in code units, for the pattern string that is to be +compiled. If the pattern is longer, an error is generated. This facility is +provided so that applications that accept patterns from external sources can +limit their size. The default is the largest number that a PCRE2_SIZE variable can hold, which is effectively unlimited. .sp .nf @@ -678,8 +678,8 @@ of the following match-time parameters: .sp A callout function The offset limit for matching an unanchored pattern - The limit for calling \fImatch()\fP - The limit for calling \fImatch()\fP recursively + The limit for calling \fBmatch()\fP (see below) + The limit for calling \fBmatch()\fP recursively .sp A match context is also required if you are using custom memory management. If none of these apply, just pass NULL as the context argument of @@ -736,7 +736,7 @@ PCRE2_USE_OFFSET_LIMIT is not set, an error is generated. .P The offset limit facility can be used to track progress when searching large subject strings. See also the PCRE2_FIRSTLINE option, which requires a match to -start within the first line of the subject. If this is set with an offset +start within the first line of the subject. If this is set with an offset limit, a match must occur in the first line and also within the offset limit. In other words, whichever limit comes first is used. .sp @@ -1228,7 +1228,7 @@ This option locks out the use of \eC in the pattern that is being compiled. This escape can cause unpredictable behaviour in UTF-8 or UTF-16 modes, because it may leave the current matching point in the middle of a multi-code-unit character. This option may be useful in applications that process patterns from -external sources. Note that there is also a build-time option that permanently +external sources. Note that there is also a build-time option that permanently locks out the use of \eC. .sp PCRE2_NEVER_UCP @@ -1565,7 +1565,7 @@ are as follows: Return a copy of the pattern's options. The third argument should point to a \fBuint32_t\fP variable. PCRE2_INFO_ARGOPTIONS returns exactly the options that were passed to \fBpcre2_compile()\fP, whereas PCRE2_INFO_ALLOPTIONS returns -the compile options as modified by any top-level option settings such as (*UTF) +the compile options as modified by any top-level option settings such as (*UTF) at the start of the pattern itself. For example, if the pattern /(*UTF)abc/ is compiled with the PCRE2_EXTENDED option, the result is PCRE2_EXTENDED and PCRE2_UTF. @@ -1611,8 +1611,9 @@ matches only CR, LF, or CRLF. .sp PCRE2_INFO_CAPTURECOUNT .sp -Return the number of capturing subpatterns in the pattern. The third argument -should point to an \fBuint32_t\fP variable. +Return the highest capturing subpattern number in the pattern. In patterns +where (?| is not used, this is also the total number of capturing subpatterns. +The third argument should point to an \fBuint32_t\fP variable. .sp PCRE2_INFO_FIRSTBITMAP .sp @@ -1629,10 +1630,8 @@ returned. Otherwise NULL is returned. The third argument should point to an .sp Return information about the first code unit of any matched string, for a non-anchored pattern. The third argument should point to an \fBuint32_t\fP -variable. -.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 +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 PCRE2_INFO_FIRSTCODEUNIT. If there is no fixed first value, but it is known that a match can occur only at the start of the subject or following a newline in the subject, 2 is returned. Otherwise, and for anchored @@ -1676,12 +1675,10 @@ Returns 1 if there is a rightmost literal code unit that must exist in any matched string, other than at its start. The third argument should point to an \fBuint32_t\fP variable. If there is no such value, 0 is returned. When 1 is returned, the code unit value itself can be retrieved using -PCRE2_INFO_LASTCODEUNIT. -.P -For anchored patterns, a last literal value is recorded only if it follows -something of variable length. For example, for the pattern /^a\ed+z\ed+/ the -returned value is 1 (with "z" returned from PCRE2_INFO_LASTCODEUNIT), but for -/^a\edz\ed/ the returned value is 0. +PCRE2_INFO_LASTCODEUNIT. For anchored patterns, a last literal value is +recorded only if it follows something of variable length. For example, for the +pattern /^a\ed+z\ed+/ the returned value is 1 (with "z" returned from +PCRE2_INFO_LASTCODEUNIT), but for /^a\edz\ed/ the returned value is 0. .sp PCRE2_INFO_LASTCODEUNIT .sp @@ -1693,9 +1690,9 @@ value, 0 is returned. PCRE2_INFO_MATCHEMPTY .sp Return 1 if the pattern might match an empty string, otherwise 0. The third -argument should point to an \fBuint32_t\fP variable. When a pattern contains -recursive subroutine calls it is not always possible to determine whether or -not it can match an empty string. PCRE2 takes a cautious approach and returns 1 +argument should point to an \fBuint32_t\fP variable. When a pattern contains +recursive subroutine calls it is not always possible to determine whether or +not it can match an empty string. PCRE2 takes a cautious approach and returns 1 in such cases. .sp PCRE2_INFO_MATCHLIMIT @@ -2181,9 +2178,19 @@ standard convention for the operating system. The default can be overridden in a .\" HTML <a href="#compilecontext"> .\" </a> -compile context. +compile context +.\" +by calling \fBpcre2_set_newline()\fP. It can also be overridden by starting a +pattern string with, for example, (*CRLF), as described in the +.\" HTML <a href="pcre2pattern.html#newlines"> +.\" </a> +section on newline conventions .\" -During matching, the newline choice affects the behaviour of the dot, +in the +.\" HREF +\fBpcre2pattern\fP +.\" +page. During matching, the newline choice affects the behaviour of the dot, circumflex, and dollar metacharacters. It may also alter the way the match starting position is advanced after a match failure for an unanchored pattern. .P @@ -2229,18 +2236,7 @@ that do not cause substrings to be captured. The \fBpcre2_pattern_info()\fP function can be used to find out how many capturing subpatterns there are in a compiled pattern. .P -A successful match returns the overall matched string and any captured -substrings to the caller via a vector of PCRE2_SIZE values. This is called the -\fBovector\fP, and is contained within the -.\" HTML <a href="#matchdatablock"> -.\" </a> -match data block. -.\" -You can obtain direct access to the ovector by calling -\fBpcre2_get_ovector_pointer()\fP to find its address, and -\fBpcre2_get_ovector_count()\fP to find the number of pairs of values it -contains. Alternatively, you can use the auxiliary functions for accessing -captured substrings +You can use auxiliary functions for accessing captured substrings .\" HTML <a href="#extractbynumber"> .\" </a> by number @@ -2248,9 +2244,20 @@ by number or .\" HTML <a href="#extractbyname"> .\" </a> -by name +by name, +.\" +as described in sections below. +.P +Alternatively, you can make direct use of the vector of PCRE2_SIZE values, +called the \fBovector\fP, which contains the offsets of captured strings. It is +part of the +.\" HTML <a href="#matchdatablock"> +.\" </a> +match data block. .\" -(see below). +The function \fBpcre2_get_ovector_pointer()\fP returns the address of the +ovector, and \fBpcre2_get_ovector_count()\fP returns the number of pairs of +values it contains. .P Within the ovector, the first in each pair of values is set to the offset of the first code unit of a substring, and the second is set to the offset of the @@ -2334,7 +2341,12 @@ After a successful match, a partial match (PCRE2_ERROR_PARTIAL), or a failure to match (PCRE2_ERROR_NOMATCH), a (*MARK) name may be available, and \fBpcre2_get_mark()\fP can be called. It returns a pointer to the zero-terminated name, which is within the compiled pattern. Otherwise NULL is -returned. After a successful match, the (*MARK) name that is returned is the +returned. The length of the (*MARK) name (excluding the terminating zero) is +stored in the code unit that preceeds the name. You should use this instead of +relying on the terminating zero if the (*MARK) name might contain a binary +zero. +.P +After a successful match, the (*MARK) name that is returned is the last one encountered on the matching path through the pattern. After a "no match" or a partial match, the last encountered (*MARK) name is returned. For example, consider this pattern: @@ -2353,7 +2365,7 @@ different to the value of \fIovector[0]\fP if the pattern contains the \eK escape sequence. After a partial match, however, this value is always the same as \fIovector[0]\fP because \eK does not affect the result of a partial match. .P -After a UTF check failure, \fBpcre2_get_startchar()\fB can be used to obtain +After a UTF check failure, \fBpcre2_get_startchar()\fP can be used to obtain the code unit offset of the invalid UTF character. Details are given in the .\" HREF \fBpcre2unicode\fP @@ -2692,7 +2704,7 @@ same number causes an error at compile time. This function calls \fBpcre2_match()\fP and then makes a copy of the subject string in \fIoutputbuffer\fP, replacing the part that was matched with the \fIreplacement\fP string, whose length is supplied in \fBrlength\fP. This can -be given as PCRE2_ZERO_TERMINATED for a zero-terminated string. Matches in +be given as PCRE2_ZERO_TERMINATED for a zero-terminated string. Matches in which a \eK item in a lookahead in the pattern causes the match to end before it starts are not supported, and give rise to an error return. .P @@ -2706,7 +2718,7 @@ allocate memory for the compiled code. The \fIoutlengthptr\fP argument must point to a variable that contains the length, in code units, of the output buffer. If the function is successful, the value is updated to contain the length of the new string, excluding the -trailing zero that is automatically added. +trailing zero that is automatically added. .P If the function is not successful, the value set via \fIoutlengthptr\fP depends on the type of error. For syntax errors in the replacement string, the value is @@ -2754,7 +2766,7 @@ advanced by one character except when CRLF is a valid newline sequence and the next two characters are CR, LF. In this case, the current position is advanced by two characters. .P -PCRE2_SUBSTITUTE_OVERFLOW_LENGTH changes what happens when the output buffer is +PCRE2_SUBSTITUTE_OVERFLOW_LENGTH changes what happens when the output buffer is too small. The default action is to return PCRE2_ERROR_NOMEMORY immediately. If this option is set, however, \fBpcre2_substitute()\fP continues to go through the motions of matching and substituting (without, of course, writing anything) @@ -2762,15 +2774,15 @@ in order to compute the size of buffer that is needed. This value is passed back via the \fIoutlengthptr\fP variable, with the result of the function still being PCRE2_ERROR_NOMEMORY. .P -Passing a buffer size of zero is a permitted way of finding out how much memory -is needed for given substitution. However, this does mean that the entire -operation is carried out twice. Depending on the application, it may be more -efficient to allocate a large buffer and free the excess afterwards, instead of +Passing a buffer size of zero is a permitted way of finding out how much memory +is needed for given substitution. However, this does mean that the entire +operation is carried out twice. Depending on the application, it may be more +efficient to allocate a large buffer and free the excess afterwards, instead of using PCRE2_SUBSTITUTE_OVERFLOW_LENGTH. .P -PCRE2_SUBSTITUTE_UNKNOWN_UNSET causes references to capturing groups that do -not appear in the pattern to be treated as unset groups. This option should be -used with care, because it means that a typo in a group name or number no +PCRE2_SUBSTITUTE_UNKNOWN_UNSET causes references to capturing groups that do +not appear in the pattern to be treated as unset groups. This option should be +used with care, because it means that a typo in a group name or number no longer causes the PCRE2_ERROR_NOSUBSTRING error. .P PCRE2_SUBSTITUTE_UNSET_EMPTY causes unset capturing groups (including unknown @@ -2828,8 +2840,8 @@ string remains in force afterwards, as shown in this \fBpcre2test\fP example: somebody 1: HELLO .sp -The PCRE2_SUBSTITUTE_UNSET_EMPTY option does not affect these extended -substitutions. However, PCRE2_SUBSTITUTE_UNKNOWN_UNSET does cause unknown +The PCRE2_SUBSTITUTE_UNSET_EMPTY option does not affect these extended +substitutions. However, PCRE2_SUBSTITUTE_UNKNOWN_UNSET does cause unknown groups in the extended syntax forms to be treated as unset. .P If successful, \fBpcre2_substitute()\fP returns the number of replacements that @@ -2838,7 +2850,7 @@ were made. This may be zero if no matches were found, and is never greater than .P In the event of an error, a negative error code is returned. Except for PCRE2_ERROR_NOMATCH (which is never returned), errors from \fBpcre2_match()\fP -are passed straight back. +are passed straight back. .P PCRE2_ERROR_NOSUBSTRING is returned for a non-existent substring insertion, unless PCRE2_SUBSTITUTE_UNKNOWN_UNSET is set. @@ -2849,7 +2861,7 @@ unknown substring when PCRE2_SUBSTITUTE_UNKNOWN_UNSET is set) when the simple .P PCRE2_ERROR_NOMEMORY is returned if the output buffer is not big enough. If the PCRE2_SUBSTITUTE_OVERFLOW_LENGTH option is set, the size of buffer that is -needed is returned via \fIoutlengthptr\fP. Note that this does not happen by +needed is returned via \fIoutlengthptr\fP. Note that this does not happen by default. .P PCRE2_ERROR_BADREPLACEMENT is used for miscellaneous syntax errors in the @@ -2857,7 +2869,7 @@ replacement string, with more particular errors being PCRE2_ERROR_BADREPESCAPE (invalid escape sequence), PCRE2_ERROR_REPMISSING_BRACE (closing curly bracket not found), PCRE2_BADSUBSTITUTION (syntax error in extended group substitution), and PCRE2_BADSUBPATTERN (the pattern match ended before it -started, which can happen if \eK is used in an assertion). +started, which can happen if \eK is used in an assertion). .P As for all PCRE2 errors, a text message that describes the error can be obtained by calling \fBpcre2_get_error_message()\fP. @@ -2901,14 +2913,14 @@ first and last entries in the name-to-number table for the given name, and the function returns the length of each entry in code units. In both cases, PCRE2_ERROR_NOSUBSTRING is returned if there are no entries for the given name. .P -The format of the name table is described above in the section entitled -\fIInformation about a pattern\fP +The format of the name table is described .\" HTML <a href="#infoaboutpattern"> .\" </a> -above. +above .\" -Given all the relevant entries for the name, you can extract each of their -numbers, and hence the captured data. +in the section entitled \fIInformation about a pattern\fP. Given all the +relevant entries for the name, you can extract each of their numbers, and hence +the captured data. . . .SH "FINDING ALL POSSIBLE MATCHES AT ONE POSITION" @@ -3154,6 +3166,6 @@ Cambridge, England. .rs .sp .nf -Last updated: 21 December 2015 +Last updated: 16 December 2015 Copyright (c) 1997-2015 University of Cambridge. .fi diff --git a/doc/pcre2limits.3 b/doc/pcre2limits.3 index 0c8272b..a5bab81 100644 --- a/doc/pcre2limits.3 +++ b/doc/pcre2limits.3 @@ -20,8 +20,8 @@ documentation for details. In these cases the limit is substantially larger. However, the speed of execution is slower. In the 32-bit library, the internal linkage size is always 4. .P -The maximum length of a source pattern string is essentially unlimited; it is -the largest number a PCRE2_SIZE variable can hold. However, the program that +The maximum length of a source pattern string is essentially unlimited; it is +the largest number a PCRE2_SIZE variable can hold. However, the program that calls \fBpcre2_compile()\fP can specify a smaller limit. .P The maximum length (in code units) of a subject string is one less than the diff --git a/doc/pcre2pattern.3 b/doc/pcre2pattern.3 index 019a7a5..8d0e9df 100644 --- a/doc/pcre2pattern.3 +++ b/doc/pcre2pattern.3 @@ -1188,11 +1188,11 @@ When the newline convention (see .\" </a> "Newline conventions" .\" -below) recognizes the two-character sequence CRLF as a newline, this is -preferred, even if the single characters CR and LF are also recognized as +below) recognizes the two-character sequence CRLF as a newline, this is +preferred, even if the single characters CR and LF are also recognized as newlines. For example, if the newline convention is "any", a multiline mode circumflex matches before "xyz" in the string "abc\er\enxyz" rather than after -CR, even though CR on its own is a valid newline. (It also matches at the very +CR, even though CR on its own is a valid newline. (It also matches at the very start of the string, of course.) .P Note that the sequences \eA, \eZ, and \ez can be used to match the start and @@ -1245,7 +1245,7 @@ with \eC in UTF-8 or UTF-16 mode means that the rest of the string may start with a malformed UTF character. This has undefined results, because PCRE2 assumes that it is matching character by character in a valid UTF string (by default it checks the subject string's validity at the start of processing -unless the PCRE2_NO_UTF_CHECK option is used). +unless the PCRE2_NO_UTF_CHECK option is used). .P An application can lock out the use of \eC by setting the PCRE2_NEVER_BACKSLASH_C option when compiling a pattern. It is also possible to @@ -1257,9 +1257,9 @@ PCRE2 does not allow \eC to appear in lookbehind assertions (described below) .\" in a UTF mode, because this would make it impossible to calculate the length of -the lookbehind. Neither the alternative matching function -\fBpcre2_dfa_match()\fP not the JIT optimizer support \eC in a UTF mode. The -former gives a match-time error; the latter fails to optimize and so the match +the lookbehind. Neither the alternative matching function +\fBpcre2_dfa_match()\fP not the JIT optimizer support \eC in a UTF mode. The +former gives a match-time error; the latter fails to optimize and so the match is always run using the interpreter. .P In general, the \eC escape sequence is best avoided. However, one way of using @@ -1347,11 +1347,11 @@ inclusive. They can also be used for code points specified numerically, for example [\e000-\e037]. Ranges can include any characters that are valid for the current mode. .P -There is a special case in EBCDIC environments for ranges whose end points are -both specified as literal letters in the same case. For compatibility with -Perl, EBCDIC code points within the range that are not letters are omitted. For -example, [h-k] matches only four characters, even though the codes for h and k -are 0x88 and 0x92, a range of 11 code points. However, if the range is +There is a special case in EBCDIC environments for ranges whose end points are +both specified as literal letters in the same case. For compatibility with +Perl, EBCDIC code points within the range that are not letters are omitted. For +example, [h-k] matches only four characters, even though the codes for h and k +are 0x88 and 0x92, a range of 11 code points. However, if the range is specified numerically, for example, [\ex88-\ex92] or [h-\ex92], all code points are included. .P @@ -1683,7 +1683,7 @@ first one in the pattern with the given number. The following pattern matches .sp /(?|(abc)|(def))(?1)/ .sp -A relative reference such as (?-1) is no different: it is just a convenient way +A relative reference such as (?-1) is no different: it is just a convenient way of computing an absolute group number. .P If a @@ -2549,7 +2549,7 @@ For example: (?(VERSION>=10.4)yes|no) .sp This pattern matches "yes" if the PCRE2 version is greater or equal to 10.4, or -"no" otherwise. The fractional part of the version number may not contain more +"no" otherwise. The fractional part of the version number may not contain more than two digits. . . @@ -2667,21 +2667,21 @@ pattern above you can write (?-2) to refer to the second most recently opened parentheses preceding the recursion. In other words, a negative number counts capturing parentheses leftwards from the point at which it is encountered. .P -Be aware however, that if +Be aware however, that if .\" HTML <a href="#dupsubpatternnumber"> .\" </a> duplicate subpattern numbers .\" -are in use, relative references refer to the earliest subpattern with the +are in use, relative references refer to the earliest subpattern with the appropriate number. Consider, for example: .sp (?|(a)|(b)) (c) (?-2) .sp The first two capturing groups (a) and (b) are both numbered 1, and group (c) is number 2. When the reference (?-2) is encountered, the second most recently -opened parentheses has the number 1, but it is the first such group (the (a) -group) to which the recursion refers. This would be the same if an absolute -reference (?1) was used. In other words, relative references are just a +opened parentheses has the number 1, but it is the first such group (the (a) +group) to which the recursion refers. This would be the same if an absolute +reference (?1) was used. In other words, relative references are just a shorthand for computing a group number. .P It is also possible to refer to subsequently opened parentheses, by writing @@ -2988,13 +2988,13 @@ parenthesis followed by an asterisk. They are generally of the form (*VERB) or depending on whether or not a name is present. .P By default, for compatibility with Perl, a name is any sequence of characters -that does not include a closing parenthesis. The name is not processed in +that does not include a closing parenthesis. The name is not processed in any way, and it is not possible to include a closing parenthesis in the name. -However, if the PCRE2_ALT_VERBNAMES option is set, normal backslash processing -is applied to verb names and only an unescaped closing parenthesis terminates -the name. A closing parenthesis can be included in a name either as \e) or -between \eQ and \eE. If the PCRE2_EXTENDED option is set, unescaped whitespace -in verb names is skipped and #-comments are recognized, exactly as in the rest +However, if the PCRE2_ALT_VERBNAMES option is set, normal backslash processing +is applied to verb names and only an unescaped closing parenthesis terminates +the name. A closing parenthesis can be included in a name either as \e) or +between \eQ and \eE. If the PCRE2_EXTENDED option is set, unescaped whitespace +in verb names is skipped and #-comments are recognized, exactly as in the rest of the pattern. .P The maximum length of a name is 255 in the 8-bit library and 65535 in the diff --git a/doc/pcre2posix.3 b/doc/pcre2posix.3 index 4835766..833e96c 100644 --- a/doc/pcre2posix.3 +++ b/doc/pcre2posix.3 @@ -174,7 +174,7 @@ Default POSIX newline handling can be obtained by setting PCRE2_DOTALL and PCRE2_DOLLAR_ENDONLY when calling \fBpcre2_compile()\fP directly, but there is no way to make PCRE2 behave exactly as for the REG_NEWLINE action. When using the POSIX API, passing REG_NEWLINE to PCRE2's \fBregcomp()\fP function -causes PCRE2_MULTILINE to be passed to \fBpcre2_compile()\fP, and REG_DOTALL +causes PCRE2_MULTILINE to be passed to \fBpcre2_compile()\fP, and REG_DOTALL passes PCRE2_DOTALL. There is no way to pass PCRE2_DOLLAR_ENDONLY. . . @@ -211,7 +211,7 @@ to have a terminating NUL located at \fIstring\fP + \fIpmatch[0].rm_eo\fP IEEE Standard 1003.2 (POSIX.2), and should be used with caution in software intended to be portable to other systems. Note that a non-zero \fIrm_so\fP does not imply REG_NOTBOL; REG_STARTEND affects only the location of the string, not -how it is matched. Setting REG_STARTEND and passing \fIpmatch\fP as NULL are +how it is matched. Setting REG_STARTEND and passing \fIpmatch\fP as NULL are mutually exclusive; the error REG_INVARG is returned. .P If the pattern was compiled with the REG_NOSUB flag, no data about any matched diff --git a/doc/pcre2serialize.3 b/doc/pcre2serialize.3 index 14b82d1..69bcb18 100644 --- a/doc/pcre2serialize.3 +++ b/doc/pcre2serialize.3 @@ -140,13 +140,13 @@ on a system with different endianness. .P Decoded patterns can be used for matching in the usual way, and must be freed by calling \fBpcre2_code_free()\fP. However, be aware that there is a potential -race issue if you are using multiple patterns that were decoded from a single +race issue if you are using multiple patterns that were decoded from a single byte stream in a multithreaded application. A single copy of the character tables is used by all the decoded patterns and a reference count is used to arrange for its memory to be automatically freed when the last pattern is freed, but there is no locking on this reference count. Therefore, if you want to call \fBpcre2_code_free()\fP for these patterns in different threads, you -must arrange your own locking, and ensure that \fBpcre2_code_free()\fP cannot +must arrange your own locking, and ensure that \fBpcre2_code_free()\fP cannot be called by two threads at the same time. .P If a pattern was processed by \fBpcre2_jit_compile()\fP before being diff --git a/doc/pcre2syntax.3 b/doc/pcre2syntax.3 index 3c009ae..8be8b92 100644 --- a/doc/pcre2syntax.3 +++ b/doc/pcre2syntax.3 @@ -83,7 +83,7 @@ it matches a literal "u". .sp \eC is dangerous because it may leave the current matching point in the middle of a UTF-8 or UTF-16 character. The application can lock out the use of \eC by -setting the PCRE2_NEVER_BACKSLASH_C option. It is also possible to build PCRE2 +setting the PCRE2_NEVER_BACKSLASH_C option. It is also possible to build PCRE2 with the use of \eC permanently disabled. .P By default, \ed, \es, and \ew match only ASCII characters, even in UTF-8 mode diff --git a/doc/pcre2test.1 b/doc/pcre2test.1 index 1255d29..b8eef93 100644 --- a/doc/pcre2test.1 +++ b/doc/pcre2test.1 @@ -444,12 +444,12 @@ the start of a modifier list. For example: .sp abc\e=notbol,notempty .sp -If the subject string is empty and \e= is followed by whitespace, the line is +If the subject string is empty and \e= is followed by whitespace, the line is treated as a comment line, and is not used for matching. For example: .sp \e= This is a comment. abc\e= This is an invalid modifier list. -.sp +.sp A backslash followed by any other non-alphanumeric character just escapes that character. A backslash followed by anything else causes an error. However, if the very last character in the line is a backslash (and there is no modifier @@ -501,7 +501,7 @@ for a description of their effects. no_utf_check set PCRE2_NO_UTF_CHECK ucp set PCRE2_UCP ungreedy set PCRE2_UNGREEDY - use_offset_limit set PCRE2_USE_OFFSET_LIMIT + use_offset_limit set PCRE2_USE_OFFSET_LIMIT utf set PCRE2_UTF .sp As well as turning on the PCRE2_UTF option, the \fButf\fP modifier causes all @@ -528,7 +528,7 @@ about the pattern: jitfast use JIT fast path jitverify verify JIT use locale=<name> use this locale - max_pattern_length=<n> set the maximum pattern length + max_pattern_length=<n> set the maximum pattern length memory show memory used newline=<type> set newline type null_context compile with a NULL context @@ -608,9 +608,9 @@ by the item that follows it in the pattern. .SS "Passing a NULL context" .rs .sp -Normally, \fBpcre2test\fP passes a context block to \fBpcre2_compile()\fP. If -the \fBnull_context\fP modifier is set, however, NULL is passed. This is for -testing that \fBpcre2_compile()\fP behaves correctly in this case (it uses +Normally, \fBpcre2test\fP passes a context block to \fBpcre2_compile()\fP. If +the \fBnull_context\fP modifier is set, however, NULL is passed. This is for +testing that \fBpcre2_compile()\fP behaves correctly in this case (it uses default values). . . @@ -634,9 +634,9 @@ actual length of the pattern is passed. .rs .sp Some tests use long patterns that are very repetitive. Instead of creating a -very long input line for such a pattern, you can use a special repetition -feature, similar to the one described for subject lines above. If the -\fBexpand\fP modifier is present on a pattern, parts of the pattern that have +very long input line for such a pattern, you can use a special repetition +feature, similar to the one described for subject lines above. If the +\fBexpand\fP modifier is present on a pattern, parts of the pattern that have the form .sp \e[<characters>]{<count>} @@ -647,12 +647,12 @@ cannot be nested. An initial "\e[" sequence is recognized only if "]{" followed by decimal digits and "}" is found later in the pattern. If not, the characters remain in the pattern unaltered. .P -If part of an expanded pattern looks like an expansion, but is really part of -the actual pattern, unwanted expansion can be avoided by giving two values in -the quantifier. For example, \e[AB]{6000,6000} is not recognized as an +If part of an expanded pattern looks like an expansion, but is really part of +the actual pattern, unwanted expansion can be avoided by giving two values in +the quantifier. For example, \e[AB]{6000,6000} is not recognized as an expansion item. .P -If the \fBinfo\fP modifier is set on an expanded pattern, the result of the +If the \fBinfo\fP modifier is set on an expanded pattern, the result of the expansion is included in the information that is output. . . @@ -771,9 +771,9 @@ suite. .SS "Limiting the pattern length" .rs .sp -The \fBmax_pattern_length\fP modifier sets a limit, in code units, to the -length of pattern that \fBpcre2_compile()\fP will accept. Breaching the limit -causes a compilation error. The default is the largest number a PCRE2_SIZE +The \fBmax_pattern_length\fP modifier sets a limit, in code units, to the +length of pattern that \fBpcre2_compile()\fP will accept. Breaching the limit +causes a compilation error. The default is the largest number a PCRE2_SIZE variable can hold (essentially unlimited). . . @@ -797,13 +797,13 @@ modifiers set options for the \fBregcomp()\fP function: ucp REG_UCP ) the POSIX standard utf REG_UTF8 ) .sp -The \fBregerror_buffsize\fP modifier specifies a size for the error buffer that +The \fBregerror_buffsize\fP modifier specifies a size for the error buffer that is passed to \fBregerror()\fP in the event of a compilation error. For example: .sp /abc/posix,regerror_buffsize=20 .sp -This provides a means of testing the behaviour of \fBregerror()\fP when the -buffer is too small for the error message. If this modifier has not been set, a +This provides a means of testing the behaviour of \fBregerror()\fP when the +buffer is too small for the error message. If this modifier has not been set, a large buffer is used. .P The \fBaftertext\fP and \fBallaftertext\fP subject modifiers work as described @@ -863,9 +863,9 @@ compilation process. replace=<string> specify a replacement string startchar show starting character when relevant substitute_extended use PCRE2_SUBSTITUTE_EXTENDED - substitute_overflow_length use PCRE2_SUBSTITUTE_OVERFLOW_LENGTH - substitute_unknown_unset use PCRE2_SUBSTITUTE_UNKNOWN_UNSET - substitute_unset_empty use PCRE2_SUBSTITUTE_UNSET_EMPTY + substitute_overflow_length use PCRE2_SUBSTITUTE_OVERFLOW_LENGTH + substitute_unknown_unset use PCRE2_SUBSTITUTE_UNKNOWN_UNSET + substitute_unset_empty use PCRE2_SUBSTITUTE_UNSET_EMPTY .sp These modifiers may not appear in a \fB#pattern\fP command. If you want them as defaults, set them in a \fB#subject\fP command. @@ -956,7 +956,7 @@ pattern. mark show mark values match_limit=<n> set a match limit memory show memory usage - null_context match with a NULL context + null_context match with a NULL context offset=<n> set starting offset offset_limit=<n> set offset limit ovector=<n> set size of output vector @@ -965,9 +965,9 @@ pattern. startchar show startchar when relevant startoffset=<n> same as offset=<n> substitute_extedded use PCRE2_SUBSTITUTE_EXTENDED - substitute_overflow_length use PCRE2_SUBSTITUTE_OVERFLOW_LENGTH - substitute_unknown_unset use PCRE2_SUBSTITUTE_UNKNOWN_UNSET - substitute_unset_empty use PCRE2_SUBSTITUTE_UNSET_EMPTY + substitute_overflow_length use PCRE2_SUBSTITUTE_OVERFLOW_LENGTH + substitute_unknown_unset use PCRE2_SUBSTITUTE_UNKNOWN_UNSET + substitute_unset_empty use PCRE2_SUBSTITUTE_UNSET_EMPTY zero_terminate pass the subject as zero-terminated .sp The effects of these modifiers are described in the following sections. @@ -1102,7 +1102,7 @@ by name. If the \fBreplace\fP modifier is set, the \fBpcre2_substitute()\fP function is called instead of one of the matching functions. Note that replacement strings cannot contain commas, because a comma signifies the end of a modifier. This is -not thought to be an issue in a test program. +not thought to be an issue in a test program. .P Unlike subject strings, \fBpcre2test\fP does not process replacement strings for escape sequences. In UTF mode, a replacement string is checked to see if it @@ -1119,7 +1119,7 @@ for \fBpcre2_substitute()\fP: substitute_overflow_length PCRE2_SUBSTITUTE_OVERFLOW_LENGTH substitute_unknown_unset PCRE2_SUBSTITUTE_UNKNOWN_UNSET substitute_unset_empty PCRE2_SUBSTITUTE_UNSET_EMPTY -.sp +.sp .P After a successful substitution, the modified string is output, preceded by the number of replacements. This may be zero if there were no matches. Here is a @@ -1230,10 +1230,10 @@ matching starts. Its value is a number of code units, not characters. .SS "Setting an offset limit" .rs .sp -The \fBoffset_limit\fP modifier sets a limit for unanchored matches. If a match -cannot be found starting at or before this offset in the subject, a "no match" -return is given. The data value is a number of code units, not characters. When -this modifier is used, the \fBuse_offset_limit\fP modifier must have been set +The \fBoffset_limit\fP modifier sets a limit for unanchored matches. If a match +cannot be found starting at or before this offset in the subject, a "no match" +return is given. The data value is a number of code units, not characters. When +this modifier is used, the \fBuse_offset_limit\fP modifier must have been set for the pattern; if not, an error is generated. . . @@ -1273,8 +1273,8 @@ passing the replacement string as zero-terminated. Normally, \fBpcre2test\fP passes a context block to \fBpcre2_match()\fP, \fBpcre2_dfa_match()\fP or \fBpcre2_jit_match()\fP. If the \fBnull_context\fP modifier is set, however, NULL is passed. This is for testing that the matching -functions behave correctly in this case (they use default values). This -modifier cannot be used with the \fBfind_limits\fP modifier or when testing the +functions behave correctly in this case (they use default values). This +modifier cannot be used with the \fBfind_limits\fP modifier or when testing the substitution function. . . diff --git a/doc/pcre2test.txt b/doc/pcre2test.txt index e880b9a..d9dbc4d 100644 --- a/doc/pcre2test.txt +++ b/doc/pcre2test.txt @@ -797,14 +797,18 @@ PATTERN MODIFIERS with that pattern. They may not appear in #pattern commands. These mod- ifiers do not affect the compilation process. - aftertext show text after match - allaftertext show text after captures - allcaptures show all captures - allusedtext show all consulted text - /g global global matching - mark show mark values - replace=<string> specify a replacement string - startchar show starting character when relevant + aftertext show text after match + allaftertext show text after captures + allcaptures show all captures + allusedtext show all consulted text + /g global global matching + mark show mark values + replace=<string> specify a replacement string + startchar show starting character when relevant + substitute_extended use PCRE2_SUBSTITUTE_EXTENDED + substitute_overflow_length use PCRE2_SUBSTITUTE_OVERFLOW_LENGTH + substitute_unknown_unset use PCRE2_SUBSTITUTE_UNKNOWN_UNSET + substitute_unset_empty use PCRE2_SUBSTITUTE_UNSET_EMPTY These modifiers may not appear in a #pattern command. If you want them as defaults, set them in a #subject command. @@ -860,33 +864,38 @@ SUBJECT MODIFIERS line (see above), in which case they apply to every subject line that is matched against that pattern. - aftertext show text after match - allaftertext show text after captures - allcaptures show all captures - allusedtext show all consulted text (non-JIT only) - altglobal alternative global matching - callout_capture show captures at callout time - callout_data=<n> set a value to pass via callouts - callout_fail=<n>[:<m>] control callout failure - callout_none do not supply a callout function - copy=<number or name> copy captured substring - dfa use pcre2_dfa_match() - find_limits find match and recursion limits - get=<number or name> extract captured substring - getall extract all captured substrings - /g global global matching - jitstack=<n> set size of JIT stack - mark show mark values - match_limit=<n> set a match limit - memory show memory usage - null_context match with a NULL context - offset=<n> set starting offset - offset_limit=<n> set offset limit - ovector=<n> set size of output vector - recursion_limit=<n> set a recursion limit - replace=<string> specify a replacement string - startchar show startchar when relevant - zero_terminate pass the subject as zero-terminated + aftertext show text after match + allaftertext show text after captures + allcaptures show all captures + allusedtext show all consulted text (non-JIT only) + altglobal alternative global matching + callout_capture show captures at callout time + callout_data=<n> set a value to pass via callouts + callout_fail=<n>[:<m>] control callout failure + callout_none do not supply a callout function + copy=<number or name> copy captured substring + dfa use pcre2_dfa_match() + find_limits find match and recursion limits + get=<number or name> extract captured substring + getall extract all captured substrings + /g global global matching + jitstack=<n> set size of JIT stack + mark show mark values + match_limit=<n> set a match limit + memory show memory usage + null_context match with a NULL context + offset=<n> set starting offset + offset_limit=<n> set offset limit + ovector=<n> set size of output vector + recursion_limit=<n> set a recursion limit + replace=<string> specify a replacement string + startchar show startchar when relevant + startoffset=<n> same as offset=<n> + substitute_extedded use PCRE2_SUBSTITUTE_EXTENDED + substitute_overflow_length use PCRE2_SUBSTITUTE_OVERFLOW_LENGTH + substitute_unknown_unset use PCRE2_SUBSTITUTE_UNKNOWN_UNSET + substitute_unset_empty use PCRE2_SUBSTITUTE_UNSET_EMPTY + zero_terminate pass the subject as zero-terminated The effects of these modifiers are described in the following sections. @@ -1011,19 +1020,30 @@ SUBJECT MODIFIERS Testing the substitution function If the replace modifier is set, the pcre2_substitute() function is - called instead of one of the matching functions. Unlike subject - strings, pcre2test does not process replacement strings for escape - sequences. In UTF mode, a replacement string is checked to see if it is - a valid UTF-8 string. If so, it is correctly converted to a UTF string - of the appropriate code unit width. If it is not a valid UTF-8 string, - the individual code units are copied directly. This provides a means of - passing an invalid UTF-8 string for testing purposes. - - If the global modifier is set, PCRE2_SUBSTITUTE_GLOBAL is passed to - pcre2_substitute(). After a successful substitution, the modified - string is output, preceded by the number of replacements. This may be - zero if there were no matches. Here is a simple example of a substitu- - tion test: + called instead of one of the matching functions. Note that replacement + strings cannot contain commas, because a comma signifies the end of a + modifier. This is not thought to be an issue in a test program. + + Unlike subject strings, pcre2test does not process replacement strings + for escape sequences. In UTF mode, a replacement string is checked to + see if it is a valid UTF-8 string. If so, it is correctly converted to + a UTF string of the appropriate code unit width. If it is not a valid + UTF-8 string, the individual code units are copied directly. This pro- + vides a means of passing an invalid UTF-8 string for testing purposes. + + The following modifiers set options (in additional to the normal match + options) for pcre2_substitute(): + + global PCRE2_SUBSTITUTE_GLOBAL + substitute_extended PCRE2_SUBSTITUTE_EXTENDED + substitute_overflow_length PCRE2_SUBSTITUTE_OVERFLOW_LENGTH + substitute_unknown_unset PCRE2_SUBSTITUTE_UNKNOWN_UNSET + substitute_unset_empty PCRE2_SUBSTITUTE_UNSET_EMPTY + + + After a successful substitution, the modified string is output, pre- + ceded by the number of replacements. This may be zero if there were no + matches. Here is a simple example of a substitution test: /abc/replace=xxx =abc=abc= @@ -1031,12 +1051,13 @@ SUBJECT MODIFIERS =abc=abc=\=global 2: =xxx=xxx= - Subject and replacement strings should be kept relatively short for - substitution tests, as fixed-size buffers are used. To make it easy to - test for buffer overflow, if the replacement string starts with a num- - ber in square brackets, that number is passed to pcre2_substitute() as - the size of the output buffer, with the replacement string starting at - the next character. Here is an example that tests the edge case: + Subject and replacement strings should be kept relatively short (fewer + than 256 characters) for substitution tests, as fixed-size buffers are + used. To make it easy to test for buffer overflow, if the replacement + string starts with a number in square brackets, that number is passed + to pcre2_substitute() as the size of the output buffer, with the + replacement string starting at the next character. Here is an example + that tests the edge case: /abc/ 123abc123\=replace=[10]XYZ @@ -1044,6 +1065,19 @@ SUBJECT MODIFIERS 123abc123\=replace=[9]XYZ Failed: error -47: no more memory + The default action of pcre2_substitute() is to return + PCRE2_ERROR_NOMEMORY when the output buffer is too small. However, if + the PCRE2_SUBSTITUTE_OVERFLOW_LENGTH option is set (by using the sub- + stitute_overflow_length modifier), pcre2_substitute() continues to go + through the motions of matching and substituting, in order to compute + the size of buffer that is required. When this happens, pcre2test shows + the required buffer length (which includes space for the trailing zero) + as part of the error message. For example: + + /abc/substitute_overflow_length + 123abc123\=replace=[9]XYZ + Failed: error -47: no more memory: 10 code units are needed + A replacement string is ignored with POSIX and DFA matching. Specifying partial matching provokes an error return ("bad option value") from pcre2_substitute(). @@ -1471,5 +1505,5 @@ AUTHOR REVISION - Last updated: 05 November 2015 + Last updated: 12 December 2015 Copyright (c) 1997-2015 University of Cambridge. diff --git a/doc/pcre2unicode.3 b/doc/pcre2unicode.3 index 0117561..59e226e 100644 --- a/doc/pcre2unicode.3 +++ b/doc/pcre2unicode.3 @@ -118,8 +118,8 @@ UTF-16 and UTF-32 strings can indicate their endianness by special code knows as a byte-order mark (BOM). The PCRE2 functions do not handle this, expecting strings to be in host byte order. .P -A UTF string is checked before any other processing takes place. In the case of -\fBpcre2_match()\fP and \fBpcre2_dfa_match()\fP calls with a non-zero starting +A UTF string is checked before any other processing takes place. In the case of +\fBpcre2_match()\fP and \fBpcre2_dfa_match()\fP calls with a non-zero starting offset, the check is applied only to that part of the subject that could be inspected during matching, and there is a check that the starting offset points to the first code unit of a character or to the end of the subject. If there diff --git a/perltest.sh b/perltest.sh index c8ac32d..9cf7b17 100755 --- a/perltest.sh +++ b/perltest.sh @@ -211,7 +211,7 @@ for (;;) last if ($_ eq ""); next if $_ =~ /^\\=(?:\s|$)/; # Comment line - + $x = eval "\"$_\""; # To get escapes processed # Empty array for holding results, ensure $REGERROR and $REGMARK are diff --git a/src/pcre2.h b/src/pcre2.h index 3f8f8e0..e5848cf 100644 --- a/src/pcre2.h +++ b/src/pcre2.h @@ -44,7 +44,7 @@ POSSIBILITY OF SUCH DAMAGE. #define PCRE2_MAJOR 10 #define PCRE2_MINOR 21 #define PCRE2_PRERELEASE -RC1 -#define PCRE2_DATE 2015-07-06 +#define PCRE2_DATE 2015-12-15 /* When an application links to a PCRE DLL in Windows, the symbols that are imported have to be identified as such. When building PCRE2, the appropriate diff --git a/src/pcre2_dfa_match.c b/src/pcre2_dfa_match.c index 5350f89..34c479b 100644 --- a/src/pcre2_dfa_match.c +++ b/src/pcre2_dfa_match.c @@ -466,7 +466,7 @@ if (*first_op == OP_REVERSE) /* In byte-mode we can do this quickly. */ { - size_t current_offset = (size_t)(current_subject - start_subject); + size_t current_offset = (size_t)(current_subject - start_subject); gone_back = (current_offset < max_back)? current_offset : max_back; current_subject -= gone_back; } diff --git a/src/pcre2_error.c b/src/pcre2_error.c index a90662b..ea651c8 100644 --- a/src/pcre2_error.c +++ b/src/pcre2_error.c @@ -251,7 +251,7 @@ static const char match_error_texts[] = "bad substitution in replacement string\0" /* 60 */ "match with end before start is not supported\0" - "too many replacements (more than INT_MAX)\0" + "too many replacements (more than INT_MAX)\0" ; diff --git a/src/pcre2_intmodedep.h b/src/pcre2_intmodedep.h index 3ae1b12..b2f4092 100644 --- a/src/pcre2_intmodedep.h +++ b/src/pcre2_intmodedep.h @@ -562,7 +562,7 @@ typedef struct pcre2_real_compile_context { int (*stack_guard)(uint32_t, void *); void *stack_guard_data; const uint8_t *tables; - PCRE2_SIZE max_pattern_length; + PCRE2_SIZE max_pattern_length; uint16_t bsr_convention; uint16_t newline_convention; uint32_t parens_nest_limit; @@ -581,7 +581,7 @@ typedef struct pcre2_real_match_context { #endif int (*callout)(pcre2_callout_block *, void *); void *callout_data; - PCRE2_SIZE offset_limit; + PCRE2_SIZE offset_limit; uint32_t match_limit; uint32_t recursion_limit; } pcre2_real_match_context; @@ -592,7 +592,7 @@ copying the size from possibly unaligned memory into a variable of the same type. Use a macro rather than a typedef to avoid compiler warnings when this file is included multiple times by pcre2test. LOOKBEHIND_MAX specifies the largest lookbehind that is supported. (OP_REVERSE in a pattern has a 16-bit -argument in 8-bit and 16-bit modes, so we need no more than a 16-bit field +argument in 8-bit and 16-bit modes, so we need no more than a 16-bit field here.) */ #undef CODE_BLOCKSIZE_TYPE @@ -660,7 +660,7 @@ typedef struct recurse_check { typedef struct recurse_cache { PCRE2_SPTR group; int recno; -} recurse_cache; +} recurse_cache; /* Structure for maintaining a chain of pointers to the currently incomplete branches, for testing for left recursion while compiling. */ @@ -693,7 +693,7 @@ typedef struct compile_block { PCRE2_SPTR start_code; /* The start of the compiled code */ PCRE2_SPTR start_pattern; /* The start of the pattern */ PCRE2_SPTR end_pattern; /* The end of the pattern */ - PCRE2_SPTR nestptr[2]; /* Pointer(s) saved for string substitution */ + PCRE2_SPTR nestptr[2]; /* Pointer(s) saved for string substitution */ PCRE2_UCHAR *name_table; /* The name/number table */ size_t workspace_size; /* Size of workspace */ uint16_t names_found; /* Number of entries so far */ @@ -717,7 +717,7 @@ typedef struct compile_block { int req_varyopt; /* "After variable item" flag for reqbyte */ BOOL had_accept; /* (*ACCEPT) encountered */ BOOL had_pruneorskip; /* (*PRUNE) or (*SKIP) encountered */ - BOOL had_recurse; /* Had a recursion or subroutine call */ + BOOL had_recurse; /* Had a recursion or subroutine call */ BOOL check_lookbehind; /* Lookbehinds need later checking */ BOOL dupnames; /* Duplicate names exist */ BOOL iscondassert; /* Next assert is a condition */ diff --git a/src/pcre2_match.c b/src/pcre2_match.c index 3740982..011ef38 100644 --- a/src/pcre2_match.c +++ b/src/pcre2_match.c @@ -2409,7 +2409,7 @@ for (;;) break; /* Match a single code unit, even in UTF-8 mode. This opcode really does - match any code unit, even newline. (It really should be called ANYCODEUNIT, + match any code unit, even newline. (It really should be called ANYCODEUNIT, of course - the byte name is from pre-16 bit days.) */ case OP_ANYBYTE: diff --git a/src/pcre2_pattern_info.c b/src/pcre2_pattern_info.c index 28c6869..6a1ae56 100644 --- a/src/pcre2_pattern_info.c +++ b/src/pcre2_pattern_info.c @@ -77,7 +77,7 @@ if (where == NULL) /* Requests field length */ case PCRE2_INFO_CAPTURECOUNT: case PCRE2_INFO_FIRSTCODETYPE: case PCRE2_INFO_FIRSTCODEUNIT: - case PCRE2_INFO_HASBACKSLASHC: + case PCRE2_INFO_HASBACKSLASHC: case PCRE2_INFO_HASCRORLF: case PCRE2_INFO_JCHANGED: case PCRE2_INFO_LASTCODETYPE: diff --git a/src/pcre2_printint.c b/src/pcre2_printint.c index 6d4fe60..a6c2f6a 100644 --- a/src/pcre2_printint.c +++ b/src/pcre2_printint.c @@ -190,13 +190,13 @@ return 0; *************************************************/ /* These take no account of UTF as they always print each individual code unit. -The string is zero-terminated for print_custring(); the length is given for +The string is zero-terminated for print_custring(); the length is given for print_custring_bylen(). Arguments: f file to write to ptr point to the string - len length for print_custring_bylen() + len length for print_custring_bylen() Returns: nothing */ diff --git a/src/pcre2_study.c b/src/pcre2_study.c index 3c61012..a30ade6 100644 --- a/src/pcre2_study.c +++ b/src/pcre2_study.c @@ -1546,7 +1546,7 @@ if ((re->overall_options & PCRE2_ANCHORED) == 0 && if (rc == SSB_DONE) re->flags |= PCRE2_FIRSTMAPSET; } -/* Find the minimum length of subject string. If it can match an empty string, +/* Find the minimum length of subject string. If it can match an empty string, the minimum length is already known. */ if ((re->flags & PCRE2_MATCH_EMPTY) == 0) @@ -1555,19 +1555,19 @@ if ((re->flags & PCRE2_MATCH_EMPTY) == 0) { case -1: /* \C in UTF mode or (*ACCEPT) or over-complex regex */ break; /* Leave minlength unchanged (will be zero) */ - + case -2: return 2; /* missing capturing bracket */ - + case -3: return 3; /* unrecognized opcode */ - + default: if (min > UINT16_MAX) min = UINT16_MAX; re->minlength = min; break; } - } + } return 0; } diff --git a/src/pcre2_valid_utf.c b/src/pcre2_valid_utf.c index 94e97d7..5b3990e 100644 --- a/src/pcre2_valid_utf.c +++ b/src/pcre2_valid_utf.c @@ -136,7 +136,7 @@ for (p = string; length > 0; p++) register uint32_t ab, d; c = *p; - length--; + length--; if (c < 128) continue; /* ASCII character */ @@ -329,7 +329,7 @@ PCRE2_ERROR_UTF16_ERR3 Isolated low surrogate for (p = string; length > 0; p++) { c = *p; - length--; + length--; if ((c & 0xf800) != 0xd800) { diff --git a/src/pcre2posix.c b/src/pcre2posix.c index cd6e664..02a5b1f 100644 --- a/src/pcre2posix.c +++ b/src/pcre2posix.c @@ -285,7 +285,7 @@ start location rather than being passed as a PCRE2 "starting offset". */ if ((eflags & REG_STARTEND) != 0) { - if (pmatch == NULL) return REG_INVARG; + if (pmatch == NULL) return REG_INVARG; so = pmatch[0].rm_so; eo = pmatch[0].rm_eo; } diff --git a/src/pcre2test.c b/src/pcre2test.c index 4f17a43..6343ff9 100644 --- a/src/pcre2test.c +++ b/src/pcre2test.c @@ -6033,14 +6033,14 @@ if (dat_datctl.replacement[0] != 0) if (rc < 0) { - PCRE2_SIZE msize; + PCRE2_SIZE msize; fprintf(outfile, "Failed: error %d", rc); if (rc != PCRE2_ERROR_NOMEMORY && nsize != PCRE2_UNSET) fprintf(outfile, " at offset %ld in replacement", (long int)nsize); fprintf(outfile, ": "); PCRE2_GET_ERROR_MESSAGE(msize, rc, pbuffer); PCHARSV(CASTVAR(void *, pbuffer), 0, msize, FALSE, outfile); - if (rc == PCRE2_ERROR_NOMEMORY && + if (rc == PCRE2_ERROR_NOMEMORY && (xoptions & PCRE2_SUBSTITUTE_OVERFLOW_LENGTH) != 0) fprintf(outfile, ": %ld code units are needed", (long int)nsize); } @@ -6405,7 +6405,7 @@ else for (gmatched = 0;; gmatched++) TESTFLD(match_data, mark, !=, NULL)) { fprintf(outfile, ", mark="); - PCHARS(rubriclength, CASTFLD(void *, match_data, mark), 0, -1, utf, + PCHARS(rubriclength, CASTFLD(void *, match_data, mark), 0, -1, utf, outfile); rubriclength += 7; } |