From 958cd1484fb45d4f1a901aba611d30b081974a3a Mon Sep 17 00:00:00 2001 From: "Philip.Hazel" Date: Sat, 13 Jan 2018 16:53:02 +0000 Subject: [PATCH] Source tidies and version etc. updates for 10.31-RC1. --- AUTHORS | 6 +- CMakeLists.txt | 2 +- ChangeLog | 4 +- LICENCE | 6 +- NEWS | 18 + NON-AUTOTOOLS-BUILD | 16 +- README | 2 +- configure.ac | 8 +- doc/html/NON-AUTOTOOLS-BUILD.txt | 16 +- doc/html/README.txt | 2 +- doc/html/pcre2_get_mark.html | 4 +- doc/html/pcre2api.html | 33 +- doc/html/pcre2grep.html | 6 +- doc/html/pcre2pattern.html | 8 +- doc/pcre2.txt | 2147 +++++++++++++++--------------- doc/pcre2_get_mark.3 | 4 +- doc/pcre2api.3 | 12 +- doc/pcre2grep.1 | 6 +- doc/pcre2pattern.3 | 8 +- src/config.h.generic | 6 +- src/pcre2.h | 2 +- src/pcre2.h.generic | 124 +- src/pcre2_convert.c | 12 +- src/pcre2_dfa_match.c | 2 +- src/pcre2_internal.h | 2 +- src/pcre2_intmodedep.h | 6 +- src/pcre2_jit_test.c | 4 +- src/pcre2_pattern_info.c | 2 +- src/pcre2test.c | 6 +- 29 files changed, 1305 insertions(+), 1169 deletions(-) diff --git a/AUTHORS b/AUTHORS index e056ad6..d5592bb 100644 --- a/AUTHORS +++ b/AUTHORS @@ -8,7 +8,7 @@ Email domain: cam.ac.uk University of Cambridge Computing Service, Cambridge, England. -Copyright (c) 1997-2017 University of Cambridge +Copyright (c) 1997-2018 University of Cambridge All rights reserved @@ -19,7 +19,7 @@ Written by: Zoltan Herczeg Email local part: hzmester Emain domain: freemail.hu -Copyright(c) 2010-2017 Zoltan Herczeg +Copyright(c) 2010-2018 Zoltan Herczeg All rights reserved. @@ -30,7 +30,7 @@ Written by: Zoltan Herczeg Email local part: hzmester Emain domain: freemail.hu -Copyright(c) 2009-2017 Zoltan Herczeg +Copyright(c) 2009-2018 Zoltan Herczeg All rights reserved. #### diff --git a/CMakeLists.txt b/CMakeLists.txt index 7303dcc..bde940a 100644 --- a/CMakeLists.txt +++ b/CMakeLists.txt @@ -432,7 +432,7 @@ SET(PCRE2_SOURCES src/pcre2_convert.c src/pcre2_dfa_match.c src/pcre2_error.c - src/pcre2_extuni.c + src/pcre2_extuni.c src/pcre2_find_bracket.c src/pcre2_jit_compile.c src/pcre2_maketables.c diff --git a/ChangeLog b/ChangeLog index fc85180..d887167 100644 --- a/ChangeLog +++ b/ChangeLog @@ -2,8 +2,8 @@ Change Log for PCRE2 -------------------- -Version 10.31 xx-xxx-201x -------------------------- +Version 10.31 13-January-2018 +----------------------------- 1. Fix typo (missing ]) in VMS code in pcre2test.c. diff --git a/LICENCE b/LICENCE index 2b34d3f..bfe3c8d 100644 --- a/LICENCE +++ b/LICENCE @@ -26,7 +26,7 @@ Email domain: cam.ac.uk University of Cambridge Computing Service, Cambridge, England. -Copyright (c) 1997-2017 University of Cambridge +Copyright (c) 1997-2018 University of Cambridge All rights reserved. @@ -37,7 +37,7 @@ Written by: Zoltan Herczeg Email local part: hzmester Emain domain: freemail.hu -Copyright(c) 2010-2017 Zoltan Herczeg +Copyright(c) 2010-2018 Zoltan Herczeg All rights reserved. @@ -48,7 +48,7 @@ Written by: Zoltan Herczeg Email local part: hzmester Emain domain: freemail.hu -Copyright(c) 2009-2017 Zoltan Herczeg +Copyright(c) 2009-2018 Zoltan Herczeg All rights reserved. diff --git a/NEWS b/NEWS index 74c52a3..5372049 100644 --- a/NEWS +++ b/NEWS @@ -1,6 +1,24 @@ News about PCRE2 releases ------------------------- +Version 10.31 13-January-2018 +----------------------------- + +This is mainly a bugfix and tidying release (see ChangeLog for full details). +However, there are some minor enhancements. + +1. New pcre2_config() options: PCRE2_CONFIG_NEVER_BACKSLASH_C and +PCRE2_CONFIG_COMPILED_WIDTHS. + +2. New pcre2_pattern_info() option PCRE2_INFO_EXTRAOPTIONS to retrieve the +extra compile time options. + +3. There are now public names for all the pcre2_compile() error numbers. + +4. Added PCRE2_CALLOUT_STARTMATCH and PCRE2_CALLOUT_BACKTRACK bits to a new +field callout_flags in callout blocks. + + Version 10.30 14-August-2017 ---------------------------- diff --git a/NON-AUTOTOOLS-BUILD b/NON-AUTOTOOLS-BUILD index fa884ee..0775794 100644 --- a/NON-AUTOTOOLS-BUILD +++ b/NON-AUTOTOOLS-BUILD @@ -91,10 +91,10 @@ can skip ahead to the CMake section. pcre2_compile.c pcre2_config.c pcre2_context.c - pcre2_convert.c + pcre2_convert.c pcre2_dfa_match.c pcre2_error.c - pcre2_extuni.c + pcre2_extuni.c pcre2_find_bracket.c pcre2_jit_compile.c pcre2_maketables.c @@ -125,10 +125,10 @@ can skip ahead to the CMake section. all of whose names begin with "sljit". It also #includes src/pcre2_jit_match.c and src/pcre2_jit_misc.c, so you should not compile these yourself. - - Not also that the pcre2_fuzzsupport.c file contains special code that is - useful to those who want to run fuzzing tests on the PCRE2 library. Unless - you are doing that, you can ignore it. + + Not also that the pcre2_fuzzsupport.c file contains special code that is + useful to those who want to run fuzzing tests on the PCRE2 library. Unless + you are doing that, you can ignore it. (5) Now link all the compiled code into an object library in whichever form your system keeps such libraries. This is the basic PCRE2 C 8-bit library. @@ -370,7 +370,7 @@ z/OS and z/VM are operating systems for mainframe computers, produced by IBM. The character code used is EBCDIC, not ASCII or Unicode. In z/OS, UNIX APIs and applications can be supported through UNIX System Services, and in such an environment it should be possible to build PCRE2 in the same way as in other -systems, with the EBCDIC related configuration settings, but it is not known if +systems, with the EBCDIC related configuration settings, but it is not known if anybody has tried this. In native z/OS (without UNIX System Services) and in z/VM, special ports are @@ -379,7 +379,7 @@ required. For details, please see file 939 on this web site: http://www.cbttape.org Everything in that location, source and executable, is in EBCDIC and native -z/OS file formats. The port provides an API for LE languages such as COBOL and +z/OS file formats. The port provides an API for LE languages such as COBOL and for the z/OS and z/VM versions of the Rexx languages. =============================== diff --git a/README b/README index 2e376b0..52859a9 100644 --- a/README +++ b/README @@ -773,7 +773,7 @@ The distribution should contain the files listed below. src/pcre2_convert.c ) src/pcre2_dfa_match.c ) src/pcre2_error.c ) - src/pcre2_extuni.c ) + src/pcre2_extuni.c ) src/pcre2_find_bracket.c ) src/pcre2_jit_compile.c ) src/pcre2_jit_match.c ) sources for the functions in the library, diff --git a/configure.ac b/configure.ac index e811f9f..6c6442a 100644 --- a/configure.ac +++ b/configure.ac @@ -11,15 +11,15 @@ dnl be defined as -RC2, for example. For real releases, it should be empty. m4_define(pcre2_major, [10]) m4_define(pcre2_minor, [31]) m4_define(pcre2_prerelease, [-RC1]) -m4_define(pcre2_date, [2017-09-12]) +m4_define(pcre2_date, [2018-01-11]) # 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, [6:0:6]) -m4_define(libpcre2_16_version, [6:0:6]) -m4_define(libpcre2_32_version, [6:0:6]) +m4_define(libpcre2_8_version, [7:0:7]) +m4_define(libpcre2_16_version, [7:0:7]) +m4_define(libpcre2_32_version, [7:0:7]) m4_define(libpcre2_posix_version, [2:0:0]) AC_PREREQ(2.57) diff --git a/doc/html/NON-AUTOTOOLS-BUILD.txt b/doc/html/NON-AUTOTOOLS-BUILD.txt index fa884ee..0775794 100644 --- a/doc/html/NON-AUTOTOOLS-BUILD.txt +++ b/doc/html/NON-AUTOTOOLS-BUILD.txt @@ -91,10 +91,10 @@ can skip ahead to the CMake section. pcre2_compile.c pcre2_config.c pcre2_context.c - pcre2_convert.c + pcre2_convert.c pcre2_dfa_match.c pcre2_error.c - pcre2_extuni.c + pcre2_extuni.c pcre2_find_bracket.c pcre2_jit_compile.c pcre2_maketables.c @@ -125,10 +125,10 @@ can skip ahead to the CMake section. all of whose names begin with "sljit". It also #includes src/pcre2_jit_match.c and src/pcre2_jit_misc.c, so you should not compile these yourself. - - Not also that the pcre2_fuzzsupport.c file contains special code that is - useful to those who want to run fuzzing tests on the PCRE2 library. Unless - you are doing that, you can ignore it. + + Not also that the pcre2_fuzzsupport.c file contains special code that is + useful to those who want to run fuzzing tests on the PCRE2 library. Unless + you are doing that, you can ignore it. (5) Now link all the compiled code into an object library in whichever form your system keeps such libraries. This is the basic PCRE2 C 8-bit library. @@ -370,7 +370,7 @@ z/OS and z/VM are operating systems for mainframe computers, produced by IBM. The character code used is EBCDIC, not ASCII or Unicode. In z/OS, UNIX APIs and applications can be supported through UNIX System Services, and in such an environment it should be possible to build PCRE2 in the same way as in other -systems, with the EBCDIC related configuration settings, but it is not known if +systems, with the EBCDIC related configuration settings, but it is not known if anybody has tried this. In native z/OS (without UNIX System Services) and in z/VM, special ports are @@ -379,7 +379,7 @@ required. For details, please see file 939 on this web site: http://www.cbttape.org Everything in that location, source and executable, is in EBCDIC and native -z/OS file formats. The port provides an API for LE languages such as COBOL and +z/OS file formats. The port provides an API for LE languages such as COBOL and for the z/OS and z/VM versions of the Rexx languages. =============================== diff --git a/doc/html/README.txt b/doc/html/README.txt index 2e376b0..52859a9 100644 --- a/doc/html/README.txt +++ b/doc/html/README.txt @@ -773,7 +773,7 @@ The distribution should contain the files listed below. src/pcre2_convert.c ) src/pcre2_dfa_match.c ) src/pcre2_error.c ) - src/pcre2_extuni.c ) + src/pcre2_extuni.c ) src/pcre2_find_bracket.c ) src/pcre2_jit_compile.c ) src/pcre2_jit_match.c ) sources for the functions in the library, diff --git a/doc/html/pcre2_get_mark.html b/doc/html/pcre2_get_mark.html index 2b77e42..88e6326 100644 --- a/doc/html/pcre2_get_mark.html +++ b/doc/html/pcre2_get_mark.html @@ -32,8 +32,8 @@ name is zero-terminated, and is within the compiled pattern. The length of the name is in the preceding code unit. If no name is available, NULL is returned.

-After a successful match, the name that is returned is the last one on the -matching path. After a failed match or a partial match, the last encountered +After a successful match, the name that is returned is the last one on the +matching path. After a failed match or a partial match, the last encountered name is returned.

diff --git a/doc/html/pcre2api.html b/doc/html/pcre2api.html index abdd0ff..ba3b2ca 100644 --- a/doc/html/pcre2api.html +++ b/doc/html/pcre2api.html @@ -920,7 +920,7 @@ The offset_limit parameter limits how far an unanchored search can advance in the subject string. The default value is PCRE2_UNSET. The pcre2_match() and pcre2_dfa_match() functions return PCRE2_ERROR_NOMATCH if a match with a starting point before or at the given -offset is not found. The pcre2_substitute() function makes no more +offset is not found. The pcre2_substitute() function makes no more substitutions.

@@ -939,10 +939,10 @@ PCRE2_USE_OFFSET_LIMIT is not set, an error is generated.

The offset limit facility can be used to track progress when searching large subject strings or to limit the extent of global substitutions. 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 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_FIRSTLINE option, which requires a match to start before or at the first +newline that follows the start of matching in 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_heap_limit(pcre2_match_context *mcontext, @@ -1506,11 +1506,16 @@ changed within a pattern by a (?xx) option setting. PCRE2_FIRSTLINE If this option is set, the start of an unanchored pattern match must be 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. 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. +or at the first newline in the subject string following the start of matching, +though the matched text may continue over the newline. If startoffset is +non-zero, the limiting newline is not necessarily the first newline in the +subject. For example, if the subject string is "abc\nxyz" (where \n +represents a single-character newline) a pattern match for "yz" succeeds with +PCRE2_FIRSTLINE if startoffset is greater than 3. See also +PCRE2_USE_OFFSET_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_LITERAL
@@ -1945,13 +1950,13 @@ are as follows: 
   PCRE2_INFO_ALLOPTIONS
   PCRE2_INFO_ARGOPTIONS
-  PCRE2_INFO_EXTRAOPTIONS 
+  PCRE2_INFO_EXTRAOPTIONS
Return copies of the pattern's options. The third argument should point to a uint32_t variable. PCRE2_INFO_ARGOPTIONS returns exactly the options that were passed to pcre2_compile(), whereas PCRE2_INFO_ALLOPTIONS returns the compile options as modified by any top-level (*XXX) option settings such as -(*UTF) at the start of the pattern itself. PCRE2_INFO_EXTRAOPTIONS returns the +(*UTF) at the start of the pattern itself. PCRE2_INFO_EXTRAOPTIONS returns the extra options that were set in the compile context by calling the pcre2_set_compile_extra_options() function.

@@ -3167,7 +3172,7 @@ options can be set in the options argument of pcre2_substitute(). PCRE2_SUBSTITUTE_GLOBAL causes the function to iterate over the subject string, replacing every matching substring. If this option is not set, only the first matching substring is replaced. The search for matches takes place in the -original subject string (that is, previous replacements do not affect it). +original subject string (that is, previous replacements do not affect it). Iteration is implemented by advancing the startoffset value for each search, which is always passed the entire subject string. If an offset limit is set in the match context, searching stops when that limit is reached. @@ -3589,7 +3594,7 @@ Cambridge, England.


REVISION

-Last updated: 16 December 2017 +Last updated: 31 December 2017
Copyright © 1997-2017 University of Cambridge.
diff --git a/doc/html/pcre2grep.html b/doc/html/pcre2grep.html index 27889d8..625a467 100644 --- a/doc/html/pcre2grep.html +++ b/doc/html/pcre2grep.html @@ -464,7 +464,7 @@ given any number of times. If a directory matches both --include-dir and -L, --files-without-match Instead of outputting lines from the files, just output the names of the files that do not contain any lines that would have been output. Each file name is -output once, on a separate line. This option overrides any previous -H, +output once, on a separate line. This option overrides any previous -H, -h, or -l options.

@@ -494,7 +494,7 @@ to terminal is normally automatically flushed by the operating system. This option can be useful when the input or output is attached to a pipe and you do not want pcre2grep to buffer up large amounts of data. However, its use will affect performance, and the -M (multiline) option ceases to work. -When input is from a compressed .gz or .bz2 file, --line-buffered is +When input is from a compressed .gz or .bz2 file, --line-buffered is ignored.

@@ -931,7 +931,7 @@ matches were found in other files) or too many matching errors. Using the affect the return code.

-When run under VMS, the return code is placed in the symbol PCRE2GREP_RC +When run under VMS, the return code is placed in the symbol PCRE2GREP_RC because VMS does not distinguish between exit(0) and exit(1).


SEE ALSO
diff --git a/doc/html/pcre2pattern.html b/doc/html/pcre2pattern.html index 01a2cc1..c495cba 100644 --- a/doc/html/pcre2pattern.html +++ b/doc/html/pcre2pattern.html @@ -513,8 +513,8 @@ limited to certain values, as follows: All UTF modes no greater than 0x10ffff and a valid codepoint Invalid Unicode codepoints are all those in the range 0xd800 to 0xdfff (the -so-called "surrogate" codepoints). The check for these can be disabled by the -caller of pcre2_compile() by setting the option +so-called "surrogate" codepoints). The check for these can be disabled by the +caller of pcre2_compile() by setting the option PCRE2_EXTRA_ALLOW_SURROGATE_ESCAPES.


@@ -1416,9 +1416,9 @@ Ranges normally include all code points between the start and end characters, 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. In any UTF mode, the so-called "surrogate" characters (those -whose code points lie between 0xd800 and 0xdfff inclusive) may not be specified +whose code points lie between 0xd800 and 0xdfff inclusive) may not be specified explicitly by default (the PCRE2_EXTRA_ALLOW_SURROGATE_ESCAPES option disables -this check). However, ranges such as [\x{d7ff}-\x{e000}], which include the +this check). However, ranges such as [\x{d7ff}-\x{e000}], which include the surrogates, are always permitted.

diff --git a/doc/pcre2.txt b/doc/pcre2.txt index efd4247..79d94e3 100644 --- a/doc/pcre2.txt +++ b/doc/pcre2.txt @@ -170,8 +170,8 @@ REVISION Last updated: 01 April 2017 Copyright (c) 1997-2017 University of Cambridge. ------------------------------------------------------------------------------ - - + + PCRE2API(3) Library Functions Manual PCRE2API(3) @@ -947,20 +947,21 @@ PCRE2 CONTEXTS The offset limit facility can be used to track progress when searching large subject strings or to limit the extent of global substitutions. 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 - limit, a match must occur in the first line and also within the offset - limit. In other words, whichever limit comes first is used. + before or at the first newline that follows the start of matching in + 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, which- + ever limit comes first is used. int pcre2_set_heap_limit(pcre2_match_context *mcontext, uint32_t value); - The heap_limit parameter specifies, in units of kilobytes, the maximum - amount of heap memory that pcre2_match() may use to hold backtracking - information when running an interpretive match. This limit does not - apply to matching with the JIT optimization, which has its own memory + The heap_limit parameter specifies, in units of kilobytes, the maximum + amount of heap memory that pcre2_match() may use to hold backtracking + information when running an interpretive match. This limit does not + apply to matching with the JIT optimization, which has its own memory control arrangements (see the pcre2jit documentation for more details), - nor does it apply to pcre2_dfa_match(). If the limit is reached, the - negative error code PCRE2_ERROR_HEAPLIMIT is returned. The default + nor does it apply to pcre2_dfa_match(). If the limit is reached, the + negative error code PCRE2_ERROR_HEAPLIMIT is returned. The default limit is set when PCRE2 is built; the default default is very large and is essentially "unlimited". @@ -969,83 +970,83 @@ PCRE2 CONTEXTS (*LIMIT_HEAP=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. - The pcre2_match() function starts out using a 20K vector on the system - stack for recording backtracking points. The more nested backtracking + The pcre2_match() function starts out using a 20K vector on the system + stack for recording backtracking points. The more nested backtracking points there are (that is, the deeper the search tree), the more memory - is needed. Heap memory is used only if the initial vector is too + is needed. Heap memory is used only if the initial vector is too small. If the heap limit is set to a value less than 21 (in particular, - zero) no heap memory will be used. In this case, only patterns that do + zero) no heap memory will be used. In this case, only patterns that do not have a lot of nested backtracking can be successfully processed. 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 computing 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 + in their search trees. The classic example is a pattern that uses nested unlimited repeats. - There is an internal counter in pcre2_match() that is incremented each - time round its main matching loop. If this value reaches the match + There is an internal counter in pcre2_match() that is incremented each + time round its main matching loop. If this value reaches the match limit, pcre2_match() returns the negative value PCRE2_ERROR_MATCHLIMIT. - This has the effect of limiting the amount of backtracking that can + This 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 also applies + zero for each position in the subject string. This limit also applies to pcre2_dfa_match(), though the counting is done in a different way. - 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. A value for the match limit may also be supplied by an item at + 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. A value for the match limit may also be supplied 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 + 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 pcre2_dfa_match() or, if no such limit is set, less than the default. int pcre2_set_depth_limit(pcre2_match_context *mcontext, uint32_t value); - This parameter limits the depth of nested backtracking in - pcre2_match(). Each time a nested backtracking point is passed, a new + This parameter limits the depth of nested backtracking in + pcre2_match(). Each time a nested backtracking point is passed, a new memory "frame" is used to remember the state of matching at that point. - Thus, this parameter indirectly limits the amount of memory that is - used in a match. However, because the size of each memory "frame" + Thus, this parameter indirectly limits the amount of memory that is + used in a match. However, because the size of each memory "frame" depends on the number of capturing parentheses, the actual memory limit - varies from pattern to pattern. This limit was more useful in versions + varies from pattern to pattern. This limit was more useful in versions before 10.30, where function recursion was used for backtracking. - The depth limit is not relevant, and is ignored, when matching is done + The depth limit is not relevant, and is ignored, when matching is done using JIT compiled code. However, it is supported by pcre2_dfa_match(), - which uses it to limit the depth of internal recursive function calls + which uses it to limit the depth of internal recursive function calls that implement atomic groups, lookaround assertions, and pattern recur- - sions. This is, therefore, an indirect limit on the amount of system + sions. This is, therefore, an indirect limit on the amount of system stack that is used. A recursive pattern such as /(.)(?1)/, when matched - to a very long string using pcre2_dfa_match(), can use a great deal of + to a very long string using pcre2_dfa_match(), can use a great deal of stack. - The default value for the depth limit can be set when PCRE2 is built; - the default default is the same value as the default for the match - limit. If the limit is exceeded, pcre2_match() or pcre2_dfa_match() + The default value for the depth limit can be set when PCRE2 is built; + the default default is the same value as the default for the match + limit. If the limit is exceeded, pcre2_match() or pcre2_dfa_match() returns PCRE2_ERROR_DEPTHLIMIT. A value for the depth limit may also be supplied by an item at the start of a pattern of the form (*LIMIT_DEPTH=ddd) - where ddd is a decimal number. However, such a setting is ignored + 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 pcre2_dfa_match() or, if no such limit is set, less than the default. @@ -1054,95 +1055,95 @@ 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_COMPILED_WIDTHS - The output is a uint32_t integer whose lower bits indicate which code - unit widths were selected when PCRE2 was built. The 1-bit indicates - 8-bit support, and the 2-bit and 4-bit indicate 16-bit and 32-bit sup- + The output is a uint32_t integer whose lower bits indicate which code + unit widths were selected when PCRE2 was built. The 1-bit indicates + 8-bit support, and the 2-bit and 4-bit indicate 16-bit and 32-bit sup- port, respectively. PCRE2_CONFIG_DEPTHLIMIT - The output is a uint32_t integer that gives the default limit for the - depth of nested backtracking in pcre2_match() or the depth of nested - recursions and lookarounds in pcre2_dfa_match(). Further details are + The output is a uint32_t integer that gives the default limit for the + depth of nested backtracking in pcre2_match() or the depth of nested + recursions and lookarounds in pcre2_dfa_match(). Further details are given with pcre2_set_depth_limit() above. PCRE2_CONFIG_HEAPLIMIT - The output is a uint32_t integer that gives, in kilobytes, the default - limit for the amount of heap memory used by pcre2_match(). Further + The output is a uint32_t integer that gives, in kilobytes, the default + limit for the amount of heap memory used by pcre2_match(). Further details are given with pcre2_set_heap_limit() above. 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 match limit for - pcre2_match(). Further details are given with pcre2_set_match_limit() + pcre2_match(). Further details are given with pcre2_set_match_limit() above. 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) @@ -1152,23 +1153,23 @@ CHECKING BUILD-TIME OPTIONS PCRE2_NEWLINE_ANYCRLF Any of CR, LF, or CRLF PCRE2_NEWLINE_NUL The NUL character (binary zero) - 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_NEVER_BACKSLASH_C - The output is a uint32_t integer that is set to one if the use of \C - was permanently disabled when PCRE2 was built; otherwise it is set to + The output is a uint32_t integer that is set to one if the use of \C + was permanently disabled when PCRE2 was built; otherwise it is set to zero. 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_STACKRECURSE @@ -1178,25 +1179,25 @@ CHECKING BUILD-TIME OPTIONS 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 24 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 24 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. @@ -1214,96 +1215,96 @@ COMPILING A PATTERN pcre2_code *pcre2_code_copy_with_tables(const 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 (in code units). 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 + 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 (in code units). 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, or NULL if an error occurred. - 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 caller must free the memory by calling pcre2_code_free() + 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 caller must free the memory by calling pcre2_code_free() when it is no longer needed. The function pcre2_code_copy() makes a copy of the compiled code in new - memory, using the same memory allocator as was used for the original. - However, if the code has been processed by the JIT compiler (see - below), the JIT information cannot be copied (because it is position- + memory, using the same memory allocator as was used for the original. + However, if the code has been processed by the JIT compiler (see + below), the JIT information cannot be copied (because it is position- dependent). The new copy can initially be used only for non-JIT match- ing, though it can be passed to pcre2_jit_compile() if required. The pcre2_code_copy() function provides a way for individual threads in - a multithreaded application to acquire a private copy of shared com- - piled code. However, it does not make a copy of the character tables - used by the compiled pattern; the new pattern code points to the same - tables as the original code. (See "Locale Support" below for details - of these character tables.) In many applications the same tables are - used throughout, so this behaviour is appropriate. Nevertheless, there + a multithreaded application to acquire a private copy of shared com- + piled code. However, it does not make a copy of the character tables + used by the compiled pattern; the new pattern code points to the same + tables as the original code. (See "Locale Support" below for details + of these character tables.) In many applications the same tables are + used throughout, so this behaviour is appropriate. Nevertheless, there are occasions when a copy of a compiled pattern and the relevant tables - are needed. The pcre2_code_copy_with_tables() provides this facility. - Copies of both the code and the tables are made, with the new code - pointing to the new tables. The memory for the new tables is automati- - cally freed when pcre2_code_free() is called for the new copy of the + are needed. The pcre2_code_copy_with_tables() provides this facility. + Copies of both the code and the tables are made, with the new code + pointing to the new tables. The memory for the new tables is automati- + cally freed when pcre2_code_free() is called for the new copy of the compiled code. - 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 substring extraction functions. - After running a match, you must not free a compiled pattern (or a sub- - ject string) until after all operations on the match data block have + so that they can be referenced by the substring extraction functions. + After running a match, you must not free a compiled pattern (or a sub- + ject string) until after all operations on the match data block have taken place. - The options argument for pcre2_compile() contains various bit settings - that affect the compilation. 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 + The options argument for pcre2_compile() contains various bit settings + that affect the compilation. 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, PCRE2_ENDANCHORED, and - PCRE2_NO_UTF_CHECK options can be set at the time of matching as well + 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, PCRE2_ENDANCHORED, 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, the variables to which these point are set to an - error code and an offset (number of code units) within the pattern, - respectively, when pcre2_compile() returns NULL because a compilation + diately. Otherwise, the variables to which these point are set to an + error code and an offset (number of code units) within the pattern, + respectively, when pcre2_compile() returns NULL because a compilation error has occurred. The values are not defined when compilation is suc- cessful and pcre2_compile() returns a non-NULL value. - There are nearly 100 positive error codes that pcre2_compile() may - return if it finds an error in the pattern. There are also some nega- - tive error codes that are used for invalid UTF strings. These are the + There are nearly 100 positive error codes that pcre2_compile() may + return if it finds an error in the pattern. There are also some nega- + tive error codes that are used for invalid UTF strings. These are the same as given by pcre2_match() and pcre2_dfa_match(), and are described - in the pcre2unicode page. There is no separate documentation for the - positive error codes, because the textual error messages that are - obtained by calling the pcre2_get_error_message() function (see - "Obtaining a textual error message" below) should be self-explanatory. - Macro names starting with PCRE2_ERROR_ are defined for both positive + in the pcre2unicode page. There is no separate documentation for the + positive error codes, because the textual error messages that are + obtained by calling the pcre2_get_error_message() function (see + "Obtaining a textual error message" below) should be self-explanatory. + Macro names starting with PCRE2_ERROR_ are defined for both positive and negative error codes in pcre2.h. The value returned in erroroffset is an indication of where in the pat- - tern the error occurred. It is not necessarily the furthest point in - the pattern that was read. For example, after the error "lookbehind + tern the error occurred. It is not necessarily the furthest point in + the pattern that was read. For example, after the error "lookbehind assertion is not fixed length", the error offset points to the start of - the failing assertion. For an invalid UTF-8 or UTF-16 string, the off- + the failing assertion. For an invalid UTF-8 or UTF-16 string, the off- set 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; @@ -1317,476 +1318,480 @@ 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 or - PCRE2_EXTENDED_MORE option is set, unescaped whitespace in verb names - is skipped and #-comments are recognized in this mode, exactly as in + 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 or + PCRE2_EXTENDED_MORE option is set, unescaped whitespace in verb names + is skipped and #-comments are recognized in this mode, exactly as in the rest of the pattern. PCRE2_AUTO_CALLOUT - If this bit is set, pcre2_compile() automatically inserts callout - items, all with number 255, before each pattern item, except immedi- - ately before or after an explicit callout in the pattern. For discus- + If this bit is set, pcre2_compile() automatically inserts callout + items, all with number 255, before each pattern item, except immedi- + ately before or after an explicit callout in the pattern. For discus- sion 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 - it can be changed within a pattern by a (?i) option setting. If - PCRE2_UTF is set, Unicode properties are used for all characters with - more than one other case, and for all characters whose code points are - greater than U+007f. For lower valued characters with only one other - case, a lookup table is used for speed. When PCRE2_UTF is not set, a + 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. If + PCRE2_UTF is set, Unicode properties are used for all characters with + more than one other case, and for all characters whose code points are + greater than U+007f. For lower valued characters with only one other + case, a lookup table is used for speed. When PCRE2_UTF is not set, a lookup table is used for all code points less than 256, and higher code - points (available only in 16-bit or 32-bit mode) are treated as not + points (available only in 16-bit or 32-bit mode) are treated as not having another case. 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_ENDANCHORED - If this bit is set, the end of any pattern match must be right at the + If this bit is set, the end of any pattern match must be right at the end of the string being searched (the "subject string"). If the pattern match succeeds by reaching (*ACCEPT), but does not reach the end of the - subject, the match fails at the current starting point. For unanchored - patterns, a new match is then tried at the next starting point. How- + subject, the match fails at the current starting point. For unanchored + patterns, a new match is then tried at the next starting point. How- ever, if the match succeeds by reaching the end of the pattern, but not - the end of the subject, backtracking occurs and an alternative match + the end of the subject, backtracking occurs and an alternative match may be found. Consider these two patterns: .(*ACCEPT)|.. .|.. - If matched against "abc" with PCRE2_ENDANCHORED set, the first matches - "c" whereas the second matches "bc". The effect of PCRE2_ENDANCHORED - can also be achieved by appropriate constructs in the pattern itself, + If matched against "abc" with PCRE2_ENDANCHORED set, the first matches + "c" whereas the second matches "bc". The effect of PCRE2_ENDANCHORED + can also be achieved by appropriate constructs in the pattern itself, which is the only way to do it in Perl. For DFA matching with pcre2_dfa_match(), PCRE2_ENDANCHORED applies only - to the first (that is, the longest) matched string. Other parallel - matches, which are necessarily substrings of the first one, must obvi- + to the first (that is, the longest) matched string. Other parallel + matches, which are necessarily substrings of the first one, must obvi- ously end before the end of the subject. 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_EXTENDED_MORE - This option has the effect of PCRE2_EXTENDED, but, in addition, - unescaped space and horizontal tab characters are ignored inside a - character class. PCRE2_EXTENDED_MORE is equivalent to Perl's 5.26 /xx - option, and it can be changed within a pattern by a (?xx) option set- + This option has the effect of PCRE2_EXTENDED, but, in addition, + unescaped space and horizontal tab characters are ignored inside a + character class. PCRE2_EXTENDED_MORE is equivalent to Perl's 5.26 /xx + option, and it can be changed within a pattern by a (?xx) option set- ting. PCRE2_FIRSTLINE If this option is set, the start of an unanchored pattern match must be - 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. + before or at the first newline in the subject string following the + start of matching, though the matched text may continue over the new- + line. If startoffset is non-zero, the limiting newline is not necessar- + ily the first newline in the subject. For example, if the subject + string is "abc\nxyz" (where \n represents a single-character newline) a + pattern match for "yz" succeeds with PCRE2_FIRSTLINE if startoffset is + greater than 3. See also PCRE2_USE_OFFSET_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_LITERAL If this option is set, all meta-characters in the pattern are disabled, - and it is treated as a literal string. Matching literal strings with a + and it is treated as a literal string. Matching literal strings with a regular expression engine is not the most efficient way of doing it. If - you are doing a lot of literal matching and are worried about effi- + you are doing a lot of literal matching and are worried about effi- ciency, you should consider using other approaches. The only other main options that are allowed with PCRE2_LITERAL are: PCRE2_ANCHORED, PCRE2_ENDANCHORED, PCRE2_AUTO_CALLOUT, PCRE2_CASELESS, PCRE2_FIRSTLINE, PCRE2_NO_START_OPTIMIZE, PCRE2_NO_UTF_CHECK, PCRE2_UTF, and - PCRE2_USE_OFFSET_LIMIT. The extra options PCRE2_EXTRA_MATCH_LINE and - PCRE2_EXTRA_MATCH_WORD are also supported. Any other options cause an + PCRE2_USE_OFFSET_LIMIT. The extra options PCRE2_EXTRA_MATCH_LINE and + PCRE2_EXTRA_MATCH_WORD are also supported. Any other options cause an error. PCRE2_MATCH_UNSET_BACKREF - If this option is set, a back reference to an unset subpattern group - matches an empty string (by default this causes the current matching - alternative to fail). A pattern such as (\1)(a) succeeds when this - option is set (assuming it can find an "a" in the subject), whereas it - fails by default, for Perl compatibility. Setting this option makes + If this option is set, a back reference to an unset subpattern group + matches an empty string (by default this causes the current matching + alternative to fail). A pattern such as (\1)(a) succeeds when this + option is set (assuming it can find an "a" in the subject), whereas it + fails by default, for Perl compatibility. Setting this option makes PCRE2 behave more like ECMAscript (aka JavaScript). PCRE2_MULTILINE - By default, for the purposes of matching "start of line" and "end of - line", PCRE2 treats the subject string as consisting of a single line - of characters, even if it actually contains newlines. The "start of - line" metacharacter (^) matches only at the start of the string, and - the "end of line" metacharacter ($) matches only at the end of the + By default, for the purposes of matching "start of line" and "end of + line", PCRE2 treats the subject string as consisting of a single line + of characters, even if it actually contains newlines. The "start of + line" metacharacter (^) matches only at the start of the string, and + the "end of line" metacharacter ($) matches only at the end of the string, or before a terminating newline (except when PCRE2_DOL- - LAR_ENDONLY is set). Note, however, that unless PCRE2_DOTALL is set, + LAR_ENDONLY is set). Note, however, that unless PCRE2_DOTALL is set, the "any character" metacharacter (.) does not match at a newline. This behaviour (for ^, $, and dot) is the same as Perl. - When PCRE2_MULTILINE it is set, the "start of line" and "end of line" - constructs match immediately following or immediately before internal - newlines in the subject string, respectively, as well as at the very - start and end. This is equivalent to Perl's /m option, and it can be + When PCRE2_MULTILINE it is set, the "start of line" and "end of line" + constructs match immediately following or immediately before internal + newlines in the subject string, respectively, as well as at the very + start and end. This is equivalent to Perl's /m option, and it can be changed within a pattern by a (?m) option setting. Note that the "start of line" metacharacter does not match after a newline at the end of the - subject, for compatibility with Perl. However, you can change this by - setting the PCRE2_ALT_CIRCUMFLEX option. If there are no newlines in a - subject string, or no occurrences of ^ or $ in a pattern, setting + subject, for compatibility with Perl. However, you can change this by + setting the PCRE2_ALT_CIRCUMFLEX option. If there are no newlines in a + subject string, or no occurrences of ^ or $ in a pattern, setting PCRE2_MULTILINE has no effect. PCRE2_NEVER_BACKSLASH_C - This option locks out the use of \C in the pattern that is being com- - piled. 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 + This option locks out the use of \C in the pattern that is being com- + piled. 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 locks out the use of \C. PCRE2_NEVER_UCP - This option locks out the use of Unicode properties for handling \B, + This option locks out the use of Unicode properties for handling \B, \b, \D, \d, \S, \s, \W, \w, and some of the POSIX character classes, as - described for the PCRE2_UCP option below. In particular, it prevents - the creator of the pattern from enabling this facility by starting the - pattern with (*UCP). This option may be useful in applications that + described for the PCRE2_UCP option below. In particular, it prevents + the creator of the pattern from enabling this facility by starting the + pattern with (*UCP). This option may be useful in applications that process patterns from external sources. The option combination PCRE_UCP and PCRE_NEVER_UCP causes an error. PCRE2_NEVER_UTF - This option locks out interpretation of the pattern as UTF-8, UTF-16, + This option locks out interpretation of the pattern as UTF-8, UTF-16, or UTF-32, depending on which library is in use. In particular, it pre- - vents the creator of the pattern from switching to UTF interpretation - by starting the pattern with (*UTF). This option may be useful in - applications that process patterns from external sources. The combina- + vents the creator of the pattern from switching to UTF interpretation + by starting the pattern with (*UTF). This option may be useful in + applications that process patterns from external sources. The combina- tion of PCRE2_UTF and PCRE2_NEVER_UTF causes an error. PCRE2_NO_AUTO_CAPTURE If this option is set, it disables the use of numbered capturing paren- - theses in the pattern. Any opening parenthesis that is not followed by - ? behaves as if it were followed by ?: but named parentheses can still + theses in the pattern. Any opening parenthesis that is not followed by + ? behaves as if it were followed by ?: but named parentheses can still be used for capturing (and they acquire numbers in the usual way). This - is the same as Perl's /n option. Note that, when this option is set, + is the same as Perl's /n option. Note that, when this option is set, references to capturing groups (back references or recursion/subroutine - calls) may only refer to named groups, though the reference can be by + calls) may only refer to named groups, though the reference can be by name or by number. PCRE2_NO_AUTO_POSSESS If this option is set, it disables "auto-possessification", which is an - optimization that, for example, turns a+b into a++b in order to avoid - backtracks into a+ that can never be successful. However, if callouts - are in use, auto-possessification means that some callouts are never + optimization that, for example, turns a+b into a++b in order to avoid + backtracks into a+ that can never be successful. However, if callouts + are in use, auto-possessification means that some callouts are never taken. You can set this option if you want the matching functions to do - a full unoptimized search and run all the callouts, but it is mainly + a full unoptimized search and run all the callouts, but it is mainly provided for testing purposes. PCRE2_NO_DOTSTAR_ANCHOR If this option is set, it disables an optimization that is applied when - .* is the first significant item in a top-level branch of a pattern, - and all the other branches also start with .* or with \A or \G or ^. - The optimization is automatically disabled for .* if it is inside an - atomic group or a capturing group that is the subject of a back refer- - ence, or if the pattern contains (*PRUNE) or (*SKIP). When the opti- - mization is not disabled, such a pattern is automatically anchored if + .* is the first significant item in a top-level branch of a pattern, + and all the other branches also start with .* or with \A or \G or ^. + The optimization is automatically disabled for .* if it is inside an + atomic group or a capturing group that is the subject of a back refer- + ence, or if the pattern contains (*PRUNE) or (*SKIP). When the opti- + mization is not disabled, such a pattern is automatically anchored if PCRE2_DOTALL is set for all the .* items and PCRE2_MULTILINE is not set - for any ^ items. Otherwise, the fact that any match must start either - at the start of the subject or following a newline is remembered. Like + for any ^ items. Otherwise, the fact that any match must start either + at the start of the subject or following a newline is remembered. Like other optimizations, this can cause callouts to be skipped. PCRE2_NO_START_OPTIMIZE - This is an option whose main effect is at matching time. It does not + This is an option whose main effect is at matching time. It does not change what pcre2_compile() generates, but it does affect the output of the JIT compiler. - There are a number of optimizations that may occur at the start of a - match, in order to speed up the process. For example, if it is known - that an unanchored match must start with a specific code unit value, - the matching code searches the subject for that value, and fails imme- - diately if it cannot find it, without actually running the main match- - ing function. This means that a special item such as (*COMMIT) at the - start of a pattern is not considered until after a suitable starting - point for the match has been found. Also, when callouts or (*MARK) - items are in use, these "start-up" optimizations can cause them to be - skipped if the pattern is never actually used. The start-up optimiza- - tions are in effect a pre-scan of the subject that takes place before + There are a number of optimizations that may occur at the start of a + match, in order to speed up the process. For example, if it is known + that an unanchored match must start with a specific code unit value, + the matching code searches the subject for that value, and fails imme- + diately if it cannot find it, without actually running the main match- + ing function. This means that a special item such as (*COMMIT) at the + start of a pattern is not considered until after a suitable starting + point for the match has been found. Also, when callouts or (*MARK) + items are in use, these "start-up" optimizations can cause them to be + skipped if the pattern is never actually used. The start-up optimiza- + tions are in effect a pre-scan of the subject that takes place before the pattern is run. The PCRE2_NO_START_OPTIMIZE option disables the start-up optimizations, - possibly causing performance to suffer, but ensuring that in cases - where the result is "no match", the callouts do occur, and that items + possibly causing performance to suffer, but ensuring that in cases + where the result is "no match", the callouts do occur, and that items such as (*COMMIT) and (*MARK) are considered at every possible starting position in the subject string. - Setting PCRE2_NO_START_OPTIMIZE may change the outcome of a matching + Setting PCRE2_NO_START_OPTIMIZE may change the outcome of a matching operation. Consider the pattern (*COMMIT)ABC - When this is compiled, PCRE2 records the fact that a match must start - with the character "A". Suppose the subject string is "DEFABC". The - start-up optimization scans along the subject, finds "A" and runs the - first match attempt from there. The (*COMMIT) item means that the pat- - tern must match the current starting position, which in this case, it - does. However, if the same match is run with PCRE2_NO_START_OPTIMIZE - set, the initial scan along the subject string does not happen. The - first match attempt is run starting from "D" and when this fails, - (*COMMIT) prevents any further matches being tried, so the overall + When this is compiled, PCRE2 records the fact that a match must start + with the character "A". Suppose the subject string is "DEFABC". The + start-up optimization scans along the subject, finds "A" and runs the + first match attempt from there. The (*COMMIT) item means that the pat- + tern must match the current starting position, which in this case, it + does. However, if the same match is run with PCRE2_NO_START_OPTIMIZE + set, the initial scan along the subject string does not happen. The + first match attempt is run starting from "D" and when this fails, + (*COMMIT) prevents any further matches being tried, so the overall result is "no match". - There are also other start-up optimizations. For example, a minimum + There are also other start-up optimizations. For example, a minimum length for the subject may be recorded. Consider the pattern (*MARK:A)(X|Y) - The minimum length for a match is one character. If the subject is + The minimum length for a match is one character. If the subject is "ABC", there will be attempts to match "ABC", "BC", and "C". An attempt to match an empty string at the end of the subject does not take place, - because PCRE2 knows that the subject is now too short, and so the - (*MARK) is never encountered. In this case, the optimization does not + because PCRE2 knows that the subject is now too short, and so the + (*MARK) is never encountered. In this case, the optimization does not affect the overall match result, which is still "no match", but it does affect the auxiliary information that is returned. PCRE2_NO_UTF_CHECK - When PCRE2_UTF is set, the validity of the pattern as a UTF string is - automatically checked. There are discussions about the validity of - UTF-8 strings, UTF-16 strings, and UTF-32 strings in the pcre2unicode - document. If an invalid UTF sequence is found, pcre2_compile() returns + When PCRE2_UTF is set, the validity of the pattern as a UTF string is + automatically checked. There are discussions about the validity of + UTF-8 strings, UTF-16 strings, and UTF-32 strings in the pcre2unicode + document. If an invalid UTF sequence is found, pcre2_compile() returns a negative error code. - If you know that your pattern is a valid UTF string, and you want to - skip this check for performance reasons, you can set the - PCRE2_NO_UTF_CHECK option. When it is set, the effect of passing an + If you know that your pattern is a valid UTF string, and you want to + skip this check for performance reasons, you can set the + PCRE2_NO_UTF_CHECK option. When it is set, the effect of passing an invalid UTF string as a pattern is undefined. It may cause your program to crash or loop. Note that this option can also be passed to pcre2_match() and - pcre_dfa_match(), to suppress UTF validity checking of the subject + pcre_dfa_match(), to suppress UTF validity checking of the subject string. Note also that setting PCRE2_NO_UTF_CHECK at compile time does not dis- - able the error that is given if an escape sequence for an invalid Uni- - code code point is encountered in the pattern. In particular, the so- - called "surrogate" code points (0xd800 to 0xdfff) are invalid. If you - want to allow escape sequences such as \x{d800} you can set the - PCRE2_EXTRA_ALLOW_SURROGATE_ESCAPES extra option, as described in the - section entitled "Extra compile options" below. However, this is pos- + able the error that is given if an escape sequence for an invalid Uni- + code code point is encountered in the pattern. In particular, the so- + called "surrogate" code points (0xd800 to 0xdfff) are invalid. If you + want to allow escape sequences such as \x{d800} you can set the + PCRE2_EXTRA_ALLOW_SURROGATE_ESCAPES extra option, as described in the + section entitled "Extra compile options" below. However, this is pos- sible only in UTF-8 and UTF-32 modes, because these values are not rep- resentable in UTF-16. PCRE2_UCP This option changes the way PCRE2 processes \B, \b, \D, \d, \S, \s, \W, - \w, and some of the POSIX character classes. By default, only ASCII - characters are recognized, but if PCRE2_UCP is set, Unicode properties - are used instead to classify characters. More details are given in the + \w, and some of the POSIX character classes. By default, only ASCII + characters are recognized, but if PCRE2_UCP is set, Unicode properties + are used instead to classify characters. More details are given in the section on generic character types in the pcre2pattern page. If you set - PCRE2_UCP, matching one of the items it affects takes much longer. The - option is available only if PCRE2 has been compiled with Unicode sup- + PCRE2_UCP, matching one of the items it affects takes much longer. The + option is available only if PCRE2 has been compiled with Unicode sup- port (which is the default). PCRE2_UNGREEDY - This option inverts the "greediness" of the quantifiers so that they - are not greedy by default, but become greedy if followed by "?". It is - not compatible with Perl. It can also be set by a (?U) option setting + This option inverts the "greediness" of the quantifiers so that they + are not greedy by default, but become greedy if followed by "?". It is + not compatible with Perl. It can also be set by a (?U) option setting within the pattern. PCRE2_USE_OFFSET_LIMIT This option must be set for pcre2_compile() if pcre2_set_offset_limit() - is going to be used to set a non-default offset limit in a match con- - text for matches that use this pattern. An error is generated if an - offset limit is set without this option. For more details, see the - description of pcre2_set_offset_limit() in the section that describes + is going to be used to set a non-default offset limit in a match con- + text for matches that use this pattern. An error is generated if an + offset limit is set without this option. For more details, see the + description of pcre2_set_offset_limit() in the section that describes match contexts. See also the PCRE2_FIRSTLINE option above. PCRE2_UTF - This option causes PCRE2 to regard both the pattern and the subject - strings that are subsequently processed as strings of UTF characters - instead of single-code-unit strings. It is available when PCRE2 is - built to include Unicode support (which is the default). If Unicode - support is not available, the use of this option provokes an error. - Details of how PCRE2_UTF changes the behaviour of PCRE2 are given in + This option causes PCRE2 to regard both the pattern and the subject + strings that are subsequently processed as strings of UTF characters + instead of single-code-unit strings. It is available when PCRE2 is + built to include Unicode support (which is the default). If Unicode + support is not available, the use of this option provokes an error. + Details of how PCRE2_UTF changes the behaviour of PCRE2 are given in the pcre2unicode page. Extra compile options - Unlike the main compile-time options, the extra options are not saved + Unlike the main compile-time options, the extra options are not saved with the compiled pattern. The option bits that can be set in a compile - context by calling the pcre2_set_compile_extra_options() function are + context by calling the pcre2_set_compile_extra_options() function are as follows: PCRE2_EXTRA_ALLOW_SURROGATE_ESCAPES - This option applies when compiling a pattern in UTF-8 or UTF-32 mode. - It is forbidden in UTF-16 mode, and ignored in non-UTF modes. Unicode + This option applies when compiling a pattern in UTF-8 or UTF-32 mode. + It is forbidden in UTF-16 mode, and ignored in non-UTF modes. Unicode "surrogate" code points in the range 0xd800 to 0xdfff are used in pairs - in UTF-16 to encode code points with values in the range 0x10000 to - 0x10ffff. The surrogates cannot therefore be represented in UTF-16. + in UTF-16 to encode code points with values in the range 0x10000 to + 0x10ffff. The surrogates cannot therefore be represented in UTF-16. They can be represented in UTF-8 and UTF-32, but are defined as invalid - code points, and cause errors if encountered in a UTF-8 or UTF-32 + code points, and cause errors if encountered in a UTF-8 or UTF-32 string that is being checked for validity by PCRE2. - These values also cause errors if encountered in escape sequences such + These values also cause errors if encountered in escape sequences such as \x{d912} within a pattern. However, it seems that some applications, - when using PCRE2 to check for unwanted characters in UTF-8 strings, - explicitly test for the surrogates using escape sequences. The - PCRE2_NO_UTF_CHECK option does not disable the error that occurs, - because it applies only to the testing of input strings for UTF valid- + when using PCRE2 to check for unwanted characters in UTF-8 strings, + explicitly test for the surrogates using escape sequences. The + PCRE2_NO_UTF_CHECK option does not disable the error that occurs, + because it applies only to the testing of input strings for UTF valid- ity. - If the extra option PCRE2_EXTRA_ALLOW_SURROGATE_ESCAPES is set, surro- - gate code point values in UTF-8 and UTF-32 patterns no longer provoke - errors and are incorporated in the compiled pattern. However, they can - only match subject characters if the matching function is called with + If the extra option PCRE2_EXTRA_ALLOW_SURROGATE_ESCAPES is set, surro- + gate code point values in UTF-8 and UTF-32 patterns no longer provoke + errors and are incorporated in the compiled pattern. However, they can + only match subject characters if the matching function is called with PCRE2_NO_UTF_CHECK set. PCRE2_EXTRA_BAD_ESCAPE_IS_LITERAL - This is a dangerous option. Use with care. By default, an unrecognized - escape such as \j or a malformed one such as \x{2z} causes a compile- + This is a dangerous option. Use with care. By default, an unrecognized + escape such as \j or a malformed one such as \x{2z} causes a compile- time error when detected by pcre2_compile(). Perl is somewhat inconsis- - tent in handling such items: for example, \j is treated as a literal - "j", and non-hexadecimal digits in \x{} are just ignored, though warn- - ings are given in both cases if Perl's warning switch is enabled. How- - ever, a malformed octal number after \o{ always causes an error in + tent in handling such items: for example, \j is treated as a literal + "j", and non-hexadecimal digits in \x{} are just ignored, though warn- + ings are given in both cases if Perl's warning switch is enabled. How- + ever, a malformed octal number after \o{ always causes an error in Perl. - If the PCRE2_EXTRA_BAD_ESCAPE_IS_LITERAL extra option is passed to - pcre2_compile(), all unrecognized or erroneous escape sequences are - treated as single-character escapes. For example, \j is a literal "j" - and \x{2z} is treated as the literal string "x{2z}". Setting this - option means that typos in patterns may go undetected and have unex- + If the PCRE2_EXTRA_BAD_ESCAPE_IS_LITERAL extra option is passed to + pcre2_compile(), all unrecognized or erroneous escape sequences are + treated as single-character escapes. For example, \j is a literal "j" + and \x{2z} is treated as the literal string "x{2z}". Setting this + option means that typos in patterns may go undetected and have unex- pected results. This is a dangerous option. Use with care. PCRE2_EXTRA_MATCH_LINE - This option is provided for use by the -x option of pcre2grep. It - causes the pattern only to match complete lines. This is achieved by - automatically inserting the code for "^(?:" at the start of the com- - piled pattern and ")$" at the end. Thus, when PCRE2_MULTILINE is set, - the matched line may be in the middle of the subject string. This + This option is provided for use by the -x option of pcre2grep. It + causes the pattern only to match complete lines. This is achieved by + automatically inserting the code for "^(?:" at the start of the com- + piled pattern and ")$" at the end. Thus, when PCRE2_MULTILINE is set, + the matched line may be in the middle of the subject string. This option can be used with PCRE2_LITERAL. PCRE2_EXTRA_MATCH_WORD - This option is provided for use by the -w option of pcre2grep. It - causes the pattern only to match strings that have a word boundary at - the start and the end. This is achieved by automatically inserting the - code for "\b(?:" at the start of the compiled pattern and ")\b" at the - end. The option may be used with PCRE2_LITERAL. However, it is ignored + This option is provided for use by the -w option of pcre2grep. It + causes the pattern only to match strings that have a word boundary at + the start and the end. This is achieved by automatically inserting the + code for "\b(?:" at the start of the compiled pattern and ")\b" at the + end. The option may be used with PCRE2_LITERAL. However, it is ignored if PCRE2_EXTRA_MATCH_LINE is also set. @@ -1809,53 +1814,53 @@ JUST-IN-TIME (JIT) COMPILATION void pcre2_jit_stack_free(pcre2_jit_stack *jit_stack); - These functions provide support for JIT compilation, which, if the - just-in-time compiler is available, further processes a compiled pat- + These functions provide support for JIT compilation, which, if the + just-in-time compiler is available, further processes a compiled pat- tern into machine code that executes much faster than the pcre2_match() - interpretive matching function. Full details are given in the pcre2jit + interpretive matching function. Full details are given in the pcre2jit documentation. - JIT compilation is a heavyweight optimization. It can take some time - for patterns to be analyzed, and for one-off matches and simple pat- - terns the benefit of faster execution might be offset by a much slower - compilation time. Most (but not all) patterns can be optimized by the + JIT compilation is a heavyweight optimization. It can take some time + for patterns to be analyzed, and for one-off matches and simple pat- + terns the benefit of faster execution might be offset by a much slower + compilation time. Most (but not all) patterns can be optimized by the JIT compiler. LOCALE SUPPORT - PCRE2 handles caseless matching, and determines whether characters are - letters, digits, or whatever, by reference to a set of tables, indexed - by character code point. This applies only to characters whose code - points are less than 256. By default, higher-valued code points never - match escapes such as \w or \d. However, if PCRE2 is built with Uni- + PCRE2 handles caseless matching, and determines whether characters are + letters, digits, or whatever, by reference to a set of tables, indexed + by character code point. This applies only to characters whose code + points are less than 256. By default, higher-valued code points never + match escapes such as \w or \d. However, if PCRE2 is built with Uni- code support, all characters can be tested with \p and \P, or, alterna- - tively, the PCRE2_UCP option can be set when a pattern is compiled; - this causes \w and friends to use Unicode property support instead of + tively, the PCRE2_UCP option can be set when a pattern is compiled; + this causes \w and friends to use Unicode property support instead of the built-in tables. - The use of locales with Unicode is discouraged. If you are handling - characters with code points greater than 128, you should either use + The use of locales with Unicode is discouraged. If you are handling + characters with code points greater than 128, you should either use Unicode support, or use locales, but not try to mix the two. - PCRE2 contains an internal set of character tables that are used by - default. These are sufficient for many applications. Normally, the + PCRE2 contains an internal set of character tables that are used by + default. These are sufficient for many applications. Normally, the internal tables recognize only ASCII characters. However, when PCRE2 is built, it is possible to cause the internal tables to be rebuilt in the default "C" locale of the local system, which may cause them to be dif- ferent. - The internal tables can be overridden by tables supplied by the appli- - cation that calls PCRE2. These may be created in a different locale - from the default. As more and more applications change to using Uni- + The internal tables can be overridden by tables supplied by the appli- + cation that calls PCRE2. These may be created in a different locale + from the default. As more and more applications change to using Uni- code, the need for this locale support is expected to die away. - External tables are built by calling the pcre2_maketables() function, - in the relevant locale. The result can be passed to pcre2_compile() as - often as necessary, by creating a compile context and calling - pcre2_set_character_tables() to set the tables pointer therein. For - example, to build and use tables that are appropriate for the French - locale (where accented characters with values greater than 128 are + External tables are built by calling the pcre2_maketables() function, + in the relevant locale. The result can be passed to pcre2_compile() as + often as necessary, by creating a compile context and calling + pcre2_set_character_tables() to set the tables pointer therein. For + example, to build and use tables that are appropriate for the French + locale (where accented characters with values greater than 128 are treated as letters), the following code could be used: setlocale(LC_CTYPE, "fr_FR"); @@ -1864,15 +1869,15 @@ LOCALE SUPPORT pcre2_set_character_tables(ccontext, tables); re = pcre2_compile(..., ccontext); - The locale name "fr_FR" is used on Linux and other Unix-like systems; - if you are using Windows, the name for the French locale is "french". - It is the caller's responsibility to ensure that the memory containing + The locale name "fr_FR" is used on Linux and other Unix-like systems; + if you are using Windows, the name for the French locale is "french". + It is the caller's responsibility to ensure that the memory containing the tables remains available for as long as it is needed. The pointer that is passed (via the compile context) to pcre2_compile() - is saved with the compiled pattern, and the same tables are used by - pcre2_match() and pcre_dfa_match(). Thus, for any single pattern, com- - pilation and matching both happen in the same locale, but different + is saved with the compiled pattern, and the same tables are used by + pcre2_match() and pcre_dfa_match(). Thus, for any single pattern, com- + pilation and matching both happen in the same locale, but different patterns can be processed in different locales. @@ -1880,13 +1885,13 @@ INFORMATION ABOUT A COMPILED PATTERN int pcre2_pattern_info(const pcre2 *code, uint32_t what, void *where); - The pcre2_pattern_info() function returns general information about a + The pcre2_pattern_info() function returns general information about a compiled pattern. For information about callouts, see the next section. - The first argument for pcre2_pattern_info() is a pointer to the com- + The first argument for pcre2_pattern_info() is a pointer to the com- piled pattern. The second argument specifies which piece of information - is required, and the third argument is a pointer to a variable to - receive the data. If the third argument is NULL, the first argument is - ignored, and the function returns the size in bytes of the variable + is required, and the third argument is a pointer to a variable to + receive the data. If the third argument is NULL, the first argument is + ignored, and the function returns the size in bytes of the variable that is required for the information requested. Otherwise, the yield of the function is zero for success, or one of the following negative num- bers: @@ -1896,9 +1901,9 @@ INFORMATION ABOUT A COMPILED PATTERN PCRE2_ERROR_BADOPTION the value of what was invalid PCRE2_ERROR_UNSET the requested field is not set - The "magic number" is placed at the start of each compiled pattern as - an simple check against passing an arbitrary memory pointer. Here is a - typical call of pcre2_pattern_info(), to obtain the length of the com- + The "magic number" is placed at the start of each compiled pattern as + an simple check against passing an arbitrary memory pointer. Here is a + typical call of pcre2_pattern_info(), to obtain the length of the com- piled pattern: int rc; @@ -1916,22 +1921,22 @@ INFORMATION ABOUT A COMPILED PATTERN PCRE2_INFO_EXTRAOPTIONS Return copies of the pattern's options. The third argument should point - 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 (*XXX) - option settings such as (*UTF) at the start of the pattern itself. - PCRE2_INFO_EXTRAOPTIONS returns the extra options that were set in the - compile context by calling the pcre2_set_compile_extra_options() func- + 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 (*XXX) + option settings such as (*UTF) at the start of the pattern itself. + PCRE2_INFO_EXTRAOPTIONS returns the extra options that were set in the + compile context by calling the pcre2_set_compile_extra_options() func- tion. - For example, if the pattern /(*UTF)abc/ is compiled with the - PCRE2_EXTENDED option, the result for PCRE2_INFO_ALLOPTIONS is - PCRE2_EXTENDED and PCRE2_UTF. Option settings such as (?i) that can - change within a pattern do not affect the result of PCRE2_INFO_ALLOP- + For example, if the pattern /(*UTF)abc/ is compiled with the + PCRE2_EXTENDED option, the result for PCRE2_INFO_ALLOPTIONS is + PCRE2_EXTENDED and PCRE2_UTF. Option settings such as (?i) that can + change within a pattern do not affect the result of PCRE2_INFO_ALLOP- TIONS, even if they appear right at the start of the pattern. (This was different in some earlier releases.) - A pattern compiled without PCRE2_ANCHORED is automatically anchored by + A pattern compiled without PCRE2_ANCHORED is automatically anchored by PCRE2 if the first significant item in every top-level branch is one of the following: @@ -1940,7 +1945,7 @@ INFORMATION ABOUT A COMPILED PATTERN \G always .* sometimes - see below - When .* is the first significant item, anchoring is possible only when + When .* is the first significant item, anchoring is possible only when all the following are true: .* is not in an atomic group @@ -1950,178 +1955,178 @@ INFORMATION ABOUT A COMPILED PATTERN Neither (*PRUNE) nor (*SKIP) appears in the pattern PCRE2_NO_DOTSTAR_ANCHOR is not set - For patterns that are auto-anchored, the PCRE2_ANCHORED bit is set in + For patterns that are auto-anchored, the PCRE2_ANCHORED bit is set in the options returned for PCRE2_INFO_ALLOPTIONS. PCRE2_INFO_BACKREFMAX - Return the number of the highest back reference in the pattern. The - third argument should point to an uint32_t variable. Named subpatterns - acquire numbers as well as names, and these count towards the highest - back reference. Back references such as \4 or \g{12} match the cap- - tured characters of the given group, but in addition, the check that a + Return the number of the highest back reference in the pattern. The + third argument should point to an uint32_t variable. Named subpatterns + acquire numbers as well as names, and these count towards the highest + back reference. Back references such as \4 or \g{12} match the cap- + tured characters of the given group, but in addition, the check that a capturing group is set in a conditional subpattern such as (?(3)a|b) is - also a back reference. Zero is returned if there are no back refer- + also a back reference. Zero is returned if there are no back refer- ences. PCRE2_INFO_BSR The output is a uint32_t whose value indicates what character sequences the \R escape sequence matches. A value of PCRE2_BSR_UNICODE means that - \R matches any Unicode line ending sequence; a value of PCRE2_BSR_ANY- + \R matches any Unicode line ending sequence; a value of PCRE2_BSR_ANY- CRLF means that \R matches only CR, LF, or CRLF. PCRE2_INFO_CAPTURECOUNT - Return the highest capturing subpattern number in the pattern. In pat- + 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_DEPTHLIMIT - If the pattern set a backtracking depth limit by including an item of - the form (*LIMIT_DEPTH=nnnn) at the start, the value is returned. The - third argument should point to an unsigned 32-bit integer. If no such - value has been set, the call to pcre2_pattern_info() returns the error + If the pattern set a backtracking depth limit by including an item of + the form (*LIMIT_DEPTH=nnnn) at the start, the value is returned. The + third argument should point to an unsigned 32-bit integer. If no such + value has been set, the call to pcre2_pattern_info() returns the error PCRE2_ERROR_UNSET. Note that this limit will only be used during match- - ing if it is less than the limit set or defaulted by the caller of the + ing if it is less than the limit set or defaulted by the caller of the match function. 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 + 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 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. + 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 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 - Return the value of the first code unit of any matched string for a - pattern where PCRE2_INFO_FIRSTCODETYPE returns 1; otherwise return 0. - The third argument should point to an uint32_t variable. In the 8-bit - library, the value is always less than 256. In the 16-bit library the - value can be up to 0xffff. In the 32-bit library in UTF-32 mode the + Return the value of the first code unit of any matched string for a + pattern where PCRE2_INFO_FIRSTCODETYPE returns 1; otherwise return 0. + The third argument should point to an uint32_t variable. In the 8-bit + library, the value is always less than 256. In the 16-bit library the + value can be up to 0xffff. In the 32-bit library in UTF-32 mode the value can be up to 0x10ffff, and up to 0xffffffff when not using UTF-32 mode. PCRE2_INFO_FRAMESIZE Return the size (in bytes) of the data frames that are used to remember - backtracking positions when the pattern is processed by pcre2_match() - without the use of JIT. The third argument should point to an size_t + backtracking positions when the pattern is processed by pcre2_match() + without the use of JIT. The third argument should point to an size_t variable. The frame size depends on the number of capturing parentheses - in the pattern. Each additional capturing group adds two PCRE2_SIZE + in the pattern. Each additional capturing group adds two PCRE2_SIZE variables. PCRE2_INFO_HASBACKSLASHC - Return 1 if the pattern contains any instances of \C, otherwise 0. The + 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 - Return 1 if the pattern contains any explicit matches for CR or LF + Return 1 if the pattern contains any explicit matches for CR or LF characters, otherwise 0. The third argument should point to an uint32_t - variable. An explicit match is either a literal CR or LF character, or - \r or \n or one of the equivalent hexadecimal or octal escape + variable. An explicit match is either a literal CR or LF character, or + \r or \n or one of the equivalent hexadecimal or octal escape sequences. PCRE2_INFO_HEAPLIMIT If the pattern set a heap memory limit by including an item of the form (*LIMIT_HEAP=nnnn) at the start, the value is returned. The third argu- - ment should point to an unsigned 32-bit integer. If no such value has - been set, the call to pcre2_pattern_info() returns the error + ment should point to an unsigned 32-bit integer. If no such value has + been set, the call to pcre2_pattern_info() returns the error PCRE2_ERROR_UNSET. Note that this limit will only be used during match- - ing if it is less than the limit set or defaulted by the caller of the + ing if it is less than the limit set or defaulted by the caller of the match function. PCRE2_INFO_JCHANGED - Return 1 if the (?J) or (?-J) option setting is used in the pattern, - otherwise 0. The third argument should point to an uint32_t variable. - (?J) and (?-J) set and unset the local PCRE2_DUPNAMES option, respec- + Return 1 if the (?J) or (?-J) option setting is used in the pattern, + otherwise 0. The third argument should point to an uint32_t variable. + (?J) and (?-J) set and unset the local PCRE2_DUPNAMES option, respec- tively. PCRE2_INFO_JITSIZE - If the compiled pattern was successfully processed by pcre2_jit_com- - pile(), return the size of the JIT compiled code, otherwise return + If the compiled pattern was successfully processed by pcre2_jit_com- + pile(), return the size of the JIT compiled code, otherwise return zero. The third argument should point to a size_t variable. PCRE2_INFO_LASTCODETYPE - 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 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 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/ + 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 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 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 code unit that must exist in - any matched string, other than at its start, for a pattern where + Return the value of the rightmost literal code unit that must exist in + any matched string, other than at its start, for a pattern where PCRE2_INFO_LASTCODETYPE returns 1. Otherwise, return 0. The third argu- ment should point to an uint32_t variable. PCRE2_INFO_MATCHEMPTY - 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 + 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- + 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 - If the pattern set a match limit by including an item of the form - (*LIMIT_MATCH=nnnn) at the start, the value is returned. The third - argument should point to an unsigned 32-bit integer. If no such value - has been set, the call to pcre2_pattern_info() returns the error + If the pattern set a match limit by including an item of the form + (*LIMIT_MATCH=nnnn) at the start, the value is returned. The third + argument should point to an unsigned 32-bit integer. If no such value + has been set, the call to pcre2_pattern_info() returns the error PCRE2_ERROR_UNSET. Note that this limit will only be used during match- - ing if it is less than the limit set or defaulted by the caller of the + ing if it is less than the limit set or defaulted by the caller of the match function. PCRE2_INFO_MAXLOOKBEHIND Return the number of characters (not code units) in the longest lookbe- - hind assertion in the pattern. The third argument should point to an - unsigned 32-bit integer. This information is useful when doing multi- - segment matching using the partial matching facilities. Note that the + hind assertion in the pattern. The third argument should point to an + unsigned 32-bit integer. This information is useful when doing multi- + segment matching using the partial matching facilities. Note that the simple assertions \b and \B require a one-character lookbehind. \A also - registers a one-character lookbehind, though it does not actually - inspect the previous character. This is to ensure that at least one - character from the old segment is retained when a new segment is pro- + registers a one-character lookbehind, though it does not actually + inspect the previous character. This is to ensure that at least one + character from the old segment is retained when a new segment is pro- cessed. Otherwise, if there are no lookbehinds in the pattern, \A might match incorrectly at the start of a second or subsequent segment. PCRE2_INFO_MINLENGTH - If a minimum length for matching subject strings was computed, its - value is returned. Otherwise the returned value is 0. The value is a - number of characters, which in UTF mode may be different from the num- - ber of code units. The third argument should point to an uint32_t - variable. The value is a lower bound to the length of any matching - string. There may not be any strings of that length that do actually + If a minimum length for matching subject strings was computed, its + value is returned. Otherwise the returned value is 0. The value is a + number of characters, which in UTF mode may be different from the num- + ber of code units. The third argument should point to an uint32_t + variable. The value is a lower bound to the length of any matching + string. There may not be any strings of that length that do actually match, but every string that does match is at least that long. PCRE2_INFO_NAMECOUNT @@ -2129,50 +2134,50 @@ INFORMATION ABOUT A COMPILED PATTERN PCRE2_INFO_NAMETABLE PCRE2 supports the use of named as well as numbered capturing parenthe- - ses. The names are just an additional way of identifying the parenthe- + ses. The names are just an additional way of identifying the parenthe- ses, which still acquire numbers. Several convenience functions such as - pcre2_substring_get_byname() are provided for extracting captured sub- - strings by name. It is also possible to extract the data directly, by - first converting the name to a number in order to access the correct - pointers in the output vector (described with pcre2_match() below). To - do the conversion, you need to use the name-to-number map, which is + pcre2_substring_get_byname() are provided for extracting captured sub- + strings by name. It is also possible to extract the data directly, by + first converting the name to a number in order to access the correct + pointers in the output vector (described with pcre2_match() below). To + do the conversion, you need to use the name-to-number map, which is described by these three values. - The map consists of a number of fixed-size entries. PCRE2_INFO_NAME- - COUNT gives the number of entries, and PCRE2_INFO_NAMEENTRYSIZE gives - the size of each entry in code units; both of these return a uint32_t + The map consists of a number of fixed-size entries. PCRE2_INFO_NAME- + COUNT gives the number of entries, and PCRE2_INFO_NAMEENTRYSIZE gives + the size of each entry in code units; both of these return a uint32_t value. The entry size depends on the length of the longest name. PCRE2_INFO_NAMETABLE returns a pointer to the first entry of the table. - This is a PCRE2_SPTR pointer to a block of code units. In the 8-bit - library, the first two bytes of each entry are the number of the cap- + This is a PCRE2_SPTR pointer to a block of code units. In the 8-bit + library, the first two bytes of each entry are the number of the cap- turing parenthesis, most significant byte first. In the 16-bit library, - the pointer points to 16-bit code units, the first of which contains - the parenthesis number. In the 32-bit library, the pointer points to - 32-bit code units, the first of which contains the parenthesis number. + the pointer points to 16-bit code units, the first of which contains + the parenthesis number. In the 32-bit library, the pointer points to + 32-bit code units, the first of which contains the parenthesis number. The rest of the entry is the corresponding name, zero terminated. - The names are in alphabetical order. If (?| is used to create multiple - groups with the same number, as described in the section on duplicate - subpattern numbers in the pcre2pattern page, the groups may be given - the same name, but there is only one entry in the table. Different + The names are in alphabetical order. If (?| is used to create multiple + groups with the same number, as described in the section on duplicate + subpattern numbers in the pcre2pattern page, the groups may be given + the same name, but there is only one entry in the table. Different names for groups of the same number are not permitted. - Duplicate names for subpatterns with different numbers are permitted, - but only if PCRE2_DUPNAMES is set. They appear in the table in the - order in which they were found in the pattern. In the absence of (?| - this is the order of increasing number; when (?| is used this is not + Duplicate names for subpatterns with different numbers are permitted, + but only if PCRE2_DUPNAMES is set. They appear in the table in the + order in which they were found in the pattern. In the absence of (?| + this is the order of increasing number; when (?| is used this is not necessarily the case because later subpatterns may have lower numbers. - As a simple example of the name/number table, consider the following - pattern after compilation by the 8-bit library (assume PCRE2_EXTENDED + As a simple example of the name/number table, consider the following + pattern after compilation by the 8-bit library (assume PCRE2_EXTENDED is set, so white space - including newlines - is ignored): (? (?(\d\d)?\d\d) - (?\d\d) - (?\d\d) ) - There are four named subpatterns, so the table has four entries, and - each entry in the table is eight bytes long. The table is as follows, + There are four named subpatterns, so the table has four entries, and + each entry in the table is eight bytes long. The table is as follows, with non-printing bytes shows in hexadecimal, and undefined bytes shown as ??: @@ -2181,8 +2186,8 @@ INFORMATION ABOUT A COMPILED PATTERN 00 04 m o n t h 00 00 02 y e a r 00 ?? - When writing code to extract data from named subpatterns using the - name-to-number map, remember that the length of the entries is likely + When writing code to extract data from named subpatterns using the + name-to-number map, remember that the length of the entries is likely to be different for each compiled pattern. PCRE2_INFO_NEWLINE @@ -2201,14 +2206,14 @@ INFORMATION ABOUT A COMPILED PATTERN PCRE2_INFO_SIZE - Return the size of the compiled pattern in bytes (for all three - libraries). The third argument should point to a size_t variable. This - value includes the size of the general data block that precedes the - code units of the compiled pattern itself. The value that is used when - pcre2_compile() is getting memory in which to place the compiled pat- - tern may be slightly larger than the value returned by this option, - because there are cases where the code that calculates the size has to - over-estimate. Processing a pattern with the JIT compiler does not + Return the size of the compiled pattern in bytes (for all three + libraries). The third argument should point to a size_t variable. This + value includes the size of the general data block that precedes the + code units of the compiled pattern itself. The value that is used when + pcre2_compile() is getting memory in which to place the compiled pat- + tern may be slightly larger than the value returned by this option, + because there are cases where the code that calculates the size has to + over-estimate. Processing a pattern with the JIT compiler does not alter the value returned by this option. @@ -2219,22 +2224,22 @@ INFORMATION ABOUT A PATTERN'S CALLOUTS void *user_data); A script language that supports the use of string arguments in callouts - might like to scan all the callouts in a pattern before running the + might like to scan all the callouts in a pattern before running the match. This can be done by calling pcre2_callout_enumerate(). The first - argument is a pointer to a compiled pattern, the second points to a - callback function, and the third is arbitrary user data. The callback - function is called for every callout in the pattern in the order in + argument is a pointer to a compiled pattern, the second points to a + callback function, and the third is arbitrary user data. The callback + function is called for every callout in the pattern in the order in which they appear. Its first argument is a pointer to a callout enumer- - ation block, and its second argument is the user_data value that was - passed to pcre2_callout_enumerate(). The contents of the callout enu- - meration block are described in the pcre2callout documentation, which + ation block, and its second argument is the user_data value that was + passed to pcre2_callout_enumerate(). The contents of the callout enu- + meration block are described in the pcre2callout documentation, which also gives further details about callouts. SERIALIZATION AND PRECOMPILING - It is possible to save compiled patterns on disc or elsewhere, and - reload them later, subject to a number of restrictions. The functions + It is possible to save compiled patterns on disc or elsewhere, and + reload them later, subject to a number of restrictions. The functions whose names begin with pcre2_serialize_ are used for this purpose. They are described in the pcre2serialize documentation. @@ -2249,56 +2254,56 @@ THE MATCH DATA BLOCK void pcre2_match_data_free(pcre2_match_data *match_data); - Information about a successful or unsuccessful match is placed in a - match data block, which is an opaque structure that is accessed by - function calls. In particular, the match data block contains a vector - of offsets into the subject string that define the matched part of the - subject and any substrings that were captured. This is known as the + Information about a successful or unsuccessful match is placed in a + match data block, which is an opaque structure that is accessed by + function calls. In particular, the match data block contains a vector + of offsets into the subject string that define the matched part of the + subject and any substrings that were captured. This is known as the ovector. - Before calling pcre2_match(), pcre2_dfa_match(), or pcre2_jit_match() + Before calling pcre2_match(), pcre2_dfa_match(), or pcre2_jit_match() you must create a match data block by calling one of the creation func- - tions above. For pcre2_match_data_create(), the first argument is the - number of pairs of offsets in the ovector. One pair of offsets is + tions above. For pcre2_match_data_create(), the first argument is the + number of pairs of offsets in the ovector. One pair of offsets is required to identify the string that matched the whole pattern, with an - additional pair for each captured substring. For example, a value of 4 - creates enough space to record the matched portion of the subject plus - three captured substrings. A minimum of at least 1 pair is imposed by + additional pair for each captured substring. For example, a value of 4 + creates enough space to record the matched portion of the subject plus + three captured substrings. A minimum of at least 1 pair is imposed by pcre2_match_data_create(), so it is always possible to return the over- all matched string. The second argument of pcre2_match_data_create() is a pointer to a gen- - eral context, which can specify custom memory management for obtaining + eral context, which can specify custom memory management for obtaining the memory for the match data block. If you are not using custom memory management, pass NULL, which causes malloc() to be used. - For pcre2_match_data_create_from_pattern(), the first argument is a + For pcre2_match_data_create_from_pattern(), the first argument is a pointer to a compiled pattern. The ovector is created to be exactly the right size to hold all the substrings a pattern might capture. The sec- - ond argument is again a pointer to a general context, but in this case + ond argument is again a pointer to a general context, but in this case if NULL is passed, the memory is obtained using the same allocator that was used for the compiled pattern (custom or default). - A match data block can be used many times, with the same or different - compiled patterns. You can extract information from a match data block + A match data block can be used many times, with the same or different + compiled patterns. You can extract information from a match data block after a match operation has finished, using functions that are - described in the sections on matched strings and other match data + described in the sections on matched strings and other match data below. - When a call of pcre2_match() fails, valid data is available in the - match block only when the error is PCRE2_ERROR_NOMATCH, - PCRE2_ERROR_PARTIAL, or one of the error codes for an invalid UTF + When a call of pcre2_match() fails, valid data is available in the + match block only when the error is PCRE2_ERROR_NOMATCH, + PCRE2_ERROR_PARTIAL, or one of the error codes for an invalid UTF string. Exactly what is available depends on the error, and is detailed below. - 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 running a - match, you must not free a compiled pattern or a subject string until - after all operations on the match data block (for that match) have + 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 running a + match, you must not free a compiled pattern or a subject string until + after all operations on the match data block (for that match) have taken place. - When a match data block itself is no longer needed, it should be freed + When a match data block itself is no longer needed, it should be freed by calling pcre2_match_data_free(). @@ -2309,15 +2314,15 @@ MATCHING A PATTERN: THE TRADITIONAL FUNCTION uint32_t options, pcre2_match_data *match_data, pcre2_match_context *mcontext); - The function pcre2_match() is called to match a subject string against - a compiled pattern, which is passed in the code argument. You can call + The function pcre2_match() is called to match a subject string against + a compiled pattern, which is passed in the code argument. You can call pcre2_match() with the same code argument as many times as you like, in - order to find multiple matches in the subject string or to match dif- + order to find multiple matches in the subject string or to match dif- ferent subject strings with the same pattern. - This function is the main matching facility of the library, and it - operates in a Perl-like manner. For specialist use there is also an - alternative matching function, which is described below in the section + This function is the main matching facility of the library, and it + operates in a Perl-like manner. For specialist use there is also an + alternative matching function, which is described below in the section about the pcre2_dfa_match() function. Here is an example of a simple call to pcre2_match(): @@ -2332,187 +2337,187 @@ MATCHING A PATTERN: THE TRADITIONAL FUNCTION md, /* the match data block */ NULL); /* a match context; NULL means use defaults */ - If the subject string is zero-terminated, the length can be given as + If the subject string is zero-terminated, the length can be given as PCRE2_ZERO_TERMINATED. A match context must be provided if certain less common matching parameters are to be changed. For details, see the sec- tion on the match context above. The string to be matched by pcre2_match() - The subject string is passed to pcre2_match() as a pointer in subject, - a length in length, and a starting offset in startoffset. The length - and offset are in code units, not characters. That is, they are in - bytes for the 8-bit library, 16-bit code units for the 16-bit library, - and 32-bit code units for the 32-bit library, whether or not UTF pro- + The subject string is passed to pcre2_match() as a pointer in subject, + a length in length, and a starting offset in startoffset. The length + and offset are in code units, not characters. That is, they are in + bytes for the 8-bit library, 16-bit code units for the 16-bit library, + and 32-bit code units for the 32-bit library, whether or not UTF pro- cessing is enabled. If startoffset is greater than the length of the subject, pcre2_match() - returns PCRE2_ERROR_BADOFFSET. When the starting offset is zero, the - search for a match starts at the beginning of the subject, and this is + returns PCRE2_ERROR_BADOFFSET. When the starting offset is zero, the + search for a match starts at the beginning of the subject, and this is by far the most common case. In UTF-8 or UTF-16 mode, the starting off- - set must point to the start of a character, or to the end of the sub- - ject (in UTF-32 mode, one code unit equals one character, so all off- - sets are valid). Like the pattern string, the subject may contain + set must point to the start of a character, or to the end of the sub- + ject (in UTF-32 mode, one code unit equals one character, so all off- + sets are valid). Like the pattern string, the subject may contain binary zeroes. - A non-zero starting offset is useful when searching for another match - in the same subject by calling pcre2_match() again after a previous - success. Setting startoffset differs from passing over a shortened - string and setting PCRE2_NOTBOL in the case of a pattern that begins + A non-zero starting offset is useful when searching for another match + in the same subject by calling pcre2_match() again after a previous + success. Setting startoffset differs from passing over a shortened + string and setting PCRE2_NOTBOL in the case of a pattern that begins with any kind of lookbehind. For example, consider the pattern \Biss\B - which finds occurrences of "iss" in the middle of words. (\B matches - only if the current position in the subject is not a word boundary.) + which finds occurrences of "iss" in the middle of words. (\B matches + only if the current position in the subject is not a word boundary.) When applied to the string "Mississipi" the first call to pcre2_match() - finds the first occurrence. If pcre2_match() is called again with just - the remainder of the subject, namely "issipi", it does not match, + finds the first occurrence. If pcre2_match() is called again with just + the remainder of the subject, namely "issipi", it does not match, because \B is always false at the start of the subject, which is deemed - to be a word boundary. However, if pcre2_match() is passed the entire + to be a word boundary. However, if pcre2_match() is passed the entire string again, but with startoffset set to 4, it finds the second occur- - rence of "iss" because it is able to look behind the starting point to + rence of "iss" because it is able to look behind the starting point to discover that it is preceded by a letter. - Finding all the matches in a subject is tricky when the pattern can + Finding all the matches in a subject is tricky when the pattern can match an empty string. It is possible to emulate Perl's /g behaviour by - first trying the match again at the same offset, with the - PCRE2_NOTEMPTY_ATSTART and PCRE2_ANCHORED options, and then if that - fails, advancing the starting offset and trying an ordinary match - again. There is some code that demonstrates how to do this in the - pcre2demo sample program. In the most general case, you have to check - to see if the newline convention recognizes CRLF as a newline, and if - so, and the current character is CR followed by LF, advance the start- + first trying the match again at the same offset, with the + PCRE2_NOTEMPTY_ATSTART and PCRE2_ANCHORED options, and then if that + fails, advancing the starting offset and trying an ordinary match + again. There is some code that demonstrates how to do this in the + pcre2demo sample program. In the most general case, you have to check + to see if the newline convention recognizes CRLF as a newline, and if + so, and the current character is CR followed by LF, advance the start- ing offset by two characters instead of one. If a non-zero starting offset is passed when the pattern is anchored, a single attempt to match at the given offset is made. This can only suc- - ceed if the pattern does not require the match to be at the start of - the subject. In other words, the anchoring must be the result of set- - ting the PCRE2_ANCHORED option or the use of .* with PCRE2_DOTALL, not + ceed if the pattern does not require the match to be at the start of + the subject. In other words, the anchoring must be the result of set- + ting the PCRE2_ANCHORED option or the use of .* with PCRE2_DOTALL, not by starting the pattern with ^ or \A. Option bits for pcre2_match() The unused bits of the options argument for pcre2_match() must be zero. - The only bits that may be set are PCRE2_ANCHORED, PCRE2_ENDANCHORED, - PCRE2_NOTBOL, PCRE2_NOTEOL, PCRE2_NOTEMPTY, PCRE2_NOTEMPTY_ATSTART, - PCRE2_NO_JIT, PCRE2_NO_UTF_CHECK, PCRE2_PARTIAL_HARD, and PCRE2_PAR- + The only bits that may be set are PCRE2_ANCHORED, PCRE2_ENDANCHORED, + PCRE2_NOTBOL, PCRE2_NOTEOL, PCRE2_NOTEMPTY, PCRE2_NOTEMPTY_ATSTART, + PCRE2_NO_JIT, PCRE2_NO_UTF_CHECK, PCRE2_PARTIAL_HARD, and PCRE2_PAR- TIAL_SOFT. Their action is described below. - Setting PCRE2_ANCHORED or PCRE2_ENDANCHORED at match time is not sup- - ported by the just-in-time (JIT) compiler. If it is set, JIT matching - is disabled and the interpretive code in pcre2_match() is run. Apart - from PCRE2_NO_JIT (obviously), the remaining options are supported for + Setting PCRE2_ANCHORED or PCRE2_ENDANCHORED at match time is not sup- + ported by the just-in-time (JIT) compiler. If it is set, JIT matching + is disabled and the interpretive code in pcre2_match() is run. Apart + from PCRE2_NO_JIT (obviously), the remaining options are supported for JIT matching. PCRE2_ANCHORED The PCRE2_ANCHORED option limits pcre2_match() to matching at the first - matching position. If a pattern was compiled with PCRE2_ANCHORED, or - turned out to be anchored by virtue of its contents, it cannot be made - unachored at matching time. Note that setting the option at match time + matching position. If a pattern was compiled with PCRE2_ANCHORED, or + turned out to be anchored by virtue of its contents, it cannot be made + unachored at matching time. Note that setting the option at match time disables JIT matching. PCRE2_ENDANCHORED - If the PCRE2_ENDANCHORED option is set, any string that pcre2_match() - matches must be right at the end of the subject string. Note that set- + If the PCRE2_ENDANCHORED option is set, any string that pcre2_match() + matches must be right at the end of the subject string. Note that set- ting the option at match time disables JIT matching. PCRE2_NOTBOL This option specifies that first character of the subject string is not - the beginning of a line, so the circumflex metacharacter should not - match before it. Setting this without having set PCRE2_MULTILINE at + the beginning of a line, so the circumflex metacharacter should not + match before it. Setting this without having set PCRE2_MULTILINE at compile time causes circumflex never to match. This option affects only the behaviour of the circumflex metacharacter. It does not affect \A. PCRE2_NOTEOL This option specifies that the end of the subject string is not the end - of a line, so the dollar metacharacter should not match it nor (except - in multiline mode) a newline immediately before it. Setting this with- - out having set PCRE2_MULTILINE at compile time causes dollar never to + of a line, so the dollar metacharacter should not match it nor (except + in multiline mode) a newline immediately before it. Setting this with- + out having set PCRE2_MULTILINE at compile time causes dollar never to match. This option affects only the behaviour of the dollar metacharac- ter. It does not affect \Z or \z. PCRE2_NOTEMPTY An empty string is not considered to be a valid match if this option is - set. If there are alternatives in the pattern, they are tried. If all - the alternatives match the empty string, the entire match fails. For + set. If there are alternatives in the pattern, they are tried. If all + the alternatives match the empty string, the entire match fails. For example, if the pattern a?b? - is applied to a string not beginning with "a" or "b", it matches an + is applied to a string not beginning with "a" or "b", it matches an empty string at the start of the subject. With PCRE2_NOTEMPTY set, this - match is not valid, so pcre2_match() searches further into the string + match is not valid, so pcre2_match() searches further into the string for occurrences of "a" or "b". PCRE2_NOTEMPTY_ATSTART - This is like PCRE2_NOTEMPTY, except that it locks out an empty string + This is like PCRE2_NOTEMPTY, except that it locks out an empty string match only at the first matching position, that is, at the start of the - subject plus the starting offset. An empty string match later in the - subject is permitted. If the pattern is anchored, such a match can + subject plus the starting offset. An empty string match later in the + subject is permitted. If the pattern is anchored, such a match can occur only if the pattern contains \K. PCRE2_NO_JIT - By default, if a pattern has been successfully processed by - pcre2_jit_compile(), JIT is automatically used when pcre2_match() is - called with options that JIT supports. Setting PCRE2_NO_JIT disables + By default, if a pattern has been successfully processed by + pcre2_jit_compile(), JIT is automatically used when pcre2_match() is + called with options that JIT supports. Setting PCRE2_NO_JIT disables the use of JIT; it forces matching to be done by the interpreter. PCRE2_NO_UTF_CHECK When PCRE2_UTF is set at compile time, the validity of the subject as a - UTF string is checked by default when pcre2_match() is subsequently - called. If a non-zero starting offset is given, the check is applied - only to that part of the subject that could be inspected during match- - ing, 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 are no - lookbehind assertions in the pattern, the check starts at the starting - offset. Otherwise, it starts at the length of the longest lookbehind + UTF string is checked by default when pcre2_match() is subsequently + called. If a non-zero starting offset is given, the check is applied + only to that part of the subject that could be inspected during match- + ing, 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 are no + lookbehind assertions in the pattern, the check starts at the starting + offset. Otherwise, it starts at the length of the longest lookbehind before the starting offset, or at the start of the subject if there are - not that many characters before the starting offset. Note that the + not that many characters before the starting offset. Note that the sequences \b and \B are one-character lookbehinds. The check is carried out before any other processing takes place, and a - negative error code is returned if the check fails. There are several - UTF error codes for each code unit width, corresponding to different - problems with the code unit sequence. There are discussions about the - validity of UTF-8 strings, UTF-16 strings, and UTF-32 strings in the + negative error code is returned if the check fails. There are several + UTF error codes for each code unit width, corresponding to different + problems with the code unit sequence. There are discussions about the + validity of UTF-8 strings, UTF-16 strings, and UTF-32 strings in the pcre2unicode page. - If you know that your subject is valid, and you want to skip these - checks for performance reasons, you can set the PCRE2_NO_UTF_CHECK - option when calling pcre2_match(). You might want to do this for the + If you know that your subject is valid, and you want to skip these + checks for performance reasons, you can set the PCRE2_NO_UTF_CHECK + option when calling pcre2_match(). You might want to do this for the second and subsequent calls to pcre2_match() if you are making repeated calls to find other matches in the same subject string. - WARNING: When PCRE2_NO_UTF_CHECK is set, the effect of passing an - invalid string as a subject, or an invalid value of startoffset, is + WARNING: When PCRE2_NO_UTF_CHECK is set, the effect of passing an + invalid string as a subject, or an invalid value of startoffset, is undefined. Your program may crash or loop indefinitely. PCRE2_PARTIAL_HARD PCRE2_PARTIAL_SOFT - These options turn on the partial matching feature. A partial match - occurs if the end of the subject string is reached successfully, but - there are not enough subject characters to complete the match. If this - happens when PCRE2_PARTIAL_SOFT (but not PCRE2_PARTIAL_HARD) is set, - matching continues by testing any remaining alternatives. Only if no - complete match can be found is PCRE2_ERROR_PARTIAL returned instead of - PCRE2_ERROR_NOMATCH. In other words, PCRE2_PARTIAL_SOFT specifies that - the caller is prepared to handle a partial match, but only if no com- + These options turn on the partial matching feature. A partial match + occurs if the end of the subject string is reached successfully, but + there are not enough subject characters to complete the match. If this + happens when PCRE2_PARTIAL_SOFT (but not PCRE2_PARTIAL_HARD) is set, + matching continues by testing any remaining alternatives. Only if no + complete match can be found is PCRE2_ERROR_PARTIAL returned instead of + PCRE2_ERROR_NOMATCH. In other words, PCRE2_PARTIAL_SOFT specifies that + the caller is prepared to handle a partial match, but only if no com- plete match can be found. - If PCRE2_PARTIAL_HARD is set, it overrides PCRE2_PARTIAL_SOFT. In this - case, if a partial match is found, pcre2_match() immediately returns - PCRE2_ERROR_PARTIAL, without considering any other alternatives. In + If PCRE2_PARTIAL_HARD is set, it overrides PCRE2_PARTIAL_SOFT. In this + case, if a partial match is found, pcre2_match() immediately returns + PCRE2_ERROR_PARTIAL, without considering any other alternatives. In other words, when PCRE2_PARTIAL_HARD is set, a partial match is consid- ered to be more important that an alternative complete match. @@ -2522,38 +2527,38 @@ MATCHING A PATTERN: THE TRADITIONAL FUNCTION 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 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 + 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 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 or equivalent + those characters in the pattern, or one of the \r or \n or equivalent octal or hexadecimal escape sequences. Implicit matches such as [^X] do - not count, nor does \s, even though it includes CR and LF in the char- + not count, nor does \s, even though it includes CR and LF in the char- acters 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. @@ -2564,81 +2569,81 @@ 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. - You can use auxiliary functions for accessing captured substrings by + 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 + 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 - offset of the first code unit after the end of a substring. These val- - ues are always code unit offsets, not character offsets. That is, they - are byte offsets in the 8-bit library, 16-bit offsets in the 16-bit + offset of the first code unit after the end of a substring. These val- + ues are always code unit offsets, not character offsets. That is, they + are byte offsets in the 8-bit library, 16-bit offsets in the 16-bit library, and 32-bit offsets in the 32-bit library. - After a partial match (error return PCRE2_ERROR_PARTIAL), only the - first pair of offsets (that is, ovector[0] and ovector[1]) are set. - They identify the part of the subject that was partially matched. See + After a partial match (error return PCRE2_ERROR_PARTIAL), only the + first pair of offsets (that is, ovector[0] and ovector[1]) are set. + They identify the part of the subject that was partially matched. See the pcre2partial documentation for details of partial matching. - After a fully successful match, the first pair of offsets identifies - the portion of the subject string that was matched by the entire pat- - tern. The next pair is used for the first captured substring, and so - on. The value returned by pcre2_match() is one more than the highest - numbered pair that has been set. For example, if two substrings have - been captured, the returned value is 3. If there are no captured sub- + After a fully successful match, the first pair of offsets identifies + the portion of the subject string that was matched by the entire pat- + tern. The next pair is used for the first captured substring, and so + on. The value returned by pcre2_match() is one more than the highest + numbered pair that has been set. For example, if two substrings have + been captured, the returned value is 3. If there are no captured sub- strings, the return value from a successful match is 1, indicating that just the first pair of offsets has been set. - 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 + 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. - If a capturing subpattern group is matched repeatedly within a single - match operation, it is the last portion of the subject that it matched + If a capturing subpattern group is matched repeatedly within a single + match operation, it is the last portion of the subject that it matched that is returned. If the ovector is too small to hold all the captured substring offsets, - as much as possible is filled in, and the function returns a value of - zero. If captured substrings are not of interest, pcre2_match() may be + as much as possible is filled in, and the function returns a value of + zero. If captured substrings are not of interest, pcre2_match() may be called with a match data block whose ovector is of minimum length (that is, one pair). - It is possible for capturing subpattern number n+1 to match some part + It is possible for capturing subpattern number n+1 to match some part of the subject when subpattern n has not been used at all. For example, - if the string "abc" is matched against the pattern (a|(z))(bc) the + if the string "abc" is matched against the pattern (a|(z))(bc) the return from the function is 4, and subpatterns 1 and 3 are matched, but - 2 is not. When this happens, both values in the offset pairs corre- + 2 is not. When this happens, both values in the offset pairs corre- sponding to unused subpatterns are set to PCRE2_UNSET. - Offset values that correspond to unused subpatterns at the end of the - expression are also set to PCRE2_UNSET. For example, if the string + Offset values that correspond to unused subpatterns at the end of the + expression are also set to PCRE2_UNSET. For example, if the string "abc" is matched against the pattern (abc)(x(yz)?)? subpatterns 2 and 3 - are not matched. The return from the function is 2, because the high- + are not matched. The return from the function is 2, because the high- est used capturing subpattern number is 1. The offsets for for the sec- - ond and third capturing subpatterns (assuming the vector is large + ond and third capturing subpatterns (assuming the vector is large enough, of course) are set to PCRE2_UNSET. Elements in the ovector that do not correspond to capturing parentheses in the pattern are never changed. That is, if a pattern contains n cap- turing parentheses, no more than ovector[0] to ovector[2n+1] are set by - pcre2_match(). The other elements retain whatever values they previ- + pcre2_match(). The other elements retain whatever values they previ- ously had. @@ -2648,60 +2653,60 @@ OTHER INFORMATION ABOUT A MATCH PCRE2_SIZE pcre2_get_startchar(pcre2_match_data *match_data); - As well as the offsets in the ovector, other information about a match - is retained in the match data block and can be retrieved by the above - functions in appropriate circumstances. If they are called at other + As well as the offsets in the ovector, other information about a match + is retained in the match data block and can be retrieved by the above + functions in appropriate circumstances. If they are called at other times, the result is undefined. - After a successful match, a partial match (PCRE2_ERROR_PARTIAL), or a + After a successful match, a partial match (PCRE2_ERROR_PARTIAL), or a failure to match (PCRE2_ERROR_NOMATCH), a (*MARK), (*PRUNE), or (*THEN) - name may be available. The function pcre2_get_mark() can be called to - access this name. The same function applies to all three verbs. It + name may be available. The function pcre2_get_mark() can be called to + access this name. The same function applies to all three verbs. It returns a pointer to the zero-terminated name, which is within the com- piled pattern. If no name is available, NULL is returned. The length of - the name (excluding the terminating zero) is stored in the code unit - that precedes the name. You should use this length instead of relying + the name (excluding the terminating zero) is stored in the code unit + that precedes the name. You should use this length instead of relying on the terminating zero if the name might contain a binary zero. - After a successful match, the name that is returned is the last - (*MARK), (*PRUNE), or (*THEN) name encountered on the matching path - through the pattern. Instances of (*PRUNE) and (*THEN) without names - are ignored. Thus, for example, if the matching path contains - (*MARK:A)(*PRUNE), the name "A" is returned. After a "no match" or a - partial match, the last encountered name is returned. For example, + After a successful match, the name that is returned is the last + (*MARK), (*PRUNE), or (*THEN) name encountered on the matching path + through the pattern. Instances of (*PRUNE) and (*THEN) without names + are ignored. Thus, for example, if the matching path contains + (*MARK:A)(*PRUNE), the name "A" is returned. After a "no match" or a + partial match, the last encountered name is returned. For example, consider this pattern: ^(*MARK:A)((*MARK:B)a|b)c - When it matches "bc", the returned name 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 name 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 name 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 the pcre2_get_error_message() func- - tion (see "Obtaining a textual error message" below). 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 checking is + If pcre2_match() fails, it returns a negative number. This can be con- + verted to a text string by calling the pcre2_get_error_message() func- + tion (see "Obtaining a textual error message" below). 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 checking 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 given in - the pcre2unicode page. The following are the other errors that may be + 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(): PCRE2_ERROR_NOMATCH @@ -2710,20 +2715,20 @@ 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 compiled pattern is passed to a function in - a library of a different code unit width, for example, a pattern com- - piled by the 8-bit library is passed to a 16-bit or 32-bit library + This error is given when a compiled pattern is passed to a function in + a library of a different code unit width, for example, a pattern com- + piled by the 8-bit library is passed to a 16-bit or 32-bit library function. PCRE2_ERROR_BADOFFSET @@ -2737,15 +2742,15 @@ 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_DEPTHLIMIT @@ -2758,14 +2763,14 @@ ERROR RETURNS FROM pcre2_match() 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_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 @@ -2774,10 +2779,10 @@ ERROR RETURNS FROM pcre2_match() PCRE2_ERROR_NOMEMORY - If a pattern contains many nested backtracking points, heap memory is - used to remember them. This error is given when the memory allocation - function (default or custom) fails. Note that a different error, - PCRE2_ERROR_HEAPLIMIT, is given if the amount of memory needed exceeds + If a pattern contains many nested backtracking points, heap memory is + used to remember them. This error is given when the memory allocation + function (default or custom) fails. Note that a different error, + PCRE2_ERROR_HEAPLIMIT, is given if the amount of memory needed exceeds the heap limit. PCRE2_ERROR_NULL @@ -2786,12 +2791,12 @@ 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. @@ -2800,20 +2805,20 @@ OBTAINING A TEXTUAL ERROR MESSAGE int pcre2_get_error_message(int errorcode, PCRE2_UCHAR *buffer, PCRE2_SIZE bufflen); - A text message for an error code from any PCRE2 function (compile, - match, or auxiliary) can be obtained by calling pcre2_get_error_mes- - sage(). The code is passed as the first argument, with the remaining - two arguments specifying a code unit buffer and its length in code - units, into which the text message is placed. The message is returned - in code units of the appropriate width for the library that is being + A text message for an error code from any PCRE2 function (compile, + match, or auxiliary) can be obtained by calling pcre2_get_error_mes- + sage(). The code is passed as the first argument, with the remaining + two arguments specifying a code unit buffer and its length in code + units, into which the text message is placed. The message is returned + in code units of the appropriate width for the library that is being used. - The returned message is terminated with a trailing zero, and the func- - tion returns the number of code units used, excluding the trailing + The returned message is terminated with a trailing zero, and the func- + tion returns the number of code units used, excluding the trailing zero. If the error number is unknown, the negative error code - PCRE2_ERROR_BADDATA is returned. If the buffer is too small, the mes- - sage is truncated (but still with a trailing zero), and the negative - error code PCRE2_ERROR_NOMEMORY is returned. None of the messages are + PCRE2_ERROR_BADDATA is returned. If the buffer is too small, the mes- + sage is truncated (but still with a trailing zero), and the negative + error code PCRE2_ERROR_NOMEMORY is returned. None of the messages are very long; a buffer size of 120 code units is ample. @@ -2832,39 +2837,39 @@ 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 @@ -2873,25 +2878,25 @@ 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 @@ -2902,8 +2907,8 @@ 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. @@ -2914,32 +2919,32 @@ 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(). @@ -2959,39 +2964,39 @@ 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(?\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 from the ovector, or use one of the + 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 from the ovector, or use one of the "bynumber" 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. @@ -3004,80 +3009,80 @@ 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, + 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, + 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 + 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), - (*PRUNE), or (*THEN) items in the pattern. The following forms are + ify the insertion of characters from capturing groups or (*MARK), + (*PRUNE), or (*THEN) items in the pattern. The following forms are always recognized: $$ insert a dollar character $ or ${} insert the contents of group $*MARK or ${*MARK} insert a (*MARK), (*PRUNE), or (*THEN) name - Either a group number or a group name can be given for . Curly - brackets are required only if the following character would be inter- + Either a group number or a group name can be given for . 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+=". $*MARK inserts the name from the last encountered (*MARK), (*PRUNE), or - (*THEN) on the matching path that has a name. (*MARK) must always - include a name, but (*PRUNE) and (*THEN) need not. For example, in the - case of (*MARK:A)(*PRUNE) the name inserted is "A", but for - (*MARK:A)(*PRUNE:B) the relevant name is "B". This facility can be - used to perform simple simultaneous substitutions, as this pcre2test + (*THEN) on the matching path that has a name. (*MARK) must always + include a name, but (*PRUNE) and (*THEN) need not. For example, in the + case of (*MARK:A)(*PRUNE) the name inserted is "A", but for + (*MARK:A)(*PRUNE:B) the relevant name is "B". This facility can be + used to perform simple simultaneous substitutions, as this pcre2test example shows: /(*MARK:pear)apple|(*MARK:orange)lemon/g,replace=${*MARK} apple lemon 2: pear orange - As well as the usual options for pcre2_match(), a number of additional + As well as the usual options for pcre2_match(), a number of additional options can be set in the options argument of pcre2_substitute(). PCRE2_SUBSTITUTE_GLOBAL causes the function to iterate over the subject - string, replacing every matching substring. If this option is not set, - only the first matching substring is replaced. The search for matches - takes place in the original subject string (that is, previous replace- - ments do not affect it). Iteration is implemented by advancing the - startoffset value for each search, which is always passed the entire + string, replacing every matching substring. If this option is not set, + only the first matching substring is replaced. The search for matches + takes place in the original subject string (that is, previous replace- + ments do not affect it). Iteration is implemented by advancing the + startoffset value for each search, which is always passed the entire subject string. If an offset limit is set in the match context, search- ing stops when that limit is reached. - You can restrict the effect of a global substitution to a portion of + You can restrict the effect of a global substitution to a portion of the subject string by setting either or both of startoffset and an off- set limit. Here is a pcre2test example: @@ -3085,87 +3090,87 @@ CREATING A NEW STRING WITH SUBSTITUTIONS ABC ABC ABC ABC\=offset=3,offset_limit=12 2: ABC A!C A!C ABC - When continuing with global substitutions after matching a substring + When continuing with global substitutions after matching a substring with zero length, an attempt to find a non-empty match at the same off- set is performed. If this is not successful, the offset 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 offset is advanced by two + two characters are CR, LF. In this case, the offset is advanced by two characters. - PCRE2_SUBSTITUTE_OVERFLOW_LENGTH changes what happens when the output + 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() + 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 + 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 + 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- + 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 + 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 + 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 + 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. - 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. + 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 + 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 - particular character codes, and backslash followed by any non-alphanu- - meric character quotes that character. Extended quoting can be coded + particular character codes, and backslash followed by any non-alphanu- + meric character quotes that character. Extended quoting can be coded using \Q...\E, exactly as in pattern strings. - There are also four escape sequences for forcing the case of inserted - letters. The insertion mechanism has three states: no case forcing, + There are also four escape sequences for forcing the case of inserted + letters. The insertion mechanism has three states: no case forcing, force upper case, and force lower case. The escape sequences change the current state: \U and \L change to upper or lower case forcing, respec- - tively, and \E (when not terminating a \Q quoted sequence) reverts to - no case forcing. The sequences \u and \l force the next character (if - it is a letter) to upper or lower case, respectively, and then the + tively, and \E (when not terminating a \Q quoted sequence) reverts to + no case forcing. The sequences \u and \l force the next character (if + it is a letter) to upper or lower case, respectively, and then the state automatically reverts to no case forcing. Case forcing applies to all inserted characters, including those from captured groups and let- ters within \Q...\E quoted sequences. Note that case forcing sequences such as \U...\E do not nest. For exam- - ple, the result of processing "\Uaa\LBB\Ecc\E" is "AAbbcc"; the final + ple, the result of processing "\Uaa\LBB\Ecc\E" is "AAbbcc"; the final \E has no effect. - The second effect of setting PCRE2_SUBSTITUTE_EXTENDED is to add more - flexibility to group substitution. The syntax is similar to that used + The second effect of setting PCRE2_SUBSTITUTE_EXTENDED is to add more + flexibility to group substitution. The syntax is similar to that used by Bash: ${:-} ${:+:} - As before, may be a group number or a name. The first form speci- - fies a default value. If group is set, its value is inserted; if - not, is expanded and the result inserted. The second form - specifies strings that are expanded and inserted when group is set - or unset, respectively. The first form is just a convenient shorthand + As before, may be a group number or a name. The first form speci- + fies a default value. If group is set, its value is inserted; if + not, is expanded and the result inserted. The second form + specifies strings that are expanded and inserted when group is set + or unset, respectively. The first form is just a convenient shorthand for ${:+${}:} - Backslash can be used to escape colons and closing curly brackets in - the replacement strings. A change of the case forcing state within a - replacement string remains in force afterwards, as shown in this + Backslash can be used to escape colons and closing curly brackets in + the replacement strings. A change of the case forcing state within a + replacement string remains in force afterwards, as shown in this pcre2test example: /(some)?(body)/substitute_extended,replace=${1:+\U:\L}HeLLo @@ -3174,41 +3179,41 @@ CREATING A NEW STRING WITH SUBSTITUTIONS somebody 1: HELLO - The PCRE2_SUBSTITUTE_UNSET_EMPTY option does not affect these extended - substitutions. However, PCRE2_SUBSTITUTE_UNKNOWN_UNSET does cause + 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 + 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_ERROR_NOMATCH (which is never returned), errors from 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) + 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 + 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 + 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 + 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- - MISSINGBRACE (closing curly bracket not found), PCRE2_ERROR_BADSUBSTI- + PCRE2_ERROR_BADREPESCAPE (invalid escape sequence), PCRE2_ERROR_REP- + MISSINGBRACE (closing curly bracket not found), PCRE2_ERROR_BADSUBSTI- TUTION (syntax error in extended group substitution), and - PCRE2_ERROR_BADSUBSPATTERN (the pattern match ended before it started, + PCRE2_ERROR_BADSUBSPATTERN (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 the pcre2_get_error_message() function (see + obtained by calling the pcre2_get_error_message() function (see "Obtaining a textual error message" above). @@ -3217,56 +3222,56 @@ 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. 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. @@ -3278,26 +3283,26 @@ 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 + 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 (not counting lookaround assertions), and does - not backtrack. This has different characteristics to the normal algo- - rithm, and is not compatible with Perl. Some of the features of PCRE2 - patterns are not supported. Nevertheless, there are times when this - kind of matching can be useful. For a discussion of the two matching + not backtrack. This has different characteristics to the normal algo- + rithm, and is not compatible with Perl. Some of the features of PCRE2 + patterns are not supported. Nevertheless, 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 sup- port, see the pcre2matching documentation. - 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(): @@ -3317,45 +3322,45 @@ 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_ENDAN- - CHORED, PCRE2_NOTBOL, PCRE2_NOTEOL, PCRE2_NOTEMPTY, + 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_ENDAN- + CHORED, 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 + 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 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. @@ -3363,8 +3368,8 @@ 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 <.*> @@ -3379,17 +3384,17 @@ MATCHING A PATTERN: THE ALTERNATIVE FUNCTION - 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 @@ -3399,64 +3404,64 @@ 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 such 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 such 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), pcre2unicode(3). @@ -3469,11 +3474,11 @@ AUTHOR REVISION - Last updated: 16 December 2017 + Last updated: 31 December 2017 Copyright (c) 1997-2017 University of Cambridge. ------------------------------------------------------------------------------ - - + + PCRE2BUILD(3) Library Functions Manual PCRE2BUILD(3) @@ -4018,8 +4023,8 @@ REVISION Last updated: 18 July 2017 Copyright (c) 1997-2017 University of Cambridge. ------------------------------------------------------------------------------ - - + + PCRE2CALLOUT(3) Library Functions Manual PCRE2CALLOUT(3) @@ -4442,8 +4447,8 @@ REVISION Last updated: 22 December 2017 Copyright (c) 1997-2017 University of Cambridge. ------------------------------------------------------------------------------ - - + + PCRE2COMPAT(3) Library Functions Manual PCRE2COMPAT(3) @@ -4640,8 +4645,8 @@ REVISION Last updated: 18 April 2017 Copyright (c) 1997-2017 University of Cambridge. ------------------------------------------------------------------------------ - - + + PCRE2JIT(3) Library Functions Manual PCRE2JIT(3) @@ -5034,8 +5039,8 @@ REVISION Last updated: 31 March 2017 Copyright (c) 1997-2017 University of Cambridge. ------------------------------------------------------------------------------ - - + + PCRE2LIMITS(3) Library Functions Manual PCRE2LIMITS(3) @@ -5105,8 +5110,8 @@ REVISION Last updated: 30 March 2017 Copyright (c) 1997-2017 University of Cambridge. ------------------------------------------------------------------------------ - - + + PCRE2MATCHING(3) Library Functions Manual PCRE2MATCHING(3) @@ -5324,8 +5329,8 @@ REVISION Last updated: 29 September 2014 Copyright (c) 1997-2014 University of Cambridge. ------------------------------------------------------------------------------ - - + + PCRE2PARTIAL(3) Library Functions Manual PCRE2PARTIAL(3) @@ -5764,8 +5769,8 @@ REVISION Last updated: 22 December 2014 Copyright (c) 1997-2014 University of Cambridge. ------------------------------------------------------------------------------ - - + + PCRE2PATTERN(3) Library Functions Manual PCRE2PATTERN(3) @@ -8875,8 +8880,8 @@ REVISION Last updated: 12 September 2017 Copyright (c) 1997-2017 University of Cambridge. ------------------------------------------------------------------------------ - - + + PCRE2PERFORM(3) Library Functions Manual PCRE2PERFORM(3) @@ -9103,8 +9108,8 @@ REVISION Last updated: 08 April 2017 Copyright (c) 1997-2017 University of Cambridge. ------------------------------------------------------------------------------ - - + + PCRE2POSIX(3) Library Functions Manual PCRE2POSIX(3) @@ -9411,8 +9416,8 @@ REVISION Last updated: 15 June 2017 Copyright (c) 1997-2017 University of Cambridge. ------------------------------------------------------------------------------ - - + + PCRE2SAMPLE(3) Library Functions Manual PCRE2SAMPLE(3) @@ -9680,8 +9685,8 @@ REVISION Last updated: 21 March 2017 Copyright (c) 1997-2017 University of Cambridge. ------------------------------------------------------------------------------ - - + + PCRE2SYNTAX(3) Library Functions Manual PCRE2SYNTAX(3) @@ -10128,8 +10133,8 @@ REVISION Last updated: 17 June 2017 Copyright (c) 1997-2017 University of Cambridge. ------------------------------------------------------------------------------ - - + + PCRE2UNICODE(3) Library Functions Manual PCRE2UNICODE(3) @@ -10385,5 +10390,5 @@ REVISION Last updated: 17 May 2017 Copyright (c) 1997-2017 University of Cambridge. ------------------------------------------------------------------------------ - - + + diff --git a/doc/pcre2_get_mark.3 b/doc/pcre2_get_mark.3 index 3b12d4e..dce377d 100644 --- a/doc/pcre2_get_mark.3 +++ b/doc/pcre2_get_mark.3 @@ -19,8 +19,8 @@ this function's argument, this function returns a pointer to the last (*MARK), name is zero-terminated, and is within the compiled pattern. The length of the name is in the preceding code unit. If no name is available, NULL is returned. .P -After a successful match, the name that is returned is the last one on the -matching path. After a failed match or a partial match, the last encountered +After a successful match, the name that is returned is the last one on the +matching path. After a failed match or a partial match, the last encountered name is returned. .P There is a complete description of the PCRE2 native API in the diff --git a/doc/pcre2api.3 b/doc/pcre2api.3 index 880309e..786b314 100644 --- a/doc/pcre2api.3 +++ b/doc/pcre2api.3 @@ -859,7 +859,7 @@ The \fIoffset_limit\fP parameter limits how far an unanchored search can advance in the subject string. The default value is PCRE2_UNSET. The \fBpcre2_match()\fP and \fBpcre2_dfa_match()\fP functions return PCRE2_ERROR_NOMATCH if a match with a starting point before or at the given -offset is not found. The \fBpcre2_substitute()\fP function makes no more +offset is not found. The \fBpcre2_substitute()\fP function makes no more substitutions. .P For example, if the pattern /abc/ is matched against "123abc" with an offset @@ -1447,8 +1447,8 @@ changed within a pattern by a (?xx) option setting. .sp If this option is set, the start of an unanchored pattern match must be before or at the first newline in the subject string following the start of matching, -though the matched text may continue over the newline. If \fIstartoffset\fP is -non-zero, the limiting newline is not necessarily the first newline in the +though the matched text may continue over the newline. If \fIstartoffset\fP is +non-zero, the limiting newline is not necessarily the first newline in the subject. For example, if the subject string is "abc\enxyz" (where \en represents a single-character newline) a pattern match for "yz" succeeds with PCRE2_FIRSTLINE if \fIstartoffset\fP is greater than 3. See also @@ -1909,13 +1909,13 @@ are as follows: .sp PCRE2_INFO_ALLOPTIONS PCRE2_INFO_ARGOPTIONS - PCRE2_INFO_EXTRAOPTIONS + PCRE2_INFO_EXTRAOPTIONS .sp Return copies 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 (*XXX) option settings such as -(*UTF) at the start of the pattern itself. PCRE2_INFO_EXTRAOPTIONS returns the +(*UTF) at the start of the pattern itself. PCRE2_INFO_EXTRAOPTIONS returns the extra options that were set in the compile context by calling the pcre2_set_compile_extra_options() function. .P @@ -3180,7 +3180,7 @@ options can be set in the \fIoptions\fP argument of \fBpcre2_substitute()\fP. PCRE2_SUBSTITUTE_GLOBAL causes the function to iterate over the subject string, replacing every matching substring. If this option is not set, only the first matching substring is replaced. The search for matches takes place in the -original subject string (that is, previous replacements do not affect it). +original subject string (that is, previous replacements do not affect it). Iteration is implemented by advancing the \fIstartoffset\fP value for each search, which is always passed the entire subject string. If an offset limit is set in the match context, searching stops when that limit is reached. diff --git a/doc/pcre2grep.1 b/doc/pcre2grep.1 index e4c8687..5e5cbea 100644 --- a/doc/pcre2grep.1 +++ b/doc/pcre2grep.1 @@ -400,7 +400,7 @@ given any number of times. If a directory matches both \fB--include-dir\fP and \fB-L\fP, \fB--files-without-match\fP Instead of outputting lines from the files, just output the names of the files that do not contain any lines that would have been output. Each file name is -output once, on a separate line. This option overrides any previous \fB-H\fP, +output once, on a separate line. This option overrides any previous \fB-H\fP, \fB-h\fP, or \fB-l\fP options. .TP \fB-l\fP, \fB--files-with-matches\fP @@ -427,7 +427,7 @@ to terminal is normally automatically flushed by the operating system. This option can be useful when the input or output is attached to a pipe and you do not want \fBpcre2grep\fP to buffer up large amounts of data. However, its use will affect performance, and the \fB-M\fP (multiline) option ceases to work. -When input is from a compressed .gz or .bz2 file, \fB--line-buffered\fP is +When input is from a compressed .gz or .bz2 file, \fB--line-buffered\fP is ignored. .TP \fB--line-offsets\fP @@ -838,7 +838,7 @@ matches were found in other files) or too many matching errors. Using the \fB-s\fP option to suppress error messages about inaccessible files does not affect the return code. .P -When run under VMS, the return code is placed in the symbol PCRE2GREP_RC +When run under VMS, the return code is placed in the symbol PCRE2GREP_RC because VMS does not distinguish between exit(0) and exit(1). . . diff --git a/doc/pcre2pattern.3 b/doc/pcre2pattern.3 index dc37e5f..5c0daa8 100644 --- a/doc/pcre2pattern.3 +++ b/doc/pcre2pattern.3 @@ -493,8 +493,8 @@ limited to certain values, as follows: All UTF modes no greater than 0x10ffff and a valid codepoint .sp Invalid Unicode codepoints are all those in the range 0xd800 to 0xdfff (the -so-called "surrogate" codepoints). The check for these can be disabled by the -caller of \fBpcre2_compile()\fP by setting the option +so-called "surrogate" codepoints). The check for these can be disabled by the +caller of \fBpcre2_compile()\fP by setting the option PCRE2_EXTRA_ALLOW_SURROGATE_ESCAPES. . . @@ -1407,9 +1407,9 @@ Ranges normally include all code points between the start and end characters, 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. In any UTF mode, the so-called "surrogate" characters (those -whose code points lie between 0xd800 and 0xdfff inclusive) may not be specified +whose code points lie between 0xd800 and 0xdfff inclusive) may not be specified explicitly by default (the PCRE2_EXTRA_ALLOW_SURROGATE_ESCAPES option disables -this check). However, ranges such as [\ex{d7ff}-\ex{e000}], which include the +this check). However, ranges such as [\ex{d7ff}-\ex{e000}], which include the surrogates, are always permitted. .P There is a special case in EBCDIC environments for ranges whose end points are diff --git a/src/config.h.generic b/src/config.h.generic index 09f16be..56a59a6 100644 --- a/src/config.h.generic +++ b/src/config.h.generic @@ -210,7 +210,7 @@ sure both macros are undefined; an emulation function will then be used. */ #define PACKAGE_NAME "PCRE2" /* Define to the full name and version of this package. */ -#define PACKAGE_STRING "PCRE2 10.30" +#define PACKAGE_STRING "PCRE2 10.31-RC1" /* Define to the one symbol short name of this package. */ #define PACKAGE_TARNAME "pcre2" @@ -219,7 +219,7 @@ sure both macros are undefined; an emulation function will then be used. */ #define PACKAGE_URL "" /* Define to the version of this package. */ -#define PACKAGE_VERSION "10.30" +#define PACKAGE_VERSION "10.31-RC1" /* The value of PARENS_NEST_LIMIT specifies the maximum depth of nested parentheses (of any kind) in a pattern. This limits the amount of system @@ -339,7 +339,7 @@ sure both macros are undefined; an emulation function will then be used. */ #endif /* Version number of package */ -#define VERSION "10.30" +#define VERSION "10.31-RC1" /* Define to 1 if on MINIX. */ /* #undef _MINIX */ diff --git a/src/pcre2.h b/src/pcre2.h index 17c5b47..d147364 100644 --- a/src/pcre2.h +++ b/src/pcre2.h @@ -44,7 +44,7 @@ POSSIBILITY OF SUCH DAMAGE. #define PCRE2_MAJOR 10 #define PCRE2_MINOR 31 #define PCRE2_PRERELEASE -RC1 -#define PCRE2_DATE 2017-09-12 +#define PCRE2_DATE 2018-01-11 /* 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.h.generic b/src/pcre2.h.generic index 5a45339..d147364 100644 --- a/src/pcre2.h.generic +++ b/src/pcre2.h.generic @@ -42,9 +42,9 @@ POSSIBILITY OF SUCH DAMAGE. /* The current PCRE version information. */ #define PCRE2_MAJOR 10 -#define PCRE2_MINOR 30 -#define PCRE2_PRERELEASE -#define PCRE2_DATE 2017-08-14 +#define PCRE2_MINOR 31 +#define PCRE2_PRERELEASE -RC1 +#define PCRE2_DATE 2018-01-11 /* 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 @@ -208,7 +208,104 @@ greater than zero. */ #define PCRE2_BSR_UNICODE 1 #define PCRE2_BSR_ANYCRLF 2 -/* Error codes: no match and partial match are "expected" errors. */ +/* Error codes for pcre2_compile(). Some of these are also used by +pcre2_pattern_convert(). */ + +#define PCRE2_ERROR_END_BACKSLASH 101 +#define PCRE2_ERROR_END_BACKSLASH_C 102 +#define PCRE2_ERROR_UNKNOWN_ESCAPE 103 +#define PCRE2_ERROR_QUANTIFIER_OUT_OF_ORDER 104 +#define PCRE2_ERROR_QUANTIFIER_TOO_BIG 105 +#define PCRE2_ERROR_MISSING_SQUARE_BRACKET 106 +#define PCRE2_ERROR_ESCAPE_INVALID_IN_CLASS 107 +#define PCRE2_ERROR_CLASS_RANGE_ORDER 108 +#define PCRE2_ERROR_QUANTIFIER_INVALID 109 +#define PCRE2_ERROR_INTERNAL_UNEXPECTED_REPEAT 110 +#define PCRE2_ERROR_INVALID_AFTER_PARENS_QUERY 111 +#define PCRE2_ERROR_POSIX_CLASS_NOT_IN_CLASS 112 +#define PCRE2_ERROR_POSIX_NO_SUPPORT_COLLATING 113 +#define PCRE2_ERROR_MISSING_CLOSING_PARENTHESIS 114 +#define PCRE2_ERROR_BAD_SUBPATTERN_REFERENCE 115 +#define PCRE2_ERROR_NULL_PATTERN 116 +#define PCRE2_ERROR_BAD_OPTIONS 117 +#define PCRE2_ERROR_MISSING_COMMENT_CLOSING 118 +#define PCRE2_ERROR_PARENTHESES_NEST_TOO_DEEP 119 +#define PCRE2_ERROR_PATTERN_TOO_LARGE 120 +#define PCRE2_ERROR_HEAP_FAILED 121 +#define PCRE2_ERROR_UNMATCHED_CLOSING_PARENTHESIS 122 +#define PCRE2_ERROR_INTERNAL_CODE_OVERFLOW 123 +#define PCRE2_ERROR_MISSING_CONDITION_CLOSING 124 +#define PCRE2_ERROR_LOOKBEHIND_NOT_FIXED_LENGTH 125 +#define PCRE2_ERROR_ZERO_RELATIVE_REFERENCE 126 +#define PCRE2_ERROR_TOO_MANY_CONDITION_BRANCHES 127 +#define PCRE2_ERROR_CONDITION_ASSERTION_EXPECTED 128 +#define PCRE2_ERROR_BAD_RELATIVE_REFERENCE 129 +#define PCRE2_ERROR_UNKNOWN_POSIX_CLASS 130 +#define PCRE2_ERROR_INTERNAL_STUDY_ERROR 131 +#define PCRE2_ERROR_UNICODE_NOT_SUPPORTED 132 +#define PCRE2_ERROR_PARENTHESES_STACK_CHECK 133 +#define PCRE2_ERROR_CODE_POINT_TOO_BIG 134 +#define PCRE2_ERROR_LOOKBEHIND_TOO_COMPLICATED 135 +#define PCRE2_ERROR_LOOKBEHIND_INVALID_BACKSLASH_C 136 +#define PCRE2_ERROR_UNSUPPORTED_ESCAPE_SEQUENCE 137 +#define PCRE2_ERROR_CALLOUT_NUMBER_TOO_BIG 138 +#define PCRE2_ERROR_MISSING_CALLOUT_CLOSING 139 +#define PCRE2_ERROR_ESCAPE_INVALID_IN_VERB 140 +#define PCRE2_ERROR_UNRECOGNIZED_AFTER_QUERY_P 141 +#define PCRE2_ERROR_MISSING_NAME_TERMINATOR 142 +#define PCRE2_ERROR_DUPLICATE_SUBPATTERN_NAME 143 +#define PCRE2_ERROR_INVALID_SUBPATTERN_NAME 144 +#define PCRE2_ERROR_UNICODE_PROPERTIES_UNAVAILABLE 145 +#define PCRE2_ERROR_MALFORMED_UNICODE_PROPERTY 146 +#define PCRE2_ERROR_UNKNOWN_UNICODE_PROPERTY 147 +#define PCRE2_ERROR_SUBPATTERN_NAME_TOO_LONG 148 +#define PCRE2_ERROR_TOO_MANY_NAMED_SUBPATTERNS 149 +#define PCRE2_ERROR_CLASS_INVALID_RANGE 150 +#define PCRE2_ERROR_OCTAL_BYTE_TOO_BIG 151 +#define PCRE2_ERROR_INTERNAL_OVERRAN_WORKSPACE 152 +#define PCRE2_ERROR_INTERNAL_MISSING_SUBPATTERN 153 +#define PCRE2_ERROR_DEFINE_TOO_MANY_BRANCHES 154 +#define PCRE2_ERROR_BACKSLASH_O_MISSING_BRACE 155 +#define PCRE2_ERROR_INTERNAL_UNKNOWN_NEWLINE 156 +#define PCRE2_ERROR_BACKSLASH_G_SYNTAX 157 +#define PCRE2_ERROR_PARENS_QUERY_R_MISSING_CLOSING 158 +#define PCRE2_ERROR_VERB_ARGUMENT_NOT_ALLOWED 159 +#define PCRE2_ERROR_VERB_UNKNOWN 160 +#define PCRE2_ERROR_SUBPATTERN_NUMBER_TOO_BIG 161 +#define PCRE2_ERROR_SUBPATTERN_NAME_EXPECTED 162 +#define PCRE2_ERROR_INTERNAL_PARSED_OVERFLOW 163 +#define PCRE2_ERROR_INVALID_OCTAL 164 +#define PCRE2_ERROR_SUBPATTERN_NAMES_MISMATCH 165 +#define PCRE2_ERROR_MARK_MISSING_ARGUMENT 166 +#define PCRE2_ERROR_INVALID_HEXADECIMAL 167 +#define PCRE2_ERROR_BACKSLASH_C_SYNTAX 168 +#define PCRE2_ERROR_BACKSLASH_K_SYNTAX 169 +#define PCRE2_ERROR_INTERNAL_BAD_CODE_LOOKBEHINDS 170 +#define PCRE2_ERROR_BACKSLASH_N_IN_CLASS 171 +#define PCRE2_ERROR_CALLOUT_STRING_TOO_LONG 172 +#define PCRE2_ERROR_UNICODE_DISALLOWED_CODE_POINT 173 +#define PCRE2_ERROR_UTF_IS_DISABLED 174 +#define PCRE2_ERROR_UCP_IS_DISABLED 175 +#define PCRE2_ERROR_VERB_NAME_TOO_LONG 176 +#define PCRE2_ERROR_BACKSLASH_U_CODE_POINT_TOO_BIG 177 +#define PCRE2_ERROR_MISSING_OCTAL_OR_HEX_DIGITS 178 +#define PCRE2_ERROR_VERSION_CONDITION_SYNTAX 179 +#define PCRE2_ERROR_INTERNAL_BAD_CODE_AUTO_POSSESS 180 +#define PCRE2_ERROR_CALLOUT_NO_STRING_DELIMITER 181 +#define PCRE2_ERROR_CALLOUT_BAD_STRING_DELIMITER 182 +#define PCRE2_ERROR_BACKSLASH_C_CALLER_DISABLED 183 +#define PCRE2_ERROR_QUERY_BARJX_NEST_TOO_DEEP 184 +#define PCRE2_ERROR_BACKSLASH_C_LIBRARY_DISABLED 185 +#define PCRE2_ERROR_PATTERN_TOO_COMPLICATED 186 +#define PCRE2_ERROR_LOOKBEHIND_TOO_LONG 187 +#define PCRE2_ERROR_PATTERN_STRING_TOO_LONG 188 +#define PCRE2_ERROR_INTERNAL_BAD_CODE 189 +#define PCRE2_ERROR_INTERNAL_BAD_CODE_IN_SKIP 190 +#define PCRE2_ERROR_NO_SURROGATES_IN_UTF16 191 +#define PCRE2_ERROR_BAD_LITERAL_OPTIONS 192 + + +/* "Expected" matching error codes: no match and partial match. */ #define PCRE2_ERROR_NOMATCH (-1) #define PCRE2_ERROR_PARTIAL (-2) @@ -248,10 +345,10 @@ greater than zero. */ #define PCRE2_ERROR_UTF32_ERR1 (-27) #define PCRE2_ERROR_UTF32_ERR2 (-28) -/* Error codes for pcre2[_dfa]_match(), substring extraction functions, context -functions, and serializing functions. They are in numerical order. Originally -they were in alphabetical order too, but now that PCRE2 is released, the -numbers must not be changed. */ +/* Miscellaneous error codes for pcre2[_dfa]_match(), substring extraction +functions, context functions, and serializing functions. They are in numerical +order. Originally they were in alphabetical order too, but now that PCRE2 is +released, the numbers must not be changed. */ #define PCRE2_ERROR_BADDATA (-29) #define PCRE2_ERROR_MIXEDTABLES (-30) /* Name was changed */ @@ -321,6 +418,7 @@ numbers must not be changed. */ #define PCRE2_INFO_HASBACKSLASHC 23 #define PCRE2_INFO_FRAMESIZE 24 #define PCRE2_INFO_HEAPLIMIT 25 +#define PCRE2_INFO_EXTRAOPTIONS 26 /* Request types for pcre2_config(). */ @@ -338,6 +436,9 @@ numbers must not be changed. */ #define PCRE2_CONFIG_UNICODE_VERSION 10 #define PCRE2_CONFIG_VERSION 11 #define PCRE2_CONFIG_HEAPLIMIT 12 +#define PCRE2_CONFIG_NEVER_BACKSLASH_C 13 +#define PCRE2_CONFIG_COMPILED_WIDTHS 14 + /* Types for code units in patterns and subject strings. */ @@ -393,6 +494,11 @@ without changing the API of the function, thereby allowing old clients to work without modification. Define the generic version in a macro; the width-specific versions are generated from this macro below. */ +/* Flags for the callout_flags field. These are cleared after a callout. */ + +#define PCRE2_CALLOUT_STARTMATCH 0x00000001u /* Set for each bumpalong */ +#define PCRE2_CALLOUT_BACKTRACK 0x00000002u /* Set after a backtrack */ + #define PCRE2_STRUCTURE_LIST \ typedef struct pcre2_callout_block { \ uint32_t version; /* Identifies version of block */ \ @@ -412,6 +518,8 @@ typedef struct pcre2_callout_block { \ PCRE2_SIZE callout_string_offset; /* Offset to string within pattern */ \ PCRE2_SIZE callout_string_length; /* Length of string compiled into pattern */ \ PCRE2_SPTR callout_string; /* String compiled into pattern */ \ + /* ------------------- Added for Version 2 -------------------------- */ \ + uint32_t callout_flags; /* See above for list */ \ /* ------------------------------------------------------------------ */ \ } pcre2_callout_block; \ \ diff --git a/src/pcre2_convert.c b/src/pcre2_convert.c index 546190a..bdf9b86 100644 --- a/src/pcre2_convert.c +++ b/src/pcre2_convert.c @@ -95,7 +95,7 @@ static const char *pcre2_escaped_literals = static const char *posix_meta_escapes = STR_LEFT_PARENTHESIS STR_RIGHT_PARENTHESIS - STR_LEFT_CURLY_BRACKET STR_RIGHT_CURLY_BRACKET + STR_LEFT_CURLY_BRACKET STR_RIGHT_CURLY_BRACKET STR_1 STR_2 STR_3 STR_4 STR_5 STR_6 STR_7 STR_8 STR_9; @@ -250,7 +250,7 @@ while (plength > 0) continue; /* With next character */ } } -#endif +#endif /* Handle start of "normal" character classes */ @@ -278,7 +278,7 @@ while (plength > 0) case CHAR_BACKSLASH: if (plength <= 0) return PCRE2_ERROR_END_BACKSLASH; if (extended) nextisliteral = TRUE; else - { + { if (*posix < 127 && strchr(posix_meta_escapes, *posix) != NULL) { if (isdigit(*posix)) PUTCHARS(STR_BACKSLASH); @@ -286,7 +286,7 @@ while (plength > 0) lastspecial = *p++ = *posix++; plength--; } - else nextisliteral = TRUE; + else nextisliteral = TRUE; } break; @@ -867,7 +867,7 @@ while (pattern < pattern_end) if (pattern >= pattern_end) { - no_slash_z = TRUE; + no_slash_z = TRUE; break; } @@ -937,7 +937,7 @@ while (pattern < pattern_end) { if (pattern >= pattern_end) { - no_slash_z = TRUE; + no_slash_z = TRUE; break; } diff --git a/src/pcre2_dfa_match.c b/src/pcre2_dfa_match.c index 6888370..c6184ff 100644 --- a/src/pcre2_dfa_match.c +++ b/src/pcre2_dfa_match.c @@ -508,7 +508,7 @@ if (*this_start_code == OP_ASSERTBACK || *this_start_code == OP_ASSERTBACK_NOT) { if (current_subject <= start_subject) break; current_subject--; - ACROSSCHAR(current_subject > start_subject, current_subject, + ACROSSCHAR(current_subject > start_subject, current_subject, current_subject--); } } diff --git a/src/pcre2_internal.h b/src/pcre2_internal.h index 4443c41..3db9d60 100644 --- a/src/pcre2_internal.h +++ b/src/pcre2_internal.h @@ -1770,7 +1770,7 @@ typedef struct open_capitem { struct open_capitem *next; /* Chain link */ uint16_t number; /* Capture number */ uint16_t flag; /* Set TRUE if recursive back ref */ - uint16_t assert_depth; /* Assertion depth when opened */ + uint16_t assert_depth; /* Assertion depth when opened */ } open_capitem; /* Layout of the UCP type table that translates property names into types and diff --git a/src/pcre2_intmodedep.h b/src/pcre2_intmodedep.h index 55bd931..3b7d18c 100644 --- a/src/pcre2_intmodedep.h +++ b/src/pcre2_intmodedep.h @@ -623,7 +623,7 @@ typedef struct pcre2_real_code { uint32_t magic_number; /* Paranoid and endianness check */ uint32_t compile_options; /* Options passed to pcre2_compile() */ uint32_t overall_options; /* Options after processing the pattern */ - uint32_t extra_options; /* Taken from compile_context */ + uint32_t extra_options; /* Taken from compile_context */ uint32_t flags; /* Various state flags */ uint32_t limit_heap; /* Limit set in the pattern */ uint32_t limit_match; /* Limit set in the pattern */ @@ -862,7 +862,7 @@ typedef struct match_block { uint32_t nltype; /* Newline type */ uint32_t nllen; /* Newline string length */ PCRE2_UCHAR nl[4]; /* Newline string when fixed */ - pcre2_callout_block *cb; /* Points to a callout block */ + pcre2_callout_block *cb; /* Points to a callout block */ void *callout_data; /* To pass back to callouts */ int (*callout)(pcre2_callout_block *,void *); /* Callout function or NULL */ } match_block; @@ -888,7 +888,7 @@ typedef struct dfa_match_block { uint32_t nllen; /* Newline string length */ PCRE2_UCHAR nl[4]; /* Newline string when fixed */ uint16_t bsr_convention; /* \R interpretation */ - pcre2_callout_block *cb; /* Points to a callout block */ + pcre2_callout_block *cb; /* Points to a callout block */ void *callout_data; /* To pass back to callouts */ int (*callout)(pcre2_callout_block *,void *); /* Callout function or NULL */ dfa_recursion_info *recursive; /* Linked list of recursion data */ diff --git a/src/pcre2_jit_test.c b/src/pcre2_jit_test.c index fd76e34..d9916b7 100644 --- a/src/pcre2_jit_test.c +++ b/src/pcre2_jit_test.c @@ -179,12 +179,12 @@ static struct regression_test_case regression_test_cases[] = { { PCRE2_CASELESS, 0, 0, 0, "\xff#a", "\xff#\xff\xfe##\xff#A" }, { PCRE2_CASELESS, 0, 0, 0, "\xfe", "\xff\xfc#\xfe\xfe" }, { PCRE2_CASELESS, 0, 0, 0, "a1", "Aa1" }, -#ifndef NEVER_BACKSLASH_C +#ifndef NEVER_BACKSLASH_C { M, A, 0, 0, "\\Ca", "cda" }, { CM, A, 0, 0, "\\Ca", "CDA" }, { M, A, 0, 0 | F_NOMATCH, "\\Cx", "cda" }, { CM, A, 0, 0 | F_NOMATCH, "\\Cx", "CDA" }, -#endif +#endif { CMUP, A, 0, 0, "\xf0\x90\x90\x80\xf0\x90\x90\xa8", "\xf0\x90\x90\xa8\xf0\x90\x90\x80" }, { CMUP, A, 0, 0, "\xf0\x90\x90\x80{2}", "\xf0\x90\x90\x80#\xf0\x90\x90\xa8\xf0\x90\x90\x80" }, { CMUP, A, 0, 0, "\xf0\x90\x90\xa8{2}", "\xf0\x90\x90\x80#\xf0\x90\x90\xa8\xf0\x90\x90\x80" }, diff --git a/src/pcre2_pattern_info.c b/src/pcre2_pattern_info.c index 1a51a92..906e919 100644 --- a/src/pcre2_pattern_info.c +++ b/src/pcre2_pattern_info.c @@ -76,7 +76,7 @@ if (where == NULL) /* Requests field length */ case PCRE2_INFO_BSR: case PCRE2_INFO_CAPTURECOUNT: case PCRE2_INFO_DEPTHLIMIT: - case PCRE2_INFO_EXTRAOPTIONS: + case PCRE2_INFO_EXTRAOPTIONS: case PCRE2_INFO_FIRSTCODETYPE: case PCRE2_INFO_FIRSTCODEUNIT: case PCRE2_INFO_HASBACKSLASHC: diff --git a/src/pcre2test.c b/src/pcre2test.c index 1206444..15bf404 100644 --- a/src/pcre2test.c +++ b/src/pcre2test.c @@ -5858,7 +5858,7 @@ output caused by CALLOUT_EXTRA. */ fdefault = (!first_callout && !callout_capture && cb->callout_string == NULL)? NULL : outfile; - + if ((dat_datctl.control2 & CTL2_CALLOUT_EXTRA) != 0) { f = outfile; @@ -8213,11 +8213,11 @@ while (argc > 1 && argv[op][0] == '-' && argv[op][1] != 0) /* Set some common pattern and subject controls */ - else if (strcmp(arg, "-AC") == 0) + else if (strcmp(arg, "-AC") == 0) { def_patctl.options |= PCRE2_AUTO_CALLOUT; def_datctl.control2 |= CTL2_CALLOUT_EXTRA; - } + } else if (strcmp(arg, "-ac") == 0) def_patctl.options |= PCRE2_AUTO_CALLOUT; else if (strcmp(arg, "-b") == 0) def_patctl.control |= CTL_FULLBINCODE; else if (strcmp(arg, "-d") == 0) def_patctl.control |= CTL_DEBUG;