diff --git a/132html b/132html index b062598..3a16a59 100755 --- a/132html +++ b/132html @@ -148,7 +148,7 @@ while () printf("
  • $title\n", $ref, $ref); printf TEMP ("
    $title
    \n", - $ref, $ref); + $ref); $ref++; } else diff --git a/ChangeLog b/ChangeLog index 12e14c2..1222835 100644 --- a/ChangeLog +++ b/ChangeLog @@ -167,6 +167,8 @@ test (there are now 20 in total). 47. Modifier lists in pcre2test were splitting at spaces without the required commas. +48. Implemented PCRE2_ALT_VERBNAMES. + Version 10.20 30-June-2015 -------------------------- diff --git a/doc/html/NON-AUTOTOOLS-BUILD.txt b/doc/html/NON-AUTOTOOLS-BUILD.txt index d8d9d2b..bdbff78 100644 --- a/doc/html/NON-AUTOTOOLS-BUILD.txt +++ b/doc/html/NON-AUTOTOOLS-BUILD.txt @@ -97,6 +97,7 @@ can skip ahead to the CMake section. pcre2_context.c pcre2_dfa_match.c pcre2_error.c + pcre2_find_bracket.c pcre2_jit_compile.c pcre2_maketables.c pcre2_match.c @@ -388,4 +389,4 @@ and executable, is in EBCDIC and native z/OS file formats and this is the recommended download site. ============================= -Last Updated: 15 June 2015 +Last Updated: 16 July 2015 diff --git a/doc/html/README.txt b/doc/html/README.txt index 7367924..955d45a 100644 --- a/doc/html/README.txt +++ b/doc/html/README.txt @@ -724,6 +724,7 @@ The distribution should contain the files listed below. src/pcre2_context.c ) src/pcre2_dfa_match.c ) src/pcre2_error.c ) + src/pcre2_find_bracket.c ) src/pcre2_jit_compile.c ) src/pcre2_jit_match.c ) sources for the functions in the library, src/pcre2_jit_misc.c ) and some internal functions that they use @@ -832,4 +833,4 @@ The distribution should contain the files listed below. Philip Hazel Email local part: ph10 Email domain: cam.ac.uk -Last updated: 24 April 2015 +Last updated: 16 July 2015 diff --git a/doc/html/pcre2_code_free.html b/doc/html/pcre2_code_free.html index 405d164..0477abe 100644 --- a/doc/html/pcre2_code_free.html +++ b/doc/html/pcre2_code_free.html @@ -19,7 +19,7 @@ SYNOPSIS #include <pcre2.h>

    -pcre2_code_free(pcre2_code *code); +void pcre2_code_free(pcre2_code *code);


    DESCRIPTION diff --git a/doc/html/pcre2_match_data_create.html b/doc/html/pcre2_match_data_create.html index 03cbe24..8d0321b 100644 --- a/doc/html/pcre2_match_data_create.html +++ b/doc/html/pcre2_match_data_create.html @@ -19,7 +19,7 @@ SYNOPSIS #include <pcre2.h>

    -pcre2_match_data_create(uint32_t ovecsize, +pcre2_match_data *pcre2_match_data_create(uint32_t ovecsize, pcre2_general_context *gcontext);


    diff --git a/doc/html/pcre2_match_data_create_from_pattern.html b/doc/html/pcre2_match_data_create_from_pattern.html index 3f8d3f5..f40cf1e 100644 --- a/doc/html/pcre2_match_data_create_from_pattern.html +++ b/doc/html/pcre2_match_data_create_from_pattern.html @@ -19,8 +19,8 @@ SYNOPSIS #include <pcre2.h>

    -pcre2_match_data_create_from_pattern(const pcre2_code *code, - pcre2_general_context *gcontext); +pcre2_match_data *pcre2_match_data_create_from_pattern( + const pcre2_code *code, pcre2_general_context *gcontext);


    DESCRIPTION diff --git a/doc/html/pcre2api.html b/doc/html/pcre2api.html index 60d2bf5..0984ece 100644 --- a/doc/html/pcre2api.html +++ b/doc/html/pcre2api.html @@ -70,15 +70,15 @@ document for an overview of all the PCRE2 documentation. pcre2_compile_context *ccontext);

    -pcre2_code_free(pcre2_code *code); +void pcre2_code_free(pcre2_code *code);

    -pcre2_match_data_create(uint32_t ovecsize, +pcre2_match_data *pcre2_match_data_create(uint32_t ovecsize, pcre2_general_context *gcontext);

    -pcre2_match_data_create_from_pattern(const pcre2_code *code, - pcre2_general_context *gcontext); +pcre2_match_data *pcre2_match_data_create_from_pattern( + const pcre2_code *code, pcre2_general_context *gcontext);

    int pcre2_match(const pcre2_code *code, PCRE2_SPTR subject, @@ -936,7 +936,7 @@ 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, "7.0.0") is +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.
    @@ -961,7 +961,7 @@ zero.
       pcre2_compile_context *ccontext);
     

    -pcre2_code_free(pcre2_code *code); +void pcre2_code_free(pcre2_code *code);

    The pcre2_compile() function compiles a pattern into an internal form. @@ -1083,6 +1083,15 @@ 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 terminating 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.
       PCRE2_AUTO_CALLOUT
     
    @@ -1778,12 +1787,12 @@ documentation.


    THE MATCH DATA BLOCK

    -pcre2_match_data_create(uint32_t ovecsize, +pcre2_match_data *pcre2_match_data_create(uint32_t ovecsize, pcre2_general_context *gcontext);

    -pcre2_match_data_create_from_pattern(const pcre2_code *code, - pcre2_general_context *gcontext); +pcre2_match_data *pcre2_match_data_create_from_pattern( + const pcre2_code *code, pcre2_general_context *gcontext);

    void pcre2_match_data_free(pcre2_match_data *match_data); @@ -2010,12 +2019,20 @@ If the pattern is anchored, such a match can occur only if the pattern contains

    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. -The entire string is checked before any other processing takes place, and a +If a non-zero starting offset is given, the check is applied only to that part +of the subject that could be inspected during matching, and there is a check +that the starting offset points to the first code unit of a character or to the +end of the subject. If there 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 +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. The value of startoffset is also checked, to ensure -that it points to the start of a character or to the end of the subject. There -are discussions about the validity of +code unit sequence. There are discussions about the validity of UTF-8 strings, UTF-16 strings, and @@ -2564,12 +2581,12 @@ be given as PCRE2_ZERO_TERMINATED for a zero-terminated string. 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 specify the insertion of -characters from capturing groups in the pattern. The following forms are -recognized: +characters from capturing groups or (*MARK) items in the pattern. The following +forms are recognized:

    -  $$      insert a dollar character
    -  $<n>    insert the contents of group <n>
    -  ${<n>}  insert the contents of group <n>
    +  $$                  insert a dollar character
    +  $<n> or ${<n>}      insert the contents of group <n>
    +  $*MARK or ${*MARK}  insert the name of the last (*MARK) encountered 
     
    Either a group number or a group name can be given for <n>. Curly brackets are required only if the following character would be interpreted as part of the @@ -2580,6 +2597,15 @@ calling pcre2_copy_byname() or pcre2_copy_bynumber() as appropriate.

    +The facility for inserting a (*MARK) name can be used to perform simple +simultaneous substitutions, as this pcre2test example shows: +

    +  /(*:pear)apple|(*:orange)lemon/g,replace=${*MARK}
    +      apple lemon
    +   2: pear orange
    +
    +

    +

    The first seven arguments of pcre2_substitute() are the same as for pcre2_match(), except that the partial matching options are not permitted, and match_data may be passed as NULL, in which case a match @@ -2883,7 +2909,7 @@ Cambridge, England.


    REVISION

    -Last updated: 22 April 2015 +Last updated: 30 August 2015
    Copyright © 1997-2015 University of Cambridge.
    diff --git a/doc/html/pcre2jit.html b/doc/html/pcre2jit.html index 9e32073..887650d 100644 --- a/doc/html/pcre2jit.html +++ b/doc/html/pcre2jit.html @@ -224,8 +224,14 @@ whether a match operation was executed by JIT or by the interpreter.

    You may safely use the same JIT stack for more than one pattern (either by -assigning directly or by callback), as long as the patterns are all matched -sequentially in the same thread. In a multithread application, if you do not +assigning directly or by callback), as long as the patterns are matched +sequentially in the same thread. Currently, the only way to set up +non-sequential matches in one thread is to use callouts: if a callout function +starts another match, that match must use a different JIT stack to the one used +for currently suspended match(es). +

    +

    +In a multithread application, if you do not specify a JIT stack, or if you assign or pass back NULL from a callback, that is thread-safe, because each thread has its own machine stack. However, if you assign or pass back a non-NULL JIT stack, this must be a different stack for @@ -419,9 +425,9 @@ Cambridge, England.


    REVISION

    -Last updated: 27 November 2014 +Last updated: 28 July 2015
    -Copyright © 1997-2014 University of Cambridge. +Copyright © 1997-2015 University of Cambridge.

    Return to the PCRE2 index page. diff --git a/doc/html/pcre2pattern.html b/doc/html/pcre2pattern.html index a9ca60e..a8e4a58 100644 --- a/doc/html/pcre2pattern.html +++ b/doc/html/pcre2pattern.html @@ -736,6 +736,8 @@ Those that are not part of an identified script are lumped together as "Common". The current list of scripts is:

    +Ahom, +Anatolian_Hieroglyphs, Arabic, Armenian, Avestan, @@ -776,6 +778,7 @@ Gurmukhi, Han, Hangul, Hanunoo, +Hatran, Hebrew, Hiragana, Imperial_Aramaic, @@ -812,12 +815,14 @@ Miao, Modi, Mongolian, Mro, +Multani, Myanmar, Nabataean, New_Tai_Lue, Nko, Ogham, Ol_Chiki, +Old_Hungarian, Old_Italic, Old_North_Arabian, Old_Permic, @@ -839,6 +844,7 @@ Saurashtra, Sharada, Shavian, Siddham, +SignWriting, Sinhala, Sora_Sompeng, Sundanese, @@ -1322,9 +1328,19 @@ where a range ending character is expected. For example, [z-\xff] is valid, but [A-\d] and [A-[:digit:]] are not.

    -Ranges operate in the collating sequence of character values. They can also be -used for characters specified numerically, for example [\000-\037]. Ranges -can include any characters that are valid for the current mode. +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. +

    +

    +There is a special case in EBCDIC environments for ranges whose end points are +both specified as literal letters in the same case. For compatibility with +Perl, EBCDIC code points within the range that are not letters are omitted. For +example, [h-k] matches only four characters, even though the codes for h and k +are 0x88 and 0x92, a range of 11 code points. However, if the range is +specified numerically, for example, [\x88-\x92] or [h-\x92], all code points +are included.

    If a range that includes letters is used when caseless matching is set, it @@ -2899,14 +2915,23 @@ remarks apply to the PCRE2 features described in this section.

    The new verbs make use of what was previously invalid syntax: an opening -parenthesis followed by an asterisk. They are generally of the form -(*VERB) or (*VERB:NAME). Some may take either form, possibly behaving -differently depending on whether or not a name is present. A name is any -sequence of characters that does not include a closing parenthesis. The maximum -length of name is 255 in the 8-bit library and 65535 in the 16-bit and 32-bit -libraries. If the name is empty, that is, if the closing parenthesis -immediately follows the colon, the effect is as if the colon were not there. -Any number of these verbs may occur in a pattern. +parenthesis followed by an asterisk. They are generally of the form (*VERB) or +(*VERB:NAME). Some verbs take either form, possibly behaving differently +depending on whether or not a name is present. +

    +

    +By default, for compatibility with Perl, a name is any sequence of characters +that does not include a closing parenthesis. The name is not processed in +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. +

    +

    +The maximum length of a name is 255 in the 8-bit library and 65535 in the +16-bit and 32-bit libraries. If the name is empty, that is, if the closing +parenthesis immediately follows the colon, the effect is as if the colon were +not there. Any number of these verbs may occur in a pattern.

    Since these verbs are specifically related to backtracking, most of them can be @@ -3323,7 +3348,7 @@ Cambridge, England.


    REVISION

    -Last updated: 13 June 2015 +Last updated: 30 August 2015
    Copyright © 1997-2015 University of Cambridge.
    diff --git a/doc/html/pcre2syntax.html b/doc/html/pcre2syntax.html index 28ba023..7a86a37 100644 --- a/doc/html/pcre2syntax.html +++ b/doc/html/pcre2syntax.html @@ -187,6 +187,8 @@ at release 5.18.


    SCRIPT NAMES FOR \p AND \P

    +Ahom, +Anatolian_Hieroglyphs, Arabic, Armenian, Avestan, @@ -227,6 +229,7 @@ Gurmukhi, Han, Hangul, Hanunoo, +Hatran, Hebrew, Hiragana, Imperial_Aramaic, @@ -263,12 +266,14 @@ Miao, Modi, Mongolian, Mro, +Multani, Myanmar, Nabataean, New_Tai_Lue, Nko, Ogham, Ol_Chiki, +Old_Hungarian, Old_Italic, Old_North_Arabian, Old_Permic, @@ -290,6 +295,7 @@ Saurashtra, Sharada, Shavian, Siddham, +SignWriting, Sinhala, Sora_Sompeng, Sundanese, @@ -582,7 +588,7 @@ Cambridge, England.


    REVISION

    -Last updated: 13 June 2015 +Last updated: 17 July 2015
    Copyright © 1997-2015 University of Cambridge.
    diff --git a/doc/html/pcre2test.html b/doc/html/pcre2test.html index 5165c1e..de3c779 100644 --- a/doc/html/pcre2test.html +++ b/doc/html/pcre2test.html @@ -340,12 +340,13 @@ subject lines. Modifiers on a subject line can change these settings.
    MODIFIER SYNTAX

    Modifier lists are used with both pattern and subject lines. Items in a list -are separated by commas and optional white space. Some modifiers may be given -for both patterns and subject lines, whereas others are valid for one or the -other only. Each modifier has a long name, for example "anchored", and some of -them must be followed by an equals sign and a value, for example, "offset=12". -Modifiers that do not take values may be preceded by a minus sign to turn off a -previous setting. +are separated by commas followed by optional white space. Trailing whitespace +in a modifier list is ignored. Some modifiers may be given for both patterns +and subject lines, whereas others are valid only for one or the other. Each +modifier has a long name, for example "anchored", and some of them must be +followed by an equals sign and a value, for example, "offset=12". Values cannot +contain comma characters, but may contain spaces. Modifiers that do not take +values may be preceded by a minus sign to turn off a previous setting.

    A few of the more common modifiers can also be specified as single letters, for @@ -479,6 +480,7 @@ for a description of their effects. allow_empty_class set PCRE2_ALLOW_EMPTY_CLASS alt_bsux set PCRE2_ALT_BSUX alt_circumflex set PCRE2_ALT_CIRCUMFLEX + alt_verbnames set PCRE2_ALT_VERBNAMES anchored set PCRE2_ANCHORED auto_callout set PCRE2_AUTO_CALLOUT /i caseless set PCRE2_CASELESS @@ -1469,7 +1471,7 @@ Cambridge, England.


    REVISION

    -Last updated: 20 May 2015 +Last updated: 30 August 2015
    Copyright © 1997-2015 University of Cambridge.
    diff --git a/doc/html/pcre2unicode.html b/doc/html/pcre2unicode.html index 22c1792..90d5dc6 100644 --- a/doc/html/pcre2unicode.html +++ b/doc/html/pcre2unicode.html @@ -126,11 +126,22 @@ as a byte-order mark (BOM). The PCRE2 functions do not handle this, expecting strings to be in host byte order.

    -The entire string is checked before any other processing takes place. In -addition to checking the format of the string, there is a check to ensure that -all code points lie in the range U+0 to U+10FFFF, excluding the surrogate area. -The so-called "non-character" code points are not excluded because Unicode -corrigendum #9 makes it clear that they should not be. +A UTF string is checked before any other processing takes place. In the case of +pcre2_match() and pcre2_dfa_match() calls with a non-zero starting +offset, the check is applied only to that part of the subject that could be +inspected during matching, and there is a check that the starting offset points +to the first code unit of a character or to the end of the subject. If there +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 sequences \b and \B are +one-character lookbehinds. +

    +

    +In addition to checking the format of the string, there is a check to ensure +that all code points lie in the range U+0 to U+10FFFF, excluding the surrogate +area. The so-called "non-character" code points are not excluded because +Unicode corrigendum #9 makes it clear that they should not be.

    Characters in the "Surrogate Area" of Unicode are reserved for use by UTF-16, @@ -264,9 +275,9 @@ Cambridge, England. REVISION

    -Last updated: 23 November 2014 +Last updated: 18 August 2015
    -Copyright © 1997-2014 University of Cambridge. +Copyright © 1997-2015 University of Cambridge.

    Return to the PCRE2 index page. diff --git a/doc/pcre2.txt b/doc/pcre2.txt index 3193d30..2b6327c 100644 --- a/doc/pcre2.txt +++ b/doc/pcre2.txt @@ -168,8 +168,8 @@ REVISION Last updated: 13 April 2015 Copyright (c) 1997-2015 University of Cambridge. ------------------------------------------------------------------------------ - - + + PCRE2API(3) Library Functions Manual PCRE2API(3) @@ -190,13 +190,13 @@ PCRE2 NATIVE API BASIC FUNCTIONS uint32_t options, int *errorcode, PCRE2_SIZE *erroroffset, pcre2_compile_context *ccontext); - pcre2_code_free(pcre2_code *code); + void pcre2_code_free(pcre2_code *code); - pcre2_match_data_create(uint32_t ovecsize, + pcre2_match_data *pcre2_match_data_create(uint32_t ovecsize, pcre2_general_context *gcontext); - pcre2_match_data_create_from_pattern(const pcre2_code *code, - pcre2_general_context *gcontext); + pcre2_match_data *pcre2_match_data_create_from_pattern( + const pcre2_code *code, pcre2_general_context *gcontext); int pcre2_match(const pcre2_code *code, PCRE2_SPTR subject, PCRE2_SIZE length, PCRE2_SIZE startoffset, @@ -989,7 +989,7 @@ CHECKING BUILD-TIME OPTIONS 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, - "7.0.0") is inserted. The number of code units used is returned. This + "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 @@ -1014,7 +1014,7 @@ COMPILING A PATTERN uint32_t options, int *errorcode, PCRE2_SIZE *erroroffset, pcre2_compile_context *ccontext); - pcre2_code_free(pcre2_code *code); + void pcre2_code_free(pcre2_code *code); The pcre2_compile() function compiles a pattern into an internal form. The pattern is defined by a pointer to a string of code units and a @@ -1128,6 +1128,16 @@ COMPILING A PATTERN 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. + PCRE2_AUTO_CALLOUT If this bit is set, pcre2_compile() automatically inserts callout @@ -1809,11 +1819,11 @@ SERIALIZATION AND PRECOMPILING THE MATCH DATA BLOCK - pcre2_match_data_create(uint32_t ovecsize, + pcre2_match_data *pcre2_match_data_create(uint32_t ovecsize, pcre2_general_context *gcontext); - pcre2_match_data_create_from_pattern(const pcre2_code *code, - pcre2_general_context *gcontext); + pcre2_match_data *pcre2_match_data_create_from_pattern( + const pcre2_code *code, pcre2_general_context *gcontext); void pcre2_match_data_free(pcre2_match_data *match_data); @@ -2022,12 +2032,20 @@ MATCHING A PATTERN: THE TRADITIONAL FUNCTION 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. The entire string is checked 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. The value of startoff- - set is also checked, to ensure that it points to the start of a charac- - ter or to the end of the subject. There are discussions about the + 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 + 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 pcre2unicode page. @@ -2525,12 +2543,12 @@ CREATING A NEW STRING WITH SUBSTITUTIONS 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 in the pattern. - The following forms are recognized: + ify the insertion of characters from capturing groups or (*MARK) items + in the pattern. The following forms are recognized: - $$ insert a dollar character - $ insert the contents of group - ${} insert the contents of group + $$ insert a dollar character + $ or ${} insert the contents of group + $*MARK or ${*MARK} insert the name of the last (*MARK) encountered Either a group number or a group name can be given for . Curly brackets are required only if the following character would be inter- @@ -2540,30 +2558,37 @@ CREATING A NEW STRING WITH SUBSTITUTIONS is "=+babcb+=". Group insertion is done by calling pcre2_copy_byname() or pcre2_copy_bynumber() as appropriate. - The first seven arguments of pcre2_substitute() are the same as for + The facility for inserting a (*MARK) name can be used to perform simple + simultaneous substitutions, as this pcre2test example shows: + + /(*:pear)apple|(*:orange)lemon/g,replace=${*MARK} + apple lemon + 2: pear orange + + 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. - There is one additional option, PCRE2_SUBSTITUTE_GLOBAL, which causes + There is one additional option, PCRE2_SUBSTITUTE_GLOBAL, which causes the function to iterate over the subject string, replacing every match- ing substring. If this is not set, only the first matching substring is replaced. - The outlengthptr argument must point to a variable that contains the - length, in code units, of the output buffer. It is updated to contain + The outlengthptr argument must point to a variable that contains the + length, in code units, of the output buffer. It is updated to contain the length of the new string, excluding the trailing zero that is auto- matically added. - The function returns the number of replacements that were made. This - may be zero if no matches were found, and is never greater than 1 + The function returns the number of replacements that were made. This + may be zero if no matches were found, and is never greater than 1 unless PCRE2_SUBSTITUTE_GLOBAL is set. In the event of an error, a neg- - ative error code is returned. Except for PCRE2_ERROR_NOMATCH (which is + ative error code is returned. Except for PCRE2_ERROR_NOMATCH (which is never returned), any errors from pcre2_match() or the substring copying functions are passed straight back. PCRE2_ERROR_BADREPLACEMENT is - returned for an invalid replacement string (unrecognized sequence fol- + returned for an invalid replacement string (unrecognized sequence fol- lowing a dollar sign), and PCRE2_ERROR_NOMEMORY is returned if the out- put buffer is not big enough. @@ -2573,56 +2598,56 @@ DUPLICATE SUBPATTERN NAMES int pcre2_substring_nametable_scan(const pcre2_code *code, PCRE2_SPTR name, PCRE2_SPTR *first, PCRE2_SPTR *last); - When a pattern is compiled with the PCRE2_DUPNAMES option, names for - subpatterns are not required to be unique. Duplicate names are always - allowed for subpatterns with the same number, created by using the (?| - feature. Indeed, if such subpatterns are named, they are required to + When a pattern is compiled with the PCRE2_DUPNAMES option, names for + subpatterns are not required to be unique. Duplicate names are always + allowed for subpatterns with the same number, created by using the (?| + feature. Indeed, if such subpatterns are named, they are required to use the same names. Normally, patterns with duplicate names are such that in any one match, - only one of the named subpatterns participates. An example is shown in + only one of the named subpatterns participates. An example is shown in the pcre2pattern documentation. - When duplicates are present, pcre2_substring_copy_byname() and - pcre2_substring_get_byname() return the first substring corresponding - to the given name that is set. Only if none are set is - PCRE2_ERROR_UNSET is returned. The pcre2_substring_number_from_name() + When duplicates are present, pcre2_substring_copy_byname() and + pcre2_substring_get_byname() return the first substring corresponding + to the given name that is set. Only if none are set is + PCRE2_ERROR_UNSET is returned. The pcre2_substring_number_from_name() function returns the error PCRE2_ERROR_NOUNIQUESUBSTRING when there are duplicate names. - If you want to get full details of all captured substrings for a given - name, you must use the pcre2_substring_nametable_scan() function. The - first argument is the compiled pattern, and the second is the name. If - the third and fourth arguments are NULL, the function returns a group + If you want to get full details of all captured substrings for a given + name, you must use the pcre2_substring_nametable_scan() function. The + first argument is the compiled pattern, and the second is the name. If + the third and fourth arguments are NULL, the function returns a group number for a unique name, or PCRE2_ERROR_NOUNIQUESUBSTRING otherwise. When the third and fourth arguments are not NULL, they must be pointers - to variables that are updated by the function. After it has run, they + to variables that are updated by the function. After it has run, they point to the first and last entries in the name-to-number table for the - given name, and the function returns the length of each entry in code - units. In both cases, PCRE2_ERROR_NOSUBSTRING is returned if there are + given name, and the function returns the length of each entry in code + units. In both cases, PCRE2_ERROR_NOSUBSTRING is returned if there are no entries for the given name. The format of the name table is described above in the section entitled - Information about a pattern above. Given all the relevant entries for + Information about a pattern above. 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. @@ -2634,26 +2659,26 @@ MATCHING A PATTERN: THE ALTERNATIVE FUNCTION pcre2_match_context *mcontext, int *workspace, PCRE2_SIZE wscount); - The function pcre2_dfa_match() is called to match a subject string - against a compiled pattern, using a matching algorithm that scans the - subject string just once, and does not backtrack. This has different - characteristics to the normal algorithm, and is not compatible with - Perl. Some of the features of PCRE2 patterns are not supported. Never- - theless, there are times when this kind of matching can be useful. For - a discussion of the two matching algorithms, and a list of features + The function pcre2_dfa_match() is called to match a subject string + against a compiled pattern, using a matching algorithm that scans the + subject string just once, and does not backtrack. This has different + characteristics to the normal algorithm, and is not compatible with + Perl. Some of the features of PCRE2 patterns are not supported. Never- + theless, there are times when this kind of matching can be useful. For + a discussion of the two matching algorithms, and a list of features that pcre2_dfa_match() does not support, see the pcre2matching documen- tation. - The arguments for the pcre2_dfa_match() function are the same as for + The arguments for the pcre2_dfa_match() function are the same as for pcre2_match(), plus two extras. The ovector within the match data block is used in a different way, and this is described below. The other com- - mon arguments are used in the same way as for pcre2_match(), so their + mon arguments are used in the same way as for pcre2_match(), so their description is not repeated here. - The two additional arguments provide workspace for the function. The - workspace vector should contain at least 20 elements. It is used for + The two additional arguments provide workspace for the function. The + workspace vector should contain at least 20 elements. It is used for keeping track of multiple paths through the pattern tree. More - workspace is needed for patterns and subjects where there are a lot of + workspace is needed for patterns and subjects where there are a lot of potential matches. Here is an example of a simple call to pcre2_dfa_match(): @@ -2673,45 +2698,45 @@ MATCHING A PATTERN: THE ALTERNATIVE FUNCTION Option bits for pcre_dfa_match() - The unused bits of the options argument for pcre2_dfa_match() must be - zero. The only bits that may be set are PCRE2_ANCHORED, PCRE2_NOTBOL, + The unused bits of the options argument for pcre2_dfa_match() must be + zero. The only bits that may be set are PCRE2_ANCHORED, PCRE2_NOTBOL, PCRE2_NOTEOL, PCRE2_NOTEMPTY, PCRE2_NOTEMPTY_ATSTART, PCRE2_NO_UTF_CHECK, PCRE2_PARTIAL_HARD, PCRE2_PARTIAL_SOFT, - PCRE2_DFA_SHORTEST, and PCRE2_DFA_RESTART. All but the last four of - these are exactly the same as for pcre2_match(), so their description + PCRE2_DFA_SHORTEST, and PCRE2_DFA_RESTART. All but the last four of + these are exactly the same as for pcre2_match(), so their description is not repeated here. PCRE2_PARTIAL_HARD PCRE2_PARTIAL_SOFT - These have the same general effect as they do for pcre2_match(), but - the details are slightly different. When PCRE2_PARTIAL_HARD is set for - pcre2_dfa_match(), it returns PCRE2_ERROR_PARTIAL if the end of the + These have the same general effect as they do for pcre2_match(), but + the details are slightly different. When PCRE2_PARTIAL_HARD is set for + pcre2_dfa_match(), it returns PCRE2_ERROR_PARTIAL if the end of the subject is reached and there is still at least one matching possibility that requires additional characters. This happens even if some complete - matches have already been found. When PCRE2_PARTIAL_SOFT is set, the - return code PCRE2_ERROR_NOMATCH is converted into PCRE2_ERROR_PARTIAL - if the end of the subject is reached, there have been no complete + matches have already been found. When PCRE2_PARTIAL_SOFT is set, the + return code PCRE2_ERROR_NOMATCH is converted into PCRE2_ERROR_PARTIAL + if the end of the subject is reached, there have been no complete matches, but there is still at least one matching possibility. The por- - tion of the string that was inspected when the longest partial match + tion of the string that was inspected when the longest partial match was found is set as the first matching string in both cases. There is a - more detailed discussion of partial and multi-segment matching, with + more detailed discussion of partial and multi-segment matching, with examples, in the pcre2partial documentation. PCRE2_DFA_SHORTEST - Setting the PCRE2_DFA_SHORTEST option causes the matching algorithm to + Setting the PCRE2_DFA_SHORTEST option causes the matching algorithm to stop as soon as it has found one match. Because of the way the alterna- - tive algorithm works, this is necessarily the shortest possible match + tive algorithm works, this is necessarily the shortest possible match at the first possible matching point in the subject string. PCRE2_DFA_RESTART - When pcre2_dfa_match() returns a partial match, it is possible to call + When pcre2_dfa_match() returns a partial match, it is possible to call it again, with additional subject characters, and have it continue with the same match. The PCRE2_DFA_RESTART option requests this action; when - it is set, the workspace and wscount options must reference the same - vector as before because data about the match so far is left in them + it is set, the workspace and wscount options must reference the same + vector as before because data about the match so far is left in them after a partial match. There is more discussion of this facility in the pcre2partial documentation. @@ -2719,8 +2744,8 @@ 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 <.*> @@ -2735,17 +2760,17 @@ 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 @@ -2755,64 +2780,64 @@ MATCHING A PATTERN: THE ALTERNATIVE FUNCTION PCRE2_ERROR_UNSET - There is a slot in the ovector for this substring, but there were + There is a slot in the ovector for this substring, but there were insufficient matches to fill it. - The matched strings are stored in the ovector in reverse order of - length; that is, the longest matching string is first. If there were - too many matches to fit into the ovector, the yield of the function is + The matched strings are stored in the ovector in reverse order of + length; that is, the longest matching string is first. If there were + too many matches to fit into the ovector, the yield of the function is zero, and the vector is filled with the longest matches. - NOTE: PCRE2's "auto-possessification" optimization usually applies to - character repeats at the end of a pattern (as well as internally). For - example, the pattern "a\d+" is compiled as if it were "a\d++". For DFA - matching, this means that only one possible match is found. If you - really do want multiple matches in such cases, either use an ungreedy - repeat auch as "a\d+?" or set the PCRE2_NO_AUTO_POSSESS option when + NOTE: PCRE2's "auto-possessification" optimization usually applies to + character repeats at the end of a pattern (as well as internally). For + example, the pattern "a\d+" is compiled as if it were "a\d++". For DFA + matching, this means that only one possible match is found. If you + really do want multiple matches in such cases, either use an ungreedy + repeat auch as "a\d+?" or set the PCRE2_NO_AUTO_POSSESS option when compiling. Error returns from pcre2_dfa_match() The pcre2_dfa_match() function returns a negative number when it fails. - Many of the errors are the same as for pcre2_match(), as described + Many of the errors are the same as for pcre2_match(), as described above. There are in addition the following errors that are specific to pcre2_dfa_match(): PCRE2_ERROR_DFA_UITEM - This return is given if pcre2_dfa_match() encounters an item in the + 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 or a back reference. PCRE2_ERROR_DFA_UCOND - This return is given if pcre2_dfa_match() encounters a condition item - that uses a back reference for the condition, or a test for recursion + This return is given if pcre2_dfa_match() encounters a condition item + that uses a back reference for the condition, or a test for recursion in a specific group. These are not supported. PCRE2_ERROR_DFA_WSSIZE - This return is given if pcre2_dfa_match() runs out of space in the + This return is given if pcre2_dfa_match() runs out of space in the workspace vector. PCRE2_ERROR_DFA_RECURSE - When a recursive subpattern is processed, the matching function calls + When a recursive subpattern is processed, the matching function calls itself recursively, using private memory for the ovector and workspace. - This error is given if the internal ovector is not large enough. This + This error is given if the internal ovector is not large enough. This should be extremely rare, as a vector of size 1000 is used. PCRE2_ERROR_DFA_BADRESTART - When pcre2_dfa_match() is called with the PCRE2_DFA_RESTART option, - some plausibility checks are made on the contents of the workspace, - which should contain data about the previous partial match. If any of + When pcre2_dfa_match() is called with the PCRE2_DFA_RESTART option, + some plausibility checks are made on the contents of the workspace, + which should contain data about the previous partial match. If any of these checks fail, this error is given. SEE ALSO - pcre2build(3), pcre2callout(3), pcre2demo(3), pcre2matching(3), + pcre2build(3), pcre2callout(3), pcre2demo(3), pcre2matching(3), pcre2partial(3), pcre2posix(3), pcre2sample(3), pcre2stack(3), pcre2unicode(3). @@ -2826,11 +2851,11 @@ AUTHOR REVISION - Last updated: 22 April 2015 + Last updated: 30 August 2015 Copyright (c) 1997-2015 University of Cambridge. ------------------------------------------------------------------------------ - - + + PCRE2BUILD(3) Library Functions Manual PCRE2BUILD(3) @@ -3305,8 +3330,8 @@ REVISION Last updated: 24 April 2015 Copyright (c) 1997-2015 University of Cambridge. ------------------------------------------------------------------------------ - - + + PCRE2CALLOUT(3) Library Functions Manual PCRE2CALLOUT(3) @@ -3669,8 +3694,8 @@ REVISION Last updated: 23 March 2015 Copyright (c) 1997-2015 University of Cambridge. ------------------------------------------------------------------------------ - - + + PCRE2COMPAT(3) Library Functions Manual PCRE2COMPAT(3) @@ -3854,8 +3879,8 @@ REVISION Last updated: 15 March 2015 Copyright (c) 1997-2015 University of Cambridge. ------------------------------------------------------------------------------ - - + + PCRE2JIT(3) Library Functions Manual PCRE2JIT(3) @@ -4051,13 +4076,17 @@ CONTROLLING THE JIT STACK interpreter. You may safely use the same JIT stack for more than one pattern (either - by assigning directly or by callback), as long as the patterns are all - matched sequentially in the same thread. In a multithread application, - if you do not specify a JIT stack, or if you assign or pass back NULL - from a callback, that is thread-safe, because each thread has its own - machine stack. However, if you assign or pass back a non-NULL JIT - stack, this must be a different stack for each thread so that the - application is thread-safe. + by assigning directly or by callback), as long as the patterns are + matched sequentially in the same thread. Currently, the only way to set + up non-sequential matches in one thread is to use callouts: if a call- + out function starts another match, that match must use a different JIT + stack to the one used for currently suspended match(es). + + In a multithread application, if you do not specify a JIT stack, or if + you assign or pass back NULL from a callback, that is thread-safe, + because each thread has its own machine stack. However, if you assign + or pass back a non-NULL JIT stack, this must be a different stack for + each thread so that the application is thread-safe. Strictly speaking, even more is allowed. You can assign the same non- NULL stack to a match context that is used by any number of patterns, @@ -4234,11 +4263,11 @@ AUTHOR REVISION - Last updated: 27 November 2014 - Copyright (c) 1997-2014 University of Cambridge. + Last updated: 28 July 2015 + Copyright (c) 1997-2015 University of Cambridge. ------------------------------------------------------------------------------ - - + + PCRE2LIMITS(3) Library Functions Manual PCRE2LIMITS(3) @@ -4309,8 +4338,8 @@ REVISION Last updated: 25 November 2014 Copyright (c) 1997-2014 University of Cambridge. ------------------------------------------------------------------------------ - - + + PCRE2MATCHING(3) Library Functions Manual PCRE2MATCHING(3) @@ -4528,8 +4557,8 @@ REVISION Last updated: 29 September 2014 Copyright (c) 1997-2014 University of Cambridge. ------------------------------------------------------------------------------ - - + + PCRE2PARTIAL(3) Library Functions Manual PCRE2PARTIAL(3) @@ -4968,8 +4997,8 @@ REVISION Last updated: 22 December 2014 Copyright (c) 1997-2014 University of Cambridge. ------------------------------------------------------------------------------ - - + + PCRE2UNICODE(3) Library Functions Manual PCRE2UNICODE(3) @@ -5069,33 +5098,44 @@ VALIDITY OF UTF STRINGS knows as a byte-order mark (BOM). The PCRE2 functions do not handle this, expecting strings to be in host byte order. - The entire string is checked before any other processing takes place. - In addition to checking the format of the string, there is a check to + A UTF string is checked before any other processing takes place. In the + case of pcre2_match() and pcre2_dfa_match() calls with a non-zero + starting offset, the check is applied only to that part of the subject + that could be inspected during matching, and there is a check that the + starting offset points to the first code unit of a character or to the + end of the subject. If there are no lookbehind assertions in the pat- + tern, 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 sequences \b and \B are one-charac- + ter lookbehinds. + + In addition to checking the format of the string, there is a check to ensure that all code points lie in the range U+0 to U+10FFFF, excluding - the surrogate area. The so-called "non-character" code points are not + the surrogate area. The so-called "non-character" code points are not excluded because Unicode corrigendum #9 makes it clear that they should not be. - Characters in the "Surrogate Area" of Unicode are reserved for use by - UTF-16, where they are used in pairs to encode code points with values - greater than 0xFFFF. The code points that are encoded by UTF-16 pairs - are available independently in the UTF-8 and UTF-32 encodings. (In - other words, the whole surrogate thing is a fudge for UTF-16 which + Characters in the "Surrogate Area" of Unicode are reserved for use by + UTF-16, where they are used in pairs to encode code points with values + greater than 0xFFFF. The code points that are encoded by UTF-16 pairs + are available independently in the UTF-8 and UTF-32 encodings. (In + other words, the whole surrogate thing is a fudge for UTF-16 which unfortunately messes up UTF-8 and UTF-32.) - In some situations, you may already know that your strings are valid, - and therefore want to skip these checks in order to improve perfor- - mance, for example in the case of a long subject string that is being - scanned repeatedly. If you set the PCRE2_NO_UTF_CHECK option at com- - pile time or at match time, PCRE2 assumes that the pattern or subject + In some situations, you may already know that your strings are valid, + and therefore want to skip these checks in order to improve perfor- + mance, for example in the case of a long subject string that is being + scanned repeatedly. If you set the PCRE2_NO_UTF_CHECK option at com- + pile time or at match time, PCRE2 assumes that the pattern or subject it is given (respectively) contains only valid UTF code unit sequences. - Passing PCRE2_NO_UTF_CHECK to pcre2_compile() just disables the check + Passing PCRE2_NO_UTF_CHECK to pcre2_compile() just disables the check for the pattern; it does not also apply to subject strings. If you want - to disable the check for a subject string you must pass this option to + to disable the check for a subject string you must pass this option to pcre2_match() or pcre2_dfa_match(). - If you pass an invalid UTF string when PCRE2_NO_UTF_CHECK is set, the + If you pass an invalid UTF string when PCRE2_NO_UTF_CHECK is set, the result is undefined and your program may crash or loop indefinitely. Errors in UTF-8 strings @@ -5108,10 +5148,10 @@ VALIDITY OF UTF STRINGS PCRE2_ERROR_UTF8_ERR4 PCRE2_ERROR_UTF8_ERR5 - The string ends with a truncated UTF-8 character; the code specifies - how many bytes are missing (1 to 5). Although RFC 3629 restricts UTF-8 - characters to be no longer than 4 bytes, the encoding scheme (origi- - nally defined by RFC 2279) allows for up to 6 bytes, and this is + The string ends with a truncated UTF-8 character; the code specifies + how many bytes are missing (1 to 5). Although RFC 3629 restricts UTF-8 + characters to be no longer than 4 bytes, the encoding scheme (origi- + nally defined by RFC 2279) allows for up to 6 bytes, and this is checked first; hence the possibility of 4 or 5 missing bytes. PCRE2_ERROR_UTF8_ERR6 @@ -5121,24 +5161,24 @@ VALIDITY OF UTF STRINGS PCRE2_ERROR_UTF8_ERR10 The two most significant bits of the 2nd, 3rd, 4th, 5th, or 6th byte of - the character do not have the binary value 0b10 (that is, either the + the character do not have the binary value 0b10 (that is, either the most significant bit is 0, or the next bit is 1). PCRE2_ERROR_UTF8_ERR11 PCRE2_ERROR_UTF8_ERR12 - A character that is valid by the RFC 2279 rules is either 5 or 6 bytes + A character that is valid by the RFC 2279 rules is either 5 or 6 bytes long; these code points are excluded by RFC 3629. PCRE2_ERROR_UTF8_ERR13 - A 4-byte character has a value greater than 0x10fff; these code points + A 4-byte character has a value greater than 0x10fff; these code points are excluded by RFC 3629. PCRE2_ERROR_UTF8_ERR14 - A 3-byte character has a value in the range 0xd800 to 0xdfff; this - range of code points are reserved by RFC 3629 for use with UTF-16, and + A 3-byte character has a value in the range 0xd800 to 0xdfff; this + range of code points are reserved by RFC 3629 for use with UTF-16, and so are excluded from UTF-8. PCRE2_ERROR_UTF8_ERR15 @@ -5147,26 +5187,26 @@ VALIDITY OF UTF STRINGS PCRE2_ERROR_UTF8_ERR18 PCRE2_ERROR_UTF8_ERR19 - A 2-, 3-, 4-, 5-, or 6-byte character is "overlong", that is, it codes - for a value that can be represented by fewer bytes, which is invalid. - For example, the two bytes 0xc0, 0xae give the value 0x2e, whose cor- + A 2-, 3-, 4-, 5-, or 6-byte character is "overlong", that is, it codes + for a value that can be represented by fewer bytes, which is invalid. + For example, the two bytes 0xc0, 0xae give the value 0x2e, whose cor- rect coding uses just one byte. PCRE2_ERROR_UTF8_ERR20 The two most significant bits of the first byte of a character have the - binary value 0b10 (that is, the most significant bit is 1 and the sec- - ond is 0). Such a byte can only validly occur as the second or subse- + binary value 0b10 (that is, the most significant bit is 1 and the sec- + ond is 0). Such a byte can only validly occur as the second or subse- quent byte of a multi-byte character. PCRE2_ERROR_UTF8_ERR21 - The first byte of a character has the value 0xfe or 0xff. These values + The first byte of a character has the value 0xfe or 0xff. These values can never occur in a valid UTF-8 string. Errors in UTF-16 strings - The following negative error codes are given for invalid UTF-16 + The following negative error codes are given for invalid UTF-16 strings: PCRE_UTF16_ERR1 Missing low surrogate at end of string @@ -5176,7 +5216,7 @@ VALIDITY OF UTF STRINGS Errors in UTF-32 strings - The following negative error codes are given for invalid UTF-32 + The following negative error codes are given for invalid UTF-32 strings: PCRE_UTF32_ERR1 Surrogate character (range from 0xd800 to 0xdfff) @@ -5192,8 +5232,8 @@ AUTHOR REVISION - Last updated: 23 November 2014 - Copyright (c) 1997-2014 University of Cambridge. + Last updated: 18 August 2015 + Copyright (c) 1997-2015 University of Cambridge. ------------------------------------------------------------------------------ - - + + diff --git a/doc/pcre2api.3 b/doc/pcre2api.3 index b888223..0f338da 100644 --- a/doc/pcre2api.3 +++ b/doc/pcre2api.3 @@ -1,4 +1,4 @@ -.TH PCRE2API 3 "29 August 2015" "PCRE2 10.21" +.TH PCRE2API 3 "30 August 2015" "PCRE2 10.21" .SH NAME PCRE2 - Perl-compatible regular expressions (revised API) .sp @@ -1052,6 +1052,15 @@ 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 terminating newline, you must set PCRE2_ALT_CIRCUMFLEX. +.sp + PCRE2_ALT_VERBNAMES +.sp +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. .sp PCRE2_AUTO_CALLOUT .sp @@ -2953,6 +2962,6 @@ Cambridge, England. .rs .sp .nf -Last updated: 29 August 2015 +Last updated: 30 August 2015 Copyright (c) 1997-2015 University of Cambridge. .fi diff --git a/doc/pcre2pattern.3 b/doc/pcre2pattern.3 index 9f0ff4f..a1156ae 100644 --- a/doc/pcre2pattern.3 +++ b/doc/pcre2pattern.3 @@ -1,4 +1,4 @@ -.TH PCRE2PATTERN 3 "24 July 2015" "PCRE2 10.21" +.TH PCRE2PATTERN 3 "30 August 2015" "PCRE2 10.21" .SH NAME PCRE2 - Perl-compatible regular expressions (revised API) .SH "PCRE2 REGULAR EXPRESSION DETAILS" @@ -1334,7 +1334,7 @@ both specified as literal letters in the same case. For compatibility with Perl, EBCDIC code points within the range that are not letters are omitted. For example, [h-k] matches only four characters, even though the codes for h and k are 0x88 and 0x92, a range of 11 code points. However, if the range is -specified numerically, for example, [\ex88-\ex92] or [h-\x92], all code points +specified numerically, for example, [\ex88-\ex92] or [h-\ex92], all code points are included. .P If a range that includes letters is used when caseless matching is set, it @@ -2944,14 +2944,21 @@ in production code should be noted to avoid problems during upgrades." The same remarks apply to the PCRE2 features described in this section. .P The new verbs make use of what was previously invalid syntax: an opening -parenthesis followed by an asterisk. They are generally of the form -(*VERB) or (*VERB:NAME). Some may take either form, possibly behaving -differently depending on whether or not a name is present. A name is any -sequence of characters that does not include a closing parenthesis. The maximum -length of name is 255 in the 8-bit library and 65535 in the 16-bit and 32-bit -libraries. If the name is empty, that is, if the closing parenthesis -immediately follows the colon, the effect is as if the colon were not there. -Any number of these verbs may occur in a pattern. +parenthesis followed by an asterisk. They are generally of the form (*VERB) or +(*VERB:NAME). Some verbs take either form, possibly behaving differently +depending on whether or not a name is present. +.P +By default, for compatibility with Perl, a name is any sequence of characters +that does not include a closing parenthesis. The name is not processed in +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. +.P +The maximum length of a name is 255 in the 8-bit library and 65535 in the +16-bit and 32-bit libraries. If the name is empty, that is, if the closing +parenthesis immediately follows the colon, the effect is as if the colon were +not there. Any number of these verbs may occur in a pattern. .P Since these verbs are specifically related to backtracking, most of them can be used only when the pattern is to be matched using the traditional matching @@ -3376,6 +3383,6 @@ Cambridge, England. .rs .sp .nf -Last updated: 24 July 2015 +Last updated: 30 August 2015 Copyright (c) 1997-2015 University of Cambridge. .fi diff --git a/doc/pcre2test.1 b/doc/pcre2test.1 index 3e0171a..523dfc1 100644 --- a/doc/pcre2test.1 +++ b/doc/pcre2test.1 @@ -445,6 +445,7 @@ for a description of their effects. allow_empty_class set PCRE2_ALLOW_EMPTY_CLASS alt_bsux set PCRE2_ALT_BSUX alt_circumflex set PCRE2_ALT_CIRCUMFLEX + alt_verbnames set PCRE2_ALT_VERBNAMES anchored set PCRE2_ANCHORED auto_callout set PCRE2_AUTO_CALLOUT /i caseless set PCRE2_CASELESS diff --git a/doc/pcre2test.txt b/doc/pcre2test.txt index c022a9c..0bf3a72 100644 --- a/doc/pcre2test.txt +++ b/doc/pcre2test.txt @@ -285,12 +285,14 @@ COMMAND LINES MODIFIER SYNTAX Modifier lists are used with both pattern and subject lines. Items in a - list are separated by commas and optional white space. Some modifiers - may be given for both patterns and subject lines, whereas others are - valid for one or the other only. Each modifier has a long name, for - example "anchored", and some of them must be followed by an equals sign - and a value, for example, "offset=12". Modifiers that do not take val- - ues may be preceded by a minus sign to turn off a previous setting. + list are separated by commas followed by optional white space. Trailing + whitespace in a modifier list is ignored. Some modifiers may be given + for both patterns and subject lines, whereas others are valid only for + one or the other. Each modifier has a long name, for example + "anchored", and some of them must be followed by an equals sign and a + value, for example, "offset=12". Values cannot contain comma charac- + ters, but may contain spaces. Modifiers that do not take values may be + preceded by a minus sign to turn off a previous setting. A few of the more common modifiers can also be specified as single let- ters, for example "i" for "caseless". In documentation, following the @@ -424,6 +426,7 @@ PATTERN MODIFIERS allow_empty_class set PCRE2_ALLOW_EMPTY_CLASS alt_bsux set PCRE2_ALT_BSUX alt_circumflex set PCRE2_ALT_CIRCUMFLEX + alt_verbnames set PCRE2_ALT_VERBNAMES anchored set PCRE2_ANCHORED auto_callout set PCRE2_AUTO_CALLOUT /i caseless set PCRE2_CASELESS @@ -1330,5 +1333,5 @@ AUTHOR REVISION - Last updated: 20 May 2015 + Last updated: 30 August 2015 Copyright (c) 1997-2015 University of Cambridge. diff --git a/src/pcre2.h.in b/src/pcre2.h.in index 94fbdd5..9aae0d9 100644 --- a/src/pcre2.h.in +++ b/src/pcre2.h.in @@ -120,6 +120,7 @@ D is inspected during pcre2_dfa_match() execution #define PCRE2_UTF 0x00080000u /* C J M D */ #define PCRE2_NEVER_BACKSLASH_C 0x00100000u /* C */ #define PCRE2_ALT_CIRCUMFLEX 0x00200000u /* J M D */ +#define PCRE2_ALT_VERBNAMES 0x00400000u /* C */ /* These are for pcre2_jit_compile(). */ diff --git a/src/pcre2_compile.c b/src/pcre2_compile.c index 4fe0236..470c716 100644 --- a/src/pcre2_compile.c +++ b/src/pcre2_compile.c @@ -561,12 +561,12 @@ static PCRE2_SPTR posix_substitutes[] = { #define PUBLIC_COMPILE_OPTIONS \ (PCRE2_ANCHORED|PCRE2_ALLOW_EMPTY_CLASS|PCRE2_ALT_BSUX|PCRE2_ALT_CIRCUMFLEX| \ - PCRE2_AUTO_CALLOUT|PCRE2_CASELESS|PCRE2_DOLLAR_ENDONLY|PCRE2_DOTALL| \ - PCRE2_DUPNAMES|PCRE2_EXTENDED|PCRE2_FIRSTLINE|PCRE2_MATCH_UNSET_BACKREF| \ - PCRE2_MULTILINE|PCRE2_NEVER_BACKSLASH_C|PCRE2_NEVER_UCP| \ - PCRE2_NEVER_UTF|PCRE2_NO_AUTO_CAPTURE|PCRE2_NO_AUTO_POSSESS| \ - PCRE2_NO_DOTSTAR_ANCHOR|PCRE2_NO_START_OPTIMIZE|PCRE2_NO_UTF_CHECK| \ - PCRE2_UCP|PCRE2_UNGREEDY|PCRE2_UTF) + PCRE2_ALT_VERBNAMES|PCRE2_AUTO_CALLOUT|PCRE2_CASELESS|PCRE2_DOLLAR_ENDONLY| \ + PCRE2_DOTALL|PCRE2_DUPNAMES|PCRE2_EXTENDED|PCRE2_FIRSTLINE| \ + PCRE2_MATCH_UNSET_BACKREF|PCRE2_MULTILINE|PCRE2_NEVER_BACKSLASH_C| \ + PCRE2_NEVER_UCP|PCRE2_NEVER_UTF|PCRE2_NO_AUTO_CAPTURE| \ + PCRE2_NO_AUTO_POSSESS|PCRE2_NO_DOTSTAR_ANCHOR|PCRE2_NO_START_OPTIMIZE| \ + PCRE2_NO_UTF_CHECK|PCRE2_UCP|PCRE2_UNGREEDY|PCRE2_UTF) /* Compile time error code numbers. They are given names so that they can more easily be tracked. When a new number is added, the tables called eint1 and @@ -5382,13 +5382,52 @@ for (;; ptr++) /* It appears that Perl allows any characters whatsoever, other than a closing parenthesis, to appear in arguments, so we no longer insist on - letters, digits, and underscores. */ + letters, digits, and underscores. Perl does not, however, do any + interpretation within arguments, and has no means of including a closing + parenthesis. PCRE supports escape processing but only when it is + requested by an option. Note that check_escape() will not return values + greater than the code unit maximum when not in UTF mode. */ if (*ptr == CHAR_COLON) { arg = ++ptr; - while (*ptr != CHAR_NULL && *ptr != CHAR_RIGHT_PARENTHESIS) ptr++; - arglen = (int)(ptr - arg); + + if ((options & PCRE2_ALT_VERBNAMES) == 0) + { + while (*ptr != CHAR_NULL && *ptr != CHAR_RIGHT_PARENTHESIS) ptr++; + arglen = (int)(ptr - arg); + } + else + { + arglen = 0; + while (*ptr != CHAR_NULL && *ptr != CHAR_RIGHT_PARENTHESIS) + { + if (*ptr == '\\') + { + uint32_t x; + *errorcodeptr = 0; + i = check_escape(&ptr, &x, errorcodeptr, options, FALSE, cb); + if (*errorcodeptr != 0) goto FAILED; + if (i != 0) + { + *errorcodeptr = ERR40; + goto FAILED; + } +#ifdef SUPPORT_UNICODE +#if PCRE2_CODE_UNIT_WIDTH == 8 + for (i = 0; i < PRIV(utf8_table1_size); i++) + if ((int)x <= PRIV(utf8_table1)[i]) break; + arglen += i; +#elif PCRE2_CODE_UNIT_WIDTH == 16 + if (x > 0xffff) arglen++; +#endif +#endif + } + arglen++; + ptr++; + } + } + if ((unsigned int)arglen > MAX_MARK) { *errorcodeptr = ERR76; @@ -5456,8 +5495,42 @@ for (;; ptr++) } setverb = *code++ = verbs[i].op_arg; *code++ = arglen; - memcpy(code, arg, CU2BYTES(arglen)); - code += arglen; + + /* If we are processing the argument for escapes, we don't need + to apply checks here because it was all checked above when + computing the length. */ + + if ((options & PCRE2_ALT_VERBNAMES) != 0) + { + for (; arg != ptr; arg++) + { + if (*arg == '\\') + { + uint32_t x; + *errorcodeptr = 0; + (void)check_escape(&arg, &x, errorcodeptr, options, FALSE, + cb); +#ifdef SUPPORT_UNICODE + if (utf) + { + PCRE2_UCHAR cbuff[8]; + x = PRIV(ord2utf)(x, cbuff); + memcpy(code, cbuff, CU2BYTES(x)); + code += x; + } + else +#endif + *code++ = x; + } + else *code++ = *arg; + } + } + else /* No argument processing */ + { + memcpy(code, arg, CU2BYTES(arglen)); + code += arglen; + } + *code++ = 0; } @@ -6322,12 +6395,12 @@ for (;; ptr++) } recno += cb->bracount; } - + if ((uint32_t)recno > cb->final_bracount) { *errorcodeptr = ERR15; goto FAILED; - } + } /* Come here from code above that handles a named recursion. We insert the number of the called group after OP_RECURSE. At the @@ -7944,9 +8017,9 @@ while (ptr[skipatstart] == CHAR_LEFT_PARENTHESIS && if (!IS_DIGIT(ptr[pp])) { errorcode = ERR60; - ptr += pp; + ptr += pp; goto HAD_ERROR; - } + } while (IS_DIGIT(ptr[pp])) { if (c > UINT32_MAX / 10 - 1) break; /* Integer overflow */ @@ -7955,7 +8028,7 @@ while (ptr[skipatstart] == CHAR_LEFT_PARENTHESIS && if (ptr[pp++] != CHAR_RIGHT_PARENTHESIS) { errorcode = ERR60; - ptr += pp; + ptr += pp; goto HAD_ERROR; } if (p->type == PSO_LIMM) limit_match = c; @@ -8237,7 +8310,7 @@ if (errorcode == 0 && cb.had_recurse) recno = (int)GET(rcode, 1); if (recno == 0) rgroup = codestart; else { - PCRE2_SPTR search_from = codestart; + PCRE2_SPTR search_from = codestart; rgroup = NULL; for (i = 0, p = start; i < ccount; i++, p = (p + 1) & 7) { @@ -8246,11 +8319,11 @@ if (errorcode == 0 && cb.had_recurse) rgroup = rc[p].group; break; } - - /* Group n+1 must always start to the right of group n, so we can save - search time below when the new group number is greater than any of the + + /* Group n+1 must always start to the right of group n, so we can save + search time below when the new group number is greater than any of the previously found groups. */ - + if (recno > rc[p].recno) search_from = rc[p].group; } diff --git a/src/pcre2_error.c b/src/pcre2_error.c index fb8d813..73ef317 100644 --- a/src/pcre2_error.c +++ b/src/pcre2_error.c @@ -111,7 +111,7 @@ static const char compile_error_texts[] = "number after (?C is greater than 255\0" "closing parenthesis for (?C expected\0" /* 40 */ - "SPARE ERROR\0" + "invalid escape sequence in (*VERB) name\0" "unrecognized character after (?P\0" "syntax error in subpattern name (missing terminator)\0" "two named subpatterns have the same name (PCRE2_DUPNAMES not set)\0" diff --git a/src/pcre2test.c b/src/pcre2test.c index cde7d2f..3f0af15 100644 --- a/src/pcre2test.c +++ b/src/pcre2test.c @@ -496,6 +496,7 @@ static modstruct modlist[] = { { "allusedtext", MOD_PNDP, MOD_CTL, CTL_ALLUSEDTEXT, PO(control) }, { "alt_bsux", MOD_PAT, MOD_OPT, PCRE2_ALT_BSUX, PO(options) }, { "alt_circumflex", MOD_PAT, MOD_OPT, PCRE2_ALT_CIRCUMFLEX, PO(options) }, + { "alt_verbnames", MOD_PAT, MOD_OPT, PCRE2_ALT_VERBNAMES, PO(options) }, { "altglobal", MOD_PND, MOD_CTL, CTL_ALTGLOBAL, PO(control) }, { "anchored", MOD_PD, MOD_OPT, PCRE2_ANCHORED, PD(options) }, { "auto_callout", MOD_PAT, MOD_OPT, PCRE2_AUTO_CALLOUT, PO(options) }, @@ -3467,10 +3468,11 @@ static void show_compile_options(uint32_t options, const char *before, const char *after) { if (options == 0) fprintf(outfile, "%s %s", before, after); -else fprintf(outfile, "%s%s%s%s%s%s%s%s%s%s%s%s%s%s%s%s%s%s%s%s%s%s%s%s%s%s", +else fprintf(outfile, "%s%s%s%s%s%s%s%s%s%s%s%s%s%s%s%s%s%s%s%s%s%s%s%s%s%s%s", before, ((options & PCRE2_ALT_BSUX) != 0)? " alt_bsux" : "", ((options & PCRE2_ALT_CIRCUMFLEX) != 0)? " alt_circumflex" : "", + ((options & PCRE2_ALT_VERBNAMES) != 0)? " alt_verbnames" : "", ((options & PCRE2_ALLOW_EMPTY_CLASS) != 0)? " allow_empty_class" : "", ((options & PCRE2_ANCHORED) != 0)? " anchored" : "", ((options & PCRE2_AUTO_CALLOUT) != 0)? " auto_callout" : "", diff --git a/testdata/testinput2 b/testdata/testinput2 index f16e75e..52b89c7 100644 --- a/testdata/testinput2 +++ b/testdata/testinput2 @@ -4442,4 +4442,11 @@ a random value. /Ix /((*MARK:A))++a(*SKIP:B)b/ aacb +/(*MARK:a\zb)z/alt_verbnames + +/(*:ab\t(d\)c)xxx/ + +/(*:ab\t(d\)c)xxx/alt_verbnames,mark + cxxxz + # End of testinput2 diff --git a/testdata/testinput5 b/testdata/testinput5 index c2adec5..bc76526 100644 --- a/testdata/testinput5 +++ b/testdata/testinput5 @@ -1662,4 +1662,9 @@ /[\pS#moq]/ = +# UTF tests + +/(*:a\x{12345}b\t(d\)c)xxx/utf,alt_verbnames,mark + cxxxz + # End of testinput5 diff --git a/testdata/testinput9 b/testdata/testinput9 index eeb5edb..7b97113 100644 --- a/testdata/testinput9 +++ b/testdata/testinput9 @@ -251,4 +251,6 @@ /[^\s]*\s* [^\W]+\W+ [^\d]*?\d0 [^\d\w]{4,6}?\w*A/B +/(*MARK:a\x{100}b)z/alt_verbnames + # End of testinput9 diff --git a/testdata/testoutput2 b/testdata/testoutput2 index 7aa92be..3451d95 100644 --- a/testdata/testoutput2 +++ b/testdata/testoutput2 @@ -14713,4 +14713,15 @@ No match aacb No match +/(*MARK:a\zb)z/alt_verbnames +Failed: error 140 at offset 9: invalid escape sequence in (*VERB) name + +/(*:ab\t(d\)c)xxx/ +Failed: error 122 at offset 12: unmatched closing parenthesis + +/(*:ab\t(d\)c)xxx/alt_verbnames,mark + cxxxz + 0: xxx +MK: ab\x09(d)c + # End of testinput2 diff --git a/testdata/testoutput5 b/testdata/testoutput5 index 4c2410e..f53f165 100644 --- a/testdata/testoutput5 +++ b/testdata/testoutput5 @@ -4064,4 +4064,11 @@ No match = 0: = +# UTF tests + +/(*:a\x{12345}b\t(d\)c)xxx/utf,alt_verbnames,mark + cxxxz + 0: xxx +MK: a\x{12345}b\x{09}(d)c + # End of testinput5 diff --git a/testdata/testoutput9 b/testdata/testoutput9 index 3aa2071..bd56523 100644 --- a/testdata/testoutput9 +++ b/testdata/testoutput9 @@ -356,4 +356,7 @@ Failed: error 177 at offset 6: character code point value in \u.... sequence is End ------------------------------------------------------------------ +/(*MARK:a\x{100}b)z/alt_verbnames +Failed: error 134 at offset 14: character code point value in \x{} or \o{} is too large + # End of testinput9