From ced3b0f06fe9cd2a66ce7c52f4aec62bb2dd29c1 Mon Sep 17 00:00:00 2001 From: Philip Hazel Date: Mon, 11 Mar 2024 15:50:52 +0000 Subject: [PATCH] Increase name length to 128 --- ChangeLog | 3 + configure.ac | 8 +- doc/html/pcre2pattern.html | 4 +- doc/pcre2.txt | 1466 ++++++++++++++++++------------------ doc/pcre2demo.3 | 2 +- doc/pcre2pattern.3 | 6 +- testdata/testinput10 | 6 +- testdata/testinput2 | 6 +- testdata/testoutput10 | 8 +- testdata/testoutput2 | 8 +- 10 files changed, 760 insertions(+), 757 deletions(-) diff --git a/ChangeLog b/ChangeLog index 5aca4d17d..44bbf696a 100644 --- a/ChangeLog +++ b/ChangeLog @@ -27,6 +27,9 @@ example pattern is: /(((?<=123?456456|ABC)))(?<=\2)/ (d) Made the output in standalone mode more readable. (e) General code tidies. + +3. Increase the maximum length of a name for a group from 32 to 128 because +there is a user for whom 32 is too small. Version 10.43 16-February-2024 diff --git a/configure.ac b/configure.ac index 77b77f3b3..4e2b16f84 100644 --- a/configure.ac +++ b/configure.ac @@ -9,9 +9,9 @@ dnl The PCRE2_PRERELEASE feature is for identifying release candidates. It might dnl be defined as -RC2, for example. For real releases, it should be empty. m4_define(pcre2_major, [10]) -m4_define(pcre2_minor, [43]) -m4_define(pcre2_prerelease, []) -m4_define(pcre2_date, [2024-02-16]) +m4_define(pcre2_minor, [44]) +m4_define(pcre2_prerelease, [-DEV]) +m4_define(pcre2_date, [2024-03-11]) # Libtool shared library interface versions (current:revision:age) m4_define(libpcre2_8_version, [12:0:12]) @@ -883,7 +883,7 @@ AC_DEFINE_UNQUOTED([HEAP_LIMIT], [$with_heap_limit], [ a pattern. It applies to both pcre2_match() and pcre2_dfa_match(). It does not apply to JIT matching. The value is in kibibytes (units of 1024 bytes).]) -AC_DEFINE([MAX_NAME_SIZE], [32], [ +AC_DEFINE([MAX_NAME_SIZE], [128], [ This limit is parameterized just in case anybody ever wants to change it. Care must be taken if it is increased, because it guards against integer overflow caused by enormously large patterns.]) diff --git a/doc/html/pcre2pattern.html b/doc/html/pcre2pattern.html index debce8d44..d90e5d5b4 100644 --- a/doc/html/pcre2pattern.html +++ b/doc/html/pcre2pattern.html @@ -1843,7 +1843,7 @@

pcre2pattern man page

In PCRE2, a capture group can be named in one of three ways: (?<name>...) or -(?'name'...) as in Perl, or (?P<name>...) as in Python. Names may be up to 32 +(?'name'...) as in Perl, or (?P<name>...) as in Python. Names may be up to 128 code units long. When PCRE2_UTF is not set, they may contain only ASCII alphanumeric characters and underscores, but must start with a non-digit. When PCRE2_UTF is set, the syntax of group names is extended to allow any Unicode @@ -3844,7 +3844,7 @@

pcre2pattern man page


REVISION

-Last updated: 19 January 2024 +Last updated: 11 March 2024
Copyright © 1997-2024 University of Cambridge.
diff --git a/doc/pcre2.txt b/doc/pcre2.txt index 4c0095d8a..3c70a8a49 100644 --- a/doc/pcre2.txt +++ b/doc/pcre2.txt @@ -8120,8 +8120,8 @@ NAMED CAPTURE GROUPS In PCRE2, a capture group can be named in one of three ways: (?...) or (?'name'...) as in Perl, or (?P...) as in Python. - Names may be up to 32 code units long. When PCRE2_UTF is not set, they - may contain only ASCII alphanumeric characters and underscores, but + Names may be up to 128 code units long. When PCRE2_UTF is not set, they + may contain only ASCII alphanumeric characters and underscores, but must start with a non-digit. When PCRE2_UTF is set, the syntax of group names is extended to allow any Unicode letter or Unicode decimal digit. In other words, group names must match one of these patterns: @@ -8129,42 +8129,42 @@ NAMED CAPTURE GROUPS ^[_A-Za-z][_A-Za-z0-9]*\z when PCRE2_UTF is not set ^[_\p{L}][_\p{L}\p{Nd}]*\z when PCRE2_UTF is set - References to capture groups from other parts of the pattern, such as - backreferences, recursion, and conditions, can all be made by name as + References to capture groups from other parts of the pattern, such as + backreferences, recursion, and conditions, can all be made by name as well as by number. Named capture groups are allocated numbers as well as names, exactly as - if the names were not present. In both PCRE2 and Perl, capture groups - are primarily identified by numbers; any names are just aliases for + if the names were not present. In both PCRE2 and Perl, capture groups + are primarily identified by numbers; any names are just aliases for these numbers. The PCRE2 API provides function calls for extracting the - complete name-to-number translation table from a compiled pattern, as - well as convenience functions for extracting captured substrings by + complete name-to-number translation table from a compiled pattern, as + well as convenience functions for extracting captured substrings by name. - Warning: When more than one capture group has the same number, as de- + Warning: When more than one capture group has the same number, as de- scribed in the previous section, a name given to one of them applies to - all of them. Perl allows identically numbered groups to have different + all of them. Perl allows identically numbered groups to have different names. Consider this pattern, where there are two capture groups, both numbered 1: (?|(?aa)|(?bb)) - Perl allows this, with both names AA and BB as aliases of group 1. + Perl allows this, with both names AA and BB as aliases of group 1. Thus, after a successful match, both names yield the same value (either "aa" or "bb"). - In an attempt to reduce confusion, PCRE2 does not allow the same group + In an attempt to reduce confusion, PCRE2 does not allow the same group number to be associated with more than one name. The example above pro- - vokes a compile-time error. However, there is still scope for confu- + vokes a compile-time error. However, there is still scope for confu- sion. Consider this pattern: (?|(?aa)|(bb)) Although the second group number 1 is not explicitly named, the name AA - is still an alias for any group 1. Whether the pattern matches "aa" or + is still an alias for any group 1. Whether the pattern matches "aa" or "bb", a reference by name to group AA yields the matched string. - By default, a name must be unique within a pattern, except that dupli- + By default, a name must be unique within a pattern, except that dupli- cate names are permitted for groups with the same number, for example: (?|(?aa)|(?bb)) @@ -8173,10 +8173,10 @@ NAMED CAPTURE GROUPS NAMES option at compile time, or by the use of (?J) within the pattern, as described in the section entitled "Internal Option Setting" above. - Duplicate names can be useful for patterns where only one instance of - the named capture group can match. Suppose you want to match the name - of a weekday, either as a 3-letter abbreviation or as the full name, - and in both cases you want to extract the abbreviation. This pattern + Duplicate names can be useful for patterns where only one instance of + the named capture group can match. Suppose you want to match the name + of a weekday, either as a 3-letter abbreviation or as the full name, + and in both cases you want to extract the abbreviation. This pattern (ignoring the line breaks) does the job: (?J) @@ -8186,17 +8186,17 @@ NAMED CAPTURE GROUPS (?Thu)(?:rsday)?| (?Sat)(?:urday)? - There are five capture groups, but only one is ever set after a match. - The convenience functions for extracting the data by name returns the - substring for the first (and in this example, the only) group of that + There are five capture groups, but only one is ever set after a match. + The convenience functions for extracting the data by name returns the + substring for the first (and in this example, the only) group of that name that matched. This saves searching to find which numbered group it - was. (An alternative way of solving this problem is to use a "branch + was. (An alternative way of solving this problem is to use a "branch reset" group, as described in the previous section.) - If you make a backreference to a non-unique named group from elsewhere - in the pattern, the groups to which the name refers are checked in the - order in which they appear in the overall pattern. The first one that - is set is used for the reference. For example, this pattern matches + If you make a backreference to a non-unique named group from elsewhere + in the pattern, the groups to which the name refers are checked in the + order in which they appear in the overall pattern. The first one that + is set is used for the reference. For example, this pattern matches both "foofoo" and "barbar" but not "foobar" or "barfoo": (?J)(?:(?foo)|(?bar))\k @@ -8209,15 +8209,15 @@ NAMED CAPTURE GROUPS If you use a named reference in a condition test (see the section about conditions below), either to check whether a capture group has matched, or to check for recursion, all groups with the same name are tested. If - the condition is true for any one of them, the overall condition is - true. This is the same behaviour as testing by number. For further de- - tails of the interfaces for handling named capture groups, see the + the condition is true for any one of them, the overall condition is + true. This is the same behaviour as testing by number. For further de- + tails of the interfaces for handling named capture groups, see the pcre2api documentation. REPETITION - Repetition is specified by quantifiers, which may follow any one of + Repetition is specified by quantifiers, which may follow any one of these items: a literal data character @@ -8233,16 +8233,16 @@ REPETITION If a quantifier does not follow a repeatable item, an error occurs. The general repetition quantifier specifies a minimum and maximum number of - permitted matches by giving two numbers in curly brackets (braces), - separated by a comma. The numbers must be less than 65536, and the + permitted matches by giving two numbers in curly brackets (braces), + separated by a comma. The numbers must be less than 65536, and the first must be less than or equal to the second. For example, z{2,4} - matches "zz", "zzz", or "zzzz". A closing brace on its own is not a - special character. If the second number is omitted, but the comma is - present, there is no upper limit; if the second number and the comma - are both omitted, the quantifier specifies an exact number of required + matches "zz", "zzz", or "zzzz". A closing brace on its own is not a + special character. If the second number is omitted, but the comma is + present, there is no upper limit; if the second number and the comma + are both omitted, the quantifier specifies an exact number of required matches. Thus [aeiou]{3,} @@ -8251,65 +8251,65 @@ REPETITION \d{8} - matches exactly 8 digits. If the first number is omitted, the lower + matches exactly 8 digits. If the first number is omitted, the lower limit is taken as zero; in this case the upper limit must be present. X{,4} is interpreted as X{0,4} - This is a change in behaviour that happened in Perl 5.34.0 and PCRE2 - 10.43. In earlier versions such a sequence was not interpreted as a + This is a change in behaviour that happened in Perl 5.34.0 and PCRE2 + 10.43. In earlier versions such a sequence was not interpreted as a quantifier. Other regular expression engines may behave either way. - If the characters that follow an opening brace do not match the syntax + If the characters that follow an opening brace do not match the syntax of a quantifier, the brace is taken as a literal character. In particu- lar, this means that {,} is a literal string of three characters. Note that not every opening brace is potentially the start of a quanti- - fier because braces are used in other items such as \N{U+345} or + fier because braces are used in other items such as \N{U+345} or \k{name}. In UTF modes, quantifiers apply to characters rather than to individual - code units. Thus, for example, \x{100}{2} matches two characters, each + code units. Thus, for example, \x{100}{2} matches two characters, each of which is represented by a two-byte sequence in a UTF-8 string. Simi- - larly, \X{3} matches three Unicode extended grapheme clusters, each of - which may be several code units long (and they may be of different + larly, \X{3} matches three Unicode extended grapheme clusters, each of + which may be several code units long (and they may be of different lengths). The quantifier {0} is permitted, causing the expression to behave as if the previous item and the quantifier were not present. This may be use- - ful for capture groups that are referenced as subroutines from else- - where in the pattern (but see also the section entitled "Defining cap- + ful for capture groups that are referenced as subroutines from else- + where in the pattern (but see also the section entitled "Defining cap- ture groups for use by reference only" below). Except for parenthesized - groups, items that have a {0} quantifier are omitted from the compiled + groups, items that have a {0} quantifier are omitted from the compiled pattern. - For convenience, the three most common quantifiers have single-charac- + For convenience, the three most common quantifiers have single-charac- ter abbreviations: * is equivalent to {0,} + is equivalent to {1,} ? is equivalent to {0,1} - It is possible to construct infinite loops by following a group that - can match no characters with a quantifier that has no upper limit, for + It is possible to construct infinite loops by following a group that + can match no characters with a quantifier that has no upper limit, for example: (a?)* - Earlier versions of Perl and PCRE1 used to give an error at compile + Earlier versions of Perl and PCRE1 used to give an error at compile time for such patterns. However, because there are cases where this can be useful, such patterns are now accepted, but whenever an iteration of - such a group matches no characters, matching moves on to the next item - in the pattern instead of repeatedly matching an empty string. This - does not prevent backtracking into any of the iterations if a subse- + such a group matches no characters, matching moves on to the next item + in the pattern instead of repeatedly matching an empty string. This + does not prevent backtracking into any of the iterations if a subse- quent item fails to match. - By default, quantifiers are "greedy", that is, they match as much as - possible (up to the maximum number of permitted repetitions), without - causing the rest of the pattern to fail. The classic example of where + By default, quantifiers are "greedy", that is, they match as much as + possible (up to the maximum number of permitted repetitions), without + causing the rest of the pattern to fail. The classic example of where this gives problems is in trying to match comments in C programs. These - appear between /* and */ and within the comment, individual * and / - characters may appear. An attempt to match C comments by applying the + appear between /* and */ and within the comment, individual * and / + characters may appear. An attempt to match C comments by applying the pattern /\*.*\*/ @@ -8318,17 +8318,17 @@ REPETITION /* first comment */ not comment /* second comment */ - fails, because it matches the entire string owing to the greediness of - the .* item. However, if a quantifier is followed by a question mark, + fails, because it matches the entire string owing to the greediness of + the .* item. However, if a quantifier is followed by a question mark, it ceases to be greedy, and instead matches the minimum number of times possible, so the pattern /\*.*?\*/ - does the right thing with C comments. The meaning of the various quan- + does the right thing with C comments. The meaning of the various quan- tifiers is not otherwise changed, just the preferred number of matches. - Do not confuse this use of question mark with its use as a quantifier - in its own right. Because it has two uses, it can sometimes appear + Do not confuse this use of question mark with its use as a quantifier + in its own right. Because it has two uses, it can sometimes appear doubled, as in \d??\d @@ -8337,55 +8337,55 @@ REPETITION only way the rest of the pattern matches. If the PCRE2_UNGREEDY option is set (an option that is not available in - Perl), the quantifiers are not greedy by default, but individual ones - can be made greedy by following them with a question mark. In other + Perl), the quantifiers are not greedy by default, but individual ones + can be made greedy by following them with a question mark. In other words, it inverts the default behaviour. - When a parenthesized group is quantified with a minimum repeat count - that is greater than 1 or with a limited maximum, more memory is re- + When a parenthesized group is quantified with a minimum repeat count + that is greater than 1 or with a limited maximum, more memory is re- quired for the compiled pattern, in proportion to the size of the mini- mum or maximum. - If a pattern starts with .* or .{0,} and the PCRE2_DOTALL option - (equivalent to Perl's /s) is set, thus allowing the dot to match new- - lines, the pattern is implicitly anchored, because whatever follows - will be tried against every character position in the subject string, - so there is no point in retrying the overall match at any position af- - ter the first. PCRE2 normally treats such a pattern as though it were + If a pattern starts with .* or .{0,} and the PCRE2_DOTALL option + (equivalent to Perl's /s) is set, thus allowing the dot to match new- + lines, the pattern is implicitly anchored, because whatever follows + will be tried against every character position in the subject string, + so there is no point in retrying the overall match at any position af- + ter the first. PCRE2 normally treats such a pattern as though it were preceded by \A. - In cases where it is known that the subject string contains no new- - lines, it is worth setting PCRE2_DOTALL in order to obtain this opti- + In cases where it is known that the subject string contains no new- + lines, it is worth setting PCRE2_DOTALL in order to obtain this opti- mization, or alternatively, using ^ to indicate anchoring explicitly. - However, there are some cases where the optimization cannot be used. - When .* is inside capturing parentheses that are the subject of a - backreference elsewhere in the pattern, a match at the start may fail + However, there are some cases where the optimization cannot be used. + When .* is inside capturing parentheses that are the subject of a + backreference elsewhere in the pattern, a match at the start may fail where a later one succeeds. Consider, for example: (.*)abc\1 - If the subject is "xyz123abc123" the match point is the fourth charac- + If the subject is "xyz123abc123" the match point is the fourth charac- ter. For this reason, such a pattern is not implicitly anchored. - Another case where implicit anchoring is not applied is when the lead- - ing .* is inside an atomic group. Once again, a match at the start may + Another case where implicit anchoring is not applied is when the lead- + ing .* is inside an atomic group. Once again, a match at the start may fail where a later one succeeds. Consider this pattern: (?>.*?a)b - It matches "ab" in the subject "aab". The use of the backtracking con- - trol verbs (*PRUNE) and (*SKIP) also disable this optimization, and + It matches "ab" in the subject "aab". The use of the backtracking con- + trol verbs (*PRUNE) and (*SKIP) also disable this optimization, and there is an option, PCRE2_NO_DOTSTAR_ANCHOR, to do so explicitly. - When a capture group is repeated, the value captured is the substring + When a capture group is repeated, the value captured is the substring that matched the final iteration. For example, after (tweedle[dume]{3}\s*)+ has matched "tweedledum tweedledee" the value of the captured substring - is "tweedledee". However, if there are nested capture groups, the cor- - responding captured values may have been set in previous iterations. + is "tweedledee". However, if there are nested capture groups, the cor- + responding captured values may have been set in previous iterations. For example, after (a|(b))+ @@ -8395,57 +8395,57 @@ REPETITION ATOMIC GROUPING AND POSSESSIVE QUANTIFIERS - With both maximizing ("greedy") and minimizing ("ungreedy" or "lazy") - repetition, failure of what follows normally causes the repeated item - to be re-evaluated to see if a different number of repeats allows the - rest of the pattern to match. Sometimes it is useful to prevent this, - either to change the nature of the match, or to cause it fail earlier - than it otherwise might, when the author of the pattern knows there is + With both maximizing ("greedy") and minimizing ("ungreedy" or "lazy") + repetition, failure of what follows normally causes the repeated item + to be re-evaluated to see if a different number of repeats allows the + rest of the pattern to match. Sometimes it is useful to prevent this, + either to change the nature of the match, or to cause it fail earlier + than it otherwise might, when the author of the pattern knows there is no point in carrying on. - Consider, for example, the pattern \d+foo when applied to the subject + Consider, for example, the pattern \d+foo when applied to the subject line 123456bar After matching all 6 digits and then failing to match "foo", the normal - action of the matcher is to try again with only 5 digits matching the - \d+ item, and then with 4, and so on, before ultimately failing. - "Atomic grouping" (a term taken from Jeffrey Friedl's book) provides + action of the matcher is to try again with only 5 digits matching the + \d+ item, and then with 4, and so on, before ultimately failing. + "Atomic grouping" (a term taken from Jeffrey Friedl's book) provides the means for specifying that once a group has matched, it is not to be re-evaluated in this way. - If we use atomic grouping for the previous example, the matcher gives - up immediately on failing to match "foo" the first time. The notation + If we use atomic grouping for the previous example, the matcher gives + up immediately on failing to match "foo" the first time. The notation is a kind of special parenthesis, starting with (?> as in this example: (?>\d+)foo - Perl 5.28 introduced an experimental alphabetic form starting with (* + Perl 5.28 introduced an experimental alphabetic form starting with (* which may be easier to remember: (*atomic:\d+)foo - This kind of parenthesized group "locks up" the part of the pattern it + This kind of parenthesized group "locks up" the part of the pattern it contains once it has matched, and a failure further into the pattern is - prevented from backtracking into it. Backtracking past it to previous + prevented from backtracking into it. Backtracking past it to previous items, however, works as normal. An alternative description is that a group of this type matches exactly - the string of characters that an identical standalone pattern would + the string of characters that an identical standalone pattern would match, if anchored at the current point in the subject string. - Atomic groups are not capture groups. Simple cases such as the above - example can be thought of as a maximizing repeat that must swallow - everything it can. So, while both \d+ and \d+? are prepared to adjust - the number of digits they match in order to make the rest of the pat- + Atomic groups are not capture groups. Simple cases such as the above + example can be thought of as a maximizing repeat that must swallow + everything it can. So, while both \d+ and \d+? are prepared to adjust + the number of digits they match in order to make the rest of the pat- tern match, (?>\d+) can only match an entire sequence of digits. - Atomic groups in general can of course contain arbitrarily complicated + Atomic groups in general can of course contain arbitrarily complicated expressions, and can be nested. However, when the contents of an atomic - group is just a single repeated item, as in the example above, a sim- - pler notation, called a "possessive quantifier" can be used. This con- - sists of an additional + character following a quantifier. Using this + group is just a single repeated item, as in the example above, a sim- + pler notation, called a "possessive quantifier" can be used. This con- + sists of an additional + character following a quantifier. Using this notation, the previous example can be rewritten as \d++foo @@ -8455,46 +8455,46 @@ ATOMIC GROUPING AND POSSESSIVE QUANTIFIERS (abc|xyz){2,3}+ - Possessive quantifiers are always greedy; the setting of the PCRE2_UN- - GREEDY option is ignored. They are a convenient notation for the sim- - pler forms of atomic group. However, there is no difference in the - meaning of a possessive quantifier and the equivalent atomic group, - though there may be a performance difference; possessive quantifiers + Possessive quantifiers are always greedy; the setting of the PCRE2_UN- + GREEDY option is ignored. They are a convenient notation for the sim- + pler forms of atomic group. However, there is no difference in the + meaning of a possessive quantifier and the equivalent atomic group, + though there may be a performance difference; possessive quantifiers should be slightly faster. - The possessive quantifier syntax is an extension to the Perl 5.8 syn- - tax. Jeffrey Friedl originated the idea (and the name) in the first + The possessive quantifier syntax is an extension to the Perl 5.8 syn- + tax. Jeffrey Friedl originated the idea (and the name) in the first edition of his book. Mike McCloskey liked it, so implemented it when he - built Sun's Java package, and PCRE1 copied it from there. It found its + built Sun's Java package, and PCRE1 copied it from there. It found its way into Perl at release 5.10. - PCRE2 has an optimization that automatically "possessifies" certain - simple pattern constructs. For example, the sequence A+B is treated as - A++B because there is no point in backtracking into a sequence of A's + PCRE2 has an optimization that automatically "possessifies" certain + simple pattern constructs. For example, the sequence A+B is treated as + A++B because there is no point in backtracking into a sequence of A's when B must follow. This feature can be disabled by the PCRE2_NO_AUTO- POSSESS option, or starting the pattern with (*NO_AUTO_POSSESS). When a pattern contains an unlimited repeat inside a group that can it- - self be repeated an unlimited number of times, the use of an atomic - group is the only way to avoid some failing matches taking a very long + self be repeated an unlimited number of times, the use of an atomic + group is the only way to avoid some failing matches taking a very long time indeed. The pattern (\D+|<\d+>)*[!?] - matches an unlimited number of substrings that either consist of non- - digits, or digits enclosed in <>, followed by either ! or ?. When it + matches an unlimited number of substrings that either consist of non- + digits, or digits enclosed in <>, followed by either ! or ?. When it matches, it runs quickly. However, if it is applied to aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa - it takes a long time before reporting failure. This is because the - string can be divided between the internal \D+ repeat and the external - * repeat in a large number of ways, and all have to be tried. (The ex- + it takes a long time before reporting failure. This is because the + string can be divided between the internal \D+ repeat and the external + * repeat in a large number of ways, and all have to be tried. (The ex- ample uses [!?] rather than a single character at the end, because both PCRE2 and Perl have an optimization that allows for fast failure when a - single character is used. They remember the last single character that - is required for a match, and fail early if it is not present in the - string.) If the pattern is changed so that it uses an atomic group, + single character is used. They remember the last single character that + is required for a match, and fail early if it is not present in the + string.) If the pattern is changed so that it uses an atomic group, like this: ((?>\D+)|<\d+>)*[!?] @@ -8505,28 +8505,28 @@ ATOMIC GROUPING AND POSSESSIVE QUANTIFIERS BACKREFERENCES Outside a character class, a backslash followed by a digit greater than - 0 (and possibly further digits) is a backreference to a capture group + 0 (and possibly further digits) is a backreference to a capture group earlier (that is, to its left) in the pattern, provided there have been that many previous capture groups. - However, if the decimal number following the backslash is less than 8, - it is always taken as a backreference, and causes an error only if - there are not that many capture groups in the entire pattern. In other + However, if the decimal number following the backslash is less than 8, + it is always taken as a backreference, and causes an error only if + there are not that many capture groups in the entire pattern. In other words, the group that is referenced need not be to the left of the ref- - erence for numbers less than 8. A "forward backreference" of this type + erence for numbers less than 8. A "forward backreference" of this type can make sense when a repetition is involved and the group to the right has participated in an earlier iteration. - It is not possible to have a numerical "forward backreference" to a - group whose number is 8 or more using this syntax because a sequence - such as \50 is interpreted as a character defined in octal. See the + It is not possible to have a numerical "forward backreference" to a + group whose number is 8 or more using this syntax because a sequence + such as \50 is interpreted as a character defined in octal. See the subsection entitled "Non-printing characters" above for further details - of the handling of digits following a backslash. Other forms of back- - referencing do not suffer from this restriction. In particular, there + of the handling of digits following a backslash. Other forms of back- + referencing do not suffer from this restriction. In particular, there is no problem when named capture groups are used (see below). - Another way of avoiding the ambiguity inherent in the use of digits - following a backslash is to use the \g escape sequence. This escape + Another way of avoiding the ambiguity inherent in the use of digits + following a backslash is to use the \g escape sequence. This escape must be followed by a signed or unsigned number, optionally enclosed in braces. These examples are all identical: @@ -8534,54 +8534,54 @@ BACKREFERENCES (ring), \g1 (ring), \g{1} - An unsigned number specifies an absolute reference without the ambigu- + An unsigned number specifies an absolute reference without the ambigu- ity that is present in the older syntax. It is also useful when literal - digits follow the reference. A signed number is a relative reference. + digits follow the reference. A signed number is a relative reference. Consider this example: (abc(def)ghi)\g{-1} The sequence \g{-1} is a reference to the capture group whose number is - one less than the number of the next group to be started, so in this - example (where the next group would be numbered 3) is it equivalent to - \2, and \g{-2} would be equivalent to \1. Note that if this construct - is inside a capture group, that group is included in the count, so in + one less than the number of the next group to be started, so in this + example (where the next group would be numbered 3) is it equivalent to + \2, and \g{-2} would be equivalent to \1. Note that if this construct + is inside a capture group, that group is included in the count, so in this example \g{-2} also refers to group 1: (A)(\g{-2}B) - The use of relative references can be helpful in long patterns, and - also in patterns that are created by joining together fragments that + The use of relative references can be helpful in long patterns, and + also in patterns that are created by joining together fragments that contain references within themselves. - The sequence \g{+1} is a reference to the next capture group that is - started after this item, and \g{+2} refers to the one after that, and - so on. This kind of forward reference can be useful in patterns that + The sequence \g{+1} is a reference to the next capture group that is + started after this item, and \g{+2} refers to the one after that, and + so on. This kind of forward reference can be useful in patterns that repeat. Perl does not support the use of + in this way. - A backreference matches whatever actually most recently matched the - capture group in the current subject string, rather than anything at + A backreference matches whatever actually most recently matched the + capture group in the current subject string, rather than anything at all that matches the group (see "Groups as subroutines" below for a way of doing that). So the pattern (sens|respons)e and \1ibility - matches "sense and sensibility" and "response and responsibility", but - not "sense and responsibility". If caseful matching is in force at the - time of the backreference, the case of letters is relevant. For exam- + matches "sense and sensibility" and "response and responsibility", but + not "sense and responsibility". If caseful matching is in force at the + time of the backreference, the case of letters is relevant. For exam- ple, ((?i)rah)\s+\1 - matches "rah rah" and "RAH RAH", but not "RAH rah", even though the + matches "rah rah" and "RAH RAH", but not "RAH rah", even though the original capture group is matched caselessly. - There are several different ways of writing backreferences to named - capture groups. The .NET syntax is \k{name}, the Python syntax is - (?=name), and the original Perl syntax is \k or \k'name'. All of - these are now supported by both Perl and PCRE2. Perl 5.10's unified - backreference syntax, in which \g can be used for both numeric and - named references, is also supported by PCRE2. We could rewrite the + There are several different ways of writing backreferences to named + capture groups. The .NET syntax is \k{name}, the Python syntax is + (?=name), and the original Perl syntax is \k or \k'name'. All of + these are now supported by both Perl and PCRE2. Perl 5.10's unified + backreference syntax, in which \g can be used for both numeric and + named references, is also supported by PCRE2. We could rewrite the above example in any of the following ways: (?(?i)rah)\s+\k @@ -8589,114 +8589,114 @@ BACKREFERENCES (?P(?i)rah)\s+(?P=p1) (?(?i)rah)\s+\g{p1} - A capture group that is referenced by name may appear in the pattern + A capture group that is referenced by name may appear in the pattern before or after the reference. - There may be more than one backreference to the same group. If a group - has not actually been used in a particular match, backreferences to it + There may be more than one backreference to the same group. If a group + has not actually been used in a particular match, backreferences to it always fail by default. For example, the pattern (a|(bc))\2 - always fails if it starts to match "a" rather than "bc". However, if + always fails if it starts to match "a" rather than "bc". However, if the PCRE2_MATCH_UNSET_BACKREF option is set at compile time, a backref- erence to an unset value matches an empty string. - Because there may be many capture groups in a pattern, all digits fol- - lowing a backslash are taken as part of a potential backreference num- - ber. If the pattern continues with a digit character, some delimiter - must be used to terminate the backreference. If the PCRE2_EXTENDED or - PCRE2_EXTENDED_MORE option is set, this can be white space. Otherwise, + Because there may be many capture groups in a pattern, all digits fol- + lowing a backslash are taken as part of a potential backreference num- + ber. If the pattern continues with a digit character, some delimiter + must be used to terminate the backreference. If the PCRE2_EXTENDED or + PCRE2_EXTENDED_MORE option is set, this can be white space. Otherwise, the \g{} syntax or an empty comment (see "Comments" below) can be used. Recursive backreferences - A backreference that occurs inside the group to which it refers fails - when the group is first used, so, for example, (a\1) never matches. - However, such references can be useful inside repeated groups. For ex- + A backreference that occurs inside the group to which it refers fails + when the group is first used, so, for example, (a\1) never matches. + However, such references can be useful inside repeated groups. For ex- ample, the pattern (a|b\1)+ matches any number of "a"s and also "aba", "ababbaa" etc. At each iter- ation of the group, the backreference matches the character string cor- - responding to the previous iteration. In order for this to work, the - pattern must be such that the first iteration does not need to match - the backreference. This can be done using alternation, as in the exam- + responding to the previous iteration. In order for this to work, the + pattern must be such that the first iteration does not need to match + the backreference. This can be done using alternation, as in the exam- ple above, or by a quantifier with a minimum of zero. For versions of PCRE2 less than 10.25, backreferences of this type used - to cause the group that they reference to be treated as an atomic - group. This restriction no longer applies, and backtracking into such + to cause the group that they reference to be treated as an atomic + group. This restriction no longer applies, and backtracking into such groups can occur as normal. ASSERTIONS - An assertion is a test on the characters following or preceding the + An assertion is a test on the characters following or preceding the current matching point that does not consume any characters. The simple - assertions coded as \b, \B, \A, \G, \Z, \z, ^ and $ are described + assertions coded as \b, \B, \A, \G, \Z, \z, ^ and $ are described above. - More complicated assertions are coded as parenthesized groups. There - are two kinds: those that look ahead of the current position in the - subject string, and those that look behind it, and in each case an as- - sertion may be positive (must match for the assertion to be true) or - negative (must not match for the assertion to be true). An assertion + More complicated assertions are coded as parenthesized groups. There + are two kinds: those that look ahead of the current position in the + subject string, and those that look behind it, and in each case an as- + sertion may be positive (must match for the assertion to be true) or + negative (must not match for the assertion to be true). An assertion group is matched in the normal way, and if it is true, matching contin- - ues after it, but with the matching position in the subject string re- + ues after it, but with the matching position in the subject string re- set to what it was before the assertion was processed. - The Perl-compatible lookaround assertions are atomic. If an assertion - is true, but there is a subsequent matching failure, there is no back- - tracking into the assertion. However, there are some cases where non- - atomic assertions can be useful. PCRE2 has some support for these, de- + The Perl-compatible lookaround assertions are atomic. If an assertion + is true, but there is a subsequent matching failure, there is no back- + tracking into the assertion. However, there are some cases where non- + atomic assertions can be useful. PCRE2 has some support for these, de- scribed in the section entitled "Non-atomic assertions" below, but they are not Perl-compatible. - A lookaround assertion may appear as the condition in a conditional - group (see below). In this case, the result of matching the assertion + A lookaround assertion may appear as the condition in a conditional + group (see below). In this case, the result of matching the assertion determines which branch of the condition is followed. - Assertion groups are not capture groups. If an assertion contains cap- - ture groups within it, these are counted for the purposes of numbering - the capture groups in the whole pattern. Within each branch of an as- - sertion, locally captured substrings may be referenced in the usual - way. For example, a sequence such as (.)\g{-1} can be used to check + Assertion groups are not capture groups. If an assertion contains cap- + ture groups within it, these are counted for the purposes of numbering + the capture groups in the whole pattern. Within each branch of an as- + sertion, locally captured substrings may be referenced in the usual + way. For example, a sequence such as (.)\g{-1} can be used to check that two adjacent characters are the same. - When a branch within an assertion fails to match, any substrings that - were captured are discarded (as happens with any pattern branch that - fails to match). A negative assertion is true only when all its + When a branch within an assertion fails to match, any substrings that + were captured are discarded (as happens with any pattern branch that + fails to match). A negative assertion is true only when all its branches fail to match; this means that no captured substrings are ever - retained after a successful negative assertion. When an assertion con- + retained after a successful negative assertion. When an assertion con- tains a matching branch, what happens depends on the type of assertion. - For a positive assertion, internally captured substrings in the suc- - cessful branch are retained, and matching continues with the next pat- - tern item after the assertion. For a negative assertion, a matching - branch means that the assertion is not true. If such an assertion is - being used as a condition in a conditional group (see below), captured - substrings are retained, because matching continues with the "no" + For a positive assertion, internally captured substrings in the suc- + cessful branch are retained, and matching continues with the next pat- + tern item after the assertion. For a negative assertion, a matching + branch means that the assertion is not true. If such an assertion is + being used as a condition in a conditional group (see below), captured + substrings are retained, because matching continues with the "no" branch of the condition. For other failing negative assertions, control passes to the previous backtracking point, thus discarding any captured strings within the assertion. - Most assertion groups may be repeated; though it makes no sense to as- + Most assertion groups may be repeated; though it makes no sense to as- sert the same thing several times, the side effect of capturing in pos- itive assertions may occasionally be useful. However, an assertion that - forms the condition for a conditional group may not be quantified. - PCRE2 used to restrict the repetition of assertions, but from release - 10.35 the only restriction is that an unlimited maximum repetition is - changed to be one more than the minimum. For example, {3,} is treated + forms the condition for a conditional group may not be quantified. + PCRE2 used to restrict the repetition of assertions, but from release + 10.35 the only restriction is that an unlimited maximum repetition is + changed to be one more than the minimum. For example, {3,} is treated as {3,4}. Alphabetic assertion names - Traditionally, symbolic sequences such as (?= and (?<= have been used - to specify lookaround assertions. Perl 5.28 introduced some experimen- + Traditionally, symbolic sequences such as (?= and (?<= have been used + to specify lookaround assertions. Perl 5.28 introduced some experimen- tal alphabetic alternatives which might be easier to remember. They all - start with (* instead of (? and must be written using lower case let- + start with (* instead of (? and must be written using lower case let- ters. PCRE2 supports the following synonyms: (*positive_lookahead: or (*pla: is the same as (?= @@ -8704,8 +8704,8 @@ ASSERTIONS (*positive_lookbehind: or (*plb: is the same as (?<= (*negative_lookbehind: or (*nlb: is the same as (? .*? \b\1\b ){2} - For a subject such as "word1 word2 word3 word2 word3 word4" the result - is "word3". How does it work? At the start, ^(?x) anchors the pattern + For a subject such as "word1 word2 word3 word2 word3 word4" the result + is "word3". How does it work? At the start, ^(?x) anchors the pattern and sets the "x" option, which causes white space (introduced for read- - ability) to be ignored. Inside the assertion, the greedy .* at first + ability) to be ignored. Inside the assertion, the greedy .* at first consumes the entire string, but then has to backtrack until the rest of - the assertion can match a word, which is captured by group 1. In other - words, when the assertion first succeeds, it captures the right-most + the assertion can match a word, which is captured by group 1. In other + words, when the assertion first succeeds, it captures the right-most word in the string. - The current matching point is then reset to the start of the subject, - and the rest of the pattern match checks for two occurrences of the - captured word, using an ungreedy .*? to scan from the left. If this - succeeds, we are done, but if the last word in the string does not oc- - cur twice, this part of the pattern fails. If a traditional atomic - lookahead (?= or (*pla: had been used, the assertion could not be re- + The current matching point is then reset to the start of the subject, + and the rest of the pattern match checks for two occurrences of the + captured word, using an ungreedy .*? to scan from the left. If this + succeeds, we are done, but if the last word in the string does not oc- + cur twice, this part of the pattern fails. If a traditional atomic + lookahead (?= or (*pla: had been used, the assertion could not be re- entered, and the whole match would fail. The pattern would succeed only if the very last word in the subject was found twice. - Using a non-atomic lookahead, however, means that when the last word - does not occur twice in the string, the lookahead can backtrack and - find the second-last word, and so on, until either the match succeeds, + Using a non-atomic lookahead, however, means that when the last word + does not occur twice in the string, the lookahead can backtrack and + find the second-last word, and so on, until either the match succeeds, or all words have been tested. Two conditions must be met for a non-atomic assertion to be useful: the - contents of one or more capturing groups must change after a backtrack - into the assertion, and there must be a backreference to a changed - group later in the pattern. If this is not the case, the rest of the - pattern match fails exactly as before because nothing has changed, so + contents of one or more capturing groups must change after a backtrack + into the assertion, and there must be a backreference to a changed + group later in the pattern. If this is not the case, the rest of the + pattern match fails exactly as before because nothing has changed, so using a non-atomic assertion just wastes resources. - There is one exception to backtracking into a non-atomic assertion. If - an (*ACCEPT) control verb is triggered, the assertion succeeds atomi- - cally. That is, a subsequent match failure cannot backtrack into the + There is one exception to backtracking into a non-atomic assertion. If + an (*ACCEPT) control verb is triggered, the assertion succeeds atomi- + cally. That is, a subsequent match failure cannot backtrack into the assertion. - Non-atomic assertions are not supported by the alternative matching + Non-atomic assertions are not supported by the alternative matching function pcre2_dfa_match(). They are supported by JIT, but only if they do not contain any control verbs such as (*ACCEPT). (This may change in future). Note that assertions that appear as conditions for conditional @@ -8914,42 +8914,42 @@ NON-ATOMIC ASSERTIONS SCRIPT RUNS - In concept, a script run is a sequence of characters that are all from - the same Unicode script such as Latin or Greek. However, because some - scripts are commonly used together, and because some diacritical and - other marks are used with multiple scripts, it is not that simple. + In concept, a script run is a sequence of characters that are all from + the same Unicode script such as Latin or Greek. However, because some + scripts are commonly used together, and because some diacritical and + other marks are used with multiple scripts, it is not that simple. There is a full description of the rules that PCRE2 uses in the section entitled "Script Runs" in the pcre2unicode documentation. - If part of a pattern is enclosed between (*script_run: or (*sr: and a - closing parenthesis, it fails if the sequence of characters that it - matches are not a script run. After a failure, normal backtracking oc- - curs. Script runs can be used to detect spoofing attacks using charac- - ters that look the same, but are from different scripts. The string - "paypal.com" is an infamous example, where the letters could be a mix- + If part of a pattern is enclosed between (*script_run: or (*sr: and a + closing parenthesis, it fails if the sequence of characters that it + matches are not a script run. After a failure, normal backtracking oc- + curs. Script runs can be used to detect spoofing attacks using charac- + ters that look the same, but are from different scripts. The string + "paypal.com" is an infamous example, where the letters could be a mix- ture of Latin and Cyrillic. This pattern ensures that the matched char- acters in a sequence of non-spaces that follow white space are a script run: \s+(*sr:\S+) - To be sure that they are all from the Latin script (for example), a + To be sure that they are all from the Latin script (for example), a lookahead can be used: \s+(?=\p{Latin})(*sr:\S+) This works as long as the first character is expected to be a character - in that script, and not (for example) punctuation, which is allowed - with any script. If this is not the case, a more creative lookahead is - needed. For example, if digits, underscore, and dots are permitted at + in that script, and not (for example) punctuation, which is allowed + with any script. If this is not the case, a more creative lookahead is + needed. For example, if digits, underscore, and dots are permitted at the start: \s+(?=[0-9_.]*\p{Latin})(*sr:\S+) - In many cases, backtracking into a script run pattern fragment is not - desirable. The script run can employ an atomic group to prevent this. - Because this is a common requirement, a shorthand notation is provided + In many cases, backtracking into a script run pattern fragment is not + desirable. The script run can employ an atomic group to prevent this. + Because this is a common requirement, a shorthand notation is provided by (*atomic_script_run: or (*asr: (*asr:...) is the same as (*sr:(?>...)) @@ -8957,13 +8957,13 @@ SCRIPT RUNS Note that the atomic group is inside the script run. Putting it outside would not prevent backtracking into the script run pattern. - Support for script runs is not available if PCRE2 is compiled without + Support for script runs is not available if PCRE2 is compiled without Unicode support. A compile-time error is given if any of the above con- - structs is encountered. Script runs are not supported by the alternate - matching function, pcre2_dfa_match() because they use the same mecha- + structs is encountered. Script runs are not supported by the alternate + matching function, pcre2_dfa_match() because they use the same mecha- nism as capturing parentheses. - Warning: The (*ACCEPT) control verb (see below) should not be used + Warning: The (*ACCEPT) control verb (see below) should not be used within a script run group, because it causes an immediate exit from the group, bypassing the script run checking. @@ -8972,117 +8972,117 @@ CONDITIONAL GROUPS It is possible to cause the matching process to obey a pattern fragment conditionally or to choose between two alternative fragments, depending - on the result of an assertion, or whether a specific capture group has + on the result of an assertion, or whether a specific capture group has already been matched. The two possible forms of conditional group are: (?(condition)yes-pattern) (?(condition)yes-pattern|no-pattern) - If the condition is satisfied, the yes-pattern is used; otherwise the - no-pattern (if present) is used. An absent no-pattern is equivalent to - an empty string (it always matches). If there are more than two alter- - natives in the group, a compile-time error occurs. Each of the two al- + If the condition is satisfied, the yes-pattern is used; otherwise the + no-pattern (if present) is used. An absent no-pattern is equivalent to + an empty string (it always matches). If there are more than two alter- + natives in the group, a compile-time error occurs. Each of the two al- ternatives may itself contain nested groups of any form, including con- - ditional groups; the restriction to two alternatives applies only at - the level of the condition itself. This pattern fragment is an example + ditional groups; the restriction to two alternatives applies only at + the level of the condition itself. This pattern fragment is an example where the alternatives are complex: (?(1) (A|B|C) | (D | (?(2)E|F) | E) ) There are five kinds of condition: references to capture groups, refer- - ences to recursion, two pseudo-conditions called DEFINE and VERSION, + ences to recursion, two pseudo-conditions called DEFINE and VERSION, and assertions. Checking for a used capture group by number - If the text between the parentheses consists of a sequence of digits, - the condition is true if a capture group of that number has previously - matched. If there is more than one capture group with the same number - (see the earlier section about duplicate group numbers), the condition - is true if any of them have matched. An alternative notation, which is + If the text between the parentheses consists of a sequence of digits, + the condition is true if a capture group of that number has previously + matched. If there is more than one capture group with the same number + (see the earlier section about duplicate group numbers), the condition + is true if any of them have matched. An alternative notation, which is a PCRE2 extension, not supported by Perl, is to precede the digits with a plus or minus sign. In this case, the group number is relative rather - than absolute. The most recently opened capture group (which could be - enclosing this condition) can be referenced by (?(-1), the next most + than absolute. The most recently opened capture group (which could be + enclosing this condition) can be referenced by (?(-1), the next most recent by (?(-2), and so on. Inside loops it can also make sense to re- - fer to subsequent groups. The next capture group to be opened can be - referenced as (?(+1), and so on. The value zero in any of these forms + fer to subsequent groups. The next capture group to be opened can be + referenced as (?(+1), and so on. The value zero in any of these forms is not used; it provokes a compile-time error. - Consider the following pattern, which contains non-significant white - space to make it more readable (assume the PCRE2_EXTENDED option) and + Consider the following pattern, which contains non-significant white + space to make it more readable (assume the PCRE2_EXTENDED option) and to divide it into three parts for ease of discussion: ( \( )? [^()]+ (?(1) \) ) - The first part matches an optional opening parenthesis, and if that + The first part matches an optional opening parenthesis, and if that character is present, sets it as the first captured substring. The sec- - ond part matches one or more characters that are not parentheses. The - third part is a conditional group that tests whether or not the first - capture group matched. If it did, that is, if subject started with an - opening parenthesis, the condition is true, and so the yes-pattern is - executed and a closing parenthesis is required. Otherwise, since no- + ond part matches one or more characters that are not parentheses. The + third part is a conditional group that tests whether or not the first + capture group matched. If it did, that is, if subject started with an + opening parenthesis, the condition is true, and so the yes-pattern is + executed and a closing parenthesis is required. Otherwise, since no- pattern is not present, the conditional group matches nothing. In other - words, this pattern matches a sequence of non-parentheses, optionally + words, this pattern matches a sequence of non-parentheses, optionally enclosed in parentheses. - If you were embedding this pattern in a larger one, you could use a + If you were embedding this pattern in a larger one, you could use a relative reference: ...other stuff... ( \( )? [^()]+ (?(-1) \) ) ... - This makes the fragment independent of the parentheses in the larger + This makes the fragment independent of the parentheses in the larger pattern. Checking for a used capture group by name - Perl uses the syntax (?()...) or (?('name')...) to test for a - used capture group by name. For compatibility with earlier versions of - PCRE1, which had this facility before Perl, the syntax (?(name)...) is - also recognized. Note, however, that undelimited names consisting of - the letter R followed by digits are ambiguous (see the following sec- + Perl uses the syntax (?()...) or (?('name')...) to test for a + used capture group by name. For compatibility with earlier versions of + PCRE1, which had this facility before Perl, the syntax (?(name)...) is + also recognized. Note, however, that undelimited names consisting of + the letter R followed by digits are ambiguous (see the following sec- tion). Rewriting the above example to use a named group gives this: (? \( )? [^()]+ (?() \) ) - If the name used in a condition of this kind is a duplicate, the test - is applied to all groups of the same name, and is true if any one of + If the name used in a condition of this kind is a duplicate, the test + is applied to all groups of the same name, and is true if any one of them has matched. Checking for pattern recursion - "Recursion" in this sense refers to any subroutine-like call from one - part of the pattern to another, whether or not it is actually recur- - sive. See the sections entitled "Recursive patterns" and "Groups as + "Recursion" in this sense refers to any subroutine-like call from one + part of the pattern to another, whether or not it is actually recur- + sive. See the sections entitled "Recursive patterns" and "Groups as subroutines" below for details of recursion and subroutine calls. - If a condition is the string (R), and there is no capture group with - the name R, the condition is true if matching is currently in a recur- - sion or subroutine call to the whole pattern or any capture group. If - digits follow the letter R, and there is no group with that name, the - condition is true if the most recent call is into a group with the - given number, which must exist somewhere in the overall pattern. This + If a condition is the string (R), and there is no capture group with + the name R, the condition is true if matching is currently in a recur- + sion or subroutine call to the whole pattern or any capture group. If + digits follow the letter R, and there is no group with that name, the + condition is true if the most recent call is into a group with the + given number, which must exist somewhere in the overall pattern. This is a contrived example that is equivalent to a+b: ((?(R1)a+|(?1)b)) - However, in both cases, if there is a capture group with a matching - name, the condition tests for its being set, as described in the sec- - tion above, instead of testing for recursion. For example, creating a - group with the name R1 by adding (?) to the above pattern com- + However, in both cases, if there is a capture group with a matching + name, the condition tests for its being set, as described in the sec- + tion above, instead of testing for recursion. For example, creating a + group with the name R1 by adding (?) to the above pattern com- pletely changes its meaning. If a name preceded by ampersand follows the letter R, for example: (?(R&name)...) - the condition is true if the most recent recursion is into a group of + the condition is true if the most recent recursion is into a group of that name (which must exist within the pattern). This condition does not check the entire recursion stack. It tests only - the current level. If the name used in a condition of this kind is a - duplicate, the test is applied to all groups of the same name, and is + the current level. If the name used in a condition of this kind is a + duplicate, the test is applied to all groups of the same name, and is true if any one of them is the most recent recursion. At "top level", all these recursion test conditions are false. @@ -9090,111 +9090,111 @@ CONDITIONAL GROUPS Defining capture groups for use by reference only If the condition is the string (DEFINE), the condition is always false, - even if there is a group with the name DEFINE. In this case, there may + even if there is a group with the name DEFINE. In this case, there may be only one alternative in the rest of the conditional group. It is al- - ways skipped if control reaches this point in the pattern; the idea of - DEFINE is that it can be used to define subroutines that can be refer- - enced from elsewhere. (The use of subroutines is described below.) For - example, a pattern to match an IPv4 address such as "192.168.23.245" + ways skipped if control reaches this point in the pattern; the idea of + DEFINE is that it can be used to define subroutines that can be refer- + enced from elsewhere. (The use of subroutines is described below.) For + example, a pattern to match an IPv4 address such as "192.168.23.245" could be written like this (ignore white space and line breaks): (?(DEFINE) (? 2[0-4]\d | 25[0-5] | 1\d\d | [1-9]?\d) ) \b (?&byte) (\.(?&byte)){3} \b - The first part of the pattern is a DEFINE group inside which another - group named "byte" is defined. This matches an individual component of - an IPv4 address (a number less than 256). When matching takes place, - this part of the pattern is skipped because DEFINE acts like a false - condition. The rest of the pattern uses references to the named group - to match the four dot-separated components of an IPv4 address, insist- + The first part of the pattern is a DEFINE group inside which another + group named "byte" is defined. This matches an individual component of + an IPv4 address (a number less than 256). When matching takes place, + this part of the pattern is skipped because DEFINE acts like a false + condition. The rest of the pattern uses references to the named group + to match the four dot-separated components of an IPv4 address, insist- ing on a word boundary at each end. Checking the PCRE2 version - Programs that link with a PCRE2 library can check the version by call- - ing pcre2_config() with appropriate arguments. Users of applications - that do not have access to the underlying code cannot do this. A spe- - cial "condition" called VERSION exists to allow such users to discover + Programs that link with a PCRE2 library can check the version by call- + ing pcre2_config() with appropriate arguments. Users of applications + that do not have access to the underlying code cannot do this. A spe- + cial "condition" called VERSION exists to allow such users to discover which version of PCRE2 they are dealing with by using this condition to - match a string such as "yesno". VERSION must be followed either by "=" + match a string such as "yesno". VERSION must be followed either by "=" or ">=" and a version number. For example: (?(VERSION>=10.4)yes|no) - This pattern matches "yes" if the PCRE2 version is greater or equal to - 10.4, or "no" otherwise. The fractional part of the version number may + This pattern matches "yes" if the PCRE2 version is greater or equal to + 10.4, or "no" otherwise. The fractional part of the version number may not contain more than two digits. Assertion conditions - If the condition is not in any of the above formats, it must be a - parenthesized assertion. This may be a positive or negative lookahead - or lookbehind assertion. However, it must be a traditional atomic as- + If the condition is not in any of the above formats, it must be a + parenthesized assertion. This may be a positive or negative lookahead + or lookbehind assertion. However, it must be a traditional atomic as- sertion, not one of the non-atomic assertions. - Consider this pattern, again containing non-significant white space, + Consider this pattern, again containing non-significant white space, and with the two alternatives on the second line: (?(?=[^a-z]*[a-z]) \d{2}-[a-z]{3}-\d{2} | \d{2}-\d{2}-\d{2} ) - The condition is a positive lookahead assertion that matches an op- + The condition is a positive lookahead assertion that matches an op- tional sequence of non-letters followed by a letter. In other words, it tests for the presence of at least one letter in the subject. If a let- - ter is found, the subject is matched against the first alternative; - otherwise it is matched against the second. This pattern matches - strings in one of the two forms dd-aaa-dd or dd-dd-dd, where aaa are + ter is found, the subject is matched against the first alternative; + otherwise it is matched against the second. This pattern matches + strings in one of the two forms dd-aaa-dd or dd-dd-dd, where aaa are letters and dd are digits. When an assertion that is a condition contains capture groups, any cap- - turing that occurs in a matching branch is retained afterwards, for - both positive and negative assertions, because matching always contin- - ues after the assertion, whether it succeeds or fails. (Compare non- - conditional assertions, for which captures are retained only for posi- + turing that occurs in a matching branch is retained afterwards, for + both positive and negative assertions, because matching always contin- + ues after the assertion, whether it succeeds or fails. (Compare non- + conditional assertions, for which captures are retained only for posi- tive assertions that succeed.) COMMENTS There are two ways of including comments in patterns that are processed - by PCRE2. In both cases, the start of the comment must not be in a - character class, nor in the middle of any other sequence of related - characters such as (?: or a group name or number. The characters that + by PCRE2. In both cases, the start of the comment must not be in a + character class, nor in the middle of any other sequence of related + characters such as (?: or a group name or number. The characters that make up a comment play no part in the pattern matching. - The sequence (?# marks the start of a comment that continues up to the - next closing parenthesis. Nested parentheses are not permitted. If the - PCRE2_EXTENDED or PCRE2_EXTENDED_MORE option is set, an unescaped # - character also introduces a comment, which in this case continues to - immediately after the next newline character or character sequence in + The sequence (?# marks the start of a comment that continues up to the + next closing parenthesis. Nested parentheses are not permitted. If the + PCRE2_EXTENDED or PCRE2_EXTENDED_MORE option is set, an unescaped # + character also introduces a comment, which in this case continues to + immediately after the next newline character or character sequence in the pattern. Which characters are interpreted as newlines is controlled - by an option passed to the compiling function or by a special sequence + by an option passed to the compiling function or by a special sequence at the start of the pattern, as described in the section entitled "New- line conventions" above. Note that the end of this type of comment is a - literal newline sequence in the pattern; escape sequences that happen + literal newline sequence in the pattern; escape sequences that happen to represent a newline do not count. For example, consider this pattern - when PCRE2_EXTENDED is set, and the default newline convention (a sin- + when PCRE2_EXTENDED is set, and the default newline convention (a sin- gle linefeed character) is in force: abc #comment \n still comment - On encountering the # character, pcre2_compile() skips along, looking - for a newline in the pattern. The sequence \n is still literal at this - stage, so it does not terminate the comment. Only an actual character + On encountering the # character, pcre2_compile() skips along, looking + for a newline in the pattern. The sequence \n is still literal at this + stage, so it does not terminate the comment. Only an actual character with the code value 0x0a (the default newline) does so. RECURSIVE PATTERNS - Consider the problem of matching a string in parentheses, allowing for - unlimited nested parentheses. Without the use of recursion, the best - that can be done is to use a pattern that matches up to some fixed - depth of nesting. It is not possible to handle an arbitrary nesting + Consider the problem of matching a string in parentheses, allowing for + unlimited nested parentheses. Without the use of recursion, the best + that can be done is to use a pattern that matches up to some fixed + depth of nesting. It is not possible to handle an arbitrary nesting depth. For some time, Perl has provided a facility that allows regular expres- - sions to recurse (amongst other things). It does this by interpolating - Perl code in the expression at run time, and the code can refer to the + sions to recurse (amongst other things). It does this by interpolating + Perl code in the expression at run time, and the code can refer to the expression itself. A Perl pattern using code interpolation to solve the parentheses problem can be created like this: @@ -9203,67 +9203,67 @@ RECURSIVE PATTERNS The (?p{...}) item interpolates Perl code at run time, and in this case refers recursively to the pattern in which it appears. - Obviously, PCRE2 cannot support the interpolation of Perl code. In- - stead, it supports special syntax for recursion of the entire pattern, + Obviously, PCRE2 cannot support the interpolation of Perl code. In- + stead, it supports special syntax for recursion of the entire pattern, and also for individual capture group recursion. After its introduction in PCRE1 and Python, this kind of recursion was subsequently introduced into Perl at release 5.10. - A special item that consists of (? followed by a number greater than - zero and a closing parenthesis is a recursive subroutine call of the - capture group of the given number, provided that it occurs inside that - group. (If not, it is a non-recursive subroutine call, which is de- + A special item that consists of (? followed by a number greater than + zero and a closing parenthesis is a recursive subroutine call of the + capture group of the given number, provided that it occurs inside that + group. (If not, it is a non-recursive subroutine call, which is de- scribed in the next section.) The special item (?R) or (?0) is a recur- sive call of the entire regular expression. - This PCRE2 pattern solves the nested parentheses problem (assume the + This PCRE2 pattern solves the nested parentheses problem (assume the PCRE2_EXTENDED option is set so that white space is ignored): \( ( [^()]++ | (?R) )* \) - First it matches an opening parenthesis. Then it matches any number of - substrings which can either be a sequence of non-parentheses, or a re- + First it matches an opening parenthesis. Then it matches any number of + substrings which can either be a sequence of non-parentheses, or a re- cursive match of the pattern itself (that is, a correctly parenthesized - substring). Finally there is a closing parenthesis. Note the use of a - possessive quantifier to avoid backtracking into sequences of non- + substring). Finally there is a closing parenthesis. Note the use of a + possessive quantifier to avoid backtracking into sequences of non- parentheses. - If this were part of a larger pattern, you would not want to recurse + If this were part of a larger pattern, you would not want to recurse the entire pattern, so instead you could use this: ( \( ( [^()]++ | (?1) )* \) ) - We have put the pattern into parentheses, and caused the recursion to + We have put the pattern into parentheses, and caused the recursion to refer to them instead of the whole pattern. - In a larger pattern, keeping track of parenthesis numbers can be - tricky. This is made easier by the use of relative references. Instead + In a larger pattern, keeping track of parenthesis numbers can be + tricky. This is made easier by the use of relative references. Instead of (?1) in the pattern above you can write (?-2) to refer to the second - most recently opened parentheses preceding the recursion. In other - words, a negative number counts capturing parentheses leftwards from + most recently opened parentheses preceding the recursion. In other + words, a negative number counts capturing parentheses leftwards from the point at which it is encountered. - Be aware however, that if duplicate capture group numbers are in use, - relative references refer to the earliest group with the appropriate + Be aware however, that if duplicate capture group numbers are in use, + relative references refer to the earliest group with the appropriate number. Consider, for example: (?|(a)|(b)) (c) (?-2) The first two capture groups (a) and (b) are both numbered 1, and group - (c) is number 2. When the reference (?-2) is encountered, the second - most recently opened parentheses has the number 1, but it is the first + (c) is number 2. When the reference (?-2) is encountered, the second + most recently opened parentheses has the number 1, but it is the first such group (the (a) group) to which the recursion refers. This would be - the same if an absolute reference (?1) was used. In other words, rela- + the same if an absolute reference (?1) was used. In other words, rela- tive references are just a shorthand for computing a group number. - It is also possible to refer to subsequent capture groups, by writing - references such as (?+2). However, these cannot be recursive because - the reference is not inside the parentheses that are referenced. They - are always non-recursive subroutine calls, as described in the next + It is also possible to refer to subsequent capture groups, by writing + references such as (?+2). However, these cannot be recursive because + the reference is not inside the parentheses that are referenced. They + are always non-recursive subroutine calls, as described in the next section. - An alternative approach is to use named parentheses. The Perl syntax - for this is (?&name); PCRE1's earlier syntax (?P>name) is also sup- + An alternative approach is to use named parentheses. The Perl syntax + for this is (?&name); PCRE1's earlier syntax (?P>name) is also sup- ported. We could rewrite the above example as follows: (? \( ( [^()]++ | (?&pn) )* \) ) @@ -9272,57 +9272,57 @@ RECURSIVE PATTERNS used. The example pattern that we have been looking at contains nested unlim- - ited repeats, and so the use of a possessive quantifier for matching - strings of non-parentheses is important when applying the pattern to + ited repeats, and so the use of a possessive quantifier for matching + strings of non-parentheses is important when applying the pattern to strings that do not match. For example, when this pattern is applied to (aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa() - it yields "no match" quickly. However, if a possessive quantifier is - not used, the match runs for a very long time indeed because there are - so many different ways the + and * repeats can carve up the subject, + it yields "no match" quickly. However, if a possessive quantifier is + not used, the match runs for a very long time indeed because there are + so many different ways the + and * repeats can carve up the subject, and all have to be tested before failure can be reported. - At the end of a match, the values of capturing parentheses are those - from the outermost level. If you want to obtain intermediate values, a + At the end of a match, the values of capturing parentheses are those + from the outermost level. If you want to obtain intermediate values, a callout function can be used (see below and the pcre2callout documenta- tion). If the pattern above is matched against (ab(cd)ef) - the value for the inner capturing parentheses (numbered 2) is "ef", - which is the last value taken on at the top level. If a capture group - is not matched at the top level, its final captured value is unset, - even if it was (temporarily) set at a deeper level during the matching + the value for the inner capturing parentheses (numbered 2) is "ef", + which is the last value taken on at the top level. If a capture group + is not matched at the top level, its final captured value is unset, + even if it was (temporarily) set at a deeper level during the matching process. - Do not confuse the (?R) item with the condition (R), which tests for - recursion. Consider this pattern, which matches text in angle brack- - ets, allowing for arbitrary nesting. Only digits are allowed in nested - brackets (that is, when recursing), whereas any characters are permit- + Do not confuse the (?R) item with the condition (R), which tests for + recursion. Consider this pattern, which matches text in angle brack- + ets, allowing for arbitrary nesting. Only digits are allowed in nested + brackets (that is, when recursing), whereas any characters are permit- ted at the outer level. < (?: (?(R) \d++ | [^<>]*+) | (?R)) * > - In this pattern, (?(R) is the start of a conditional group, with two - different alternatives for the recursive and non-recursive cases. The + In this pattern, (?(R) is the start of a conditional group, with two + different alternatives for the recursive and non-recursive cases. The (?R) item is the actual recursive call. Differences in recursion processing between PCRE2 and Perl Some former differences between PCRE2 and Perl no longer exist. - Before release 10.30, recursion processing in PCRE2 differed from Perl - in that a recursive subroutine call was always treated as an atomic - group. That is, once it had matched some of the subject string, it was - never re-entered, even if it contained untried alternatives and there - was a subsequent matching failure. (Historical note: PCRE implemented + Before release 10.30, recursion processing in PCRE2 differed from Perl + in that a recursive subroutine call was always treated as an atomic + group. That is, once it had matched some of the subject string, it was + never re-entered, even if it contained untried alternatives and there + was a subsequent matching failure. (Historical note: PCRE implemented recursion before Perl did.) - Starting with release 10.30, recursive subroutine calls are no longer + Starting with release 10.30, recursive subroutine calls are no longer treated as atomic. That is, they can be re-entered to try unused alter- - natives if there is a matching failure later in the pattern. This is - now compatible with the way Perl works. If you want a subroutine call + natives if there is a matching failure later in the pattern. This is + now compatible with the way Perl works. If you want a subroutine call to be atomic, you must explicitly enclose it in an atomic group. Supporting backtracking into recursions simplifies certain types of re- @@ -9330,47 +9330,47 @@ RECURSIVE PATTERNS ^((.)(?1)\2|.?)$ - The second branch in the group matches a single central character in - the palindrome when there are an odd number of characters, or nothing - when there are an even number of characters, but in order to work it - has to be able to try the second case when the rest of the pattern + The second branch in the group matches a single central character in + the palindrome when there are an odd number of characters, or nothing + when there are an even number of characters, but in order to work it + has to be able to try the second case when the rest of the pattern match fails. If you want to match typical palindromic phrases, the pat- - tern has to ignore all non-word characters, which can be done like + tern has to ignore all non-word characters, which can be done like this: ^\W*+((.)\W*+(?1)\W*+\2|\W*+.?)\W*+$ - If run with the PCRE2_CASELESS option, this pattern matches phrases - such as "A man, a plan, a canal: Panama!". Note the use of the posses- - sive quantifier *+ to avoid backtracking into sequences of non-word + If run with the PCRE2_CASELESS option, this pattern matches phrases + such as "A man, a plan, a canal: Panama!". Note the use of the posses- + sive quantifier *+ to avoid backtracking into sequences of non-word characters. Without this, PCRE2 takes a great deal longer (ten times or - more) to match typical phrases, and Perl takes so long that you think + more) to match typical phrases, and Perl takes so long that you think it has gone into a loop. - Another way in which PCRE2 and Perl used to differ in their recursion - processing is in the handling of captured values. Formerly in Perl, - when a group was called recursively or as a subroutine (see the next + Another way in which PCRE2 and Perl used to differ in their recursion + processing is in the handling of captured values. Formerly in Perl, + when a group was called recursively or as a subroutine (see the next section), it had no access to any values that were captured outside the - recursion, whereas in PCRE2 these values can be referenced. Consider + recursion, whereas in PCRE2 these values can be referenced. Consider this pattern: ^(.)(\1|a(?2)) - This pattern matches "bab". The first capturing parentheses match "b", + This pattern matches "bab". The first capturing parentheses match "b", then in the second group, when the backreference \1 fails to match "b", the second alternative matches "a" and then recurses. In the recursion, - \1 does now match "b" and so the whole match succeeds. This match used + \1 does now match "b" and so the whole match succeeds. This match used to fail in Perl, but in later versions (I tried 5.024) it now works. GROUPS AS SUBROUTINES - If the syntax for a recursive group call (either by number or by name) - is used outside the parentheses to which it refers, it operates a bit - like a subroutine in a programming language. More accurately, PCRE2 + If the syntax for a recursive group call (either by number or by name) + is used outside the parentheses to which it refers, it operates a bit + like a subroutine in a programming language. More accurately, PCRE2 treats the referenced group as an independent subpattern which it tries - to match at the current matching position. The called group may be de- - fined before or after the reference. A numbered reference can be ab- + to match at the current matching position. The called group may be de- + fined before or after the reference. A numbered reference can be ab- solute or relative, as in these examples: (...(absolute)...)...(?2)... @@ -9381,106 +9381,106 @@ GROUPS AS SUBROUTINES (sens|respons)e and \1ibility - matches "sense and sensibility" and "response and responsibility", but + matches "sense and sensibility" and "response and responsibility", but not "sense and responsibility". If instead the pattern (sens|respons)e and (?1)ibility - is used, it does match "sense and responsibility" as well as the other - two strings. Another example is given in the discussion of DEFINE + is used, it does match "sense and responsibility" as well as the other + two strings. Another example is given in the discussion of DEFINE above. - Like recursions, subroutine calls used to be treated as atomic, but - this changed at PCRE2 release 10.30, so backtracking into subroutine - calls can now occur. However, any capturing parentheses that are set + Like recursions, subroutine calls used to be treated as atomic, but + this changed at PCRE2 release 10.30, so backtracking into subroutine + calls can now occur. However, any capturing parentheses that are set during the subroutine call revert to their previous values afterwards. - Processing options such as case-independence are fixed when a group is - defined, so if it is used as a subroutine, such options cannot be + Processing options such as case-independence are fixed when a group is + defined, so if it is used as a subroutine, such options cannot be changed for different calls. For example, consider this pattern: (abc)(?i:(?-1)) - It matches "abcabc". It does not match "abcABC" because the change of + It matches "abcabc". It does not match "abcABC" because the change of processing option does not affect the called group. - The behaviour of backtracking control verbs in groups when called as + The behaviour of backtracking control verbs in groups when called as subroutines is described in the section entitled "Backtracking verbs in subroutines" below. ONIGURUMA SUBROUTINE SYNTAX - For compatibility with Oniguruma, the non-Perl syntax \g followed by a + For compatibility with Oniguruma, the non-Perl syntax \g followed by a name or a number enclosed either in angle brackets or single quotes, is an alternative syntax for calling a group as a subroutine, possibly re- - cursively. Here are two of the examples used above, rewritten using + cursively. Here are two of the examples used above, rewritten using this syntax: (? \( ( (?>[^()]+) | \g )* \) ) (sens|respons)e and \g'1'ibility - PCRE2 supports an extension to Oniguruma: if a number is preceded by a + PCRE2 supports an extension to Oniguruma: if a number is preceded by a plus or a minus sign it is taken as a relative reference. For example: (abc)(?i:\g<-1>) - Note that \g{...} (Perl syntax) and \g<...> (Oniguruma syntax) are not - synonymous. The former is a backreference; the latter is a subroutine + Note that \g{...} (Perl syntax) and \g<...> (Oniguruma syntax) are not + synonymous. The former is a backreference; the latter is a subroutine call. CALLOUTS Perl has a feature whereby using the sequence (?{...}) causes arbitrary - Perl code to be obeyed in the middle of matching a regular expression. + Perl code to be obeyed in the middle of matching a regular expression. This makes it possible, amongst other things, to extract different sub- strings that match the same pair of parentheses when there is a repeti- tion. - PCRE2 provides a similar feature, but of course it cannot obey arbi- - trary Perl code. The feature is called "callout". The caller of PCRE2 - provides an external function by putting its entry point in a match - context using the function pcre2_set_callout(), and then passing that - context to pcre2_match() or pcre2_dfa_match(). If no match context is + PCRE2 provides a similar feature, but of course it cannot obey arbi- + trary Perl code. The feature is called "callout". The caller of PCRE2 + provides an external function by putting its entry point in a match + context using the function pcre2_set_callout(), and then passing that + context to pcre2_match() or pcre2_dfa_match(). If no match context is passed, or if the callout entry point is set to NULL, callouts are dis- abled. - Within a regular expression, (?C) indicates a point at which the - external function is to be called. There are two kinds of callout: - those with a numerical argument and those with a string argument. (?C) - on its own with no argument is treated as (?C0). A numerical argument - allows the application to distinguish between different callouts. - String arguments were added for release 10.20 to make it possible for - script languages that use PCRE2 to embed short scripts within patterns + Within a regular expression, (?C) indicates a point at which the + external function is to be called. There are two kinds of callout: + those with a numerical argument and those with a string argument. (?C) + on its own with no argument is treated as (?C0). A numerical argument + allows the application to distinguish between different callouts. + String arguments were added for release 10.20 to make it possible for + script languages that use PCRE2 to embed short scripts within patterns in a similar way to Perl. During matching, when PCRE2 reaches a callout point, the external func- - tion is called. It is provided with the number or string argument of - the callout, the position in the pattern, and one item of data that is + tion is called. It is provided with the number or string argument of + the callout, the position in the pattern, and one item of data that is also set in the match block. The callout function may cause matching to proceed, to backtrack, or to fail. - By default, PCRE2 implements a number of optimizations at matching - time, and one side-effect is that sometimes callouts are skipped. If - you need all possible callouts to happen, you need to set options that - disable the relevant optimizations. More details, including a complete - description of the programming interface to the callout function, are + By default, PCRE2 implements a number of optimizations at matching + time, and one side-effect is that sometimes callouts are skipped. If + you need all possible callouts to happen, you need to set options that + disable the relevant optimizations. More details, including a complete + description of the programming interface to the callout function, are given in the pcre2callout documentation. Callouts with numerical arguments - If you just want to have a means of identifying different callout - points, put a number less than 256 after the letter C. For example, + If you just want to have a means of identifying different callout + points, put a number less than 256 after the letter C. For example, this pattern has two callout points: (?C1)abc(?C2)def - If the PCRE2_AUTO_CALLOUT flag is passed to pcre2_compile(), numerical - callouts are automatically installed before each item in the pattern. - They are all numbered 255. If there is a conditional group in the pat- + If the PCRE2_AUTO_CALLOUT flag is passed to pcre2_compile(), numerical + callouts are automatically installed before each item in the pattern. + They are all numbered 255. If there is a conditional group in the pat- tern whose condition is an assertion, an additional callout is inserted - just before the condition. An explicit callout may also be set at this + just before the condition. An explicit callout may also be set at this position, as in this example: (?(?C9)(?=a)abc|def) @@ -9490,78 +9490,78 @@ CALLOUTS Callouts with string arguments - A delimited string may be used instead of a number as a callout argu- - ment. The starting delimiter must be one of ` ' " ^ % # $ { and the + A delimited string may be used instead of a number as a callout argu- + ment. The starting delimiter must be one of ` ' " ^ % # $ { and the ending delimiter is the same as the start, except for {, where the end- - ing delimiter is }. If the ending delimiter is needed within the + ing delimiter is }. If the ending delimiter is needed within the string, it must be doubled. For example: (?C'ab ''c'' d')xyz(?C{any text})pqr - The doubling is removed before the string is passed to the callout + The doubling is removed before the string is passed to the callout function. BACKTRACKING CONTROL - There are a number of special "Backtracking Control Verbs" (to use - Perl's terminology) that modify the behaviour of backtracking during - matching. They are generally of the form (*VERB) or (*VERB:NAME). Some + There are a number of special "Backtracking Control Verbs" (to use + Perl's terminology) that modify the behaviour of backtracking during + matching. They are generally of the form (*VERB) or (*VERB:NAME). Some verbs take either form, and may behave differently depending on whether - or not a name argument is present. The names are not required to be + or not a name argument is present. The names are not required to be unique within the pattern. - By default, for compatibility with Perl, a name is any sequence of + 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. This can be changed by setting the - PCRE2_ALT_VERBNAMES option, but the result is no longer Perl-compati- + processed in any way, and it is not possible to include a closing + parenthesis in the name. This can be changed by setting the + PCRE2_ALT_VERBNAMES option, but the result is no longer Perl-compati- ble. - When PCRE2_ALT_VERBNAMES is set, backslash processing is applied to - verb names and only an unescaped closing parenthesis terminates the - name. However, the only backslash items that are permitted are \Q, \E, - and sequences such as \x{100} that define character code points. Char- + When PCRE2_ALT_VERBNAMES is set, backslash processing is applied to + verb names and only an unescaped closing parenthesis terminates the + name. However, the only backslash items that are permitted are \Q, \E, + and sequences such as \x{100} that define character code points. Char- acter type escapes such as \d are faulted. A closing parenthesis can be included in a name either as \) or between - \Q and \E. In addition to backslash processing, if the PCRE2_EXTENDED + \Q and \E. In addition to backslash processing, if the PCRE2_EXTENDED or PCRE2_EXTENDED_MORE option is also set, unescaped whitespace in verb names is skipped, and #-comments are recognized, exactly as in the rest - of the pattern. PCRE2_EXTENDED and PCRE2_EXTENDED_MORE do not affect + of the pattern. PCRE2_EXTENDED and PCRE2_EXTENDED_MORE do not affect verb names unless PCRE2_ALT_VERBNAMES is also set. - 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 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 pat- tern. Except for (*ACCEPT), they may not be quantified. - Since these verbs are specifically related to backtracking, most of - them can be used only when the pattern is to be matched using the tra- + Since these verbs are specifically related to backtracking, most of + them can be used only when the pattern is to be matched using the tra- ditional matching function, because that uses a backtracking algorithm. - With the exception of (*FAIL), which behaves like a failing negative + With the exception of (*FAIL), which behaves like a failing negative assertion, the backtracking control verbs cause an error if encountered by the DFA matching function. - The behaviour of these verbs in repeated groups, assertions, and in - capture groups called as subroutines (whether or not recursively) is + The behaviour of these verbs in repeated groups, assertions, and in + capture groups called as subroutines (whether or not recursively) is documented below. Optimizations that affect backtracking verbs PCRE2 contains some optimizations that are used to speed up matching by running some checks at the start of each match attempt. For example, it - may know the minimum length of matching subject, or that a particular + may know the minimum length of matching subject, or that a particular character must be present. When one of these optimizations bypasses the - running of a match, any included backtracking verbs will not, of + running of a match, any included backtracking verbs will not, of course, be processed. You can suppress the start-of-match optimizations - by setting the PCRE2_NO_START_OPTIMIZE option when calling pcre2_com- - pile(), or by starting the pattern with (*NO_START_OPT). There is more + by setting the PCRE2_NO_START_OPTIMIZE option when calling pcre2_com- + pile(), or by starting the pattern with (*NO_START_OPT). There is more discussion of this option in the section entitled "Compiling a pattern" in the pcre2api documentation. - Experiments with Perl suggest that it too has similar optimizations, + Experiments with Perl suggest that it too has similar optimizations, and like PCRE2, turning them off can change the result of a match. Verbs that act immediately @@ -9570,77 +9570,77 @@ BACKTRACKING CONTROL (*ACCEPT) or (*ACCEPT:NAME) - This verb causes the match to end successfully, skipping the remainder - of the pattern. However, when it is inside a capture group that is + This verb causes the match to end successfully, skipping the remainder + of the pattern. However, when it is inside a capture group that is called as a subroutine, only that group is ended successfully. Matching then continues at the outer level. If (*ACCEPT) in triggered in a posi- - tive assertion, the assertion succeeds; in a negative assertion, the + tive assertion, the assertion succeeds; in a negative assertion, the assertion fails. - If (*ACCEPT) is inside capturing parentheses, the data so far is cap- + If (*ACCEPT) is inside capturing parentheses, the data so far is cap- tured. For example: A((?:A|B(*ACCEPT)|C)D) - This matches "AB", "AAD", or "ACD"; when it matches "AB", "B" is cap- + This matches "AB", "AAD", or "ACD"; when it matches "AB", "B" is cap- tured by the outer parentheses. - (*ACCEPT) is the only backtracking verb that is allowed to be quanti- - fied because an ungreedy quantification with a minimum of zero acts + (*ACCEPT) is the only backtracking verb that is allowed to be quanti- + fied because an ungreedy quantification with a minimum of zero acts only when a backtrack happens. Consider, for example, (A(*ACCEPT)??B)C - where A, B, and C may be complex expressions. After matching "A", the - matcher processes "BC"; if that fails, causing a backtrack, (*ACCEPT) - is triggered and the match succeeds. In both cases, all but C is cap- - tured. Whereas (*COMMIT) (see below) means "fail on backtrack", a re- + where A, B, and C may be complex expressions. After matching "A", the + matcher processes "BC"; if that fails, causing a backtrack, (*ACCEPT) + is triggered and the match succeeds. In both cases, all but C is cap- + tured. Whereas (*COMMIT) (see below) means "fail on backtrack", a re- peated (*ACCEPT) of this type means "succeed on backtrack". - Warning: (*ACCEPT) should not be used within a script run group, be- - cause it causes an immediate exit from the group, bypassing the script + Warning: (*ACCEPT) should not be used within a script run group, be- + cause it causes an immediate exit from the group, bypassing the script run checking. (*FAIL) or (*FAIL:NAME) - This verb causes a matching failure, forcing backtracking to occur. It - may be abbreviated to (*F). It is equivalent to (?!) but easier to + This verb causes a matching failure, forcing backtracking to occur. It + may be abbreviated to (*F). It is equivalent to (?!) but easier to read. The Perl documentation notes that it is probably useful only when combined with (?{}) or (??{}). Those are, of course, Perl features that - are not present in PCRE2. The nearest equivalent is the callout fea- + are not present in PCRE2. The nearest equivalent is the callout fea- ture, as for example in this pattern: a+(?C)(*FAIL) - A match with the string "aaaa" always fails, but the callout is taken + A match with the string "aaaa" always fails, but the callout is taken before each backtrack happens (in this example, 10 times). - (*ACCEPT:NAME) and (*FAIL:NAME) behave the same as (*MARK:NAME)(*AC- - CEPT) and (*MARK:NAME)(*FAIL), respectively, that is, a (*MARK) is + (*ACCEPT:NAME) and (*FAIL:NAME) behave the same as (*MARK:NAME)(*AC- + CEPT) and (*MARK:NAME)(*FAIL), respectively, that is, a (*MARK) is recorded just before the verb acts. Recording which path was taken - There is one verb whose main purpose is to track how a match was ar- - rived at, though it also has a secondary use in conjunction with ad- + There is one verb whose main purpose is to track how a match was ar- + rived at, though it also has a secondary use in conjunction with ad- vancing the match starting point (see (*SKIP) below). (*MARK:NAME) or (*:NAME) - A name is always required with this verb. For all the other backtrack- + A name is always required with this verb. For all the other backtrack- ing control verbs, a NAME argument is optional. - When a match succeeds, the name of the last-encountered mark name on + When a match succeeds, the name of the last-encountered mark name on the matching path is passed back to the caller as described in the sec- tion entitled "Other information about the match" in the pcre2api docu- - mentation. This applies to all instances of (*MARK) and other verbs, + mentation. This applies to all instances of (*MARK) and other verbs, including those inside assertions and atomic groups. However, there are - differences in those cases when (*MARK) is used in conjunction with + differences in those cases when (*MARK) is used in conjunction with (*SKIP) as described below. - The mark name that was last encountered on the matching path is passed - back. A verb without a NAME argument is ignored for this purpose. Here - is an example of pcre2test output, where the "mark" modifier requests + The mark name that was last encountered on the matching path is passed + back. A verb without a NAME argument is ignored for this purpose. Here + is an example of pcre2test output, where the "mark" modifier requests the retrieval and outputting of (*MARK) data: re> /X(*MARK:A)Y|X(*MARK:B)Z/mark @@ -9652,76 +9652,76 @@ BACKTRACKING CONTROL MK: B The (*MARK) name is tagged with "MK:" in this output, and in this exam- - ple it indicates which of the two alternatives matched. This is a more - efficient way of obtaining this information than putting each alterna- + ple it indicates which of the two alternatives matched. This is a more + efficient way of obtaining this information than putting each alterna- tive in its own capturing parentheses. - If a verb with a name is encountered in a positive assertion that is - true, the name is recorded and passed back if it is the last-encoun- + If a verb with a name is encountered in a positive assertion that is + true, the name is recorded and passed back if it is the last-encoun- tered. This does not happen for negative assertions or failing positive assertions. - After a partial match or a failed match, the last encountered name in + After a partial match or a failed match, the last encountered name in the entire match process is returned. For example: re> /X(*MARK:A)Y|X(*MARK:B)Z/mark data> XP No match, mark = B - Note that in this unanchored example the mark is retained from the + Note that in this unanchored example the mark is retained from the match attempt that started at the letter "X" in the subject. Subsequent match attempts starting at "P" and then with an empty string do not get as far as the (*MARK) item, but nevertheless do not reset it. - If you are interested in (*MARK) values after failed matches, you - should probably set the PCRE2_NO_START_OPTIMIZE option (see above) to + If you are interested in (*MARK) values after failed matches, you + should probably set the PCRE2_NO_START_OPTIMIZE option (see above) to ensure that the match is always attempted. Verbs that act after backtracking The following verbs do nothing when they are encountered. Matching con- - tinues with what follows, but if there is a subsequent match failure, - causing a backtrack to the verb, a failure is forced. That is, back- - tracking cannot pass to the left of the verb. However, when one of + tinues with what follows, but if there is a subsequent match failure, + causing a backtrack to the verb, a failure is forced. That is, back- + tracking cannot pass to the left of the verb. However, when one of these verbs appears inside an atomic group or in a lookaround assertion - that is true, its effect is confined to that group, because once the - group has been matched, there is never any backtracking into it. Back- + that is true, its effect is confined to that group, because once the + group has been matched, there is never any backtracking into it. Back- tracking from beyond an assertion or an atomic group ignores the entire group, and seeks a preceding backtracking point. - These verbs differ in exactly what kind of failure occurs when back- - tracking reaches them. The behaviour described below is what happens - when the verb is not in a subroutine or an assertion. Subsequent sec- + These verbs differ in exactly what kind of failure occurs when back- + tracking reaches them. The behaviour described below is what happens + when the verb is not in a subroutine or an assertion. Subsequent sec- tions cover these special cases. (*COMMIT) or (*COMMIT:NAME) - This verb causes the whole match to fail outright if there is a later + This verb causes the whole match to fail outright if there is a later matching failure that causes backtracking to reach it. Even if the pat- - tern is unanchored, no further attempts to find a match by advancing - the starting point take place. If (*COMMIT) is the only backtracking + tern is unanchored, no further attempts to find a match by advancing + the starting point take place. If (*COMMIT) is the only backtracking verb that is encountered, once it has been passed pcre2_match() is com- mitted to finding a match at the current starting point, or not at all. For example: a+(*COMMIT)b - This matches "xxaab" but not "aacaab". It can be thought of as a kind + This matches "xxaab" but not "aacaab". It can be thought of as a kind of dynamic anchor, or "I've started, so I must finish." - The behaviour of (*COMMIT:NAME) is not the same as (*MARK:NAME)(*COM- - MIT). It is like (*MARK:NAME) in that the name is remembered for pass- - ing back to the caller. However, (*SKIP:NAME) searches only for names + The behaviour of (*COMMIT:NAME) is not the same as (*MARK:NAME)(*COM- + MIT). It is like (*MARK:NAME) in that the name is remembered for pass- + ing back to the caller. However, (*SKIP:NAME) searches only for names that are set with (*MARK), ignoring those set by any of the other back- tracking verbs. - If there is more than one backtracking verb in a pattern, a different - one that follows (*COMMIT) may be triggered first, so merely passing + If there is more than one backtracking verb in a pattern, a different + one that follows (*COMMIT) may be triggered first, so merely passing (*COMMIT) during a match does not always guarantee that a match must be at this starting point. Note that (*COMMIT) at the start of a pattern is not the same as an an- - chor, unless PCRE2's start-of-match optimizations are turned off, as + chor, unless PCRE2's start-of-match optimizations are turned off, as shown in this output from pcre2test: re> /(*COMMIT)abc/ @@ -9732,68 +9732,68 @@ BACKTRACKING CONTROL data> xyzabc No match - For the first pattern, PCRE2 knows that any match must start with "a", - so the optimization skips along the subject to "a" before applying the - pattern to the first set of data. The match attempt then succeeds. The - second pattern disables the optimization that skips along to the first - character. The pattern is now applied starting at "x", and so the - (*COMMIT) causes the match to fail without trying any other starting + For the first pattern, PCRE2 knows that any match must start with "a", + so the optimization skips along the subject to "a" before applying the + pattern to the first set of data. The match attempt then succeeds. The + second pattern disables the optimization that skips along to the first + character. The pattern is now applied starting at "x", and so the + (*COMMIT) causes the match to fail without trying any other starting points. (*PRUNE) or (*PRUNE:NAME) - This verb causes the match to fail at the current starting position in + This verb causes the match to fail at the current starting position in the subject if there is a later matching failure that causes backtrack- - ing to reach it. If the pattern is unanchored, the normal "bumpalong" - advance to the next starting character then happens. Backtracking can - occur as usual to the left of (*PRUNE), before it is reached, or when - matching to the right of (*PRUNE), but if there is no match to the - right, backtracking cannot cross (*PRUNE). In simple cases, the use of - (*PRUNE) is just an alternative to an atomic group or possessive quan- + ing to reach it. If the pattern is unanchored, the normal "bumpalong" + advance to the next starting character then happens. Backtracking can + occur as usual to the left of (*PRUNE), before it is reached, or when + matching to the right of (*PRUNE), but if there is no match to the + right, backtracking cannot cross (*PRUNE). In simple cases, the use of + (*PRUNE) is just an alternative to an atomic group or possessive quan- tifier, but there are some uses of (*PRUNE) that cannot be expressed in - any other way. In an anchored pattern (*PRUNE) has the same effect as + any other way. In an anchored pattern (*PRUNE) has the same effect as (*COMMIT). The behaviour of (*PRUNE:NAME) is not the same as (*MARK:NAME)(*PRUNE). It is like (*MARK:NAME) in that the name is remembered for passing back - to the caller. However, (*SKIP:NAME) searches only for names set with + to the caller. However, (*SKIP:NAME) searches only for names set with (*MARK), ignoring those set by other backtracking verbs. (*SKIP) - This verb, when given without a name, is like (*PRUNE), except that if - the pattern is unanchored, the "bumpalong" advance is not to the next + This verb, when given without a name, is like (*PRUNE), except that if + the pattern is unanchored, the "bumpalong" advance is not to the next character, but to the position in the subject where (*SKIP) was encoun- - tered. (*SKIP) signifies that whatever text was matched leading up to - it cannot be part of a successful match if there is a later mismatch. + tered. (*SKIP) signifies that whatever text was matched leading up to + it cannot be part of a successful match if there is a later mismatch. Consider: a+(*SKIP)b - If the subject is "aaaac...", after the first match attempt fails - (starting at the first character in the string), the starting point + If the subject is "aaaac...", after the first match attempt fails + (starting at the first character in the string), the starting point skips on to start the next attempt at "c". Note that a possessive quan- tifier does not have the same effect as this example; although it would - suppress backtracking during the first match attempt, the second at- - tempt would start at the second character instead of skipping on to + suppress backtracking during the first match attempt, the second at- + tempt would start at the second character instead of skipping on to "c". - If (*SKIP) is used to specify a new starting position that is the same - as the starting position of the current match, or (by being inside a - lookbehind) earlier, the position specified by (*SKIP) is ignored, and + If (*SKIP) is used to specify a new starting position that is the same + as the starting position of the current match, or (by being inside a + lookbehind) earlier, the position specified by (*SKIP) is ignored, and instead the normal "bumpalong" occurs. (*SKIP:NAME) - When (*SKIP) has an associated name, its behaviour is modified. When - such a (*SKIP) is triggered, the previous path through the pattern is - searched for the most recent (*MARK) that has the same name. If one is - found, the "bumpalong" advance is to the subject position that corre- - sponds to that (*MARK) instead of to where (*SKIP) was encountered. If + When (*SKIP) has an associated name, its behaviour is modified. When + such a (*SKIP) is triggered, the previous path through the pattern is + searched for the most recent (*MARK) that has the same name. If one is + found, the "bumpalong" advance is to the subject position that corre- + sponds to that (*MARK) instead of to where (*SKIP) was encountered. If no (*MARK) with a matching name is found, the (*SKIP) is ignored. - The search for a (*MARK) name uses the normal backtracking mechanism, - which means that it does not see (*MARK) settings that are inside + The search for a (*MARK) name uses the normal backtracking mechanism, + which means that it does not see (*MARK) settings that are inside atomic groups or assertions, because they are never re-entered by back- tracking. Compare the following pcre2test examples: @@ -9807,105 +9807,105 @@ BACKTRACKING CONTROL 0: b 1: b - In the first example, the (*MARK) setting is in an atomic group, so it + In the first example, the (*MARK) setting is in an atomic group, so it is not seen when (*SKIP:X) triggers, causing the (*SKIP) to be ignored. - This allows the second branch of the pattern to be tried at the first - character position. In the second example, the (*MARK) setting is not - in an atomic group. This allows (*SKIP:X) to find the (*MARK) when it + This allows the second branch of the pattern to be tried at the first + character position. In the second example, the (*MARK) setting is not + in an atomic group. This allows (*SKIP:X) to find the (*MARK) when it backtracks, and this causes a new matching attempt to start at the sec- - ond character. This time, the (*MARK) is never seen because "a" does + ond character. This time, the (*MARK) is never seen because "a" does not match "b", so the matcher immediately jumps to the second branch of the pattern. - Note that (*SKIP:NAME) searches only for names set by (*MARK:NAME). It + Note that (*SKIP:NAME) searches only for names set by (*MARK:NAME). It ignores names that are set by other backtracking verbs. (*THEN) or (*THEN:NAME) - This verb causes a skip to the next innermost alternative when back- - tracking reaches it. That is, it cancels any further backtracking - within the current alternative. Its name comes from the observation + This verb causes a skip to the next innermost alternative when back- + tracking reaches it. That is, it cancels any further backtracking + within the current alternative. Its name comes from the observation that it can be used for a pattern-based if-then-else block: ( COND1 (*THEN) FOO | COND2 (*THEN) BAR | COND3 (*THEN) BAZ ) ... - If the COND1 pattern matches, FOO is tried (and possibly further items - after the end of the group if FOO succeeds); on failure, the matcher - skips to the second alternative and tries COND2, without backtracking - into COND1. If that succeeds and BAR fails, COND3 is tried. If subse- - quently BAZ fails, there are no more alternatives, so there is a back- - track to whatever came before the entire group. If (*THEN) is not in- + If the COND1 pattern matches, FOO is tried (and possibly further items + after the end of the group if FOO succeeds); on failure, the matcher + skips to the second alternative and tries COND2, without backtracking + into COND1. If that succeeds and BAR fails, COND3 is tried. If subse- + quently BAZ fails, there are no more alternatives, so there is a back- + track to whatever came before the entire group. If (*THEN) is not in- side an alternation, it acts like (*PRUNE). - The behaviour of (*THEN:NAME) is not the same as (*MARK:NAME)(*THEN). + The behaviour of (*THEN:NAME) is not the same as (*MARK:NAME)(*THEN). It is like (*MARK:NAME) in that the name is remembered for passing back - to the caller. However, (*SKIP:NAME) searches only for names set with + to the caller. However, (*SKIP:NAME) searches only for names set with (*MARK), ignoring those set by other backtracking verbs. - A group that does not contain a | character is just a part of the en- - closing alternative; it is not a nested alternation with only one al- + A group that does not contain a | character is just a part of the en- + closing alternative; it is not a nested alternation with only one al- ternative. The effect of (*THEN) extends beyond such a group to the en- - closing alternative. Consider this pattern, where A, B, etc. are com- - plex pattern fragments that do not contain any | characters at this + closing alternative. Consider this pattern, where A, B, etc. are com- + plex pattern fragments that do not contain any | characters at this level: A (B(*THEN)C) | D - If A and B are matched, but there is a failure in C, matching does not + If A and B are matched, but there is a failure in C, matching does not backtrack into A; instead it moves to the next alternative, that is, D. - However, if the group containing (*THEN) is given an alternative, it + However, if the group containing (*THEN) is given an alternative, it behaves differently: A (B(*THEN)C | (*FAIL)) | D The effect of (*THEN) is now confined to the inner group. After a fail- - ure in C, matching moves to (*FAIL), which causes the whole group to - fail because there are no more alternatives to try. In this case, + ure in C, matching moves to (*FAIL), which causes the whole group to + fail because there are no more alternatives to try. In this case, matching does backtrack into A. - Note that a conditional group is not considered as having two alterna- - tives, because only one is ever used. In other words, the | character - in a conditional group has a different meaning. Ignoring white space, + Note that a conditional group is not considered as having two alterna- + tives, because only one is ever used. In other words, the | character + in a conditional group has a different meaning. Ignoring white space, consider: ^.*? (?(?=a) a | b(*THEN)c ) If the subject is "ba", this pattern does not match. Because .*? is un- - greedy, it initially matches zero characters. The condition (?=a) then - fails, the character "b" is matched, but "c" is not. At this point, - matching does not backtrack to .*? as might perhaps be expected from - the presence of the | character. The conditional group is part of the - single alternative that comprises the whole pattern, and so the match - fails. (If there was a backtrack into .*?, allowing it to match "b", + greedy, it initially matches zero characters. The condition (?=a) then + fails, the character "b" is matched, but "c" is not. At this point, + matching does not backtrack to .*? as might perhaps be expected from + the presence of the | character. The conditional group is part of the + single alternative that comprises the whole pattern, and so the match + fails. (If there was a backtrack into .*?, allowing it to match "b", the match would succeed.) - The verbs just described provide four different "strengths" of control + The verbs just described provide four different "strengths" of control when subsequent matching fails. (*THEN) is the weakest, carrying on the - match at the next alternative. (*PRUNE) comes next, failing the match - at the current starting position, but allowing an advance to the next - character (for an unanchored pattern). (*SKIP) is similar, except that + match at the next alternative. (*PRUNE) comes next, failing the match + at the current starting position, but allowing an advance to the next + character (for an unanchored pattern). (*SKIP) is similar, except that the advance may be more than one character. (*COMMIT) is the strongest, causing the entire match to fail. More than one backtracking verb - If more than one backtracking verb is present in a pattern, the one - that is backtracked onto first acts. For example, consider this pat- + If more than one backtracking verb is present in a pattern, the one + that is backtracked onto first acts. For example, consider this pat- tern, where A, B, etc. are complex pattern fragments: (A(*COMMIT)B(*THEN)C|ABD) - If A matches but B fails, the backtrack to (*COMMIT) causes the entire + If A matches but B fails, the backtrack to (*COMMIT) causes the entire match to fail. However, if A and B match, but C fails, the backtrack to - (*THEN) causes the next alternative (ABD) to be tried. This behaviour - is consistent, but is not always the same as Perl's. It means that if - two or more backtracking verbs appear in succession, all but the last + (*THEN) causes the next alternative (ABD) to be tried. This behaviour + is consistent, but is not always the same as Perl's. It means that if + two or more backtracking verbs appear in succession, all but the last of them has no effect. Consider this example: ...(*COMMIT)(*PRUNE)... If there is a matching failure to the right, backtracking onto (*PRUNE) - causes it to be triggered, and its action is taken. There can never be + causes it to be triggered, and its action is taken. There can never be a backtrack onto (*COMMIT). Backtracking verbs in repeated groups @@ -9915,50 +9915,50 @@ BACKTRACKING CONTROL /(a(*COMMIT)b)+ac/ - If the subject is "abac", Perl matches unless its optimizations are - disabled, but PCRE2 always fails because the (*COMMIT) in the second + If the subject is "abac", Perl matches unless its optimizations are + disabled, but PCRE2 always fails because the (*COMMIT) in the second repeat of the group acts. Backtracking verbs in assertions - (*FAIL) in any assertion has its normal effect: it forces an immediate - backtrack. The behaviour of the other backtracking verbs depends on - whether or not the assertion is standalone or acting as the condition + (*FAIL) in any assertion has its normal effect: it forces an immediate + backtrack. The behaviour of the other backtracking verbs depends on + whether or not the assertion is standalone or acting as the condition in a conditional group. - (*ACCEPT) in a standalone positive assertion causes the assertion to - succeed without any further processing; captured strings and a mark - name (if set) are retained. In a standalone negative assertion, (*AC- + (*ACCEPT) in a standalone positive assertion causes the assertion to + succeed without any further processing; captured strings and a mark + name (if set) are retained. In a standalone negative assertion, (*AC- CEPT) causes the assertion to fail without any further processing; cap- tured substrings and any mark name are discarded. - If the assertion is a condition, (*ACCEPT) causes the condition to be - true for a positive assertion and false for a negative one; captured + If the assertion is a condition, (*ACCEPT) causes the condition to be + true for a positive assertion and false for a negative one; captured substrings are retained in both cases. The remaining verbs act only when a later failure causes a backtrack to - reach them. This means that, for the Perl-compatible assertions, their + reach them. This means that, for the Perl-compatible assertions, their effect is confined to the assertion, because Perl lookaround assertions are atomic. A backtrack that occurs after such an assertion is complete - does not jump back into the assertion. Note in particular that a - (*MARK) name that is set in an assertion is not "seen" by an instance + does not jump back into the assertion. Note in particular that a + (*MARK) name that is set in an assertion is not "seen" by an instance of (*SKIP:NAME) later in the pattern. - PCRE2 now supports non-atomic positive assertions, as described in the - section entitled "Non-atomic assertions" above. These assertions must - be standalone (not used as conditions). They are not Perl-compatible. - For these assertions, a later backtrack does jump back into the asser- - tion, and therefore verbs such as (*COMMIT) can be triggered by back- + PCRE2 now supports non-atomic positive assertions, as described in the + section entitled "Non-atomic assertions" above. These assertions must + be standalone (not used as conditions). They are not Perl-compatible. + For these assertions, a later backtrack does jump back into the asser- + tion, and therefore verbs such as (*COMMIT) can be triggered by back- tracks from later in the pattern. - The effect of (*THEN) is not allowed to escape beyond an assertion. If - there are no more branches to try, (*THEN) causes a positive assertion + The effect of (*THEN) is not allowed to escape beyond an assertion. If + there are no more branches to try, (*THEN) causes a positive assertion to be false, and a negative assertion to be true. - The other backtracking verbs are not treated specially if they appear - in a standalone positive assertion. In a conditional positive asser- + The other backtracking verbs are not treated specially if they appear + in a standalone positive assertion. In a conditional positive asser- tion, backtracking (from within the assertion) into (*COMMIT), (*SKIP), - or (*PRUNE) causes the condition to be false. However, for both stand- + or (*PRUNE) causes the condition to be false. However, for both stand- alone and conditional negative assertions, backtracking into (*COMMIT), (*SKIP), or (*PRUNE) causes the assertion to be true, without consider- ing any further alternative branches. @@ -9968,26 +9968,26 @@ BACKTRACKING CONTROL These behaviours occur whether or not the group is called recursively. (*ACCEPT) in a group called as a subroutine causes the subroutine match - to succeed without any further processing. Matching then continues af- - ter the subroutine call. Perl documents this behaviour. Perl's treat- + to succeed without any further processing. Matching then continues af- + ter the subroutine call. Perl documents this behaviour. Perl's treat- ment of the other verbs in subroutines is different in some cases. - (*FAIL) in a group called as a subroutine has its normal effect: it + (*FAIL) in a group called as a subroutine has its normal effect: it forces an immediate backtrack. - (*COMMIT), (*SKIP), and (*PRUNE) cause the subroutine match to fail - when triggered by being backtracked to in a group called as a subrou- + (*COMMIT), (*SKIP), and (*PRUNE) cause the subroutine match to fail + when triggered by being backtracked to in a group called as a subrou- tine. There is then a backtrack at the outer level. (*THEN), when triggered, skips to the next alternative in the innermost - enclosing group that has alternatives (its normal behaviour). However, + enclosing group that has alternatives (its normal behaviour). However, if there is no such group within the subroutine's group, the subroutine match fails and there is a backtrack at the outer level. SEE ALSO - pcre2api(3), pcre2callout(3), pcre2matching(3), pcre2syntax(3), + pcre2api(3), pcre2callout(3), pcre2matching(3), pcre2syntax(3), pcre2(3). @@ -10000,11 +10000,11 @@ AUTHOR REVISION - Last updated: 19 January 2024 + Last updated: 11 March 2024 Copyright (c) 1997-2024 University of Cambridge. -PCRE2 10.43 19 January 2024 PCRE2PATTERN(3) +PCRE2 10.44 11 March 2024 PCRE2PATTERN(3) ------------------------------------------------------------------------------ diff --git a/doc/pcre2demo.3 b/doc/pcre2demo.3 index e17f18667..c3c988ae7 100644 --- a/doc/pcre2demo.3 +++ b/doc/pcre2demo.3 @@ -1,4 +1,4 @@ -.TH PCRE2DEMO 3 "21 February 2024" "PCRE2 10.43" +.TH PCRE2DEMO 3 "11 March 2024" "PCRE2 10.43" .\"AUTOMATICALLY GENERATED BY PrepareRelease - do not EDIT! .SH NAME PCRE2DEMO - A demonstration C program for PCRE2 diff --git a/doc/pcre2pattern.3 b/doc/pcre2pattern.3 index af107b46a..ad1813a55 100644 --- a/doc/pcre2pattern.3 +++ b/doc/pcre2pattern.3 @@ -1,4 +1,4 @@ -.TH PCRE2PATTERN 3 "19 January 2024" "PCRE2 10.43" +.TH PCRE2PATTERN 3 "11 March 2024" "PCRE2 10.44" .SH NAME PCRE2 - Perl-compatible regular expressions (revised API) .SH "PCRE2 REGULAR EXPRESSION DETAILS" @@ -1844,7 +1844,7 @@ the naming of capture groups. This feature was not added to Perl until release using the Python syntax. PCRE2 supports both the Perl and the Python syntax. .P In PCRE2, a capture group can be named in one of three ways: (?...) or -(?'name'...) as in Perl, or (?P...) as in Python. Names may be up to 32 +(?'name'...) as in Perl, or (?P...) as in Python. Names may be up to 128 code units long. When PCRE2_UTF is not set, they may contain only ASCII alphanumeric characters and underscores, but must start with a non-digit. When PCRE2_UTF is set, the syntax of group names is extended to allow any Unicode @@ -3889,6 +3889,6 @@ Cambridge, England. .rs .sp .nf -Last updated: 19 January 2024 +Last updated: 11 March 2024 Copyright (c) 1997-2024 University of Cambridge. .fi diff --git a/testdata/testinput10 b/testdata/testinput10 index e901d51d8..3190ebcd8 100644 --- a/testdata/testinput10 +++ b/testdata/testinput10 @@ -487,11 +487,11 @@ # Check name length with non-ASCII characters -/(?'ABáC678901234567890123456789012'...)/utf +/(?'ABáC678901234567890123456789012012345678901234567890123456789AB012345678901234567890123456789AB012345678901234567890123456789AB'...)/utf -/(?'ABáC6789012345678901234567890123'...)/utf +/(?'ABáC6789012345678901234567890123012345678901234567890123456789AB012345678901234567890123456789AB012345678901234567890123456789AB'...)/utf -/(?'ABZC6789012345678901234567890123'...)/utf +/(?'ABZC6789012345678901234567890123012345678901234567890123456789AB012345678901234567890123456789AB012345678901234567890123456789AB'...)/utf /(?(n/utf diff --git a/testdata/testinput2 b/testdata/testinput2 index 9b4c0684a..d63b74c43 100644 --- a/testdata/testinput2 +++ b/testdata/testinput2 @@ -4680,9 +4680,9 @@ B)x/alt_verbnames,mark /(?<=\K.)/g,replace=-,allow_lookaround_bsk ab -/(?'abcdefghijklmnopqrstuvwxyzABCDEFG'toolong)/ +/(?'abcdefghijklmnopqrstuvwxyzABCDEFGabcdefghijklmnopqrstuvwxyzABCDEabcdefghijklmnopqrstuvwxyzABCDEabcdefghijklmnopqrstuvwxyzABCDEFGH'toolong)/ -/(?'abcdefghijklmnopqrstuvwxyzABCDEF'justright)/ +/(?'abcdefghijklmnopqrstuvwxyzABCDEFGabcdefghijklmnopqrstuvwxyzABCDEabcdefghijklmnopqrstuvwxyzABCDEabcdefghijklmnopqrstuvwxyzABCDEFG'justright)/ # These two use zero-termination /abcd/max_pattern_length=3 @@ -4949,7 +4949,7 @@ a)"xI /{„Í„ÍÍ„Í{'{22{2{{2{'{22{{22{2{'{22{2{{2{{222{{2{'{22{2{22{2{'{22{2{{2{'{22{2{22{2{'{'{22{2{22{2{'{22{2{{2{'{22{2{22{2{'{222{2Ä„Í„ÍÍ„Í{'{22{2{{2{'{22{{11{2{'{22{2{{2{{'{22{2{{2{'{22{{22{1{'{22{2{{2{{222{{2{'{22{2{22{2{'{/auto_callout // -\=get=i00000000000000000000000000000000 +\=get=i00000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000 \=get=i2345678901234567890123456789012,get=i1245678901234567890123456789012 "(?(?C))" diff --git a/testdata/testoutput10 b/testdata/testoutput10 index 8145891fd..1cf758455 100644 --- a/testdata/testoutput10 +++ b/testdata/testoutput10 @@ -1615,12 +1615,12 @@ No match # Check name length with non-ASCII characters -/(?'ABáC678901234567890123456789012'...)/utf +/(?'ABáC678901234567890123456789012012345678901234567890123456789AB012345678901234567890123456789AB012345678901234567890123456789AB'...)/utf -/(?'ABáC6789012345678901234567890123'...)/utf -Failed: error 148 at offset 36: subpattern name is too long (maximum 32 code units) +/(?'ABáC6789012345678901234567890123012345678901234567890123456789AB012345678901234567890123456789AB012345678901234567890123456789AB'...)/utf +Failed: error 148 at offset 132: subpattern name is too long (maximum 128 code units) -/(?'ABZC6789012345678901234567890123'...)/utf +/(?'ABZC6789012345678901234567890123012345678901234567890123456789AB012345678901234567890123456789AB012345678901234567890123456789AB'...)/utf /(?(n/utf Failed: error 142 at offset 4: syntax error in subpattern name (missing terminator?) diff --git a/testdata/testoutput2 b/testdata/testoutput2 index 30c5a83ef..0c7948251 100644 --- a/testdata/testoutput2 +++ b/testdata/testoutput2 @@ -14935,10 +14935,10 @@ Failed: error -60: match with end before start or start moved backwards is not s ab Failed: error -60: match with end before start or start moved backwards is not supported -/(?'abcdefghijklmnopqrstuvwxyzABCDEFG'toolong)/ -Failed: error 148 at offset 36: subpattern name is too long (maximum 32 code units) +/(?'abcdefghijklmnopqrstuvwxyzABCDEFGabcdefghijklmnopqrstuvwxyzABCDEabcdefghijklmnopqrstuvwxyzABCDEabcdefghijklmnopqrstuvwxyzABCDEFGH'toolong)/ +Failed: error 148 at offset 132: subpattern name is too long (maximum 128 code units) -/(?'abcdefghijklmnopqrstuvwxyzABCDEF'justright)/ +/(?'abcdefghijklmnopqrstuvwxyzABCDEFGabcdefghijklmnopqrstuvwxyzABCDEabcdefghijklmnopqrstuvwxyzABCDEabcdefghijklmnopqrstuvwxyzABCDEFG'justright)/ # These two use zero-termination /abcd/max_pattern_length=3 @@ -15549,7 +15549,7 @@ Failed: error 157 at offset 6: \g is not followed by a braced, angle-bracketed, /{„Í„ÍÍ„Í{'{22{2{{2{'{22{{22{2{'{22{2{{2{{222{{2{'{22{2{22{2{'{22{2{{2{'{22{2{22{2{'{'{22{2{22{2{'{22{2{{2{'{22{2{22{2{'{222{2Ä„Í„ÍÍ„Í{'{22{2{{2{'{22{{11{2{'{22{2{{2{{'{22{2{{2{'{22{{22{1{'{22{2{{2{{222{{2{'{22{2{22{2{'{/auto_callout // -\=get=i00000000000000000000000000000000 +\=get=i00000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000 ** Group name in 'get' is too long \=get=i2345678901234567890123456789012,get=i1245678901234567890123456789012 ** Too many characters in named 'get' modifiers