diff --git a/doc/html/boost_regex/background_information/examples.html b/doc/html/boost_regex/background_information/examples.html index 2de70f4d..24db4e92 100644 --- a/doc/html/boost_regex/background_information/examples.html +++ b/doc/html/boost_regex/background_information/examples.html @@ -28,7 +28,7 @@ Example Programs
- + Test Programs
@@ -107,7 +107,7 @@ Files: captures_test.cpp.

- + Example programs
@@ -133,7 +133,7 @@ Files: regex_timer.cpp.

- + Code snippets
diff --git a/doc/html/boost_regex/background_information/history.html b/doc/html/boost_regex/background_information/history.html index 3f48c3c3..ed503d51 100644 --- a/doc/html/boost_regex/background_information/history.html +++ b/doc/html/boost_regex/background_information/history.html @@ -26,7 +26,7 @@ History
- + Boost 1.38
@@ -53,7 +53,7 @@
- + Boost 1.34
@@ -76,7 +76,7 @@
- + Boost 1.33.1
@@ -146,7 +146,7 @@
- + Boost 1.33.0
@@ -201,7 +201,7 @@
- + Boost 1.32.1
@@ -209,7 +209,7 @@ Fixed bug in partial matches of bounded repeats of '.'.
- + Boost 1.31.0
diff --git a/doc/html/boost_regex/background_information/locale.html b/doc/html/boost_regex/background_information/locale.html index 4c0fc1c7..5c9a1bdd 100644 --- a/doc/html/boost_regex/background_information/locale.html +++ b/doc/html/boost_regex/background_information/locale.html @@ -58,7 +58,7 @@ There are three separate localization mechanisms supported by Boost.Regex:

- + Win32 localization model.
@@ -90,7 +90,7 @@ are treated as "unknown" graphic characters.

- + C localization model.
@@ -114,7 +114,7 @@ libraries including version 1 of this library.

- + C++ localization model.
@@ -151,7 +151,7 @@ in your code. The best way to ensure this is to add the #define to <boost/regex/user.hpp>.

- + Providing a message catalogue
diff --git a/doc/html/boost_regex/background_information/standards.html b/doc/html/boost_regex/background_information/standards.html index 2301ab6f..95cb80a2 100644 --- a/doc/html/boost_regex/background_information/standards.html +++ b/doc/html/boost_regex/background_information/standards.html @@ -28,7 +28,7 @@ Conformance
- + C++

@@ -36,7 +36,7 @@ Report on C++ Library Extensions.

- + ECMAScript / JavaScript
@@ -49,7 +49,7 @@ rather than a Unicode escape sequence; use \x{DDDD} for Unicode escape sequences.

- + Perl

@@ -62,7 +62,7 @@ (??{code}) Not implementable in a compiled strongly typed language.

- + POSIX

@@ -82,7 +82,7 @@ a custom traits class.

- + Unicode

diff --git a/doc/html/boost_regex/captures.html b/doc/html/boost_regex/captures.html index e1649644..613c1b0a 100644 --- a/doc/html/boost_regex/captures.html +++ b/doc/html/boost_regex/captures.html @@ -35,7 +35,7 @@ accessed.

- + Marked sub-expressions

@@ -218,7 +218,7 @@ output stream.

- + Unmatched Sub-Expressions

@@ -231,7 +231,7 @@ you can determine which sub-expressions matched by accessing the sub_match::matched data member.

- + Repeated Captures

diff --git a/doc/html/boost_regex/format/boost_format_syntax.html b/doc/html/boost_regex/format/boost_format_syntax.html index 4a9b80eb..a98f3691 100644 --- a/doc/html/boost_regex/format/boost_format_syntax.html +++ b/doc/html/boost_regex/format/boost_format_syntax.html @@ -32,7 +32,7 @@ '$', '\', '(', ')', '?', and ':'.

- + Grouping

@@ -40,7 +40,7 @@ you want a to output literal parenthesis.

- + Conditionals

@@ -79,7 +79,7 @@ ?{NAME}true-expression:false-expression

- + Placeholder Sequences
@@ -319,7 +319,7 @@ as a literal.

- + Escape Sequences
diff --git a/doc/html/boost_regex/install.html b/doc/html/boost_regex/install.html index 609ba749..dbb05cd2 100644 --- a/doc/html/boost_regex/install.html +++ b/doc/html/boost_regex/install.html @@ -49,7 +49,7 @@ file before you can use it, instructions for specific platforms are as follows:

- + Building with bjam

@@ -58,7 +58,7 @@ started guide for more information.

- + Building With Unicode and ICU Support
@@ -96,11 +96,11 @@ ICU you are using is binary compatible with the toolset you use to build Boost.

- + Building via makefiles
- + Borland C++ Builder:
- + GCC(2.95 and later)

@@ -302,7 +302,7 @@ see the config library documentation.

- + Sun Workshop 6.1

@@ -347,7 +347,7 @@ will build v9 variants of the regex library named libboost_regex_v9.a etc.

- + Makefiles for Other compilers
diff --git a/doc/html/boost_regex/ref/bad_expression.html b/doc/html/boost_regex/ref/bad_expression.html index 3189d62c..a5fe7ddf 100644 --- a/doc/html/boost_regex/ref/bad_expression.html +++ b/doc/html/boost_regex/ref/bad_expression.html @@ -27,7 +27,7 @@ bad_expression
- + Synopsis
#include <boost/pattern_except.hpp>
@@ -54,7 +54,7 @@
 } // namespace boost
 
- + Description
regex_error(const std::string& s, regex_constants::error_type err, std::ptrdiff_t pos);
diff --git a/doc/html/boost_regex/ref/basic_regex.html b/doc/html/boost_regex/ref/basic_regex.html
index c009b8d5..dabf17a1 100644
--- a/doc/html/boost_regex/ref/basic_regex.html
+++ b/doc/html/boost_regex/ref/basic_regex.html
@@ -27,7 +27,7 @@
  basic_regex
 
 
- + Synopsis
#include <boost/regex.hpp>
@@ -244,7 +244,7 @@
 } // namespace boost
 
- + Description

@@ -327,7 +327,7 @@ basic_regex.

-

Table 1. basic_regex default construction postconditions

+

Table 1. basic_regex default construction postconditions

@@ -407,7 +407,7 @@ flags specified in f.

-

Table 2. Postconditions for basic_regex construction

+

Table 2. Postconditions for basic_regex construction

@@ -512,7 +512,7 @@ specified in f.

-

Table 3. Postconditions for basic_regex construction

+

Table 3. Postconditions for basic_regex construction

@@ -616,7 +616,7 @@ according the option flags specified in f.

-

Table 4. Postconditions for basic_regex construction

+

Table 4. Postconditions for basic_regex construction

@@ -727,7 +727,7 @@ flags specified in f.

-

Table 5. Postconditions for basic_regex construction

+

Table 5. Postconditions for basic_regex construction

@@ -829,7 +829,7 @@ flags specified in f.

-

Table 6. Postconditions for basic_regex construction

+

Table 6. Postconditions for basic_regex construction

@@ -1043,7 +1043,7 @@ in f.

-

Table 7. Postconditions for basic_regex::assign

+

Table 7. Postconditions for basic_regex::assign

diff --git a/doc/html/boost_regex/ref/concepts/traits_concept.html b/doc/html/boost_regex/ref/concepts/traits_concept.html index 6d159362..c517de45 100644 --- a/doc/html/boost_regex/ref/concepts/traits_concept.html +++ b/doc/html/boost_regex/ref/concepts/traits_concept.html @@ -34,7 +34,7 @@ Boost-specific enhanced interface.

- + Minimal requirements.
@@ -381,7 +381,7 @@
- + Additional Optional Requirements
diff --git a/doc/html/boost_regex/ref/deprecated_interfaces/regex_format.html b/doc/html/boost_regex/ref/deprecated_interfaces/regex_format.html index 07a47ad4..7c3b91e6 100644 --- a/doc/html/boost_regex/ref/deprecated_interfaces/regex_format.html +++ b/doc/html/boost_regex/ref/deprecated_interfaces/regex_format.html @@ -34,7 +34,7 @@ previous version of Boost.Regex and will not be further updated:

- + Algorithm regex_format
diff --git a/doc/html/boost_regex/ref/error_type.html b/doc/html/boost_regex/ref/error_type.html index 7923d13c..260f3c72 100644 --- a/doc/html/boost_regex/ref/error_type.html +++ b/doc/html/boost_regex/ref/error_type.html @@ -27,7 +27,7 @@ error_type
- + Synopsis

@@ -57,7 +57,7 @@ } // namespace boost

- + Description

diff --git a/doc/html/boost_regex/ref/match_flag_type.html b/doc/html/boost_regex/ref/match_flag_type.html index 4be97bd4..a7152b4d 100644 --- a/doc/html/boost_regex/ref/match_flag_type.html +++ b/doc/html/boost_regex/ref/match_flag_type.html @@ -69,7 +69,7 @@ } // namespace boost

- + Description

diff --git a/doc/html/boost_regex/ref/match_results.html b/doc/html/boost_regex/ref/match_results.html index ac2057f0..8d065dae 100644 --- a/doc/html/boost_regex/ref/match_results.html +++ b/doc/html/boost_regex/ref/match_results.html @@ -27,7 +27,7 @@ match_results

- + Synopsis
#include <boost/regex.hpp>
@@ -166,7 +166,7 @@
          match_results<BidirectionalIterator, Allocator>& m2);
 
- + Description

diff --git a/doc/html/boost_regex/ref/non_std_strings/icu/unicode_algo.html b/doc/html/boost_regex/ref/non_std_strings/icu/unicode_algo.html index 79bbe08d..0a7705fc 100644 --- a/doc/html/boost_regex/ref/non_std_strings/icu/unicode_algo.html +++ b/doc/html/boost_regex/ref/non_std_strings/icu/unicode_algo.html @@ -43,7 +43,7 @@ on to the "real" algorithm.

- + u32regex_match

@@ -89,7 +89,7 @@ }

- + u32regex_search

@@ -128,7 +128,7 @@ }

- + u32regex_replace

diff --git a/doc/html/boost_regex/ref/non_std_strings/icu/unicode_iter.html b/doc/html/boost_regex/ref/non_std_strings/icu/unicode_iter.html index 6f6698a3..b179c8e4 100644 --- a/doc/html/boost_regex/ref/non_std_strings/icu/unicode_iter.html +++ b/doc/html/boost_regex/ref/non_std_strings/icu/unicode_iter.html @@ -28,7 +28,7 @@ Unicode Aware Regex Iterators

- + u32regex_iterator

@@ -126,7 +126,7 @@ Provided of course that the input is encoded as UTF-8.

- + u32regex_token_iterator

diff --git a/doc/html/boost_regex/ref/non_std_strings/mfc_strings/mfc_algo.html b/doc/html/boost_regex/ref/non_std_strings/mfc_strings/mfc_algo.html index 48f67005..d62ab666 100644 --- a/doc/html/boost_regex/ref/non_std_strings/mfc_strings/mfc_algo.html +++ b/doc/html/boost_regex/ref/non_std_strings/mfc_strings/mfc_algo.html @@ -34,7 +34,7 @@ here they are anyway:

- + regex_match

@@ -82,7 +82,7 @@ }

- + regex_match (second overload)
@@ -110,7 +110,7 @@ }
- + regex_search

@@ -149,7 +149,7 @@ }

- + regex_search (second overload)
@@ -164,7 +164,7 @@ + s.GetLength(), e, f);

- + regex_replace

diff --git a/doc/html/boost_regex/ref/non_std_strings/mfc_strings/mfc_iter.html b/doc/html/boost_regex/ref/non_std_strings/mfc_strings/mfc_iter.html index 27380fa3..74043549 100644 --- a/doc/html/boost_regex/ref/non_std_strings/mfc_strings/mfc_iter.html +++ b/doc/html/boost_regex/ref/non_std_strings/mfc_strings/mfc_iter.html @@ -32,7 +32,7 @@ an MFC/ATL string to a regex_iterator or regex_token_iterator:

- + regex_iterator creation helper
@@ -68,7 +68,7 @@ }
- + regex_token_iterator creation helpers
diff --git a/doc/html/boost_regex/ref/posix.html b/doc/html/boost_regex/ref/posix.html index 916e4a24..a7456c78 100644 --- a/doc/html/boost_regex/ref/posix.html +++ b/doc/html/boost_regex/ref/posix.html @@ -165,7 +165,7 @@

- + regcomp

@@ -379,7 +379,7 @@

- + regerror

@@ -467,7 +467,7 @@

- + regexec

@@ -537,7 +537,7 @@

- + regfree

diff --git a/doc/html/boost_regex/ref/regex_iterator.html b/doc/html/boost_regex/ref/regex_iterator.html index 6cb4652a..33a69671 100644 --- a/doc/html/boost_regex/ref/regex_iterator.html +++ b/doc/html/boost_regex/ref/regex_iterator.html @@ -78,7 +78,7 @@ regex_constants::match_flag_type m = regex_constants::match_default);

- + Description

@@ -436,7 +436,7 @@ m.

- + Examples

diff --git a/doc/html/boost_regex/ref/regex_match.html b/doc/html/boost_regex/ref/regex_match.html index 9e58948d..7647ea87 100644 --- a/doc/html/boost_regex/ref/regex_match.html +++ b/doc/html/boost_regex/ref/regex_match.html @@ -80,7 +80,7 @@ match_flag_type flags = match_default);

- + Description
template <class BidirectionalIterator, class Allocator, class charT, class traits>
@@ -360,7 +360,7 @@
         Effects: Returns the result of regex_match(s.begin(), s.end(), e, flags).
       

- + Examples

diff --git a/doc/html/boost_regex/ref/regex_replace.html b/doc/html/boost_regex/ref/regex_replace.html index eb2b081f..2e4551f9 100644 --- a/doc/html/boost_regex/ref/regex_replace.html +++ b/doc/html/boost_regex/ref/regex_replace.html @@ -53,7 +53,7 @@ match_flag_type flags = match_default);

- + Description
template <class OutputIterator, class BidirectionalIterator, class traits, class charT>
@@ -163,7 +163,7 @@
         and then returns result.
       

- + Examples

diff --git a/doc/html/boost_regex/ref/regex_search.html b/doc/html/boost_regex/ref/regex_search.html index 9ab5b031..4017b942 100644 --- a/doc/html/boost_regex/ref/regex_search.html +++ b/doc/html/boost_regex/ref/regex_search.html @@ -73,7 +73,7 @@ match_flag_type flags = match_default);

- + Description
template <class BidirectionalIterator, class Allocator, class charT, class traits>
@@ -355,7 +355,7 @@
         Effects: Returns the result of regex_search(s.begin(), s.end(), e, flags).
       

- + Examples

diff --git a/doc/html/boost_regex/ref/regex_token_iterator.html b/doc/html/boost_regex/ref/regex_token_iterator.html index 7ce064f0..d837fb03 100644 --- a/doc/html/boost_regex/ref/regex_token_iterator.html +++ b/doc/html/boost_regex/ref/regex_token_iterator.html @@ -136,7 +136,7 @@ regex_constants::match_flag_type m = regex_constants::match_default);

- + Description

@@ -383,7 +383,7 @@ m.

- + Examples

diff --git a/doc/html/boost_regex/ref/regex_traits.html b/doc/html/boost_regex/ref/regex_traits.html index 88c599ce..43fc043e 100644 --- a/doc/html/boost_regex/ref/regex_traits.html +++ b/doc/html/boost_regex/ref/regex_traits.html @@ -46,7 +46,7 @@ } // namespace boost

- + Description

diff --git a/doc/html/boost_regex/ref/sub_match.html b/doc/html/boost_regex/ref/sub_match.html index ab42cbe1..4360bb0d 100644 --- a/doc/html/boost_regex/ref/sub_match.html +++ b/doc/html/boost_regex/ref/sub_match.html @@ -329,11 +329,11 @@ } // namespace boost

- + Description
- + Members

@@ -473,7 +473,7 @@

- + sub_match non-member operators
@@ -1008,7 +1008,7 @@ + m2.str().

- + Stream inserter

diff --git a/doc/html/boost_regex/syntax/basic_extended.html b/doc/html/boost_regex/syntax/basic_extended.html index f3a7175d..afaca7c9 100644 --- a/doc/html/boost_regex/syntax/basic_extended.html +++ b/doc/html/boost_regex/syntax/basic_extended.html @@ -28,7 +28,7 @@ Expression Syntax

- + Synopsis

@@ -46,7 +46,7 @@

- + POSIX Extended Syntax

@@ -56,7 +56,7 @@

.[{()\*+?|^$
- + Wildcard:

@@ -74,7 +74,7 @@

- + Anchors:

@@ -86,7 +86,7 @@ of an expression, or the last character of a sub-expression.

- + Marked sub-expressions:
@@ -98,7 +98,7 @@ to by a back-reference.

- + Repeats:

@@ -184,7 +184,7 @@ cab operator to be applied to.

- + Back references:

@@ -214,7 +214,7 @@ cab

- + Alternation

@@ -227,7 +227,7 @@ cab will match either of "abd" or "abef".

- + Character sets:
@@ -240,7 +240,7 @@ cab A bracket expression may contain any combination of the following:

- + Single characters:
@@ -249,7 +249,7 @@ cab or 'c'.

- + Character ranges:
@@ -265,7 +265,7 @@ cab the code points of the characters only.

- + Negation:

@@ -274,7 +274,7 @@ cab range a-c.

- + Character classes:
@@ -284,7 +284,7 @@ cab character class names.

- + Collating Elements:
@@ -312,7 +312,7 @@ cab matches a NUL character.

- + Equivalence classes:
@@ -329,7 +329,7 @@ cab or even all locales on one platform.

- + Combinations:

@@ -337,7 +337,7 @@ cab [[:digit:]a-c[.NUL.]].

- + Escapes

@@ -363,7 +363,7 @@ cab extensions are also supported by Boost.Regex:

- + Escapes matching a specific character
@@ -552,7 +552,7 @@ cab
- + "Single character" character classes:
@@ -706,7 +706,7 @@ cab
- + Character Properties
@@ -813,7 +813,7 @@ cab matches any "digit" character, as does \p{digit}.

- + Word Boundaries

@@ -888,7 +888,7 @@ cab

- + Buffer boundaries
@@ -979,7 +979,7 @@ cab
- + Continuation Escape
@@ -991,7 +991,7 @@ cab match to start where the last one ended.

- + Quoting escape
@@ -1005,7 +1005,7 @@ cab \*+aaa
- + Unicode escapes
@@ -1056,7 +1056,7 @@ cab
- + Any other escape
@@ -1065,7 +1065,7 @@ cab \@ matches a literal '@'.

- + Operator precedence
@@ -1101,7 +1101,7 @@ cab
- + What Gets Matched
@@ -1111,11 +1111,11 @@ cab rule.

- + Variations

- + Egrep

@@ -1136,7 +1136,7 @@ cab used with the -E option.

- + awk

@@ -1150,7 +1150,7 @@ cab these by default anyway.

- + Options

@@ -1163,7 +1163,7 @@ cab modify how the case and locale sensitivity are to be applied.

- + References

diff --git a/doc/html/boost_regex/syntax/basic_syntax.html b/doc/html/boost_regex/syntax/basic_syntax.html index 266b7d0f..47bc62d0 100644 --- a/doc/html/boost_regex/syntax/basic_syntax.html +++ b/doc/html/boost_regex/syntax/basic_syntax.html @@ -28,7 +28,7 @@ Expression Syntax

- + Synopsis

@@ -45,7 +45,7 @@

- + POSIX Basic Syntax

@@ -55,7 +55,7 @@

.[\*^$
- + Wildcard:

@@ -73,7 +73,7 @@

- + Anchors:

@@ -85,7 +85,7 @@ of an expression, or the last character of a sub-expression.

- + Marked sub-expressions:
@@ -97,7 +97,7 @@ by a back-reference.

- + Repeats:

@@ -155,7 +155,7 @@ aaaa to.

- + Back references:

@@ -173,7 +173,7 @@ aaaa

aaabba
- + Character sets:
@@ -186,7 +186,7 @@ aaaa A bracket expression may contain any combination of the following:

- + Single characters:
@@ -195,7 +195,7 @@ aaaa or 'c'.

- + Character ranges:
@@ -211,7 +211,7 @@ aaaa of the characters only.

- + Negation:

@@ -220,7 +220,7 @@ aaaa range a-c.

- + Character classes:
@@ -230,7 +230,7 @@ aaaa character class names.

- + Collating Elements:
@@ -259,7 +259,7 @@ aaaa element names.

- + Equivalence classes:
@@ -276,7 +276,7 @@ aaaa or even all locales on one platform.

- + Combinations:

@@ -284,7 +284,7 @@ aaaa [[:digit:]a-c[.NUL.]].

- + Escapes

@@ -299,7 +299,7 @@ aaaa will match either a literal '\' or a '^'.

- + What Gets Matched

@@ -309,13 +309,13 @@ aaaa rule.

- + Variations

- + Grep

@@ -333,7 +333,7 @@ aaaa As its name suggests, this behavior is consistent with the Unix utility grep.

- + emacs

@@ -613,7 +613,7 @@ aaaa leftmost-longest rule.

- + Options

@@ -627,7 +627,7 @@ aaaa options modify how the case and locale sensitivity are to be applied.

- + References

diff --git a/doc/html/boost_regex/syntax/perl_syntax.html b/doc/html/boost_regex/syntax/perl_syntax.html index c77eeddb..f257a5d0 100644 --- a/doc/html/boost_regex/syntax/perl_syntax.html +++ b/doc/html/boost_regex/syntax/perl_syntax.html @@ -28,7 +28,7 @@ Syntax

- + Synopsis

@@ -43,7 +43,7 @@ boost::regex e2(my_expression, boost::regex::perl|boost::regex::icase);

- + Perl Regular Expression Syntax

@@ -53,7 +53,7 @@

.[{()\*+?|^$
- + Wildcard

@@ -73,7 +73,7 @@

- + Anchors

@@ -83,7 +83,7 @@ A '$' character shall match the end of a line.

- + Marked sub-expressions
@@ -94,7 +94,7 @@ can also repeated, or referred to by a back-reference.

- + Non-marking grouping
@@ -107,7 +107,7 @@ without splitting out any separate sub-expressions.

- + Repeats

@@ -188,7 +188,7 @@ to be applied to.

- + Non greedy repeats
@@ -218,7 +218,7 @@ while consuming as little input as possible.

- + Pocessive repeats
@@ -250,7 +250,7 @@ while giving nothing back.

- + Back references

@@ -360,7 +360,7 @@ named "two".

- + Alternation

@@ -387,7 +387,7 @@ (?:abc)?? has exactly the same effect.

- + Character sets

@@ -399,7 +399,7 @@ A bracket expression may contain any combination of the following:

- + Single characters

@@ -407,7 +407,7 @@ 'b', or 'c'.

- + Character ranges
@@ -421,7 +421,7 @@ sensitive.

- + Negation

@@ -430,7 +430,7 @@ matches any character that is not in the range a-c.

- + Character classes
@@ -441,7 +441,7 @@ class names.

- + Collating Elements
@@ -463,7 +463,7 @@ matches a \0 character.

- + Equivalence classes
@@ -480,7 +480,7 @@ or even all locales on one platform.

- + Escaped Characters
@@ -492,7 +492,7 @@ is not a "word" character.

- + Combinations

@@ -500,7 +500,7 @@ [[:digit:]a-c[.NUL.]].

- + Escapes

@@ -692,7 +692,7 @@

- + "Single character" character classes:
@@ -894,7 +894,7 @@
- + Character Properties
@@ -1002,7 +1002,7 @@ as does \p{digit}.

- + Word Boundaries

@@ -1021,7 +1021,7 @@ \B Matches only when not at a word boundary.

- + Buffer boundaries

@@ -1046,7 +1046,7 @@ to the regular expression \n*\z

- + Continuation Escape
@@ -1058,7 +1058,7 @@ one ended.

- + Quoting escape

@@ -1071,7 +1071,7 @@ \*+aaa

- + Unicode escapes

@@ -1081,7 +1081,7 @@ followed by a sequence of zero or more combining characters.

- + Matching Line Endings
@@ -1090,7 +1090,7 @@ sequence, specifically it is identical to the expression (?>\x0D\x0A?|[\x0A-\x0C\x85\x{2028}\x{2029}]).

- + Keeping back some text
@@ -1105,7 +1105,7 @@ This can be used to simulate variable width lookbehind assertions.

- + Any other escape
@@ -1114,7 +1114,7 @@ \@ matches a literal '@'.

- + Perl Extended Patterns
@@ -1123,7 +1123,7 @@ (?.

- + Named Subexpressions
@@ -1145,14 +1145,14 @@ format string for search and replace operations, or in the match_results member functions.

- + Comments

(?# ... ) is treated as a comment, it's contents are ignored.

- + Modifiers

@@ -1166,7 +1166,7 @@ pattern only.

- + Non-marking groups
@@ -1174,8 +1174,30 @@ (?:pattern) lexically groups pattern, without generating an additional sub-expression.

+
+ + Branch reset +
+

+ (?|pattern) resets the subexpression count at the start + of each "|" alternative within pattern. +

+

+ The sub-expression count following this construct is that of whichever branch + had the largest number of sub-expressions. This construct is useful when + you want to capture one of a number of alternative matches in a single sub-expression + index. +

+

+ In the following example the index of each sub-expression is shown below + the expression: +

+
# before  ---------------branch-reset----------- after        
+/ ( a )  (?| x ( y ) z | (p (q) r) | (t) u (v) ) ( z ) /x
+# 1            2         2  3        2     3     4
+
- + Lookahead

@@ -1198,7 +1220,7 @@ could be used to validate the password.

- + Lookbehind

@@ -1212,7 +1234,7 @@ (pattern must be of fixed length).

- + Independent sub-expressions
@@ -1225,7 +1247,7 @@ no match is found at all.

- + Conditional Expressions
@@ -1244,7 +1266,7 @@ sub-expression has been matched).

- + Operator precedence
@@ -1279,7 +1301,7 @@

- + What gets matched

@@ -1454,7 +1476,7 @@

- + Variations

@@ -1463,7 +1485,7 @@ and JScript are all synonyms for perl.

- + Options

@@ -1475,7 +1497,7 @@ are to be applied.

- + Pattern Modifiers

@@ -1487,7 +1509,7 @@ and no_mod_s.

- + References

diff --git a/doc/html/boost_regex/unicode.html b/doc/html/boost_regex/unicode.html index 427cb889..84b3eb20 100644 --- a/doc/html/boost_regex/unicode.html +++ b/doc/html/boost_regex/unicode.html @@ -30,7 +30,7 @@ There are two ways to use Boost.Regex with Unicode strings:

- + Rely on wchar_t

@@ -56,7 +56,7 @@

- + Use a Unicode Aware Regular Expression Type.
diff --git a/doc/html/index.html b/doc/html/index.html index 25083a6f..0e5fb761 100644 --- a/doc/html/index.html +++ b/doc/html/index.html @@ -28,7 +28,7 @@
-

+

Distributed under the Boost Software License, Version 1.0. (See accompanying file LICENSE_1_0.txt or copy at http://www.boost.org/LICENSE_1_0.txt)

@@ -196,7 +196,7 @@

- +

Last revised: May 09, 2009 at 16:16:54 GMT

Last revised: May 13, 2009 at 09:14:16 GMT


diff --git a/doc/syntax_perl.qbk b/doc/syntax_perl.qbk index ff14c703..93707e2b 100644 --- a/doc/syntax_perl.qbk +++ b/doc/syntax_perl.qbk @@ -462,6 +462,22 @@ modifier on, letters afterward, turn it off. =(?:pattern)= lexically groups pattern, without generating an additional sub-expression. +[h5 Branch reset] + +=(?|pattern)= resets the subexpression count at the start of each "|" alternative within /pattern/. + +The sub-expression count following this construct is that of whichever branch had the largest number of +sub-expressions. This construct is useful when you want to capture one of a number of alternative matches +in a single sub-expression index. + +In the following example the index of each sub-expression is shown below the expression: + +[pre +# before ---------------branch-reset----------- after +/ ( a ) (?| x ( y ) z | (p (q) r) | (t) u (v) ) ( z ) /x +# 1 2 2 3 2 3 4 +] + [h5 Lookahead] [^(?=pattern)] consumes zero characters, only if pattern matches. diff --git a/include/boost/regex/v4/basic_regex_parser.hpp b/include/boost/regex/v4/basic_regex_parser.hpp index 09777d20..e36f91db 100644 --- a/include/boost/regex/v4/basic_regex_parser.hpp +++ b/include/boost/regex/v4/basic_regex_parser.hpp @@ -78,6 +78,8 @@ private: const charT* m_end; // the end of the string being parsed const charT* m_position; // our current parser position unsigned m_mark_count; // how many sub-expressions we have + int m_mark_reset; // used to indicate that we're inside a (?|...) block. + unsigned m_max_mark; // largest mark count seen inside a (?|...) block. std::ptrdiff_t m_paren_start; // where the last seen ')' began (where repeats are inserted). std::ptrdiff_t m_alt_insert_point; // where to insert the next alternative bool m_has_case_change; // true if somewhere in the current block the case has changed @@ -96,7 +98,7 @@ private: template basic_regex_parser::basic_regex_parser(regex_data* data) - : basic_regex_creator(data), m_mark_count(0), m_paren_start(0), m_alt_insert_point(0), m_has_case_change(false) + : basic_regex_creator(data), m_mark_count(0), m_mark_reset(-1), m_max_mark(0), m_paren_start(0), m_alt_insert_point(0), m_has_case_change(false) { } @@ -1072,6 +1074,14 @@ bool basic_regex_parser::parse_alt() fail(regex_constants::error_empty, this->m_position - this->m_base); return false; } + // + // Reset mark count if required: + // + if(m_max_mark < m_mark_count) + m_max_mark = m_mark_count; + if(m_mark_reset >= 0) + m_mark_count = m_mark_reset; + ++m_position; // // we need to append a trailing jump: @@ -1794,11 +1804,16 @@ bool basic_regex_parser::parse_perl_extension() bool old_case_change = m_has_case_change; m_has_case_change = false; charT name_delim; + int mark_reset = m_mark_reset; + m_mark_reset = -1; // // select the actual extension used: // switch(this->m_traits.syntax_type(*m_position)) { + case regex_constants::syntax_or: + m_mark_reset = m_mark_count; + // fall through: case regex_constants::syntax_colon: // // a non-capturing mark: @@ -2089,6 +2104,15 @@ named_capture_jump: // and the case change data: // m_has_case_change = old_case_change; + // + // And the mark_reset data: + // + if(m_max_mark > m_mark_count) + { + m_mark_count = m_max_mark; + } + m_mark_reset = mark_reset; + if(markid > 0) { diff --git a/test/regress/main.cpp b/test/regress/main.cpp index 73692208..064a19dd 100644 --- a/test/regress/main.cpp +++ b/test/regress/main.cpp @@ -40,7 +40,6 @@ int error_count = 0; void run_tests() { - RUN_TESTS(test_pocessive_repeats); RUN_TESTS(basic_tests); RUN_TESTS(test_simple_repeats); RUN_TESTS(test_alt); @@ -71,6 +70,8 @@ void run_tests() RUN_TESTS(test_operators); RUN_TESTS(test_overloads); RUN_TESTS(test_unicode); + RUN_TESTS(test_pocessive_repeats); + RUN_TESTS(test_mark_resets); } int cpp_main(int /*argc*/, char * /*argv*/[]) diff --git a/test/regress/test.hpp b/test/regress/test.hpp index e812aa94..0e6b88f9 100644 --- a/test/regress/test.hpp +++ b/test/regress/test.hpp @@ -259,5 +259,6 @@ void test_operators(); void test_overloads(); void test_unicode(); void test_pocessive_repeats(); +void test_mark_resets(); #endif diff --git a/test/regress/test_perl_ex.cpp b/test/regress/test_perl_ex.cpp index 6aa31684..2cb5f208 100644 --- a/test/regress/test_perl_ex.cpp +++ b/test/regress/test_perl_ex.cpp @@ -651,3 +651,28 @@ void test_options3() #endif } +void test_mark_resets() +{ + using namespace boost::regex_constants; + + TEST_REGEX_SEARCH("(?|(abc)|(xyz))", perl, "abc", match_default, make_array(0, 3, 0, 3, -2, -2)); + TEST_REGEX_SEARCH("(?|(abc)|(xyz))", perl, "xyz", match_default, make_array(0, 3, 0, 3, -2, -2)); + TEST_REGEX_SEARCH("(x)(?|(abc)|(xyz))(x)", perl, "xabcx", match_default, make_array(0, 5, 0, 1, 1, 4, 4, 5, -2, -2)); + TEST_REGEX_SEARCH("(x)(?|(abc)|(xyz))(x)", perl, "xxyzx", match_default, make_array(0, 5, 0, 1, 1, 4, 4, 5, -2, -2)); + TEST_REGEX_SEARCH("(x)(?|(abc)(pqr)|(xyz))(x)", perl, "xabcpqrx", match_default, make_array(0, 8, 0, 1, 1, 4, 4, 7, 7, 8, -2, -2)); + TEST_REGEX_SEARCH("(x)(?|(abc)(pqr)|(xyz))(x)", perl, "xxyzx", match_default, make_array(0, 5, 0, 1, 1, 4, -1, -1, 4, 5, -2, -2)); + TEST_REGEX_SEARCH("(?|(abc)|(xyz))\\1", perl, "abcabc", match_default, make_array(0, 6, 0, 3, -2, -2)); + TEST_REGEX_SEARCH("(?|(abc)|(xyz))\\1", perl, "xyzxyz", match_default, make_array(0, 6, 0, 3, -2, -2)); + TEST_REGEX_SEARCH("(?|(abc)|(xyz))\\1", perl, "abcxyz", match_default, make_array(-2, -2)); + TEST_REGEX_SEARCH("(?|(abc)|(xyz))\\1", perl, "xyzabc", match_default, make_array(-2, -2)); + //TEST_REGEX_SEARCH("(?|(abc)|(xyz))(?1)", perl, "abcabc", match_default, make_array(0, 6, 0, 3, -2, -2)); + //TEST_REGEX_SEARCH("(?|(abc)|(xyz))(?1)", perl, "xyzabc", match_default, make_array(0, 6, 0, 3, -2, -2)); + //TEST_REGEX_SEARCH("(?|(abc)|(xyz))(?1)", perl, "xyzxyz", match_default, make_array(-2, -2)); + //TEST_REGEX_SEARCH("^X(?5)(a)(?|(b)|(q))(c)(d)(Y)", perl, "XYabcdY", match_default, make_array(0, 7, 2, 3, 3, 4, 4, 5, 5, 6, 6, 7, -2, -2)); + //TEST_INVALID_REGEX("^X(?5)(a)(?|(b)|(q))(c)(d)Y", perl); + //TEST_REGEX_SEARCH("^X(?&N)(a)(?|(b)|(q))(c)(d)(?Y)", perl, "XYabcdY", match_default, make_array(0, 7, 2, 3, 3, 4, 4, 5, 5, 6, 6, 7, -2, -2)); + //TEST_REGEX_SEARCH("^X(?7)(a)(?|(b)|(q)(r)(s))(c)(d)(Y)", perl, "XYabcdY", match_default, make_array(0, 7, 2, 3, 3, 4, -1, -1, -1, -1, 6, 7, -2, -2)); + //TEST_REGEX_SEARCH("^X(?7)(a)(?|(b|(r)(s))|(q))(c)(d)(Y)", perl, "XYabcdY", match_default, make_array(0, 7, 2, 3, 3, 4, -1, -1, -1, -1, 6, 7, -2, -2)); + //TEST_REGEX_SEARCH("^X(?7)(a)(?|(b|(?|(r)|(t))(s))|(q))(c)(d)(Y)", perl, "XYabcdY", match_default, make_array(0, 7, 2, 3, 3, 4, -1, -1, -1, -1, 6, 7, -2, -2)); +} +