boostorg/regex
1
0
Fork 1
mirror of https://github.com/boostorg/regex.git synced 2025-07-31 21:14:36 +02:00
Code Issues Packages Projects Releases Wiki Activity

Merge branch 'develop'

Browse Source
This commit is contained in:
jzmaddock
2015-02-14 12:56:15 +00:00
parent 741e684ac3 a87ecdc49c
commit d4506c48ac
16 changed files with 40 additions and 38 deletions
Download Patch File Download Diff File Expand all files Collapse all files

17
build/Jamfile.v2
View File

@@ -60,9 +60,9 @@ if ! $(disable-icu)
lib icuin : : <name>icui18n <link>shared <runtime-link>shared <conditional>@path_options ; lib icuin : : <name>icui18n <link>shared <runtime-link>shared <conditional>@path_options ;
lib icuin : : <toolset>msvc <variant>debug <name>icuind <link>shared <runtime-link>shared <conditional>@path_options ; lib icuin : : <toolset>msvc <variant>debug <name>icuind <link>shared <runtime-link>shared <conditional>@path_options ;
lib icuin : : <toolset>msvc <variant>release <name>icuin <link>shared <runtime-link>shared <conditional>@path_options ; lib icuin : : <toolset>msvc <name>icuin <link>shared <runtime-link>shared <conditional>@path_options ;
lib icuin : : <toolset>intel <target-os>windows <variant>debug <name>icuind <link>shared <runtime-link>shared <conditional>@path_options ; lib icuin : : <toolset>intel <target-os>windows <variant>debug <name>icuind <link>shared <runtime-link>shared <conditional>@path_options ;
lib icuin : : <toolset>intel <target-os>windows <variant>release <name>icuin <link>shared <runtime-link>shared <conditional>@path_options ; lib icuin : : <toolset>intel <target-os>windows <name>icuin <link>shared <runtime-link>shared <conditional>@path_options ;
lib icuin : : <name>this_is_an_invalid_library_name ; lib icuin : : <name>this_is_an_invalid_library_name ;
if $(ICU_PATH) if $(ICU_PATH)
@@ -103,12 +103,13 @@ if ! $(disable-icu)
<library>icuin/<link>shared/<runtime-link>shared <library>icuin/<link>shared/<runtime-link>shared
<define>BOOST_HAS_ICU=1 <define>BOOST_HAS_ICU=1
<runtime-link>shared <runtime-link>shared
<toolset>msvc:<linkflags>/delayload:$(icuucd_name:B).dll # As of ICU-54 this does not work anymore (release mode):
<toolset>msvc:<linkflags>/delayload:$(icuuc_name:B).dll #<toolset>msvc:<linkflags>/delayload:$(icuucd_name:B).dll
<toolset>msvc:<linkflags>/delayload:$(icudt_name:B).dll #<toolset>msvc:<linkflags>/delayload:$(icuuc_name:B).dll
<toolset>msvc:<linkflags>/delayload:$(icuin_name:B).dll #<toolset>msvc:<linkflags>/delayload:$(icudt_name:B).dll
<toolset>msvc:<linkflags>/delayload:$(icuind_name:B).dll #<toolset>msvc:<linkflags>/delayload:$(icuin_name:B).dll
<toolset>msvc:<linkflags>delayimp.lib #<toolset>msvc:<linkflags>/delayload:$(icuind_name:B).dll
#<toolset>msvc:<linkflags>delayimp.lib
; ;
} }

4
doc/history.qbk
View File

@@ -25,7 +25,7 @@ this gets bumped up from v4 to v5.
* Fixed documentation typos from [@https://svn.boost.org/trac/boost/ticket/9283 #9283]. * Fixed documentation typos from [@https://svn.boost.org/trac/boost/ticket/9283 #9283].
* Fixed bug in collation code that failed if the locale generated collation strings with embedded nul's, * Fixed bug in collation code that failed if the locale generated collation strings with embedded nul's,
see [@https://svn.boost.org/trac/boost/ticket/9451 #9451]. see [@https://svn.boost.org/trac/boost/ticket/9451 #9451].
* Apply patch for unusual thread usage (no statically initiallized mutexes), see [@https://svn.boost.org/trac/boost/ticket/9461 #9461]. * Apply patch for unusual thread usage (no statically initialized mutexes), see [@https://svn.boost.org/trac/boost/ticket/9461 #9461].
* Added better checks for invalid UTF-8 sequences, see [@https://svn.boost.org/trac/boost/ticket/9473 #9473]. * Added better checks for invalid UTF-8 sequences, see [@https://svn.boost.org/trac/boost/ticket/9473 #9473].
[h4 Boost-1.54] [h4 Boost-1.54]
@@ -153,7 +153,7 @@ and
* Breaking Change: POSIX-extended and POSIX-basic regular expressions now enforce the letter of the POSIX standard much more closely than before. * Breaking Change: POSIX-extended and POSIX-basic regular expressions now enforce the letter of the POSIX standard much more closely than before.
* Added support for (?imsx-imsx) constructs. * Added support for (?imsx-imsx) constructs.
* Added support for lookbehind expressions (?<=positive-lookbehind) and (?<!negative-lookbehind). * Added support for lookbehind expressions (?<=positive-lookbehind) and (?<!negative-lookbehind).
* Added support for conditional expressions (?(assertion)true-expresion|false-expression). * Added support for conditional expressions (?(assertion)true-expression|false-expression).
* Added MFC/ATL string wrappers. * Added MFC/ATL string wrappers.
* Added Unicode support; based on ICU. * Added Unicode support; based on ICU.
* Changed newline support to recognise \\f as a line separator (all character types), and \\x85 as a line separator for wide characters / Unicode only. * Changed newline support to recognise \\f as a line separator (all character types), and \\x85 as a line separator for wide characters / Unicode only.

2
doc/install.qbk
View File

@@ -43,7 +43,7 @@ this:
- has_icu builds : yes - has_icu builds : yes
Whick means that ICU has been found, and support for it will be enabled Which means that ICU has been found, and support for it will be enabled
in the library build. in the library build.
[tip If you don't want the regex library to use ICU then build with the [tip If you don't want the regex library to use ICU then build with the

2
doc/introduction.qbk
View File

@@ -69,7 +69,7 @@ Note how we had to add some extra escapes to the expression: remember that
the escape is seen once by the C++ compiler, before it gets to be seen by the escape is seen once by the C++ compiler, before it gets to be seen by
the regular expression engine, consequently escapes in regular expressions the regular expression engine, consequently escapes in regular expressions
have to be doubled up when embedding them in C/C++ code. Also note that have to be doubled up when embedding them in C/C++ code. Also note that
all the examples assume that your compiler supports argument-dependent-lookup all the examples assume that your compiler supports argument-dependent
lookup, if yours doesn't (for example VC6), then you will have to add some lookup, if yours doesn't (for example VC6), then you will have to add some
`boost::` prefixes to some of the function calls in the examples. `boost::` prefixes to some of the function calls in the examples.

2
doc/locale.qbk
View File

@@ -165,7 +165,7 @@ catalogue. The messages and their id's are as follows:
[[150][The character which when preceded by an escape character represents any single character.]["C" ]] [[150][The character which when preceded by an escape character represents any single character.]["C" ]]
[[151][The character which when preceded by an escape character represents end of buffer operator.]["Z" ]] [[151][The character which when preceded by an escape character represents end of buffer operator.]["Z" ]]
[[152][The character which when preceded by an escape character represents the continuation assertion.]["G" ]] [[152][The character which when preceded by an escape character represents the continuation assertion.]["G" ]]
[[153][The character which when preceeded by (? indicates a zero width negated forward lookahead assert.][! ]] [[153][The character which when preceded by (? indicates a zero width negated forward lookahead assert.][! ]]
] ]
Custom error messages are loaded as follows: Custom error messages are loaded as follows:

2
doc/non_std_strings.qbk
View File

@@ -17,7 +17,7 @@ Certainly any string type that provides access to it's internal buffer, along
with it's length, can be converted into a pair of pointers (which can be with it's length, can be converted into a pair of pointers (which can be
used as iterators). used as iterators).
Some non-standard string types are sufficiently common that wappers have been Some non-standard string types are sufficiently common that wrappers have been
provided for them already: currently this includes the ICU and MFC string class provided for them already: currently this includes the ICU and MFC string class
types. types.

10
doc/old_regex.qbk
View File

@@ -109,7 +109,7 @@ Member functions for class RegEx are defined as follows:
`SetExpression(p, false)`. Throws [bad_expression] on failure. ]] `SetExpression(p, false)`. Throws [bad_expression] on failure. ]]
[[`RegEx& operator=(const std::string& s);`][Assignment operator, equivalent to [[`RegEx& operator=(const std::string& s);`][Assignment operator, equivalent to
calling `SetExpression(s, false)`. Throws [bad_expression] on failure. ]] calling `SetExpression(s, false)`. Throws [bad_expression] on failure. ]]
[[`unsigned int SetExpression(constchar* p, bool icase = false);`][Sets the [[`unsigned int SetExpression(const char* p, bool icase = false);`][Sets the
current expression to /p/, if /icase/ is true then matching is current expression to /p/, if /icase/ is true then matching is
insensitive to case, otherwise it is sensitive to case. insensitive to case, otherwise it is sensitive to case.
Throws [bad_expression] on failure. ]] Throws [bad_expression] on failure. ]]
@@ -165,7 +165,7 @@ Member functions for class RegEx are defined as follows:
[match_flag_type] /flags/. For each match pushes the starting index of what [match_flag_type] /flags/. For each match pushes the starting index of what
matched onto /v/. Returns the number of matches found. ]] matched onto /v/. Returns the number of matches found. ]]
[[`unsigned int GrepFiles(GrepFileCallback cb, const char* files, bool recurse = false, boost::match_flag_type flags = match_default);`] [[`unsigned int GrepFiles(GrepFileCallback cb, const char* files, bool recurse = false, boost::match_flag_type flags = match_default);`]
[Finds all matches of the current expression in the files files using [Finds all matches of the current expression in the files /files/ using
the [match_flag_type] /flags/. For each match calls the call-back function cb. the [match_flag_type] /flags/. For each match calls the call-back function cb.
If the call-back returns false then the algorithm returns without If the call-back returns false then the algorithm returns without
considering further matches in the current file, or any further files. considering further matches in the current file, or any further files.
@@ -178,7 +178,7 @@ Member functions for class RegEx are defined as follows:
May throw an exception derived from `std::runtime_error` if file io fails.]] May throw an exception derived from `std::runtime_error` if file io fails.]]
[[`unsigned int GrepFiles(GrepFileCallback cb, const std::string& files, bool recurse = false, boost::match_flag_type flags = match_default);`] [[`unsigned int GrepFiles(GrepFileCallback cb, const std::string& files, bool recurse = false, boost::match_flag_type flags = match_default);`]
[Finds all matches of the current expression in the files files using the [Finds all matches of the current expression in the files /files/ using the
[match_flag_type] /flags/. For each match calls the call-back function cb. [match_flag_type] /flags/. For each match calls the call-back function cb.
If the call-back returns false then the algorithm returns without If the call-back returns false then the algorithm returns without
@@ -229,7 +229,7 @@ Member functions for class RegEx are defined as follows:
to determine what gets matched, and how the format string should be to determine what gets matched, and how the format string should be
treated. If /copy/ is true then all unmatched sections of input are treated. If /copy/ is true then all unmatched sections of input are
copied unchanged to output, if the flag /format_first_only/ is set then copied unchanged to output, if the flag /format_first_only/ is set then
only the first occurance of the pattern found is replaced. only the first occurrence of the pattern found is replaced.
Returns the new string. See also Returns the new string. See also
[link boost_regex.format format string syntax], and [match_flag_type].]] [link boost_regex.format format string syntax], and [match_flag_type].]]
[[`std::string Merge(const char* in, const char* fmt, bool copy = true, boost::match_flag_type flags = match_default);`] [[`std::string Merge(const char* in, const char* fmt, bool copy = true, boost::match_flag_type flags = match_default);`]
@@ -239,7 +239,7 @@ Member functions for class RegEx are defined as follows:
what gets matched, and how the format string should be treated. what gets matched, and how the format string should be treated.
If /copy/ is true then all unmatched sections of input are copied If /copy/ is true then all unmatched sections of input are copied
unchanged to output, if the flag /format_first_only/ is set then only unchanged to output, if the flag /format_first_only/ is set then only
the first occurance of the pattern found is replaced. Returns the first occurrence of the pattern found is replaced. Returns
the new string. See also [link boost_regex.format format string syntax], and [match_flag_type].]] the new string. See also [link boost_regex.format format string syntax], and [match_flag_type].]]
[[`unsigned Split(std::vector<std::string>& v, std::string& s, boost::match_flag_type flags = match_default, unsigned max_count = ~0);`] [[`unsigned Split(std::vector<std::string>& v, std::string& s, boost::match_flag_type flags = match_default, unsigned max_count = ~0);`]
[Splits the input string and pushes each one onto the vector. [Splits the input string and pushes each one onto the vector.

2
doc/regex_split.qbk
View File

@@ -87,7 +87,7 @@ from a html file, and print them out to cout:
char c; char c;
while(is.get(c)) while(is.get(c))
{ {
// use logarithmic growth stategy, in case // use logarithmic growth strategy, in case
// in_avail (above) returned zero: // in_avail (above) returned zero:
if(s.capacity() == s.size()) if(s.capacity() == s.size())
s.reserve(s.capacity() * 3); s.reserve(s.capacity() * 3);

2
doc/syntax_basic.qbk
View File

@@ -156,7 +156,7 @@ An expression of the form `[[.col.]` matches the collating element /col/.
A collating element is any single character, or any sequence of A collating element is any single character, or any sequence of
characters that collates as a single unit. Collating elements may also characters that collates as a single unit. Collating elements may also
be used as the end point of a range, for example: `[[.ae.]-c]` matches be used as the end point of a range, for example: `[[.ae.]-c]` matches
the character sequence "ae", plus any single character in the rangle "ae"-c, the character sequence "ae", plus any single character in the range "ae"-c,
assuming that "ae" is treated as a single collating element in the current locale. assuming that "ae" is treated as a single collating element in the current locale.
Collating elements may be used in place of escapes (which are not Collating elements may be used in place of escapes (which are not

4
include/boost/regex/icu.hpp
View File

@@ -397,10 +397,10 @@ void copy_results(MR1& out, MR2 const& in)
out.set_base(in.base().base()); out.set_base(in.base().base());
for(int i = 0; i < (int)in.size(); ++i) for(int i = 0; i < (int)in.size(); ++i)
{ {
if(in[i].matched) if(in[i].matched || !i)
{ {
out.set_first(in[i].first.base(), i); out.set_first(in[i].first.base(), i);
out.set_second(in[i].second.base(), i); out.set_second(in[i].second.base(), i, in[i].matched);
} }
} }
} }

2
include/boost/regex/v4/basic_regex_parser.hpp
View File

@@ -1220,7 +1220,7 @@ bool basic_regex_parser<charT, traits>::parse_alt()
) )
) )
{ {
fail(regex_constants::error_empty, this->m_position - this->m_base, "A regular expression can start with the alternation operator |."); fail(regex_constants::error_empty, this->m_position - this->m_base, "A regular expression cannot start with the alternation operator |.");
return false; return false;
} }
// //

9
include/boost/regex/v4/match_results.hpp
View File

@@ -76,10 +76,15 @@ public:
// construct/copy/destroy: // construct/copy/destroy:
explicit match_results(const Allocator& a = Allocator()) explicit match_results(const Allocator& a = Allocator())
#ifndef BOOST_NO_STD_ALLOCATOR #ifndef BOOST_NO_STD_ALLOCATOR
: m_subs(a), m_base(), m_last_closed_paren(0), m_is_singular(true) {} : m_subs(a), m_base(), m_null(), m_last_closed_paren(0), m_is_singular(true) {}
#else #else
: m_subs(), m_base(), m_last_closed_paren(0), m_is_singular(true) { (void)a; } : m_subs(), m_base(), m_null(), m_last_closed_paren(0), m_is_singular(true) { (void)a; }
#endif #endif
//
// IMPORTANT: in the code below, the crazy looking checks around m_is_singular are
// all required because it is illegal to copy a singular iterator.
// See https://svn.boost.org/trac/boost/ticket/3632.
//
match_results(const match_results& m) match_results(const match_results& m)
: m_subs(m.m_subs), m_named_subs(m.m_named_subs), m_last_closed_paren(m.m_last_closed_paren), m_is_singular(m.m_is_singular) : m_subs(m.m_subs), m_named_subs(m.m_named_subs), m_last_closed_paren(m.m_last_closed_paren), m_is_singular(m.m_is_singular)
{ {

9
include/boost/regex/v4/perl_matcher.hpp
View File

@@ -254,13 +254,8 @@ class repeater_count
std::size_t count; // the number of iterations so far std::size_t count; // the number of iterations so far
BidiIterator start_pos; // where the last repeat started BidiIterator start_pos; // where the last repeat started
public: public:
repeater_count(repeater_count** s) repeater_count(repeater_count** s) : stack(s), next(0), state_id(-1), count(0), start_pos() {}
{
stack = s;
next = 0;
state_id = -1;
count = 0;
}
repeater_count(int i, repeater_count** s, BidiIterator start) repeater_count(int i, repeater_count** s, BidiIterator start)
: start_pos(start) : start_pos(start)
{ {

2
include/boost/regex/v4/regex_format.hpp
View File

@@ -96,7 +96,7 @@ class basic_regex_formatter
public: public:
typedef typename traits::char_type char_type; typedef typename traits::char_type char_type;
basic_regex_formatter(OutputIterator o, const Results& r, const traits& t) basic_regex_formatter(OutputIterator o, const Results& r, const traits& t)
: m_traits(t), m_results(r), m_out(o), m_state(output_copy), m_restore_state(output_copy), m_have_conditional(false) {} : m_traits(t), m_results(r), m_out(o), m_position(), m_end(), m_flags(), m_state(output_copy), m_restore_state(output_copy), m_have_conditional(false) {}
OutputIterator format(ForwardIter p1, ForwardIter p2, match_flag_type f); OutputIterator format(ForwardIter p1, ForwardIter p2, match_flag_type f);
OutputIterator format(ForwardIter p1, match_flag_type f) OutputIterator format(ForwardIter p1, match_flag_type f)
{ {

2
include/boost/regex/v4/regex_workaround.hpp
View File

@@ -71,7 +71,7 @@ using std::distance;
/***************************************************************************** /*****************************************************************************
* *
* Fix broken broken namespace support: * Fix broken namespace support:
* *
****************************************************************************/ ****************************************************************************/

5
src/fileiter.cpp
View File

@@ -267,15 +267,16 @@ void mapfile::lock(pointer* node)const
read_size = std::fread(*node + sizeof(int), _size % buf_size, 1, hfile); read_size = std::fread(*node + sizeof(int), _size % buf_size, 1, hfile);
else else
read_size = std::fread(*node + sizeof(int), buf_size, 1, hfile); read_size = std::fread(*node + sizeof(int), buf_size, 1, hfile);
#ifndef BOOST_NO_EXCEPTIONS
if((read_size == 0) || (std::ferror(hfile))) if((read_size == 0) || (std::ferror(hfile)))
{ {
#ifndef BOOST_NO_EXCEPTIONS
unlock(node);
throw std::runtime_error("Unable to read file."); throw std::runtime_error("Unable to read file.");
}
#else #else
BOOST_REGEX_NOEH_ASSERT((0 == std::ferror(hfile)) && (read_size != 0)); BOOST_REGEX_NOEH_ASSERT((0 == std::ferror(hfile)) && (read_size != 0));
#endif #endif
} }
}
else else
{ {
if(*reinterpret_cast<int*>(*node) == 0) if(*reinterpret_cast<int*>(*node) == 0)