Difference between revisions of "cpp/regex/regex match"
Andreas Krug (Talk | contribs) m ([first,last) -> [first, last), headers sorted, fmt) |
m (Wording fix.) |
||
(3 intermediate revisions by 2 users not shown) | |||
Line 4: | Line 4: | ||
{{dcl header|regex}} | {{dcl header|regex}} | ||
{{dcl|num=1|since=c++11|1= | {{dcl|num=1|since=c++11|1= | ||
− | template< class BidirIt, | + | template< class BidirIt, class Alloc, class CharT, class Traits > |
− | + | ||
bool regex_match( BidirIt first, BidirIt last, | bool regex_match( BidirIt first, BidirIt last, | ||
std::match_results<BidirIt, Alloc>& m, | std::match_results<BidirIt, Alloc>& m, | ||
Line 13: | Line 12: | ||
}} | }} | ||
{{dcl|num=2|since=c++11|1= | {{dcl|num=2|since=c++11|1= | ||
− | template< class BidirIt, | + | template< class BidirIt, class CharT, class Traits > |
− | + | ||
bool regex_match( BidirIt first, BidirIt last, | bool regex_match( BidirIt first, BidirIt last, | ||
const std::basic_regex<CharT, Traits>& e, | const std::basic_regex<CharT, Traits>& e, | ||
Line 29: | Line 27: | ||
}} | }} | ||
{{dcl|num=4|since=c++11|1= | {{dcl|num=4|since=c++11|1= | ||
− | template< | + | template< class CharT, class Traits > |
− | + | bool regex_match( const CharT* str, const std::basic_regex<CharT, Traits>& e, | |
− | bool regex_match( const | + | |
− | + | ||
− | + | ||
− | + | ||
− | + | ||
− | + | ||
std::regex_constants::match_flag_type flags = | std::regex_constants::match_flag_type flags = | ||
std::regex_constants::match_default ); | std::regex_constants::match_default ); | ||
}} | }} | ||
{{dcl|num=5|since=c++11|1= | {{dcl|num=5|since=c++11|1= | ||
− | template< class CharT, class Traits > | + | template< class STraits, class SAlloc, class Alloc, |
− | bool regex_match( const CharT | + | class CharT, class Traits > |
− | + | bool regex_match | |
− | + | ( const std::basic_string<CharT, STraits, SAlloc>& s, | |
− | + | std::match_results | |
+ | <typename std::basic_string<CharT, STraits, SAlloc>::const_iterator, | ||
+ | Alloc>& m, | ||
+ | const std::basic_regex<CharT, Traits>& e, | ||
+ | std::regex_constants::match_flag_type flags = | ||
+ | std::regex_constants::match_default ); | ||
}} | }} | ||
{{dcl|num=6|since=c++11|1= | {{dcl|num=6|since=c++11|1= | ||
− | template< class STraits, class SAlloc, | + | template< class STraits, class SAlloc, class CharT, class Traits > |
− | + | ||
bool regex_match( const std::basic_string<CharT, STraits, SAlloc>& s, | bool regex_match( const std::basic_string<CharT, STraits, SAlloc>& s, | ||
const std::basic_regex<CharT, Traits>& e, | const std::basic_regex<CharT, Traits>& e, | ||
Line 56: | Line 52: | ||
}} | }} | ||
{{dcl|num=7|since=c++11|1= | {{dcl|num=7|since=c++11|1= | ||
− | template< class STraits, class SAlloc, | + | template< class STraits, class SAlloc, class Alloc, |
− | + | class CharT, class Traits > | |
− | bool regex_match( const std::basic_string<CharT, STraits, SAlloc>&&, | + | bool regex_match |
− | + | ( const std::basic_string<CharT, STraits, SAlloc>&&, | |
− | + | std::match_results | |
− | + | <typename std::basic_string<CharT, STraits, SAlloc>::const_iterator, | |
− | + | Alloc>&, | |
− | + | const std::basic_regex<CharT, Traits>&, | |
− | + | std::regex_constants::match_flag_type flags = | |
− | + | std::regex_constants::match_default ) = delete; | |
}} | }} | ||
{{dcl end}} | {{dcl end}} | ||
− | Determines if the regular expression {{ | + | Determines if the regular expression {{c|e}} matches the entire target character sequence. The detailed match result is stored in {{c|m}} (if present). |
− | @1@ | + | @1,2@ The target character sequence is represented by the range {{range|first|last}}. |
− | + | {{rev begin}} | |
− | + | {{rev|until=c++23| | |
− | + | If {{tt|BidirIt}} does not satisfy the requirements of {{named req|BidirectionalIterator}}, the behavior is undefined. | |
− | + | }} | |
+ | {{rev|since=c++23| | ||
+ | If {{tt|BidirIt}} does not model {{lconcept|bidirectional_iterator}}, the behavior is undefined. | ||
+ | }} | ||
+ | {{rev end}} | ||
− | @4@ | + | @3,4@ The target character sequence is represented by the range {{range|str|str + std::char_traits<CharT>::length(str)}}. |
− | @5@ | + | @5,6@ The target character sequence is represented by the string {{c|s}}. |
− | @ | + | @7@ The target character sequence cannot be represented by a {{lc|std::string}} rvalue. |
− | + | If the match does not exist, the following expressions involving {{c|m}} (if exists) should yield the specified values: | |
+ | {|class="wikitable" style="text-align: center;" | ||
+ | !{{nbsp}}Expression{{nbsp}} | ||
+ | !{{nbsp}}Value{{nbsp}} | ||
+ | |- | ||
+ | |{{box|{{c/core|m.}}{{ltt|cpp/regex/match_results/ready}}{{c/core|()}}}} | ||
+ | |{{c|true}} | ||
+ | |- | ||
+ | |{{box|{{c/core|m.}}{{ltt|cpp/regex/match_results/size}}{{c/core|()}}}} | ||
+ | |{{c|0}} | ||
+ | |- | ||
+ | |{{box|{{c/core|m.}}{{ltt|cpp/regex/match_results/empty}}{{c/core|()}}}} | ||
+ | |{{c|true}} | ||
+ | |} | ||
− | + | If the match exists, given any integer in {{open range|0|m.size()}} as {{c|n}}, the following expressions involving {{c|m}} should yield the specified values for each overload listed below: | |
+ | {|class="wikitable" style="text-align: center;" | ||
+ | !rowspan=2|{{nbsp|6}}Expression{{nbsp|6}} | ||
+ | !colspan=3|Value | ||
+ | |- | ||
+ | !{{nbsp|11}}Overload {{v|1}}{{nbsp|11}} | ||
+ | !{{nbsp|11}}Overload {{v|3}}{{nbsp|11}} | ||
+ | !{{nbsp|11}}Overload {{v|5}}{{nbsp|11}} | ||
+ | |- | ||
+ | |{{box|{{c/core|m.}}{{ltt|cpp/regex/match_results/ready}}{{c/core|()}}}} | ||
+ | |colspan=3|{{c|true}} | ||
+ | |- | ||
+ | |{{box|{{c/core|m.}}{{ltt|cpp/regex/match_results/size}}{{c/core|()}}}} | ||
+ | |colspan=3|{{box|{{c/core|1 + e.}}{{ltt|cpp/regex/basic_regex/mark_count}}{{c/core|()}}}} | ||
+ | |- | ||
+ | |{{box|{{c/core|m.}}{{ltt|cpp/regex/match_results/empty}}{{c/core|()}}}} | ||
+ | |colspan=3|{{c|false}} | ||
+ | |- | ||
+ | |{{box|{{c/core|m.}}{{ltt|cpp/regex/match_results/prefix}}{{c/core|().first}}}} | ||
+ | |rowspan=2|{{c|first}} | ||
+ | |rowspan=2|{{c|str}} | ||
+ | |rowspan=2|{{c|s.begin()}} | ||
+ | |- | ||
+ | |{{box|{{c/core|m.}}{{ltt|cpp/regex/match_results/prefix}}{{c/core|().second}}}} | ||
+ | |- | ||
+ | |{{box|{{c/core|m.}}{{ltt|cpp/regex/match_results/prefix}}{{c/core|().matched}}}} | ||
+ | |colspan=3|{{nbsp|4}}{{c|false}}<ref>The match prefix is empty.</ref> | ||
+ | |- | ||
+ | |{{box|{{c/core|m.}}{{ltt|cpp/regex/match_results/suffix}}{{c/core|().first}}}} | ||
+ | |rowspan=2|{{c|last}} | ||
+ | |rowspan=2|<span style="text-align: start;">{{c multi|std::char_traits<CharT>::| length(str) + str}}</span> | ||
+ | |rowspan=2|{{c|s.end()}} | ||
+ | |- | ||
+ | |{{box|{{c/core|m.}}{{ltt|cpp/regex/match_results/suffix}}{{c/core|().second}}}} | ||
+ | |- | ||
+ | |{{box|{{c/core|m.}}{{ltt|cpp/regex/match_results/suffix}}{{c/core|().matched}}}} | ||
+ | |colspan=3|{{nbsp|4}}{{c|false}}<ref>The match suffix is empty.</ref> | ||
+ | |- | ||
+ | |{{box|{{c/core|m}}{{ltt|cpp/regex/match_results/operator at|[0]}}{{c/core|.first}}}} | ||
+ | |{{c|first}} | ||
+ | |{{c|str}} | ||
+ | |{{c|s.begin()}} | ||
+ | |- | ||
+ | |{{box|{{c/core|m}}{{ltt|cpp/regex/match_results/operator at|[0]}}{{c/core|.second}}}} | ||
+ | |{{c|last}} | ||
+ | |<span style="text-align: start;">{{c multi|std::char_traits<CharT>::| length(str) + str}}</span> | ||
+ | |{{c|s.end()}} | ||
+ | |- | ||
+ | |{{box|{{c/core|m}}{{ltt|cpp/regex/match_results/operator at|[0]}}{{c/core|.matched}}}} | ||
+ | |colspan=3|{{nbsp|4}}{{c|true}}<ref>The entire sequence is matched.</ref> | ||
+ | |- | ||
+ | |{{box|{{c/core|m}}{{ltt|cpp/regex/match_results/operator at|[n]}}{{c/core|.first}}}} | ||
+ | |colspan=3| | ||
+ | * {{c|last}} if [[cpp/regex/ecmascript#Sub-expressions|marked sub-expression]] {{c|n}} did not participate in the match | ||
+ | * the start of the sequence otherwise matching sub-expression {{c|n}} otherwise | ||
+ | |- | ||
+ | |{{box|{{c/core|m}}{{ltt|cpp/regex/match_results/operator at|[n]}}{{c/core|.second}}}} | ||
+ | |colspan=3| | ||
+ | * {{c|last}} if [[cpp/regex/ecmascript#Sub-expressions|marked sub-expression]] {{c|n}} did not participate in the match | ||
+ | * the end of the sequence otherwise matching sub-expression {{c|n}} otherwise | ||
+ | |- | ||
+ | |{{box|{{c/core|m}}{{ltt|cpp/regex/match_results/operator at|[n]}}{{c/core|.matched}}}} | ||
+ | |colspan=3| | ||
+ | * {{c|false}} if [[cpp/regex/ecmascript#Sub-expressions|marked sub-expression]] {{c|n}} did not participate in the match | ||
+ | * {{c|true}} otherwise | ||
+ | |} | ||
+ | <references/> | ||
===Parameters=== | ===Parameters=== | ||
{{par begin}} | {{par begin}} | ||
− | {{par|first, last|the target character range | + | {{par|first, last|the target character range}} |
+ | {{par|str|the target null-terminated C-style string}} | ||
+ | {{par|s|the target {{lc|std::basic_string}}}} | ||
{{par|m|the match results}} | {{par|m|the match results}} | ||
− | |||
− | |||
{{par|e|the regular expression}} | {{par|e|the regular expression}} | ||
{{par|flags|flags used to determine how the match will be performed}} | {{par|flags|flags used to determine how the match will be performed}} | ||
− | |||
− | |||
{{par end}} | {{par end}} | ||
===Return value=== | ===Return value=== | ||
− | Returns {{c|true}} if | + | Returns {{c|true}} if the entire target sequence matches {{c|e}}, {{c|false}} otherwise. |
− | + | ||
− | + | ||
− | + | ||
− | + | ||
− | + | ||
− | + | ||
− | + | ||
− | + | ||
− | + | ||
− | + | ||
− | + | ||
− | + | ||
− | + | ||
− | + | ||
− | + | ||
− | + | ||
− | + | ||
− | + | ||
− | + | ||
− | + | ||
− | + | ||
− | + | ||
− | + | ||
− | + | ||
− | + | ||
− | + | ||
===Notes=== | ===Notes=== | ||
Line 142: | Line 193: | ||
{{example | {{example | ||
|code= | |code= | ||
+ | #include <cstddef> | ||
#include <iostream> | #include <iostream> | ||
#include <regex> | #include <regex> | ||
Line 151: | Line 203: | ||
const std::string fnames[] = {"foo.txt", "bar.txt", "baz.dat", "zoidberg"}; | const std::string fnames[] = {"foo.txt", "bar.txt", "baz.dat", "zoidberg"}; | ||
const std::regex txt_regex("[a-z]+\\.txt"); | const std::regex txt_regex("[a-z]+\\.txt"); | ||
− | + | ||
− | for (const auto &fname : fnames) | + | for (const auto& fname : fnames) |
std::cout << fname << ": " << std::regex_match(fname, txt_regex) << '\n'; | std::cout << fname << ": " << std::regex_match(fname, txt_regex) << '\n'; | ||
− | + | ||
// Extraction of a sub-match | // Extraction of a sub-match | ||
const std::regex base_regex("([a-z]+)\\.txt"); | const std::regex base_regex("([a-z]+)\\.txt"); | ||
std::smatch base_match; | std::smatch base_match; | ||
− | + | ||
− | for (const auto &fname : fnames) | + | for (const auto& fname : fnames) |
− | + | ||
if (std::regex_match(fname, base_match, base_regex)) | if (std::regex_match(fname, base_match, base_regex)) | ||
− | |||
// The first sub_match is the whole string; the next | // The first sub_match is the whole string; the next | ||
// sub_match is the first parenthesized expression. | // sub_match is the first parenthesized expression. | ||
Line 171: | Line 221: | ||
std::cout << fname << " has a base of " << base << '\n'; | std::cout << fname << " has a base of " << base << '\n'; | ||
} | } | ||
− | + | ||
− | + | ||
− | + | ||
// Extraction of several sub-matches | // Extraction of several sub-matches | ||
const std::regex pieces_regex("([a-z]+)\\.([a-z]+)"); | const std::regex pieces_regex("([a-z]+)\\.([a-z]+)"); | ||
std::smatch pieces_match; | std::smatch pieces_match; | ||
− | + | ||
− | for (const auto &fname : fnames) | + | for (const auto& fname : fnames) |
− | + | ||
if (std::regex_match(fname, pieces_match, pieces_regex)) | if (std::regex_match(fname, pieces_match, pieces_regex)) | ||
{ | { | ||
std::cout << fname << '\n'; | std::cout << fname << '\n'; | ||
− | for (size_t i = 0; i < pieces_match.size(); ++i) | + | for (std::size_t i = 0; i < pieces_match.size(); ++i) |
{ | { | ||
std::ssub_match sub_match = pieces_match[i]; | std::ssub_match sub_match = pieces_match[i]; | ||
Line 190: | Line 237: | ||
} | } | ||
} | } | ||
− | |||
} | } | ||
|output= | |output= | ||
Line 215: | Line 261: | ||
===Defect reports=== | ===Defect reports=== | ||
{{dr list begin}} | {{dr list begin}} | ||
− | {{dr list item|wg=lwg|dr=2329|std=C++11|before={{tt|basic_string}} rvalues | + | {{dr list item|wg=lwg|dr=2205|std=C++11|before={{c|n}} could be zero in the postcondition|after=can only be positive}} |
+ | {{dr list item|wg=lwg|dr=2273|std=C++11|before=it was unclear whether partial matches are considered|after=only considers full matches}} | ||
+ | {{dr list item|wg=lwg|dr=2329|std=C++11|before=overload {{v|5}} accepted {{tt|basic_string}} rvalues,<br>which could result in dangling iterators|after=rejected via deleted overload {{v|7}}}} | ||
{{dr list end}} | {{dr list end}} | ||
Latest revision as of 18:55, 14 November 2024
Defined in header <regex>
|
||
template< class BidirIt, class Alloc, class CharT, class Traits > bool regex_match( BidirIt first, BidirIt last, |
(1) | (since C++11) |
template< class BidirIt, class CharT, class Traits > bool regex_match( BidirIt first, BidirIt last, |
(2) | (since C++11) |
template< class CharT, class Alloc, class Traits > bool regex_match( const CharT* str, |
(3) | (since C++11) |
template< class CharT, class Traits > bool regex_match( const CharT* str, const std::basic_regex<CharT, Traits>& e, |
(4) | (since C++11) |
template< class STraits, class SAlloc, class Alloc, class CharT, class Traits > |
(5) | (since C++11) |
template< class STraits, class SAlloc, class CharT, class Traits > bool regex_match( const std::basic_string<CharT, STraits, SAlloc>& s, |
(6) | (since C++11) |
template< class STraits, class SAlloc, class Alloc, class CharT, class Traits > |
(7) | (since C++11) |
Determines if the regular expression e matches the entire target character sequence. The detailed match result is stored in m (if present).
[
first,
last)
.
If |
(until C++23) |
If |
(since C++23) |
[
str,
str + std::char_traits<CharT>::length(str))
.If the match does not exist, the following expressions involving m (if exists) should yield the specified values:
Expression | Value |
---|---|
m.ready() | true |
m.size() | 0 |
m.empty() | true |
If the match exists, given any integer in (
0,
m.size())
as n, the following expressions involving m should yield the specified values for each overload listed below:
Expression | Value | ||
---|---|---|---|
Overload (1) | Overload (3) | Overload (5) | |
m.ready() | true | ||
m.size() | 1 + e.mark_count() | ||
m.empty() | false | ||
m.prefix().first | first | str | s.begin() |
m.prefix().second | |||
m.prefix().matched | false[1] | ||
m.suffix().first | last | std::char_traits<CharT>:: length(str) + str |
s.end() |
m.suffix().second | |||
m.suffix().matched | false[2] | ||
m[0].first | first | str | s.begin() |
m[0].second | last | std::char_traits<CharT>:: length(str) + str |
s.end() |
m[0].matched | true[3] | ||
m[n].first |
| ||
m[n].second |
| ||
m[n].matched |
|
Contents |
[edit] Parameters
first, last | - | the target character range |
str | - | the target null-terminated C-style string |
s | - | the target std::basic_string |
m | - | the match results |
e | - | the regular expression |
flags | - | flags used to determine how the match will be performed |
[edit] Return value
Returns true if the entire target sequence matches e, false otherwise.
[edit] Notes
Because regex_match
only considers full matches, the same regex may give different matches between regex_match
and std::regex_search:
std::regex re("Get|GetValue"); std::cmatch m; std::regex_search("GetValue", m, re); // returns true, and m[0] contains "Get" std::regex_match ("GetValue", m, re); // returns true, and m[0] contains "GetValue" std::regex_search("GetValues", m, re); // returns true, and m[0] contains "Get" std::regex_match ("GetValues", m, re); // returns false
[edit] Example
#include <cstddef> #include <iostream> #include <regex> #include <string> int main() { // Simple regular expression matching const std::string fnames[] = {"foo.txt", "bar.txt", "baz.dat", "zoidberg"}; const std::regex txt_regex("[a-z]+\\.txt"); for (const auto& fname : fnames) std::cout << fname << ": " << std::regex_match(fname, txt_regex) << '\n'; // Extraction of a sub-match const std::regex base_regex("([a-z]+)\\.txt"); std::smatch base_match; for (const auto& fname : fnames) if (std::regex_match(fname, base_match, base_regex)) // The first sub_match is the whole string; the next // sub_match is the first parenthesized expression. if (base_match.size() == 2) { std::ssub_match base_sub_match = base_match[1]; std::string base = base_sub_match.str(); std::cout << fname << " has a base of " << base << '\n'; } // Extraction of several sub-matches const std::regex pieces_regex("([a-z]+)\\.([a-z]+)"); std::smatch pieces_match; for (const auto& fname : fnames) if (std::regex_match(fname, pieces_match, pieces_regex)) { std::cout << fname << '\n'; for (std::size_t i = 0; i < pieces_match.size(); ++i) { std::ssub_match sub_match = pieces_match[i]; std::string piece = sub_match.str(); std::cout << " submatch " << i << ": " << piece << '\n'; } } }
Output:
foo.txt: 1 bar.txt: 1 baz.dat: 0 zoidberg: 0 foo.txt has a base of foo bar.txt has a base of bar foo.txt submatch 0: foo.txt submatch 1: foo submatch 2: txt bar.txt submatch 0: bar.txt submatch 1: bar submatch 2: txt baz.dat submatch 0: baz.dat submatch 1: baz submatch 2: dat
[edit] Defect reports
The following behavior-changing defect reports were applied retroactively to previously published C++ standards.
DR | Applied to | Behavior as published | Correct behavior |
---|---|---|---|
LWG 2205 | C++11 | n could be zero in the postcondition | can only be positive |
LWG 2273 | C++11 | it was unclear whether partial matches are considered | only considers full matches |
LWG 2329 | C++11 | overload (5) accepted basic_string rvalues,which could result in dangling iterators |
rejected via deleted overload (7) |
[edit] See also
(C++11) |
regular expression object (class template) |
(C++11) |
identifies one regular expression match, including all sub-expression matches (class template) |
(C++11) |
attempts to match a regular expression to any part of a character sequence (function template) |