1 // class template regex -*- C++ -*-
3 // Copyright (C) 2010-2013 Free Software Foundation, Inc.
5 // This file is part of the GNU ISO C++ Library. This library is free
6 // software; you can redistribute it and/or modify it under the
7 // terms of the GNU General Public License as published by the
8 // Free Software Foundation; either version 3, or (at your option)
11 // This library is distributed in the hope that it will be useful,
12 // but WITHOUT ANY WARRANTY; without even the implied warranty of
13 // MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
14 // GNU General Public License for more details.
16 // Under Section 7 of GPL version 3, you are granted additional
17 // permissions described in the GCC Runtime Library Exception, version
18 // 3.1, as published by the Free Software Foundation.
20 // You should have received a copy of the GNU General Public License and
21 // a copy of the GCC Runtime Library Exception along with this program;
22 // see the files COPYING3 and COPYING.RUNTIME respectively. If not, see
23 // <http://www.gnu.org/licenses/>.
26 * @file bits/regex_constants.h
27 * @brief Constant definitions for the std regex library.
29 * This is an internal header file, included by other library headers.
30 * Do not attempt to use it directly. @headername{regex}
33 namespace std _GLIBCXX_VISIBILITY(default)
36 * @defgroup regex Regular Expressions
38 * A facility for performing regular expression pattern matching.
43 * @namespace std::regex_constants
44 * @brief ISO C++-0x entities sub namespace for regex.
46 namespace regex_constants
48 _GLIBCXX_BEGIN_NAMESPACE_VERSION
51 * @name 5.1 Regular Expression Syntax Options
70 * @brief This is a bitmask type indicating how to interpret the regex.
72 * The @c syntax_option_type is implementation defined but it is valid to
73 * perform bitwise operations on these values and expect the right thing to
76 * A valid value of type syntax_option_type shall have exactly one of the
77 * elements @c ECMAScript, @c basic, @c extended, @c awk, @c grep, @c egrep
80 typedef unsigned int syntax_option_type;
83 * Specifies that the matching of regular expressions against a character
84 * sequence shall be performed without regard to case.
86 constexpr syntax_option_type icase = 1 << _S_icase;
89 * Specifies that when a regular expression is matched against a character
90 * container sequence, no sub-expression matches are to be stored in the
91 * supplied match_results structure.
93 constexpr syntax_option_type nosubs = 1 << _S_nosubs;
96 * Specifies that the regular expression engine should pay more attention to
97 * the speed with which regular expressions are matched, and less to the
98 * speed with which regular expression objects are constructed. Otherwise
99 * it has no detectable effect on the program output.
101 constexpr syntax_option_type optimize = 1 << _S_optimize;
104 * Specifies that character ranges of the form [a-b] should be locale
107 constexpr syntax_option_type collate = 1 << _S_collate;
110 * Specifies that the grammar recognized by the regular expression engine is
111 * that used by ECMAScript in ECMA-262 [Ecma International, ECMAScript
112 * Language Specification, Standard Ecma-262, third edition, 1999], as
113 * modified in section [28.13]. This grammar is similar to that defined
114 * in the PERL scripting language but extended with elements found in the
115 * POSIX regular expression grammar.
117 constexpr syntax_option_type ECMAScript = 1 << _S_ECMAScript;
120 * Specifies that the grammar recognized by the regular expression engine is
121 * that used by POSIX basic regular expressions in IEEE Std 1003.1-2001,
122 * Portable Operating System Interface (POSIX), Base Definitions and
123 * Headers, Section 9, Regular Expressions [IEEE, Information Technology --
124 * Portable Operating System Interface (POSIX), IEEE Standard 1003.1-2001].
126 constexpr syntax_option_type basic = 1 << _S_basic;
129 * Specifies that the grammar recognized by the regular expression engine is
130 * that used by POSIX extended regular expressions in IEEE Std 1003.1-2001,
131 * Portable Operating System Interface (POSIX), Base Definitions and Headers,
132 * Section 9, Regular Expressions.
134 constexpr syntax_option_type extended = 1 << _S_extended;
137 * Specifies that the grammar recognized by the regular expression engine is
138 * that used by POSIX utility awk in IEEE Std 1003.1-2001. This option is
139 * identical to syntax_option_type extended, except that C-style escape
140 * sequences are supported. These sequences are:
141 * \\\\, \\a, \\b, \\f, \\n, \\r, \\t , \\v, \\', ',
142 * and \\ddd (where ddd is one, two, or three octal digits).
144 constexpr syntax_option_type awk = 1 << _S_awk;
147 * Specifies that the grammar recognized by the regular expression engine is
148 * that used by POSIX utility grep in IEEE Std 1003.1-2001. This option is
149 * identical to syntax_option_type basic, except that newlines are treated
152 constexpr syntax_option_type grep = 1 << _S_grep;
155 * Specifies that the grammar recognized by the regular expression engine is
156 * that used by POSIX utility grep when given the -E option in
157 * IEEE Std 1003.1-2001. This option is identical to syntax_option_type
158 * extended, except that newlines are treated as whitespace.
160 constexpr syntax_option_type egrep = 1 << _S_egrep;
165 * @name 5.2 Matching Rules
167 * Matching a regular expression against a sequence of characters [first,
168 * last) proceeds according to the rules of the grammar specified for the
169 * regular expression object, modified according to the effects listed
170 * below for any bitmask elements set.
192 * @brief This is a bitmask type indicating regex matching rules.
194 * The @c match_flag_type is implementation defined but it is valid to
195 * perform bitwise operations on these values and expect the right thing to
198 typedef std::bitset<_S_match_flag_last> match_flag_type;
201 * The default matching rules.
203 constexpr match_flag_type match_default = 0;
206 * The first character in the sequence [first, last) is treated as though it
207 * is not at the beginning of a line, so the character (^) in the regular
208 * expression shall not match [first, first).
210 constexpr match_flag_type match_not_bol = 1 << _S_not_bol;
213 * The last character in the sequence [first, last) is treated as though it
214 * is not at the end of a line, so the character ($) in the regular
215 * expression shall not match [last, last).
217 constexpr match_flag_type match_not_eol = 1 << _S_not_eol;
220 * The expression \\b is not matched against the sub-sequence
223 constexpr match_flag_type match_not_bow = 1 << _S_not_bow;
226 * The expression \\b should not be matched against the sub-sequence
229 constexpr match_flag_type match_not_eow = 1 << _S_not_eow;
232 * If more than one match is possible then any match is an acceptable
235 constexpr match_flag_type match_any = 1 << _S_any;
238 * The expression does not match an empty sequence.
240 constexpr match_flag_type match_not_null = 1 << _S_not_null;
243 * The expression only matches a sub-sequence that begins at first .
245 constexpr match_flag_type match_continuous = 1 << _S_continuous;
248 * --first is a valid iterator position. When this flag is set then the
249 * flags match_not_bol and match_not_bow are ignored by the regular
250 * expression algorithms 28.11 and iterators 28.12.
252 constexpr match_flag_type match_prev_avail = 1 << _S_prev_avail;
255 * When a regular expression match is to be replaced by a new string, the
256 * new string is constructed using the rules used by the ECMAScript replace
257 * function in ECMA- 262 [Ecma International, ECMAScript Language
258 * Specification, Standard Ecma-262, third edition, 1999], part 15.5.4.11
259 * String.prototype.replace. In addition, during search and replace
260 * operations all non-overlapping occurrences of the regular expression
261 * are located and replaced, and sections of the input that did not match
262 * the expression are copied unchanged to the output string.
264 * Format strings (from ECMA-262 [15.5.4.11]):
265 * @li $$ The dollar-sign itself ($)
266 * @li $& The matched substring.
267 * @li $` The portion of @a string that precedes the matched substring.
268 * This would be match_results::prefix().
269 * @li $' The portion of @a string that follows the matched substring.
270 * This would be match_results::suffix().
271 * @li $n The nth capture, where n is in [1,9] and $n is not followed by a
272 * decimal digit. If n <= match_results::size() and the nth capture
273 * is undefined, use the empty string instead. If n >
274 * match_results::size(), the result is implementation-defined.
275 * @li $nn The nnth capture, where nn is a two-digit decimal number on
276 * [01, 99]. If nn <= match_results::size() and the nth capture is
277 * undefined, use the empty string instead. If
278 * nn > match_results::size(), the result is implementation-defined.
280 constexpr match_flag_type format_default = 0;
283 * When a regular expression match is to be replaced by a new string, the
284 * new string is constructed using the rules used by the POSIX sed utility
285 * in IEEE Std 1003.1- 2001 [IEEE, Information Technology -- Portable
286 * Operating System Interface (POSIX), IEEE Standard 1003.1-2001].
288 constexpr match_flag_type format_sed = 1 << _S_sed;
291 * During a search and replace operation, sections of the character
292 * container sequence being searched that do not match the regular
293 * expression shall not be copied to the output string.
295 constexpr match_flag_type format_no_copy = 1 << _S_no_copy;
298 * When specified during a search and replace operation, only the first
299 * occurrence of the regular expression shall be replaced.
301 constexpr match_flag_type format_first_only = 1 << _S_first_only;
305 _GLIBCXX_END_NAMESPACE_VERSION
306 } // namespace regex_constants
308 /* @} */ // group regex