1// class template regex -*- C++ -*-
2
3// Copyright (C) 2010-2021 Free Software Foundation, Inc.
4//
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)
9// any later version.
10
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.
15
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.
19
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/>.
24
25/**
26 * @file bits/regex_constants.h
27 * @brief Constant definitions for the std regex library.
28 *
29 * This is an internal header file, included by other library headers.
30 * Do not attempt to use it directly. @headername{regex}
31 */
32
33namespace std _GLIBCXX_VISIBILITY(default)
34{
35_GLIBCXX_BEGIN_NAMESPACE_VERSION
36
37/**
38 * @defgroup regex Regular Expressions
39 *
40 * A facility for performing regular expression pattern matching.
41 * @{
42 */
43
44/**
45 * @namespace std::regex_constants
46 * @brief ISO C++ 2011 namespace for options and flags used with std::regex
47 */
48namespace regex_constants
49{
50 /**
51 * @name 5.1 Regular Expression Syntax Options
52 */
53 ///@{
54 enum __syntax_option
55 {
56 _S_icase,
57 _S_nosubs,
58 _S_optimize,
59 _S_collate,
60 _S_ECMAScript,
61 _S_basic,
62 _S_extended,
63 _S_awk,
64 _S_grep,
65 _S_egrep,
66 _S_polynomial,
67 _S_syntax_last
68 };
69
70 /**
71 * @brief This is a bitmask type indicating how to interpret the regex.
72 *
73 * The @c syntax_option_type is implementation defined but it is valid to
74 * perform bitwise operations on these values and expect the right thing to
75 * happen.
76 *
77 * A valid value of type syntax_option_type shall have exactly one of the
78 * elements @c ECMAScript, @c basic, @c extended, @c awk, @c grep, @c egrep
79 * %set.
80 */
81 enum syntax_option_type : unsigned int { };
82
83 /**
84 * Specifies that the matching of regular expressions against a character
85 * sequence shall be performed without regard to case.
86 */
87 _GLIBCXX17_INLINE constexpr syntax_option_type icase =
88 static_cast<syntax_option_type>(1 << _S_icase);
89
90 /**
91 * Specifies that when a regular expression is matched against a character
92 * container sequence, no sub-expression matches are to be stored in the
93 * supplied match_results structure.
94 */
95 _GLIBCXX17_INLINE constexpr syntax_option_type nosubs =
96 static_cast<syntax_option_type>(1 << _S_nosubs);
97
98 /**
99 * Specifies that the regular expression engine should pay more attention to
100 * the speed with which regular expressions are matched, and less to the
101 * speed with which regular expression objects are constructed. Otherwise
102 * it has no detectable effect on the program output.
103 */
104 _GLIBCXX17_INLINE constexpr syntax_option_type optimize =
105 static_cast<syntax_option_type>(1 << _S_optimize);
106
107 /**
108 * Specifies that character ranges of the form [a-b] should be locale
109 * sensitive.
110 */
111 _GLIBCXX17_INLINE constexpr syntax_option_type collate =
112 static_cast<syntax_option_type>(1 << _S_collate);
113
114 /**
115 * Specifies that the grammar recognized by the regular expression engine is
116 * that used by ECMAScript in ECMA-262 [Ecma International, ECMAScript
117 * Language Specification, Standard Ecma-262, third edition, 1999], as
118 * modified in section [28.13]. This grammar is similar to that defined
119 * in the PERL scripting language but extended with elements found in the
120 * POSIX regular expression grammar.
121 */
122 _GLIBCXX17_INLINE constexpr syntax_option_type ECMAScript =
123 static_cast<syntax_option_type>(1 << _S_ECMAScript);
124
125 /**
126 * Specifies that the grammar recognized by the regular expression engine is
127 * that used by POSIX basic regular expressions in IEEE Std 1003.1-2001,
128 * Portable Operating System Interface (POSIX), Base Definitions and
129 * Headers, Section 9, Regular Expressions [IEEE, Information Technology --
130 * Portable Operating System Interface (POSIX), IEEE Standard 1003.1-2001].
131 */
132 _GLIBCXX17_INLINE constexpr syntax_option_type basic =
133 static_cast<syntax_option_type>(1 << _S_basic);
134
135 /**
136 * Specifies that the grammar recognized by the regular expression engine is
137 * that used by POSIX extended regular expressions in IEEE Std 1003.1-2001,
138 * Portable Operating System Interface (POSIX), Base Definitions and
139 * Headers, Section 9, Regular Expressions.
140 */
141 _GLIBCXX17_INLINE constexpr syntax_option_type extended =
142 static_cast<syntax_option_type>(1 << _S_extended);
143
144 /**
145 * Specifies that the grammar recognized by the regular expression engine is
146 * that used by POSIX utility awk in IEEE Std 1003.1-2001. This option is
147 * identical to syntax_option_type extended, except that C-style escape
148 * sequences are supported. These sequences are:
149 * \\\\, \\a, \\b, \\f, \\n, \\r, \\t , \\v, \\&apos,, &apos,,
150 * and \\ddd (where ddd is one, two, or three octal digits).
151 */
152 _GLIBCXX17_INLINE constexpr syntax_option_type awk =
153 static_cast<syntax_option_type>(1 << _S_awk);
154
155 /**
156 * Specifies that the grammar recognized by the regular expression engine is
157 * that used by POSIX utility grep in IEEE Std 1003.1-2001. This option is
158 * identical to syntax_option_type basic, except that newlines are treated
159 * as whitespace.
160 */
161 _GLIBCXX17_INLINE constexpr syntax_option_type grep =
162 static_cast<syntax_option_type>(1 << _S_grep);
163
164 /**
165 * Specifies that the grammar recognized by the regular expression engine is
166 * that used by POSIX utility grep when given the -E option in
167 * IEEE Std 1003.1-2001. This option is identical to syntax_option_type
168 * extended, except that newlines are treated as whitespace.
169 */
170 _GLIBCXX17_INLINE constexpr syntax_option_type egrep =
171 static_cast<syntax_option_type>(1 << _S_egrep);
172
173 /**
174 * Extension: Ensure both space complexity of compiled regex and
175 * time complexity execution are not exponential.
176 * If specified in a regex with back-references, the exception
177 * regex_constants::error_complexity will be thrown.
178 */
179 _GLIBCXX17_INLINE constexpr syntax_option_type __polynomial =
180 static_cast<syntax_option_type>(1 << _S_polynomial);
181
182 constexpr inline syntax_option_type
183 operator&(syntax_option_type __a, syntax_option_type __b)
184 {
185 return (syntax_option_type)(static_cast<unsigned int>(__a)
186 & static_cast<unsigned int>(__b));
187 }
188
189 constexpr inline syntax_option_type
190 operator|(syntax_option_type __a, syntax_option_type __b)
191 {
192 return (syntax_option_type)(static_cast<unsigned int>(__a)
193 | static_cast<unsigned int>(__b));
194 }
195
196 constexpr inline syntax_option_type
197 operator^(syntax_option_type __a, syntax_option_type __b)
198 {
199 return (syntax_option_type)(static_cast<unsigned int>(__a)
200 ^ static_cast<unsigned int>(__b));
201 }
202
203 constexpr inline syntax_option_type
204 operator~(syntax_option_type __a)
205 { return (syntax_option_type)(~static_cast<unsigned int>(__a)); }
206
207 inline syntax_option_type&
208 operator&=(syntax_option_type& __a, syntax_option_type __b)
209 { return __a = __a & __b; }
210
211 inline syntax_option_type&
212 operator|=(syntax_option_type& __a, syntax_option_type __b)
213 { return __a = __a | __b; }
214
215 inline syntax_option_type&
216 operator^=(syntax_option_type& __a, syntax_option_type __b)
217 { return __a = __a ^ __b; }
218
219 ///@}
220
221 /**
222 * @name 5.2 Matching Rules
223 *
224 * Matching a regular expression against a sequence of characters [first,
225 * last) proceeds according to the rules of the grammar specified for the
226 * regular expression object, modified according to the effects listed
227 * below for any bitmask elements set.
228 *
229 */
230 ///@{
231
232 enum __match_flag
233 {
234 _S_not_bol,
235 _S_not_eol,
236 _S_not_bow,
237 _S_not_eow,
238 _S_any,
239 _S_not_null,
240 _S_continuous,
241 _S_prev_avail,
242 _S_sed,
243 _S_no_copy,
244 _S_first_only,
245 _S_match_flag_last
246 };
247
248 /**
249 * @brief This is a bitmask type indicating regex matching rules.
250 *
251 * The @c match_flag_type is implementation defined but it is valid to
252 * perform bitwise operations on these values and expect the right thing to
253 * happen.
254 */
255 enum match_flag_type : unsigned int { };
256
257 /**
258 * The default matching rules.
259 */
260 _GLIBCXX17_INLINE constexpr match_flag_type match_default =
261 static_cast<match_flag_type>(0);
262
263 /**
264 * The first character in the sequence [first, last) is treated as though it
265 * is not at the beginning of a line, so the character (^) in the regular
266 * expression shall not match [first, first).
267 */
268 _GLIBCXX17_INLINE constexpr match_flag_type match_not_bol =
269 static_cast<match_flag_type>(1 << _S_not_bol);
270
271 /**
272 * The last character in the sequence [first, last) is treated as though it
273 * is not at the end of a line, so the character ($) in the regular
274 * expression shall not match [last, last).
275 */
276 _GLIBCXX17_INLINE constexpr match_flag_type match_not_eol =
277 static_cast<match_flag_type>(1 << _S_not_eol);
278
279 /**
280 * The expression \\b is not matched against the sub-sequence
281 * [first,first).
282 */
283 _GLIBCXX17_INLINE constexpr match_flag_type match_not_bow =
284 static_cast<match_flag_type>(1 << _S_not_bow);
285
286 /**
287 * The expression \\b should not be matched against the sub-sequence
288 * [last,last).
289 */
290 _GLIBCXX17_INLINE constexpr match_flag_type match_not_eow =
291 static_cast<match_flag_type>(1 << _S_not_eow);
292
293 /**
294 * If more than one match is possible then any match is an acceptable
295 * result.
296 */
297 _GLIBCXX17_INLINE constexpr match_flag_type match_any =
298 static_cast<match_flag_type>(1 << _S_any);
299
300 /**
301 * The expression does not match an empty sequence.
302 */
303 _GLIBCXX17_INLINE constexpr match_flag_type match_not_null =
304 static_cast<match_flag_type>(1 << _S_not_null);
305
306 /**
307 * The expression only matches a sub-sequence that begins at first .
308 */
309 _GLIBCXX17_INLINE constexpr match_flag_type match_continuous =
310 static_cast<match_flag_type>(1 << _S_continuous);
311
312 /**
313 * --first is a valid iterator position. When this flag is set then the
314 * flags match_not_bol and match_not_bow are ignored by the regular
315 * expression algorithms 28.11 and iterators 28.12.
316 */
317 _GLIBCXX17_INLINE constexpr match_flag_type match_prev_avail =
318 static_cast<match_flag_type>(1 << _S_prev_avail);
319
320 /**
321 * When a regular expression match is to be replaced by a new string, the
322 * new string is constructed using the rules used by the ECMAScript replace
323 * function in ECMA- 262 [Ecma International, ECMAScript Language
324 * Specification, Standard Ecma-262, third edition, 1999], part 15.5.4.11
325 * String.prototype.replace. In addition, during search and replace
326 * operations all non-overlapping occurrences of the regular expression
327 * are located and replaced, and sections of the input that did not match
328 * the expression are copied unchanged to the output string.
329 *
330 * Format strings (from ECMA-262 [15.5.4.11]):
331 * @li $$ The dollar-sign itself ($)
332 * @li $& The matched substring.
333 * @li $` The portion of @a string that precedes the matched substring.
334 * This would be match_results::prefix().
335 * @li $' The portion of @a string that follows the matched substring.
336 * This would be match_results::suffix().
337 * @li $n The nth capture, where n is in [1,9] and $n is not followed by a
338 * decimal digit. If n <= match_results::size() and the nth capture
339 * is undefined, use the empty string instead. If n >
340 * match_results::size(), the result is implementation-defined.
341 * @li $nn The nnth capture, where nn is a two-digit decimal number on
342 * [01, 99]. If nn <= match_results::size() and the nth capture is
343 * undefined, use the empty string instead. If
344 * nn > match_results::size(), the result is implementation-defined.
345 */
346 _GLIBCXX17_INLINE constexpr match_flag_type format_default =
347 static_cast<match_flag_type>(0);
348
349 /**
350 * When a regular expression match is to be replaced by a new string, the
351 * new string is constructed using the rules used by the POSIX sed utility
352 * in IEEE Std 1003.1- 2001 [IEEE, Information Technology -- Portable
353 * Operating System Interface (POSIX), IEEE Standard 1003.1-2001].
354 */
355 _GLIBCXX17_INLINE constexpr match_flag_type format_sed =
356 static_cast<match_flag_type>(1 << _S_sed);
357
358 /**
359 * During a search and replace operation, sections of the character
360 * container sequence being searched that do not match the regular
361 * expression shall not be copied to the output string.
362 */
363 _GLIBCXX17_INLINE constexpr match_flag_type format_no_copy =
364 static_cast<match_flag_type>(1 << _S_no_copy);
365
366 /**
367 * When specified during a search and replace operation, only the first
368 * occurrence of the regular expression shall be replaced.
369 */
370 _GLIBCXX17_INLINE constexpr match_flag_type format_first_only =
371 static_cast<match_flag_type>(1 << _S_first_only);
372
373 constexpr inline match_flag_type
374 operator&(match_flag_type __a, match_flag_type __b)
375 {
376 return (match_flag_type)(static_cast<unsigned int>(__a)
377 & static_cast<unsigned int>(__b));
378 }
379
380 constexpr inline match_flag_type
381 operator|(match_flag_type __a, match_flag_type __b)
382 {
383 return (match_flag_type)(static_cast<unsigned int>(__a)
384 | static_cast<unsigned int>(__b));
385 }
386
387 constexpr inline match_flag_type
388 operator^(match_flag_type __a, match_flag_type __b)
389 {
390 return (match_flag_type)(static_cast<unsigned int>(__a)
391 ^ static_cast<unsigned int>(__b));
392 }
393
394 constexpr inline match_flag_type
395 operator~(match_flag_type __a)
396 { return (match_flag_type)(~static_cast<unsigned int>(__a)); }
397
398 inline match_flag_type&
399 operator&=(match_flag_type& __a, match_flag_type __b)
400 { return __a = __a & __b; }
401
402 inline match_flag_type&
403 operator|=(match_flag_type& __a, match_flag_type __b)
404 { return __a = __a | __b; }
405
406 inline match_flag_type&
407 operator^=(match_flag_type& __a, match_flag_type __b)
408 { return __a = __a ^ __b; }
409
410 ///@}
411} // namespace regex_constants
412/// @} group regex
413
414_GLIBCXX_END_NAMESPACE_VERSION
415} // namespace std
416
417