1 /* GRegex -- regular expression API wrapper around PCRE.
3 * Copyright (C) 1999, 2000 Scott Wimer
4 * Copyright (C) 2004, Matthias Clasen <mclasen@redhat.com>
5 * Copyright (C) 2005 - 2007, Marco Barisione <marco@barisione.org>
7 * This library is free software; you can redistribute it and/or
8 * modify it under the terms of the GNU Lesser General Public
9 * License as published by the Free Software Foundation; either
10 * version 2.1 of the License, or (at your option) any later version.
12 * This library is distributed in the hope that it will be useful,
13 * but WITHOUT ANY WARRANTY; without even the implied warranty of
14 * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
15 * Lesser General Public License for more details.
17 * You should have received a copy of the GNU Lesser General Public
18 * License along with this library; if not, write to the Free Software
19 * Foundation, Inc., 51 Franklin St, Fifth Floor, Boston, MA 02110-1301 USA
22 #if !defined (__GLIB_H_INSIDE__) && !defined (GLIB_COMPILATION)
23 #error "Only <glib.h> can be included directly."
29 #include <glib/gerror.h>
30 #include <glib/gstring.h>
36 * @G_REGEX_ERROR_COMPILE: Compilation of the regular expression failed.
37 * @G_REGEX_ERROR_OPTIMIZE: Optimization of the regular expression failed.
38 * @G_REGEX_ERROR_REPLACE: Replacement failed due to an ill-formed replacement
40 * @G_REGEX_ERROR_MATCH: The match process failed.
41 * @G_REGEX_ERROR_INTERNAL: Internal error of the regular expression engine.
43 * @G_REGEX_ERROR_STRAY_BACKSLASH: "\\" at end of pattern. Since 2.16
44 * @G_REGEX_ERROR_MISSING_CONTROL_CHAR: "\\c" at end of pattern. Since 2.16
45 * @G_REGEX_ERROR_UNRECOGNIZED_ESCAPE: Unrecognized character follows "\\".
47 * @G_REGEX_ERROR_QUANTIFIERS_OUT_OF_ORDER: Numbers out of order in "{}"
48 * quantifier. Since 2.16
49 * @G_REGEX_ERROR_QUANTIFIER_TOO_BIG: Number too big in "{}" quantifier.
51 * @G_REGEX_ERROR_UNTERMINATED_CHARACTER_CLASS: Missing terminating "]" for
52 * character class. Since 2.16
53 * @G_REGEX_ERROR_INVALID_ESCAPE_IN_CHARACTER_CLASS: Invalid escape sequence
54 * in character class. Since 2.16
55 * @G_REGEX_ERROR_RANGE_OUT_OF_ORDER: Range out of order in character class.
57 * @G_REGEX_ERROR_NOTHING_TO_REPEAT: Nothing to repeat. Since 2.16
58 * @G_REGEX_ERROR_UNRECOGNIZED_CHARACTER: Unrecognized character after "(?",
59 * "(?<" or "(?P". Since 2.16
60 * @G_REGEX_ERROR_POSIX_NAMED_CLASS_OUTSIDE_CLASS: POSIX named classes are
61 * supported only within a class. Since 2.16
62 * @G_REGEX_ERROR_UNMATCHED_PARENTHESIS: Missing terminating ")" or ")"
63 * without opening "(". Since 2.16
64 * @G_REGEX_ERROR_INEXISTENT_SUBPATTERN_REFERENCE: Reference to non-existent
65 * subpattern. Since 2.16
66 * @G_REGEX_ERROR_UNTERMINATED_COMMENT: Missing terminating ")" after comment.
68 * @G_REGEX_ERROR_EXPRESSION_TOO_LARGE: Regular expression too large.
70 * @G_REGEX_ERROR_MEMORY_ERROR: Failed to get memory. Since 2.16
71 * @G_REGEX_ERROR_VARIABLE_LENGTH_LOOKBEHIND: Lookbehind assertion is not
72 * fixed length. Since 2.16
73 * @G_REGEX_ERROR_MALFORMED_CONDITION: Malformed number or name after "(?(".
75 * @G_REGEX_ERROR_TOO_MANY_CONDITIONAL_BRANCHES: Conditional group contains
76 * more than two branches. Since 2.16
77 * @G_REGEX_ERROR_ASSERTION_EXPECTED: Assertion expected after "(?(".
79 * @G_REGEX_ERROR_UNKNOWN_POSIX_CLASS_NAME: Unknown POSIX class name.
81 * @G_REGEX_ERROR_POSIX_COLLATING_ELEMENTS_NOT_SUPPORTED: POSIX collating
82 * elements are not supported. Since 2.16
83 * @G_REGEX_ERROR_HEX_CODE_TOO_LARGE: Character value in "\\x{...}" sequence
84 * is too large. Since 2.16
85 * @G_REGEX_ERROR_INVALID_CONDITION: Invalid condition "(?(0)". Since 2.16
86 * @G_REGEX_ERROR_SINGLE_BYTE_MATCH_IN_LOOKBEHIND: \\C not allowed in
87 * lookbehind assertion. Since 2.16
88 * @G_REGEX_ERROR_INFINITE_LOOP: Recursive call could loop indefinitely.
90 * @G_REGEX_ERROR_MISSING_SUBPATTERN_NAME_TERMINATOR: Missing terminator
91 * in subpattern name. Since 2.16
92 * @G_REGEX_ERROR_DUPLICATE_SUBPATTERN_NAME: Two named subpatterns have
93 * the same name. Since 2.16
94 * @G_REGEX_ERROR_MALFORMED_PROPERTY: Malformed "\\P" or "\\p" sequence.
96 * @G_REGEX_ERROR_UNKNOWN_PROPERTY: Unknown property name after "\\P" or
98 * @G_REGEX_ERROR_SUBPATTERN_NAME_TOO_LONG: Subpattern name is too long
99 * (maximum 32 characters). Since 2.16
100 * @G_REGEX_ERROR_TOO_MANY_SUBPATTERNS: Too many named subpatterns (maximum
101 * 10,000). Since 2.16
102 * @G_REGEX_ERROR_INVALID_OCTAL_VALUE: Octal value is greater than "\\377".
104 * @G_REGEX_ERROR_TOO_MANY_BRANCHES_IN_DEFINE: "DEFINE" group contains more
105 * than one branch. Since 2.16
106 * @G_REGEX_ERROR_DEFINE_REPETION: Repeating a "DEFINE" group is not allowed.
107 * This error is never raised. Since: 2.16 Deprecated: 2.34
108 * @G_REGEX_ERROR_INCONSISTENT_NEWLINE_OPTIONS: Inconsistent newline options.
110 * @G_REGEX_ERROR_MISSING_BACK_REFERENCE: "\\g" is not followed by a braced,
111 * angle-bracketed, or quoted name or number, or by a plain number. Since: 2.16
112 * @G_REGEX_ERROR_INVALID_RELATIVE_REFERENCE: relative reference must not be zero. Since: 2.34
113 * @G_REGEX_ERROR_BACKTRACKING_CONTROL_VERB_ARGUMENT_FORBIDDEN: the backtracing
114 * control verb used does not allow an argument. Since: 2.34
115 * @G_REGEX_ERROR_UNKNOWN_BACKTRACKING_CONTROL_VERB: unknown backtracing
116 * control verb. Since: 2.34
117 * @G_REGEX_ERROR_NUMBER_TOO_BIG: number is too big in escape sequence. Since: 2.34
118 * @G_REGEX_ERROR_MISSING_SUBPATTERN_NAME: Missing subpattern name. Since: 2.34
119 * @G_REGEX_ERROR_INVALID_DATA_CHARACTER: In JavaScript compatibility mode,
120 * "[" is an invalid data character. Since: 2.34
121 * @G_REGEX_ERROR_EXTRA_SUBPATTERN_NAME: different names for subpatterns of the
122 * same number are not allowed. Since: 2.34
123 * @G_REGEX_ERROR_BACKTRACKING_CONTROL_VERB_ARGUMENT_REQUIRED: the backtracing control
124 * verb requires an argument. Since: 2.34
125 * @G_REGEX_ERROR_INVALID_CONTROL_CHAR: "\\c" must be followed by an ASCII
126 * character. Since: 2.34
127 * @G_REGEX_ERROR_MISSING_NAME: "\\k" is not followed by a braced, angle-bracketed, or
128 * quoted name. Since: 2.34
129 * @G_REGEX_ERROR_NOT_SUPPORTED_IN_CLASS: "\\N" is not supported in a class. Since: 2.34
130 * @G_REGEX_ERROR_TOO_MANY_FORWARD_REFERENCES: too many forward references. Since: 2.34
131 * @G_REGEX_ERROR_NAME_TOO_LONG: the name is too long in "(*MARK)", "(*PRUNE)",
132 * "(*SKIP)", or "(*THEN)". Since: 2.34
134 * Error codes returned by regular expressions functions.
140 G_REGEX_ERROR_COMPILE,
141 G_REGEX_ERROR_OPTIMIZE,
142 G_REGEX_ERROR_REPLACE,
144 G_REGEX_ERROR_INTERNAL,
146 /* These are the error codes from PCRE + 100 */
147 G_REGEX_ERROR_STRAY_BACKSLASH = 101,
148 G_REGEX_ERROR_MISSING_CONTROL_CHAR = 102,
149 G_REGEX_ERROR_UNRECOGNIZED_ESCAPE = 103,
150 G_REGEX_ERROR_QUANTIFIERS_OUT_OF_ORDER = 104,
151 G_REGEX_ERROR_QUANTIFIER_TOO_BIG = 105,
152 G_REGEX_ERROR_UNTERMINATED_CHARACTER_CLASS = 106,
153 G_REGEX_ERROR_INVALID_ESCAPE_IN_CHARACTER_CLASS = 107,
154 G_REGEX_ERROR_RANGE_OUT_OF_ORDER = 108,
155 G_REGEX_ERROR_NOTHING_TO_REPEAT = 109,
156 G_REGEX_ERROR_UNRECOGNIZED_CHARACTER = 112,
157 G_REGEX_ERROR_POSIX_NAMED_CLASS_OUTSIDE_CLASS = 113,
158 G_REGEX_ERROR_UNMATCHED_PARENTHESIS = 114,
159 G_REGEX_ERROR_INEXISTENT_SUBPATTERN_REFERENCE = 115,
160 G_REGEX_ERROR_UNTERMINATED_COMMENT = 118,
161 G_REGEX_ERROR_EXPRESSION_TOO_LARGE = 120,
162 G_REGEX_ERROR_MEMORY_ERROR = 121,
163 G_REGEX_ERROR_VARIABLE_LENGTH_LOOKBEHIND = 125,
164 G_REGEX_ERROR_MALFORMED_CONDITION = 126,
165 G_REGEX_ERROR_TOO_MANY_CONDITIONAL_BRANCHES = 127,
166 G_REGEX_ERROR_ASSERTION_EXPECTED = 128,
167 G_REGEX_ERROR_UNKNOWN_POSIX_CLASS_NAME = 130,
168 G_REGEX_ERROR_POSIX_COLLATING_ELEMENTS_NOT_SUPPORTED = 131,
169 G_REGEX_ERROR_HEX_CODE_TOO_LARGE = 134,
170 G_REGEX_ERROR_INVALID_CONDITION = 135,
171 G_REGEX_ERROR_SINGLE_BYTE_MATCH_IN_LOOKBEHIND = 136,
172 G_REGEX_ERROR_INFINITE_LOOP = 140,
173 G_REGEX_ERROR_MISSING_SUBPATTERN_NAME_TERMINATOR = 142,
174 G_REGEX_ERROR_DUPLICATE_SUBPATTERN_NAME = 143,
175 G_REGEX_ERROR_MALFORMED_PROPERTY = 146,
176 G_REGEX_ERROR_UNKNOWN_PROPERTY = 147,
177 G_REGEX_ERROR_SUBPATTERN_NAME_TOO_LONG = 148,
178 G_REGEX_ERROR_TOO_MANY_SUBPATTERNS = 149,
179 G_REGEX_ERROR_INVALID_OCTAL_VALUE = 151,
180 G_REGEX_ERROR_TOO_MANY_BRANCHES_IN_DEFINE = 154,
181 G_REGEX_ERROR_DEFINE_REPETION = 155,
182 G_REGEX_ERROR_INCONSISTENT_NEWLINE_OPTIONS = 156,
183 G_REGEX_ERROR_MISSING_BACK_REFERENCE = 157,
184 G_REGEX_ERROR_INVALID_RELATIVE_REFERENCE = 158,
185 G_REGEX_ERROR_BACKTRACKING_CONTROL_VERB_ARGUMENT_FORBIDDEN = 159,
186 G_REGEX_ERROR_UNKNOWN_BACKTRACKING_CONTROL_VERB = 160,
187 G_REGEX_ERROR_NUMBER_TOO_BIG = 161,
188 G_REGEX_ERROR_MISSING_SUBPATTERN_NAME = 162,
189 G_REGEX_ERROR_MISSING_DIGIT = 163,
190 G_REGEX_ERROR_INVALID_DATA_CHARACTER = 164,
191 G_REGEX_ERROR_EXTRA_SUBPATTERN_NAME = 165,
192 G_REGEX_ERROR_BACKTRACKING_CONTROL_VERB_ARGUMENT_REQUIRED = 166,
193 G_REGEX_ERROR_INVALID_CONTROL_CHAR = 168,
194 G_REGEX_ERROR_MISSING_NAME = 169,
195 G_REGEX_ERROR_NOT_SUPPORTED_IN_CLASS = 171,
196 G_REGEX_ERROR_TOO_MANY_FORWARD_REFERENCES = 172,
197 G_REGEX_ERROR_NAME_TOO_LONG = 175
203 * Error domain for regular expressions. Errors in this domain will be
204 * from the #GRegexError enumeration. See #GError for information on
209 #define G_REGEX_ERROR g_regex_error_quark ()
211 GQuark g_regex_error_quark (void);
214 * GRegexCompileFlags:
215 * @G_REGEX_CASELESS: Letters in the pattern match both upper- and
216 * lowercase letters. This option can be changed within a pattern
217 * by a "(?i)" option setting.
218 * @G_REGEX_MULTILINE: By default, GRegex treats the strings as consisting
219 * of a single line of characters (even if it actually contains
220 * newlines). The "start of line" metacharacter ("^") matches only
221 * at the start of the string, while the "end of line" metacharacter
222 * ("$") matches only at the end of the string, or before a terminating
223 * newline (unless #G_REGEX_DOLLAR_ENDONLY is set). When
224 * #G_REGEX_MULTILINE is set, the "start of line" and "end of line"
225 * constructs match immediately following or immediately before any
226 * newline in the string, respectively, as well as at the very start
227 * and end. This can be changed within a pattern by a "(?m)" option
229 * @G_REGEX_DOTALL: A dot metacharater (".") in the pattern matches all
230 * characters, including newlines. Without it, newlines are excluded.
231 * This option can be changed within a pattern by a ("?s") option setting.
232 * @G_REGEX_EXTENDED: Whitespace data characters in the pattern are
233 * totally ignored except when escaped or inside a character class.
234 * Whitespace does not include the VT character (code 11). In addition,
235 * characters between an unescaped "#" outside a character class and
236 * the next newline character, inclusive, are also ignored. This can
237 * be changed within a pattern by a "(?x)" option setting.
238 * @G_REGEX_ANCHORED: The pattern is forced to be "anchored", that is,
239 * it is constrained to match only at the first matching point in the
240 * string that is being searched. This effect can also be achieved by
241 * appropriate constructs in the pattern itself such as the "^"
243 * @G_REGEX_DOLLAR_ENDONLY: A dollar metacharacter ("$") in the pattern
244 * matches only at the end of the string. Without this option, a
245 * dollar also matches immediately before the final character if
246 * it is a newline (but not before any other newlines). This option
247 * is ignored if #G_REGEX_MULTILINE is set.
248 * @G_REGEX_UNGREEDY: Inverts the "greediness" of the quantifiers so that
249 * they are not greedy by default, but become greedy if followed by "?".
250 * It can also be set by a "(?U)" option setting within the pattern.
251 * @G_REGEX_RAW: Usually strings must be valid UTF-8 strings, using this
252 * flag they are considered as a raw sequence of bytes.
253 * @G_REGEX_NO_AUTO_CAPTURE: Disables the use of numbered capturing
254 * parentheses in the pattern. Any opening parenthesis that is not
255 * followed by "?" behaves as if it were followed by "?:" but named
256 * parentheses can still be used for capturing (and they acquire numbers
258 * @G_REGEX_OPTIMIZE: Optimize the regular expression. If the pattern will
259 * be used many times, then it may be worth the effort to optimize it
260 * to improve the speed of matches.
261 * @G_REGEX_FIRSTLINE: Limits an unanchored pattern to match before (or at) the
262 * first newline. Since: 2.34
263 * @G_REGEX_DUPNAMES: Names used to identify capturing subpatterns need not
264 * be unique. This can be helpful for certain types of pattern when it
265 * is known that only one instance of the named subpattern can ever be
267 * @G_REGEX_NEWLINE_CR: Usually any newline character or character sequence is
268 * recognized. If this option is set, the only recognized newline character
270 * @G_REGEX_NEWLINE_LF: Usually any newline character or character sequence is
271 * recognized. If this option is set, the only recognized newline character
273 * @G_REGEX_NEWLINE_CRLF: Usually any newline character or character sequence is
274 * recognized. If this option is set, the only recognized newline character
275 * sequence is '\r\n'.
276 * @G_REGEX_NEWLINE_ANYCRLF: Usually any newline character or character sequence
277 * is recognized. If this option is set, the only recognized newline character
278 * sequences are '\r', '\n', and '\r\n'. Since: 2.34
279 * G_REGEX_BSR_ANYCRLF: Usually any newline character or character sequence
280 * is recognised. If this option is set, then "\R" only recognizes the newline
281 * characters '\r', '\n' and '\r\n'. Since: 2.34
284 * Flags specifying compile-time options.
288 /* Remember to update G_REGEX_COMPILE_MASK in gregex.c after
289 * adding a new flag. */
292 G_REGEX_CASELESS = 1 << 0,
293 G_REGEX_MULTILINE = 1 << 1,
294 G_REGEX_DOTALL = 1 << 2,
295 G_REGEX_EXTENDED = 1 << 3,
296 G_REGEX_ANCHORED = 1 << 4,
297 G_REGEX_DOLLAR_ENDONLY = 1 << 5,
298 G_REGEX_UNGREEDY = 1 << 9,
299 G_REGEX_RAW = 1 << 11,
300 G_REGEX_NO_AUTO_CAPTURE = 1 << 12,
301 G_REGEX_OPTIMIZE = 1 << 13,
302 G_REGEX_FIRSTLINE = 1 << 18,
303 G_REGEX_DUPNAMES = 1 << 19,
304 G_REGEX_NEWLINE_CR = 1 << 20,
305 G_REGEX_NEWLINE_LF = 1 << 21,
306 G_REGEX_NEWLINE_CRLF = G_REGEX_NEWLINE_CR | G_REGEX_NEWLINE_LF,
307 G_REGEX_NEWLINE_ANYCRLF = G_REGEX_NEWLINE_CR | 1 << 22,
308 G_REGEX_BSR_ANYCRLF = 1 << 23,
309 G_REGEX_JAVASCRIPT_COMPAT = 1 << 25
310 } GRegexCompileFlags;
314 * @G_REGEX_MATCH_ANCHORED: The pattern is forced to be "anchored", that is,
315 * it is constrained to match only at the first matching point in the
316 * string that is being searched. This effect can also be achieved by
317 * appropriate constructs in the pattern itself such as the "^"
319 * @G_REGEX_MATCH_NOTBOL: Specifies that first character of the string is
320 * not the beginning of a line, so the circumflex metacharacter should
321 * not match before it. Setting this without #G_REGEX_MULTILINE (at
322 * compile time) causes circumflex never to match. This option affects
323 * only the behaviour of the circumflex metacharacter, it does not
325 * @G_REGEX_MATCH_NOTEOL: Specifies that the end of the subject string is
326 * not the end of a line, so the dollar metacharacter should not match
327 * it nor (except in multiline mode) a newline immediately before it.
328 * Setting this without #G_REGEX_MULTILINE (at compile time) causes
329 * dollar never to match. This option affects only the behaviour of
330 * the dollar metacharacter, it does not affect "\Z" or "\z".
331 * @G_REGEX_MATCH_NOTEMPTY: An empty string is not considered to be a valid
332 * match if this option is set. If there are alternatives in the pattern,
333 * they are tried. If all the alternatives match the empty string, the
334 * entire match fails. For example, if the pattern "a?b?" is applied to
335 * a string not beginning with "a" or "b", it matches the empty string
336 * at the start of the string. With this flag set, this match is not
337 * valid, so GRegex searches further into the string for occurrences
339 * @G_REGEX_MATCH_PARTIAL: Turns on the partial matching feature, for more
340 * documentation on partial matching see g_match_info_is_partial_match().
341 * @G_REGEX_MATCH_NEWLINE_CR: Overrides the newline definition set when
342 * creating a new #GRegex, setting the '\r' character as line terminator.
343 * @G_REGEX_MATCH_NEWLINE_LF: Overrides the newline definition set when
344 * creating a new #GRegex, setting the '\n' character as line terminator.
345 * @G_REGEX_MATCH_NEWLINE_CRLF: Overrides the newline definition set when
346 * creating a new #GRegex, setting the '\r\n' characters sequence as line terminator.
347 * @G_REGEX_MATCH_NEWLINE_ANY: Overrides the newline definition set when
348 * creating a new #GRegex, any Unicode newline sequence
349 * is recognised as a newline. These are '\r', '\n' and '\rn', and the
350 * single characters U+000B LINE TABULATION, U+000C FORM FEED (FF),
351 * U+0085 NEXT LINE (NEL), U+2028 LINE SEPARATOR and
352 * U+2029 PARAGRAPH SEPARATOR.
353 * @G_REGEX_MATCH_NEWLINE_ANYCRLF: Overrides the newline definition set when
354 * creating a new #GRegex; any '\r', '\n', or '\r\n' character sequence
355 * is recognized as a newline. Since: 2.34
356 * @G_REGEX_MATCH_BSR_ANYCRLF: Overrides the newline definition for "\R" set when
357 * creating a new #GRegex; only '\r', '\n', or '\r\n' character sequences
358 * are recognized as a newline by "\R". Since: 2.34
359 * @G_REGEX_MATCH_BSR_ANY: Overrides the newline definition for "\R" set when
360 * creating a new #GRegex; any Unicode newline character or character sequence
361 * are recognized as a newline by "\R". These are '\r', '\n' and '\rn', and the
362 * single characters U+000B LINE TABULATION, U+000C FORM FEED (FF),
363 * U+0085 NEXT LINE (NEL), U+2028 LINE SEPARATOR and
364 * U+2029 PARAGRAPH SEPARATOR. Since: 2.34
365 * @G_REGEX_JAVASCRIPT_COMPAT: Changes behaviour so that it is compatible with
366 * JavaScript rather than PCRE. Since: 2.34
367 * @G_REGEX_MATCH_PARTIAL_SOFT: An alias for #G_REGEX_MATCH_PARTIAL. Since: 2.34
368 * @G_REGEX_MATCH_PARTIAL_HARD: Turns on the partial matching feature. In contrast to
369 * to #G_REGEX_MATCH_PARTIAL_SOFT, this stops matching as soon as a partial match
370 * is found, without continuing to search for a possible complete match. See
371 * see g_match_info_is_partial_match() for more information. Since: 2.34
372 * @G_REGEX_MATCH_NOTEMPTY_ATSTART: Like #G_REGEX_MATCH_NOTEMPTY, but only applied to
373 * the start of the matched string. For anchored
374 * patterns this can only happen for pattern containing "\K". Since: 2.34
376 * Flags specifying match-time options.
380 /* Remember to update G_REGEX_MATCH_MASK in gregex.c after
381 * adding a new flag. */
384 G_REGEX_MATCH_ANCHORED = 1 << 4,
385 G_REGEX_MATCH_NOTBOL = 1 << 7,
386 G_REGEX_MATCH_NOTEOL = 1 << 8,
387 G_REGEX_MATCH_NOTEMPTY = 1 << 10,
388 G_REGEX_MATCH_PARTIAL = 1 << 15,
389 G_REGEX_MATCH_NEWLINE_CR = 1 << 20,
390 G_REGEX_MATCH_NEWLINE_LF = 1 << 21,
391 G_REGEX_MATCH_NEWLINE_CRLF = G_REGEX_MATCH_NEWLINE_CR | G_REGEX_MATCH_NEWLINE_LF,
392 G_REGEX_MATCH_NEWLINE_ANY = 1 << 22,
393 G_REGEX_MATCH_NEWLINE_ANYCRLF = G_REGEX_MATCH_NEWLINE_CR | G_REGEX_MATCH_NEWLINE_ANY,
394 G_REGEX_MATCH_BSR_ANYCRLF = 1 << 23,
395 G_REGEX_MATCH_BSR_ANY = 1 << 24,
396 G_REGEX_MATCH_PARTIAL_SOFT = G_REGEX_MATCH_PARTIAL,
397 G_REGEX_MATCH_PARTIAL_HARD = 1 << 27,
398 G_REGEX_MATCH_NOTEMPTY_ATSTART = 1 << 28
404 * A GRegex is the "compiled" form of a regular expression pattern. This
405 * structure is opaque and its fields cannot be accessed directly.
409 typedef struct _GRegex GRegex;
412 typedef struct _GMatchInfo GMatchInfo;
415 * GRegexEvalCallback:
416 * @match_info: the #GMatchInfo generated by the match.
417 * Use g_match_info_get_regex() and g_match_info_get_string() if you
418 * need the #GRegex or the matched string.
419 * @result: a #GString containing the new string
420 * @user_data: user data passed to g_regex_replace_eval()
422 * Specifies the type of the function passed to g_regex_replace_eval().
423 * It is called for each occurrence of the pattern in the string passed
424 * to g_regex_replace_eval(), and it should append the replacement to
427 * Returns: %FALSE to continue the replacement process, %TRUE to stop it
431 typedef gboolean (*GRegexEvalCallback) (const GMatchInfo *match_info,
436 GRegex *g_regex_new (const gchar *pattern,
437 GRegexCompileFlags compile_options,
438 GRegexMatchFlags match_options,
440 GRegex *g_regex_ref (GRegex *regex);
441 void g_regex_unref (GRegex *regex);
442 const gchar *g_regex_get_pattern (const GRegex *regex);
443 gint g_regex_get_max_backref (const GRegex *regex);
444 gint g_regex_get_capture_count (const GRegex *regex);
445 gboolean g_regex_get_has_cr_or_lf (const GRegex *regex);
446 gint g_regex_get_string_number (const GRegex *regex,
448 gchar *g_regex_escape_string (const gchar *string,
450 gchar *g_regex_escape_nul (const gchar *string,
453 GRegexCompileFlags g_regex_get_compile_flags (const GRegex *regex);
454 GRegexMatchFlags g_regex_get_match_flags (const GRegex *regex);
457 gboolean g_regex_match_simple (const gchar *pattern,
459 GRegexCompileFlags compile_options,
460 GRegexMatchFlags match_options);
461 gboolean g_regex_match (const GRegex *regex,
463 GRegexMatchFlags match_options,
464 GMatchInfo **match_info);
465 gboolean g_regex_match_full (const GRegex *regex,
469 GRegexMatchFlags match_options,
470 GMatchInfo **match_info,
472 gboolean g_regex_match_all (const GRegex *regex,
474 GRegexMatchFlags match_options,
475 GMatchInfo **match_info);
476 gboolean g_regex_match_all_full (const GRegex *regex,
480 GRegexMatchFlags match_options,
481 GMatchInfo **match_info,
484 /* String splitting. */
485 gchar **g_regex_split_simple (const gchar *pattern,
487 GRegexCompileFlags compile_options,
488 GRegexMatchFlags match_options);
489 gchar **g_regex_split (const GRegex *regex,
491 GRegexMatchFlags match_options);
492 gchar **g_regex_split_full (const GRegex *regex,
496 GRegexMatchFlags match_options,
500 /* String replacement. */
501 gchar *g_regex_replace (const GRegex *regex,
505 const gchar *replacement,
506 GRegexMatchFlags match_options,
508 gchar *g_regex_replace_literal (const GRegex *regex,
512 const gchar *replacement,
513 GRegexMatchFlags match_options,
515 gchar *g_regex_replace_eval (const GRegex *regex,
519 GRegexMatchFlags match_options,
520 GRegexEvalCallback eval,
523 gboolean g_regex_check_replacement (const gchar *replacement,
524 gboolean *has_references,
528 GRegex *g_match_info_get_regex (const GMatchInfo *match_info);
529 const gchar *g_match_info_get_string (const GMatchInfo *match_info);
531 GMatchInfo *g_match_info_ref (GMatchInfo *match_info);
532 void g_match_info_unref (GMatchInfo *match_info);
533 void g_match_info_free (GMatchInfo *match_info);
534 gboolean g_match_info_next (GMatchInfo *match_info,
536 gboolean g_match_info_matches (const GMatchInfo *match_info);
537 gint g_match_info_get_match_count (const GMatchInfo *match_info);
538 gboolean g_match_info_is_partial_match (const GMatchInfo *match_info);
539 gchar *g_match_info_expand_references(const GMatchInfo *match_info,
540 const gchar *string_to_expand,
542 gchar *g_match_info_fetch (const GMatchInfo *match_info,
544 gboolean g_match_info_fetch_pos (const GMatchInfo *match_info,
548 gchar *g_match_info_fetch_named (const GMatchInfo *match_info,
550 gboolean g_match_info_fetch_named_pos (const GMatchInfo *match_info,
554 gchar **g_match_info_fetch_all (const GMatchInfo *match_info);
558 #endif /* __G_REGEX_H__ */