xref: /PHP-5.3/ext/mbstring/oniguruma/doc/API (revision 7aab46a2)
1Oniguruma API  Version 4.7.1  2007/07/04
2
3#include <oniguruma.h>
4
5
6# int onig_init(void)
7
8  Initialize library.
9
10  You don't have to call it explicitly, because it is called in onig_new().
11
12
13# int onig_error_code_to_str(UChar* err_buf, int err_code, ...)
14
15  Get error message string.
16  If this function is used for onig_new(),
17  don't call this after the pattern argument of onig_new() is freed.
18
19  normal return: error message string length
20
21  arguments
22  1 err_buf:              error message string buffer.
23                          (required size: ONIG_MAX_ERROR_MESSAGE_LEN)
24  2 err_code:             error code returned by other API functions.
25  3 err_info (optional):  error info returned by onig_new().
26
27
28# void onig_set_warn_func(OnigWarnFunc func)
29
30  Set warning function.
31
32  WARNING:
33    '[', '-', ']' in character class without escape.
34    ']' in pattern without escape.
35
36  arguments
37  1 func:     function pointer.    void (*func)(char* warning_message)
38
39
40# void onig_set_verb_warn_func(OnigWarnFunc func)
41
42  Set verbose warning function.
43
44  WARNING:
45    redundant nested repeat operator.
46
47  arguments
48  1 func:     function pointer.    void (*func)(char* warning_message)
49
50
51# int onig_new(regex_t** reg, const UChar* pattern, const UChar* pattern_end,
52            OnigOptionType option, OnigEncoding enc, OnigSyntaxType* syntax,
53            OnigErrorInfo* err_info)
54
55  Create a regex object.
56
57  normal return: ONIG_NORMAL
58
59  arguments
60  1 reg:         return regex object's address.
61  2 pattern:     regex pattern string.
62  3 pattern_end: terminate address of pattern. (pattern + pattern length)
63  4 option:      compile time options.
64
65      ONIG_OPTION_NONE               no option
66      ONIG_OPTION_SINGLELINE         '^' -> '\A', '$' -> '\Z'
67      ONIG_OPTION_MULTILINE          '.' match with newline
68      ONIG_OPTION_IGNORECASE         ambiguity match on
69      ONIG_OPTION_EXTEND             extended pattern form
70      ONIG_OPTION_FIND_LONGEST       find longest match
71      ONIG_OPTION_FIND_NOT_EMPTY     ignore empty match
72      ONIG_OPTION_NEGATE_SINGLELINE
73            clear ONIG_OPTION_SINGLELINE which is enabled on
74            ONIG_SYNTAX_POSIX_BASIC, ONIG_SYNTAX_POSIX_EXTENDED,
75            ONIG_SYNTAX_PERL, ONIG_SYNTAX_PERL_NG, ONIG_SYNTAX_JAVA
76
77      ONIG_OPTION_DONT_CAPTURE_GROUP only named group captured.
78      ONIG_OPTION_CAPTURE_GROUP      named and no-named group captured.
79
80  5 enc:        character encoding.
81
82      ONIG_ENCODING_ASCII         ASCII
83      ONIG_ENCODING_ISO_8859_1    ISO 8859-1
84      ONIG_ENCODING_ISO_8859_2    ISO 8859-2
85      ONIG_ENCODING_ISO_8859_3    ISO 8859-3
86      ONIG_ENCODING_ISO_8859_4    ISO 8859-4
87      ONIG_ENCODING_ISO_8859_5    ISO 8859-5
88      ONIG_ENCODING_ISO_8859_6    ISO 8859-6
89      ONIG_ENCODING_ISO_8859_7    ISO 8859-7
90      ONIG_ENCODING_ISO_8859_8    ISO 8859-8
91      ONIG_ENCODING_ISO_8859_9    ISO 8859-9
92      ONIG_ENCODING_ISO_8859_10   ISO 8859-10
93      ONIG_ENCODING_ISO_8859_11   ISO 8859-11
94      ONIG_ENCODING_ISO_8859_13   ISO 8859-13
95      ONIG_ENCODING_ISO_8859_14   ISO 8859-14
96      ONIG_ENCODING_ISO_8859_15   ISO 8859-15
97      ONIG_ENCODING_ISO_8859_16   ISO 8859-16
98      ONIG_ENCODING_UTF8          UTF-8
99      ONIG_ENCODING_UTF16_BE      UTF-16BE
100      ONIG_ENCODING_UTF16_LE      UTF-16LE
101      ONIG_ENCODING_UTF32_BE      UTF-32BE
102      ONIG_ENCODING_UTF32_LE      UTF-32LE
103      ONIG_ENCODING_EUC_JP        EUC-JP
104      ONIG_ENCODING_EUC_TW        EUC-TW
105      ONIG_ENCODING_EUC_KR        EUC-KR
106      ONIG_ENCODING_EUC_CN        EUC-CN
107      ONIG_ENCODING_SJIS          Shift_JIS
108      ONIG_ENCODING_KOI8          KOI8
109      ONIG_ENCODING_KOI8_R        KOI8-R
110      ONIG_ENCODING_BIG5          Big5
111      ONIG_ENCODING_GB18030       GB 18030
112
113      or any OnigEncodingType data address defined by user.
114
115  6 syntax:     address of pattern syntax definition.
116
117      ONIG_SYNTAX_ASIS              plain text
118      ONIG_SYNTAX_POSIX_BASIC       POSIX Basic RE
119      ONIG_SYNTAX_POSIX_EXTENDED    POSIX Extended RE
120      ONIG_SYNTAX_EMACS             Emacs
121      ONIG_SYNTAX_GREP              grep
122      ONIG_SYNTAX_GNU_REGEX         GNU regex
123      ONIG_SYNTAX_JAVA              Java (Sun java.util.regex)
124      ONIG_SYNTAX_PERL              Perl
125      ONIG_SYNTAX_PERL_NG           Perl + named group
126      ONIG_SYNTAX_RUBY              Ruby
127      ONIG_SYNTAX_DEFAULT           default (== Ruby)
128                                   onig_set_default_syntax()
129
130      or any OnigSyntaxType data address defined by user.
131
132  7 err_info: address for return optional error info.
133              Use this value as 3rd argument of onig_error_code_to_str().
134
135
136
137# int onig_new_deluxe(regex_t** reg, const UChar* pattern, const UChar* pattern_end,
138                      OnigCompileInfo* ci, OnigErrorInfo* einfo)
139
140  Create a regex object.
141  This function is deluxe version of onig_new().
142
143  normal return: ONIG_NORMAL
144
145  arguments
146  1 reg:         return address of regex object.
147  2 pattern:     regex pattern string.
148  3 pattern_end: terminate address of pattern. (pattern + pattern length)
149  4 ci:          compile time info.
150
151    ci->num_of_elements: number of elements in ci. (current version: 5)
152    ci->pattern_enc:     pattern string character encoding.
153    ci->target_enc:      target string character encoding.
154    ci->syntax:          address of pattern syntax definition.
155    ci->option:          compile time option.
156    ci->ambig_flag:      character matching ambiguity bit flag for
157                         ONIG_OPTION_IGNORECASE mode.
158
159       ONIGENC_AMBIGUOUS_MATCH_NONE:          exact
160       ONIGENC_AMBIGUOUS_MATCH_ASCII_CASE:    ignore case for ASCII
161       ONIGENC_AMBIGUOUS_MATCH_NONASCII_CASE: ignore case for non-ASCII
162       ONIGENC_AMBIGUOUS_MATCH_FULL:          all ambiguity on
163       ONIGENC_AMBIGUOUS_MATCH_DEFAULT:       (ASCII | NONASCII)
164                                              onig_set_default_ambig_flag()
165
166  5 err_info:    address for return optional error info.
167                 Use this value as 3rd argument of onig_error_code_to_str().
168
169
170  Different character encoding combination is allowed for
171  the following cases only.
172
173    pattern_enc: ASCII, ISO_8859_1
174    target_enc:  UTF16_BE, UTF16_LE, UTF32_BE, UTF32_LE
175
176    pattern_enc: UTF16_BE/LE
177    target_enc:  UTF16_LE/BE
178
179    pattern_enc: UTF32_BE/LE
180    target_enc:  UTF32_LE/BE
181
182
183# void onig_free(regex_t* reg)
184
185  Free memory used by regex object.
186
187  arguments
188  1 reg: regex object.
189
190
191# int onig_search(regex_t* reg, const UChar* str, const UChar* end, const UChar* start,
192                   const UChar* range, OnigRegion* region, OnigOptionType option)
193
194  Search string and return search result and matching region.
195
196  normal return: match position offset (i.e.  p - str >= 0)
197  not found:     ONIG_MISMATCH (< 0)
198
199  arguments
200  1 reg:    regex object
201  2 str:    target string
202  3 end:    terminate address of target string
203  4 start:  search start address of target string
204  5 range:  search terminate address of target string
205    in forward search  (start <= searched string head < range)
206    in backward search (range <= searched string head <= start)
207  6 region: address for return group match range info (NULL is allowed)
208  7 option: search time option
209
210    ONIG_OPTION_NOTBOL        string head(str) isn't considered as begin of line
211    ONIG_OPTION_NOTEOL        string end (end) isn't considered as end of line
212    ONIG_OPTION_POSIX_REGION  region argument is regmatch_t[] of POSIX API.
213
214
215# int onig_match(regex_t* reg, const UChar* str, const UChar* end, const UChar* at,
216		 OnigRegion* region, OnigOptionType option)
217
218  Match string and return result and matching region.
219
220  normal return: match length  (>= 0)
221  not match:     ONIG_MISMATCH ( < 0)
222
223  arguments
224  1 reg:    regex object
225  2 str:    target string
226  3 end:    terminate address of target string
227  4 at:     match address of target string
228  5 region: address for return group match range info (NULL is allowed)
229  6 option: search time option
230
231    ONIG_OPTION_NOTBOL       string head(str) isn't considered as begin of line
232    ONIG_OPTION_NOTEOL       string end (end) isn't considered as end of line
233    ONIG_OPTION_POSIX_REGION region argument is regmatch_t[] type of POSIX API.
234
235
236# OnigRegion* onig_region_new(void)
237
238  Create a region.
239
240
241# void onig_region_free(OnigRegion* region, int free_self)
242
243  Free memory used by region.
244
245  arguments
246  1 region:    target region
247  2 free_self: [1: free all, 0: free memory used in region but not self]
248
249
250# void onig_region_copy(OnigRegion* to, OnigRegion* from)
251
252  Copy contents of region.
253
254  arguments
255  1 to:   target region
256  2 from: source region
257
258
259# void onig_region_clear(OnigRegion* region)
260
261  Clear contents of region.
262
263  arguments
264  1 region: target region
265
266
267# int onig_region_resize(OnigRegion* region, int n)
268
269  Resize group range area of region.
270
271  normal return: ONIG_NORMAL
272
273  arguments
274  1 region: target region
275  2 n:      new size
276
277
278# int onig_name_to_group_numbers(regex_t* reg, const UChar* name, const UChar* name_end,
279                                  int** num_list)
280
281  Return the group number list of the name.
282  Named subexp is defined by (?<name>....).
283
284  normal return:  number of groups for the name.
285                  (ex. /(?<x>..)(?<x>..)/  ==>  2)
286  name not found: -1
287
288  arguments
289  1 reg:       regex object.
290  2 name:      group name.
291  3 name_end:  terminate address of group name.
292  4 num_list:  return list of group number.
293
294
295# int onig_name_to_backref_number(regex_t* reg, const UChar* name, const UChar* name_end,
296                                  OnigRegion *region)
297
298  Return the group number corresponding to the named backref (\k<name>).
299  If two or more regions for the groups of the name are effective,
300  the greatest number in it is obtained.
301
302  normal return: group number.
303
304  arguments
305  1 reg:      regex object.
306  2 name:     group name.
307  3 name_end: terminate address of group name.
308  4 region:   search/match result region.
309
310
311# int onig_foreach_name(regex_t* reg,
312                        int (*func)(const UChar*, const UChar*, int,int*,regex_t*,void*),
313                        void* arg)
314
315  Iterate function call for all names.
316
317  normal return: 0
318  error:         func's return value.
319
320  arguments
321  1 reg:     regex object.
322  2 func:    callback function.
323             func(name, name_end, <number of groups>, <group number's list>,
324                  reg, arg);
325             if func does not return 0, then iteration is stopped.
326  3 arg:     argument for func.
327
328
329# int onig_number_of_names(regex_t* reg)
330
331  Return the number of names defined in the pattern.
332  Multiple definitions of one name is counted as one.
333
334  arguments
335  1 reg:     regex object.
336
337
338# OnigEncoding    onig_get_encoding(regex_t* reg)
339# OnigOptionType  onig_get_options(regex_t* reg)
340# OnigAmbigType   onig_get_ambig_flag(regex_t* reg)
341# OnigSyntaxType* onig_get_syntax(regex_t* reg)
342
343  Return a value of the regex object.
344
345  arguments
346  1 reg:     regex object.
347
348
349# int onig_number_of_captures(regex_t* reg)
350
351  Return the number of capture group in the pattern.
352
353  arguments
354  1 reg:     regex object.
355
356
357# int onig_number_of_capture_histories(regex_t* reg)
358
359  Return the number of capture history defined in the pattern.
360
361  You can't use capture history if ONIG_SYN_OP2_ATMARK_CAPTURE_HISTORY
362  is disabled in the pattern syntax.(disabled in the default syntax)
363
364  arguments
365  1 reg:     regex object.
366
367
368
369# OnigCaptureTreeNode* onig_get_capture_tree(OnigRegion* region)
370
371  Return the root node of capture history data tree.
372
373  This value is undefined if matching has faild.
374
375  arguments
376  1 region: matching result.
377
378
379# int onig_capture_tree_traverse(OnigRegion* region, int at,
380                  int(*func)(int,int,int,int,int,void*), void* arg)
381
382 Traverse and callback in capture history data tree.
383
384  normal return: 0
385  error:         callback func's return value.
386
387  arguments
388  1 region:  match region data.
389  2 at:      callback position.
390
391    ONIG_TRAVERSE_CALLBACK_AT_FIRST: callback first, then traverse childs.
392    ONIG_TRAVERSE_CALLBACK_AT_LAST:  traverse childs first, then callback.
393    ONIG_TRAVERSE_CALLBACK_AT_BOTH:  callback first, then traverse childs,
394                                     and at last callback again.
395
396  3 func:    callback function.
397             if func does not return 0, then traverse is stopped.
398
399             int func(int group, int beg, int end, int level, int at,
400                      void* arg)
401
402               group: group number
403               beg:   capture start position
404               end:   capture end position
405               level: nest level (from 0)
406               at:    callback position
407                      ONIG_TRAVERSE_CALLBACK_AT_FIRST
408                      ONIG_TRAVERSE_CALLBACK_AT_LAST
409               arg:   optional callback argument
410
411  4 arg;     optional callback argument.
412
413
414# int onig_noname_group_capture_is_active(regex_t* reg)
415
416  Return noname group capture activity.
417
418  active:   1
419  inactive: 0
420
421  arguments
422  1 reg:     regex object.
423
424  if option ONIG_OPTION_DONT_CAPTURE_GROUP == ON
425    --> inactive
426
427  if the regex pattern have named group
428     and syntax ONIG_SYN_CAPTURE_ONLY_NAMED_GROUP == ON
429     and option ONIG_OPTION_CAPTURE_GROUP == OFF
430    --> inactive
431
432  else --> active
433
434
435# UChar* onigenc_get_prev_char_head(OnigEncoding enc, const UChar* start, const UChar* s)
436
437  Return previous character head address.
438
439  arguments
440  1 enc:   character encoding
441  2 start: string address
442  3 s:     target address of string
443
444
445# UChar* onigenc_get_left_adjust_char_head(OnigEncoding enc,
446                                           const UChar* start, const UChar* s)
447
448  Return left-adjusted head address of a character.
449
450  arguments
451  1 enc:   character encoding
452  2 start: string address
453  3 s:     target address of string
454
455
456# UChar* onigenc_get_right_adjust_char_head(OnigEncoding enc,
457                                            const UChar* start, const UChar* s)
458
459  Return right-adjusted head address of a character.
460
461  arguments
462  1 enc:   character encoding
463  2 start: string address
464  3 s:     target address of string
465
466
467# int onigenc_strlen(OnigEncoding enc, const UChar* s, const UChar* end)
468# int onigenc_strlen_null(OnigEncoding enc, const UChar* s)
469
470  Return number of characters in the string.
471
472
473# int onigenc_str_bytelen_null(OnigEncoding enc, const UChar* s)
474
475  Return number of bytes in the string.
476
477
478# int onig_set_default_syntax(OnigSyntaxType* syntax)
479
480  Set default syntax.
481
482  arguments
483  1 syntax: address of pattern syntax definition.
484
485
486# void onig_copy_syntax(OnigSyntaxType* to, OnigSyntaxType* from)
487
488  Copy syntax.
489
490  arguments
491  1 to:   destination address.
492  2 from: source address.
493
494
495# unsigned int onig_get_syntax_op(OnigSyntaxType* syntax)
496# unsigned int onig_get_syntax_op2(OnigSyntaxType* syntax)
497# unsigned int onig_get_syntax_behavior(OnigSyntaxType* syntax)
498# OnigOptionType onig_get_syntax_options(OnigSyntaxType* syntax)
499
500# void onig_set_syntax_op(OnigSyntaxType* syntax, unsigned int op)
501# void onig_set_syntax_op2(OnigSyntaxType* syntax, unsigned int op2)
502# void onig_set_syntax_behavior(OnigSyntaxType* syntax, unsigned int behavior)
503# void onig_set_syntax_options(OnigSyntaxType* syntax, OnigOptionType options)
504
505 Get/Set elements of the syntax.
506
507  arguments
508  1 syntax:  syntax
509  2 op, op2, behavior, options: value of element.
510
511
512# void onig_copy_encoding(OnigEncoding to, OnigOnigEncoding from)
513
514  Copy encoding.
515
516  arguments
517  1 to:   destination address.
518  2 from: source address.
519
520
521# int onig_set_meta_char(OnigEncoding enc, unsigned int what,
522                         OnigCodePoint code)
523
524  Set a variable meta character to the code point value.
525  Except for an escape character, this meta characters specification
526  is not work, if ONIG_SYN_OP_VARIABLE_META_CHARACTERS is not effective
527  by the syntax. (Build-in syntaxes are not effective.)
528
529  normal return: ONIG_NORMAL
530
531  arguments
532  1 enc:  target encoding
533  2 what: specifies which meta character it is.
534
535          ONIG_META_CHAR_ESCAPE
536          ONIG_META_CHAR_ANYCHAR
537          ONIG_META_CHAR_ANYTIME
538          ONIG_META_CHAR_ZERO_OR_ONE_TIME
539          ONIG_META_CHAR_ONE_OR_MORE_TIME
540          ONIG_META_CHAR_ANYCHAR_ANYTIME
541
542  3 code: meta character or ONIG_INEFFECTIVE_META_CHAR.
543
544
545# OnigAmbigType onig_get_default_ambig_flag()
546
547  Get default ambig flag.
548
549
550# int onig_set_default_ambig_flag(OnigAmbigType ambig_flag)
551
552  Set default ambig flag.
553
554  1 ambig_flag: ambiguity flag
555
556
557# unsigned int onig_get_match_stack_limit_size(void)
558
559  Return the maximum number of stack size.
560  (default: 0 == unlimited)
561
562
563# int onig_set_match_stack_limit_size(unsigned int size)
564
565  Set the maximum number of stack size.
566  (size = 0: unlimited)
567
568  normal return: ONIG_NORMAL
569
570
571# int onig_end(void)
572
573  The use of this library is finished.
574
575  normal return: ONIG_NORMAL
576
577  It is not allowed to use regex objects which created
578  before onig_end() call.
579
580
581# const char* onig_version(void)
582
583  Return version string.  (ex. "2.2.8")
584
585// END
586