-
-
Notifications
You must be signed in to change notification settings - Fork 708
/
regex.h
1882 lines (1681 loc) · 84.5 KB
/
regex.h
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
483
484
485
486
487
488
489
490
491
492
493
494
495
496
497
498
499
500
501
502
503
504
505
506
507
508
509
510
511
512
513
514
515
516
517
518
519
520
521
522
523
524
525
526
527
528
529
530
531
532
533
534
535
536
537
538
539
540
541
542
543
544
545
546
547
548
549
550
551
552
553
554
555
556
557
558
559
560
561
562
563
564
565
566
567
568
569
570
571
572
573
574
575
576
577
578
579
580
581
582
583
584
585
586
587
588
589
590
591
592
593
594
595
596
597
598
599
600
601
602
603
604
605
606
607
608
609
610
611
612
613
614
615
616
617
618
619
620
621
622
623
624
625
626
627
628
629
630
631
632
633
634
635
636
637
638
639
640
641
642
643
644
645
646
647
648
649
650
651
652
653
654
655
656
657
658
659
660
661
662
663
664
665
666
667
668
669
670
671
672
673
674
675
676
677
678
679
680
681
682
683
684
685
686
687
688
689
690
691
692
693
694
695
696
697
698
699
700
701
702
703
704
705
706
707
708
709
710
711
712
713
714
715
716
717
718
719
720
721
722
723
724
725
726
727
728
729
730
731
732
733
734
735
736
737
738
739
740
741
742
743
744
745
746
747
748
749
750
751
752
753
754
755
756
757
758
759
760
761
762
763
764
765
766
767
768
769
770
771
772
773
774
775
776
777
778
779
780
781
782
783
784
785
786
787
788
789
790
791
792
793
794
795
796
797
798
799
800
801
802
803
804
805
806
807
808
809
810
811
812
813
814
815
816
817
818
819
820
821
822
823
824
825
826
827
828
829
830
831
832
833
834
835
836
837
838
839
840
841
842
843
844
845
846
847
848
849
850
851
852
853
854
855
856
857
858
859
860
861
862
863
864
865
866
867
868
869
870
871
872
873
874
875
876
877
878
879
880
881
882
883
884
885
886
887
888
889
890
891
892
893
894
895
896
897
898
899
900
901
902
903
904
905
906
907
908
909
910
911
912
913
914
915
916
917
918
919
920
921
922
923
924
925
926
927
928
929
930
931
932
933
934
935
936
937
938
939
940
941
942
943
944
945
946
947
948
949
950
951
952
953
954
955
956
957
958
959
960
961
962
963
964
965
966
967
968
969
970
971
972
973
974
975
976
977
978
979
980
981
982
983
984
985
986
987
988
989
990
991
992
993
994
995
996
997
998
999
1000
// © 2016 and later: Unicode, Inc. and others.
// License & terms of use: http://www.unicode.org/copyright.html
/*
**********************************************************************
* Copyright (C) 2002-2016, International Business Machines
* Corporation and others. All Rights Reserved.
**********************************************************************
* file name: regex.h
* encoding: UTF-8
* indentation:4
*
* created on: 2002oct22
* created by: Andy Heninger
*
* ICU Regular Expressions, API for C++
*/
#ifndef REGEX_H
#define REGEX_H
//#define REGEX_DEBUG
/**
* \file
* \brief C++ API: Regular Expressions
*
* The ICU API for processing regular expressions consists of two classes,
* `RegexPattern` and `RegexMatcher`.
* `RegexPattern` objects represent a pre-processed, or compiled
* regular expression. They are created from a regular expression pattern string,
* and can be used to create `RegexMatcher` objects for the pattern.
*
* Class `RegexMatcher` bundles together a regular expression
* pattern and a target string to which the search pattern will be applied.
* `RegexMatcher` includes API for doing plain find or search
* operations, for search and replace operations, and for obtaining detailed
* information about bounds of a match.
*
* Note that by constructing `RegexMatcher` objects directly from regular
* expression pattern strings application code can be simplified and the explicit
* need for `RegexPattern` objects can usually be eliminated.
*
*/
#include "unicode/utypes.h"
#if U_SHOW_CPLUSPLUS_API
#if !UCONFIG_NO_REGULAR_EXPRESSIONS
#include "unicode/uobject.h"
#include "unicode/unistr.h"
#include "unicode/utext.h"
#include "unicode/parseerr.h"
#include "unicode/uregex.h"
// Forward Declarations
struct UHashtable;
U_NAMESPACE_BEGIN
struct Regex8BitSet;
class RegexCImpl;
class RegexMatcher;
class RegexPattern;
struct REStackFrame;
class BreakIterator;
class UnicodeSet;
class UVector;
class UVector32;
class UVector64;
/**
* Class `RegexPattern` represents a compiled regular expression. It includes
* factory methods for creating a RegexPattern object from the source (string) form
* of a regular expression, methods for creating RegexMatchers that allow the pattern
* to be applied to input text, and a few convenience methods for simple common
* uses of regular expressions.
*
* Class RegexPattern is not intended to be subclassed.
*
* @stable ICU 2.4
*/
class U_I18N_API RegexPattern final : public UObject {
public:
/**
* default constructor. Create a RegexPattern object that refers to no actual
* pattern. Not normally needed; RegexPattern objects are usually
* created using the factory method `compile()`.
*
* @stable ICU 2.4
*/
RegexPattern();
/**
* Copy Constructor. Create a new RegexPattern object that is equivalent
* to the source object.
* @param source the pattern object to be copied.
* @stable ICU 2.4
*/
RegexPattern(const RegexPattern &source);
/**
* Destructor. Note that a RegexPattern object must persist so long as any
* RegexMatcher objects that were created from the RegexPattern are active.
* @stable ICU 2.4
*/
virtual ~RegexPattern();
/**
* Comparison operator. Two RegexPattern objects are considered equal if they
* were constructed from identical source patterns using the same #URegexpFlag
* settings.
* @param that a RegexPattern object to compare with "this".
* @return true if the objects are equivalent.
* @stable ICU 2.4
*/
bool operator==(const RegexPattern& that) const;
/**
* Comparison operator. Two RegexPattern objects are considered equal if they
* were constructed from identical source patterns using the same #URegexpFlag
* settings.
* @param that a RegexPattern object to compare with "this".
* @return true if the objects are different.
* @stable ICU 2.4
*/
inline bool operator!=(const RegexPattern& that) const {return ! operator ==(that);}
/**
* Assignment operator. After assignment, this RegexPattern will behave identically
* to the source object.
* @stable ICU 2.4
*/
RegexPattern &operator =(const RegexPattern &source);
/**
* Create an exact copy of this RegexPattern object. Since RegexPattern is not
* intended to be subclassed, <code>clone()</code> and the copy construction are
* equivalent operations.
* @return the copy of this RegexPattern
* @stable ICU 2.4
*/
virtual RegexPattern *clone() const;
/**
* Compiles the regular expression in string form into a RegexPattern
* object. These compile methods, rather than the constructors, are the usual
* way that RegexPattern objects are created.
*
* Note that RegexPattern objects must not be deleted while RegexMatcher
* objects created from the pattern are active. RegexMatchers keep a pointer
* back to their pattern, so premature deletion of the pattern is a
* catastrophic error.
*
* All #URegexpFlag pattern match mode flags are set to their default values.
*
* Note that it is often more convenient to construct a RegexMatcher directly
* from a pattern string rather than separately compiling the pattern and
* then creating a RegexMatcher object from the pattern.
*
* @param regex The regular expression to be compiled.
* @param pe Receives the position (line and column nubers) of any error
* within the regular expression.)
* @param status A reference to a UErrorCode to receive any errors.
* @return A regexPattern object for the compiled pattern.
*
* @stable ICU 2.4
*/
static RegexPattern * U_EXPORT2 compile( const UnicodeString ®ex,
UParseError &pe,
UErrorCode &status);
/**
* Compiles the regular expression in string form into a RegexPattern
* object. These compile methods, rather than the constructors, are the usual
* way that RegexPattern objects are created.
*
* Note that RegexPattern objects must not be deleted while RegexMatcher
* objects created from the pattern are active. RegexMatchers keep a pointer
* back to their pattern, so premature deletion of the pattern is a
* catastrophic error.
*
* All #URegexpFlag pattern match mode flags are set to their default values.
*
* Note that it is often more convenient to construct a RegexMatcher directly
* from a pattern string rather than separately compiling the pattern and
* then creating a RegexMatcher object from the pattern.
*
* @param regex The regular expression to be compiled. Note, the text referred
* to by this UText must not be deleted during the lifetime of the
* RegexPattern object or any RegexMatcher object created from it.
* @param pe Receives the position (line and column nubers) of any error
* within the regular expression.)
* @param status A reference to a UErrorCode to receive any errors.
* @return A regexPattern object for the compiled pattern.
*
* @stable ICU 4.6
*/
static RegexPattern * U_EXPORT2 compile( UText *regex,
UParseError &pe,
UErrorCode &status);
/**
* Compiles the regular expression in string form into a RegexPattern
* object using the specified #URegexpFlag match mode flags. These compile methods,
* rather than the constructors, are the usual way that RegexPattern objects
* are created.
*
* Note that RegexPattern objects must not be deleted while RegexMatcher
* objects created from the pattern are active. RegexMatchers keep a pointer
* back to their pattern, so premature deletion of the pattern is a
* catastrophic error.
*
* Note that it is often more convenient to construct a RegexMatcher directly
* from a pattern string instead of than separately compiling the pattern and
* then creating a RegexMatcher object from the pattern.
*
* @param regex The regular expression to be compiled.
* @param flags The #URegexpFlag match mode flags to be used, e.g. #UREGEX_CASE_INSENSITIVE.
* @param pe Receives the position (line and column numbers) of any error
* within the regular expression.)
* @param status A reference to a UErrorCode to receive any errors.
* @return A regexPattern object for the compiled pattern.
*
* @stable ICU 2.4
*/
static RegexPattern * U_EXPORT2 compile( const UnicodeString ®ex,
uint32_t flags,
UParseError &pe,
UErrorCode &status);
/**
* Compiles the regular expression in string form into a RegexPattern
* object using the specified #URegexpFlag match mode flags. These compile methods,
* rather than the constructors, are the usual way that RegexPattern objects
* are created.
*
* Note that RegexPattern objects must not be deleted while RegexMatcher
* objects created from the pattern are active. RegexMatchers keep a pointer
* back to their pattern, so premature deletion of the pattern is a
* catastrophic error.
*
* Note that it is often more convenient to construct a RegexMatcher directly
* from a pattern string instead of than separately compiling the pattern and
* then creating a RegexMatcher object from the pattern.
*
* @param regex The regular expression to be compiled. Note, the text referred
* to by this UText must not be deleted during the lifetime of the
* RegexPattern object or any RegexMatcher object created from it.
* @param flags The #URegexpFlag match mode flags to be used, e.g. #UREGEX_CASE_INSENSITIVE.
* @param pe Receives the position (line and column numbers) of any error
* within the regular expression.)
* @param status A reference to a UErrorCode to receive any errors.
* @return A regexPattern object for the compiled pattern.
*
* @stable ICU 4.6
*/
static RegexPattern * U_EXPORT2 compile( UText *regex,
uint32_t flags,
UParseError &pe,
UErrorCode &status);
/**
* Compiles the regular expression in string form into a RegexPattern
* object using the specified #URegexpFlag match mode flags. These compile methods,
* rather than the constructors, are the usual way that RegexPattern objects
* are created.
*
* Note that RegexPattern objects must not be deleted while RegexMatcher
* objects created from the pattern are active. RegexMatchers keep a pointer
* back to their pattern, so premature deletion of the pattern is a
* catastrophic error.
*
* Note that it is often more convenient to construct a RegexMatcher directly
* from a pattern string instead of than separately compiling the pattern and
* then creating a RegexMatcher object from the pattern.
*
* @param regex The regular expression to be compiled.
* @param flags The #URegexpFlag match mode flags to be used, e.g. #UREGEX_CASE_INSENSITIVE.
* @param status A reference to a UErrorCode to receive any errors.
* @return A regexPattern object for the compiled pattern.
*
* @stable ICU 2.6
*/
static RegexPattern * U_EXPORT2 compile( const UnicodeString ®ex,
uint32_t flags,
UErrorCode &status);
/**
* Compiles the regular expression in string form into a RegexPattern
* object using the specified #URegexpFlag match mode flags. These compile methods,
* rather than the constructors, are the usual way that RegexPattern objects
* are created.
*
* Note that RegexPattern objects must not be deleted while RegexMatcher
* objects created from the pattern are active. RegexMatchers keep a pointer
* back to their pattern, so premature deletion of the pattern is a
* catastrophic error.
*
* Note that it is often more convenient to construct a RegexMatcher directly
* from a pattern string instead of than separately compiling the pattern and
* then creating a RegexMatcher object from the pattern.
*
* @param regex The regular expression to be compiled. Note, the text referred
* to by this UText must not be deleted during the lifetime of the
* RegexPattern object or any RegexMatcher object created from it.
* @param flags The #URegexpFlag match mode flags to be used, e.g. #UREGEX_CASE_INSENSITIVE.
* @param status A reference to a UErrorCode to receive any errors.
* @return A regexPattern object for the compiled pattern.
*
* @stable ICU 4.6
*/
static RegexPattern * U_EXPORT2 compile( UText *regex,
uint32_t flags,
UErrorCode &status);
/**
* Get the #URegexpFlag match mode flags that were used when compiling this pattern.
* @return the #URegexpFlag match mode flags
* @stable ICU 2.4
*/
virtual uint32_t flags() const;
/**
* Creates a RegexMatcher that will match the given input against this pattern. The
* RegexMatcher can then be used to perform match, find or replace operations
* on the input. Note that a RegexPattern object must not be deleted while
* RegexMatchers created from it still exist and might possibly be used again.
*
* The matcher will retain a reference to the supplied input string, and all regexp
* pattern matching operations happen directly on this original string. It is
* critical that the string not be altered or deleted before use by the regular
* expression operations is complete.
*
* @param input The input string to which the regular expression will be applied.
* @param status A reference to a UErrorCode to receive any errors.
* @return A RegexMatcher object for this pattern and input.
*
* @stable ICU 2.4
*/
virtual RegexMatcher *matcher(const UnicodeString &input,
UErrorCode &status) const;
private:
/**
* Cause a compilation error if an application accidentally attempts to
* create a matcher with a (char16_t *) string as input rather than
* a UnicodeString. Avoids a dangling reference to a temporary string.
*
* To efficiently work with char16_t *strings, wrap the data in a UnicodeString
* using one of the aliasing constructors, such as
* `UnicodeString(UBool isTerminated, const char16_t *text, int32_t textLength);`
* or in a UText, using
* `utext_openUChars(UText *ut, const char16_t *text, int64_t textLength, UErrorCode *status);`
*
*/
RegexMatcher *matcher(const char16_t *input,
UErrorCode &status) const = delete;
public:
/**
* Creates a RegexMatcher that will match against this pattern. The
* RegexMatcher can be used to perform match, find or replace operations.
* Note that a RegexPattern object must not be deleted while
* RegexMatchers created from it still exist and might possibly be used again.
*
* @param status A reference to a UErrorCode to receive any errors.
* @return A RegexMatcher object for this pattern and input.
*
* @stable ICU 2.6
*/
virtual RegexMatcher *matcher(UErrorCode &status) const;
/**
* Test whether a string matches a regular expression. This convenience function
* both compiles the regular expression and applies it in a single operation.
* Note that if the same pattern needs to be applied repeatedly, this method will be
* less efficient than creating and reusing a RegexMatcher object.
*
* @param regex The regular expression
* @param input The string data to be matched
* @param pe Receives the position of any syntax errors within the regular expression
* @param status A reference to a UErrorCode to receive any errors.
* @return True if the regular expression exactly matches the full input string.
*
* @stable ICU 2.4
*/
static UBool U_EXPORT2 matches(const UnicodeString ®ex,
const UnicodeString &input,
UParseError &pe,
UErrorCode &status);
/**
* Test whether a string matches a regular expression. This convenience function
* both compiles the regular expression and applies it in a single operation.
* Note that if the same pattern needs to be applied repeatedly, this method will be
* less efficient than creating and reusing a RegexMatcher object.
*
* @param regex The regular expression
* @param input The string data to be matched
* @param pe Receives the position of any syntax errors within the regular expression
* @param status A reference to a UErrorCode to receive any errors.
* @return True if the regular expression exactly matches the full input string.
*
* @stable ICU 4.6
*/
static UBool U_EXPORT2 matches(UText *regex,
UText *input,
UParseError &pe,
UErrorCode &status);
/**
* Returns the regular expression from which this pattern was compiled. This method will work
* even if the pattern was compiled from a UText.
*
* Note: If the pattern was originally compiled from a UText, and that UText was modified,
* the returned string may no longer reflect the RegexPattern object.
* @stable ICU 2.4
*/
virtual UnicodeString pattern() const;
/**
* Returns the regular expression from which this pattern was compiled. This method will work
* even if the pattern was compiled from a UnicodeString.
*
* Note: This is the original input, not a clone. If the pattern was originally compiled from a
* UText, and that UText was modified, the returned UText may no longer reflect the RegexPattern
* object.
*
* @stable ICU 4.6
*/
virtual UText *patternText(UErrorCode &status) const;
/**
* Get the group number corresponding to a named capture group.
* The returned number can be used with any function that access
* capture groups by number.
*
* The function returns an error status if the specified name does not
* appear in the pattern.
*
* @param groupName The capture group name.
* @param status A UErrorCode to receive any errors.
*
* @stable ICU 55
*/
virtual int32_t groupNumberFromName(const UnicodeString &groupName, UErrorCode &status) const;
/**
* Get the group number corresponding to a named capture group.
* The returned number can be used with any function that access
* capture groups by number.
*
* The function returns an error status if the specified name does not
* appear in the pattern.
*
* @param groupName The capture group name,
* platform invariant characters only.
* @param nameLength The length of the name, or -1 if the name is
* nul-terminated.
* @param status A UErrorCode to receive any errors.
*
* @stable ICU 55
*/
virtual int32_t groupNumberFromName(const char *groupName, int32_t nameLength, UErrorCode &status) const;
/**
* Split a string into fields. Somewhat like split() from Perl or Java.
* Pattern matches identify delimiters that separate the input
* into fields. The input data between the delimiters becomes the
* fields themselves.
*
* If the delimiter pattern includes capture groups, the captured text will
* also appear in the destination array of output strings, interspersed
* with the fields. This is similar to Perl, but differs from Java,
* which ignores the presence of capture groups in the pattern.
*
* Trailing empty fields will always be returned, assuming sufficient
* destination capacity. This differs from the default behavior for Java
* and Perl where trailing empty fields are not returned.
*
* The number of strings produced by the split operation is returned.
* This count includes the strings from capture groups in the delimiter pattern.
* This behavior differs from Java, which ignores capture groups.
*
* For the best performance on split() operations,
* <code>RegexMatcher::split</code> is preferable to this function
*
* @param input The string to be split into fields. The field delimiters
* match the pattern (in the "this" object)
* @param dest An array of UnicodeStrings to receive the results of the split.
* This is an array of actual UnicodeString objects, not an
* array of pointers to strings. Local (stack based) arrays can
* work well here.
* @param destCapacity The number of elements in the destination array.
* If the number of fields found is less than destCapacity, the
* extra strings in the destination array are not altered.
* If the number of destination strings is less than the number
* of fields, the trailing part of the input string, including any
* field delimiters, is placed in the last destination string.
* @param status A reference to a UErrorCode to receive any errors.
* @return The number of fields into which the input string was split.
* @stable ICU 2.4
*/
virtual int32_t split(const UnicodeString &input,
UnicodeString dest[],
int32_t destCapacity,
UErrorCode &status) const;
/**
* Split a string into fields. Somewhat like %split() from Perl or Java.
* Pattern matches identify delimiters that separate the input
* into fields. The input data between the delimiters becomes the
* fields themselves.
*
* If the delimiter pattern includes capture groups, the captured text will
* also appear in the destination array of output strings, interspersed
* with the fields. This is similar to Perl, but differs from Java,
* which ignores the presence of capture groups in the pattern.
*
* Trailing empty fields will always be returned, assuming sufficient
* destination capacity. This differs from the default behavior for Java
* and Perl where trailing empty fields are not returned.
*
* The number of strings produced by the split operation is returned.
* This count includes the strings from capture groups in the delimiter pattern.
* This behavior differs from Java, which ignores capture groups.
*
* For the best performance on split() operations,
* `RegexMatcher::split()` is preferable to this function
*
* @param input The string to be split into fields. The field delimiters
* match the pattern (in the "this" object)
* @param dest An array of mutable UText structs to receive the results of the split.
* If a field is nullptr, a new UText is allocated to contain the results for
* that field. This new UText is not guaranteed to be mutable.
* @param destCapacity The number of elements in the destination array.
* If the number of fields found is less than destCapacity, the
* extra strings in the destination array are not altered.
* If the number of destination strings is less than the number
* of fields, the trailing part of the input string, including any
* field delimiters, is placed in the last destination string.
* @param status A reference to a UErrorCode to receive any errors.
* @return The number of destination strings used.
*
* @stable ICU 4.6
*/
virtual int32_t split(UText *input,
UText *dest[],
int32_t destCapacity,
UErrorCode &status) const;
/**
* ICU "poor man's RTTI", returns a UClassID for the actual class.
*
* @stable ICU 2.4
*/
virtual UClassID getDynamicClassID() const override;
/**
* ICU "poor man's RTTI", returns a UClassID for this class.
*
* @stable ICU 2.4
*/
static UClassID U_EXPORT2 getStaticClassID();
private:
//
// Implementation Data
//
UText *fPattern; // The original pattern string.
UnicodeString *fPatternString; // The original pattern UncodeString if relevant
uint32_t fFlags; // The flags used when compiling the pattern.
//
UVector64 *fCompiledPat; // The compiled pattern p-code.
UnicodeString fLiteralText; // Any literal string data from the pattern,
// after un-escaping, for use during the match.
UVector *fSets; // Any UnicodeSets referenced from the pattern.
Regex8BitSet *fSets8; // (and fast sets for latin-1 range.)
UErrorCode fDeferredStatus; // status if some prior error has left this
// RegexPattern in an unusable state.
int32_t fMinMatchLen; // Minimum Match Length. All matches will have length
// >= this value. For some patterns, this calculated
// value may be less than the true shortest
// possible match.
int32_t fFrameSize; // Size of a state stack frame in the
// execution engine.
int32_t fDataSize; // The size of the data needed by the pattern that
// does not go on the state stack, but has just
// a single copy per matcher.
UVector32 *fGroupMap; // Map from capture group number to position of
// the group's variables in the matcher stack frame.
int32_t fStartType; // Info on how a match must start.
int32_t fInitialStringIdx; //
int32_t fInitialStringLen;
UnicodeSet *fInitialChars;
UChar32 fInitialChar;
Regex8BitSet *fInitialChars8;
UBool fNeedsAltInput;
UHashtable *fNamedCaptureMap; // Map from capture group names to numbers.
friend class RegexCompile;
friend class RegexMatcher;
friend class RegexCImpl;
//
// Implementation Methods
//
void init(); // Common initialization, for use by constructors.
bool initNamedCaptureMap(); // Lazy init for fNamedCaptureMap.
void zap(); // Common cleanup
void dumpOp(int32_t index) const;
public:
#ifndef U_HIDE_INTERNAL_API
/**
* Dump a compiled pattern. Internal debug function.
* @internal
*/
void dumpPattern() const;
#endif /* U_HIDE_INTERNAL_API */
};
/**
* class RegexMatcher bundles together a regular expression pattern and
* input text to which the expression can be applied. It includes methods
* for testing for matches, and for find and replace operations.
*
* <p>Class RegexMatcher is not intended to be subclassed.</p>
*
* @stable ICU 2.4
*/
class U_I18N_API RegexMatcher final : public UObject {
public:
/**
* Construct a RegexMatcher for a regular expression.
* This is a convenience method that avoids the need to explicitly create
* a RegexPattern object. Note that if several RegexMatchers need to be
* created for the same expression, it will be more efficient to
* separately create and cache a RegexPattern object, and use
* its matcher() method to create the RegexMatcher objects.
*
* @param regexp The Regular Expression to be compiled.
* @param flags #URegexpFlag options, such as #UREGEX_CASE_INSENSITIVE.
* @param status Any errors are reported by setting this UErrorCode variable.
* @stable ICU 2.6
*/
RegexMatcher(const UnicodeString ®exp, uint32_t flags, UErrorCode &status);
/**
* Construct a RegexMatcher for a regular expression.
* This is a convenience method that avoids the need to explicitly create
* a RegexPattern object. Note that if several RegexMatchers need to be
* created for the same expression, it will be more efficient to
* separately create and cache a RegexPattern object, and use
* its matcher() method to create the RegexMatcher objects.
*
* @param regexp The regular expression to be compiled.
* @param flags #URegexpFlag options, such as #UREGEX_CASE_INSENSITIVE.
* @param status Any errors are reported by setting this UErrorCode variable.
*
* @stable ICU 4.6
*/
RegexMatcher(UText *regexp, uint32_t flags, UErrorCode &status);
/**
* Construct a RegexMatcher for a regular expression.
* This is a convenience method that avoids the need to explicitly create
* a RegexPattern object. Note that if several RegexMatchers need to be
* created for the same expression, it will be more efficient to
* separately create and cache a RegexPattern object, and use
* its matcher() method to create the RegexMatcher objects.
*
* The matcher will retain a reference to the supplied input string, and all regexp
* pattern matching operations happen directly on the original string. It is
* critical that the string not be altered or deleted before use by the regular
* expression operations is complete.
*
* @param regexp The Regular Expression to be compiled.
* @param input The string to match. The matcher retains a reference to the
* caller's string; mo copy is made.
* @param flags #URegexpFlag options, such as #UREGEX_CASE_INSENSITIVE.
* @param status Any errors are reported by setting this UErrorCode variable.
* @stable ICU 2.6
*/
RegexMatcher(const UnicodeString ®exp, const UnicodeString &input,
uint32_t flags, UErrorCode &status);
/**
* Construct a RegexMatcher for a regular expression.
* This is a convenience method that avoids the need to explicitly create
* a RegexPattern object. Note that if several RegexMatchers need to be
* created for the same expression, it will be more efficient to
* separately create and cache a RegexPattern object, and use
* its matcher() method to create the RegexMatcher objects.
*
* The matcher will make a shallow clone of the supplied input text, and all regexp
* pattern matching operations happen on this clone. While read-only operations on
* the supplied text are permitted, it is critical that the underlying string not be
* altered or deleted before use by the regular expression operations is complete.
*
* @param regexp The Regular Expression to be compiled.
* @param input The string to match. The matcher retains a shallow clone of the text.
* @param flags #URegexpFlag options, such as #UREGEX_CASE_INSENSITIVE.
* @param status Any errors are reported by setting this UErrorCode variable.
*
* @stable ICU 4.6
*/
RegexMatcher(UText *regexp, UText *input,
uint32_t flags, UErrorCode &status);
private:
/**
* Cause a compilation error if an application accidentally attempts to
* create a matcher with a (char16_t *) string as input rather than
* a UnicodeString. Avoids a dangling reference to a temporary string.
*
* To efficiently work with char16_t *strings, wrap the data in a UnicodeString
* using one of the aliasing constructors, such as
* `UnicodeString(UBool isTerminated, const char16_t *text, int32_t textLength);`
* or in a UText, using
* `utext_openUChars(UText *ut, const char16_t *text, int64_t textLength, UErrorCode *status);`
*/
RegexMatcher(const UnicodeString ®exp, const char16_t *input,
uint32_t flags, UErrorCode &status) = delete;
public:
/**
* Destructor.
*
* @stable ICU 2.4
*/
virtual ~RegexMatcher();
/**
* Attempts to match the entire input region against the pattern.
* @param status A reference to a UErrorCode to receive any errors.
* @return true if there is a match
* @stable ICU 2.4
*/
virtual UBool matches(UErrorCode &status);
/**
* Resets the matcher, then attempts to match the input beginning
* at the specified startIndex, and extending to the end of the input.
* The input region is reset to include the entire input string.
* A successful match must extend to the end of the input.
* @param startIndex The input string (native) index at which to begin matching.
* @param status A reference to a UErrorCode to receive any errors.
* @return true if there is a match
* @stable ICU 2.8
*/
virtual UBool matches(int64_t startIndex, UErrorCode &status);
/**
* Attempts to match the input string, starting from the beginning of the region,
* against the pattern. Like the matches() method, this function
* always starts at the beginning of the input region;
* unlike that function, it does not require that the entire region be matched.
*
* If the match succeeds then more information can be obtained via the start(),
* end(), and group() functions.
*
* @param status A reference to a UErrorCode to receive any errors.
* @return true if there is a match at the start of the input string.
* @stable ICU 2.4
*/
virtual UBool lookingAt(UErrorCode &status);
/**
* Attempts to match the input string, starting from the specified index, against the pattern.
* The match may be of any length, and is not required to extend to the end
* of the input string. Contrast with match().
*
* If the match succeeds then more information can be obtained via the start(),
* end(), and group() functions.
*
* @param startIndex The input string (native) index at which to begin matching.
* @param status A reference to a UErrorCode to receive any errors.
* @return true if there is a match.
* @stable ICU 2.8
*/
virtual UBool lookingAt(int64_t startIndex, UErrorCode &status);
/**
* Find the next pattern match in the input string.
* The find begins searching the input at the location following the end of
* the previous match, or at the start of the string if there is no previous match.
* If a match is found, `start()`, `end()` and `group()`
* will provide more information regarding the match.
* Note that if the input string is changed by the application,
* use find(startPos, status) instead of find(), because the saved starting
* position may not be valid with the altered input string.
* @return true if a match is found.
* @stable ICU 2.4
*/
virtual UBool find();
/**
* Find the next pattern match in the input string.
* The find begins searching the input at the location following the end of
* the previous match, or at the start of the string if there is no previous match.
* If a match is found, `start()`, `end()` and `group()`
* will provide more information regarding the match.
*
* Note that if the input string is changed by the application,
* use find(startPos, status) instead of find(), because the saved starting
* position may not be valid with the altered input string.
* @param status A reference to a UErrorCode to receive any errors.
* @return true if a match is found.
* @stable ICU 55
*/
virtual UBool find(UErrorCode &status);
/**
* Resets this RegexMatcher and then attempts to find the next substring of the
* input string that matches the pattern, starting at the specified index.
*
* @param start The (native) index in the input string to begin the search.
* @param status A reference to a UErrorCode to receive any errors.
* @return true if a match is found.
* @stable ICU 2.4
*/
virtual UBool find(int64_t start, UErrorCode &status);
/**
* Returns a string containing the text matched by the previous match.
* If the pattern can match an empty string, an empty string may be returned.
* @param status A reference to a UErrorCode to receive any errors.
* Possible errors are U_REGEX_INVALID_STATE if no match
* has been attempted or the last match failed.
* @return a string containing the matched input text.
* @stable ICU 2.4
*/
virtual UnicodeString group(UErrorCode &status) const;
/**
* Returns a string containing the text captured by the given group
* during the previous match operation. Group(0) is the entire match.
*
* A zero length string is returned both for capture groups that did not
* participate in the match and for actual zero length matches.
* To distinguish between these two cases use the function start(),
* which returns -1 for non-participating groups.
*
* @param groupNum the capture group number
* @param status A reference to a UErrorCode to receive any errors.
* Possible errors are U_REGEX_INVALID_STATE if no match
* has been attempted or the last match failed and
* U_INDEX_OUTOFBOUNDS_ERROR for a bad capture group number.
* @return the captured text
* @stable ICU 2.4
*/
virtual UnicodeString group(int32_t groupNum, UErrorCode &status) const;
/**
* Returns the number of capturing groups in this matcher's pattern.
* @return the number of capture groups
* @stable ICU 2.4
*/
virtual int32_t groupCount() const;
/**
* Returns a shallow clone of the entire live input string with the UText current native index
* set to the beginning of the requested group.
*
* @param dest The UText into which the input should be cloned, or nullptr to create a new UText
* @param group_len A reference to receive the length of the desired capture group
* @param status A reference to a UErrorCode to receive any errors.
* Possible errors are U_REGEX_INVALID_STATE if no match
* has been attempted or the last match failed and
* U_INDEX_OUTOFBOUNDS_ERROR for a bad capture group number.
* @return dest if non-nullptr, a shallow copy of the input text otherwise
*
* @stable ICU 4.6
*/
virtual UText *group(UText *dest, int64_t &group_len, UErrorCode &status) const;
/**
* Returns a shallow clone of the entire live input string with the UText current native index
* set to the beginning of the requested group.
*
* A group length of zero is returned both for capture groups that did not
* participate in the match and for actual zero length matches.
* To distinguish between these two cases use the function start(),
* which returns -1 for non-participating groups.
*
* @param groupNum The capture group number.
* @param dest The UText into which the input should be cloned, or nullptr to create a new UText.
* @param group_len A reference to receive the length of the desired capture group
* @param status A reference to a UErrorCode to receive any errors.
* Possible errors are U_REGEX_INVALID_STATE if no match
* has been attempted or the last match failed and
* U_INDEX_OUTOFBOUNDS_ERROR for a bad capture group number.
* @return dest if non-nullptr, a shallow copy of the input text otherwise
*
* @stable ICU 4.6
*/
virtual UText *group(int32_t groupNum, UText *dest, int64_t &group_len, UErrorCode &status) const;
/**
* Returns the index in the input string of the start of the text matched
* during the previous match operation.
* @param status a reference to a UErrorCode to receive any errors.
* @return The (native) position in the input string of the start of the last match.
* @stable ICU 2.4
*/
virtual int32_t start(UErrorCode &status) const;
/**
* Returns the index in the input string of the start of the text matched
* during the previous match operation.
* @param status a reference to a UErrorCode to receive any errors.
* @return The (native) position in the input string of the start of the last match.
* @stable ICU 4.6
*/
virtual int64_t start64(UErrorCode &status) const;
/**
* Returns the index in the input string of the start of the text matched by the
* specified capture group during the previous match operation. Return -1 if
* the capture group exists in the pattern, but was not part of the last match.
*
* @param group the capture group number
* @param status A reference to a UErrorCode to receive any errors. Possible
* errors are U_REGEX_INVALID_STATE if no match has been
* attempted or the last match failed, and
* U_INDEX_OUTOFBOUNDS_ERROR for a bad capture group number
* @return the (native) start position of substring matched by the specified group.
* @stable ICU 2.4
*/
virtual int32_t start(int32_t group, UErrorCode &status) const;
/**
* Returns the index in the input string of the start of the text matched by the
* specified capture group during the previous match operation. Return -1 if
* the capture group exists in the pattern, but was not part of the last match.
*
* @param group the capture group number.
* @param status A reference to a UErrorCode to receive any errors. Possible
* errors are U_REGEX_INVALID_STATE if no match has been
* attempted or the last match failed, and
* U_INDEX_OUTOFBOUNDS_ERROR for a bad capture group number.
* @return the (native) start position of substring matched by the specified group.
* @stable ICU 4.6
*/
virtual int64_t start64(int32_t group, UErrorCode &status) const;
/**
* Returns the index in the input string of the first character following the
* text matched during the previous match operation.
*
* @param status A reference to a UErrorCode to receive any errors. Possible
* errors are U_REGEX_INVALID_STATE if no match has been
* attempted or the last match failed.
* @return the index of the last character matched, plus one.
* The index value returned is a native index, corresponding to
* code units for the underlying encoding type, for example,
* a byte index for UTF-8.
* @stable ICU 2.4
*/
virtual int32_t end(UErrorCode &status) const;