This repository was archived by the owner on Jul 11, 2025. It is now read-only.
forked from phoboslab/JavaScriptCore-iOS
-
Notifications
You must be signed in to change notification settings - Fork 0
Expand file tree
/
Copy pathuset.h
More file actions
1120 lines (1045 loc) · 39.3 KB
/
uset.h
File metadata and controls
1120 lines (1045 loc) · 39.3 KB
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
/*
*******************************************************************************
*
* Copyright (C) 2002-2010, International Business Machines
* Corporation and others. All Rights Reserved.
*
*******************************************************************************
* file name: uset.h
* encoding: US-ASCII
* tab size: 8 (not used)
* indentation:4
*
* created on: 2002mar07
* created by: Markus W. Scherer
*
* C version of UnicodeSet.
*/
/**
* \file
* \brief C API: Unicode Set
*
* <p>This is a C wrapper around the C++ UnicodeSet class.</p>
*/
#ifndef __USET_H__
#define __USET_H__
#include "unicode/utypes.h"
#include "unicode/uchar.h"
#include "unicode/localpointer.h"
#ifndef UCNV_H
struct USet;
/**
* A UnicodeSet. Use the uset_* API to manipulate. Create with
* uset_open*, and destroy with uset_close.
* @stable ICU 2.4
*/
typedef struct USet USet;
#endif
/**
* Bitmask values to be passed to uset_openPatternOptions() or
* uset_applyPattern() taking an option parameter.
* @stable ICU 2.4
*/
enum {
/**
* Ignore white space within patterns unless quoted or escaped.
* @stable ICU 2.4
*/
USET_IGNORE_SPACE = 1,
/**
* Enable case insensitive matching. E.g., "[ab]" with this flag
* will match 'a', 'A', 'b', and 'B'. "[^ab]" with this flag will
* match all except 'a', 'A', 'b', and 'B'. This performs a full
* closure over case mappings, e.g. U+017F for s.
*
* The resulting set is a superset of the input for the code points but
* not for the strings.
* It performs a case mapping closure of the code points and adds
* full case folding strings for the code points, and reduces strings of
* the original set to their full case folding equivalents.
*
* This is designed for case-insensitive matches, for example
* in regular expressions. The full code point case closure allows checking of
* an input character directly against the closure set.
* Strings are matched by comparing the case-folded form from the closure
* set with an incremental case folding of the string in question.
*
* The closure set will also contain single code points if the original
* set contained case-equivalent strings (like U+00DF for "ss" or "Ss" etc.).
* This is not necessary (that is, redundant) for the above matching method
* but results in the same closure sets regardless of whether the original
* set contained the code point or a string.
*
* @stable ICU 2.4
*/
USET_CASE_INSENSITIVE = 2,
/**
* Enable case insensitive matching. E.g., "[ab]" with this flag
* will match 'a', 'A', 'b', and 'B'. "[^ab]" with this flag will
* match all except 'a', 'A', 'b', and 'B'. This adds the lower-,
* title-, and uppercase mappings as well as the case folding
* of each existing element in the set.
* @stable ICU 3.2
*/
USET_ADD_CASE_MAPPINGS = 4,
/**
* Enough for any single-code point set
* @internal
*/
USET_SERIALIZED_STATIC_ARRAY_CAPACITY=8
};
/**
* Argument values for whether span() and similar functions continue while
* the current character is contained vs. not contained in the set.
*
* The functionality is straightforward for sets with only single code points,
* without strings (which is the common case):
* - USET_SPAN_CONTAINED and USET_SPAN_SIMPLE
* work the same.
* - span() and spanBack() partition any string the same way when
* alternating between span(USET_SPAN_NOT_CONTAINED) and
* span(either "contained" condition).
* - Using a complemented (inverted) set and the opposite span conditions
* yields the same results.
*
* When a set contains multi-code point strings, then these statements may not
* be true, depending on the strings in the set (for example, whether they
* overlap with each other) and the string that is processed.
* For a set with strings:
* - The complement of the set contains the opposite set of code points,
* but the same set of strings.
* Therefore, complementing both the set and the span conditions
* may yield different results.
* - When starting spans at different positions in a string
* (span(s, ...) vs. span(s+1, ...)) the ends of the spans may be different
* because a set string may start before the later position.
* - span(USET_SPAN_SIMPLE) may be shorter than
* span(USET_SPAN_CONTAINED) because it will not recursively try
* all possible paths.
* For example, with a set which contains the three strings "xy", "xya" and "ax",
* span("xyax", USET_SPAN_CONTAINED) will return 4 but
* span("xyax", USET_SPAN_SIMPLE) will return 3.
* span(USET_SPAN_SIMPLE) will never be longer than
* span(USET_SPAN_CONTAINED).
* - With either "contained" condition, span() and spanBack() may partition
* a string in different ways.
* For example, with a set which contains the two strings "ab" and "ba",
* and when processing the string "aba",
* span() will yield contained/not-contained boundaries of { 0, 2, 3 }
* while spanBack() will yield boundaries of { 0, 1, 3 }.
*
* Note: If it is important to get the same boundaries whether iterating forward
* or backward through a string, then either only span() should be used and
* the boundaries cached for backward operation, or an ICU BreakIterator
* could be used.
*
* Note: Unpaired surrogates are treated like surrogate code points.
* Similarly, set strings match only on code point boundaries,
* never in the middle of a surrogate pair.
* Illegal UTF-8 sequences are treated like U+FFFD.
* When processing UTF-8 strings, malformed set strings
* (strings with unpaired surrogates which cannot be converted to UTF-8)
* are ignored.
*
* @stable ICU 3.8
*/
typedef enum USetSpanCondition {
/**
* Continue a span() while there is no set element at the current position.
* Stops before the first set element (character or string).
* (For code points only, this is like while contains(current)==FALSE).
*
* When span() returns, the substring between where it started and the position
* it returned consists only of characters that are not in the set,
* and none of its strings overlap with the span.
*
* @stable ICU 3.8
*/
USET_SPAN_NOT_CONTAINED = 0,
/**
* Continue a span() while there is a set element at the current position.
* (For characters only, this is like while contains(current)==TRUE).
*
* When span() returns, the substring between where it started and the position
* it returned consists only of set elements (characters or strings) that are in the set.
*
* If a set contains strings, then the span will be the longest substring
* matching any of the possible concatenations of set elements (characters or strings).
* (There must be a single, non-overlapping concatenation of characters or strings.)
* This is equivalent to a POSIX regular expression for (OR of each set element)*.
*
* @stable ICU 3.8
*/
USET_SPAN_CONTAINED = 1,
/**
* Continue a span() while there is a set element at the current position.
* (For characters only, this is like while contains(current)==TRUE).
*
* When span() returns, the substring between where it started and the position
* it returned consists only of set elements (characters or strings) that are in the set.
*
* If a set only contains single characters, then this is the same
* as USET_SPAN_CONTAINED.
*
* If a set contains strings, then the span will be the longest substring
* with a match at each position with the longest single set element (character or string).
*
* Use this span condition together with other longest-match algorithms,
* such as ICU converters (ucnv_getUnicodeSet()).
*
* @stable ICU 3.8
*/
USET_SPAN_SIMPLE = 2,
/**
* One more than the last span condition.
* @stable ICU 3.8
*/
USET_SPAN_CONDITION_COUNT
} USetSpanCondition;
/**
* A serialized form of a Unicode set. Limited manipulations are
* possible directly on a serialized set. See below.
* @stable ICU 2.4
*/
typedef struct USerializedSet {
/**
* The serialized Unicode Set.
* @stable ICU 2.4
*/
const uint16_t *array;
/**
* The length of the array that contains BMP characters.
* @stable ICU 2.4
*/
int32_t bmpLength;
/**
* The total length of the array.
* @stable ICU 2.4
*/
int32_t length;
/**
* A small buffer for the array to reduce memory allocations.
* @stable ICU 2.4
*/
uint16_t staticArray[USET_SERIALIZED_STATIC_ARRAY_CAPACITY];
} USerializedSet;
/*********************************************************************
* USet API
*********************************************************************/
/**
* Create an empty USet object.
* Equivalent to uset_open(1, 0).
* @return a newly created USet. The caller must call uset_close() on
* it when done.
* @stable ICU 4.2
*/
U_STABLE USet* U_EXPORT2
uset_openEmpty();
/**
* Creates a USet object that contains the range of characters
* start..end, inclusive. If <code>start > end</code>
* then an empty set is created (same as using uset_openEmpty()).
* @param start first character of the range, inclusive
* @param end last character of the range, inclusive
* @return a newly created USet. The caller must call uset_close() on
* it when done.
* @stable ICU 2.4
*/
U_STABLE USet* U_EXPORT2
uset_open(UChar32 start, UChar32 end);
/**
* Creates a set from the given pattern. See the UnicodeSet class
* description for the syntax of the pattern language.
* @param pattern a string specifying what characters are in the set
* @param patternLength the length of the pattern, or -1 if null
* terminated
* @param ec the error code
* @stable ICU 2.4
*/
U_STABLE USet* U_EXPORT2
uset_openPattern(const UChar* pattern, int32_t patternLength,
UErrorCode* ec);
/**
* Creates a set from the given pattern. See the UnicodeSet class
* description for the syntax of the pattern language.
* @param pattern a string specifying what characters are in the set
* @param patternLength the length of the pattern, or -1 if null
* terminated
* @param options bitmask for options to apply to the pattern.
* Valid options are USET_IGNORE_SPACE and USET_CASE_INSENSITIVE.
* @param ec the error code
* @stable ICU 2.4
*/
U_STABLE USet* U_EXPORT2
uset_openPatternOptions(const UChar* pattern, int32_t patternLength,
uint32_t options,
UErrorCode* ec);
/**
* Disposes of the storage used by a USet object. This function should
* be called exactly once for objects returned by uset_open().
* @param set the object to dispose of
* @stable ICU 2.4
*/
U_STABLE void U_EXPORT2
uset_close(USet* set);
#if U_SHOW_CPLUSPLUS_API
U_NAMESPACE_BEGIN
/**
* \class LocalUSetPointer
* "Smart pointer" class, closes a USet via uset_close().
* For most methods see the LocalPointerBase base class.
*
* @see LocalPointerBase
* @see LocalPointer
* @stable ICU 4.4
*/
U_DEFINE_LOCAL_OPEN_POINTER(LocalUSetPointer, USet, uset_close);
U_NAMESPACE_END
#endif
/**
* Returns a copy of this object.
* If this set is frozen, then the clone will be frozen as well.
* Use uset_cloneAsThawed() for a mutable clone of a frozen set.
* @param set the original set
* @return the newly allocated copy of the set
* @see uset_cloneAsThawed
* @stable ICU 3.8
*/
U_STABLE USet * U_EXPORT2
uset_clone(const USet *set);
/**
* Determines whether the set has been frozen (made immutable) or not.
* See the ICU4J Freezable interface for details.
* @param set the set
* @return TRUE/FALSE for whether the set has been frozen
* @see uset_freeze
* @see uset_cloneAsThawed
* @stable ICU 3.8
*/
U_STABLE UBool U_EXPORT2
uset_isFrozen(const USet *set);
/**
* Freeze the set (make it immutable).
* Once frozen, it cannot be unfrozen and is therefore thread-safe
* until it is deleted.
* See the ICU4J Freezable interface for details.
* Freezing the set may also make some operations faster, for example
* uset_contains() and uset_span().
* A frozen set will not be modified. (It remains frozen.)
* @param set the set
* @return the same set, now frozen
* @see uset_isFrozen
* @see uset_cloneAsThawed
* @stable ICU 3.8
*/
U_STABLE void U_EXPORT2
uset_freeze(USet *set);
/**
* Clone the set and make the clone mutable.
* See the ICU4J Freezable interface for details.
* @param set the set
* @return the mutable clone
* @see uset_freeze
* @see uset_isFrozen
* @see uset_clone
* @stable ICU 3.8
*/
U_STABLE USet * U_EXPORT2
uset_cloneAsThawed(const USet *set);
/**
* Causes the USet object to represent the range <code>start - end</code>.
* If <code>start > end</code> then this USet is set to an empty range.
* A frozen set will not be modified.
* @param set the object to set to the given range
* @param start first character in the set, inclusive
* @param end last character in the set, inclusive
* @stable ICU 3.2
*/
U_STABLE void U_EXPORT2
uset_set(USet* set,
UChar32 start, UChar32 end);
/**
* Modifies the set to represent the set specified by the given
* pattern. See the UnicodeSet class description for the syntax of
* the pattern language. See also the User Guide chapter about UnicodeSet.
* <em>Empties the set passed before applying the pattern.</em>
* A frozen set will not be modified.
* @param set The set to which the pattern is to be applied.
* @param pattern A pointer to UChar string specifying what characters are in the set.
* The character at pattern[0] must be a '['.
* @param patternLength The length of the UChar string. -1 if NUL terminated.
* @param options A bitmask for options to apply to the pattern.
* Valid options are USET_IGNORE_SPACE and USET_CASE_INSENSITIVE.
* @param status Returns an error if the pattern cannot be parsed.
* @return Upon successful parse, the value is either
* the index of the character after the closing ']'
* of the parsed pattern.
* If the status code indicates failure, then the return value
* is the index of the error in the source.
*
* @stable ICU 2.8
*/
U_STABLE int32_t U_EXPORT2
uset_applyPattern(USet *set,
const UChar *pattern, int32_t patternLength,
uint32_t options,
UErrorCode *status);
/**
* Modifies the set to contain those code points which have the given value
* for the given binary or enumerated property, as returned by
* u_getIntPropertyValue. Prior contents of this set are lost.
* A frozen set will not be modified.
*
* @param set the object to contain the code points defined by the property
*
* @param prop a property in the range UCHAR_BIN_START..UCHAR_BIN_LIMIT-1
* or UCHAR_INT_START..UCHAR_INT_LIMIT-1
* or UCHAR_MASK_START..UCHAR_MASK_LIMIT-1.
*
* @param value a value in the range u_getIntPropertyMinValue(prop)..
* u_getIntPropertyMaxValue(prop), with one exception. If prop is
* UCHAR_GENERAL_CATEGORY_MASK, then value should not be a UCharCategory, but
* rather a mask value produced by U_GET_GC_MASK(). This allows grouped
* categories such as [:L:] to be represented.
*
* @param ec error code input/output parameter
*
* @stable ICU 3.2
*/
U_STABLE void U_EXPORT2
uset_applyIntPropertyValue(USet* set,
UProperty prop, int32_t value, UErrorCode* ec);
/**
* Modifies the set to contain those code points which have the
* given value for the given property. Prior contents of this
* set are lost.
* A frozen set will not be modified.
*
* @param set the object to contain the code points defined by the given
* property and value alias
*
* @param prop a string specifying a property alias, either short or long.
* The name is matched loosely. See PropertyAliases.txt for names and a
* description of loose matching. If the value string is empty, then this
* string is interpreted as either a General_Category value alias, a Script
* value alias, a binary property alias, or a special ID. Special IDs are
* matched loosely and correspond to the following sets:
*
* "ANY" = [\\u0000-\\U0010FFFF],
* "ASCII" = [\\u0000-\\u007F],
* "Assigned" = [:^Cn:].
*
* @param propLength the length of the prop, or -1 if NULL
*
* @param value a string specifying a value alias, either short or long.
* The name is matched loosely. See PropertyValueAliases.txt for names
* and a description of loose matching. In addition to aliases listed,
* numeric values and canonical combining classes may be expressed
* numerically, e.g., ("nv", "0.5") or ("ccc", "220"). The value string
* may also be empty.
*
* @param valueLength the length of the value, or -1 if NULL
*
* @param ec error code input/output parameter
*
* @stable ICU 3.2
*/
U_STABLE void U_EXPORT2
uset_applyPropertyAlias(USet* set,
const UChar *prop, int32_t propLength,
const UChar *value, int32_t valueLength,
UErrorCode* ec);
/**
* Return true if the given position, in the given pattern, appears
* to be the start of a UnicodeSet pattern.
*
* @param pattern a string specifying the pattern
* @param patternLength the length of the pattern, or -1 if NULL
* @param pos the given position
* @stable ICU 3.2
*/
U_STABLE UBool U_EXPORT2
uset_resemblesPattern(const UChar *pattern, int32_t patternLength,
int32_t pos);
/**
* Returns a string representation of this set. If the result of
* calling this function is passed to a uset_openPattern(), it
* will produce another set that is equal to this one.
* @param set the set
* @param result the string to receive the rules, may be NULL
* @param resultCapacity the capacity of result, may be 0 if result is NULL
* @param escapeUnprintable if TRUE then convert unprintable
* character to their hex escape representations, \\uxxxx or
* \\Uxxxxxxxx. Unprintable characters are those other than
* U+000A, U+0020..U+007E.
* @param ec error code.
* @return length of string, possibly larger than resultCapacity
* @stable ICU 2.4
*/
U_STABLE int32_t U_EXPORT2
uset_toPattern(const USet* set,
UChar* result, int32_t resultCapacity,
UBool escapeUnprintable,
UErrorCode* ec);
/**
* Adds the given character to the given USet. After this call,
* uset_contains(set, c) will return TRUE.
* A frozen set will not be modified.
* @param set the object to which to add the character
* @param c the character to add
* @stable ICU 2.4
*/
U_STABLE void U_EXPORT2
uset_add(USet* set, UChar32 c);
/**
* Adds all of the elements in the specified set to this set if
* they're not already present. This operation effectively
* modifies this set so that its value is the <i>union</i> of the two
* sets. The behavior of this operation is unspecified if the specified
* collection is modified while the operation is in progress.
* A frozen set will not be modified.
*
* @param set the object to which to add the set
* @param additionalSet the source set whose elements are to be added to this set.
* @stable ICU 2.6
*/
U_STABLE void U_EXPORT2
uset_addAll(USet* set, const USet *additionalSet);
/**
* Adds the given range of characters to the given USet. After this call,
* uset_contains(set, start, end) will return TRUE.
* A frozen set will not be modified.
* @param set the object to which to add the character
* @param start the first character of the range to add, inclusive
* @param end the last character of the range to add, inclusive
* @stable ICU 2.2
*/
U_STABLE void U_EXPORT2
uset_addRange(USet* set, UChar32 start, UChar32 end);
/**
* Adds the given string to the given USet. After this call,
* uset_containsString(set, str, strLen) will return TRUE.
* A frozen set will not be modified.
* @param set the object to which to add the character
* @param str the string to add
* @param strLen the length of the string or -1 if null terminated.
* @stable ICU 2.4
*/
U_STABLE void U_EXPORT2
uset_addString(USet* set, const UChar* str, int32_t strLen);
/**
* Adds each of the characters in this string to the set. Thus "ch" => {"c", "h"}
* If this set already any particular character, it has no effect on that character.
* A frozen set will not be modified.
* @param set the object to which to add the character
* @param str the source string
* @param strLen the length of the string or -1 if null terminated.
* @stable ICU 3.4
*/
U_STABLE void U_EXPORT2
uset_addAllCodePoints(USet* set, const UChar *str, int32_t strLen);
/**
* Removes the given character from the given USet. After this call,
* uset_contains(set, c) will return FALSE.
* A frozen set will not be modified.
* @param set the object from which to remove the character
* @param c the character to remove
* @stable ICU 2.4
*/
U_STABLE void U_EXPORT2
uset_remove(USet* set, UChar32 c);
/**
* Removes the given range of characters from the given USet. After this call,
* uset_contains(set, start, end) will return FALSE.
* A frozen set will not be modified.
* @param set the object to which to add the character
* @param start the first character of the range to remove, inclusive
* @param end the last character of the range to remove, inclusive
* @stable ICU 2.2
*/
U_STABLE void U_EXPORT2
uset_removeRange(USet* set, UChar32 start, UChar32 end);
/**
* Removes the given string to the given USet. After this call,
* uset_containsString(set, str, strLen) will return FALSE.
* A frozen set will not be modified.
* @param set the object to which to add the character
* @param str the string to remove
* @param strLen the length of the string or -1 if null terminated.
* @stable ICU 2.4
*/
U_STABLE void U_EXPORT2
uset_removeString(USet* set, const UChar* str, int32_t strLen);
/**
* Removes from this set all of its elements that are contained in the
* specified set. This operation effectively modifies this
* set so that its value is the <i>asymmetric set difference</i> of
* the two sets.
* A frozen set will not be modified.
* @param set the object from which the elements are to be removed
* @param removeSet the object that defines which elements will be
* removed from this set
* @stable ICU 3.2
*/
U_STABLE void U_EXPORT2
uset_removeAll(USet* set, const USet* removeSet);
/**
* Retain only the elements in this set that are contained in the
* specified range. If <code>start > end</code> then an empty range is
* retained, leaving the set empty. This is equivalent to
* a boolean logic AND, or a set INTERSECTION.
* A frozen set will not be modified.
*
* @param set the object for which to retain only the specified range
* @param start first character, inclusive, of range to be retained
* to this set.
* @param end last character, inclusive, of range to be retained
* to this set.
* @stable ICU 3.2
*/
U_STABLE void U_EXPORT2
uset_retain(USet* set, UChar32 start, UChar32 end);
/**
* Retains only the elements in this set that are contained in the
* specified set. In other words, removes from this set all of
* its elements that are not contained in the specified set. This
* operation effectively modifies this set so that its value is
* the <i>intersection</i> of the two sets.
* A frozen set will not be modified.
*
* @param set the object on which to perform the retain
* @param retain set that defines which elements this set will retain
* @stable ICU 3.2
*/
U_STABLE void U_EXPORT2
uset_retainAll(USet* set, const USet* retain);
/**
* Reallocate this objects internal structures to take up the least
* possible space, without changing this object's value.
* A frozen set will not be modified.
*
* @param set the object on which to perfrom the compact
* @stable ICU 3.2
*/
U_STABLE void U_EXPORT2
uset_compact(USet* set);
/**
* Inverts this set. This operation modifies this set so that
* its value is its complement. This operation does not affect
* the multicharacter strings, if any.
* A frozen set will not be modified.
* @param set the set
* @stable ICU 2.4
*/
U_STABLE void U_EXPORT2
uset_complement(USet* set);
/**
* Complements in this set all elements contained in the specified
* set. Any character in the other set will be removed if it is
* in this set, or will be added if it is not in this set.
* A frozen set will not be modified.
*
* @param set the set with which to complement
* @param complement set that defines which elements will be xor'ed
* from this set.
* @stable ICU 3.2
*/
U_STABLE void U_EXPORT2
uset_complementAll(USet* set, const USet* complement);
/**
* Removes all of the elements from this set. This set will be
* empty after this call returns.
* A frozen set will not be modified.
* @param set the set
* @stable ICU 2.4
*/
U_STABLE void U_EXPORT2
uset_clear(USet* set);
/**
* Close this set over the given attribute. For the attribute
* USET_CASE, the result is to modify this set so that:
*
* 1. For each character or string 'a' in this set, all strings or
* characters 'b' such that foldCase(a) == foldCase(b) are added
* to this set.
*
* 2. For each string 'e' in the resulting set, if e !=
* foldCase(e), 'e' will be removed.
*
* Example: [aq\\u00DF{Bc}{bC}{Fi}] => [aAqQ\\u00DF\\uFB01{ss}{bc}{fi}]
*
* (Here foldCase(x) refers to the operation u_strFoldCase, and a
* == b denotes that the contents are the same, not pointer
* comparison.)
*
* A frozen set will not be modified.
*
* @param set the set
*
* @param attributes bitmask for attributes to close over.
* Currently only the USET_CASE bit is supported. Any undefined bits
* are ignored.
* @stable ICU 4.2
*/
U_STABLE void U_EXPORT2
uset_closeOver(USet* set, int32_t attributes);
/**
* Remove all strings from this set.
*
* @param set the set
* @stable ICU 4.2
*/
U_STABLE void U_EXPORT2
uset_removeAllStrings(USet* set);
/**
* Returns TRUE if the given USet contains no characters and no
* strings.
* @param set the set
* @return true if set is empty
* @stable ICU 2.4
*/
U_STABLE UBool U_EXPORT2
uset_isEmpty(const USet* set);
/**
* Returns TRUE if the given USet contains the given character.
* This function works faster with a frozen set.
* @param set the set
* @param c The codepoint to check for within the set
* @return true if set contains c
* @stable ICU 2.4
*/
U_STABLE UBool U_EXPORT2
uset_contains(const USet* set, UChar32 c);
/**
* Returns TRUE if the given USet contains all characters c
* where start <= c && c <= end.
* @param set the set
* @param start the first character of the range to test, inclusive
* @param end the last character of the range to test, inclusive
* @return TRUE if set contains the range
* @stable ICU 2.2
*/
U_STABLE UBool U_EXPORT2
uset_containsRange(const USet* set, UChar32 start, UChar32 end);
/**
* Returns TRUE if the given USet contains the given string.
* @param set the set
* @param str the string
* @param strLen the length of the string or -1 if null terminated.
* @return true if set contains str
* @stable ICU 2.4
*/
U_STABLE UBool U_EXPORT2
uset_containsString(const USet* set, const UChar* str, int32_t strLen);
/**
* Returns the index of the given character within this set, where
* the set is ordered by ascending code point. If the character
* is not in this set, return -1. The inverse of this method is
* <code>charAt()</code>.
* @param set the set
* @param c the character to obtain the index for
* @return an index from 0..size()-1, or -1
* @stable ICU 3.2
*/
U_STABLE int32_t U_EXPORT2
uset_indexOf(const USet* set, UChar32 c);
/**
* Returns the character at the given index within this set, where
* the set is ordered by ascending code point. If the index is
* out of range, return (UChar32)-1. The inverse of this method is
* <code>indexOf()</code>.
* @param set the set
* @param charIndex an index from 0..size()-1 to obtain the char for
* @return the character at the given index, or (UChar32)-1.
* @stable ICU 3.2
*/
U_STABLE UChar32 U_EXPORT2
uset_charAt(const USet* set, int32_t charIndex);
/**
* Returns the number of characters and strings contained in the given
* USet.
* @param set the set
* @return a non-negative integer counting the characters and strings
* contained in set
* @stable ICU 2.4
*/
U_STABLE int32_t U_EXPORT2
uset_size(const USet* set);
/**
* Returns the number of items in this set. An item is either a range
* of characters or a single multicharacter string.
* @param set the set
* @return a non-negative integer counting the character ranges
* and/or strings contained in set
* @stable ICU 2.4
*/
U_STABLE int32_t U_EXPORT2
uset_getItemCount(const USet* set);
/**
* Returns an item of this set. An item is either a range of
* characters or a single multicharacter string.
* @param set the set
* @param itemIndex a non-negative integer in the range 0..
* uset_getItemCount(set)-1
* @param start pointer to variable to receive first character
* in range, inclusive
* @param end pointer to variable to receive last character in range,
* inclusive
* @param str buffer to receive the string, may be NULL
* @param strCapacity capacity of str, or 0 if str is NULL
* @param ec error code
* @return the length of the string (>= 2), or 0 if the item is a
* range, in which case it is the range *start..*end, or -1 if
* itemIndex is out of range
* @stable ICU 2.4
*/
U_STABLE int32_t U_EXPORT2
uset_getItem(const USet* set, int32_t itemIndex,
UChar32* start, UChar32* end,
UChar* str, int32_t strCapacity,
UErrorCode* ec);
/**
* Returns true if set1 contains all the characters and strings
* of set2. It answers the question, 'Is set1 a superset of set2?'
* @param set1 set to be checked for containment
* @param set2 set to be checked for containment
* @return true if the test condition is met
* @stable ICU 3.2
*/
U_STABLE UBool U_EXPORT2
uset_containsAll(const USet* set1, const USet* set2);
/**
* Returns true if this set contains all the characters
* of the given string. This is does not check containment of grapheme
* clusters, like uset_containsString.
* @param set set of characters to be checked for containment
* @param str string containing codepoints to be checked for containment
* @param strLen the length of the string or -1 if null terminated.
* @return true if the test condition is met
* @stable ICU 3.4
*/
U_STABLE UBool U_EXPORT2
uset_containsAllCodePoints(const USet* set, const UChar *str, int32_t strLen);
/**
* Returns true if set1 contains none of the characters and strings
* of set2. It answers the question, 'Is set1 a disjoint set of set2?'
* @param set1 set to be checked for containment
* @param set2 set to be checked for containment
* @return true if the test condition is met
* @stable ICU 3.2
*/
U_STABLE UBool U_EXPORT2
uset_containsNone(const USet* set1, const USet* set2);
/**
* Returns true if set1 contains some of the characters and strings
* of set2. It answers the question, 'Does set1 and set2 have an intersection?'
* @param set1 set to be checked for containment
* @param set2 set to be checked for containment
* @return true if the test condition is met
* @stable ICU 3.2
*/
U_STABLE UBool U_EXPORT2
uset_containsSome(const USet* set1, const USet* set2);
/**
* Returns the length of the initial substring of the input string which
* consists only of characters and strings that are contained in this set
* (USET_SPAN_CONTAINED, USET_SPAN_SIMPLE),
* or only of characters and strings that are not contained
* in this set (USET_SPAN_NOT_CONTAINED).
* See USetSpanCondition for details.
* Similar to the strspn() C library function.
* Unpaired surrogates are treated according to contains() of their surrogate code points.
* This function works faster with a frozen set and with a non-negative string length argument.
* @param set the set
* @param s start of the string
* @param length of the string; can be -1 for NUL-terminated
* @param spanCondition specifies the containment condition
* @return the length of the initial substring according to the spanCondition;
* 0 if the start of the string does not fit the spanCondition
* @stable ICU 3.8
* @see USetSpanCondition
*/
U_STABLE int32_t U_EXPORT2
uset_span(const USet *set, const UChar *s, int32_t length, USetSpanCondition spanCondition);
/**
* Returns the start of the trailing substring of the input string which
* consists only of characters and strings that are contained in this set
* (USET_SPAN_CONTAINED, USET_SPAN_SIMPLE),
* or only of characters and strings that are not contained
* in this set (USET_SPAN_NOT_CONTAINED).
* See USetSpanCondition for details.
* Unpaired surrogates are treated according to contains() of their surrogate code points.
* This function works faster with a frozen set and with a non-negative string length argument.
* @param set the set
* @param s start of the string
* @param length of the string; can be -1 for NUL-terminated
* @param spanCondition specifies the containment condition
* @return the start of the trailing substring according to the spanCondition;
* the string length if the end of the string does not fit the spanCondition
* @stable ICU 3.8
* @see USetSpanCondition
*/
U_STABLE int32_t U_EXPORT2
uset_spanBack(const USet *set, const UChar *s, int32_t length, USetSpanCondition spanCondition);
/**
* Returns the length of the initial substring of the input string which
* consists only of characters and strings that are contained in this set
* (USET_SPAN_CONTAINED, USET_SPAN_SIMPLE),
* or only of characters and strings that are not contained
* in this set (USET_SPAN_NOT_CONTAINED).
* See USetSpanCondition for details.
* Similar to the strspn() C library function.
* Malformed byte sequences are treated according to contains(0xfffd).
* This function works faster with a frozen set and with a non-negative string length argument.
* @param set the set
* @param s start of the string (UTF-8)
* @param length of the string; can be -1 for NUL-terminated
* @param spanCondition specifies the containment condition
* @return the length of the initial substring according to the spanCondition;
* 0 if the start of the string does not fit the spanCondition
* @stable ICU 3.8
* @see USetSpanCondition
*/
U_STABLE int32_t U_EXPORT2
uset_spanUTF8(const USet *set, const char *s, int32_t length, USetSpanCondition spanCondition);
/**
* Returns the start of the trailing substring of the input string which
* consists only of characters and strings that are contained in this set
* (USET_SPAN_CONTAINED, USET_SPAN_SIMPLE),
* or only of characters and strings that are not contained
* in this set (USET_SPAN_NOT_CONTAINED).
* See USetSpanCondition for details.
* Malformed byte sequences are treated according to contains(0xfffd).
* This function works faster with a frozen set and with a non-negative string length argument.
* @param set the set
* @param s start of the string (UTF-8)
* @param length of the string; can be -1 for NUL-terminated
* @param spanCondition specifies the containment condition
* @return the start of the trailing substring according to the spanCondition;
* the string length if the end of the string does not fit the spanCondition
* @stable ICU 3.8
* @see USetSpanCondition
*/
U_STABLE int32_t U_EXPORT2
uset_spanBackUTF8(const USet *set, const char *s, int32_t length, USetSpanCondition spanCondition);
/**
* Returns true if set1 contains all of the characters and strings
* of set2, and vis versa. It answers the question, 'Is set1 equal to set2?'
* @param set1 set to be checked for containment
* @param set2 set to be checked for containment
* @return true if the test condition is met
* @stable ICU 3.2
*/
U_STABLE UBool U_EXPORT2