forked from qt/qtwebkit
-
Notifications
You must be signed in to change notification settings - Fork 0
Expand file tree
/
Copy pathucol.h
More file actions
1433 lines (1348 loc) · 58.8 KB
/
Copy pathucol.h
File metadata and controls
1433 lines (1348 loc) · 58.8 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) 1996-2013, International Business Machines Corporation and others.
* All Rights Reserved.
*******************************************************************************
*/
#ifndef UCOL_H
#define UCOL_H
#include "unicode/utypes.h"
#if !UCONFIG_NO_COLLATION
#include "unicode/unorm.h"
#include "unicode/localpointer.h"
#include "unicode/parseerr.h"
#include "unicode/uloc.h"
#include "unicode/uset.h"
#include "unicode/uscript.h"
/**
* \file
* \brief C API: Collator
*
* <h2> Collator C API </h2>
*
* The C API for Collator performs locale-sensitive
* string comparison. You use this service to build
* searching and sorting routines for natural language text.
* <em>Important: </em>The ICU collation service has been reimplemented
* in order to achieve better performance and UCA compliance.
* For details, see the
* <a href="http://source.icu-project.org/repos/icu/icuhtml/trunk/design/collation/ICU_collation_design.htm">
* collation design document</a>.
* <p>
* For more information about the collation service see
* <a href="http://icu-project.org/userguide/Collate_Intro.html">the users guide</a>.
* <p>
* Collation service provides correct sorting orders for most locales supported in ICU.
* If specific data for a locale is not available, the orders eventually falls back
* to the <a href="http://www.unicode.org/unicode/reports/tr10/">UCA sort order</a>.
* <p>
* Sort ordering may be customized by providing your own set of rules. For more on
* this subject see the
* <a href="http://icu-project.org/userguide/Collate_Customization.html">
* Collation customization</a> section of the users guide.
* <p>
* @see UCollationResult
* @see UNormalizationMode
* @see UCollationStrength
* @see UCollationElements
*/
/** A collator.
* For usage in C programs.
*/
struct UCollator;
/** structure representing a collator object instance
* @stable ICU 2.0
*/
typedef struct UCollator UCollator;
/**
* UCOL_LESS is returned if source string is compared to be less than target
* string in the ucol_strcoll() method.
* UCOL_EQUAL is returned if source string is compared to be equal to target
* string in the ucol_strcoll() method.
* UCOL_GREATER is returned if source string is compared to be greater than
* target string in the ucol_strcoll() method.
* @see ucol_strcoll()
* <p>
* Possible values for a comparison result
* @stable ICU 2.0
*/
typedef enum {
/** string a == string b */
UCOL_EQUAL = 0,
/** string a > string b */
UCOL_GREATER = 1,
/** string a < string b */
UCOL_LESS = -1
} UCollationResult ;
/** Enum containing attribute values for controling collation behavior.
* Here are all the allowable values. Not every attribute can take every value. The only
* universal value is UCOL_DEFAULT, which resets the attribute value to the predefined
* value for that locale
* @stable ICU 2.0
*/
typedef enum {
/** accepted by most attributes */
UCOL_DEFAULT = -1,
/** Primary collation strength */
UCOL_PRIMARY = 0,
/** Secondary collation strength */
UCOL_SECONDARY = 1,
/** Tertiary collation strength */
UCOL_TERTIARY = 2,
/** Default collation strength */
UCOL_DEFAULT_STRENGTH = UCOL_TERTIARY,
UCOL_CE_STRENGTH_LIMIT,
/** Quaternary collation strength */
UCOL_QUATERNARY=3,
/** Identical collation strength */
UCOL_IDENTICAL=15,
UCOL_STRENGTH_LIMIT,
/** Turn the feature off - works for UCOL_FRENCH_COLLATION,
UCOL_CASE_LEVEL, UCOL_HIRAGANA_QUATERNARY_MODE
& UCOL_DECOMPOSITION_MODE*/
UCOL_OFF = 16,
/** Turn the feature on - works for UCOL_FRENCH_COLLATION,
UCOL_CASE_LEVEL, UCOL_HIRAGANA_QUATERNARY_MODE
& UCOL_DECOMPOSITION_MODE*/
UCOL_ON = 17,
/** Valid for UCOL_ALTERNATE_HANDLING. Alternate handling will be shifted */
UCOL_SHIFTED = 20,
/** Valid for UCOL_ALTERNATE_HANDLING. Alternate handling will be non ignorable */
UCOL_NON_IGNORABLE = 21,
/** Valid for UCOL_CASE_FIRST -
lower case sorts before upper case */
UCOL_LOWER_FIRST = 24,
/** upper case sorts before lower case */
UCOL_UPPER_FIRST = 25,
UCOL_ATTRIBUTE_VALUE_COUNT
} UColAttributeValue;
/**
* Enum containing the codes for reordering segments of the collation table that are not script
* codes. These reordering codes are to be used in conjunction with the script codes.
* @see ucol_getReorderCodes
* @see ucol_setReorderCodes
* @see ucol_getEquivalentReorderCodes
* @see UScriptCode
* @stable ICU 4.8
*/
typedef enum {
/**
* A special reordering code that is used to specify the default
* reordering codes for a locale.
* @stable ICU 4.8
*/
UCOL_REORDER_CODE_DEFAULT = -1,
/**
* A special reordering code that is used to specify no reordering codes.
* @stable ICU 4.8
*/
UCOL_REORDER_CODE_NONE = USCRIPT_UNKNOWN,
/**
* A special reordering code that is used to specify all other codes used for
* reordering except for the codes lised as UColReorderCode values and those
* listed explicitly in a reordering.
* @stable ICU 4.8
*/
UCOL_REORDER_CODE_OTHERS = USCRIPT_UNKNOWN,
/**
* Characters with the space property.
* This is equivalent to the rule value "space".
* @stable ICU 4.8
*/
UCOL_REORDER_CODE_SPACE = 0x1000,
/**
* The first entry in the enumeration of reordering groups. This is intended for use in
* range checking and enumeration of the reorder codes.
* @stable ICU 4.8
*/
UCOL_REORDER_CODE_FIRST = UCOL_REORDER_CODE_SPACE,
/**
* Characters with the punctuation property.
* This is equivalent to the rule value "punct".
* @stable ICU 4.8
*/
UCOL_REORDER_CODE_PUNCTUATION = 0x1001,
/**
* Characters with the symbol property.
* This is equivalent to the rule value "symbol".
* @stable ICU 4.8
*/
UCOL_REORDER_CODE_SYMBOL = 0x1002,
/**
* Characters with the currency property.
* This is equivalent to the rule value "currency".
* @stable ICU 4.8
*/
UCOL_REORDER_CODE_CURRENCY = 0x1003,
/**
* Characters with the digit property.
* This is equivalent to the rule value "digit".
* @stable ICU 4.8
*/
UCOL_REORDER_CODE_DIGIT = 0x1004,
/**
* The limit of the reorder codes. This is intended for use in range checking
* and enumeration of the reorder codes.
* @stable ICU 4.8
*/
UCOL_REORDER_CODE_LIMIT = 0x1005
} UColReorderCode;
/**
* Base letter represents a primary difference. Set comparison
* level to UCOL_PRIMARY to ignore secondary and tertiary differences.
* Use this to set the strength of a Collator object.
* Example of primary difference, "abc" < "abd"
*
* Diacritical differences on the same base letter represent a secondary
* difference. Set comparison level to UCOL_SECONDARY to ignore tertiary
* differences. Use this to set the strength of a Collator object.
* Example of secondary difference, "ä" >> "a".
*
* Uppercase and lowercase versions of the same character represents a
* tertiary difference. Set comparison level to UCOL_TERTIARY to include
* all comparison differences. Use this to set the strength of a Collator
* object.
* Example of tertiary difference, "abc" <<< "ABC".
*
* Two characters are considered "identical" when they have the same
* unicode spellings. UCOL_IDENTICAL.
* For example, "ä" == "ä".
*
* UCollationStrength is also used to determine the strength of sort keys
* generated from UCollator objects
* These values can be now found in the UColAttributeValue enum.
* @stable ICU 2.0
**/
typedef UColAttributeValue UCollationStrength;
/** Attributes that collation service understands. All the attributes can take UCOL_DEFAULT
* value, as well as the values specific to each one.
* @stable ICU 2.0
*/
typedef enum {
/** Attribute for direction of secondary weights - used in Canadian French.
* Acceptable values are UCOL_ON, which results in secondary weights
* being considered backwards and UCOL_OFF which treats secondary
* weights in the order they appear.
* @stable ICU 2.0
*/
UCOL_FRENCH_COLLATION,
/** Attribute for handling variable elements.
* Acceptable values are UCOL_NON_IGNORABLE (default)
* which treats all the codepoints with non-ignorable
* primary weights in the same way,
* and UCOL_SHIFTED which causes codepoints with primary
* weights that are equal or below the variable top value
* to be ignored on primary level and moved to the quaternary
* level.
* @stable ICU 2.0
*/
UCOL_ALTERNATE_HANDLING,
/** Controls the ordering of upper and lower case letters.
* Acceptable values are UCOL_OFF (default), which orders
* upper and lower case letters in accordance to their tertiary
* weights, UCOL_UPPER_FIRST which forces upper case letters to
* sort before lower case letters, and UCOL_LOWER_FIRST which does
* the opposite.
* @stable ICU 2.0
*/
UCOL_CASE_FIRST,
/** Controls whether an extra case level (positioned before the third
* level) is generated or not. Acceptable values are UCOL_OFF (default),
* when case level is not generated, and UCOL_ON which causes the case
* level to be generated. Contents of the case level are affected by
* the value of UCOL_CASE_FIRST attribute. A simple way to ignore
* accent differences in a string is to set the strength to UCOL_PRIMARY
* and enable case level.
* @stable ICU 2.0
*/
UCOL_CASE_LEVEL,
/** Controls whether the normalization check and necessary normalizations
* are performed. When set to UCOL_OFF (default) no normalization check
* is performed. The correctness of the result is guaranteed only if the
* input data is in so-called FCD form (see users manual for more info).
* When set to UCOL_ON, an incremental check is performed to see whether
* the input data is in the FCD form. If the data is not in the FCD form,
* incremental NFD normalization is performed.
* @stable ICU 2.0
*/
UCOL_NORMALIZATION_MODE,
/** An alias for UCOL_NORMALIZATION_MODE attribute.
* @stable ICU 2.0
*/
UCOL_DECOMPOSITION_MODE = UCOL_NORMALIZATION_MODE,
/** The strength attribute. Can be either UCOL_PRIMARY, UCOL_SECONDARY,
* UCOL_TERTIARY, UCOL_QUATERNARY or UCOL_IDENTICAL. The usual strength
* for most locales (except Japanese) is tertiary. Quaternary strength
* is useful when combined with shifted setting for alternate handling
* attribute and for JIS x 4061 collation, when it is used to distinguish
* between Katakana and Hiragana (this is achieved by setting the
* UCOL_HIRAGANA_QUATERNARY mode to on. Otherwise, quaternary level
* is affected only by the number of non ignorable code points in
* the string. Identical strength is rarely useful, as it amounts
* to codepoints of the NFD form of the string.
* @stable ICU 2.0
*/
UCOL_STRENGTH,
#ifndef U_HIDE_DEPRECATED_API
/** When turned on, this attribute positions Hiragana before all
* non-ignorables on quaternary level This is a sneaky way to produce JIS
* sort order.
*
* This attribute is an implementation detail of the CLDR Japanese tailoring.
* The implementation might change to use a different mechanism
* to achieve the same Japanese sort order.
* Since ICU 50, this attribute is not settable any more via API functions.
* @deprecated ICU 50 Implementation detail, cannot be set via API, might be removed from implementation.
*/
UCOL_HIRAGANA_QUATERNARY_MODE = UCOL_STRENGTH + 1,
#endif /* U_HIDE_DEPRECATED_API */
/** When turned on, this attribute generates a collation key
* for the numeric value of substrings of digits.
* This is a way to get '100' to sort AFTER '2'. Note that the longest
* digit substring that can be treated as a single collation element is
* 254 digits (not counting leading zeros). If a digit substring is
* longer than that, the digits beyond the limit will be treated as a
* separate digit substring associated with a separate collation element.
* @stable ICU 2.8
*/
UCOL_NUMERIC_COLLATION = UCOL_STRENGTH + 2,
/**
* The number of UColAttribute constants.
* @stable ICU 2.0
*/
UCOL_ATTRIBUTE_COUNT
} UColAttribute;
/** Options for retrieving the rule string
* @stable ICU 2.0
*/
typedef enum {
/**
* Retrieves the tailoring rules only.
* Same as calling the version of getRules() without UColRuleOption.
* @stable ICU 2.0
*/
UCOL_TAILORING_ONLY,
/**
* Retrieves the "UCA rules" concatenated with the tailoring rules.
* The "UCA rules" are an <i>approximation</i> of the root collator's sort order.
* They are almost never used or useful at runtime and can be removed from the data.
* See http://userguide.icu-project.org/collation/customization#TOC-Building-on-Existing-Locales
* @stable ICU 2.0
*/
UCOL_FULL_RULES
} UColRuleOption ;
/**
* Open a UCollator for comparing strings.
* The UCollator pointer is used in all the calls to the Collation
* service. After finished, collator must be disposed of by calling
* {@link #ucol_close }.
* @param loc The locale containing the required collation rules.
* Special values for locales can be passed in -
* if NULL is passed for the locale, the default locale
* collation rules will be used. If empty string ("") or
* "root" are passed, UCA rules will be used.
* @param status A pointer to an UErrorCode to receive any errors
* @return A pointer to a UCollator, or 0 if an error occurred.
* @see ucol_openRules
* @see ucol_safeClone
* @see ucol_close
* @stable ICU 2.0
*/
U_STABLE UCollator* U_EXPORT2
ucol_open(const char *loc, UErrorCode *status);
/**
* Produce an UCollator instance according to the rules supplied.
* The rules are used to change the default ordering, defined in the
* UCA in a process called tailoring. The resulting UCollator pointer
* can be used in the same way as the one obtained by {@link #ucol_strcoll }.
* @param rules A string describing the collation rules. For the syntax
* of the rules please see users guide.
* @param rulesLength The length of rules, or -1 if null-terminated.
* @param normalizationMode The normalization mode: One of
* UCOL_OFF (expect the text to not need normalization),
* UCOL_ON (normalize), or
* UCOL_DEFAULT (set the mode according to the rules)
* @param strength The default collation strength; one of UCOL_PRIMARY, UCOL_SECONDARY,
* UCOL_TERTIARY, UCOL_IDENTICAL,UCOL_DEFAULT_STRENGTH - can be also set in the rules.
* @param parseError A pointer to UParseError to recieve information about errors
* occurred during parsing. This argument can currently be set
* to NULL, but at users own risk. Please provide a real structure.
* @param status A pointer to an UErrorCode to receive any errors
* @return A pointer to a UCollator. It is not guaranteed that NULL be returned in case
* of error - please use status argument to check for errors.
* @see ucol_open
* @see ucol_safeClone
* @see ucol_close
* @stable ICU 2.0
*/
U_STABLE UCollator* U_EXPORT2
ucol_openRules( const UChar *rules,
int32_t rulesLength,
UColAttributeValue normalizationMode,
UCollationStrength strength,
UParseError *parseError,
UErrorCode *status);
/**
* Open a collator defined by a short form string.
* The structure and the syntax of the string is defined in the "Naming collators"
* section of the users guide:
* http://icu-project.org/userguide/Collate_Concepts.html#Naming_Collators
* Attributes are overriden by the subsequent attributes. So, for "S2_S3", final
* strength will be 3. 3066bis locale overrides individual locale parts.
* The call to this function is equivalent to a call to ucol_open, followed by a
* series of calls to ucol_setAttribute and ucol_setVariableTop.
* @param definition A short string containing a locale and a set of attributes.
* Attributes not explicitly mentioned are left at the default
* state for a locale.
* @param parseError if not NULL, structure that will get filled with error's pre
* and post context in case of error.
* @param forceDefaults if FALSE, the settings that are the same as the collator
* default settings will not be applied (for example, setting
* French secondary on a French collator would not be executed).
* If TRUE, all the settings will be applied regardless of the
* collator default value. If the definition
* strings are to be cached, should be set to FALSE.
* @param status Error code. Apart from regular error conditions connected to
* instantiating collators (like out of memory or similar), this
* API will return an error if an invalid attribute or attribute/value
* combination is specified.
* @return A pointer to a UCollator or 0 if an error occured (including an
* invalid attribute).
* @see ucol_open
* @see ucol_setAttribute
* @see ucol_setVariableTop
* @see ucol_getShortDefinitionString
* @see ucol_normalizeShortDefinitionString
* @stable ICU 3.0
*
*/
U_STABLE UCollator* U_EXPORT2
ucol_openFromShortString( const char *definition,
UBool forceDefaults,
UParseError *parseError,
UErrorCode *status);
#ifndef U_HIDE_DEPRECATED_API
/**
* Get a set containing the contractions defined by the collator. The set includes
* both the UCA contractions and the contractions defined by the collator. This set
* will contain only strings. If a tailoring explicitly suppresses contractions from
* the UCA (like Russian), removed contractions will not be in the resulting set.
* @param coll collator
* @param conts the set to hold the result. It gets emptied before
* contractions are added.
* @param status to hold the error code
* @return the size of the contraction set
*
* @deprecated ICU 3.4, use ucol_getContractionsAndExpansions instead
*/
U_DEPRECATED int32_t U_EXPORT2
ucol_getContractions( const UCollator *coll,
USet *conts,
UErrorCode *status);
#endif /* U_HIDE_DEPRECATED_API */
/**
* Get a set containing the expansions defined by the collator. The set includes
* both the UCA expansions and the expansions defined by the tailoring
* @param coll collator
* @param contractions if not NULL, the set to hold the contractions
* @param expansions if not NULL, the set to hold the expansions
* @param addPrefixes add the prefix contextual elements to contractions
* @param status to hold the error code
*
* @stable ICU 3.4
*/
U_STABLE void U_EXPORT2
ucol_getContractionsAndExpansions( const UCollator *coll,
USet *contractions, USet *expansions,
UBool addPrefixes, UErrorCode *status);
/**
* Close a UCollator.
* Once closed, a UCollator should not be used. Every open collator should
* be closed. Otherwise, a memory leak will result.
* @param coll The UCollator to close.
* @see ucol_open
* @see ucol_openRules
* @see ucol_safeClone
* @stable ICU 2.0
*/
U_STABLE void U_EXPORT2
ucol_close(UCollator *coll);
#if U_SHOW_CPLUSPLUS_API
U_NAMESPACE_BEGIN
/**
* \class LocalUCollatorPointer
* "Smart pointer" class, closes a UCollator via ucol_close().
* For most methods see the LocalPointerBase base class.
*
* @see LocalPointerBase
* @see LocalPointer
* @stable ICU 4.4
*/
U_DEFINE_LOCAL_OPEN_POINTER(LocalUCollatorPointer, UCollator, ucol_close);
U_NAMESPACE_END
#endif
/**
* Compare two strings.
* The strings will be compared using the options already specified.
* @param coll The UCollator containing the comparison rules.
* @param source The source string.
* @param sourceLength The length of source, or -1 if null-terminated.
* @param target The target string.
* @param targetLength The length of target, or -1 if null-terminated.
* @return The result of comparing the strings; one of UCOL_EQUAL,
* UCOL_GREATER, UCOL_LESS
* @see ucol_greater
* @see ucol_greaterOrEqual
* @see ucol_equal
* @stable ICU 2.0
*/
U_STABLE UCollationResult U_EXPORT2
ucol_strcoll( const UCollator *coll,
const UChar *source,
int32_t sourceLength,
const UChar *target,
int32_t targetLength);
/**
* Compare two strings in UTF-8.
* The strings will be compared using the options already specified.
* Note: When input string contains malformed a UTF-8 byte sequence,
* this function treats these bytes as REPLACEMENT CHARACTER (U+FFFD).
* @param coll The UCollator containing the comparison rules.
* @param source The source UTF-8 string.
* @param sourceLength The length of source, or -1 if null-terminated.
* @param target The target UTF-8 string.
* @param targetLength The length of target, or -1 if null-terminated.
* @param status A pointer to an UErrorCode to receive any errors
* @return The result of comparing the strings; one of UCOL_EQUAL,
* UCOL_GREATER, UCOL_LESS
* @see ucol_greater
* @see ucol_greaterOrEqual
* @see ucol_equal
* @stable ICU 50
*/
U_STABLE UCollationResult U_EXPORT2
ucol_strcollUTF8(
const UCollator *coll,
const char *source,
int32_t sourceLength,
const char *target,
int32_t targetLength,
UErrorCode *status);
/**
* Determine if one string is greater than another.
* This function is equivalent to {@link #ucol_strcoll } == UCOL_GREATER
* @param coll The UCollator containing the comparison rules.
* @param source The source string.
* @param sourceLength The length of source, or -1 if null-terminated.
* @param target The target string.
* @param targetLength The length of target, or -1 if null-terminated.
* @return TRUE if source is greater than target, FALSE otherwise.
* @see ucol_strcoll
* @see ucol_greaterOrEqual
* @see ucol_equal
* @stable ICU 2.0
*/
U_STABLE UBool U_EXPORT2
ucol_greater(const UCollator *coll,
const UChar *source, int32_t sourceLength,
const UChar *target, int32_t targetLength);
/**
* Determine if one string is greater than or equal to another.
* This function is equivalent to {@link #ucol_strcoll } != UCOL_LESS
* @param coll The UCollator containing the comparison rules.
* @param source The source string.
* @param sourceLength The length of source, or -1 if null-terminated.
* @param target The target string.
* @param targetLength The length of target, or -1 if null-terminated.
* @return TRUE if source is greater than or equal to target, FALSE otherwise.
* @see ucol_strcoll
* @see ucol_greater
* @see ucol_equal
* @stable ICU 2.0
*/
U_STABLE UBool U_EXPORT2
ucol_greaterOrEqual(const UCollator *coll,
const UChar *source, int32_t sourceLength,
const UChar *target, int32_t targetLength);
/**
* Compare two strings for equality.
* This function is equivalent to {@link #ucol_strcoll } == UCOL_EQUAL
* @param coll The UCollator containing the comparison rules.
* @param source The source string.
* @param sourceLength The length of source, or -1 if null-terminated.
* @param target The target string.
* @param targetLength The length of target, or -1 if null-terminated.
* @return TRUE if source is equal to target, FALSE otherwise
* @see ucol_strcoll
* @see ucol_greater
* @see ucol_greaterOrEqual
* @stable ICU 2.0
*/
U_STABLE UBool U_EXPORT2
ucol_equal(const UCollator *coll,
const UChar *source, int32_t sourceLength,
const UChar *target, int32_t targetLength);
/**
* Compare two UTF-8 encoded trings.
* The strings will be compared using the options already specified.
* @param coll The UCollator containing the comparison rules.
* @param sIter The source string iterator.
* @param tIter The target string iterator.
* @return The result of comparing the strings; one of UCOL_EQUAL,
* UCOL_GREATER, UCOL_LESS
* @param status A pointer to an UErrorCode to receive any errors
* @see ucol_strcoll
* @stable ICU 2.6
*/
U_STABLE UCollationResult U_EXPORT2
ucol_strcollIter( const UCollator *coll,
UCharIterator *sIter,
UCharIterator *tIter,
UErrorCode *status);
/**
* Get the collation strength used in a UCollator.
* The strength influences how strings are compared.
* @param coll The UCollator to query.
* @return The collation strength; one of UCOL_PRIMARY, UCOL_SECONDARY,
* UCOL_TERTIARY, UCOL_QUATERNARY, UCOL_IDENTICAL
* @see ucol_setStrength
* @stable ICU 2.0
*/
U_STABLE UCollationStrength U_EXPORT2
ucol_getStrength(const UCollator *coll);
/**
* Set the collation strength used in a UCollator.
* The strength influences how strings are compared.
* @param coll The UCollator to set.
* @param strength The desired collation strength; one of UCOL_PRIMARY,
* UCOL_SECONDARY, UCOL_TERTIARY, UCOL_QUATERNARY, UCOL_IDENTICAL, UCOL_DEFAULT
* @see ucol_getStrength
* @stable ICU 2.0
*/
U_STABLE void U_EXPORT2
ucol_setStrength(UCollator *coll,
UCollationStrength strength);
/**
* Retrieves the reordering codes for this collator.
* These reordering codes are a combination of UScript codes and UColReorderCode entries.
* @param coll The UCollator to query.
* @param dest The array to fill with the script ordering.
* @param destCapacity The length of dest. If it is 0, then dest may be NULL and the function
* will only return the length of the result without writing any of the result string (pre-flighting).
* @param pErrorCode Must be a valid pointer to an error code value, which must not indicate a
* failure before the function call.
* @return The number of reordering codes written to the dest array.
* @see ucol_setReorderCodes
* @see ucol_getEquivalentReorderCodes
* @see UScriptCode
* @see UColReorderCode
* @stable ICU 4.8
*/
U_STABLE int32_t U_EXPORT2
ucol_getReorderCodes(const UCollator* coll,
int32_t* dest,
int32_t destCapacity,
UErrorCode *pErrorCode);
/**
* Sets the reordering codes for this collator.
* Collation reordering allows scripts and some other defined blocks of characters
* to be moved relative to each other as a block. This reordering is done on top of
* the DUCET/CLDR standard collation order. Reordering can specify groups to be placed
* at the start and/or the end of the collation order. These groups are specified using
* UScript codes and UColReorderCode entries.
* <p>By default, reordering codes specified for the start of the order are placed in the
* order given after a group of "special" non-script blocks. These special groups of characters
* are space, punctuation, symbol, currency, and digit. These special groups are represented with
* UColReorderCode entries. Script groups can be intermingled with
* these special non-script blocks if those special blocks are explicitly specified in the reordering.
* <p>The special code OTHERS stands for any script that is not explicitly
* mentioned in the list of reordering codes given. Anything that is after OTHERS
* will go at the very end of the reordering in the order given.
* <p>The special reorder code DEFAULT will reset the reordering for this collator
* to the default for this collator. The default reordering may be the DUCET/CLDR order or may be a reordering that
* was specified when this collator was created from resource data or from rules. The
* DEFAULT code <b>must</b> be the sole code supplied when it used. If not
* that will result in an U_ILLEGAL_ARGUMENT_ERROR being set.
* <p>The special reorder code NONE will remove any reordering for this collator.
* The result of setting no reordering will be to have the DUCET/CLDR ordering used. The
* NONE code <b>must</b> be the sole code supplied when it used.
* @param coll The UCollator to set.
* @param reorderCodes An array of script codes in the new order. This can be NULL if the
* length is also set to 0. An empty array will clear any reordering codes on the collator.
* @param reorderCodesLength The length of reorderCodes.
* @param pErrorCode Must be a valid pointer to an error code value, which must not indicate a
* failure before the function call.
* @see ucol_getReorderCodes
* @see ucol_getEquivalentReorderCodes
* @see UScriptCode
* @see UColReorderCode
* @stable ICU 4.8
*/
U_STABLE void U_EXPORT2
ucol_setReorderCodes(UCollator* coll,
const int32_t* reorderCodes,
int32_t reorderCodesLength,
UErrorCode *pErrorCode);
/**
* Retrieves the reorder codes that are grouped with the given reorder code. Some reorder
* codes will be grouped and must reorder together.
* @param reorderCode The reorder code to determine equivalence for.
* @param dest The array to fill with the script ordering.
* @param destCapacity The length of dest. If it is 0, then dest may be NULL and the function
* will only return the length of the result without writing any of the result string (pre-flighting).
* @param pErrorCode Must be a valid pointer to an error code value, which must not indicate
* a failure before the function call.
* @return The number of reordering codes written to the dest array.
* @see ucol_setReorderCodes
* @see ucol_getReorderCodes
* @see UScriptCode
* @see UColReorderCode
* @stable ICU 4.8
*/
U_STABLE int32_t U_EXPORT2
ucol_getEquivalentReorderCodes(int32_t reorderCode,
int32_t* dest,
int32_t destCapacity,
UErrorCode *pErrorCode);
/**
* Get the display name for a UCollator.
* The display name is suitable for presentation to a user.
* @param objLoc The locale of the collator in question.
* @param dispLoc The locale for display.
* @param result A pointer to a buffer to receive the attribute.
* @param resultLength The maximum size of result.
* @param status A pointer to an UErrorCode to receive any errors
* @return The total buffer size needed; if greater than resultLength,
* the output was truncated.
* @stable ICU 2.0
*/
U_STABLE int32_t U_EXPORT2
ucol_getDisplayName( const char *objLoc,
const char *dispLoc,
UChar *result,
int32_t resultLength,
UErrorCode *status);
/**
* Get a locale for which collation rules are available.
* A UCollator in a locale returned by this function will perform the correct
* collation for the locale.
* @param localeIndex The index of the desired locale.
* @return A locale for which collation rules are available, or 0 if none.
* @see ucol_countAvailable
* @stable ICU 2.0
*/
U_STABLE const char* U_EXPORT2
ucol_getAvailable(int32_t localeIndex);
/**
* Determine how many locales have collation rules available.
* This function is most useful as determining the loop ending condition for
* calls to {@link #ucol_getAvailable }.
* @return The number of locales for which collation rules are available.
* @see ucol_getAvailable
* @stable ICU 2.0
*/
U_STABLE int32_t U_EXPORT2
ucol_countAvailable(void);
#if !UCONFIG_NO_SERVICE
/**
* Create a string enumerator of all locales for which a valid
* collator may be opened.
* @param status input-output error code
* @return a string enumeration over locale strings. The caller is
* responsible for closing the result.
* @stable ICU 3.0
*/
U_STABLE UEnumeration* U_EXPORT2
ucol_openAvailableLocales(UErrorCode *status);
#endif
/**
* Create a string enumerator of all possible keywords that are relevant to
* collation. At this point, the only recognized keyword for this
* service is "collation".
* @param status input-output error code
* @return a string enumeration over locale strings. The caller is
* responsible for closing the result.
* @stable ICU 3.0
*/
U_STABLE UEnumeration* U_EXPORT2
ucol_getKeywords(UErrorCode *status);
/**
* Given a keyword, create a string enumeration of all values
* for that keyword that are currently in use.
* @param keyword a particular keyword as enumerated by
* ucol_getKeywords. If any other keyword is passed in, *status is set
* to U_ILLEGAL_ARGUMENT_ERROR.
* @param status input-output error code
* @return a string enumeration over collation keyword values, or NULL
* upon error. The caller is responsible for closing the result.
* @stable ICU 3.0
*/
U_STABLE UEnumeration* U_EXPORT2
ucol_getKeywordValues(const char *keyword, UErrorCode *status);
/**
* Given a key and a locale, returns an array of string values in a preferred
* order that would make a difference. These are all and only those values where
* the open (creation) of the service with the locale formed from the input locale
* plus input keyword and that value has different behavior than creation with the
* input locale alone.
* @param key one of the keys supported by this service. For now, only
* "collation" is supported.
* @param locale the locale
* @param commonlyUsed if set to true it will return only commonly used values
* with the given locale in preferred order. Otherwise,
* it will return all the available values for the locale.
* @param status error status
* @return a string enumeration over keyword values for the given key and the locale.
* @stable ICU 4.2
*/
U_STABLE UEnumeration* U_EXPORT2
ucol_getKeywordValuesForLocale(const char* key,
const char* locale,
UBool commonlyUsed,
UErrorCode* status);
/**
* Return the functionally equivalent locale for the given
* requested locale, with respect to given keyword, for the
* collation service. If two locales return the same result, then
* collators instantiated for these locales will behave
* equivalently. The converse is not always true; two collators
* may in fact be equivalent, but return different results, due to
* internal details. The return result has no other meaning than
* that stated above, and implies nothing as to the relationship
* between the two locales. This is intended for use by
* applications who wish to cache collators, or otherwise reuse
* collators when possible. The functional equivalent may change
* over time. For more information, please see the <a
* href="http://icu-project.org/userguide/locale.html#services">
* Locales and Services</a> section of the ICU User Guide.
* @param result fillin for the functionally equivalent locale
* @param resultCapacity capacity of the fillin buffer
* @param keyword a particular keyword as enumerated by
* ucol_getKeywords.
* @param locale the requested locale
* @param isAvailable if non-NULL, pointer to a fillin parameter that
* indicates whether the requested locale was 'available' to the
* collation service. A locale is defined as 'available' if it
* physically exists within the collation locale data.
* @param status pointer to input-output error code
* @return the actual buffer size needed for the locale. If greater
* than resultCapacity, the returned full name will be truncated and
* an error code will be returned.
* @stable ICU 3.0
*/
U_STABLE int32_t U_EXPORT2
ucol_getFunctionalEquivalent(char* result, int32_t resultCapacity,
const char* keyword, const char* locale,
UBool* isAvailable, UErrorCode* status);
/**
* Get the collation tailoring rules from a UCollator.
* The rules will follow the rule syntax.
* @param coll The UCollator to query.
* @param length
* @return The collation tailoring rules.
* @stable ICU 2.0
*/
U_STABLE const UChar* U_EXPORT2
ucol_getRules( const UCollator *coll,
int32_t *length);
/** Get the short definition string for a collator. This API harvests the collator's
* locale and the attribute set and produces a string that can be used for opening
* a collator with the same properties using the ucol_openFromShortString API.
* This string will be normalized.
* The structure and the syntax of the string is defined in the "Naming collators"
* section of the users guide:
* http://icu-project.org/userguide/Collate_Concepts.html#Naming_Collators
* This API supports preflighting.
* @param coll a collator
* @param locale a locale that will appear as a collators locale in the resulting
* short string definition. If NULL, the locale will be harvested
* from the collator.
* @param buffer space to hold the resulting string
* @param capacity capacity of the buffer
* @param status for returning errors. All the preflighting errors are featured
* @return length of the resulting string
* @see ucol_openFromShortString
* @see ucol_normalizeShortDefinitionString
* @stable ICU 3.0
*/
U_STABLE int32_t U_EXPORT2
ucol_getShortDefinitionString(const UCollator *coll,
const char *locale,
char *buffer,
int32_t capacity,
UErrorCode *status);
/** Verifies and normalizes short definition string.
* Normalized short definition string has all the option sorted by the argument name,
* so that equivalent definition strings are the same.
* This API supports preflighting.
* @param source definition string
* @param destination space to hold the resulting string
* @param capacity capacity of the buffer
* @param parseError if not NULL, structure that will get filled with error's pre
* and post context in case of error.
* @param status Error code. This API will return an error if an invalid attribute
* or attribute/value combination is specified. All the preflighting
* errors are also featured
* @return length of the resulting normalized string.
*
* @see ucol_openFromShortString
* @see ucol_getShortDefinitionString
*
* @stable ICU 3.0
*/
U_STABLE int32_t U_EXPORT2
ucol_normalizeShortDefinitionString(const char *source,
char *destination,
int32_t capacity,
UParseError *parseError,
UErrorCode *status);
/**
* Get a sort key for a string from a UCollator.
* Sort keys may be compared using <TT>strcmp</TT>.
*
* Like ICU functions that write to an output buffer, the buffer contents
* is undefined if the buffer capacity (resultLength parameter) is too small.
* Unlike ICU functions that write a string to an output buffer,
* the terminating zero byte is counted in the sort key length.
* @param coll The UCollator containing the collation rules.
* @param source The string to transform.
* @param sourceLength The length of source, or -1 if null-terminated.
* @param result A pointer to a buffer to receive the attribute.
* @param resultLength The maximum size of result.
* @return The size needed to fully store the sort key.
* If there was an internal error generating the sort key,
* a zero value is returned.
* @see ucol_keyHashCode
* @stable ICU 2.0
*/
U_STABLE int32_t U_EXPORT2
ucol_getSortKey(const UCollator *coll,
const UChar *source,
int32_t sourceLength,
uint8_t *result,
int32_t resultLength);
/** Gets the next count bytes of a sort key. Caller needs
* to preserve state array between calls and to provide
* the same type of UCharIterator set with the same string.
* The destination buffer provided must be big enough to store
* the number of requested bytes.
*
* The generated sort key may or may not be compatible with
* sort keys generated using ucol_getSortKey().
* @param coll The UCollator containing the collation rules.
* @param iter UCharIterator containing the string we need
* the sort key to be calculated for.
* @param state Opaque state of sortkey iteration.
* @param dest Buffer to hold the resulting sortkey part
* @param count number of sort key bytes required.
* @param status error code indicator.
* @return the actual number of bytes of a sortkey. It can be
* smaller than count if we have reached the end of
* the sort key.
* @stable ICU 2.6
*/