forked from phoboslab/JavaScriptCore-iOS
-
Notifications
You must be signed in to change notification settings - Fork 0
Expand file tree
/
Copy pathuchar.h
More file actions
2798 lines (2581 loc) · 97.6 KB
/
uchar.h
File metadata and controls
2798 lines (2581 loc) · 97.6 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) 1997-2004, International Business Machines
* Corporation and others. All Rights Reserved.
**********************************************************************
*
* File UCHAR.H
*
* Modification History:
*
* Date Name Description
* 04/02/97 aliu Creation.
* 03/29/99 helena Updated for C APIs.
* 4/15/99 Madhu Updated for C Implementation and Javadoc
* 5/20/99 Madhu Added the function u_getVersion()
* 8/19/1999 srl Upgraded scripts to Unicode 3.0
* 8/27/1999 schererm UCharDirection constants: U_...
* 11/11/1999 weiv added u_isalnum(), cleaned comments
* 01/11/2000 helena Renamed u_getVersion to u_getUnicodeVersion().
******************************************************************************
*/
#ifndef UCHAR_H
#define UCHAR_H
#include "unicode/utypes.h"
U_CDECL_BEGIN
/*==========================================================================*/
/* Unicode version number */
/*==========================================================================*/
/**
* Unicode version number, default for the current ICU version.
* The actual Unicode Character Database (UCD) data is stored in uprops.dat
* and may be generated from UCD files from a different Unicode version.
* Call u_getUnicodeVersion to get the actual Unicode version of the data.
*
* @see u_getUnicodeVersion
* @stable ICU 2.0
*/
#define U_UNICODE_VERSION "4.0.1"
/**
* \file
* \brief C API: Unicode Properties
*
* This C API provides low-level access to the Unicode Character Database.
* In addition to raw property values, some convenience functions calculate
* derived properties, for example for Java-style programming.
*
* Unicode assigns each code point (not just assigned character) values for
* many properties.
* Most of them are simple boolean flags, or constants from a small enumerated list.
* For some properties, values are strings or other relatively more complex types.
*
* For more information see
* "About the Unicode Character Database" (http://www.unicode.org/ucd/)
* and the ICU User Guide chapter on Properties (http://oss.software.ibm.com/icu/userguide/properties.html).
*
* Many functions are designed to match java.lang.Character functions.
* See the individual function documentation,
* and see the JDK 1.4.1 java.lang.Character documentation
* at http://java.sun.com/j2se/1.4.1/docs/api/java/lang/Character.html
*
* There are also functions that provide easy migration from C/POSIX functions
* like isblank(). Their use is generally discouraged because the C/POSIX
* standards do not define their semantics beyond the ASCII range, which means
* that different implementations exhibit very different behavior.
* Instead, Unicode properties should be used directly.
*
* There are also only a few, broad C/POSIX character classes, and they tend
* to be used for conflicting purposes. For example, the "isalpha()" class
* is sometimes used to determine word boundaries, while a more sophisticated
* approach would at least distinguish initial letters from continuation
* characters (the latter including combining marks).
* (In ICU, BreakIterator is the most sophisticated API for word boundaries.)
* Another example: There is no "istitle()" class for titlecase characters.
*
* A summary of the behavior of some C/POSIX character classification implementations
* for Unicode is available at http://oss.software.ibm.com/cvs/icu/~checkout~/icuhtml/design/posix_classes.html
*
* <strong>Important</strong>:
* The behavior of the ICU C/POSIX-style character classification
* functions is subject to change according to discussion of the above summary.
*
* Note: There are several ICU whitespace functions.
* Comparison:
* - u_isUWhiteSpace=UCHAR_WHITE_SPACE: Unicode White_Space property;
* most of general categories "Z" (separators) + most whitespace ISO controls
* (including no-break spaces, but excluding IS1..IS4 and ZWSP)
* - u_isWhitespace: Java isWhitespace; Z + whitespace ISO controls but excluding no-break spaces
* - u_isJavaSpaceChar: Java isSpaceChar; just Z (including no-break spaces)
* - u_isspace: Z + whitespace ISO controls (including no-break spaces)
* - u_isblank: "horizontal spaces" = TAB + Zs - ZWSP
*/
/**
* Constants.
*/
/** The lowest Unicode code point value. Code points are non-negative. @stable ICU 2.0 */
#define UCHAR_MIN_VALUE 0
/**
* The highest Unicode code point value (scalar value) according to
* The Unicode Standard. This is a 21-bit value (20.1 bits, rounded up).
* For a single character, UChar32 is a simple type that can hold any code point value.
*
* @see UChar32
* @stable ICU 2.0
*/
#define UCHAR_MAX_VALUE 0x10ffff
/**
* Get a single-bit bit set (a flag) from a bit number 0..31.
* @stable ICU 2.1
*/
#define U_MASK(x) ((uint32_t)1<<(x))
/*
* !! Note: Several comments in this file are machine-read by the
* genpname tool. These comments describe the correspondence between
* icu enum constants and UCD entities. Do not delete them. Update
* these comments as needed.
*
* Any comment of the form "/ *[name]* /" (spaces added) is such
* a comment.
*
* The U_JG_* and U_GC_*_MASK constants are matched by their symbolic
* name, which must match PropertyValueAliases.txt.
*/
/**
* Selection constants for Unicode properties.
* These constants are used in functions like u_hasBinaryProperty to select
* one of the Unicode properties.
*
* The properties APIs are intended to reflect Unicode properties as defined
* in the Unicode Character Database (UCD) and Unicode Technical Reports (UTR).
* For details about the properties see http://www.unicode.org/ucd/ .
* For names of Unicode properties see the UCD file PropertyAliases.txt.
*
* Important: If ICU is built with UCD files from Unicode versions below, e.g., 3.2,
* then properties marked with "new in Unicode 3.2" are not or not fully available.
* Check u_getUnicodeVersion to be sure.
*
* @see u_hasBinaryProperty
* @see u_getIntPropertyValue
* @see u_getUnicodeVersion
* @stable ICU 2.1
*/
typedef enum UProperty {
/* See note !!. Comments of the form "Binary property Dash",
"Enumerated property Script", "Double property Numeric_Value",
and "String property Age" are read by genpname. */
/* Note: Place UCHAR_ALPHABETIC before UCHAR_BINARY_START so that
debuggers display UCHAR_ALPHABETIC as the symbolic name for 0,
rather than UCHAR_BINARY_START. Likewise for other *_START
identifiers. */
/** Binary property Alphabetic. Same as u_isUAlphabetic, different from u_isalpha.
Lu+Ll+Lt+Lm+Lo+Nl+Other_Alphabetic @stable ICU 2.1 */
UCHAR_ALPHABETIC=0,
/** First constant for binary Unicode properties. @stable ICU 2.1 */
UCHAR_BINARY_START=UCHAR_ALPHABETIC,
/** Binary property ASCII_Hex_Digit. 0-9 A-F a-f @stable ICU 2.1 */
UCHAR_ASCII_HEX_DIGIT,
/** Binary property Bidi_Control.
Format controls which have specific functions
in the Bidi Algorithm. @stable ICU 2.1 */
UCHAR_BIDI_CONTROL,
/** Binary property Bidi_Mirrored.
Characters that may change display in RTL text.
Same as u_isMirrored.
See Bidi Algorithm, UTR 9. @stable ICU 2.1 */
UCHAR_BIDI_MIRRORED,
/** Binary property Dash. Variations of dashes. @stable ICU 2.1 */
UCHAR_DASH,
/** Binary property Default_Ignorable_Code_Point (new in Unicode 3.2).
Ignorable in most processing.
<2060..206F, FFF0..FFFB, E0000..E0FFF>+Other_Default_Ignorable_Code_Point+(Cf+Cc+Cs-White_Space) @stable ICU 2.1 */
UCHAR_DEFAULT_IGNORABLE_CODE_POINT,
/** Binary property Deprecated (new in Unicode 3.2).
The usage of deprecated characters is strongly discouraged. @stable ICU 2.1 */
UCHAR_DEPRECATED,
/** Binary property Diacritic. Characters that linguistically modify
the meaning of another character to which they apply. @stable ICU 2.1 */
UCHAR_DIACRITIC,
/** Binary property Extender.
Extend the value or shape of a preceding alphabetic character,
e.g., length and iteration marks. @stable ICU 2.1 */
UCHAR_EXTENDER,
/** Binary property Full_Composition_Exclusion.
CompositionExclusions.txt+Singleton Decompositions+
Non-Starter Decompositions. @stable ICU 2.1 */
UCHAR_FULL_COMPOSITION_EXCLUSION,
/** Binary property Grapheme_Base (new in Unicode 3.2).
For programmatic determination of grapheme cluster boundaries.
[0..10FFFF]-Cc-Cf-Cs-Co-Cn-Zl-Zp-Grapheme_Link-Grapheme_Extend-CGJ @stable ICU 2.1 */
UCHAR_GRAPHEME_BASE,
/** Binary property Grapheme_Extend (new in Unicode 3.2).
For programmatic determination of grapheme cluster boundaries.
Me+Mn+Mc+Other_Grapheme_Extend-Grapheme_Link-CGJ @stable ICU 2.1 */
UCHAR_GRAPHEME_EXTEND,
/** Binary property Grapheme_Link (new in Unicode 3.2).
For programmatic determination of grapheme cluster boundaries. @stable ICU 2.1 */
UCHAR_GRAPHEME_LINK,
/** Binary property Hex_Digit.
Characters commonly used for hexadecimal numbers. @stable ICU 2.1 */
UCHAR_HEX_DIGIT,
/** Binary property Hyphen. Dashes used to mark connections
between pieces of words, plus the Katakana middle dot. @stable ICU 2.1 */
UCHAR_HYPHEN,
/** Binary property ID_Continue.
Characters that can continue an identifier.
DerivedCoreProperties.txt also says "NOTE: Cf characters should be filtered out."
ID_Start+Mn+Mc+Nd+Pc @stable ICU 2.1 */
UCHAR_ID_CONTINUE,
/** Binary property ID_Start.
Characters that can start an identifier.
Lu+Ll+Lt+Lm+Lo+Nl @stable ICU 2.1 */
UCHAR_ID_START,
/** Binary property Ideographic.
CJKV ideographs. @stable ICU 2.1 */
UCHAR_IDEOGRAPHIC,
/** Binary property IDS_Binary_Operator (new in Unicode 3.2).
For programmatic determination of
Ideographic Description Sequences. @stable ICU 2.1 */
UCHAR_IDS_BINARY_OPERATOR,
/** Binary property IDS_Trinary_Operator (new in Unicode 3.2).
For programmatic determination of
Ideographic Description Sequences. @stable ICU 2.1 */
UCHAR_IDS_TRINARY_OPERATOR,
/** Binary property Join_Control.
Format controls for cursive joining and ligation. @stable ICU 2.1 */
UCHAR_JOIN_CONTROL,
/** Binary property Logical_Order_Exception (new in Unicode 3.2).
Characters that do not use logical order and
require special handling in most processing. @stable ICU 2.1 */
UCHAR_LOGICAL_ORDER_EXCEPTION,
/** Binary property Lowercase. Same as u_isULowercase, different from u_islower.
Ll+Other_Lowercase @stable ICU 2.1 */
UCHAR_LOWERCASE,
/** Binary property Math. Sm+Other_Math @stable ICU 2.1 */
UCHAR_MATH,
/** Binary property Noncharacter_Code_Point.
Code points that are explicitly defined as illegal
for the encoding of characters. @stable ICU 2.1 */
UCHAR_NONCHARACTER_CODE_POINT,
/** Binary property Quotation_Mark. @stable ICU 2.1 */
UCHAR_QUOTATION_MARK,
/** Binary property Radical (new in Unicode 3.2).
For programmatic determination of
Ideographic Description Sequences. @stable ICU 2.1 */
UCHAR_RADICAL,
/** Binary property Soft_Dotted (new in Unicode 3.2).
Characters with a "soft dot", like i or j.
An accent placed on these characters causes
the dot to disappear. @stable ICU 2.1 */
UCHAR_SOFT_DOTTED,
/** Binary property Terminal_Punctuation.
Punctuation characters that generally mark
the end of textual units. @stable ICU 2.1 */
UCHAR_TERMINAL_PUNCTUATION,
/** Binary property Unified_Ideograph (new in Unicode 3.2).
For programmatic determination of
Ideographic Description Sequences. @stable ICU 2.1 */
UCHAR_UNIFIED_IDEOGRAPH,
/** Binary property Uppercase. Same as u_isUUppercase, different from u_isupper.
Lu+Other_Uppercase @stable ICU 2.1 */
UCHAR_UPPERCASE,
/** Binary property White_Space.
Same as u_isUWhiteSpace, different from u_isspace and u_isWhitespace.
Space characters+TAB+CR+LF-ZWSP-ZWNBSP @stable ICU 2.1 */
UCHAR_WHITE_SPACE,
/** Binary property XID_Continue.
ID_Continue modified to allow closure under
normalization forms NFKC and NFKD. @stable ICU 2.1 */
UCHAR_XID_CONTINUE,
/** Binary property XID_Start. ID_Start modified to allow
closure under normalization forms NFKC and NFKD. @stable ICU 2.1 */
UCHAR_XID_START,
/** Binary property Case_Sensitive. Either the source of a case
mapping or _in_ the target of a case mapping. Not the same as
the general category Cased_Letter. @stable ICU 2.6 */
UCHAR_CASE_SENSITIVE,
/** Binary property STerm (new in Unicode 4.0.1).
Sentence Terminal. Used in UAX #29: Text Boundaries
(http://www.unicode.org/reports/tr29/)
@draft ICU 3.0 */
UCHAR_S_TERM,
/** Binary property Variation_Selector (new in Unicode 4.0.1).
Indicates all those characters that qualify as Variation Selectors.
For details on the behavior of these characters,
see StandardizedVariants.html and 15.6 Variation Selectors.
@draft ICU 3.0 */
UCHAR_VARIATION_SELECTOR,
/** Binary property NFD_Inert.
ICU-specific property for characters that are inert under NFD,
i.e., they do not interact with adjacent characters.
Used for example in normalizing transforms in incremental mode
to find the boundary of safely normalizable text despite possible
text additions.
There is one such property per normalization form.
These properties are computed as follows - an inert character is:
a) unassigned, or ALL of the following:
b) of combining class 0.
c) not decomposed by this normalization form.
AND if NFC or NFKC,
d) can never compose with a previous character.
e) can never compose with a following character.
f) can never change if another character is added.
Example: a-breve might satisfy all but f, but if you
add an ogonek it changes to a-ogonek + breve
See also com.ibm.text.UCD.NFSkippable in the ICU4J repository,
and icu/source/common/unormimp.h .
@draft ICU 3.0 */
UCHAR_NFD_INERT,
/** Binary property NFKD_Inert.
ICU-specific property for characters that are inert under NFKD,
i.e., they do not interact with adjacent characters.
Used for example in normalizing transforms in incremental mode
to find the boundary of safely normalizable text despite possible
text additions.
@see UCHAR_NFD_INERT
@draft ICU 3.0 */
UCHAR_NFKD_INERT,
/** Binary property NFC_Inert.
ICU-specific property for characters that are inert under NFC,
i.e., they do not interact with adjacent characters.
Used for example in normalizing transforms in incremental mode
to find the boundary of safely normalizable text despite possible
text additions.
@see UCHAR_NFD_INERT
@draft ICU 3.0 */
UCHAR_NFC_INERT,
/** Binary property NFKC_Inert.
ICU-specific property for characters that are inert under NFKC,
i.e., they do not interact with adjacent characters.
Used for example in normalizing transforms in incremental mode
to find the boundary of safely normalizable text despite possible
text additions.
@see UCHAR_NFD_INERT
@draft ICU 3.0 */
UCHAR_NFKC_INERT,
/** Binary Property Segment_Starter.
ICU-specific property for characters that are starters in terms of
Unicode normalization and combining character sequences.
They have ccc=0 and do not occur in non-initial position of the
canonical decomposition of any character
(like " in NFD(a-umlaut) and a Jamo T in an NFD(Hangul LVT)).
ICU uses this property for segmenting a string for generating a set of
canonically equivalent strings, e.g. for canonical closure while
processing collation tailoring rules.
@draft ICU 3.0 */
UCHAR_SEGMENT_STARTER,
/** One more than the last constant for binary Unicode properties. @stable ICU 2.1 */
UCHAR_BINARY_LIMIT,
/** Enumerated property Bidi_Class.
Same as u_charDirection, returns UCharDirection values. @stable ICU 2.2 */
UCHAR_BIDI_CLASS=0x1000,
/** First constant for enumerated/integer Unicode properties. @stable ICU 2.2 */
UCHAR_INT_START=UCHAR_BIDI_CLASS,
/** Enumerated property Block.
Same as ublock_getCode, returns UBlockCode values. @stable ICU 2.2 */
UCHAR_BLOCK,
/** Enumerated property Canonical_Combining_Class.
Same as u_getCombiningClass, returns 8-bit numeric values. @stable ICU 2.2 */
UCHAR_CANONICAL_COMBINING_CLASS,
/** Enumerated property Decomposition_Type.
Returns UDecompositionType values. @stable ICU 2.2 */
UCHAR_DECOMPOSITION_TYPE,
/** Enumerated property East_Asian_Width.
See http://www.unicode.org/reports/tr11/
Returns UEastAsianWidth values. @stable ICU 2.2 */
UCHAR_EAST_ASIAN_WIDTH,
/** Enumerated property General_Category.
Same as u_charType, returns UCharCategory values. @stable ICU 2.2 */
UCHAR_GENERAL_CATEGORY,
/** Enumerated property Joining_Group.
Returns UJoiningGroup values. @stable ICU 2.2 */
UCHAR_JOINING_GROUP,
/** Enumerated property Joining_Type.
Returns UJoiningType values. @stable ICU 2.2 */
UCHAR_JOINING_TYPE,
/** Enumerated property Line_Break.
Returns ULineBreak values. @stable ICU 2.2 */
UCHAR_LINE_BREAK,
/** Enumerated property Numeric_Type.
Returns UNumericType values. @stable ICU 2.2 */
UCHAR_NUMERIC_TYPE,
/** Enumerated property Script.
Same as uscript_getScript, returns UScriptCode values. @stable ICU 2.2 */
UCHAR_SCRIPT,
/** Enumerated property Hangul_Syllable_Type, new in Unicode 4.
Returns UHangulSyllableType values. @stable ICU 2.6 */
UCHAR_HANGUL_SYLLABLE_TYPE,
/** Enumerated property NFD_Quick_Check.
Returns UNormalizationCheckResult values. @draft ICU 3.0 */
UCHAR_NFD_QUICK_CHECK,
/** Enumerated property NFKD_Quick_Check.
Returns UNormalizationCheckResult values. @draft ICU 3.0 */
UCHAR_NFKD_QUICK_CHECK,
/** Enumerated property NFC_Quick_Check.
Returns UNormalizationCheckResult values. @draft ICU 3.0 */
UCHAR_NFC_QUICK_CHECK,
/** Enumerated property NFKC_Quick_Check.
Returns UNormalizationCheckResult values. @draft ICU 3.0 */
UCHAR_NFKC_QUICK_CHECK,
/** Enumerated property Lead_Canonical_Combining_Class.
ICU-specific property for the ccc of the first code point
of the decomposition, or lccc(c)=ccc(NFD(c)[0]).
Useful for checking for canonically ordered text;
see UNORM_FCD and http://www.unicode.org/notes/tn5/#FCD .
Returns 8-bit numeric values like UCHAR_CANONICAL_COMBINING_CLASS. @draft ICU 3.0 */
UCHAR_LEAD_CANONICAL_COMBINING_CLASS,
/** Enumerated property Trail_Canonical_Combining_Class.
ICU-specific property for the ccc of the last code point
of the decomposition, or tccc(c)=ccc(NFD(c)[last]).
Useful for checking for canonically ordered text;
see UNORM_FCD and http://www.unicode.org/notes/tn5/#FCD .
Returns 8-bit numeric values like UCHAR_CANONICAL_COMBINING_CLASS. @draft ICU 3.0 */
UCHAR_TRAIL_CANONICAL_COMBINING_CLASS,
/** One more than the last constant for enumerated/integer Unicode properties. @stable ICU 2.2 */
UCHAR_INT_LIMIT,
/** Bitmask property General_Category_Mask.
This is the General_Category property returned as a bit mask.
When used in u_getIntPropertyValue(c), same as U_MASK(u_charType(c)),
returns bit masks for UCharCategory values where exactly one bit is set.
When used with u_getPropertyValueName() and u_getPropertyValueEnum(),
a multi-bit mask is used for sets of categories like "Letters".
Mask values should be cast to uint32_t.
@stable ICU 2.4 */
UCHAR_GENERAL_CATEGORY_MASK=0x2000,
/** First constant for bit-mask Unicode properties. @stable ICU 2.4 */
UCHAR_MASK_START=UCHAR_GENERAL_CATEGORY_MASK,
/** One more than the last constant for bit-mask Unicode properties. @stable ICU 2.4 */
UCHAR_MASK_LIMIT,
/** Double property Numeric_Value.
Corresponds to u_getNumericValue. @stable ICU 2.4 */
UCHAR_NUMERIC_VALUE=0x3000,
/** First constant for double Unicode properties. @stable ICU 2.4 */
UCHAR_DOUBLE_START=UCHAR_NUMERIC_VALUE,
/** One more than the last constant for double Unicode properties. @stable ICU 2.4 */
UCHAR_DOUBLE_LIMIT,
/** String property Age.
Corresponds to u_charAge. @stable ICU 2.4 */
UCHAR_AGE=0x4000,
/** First constant for string Unicode properties. @stable ICU 2.4 */
UCHAR_STRING_START=UCHAR_AGE,
/** String property Bidi_Mirroring_Glyph.
Corresponds to u_charMirror. @stable ICU 2.4 */
UCHAR_BIDI_MIRRORING_GLYPH,
/** String property Case_Folding.
Corresponds to u_strFoldCase in ustring.h. @stable ICU 2.4 */
UCHAR_CASE_FOLDING,
/** String property ISO_Comment.
Corresponds to u_getISOComment. @stable ICU 2.4 */
UCHAR_ISO_COMMENT,
/** String property Lowercase_Mapping.
Corresponds to u_strToLower in ustring.h. @stable ICU 2.4 */
UCHAR_LOWERCASE_MAPPING,
/** String property Name.
Corresponds to u_charName. @stable ICU 2.4 */
UCHAR_NAME,
/** String property Simple_Case_Folding.
Corresponds to u_foldCase. @stable ICU 2.4 */
UCHAR_SIMPLE_CASE_FOLDING,
/** String property Simple_Lowercase_Mapping.
Corresponds to u_tolower. @stable ICU 2.4 */
UCHAR_SIMPLE_LOWERCASE_MAPPING,
/** String property Simple_Titlecase_Mapping.
Corresponds to u_totitle. @stable ICU 2.4 */
UCHAR_SIMPLE_TITLECASE_MAPPING,
/** String property Simple_Uppercase_Mapping.
Corresponds to u_toupper. @stable ICU 2.4 */
UCHAR_SIMPLE_UPPERCASE_MAPPING,
/** String property Titlecase_Mapping.
Corresponds to u_strToTitle in ustring.h. @stable ICU 2.4 */
UCHAR_TITLECASE_MAPPING,
/** String property Unicode_1_Name.
Corresponds to u_charName. @stable ICU 2.4 */
UCHAR_UNICODE_1_NAME,
/** String property Uppercase_Mapping.
Corresponds to u_strToUpper in ustring.h. @stable ICU 2.4 */
UCHAR_UPPERCASE_MAPPING,
/** One more than the last constant for string Unicode properties. @stable ICU 2.4 */
UCHAR_STRING_LIMIT,
/** Represents a nonexistent or invalid property or property value. @stable ICU 2.4 */
UCHAR_INVALID_CODE = -1
} UProperty;
/**
* Data for enumerated Unicode general category types.
* See http://www.unicode.org/Public/UNIDATA/UnicodeData.html .
* @stable ICU 2.0
*/
typedef enum UCharCategory
{
/** See note !!. Comments of the form "Cn" are read by genpname. */
/** Non-category for unassigned and non-character code points. @stable ICU 2.0 */
U_UNASSIGNED = 0,
/** Cn "Other, Not Assigned (no characters in [UnicodeData.txt] have this property)" (same as U_UNASSIGNED!) @stable ICU 2.0 */
U_GENERAL_OTHER_TYPES = 0,
/** Lu @stable ICU 2.0 */
U_UPPERCASE_LETTER = 1,
/** Ll @stable ICU 2.0 */
U_LOWERCASE_LETTER = 2,
/** Lt @stable ICU 2.0 */
U_TITLECASE_LETTER = 3,
/** Lm @stable ICU 2.0 */
U_MODIFIER_LETTER = 4,
/** Lo @stable ICU 2.0 */
U_OTHER_LETTER = 5,
/** Mn @stable ICU 2.0 */
U_NON_SPACING_MARK = 6,
/** Me @stable ICU 2.0 */
U_ENCLOSING_MARK = 7,
/** Mc @stable ICU 2.0 */
U_COMBINING_SPACING_MARK = 8,
/** Nd @stable ICU 2.0 */
U_DECIMAL_DIGIT_NUMBER = 9,
/** Nl @stable ICU 2.0 */
U_LETTER_NUMBER = 10,
/** No @stable ICU 2.0 */
U_OTHER_NUMBER = 11,
/** Zs @stable ICU 2.0 */
U_SPACE_SEPARATOR = 12,
/** Zl @stable ICU 2.0 */
U_LINE_SEPARATOR = 13,
/** Zp @stable ICU 2.0 */
U_PARAGRAPH_SEPARATOR = 14,
/** Cc @stable ICU 2.0 */
U_CONTROL_CHAR = 15,
/** Cf @stable ICU 2.0 */
U_FORMAT_CHAR = 16,
/** Co @stable ICU 2.0 */
U_PRIVATE_USE_CHAR = 17,
/** Cs @stable ICU 2.0 */
U_SURROGATE = 18,
/** Pd @stable ICU 2.0 */
U_DASH_PUNCTUATION = 19,
/** Ps @stable ICU 2.0 */
U_START_PUNCTUATION = 20,
/** Pe @stable ICU 2.0 */
U_END_PUNCTUATION = 21,
/** Pc @stable ICU 2.0 */
U_CONNECTOR_PUNCTUATION = 22,
/** Po @stable ICU 2.0 */
U_OTHER_PUNCTUATION = 23,
/** Sm @stable ICU 2.0 */
U_MATH_SYMBOL = 24,
/** Sc @stable ICU 2.0 */
U_CURRENCY_SYMBOL = 25,
/** Sk @stable ICU 2.0 */
U_MODIFIER_SYMBOL = 26,
/** So @stable ICU 2.0 */
U_OTHER_SYMBOL = 27,
/** Pi @stable ICU 2.0 */
U_INITIAL_PUNCTUATION = 28,
/** Pf @stable ICU 2.0 */
U_FINAL_PUNCTUATION = 29,
/** One higher than the last enum UCharCategory constant. @stable ICU 2.0 */
U_CHAR_CATEGORY_COUNT
} UCharCategory;
/**
* U_GC_XX_MASK constants are bit flags corresponding to Unicode
* general category values.
* For each category, the nth bit is set if the numeric value of the
* corresponding UCharCategory constant is n.
*
* There are also some U_GC_Y_MASK constants for groups of general categories
* like L for all letter categories.
*
* @see u_charType
* @see U_GET_GC_MASK
* @see UCharCategory
* @stable ICU 2.1
*/
#define U_GC_CN_MASK U_MASK(U_GENERAL_OTHER_TYPES)
/** Mask constant for a UCharCategory. @stable ICU 2.1 */
#define U_GC_LU_MASK U_MASK(U_UPPERCASE_LETTER)
/** Mask constant for a UCharCategory. @stable ICU 2.1 */
#define U_GC_LL_MASK U_MASK(U_LOWERCASE_LETTER)
/** Mask constant for a UCharCategory. @stable ICU 2.1 */
#define U_GC_LT_MASK U_MASK(U_TITLECASE_LETTER)
/** Mask constant for a UCharCategory. @stable ICU 2.1 */
#define U_GC_LM_MASK U_MASK(U_MODIFIER_LETTER)
/** Mask constant for a UCharCategory. @stable ICU 2.1 */
#define U_GC_LO_MASK U_MASK(U_OTHER_LETTER)
/** Mask constant for a UCharCategory. @stable ICU 2.1 */
#define U_GC_MN_MASK U_MASK(U_NON_SPACING_MARK)
/** Mask constant for a UCharCategory. @stable ICU 2.1 */
#define U_GC_ME_MASK U_MASK(U_ENCLOSING_MARK)
/** Mask constant for a UCharCategory. @stable ICU 2.1 */
#define U_GC_MC_MASK U_MASK(U_COMBINING_SPACING_MARK)
/** Mask constant for a UCharCategory. @stable ICU 2.1 */
#define U_GC_ND_MASK U_MASK(U_DECIMAL_DIGIT_NUMBER)
/** Mask constant for a UCharCategory. @stable ICU 2.1 */
#define U_GC_NL_MASK U_MASK(U_LETTER_NUMBER)
/** Mask constant for a UCharCategory. @stable ICU 2.1 */
#define U_GC_NO_MASK U_MASK(U_OTHER_NUMBER)
/** Mask constant for a UCharCategory. @stable ICU 2.1 */
#define U_GC_ZS_MASK U_MASK(U_SPACE_SEPARATOR)
/** Mask constant for a UCharCategory. @stable ICU 2.1 */
#define U_GC_ZL_MASK U_MASK(U_LINE_SEPARATOR)
/** Mask constant for a UCharCategory. @stable ICU 2.1 */
#define U_GC_ZP_MASK U_MASK(U_PARAGRAPH_SEPARATOR)
/** Mask constant for a UCharCategory. @stable ICU 2.1 */
#define U_GC_CC_MASK U_MASK(U_CONTROL_CHAR)
/** Mask constant for a UCharCategory. @stable ICU 2.1 */
#define U_GC_CF_MASK U_MASK(U_FORMAT_CHAR)
/** Mask constant for a UCharCategory. @stable ICU 2.1 */
#define U_GC_CO_MASK U_MASK(U_PRIVATE_USE_CHAR)
/** Mask constant for a UCharCategory. @stable ICU 2.1 */
#define U_GC_CS_MASK U_MASK(U_SURROGATE)
/** Mask constant for a UCharCategory. @stable ICU 2.1 */
#define U_GC_PD_MASK U_MASK(U_DASH_PUNCTUATION)
/** Mask constant for a UCharCategory. @stable ICU 2.1 */
#define U_GC_PS_MASK U_MASK(U_START_PUNCTUATION)
/** Mask constant for a UCharCategory. @stable ICU 2.1 */
#define U_GC_PE_MASK U_MASK(U_END_PUNCTUATION)
/** Mask constant for a UCharCategory. @stable ICU 2.1 */
#define U_GC_PC_MASK U_MASK(U_CONNECTOR_PUNCTUATION)
/** Mask constant for a UCharCategory. @stable ICU 2.1 */
#define U_GC_PO_MASK U_MASK(U_OTHER_PUNCTUATION)
/** Mask constant for a UCharCategory. @stable ICU 2.1 */
#define U_GC_SM_MASK U_MASK(U_MATH_SYMBOL)
/** Mask constant for a UCharCategory. @stable ICU 2.1 */
#define U_GC_SC_MASK U_MASK(U_CURRENCY_SYMBOL)
/** Mask constant for a UCharCategory. @stable ICU 2.1 */
#define U_GC_SK_MASK U_MASK(U_MODIFIER_SYMBOL)
/** Mask constant for a UCharCategory. @stable ICU 2.1 */
#define U_GC_SO_MASK U_MASK(U_OTHER_SYMBOL)
/** Mask constant for a UCharCategory. @stable ICU 2.1 */
#define U_GC_PI_MASK U_MASK(U_INITIAL_PUNCTUATION)
/** Mask constant for a UCharCategory. @stable ICU 2.1 */
#define U_GC_PF_MASK U_MASK(U_FINAL_PUNCTUATION)
/** Mask constant for multiple UCharCategory bits (L Letters). @stable ICU 2.1 */
#define U_GC_L_MASK \
(U_GC_LU_MASK|U_GC_LL_MASK|U_GC_LT_MASK|U_GC_LM_MASK|U_GC_LO_MASK)
/** Mask constant for multiple UCharCategory bits (LC Cased Letters). @stable ICU 2.1 */
#define U_GC_LC_MASK \
(U_GC_LU_MASK|U_GC_LL_MASK|U_GC_LT_MASK)
/** Mask constant for multiple UCharCategory bits (M Marks). @stable ICU 2.1 */
#define U_GC_M_MASK (U_GC_MN_MASK|U_GC_ME_MASK|U_GC_MC_MASK)
/** Mask constant for multiple UCharCategory bits (N Numbers). @stable ICU 2.1 */
#define U_GC_N_MASK (U_GC_ND_MASK|U_GC_NL_MASK|U_GC_NO_MASK)
/** Mask constant for multiple UCharCategory bits (Z Separators). @stable ICU 2.1 */
#define U_GC_Z_MASK (U_GC_ZS_MASK|U_GC_ZL_MASK|U_GC_ZP_MASK)
/** Mask constant for multiple UCharCategory bits (C Others). @stable ICU 2.1 */
#define U_GC_C_MASK \
(U_GC_CN_MASK|U_GC_CC_MASK|U_GC_CF_MASK|U_GC_CO_MASK|U_GC_CS_MASK)
/** Mask constant for multiple UCharCategory bits (P Punctuation). @stable ICU 2.1 */
#define U_GC_P_MASK \
(U_GC_PD_MASK|U_GC_PS_MASK|U_GC_PE_MASK|U_GC_PC_MASK|U_GC_PO_MASK| \
U_GC_PI_MASK|U_GC_PF_MASK)
/** Mask constant for multiple UCharCategory bits (S Symbols). @stable ICU 2.1 */
#define U_GC_S_MASK (U_GC_SM_MASK|U_GC_SC_MASK|U_GC_SK_MASK|U_GC_SO_MASK)
/**
* This specifies the language directional property of a character set.
* @stable ICU 2.0
*/
typedef enum UCharDirection {
/** See note !!. Comments of the form "EN" are read by genpname. */
/** L @stable ICU 2.0 */
U_LEFT_TO_RIGHT = 0,
/** R @stable ICU 2.0 */
U_RIGHT_TO_LEFT = 1,
/** EN @stable ICU 2.0 */
U_EUROPEAN_NUMBER = 2,
/** ES @stable ICU 2.0 */
U_EUROPEAN_NUMBER_SEPARATOR = 3,
/** ET @stable ICU 2.0 */
U_EUROPEAN_NUMBER_TERMINATOR = 4,
/** AN @stable ICU 2.0 */
U_ARABIC_NUMBER = 5,
/** CS @stable ICU 2.0 */
U_COMMON_NUMBER_SEPARATOR = 6,
/** B @stable ICU 2.0 */
U_BLOCK_SEPARATOR = 7,
/** S @stable ICU 2.0 */
U_SEGMENT_SEPARATOR = 8,
/** WS @stable ICU 2.0 */
U_WHITE_SPACE_NEUTRAL = 9,
/** ON @stable ICU 2.0 */
U_OTHER_NEUTRAL = 10,
/** LRE @stable ICU 2.0 */
U_LEFT_TO_RIGHT_EMBEDDING = 11,
/** LRO @stable ICU 2.0 */
U_LEFT_TO_RIGHT_OVERRIDE = 12,
/** AL @stable ICU 2.0 */
U_RIGHT_TO_LEFT_ARABIC = 13,
/** RLE @stable ICU 2.0 */
U_RIGHT_TO_LEFT_EMBEDDING = 14,
/** RLO @stable ICU 2.0 */
U_RIGHT_TO_LEFT_OVERRIDE = 15,
/** PDF @stable ICU 2.0 */
U_POP_DIRECTIONAL_FORMAT = 16,
/** NSM @stable ICU 2.0 */
U_DIR_NON_SPACING_MARK = 17,
/** BN @stable ICU 2.0 */
U_BOUNDARY_NEUTRAL = 18,
/** @stable ICU 2.0 */
U_CHAR_DIRECTION_COUNT
} UCharDirection;
/**
* Constants for Unicode blocks, see the Unicode Data file Blocks.txt
* @stable ICU 2.0
*/
enum UBlockCode {
/** New No_Block value in Unicode 4. @stable ICU 2.6 */
UBLOCK_NO_BLOCK = 0, /*[none]*/ /* Special range indicating No_Block */
/** @stable ICU 2.0 */
UBLOCK_BASIC_LATIN = 1, /*[0000]*/ /*See note !!*/
/** @stable ICU 2.0 */
UBLOCK_LATIN_1_SUPPLEMENT=2, /*[0080]*/
/** @stable ICU 2.0 */
UBLOCK_LATIN_EXTENDED_A =3, /*[0100]*/
/** @stable ICU 2.0 */
UBLOCK_LATIN_EXTENDED_B =4, /*[0180]*/
/** @stable ICU 2.0 */
UBLOCK_IPA_EXTENSIONS =5, /*[0250]*/
/** @stable ICU 2.0 */
UBLOCK_SPACING_MODIFIER_LETTERS =6, /*[02B0]*/
/** @stable ICU 2.0 */
UBLOCK_COMBINING_DIACRITICAL_MARKS =7, /*[0300]*/
/**
* Unicode 3.2 renames this block to "Greek and Coptic".
* @stable ICU 2.0
*/
UBLOCK_GREEK =8, /*[0370]*/
/** @stable ICU 2.0 */
UBLOCK_CYRILLIC =9, /*[0400]*/
/** @stable ICU 2.0 */
UBLOCK_ARMENIAN =10, /*[0530]*/
/** @stable ICU 2.0 */
UBLOCK_HEBREW =11, /*[0590]*/
/** @stable ICU 2.0 */
UBLOCK_ARABIC =12, /*[0600]*/
/** @stable ICU 2.0 */
UBLOCK_SYRIAC =13, /*[0700]*/
/** @stable ICU 2.0 */
UBLOCK_THAANA =14, /*[0780]*/
/** @stable ICU 2.0 */
UBLOCK_DEVANAGARI =15, /*[0900]*/
/** @stable ICU 2.0 */
UBLOCK_BENGALI =16, /*[0980]*/
/** @stable ICU 2.0 */
UBLOCK_GURMUKHI =17, /*[0A00]*/
/** @stable ICU 2.0 */
UBLOCK_GUJARATI =18, /*[0A80]*/
/** @stable ICU 2.0 */
UBLOCK_ORIYA =19, /*[0B00]*/
/** @stable ICU 2.0 */
UBLOCK_TAMIL =20, /*[0B80]*/
/** @stable ICU 2.0 */
UBLOCK_TELUGU =21, /*[0C00]*/
/** @stable ICU 2.0 */
UBLOCK_KANNADA =22, /*[0C80]*/
/** @stable ICU 2.0 */
UBLOCK_MALAYALAM =23, /*[0D00]*/
/** @stable ICU 2.0 */
UBLOCK_SINHALA =24, /*[0D80]*/
/** @stable ICU 2.0 */
UBLOCK_THAI =25, /*[0E00]*/
/** @stable ICU 2.0 */
UBLOCK_LAO =26, /*[0E80]*/
/** @stable ICU 2.0 */
UBLOCK_TIBETAN =27, /*[0F00]*/
/** @stable ICU 2.0 */
UBLOCK_MYANMAR =28, /*[1000]*/
/** @stable ICU 2.0 */
UBLOCK_GEORGIAN =29, /*[10A0]*/
/** @stable ICU 2.0 */
UBLOCK_HANGUL_JAMO =30, /*[1100]*/
/** @stable ICU 2.0 */
UBLOCK_ETHIOPIC =31, /*[1200]*/
/** @stable ICU 2.0 */
UBLOCK_CHEROKEE =32, /*[13A0]*/
/** @stable ICU 2.0 */
UBLOCK_UNIFIED_CANADIAN_ABORIGINAL_SYLLABICS =33, /*[1400]*/
/** @stable ICU 2.0 */
UBLOCK_OGHAM =34, /*[1680]*/
/** @stable ICU 2.0 */
UBLOCK_RUNIC =35, /*[16A0]*/
/** @stable ICU 2.0 */
UBLOCK_KHMER =36, /*[1780]*/
/** @stable ICU 2.0 */
UBLOCK_MONGOLIAN =37, /*[1800]*/
/** @stable ICU 2.0 */
UBLOCK_LATIN_EXTENDED_ADDITIONAL =38, /*[1E00]*/
/** @stable ICU 2.0 */
UBLOCK_GREEK_EXTENDED =39, /*[1F00]*/
/** @stable ICU 2.0 */
UBLOCK_GENERAL_PUNCTUATION =40, /*[2000]*/
/** @stable ICU 2.0 */
UBLOCK_SUPERSCRIPTS_AND_SUBSCRIPTS =41, /*[2070]*/
/** @stable ICU 2.0 */
UBLOCK_CURRENCY_SYMBOLS =42, /*[20A0]*/
/**
* Unicode 3.2 renames this block to "Combining Diacritical Marks for Symbols".
* @stable ICU 2.0
*/
UBLOCK_COMBINING_MARKS_FOR_SYMBOLS =43, /*[20D0]*/
/** @stable ICU 2.0 */
UBLOCK_LETTERLIKE_SYMBOLS =44, /*[2100]*/
/** @stable ICU 2.0 */
UBLOCK_NUMBER_FORMS =45, /*[2150]*/
/** @stable ICU 2.0 */
UBLOCK_ARROWS =46, /*[2190]*/
/** @stable ICU 2.0 */
UBLOCK_MATHEMATICAL_OPERATORS =47, /*[2200]*/
/** @stable ICU 2.0 */
UBLOCK_MISCELLANEOUS_TECHNICAL =48, /*[2300]*/
/** @stable ICU 2.0 */
UBLOCK_CONTROL_PICTURES =49, /*[2400]*/
/** @stable ICU 2.0 */
UBLOCK_OPTICAL_CHARACTER_RECOGNITION =50, /*[2440]*/
/** @stable ICU 2.0 */
UBLOCK_ENCLOSED_ALPHANUMERICS =51, /*[2460]*/
/** @stable ICU 2.0 */
UBLOCK_BOX_DRAWING =52, /*[2500]*/
/** @stable ICU 2.0 */
UBLOCK_BLOCK_ELEMENTS =53, /*[2580]*/
/** @stable ICU 2.0 */
UBLOCK_GEOMETRIC_SHAPES =54, /*[25A0]*/
/** @stable ICU 2.0 */
UBLOCK_MISCELLANEOUS_SYMBOLS =55, /*[2600]*/
/** @stable ICU 2.0 */
UBLOCK_DINGBATS =56, /*[2700]*/
/** @stable ICU 2.0 */
UBLOCK_BRAILLE_PATTERNS =57, /*[2800]*/
/** @stable ICU 2.0 */
UBLOCK_CJK_RADICALS_SUPPLEMENT =58, /*[2E80]*/
/** @stable ICU 2.0 */
UBLOCK_KANGXI_RADICALS =59, /*[2F00]*/
/** @stable ICU 2.0 */
UBLOCK_IDEOGRAPHIC_DESCRIPTION_CHARACTERS =60, /*[2FF0]*/
/** @stable ICU 2.0 */
UBLOCK_CJK_SYMBOLS_AND_PUNCTUATION =61, /*[3000]*/
/** @stable ICU 2.0 */
UBLOCK_HIRAGANA =62, /*[3040]*/
/** @stable ICU 2.0 */
UBLOCK_KATAKANA =63, /*[30A0]*/
/** @stable ICU 2.0 */
UBLOCK_BOPOMOFO =64, /*[3100]*/
/** @stable ICU 2.0 */
UBLOCK_HANGUL_COMPATIBILITY_JAMO =65, /*[3130]*/
/** @stable ICU 2.0 */
UBLOCK_KANBUN =66, /*[3190]*/
/** @stable ICU 2.0 */
UBLOCK_BOPOMOFO_EXTENDED =67, /*[31A0]*/
/** @stable ICU 2.0 */
UBLOCK_ENCLOSED_CJK_LETTERS_AND_MONTHS =68, /*[3200]*/
/** @stable ICU 2.0 */
UBLOCK_CJK_COMPATIBILITY =69, /*[3300]*/
/** @stable ICU 2.0 */
UBLOCK_CJK_UNIFIED_IDEOGRAPHS_EXTENSION_A =70, /*[3400]*/
/** @stable ICU 2.0 */
UBLOCK_CJK_UNIFIED_IDEOGRAPHS =71, /*[4E00]*/
/** @stable ICU 2.0 */
UBLOCK_YI_SYLLABLES =72, /*[A000]*/
/** @stable ICU 2.0 */
UBLOCK_YI_RADICALS =73, /*[A490]*/
/** @stable ICU 2.0 */
UBLOCK_HANGUL_SYLLABLES =74, /*[AC00]*/
/** @stable ICU 2.0 */
UBLOCK_HIGH_SURROGATES =75, /*[D800]*/
/** @stable ICU 2.0 */
UBLOCK_HIGH_PRIVATE_USE_SURROGATES =76, /*[DB80]*/
/** @stable ICU 2.0 */
UBLOCK_LOW_SURROGATES =77, /*[DC00]*/
/**
* Same as UBLOCK_PRIVATE_USE_AREA.
* Until Unicode 3.1.1, the corresponding block name was "Private Use",
* and multiple code point ranges had this block.
* Unicode 3.2 renames the block for the BMP PUA to "Private Use Area" and
* adds separate blocks for the supplementary PUAs.
*
* @stable ICU 2.0
*/
UBLOCK_PRIVATE_USE = 78,
/**
* Same as UBLOCK_PRIVATE_USE.
* Until Unicode 3.1.1, the corresponding block name was "Private Use",
* and multiple code point ranges had this block.
* Unicode 3.2 renames the block for the BMP PUA to "Private Use Area" and
* adds separate blocks for the supplementary PUAs.
*