1 // Copyright (C) 2016 and later: Unicode, Inc. and others.
2 // License & terms of use: http://www.unicode.org/copyright.html
4 **********************************************************************
5 * Copyright (C) 1997-2016, International Business Machines
6 * Corporation and others. All Rights Reserved.
7 **********************************************************************
11 * Modification History:
13 * Date Name Description
14 * 04/02/97 aliu Creation.
15 * 03/29/99 helena Updated for C APIs.
16 * 4/15/99 Madhu Updated for C Implementation and Javadoc
17 * 5/20/99 Madhu Added the function u_getVersion()
18 * 8/19/1999 srl Upgraded scripts to Unicode 3.0
19 * 8/27/1999 schererm UCharDirection constants: U_...
20 * 11/11/1999 weiv added u_isalnum(), cleaned comments
21 * 01/11/2000 helena Renamed u_getVersion to u_getUnicodeVersion().
22 ******************************************************************************
28 #include "unicode/utypes.h"
32 /*==========================================================================*/
33 /* Unicode version number */
34 /*==========================================================================*/
36 * Unicode version number, default for the current ICU version.
37 * The actual Unicode Character Database (UCD) data is stored in uprops.dat
38 * and may be generated from UCD files from a different Unicode version.
39 * Call u_getUnicodeVersion to get the actual Unicode version of the data.
41 * @see u_getUnicodeVersion
44 #define U_UNICODE_VERSION "9.0"
48 * \brief C API: Unicode Properties
50 * This C API provides low-level access to the Unicode Character Database.
51 * In addition to raw property values, some convenience functions calculate
52 * derived properties, for example for Java-style programming.
54 * Unicode assigns each code point (not just assigned character) values for
56 * Most of them are simple boolean flags, or constants from a small enumerated list.
57 * For some properties, values are strings or other relatively more complex types.
59 * For more information see
60 * "About the Unicode Character Database" (http://www.unicode.org/ucd/)
61 * and the ICU User Guide chapter on Properties (http://icu-project.org/userguide/properties.html).
63 * Many functions are designed to match java.lang.Character functions.
64 * See the individual function documentation,
65 * and see the JDK 1.4 java.lang.Character documentation
66 * at http://java.sun.com/j2se/1.4/docs/api/java/lang/Character.html
68 * There are also functions that provide easy migration from C/POSIX functions
69 * like isblank(). Their use is generally discouraged because the C/POSIX
70 * standards do not define their semantics beyond the ASCII range, which means
71 * that different implementations exhibit very different behavior.
72 * Instead, Unicode properties should be used directly.
74 * There are also only a few, broad C/POSIX character classes, and they tend
75 * to be used for conflicting purposes. For example, the "isalpha()" class
76 * is sometimes used to determine word boundaries, while a more sophisticated
77 * approach would at least distinguish initial letters from continuation
78 * characters (the latter including combining marks).
79 * (In ICU, BreakIterator is the most sophisticated API for word boundaries.)
80 * Another example: There is no "istitle()" class for titlecase characters.
82 * ICU 3.4 and later provides API access for all twelve C/POSIX character classes.
83 * ICU implements them according to the Standard Recommendations in
84 * Annex C: Compatibility Properties of UTS #18 Unicode Regular Expressions
85 * (http://www.unicode.org/reports/tr18/#Compatibility_Properties).
87 * API access for C/POSIX character classes is as follows:
88 * - alpha: u_isUAlphabetic(c) or u_hasBinaryProperty(c, UCHAR_ALPHABETIC)
89 * - lower: u_isULowercase(c) or u_hasBinaryProperty(c, UCHAR_LOWERCASE)
90 * - upper: u_isUUppercase(c) or u_hasBinaryProperty(c, UCHAR_UPPERCASE)
91 * - punct: u_ispunct(c)
92 * - digit: u_isdigit(c) or u_charType(c)==U_DECIMAL_DIGIT_NUMBER
93 * - xdigit: u_isxdigit(c) or u_hasBinaryProperty(c, UCHAR_POSIX_XDIGIT)
94 * - alnum: u_hasBinaryProperty(c, UCHAR_POSIX_ALNUM)
95 * - space: u_isUWhiteSpace(c) or u_hasBinaryProperty(c, UCHAR_WHITE_SPACE)
96 * - blank: u_isblank(c) or u_hasBinaryProperty(c, UCHAR_POSIX_BLANK)
97 * - cntrl: u_charType(c)==U_CONTROL_CHAR
98 * - graph: u_hasBinaryProperty(c, UCHAR_POSIX_GRAPH)
99 * - print: u_hasBinaryProperty(c, UCHAR_POSIX_PRINT)
101 * Note: Some of the u_isxyz() functions in uchar.h predate, and do not match,
102 * the Standard Recommendations in UTS #18. Instead, they match Java
103 * functions according to their API documentation.
106 * The C/POSIX character classes are also available in UnicodeSet patterns,
107 * using patterns like [:graph:] or \p{graph}.
110 * Note: There are several ICU whitespace functions.
112 * - u_isUWhiteSpace=UCHAR_WHITE_SPACE: Unicode White_Space property;
113 * most of general categories "Z" (separators) + most whitespace ISO controls
114 * (including no-break spaces, but excluding IS1..IS4 and ZWSP)
115 * - u_isWhitespace: Java isWhitespace; Z + whitespace ISO controls but excluding no-break spaces
116 * - u_isJavaSpaceChar: Java isSpaceChar; just Z (including no-break spaces)
117 * - u_isspace: Z + whitespace ISO controls (including no-break spaces)
118 * - u_isblank: "horizontal spaces" = TAB + Zs - ZWSP
125 /** The lowest Unicode code point value. Code points are non-negative. @stable ICU 2.0 */
126 #define UCHAR_MIN_VALUE 0
129 * The highest Unicode code point value (scalar value) according to
130 * The Unicode Standard. This is a 21-bit value (20.1 bits, rounded up).
131 * For a single character, UChar32 is a simple type that can hold any code point value.
136 #define UCHAR_MAX_VALUE 0x10ffff
139 * Get a single-bit bit set (a flag) from a bit number 0..31.
142 #define U_MASK(x) ((uint32_t)1<<(x))
145 * Selection constants for Unicode properties.
146 * These constants are used in functions like u_hasBinaryProperty to select
147 * one of the Unicode properties.
149 * The properties APIs are intended to reflect Unicode properties as defined
150 * in the Unicode Character Database (UCD) and Unicode Technical Reports (UTR).
151 * For details about the properties see http://www.unicode.org/ucd/ .
152 * For names of Unicode properties see the UCD file PropertyAliases.txt.
154 * Important: If ICU is built with UCD files from Unicode versions below, e.g., 3.2,
155 * then properties marked with "new in Unicode 3.2" are not or not fully available.
156 * Check u_getUnicodeVersion to be sure.
158 * @see u_hasBinaryProperty
159 * @see u_getIntPropertyValue
160 * @see u_getUnicodeVersion
163 typedef enum UProperty {
165 * Note: UProperty constants are parsed by preparseucd.py.
166 * It matches lines like
167 * UCHAR_<Unicode property name>=<integer>,
170 /* Note: Place UCHAR_ALPHABETIC before UCHAR_BINARY_START so that
171 debuggers display UCHAR_ALPHABETIC as the symbolic name for 0,
172 rather than UCHAR_BINARY_START. Likewise for other *_START
175 /** Binary property Alphabetic. Same as u_isUAlphabetic, different from u_isalpha.
176 Lu+Ll+Lt+Lm+Lo+Nl+Other_Alphabetic @stable ICU 2.1 */
178 /** First constant for binary Unicode properties. @stable ICU 2.1 */
179 UCHAR_BINARY_START=UCHAR_ALPHABETIC,
180 /** Binary property ASCII_Hex_Digit. 0-9 A-F a-f @stable ICU 2.1 */
181 UCHAR_ASCII_HEX_DIGIT=1,
182 /** Binary property Bidi_Control.
183 Format controls which have specific functions
184 in the Bidi Algorithm. @stable ICU 2.1 */
185 UCHAR_BIDI_CONTROL=2,
186 /** Binary property Bidi_Mirrored.
187 Characters that may change display in RTL text.
188 Same as u_isMirrored.
189 See Bidi Algorithm, UTR 9. @stable ICU 2.1 */
190 UCHAR_BIDI_MIRRORED=3,
191 /** Binary property Dash. Variations of dashes. @stable ICU 2.1 */
193 /** Binary property Default_Ignorable_Code_Point (new in Unicode 3.2).
194 Ignorable in most processing.
195 <2060..206F, FFF0..FFFB, E0000..E0FFF>+Other_Default_Ignorable_Code_Point+(Cf+Cc+Cs-White_Space) @stable ICU 2.1 */
196 UCHAR_DEFAULT_IGNORABLE_CODE_POINT=5,
197 /** Binary property Deprecated (new in Unicode 3.2).
198 The usage of deprecated characters is strongly discouraged. @stable ICU 2.1 */
200 /** Binary property Diacritic. Characters that linguistically modify
201 the meaning of another character to which they apply. @stable ICU 2.1 */
203 /** Binary property Extender.
204 Extend the value or shape of a preceding alphabetic character,
205 e.g., length and iteration marks. @stable ICU 2.1 */
207 /** Binary property Full_Composition_Exclusion.
208 CompositionExclusions.txt+Singleton Decompositions+
209 Non-Starter Decompositions. @stable ICU 2.1 */
210 UCHAR_FULL_COMPOSITION_EXCLUSION=9,
211 /** Binary property Grapheme_Base (new in Unicode 3.2).
212 For programmatic determination of grapheme cluster boundaries.
213 [0..10FFFF]-Cc-Cf-Cs-Co-Cn-Zl-Zp-Grapheme_Link-Grapheme_Extend-CGJ @stable ICU 2.1 */
214 UCHAR_GRAPHEME_BASE=10,
215 /** Binary property Grapheme_Extend (new in Unicode 3.2).
216 For programmatic determination of grapheme cluster boundaries.
217 Me+Mn+Mc+Other_Grapheme_Extend-Grapheme_Link-CGJ @stable ICU 2.1 */
218 UCHAR_GRAPHEME_EXTEND=11,
219 /** Binary property Grapheme_Link (new in Unicode 3.2).
220 For programmatic determination of grapheme cluster boundaries. @stable ICU 2.1 */
221 UCHAR_GRAPHEME_LINK=12,
222 /** Binary property Hex_Digit.
223 Characters commonly used for hexadecimal numbers. @stable ICU 2.1 */
225 /** Binary property Hyphen. Dashes used to mark connections
226 between pieces of words, plus the Katakana middle dot. @stable ICU 2.1 */
228 /** Binary property ID_Continue.
229 Characters that can continue an identifier.
230 DerivedCoreProperties.txt also says "NOTE: Cf characters should be filtered out."
231 ID_Start+Mn+Mc+Nd+Pc @stable ICU 2.1 */
232 UCHAR_ID_CONTINUE=15,
233 /** Binary property ID_Start.
234 Characters that can start an identifier.
235 Lu+Ll+Lt+Lm+Lo+Nl @stable ICU 2.1 */
237 /** Binary property Ideographic.
238 CJKV ideographs. @stable ICU 2.1 */
239 UCHAR_IDEOGRAPHIC=17,
240 /** Binary property IDS_Binary_Operator (new in Unicode 3.2).
241 For programmatic determination of
242 Ideographic Description Sequences. @stable ICU 2.1 */
243 UCHAR_IDS_BINARY_OPERATOR=18,
244 /** Binary property IDS_Trinary_Operator (new in Unicode 3.2).
245 For programmatic determination of
246 Ideographic Description Sequences. @stable ICU 2.1 */
247 UCHAR_IDS_TRINARY_OPERATOR=19,
248 /** Binary property Join_Control.
249 Format controls for cursive joining and ligation. @stable ICU 2.1 */
250 UCHAR_JOIN_CONTROL=20,
251 /** Binary property Logical_Order_Exception (new in Unicode 3.2).
252 Characters that do not use logical order and
253 require special handling in most processing. @stable ICU 2.1 */
254 UCHAR_LOGICAL_ORDER_EXCEPTION=21,
255 /** Binary property Lowercase. Same as u_isULowercase, different from u_islower.
256 Ll+Other_Lowercase @stable ICU 2.1 */
258 /** Binary property Math. Sm+Other_Math @stable ICU 2.1 */
260 /** Binary property Noncharacter_Code_Point.
261 Code points that are explicitly defined as illegal
262 for the encoding of characters. @stable ICU 2.1 */
263 UCHAR_NONCHARACTER_CODE_POINT=24,
264 /** Binary property Quotation_Mark. @stable ICU 2.1 */
265 UCHAR_QUOTATION_MARK=25,
266 /** Binary property Radical (new in Unicode 3.2).
267 For programmatic determination of
268 Ideographic Description Sequences. @stable ICU 2.1 */
270 /** Binary property Soft_Dotted (new in Unicode 3.2).
271 Characters with a "soft dot", like i or j.
272 An accent placed on these characters causes
273 the dot to disappear. @stable ICU 2.1 */
274 UCHAR_SOFT_DOTTED=27,
275 /** Binary property Terminal_Punctuation.
276 Punctuation characters that generally mark
277 the end of textual units. @stable ICU 2.1 */
278 UCHAR_TERMINAL_PUNCTUATION=28,
279 /** Binary property Unified_Ideograph (new in Unicode 3.2).
280 For programmatic determination of
281 Ideographic Description Sequences. @stable ICU 2.1 */
282 UCHAR_UNIFIED_IDEOGRAPH=29,
283 /** Binary property Uppercase. Same as u_isUUppercase, different from u_isupper.
284 Lu+Other_Uppercase @stable ICU 2.1 */
286 /** Binary property White_Space.
287 Same as u_isUWhiteSpace, different from u_isspace and u_isWhitespace.
288 Space characters+TAB+CR+LF-ZWSP-ZWNBSP @stable ICU 2.1 */
289 UCHAR_WHITE_SPACE=31,
290 /** Binary property XID_Continue.
291 ID_Continue modified to allow closure under
292 normalization forms NFKC and NFKD. @stable ICU 2.1 */
293 UCHAR_XID_CONTINUE=32,
294 /** Binary property XID_Start. ID_Start modified to allow
295 closure under normalization forms NFKC and NFKD. @stable ICU 2.1 */
297 /** Binary property Case_Sensitive. Either the source of a case
298 mapping or _in_ the target of a case mapping. Not the same as
299 the general category Cased_Letter. @stable ICU 2.6 */
300 UCHAR_CASE_SENSITIVE=34,
301 /** Binary property STerm (new in Unicode 4.0.1).
302 Sentence Terminal. Used in UAX #29: Text Boundaries
303 (http://www.unicode.org/reports/tr29/)
306 /** Binary property Variation_Selector (new in Unicode 4.0.1).
307 Indicates all those characters that qualify as Variation Selectors.
308 For details on the behavior of these characters,
309 see StandardizedVariants.html and 15.6 Variation Selectors.
311 UCHAR_VARIATION_SELECTOR=36,
312 /** Binary property NFD_Inert.
313 ICU-specific property for characters that are inert under NFD,
314 i.e., they do not interact with adjacent characters.
315 See the documentation for the Normalizer2 class and the
316 Normalizer2::isInert() method.
319 /** Binary property NFKD_Inert.
320 ICU-specific property for characters that are inert under NFKD,
321 i.e., they do not interact with adjacent characters.
322 See the documentation for the Normalizer2 class and the
323 Normalizer2::isInert() method.
326 /** Binary property NFC_Inert.
327 ICU-specific property for characters that are inert under NFC,
328 i.e., they do not interact with adjacent characters.
329 See the documentation for the Normalizer2 class and the
330 Normalizer2::isInert() method.
333 /** Binary property NFKC_Inert.
334 ICU-specific property for characters that are inert under NFKC,
335 i.e., they do not interact with adjacent characters.
336 See the documentation for the Normalizer2 class and the
337 Normalizer2::isInert() method.
340 /** Binary Property Segment_Starter.
341 ICU-specific property for characters that are starters in terms of
342 Unicode normalization and combining character sequences.
343 They have ccc=0 and do not occur in non-initial position of the
344 canonical decomposition of any character
345 (like a-umlaut in NFD and a Jamo T in an NFD(Hangul LVT)).
346 ICU uses this property for segmenting a string for generating a set of
347 canonically equivalent strings, e.g. for canonical closure while
348 processing collation tailoring rules.
350 UCHAR_SEGMENT_STARTER=41,
351 /** Binary property Pattern_Syntax (new in Unicode 4.1).
352 See UAX #31 Identifier and Pattern Syntax
353 (http://www.unicode.org/reports/tr31/)
355 UCHAR_PATTERN_SYNTAX=42,
356 /** Binary property Pattern_White_Space (new in Unicode 4.1).
357 See UAX #31 Identifier and Pattern Syntax
358 (http://www.unicode.org/reports/tr31/)
360 UCHAR_PATTERN_WHITE_SPACE=43,
361 /** Binary property alnum (a C/POSIX character class).
362 Implemented according to the UTS #18 Annex C Standard Recommendation.
363 See the uchar.h file documentation.
365 UCHAR_POSIX_ALNUM=44,
366 /** Binary property blank (a C/POSIX character class).
367 Implemented according to the UTS #18 Annex C Standard Recommendation.
368 See the uchar.h file documentation.
370 UCHAR_POSIX_BLANK=45,
371 /** Binary property graph (a C/POSIX character class).
372 Implemented according to the UTS #18 Annex C Standard Recommendation.
373 See the uchar.h file documentation.
375 UCHAR_POSIX_GRAPH=46,
376 /** Binary property print (a C/POSIX character class).
377 Implemented according to the UTS #18 Annex C Standard Recommendation.
378 See the uchar.h file documentation.
380 UCHAR_POSIX_PRINT=47,
381 /** Binary property xdigit (a C/POSIX character class).
382 Implemented according to the UTS #18 Annex C Standard Recommendation.
383 See the uchar.h file documentation.
385 UCHAR_POSIX_XDIGIT=48,
386 /** Binary property Cased. For Lowercase, Uppercase and Titlecase characters. @stable ICU 4.4 */
388 /** Binary property Case_Ignorable. Used in context-sensitive case mappings. @stable ICU 4.4 */
389 UCHAR_CASE_IGNORABLE=50,
390 /** Binary property Changes_When_Lowercased. @stable ICU 4.4 */
391 UCHAR_CHANGES_WHEN_LOWERCASED=51,
392 /** Binary property Changes_When_Uppercased. @stable ICU 4.4 */
393 UCHAR_CHANGES_WHEN_UPPERCASED=52,
394 /** Binary property Changes_When_Titlecased. @stable ICU 4.4 */
395 UCHAR_CHANGES_WHEN_TITLECASED=53,
396 /** Binary property Changes_When_Casefolded. @stable ICU 4.4 */
397 UCHAR_CHANGES_WHEN_CASEFOLDED=54,
398 /** Binary property Changes_When_Casemapped. @stable ICU 4.4 */
399 UCHAR_CHANGES_WHEN_CASEMAPPED=55,
400 /** Binary property Changes_When_NFKC_Casefolded. @stable ICU 4.4 */
401 UCHAR_CHANGES_WHEN_NFKC_CASEFOLDED=56,
402 #ifndef U_HIDE_DRAFT_API
404 * Binary property Emoji.
405 * See http://www.unicode.org/reports/tr51/#Emoji_Properties
411 * Binary property Emoji_Presentation.
412 * See http://www.unicode.org/reports/tr51/#Emoji_Properties
416 UCHAR_EMOJI_PRESENTATION=58,
418 * Binary property Emoji_Modifier.
419 * See http://www.unicode.org/reports/tr51/#Emoji_Properties
423 UCHAR_EMOJI_MODIFIER=59,
425 * Binary property Emoji_Modifier_Base.
426 * See http://www.unicode.org/reports/tr51/#Emoji_Properties
430 UCHAR_EMOJI_MODIFIER_BASE=60,
431 #endif /* U_HIDE_DRAFT_API */
432 #ifndef U_HIDE_DEPRECATED_API
434 * One more than the last constant for binary Unicode properties.
435 * @deprecated ICU 58 The numeric value may change over time, see ICU ticket #12420.
437 UCHAR_BINARY_LIMIT=61,
438 #endif // U_HIDE_DEPRECATED_API
440 /** Enumerated property Bidi_Class.
441 Same as u_charDirection, returns UCharDirection values. @stable ICU 2.2 */
442 UCHAR_BIDI_CLASS=0x1000,
443 /** First constant for enumerated/integer Unicode properties. @stable ICU 2.2 */
444 UCHAR_INT_START=UCHAR_BIDI_CLASS,
445 /** Enumerated property Block.
446 Same as ublock_getCode, returns UBlockCode values. @stable ICU 2.2 */
448 /** Enumerated property Canonical_Combining_Class.
449 Same as u_getCombiningClass, returns 8-bit numeric values. @stable ICU 2.2 */
450 UCHAR_CANONICAL_COMBINING_CLASS=0x1002,
451 /** Enumerated property Decomposition_Type.
452 Returns UDecompositionType values. @stable ICU 2.2 */
453 UCHAR_DECOMPOSITION_TYPE=0x1003,
454 /** Enumerated property East_Asian_Width.
455 See http://www.unicode.org/reports/tr11/
456 Returns UEastAsianWidth values. @stable ICU 2.2 */
457 UCHAR_EAST_ASIAN_WIDTH=0x1004,
458 /** Enumerated property General_Category.
459 Same as u_charType, returns UCharCategory values. @stable ICU 2.2 */
460 UCHAR_GENERAL_CATEGORY=0x1005,
461 /** Enumerated property Joining_Group.
462 Returns UJoiningGroup values. @stable ICU 2.2 */
463 UCHAR_JOINING_GROUP=0x1006,
464 /** Enumerated property Joining_Type.
465 Returns UJoiningType values. @stable ICU 2.2 */
466 UCHAR_JOINING_TYPE=0x1007,
467 /** Enumerated property Line_Break.
468 Returns ULineBreak values. @stable ICU 2.2 */
469 UCHAR_LINE_BREAK=0x1008,
470 /** Enumerated property Numeric_Type.
471 Returns UNumericType values. @stable ICU 2.2 */
472 UCHAR_NUMERIC_TYPE=0x1009,
473 /** Enumerated property Script.
474 Same as uscript_getScript, returns UScriptCode values. @stable ICU 2.2 */
476 /** Enumerated property Hangul_Syllable_Type, new in Unicode 4.
477 Returns UHangulSyllableType values. @stable ICU 2.6 */
478 UCHAR_HANGUL_SYLLABLE_TYPE=0x100B,
479 /** Enumerated property NFD_Quick_Check.
480 Returns UNormalizationCheckResult values. @stable ICU 3.0 */
481 UCHAR_NFD_QUICK_CHECK=0x100C,
482 /** Enumerated property NFKD_Quick_Check.
483 Returns UNormalizationCheckResult values. @stable ICU 3.0 */
484 UCHAR_NFKD_QUICK_CHECK=0x100D,
485 /** Enumerated property NFC_Quick_Check.
486 Returns UNormalizationCheckResult values. @stable ICU 3.0 */
487 UCHAR_NFC_QUICK_CHECK=0x100E,
488 /** Enumerated property NFKC_Quick_Check.
489 Returns UNormalizationCheckResult values. @stable ICU 3.0 */
490 UCHAR_NFKC_QUICK_CHECK=0x100F,
491 /** Enumerated property Lead_Canonical_Combining_Class.
492 ICU-specific property for the ccc of the first code point
493 of the decomposition, or lccc(c)=ccc(NFD(c)[0]).
494 Useful for checking for canonically ordered text;
495 see UNORM_FCD and http://www.unicode.org/notes/tn5/#FCD .
496 Returns 8-bit numeric values like UCHAR_CANONICAL_COMBINING_CLASS. @stable ICU 3.0 */
497 UCHAR_LEAD_CANONICAL_COMBINING_CLASS=0x1010,
498 /** Enumerated property Trail_Canonical_Combining_Class.
499 ICU-specific property for the ccc of the last code point
500 of the decomposition, or tccc(c)=ccc(NFD(c)[last]).
501 Useful for checking for canonically ordered text;
502 see UNORM_FCD and http://www.unicode.org/notes/tn5/#FCD .
503 Returns 8-bit numeric values like UCHAR_CANONICAL_COMBINING_CLASS. @stable ICU 3.0 */
504 UCHAR_TRAIL_CANONICAL_COMBINING_CLASS=0x1011,
505 /** Enumerated property Grapheme_Cluster_Break (new in Unicode 4.1).
506 Used in UAX #29: Text Boundaries
507 (http://www.unicode.org/reports/tr29/)
508 Returns UGraphemeClusterBreak values. @stable ICU 3.4 */
509 UCHAR_GRAPHEME_CLUSTER_BREAK=0x1012,
510 /** Enumerated property Sentence_Break (new in Unicode 4.1).
511 Used in UAX #29: Text Boundaries
512 (http://www.unicode.org/reports/tr29/)
513 Returns USentenceBreak values. @stable ICU 3.4 */
514 UCHAR_SENTENCE_BREAK=0x1013,
515 /** Enumerated property Word_Break (new in Unicode 4.1).
516 Used in UAX #29: Text Boundaries
517 (http://www.unicode.org/reports/tr29/)
518 Returns UWordBreakValues values. @stable ICU 3.4 */
519 UCHAR_WORD_BREAK=0x1014,
520 /** Enumerated property Bidi_Paired_Bracket_Type (new in Unicode 6.3).
521 Used in UAX #9: Unicode Bidirectional Algorithm
522 (http://www.unicode.org/reports/tr9/)
523 Returns UBidiPairedBracketType values. @stable ICU 52 */
524 UCHAR_BIDI_PAIRED_BRACKET_TYPE=0x1015,
525 #ifndef U_HIDE_DEPRECATED_API
527 * One more than the last constant for enumerated/integer Unicode properties.
528 * @deprecated ICU 58 The numeric value may change over time, see ICU ticket #12420.
530 UCHAR_INT_LIMIT=0x1016,
531 #endif // U_HIDE_DEPRECATED_API
533 /** Bitmask property General_Category_Mask.
534 This is the General_Category property returned as a bit mask.
535 When used in u_getIntPropertyValue(c), same as U_MASK(u_charType(c)),
536 returns bit masks for UCharCategory values where exactly one bit is set.
537 When used with u_getPropertyValueName() and u_getPropertyValueEnum(),
538 a multi-bit mask is used for sets of categories like "Letters".
539 Mask values should be cast to uint32_t.
541 UCHAR_GENERAL_CATEGORY_MASK=0x2000,
542 /** First constant for bit-mask Unicode properties. @stable ICU 2.4 */
543 UCHAR_MASK_START=UCHAR_GENERAL_CATEGORY_MASK,
544 #ifndef U_HIDE_DEPRECATED_API
546 * One more than the last constant for bit-mask Unicode properties.
547 * @deprecated ICU 58 The numeric value may change over time, see ICU ticket #12420.
549 UCHAR_MASK_LIMIT=0x2001,
550 #endif // U_HIDE_DEPRECATED_API
552 /** Double property Numeric_Value.
553 Corresponds to u_getNumericValue. @stable ICU 2.4 */
554 UCHAR_NUMERIC_VALUE=0x3000,
555 /** First constant for double Unicode properties. @stable ICU 2.4 */
556 UCHAR_DOUBLE_START=UCHAR_NUMERIC_VALUE,
557 #ifndef U_HIDE_DEPRECATED_API
559 * One more than the last constant for double Unicode properties.
560 * @deprecated ICU 58 The numeric value may change over time, see ICU ticket #12420.
562 UCHAR_DOUBLE_LIMIT=0x3001,
563 #endif // U_HIDE_DEPRECATED_API
565 /** String property Age.
566 Corresponds to u_charAge. @stable ICU 2.4 */
568 /** First constant for string Unicode properties. @stable ICU 2.4 */
569 UCHAR_STRING_START=UCHAR_AGE,
570 /** String property Bidi_Mirroring_Glyph.
571 Corresponds to u_charMirror. @stable ICU 2.4 */
572 UCHAR_BIDI_MIRRORING_GLYPH=0x4001,
573 /** String property Case_Folding.
574 Corresponds to u_strFoldCase in ustring.h. @stable ICU 2.4 */
575 UCHAR_CASE_FOLDING=0x4002,
576 #ifndef U_HIDE_DEPRECATED_API
577 /** Deprecated string property ISO_Comment.
578 Corresponds to u_getISOComment. @deprecated ICU 49 */
579 UCHAR_ISO_COMMENT=0x4003,
580 #endif /* U_HIDE_DEPRECATED_API */
581 /** String property Lowercase_Mapping.
582 Corresponds to u_strToLower in ustring.h. @stable ICU 2.4 */
583 UCHAR_LOWERCASE_MAPPING=0x4004,
584 /** String property Name.
585 Corresponds to u_charName. @stable ICU 2.4 */
587 /** String property Simple_Case_Folding.
588 Corresponds to u_foldCase. @stable ICU 2.4 */
589 UCHAR_SIMPLE_CASE_FOLDING=0x4006,
590 /** String property Simple_Lowercase_Mapping.
591 Corresponds to u_tolower. @stable ICU 2.4 */
592 UCHAR_SIMPLE_LOWERCASE_MAPPING=0x4007,
593 /** String property Simple_Titlecase_Mapping.
594 Corresponds to u_totitle. @stable ICU 2.4 */
595 UCHAR_SIMPLE_TITLECASE_MAPPING=0x4008,
596 /** String property Simple_Uppercase_Mapping.
597 Corresponds to u_toupper. @stable ICU 2.4 */
598 UCHAR_SIMPLE_UPPERCASE_MAPPING=0x4009,
599 /** String property Titlecase_Mapping.
600 Corresponds to u_strToTitle in ustring.h. @stable ICU 2.4 */
601 UCHAR_TITLECASE_MAPPING=0x400A,
602 #ifndef U_HIDE_DEPRECATED_API
603 /** String property Unicode_1_Name.
604 This property is of little practical value.
605 Beginning with ICU 49, ICU APIs return an empty string for this property.
606 Corresponds to u_charName(U_UNICODE_10_CHAR_NAME). @deprecated ICU 49 */
607 UCHAR_UNICODE_1_NAME=0x400B,
608 #endif /* U_HIDE_DEPRECATED_API */
609 /** String property Uppercase_Mapping.
610 Corresponds to u_strToUpper in ustring.h. @stable ICU 2.4 */
611 UCHAR_UPPERCASE_MAPPING=0x400C,
612 /** String property Bidi_Paired_Bracket (new in Unicode 6.3).
613 Corresponds to u_getBidiPairedBracket. @stable ICU 52 */
614 UCHAR_BIDI_PAIRED_BRACKET=0x400D,
615 #ifndef U_HIDE_DEPRECATED_API
617 * One more than the last constant for string Unicode properties.
618 * @deprecated ICU 58 The numeric value may change over time, see ICU ticket #12420.
620 UCHAR_STRING_LIMIT=0x400E,
621 #endif // U_HIDE_DEPRECATED_API
623 /** Miscellaneous property Script_Extensions (new in Unicode 6.0).
624 Some characters are commonly used in multiple scripts.
625 For more information, see UAX #24: http://www.unicode.org/reports/tr24/.
626 Corresponds to uscript_hasScript and uscript_getScriptExtensions in uscript.h.
628 UCHAR_SCRIPT_EXTENSIONS=0x7000,
629 /** First constant for Unicode properties with unusual value types. @stable ICU 4.6 */
630 UCHAR_OTHER_PROPERTY_START=UCHAR_SCRIPT_EXTENSIONS,
631 #ifndef U_HIDE_DEPRECATED_API
633 * One more than the last constant for Unicode properties with unusual value types.
634 * @deprecated ICU 58 The numeric value may change over time, see ICU ticket #12420.
636 UCHAR_OTHER_PROPERTY_LIMIT=0x7001,
637 #endif // U_HIDE_DEPRECATED_API
639 /** Represents a nonexistent or invalid property or property value. @stable ICU 2.4 */
640 UCHAR_INVALID_CODE = -1
644 * Data for enumerated Unicode general category types.
645 * See http://www.unicode.org/Public/UNIDATA/UnicodeData.html .
648 typedef enum UCharCategory
651 * Note: UCharCategory constants and their API comments are parsed by preparseucd.py.
652 * It matches pairs of lines like
653 * / ** <Unicode 2-letter General_Category value> comment... * /
654 * U_<[A-Z_]+> = <integer>,
657 /** Non-category for unassigned and non-character code points. @stable ICU 2.0 */
659 /** Cn "Other, Not Assigned (no characters in [UnicodeData.txt] have this property)" (same as U_UNASSIGNED!) @stable ICU 2.0 */
660 U_GENERAL_OTHER_TYPES = 0,
661 /** Lu @stable ICU 2.0 */
662 U_UPPERCASE_LETTER = 1,
663 /** Ll @stable ICU 2.0 */
664 U_LOWERCASE_LETTER = 2,
665 /** Lt @stable ICU 2.0 */
666 U_TITLECASE_LETTER = 3,
667 /** Lm @stable ICU 2.0 */
668 U_MODIFIER_LETTER = 4,
669 /** Lo @stable ICU 2.0 */
671 /** Mn @stable ICU 2.0 */
672 U_NON_SPACING_MARK = 6,
673 /** Me @stable ICU 2.0 */
674 U_ENCLOSING_MARK = 7,
675 /** Mc @stable ICU 2.0 */
676 U_COMBINING_SPACING_MARK = 8,
677 /** Nd @stable ICU 2.0 */
678 U_DECIMAL_DIGIT_NUMBER = 9,
679 /** Nl @stable ICU 2.0 */
680 U_LETTER_NUMBER = 10,
681 /** No @stable ICU 2.0 */
683 /** Zs @stable ICU 2.0 */
684 U_SPACE_SEPARATOR = 12,
685 /** Zl @stable ICU 2.0 */
686 U_LINE_SEPARATOR = 13,
687 /** Zp @stable ICU 2.0 */
688 U_PARAGRAPH_SEPARATOR = 14,
689 /** Cc @stable ICU 2.0 */
691 /** Cf @stable ICU 2.0 */
693 /** Co @stable ICU 2.0 */
694 U_PRIVATE_USE_CHAR = 17,
695 /** Cs @stable ICU 2.0 */
697 /** Pd @stable ICU 2.0 */
698 U_DASH_PUNCTUATION = 19,
699 /** Ps @stable ICU 2.0 */
700 U_START_PUNCTUATION = 20,
701 /** Pe @stable ICU 2.0 */
702 U_END_PUNCTUATION = 21,
703 /** Pc @stable ICU 2.0 */
704 U_CONNECTOR_PUNCTUATION = 22,
705 /** Po @stable ICU 2.0 */
706 U_OTHER_PUNCTUATION = 23,
707 /** Sm @stable ICU 2.0 */
709 /** Sc @stable ICU 2.0 */
710 U_CURRENCY_SYMBOL = 25,
711 /** Sk @stable ICU 2.0 */
712 U_MODIFIER_SYMBOL = 26,
713 /** So @stable ICU 2.0 */
715 /** Pi @stable ICU 2.0 */
716 U_INITIAL_PUNCTUATION = 28,
717 /** Pf @stable ICU 2.0 */
718 U_FINAL_PUNCTUATION = 29,
720 * One higher than the last enum UCharCategory constant.
721 * This numeric value is stable (will not change), see
722 * http://www.unicode.org/policies/stability_policy.html#Property_Value
726 U_CHAR_CATEGORY_COUNT
730 * U_GC_XX_MASK constants are bit flags corresponding to Unicode
731 * general category values.
732 * For each category, the nth bit is set if the numeric value of the
733 * corresponding UCharCategory constant is n.
735 * There are also some U_GC_Y_MASK constants for groups of general categories
736 * like L for all letter categories.
743 #define U_GC_CN_MASK U_MASK(U_GENERAL_OTHER_TYPES)
745 /** Mask constant for a UCharCategory. @stable ICU 2.1 */
746 #define U_GC_LU_MASK U_MASK(U_UPPERCASE_LETTER)
747 /** Mask constant for a UCharCategory. @stable ICU 2.1 */
748 #define U_GC_LL_MASK U_MASK(U_LOWERCASE_LETTER)
749 /** Mask constant for a UCharCategory. @stable ICU 2.1 */
750 #define U_GC_LT_MASK U_MASK(U_TITLECASE_LETTER)
751 /** Mask constant for a UCharCategory. @stable ICU 2.1 */
752 #define U_GC_LM_MASK U_MASK(U_MODIFIER_LETTER)
753 /** Mask constant for a UCharCategory. @stable ICU 2.1 */
754 #define U_GC_LO_MASK U_MASK(U_OTHER_LETTER)
756 /** Mask constant for a UCharCategory. @stable ICU 2.1 */
757 #define U_GC_MN_MASK U_MASK(U_NON_SPACING_MARK)
758 /** Mask constant for a UCharCategory. @stable ICU 2.1 */
759 #define U_GC_ME_MASK U_MASK(U_ENCLOSING_MARK)
760 /** Mask constant for a UCharCategory. @stable ICU 2.1 */
761 #define U_GC_MC_MASK U_MASK(U_COMBINING_SPACING_MARK)
763 /** Mask constant for a UCharCategory. @stable ICU 2.1 */
764 #define U_GC_ND_MASK U_MASK(U_DECIMAL_DIGIT_NUMBER)
765 /** Mask constant for a UCharCategory. @stable ICU 2.1 */
766 #define U_GC_NL_MASK U_MASK(U_LETTER_NUMBER)
767 /** Mask constant for a UCharCategory. @stable ICU 2.1 */
768 #define U_GC_NO_MASK U_MASK(U_OTHER_NUMBER)
770 /** Mask constant for a UCharCategory. @stable ICU 2.1 */
771 #define U_GC_ZS_MASK U_MASK(U_SPACE_SEPARATOR)
772 /** Mask constant for a UCharCategory. @stable ICU 2.1 */
773 #define U_GC_ZL_MASK U_MASK(U_LINE_SEPARATOR)
774 /** Mask constant for a UCharCategory. @stable ICU 2.1 */
775 #define U_GC_ZP_MASK U_MASK(U_PARAGRAPH_SEPARATOR)
777 /** Mask constant for a UCharCategory. @stable ICU 2.1 */
778 #define U_GC_CC_MASK U_MASK(U_CONTROL_CHAR)
779 /** Mask constant for a UCharCategory. @stable ICU 2.1 */
780 #define U_GC_CF_MASK U_MASK(U_FORMAT_CHAR)
781 /** Mask constant for a UCharCategory. @stable ICU 2.1 */
782 #define U_GC_CO_MASK U_MASK(U_PRIVATE_USE_CHAR)
783 /** Mask constant for a UCharCategory. @stable ICU 2.1 */
784 #define U_GC_CS_MASK U_MASK(U_SURROGATE)
786 /** Mask constant for a UCharCategory. @stable ICU 2.1 */
787 #define U_GC_PD_MASK U_MASK(U_DASH_PUNCTUATION)
788 /** Mask constant for a UCharCategory. @stable ICU 2.1 */
789 #define U_GC_PS_MASK U_MASK(U_START_PUNCTUATION)
790 /** Mask constant for a UCharCategory. @stable ICU 2.1 */
791 #define U_GC_PE_MASK U_MASK(U_END_PUNCTUATION)
792 /** Mask constant for a UCharCategory. @stable ICU 2.1 */
793 #define U_GC_PC_MASK U_MASK(U_CONNECTOR_PUNCTUATION)
794 /** Mask constant for a UCharCategory. @stable ICU 2.1 */
795 #define U_GC_PO_MASK U_MASK(U_OTHER_PUNCTUATION)
797 /** Mask constant for a UCharCategory. @stable ICU 2.1 */
798 #define U_GC_SM_MASK U_MASK(U_MATH_SYMBOL)
799 /** Mask constant for a UCharCategory. @stable ICU 2.1 */
800 #define U_GC_SC_MASK U_MASK(U_CURRENCY_SYMBOL)
801 /** Mask constant for a UCharCategory. @stable ICU 2.1 */
802 #define U_GC_SK_MASK U_MASK(U_MODIFIER_SYMBOL)
803 /** Mask constant for a UCharCategory. @stable ICU 2.1 */
804 #define U_GC_SO_MASK U_MASK(U_OTHER_SYMBOL)
806 /** Mask constant for a UCharCategory. @stable ICU 2.1 */
807 #define U_GC_PI_MASK U_MASK(U_INITIAL_PUNCTUATION)
808 /** Mask constant for a UCharCategory. @stable ICU 2.1 */
809 #define U_GC_PF_MASK U_MASK(U_FINAL_PUNCTUATION)
812 /** Mask constant for multiple UCharCategory bits (L Letters). @stable ICU 2.1 */
813 #define U_GC_L_MASK \
814 (U_GC_LU_MASK|U_GC_LL_MASK|U_GC_LT_MASK|U_GC_LM_MASK|U_GC_LO_MASK)
816 /** Mask constant for multiple UCharCategory bits (LC Cased Letters). @stable ICU 2.1 */
817 #define U_GC_LC_MASK \
818 (U_GC_LU_MASK|U_GC_LL_MASK|U_GC_LT_MASK)
820 /** Mask constant for multiple UCharCategory bits (M Marks). @stable ICU 2.1 */
821 #define U_GC_M_MASK (U_GC_MN_MASK|U_GC_ME_MASK|U_GC_MC_MASK)
823 /** Mask constant for multiple UCharCategory bits (N Numbers). @stable ICU 2.1 */
824 #define U_GC_N_MASK (U_GC_ND_MASK|U_GC_NL_MASK|U_GC_NO_MASK)
826 /** Mask constant for multiple UCharCategory bits (Z Separators). @stable ICU 2.1 */
827 #define U_GC_Z_MASK (U_GC_ZS_MASK|U_GC_ZL_MASK|U_GC_ZP_MASK)
829 /** Mask constant for multiple UCharCategory bits (C Others). @stable ICU 2.1 */
830 #define U_GC_C_MASK \
831 (U_GC_CN_MASK|U_GC_CC_MASK|U_GC_CF_MASK|U_GC_CO_MASK|U_GC_CS_MASK)
833 /** Mask constant for multiple UCharCategory bits (P Punctuation). @stable ICU 2.1 */
834 #define U_GC_P_MASK \
835 (U_GC_PD_MASK|U_GC_PS_MASK|U_GC_PE_MASK|U_GC_PC_MASK|U_GC_PO_MASK| \
836 U_GC_PI_MASK|U_GC_PF_MASK)
838 /** Mask constant for multiple UCharCategory bits (S Symbols). @stable ICU 2.1 */
839 #define U_GC_S_MASK (U_GC_SM_MASK|U_GC_SC_MASK|U_GC_SK_MASK|U_GC_SO_MASK)
842 * This specifies the language directional property of a character set.
845 typedef enum UCharDirection {
847 * Note: UCharDirection constants and their API comments are parsed by preparseucd.py.
848 * It matches pairs of lines like
849 * / ** <Unicode 1..3-letter Bidi_Class value> comment... * /
850 * U_<[A-Z_]+> = <integer>,
853 /** L @stable ICU 2.0 */
855 /** R @stable ICU 2.0 */
857 /** EN @stable ICU 2.0 */
858 U_EUROPEAN_NUMBER = 2,
859 /** ES @stable ICU 2.0 */
860 U_EUROPEAN_NUMBER_SEPARATOR = 3,
861 /** ET @stable ICU 2.0 */
862 U_EUROPEAN_NUMBER_TERMINATOR = 4,
863 /** AN @stable ICU 2.0 */
865 /** CS @stable ICU 2.0 */
866 U_COMMON_NUMBER_SEPARATOR = 6,
867 /** B @stable ICU 2.0 */
868 U_BLOCK_SEPARATOR = 7,
869 /** S @stable ICU 2.0 */
870 U_SEGMENT_SEPARATOR = 8,
871 /** WS @stable ICU 2.0 */
872 U_WHITE_SPACE_NEUTRAL = 9,
873 /** ON @stable ICU 2.0 */
874 U_OTHER_NEUTRAL = 10,
875 /** LRE @stable ICU 2.0 */
876 U_LEFT_TO_RIGHT_EMBEDDING = 11,
877 /** LRO @stable ICU 2.0 */
878 U_LEFT_TO_RIGHT_OVERRIDE = 12,
879 /** AL @stable ICU 2.0 */
880 U_RIGHT_TO_LEFT_ARABIC = 13,
881 /** RLE @stable ICU 2.0 */
882 U_RIGHT_TO_LEFT_EMBEDDING = 14,
883 /** RLO @stable ICU 2.0 */
884 U_RIGHT_TO_LEFT_OVERRIDE = 15,
885 /** PDF @stable ICU 2.0 */
886 U_POP_DIRECTIONAL_FORMAT = 16,
887 /** NSM @stable ICU 2.0 */
888 U_DIR_NON_SPACING_MARK = 17,
889 /** BN @stable ICU 2.0 */
890 U_BOUNDARY_NEUTRAL = 18,
891 /** FSI @stable ICU 52 */
892 U_FIRST_STRONG_ISOLATE = 19,
893 /** LRI @stable ICU 52 */
894 U_LEFT_TO_RIGHT_ISOLATE = 20,
895 /** RLI @stable ICU 52 */
896 U_RIGHT_TO_LEFT_ISOLATE = 21,
897 /** PDI @stable ICU 52 */
898 U_POP_DIRECTIONAL_ISOLATE = 22,
899 #ifndef U_HIDE_DEPRECATED_API
901 * One more than the highest UCharDirection value.
902 * The highest value is available via u_getIntPropertyMaxValue(UCHAR_BIDI_CLASS).
904 * @deprecated ICU 58 The numeric value may change over time, see ICU ticket #12420.
906 U_CHAR_DIRECTION_COUNT
907 #endif // U_HIDE_DEPRECATED_API
911 * Bidi Paired Bracket Type constants.
913 * @see UCHAR_BIDI_PAIRED_BRACKET_TYPE
916 typedef enum UBidiPairedBracketType {
918 * Note: UBidiPairedBracketType constants are parsed by preparseucd.py.
919 * It matches lines like
920 * U_BPT_<Unicode Bidi_Paired_Bracket_Type value name>
923 /** Not a paired bracket. @stable ICU 52 */
925 /** Open paired bracket. @stable ICU 52 */
927 /** Close paired bracket. @stable ICU 52 */
929 #ifndef U_HIDE_DEPRECATED_API
931 * One more than the highest normal UBidiPairedBracketType value.
932 * The highest value is available via u_getIntPropertyMaxValue(UCHAR_BIDI_PAIRED_BRACKET_TYPE).
934 * @deprecated ICU 58 The numeric value may change over time, see ICU ticket #12420.
937 #endif // U_HIDE_DEPRECATED_API
938 } UBidiPairedBracketType;
941 * Constants for Unicode blocks, see the Unicode Data file Blocks.txt
946 * Note: UBlockCode constants are parsed by preparseucd.py.
947 * It matches lines like
948 * UBLOCK_<Unicode Block value name> = <integer>,
951 /** New No_Block value in Unicode 4. @stable ICU 2.6 */
952 UBLOCK_NO_BLOCK = 0, /*[none]*/ /* Special range indicating No_Block */
954 /** @stable ICU 2.0 */
955 UBLOCK_BASIC_LATIN = 1, /*[0000]*/
957 /** @stable ICU 2.0 */
958 UBLOCK_LATIN_1_SUPPLEMENT=2, /*[0080]*/
960 /** @stable ICU 2.0 */
961 UBLOCK_LATIN_EXTENDED_A =3, /*[0100]*/
963 /** @stable ICU 2.0 */
964 UBLOCK_LATIN_EXTENDED_B =4, /*[0180]*/
966 /** @stable ICU 2.0 */
967 UBLOCK_IPA_EXTENSIONS =5, /*[0250]*/
969 /** @stable ICU 2.0 */
970 UBLOCK_SPACING_MODIFIER_LETTERS =6, /*[02B0]*/
972 /** @stable ICU 2.0 */
973 UBLOCK_COMBINING_DIACRITICAL_MARKS =7, /*[0300]*/
976 * Unicode 3.2 renames this block to "Greek and Coptic".
979 UBLOCK_GREEK =8, /*[0370]*/
981 /** @stable ICU 2.0 */
982 UBLOCK_CYRILLIC =9, /*[0400]*/
984 /** @stable ICU 2.0 */
985 UBLOCK_ARMENIAN =10, /*[0530]*/
987 /** @stable ICU 2.0 */
988 UBLOCK_HEBREW =11, /*[0590]*/
990 /** @stable ICU 2.0 */
991 UBLOCK_ARABIC =12, /*[0600]*/
993 /** @stable ICU 2.0 */
994 UBLOCK_SYRIAC =13, /*[0700]*/
996 /** @stable ICU 2.0 */
997 UBLOCK_THAANA =14, /*[0780]*/
999 /** @stable ICU 2.0 */
1000 UBLOCK_DEVANAGARI =15, /*[0900]*/
1002 /** @stable ICU 2.0 */
1003 UBLOCK_BENGALI =16, /*[0980]*/
1005 /** @stable ICU 2.0 */
1006 UBLOCK_GURMUKHI =17, /*[0A00]*/
1008 /** @stable ICU 2.0 */
1009 UBLOCK_GUJARATI =18, /*[0A80]*/
1011 /** @stable ICU 2.0 */
1012 UBLOCK_ORIYA =19, /*[0B00]*/
1014 /** @stable ICU 2.0 */
1015 UBLOCK_TAMIL =20, /*[0B80]*/
1017 /** @stable ICU 2.0 */
1018 UBLOCK_TELUGU =21, /*[0C00]*/
1020 /** @stable ICU 2.0 */
1021 UBLOCK_KANNADA =22, /*[0C80]*/
1023 /** @stable ICU 2.0 */
1024 UBLOCK_MALAYALAM =23, /*[0D00]*/
1026 /** @stable ICU 2.0 */
1027 UBLOCK_SINHALA =24, /*[0D80]*/
1029 /** @stable ICU 2.0 */
1030 UBLOCK_THAI =25, /*[0E00]*/
1032 /** @stable ICU 2.0 */
1033 UBLOCK_LAO =26, /*[0E80]*/
1035 /** @stable ICU 2.0 */
1036 UBLOCK_TIBETAN =27, /*[0F00]*/
1038 /** @stable ICU 2.0 */
1039 UBLOCK_MYANMAR =28, /*[1000]*/
1041 /** @stable ICU 2.0 */
1042 UBLOCK_GEORGIAN =29, /*[10A0]*/
1044 /** @stable ICU 2.0 */
1045 UBLOCK_HANGUL_JAMO =30, /*[1100]*/
1047 /** @stable ICU 2.0 */
1048 UBLOCK_ETHIOPIC =31, /*[1200]*/
1050 /** @stable ICU 2.0 */
1051 UBLOCK_CHEROKEE =32, /*[13A0]*/
1053 /** @stable ICU 2.0 */
1054 UBLOCK_UNIFIED_CANADIAN_ABORIGINAL_SYLLABICS =33, /*[1400]*/
1056 /** @stable ICU 2.0 */
1057 UBLOCK_OGHAM =34, /*[1680]*/
1059 /** @stable ICU 2.0 */
1060 UBLOCK_RUNIC =35, /*[16A0]*/
1062 /** @stable ICU 2.0 */
1063 UBLOCK_KHMER =36, /*[1780]*/
1065 /** @stable ICU 2.0 */
1066 UBLOCK_MONGOLIAN =37, /*[1800]*/
1068 /** @stable ICU 2.0 */
1069 UBLOCK_LATIN_EXTENDED_ADDITIONAL =38, /*[1E00]*/
1071 /** @stable ICU 2.0 */
1072 UBLOCK_GREEK_EXTENDED =39, /*[1F00]*/
1074 /** @stable ICU 2.0 */
1075 UBLOCK_GENERAL_PUNCTUATION =40, /*[2000]*/
1077 /** @stable ICU 2.0 */
1078 UBLOCK_SUPERSCRIPTS_AND_SUBSCRIPTS =41, /*[2070]*/
1080 /** @stable ICU 2.0 */
1081 UBLOCK_CURRENCY_SYMBOLS =42, /*[20A0]*/
1084 * Unicode 3.2 renames this block to "Combining Diacritical Marks for Symbols".
1087 UBLOCK_COMBINING_MARKS_FOR_SYMBOLS =43, /*[20D0]*/
1089 /** @stable ICU 2.0 */
1090 UBLOCK_LETTERLIKE_SYMBOLS =44, /*[2100]*/
1092 /** @stable ICU 2.0 */
1093 UBLOCK_NUMBER_FORMS =45, /*[2150]*/
1095 /** @stable ICU 2.0 */
1096 UBLOCK_ARROWS =46, /*[2190]*/
1098 /** @stable ICU 2.0 */
1099 UBLOCK_MATHEMATICAL_OPERATORS =47, /*[2200]*/
1101 /** @stable ICU 2.0 */
1102 UBLOCK_MISCELLANEOUS_TECHNICAL =48, /*[2300]*/
1104 /** @stable ICU 2.0 */
1105 UBLOCK_CONTROL_PICTURES =49, /*[2400]*/
1107 /** @stable ICU 2.0 */
1108 UBLOCK_OPTICAL_CHARACTER_RECOGNITION =50, /*[2440]*/
1110 /** @stable ICU 2.0 */
1111 UBLOCK_ENCLOSED_ALPHANUMERICS =51, /*[2460]*/
1113 /** @stable ICU 2.0 */
1114 UBLOCK_BOX_DRAWING =52, /*[2500]*/
1116 /** @stable ICU 2.0 */
1117 UBLOCK_BLOCK_ELEMENTS =53, /*[2580]*/
1119 /** @stable ICU 2.0 */
1120 UBLOCK_GEOMETRIC_SHAPES =54, /*[25A0]*/
1122 /** @stable ICU 2.0 */
1123 UBLOCK_MISCELLANEOUS_SYMBOLS =55, /*[2600]*/
1125 /** @stable ICU 2.0 */
1126 UBLOCK_DINGBATS =56, /*[2700]*/
1128 /** @stable ICU 2.0 */
1129 UBLOCK_BRAILLE_PATTERNS =57, /*[2800]*/
1131 /** @stable ICU 2.0 */
1132 UBLOCK_CJK_RADICALS_SUPPLEMENT =58, /*[2E80]*/
1134 /** @stable ICU 2.0 */
1135 UBLOCK_KANGXI_RADICALS =59, /*[2F00]*/
1137 /** @stable ICU 2.0 */
1138 UBLOCK_IDEOGRAPHIC_DESCRIPTION_CHARACTERS =60, /*[2FF0]*/
1140 /** @stable ICU 2.0 */
1141 UBLOCK_CJK_SYMBOLS_AND_PUNCTUATION =61, /*[3000]*/
1143 /** @stable ICU 2.0 */
1144 UBLOCK_HIRAGANA =62, /*[3040]*/
1146 /** @stable ICU 2.0 */
1147 UBLOCK_KATAKANA =63, /*[30A0]*/
1149 /** @stable ICU 2.0 */
1150 UBLOCK_BOPOMOFO =64, /*[3100]*/
1152 /** @stable ICU 2.0 */
1153 UBLOCK_HANGUL_COMPATIBILITY_JAMO =65, /*[3130]*/
1155 /** @stable ICU 2.0 */
1156 UBLOCK_KANBUN =66, /*[3190]*/
1158 /** @stable ICU 2.0 */
1159 UBLOCK_BOPOMOFO_EXTENDED =67, /*[31A0]*/
1161 /** @stable ICU 2.0 */
1162 UBLOCK_ENCLOSED_CJK_LETTERS_AND_MONTHS =68, /*[3200]*/
1164 /** @stable ICU 2.0 */
1165 UBLOCK_CJK_COMPATIBILITY =69, /*[3300]*/
1167 /** @stable ICU 2.0 */
1168 UBLOCK_CJK_UNIFIED_IDEOGRAPHS_EXTENSION_A =70, /*[3400]*/
1170 /** @stable ICU 2.0 */
1171 UBLOCK_CJK_UNIFIED_IDEOGRAPHS =71, /*[4E00]*/
1173 /** @stable ICU 2.0 */
1174 UBLOCK_YI_SYLLABLES =72, /*[A000]*/
1176 /** @stable ICU 2.0 */
1177 UBLOCK_YI_RADICALS =73, /*[A490]*/
1179 /** @stable ICU 2.0 */
1180 UBLOCK_HANGUL_SYLLABLES =74, /*[AC00]*/
1182 /** @stable ICU 2.0 */
1183 UBLOCK_HIGH_SURROGATES =75, /*[D800]*/
1185 /** @stable ICU 2.0 */
1186 UBLOCK_HIGH_PRIVATE_USE_SURROGATES =76, /*[DB80]*/
1188 /** @stable ICU 2.0 */
1189 UBLOCK_LOW_SURROGATES =77, /*[DC00]*/
1192 * Same as UBLOCK_PRIVATE_USE.
1193 * Until Unicode 3.1.1, the corresponding block name was "Private Use",
1194 * and multiple code point ranges had this block.
1195 * Unicode 3.2 renames the block for the BMP PUA to "Private Use Area" and
1196 * adds separate blocks for the supplementary PUAs.
1200 UBLOCK_PRIVATE_USE_AREA =78, /*[E000]*/
1202 * Same as UBLOCK_PRIVATE_USE_AREA.
1203 * Until Unicode 3.1.1, the corresponding block name was "Private Use",
1204 * and multiple code point ranges had this block.
1205 * Unicode 3.2 renames the block for the BMP PUA to "Private Use Area" and
1206 * adds separate blocks for the supplementary PUAs.
1210 UBLOCK_PRIVATE_USE = UBLOCK_PRIVATE_USE_AREA,
1212 /** @stable ICU 2.0 */
1213 UBLOCK_CJK_COMPATIBILITY_IDEOGRAPHS =79, /*[F900]*/
1215 /** @stable ICU 2.0 */
1216 UBLOCK_ALPHABETIC_PRESENTATION_FORMS =80, /*[FB00]*/
1218 /** @stable ICU 2.0 */
1219 UBLOCK_ARABIC_PRESENTATION_FORMS_A =81, /*[FB50]*/
1221 /** @stable ICU 2.0 */
1222 UBLOCK_COMBINING_HALF_MARKS =82, /*[FE20]*/
1224 /** @stable ICU 2.0 */
1225 UBLOCK_CJK_COMPATIBILITY_FORMS =83, /*[FE30]*/
1227 /** @stable ICU 2.0 */
1228 UBLOCK_SMALL_FORM_VARIANTS =84, /*[FE50]*/
1230 /** @stable ICU 2.0 */
1231 UBLOCK_ARABIC_PRESENTATION_FORMS_B =85, /*[FE70]*/
1233 /** @stable ICU 2.0 */
1234 UBLOCK_SPECIALS =86, /*[FFF0]*/
1236 /** @stable ICU 2.0 */
1237 UBLOCK_HALFWIDTH_AND_FULLWIDTH_FORMS =87, /*[FF00]*/
1239 /* New blocks in Unicode 3.1 */
1241 /** @stable ICU 2.0 */
1242 UBLOCK_OLD_ITALIC = 88, /*[10300]*/
1243 /** @stable ICU 2.0 */
1244 UBLOCK_GOTHIC = 89, /*[10330]*/
1245 /** @stable ICU 2.0 */
1246 UBLOCK_DESERET = 90, /*[10400]*/
1247 /** @stable ICU 2.0 */
1248 UBLOCK_BYZANTINE_MUSICAL_SYMBOLS = 91, /*[1D000]*/
1249 /** @stable ICU 2.0 */
1250 UBLOCK_MUSICAL_SYMBOLS = 92, /*[1D100]*/
1251 /** @stable ICU 2.0 */
1252 UBLOCK_MATHEMATICAL_ALPHANUMERIC_SYMBOLS = 93, /*[1D400]*/
1253 /** @stable ICU 2.0 */
1254 UBLOCK_CJK_UNIFIED_IDEOGRAPHS_EXTENSION_B = 94, /*[20000]*/
1255 /** @stable ICU 2.0 */
1256 UBLOCK_CJK_COMPATIBILITY_IDEOGRAPHS_SUPPLEMENT = 95, /*[2F800]*/
1257 /** @stable ICU 2.0 */
1258 UBLOCK_TAGS = 96, /*[E0000]*/
1260 /* New blocks in Unicode 3.2 */
1262 /** @stable ICU 3.0 */
1263 UBLOCK_CYRILLIC_SUPPLEMENT = 97, /*[0500]*/
1265 * Unicode 4.0.1 renames the "Cyrillic Supplementary" block to "Cyrillic Supplement".
1268 UBLOCK_CYRILLIC_SUPPLEMENTARY = UBLOCK_CYRILLIC_SUPPLEMENT,
1269 /** @stable ICU 2.2 */
1270 UBLOCK_TAGALOG = 98, /*[1700]*/
1271 /** @stable ICU 2.2 */
1272 UBLOCK_HANUNOO = 99, /*[1720]*/
1273 /** @stable ICU 2.2 */
1274 UBLOCK_BUHID = 100, /*[1740]*/
1275 /** @stable ICU 2.2 */
1276 UBLOCK_TAGBANWA = 101, /*[1760]*/
1277 /** @stable ICU 2.2 */
1278 UBLOCK_MISCELLANEOUS_MATHEMATICAL_SYMBOLS_A = 102, /*[27C0]*/
1279 /** @stable ICU 2.2 */
1280 UBLOCK_SUPPLEMENTAL_ARROWS_A = 103, /*[27F0]*/
1281 /** @stable ICU 2.2 */
1282 UBLOCK_SUPPLEMENTAL_ARROWS_B = 104, /*[2900]*/
1283 /** @stable ICU 2.2 */
1284 UBLOCK_MISCELLANEOUS_MATHEMATICAL_SYMBOLS_B = 105, /*[2980]*/
1285 /** @stable ICU 2.2 */
1286 UBLOCK_SUPPLEMENTAL_MATHEMATICAL_OPERATORS = 106, /*[2A00]*/
1287 /** @stable ICU 2.2 */
1288 UBLOCK_KATAKANA_PHONETIC_EXTENSIONS = 107, /*[31F0]*/
1289 /** @stable ICU 2.2 */
1290 UBLOCK_VARIATION_SELECTORS = 108, /*[FE00]*/
1291 /** @stable ICU 2.2 */
1292 UBLOCK_SUPPLEMENTARY_PRIVATE_USE_AREA_A = 109, /*[F0000]*/
1293 /** @stable ICU 2.2 */
1294 UBLOCK_SUPPLEMENTARY_PRIVATE_USE_AREA_B = 110, /*[100000]*/
1296 /* New blocks in Unicode 4 */
1298 /** @stable ICU 2.6 */
1299 UBLOCK_LIMBU = 111, /*[1900]*/
1300 /** @stable ICU 2.6 */
1301 UBLOCK_TAI_LE = 112, /*[1950]*/
1302 /** @stable ICU 2.6 */
1303 UBLOCK_KHMER_SYMBOLS = 113, /*[19E0]*/
1304 /** @stable ICU 2.6 */
1305 UBLOCK_PHONETIC_EXTENSIONS = 114, /*[1D00]*/
1306 /** @stable ICU 2.6 */
1307 UBLOCK_MISCELLANEOUS_SYMBOLS_AND_ARROWS = 115, /*[2B00]*/
1308 /** @stable ICU 2.6 */
1309 UBLOCK_YIJING_HEXAGRAM_SYMBOLS = 116, /*[4DC0]*/
1310 /** @stable ICU 2.6 */
1311 UBLOCK_LINEAR_B_SYLLABARY = 117, /*[10000]*/
1312 /** @stable ICU 2.6 */
1313 UBLOCK_LINEAR_B_IDEOGRAMS = 118, /*[10080]*/
1314 /** @stable ICU 2.6 */
1315 UBLOCK_AEGEAN_NUMBERS = 119, /*[10100]*/
1316 /** @stable ICU 2.6 */
1317 UBLOCK_UGARITIC = 120, /*[10380]*/
1318 /** @stable ICU 2.6 */
1319 UBLOCK_SHAVIAN = 121, /*[10450]*/
1320 /** @stable ICU 2.6 */
1321 UBLOCK_OSMANYA = 122, /*[10480]*/
1322 /** @stable ICU 2.6 */
1323 UBLOCK_CYPRIOT_SYLLABARY = 123, /*[10800]*/
1324 /** @stable ICU 2.6 */
1325 UBLOCK_TAI_XUAN_JING_SYMBOLS = 124, /*[1D300]*/
1326 /** @stable ICU 2.6 */
1327 UBLOCK_VARIATION_SELECTORS_SUPPLEMENT = 125, /*[E0100]*/
1329 /* New blocks in Unicode 4.1 */
1331 /** @stable ICU 3.4 */
1332 UBLOCK_ANCIENT_GREEK_MUSICAL_NOTATION = 126, /*[1D200]*/
1333 /** @stable ICU 3.4 */
1334 UBLOCK_ANCIENT_GREEK_NUMBERS = 127, /*[10140]*/
1335 /** @stable ICU 3.4 */
1336 UBLOCK_ARABIC_SUPPLEMENT = 128, /*[0750]*/
1337 /** @stable ICU 3.4 */
1338 UBLOCK_BUGINESE = 129, /*[1A00]*/
1339 /** @stable ICU 3.4 */
1340 UBLOCK_CJK_STROKES = 130, /*[31C0]*/
1341 /** @stable ICU 3.4 */
1342 UBLOCK_COMBINING_DIACRITICAL_MARKS_SUPPLEMENT = 131, /*[1DC0]*/
1343 /** @stable ICU 3.4 */
1344 UBLOCK_COPTIC = 132, /*[2C80]*/
1345 /** @stable ICU 3.4 */
1346 UBLOCK_ETHIOPIC_EXTENDED = 133, /*[2D80]*/
1347 /** @stable ICU 3.4 */
1348 UBLOCK_ETHIOPIC_SUPPLEMENT = 134, /*[1380]*/
1349 /** @stable ICU 3.4 */
1350 UBLOCK_GEORGIAN_SUPPLEMENT = 135, /*[2D00]*/
1351 /** @stable ICU 3.4 */
1352 UBLOCK_GLAGOLITIC = 136, /*[2C00]*/
1353 /** @stable ICU 3.4 */
1354 UBLOCK_KHAROSHTHI = 137, /*[10A00]*/
1355 /** @stable ICU 3.4 */
1356 UBLOCK_MODIFIER_TONE_LETTERS = 138, /*[A700]*/
1357 /** @stable ICU 3.4 */
1358 UBLOCK_NEW_TAI_LUE = 139, /*[1980]*/
1359 /** @stable ICU 3.4 */
1360 UBLOCK_OLD_PERSIAN = 140, /*[103A0]*/
1361 /** @stable ICU 3.4 */
1362 UBLOCK_PHONETIC_EXTENSIONS_SUPPLEMENT = 141, /*[1D80]*/
1363 /** @stable ICU 3.4 */
1364 UBLOCK_SUPPLEMENTAL_PUNCTUATION = 142, /*[2E00]*/
1365 /** @stable ICU 3.4 */
1366 UBLOCK_SYLOTI_NAGRI = 143, /*[A800]*/
1367 /** @stable ICU 3.4 */
1368 UBLOCK_TIFINAGH = 144, /*[2D30]*/
1369 /** @stable ICU 3.4 */
1370 UBLOCK_VERTICAL_FORMS = 145, /*[FE10]*/
1372 /* New blocks in Unicode 5.0 */
1374 /** @stable ICU 3.6 */
1375 UBLOCK_NKO = 146, /*[07C0]*/
1376 /** @stable ICU 3.6 */
1377 UBLOCK_BALINESE = 147, /*[1B00]*/
1378 /** @stable ICU 3.6 */
1379 UBLOCK_LATIN_EXTENDED_C = 148, /*[2C60]*/
1380 /** @stable ICU 3.6 */
1381 UBLOCK_LATIN_EXTENDED_D = 149, /*[A720]*/
1382 /** @stable ICU 3.6 */
1383 UBLOCK_PHAGS_PA = 150, /*[A840]*/
1384 /** @stable ICU 3.6 */
1385 UBLOCK_PHOENICIAN = 151, /*[10900]*/
1386 /** @stable ICU 3.6 */
1387 UBLOCK_CUNEIFORM = 152, /*[12000]*/
1388 /** @stable ICU 3.6 */
1389 UBLOCK_CUNEIFORM_NUMBERS_AND_PUNCTUATION = 153, /*[12400]*/
1390 /** @stable ICU 3.6 */
1391 UBLOCK_COUNTING_ROD_NUMERALS = 154, /*[1D360]*/
1393 /* New blocks in Unicode 5.1 */
1395 /** @stable ICU 4.0 */
1396 UBLOCK_SUNDANESE = 155, /*[1B80]*/
1397 /** @stable ICU 4.0 */
1398 UBLOCK_LEPCHA = 156, /*[1C00]*/
1399 /** @stable ICU 4.0 */
1400 UBLOCK_OL_CHIKI = 157, /*[1C50]*/
1401 /** @stable ICU 4.0 */
1402 UBLOCK_CYRILLIC_EXTENDED_A = 158, /*[2DE0]*/
1403 /** @stable ICU 4.0 */
1404 UBLOCK_VAI = 159, /*[A500]*/
1405 /** @stable ICU 4.0 */
1406 UBLOCK_CYRILLIC_EXTENDED_B = 160, /*[A640]*/
1407 /** @stable ICU 4.0 */
1408 UBLOCK_SAURASHTRA = 161, /*[A880]*/
1409 /** @stable ICU 4.0 */
1410 UBLOCK_KAYAH_LI = 162, /*[A900]*/
1411 /** @stable ICU 4.0 */
1412 UBLOCK_REJANG = 163, /*[A930]*/
1413 /** @stable ICU 4.0 */
1414 UBLOCK_CHAM = 164, /*[AA00]*/
1415 /** @stable ICU 4.0 */
1416 UBLOCK_ANCIENT_SYMBOLS = 165, /*[10190]*/
1417 /** @stable ICU 4.0 */
1418 UBLOCK_PHAISTOS_DISC = 166, /*[101D0]*/
1419 /** @stable ICU 4.0 */
1420 UBLOCK_LYCIAN = 167, /*[10280]*/
1421 /** @stable ICU 4.0 */
1422 UBLOCK_CARIAN = 168, /*[102A0]*/
1423 /** @stable ICU 4.0 */
1424 UBLOCK_LYDIAN = 169, /*[10920]*/
1425 /** @stable ICU 4.0 */
1426 UBLOCK_MAHJONG_TILES = 170, /*[1F000]*/
1427 /** @stable ICU 4.0 */
1428 UBLOCK_DOMINO_TILES = 171, /*[1F030]*/
1430 /* New blocks in Unicode 5.2 */
1432 /** @stable ICU 4.4 */
1433 UBLOCK_SAMARITAN = 172, /*[0800]*/
1434 /** @stable ICU 4.4 */
1435 UBLOCK_UNIFIED_CANADIAN_ABORIGINAL_SYLLABICS_EXTENDED = 173, /*[18B0]*/
1436 /** @stable ICU 4.4 */
1437 UBLOCK_TAI_THAM = 174, /*[1A20]*/
1438 /** @stable ICU 4.4 */
1439 UBLOCK_VEDIC_EXTENSIONS = 175, /*[1CD0]*/
1440 /** @stable ICU 4.4 */
1441 UBLOCK_LISU = 176, /*[A4D0]*/
1442 /** @stable ICU 4.4 */
1443 UBLOCK_BAMUM = 177, /*[A6A0]*/
1444 /** @stable ICU 4.4 */
1445 UBLOCK_COMMON_INDIC_NUMBER_FORMS = 178, /*[A830]*/
1446 /** @stable ICU 4.4 */
1447 UBLOCK_DEVANAGARI_EXTENDED = 179, /*[A8E0]*/
1448 /** @stable ICU 4.4 */
1449 UBLOCK_HANGUL_JAMO_EXTENDED_A = 180, /*[A960]*/
1450 /** @stable ICU 4.4 */
1451 UBLOCK_JAVANESE = 181, /*[A980]*/
1452 /** @stable ICU 4.4 */
1453 UBLOCK_MYANMAR_EXTENDED_A = 182, /*[AA60]*/
1454 /** @stable ICU 4.4 */
1455 UBLOCK_TAI_VIET = 183, /*[AA80]*/
1456 /** @stable ICU 4.4 */
1457 UBLOCK_MEETEI_MAYEK = 184, /*[ABC0]*/
1458 /** @stable ICU 4.4 */
1459 UBLOCK_HANGUL_JAMO_EXTENDED_B = 185, /*[D7B0]*/
1460 /** @stable ICU 4.4 */
1461 UBLOCK_IMPERIAL_ARAMAIC = 186, /*[10840]*/
1462 /** @stable ICU 4.4 */
1463 UBLOCK_OLD_SOUTH_ARABIAN = 187, /*[10A60]*/
1464 /** @stable ICU 4.4 */
1465 UBLOCK_AVESTAN = 188, /*[10B00]*/
1466 /** @stable ICU 4.4 */
1467 UBLOCK_INSCRIPTIONAL_PARTHIAN = 189, /*[10B40]*/
1468 /** @stable ICU 4.4 */
1469 UBLOCK_INSCRIPTIONAL_PAHLAVI = 190, /*[10B60]*/
1470 /** @stable ICU 4.4 */
1471 UBLOCK_OLD_TURKIC = 191, /*[10C00]*/
1472 /** @stable ICU 4.4 */
1473 UBLOCK_RUMI_NUMERAL_SYMBOLS = 192, /*[10E60]*/
1474 /** @stable ICU 4.4 */
1475 UBLOCK_KAITHI = 193, /*[11080]*/
1476 /** @stable ICU 4.4 */
1477 UBLOCK_EGYPTIAN_HIEROGLYPHS = 194, /*[13000]*/
1478 /** @stable ICU 4.4 */
1479 UBLOCK_ENCLOSED_ALPHANUMERIC_SUPPLEMENT = 195, /*[1F100]*/
1480 /** @stable ICU 4.4 */
1481 UBLOCK_ENCLOSED_IDEOGRAPHIC_SUPPLEMENT = 196, /*[1F200]*/
1482 /** @stable ICU 4.4 */
1483 UBLOCK_CJK_UNIFIED_IDEOGRAPHS_EXTENSION_C = 197, /*[2A700]*/
1485 /* New blocks in Unicode 6.0 */
1487 /** @stable ICU 4.6 */
1488 UBLOCK_MANDAIC = 198, /*[0840]*/
1489 /** @stable ICU 4.6 */
1490 UBLOCK_BATAK = 199, /*[1BC0]*/
1491 /** @stable ICU 4.6 */
1492 UBLOCK_ETHIOPIC_EXTENDED_A = 200, /*[AB00]*/
1493 /** @stable ICU 4.6 */
1494 UBLOCK_BRAHMI = 201, /*[11000]*/
1495 /** @stable ICU 4.6 */
1496 UBLOCK_BAMUM_SUPPLEMENT = 202, /*[16800]*/
1497 /** @stable ICU 4.6 */
1498 UBLOCK_KANA_SUPPLEMENT = 203, /*[1B000]*/
1499 /** @stable ICU 4.6 */
1500 UBLOCK_PLAYING_CARDS = 204, /*[1F0A0]*/
1501 /** @stable ICU 4.6 */
1502 UBLOCK_MISCELLANEOUS_SYMBOLS_AND_PICTOGRAPHS = 205, /*[1F300]*/
1503 /** @stable ICU 4.6 */
1504 UBLOCK_EMOTICONS = 206, /*[1F600]*/
1505 /** @stable ICU 4.6 */
1506 UBLOCK_TRANSPORT_AND_MAP_SYMBOLS = 207, /*[1F680]*/
1507 /** @stable ICU 4.6 */
1508 UBLOCK_ALCHEMICAL_SYMBOLS = 208, /*[1F700]*/
1509 /** @stable ICU 4.6 */
1510 UBLOCK_CJK_UNIFIED_IDEOGRAPHS_EXTENSION_D = 209, /*[2B740]*/
1512 /* New blocks in Unicode 6.1 */
1514 /** @stable ICU 49 */
1515 UBLOCK_ARABIC_EXTENDED_A = 210, /*[08A0]*/
1516 /** @stable ICU 49 */
1517 UBLOCK_ARABIC_MATHEMATICAL_ALPHABETIC_SYMBOLS = 211, /*[1EE00]*/
1518 /** @stable ICU 49 */
1519 UBLOCK_CHAKMA = 212, /*[11100]*/
1520 /** @stable ICU 49 */
1521 UBLOCK_MEETEI_MAYEK_EXTENSIONS = 213, /*[AAE0]*/
1522 /** @stable ICU 49 */
1523 UBLOCK_MEROITIC_CURSIVE = 214, /*[109A0]*/
1524 /** @stable ICU 49 */
1525 UBLOCK_MEROITIC_HIEROGLYPHS = 215, /*[10980]*/
1526 /** @stable ICU 49 */
1527 UBLOCK_MIAO = 216, /*[16F00]*/
1528 /** @stable ICU 49 */
1529 UBLOCK_SHARADA = 217, /*[11180]*/
1530 /** @stable ICU 49 */
1531 UBLOCK_SORA_SOMPENG = 218, /*[110D0]*/
1532 /** @stable ICU 49 */
1533 UBLOCK_SUNDANESE_SUPPLEMENT = 219, /*[1CC0]*/
1534 /** @stable ICU 49 */
1535 UBLOCK_TAKRI = 220, /*[11680]*/
1537 /* New blocks in Unicode 7.0 */
1539 /** @stable ICU 54 */
1540 UBLOCK_BASSA_VAH = 221, /*[16AD0]*/
1541 /** @stable ICU 54 */
1542 UBLOCK_CAUCASIAN_ALBANIAN = 222, /*[10530]*/
1543 /** @stable ICU 54 */
1544 UBLOCK_COPTIC_EPACT_NUMBERS = 223, /*[102E0]*/
1545 /** @stable ICU 54 */
1546 UBLOCK_COMBINING_DIACRITICAL_MARKS_EXTENDED = 224, /*[1AB0]*/
1547 /** @stable ICU 54 */
1548 UBLOCK_DUPLOYAN = 225, /*[1BC00]*/
1549 /** @stable ICU 54 */
1550 UBLOCK_ELBASAN = 226, /*[10500]*/
1551 /** @stable ICU 54 */
1552 UBLOCK_GEOMETRIC_SHAPES_EXTENDED = 227, /*[1F780]*/
1553 /** @stable ICU 54 */
1554 UBLOCK_GRANTHA = 228, /*[11300]*/
1555 /** @stable ICU 54 */
1556 UBLOCK_KHOJKI = 229, /*[11200]*/
1557 /** @stable ICU 54 */
1558 UBLOCK_KHUDAWADI = 230, /*[112B0]*/
1559 /** @stable ICU 54 */
1560 UBLOCK_LATIN_EXTENDED_E = 231, /*[AB30]*/
1561 /** @stable ICU 54 */
1562 UBLOCK_LINEAR_A = 232, /*[10600]*/
1563 /** @stable ICU 54 */
1564 UBLOCK_MAHAJANI = 233, /*[11150]*/
1565 /** @stable ICU 54 */
1566 UBLOCK_MANICHAEAN = 234, /*[10AC0]*/
1567 /** @stable ICU 54 */
1568 UBLOCK_MENDE_KIKAKUI = 235, /*[1E800]*/
1569 /** @stable ICU 54 */
1570 UBLOCK_MODI = 236, /*[11600]*/
1571 /** @stable ICU 54 */
1572 UBLOCK_MRO = 237, /*[16A40]*/
1573 /** @stable ICU 54 */
1574 UBLOCK_MYANMAR_EXTENDED_B = 238, /*[A9E0]*/
1575 /** @stable ICU 54 */
1576 UBLOCK_NABATAEAN = 239, /*[10880]*/
1577 /** @stable ICU 54 */
1578 UBLOCK_OLD_NORTH_ARABIAN = 240, /*[10A80]*/
1579 /** @stable ICU 54 */
1580 UBLOCK_OLD_PERMIC = 241, /*[10350]*/
1581 /** @stable ICU 54 */
1582 UBLOCK_ORNAMENTAL_DINGBATS = 242, /*[1F650]*/
1583 /** @stable ICU 54 */
1584 UBLOCK_PAHAWH_HMONG = 243, /*[16B00]*/
1585 /** @stable ICU 54 */
1586 UBLOCK_PALMYRENE = 244, /*[10860]*/
1587 /** @stable ICU 54 */
1588 UBLOCK_PAU_CIN_HAU = 245, /*[11AC0]*/
1589 /** @stable ICU 54 */
1590 UBLOCK_PSALTER_PAHLAVI = 246, /*[10B80]*/
1591 /** @stable ICU 54 */
1592 UBLOCK_SHORTHAND_FORMAT_CONTROLS = 247, /*[1BCA0]*/
1593 /** @stable ICU 54 */
1594 UBLOCK_SIDDHAM = 248, /*[11580]*/
1595 /** @stable ICU 54 */
1596 UBLOCK_SINHALA_ARCHAIC_NUMBERS = 249, /*[111E0]*/
1597 /** @stable ICU 54 */
1598 UBLOCK_SUPPLEMENTAL_ARROWS_C = 250, /*[1F800]*/
1599 /** @stable ICU 54 */
1600 UBLOCK_TIRHUTA = 251, /*[11480]*/
1601 /** @stable ICU 54 */
1602 UBLOCK_WARANG_CITI = 252, /*[118A0]*/
1604 /* New blocks in Unicode 8.0 */
1606 /** @stable ICU 56 */
1607 UBLOCK_AHOM = 253, /*[11700]*/
1608 /** @stable ICU 56 */
1609 UBLOCK_ANATOLIAN_HIEROGLYPHS = 254, /*[14400]*/
1610 /** @stable ICU 56 */
1611 UBLOCK_CHEROKEE_SUPPLEMENT = 255, /*[AB70]*/
1612 /** @stable ICU 56 */
1613 UBLOCK_CJK_UNIFIED_IDEOGRAPHS_EXTENSION_E = 256, /*[2B820]*/
1614 /** @stable ICU 56 */
1615 UBLOCK_EARLY_DYNASTIC_CUNEIFORM = 257, /*[12480]*/
1616 /** @stable ICU 56 */
1617 UBLOCK_HATRAN = 258, /*[108E0]*/
1618 /** @stable ICU 56 */
1619 UBLOCK_MULTANI = 259, /*[11280]*/
1620 /** @stable ICU 56 */
1621 UBLOCK_OLD_HUNGARIAN = 260, /*[10C80]*/
1622 /** @stable ICU 56 */
1623 UBLOCK_SUPPLEMENTAL_SYMBOLS_AND_PICTOGRAPHS = 261, /*[1F900]*/
1624 /** @stable ICU 56 */
1625 UBLOCK_SUTTON_SIGNWRITING = 262, /*[1D800]*/
1627 /* New blocks in Unicode 9.0 */
1629 /** @stable ICU 58 */
1630 UBLOCK_ADLAM = 263, /*[1E900]*/
1631 /** @stable ICU 58 */
1632 UBLOCK_BHAIKSUKI = 264, /*[11C00]*/
1633 /** @stable ICU 58 */
1634 UBLOCK_CYRILLIC_EXTENDED_C = 265, /*[1C80]*/
1635 /** @stable ICU 58 */
1636 UBLOCK_GLAGOLITIC_SUPPLEMENT = 266, /*[1E000]*/
1637 /** @stable ICU 58 */
1638 UBLOCK_IDEOGRAPHIC_SYMBOLS_AND_PUNCTUATION = 267, /*[16FE0]*/
1639 /** @stable ICU 58 */
1640 UBLOCK_MARCHEN = 268, /*[11C70]*/
1641 /** @stable ICU 58 */
1642 UBLOCK_MONGOLIAN_SUPPLEMENT = 269, /*[11660]*/
1643 /** @stable ICU 58 */
1644 UBLOCK_NEWA = 270, /*[11400]*/
1645 /** @stable ICU 58 */
1646 UBLOCK_OSAGE = 271, /*[104B0]*/
1647 /** @stable ICU 58 */
1648 UBLOCK_TANGUT = 272, /*[17000]*/
1649 /** @stable ICU 58 */
1650 UBLOCK_TANGUT_COMPONENTS = 273, /*[18800]*/
1652 #ifndef U_HIDE_DEPRECATED_API
1654 * One more than the highest normal UBlockCode value.
1655 * The highest value is available via u_getIntPropertyMaxValue(UCHAR_BLOCK).
1657 * @deprecated ICU 58 The numeric value may change over time, see ICU ticket #12420.
1660 #endif // U_HIDE_DEPRECATED_API
1662 /** @stable ICU 2.0 */
1663 UBLOCK_INVALID_CODE=-1
1666 /** @stable ICU 2.0 */
1667 typedef enum UBlockCode UBlockCode;
1670 * East Asian Width constants.
1672 * @see UCHAR_EAST_ASIAN_WIDTH
1673 * @see u_getIntPropertyValue
1676 typedef enum UEastAsianWidth {
1678 * Note: UEastAsianWidth constants are parsed by preparseucd.py.
1679 * It matches lines like
1680 * U_EA_<Unicode East_Asian_Width value name>
1683 U_EA_NEUTRAL, /*[N]*/
1684 U_EA_AMBIGUOUS, /*[A]*/
1685 U_EA_HALFWIDTH, /*[H]*/
1686 U_EA_FULLWIDTH, /*[F]*/
1687 U_EA_NARROW, /*[Na]*/
1689 #ifndef U_HIDE_DEPRECATED_API
1691 * One more than the highest normal UEastAsianWidth value.
1692 * The highest value is available via u_getIntPropertyMaxValue(UCHAR_EAST_ASIAN_WIDTH).
1694 * @deprecated ICU 58 The numeric value may change over time, see ICU ticket #12420.
1697 #endif // U_HIDE_DEPRECATED_API
1701 * Selector constants for u_charName().
1702 * u_charName() returns the "modern" name of a
1703 * Unicode character; or the name that was defined in
1704 * Unicode version 1.0, before the Unicode standard merged
1705 * with ISO-10646; or an "extended" name that gives each
1706 * Unicode code point a unique name.
1711 typedef enum UCharNameChoice {
1712 /** Unicode character name (Name property). @stable ICU 2.0 */
1713 U_UNICODE_CHAR_NAME,
1714 #ifndef U_HIDE_DEPRECATED_API
1716 * The Unicode_1_Name property value which is of little practical value.
1717 * Beginning with ICU 49, ICU APIs return an empty string for this name choice.
1718 * @deprecated ICU 49
1720 U_UNICODE_10_CHAR_NAME,
1721 #endif /* U_HIDE_DEPRECATED_API */
1722 /** Standard or synthetic character name. @stable ICU 2.0 */
1723 U_EXTENDED_CHAR_NAME = U_UNICODE_CHAR_NAME+2,
1724 /** Corrected name from NameAliases.txt. @stable ICU 4.4 */
1726 #ifndef U_HIDE_DEPRECATED_API
1728 * One more than the highest normal UCharNameChoice value.
1729 * @deprecated ICU 58 The numeric value may change over time, see ICU ticket #12420.
1731 U_CHAR_NAME_CHOICE_COUNT
1732 #endif // U_HIDE_DEPRECATED_API
1736 * Selector constants for u_getPropertyName() and
1737 * u_getPropertyValueName(). These selectors are used to choose which
1738 * name is returned for a given property or value. All properties and
1739 * values have a long name. Most have a short name, but some do not.
1740 * Unicode allows for additional names, beyond the long and short
1741 * name, which would be indicated by U_LONG_PROPERTY_NAME + i, where
1744 * @see u_getPropertyName()
1745 * @see u_getPropertyValueName()
1748 typedef enum UPropertyNameChoice {
1749 U_SHORT_PROPERTY_NAME,
1750 U_LONG_PROPERTY_NAME,
1751 #ifndef U_HIDE_DEPRECATED_API
1753 * One more than the highest normal UPropertyNameChoice value.
1754 * @deprecated ICU 58 The numeric value may change over time, see ICU ticket #12420.
1756 U_PROPERTY_NAME_CHOICE_COUNT
1757 #endif // U_HIDE_DEPRECATED_API
1758 } UPropertyNameChoice;
1761 * Decomposition Type constants.
1763 * @see UCHAR_DECOMPOSITION_TYPE
1766 typedef enum UDecompositionType {
1768 * Note: UDecompositionType constants are parsed by preparseucd.py.
1769 * It matches lines like
1770 * U_DT_<Unicode Decomposition_Type value name>
1773 U_DT_NONE, /*[none]*/
1774 U_DT_CANONICAL, /*[can]*/
1775 U_DT_COMPAT, /*[com]*/
1776 U_DT_CIRCLE, /*[enc]*/
1777 U_DT_FINAL, /*[fin]*/
1778 U_DT_FONT, /*[font]*/
1779 U_DT_FRACTION, /*[fra]*/
1780 U_DT_INITIAL, /*[init]*/
1781 U_DT_ISOLATED, /*[iso]*/
1782 U_DT_MEDIAL, /*[med]*/
1783 U_DT_NARROW, /*[nar]*/
1784 U_DT_NOBREAK, /*[nb]*/
1785 U_DT_SMALL, /*[sml]*/
1786 U_DT_SQUARE, /*[sqr]*/
1788 U_DT_SUPER, /*[sup]*/
1789 U_DT_VERTICAL, /*[vert]*/
1790 U_DT_WIDE, /*[wide]*/
1791 #ifndef U_HIDE_DEPRECATED_API
1793 * One more than the highest normal UDecompositionType value.
1794 * The highest value is available via u_getIntPropertyMaxValue(UCHAR_DECOMPOSITION_TYPE).
1796 * @deprecated ICU 58 The numeric value may change over time, see ICU ticket #12420.
1799 #endif // U_HIDE_DEPRECATED_API
1800 } UDecompositionType;
1803 * Joining Type constants.
1805 * @see UCHAR_JOINING_TYPE
1808 typedef enum UJoiningType {
1810 * Note: UJoiningType constants are parsed by preparseucd.py.
1811 * It matches lines like
1812 * U_JT_<Unicode Joining_Type value name>
1815 U_JT_NON_JOINING, /*[U]*/
1816 U_JT_JOIN_CAUSING, /*[C]*/
1817 U_JT_DUAL_JOINING, /*[D]*/
1818 U_JT_LEFT_JOINING, /*[L]*/
1819 U_JT_RIGHT_JOINING, /*[R]*/
1820 U_JT_TRANSPARENT, /*[T]*/
1821 #ifndef U_HIDE_DEPRECATED_API
1823 * One more than the highest normal UJoiningType value.
1824 * The highest value is available via u_getIntPropertyMaxValue(UCHAR_JOINING_TYPE).
1826 * @deprecated ICU 58 The numeric value may change over time, see ICU ticket #12420.
1829 #endif // U_HIDE_DEPRECATED_API
1833 * Joining Group constants.
1835 * @see UCHAR_JOINING_GROUP
1838 typedef enum UJoiningGroup {
1840 * Note: UJoiningGroup constants are parsed by preparseucd.py.
1841 * It matches lines like
1842 * U_JG_<Unicode Joining_Group value name>
1845 U_JG_NO_JOINING_GROUP,
1859 U_JG_TEH_MARBUTA_GOAL, /**< @stable ICU 4.6 */
1860 U_JG_HAMZA_ON_HEH_GOAL=U_JG_TEH_MARBUTA_GOAL,
1897 U_JG_FE, /**< @stable ICU 2.6 */
1898 U_JG_KHAPH, /**< @stable ICU 2.6 */
1899 U_JG_ZHAIN, /**< @stable ICU 2.6 */
1900 U_JG_BURUSHASKI_YEH_BARREE, /**< @stable ICU 4.0 */
1901 U_JG_FARSI_YEH, /**< @stable ICU 4.4 */
1902 U_JG_NYA, /**< @stable ICU 4.4 */
1903 U_JG_ROHINGYA_YEH, /**< @stable ICU 49 */
1904 U_JG_MANICHAEAN_ALEPH, /**< @stable ICU 54 */
1905 U_JG_MANICHAEAN_AYIN, /**< @stable ICU 54 */
1906 U_JG_MANICHAEAN_BETH, /**< @stable ICU 54 */
1907 U_JG_MANICHAEAN_DALETH, /**< @stable ICU 54 */
1908 U_JG_MANICHAEAN_DHAMEDH, /**< @stable ICU 54 */
1909 U_JG_MANICHAEAN_FIVE, /**< @stable ICU 54 */
1910 U_JG_MANICHAEAN_GIMEL, /**< @stable ICU 54 */
1911 U_JG_MANICHAEAN_HETH, /**< @stable ICU 54 */
1912 U_JG_MANICHAEAN_HUNDRED, /**< @stable ICU 54 */
1913 U_JG_MANICHAEAN_KAPH, /**< @stable ICU 54 */
1914 U_JG_MANICHAEAN_LAMEDH, /**< @stable ICU 54 */
1915 U_JG_MANICHAEAN_MEM, /**< @stable ICU 54 */
1916 U_JG_MANICHAEAN_NUN, /**< @stable ICU 54 */
1917 U_JG_MANICHAEAN_ONE, /**< @stable ICU 54 */
1918 U_JG_MANICHAEAN_PE, /**< @stable ICU 54 */
1919 U_JG_MANICHAEAN_QOPH, /**< @stable ICU 54 */
1920 U_JG_MANICHAEAN_RESH, /**< @stable ICU 54 */
1921 U_JG_MANICHAEAN_SADHE, /**< @stable ICU 54 */
1922 U_JG_MANICHAEAN_SAMEKH, /**< @stable ICU 54 */
1923 U_JG_MANICHAEAN_TAW, /**< @stable ICU 54 */
1924 U_JG_MANICHAEAN_TEN, /**< @stable ICU 54 */
1925 U_JG_MANICHAEAN_TETH, /**< @stable ICU 54 */
1926 U_JG_MANICHAEAN_THAMEDH, /**< @stable ICU 54 */
1927 U_JG_MANICHAEAN_TWENTY, /**< @stable ICU 54 */
1928 U_JG_MANICHAEAN_WAW, /**< @stable ICU 54 */
1929 U_JG_MANICHAEAN_YODH, /**< @stable ICU 54 */
1930 U_JG_MANICHAEAN_ZAYIN, /**< @stable ICU 54 */
1931 U_JG_STRAIGHT_WAW, /**< @stable ICU 54 */
1932 U_JG_AFRICAN_FEH, /**< @stable ICU 58 */
1933 U_JG_AFRICAN_NOON, /**< @stable ICU 58 */
1934 U_JG_AFRICAN_QAF, /**< @stable ICU 58 */
1935 #ifndef U_HIDE_DEPRECATED_API
1937 * One more than the highest normal UJoiningGroup value.
1938 * The highest value is available via u_getIntPropertyMaxValue(UCHAR_JOINING_GROUP).
1940 * @deprecated ICU 58 The numeric value may change over time, see ICU ticket #12420.
1943 #endif // U_HIDE_DEPRECATED_API
1947 * Grapheme Cluster Break constants.
1949 * @see UCHAR_GRAPHEME_CLUSTER_BREAK
1952 typedef enum UGraphemeClusterBreak {
1954 * Note: UGraphemeClusterBreak constants are parsed by preparseucd.py.
1955 * It matches lines like
1956 * U_GCB_<Unicode Grapheme_Cluster_Break value name>
1959 U_GCB_OTHER = 0, /*[XX]*/
1960 U_GCB_CONTROL = 1, /*[CN]*/
1961 U_GCB_CR = 2, /*[CR]*/
1962 U_GCB_EXTEND = 3, /*[EX]*/
1963 U_GCB_L = 4, /*[L]*/
1964 U_GCB_LF = 5, /*[LF]*/
1965 U_GCB_LV = 6, /*[LV]*/
1966 U_GCB_LVT = 7, /*[LVT]*/
1967 U_GCB_T = 8, /*[T]*/
1968 U_GCB_V = 9, /*[V]*/
1969 /** @stable ICU 4.0 */
1970 U_GCB_SPACING_MARK = 10, /*[SM]*/ /* from here on: new in Unicode 5.1/ICU 4.0 */
1971 /** @stable ICU 4.0 */
1972 U_GCB_PREPEND = 11, /*[PP]*/
1973 /** @stable ICU 50 */
1974 U_GCB_REGIONAL_INDICATOR = 12, /*[RI]*/ /* new in Unicode 6.2/ICU 50 */
1975 /** @stable ICU 58 */
1976 U_GCB_E_BASE = 13, /*[EB]*/ /* from here on: new in Unicode 9.0/ICU 58 */
1977 /** @stable ICU 58 */
1978 U_GCB_E_BASE_GAZ = 14, /*[EBG]*/
1979 /** @stable ICU 58 */
1980 U_GCB_E_MODIFIER = 15, /*[EM]*/
1981 /** @stable ICU 58 */
1982 U_GCB_GLUE_AFTER_ZWJ = 16, /*[GAZ]*/
1983 /** @stable ICU 58 */
1984 U_GCB_ZWJ = 17, /*[ZWJ]*/
1985 #ifndef U_HIDE_DEPRECATED_API
1987 * One more than the highest normal UGraphemeClusterBreak value.
1988 * The highest value is available via u_getIntPropertyMaxValue(UCHAR_GRAPHEME_CLUSTER_BREAK).
1990 * @deprecated ICU 58 The numeric value may change over time, see ICU ticket #12420.
1993 #endif // U_HIDE_DEPRECATED_API
1994 } UGraphemeClusterBreak;
1997 * Word Break constants.
1998 * (UWordBreak is a pre-existing enum type in ubrk.h for word break status tags.)
2000 * @see UCHAR_WORD_BREAK
2003 typedef enum UWordBreakValues {
2005 * Note: UWordBreakValues constants are parsed by preparseucd.py.
2006 * It matches lines like
2007 * U_WB_<Unicode Word_Break value name>
2010 U_WB_OTHER = 0, /*[XX]*/
2011 U_WB_ALETTER = 1, /*[LE]*/
2012 U_WB_FORMAT = 2, /*[FO]*/
2013 U_WB_KATAKANA = 3, /*[KA]*/
2014 U_WB_MIDLETTER = 4, /*[ML]*/
2015 U_WB_MIDNUM = 5, /*[MN]*/
2016 U_WB_NUMERIC = 6, /*[NU]*/
2017 U_WB_EXTENDNUMLET = 7, /*[EX]*/
2018 /** @stable ICU 4.0 */
2019 U_WB_CR = 8, /*[CR]*/ /* from here on: new in Unicode 5.1/ICU 4.0 */
2020 /** @stable ICU 4.0 */
2021 U_WB_EXTEND = 9, /*[Extend]*/
2022 /** @stable ICU 4.0 */
2023 U_WB_LF = 10, /*[LF]*/
2024 /** @stable ICU 4.0 */
2025 U_WB_MIDNUMLET =11, /*[MB]*/
2026 /** @stable ICU 4.0 */
2027 U_WB_NEWLINE =12, /*[NL]*/
2028 /** @stable ICU 50 */
2029 U_WB_REGIONAL_INDICATOR = 13, /*[RI]*/ /* new in Unicode 6.2/ICU 50 */
2030 /** @stable ICU 52 */
2031 U_WB_HEBREW_LETTER = 14, /*[HL]*/ /* from here on: new in Unicode 6.3/ICU 52 */
2032 /** @stable ICU 52 */
2033 U_WB_SINGLE_QUOTE = 15, /*[SQ]*/
2034 /** @stable ICU 52 */
2035 U_WB_DOUBLE_QUOTE = 16, /*[DQ]*/
2036 /** @stable ICU 58 */
2037 U_WB_E_BASE = 17, /*[EB]*/ /* from here on: new in Unicode 9.0/ICU 58 */
2038 /** @stable ICU 58 */
2039 U_WB_E_BASE_GAZ = 18, /*[EBG]*/
2040 /** @stable ICU 58 */
2041 U_WB_E_MODIFIER = 19, /*[EM]*/
2042 /** @stable ICU 58 */
2043 U_WB_GLUE_AFTER_ZWJ = 20, /*[GAZ]*/
2044 /** @stable ICU 58 */
2045 U_WB_ZWJ = 21, /*[ZWJ]*/
2046 #ifndef U_HIDE_DEPRECATED_API
2048 * One more than the highest normal UWordBreakValues value.
2049 * The highest value is available via u_getIntPropertyMaxValue(UCHAR_WORD_BREAK).
2051 * @deprecated ICU 58 The numeric value may change over time, see ICU ticket #12420.
2054 #endif // U_HIDE_DEPRECATED_API
2058 * Sentence Break constants.
2060 * @see UCHAR_SENTENCE_BREAK
2063 typedef enum USentenceBreak {
2065 * Note: USentenceBreak constants are parsed by preparseucd.py.
2066 * It matches lines like
2067 * U_SB_<Unicode Sentence_Break value name>
2070 U_SB_OTHER = 0, /*[XX]*/
2071 U_SB_ATERM = 1, /*[AT]*/
2072 U_SB_CLOSE = 2, /*[CL]*/
2073 U_SB_FORMAT = 3, /*[FO]*/
2074 U_SB_LOWER = 4, /*[LO]*/
2075 U_SB_NUMERIC = 5, /*[NU]*/
2076 U_SB_OLETTER = 6, /*[LE]*/
2077 U_SB_SEP = 7, /*[SE]*/
2078 U_SB_SP = 8, /*[SP]*/
2079 U_SB_STERM = 9, /*[ST]*/
2080 U_SB_UPPER = 10, /*[UP]*/
2081 U_SB_CR = 11, /*[CR]*/ /* from here on: new in Unicode 5.1/ICU 4.0 */
2082 U_SB_EXTEND = 12, /*[EX]*/
2083 U_SB_LF = 13, /*[LF]*/
2084 U_SB_SCONTINUE = 14, /*[SC]*/
2085 #ifndef U_HIDE_DEPRECATED_API
2087 * One more than the highest normal USentenceBreak value.
2088 * The highest value is available via u_getIntPropertyMaxValue(UCHAR_SENTENCE_BREAK).
2090 * @deprecated ICU 58 The numeric value may change over time, see ICU ticket #12420.
2093 #endif // U_HIDE_DEPRECATED_API
2097 * Line Break constants.
2099 * @see UCHAR_LINE_BREAK
2102 typedef enum ULineBreak {
2104 * Note: ULineBreak constants are parsed by preparseucd.py.
2105 * It matches lines like
2106 * U_LB_<Unicode Line_Break value name>
2109 U_LB_UNKNOWN = 0, /*[XX]*/
2110 U_LB_AMBIGUOUS = 1, /*[AI]*/
2111 U_LB_ALPHABETIC = 2, /*[AL]*/
2112 U_LB_BREAK_BOTH = 3, /*[B2]*/
2113 U_LB_BREAK_AFTER = 4, /*[BA]*/
2114 U_LB_BREAK_BEFORE = 5, /*[BB]*/
2115 U_LB_MANDATORY_BREAK = 6, /*[BK]*/
2116 U_LB_CONTINGENT_BREAK = 7, /*[CB]*/
2117 U_LB_CLOSE_PUNCTUATION = 8, /*[CL]*/
2118 U_LB_COMBINING_MARK = 9, /*[CM]*/
2119 U_LB_CARRIAGE_RETURN = 10, /*[CR]*/
2120 U_LB_EXCLAMATION = 11, /*[EX]*/
2121 U_LB_GLUE = 12, /*[GL]*/
2122 U_LB_HYPHEN = 13, /*[HY]*/
2123 U_LB_IDEOGRAPHIC = 14, /*[ID]*/
2124 /** Renamed from the misspelled "inseperable" in Unicode 4.0.1/ICU 3.0 @stable ICU 3.0 */
2125 U_LB_INSEPARABLE = 15, /*[IN]*/
2126 U_LB_INSEPERABLE = U_LB_INSEPARABLE,
2127 U_LB_INFIX_NUMERIC = 16, /*[IS]*/
2128 U_LB_LINE_FEED = 17, /*[LF]*/
2129 U_LB_NONSTARTER = 18, /*[NS]*/
2130 U_LB_NUMERIC = 19, /*[NU]*/
2131 U_LB_OPEN_PUNCTUATION = 20, /*[OP]*/
2132 U_LB_POSTFIX_NUMERIC = 21, /*[PO]*/
2133 U_LB_PREFIX_NUMERIC = 22, /*[PR]*/
2134 U_LB_QUOTATION = 23, /*[QU]*/
2135 U_LB_COMPLEX_CONTEXT = 24, /*[SA]*/
2136 U_LB_SURROGATE = 25, /*[SG]*/
2137 U_LB_SPACE = 26, /*[SP]*/
2138 U_LB_BREAK_SYMBOLS = 27, /*[SY]*/
2139 U_LB_ZWSPACE = 28, /*[ZW]*/
2140 /** @stable ICU 2.6 */
2141 U_LB_NEXT_LINE = 29, /*[NL]*/ /* from here on: new in Unicode 4/ICU 2.6 */
2142 /** @stable ICU 2.6 */
2143 U_LB_WORD_JOINER = 30, /*[WJ]*/
2144 /** @stable ICU 3.4 */
2145 U_LB_H2 = 31, /*[H2]*/ /* from here on: new in Unicode 4.1/ICU 3.4 */
2146 /** @stable ICU 3.4 */
2147 U_LB_H3 = 32, /*[H3]*/
2148 /** @stable ICU 3.4 */
2149 U_LB_JL = 33, /*[JL]*/
2150 /** @stable ICU 3.4 */
2151 U_LB_JT = 34, /*[JT]*/
2152 /** @stable ICU 3.4 */
2153 U_LB_JV = 35, /*[JV]*/
2154 /** @stable ICU 4.4 */
2155 U_LB_CLOSE_PARENTHESIS = 36, /*[CP]*/ /* new in Unicode 5.2/ICU 4.4 */
2156 /** @stable ICU 49 */
2157 U_LB_CONDITIONAL_JAPANESE_STARTER = 37,/*[CJ]*/ /* new in Unicode 6.1/ICU 49 */
2158 /** @stable ICU 49 */
2159 U_LB_HEBREW_LETTER = 38, /*[HL]*/ /* new in Unicode 6.1/ICU 49 */
2160 /** @stable ICU 50 */
2161 U_LB_REGIONAL_INDICATOR = 39,/*[RI]*/ /* new in Unicode 6.2/ICU 50 */
2162 /** @stable ICU 58 */
2163 U_LB_E_BASE = 40, /*[EB]*/ /* from here on: new in Unicode 9.0/ICU 58 */
2164 /** @stable ICU 58 */
2165 U_LB_E_MODIFIER = 41, /*[EM]*/
2166 /** @stable ICU 58 */
2167 U_LB_ZWJ = 42, /*[ZWJ]*/
2168 #ifndef U_HIDE_DEPRECATED_API
2170 * One more than the highest normal ULineBreak value.
2171 * The highest value is available via u_getIntPropertyMaxValue(UCHAR_LINE_BREAK).
2173 * @deprecated ICU 58 The numeric value may change over time, see ICU ticket #12420.
2176 #endif // U_HIDE_DEPRECATED_API
2180 * Numeric Type constants.
2182 * @see UCHAR_NUMERIC_TYPE
2185 typedef enum UNumericType {
2187 * Note: UNumericType constants are parsed by preparseucd.py.
2188 * It matches lines like
2189 * U_NT_<Unicode Numeric_Type value name>
2192 U_NT_NONE, /*[None]*/
2193 U_NT_DECIMAL, /*[de]*/
2194 U_NT_DIGIT, /*[di]*/
2195 U_NT_NUMERIC, /*[nu]*/
2196 #ifndef U_HIDE_DEPRECATED_API
2198 * One more than the highest normal UNumericType value.
2199 * The highest value is available via u_getIntPropertyMaxValue(UCHAR_NUMERIC_TYPE).
2201 * @deprecated ICU 58 The numeric value may change over time, see ICU ticket #12420.
2204 #endif // U_HIDE_DEPRECATED_API
2208 * Hangul Syllable Type constants.
2210 * @see UCHAR_HANGUL_SYLLABLE_TYPE
2213 typedef enum UHangulSyllableType {
2215 * Note: UHangulSyllableType constants are parsed by preparseucd.py.
2216 * It matches lines like
2217 * U_HST_<Unicode Hangul_Syllable_Type value name>
2220 U_HST_NOT_APPLICABLE, /*[NA]*/
2221 U_HST_LEADING_JAMO, /*[L]*/
2222 U_HST_VOWEL_JAMO, /*[V]*/
2223 U_HST_TRAILING_JAMO, /*[T]*/
2224 U_HST_LV_SYLLABLE, /*[LV]*/
2225 U_HST_LVT_SYLLABLE, /*[LVT]*/
2226 #ifndef U_HIDE_DEPRECATED_API
2228 * One more than the highest normal UHangulSyllableType value.
2229 * The highest value is available via u_getIntPropertyMaxValue(UCHAR_HANGUL_SYLLABLE_TYPE).
2231 * @deprecated ICU 58 The numeric value may change over time, see ICU ticket #12420.
2234 #endif // U_HIDE_DEPRECATED_API
2235 } UHangulSyllableType;
2238 * Check a binary Unicode property for a code point.
2240 * Unicode, especially in version 3.2, defines many more properties than the
2241 * original set in UnicodeData.txt.
2243 * The properties APIs are intended to reflect Unicode properties as defined
2244 * in the Unicode Character Database (UCD) and Unicode Technical Reports (UTR).
2245 * For details about the properties see http://www.unicode.org/ucd/ .
2246 * For names of Unicode properties see the UCD file PropertyAliases.txt.
2248 * Important: If ICU is built with UCD files from Unicode versions below 3.2,
2249 * then properties marked with "new in Unicode 3.2" are not or not fully available.
2251 * @param c Code point to test.
2252 * @param which UProperty selector constant, identifies which binary property to check.
2253 * Must be UCHAR_BINARY_START<=which<UCHAR_BINARY_LIMIT.
2254 * @return TRUE or FALSE according to the binary Unicode property value for c.
2255 * Also FALSE if 'which' is out of bounds or if the Unicode version
2256 * does not have data for the property at all, or not for this code point.
2259 * @see u_getIntPropertyValue
2260 * @see u_getUnicodeVersion
2263 U_STABLE UBool U_EXPORT2
2264 u_hasBinaryProperty(UChar32 c, UProperty which);
2267 * Check if a code point has the Alphabetic Unicode property.
2268 * Same as u_hasBinaryProperty(c, UCHAR_ALPHABETIC).
2269 * This is different from u_isalpha!
2270 * @param c Code point to test
2271 * @return true if the code point has the Alphabetic Unicode property, false otherwise
2273 * @see UCHAR_ALPHABETIC
2275 * @see u_hasBinaryProperty
2278 U_STABLE UBool U_EXPORT2
2279 u_isUAlphabetic(UChar32 c);
2282 * Check if a code point has the Lowercase Unicode property.
2283 * Same as u_hasBinaryProperty(c, UCHAR_LOWERCASE).
2284 * This is different from u_islower!
2285 * @param c Code point to test
2286 * @return true if the code point has the Lowercase Unicode property, false otherwise
2288 * @see UCHAR_LOWERCASE
2290 * @see u_hasBinaryProperty
2293 U_STABLE UBool U_EXPORT2
2294 u_isULowercase(UChar32 c);
2297 * Check if a code point has the Uppercase Unicode property.
2298 * Same as u_hasBinaryProperty(c, UCHAR_UPPERCASE).
2299 * This is different from u_isupper!
2300 * @param c Code point to test
2301 * @return true if the code point has the Uppercase Unicode property, false otherwise
2303 * @see UCHAR_UPPERCASE
2305 * @see u_hasBinaryProperty
2308 U_STABLE UBool U_EXPORT2
2309 u_isUUppercase(UChar32 c);
2312 * Check if a code point has the White_Space Unicode property.
2313 * Same as u_hasBinaryProperty(c, UCHAR_WHITE_SPACE).
2314 * This is different from both u_isspace and u_isWhitespace!
2316 * Note: There are several ICU whitespace functions; please see the uchar.h
2317 * file documentation for a detailed comparison.
2319 * @param c Code point to test
2320 * @return true if the code point has the White_Space Unicode property, false otherwise.
2322 * @see UCHAR_WHITE_SPACE
2323 * @see u_isWhitespace
2325 * @see u_isJavaSpaceChar
2326 * @see u_hasBinaryProperty
2329 U_STABLE UBool U_EXPORT2
2330 u_isUWhiteSpace(UChar32 c);
2333 * Get the property value for an enumerated or integer Unicode property for a code point.
2334 * Also returns binary and mask property values.
2336 * Unicode, especially in version 3.2, defines many more properties than the
2337 * original set in UnicodeData.txt.
2339 * The properties APIs are intended to reflect Unicode properties as defined
2340 * in the Unicode Character Database (UCD) and Unicode Technical Reports (UTR).
2341 * For details about the properties see http://www.unicode.org/ .
2342 * For names of Unicode properties see the UCD file PropertyAliases.txt.
2345 * UEastAsianWidth ea=(UEastAsianWidth)u_getIntPropertyValue(c, UCHAR_EAST_ASIAN_WIDTH);
2346 * UBool b=(UBool)u_getIntPropertyValue(c, UCHAR_IDEOGRAPHIC);
2348 * @param c Code point to test.
2349 * @param which UProperty selector constant, identifies which property to check.
2350 * Must be UCHAR_BINARY_START<=which<UCHAR_BINARY_LIMIT
2351 * or UCHAR_INT_START<=which<UCHAR_INT_LIMIT
2352 * or UCHAR_MASK_START<=which<UCHAR_MASK_LIMIT.
2353 * @return Numeric value that is directly the property value or,
2354 * for enumerated properties, corresponds to the numeric value of the enumerated
2355 * constant of the respective property value enumeration type
2356 * (cast to enum type if necessary).
2357 * Returns 0 or 1 (for FALSE/TRUE) for binary Unicode properties.
2358 * Returns a bit-mask for mask properties.
2359 * Returns 0 if 'which' is out of bounds or if the Unicode version
2360 * does not have data for the property at all, or not for this code point.
2363 * @see u_hasBinaryProperty
2364 * @see u_getIntPropertyMinValue
2365 * @see u_getIntPropertyMaxValue
2366 * @see u_getUnicodeVersion
2369 U_STABLE int32_t U_EXPORT2
2370 u_getIntPropertyValue(UChar32 c, UProperty which);
2373 * Get the minimum value for an enumerated/integer/binary Unicode property.
2374 * Can be used together with u_getIntPropertyMaxValue
2375 * to allocate arrays of UnicodeSet or similar.
2377 * @param which UProperty selector constant, identifies which binary property to check.
2378 * Must be UCHAR_BINARY_START<=which<UCHAR_BINARY_LIMIT
2379 * or UCHAR_INT_START<=which<UCHAR_INT_LIMIT.
2380 * @return Minimum value returned by u_getIntPropertyValue for a Unicode property.
2381 * 0 if the property selector is out of range.
2384 * @see u_hasBinaryProperty
2385 * @see u_getUnicodeVersion
2386 * @see u_getIntPropertyMaxValue
2387 * @see u_getIntPropertyValue
2390 U_STABLE int32_t U_EXPORT2
2391 u_getIntPropertyMinValue(UProperty which);
2394 * Get the maximum value for an enumerated/integer/binary Unicode property.
2395 * Can be used together with u_getIntPropertyMinValue
2396 * to allocate arrays of UnicodeSet or similar.
2398 * Examples for min/max values (for Unicode 3.2):
2400 * - UCHAR_BIDI_CLASS: 0/18 (U_LEFT_TO_RIGHT/U_BOUNDARY_NEUTRAL)
2401 * - UCHAR_SCRIPT: 0/45 (USCRIPT_COMMON/USCRIPT_TAGBANWA)
2402 * - UCHAR_IDEOGRAPHIC: 0/1 (FALSE/TRUE)
2404 * For undefined UProperty constant values, min/max values will be 0/-1.
2406 * @param which UProperty selector constant, identifies which binary property to check.
2407 * Must be UCHAR_BINARY_START<=which<UCHAR_BINARY_LIMIT
2408 * or UCHAR_INT_START<=which<UCHAR_INT_LIMIT.
2409 * @return Maximum value returned by u_getIntPropertyValue for a Unicode property.
2410 * <=0 if the property selector is out of range.
2413 * @see u_hasBinaryProperty
2414 * @see u_getUnicodeVersion
2415 * @see u_getIntPropertyMaxValue
2416 * @see u_getIntPropertyValue
2419 U_STABLE int32_t U_EXPORT2
2420 u_getIntPropertyMaxValue(UProperty which);
2423 * Get the numeric value for a Unicode code point as defined in the
2424 * Unicode Character Database.
2426 * A "double" return type is necessary because
2427 * some numeric values are fractions, negative, or too large for int32_t.
2429 * For characters without any numeric values in the Unicode Character Database,
2430 * this function will return U_NO_NUMERIC_VALUE.
2431 * Note: This is different from the Unicode Standard which specifies NaN as the default value.
2432 * (NaN is not available on all platforms.)
2434 * Similar to java.lang.Character.getNumericValue(), but u_getNumericValue()
2435 * also supports negative values, large values, and fractions,
2436 * while Java's getNumericValue() returns values 10..35 for ASCII letters.
2438 * @param c Code point to get the numeric value for.
2439 * @return Numeric value of c, or U_NO_NUMERIC_VALUE if none is defined.
2441 * @see U_NO_NUMERIC_VALUE
2444 U_STABLE double U_EXPORT2
2445 u_getNumericValue(UChar32 c);
2448 * Special value that is returned by u_getNumericValue when
2449 * no numeric value is defined for a code point.
2451 * @see u_getNumericValue
2454 #define U_NO_NUMERIC_VALUE ((double)-123456789.)
2457 * Determines whether the specified code point has the general category "Ll"
2458 * (lowercase letter).
2460 * Same as java.lang.Character.isLowerCase().
2462 * This misses some characters that are also lowercase but
2463 * have a different general category value.
2464 * In order to include those, use UCHAR_LOWERCASE.
2466 * In addition to being equivalent to a Java function, this also serves
2467 * as a C/POSIX migration function.
2468 * See the comments about C/POSIX character classification functions in the
2469 * documentation at the top of this header file.
2471 * @param c the code point to be tested
2472 * @return TRUE if the code point is an Ll lowercase letter
2474 * @see UCHAR_LOWERCASE
2479 U_STABLE UBool U_EXPORT2
2480 u_islower(UChar32 c);
2483 * Determines whether the specified code point has the general category "Lu"
2484 * (uppercase letter).
2486 * Same as java.lang.Character.isUpperCase().
2488 * This misses some characters that are also uppercase but
2489 * have a different general category value.
2490 * In order to include those, use UCHAR_UPPERCASE.
2492 * In addition to being equivalent to a Java function, this also serves
2493 * as a C/POSIX migration function.
2494 * See the comments about C/POSIX character classification functions in the
2495 * documentation at the top of this header file.
2497 * @param c the code point to be tested
2498 * @return TRUE if the code point is an Lu uppercase letter
2500 * @see UCHAR_UPPERCASE
2506 U_STABLE UBool U_EXPORT2
2507 u_isupper(UChar32 c);
2510 * Determines whether the specified code point is a titlecase letter.
2511 * True for general category "Lt" (titlecase letter).
2513 * Same as java.lang.Character.isTitleCase().
2515 * @param c the code point to be tested
2516 * @return TRUE if the code point is an Lt titlecase letter
2523 U_STABLE UBool U_EXPORT2
2524 u_istitle(UChar32 c);
2527 * Determines whether the specified code point is a digit character according to Java.
2528 * True for characters with general category "Nd" (decimal digit numbers).
2529 * Beginning with Unicode 4, this is the same as
2530 * testing for the Numeric_Type of Decimal.
2532 * Same as java.lang.Character.isDigit().
2534 * In addition to being equivalent to a Java function, this also serves
2535 * as a C/POSIX migration function.
2536 * See the comments about C/POSIX character classification functions in the
2537 * documentation at the top of this header file.
2539 * @param c the code point to be tested
2540 * @return TRUE if the code point is a digit character according to Character.isDigit()
2544 U_STABLE UBool U_EXPORT2
2545 u_isdigit(UChar32 c);
2548 * Determines whether the specified code point is a letter character.
2549 * True for general categories "L" (letters).
2551 * Same as java.lang.Character.isLetter().
2553 * In addition to being equivalent to a Java function, this also serves
2554 * as a C/POSIX migration function.
2555 * See the comments about C/POSIX character classification functions in the
2556 * documentation at the top of this header file.
2558 * @param c the code point to be tested
2559 * @return TRUE if the code point is a letter character
2565 U_STABLE UBool U_EXPORT2
2566 u_isalpha(UChar32 c);
2569 * Determines whether the specified code point is an alphanumeric character
2570 * (letter or digit) according to Java.
2571 * True for characters with general categories
2572 * "L" (letters) and "Nd" (decimal digit numbers).
2574 * Same as java.lang.Character.isLetterOrDigit().
2576 * In addition to being equivalent to a Java function, this also serves
2577 * as a C/POSIX migration function.
2578 * See the comments about C/POSIX character classification functions in the
2579 * documentation at the top of this header file.
2581 * @param c the code point to be tested
2582 * @return TRUE if the code point is an alphanumeric character according to Character.isLetterOrDigit()
2586 U_STABLE UBool U_EXPORT2
2587 u_isalnum(UChar32 c);
2590 * Determines whether the specified code point is a hexadecimal digit.
2591 * This is equivalent to u_digit(c, 16)>=0.
2592 * True for characters with general category "Nd" (decimal digit numbers)
2593 * as well as Latin letters a-f and A-F in both ASCII and Fullwidth ASCII.
2594 * (That is, for letters with code points
2595 * 0041..0046, 0061..0066, FF21..FF26, FF41..FF46.)
2597 * In order to narrow the definition of hexadecimal digits to only ASCII
2598 * characters, use (c<=0x7f && u_isxdigit(c)).
2600 * This is a C/POSIX migration function.
2601 * See the comments about C/POSIX character classification functions in the
2602 * documentation at the top of this header file.
2604 * @param c the code point to be tested
2605 * @return TRUE if the code point is a hexadecimal digit
2609 U_STABLE UBool U_EXPORT2
2610 u_isxdigit(UChar32 c);
2613 * Determines whether the specified code point is a punctuation character.
2614 * True for characters with general categories "P" (punctuation).
2616 * This is a C/POSIX migration function.
2617 * See the comments about C/POSIX character classification functions in the
2618 * documentation at the top of this header file.
2620 * @param c the code point to be tested
2621 * @return TRUE if the code point is a punctuation character
2625 U_STABLE UBool U_EXPORT2
2626 u_ispunct(UChar32 c);
2629 * Determines whether the specified code point is a "graphic" character
2630 * (printable, excluding spaces).
2631 * TRUE for all characters except those with general categories
2632 * "Cc" (control codes), "Cf" (format controls), "Cs" (surrogates),
2633 * "Cn" (unassigned), and "Z" (separators).
2635 * This is a C/POSIX migration function.
2636 * See the comments about C/POSIX character classification functions in the
2637 * documentation at the top of this header file.
2639 * @param c the code point to be tested
2640 * @return TRUE if the code point is a "graphic" character
2644 U_STABLE UBool U_EXPORT2
2645 u_isgraph(UChar32 c);
2648 * Determines whether the specified code point is a "blank" or "horizontal space",
2649 * a character that visibly separates words on a line.
2650 * The following are equivalent definitions:
2652 * TRUE for Unicode White_Space characters except for "vertical space controls"
2653 * where "vertical space controls" are the following characters:
2654 * U+000A (LF) U+000B (VT) U+000C (FF) U+000D (CR) U+0085 (NEL) U+2028 (LS) U+2029 (PS)
2658 * TRUE for U+0009 (TAB) and characters with general category "Zs" (space separators)
2659 * except Zero Width Space (ZWSP, U+200B).
2661 * Note: There are several ICU whitespace functions; please see the uchar.h
2662 * file documentation for a detailed comparison.
2664 * This is a C/POSIX migration function.
2665 * See the comments about C/POSIX character classification functions in the
2666 * documentation at the top of this header file.
2668 * @param c the code point to be tested
2669 * @return TRUE if the code point is a "blank"
2673 U_STABLE UBool U_EXPORT2
2674 u_isblank(UChar32 c);
2677 * Determines whether the specified code point is "defined",
2678 * which usually means that it is assigned a character.
2679 * True for general categories other than "Cn" (other, not assigned),
2680 * i.e., true for all code points mentioned in UnicodeData.txt.
2682 * Note that non-character code points (e.g., U+FDD0) are not "defined"
2683 * (they are Cn), but surrogate code points are "defined" (Cs).
2685 * Same as java.lang.Character.isDefined().
2687 * @param c the code point to be tested
2688 * @return TRUE if the code point is assigned a character
2698 U_STABLE UBool U_EXPORT2
2699 u_isdefined(UChar32 c);
2702 * Determines if the specified character is a space character or not.
2704 * Note: There are several ICU whitespace functions; please see the uchar.h
2705 * file documentation for a detailed comparison.
2707 * This is a C/POSIX migration function.
2708 * See the comments about C/POSIX character classification functions in the
2709 * documentation at the top of this header file.
2711 * @param c the character to be tested
2712 * @return true if the character is a space character; false otherwise.
2714 * @see u_isJavaSpaceChar
2715 * @see u_isWhitespace
2716 * @see u_isUWhiteSpace
2719 U_STABLE UBool U_EXPORT2
2720 u_isspace(UChar32 c);
2723 * Determine if the specified code point is a space character according to Java.
2724 * True for characters with general categories "Z" (separators),
2725 * which does not include control codes (e.g., TAB or Line Feed).
2727 * Same as java.lang.Character.isSpaceChar().
2729 * Note: There are several ICU whitespace functions; please see the uchar.h
2730 * file documentation for a detailed comparison.
2732 * @param c the code point to be tested
2733 * @return TRUE if the code point is a space character according to Character.isSpaceChar()
2736 * @see u_isWhitespace
2737 * @see u_isUWhiteSpace
2740 U_STABLE UBool U_EXPORT2
2741 u_isJavaSpaceChar(UChar32 c);
2744 * Determines if the specified code point is a whitespace character according to Java/ICU.
2745 * A character is considered to be a Java whitespace character if and only
2746 * if it satisfies one of the following criteria:
2748 * - It is a Unicode Separator character (categories "Z" = "Zs" or "Zl" or "Zp"), but is not
2749 * also a non-breaking space (U+00A0 NBSP or U+2007 Figure Space or U+202F Narrow NBSP).
2750 * - It is U+0009 HORIZONTAL TABULATION.
2751 * - It is U+000A LINE FEED.
2752 * - It is U+000B VERTICAL TABULATION.
2753 * - It is U+000C FORM FEED.
2754 * - It is U+000D CARRIAGE RETURN.
2755 * - It is U+001C FILE SEPARATOR.
2756 * - It is U+001D GROUP SEPARATOR.
2757 * - It is U+001E RECORD SEPARATOR.
2758 * - It is U+001F UNIT SEPARATOR.
2760 * This API tries to sync with the semantics of Java's
2761 * java.lang.Character.isWhitespace(), but it may not return
2762 * the exact same results because of the Unicode version
2765 * Note: Unicode 4.0.1 changed U+200B ZERO WIDTH SPACE from a Space Separator (Zs)
2766 * to a Format Control (Cf). Since then, isWhitespace(0x200b) returns false.
2767 * See http://www.unicode.org/versions/Unicode4.0.1/
2769 * Note: There are several ICU whitespace functions; please see the uchar.h
2770 * file documentation for a detailed comparison.
2772 * @param c the code point to be tested
2773 * @return TRUE if the code point is a whitespace character according to Java/ICU
2776 * @see u_isJavaSpaceChar
2777 * @see u_isUWhiteSpace
2780 U_STABLE UBool U_EXPORT2
2781 u_isWhitespace(UChar32 c);
2784 * Determines whether the specified code point is a control character
2785 * (as defined by this function).
2786 * A control character is one of the following:
2787 * - ISO 8-bit control character (U+0000..U+001f and U+007f..U+009f)
2788 * - U_CONTROL_CHAR (Cc)
2789 * - U_FORMAT_CHAR (Cf)
2790 * - U_LINE_SEPARATOR (Zl)
2791 * - U_PARAGRAPH_SEPARATOR (Zp)
2793 * This is a C/POSIX migration function.
2794 * See the comments about C/POSIX character classification functions in the
2795 * documentation at the top of this header file.
2797 * @param c the code point to be tested
2798 * @return TRUE if the code point is a control character
2800 * @see UCHAR_DEFAULT_IGNORABLE_CODE_POINT
2804 U_STABLE UBool U_EXPORT2
2805 u_iscntrl(UChar32 c);
2808 * Determines whether the specified code point is an ISO control code.
2809 * True for U+0000..U+001f and U+007f..U+009f (general category "Cc").
2811 * Same as java.lang.Character.isISOControl().
2813 * @param c the code point to be tested
2814 * @return TRUE if the code point is an ISO control code
2819 U_STABLE UBool U_EXPORT2
2820 u_isISOControl(UChar32 c);
2823 * Determines whether the specified code point is a printable character.
2824 * True for general categories <em>other</em> than "C" (controls).
2826 * This is a C/POSIX migration function.
2827 * See the comments about C/POSIX character classification functions in the
2828 * documentation at the top of this header file.
2830 * @param c the code point to be tested
2831 * @return TRUE if the code point is a printable character
2833 * @see UCHAR_DEFAULT_IGNORABLE_CODE_POINT
2837 U_STABLE UBool U_EXPORT2
2838 u_isprint(UChar32 c);
2841 * Determines whether the specified code point is a base character.
2842 * True for general categories "L" (letters), "N" (numbers),
2843 * "Mc" (spacing combining marks), and "Me" (enclosing marks).
2845 * Note that this is different from the Unicode definition in
2846 * chapter 3.5, conformance clause D13,
2847 * which defines base characters to be all characters (not Cn)
2848 * that do not graphically combine with preceding characters (M)
2849 * and that are neither control (Cc) or format (Cf) characters.
2851 * @param c the code point to be tested
2852 * @return TRUE if the code point is a base character according to this function
2858 U_STABLE UBool U_EXPORT2
2859 u_isbase(UChar32 c);
2862 * Returns the bidirectional category value for the code point,
2863 * which is used in the Unicode bidirectional algorithm
2864 * (UAX #9 http://www.unicode.org/reports/tr9/).
2865 * Note that some <em>unassigned</em> code points have bidi values
2866 * of R or AL because they are in blocks that are reserved
2867 * for Right-To-Left scripts.
2869 * Same as java.lang.Character.getDirectionality()
2871 * @param c the code point to be tested
2872 * @return the bidirectional category (UCharDirection) value
2874 * @see UCharDirection
2877 U_STABLE UCharDirection U_EXPORT2
2878 u_charDirection(UChar32 c);
2881 * Determines whether the code point has the Bidi_Mirrored property.
2882 * This property is set for characters that are commonly used in
2883 * Right-To-Left contexts and need to be displayed with a "mirrored"
2886 * Same as java.lang.Character.isMirrored().
2887 * Same as UCHAR_BIDI_MIRRORED
2889 * @param c the code point to be tested
2890 * @return TRUE if the character has the Bidi_Mirrored property
2892 * @see UCHAR_BIDI_MIRRORED
2895 U_STABLE UBool U_EXPORT2
2896 u_isMirrored(UChar32 c);
2899 * Maps the specified character to a "mirror-image" character.
2900 * For characters with the Bidi_Mirrored property, implementations
2901 * sometimes need a "poor man's" mapping to another Unicode
2902 * character (code point) such that the default glyph may serve
2903 * as the mirror-image of the default glyph of the specified
2904 * character. This is useful for text conversion to and from
2905 * codepages with visual order, and for displays without glyph
2906 * selection capabilities.
2908 * @param c the code point to be mapped
2909 * @return another Unicode code point that may serve as a mirror-image
2910 * substitute, or c itself if there is no such mapping or c
2911 * does not have the Bidi_Mirrored property
2913 * @see UCHAR_BIDI_MIRRORED
2917 U_STABLE UChar32 U_EXPORT2
2918 u_charMirror(UChar32 c);
2921 * Maps the specified character to its paired bracket character.
2922 * For Bidi_Paired_Bracket_Type!=None, this is the same as u_charMirror().
2923 * Otherwise c itself is returned.
2924 * See http://www.unicode.org/reports/tr9/
2926 * @param c the code point to be mapped
2927 * @return the paired bracket code point,
2928 * or c itself if there is no such mapping
2929 * (Bidi_Paired_Bracket_Type=None)
2931 * @see UCHAR_BIDI_PAIRED_BRACKET
2932 * @see UCHAR_BIDI_PAIRED_BRACKET_TYPE
2936 U_STABLE UChar32 U_EXPORT2
2937 u_getBidiPairedBracket(UChar32 c);
2940 * Returns the general category value for the code point.
2942 * Same as java.lang.Character.getType().
2944 * @param c the code point to be tested
2945 * @return the general category (UCharCategory) value
2947 * @see UCharCategory
2950 U_STABLE int8_t U_EXPORT2
2951 u_charType(UChar32 c);
2954 * Get a single-bit bit set for the general category of a character.
2955 * This bit set can be compared bitwise with U_GC_SM_MASK, U_GC_L_MASK, etc.
2956 * Same as U_MASK(u_charType(c)).
2958 * @param c the code point to be tested
2959 * @return a single-bit mask corresponding to the general category (UCharCategory) value
2962 * @see UCharCategory
2966 #define U_GET_GC_MASK(c) U_MASK(u_charType(c))
2969 * Callback from u_enumCharTypes(), is called for each contiguous range
2970 * of code points c (where start<=c<limit)
2971 * with the same Unicode general category ("character type").
2973 * The callback function can stop the enumeration by returning FALSE.
2975 * @param context an opaque pointer, as passed into utrie_enum()
2976 * @param start the first code point in a contiguous range with value
2977 * @param limit one past the last code point in a contiguous range with value
2978 * @param type the general category for all code points in [start..limit[
2979 * @return FALSE to stop the enumeration
2982 * @see UCharCategory
2983 * @see u_enumCharTypes
2985 typedef UBool U_CALLCONV
2986 UCharEnumTypeRange(const void *context, UChar32 start, UChar32 limit, UCharCategory type);
2989 * Enumerate efficiently all code points with their Unicode general categories.
2991 * This is useful for building data structures (e.g., UnicodeSet's),
2992 * for enumerating all assigned code points (type!=U_UNASSIGNED), etc.
2994 * For each contiguous range of code points with a given general category ("character type"),
2995 * the UCharEnumTypeRange function is called.
2996 * Adjacent ranges have different types.
2997 * The Unicode Standard guarantees that the numeric value of the type is 0..31.
2999 * @param enumRange a pointer to a function that is called for each contiguous range
3000 * of code points with the same general category
3001 * @param context an opaque pointer that is passed on to the callback function
3004 * @see UCharCategory
3005 * @see UCharEnumTypeRange
3007 U_STABLE void U_EXPORT2
3008 u_enumCharTypes(UCharEnumTypeRange *enumRange, const void *context);
3010 #if !UCONFIG_NO_NORMALIZATION
3013 * Returns the combining class of the code point as specified in UnicodeData.txt.
3015 * @param c the code point of the character
3016 * @return the combining class of the character
3019 U_STABLE uint8_t U_EXPORT2
3020 u_getCombiningClass(UChar32 c);
3025 * Returns the decimal digit value of a decimal digit character.
3026 * Such characters have the general category "Nd" (decimal digit numbers)
3027 * and a Numeric_Type of Decimal.
3029 * Unlike ICU releases before 2.6, no digit values are returned for any
3030 * Han characters because Han number characters are often used with a special
3031 * Chinese-style number format (with characters for powers of 10 in between)
3032 * instead of in decimal-positional notation.
3033 * Unicode 4 explicitly assigns Han number characters the Numeric_Type
3034 * Numeric instead of Decimal.
3035 * See Jitterbug 1483 for more details.
3037 * Use u_getIntPropertyValue(c, UCHAR_NUMERIC_TYPE) and u_getNumericValue()
3038 * for complete numeric Unicode properties.
3040 * @param c the code point for which to get the decimal digit value
3041 * @return the decimal digit value of c,
3042 * or -1 if c is not a decimal digit character
3044 * @see u_getNumericValue
3047 U_STABLE int32_t U_EXPORT2
3048 u_charDigitValue(UChar32 c);
3051 * Returns the Unicode allocation block that contains the character.
3053 * @param c the code point to be tested
3054 * @return the block value (UBlockCode) for c
3059 U_STABLE UBlockCode U_EXPORT2
3060 ublock_getCode(UChar32 c);
3063 * Retrieve the name of a Unicode character.
3064 * Depending on <code>nameChoice</code>, the character name written
3065 * into the buffer is the "modern" name or the name that was defined
3066 * in Unicode version 1.0.
3067 * The name contains only "invariant" characters
3068 * like A-Z, 0-9, space, and '-'.
3069 * Unicode 1.0 names are only retrieved if they are different from the modern
3070 * names and if the data file contains the data for them. gennames may or may
3071 * not be called with a command line option to include 1.0 names in unames.dat.
3073 * @param code The character (code point) for which to get the name.
3074 * It must be <code>0<=code<=0x10ffff</code>.
3075 * @param nameChoice Selector for which name to get.
3076 * @param buffer Destination address for copying the name.
3077 * The name will always be zero-terminated.
3078 * If there is no name, then the buffer will be set to the empty string.
3079 * @param bufferLength <code>==sizeof(buffer)</code>
3080 * @param pErrorCode Pointer to a UErrorCode variable;
3081 * check for <code>U_SUCCESS()</code> after <code>u_charName()</code>
3083 * @return The length of the name, or 0 if there is no name for this character.
3084 * If the bufferLength is less than or equal to the length, then the buffer
3085 * contains the truncated name and the returned length indicates the full
3086 * length of the name.
3087 * The length does not include the zero-termination.
3089 * @see UCharNameChoice
3090 * @see u_charFromName
3091 * @see u_enumCharNames
3094 U_STABLE int32_t U_EXPORT2
3095 u_charName(UChar32 code, UCharNameChoice nameChoice,
3096 char *buffer, int32_t bufferLength,
3097 UErrorCode *pErrorCode);
3099 #ifndef U_HIDE_DEPRECATED_API
3101 * Returns an empty string.
3102 * Used to return the ISO 10646 comment for a character.
3103 * The Unicode ISO_Comment property is deprecated and has no values.
3105 * @param c The character (code point) for which to get the ISO comment.
3106 * It must be <code>0<=c<=0x10ffff</code>.
3107 * @param dest Destination address for copying the comment.
3108 * The comment will be zero-terminated if possible.
3109 * If there is no comment, then the buffer will be set to the empty string.
3110 * @param destCapacity <code>==sizeof(dest)</code>
3111 * @param pErrorCode Pointer to a UErrorCode variable;
3112 * check for <code>U_SUCCESS()</code> after <code>u_getISOComment()</code>
3116 * @deprecated ICU 49
3118 U_DEPRECATED int32_t U_EXPORT2
3119 u_getISOComment(UChar32 c,
3120 char *dest, int32_t destCapacity,
3121 UErrorCode *pErrorCode);
3122 #endif /* U_HIDE_DEPRECATED_API */
3125 * Find a Unicode character by its name and return its code point value.
3126 * The name is matched exactly and completely.
3127 * If the name does not correspond to a code point, <i>pErrorCode</i>
3128 * is set to <code>U_INVALID_CHAR_FOUND</code>.
3129 * A Unicode 1.0 name is matched only if it differs from the modern name.
3130 * Unicode names are all uppercase. Extended names are lowercase followed
3131 * by an uppercase hexadecimal number, and within angle brackets.
3133 * @param nameChoice Selector for which name to match.
3134 * @param name The name to match.
3135 * @param pErrorCode Pointer to a UErrorCode variable
3136 * @return The Unicode value of the code point with the given name,
3137 * or an undefined value if there is no such code point.
3139 * @see UCharNameChoice
3141 * @see u_enumCharNames
3144 U_STABLE UChar32 U_EXPORT2
3145 u_charFromName(UCharNameChoice nameChoice,
3147 UErrorCode *pErrorCode);
3150 * Type of a callback function for u_enumCharNames() that gets called
3151 * for each Unicode character with the code point value and
3152 * the character name.
3153 * If such a function returns FALSE, then the enumeration is stopped.
3155 * @param context The context pointer that was passed to u_enumCharNames().
3156 * @param code The Unicode code point for the character with this name.
3157 * @param nameChoice Selector for which kind of names is enumerated.
3158 * @param name The character's name, zero-terminated.
3159 * @param length The length of the name.
3160 * @return TRUE if the enumeration should continue, FALSE to stop it.
3162 * @see UCharNameChoice
3163 * @see u_enumCharNames
3166 typedef UBool U_CALLCONV UEnumCharNamesFn(void *context,
3168 UCharNameChoice nameChoice,
3173 * Enumerate all assigned Unicode characters between the start and limit
3174 * code points (start inclusive, limit exclusive) and call a function
3175 * for each, passing the code point value and the character name.
3176 * For Unicode 1.0 names, only those are enumerated that differ from the
3179 * @param start The first code point in the enumeration range.
3180 * @param limit One more than the last code point in the enumeration range
3181 * (the first one after the range).
3182 * @param fn The function that is to be called for each character name.
3183 * @param context An arbitrary pointer that is passed to the function.
3184 * @param nameChoice Selector for which kind of names to enumerate.
3185 * @param pErrorCode Pointer to a UErrorCode variable
3187 * @see UCharNameChoice
3188 * @see UEnumCharNamesFn
3190 * @see u_charFromName
3193 U_STABLE void U_EXPORT2
3194 u_enumCharNames(UChar32 start, UChar32 limit,
3195 UEnumCharNamesFn *fn,
3197 UCharNameChoice nameChoice,
3198 UErrorCode *pErrorCode);
3201 * Return the Unicode name for a given property, as given in the
3202 * Unicode database file PropertyAliases.txt.
3204 * In addition, this function maps the property
3205 * UCHAR_GENERAL_CATEGORY_MASK to the synthetic names "gcm" /
3206 * "General_Category_Mask". These names are not in
3207 * PropertyAliases.txt.
3209 * @param property UProperty selector other than UCHAR_INVALID_CODE.
3210 * If out of range, NULL is returned.
3212 * @param nameChoice selector for which name to get. If out of range,
3213 * NULL is returned. All properties have a long name. Most
3214 * have a short name, but some do not. Unicode allows for
3215 * additional names; if present these will be returned by
3216 * U_LONG_PROPERTY_NAME + i, where i=1, 2,...
3218 * @return a pointer to the name, or NULL if either the
3219 * property or the nameChoice is out of range. If a given
3220 * nameChoice returns NULL, then all larger values of
3221 * nameChoice will return NULL, with one exception: if NULL is
3222 * returned for U_SHORT_PROPERTY_NAME, then
3223 * U_LONG_PROPERTY_NAME (and higher) may still return a
3224 * non-NULL value. The returned pointer is valid until
3225 * u_cleanup() is called.
3228 * @see UPropertyNameChoice
3231 U_STABLE const char* U_EXPORT2
3232 u_getPropertyName(UProperty property,
3233 UPropertyNameChoice nameChoice);
3236 * Return the UProperty enum for a given property name, as specified
3237 * in the Unicode database file PropertyAliases.txt. Short, long, and
3238 * any other variants are recognized.
3240 * In addition, this function maps the synthetic names "gcm" /
3241 * "General_Category_Mask" to the property
3242 * UCHAR_GENERAL_CATEGORY_MASK. These names are not in
3243 * PropertyAliases.txt.
3245 * @param alias the property name to be matched. The name is compared
3246 * using "loose matching" as described in PropertyAliases.txt.
3248 * @return a UProperty enum, or UCHAR_INVALID_CODE if the given name
3249 * does not match any property.
3254 U_STABLE UProperty U_EXPORT2
3255 u_getPropertyEnum(const char* alias);
3258 * Return the Unicode name for a given property value, as given in the
3259 * Unicode database file PropertyValueAliases.txt.
3261 * Note: Some of the names in PropertyValueAliases.txt can only be
3262 * retrieved using UCHAR_GENERAL_CATEGORY_MASK, not
3263 * UCHAR_GENERAL_CATEGORY. These include: "C" / "Other", "L" /
3264 * "Letter", "LC" / "Cased_Letter", "M" / "Mark", "N" / "Number", "P"
3265 * / "Punctuation", "S" / "Symbol", and "Z" / "Separator".
3267 * @param property UProperty selector constant.
3268 * Must be UCHAR_BINARY_START<=which<UCHAR_BINARY_LIMIT
3269 * or UCHAR_INT_START<=which<UCHAR_INT_LIMIT
3270 * or UCHAR_MASK_START<=which<UCHAR_MASK_LIMIT.
3271 * If out of range, NULL is returned.
3273 * @param value selector for a value for the given property. If out
3274 * of range, NULL is returned. In general, valid values range
3275 * from 0 up to some maximum. There are a few exceptions:
3276 * (1.) UCHAR_BLOCK values begin at the non-zero value
3277 * UBLOCK_BASIC_LATIN. (2.) UCHAR_CANONICAL_COMBINING_CLASS
3278 * values are not contiguous and range from 0..240. (3.)
3279 * UCHAR_GENERAL_CATEGORY_MASK values are not values of
3280 * UCharCategory, but rather mask values produced by
3281 * U_GET_GC_MASK(). This allows grouped categories such as
3282 * [:L:] to be represented. Mask values range
3283 * non-contiguously from 1..U_GC_P_MASK.
3285 * @param nameChoice selector for which name to get. If out of range,
3286 * NULL is returned. All values have a long name. Most have
3287 * a short name, but some do not. Unicode allows for
3288 * additional names; if present these will be returned by
3289 * U_LONG_PROPERTY_NAME + i, where i=1, 2,...
3291 * @return a pointer to the name, or NULL if either the
3292 * property or the nameChoice is out of range. If a given
3293 * nameChoice returns NULL, then all larger values of
3294 * nameChoice will return NULL, with one exception: if NULL is
3295 * returned for U_SHORT_PROPERTY_NAME, then
3296 * U_LONG_PROPERTY_NAME (and higher) may still return a
3297 * non-NULL value. The returned pointer is valid until
3298 * u_cleanup() is called.
3301 * @see UPropertyNameChoice
3304 U_STABLE const char* U_EXPORT2
3305 u_getPropertyValueName(UProperty property,
3307 UPropertyNameChoice nameChoice);
3310 * Return the property value integer for a given value name, as
3311 * specified in the Unicode database file PropertyValueAliases.txt.
3312 * Short, long, and any other variants are recognized.
3314 * Note: Some of the names in PropertyValueAliases.txt will only be
3315 * recognized with UCHAR_GENERAL_CATEGORY_MASK, not
3316 * UCHAR_GENERAL_CATEGORY. These include: "C" / "Other", "L" /
3317 * "Letter", "LC" / "Cased_Letter", "M" / "Mark", "N" / "Number", "P"
3318 * / "Punctuation", "S" / "Symbol", and "Z" / "Separator".
3320 * @param property UProperty selector constant.
3321 * Must be UCHAR_BINARY_START<=which<UCHAR_BINARY_LIMIT
3322 * or UCHAR_INT_START<=which<UCHAR_INT_LIMIT
3323 * or UCHAR_MASK_START<=which<UCHAR_MASK_LIMIT.
3324 * If out of range, UCHAR_INVALID_CODE is returned.
3326 * @param alias the value name to be matched. The name is compared
3327 * using "loose matching" as described in
3328 * PropertyValueAliases.txt.
3330 * @return a value integer or UCHAR_INVALID_CODE if the given name
3331 * does not match any value of the given property, or if the
3332 * property is invalid. Note: UCHAR_GENERAL_CATEGORY_MASK values
3333 * are not values of UCharCategory, but rather mask values
3334 * produced by U_GET_GC_MASK(). This allows grouped
3335 * categories such as [:L:] to be represented.
3340 U_STABLE int32_t U_EXPORT2
3341 u_getPropertyValueEnum(UProperty property,
3345 * Determines if the specified character is permissible as the
3346 * first character in an identifier according to Unicode
3347 * (The Unicode Standard, Version 3.0, chapter 5.16 Identifiers).
3348 * True for characters with general categories "L" (letters) and "Nl" (letter numbers).
3350 * Same as java.lang.Character.isUnicodeIdentifierStart().
3351 * Same as UCHAR_ID_START
3353 * @param c the code point to be tested
3354 * @return TRUE if the code point may start an identifier
3356 * @see UCHAR_ID_START
3361 U_STABLE UBool U_EXPORT2
3362 u_isIDStart(UChar32 c);
3365 * Determines if the specified character is permissible
3366 * in an identifier according to Java.
3367 * True for characters with general categories "L" (letters),
3368 * "Nl" (letter numbers), "Nd" (decimal digits),
3369 * "Mc" and "Mn" (combining marks), "Pc" (connecting punctuation), and
3370 * u_isIDIgnorable(c).
3372 * Same as java.lang.Character.isUnicodeIdentifierPart().
3373 * Almost the same as Unicode's ID_Continue (UCHAR_ID_CONTINUE)
3374 * except that Unicode recommends to ignore Cf which is less than
3375 * u_isIDIgnorable(c).
3377 * @param c the code point to be tested
3378 * @return TRUE if the code point may occur in an identifier according to Java
3380 * @see UCHAR_ID_CONTINUE
3382 * @see u_isIDIgnorable
3385 U_STABLE UBool U_EXPORT2
3386 u_isIDPart(UChar32 c);
3389 * Determines if the specified character should be regarded
3390 * as an ignorable character in an identifier,
3391 * according to Java.
3392 * True for characters with general category "Cf" (format controls) as well as
3393 * non-whitespace ISO controls
3394 * (U+0000..U+0008, U+000E..U+001B, U+007F..U+009F).
3396 * Same as java.lang.Character.isIdentifierIgnorable().
3398 * Note that Unicode just recommends to ignore Cf (format controls).
3400 * @param c the code point to be tested
3401 * @return TRUE if the code point is ignorable in identifiers according to Java
3403 * @see UCHAR_DEFAULT_IGNORABLE_CODE_POINT
3408 U_STABLE UBool U_EXPORT2
3409 u_isIDIgnorable(UChar32 c);
3412 * Determines if the specified character is permissible as the
3413 * first character in a Java identifier.
3414 * In addition to u_isIDStart(c), true for characters with
3415 * general categories "Sc" (currency symbols) and "Pc" (connecting punctuation).
3417 * Same as java.lang.Character.isJavaIdentifierStart().
3419 * @param c the code point to be tested
3420 * @return TRUE if the code point may start a Java identifier
3422 * @see u_isJavaIDPart
3427 U_STABLE UBool U_EXPORT2
3428 u_isJavaIDStart(UChar32 c);
3431 * Determines if the specified character is permissible
3432 * in a Java identifier.
3433 * In addition to u_isIDPart(c), true for characters with
3434 * general category "Sc" (currency symbols).
3436 * Same as java.lang.Character.isJavaIdentifierPart().
3438 * @param c the code point to be tested
3439 * @return TRUE if the code point may occur in a Java identifier
3441 * @see u_isIDIgnorable
3442 * @see u_isJavaIDStart
3448 U_STABLE UBool U_EXPORT2
3449 u_isJavaIDPart(UChar32 c);
3452 * The given character is mapped to its lowercase equivalent according to
3453 * UnicodeData.txt; if the character has no lowercase equivalent, the character
3454 * itself is returned.
3456 * Same as java.lang.Character.toLowerCase().
3458 * This function only returns the simple, single-code point case mapping.
3459 * Full case mappings should be used whenever possible because they produce
3460 * better results by working on whole strings.
3461 * They take into account the string context and the language and can map
3462 * to a result string with a different length as appropriate.
3463 * Full case mappings are applied by the string case mapping functions,
3464 * see ustring.h and the UnicodeString class.
3465 * See also the User Guide chapter on C/POSIX migration:
3466 * http://icu-project.org/userguide/posix.html#case_mappings
3468 * @param c the code point to be mapped
3469 * @return the Simple_Lowercase_Mapping of the code point, if any;
3470 * otherwise the code point itself.
3473 U_STABLE UChar32 U_EXPORT2
3474 u_tolower(UChar32 c);
3477 * The given character is mapped to its uppercase equivalent according to UnicodeData.txt;
3478 * if the character has no uppercase equivalent, the character itself is
3481 * Same as java.lang.Character.toUpperCase().
3483 * This function only returns the simple, single-code point case mapping.
3484 * Full case mappings should be used whenever possible because they produce
3485 * better results by working on whole strings.
3486 * They take into account the string context and the language and can map
3487 * to a result string with a different length as appropriate.
3488 * Full case mappings are applied by the string case mapping functions,
3489 * see ustring.h and the UnicodeString class.
3490 * See also the User Guide chapter on C/POSIX migration:
3491 * http://icu-project.org/userguide/posix.html#case_mappings
3493 * @param c the code point to be mapped
3494 * @return the Simple_Uppercase_Mapping of the code point, if any;
3495 * otherwise the code point itself.
3498 U_STABLE UChar32 U_EXPORT2
3499 u_toupper(UChar32 c);
3502 * The given character is mapped to its titlecase equivalent
3503 * according to UnicodeData.txt;
3504 * if none is defined, the character itself is returned.
3506 * Same as java.lang.Character.toTitleCase().
3508 * This function only returns the simple, single-code point case mapping.
3509 * Full case mappings should be used whenever possible because they produce
3510 * better results by working on whole strings.
3511 * They take into account the string context and the language and can map
3512 * to a result string with a different length as appropriate.
3513 * Full case mappings are applied by the string case mapping functions,
3514 * see ustring.h and the UnicodeString class.
3515 * See also the User Guide chapter on C/POSIX migration:
3516 * http://icu-project.org/userguide/posix.html#case_mappings
3518 * @param c the code point to be mapped
3519 * @return the Simple_Titlecase_Mapping of the code point, if any;
3520 * otherwise the code point itself.
3523 U_STABLE UChar32 U_EXPORT2
3524 u_totitle(UChar32 c);
3526 /** Option value for case folding: use default mappings defined in CaseFolding.txt. @stable ICU 2.0 */
3527 #define U_FOLD_CASE_DEFAULT 0
3530 * Option value for case folding:
3532 * Use the modified set of mappings provided in CaseFolding.txt to handle dotted I
3533 * and dotless i appropriately for Turkic languages (tr, az).
3535 * Before Unicode 3.2, CaseFolding.txt contains mappings marked with 'I' that
3536 * are to be included for default mappings and
3537 * excluded for the Turkic-specific mappings.
3539 * Unicode 3.2 CaseFolding.txt instead contains mappings marked with 'T' that
3540 * are to be excluded for default mappings and
3541 * included for the Turkic-specific mappings.
3545 #define U_FOLD_CASE_EXCLUDE_SPECIAL_I 1
3548 * The given character is mapped to its case folding equivalent according to
3549 * UnicodeData.txt and CaseFolding.txt;
3550 * if the character has no case folding equivalent, the character
3551 * itself is returned.
3553 * This function only returns the simple, single-code point case mapping.
3554 * Full case mappings should be used whenever possible because they produce
3555 * better results by working on whole strings.
3556 * They take into account the string context and the language and can map
3557 * to a result string with a different length as appropriate.
3558 * Full case mappings are applied by the string case mapping functions,
3559 * see ustring.h and the UnicodeString class.
3560 * See also the User Guide chapter on C/POSIX migration:
3561 * http://icu-project.org/userguide/posix.html#case_mappings
3563 * @param c the code point to be mapped
3564 * @param options Either U_FOLD_CASE_DEFAULT or U_FOLD_CASE_EXCLUDE_SPECIAL_I
3565 * @return the Simple_Case_Folding of the code point, if any;
3566 * otherwise the code point itself.
3569 U_STABLE UChar32 U_EXPORT2
3570 u_foldCase(UChar32 c, uint32_t options);
3573 * Returns the decimal digit value of the code point in the
3576 * If the radix is not in the range <code>2<=radix<=36</code> or if the
3577 * value of <code>c</code> is not a valid digit in the specified
3578 * radix, <code>-1</code> is returned. A character is a valid digit
3579 * if at least one of the following is true:
3581 * <li>The character has a decimal digit value.
3582 * Such characters have the general category "Nd" (decimal digit numbers)
3583 * and a Numeric_Type of Decimal.
3584 * In this case the value is the character's decimal digit value.</li>
3585 * <li>The character is one of the uppercase Latin letters
3586 * <code>'A'</code> through <code>'Z'</code>.
3587 * In this case the value is <code>c-'A'+10</code>.</li>
3588 * <li>The character is one of the lowercase Latin letters
3589 * <code>'a'</code> through <code>'z'</code>.
3590 * In this case the value is <code>ch-'a'+10</code>.</li>
3591 * <li>Latin letters from both the ASCII range (0061..007A, 0041..005A)
3592 * as well as from the Fullwidth ASCII range (FF41..FF5A, FF21..FF3A)
3593 * are recognized.</li>
3596 * Same as java.lang.Character.digit().
3598 * @param ch the code point to be tested.
3599 * @param radix the radix.
3600 * @return the numeric value represented by the character in the
3602 * or -1 if there is no value or if the value exceeds the radix.
3604 * @see UCHAR_NUMERIC_TYPE
3606 * @see u_charDigitValue
3610 U_STABLE int32_t U_EXPORT2
3611 u_digit(UChar32 ch, int8_t radix);
3614 * Determines the character representation for a specific digit in
3615 * the specified radix. If the value of <code>radix</code> is not a
3616 * valid radix, or the value of <code>digit</code> is not a valid
3617 * digit in the specified radix, the null character
3618 * (<code>U+0000</code>) is returned.
3620 * The <code>radix</code> argument is valid if it is greater than or
3621 * equal to 2 and less than or equal to 36.
3622 * The <code>digit</code> argument is valid if
3623 * <code>0 <= digit < radix</code>.
3625 * If the digit is less than 10, then
3626 * <code>'0' + digit</code> is returned. Otherwise, the value
3627 * <code>'a' + digit - 10</code> is returned.
3629 * Same as java.lang.Character.forDigit().
3631 * @param digit the number to convert to a character.
3632 * @param radix the radix.
3633 * @return the <code>char</code> representation of the specified digit
3634 * in the specified radix.
3637 * @see u_charDigitValue
3641 U_STABLE UChar32 U_EXPORT2
3642 u_forDigit(int32_t digit, int8_t radix);
3645 * Get the "age" of the code point.
3646 * The "age" is the Unicode version when the code point was first
3647 * designated (as a non-character or for Private Use)
3648 * or assigned a character.
3649 * This can be useful to avoid emitting code points to receiving
3650 * processes that do not accept newer characters.
3651 * The data is from the UCD file DerivedAge.txt.
3653 * @param c The code point.
3654 * @param versionArray The Unicode version number array, to be filled in.
3658 U_STABLE void U_EXPORT2
3659 u_charAge(UChar32 c, UVersionInfo versionArray);
3662 * Gets the Unicode version information.
3663 * The version array is filled in with the version information
3664 * for the Unicode standard that is currently used by ICU.
3665 * For example, Unicode version 3.1.1 is represented as an array with
3666 * the values { 3, 1, 1, 0 }.
3668 * @param versionArray an output array that will be filled in with
3669 * the Unicode version number
3672 U_STABLE void U_EXPORT2
3673 u_getUnicodeVersion(UVersionInfo versionArray);
3675 #if !UCONFIG_NO_NORMALIZATION
3677 * Get the FC_NFKC_Closure property string for a character.
3678 * See Unicode Standard Annex #15 for details, search for "FC_NFKC_Closure"
3679 * or for "FNC": http://www.unicode.org/reports/tr15/
3681 * @param c The character (code point) for which to get the FC_NFKC_Closure string.
3682 * It must be <code>0<=c<=0x10ffff</code>.
3683 * @param dest Destination address for copying the string.
3684 * The string will be zero-terminated if possible.
3685 * If there is no FC_NFKC_Closure string,
3686 * then the buffer will be set to the empty string.
3687 * @param destCapacity <code>==sizeof(dest)</code>
3688 * @param pErrorCode Pointer to a UErrorCode variable.
3689 * @return The length of the string, or 0 if there is no FC_NFKC_Closure string for this character.
3690 * If the destCapacity is less than or equal to the length, then the buffer
3691 * contains the truncated name and the returned length indicates the full
3692 * length of the name.
3693 * The length does not include the zero-termination.
3697 U_STABLE int32_t U_EXPORT2
3698 u_getFC_NFKC_Closure(UChar32 c, UChar *dest, int32_t destCapacity, UErrorCode *pErrorCode);