1// © 2016 and later: Unicode, Inc. and others.
2// License & terms of use: http://www.unicode.org/copyright.html
3/*
4**********************************************************************
5* Copyright (C) 1997-2016, International Business Machines
6* Corporation and others. All Rights Reserved.
7**********************************************************************
8*
9* File UCHAR.H
10*
11* Modification History:
12*
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******************************************************************************
23*/
24
25#ifndef UCHAR_H
26#define UCHAR_H
27
28#include "unicode/utypes.h"
29#include "unicode/stringoptions.h"
30
31U_CDECL_BEGIN
32
33/*==========================================================================*/
34/* Unicode version number */
35/*==========================================================================*/
36/**
37 * Unicode version number, default for the current ICU version.
38 * The actual Unicode Character Database (UCD) data is stored in uprops.dat
39 * and may be generated from UCD files from a different Unicode version.
40 * Call u_getUnicodeVersion to get the actual Unicode version of the data.
41 *
42 * @see u_getUnicodeVersion
43 * @stable ICU 2.0
44 */
45#define U_UNICODE_VERSION "10.0"
46
47/**
48 * \file
49 * \brief C API: Unicode Properties
50 *
51 * This C API provides low-level access to the Unicode Character Database.
52 * In addition to raw property values, some convenience functions calculate
53 * derived properties, for example for Java-style programming.
54 *
55 * Unicode assigns each code point (not just assigned character) values for
56 * many properties.
57 * Most of them are simple boolean flags, or constants from a small enumerated list.
58 * For some properties, values are strings or other relatively more complex types.
59 *
60 * For more information see
61 * "About the Unicode Character Database" (http://www.unicode.org/ucd/)
62 * and the ICU User Guide chapter on Properties (http://icu-project.org/userguide/properties.html).
63 *
64 * Many functions are designed to match java.lang.Character functions.
65 * See the individual function documentation,
66 * and see the JDK 1.4 java.lang.Character documentation
67 * at http://java.sun.com/j2se/1.4/docs/api/java/lang/Character.html
68 *
69 * There are also functions that provide easy migration from C/POSIX functions
70 * like isblank(). Their use is generally discouraged because the C/POSIX
71 * standards do not define their semantics beyond the ASCII range, which means
72 * that different implementations exhibit very different behavior.
73 * Instead, Unicode properties should be used directly.
74 *
75 * There are also only a few, broad C/POSIX character classes, and they tend
76 * to be used for conflicting purposes. For example, the "isalpha()" class
77 * is sometimes used to determine word boundaries, while a more sophisticated
78 * approach would at least distinguish initial letters from continuation
79 * characters (the latter including combining marks).
80 * (In ICU, BreakIterator is the most sophisticated API for word boundaries.)
81 * Another example: There is no "istitle()" class for titlecase characters.
82 *
83 * ICU 3.4 and later provides API access for all twelve C/POSIX character classes.
84 * ICU implements them according to the Standard Recommendations in
85 * Annex C: Compatibility Properties of UTS #18 Unicode Regular Expressions
86 * (http://www.unicode.org/reports/tr18/#Compatibility_Properties).
87 *
88 * API access for C/POSIX character classes is as follows:
89 * - alpha: u_isUAlphabetic(c) or u_hasBinaryProperty(c, UCHAR_ALPHABETIC)
90 * - lower: u_isULowercase(c) or u_hasBinaryProperty(c, UCHAR_LOWERCASE)
91 * - upper: u_isUUppercase(c) or u_hasBinaryProperty(c, UCHAR_UPPERCASE)
92 * - punct: u_ispunct(c)
93 * - digit: u_isdigit(c) or u_charType(c)==U_DECIMAL_DIGIT_NUMBER
94 * - xdigit: u_isxdigit(c) or u_hasBinaryProperty(c, UCHAR_POSIX_XDIGIT)
95 * - alnum: u_hasBinaryProperty(c, UCHAR_POSIX_ALNUM)
96 * - space: u_isUWhiteSpace(c) or u_hasBinaryProperty(c, UCHAR_WHITE_SPACE)
97 * - blank: u_isblank(c) or u_hasBinaryProperty(c, UCHAR_POSIX_BLANK)
98 * - cntrl: u_charType(c)==U_CONTROL_CHAR
99 * - graph: u_hasBinaryProperty(c, UCHAR_POSIX_GRAPH)
100 * - print: u_hasBinaryProperty(c, UCHAR_POSIX_PRINT)
101 *
102 * Note: Some of the u_isxyz() functions in uchar.h predate, and do not match,
103 * the Standard Recommendations in UTS #18. Instead, they match Java
104 * functions according to their API documentation.
105 *
106 * \htmlonly
107 * The C/POSIX character classes are also available in UnicodeSet patterns,
108 * using patterns like [:graph:] or \p{graph}.
109 * \endhtmlonly
110 *
111 * Note: There are several ICU whitespace functions.
112 * Comparison:
113 * - u_isUWhiteSpace=UCHAR_WHITE_SPACE: Unicode White_Space property;
114 * most of general categories "Z" (separators) + most whitespace ISO controls
115 * (including no-break spaces, but excluding IS1..IS4 and ZWSP)
116 * - u_isWhitespace: Java isWhitespace; Z + whitespace ISO controls but excluding no-break spaces
117 * - u_isJavaSpaceChar: Java isSpaceChar; just Z (including no-break spaces)
118 * - u_isspace: Z + whitespace ISO controls (including no-break spaces)
119 * - u_isblank: "horizontal spaces" = TAB + Zs - ZWSP
120 */
121
122/**
123 * Constants.
124 */
125
126/** The lowest Unicode code point value. Code points are non-negative. @stable ICU 2.0 */
127#define UCHAR_MIN_VALUE 0
128
129/**
130 * The highest Unicode code point value (scalar value) according to
131 * The Unicode Standard. This is a 21-bit value (20.1 bits, rounded up).
132 * For a single character, UChar32 is a simple type that can hold any code point value.
133 *
134 * @see UChar32
135 * @stable ICU 2.0
136 */
137#define UCHAR_MAX_VALUE 0x10ffff
138
139/**
140 * Get a single-bit bit set (a flag) from a bit number 0..31.
141 * @stable ICU 2.1
142 */
143#define U_MASK(x) ((uint32_t)1<<(x))
144
145/**
146 * Selection constants for Unicode properties.
147 * These constants are used in functions like u_hasBinaryProperty to select
148 * one of the Unicode properties.
149 *
150 * The properties APIs are intended to reflect Unicode properties as defined
151 * in the Unicode Character Database (UCD) and Unicode Technical Reports (UTR).
152 *
153 * For details about the properties see
154 * UAX #44: Unicode Character Database (http://www.unicode.org/reports/tr44/).
155 *
156 * Important: If ICU is built with UCD files from Unicode versions below, e.g., 3.2,
157 * then properties marked with "new in Unicode 3.2" are not or not fully available.
158 * Check u_getUnicodeVersion to be sure.
159 *
160 * @see u_hasBinaryProperty
161 * @see u_getIntPropertyValue
162 * @see u_getUnicodeVersion
163 * @stable ICU 2.1
164 */
165typedef enum UProperty {
166 /*
167 * Note: UProperty constants are parsed by preparseucd.py.
168 * It matches lines like
169 * UCHAR_<Unicode property name>=<integer>,
170 */
171
172 /* Note: Place UCHAR_ALPHABETIC before UCHAR_BINARY_START so that
173 debuggers display UCHAR_ALPHABETIC as the symbolic name for 0,
174 rather than UCHAR_BINARY_START. Likewise for other *_START
175 identifiers. */
176
177 /** Binary property Alphabetic. Same as u_isUAlphabetic, different from u_isalpha.
178 Lu+Ll+Lt+Lm+Lo+Nl+Other_Alphabetic @stable ICU 2.1 */
179 UCHAR_ALPHABETIC=0,
180 /** First constant for binary Unicode properties. @stable ICU 2.1 */
181 UCHAR_BINARY_START=UCHAR_ALPHABETIC,
182 /** Binary property ASCII_Hex_Digit. 0-9 A-F a-f @stable ICU 2.1 */
183 UCHAR_ASCII_HEX_DIGIT=1,
184 /** Binary property Bidi_Control.
185 Format controls which have specific functions
186 in the Bidi Algorithm. @stable ICU 2.1 */
187 UCHAR_BIDI_CONTROL=2,
188 /** Binary property Bidi_Mirrored.
189 Characters that may change display in RTL text.
190 Same as u_isMirrored.
191 See Bidi Algorithm, UTR 9. @stable ICU 2.1 */
192 UCHAR_BIDI_MIRRORED=3,
193 /** Binary property Dash. Variations of dashes. @stable ICU 2.1 */
194 UCHAR_DASH=4,
195 /** Binary property Default_Ignorable_Code_Point (new in Unicode 3.2).
196 Ignorable in most processing.
197 <2060..206F, FFF0..FFFB, E0000..E0FFF>+Other_Default_Ignorable_Code_Point+(Cf+Cc+Cs-White_Space) @stable ICU 2.1 */
198 UCHAR_DEFAULT_IGNORABLE_CODE_POINT=5,
199 /** Binary property Deprecated (new in Unicode 3.2).
200 The usage of deprecated characters is strongly discouraged. @stable ICU 2.1 */
201 UCHAR_DEPRECATED=6,
202 /** Binary property Diacritic. Characters that linguistically modify
203 the meaning of another character to which they apply. @stable ICU 2.1 */
204 UCHAR_DIACRITIC=7,
205 /** Binary property Extender.
206 Extend the value or shape of a preceding alphabetic character,
207 e.g., length and iteration marks. @stable ICU 2.1 */
208 UCHAR_EXTENDER=8,
209 /** Binary property Full_Composition_Exclusion.
210 CompositionExclusions.txt+Singleton Decompositions+
211 Non-Starter Decompositions. @stable ICU 2.1 */
212 UCHAR_FULL_COMPOSITION_EXCLUSION=9,
213 /** Binary property Grapheme_Base (new in Unicode 3.2).
214 For programmatic determination of grapheme cluster boundaries.
215 [0..10FFFF]-Cc-Cf-Cs-Co-Cn-Zl-Zp-Grapheme_Link-Grapheme_Extend-CGJ @stable ICU 2.1 */
216 UCHAR_GRAPHEME_BASE=10,
217 /** Binary property Grapheme_Extend (new in Unicode 3.2).
218 For programmatic determination of grapheme cluster boundaries.
219 Me+Mn+Mc+Other_Grapheme_Extend-Grapheme_Link-CGJ @stable ICU 2.1 */
220 UCHAR_GRAPHEME_EXTEND=11,
221 /** Binary property Grapheme_Link (new in Unicode 3.2).
222 For programmatic determination of grapheme cluster boundaries. @stable ICU 2.1 */
223 UCHAR_GRAPHEME_LINK=12,
224 /** Binary property Hex_Digit.
225 Characters commonly used for hexadecimal numbers. @stable ICU 2.1 */
226 UCHAR_HEX_DIGIT=13,
227 /** Binary property Hyphen. Dashes used to mark connections
228 between pieces of words, plus the Katakana middle dot. @stable ICU 2.1 */
229 UCHAR_HYPHEN=14,
230 /** Binary property ID_Continue.
231 Characters that can continue an identifier.
232 DerivedCoreProperties.txt also says "NOTE: Cf characters should be filtered out."
233 ID_Start+Mn+Mc+Nd+Pc @stable ICU 2.1 */
234 UCHAR_ID_CONTINUE=15,
235 /** Binary property ID_Start.
236 Characters that can start an identifier.
237 Lu+Ll+Lt+Lm+Lo+Nl @stable ICU 2.1 */
238 UCHAR_ID_START=16,
239 /** Binary property Ideographic.
240 CJKV ideographs. @stable ICU 2.1 */
241 UCHAR_IDEOGRAPHIC=17,
242 /** Binary property IDS_Binary_Operator (new in Unicode 3.2).
243 For programmatic determination of
244 Ideographic Description Sequences. @stable ICU 2.1 */
245 UCHAR_IDS_BINARY_OPERATOR=18,
246 /** Binary property IDS_Trinary_Operator (new in Unicode 3.2).
247 For programmatic determination of
248 Ideographic Description Sequences. @stable ICU 2.1 */
249 UCHAR_IDS_TRINARY_OPERATOR=19,
250 /** Binary property Join_Control.
251 Format controls for cursive joining and ligation. @stable ICU 2.1 */
252 UCHAR_JOIN_CONTROL=20,
253 /** Binary property Logical_Order_Exception (new in Unicode 3.2).
254 Characters that do not use logical order and
255 require special handling in most processing. @stable ICU 2.1 */
256 UCHAR_LOGICAL_ORDER_EXCEPTION=21,
257 /** Binary property Lowercase. Same as u_isULowercase, different from u_islower.
258 Ll+Other_Lowercase @stable ICU 2.1 */
259 UCHAR_LOWERCASE=22,
260 /** Binary property Math. Sm+Other_Math @stable ICU 2.1 */
261 UCHAR_MATH=23,
262 /** Binary property Noncharacter_Code_Point.
263 Code points that are explicitly defined as illegal
264 for the encoding of characters. @stable ICU 2.1 */
265 UCHAR_NONCHARACTER_CODE_POINT=24,
266 /** Binary property Quotation_Mark. @stable ICU 2.1 */
267 UCHAR_QUOTATION_MARK=25,
268 /** Binary property Radical (new in Unicode 3.2).
269 For programmatic determination of
270 Ideographic Description Sequences. @stable ICU 2.1 */
271 UCHAR_RADICAL=26,
272 /** Binary property Soft_Dotted (new in Unicode 3.2).
273 Characters with a "soft dot", like i or j.
274 An accent placed on these characters causes
275 the dot to disappear. @stable ICU 2.1 */
276 UCHAR_SOFT_DOTTED=27,
277 /** Binary property Terminal_Punctuation.
278 Punctuation characters that generally mark
279 the end of textual units. @stable ICU 2.1 */
280 UCHAR_TERMINAL_PUNCTUATION=28,
281 /** Binary property Unified_Ideograph (new in Unicode 3.2).
282 For programmatic determination of
283 Ideographic Description Sequences. @stable ICU 2.1 */
284 UCHAR_UNIFIED_IDEOGRAPH=29,
285 /** Binary property Uppercase. Same as u_isUUppercase, different from u_isupper.
286 Lu+Other_Uppercase @stable ICU 2.1 */
287 UCHAR_UPPERCASE=30,
288 /** Binary property White_Space.
289 Same as u_isUWhiteSpace, different from u_isspace and u_isWhitespace.
290 Space characters+TAB+CR+LF-ZWSP-ZWNBSP @stable ICU 2.1 */
291 UCHAR_WHITE_SPACE=31,
292 /** Binary property XID_Continue.
293 ID_Continue modified to allow closure under
294 normalization forms NFKC and NFKD. @stable ICU 2.1 */
295 UCHAR_XID_CONTINUE=32,
296 /** Binary property XID_Start. ID_Start modified to allow
297 closure under normalization forms NFKC and NFKD. @stable ICU 2.1 */
298 UCHAR_XID_START=33,
299 /** Binary property Case_Sensitive. Either the source of a case
300 mapping or _in_ the target of a case mapping. Not the same as
301 the general category Cased_Letter. @stable ICU 2.6 */
302 UCHAR_CASE_SENSITIVE=34,
303 /** Binary property STerm (new in Unicode 4.0.1).
304 Sentence Terminal. Used in UAX #29: Text Boundaries
305 (http://www.unicode.org/reports/tr29/)
306 @stable ICU 3.0 */
307 UCHAR_S_TERM=35,
308 /** Binary property Variation_Selector (new in Unicode 4.0.1).
309 Indicates all those characters that qualify as Variation Selectors.
310 For details on the behavior of these characters,
311 see StandardizedVariants.html and 15.6 Variation Selectors.
312 @stable ICU 3.0 */
313 UCHAR_VARIATION_SELECTOR=36,
314 /** Binary property NFD_Inert.
315 ICU-specific property for characters that are inert under NFD,
316 i.e., they do not interact with adjacent characters.
317 See the documentation for the Normalizer2 class and the
318 Normalizer2::isInert() method.
319 @stable ICU 3.0 */
320 UCHAR_NFD_INERT=37,
321 /** Binary property NFKD_Inert.
322 ICU-specific property for characters that are inert under NFKD,
323 i.e., they do not interact with adjacent characters.
324 See the documentation for the Normalizer2 class and the
325 Normalizer2::isInert() method.
326 @stable ICU 3.0 */
327 UCHAR_NFKD_INERT=38,
328 /** Binary property NFC_Inert.
329 ICU-specific property for characters that are inert under NFC,
330 i.e., they do not interact with adjacent characters.
331 See the documentation for the Normalizer2 class and the
332 Normalizer2::isInert() method.
333 @stable ICU 3.0 */
334 UCHAR_NFC_INERT=39,
335 /** Binary property NFKC_Inert.
336 ICU-specific property for characters that are inert under NFKC,
337 i.e., they do not interact with adjacent characters.
338 See the documentation for the Normalizer2 class and the
339 Normalizer2::isInert() method.
340 @stable ICU 3.0 */
341 UCHAR_NFKC_INERT=40,
342 /** Binary Property Segment_Starter.
343 ICU-specific property for characters that are starters in terms of
344 Unicode normalization and combining character sequences.
345 They have ccc=0 and do not occur in non-initial position of the
346 canonical decomposition of any character
347 (like a-umlaut in NFD and a Jamo T in an NFD(Hangul LVT)).
348 ICU uses this property for segmenting a string for generating a set of
349 canonically equivalent strings, e.g. for canonical closure while
350 processing collation tailoring rules.
351 @stable ICU 3.0 */
352 UCHAR_SEGMENT_STARTER=41,
353 /** Binary property Pattern_Syntax (new in Unicode 4.1).
354 See UAX #31 Identifier and Pattern Syntax
355 (http://www.unicode.org/reports/tr31/)
356 @stable ICU 3.4 */
357 UCHAR_PATTERN_SYNTAX=42,
358 /** Binary property Pattern_White_Space (new in Unicode 4.1).
359 See UAX #31 Identifier and Pattern Syntax
360 (http://www.unicode.org/reports/tr31/)
361 @stable ICU 3.4 */
362 UCHAR_PATTERN_WHITE_SPACE=43,
363 /** Binary property alnum (a C/POSIX character class).
364 Implemented according to the UTS #18 Annex C Standard Recommendation.
365 See the uchar.h file documentation.
366 @stable ICU 3.4 */
367 UCHAR_POSIX_ALNUM=44,
368 /** Binary property blank (a C/POSIX character class).
369 Implemented according to the UTS #18 Annex C Standard Recommendation.
370 See the uchar.h file documentation.
371 @stable ICU 3.4 */
372 UCHAR_POSIX_BLANK=45,
373 /** Binary property graph (a C/POSIX character class).
374 Implemented according to the UTS #18 Annex C Standard Recommendation.
375 See the uchar.h file documentation.
376 @stable ICU 3.4 */
377 UCHAR_POSIX_GRAPH=46,
378 /** Binary property print (a C/POSIX character class).
379 Implemented according to the UTS #18 Annex C Standard Recommendation.
380 See the uchar.h file documentation.
381 @stable ICU 3.4 */
382 UCHAR_POSIX_PRINT=47,
383 /** Binary property xdigit (a C/POSIX character class).
384 Implemented according to the UTS #18 Annex C Standard Recommendation.
385 See the uchar.h file documentation.
386 @stable ICU 3.4 */
387 UCHAR_POSIX_XDIGIT=48,
388 /** Binary property Cased. For Lowercase, Uppercase and Titlecase characters. @stable ICU 4.4 */
389 UCHAR_CASED=49,
390 /** Binary property Case_Ignorable. Used in context-sensitive case mappings. @stable ICU 4.4 */
391 UCHAR_CASE_IGNORABLE=50,
392 /** Binary property Changes_When_Lowercased. @stable ICU 4.4 */
393 UCHAR_CHANGES_WHEN_LOWERCASED=51,
394 /** Binary property Changes_When_Uppercased. @stable ICU 4.4 */
395 UCHAR_CHANGES_WHEN_UPPERCASED=52,
396 /** Binary property Changes_When_Titlecased. @stable ICU 4.4 */
397 UCHAR_CHANGES_WHEN_TITLECASED=53,
398 /** Binary property Changes_When_Casefolded. @stable ICU 4.4 */
399 UCHAR_CHANGES_WHEN_CASEFOLDED=54,
400 /** Binary property Changes_When_Casemapped. @stable ICU 4.4 */
401 UCHAR_CHANGES_WHEN_CASEMAPPED=55,
402 /** Binary property Changes_When_NFKC_Casefolded. @stable ICU 4.4 */
403 UCHAR_CHANGES_WHEN_NFKC_CASEFOLDED=56,
404 /**
405 * Binary property Emoji.
406 * See http://www.unicode.org/reports/tr51/#Emoji_Properties
407 *
408 * @stable ICU 57
409 */
410 UCHAR_EMOJI=57,
411 /**
412 * Binary property Emoji_Presentation.
413 * See http://www.unicode.org/reports/tr51/#Emoji_Properties
414 *
415 * @stable ICU 57
416 */
417 UCHAR_EMOJI_PRESENTATION=58,
418 /**
419 * Binary property Emoji_Modifier.
420 * See http://www.unicode.org/reports/tr51/#Emoji_Properties
421 *
422 * @stable ICU 57
423 */
424 UCHAR_EMOJI_MODIFIER=59,
425 /**
426 * Binary property Emoji_Modifier_Base.
427 * See http://www.unicode.org/reports/tr51/#Emoji_Properties
428 *
429 * @stable ICU 57
430 */
431 UCHAR_EMOJI_MODIFIER_BASE=60,
432 /**
433 * Binary property Emoji_Component.
434 * See http://www.unicode.org/reports/tr51/#Emoji_Properties
435 *
436 * @stable ICU 60
437 */
438 UCHAR_EMOJI_COMPONENT=61,
439 /**
440 * Binary property Regional_Indicator.
441 * @stable ICU 60
442 */
443 UCHAR_REGIONAL_INDICATOR=62,
444 /**
445 * Binary property Prepended_Concatenation_Mark.
446 * @stable ICU 60
447 */
448 UCHAR_PREPENDED_CONCATENATION_MARK=63,
449#ifndef U_HIDE_DEPRECATED_API
450 /**
451 * One more than the last constant for binary Unicode properties.
452 * @deprecated ICU 58 The numeric value may change over time, see ICU ticket #12420.
453 */
454 UCHAR_BINARY_LIMIT,
455#endif // U_HIDE_DEPRECATED_API
456
457 /** Enumerated property Bidi_Class.
458 Same as u_charDirection, returns UCharDirection values. @stable ICU 2.2 */
459 UCHAR_BIDI_CLASS=0x1000,
460 /** First constant for enumerated/integer Unicode properties. @stable ICU 2.2 */
461 UCHAR_INT_START=UCHAR_BIDI_CLASS,
462 /** Enumerated property Block.
463 Same as ublock_getCode, returns UBlockCode values. @stable ICU 2.2 */
464 UCHAR_BLOCK=0x1001,
465 /** Enumerated property Canonical_Combining_Class.
466 Same as u_getCombiningClass, returns 8-bit numeric values. @stable ICU 2.2 */
467 UCHAR_CANONICAL_COMBINING_CLASS=0x1002,
468 /** Enumerated property Decomposition_Type.
469 Returns UDecompositionType values. @stable ICU 2.2 */
470 UCHAR_DECOMPOSITION_TYPE=0x1003,
471 /** Enumerated property East_Asian_Width.
472 See http://www.unicode.org/reports/tr11/
473 Returns UEastAsianWidth values. @stable ICU 2.2 */
474 UCHAR_EAST_ASIAN_WIDTH=0x1004,
475 /** Enumerated property General_Category.
476 Same as u_charType, returns UCharCategory values. @stable ICU 2.2 */
477 UCHAR_GENERAL_CATEGORY=0x1005,
478 /** Enumerated property Joining_Group.
479 Returns UJoiningGroup values. @stable ICU 2.2 */
480 UCHAR_JOINING_GROUP=0x1006,
481 /** Enumerated property Joining_Type.
482 Returns UJoiningType values. @stable ICU 2.2 */
483 UCHAR_JOINING_TYPE=0x1007,
484 /** Enumerated property Line_Break.
485 Returns ULineBreak values. @stable ICU 2.2 */
486 UCHAR_LINE_BREAK=0x1008,
487 /** Enumerated property Numeric_Type.
488 Returns UNumericType values. @stable ICU 2.2 */
489 UCHAR_NUMERIC_TYPE=0x1009,
490 /** Enumerated property Script.
491 Same as uscript_getScript, returns UScriptCode values. @stable ICU 2.2 */
492 UCHAR_SCRIPT=0x100A,
493 /** Enumerated property Hangul_Syllable_Type, new in Unicode 4.
494 Returns UHangulSyllableType values. @stable ICU 2.6 */
495 UCHAR_HANGUL_SYLLABLE_TYPE=0x100B,
496 /** Enumerated property NFD_Quick_Check.
497 Returns UNormalizationCheckResult values. @stable ICU 3.0 */
498 UCHAR_NFD_QUICK_CHECK=0x100C,
499 /** Enumerated property NFKD_Quick_Check.
500 Returns UNormalizationCheckResult values. @stable ICU 3.0 */
501 UCHAR_NFKD_QUICK_CHECK=0x100D,
502 /** Enumerated property NFC_Quick_Check.
503 Returns UNormalizationCheckResult values. @stable ICU 3.0 */
504 UCHAR_NFC_QUICK_CHECK=0x100E,
505 /** Enumerated property NFKC_Quick_Check.
506 Returns UNormalizationCheckResult values. @stable ICU 3.0 */
507 UCHAR_NFKC_QUICK_CHECK=0x100F,
508 /** Enumerated property Lead_Canonical_Combining_Class.
509 ICU-specific property for the ccc of the first code point
510 of the decomposition, or lccc(c)=ccc(NFD(c)[0]).
511 Useful for checking for canonically ordered text;
512 see UNORM_FCD and http://www.unicode.org/notes/tn5/#FCD .
513 Returns 8-bit numeric values like UCHAR_CANONICAL_COMBINING_CLASS. @stable ICU 3.0 */
514 UCHAR_LEAD_CANONICAL_COMBINING_CLASS=0x1010,
515 /** Enumerated property Trail_Canonical_Combining_Class.
516 ICU-specific property for the ccc of the last code point
517 of the decomposition, or tccc(c)=ccc(NFD(c)[last]).
518 Useful for checking for canonically ordered text;
519 see UNORM_FCD and http://www.unicode.org/notes/tn5/#FCD .
520 Returns 8-bit numeric values like UCHAR_CANONICAL_COMBINING_CLASS. @stable ICU 3.0 */
521 UCHAR_TRAIL_CANONICAL_COMBINING_CLASS=0x1011,
522 /** Enumerated property Grapheme_Cluster_Break (new in Unicode 4.1).
523 Used in UAX #29: Text Boundaries
524 (http://www.unicode.org/reports/tr29/)
525 Returns UGraphemeClusterBreak values. @stable ICU 3.4 */
526 UCHAR_GRAPHEME_CLUSTER_BREAK=0x1012,
527 /** Enumerated property Sentence_Break (new in Unicode 4.1).
528 Used in UAX #29: Text Boundaries
529 (http://www.unicode.org/reports/tr29/)
530 Returns USentenceBreak values. @stable ICU 3.4 */
531 UCHAR_SENTENCE_BREAK=0x1013,
532 /** Enumerated property Word_Break (new in Unicode 4.1).
533 Used in UAX #29: Text Boundaries
534 (http://www.unicode.org/reports/tr29/)
535 Returns UWordBreakValues values. @stable ICU 3.4 */
536 UCHAR_WORD_BREAK=0x1014,
537 /** Enumerated property Bidi_Paired_Bracket_Type (new in Unicode 6.3).
538 Used in UAX #9: Unicode Bidirectional Algorithm
539 (http://www.unicode.org/reports/tr9/)
540 Returns UBidiPairedBracketType values. @stable ICU 52 */
541 UCHAR_BIDI_PAIRED_BRACKET_TYPE=0x1015,
542#ifndef U_HIDE_DEPRECATED_API
543 /**
544 * One more than the last constant for enumerated/integer Unicode properties.
545 * @deprecated ICU 58 The numeric value may change over time, see ICU ticket #12420.
546 */
547 UCHAR_INT_LIMIT=0x1016,
548#endif // U_HIDE_DEPRECATED_API
549
550 /** Bitmask property General_Category_Mask.
551 This is the General_Category property returned as a bit mask.
552 When used in u_getIntPropertyValue(c), same as U_MASK(u_charType(c)),
553 returns bit masks for UCharCategory values where exactly one bit is set.
554 When used with u_getPropertyValueName() and u_getPropertyValueEnum(),
555 a multi-bit mask is used for sets of categories like "Letters".
556 Mask values should be cast to uint32_t.
557 @stable ICU 2.4 */
558 UCHAR_GENERAL_CATEGORY_MASK=0x2000,
559 /** First constant for bit-mask Unicode properties. @stable ICU 2.4 */
560 UCHAR_MASK_START=UCHAR_GENERAL_CATEGORY_MASK,
561#ifndef U_HIDE_DEPRECATED_API
562 /**
563 * One more than the last constant for bit-mask Unicode properties.
564 * @deprecated ICU 58 The numeric value may change over time, see ICU ticket #12420.
565 */
566 UCHAR_MASK_LIMIT=0x2001,
567#endif // U_HIDE_DEPRECATED_API
568
569 /** Double property Numeric_Value.
570 Corresponds to u_getNumericValue. @stable ICU 2.4 */
571 UCHAR_NUMERIC_VALUE=0x3000,
572 /** First constant for double Unicode properties. @stable ICU 2.4 */
573 UCHAR_DOUBLE_START=UCHAR_NUMERIC_VALUE,
574#ifndef U_HIDE_DEPRECATED_API
575 /**
576 * One more than the last constant for double Unicode properties.
577 * @deprecated ICU 58 The numeric value may change over time, see ICU ticket #12420.
578 */
579 UCHAR_DOUBLE_LIMIT=0x3001,
580#endif // U_HIDE_DEPRECATED_API
581
582 /** String property Age.
583 Corresponds to u_charAge. @stable ICU 2.4 */
584 UCHAR_AGE=0x4000,
585 /** First constant for string Unicode properties. @stable ICU 2.4 */
586 UCHAR_STRING_START=UCHAR_AGE,
587 /** String property Bidi_Mirroring_Glyph.
588 Corresponds to u_charMirror. @stable ICU 2.4 */
589 UCHAR_BIDI_MIRRORING_GLYPH=0x4001,
590 /** String property Case_Folding.
591 Corresponds to u_strFoldCase in ustring.h. @stable ICU 2.4 */
592 UCHAR_CASE_FOLDING=0x4002,
593#ifndef U_HIDE_DEPRECATED_API
594 /** Deprecated string property ISO_Comment.
595 Corresponds to u_getISOComment. @deprecated ICU 49 */
596 UCHAR_ISO_COMMENT=0x4003,
597#endif /* U_HIDE_DEPRECATED_API */
598 /** String property Lowercase_Mapping.
599 Corresponds to u_strToLower in ustring.h. @stable ICU 2.4 */
600 UCHAR_LOWERCASE_MAPPING=0x4004,
601 /** String property Name.
602 Corresponds to u_charName. @stable ICU 2.4 */
603 UCHAR_NAME=0x4005,
604 /** String property Simple_Case_Folding.
605 Corresponds to u_foldCase. @stable ICU 2.4 */
606 UCHAR_SIMPLE_CASE_FOLDING=0x4006,
607 /** String property Simple_Lowercase_Mapping.
608 Corresponds to u_tolower. @stable ICU 2.4 */
609 UCHAR_SIMPLE_LOWERCASE_MAPPING=0x4007,
610 /** String property Simple_Titlecase_Mapping.
611 Corresponds to u_totitle. @stable ICU 2.4 */
612 UCHAR_SIMPLE_TITLECASE_MAPPING=0x4008,
613 /** String property Simple_Uppercase_Mapping.
614 Corresponds to u_toupper. @stable ICU 2.4 */
615 UCHAR_SIMPLE_UPPERCASE_MAPPING=0x4009,
616 /** String property Titlecase_Mapping.
617 Corresponds to u_strToTitle in ustring.h. @stable ICU 2.4 */
618 UCHAR_TITLECASE_MAPPING=0x400A,
619#ifndef U_HIDE_DEPRECATED_API
620 /** String property Unicode_1_Name.
621 This property is of little practical value.
622 Beginning with ICU 49, ICU APIs return an empty string for this property.
623 Corresponds to u_charName(U_UNICODE_10_CHAR_NAME). @deprecated ICU 49 */
624 UCHAR_UNICODE_1_NAME=0x400B,
625#endif /* U_HIDE_DEPRECATED_API */
626 /** String property Uppercase_Mapping.
627 Corresponds to u_strToUpper in ustring.h. @stable ICU 2.4 */
628 UCHAR_UPPERCASE_MAPPING=0x400C,
629 /** String property Bidi_Paired_Bracket (new in Unicode 6.3).
630 Corresponds to u_getBidiPairedBracket. @stable ICU 52 */
631 UCHAR_BIDI_PAIRED_BRACKET=0x400D,
632#ifndef U_HIDE_DEPRECATED_API
633 /**
634 * One more than the last constant for string Unicode properties.
635 * @deprecated ICU 58 The numeric value may change over time, see ICU ticket #12420.
636 */
637 UCHAR_STRING_LIMIT=0x400E,
638#endif // U_HIDE_DEPRECATED_API
639
640 /** Miscellaneous property Script_Extensions (new in Unicode 6.0).
641 Some characters are commonly used in multiple scripts.
642 For more information, see UAX #24: http://www.unicode.org/reports/tr24/.
643 Corresponds to uscript_hasScript and uscript_getScriptExtensions in uscript.h.
644 @stable ICU 4.6 */
645 UCHAR_SCRIPT_EXTENSIONS=0x7000,
646 /** First constant for Unicode properties with unusual value types. @stable ICU 4.6 */
647 UCHAR_OTHER_PROPERTY_START=UCHAR_SCRIPT_EXTENSIONS,
648#ifndef U_HIDE_DEPRECATED_API
649 /**
650 * One more than the last constant for Unicode properties with unusual value types.
651 * @deprecated ICU 58 The numeric value may change over time, see ICU ticket #12420.
652 */
653 UCHAR_OTHER_PROPERTY_LIMIT=0x7001,
654#endif // U_HIDE_DEPRECATED_API
655
656 /** Represents a nonexistent or invalid property or property value. @stable ICU 2.4 */
657 UCHAR_INVALID_CODE = -1
658} UProperty;
659
660/**
661 * Data for enumerated Unicode general category types.
662 * See http://www.unicode.org/Public/UNIDATA/UnicodeData.html .
663 * @stable ICU 2.0
664 */
665typedef enum UCharCategory
666{
667 /*
668 * Note: UCharCategory constants and their API comments are parsed by preparseucd.py.
669 * It matches pairs of lines like
670 * / ** <Unicode 2-letter General_Category value> comment... * /
671 * U_<[A-Z_]+> = <integer>,
672 */
673
674 /** Non-category for unassigned and non-character code points. @stable ICU 2.0 */
675 U_UNASSIGNED = 0,
676 /** Cn "Other, Not Assigned (no characters in [UnicodeData.txt] have this property)" (same as U_UNASSIGNED!) @stable ICU 2.0 */
677 U_GENERAL_OTHER_TYPES = 0,
678 /** Lu @stable ICU 2.0 */
679 U_UPPERCASE_LETTER = 1,
680 /** Ll @stable ICU 2.0 */
681 U_LOWERCASE_LETTER = 2,
682 /** Lt @stable ICU 2.0 */
683 U_TITLECASE_LETTER = 3,
684 /** Lm @stable ICU 2.0 */
685 U_MODIFIER_LETTER = 4,
686 /** Lo @stable ICU 2.0 */
687 U_OTHER_LETTER = 5,
688 /** Mn @stable ICU 2.0 */
689 U_NON_SPACING_MARK = 6,
690 /** Me @stable ICU 2.0 */
691 U_ENCLOSING_MARK = 7,
692 /** Mc @stable ICU 2.0 */
693 U_COMBINING_SPACING_MARK = 8,
694 /** Nd @stable ICU 2.0 */
695 U_DECIMAL_DIGIT_NUMBER = 9,
696 /** Nl @stable ICU 2.0 */
697 U_LETTER_NUMBER = 10,
698 /** No @stable ICU 2.0 */
699 U_OTHER_NUMBER = 11,
700 /** Zs @stable ICU 2.0 */
701 U_SPACE_SEPARATOR = 12,
702 /** Zl @stable ICU 2.0 */
703 U_LINE_SEPARATOR = 13,
704 /** Zp @stable ICU 2.0 */
705 U_PARAGRAPH_SEPARATOR = 14,
706 /** Cc @stable ICU 2.0 */
707 U_CONTROL_CHAR = 15,
708 /** Cf @stable ICU 2.0 */
709 U_FORMAT_CHAR = 16,
710 /** Co @stable ICU 2.0 */
711 U_PRIVATE_USE_CHAR = 17,
712 /** Cs @stable ICU 2.0 */
713 U_SURROGATE = 18,
714 /** Pd @stable ICU 2.0 */
715 U_DASH_PUNCTUATION = 19,
716 /** Ps @stable ICU 2.0 */
717 U_START_PUNCTUATION = 20,
718 /** Pe @stable ICU 2.0 */
719 U_END_PUNCTUATION = 21,
720 /** Pc @stable ICU 2.0 */
721 U_CONNECTOR_PUNCTUATION = 22,
722 /** Po @stable ICU 2.0 */
723 U_OTHER_PUNCTUATION = 23,
724 /** Sm @stable ICU 2.0 */
725 U_MATH_SYMBOL = 24,
726 /** Sc @stable ICU 2.0 */
727 U_CURRENCY_SYMBOL = 25,
728 /** Sk @stable ICU 2.0 */
729 U_MODIFIER_SYMBOL = 26,
730 /** So @stable ICU 2.0 */
731 U_OTHER_SYMBOL = 27,
732 /** Pi @stable ICU 2.0 */
733 U_INITIAL_PUNCTUATION = 28,
734 /** Pf @stable ICU 2.0 */
735 U_FINAL_PUNCTUATION = 29,
736 /**
737 * One higher than the last enum UCharCategory constant.
738 * This numeric value is stable (will not change), see
739 * http://www.unicode.org/policies/stability_policy.html#Property_Value
740 *
741 * @stable ICU 2.0
742 */
743 U_CHAR_CATEGORY_COUNT
744} UCharCategory;
745
746/**
747 * U_GC_XX_MASK constants are bit flags corresponding to Unicode
748 * general category values.
749 * For each category, the nth bit is set if the numeric value of the
750 * corresponding UCharCategory constant is n.
751 *
752 * There are also some U_GC_Y_MASK constants for groups of general categories
753 * like L for all letter categories.
754 *
755 * @see u_charType
756 * @see U_GET_GC_MASK
757 * @see UCharCategory
758 * @stable ICU 2.1
759 */
760#define U_GC_CN_MASK U_MASK(U_GENERAL_OTHER_TYPES)
761
762/** Mask constant for a UCharCategory. @stable ICU 2.1 */
763#define U_GC_LU_MASK U_MASK(U_UPPERCASE_LETTER)
764/** Mask constant for a UCharCategory. @stable ICU 2.1 */
765#define U_GC_LL_MASK U_MASK(U_LOWERCASE_LETTER)
766/** Mask constant for a UCharCategory. @stable ICU 2.1 */
767#define U_GC_LT_MASK U_MASK(U_TITLECASE_LETTER)
768/** Mask constant for a UCharCategory. @stable ICU 2.1 */
769#define U_GC_LM_MASK U_MASK(U_MODIFIER_LETTER)
770/** Mask constant for a UCharCategory. @stable ICU 2.1 */
771#define U_GC_LO_MASK U_MASK(U_OTHER_LETTER)
772
773/** Mask constant for a UCharCategory. @stable ICU 2.1 */
774#define U_GC_MN_MASK U_MASK(U_NON_SPACING_MARK)
775/** Mask constant for a UCharCategory. @stable ICU 2.1 */
776#define U_GC_ME_MASK U_MASK(U_ENCLOSING_MARK)
777/** Mask constant for a UCharCategory. @stable ICU 2.1 */
778#define U_GC_MC_MASK U_MASK(U_COMBINING_SPACING_MARK)
779
780/** Mask constant for a UCharCategory. @stable ICU 2.1 */
781#define U_GC_ND_MASK U_MASK(U_DECIMAL_DIGIT_NUMBER)
782/** Mask constant for a UCharCategory. @stable ICU 2.1 */
783#define U_GC_NL_MASK U_MASK(U_LETTER_NUMBER)
784/** Mask constant for a UCharCategory. @stable ICU 2.1 */
785#define U_GC_NO_MASK U_MASK(U_OTHER_NUMBER)
786
787/** Mask constant for a UCharCategory. @stable ICU 2.1 */
788#define U_GC_ZS_MASK U_MASK(U_SPACE_SEPARATOR)
789/** Mask constant for a UCharCategory. @stable ICU 2.1 */
790#define U_GC_ZL_MASK U_MASK(U_LINE_SEPARATOR)
791/** Mask constant for a UCharCategory. @stable ICU 2.1 */
792#define U_GC_ZP_MASK U_MASK(U_PARAGRAPH_SEPARATOR)
793
794/** Mask constant for a UCharCategory. @stable ICU 2.1 */
795#define U_GC_CC_MASK U_MASK(U_CONTROL_CHAR)
796/** Mask constant for a UCharCategory. @stable ICU 2.1 */
797#define U_GC_CF_MASK U_MASK(U_FORMAT_CHAR)
798/** Mask constant for a UCharCategory. @stable ICU 2.1 */
799#define U_GC_CO_MASK U_MASK(U_PRIVATE_USE_CHAR)
800/** Mask constant for a UCharCategory. @stable ICU 2.1 */
801#define U_GC_CS_MASK U_MASK(U_SURROGATE)
802
803/** Mask constant for a UCharCategory. @stable ICU 2.1 */
804#define U_GC_PD_MASK U_MASK(U_DASH_PUNCTUATION)
805/** Mask constant for a UCharCategory. @stable ICU 2.1 */
806#define U_GC_PS_MASK U_MASK(U_START_PUNCTUATION)
807/** Mask constant for a UCharCategory. @stable ICU 2.1 */
808#define U_GC_PE_MASK U_MASK(U_END_PUNCTUATION)
809/** Mask constant for a UCharCategory. @stable ICU 2.1 */
810#define U_GC_PC_MASK U_MASK(U_CONNECTOR_PUNCTUATION)
811/** Mask constant for a UCharCategory. @stable ICU 2.1 */
812#define U_GC_PO_MASK U_MASK(U_OTHER_PUNCTUATION)
813
814/** Mask constant for a UCharCategory. @stable ICU 2.1 */
815#define U_GC_SM_MASK U_MASK(U_MATH_SYMBOL)
816/** Mask constant for a UCharCategory. @stable ICU 2.1 */
817#define U_GC_SC_MASK U_MASK(U_CURRENCY_SYMBOL)
818/** Mask constant for a UCharCategory. @stable ICU 2.1 */
819#define U_GC_SK_MASK U_MASK(U_MODIFIER_SYMBOL)
820/** Mask constant for a UCharCategory. @stable ICU 2.1 */
821#define U_GC_SO_MASK U_MASK(U_OTHER_SYMBOL)
822
823/** Mask constant for a UCharCategory. @stable ICU 2.1 */
824#define U_GC_PI_MASK U_MASK(U_INITIAL_PUNCTUATION)
825/** Mask constant for a UCharCategory. @stable ICU 2.1 */
826#define U_GC_PF_MASK U_MASK(U_FINAL_PUNCTUATION)
827
828
829/** Mask constant for multiple UCharCategory bits (L Letters). @stable ICU 2.1 */
830#define U_GC_L_MASK \
831 (U_GC_LU_MASK|U_GC_LL_MASK|U_GC_LT_MASK|U_GC_LM_MASK|U_GC_LO_MASK)
832
833/** Mask constant for multiple UCharCategory bits (LC Cased Letters). @stable ICU 2.1 */
834#define U_GC_LC_MASK \
835 (U_GC_LU_MASK|U_GC_LL_MASK|U_GC_LT_MASK)
836
837/** Mask constant for multiple UCharCategory bits (M Marks). @stable ICU 2.1 */
838#define U_GC_M_MASK (U_GC_MN_MASK|U_GC_ME_MASK|U_GC_MC_MASK)
839
840/** Mask constant for multiple UCharCategory bits (N Numbers). @stable ICU 2.1 */
841#define U_GC_N_MASK (U_GC_ND_MASK|U_GC_NL_MASK|U_GC_NO_MASK)
842
843/** Mask constant for multiple UCharCategory bits (Z Separators). @stable ICU 2.1 */
844#define U_GC_Z_MASK (U_GC_ZS_MASK|U_GC_ZL_MASK|U_GC_ZP_MASK)
845
846/** Mask constant for multiple UCharCategory bits (C Others). @stable ICU 2.1 */
847#define U_GC_C_MASK \
848 (U_GC_CN_MASK|U_GC_CC_MASK|U_GC_CF_MASK|U_GC_CO_MASK|U_GC_CS_MASK)
849
850/** Mask constant for multiple UCharCategory bits (P Punctuation). @stable ICU 2.1 */
851#define U_GC_P_MASK \
852 (U_GC_PD_MASK|U_GC_PS_MASK|U_GC_PE_MASK|U_GC_PC_MASK|U_GC_PO_MASK| \
853 U_GC_PI_MASK|U_GC_PF_MASK)
854
855/** Mask constant for multiple UCharCategory bits (S Symbols). @stable ICU 2.1 */
856#define U_GC_S_MASK (U_GC_SM_MASK|U_GC_SC_MASK|U_GC_SK_MASK|U_GC_SO_MASK)
857
858/**
859 * This specifies the language directional property of a character set.
860 * @stable ICU 2.0
861 */
862typedef enum UCharDirection {
863 /*
864 * Note: UCharDirection constants and their API comments are parsed by preparseucd.py.
865 * It matches pairs of lines like
866 * / ** <Unicode 1..3-letter Bidi_Class value> comment... * /
867 * U_<[A-Z_]+> = <integer>,
868 */
869
870 /** L @stable ICU 2.0 */
871 U_LEFT_TO_RIGHT = 0,
872 /** R @stable ICU 2.0 */
873 U_RIGHT_TO_LEFT = 1,
874 /** EN @stable ICU 2.0 */
875 U_EUROPEAN_NUMBER = 2,
876 /** ES @stable ICU 2.0 */
877 U_EUROPEAN_NUMBER_SEPARATOR = 3,
878 /** ET @stable ICU 2.0 */
879 U_EUROPEAN_NUMBER_TERMINATOR = 4,
880 /** AN @stable ICU 2.0 */
881 U_ARABIC_NUMBER = 5,
882 /** CS @stable ICU 2.0 */
883 U_COMMON_NUMBER_SEPARATOR = 6,
884 /** B @stable ICU 2.0 */
885 U_BLOCK_SEPARATOR = 7,
886 /** S @stable ICU 2.0 */
887 U_SEGMENT_SEPARATOR = 8,
888 /** WS @stable ICU 2.0 */
889 U_WHITE_SPACE_NEUTRAL = 9,
890 /** ON @stable ICU 2.0 */
891 U_OTHER_NEUTRAL = 10,
892 /** LRE @stable ICU 2.0 */
893 U_LEFT_TO_RIGHT_EMBEDDING = 11,
894 /** LRO @stable ICU 2.0 */
895 U_LEFT_TO_RIGHT_OVERRIDE = 12,
896 /** AL @stable ICU 2.0 */
897 U_RIGHT_TO_LEFT_ARABIC = 13,
898 /** RLE @stable ICU 2.0 */
899 U_RIGHT_TO_LEFT_EMBEDDING = 14,
900 /** RLO @stable ICU 2.0 */
901 U_RIGHT_TO_LEFT_OVERRIDE = 15,
902 /** PDF @stable ICU 2.0 */
903 U_POP_DIRECTIONAL_FORMAT = 16,
904 /** NSM @stable ICU 2.0 */
905 U_DIR_NON_SPACING_MARK = 17,
906 /** BN @stable ICU 2.0 */
907 U_BOUNDARY_NEUTRAL = 18,
908 /** FSI @stable ICU 52 */
909 U_FIRST_STRONG_ISOLATE = 19,
910 /** LRI @stable ICU 52 */
911 U_LEFT_TO_RIGHT_ISOLATE = 20,
912 /** RLI @stable ICU 52 */
913 U_RIGHT_TO_LEFT_ISOLATE = 21,
914 /** PDI @stable ICU 52 */
915 U_POP_DIRECTIONAL_ISOLATE = 22,
916#ifndef U_HIDE_DEPRECATED_API
917 /**
918 * One more than the highest UCharDirection value.
919 * The highest value is available via u_getIntPropertyMaxValue(UCHAR_BIDI_CLASS).
920 *
921 * @deprecated ICU 58 The numeric value may change over time, see ICU ticket #12420.
922 */
923 U_CHAR_DIRECTION_COUNT
924#endif // U_HIDE_DEPRECATED_API
925} UCharDirection;
926
927/**
928 * Bidi Paired Bracket Type constants.
929 *
930 * @see UCHAR_BIDI_PAIRED_BRACKET_TYPE
931 * @stable ICU 52
932 */
933typedef enum UBidiPairedBracketType {
934 /*
935 * Note: UBidiPairedBracketType constants are parsed by preparseucd.py.
936 * It matches lines like
937 * U_BPT_<Unicode Bidi_Paired_Bracket_Type value name>
938 */
939
940 /** Not a paired bracket. @stable ICU 52 */
941 U_BPT_NONE,
942 /** Open paired bracket. @stable ICU 52 */
943 U_BPT_OPEN,
944 /** Close paired bracket. @stable ICU 52 */
945 U_BPT_CLOSE,
946#ifndef U_HIDE_DEPRECATED_API
947 /**
948 * One more than the highest normal UBidiPairedBracketType value.
949 * The highest value is available via u_getIntPropertyMaxValue(UCHAR_BIDI_PAIRED_BRACKET_TYPE).
950 *
951 * @deprecated ICU 58 The numeric value may change over time, see ICU ticket #12420.
952 */
953 U_BPT_COUNT /* 3 */
954#endif // U_HIDE_DEPRECATED_API
955} UBidiPairedBracketType;
956
957/**
958 * Constants for Unicode blocks, see the Unicode Data file Blocks.txt
959 * @stable ICU 2.0
960 */
961enum UBlockCode {
962 /*
963 * Note: UBlockCode constants are parsed by preparseucd.py.
964 * It matches lines like
965 * UBLOCK_<Unicode Block value name> = <integer>,
966 */
967
968 /** New No_Block value in Unicode 4. @stable ICU 2.6 */
969 UBLOCK_NO_BLOCK = 0, /*[none]*/ /* Special range indicating No_Block */
970
971 /** @stable ICU 2.0 */
972 UBLOCK_BASIC_LATIN = 1, /*[0000]*/
973
974 /** @stable ICU 2.0 */
975 UBLOCK_LATIN_1_SUPPLEMENT=2, /*[0080]*/
976
977 /** @stable ICU 2.0 */
978 UBLOCK_LATIN_EXTENDED_A =3, /*[0100]*/
979
980 /** @stable ICU 2.0 */
981 UBLOCK_LATIN_EXTENDED_B =4, /*[0180]*/
982
983 /** @stable ICU 2.0 */
984 UBLOCK_IPA_EXTENSIONS =5, /*[0250]*/
985
986 /** @stable ICU 2.0 */
987 UBLOCK_SPACING_MODIFIER_LETTERS =6, /*[02B0]*/
988
989 /** @stable ICU 2.0 */
990 UBLOCK_COMBINING_DIACRITICAL_MARKS =7, /*[0300]*/
991
992 /**
993 * Unicode 3.2 renames this block to "Greek and Coptic".
994 * @stable ICU 2.0
995 */
996 UBLOCK_GREEK =8, /*[0370]*/
997
998 /** @stable ICU 2.0 */
999 UBLOCK_CYRILLIC =9, /*[0400]*/
1000
1001 /** @stable ICU 2.0 */
1002 UBLOCK_ARMENIAN =10, /*[0530]*/
1003
1004 /** @stable ICU 2.0 */
1005 UBLOCK_HEBREW =11, /*[0590]*/
1006
1007 /** @stable ICU 2.0 */
1008 UBLOCK_ARABIC =12, /*[0600]*/
1009
1010 /** @stable ICU 2.0 */
1011 UBLOCK_SYRIAC =13, /*[0700]*/
1012
1013 /** @stable ICU 2.0 */
1014 UBLOCK_THAANA =14, /*[0780]*/
1015
1016 /** @stable ICU 2.0 */
1017 UBLOCK_DEVANAGARI =15, /*[0900]*/
1018
1019 /** @stable ICU 2.0 */
1020 UBLOCK_BENGALI =16, /*[0980]*/
1021
1022 /** @stable ICU 2.0 */
1023 UBLOCK_GURMUKHI =17, /*[0A00]*/
1024
1025 /** @stable ICU 2.0 */
1026 UBLOCK_GUJARATI =18, /*[0A80]*/
1027
1028 /** @stable ICU 2.0 */
1029 UBLOCK_ORIYA =19, /*[0B00]*/
1030
1031 /** @stable ICU 2.0 */
1032 UBLOCK_TAMIL =20, /*[0B80]*/
1033
1034 /** @stable ICU 2.0 */
1035 UBLOCK_TELUGU =21, /*[0C00]*/
1036
1037 /** @stable ICU 2.0 */
1038 UBLOCK_KANNADA =22, /*[0C80]*/
1039
1040 /** @stable ICU 2.0 */
1041 UBLOCK_MALAYALAM =23, /*[0D00]*/
1042
1043 /** @stable ICU 2.0 */
1044 UBLOCK_SINHALA =24, /*[0D80]*/
1045
1046 /** @stable ICU 2.0 */
1047 UBLOCK_THAI =25, /*[0E00]*/
1048
1049 /** @stable ICU 2.0 */
1050 UBLOCK_LAO =26, /*[0E80]*/
1051
1052 /** @stable ICU 2.0 */
1053 UBLOCK_TIBETAN =27, /*[0F00]*/
1054
1055 /** @stable ICU 2.0 */
1056 UBLOCK_MYANMAR =28, /*[1000]*/
1057
1058 /** @stable ICU 2.0 */
1059 UBLOCK_GEORGIAN =29, /*[10A0]*/
1060
1061 /** @stable ICU 2.0 */
1062 UBLOCK_HANGUL_JAMO =30, /*[1100]*/
1063
1064 /** @stable ICU 2.0 */
1065 UBLOCK_ETHIOPIC =31, /*[1200]*/
1066
1067 /** @stable ICU 2.0 */
1068 UBLOCK_CHEROKEE =32, /*[13A0]*/
1069
1070 /** @stable ICU 2.0 */
1071 UBLOCK_UNIFIED_CANADIAN_ABORIGINAL_SYLLABICS =33, /*[1400]*/
1072
1073 /** @stable ICU 2.0 */
1074 UBLOCK_OGHAM =34, /*[1680]*/
1075
1076 /** @stable ICU 2.0 */
1077 UBLOCK_RUNIC =35, /*[16A0]*/
1078
1079 /** @stable ICU 2.0 */
1080 UBLOCK_KHMER =36, /*[1780]*/
1081
1082 /** @stable ICU 2.0 */
1083 UBLOCK_MONGOLIAN =37, /*[1800]*/
1084
1085 /** @stable ICU 2.0 */
1086 UBLOCK_LATIN_EXTENDED_ADDITIONAL =38, /*[1E00]*/
1087
1088 /** @stable ICU 2.0 */
1089 UBLOCK_GREEK_EXTENDED =39, /*[1F00]*/
1090
1091 /** @stable ICU 2.0 */
1092 UBLOCK_GENERAL_PUNCTUATION =40, /*[2000]*/
1093
1094 /** @stable ICU 2.0 */
1095 UBLOCK_SUPERSCRIPTS_AND_SUBSCRIPTS =41, /*[2070]*/
1096
1097 /** @stable ICU 2.0 */
1098 UBLOCK_CURRENCY_SYMBOLS =42, /*[20A0]*/
1099
1100 /**
1101 * Unicode 3.2 renames this block to "Combining Diacritical Marks for Symbols".
1102 * @stable ICU 2.0
1103 */
1104 UBLOCK_COMBINING_MARKS_FOR_SYMBOLS =43, /*[20D0]*/
1105
1106 /** @stable ICU 2.0 */
1107 UBLOCK_LETTERLIKE_SYMBOLS =44, /*[2100]*/
1108
1109 /** @stable ICU 2.0 */
1110 UBLOCK_NUMBER_FORMS =45, /*[2150]*/
1111
1112 /** @stable ICU 2.0 */
1113 UBLOCK_ARROWS =46, /*[2190]*/
1114
1115 /** @stable ICU 2.0 */
1116 UBLOCK_MATHEMATICAL_OPERATORS =47, /*[2200]*/
1117
1118 /** @stable ICU 2.0 */
1119 UBLOCK_MISCELLANEOUS_TECHNICAL =48, /*[2300]*/
1120
1121 /** @stable ICU 2.0 */
1122 UBLOCK_CONTROL_PICTURES =49, /*[2400]*/
1123
1124 /** @stable ICU 2.0 */
1125 UBLOCK_OPTICAL_CHARACTER_RECOGNITION =50, /*[2440]*/
1126
1127 /** @stable ICU 2.0 */
1128 UBLOCK_ENCLOSED_ALPHANUMERICS =51, /*[2460]*/
1129
1130 /** @stable ICU 2.0 */
1131 UBLOCK_BOX_DRAWING =52, /*[2500]*/
1132
1133 /** @stable ICU 2.0 */
1134 UBLOCK_BLOCK_ELEMENTS =53, /*[2580]*/
1135
1136 /** @stable ICU 2.0 */
1137 UBLOCK_GEOMETRIC_SHAPES =54, /*[25A0]*/
1138
1139 /** @stable ICU 2.0 */
1140 UBLOCK_MISCELLANEOUS_SYMBOLS =55, /*[2600]*/
1141
1142 /** @stable ICU 2.0 */
1143 UBLOCK_DINGBATS =56, /*[2700]*/
1144
1145 /** @stable ICU 2.0 */
1146 UBLOCK_BRAILLE_PATTERNS =57, /*[2800]*/
1147
1148 /** @stable ICU 2.0 */
1149 UBLOCK_CJK_RADICALS_SUPPLEMENT =58, /*[2E80]*/
1150
1151 /** @stable ICU 2.0 */
1152 UBLOCK_KANGXI_RADICALS =59, /*[2F00]*/
1153
1154 /** @stable ICU 2.0 */
1155 UBLOCK_IDEOGRAPHIC_DESCRIPTION_CHARACTERS =60, /*[2FF0]*/
1156
1157 /** @stable ICU 2.0 */
1158 UBLOCK_CJK_SYMBOLS_AND_PUNCTUATION =61, /*[3000]*/
1159
1160 /** @stable ICU 2.0 */
1161 UBLOCK_HIRAGANA =62, /*[3040]*/
1162
1163 /** @stable ICU 2.0 */
1164 UBLOCK_KATAKANA =63, /*[30A0]*/
1165
1166 /** @stable ICU 2.0 */
1167 UBLOCK_BOPOMOFO =64, /*[3100]*/
1168
1169 /** @stable ICU 2.0 */
1170 UBLOCK_HANGUL_COMPATIBILITY_JAMO =65, /*[3130]*/
1171
1172 /** @stable ICU 2.0 */
1173 UBLOCK_KANBUN =66, /*[3190]*/
1174
1175 /** @stable ICU 2.0 */
1176 UBLOCK_BOPOMOFO_EXTENDED =67, /*[31A0]*/
1177
1178 /** @stable ICU 2.0 */
1179 UBLOCK_ENCLOSED_CJK_LETTERS_AND_MONTHS =68, /*[3200]*/
1180
1181 /** @stable ICU 2.0 */
1182 UBLOCK_CJK_COMPATIBILITY =69, /*[3300]*/
1183
1184 /** @stable ICU 2.0 */
1185 UBLOCK_CJK_UNIFIED_IDEOGRAPHS_EXTENSION_A =70, /*[3400]*/
1186
1187 /** @stable ICU 2.0 */
1188 UBLOCK_CJK_UNIFIED_IDEOGRAPHS =71, /*[4E00]*/
1189
1190 /** @stable ICU 2.0 */
1191 UBLOCK_YI_SYLLABLES =72, /*[A000]*/
1192
1193 /** @stable ICU 2.0 */
1194 UBLOCK_YI_RADICALS =73, /*[A490]*/
1195
1196 /** @stable ICU 2.0 */
1197 UBLOCK_HANGUL_SYLLABLES =74, /*[AC00]*/
1198
1199 /** @stable ICU 2.0 */
1200 UBLOCK_HIGH_SURROGATES =75, /*[D800]*/
1201
1202 /** @stable ICU 2.0 */
1203 UBLOCK_HIGH_PRIVATE_USE_SURROGATES =76, /*[DB80]*/
1204
1205 /** @stable ICU 2.0 */
1206 UBLOCK_LOW_SURROGATES =77, /*[DC00]*/
1207
1208 /**
1209 * Same as UBLOCK_PRIVATE_USE.
1210 * Until Unicode 3.1.1, the corresponding block name was "Private Use",
1211 * and multiple code point ranges had this block.
1212 * Unicode 3.2 renames the block for the BMP PUA to "Private Use Area" and
1213 * adds separate blocks for the supplementary PUAs.
1214 *
1215 * @stable ICU 2.0
1216 */
1217 UBLOCK_PRIVATE_USE_AREA =78, /*[E000]*/
1218 /**
1219 * Same as UBLOCK_PRIVATE_USE_AREA.
1220 * Until Unicode 3.1.1, the corresponding block name was "Private Use",
1221 * and multiple code point ranges had this block.
1222 * Unicode 3.2 renames the block for the BMP PUA to "Private Use Area" and
1223 * adds separate blocks for the supplementary PUAs.
1224 *
1225 * @stable ICU 2.0
1226 */
1227 UBLOCK_PRIVATE_USE = UBLOCK_PRIVATE_USE_AREA,
1228
1229 /** @stable ICU 2.0 */
1230 UBLOCK_CJK_COMPATIBILITY_IDEOGRAPHS =79, /*[F900]*/
1231
1232 /** @stable ICU 2.0 */
1233 UBLOCK_ALPHABETIC_PRESENTATION_FORMS =80, /*[FB00]*/
1234
1235 /** @stable ICU 2.0 */
1236 UBLOCK_ARABIC_PRESENTATION_FORMS_A =81, /*[FB50]*/
1237
1238 /** @stable ICU 2.0 */
1239 UBLOCK_COMBINING_HALF_MARKS =82, /*[FE20]*/
1240
1241 /** @stable ICU 2.0 */
1242 UBLOCK_CJK_COMPATIBILITY_FORMS =83, /*[FE30]*/
1243
1244 /** @stable ICU 2.0 */
1245 UBLOCK_SMALL_FORM_VARIANTS =84, /*[FE50]*/
1246
1247 /** @stable ICU 2.0 */
1248 UBLOCK_ARABIC_PRESENTATION_FORMS_B =85, /*[FE70]*/
1249
1250 /** @stable ICU 2.0 */
1251 UBLOCK_SPECIALS =86, /*[FFF0]*/
1252
1253 /** @stable ICU 2.0 */
1254 UBLOCK_HALFWIDTH_AND_FULLWIDTH_FORMS =87, /*[FF00]*/
1255
1256 /* New blocks in Unicode 3.1 */
1257
1258 /** @stable ICU 2.0 */
1259 UBLOCK_OLD_ITALIC = 88, /*[10300]*/
1260 /** @stable ICU 2.0 */
1261 UBLOCK_GOTHIC = 89, /*[10330]*/
1262 /** @stable ICU 2.0 */
1263 UBLOCK_DESERET = 90, /*[10400]*/
1264 /** @stable ICU 2.0 */
1265 UBLOCK_BYZANTINE_MUSICAL_SYMBOLS = 91, /*[1D000]*/
1266 /** @stable ICU 2.0 */
1267 UBLOCK_MUSICAL_SYMBOLS = 92, /*[1D100]*/
1268 /** @stable ICU 2.0 */
1269 UBLOCK_MATHEMATICAL_ALPHANUMERIC_SYMBOLS = 93, /*[1D400]*/
1270 /** @stable ICU 2.0 */
1271 UBLOCK_CJK_UNIFIED_IDEOGRAPHS_EXTENSION_B = 94, /*[20000]*/
1272 /** @stable ICU 2.0 */
1273 UBLOCK_CJK_COMPATIBILITY_IDEOGRAPHS_SUPPLEMENT = 95, /*[2F800]*/
1274 /** @stable ICU 2.0 */
1275 UBLOCK_TAGS = 96, /*[E0000]*/
1276
1277 /* New blocks in Unicode 3.2 */
1278
1279 /** @stable ICU 3.0 */
1280 UBLOCK_CYRILLIC_SUPPLEMENT = 97, /*[0500]*/
1281 /**
1282 * Unicode 4.0.1 renames the "Cyrillic Supplementary" block to "Cyrillic Supplement".
1283 * @stable ICU 2.2
1284 */
1285 UBLOCK_CYRILLIC_SUPPLEMENTARY = UBLOCK_CYRILLIC_SUPPLEMENT,
1286 /** @stable ICU 2.2 */
1287 UBLOCK_TAGALOG = 98, /*[1700]*/
1288 /** @stable ICU 2.2 */
1289 UBLOCK_HANUNOO = 99, /*[1720]*/
1290 /** @stable ICU 2.2 */
1291 UBLOCK_BUHID = 100, /*[1740]*/
1292 /** @stable ICU 2.2 */
1293 UBLOCK_TAGBANWA = 101, /*[1760]*/
1294 /** @stable ICU 2.2 */
1295 UBLOCK_MISCELLANEOUS_MATHEMATICAL_SYMBOLS_A = 102, /*[27C0]*/
1296 /** @stable ICU 2.2 */
1297 UBLOCK_SUPPLEMENTAL_ARROWS_A = 103, /*[27F0]*/
1298 /** @stable ICU 2.2 */
1299 UBLOCK_SUPPLEMENTAL_ARROWS_B = 104, /*[2900]*/
1300 /** @stable ICU 2.2 */
1301 UBLOCK_MISCELLANEOUS_MATHEMATICAL_SYMBOLS_B = 105, /*[2980]*/
1302 /** @stable ICU 2.2 */
1303 UBLOCK_SUPPLEMENTAL_MATHEMATICAL_OPERATORS = 106, /*[2A00]*/
1304 /** @stable ICU 2.2 */
1305 UBLOCK_KATAKANA_PHONETIC_EXTENSIONS = 107, /*[31F0]*/
1306 /** @stable ICU 2.2 */
1307 UBLOCK_VARIATION_SELECTORS = 108, /*[FE00]*/
1308 /** @stable ICU 2.2 */
1309 UBLOCK_SUPPLEMENTARY_PRIVATE_USE_AREA_A = 109, /*[F0000]*/
1310 /** @stable ICU 2.2 */
1311 UBLOCK_SUPPLEMENTARY_PRIVATE_USE_AREA_B = 110, /*[100000]*/
1312
1313 /* New blocks in Unicode 4 */
1314
1315 /** @stable ICU 2.6 */
1316 UBLOCK_LIMBU = 111, /*[1900]*/
1317 /** @stable ICU 2.6 */
1318 UBLOCK_TAI_LE = 112, /*[1950]*/
1319 /** @stable ICU 2.6 */
1320 UBLOCK_KHMER_SYMBOLS = 113, /*[19E0]*/
1321 /** @stable ICU 2.6 */
1322 UBLOCK_PHONETIC_EXTENSIONS = 114, /*[1D00]*/
1323 /** @stable ICU 2.6 */
1324 UBLOCK_MISCELLANEOUS_SYMBOLS_AND_ARROWS = 115, /*[2B00]*/
1325 /** @stable ICU 2.6 */
1326 UBLOCK_YIJING_HEXAGRAM_SYMBOLS = 116, /*[4DC0]*/
1327 /** @stable ICU 2.6 */
1328 UBLOCK_LINEAR_B_SYLLABARY = 117, /*[10000]*/
1329 /** @stable ICU 2.6 */
1330 UBLOCK_LINEAR_B_IDEOGRAMS = 118, /*[10080]*/
1331 /** @stable ICU 2.6 */
1332 UBLOCK_AEGEAN_NUMBERS = 119, /*[10100]*/
1333 /** @stable ICU 2.6 */
1334 UBLOCK_UGARITIC = 120, /*[10380]*/
1335 /** @stable ICU 2.6 */
1336 UBLOCK_SHAVIAN = 121, /*[10450]*/
1337 /** @stable ICU 2.6 */
1338 UBLOCK_OSMANYA = 122, /*[10480]*/
1339 /** @stable ICU 2.6 */
1340 UBLOCK_CYPRIOT_SYLLABARY = 123, /*[10800]*/
1341 /** @stable ICU 2.6 */
1342 UBLOCK_TAI_XUAN_JING_SYMBOLS = 124, /*[1D300]*/
1343 /** @stable ICU 2.6 */
1344 UBLOCK_VARIATION_SELECTORS_SUPPLEMENT = 125, /*[E0100]*/
1345
1346 /* New blocks in Unicode 4.1 */
1347
1348 /** @stable ICU 3.4 */
1349 UBLOCK_ANCIENT_GREEK_MUSICAL_NOTATION = 126, /*[1D200]*/
1350 /** @stable ICU 3.4 */
1351 UBLOCK_ANCIENT_GREEK_NUMBERS = 127, /*[10140]*/
1352 /** @stable ICU 3.4 */
1353 UBLOCK_ARABIC_SUPPLEMENT = 128, /*[0750]*/
1354 /** @stable ICU 3.4 */
1355 UBLOCK_BUGINESE = 129, /*[1A00]*/
1356 /** @stable ICU 3.4 */
1357 UBLOCK_CJK_STROKES = 130, /*[31C0]*/
1358 /** @stable ICU 3.4 */
1359 UBLOCK_COMBINING_DIACRITICAL_MARKS_SUPPLEMENT = 131, /*[1DC0]*/
1360 /** @stable ICU 3.4 */
1361 UBLOCK_COPTIC = 132, /*[2C80]*/
1362 /** @stable ICU 3.4 */
1363 UBLOCK_ETHIOPIC_EXTENDED = 133, /*[2D80]*/
1364 /** @stable ICU 3.4 */
1365 UBLOCK_ETHIOPIC_SUPPLEMENT = 134, /*[1380]*/
1366 /** @stable ICU 3.4 */
1367 UBLOCK_GEORGIAN_SUPPLEMENT = 135, /*[2D00]*/
1368 /** @stable ICU 3.4 */
1369 UBLOCK_GLAGOLITIC = 136, /*[2C00]*/
1370 /** @stable ICU 3.4 */
1371 UBLOCK_KHAROSHTHI = 137, /*[10A00]*/
1372 /** @stable ICU 3.4 */
1373 UBLOCK_MODIFIER_TONE_LETTERS = 138, /*[A700]*/
1374 /** @stable ICU 3.4 */
1375 UBLOCK_NEW_TAI_LUE = 139, /*[1980]*/
1376 /** @stable ICU 3.4 */
1377 UBLOCK_OLD_PERSIAN = 140, /*[103A0]*/
1378 /** @stable ICU 3.4 */
1379 UBLOCK_PHONETIC_EXTENSIONS_SUPPLEMENT = 141, /*[1D80]*/
1380 /** @stable ICU 3.4 */
1381 UBLOCK_SUPPLEMENTAL_PUNCTUATION = 142, /*[2E00]*/
1382 /** @stable ICU 3.4 */
1383 UBLOCK_SYLOTI_NAGRI = 143, /*[A800]*/
1384 /** @stable ICU 3.4 */
1385 UBLOCK_TIFINAGH = 144, /*[2D30]*/
1386 /** @stable ICU 3.4 */
1387 UBLOCK_VERTICAL_FORMS = 145, /*[FE10]*/
1388
1389 /* New blocks in Unicode 5.0 */
1390
1391 /** @stable ICU 3.6 */
1392 UBLOCK_NKO = 146, /*[07C0]*/
1393 /** @stable ICU 3.6 */
1394 UBLOCK_BALINESE = 147, /*[1B00]*/
1395 /** @stable ICU 3.6 */
1396 UBLOCK_LATIN_EXTENDED_C = 148, /*[2C60]*/
1397 /** @stable ICU 3.6 */
1398 UBLOCK_LATIN_EXTENDED_D = 149, /*[A720]*/
1399 /** @stable ICU 3.6 */
1400 UBLOCK_PHAGS_PA = 150, /*[A840]*/
1401 /** @stable ICU 3.6 */
1402 UBLOCK_PHOENICIAN = 151, /*[10900]*/
1403 /** @stable ICU 3.6 */
1404 UBLOCK_CUNEIFORM = 152, /*[12000]*/
1405 /** @stable ICU 3.6 */
1406 UBLOCK_CUNEIFORM_NUMBERS_AND_PUNCTUATION = 153, /*[12400]*/
1407 /** @stable ICU 3.6 */
1408 UBLOCK_COUNTING_ROD_NUMERALS = 154, /*[1D360]*/
1409
1410 /* New blocks in Unicode 5.1 */
1411
1412 /** @stable ICU 4.0 */
1413 UBLOCK_SUNDANESE = 155, /*[1B80]*/
1414 /** @stable ICU 4.0 */
1415 UBLOCK_LEPCHA = 156, /*[1C00]*/
1416 /** @stable ICU 4.0 */
1417 UBLOCK_OL_CHIKI = 157, /*[1C50]*/
1418 /** @stable ICU 4.0 */
1419 UBLOCK_CYRILLIC_EXTENDED_A = 158, /*[2DE0]*/
1420 /** @stable ICU 4.0 */
1421 UBLOCK_VAI = 159, /*[A500]*/
1422 /** @stable ICU 4.0 */
1423 UBLOCK_CYRILLIC_EXTENDED_B = 160, /*[A640]*/
1424 /** @stable ICU 4.0 */
1425 UBLOCK_SAURASHTRA = 161, /*[A880]*/
1426 /** @stable ICU 4.0 */
1427 UBLOCK_KAYAH_LI = 162, /*[A900]*/
1428 /** @stable ICU 4.0 */
1429 UBLOCK_REJANG = 163, /*[A930]*/
1430 /** @stable ICU 4.0 */
1431 UBLOCK_CHAM = 164, /*[AA00]*/
1432 /** @stable ICU 4.0 */
1433 UBLOCK_ANCIENT_SYMBOLS = 165, /*[10190]*/
1434 /** @stable ICU 4.0 */
1435 UBLOCK_PHAISTOS_DISC = 166, /*[101D0]*/
1436 /** @stable ICU 4.0 */
1437 UBLOCK_LYCIAN = 167, /*[10280]*/
1438 /** @stable ICU 4.0 */
1439 UBLOCK_CARIAN = 168, /*[102A0]*/
1440 /** @stable ICU 4.0 */
1441 UBLOCK_LYDIAN = 169, /*[10920]*/
1442 /** @stable ICU 4.0 */
1443 UBLOCK_MAHJONG_TILES = 170, /*[1F000]*/
1444 /** @stable ICU 4.0 */
1445 UBLOCK_DOMINO_TILES = 171, /*[1F030]*/
1446
1447 /* New blocks in Unicode 5.2 */
1448
1449 /** @stable ICU 4.4 */
1450 UBLOCK_SAMARITAN = 172, /*[0800]*/
1451 /** @stable ICU 4.4 */
1452 UBLOCK_UNIFIED_CANADIAN_ABORIGINAL_SYLLABICS_EXTENDED = 173, /*[18B0]*/
1453 /** @stable ICU 4.4 */
1454 UBLOCK_TAI_THAM = 174, /*[1A20]*/
1455 /** @stable ICU 4.4 */
1456 UBLOCK_VEDIC_EXTENSIONS = 175, /*[1CD0]*/
1457 /** @stable ICU 4.4 */
1458 UBLOCK_LISU = 176, /*[A4D0]*/
1459 /** @stable ICU 4.4 */
1460 UBLOCK_BAMUM = 177, /*[A6A0]*/
1461 /** @stable ICU 4.4 */
1462 UBLOCK_COMMON_INDIC_NUMBER_FORMS = 178, /*[A830]*/
1463 /** @stable ICU 4.4 */
1464 UBLOCK_DEVANAGARI_EXTENDED = 179, /*[A8E0]*/
1465 /** @stable ICU 4.4 */
1466 UBLOCK_HANGUL_JAMO_EXTENDED_A = 180, /*[A960]*/
1467 /** @stable ICU 4.4 */
1468 UBLOCK_JAVANESE = 181, /*[A980]*/
1469 /** @stable ICU 4.4 */
1470 UBLOCK_MYANMAR_EXTENDED_A = 182, /*[AA60]*/
1471 /** @stable ICU 4.4 */
1472 UBLOCK_TAI_VIET = 183, /*[AA80]*/
1473 /** @stable ICU 4.4 */
1474 UBLOCK_MEETEI_MAYEK = 184, /*[ABC0]*/
1475 /** @stable ICU 4.4 */
1476 UBLOCK_HANGUL_JAMO_EXTENDED_B = 185, /*[D7B0]*/
1477 /** @stable ICU 4.4 */
1478 UBLOCK_IMPERIAL_ARAMAIC = 186, /*[10840]*/
1479 /** @stable ICU 4.4 */
1480 UBLOCK_OLD_SOUTH_ARABIAN = 187, /*[10A60]*/
1481 /** @stable ICU 4.4 */
1482 UBLOCK_AVESTAN = 188, /*[10B00]*/
1483 /** @stable ICU 4.4 */
1484 UBLOCK_INSCRIPTIONAL_PARTHIAN = 189, /*[10B40]*/
1485 /** @stable ICU 4.4 */
1486 UBLOCK_INSCRIPTIONAL_PAHLAVI = 190, /*[10B60]*/
1487 /** @stable ICU 4.4 */
1488 UBLOCK_OLD_TURKIC = 191, /*[10C00]*/
1489 /** @stable ICU 4.4 */
1490 UBLOCK_RUMI_NUMERAL_SYMBOLS = 192, /*[10E60]*/
1491 /** @stable ICU 4.4 */
1492 UBLOCK_KAITHI = 193, /*[11080]*/
1493 /** @stable ICU 4.4 */
1494 UBLOCK_EGYPTIAN_HIEROGLYPHS = 194, /*[13000]*/
1495 /** @stable ICU 4.4 */
1496 UBLOCK_ENCLOSED_ALPHANUMERIC_SUPPLEMENT = 195, /*[1F100]*/
1497 /** @stable ICU 4.4 */
1498 UBLOCK_ENCLOSED_IDEOGRAPHIC_SUPPLEMENT = 196, /*[1F200]*/
1499 /** @stable ICU 4.4 */
1500 UBLOCK_CJK_UNIFIED_IDEOGRAPHS_EXTENSION_C = 197, /*[2A700]*/
1501
1502 /* New blocks in Unicode 6.0 */
1503
1504 /** @stable ICU 4.6 */
1505 UBLOCK_MANDAIC = 198, /*[0840]*/
1506 /** @stable ICU 4.6 */
1507 UBLOCK_BATAK = 199, /*[1BC0]*/
1508 /** @stable ICU 4.6 */
1509 UBLOCK_ETHIOPIC_EXTENDED_A = 200, /*[AB00]*/
1510 /** @stable ICU 4.6 */
1511 UBLOCK_BRAHMI = 201, /*[11000]*/
1512 /** @stable ICU 4.6 */
1513 UBLOCK_BAMUM_SUPPLEMENT = 202, /*[16800]*/
1514 /** @stable ICU 4.6 */
1515 UBLOCK_KANA_SUPPLEMENT = 203, /*[1B000]*/
1516 /** @stable ICU 4.6 */
1517 UBLOCK_PLAYING_CARDS = 204, /*[1F0A0]*/
1518 /** @stable ICU 4.6 */
1519 UBLOCK_MISCELLANEOUS_SYMBOLS_AND_PICTOGRAPHS = 205, /*[1F300]*/
1520 /** @stable ICU 4.6 */
1521 UBLOCK_EMOTICONS = 206, /*[1F600]*/
1522 /** @stable ICU 4.6 */
1523 UBLOCK_TRANSPORT_AND_MAP_SYMBOLS = 207, /*[1F680]*/
1524 /** @stable ICU 4.6 */
1525 UBLOCK_ALCHEMICAL_SYMBOLS = 208, /*[1F700]*/
1526 /** @stable ICU 4.6 */
1527 UBLOCK_CJK_UNIFIED_IDEOGRAPHS_EXTENSION_D = 209, /*[2B740]*/
1528
1529 /* New blocks in Unicode 6.1 */
1530
1531 /** @stable ICU 49 */
1532 UBLOCK_ARABIC_EXTENDED_A = 210, /*[08A0]*/
1533 /** @stable ICU 49 */
1534 UBLOCK_ARABIC_MATHEMATICAL_ALPHABETIC_SYMBOLS = 211, /*[1EE00]*/
1535 /** @stable ICU 49 */
1536 UBLOCK_CHAKMA = 212, /*[11100]*/
1537 /** @stable ICU 49 */
1538 UBLOCK_MEETEI_MAYEK_EXTENSIONS = 213, /*[AAE0]*/
1539 /** @stable ICU 49 */
1540 UBLOCK_MEROITIC_CURSIVE = 214, /*[109A0]*/
1541 /** @stable ICU 49 */
1542 UBLOCK_MEROITIC_HIEROGLYPHS = 215, /*[10980]*/
1543 /** @stable ICU 49 */
1544 UBLOCK_MIAO = 216, /*[16F00]*/
1545 /** @stable ICU 49 */
1546 UBLOCK_SHARADA = 217, /*[11180]*/
1547 /** @stable ICU 49 */
1548 UBLOCK_SORA_SOMPENG = 218, /*[110D0]*/
1549 /** @stable ICU 49 */
1550 UBLOCK_SUNDANESE_SUPPLEMENT = 219, /*[1CC0]*/
1551 /** @stable ICU 49 */
1552 UBLOCK_TAKRI = 220, /*[11680]*/
1553
1554 /* New blocks in Unicode 7.0 */
1555
1556 /** @stable ICU 54 */
1557 UBLOCK_BASSA_VAH = 221, /*[16AD0]*/
1558 /** @stable ICU 54 */
1559 UBLOCK_CAUCASIAN_ALBANIAN = 222, /*[10530]*/
1560 /** @stable ICU 54 */
1561 UBLOCK_COPTIC_EPACT_NUMBERS = 223, /*[102E0]*/
1562 /** @stable ICU 54 */
1563 UBLOCK_COMBINING_DIACRITICAL_MARKS_EXTENDED = 224, /*[1AB0]*/
1564 /** @stable ICU 54 */
1565 UBLOCK_DUPLOYAN = 225, /*[1BC00]*/
1566 /** @stable ICU 54 */
1567 UBLOCK_ELBASAN = 226, /*[10500]*/
1568 /** @stable ICU 54 */
1569 UBLOCK_GEOMETRIC_SHAPES_EXTENDED = 227, /*[1F780]*/
1570 /** @stable ICU 54 */
1571 UBLOCK_GRANTHA = 228, /*[11300]*/
1572 /** @stable ICU 54 */
1573 UBLOCK_KHOJKI = 229, /*[11200]*/
1574 /** @stable ICU 54 */
1575 UBLOCK_KHUDAWADI = 230, /*[112B0]*/
1576 /** @stable ICU 54 */
1577 UBLOCK_LATIN_EXTENDED_E = 231, /*[AB30]*/
1578 /** @stable ICU 54 */
1579 UBLOCK_LINEAR_A = 232, /*[10600]*/
1580 /** @stable ICU 54 */
1581 UBLOCK_MAHAJANI = 233, /*[11150]*/
1582 /** @stable ICU 54 */
1583 UBLOCK_MANICHAEAN = 234, /*[10AC0]*/
1584 /** @stable ICU 54 */
1585 UBLOCK_MENDE_KIKAKUI = 235, /*[1E800]*/
1586 /** @stable ICU 54 */
1587 UBLOCK_MODI = 236, /*[11600]*/
1588 /** @stable ICU 54 */
1589 UBLOCK_MRO = 237, /*[16A40]*/
1590 /** @stable ICU 54 */
1591 UBLOCK_MYANMAR_EXTENDED_B = 238, /*[A9E0]*/
1592 /** @stable ICU 54 */
1593 UBLOCK_NABATAEAN = 239, /*[10880]*/
1594 /** @stable ICU 54 */
1595 UBLOCK_OLD_NORTH_ARABIAN = 240, /*[10A80]*/
1596 /** @stable ICU 54 */
1597 UBLOCK_OLD_PERMIC = 241, /*[10350]*/
1598 /** @stable ICU 54 */
1599 UBLOCK_ORNAMENTAL_DINGBATS = 242, /*[1F650]*/
1600 /** @stable ICU 54 */
1601 UBLOCK_PAHAWH_HMONG = 243, /*[16B00]*/
1602 /** @stable ICU 54 */
1603 UBLOCK_PALMYRENE = 244, /*[10860]*/
1604 /** @stable ICU 54 */
1605 UBLOCK_PAU_CIN_HAU = 245, /*[11AC0]*/
1606 /** @stable ICU 54 */
1607 UBLOCK_PSALTER_PAHLAVI = 246, /*[10B80]*/
1608 /** @stable ICU 54 */
1609 UBLOCK_SHORTHAND_FORMAT_CONTROLS = 247, /*[1BCA0]*/
1610 /** @stable ICU 54 */
1611 UBLOCK_SIDDHAM = 248, /*[11580]*/
1612 /** @stable ICU 54 */
1613 UBLOCK_SINHALA_ARCHAIC_NUMBERS = 249, /*[111E0]*/
1614 /** @stable ICU 54 */
1615 UBLOCK_SUPPLEMENTAL_ARROWS_C = 250, /*[1F800]*/
1616 /** @stable ICU 54 */
1617 UBLOCK_TIRHUTA = 251, /*[11480]*/
1618 /** @stable ICU 54 */
1619 UBLOCK_WARANG_CITI = 252, /*[118A0]*/
1620
1621 /* New blocks in Unicode 8.0 */
1622
1623 /** @stable ICU 56 */
1624 UBLOCK_AHOM = 253, /*[11700]*/
1625 /** @stable ICU 56 */
1626 UBLOCK_ANATOLIAN_HIEROGLYPHS = 254, /*[14400]*/
1627 /** @stable ICU 56 */
1628 UBLOCK_CHEROKEE_SUPPLEMENT = 255, /*[AB70]*/
1629 /** @stable ICU 56 */
1630 UBLOCK_CJK_UNIFIED_IDEOGRAPHS_EXTENSION_E = 256, /*[2B820]*/
1631 /** @stable ICU 56 */
1632 UBLOCK_EARLY_DYNASTIC_CUNEIFORM = 257, /*[12480]*/
1633 /** @stable ICU 56 */
1634 UBLOCK_HATRAN = 258, /*[108E0]*/
1635 /** @stable ICU 56 */
1636 UBLOCK_MULTANI = 259, /*[11280]*/
1637 /** @stable ICU 56 */
1638 UBLOCK_OLD_HUNGARIAN = 260, /*[10C80]*/
1639 /** @stable ICU 56 */
1640 UBLOCK_SUPPLEMENTAL_SYMBOLS_AND_PICTOGRAPHS = 261, /*[1F900]*/
1641 /** @stable ICU 56 */
1642 UBLOCK_SUTTON_SIGNWRITING = 262, /*[1D800]*/
1643
1644 /* New blocks in Unicode 9.0 */
1645
1646 /** @stable ICU 58 */
1647 UBLOCK_ADLAM = 263, /*[1E900]*/
1648 /** @stable ICU 58 */
1649 UBLOCK_BHAIKSUKI = 264, /*[11C00]*/
1650 /** @stable ICU 58 */
1651 UBLOCK_CYRILLIC_EXTENDED_C = 265, /*[1C80]*/
1652 /** @stable ICU 58 */
1653 UBLOCK_GLAGOLITIC_SUPPLEMENT = 266, /*[1E000]*/
1654 /** @stable ICU 58 */
1655 UBLOCK_IDEOGRAPHIC_SYMBOLS_AND_PUNCTUATION = 267, /*[16FE0]*/
1656 /** @stable ICU 58 */
1657 UBLOCK_MARCHEN = 268, /*[11C70]*/
1658 /** @stable ICU 58 */
1659 UBLOCK_MONGOLIAN_SUPPLEMENT = 269, /*[11660]*/
1660 /** @stable ICU 58 */
1661 UBLOCK_NEWA = 270, /*[11400]*/
1662 /** @stable ICU 58 */
1663 UBLOCK_OSAGE = 271, /*[104B0]*/
1664 /** @stable ICU 58 */
1665 UBLOCK_TANGUT = 272, /*[17000]*/
1666 /** @stable ICU 58 */
1667 UBLOCK_TANGUT_COMPONENTS = 273, /*[18800]*/
1668
1669 // New blocks in Unicode 10.0
1670
1671 /** @stable ICU 60 */
1672 UBLOCK_CJK_UNIFIED_IDEOGRAPHS_EXTENSION_F = 274, /*[2CEB0]*/
1673 /** @stable ICU 60 */
1674 UBLOCK_KANA_EXTENDED_A = 275, /*[1B100]*/
1675 /** @stable ICU 60 */
1676 UBLOCK_MASARAM_GONDI = 276, /*[11D00]*/
1677 /** @stable ICU 60 */
1678 UBLOCK_NUSHU = 277, /*[1B170]*/
1679 /** @stable ICU 60 */
1680 UBLOCK_SOYOMBO = 278, /*[11A50]*/
1681 /** @stable ICU 60 */
1682 UBLOCK_SYRIAC_SUPPLEMENT = 279, /*[0860]*/
1683 /** @stable ICU 60 */
1684 UBLOCK_ZANABAZAR_SQUARE = 280, /*[11A00]*/
1685
1686#ifndef U_HIDE_DEPRECATED_API
1687 /**
1688 * One more than the highest normal UBlockCode value.
1689 * The highest value is available via u_getIntPropertyMaxValue(UCHAR_BLOCK).
1690 *
1691 * @deprecated ICU 58 The numeric value may change over time, see ICU ticket #12420.
1692 */
1693 UBLOCK_COUNT = 281,
1694#endif // U_HIDE_DEPRECATED_API
1695
1696 /** @stable ICU 2.0 */
1697 UBLOCK_INVALID_CODE=-1
1698};
1699
1700/** @stable ICU 2.0 */
1701typedef enum UBlockCode UBlockCode;
1702
1703/**
1704 * East Asian Width constants.
1705 *
1706 * @see UCHAR_EAST_ASIAN_WIDTH
1707 * @see u_getIntPropertyValue
1708 * @stable ICU 2.2
1709 */
1710typedef enum UEastAsianWidth {
1711 /*
1712 * Note: UEastAsianWidth constants are parsed by preparseucd.py.
1713 * It matches lines like
1714 * U_EA_<Unicode East_Asian_Width value name>
1715 */
1716
1717 U_EA_NEUTRAL, /*[N]*/
1718 U_EA_AMBIGUOUS, /*[A]*/
1719 U_EA_HALFWIDTH, /*[H]*/
1720 U_EA_FULLWIDTH, /*[F]*/
1721 U_EA_NARROW, /*[Na]*/
1722 U_EA_WIDE, /*[W]*/
1723#ifndef U_HIDE_DEPRECATED_API
1724 /**
1725 * One more than the highest normal UEastAsianWidth value.
1726 * The highest value is available via u_getIntPropertyMaxValue(UCHAR_EAST_ASIAN_WIDTH).
1727 *
1728 * @deprecated ICU 58 The numeric value may change over time, see ICU ticket #12420.
1729 */
1730 U_EA_COUNT
1731#endif // U_HIDE_DEPRECATED_API
1732} UEastAsianWidth;
1733
1734/**
1735 * Selector constants for u_charName().
1736 * u_charName() returns the "modern" name of a
1737 * Unicode character; or the name that was defined in
1738 * Unicode version 1.0, before the Unicode standard merged
1739 * with ISO-10646; or an "extended" name that gives each
1740 * Unicode code point a unique name.
1741 *
1742 * @see u_charName
1743 * @stable ICU 2.0
1744 */
1745typedef enum UCharNameChoice {
1746 /** Unicode character name (Name property). @stable ICU 2.0 */
1747 U_UNICODE_CHAR_NAME,
1748#ifndef U_HIDE_DEPRECATED_API
1749 /**
1750 * The Unicode_1_Name property value which is of little practical value.
1751 * Beginning with ICU 49, ICU APIs return an empty string for this name choice.
1752 * @deprecated ICU 49
1753 */
1754 U_UNICODE_10_CHAR_NAME,
1755#endif /* U_HIDE_DEPRECATED_API */
1756 /** Standard or synthetic character name. @stable ICU 2.0 */
1757 U_EXTENDED_CHAR_NAME = U_UNICODE_CHAR_NAME+2,
1758 /** Corrected name from NameAliases.txt. @stable ICU 4.4 */
1759 U_CHAR_NAME_ALIAS,
1760#ifndef U_HIDE_DEPRECATED_API
1761 /**
1762 * One more than the highest normal UCharNameChoice value.
1763 * @deprecated ICU 58 The numeric value may change over time, see ICU ticket #12420.
1764 */
1765 U_CHAR_NAME_CHOICE_COUNT
1766#endif // U_HIDE_DEPRECATED_API
1767} UCharNameChoice;
1768
1769/**
1770 * Selector constants for u_getPropertyName() and
1771 * u_getPropertyValueName(). These selectors are used to choose which
1772 * name is returned for a given property or value. All properties and
1773 * values have a long name. Most have a short name, but some do not.
1774 * Unicode allows for additional names, beyond the long and short
1775 * name, which would be indicated by U_LONG_PROPERTY_NAME + i, where
1776 * i=1, 2,...
1777 *
1778 * @see u_getPropertyName()
1779 * @see u_getPropertyValueName()
1780 * @stable ICU 2.4
1781 */
1782typedef enum UPropertyNameChoice {
1783 U_SHORT_PROPERTY_NAME,
1784 U_LONG_PROPERTY_NAME,
1785#ifndef U_HIDE_DEPRECATED_API
1786 /**
1787 * One more than the highest normal UPropertyNameChoice value.
1788 * @deprecated ICU 58 The numeric value may change over time, see ICU ticket #12420.
1789 */
1790 U_PROPERTY_NAME_CHOICE_COUNT
1791#endif // U_HIDE_DEPRECATED_API
1792} UPropertyNameChoice;
1793
1794/**
1795 * Decomposition Type constants.
1796 *
1797 * @see UCHAR_DECOMPOSITION_TYPE
1798 * @stable ICU 2.2
1799 */
1800typedef enum UDecompositionType {
1801 /*
1802 * Note: UDecompositionType constants are parsed by preparseucd.py.
1803 * It matches lines like
1804 * U_DT_<Unicode Decomposition_Type value name>
1805 */
1806
1807 U_DT_NONE, /*[none]*/
1808 U_DT_CANONICAL, /*[can]*/
1809 U_DT_COMPAT, /*[com]*/
1810 U_DT_CIRCLE, /*[enc]*/
1811 U_DT_FINAL, /*[fin]*/
1812 U_DT_FONT, /*[font]*/
1813 U_DT_FRACTION, /*[fra]*/
1814 U_DT_INITIAL, /*[init]*/
1815 U_DT_ISOLATED, /*[iso]*/
1816 U_DT_MEDIAL, /*[med]*/
1817 U_DT_NARROW, /*[nar]*/
1818 U_DT_NOBREAK, /*[nb]*/
1819 U_DT_SMALL, /*[sml]*/
1820 U_DT_SQUARE, /*[sqr]*/
1821 U_DT_SUB, /*[sub]*/
1822 U_DT_SUPER, /*[sup]*/
1823 U_DT_VERTICAL, /*[vert]*/
1824 U_DT_WIDE, /*[wide]*/
1825#ifndef U_HIDE_DEPRECATED_API
1826 /**
1827 * One more than the highest normal UDecompositionType value.
1828 * The highest value is available via u_getIntPropertyMaxValue(UCHAR_DECOMPOSITION_TYPE).
1829 *
1830 * @deprecated ICU 58 The numeric value may change over time, see ICU ticket #12420.
1831 */
1832 U_DT_COUNT /* 18 */
1833#endif // U_HIDE_DEPRECATED_API
1834} UDecompositionType;
1835
1836/**
1837 * Joining Type constants.
1838 *
1839 * @see UCHAR_JOINING_TYPE
1840 * @stable ICU 2.2
1841 */
1842typedef enum UJoiningType {
1843 /*
1844 * Note: UJoiningType constants are parsed by preparseucd.py.
1845 * It matches lines like
1846 * U_JT_<Unicode Joining_Type value name>
1847 */
1848
1849 U_JT_NON_JOINING, /*[U]*/
1850 U_JT_JOIN_CAUSING, /*[C]*/
1851 U_JT_DUAL_JOINING, /*[D]*/
1852 U_JT_LEFT_JOINING, /*[L]*/
1853 U_JT_RIGHT_JOINING, /*[R]*/
1854 U_JT_TRANSPARENT, /*[T]*/
1855#ifndef U_HIDE_DEPRECATED_API
1856 /**
1857 * One more than the highest normal UJoiningType value.
1858 * The highest value is available via u_getIntPropertyMaxValue(UCHAR_JOINING_TYPE).
1859 *
1860 * @deprecated ICU 58 The numeric value may change over time, see ICU ticket #12420.
1861 */
1862 U_JT_COUNT /* 6 */
1863#endif // U_HIDE_DEPRECATED_API
1864} UJoiningType;
1865
1866/**
1867 * Joining Group constants.
1868 *
1869 * @see UCHAR_JOINING_GROUP
1870 * @stable ICU 2.2
1871 */
1872typedef enum UJoiningGroup {
1873 /*
1874 * Note: UJoiningGroup constants are parsed by preparseucd.py.
1875 * It matches lines like
1876 * U_JG_<Unicode Joining_Group value name>
1877 */
1878
1879 U_JG_NO_JOINING_GROUP,
1880 U_JG_AIN,
1881 U_JG_ALAPH,
1882 U_JG_ALEF,
1883 U_JG_BEH,
1884 U_JG_BETH,
1885 U_JG_DAL,
1886 U_JG_DALATH_RISH,
1887 U_JG_E,
1888 U_JG_FEH,
1889 U_JG_FINAL_SEMKATH,
1890 U_JG_GAF,
1891 U_JG_GAMAL,
1892 U_JG_HAH,
1893 U_JG_TEH_MARBUTA_GOAL, /**< @stable ICU 4.6 */
1894 U_JG_HAMZA_ON_HEH_GOAL=U_JG_TEH_MARBUTA_GOAL,
1895 U_JG_HE,
1896 U_JG_HEH,
1897 U_JG_HEH_GOAL,
1898 U_JG_HETH,
1899 U_JG_KAF,
1900 U_JG_KAPH,
1901 U_JG_KNOTTED_HEH,
1902 U_JG_LAM,
1903 U_JG_LAMADH,
1904 U_JG_MEEM,
1905 U_JG_MIM,
1906 U_JG_NOON,
1907 U_JG_NUN,
1908 U_JG_PE,
1909 U_JG_QAF,
1910 U_JG_QAPH,
1911 U_JG_REH,
1912 U_JG_REVERSED_PE,
1913 U_JG_SAD,
1914 U_JG_SADHE,
1915 U_JG_SEEN,
1916 U_JG_SEMKATH,
1917 U_JG_SHIN,
1918 U_JG_SWASH_KAF,
1919 U_JG_SYRIAC_WAW,
1920 U_JG_TAH,
1921 U_JG_TAW,
1922 U_JG_TEH_MARBUTA,
1923 U_JG_TETH,
1924 U_JG_WAW,
1925 U_JG_YEH,
1926 U_JG_YEH_BARREE,
1927 U_JG_YEH_WITH_TAIL,
1928 U_JG_YUDH,
1929 U_JG_YUDH_HE,
1930 U_JG_ZAIN,
1931 U_JG_FE, /**< @stable ICU 2.6 */
1932 U_JG_KHAPH, /**< @stable ICU 2.6 */
1933 U_JG_ZHAIN, /**< @stable ICU 2.6 */
1934 U_JG_BURUSHASKI_YEH_BARREE, /**< @stable ICU 4.0 */
1935 U_JG_FARSI_YEH, /**< @stable ICU 4.4 */
1936 U_JG_NYA, /**< @stable ICU 4.4 */
1937 U_JG_ROHINGYA_YEH, /**< @stable ICU 49 */
1938 U_JG_MANICHAEAN_ALEPH, /**< @stable ICU 54 */
1939 U_JG_MANICHAEAN_AYIN, /**< @stable ICU 54 */
1940 U_JG_MANICHAEAN_BETH, /**< @stable ICU 54 */
1941 U_JG_MANICHAEAN_DALETH, /**< @stable ICU 54 */
1942 U_JG_MANICHAEAN_DHAMEDH, /**< @stable ICU 54 */
1943 U_JG_MANICHAEAN_FIVE, /**< @stable ICU 54 */
1944 U_JG_MANICHAEAN_GIMEL, /**< @stable ICU 54 */
1945 U_JG_MANICHAEAN_HETH, /**< @stable ICU 54 */
1946 U_JG_MANICHAEAN_HUNDRED, /**< @stable ICU 54 */
1947 U_JG_MANICHAEAN_KAPH, /**< @stable ICU 54 */
1948 U_JG_MANICHAEAN_LAMEDH, /**< @stable ICU 54 */
1949 U_JG_MANICHAEAN_MEM, /**< @stable ICU 54 */
1950 U_JG_MANICHAEAN_NUN, /**< @stable ICU 54 */
1951 U_JG_MANICHAEAN_ONE, /**< @stable ICU 54 */
1952 U_JG_MANICHAEAN_PE, /**< @stable ICU 54 */
1953 U_JG_MANICHAEAN_QOPH, /**< @stable ICU 54 */
1954 U_JG_MANICHAEAN_RESH, /**< @stable ICU 54 */
1955 U_JG_MANICHAEAN_SADHE, /**< @stable ICU 54 */
1956 U_JG_MANICHAEAN_SAMEKH, /**< @stable ICU 54 */
1957 U_JG_MANICHAEAN_TAW, /**< @stable ICU 54 */
1958 U_JG_MANICHAEAN_TEN, /**< @stable ICU 54 */
1959 U_JG_MANICHAEAN_TETH, /**< @stable ICU 54 */
1960 U_JG_MANICHAEAN_THAMEDH, /**< @stable ICU 54 */
1961 U_JG_MANICHAEAN_TWENTY, /**< @stable ICU 54 */
1962 U_JG_MANICHAEAN_WAW, /**< @stable ICU 54 */
1963 U_JG_MANICHAEAN_YODH, /**< @stable ICU 54 */
1964 U_JG_MANICHAEAN_ZAYIN, /**< @stable ICU 54 */
1965 U_JG_STRAIGHT_WAW, /**< @stable ICU 54 */
1966 U_JG_AFRICAN_FEH, /**< @stable ICU 58 */
1967 U_JG_AFRICAN_NOON, /**< @stable ICU 58 */
1968 U_JG_AFRICAN_QAF, /**< @stable ICU 58 */
1969
1970 U_JG_MALAYALAM_BHA, /**< @stable ICU 60 */
1971 U_JG_MALAYALAM_JA, /**< @stable ICU 60 */
1972 U_JG_MALAYALAM_LLA, /**< @stable ICU 60 */
1973 U_JG_MALAYALAM_LLLA, /**< @stable ICU 60 */
1974 U_JG_MALAYALAM_NGA, /**< @stable ICU 60 */
1975 U_JG_MALAYALAM_NNA, /**< @stable ICU 60 */
1976 U_JG_MALAYALAM_NNNA, /**< @stable ICU 60 */
1977 U_JG_MALAYALAM_NYA, /**< @stable ICU 60 */
1978 U_JG_MALAYALAM_RA, /**< @stable ICU 60 */
1979 U_JG_MALAYALAM_SSA, /**< @stable ICU 60 */
1980 U_JG_MALAYALAM_TTA, /**< @stable ICU 60 */
1981
1982#ifndef U_HIDE_DEPRECATED_API
1983 /**
1984 * One more than the highest normal UJoiningGroup value.
1985 * The highest value is available via u_getIntPropertyMaxValue(UCHAR_JOINING_GROUP).
1986 *
1987 * @deprecated ICU 58 The numeric value may change over time, see ICU ticket #12420.
1988 */
1989 U_JG_COUNT
1990#endif // U_HIDE_DEPRECATED_API
1991} UJoiningGroup;
1992
1993/**
1994 * Grapheme Cluster Break constants.
1995 *
1996 * @see UCHAR_GRAPHEME_CLUSTER_BREAK
1997 * @stable ICU 3.4
1998 */
1999typedef enum UGraphemeClusterBreak {
2000 /*
2001 * Note: UGraphemeClusterBreak constants are parsed by preparseucd.py.
2002 * It matches lines like
2003 * U_GCB_<Unicode Grapheme_Cluster_Break value name>
2004 */
2005
2006 U_GCB_OTHER = 0, /*[XX]*/
2007 U_GCB_CONTROL = 1, /*[CN]*/
2008 U_GCB_CR = 2, /*[CR]*/
2009 U_GCB_EXTEND = 3, /*[EX]*/
2010 U_GCB_L = 4, /*[L]*/
2011 U_GCB_LF = 5, /*[LF]*/
2012 U_GCB_LV = 6, /*[LV]*/
2013 U_GCB_LVT = 7, /*[LVT]*/
2014 U_GCB_T = 8, /*[T]*/
2015 U_GCB_V = 9, /*[V]*/
2016 /** @stable ICU 4.0 */
2017 U_GCB_SPACING_MARK = 10, /*[SM]*/ /* from here on: new in Unicode 5.1/ICU 4.0 */
2018 /** @stable ICU 4.0 */
2019 U_GCB_PREPEND = 11, /*[PP]*/
2020 /** @stable ICU 50 */
2021 U_GCB_REGIONAL_INDICATOR = 12, /*[RI]*/ /* new in Unicode 6.2/ICU 50 */
2022 /** @stable ICU 58 */
2023 U_GCB_E_BASE = 13, /*[EB]*/ /* from here on: new in Unicode 9.0/ICU 58 */
2024 /** @stable ICU 58 */
2025 U_GCB_E_BASE_GAZ = 14, /*[EBG]*/
2026 /** @stable ICU 58 */
2027 U_GCB_E_MODIFIER = 15, /*[EM]*/
2028 /** @stable ICU 58 */
2029 U_GCB_GLUE_AFTER_ZWJ = 16, /*[GAZ]*/
2030 /** @stable ICU 58 */
2031 U_GCB_ZWJ = 17, /*[ZWJ]*/
2032#ifndef U_HIDE_DEPRECATED_API
2033 /**
2034 * One more than the highest normal UGraphemeClusterBreak value.
2035 * The highest value is available via u_getIntPropertyMaxValue(UCHAR_GRAPHEME_CLUSTER_BREAK).
2036 *
2037 * @deprecated ICU 58 The numeric value may change over time, see ICU ticket #12420.
2038 */
2039 U_GCB_COUNT = 18
2040#endif // U_HIDE_DEPRECATED_API
2041} UGraphemeClusterBreak;
2042
2043/**
2044 * Word Break constants.
2045 * (UWordBreak is a pre-existing enum type in ubrk.h for word break status tags.)
2046 *
2047 * @see UCHAR_WORD_BREAK
2048 * @stable ICU 3.4
2049 */
2050typedef enum UWordBreakValues {
2051 /*
2052 * Note: UWordBreakValues constants are parsed by preparseucd.py.
2053 * It matches lines like
2054 * U_WB_<Unicode Word_Break value name>
2055 */
2056
2057 U_WB_OTHER = 0, /*[XX]*/
2058 U_WB_ALETTER = 1, /*[LE]*/
2059 U_WB_FORMAT = 2, /*[FO]*/
2060 U_WB_KATAKANA = 3, /*[KA]*/
2061 U_WB_MIDLETTER = 4, /*[ML]*/
2062 U_WB_MIDNUM = 5, /*[MN]*/
2063 U_WB_NUMERIC = 6, /*[NU]*/
2064 U_WB_EXTENDNUMLET = 7, /*[EX]*/
2065 /** @stable ICU 4.0 */
2066 U_WB_CR = 8, /*[CR]*/ /* from here on: new in Unicode 5.1/ICU 4.0 */
2067 /** @stable ICU 4.0 */
2068 U_WB_EXTEND = 9, /*[Extend]*/
2069 /** @stable ICU 4.0 */
2070 U_WB_LF = 10, /*[LF]*/
2071 /** @stable ICU 4.0 */
2072 U_WB_MIDNUMLET =11, /*[MB]*/
2073 /** @stable ICU 4.0 */
2074 U_WB_NEWLINE =12, /*[NL]*/
2075 /** @stable ICU 50 */
2076 U_WB_REGIONAL_INDICATOR = 13, /*[RI]*/ /* new in Unicode 6.2/ICU 50 */
2077 /** @stable ICU 52 */
2078 U_WB_HEBREW_LETTER = 14, /*[HL]*/ /* from here on: new in Unicode 6.3/ICU 52 */
2079 /** @stable ICU 52 */
2080 U_WB_SINGLE_QUOTE = 15, /*[SQ]*/
2081 /** @stable ICU 52 */
2082 U_WB_DOUBLE_QUOTE = 16, /*[DQ]*/
2083 /** @stable ICU 58 */
2084 U_WB_E_BASE = 17, /*[EB]*/ /* from here on: new in Unicode 9.0/ICU 58 */
2085 /** @stable ICU 58 */
2086 U_WB_E_BASE_GAZ = 18, /*[EBG]*/
2087 /** @stable ICU 58 */
2088 U_WB_E_MODIFIER = 19, /*[EM]*/
2089 /** @stable ICU 58 */
2090 U_WB_GLUE_AFTER_ZWJ = 20, /*[GAZ]*/
2091 /** @stable ICU 58 */
2092 U_WB_ZWJ = 21, /*[ZWJ]*/
2093#ifndef U_HIDE_DEPRECATED_API
2094 /**
2095 * One more than the highest normal UWordBreakValues value.
2096 * The highest value is available via u_getIntPropertyMaxValue(UCHAR_WORD_BREAK).
2097 *
2098 * @deprecated ICU 58 The numeric value may change over time, see ICU ticket #12420.
2099 */
2100 U_WB_COUNT = 22
2101#endif // U_HIDE_DEPRECATED_API
2102} UWordBreakValues;
2103
2104/**
2105 * Sentence Break constants.
2106 *
2107 * @see UCHAR_SENTENCE_BREAK
2108 * @stable ICU 3.4
2109 */
2110typedef enum USentenceBreak {
2111 /*
2112 * Note: USentenceBreak constants are parsed by preparseucd.py.
2113 * It matches lines like
2114 * U_SB_<Unicode Sentence_Break value name>
2115 */
2116
2117 U_SB_OTHER = 0, /*[XX]*/
2118 U_SB_ATERM = 1, /*[AT]*/
2119 U_SB_CLOSE = 2, /*[CL]*/
2120 U_SB_FORMAT = 3, /*[FO]*/
2121 U_SB_LOWER = 4, /*[LO]*/
2122 U_SB_NUMERIC = 5, /*[NU]*/
2123 U_SB_OLETTER = 6, /*[LE]*/
2124 U_SB_SEP = 7, /*[SE]*/
2125 U_SB_SP = 8, /*[SP]*/
2126 U_SB_STERM = 9, /*[ST]*/
2127 U_SB_UPPER = 10, /*[UP]*/
2128 U_SB_CR = 11, /*[CR]*/ /* from here on: new in Unicode 5.1/ICU 4.0 */
2129 U_SB_EXTEND = 12, /*[EX]*/
2130 U_SB_LF = 13, /*[LF]*/
2131 U_SB_SCONTINUE = 14, /*[SC]*/
2132#ifndef U_HIDE_DEPRECATED_API
2133 /**
2134 * One more than the highest normal USentenceBreak value.
2135 * The highest value is available via u_getIntPropertyMaxValue(UCHAR_SENTENCE_BREAK).
2136 *
2137 * @deprecated ICU 58 The numeric value may change over time, see ICU ticket #12420.
2138 */
2139 U_SB_COUNT = 15
2140#endif // U_HIDE_DEPRECATED_API
2141} USentenceBreak;
2142
2143/**
2144 * Line Break constants.
2145 *
2146 * @see UCHAR_LINE_BREAK
2147 * @stable ICU 2.2
2148 */
2149typedef enum ULineBreak {
2150 /*
2151 * Note: ULineBreak constants are parsed by preparseucd.py.
2152 * It matches lines like
2153 * U_LB_<Unicode Line_Break value name>
2154 */
2155
2156 U_LB_UNKNOWN = 0, /*[XX]*/
2157 U_LB_AMBIGUOUS = 1, /*[AI]*/
2158 U_LB_ALPHABETIC = 2, /*[AL]*/
2159 U_LB_BREAK_BOTH = 3, /*[B2]*/
2160 U_LB_BREAK_AFTER = 4, /*[BA]*/
2161 U_LB_BREAK_BEFORE = 5, /*[BB]*/
2162 U_LB_MANDATORY_BREAK = 6, /*[BK]*/
2163 U_LB_CONTINGENT_BREAK = 7, /*[CB]*/
2164 U_LB_CLOSE_PUNCTUATION = 8, /*[CL]*/
2165 U_LB_COMBINING_MARK = 9, /*[CM]*/
2166 U_LB_CARRIAGE_RETURN = 10, /*[CR]*/
2167 U_LB_EXCLAMATION = 11, /*[EX]*/
2168 U_LB_GLUE = 12, /*[GL]*/
2169 U_LB_HYPHEN = 13, /*[HY]*/
2170 U_LB_IDEOGRAPHIC = 14, /*[ID]*/
2171 /** Renamed from the misspelled "inseperable" in Unicode 4.0.1/ICU 3.0 @stable ICU 3.0 */
2172 U_LB_INSEPARABLE = 15, /*[IN]*/
2173 U_LB_INSEPERABLE = U_LB_INSEPARABLE,
2174 U_LB_INFIX_NUMERIC = 16, /*[IS]*/
2175 U_LB_LINE_FEED = 17, /*[LF]*/
2176 U_LB_NONSTARTER = 18, /*[NS]*/
2177 U_LB_NUMERIC = 19, /*[NU]*/
2178 U_LB_OPEN_PUNCTUATION = 20, /*[OP]*/
2179 U_LB_POSTFIX_NUMERIC = 21, /*[PO]*/
2180 U_LB_PREFIX_NUMERIC = 22, /*[PR]*/
2181 U_LB_QUOTATION = 23, /*[QU]*/
2182 U_LB_COMPLEX_CONTEXT = 24, /*[SA]*/
2183 U_LB_SURROGATE = 25, /*[SG]*/
2184 U_LB_SPACE = 26, /*[SP]*/
2185 U_LB_BREAK_SYMBOLS = 27, /*[SY]*/
2186 U_LB_ZWSPACE = 28, /*[ZW]*/
2187 /** @stable ICU 2.6 */
2188 U_LB_NEXT_LINE = 29, /*[NL]*/ /* from here on: new in Unicode 4/ICU 2.6 */
2189 /** @stable ICU 2.6 */
2190 U_LB_WORD_JOINER = 30, /*[WJ]*/
2191 /** @stable ICU 3.4 */
2192 U_LB_H2 = 31, /*[H2]*/ /* from here on: new in Unicode 4.1/ICU 3.4 */
2193 /** @stable ICU 3.4 */
2194 U_LB_H3 = 32, /*[H3]*/
2195 /** @stable ICU 3.4 */
2196 U_LB_JL = 33, /*[JL]*/
2197 /** @stable ICU 3.4 */
2198 U_LB_JT = 34, /*[JT]*/
2199 /** @stable ICU 3.4 */
2200 U_LB_JV = 35, /*[JV]*/
2201 /** @stable ICU 4.4 */
2202 U_LB_CLOSE_PARENTHESIS = 36, /*[CP]*/ /* new in Unicode 5.2/ICU 4.4 */
2203 /** @stable ICU 49 */
2204 U_LB_CONDITIONAL_JAPANESE_STARTER = 37,/*[CJ]*/ /* new in Unicode 6.1/ICU 49 */
2205 /** @stable ICU 49 */
2206 U_LB_HEBREW_LETTER = 38, /*[HL]*/ /* new in Unicode 6.1/ICU 49 */
2207 /** @stable ICU 50 */
2208 U_LB_REGIONAL_INDICATOR = 39,/*[RI]*/ /* new in Unicode 6.2/ICU 50 */
2209 /** @stable ICU 58 */
2210 U_LB_E_BASE = 40, /*[EB]*/ /* from here on: new in Unicode 9.0/ICU 58 */
2211 /** @stable ICU 58 */
2212 U_LB_E_MODIFIER = 41, /*[EM]*/
2213 /** @stable ICU 58 */
2214 U_LB_ZWJ = 42, /*[ZWJ]*/
2215#ifndef U_HIDE_DEPRECATED_API
2216 /**
2217 * One more than the highest normal ULineBreak value.
2218 * The highest value is available via u_getIntPropertyMaxValue(UCHAR_LINE_BREAK).
2219 *
2220 * @deprecated ICU 58 The numeric value may change over time, see ICU ticket #12420.
2221 */
2222 U_LB_COUNT = 43
2223#endif // U_HIDE_DEPRECATED_API
2224} ULineBreak;
2225
2226/**
2227 * Numeric Type constants.
2228 *
2229 * @see UCHAR_NUMERIC_TYPE
2230 * @stable ICU 2.2
2231 */
2232typedef enum UNumericType {
2233 /*
2234 * Note: UNumericType constants are parsed by preparseucd.py.
2235 * It matches lines like
2236 * U_NT_<Unicode Numeric_Type value name>
2237 */
2238
2239 U_NT_NONE, /*[None]*/
2240 U_NT_DECIMAL, /*[de]*/
2241 U_NT_DIGIT, /*[di]*/
2242 U_NT_NUMERIC, /*[nu]*/
2243#ifndef U_HIDE_DEPRECATED_API
2244 /**
2245 * One more than the highest normal UNumericType value.
2246 * The highest value is available via u_getIntPropertyMaxValue(UCHAR_NUMERIC_TYPE).
2247 *
2248 * @deprecated ICU 58 The numeric value may change over time, see ICU ticket #12420.
2249 */
2250 U_NT_COUNT
2251#endif // U_HIDE_DEPRECATED_API
2252} UNumericType;
2253
2254/**
2255 * Hangul Syllable Type constants.
2256 *
2257 * @see UCHAR_HANGUL_SYLLABLE_TYPE
2258 * @stable ICU 2.6
2259 */
2260typedef enum UHangulSyllableType {
2261 /*
2262 * Note: UHangulSyllableType constants are parsed by preparseucd.py.
2263 * It matches lines like
2264 * U_HST_<Unicode Hangul_Syllable_Type value name>
2265 */
2266
2267 U_HST_NOT_APPLICABLE, /*[NA]*/
2268 U_HST_LEADING_JAMO, /*[L]*/
2269 U_HST_VOWEL_JAMO, /*[V]*/
2270 U_HST_TRAILING_JAMO, /*[T]*/
2271 U_HST_LV_SYLLABLE, /*[LV]*/
2272 U_HST_LVT_SYLLABLE, /*[LVT]*/
2273#ifndef U_HIDE_DEPRECATED_API
2274 /**
2275 * One more than the highest normal UHangulSyllableType value.
2276 * The highest value is available via u_getIntPropertyMaxValue(UCHAR_HANGUL_SYLLABLE_TYPE).
2277 *
2278 * @deprecated ICU 58 The numeric value may change over time, see ICU ticket #12420.
2279 */
2280 U_HST_COUNT
2281#endif // U_HIDE_DEPRECATED_API
2282} UHangulSyllableType;
2283
2284/**
2285 * Check a binary Unicode property for a code point.
2286 *
2287 * Unicode, especially in version 3.2, defines many more properties than the
2288 * original set in UnicodeData.txt.
2289 *
2290 * The properties APIs are intended to reflect Unicode properties as defined
2291 * in the Unicode Character Database (UCD) and Unicode Technical Reports (UTR).
2292 * For details about the properties see http://www.unicode.org/ucd/ .
2293 * For names of Unicode properties see the UCD file PropertyAliases.txt.
2294 *
2295 * Important: If ICU is built with UCD files from Unicode versions below 3.2,
2296 * then properties marked with "new in Unicode 3.2" are not or not fully available.
2297 *
2298 * @param c Code point to test.
2299 * @param which UProperty selector constant, identifies which binary property to check.
2300 * Must be UCHAR_BINARY_START<=which<UCHAR_BINARY_LIMIT.
2301 * @return TRUE or FALSE according to the binary Unicode property value for c.
2302 * Also FALSE if 'which' is out of bounds or if the Unicode version
2303 * does not have data for the property at all, or not for this code point.
2304 *
2305 * @see UProperty
2306 * @see u_getIntPropertyValue
2307 * @see u_getUnicodeVersion
2308 * @stable ICU 2.1
2309 */
2310U_STABLE UBool U_EXPORT2
2311u_hasBinaryProperty(UChar32 c, UProperty which);
2312
2313/**
2314 * Check if a code point has the Alphabetic Unicode property.
2315 * Same as u_hasBinaryProperty(c, UCHAR_ALPHABETIC).
2316 * This is different from u_isalpha!
2317 * @param c Code point to test
2318 * @return true if the code point has the Alphabetic Unicode property, false otherwise
2319 *
2320 * @see UCHAR_ALPHABETIC
2321 * @see u_isalpha
2322 * @see u_hasBinaryProperty
2323 * @stable ICU 2.1
2324 */
2325U_STABLE UBool U_EXPORT2
2326u_isUAlphabetic(UChar32 c);
2327
2328/**
2329 * Check if a code point has the Lowercase Unicode property.
2330 * Same as u_hasBinaryProperty(c, UCHAR_LOWERCASE).
2331 * This is different from u_islower!
2332 * @param c Code point to test
2333 * @return true if the code point has the Lowercase Unicode property, false otherwise
2334 *
2335 * @see UCHAR_LOWERCASE
2336 * @see u_islower
2337 * @see u_hasBinaryProperty
2338 * @stable ICU 2.1
2339 */
2340U_STABLE UBool U_EXPORT2
2341u_isULowercase(UChar32 c);
2342
2343/**
2344 * Check if a code point has the Uppercase Unicode property.
2345 * Same as u_hasBinaryProperty(c, UCHAR_UPPERCASE).
2346 * This is different from u_isupper!
2347 * @param c Code point to test
2348 * @return true if the code point has the Uppercase Unicode property, false otherwise
2349 *
2350 * @see UCHAR_UPPERCASE
2351 * @see u_isupper
2352 * @see u_hasBinaryProperty
2353 * @stable ICU 2.1
2354 */
2355U_STABLE UBool U_EXPORT2
2356u_isUUppercase(UChar32 c);
2357
2358/**
2359 * Check if a code point has the White_Space Unicode property.
2360 * Same as u_hasBinaryProperty(c, UCHAR_WHITE_SPACE).
2361 * This is different from both u_isspace and u_isWhitespace!
2362 *
2363 * Note: There are several ICU whitespace functions; please see the uchar.h
2364 * file documentation for a detailed comparison.
2365 *
2366 * @param c Code point to test
2367 * @return true if the code point has the White_Space Unicode property, false otherwise.
2368 *
2369 * @see UCHAR_WHITE_SPACE
2370 * @see u_isWhitespace
2371 * @see u_isspace
2372 * @see u_isJavaSpaceChar
2373 * @see u_hasBinaryProperty
2374 * @stable ICU 2.1
2375 */
2376U_STABLE UBool U_EXPORT2
2377u_isUWhiteSpace(UChar32 c);
2378
2379/**
2380 * Get the property value for an enumerated or integer Unicode property for a code point.
2381 * Also returns binary and mask property values.
2382 *
2383 * Unicode, especially in version 3.2, defines many more properties than the
2384 * original set in UnicodeData.txt.
2385 *
2386 * The properties APIs are intended to reflect Unicode properties as defined
2387 * in the Unicode Character Database (UCD) and Unicode Technical Reports (UTR).
2388 * For details about the properties see http://www.unicode.org/ .
2389 * For names of Unicode properties see the UCD file PropertyAliases.txt.
2390 *
2391 * Sample usage:
2392 * UEastAsianWidth ea=(UEastAsianWidth)u_getIntPropertyValue(c, UCHAR_EAST_ASIAN_WIDTH);
2393 * UBool b=(UBool)u_getIntPropertyValue(c, UCHAR_IDEOGRAPHIC);
2394 *
2395 * @param c Code point to test.
2396 * @param which UProperty selector constant, identifies which property to check.
2397 * Must be UCHAR_BINARY_START<=which<UCHAR_BINARY_LIMIT
2398 * or UCHAR_INT_START<=which<UCHAR_INT_LIMIT
2399 * or UCHAR_MASK_START<=which<UCHAR_MASK_LIMIT.
2400 * @return Numeric value that is directly the property value or,
2401 * for enumerated properties, corresponds to the numeric value of the enumerated
2402 * constant of the respective property value enumeration type
2403 * (cast to enum type if necessary).
2404 * Returns 0 or 1 (for FALSE/TRUE) for binary Unicode properties.
2405 * Returns a bit-mask for mask properties.
2406 * Returns 0 if 'which' is out of bounds or if the Unicode version
2407 * does not have data for the property at all, or not for this code point.
2408 *
2409 * @see UProperty
2410 * @see u_hasBinaryProperty
2411 * @see u_getIntPropertyMinValue
2412 * @see u_getIntPropertyMaxValue
2413 * @see u_getUnicodeVersion
2414 * @stable ICU 2.2
2415 */
2416U_STABLE int32_t U_EXPORT2
2417u_getIntPropertyValue(UChar32 c, UProperty which);
2418
2419/**
2420 * Get the minimum value for an enumerated/integer/binary Unicode property.
2421 * Can be used together with u_getIntPropertyMaxValue
2422 * to allocate arrays of UnicodeSet or similar.
2423 *
2424 * @param which UProperty selector constant, identifies which binary property to check.
2425 * Must be UCHAR_BINARY_START<=which<UCHAR_BINARY_LIMIT
2426 * or UCHAR_INT_START<=which<UCHAR_INT_LIMIT.
2427 * @return Minimum value returned by u_getIntPropertyValue for a Unicode property.
2428 * 0 if the property selector is out of range.
2429 *
2430 * @see UProperty
2431 * @see u_hasBinaryProperty
2432 * @see u_getUnicodeVersion
2433 * @see u_getIntPropertyMaxValue
2434 * @see u_getIntPropertyValue
2435 * @stable ICU 2.2
2436 */
2437U_STABLE int32_t U_EXPORT2
2438u_getIntPropertyMinValue(UProperty which);
2439
2440/**
2441 * Get the maximum value for an enumerated/integer/binary Unicode property.
2442 * Can be used together with u_getIntPropertyMinValue
2443 * to allocate arrays of UnicodeSet or similar.
2444 *
2445 * Examples for min/max values (for Unicode 3.2):
2446 *
2447 * - UCHAR_BIDI_CLASS: 0/18 (U_LEFT_TO_RIGHT/U_BOUNDARY_NEUTRAL)
2448 * - UCHAR_SCRIPT: 0/45 (USCRIPT_COMMON/USCRIPT_TAGBANWA)
2449 * - UCHAR_IDEOGRAPHIC: 0/1 (FALSE/TRUE)
2450 *
2451 * For undefined UProperty constant values, min/max values will be 0/-1.
2452 *
2453 * @param which UProperty selector constant, identifies which binary property to check.
2454 * Must be UCHAR_BINARY_START<=which<UCHAR_BINARY_LIMIT
2455 * or UCHAR_INT_START<=which<UCHAR_INT_LIMIT.
2456 * @return Maximum value returned by u_getIntPropertyValue for a Unicode property.
2457 * <=0 if the property selector is out of range.
2458 *
2459 * @see UProperty
2460 * @see u_hasBinaryProperty
2461 * @see u_getUnicodeVersion
2462 * @see u_getIntPropertyMaxValue
2463 * @see u_getIntPropertyValue
2464 * @stable ICU 2.2
2465 */
2466U_STABLE int32_t U_EXPORT2
2467u_getIntPropertyMaxValue(UProperty which);
2468
2469/**
2470 * Get the numeric value for a Unicode code point as defined in the
2471 * Unicode Character Database.
2472 *
2473 * A "double" return type is necessary because
2474 * some numeric values are fractions, negative, or too large for int32_t.
2475 *
2476 * For characters without any numeric values in the Unicode Character Database,
2477 * this function will return U_NO_NUMERIC_VALUE.
2478 * Note: This is different from the Unicode Standard which specifies NaN as the default value.
2479 * (NaN is not available on all platforms.)
2480 *
2481 * Similar to java.lang.Character.getNumericValue(), but u_getNumericValue()
2482 * also supports negative values, large values, and fractions,
2483 * while Java's getNumericValue() returns values 10..35 for ASCII letters.
2484 *
2485 * @param c Code point to get the numeric value for.
2486 * @return Numeric value of c, or U_NO_NUMERIC_VALUE if none is defined.
2487 *
2488 * @see U_NO_NUMERIC_VALUE
2489 * @stable ICU 2.2
2490 */
2491U_STABLE double U_EXPORT2
2492u_getNumericValue(UChar32 c);
2493
2494/**
2495 * Special value that is returned by u_getNumericValue when
2496 * no numeric value is defined for a code point.
2497 *
2498 * @see u_getNumericValue
2499 * @stable ICU 2.2
2500 */
2501#define U_NO_NUMERIC_VALUE ((double)-123456789.)
2502
2503/**
2504 * Determines whether the specified code point has the general category "Ll"
2505 * (lowercase letter).
2506 *
2507 * Same as java.lang.Character.isLowerCase().
2508 *
2509 * This misses some characters that are also lowercase but
2510 * have a different general category value.
2511 * In order to include those, use UCHAR_LOWERCASE.
2512 *
2513 * In addition to being equivalent to a Java function, this also serves
2514 * as a C/POSIX migration function.
2515 * See the comments about C/POSIX character classification functions in the
2516 * documentation at the top of this header file.
2517 *
2518 * @param c the code point to be tested
2519 * @return TRUE if the code point is an Ll lowercase letter
2520 *
2521 * @see UCHAR_LOWERCASE
2522 * @see u_isupper
2523 * @see u_istitle
2524 * @stable ICU 2.0
2525 */
2526U_STABLE UBool U_EXPORT2
2527u_islower(UChar32 c);
2528
2529/**
2530 * Determines whether the specified code point has the general category "Lu"
2531 * (uppercase letter).
2532 *
2533 * Same as java.lang.Character.isUpperCase().
2534 *
2535 * This misses some characters that are also uppercase but
2536 * have a different general category value.
2537 * In order to include those, use UCHAR_UPPERCASE.
2538 *
2539 * In addition to being equivalent to a Java function, this also serves
2540 * as a C/POSIX migration function.
2541 * See the comments about C/POSIX character classification functions in the
2542 * documentation at the top of this header file.
2543 *
2544 * @param c the code point to be tested
2545 * @return TRUE if the code point is an Lu uppercase letter
2546 *
2547 * @see UCHAR_UPPERCASE
2548 * @see u_islower
2549 * @see u_istitle
2550 * @see u_tolower
2551 * @stable ICU 2.0
2552 */
2553U_STABLE UBool U_EXPORT2
2554u_isupper(UChar32 c);
2555
2556/**
2557 * Determines whether the specified code point is a titlecase letter.
2558 * True for general category "Lt" (titlecase letter).
2559 *
2560 * Same as java.lang.Character.isTitleCase().
2561 *
2562 * @param c the code point to be tested
2563 * @return TRUE if the code point is an Lt titlecase letter
2564 *
2565 * @see u_isupper
2566 * @see u_islower
2567 * @see u_totitle
2568 * @stable ICU 2.0
2569 */
2570U_STABLE UBool U_EXPORT2
2571u_istitle(UChar32 c);
2572
2573/**
2574 * Determines whether the specified code point is a digit character according to Java.
2575 * True for characters with general category "Nd" (decimal digit numbers).
2576 * Beginning with Unicode 4, this is the same as
2577 * testing for the Numeric_Type of Decimal.
2578 *
2579 * Same as java.lang.Character.isDigit().
2580 *
2581 * In addition to being equivalent to a Java function, this also serves
2582 * as a C/POSIX migration function.
2583 * See the comments about C/POSIX character classification functions in the
2584 * documentation at the top of this header file.
2585 *
2586 * @param c the code point to be tested
2587 * @return TRUE if the code point is a digit character according to Character.isDigit()
2588 *
2589 * @stable ICU 2.0
2590 */
2591U_STABLE UBool U_EXPORT2
2592u_isdigit(UChar32 c);
2593
2594/**
2595 * Determines whether the specified code point is a letter character.
2596 * True for general categories "L" (letters).
2597 *
2598 * Same as java.lang.Character.isLetter().
2599 *
2600 * In addition to being equivalent to a Java function, this also serves
2601 * as a C/POSIX migration function.
2602 * See the comments about C/POSIX character classification functions in the
2603 * documentation at the top of this header file.
2604 *
2605 * @param c the code point to be tested
2606 * @return TRUE if the code point is a letter character
2607 *
2608 * @see u_isdigit
2609 * @see u_isalnum
2610 * @stable ICU 2.0
2611 */
2612U_STABLE UBool U_EXPORT2
2613u_isalpha(UChar32 c);
2614
2615/**
2616 * Determines whether the specified code point is an alphanumeric character
2617 * (letter or digit) according to Java.
2618 * True for characters with general categories
2619 * "L" (letters) and "Nd" (decimal digit numbers).
2620 *
2621 * Same as java.lang.Character.isLetterOrDigit().
2622 *
2623 * In addition to being equivalent to a Java function, this also serves
2624 * as a C/POSIX migration function.
2625 * See the comments about C/POSIX character classification functions in the
2626 * documentation at the top of this header file.
2627 *
2628 * @param c the code point to be tested
2629 * @return TRUE if the code point is an alphanumeric character according to Character.isLetterOrDigit()
2630 *
2631 * @stable ICU 2.0
2632 */
2633U_STABLE UBool U_EXPORT2
2634u_isalnum(UChar32 c);
2635
2636/**
2637 * Determines whether the specified code point is a hexadecimal digit.
2638 * This is equivalent to u_digit(c, 16)>=0.
2639 * True for characters with general category "Nd" (decimal digit numbers)
2640 * as well as Latin letters a-f and A-F in both ASCII and Fullwidth ASCII.
2641 * (That is, for letters with code points
2642 * 0041..0046, 0061..0066, FF21..FF26, FF41..FF46.)
2643 *
2644 * In order to narrow the definition of hexadecimal digits to only ASCII
2645 * characters, use (c<=0x7f && u_isxdigit(c)).
2646 *
2647 * This is a C/POSIX migration function.
2648 * See the comments about C/POSIX character classification functions in the
2649 * documentation at the top of this header file.
2650 *
2651 * @param c the code point to be tested
2652 * @return TRUE if the code point is a hexadecimal digit
2653 *
2654 * @stable ICU 2.6
2655 */
2656U_STABLE UBool U_EXPORT2
2657u_isxdigit(UChar32 c);
2658
2659/**
2660 * Determines whether the specified code point is a punctuation character.
2661 * True for characters with general categories "P" (punctuation).
2662 *
2663 * This is a C/POSIX migration function.
2664 * See the comments about C/POSIX character classification functions in the
2665 * documentation at the top of this header file.
2666 *
2667 * @param c the code point to be tested
2668 * @return TRUE if the code point is a punctuation character
2669 *
2670 * @stable ICU 2.6
2671 */
2672U_STABLE UBool U_EXPORT2
2673u_ispunct(UChar32 c);
2674
2675/**
2676 * Determines whether the specified code point is a "graphic" character
2677 * (printable, excluding spaces).
2678 * TRUE for all characters except those with general categories
2679 * "Cc" (control codes), "Cf" (format controls), "Cs" (surrogates),
2680 * "Cn" (unassigned), and "Z" (separators).
2681 *
2682 * This is a C/POSIX migration function.
2683 * See the comments about C/POSIX character classification functions in the
2684 * documentation at the top of this header file.
2685 *
2686 * @param c the code point to be tested
2687 * @return TRUE if the code point is a "graphic" character
2688 *
2689 * @stable ICU 2.6
2690 */
2691U_STABLE UBool U_EXPORT2
2692u_isgraph(UChar32 c);
2693
2694/**
2695 * Determines whether the specified code point is a "blank" or "horizontal space",
2696 * a character that visibly separates words on a line.
2697 * The following are equivalent definitions:
2698 *
2699 * TRUE for Unicode White_Space characters except for "vertical space controls"
2700 * where "vertical space controls" are the following characters:
2701 * U+000A (LF) U+000B (VT) U+000C (FF) U+000D (CR) U+0085 (NEL) U+2028 (LS) U+2029 (PS)
2702 *
2703 * same as
2704 *
2705 * TRUE for U+0009 (TAB) and characters with general category "Zs" (space separators)
2706 * except Zero Width Space (ZWSP, U+200B).
2707 *
2708 * Note: There are several ICU whitespace functions; please see the uchar.h
2709 * file documentation for a detailed comparison.
2710 *
2711 * This is a C/POSIX migration function.
2712 * See the comments about C/POSIX character classification functions in the
2713 * documentation at the top of this header file.
2714 *
2715 * @param c the code point to be tested
2716 * @return TRUE if the code point is a "blank"
2717 *
2718 * @stable ICU 2.6
2719 */
2720U_STABLE UBool U_EXPORT2
2721u_isblank(UChar32 c);
2722
2723/**
2724 * Determines whether the specified code point is "defined",
2725 * which usually means that it is assigned a character.
2726 * True for general categories other than "Cn" (other, not assigned),
2727 * i.e., true for all code points mentioned in UnicodeData.txt.
2728 *
2729 * Note that non-character code points (e.g., U+FDD0) are not "defined"
2730 * (they are Cn), but surrogate code points are "defined" (Cs).
2731 *
2732 * Same as java.lang.Character.isDefined().
2733 *
2734 * @param c the code point to be tested
2735 * @return TRUE if the code point is assigned a character
2736 *
2737 * @see u_isdigit
2738 * @see u_isalpha
2739 * @see u_isalnum
2740 * @see u_isupper
2741 * @see u_islower
2742 * @see u_istitle
2743 * @stable ICU 2.0
2744 */
2745U_STABLE UBool U_EXPORT2
2746u_isdefined(UChar32 c);
2747
2748/**
2749 * Determines if the specified character is a space character or not.
2750 *
2751 * Note: There are several ICU whitespace functions; please see the uchar.h
2752 * file documentation for a detailed comparison.
2753 *
2754 * This is a C/POSIX migration function.
2755 * See the comments about C/POSIX character classification functions in the
2756 * documentation at the top of this header file.
2757 *
2758 * @param c the character to be tested
2759 * @return true if the character is a space character; false otherwise.
2760 *
2761 * @see u_isJavaSpaceChar
2762 * @see u_isWhitespace
2763 * @see u_isUWhiteSpace
2764 * @stable ICU 2.0
2765 */
2766U_STABLE UBool U_EXPORT2
2767u_isspace(UChar32 c);
2768
2769/**
2770 * Determine if the specified code point is a space character according to Java.
2771 * True for characters with general categories "Z" (separators),
2772 * which does not include control codes (e.g., TAB or Line Feed).
2773 *
2774 * Same as java.lang.Character.isSpaceChar().
2775 *
2776 * Note: There are several ICU whitespace functions; please see the uchar.h
2777 * file documentation for a detailed comparison.
2778 *
2779 * @param c the code point to be tested
2780 * @return TRUE if the code point is a space character according to Character.isSpaceChar()
2781 *
2782 * @see u_isspace
2783 * @see u_isWhitespace
2784 * @see u_isUWhiteSpace
2785 * @stable ICU 2.6
2786 */
2787U_STABLE UBool U_EXPORT2
2788u_isJavaSpaceChar(UChar32 c);
2789
2790/**
2791 * Determines if the specified code point is a whitespace character according to Java/ICU.
2792 * A character is considered to be a Java whitespace character if and only
2793 * if it satisfies one of the following criteria:
2794 *
2795 * - It is a Unicode Separator character (categories "Z" = "Zs" or "Zl" or "Zp"), but is not
2796 * also a non-breaking space (U+00A0 NBSP or U+2007 Figure Space or U+202F Narrow NBSP).
2797 * - It is U+0009 HORIZONTAL TABULATION.
2798 * - It is U+000A LINE FEED.
2799 * - It is U+000B VERTICAL TABULATION.
2800 * - It is U+000C FORM FEED.
2801 * - It is U+000D CARRIAGE RETURN.
2802 * - It is U+001C FILE SEPARATOR.
2803 * - It is U+001D GROUP SEPARATOR.
2804 * - It is U+001E RECORD SEPARATOR.
2805 * - It is U+001F UNIT SEPARATOR.
2806 *
2807 * This API tries to sync with the semantics of Java's
2808 * java.lang.Character.isWhitespace(), but it may not return
2809 * the exact same results because of the Unicode version
2810 * difference.
2811 *
2812 * Note: Unicode 4.0.1 changed U+200B ZERO WIDTH SPACE from a Space Separator (Zs)
2813 * to a Format Control (Cf). Since then, isWhitespace(0x200b) returns false.
2814 * See http://www.unicode.org/versions/Unicode4.0.1/
2815 *
2816 * Note: There are several ICU whitespace functions; please see the uchar.h
2817 * file documentation for a detailed comparison.
2818 *
2819 * @param c the code point to be tested
2820 * @return TRUE if the code point is a whitespace character according to Java/ICU
2821 *
2822 * @see u_isspace
2823 * @see u_isJavaSpaceChar
2824 * @see u_isUWhiteSpace
2825 * @stable ICU 2.0
2826 */
2827U_STABLE UBool U_EXPORT2
2828u_isWhitespace(UChar32 c);
2829
2830/**
2831 * Determines whether the specified code point is a control character
2832 * (as defined by this function).
2833 * A control character is one of the following:
2834 * - ISO 8-bit control character (U+0000..U+001f and U+007f..U+009f)
2835 * - U_CONTROL_CHAR (Cc)
2836 * - U_FORMAT_CHAR (Cf)
2837 * - U_LINE_SEPARATOR (Zl)
2838 * - U_PARAGRAPH_SEPARATOR (Zp)
2839 *
2840 * This is a C/POSIX migration function.
2841 * See the comments about C/POSIX character classification functions in the
2842 * documentation at the top of this header file.
2843 *
2844 * @param c the code point to be tested
2845 * @return TRUE if the code point is a control character
2846 *
2847 * @see UCHAR_DEFAULT_IGNORABLE_CODE_POINT
2848 * @see u_isprint
2849 * @stable ICU 2.0
2850 */
2851U_STABLE UBool U_EXPORT2
2852u_iscntrl(UChar32 c);
2853
2854/**
2855 * Determines whether the specified code point is an ISO control code.
2856 * True for U+0000..U+001f and U+007f..U+009f (general category "Cc").
2857 *
2858 * Same as java.lang.Character.isISOControl().
2859 *
2860 * @param c the code point to be tested
2861 * @return TRUE if the code point is an ISO control code
2862 *
2863 * @see u_iscntrl
2864 * @stable ICU 2.6
2865 */
2866U_STABLE UBool U_EXPORT2
2867u_isISOControl(UChar32 c);
2868
2869/**
2870 * Determines whether the specified code point is a printable character.
2871 * True for general categories <em>other</em> than "C" (controls).
2872 *
2873 * This is a C/POSIX migration function.
2874 * See the comments about C/POSIX character classification functions in the
2875 * documentation at the top of this header file.
2876 *
2877 * @param c the code point to be tested
2878 * @return TRUE if the code point is a printable character
2879 *
2880 * @see UCHAR_DEFAULT_IGNORABLE_CODE_POINT
2881 * @see u_iscntrl
2882 * @stable ICU 2.0
2883 */
2884U_STABLE UBool U_EXPORT2
2885u_isprint(UChar32 c);
2886
2887/**
2888 * Determines whether the specified code point is a base character.
2889 * True for general categories "L" (letters), "N" (numbers),
2890 * "Mc" (spacing combining marks), and "Me" (enclosing marks).
2891 *
2892 * Note that this is different from the Unicode definition in
2893 * chapter 3.5, conformance clause D13,
2894 * which defines base characters to be all characters (not Cn)
2895 * that do not graphically combine with preceding characters (M)
2896 * and that are neither control (Cc) or format (Cf) characters.
2897 *
2898 * @param c the code point to be tested
2899 * @return TRUE if the code point is a base character according to this function
2900 *
2901 * @see u_isalpha
2902 * @see u_isdigit
2903 * @stable ICU 2.0
2904 */
2905U_STABLE UBool U_EXPORT2
2906u_isbase(UChar32 c);
2907
2908/**
2909 * Returns the bidirectional category value for the code point,
2910 * which is used in the Unicode bidirectional algorithm
2911 * (UAX #9 http://www.unicode.org/reports/tr9/).
2912 * Note that some <em>unassigned</em> code points have bidi values
2913 * of R or AL because they are in blocks that are reserved
2914 * for Right-To-Left scripts.
2915 *
2916 * Same as java.lang.Character.getDirectionality()
2917 *
2918 * @param c the code point to be tested
2919 * @return the bidirectional category (UCharDirection) value
2920 *
2921 * @see UCharDirection
2922 * @stable ICU 2.0
2923 */
2924U_STABLE UCharDirection U_EXPORT2
2925u_charDirection(UChar32 c);
2926
2927/**
2928 * Determines whether the code point has the Bidi_Mirrored property.
2929 * This property is set for characters that are commonly used in
2930 * Right-To-Left contexts and need to be displayed with a "mirrored"
2931 * glyph.
2932 *
2933 * Same as java.lang.Character.isMirrored().
2934 * Same as UCHAR_BIDI_MIRRORED
2935 *
2936 * @param c the code point to be tested
2937 * @return TRUE if the character has the Bidi_Mirrored property
2938 *
2939 * @see UCHAR_BIDI_MIRRORED
2940 * @stable ICU 2.0
2941 */
2942U_STABLE UBool U_EXPORT2
2943u_isMirrored(UChar32 c);
2944
2945/**
2946 * Maps the specified character to a "mirror-image" character.
2947 * For characters with the Bidi_Mirrored property, implementations
2948 * sometimes need a "poor man's" mapping to another Unicode
2949 * character (code point) such that the default glyph may serve
2950 * as the mirror-image of the default glyph of the specified
2951 * character. This is useful for text conversion to and from
2952 * codepages with visual order, and for displays without glyph
2953 * selection capabilities.
2954 *
2955 * @param c the code point to be mapped
2956 * @return another Unicode code point that may serve as a mirror-image
2957 * substitute, or c itself if there is no such mapping or c
2958 * does not have the Bidi_Mirrored property
2959 *
2960 * @see UCHAR_BIDI_MIRRORED
2961 * @see u_isMirrored
2962 * @stable ICU 2.0
2963 */
2964U_STABLE UChar32 U_EXPORT2
2965u_charMirror(UChar32 c);
2966
2967/**
2968 * Maps the specified character to its paired bracket character.
2969 * For Bidi_Paired_Bracket_Type!=None, this is the same as u_charMirror().
2970 * Otherwise c itself is returned.
2971 * See http://www.unicode.org/reports/tr9/
2972 *
2973 * @param c the code point to be mapped
2974 * @return the paired bracket code point,
2975 * or c itself if there is no such mapping
2976 * (Bidi_Paired_Bracket_Type=None)
2977 *
2978 * @see UCHAR_BIDI_PAIRED_BRACKET
2979 * @see UCHAR_BIDI_PAIRED_BRACKET_TYPE
2980 * @see u_charMirror
2981 * @stable ICU 52
2982 */
2983U_STABLE UChar32 U_EXPORT2
2984u_getBidiPairedBracket(UChar32 c);
2985
2986/**
2987 * Returns the general category value for the code point.
2988 *
2989 * Same as java.lang.Character.getType().
2990 *
2991 * @param c the code point to be tested
2992 * @return the general category (UCharCategory) value
2993 *
2994 * @see UCharCategory
2995 * @stable ICU 2.0
2996 */
2997U_STABLE int8_t U_EXPORT2
2998u_charType(UChar32 c);
2999
3000/**
3001 * Get a single-bit bit set for the general category of a character.
3002 * This bit set can be compared bitwise with U_GC_SM_MASK, U_GC_L_MASK, etc.
3003 * Same as U_MASK(u_charType(c)).
3004 *
3005 * @param c the code point to be tested
3006 * @return a single-bit mask corresponding to the general category (UCharCategory) value
3007 *
3008 * @see u_charType
3009 * @see UCharCategory
3010 * @see U_GC_CN_MASK
3011 * @stable ICU 2.1
3012 */
3013#define U_GET_GC_MASK(c) U_MASK(u_charType(c))
3014
3015/**
3016 * Callback from u_enumCharTypes(), is called for each contiguous range
3017 * of code points c (where start<=c<limit)
3018 * with the same Unicode general category ("character type").
3019 *
3020 * The callback function can stop the enumeration by returning FALSE.
3021 *
3022 * @param context an opaque pointer, as passed into utrie_enum()
3023 * @param start the first code point in a contiguous range with value
3024 * @param limit one past the last code point in a contiguous range with value
3025 * @param type the general category for all code points in [start..limit[
3026 * @return FALSE to stop the enumeration
3027 *
3028 * @stable ICU 2.1
3029 * @see UCharCategory
3030 * @see u_enumCharTypes
3031 */
3032typedef UBool U_CALLCONV
3033UCharEnumTypeRange(const void *context, UChar32 start, UChar32 limit, UCharCategory type);
3034
3035/**
3036 * Enumerate efficiently all code points with their Unicode general categories.
3037 *
3038 * This is useful for building data structures (e.g., UnicodeSet's),
3039 * for enumerating all assigned code points (type!=U_UNASSIGNED), etc.
3040 *
3041 * For each contiguous range of code points with a given general category ("character type"),
3042 * the UCharEnumTypeRange function is called.
3043 * Adjacent ranges have different types.
3044 * The Unicode Standard guarantees that the numeric value of the type is 0..31.
3045 *
3046 * @param enumRange a pointer to a function that is called for each contiguous range
3047 * of code points with the same general category
3048 * @param context an opaque pointer that is passed on to the callback function
3049 *
3050 * @stable ICU 2.1
3051 * @see UCharCategory
3052 * @see UCharEnumTypeRange
3053 */
3054U_STABLE void U_EXPORT2
3055u_enumCharTypes(UCharEnumTypeRange *enumRange, const void *context);
3056
3057#if !UCONFIG_NO_NORMALIZATION
3058
3059/**
3060 * Returns the combining class of the code point as specified in UnicodeData.txt.
3061 *
3062 * @param c the code point of the character
3063 * @return the combining class of the character
3064 * @stable ICU 2.0
3065 */
3066U_STABLE uint8_t U_EXPORT2
3067u_getCombiningClass(UChar32 c);
3068
3069#endif
3070
3071/**
3072 * Returns the decimal digit value of a decimal digit character.
3073 * Such characters have the general category "Nd" (decimal digit numbers)
3074 * and a Numeric_Type of Decimal.
3075 *
3076 * Unlike ICU releases before 2.6, no digit values are returned for any
3077 * Han characters because Han number characters are often used with a special
3078 * Chinese-style number format (with characters for powers of 10 in between)
3079 * instead of in decimal-positional notation.
3080 * Unicode 4 explicitly assigns Han number characters the Numeric_Type
3081 * Numeric instead of Decimal.
3082 * See Jitterbug 1483 for more details.
3083 *
3084 * Use u_getIntPropertyValue(c, UCHAR_NUMERIC_TYPE) and u_getNumericValue()
3085 * for complete numeric Unicode properties.
3086 *
3087 * @param c the code point for which to get the decimal digit value
3088 * @return the decimal digit value of c,
3089 * or -1 if c is not a decimal digit character
3090 *
3091 * @see u_getNumericValue
3092 * @stable ICU 2.0
3093 */
3094U_STABLE int32_t U_EXPORT2
3095u_charDigitValue(UChar32 c);
3096
3097/**
3098 * Returns the Unicode allocation block that contains the character.
3099 *
3100 * @param c the code point to be tested
3101 * @return the block value (UBlockCode) for c
3102 *
3103 * @see UBlockCode
3104 * @stable ICU 2.0
3105 */
3106U_STABLE UBlockCode U_EXPORT2
3107ublock_getCode(UChar32 c);
3108
3109/**
3110 * Retrieve the name of a Unicode character.
3111 * Depending on <code>nameChoice</code>, the character name written
3112 * into the buffer is the "modern" name or the name that was defined
3113 * in Unicode version 1.0.
3114 * The name contains only "invariant" characters
3115 * like A-Z, 0-9, space, and '-'.
3116 * Unicode 1.0 names are only retrieved if they are different from the modern
3117 * names and if the data file contains the data for them. gennames may or may
3118 * not be called with a command line option to include 1.0 names in unames.dat.
3119 *
3120 * @param code The character (code point) for which to get the name.
3121 * It must be <code>0<=code<=0x10ffff</code>.
3122 * @param nameChoice Selector for which name to get.
3123 * @param buffer Destination address for copying the name.
3124 * The name will always be zero-terminated.
3125 * If there is no name, then the buffer will be set to the empty string.
3126 * @param bufferLength <code>==sizeof(buffer)</code>
3127 * @param pErrorCode Pointer to a UErrorCode variable;
3128 * check for <code>U_SUCCESS()</code> after <code>u_charName()</code>
3129 * returns.
3130 * @return The length of the name, or 0 if there is no name for this character.
3131 * If the bufferLength is less than or equal to the length, then the buffer
3132 * contains the truncated name and the returned length indicates the full
3133 * length of the name.
3134 * The length does not include the zero-termination.
3135 *
3136 * @see UCharNameChoice
3137 * @see u_charFromName
3138 * @see u_enumCharNames
3139 * @stable ICU 2.0
3140 */
3141U_STABLE int32_t U_EXPORT2
3142u_charName(UChar32 code, UCharNameChoice nameChoice,
3143 char *buffer, int32_t bufferLength,
3144 UErrorCode *pErrorCode);
3145
3146#ifndef U_HIDE_DEPRECATED_API
3147/**
3148 * Returns an empty string.
3149 * Used to return the ISO 10646 comment for a character.
3150 * The Unicode ISO_Comment property is deprecated and has no values.
3151 *
3152 * @param c The character (code point) for which to get the ISO comment.
3153 * It must be <code>0<=c<=0x10ffff</code>.
3154 * @param dest Destination address for copying the comment.
3155 * The comment will be zero-terminated if possible.
3156 * If there is no comment, then the buffer will be set to the empty string.
3157 * @param destCapacity <code>==sizeof(dest)</code>
3158 * @param pErrorCode Pointer to a UErrorCode variable;
3159 * check for <code>U_SUCCESS()</code> after <code>u_getISOComment()</code>
3160 * returns.
3161 * @return 0
3162 *
3163 * @deprecated ICU 49
3164 */
3165U_DEPRECATED int32_t U_EXPORT2
3166u_getISOComment(UChar32 c,
3167 char *dest, int32_t destCapacity,
3168 UErrorCode *pErrorCode);
3169#endif /* U_HIDE_DEPRECATED_API */
3170
3171/**
3172 * Find a Unicode character by its name and return its code point value.
3173 * The name is matched exactly and completely.
3174 * If the name does not correspond to a code point, <i>pErrorCode</i>
3175 * is set to <code>U_INVALID_CHAR_FOUND</code>.
3176 * A Unicode 1.0 name is matched only if it differs from the modern name.
3177 * Unicode names are all uppercase. Extended names are lowercase followed
3178 * by an uppercase hexadecimal number, and within angle brackets.
3179 *
3180 * @param nameChoice Selector for which name to match.
3181 * @param name The name to match.
3182 * @param pErrorCode Pointer to a UErrorCode variable
3183 * @return The Unicode value of the code point with the given name,
3184 * or an undefined value if there is no such code point.
3185 *
3186 * @see UCharNameChoice
3187 * @see u_charName
3188 * @see u_enumCharNames
3189 * @stable ICU 1.7
3190 */
3191U_STABLE UChar32 U_EXPORT2
3192u_charFromName(UCharNameChoice nameChoice,
3193 const char *name,
3194 UErrorCode *pErrorCode);
3195
3196/**
3197 * Type of a callback function for u_enumCharNames() that gets called
3198 * for each Unicode character with the code point value and
3199 * the character name.
3200 * If such a function returns FALSE, then the enumeration is stopped.
3201 *
3202 * @param context The context pointer that was passed to u_enumCharNames().
3203 * @param code The Unicode code point for the character with this name.
3204 * @param nameChoice Selector for which kind of names is enumerated.
3205 * @param name The character's name, zero-terminated.
3206 * @param length The length of the name.
3207 * @return TRUE if the enumeration should continue, FALSE to stop it.
3208 *
3209 * @see UCharNameChoice
3210 * @see u_enumCharNames
3211 * @stable ICU 1.7
3212 */
3213typedef UBool U_CALLCONV UEnumCharNamesFn(void *context,
3214 UChar32 code,
3215 UCharNameChoice nameChoice,
3216 const char *name,
3217 int32_t length);
3218
3219/**
3220 * Enumerate all assigned Unicode characters between the start and limit
3221 * code points (start inclusive, limit exclusive) and call a function
3222 * for each, passing the code point value and the character name.
3223 * For Unicode 1.0 names, only those are enumerated that differ from the
3224 * modern names.
3225 *
3226 * @param start The first code point in the enumeration range.
3227 * @param limit One more than the last code point in the enumeration range
3228 * (the first one after the range).
3229 * @param fn The function that is to be called for each character name.
3230 * @param context An arbitrary pointer that is passed to the function.
3231 * @param nameChoice Selector for which kind of names to enumerate.
3232 * @param pErrorCode Pointer to a UErrorCode variable
3233 *
3234 * @see UCharNameChoice
3235 * @see UEnumCharNamesFn
3236 * @see u_charName
3237 * @see u_charFromName
3238 * @stable ICU 1.7
3239 */
3240U_STABLE void U_EXPORT2
3241u_enumCharNames(UChar32 start, UChar32 limit,
3242 UEnumCharNamesFn *fn,
3243 void *context,
3244 UCharNameChoice nameChoice,
3245 UErrorCode *pErrorCode);
3246
3247/**
3248 * Return the Unicode name for a given property, as given in the
3249 * Unicode database file PropertyAliases.txt.
3250 *
3251 * In addition, this function maps the property
3252 * UCHAR_GENERAL_CATEGORY_MASK to the synthetic names "gcm" /
3253 * "General_Category_Mask". These names are not in
3254 * PropertyAliases.txt.
3255 *
3256 * @param property UProperty selector other than UCHAR_INVALID_CODE.
3257 * If out of range, NULL is returned.
3258 *
3259 * @param nameChoice selector for which name to get. If out of range,
3260 * NULL is returned. All properties have a long name. Most
3261 * have a short name, but some do not. Unicode allows for
3262 * additional names; if present these will be returned by
3263 * U_LONG_PROPERTY_NAME + i, where i=1, 2,...
3264 *
3265 * @return a pointer to the name, or NULL if either the
3266 * property or the nameChoice is out of range. If a given
3267 * nameChoice returns NULL, then all larger values of
3268 * nameChoice will return NULL, with one exception: if NULL is
3269 * returned for U_SHORT_PROPERTY_NAME, then
3270 * U_LONG_PROPERTY_NAME (and higher) may still return a
3271 * non-NULL value. The returned pointer is valid until
3272 * u_cleanup() is called.
3273 *
3274 * @see UProperty
3275 * @see UPropertyNameChoice
3276 * @stable ICU 2.4
3277 */
3278U_STABLE const char* U_EXPORT2
3279u_getPropertyName(UProperty property,
3280 UPropertyNameChoice nameChoice);
3281
3282/**
3283 * Return the UProperty enum for a given property name, as specified
3284 * in the Unicode database file PropertyAliases.txt. Short, long, and
3285 * any other variants are recognized.
3286 *
3287 * In addition, this function maps the synthetic names "gcm" /
3288 * "General_Category_Mask" to the property
3289 * UCHAR_GENERAL_CATEGORY_MASK. These names are not in
3290 * PropertyAliases.txt.
3291 *
3292 * @param alias the property name to be matched. The name is compared
3293 * using "loose matching" as described in PropertyAliases.txt.
3294 *
3295 * @return a UProperty enum, or UCHAR_INVALID_CODE if the given name
3296 * does not match any property.
3297 *
3298 * @see UProperty
3299 * @stable ICU 2.4
3300 */
3301U_STABLE UProperty U_EXPORT2
3302u_getPropertyEnum(const char* alias);
3303
3304/**
3305 * Return the Unicode name for a given property value, as given in the
3306 * Unicode database file PropertyValueAliases.txt.
3307 *
3308 * Note: Some of the names in PropertyValueAliases.txt can only be
3309 * retrieved using UCHAR_GENERAL_CATEGORY_MASK, not
3310 * UCHAR_GENERAL_CATEGORY. These include: "C" / "Other", "L" /
3311 * "Letter", "LC" / "Cased_Letter", "M" / "Mark", "N" / "Number", "P"
3312 * / "Punctuation", "S" / "Symbol", and "Z" / "Separator".
3313 *
3314 * @param property UProperty selector constant.
3315 * Must be UCHAR_BINARY_START<=which<UCHAR_BINARY_LIMIT
3316 * or UCHAR_INT_START<=which<UCHAR_INT_LIMIT
3317 * or UCHAR_MASK_START<=which<UCHAR_MASK_LIMIT.
3318 * If out of range, NULL is returned.
3319 *
3320 * @param value selector for a value for the given property. If out
3321 * of range, NULL is returned. In general, valid values range
3322 * from 0 up to some maximum. There are a few exceptions:
3323 * (1.) UCHAR_BLOCK values begin at the non-zero value
3324 * UBLOCK_BASIC_LATIN. (2.) UCHAR_CANONICAL_COMBINING_CLASS
3325 * values are not contiguous and range from 0..240. (3.)
3326 * UCHAR_GENERAL_CATEGORY_MASK values are not values of
3327 * UCharCategory, but rather mask values produced by
3328 * U_GET_GC_MASK(). This allows grouped categories such as
3329 * [:L:] to be represented. Mask values range
3330 * non-contiguously from 1..U_GC_P_MASK.
3331 *
3332 * @param nameChoice selector for which name to get. If out of range,
3333 * NULL is returned. All values have a long name. Most have
3334 * a short name, but some do not. Unicode allows for
3335 * additional names; if present these will be returned by
3336 * U_LONG_PROPERTY_NAME + i, where i=1, 2,...
3337
3338 * @return a pointer to the name, or NULL if either the
3339 * property or the nameChoice is out of range. If a given
3340 * nameChoice returns NULL, then all larger values of
3341 * nameChoice will return NULL, with one exception: if NULL is
3342 * returned for U_SHORT_PROPERTY_NAME, then
3343 * U_LONG_PROPERTY_NAME (and higher) may still return a
3344 * non-NULL value. The returned pointer is valid until
3345 * u_cleanup() is called.
3346 *
3347 * @see UProperty
3348 * @see UPropertyNameChoice
3349 * @stable ICU 2.4
3350 */
3351U_STABLE const char* U_EXPORT2
3352u_getPropertyValueName(UProperty property,
3353 int32_t value,
3354 UPropertyNameChoice nameChoice);
3355
3356/**
3357 * Return the property value integer for a given value name, as
3358 * specified in the Unicode database file PropertyValueAliases.txt.
3359 * Short, long, and any other variants are recognized.
3360 *
3361 * Note: Some of the names in PropertyValueAliases.txt will only be
3362 * recognized with UCHAR_GENERAL_CATEGORY_MASK, not
3363 * UCHAR_GENERAL_CATEGORY. These include: "C" / "Other", "L" /
3364 * "Letter", "LC" / "Cased_Letter", "M" / "Mark", "N" / "Number", "P"
3365 * / "Punctuation", "S" / "Symbol", and "Z" / "Separator".
3366 *
3367 * @param property UProperty selector constant.
3368 * Must be UCHAR_BINARY_START<=which<UCHAR_BINARY_LIMIT
3369 * or UCHAR_INT_START<=which<UCHAR_INT_LIMIT
3370 * or UCHAR_MASK_START<=which<UCHAR_MASK_LIMIT.
3371 * If out of range, UCHAR_INVALID_CODE is returned.
3372 *
3373 * @param alias the value name to be matched. The name is compared
3374 * using "loose matching" as described in
3375 * PropertyValueAliases.txt.
3376 *
3377 * @return a value integer or UCHAR_INVALID_CODE if the given name
3378 * does not match any value of the given property, or if the
3379 * property is invalid. Note: UCHAR_GENERAL_CATEGORY_MASK values
3380 * are not values of UCharCategory, but rather mask values
3381 * produced by U_GET_GC_MASK(). This allows grouped
3382 * categories such as [:L:] to be represented.
3383 *
3384 * @see UProperty
3385 * @stable ICU 2.4
3386 */
3387U_STABLE int32_t U_EXPORT2
3388u_getPropertyValueEnum(UProperty property,
3389 const char* alias);
3390
3391/**
3392 * Determines if the specified character is permissible as the
3393 * first character in an identifier according to Unicode
3394 * (The Unicode Standard, Version 3.0, chapter 5.16 Identifiers).
3395 * True for characters with general categories "L" (letters) and "Nl" (letter numbers).
3396 *
3397 * Same as java.lang.Character.isUnicodeIdentifierStart().
3398 * Same as UCHAR_ID_START
3399 *
3400 * @param c the code point to be tested
3401 * @return TRUE if the code point may start an identifier
3402 *
3403 * @see UCHAR_ID_START
3404 * @see u_isalpha
3405 * @see u_isIDPart
3406 * @stable ICU 2.0
3407 */
3408U_STABLE UBool U_EXPORT2
3409u_isIDStart(UChar32 c);
3410
3411/**
3412 * Determines if the specified character is permissible
3413 * in an identifier according to Java.
3414 * True for characters with general categories "L" (letters),
3415 * "Nl" (letter numbers), "Nd" (decimal digits),
3416 * "Mc" and "Mn" (combining marks), "Pc" (connecting punctuation), and
3417 * u_isIDIgnorable(c).
3418 *
3419 * Same as java.lang.Character.isUnicodeIdentifierPart().
3420 * Almost the same as Unicode's ID_Continue (UCHAR_ID_CONTINUE)
3421 * except that Unicode recommends to ignore Cf which is less than
3422 * u_isIDIgnorable(c).
3423 *
3424 * @param c the code point to be tested
3425 * @return TRUE if the code point may occur in an identifier according to Java
3426 *
3427 * @see UCHAR_ID_CONTINUE
3428 * @see u_isIDStart
3429 * @see u_isIDIgnorable
3430 * @stable ICU 2.0
3431 */
3432U_STABLE UBool U_EXPORT2
3433u_isIDPart(UChar32 c);
3434
3435/**
3436 * Determines if the specified character should be regarded
3437 * as an ignorable character in an identifier,
3438 * according to Java.
3439 * True for characters with general category "Cf" (format controls) as well as
3440 * non-whitespace ISO controls
3441 * (U+0000..U+0008, U+000E..U+001B, U+007F..U+009F).
3442 *
3443 * Same as java.lang.Character.isIdentifierIgnorable().
3444 *
3445 * Note that Unicode just recommends to ignore Cf (format controls).
3446 *
3447 * @param c the code point to be tested
3448 * @return TRUE if the code point is ignorable in identifiers according to Java
3449 *
3450 * @see UCHAR_DEFAULT_IGNORABLE_CODE_POINT
3451 * @see u_isIDStart
3452 * @see u_isIDPart
3453 * @stable ICU 2.0
3454 */
3455U_STABLE UBool U_EXPORT2
3456u_isIDIgnorable(UChar32 c);
3457
3458/**
3459 * Determines if the specified character is permissible as the
3460 * first character in a Java identifier.
3461 * In addition to u_isIDStart(c), true for characters with
3462 * general categories "Sc" (currency symbols) and "Pc" (connecting punctuation).
3463 *
3464 * Same as java.lang.Character.isJavaIdentifierStart().
3465 *
3466 * @param c the code point to be tested
3467 * @return TRUE if the code point may start a Java identifier
3468 *
3469 * @see u_isJavaIDPart
3470 * @see u_isalpha
3471 * @see u_isIDStart
3472 * @stable ICU 2.0
3473 */
3474U_STABLE UBool U_EXPORT2
3475u_isJavaIDStart(UChar32 c);
3476
3477/**
3478 * Determines if the specified character is permissible
3479 * in a Java identifier.
3480 * In addition to u_isIDPart(c), true for characters with
3481 * general category "Sc" (currency symbols).
3482 *
3483 * Same as java.lang.Character.isJavaIdentifierPart().
3484 *
3485 * @param c the code point to be tested
3486 * @return TRUE if the code point may occur in a Java identifier
3487 *
3488 * @see u_isIDIgnorable
3489 * @see u_isJavaIDStart
3490 * @see u_isalpha
3491 * @see u_isdigit
3492 * @see u_isIDPart
3493 * @stable ICU 2.0
3494 */
3495U_STABLE UBool U_EXPORT2
3496u_isJavaIDPart(UChar32 c);
3497
3498/**
3499 * The given character is mapped to its lowercase equivalent according to
3500 * UnicodeData.txt; if the character has no lowercase equivalent, the character
3501 * itself is returned.
3502 *
3503 * Same as java.lang.Character.toLowerCase().
3504 *
3505 * This function only returns the simple, single-code point case mapping.
3506 * Full case mappings should be used whenever possible because they produce
3507 * better results by working on whole strings.
3508 * They take into account the string context and the language and can map
3509 * to a result string with a different length as appropriate.
3510 * Full case mappings are applied by the string case mapping functions,
3511 * see ustring.h and the UnicodeString class.
3512 * See also the User Guide chapter on C/POSIX migration:
3513 * http://icu-project.org/userguide/posix.html#case_mappings
3514 *
3515 * @param c the code point to be mapped
3516 * @return the Simple_Lowercase_Mapping of the code point, if any;
3517 * otherwise the code point itself.
3518 * @stable ICU 2.0
3519 */
3520U_STABLE UChar32 U_EXPORT2
3521u_tolower(UChar32 c);
3522
3523/**
3524 * The given character is mapped to its uppercase equivalent according to UnicodeData.txt;
3525 * if the character has no uppercase equivalent, the character itself is
3526 * returned.
3527 *
3528 * Same as java.lang.Character.toUpperCase().
3529 *
3530 * This function only returns the simple, single-code point case mapping.
3531 * Full case mappings should be used whenever possible because they produce
3532 * better results by working on whole strings.
3533 * They take into account the string context and the language and can map
3534 * to a result string with a different length as appropriate.
3535 * Full case mappings are applied by the string case mapping functions,
3536 * see ustring.h and the UnicodeString class.
3537 * See also the User Guide chapter on C/POSIX migration:
3538 * http://icu-project.org/userguide/posix.html#case_mappings
3539 *
3540 * @param c the code point to be mapped
3541 * @return the Simple_Uppercase_Mapping of the code point, if any;
3542 * otherwise the code point itself.
3543 * @stable ICU 2.0
3544 */
3545U_STABLE UChar32 U_EXPORT2
3546u_toupper(UChar32 c);
3547
3548/**
3549 * The given character is mapped to its titlecase equivalent
3550 * according to UnicodeData.txt;
3551 * if none is defined, the character itself is returned.
3552 *
3553 * Same as java.lang.Character.toTitleCase().
3554 *
3555 * This function only returns the simple, single-code point case mapping.
3556 * Full case mappings should be used whenever possible because they produce
3557 * better results by working on whole strings.
3558 * They take into account the string context and the language and can map
3559 * to a result string with a different length as appropriate.
3560 * Full case mappings are applied by the string case mapping functions,
3561 * see ustring.h and the UnicodeString class.
3562 * See also the User Guide chapter on C/POSIX migration:
3563 * http://icu-project.org/userguide/posix.html#case_mappings
3564 *
3565 * @param c the code point to be mapped
3566 * @return the Simple_Titlecase_Mapping of the code point, if any;
3567 * otherwise the code point itself.
3568 * @stable ICU 2.0
3569 */
3570U_STABLE UChar32 U_EXPORT2
3571u_totitle(UChar32 c);
3572
3573/**
3574 * The given character is mapped to its case folding equivalent according to
3575 * UnicodeData.txt and CaseFolding.txt;
3576 * if the character has no case folding equivalent, the character
3577 * itself is returned.
3578 *
3579 * This function only returns the simple, single-code point case mapping.
3580 * Full case mappings should be used whenever possible because they produce
3581 * better results by working on whole strings.
3582 * They take into account the string context and the language and can map
3583 * to a result string with a different length as appropriate.
3584 * Full case mappings are applied by the string case mapping functions,
3585 * see ustring.h and the UnicodeString class.
3586 * See also the User Guide chapter on C/POSIX migration:
3587 * http://icu-project.org/userguide/posix.html#case_mappings
3588 *
3589 * @param c the code point to be mapped
3590 * @param options Either U_FOLD_CASE_DEFAULT or U_FOLD_CASE_EXCLUDE_SPECIAL_I
3591 * @return the Simple_Case_Folding of the code point, if any;
3592 * otherwise the code point itself.
3593 * @stable ICU 2.0
3594 */
3595U_STABLE UChar32 U_EXPORT2
3596u_foldCase(UChar32 c, uint32_t options);
3597
3598/**
3599 * Returns the decimal digit value of the code point in the
3600 * specified radix.
3601 *
3602 * If the radix is not in the range <code>2<=radix<=36</code> or if the
3603 * value of <code>c</code> is not a valid digit in the specified
3604 * radix, <code>-1</code> is returned. A character is a valid digit
3605 * if at least one of the following is true:
3606 * <ul>
3607 * <li>The character has a decimal digit value.
3608 * Such characters have the general category "Nd" (decimal digit numbers)
3609 * and a Numeric_Type of Decimal.
3610 * In this case the value is the character's decimal digit value.</li>
3611 * <li>The character is one of the uppercase Latin letters
3612 * <code>'A'</code> through <code>'Z'</code>.
3613 * In this case the value is <code>c-'A'+10</code>.</li>
3614 * <li>The character is one of the lowercase Latin letters
3615 * <code>'a'</code> through <code>'z'</code>.
3616 * In this case the value is <code>ch-'a'+10</code>.</li>
3617 * <li>Latin letters from both the ASCII range (0061..007A, 0041..005A)
3618 * as well as from the Fullwidth ASCII range (FF41..FF5A, FF21..FF3A)
3619 * are recognized.</li>
3620 * </ul>
3621 *
3622 * Same as java.lang.Character.digit().
3623 *
3624 * @param ch the code point to be tested.
3625 * @param radix the radix.
3626 * @return the numeric value represented by the character in the
3627 * specified radix,
3628 * or -1 if there is no value or if the value exceeds the radix.
3629 *
3630 * @see UCHAR_NUMERIC_TYPE
3631 * @see u_forDigit
3632 * @see u_charDigitValue
3633 * @see u_isdigit
3634 * @stable ICU 2.0
3635 */
3636U_STABLE int32_t U_EXPORT2
3637u_digit(UChar32 ch, int8_t radix);
3638
3639/**
3640 * Determines the character representation for a specific digit in
3641 * the specified radix. If the value of <code>radix</code> is not a
3642 * valid radix, or the value of <code>digit</code> is not a valid
3643 * digit in the specified radix, the null character
3644 * (<code>U+0000</code>) is returned.
3645 * <p>
3646 * The <code>radix</code> argument is valid if it is greater than or
3647 * equal to 2 and less than or equal to 36.
3648 * The <code>digit</code> argument is valid if
3649 * <code>0 <= digit < radix</code>.
3650 * <p>
3651 * If the digit is less than 10, then
3652 * <code>'0' + digit</code> is returned. Otherwise, the value
3653 * <code>'a' + digit - 10</code> is returned.
3654 *
3655 * Same as java.lang.Character.forDigit().
3656 *
3657 * @param digit the number to convert to a character.
3658 * @param radix the radix.
3659 * @return the <code>char</code> representation of the specified digit
3660 * in the specified radix.
3661 *
3662 * @see u_digit
3663 * @see u_charDigitValue
3664 * @see u_isdigit
3665 * @stable ICU 2.0
3666 */
3667U_STABLE UChar32 U_EXPORT2
3668u_forDigit(int32_t digit, int8_t radix);
3669
3670/**
3671 * Get the "age" of the code point.
3672 * The "age" is the Unicode version when the code point was first
3673 * designated (as a non-character or for Private Use)
3674 * or assigned a character.
3675 * This can be useful to avoid emitting code points to receiving
3676 * processes that do not accept newer characters.
3677 * The data is from the UCD file DerivedAge.txt.
3678 *
3679 * @param c The code point.
3680 * @param versionArray The Unicode version number array, to be filled in.
3681 *
3682 * @stable ICU 2.1
3683 */
3684U_STABLE void U_EXPORT2
3685u_charAge(UChar32 c, UVersionInfo versionArray);
3686
3687/**
3688 * Gets the Unicode version information.
3689 * The version array is filled in with the version information
3690 * for the Unicode standard that is currently used by ICU.
3691 * For example, Unicode version 3.1.1 is represented as an array with
3692 * the values { 3, 1, 1, 0 }.
3693 *
3694 * @param versionArray an output array that will be filled in with
3695 * the Unicode version number
3696 * @stable ICU 2.0
3697 */
3698U_STABLE void U_EXPORT2
3699u_getUnicodeVersion(UVersionInfo versionArray);
3700
3701#if !UCONFIG_NO_NORMALIZATION
3702/**
3703 * Get the FC_NFKC_Closure property string for a character.
3704 * See Unicode Standard Annex #15 for details, search for "FC_NFKC_Closure"
3705 * or for "FNC": http://www.unicode.org/reports/tr15/
3706 *
3707 * @param c The character (code point) for which to get the FC_NFKC_Closure string.
3708 * It must be <code>0<=c<=0x10ffff</code>.
3709 * @param dest Destination address for copying the string.
3710 * The string will be zero-terminated if possible.
3711 * If there is no FC_NFKC_Closure string,
3712 * then the buffer will be set to the empty string.
3713 * @param destCapacity <code>==sizeof(dest)</code>
3714 * @param pErrorCode Pointer to a UErrorCode variable.
3715 * @return The length of the string, or 0 if there is no FC_NFKC_Closure string for this character.
3716 * If the destCapacity is less than or equal to the length, then the buffer
3717 * contains the truncated name and the returned length indicates the full
3718 * length of the name.
3719 * The length does not include the zero-termination.
3720 *
3721 * @stable ICU 2.2
3722 */
3723U_STABLE int32_t U_EXPORT2
3724u_getFC_NFKC_Closure(UChar32 c, UChar *dest, int32_t destCapacity, UErrorCode *pErrorCode);
3725
3726#endif
3727
3728
3729U_CDECL_END
3730
3731#endif /*_UCHAR*/
3732/*eof*/
3733