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 USCRIPT.H |
10 | * |
11 | * Modification History: |
12 | * |
13 | * Date Name Description |
14 | * 07/06/2001 Ram Creation. |
15 | ****************************************************************************** |
16 | */ |
17 | |
18 | #ifndef USCRIPT_H |
19 | #define USCRIPT_H |
20 | #include "unicode/utypes.h" |
21 | |
22 | /** |
23 | * \file |
24 | * \brief C API: Unicode Script Information |
25 | */ |
26 | |
27 | /** |
28 | * Constants for ISO 15924 script codes. |
29 | * |
30 | * The current set of script code constants supports at least all scripts |
31 | * that are encoded in the version of Unicode which ICU currently supports. |
32 | * The names of the constants are usually derived from the |
33 | * Unicode script property value aliases. |
34 | * See UAX #24 Unicode Script Property (http://www.unicode.org/reports/tr24/) |
35 | * and http://www.unicode.org/Public/UCD/latest/ucd/PropertyValueAliases.txt . |
36 | * |
37 | * In addition, constants for many ISO 15924 script codes |
38 | * are included, for use with language tags, CLDR data, and similar. |
39 | * Some of those codes are not used in the Unicode Character Database (UCD). |
40 | * For example, there are no characters that have a UCD script property value of |
41 | * Hans or Hant. All Han ideographs have the Hani script property value in Unicode. |
42 | * |
43 | * Private-use codes Qaaa..Qabx are not included, except as used in the UCD or in CLDR. |
44 | * |
45 | * Starting with ICU 55, script codes are only added when their scripts |
46 | * have been or will certainly be encoded in Unicode, |
47 | * and have been assigned Unicode script property value aliases, |
48 | * to ensure that their script names are stable and match the names of the constants. |
49 | * Script codes like Latf and Aran that are not subject to separate encoding |
50 | * may be added at any time. |
51 | * |
52 | * @stable ICU 2.2 |
53 | */ |
54 | typedef enum UScriptCode { |
55 | /* |
56 | * Note: UScriptCode constants and their ISO script code comments |
57 | * are parsed by preparseucd.py. |
58 | * It matches lines like |
59 | * USCRIPT_<Unicode Script value name> = <integer>, / * <ISO script code> * / |
60 | */ |
61 | |
62 | /** @stable ICU 2.2 */ |
63 | USCRIPT_INVALID_CODE = -1, |
64 | /** @stable ICU 2.2 */ |
65 | USCRIPT_COMMON = 0, /* Zyyy */ |
66 | /** @stable ICU 2.2 */ |
67 | USCRIPT_INHERITED = 1, /* Zinh */ /* "Code for inherited script", for non-spacing combining marks; also Qaai */ |
68 | /** @stable ICU 2.2 */ |
69 | USCRIPT_ARABIC = 2, /* Arab */ |
70 | /** @stable ICU 2.2 */ |
71 | USCRIPT_ARMENIAN = 3, /* Armn */ |
72 | /** @stable ICU 2.2 */ |
73 | USCRIPT_BENGALI = 4, /* Beng */ |
74 | /** @stable ICU 2.2 */ |
75 | USCRIPT_BOPOMOFO = 5, /* Bopo */ |
76 | /** @stable ICU 2.2 */ |
77 | USCRIPT_CHEROKEE = 6, /* Cher */ |
78 | /** @stable ICU 2.2 */ |
79 | USCRIPT_COPTIC = 7, /* Copt */ |
80 | /** @stable ICU 2.2 */ |
81 | USCRIPT_CYRILLIC = 8, /* Cyrl */ |
82 | /** @stable ICU 2.2 */ |
83 | USCRIPT_DESERET = 9, /* Dsrt */ |
84 | /** @stable ICU 2.2 */ |
85 | USCRIPT_DEVANAGARI = 10, /* Deva */ |
86 | /** @stable ICU 2.2 */ |
87 | USCRIPT_ETHIOPIC = 11, /* Ethi */ |
88 | /** @stable ICU 2.2 */ |
89 | USCRIPT_GEORGIAN = 12, /* Geor */ |
90 | /** @stable ICU 2.2 */ |
91 | USCRIPT_GOTHIC = 13, /* Goth */ |
92 | /** @stable ICU 2.2 */ |
93 | USCRIPT_GREEK = 14, /* Grek */ |
94 | /** @stable ICU 2.2 */ |
95 | USCRIPT_GUJARATI = 15, /* Gujr */ |
96 | /** @stable ICU 2.2 */ |
97 | USCRIPT_GURMUKHI = 16, /* Guru */ |
98 | /** @stable ICU 2.2 */ |
99 | USCRIPT_HAN = 17, /* Hani */ |
100 | /** @stable ICU 2.2 */ |
101 | USCRIPT_HANGUL = 18, /* Hang */ |
102 | /** @stable ICU 2.2 */ |
103 | USCRIPT_HEBREW = 19, /* Hebr */ |
104 | /** @stable ICU 2.2 */ |
105 | USCRIPT_HIRAGANA = 20, /* Hira */ |
106 | /** @stable ICU 2.2 */ |
107 | USCRIPT_KANNADA = 21, /* Knda */ |
108 | /** @stable ICU 2.2 */ |
109 | USCRIPT_KATAKANA = 22, /* Kana */ |
110 | /** @stable ICU 2.2 */ |
111 | USCRIPT_KHMER = 23, /* Khmr */ |
112 | /** @stable ICU 2.2 */ |
113 | USCRIPT_LAO = 24, /* Laoo */ |
114 | /** @stable ICU 2.2 */ |
115 | USCRIPT_LATIN = 25, /* Latn */ |
116 | /** @stable ICU 2.2 */ |
117 | USCRIPT_MALAYALAM = 26, /* Mlym */ |
118 | /** @stable ICU 2.2 */ |
119 | USCRIPT_MONGOLIAN = 27, /* Mong */ |
120 | /** @stable ICU 2.2 */ |
121 | USCRIPT_MYANMAR = 28, /* Mymr */ |
122 | /** @stable ICU 2.2 */ |
123 | USCRIPT_OGHAM = 29, /* Ogam */ |
124 | /** @stable ICU 2.2 */ |
125 | USCRIPT_OLD_ITALIC = 30, /* Ital */ |
126 | /** @stable ICU 2.2 */ |
127 | USCRIPT_ORIYA = 31, /* Orya */ |
128 | /** @stable ICU 2.2 */ |
129 | USCRIPT_RUNIC = 32, /* Runr */ |
130 | /** @stable ICU 2.2 */ |
131 | USCRIPT_SINHALA = 33, /* Sinh */ |
132 | /** @stable ICU 2.2 */ |
133 | USCRIPT_SYRIAC = 34, /* Syrc */ |
134 | /** @stable ICU 2.2 */ |
135 | USCRIPT_TAMIL = 35, /* Taml */ |
136 | /** @stable ICU 2.2 */ |
137 | USCRIPT_TELUGU = 36, /* Telu */ |
138 | /** @stable ICU 2.2 */ |
139 | USCRIPT_THAANA = 37, /* Thaa */ |
140 | /** @stable ICU 2.2 */ |
141 | USCRIPT_THAI = 38, /* Thai */ |
142 | /** @stable ICU 2.2 */ |
143 | USCRIPT_TIBETAN = 39, /* Tibt */ |
144 | /** Canadian_Aboriginal script. @stable ICU 2.6 */ |
145 | USCRIPT_CANADIAN_ABORIGINAL = 40, /* Cans */ |
146 | /** Canadian_Aboriginal script (alias). @stable ICU 2.2 */ |
147 | USCRIPT_UCAS = USCRIPT_CANADIAN_ABORIGINAL, |
148 | /** @stable ICU 2.2 */ |
149 | USCRIPT_YI = 41, /* Yiii */ |
150 | /* New scripts in Unicode 3.2 */ |
151 | /** @stable ICU 2.2 */ |
152 | USCRIPT_TAGALOG = 42, /* Tglg */ |
153 | /** @stable ICU 2.2 */ |
154 | USCRIPT_HANUNOO = 43, /* Hano */ |
155 | /** @stable ICU 2.2 */ |
156 | USCRIPT_BUHID = 44, /* Buhd */ |
157 | /** @stable ICU 2.2 */ |
158 | USCRIPT_TAGBANWA = 45, /* Tagb */ |
159 | |
160 | /* New scripts in Unicode 4 */ |
161 | /** @stable ICU 2.6 */ |
162 | USCRIPT_BRAILLE = 46, /* Brai */ |
163 | /** @stable ICU 2.6 */ |
164 | USCRIPT_CYPRIOT = 47, /* Cprt */ |
165 | /** @stable ICU 2.6 */ |
166 | USCRIPT_LIMBU = 48, /* Limb */ |
167 | /** @stable ICU 2.6 */ |
168 | USCRIPT_LINEAR_B = 49, /* Linb */ |
169 | /** @stable ICU 2.6 */ |
170 | USCRIPT_OSMANYA = 50, /* Osma */ |
171 | /** @stable ICU 2.6 */ |
172 | USCRIPT_SHAVIAN = 51, /* Shaw */ |
173 | /** @stable ICU 2.6 */ |
174 | USCRIPT_TAI_LE = 52, /* Tale */ |
175 | /** @stable ICU 2.6 */ |
176 | USCRIPT_UGARITIC = 53, /* Ugar */ |
177 | |
178 | /** New script code in Unicode 4.0.1 @stable ICU 3.0 */ |
179 | USCRIPT_KATAKANA_OR_HIRAGANA = 54,/*Hrkt */ |
180 | |
181 | /* New scripts in Unicode 4.1 */ |
182 | /** @stable ICU 3.4 */ |
183 | USCRIPT_BUGINESE = 55, /* Bugi */ |
184 | /** @stable ICU 3.4 */ |
185 | USCRIPT_GLAGOLITIC = 56, /* Glag */ |
186 | /** @stable ICU 3.4 */ |
187 | USCRIPT_KHAROSHTHI = 57, /* Khar */ |
188 | /** @stable ICU 3.4 */ |
189 | USCRIPT_SYLOTI_NAGRI = 58, /* Sylo */ |
190 | /** @stable ICU 3.4 */ |
191 | USCRIPT_NEW_TAI_LUE = 59, /* Talu */ |
192 | /** @stable ICU 3.4 */ |
193 | USCRIPT_TIFINAGH = 60, /* Tfng */ |
194 | /** @stable ICU 3.4 */ |
195 | USCRIPT_OLD_PERSIAN = 61, /* Xpeo */ |
196 | |
197 | /* New script codes from Unicode and ISO 15924 */ |
198 | /** @stable ICU 3.6 */ |
199 | USCRIPT_BALINESE = 62, /* Bali */ |
200 | /** @stable ICU 3.6 */ |
201 | USCRIPT_BATAK = 63, /* Batk */ |
202 | /** @stable ICU 3.6 */ |
203 | USCRIPT_BLISSYMBOLS = 64, /* Blis */ |
204 | /** @stable ICU 3.6 */ |
205 | USCRIPT_BRAHMI = 65, /* Brah */ |
206 | /** @stable ICU 3.6 */ |
207 | USCRIPT_CHAM = 66, /* Cham */ |
208 | /** @stable ICU 3.6 */ |
209 | USCRIPT_CIRTH = 67, /* Cirt */ |
210 | /** @stable ICU 3.6 */ |
211 | USCRIPT_OLD_CHURCH_SLAVONIC_CYRILLIC = 68, /* Cyrs */ |
212 | /** @stable ICU 3.6 */ |
213 | USCRIPT_DEMOTIC_EGYPTIAN = 69, /* Egyd */ |
214 | /** @stable ICU 3.6 */ |
215 | USCRIPT_HIERATIC_EGYPTIAN = 70, /* Egyh */ |
216 | /** @stable ICU 3.6 */ |
217 | USCRIPT_EGYPTIAN_HIEROGLYPHS = 71, /* Egyp */ |
218 | /** @stable ICU 3.6 */ |
219 | USCRIPT_KHUTSURI = 72, /* Geok */ |
220 | /** @stable ICU 3.6 */ |
221 | USCRIPT_SIMPLIFIED_HAN = 73, /* Hans */ |
222 | /** @stable ICU 3.6 */ |
223 | USCRIPT_TRADITIONAL_HAN = 74, /* Hant */ |
224 | /** @stable ICU 3.6 */ |
225 | USCRIPT_PAHAWH_HMONG = 75, /* Hmng */ |
226 | /** @stable ICU 3.6 */ |
227 | USCRIPT_OLD_HUNGARIAN = 76, /* Hung */ |
228 | /** @stable ICU 3.6 */ |
229 | USCRIPT_HARAPPAN_INDUS = 77, /* Inds */ |
230 | /** @stable ICU 3.6 */ |
231 | USCRIPT_JAVANESE = 78, /* Java */ |
232 | /** @stable ICU 3.6 */ |
233 | USCRIPT_KAYAH_LI = 79, /* Kali */ |
234 | /** @stable ICU 3.6 */ |
235 | USCRIPT_LATIN_FRAKTUR = 80, /* Latf */ |
236 | /** @stable ICU 3.6 */ |
237 | USCRIPT_LATIN_GAELIC = 81, /* Latg */ |
238 | /** @stable ICU 3.6 */ |
239 | USCRIPT_LEPCHA = 82, /* Lepc */ |
240 | /** @stable ICU 3.6 */ |
241 | USCRIPT_LINEAR_A = 83, /* Lina */ |
242 | /** @stable ICU 4.6 */ |
243 | USCRIPT_MANDAIC = 84, /* Mand */ |
244 | /** @stable ICU 3.6 */ |
245 | USCRIPT_MANDAEAN = USCRIPT_MANDAIC, |
246 | /** @stable ICU 3.6 */ |
247 | USCRIPT_MAYAN_HIEROGLYPHS = 85, /* Maya */ |
248 | /** @stable ICU 4.6 */ |
249 | USCRIPT_MEROITIC_HIEROGLYPHS = 86, /* Mero */ |
250 | /** @stable ICU 3.6 */ |
251 | USCRIPT_MEROITIC = USCRIPT_MEROITIC_HIEROGLYPHS, |
252 | /** @stable ICU 3.6 */ |
253 | USCRIPT_NKO = 87, /* Nkoo */ |
254 | /** @stable ICU 3.6 */ |
255 | USCRIPT_ORKHON = 88, /* Orkh */ |
256 | /** @stable ICU 3.6 */ |
257 | USCRIPT_OLD_PERMIC = 89, /* Perm */ |
258 | /** @stable ICU 3.6 */ |
259 | USCRIPT_PHAGS_PA = 90, /* Phag */ |
260 | /** @stable ICU 3.6 */ |
261 | USCRIPT_PHOENICIAN = 91, /* Phnx */ |
262 | /** @stable ICU 52 */ |
263 | USCRIPT_MIAO = 92, /* Plrd */ |
264 | /** @stable ICU 3.6 */ |
265 | USCRIPT_PHONETIC_POLLARD = USCRIPT_MIAO, |
266 | /** @stable ICU 3.6 */ |
267 | USCRIPT_RONGORONGO = 93, /* Roro */ |
268 | /** @stable ICU 3.6 */ |
269 | USCRIPT_SARATI = 94, /* Sara */ |
270 | /** @stable ICU 3.6 */ |
271 | USCRIPT_ESTRANGELO_SYRIAC = 95, /* Syre */ |
272 | /** @stable ICU 3.6 */ |
273 | USCRIPT_WESTERN_SYRIAC = 96, /* Syrj */ |
274 | /** @stable ICU 3.6 */ |
275 | USCRIPT_EASTERN_SYRIAC = 97, /* Syrn */ |
276 | /** @stable ICU 3.6 */ |
277 | USCRIPT_TENGWAR = 98, /* Teng */ |
278 | /** @stable ICU 3.6 */ |
279 | USCRIPT_VAI = 99, /* Vaii */ |
280 | /** @stable ICU 3.6 */ |
281 | USCRIPT_VISIBLE_SPEECH = 100,/* Visp */ |
282 | /** @stable ICU 3.6 */ |
283 | USCRIPT_CUNEIFORM = 101,/* Xsux */ |
284 | /** @stable ICU 3.6 */ |
285 | USCRIPT_UNWRITTEN_LANGUAGES = 102,/* Zxxx */ |
286 | /** @stable ICU 3.6 */ |
287 | USCRIPT_UNKNOWN = 103,/* Zzzz */ /* Unknown="Code for uncoded script", for unassigned code points */ |
288 | |
289 | /** @stable ICU 3.8 */ |
290 | USCRIPT_CARIAN = 104,/* Cari */ |
291 | /** @stable ICU 3.8 */ |
292 | USCRIPT_JAPANESE = 105,/* Jpan */ |
293 | /** @stable ICU 3.8 */ |
294 | USCRIPT_LANNA = 106,/* Lana */ |
295 | /** @stable ICU 3.8 */ |
296 | USCRIPT_LYCIAN = 107,/* Lyci */ |
297 | /** @stable ICU 3.8 */ |
298 | USCRIPT_LYDIAN = 108,/* Lydi */ |
299 | /** @stable ICU 3.8 */ |
300 | USCRIPT_OL_CHIKI = 109,/* Olck */ |
301 | /** @stable ICU 3.8 */ |
302 | USCRIPT_REJANG = 110,/* Rjng */ |
303 | /** @stable ICU 3.8 */ |
304 | USCRIPT_SAURASHTRA = 111,/* Saur */ |
305 | /** Sutton SignWriting @stable ICU 3.8 */ |
306 | USCRIPT_SIGN_WRITING = 112,/* Sgnw */ |
307 | /** @stable ICU 3.8 */ |
308 | USCRIPT_SUNDANESE = 113,/* Sund */ |
309 | /** @stable ICU 3.8 */ |
310 | USCRIPT_MOON = 114,/* Moon */ |
311 | /** @stable ICU 3.8 */ |
312 | USCRIPT_MEITEI_MAYEK = 115,/* Mtei */ |
313 | |
314 | /** @stable ICU 4.0 */ |
315 | USCRIPT_IMPERIAL_ARAMAIC = 116,/* Armi */ |
316 | /** @stable ICU 4.0 */ |
317 | USCRIPT_AVESTAN = 117,/* Avst */ |
318 | /** @stable ICU 4.0 */ |
319 | USCRIPT_CHAKMA = 118,/* Cakm */ |
320 | /** @stable ICU 4.0 */ |
321 | USCRIPT_KOREAN = 119,/* Kore */ |
322 | /** @stable ICU 4.0 */ |
323 | USCRIPT_KAITHI = 120,/* Kthi */ |
324 | /** @stable ICU 4.0 */ |
325 | USCRIPT_MANICHAEAN = 121,/* Mani */ |
326 | /** @stable ICU 4.0 */ |
327 | USCRIPT_INSCRIPTIONAL_PAHLAVI = 122,/* Phli */ |
328 | /** @stable ICU 4.0 */ |
329 | USCRIPT_PSALTER_PAHLAVI = 123,/* Phlp */ |
330 | /** @stable ICU 4.0 */ |
331 | USCRIPT_BOOK_PAHLAVI = 124,/* Phlv */ |
332 | /** @stable ICU 4.0 */ |
333 | USCRIPT_INSCRIPTIONAL_PARTHIAN = 125,/* Prti */ |
334 | /** @stable ICU 4.0 */ |
335 | USCRIPT_SAMARITAN = 126,/* Samr */ |
336 | /** @stable ICU 4.0 */ |
337 | USCRIPT_TAI_VIET = 127,/* Tavt */ |
338 | /** @stable ICU 4.0 */ |
339 | USCRIPT_MATHEMATICAL_NOTATION = 128,/* Zmth */ |
340 | /** @stable ICU 4.0 */ |
341 | USCRIPT_SYMBOLS = 129,/* Zsym */ |
342 | |
343 | /** @stable ICU 4.4 */ |
344 | USCRIPT_BAMUM = 130,/* Bamu */ |
345 | /** @stable ICU 4.4 */ |
346 | USCRIPT_LISU = 131,/* Lisu */ |
347 | /** @stable ICU 4.4 */ |
348 | USCRIPT_NAKHI_GEBA = 132,/* Nkgb */ |
349 | /** @stable ICU 4.4 */ |
350 | USCRIPT_OLD_SOUTH_ARABIAN = 133,/* Sarb */ |
351 | |
352 | /** @stable ICU 4.6 */ |
353 | USCRIPT_BASSA_VAH = 134,/* Bass */ |
354 | /** @stable ICU 54 */ |
355 | USCRIPT_DUPLOYAN = 135,/* Dupl */ |
356 | #ifndef U_HIDE_DEPRECATED_API |
357 | /** @deprecated ICU 54 Typo, use USCRIPT_DUPLOYAN */ |
358 | USCRIPT_DUPLOYAN_SHORTAND = USCRIPT_DUPLOYAN, |
359 | #endif /* U_HIDE_DEPRECATED_API */ |
360 | /** @stable ICU 4.6 */ |
361 | USCRIPT_ELBASAN = 136,/* Elba */ |
362 | /** @stable ICU 4.6 */ |
363 | USCRIPT_GRANTHA = 137,/* Gran */ |
364 | /** @stable ICU 4.6 */ |
365 | USCRIPT_KPELLE = 138,/* Kpel */ |
366 | /** @stable ICU 4.6 */ |
367 | USCRIPT_LOMA = 139,/* Loma */ |
368 | /** Mende Kikakui @stable ICU 4.6 */ |
369 | USCRIPT_MENDE = 140,/* Mend */ |
370 | /** @stable ICU 4.6 */ |
371 | USCRIPT_MEROITIC_CURSIVE = 141,/* Merc */ |
372 | /** @stable ICU 4.6 */ |
373 | USCRIPT_OLD_NORTH_ARABIAN = 142,/* Narb */ |
374 | /** @stable ICU 4.6 */ |
375 | USCRIPT_NABATAEAN = 143,/* Nbat */ |
376 | /** @stable ICU 4.6 */ |
377 | USCRIPT_PALMYRENE = 144,/* Palm */ |
378 | /** @stable ICU 54 */ |
379 | USCRIPT_KHUDAWADI = 145,/* Sind */ |
380 | /** @stable ICU 4.6 */ |
381 | USCRIPT_SINDHI = USCRIPT_KHUDAWADI, |
382 | /** @stable ICU 4.6 */ |
383 | USCRIPT_WARANG_CITI = 146,/* Wara */ |
384 | |
385 | /** @stable ICU 4.8 */ |
386 | USCRIPT_AFAKA = 147,/* Afak */ |
387 | /** @stable ICU 4.8 */ |
388 | USCRIPT_JURCHEN = 148,/* Jurc */ |
389 | /** @stable ICU 4.8 */ |
390 | USCRIPT_MRO = 149,/* Mroo */ |
391 | /** @stable ICU 4.8 */ |
392 | USCRIPT_NUSHU = 150,/* Nshu */ |
393 | /** @stable ICU 4.8 */ |
394 | USCRIPT_SHARADA = 151,/* Shrd */ |
395 | /** @stable ICU 4.8 */ |
396 | USCRIPT_SORA_SOMPENG = 152,/* Sora */ |
397 | /** @stable ICU 4.8 */ |
398 | USCRIPT_TAKRI = 153,/* Takr */ |
399 | /** @stable ICU 4.8 */ |
400 | USCRIPT_TANGUT = 154,/* Tang */ |
401 | /** @stable ICU 4.8 */ |
402 | USCRIPT_WOLEAI = 155,/* Wole */ |
403 | |
404 | /** @stable ICU 49 */ |
405 | USCRIPT_ANATOLIAN_HIEROGLYPHS = 156,/* Hluw */ |
406 | /** @stable ICU 49 */ |
407 | USCRIPT_KHOJKI = 157,/* Khoj */ |
408 | /** @stable ICU 49 */ |
409 | USCRIPT_TIRHUTA = 158,/* Tirh */ |
410 | |
411 | /** @stable ICU 52 */ |
412 | USCRIPT_CAUCASIAN_ALBANIAN = 159,/* Aghb */ |
413 | /** @stable ICU 52 */ |
414 | USCRIPT_MAHAJANI = 160,/* Mahj */ |
415 | |
416 | /** @stable ICU 54 */ |
417 | USCRIPT_AHOM = 161,/* Ahom */ |
418 | /** @stable ICU 54 */ |
419 | USCRIPT_HATRAN = 162,/* Hatr */ |
420 | /** @stable ICU 54 */ |
421 | USCRIPT_MODI = 163,/* Modi */ |
422 | /** @stable ICU 54 */ |
423 | USCRIPT_MULTANI = 164,/* Mult */ |
424 | /** @stable ICU 54 */ |
425 | USCRIPT_PAU_CIN_HAU = 165,/* Pauc */ |
426 | /** @stable ICU 54 */ |
427 | USCRIPT_SIDDHAM = 166,/* Sidd */ |
428 | |
429 | /** @stable ICU 58 */ |
430 | USCRIPT_ADLAM = 167,/* Adlm */ |
431 | /** @stable ICU 58 */ |
432 | USCRIPT_BHAIKSUKI = 168,/* Bhks */ |
433 | /** @stable ICU 58 */ |
434 | USCRIPT_MARCHEN = 169,/* Marc */ |
435 | /** @stable ICU 58 */ |
436 | USCRIPT_NEWA = 170,/* Newa */ |
437 | /** @stable ICU 58 */ |
438 | USCRIPT_OSAGE = 171,/* Osge */ |
439 | |
440 | /** @stable ICU 58 */ |
441 | USCRIPT_HAN_WITH_BOPOMOFO = 172,/* Hanb */ |
442 | /** @stable ICU 58 */ |
443 | USCRIPT_JAMO = 173,/* Jamo */ |
444 | /** @stable ICU 58 */ |
445 | USCRIPT_SYMBOLS_EMOJI = 174,/* Zsye */ |
446 | |
447 | /** @stable ICU 60 */ |
448 | USCRIPT_MASARAM_GONDI = 175,/* Gonm */ |
449 | /** @stable ICU 60 */ |
450 | USCRIPT_SOYOMBO = 176,/* Soyo */ |
451 | /** @stable ICU 60 */ |
452 | USCRIPT_ZANABAZAR_SQUARE = 177,/* Zanb */ |
453 | |
454 | #ifndef U_HIDE_DEPRECATED_API |
455 | /** |
456 | * One more than the highest normal UScriptCode value. |
457 | * The highest value is available via u_getIntPropertyMaxValue(UCHAR_SCRIPT). |
458 | * |
459 | * @deprecated ICU 58 The numeric value may change over time, see ICU ticket #12420. |
460 | */ |
461 | USCRIPT_CODE_LIMIT = 178 |
462 | #endif // U_HIDE_DEPRECATED_API |
463 | } UScriptCode; |
464 | |
465 | /** |
466 | * Gets the script codes associated with the given locale or ISO 15924 abbreviation or name. |
467 | * Fills in USCRIPT_MALAYALAM given "Malayam" OR "Mlym". |
468 | * Fills in USCRIPT_LATIN given "en" OR "en_US" |
469 | * If the required capacity is greater than the capacity of the destination buffer, |
470 | * then the error code is set to U_BUFFER_OVERFLOW_ERROR and the required capacity is returned. |
471 | * |
472 | * <p>Note: To search by short or long script alias only, use |
473 | * u_getPropertyValueEnum(UCHAR_SCRIPT, alias) instead. That does |
474 | * a fast lookup with no access of the locale data. |
475 | * |
476 | * @param nameOrAbbrOrLocale name of the script, as given in |
477 | * PropertyValueAliases.txt, or ISO 15924 code or locale |
478 | * @param fillIn the UScriptCode buffer to fill in the script code |
479 | * @param capacity the capacity (size) fo UScriptCode buffer passed in. |
480 | * @param err the error status code. |
481 | * @return The number of script codes filled in the buffer passed in |
482 | * @stable ICU 2.4 |
483 | */ |
484 | U_STABLE int32_t U_EXPORT2 |
485 | uscript_getCode(const char* nameOrAbbrOrLocale,UScriptCode* fillIn,int32_t capacity,UErrorCode *err); |
486 | |
487 | /** |
488 | * Returns the long Unicode script name, if there is one. |
489 | * Otherwise returns the 4-letter ISO 15924 script code. |
490 | * Returns "Malayam" given USCRIPT_MALAYALAM. |
491 | * |
492 | * @param scriptCode UScriptCode enum |
493 | * @return long script name as given in PropertyValueAliases.txt, or the 4-letter code, |
494 | * or NULL if scriptCode is invalid |
495 | * @stable ICU 2.4 |
496 | */ |
497 | U_STABLE const char* U_EXPORT2 |
498 | uscript_getName(UScriptCode scriptCode); |
499 | |
500 | /** |
501 | * Returns the 4-letter ISO 15924 script code, |
502 | * which is the same as the short Unicode script name if Unicode has names for the script. |
503 | * Returns "Mlym" given USCRIPT_MALAYALAM. |
504 | * |
505 | * @param scriptCode UScriptCode enum |
506 | * @return short script name (4-letter code), or NULL if scriptCode is invalid |
507 | * @stable ICU 2.4 |
508 | */ |
509 | U_STABLE const char* U_EXPORT2 |
510 | uscript_getShortName(UScriptCode scriptCode); |
511 | |
512 | /** |
513 | * Gets the script code associated with the given codepoint. |
514 | * Returns USCRIPT_MALAYALAM given 0x0D02 |
515 | * @param codepoint UChar32 codepoint |
516 | * @param err the error status code. |
517 | * @return The UScriptCode, or 0 if codepoint is invalid |
518 | * @stable ICU 2.4 |
519 | */ |
520 | U_STABLE UScriptCode U_EXPORT2 |
521 | uscript_getScript(UChar32 codepoint, UErrorCode *err); |
522 | |
523 | /** |
524 | * Do the Script_Extensions of code point c contain script sc? |
525 | * If c does not have explicit Script_Extensions, then this tests whether |
526 | * c has the Script property value sc. |
527 | * |
528 | * Some characters are commonly used in multiple scripts. |
529 | * For more information, see UAX #24: http://www.unicode.org/reports/tr24/. |
530 | * @param c code point |
531 | * @param sc script code |
532 | * @return TRUE if sc is in Script_Extensions(c) |
533 | * @stable ICU 49 |
534 | */ |
535 | U_STABLE UBool U_EXPORT2 |
536 | uscript_hasScript(UChar32 c, UScriptCode sc); |
537 | |
538 | /** |
539 | * Writes code point c's Script_Extensions as a list of UScriptCode values |
540 | * to the output scripts array and returns the number of script codes. |
541 | * - If c does have Script_Extensions, then the Script property value |
542 | * (normally Common or Inherited) is not included. |
543 | * - If c does not have Script_Extensions, then the one Script code is written to the output array. |
544 | * - If c is not a valid code point, then the one USCRIPT_UNKNOWN code is written. |
545 | * In other words, if the return value is 1, |
546 | * then the output array contains exactly c's single Script code. |
547 | * If the return value is n>=2, then the output array contains c's n Script_Extensions script codes. |
548 | * |
549 | * Some characters are commonly used in multiple scripts. |
550 | * For more information, see UAX #24: http://www.unicode.org/reports/tr24/. |
551 | * |
552 | * If there are more than capacity script codes to be written, then |
553 | * U_BUFFER_OVERFLOW_ERROR is set and the number of Script_Extensions is returned. |
554 | * (Usual ICU buffer handling behavior.) |
555 | * |
556 | * @param c code point |
557 | * @param scripts output script code array |
558 | * @param capacity capacity of the scripts array |
559 | * @param errorCode Standard ICU error code. Its input value must |
560 | * pass the U_SUCCESS() test, or else the function returns |
561 | * immediately. Check for U_FAILURE() on output or use with |
562 | * function chaining. (See User Guide for details.) |
563 | * @return number of script codes in c's Script_Extensions, or 1 for the single Script value, |
564 | * written to scripts unless U_BUFFER_OVERFLOW_ERROR indicates insufficient capacity |
565 | * @stable ICU 49 |
566 | */ |
567 | U_STABLE int32_t U_EXPORT2 |
568 | uscript_getScriptExtensions(UChar32 c, |
569 | UScriptCode *scripts, int32_t capacity, |
570 | UErrorCode *errorCode); |
571 | |
572 | /** |
573 | * Script usage constants. |
574 | * See UAX #31 Unicode Identifier and Pattern Syntax. |
575 | * http://www.unicode.org/reports/tr31/#Table_Candidate_Characters_for_Exclusion_from_Identifiers |
576 | * |
577 | * @stable ICU 51 |
578 | */ |
579 | typedef enum UScriptUsage { |
580 | /** Not encoded in Unicode. @stable ICU 51 */ |
581 | USCRIPT_USAGE_NOT_ENCODED, |
582 | /** Unknown script usage. @stable ICU 51 */ |
583 | USCRIPT_USAGE_UNKNOWN, |
584 | /** Candidate for Exclusion from Identifiers. @stable ICU 51 */ |
585 | USCRIPT_USAGE_EXCLUDED, |
586 | /** Limited Use script. @stable ICU 51 */ |
587 | USCRIPT_USAGE_LIMITED_USE, |
588 | /** Aspirational Use script. @stable ICU 51 */ |
589 | USCRIPT_USAGE_ASPIRATIONAL, |
590 | /** Recommended script. @stable ICU 51 */ |
591 | USCRIPT_USAGE_RECOMMENDED |
592 | } UScriptUsage; |
593 | |
594 | /** |
595 | * Writes the script sample character string. |
596 | * This string normally consists of one code point but might be longer. |
597 | * The string is empty if the script is not encoded. |
598 | * |
599 | * @param script script code |
600 | * @param dest output string array |
601 | * @param capacity number of UChars in the dest array |
602 | * @param pErrorCode standard ICU in/out error code, must pass U_SUCCESS() on input |
603 | * @return the string length, even if U_BUFFER_OVERFLOW_ERROR |
604 | * @stable ICU 51 |
605 | */ |
606 | U_STABLE int32_t U_EXPORT2 |
607 | uscript_getSampleString(UScriptCode script, UChar *dest, int32_t capacity, UErrorCode *pErrorCode); |
608 | |
609 | #if U_SHOW_CPLUSPLUS_API |
610 | |
611 | U_NAMESPACE_BEGIN |
612 | class UnicodeString; |
613 | U_NAMESPACE_END |
614 | |
615 | /** |
616 | * Returns the script sample character string. |
617 | * This string normally consists of one code point but might be longer. |
618 | * The string is empty if the script is not encoded. |
619 | * |
620 | * @param script script code |
621 | * @return the sample character string |
622 | * @stable ICU 51 |
623 | */ |
624 | U_COMMON_API icu::UnicodeString U_EXPORT2 |
625 | uscript_getSampleUnicodeString(UScriptCode script); |
626 | |
627 | #endif |
628 | |
629 | /** |
630 | * Returns the script usage according to UAX #31 Unicode Identifier and Pattern Syntax. |
631 | * Returns USCRIPT_USAGE_NOT_ENCODED if the script is not encoded in Unicode. |
632 | * |
633 | * @param script script code |
634 | * @return script usage |
635 | * @see UScriptUsage |
636 | * @stable ICU 51 |
637 | */ |
638 | U_STABLE UScriptUsage U_EXPORT2 |
639 | uscript_getUsage(UScriptCode script); |
640 | |
641 | /** |
642 | * Returns TRUE if the script is written right-to-left. |
643 | * For example, Arab and Hebr. |
644 | * |
645 | * @param script script code |
646 | * @return TRUE if the script is right-to-left |
647 | * @stable ICU 51 |
648 | */ |
649 | U_STABLE UBool U_EXPORT2 |
650 | uscript_isRightToLeft(UScriptCode script); |
651 | |
652 | /** |
653 | * Returns TRUE if the script allows line breaks between letters (excluding hyphenation). |
654 | * Such a script typically requires dictionary-based line breaking. |
655 | * For example, Hani and Thai. |
656 | * |
657 | * @param script script code |
658 | * @return TRUE if the script allows line breaks between letters |
659 | * @stable ICU 51 |
660 | */ |
661 | U_STABLE UBool U_EXPORT2 |
662 | uscript_breaksBetweenLetters(UScriptCode script); |
663 | |
664 | /** |
665 | * Returns TRUE if in modern (or most recent) usage of the script case distinctions are customary. |
666 | * For example, Latn and Cyrl. |
667 | * |
668 | * @param script script code |
669 | * @return TRUE if the script is cased |
670 | * @stable ICU 51 |
671 | */ |
672 | U_STABLE UBool U_EXPORT2 |
673 | uscript_isCased(UScriptCode script); |
674 | |
675 | #endif |
676 | |