1 | /* |
2 | ********************************************************************** |
3 | * Copyright (C) 1997-2014, International Business Machines |
4 | * Corporation and others. All Rights Reserved. |
5 | ********************************************************************** |
6 | * |
7 | * File USCRIPT.H |
8 | * |
9 | * Modification History: |
10 | * |
11 | * Date Name Description |
12 | * 07/06/2001 Ram Creation. |
13 | ****************************************************************************** |
14 | */ |
15 | |
16 | #ifndef USCRIPT_H |
17 | #define USCRIPT_H |
18 | #include "unicode/utypes.h" |
19 | |
20 | /** |
21 | * \file |
22 | * \brief C API: Unicode Script Information |
23 | */ |
24 | |
25 | /** |
26 | * Constants for ISO 15924 script codes. |
27 | * |
28 | * Many of these script codes - those from Unicode's ScriptNames.txt - |
29 | * are character property values for Unicode's Script property. |
30 | * See UAX #24 Script Names (http://www.unicode.org/reports/tr24/). |
31 | * |
32 | * Starting with ICU 3.6, constants for most ISO 15924 script codes |
33 | * are included (currently excluding private-use codes Qaaa..Qabx). |
34 | * For scripts for which there are codes in ISO 15924 but which are not |
35 | * used in the Unicode Character Database (UCD), there are no Unicode characters |
36 | * associated with those scripts. |
37 | * |
38 | * For example, there are no characters that have a UCD script code of |
39 | * Hans or Hant. All Han ideographs have the Hani script code. |
40 | * The Hans and Hant script codes are used with CLDR data. |
41 | * |
42 | * ISO 15924 script codes are included for use with CLDR and similar. |
43 | * |
44 | * @stable ICU 2.2 |
45 | */ |
46 | typedef enum UScriptCode { |
47 | /* |
48 | * Note: UScriptCode constants and their ISO script code comments |
49 | * are parsed by preparseucd.py. |
50 | * It matches lines like |
51 | * USCRIPT_<Unicode Script value name> = <integer>, / * <ISO script code> * / |
52 | */ |
53 | |
54 | /** @stable ICU 2.2 */ |
55 | USCRIPT_INVALID_CODE = -1, |
56 | /** @stable ICU 2.2 */ |
57 | USCRIPT_COMMON = 0, /* Zyyy */ |
58 | /** @stable ICU 2.2 */ |
59 | USCRIPT_INHERITED = 1, /* Zinh */ /* "Code for inherited script", for non-spacing combining marks; also Qaai */ |
60 | /** @stable ICU 2.2 */ |
61 | USCRIPT_ARABIC = 2, /* Arab */ |
62 | /** @stable ICU 2.2 */ |
63 | USCRIPT_ARMENIAN = 3, /* Armn */ |
64 | /** @stable ICU 2.2 */ |
65 | USCRIPT_BENGALI = 4, /* Beng */ |
66 | /** @stable ICU 2.2 */ |
67 | USCRIPT_BOPOMOFO = 5, /* Bopo */ |
68 | /** @stable ICU 2.2 */ |
69 | USCRIPT_CHEROKEE = 6, /* Cher */ |
70 | /** @stable ICU 2.2 */ |
71 | USCRIPT_COPTIC = 7, /* Copt */ |
72 | /** @stable ICU 2.2 */ |
73 | USCRIPT_CYRILLIC = 8, /* Cyrl */ |
74 | /** @stable ICU 2.2 */ |
75 | USCRIPT_DESERET = 9, /* Dsrt */ |
76 | /** @stable ICU 2.2 */ |
77 | USCRIPT_DEVANAGARI = 10, /* Deva */ |
78 | /** @stable ICU 2.2 */ |
79 | USCRIPT_ETHIOPIC = 11, /* Ethi */ |
80 | /** @stable ICU 2.2 */ |
81 | USCRIPT_GEORGIAN = 12, /* Geor */ |
82 | /** @stable ICU 2.2 */ |
83 | USCRIPT_GOTHIC = 13, /* Goth */ |
84 | /** @stable ICU 2.2 */ |
85 | USCRIPT_GREEK = 14, /* Grek */ |
86 | /** @stable ICU 2.2 */ |
87 | USCRIPT_GUJARATI = 15, /* Gujr */ |
88 | /** @stable ICU 2.2 */ |
89 | USCRIPT_GURMUKHI = 16, /* Guru */ |
90 | /** @stable ICU 2.2 */ |
91 | USCRIPT_HAN = 17, /* Hani */ |
92 | /** @stable ICU 2.2 */ |
93 | USCRIPT_HANGUL = 18, /* Hang */ |
94 | /** @stable ICU 2.2 */ |
95 | USCRIPT_HEBREW = 19, /* Hebr */ |
96 | /** @stable ICU 2.2 */ |
97 | USCRIPT_HIRAGANA = 20, /* Hira */ |
98 | /** @stable ICU 2.2 */ |
99 | USCRIPT_KANNADA = 21, /* Knda */ |
100 | /** @stable ICU 2.2 */ |
101 | USCRIPT_KATAKANA = 22, /* Kana */ |
102 | /** @stable ICU 2.2 */ |
103 | USCRIPT_KHMER = 23, /* Khmr */ |
104 | /** @stable ICU 2.2 */ |
105 | USCRIPT_LAO = 24, /* Laoo */ |
106 | /** @stable ICU 2.2 */ |
107 | USCRIPT_LATIN = 25, /* Latn */ |
108 | /** @stable ICU 2.2 */ |
109 | USCRIPT_MALAYALAM = 26, /* Mlym */ |
110 | /** @stable ICU 2.2 */ |
111 | USCRIPT_MONGOLIAN = 27, /* Mong */ |
112 | /** @stable ICU 2.2 */ |
113 | USCRIPT_MYANMAR = 28, /* Mymr */ |
114 | /** @stable ICU 2.2 */ |
115 | USCRIPT_OGHAM = 29, /* Ogam */ |
116 | /** @stable ICU 2.2 */ |
117 | USCRIPT_OLD_ITALIC = 30, /* Ital */ |
118 | /** @stable ICU 2.2 */ |
119 | USCRIPT_ORIYA = 31, /* Orya */ |
120 | /** @stable ICU 2.2 */ |
121 | USCRIPT_RUNIC = 32, /* Runr */ |
122 | /** @stable ICU 2.2 */ |
123 | USCRIPT_SINHALA = 33, /* Sinh */ |
124 | /** @stable ICU 2.2 */ |
125 | USCRIPT_SYRIAC = 34, /* Syrc */ |
126 | /** @stable ICU 2.2 */ |
127 | USCRIPT_TAMIL = 35, /* Taml */ |
128 | /** @stable ICU 2.2 */ |
129 | USCRIPT_TELUGU = 36, /* Telu */ |
130 | /** @stable ICU 2.2 */ |
131 | USCRIPT_THAANA = 37, /* Thaa */ |
132 | /** @stable ICU 2.2 */ |
133 | USCRIPT_THAI = 38, /* Thai */ |
134 | /** @stable ICU 2.2 */ |
135 | USCRIPT_TIBETAN = 39, /* Tibt */ |
136 | /** Canadian_Aboriginal script. @stable ICU 2.6 */ |
137 | USCRIPT_CANADIAN_ABORIGINAL = 40, /* Cans */ |
138 | /** Canadian_Aboriginal script (alias). @stable ICU 2.2 */ |
139 | USCRIPT_UCAS = USCRIPT_CANADIAN_ABORIGINAL, |
140 | /** @stable ICU 2.2 */ |
141 | USCRIPT_YI = 41, /* Yiii */ |
142 | /* New scripts in Unicode 3.2 */ |
143 | /** @stable ICU 2.2 */ |
144 | USCRIPT_TAGALOG = 42, /* Tglg */ |
145 | /** @stable ICU 2.2 */ |
146 | USCRIPT_HANUNOO = 43, /* Hano */ |
147 | /** @stable ICU 2.2 */ |
148 | USCRIPT_BUHID = 44, /* Buhd */ |
149 | /** @stable ICU 2.2 */ |
150 | USCRIPT_TAGBANWA = 45, /* Tagb */ |
151 | |
152 | /* New scripts in Unicode 4 */ |
153 | /** @stable ICU 2.6 */ |
154 | USCRIPT_BRAILLE = 46, /* Brai */ |
155 | /** @stable ICU 2.6 */ |
156 | USCRIPT_CYPRIOT = 47, /* Cprt */ |
157 | /** @stable ICU 2.6 */ |
158 | USCRIPT_LIMBU = 48, /* Limb */ |
159 | /** @stable ICU 2.6 */ |
160 | USCRIPT_LINEAR_B = 49, /* Linb */ |
161 | /** @stable ICU 2.6 */ |
162 | USCRIPT_OSMANYA = 50, /* Osma */ |
163 | /** @stable ICU 2.6 */ |
164 | USCRIPT_SHAVIAN = 51, /* Shaw */ |
165 | /** @stable ICU 2.6 */ |
166 | USCRIPT_TAI_LE = 52, /* Tale */ |
167 | /** @stable ICU 2.6 */ |
168 | USCRIPT_UGARITIC = 53, /* Ugar */ |
169 | |
170 | /** New script code in Unicode 4.0.1 @stable ICU 3.0 */ |
171 | USCRIPT_KATAKANA_OR_HIRAGANA = 54,/*Hrkt */ |
172 | |
173 | /* New scripts in Unicode 4.1 */ |
174 | /** @stable ICU 3.4 */ |
175 | USCRIPT_BUGINESE = 55, /* Bugi */ |
176 | /** @stable ICU 3.4 */ |
177 | USCRIPT_GLAGOLITIC = 56, /* Glag */ |
178 | /** @stable ICU 3.4 */ |
179 | USCRIPT_KHAROSHTHI = 57, /* Khar */ |
180 | /** @stable ICU 3.4 */ |
181 | USCRIPT_SYLOTI_NAGRI = 58, /* Sylo */ |
182 | /** @stable ICU 3.4 */ |
183 | USCRIPT_NEW_TAI_LUE = 59, /* Talu */ |
184 | /** @stable ICU 3.4 */ |
185 | USCRIPT_TIFINAGH = 60, /* Tfng */ |
186 | /** @stable ICU 3.4 */ |
187 | USCRIPT_OLD_PERSIAN = 61, /* Xpeo */ |
188 | |
189 | /* New script codes from ISO 15924 */ |
190 | /** @stable ICU 3.6 */ |
191 | USCRIPT_BALINESE = 62, /* Bali */ |
192 | /** @stable ICU 3.6 */ |
193 | USCRIPT_BATAK = 63, /* Batk */ |
194 | /** @stable ICU 3.6 */ |
195 | USCRIPT_BLISSYMBOLS = 64, /* Blis */ |
196 | /** @stable ICU 3.6 */ |
197 | USCRIPT_BRAHMI = 65, /* Brah */ |
198 | /** @stable ICU 3.6 */ |
199 | USCRIPT_CHAM = 66, /* Cham */ |
200 | /** @stable ICU 3.6 */ |
201 | USCRIPT_CIRTH = 67, /* Cirt */ |
202 | /** @stable ICU 3.6 */ |
203 | USCRIPT_OLD_CHURCH_SLAVONIC_CYRILLIC = 68, /* Cyrs */ |
204 | /** @stable ICU 3.6 */ |
205 | USCRIPT_DEMOTIC_EGYPTIAN = 69, /* Egyd */ |
206 | /** @stable ICU 3.6 */ |
207 | USCRIPT_HIERATIC_EGYPTIAN = 70, /* Egyh */ |
208 | /** @stable ICU 3.6 */ |
209 | USCRIPT_EGYPTIAN_HIEROGLYPHS = 71, /* Egyp */ |
210 | /** @stable ICU 3.6 */ |
211 | USCRIPT_KHUTSURI = 72, /* Geok */ |
212 | /** @stable ICU 3.6 */ |
213 | USCRIPT_SIMPLIFIED_HAN = 73, /* Hans */ |
214 | /** @stable ICU 3.6 */ |
215 | USCRIPT_TRADITIONAL_HAN = 74, /* Hant */ |
216 | /** @stable ICU 3.6 */ |
217 | USCRIPT_PAHAWH_HMONG = 75, /* Hmng */ |
218 | /** @stable ICU 3.6 */ |
219 | USCRIPT_OLD_HUNGARIAN = 76, /* Hung */ |
220 | /** @stable ICU 3.6 */ |
221 | USCRIPT_HARAPPAN_INDUS = 77, /* Inds */ |
222 | /** @stable ICU 3.6 */ |
223 | USCRIPT_JAVANESE = 78, /* Java */ |
224 | /** @stable ICU 3.6 */ |
225 | USCRIPT_KAYAH_LI = 79, /* Kali */ |
226 | /** @stable ICU 3.6 */ |
227 | USCRIPT_LATIN_FRAKTUR = 80, /* Latf */ |
228 | /** @stable ICU 3.6 */ |
229 | USCRIPT_LATIN_GAELIC = 81, /* Latg */ |
230 | /** @stable ICU 3.6 */ |
231 | USCRIPT_LEPCHA = 82, /* Lepc */ |
232 | /** @stable ICU 3.6 */ |
233 | USCRIPT_LINEAR_A = 83, /* Lina */ |
234 | /** @stable ICU 4.6 */ |
235 | USCRIPT_MANDAIC = 84, /* Mand */ |
236 | /** @stable ICU 3.6 */ |
237 | USCRIPT_MANDAEAN = USCRIPT_MANDAIC, |
238 | /** @stable ICU 3.6 */ |
239 | USCRIPT_MAYAN_HIEROGLYPHS = 85, /* Maya */ |
240 | /** @stable ICU 4.6 */ |
241 | USCRIPT_MEROITIC_HIEROGLYPHS = 86, /* Mero */ |
242 | /** @stable ICU 3.6 */ |
243 | USCRIPT_MEROITIC = USCRIPT_MEROITIC_HIEROGLYPHS, |
244 | /** @stable ICU 3.6 */ |
245 | USCRIPT_NKO = 87, /* Nkoo */ |
246 | /** @stable ICU 3.6 */ |
247 | USCRIPT_ORKHON = 88, /* Orkh */ |
248 | /** @stable ICU 3.6 */ |
249 | USCRIPT_OLD_PERMIC = 89, /* Perm */ |
250 | /** @stable ICU 3.6 */ |
251 | USCRIPT_PHAGS_PA = 90, /* Phag */ |
252 | /** @stable ICU 3.6 */ |
253 | USCRIPT_PHOENICIAN = 91, /* Phnx */ |
254 | /** @stable ICU 52 */ |
255 | USCRIPT_MIAO = 92, /* Plrd */ |
256 | /** @stable ICU 3.6 */ |
257 | USCRIPT_PHONETIC_POLLARD = USCRIPT_MIAO, |
258 | /** @stable ICU 3.6 */ |
259 | USCRIPT_RONGORONGO = 93, /* Roro */ |
260 | /** @stable ICU 3.6 */ |
261 | USCRIPT_SARATI = 94, /* Sara */ |
262 | /** @stable ICU 3.6 */ |
263 | USCRIPT_ESTRANGELO_SYRIAC = 95, /* Syre */ |
264 | /** @stable ICU 3.6 */ |
265 | USCRIPT_WESTERN_SYRIAC = 96, /* Syrj */ |
266 | /** @stable ICU 3.6 */ |
267 | USCRIPT_EASTERN_SYRIAC = 97, /* Syrn */ |
268 | /** @stable ICU 3.6 */ |
269 | USCRIPT_TENGWAR = 98, /* Teng */ |
270 | /** @stable ICU 3.6 */ |
271 | USCRIPT_VAI = 99, /* Vaii */ |
272 | /** @stable ICU 3.6 */ |
273 | USCRIPT_VISIBLE_SPEECH = 100,/* Visp */ |
274 | /** @stable ICU 3.6 */ |
275 | USCRIPT_CUNEIFORM = 101,/* Xsux */ |
276 | /** @stable ICU 3.6 */ |
277 | USCRIPT_UNWRITTEN_LANGUAGES = 102,/* Zxxx */ |
278 | /** @stable ICU 3.6 */ |
279 | USCRIPT_UNKNOWN = 103,/* Zzzz */ /* Unknown="Code for uncoded script", for unassigned code points */ |
280 | |
281 | /* New script codes from ISO 15924 */ |
282 | /** @stable ICU 3.8 */ |
283 | USCRIPT_CARIAN = 104,/* Cari */ |
284 | /** @stable ICU 3.8 */ |
285 | USCRIPT_JAPANESE = 105,/* Jpan */ |
286 | /** @stable ICU 3.8 */ |
287 | USCRIPT_LANNA = 106,/* Lana */ |
288 | /** @stable ICU 3.8 */ |
289 | USCRIPT_LYCIAN = 107,/* Lyci */ |
290 | /** @stable ICU 3.8 */ |
291 | USCRIPT_LYDIAN = 108,/* Lydi */ |
292 | /** @stable ICU 3.8 */ |
293 | USCRIPT_OL_CHIKI = 109,/* Olck */ |
294 | /** @stable ICU 3.8 */ |
295 | USCRIPT_REJANG = 110,/* Rjng */ |
296 | /** @stable ICU 3.8 */ |
297 | USCRIPT_SAURASHTRA = 111,/* Saur */ |
298 | /** @stable ICU 3.8 */ |
299 | USCRIPT_SIGN_WRITING = 112,/* Sgnw */ |
300 | /** @stable ICU 3.8 */ |
301 | USCRIPT_SUNDANESE = 113,/* Sund */ |
302 | /** @stable ICU 3.8 */ |
303 | USCRIPT_MOON = 114,/* Moon */ |
304 | /** @stable ICU 3.8 */ |
305 | USCRIPT_MEITEI_MAYEK = 115,/* Mtei */ |
306 | |
307 | /* New script codes from ISO 15924 */ |
308 | /** @stable ICU 4.0 */ |
309 | USCRIPT_IMPERIAL_ARAMAIC = 116,/* Armi */ |
310 | /** @stable ICU 4.0 */ |
311 | USCRIPT_AVESTAN = 117,/* Avst */ |
312 | /** @stable ICU 4.0 */ |
313 | USCRIPT_CHAKMA = 118,/* Cakm */ |
314 | /** @stable ICU 4.0 */ |
315 | USCRIPT_KOREAN = 119,/* Kore */ |
316 | /** @stable ICU 4.0 */ |
317 | USCRIPT_KAITHI = 120,/* Kthi */ |
318 | /** @stable ICU 4.0 */ |
319 | USCRIPT_MANICHAEAN = 121,/* Mani */ |
320 | /** @stable ICU 4.0 */ |
321 | USCRIPT_INSCRIPTIONAL_PAHLAVI = 122,/* Phli */ |
322 | /** @stable ICU 4.0 */ |
323 | USCRIPT_PSALTER_PAHLAVI = 123,/* Phlp */ |
324 | /** @stable ICU 4.0 */ |
325 | USCRIPT_BOOK_PAHLAVI = 124,/* Phlv */ |
326 | /** @stable ICU 4.0 */ |
327 | USCRIPT_INSCRIPTIONAL_PARTHIAN = 125,/* Prti */ |
328 | /** @stable ICU 4.0 */ |
329 | USCRIPT_SAMARITAN = 126,/* Samr */ |
330 | /** @stable ICU 4.0 */ |
331 | USCRIPT_TAI_VIET = 127,/* Tavt */ |
332 | /** @stable ICU 4.0 */ |
333 | USCRIPT_MATHEMATICAL_NOTATION = 128,/* Zmth */ |
334 | /** @stable ICU 4.0 */ |
335 | USCRIPT_SYMBOLS = 129,/* Zsym */ |
336 | |
337 | /* New script codes from ISO 15924 */ |
338 | /** @stable ICU 4.4 */ |
339 | USCRIPT_BAMUM = 130,/* Bamu */ |
340 | /** @stable ICU 4.4 */ |
341 | USCRIPT_LISU = 131,/* Lisu */ |
342 | /** @stable ICU 4.4 */ |
343 | USCRIPT_NAKHI_GEBA = 132,/* Nkgb */ |
344 | /** @stable ICU 4.4 */ |
345 | USCRIPT_OLD_SOUTH_ARABIAN = 133,/* Sarb */ |
346 | |
347 | /* New script codes from ISO 15924 */ |
348 | /** @stable ICU 4.6 */ |
349 | USCRIPT_BASSA_VAH = 134,/* Bass */ |
350 | /** @stable ICU 4.6 */ |
351 | USCRIPT_DUPLOYAN_SHORTAND = 135,/* Dupl */ |
352 | /** @stable ICU 4.6 */ |
353 | USCRIPT_ELBASAN = 136,/* Elba */ |
354 | /** @stable ICU 4.6 */ |
355 | USCRIPT_GRANTHA = 137,/* Gran */ |
356 | /** @stable ICU 4.6 */ |
357 | USCRIPT_KPELLE = 138,/* Kpel */ |
358 | /** @stable ICU 4.6 */ |
359 | USCRIPT_LOMA = 139,/* Loma */ |
360 | /** @stable ICU 4.6 */ |
361 | USCRIPT_MENDE = 140,/* Mend */ |
362 | /** @stable ICU 4.6 */ |
363 | USCRIPT_MEROITIC_CURSIVE = 141,/* Merc */ |
364 | /** @stable ICU 4.6 */ |
365 | USCRIPT_OLD_NORTH_ARABIAN = 142,/* Narb */ |
366 | /** @stable ICU 4.6 */ |
367 | USCRIPT_NABATAEAN = 143,/* Nbat */ |
368 | /** @stable ICU 4.6 */ |
369 | USCRIPT_PALMYRENE = 144,/* Palm */ |
370 | /** @stable ICU 4.6 */ |
371 | USCRIPT_SINDHI = 145,/* Sind */ |
372 | /** @stable ICU 4.6 */ |
373 | USCRIPT_WARANG_CITI = 146,/* Wara */ |
374 | |
375 | /** @stable ICU 4.8 */ |
376 | USCRIPT_AFAKA = 147,/* Afak */ |
377 | /** @stable ICU 4.8 */ |
378 | USCRIPT_JURCHEN = 148,/* Jurc */ |
379 | /** @stable ICU 4.8 */ |
380 | USCRIPT_MRO = 149,/* Mroo */ |
381 | /** @stable ICU 4.8 */ |
382 | USCRIPT_NUSHU = 150,/* Nshu */ |
383 | /** @stable ICU 4.8 */ |
384 | USCRIPT_SHARADA = 151,/* Shrd */ |
385 | /** @stable ICU 4.8 */ |
386 | USCRIPT_SORA_SOMPENG = 152,/* Sora */ |
387 | /** @stable ICU 4.8 */ |
388 | USCRIPT_TAKRI = 153,/* Takr */ |
389 | /** @stable ICU 4.8 */ |
390 | USCRIPT_TANGUT = 154,/* Tang */ |
391 | /** @stable ICU 4.8 */ |
392 | USCRIPT_WOLEAI = 155,/* Wole */ |
393 | |
394 | /** @stable ICU 49 */ |
395 | USCRIPT_ANATOLIAN_HIEROGLYPHS = 156,/* Hluw */ |
396 | /** @stable ICU 49 */ |
397 | USCRIPT_KHOJKI = 157,/* Khoj */ |
398 | /** @stable ICU 49 */ |
399 | USCRIPT_TIRHUTA = 158,/* Tirh */ |
400 | |
401 | /** @stable ICU 52 */ |
402 | USCRIPT_CAUCASIAN_ALBANIAN = 159,/* Aghb */ |
403 | /** @stable ICU 52 */ |
404 | USCRIPT_MAHAJANI = 160,/* Mahj */ |
405 | |
406 | /* Private use codes from Qaaa - Qabx are not supported */ |
407 | |
408 | /** @stable ICU 2.2 */ |
409 | USCRIPT_CODE_LIMIT = 161 |
410 | } UScriptCode; |
411 | |
412 | /** |
413 | * Gets script codes associated with the given locale or ISO 15924 abbreviation or name. |
414 | * Fills in USCRIPT_MALAYALAM given "Malayam" OR "Mlym". |
415 | * Fills in USCRIPT_LATIN given "en" OR "en_US" |
416 | * If required capacity is greater than capacity of the destination buffer then the error code |
417 | * is set to U_BUFFER_OVERFLOW_ERROR and the required capacity is returned |
418 | * |
419 | * <p>Note: To search by short or long script alias only, use |
420 | * u_getPropertyValueEnum(UCHAR_SCRIPT, alias) instead. This does |
421 | * a fast lookup with no access of the locale data. |
422 | * @param nameOrAbbrOrLocale name of the script, as given in |
423 | * PropertyValueAliases.txt, or ISO 15924 code or locale |
424 | * @param fillIn the UScriptCode buffer to fill in the script code |
425 | * @param capacity the capacity (size) fo UScriptCode buffer passed in. |
426 | * @param err the error status code. |
427 | * @return The number of script codes filled in the buffer passed in |
428 | * @stable ICU 2.4 |
429 | */ |
430 | U_STABLE int32_t U_EXPORT2 |
431 | uscript_getCode(const char* nameOrAbbrOrLocale,UScriptCode* fillIn,int32_t capacity,UErrorCode *err); |
432 | |
433 | /** |
434 | * Gets a script name associated with the given script code. |
435 | * Returns "Malayam" given USCRIPT_MALAYALAM |
436 | * @param scriptCode UScriptCode enum |
437 | * @return script long name as given in |
438 | * PropertyValueAliases.txt, or NULL if scriptCode is invalid |
439 | * @stable ICU 2.4 |
440 | */ |
441 | U_STABLE const char* U_EXPORT2 |
442 | uscript_getName(UScriptCode scriptCode); |
443 | |
444 | /** |
445 | * Gets a script name associated with the given script code. |
446 | * Returns "Mlym" given USCRIPT_MALAYALAM |
447 | * @param scriptCode UScriptCode enum |
448 | * @return script abbreviated name as given in |
449 | * PropertyValueAliases.txt, or NULL if scriptCode is invalid |
450 | * @stable ICU 2.4 |
451 | */ |
452 | U_STABLE const char* U_EXPORT2 |
453 | uscript_getShortName(UScriptCode scriptCode); |
454 | |
455 | /** |
456 | * Gets the script code associated with the given codepoint. |
457 | * Returns USCRIPT_MALAYALAM given 0x0D02 |
458 | * @param codepoint UChar32 codepoint |
459 | * @param err the error status code. |
460 | * @return The UScriptCode, or 0 if codepoint is invalid |
461 | * @stable ICU 2.4 |
462 | */ |
463 | U_STABLE UScriptCode U_EXPORT2 |
464 | uscript_getScript(UChar32 codepoint, UErrorCode *err); |
465 | |
466 | /** |
467 | * Do the Script_Extensions of code point c contain script sc? |
468 | * If c does not have explicit Script_Extensions, then this tests whether |
469 | * c has the Script property value sc. |
470 | * |
471 | * Some characters are commonly used in multiple scripts. |
472 | * For more information, see UAX #24: http://www.unicode.org/reports/tr24/. |
473 | * |
474 | * The Script_Extensions property is provisional. It may be modified or removed |
475 | * in future versions of the Unicode Standard, and thus in ICU. |
476 | * @param c code point |
477 | * @param sc script code |
478 | * @return TRUE if sc is in Script_Extensions(c) |
479 | * @stable ICU 49 |
480 | */ |
481 | U_STABLE UBool U_EXPORT2 |
482 | uscript_hasScript(UChar32 c, UScriptCode sc); |
483 | |
484 | /** |
485 | * Writes code point c's Script_Extensions as a list of UScriptCode values |
486 | * to the output scripts array and returns the number of script codes. |
487 | * - If c does have Script_Extensions, then the Script property value |
488 | * (normally Common or Inherited) is not included. |
489 | * - If c does not have Script_Extensions, then the one Script code is written to the output array. |
490 | * - If c is not a valid code point, then the one USCRIPT_UNKNOWN code is written. |
491 | * In other words, if the return value is 1, |
492 | * then the output array contains exactly c's single Script code. |
493 | * If the return value is n>=2, then the output array contains c's n Script_Extensions script codes. |
494 | * |
495 | * Some characters are commonly used in multiple scripts. |
496 | * For more information, see UAX #24: http://www.unicode.org/reports/tr24/. |
497 | * |
498 | * If there are more than capacity script codes to be written, then |
499 | * U_BUFFER_OVERFLOW_ERROR is set and the number of Script_Extensions is returned. |
500 | * (Usual ICU buffer handling behavior.) |
501 | * |
502 | * The Script_Extensions property is provisional. It may be modified or removed |
503 | * in future versions of the Unicode Standard, and thus in ICU. |
504 | * @param c code point |
505 | * @param scripts output script code array |
506 | * @param capacity capacity of the scripts array |
507 | * @param errorCode Standard ICU error code. Its input value must |
508 | * pass the U_SUCCESS() test, or else the function returns |
509 | * immediately. Check for U_FAILURE() on output or use with |
510 | * function chaining. (See User Guide for details.) |
511 | * @return number of script codes in c's Script_Extensions, or 1 for the single Script value, |
512 | * written to scripts unless U_BUFFER_OVERFLOW_ERROR indicates insufficient capacity |
513 | * @stable ICU 49 |
514 | */ |
515 | U_STABLE int32_t U_EXPORT2 |
516 | uscript_getScriptExtensions(UChar32 c, |
517 | UScriptCode *scripts, int32_t capacity, |
518 | UErrorCode *errorCode); |
519 | |
520 | /** |
521 | * Script usage constants. |
522 | * See UAX #31 Unicode Identifier and Pattern Syntax. |
523 | * http://www.unicode.org/reports/tr31/#Table_Candidate_Characters_for_Exclusion_from_Identifiers |
524 | * |
525 | * @stable ICU 51 |
526 | */ |
527 | typedef enum UScriptUsage { |
528 | /** Not encoded in Unicode. @stable ICU 51 */ |
529 | USCRIPT_USAGE_NOT_ENCODED, |
530 | /** Unknown script usage. @stable ICU 51 */ |
531 | USCRIPT_USAGE_UNKNOWN, |
532 | /** Candidate for Exclusion from Identifiers. @stable ICU 51 */ |
533 | USCRIPT_USAGE_EXCLUDED, |
534 | /** Limited Use script. @stable ICU 51 */ |
535 | USCRIPT_USAGE_LIMITED_USE, |
536 | /** Aspirational Use script. @stable ICU 51 */ |
537 | USCRIPT_USAGE_ASPIRATIONAL, |
538 | /** Recommended script. @stable ICU 51 */ |
539 | USCRIPT_USAGE_RECOMMENDED |
540 | } UScriptUsage; |
541 | |
542 | /** |
543 | * Writes the script sample character string. |
544 | * This string normally consists of one code point but might be longer. |
545 | * The string is empty if the script is not encoded. |
546 | * |
547 | * @param script script code |
548 | * @param dest output string array |
549 | * @param capacity number of UChars in the dest array |
550 | * @param pErrorCode standard ICU in/out error code, must pass U_SUCCESS() on input |
551 | * @return the string length, even if U_BUFFER_OVERFLOW_ERROR |
552 | * @stable ICU 51 |
553 | */ |
554 | U_STABLE int32_t U_EXPORT2 |
555 | uscript_getSampleString(UScriptCode script, UChar *dest, int32_t capacity, UErrorCode *pErrorCode); |
556 | |
557 | #if U_SHOW_CPLUSPLUS_API |
558 | |
559 | U_NAMESPACE_BEGIN |
560 | class UnicodeString; |
561 | U_NAMESPACE_END |
562 | |
563 | /** |
564 | * Returns the script sample character string. |
565 | * This string normally consists of one code point but might be longer. |
566 | * The string is empty if the script is not encoded. |
567 | * |
568 | * @param script script code |
569 | * @return the sample character string |
570 | * @stable ICU 51 |
571 | */ |
572 | U_COMMON_API icu::UnicodeString U_EXPORT2 |
573 | uscript_getSampleUnicodeString(UScriptCode script); |
574 | |
575 | #endif |
576 | |
577 | /** |
578 | * Returns the script usage according to UAX #31 Unicode Identifier and Pattern Syntax. |
579 | * Returns USCRIPT_USAGE_NOT_ENCODED if the script is not encoded in Unicode. |
580 | * |
581 | * @param script script code |
582 | * @return script usage |
583 | * @see UScriptUsage |
584 | * @stable ICU 51 |
585 | */ |
586 | U_STABLE UScriptUsage U_EXPORT2 |
587 | uscript_getUsage(UScriptCode script); |
588 | |
589 | /** |
590 | * Returns TRUE if the script is written right-to-left. |
591 | * For example, Arab and Hebr. |
592 | * |
593 | * @param script script code |
594 | * @return TRUE if the script is right-to-left |
595 | * @stable ICU 51 |
596 | */ |
597 | U_STABLE UBool U_EXPORT2 |
598 | uscript_isRightToLeft(UScriptCode script); |
599 | |
600 | /** |
601 | * Returns TRUE if the script allows line breaks between letters (excluding hyphenation). |
602 | * Such a script typically requires dictionary-based line breaking. |
603 | * For example, Hani and Thai. |
604 | * |
605 | * @param script script code |
606 | * @return TRUE if the script allows line breaks between letters |
607 | * @stable ICU 51 |
608 | */ |
609 | U_STABLE UBool U_EXPORT2 |
610 | uscript_breaksBetweenLetters(UScriptCode script); |
611 | |
612 | /** |
613 | * Returns TRUE if in modern (or most recent) usage of the script case distinctions are customary. |
614 | * For example, Latn and Cyrl. |
615 | * |
616 | * @param script script code |
617 | * @return TRUE if the script is cased |
618 | * @stable ICU 51 |
619 | */ |
620 | U_STABLE UBool U_EXPORT2 |
621 | uscript_isCased(UScriptCode script); |
622 | |
623 | #endif |
624 | |