|
||||
Warning, file /include/unicode/uscript.h was not indexed or was modified since last indexation (in which case cross-reference links may be missing, inaccurate or erroneous).
0001 // © 2016 and later: Unicode, Inc. and others. 0002 // License & terms of use: http://www.unicode.org/copyright.html 0003 /* 0004 ********************************************************************** 0005 * Copyright (C) 1997-2016, International Business Machines 0006 * Corporation and others. All Rights Reserved. 0007 ********************************************************************** 0008 * 0009 * File USCRIPT.H 0010 * 0011 * Modification History: 0012 * 0013 * Date Name Description 0014 * 07/06/2001 Ram Creation. 0015 ****************************************************************************** 0016 */ 0017 0018 #ifndef USCRIPT_H 0019 #define USCRIPT_H 0020 #include "unicode/utypes.h" 0021 0022 /** 0023 * \file 0024 * \brief C API: Unicode Script Information 0025 */ 0026 0027 /** 0028 * Constants for ISO 15924 script codes. 0029 * 0030 * The current set of script code constants supports at least all scripts 0031 * that are encoded in the version of Unicode which ICU currently supports. 0032 * The names of the constants are usually derived from the 0033 * Unicode script property value aliases. 0034 * See UAX #24 Unicode Script Property (http://www.unicode.org/reports/tr24/) 0035 * and http://www.unicode.org/Public/UCD/latest/ucd/PropertyValueAliases.txt . 0036 * 0037 * In addition, constants for many ISO 15924 script codes 0038 * are included, for use with language tags, CLDR data, and similar. 0039 * Some of those codes are not used in the Unicode Character Database (UCD). 0040 * For example, there are no characters that have a UCD script property value of 0041 * Hans or Hant. All Han ideographs have the Hani script property value in Unicode. 0042 * 0043 * Private-use codes Qaaa..Qabx are not included, except as used in the UCD or in CLDR. 0044 * 0045 * Starting with ICU 55, script codes are only added when their scripts 0046 * have been or will certainly be encoded in Unicode, 0047 * and have been assigned Unicode script property value aliases, 0048 * to ensure that their script names are stable and match the names of the constants. 0049 * Script codes like Latf and Aran that are not subject to separate encoding 0050 * may be added at any time. 0051 * 0052 * @stable ICU 2.2 0053 */ 0054 typedef enum UScriptCode { 0055 /* 0056 * Note: UScriptCode constants and their ISO script code comments 0057 * are parsed by preparseucd.py. 0058 * It matches lines like 0059 * USCRIPT_<Unicode Script value name> = <integer>, / * <ISO script code> * / 0060 */ 0061 0062 /** @stable ICU 2.2 */ 0063 USCRIPT_INVALID_CODE = -1, 0064 /** @stable ICU 2.2 */ 0065 USCRIPT_COMMON = 0, /* Zyyy */ 0066 /** @stable ICU 2.2 */ 0067 USCRIPT_INHERITED = 1, /* Zinh */ /* "Code for inherited script", for non-spacing combining marks; also Qaai */ 0068 /** @stable ICU 2.2 */ 0069 USCRIPT_ARABIC = 2, /* Arab */ 0070 /** @stable ICU 2.2 */ 0071 USCRIPT_ARMENIAN = 3, /* Armn */ 0072 /** @stable ICU 2.2 */ 0073 USCRIPT_BENGALI = 4, /* Beng */ 0074 /** @stable ICU 2.2 */ 0075 USCRIPT_BOPOMOFO = 5, /* Bopo */ 0076 /** @stable ICU 2.2 */ 0077 USCRIPT_CHEROKEE = 6, /* Cher */ 0078 /** @stable ICU 2.2 */ 0079 USCRIPT_COPTIC = 7, /* Copt */ 0080 /** @stable ICU 2.2 */ 0081 USCRIPT_CYRILLIC = 8, /* Cyrl */ 0082 /** @stable ICU 2.2 */ 0083 USCRIPT_DESERET = 9, /* Dsrt */ 0084 /** @stable ICU 2.2 */ 0085 USCRIPT_DEVANAGARI = 10, /* Deva */ 0086 /** @stable ICU 2.2 */ 0087 USCRIPT_ETHIOPIC = 11, /* Ethi */ 0088 /** @stable ICU 2.2 */ 0089 USCRIPT_GEORGIAN = 12, /* Geor */ 0090 /** @stable ICU 2.2 */ 0091 USCRIPT_GOTHIC = 13, /* Goth */ 0092 /** @stable ICU 2.2 */ 0093 USCRIPT_GREEK = 14, /* Grek */ 0094 /** @stable ICU 2.2 */ 0095 USCRIPT_GUJARATI = 15, /* Gujr */ 0096 /** @stable ICU 2.2 */ 0097 USCRIPT_GURMUKHI = 16, /* Guru */ 0098 /** @stable ICU 2.2 */ 0099 USCRIPT_HAN = 17, /* Hani */ 0100 /** @stable ICU 2.2 */ 0101 USCRIPT_HANGUL = 18, /* Hang */ 0102 /** @stable ICU 2.2 */ 0103 USCRIPT_HEBREW = 19, /* Hebr */ 0104 /** @stable ICU 2.2 */ 0105 USCRIPT_HIRAGANA = 20, /* Hira */ 0106 /** @stable ICU 2.2 */ 0107 USCRIPT_KANNADA = 21, /* Knda */ 0108 /** @stable ICU 2.2 */ 0109 USCRIPT_KATAKANA = 22, /* Kana */ 0110 /** @stable ICU 2.2 */ 0111 USCRIPT_KHMER = 23, /* Khmr */ 0112 /** @stable ICU 2.2 */ 0113 USCRIPT_LAO = 24, /* Laoo */ 0114 /** @stable ICU 2.2 */ 0115 USCRIPT_LATIN = 25, /* Latn */ 0116 /** @stable ICU 2.2 */ 0117 USCRIPT_MALAYALAM = 26, /* Mlym */ 0118 /** @stable ICU 2.2 */ 0119 USCRIPT_MONGOLIAN = 27, /* Mong */ 0120 /** @stable ICU 2.2 */ 0121 USCRIPT_MYANMAR = 28, /* Mymr */ 0122 /** @stable ICU 2.2 */ 0123 USCRIPT_OGHAM = 29, /* Ogam */ 0124 /** @stable ICU 2.2 */ 0125 USCRIPT_OLD_ITALIC = 30, /* Ital */ 0126 /** @stable ICU 2.2 */ 0127 USCRIPT_ORIYA = 31, /* Orya */ 0128 /** @stable ICU 2.2 */ 0129 USCRIPT_RUNIC = 32, /* Runr */ 0130 /** @stable ICU 2.2 */ 0131 USCRIPT_SINHALA = 33, /* Sinh */ 0132 /** @stable ICU 2.2 */ 0133 USCRIPT_SYRIAC = 34, /* Syrc */ 0134 /** @stable ICU 2.2 */ 0135 USCRIPT_TAMIL = 35, /* Taml */ 0136 /** @stable ICU 2.2 */ 0137 USCRIPT_TELUGU = 36, /* Telu */ 0138 /** @stable ICU 2.2 */ 0139 USCRIPT_THAANA = 37, /* Thaa */ 0140 /** @stable ICU 2.2 */ 0141 USCRIPT_THAI = 38, /* Thai */ 0142 /** @stable ICU 2.2 */ 0143 USCRIPT_TIBETAN = 39, /* Tibt */ 0144 /** Canadian_Aboriginal script. @stable ICU 2.6 */ 0145 USCRIPT_CANADIAN_ABORIGINAL = 40, /* Cans */ 0146 /** Canadian_Aboriginal script (alias). @stable ICU 2.2 */ 0147 USCRIPT_UCAS = USCRIPT_CANADIAN_ABORIGINAL, 0148 /** @stable ICU 2.2 */ 0149 USCRIPT_YI = 41, /* Yiii */ 0150 /* New scripts in Unicode 3.2 */ 0151 /** @stable ICU 2.2 */ 0152 USCRIPT_TAGALOG = 42, /* Tglg */ 0153 /** @stable ICU 2.2 */ 0154 USCRIPT_HANUNOO = 43, /* Hano */ 0155 /** @stable ICU 2.2 */ 0156 USCRIPT_BUHID = 44, /* Buhd */ 0157 /** @stable ICU 2.2 */ 0158 USCRIPT_TAGBANWA = 45, /* Tagb */ 0159 0160 /* New scripts in Unicode 4 */ 0161 /** @stable ICU 2.6 */ 0162 USCRIPT_BRAILLE = 46, /* Brai */ 0163 /** @stable ICU 2.6 */ 0164 USCRIPT_CYPRIOT = 47, /* Cprt */ 0165 /** @stable ICU 2.6 */ 0166 USCRIPT_LIMBU = 48, /* Limb */ 0167 /** @stable ICU 2.6 */ 0168 USCRIPT_LINEAR_B = 49, /* Linb */ 0169 /** @stable ICU 2.6 */ 0170 USCRIPT_OSMANYA = 50, /* Osma */ 0171 /** @stable ICU 2.6 */ 0172 USCRIPT_SHAVIAN = 51, /* Shaw */ 0173 /** @stable ICU 2.6 */ 0174 USCRIPT_TAI_LE = 52, /* Tale */ 0175 /** @stable ICU 2.6 */ 0176 USCRIPT_UGARITIC = 53, /* Ugar */ 0177 0178 /** New script code in Unicode 4.0.1 @stable ICU 3.0 */ 0179 USCRIPT_KATAKANA_OR_HIRAGANA = 54,/*Hrkt */ 0180 0181 /* New scripts in Unicode 4.1 */ 0182 /** @stable ICU 3.4 */ 0183 USCRIPT_BUGINESE = 55, /* Bugi */ 0184 /** @stable ICU 3.4 */ 0185 USCRIPT_GLAGOLITIC = 56, /* Glag */ 0186 /** @stable ICU 3.4 */ 0187 USCRIPT_KHAROSHTHI = 57, /* Khar */ 0188 /** @stable ICU 3.4 */ 0189 USCRIPT_SYLOTI_NAGRI = 58, /* Sylo */ 0190 /** @stable ICU 3.4 */ 0191 USCRIPT_NEW_TAI_LUE = 59, /* Talu */ 0192 /** @stable ICU 3.4 */ 0193 USCRIPT_TIFINAGH = 60, /* Tfng */ 0194 /** @stable ICU 3.4 */ 0195 USCRIPT_OLD_PERSIAN = 61, /* Xpeo */ 0196 0197 /* New script codes from Unicode and ISO 15924 */ 0198 /** @stable ICU 3.6 */ 0199 USCRIPT_BALINESE = 62, /* Bali */ 0200 /** @stable ICU 3.6 */ 0201 USCRIPT_BATAK = 63, /* Batk */ 0202 /** @stable ICU 3.6 */ 0203 USCRIPT_BLISSYMBOLS = 64, /* Blis */ 0204 /** @stable ICU 3.6 */ 0205 USCRIPT_BRAHMI = 65, /* Brah */ 0206 /** @stable ICU 3.6 */ 0207 USCRIPT_CHAM = 66, /* Cham */ 0208 /** @stable ICU 3.6 */ 0209 USCRIPT_CIRTH = 67, /* Cirt */ 0210 /** @stable ICU 3.6 */ 0211 USCRIPT_OLD_CHURCH_SLAVONIC_CYRILLIC = 68, /* Cyrs */ 0212 /** @stable ICU 3.6 */ 0213 USCRIPT_DEMOTIC_EGYPTIAN = 69, /* Egyd */ 0214 /** @stable ICU 3.6 */ 0215 USCRIPT_HIERATIC_EGYPTIAN = 70, /* Egyh */ 0216 /** @stable ICU 3.6 */ 0217 USCRIPT_EGYPTIAN_HIEROGLYPHS = 71, /* Egyp */ 0218 /** @stable ICU 3.6 */ 0219 USCRIPT_KHUTSURI = 72, /* Geok */ 0220 /** @stable ICU 3.6 */ 0221 USCRIPT_SIMPLIFIED_HAN = 73, /* Hans */ 0222 /** @stable ICU 3.6 */ 0223 USCRIPT_TRADITIONAL_HAN = 74, /* Hant */ 0224 /** @stable ICU 3.6 */ 0225 USCRIPT_PAHAWH_HMONG = 75, /* Hmng */ 0226 /** @stable ICU 3.6 */ 0227 USCRIPT_OLD_HUNGARIAN = 76, /* Hung */ 0228 /** @stable ICU 3.6 */ 0229 USCRIPT_HARAPPAN_INDUS = 77, /* Inds */ 0230 /** @stable ICU 3.6 */ 0231 USCRIPT_JAVANESE = 78, /* Java */ 0232 /** @stable ICU 3.6 */ 0233 USCRIPT_KAYAH_LI = 79, /* Kali */ 0234 /** @stable ICU 3.6 */ 0235 USCRIPT_LATIN_FRAKTUR = 80, /* Latf */ 0236 /** @stable ICU 3.6 */ 0237 USCRIPT_LATIN_GAELIC = 81, /* Latg */ 0238 /** @stable ICU 3.6 */ 0239 USCRIPT_LEPCHA = 82, /* Lepc */ 0240 /** @stable ICU 3.6 */ 0241 USCRIPT_LINEAR_A = 83, /* Lina */ 0242 /** @stable ICU 4.6 */ 0243 USCRIPT_MANDAIC = 84, /* Mand */ 0244 /** @stable ICU 3.6 */ 0245 USCRIPT_MANDAEAN = USCRIPT_MANDAIC, 0246 /** @stable ICU 3.6 */ 0247 USCRIPT_MAYAN_HIEROGLYPHS = 85, /* Maya */ 0248 /** @stable ICU 4.6 */ 0249 USCRIPT_MEROITIC_HIEROGLYPHS = 86, /* Mero */ 0250 /** @stable ICU 3.6 */ 0251 USCRIPT_MEROITIC = USCRIPT_MEROITIC_HIEROGLYPHS, 0252 /** @stable ICU 3.6 */ 0253 USCRIPT_NKO = 87, /* Nkoo */ 0254 /** @stable ICU 3.6 */ 0255 USCRIPT_ORKHON = 88, /* Orkh */ 0256 /** @stable ICU 3.6 */ 0257 USCRIPT_OLD_PERMIC = 89, /* Perm */ 0258 /** @stable ICU 3.6 */ 0259 USCRIPT_PHAGS_PA = 90, /* Phag */ 0260 /** @stable ICU 3.6 */ 0261 USCRIPT_PHOENICIAN = 91, /* Phnx */ 0262 /** @stable ICU 52 */ 0263 USCRIPT_MIAO = 92, /* Plrd */ 0264 /** @stable ICU 3.6 */ 0265 USCRIPT_PHONETIC_POLLARD = USCRIPT_MIAO, 0266 /** @stable ICU 3.6 */ 0267 USCRIPT_RONGORONGO = 93, /* Roro */ 0268 /** @stable ICU 3.6 */ 0269 USCRIPT_SARATI = 94, /* Sara */ 0270 /** @stable ICU 3.6 */ 0271 USCRIPT_ESTRANGELO_SYRIAC = 95, /* Syre */ 0272 /** @stable ICU 3.6 */ 0273 USCRIPT_WESTERN_SYRIAC = 96, /* Syrj */ 0274 /** @stable ICU 3.6 */ 0275 USCRIPT_EASTERN_SYRIAC = 97, /* Syrn */ 0276 /** @stable ICU 3.6 */ 0277 USCRIPT_TENGWAR = 98, /* Teng */ 0278 /** @stable ICU 3.6 */ 0279 USCRIPT_VAI = 99, /* Vaii */ 0280 /** @stable ICU 3.6 */ 0281 USCRIPT_VISIBLE_SPEECH = 100,/* Visp */ 0282 /** @stable ICU 3.6 */ 0283 USCRIPT_CUNEIFORM = 101,/* Xsux */ 0284 /** @stable ICU 3.6 */ 0285 USCRIPT_UNWRITTEN_LANGUAGES = 102,/* Zxxx */ 0286 /** @stable ICU 3.6 */ 0287 USCRIPT_UNKNOWN = 103,/* Zzzz */ /* Unknown="Code for uncoded script", for unassigned code points */ 0288 0289 /** @stable ICU 3.8 */ 0290 USCRIPT_CARIAN = 104,/* Cari */ 0291 /** @stable ICU 3.8 */ 0292 USCRIPT_JAPANESE = 105,/* Jpan */ 0293 /** @stable ICU 3.8 */ 0294 USCRIPT_LANNA = 106,/* Lana */ 0295 /** @stable ICU 3.8 */ 0296 USCRIPT_LYCIAN = 107,/* Lyci */ 0297 /** @stable ICU 3.8 */ 0298 USCRIPT_LYDIAN = 108,/* Lydi */ 0299 /** @stable ICU 3.8 */ 0300 USCRIPT_OL_CHIKI = 109,/* Olck */ 0301 /** @stable ICU 3.8 */ 0302 USCRIPT_REJANG = 110,/* Rjng */ 0303 /** @stable ICU 3.8 */ 0304 USCRIPT_SAURASHTRA = 111,/* Saur */ 0305 /** Sutton SignWriting @stable ICU 3.8 */ 0306 USCRIPT_SIGN_WRITING = 112,/* Sgnw */ 0307 /** @stable ICU 3.8 */ 0308 USCRIPT_SUNDANESE = 113,/* Sund */ 0309 /** @stable ICU 3.8 */ 0310 USCRIPT_MOON = 114,/* Moon */ 0311 /** @stable ICU 3.8 */ 0312 USCRIPT_MEITEI_MAYEK = 115,/* Mtei */ 0313 0314 /** @stable ICU 4.0 */ 0315 USCRIPT_IMPERIAL_ARAMAIC = 116,/* Armi */ 0316 /** @stable ICU 4.0 */ 0317 USCRIPT_AVESTAN = 117,/* Avst */ 0318 /** @stable ICU 4.0 */ 0319 USCRIPT_CHAKMA = 118,/* Cakm */ 0320 /** @stable ICU 4.0 */ 0321 USCRIPT_KOREAN = 119,/* Kore */ 0322 /** @stable ICU 4.0 */ 0323 USCRIPT_KAITHI = 120,/* Kthi */ 0324 /** @stable ICU 4.0 */ 0325 USCRIPT_MANICHAEAN = 121,/* Mani */ 0326 /** @stable ICU 4.0 */ 0327 USCRIPT_INSCRIPTIONAL_PAHLAVI = 122,/* Phli */ 0328 /** @stable ICU 4.0 */ 0329 USCRIPT_PSALTER_PAHLAVI = 123,/* Phlp */ 0330 /** @stable ICU 4.0 */ 0331 USCRIPT_BOOK_PAHLAVI = 124,/* Phlv */ 0332 /** @stable ICU 4.0 */ 0333 USCRIPT_INSCRIPTIONAL_PARTHIAN = 125,/* Prti */ 0334 /** @stable ICU 4.0 */ 0335 USCRIPT_SAMARITAN = 126,/* Samr */ 0336 /** @stable ICU 4.0 */ 0337 USCRIPT_TAI_VIET = 127,/* Tavt */ 0338 /** @stable ICU 4.0 */ 0339 USCRIPT_MATHEMATICAL_NOTATION = 128,/* Zmth */ 0340 /** @stable ICU 4.0 */ 0341 USCRIPT_SYMBOLS = 129,/* Zsym */ 0342 0343 /** @stable ICU 4.4 */ 0344 USCRIPT_BAMUM = 130,/* Bamu */ 0345 /** @stable ICU 4.4 */ 0346 USCRIPT_LISU = 131,/* Lisu */ 0347 /** @stable ICU 4.4 */ 0348 USCRIPT_NAKHI_GEBA = 132,/* Nkgb */ 0349 /** @stable ICU 4.4 */ 0350 USCRIPT_OLD_SOUTH_ARABIAN = 133,/* Sarb */ 0351 0352 /** @stable ICU 4.6 */ 0353 USCRIPT_BASSA_VAH = 134,/* Bass */ 0354 /** @stable ICU 54 */ 0355 USCRIPT_DUPLOYAN = 135,/* Dupl */ 0356 #ifndef U_HIDE_DEPRECATED_API 0357 /** @deprecated ICU 54 Typo, use USCRIPT_DUPLOYAN */ 0358 USCRIPT_DUPLOYAN_SHORTAND = USCRIPT_DUPLOYAN, 0359 #endif /* U_HIDE_DEPRECATED_API */ 0360 /** @stable ICU 4.6 */ 0361 USCRIPT_ELBASAN = 136,/* Elba */ 0362 /** @stable ICU 4.6 */ 0363 USCRIPT_GRANTHA = 137,/* Gran */ 0364 /** @stable ICU 4.6 */ 0365 USCRIPT_KPELLE = 138,/* Kpel */ 0366 /** @stable ICU 4.6 */ 0367 USCRIPT_LOMA = 139,/* Loma */ 0368 /** Mende Kikakui @stable ICU 4.6 */ 0369 USCRIPT_MENDE = 140,/* Mend */ 0370 /** @stable ICU 4.6 */ 0371 USCRIPT_MEROITIC_CURSIVE = 141,/* Merc */ 0372 /** @stable ICU 4.6 */ 0373 USCRIPT_OLD_NORTH_ARABIAN = 142,/* Narb */ 0374 /** @stable ICU 4.6 */ 0375 USCRIPT_NABATAEAN = 143,/* Nbat */ 0376 /** @stable ICU 4.6 */ 0377 USCRIPT_PALMYRENE = 144,/* Palm */ 0378 /** @stable ICU 54 */ 0379 USCRIPT_KHUDAWADI = 145,/* Sind */ 0380 /** @stable ICU 4.6 */ 0381 USCRIPT_SINDHI = USCRIPT_KHUDAWADI, 0382 /** @stable ICU 4.6 */ 0383 USCRIPT_WARANG_CITI = 146,/* Wara */ 0384 0385 /** @stable ICU 4.8 */ 0386 USCRIPT_AFAKA = 147,/* Afak */ 0387 /** @stable ICU 4.8 */ 0388 USCRIPT_JURCHEN = 148,/* Jurc */ 0389 /** @stable ICU 4.8 */ 0390 USCRIPT_MRO = 149,/* Mroo */ 0391 /** @stable ICU 4.8 */ 0392 USCRIPT_NUSHU = 150,/* Nshu */ 0393 /** @stable ICU 4.8 */ 0394 USCRIPT_SHARADA = 151,/* Shrd */ 0395 /** @stable ICU 4.8 */ 0396 USCRIPT_SORA_SOMPENG = 152,/* Sora */ 0397 /** @stable ICU 4.8 */ 0398 USCRIPT_TAKRI = 153,/* Takr */ 0399 /** @stable ICU 4.8 */ 0400 USCRIPT_TANGUT = 154,/* Tang */ 0401 /** @stable ICU 4.8 */ 0402 USCRIPT_WOLEAI = 155,/* Wole */ 0403 0404 /** @stable ICU 49 */ 0405 USCRIPT_ANATOLIAN_HIEROGLYPHS = 156,/* Hluw */ 0406 /** @stable ICU 49 */ 0407 USCRIPT_KHOJKI = 157,/* Khoj */ 0408 /** @stable ICU 49 */ 0409 USCRIPT_TIRHUTA = 158,/* Tirh */ 0410 0411 /** @stable ICU 52 */ 0412 USCRIPT_CAUCASIAN_ALBANIAN = 159,/* Aghb */ 0413 /** @stable ICU 52 */ 0414 USCRIPT_MAHAJANI = 160,/* Mahj */ 0415 0416 /** @stable ICU 54 */ 0417 USCRIPT_AHOM = 161,/* Ahom */ 0418 /** @stable ICU 54 */ 0419 USCRIPT_HATRAN = 162,/* Hatr */ 0420 /** @stable ICU 54 */ 0421 USCRIPT_MODI = 163,/* Modi */ 0422 /** @stable ICU 54 */ 0423 USCRIPT_MULTANI = 164,/* Mult */ 0424 /** @stable ICU 54 */ 0425 USCRIPT_PAU_CIN_HAU = 165,/* Pauc */ 0426 /** @stable ICU 54 */ 0427 USCRIPT_SIDDHAM = 166,/* Sidd */ 0428 0429 /** @stable ICU 58 */ 0430 USCRIPT_ADLAM = 167,/* Adlm */ 0431 /** @stable ICU 58 */ 0432 USCRIPT_BHAIKSUKI = 168,/* Bhks */ 0433 /** @stable ICU 58 */ 0434 USCRIPT_MARCHEN = 169,/* Marc */ 0435 /** @stable ICU 58 */ 0436 USCRIPT_NEWA = 170,/* Newa */ 0437 /** @stable ICU 58 */ 0438 USCRIPT_OSAGE = 171,/* Osge */ 0439 0440 /** @stable ICU 58 */ 0441 USCRIPT_HAN_WITH_BOPOMOFO = 172,/* Hanb */ 0442 /** @stable ICU 58 */ 0443 USCRIPT_JAMO = 173,/* Jamo */ 0444 /** @stable ICU 58 */ 0445 USCRIPT_SYMBOLS_EMOJI = 174,/* Zsye */ 0446 0447 /** @stable ICU 60 */ 0448 USCRIPT_MASARAM_GONDI = 175,/* Gonm */ 0449 /** @stable ICU 60 */ 0450 USCRIPT_SOYOMBO = 176,/* Soyo */ 0451 /** @stable ICU 60 */ 0452 USCRIPT_ZANABAZAR_SQUARE = 177,/* Zanb */ 0453 0454 /** @stable ICU 62 */ 0455 USCRIPT_DOGRA = 178,/* Dogr */ 0456 /** @stable ICU 62 */ 0457 USCRIPT_GUNJALA_GONDI = 179,/* Gong */ 0458 /** @stable ICU 62 */ 0459 USCRIPT_MAKASAR = 180,/* Maka */ 0460 /** @stable ICU 62 */ 0461 USCRIPT_MEDEFAIDRIN = 181,/* Medf */ 0462 /** @stable ICU 62 */ 0463 USCRIPT_HANIFI_ROHINGYA = 182,/* Rohg */ 0464 /** @stable ICU 62 */ 0465 USCRIPT_SOGDIAN = 183,/* Sogd */ 0466 /** @stable ICU 62 */ 0467 USCRIPT_OLD_SOGDIAN = 184,/* Sogo */ 0468 0469 /** @stable ICU 64 */ 0470 USCRIPT_ELYMAIC = 185,/* Elym */ 0471 /** @stable ICU 64 */ 0472 USCRIPT_NYIAKENG_PUACHUE_HMONG = 186,/* Hmnp */ 0473 /** @stable ICU 64 */ 0474 USCRIPT_NANDINAGARI = 187,/* Nand */ 0475 /** @stable ICU 64 */ 0476 USCRIPT_WANCHO = 188,/* Wcho */ 0477 0478 /** @stable ICU 66 */ 0479 USCRIPT_CHORASMIAN = 189,/* Chrs */ 0480 /** @stable ICU 66 */ 0481 USCRIPT_DIVES_AKURU = 190,/* Diak */ 0482 /** @stable ICU 66 */ 0483 USCRIPT_KHITAN_SMALL_SCRIPT = 191,/* Kits */ 0484 /** @stable ICU 66 */ 0485 USCRIPT_YEZIDI = 192,/* Yezi */ 0486 0487 /** @stable ICU 70 */ 0488 USCRIPT_CYPRO_MINOAN = 193,/* Cpmn */ 0489 /** @stable ICU 70 */ 0490 USCRIPT_OLD_UYGHUR = 194,/* Ougr */ 0491 /** @stable ICU 70 */ 0492 USCRIPT_TANGSA = 195,/* Tnsa */ 0493 /** @stable ICU 70 */ 0494 USCRIPT_TOTO = 196,/* Toto */ 0495 /** @stable ICU 70 */ 0496 USCRIPT_VITHKUQI = 197,/* Vith */ 0497 0498 /** @stable ICU 72 */ 0499 USCRIPT_KAWI = 198,/* Kawi */ 0500 /** @stable ICU 72 */ 0501 USCRIPT_NAG_MUNDARI = 199,/* Nagm */ 0502 0503 #ifndef U_HIDE_DEPRECATED_API 0504 /** 0505 * One more than the highest normal UScriptCode value. 0506 * The highest value is available via u_getIntPropertyMaxValue(UCHAR_SCRIPT). 0507 * 0508 * @deprecated ICU 58 The numeric value may change over time, see ICU ticket #12420. 0509 */ 0510 USCRIPT_CODE_LIMIT = 200 0511 #endif // U_HIDE_DEPRECATED_API 0512 } UScriptCode; 0513 0514 /** 0515 * Gets the script codes associated with the given locale or ISO 15924 abbreviation or name. 0516 * Fills in USCRIPT_MALAYALAM given "Malayam" OR "Mlym". 0517 * Fills in USCRIPT_LATIN given "en" OR "en_US" 0518 * If the required capacity is greater than the capacity of the destination buffer, 0519 * then the error code is set to U_BUFFER_OVERFLOW_ERROR and the required capacity is returned. 0520 * 0521 * <p>Note: To search by short or long script alias only, use 0522 * u_getPropertyValueEnum(UCHAR_SCRIPT, alias) instead. That does 0523 * a fast lookup with no access of the locale data. 0524 * 0525 * @param nameOrAbbrOrLocale name of the script, as given in 0526 * PropertyValueAliases.txt, or ISO 15924 code or locale 0527 * @param fillIn the UScriptCode buffer to fill in the script code 0528 * @param capacity the capacity (size) of UScriptCode buffer passed in. 0529 * @param err the error status code. 0530 * @return The number of script codes filled in the buffer passed in 0531 * @stable ICU 2.4 0532 */ 0533 U_CAPI int32_t U_EXPORT2 0534 uscript_getCode(const char* nameOrAbbrOrLocale,UScriptCode* fillIn,int32_t capacity,UErrorCode *err); 0535 0536 /** 0537 * Returns the long Unicode script name, if there is one. 0538 * Otherwise returns the 4-letter ISO 15924 script code. 0539 * Returns "Malayam" given USCRIPT_MALAYALAM. 0540 * 0541 * @param scriptCode UScriptCode enum 0542 * @return long script name as given in PropertyValueAliases.txt, or the 4-letter code, 0543 * or NULL if scriptCode is invalid 0544 * @stable ICU 2.4 0545 */ 0546 U_CAPI const char* U_EXPORT2 0547 uscript_getName(UScriptCode scriptCode); 0548 0549 /** 0550 * Returns the 4-letter ISO 15924 script code, 0551 * which is the same as the short Unicode script name if Unicode has names for the script. 0552 * Returns "Mlym" given USCRIPT_MALAYALAM. 0553 * 0554 * @param scriptCode UScriptCode enum 0555 * @return short script name (4-letter code), or NULL if scriptCode is invalid 0556 * @stable ICU 2.4 0557 */ 0558 U_CAPI const char* U_EXPORT2 0559 uscript_getShortName(UScriptCode scriptCode); 0560 0561 /** 0562 * Gets the script code associated with the given codepoint. 0563 * Returns USCRIPT_MALAYALAM given 0x0D02 0564 * @param codepoint UChar32 codepoint 0565 * @param err the error status code. 0566 * @return The UScriptCode, or 0 if codepoint is invalid 0567 * @stable ICU 2.4 0568 */ 0569 U_CAPI UScriptCode U_EXPORT2 0570 uscript_getScript(UChar32 codepoint, UErrorCode *err); 0571 0572 /** 0573 * Do the Script_Extensions of code point c contain script sc? 0574 * If c does not have explicit Script_Extensions, then this tests whether 0575 * c has the Script property value sc. 0576 * 0577 * Some characters are commonly used in multiple scripts. 0578 * For more information, see UAX #24: http://www.unicode.org/reports/tr24/. 0579 * @param c code point 0580 * @param sc script code 0581 * @return true if sc is in Script_Extensions(c) 0582 * @stable ICU 49 0583 */ 0584 U_CAPI UBool U_EXPORT2 0585 uscript_hasScript(UChar32 c, UScriptCode sc); 0586 0587 /** 0588 * Writes code point c's Script_Extensions as a list of UScriptCode values 0589 * to the output scripts array and returns the number of script codes. 0590 * - If c does have Script_Extensions, then the Script property value 0591 * (normally Common or Inherited) is not included. 0592 * - If c does not have Script_Extensions, then the one Script code is written to the output array. 0593 * - If c is not a valid code point, then the one USCRIPT_UNKNOWN code is written. 0594 * In other words, if the return value is 1, 0595 * then the output array contains exactly c's single Script code. 0596 * If the return value is n>=2, then the output array contains c's n Script_Extensions script codes. 0597 * 0598 * Some characters are commonly used in multiple scripts. 0599 * For more information, see UAX #24: http://www.unicode.org/reports/tr24/. 0600 * 0601 * If there are more than capacity script codes to be written, then 0602 * U_BUFFER_OVERFLOW_ERROR is set and the number of Script_Extensions is returned. 0603 * (Usual ICU buffer handling behavior.) 0604 * 0605 * @param c code point 0606 * @param scripts output script code array 0607 * @param capacity capacity of the scripts array 0608 * @param errorCode Standard ICU error code. Its input value must 0609 * pass the U_SUCCESS() test, or else the function returns 0610 * immediately. Check for U_FAILURE() on output or use with 0611 * function chaining. (See User Guide for details.) 0612 * @return number of script codes in c's Script_Extensions, or 1 for the single Script value, 0613 * written to scripts unless U_BUFFER_OVERFLOW_ERROR indicates insufficient capacity 0614 * @stable ICU 49 0615 */ 0616 U_CAPI int32_t U_EXPORT2 0617 uscript_getScriptExtensions(UChar32 c, 0618 UScriptCode *scripts, int32_t capacity, 0619 UErrorCode *errorCode); 0620 0621 /** 0622 * Script usage constants. 0623 * See UAX #31 Unicode Identifier and Pattern Syntax. 0624 * http://www.unicode.org/reports/tr31/#Table_Candidate_Characters_for_Exclusion_from_Identifiers 0625 * 0626 * @stable ICU 51 0627 */ 0628 typedef enum UScriptUsage { 0629 /** Not encoded in Unicode. @stable ICU 51 */ 0630 USCRIPT_USAGE_NOT_ENCODED, 0631 /** Unknown script usage. @stable ICU 51 */ 0632 USCRIPT_USAGE_UNKNOWN, 0633 /** Candidate for Exclusion from Identifiers. @stable ICU 51 */ 0634 USCRIPT_USAGE_EXCLUDED, 0635 /** Limited Use script. @stable ICU 51 */ 0636 USCRIPT_USAGE_LIMITED_USE, 0637 /** Aspirational Use script. @stable ICU 51 */ 0638 USCRIPT_USAGE_ASPIRATIONAL, 0639 /** Recommended script. @stable ICU 51 */ 0640 USCRIPT_USAGE_RECOMMENDED 0641 } UScriptUsage; 0642 0643 /** 0644 * Writes the script sample character string. 0645 * This string normally consists of one code point but might be longer. 0646 * The string is empty if the script is not encoded. 0647 * 0648 * @param script script code 0649 * @param dest output string array 0650 * @param capacity number of UChars in the dest array 0651 * @param pErrorCode standard ICU in/out error code, must pass U_SUCCESS() on input 0652 * @return the string length, even if U_BUFFER_OVERFLOW_ERROR 0653 * @stable ICU 51 0654 */ 0655 U_CAPI int32_t U_EXPORT2 0656 uscript_getSampleString(UScriptCode script, UChar *dest, int32_t capacity, UErrorCode *pErrorCode); 0657 0658 #if U_SHOW_CPLUSPLUS_API 0659 0660 U_NAMESPACE_BEGIN 0661 class UnicodeString; 0662 U_NAMESPACE_END 0663 0664 /** 0665 * Returns the script sample character string. 0666 * This string normally consists of one code point but might be longer. 0667 * The string is empty if the script is not encoded. 0668 * 0669 * @param script script code 0670 * @return the sample character string 0671 * @stable ICU 51 0672 */ 0673 U_COMMON_API icu::UnicodeString U_EXPORT2 0674 uscript_getSampleUnicodeString(UScriptCode script); 0675 0676 #endif 0677 0678 /** 0679 * Returns the script usage according to UAX #31 Unicode Identifier and Pattern Syntax. 0680 * Returns USCRIPT_USAGE_NOT_ENCODED if the script is not encoded in Unicode. 0681 * 0682 * @param script script code 0683 * @return script usage 0684 * @see UScriptUsage 0685 * @stable ICU 51 0686 */ 0687 U_CAPI UScriptUsage U_EXPORT2 0688 uscript_getUsage(UScriptCode script); 0689 0690 /** 0691 * Returns true if the script is written right-to-left. 0692 * For example, Arab and Hebr. 0693 * 0694 * @param script script code 0695 * @return true if the script is right-to-left 0696 * @stable ICU 51 0697 */ 0698 U_CAPI UBool U_EXPORT2 0699 uscript_isRightToLeft(UScriptCode script); 0700 0701 /** 0702 * Returns true if the script allows line breaks between letters (excluding hyphenation). 0703 * Such a script typically requires dictionary-based line breaking. 0704 * For example, Hani and Thai. 0705 * 0706 * @param script script code 0707 * @return true if the script allows line breaks between letters 0708 * @stable ICU 51 0709 */ 0710 U_CAPI UBool U_EXPORT2 0711 uscript_breaksBetweenLetters(UScriptCode script); 0712 0713 /** 0714 * Returns true if in modern (or most recent) usage of the script case distinctions are customary. 0715 * For example, Latn and Cyrl. 0716 * 0717 * @param script script code 0718 * @return true if the script is cased 0719 * @stable ICU 51 0720 */ 0721 U_CAPI UBool U_EXPORT2 0722 uscript_isCased(UScriptCode script); 0723 0724 #endif
[ Source navigation ] | [ Diff markup ] | [ Identifier search ] | [ general search ] |
This page was automatically generated by the 2.3.7 LXR engine. The LXR team |