1.1 --- /dev/null Thu Jan 01 00:00:00 1970 +0000
1.2 +++ b/intl/icu/source/common/unicode/uscript.h Wed Dec 31 06:09:35 2014 +0100
1.3 @@ -0,0 +1,627 @@
1.4 +/*
1.5 + **********************************************************************
1.6 + * Copyright (C) 1997-2013, International Business Machines
1.7 + * Corporation and others. All Rights Reserved.
1.8 + **********************************************************************
1.9 + *
1.10 + * File USCRIPT.H
1.11 + *
1.12 + * Modification History:
1.13 + *
1.14 + * Date Name Description
1.15 + * 07/06/2001 Ram Creation.
1.16 + ******************************************************************************
1.17 + */
1.18 +
1.19 +#ifndef USCRIPT_H
1.20 +#define USCRIPT_H
1.21 +#include "unicode/utypes.h"
1.22 +
1.23 +/**
1.24 + * \file
1.25 + * \brief C API: Unicode Script Information
1.26 + */
1.27 +
1.28 +/**
1.29 + * Constants for ISO 15924 script codes.
1.30 + *
1.31 + * Many of these script codes - those from Unicode's ScriptNames.txt -
1.32 + * are character property values for Unicode's Script property.
1.33 + * See UAX #24 Script Names (http://www.unicode.org/reports/tr24/).
1.34 + *
1.35 + * Starting with ICU 3.6, constants for most ISO 15924 script codes
1.36 + * are included (currently excluding private-use codes Qaaa..Qabx).
1.37 + * For scripts for which there are codes in ISO 15924 but which are not
1.38 + * used in the Unicode Character Database (UCD), there are no Unicode characters
1.39 + * associated with those scripts.
1.40 + *
1.41 + * For example, there are no characters that have a UCD script code of
1.42 + * Hans or Hant. All Han ideographs have the Hani script code.
1.43 + * The Hans and Hant script codes are used with CLDR data.
1.44 + *
1.45 + * ISO 15924 script codes are included for use with CLDR and similar.
1.46 + *
1.47 + * @stable ICU 2.2
1.48 + */
1.49 +typedef enum UScriptCode {
1.50 + /*
1.51 + * Note: UScriptCode constants and their ISO script code comments
1.52 + * are parsed by preparseucd.py.
1.53 + * It matches lines like
1.54 + * USCRIPT_<Unicode Script value name> = <integer>, / * <ISO script code> * /
1.55 + */
1.56 +
1.57 + /** @stable ICU 2.2 */
1.58 + USCRIPT_INVALID_CODE = -1,
1.59 + /** @stable ICU 2.2 */
1.60 + USCRIPT_COMMON = 0, /* Zyyy */
1.61 + /** @stable ICU 2.2 */
1.62 + USCRIPT_INHERITED = 1, /* Zinh */ /* "Code for inherited script", for non-spacing combining marks; also Qaai */
1.63 + /** @stable ICU 2.2 */
1.64 + USCRIPT_ARABIC = 2, /* Arab */
1.65 + /** @stable ICU 2.2 */
1.66 + USCRIPT_ARMENIAN = 3, /* Armn */
1.67 + /** @stable ICU 2.2 */
1.68 + USCRIPT_BENGALI = 4, /* Beng */
1.69 + /** @stable ICU 2.2 */
1.70 + USCRIPT_BOPOMOFO = 5, /* Bopo */
1.71 + /** @stable ICU 2.2 */
1.72 + USCRIPT_CHEROKEE = 6, /* Cher */
1.73 + /** @stable ICU 2.2 */
1.74 + USCRIPT_COPTIC = 7, /* Copt */
1.75 + /** @stable ICU 2.2 */
1.76 + USCRIPT_CYRILLIC = 8, /* Cyrl */
1.77 + /** @stable ICU 2.2 */
1.78 + USCRIPT_DESERET = 9, /* Dsrt */
1.79 + /** @stable ICU 2.2 */
1.80 + USCRIPT_DEVANAGARI = 10, /* Deva */
1.81 + /** @stable ICU 2.2 */
1.82 + USCRIPT_ETHIOPIC = 11, /* Ethi */
1.83 + /** @stable ICU 2.2 */
1.84 + USCRIPT_GEORGIAN = 12, /* Geor */
1.85 + /** @stable ICU 2.2 */
1.86 + USCRIPT_GOTHIC = 13, /* Goth */
1.87 + /** @stable ICU 2.2 */
1.88 + USCRIPT_GREEK = 14, /* Grek */
1.89 + /** @stable ICU 2.2 */
1.90 + USCRIPT_GUJARATI = 15, /* Gujr */
1.91 + /** @stable ICU 2.2 */
1.92 + USCRIPT_GURMUKHI = 16, /* Guru */
1.93 + /** @stable ICU 2.2 */
1.94 + USCRIPT_HAN = 17, /* Hani */
1.95 + /** @stable ICU 2.2 */
1.96 + USCRIPT_HANGUL = 18, /* Hang */
1.97 + /** @stable ICU 2.2 */
1.98 + USCRIPT_HEBREW = 19, /* Hebr */
1.99 + /** @stable ICU 2.2 */
1.100 + USCRIPT_HIRAGANA = 20, /* Hira */
1.101 + /** @stable ICU 2.2 */
1.102 + USCRIPT_KANNADA = 21, /* Knda */
1.103 + /** @stable ICU 2.2 */
1.104 + USCRIPT_KATAKANA = 22, /* Kana */
1.105 + /** @stable ICU 2.2 */
1.106 + USCRIPT_KHMER = 23, /* Khmr */
1.107 + /** @stable ICU 2.2 */
1.108 + USCRIPT_LAO = 24, /* Laoo */
1.109 + /** @stable ICU 2.2 */
1.110 + USCRIPT_LATIN = 25, /* Latn */
1.111 + /** @stable ICU 2.2 */
1.112 + USCRIPT_MALAYALAM = 26, /* Mlym */
1.113 + /** @stable ICU 2.2 */
1.114 + USCRIPT_MONGOLIAN = 27, /* Mong */
1.115 + /** @stable ICU 2.2 */
1.116 + USCRIPT_MYANMAR = 28, /* Mymr */
1.117 + /** @stable ICU 2.2 */
1.118 + USCRIPT_OGHAM = 29, /* Ogam */
1.119 + /** @stable ICU 2.2 */
1.120 + USCRIPT_OLD_ITALIC = 30, /* Ital */
1.121 + /** @stable ICU 2.2 */
1.122 + USCRIPT_ORIYA = 31, /* Orya */
1.123 + /** @stable ICU 2.2 */
1.124 + USCRIPT_RUNIC = 32, /* Runr */
1.125 + /** @stable ICU 2.2 */
1.126 + USCRIPT_SINHALA = 33, /* Sinh */
1.127 + /** @stable ICU 2.2 */
1.128 + USCRIPT_SYRIAC = 34, /* Syrc */
1.129 + /** @stable ICU 2.2 */
1.130 + USCRIPT_TAMIL = 35, /* Taml */
1.131 + /** @stable ICU 2.2 */
1.132 + USCRIPT_TELUGU = 36, /* Telu */
1.133 + /** @stable ICU 2.2 */
1.134 + USCRIPT_THAANA = 37, /* Thaa */
1.135 + /** @stable ICU 2.2 */
1.136 + USCRIPT_THAI = 38, /* Thai */
1.137 + /** @stable ICU 2.2 */
1.138 + USCRIPT_TIBETAN = 39, /* Tibt */
1.139 + /** Canadian_Aboriginal script. @stable ICU 2.6 */
1.140 + USCRIPT_CANADIAN_ABORIGINAL = 40, /* Cans */
1.141 + /** Canadian_Aboriginal script (alias). @stable ICU 2.2 */
1.142 + USCRIPT_UCAS = USCRIPT_CANADIAN_ABORIGINAL,
1.143 + /** @stable ICU 2.2 */
1.144 + USCRIPT_YI = 41, /* Yiii */
1.145 + /* New scripts in Unicode 3.2 */
1.146 + /** @stable ICU 2.2 */
1.147 + USCRIPT_TAGALOG = 42, /* Tglg */
1.148 + /** @stable ICU 2.2 */
1.149 + USCRIPT_HANUNOO = 43, /* Hano */
1.150 + /** @stable ICU 2.2 */
1.151 + USCRIPT_BUHID = 44, /* Buhd */
1.152 + /** @stable ICU 2.2 */
1.153 + USCRIPT_TAGBANWA = 45, /* Tagb */
1.154 +
1.155 + /* New scripts in Unicode 4 */
1.156 + /** @stable ICU 2.6 */
1.157 + USCRIPT_BRAILLE = 46, /* Brai */
1.158 + /** @stable ICU 2.6 */
1.159 + USCRIPT_CYPRIOT = 47, /* Cprt */
1.160 + /** @stable ICU 2.6 */
1.161 + USCRIPT_LIMBU = 48, /* Limb */
1.162 + /** @stable ICU 2.6 */
1.163 + USCRIPT_LINEAR_B = 49, /* Linb */
1.164 + /** @stable ICU 2.6 */
1.165 + USCRIPT_OSMANYA = 50, /* Osma */
1.166 + /** @stable ICU 2.6 */
1.167 + USCRIPT_SHAVIAN = 51, /* Shaw */
1.168 + /** @stable ICU 2.6 */
1.169 + USCRIPT_TAI_LE = 52, /* Tale */
1.170 + /** @stable ICU 2.6 */
1.171 + USCRIPT_UGARITIC = 53, /* Ugar */
1.172 +
1.173 + /** New script code in Unicode 4.0.1 @stable ICU 3.0 */
1.174 + USCRIPT_KATAKANA_OR_HIRAGANA = 54,/*Hrkt */
1.175 +
1.176 + /* New scripts in Unicode 4.1 */
1.177 + /** @stable ICU 3.4 */
1.178 + USCRIPT_BUGINESE = 55, /* Bugi */
1.179 + /** @stable ICU 3.4 */
1.180 + USCRIPT_GLAGOLITIC = 56, /* Glag */
1.181 + /** @stable ICU 3.4 */
1.182 + USCRIPT_KHAROSHTHI = 57, /* Khar */
1.183 + /** @stable ICU 3.4 */
1.184 + USCRIPT_SYLOTI_NAGRI = 58, /* Sylo */
1.185 + /** @stable ICU 3.4 */
1.186 + USCRIPT_NEW_TAI_LUE = 59, /* Talu */
1.187 + /** @stable ICU 3.4 */
1.188 + USCRIPT_TIFINAGH = 60, /* Tfng */
1.189 + /** @stable ICU 3.4 */
1.190 + USCRIPT_OLD_PERSIAN = 61, /* Xpeo */
1.191 +
1.192 + /* New script codes from ISO 15924 */
1.193 + /** @stable ICU 3.6 */
1.194 + USCRIPT_BALINESE = 62, /* Bali */
1.195 + /** @stable ICU 3.6 */
1.196 + USCRIPT_BATAK = 63, /* Batk */
1.197 + /** @stable ICU 3.6 */
1.198 + USCRIPT_BLISSYMBOLS = 64, /* Blis */
1.199 + /** @stable ICU 3.6 */
1.200 + USCRIPT_BRAHMI = 65, /* Brah */
1.201 + /** @stable ICU 3.6 */
1.202 + USCRIPT_CHAM = 66, /* Cham */
1.203 + /** @stable ICU 3.6 */
1.204 + USCRIPT_CIRTH = 67, /* Cirt */
1.205 + /** @stable ICU 3.6 */
1.206 + USCRIPT_OLD_CHURCH_SLAVONIC_CYRILLIC = 68, /* Cyrs */
1.207 + /** @stable ICU 3.6 */
1.208 + USCRIPT_DEMOTIC_EGYPTIAN = 69, /* Egyd */
1.209 + /** @stable ICU 3.6 */
1.210 + USCRIPT_HIERATIC_EGYPTIAN = 70, /* Egyh */
1.211 + /** @stable ICU 3.6 */
1.212 + USCRIPT_EGYPTIAN_HIEROGLYPHS = 71, /* Egyp */
1.213 + /** @stable ICU 3.6 */
1.214 + USCRIPT_KHUTSURI = 72, /* Geok */
1.215 + /** @stable ICU 3.6 */
1.216 + USCRIPT_SIMPLIFIED_HAN = 73, /* Hans */
1.217 + /** @stable ICU 3.6 */
1.218 + USCRIPT_TRADITIONAL_HAN = 74, /* Hant */
1.219 + /** @stable ICU 3.6 */
1.220 + USCRIPT_PAHAWH_HMONG = 75, /* Hmng */
1.221 + /** @stable ICU 3.6 */
1.222 + USCRIPT_OLD_HUNGARIAN = 76, /* Hung */
1.223 + /** @stable ICU 3.6 */
1.224 + USCRIPT_HARAPPAN_INDUS = 77, /* Inds */
1.225 + /** @stable ICU 3.6 */
1.226 + USCRIPT_JAVANESE = 78, /* Java */
1.227 + /** @stable ICU 3.6 */
1.228 + USCRIPT_KAYAH_LI = 79, /* Kali */
1.229 + /** @stable ICU 3.6 */
1.230 + USCRIPT_LATIN_FRAKTUR = 80, /* Latf */
1.231 + /** @stable ICU 3.6 */
1.232 + USCRIPT_LATIN_GAELIC = 81, /* Latg */
1.233 + /** @stable ICU 3.6 */
1.234 + USCRIPT_LEPCHA = 82, /* Lepc */
1.235 + /** @stable ICU 3.6 */
1.236 + USCRIPT_LINEAR_A = 83, /* Lina */
1.237 + /** @stable ICU 4.6 */
1.238 + USCRIPT_MANDAIC = 84, /* Mand */
1.239 + /** @stable ICU 3.6 */
1.240 + USCRIPT_MANDAEAN = USCRIPT_MANDAIC,
1.241 + /** @stable ICU 3.6 */
1.242 + USCRIPT_MAYAN_HIEROGLYPHS = 85, /* Maya */
1.243 + /** @stable ICU 4.6 */
1.244 + USCRIPT_MEROITIC_HIEROGLYPHS = 86, /* Mero */
1.245 + /** @stable ICU 3.6 */
1.246 + USCRIPT_MEROITIC = USCRIPT_MEROITIC_HIEROGLYPHS,
1.247 + /** @stable ICU 3.6 */
1.248 + USCRIPT_NKO = 87, /* Nkoo */
1.249 + /** @stable ICU 3.6 */
1.250 + USCRIPT_ORKHON = 88, /* Orkh */
1.251 + /** @stable ICU 3.6 */
1.252 + USCRIPT_OLD_PERMIC = 89, /* Perm */
1.253 + /** @stable ICU 3.6 */
1.254 + USCRIPT_PHAGS_PA = 90, /* Phag */
1.255 + /** @stable ICU 3.6 */
1.256 + USCRIPT_PHOENICIAN = 91, /* Phnx */
1.257 + /** @stable ICU 52 */
1.258 + USCRIPT_MIAO = 92, /* Plrd */
1.259 + /** @stable ICU 3.6 */
1.260 + USCRIPT_PHONETIC_POLLARD = USCRIPT_MIAO,
1.261 + /** @stable ICU 3.6 */
1.262 + USCRIPT_RONGORONGO = 93, /* Roro */
1.263 + /** @stable ICU 3.6 */
1.264 + USCRIPT_SARATI = 94, /* Sara */
1.265 + /** @stable ICU 3.6 */
1.266 + USCRIPT_ESTRANGELO_SYRIAC = 95, /* Syre */
1.267 + /** @stable ICU 3.6 */
1.268 + USCRIPT_WESTERN_SYRIAC = 96, /* Syrj */
1.269 + /** @stable ICU 3.6 */
1.270 + USCRIPT_EASTERN_SYRIAC = 97, /* Syrn */
1.271 + /** @stable ICU 3.6 */
1.272 + USCRIPT_TENGWAR = 98, /* Teng */
1.273 + /** @stable ICU 3.6 */
1.274 + USCRIPT_VAI = 99, /* Vaii */
1.275 + /** @stable ICU 3.6 */
1.276 + USCRIPT_VISIBLE_SPEECH = 100,/* Visp */
1.277 + /** @stable ICU 3.6 */
1.278 + USCRIPT_CUNEIFORM = 101,/* Xsux */
1.279 + /** @stable ICU 3.6 */
1.280 + USCRIPT_UNWRITTEN_LANGUAGES = 102,/* Zxxx */
1.281 + /** @stable ICU 3.6 */
1.282 + USCRIPT_UNKNOWN = 103,/* Zzzz */ /* Unknown="Code for uncoded script", for unassigned code points */
1.283 +
1.284 + /* New script codes from ISO 15924 */
1.285 + /** @stable ICU 3.8 */
1.286 + USCRIPT_CARIAN = 104,/* Cari */
1.287 + /** @stable ICU 3.8 */
1.288 + USCRIPT_JAPANESE = 105,/* Jpan */
1.289 + /** @stable ICU 3.8 */
1.290 + USCRIPT_LANNA = 106,/* Lana */
1.291 + /** @stable ICU 3.8 */
1.292 + USCRIPT_LYCIAN = 107,/* Lyci */
1.293 + /** @stable ICU 3.8 */
1.294 + USCRIPT_LYDIAN = 108,/* Lydi */
1.295 + /** @stable ICU 3.8 */
1.296 + USCRIPT_OL_CHIKI = 109,/* Olck */
1.297 + /** @stable ICU 3.8 */
1.298 + USCRIPT_REJANG = 110,/* Rjng */
1.299 + /** @stable ICU 3.8 */
1.300 + USCRIPT_SAURASHTRA = 111,/* Saur */
1.301 + /** @stable ICU 3.8 */
1.302 + USCRIPT_SIGN_WRITING = 112,/* Sgnw */
1.303 + /** @stable ICU 3.8 */
1.304 + USCRIPT_SUNDANESE = 113,/* Sund */
1.305 + /** @stable ICU 3.8 */
1.306 + USCRIPT_MOON = 114,/* Moon */
1.307 + /** @stable ICU 3.8 */
1.308 + USCRIPT_MEITEI_MAYEK = 115,/* Mtei */
1.309 +
1.310 + /* New script codes from ISO 15924 */
1.311 + /** @stable ICU 4.0 */
1.312 + USCRIPT_IMPERIAL_ARAMAIC = 116,/* Armi */
1.313 + /** @stable ICU 4.0 */
1.314 + USCRIPT_AVESTAN = 117,/* Avst */
1.315 + /** @stable ICU 4.0 */
1.316 + USCRIPT_CHAKMA = 118,/* Cakm */
1.317 + /** @stable ICU 4.0 */
1.318 + USCRIPT_KOREAN = 119,/* Kore */
1.319 + /** @stable ICU 4.0 */
1.320 + USCRIPT_KAITHI = 120,/* Kthi */
1.321 + /** @stable ICU 4.0 */
1.322 + USCRIPT_MANICHAEAN = 121,/* Mani */
1.323 + /** @stable ICU 4.0 */
1.324 + USCRIPT_INSCRIPTIONAL_PAHLAVI = 122,/* Phli */
1.325 + /** @stable ICU 4.0 */
1.326 + USCRIPT_PSALTER_PAHLAVI = 123,/* Phlp */
1.327 + /** @stable ICU 4.0 */
1.328 + USCRIPT_BOOK_PAHLAVI = 124,/* Phlv */
1.329 + /** @stable ICU 4.0 */
1.330 + USCRIPT_INSCRIPTIONAL_PARTHIAN = 125,/* Prti */
1.331 + /** @stable ICU 4.0 */
1.332 + USCRIPT_SAMARITAN = 126,/* Samr */
1.333 + /** @stable ICU 4.0 */
1.334 + USCRIPT_TAI_VIET = 127,/* Tavt */
1.335 + /** @stable ICU 4.0 */
1.336 + USCRIPT_MATHEMATICAL_NOTATION = 128,/* Zmth */
1.337 + /** @stable ICU 4.0 */
1.338 + USCRIPT_SYMBOLS = 129,/* Zsym */
1.339 +
1.340 + /* New script codes from ISO 15924 */
1.341 + /** @stable ICU 4.4 */
1.342 + USCRIPT_BAMUM = 130,/* Bamu */
1.343 + /** @stable ICU 4.4 */
1.344 + USCRIPT_LISU = 131,/* Lisu */
1.345 + /** @stable ICU 4.4 */
1.346 + USCRIPT_NAKHI_GEBA = 132,/* Nkgb */
1.347 + /** @stable ICU 4.4 */
1.348 + USCRIPT_OLD_SOUTH_ARABIAN = 133,/* Sarb */
1.349 +
1.350 + /* New script codes from ISO 15924 */
1.351 + /** @stable ICU 4.6 */
1.352 + USCRIPT_BASSA_VAH = 134,/* Bass */
1.353 + /** @stable ICU 4.6 */
1.354 + USCRIPT_DUPLOYAN_SHORTAND = 135,/* Dupl */
1.355 + /** @stable ICU 4.6 */
1.356 + USCRIPT_ELBASAN = 136,/* Elba */
1.357 + /** @stable ICU 4.6 */
1.358 + USCRIPT_GRANTHA = 137,/* Gran */
1.359 + /** @stable ICU 4.6 */
1.360 + USCRIPT_KPELLE = 138,/* Kpel */
1.361 + /** @stable ICU 4.6 */
1.362 + USCRIPT_LOMA = 139,/* Loma */
1.363 + /** @stable ICU 4.6 */
1.364 + USCRIPT_MENDE = 140,/* Mend */
1.365 + /** @stable ICU 4.6 */
1.366 + USCRIPT_MEROITIC_CURSIVE = 141,/* Merc */
1.367 + /** @stable ICU 4.6 */
1.368 + USCRIPT_OLD_NORTH_ARABIAN = 142,/* Narb */
1.369 + /** @stable ICU 4.6 */
1.370 + USCRIPT_NABATAEAN = 143,/* Nbat */
1.371 + /** @stable ICU 4.6 */
1.372 + USCRIPT_PALMYRENE = 144,/* Palm */
1.373 + /** @stable ICU 4.6 */
1.374 + USCRIPT_SINDHI = 145,/* Sind */
1.375 + /** @stable ICU 4.6 */
1.376 + USCRIPT_WARANG_CITI = 146,/* Wara */
1.377 +
1.378 + /** @stable ICU 4.8 */
1.379 + USCRIPT_AFAKA = 147,/* Afak */
1.380 + /** @stable ICU 4.8 */
1.381 + USCRIPT_JURCHEN = 148,/* Jurc */
1.382 + /** @stable ICU 4.8 */
1.383 + USCRIPT_MRO = 149,/* Mroo */
1.384 + /** @stable ICU 4.8 */
1.385 + USCRIPT_NUSHU = 150,/* Nshu */
1.386 + /** @stable ICU 4.8 */
1.387 + USCRIPT_SHARADA = 151,/* Shrd */
1.388 + /** @stable ICU 4.8 */
1.389 + USCRIPT_SORA_SOMPENG = 152,/* Sora */
1.390 + /** @stable ICU 4.8 */
1.391 + USCRIPT_TAKRI = 153,/* Takr */
1.392 + /** @stable ICU 4.8 */
1.393 + USCRIPT_TANGUT = 154,/* Tang */
1.394 + /** @stable ICU 4.8 */
1.395 + USCRIPT_WOLEAI = 155,/* Wole */
1.396 +
1.397 + /** @stable ICU 49 */
1.398 + USCRIPT_ANATOLIAN_HIEROGLYPHS = 156,/* Hluw */
1.399 + /** @stable ICU 49 */
1.400 + USCRIPT_KHOJKI = 157,/* Khoj */
1.401 + /** @stable ICU 49 */
1.402 + USCRIPT_TIRHUTA = 158,/* Tirh */
1.403 +
1.404 + /** @stable ICU 52 */
1.405 + USCRIPT_CAUCASIAN_ALBANIAN = 159,/* Aghb */
1.406 + /** @stable ICU 52 */
1.407 + USCRIPT_MAHAJANI = 160,/* Mahj */
1.408 +
1.409 + /* Private use codes from Qaaa - Qabx are not supported */
1.410 +
1.411 + /** @stable ICU 2.2 */
1.412 + USCRIPT_CODE_LIMIT = 161
1.413 +} UScriptCode;
1.414 +
1.415 +/**
1.416 + * Gets script codes associated with the given locale or ISO 15924 abbreviation or name.
1.417 + * Fills in USCRIPT_MALAYALAM given "Malayam" OR "Mlym".
1.418 + * Fills in USCRIPT_LATIN given "en" OR "en_US"
1.419 + * If required capacity is greater than capacity of the destination buffer then the error code
1.420 + * is set to U_BUFFER_OVERFLOW_ERROR and the required capacity is returned
1.421 + *
1.422 + * <p>Note: To search by short or long script alias only, use
1.423 + * u_getPropertyValueEnum(UCHAR_SCRIPT, alias) instead. This does
1.424 + * a fast lookup with no access of the locale data.
1.425 + * @param nameOrAbbrOrLocale name of the script, as given in
1.426 + * PropertyValueAliases.txt, or ISO 15924 code or locale
1.427 + * @param fillIn the UScriptCode buffer to fill in the script code
1.428 + * @param capacity the capacity (size) fo UScriptCode buffer passed in.
1.429 + * @param err the error status code.
1.430 + * @return The number of script codes filled in the buffer passed in
1.431 + * @stable ICU 2.4
1.432 + */
1.433 +U_STABLE int32_t U_EXPORT2
1.434 +uscript_getCode(const char* nameOrAbbrOrLocale,UScriptCode* fillIn,int32_t capacity,UErrorCode *err);
1.435 +
1.436 +/**
1.437 + * Gets a script name associated with the given script code.
1.438 + * Returns "Malayam" given USCRIPT_MALAYALAM
1.439 + * @param scriptCode UScriptCode enum
1.440 + * @return script long name as given in
1.441 + * PropertyValueAliases.txt, or NULL if scriptCode is invalid
1.442 + * @stable ICU 2.4
1.443 + */
1.444 +U_STABLE const char* U_EXPORT2
1.445 +uscript_getName(UScriptCode scriptCode);
1.446 +
1.447 +/**
1.448 + * Gets a script name associated with the given script code.
1.449 + * Returns "Mlym" given USCRIPT_MALAYALAM
1.450 + * @param scriptCode UScriptCode enum
1.451 + * @return script abbreviated name as given in
1.452 + * PropertyValueAliases.txt, or NULL if scriptCode is invalid
1.453 + * @stable ICU 2.4
1.454 + */
1.455 +U_STABLE const char* U_EXPORT2
1.456 +uscript_getShortName(UScriptCode scriptCode);
1.457 +
1.458 +/**
1.459 + * Gets the script code associated with the given codepoint.
1.460 + * Returns USCRIPT_MALAYALAM given 0x0D02
1.461 + * @param codepoint UChar32 codepoint
1.462 + * @param err the error status code.
1.463 + * @return The UScriptCode, or 0 if codepoint is invalid
1.464 + * @stable ICU 2.4
1.465 + */
1.466 +U_STABLE UScriptCode U_EXPORT2
1.467 +uscript_getScript(UChar32 codepoint, UErrorCode *err);
1.468 +
1.469 +/**
1.470 + * Do the Script_Extensions of code point c contain script sc?
1.471 + * If c does not have explicit Script_Extensions, then this tests whether
1.472 + * c has the Script property value sc.
1.473 + *
1.474 + * Some characters are commonly used in multiple scripts.
1.475 + * For more information, see UAX #24: http://www.unicode.org/reports/tr24/.
1.476 + *
1.477 + * The Script_Extensions property is provisional. It may be modified or removed
1.478 + * in future versions of the Unicode Standard, and thus in ICU.
1.479 + * @param c code point
1.480 + * @param sc script code
1.481 + * @return TRUE if sc is in Script_Extensions(c)
1.482 + * @stable ICU 49
1.483 + */
1.484 +U_STABLE UBool U_EXPORT2
1.485 +uscript_hasScript(UChar32 c, UScriptCode sc);
1.486 +
1.487 +/**
1.488 + * Writes code point c's Script_Extensions as a list of UScriptCode values
1.489 + * to the output scripts array and returns the number of script codes.
1.490 + * - If c does have Script_Extensions, then the Script property value
1.491 + * (normally Common or Inherited) is not included.
1.492 + * - If c does not have Script_Extensions, then the one Script code is written to the output array.
1.493 + * - If c is not a valid code point, then the one USCRIPT_UNKNOWN code is written.
1.494 + * In other words, if the return value is 1,
1.495 + * then the output array contains exactly c's single Script code.
1.496 + * If the return value is n>=2, then the output array contains c's n Script_Extensions script codes.
1.497 + *
1.498 + * Some characters are commonly used in multiple scripts.
1.499 + * For more information, see UAX #24: http://www.unicode.org/reports/tr24/.
1.500 + *
1.501 + * If there are more than capacity script codes to be written, then
1.502 + * U_BUFFER_OVERFLOW_ERROR is set and the number of Script_Extensions is returned.
1.503 + * (Usual ICU buffer handling behavior.)
1.504 + *
1.505 + * The Script_Extensions property is provisional. It may be modified or removed
1.506 + * in future versions of the Unicode Standard, and thus in ICU.
1.507 + * @param c code point
1.508 + * @param scripts output script code array
1.509 + * @param capacity capacity of the scripts array
1.510 + * @param errorCode Standard ICU error code. Its input value must
1.511 + * pass the U_SUCCESS() test, or else the function returns
1.512 + * immediately. Check for U_FAILURE() on output or use with
1.513 + * function chaining. (See User Guide for details.)
1.514 + * @return number of script codes in c's Script_Extensions, or 1 for the single Script value,
1.515 + * written to scripts unless U_BUFFER_OVERFLOW_ERROR indicates insufficient capacity
1.516 + * @stable ICU 49
1.517 + */
1.518 +U_STABLE int32_t U_EXPORT2
1.519 +uscript_getScriptExtensions(UChar32 c,
1.520 + UScriptCode *scripts, int32_t capacity,
1.521 + UErrorCode *errorCode);
1.522 +
1.523 +#ifndef U_HIDE_DRAFT_API
1.524 +
1.525 +/**
1.526 + * Script usage constants.
1.527 + * See UAX #31 Unicode Identifier and Pattern Syntax.
1.528 + * http://www.unicode.org/reports/tr31/#Table_Candidate_Characters_for_Exclusion_from_Identifiers
1.529 + *
1.530 + * @draft ICU 51
1.531 + */
1.532 +typedef enum UScriptUsage {
1.533 + /** Not encoded in Unicode. @draft ICU 51 */
1.534 + USCRIPT_USAGE_NOT_ENCODED,
1.535 + /** Unknown script usage. @draft ICU 51 */
1.536 + USCRIPT_USAGE_UNKNOWN,
1.537 + /** Candidate for Exclusion from Identifiers. @draft ICU 51 */
1.538 + USCRIPT_USAGE_EXCLUDED,
1.539 + /** Limited Use script. @draft ICU 51 */
1.540 + USCRIPT_USAGE_LIMITED_USE,
1.541 + /** Aspirational Use script. @draft ICU 51 */
1.542 + USCRIPT_USAGE_ASPIRATIONAL,
1.543 + /** Recommended script. @draft ICU 51 */
1.544 + USCRIPT_USAGE_RECOMMENDED
1.545 +} UScriptUsage;
1.546 +
1.547 +/**
1.548 + * Writes the script sample character string.
1.549 + * This string normally consists of one code point but might be longer.
1.550 + * The string is empty if the script is not encoded.
1.551 + *
1.552 + * @param script script code
1.553 + * @param dest output string array
1.554 + * @param capacity number of UChars in the dest array
1.555 + * @param pErrorCode standard ICU in/out error code, must pass U_SUCCESS() on input
1.556 + * @return the string length, even if U_BUFFER_OVERFLOW_ERROR
1.557 + * @draft ICU 51
1.558 + */
1.559 +U_DRAFT int32_t U_EXPORT2
1.560 +uscript_getSampleString(UScriptCode script, UChar *dest, int32_t capacity, UErrorCode *pErrorCode);
1.561 +
1.562 +#if U_SHOW_CPLUSPLUS_API
1.563 +
1.564 +U_NAMESPACE_BEGIN
1.565 +class UnicodeString;
1.566 +U_NAMESPACE_END
1.567 +
1.568 +/**
1.569 + * Returns the script sample character string.
1.570 + * This string normally consists of one code point but might be longer.
1.571 + * The string is empty if the script is not encoded.
1.572 + *
1.573 + * @param script script code
1.574 + * @return the sample character string
1.575 + * @draft ICU 51
1.576 + */
1.577 +U_COMMON_API icu::UnicodeString U_EXPORT2
1.578 +uscript_getSampleUnicodeString(UScriptCode script);
1.579 +
1.580 +#endif
1.581 +
1.582 +/**
1.583 + * Returns the script usage according to UAX #31 Unicode Identifier and Pattern Syntax.
1.584 + * Returns USCRIPT_USAGE_NOT_ENCODED if the script is not encoded in Unicode.
1.585 + *
1.586 + * @param script script code
1.587 + * @return script usage
1.588 + * @see UScriptUsage
1.589 + * @draft ICU 51
1.590 + */
1.591 +U_DRAFT UScriptUsage U_EXPORT2
1.592 +uscript_getUsage(UScriptCode script);
1.593 +
1.594 +/**
1.595 + * Returns TRUE if the script is written right-to-left.
1.596 + * For example, Arab and Hebr.
1.597 + *
1.598 + * @param script script code
1.599 + * @return TRUE if the script is right-to-left
1.600 + * @draft ICU 51
1.601 + */
1.602 +U_DRAFT UBool U_EXPORT2
1.603 +uscript_isRightToLeft(UScriptCode script);
1.604 +
1.605 +/**
1.606 + * Returns TRUE if the script allows line breaks between letters (excluding hyphenation).
1.607 + * Such a script typically requires dictionary-based line breaking.
1.608 + * For example, Hani and Thai.
1.609 + *
1.610 + * @param script script code
1.611 + * @return TRUE if the script allows line breaks between letters
1.612 + * @draft ICU 51
1.613 + */
1.614 +U_DRAFT UBool U_EXPORT2
1.615 +uscript_breaksBetweenLetters(UScriptCode script);
1.616 +
1.617 +/**
1.618 + * Returns TRUE if in modern (or most recent) usage of the script case distinctions are customary.
1.619 + * For example, Latn and Cyrl.
1.620 + *
1.621 + * @param script script code
1.622 + * @return TRUE if the script is cased
1.623 + * @draft ICU 51
1.624 + */
1.625 +U_DRAFT UBool U_EXPORT2
1.626 +uscript_isCased(UScriptCode script);
1.627 +
1.628 +#endif /* U_HIDE_DRAFT_API */
1.629 +
1.630 +#endif
