1 /* 2 ********************************************************************** 3 * Copyright (C) 1997-2010, 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 USCRIPT_INVALID_CODE = -1, 48 USCRIPT_COMMON = 0, /* Zyyy */ 49 USCRIPT_INHERITED = 1, /* Zinh */ /* "Code for inherited script", for non-spacing combining marks; also Qaai */ 50 USCRIPT_ARABIC = 2, /* Arab */ 51 USCRIPT_ARMENIAN = 3, /* Armn */ 52 USCRIPT_BENGALI = 4, /* Beng */ 53 USCRIPT_BOPOMOFO = 5, /* Bopo */ 54 USCRIPT_CHEROKEE = 6, /* Cher */ 55 USCRIPT_COPTIC = 7, /* Copt */ 56 USCRIPT_CYRILLIC = 8, /* Cyrl */ 57 USCRIPT_DESERET = 9, /* Dsrt */ 58 USCRIPT_DEVANAGARI = 10, /* Deva */ 59 USCRIPT_ETHIOPIC = 11, /* Ethi */ 60 USCRIPT_GEORGIAN = 12, /* Geor */ 61 USCRIPT_GOTHIC = 13, /* Goth */ 62 USCRIPT_GREEK = 14, /* Grek */ 63 USCRIPT_GUJARATI = 15, /* Gujr */ 64 USCRIPT_GURMUKHI = 16, /* Guru */ 65 USCRIPT_HAN = 17, /* Hani */ 66 USCRIPT_HANGUL = 18, /* Hang */ 67 USCRIPT_HEBREW = 19, /* Hebr */ 68 USCRIPT_HIRAGANA = 20, /* Hira */ 69 USCRIPT_KANNADA = 21, /* Knda */ 70 USCRIPT_KATAKANA = 22, /* Kana */ 71 USCRIPT_KHMER = 23, /* Khmr */ 72 USCRIPT_LAO = 24, /* Laoo */ 73 USCRIPT_LATIN = 25, /* Latn */ 74 USCRIPT_MALAYALAM = 26, /* Mlym */ 75 USCRIPT_MONGOLIAN = 27, /* Mong */ 76 USCRIPT_MYANMAR = 28, /* Mymr */ 77 USCRIPT_OGHAM = 29, /* Ogam */ 78 USCRIPT_OLD_ITALIC = 30, /* Ital */ 79 USCRIPT_ORIYA = 31, /* Orya */ 80 USCRIPT_RUNIC = 32, /* Runr */ 81 USCRIPT_SINHALA = 33, /* Sinh */ 82 USCRIPT_SYRIAC = 34, /* Syrc */ 83 USCRIPT_TAMIL = 35, /* Taml */ 84 USCRIPT_TELUGU = 36, /* Telu */ 85 USCRIPT_THAANA = 37, /* Thaa */ 86 USCRIPT_THAI = 38, /* Thai */ 87 USCRIPT_TIBETAN = 39, /* Tibt */ 88 /** Canadian_Aboriginal script. @stable ICU 2.6 */ 89 USCRIPT_CANADIAN_ABORIGINAL = 40, /* Cans */ 90 /** Canadian_Aboriginal script (alias). @stable ICU 2.2 */ 91 USCRIPT_UCAS = USCRIPT_CANADIAN_ABORIGINAL, 92 USCRIPT_YI = 41, /* Yiii */ 93 USCRIPT_TAGALOG = 42, /* Tglg */ 94 USCRIPT_HANUNOO = 43, /* Hano */ 95 USCRIPT_BUHID = 44, /* Buhd */ 96 USCRIPT_TAGBANWA = 45, /* Tagb */ 97 98 /* New scripts in Unicode 4 @stable ICU 2.6 */ 99 USCRIPT_BRAILLE = 46, /* Brai */ 100 USCRIPT_CYPRIOT = 47, /* Cprt */ 101 USCRIPT_LIMBU = 48, /* Limb */ 102 USCRIPT_LINEAR_B = 49, /* Linb */ 103 USCRIPT_OSMANYA = 50, /* Osma */ 104 USCRIPT_SHAVIAN = 51, /* Shaw */ 105 USCRIPT_TAI_LE = 52, /* Tale */ 106 USCRIPT_UGARITIC = 53, /* Ugar */ 107 108 /** New script code in Unicode 4.0.1 @stable ICU 3.0 */ 109 USCRIPT_KATAKANA_OR_HIRAGANA = 54,/*Hrkt */ 110 111 /* New scripts in Unicode 4.1 @stable ICU 3.4 */ 112 USCRIPT_BUGINESE = 55, /* Bugi */ 113 USCRIPT_GLAGOLITIC = 56, /* Glag */ 114 USCRIPT_KHAROSHTHI = 57, /* Khar */ 115 USCRIPT_SYLOTI_NAGRI = 58, /* Sylo */ 116 USCRIPT_NEW_TAI_LUE = 59, /* Talu */ 117 USCRIPT_TIFINAGH = 60, /* Tfng */ 118 USCRIPT_OLD_PERSIAN = 61, /* Xpeo */ 119 120 /* New script codes from ISO 15924 @stable ICU 3.6 */ 121 USCRIPT_BALINESE = 62, /* Bali */ 122 USCRIPT_BATAK = 63, /* Batk */ 123 USCRIPT_BLISSYMBOLS = 64, /* Blis */ 124 USCRIPT_BRAHMI = 65, /* Brah */ 125 USCRIPT_CHAM = 66, /* Cham */ 126 USCRIPT_CIRTH = 67, /* Cirt */ 127 USCRIPT_OLD_CHURCH_SLAVONIC_CYRILLIC = 68, /* Cyrs */ 128 USCRIPT_DEMOTIC_EGYPTIAN = 69, /* Egyd */ 129 USCRIPT_HIERATIC_EGYPTIAN = 70, /* Egyh */ 130 USCRIPT_EGYPTIAN_HIEROGLYPHS = 71, /* Egyp */ 131 USCRIPT_KHUTSURI = 72, /* Geok */ 132 USCRIPT_SIMPLIFIED_HAN = 73, /* Hans */ 133 USCRIPT_TRADITIONAL_HAN = 74, /* Hant */ 134 USCRIPT_PAHAWH_HMONG = 75, /* Hmng */ 135 USCRIPT_OLD_HUNGARIAN = 76, /* Hung */ 136 USCRIPT_HARAPPAN_INDUS = 77, /* Inds */ 137 USCRIPT_JAVANESE = 78, /* Java */ 138 USCRIPT_KAYAH_LI = 79, /* Kali */ 139 USCRIPT_LATIN_FRAKTUR = 80, /* Latf */ 140 USCRIPT_LATIN_GAELIC = 81, /* Latg */ 141 USCRIPT_LEPCHA = 82, /* Lepc */ 142 USCRIPT_LINEAR_A = 83, /* Lina */ 143 /** @stable ICU 4.6 */ 144 USCRIPT_MANDAIC = 84, /* Mand */ 145 /** @stable ICU 3.6 */ 146 USCRIPT_MANDAEAN = USCRIPT_MANDAIC, 147 USCRIPT_MAYAN_HIEROGLYPHS = 85, /* Maya */ 148 /** @stable ICU 4.6 */ 149 USCRIPT_MEROITIC_HIEROGLYPHS = 86, /* Mero */ 150 /** @stable ICU 3.6 */ 151 USCRIPT_MEROITIC = USCRIPT_MEROITIC_HIEROGLYPHS, 152 USCRIPT_NKO = 87, /* Nkoo */ 153 USCRIPT_ORKHON = 88, /* Orkh */ 154 USCRIPT_OLD_PERMIC = 89, /* Perm */ 155 USCRIPT_PHAGS_PA = 90, /* Phag */ 156 USCRIPT_PHOENICIAN = 91, /* Phnx */ 157 USCRIPT_PHONETIC_POLLARD = 92, /* Plrd */ 158 USCRIPT_RONGORONGO = 93, /* Roro */ 159 USCRIPT_SARATI = 94, /* Sara */ 160 USCRIPT_ESTRANGELO_SYRIAC = 95, /* Syre */ 161 USCRIPT_WESTERN_SYRIAC = 96, /* Syrj */ 162 USCRIPT_EASTERN_SYRIAC = 97, /* Syrn */ 163 USCRIPT_TENGWAR = 98, /* Teng */ 164 USCRIPT_VAI = 99, /* Vaii */ 165 USCRIPT_VISIBLE_SPEECH = 100,/* Visp */ 166 USCRIPT_CUNEIFORM = 101,/* Xsux */ 167 USCRIPT_UNWRITTEN_LANGUAGES = 102,/* Zxxx */ 168 USCRIPT_UNKNOWN = 103,/* Zzzz */ /* Unknown="Code for uncoded script", for unassigned code points */ 169 170 /* New script codes from ISO 15924 @stable ICU 3.8 */ 171 USCRIPT_CARIAN = 104,/* Cari */ 172 USCRIPT_JAPANESE = 105,/* Jpan */ 173 USCRIPT_LANNA = 106,/* Lana */ 174 USCRIPT_LYCIAN = 107,/* Lyci */ 175 USCRIPT_LYDIAN = 108,/* Lydi */ 176 USCRIPT_OL_CHIKI = 109,/* Olck */ 177 USCRIPT_REJANG = 110,/* Rjng */ 178 USCRIPT_SAURASHTRA = 111,/* Saur */ 179 USCRIPT_SIGN_WRITING = 112,/* Sgnw */ 180 USCRIPT_SUNDANESE = 113,/* Sund */ 181 USCRIPT_MOON = 114,/* Moon */ 182 USCRIPT_MEITEI_MAYEK = 115,/* Mtei */ 183 184 /* New script codes from ISO 15924 @stable ICU 4.0 */ 185 USCRIPT_IMPERIAL_ARAMAIC = 116,/* Armi */ 186 USCRIPT_AVESTAN = 117,/* Avst */ 187 USCRIPT_CHAKMA = 118,/* Cakm */ 188 USCRIPT_KOREAN = 119,/* Kore */ 189 USCRIPT_KAITHI = 120,/* Kthi */ 190 USCRIPT_MANICHAEAN = 121,/* Mani */ 191 USCRIPT_INSCRIPTIONAL_PAHLAVI = 122,/* Phli */ 192 USCRIPT_PSALTER_PAHLAVI = 123,/* Phlp */ 193 USCRIPT_BOOK_PAHLAVI = 124,/* Phlv */ 194 USCRIPT_INSCRIPTIONAL_PARTHIAN = 125,/* Prti */ 195 USCRIPT_SAMARITAN = 126,/* Samr */ 196 USCRIPT_TAI_VIET = 127,/* Tavt */ 197 USCRIPT_MATHEMATICAL_NOTATION = 128,/* Zmth */ 198 USCRIPT_SYMBOLS = 129,/* Zsym */ 199 200 /* New script codes from ISO 15924 @stable ICU 4.4 */ 201 USCRIPT_BAMUM = 130,/* Bamu */ 202 USCRIPT_LISU = 131,/* Lisu */ 203 USCRIPT_NAKHI_GEBA = 132,/* Nkgb */ 204 USCRIPT_OLD_SOUTH_ARABIAN = 133,/* Sarb */ 205 206 /* New script codes from ISO 15924 @stable ICU 4.6 */ 207 USCRIPT_BASSA_VAH = 134,/* Bass */ 208 USCRIPT_DUPLOYAN_SHORTAND = 135,/* Dupl */ 209 USCRIPT_ELBASAN = 136,/* Elba */ 210 USCRIPT_GRANTHA = 137,/* Gran */ 211 USCRIPT_KPELLE = 138,/* Kpel */ 212 USCRIPT_LOMA = 139,/* Loma */ 213 USCRIPT_MENDE = 140,/* Mend */ 214 USCRIPT_MEROITIC_CURSIVE = 141,/* Merc */ 215 USCRIPT_OLD_NORTH_ARABIAN = 142,/* Narb */ 216 USCRIPT_NABATAEAN = 143,/* Nbat */ 217 USCRIPT_PALMYRENE = 144,/* Palm */ 218 USCRIPT_SINDHI = 145,/* Sind */ 219 USCRIPT_WARANG_CITI = 146,/* Wara */ 220 221 /* Private use codes from Qaaa - Qabx are not supported */ 222 USCRIPT_CODE_LIMIT = 147 223 } UScriptCode; 224 225 /** 226 * Gets script codes associated with the given locale or ISO 15924 abbreviation or name. 227 * Fills in USCRIPT_MALAYALAM given "Malayam" OR "Mlym". 228 * Fills in USCRIPT_LATIN given "en" OR "en_US" 229 * If required capacity is greater than capacity of the destination buffer then the error code 230 * is set to U_BUFFER_OVERFLOW_ERROR and the required capacity is returned 231 * 232 * <p>Note: To search by short or long script alias only, use 233 * u_getPropertyValueEnum(UCHAR_SCRIPT, alias) instead. This does 234 * a fast lookup with no access of the locale data. 235 * @param nameOrAbbrOrLocale name of the script, as given in 236 * PropertyValueAliases.txt, or ISO 15924 code or locale 237 * @param fillIn the UScriptCode buffer to fill in the script code 238 * @param capacity the capacity (size) fo UScriptCode buffer passed in. 239 * @param err the error status code. 240 * @return The number of script codes filled in the buffer passed in 241 * @stable ICU 2.4 242 */ 243 U_STABLE int32_t U_EXPORT2 244 uscript_getCode(const char* nameOrAbbrOrLocale,UScriptCode* fillIn,int32_t capacity,UErrorCode *err); 245 246 /** 247 * Gets a script name associated with the given script code. 248 * Returns "Malayam" given USCRIPT_MALAYALAM 249 * @param scriptCode UScriptCode enum 250 * @return script long name as given in 251 * PropertyValueAliases.txt, or NULL if scriptCode is invalid 252 * @stable ICU 2.4 253 */ 254 U_STABLE const char* U_EXPORT2 255 uscript_getName(UScriptCode scriptCode); 256 257 /** 258 * Gets a script name associated with the given script code. 259 * Returns "Mlym" given USCRIPT_MALAYALAM 260 * @param scriptCode UScriptCode enum 261 * @return script abbreviated name as given in 262 * PropertyValueAliases.txt, or NULL if scriptCode is invalid 263 * @stable ICU 2.4 264 */ 265 U_STABLE const char* U_EXPORT2 266 uscript_getShortName(UScriptCode scriptCode); 267 268 /** 269 * Gets the script code associated with the given codepoint. 270 * Returns USCRIPT_MALAYALAM given 0x0D02 271 * @param codepoint UChar32 codepoint 272 * @param err the error status code. 273 * @return The UScriptCode, or 0 if codepoint is invalid 274 * @stable ICU 2.4 275 */ 276 U_STABLE UScriptCode U_EXPORT2 277 uscript_getScript(UChar32 codepoint, UErrorCode *err); 278 279 /** 280 * Is code point c used in script sc? 281 * That is, does code point c have the Script property value sc, 282 * or do code point c's Script_Extensions include script code sc? 283 * 284 * Some characters are commonly used in multiple scripts. 285 * For more information, see UAX #24: http://www.unicode.org/reports/tr24/. 286 * 287 * The Script_Extensions property is provisional. It may be modified or removed 288 * in future versions of the Unicode Standard, and thus in ICU. 289 * @param c code point 290 * @param sc script code 291 * @return TRUE if Script(c)==sc or sc is in Script_Extensions(c) 292 * @draft ICU 4.6 293 */ 294 U_DRAFT UBool U_EXPORT2 295 uscript_hasScript(UChar32 c, UScriptCode sc); 296 297 /** 298 * Writes code point c's Script_Extensions as a list of UScriptCode values 299 * to the output scripts array. 300 * 301 * Some characters are commonly used in multiple scripts. 302 * For more information, see UAX #24: http://www.unicode.org/reports/tr24/. 303 * 304 * If there are more than capacity script codes to be written, then 305 * U_BUFFER_OVERFLOW_ERROR is set and the number of Script_Extensions is returned. 306 * (Usual ICU buffer handling behavior.) 307 * 308 * The Script_Extensions property is provisional. It may be modified or removed 309 * in future versions of the Unicode Standard, and thus in ICU. 310 * @param c code point 311 * @param scripts output script code array 312 * @param capacity capacity of the scripts array 313 * @param errorCode Standard ICU error code. Its input value must 314 * pass the U_SUCCESS() test, or else the function returns 315 * immediately. Check for U_FAILURE() on output or use with 316 * function chaining. (See User Guide for details.) 317 * @return number of script codes in c's Script_Extensions, 318 * written to scripts unless U_BUFFER_OVERFLOW_ERROR indicates insufficient capacity 319 * @draft ICU 4.6 320 */ 321 U_DRAFT int32_t U_EXPORT2 322 uscript_getScriptExtensions(UChar32 c, 323 UScriptCode *scripts, int32_t capacity, 324 UErrorCode *pErrorCode); 325 326 #endif 327