ICU 67.1: uscript.h Source File

00001 // © 2016 and later: Unicode, Inc. and others.
00002 // License & terms of use: http://www.unicode.org/copyright.html
00003 /*
00004  **********************************************************************
00005  *   Copyright (C) 1997-2016, International Business Machines
00006  *   Corporation and others.  All Rights Reserved.
00007  **********************************************************************
00008  *
00009  * File USCRIPT.H
00010  *
00011  * Modification History:
00012  *
00013  *   Date        Name        Description
00014  *   07/06/2001    Ram         Creation.
00015  ******************************************************************************
00016  */
00017 
00018 #ifndef USCRIPT_H
00019 #define USCRIPT_H
00020 #include "unicode/utypes.h"
00021 
00054 typedef enum UScriptCode {
00055     /*
00056      * Note: UScriptCode constants and their ISO script code comments
00057      * are parsed by preparseucd.py.
00058      * It matches lines like
00059      *     USCRIPT_<Unicode Script value name> = <integer>,  / * <ISO script code> * /
00060      */
00061 
00063       USCRIPT_INVALID_CODE = -1,
00065       USCRIPT_COMMON       =  0,  /* Zyyy */
00067       USCRIPT_INHERITED    =  1,  /* Zinh */ /* "Code for inherited script", for non-spacing combining marks; also Qaai */
00069       USCRIPT_ARABIC       =  2,  /* Arab */
00071       USCRIPT_ARMENIAN     =  3,  /* Armn */
00073       USCRIPT_BENGALI      =  4,  /* Beng */
00075       USCRIPT_BOPOMOFO     =  5,  /* Bopo */
00077       USCRIPT_CHEROKEE     =  6,  /* Cher */
00079       USCRIPT_COPTIC       =  7,  /* Copt */
00081       USCRIPT_CYRILLIC     =  8,  /* Cyrl */
00083       USCRIPT_DESERET      =  9,  /* Dsrt */
00085       USCRIPT_DEVANAGARI   = 10,  /* Deva */
00087       USCRIPT_ETHIOPIC     = 11,  /* Ethi */
00089       USCRIPT_GEORGIAN     = 12,  /* Geor */
00091       USCRIPT_GOTHIC       = 13,  /* Goth */
00093       USCRIPT_GREEK        = 14,  /* Grek */
00095       USCRIPT_GUJARATI     = 15,  /* Gujr */
00097       USCRIPT_GURMUKHI     = 16,  /* Guru */
00099       USCRIPT_HAN          = 17,  /* Hani */
00101       USCRIPT_HANGUL       = 18,  /* Hang */
00103       USCRIPT_HEBREW       = 19,  /* Hebr */
00105       USCRIPT_HIRAGANA     = 20,  /* Hira */
00107       USCRIPT_KANNADA      = 21,  /* Knda */
00109       USCRIPT_KATAKANA     = 22,  /* Kana */
00111       USCRIPT_KHMER        = 23,  /* Khmr */
00113       USCRIPT_LAO          = 24,  /* Laoo */
00115       USCRIPT_LATIN        = 25,  /* Latn */
00117       USCRIPT_MALAYALAM    = 26,  /* Mlym */
00119       USCRIPT_MONGOLIAN    = 27,  /* Mong */
00121       USCRIPT_MYANMAR      = 28,  /* Mymr */
00123       USCRIPT_OGHAM        = 29,  /* Ogam */
00125       USCRIPT_OLD_ITALIC   = 30,  /* Ital */
00127       USCRIPT_ORIYA        = 31,  /* Orya */
00129       USCRIPT_RUNIC        = 32,  /* Runr */
00131       USCRIPT_SINHALA      = 33,  /* Sinh */
00133       USCRIPT_SYRIAC       = 34,  /* Syrc */
00135       USCRIPT_TAMIL        = 35,  /* Taml */
00137       USCRIPT_TELUGU       = 36,  /* Telu */
00139       USCRIPT_THAANA       = 37,  /* Thaa */
00141       USCRIPT_THAI         = 38,  /* Thai */
00143       USCRIPT_TIBETAN      = 39,  /* Tibt */
00145       USCRIPT_CANADIAN_ABORIGINAL = 40,  /* Cans */
00147       USCRIPT_UCAS         = USCRIPT_CANADIAN_ABORIGINAL,
00149       USCRIPT_YI           = 41,  /* Yiii */
00150       /* New scripts in Unicode 3.2 */
00152       USCRIPT_TAGALOG      = 42,  /* Tglg */
00154       USCRIPT_HANUNOO      = 43,  /* Hano */
00156       USCRIPT_BUHID        = 44,  /* Buhd */
00158       USCRIPT_TAGBANWA     = 45,  /* Tagb */
00159 
00160       /* New scripts in Unicode 4 */
00162       USCRIPT_BRAILLE      = 46,  /* Brai */
00164       USCRIPT_CYPRIOT      = 47,  /* Cprt */
00166       USCRIPT_LIMBU        = 48,  /* Limb */
00168       USCRIPT_LINEAR_B     = 49,  /* Linb */
00170       USCRIPT_OSMANYA      = 50,  /* Osma */
00172       USCRIPT_SHAVIAN      = 51,  /* Shaw */
00174       USCRIPT_TAI_LE       = 52,  /* Tale */
00176       USCRIPT_UGARITIC     = 53,  /* Ugar */
00177 
00179       USCRIPT_KATAKANA_OR_HIRAGANA = 54,/*Hrkt */
00180 
00181       /* New scripts in Unicode 4.1 */
00183       USCRIPT_BUGINESE      = 55, /* Bugi */
00185       USCRIPT_GLAGOLITIC    = 56, /* Glag */
00187       USCRIPT_KHAROSHTHI    = 57, /* Khar */
00189       USCRIPT_SYLOTI_NAGRI  = 58, /* Sylo */
00191       USCRIPT_NEW_TAI_LUE   = 59, /* Talu */
00193       USCRIPT_TIFINAGH      = 60, /* Tfng */
00195       USCRIPT_OLD_PERSIAN   = 61, /* Xpeo */
00196 
00197       /* New script codes from Unicode and ISO 15924 */
00199       USCRIPT_BALINESE                      = 62, /* Bali */
00201       USCRIPT_BATAK                         = 63, /* Batk */
00203       USCRIPT_BLISSYMBOLS                   = 64, /* Blis */
00205       USCRIPT_BRAHMI                        = 65, /* Brah */
00207       USCRIPT_CHAM                          = 66, /* Cham */
00209       USCRIPT_CIRTH                         = 67, /* Cirt */
00211       USCRIPT_OLD_CHURCH_SLAVONIC_CYRILLIC  = 68, /* Cyrs */
00213       USCRIPT_DEMOTIC_EGYPTIAN              = 69, /* Egyd */
00215       USCRIPT_HIERATIC_EGYPTIAN             = 70, /* Egyh */
00217       USCRIPT_EGYPTIAN_HIEROGLYPHS          = 71, /* Egyp */
00219       USCRIPT_KHUTSURI                      = 72, /* Geok */
00221       USCRIPT_SIMPLIFIED_HAN                = 73, /* Hans */
00223       USCRIPT_TRADITIONAL_HAN               = 74, /* Hant */
00225       USCRIPT_PAHAWH_HMONG                  = 75, /* Hmng */
00227       USCRIPT_OLD_HUNGARIAN                 = 76, /* Hung */
00229       USCRIPT_HARAPPAN_INDUS                = 77, /* Inds */
00231       USCRIPT_JAVANESE                      = 78, /* Java */
00233       USCRIPT_KAYAH_LI                      = 79, /* Kali */
00235       USCRIPT_LATIN_FRAKTUR                 = 80, /* Latf */
00237       USCRIPT_LATIN_GAELIC                  = 81, /* Latg */
00239       USCRIPT_LEPCHA                        = 82, /* Lepc */
00241       USCRIPT_LINEAR_A                      = 83, /* Lina */
00243       USCRIPT_MANDAIC                       = 84, /* Mand */
00245       USCRIPT_MANDAEAN                      = USCRIPT_MANDAIC,
00247       USCRIPT_MAYAN_HIEROGLYPHS             = 85, /* Maya */
00249       USCRIPT_MEROITIC_HIEROGLYPHS          = 86, /* Mero */
00251       USCRIPT_MEROITIC                      = USCRIPT_MEROITIC_HIEROGLYPHS,
00253       USCRIPT_NKO                           = 87, /* Nkoo */
00255       USCRIPT_ORKHON                        = 88, /* Orkh */
00257       USCRIPT_OLD_PERMIC                    = 89, /* Perm */
00259       USCRIPT_PHAGS_PA                      = 90, /* Phag */
00261       USCRIPT_PHOENICIAN                    = 91, /* Phnx */
00263       USCRIPT_MIAO                          = 92, /* Plrd */
00265       USCRIPT_PHONETIC_POLLARD              = USCRIPT_MIAO,
00267       USCRIPT_RONGORONGO                    = 93, /* Roro */
00269       USCRIPT_SARATI                        = 94, /* Sara */
00271       USCRIPT_ESTRANGELO_SYRIAC             = 95, /* Syre */
00273       USCRIPT_WESTERN_SYRIAC                = 96, /* Syrj */
00275       USCRIPT_EASTERN_SYRIAC                = 97, /* Syrn */
00277       USCRIPT_TENGWAR                       = 98, /* Teng */
00279       USCRIPT_VAI                           = 99, /* Vaii */
00281       USCRIPT_VISIBLE_SPEECH                = 100,/* Visp */
00283       USCRIPT_CUNEIFORM                     = 101,/* Xsux */
00285       USCRIPT_UNWRITTEN_LANGUAGES           = 102,/* Zxxx */
00287       USCRIPT_UNKNOWN                       = 103,/* Zzzz */ /* Unknown="Code for uncoded script", for unassigned code points */
00288 
00290       USCRIPT_CARIAN                        = 104,/* Cari */
00292       USCRIPT_JAPANESE                      = 105,/* Jpan */
00294       USCRIPT_LANNA                         = 106,/* Lana */
00296       USCRIPT_LYCIAN                        = 107,/* Lyci */
00298       USCRIPT_LYDIAN                        = 108,/* Lydi */
00300       USCRIPT_OL_CHIKI                      = 109,/* Olck */
00302       USCRIPT_REJANG                        = 110,/* Rjng */
00304       USCRIPT_SAURASHTRA                    = 111,/* Saur */
00306       USCRIPT_SIGN_WRITING                  = 112,/* Sgnw */
00308       USCRIPT_SUNDANESE                     = 113,/* Sund */
00310       USCRIPT_MOON                          = 114,/* Moon */
00312       USCRIPT_MEITEI_MAYEK                  = 115,/* Mtei */
00313 
00315       USCRIPT_IMPERIAL_ARAMAIC              = 116,/* Armi */
00317       USCRIPT_AVESTAN                       = 117,/* Avst */
00319       USCRIPT_CHAKMA                        = 118,/* Cakm */
00321       USCRIPT_KOREAN                        = 119,/* Kore */
00323       USCRIPT_KAITHI                        = 120,/* Kthi */
00325       USCRIPT_MANICHAEAN                    = 121,/* Mani */
00327       USCRIPT_INSCRIPTIONAL_PAHLAVI         = 122,/* Phli */
00329       USCRIPT_PSALTER_PAHLAVI               = 123,/* Phlp */
00331       USCRIPT_BOOK_PAHLAVI                  = 124,/* Phlv */
00333       USCRIPT_INSCRIPTIONAL_PARTHIAN        = 125,/* Prti */
00335       USCRIPT_SAMARITAN                     = 126,/* Samr */
00337       USCRIPT_TAI_VIET                      = 127,/* Tavt */
00339       USCRIPT_MATHEMATICAL_NOTATION         = 128,/* Zmth */
00341       USCRIPT_SYMBOLS                       = 129,/* Zsym */
00342 
00344       USCRIPT_BAMUM                         = 130,/* Bamu */
00346       USCRIPT_LISU                          = 131,/* Lisu */
00348       USCRIPT_NAKHI_GEBA                    = 132,/* Nkgb */
00350       USCRIPT_OLD_SOUTH_ARABIAN             = 133,/* Sarb */
00351 
00353       USCRIPT_BASSA_VAH                     = 134,/* Bass */
00355       USCRIPT_DUPLOYAN                      = 135,/* Dupl */
00356 #ifndef U_HIDE_DEPRECATED_API
00357 
00358       USCRIPT_DUPLOYAN_SHORTAND             = USCRIPT_DUPLOYAN,
00359 #endif  /* U_HIDE_DEPRECATED_API */
00360 
00361       USCRIPT_ELBASAN                       = 136,/* Elba */
00363       USCRIPT_GRANTHA                       = 137,/* Gran */
00365       USCRIPT_KPELLE                        = 138,/* Kpel */
00367       USCRIPT_LOMA                          = 139,/* Loma */
00369       USCRIPT_MENDE                         = 140,/* Mend */
00371       USCRIPT_MEROITIC_CURSIVE              = 141,/* Merc */
00373       USCRIPT_OLD_NORTH_ARABIAN             = 142,/* Narb */
00375       USCRIPT_NABATAEAN                     = 143,/* Nbat */
00377       USCRIPT_PALMYRENE                     = 144,/* Palm */
00379       USCRIPT_KHUDAWADI                     = 145,/* Sind */
00381       USCRIPT_SINDHI                        = USCRIPT_KHUDAWADI,
00383       USCRIPT_WARANG_CITI                   = 146,/* Wara */
00384 
00386       USCRIPT_AFAKA                         = 147,/* Afak */
00388       USCRIPT_JURCHEN                       = 148,/* Jurc */
00390       USCRIPT_MRO                           = 149,/* Mroo */
00392       USCRIPT_NUSHU                         = 150,/* Nshu */
00394       USCRIPT_SHARADA                       = 151,/* Shrd */
00396       USCRIPT_SORA_SOMPENG                  = 152,/* Sora */
00398       USCRIPT_TAKRI                         = 153,/* Takr */
00400       USCRIPT_TANGUT                        = 154,/* Tang */
00402       USCRIPT_WOLEAI                        = 155,/* Wole */
00403 
00405       USCRIPT_ANATOLIAN_HIEROGLYPHS         = 156,/* Hluw */
00407       USCRIPT_KHOJKI                        = 157,/* Khoj */
00409       USCRIPT_TIRHUTA                       = 158,/* Tirh */
00410 
00412       USCRIPT_CAUCASIAN_ALBANIAN            = 159,/* Aghb */
00414       USCRIPT_MAHAJANI                      = 160,/* Mahj */
00415 
00417       USCRIPT_AHOM                          = 161,/* Ahom */
00419       USCRIPT_HATRAN                        = 162,/* Hatr */
00421       USCRIPT_MODI                          = 163,/* Modi */
00423       USCRIPT_MULTANI                       = 164,/* Mult */
00425       USCRIPT_PAU_CIN_HAU                   = 165,/* Pauc */
00427       USCRIPT_SIDDHAM                       = 166,/* Sidd */
00428 
00430       USCRIPT_ADLAM                         = 167,/* Adlm */
00432       USCRIPT_BHAIKSUKI                     = 168,/* Bhks */
00434       USCRIPT_MARCHEN                       = 169,/* Marc */
00436       USCRIPT_NEWA                          = 170,/* Newa */
00438       USCRIPT_OSAGE                         = 171,/* Osge */
00439 
00441       USCRIPT_HAN_WITH_BOPOMOFO             = 172,/* Hanb */
00443       USCRIPT_JAMO                          = 173,/* Jamo */
00445       USCRIPT_SYMBOLS_EMOJI                 = 174,/* Zsye */
00446 
00448       USCRIPT_MASARAM_GONDI                 = 175,/* Gonm */
00450       USCRIPT_SOYOMBO                       = 176,/* Soyo */
00452       USCRIPT_ZANABAZAR_SQUARE              = 177,/* Zanb */
00453 
00455       USCRIPT_DOGRA                         = 178,/* Dogr */
00457       USCRIPT_GUNJALA_GONDI                 = 179,/* Gong */
00459       USCRIPT_MAKASAR                       = 180,/* Maka */
00461       USCRIPT_MEDEFAIDRIN                   = 181,/* Medf */
00463       USCRIPT_HANIFI_ROHINGYA               = 182,/* Rohg */
00465       USCRIPT_SOGDIAN                       = 183,/* Sogd */
00467       USCRIPT_OLD_SOGDIAN                   = 184,/* Sogo */
00468 
00470       USCRIPT_ELYMAIC                       = 185,/* Elym */
00472       USCRIPT_NYIAKENG_PUACHUE_HMONG        = 186,/* Hmnp */
00474       USCRIPT_NANDINAGARI                   = 187,/* Nand */
00476       USCRIPT_WANCHO                        = 188,/* Wcho */
00477 
00479       USCRIPT_CHORASMIAN                    = 189,/* Chrs */
00481       USCRIPT_DIVES_AKURU                   = 190,/* Diak */
00483       USCRIPT_KHITAN_SMALL_SCRIPT           = 191,/* Kits */
00485       USCRIPT_YEZIDI                        = 192,/* Yezi */
00486 
00487 #ifndef U_HIDE_DEPRECATED_API
00488 
00494     USCRIPT_CODE_LIMIT    = 193
00495 #endif  // U_HIDE_DEPRECATED_API
00496 } UScriptCode;
00497 
00517 U_STABLE int32_t  U_EXPORT2
00518 uscript_getCode(const char* nameOrAbbrOrLocale,UScriptCode* fillIn,int32_t capacity,UErrorCode *err);
00519 
00530 U_STABLE const char*  U_EXPORT2
00531 uscript_getName(UScriptCode scriptCode);
00532 
00542 U_STABLE const char*  U_EXPORT2
00543 uscript_getShortName(UScriptCode scriptCode);
00544 
00553 U_STABLE UScriptCode  U_EXPORT2
00554 uscript_getScript(UChar32 codepoint, UErrorCode *err);
00555 
00568 U_STABLE UBool U_EXPORT2
00569 uscript_hasScript(UChar32 c, UScriptCode sc);
00570 
00600 U_STABLE int32_t U_EXPORT2
00601 uscript_getScriptExtensions(UChar32 c,
00602                             UScriptCode *scripts, int32_t capacity,
00603                             UErrorCode *errorCode);
00604 
00612 typedef enum UScriptUsage {
00614     USCRIPT_USAGE_NOT_ENCODED,
00616     USCRIPT_USAGE_UNKNOWN,
00618     USCRIPT_USAGE_EXCLUDED,
00620     USCRIPT_USAGE_LIMITED_USE,
00622     USCRIPT_USAGE_ASPIRATIONAL,
00624     USCRIPT_USAGE_RECOMMENDED
00625 } UScriptUsage;
00626 
00639 U_STABLE int32_t U_EXPORT2
00640 uscript_getSampleString(UScriptCode script, UChar *dest, int32_t capacity, UErrorCode *pErrorCode);
00641 
00642 #if U_SHOW_CPLUSPLUS_API
00643 
00644 U_NAMESPACE_BEGIN
00645 class UnicodeString;
00646 U_NAMESPACE_END
00647 
00657 U_COMMON_API icu::UnicodeString U_EXPORT2
00658 uscript_getSampleUnicodeString(UScriptCode script);
00659 
00660 #endif
00661 
00671 U_STABLE UScriptUsage U_EXPORT2
00672 uscript_getUsage(UScriptCode script);
00673 
00682 U_STABLE UBool U_EXPORT2
00683 uscript_isRightToLeft(UScriptCode script);
00684 
00694 U_STABLE UBool U_EXPORT2
00695 uscript_breaksBetweenLetters(UScriptCode script);
00696 
00705 U_STABLE UBool U_EXPORT2
00706 uscript_isCased(UScriptCode script);
00707 
00708 #endif