michael@0: /*
michael@0:  **********************************************************************
michael@0:  *   Copyright (C) 1997-2013, International Business Machines
michael@0:  *   Corporation and others.  All Rights Reserved.
michael@0:  **********************************************************************
michael@0:  *
michael@0:  * File USCRIPT.H
michael@0:  *
michael@0:  * Modification History:
michael@0:  *
michael@0:  *   Date        Name        Description
michael@0:  *   07/06/2001    Ram         Creation.
michael@0:  ******************************************************************************
michael@0:  */
michael@0: 
michael@0: #ifndef USCRIPT_H
michael@0: #define USCRIPT_H
michael@0: #include "unicode/utypes.h"
michael@0: 
michael@0: /**
michael@0:  * \file
michael@0:  * \brief C API: Unicode Script Information
michael@0:  */
michael@0:  
michael@0: /**
michael@0:  * Constants for ISO 15924 script codes.
michael@0:  *
michael@0:  * Many of these script codes - those from Unicode's ScriptNames.txt -
michael@0:  * are character property values for Unicode's Script property.
michael@0:  * See UAX #24 Script Names (http://www.unicode.org/reports/tr24/).
michael@0:  *
michael@0:  * Starting with ICU 3.6, constants for most ISO 15924 script codes
michael@0:  * are included (currently excluding private-use codes Qaaa..Qabx).
michael@0:  * For scripts for which there are codes in ISO 15924 but which are not
michael@0:  * used in the Unicode Character Database (UCD), there are no Unicode characters
michael@0:  * associated with those scripts.
michael@0:  *
michael@0:  * For example, there are no characters that have a UCD script code of
michael@0:  * Hans or Hant. All Han ideographs have the Hani script code.
michael@0:  * The Hans and Hant script codes are used with CLDR data.
michael@0:  *
michael@0:  * ISO 15924 script codes are included for use with CLDR and similar.
michael@0:  *
michael@0:  * @stable ICU 2.2
michael@0:  */
michael@0: typedef enum UScriptCode {
michael@0:     /*
michael@0:      * Note: UScriptCode constants and their ISO script code comments
michael@0:      * are parsed by preparseucd.py.
michael@0:      * It matches lines like
michael@0:      *     USCRIPT_<Unicode Script value name> = <integer>,  / * <ISO script code> * /
michael@0:      */
michael@0: 
michael@0:       /** @stable ICU 2.2 */
michael@0:       USCRIPT_INVALID_CODE = -1,
michael@0:       /** @stable ICU 2.2 */
michael@0:       USCRIPT_COMMON       =  0,  /* Zyyy */
michael@0:       /** @stable ICU 2.2 */
michael@0:       USCRIPT_INHERITED    =  1,  /* Zinh */ /* "Code for inherited script", for non-spacing combining marks; also Qaai */
michael@0:       /** @stable ICU 2.2 */
michael@0:       USCRIPT_ARABIC       =  2,  /* Arab */
michael@0:       /** @stable ICU 2.2 */
michael@0:       USCRIPT_ARMENIAN     =  3,  /* Armn */
michael@0:       /** @stable ICU 2.2 */
michael@0:       USCRIPT_BENGALI      =  4,  /* Beng */
michael@0:       /** @stable ICU 2.2 */
michael@0:       USCRIPT_BOPOMOFO     =  5,  /* Bopo */
michael@0:       /** @stable ICU 2.2 */
michael@0:       USCRIPT_CHEROKEE     =  6,  /* Cher */
michael@0:       /** @stable ICU 2.2 */
michael@0:       USCRIPT_COPTIC       =  7,  /* Copt */
michael@0:       /** @stable ICU 2.2 */
michael@0:       USCRIPT_CYRILLIC     =  8,  /* Cyrl */
michael@0:       /** @stable ICU 2.2 */
michael@0:       USCRIPT_DESERET      =  9,  /* Dsrt */
michael@0:       /** @stable ICU 2.2 */
michael@0:       USCRIPT_DEVANAGARI   = 10,  /* Deva */
michael@0:       /** @stable ICU 2.2 */
michael@0:       USCRIPT_ETHIOPIC     = 11,  /* Ethi */
michael@0:       /** @stable ICU 2.2 */
michael@0:       USCRIPT_GEORGIAN     = 12,  /* Geor */
michael@0:       /** @stable ICU 2.2 */
michael@0:       USCRIPT_GOTHIC       = 13,  /* Goth */
michael@0:       /** @stable ICU 2.2 */
michael@0:       USCRIPT_GREEK        = 14,  /* Grek */
michael@0:       /** @stable ICU 2.2 */
michael@0:       USCRIPT_GUJARATI     = 15,  /* Gujr */
michael@0:       /** @stable ICU 2.2 */
michael@0:       USCRIPT_GURMUKHI     = 16,  /* Guru */
michael@0:       /** @stable ICU 2.2 */
michael@0:       USCRIPT_HAN          = 17,  /* Hani */
michael@0:       /** @stable ICU 2.2 */
michael@0:       USCRIPT_HANGUL       = 18,  /* Hang */
michael@0:       /** @stable ICU 2.2 */
michael@0:       USCRIPT_HEBREW       = 19,  /* Hebr */
michael@0:       /** @stable ICU 2.2 */
michael@0:       USCRIPT_HIRAGANA     = 20,  /* Hira */
michael@0:       /** @stable ICU 2.2 */
michael@0:       USCRIPT_KANNADA      = 21,  /* Knda */
michael@0:       /** @stable ICU 2.2 */
michael@0:       USCRIPT_KATAKANA     = 22,  /* Kana */
michael@0:       /** @stable ICU 2.2 */
michael@0:       USCRIPT_KHMER        = 23,  /* Khmr */
michael@0:       /** @stable ICU 2.2 */
michael@0:       USCRIPT_LAO          = 24,  /* Laoo */
michael@0:       /** @stable ICU 2.2 */
michael@0:       USCRIPT_LATIN        = 25,  /* Latn */
michael@0:       /** @stable ICU 2.2 */
michael@0:       USCRIPT_MALAYALAM    = 26,  /* Mlym */
michael@0:       /** @stable ICU 2.2 */
michael@0:       USCRIPT_MONGOLIAN    = 27,  /* Mong */
michael@0:       /** @stable ICU 2.2 */
michael@0:       USCRIPT_MYANMAR      = 28,  /* Mymr */
michael@0:       /** @stable ICU 2.2 */
michael@0:       USCRIPT_OGHAM        = 29,  /* Ogam */
michael@0:       /** @stable ICU 2.2 */
michael@0:       USCRIPT_OLD_ITALIC   = 30,  /* Ital */
michael@0:       /** @stable ICU 2.2 */
michael@0:       USCRIPT_ORIYA        = 31,  /* Orya */
michael@0:       /** @stable ICU 2.2 */
michael@0:       USCRIPT_RUNIC        = 32,  /* Runr */
michael@0:       /** @stable ICU 2.2 */
michael@0:       USCRIPT_SINHALA      = 33,  /* Sinh */
michael@0:       /** @stable ICU 2.2 */
michael@0:       USCRIPT_SYRIAC       = 34,  /* Syrc */
michael@0:       /** @stable ICU 2.2 */
michael@0:       USCRIPT_TAMIL        = 35,  /* Taml */
michael@0:       /** @stable ICU 2.2 */
michael@0:       USCRIPT_TELUGU       = 36,  /* Telu */
michael@0:       /** @stable ICU 2.2 */
michael@0:       USCRIPT_THAANA       = 37,  /* Thaa */
michael@0:       /** @stable ICU 2.2 */
michael@0:       USCRIPT_THAI         = 38,  /* Thai */
michael@0:       /** @stable ICU 2.2 */
michael@0:       USCRIPT_TIBETAN      = 39,  /* Tibt */
michael@0:       /** Canadian_Aboriginal script. @stable ICU 2.6 */
michael@0:       USCRIPT_CANADIAN_ABORIGINAL = 40,  /* Cans */
michael@0:       /** Canadian_Aboriginal script (alias). @stable ICU 2.2 */
michael@0:       USCRIPT_UCAS         = USCRIPT_CANADIAN_ABORIGINAL,
michael@0:       /** @stable ICU 2.2 */
michael@0:       USCRIPT_YI           = 41,  /* Yiii */
michael@0:       /* New scripts in Unicode 3.2 */
michael@0:       /** @stable ICU 2.2 */
michael@0:       USCRIPT_TAGALOG      = 42,  /* Tglg */
michael@0:       /** @stable ICU 2.2 */
michael@0:       USCRIPT_HANUNOO      = 43,  /* Hano */
michael@0:       /** @stable ICU 2.2 */
michael@0:       USCRIPT_BUHID        = 44,  /* Buhd */
michael@0:       /** @stable ICU 2.2 */
michael@0:       USCRIPT_TAGBANWA     = 45,  /* Tagb */
michael@0: 
michael@0:       /* New scripts in Unicode 4 */
michael@0:       /** @stable ICU 2.6 */
michael@0:       USCRIPT_BRAILLE      = 46,  /* Brai */
michael@0:       /** @stable ICU 2.6 */
michael@0:       USCRIPT_CYPRIOT      = 47,  /* Cprt */
michael@0:       /** @stable ICU 2.6 */
michael@0:       USCRIPT_LIMBU        = 48,  /* Limb */
michael@0:       /** @stable ICU 2.6 */
michael@0:       USCRIPT_LINEAR_B     = 49,  /* Linb */
michael@0:       /** @stable ICU 2.6 */
michael@0:       USCRIPT_OSMANYA      = 50,  /* Osma */
michael@0:       /** @stable ICU 2.6 */
michael@0:       USCRIPT_SHAVIAN      = 51,  /* Shaw */
michael@0:       /** @stable ICU 2.6 */
michael@0:       USCRIPT_TAI_LE       = 52,  /* Tale */
michael@0:       /** @stable ICU 2.6 */
michael@0:       USCRIPT_UGARITIC     = 53,  /* Ugar */
michael@0: 
michael@0:       /** New script code in Unicode 4.0.1 @stable ICU 3.0 */
michael@0:       USCRIPT_KATAKANA_OR_HIRAGANA = 54,/*Hrkt */
michael@0: 
michael@0:       /* New scripts in Unicode 4.1 */
michael@0:       /** @stable ICU 3.4 */
michael@0:       USCRIPT_BUGINESE      = 55, /* Bugi */
michael@0:       /** @stable ICU 3.4 */
michael@0:       USCRIPT_GLAGOLITIC    = 56, /* Glag */
michael@0:       /** @stable ICU 3.4 */
michael@0:       USCRIPT_KHAROSHTHI    = 57, /* Khar */
michael@0:       /** @stable ICU 3.4 */
michael@0:       USCRIPT_SYLOTI_NAGRI  = 58, /* Sylo */
michael@0:       /** @stable ICU 3.4 */
michael@0:       USCRIPT_NEW_TAI_LUE   = 59, /* Talu */
michael@0:       /** @stable ICU 3.4 */
michael@0:       USCRIPT_TIFINAGH      = 60, /* Tfng */
michael@0:       /** @stable ICU 3.4 */
michael@0:       USCRIPT_OLD_PERSIAN   = 61, /* Xpeo */
michael@0: 
michael@0:       /* New script codes from ISO 15924 */
michael@0:       /** @stable ICU 3.6 */
michael@0:       USCRIPT_BALINESE                      = 62, /* Bali */
michael@0:       /** @stable ICU 3.6 */
michael@0:       USCRIPT_BATAK                         = 63, /* Batk */
michael@0:       /** @stable ICU 3.6 */
michael@0:       USCRIPT_BLISSYMBOLS                   = 64, /* Blis */
michael@0:       /** @stable ICU 3.6 */
michael@0:       USCRIPT_BRAHMI                        = 65, /* Brah */
michael@0:       /** @stable ICU 3.6 */
michael@0:       USCRIPT_CHAM                          = 66, /* Cham */
michael@0:       /** @stable ICU 3.6 */
michael@0:       USCRIPT_CIRTH                         = 67, /* Cirt */
michael@0:       /** @stable ICU 3.6 */
michael@0:       USCRIPT_OLD_CHURCH_SLAVONIC_CYRILLIC  = 68, /* Cyrs */
michael@0:       /** @stable ICU 3.6 */
michael@0:       USCRIPT_DEMOTIC_EGYPTIAN              = 69, /* Egyd */
michael@0:       /** @stable ICU 3.6 */
michael@0:       USCRIPT_HIERATIC_EGYPTIAN             = 70, /* Egyh */
michael@0:       /** @stable ICU 3.6 */
michael@0:       USCRIPT_EGYPTIAN_HIEROGLYPHS          = 71, /* Egyp */
michael@0:       /** @stable ICU 3.6 */
michael@0:       USCRIPT_KHUTSURI                      = 72, /* Geok */
michael@0:       /** @stable ICU 3.6 */
michael@0:       USCRIPT_SIMPLIFIED_HAN                = 73, /* Hans */
michael@0:       /** @stable ICU 3.6 */
michael@0:       USCRIPT_TRADITIONAL_HAN               = 74, /* Hant */
michael@0:       /** @stable ICU 3.6 */
michael@0:       USCRIPT_PAHAWH_HMONG                  = 75, /* Hmng */
michael@0:       /** @stable ICU 3.6 */
michael@0:       USCRIPT_OLD_HUNGARIAN                 = 76, /* Hung */
michael@0:       /** @stable ICU 3.6 */
michael@0:       USCRIPT_HARAPPAN_INDUS                = 77, /* Inds */
michael@0:       /** @stable ICU 3.6 */
michael@0:       USCRIPT_JAVANESE                      = 78, /* Java */
michael@0:       /** @stable ICU 3.6 */
michael@0:       USCRIPT_KAYAH_LI                      = 79, /* Kali */
michael@0:       /** @stable ICU 3.6 */
michael@0:       USCRIPT_LATIN_FRAKTUR                 = 80, /* Latf */
michael@0:       /** @stable ICU 3.6 */
michael@0:       USCRIPT_LATIN_GAELIC                  = 81, /* Latg */
michael@0:       /** @stable ICU 3.6 */
michael@0:       USCRIPT_LEPCHA                        = 82, /* Lepc */
michael@0:       /** @stable ICU 3.6 */
michael@0:       USCRIPT_LINEAR_A                      = 83, /* Lina */
michael@0:       /** @stable ICU 4.6 */
michael@0:       USCRIPT_MANDAIC                       = 84, /* Mand */
michael@0:       /** @stable ICU 3.6 */
michael@0:       USCRIPT_MANDAEAN                      = USCRIPT_MANDAIC,
michael@0:       /** @stable ICU 3.6 */
michael@0:       USCRIPT_MAYAN_HIEROGLYPHS             = 85, /* Maya */
michael@0:       /** @stable ICU 4.6 */
michael@0:       USCRIPT_MEROITIC_HIEROGLYPHS          = 86, /* Mero */
michael@0:       /** @stable ICU 3.6 */
michael@0:       USCRIPT_MEROITIC                      = USCRIPT_MEROITIC_HIEROGLYPHS,
michael@0:       /** @stable ICU 3.6 */
michael@0:       USCRIPT_NKO                           = 87, /* Nkoo */
michael@0:       /** @stable ICU 3.6 */
michael@0:       USCRIPT_ORKHON                        = 88, /* Orkh */
michael@0:       /** @stable ICU 3.6 */
michael@0:       USCRIPT_OLD_PERMIC                    = 89, /* Perm */
michael@0:       /** @stable ICU 3.6 */
michael@0:       USCRIPT_PHAGS_PA                      = 90, /* Phag */
michael@0:       /** @stable ICU 3.6 */
michael@0:       USCRIPT_PHOENICIAN                    = 91, /* Phnx */
michael@0:       /** @stable ICU 52 */
michael@0:       USCRIPT_MIAO                          = 92, /* Plrd */
michael@0:       /** @stable ICU 3.6 */
michael@0:       USCRIPT_PHONETIC_POLLARD              = USCRIPT_MIAO,
michael@0:       /** @stable ICU 3.6 */
michael@0:       USCRIPT_RONGORONGO                    = 93, /* Roro */
michael@0:       /** @stable ICU 3.6 */
michael@0:       USCRIPT_SARATI                        = 94, /* Sara */
michael@0:       /** @stable ICU 3.6 */
michael@0:       USCRIPT_ESTRANGELO_SYRIAC             = 95, /* Syre */
michael@0:       /** @stable ICU 3.6 */
michael@0:       USCRIPT_WESTERN_SYRIAC                = 96, /* Syrj */
michael@0:       /** @stable ICU 3.6 */
michael@0:       USCRIPT_EASTERN_SYRIAC                = 97, /* Syrn */
michael@0:       /** @stable ICU 3.6 */
michael@0:       USCRIPT_TENGWAR                       = 98, /* Teng */
michael@0:       /** @stable ICU 3.6 */
michael@0:       USCRIPT_VAI                           = 99, /* Vaii */
michael@0:       /** @stable ICU 3.6 */
michael@0:       USCRIPT_VISIBLE_SPEECH                = 100,/* Visp */
michael@0:       /** @stable ICU 3.6 */
michael@0:       USCRIPT_CUNEIFORM                     = 101,/* Xsux */
michael@0:       /** @stable ICU 3.6 */
michael@0:       USCRIPT_UNWRITTEN_LANGUAGES           = 102,/* Zxxx */
michael@0:       /** @stable ICU 3.6 */
michael@0:       USCRIPT_UNKNOWN                       = 103,/* Zzzz */ /* Unknown="Code for uncoded script", for unassigned code points */
michael@0: 
michael@0:       /* New script codes from ISO 15924 */
michael@0:       /** @stable ICU 3.8 */
michael@0:       USCRIPT_CARIAN                        = 104,/* Cari */
michael@0:       /** @stable ICU 3.8 */
michael@0:       USCRIPT_JAPANESE                      = 105,/* Jpan */
michael@0:       /** @stable ICU 3.8 */
michael@0:       USCRIPT_LANNA                         = 106,/* Lana */
michael@0:       /** @stable ICU 3.8 */
michael@0:       USCRIPT_LYCIAN                        = 107,/* Lyci */
michael@0:       /** @stable ICU 3.8 */
michael@0:       USCRIPT_LYDIAN                        = 108,/* Lydi */
michael@0:       /** @stable ICU 3.8 */
michael@0:       USCRIPT_OL_CHIKI                      = 109,/* Olck */
michael@0:       /** @stable ICU 3.8 */
michael@0:       USCRIPT_REJANG                        = 110,/* Rjng */
michael@0:       /** @stable ICU 3.8 */
michael@0:       USCRIPT_SAURASHTRA                    = 111,/* Saur */
michael@0:       /** @stable ICU 3.8 */
michael@0:       USCRIPT_SIGN_WRITING                  = 112,/* Sgnw */
michael@0:       /** @stable ICU 3.8 */
michael@0:       USCRIPT_SUNDANESE                     = 113,/* Sund */
michael@0:       /** @stable ICU 3.8 */
michael@0:       USCRIPT_MOON                          = 114,/* Moon */
michael@0:       /** @stable ICU 3.8 */
michael@0:       USCRIPT_MEITEI_MAYEK                  = 115,/* Mtei */
michael@0: 
michael@0:       /* New script codes from ISO 15924 */
michael@0:       /** @stable ICU 4.0 */
michael@0:       USCRIPT_IMPERIAL_ARAMAIC              = 116,/* Armi */
michael@0:       /** @stable ICU 4.0 */
michael@0:       USCRIPT_AVESTAN                       = 117,/* Avst */
michael@0:       /** @stable ICU 4.0 */
michael@0:       USCRIPT_CHAKMA                        = 118,/* Cakm */
michael@0:       /** @stable ICU 4.0 */
michael@0:       USCRIPT_KOREAN                        = 119,/* Kore */
michael@0:       /** @stable ICU 4.0 */
michael@0:       USCRIPT_KAITHI                        = 120,/* Kthi */
michael@0:       /** @stable ICU 4.0 */
michael@0:       USCRIPT_MANICHAEAN                    = 121,/* Mani */
michael@0:       /** @stable ICU 4.0 */
michael@0:       USCRIPT_INSCRIPTIONAL_PAHLAVI         = 122,/* Phli */
michael@0:       /** @stable ICU 4.0 */
michael@0:       USCRIPT_PSALTER_PAHLAVI               = 123,/* Phlp */
michael@0:       /** @stable ICU 4.0 */
michael@0:       USCRIPT_BOOK_PAHLAVI                  = 124,/* Phlv */
michael@0:       /** @stable ICU 4.0 */
michael@0:       USCRIPT_INSCRIPTIONAL_PARTHIAN        = 125,/* Prti */
michael@0:       /** @stable ICU 4.0 */
michael@0:       USCRIPT_SAMARITAN                     = 126,/* Samr */
michael@0:       /** @stable ICU 4.0 */
michael@0:       USCRIPT_TAI_VIET                      = 127,/* Tavt */
michael@0:       /** @stable ICU 4.0 */
michael@0:       USCRIPT_MATHEMATICAL_NOTATION         = 128,/* Zmth */
michael@0:       /** @stable ICU 4.0 */
michael@0:       USCRIPT_SYMBOLS                       = 129,/* Zsym */
michael@0: 
michael@0:       /* New script codes from ISO 15924 */
michael@0:       /** @stable ICU 4.4 */
michael@0:       USCRIPT_BAMUM                         = 130,/* Bamu */
michael@0:       /** @stable ICU 4.4 */
michael@0:       USCRIPT_LISU                          = 131,/* Lisu */
michael@0:       /** @stable ICU 4.4 */
michael@0:       USCRIPT_NAKHI_GEBA                    = 132,/* Nkgb */
michael@0:       /** @stable ICU 4.4 */
michael@0:       USCRIPT_OLD_SOUTH_ARABIAN             = 133,/* Sarb */
michael@0: 
michael@0:       /* New script codes from ISO 15924 */
michael@0:       /** @stable ICU 4.6 */
michael@0:       USCRIPT_BASSA_VAH                     = 134,/* Bass */
michael@0:       /** @stable ICU 4.6 */
michael@0:       USCRIPT_DUPLOYAN_SHORTAND             = 135,/* Dupl */
michael@0:       /** @stable ICU 4.6 */
michael@0:       USCRIPT_ELBASAN                       = 136,/* Elba */
michael@0:       /** @stable ICU 4.6 */
michael@0:       USCRIPT_GRANTHA                       = 137,/* Gran */
michael@0:       /** @stable ICU 4.6 */
michael@0:       USCRIPT_KPELLE                        = 138,/* Kpel */
michael@0:       /** @stable ICU 4.6 */
michael@0:       USCRIPT_LOMA                          = 139,/* Loma */
michael@0:       /** @stable ICU 4.6 */
michael@0:       USCRIPT_MENDE                         = 140,/* Mend */
michael@0:       /** @stable ICU 4.6 */
michael@0:       USCRIPT_MEROITIC_CURSIVE              = 141,/* Merc */
michael@0:       /** @stable ICU 4.6 */
michael@0:       USCRIPT_OLD_NORTH_ARABIAN             = 142,/* Narb */
michael@0:       /** @stable ICU 4.6 */
michael@0:       USCRIPT_NABATAEAN                     = 143,/* Nbat */
michael@0:       /** @stable ICU 4.6 */
michael@0:       USCRIPT_PALMYRENE                     = 144,/* Palm */
michael@0:       /** @stable ICU 4.6 */
michael@0:       USCRIPT_SINDHI                        = 145,/* Sind */
michael@0:       /** @stable ICU 4.6 */
michael@0:       USCRIPT_WARANG_CITI                   = 146,/* Wara */
michael@0: 
michael@0:       /** @stable ICU 4.8 */
michael@0:       USCRIPT_AFAKA                         = 147,/* Afak */
michael@0:       /** @stable ICU 4.8 */
michael@0:       USCRIPT_JURCHEN                       = 148,/* Jurc */
michael@0:       /** @stable ICU 4.8 */
michael@0:       USCRIPT_MRO                           = 149,/* Mroo */
michael@0:       /** @stable ICU 4.8 */
michael@0:       USCRIPT_NUSHU                         = 150,/* Nshu */
michael@0:       /** @stable ICU 4.8 */
michael@0:       USCRIPT_SHARADA                       = 151,/* Shrd */
michael@0:       /** @stable ICU 4.8 */
michael@0:       USCRIPT_SORA_SOMPENG                  = 152,/* Sora */
michael@0:       /** @stable ICU 4.8 */
michael@0:       USCRIPT_TAKRI                         = 153,/* Takr */
michael@0:       /** @stable ICU 4.8 */
michael@0:       USCRIPT_TANGUT                        = 154,/* Tang */
michael@0:       /** @stable ICU 4.8 */
michael@0:       USCRIPT_WOLEAI                        = 155,/* Wole */
michael@0: 
michael@0:       /** @stable ICU 49 */
michael@0:       USCRIPT_ANATOLIAN_HIEROGLYPHS         = 156,/* Hluw */
michael@0:       /** @stable ICU 49 */
michael@0:       USCRIPT_KHOJKI                        = 157,/* Khoj */
michael@0:       /** @stable ICU 49 */
michael@0:       USCRIPT_TIRHUTA                       = 158,/* Tirh */
michael@0: 
michael@0:       /** @stable ICU 52 */
michael@0:       USCRIPT_CAUCASIAN_ALBANIAN            = 159,/* Aghb */
michael@0:       /** @stable ICU 52 */
michael@0:       USCRIPT_MAHAJANI                      = 160,/* Mahj */
michael@0: 
michael@0:       /* Private use codes from Qaaa - Qabx are not supported */
michael@0: 
michael@0:       /** @stable ICU 2.2 */
michael@0:       USCRIPT_CODE_LIMIT    = 161
michael@0: } UScriptCode;
michael@0: 
michael@0: /**
michael@0:  * Gets script codes associated with the given locale or ISO 15924 abbreviation or name. 
michael@0:  * Fills in USCRIPT_MALAYALAM given "Malayam" OR "Mlym".
michael@0:  * Fills in USCRIPT_LATIN given "en" OR "en_US" 
michael@0:  * If required capacity is greater than capacity of the destination buffer then the error code
michael@0:  * is set to U_BUFFER_OVERFLOW_ERROR and the required capacity is returned
michael@0:  *
michael@0:  * <p>Note: To search by short or long script alias only, use
michael@0:  * u_getPropertyValueEnum(UCHAR_SCRIPT, alias) instead.  This does
michael@0:  * a fast lookup with no access of the locale data.
michael@0:  * @param nameOrAbbrOrLocale name of the script, as given in
michael@0:  * PropertyValueAliases.txt, or ISO 15924 code or locale
michael@0:  * @param fillIn the UScriptCode buffer to fill in the script code
michael@0:  * @param capacity the capacity (size) fo UScriptCode buffer passed in.
michael@0:  * @param err the error status code.
michael@0:  * @return The number of script codes filled in the buffer passed in 
michael@0:  * @stable ICU 2.4
michael@0:  */
michael@0: U_STABLE int32_t  U_EXPORT2 
michael@0: uscript_getCode(const char* nameOrAbbrOrLocale,UScriptCode* fillIn,int32_t capacity,UErrorCode *err);
michael@0: 
michael@0: /**
michael@0:  * Gets a script name associated with the given script code. 
michael@0:  * Returns  "Malayam" given USCRIPT_MALAYALAM
michael@0:  * @param scriptCode UScriptCode enum
michael@0:  * @return script long name as given in
michael@0:  * PropertyValueAliases.txt, or NULL if scriptCode is invalid
michael@0:  * @stable ICU 2.4
michael@0:  */
michael@0: U_STABLE const char*  U_EXPORT2 
michael@0: uscript_getName(UScriptCode scriptCode);
michael@0: 
michael@0: /**
michael@0:  * Gets a script name associated with the given script code. 
michael@0:  * Returns  "Mlym" given USCRIPT_MALAYALAM
michael@0:  * @param scriptCode UScriptCode enum
michael@0:  * @return script abbreviated name as given in
michael@0:  * PropertyValueAliases.txt, or NULL if scriptCode is invalid
michael@0:  * @stable ICU 2.4
michael@0:  */
michael@0: U_STABLE const char*  U_EXPORT2 
michael@0: uscript_getShortName(UScriptCode scriptCode);
michael@0: 
michael@0: /**
michael@0:  * Gets the script code associated with the given codepoint.
michael@0:  * Returns USCRIPT_MALAYALAM given 0x0D02 
michael@0:  * @param codepoint UChar32 codepoint
michael@0:  * @param err the error status code.
michael@0:  * @return The UScriptCode, or 0 if codepoint is invalid 
michael@0:  * @stable ICU 2.4
michael@0:  */
michael@0: U_STABLE UScriptCode  U_EXPORT2 
michael@0: uscript_getScript(UChar32 codepoint, UErrorCode *err);
michael@0: 
michael@0: /**
michael@0:  * Do the Script_Extensions of code point c contain script sc?
michael@0:  * If c does not have explicit Script_Extensions, then this tests whether
michael@0:  * c has the Script property value sc.
michael@0:  *
michael@0:  * Some characters are commonly used in multiple scripts.
michael@0:  * For more information, see UAX #24: http://www.unicode.org/reports/tr24/.
michael@0:  *
michael@0:  * The Script_Extensions property is provisional. It may be modified or removed
michael@0:  * in future versions of the Unicode Standard, and thus in ICU.
michael@0:  * @param c code point
michael@0:  * @param sc script code
michael@0:  * @return TRUE if sc is in Script_Extensions(c)
michael@0:  * @stable ICU 49
michael@0:  */
michael@0: U_STABLE UBool U_EXPORT2
michael@0: uscript_hasScript(UChar32 c, UScriptCode sc);
michael@0: 
michael@0: /**
michael@0:  * Writes code point c's Script_Extensions as a list of UScriptCode values
michael@0:  * to the output scripts array and returns the number of script codes.
michael@0:  * - If c does have Script_Extensions, then the Script property value
michael@0:  *   (normally Common or Inherited) is not included.
michael@0:  * - If c does not have Script_Extensions, then the one Script code is written to the output array.
michael@0:  * - If c is not a valid code point, then the one USCRIPT_UNKNOWN code is written.
michael@0:  * In other words, if the return value is 1,
michael@0:  * then the output array contains exactly c's single Script code.
michael@0:  * If the return value is n>=2, then the output array contains c's n Script_Extensions script codes.
michael@0:  *
michael@0:  * Some characters are commonly used in multiple scripts.
michael@0:  * For more information, see UAX #24: http://www.unicode.org/reports/tr24/.
michael@0:  *
michael@0:  * If there are more than capacity script codes to be written, then
michael@0:  * U_BUFFER_OVERFLOW_ERROR is set and the number of Script_Extensions is returned.
michael@0:  * (Usual ICU buffer handling behavior.)
michael@0:  *
michael@0:  * The Script_Extensions property is provisional. It may be modified or removed
michael@0:  * in future versions of the Unicode Standard, and thus in ICU.
michael@0:  * @param c code point
michael@0:  * @param scripts output script code array
michael@0:  * @param capacity capacity of the scripts array
michael@0:  * @param errorCode Standard ICU error code. Its input value must
michael@0:  *                  pass the U_SUCCESS() test, or else the function returns
michael@0:  *                  immediately. Check for U_FAILURE() on output or use with
michael@0:  *                  function chaining. (See User Guide for details.)
michael@0:  * @return number of script codes in c's Script_Extensions, or 1 for the single Script value,
michael@0:  *         written to scripts unless U_BUFFER_OVERFLOW_ERROR indicates insufficient capacity
michael@0:  * @stable ICU 49
michael@0:  */
michael@0: U_STABLE int32_t U_EXPORT2
michael@0: uscript_getScriptExtensions(UChar32 c,
michael@0:                             UScriptCode *scripts, int32_t capacity,
michael@0:                             UErrorCode *errorCode);
michael@0: 
michael@0: #ifndef U_HIDE_DRAFT_API
michael@0: 
michael@0: /**
michael@0:  * Script usage constants.
michael@0:  * See UAX #31 Unicode Identifier and Pattern Syntax.
michael@0:  * http://www.unicode.org/reports/tr31/#Table_Candidate_Characters_for_Exclusion_from_Identifiers
michael@0:  *
michael@0:  * @draft ICU 51
michael@0:  */
michael@0: typedef enum UScriptUsage {
michael@0:     /** Not encoded in Unicode. @draft ICU 51 */
michael@0:     USCRIPT_USAGE_NOT_ENCODED,
michael@0:     /** Unknown script usage. @draft ICU 51 */
michael@0:     USCRIPT_USAGE_UNKNOWN,
michael@0:     /** Candidate for Exclusion from Identifiers. @draft ICU 51 */
michael@0:     USCRIPT_USAGE_EXCLUDED,
michael@0:     /** Limited Use script. @draft ICU 51 */
michael@0:     USCRIPT_USAGE_LIMITED_USE,
michael@0:     /** Aspirational Use script. @draft ICU 51 */
michael@0:     USCRIPT_USAGE_ASPIRATIONAL,
michael@0:     /** Recommended script. @draft ICU 51 */
michael@0:     USCRIPT_USAGE_RECOMMENDED
michael@0: } UScriptUsage;
michael@0: 
michael@0: /**
michael@0:  * Writes the script sample character string.
michael@0:  * This string normally consists of one code point but might be longer.
michael@0:  * The string is empty if the script is not encoded.
michael@0:  *
michael@0:  * @param script script code
michael@0:  * @param dest output string array
michael@0:  * @param capacity number of UChars in the dest array
michael@0:  * @param pErrorCode standard ICU in/out error code, must pass U_SUCCESS() on input
michael@0:  * @return the string length, even if U_BUFFER_OVERFLOW_ERROR
michael@0:  * @draft ICU 51
michael@0:  */
michael@0: U_DRAFT int32_t U_EXPORT2
michael@0: uscript_getSampleString(UScriptCode script, UChar *dest, int32_t capacity, UErrorCode *pErrorCode);
michael@0: 
michael@0: #if U_SHOW_CPLUSPLUS_API
michael@0: 
michael@0: U_NAMESPACE_BEGIN
michael@0: class UnicodeString;
michael@0: U_NAMESPACE_END
michael@0: 
michael@0: /**
michael@0:  * Returns the script sample character string.
michael@0:  * This string normally consists of one code point but might be longer.
michael@0:  * The string is empty if the script is not encoded.
michael@0:  *
michael@0:  * @param script script code
michael@0:  * @return the sample character string
michael@0:  * @draft ICU 51
michael@0:  */
michael@0: U_COMMON_API icu::UnicodeString U_EXPORT2
michael@0: uscript_getSampleUnicodeString(UScriptCode script);
michael@0: 
michael@0: #endif
michael@0: 
michael@0: /**
michael@0:  * Returns the script usage according to UAX #31 Unicode Identifier and Pattern Syntax.
michael@0:  * Returns USCRIPT_USAGE_NOT_ENCODED if the script is not encoded in Unicode.
michael@0:  *
michael@0:  * @param script script code
michael@0:  * @return script usage
michael@0:  * @see UScriptUsage
michael@0:  * @draft ICU 51
michael@0:  */
michael@0: U_DRAFT UScriptUsage U_EXPORT2
michael@0: uscript_getUsage(UScriptCode script);
michael@0: 
michael@0: /**
michael@0:  * Returns TRUE if the script is written right-to-left.
michael@0:  * For example, Arab and Hebr.
michael@0:  *
michael@0:  * @param script script code
michael@0:  * @return TRUE if the script is right-to-left
michael@0:  * @draft ICU 51
michael@0:  */
michael@0: U_DRAFT UBool U_EXPORT2
michael@0: uscript_isRightToLeft(UScriptCode script);
michael@0: 
michael@0: /**
michael@0:  * Returns TRUE if the script allows line breaks between letters (excluding hyphenation).
michael@0:  * Such a script typically requires dictionary-based line breaking.
michael@0:  * For example, Hani and Thai.
michael@0:  *
michael@0:  * @param script script code
michael@0:  * @return TRUE if the script allows line breaks between letters
michael@0:  * @draft ICU 51
michael@0:  */
michael@0: U_DRAFT UBool U_EXPORT2
michael@0: uscript_breaksBetweenLetters(UScriptCode script);
michael@0: 
michael@0: /**
michael@0:  * Returns TRUE if in modern (or most recent) usage of the script case distinctions are customary.
michael@0:  * For example, Latn and Cyrl.
michael@0:  *
michael@0:  * @param script script code
michael@0:  * @return TRUE if the script is cased
michael@0:  * @draft ICU 51
michael@0:  */
michael@0: U_DRAFT UBool U_EXPORT2
michael@0: uscript_isCased(UScriptCode script);
michael@0: 
michael@0: #endif  /* U_HIDE_DRAFT_API */
michael@0: 
michael@0: #endif