2 * Copyright (C) 1997-2006, International Business Machines
3 * Corporation and others. All Rights Reserved.
6 #ifndef WTF_ScriptCodesFromICU_h
7 #define WTF_ScriptCodesFromICU_h
10 * Constants for ISO 15924 script codes.
12 * Many of these script codes - those from Unicode's ScriptNames.txt -
13 * are character property values for Unicode's Script property.
14 * See UAX #24 Script Names (http://www.unicode.org/reports/tr24/).
16 * Starting with ICU 3.6, constants for most ISO 15924 script codes
17 * are included (currently excluding private-use codes Qaaa..Qabx).
18 * For scripts for which there are codes in ISO 15924 but which are not
19 * used in the Unicode Character Database (UCD), there are no Unicode characters
20 * associated with those scripts.
22 * For example, there are no characters that have a UCD script code of
23 * Hans or Hant. All Han ideographs have the Hani script code.
24 * The Hans and Hant script codes are used with CLDR data.
26 * ISO 15924 script codes are included for use with CLDR and similar.
30 typedef enum UScriptCode {
31 USCRIPT_INVALID_CODE = -1,
32 USCRIPT_COMMON = 0 , /* Zyyy */
33 USCRIPT_INHERITED = 1, /* Qaai */
34 USCRIPT_ARABIC = 2, /* Arab */
35 USCRIPT_ARMENIAN = 3, /* Armn */
36 USCRIPT_BENGALI = 4, /* Beng */
37 USCRIPT_BOPOMOFO = 5, /* Bopo */
38 USCRIPT_CHEROKEE = 6, /* Cher */
39 USCRIPT_COPTIC = 7, /* Copt */
40 USCRIPT_CYRILLIC = 8, /* Cyrl */
41 USCRIPT_DESERET = 9, /* Dsrt */
42 USCRIPT_DEVANAGARI = 10, /* Deva */
43 USCRIPT_ETHIOPIC = 11, /* Ethi */
44 USCRIPT_GEORGIAN = 12, /* Geor */
45 USCRIPT_GOTHIC = 13, /* Goth */
46 USCRIPT_GREEK = 14, /* Grek */
47 USCRIPT_GUJARATI = 15, /* Gujr */
48 USCRIPT_GURMUKHI = 16, /* Guru */
49 USCRIPT_HAN = 17, /* Hani */
50 USCRIPT_HANGUL = 18, /* Hang */
51 USCRIPT_HEBREW = 19, /* Hebr */
52 USCRIPT_HIRAGANA = 20, /* Hira */
53 USCRIPT_KANNADA = 21, /* Knda */
54 USCRIPT_KATAKANA = 22, /* Kana */
55 USCRIPT_KHMER = 23, /* Khmr */
56 USCRIPT_LAO = 24, /* Laoo */
57 USCRIPT_LATIN = 25, /* Latn */
58 USCRIPT_MALAYALAM = 26, /* Mlym */
59 USCRIPT_MONGOLIAN = 27, /* Mong */
60 USCRIPT_MYANMAR = 28, /* Mymr */
61 USCRIPT_OGHAM = 29, /* Ogam */
62 USCRIPT_OLD_ITALIC = 30, /* Ital */
63 USCRIPT_ORIYA = 31, /* Orya */
64 USCRIPT_RUNIC = 32, /* Runr */
65 USCRIPT_SINHALA = 33, /* Sinh */
66 USCRIPT_SYRIAC = 34, /* Syrc */
67 USCRIPT_TAMIL = 35, /* Taml */
68 USCRIPT_TELUGU = 36, /* Telu */
69 USCRIPT_THAANA = 37, /* Thaa */
70 USCRIPT_THAI = 38, /* Thai */
71 USCRIPT_TIBETAN = 39, /* Tibt */
72 /** Canadian_Aboriginal script. @stable ICU 2.6 */
73 USCRIPT_CANADIAN_ABORIGINAL = 40, /* Cans */
74 /** Canadian_Aboriginal script (alias). @stable ICU 2.2 */
75 USCRIPT_UCAS = USCRIPT_CANADIAN_ABORIGINAL,
76 USCRIPT_YI = 41, /* Yiii */
77 USCRIPT_TAGALOG = 42, /* Tglg */
78 USCRIPT_HANUNOO = 43, /* Hano */
79 USCRIPT_BUHID = 44, /* Buhd */
80 USCRIPT_TAGBANWA = 45, /* Tagb */
82 /* New scripts in Unicode 4 @stable ICU 2.6 */
83 USCRIPT_BRAILLE = 46, /* Brai */
84 USCRIPT_CYPRIOT = 47, /* Cprt */
85 USCRIPT_LIMBU = 48, /* Limb */
86 USCRIPT_LINEAR_B = 49, /* Linb */
87 USCRIPT_OSMANYA = 50, /* Osma */
88 USCRIPT_SHAVIAN = 51, /* Shaw */
89 USCRIPT_TAI_LE = 52, /* Tale */
90 USCRIPT_UGARITIC = 53, /* Ugar */
92 /** New script code in Unicode 4.0.1 @stable ICU 3.0 */
93 USCRIPT_KATAKANA_OR_HIRAGANA = 54,/*Hrkt */
95 #ifndef U_HIDE_DRAFT_API
96 /* New scripts in Unicode 4.1 @draft ICU 3.4 */
97 USCRIPT_BUGINESE = 55, /* Bugi */
98 USCRIPT_GLAGOLITIC = 56, /* Glag */
99 USCRIPT_KHAROSHTHI = 57, /* Khar */
100 USCRIPT_SYLOTI_NAGRI = 58, /* Sylo */
101 USCRIPT_NEW_TAI_LUE = 59, /* Talu */
102 USCRIPT_TIFINAGH = 60, /* Tfng */
103 USCRIPT_OLD_PERSIAN = 61, /* Xpeo */
105 /* New script codes from ISO 15924 @draft ICU 3.6 */
106 USCRIPT_BALINESE = 62, /* Bali */
107 USCRIPT_BATAK = 63, /* Batk */
108 USCRIPT_BLISSYMBOLS = 64, /* Blis */
109 USCRIPT_BRAHMI = 65, /* Brah */
110 USCRIPT_CHAM = 66, /* Cham */
111 USCRIPT_CIRTH = 67, /* Cirt */
112 USCRIPT_OLD_CHURCH_SLAVONIC_CYRILLIC = 68, /* Cyrs */
113 USCRIPT_DEMOTIC_EGYPTIAN = 69, /* Egyd */
114 USCRIPT_HIERATIC_EGYPTIAN = 70, /* Egyh */
115 USCRIPT_EGYPTIAN_HIEROGLYPHS = 71, /* Egyp */
116 USCRIPT_KHUTSURI = 72, /* Geok */
117 USCRIPT_SIMPLIFIED_HAN = 73, /* Hans */
118 USCRIPT_TRADITIONAL_HAN = 74, /* Hant */
119 USCRIPT_PAHAWH_HMONG = 75, /* Hmng */
120 USCRIPT_OLD_HUNGARIAN = 76, /* Hung */
121 USCRIPT_HARAPPAN_INDUS = 77, /* Inds */
122 USCRIPT_JAVANESE = 78, /* Java */
123 USCRIPT_KAYAH_LI = 79, /* Kali */
124 USCRIPT_LATIN_FRAKTUR = 80, /* Latf */
125 USCRIPT_LATIN_GAELIC = 81, /* Latg */
126 USCRIPT_LEPCHA = 82, /* Lepc */
127 USCRIPT_LINEAR_A = 83, /* Lina */
128 USCRIPT_MANDAEAN = 84, /* Mand */
129 USCRIPT_MAYAN_HIEROGLYPHS = 85, /* Maya */
130 USCRIPT_MEROITIC = 86, /* Mero */
131 USCRIPT_NKO = 87, /* Nkoo */
132 USCRIPT_ORKHON = 88, /* Orkh */
133 USCRIPT_OLD_PERMIC = 89, /* Perm */
134 USCRIPT_PHAGS_PA = 90, /* Phag */
135 USCRIPT_PHOENICIAN = 91, /* Phnx */
136 USCRIPT_PHONETIC_POLLARD = 92, /* Plrd */
137 USCRIPT_RONGORONGO = 93, /* Roro */
138 USCRIPT_SARATI = 94, /* Sara */
139 USCRIPT_ESTRANGELO_SYRIAC = 95, /* Syre */
140 USCRIPT_WESTERN_SYRIAC = 96, /* Syrj */
141 USCRIPT_EASTERN_SYRIAC = 97, /* Syrn */
142 USCRIPT_TENGWAR = 98, /* Teng */
143 USCRIPT_VAI = 99, /* Vaii */
144 USCRIPT_VISIBLE_SPEECH = 100, /* Visp */
145 USCRIPT_CUNEIFORM = 101,/* Xsux */
146 USCRIPT_UNWRITTEN_LANGUAGES = 102,/* Zxxx */
147 USCRIPT_UNKNOWN = 103,/* Zzzz */ /* Unknown="Code for uncoded script", for unassigned code points */
148 /* Private use codes from Qaaa - Qabx are not supported*/
149 #endif /* U_HIDE_DRAFT_API */
150 USCRIPT_CODE_LIMIT = 104
projects / vuplus_webkit / blob