|
1 /* |
|
2 ********************************************************************** |
|
3 * Copyright (C) 1997-2004, 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 #ifndef USCRIPT_H |
|
16 #define USCRIPT_H |
|
17 #include "unicode/utypes.h" |
|
18 |
|
19 /** |
|
20 * Constants for Unicode script values from ScriptNames.txt . |
|
21 * |
|
22 * @stable ICU 2.2 |
|
23 */ |
|
24 typedef enum UScriptCode { |
|
25 USCRIPT_INVALID_CODE = -1, |
|
26 USCRIPT_COMMON = 0 , /* Zyyy */ |
|
27 USCRIPT_INHERITED = 1, /* Qaai */ |
|
28 USCRIPT_ARABIC = 2, /* Arab */ |
|
29 USCRIPT_ARMENIAN = 3, /* Armn */ |
|
30 USCRIPT_BENGALI = 4, /* Beng */ |
|
31 USCRIPT_BOPOMOFO = 5, /* Bopo */ |
|
32 USCRIPT_CHEROKEE = 6, /* Cher */ |
|
33 USCRIPT_COPTIC = 7, /* Copt */ |
|
34 USCRIPT_CYRILLIC = 8, /* Cyrl (Cyrs) */ |
|
35 USCRIPT_DESERET = 9, /* Dsrt */ |
|
36 USCRIPT_DEVANAGARI = 10, /* Deva */ |
|
37 USCRIPT_ETHIOPIC = 11, /* Ethi */ |
|
38 USCRIPT_GEORGIAN = 12, /* Geor (Geon, Geoa) */ |
|
39 USCRIPT_GOTHIC = 13, /* Goth */ |
|
40 USCRIPT_GREEK = 14, /* Grek */ |
|
41 USCRIPT_GUJARATI = 15, /* Gujr */ |
|
42 USCRIPT_GURMUKHI = 16, /* Guru */ |
|
43 USCRIPT_HAN = 17, /* Hani */ |
|
44 USCRIPT_HANGUL = 18, /* Hang */ |
|
45 USCRIPT_HEBREW = 19, /* Hebr */ |
|
46 USCRIPT_HIRAGANA = 20, /* Hira */ |
|
47 USCRIPT_KANNADA = 21, /* Knda */ |
|
48 USCRIPT_KATAKANA = 22, /* Kana */ |
|
49 USCRIPT_KHMER = 23, /* Khmr */ |
|
50 USCRIPT_LAO = 24, /* Laoo */ |
|
51 USCRIPT_LATIN = 25, /* Latn (Latf, Latg) */ |
|
52 USCRIPT_MALAYALAM = 26, /* Mlym */ |
|
53 USCRIPT_MONGOLIAN = 27, /* Mong */ |
|
54 USCRIPT_MYANMAR = 28, /* Mymr */ |
|
55 USCRIPT_OGHAM = 29, /* Ogam */ |
|
56 USCRIPT_OLD_ITALIC = 30, /* Ital */ |
|
57 USCRIPT_ORIYA = 31, /* Orya */ |
|
58 USCRIPT_RUNIC = 32, /* Runr */ |
|
59 USCRIPT_SINHALA = 33, /* Sinh */ |
|
60 USCRIPT_SYRIAC = 34, /* Syrc (Syrj, Syrn, Syre) */ |
|
61 USCRIPT_TAMIL = 35, /* Taml */ |
|
62 USCRIPT_TELUGU = 36, /* Telu */ |
|
63 USCRIPT_THAANA = 37, /* Thaa */ |
|
64 USCRIPT_THAI = 38, /* Thai */ |
|
65 USCRIPT_TIBETAN = 39, /* Tibt */ |
|
66 /** Canadian_Aboriginal script. @stable ICU 2.6 */ |
|
67 USCRIPT_CANADIAN_ABORIGINAL = 40, /* Cans */ |
|
68 /** Canadian_Aboriginal script (alias). @stable ICU 2.2 */ |
|
69 USCRIPT_UCAS = USCRIPT_CANADIAN_ABORIGINAL, |
|
70 USCRIPT_YI = 41, /* Yiii */ |
|
71 USCRIPT_TAGALOG = 42, /* Tglg */ |
|
72 USCRIPT_HANUNOO = 43, /* Hano */ |
|
73 USCRIPT_BUHID = 44, /* Buhd */ |
|
74 USCRIPT_TAGBANWA = 45, /* Tagb */ |
|
75 |
|
76 /* New scripts in Unicode 4 @stable ICU 2.6 */ |
|
77 USCRIPT_BRAILLE, /* Brai */ |
|
78 USCRIPT_CYPRIOT, /* Cprt */ |
|
79 USCRIPT_LIMBU, /* Limb */ |
|
80 USCRIPT_LINEAR_B, /* Linb */ |
|
81 USCRIPT_OSMANYA, /* Osma */ |
|
82 USCRIPT_SHAVIAN, /* Shaw */ |
|
83 USCRIPT_TAI_LE, /* Tale */ |
|
84 USCRIPT_UGARITIC, /* Ugar */ |
|
85 |
|
86 /** New script code in Unicode 4.0.1 @draft ICU 3.0 */ |
|
87 USCRIPT_KATAKANA_OR_HIRAGANA,/*Hrkt */ |
|
88 |
|
89 USCRIPT_CODE_LIMIT |
|
90 } UScriptCode; |
|
91 |
|
92 /** |
|
93 * Gets script codes associated with the given locale or ISO 15924 abbreviation or name. |
|
94 * Fills in USCRIPT_MALAYALAM given "Malayam" OR "Mlym". |
|
95 * Fills in USCRIPT_LATIN given "en" OR "en_US" |
|
96 * If required capacity is greater than capacity of the destination buffer then the error code |
|
97 * is set to U_BUFFER_OVERFLOW_ERROR and the required capacity is returned |
|
98 * |
|
99 * <p>Note: To search by short or long script alias only, use |
|
100 * u_getPropertyValueEnum(UCHAR_SCRIPT, alias) instead. This does |
|
101 * a fast lookup with no access of the locale data. |
|
102 * @param nameOrAbbrOrLocale name of the script, as given in |
|
103 * PropertyValueAliases.txt, or ISO 15924 code or locale |
|
104 * @param fillIn the UScriptCode buffer to fill in the script code |
|
105 * @param capacity the capacity (size) fo UScriptCode buffer passed in. |
|
106 * @param err the error status code. |
|
107 * @return The number of script codes filled in the buffer passed in |
|
108 * @stable ICU 2.4 |
|
109 */ |
|
110 U_STABLE int32_t U_EXPORT2 |
|
111 uscript_getCode(const char* nameOrAbbrOrLocale,UScriptCode* fillIn,int32_t capacity,UErrorCode *err); |
|
112 |
|
113 /** |
|
114 * Gets a script name associated with the given script code. |
|
115 * Returns "Malayam" given USCRIPT_MALAYALAM |
|
116 * @param scriptCode UScriptCode enum |
|
117 * @return script long name as given in |
|
118 * PropertyValueAliases.txt, or NULL if scriptCode is invalid |
|
119 * @stable ICU 2.4 |
|
120 */ |
|
121 U_STABLE const char* U_EXPORT2 |
|
122 uscript_getName(UScriptCode scriptCode); |
|
123 |
|
124 /** |
|
125 * Gets a script name associated with the given script code. |
|
126 * Returns "Mlym" given USCRIPT_MALAYALAM |
|
127 * @param scriptCode UScriptCode enum |
|
128 * @return script abbreviated name as given in |
|
129 * PropertyValueAliases.txt, or NULL if scriptCode is invalid |
|
130 * @stable ICU 2.4 |
|
131 */ |
|
132 U_STABLE const char* U_EXPORT2 |
|
133 uscript_getShortName(UScriptCode scriptCode); |
|
134 |
|
135 /** |
|
136 * Gets the script code associated with the given codepoint. |
|
137 * Returns USCRIPT_MALAYALAM given 0x0D02 |
|
138 * @param codepoint UChar32 codepoint |
|
139 * @param err the error status code. |
|
140 * @return The UScriptCode, or 0 if codepoint is invalid |
|
141 * @stable ICU 2.4 |
|
142 */ |
|
143 U_STABLE UScriptCode U_EXPORT2 |
|
144 uscript_getScript(UChar32 codepoint, UErrorCode *err); |
|
145 |
|
146 #endif |
|
147 |
|
148 |