|
sl@0
|
1 |
/*
|
|
sl@0
|
2 |
**********************************************************************
|
|
sl@0
|
3 |
* Copyright (C) 1997-2005, International Business Machines
|
|
sl@0
|
4 |
* Corporation and others. All Rights Reserved.
|
|
sl@0
|
5 |
**********************************************************************
|
|
sl@0
|
6 |
*
|
|
sl@0
|
7 |
* File USCRIPT.H
|
|
sl@0
|
8 |
*
|
|
sl@0
|
9 |
* Modification History:
|
|
sl@0
|
10 |
*
|
|
sl@0
|
11 |
* Date Name Description
|
|
sl@0
|
12 |
* 07/06/2001 Ram Creation.
|
|
sl@0
|
13 |
******************************************************************************
|
|
sl@0
|
14 |
*/
|
|
sl@0
|
15 |
#ifndef USCRIPT_H
|
|
sl@0
|
16 |
#define USCRIPT_H
|
|
sl@0
|
17 |
#include "unicode/utypes.h"
|
|
sl@0
|
18 |
|
|
sl@0
|
19 |
/**
|
|
sl@0
|
20 |
* \file
|
|
sl@0
|
21 |
* \brief C API: Unicode Script Information
|
|
sl@0
|
22 |
*/
|
|
sl@0
|
23 |
|
|
sl@0
|
24 |
/**
|
|
sl@0
|
25 |
* Constants for Unicode script values from ScriptNames.txt.
|
|
sl@0
|
26 |
*
|
|
sl@0
|
27 |
* @stable ICU 2.2
|
|
sl@0
|
28 |
*/
|
|
sl@0
|
29 |
typedef enum UScriptCode {
|
|
sl@0
|
30 |
USCRIPT_INVALID_CODE = -1,
|
|
sl@0
|
31 |
USCRIPT_COMMON = 0 , /* Zyyy */
|
|
sl@0
|
32 |
USCRIPT_INHERITED = 1, /* Qaai */
|
|
sl@0
|
33 |
USCRIPT_ARABIC = 2, /* Arab */
|
|
sl@0
|
34 |
USCRIPT_ARMENIAN = 3, /* Armn */
|
|
sl@0
|
35 |
USCRIPT_BENGALI = 4, /* Beng */
|
|
sl@0
|
36 |
USCRIPT_BOPOMOFO = 5, /* Bopo */
|
|
sl@0
|
37 |
USCRIPT_CHEROKEE = 6, /* Cher */
|
|
sl@0
|
38 |
USCRIPT_COPTIC = 7, /* Copt */
|
|
sl@0
|
39 |
USCRIPT_CYRILLIC = 8, /* Cyrl (Cyrs) */
|
|
sl@0
|
40 |
USCRIPT_DESERET = 9, /* Dsrt */
|
|
sl@0
|
41 |
USCRIPT_DEVANAGARI = 10, /* Deva */
|
|
sl@0
|
42 |
USCRIPT_ETHIOPIC = 11, /* Ethi */
|
|
sl@0
|
43 |
USCRIPT_GEORGIAN = 12, /* Geor (Geon, Geoa) */
|
|
sl@0
|
44 |
USCRIPT_GOTHIC = 13, /* Goth */
|
|
sl@0
|
45 |
USCRIPT_GREEK = 14, /* Grek */
|
|
sl@0
|
46 |
USCRIPT_GUJARATI = 15, /* Gujr */
|
|
sl@0
|
47 |
USCRIPT_GURMUKHI = 16, /* Guru */
|
|
sl@0
|
48 |
USCRIPT_HAN = 17, /* Hani */
|
|
sl@0
|
49 |
USCRIPT_HANGUL = 18, /* Hang */
|
|
sl@0
|
50 |
USCRIPT_HEBREW = 19, /* Hebr */
|
|
sl@0
|
51 |
USCRIPT_HIRAGANA = 20, /* Hira */
|
|
sl@0
|
52 |
USCRIPT_KANNADA = 21, /* Knda */
|
|
sl@0
|
53 |
USCRIPT_KATAKANA = 22, /* Kana */
|
|
sl@0
|
54 |
USCRIPT_KHMER = 23, /* Khmr */
|
|
sl@0
|
55 |
USCRIPT_LAO = 24, /* Laoo */
|
|
sl@0
|
56 |
USCRIPT_LATIN = 25, /* Latn (Latf, Latg) */
|
|
sl@0
|
57 |
USCRIPT_MALAYALAM = 26, /* Mlym */
|
|
sl@0
|
58 |
USCRIPT_MONGOLIAN = 27, /* Mong */
|
|
sl@0
|
59 |
USCRIPT_MYANMAR = 28, /* Mymr */
|
|
sl@0
|
60 |
USCRIPT_OGHAM = 29, /* Ogam */
|
|
sl@0
|
61 |
USCRIPT_OLD_ITALIC = 30, /* Ital */
|
|
sl@0
|
62 |
USCRIPT_ORIYA = 31, /* Orya */
|
|
sl@0
|
63 |
USCRIPT_RUNIC = 32, /* Runr */
|
|
sl@0
|
64 |
USCRIPT_SINHALA = 33, /* Sinh */
|
|
sl@0
|
65 |
USCRIPT_SYRIAC = 34, /* Syrc (Syrj, Syrn, Syre) */
|
|
sl@0
|
66 |
USCRIPT_TAMIL = 35, /* Taml */
|
|
sl@0
|
67 |
USCRIPT_TELUGU = 36, /* Telu */
|
|
sl@0
|
68 |
USCRIPT_THAANA = 37, /* Thaa */
|
|
sl@0
|
69 |
USCRIPT_THAI = 38, /* Thai */
|
|
sl@0
|
70 |
USCRIPT_TIBETAN = 39, /* Tibt */
|
|
sl@0
|
71 |
/** Canadian_Aboriginal script. @stable ICU 2.6 */
|
|
sl@0
|
72 |
USCRIPT_CANADIAN_ABORIGINAL = 40, /* Cans */
|
|
sl@0
|
73 |
/** Canadian_Aboriginal script (alias). @stable ICU 2.2 */
|
|
sl@0
|
74 |
USCRIPT_UCAS = USCRIPT_CANADIAN_ABORIGINAL,
|
|
sl@0
|
75 |
USCRIPT_YI = 41, /* Yiii */
|
|
sl@0
|
76 |
USCRIPT_TAGALOG = 42, /* Tglg */
|
|
sl@0
|
77 |
USCRIPT_HANUNOO = 43, /* Hano */
|
|
sl@0
|
78 |
USCRIPT_BUHID = 44, /* Buhd */
|
|
sl@0
|
79 |
USCRIPT_TAGBANWA = 45, /* Tagb */
|
|
sl@0
|
80 |
|
|
sl@0
|
81 |
/* New scripts in Unicode 4 @stable ICU 2.6 */
|
|
sl@0
|
82 |
USCRIPT_BRAILLE, /* Brai */
|
|
sl@0
|
83 |
USCRIPT_CYPRIOT, /* Cprt */
|
|
sl@0
|
84 |
USCRIPT_LIMBU, /* Limb */
|
|
sl@0
|
85 |
USCRIPT_LINEAR_B, /* Linb */
|
|
sl@0
|
86 |
USCRIPT_OSMANYA, /* Osma */
|
|
sl@0
|
87 |
USCRIPT_SHAVIAN, /* Shaw */
|
|
sl@0
|
88 |
USCRIPT_TAI_LE, /* Tale */
|
|
sl@0
|
89 |
USCRIPT_UGARITIC, /* Ugar */
|
|
sl@0
|
90 |
|
|
sl@0
|
91 |
/** New script code in Unicode 4.0.1 @draft ICU 3.0 */
|
|
sl@0
|
92 |
USCRIPT_KATAKANA_OR_HIRAGANA,/*Hrkt */
|
|
sl@0
|
93 |
|
|
sl@0
|
94 |
/* New scripts in Unicode 4.1 @draft ICU 3.4 */
|
|
sl@0
|
95 |
USCRIPT_BUGINESE, /* Bugi */
|
|
sl@0
|
96 |
USCRIPT_GLAGOLITIC, /* Glag */
|
|
sl@0
|
97 |
USCRIPT_KHAROSHTHI, /* Khar */
|
|
sl@0
|
98 |
USCRIPT_SYLOTI_NAGRI, /* Sylo */
|
|
sl@0
|
99 |
USCRIPT_NEW_TAI_LUE, /* Talu */
|
|
sl@0
|
100 |
USCRIPT_TIFINAGH, /* Tfng */
|
|
sl@0
|
101 |
USCRIPT_OLD_PERSIAN, /* Xpeo */
|
|
sl@0
|
102 |
|
|
sl@0
|
103 |
USCRIPT_CODE_LIMIT
|
|
sl@0
|
104 |
} UScriptCode;
|
|
sl@0
|
105 |
|
|
sl@0
|
106 |
/**
|
|
sl@0
|
107 |
* Gets script codes associated with the given locale or ISO 15924 abbreviation or name.
|
|
sl@0
|
108 |
* Fills in USCRIPT_MALAYALAM given "Malayam" OR "Mlym".
|
|
sl@0
|
109 |
* Fills in USCRIPT_LATIN given "en" OR "en_US"
|
|
sl@0
|
110 |
* If required capacity is greater than capacity of the destination buffer then the error code
|
|
sl@0
|
111 |
* is set to U_BUFFER_OVERFLOW_ERROR and the required capacity is returned
|
|
sl@0
|
112 |
*
|
|
sl@0
|
113 |
* <p>Note: To search by short or long script alias only, use
|
|
sl@0
|
114 |
* u_getPropertyValueEnum(UCHAR_SCRIPT, alias) instead. This does
|
|
sl@0
|
115 |
* a fast lookup with no access of the locale data.
|
|
sl@0
|
116 |
* @param nameOrAbbrOrLocale name of the script, as given in
|
|
sl@0
|
117 |
* PropertyValueAliases.txt, or ISO 15924 code or locale
|
|
sl@0
|
118 |
* @param fillIn the UScriptCode buffer to fill in the script code
|
|
sl@0
|
119 |
* @param capacity the capacity (size) fo UScriptCode buffer passed in.
|
|
sl@0
|
120 |
* @param err the error status code.
|
|
sl@0
|
121 |
* @return The number of script codes filled in the buffer passed in
|
|
sl@0
|
122 |
* @stable ICU 2.4
|
|
sl@0
|
123 |
*/
|
|
sl@0
|
124 |
U_STABLE int32_t U_EXPORT2
|
|
sl@0
|
125 |
uscript_getCode(const char* nameOrAbbrOrLocale,UScriptCode* fillIn,int32_t capacity,UErrorCode *err);
|
|
sl@0
|
126 |
|
|
sl@0
|
127 |
/**
|
|
sl@0
|
128 |
* Gets a script name associated with the given script code.
|
|
sl@0
|
129 |
* Returns "Malayam" given USCRIPT_MALAYALAM
|
|
sl@0
|
130 |
* @param scriptCode UScriptCode enum
|
|
sl@0
|
131 |
* @return script long name as given in
|
|
sl@0
|
132 |
* PropertyValueAliases.txt, or NULL if scriptCode is invalid
|
|
sl@0
|
133 |
* @stable ICU 2.4
|
|
sl@0
|
134 |
*/
|
|
sl@0
|
135 |
U_STABLE const char* U_EXPORT2
|
|
sl@0
|
136 |
uscript_getName(UScriptCode scriptCode);
|
|
sl@0
|
137 |
|
|
sl@0
|
138 |
/**
|
|
sl@0
|
139 |
* Gets a script name associated with the given script code.
|
|
sl@0
|
140 |
* Returns "Mlym" given USCRIPT_MALAYALAM
|
|
sl@0
|
141 |
* @param scriptCode UScriptCode enum
|
|
sl@0
|
142 |
* @return script abbreviated name as given in
|
|
sl@0
|
143 |
* PropertyValueAliases.txt, or NULL if scriptCode is invalid
|
|
sl@0
|
144 |
* @stable ICU 2.4
|
|
sl@0
|
145 |
*/
|
|
sl@0
|
146 |
U_STABLE const char* U_EXPORT2
|
|
sl@0
|
147 |
uscript_getShortName(UScriptCode scriptCode);
|
|
sl@0
|
148 |
|
|
sl@0
|
149 |
/**
|
|
sl@0
|
150 |
* Gets the script code associated with the given codepoint.
|
|
sl@0
|
151 |
* Returns USCRIPT_MALAYALAM given 0x0D02
|
|
sl@0
|
152 |
* @param codepoint UChar32 codepoint
|
|
sl@0
|
153 |
* @param err the error status code.
|
|
sl@0
|
154 |
* @return The UScriptCode, or 0 if codepoint is invalid
|
|
sl@0
|
155 |
* @stable ICU 2.4
|
|
sl@0
|
156 |
*/
|
|
sl@0
|
157 |
U_STABLE UScriptCode U_EXPORT2
|
|
sl@0
|
158 |
uscript_getScript(UChar32 codepoint, UErrorCode *err);
|
|
sl@0
|
159 |
|
|
sl@0
|
160 |
#endif
|
|
sl@0
|
161 |
|
|
sl@0
|
162 |
|