ICU 4.8.1.1  4.8.1.1
 All Data Structures Files Functions Variables Typedefs Enumerations Enumerator Friends Macros Groups Pages
uscript.h
Go to the documentation of this file.
1 /*
2  **********************************************************************
3  * Copyright (C) 1997-2011, 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 
16 #ifndef USCRIPT_H
17 #define USCRIPT_H
18 #include "unicode/utypes.h"
19 
46 typedef enum UScriptCode {
50  USCRIPT_COMMON = 0, /* Zyyy */
52  USCRIPT_INHERITED = 1, /* Zinh */ /* "Code for inherited script", for non-spacing combining marks; also Qaai */
54  USCRIPT_ARABIC = 2, /* Arab */
56  USCRIPT_ARMENIAN = 3, /* Armn */
58  USCRIPT_BENGALI = 4, /* Beng */
60  USCRIPT_BOPOMOFO = 5, /* Bopo */
62  USCRIPT_CHEROKEE = 6, /* Cher */
64  USCRIPT_COPTIC = 7, /* Copt */
66  USCRIPT_CYRILLIC = 8, /* Cyrl */
68  USCRIPT_DESERET = 9, /* Dsrt */
70  USCRIPT_DEVANAGARI = 10, /* Deva */
72  USCRIPT_ETHIOPIC = 11, /* Ethi */
74  USCRIPT_GEORGIAN = 12, /* Geor */
76  USCRIPT_GOTHIC = 13, /* Goth */
78  USCRIPT_GREEK = 14, /* Grek */
80  USCRIPT_GUJARATI = 15, /* Gujr */
82  USCRIPT_GURMUKHI = 16, /* Guru */
84  USCRIPT_HAN = 17, /* Hani */
86  USCRIPT_HANGUL = 18, /* Hang */
88  USCRIPT_HEBREW = 19, /* Hebr */
90  USCRIPT_HIRAGANA = 20, /* Hira */
92  USCRIPT_KANNADA = 21, /* Knda */
94  USCRIPT_KATAKANA = 22, /* Kana */
96  USCRIPT_KHMER = 23, /* Khmr */
98  USCRIPT_LAO = 24, /* Laoo */
100  USCRIPT_LATIN = 25, /* Latn */
102  USCRIPT_MALAYALAM = 26, /* Mlym */
104  USCRIPT_MONGOLIAN = 27, /* Mong */
106  USCRIPT_MYANMAR = 28, /* Mymr */
108  USCRIPT_OGHAM = 29, /* Ogam */
110  USCRIPT_OLD_ITALIC = 30, /* Ital */
112  USCRIPT_ORIYA = 31, /* Orya */
114  USCRIPT_RUNIC = 32, /* Runr */
116  USCRIPT_SINHALA = 33, /* Sinh */
118  USCRIPT_SYRIAC = 34, /* Syrc */
120  USCRIPT_TAMIL = 35, /* Taml */
122  USCRIPT_TELUGU = 36, /* Telu */
124  USCRIPT_THAANA = 37, /* Thaa */
126  USCRIPT_THAI = 38, /* Thai */
128  USCRIPT_TIBETAN = 39, /* Tibt */
134  USCRIPT_YI = 41, /* Yiii */
135  /* New scripts in Unicode 3.2 */
137  USCRIPT_TAGALOG = 42, /* Tglg */
139  USCRIPT_HANUNOO = 43, /* Hano */
141  USCRIPT_BUHID = 44, /* Buhd */
143  USCRIPT_TAGBANWA = 45, /* Tagb */
144 
145  /* New scripts in Unicode 4 */
147  USCRIPT_BRAILLE = 46, /* Brai */
149  USCRIPT_CYPRIOT = 47, /* Cprt */
151  USCRIPT_LIMBU = 48, /* Limb */
153  USCRIPT_LINEAR_B = 49, /* Linb */
155  USCRIPT_OSMANYA = 50, /* Osma */
157  USCRIPT_SHAVIAN = 51, /* Shaw */
159  USCRIPT_TAI_LE = 52, /* Tale */
161  USCRIPT_UGARITIC = 53, /* Ugar */
162 
165 
166  /* New scripts in Unicode 4.1 */
168  USCRIPT_BUGINESE = 55, /* Bugi */
170  USCRIPT_GLAGOLITIC = 56, /* Glag */
172  USCRIPT_KHAROSHTHI = 57, /* Khar */
174  USCRIPT_SYLOTI_NAGRI = 58, /* Sylo */
176  USCRIPT_NEW_TAI_LUE = 59, /* Talu */
178  USCRIPT_TIFINAGH = 60, /* Tfng */
180  USCRIPT_OLD_PERSIAN = 61, /* Xpeo */
181 
182  /* New script codes from ISO 15924 */
184  USCRIPT_BALINESE = 62, /* Bali */
186  USCRIPT_BATAK = 63, /* Batk */
188  USCRIPT_BLISSYMBOLS = 64, /* Blis */
190  USCRIPT_BRAHMI = 65, /* Brah */
192  USCRIPT_CHAM = 66, /* Cham */
194  USCRIPT_CIRTH = 67, /* Cirt */
198  USCRIPT_DEMOTIC_EGYPTIAN = 69, /* Egyd */
200  USCRIPT_HIERATIC_EGYPTIAN = 70, /* Egyh */
204  USCRIPT_KHUTSURI = 72, /* Geok */
206  USCRIPT_SIMPLIFIED_HAN = 73, /* Hans */
208  USCRIPT_TRADITIONAL_HAN = 74, /* Hant */
210  USCRIPT_PAHAWH_HMONG = 75, /* Hmng */
212  USCRIPT_OLD_HUNGARIAN = 76, /* Hung */
214  USCRIPT_HARAPPAN_INDUS = 77, /* Inds */
216  USCRIPT_JAVANESE = 78, /* Java */
218  USCRIPT_KAYAH_LI = 79, /* Kali */
220  USCRIPT_LATIN_FRAKTUR = 80, /* Latf */
222  USCRIPT_LATIN_GAELIC = 81, /* Latg */
224  USCRIPT_LEPCHA = 82, /* Lepc */
226  USCRIPT_LINEAR_A = 83, /* Lina */
228  USCRIPT_MANDAIC = 84, /* Mand */
232  USCRIPT_MAYAN_HIEROGLYPHS = 85, /* Maya */
238  USCRIPT_NKO = 87, /* Nkoo */
240  USCRIPT_ORKHON = 88, /* Orkh */
242  USCRIPT_OLD_PERMIC = 89, /* Perm */
244  USCRIPT_PHAGS_PA = 90, /* Phag */
246  USCRIPT_PHOENICIAN = 91, /* Phnx */
248  USCRIPT_PHONETIC_POLLARD = 92, /* Plrd */
250  USCRIPT_RONGORONGO = 93, /* Roro */
252  USCRIPT_SARATI = 94, /* Sara */
254  USCRIPT_ESTRANGELO_SYRIAC = 95, /* Syre */
256  USCRIPT_WESTERN_SYRIAC = 96, /* Syrj */
258  USCRIPT_EASTERN_SYRIAC = 97, /* Syrn */
260  USCRIPT_TENGWAR = 98, /* Teng */
262  USCRIPT_VAI = 99, /* Vaii */
264  USCRIPT_VISIBLE_SPEECH = 100,/* Visp */
266  USCRIPT_CUNEIFORM = 101,/* Xsux */
270  USCRIPT_UNKNOWN = 103,/* Zzzz */ /* Unknown="Code for uncoded script", for unassigned code points */
271 
272  /* New script codes from ISO 15924 */
274  USCRIPT_CARIAN = 104,/* Cari */
276  USCRIPT_JAPANESE = 105,/* Jpan */
278  USCRIPT_LANNA = 106,/* Lana */
280  USCRIPT_LYCIAN = 107,/* Lyci */
282  USCRIPT_LYDIAN = 108,/* Lydi */
284  USCRIPT_OL_CHIKI = 109,/* Olck */
286  USCRIPT_REJANG = 110,/* Rjng */
288  USCRIPT_SAURASHTRA = 111,/* Saur */
290  USCRIPT_SIGN_WRITING = 112,/* Sgnw */
292  USCRIPT_SUNDANESE = 113,/* Sund */
294  USCRIPT_MOON = 114,/* Moon */
296  USCRIPT_MEITEI_MAYEK = 115,/* Mtei */
297 
298  /* New script codes from ISO 15924 */
300  USCRIPT_IMPERIAL_ARAMAIC = 116,/* Armi */
302  USCRIPT_AVESTAN = 117,/* Avst */
304  USCRIPT_CHAKMA = 118,/* Cakm */
306  USCRIPT_KOREAN = 119,/* Kore */
308  USCRIPT_KAITHI = 120,/* Kthi */
310  USCRIPT_MANICHAEAN = 121,/* Mani */
314  USCRIPT_PSALTER_PAHLAVI = 123,/* Phlp */
316  USCRIPT_BOOK_PAHLAVI = 124,/* Phlv */
320  USCRIPT_SAMARITAN = 126,/* Samr */
322  USCRIPT_TAI_VIET = 127,/* Tavt */
326  USCRIPT_SYMBOLS = 129,/* Zsym */
327 
328  /* New script codes from ISO 15924 */
330  USCRIPT_BAMUM = 130,/* Bamu */
332  USCRIPT_LISU = 131,/* Lisu */
334  USCRIPT_NAKHI_GEBA = 132,/* Nkgb */
336  USCRIPT_OLD_SOUTH_ARABIAN = 133,/* Sarb */
337 
338  /* New script codes from ISO 15924 */
340  USCRIPT_BASSA_VAH = 134,/* Bass */
342  USCRIPT_DUPLOYAN_SHORTAND = 135,/* Dupl */
344  USCRIPT_ELBASAN = 136,/* Elba */
346  USCRIPT_GRANTHA = 137,/* Gran */
348  USCRIPT_KPELLE = 138,/* Kpel */
350  USCRIPT_LOMA = 139,/* Loma */
352  USCRIPT_MENDE = 140,/* Mend */
354  USCRIPT_MEROITIC_CURSIVE = 141,/* Merc */
356  USCRIPT_OLD_NORTH_ARABIAN = 142,/* Narb */
358  USCRIPT_NABATAEAN = 143,/* Nbat */
360  USCRIPT_PALMYRENE = 144,/* Palm */
362  USCRIPT_SINDHI = 145,/* Sind */
364  USCRIPT_WARANG_CITI = 146,/* Wara */
365 
367  USCRIPT_AFAKA = 147,/* Afak */
369  USCRIPT_JURCHEN = 148,/* Jurc */
371  USCRIPT_MRO = 149,/* Mroo */
373  USCRIPT_NUSHU = 150,/* Nshu */
375  USCRIPT_SHARADA = 151,/* Shrd */
377  USCRIPT_SORA_SOMPENG = 152,/* Sora */
379  USCRIPT_TAKRI = 153,/* Takr */
381  USCRIPT_TANGUT = 154,/* Tang */
383  USCRIPT_WOLEAI = 155,/* Wole */
384 
385  /* Private use codes from Qaaa - Qabx are not supported */
386 
389 } UScriptCode;
390 
409 U_STABLE int32_t U_EXPORT2
410 uscript_getCode(const char* nameOrAbbrOrLocale,UScriptCode* fillIn,int32_t capacity,UErrorCode *err);
411 
420 U_STABLE const char* U_EXPORT2
421 uscript_getName(UScriptCode scriptCode);
422 
431 U_STABLE const char* U_EXPORT2
433 
443 uscript_getScript(UChar32 codepoint, UErrorCode *err);
444 
462 
487 U_DRAFT int32_t U_EXPORT2
489  UScriptCode *scripts, int32_t capacity,
490  UErrorCode *errorCode);
491 
492 #endif
UScriptCode uscript_getScript(UChar32 codepoint, UErrorCode *err)
Gets the script code associated with the given codepoint.
Canadian_Aboriginal script.
Definition: uscript.h:130
New script code in Unicode 4.0.1.
Definition: uscript.h:164
const char * uscript_getName(UScriptCode scriptCode)
Gets a script name associated with the given script code.
UScriptCode
Constants for ISO 15924 script codes.
Definition: uscript.h:46
int32_t uscript_getScriptExtensions(UChar32 c, UScriptCode *scripts, int32_t capacity, UErrorCode *errorCode)
Writes code point c's Script_Extensions as a list of UScriptCode values to the output scripts array...
int32_t UChar32
Define UChar32 as a type for single Unicode code points.
Definition: umachine.h:345
#define U_EXPORT2
Definition: platform.h:314
Canadian_Aboriginal script (alias).
Definition: uscript.h:132
UErrorCode
Error code to replace exception handling, so that the code is compatible with all C++ compilers...
Definition: utypes.h:639
Basic definitions for ICU, for both C and C++ APIs.
const char * uscript_getShortName(UScriptCode scriptCode)
Gets a script name associated with the given script code.
int32_t uscript_getCode(const char *nameOrAbbrOrLocale, UScriptCode *fillIn, int32_t capacity, UErrorCode *err)
Gets script codes associated with the given locale or ISO 15924 abbreviation or name.
UBool uscript_hasScript(UChar32 c, UScriptCode sc)
Is code point c used in script sc? That is, does code point c have the Script property value sc...
#define U_DRAFT
This is used to declare a function as a draft public ICU C API.
Definition: umachine.h:139
#define U_STABLE
This is used to declare a function as a stable public ICU C API.
Definition: umachine.h:137
int8_t UBool
The ICU boolean type.
Definition: umachine.h:228