ICU 57.1  57.1
uscript.h
Go to the documentation of this file.
1 /*
2  **********************************************************************
3  * Copyright (C) 1997-2015, 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 
52 typedef enum UScriptCode {
53  /*
54  * Note: UScriptCode constants and their ISO script code comments
55  * are parsed by preparseucd.py.
56  * It matches lines like
57  * USCRIPT_<Unicode Script value name> = <integer>, / * <ISO script code> * /
58  */
59 
63  USCRIPT_COMMON = 0, /* Zyyy */
65  USCRIPT_INHERITED = 1, /* Zinh */ /* "Code for inherited script", for non-spacing combining marks; also Qaai */
67  USCRIPT_ARABIC = 2, /* Arab */
69  USCRIPT_ARMENIAN = 3, /* Armn */
71  USCRIPT_BENGALI = 4, /* Beng */
73  USCRIPT_BOPOMOFO = 5, /* Bopo */
75  USCRIPT_CHEROKEE = 6, /* Cher */
77  USCRIPT_COPTIC = 7, /* Copt */
79  USCRIPT_CYRILLIC = 8, /* Cyrl */
81  USCRIPT_DESERET = 9, /* Dsrt */
83  USCRIPT_DEVANAGARI = 10, /* Deva */
85  USCRIPT_ETHIOPIC = 11, /* Ethi */
87  USCRIPT_GEORGIAN = 12, /* Geor */
89  USCRIPT_GOTHIC = 13, /* Goth */
91  USCRIPT_GREEK = 14, /* Grek */
93  USCRIPT_GUJARATI = 15, /* Gujr */
95  USCRIPT_GURMUKHI = 16, /* Guru */
97  USCRIPT_HAN = 17, /* Hani */
99  USCRIPT_HANGUL = 18, /* Hang */
101  USCRIPT_HEBREW = 19, /* Hebr */
103  USCRIPT_HIRAGANA = 20, /* Hira */
105  USCRIPT_KANNADA = 21, /* Knda */
107  USCRIPT_KATAKANA = 22, /* Kana */
109  USCRIPT_KHMER = 23, /* Khmr */
111  USCRIPT_LAO = 24, /* Laoo */
113  USCRIPT_LATIN = 25, /* Latn */
115  USCRIPT_MALAYALAM = 26, /* Mlym */
117  USCRIPT_MONGOLIAN = 27, /* Mong */
119  USCRIPT_MYANMAR = 28, /* Mymr */
121  USCRIPT_OGHAM = 29, /* Ogam */
123  USCRIPT_OLD_ITALIC = 30, /* Ital */
125  USCRIPT_ORIYA = 31, /* Orya */
127  USCRIPT_RUNIC = 32, /* Runr */
129  USCRIPT_SINHALA = 33, /* Sinh */
131  USCRIPT_SYRIAC = 34, /* Syrc */
133  USCRIPT_TAMIL = 35, /* Taml */
135  USCRIPT_TELUGU = 36, /* Telu */
137  USCRIPT_THAANA = 37, /* Thaa */
139  USCRIPT_THAI = 38, /* Thai */
141  USCRIPT_TIBETAN = 39, /* Tibt */
147  USCRIPT_YI = 41, /* Yiii */
148  /* New scripts in Unicode 3.2 */
150  USCRIPT_TAGALOG = 42, /* Tglg */
152  USCRIPT_HANUNOO = 43, /* Hano */
154  USCRIPT_BUHID = 44, /* Buhd */
156  USCRIPT_TAGBANWA = 45, /* Tagb */
157 
158  /* New scripts in Unicode 4 */
160  USCRIPT_BRAILLE = 46, /* Brai */
162  USCRIPT_CYPRIOT = 47, /* Cprt */
164  USCRIPT_LIMBU = 48, /* Limb */
166  USCRIPT_LINEAR_B = 49, /* Linb */
168  USCRIPT_OSMANYA = 50, /* Osma */
170  USCRIPT_SHAVIAN = 51, /* Shaw */
172  USCRIPT_TAI_LE = 52, /* Tale */
174  USCRIPT_UGARITIC = 53, /* Ugar */
175 
178 
179  /* New scripts in Unicode 4.1 */
181  USCRIPT_BUGINESE = 55, /* Bugi */
183  USCRIPT_GLAGOLITIC = 56, /* Glag */
185  USCRIPT_KHAROSHTHI = 57, /* Khar */
187  USCRIPT_SYLOTI_NAGRI = 58, /* Sylo */
189  USCRIPT_NEW_TAI_LUE = 59, /* Talu */
191  USCRIPT_TIFINAGH = 60, /* Tfng */
193  USCRIPT_OLD_PERSIAN = 61, /* Xpeo */
194 
195  /* New script codes from Unicode and ISO 15924 */
197  USCRIPT_BALINESE = 62, /* Bali */
199  USCRIPT_BATAK = 63, /* Batk */
201  USCRIPT_BLISSYMBOLS = 64, /* Blis */
203  USCRIPT_BRAHMI = 65, /* Brah */
205  USCRIPT_CHAM = 66, /* Cham */
207  USCRIPT_CIRTH = 67, /* Cirt */
211  USCRIPT_DEMOTIC_EGYPTIAN = 69, /* Egyd */
213  USCRIPT_HIERATIC_EGYPTIAN = 70, /* Egyh */
217  USCRIPT_KHUTSURI = 72, /* Geok */
219  USCRIPT_SIMPLIFIED_HAN = 73, /* Hans */
221  USCRIPT_TRADITIONAL_HAN = 74, /* Hant */
223  USCRIPT_PAHAWH_HMONG = 75, /* Hmng */
225  USCRIPT_OLD_HUNGARIAN = 76, /* Hung */
227  USCRIPT_HARAPPAN_INDUS = 77, /* Inds */
229  USCRIPT_JAVANESE = 78, /* Java */
231  USCRIPT_KAYAH_LI = 79, /* Kali */
233  USCRIPT_LATIN_FRAKTUR = 80, /* Latf */
235  USCRIPT_LATIN_GAELIC = 81, /* Latg */
237  USCRIPT_LEPCHA = 82, /* Lepc */
239  USCRIPT_LINEAR_A = 83, /* Lina */
241  USCRIPT_MANDAIC = 84, /* Mand */
245  USCRIPT_MAYAN_HIEROGLYPHS = 85, /* Maya */
251  USCRIPT_NKO = 87, /* Nkoo */
253  USCRIPT_ORKHON = 88, /* Orkh */
255  USCRIPT_OLD_PERMIC = 89, /* Perm */
257  USCRIPT_PHAGS_PA = 90, /* Phag */
259  USCRIPT_PHOENICIAN = 91, /* Phnx */
261  USCRIPT_MIAO = 92, /* Plrd */
265  USCRIPT_RONGORONGO = 93, /* Roro */
267  USCRIPT_SARATI = 94, /* Sara */
269  USCRIPT_ESTRANGELO_SYRIAC = 95, /* Syre */
271  USCRIPT_WESTERN_SYRIAC = 96, /* Syrj */
273  USCRIPT_EASTERN_SYRIAC = 97, /* Syrn */
275  USCRIPT_TENGWAR = 98, /* Teng */
277  USCRIPT_VAI = 99, /* Vaii */
279  USCRIPT_VISIBLE_SPEECH = 100,/* Visp */
281  USCRIPT_CUNEIFORM = 101,/* Xsux */
285  USCRIPT_UNKNOWN = 103,/* Zzzz */ /* Unknown="Code for uncoded script", for unassigned code points */
286 
288  USCRIPT_CARIAN = 104,/* Cari */
290  USCRIPT_JAPANESE = 105,/* Jpan */
292  USCRIPT_LANNA = 106,/* Lana */
294  USCRIPT_LYCIAN = 107,/* Lyci */
296  USCRIPT_LYDIAN = 108,/* Lydi */
298  USCRIPT_OL_CHIKI = 109,/* Olck */
300  USCRIPT_REJANG = 110,/* Rjng */
302  USCRIPT_SAURASHTRA = 111,/* Saur */
304  USCRIPT_SIGN_WRITING = 112,/* Sgnw */
306  USCRIPT_SUNDANESE = 113,/* Sund */
308  USCRIPT_MOON = 114,/* Moon */
310  USCRIPT_MEITEI_MAYEK = 115,/* Mtei */
311 
313  USCRIPT_IMPERIAL_ARAMAIC = 116,/* Armi */
315  USCRIPT_AVESTAN = 117,/* Avst */
317  USCRIPT_CHAKMA = 118,/* Cakm */
319  USCRIPT_KOREAN = 119,/* Kore */
321  USCRIPT_KAITHI = 120,/* Kthi */
323  USCRIPT_MANICHAEAN = 121,/* Mani */
327  USCRIPT_PSALTER_PAHLAVI = 123,/* Phlp */
329  USCRIPT_BOOK_PAHLAVI = 124,/* Phlv */
333  USCRIPT_SAMARITAN = 126,/* Samr */
335  USCRIPT_TAI_VIET = 127,/* Tavt */
339  USCRIPT_SYMBOLS = 129,/* Zsym */
340 
342  USCRIPT_BAMUM = 130,/* Bamu */
344  USCRIPT_LISU = 131,/* Lisu */
346  USCRIPT_NAKHI_GEBA = 132,/* Nkgb */
348  USCRIPT_OLD_SOUTH_ARABIAN = 133,/* Sarb */
349 
351  USCRIPT_BASSA_VAH = 134,/* Bass */
353  USCRIPT_DUPLOYAN = 135,/* Dupl */
354 #ifndef U_HIDE_DEPRECATED_API
355 
357 #endif /* U_HIDE_DEPRECATED_API */
358 
359  USCRIPT_ELBASAN = 136,/* Elba */
361  USCRIPT_GRANTHA = 137,/* Gran */
363  USCRIPT_KPELLE = 138,/* Kpel */
365  USCRIPT_LOMA = 139,/* Loma */
367  USCRIPT_MENDE = 140,/* Mend */
369  USCRIPT_MEROITIC_CURSIVE = 141,/* Merc */
371  USCRIPT_OLD_NORTH_ARABIAN = 142,/* Narb */
373  USCRIPT_NABATAEAN = 143,/* Nbat */
375  USCRIPT_PALMYRENE = 144,/* Palm */
377  USCRIPT_KHUDAWADI = 145,/* Sind */
381  USCRIPT_WARANG_CITI = 146,/* Wara */
382 
384  USCRIPT_AFAKA = 147,/* Afak */
386  USCRIPT_JURCHEN = 148,/* Jurc */
388  USCRIPT_MRO = 149,/* Mroo */
390  USCRIPT_NUSHU = 150,/* Nshu */
392  USCRIPT_SHARADA = 151,/* Shrd */
394  USCRIPT_SORA_SOMPENG = 152,/* Sora */
396  USCRIPT_TAKRI = 153,/* Takr */
398  USCRIPT_TANGUT = 154,/* Tang */
400  USCRIPT_WOLEAI = 155,/* Wole */
401 
405  USCRIPT_KHOJKI = 157,/* Khoj */
407  USCRIPT_TIRHUTA = 158,/* Tirh */
408 
410  USCRIPT_CAUCASIAN_ALBANIAN = 159,/* Aghb */
412  USCRIPT_MAHAJANI = 160,/* Mahj */
413 
415  USCRIPT_AHOM = 161,/* Ahom */
417  USCRIPT_HATRAN = 162,/* Hatr */
419  USCRIPT_MODI = 163,/* Modi */
421  USCRIPT_MULTANI = 164,/* Mult */
423  USCRIPT_PAU_CIN_HAU = 165,/* Pauc */
425  USCRIPT_SIDDHAM = 166,/* Sidd */
426 
439 } UScriptCode;
440 
460 U_STABLE int32_t U_EXPORT2
461 uscript_getCode(const char* nameOrAbbrOrLocale,UScriptCode* fillIn,int32_t capacity,UErrorCode *err);
462 
473 U_STABLE const char* U_EXPORT2
474 uscript_getName(UScriptCode scriptCode);
475 
485 U_STABLE const char* U_EXPORT2
487 
496 U_STABLE UScriptCode U_EXPORT2
497 uscript_getScript(UChar32 codepoint, UErrorCode *err);
498 
514 U_STABLE UBool U_EXPORT2
516 
548 U_STABLE int32_t U_EXPORT2
550  UScriptCode *scripts, int32_t capacity,
551  UErrorCode *errorCode);
552 
560 typedef enum UScriptUsage {
573 } UScriptUsage;
574 
587 U_STABLE int32_t U_EXPORT2
588 uscript_getSampleString(UScriptCode script, UChar *dest, int32_t capacity, UErrorCode *pErrorCode);
589 
590 #if U_SHOW_CPLUSPLUS_API
591 
593 class UnicodeString;
595 
607 
608 #endif
609 
619 U_STABLE UScriptUsage U_EXPORT2
621 
630 U_STABLE UBool U_EXPORT2
632 
642 U_STABLE UBool U_EXPORT2
644 
653 U_STABLE UBool U_EXPORT2
655 
656 #endif
Sutton SignWriting.
Definition: uscript.h:304
UScriptCode uscript_getScript(UChar32 codepoint, UErrorCode *err)
Gets the script code associated with the given codepoint.
Canadian_Aboriginal script.
Definition: uscript.h:143
Aspirational Use script.
Definition: uscript.h:570
New script code in Unicode 4.0.1.
Definition: uscript.h:177
Candidate for Exclusion from Identifiers.
Definition: uscript.h:566
Mende Kikakui.
Definition: uscript.h:367
const char * uscript_getName(UScriptCode scriptCode)
Returns the long Unicode script name, if there is one.
int32_t uscript_getSampleString(UScriptCode script, UChar *dest, int32_t capacity, UErrorCode *pErrorCode)
Writes the script sample character string.
One higher than the last script code constant.
Definition: uscript.h:438
UBool uscript_isCased(UScriptCode script)
Returns TRUE if in modern (or most recent) usage of the script case distinctions are customary...
UScriptCode
Constants for ISO 15924 script codes.
Definition: uscript.h:52
UBool uscript_isRightToLeft(UScriptCode script)
Returns TRUE if the script is written right-to-left.
UScriptUsage uscript_getUsage(UScriptCode script)
Returns the script usage according to UAX #31 Unicode Identifier and Pattern Syntax.
#define U_NAMESPACE_BEGIN
This is used to begin a declaration of a public ICU C++ API.
Definition: uversion.h:129
int32_t uscript_getScriptExtensions(UChar32 c, UScriptCode *scripts, int32_t capacity, UErrorCode *errorCode)
Writes code point c&#39;s Script_Extensions as a list of UScriptCode values to the output scripts array a...
int32_t UChar32
Define UChar32 as a type for single Unicode code points.
Definition: umachine.h:332
Unknown script usage.
Definition: uscript.h:564
uint16_t UChar
Define UChar to be UCHAR_TYPE, if that is #defined (for example, to char16_t), or wchar_t if that is ...
Definition: umachine.h:312
UBool uscript_breaksBetweenLetters(UScriptCode script)
Returns TRUE if the script allows line breaks between letters (excluding hyphenation).
#define U_NAMESPACE_END
This is used to end a declaration of a public ICU C++ API.
Definition: uversion.h:130
Canadian_Aboriginal script (alias).
Definition: uscript.h:145
UErrorCode
Error code to replace exception handling, so that the code is compatible with all C++ compilers...
Definition: utypes.h:476
UScriptUsage
Script usage constants.
Definition: uscript.h:560
Not encoded in Unicode.
Definition: uscript.h:562
Recommended script.
Definition: uscript.h:572
Basic definitions for ICU, for both C and C++ APIs.
Limited Use script.
Definition: uscript.h:568
const char * uscript_getShortName(UScriptCode scriptCode)
Returns the 4-letter ISO 15924 script code, which is the same as the short Unicode script name if Uni...
int32_t uscript_getCode(const char *nameOrAbbrOrLocale, UScriptCode *fillIn, int32_t capacity, UErrorCode *err)
Gets the script codes associated with the given locale or ISO 15924 abbreviation or name...
#define U_COMMON_API
Set to export library symbols from inside the common library, and to import them from outside...
Definition: utypes.h:357
UnicodeString is a string class that stores Unicode characters directly and provides similar function...
Definition: unistr.h:293
UBool uscript_hasScript(UChar32 c, UScriptCode sc)
Do the Script_Extensions of code point c contain script sc? If c does not have explicit Script_Extens...
U_COMMON_API icu::UnicodeString uscript_getSampleUnicodeString(UScriptCode script)
Returns the script sample character string.
#define U_STABLE
This is used to declare a function as a stable public ICU C API.
Definition: umachine.h:109
int8_t UBool
The ICU boolean type.
Definition: umachine.h:234