1/*
2 * Copyright (C) 2012 Grigori Goronzy <greg@kinoho.net>
3 *
4 * Permission to use, copy, modify, and/or distribute this software for any
5 * purpose with or without fee is hereby granted, provided that the above
6 * copyright notice and this permission notice appear in all copies.
7 *
8 * THE SOFTWARE IS PROVIDED "AS IS" AND THE AUTHOR DISCLAIMS ALL WARRANTIES
9 * WITH REGARD TO THIS SOFTWARE INCLUDING ALL IMPLIED WARRANTIES OF
10 * MERCHANTABILITY AND FITNESS. IN NO EVENT SHALL THE AUTHOR BE LIABLE FOR
11 * ANY SPECIAL, DIRECT, INDIRECT, OR CONSEQUENTIAL DAMAGES OR ANY DAMAGES
12 * WHATSOEVER RESULTING FROM LOSS OF USE, DATA OR PROFITS, WHETHER IN AN
13 * ACTION OF CONTRACT, NEGLIGENCE OR OTHER TORTIOUS ACTION, ARISING OUT OF
14 * OR IN CONNECTION WITH THE USE OR PERFORMANCE OF THIS SOFTWARE.
15 */
16
17#ifndef UCDN_H
18#define UCDN_H
19
20
21
22#if defined(__GNUC__) && (__GNUC__ >= 4) && !defined(__MINGW32__)
23# define HB_BEGIN_VISIBILITY _Pragma ("GCC visibility push(hidden)")
24# define HB_END_VISIBILITY _Pragma ("GCC visibility pop")
25#else
26# define HB_BEGIN_VISIBILITY
27# define HB_END_VISIBILITY
28#endif
29#ifdef __cplusplus
30# define HB_BEGIN_HEADER extern "C" { HB_BEGIN_VISIBILITY
31# define HB_END_HEADER HB_END_VISIBILITY }
32#else
33# define HB_BEGIN_HEADER HB_BEGIN_VISIBILITY
34# define HB_END_HEADER HB_END_VISIBILITY
35#endif
36
37HB_BEGIN_HEADER
38
39#if defined (_SVR4) || defined (SVR4) || defined (__OpenBSD__) || \
40 defined (_sgi) || defined (__sun) || defined (sun) || \
41 defined (__digital__) || defined (__HP_cc)
42# include <inttypes.h>
43#elif defined (_AIX)
44# include <sys/inttypes.h>
45#elif defined (_MSC_VER) && _MSC_VER < 1600
46/* VS 2010 (_MSC_VER 1600) has stdint.h */
47typedef __int8 int8_t;
48typedef unsigned __int8 uint8_t;
49typedef __int16 int16_t;
50typedef unsigned __int16 uint16_t;
51typedef __int32 int32_t;
52typedef unsigned __int32 uint32_t;
53typedef __int64 int64_t;
54typedef unsigned __int64 uint64_t;
55#else
56# include <stdint.h>
57#endif
58
59
60#define UCDN_EAST_ASIAN_F 0
61#define UCDN_EAST_ASIAN_H 1
62#define UCDN_EAST_ASIAN_W 2
63#define UCDN_EAST_ASIAN_NA 3
64#define UCDN_EAST_ASIAN_A 4
65#define UCDN_EAST_ASIAN_N 5
66
67#define UCDN_SCRIPT_COMMON 0
68#define UCDN_SCRIPT_LATIN 1
69#define UCDN_SCRIPT_GREEK 2
70#define UCDN_SCRIPT_CYRILLIC 3
71#define UCDN_SCRIPT_ARMENIAN 4
72#define UCDN_SCRIPT_HEBREW 5
73#define UCDN_SCRIPT_ARABIC 6
74#define UCDN_SCRIPT_SYRIAC 7
75#define UCDN_SCRIPT_THAANA 8
76#define UCDN_SCRIPT_DEVANAGARI 9
77#define UCDN_SCRIPT_BENGALI 10
78#define UCDN_SCRIPT_GURMUKHI 11
79#define UCDN_SCRIPT_GUJARATI 12
80#define UCDN_SCRIPT_ORIYA 13
81#define UCDN_SCRIPT_TAMIL 14
82#define UCDN_SCRIPT_TELUGU 15
83#define UCDN_SCRIPT_KANNADA 16
84#define UCDN_SCRIPT_MALAYALAM 17
85#define UCDN_SCRIPT_SINHALA 18
86#define UCDN_SCRIPT_THAI 19
87#define UCDN_SCRIPT_LAO 20
88#define UCDN_SCRIPT_TIBETAN 21
89#define UCDN_SCRIPT_MYANMAR 22
90#define UCDN_SCRIPT_GEORGIAN 23
91#define UCDN_SCRIPT_HANGUL 24
92#define UCDN_SCRIPT_ETHIOPIC 25
93#define UCDN_SCRIPT_CHEROKEE 26
94#define UCDN_SCRIPT_CANADIAN_ABORIGINAL 27
95#define UCDN_SCRIPT_OGHAM 28
96#define UCDN_SCRIPT_RUNIC 29
97#define UCDN_SCRIPT_KHMER 30
98#define UCDN_SCRIPT_MONGOLIAN 31
99#define UCDN_SCRIPT_HIRAGANA 32
100#define UCDN_SCRIPT_KATAKANA 33
101#define UCDN_SCRIPT_BOPOMOFO 34
102#define UCDN_SCRIPT_HAN 35
103#define UCDN_SCRIPT_YI 36
104#define UCDN_SCRIPT_OLD_ITALIC 37
105#define UCDN_SCRIPT_GOTHIC 38
106#define UCDN_SCRIPT_DESERET 39
107#define UCDN_SCRIPT_INHERITED 40
108#define UCDN_SCRIPT_TAGALOG 41
109#define UCDN_SCRIPT_HANUNOO 42
110#define UCDN_SCRIPT_BUHID 43
111#define UCDN_SCRIPT_TAGBANWA 44
112#define UCDN_SCRIPT_LIMBU 45
113#define UCDN_SCRIPT_TAI_LE 46
114#define UCDN_SCRIPT_LINEAR_B 47
115#define UCDN_SCRIPT_UGARITIC 48
116#define UCDN_SCRIPT_SHAVIAN 49
117#define UCDN_SCRIPT_OSMANYA 50
118#define UCDN_SCRIPT_CYPRIOT 51
119#define UCDN_SCRIPT_BRAILLE 52
120#define UCDN_SCRIPT_BUGINESE 53
121#define UCDN_SCRIPT_COPTIC 54
122#define UCDN_SCRIPT_NEW_TAI_LUE 55
123#define UCDN_SCRIPT_GLAGOLITIC 56
124#define UCDN_SCRIPT_TIFINAGH 57
125#define UCDN_SCRIPT_SYLOTI_NAGRI 58
126#define UCDN_SCRIPT_OLD_PERSIAN 59
127#define UCDN_SCRIPT_KHAROSHTHI 60
128#define UCDN_SCRIPT_BALINESE 61
129#define UCDN_SCRIPT_CUNEIFORM 62
130#define UCDN_SCRIPT_PHOENICIAN 63
131#define UCDN_SCRIPT_PHAGS_PA 64
132#define UCDN_SCRIPT_NKO 65
133#define UCDN_SCRIPT_SUNDANESE 66
134#define UCDN_SCRIPT_LEPCHA 67
135#define UCDN_SCRIPT_OL_CHIKI 68
136#define UCDN_SCRIPT_VAI 69
137#define UCDN_SCRIPT_SAURASHTRA 70
138#define UCDN_SCRIPT_KAYAH_LI 71
139#define UCDN_SCRIPT_REJANG 72
140#define UCDN_SCRIPT_LYCIAN 73
141#define UCDN_SCRIPT_CARIAN 74
142#define UCDN_SCRIPT_LYDIAN 75
143#define UCDN_SCRIPT_CHAM 76
144#define UCDN_SCRIPT_TAI_THAM 77
145#define UCDN_SCRIPT_TAI_VIET 78
146#define UCDN_SCRIPT_AVESTAN 79
147#define UCDN_SCRIPT_EGYPTIAN_HIEROGLYPHS 80
148#define UCDN_SCRIPT_SAMARITAN 81
149#define UCDN_SCRIPT_LISU 82
150#define UCDN_SCRIPT_BAMUM 83
151#define UCDN_SCRIPT_JAVANESE 84
152#define UCDN_SCRIPT_MEETEI_MAYEK 85
153#define UCDN_SCRIPT_IMPERIAL_ARAMAIC 86
154#define UCDN_SCRIPT_OLD_SOUTH_ARABIAN 87
155#define UCDN_SCRIPT_INSCRIPTIONAL_PARTHIAN 88
156#define UCDN_SCRIPT_INSCRIPTIONAL_PAHLAVI 89
157#define UCDN_SCRIPT_OLD_TURKIC 90
158#define UCDN_SCRIPT_KAITHI 91
159#define UCDN_SCRIPT_BATAK 92
160#define UCDN_SCRIPT_BRAHMI 93
161#define UCDN_SCRIPT_MANDAIC 94
162#define UCDN_SCRIPT_CHAKMA 95
163#define UCDN_SCRIPT_MEROITIC_CURSIVE 96
164#define UCDN_SCRIPT_MEROITIC_HIEROGLYPHS 97
165#define UCDN_SCRIPT_MIAO 98
166#define UCDN_SCRIPT_SHARADA 99
167#define UCDN_SCRIPT_SORA_SOMPENG 100
168#define UCDN_SCRIPT_TAKRI 101
169#define UCDN_SCRIPT_UNKNOWN 102
170#define UCDN_SCRIPT_BASSA_VAH 103
171#define UCDN_SCRIPT_CAUCASIAN_ALBANIAN 104
172#define UCDN_SCRIPT_DUPLOYAN 105
173#define UCDN_SCRIPT_ELBASAN 106
174#define UCDN_SCRIPT_GRANTHA 107
175#define UCDN_SCRIPT_KHOJKI 108
176#define UCDN_SCRIPT_KHUDAWADI 109
177#define UCDN_SCRIPT_LINEAR_A 110
178#define UCDN_SCRIPT_MAHAJANI 111
179#define UCDN_SCRIPT_MANICHAEAN 112
180#define UCDN_SCRIPT_MENDE_KIKAKUI 113
181#define UCDN_SCRIPT_MODI 114
182#define UCDN_SCRIPT_MRO 115
183#define UCDN_SCRIPT_NABATAEAN 116
184#define UCDN_SCRIPT_OLD_NORTH_ARABIAN 117
185#define UCDN_SCRIPT_OLD_PERMIC 118
186#define UCDN_SCRIPT_PAHAWH_HMONG 119
187#define UCDN_SCRIPT_PALMYRENE 120
188#define UCDN_SCRIPT_PAU_CIN_HAU 121
189#define UCDN_SCRIPT_PSALTER_PAHLAVI 122
190#define UCDN_SCRIPT_SIDDHAM 123
191#define UCDN_SCRIPT_TIRHUTA 124
192#define UCDN_SCRIPT_WARANG_CITI 125
193#define UCDN_SCRIPT_AHOM 126
194#define UCDN_SCRIPT_ANATOLIAN_HIEROGLYPHS 127
195#define UCDN_SCRIPT_HATRAN 128
196#define UCDN_SCRIPT_MULTANI 129
197#define UCDN_SCRIPT_OLD_HUNGARIAN 130
198#define UCDN_SCRIPT_SIGNWRITING 131
199#define UCDN_SCRIPT_ADLAM 132
200#define UCDN_SCRIPT_BHAIKSUKI 133
201#define UCDN_SCRIPT_MARCHEN 134
202#define UCDN_SCRIPT_NEWA 135
203#define UCDN_SCRIPT_OSAGE 136
204#define UCDN_SCRIPT_TANGUT 137
205#define UCDN_SCRIPT_MASARAM_GONDI 138
206#define UCDN_SCRIPT_NUSHU 139
207#define UCDN_SCRIPT_SOYOMBO 140
208#define UCDN_SCRIPT_ZANABAZAR_SQUARE 141
209
210#define UCDN_LINEBREAK_CLASS_OP 0
211#define UCDN_LINEBREAK_CLASS_CL 1
212#define UCDN_LINEBREAK_CLASS_CP 2
213#define UCDN_LINEBREAK_CLASS_QU 3
214#define UCDN_LINEBREAK_CLASS_GL 4
215#define UCDN_LINEBREAK_CLASS_NS 5
216#define UCDN_LINEBREAK_CLASS_EX 6
217#define UCDN_LINEBREAK_CLASS_SY 7
218#define UCDN_LINEBREAK_CLASS_IS 8
219#define UCDN_LINEBREAK_CLASS_PR 9
220#define UCDN_LINEBREAK_CLASS_PO 10
221#define UCDN_LINEBREAK_CLASS_NU 11
222#define UCDN_LINEBREAK_CLASS_AL 12
223#define UCDN_LINEBREAK_CLASS_HL 13
224#define UCDN_LINEBREAK_CLASS_ID 14
225#define UCDN_LINEBREAK_CLASS_IN 15
226#define UCDN_LINEBREAK_CLASS_HY 16
227#define UCDN_LINEBREAK_CLASS_BA 17
228#define UCDN_LINEBREAK_CLASS_BB 18
229#define UCDN_LINEBREAK_CLASS_B2 19
230#define UCDN_LINEBREAK_CLASS_ZW 20
231#define UCDN_LINEBREAK_CLASS_CM 21
232#define UCDN_LINEBREAK_CLASS_WJ 22
233#define UCDN_LINEBREAK_CLASS_H2 23
234#define UCDN_LINEBREAK_CLASS_H3 24
235#define UCDN_LINEBREAK_CLASS_JL 25
236#define UCDN_LINEBREAK_CLASS_JV 26
237#define UCDN_LINEBREAK_CLASS_JT 27
238#define UCDN_LINEBREAK_CLASS_RI 28
239#define UCDN_LINEBREAK_CLASS_AI 29
240#define UCDN_LINEBREAK_CLASS_BK 30
241#define UCDN_LINEBREAK_CLASS_CB 31
242#define UCDN_LINEBREAK_CLASS_CJ 32
243#define UCDN_LINEBREAK_CLASS_CR 33
244#define UCDN_LINEBREAK_CLASS_LF 34
245#define UCDN_LINEBREAK_CLASS_NL 35
246#define UCDN_LINEBREAK_CLASS_SA 36
247#define UCDN_LINEBREAK_CLASS_SG 37
248#define UCDN_LINEBREAK_CLASS_SP 38
249#define UCDN_LINEBREAK_CLASS_XX 39
250#define UCDN_LINEBREAK_CLASS_ZWJ 40
251#define UCDN_LINEBREAK_CLASS_EB 41
252#define UCDN_LINEBREAK_CLASS_EM 42
253
254#define UCDN_GENERAL_CATEGORY_CC 0
255#define UCDN_GENERAL_CATEGORY_CF 1
256#define UCDN_GENERAL_CATEGORY_CN 2
257#define UCDN_GENERAL_CATEGORY_CO 3
258#define UCDN_GENERAL_CATEGORY_CS 4
259#define UCDN_GENERAL_CATEGORY_LL 5
260#define UCDN_GENERAL_CATEGORY_LM 6
261#define UCDN_GENERAL_CATEGORY_LO 7
262#define UCDN_GENERAL_CATEGORY_LT 8
263#define UCDN_GENERAL_CATEGORY_LU 9
264#define UCDN_GENERAL_CATEGORY_MC 10
265#define UCDN_GENERAL_CATEGORY_ME 11
266#define UCDN_GENERAL_CATEGORY_MN 12
267#define UCDN_GENERAL_CATEGORY_ND 13
268#define UCDN_GENERAL_CATEGORY_NL 14
269#define UCDN_GENERAL_CATEGORY_NO 15
270#define UCDN_GENERAL_CATEGORY_PC 16
271#define UCDN_GENERAL_CATEGORY_PD 17
272#define UCDN_GENERAL_CATEGORY_PE 18
273#define UCDN_GENERAL_CATEGORY_PF 19
274#define UCDN_GENERAL_CATEGORY_PI 20
275#define UCDN_GENERAL_CATEGORY_PO 21
276#define UCDN_GENERAL_CATEGORY_PS 22
277#define UCDN_GENERAL_CATEGORY_SC 23
278#define UCDN_GENERAL_CATEGORY_SK 24
279#define UCDN_GENERAL_CATEGORY_SM 25
280#define UCDN_GENERAL_CATEGORY_SO 26
281#define UCDN_GENERAL_CATEGORY_ZL 27
282#define UCDN_GENERAL_CATEGORY_ZP 28
283#define UCDN_GENERAL_CATEGORY_ZS 29
284
285#define UCDN_BIDI_CLASS_L 0
286#define UCDN_BIDI_CLASS_LRE 1
287#define UCDN_BIDI_CLASS_LRO 2
288#define UCDN_BIDI_CLASS_R 3
289#define UCDN_BIDI_CLASS_AL 4
290#define UCDN_BIDI_CLASS_RLE 5
291#define UCDN_BIDI_CLASS_RLO 6
292#define UCDN_BIDI_CLASS_PDF 7
293#define UCDN_BIDI_CLASS_EN 8
294#define UCDN_BIDI_CLASS_ES 9
295#define UCDN_BIDI_CLASS_ET 10
296#define UCDN_BIDI_CLASS_AN 11
297#define UCDN_BIDI_CLASS_CS 12
298#define UCDN_BIDI_CLASS_NSM 13
299#define UCDN_BIDI_CLASS_BN 14
300#define UCDN_BIDI_CLASS_B 15
301#define UCDN_BIDI_CLASS_S 16
302#define UCDN_BIDI_CLASS_WS 17
303#define UCDN_BIDI_CLASS_ON 18
304#define UCDN_BIDI_CLASS_LRI 19
305#define UCDN_BIDI_CLASS_RLI 20
306#define UCDN_BIDI_CLASS_FSI 21
307#define UCDN_BIDI_CLASS_PDI 22
308
309#define UCDN_BIDI_PAIRED_BRACKET_TYPE_OPEN 0
310#define UCDN_BIDI_PAIRED_BRACKET_TYPE_CLOSE 1
311#define UCDN_BIDI_PAIRED_BRACKET_TYPE_NONE 2
312
313/**
314 * Return version of the Unicode database.
315 *
316 * @return Unicode database version
317 */
318const char *ucdn_get_unicode_version(void);
319
320/**
321 * Get combining class of a codepoint.
322 *
323 * @param code Unicode codepoint
324 * @return combining class value, as defined in UAX#44
325 */
326int ucdn_get_combining_class(uint32_t code);
327
328/**
329 * Get east-asian width of a codepoint.
330 *
331 * @param code Unicode codepoint
332 * @return value according to UCDN_EAST_ASIAN_* and as defined in UAX#11.
333 */
334int ucdn_get_east_asian_width(uint32_t code);
335
336/**
337 * Get general category of a codepoint.
338 *
339 * @param code Unicode codepoint
340 * @return value according to UCDN_GENERAL_CATEGORY_* and as defined in
341 * UAX#44.
342 */
343int ucdn_get_general_category(uint32_t code);
344
345/**
346 * Get bidirectional class of a codepoint.
347 *
348 * @param code Unicode codepoint
349 * @return value according to UCDN_BIDI_CLASS_* and as defined in UAX#44.
350 */
351int ucdn_get_bidi_class(uint32_t code);
352
353/**
354 * Get script of a codepoint.
355 *
356 * @param code Unicode codepoint
357 * @return value according to UCDN_SCRIPT_* and as defined in UAX#24.
358 */
359int ucdn_get_script(uint32_t code);
360
361/**
362 * Get unresolved linebreak class of a codepoint. This does not take
363 * rule LB1 of UAX#14 into account. See ucdn_get_resolved_linebreak_class()
364 * for resolved linebreak classes.
365 *
366 * @param code Unicode codepoint
367 * @return value according to UCDN_LINEBREAK_* and as defined in UAX#14.
368 */
369int ucdn_get_linebreak_class(uint32_t code);
370
371/**
372 * Get resolved linebreak class of a codepoint. This resolves characters
373 * in the AI, SG, XX, SA and CJ classes according to rule LB1 of UAX#14.
374 * In addition the CB class is resolved as the equivalent B2 class and
375 * the NL class is resolved as the equivalent BK class.
376 *
377 * @param code Unicode codepoint
378 * @return value according to UCDN_LINEBREAK_* and as defined in UAX#14.
379 */
380int ucdn_get_resolved_linebreak_class(uint32_t code);
381
382/**
383 * Check if codepoint can be mirrored.
384 *
385 * @param code Unicode codepoint
386 * @return 1 if mirrored character exists, otherwise 0
387 */
388int ucdn_get_mirrored(uint32_t code);
389
390/**
391 * Mirror a codepoint.
392 *
393 * @param code Unicode codepoint
394 * @return mirrored codepoint or the original codepoint if no
395 * mirrored character exists
396 */
397uint32_t ucdn_mirror(uint32_t code);
398
399/**
400 * Get paired bracket for a codepoint.
401 *
402 * @param code Unicode codepoint
403 * @return paired bracket codepoint or the original codepoint if no
404 * paired bracket character exists
405 */
406uint32_t ucdn_paired_bracket(uint32_t code);
407
408/**
409 * Get paired bracket type for a codepoint.
410 *
411 * @param code Unicode codepoint
412 * @return value according to UCDN_BIDI_PAIRED_BRACKET_TYPE_* and as defined
413 * in UAX#9.
414 *
415 */
416int ucdn_paired_bracket_type(uint32_t code);
417
418/**
419 * Pairwise canonical decomposition of a codepoint. This includes
420 * Hangul Jamo decomposition (see chapter 3.12 of the Unicode core
421 * specification).
422 *
423 * Hangul is decomposed into L and V jamos for LV forms, and an
424 * LV precomposed syllable and a T jamo for LVT forms.
425 *
426 * @param code Unicode codepoint
427 * @param a filled with first codepoint of decomposition
428 * @param b filled with second codepoint of decomposition, or 0
429 * @return success
430 */
431int ucdn_decompose(uint32_t code, uint32_t *a, uint32_t *b);
432
433/**
434 * Compatibility decomposition of a codepoint.
435 *
436 * @param code Unicode codepoint
437 * @param decomposed filled with decomposition, must be able to hold 18
438 * characters
439 * @return length of decomposition or 0 in case none exists
440 */
441int ucdn_compat_decompose(uint32_t code, uint32_t *decomposed);
442
443/**
444 * Pairwise canonical composition of two codepoints. This includes
445 * Hangul Jamo composition (see chapter 3.12 of the Unicode core
446 * specification).
447 *
448 * Hangul composition expects either L and V jamos, or an LV
449 * precomposed syllable and a T jamo. This is exactly the inverse
450 * of pairwise Hangul decomposition.
451 *
452 * @param code filled with composition
453 * @param a first codepoint
454 * @param b second codepoint
455 * @return success
456 */
457int ucdn_compose(uint32_t *code, uint32_t a, uint32_t b);
458
459HB_END_HEADER
460
461#endif
462