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