1/*
2 * Copyright �� 2009  Red Hat, Inc.
3 * Copyright �� 2011  Codethink Limited
4 * Copyright �� 2011,2012  Google, Inc.
5 *
6 *  This is part of HarfBuzz, a text shaping library.
7 *
8 * Permission is hereby granted, without written agreement and without
9 * license or royalty fees, to use, copy, modify, and distribute this
10 * software and its documentation for any purpose, provided that the
11 * above copyright notice and the following two paragraphs appear in
12 * all copies of this software.
13 *
14 * IN NO EVENT SHALL THE COPYRIGHT HOLDER BE LIABLE TO ANY PARTY FOR
15 * DIRECT, INDIRECT, SPECIAL, INCIDENTAL, OR CONSEQUENTIAL DAMAGES
16 * ARISING OUT OF THE USE OF THIS SOFTWARE AND ITS DOCUMENTATION, EVEN
17 * IF THE COPYRIGHT HOLDER HAS BEEN ADVISED OF THE POSSIBILITY OF SUCH
18 * DAMAGE.
19 *
20 * THE COPYRIGHT HOLDER SPECIFICALLY DISCLAIMS ANY WARRANTIES, INCLUDING,
21 * BUT NOT LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND
22 * FITNESS FOR A PARTICULAR PURPOSE.  THE SOFTWARE PROVIDED HEREUNDER IS
23 * ON AN "AS IS" BASIS, AND THE COPYRIGHT HOLDER HAS NO OBLIGATION TO
24 * PROVIDE MAINTENANCE, SUPPORT, UPDATES, ENHANCEMENTS, OR MODIFICATIONS.
25 *
26 * Red Hat Author(s): Behdad Esfahbod
27 * Codethink Author(s): Ryan Lortie
28 * Google Author(s): Behdad Esfahbod
29 */
30
31#ifndef HB_H_IN
32#error "Include <hb.h> instead."
33#endif
34
35#ifndef HB_UNICODE_H
36#define HB_UNICODE_H
37
38#include "hb-common.h"
39
40HB_BEGIN_DECLS
41
42
43/* hb_unicode_general_category_t */
44
45/* Unicode Character Database property: General_Category (gc) */
46typedef enum
47{
48  HB_UNICODE_GENERAL_CATEGORY_CONTROL,                  /* Cc */
49  HB_UNICODE_GENERAL_CATEGORY_FORMAT,                   /* Cf */
50  HB_UNICODE_GENERAL_CATEGORY_UNASSIGNED,               /* Cn */
51  HB_UNICODE_GENERAL_CATEGORY_PRIVATE_USE,              /* Co */
52  HB_UNICODE_GENERAL_CATEGORY_SURROGATE,                /* Cs */
53  HB_UNICODE_GENERAL_CATEGORY_LOWERCASE_LETTER,         /* Ll */
54  HB_UNICODE_GENERAL_CATEGORY_MODIFIER_LETTER,          /* Lm */
55  HB_UNICODE_GENERAL_CATEGORY_OTHER_LETTER,             /* Lo */
56  HB_UNICODE_GENERAL_CATEGORY_TITLECASE_LETTER,         /* Lt */
57  HB_UNICODE_GENERAL_CATEGORY_UPPERCASE_LETTER,         /* Lu */
58  HB_UNICODE_GENERAL_CATEGORY_SPACING_MARK,             /* Mc */
59  HB_UNICODE_GENERAL_CATEGORY_ENCLOSING_MARK,           /* Me */
60  HB_UNICODE_GENERAL_CATEGORY_NON_SPACING_MARK,         /* Mn */
61  HB_UNICODE_GENERAL_CATEGORY_DECIMAL_NUMBER,           /* Nd */
62  HB_UNICODE_GENERAL_CATEGORY_LETTER_NUMBER,            /* Nl */
63  HB_UNICODE_GENERAL_CATEGORY_OTHER_NUMBER,             /* No */
64  HB_UNICODE_GENERAL_CATEGORY_CONNECT_PUNCTUATION,      /* Pc */
65  HB_UNICODE_GENERAL_CATEGORY_DASH_PUNCTUATION,         /* Pd */
66  HB_UNICODE_GENERAL_CATEGORY_CLOSE_PUNCTUATION,        /* Pe */
67  HB_UNICODE_GENERAL_CATEGORY_FINAL_PUNCTUATION,        /* Pf */
68  HB_UNICODE_GENERAL_CATEGORY_INITIAL_PUNCTUATION,      /* Pi */
69  HB_UNICODE_GENERAL_CATEGORY_OTHER_PUNCTUATION,        /* Po */
70  HB_UNICODE_GENERAL_CATEGORY_OPEN_PUNCTUATION,         /* Ps */
71  HB_UNICODE_GENERAL_CATEGORY_CURRENCY_SYMBOL,          /* Sc */
72  HB_UNICODE_GENERAL_CATEGORY_MODIFIER_SYMBOL,          /* Sk */
73  HB_UNICODE_GENERAL_CATEGORY_MATH_SYMBOL,              /* Sm */
74  HB_UNICODE_GENERAL_CATEGORY_OTHER_SYMBOL,             /* So */
75  HB_UNICODE_GENERAL_CATEGORY_LINE_SEPARATOR,           /* Zl */
76  HB_UNICODE_GENERAL_CATEGORY_PARAGRAPH_SEPARATOR,      /* Zp */
77  HB_UNICODE_GENERAL_CATEGORY_SPACE_SEPARATOR           /* Zs */
78} hb_unicode_general_category_t;
79
80/* hb_unicode_combining_class_t */
81
82/* Note: newer versions of Unicode may add new values.  Clients should be ready to handle
83 * any value in the 0..254 range being returned from hb_unicode_combining_class().
84 */
85
86/* Unicode Character Database property: Canonical_Combining_Class (ccc) */
87typedef enum
88{
89  HB_UNICODE_COMBINING_CLASS_NOT_REORDERED      = 0,
90  HB_UNICODE_COMBINING_CLASS_OVERLAY            = 1,
91  HB_UNICODE_COMBINING_CLASS_NUKTA              = 7,
92  HB_UNICODE_COMBINING_CLASS_KANA_VOICING       = 8,
93  HB_UNICODE_COMBINING_CLASS_VIRAMA             = 9,
94
95  /* Hebrew */
96  HB_UNICODE_COMBINING_CLASS_CCC10      =  10,
97  HB_UNICODE_COMBINING_CLASS_CCC11      =  11,
98  HB_UNICODE_COMBINING_CLASS_CCC12      =  12,
99  HB_UNICODE_COMBINING_CLASS_CCC13      =  13,
100  HB_UNICODE_COMBINING_CLASS_CCC14      =  14,
101  HB_UNICODE_COMBINING_CLASS_CCC15      =  15,
102  HB_UNICODE_COMBINING_CLASS_CCC16      =  16,
103  HB_UNICODE_COMBINING_CLASS_CCC17      =  17,
104  HB_UNICODE_COMBINING_CLASS_CCC18      =  18,
105  HB_UNICODE_COMBINING_CLASS_CCC19      =  19,
106  HB_UNICODE_COMBINING_CLASS_CCC20      =  20,
107  HB_UNICODE_COMBINING_CLASS_CCC21      =  21,
108  HB_UNICODE_COMBINING_CLASS_CCC22      =  22,
109  HB_UNICODE_COMBINING_CLASS_CCC23      =  23,
110  HB_UNICODE_COMBINING_CLASS_CCC24      =  24,
111  HB_UNICODE_COMBINING_CLASS_CCC25      =  25,
112  HB_UNICODE_COMBINING_CLASS_CCC26      =  26,
113
114  /* Arabic */
115  HB_UNICODE_COMBINING_CLASS_CCC27      =  27,
116  HB_UNICODE_COMBINING_CLASS_CCC28      =  28,
117  HB_UNICODE_COMBINING_CLASS_CCC29      =  29,
118  HB_UNICODE_COMBINING_CLASS_CCC30      =  30,
119  HB_UNICODE_COMBINING_CLASS_CCC31      =  31,
120  HB_UNICODE_COMBINING_CLASS_CCC32      =  32,
121  HB_UNICODE_COMBINING_CLASS_CCC33      =  33,
122  HB_UNICODE_COMBINING_CLASS_CCC34      =  34,
123  HB_UNICODE_COMBINING_CLASS_CCC35      =  35,
124
125  /* Syriac */
126  HB_UNICODE_COMBINING_CLASS_CCC36      =  36,
127
128  /* Telugu */
129  HB_UNICODE_COMBINING_CLASS_CCC84      =  84,
130  HB_UNICODE_COMBINING_CLASS_CCC91      =  91,
131
132  /* Thai */
133  HB_UNICODE_COMBINING_CLASS_CCC103     = 103,
134  HB_UNICODE_COMBINING_CLASS_CCC107     = 107,
135
136  /* Lao */
137  HB_UNICODE_COMBINING_CLASS_CCC118     = 118,
138  HB_UNICODE_COMBINING_CLASS_CCC122     = 122,
139
140  /* Tibetan */
141  HB_UNICODE_COMBINING_CLASS_CCC129     = 129,
142  HB_UNICODE_COMBINING_CLASS_CCC130     = 130,
143  HB_UNICODE_COMBINING_CLASS_CCC133     = 132,
144
145
146  HB_UNICODE_COMBINING_CLASS_ATTACHED_BELOW_LEFT        = 200,
147  HB_UNICODE_COMBINING_CLASS_ATTACHED_BELOW             = 202,
148  HB_UNICODE_COMBINING_CLASS_ATTACHED_ABOVE             = 214,
149  HB_UNICODE_COMBINING_CLASS_ATTACHED_ABOVE_RIGHT       = 216,
150  HB_UNICODE_COMBINING_CLASS_BELOW_LEFT                 = 218,
151  HB_UNICODE_COMBINING_CLASS_BELOW                      = 220,
152  HB_UNICODE_COMBINING_CLASS_BELOW_RIGHT                = 222,
153  HB_UNICODE_COMBINING_CLASS_LEFT                       = 224,
154  HB_UNICODE_COMBINING_CLASS_RIGHT                      = 226,
155  HB_UNICODE_COMBINING_CLASS_ABOVE_LEFT                 = 228,
156  HB_UNICODE_COMBINING_CLASS_ABOVE                      = 230,
157  HB_UNICODE_COMBINING_CLASS_ABOVE_RIGHT                = 232,
158  HB_UNICODE_COMBINING_CLASS_DOUBLE_BELOW               = 233,
159  HB_UNICODE_COMBINING_CLASS_DOUBLE_ABOVE               = 234,
160
161  HB_UNICODE_COMBINING_CLASS_IOTA_SUBSCRIPT             = 240,
162
163  HB_UNICODE_COMBINING_CLASS_INVALID    = 255
164} hb_unicode_combining_class_t;
165
166
167/*
168 * hb_unicode_funcs_t
169 */
170
171typedef struct hb_unicode_funcs_t hb_unicode_funcs_t;
172
173
174/*
175 * just give me the best implementation you've got there.
176 */
177HB_EXTERN hb_unicode_funcs_t *
178hb_unicode_funcs_get_default (void);
179
180
181HB_EXTERN hb_unicode_funcs_t *
182hb_unicode_funcs_create (hb_unicode_funcs_t *parent);
183
184HB_EXTERN hb_unicode_funcs_t *
185hb_unicode_funcs_get_empty (void);
186
187HB_EXTERN hb_unicode_funcs_t *
188hb_unicode_funcs_reference (hb_unicode_funcs_t *ufuncs);
189
190HB_EXTERN void
191hb_unicode_funcs_destroy (hb_unicode_funcs_t *ufuncs);
192
193HB_EXTERN hb_bool_t
194hb_unicode_funcs_set_user_data (hb_unicode_funcs_t *ufuncs,
195                                hb_user_data_key_t *key,
196                                void *              data,
197                                hb_destroy_func_t   destroy,
198                                hb_bool_t           replace);
199
200
201HB_EXTERN void *
202hb_unicode_funcs_get_user_data (hb_unicode_funcs_t *ufuncs,
203                                hb_user_data_key_t *key);
204
205
206HB_EXTERN void
207hb_unicode_funcs_make_immutable (hb_unicode_funcs_t *ufuncs);
208
209HB_EXTERN hb_bool_t
210hb_unicode_funcs_is_immutable (hb_unicode_funcs_t *ufuncs);
211
212HB_EXTERN hb_unicode_funcs_t *
213hb_unicode_funcs_get_parent (hb_unicode_funcs_t *ufuncs);
214
215
216/*
217 * funcs
218 */
219
220/* typedefs */
221
222typedef hb_unicode_combining_class_t    (*hb_unicode_combining_class_func_t)    (hb_unicode_funcs_t *ufuncs,
223                                                                                 hb_codepoint_t      unicode,
224                                                                                 void               *user_data);
225typedef unsigned int                    (*hb_unicode_eastasian_width_func_t)    (hb_unicode_funcs_t *ufuncs,
226                                                                                 hb_codepoint_t      unicode,
227                                                                                 void               *user_data);
228typedef hb_unicode_general_category_t   (*hb_unicode_general_category_func_t)   (hb_unicode_funcs_t *ufuncs,
229                                                                                 hb_codepoint_t      unicode,
230                                                                                 void               *user_data);
231typedef hb_codepoint_t                  (*hb_unicode_mirroring_func_t)          (hb_unicode_funcs_t *ufuncs,
232                                                                                 hb_codepoint_t      unicode,
233                                                                                 void               *user_data);
234typedef hb_script_t                     (*hb_unicode_script_func_t)             (hb_unicode_funcs_t *ufuncs,
235                                                                                 hb_codepoint_t      unicode,
236                                                                                 void               *user_data);
237
238typedef hb_bool_t                       (*hb_unicode_compose_func_t)            (hb_unicode_funcs_t *ufuncs,
239                                                                                 hb_codepoint_t      a,
240                                                                                 hb_codepoint_t      b,
241                                                                                 hb_codepoint_t     *ab,
242                                                                                 void               *user_data);
243typedef hb_bool_t                       (*hb_unicode_decompose_func_t)          (hb_unicode_funcs_t *ufuncs,
244                                                                                 hb_codepoint_t      ab,
245                                                                                 hb_codepoint_t     *a,
246                                                                                 hb_codepoint_t     *b,
247                                                                                 void               *user_data);
248
249/**
250 * hb_unicode_decompose_compatibility_func_t:
251 * @ufuncs: a Unicode function structure
252 * @u: codepoint to decompose
253 * @decomposed: address of codepoint array (of length %HB_UNICODE_MAX_DECOMPOSITION_LEN) to write decomposition into
254 * @user_data: user data pointer as passed to hb_unicode_funcs_set_decompose_compatibility_func()
255 *
256 * Fully decompose @u to its Unicode compatibility decomposition. The codepoints of the decomposition will be written to @decomposed.
257 * The complete length of the decomposition will be returned.
258 *
259 * If @u has no compatibility decomposition, zero should be returned.
260 *
261 * The Unicode standard guarantees that a buffer of length %HB_UNICODE_MAX_DECOMPOSITION_LEN codepoints will always be sufficient for any
262 * compatibility decomposition plus an terminating value of 0.  Consequently, @decompose must be allocated by the caller to be at least this length.  Implementations
263 * of this function type must ensure that they do not write past the provided array.
264 *
265 * Return value: number of codepoints in the full compatibility decomposition of @u, or 0 if no decomposition available.
266 */
267typedef unsigned int                    (*hb_unicode_decompose_compatibility_func_t)    (hb_unicode_funcs_t *ufuncs,
268                                                                                         hb_codepoint_t      u,
269                                                                                         hb_codepoint_t     *decomposed,
270                                                                                         void               *user_data);
271
272/* See Unicode 6.1 for details on the maximum decomposition length. */
273#define HB_UNICODE_MAX_DECOMPOSITION_LEN (18+1) /* codepoints */
274
275/* setters */
276
277/**
278 * hb_unicode_funcs_set_combining_class_func:
279 * @ufuncs: a Unicode function structure
280 * @func: (closure user_data) (destroy destroy) (scope notified):
281 * @user_data:
282 * @destroy:
283 *
284 *
285 *
286 * Since: 0.9.2
287 **/
288HB_EXTERN void
289hb_unicode_funcs_set_combining_class_func (hb_unicode_funcs_t *ufuncs,
290                                           hb_unicode_combining_class_func_t func,
291                                           void *user_data, hb_destroy_func_t destroy);
292
293/**
294 * hb_unicode_funcs_set_eastasian_width_func:
295 * @ufuncs: a Unicode function structure
296 * @func: (closure user_data) (destroy destroy) (scope notified):
297 * @user_data:
298 * @destroy:
299 *
300 *
301 *
302 * Since: 0.9.2
303 **/
304HB_EXTERN void
305hb_unicode_funcs_set_eastasian_width_func (hb_unicode_funcs_t *ufuncs,
306                                           hb_unicode_eastasian_width_func_t func,
307                                           void *user_data, hb_destroy_func_t destroy);
308
309/**
310 * hb_unicode_funcs_set_general_category_func:
311 * @ufuncs: a Unicode function structure
312 * @func: (closure user_data) (destroy destroy) (scope notified):
313 * @user_data:
314 * @destroy:
315 *
316 *
317 *
318 * Since: 0.9.2
319 **/
320HB_EXTERN void
321hb_unicode_funcs_set_general_category_func (hb_unicode_funcs_t *ufuncs,
322                                            hb_unicode_general_category_func_t func,
323                                            void *user_data, hb_destroy_func_t destroy);
324
325/**
326 * hb_unicode_funcs_set_mirroring_func:
327 * @ufuncs: a Unicode function structure
328 * @func: (closure user_data) (destroy destroy) (scope notified):
329 * @user_data:
330 * @destroy:
331 *
332 *
333 *
334 * Since: 0.9.2
335 **/
336HB_EXTERN void
337hb_unicode_funcs_set_mirroring_func (hb_unicode_funcs_t *ufuncs,
338                                     hb_unicode_mirroring_func_t func,
339                                     void *user_data, hb_destroy_func_t destroy);
340
341/**
342 * hb_unicode_funcs_set_script_func:
343 * @ufuncs: a Unicode function structure
344 * @func: (closure user_data) (destroy destroy) (scope notified):
345 * @user_data:
346 * @destroy:
347 *
348 *
349 *
350 * Since: 0.9.2
351 **/
352HB_EXTERN void
353hb_unicode_funcs_set_script_func (hb_unicode_funcs_t *ufuncs,
354                                  hb_unicode_script_func_t func,
355                                  void *user_data, hb_destroy_func_t destroy);
356
357/**
358 * hb_unicode_funcs_set_compose_func:
359 * @ufuncs: a Unicode function structure
360 * @func: (closure user_data) (destroy destroy) (scope notified):
361 * @user_data:
362 * @destroy:
363 *
364 *
365 *
366 * Since: 0.9.2
367 **/
368HB_EXTERN void
369hb_unicode_funcs_set_compose_func (hb_unicode_funcs_t *ufuncs,
370                                   hb_unicode_compose_func_t func,
371                                   void *user_data, hb_destroy_func_t destroy);
372
373/**
374 * hb_unicode_funcs_set_decompose_func:
375 * @ufuncs: a Unicode function structure
376 * @func: (closure user_data) (destroy destroy) (scope notified):
377 * @user_data:
378 * @destroy:
379 *
380 *
381 *
382 * Since: 0.9.2
383 **/
384HB_EXTERN void
385hb_unicode_funcs_set_decompose_func (hb_unicode_funcs_t *ufuncs,
386                                     hb_unicode_decompose_func_t func,
387                                     void *user_data, hb_destroy_func_t destroy);
388
389/**
390 * hb_unicode_funcs_set_decompose_compatibility_func:
391 * @ufuncs: a Unicode function structure
392 * @func: (closure user_data) (destroy destroy) (scope notified):
393 * @user_data:
394 * @destroy:
395 *
396 *
397 *
398 * Since: 0.9.2
399 **/
400HB_EXTERN void
401hb_unicode_funcs_set_decompose_compatibility_func (hb_unicode_funcs_t *ufuncs,
402                                                   hb_unicode_decompose_compatibility_func_t func,
403                                                   void *user_data, hb_destroy_func_t destroy);
404
405/* accessors */
406
407/**
408 * hb_unicode_combining_class:
409 *
410 * Since: 0.9.2
411 **/
412HB_EXTERN hb_unicode_combining_class_t
413hb_unicode_combining_class (hb_unicode_funcs_t *ufuncs,
414                            hb_codepoint_t unicode);
415
416/**
417 * hb_unicode_eastasian_width:
418 *
419 * Since: 0.9.2
420 **/
421HB_EXTERN unsigned int
422hb_unicode_eastasian_width (hb_unicode_funcs_t *ufuncs,
423                            hb_codepoint_t unicode);
424
425/**
426 * hb_unicode_general_category:
427 *
428 * Since: 0.9.2
429 **/
430HB_EXTERN hb_unicode_general_category_t
431hb_unicode_general_category (hb_unicode_funcs_t *ufuncs,
432                             hb_codepoint_t unicode);
433
434/**
435 * hb_unicode_mirroring:
436 *
437 * Since: 0.9.2
438 **/
439HB_EXTERN hb_codepoint_t
440hb_unicode_mirroring (hb_unicode_funcs_t *ufuncs,
441                      hb_codepoint_t unicode);
442
443/**
444 * hb_unicode_script:
445 *
446 * Since: 0.9.2
447 **/
448HB_EXTERN hb_script_t
449hb_unicode_script (hb_unicode_funcs_t *ufuncs,
450                   hb_codepoint_t unicode);
451
452HB_EXTERN hb_bool_t
453hb_unicode_compose (hb_unicode_funcs_t *ufuncs,
454                    hb_codepoint_t      a,
455                    hb_codepoint_t      b,
456                    hb_codepoint_t     *ab);
457
458HB_EXTERN hb_bool_t
459hb_unicode_decompose (hb_unicode_funcs_t *ufuncs,
460                      hb_codepoint_t      ab,
461                      hb_codepoint_t     *a,
462                      hb_codepoint_t     *b);
463
464HB_EXTERN unsigned int
465hb_unicode_decompose_compatibility (hb_unicode_funcs_t *ufuncs,
466                                    hb_codepoint_t      u,
467                                    hb_codepoint_t     *decomposed);
468
469HB_END_DECLS
470
471#endif /* HB_UNICODE_H */
472