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 
40 HB_BEGIN_DECLS
41 
42 
43 /**
44  * HB_UNICODE_MAX
45  *
46  * Since: 1.9.0
47  **/
48 #define HB_UNICODE_MAX 0x10FFFFu
49 
50 
51 /* hb_unicode_general_category_t */
52 
53 /* Unicode Character Database property: General_Category (gc) */
54 typedef enum
55 {
56   HB_UNICODE_GENERAL_CATEGORY_CONTROL,			/* Cc */
57   HB_UNICODE_GENERAL_CATEGORY_FORMAT,			/* Cf */
58   HB_UNICODE_GENERAL_CATEGORY_UNASSIGNED,		/* Cn */
59   HB_UNICODE_GENERAL_CATEGORY_PRIVATE_USE,		/* Co */
60   HB_UNICODE_GENERAL_CATEGORY_SURROGATE,		/* Cs */
61   HB_UNICODE_GENERAL_CATEGORY_LOWERCASE_LETTER,		/* Ll */
62   HB_UNICODE_GENERAL_CATEGORY_MODIFIER_LETTER,		/* Lm */
63   HB_UNICODE_GENERAL_CATEGORY_OTHER_LETTER,		/* Lo */
64   HB_UNICODE_GENERAL_CATEGORY_TITLECASE_LETTER,		/* Lt */
65   HB_UNICODE_GENERAL_CATEGORY_UPPERCASE_LETTER,		/* Lu */
66   HB_UNICODE_GENERAL_CATEGORY_SPACING_MARK,		/* Mc */
67   HB_UNICODE_GENERAL_CATEGORY_ENCLOSING_MARK,		/* Me */
68   HB_UNICODE_GENERAL_CATEGORY_NON_SPACING_MARK,		/* Mn */
69   HB_UNICODE_GENERAL_CATEGORY_DECIMAL_NUMBER,		/* Nd */
70   HB_UNICODE_GENERAL_CATEGORY_LETTER_NUMBER,		/* Nl */
71   HB_UNICODE_GENERAL_CATEGORY_OTHER_NUMBER,		/* No */
72   HB_UNICODE_GENERAL_CATEGORY_CONNECT_PUNCTUATION,	/* Pc */
73   HB_UNICODE_GENERAL_CATEGORY_DASH_PUNCTUATION,		/* Pd */
74   HB_UNICODE_GENERAL_CATEGORY_CLOSE_PUNCTUATION,	/* Pe */
75   HB_UNICODE_GENERAL_CATEGORY_FINAL_PUNCTUATION,	/* Pf */
76   HB_UNICODE_GENERAL_CATEGORY_INITIAL_PUNCTUATION,	/* Pi */
77   HB_UNICODE_GENERAL_CATEGORY_OTHER_PUNCTUATION,	/* Po */
78   HB_UNICODE_GENERAL_CATEGORY_OPEN_PUNCTUATION,		/* Ps */
79   HB_UNICODE_GENERAL_CATEGORY_CURRENCY_SYMBOL,		/* Sc */
80   HB_UNICODE_GENERAL_CATEGORY_MODIFIER_SYMBOL,		/* Sk */
81   HB_UNICODE_GENERAL_CATEGORY_MATH_SYMBOL,		/* Sm */
82   HB_UNICODE_GENERAL_CATEGORY_OTHER_SYMBOL,		/* So */
83   HB_UNICODE_GENERAL_CATEGORY_LINE_SEPARATOR,		/* Zl */
84   HB_UNICODE_GENERAL_CATEGORY_PARAGRAPH_SEPARATOR,	/* Zp */
85   HB_UNICODE_GENERAL_CATEGORY_SPACE_SEPARATOR		/* Zs */
86 } hb_unicode_general_category_t;
87 
88 /* hb_unicode_combining_class_t */
89 
90 /* Note: newer versions of Unicode may add new values.  Clients should be ready to handle
91  * any value in the 0..254 range being returned from hb_unicode_combining_class().
92  */
93 
94 /* Unicode Character Database property: Canonical_Combining_Class (ccc) */
95 typedef enum
96 {
97   HB_UNICODE_COMBINING_CLASS_NOT_REORDERED	= 0,
98   HB_UNICODE_COMBINING_CLASS_OVERLAY		= 1,
99   HB_UNICODE_COMBINING_CLASS_NUKTA		= 7,
100   HB_UNICODE_COMBINING_CLASS_KANA_VOICING	= 8,
101   HB_UNICODE_COMBINING_CLASS_VIRAMA		= 9,
102 
103   /* Hebrew */
104   HB_UNICODE_COMBINING_CLASS_CCC10	=  10,
105   HB_UNICODE_COMBINING_CLASS_CCC11	=  11,
106   HB_UNICODE_COMBINING_CLASS_CCC12	=  12,
107   HB_UNICODE_COMBINING_CLASS_CCC13	=  13,
108   HB_UNICODE_COMBINING_CLASS_CCC14	=  14,
109   HB_UNICODE_COMBINING_CLASS_CCC15	=  15,
110   HB_UNICODE_COMBINING_CLASS_CCC16	=  16,
111   HB_UNICODE_COMBINING_CLASS_CCC17	=  17,
112   HB_UNICODE_COMBINING_CLASS_CCC18	=  18,
113   HB_UNICODE_COMBINING_CLASS_CCC19	=  19,
114   HB_UNICODE_COMBINING_CLASS_CCC20	=  20,
115   HB_UNICODE_COMBINING_CLASS_CCC21	=  21,
116   HB_UNICODE_COMBINING_CLASS_CCC22	=  22,
117   HB_UNICODE_COMBINING_CLASS_CCC23	=  23,
118   HB_UNICODE_COMBINING_CLASS_CCC24	=  24,
119   HB_UNICODE_COMBINING_CLASS_CCC25	=  25,
120   HB_UNICODE_COMBINING_CLASS_CCC26	=  26,
121 
122   /* Arabic */
123   HB_UNICODE_COMBINING_CLASS_CCC27	=  27,
124   HB_UNICODE_COMBINING_CLASS_CCC28	=  28,
125   HB_UNICODE_COMBINING_CLASS_CCC29	=  29,
126   HB_UNICODE_COMBINING_CLASS_CCC30	=  30,
127   HB_UNICODE_COMBINING_CLASS_CCC31	=  31,
128   HB_UNICODE_COMBINING_CLASS_CCC32	=  32,
129   HB_UNICODE_COMBINING_CLASS_CCC33	=  33,
130   HB_UNICODE_COMBINING_CLASS_CCC34	=  34,
131   HB_UNICODE_COMBINING_CLASS_CCC35	=  35,
132 
133   /* Syriac */
134   HB_UNICODE_COMBINING_CLASS_CCC36	=  36,
135 
136   /* Telugu */
137   HB_UNICODE_COMBINING_CLASS_CCC84	=  84,
138   HB_UNICODE_COMBINING_CLASS_CCC91	=  91,
139 
140   /* Thai */
141   HB_UNICODE_COMBINING_CLASS_CCC103	= 103,
142   HB_UNICODE_COMBINING_CLASS_CCC107	= 107,
143 
144   /* Lao */
145   HB_UNICODE_COMBINING_CLASS_CCC118	= 118,
146   HB_UNICODE_COMBINING_CLASS_CCC122	= 122,
147 
148   /* Tibetan */
149   HB_UNICODE_COMBINING_CLASS_CCC129	= 129,
150   HB_UNICODE_COMBINING_CLASS_CCC130	= 130,
151   HB_UNICODE_COMBINING_CLASS_CCC133	= 132,
152 
153 
154   HB_UNICODE_COMBINING_CLASS_ATTACHED_BELOW_LEFT	= 200,
155   HB_UNICODE_COMBINING_CLASS_ATTACHED_BELOW		= 202,
156   HB_UNICODE_COMBINING_CLASS_ATTACHED_ABOVE		= 214,
157   HB_UNICODE_COMBINING_CLASS_ATTACHED_ABOVE_RIGHT	= 216,
158   HB_UNICODE_COMBINING_CLASS_BELOW_LEFT			= 218,
159   HB_UNICODE_COMBINING_CLASS_BELOW			= 220,
160   HB_UNICODE_COMBINING_CLASS_BELOW_RIGHT		= 222,
161   HB_UNICODE_COMBINING_CLASS_LEFT			= 224,
162   HB_UNICODE_COMBINING_CLASS_RIGHT			= 226,
163   HB_UNICODE_COMBINING_CLASS_ABOVE_LEFT			= 228,
164   HB_UNICODE_COMBINING_CLASS_ABOVE			= 230,
165   HB_UNICODE_COMBINING_CLASS_ABOVE_RIGHT		= 232,
166   HB_UNICODE_COMBINING_CLASS_DOUBLE_BELOW		= 233,
167   HB_UNICODE_COMBINING_CLASS_DOUBLE_ABOVE		= 234,
168 
169   HB_UNICODE_COMBINING_CLASS_IOTA_SUBSCRIPT		= 240,
170 
171   HB_UNICODE_COMBINING_CLASS_INVALID	= 255
172 } hb_unicode_combining_class_t;
173 
174 
175 /*
176  * hb_unicode_funcs_t
177  */
178 
179 typedef struct hb_unicode_funcs_t hb_unicode_funcs_t;
180 
181 
182 /*
183  * just give me the best implementation you've got there.
184  */
185 HB_EXTERN hb_unicode_funcs_t *
186 hb_unicode_funcs_get_default (void);
187 
188 
189 HB_EXTERN hb_unicode_funcs_t *
190 hb_unicode_funcs_create (hb_unicode_funcs_t *parent);
191 
192 HB_EXTERN hb_unicode_funcs_t *
193 hb_unicode_funcs_get_empty (void);
194 
195 HB_EXTERN hb_unicode_funcs_t *
196 hb_unicode_funcs_reference (hb_unicode_funcs_t *ufuncs);
197 
198 HB_EXTERN void
199 hb_unicode_funcs_destroy (hb_unicode_funcs_t *ufuncs);
200 
201 HB_EXTERN hb_bool_t
202 hb_unicode_funcs_set_user_data (hb_unicode_funcs_t *ufuncs,
203 				hb_user_data_key_t *key,
204 				void *              data,
205 				hb_destroy_func_t   destroy,
206 				hb_bool_t           replace);
207 
208 
209 HB_EXTERN void *
210 hb_unicode_funcs_get_user_data (hb_unicode_funcs_t *ufuncs,
211 				hb_user_data_key_t *key);
212 
213 
214 HB_EXTERN void
215 hb_unicode_funcs_make_immutable (hb_unicode_funcs_t *ufuncs);
216 
217 HB_EXTERN hb_bool_t
218 hb_unicode_funcs_is_immutable (hb_unicode_funcs_t *ufuncs);
219 
220 HB_EXTERN hb_unicode_funcs_t *
221 hb_unicode_funcs_get_parent (hb_unicode_funcs_t *ufuncs);
222 
223 
224 /*
225  * funcs
226  */
227 
228 /* typedefs */
229 
230 typedef hb_unicode_combining_class_t	(*hb_unicode_combining_class_func_t)	(hb_unicode_funcs_t *ufuncs,
231 										 hb_codepoint_t      unicode,
232 										 void               *user_data);
233 typedef hb_unicode_general_category_t	(*hb_unicode_general_category_func_t)	(hb_unicode_funcs_t *ufuncs,
234 										 hb_codepoint_t      unicode,
235 										 void               *user_data);
236 typedef hb_codepoint_t			(*hb_unicode_mirroring_func_t)		(hb_unicode_funcs_t *ufuncs,
237 										 hb_codepoint_t      unicode,
238 										 void               *user_data);
239 typedef hb_script_t			(*hb_unicode_script_func_t)		(hb_unicode_funcs_t *ufuncs,
240 										 hb_codepoint_t      unicode,
241 										 void               *user_data);
242 
243 typedef hb_bool_t			(*hb_unicode_compose_func_t)		(hb_unicode_funcs_t *ufuncs,
244 										 hb_codepoint_t      a,
245 										 hb_codepoint_t      b,
246 										 hb_codepoint_t     *ab,
247 										 void               *user_data);
248 typedef hb_bool_t			(*hb_unicode_decompose_func_t)		(hb_unicode_funcs_t *ufuncs,
249 										 hb_codepoint_t      ab,
250 										 hb_codepoint_t     *a,
251 										 hb_codepoint_t     *b,
252 										 void               *user_data);
253 
254 /* setters */
255 
256 /**
257  * hb_unicode_funcs_set_combining_class_func:
258  * @ufuncs: a Unicode function structure
259  * @func: (closure user_data) (destroy destroy) (scope notified):
260  * @user_data:
261  * @destroy:
262  *
263  *
264  *
265  * Since: 0.9.2
266  **/
267 HB_EXTERN void
268 hb_unicode_funcs_set_combining_class_func (hb_unicode_funcs_t *ufuncs,
269 					   hb_unicode_combining_class_func_t func,
270 					   void *user_data, hb_destroy_func_t destroy);
271 
272 /**
273  * hb_unicode_funcs_set_general_category_func:
274  * @ufuncs: a Unicode function structure
275  * @func: (closure user_data) (destroy destroy) (scope notified):
276  * @user_data:
277  * @destroy:
278  *
279  *
280  *
281  * Since: 0.9.2
282  **/
283 HB_EXTERN void
284 hb_unicode_funcs_set_general_category_func (hb_unicode_funcs_t *ufuncs,
285 					    hb_unicode_general_category_func_t func,
286 					    void *user_data, hb_destroy_func_t destroy);
287 
288 /**
289  * hb_unicode_funcs_set_mirroring_func:
290  * @ufuncs: a Unicode function structure
291  * @func: (closure user_data) (destroy destroy) (scope notified):
292  * @user_data:
293  * @destroy:
294  *
295  *
296  *
297  * Since: 0.9.2
298  **/
299 HB_EXTERN void
300 hb_unicode_funcs_set_mirroring_func (hb_unicode_funcs_t *ufuncs,
301 				     hb_unicode_mirroring_func_t func,
302 				     void *user_data, hb_destroy_func_t destroy);
303 
304 /**
305  * hb_unicode_funcs_set_script_func:
306  * @ufuncs: a Unicode function structure
307  * @func: (closure user_data) (destroy destroy) (scope notified):
308  * @user_data:
309  * @destroy:
310  *
311  *
312  *
313  * Since: 0.9.2
314  **/
315 HB_EXTERN void
316 hb_unicode_funcs_set_script_func (hb_unicode_funcs_t *ufuncs,
317 				  hb_unicode_script_func_t func,
318 				  void *user_data, hb_destroy_func_t destroy);
319 
320 /**
321  * hb_unicode_funcs_set_compose_func:
322  * @ufuncs: a Unicode function structure
323  * @func: (closure user_data) (destroy destroy) (scope notified):
324  * @user_data:
325  * @destroy:
326  *
327  *
328  *
329  * Since: 0.9.2
330  **/
331 HB_EXTERN void
332 hb_unicode_funcs_set_compose_func (hb_unicode_funcs_t *ufuncs,
333 				   hb_unicode_compose_func_t func,
334 				   void *user_data, hb_destroy_func_t destroy);
335 
336 /**
337  * hb_unicode_funcs_set_decompose_func:
338  * @ufuncs: a Unicode function structure
339  * @func: (closure user_data) (destroy destroy) (scope notified):
340  * @user_data:
341  * @destroy:
342  *
343  *
344  *
345  * Since: 0.9.2
346  **/
347 HB_EXTERN void
348 hb_unicode_funcs_set_decompose_func (hb_unicode_funcs_t *ufuncs,
349 				     hb_unicode_decompose_func_t func,
350 				     void *user_data, hb_destroy_func_t destroy);
351 
352 /* accessors */
353 
354 /**
355  * hb_unicode_combining_class:
356  *
357  * Since: 0.9.2
358  **/
359 HB_EXTERN hb_unicode_combining_class_t
360 hb_unicode_combining_class (hb_unicode_funcs_t *ufuncs,
361 			    hb_codepoint_t unicode);
362 
363 /**
364  * hb_unicode_general_category:
365  *
366  * Since: 0.9.2
367  **/
368 HB_EXTERN hb_unicode_general_category_t
369 hb_unicode_general_category (hb_unicode_funcs_t *ufuncs,
370 			     hb_codepoint_t unicode);
371 
372 /**
373  * hb_unicode_mirroring:
374  *
375  * Since: 0.9.2
376  **/
377 HB_EXTERN hb_codepoint_t
378 hb_unicode_mirroring (hb_unicode_funcs_t *ufuncs,
379 		      hb_codepoint_t unicode);
380 
381 /**
382  * hb_unicode_script:
383  *
384  * Since: 0.9.2
385  **/
386 HB_EXTERN hb_script_t
387 hb_unicode_script (hb_unicode_funcs_t *ufuncs,
388 		   hb_codepoint_t unicode);
389 
390 HB_EXTERN hb_bool_t
391 hb_unicode_compose (hb_unicode_funcs_t *ufuncs,
392 		    hb_codepoint_t      a,
393 		    hb_codepoint_t      b,
394 		    hb_codepoint_t     *ab);
395 
396 HB_EXTERN hb_bool_t
397 hb_unicode_decompose (hb_unicode_funcs_t *ufuncs,
398 		      hb_codepoint_t      ab,
399 		      hb_codepoint_t     *a,
400 		      hb_codepoint_t     *b);
401 
402 HB_END_DECLS
403 
404 #endif /* HB_UNICODE_H */
405