/src/harfbuzz/src/hb-unicode.hh
Line | Count | Source (jump to first uncovered line) |
1 | | /* |
2 | | * Copyright © 2009 Red Hat, Inc. |
3 | | * Copyright © 2011 Codethink Limited |
4 | | * Copyright © 2010,2011,2012 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_UNICODE_HH |
32 | | #define HB_UNICODE_HH |
33 | | |
34 | | #include "hb.hh" |
35 | | |
36 | | |
37 | | extern HB_INTERNAL const uint8_t _hb_modified_combining_class[256]; |
38 | | |
39 | | /* |
40 | | * hb_unicode_funcs_t |
41 | | */ |
42 | | |
43 | | #define HB_UNICODE_FUNCS_IMPLEMENT_CALLBACKS \ |
44 | 1 | HB_UNICODE_FUNC_IMPLEMENT (combining_class) \ |
45 | 1 | HB_IF_NOT_DEPRECATED (HB_UNICODE_FUNC_IMPLEMENT (eastasian_width)) \ |
46 | 1 | HB_UNICODE_FUNC_IMPLEMENT (general_category) \ |
47 | 1 | HB_UNICODE_FUNC_IMPLEMENT (mirroring) \ |
48 | 1 | HB_UNICODE_FUNC_IMPLEMENT (script) \ |
49 | 1 | HB_UNICODE_FUNC_IMPLEMENT (compose) \ |
50 | 1 | HB_UNICODE_FUNC_IMPLEMENT (decompose) \ |
51 | 1 | HB_IF_NOT_DEPRECATED (HB_UNICODE_FUNC_IMPLEMENT (decompose_compatibility)) \ |
52 | | /* ^--- Add new callbacks here */ |
53 | | |
54 | | /* Simple callbacks are those taking a hb_codepoint_t and returning a hb_codepoint_t */ |
55 | | #define HB_UNICODE_FUNCS_IMPLEMENT_CALLBACKS_SIMPLE \ |
56 | | HB_UNICODE_FUNC_IMPLEMENT (hb_unicode_combining_class_t, combining_class) \ |
57 | | HB_IF_NOT_DEPRECATED (HB_UNICODE_FUNC_IMPLEMENT (unsigned int, eastasian_width)) \ |
58 | | HB_UNICODE_FUNC_IMPLEMENT (hb_unicode_general_category_t, general_category) \ |
59 | | HB_UNICODE_FUNC_IMPLEMENT (hb_codepoint_t, mirroring) \ |
60 | | HB_UNICODE_FUNC_IMPLEMENT (hb_script_t, script) \ |
61 | | /* ^--- Add new simple callbacks here */ |
62 | | |
63 | | struct hb_unicode_funcs_t |
64 | | { |
65 | | hb_object_header_t header; |
66 | | |
67 | | hb_unicode_funcs_t *parent; |
68 | | |
69 | | #define HB_UNICODE_FUNC_IMPLEMENT(return_type, name) \ |
70 | 1.96M | return_type name (hb_codepoint_t unicode) { return func.name (this, unicode, user_data.name); } hb_unicode_funcs_t::script(unsigned int) Line | Count | Source | 70 | 982k | return_type name (hb_codepoint_t unicode) { return func.name (this, unicode, user_data.name); } |
hb_unicode_funcs_t::combining_class(unsigned int) Line | Count | Source | 70 | 71 | return_type name (hb_codepoint_t unicode) { return func.name (this, unicode, user_data.name); } |
hb_unicode_funcs_t::general_category(unsigned int) Line | Count | Source | 70 | 979k | return_type name (hb_codepoint_t unicode) { return func.name (this, unicode, user_data.name); } |
hb_unicode_funcs_t::mirroring(unsigned int) Line | Count | Source | 70 | 32 | return_type name (hb_codepoint_t unicode) { return func.name (this, unicode, user_data.name); } |
|
71 | | HB_UNICODE_FUNCS_IMPLEMENT_CALLBACKS_SIMPLE |
72 | | #undef HB_UNICODE_FUNC_IMPLEMENT |
73 | | |
74 | | hb_bool_t compose (hb_codepoint_t a, hb_codepoint_t b, |
75 | | hb_codepoint_t *ab) |
76 | 68 | { |
77 | 68 | *ab = 0; |
78 | 68 | if (unlikely (!a || !b)) return false; |
79 | 68 | return func.compose (this, a, b, ab, user_data.compose); |
80 | 68 | } |
81 | | |
82 | | hb_bool_t decompose (hb_codepoint_t ab, |
83 | | hb_codepoint_t *a, hb_codepoint_t *b) |
84 | 28.1k | { |
85 | 28.1k | *a = ab; *b = 0; |
86 | 28.1k | return func.decompose (this, ab, a, b, user_data.decompose); |
87 | 28.1k | } |
88 | | |
89 | | unsigned int decompose_compatibility (hb_codepoint_t u, |
90 | | hb_codepoint_t *decomposed) |
91 | 0 | { |
92 | | #ifdef HB_DISABLE_DEPRECATED |
93 | | unsigned int ret = 0; |
94 | | #else |
95 | 0 | unsigned int ret = func.decompose_compatibility (this, u, decomposed, user_data.decompose_compatibility); |
96 | 0 | #endif |
97 | 0 | if (ret == 1 && u == decomposed[0]) { |
98 | 0 | decomposed[0] = 0; |
99 | 0 | return 0; |
100 | 0 | } |
101 | 0 | decomposed[ret] = 0; |
102 | 0 | return ret; |
103 | 0 | } |
104 | | |
105 | | unsigned int |
106 | | modified_combining_class (hb_codepoint_t u) |
107 | 71 | { |
108 | | /* Reorder SAKOT to ensure it comes after any tone marks. */ |
109 | 71 | if (unlikely (u == 0x1A60u)) return 254; |
110 | | /* Reorder PADMA to ensure it comes after any vowel marks. */ |
111 | 71 | if (unlikely (u == 0x0FC6u)) return 254; |
112 | | /* Reorder TSA -PHRU to reorder before U+0F74 */ |
113 | 71 | if (unlikely (u == 0x0F39u)) return 127; |
114 | | |
115 | 71 | return _hb_modified_combining_class[combining_class (u)]; |
116 | 71 | } |
117 | | |
118 | | static hb_bool_t |
119 | | is_variation_selector (hb_codepoint_t unicode) |
120 | 136 | { |
121 | | /* U+180B..180D, U+180F MONGOLIAN FREE VARIATION SELECTORs are handled in the |
122 | | * Arabic shaper. No need to match them here. */ |
123 | 136 | return unlikely (hb_in_ranges<hb_codepoint_t> (unicode, |
124 | 136 | 0xFE00u, 0xFE0Fu, /* VARIATION SELECTOR-1..16 */ |
125 | 136 | 0xE0100u, 0xE01EFu)); /* VARIATION SELECTOR-17..256 */ |
126 | 136 | } |
127 | | |
128 | | /* Default_Ignorable codepoints: |
129 | | * |
130 | | * Note: While U+115F, U+1160, U+3164 and U+FFA0 are Default_Ignorable, |
131 | | * we do NOT want to hide them, as the way Uniscribe has implemented them |
132 | | * is with regular spacing glyphs, and that's the way fonts are made to work. |
133 | | * As such, we make exceptions for those four. |
134 | | * Also ignoring U+1BCA0..1BCA3. https://github.com/harfbuzz/harfbuzz/issues/503 |
135 | | * |
136 | | * Unicode 14.0: |
137 | | * $ grep '; Default_Ignorable_Code_Point ' DerivedCoreProperties.txt | sed 's/;.*#/#/' |
138 | | * 00AD # Cf SOFT HYPHEN |
139 | | * 034F # Mn COMBINING GRAPHEME JOINER |
140 | | * 061C # Cf ARABIC LETTER MARK |
141 | | * 115F..1160 # Lo [2] HANGUL CHOSEONG FILLER..HANGUL JUNGSEONG FILLER |
142 | | * 17B4..17B5 # Mn [2] KHMER VOWEL INHERENT AQ..KHMER VOWEL INHERENT AA |
143 | | * 180B..180D # Mn [3] MONGOLIAN FREE VARIATION SELECTOR ONE..MONGOLIAN FREE VARIATION SELECTOR THREE |
144 | | * 180E # Cf MONGOLIAN VOWEL SEPARATOR |
145 | | * 180F # Mn MONGOLIAN FREE VARIATION SELECTOR FOUR |
146 | | * 200B..200F # Cf [5] ZERO WIDTH SPACE..RIGHT-TO-LEFT MARK |
147 | | * 202A..202E # Cf [5] LEFT-TO-RIGHT EMBEDDING..RIGHT-TO-LEFT OVERRIDE |
148 | | * 2060..2064 # Cf [5] WORD JOINER..INVISIBLE PLUS |
149 | | * 2065 # Cn <reserved-2065> |
150 | | * 2066..206F # Cf [10] LEFT-TO-RIGHT ISOLATE..NOMINAL DIGIT SHAPES |
151 | | * 3164 # Lo HANGUL FILLER |
152 | | * FE00..FE0F # Mn [16] VARIATION SELECTOR-1..VARIATION SELECTOR-16 |
153 | | * FEFF # Cf ZERO WIDTH NO-BREAK SPACE |
154 | | * FFA0 # Lo HALFWIDTH HANGUL FILLER |
155 | | * FFF0..FFF8 # Cn [9] <reserved-FFF0>..<reserved-FFF8> |
156 | | * 1BCA0..1BCA3 # Cf [4] SHORTHAND FORMAT LETTER OVERLAP..SHORTHAND FORMAT UP STEP |
157 | | * 1D173..1D17A # Cf [8] MUSICAL SYMBOL BEGIN BEAM..MUSICAL SYMBOL END PHRASE |
158 | | * E0000 # Cn <reserved-E0000> |
159 | | * E0001 # Cf LANGUAGE TAG |
160 | | * E0002..E001F # Cn [30] <reserved-E0002>..<reserved-E001F> |
161 | | * E0020..E007F # Cf [96] TAG SPACE..CANCEL TAG |
162 | | * E0080..E00FF # Cn [128] <reserved-E0080>..<reserved-E00FF> |
163 | | * E0100..E01EF # Mn [240] VARIATION SELECTOR-17..VARIATION SELECTOR-256 |
164 | | * E01F0..E0FFF # Cn [3600] <reserved-E01F0>..<reserved-E0FFF> |
165 | | */ |
166 | | static hb_bool_t |
167 | | is_default_ignorable (hb_codepoint_t ch) |
168 | 125k | { |
169 | 125k | hb_codepoint_t plane = ch >> 16; |
170 | 125k | if (likely (plane == 0)) |
171 | 122k | { |
172 | | /* BMP */ |
173 | 122k | hb_codepoint_t page = ch >> 8; |
174 | 122k | switch (page) { |
175 | 122k | case 0x00: return unlikely (ch == 0x00ADu); |
176 | 36 | case 0x03: return unlikely (ch == 0x034Fu); |
177 | 0 | case 0x06: return unlikely (ch == 0x061Cu); |
178 | 0 | case 0x17: return hb_in_range<hb_codepoint_t> (ch, 0x17B4u, 0x17B5u); |
179 | 0 | case 0x18: return hb_in_range<hb_codepoint_t> (ch, 0x180Bu, 0x180Eu); |
180 | 70 | case 0x20: return hb_in_ranges<hb_codepoint_t> (ch, 0x200Bu, 0x200Fu, |
181 | 70 | 0x202Au, 0x202Eu, |
182 | 70 | 0x2060u, 0x206Fu); |
183 | 3 | case 0xFE: return hb_in_range<hb_codepoint_t> (ch, 0xFE00u, 0xFE0Fu) || ch == 0xFEFFu; |
184 | 41 | case 0xFF: return hb_in_range<hb_codepoint_t> (ch, 0xFFF0u, 0xFFF8u); |
185 | 595 | default: return false; |
186 | 122k | } |
187 | 122k | } |
188 | 2.39k | else |
189 | 2.39k | { |
190 | | /* Other planes */ |
191 | 2.39k | switch (plane) { |
192 | 0 | case 0x01: return hb_in_range<hb_codepoint_t> (ch, 0x1D173u, 0x1D17Au); |
193 | 2.30k | case 0x0E: return hb_in_range<hb_codepoint_t> (ch, 0xE0000u, 0xE0FFFu); |
194 | 95 | default: return false; |
195 | 2.39k | } |
196 | 2.39k | } |
197 | 125k | } |
198 | | |
199 | | /* Space estimates based on: |
200 | | * https://unicode.org/charts/PDF/U2000.pdf |
201 | | * https://docs.microsoft.com/en-us/typography/develop/character-design-standards/whitespace |
202 | | */ |
203 | | enum space_t { |
204 | | NOT_SPACE = 0, |
205 | | SPACE_EM = 1, |
206 | | SPACE_EM_2 = 2, |
207 | | SPACE_EM_3 = 3, |
208 | | SPACE_EM_4 = 4, |
209 | | SPACE_EM_5 = 5, |
210 | | SPACE_EM_6 = 6, |
211 | | SPACE_EM_16 = 16, |
212 | | SPACE_4_EM_18, /* 4/18th of an EM! */ |
213 | | SPACE, |
214 | | SPACE_FIGURE, |
215 | | SPACE_PUNCTUATION, |
216 | | SPACE_NARROW, |
217 | | }; |
218 | | static space_t |
219 | | space_fallback_type (hb_codepoint_t u) |
220 | 0 | { |
221 | 0 | switch (u) |
222 | 0 | { |
223 | | /* All GC=Zs chars that can use a fallback. */ |
224 | 0 | default: return NOT_SPACE; /* U+1680 OGHAM SPACE MARK */ |
225 | 0 | case 0x0020u: return SPACE; /* U+0020 SPACE */ |
226 | 0 | case 0x00A0u: return SPACE; /* U+00A0 NO-BREAK SPACE */ |
227 | 0 | case 0x2000u: return SPACE_EM_2; /* U+2000 EN QUAD */ |
228 | 0 | case 0x2001u: return SPACE_EM; /* U+2001 EM QUAD */ |
229 | 0 | case 0x2002u: return SPACE_EM_2; /* U+2002 EN SPACE */ |
230 | 0 | case 0x2003u: return SPACE_EM; /* U+2003 EM SPACE */ |
231 | 0 | case 0x2004u: return SPACE_EM_3; /* U+2004 THREE-PER-EM SPACE */ |
232 | 0 | case 0x2005u: return SPACE_EM_4; /* U+2005 FOUR-PER-EM SPACE */ |
233 | 0 | case 0x2006u: return SPACE_EM_6; /* U+2006 SIX-PER-EM SPACE */ |
234 | 0 | case 0x2007u: return SPACE_FIGURE; /* U+2007 FIGURE SPACE */ |
235 | 0 | case 0x2008u: return SPACE_PUNCTUATION; /* U+2008 PUNCTUATION SPACE */ |
236 | 0 | case 0x2009u: return SPACE_EM_5; /* U+2009 THIN SPACE */ |
237 | 0 | case 0x200Au: return SPACE_EM_16; /* U+200A HAIR SPACE */ |
238 | 0 | case 0x202Fu: return SPACE_NARROW; /* U+202F NARROW NO-BREAK SPACE */ |
239 | 0 | case 0x205Fu: return SPACE_4_EM_18; /* U+205F MEDIUM MATHEMATICAL SPACE */ |
240 | 0 | case 0x3000u: return SPACE_EM; /* U+3000 IDEOGRAPHIC SPACE */ |
241 | 0 | } |
242 | 0 | } |
243 | | |
244 | | static hb_codepoint_t |
245 | | vertical_char_for (hb_codepoint_t u) |
246 | 0 | { |
247 | 0 | switch (u >> 8) |
248 | 0 | { |
249 | 0 | case 0x20: switch (u) { |
250 | 0 | case 0x2013u: return 0xfe32u; // EN DASH |
251 | 0 | case 0x2014u: return 0xfe31u; // EM DASH |
252 | 0 | case 0x2025u: return 0xfe30u; // TWO DOT LEADER |
253 | 0 | case 0x2026u: return 0xfe19u; // HORIZONTAL ELLIPSIS |
254 | 0 | } break; |
255 | 0 | case 0x30: switch (u) { |
256 | 0 | case 0x3001u: return 0xfe11u; // IDEOGRAPHIC COMMA |
257 | 0 | case 0x3002u: return 0xfe12u; // IDEOGRAPHIC FULL STOP |
258 | 0 | case 0x3008u: return 0xfe3fu; // LEFT ANGLE BRACKET |
259 | 0 | case 0x3009u: return 0xfe40u; // RIGHT ANGLE BRACKET |
260 | 0 | case 0x300au: return 0xfe3du; // LEFT DOUBLE ANGLE BRACKET |
261 | 0 | case 0x300bu: return 0xfe3eu; // RIGHT DOUBLE ANGLE BRACKET |
262 | 0 | case 0x300cu: return 0xfe41u; // LEFT CORNER BRACKET |
263 | 0 | case 0x300du: return 0xfe42u; // RIGHT CORNER BRACKET |
264 | 0 | case 0x300eu: return 0xfe43u; // LEFT WHITE CORNER BRACKET |
265 | 0 | case 0x300fu: return 0xfe44u; // RIGHT WHITE CORNER BRACKET |
266 | 0 | case 0x3010u: return 0xfe3bu; // LEFT BLACK LENTICULAR BRACKET |
267 | 0 | case 0x3011u: return 0xfe3cu; // RIGHT BLACK LENTICULAR BRACKET |
268 | 0 | case 0x3014u: return 0xfe39u; // LEFT TORTOISE SHELL BRACKET |
269 | 0 | case 0x3015u: return 0xfe3au; // RIGHT TORTOISE SHELL BRACKET |
270 | 0 | case 0x3016u: return 0xfe17u; // LEFT WHITE LENTICULAR BRACKET |
271 | 0 | case 0x3017u: return 0xfe18u; // RIGHT WHITE LENTICULAR BRACKET |
272 | 0 | } break; |
273 | 0 | case 0xfe: switch (u) { |
274 | 0 | case 0xfe4fu: return 0xfe34u; // WAVY LOW LINE |
275 | 0 | } break; |
276 | 0 | case 0xff: switch (u) { |
277 | 0 | case 0xff01u: return 0xfe15u; // FULLWIDTH EXCLAMATION MARK |
278 | 0 | case 0xff08u: return 0xfe35u; // FULLWIDTH LEFT PARENTHESIS |
279 | 0 | case 0xff09u: return 0xfe36u; // FULLWIDTH RIGHT PARENTHESIS |
280 | 0 | case 0xff0cu: return 0xfe10u; // FULLWIDTH COMMA |
281 | 0 | case 0xff1au: return 0xfe13u; // FULLWIDTH COLON |
282 | 0 | case 0xff1bu: return 0xfe14u; // FULLWIDTH SEMICOLON |
283 | 0 | case 0xff1fu: return 0xfe16u; // FULLWIDTH QUESTION MARK |
284 | 0 | case 0xff3bu: return 0xfe47u; // FULLWIDTH LEFT SQUARE BRACKET |
285 | 0 | case 0xff3du: return 0xfe48u; // FULLWIDTH RIGHT SQUARE BRACKET |
286 | 0 | case 0xff3fu: return 0xfe33u; // FULLWIDTH LOW LINE |
287 | 0 | case 0xff5bu: return 0xfe37u; // FULLWIDTH LEFT CURLY BRACKET |
288 | 0 | case 0xff5du: return 0xfe38u; // FULLWIDTH RIGHT CURLY BRACKET |
289 | 0 | } break; |
290 | 0 | } |
291 | | |
292 | 0 | return u; |
293 | 0 | } |
294 | | |
295 | | struct { |
296 | | #define HB_UNICODE_FUNC_IMPLEMENT(name) hb_unicode_##name##_func_t name; |
297 | | HB_UNICODE_FUNCS_IMPLEMENT_CALLBACKS |
298 | | #undef HB_UNICODE_FUNC_IMPLEMENT |
299 | | } func; |
300 | | |
301 | | struct { |
302 | | #define HB_UNICODE_FUNC_IMPLEMENT(name) void *name; |
303 | | HB_UNICODE_FUNCS_IMPLEMENT_CALLBACKS |
304 | | #undef HB_UNICODE_FUNC_IMPLEMENT |
305 | | } user_data; |
306 | | |
307 | | struct { |
308 | | #define HB_UNICODE_FUNC_IMPLEMENT(name) hb_destroy_func_t name; |
309 | | HB_UNICODE_FUNCS_IMPLEMENT_CALLBACKS |
310 | | #undef HB_UNICODE_FUNC_IMPLEMENT |
311 | | } destroy; |
312 | | }; |
313 | | DECLARE_NULL_INSTANCE (hb_unicode_funcs_t); |
314 | | |
315 | | |
316 | | /* |
317 | | * Modified combining marks |
318 | | */ |
319 | | |
320 | | /* Hebrew |
321 | | * |
322 | | * We permute the "fixed-position" classes 10-26 into the order |
323 | | * described in the SBL Hebrew manual: |
324 | | * |
325 | | * https://www.sbl-site.org/Fonts/SBLHebrewUserManual1.5x.pdf |
326 | | * |
327 | | * (as recommended by: |
328 | | * https://forum.fontlab.com/archive-old-microsoft-volt-group/vista-and-diacritic-ordering/msg22823/) |
329 | | * |
330 | | * More details here: |
331 | | * https://bugzilla.mozilla.org/show_bug.cgi?id=662055 |
332 | | */ |
333 | 0 | #define HB_MODIFIED_COMBINING_CLASS_CCC10 22 /* sheva */ |
334 | 0 | #define HB_MODIFIED_COMBINING_CLASS_CCC11 15 /* hataf segol */ |
335 | 0 | #define HB_MODIFIED_COMBINING_CLASS_CCC12 16 /* hataf patah */ |
336 | 0 | #define HB_MODIFIED_COMBINING_CLASS_CCC13 17 /* hataf qamats */ |
337 | 0 | #define HB_MODIFIED_COMBINING_CLASS_CCC14 23 /* hiriq */ |
338 | 0 | #define HB_MODIFIED_COMBINING_CLASS_CCC15 18 /* tsere */ |
339 | 0 | #define HB_MODIFIED_COMBINING_CLASS_CCC16 19 /* segol */ |
340 | 0 | #define HB_MODIFIED_COMBINING_CLASS_CCC17 20 /* patah */ |
341 | 0 | #define HB_MODIFIED_COMBINING_CLASS_CCC18 21 /* qamats & qamats qatan */ |
342 | 0 | #define HB_MODIFIED_COMBINING_CLASS_CCC19 14 /* holam & holam haser for vav*/ |
343 | 0 | #define HB_MODIFIED_COMBINING_CLASS_CCC20 24 /* qubuts */ |
344 | 0 | #define HB_MODIFIED_COMBINING_CLASS_CCC21 12 /* dagesh */ |
345 | 0 | #define HB_MODIFIED_COMBINING_CLASS_CCC22 25 /* meteg */ |
346 | 0 | #define HB_MODIFIED_COMBINING_CLASS_CCC23 13 /* rafe */ |
347 | 0 | #define HB_MODIFIED_COMBINING_CLASS_CCC24 10 /* shin dot */ |
348 | 0 | #define HB_MODIFIED_COMBINING_CLASS_CCC25 11 /* sin dot */ |
349 | 0 | #define HB_MODIFIED_COMBINING_CLASS_CCC26 26 /* point varika */ |
350 | | |
351 | | /* |
352 | | * Arabic |
353 | | * |
354 | | * Modify to move Shadda (ccc=33) before other marks. See: |
355 | | * https://unicode.org/faq/normalization.html#8 |
356 | | * https://unicode.org/faq/normalization.html#9 |
357 | | */ |
358 | 0 | #define HB_MODIFIED_COMBINING_CLASS_CCC27 28 /* fathatan */ |
359 | 0 | #define HB_MODIFIED_COMBINING_CLASS_CCC28 29 /* dammatan */ |
360 | 0 | #define HB_MODIFIED_COMBINING_CLASS_CCC29 30 /* kasratan */ |
361 | 0 | #define HB_MODIFIED_COMBINING_CLASS_CCC30 31 /* fatha */ |
362 | 0 | #define HB_MODIFIED_COMBINING_CLASS_CCC31 32 /* damma */ |
363 | 0 | #define HB_MODIFIED_COMBINING_CLASS_CCC32 33 /* kasra */ |
364 | 0 | #define HB_MODIFIED_COMBINING_CLASS_CCC33 27 /* shadda */ |
365 | 0 | #define HB_MODIFIED_COMBINING_CLASS_CCC34 34 /* sukun */ |
366 | 0 | #define HB_MODIFIED_COMBINING_CLASS_CCC35 35 /* superscript alef */ |
367 | | |
368 | | /* Syriac */ |
369 | 0 | #define HB_MODIFIED_COMBINING_CLASS_CCC36 36 /* superscript alaph */ |
370 | | |
371 | | /* Telugu |
372 | | * |
373 | | * Modify Telugu length marks (ccc=84, ccc=91). |
374 | | * These are the only matras in the main Indic scripts range that have |
375 | | * a non-zero ccc. That makes them reorder with the Halant (ccc=9). |
376 | | * Assign 4 and 5, which are otherwise unassigned. |
377 | | */ |
378 | | #define HB_MODIFIED_COMBINING_CLASS_CCC84 4 /* length mark */ |
379 | | #define HB_MODIFIED_COMBINING_CLASS_CCC91 5 /* ai length mark */ |
380 | | |
381 | | /* Thai |
382 | | * |
383 | | * Modify U+0E38 and U+0E39 (ccc=103) to be reordered before U+0E3A (ccc=9). |
384 | | * Assign 3, which is unassigned otherwise. |
385 | | * Uniscribe does this reordering too. |
386 | | */ |
387 | 0 | #define HB_MODIFIED_COMBINING_CLASS_CCC103 3 /* sara u / sara uu */ |
388 | 0 | #define HB_MODIFIED_COMBINING_CLASS_CCC107 107 /* mai * */ |
389 | | |
390 | | /* Lao */ |
391 | 0 | #define HB_MODIFIED_COMBINING_CLASS_CCC118 118 /* sign u / sign uu */ |
392 | 0 | #define HB_MODIFIED_COMBINING_CLASS_CCC122 122 /* mai * */ |
393 | | |
394 | | /* Tibetan |
395 | | * |
396 | | * In case of multiple vowel-signs, use u first (but after achung) |
397 | | * this allows Dzongkha multi-vowel shortcuts to render correctly |
398 | | */ |
399 | 0 | #define HB_MODIFIED_COMBINING_CLASS_CCC129 129 /* sign aa */ |
400 | 0 | #define HB_MODIFIED_COMBINING_CLASS_CCC130 132 /* sign i */ |
401 | 0 | #define HB_MODIFIED_COMBINING_CLASS_CCC132 131 /* sign u */ |
402 | | |
403 | | /* Misc */ |
404 | | |
405 | | #define HB_UNICODE_GENERAL_CATEGORY_IS_MARK(gen_cat) \ |
406 | 857k | (FLAG_UNSAFE (gen_cat) & \ |
407 | 857k | (FLAG (HB_UNICODE_GENERAL_CATEGORY_SPACING_MARK) | \ |
408 | 857k | FLAG (HB_UNICODE_GENERAL_CATEGORY_ENCLOSING_MARK) | \ |
409 | 857k | FLAG (HB_UNICODE_GENERAL_CATEGORY_NON_SPACING_MARK))) |
410 | | |
411 | | #define HB_UNICODE_GENERAL_CATEGORY_IS_LETTER(gen_cat) \ |
412 | 99 | (FLAG_UNSAFE (gen_cat) & \ |
413 | 99 | (FLAG (HB_UNICODE_GENERAL_CATEGORY_LOWERCASE_LETTER) | \ |
414 | 99 | FLAG (HB_UNICODE_GENERAL_CATEGORY_MODIFIER_LETTER) | \ |
415 | 99 | FLAG (HB_UNICODE_GENERAL_CATEGORY_OTHER_LETTER) | \ |
416 | 99 | FLAG (HB_UNICODE_GENERAL_CATEGORY_TITLECASE_LETTER) | \ |
417 | 99 | FLAG (HB_UNICODE_GENERAL_CATEGORY_UPPERCASE_LETTER))) |
418 | | |
419 | | /* |
420 | | * Ranges, used for bsearch tables. |
421 | | */ |
422 | | |
423 | | struct hb_unicode_range_t |
424 | | { |
425 | | static int |
426 | | cmp (const void *_key, const void *_item) |
427 | 0 | { |
428 | 0 | hb_codepoint_t cp = *((hb_codepoint_t *) _key); |
429 | 0 | const hb_unicode_range_t *range = (hb_unicode_range_t *) _item; |
430 | 0 |
|
431 | 0 | if (cp < range->start) |
432 | 0 | return -1; |
433 | 0 | else if (cp <= range->end) |
434 | 0 | return 0; |
435 | 0 | else |
436 | 0 | return +1; |
437 | 0 | } |
438 | | |
439 | | hb_codepoint_t start; |
440 | | hb_codepoint_t end; |
441 | | }; |
442 | | |
443 | | /* |
444 | | * Emoji. |
445 | | */ |
446 | | |
447 | | HB_INTERNAL bool |
448 | | _hb_unicode_is_emoji_Extended_Pictographic (hb_codepoint_t cp); |
449 | | |
450 | | |
451 | | extern "C" HB_INTERNAL hb_unicode_funcs_t *hb_ucd_get_unicode_funcs (); |
452 | | |
453 | | |
454 | | #endif /* HB_UNICODE_HH */ |