1 | use core::convert::TryFrom; |
2 | |
3 | pub use unicode_ccc::CanonicalCombiningClass; |
4 | pub use unicode_properties::GeneralCategory; // TODO: prefer unic-ucd-normal::CanonicalCombiningClass |
5 | |
6 | use crate::Script; |
7 | |
8 | // Space estimates based on: |
9 | // https://unicode.org/charts/PDF/U2000.pdf |
10 | // https://docs.microsoft.com/en-us/typography/develop/character-design-standards/whitespace |
11 | pub type Space = u8; |
12 | pub mod space { |
13 | pub const SPACE_EM: u8 = 1; |
14 | pub const SPACE_EM_2: u8 = 2; |
15 | pub const SPACE_EM_3: u8 = 3; |
16 | pub const SPACE_EM_4: u8 = 4; |
17 | pub const SPACE_EM_5: u8 = 5; |
18 | pub const SPACE_EM_6: u8 = 6; |
19 | pub const SPACE_EM_16: u8 = 16; |
20 | pub const SPACE_4_EM_18: u8 = 17; // 4/18th of an EM! |
21 | pub const SPACE: u8 = 18; |
22 | pub const SPACE_FIGURE: u8 = 19; |
23 | pub const SPACE_PUNCTUATION: u8 = 20; |
24 | pub const SPACE_NARROW: u8 = 21; |
25 | } |
26 | |
27 | #[allow (dead_code)] |
28 | pub mod modified_combining_class { |
29 | // Hebrew |
30 | // |
31 | // We permute the "fixed-position" classes 10-26 into the order |
32 | // described in the SBL Hebrew manual: |
33 | // |
34 | // https://www.sbl-site.org/Fonts/SBLHebrewUserManual1.5x.pdf |
35 | // |
36 | // (as recommended by: |
37 | // https://forum.fontlab.com/archive-old-microsoft-volt-group/vista-and-diacritic-ordering/msg22823/) |
38 | // |
39 | // More details here: |
40 | // https://bugzilla.mozilla.org/show_bug.cgi?id=662055 |
41 | pub const CCC10: u8 = 22; // sheva |
42 | pub const CCC11: u8 = 15; // hataf segol |
43 | pub const CCC12: u8 = 16; // hataf patah |
44 | pub const CCC13: u8 = 17; // hataf qamats |
45 | pub const CCC14: u8 = 23; // hiriq |
46 | pub const CCC15: u8 = 18; // tsere |
47 | pub const CCC16: u8 = 19; // segol |
48 | pub const CCC17: u8 = 20; // patah |
49 | pub const CCC18: u8 = 21; // qamats & qamats qatan |
50 | pub const CCC19: u8 = 14; // holam & holam haser for vav |
51 | pub const CCC20: u8 = 24; // qubuts |
52 | pub const CCC21: u8 = 12; // dagesh |
53 | pub const CCC22: u8 = 25; // meteg |
54 | pub const CCC23: u8 = 13; // rafe |
55 | pub const CCC24: u8 = 10; // shin dot |
56 | pub const CCC25: u8 = 11; // sin dot |
57 | pub const CCC26: u8 = 26; // point varika |
58 | |
59 | // Arabic |
60 | // |
61 | // Modify to move Shadda (ccc=33) before other marks. See: |
62 | // https://unicode.org/faq/normalization.html#8 |
63 | // https://unicode.org/faq/normalization.html#9 |
64 | pub const CCC27: u8 = 28; // fathatan |
65 | pub const CCC28: u8 = 29; // dammatan |
66 | pub const CCC29: u8 = 30; // kasratan |
67 | pub const CCC30: u8 = 31; // fatha |
68 | pub const CCC31: u8 = 32; // damma |
69 | pub const CCC32: u8 = 33; // kasra |
70 | pub const CCC33: u8 = 27; // shadda |
71 | pub const CCC34: u8 = 34; // sukun |
72 | pub const CCC35: u8 = 35; // superscript alef |
73 | |
74 | // Syriac |
75 | pub const CCC36: u8 = 36; // superscript alaph |
76 | |
77 | // Telugu |
78 | // |
79 | // Modify Telugu length marks (ccc=84, ccc=91). |
80 | // These are the only matras in the main Indic scripts range that have |
81 | // a non-zero ccc. That makes them reorder with the Halant that is |
82 | // ccc=9. Just zero them, we don't need them in our Indic shaper. |
83 | pub const CCC84: u8 = 0; // length mark |
84 | pub const CCC91: u8 = 0; // ai length mark |
85 | |
86 | // Thai |
87 | // |
88 | // Modify U+0E38 and U+0E39 (ccc=103) to be reordered before U+0E3A (ccc=9). |
89 | // Assign 3, which is unassigned otherwise. |
90 | // Uniscribe does this reordering too. |
91 | pub const CCC103: u8 = 3; // sara u / sara uu |
92 | pub const CCC107: u8 = 107; // mai * |
93 | |
94 | // Lao |
95 | pub const CCC118: u8 = 118; // sign u / sign uu |
96 | pub const CCC122: u8 = 122; // mai * |
97 | |
98 | // Tibetan |
99 | // |
100 | // In case of multiple vowel-signs, use u first (but after achung) |
101 | // this allows Dzongkha multi-vowel shortcuts to render correctly |
102 | pub const CCC129: u8 = 129; // sign aa |
103 | pub const CCC130: u8 = 132; // sign i |
104 | pub const CCC132: u8 = 131; // sign u |
105 | } |
106 | |
107 | #[rustfmt::skip] |
108 | const MODIFIED_COMBINING_CLASS: &[u8; 256] = &[ |
109 | CanonicalCombiningClass::NotReordered as u8, |
110 | CanonicalCombiningClass::Overlay as u8, |
111 | 2, 3, 4, 5, 6, |
112 | CanonicalCombiningClass::Nukta as u8, |
113 | CanonicalCombiningClass::KanaVoicing as u8, |
114 | CanonicalCombiningClass::Virama as u8, |
115 | |
116 | // Hebrew |
117 | modified_combining_class::CCC10, |
118 | modified_combining_class::CCC11, |
119 | modified_combining_class::CCC12, |
120 | modified_combining_class::CCC13, |
121 | modified_combining_class::CCC14, |
122 | modified_combining_class::CCC15, |
123 | modified_combining_class::CCC16, |
124 | modified_combining_class::CCC17, |
125 | modified_combining_class::CCC18, |
126 | modified_combining_class::CCC19, |
127 | modified_combining_class::CCC20, |
128 | modified_combining_class::CCC21, |
129 | modified_combining_class::CCC22, |
130 | modified_combining_class::CCC23, |
131 | modified_combining_class::CCC24, |
132 | modified_combining_class::CCC25, |
133 | modified_combining_class::CCC26, |
134 | |
135 | // Arabic |
136 | modified_combining_class::CCC27, |
137 | modified_combining_class::CCC28, |
138 | modified_combining_class::CCC29, |
139 | modified_combining_class::CCC30, |
140 | modified_combining_class::CCC31, |
141 | modified_combining_class::CCC32, |
142 | modified_combining_class::CCC33, |
143 | modified_combining_class::CCC34, |
144 | modified_combining_class::CCC35, |
145 | |
146 | // Syriac |
147 | modified_combining_class::CCC36, |
148 | |
149 | 37, 38, 39, |
150 | 40, 41, 42, 43, 44, 45, 46, 47, 48, 49, 50, 51, 52, 53, 54, 55, 56, 57, 58, 59, |
151 | 60, 61, 62, 63, 64, 65, 66, 67, 68, 69, 70, 71, 72, 73, 74, 75, 76, 77, 78, 79, |
152 | 80, 81, 82, 83, |
153 | |
154 | // Telugu |
155 | modified_combining_class::CCC84, |
156 | 85, 86, 87, 88, 89, 90, |
157 | modified_combining_class::CCC91, |
158 | 92, 93, 94, 95, 96, 97, 98, 99, 100, 101, 102, |
159 | |
160 | // Thai |
161 | modified_combining_class::CCC103, |
162 | 104, 105, 106, |
163 | modified_combining_class::CCC107, |
164 | 108, 109, 110, 111, 112, 113, 114, 115, 116, 117, |
165 | |
166 | // Lao |
167 | modified_combining_class::CCC118, |
168 | 119, 120, 121, |
169 | modified_combining_class::CCC122, |
170 | 123, 124, 125, 126, 127, 128, |
171 | |
172 | // Tibetan |
173 | modified_combining_class::CCC129, |
174 | modified_combining_class::CCC130, |
175 | 131, |
176 | modified_combining_class::CCC132, |
177 | 133, 134, 135, 136, 137, 138, 139, |
178 | |
179 | |
180 | 140, 141, 142, 143, 144, 145, 146, 147, 148, 149, |
181 | 150, 151, 152, 153, 154, 155, 156, 157, 158, 159, |
182 | 160, 161, 162, 163, 164, 165, 166, 167, 168, 169, |
183 | 170, 171, 172, 173, 174, 175, 176, 177, 178, 179, |
184 | 180, 181, 182, 183, 184, 185, 186, 187, 188, 189, |
185 | 190, 191, 192, 193, 194, 195, 196, 197, 198, 199, |
186 | |
187 | CanonicalCombiningClass::AttachedBelowLeft as u8, |
188 | 201, |
189 | CanonicalCombiningClass::AttachedBelow as u8, |
190 | 203, 204, 205, 206, 207, 208, 209, 210, 211, 212, 213, |
191 | CanonicalCombiningClass::AttachedAbove as u8, |
192 | 215, |
193 | CanonicalCombiningClass::AttachedAboveRight as u8, |
194 | 217, |
195 | CanonicalCombiningClass::BelowLeft as u8, |
196 | 219, |
197 | CanonicalCombiningClass::Below as u8, |
198 | 221, |
199 | CanonicalCombiningClass::BelowRight as u8, |
200 | 223, |
201 | CanonicalCombiningClass::Left as u8, |
202 | 225, |
203 | CanonicalCombiningClass::Right as u8, |
204 | 227, |
205 | CanonicalCombiningClass::AboveLeft as u8, |
206 | 229, |
207 | CanonicalCombiningClass::Above as u8, |
208 | 231, |
209 | CanonicalCombiningClass::AboveRight as u8, |
210 | CanonicalCombiningClass::DoubleBelow as u8, |
211 | CanonicalCombiningClass::DoubleAbove as u8, |
212 | 235, 236, 237, 238, 239, |
213 | CanonicalCombiningClass::IotaSubscript as u8, |
214 | 241, 242, 243, 244, 245, 246, 247, 248, 249, 250, 251, 252, 253, 254, |
215 | 255, // RB_UNICODE_COMBINING_CLASS_INVALID |
216 | ]; |
217 | |
218 | pub trait GeneralCategoryExt { |
219 | fn to_rb(&self) -> u32; |
220 | fn from_rb(gc: u32) -> Self; |
221 | fn is_mark(&self) -> bool; |
222 | fn is_letter(&self) -> bool; |
223 | } |
224 | |
225 | #[rustfmt::skip] |
226 | impl GeneralCategoryExt for GeneralCategory { |
227 | fn to_rb(&self) -> u32 { |
228 | match *self { |
229 | GeneralCategory::ClosePunctuation => hb_gc::RB_UNICODE_GENERAL_CATEGORY_CLOSE_PUNCTUATION, |
230 | GeneralCategory::ConnectorPunctuation => hb_gc::RB_UNICODE_GENERAL_CATEGORY_CONNECT_PUNCTUATION, |
231 | GeneralCategory::Control => hb_gc::RB_UNICODE_GENERAL_CATEGORY_CONTROL, |
232 | GeneralCategory::CurrencySymbol => hb_gc::RB_UNICODE_GENERAL_CATEGORY_CURRENCY_SYMBOL, |
233 | GeneralCategory::DashPunctuation => hb_gc::RB_UNICODE_GENERAL_CATEGORY_DASH_PUNCTUATION, |
234 | GeneralCategory::DecimalNumber => hb_gc::RB_UNICODE_GENERAL_CATEGORY_DECIMAL_NUMBER, |
235 | GeneralCategory::EnclosingMark => hb_gc::RB_UNICODE_GENERAL_CATEGORY_ENCLOSING_MARK, |
236 | GeneralCategory::FinalPunctuation => hb_gc::RB_UNICODE_GENERAL_CATEGORY_FINAL_PUNCTUATION, |
237 | GeneralCategory::Format => hb_gc::RB_UNICODE_GENERAL_CATEGORY_FORMAT, |
238 | GeneralCategory::InitialPunctuation => hb_gc::RB_UNICODE_GENERAL_CATEGORY_INITIAL_PUNCTUATION, |
239 | GeneralCategory::LetterNumber => hb_gc::RB_UNICODE_GENERAL_CATEGORY_LETTER_NUMBER, |
240 | GeneralCategory::LineSeparator => hb_gc::RB_UNICODE_GENERAL_CATEGORY_LINE_SEPARATOR, |
241 | GeneralCategory::LowercaseLetter => hb_gc::RB_UNICODE_GENERAL_CATEGORY_LOWERCASE_LETTER, |
242 | GeneralCategory::MathSymbol => hb_gc::RB_UNICODE_GENERAL_CATEGORY_MATH_SYMBOL, |
243 | GeneralCategory::ModifierLetter => hb_gc::RB_UNICODE_GENERAL_CATEGORY_MODIFIER_LETTER, |
244 | GeneralCategory::ModifierSymbol => hb_gc::RB_UNICODE_GENERAL_CATEGORY_MODIFIER_SYMBOL, |
245 | GeneralCategory::NonspacingMark => hb_gc::RB_UNICODE_GENERAL_CATEGORY_NON_SPACING_MARK, |
246 | GeneralCategory::OpenPunctuation => hb_gc::RB_UNICODE_GENERAL_CATEGORY_OPEN_PUNCTUATION, |
247 | GeneralCategory::OtherLetter => hb_gc::RB_UNICODE_GENERAL_CATEGORY_OTHER_LETTER, |
248 | GeneralCategory::OtherNumber => hb_gc::RB_UNICODE_GENERAL_CATEGORY_OTHER_NUMBER, |
249 | GeneralCategory::OtherPunctuation => hb_gc::RB_UNICODE_GENERAL_CATEGORY_OTHER_PUNCTUATION, |
250 | GeneralCategory::OtherSymbol => hb_gc::RB_UNICODE_GENERAL_CATEGORY_OTHER_SYMBOL, |
251 | GeneralCategory::ParagraphSeparator => hb_gc::RB_UNICODE_GENERAL_CATEGORY_PARAGRAPH_SEPARATOR, |
252 | GeneralCategory::PrivateUse => hb_gc::RB_UNICODE_GENERAL_CATEGORY_PRIVATE_USE, |
253 | GeneralCategory::SpaceSeparator => hb_gc::RB_UNICODE_GENERAL_CATEGORY_SPACE_SEPARATOR, |
254 | GeneralCategory::SpacingMark => hb_gc::RB_UNICODE_GENERAL_CATEGORY_SPACING_MARK, |
255 | GeneralCategory::Surrogate => hb_gc::RB_UNICODE_GENERAL_CATEGORY_SURROGATE, |
256 | GeneralCategory::TitlecaseLetter => hb_gc::RB_UNICODE_GENERAL_CATEGORY_TITLECASE_LETTER, |
257 | GeneralCategory::Unassigned => hb_gc::RB_UNICODE_GENERAL_CATEGORY_UNASSIGNED, |
258 | GeneralCategory::UppercaseLetter => hb_gc::RB_UNICODE_GENERAL_CATEGORY_UPPERCASE_LETTER, |
259 | } |
260 | } |
261 | |
262 | fn from_rb(gc: u32) -> Self { |
263 | match gc { |
264 | hb_gc::RB_UNICODE_GENERAL_CATEGORY_CLOSE_PUNCTUATION => GeneralCategory::ClosePunctuation, |
265 | hb_gc::RB_UNICODE_GENERAL_CATEGORY_CONNECT_PUNCTUATION => GeneralCategory::ConnectorPunctuation, |
266 | hb_gc::RB_UNICODE_GENERAL_CATEGORY_CONTROL => GeneralCategory::Control, |
267 | hb_gc::RB_UNICODE_GENERAL_CATEGORY_CURRENCY_SYMBOL => GeneralCategory::CurrencySymbol, |
268 | hb_gc::RB_UNICODE_GENERAL_CATEGORY_DASH_PUNCTUATION => GeneralCategory::DashPunctuation, |
269 | hb_gc::RB_UNICODE_GENERAL_CATEGORY_DECIMAL_NUMBER => GeneralCategory::DecimalNumber, |
270 | hb_gc::RB_UNICODE_GENERAL_CATEGORY_ENCLOSING_MARK => GeneralCategory::EnclosingMark, |
271 | hb_gc::RB_UNICODE_GENERAL_CATEGORY_FINAL_PUNCTUATION => GeneralCategory::FinalPunctuation, |
272 | hb_gc::RB_UNICODE_GENERAL_CATEGORY_FORMAT => GeneralCategory::Format, |
273 | hb_gc::RB_UNICODE_GENERAL_CATEGORY_INITIAL_PUNCTUATION => GeneralCategory::InitialPunctuation, |
274 | hb_gc::RB_UNICODE_GENERAL_CATEGORY_LETTER_NUMBER => GeneralCategory::LetterNumber, |
275 | hb_gc::RB_UNICODE_GENERAL_CATEGORY_LINE_SEPARATOR => GeneralCategory::LineSeparator, |
276 | hb_gc::RB_UNICODE_GENERAL_CATEGORY_LOWERCASE_LETTER => GeneralCategory::LowercaseLetter, |
277 | hb_gc::RB_UNICODE_GENERAL_CATEGORY_MATH_SYMBOL => GeneralCategory::MathSymbol, |
278 | hb_gc::RB_UNICODE_GENERAL_CATEGORY_MODIFIER_LETTER => GeneralCategory::ModifierLetter, |
279 | hb_gc::RB_UNICODE_GENERAL_CATEGORY_MODIFIER_SYMBOL => GeneralCategory::ModifierSymbol, |
280 | hb_gc::RB_UNICODE_GENERAL_CATEGORY_NON_SPACING_MARK => GeneralCategory::NonspacingMark, |
281 | hb_gc::RB_UNICODE_GENERAL_CATEGORY_OPEN_PUNCTUATION => GeneralCategory::OpenPunctuation, |
282 | hb_gc::RB_UNICODE_GENERAL_CATEGORY_OTHER_LETTER => GeneralCategory::OtherLetter, |
283 | hb_gc::RB_UNICODE_GENERAL_CATEGORY_OTHER_NUMBER => GeneralCategory::OtherNumber, |
284 | hb_gc::RB_UNICODE_GENERAL_CATEGORY_OTHER_PUNCTUATION => GeneralCategory::OtherPunctuation, |
285 | hb_gc::RB_UNICODE_GENERAL_CATEGORY_OTHER_SYMBOL => GeneralCategory::OtherSymbol, |
286 | hb_gc::RB_UNICODE_GENERAL_CATEGORY_PARAGRAPH_SEPARATOR => GeneralCategory::ParagraphSeparator, |
287 | hb_gc::RB_UNICODE_GENERAL_CATEGORY_PRIVATE_USE => GeneralCategory::PrivateUse, |
288 | hb_gc::RB_UNICODE_GENERAL_CATEGORY_SPACE_SEPARATOR => GeneralCategory::SpaceSeparator, |
289 | hb_gc::RB_UNICODE_GENERAL_CATEGORY_SPACING_MARK => GeneralCategory::SpacingMark, |
290 | hb_gc::RB_UNICODE_GENERAL_CATEGORY_SURROGATE => GeneralCategory::Surrogate, |
291 | hb_gc::RB_UNICODE_GENERAL_CATEGORY_TITLECASE_LETTER => GeneralCategory::TitlecaseLetter, |
292 | hb_gc::RB_UNICODE_GENERAL_CATEGORY_UNASSIGNED => GeneralCategory::Unassigned, |
293 | hb_gc::RB_UNICODE_GENERAL_CATEGORY_UPPERCASE_LETTER => GeneralCategory::UppercaseLetter, |
294 | _ => unreachable!(), |
295 | } |
296 | } |
297 | |
298 | fn is_mark(&self) -> bool { |
299 | match *self { |
300 | GeneralCategory::SpacingMark | |
301 | GeneralCategory::EnclosingMark | |
302 | GeneralCategory::NonspacingMark => true, |
303 | _ => false, |
304 | } |
305 | } |
306 | |
307 | fn is_letter(&self) -> bool { |
308 | match *self { |
309 | GeneralCategory::LowercaseLetter | |
310 | GeneralCategory::ModifierLetter | |
311 | GeneralCategory::OtherLetter | |
312 | GeneralCategory::TitlecaseLetter | |
313 | GeneralCategory::UppercaseLetter => true, |
314 | _ => false, |
315 | } |
316 | } |
317 | } |
318 | |
319 | pub trait CharExt { |
320 | fn script(self) -> Script; |
321 | fn general_category(self) -> GeneralCategory; |
322 | fn combining_class(self) -> CanonicalCombiningClass; |
323 | fn space_fallback(self) -> Option<Space>; |
324 | fn modified_combining_class(self) -> u8; |
325 | fn mirrored(self) -> Option<char>; |
326 | fn is_emoji_extended_pictographic(self) -> bool; |
327 | fn is_default_ignorable(self) -> bool; |
328 | fn is_variation_selector(self) -> bool; |
329 | fn vertical(self) -> Option<char>; |
330 | } |
331 | |
332 | impl CharExt for char { |
333 | fn script(self) -> Script { |
334 | use crate::script; |
335 | use unicode_script as us; |
336 | |
337 | match unicode_script::UnicodeScript::script(&self) { |
338 | us::Script::Common => script::COMMON, |
339 | us::Script::Inherited => script::INHERITED, |
340 | us::Script::Adlam => script::ADLAM, |
341 | us::Script::Ahom => script::AHOM, |
342 | us::Script::Anatolian_Hieroglyphs => script::ANATOLIAN_HIEROGLYPHS, |
343 | us::Script::Arabic => script::ARABIC, |
344 | us::Script::Armenian => script::ARMENIAN, |
345 | us::Script::Avestan => script::AVESTAN, |
346 | us::Script::Balinese => script::BALINESE, |
347 | us::Script::Bamum => script::BAMUM, |
348 | us::Script::Bassa_Vah => script::BASSA_VAH, |
349 | us::Script::Batak => script::BATAK, |
350 | us::Script::Bengali => script::BENGALI, |
351 | us::Script::Bhaiksuki => script::BHAIKSUKI, |
352 | us::Script::Bopomofo => script::BOPOMOFO, |
353 | us::Script::Brahmi => script::BRAHMI, |
354 | us::Script::Braille => script::BRAILLE, |
355 | us::Script::Buginese => script::BUGINESE, |
356 | us::Script::Buhid => script::BUHID, |
357 | us::Script::Canadian_Aboriginal => script::CANADIAN_SYLLABICS, |
358 | us::Script::Carian => script::CARIAN, |
359 | us::Script::Caucasian_Albanian => script::CAUCASIAN_ALBANIAN, |
360 | us::Script::Chakma => script::CHAKMA, |
361 | us::Script::Cham => script::CHAM, |
362 | us::Script::Cherokee => script::CHEROKEE, |
363 | us::Script::Chorasmian => script::CHORASMIAN, |
364 | us::Script::Coptic => script::COPTIC, |
365 | us::Script::Cuneiform => script::CUNEIFORM, |
366 | us::Script::Cypriot => script::CYPRIOT, |
367 | us::Script::Cyrillic => script::CYRILLIC, |
368 | us::Script::Deseret => script::DESERET, |
369 | us::Script::Devanagari => script::DEVANAGARI, |
370 | us::Script::Dives_Akuru => script::DIVES_AKURU, |
371 | us::Script::Dogra => script::DOGRA, |
372 | us::Script::Duployan => script::DUPLOYAN, |
373 | us::Script::Egyptian_Hieroglyphs => script::EGYPTIAN_HIEROGLYPHS, |
374 | us::Script::Elbasan => script::ELBASAN, |
375 | us::Script::Elymaic => script::ELYMAIC, |
376 | us::Script::Ethiopic => script::ETHIOPIC, |
377 | us::Script::Georgian => script::GEORGIAN, |
378 | us::Script::Glagolitic => script::GLAGOLITIC, |
379 | us::Script::Gothic => script::GOTHIC, |
380 | us::Script::Grantha => script::GRANTHA, |
381 | us::Script::Greek => script::GREEK, |
382 | us::Script::Gujarati => script::GUJARATI, |
383 | us::Script::Gunjala_Gondi => script::GUNJALA_GONDI, |
384 | us::Script::Gurmukhi => script::GURMUKHI, |
385 | us::Script::Han => script::HAN, |
386 | us::Script::Hangul => script::HANGUL, |
387 | us::Script::Hanifi_Rohingya => script::HANIFI_ROHINGYA, |
388 | us::Script::Hanunoo => script::HANUNOO, |
389 | us::Script::Hatran => script::HATRAN, |
390 | us::Script::Hebrew => script::HEBREW, |
391 | us::Script::Hiragana => script::HIRAGANA, |
392 | us::Script::Imperial_Aramaic => script::IMPERIAL_ARAMAIC, |
393 | us::Script::Inscriptional_Pahlavi => script::INSCRIPTIONAL_PAHLAVI, |
394 | us::Script::Inscriptional_Parthian => script::INSCRIPTIONAL_PARTHIAN, |
395 | us::Script::Javanese => script::JAVANESE, |
396 | us::Script::Kaithi => script::KAITHI, |
397 | us::Script::Kannada => script::KANNADA, |
398 | us::Script::Katakana => script::KATAKANA, |
399 | us::Script::Kayah_Li => script::KAYAH_LI, |
400 | us::Script::Kharoshthi => script::KHAROSHTHI, |
401 | us::Script::Khitan_Small_Script => script::KHITAN_SMALL_SCRIPT, |
402 | us::Script::Khmer => script::KHMER, |
403 | us::Script::Khojki => script::KHOJKI, |
404 | us::Script::Khudawadi => script::KHUDAWADI, |
405 | us::Script::Lao => script::LAO, |
406 | us::Script::Latin => script::LATIN, |
407 | us::Script::Lepcha => script::LEPCHA, |
408 | us::Script::Limbu => script::LIMBU, |
409 | us::Script::Linear_A => script::LINEAR_A, |
410 | us::Script::Linear_B => script::LINEAR_B, |
411 | us::Script::Lisu => script::LISU, |
412 | us::Script::Lycian => script::LYCIAN, |
413 | us::Script::Lydian => script::LYDIAN, |
414 | us::Script::Mahajani => script::MAHAJANI, |
415 | us::Script::Makasar => script::MAKASAR, |
416 | us::Script::Malayalam => script::MALAYALAM, |
417 | us::Script::Mandaic => script::MANDAIC, |
418 | us::Script::Manichaean => script::MANICHAEAN, |
419 | us::Script::Marchen => script::MARCHEN, |
420 | us::Script::Masaram_Gondi => script::MASARAM_GONDI, |
421 | us::Script::Medefaidrin => script::MEDEFAIDRIN, |
422 | us::Script::Meetei_Mayek => script::MEETEI_MAYEK, |
423 | us::Script::Mende_Kikakui => script::MENDE_KIKAKUI, |
424 | us::Script::Meroitic_Cursive => script::MEROITIC_CURSIVE, |
425 | us::Script::Meroitic_Hieroglyphs => script::MEROITIC_HIEROGLYPHS, |
426 | us::Script::Miao => script::MIAO, |
427 | us::Script::Modi => script::MODI, |
428 | us::Script::Mongolian => script::MONGOLIAN, |
429 | us::Script::Mro => script::MRO, |
430 | us::Script::Multani => script::MULTANI, |
431 | us::Script::Myanmar => script::MYANMAR, |
432 | us::Script::Nabataean => script::NABATAEAN, |
433 | us::Script::Nandinagari => script::NANDINAGARI, |
434 | us::Script::New_Tai_Lue => script::NEW_TAI_LUE, |
435 | us::Script::Newa => script::NEWA, |
436 | us::Script::Nko => script::NKO, |
437 | us::Script::Nushu => script::NUSHU, |
438 | us::Script::Nyiakeng_Puachue_Hmong => script::NYIAKENG_PUACHUE_HMONG, |
439 | us::Script::Ogham => script::OGHAM, |
440 | us::Script::Ol_Chiki => script::OL_CHIKI, |
441 | us::Script::Old_Hungarian => script::OLD_HUNGARIAN, |
442 | us::Script::Old_Italic => script::OLD_ITALIC, |
443 | us::Script::Old_North_Arabian => script::OLD_NORTH_ARABIAN, |
444 | us::Script::Old_Permic => script::OLD_PERMIC, |
445 | us::Script::Old_Persian => script::OLD_PERSIAN, |
446 | us::Script::Old_Sogdian => script::OLD_SOGDIAN, |
447 | us::Script::Old_South_Arabian => script::OLD_SOUTH_ARABIAN, |
448 | us::Script::Old_Turkic => script::OLD_TURKIC, |
449 | us::Script::Oriya => script::ORIYA, |
450 | us::Script::Osage => script::OSAGE, |
451 | us::Script::Osmanya => script::OSMANYA, |
452 | us::Script::Pahawh_Hmong => script::PAHAWH_HMONG, |
453 | us::Script::Palmyrene => script::PALMYRENE, |
454 | us::Script::Pau_Cin_Hau => script::PAU_CIN_HAU, |
455 | us::Script::Phags_Pa => script::PHAGS_PA, |
456 | us::Script::Phoenician => script::PHOENICIAN, |
457 | us::Script::Psalter_Pahlavi => script::PSALTER_PAHLAVI, |
458 | us::Script::Rejang => script::REJANG, |
459 | us::Script::Runic => script::RUNIC, |
460 | us::Script::Samaritan => script::SAMARITAN, |
461 | us::Script::Saurashtra => script::SAURASHTRA, |
462 | us::Script::Sharada => script::SHARADA, |
463 | us::Script::Shavian => script::SHAVIAN, |
464 | us::Script::Siddham => script::SIDDHAM, |
465 | us::Script::SignWriting => script::SIGNWRITING, |
466 | us::Script::Sinhala => script::SINHALA, |
467 | us::Script::Sogdian => script::SOGDIAN, |
468 | us::Script::Sora_Sompeng => script::SORA_SOMPENG, |
469 | us::Script::Soyombo => script::SOYOMBO, |
470 | us::Script::Sundanese => script::SUNDANESE, |
471 | us::Script::Syloti_Nagri => script::SYLOTI_NAGRI, |
472 | us::Script::Syriac => script::SYRIAC, |
473 | us::Script::Tagalog => script::TAGALOG, |
474 | us::Script::Tagbanwa => script::TAGBANWA, |
475 | us::Script::Tai_Le => script::TAI_LE, |
476 | us::Script::Tai_Tham => script::TAI_THAM, |
477 | us::Script::Tai_Viet => script::TAI_VIET, |
478 | us::Script::Takri => script::TAKRI, |
479 | us::Script::Tamil => script::TAMIL, |
480 | us::Script::Tangut => script::TANGUT, |
481 | us::Script::Telugu => script::TELUGU, |
482 | us::Script::Thaana => script::THAANA, |
483 | us::Script::Thai => script::THAI, |
484 | us::Script::Tibetan => script::TIBETAN, |
485 | us::Script::Tifinagh => script::TIFINAGH, |
486 | us::Script::Tirhuta => script::TIRHUTA, |
487 | us::Script::Ugaritic => script::UGARITIC, |
488 | us::Script::Vai => script::VAI, |
489 | us::Script::Wancho => script::WANCHO, |
490 | us::Script::Warang_Citi => script::WARANG_CITI, |
491 | us::Script::Yezidi => script::YEZIDI, |
492 | us::Script::Yi => script::YI, |
493 | us::Script::Zanabazar_Square => script::ZANABAZAR_SQUARE, |
494 | _ => script::UNKNOWN, |
495 | } |
496 | } |
497 | |
498 | fn general_category(self) -> GeneralCategory { |
499 | unicode_properties::general_category::UnicodeGeneralCategory::general_category(self) |
500 | } |
501 | |
502 | fn combining_class(self) -> CanonicalCombiningClass { |
503 | unicode_ccc::get_canonical_combining_class(self) |
504 | } |
505 | |
506 | fn space_fallback(self) -> Option<Space> { |
507 | // All GC=Zs chars that can use a fallback. |
508 | match self { |
509 | ' \u{0020}' => Some(space::SPACE), // SPACE |
510 | ' \u{00A0}' => Some(space::SPACE), // NO-BREAK SPACE |
511 | ' \u{2000}' => Some(space::SPACE_EM_2), // EN QUAD |
512 | ' \u{2001}' => Some(space::SPACE_EM), // EM QUAD |
513 | ' \u{2002}' => Some(space::SPACE_EM_2), // EN SPACE |
514 | ' \u{2003}' => Some(space::SPACE_EM), // EM SPACE |
515 | ' \u{2004}' => Some(space::SPACE_EM_3), // THREE-PER-EM SPACE |
516 | ' \u{2005}' => Some(space::SPACE_EM_4), // FOUR-PER-EM SPACE |
517 | ' \u{2006}' => Some(space::SPACE_EM_6), // SIX-PER-EM SPACE |
518 | ' \u{2007}' => Some(space::SPACE_FIGURE), // FIGURE SPACE |
519 | ' \u{2008}' => Some(space::SPACE_PUNCTUATION), // PUNCTUATION SPACE |
520 | ' \u{2009}' => Some(space::SPACE_EM_5), // THIN SPACE |
521 | ' \u{200A}' => Some(space::SPACE_EM_16), // HAIR SPACE |
522 | ' \u{202F}' => Some(space::SPACE_NARROW), // NARROW NO-BREAK SPACE |
523 | ' \u{205F}' => Some(space::SPACE_4_EM_18), // MEDIUM MATHEMATICAL SPACE |
524 | ' \u{3000}' => Some(space::SPACE_EM), // IDEOGRAPHIC SPACE |
525 | _ => None, // OGHAM SPACE MARK |
526 | } |
527 | } |
528 | |
529 | fn modified_combining_class(self) -> u8 { |
530 | let mut u = self; |
531 | |
532 | // XXX This hack belongs to the Myanmar shaper. |
533 | if u == ' \u{1037}' { |
534 | u = ' \u{103A}' ; |
535 | } |
536 | |
537 | // XXX This hack belongs to the USE shaper (for Tai Tham): |
538 | // Reorder SAKOT to ensure it comes after any tone marks. |
539 | if u == ' \u{1A60}' { |
540 | return 254; |
541 | } |
542 | |
543 | // XXX This hack belongs to the Tibetan shaper: |
544 | // Reorder PADMA to ensure it comes after any vowel marks. |
545 | if u == ' \u{0FC6}' { |
546 | return 254; |
547 | } |
548 | |
549 | // Reorder TSA -PHRU to reorder before U+0F74 |
550 | if u == ' \u{0F39}' { |
551 | return 127; |
552 | } |
553 | |
554 | let k = unicode_ccc::get_canonical_combining_class(u); |
555 | MODIFIED_COMBINING_CLASS[k as usize] |
556 | } |
557 | |
558 | fn mirrored(self) -> Option<char> { |
559 | unicode_bidi_mirroring::get_mirrored(self) |
560 | } |
561 | |
562 | fn is_emoji_extended_pictographic(self) -> bool { |
563 | // Generated by scripts/gen-unicode-is-emoji-ext-pict.py |
564 | match self as u32 { |
565 | 0x00A9 => true, |
566 | 0x00AE => true, |
567 | 0x203C => true, |
568 | 0x2049 => true, |
569 | 0x2122 => true, |
570 | 0x2139 => true, |
571 | 0x2194..=0x2199 => true, |
572 | 0x21A9..=0x21AA => true, |
573 | 0x231A..=0x231B => true, |
574 | 0x2328 => true, |
575 | 0x2388 => true, |
576 | 0x23CF => true, |
577 | 0x23E9..=0x23F3 => true, |
578 | 0x23F8..=0x23FA => true, |
579 | 0x24C2 => true, |
580 | 0x25AA..=0x25AB => true, |
581 | 0x25B6 => true, |
582 | 0x25C0 => true, |
583 | 0x25FB..=0x25FE => true, |
584 | 0x2600..=0x2605 => true, |
585 | 0x2607..=0x2612 => true, |
586 | 0x2614..=0x2685 => true, |
587 | 0x2690..=0x2705 => true, |
588 | 0x2708..=0x2712 => true, |
589 | 0x2714 => true, |
590 | 0x2716 => true, |
591 | 0x271D => true, |
592 | 0x2721 => true, |
593 | 0x2728 => true, |
594 | 0x2733..=0x2734 => true, |
595 | 0x2744 => true, |
596 | 0x2747 => true, |
597 | 0x274C => true, |
598 | 0x274E => true, |
599 | 0x2753..=0x2755 => true, |
600 | 0x2757 => true, |
601 | 0x2763..=0x2767 => true, |
602 | 0x2795..=0x2797 => true, |
603 | 0x27A1 => true, |
604 | 0x27B0 => true, |
605 | 0x27BF => true, |
606 | 0x2934..=0x2935 => true, |
607 | 0x2B05..=0x2B07 => true, |
608 | 0x2B1B..=0x2B1C => true, |
609 | 0x2B50 => true, |
610 | 0x2B55 => true, |
611 | 0x3030 => true, |
612 | 0x303D => true, |
613 | 0x3297 => true, |
614 | 0x3299 => true, |
615 | 0x1F000..=0x1F0FF => true, |
616 | 0x1F10D..=0x1F10F => true, |
617 | 0x1F12F => true, |
618 | 0x1F16C..=0x1F171 => true, |
619 | 0x1F17E..=0x1F17F => true, |
620 | 0x1F18E => true, |
621 | 0x1F191..=0x1F19A => true, |
622 | 0x1F1AD..=0x1F1E5 => true, |
623 | 0x1F201..=0x1F20F => true, |
624 | 0x1F21A => true, |
625 | 0x1F22F => true, |
626 | 0x1F232..=0x1F23A => true, |
627 | 0x1F23C..=0x1F23F => true, |
628 | 0x1F249..=0x1F3FA => true, |
629 | 0x1F400..=0x1F53D => true, |
630 | 0x1F546..=0x1F64F => true, |
631 | 0x1F680..=0x1F6FF => true, |
632 | 0x1F774..=0x1F77F => true, |
633 | 0x1F7D5..=0x1F7FF => true, |
634 | 0x1F80C..=0x1F80F => true, |
635 | 0x1F848..=0x1F84F => true, |
636 | 0x1F85A..=0x1F85F => true, |
637 | 0x1F888..=0x1F88F => true, |
638 | 0x1F8AE..=0x1F8FF => true, |
639 | 0x1F90C..=0x1F93A => true, |
640 | 0x1F93C..=0x1F945 => true, |
641 | 0x1F947..=0x1FFFD => true, |
642 | _ => false, |
643 | } |
644 | } |
645 | |
646 | /// Default_Ignorable codepoints: |
647 | /// |
648 | /// Note: While U+115F, U+1160, U+3164 and U+FFA0 are Default_Ignorable, |
649 | /// we do NOT want to hide them, as the way Uniscribe has implemented them |
650 | /// is with regular spacing glyphs, and that's the way fonts are made to work. |
651 | /// As such, we make exceptions for those four. |
652 | /// Also ignoring U+1BCA0..1BCA3. https://github.com/harfbuzz/harfbuzz/issues/503 |
653 | /// |
654 | /// Unicode 7.0: |
655 | /// $ grep '; Default_Ignorable_Code_Point ' DerivedCoreProperties.txt | sed 's/;.*#/#/' |
656 | /// 00AD # Cf SOFT HYPHEN |
657 | /// 034F # Mn COMBINING GRAPHEME JOINER |
658 | /// 061C # Cf ARABIC LETTER MARK |
659 | /// 115F..1160 # Lo [2] HANGUL CHOSEONG FILLER..HANGUL JUNGSEONG FILLER |
660 | /// 17B4..17B5 # Mn [2] KHMER VOWEL INHERENT AQ..KHMER VOWEL INHERENT AA |
661 | /// 180B..180D # Mn [3] MONGOLIAN FREE VARIATION SELECTOR ONE..MONGOLIAN FREE VARIATION SELECTOR THREE |
662 | /// 180E # Cf MONGOLIAN VOWEL SEPARATOR |
663 | /// 200B..200F # Cf [5] ZERO WIDTH SPACE..RIGHT-TO-LEFT MARK |
664 | /// 202A..202E # Cf [5] LEFT-TO-RIGHT EMBEDDING..RIGHT-TO-LEFT OVERRIDE |
665 | /// 2060..2064 # Cf [5] WORD JOINER..INVISIBLE PLUS |
666 | /// 2065 # Cn <reserved-2065> |
667 | /// 2066..206F # Cf [10] LEFT-TO-RIGHT ISOLATE..NOMINAL DIGIT SHAPES |
668 | /// 3164 # Lo HANGUL FILLER |
669 | /// FE00..FE0F # Mn [16] VARIATION SELECTOR-1..VARIATION SELECTOR-16 |
670 | /// FEFF # Cf ZERO WIDTH NO-BREAK SPACE |
671 | /// FFA0 # Lo HALFWIDTH HANGUL FILLER |
672 | /// FFF0..FFF8 # Cn [9] <reserved-FFF0>..<reserved-FFF8> |
673 | /// 1BCA0..1BCA3 # Cf [4] SHORTHAND FORMAT LETTER OVERLAP..SHORTHAND FORMAT UP STEP |
674 | /// 1D173..1D17A # Cf [8] MUSICAL SYMBOL BEGIN BEAM..MUSICAL SYMBOL END PHRASE |
675 | /// E0000 # Cn <reserved-E0000> |
676 | /// E0001 # Cf LANGUAGE TAG |
677 | /// E0002..E001F # Cn [30] <reserved-E0002>..<reserved-E001F> |
678 | /// E0020..E007F # Cf [96] TAG SPACE..CANCEL TAG |
679 | /// E0080..E00FF # Cn [128] <reserved-E0080>..<reserved-E00FF> |
680 | /// E0100..E01EF # Mn [240] VARIATION SELECTOR-17..VARIATION SELECTOR-256 |
681 | /// E01F0..E0FFF # Cn [3600] <reserved-E01F0>..<reserved-E0FFF> |
682 | fn is_default_ignorable(self) -> bool { |
683 | let ch = u32::from(self); |
684 | let plane = ch >> 16; |
685 | if plane == 0 { |
686 | // BMP |
687 | let page = ch >> 8; |
688 | match page { |
689 | 0x00 => ch == 0x00AD, |
690 | 0x03 => ch == 0x034F, |
691 | 0x06 => ch == 0x061C, |
692 | 0x17 => (0x17B4..=0x17B5).contains(&ch), |
693 | 0x18 => (0x180B..=0x180E).contains(&ch), |
694 | 0x20 => { |
695 | (0x200B..=0x200F).contains(&ch) |
696 | || (0x202A..=0x202E).contains(&ch) |
697 | || (0x2060..=0x206F).contains(&ch) |
698 | } |
699 | 0xFE => (0xFE00..=0xFE0F).contains(&ch) || ch == 0xFEFF, |
700 | 0xFF => (0xFFF0..=0xFFF8).contains(&ch), |
701 | _ => false, |
702 | } |
703 | } else { |
704 | // Other planes |
705 | match plane { |
706 | 0x01 => (0x1D173..=0x1D17A).contains(&ch), |
707 | 0x0E => (0xE0000..=0xE0FFF).contains(&ch), |
708 | _ => false, |
709 | } |
710 | } |
711 | } |
712 | |
713 | fn is_variation_selector(self) -> bool { |
714 | // U+180B..180D MONGOLIAN FREE VARIATION SELECTORs are handled in the |
715 | // Arabic shaper. No need to match them here. |
716 | let ch = u32::from(self); |
717 | (0x0FE00..=0x0FE0F).contains(&ch) || // VARIATION SELECTOR - 1..16 |
718 | (0xE0100..=0xE01EF).contains(&ch) // VARIATION SELECTOR - 17..256 |
719 | } |
720 | |
721 | fn vertical(self) -> Option<char> { |
722 | Some(match u32::from(self) >> 8 { |
723 | 0x20 => match self { |
724 | ' \u{2013}' => ' \u{fe32}' , // EN DASH |
725 | ' \u{2014}' => ' \u{fe31}' , // EM DASH |
726 | ' \u{2025}' => ' \u{fe30}' , // TWO DOT LEADER |
727 | ' \u{2026}' => ' \u{fe19}' , // HORIZONTAL ELLIPSIS |
728 | _ => return None, |
729 | }, |
730 | 0x30 => match self { |
731 | ' \u{3001}' => ' \u{fe11}' , // IDEOGRAPHIC COMMA |
732 | ' \u{3002}' => ' \u{fe12}' , // IDEOGRAPHIC FULL STOP |
733 | ' \u{3008}' => ' \u{fe3f}' , // LEFT ANGLE BRACKET |
734 | ' \u{3009}' => ' \u{fe40}' , // RIGHT ANGLE BRACKET |
735 | ' \u{300a}' => ' \u{fe3d}' , // LEFT DOUBLE ANGLE BRACKET |
736 | ' \u{300b}' => ' \u{fe3e}' , // RIGHT DOUBLE ANGLE BRACKET |
737 | ' \u{300c}' => ' \u{fe41}' , // LEFT CORNER BRACKET |
738 | ' \u{300d}' => ' \u{fe42}' , // RIGHT CORNER BRACKET |
739 | ' \u{300e}' => ' \u{fe43}' , // LEFT WHITE CORNER BRACKET |
740 | ' \u{300f}' => ' \u{fe44}' , // RIGHT WHITE CORNER BRACKET |
741 | ' \u{3010}' => ' \u{fe3b}' , // LEFT BLACK LENTICULAR BRACKET |
742 | ' \u{3011}' => ' \u{fe3c}' , // RIGHT BLACK LENTICULAR BRACKET |
743 | ' \u{3014}' => ' \u{fe39}' , // LEFT TORTOISE SHELL BRACKET |
744 | ' \u{3015}' => ' \u{fe3a}' , // RIGHT TORTOISE SHELL BRACKET |
745 | ' \u{3016}' => ' \u{fe17}' , // LEFT WHITE LENTICULAR BRACKET |
746 | ' \u{3017}' => ' \u{fe18}' , // RIGHT WHITE LENTICULAR BRACKET |
747 | _ => return None, |
748 | }, |
749 | 0xfe => match self { |
750 | ' \u{fe4f}' => ' \u{fe34}' , // WAVY LOW LINE |
751 | _ => return None, |
752 | }, |
753 | 0xff => match self { |
754 | ' \u{ff01}' => ' \u{fe15}' , // FULLWIDTH EXCLAMATION MARK |
755 | ' \u{ff08}' => ' \u{fe35}' , // FULLWIDTH LEFT PARENTHESIS |
756 | ' \u{ff09}' => ' \u{fe36}' , // FULLWIDTH RIGHT PARENTHESIS |
757 | ' \u{ff0c}' => ' \u{fe10}' , // FULLWIDTH COMMA |
758 | ' \u{ff1a}' => ' \u{fe13}' , // FULLWIDTH COLON |
759 | ' \u{ff1b}' => ' \u{fe14}' , // FULLWIDTH SEMICOLON |
760 | ' \u{ff1f}' => ' \u{fe16}' , // FULLWIDTH QUESTION MARK |
761 | ' \u{ff3b}' => ' \u{fe47}' , // FULLWIDTH LEFT SQUARE BRACKET |
762 | ' \u{ff3d}' => ' \u{fe48}' , // FULLWIDTH RIGHT SQUARE BRACKET |
763 | ' \u{ff3f}' => ' \u{fe33}' , // FULLWIDTH LOW LINE |
764 | ' \u{ff5b}' => ' \u{fe37}' , // FULLWIDTH LEFT CURLY BRACKET |
765 | ' \u{ff5d}' => ' \u{fe38}' , // FULLWIDTH RIGHT CURLY BRACKET |
766 | _ => return None, |
767 | }, |
768 | _ => return None, |
769 | }) |
770 | } |
771 | } |
772 | |
773 | const S_BASE: u32 = 0xAC00; |
774 | const L_BASE: u32 = 0x1100; |
775 | const V_BASE: u32 = 0x1161; |
776 | const T_BASE: u32 = 0x11A7; |
777 | const L_COUNT: u32 = 19; |
778 | const V_COUNT: u32 = 21; |
779 | const T_COUNT: u32 = 28; |
780 | const N_COUNT: u32 = V_COUNT * T_COUNT; |
781 | const S_COUNT: u32 = L_COUNT * N_COUNT; |
782 | |
783 | pub fn compose(a: char, b: char) -> Option<char> { |
784 | if let Some(ab: char) = compose_hangul(a, b) { |
785 | return Some(ab); |
786 | } |
787 | |
788 | let needle: u64 = (a as u64) << 32 | (b as u64); |
789 | crateResult::unicode_norm::COMPOSITION_TABLE |
790 | .binary_search_by(|item| item.0.cmp(&needle)) |
791 | .map(|idx: usize| crate::unicode_norm::COMPOSITION_TABLE[idx].1) |
792 | .ok() |
793 | } |
794 | |
795 | fn compose_hangul(a: char, b: char) -> Option<char> { |
796 | let l: u32 = u32::from(a); |
797 | let v: u32 = u32::from(b); |
798 | if L_BASE <= l && l < (L_BASE + L_COUNT) && V_BASE <= v && v < (V_BASE + V_COUNT) { |
799 | let r: u32 = S_BASE + (l - L_BASE) * N_COUNT + (v - V_BASE) * T_COUNT; |
800 | Some(char::try_from(r).unwrap()) |
801 | } else if S_BASE <= l |
802 | && l <= (S_BASE + S_COUNT - T_COUNT) |
803 | && T_BASE <= v |
804 | && v < (T_BASE + T_COUNT) |
805 | && (l - S_BASE) % T_COUNT == 0 |
806 | { |
807 | let r: u32 = l + (v - T_BASE); |
808 | Some(char::try_from(r).unwrap()) |
809 | } else { |
810 | None |
811 | } |
812 | } |
813 | |
814 | pub fn decompose(ab: char) -> Option<(char, char)> { |
815 | if let Some(ab: (char, char)) = decompose_hangul(ab) { |
816 | return Some(ab); |
817 | } |
818 | |
819 | crateResult<(char, char), usize>::unicode_norm::DECOMPOSITION_TABLE |
820 | .binary_search_by(|item| item.0.cmp(&ab)) |
821 | .map(|idx: usize| { |
822 | let chars: &(char, char, Option) = &crate::unicode_norm::DECOMPOSITION_TABLE[idx]; |
823 | (chars.1, chars.2.unwrap_or(default:' \0' )) |
824 | }) |
825 | .ok() |
826 | } |
827 | |
828 | pub fn decompose_hangul(ab: char) -> Option<(char, char)> { |
829 | let si: u32 = u32::from(ab).wrapping_sub(S_BASE); |
830 | if si >= S_COUNT { |
831 | return None; |
832 | } |
833 | |
834 | let (a: u32, b: u32) = if si % T_COUNT != 0 { |
835 | // LV,T |
836 | (S_BASE + (si / T_COUNT) * T_COUNT, T_BASE + (si % T_COUNT)) |
837 | } else { |
838 | // L,V |
839 | (L_BASE + (si / N_COUNT), V_BASE + (si % N_COUNT) / T_COUNT) |
840 | }; |
841 | |
842 | Some((char::try_from(a).unwrap(), char::try_from(b).unwrap())) |
843 | } |
844 | |
845 | #[cfg (test)] |
846 | mod tests { |
847 | #[test ] |
848 | fn check_unicode_version() { |
849 | assert_eq!(unicode_bidi_mirroring::UNICODE_VERSION, (13, 0, 0)); |
850 | assert_eq!(unicode_ccc::UNICODE_VERSION, (13, 0, 0)); |
851 | assert_eq!(unicode_properties::UNICODE_VERSION, (15, 0, 0)); |
852 | assert_eq!(unicode_script::UNICODE_VERSION, (15, 0, 0)); |
853 | assert_eq!(crate::unicode_norm::UNICODE_VERSION, (13, 0, 0)); |
854 | } |
855 | } |
856 | |
857 | // TODO: remove |
858 | pub mod hb_gc { |
859 | pub const RB_UNICODE_GENERAL_CATEGORY_CONTROL: u32 = 0; |
860 | pub const RB_UNICODE_GENERAL_CATEGORY_FORMAT: u32 = 1; |
861 | pub const RB_UNICODE_GENERAL_CATEGORY_UNASSIGNED: u32 = 2; |
862 | pub const RB_UNICODE_GENERAL_CATEGORY_PRIVATE_USE: u32 = 3; |
863 | pub const RB_UNICODE_GENERAL_CATEGORY_SURROGATE: u32 = 4; |
864 | pub const RB_UNICODE_GENERAL_CATEGORY_LOWERCASE_LETTER: u32 = 5; |
865 | pub const RB_UNICODE_GENERAL_CATEGORY_MODIFIER_LETTER: u32 = 6; |
866 | pub const RB_UNICODE_GENERAL_CATEGORY_OTHER_LETTER: u32 = 7; |
867 | pub const RB_UNICODE_GENERAL_CATEGORY_TITLECASE_LETTER: u32 = 8; |
868 | pub const RB_UNICODE_GENERAL_CATEGORY_UPPERCASE_LETTER: u32 = 9; |
869 | pub const RB_UNICODE_GENERAL_CATEGORY_SPACING_MARK: u32 = 10; |
870 | pub const RB_UNICODE_GENERAL_CATEGORY_ENCLOSING_MARK: u32 = 11; |
871 | pub const RB_UNICODE_GENERAL_CATEGORY_NON_SPACING_MARK: u32 = 12; |
872 | pub const RB_UNICODE_GENERAL_CATEGORY_DECIMAL_NUMBER: u32 = 13; |
873 | pub const RB_UNICODE_GENERAL_CATEGORY_LETTER_NUMBER: u32 = 14; |
874 | pub const RB_UNICODE_GENERAL_CATEGORY_OTHER_NUMBER: u32 = 15; |
875 | pub const RB_UNICODE_GENERAL_CATEGORY_CONNECT_PUNCTUATION: u32 = 16; |
876 | pub const RB_UNICODE_GENERAL_CATEGORY_DASH_PUNCTUATION: u32 = 17; |
877 | pub const RB_UNICODE_GENERAL_CATEGORY_CLOSE_PUNCTUATION: u32 = 18; |
878 | pub const RB_UNICODE_GENERAL_CATEGORY_FINAL_PUNCTUATION: u32 = 19; |
879 | pub const RB_UNICODE_GENERAL_CATEGORY_INITIAL_PUNCTUATION: u32 = 20; |
880 | pub const RB_UNICODE_GENERAL_CATEGORY_OTHER_PUNCTUATION: u32 = 21; |
881 | pub const RB_UNICODE_GENERAL_CATEGORY_OPEN_PUNCTUATION: u32 = 22; |
882 | pub const RB_UNICODE_GENERAL_CATEGORY_CURRENCY_SYMBOL: u32 = 23; |
883 | pub const RB_UNICODE_GENERAL_CATEGORY_MODIFIER_SYMBOL: u32 = 24; |
884 | pub const RB_UNICODE_GENERAL_CATEGORY_MATH_SYMBOL: u32 = 25; |
885 | pub const RB_UNICODE_GENERAL_CATEGORY_OTHER_SYMBOL: u32 = 26; |
886 | pub const RB_UNICODE_GENERAL_CATEGORY_LINE_SEPARATOR: u32 = 27; |
887 | pub const RB_UNICODE_GENERAL_CATEGORY_PARAGRAPH_SEPARATOR: u32 = 28; |
888 | pub const RB_UNICODE_GENERAL_CATEGORY_SPACE_SEPARATOR: u32 = 29; |
889 | } |
890 | |