Commit | Line | Data |
9fdf68be |
1 | # !!!!!!! DO NOT EDIT THIS FILE !!!!!!! |
d73e5302 |
2 | # This file is built by mktables from e.g. Unicode.txt. |
9fdf68be |
3 | # Any changes made here will be lost! |
d73e5302 |
4 | %utf8::In = |
5 | ( |
6 | 'ARABIC' => '16', |
7 | 'ARMENIAN' => '14', |
8 | 'ASCII_Hex_Digit' => '152', |
9 | 'Alphabetic' => '164', |
10 | 'Alphabetic Presentation Forms' => '129', |
11 | 'Any' => '171', |
12 | 'Arabic Block' => '62', |
13 | 'Arabic Presentation Forms-A' => '130', |
14 | 'Arabic Presentation Forms-B' => '134', |
15 | 'Armenian Block' => '60', |
16 | 'Arrows' => '96', |
17 | 'Assigned' => '163', |
18 | 'BENGALI' => '20', |
19 | 'BOPOMOFO' => '45', |
20 | 'Basic Latin' => '51', |
21 | 'Bengali Block' => '66', |
22 | 'Bidi_Control' => '159', |
23 | 'Block Elements' => '103', |
24 | 'Bopomofo Block' => '114', |
25 | 'Bopomofo Extended' => '117', |
26 | 'Box Drawing' => '102', |
27 | 'Braille Patterns' => '107', |
28 | 'Byzantine Musical Symbols' => '140', |
29 | 'CANADIAN-ABORIGINAL' => '37', |
30 | 'CHEROKEE' => '36', |
31 | 'CJK Compatibility' => '119', |
32 | 'CJK Compatibility Forms' => '132', |
33 | 'CJK Compatibility Ideographs' => '128', |
34 | 'CJK Compatibility Ideographs Supplement' => '144', |
35 | 'CJK Ideograph' => '1', |
36 | 'CJK Ideograph Extension A' => '0', |
37 | 'CJK Ideograph Extension B' => '7', |
38 | 'CJK Radicals Supplement' => '108', |
39 | 'CJK Symbols and Punctuation' => '111', |
40 | 'CJK Unified Ideographs' => '121', |
41 | 'CJK Unified Ideographs Extension A' => '120', |
42 | 'CJK Unified Ideographs Extension B' => '143', |
43 | 'CYRILLIC' => '13', |
44 | 'Cherokee Block' => '82', |
45 | 'Combining Diacritical Marks' => '57', |
46 | 'Combining Half Marks' => '131', |
47 | 'Combining Marks for Symbols' => '93', |
48 | 'Common' => '50', |
49 | 'Control Pictures' => '99', |
50 | 'Currency Symbols' => '92', |
51 | 'Cyrillic Block' => '59', |
52 | 'DESERET' => '49', |
53 | 'DEVANAGARI' => '19', |
54 | 'Dash' => '151', |
55 | 'Deseret Block' => '139', |
56 | 'Devanagari Block' => '65', |
57 | 'Diacritic' => '154', |
58 | 'Dingbats' => '106', |
59 | 'ETHIOPIC' => '35', |
60 | 'Enclosed Alphanumerics' => '101', |
61 | 'Enclosed CJK Letters and Months' => '118', |
62 | 'Ethiopic Block' => '81', |
63 | 'Extender' => '155', |
64 | 'GEORGIAN' => '33', |
65 | 'GOTHIC' => '48', |
66 | 'GREEK' => '11', |
67 | 'GUJARATI' => '22', |
68 | 'GURMUKHI' => '21', |
69 | 'General Punctuation' => '90', |
70 | 'Geometric Shapes' => '104', |
71 | 'Georgian Block' => '79', |
72 | 'Gothic Block' => '138', |
73 | 'Greek Block' => '58', |
74 | 'Greek Extended' => '89', |
75 | 'Gujarati Block' => '68', |
76 | 'Gurmukhi Block' => '67', |
77 | 'HAN' => '42', |
78 | 'HANGUL' => '34', |
79 | 'HEBREW' => '15', |
80 | 'HIRAGANA' => '43', |
81 | 'Halfwidth and Fullwidth Forms' => '136', |
82 | 'Hangul Compatibility Jamo' => '115', |
83 | 'Hangul Jamo' => '80', |
84 | 'Hangul Syllable' => '2', |
85 | 'Hangul Syllables' => '124', |
86 | 'Hebrew Block' => '61', |
87 | 'Hex_Digit' => '153', |
88 | 'High Private Use Surrogates' => '126', |
89 | 'High Surrogates' => '125', |
90 | 'Hiragana Block' => '112', |
91 | 'Hyphen' => '150', |
92 | 'ID_Continue' => '170', |
93 | 'ID_Start' => '169', |
94 | 'INHERITED' => '12', |
95 | 'IPA Extensions' => '55', |
96 | 'Ideographic' => '161', |
97 | 'Ideographic Description Characters' => '110', |
98 | 'Join_Control' => '158', |
99 | 'KANNADA' => '26', |
100 | 'KATAKANA' => '44', |
101 | 'KHMER' => '40', |
102 | 'Kanbun' => '116', |
103 | 'Kangxi Radicals' => '109', |
104 | 'Kannada Block' => '72', |
105 | 'Katakana Block' => '113', |
106 | 'Khmer Block' => '86', |
107 | 'LAO' => '30', |
108 | 'LATIN' => '10', |
109 | 'Lampersand' => '168', |
110 | 'Lao Block' => '76', |
111 | 'Latin Extended Additional' => '88', |
112 | 'Latin Extended-A' => '53', |
113 | 'Latin Extended-B' => '54', |
114 | 'Latin-1 Supplement' => '52', |
115 | 'Letterlike Symbols' => '94', |
116 | 'Low Surrogate' => '5', |
117 | 'Low Surrogates' => '127', |
118 | 'Lowercase' => '165', |
119 | 'MALAYALAM' => '27', |
120 | 'MONGOLIAN' => '41', |
121 | 'MYANMAR' => '32', |
122 | 'Malayalam Block' => '73', |
123 | 'Math' => '167', |
124 | 'Mathematical Alphanumeric Symbols' => '142', |
125 | 'Mathematical Operators' => '97', |
126 | 'Miscellaneous Symbols' => '105', |
127 | 'Miscellaneous Technical' => '98', |
128 | 'Mongolian Block' => '87', |
129 | 'Musical Symbols' => '141', |
130 | 'Myanmar Block' => '78', |
131 | 'Non Private Use High Surrogate' => '3', |
132 | 'Noncharacter_Code_Point' => '162', |
133 | 'Number Forms' => '95', |
134 | 'OGHAM' => '38', |
135 | 'OLD-ITALIC' => '47', |
136 | 'ORIYA' => '23', |
137 | 'Ogham Block' => '84', |
138 | 'Old Italic' => '137', |
139 | 'Optical Character Recognition' => '100', |
140 | 'Oriya Block' => '69', |
141 | 'Other_Alphabetic' => '157', |
142 | 'Other_Lowercase' => '156', |
143 | 'Other_Math' => '149', |
144 | 'Other_Uppercase' => '160', |
145 | 'Plane 15 Private Use' => '8', |
146 | 'Plane 16 Private Use' => '9', |
147 | 'Private Use' => '6', |
148 | 'Private Use High Surrogate' => '4', |
149 | 'Quotation_Mark' => '148', |
150 | 'RUNIC' => '39', |
151 | 'Runic Block' => '85', |
152 | 'SINHALA' => '28', |
153 | 'SYRIAC' => '17', |
154 | 'Sinhala Block' => '74', |
155 | 'Small Form Variants' => '133', |
156 | 'Spacing Modifier Letters' => '56', |
157 | 'Specials' => '135', |
158 | 'Superscripts and Subscripts' => '91', |
159 | 'Syriac Block' => '63', |
160 | 'TAMIL' => '24', |
161 | 'TELUGU' => '25', |
162 | 'THAANA' => '18', |
163 | 'THAI' => '29', |
164 | 'TIBETAN' => '31', |
165 | 'Tags' => '145', |
166 | 'Tamil Block' => '70', |
167 | 'Telugu Block' => '71', |
168 | 'Terminal_Punctuation' => '147', |
169 | 'Thaana Block' => '64', |
170 | 'Thai Block' => '75', |
171 | 'Tibetan Block' => '77', |
172 | 'Unified Canadian Aboriginal Syllabics' => '83', |
173 | 'Uppercase' => '166', |
174 | 'White_space' => '146', |
175 | 'YI' => '46', |
176 | 'Yi Radicals' => '123', |
177 | 'Yi Syllables' => '122', |
d9efae67 |
178 | ); |
d73e5302 |
179 | %utf8::InPat = |
180 | ( |
c8b5a1e3 |
181 | 'al' => { |
d73e5302 |
182 | 'Alphabetic' => '164', |
183 | 'Alphabetic(?:[-_]|\s+)?Presentation(?:[-_]|\s+)?Forms' => '129', |
1ac13f9a |
184 | }, |
c8b5a1e3 |
185 | 'an' => { |
d73e5302 |
186 | 'Any' => '171', |
d9efae67 |
187 | }, |
c8b5a1e3 |
188 | 'ar' => { |
d73e5302 |
189 | 'ARABIC' => '16', |
190 | 'ARMENIAN' => '14', |
191 | 'Arabic(?:[-_]|\s+)?Block' => '62', |
192 | 'Arabic(?:[-_]|\s+)?Presentation(?:[-_]|\s+)?Forms(?:[-_]|\s+)?A' => '130', |
193 | 'Arabic(?:[-_]|\s+)?Presentation(?:[-_]|\s+)?Forms(?:[-_]|\s+)?B' => '134', |
194 | 'Armenian(?:[-_]|\s+)?Block' => '60', |
195 | 'Arrows' => '96', |
d9efae67 |
196 | }, |
c8b5a1e3 |
197 | 'as' => { |
d73e5302 |
198 | 'ASCII(?:[-_]|\s+)?Hex(?:[-_]|\s+)?Digit' => '152', |
199 | 'Assigned' => '163', |
1ac13f9a |
200 | }, |
c8b5a1e3 |
201 | 'ba' => { |
d73e5302 |
202 | 'Basic(?:[-_]|\s+)?Latin' => '51', |
d9efae67 |
203 | }, |
c8b5a1e3 |
204 | 'be' => { |
d73e5302 |
205 | 'BENGALI' => '20', |
206 | 'Bengali(?:[-_]|\s+)?Block' => '66', |
d9efae67 |
207 | }, |
c8b5a1e3 |
208 | 'bi' => { |
d73e5302 |
209 | 'Bidi(?:[-_]|\s+)?Control' => '159', |
1ac13f9a |
210 | }, |
c8b5a1e3 |
211 | 'bl' => { |
d73e5302 |
212 | 'Block(?:[-_]|\s+)?Elements' => '103', |
d9efae67 |
213 | }, |
c8b5a1e3 |
214 | 'bo' => { |
d73e5302 |
215 | 'BOPOMOFO' => '45', |
216 | 'Bopomofo(?:[-_]|\s+)?Block' => '114', |
217 | 'Bopomofo(?:[-_]|\s+)?Extended' => '117', |
218 | 'Box(?:[-_]|\s+)?Drawing' => '102', |
d9efae67 |
219 | }, |
c8b5a1e3 |
220 | 'br' => { |
d73e5302 |
221 | 'Braille(?:[-_]|\s+)?Patterns' => '107', |
d9efae67 |
222 | }, |
c8b5a1e3 |
223 | 'by' => { |
d73e5302 |
224 | 'Byzantine(?:[-_]|\s+)?Musical(?:[-_]|\s+)?Symbols' => '140', |
d9efae67 |
225 | }, |
c8b5a1e3 |
226 | 'ca' => { |
d73e5302 |
227 | 'CANADIAN(?:[-_]|\s+)?ABORIGINAL' => '37', |
d9efae67 |
228 | }, |
c8b5a1e3 |
229 | 'ch' => { |
d73e5302 |
230 | 'CHEROKEE' => '36', |
231 | 'Cherokee(?:[-_]|\s+)?Block' => '82', |
d9efae67 |
232 | }, |
c8b5a1e3 |
233 | 'cj' => { |
d73e5302 |
234 | 'CJK(?:[-_]|\s+)?Compatibility' => '119', |
235 | 'CJK(?:[-_]|\s+)?Compatibility(?:[-_]|\s+)?Forms' => '132', |
236 | 'CJK(?:[-_]|\s+)?Compatibility(?:[-_]|\s+)?Ideographs' => '128', |
237 | 'CJK(?:[-_]|\s+)?Compatibility(?:[-_]|\s+)?Ideographs(?:[-_]|\s+)?Supplement' => '144', |
238 | 'CJK(?:[-_]|\s+)?Ideograph' => '1', |
239 | 'CJK(?:[-_]|\s+)?Ideograph(?:[-_]|\s+)?Extension(?:[-_]|\s+)?A' => '0', |
240 | 'CJK(?:[-_]|\s+)?Ideograph(?:[-_]|\s+)?Extension(?:[-_]|\s+)?B' => '7', |
241 | 'CJK(?:[-_]|\s+)?Radicals(?:[-_]|\s+)?Supplement' => '108', |
242 | 'CJK(?:[-_]|\s+)?Symbols(?:[-_]|\s+)?and(?:[-_]|\s+)?Punctuation' => '111', |
243 | 'CJK(?:[-_]|\s+)?Unified(?:[-_]|\s+)?Ideographs' => '121', |
244 | 'CJK(?:[-_]|\s+)?Unified(?:[-_]|\s+)?Ideographs(?:[-_]|\s+)?Extension(?:[-_]|\s+)?A' => '120', |
245 | 'CJK(?:[-_]|\s+)?Unified(?:[-_]|\s+)?Ideographs(?:[-_]|\s+)?Extension(?:[-_]|\s+)?B' => '143', |
d9efae67 |
246 | }, |
c8b5a1e3 |
247 | 'co' => { |
d73e5302 |
248 | 'Combining(?:[-_]|\s+)?Diacritical(?:[-_]|\s+)?Marks' => '57', |
249 | 'Combining(?:[-_]|\s+)?Half(?:[-_]|\s+)?Marks' => '131', |
250 | 'Combining(?:[-_]|\s+)?Marks(?:[-_]|\s+)?for(?:[-_]|\s+)?Symbols' => '93', |
251 | 'Common' => '50', |
252 | 'Control(?:[-_]|\s+)?Pictures' => '99', |
d9efae67 |
253 | }, |
c8b5a1e3 |
254 | 'cu' => { |
d73e5302 |
255 | 'Currency(?:[-_]|\s+)?Symbols' => '92', |
d9efae67 |
256 | }, |
c8b5a1e3 |
257 | 'cy' => { |
d73e5302 |
258 | 'CYRILLIC' => '13', |
259 | 'Cyrillic(?:[-_]|\s+)?Block' => '59', |
d9efae67 |
260 | }, |
c8b5a1e3 |
261 | 'da' => { |
d73e5302 |
262 | 'Dash' => '151', |
1ac13f9a |
263 | }, |
c8b5a1e3 |
264 | 'de' => { |
d73e5302 |
265 | 'DESERET' => '49', |
266 | 'DEVANAGARI' => '19', |
267 | 'Deseret(?:[-_]|\s+)?Block' => '139', |
268 | 'Devanagari(?:[-_]|\s+)?Block' => '65', |
d9efae67 |
269 | }, |
c8b5a1e3 |
270 | 'di' => { |
d73e5302 |
271 | 'Diacritic' => '154', |
272 | 'Dingbats' => '106', |
d9efae67 |
273 | }, |
c8b5a1e3 |
274 | 'en' => { |
d73e5302 |
275 | 'Enclosed(?:[-_]|\s+)?Alphanumerics' => '101', |
276 | 'Enclosed(?:[-_]|\s+)?CJK(?:[-_]|\s+)?Letters(?:[-_]|\s+)?and(?:[-_]|\s+)?Months' => '118', |
d9efae67 |
277 | }, |
c8b5a1e3 |
278 | 'et' => { |
d73e5302 |
279 | 'ETHIOPIC' => '35', |
280 | 'Ethiopic(?:[-_]|\s+)?Block' => '81', |
d9efae67 |
281 | }, |
c8b5a1e3 |
282 | 'ex' => { |
d73e5302 |
283 | 'Extender' => '155', |
1ac13f9a |
284 | }, |
c8b5a1e3 |
285 | 'ge' => { |
d73e5302 |
286 | 'GEORGIAN' => '33', |
287 | 'General(?:[-_]|\s+)?Punctuation' => '90', |
288 | 'Geometric(?:[-_]|\s+)?Shapes' => '104', |
289 | 'Georgian(?:[-_]|\s+)?Block' => '79', |
d9efae67 |
290 | }, |
c8b5a1e3 |
291 | 'go' => { |
d73e5302 |
292 | 'GOTHIC' => '48', |
293 | 'Gothic(?:[-_]|\s+)?Block' => '138', |
d9efae67 |
294 | }, |
c8b5a1e3 |
295 | 'gr' => { |
d73e5302 |
296 | 'GREEK' => '11', |
297 | 'Greek(?:[-_]|\s+)?Block' => '58', |
298 | 'Greek(?:[-_]|\s+)?Extended' => '89', |
d9efae67 |
299 | }, |
c8b5a1e3 |
300 | 'gu' => { |
d73e5302 |
301 | 'GUJARATI' => '22', |
302 | 'GURMUKHI' => '21', |
303 | 'Gujarati(?:[-_]|\s+)?Block' => '68', |
304 | 'Gurmukhi(?:[-_]|\s+)?Block' => '67', |
d9efae67 |
305 | }, |
c8b5a1e3 |
306 | 'ha' => { |
d73e5302 |
307 | 'HAN' => '42', |
308 | 'HANGUL' => '34', |
309 | 'Halfwidth(?:[-_]|\s+)?and(?:[-_]|\s+)?Fullwidth(?:[-_]|\s+)?Forms' => '136', |
310 | 'Hangul(?:[-_]|\s+)?Compatibility(?:[-_]|\s+)?Jamo' => '115', |
311 | 'Hangul(?:[-_]|\s+)?Jamo' => '80', |
312 | 'Hangul(?:[-_]|\s+)?Syllable' => '2', |
313 | 'Hangul(?:[-_]|\s+)?Syllables' => '124', |
d9efae67 |
314 | }, |
c8b5a1e3 |
315 | 'he' => { |
d73e5302 |
316 | 'HEBREW' => '15', |
317 | 'Hebrew(?:[-_]|\s+)?Block' => '61', |
318 | 'Hex(?:[-_]|\s+)?Digit' => '153', |
1ac13f9a |
319 | }, |
c8b5a1e3 |
320 | 'hi' => { |
d73e5302 |
321 | 'HIRAGANA' => '43', |
322 | 'High(?:[-_]|\s+)?Private(?:[-_]|\s+)?Use(?:[-_]|\s+)?Surrogates' => '126', |
323 | 'High(?:[-_]|\s+)?Surrogates' => '125', |
324 | 'Hiragana(?:[-_]|\s+)?Block' => '112', |
d9efae67 |
325 | }, |
c8b5a1e3 |
326 | 'hy' => { |
d73e5302 |
327 | 'Hyphen' => '150', |
1ac13f9a |
328 | }, |
c8b5a1e3 |
329 | 'id' => { |
d73e5302 |
330 | 'ID(?:[-_]|\s+)?Continue' => '170', |
331 | 'ID(?:[-_]|\s+)?Start' => '169', |
332 | 'Ideographic' => '161', |
333 | 'Ideographic(?:[-_]|\s+)?Description(?:[-_]|\s+)?Characters' => '110', |
d9efae67 |
334 | }, |
c8b5a1e3 |
335 | 'in' => { |
d73e5302 |
336 | 'INHERITED' => '12', |
d9efae67 |
337 | }, |
c8b5a1e3 |
338 | 'ip' => { |
d73e5302 |
339 | 'IPA(?:[-_]|\s+)?Extensions' => '55', |
d9efae67 |
340 | }, |
c8b5a1e3 |
341 | 'jo' => { |
d73e5302 |
342 | 'Join(?:[-_]|\s+)?Control' => '158', |
1ac13f9a |
343 | }, |
c8b5a1e3 |
344 | 'ka' => { |
d73e5302 |
345 | 'KANNADA' => '26', |
346 | 'KATAKANA' => '44', |
347 | 'Kanbun' => '116', |
348 | 'Kangxi(?:[-_]|\s+)?Radicals' => '109', |
349 | 'Kannada(?:[-_]|\s+)?Block' => '72', |
350 | 'Katakana(?:[-_]|\s+)?Block' => '113', |
d9efae67 |
351 | }, |
c8b5a1e3 |
352 | 'kh' => { |
d73e5302 |
353 | 'KHMER' => '40', |
354 | 'Khmer(?:[-_]|\s+)?Block' => '86', |
d9efae67 |
355 | }, |
c8b5a1e3 |
356 | 'la' => { |
d73e5302 |
357 | 'LAO' => '30', |
358 | 'LATIN' => '10', |
359 | 'Lampersand' => '168', |
360 | 'Lao(?:[-_]|\s+)?Block' => '76', |
361 | 'Latin(?:[-_]|\s+)?Extended(?:[-_]|\s+)?Additional' => '88', |
362 | 'Latin(?:[-_]|\s+)?Extended(?:[-_]|\s+)?A' => '53', |
363 | 'Latin(?:[-_]|\s+)?Extended(?:[-_]|\s+)?B' => '54', |
364 | 'Latin(?:[-_]|\s+)?1(?:[-_]|\s+)?Supplement' => '52', |
d9efae67 |
365 | }, |
c8b5a1e3 |
366 | 'le' => { |
d73e5302 |
367 | 'Letterlike(?:[-_]|\s+)?Symbols' => '94', |
d9efae67 |
368 | }, |
c8b5a1e3 |
369 | 'lo' => { |
d73e5302 |
370 | 'Low(?:[-_]|\s+)?Surrogate' => '5', |
371 | 'Low(?:[-_]|\s+)?Surrogates' => '127', |
372 | 'Lowercase' => '165', |
d9efae67 |
373 | }, |
c8b5a1e3 |
374 | 'ma' => { |
d73e5302 |
375 | 'MALAYALAM' => '27', |
376 | 'Malayalam(?:[-_]|\s+)?Block' => '73', |
377 | 'Math' => '167', |
378 | 'Mathematical(?:[-_]|\s+)?Alphanumeric(?:[-_]|\s+)?Symbols' => '142', |
379 | 'Mathematical(?:[-_]|\s+)?Operators' => '97', |
d9efae67 |
380 | }, |
c8b5a1e3 |
381 | 'mi' => { |
d73e5302 |
382 | 'Miscellaneous(?:[-_]|\s+)?Symbols' => '105', |
383 | 'Miscellaneous(?:[-_]|\s+)?Technical' => '98', |
d9efae67 |
384 | }, |
c8b5a1e3 |
385 | 'mo' => { |
d73e5302 |
386 | 'MONGOLIAN' => '41', |
387 | 'Mongolian(?:[-_]|\s+)?Block' => '87', |
d9efae67 |
388 | }, |
c8b5a1e3 |
389 | 'mu' => { |
d73e5302 |
390 | 'Musical(?:[-_]|\s+)?Symbols' => '141', |
d9efae67 |
391 | }, |
c8b5a1e3 |
392 | 'my' => { |
d73e5302 |
393 | 'MYANMAR' => '32', |
394 | 'Myanmar(?:[-_]|\s+)?Block' => '78', |
d9efae67 |
395 | }, |
c8b5a1e3 |
396 | 'no' => { |
d73e5302 |
397 | 'Non(?:[-_]|\s+)?Private(?:[-_]|\s+)?Use(?:[-_]|\s+)?High(?:[-_]|\s+)?Surrogate' => '3', |
398 | 'Noncharacter(?:[-_]|\s+)?Code(?:[-_]|\s+)?Point' => '162', |
1ac13f9a |
399 | }, |
c8b5a1e3 |
400 | 'nu' => { |
d73e5302 |
401 | 'Number(?:[-_]|\s+)?Forms' => '95', |
d9efae67 |
402 | }, |
c8b5a1e3 |
403 | 'og' => { |
d73e5302 |
404 | 'OGHAM' => '38', |
405 | 'Ogham(?:[-_]|\s+)?Block' => '84', |
d9efae67 |
406 | }, |
c8b5a1e3 |
407 | 'ol' => { |
d73e5302 |
408 | 'OLD(?:[-_]|\s+)?ITALIC' => '47', |
409 | 'Old(?:[-_]|\s+)?Italic' => '137', |
d9efae67 |
410 | }, |
c8b5a1e3 |
411 | 'op' => { |
d73e5302 |
412 | 'Optical(?:[-_]|\s+)?Character(?:[-_]|\s+)?Recognition' => '100', |
d9efae67 |
413 | }, |
c8b5a1e3 |
414 | 'or' => { |
d73e5302 |
415 | 'ORIYA' => '23', |
416 | 'Oriya(?:[-_]|\s+)?Block' => '69', |
d9efae67 |
417 | }, |
c8b5a1e3 |
418 | 'ot' => { |
d73e5302 |
419 | 'Other(?:[-_]|\s+)?Alphabetic' => '157', |
420 | 'Other(?:[-_]|\s+)?Lowercase' => '156', |
421 | 'Other(?:[-_]|\s+)?Math' => '149', |
422 | 'Other(?:[-_]|\s+)?Uppercase' => '160', |
423 | }, |
424 | 'pl' => { |
425 | 'Plane(?:[-_]|\s+)?15(?:[-_]|\s+)?Private(?:[-_]|\s+)?Use' => '8', |
426 | 'Plane(?:[-_]|\s+)?16(?:[-_]|\s+)?Private(?:[-_]|\s+)?Use' => '9', |
1ac13f9a |
427 | }, |
c8b5a1e3 |
428 | 'pr' => { |
d73e5302 |
429 | 'Private(?:[-_]|\s+)?Use' => '6', |
430 | 'Private(?:[-_]|\s+)?Use(?:[-_]|\s+)?High(?:[-_]|\s+)?Surrogate' => '4', |
d9efae67 |
431 | }, |
c8b5a1e3 |
432 | 'qu' => { |
d73e5302 |
433 | 'Quotation(?:[-_]|\s+)?Mark' => '148', |
1ac13f9a |
434 | }, |
c8b5a1e3 |
435 | 'ru' => { |
d73e5302 |
436 | 'RUNIC' => '39', |
437 | 'Runic(?:[-_]|\s+)?Block' => '85', |
d9efae67 |
438 | }, |
c8b5a1e3 |
439 | 'si' => { |
d73e5302 |
440 | 'SINHALA' => '28', |
441 | 'Sinhala(?:[-_]|\s+)?Block' => '74', |
d9efae67 |
442 | }, |
c8b5a1e3 |
443 | 'sm' => { |
d73e5302 |
444 | 'Small(?:[-_]|\s+)?Form(?:[-_]|\s+)?Variants' => '133', |
d9efae67 |
445 | }, |
c8b5a1e3 |
446 | 'sp' => { |
d73e5302 |
447 | 'Spacing(?:[-_]|\s+)?Modifier(?:[-_]|\s+)?Letters' => '56', |
448 | 'Specials' => '135', |
d9efae67 |
449 | }, |
c8b5a1e3 |
450 | 'su' => { |
d73e5302 |
451 | 'Superscripts(?:[-_]|\s+)?and(?:[-_]|\s+)?Subscripts' => '91', |
d9efae67 |
452 | }, |
c8b5a1e3 |
453 | 'sy' => { |
d73e5302 |
454 | 'SYRIAC' => '17', |
455 | 'Syriac(?:[-_]|\s+)?Block' => '63', |
d9efae67 |
456 | }, |
c8b5a1e3 |
457 | 'ta' => { |
d73e5302 |
458 | 'TAMIL' => '24', |
459 | 'Tags' => '145', |
460 | 'Tamil(?:[-_]|\s+)?Block' => '70', |
d9efae67 |
461 | }, |
c8b5a1e3 |
462 | 'te' => { |
d73e5302 |
463 | 'TELUGU' => '25', |
464 | 'Telugu(?:[-_]|\s+)?Block' => '71', |
465 | 'Terminal(?:[-_]|\s+)?Punctuation' => '147', |
1ac13f9a |
466 | }, |
c8b5a1e3 |
467 | 'th' => { |
d73e5302 |
468 | 'THAANA' => '18', |
469 | 'THAI' => '29', |
470 | 'Thaana(?:[-_]|\s+)?Block' => '64', |
471 | 'Thai(?:[-_]|\s+)?Block' => '75', |
d9efae67 |
472 | }, |
c8b5a1e3 |
473 | 'ti' => { |
d73e5302 |
474 | 'TIBETAN' => '31', |
475 | 'Tibetan(?:[-_]|\s+)?Block' => '77', |
d9efae67 |
476 | }, |
c8b5a1e3 |
477 | 'un' => { |
d73e5302 |
478 | 'Unified(?:[-_]|\s+)?Canadian(?:[-_]|\s+)?Aboriginal(?:[-_]|\s+)?Syllabics' => '83', |
d9efae67 |
479 | }, |
c8b5a1e3 |
480 | 'up' => { |
d73e5302 |
481 | 'Uppercase' => '166', |
1ac13f9a |
482 | }, |
c8b5a1e3 |
483 | 'wh' => { |
d73e5302 |
484 | 'White(?:[-_]|\s+)?space' => '146', |
1ac13f9a |
485 | }, |
d9efae67 |
486 | 'yi' => { |
d73e5302 |
487 | 'YI' => '46', |
488 | 'Yi(?:[-_]|\s+)?Radicals' => '123', |
489 | 'Yi(?:[-_]|\s+)?Syllables' => '122', |
d9efae67 |
490 | }, |
9fdf68be |
491 | ); |