1 # !!!!!!! DO NOT EDIT THIS FILE !!!!!!!
2 # This file is built by mktables from e.g. Unicode.txt.
3 # Any changes made here will be lost!
7 'Alphabetic Presentation Forms' => '129',
10 'Arabic Block' => '62',
11 'Arabic Presentation Forms-A' => '130',
12 'Arabic Presentation Forms-B' => '134',
14 'Armenian Block' => '60',
16 'ASCII_Hex_Digit' => '152',
18 'Basic Latin' => '51',
20 'Bengali Block' => '66',
21 'Bidi_Control' => '159',
22 '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',
31 'Cherokee Block' => '82',
32 'CJK Compatibility' => '119',
33 'CJK Compatibility Forms' => '132',
34 'CJK Compatibility Ideographs' => '128',
35 'CJK Compatibility Ideographs Supplement' => '144',
36 'CJK Ideograph' => '1',
37 'CJK Ideograph Extension A' => '0',
38 'CJK Ideograph Extension B' => '7',
39 'CJK Radicals Supplement' => '108',
40 'CJK Symbols and Punctuation' => '111',
41 'CJK Unified Ideographs' => '121',
42 'CJK Unified Ideographs Extension A' => '120',
43 'CJK Unified Ideographs Extension B' => '143',
44 'Combining Diacritical Marks' => '57',
45 'Combining Half Marks' => '131',
46 'Combining Marks for Symbols' => '93',
48 'Control Pictures' => '99',
49 'Currency Symbols' => '92',
51 'Cyrillic Block' => '59',
54 'Deseret Block' => '139',
56 'Devanagari Block' => '65',
59 'Enclosed Alphanumerics' => '101',
60 'Enclosed CJK Letters and Months' => '118',
62 'Ethiopic Block' => '81',
64 'General Punctuation' => '90',
65 'Geometric Shapes' => '104',
67 'Georgian Block' => '79',
69 'Gothic Block' => '138',
71 'Greek Block' => '58',
72 'Greek Extended' => '89',
74 'Gujarati Block' => '68',
76 'Gurmukhi Block' => '67',
77 'Halfwidth and Fullwidth Forms' => '136',
80 'Hangul Compatibility Jamo' => '115',
81 'Hangul Jamo' => '80',
82 'Hangul Syllable' => '2',
83 'Hangul Syllables' => '124',
85 'Hebrew Block' => '61',
87 'High Private Use Surrogates' => '126',
88 'High Surrogates' => '125',
90 'Hiragana Block' => '112',
92 'ID_Continue' => '170',
94 'Ideographic' => '161',
95 'Ideographic Description Characters' => '110',
97 'IPA Extensions' => '55',
98 'Join_Control' => '158',
100 'Kangxi Radicals' => '109',
102 'Kannada Block' => '72',
104 'Katakana Block' => '113',
106 'Khmer Block' => '86',
107 'Lampersand' => '168',
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',
120 'Malayalam Block' => '73',
122 'Mathematical Alphanumeric Symbols' => '142',
123 'Mathematical Operators' => '97',
124 'Miscellaneous Symbols' => '105',
125 'Miscellaneous Technical' => '98',
127 'Mongolian Block' => '87',
128 'Musical Symbols' => '141',
130 'Myanmar Block' => '78',
131 'Non Private Use High Surrogate' => '3',
132 'Noncharacter_Code_Point' => '162',
133 'Number Forms' => '95',
135 'Ogham Block' => '84',
136 'Old Italic Block' => '137',
137 'OLD-ITALIC' => '47',
138 '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',
151 'Runic Block' => '85',
153 'Sinhala Block' => '74',
154 'Small Form Variants' => '133',
155 'Spacing Modifier Letters' => '56',
157 'Superscripts and Subscripts' => '91',
159 'Syriac Block' => '63',
162 'Tamil Block' => '70',
164 'Telugu Block' => '71',
165 'Terminal_Punctuation' => '147',
167 'Thaana Block' => '64',
169 'Thai Block' => '75',
171 'Tibetan Block' => '77',
172 'Unified Canadian Aboriginal Syllabics' => '83',
173 'Uppercase' => '166',
174 'White_space' => '146',
176 'Yi Radicals' => '123',
177 'Yi Syllables' => '122',
182 'Alphabetic' => '164',
183 'Alphabetic(?:[-_]|\s+)?Presentation(?:[-_]|\s+)?Forms' => '129',
190 'Arabic(?:[-_]|\s+)?Block' => '62',
191 'Arabic(?:[-_]|\s+)?Presentation(?:[-_]|\s+)?Forms(?:[-_]|\s+)?A' => '130',
192 'Arabic(?:[-_]|\s+)?Presentation(?:[-_]|\s+)?Forms(?:[-_]|\s+)?B' => '134',
194 'Armenian(?:[-_]|\s+)?Block' => '60',
198 'ASCII(?:[-_]|\s+)?Hex(?:[-_]|\s+)?Digit' => '152',
202 'Basic(?:[-_]|\s+)?Latin' => '51',
206 'Bengali(?:[-_]|\s+)?Block' => '66',
209 'Bidi(?:[-_]|\s+)?Control' => '159',
212 'Block(?:[-_]|\s+)?Elements' => '103',
216 'Bopomofo(?:[-_]|\s+)?Block' => '114',
217 'Bopomofo(?:[-_]|\s+)?Extended' => '117',
218 'Box(?:[-_]|\s+)?Drawing' => '102',
221 'Braille(?:[-_]|\s+)?Patterns' => '107',
224 'Byzantine(?:[-_]|\s+)?Musical(?:[-_]|\s+)?Symbols' => '140',
227 'CANADIAN(?:[-_]|\s+)?ABORIGINAL' => '37',
231 'Cherokee(?:[-_]|\s+)?Block' => '82',
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',
248 'Combining(?:[-_]|\s+)?Diacritical(?:[-_]|\s+)?Marks' => '57',
249 'Combining(?:[-_]|\s+)?Half(?:[-_]|\s+)?Marks' => '131',
250 'Combining(?:[-_]|\s+)?Marks(?:[-_]|\s+)?for(?:[-_]|\s+)?Symbols' => '93',
252 'Control(?:[-_]|\s+)?Pictures' => '99',
255 'Currency(?:[-_]|\s+)?Symbols' => '92',
259 'Cyrillic(?:[-_]|\s+)?Block' => '59',
266 'Deseret(?:[-_]|\s+)?Block' => '139',
267 'DEVANAGARI' => '19',
268 'Devanagari(?:[-_]|\s+)?Block' => '65',
271 'Diacritic' => '154',
275 'Enclosed(?:[-_]|\s+)?Alphanumerics' => '101',
276 'Enclosed(?:[-_]|\s+)?CJK(?:[-_]|\s+)?Letters(?:[-_]|\s+)?and(?:[-_]|\s+)?Months' => '118',
280 'Ethiopic(?:[-_]|\s+)?Block' => '81',
286 'General(?:[-_]|\s+)?Punctuation' => '90',
287 'Geometric(?:[-_]|\s+)?Shapes' => '104',
289 'Georgian(?:[-_]|\s+)?Block' => '79',
293 'Gothic(?:[-_]|\s+)?Block' => '138',
297 'Greek(?:[-_]|\s+)?Block' => '58',
298 'Greek(?:[-_]|\s+)?Extended' => '89',
302 'Gujarati(?:[-_]|\s+)?Block' => '68',
304 'Gurmukhi(?:[-_]|\s+)?Block' => '67',
307 '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',
317 'Hebrew(?:[-_]|\s+)?Block' => '61',
318 'Hex(?:[-_]|\s+)?Digit' => '153',
321 'High(?:[-_]|\s+)?Private(?:[-_]|\s+)?Use(?:[-_]|\s+)?Surrogates' => '126',
322 'High(?:[-_]|\s+)?Surrogates' => '125',
324 'Hiragana(?:[-_]|\s+)?Block' => '112',
330 'ID(?:[-_]|\s+)?Continue' => '170',
331 'ID(?:[-_]|\s+)?Start' => '169',
332 'Ideographic' => '161',
333 'Ideographic(?:[-_]|\s+)?Description(?:[-_]|\s+)?Characters' => '110',
339 'IPA(?:[-_]|\s+)?Extensions' => '55',
342 'Join(?:[-_]|\s+)?Control' => '158',
346 'Kangxi(?:[-_]|\s+)?Radicals' => '109',
348 'Kannada(?:[-_]|\s+)?Block' => '72',
350 'Katakana(?:[-_]|\s+)?Block' => '113',
354 'Khmer(?:[-_]|\s+)?Block' => '86',
357 'Lampersand' => '168',
359 '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',
367 'Letterlike(?:[-_]|\s+)?Symbols' => '94',
370 'Low(?:[-_]|\s+)?Surrogate' => '5',
371 'Low(?:[-_]|\s+)?Surrogates' => '127',
372 'Lowercase' => '165',
376 'Malayalam(?:[-_]|\s+)?Block' => '73',
378 'Mathematical(?:[-_]|\s+)?Alphanumeric(?:[-_]|\s+)?Symbols' => '142',
379 'Mathematical(?:[-_]|\s+)?Operators' => '97',
382 'Miscellaneous(?:[-_]|\s+)?Symbols' => '105',
383 'Miscellaneous(?:[-_]|\s+)?Technical' => '98',
387 'Mongolian(?:[-_]|\s+)?Block' => '87',
390 'Musical(?:[-_]|\s+)?Symbols' => '141',
394 'Myanmar(?:[-_]|\s+)?Block' => '78',
397 'Non(?:[-_]|\s+)?Private(?:[-_]|\s+)?Use(?:[-_]|\s+)?High(?:[-_]|\s+)?Surrogate' => '3',
398 'Noncharacter(?:[-_]|\s+)?Code(?:[-_]|\s+)?Point' => '162',
401 'Number(?:[-_]|\s+)?Forms' => '95',
405 'Ogham(?:[-_]|\s+)?Block' => '84',
408 'Old(?:[-_]|\s+)?Italic(?:[-_]|\s+)?Block' => '137',
409 'OLD(?:[-_]|\s+)?ITALIC' => '47',
412 'Optical(?:[-_]|\s+)?Character(?:[-_]|\s+)?Recognition' => '100',
416 'Oriya(?:[-_]|\s+)?Block' => '69',
419 'Other(?:[-_]|\s+)?Alphabetic' => '157',
420 'Other(?:[-_]|\s+)?Lowercase' => '156',
421 'Other(?:[-_]|\s+)?Math' => '149',
422 'Other(?:[-_]|\s+)?Uppercase' => '160',
425 'Plane(?:[-_]|\s+)?15(?:[-_]|\s+)?Private(?:[-_]|\s+)?Use' => '8',
426 'Plane(?:[-_]|\s+)?16(?:[-_]|\s+)?Private(?:[-_]|\s+)?Use' => '9',
429 'Private(?:[-_]|\s+)?Use' => '6',
430 'Private(?:[-_]|\s+)?Use(?:[-_]|\s+)?High(?:[-_]|\s+)?Surrogate' => '4',
433 'Quotation(?:[-_]|\s+)?Mark' => '148',
437 'Runic(?:[-_]|\s+)?Block' => '85',
441 'Sinhala(?:[-_]|\s+)?Block' => '74',
444 'Small(?:[-_]|\s+)?Form(?:[-_]|\s+)?Variants' => '133',
447 'Spacing(?:[-_]|\s+)?Modifier(?:[-_]|\s+)?Letters' => '56',
451 'Superscripts(?:[-_]|\s+)?and(?:[-_]|\s+)?Subscripts' => '91',
455 'Syriac(?:[-_]|\s+)?Block' => '63',
460 'Tamil(?:[-_]|\s+)?Block' => '70',
464 'Telugu(?:[-_]|\s+)?Block' => '71',
465 'Terminal(?:[-_]|\s+)?Punctuation' => '147',
469 'Thaana(?:[-_]|\s+)?Block' => '64',
471 'Thai(?:[-_]|\s+)?Block' => '75',
475 'Tibetan(?:[-_]|\s+)?Block' => '77',
478 'Unified(?:[-_]|\s+)?Canadian(?:[-_]|\s+)?Aboriginal(?:[-_]|\s+)?Syllabics' => '83',
481 'Uppercase' => '166',
484 'White(?:[-_]|\s+)?space' => '146',
488 'Yi(?:[-_]|\s+)?Radicals' => '123',
489 'Yi(?:[-_]|\s+)?Syllables' => '122',
522 37 => 'CANADIAN-ABORIGINAL',
540 52 => 'Latin-1 Supplement',
541 53 => 'Latin Extended-A',
542 54 => 'Latin Extended-B',
543 55 => 'IPA Extensions',
544 56 => 'Spacing Modifier Letters',
545 57 => 'Combining Diacritical Marks',
571 83 => 'Unified Canadian Aboriginal Syllabics',
576 88 => 'Latin Extended Additional',
577 89 => 'Greek Extended',
578 90 => 'General Punctuation',
579 91 => 'Superscripts and Subscripts',
580 92 => 'Currency Symbols',
581 93 => 'Combining Marks for Symbols',
582 94 => 'Letterlike Symbols',
583 95 => 'Number Forms',
585 97 => 'Mathematical Operators',
586 98 => 'Miscellaneous Technical',
587 99 => 'Control Pictures',
588 100 => 'Optical Character Recognition',
589 101 => 'Enclosed Alphanumerics',
590 102 => 'Box Drawing',
591 103 => 'Block Elements',
592 104 => 'Geometric Shapes',
593 105 => 'Miscellaneous Symbols',
595 107 => 'Braille Patterns',
596 108 => 'CJK Radicals Supplement',
597 109 => 'Kangxi Radicals',
598 110 => 'Ideographic Description Characters',
599 111 => 'CJK Symbols and Punctuation',
603 115 => 'Hangul Compatibility Jamo',
605 117 => 'Bopomofo Extended',
606 118 => 'Enclosed CJK Letters and Months',
607 119 => 'CJK Compatibility',
608 120 => 'CJK Unified Ideographs Extension A',
609 121 => 'CJK Unified Ideographs',
610 122 => 'Yi Syllables',
611 123 => 'Yi Radicals',
612 124 => 'Hangul Syllables',
613 125 => 'High Surrogates',
614 126 => 'High Private Use Surrogates',
615 127 => 'Low Surrogates',
616 128 => 'CJK Compatibility Ideographs',
617 129 => 'Alphabetic Presentation Forms',
618 130 => 'Arabic Presentation Forms-A',
619 131 => 'Combining Half Marks',
620 132 => 'CJK Compatibility Forms',
621 133 => 'Small Form Variants',
622 134 => 'Arabic Presentation Forms-B',
624 136 => 'Halfwidth and Fullwidth Forms',
628 140 => 'Byzantine Musical Symbols',
629 141 => 'Musical Symbols',
630 142 => 'Mathematical Alphanumeric Symbols',
631 143 => 'CJK Unified Ideographs Extension B',
632 144 => 'CJK Compatibility Ideographs Supplement',