1 # !!!!!!! DO NOT EDIT THIS FILE !!!!!!!
2 # This file is built by mktables.PL from e.g. Unicode.txt.
3 # Any changes made here will be lost!
31 'CANADIAN-ABORIGINAL' => 26,
46 'Latin-1 Supplement' => 41,
47 'Latin Extended-A' => 42,
48 'Latin Extended-B' => 43,
49 'IPA Extensions' => 44,
50 'Spacing Modifier Letters' => 45,
51 'Combining Diacritical Marks' => 46,
53 'Cyrillic Block' => 48,
54 'Armenian Block' => 49,
59 'Devanagari Block' => 54,
60 'Bengali Block' => 55,
61 'Gurmukhi Block' => 56,
62 'Gujarati Block' => 57,
66 'Kannada Block' => 61,
67 'Malayalam Block' => 62,
68 'Sinhala Block' => 63,
71 'Tibetan Block' => 66,
72 'Myanmar Block' => 67,
73 'Georgian Block' => 68,
75 'Ethiopic Block' => 70,
76 'Cherokee Block' => 71,
77 'Unified Canadian Aboriginal Syllabics' => 72,
81 'Mongolian Block' => 76,
82 'Latin Extended Additional' => 77,
83 'Greek Extended' => 78,
84 'General Punctuation' => 79,
85 'Superscripts and Subscripts' => 80,
86 'Currency Symbols' => 81,
87 'Combining Marks for Symbols' => 82,
88 'Letterlike Symbols' => 83,
91 'Mathematical Operators' => 86,
92 'Miscellaneous Technical' => 87,
93 'Control Pictures' => 88,
94 'Optical Character Recognition' => 89,
95 'Enclosed Alphanumerics' => 90,
97 'Block Elements' => 92,
98 'Geometric Shapes' => 93,
99 'Miscellaneous Symbols' => 94,
101 'Braille Patterns' => 96,
102 'CJK Radicals Supplement' => 97,
103 'Kangxi Radicals' => 98,
104 'Ideographic Description Characters' => 99,
105 'CJK Symbols and Punctuation' => 100,
106 'Hiragana Block' => 101,
107 'Katakana Block' => 102,
108 'Bopomofo Block' => 103,
109 'Hangul Compatibility Jamo' => 104,
111 'Bopomofo Extended' => 106,
112 'Enclosed CJK Letters and Months' => 107,
113 'CJK Compatibility' => 108,
114 'CJK Unified Ideographs Extension A' => 109,
115 'CJK Unified Ideographs' => 110,
116 'Yi Syllables' => 111,
117 'Yi Radicals' => 112,
118 'Hangul Syllables' => 113,
119 'High Surrogates' => 114,
120 'High Private Use Surrogates' => 115,
121 'Low Surrogates' => 116,
122 'Private Use' => 117,
123 'CJK Compatibility Ideographs' => 118,
124 'Alphabetic Presentation Forms' => 119,
125 'Arabic Presentation Forms-A' => 120,
126 'Combining Half Marks' => 121,
127 'CJK Compatibility Forms' => 122,
128 'Small Form Variants' => 123,
129 'Arabic Presentation Forms-B' => 124,
131 'Halfwidth and Fullwidth Forms' => 126,
133 'Gothic Block' => 128,
134 'Deseret Block' => 129,
135 'Byzantine Musical Symbols' => 130,
136 'Musical Symbols' => 131,
137 'Mathematical Alphanumeric Symbols' => 132,
138 'CJK Unified Ideographs Extension B' => 133,
139 'CJK Compatibility Ideographs Supplement' => 134,
145 'Alphabetic(?:[-_]|\s+)?Presentation(?:[-_]|\s+)?Forms' => 'Alphabetic Presentation Forms',
148 'ARABIC' => 'ARABIC',
149 'Arabic(?:[-_]|\s+)?Block' => 'Arabic Block',
150 'Arabic(?:[-_]|\s+)?Presentation(?:[-_]|\s+)?Forms(?:[-_]|\s+)?A' => 'Arabic Presentation Forms-A',
151 'Arabic(?:[-_]|\s+)?Presentation(?:[-_]|\s+)?Forms(?:[-_]|\s+)?B' => 'Arabic Presentation Forms-B',
154 'ARMENIAN' => 'ARMENIAN',
155 'Armenian(?:[-_]|\s+)?Block' => 'Armenian Block',
158 'Arrows' => 'Arrows',
161 'Basic(?:[-_]|\s+)?Latin' => 'Basic Latin',
164 'BENGALI' => 'BENGALI',
165 'Bengali(?:[-_]|\s+)?Block' => 'Bengali Block',
168 'Block(?:[-_]|\s+)?Elements' => 'Block Elements',
171 'BOPOMOFO' => 'BOPOMOFO',
172 'Bopomofo(?:[-_]|\s+)?Block' => 'Bopomofo Block',
173 'Bopomofo(?:[-_]|\s+)?Extended' => 'Bopomofo Extended',
176 'Box(?:[-_]|\s+)?Drawing' => 'Box Drawing',
179 'Braille(?:[-_]|\s+)?Patterns' => 'Braille Patterns',
182 'Byzantine(?:[-_]|\s+)?Musical(?:[-_]|\s+)?Symbols' => 'Byzantine Musical Symbols',
185 'CANADIAN(?:[-_]|\s+)?ABORIGINAL' => 'CANADIAN-ABORIGINAL',
188 'CHEROKEE' => 'CHEROKEE',
189 'Cherokee(?:[-_]|\s+)?Block' => 'Cherokee Block',
192 'CJK(?:[-_]|\s+)?Radicals(?:[-_]|\s+)?Supplement' => 'CJK Radicals Supplement',
193 'CJK(?:[-_]|\s+)?Symbols(?:[-_]|\s+)?and(?:[-_]|\s+)?Punctuation' => 'CJK Symbols and Punctuation',
194 'CJK(?:[-_]|\s+)?Compatibility' => 'CJK Compatibility',
195 'CJK(?:[-_]|\s+)?Unified(?:[-_]|\s+)?Ideographs(?:[-_]|\s+)?Extension(?:[-_]|\s+)?A' => 'CJK Unified Ideographs Extension A',
196 'CJK(?:[-_]|\s+)?Unified(?:[-_]|\s+)?Ideographs' => 'CJK Unified Ideographs',
197 'CJK(?:[-_]|\s+)?Compatibility(?:[-_]|\s+)?Ideographs' => 'CJK Compatibility Ideographs',
198 'CJK(?:[-_]|\s+)?Compatibility(?:[-_]|\s+)?Forms' => 'CJK Compatibility Forms',
199 'CJK(?:[-_]|\s+)?Unified(?:[-_]|\s+)?Ideographs(?:[-_]|\s+)?Extension(?:[-_]|\s+)?B' => 'CJK Unified Ideographs Extension B',
200 'CJK(?:[-_]|\s+)?Compatibility(?:[-_]|\s+)?Ideographs(?:[-_]|\s+)?Supplement' => 'CJK Compatibility Ideographs Supplement',
203 'Combining(?:[-_]|\s+)?Diacritical(?:[-_]|\s+)?Marks' => 'Combining Diacritical Marks',
204 'Combining(?:[-_]|\s+)?Marks(?:[-_]|\s+)?for(?:[-_]|\s+)?Symbols' => 'Combining Marks for Symbols',
205 'Combining(?:[-_]|\s+)?Half(?:[-_]|\s+)?Marks' => 'Combining Half Marks',
206 'Common' => 'Common',
209 'Control(?:[-_]|\s+)?Pictures' => 'Control Pictures',
212 'Currency(?:[-_]|\s+)?Symbols' => 'Currency Symbols',
215 'CYRILLIC' => 'CYRILLIC',
216 'Cyrillic(?:[-_]|\s+)?Block' => 'Cyrillic Block',
219 'DESERET' => 'DESERET',
220 'Deseret(?:[-_]|\s+)?Block' => 'Deseret Block',
223 'DEVANAGARI' => 'DEVANAGARI',
224 'Devanagari(?:[-_]|\s+)?Block' => 'Devanagari Block',
227 'Dingbats' => 'Dingbats',
230 'Enclosed(?:[-_]|\s+)?Alphanumerics' => 'Enclosed Alphanumerics',
231 'Enclosed(?:[-_]|\s+)?CJK(?:[-_]|\s+)?Letters(?:[-_]|\s+)?and(?:[-_]|\s+)?Months' => 'Enclosed CJK Letters and Months',
234 'ETHIOPIC' => 'ETHIOPIC',
235 'Ethiopic(?:[-_]|\s+)?Block' => 'Ethiopic Block',
238 'General(?:[-_]|\s+)?Punctuation' => 'General Punctuation',
241 'GEORGIAN' => 'GEORGIAN',
242 'Georgian(?:[-_]|\s+)?Block' => 'Georgian Block',
243 'Geometric(?:[-_]|\s+)?Shapes' => 'Geometric Shapes',
246 'GOTHIC' => 'GOTHIC',
247 'Gothic(?:[-_]|\s+)?Block' => 'Gothic Block',
251 'Greek(?:[-_]|\s+)?Block' => 'Greek Block',
252 'Greek(?:[-_]|\s+)?Extended' => 'Greek Extended',
255 'GUJARATI' => 'GUJARATI',
256 'Gujarati(?:[-_]|\s+)?Block' => 'Gujarati Block',
259 'GURMUKHI' => 'GURMUKHI',
260 'Gurmukhi(?:[-_]|\s+)?Block' => 'Gurmukhi Block',
263 'Halfwidth(?:[-_]|\s+)?and(?:[-_]|\s+)?Fullwidth(?:[-_]|\s+)?Forms' => 'Halfwidth and Fullwidth Forms',
266 'HANGUL' => 'HANGUL',
268 'Hangul(?:[-_]|\s+)?Jamo' => 'Hangul Jamo',
269 'Hangul(?:[-_]|\s+)?Compatibility(?:[-_]|\s+)?Jamo' => 'Hangul Compatibility Jamo',
270 'Hangul(?:[-_]|\s+)?Syllables' => 'Hangul Syllables',
273 'HEBREW' => 'HEBREW',
274 'Hebrew(?:[-_]|\s+)?Block' => 'Hebrew Block',
277 'High(?:[-_]|\s+)?Surrogates' => 'High Surrogates',
278 'High(?:[-_]|\s+)?Private(?:[-_]|\s+)?Use(?:[-_]|\s+)?Surrogates' => 'High Private Use Surrogates',
281 'HIRAGANA' => 'HIRAGANA',
282 'Hiragana(?:[-_]|\s+)?Block' => 'Hiragana Block',
285 'Ideographic(?:[-_]|\s+)?Description(?:[-_]|\s+)?Characters' => 'Ideographic Description Characters',
288 'INHERITED' => 'INHERITED',
291 'IPA(?:[-_]|\s+)?Extensions' => 'IPA Extensions',
294 'KANNADA' => 'KANNADA',
295 'Kannada(?:[-_]|\s+)?Block' => 'Kannada Block',
296 'Kangxi(?:[-_]|\s+)?Radicals' => 'Kangxi Radicals',
297 'Kanbun' => 'Kanbun',
300 'KATAKANA' => 'KATAKANA',
301 'Katakana(?:[-_]|\s+)?Block' => 'Katakana Block',
305 'Khmer(?:[-_]|\s+)?Block' => 'Khmer Block',
309 'Lao(?:[-_]|\s+)?Block' => 'Lao Block',
313 'Latin(?:[-_]|\s+)?1(?:[-_]|\s+)?Supplement' => 'Latin-1 Supplement',
314 'Latin(?:[-_]|\s+)?Extended(?:[-_]|\s+)?A' => 'Latin Extended-A',
315 'Latin(?:[-_]|\s+)?Extended(?:[-_]|\s+)?B' => 'Latin Extended-B',
316 'Latin(?:[-_]|\s+)?Extended(?:[-_]|\s+)?Additional' => 'Latin Extended Additional',
319 'Letterlike(?:[-_]|\s+)?Symbols' => 'Letterlike Symbols',
322 'Low(?:[-_]|\s+)?Surrogates' => 'Low Surrogates',
325 'MALAYALAM' => 'MALAYALAM',
326 'Malayalam(?:[-_]|\s+)?Block' => 'Malayalam Block',
329 'Mathematical(?:[-_]|\s+)?Operators' => 'Mathematical Operators',
330 'Mathematical(?:[-_]|\s+)?Alphanumeric(?:[-_]|\s+)?Symbols' => 'Mathematical Alphanumeric Symbols',
333 'Miscellaneous(?:[-_]|\s+)?Technical' => 'Miscellaneous Technical',
334 'Miscellaneous(?:[-_]|\s+)?Symbols' => 'Miscellaneous Symbols',
337 'MONGOLIAN' => 'MONGOLIAN',
338 'Mongolian(?:[-_]|\s+)?Block' => 'Mongolian Block',
341 'Musical(?:[-_]|\s+)?Symbols' => 'Musical Symbols',
344 'MYANMAR' => 'MYANMAR',
345 'Myanmar(?:[-_]|\s+)?Block' => 'Myanmar Block',
348 'Number(?:[-_]|\s+)?Forms' => 'Number Forms',
352 'Ogham(?:[-_]|\s+)?Block' => 'Ogham Block',
355 'OLD(?:[-_]|\s+)?ITALIC' => 'OLD-ITALIC',
356 'Old(?:[-_]|\s+)?Italic' => 'Old Italic',
359 'Optical(?:[-_]|\s+)?Character(?:[-_]|\s+)?Recognition' => 'Optical Character Recognition',
363 'Oriya(?:[-_]|\s+)?Block' => 'Oriya Block',
366 'Private(?:[-_]|\s+)?Use' => 'Private Use',
370 'Runic(?:[-_]|\s+)?Block' => 'Runic Block',
373 'SINHALA' => 'SINHALA',
374 'Sinhala(?:[-_]|\s+)?Block' => 'Sinhala Block',
377 'Small(?:[-_]|\s+)?Form(?:[-_]|\s+)?Variants' => 'Small Form Variants',
380 'Spacing(?:[-_]|\s+)?Modifier(?:[-_]|\s+)?Letters' => 'Spacing Modifier Letters',
383 'Specials' => 'Specials',
386 'Superscripts(?:[-_]|\s+)?and(?:[-_]|\s+)?Subscripts' => 'Superscripts and Subscripts',
389 'SYRIAC' => 'SYRIAC',
390 'Syriac(?:[-_]|\s+)?Block' => 'Syriac Block',
397 'Tamil(?:[-_]|\s+)?Block' => 'Tamil Block',
400 'TELUGU' => 'TELUGU',
401 'Telugu(?:[-_]|\s+)?Block' => 'Telugu Block',
404 'THAANA' => 'THAANA',
406 'Thaana(?:[-_]|\s+)?Block' => 'Thaana Block',
407 'Thai(?:[-_]|\s+)?Block' => 'Thai Block',
410 'TIBETAN' => 'TIBETAN',
411 'Tibetan(?:[-_]|\s+)?Block' => 'Tibetan Block',
414 'Unified(?:[-_]|\s+)?Canadian(?:[-_]|\s+)?Aboriginal(?:[-_]|\s+)?Syllabics' => 'Unified Canadian Aboriginal Syllabics',
420 'Yi(?:[-_]|\s+)?Syllables' => 'Yi Syllables',
421 'Yi(?:[-_]|\s+)?Radicals' => 'Yi Radicals',