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!
4 # Built Mon Jan 14 15:52:42 2002.
7 ## Data in this file used by ../utf8_heavy.pl
10 ## Mapping from name to filename in ./In
14 ## Mappings from regex to filename in ./In/
17 'Alphabetic(?:[-_]|\s+)?Presentation(?:[-_]|\s+)?Forms' => 'Alphabet',
20 'Armenian' => 'Armenian',
23 'Arabic(?:[-_]|\s+)?Presentation(?:[-_]|\s+)?Forms(?:[-_]|\s+)?A' => 'ArabicPr',
24 'Arabic(?:[-_]|\s+)?Presentation(?:[-_]|\s+)?Forms(?:[-_]|\s+)?B' => 'ArabicP2',
27 'Basic(?:[-_]|\s+)?Latin' => 'BasicLat',
30 'Bengali' => 'Bengali',
33 'Block(?:[-_]|\s+)?Elements' => 'BlockEle',
36 'Bopomofo' => 'Bopomof2',
37 'Bopomofo(?:[-_]|\s+)?Extended' => 'Bopomofo',
38 'Box(?:[-_]|\s+)?Drawing' => 'BoxDrawi',
41 'Braille(?:[-_]|\s+)?Patterns' => 'BrailleP',
44 'Byzantine(?:[-_]|\s+)?Musical(?:[-_]|\s+)?Symbols' => 'Byzantin',
47 'Cherokee' => 'Cherokee',
50 'Cjk(?:[-_]|\s+)?Radicals(?:[-_]|\s+)?Supplement' => 'CjkRadic',
51 'Cjk(?:[-_]|\s+)?Symbols(?:[-_]|\s+)?And(?:[-_]|\s+)?Punctuation' => 'CjkSymbo',
52 'Cjk(?:[-_]|\s+)?Unified(?:[-_]|\s+)?Ideographs(?:[-_]|\s+)?Extension(?:[-_]|\s+)?A' => 'CjkUnif2',
53 'Cjk(?:[-_]|\s+)?Unified(?:[-_]|\s+)?Ideographs(?:[-_]|\s+)?Extension(?:[-_]|\s+)?B' => 'CjkUnif3',
54 'Cjk(?:[-_]|\s+)?Unified(?:[-_]|\s+)?Ideographs' => 'CjkUnifi',
55 'Cjk(?:[-_]|\s+)?Compatibility(?:[-_]|\s+)?Ideographs' => 'CjkComp2',
56 'Cjk(?:[-_]|\s+)?Compatibility(?:[-_]|\s+)?Ideographs(?:[-_]|\s+)?Supplement' => 'CjkComp4',
57 'Cjk(?:[-_]|\s+)?Compatibility' => 'CjkComp3',
58 'Cjk(?:[-_]|\s+)?Compatibility(?:[-_]|\s+)?Forms' => 'CjkCompa',
61 'Combining(?:[-_]|\s+)?Marks(?:[-_]|\s+)?For(?:[-_]|\s+)?Symbols' => 'Combini2',
62 'Combining(?:[-_]|\s+)?Half(?:[-_]|\s+)?Marks' => 'Combini3',
63 'Combining(?:[-_]|\s+)?Diacritical(?:[-_]|\s+)?Marks' => 'Combinin',
64 'Control(?:[-_]|\s+)?Pictures' => 'ControlP',
67 'Currency(?:[-_]|\s+)?Symbols' => 'Currency',
70 'Cyrillic' => 'Cyrillic',
73 'Devanagari' => 'Devanaga',
74 'Deseret' => 'Deseret',
77 'Dingbats' => 'Dingbats',
80 'Enclosed(?:[-_]|\s+)?Alphanumerics' => 'Enclose2',
81 'Enclosed(?:[-_]|\s+)?Cjk(?:[-_]|\s+)?Letters(?:[-_]|\s+)?And(?:[-_]|\s+)?Months' => 'Enclosed',
84 'Ethiopic' => 'Ethiopic',
87 'Geometric(?:[-_]|\s+)?Shapes' => 'Geometri',
88 'General(?:[-_]|\s+)?Punctuation' => 'GeneralP',
89 'Georgian' => 'Georgian',
95 'Greek(?:[-_]|\s+)?Extended' => 'GreekExt',
99 'Gurmukhi' => 'Gurmukhi',
100 'Gujarati' => 'Gujarati',
103 'Hangul(?:[-_]|\s+)?Compatibility(?:[-_]|\s+)?Jamo' => 'HangulCo',
104 'Hangul(?:[-_]|\s+)?Syllables' => 'HangulSy',
105 'Halfwidth(?:[-_]|\s+)?And(?:[-_]|\s+)?Fullwidth(?:[-_]|\s+)?Forms' => 'Halfwidt',
106 'Hangul(?:[-_]|\s+)?Jamo' => 'HangulJa',
109 'Hebrew' => 'Hebrew',
112 'High(?:[-_]|\s+)?Private(?:[-_]|\s+)?Use(?:[-_]|\s+)?Surrogates' => 'HighPriv',
113 'Hiragana' => 'Hiragana',
114 'High(?:[-_]|\s+)?Surrogates' => 'HighSurr',
117 'Ideographic(?:[-_]|\s+)?Description(?:[-_]|\s+)?Characters' => 'Ideograp',
120 'Ipa(?:[-_]|\s+)?Extensions' => 'IpaExten',
123 'Katakana' => 'Katakana',
124 'Kangxi(?:[-_]|\s+)?Radicals' => 'KangxiRa',
125 'Kannada' => 'Kannada',
126 'Kanbun' => 'Kanbun',
132 'Latin(?:[-_]|\s+)?Extended(?:[-_]|\s+)?Additional' => 'LatinExt',
133 'Latin(?:[-_]|\s+)?1(?:[-_]|\s+)?Supplement' => 'Latin1Su',
135 'Latin(?:[-_]|\s+)?Extended(?:[-_]|\s+)?A' => 'LatinEx2',
136 'Latin(?:[-_]|\s+)?Extended(?:[-_]|\s+)?B' => 'LatinEx3',
139 'Letterlike(?:[-_]|\s+)?Symbols' => 'Letterli',
142 'Low(?:[-_]|\s+)?Surrogates' => 'LowSurro',
145 'Mathematical(?:[-_]|\s+)?Operators' => 'Mathemat',
146 'Mathematical(?:[-_]|\s+)?Alphanumeric(?:[-_]|\s+)?Symbols' => 'Mathema2',
147 'Malayalam' => 'Malayala',
150 'Miscellaneous(?:[-_]|\s+)?Symbols' => 'Miscell2',
151 'Miscellaneous(?:[-_]|\s+)?Technical' => 'Miscella',
154 'Mongolian' => 'Mongolia',
157 'Musical(?:[-_]|\s+)?Symbols' => 'MusicalS',
160 'Myanmar' => 'Myanmar',
163 'Number(?:[-_]|\s+)?Forms' => 'NumberFo',
169 'Old(?:[-_]|\s+)?Italic' => 'OldItali',
172 'Optical(?:[-_]|\s+)?Character(?:[-_]|\s+)?Recognition' => 'OpticalC',
178 'Private(?:[-_]|\s+)?Use' => 'PrivateU',
184 'Sinhala' => 'Sinhala',
187 'Small(?:[-_]|\s+)?Form(?:[-_]|\s+)?Variants' => 'SmallFor',
190 'Specials' => 'Specials',
191 'Spacing(?:[-_]|\s+)?Modifier(?:[-_]|\s+)?Letters' => 'SpacingM',
194 'Superscripts(?:[-_]|\s+)?And(?:[-_]|\s+)?Subscripts' => 'Superscr',
197 'Syriac' => 'Syriac',
204 'Telugu' => 'Telugu',
207 'Thaana' => 'Thaana',
211 'Tibetan' => 'Tibetan',
214 'Unified(?:[-_]|\s+)?Canadian(?:[-_]|\s+)?Aboriginal(?:[-_]|\s+)?Syllabics' => 'UnifiedC',
217 'Yi(?:[-_]|\s+)?Radicals' => 'YiRadica',
218 'Yi(?:[-_]|\s+)?Syllables' => 'YiSyllab',