# !!!!!!! DO NOT EDIT THIS FILE !!!!!!!
# This file is built by mktables from e.g. Unicode.txt.
# Any changes made here will be lost!
-%utf8::In =
-(
-'All' => '173',
-'Alphabetic' => '165',
-'Alphabetic Presentation Forms' => '129',
-'Any' => '172',
-'ARABIC' => '16',
-'Arabic Block' => '62',
-'Arabic Presentation Forms-A' => '130',
-'Arabic Presentation Forms-B' => '134',
-'ARMENIAN' => '14',
-'Armenian Block' => '60',
-'Arrows' => '96',
-'ASCII_Hex_Digit' => '152',
-'Assigned' => '163',
-'Basic Latin' => '51',
-'BENGALI' => '20',
-'Bengali Block' => '66',
-'Bidi_Control' => '159',
-'Block Elements' => '103',
-'BOPOMOFO' => '45',
-'Bopomofo Block' => '114',
-'Bopomofo Extended' => '117',
-'Box Drawing' => '102',
-'Braille Patterns' => '107',
-'Byzantine Musical Symbols' => '140',
-'CANADIAN-ABORIGINAL' => '37',
-'CHEROKEE' => '36',
-'Cherokee Block' => '82',
-'CJK Compatibility' => '119',
-'CJK Compatibility Forms' => '132',
-'CJK Compatibility Ideographs' => '128',
-'CJK Compatibility Ideographs Supplement' => '144',
-'CJK Ideograph' => '1',
-'CJK Ideograph Extension A' => '0',
-'CJK Ideograph Extension B' => '7',
-'CJK Radicals Supplement' => '108',
-'CJK Symbols and Punctuation' => '111',
-'CJK Unified Ideographs' => '121',
-'CJK Unified Ideographs Extension A' => '120',
-'CJK Unified Ideographs Extension B' => '143',
-'Combining Diacritical Marks' => '57',
-'Combining Half Marks' => '131',
-'Combining Marks for Symbols' => '93',
-'Common' => '50',
-'Control Pictures' => '99',
-'Currency Symbols' => '92',
-'CYRILLIC' => '13',
-'Cyrillic Block' => '59',
-'Dash' => '151',
-'DESERET' => '49',
-'Deseret Block' => '139',
-'DEVANAGARI' => '19',
-'Devanagari Block' => '65',
-'Diacritic' => '154',
-'Dingbats' => '106',
-'Enclosed Alphanumerics' => '101',
-'Enclosed CJK Letters and Months' => '118',
-'ETHIOPIC' => '35',
-'Ethiopic Block' => '81',
-'Extender' => '155',
-'General Punctuation' => '90',
-'Geometric Shapes' => '104',
-'GEORGIAN' => '33',
-'Georgian Block' => '79',
-'GOTHIC' => '48',
-'Gothic Block' => '138',
-'GREEK' => '11',
-'Greek Block' => '58',
-'Greek Extended' => '89',
-'GUJARATI' => '22',
-'Gujarati Block' => '68',
-'GURMUKHI' => '21',
-'Gurmukhi Block' => '67',
-'Halfwidth and Fullwidth Forms' => '136',
-'HAN' => '42',
-'HANGUL' => '34',
-'Hangul Compatibility Jamo' => '115',
-'Hangul Jamo' => '80',
-'Hangul Syllable' => '2',
-'Hangul Syllables' => '124',
-'HEBREW' => '15',
-'Hebrew Block' => '61',
-'Hex_Digit' => '153',
-'High Private Use Surrogates' => '126',
-'High Surrogates' => '125',
-'HIRAGANA' => '43',
-'Hiragana Block' => '112',
-'Hyphen' => '150',
-'ID_Continue' => '171',
-'ID_Start' => '170',
-'Ideographic' => '161',
-'Ideographic Description Characters' => '110',
-'INHERITED' => '12',
-'IPA Extensions' => '55',
-'Join_Control' => '158',
-'Kanbun' => '116',
-'Kangxi Radicals' => '109',
-'KANNADA' => '26',
-'Kannada Block' => '72',
-'KATAKANA' => '44',
-'Katakana Block' => '113',
-'KHMER' => '40',
-'Khmer Block' => '86',
-'Lampersand' => '169',
-'LAO' => '30',
-'Lao Block' => '76',
-'LATIN' => '10',
-'Latin Extended Additional' => '88',
-'Latin Extended-A' => '53',
-'Latin Extended-B' => '54',
-'Latin-1 Supplement' => '52',
-'Letterlike Symbols' => '94',
-'Low Surrogate' => '5',
-'Low Surrogates' => '127',
-'Lowercase' => '166',
-'MALAYALAM' => '27',
-'Malayalam Block' => '73',
-'Math' => '168',
-'Mathematical Alphanumeric Symbols' => '142',
-'Mathematical Operators' => '97',
-'Miscellaneous Symbols' => '105',
-'Miscellaneous Technical' => '98',
-'MONGOLIAN' => '41',
-'Mongolian Block' => '87',
-'Musical Symbols' => '141',
-'MYANMAR' => '32',
-'Myanmar Block' => '78',
-'Non Private Use High Surrogate' => '3',
-'Noncharacter_Code_Point' => '162',
-'Number Forms' => '95',
-'OGHAM' => '38',
-'Ogham Block' => '84',
-'Old Italic Block' => '137',
-'OLD-ITALIC' => '47',
-'Optical Character Recognition' => '100',
-'ORIYA' => '23',
-'Oriya Block' => '69',
-'Other_Alphabetic' => '157',
-'Other_Lowercase' => '156',
-'Other_Math' => '149',
-'Other_Uppercase' => '160',
-'Plane 15 Private Use' => '8',
-'Plane 16 Private Use' => '9',
-'Private Use' => '6',
-'Private Use High Surrogate' => '4',
-'Quotation_Mark' => '148',
-'RUNIC' => '39',
-'Runic Block' => '85',
-'SINHALA' => '28',
-'Sinhala Block' => '74',
-'Small Form Variants' => '133',
-'Spacing Modifier Letters' => '56',
-'Specials' => '135',
-'Superscripts and Subscripts' => '91',
-'SYRIAC' => '17',
-'Syriac Block' => '63',
-'Tags' => '145',
-'TAMIL' => '24',
-'Tamil Block' => '70',
-'TELUGU' => '25',
-'Telugu Block' => '71',
-'Terminal_Punctuation' => '147',
-'THAANA' => '18',
-'Thaana Block' => '64',
-'THAI' => '29',
-'Thai Block' => '75',
-'TIBETAN' => '31',
-'Tibetan Block' => '77',
-'Unassigned' => '164',
-'Unified Canadian Aboriginal Syllabics' => '83',
-'Uppercase' => '167',
-'White_space' => '146',
-'YI' => '46',
-'Yi Radicals' => '123',
-'Yi Syllables' => '122',
-);
-%utf8::InPat =
-(
-'al' => {
- 'All' => '173',
- 'Alphabetic' => '165',
- 'Alphabetic(?:[-_]|\s+)?Presentation(?:[-_]|\s+)?Forms' => '129',
-},
-'an' => {
- 'Any' => '172',
-},
-'ar' => {
- 'ARABIC' => '16',
- 'Arabic(?:[-_]|\s+)?Block' => '62',
- 'Arabic(?:[-_]|\s+)?Presentation(?:[-_]|\s+)?Forms(?:[-_]|\s+)?A' => '130',
- 'Arabic(?:[-_]|\s+)?Presentation(?:[-_]|\s+)?Forms(?:[-_]|\s+)?B' => '134',
- 'ARMENIAN' => '14',
- 'Armenian(?:[-_]|\s+)?Block' => '60',
- 'Arrows' => '96',
-},
-'as' => {
- 'ASCII(?:[-_]|\s+)?Hex(?:[-_]|\s+)?Digit' => '152',
- 'Assigned' => '163',
-},
-'ba' => {
- 'Basic(?:[-_]|\s+)?Latin' => '51',
-},
-'be' => {
- 'BENGALI' => '20',
- 'Bengali(?:[-_]|\s+)?Block' => '66',
-},
-'bi' => {
- 'Bidi(?:[-_]|\s+)?Control' => '159',
-},
-'bl' => {
- 'Block(?:[-_]|\s+)?Elements' => '103',
-},
-'bo' => {
- 'BOPOMOFO' => '45',
- 'Bopomofo(?:[-_]|\s+)?Block' => '114',
- 'Bopomofo(?:[-_]|\s+)?Extended' => '117',
- 'Box(?:[-_]|\s+)?Drawing' => '102',
-},
-'br' => {
- 'Braille(?:[-_]|\s+)?Patterns' => '107',
-},
-'by' => {
- 'Byzantine(?:[-_]|\s+)?Musical(?:[-_]|\s+)?Symbols' => '140',
-},
-'ca' => {
- 'CANADIAN(?:[-_]|\s+)?ABORIGINAL' => '37',
-},
-'ch' => {
- 'CHEROKEE' => '36',
- 'Cherokee(?:[-_]|\s+)?Block' => '82',
-},
-'cj' => {
- 'CJK(?:[-_]|\s+)?Compatibility' => '119',
- 'CJK(?:[-_]|\s+)?Compatibility(?:[-_]|\s+)?Forms' => '132',
- 'CJK(?:[-_]|\s+)?Compatibility(?:[-_]|\s+)?Ideographs' => '128',
- 'CJK(?:[-_]|\s+)?Compatibility(?:[-_]|\s+)?Ideographs(?:[-_]|\s+)?Supplement' => '144',
- 'CJK(?:[-_]|\s+)?Ideograph' => '1',
- 'CJK(?:[-_]|\s+)?Ideograph(?:[-_]|\s+)?Extension(?:[-_]|\s+)?A' => '0',
- 'CJK(?:[-_]|\s+)?Ideograph(?:[-_]|\s+)?Extension(?:[-_]|\s+)?B' => '7',
- 'CJK(?:[-_]|\s+)?Radicals(?:[-_]|\s+)?Supplement' => '108',
- 'CJK(?:[-_]|\s+)?Symbols(?:[-_]|\s+)?and(?:[-_]|\s+)?Punctuation' => '111',
- 'CJK(?:[-_]|\s+)?Unified(?:[-_]|\s+)?Ideographs' => '121',
- 'CJK(?:[-_]|\s+)?Unified(?:[-_]|\s+)?Ideographs(?:[-_]|\s+)?Extension(?:[-_]|\s+)?A' => '120',
- 'CJK(?:[-_]|\s+)?Unified(?:[-_]|\s+)?Ideographs(?:[-_]|\s+)?Extension(?:[-_]|\s+)?B' => '143',
-},
-'co' => {
- 'Combining(?:[-_]|\s+)?Diacritical(?:[-_]|\s+)?Marks' => '57',
- 'Combining(?:[-_]|\s+)?Half(?:[-_]|\s+)?Marks' => '131',
- 'Combining(?:[-_]|\s+)?Marks(?:[-_]|\s+)?for(?:[-_]|\s+)?Symbols' => '93',
- 'Common' => '50',
- 'Control(?:[-_]|\s+)?Pictures' => '99',
-},
-'cu' => {
- 'Currency(?:[-_]|\s+)?Symbols' => '92',
-},
-'cy' => {
- 'CYRILLIC' => '13',
- 'Cyrillic(?:[-_]|\s+)?Block' => '59',
-},
-'da' => {
- 'Dash' => '151',
-},
-'de' => {
- 'DESERET' => '49',
- 'Deseret(?:[-_]|\s+)?Block' => '139',
- 'DEVANAGARI' => '19',
- 'Devanagari(?:[-_]|\s+)?Block' => '65',
-},
-'di' => {
- 'Diacritic' => '154',
- 'Dingbats' => '106',
-},
-'en' => {
- 'Enclosed(?:[-_]|\s+)?Alphanumerics' => '101',
- 'Enclosed(?:[-_]|\s+)?CJK(?:[-_]|\s+)?Letters(?:[-_]|\s+)?and(?:[-_]|\s+)?Months' => '118',
-},
-'et' => {
- 'ETHIOPIC' => '35',
- 'Ethiopic(?:[-_]|\s+)?Block' => '81',
-},
-'ex' => {
- 'Extender' => '155',
-},
-'ge' => {
- 'General(?:[-_]|\s+)?Punctuation' => '90',
- 'Geometric(?:[-_]|\s+)?Shapes' => '104',
- 'GEORGIAN' => '33',
- 'Georgian(?:[-_]|\s+)?Block' => '79',
-},
-'go' => {
- 'GOTHIC' => '48',
- 'Gothic(?:[-_]|\s+)?Block' => '138',
-},
-'gr' => {
- 'GREEK' => '11',
- 'Greek(?:[-_]|\s+)?Block' => '58',
- 'Greek(?:[-_]|\s+)?Extended' => '89',
-},
-'gu' => {
- 'GUJARATI' => '22',
- 'Gujarati(?:[-_]|\s+)?Block' => '68',
- 'GURMUKHI' => '21',
- 'Gurmukhi(?:[-_]|\s+)?Block' => '67',
-},
-'ha' => {
- 'Halfwidth(?:[-_]|\s+)?and(?:[-_]|\s+)?Fullwidth(?:[-_]|\s+)?Forms' => '136',
- 'HAN' => '42',
- 'HANGUL' => '34',
- 'Hangul(?:[-_]|\s+)?Compatibility(?:[-_]|\s+)?Jamo' => '115',
- 'Hangul(?:[-_]|\s+)?Jamo' => '80',
- 'Hangul(?:[-_]|\s+)?Syllable' => '2',
- 'Hangul(?:[-_]|\s+)?Syllables' => '124',
-},
-'he' => {
- 'HEBREW' => '15',
- 'Hebrew(?:[-_]|\s+)?Block' => '61',
- 'Hex(?:[-_]|\s+)?Digit' => '153',
-},
-'hi' => {
- 'High(?:[-_]|\s+)?Private(?:[-_]|\s+)?Use(?:[-_]|\s+)?Surrogates' => '126',
- 'High(?:[-_]|\s+)?Surrogates' => '125',
- 'HIRAGANA' => '43',
- 'Hiragana(?:[-_]|\s+)?Block' => '112',
-},
-'hy' => {
- 'Hyphen' => '150',
-},
-'id' => {
- 'ID(?:[-_]|\s+)?Continue' => '171',
- 'ID(?:[-_]|\s+)?Start' => '170',
- 'Ideographic' => '161',
- 'Ideographic(?:[-_]|\s+)?Description(?:[-_]|\s+)?Characters' => '110',
-},
-'in' => {
- 'INHERITED' => '12',
-},
-'ip' => {
- 'IPA(?:[-_]|\s+)?Extensions' => '55',
-},
-'jo' => {
- 'Join(?:[-_]|\s+)?Control' => '158',
-},
-'ka' => {
- 'Kanbun' => '116',
- 'Kangxi(?:[-_]|\s+)?Radicals' => '109',
- 'KANNADA' => '26',
- 'Kannada(?:[-_]|\s+)?Block' => '72',
- 'KATAKANA' => '44',
- 'Katakana(?:[-_]|\s+)?Block' => '113',
-},
-'kh' => {
- 'KHMER' => '40',
- 'Khmer(?:[-_]|\s+)?Block' => '86',
-},
-'la' => {
- 'Lampersand' => '169',
- 'LAO' => '30',
- 'Lao(?:[-_]|\s+)?Block' => '76',
- 'LATIN' => '10',
- 'Latin(?:[-_]|\s+)?Extended(?:[-_]|\s+)?Additional' => '88',
- 'Latin(?:[-_]|\s+)?Extended(?:[-_]|\s+)?A' => '53',
- 'Latin(?:[-_]|\s+)?Extended(?:[-_]|\s+)?B' => '54',
- 'Latin(?:[-_]|\s+)?1(?:[-_]|\s+)?Supplement' => '52',
-},
-'le' => {
- 'Letterlike(?:[-_]|\s+)?Symbols' => '94',
-},
-'lo' => {
- 'Low(?:[-_]|\s+)?Surrogate' => '5',
- 'Low(?:[-_]|\s+)?Surrogates' => '127',
- 'Lowercase' => '166',
-},
-'ma' => {
- 'MALAYALAM' => '27',
- 'Malayalam(?:[-_]|\s+)?Block' => '73',
- 'Math' => '168',
- 'Mathematical(?:[-_]|\s+)?Alphanumeric(?:[-_]|\s+)?Symbols' => '142',
- 'Mathematical(?:[-_]|\s+)?Operators' => '97',
-},
-'mi' => {
- 'Miscellaneous(?:[-_]|\s+)?Symbols' => '105',
- 'Miscellaneous(?:[-_]|\s+)?Technical' => '98',
-},
-'mo' => {
- 'MONGOLIAN' => '41',
- 'Mongolian(?:[-_]|\s+)?Block' => '87',
-},
-'mu' => {
- 'Musical(?:[-_]|\s+)?Symbols' => '141',
-},
-'my' => {
- 'MYANMAR' => '32',
- 'Myanmar(?:[-_]|\s+)?Block' => '78',
-},
-'no' => {
- 'Non(?:[-_]|\s+)?Private(?:[-_]|\s+)?Use(?:[-_]|\s+)?High(?:[-_]|\s+)?Surrogate' => '3',
- 'Noncharacter(?:[-_]|\s+)?Code(?:[-_]|\s+)?Point' => '162',
-},
-'nu' => {
- 'Number(?:[-_]|\s+)?Forms' => '95',
-},
-'og' => {
- 'OGHAM' => '38',
- 'Ogham(?:[-_]|\s+)?Block' => '84',
-},
-'ol' => {
- 'Old(?:[-_]|\s+)?Italic(?:[-_]|\s+)?Block' => '137',
- 'OLD(?:[-_]|\s+)?ITALIC' => '47',
-},
-'op' => {
- 'Optical(?:[-_]|\s+)?Character(?:[-_]|\s+)?Recognition' => '100',
-},
-'or' => {
- 'ORIYA' => '23',
- 'Oriya(?:[-_]|\s+)?Block' => '69',
-},
-'ot' => {
- 'Other(?:[-_]|\s+)?Alphabetic' => '157',
- 'Other(?:[-_]|\s+)?Lowercase' => '156',
- 'Other(?:[-_]|\s+)?Math' => '149',
- 'Other(?:[-_]|\s+)?Uppercase' => '160',
-},
-'pl' => {
- 'Plane(?:[-_]|\s+)?15(?:[-_]|\s+)?Private(?:[-_]|\s+)?Use' => '8',
- 'Plane(?:[-_]|\s+)?16(?:[-_]|\s+)?Private(?:[-_]|\s+)?Use' => '9',
-},
-'pr' => {
- 'Private(?:[-_]|\s+)?Use' => '6',
- 'Private(?:[-_]|\s+)?Use(?:[-_]|\s+)?High(?:[-_]|\s+)?Surrogate' => '4',
-},
-'qu' => {
- 'Quotation(?:[-_]|\s+)?Mark' => '148',
-},
-'ru' => {
- 'RUNIC' => '39',
- 'Runic(?:[-_]|\s+)?Block' => '85',
-},
-'si' => {
- 'SINHALA' => '28',
- 'Sinhala(?:[-_]|\s+)?Block' => '74',
-},
-'sm' => {
- 'Small(?:[-_]|\s+)?Form(?:[-_]|\s+)?Variants' => '133',
-},
-'sp' => {
- 'Spacing(?:[-_]|\s+)?Modifier(?:[-_]|\s+)?Letters' => '56',
- 'Specials' => '135',
-},
-'su' => {
- 'Superscripts(?:[-_]|\s+)?and(?:[-_]|\s+)?Subscripts' => '91',
-},
-'sy' => {
- 'SYRIAC' => '17',
- 'Syriac(?:[-_]|\s+)?Block' => '63',
-},
-'ta' => {
- 'Tags' => '145',
- 'TAMIL' => '24',
- 'Tamil(?:[-_]|\s+)?Block' => '70',
-},
-'te' => {
- 'TELUGU' => '25',
- 'Telugu(?:[-_]|\s+)?Block' => '71',
- 'Terminal(?:[-_]|\s+)?Punctuation' => '147',
-},
-'th' => {
- 'THAANA' => '18',
- 'Thaana(?:[-_]|\s+)?Block' => '64',
- 'THAI' => '29',
- 'Thai(?:[-_]|\s+)?Block' => '75',
-},
-'ti' => {
- 'TIBETAN' => '31',
- 'Tibetan(?:[-_]|\s+)?Block' => '77',
-},
-'un' => {
- 'Unassigned' => '164',
- 'Unified(?:[-_]|\s+)?Canadian(?:[-_]|\s+)?Aboriginal(?:[-_]|\s+)?Syllabics' => '83',
-},
-'up' => {
- 'Uppercase' => '167',
-},
-'wh' => {
- 'White(?:[-_]|\s+)?space' => '146',
-},
-'yi' => {
- 'YI' => '46',
- 'Yi(?:[-_]|\s+)?Radicals' => '123',
- 'Yi(?:[-_]|\s+)?Syllables' => '122',
-},
-);
+# Built Mon Jan 14 15:52:42 2002.
+
+##
+## Data in this file used by ../utf8_heavy.pl
+##
-%utf8::InScript =
-(
- 10 => 'LATIN',
- 11 => 'GREEK',
- 12 => 'INHERITED',
- 13 => 'CYRILLIC',
- 14 => 'ARMENIAN',
- 15 => 'HEBREW',
- 16 => 'ARABIC',
- 17 => 'SYRIAC',
- 18 => 'THAANA',
- 19 => 'DEVANAGARI',
- 20 => 'BENGALI',
- 21 => 'GURMUKHI',
- 22 => 'GUJARATI',
- 23 => 'ORIYA',
- 24 => 'TAMIL',
- 25 => 'TELUGU',
- 26 => 'KANNADA',
- 27 => 'MALAYALAM',
- 28 => 'SINHALA',
- 29 => 'THAI',
- 30 => 'LAO',
- 31 => 'TIBETAN',
- 32 => 'MYANMAR',
- 33 => 'GEORGIAN',
- 34 => 'HANGUL',
- 35 => 'ETHIOPIC',
- 36 => 'CHEROKEE',
- 37 => 'CANADIAN-ABORIGINAL',
- 38 => 'OGHAM',
- 39 => 'RUNIC',
- 40 => 'KHMER',
- 41 => 'MONGOLIAN',
- 42 => 'HAN',
- 43 => 'HIRAGANA',
- 44 => 'KATAKANA',
- 45 => 'BOPOMOFO',
- 46 => 'YI',
- 47 => 'OLD-ITALIC',
- 48 => 'GOTHIC',
- 49 => 'DESERET',
+## Mapping from name to filename in ./In
+%utf8::In = (
);
-%utf8::InBlock =
-(
- 51 => 'Basic Latin',
- 52 => 'Latin-1 Supplement',
- 53 => 'Latin Extended-A',
- 54 => 'Latin Extended-B',
- 55 => 'IPA Extensions',
- 56 => 'Spacing Modifier Letters',
- 57 => 'Combining Diacritical Marks',
- 58 => 'Greek',
- 59 => 'Cyrillic',
- 60 => 'Armenian',
- 61 => 'Hebrew',
- 62 => 'Arabic',
- 63 => 'Syriac',
- 64 => 'Thaana',
- 65 => 'Devanagari',
- 66 => 'Bengali',
- 67 => 'Gurmukhi',
- 68 => 'Gujarati',
- 69 => 'Oriya',
- 70 => 'Tamil',
- 71 => 'Telugu',
- 72 => 'Kannada',
- 73 => 'Malayalam',
- 74 => 'Sinhala',
- 75 => 'Thai',
- 76 => 'Lao',
- 77 => 'Tibetan',
- 78 => 'Myanmar',
- 79 => 'Georgian',
- 80 => 'Hangul Jamo',
- 81 => 'Ethiopic',
- 82 => 'Cherokee',
- 83 => 'Unified Canadian Aboriginal Syllabics',
- 84 => 'Ogham',
- 85 => 'Runic',
- 86 => 'Khmer',
- 87 => 'Mongolian',
- 88 => 'Latin Extended Additional',
- 89 => 'Greek Extended',
- 90 => 'General Punctuation',
- 91 => 'Superscripts and Subscripts',
- 92 => 'Currency Symbols',
- 93 => 'Combining Marks for Symbols',
- 94 => 'Letterlike Symbols',
- 95 => 'Number Forms',
- 96 => 'Arrows',
- 97 => 'Mathematical Operators',
- 98 => 'Miscellaneous Technical',
- 99 => 'Control Pictures',
- 100 => 'Optical Character Recognition',
- 101 => 'Enclosed Alphanumerics',
- 102 => 'Box Drawing',
- 103 => 'Block Elements',
- 104 => 'Geometric Shapes',
- 105 => 'Miscellaneous Symbols',
- 106 => 'Dingbats',
- 107 => 'Braille Patterns',
- 108 => 'CJK Radicals Supplement',
- 109 => 'Kangxi Radicals',
- 110 => 'Ideographic Description Characters',
- 111 => 'CJK Symbols and Punctuation',
- 112 => 'Hiragana',
- 113 => 'Katakana',
- 114 => 'Bopomofo',
- 115 => 'Hangul Compatibility Jamo',
- 116 => 'Kanbun',
- 117 => 'Bopomofo Extended',
- 118 => 'Enclosed CJK Letters and Months',
- 119 => 'CJK Compatibility',
- 120 => 'CJK Unified Ideographs Extension A',
- 121 => 'CJK Unified Ideographs',
- 122 => 'Yi Syllables',
- 123 => 'Yi Radicals',
- 124 => 'Hangul Syllables',
- 125 => 'High Surrogates',
- 126 => 'High Private Use Surrogates',
- 127 => 'Low Surrogates',
- 128 => 'CJK Compatibility Ideographs',
- 129 => 'Alphabetic Presentation Forms',
- 130 => 'Arabic Presentation Forms-A',
- 131 => 'Combining Half Marks',
- 132 => 'CJK Compatibility Forms',
- 133 => 'Small Form Variants',
- 134 => 'Arabic Presentation Forms-B',
- 135 => 'Specials',
- 136 => 'Halfwidth and Fullwidth Forms',
- 137 => 'Old Italic',
- 138 => 'Gothic',
- 139 => 'Deseret',
- 140 => 'Byzantine Musical Symbols',
- 141 => 'Musical Symbols',
- 142 => 'Mathematical Alphanumeric Symbols',
- 143 => 'CJK Unified Ideographs Extension B',
- 144 => 'CJK Compatibility Ideographs Supplement',
- 145 => 'Tags',
+## Mappings from regex to filename in ./In/
+%utf8::InPat = (
+ 'al' => {
+ 'Alphabetic(?:[-_]|\s+)?Presentation(?:[-_]|\s+)?Forms' => 'Alphabet',
+ },
+ 'ar' => {
+ 'Armenian' => 'Armenian',
+ 'Arabic' => 'Arabic',
+ 'Arrows' => 'Arrows',
+ 'Arabic(?:[-_]|\s+)?Presentation(?:[-_]|\s+)?Forms(?:[-_]|\s+)?A' => 'ArabicPr',
+ 'Arabic(?:[-_]|\s+)?Presentation(?:[-_]|\s+)?Forms(?:[-_]|\s+)?B' => 'ArabicP2',
+ },
+ 'ba' => {
+ 'Basic(?:[-_]|\s+)?Latin' => 'BasicLat',
+ },
+ 'be' => {
+ 'Bengali' => 'Bengali',
+ },
+ 'bl' => {
+ 'Block(?:[-_]|\s+)?Elements' => 'BlockEle',
+ },
+ 'bo' => {
+ 'Bopomofo' => 'Bopomof2',
+ 'Bopomofo(?:[-_]|\s+)?Extended' => 'Bopomofo',
+ 'Box(?:[-_]|\s+)?Drawing' => 'BoxDrawi',
+ },
+ 'br' => {
+ 'Braille(?:[-_]|\s+)?Patterns' => 'BrailleP',
+ },
+ 'by' => {
+ 'Byzantine(?:[-_]|\s+)?Musical(?:[-_]|\s+)?Symbols' => 'Byzantin',
+ },
+ 'ch' => {
+ 'Cherokee' => 'Cherokee',
+ },
+ 'cj' => {
+ 'Cjk(?:[-_]|\s+)?Radicals(?:[-_]|\s+)?Supplement' => 'CjkRadic',
+ 'Cjk(?:[-_]|\s+)?Symbols(?:[-_]|\s+)?And(?:[-_]|\s+)?Punctuation' => 'CjkSymbo',
+ 'Cjk(?:[-_]|\s+)?Unified(?:[-_]|\s+)?Ideographs(?:[-_]|\s+)?Extension(?:[-_]|\s+)?A' => 'CjkUnif2',
+ 'Cjk(?:[-_]|\s+)?Unified(?:[-_]|\s+)?Ideographs(?:[-_]|\s+)?Extension(?:[-_]|\s+)?B' => 'CjkUnif3',
+ 'Cjk(?:[-_]|\s+)?Unified(?:[-_]|\s+)?Ideographs' => 'CjkUnifi',
+ 'Cjk(?:[-_]|\s+)?Compatibility(?:[-_]|\s+)?Ideographs' => 'CjkComp2',
+ 'Cjk(?:[-_]|\s+)?Compatibility(?:[-_]|\s+)?Ideographs(?:[-_]|\s+)?Supplement' => 'CjkComp4',
+ 'Cjk(?:[-_]|\s+)?Compatibility' => 'CjkComp3',
+ 'Cjk(?:[-_]|\s+)?Compatibility(?:[-_]|\s+)?Forms' => 'CjkCompa',
+ },
+ 'co' => {
+ 'Combining(?:[-_]|\s+)?Marks(?:[-_]|\s+)?For(?:[-_]|\s+)?Symbols' => 'Combini2',
+ 'Combining(?:[-_]|\s+)?Half(?:[-_]|\s+)?Marks' => 'Combini3',
+ 'Combining(?:[-_]|\s+)?Diacritical(?:[-_]|\s+)?Marks' => 'Combinin',
+ 'Control(?:[-_]|\s+)?Pictures' => 'ControlP',
+ },
+ 'cu' => {
+ 'Currency(?:[-_]|\s+)?Symbols' => 'Currency',
+ },
+ 'cy' => {
+ 'Cyrillic' => 'Cyrillic',
+ },
+ 'de' => {
+ 'Devanagari' => 'Devanaga',
+ 'Deseret' => 'Deseret',
+ },
+ 'di' => {
+ 'Dingbats' => 'Dingbats',
+ },
+ 'en' => {
+ 'Enclosed(?:[-_]|\s+)?Alphanumerics' => 'Enclose2',
+ 'Enclosed(?:[-_]|\s+)?Cjk(?:[-_]|\s+)?Letters(?:[-_]|\s+)?And(?:[-_]|\s+)?Months' => 'Enclosed',
+ },
+ 'et' => {
+ 'Ethiopic' => 'Ethiopic',
+ },
+ 'ge' => {
+ 'Geometric(?:[-_]|\s+)?Shapes' => 'Geometri',
+ 'General(?:[-_]|\s+)?Punctuation' => 'GeneralP',
+ 'Georgian' => 'Georgian',
+ },
+ 'go' => {
+ 'Gothic' => 'Gothic',
+ },
+ 'gr' => {
+ 'Greek(?:[-_]|\s+)?Extended' => 'GreekExt',
+ 'Greek' => 'Greek',
+ },
+ 'gu' => {
+ 'Gurmukhi' => 'Gurmukhi',
+ 'Gujarati' => 'Gujarati',
+ },
+ 'ha' => {
+ 'Hangul(?:[-_]|\s+)?Compatibility(?:[-_]|\s+)?Jamo' => 'HangulCo',
+ 'Hangul(?:[-_]|\s+)?Syllables' => 'HangulSy',
+ 'Halfwidth(?:[-_]|\s+)?And(?:[-_]|\s+)?Fullwidth(?:[-_]|\s+)?Forms' => 'Halfwidt',
+ 'Hangul(?:[-_]|\s+)?Jamo' => 'HangulJa',
+ },
+ 'he' => {
+ 'Hebrew' => 'Hebrew',
+ },
+ 'hi' => {
+ 'High(?:[-_]|\s+)?Private(?:[-_]|\s+)?Use(?:[-_]|\s+)?Surrogates' => 'HighPriv',
+ 'Hiragana' => 'Hiragana',
+ 'High(?:[-_]|\s+)?Surrogates' => 'HighSurr',
+ },
+ 'id' => {
+ 'Ideographic(?:[-_]|\s+)?Description(?:[-_]|\s+)?Characters' => 'Ideograp',
+ },
+ 'ip' => {
+ 'Ipa(?:[-_]|\s+)?Extensions' => 'IpaExten',
+ },
+ 'ka' => {
+ 'Katakana' => 'Katakana',
+ 'Kangxi(?:[-_]|\s+)?Radicals' => 'KangxiRa',
+ 'Kannada' => 'Kannada',
+ 'Kanbun' => 'Kanbun',
+ },
+ 'kh' => {
+ 'Khmer' => 'Khmer',
+ },
+ 'la' => {
+ 'Latin(?:[-_]|\s+)?Extended(?:[-_]|\s+)?Additional' => 'LatinExt',
+ 'Latin(?:[-_]|\s+)?1(?:[-_]|\s+)?Supplement' => 'Latin1Su',
+ 'Lao' => 'Lao',
+ 'Latin(?:[-_]|\s+)?Extended(?:[-_]|\s+)?A' => 'LatinEx2',
+ 'Latin(?:[-_]|\s+)?Extended(?:[-_]|\s+)?B' => 'LatinEx3',
+ },
+ 'le' => {
+ 'Letterlike(?:[-_]|\s+)?Symbols' => 'Letterli',
+ },
+ 'lo' => {
+ 'Low(?:[-_]|\s+)?Surrogates' => 'LowSurro',
+ },
+ 'ma' => {
+ 'Mathematical(?:[-_]|\s+)?Operators' => 'Mathemat',
+ 'Mathematical(?:[-_]|\s+)?Alphanumeric(?:[-_]|\s+)?Symbols' => 'Mathema2',
+ 'Malayalam' => 'Malayala',
+ },
+ 'mi' => {
+ 'Miscellaneous(?:[-_]|\s+)?Symbols' => 'Miscell2',
+ 'Miscellaneous(?:[-_]|\s+)?Technical' => 'Miscella',
+ },
+ 'mo' => {
+ 'Mongolian' => 'Mongolia',
+ },
+ 'mu' => {
+ 'Musical(?:[-_]|\s+)?Symbols' => 'MusicalS',
+ },
+ 'my' => {
+ 'Myanmar' => 'Myanmar',
+ },
+ 'nu' => {
+ 'Number(?:[-_]|\s+)?Forms' => 'NumberFo',
+ },
+ 'og' => {
+ 'Ogham' => 'Ogham',
+ },
+ 'ol' => {
+ 'Old(?:[-_]|\s+)?Italic' => 'OldItali',
+ },
+ 'op' => {
+ 'Optical(?:[-_]|\s+)?Character(?:[-_]|\s+)?Recognition' => 'OpticalC',
+ },
+ 'or' => {
+ 'Oriya' => 'Oriya',
+ },
+ 'pr' => {
+ 'Private(?:[-_]|\s+)?Use' => 'PrivateU',
+ },
+ 'ru' => {
+ 'Runic' => 'Runic',
+ },
+ 'si' => {
+ 'Sinhala' => 'Sinhala',
+ },
+ 'sm' => {
+ 'Small(?:[-_]|\s+)?Form(?:[-_]|\s+)?Variants' => 'SmallFor',
+ },
+ 'sp' => {
+ 'Specials' => 'Specials',
+ 'Spacing(?:[-_]|\s+)?Modifier(?:[-_]|\s+)?Letters' => 'SpacingM',
+ },
+ 'su' => {
+ 'Superscripts(?:[-_]|\s+)?And(?:[-_]|\s+)?Subscripts' => 'Superscr',
+ },
+ 'sy' => {
+ 'Syriac' => 'Syriac',
+ },
+ 'ta' => {
+ 'Tags' => 'Tags',
+ 'Tamil' => 'Tamil',
+ },
+ 'te' => {
+ 'Telugu' => 'Telugu',
+ },
+ 'th' => {
+ 'Thaana' => 'Thaana',
+ 'Thai' => 'Thai',
+ },
+ 'ti' => {
+ 'Tibetan' => 'Tibetan',
+ },
+ 'un' => {
+ 'Unified(?:[-_]|\s+)?Canadian(?:[-_]|\s+)?Aboriginal(?:[-_]|\s+)?Syllabics' => 'UnifiedC',
+ },
+ 'yi' => {
+ 'Yi(?:[-_]|\s+)?Radicals' => 'YiRadica',
+ 'Yi(?:[-_]|\s+)?Syllables' => 'YiSyllab',
+ },
);