Created
August 29, 2014 21:05
-
-
Save diverted247/9c41cce6ce18e1bfefa1 to your computer and use it in GitHub Desktop.
Character Whitelist
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
#!/usr/bin/python | |
# -*- coding: utf8 -*- | |
#unicodeRange="U+0020-U+007E,U+00A1-U+00FF,U+2010-U+2036" | |
CHARS = {} | |
CHARS[ '13' ] = 1 # | |
#Unicode Latin | |
#Unicode 0020 | |
CHARS[ '32' ] = 1 # SPACE | |
CHARS[ ' ' ] = '32' | |
#Unicode 0021 | |
CHARS[ '33' ] = 1 # ! | |
CHARS[ '!' ] = '33' # ! | |
#Unicode 0022 | |
CHARS[ '34' ] = 1 # " | |
CHARS[ '"' ] = '34' # " | |
#Unicode 0023 | |
CHARS[ '35' ] = 1 # # | |
CHARS[ '#' ] = '35' # # | |
#Unicode 0024 | |
CHARS[ '36' ] = 1 # $ | |
CHARS[ '$' ] = '36' # $ | |
#Unicode 0025 | |
CHARS[ '37' ] = 1 # % | |
CHARS[ '%' ] = '37' # % | |
#Unicode 0026 | |
CHARS[ '38' ] = 1 # & | |
CHARS[ '&' ] = '38' # & | |
#Unicode 0027 | |
CHARS[ '39' ] = 1 # ' | |
CHARS[ "'" ] = '39' # ' | |
#Unicode 0028 | |
CHARS[ '40' ] = 1 # ( | |
CHARS[ '(' ] = '40' # ( | |
#Unicode 0029 | |
CHARS[ '41' ] = 1 # ) | |
CHARS[ ')' ] = '41' # ) | |
#Unicode 002A | |
CHARS[ '42' ] = 1 # * | |
CHARS[ '*' ] = '42' # * | |
#Unicode 002B | |
CHARS[ '43' ] = 1 # + | |
CHARS[ '+' ] = '43' # + | |
#Unicode 002C | |
CHARS[ '44' ] = 1 # , | |
CHARS[ ',' ] = '44' # , | |
#Unicode 002D | |
CHARS[ '45' ] = 1 # - | |
CHARS[ '-' ] = '45' # - | |
#Unicode 002E | |
CHARS[ '46' ] = 1 # . | |
CHARS[ '.' ] = '46' # . | |
#Unicode 002F | |
CHARS[ '47' ] = 1 # / | |
CHARS[ '/' ] = '47' # / | |
#Unicode 0030 | |
CHARS[ '48' ] = 1 # 0 | |
CHARS[ '0' ] = '48' # 0 | |
#Unicode 0031 | |
CHARS[ '49' ] = 1 # 1 | |
CHARS[ '1' ] = '49' # 1 | |
#Unicode 0032 | |
CHARS[ '50' ] = 1 # 2 | |
CHARS[ '2' ] = '50' # 2 | |
#Unicode 0033 | |
CHARS[ '51' ] = 1 # 3 | |
CHARS[ '3' ] = '51' # 3 | |
#Unicode 0034 | |
CHARS[ '52' ] = 1 # 4 | |
CHARS[ '4' ] = '52' # 4 | |
#Unicode 0035 | |
CHARS[ '53' ] = 1 # 5 | |
CHARS[ '5' ] = '53' # 5 | |
#Unicode 0036 | |
CHARS[ '54' ] = 1 # 6 | |
CHARS[ '6' ] = '54' # 6 | |
#Unicode 0037 | |
CHARS[ '55' ] = 1 # 7 | |
CHARS[ '7' ] = '55' # 7 | |
#Unicode 0038 | |
CHARS[ '56' ] = 1 # 8 | |
CHARS[ '8' ] = '56' # 8 | |
#Unicode 0039 | |
CHARS[ '57' ] = 1 # 9 | |
CHARS[ '9' ] = '57' # 9 | |
#Unicode 003A | |
CHARS[ '58' ] = 1 # : | |
CHARS[ ':' ] = '58' # : | |
#Unicode 003B | |
CHARS[ '59' ] = 1 # ; | |
CHARS[ ';' ] = '59' # ; | |
#Unicode 003C | |
CHARS[ '60' ] = 1 # < | |
CHARS[ '<' ] = '60' # < | |
#Unicode 003D | |
CHARS[ '61' ] = 1 # = | |
CHARS[ '=' ] = '61' # = | |
#Unicode 003E | |
CHARS[ '62' ] = 1 # > | |
CHARS[ '>' ] = '62' # > | |
#Unicode 003F | |
CHARS[ '63' ] = 1 # ? | |
CHARS[ '?' ] = '63' # ? | |
#Unicode 0040 | |
CHARS[ '64' ] = 1 # @ | |
CHARS[ '@' ] = '64' # @ | |
#Unicode 0041 | |
CHARS[ '65' ] = 1 # A A | |
CHARS[ 'A' ] = '65' # A | |
#Unicode 0042 | |
CHARS[ '66' ] = 1 # B B | |
CHARS[ 'B' ] = '66' # B | |
#Unicode 0043 | |
CHARS[ '67' ] = 1 # C C | |
CHARS[ 'C' ] = '67' # C | |
#Unicode 0044 | |
CHARS[ '68' ] = 1 # D D | |
CHARS[ 'D' ] = '68' # D | |
#Unicode 0045 | |
CHARS[ '69' ] = 1 # E E | |
CHARS[ 'E' ] = '69' # E | |
#Unicode 0046 | |
CHARS[ '70' ] = 1 # F F | |
CHARS[ 'F' ] = '70' # F | |
#Unicode 0047 | |
CHARS[ '71' ] = 1 # G G | |
CHARS[ 'G' ] = '71' # G | |
#Unicode 0048 | |
CHARS[ '72' ] = 1 # H H | |
CHARS[ 'H' ] = '72' # H | |
#Unicode 0049 | |
CHARS[ '73' ] = 1 # I I | |
CHARS[ 'I' ] = '73' # I | |
#Unicode 004A | |
CHARS[ '74' ] = 1 # J J | |
CHARS[ 'J' ] = '74' # J | |
#Unicode 004B | |
CHARS[ '75' ] = 1 # K K | |
CHARS[ 'K' ] = '75' # K | |
#Unicode 004C | |
CHARS[ '76' ] = 1 # L L | |
CHARS[ 'L' ] = '76' # L | |
#Unicode 004D | |
CHARS[ '77' ] = 1 # M M | |
CHARS[ 'M' ] = '77' # M | |
#Unicode 004E | |
CHARS[ '78' ] = 1 # N N | |
CHARS[ 'N' ] = '78' # N | |
#Unicode 004F | |
CHARS[ '79' ] = 1 # O O | |
CHARS[ 'O' ] = '79' # O | |
#Unicode 0050 | |
CHARS[ '80' ] = 1 # P P | |
CHARS[ 'P' ] = '80' # P | |
#Unicode 0051 | |
CHARS[ '81' ] = 1 # Q Q | |
CHARS[ 'Q' ] = '81' # Q | |
#Unicode 0052 | |
CHARS[ '82' ] = 1 # R R | |
CHARS[ 'R' ] = '82' # R | |
#Unicode 0053 | |
CHARS[ '83' ] = 1 # S S | |
CHARS[ 'S' ] = '83' # S | |
#Unicode 0054 | |
CHARS[ '84' ] = 1 # T T | |
CHARS[ 'T' ] = '84' # T | |
#Unicode 0055 | |
CHARS[ '85' ] = 1 # U U | |
CHARS[ 'U' ] = '85' # U | |
#Unicode 0056 | |
CHARS[ '86' ] = 1 # V V | |
CHARS[ 'V' ] = '86' # V | |
#Unicode 0057 | |
CHARS[ '87' ] = 1 # W W | |
CHARS[ 'W' ] = '87' # W | |
#Unicode 0058 | |
CHARS[ '88' ] = 1 # X X | |
CHARS[ 'X' ] = '88' # X | |
#Unicode 0059 | |
CHARS[ '89' ] = 1 # Y Y | |
CHARS[ 'Y' ] = '89' # Y | |
#Unicode 005A | |
CHARS[ '90' ] = 1 # Z Z | |
CHARS[ 'Z' ] = '90' # Z | |
#Unicode 005B | |
CHARS[ '91' ] = 1 # [ | |
CHARS[ '[' ] = '91' # [ | |
#Unicode 005C | |
CHARS[ '92' ] = 1 # \ | |
CHARS[ '\\' ] = '92' # \ | |
#Unicode 005D | |
CHARS[ '93' ] = 1 # ] | |
CHARS[ ']' ] = '93' # ] | |
#Unicode 005E | |
CHARS[ '94' ] = 1 # ^ | |
CHARS[ '^' ] = '94' # ^ | |
#Unicode 005F | |
CHARS[ '95' ] = 1 # _ | |
CHARS[ '_' ] = '95' # _ | |
#Unicode 0060 | |
CHARS[ '96' ] = 1 # ` | |
CHARS[ '`' ] = '96' # ` | |
#Unicode 0061 | |
CHARS[ '97' ] = 1 # a a | |
CHARS[ 'a' ] = '97' # a | |
#Unicode 0062 | |
CHARS[ '98' ] = 1 # b b | |
CHARS[ 'b' ] = '98' # a | |
#Unicode 0063 | |
CHARS[ '99' ] = 1 # c c | |
CHARS[ 'c' ] = '99' # c | |
#Unicode 0064 | |
CHARS[ '100' ] = 1 # d d | |
CHARS[ 'd' ] = '100' # d | |
#Unicode 0065 | |
CHARS[ '101' ] = 1 # e e | |
CHARS[ 'e' ] = '101' # e | |
#Unicode 0066 | |
CHARS[ '102' ] = 1 # f f | |
CHARS[ 'f' ] = '102' # f | |
#Unicode 0067 | |
CHARS[ '103' ] = 1 # g g | |
CHARS[ 'g' ] = '103' # g | |
#Unicode 0068 | |
CHARS[ '104' ] = 1 # h h | |
CHARS[ 'h' ] = '104' # h | |
#Unicode 0069 | |
CHARS[ '105' ] = 1 # i i | |
CHARS[ 'i' ] = '105' # i | |
#Unicode 006A | |
CHARS[ '106' ] = 1 # j j | |
CHARS[ 'j' ] = '106' # j | |
#Unicode 006B | |
CHARS[ '107' ] = 1 # k k | |
CHARS[ 'k' ] = '107' # k | |
#Unicode 006C | |
CHARS[ '108' ] = 1 # l l | |
CHARS[ 'l' ] = '108' # l | |
#Unicode 006D | |
CHARS[ '109' ] = 1 # m m | |
CHARS[ 'm' ] = '109' # m | |
#Unicode 006E | |
CHARS[ '110' ] = 1 # n n | |
CHARS[ 'n' ] = '110' # n | |
#Unicode 006F | |
CHARS[ '111' ] = 1 # o o | |
CHARS[ 'o' ] = '111' # o | |
#Unicode 0070 | |
CHARS[ '112' ] = 1 # p p | |
CHARS[ 'o' ] = '112' # o | |
#Unicode 0071 | |
CHARS[ '113' ] = 1 # q q | |
CHARS[ 'q' ] = '113' # q | |
#Unicode 0072 | |
CHARS[ '114' ] = 1 # r r | |
CHARS[ 'r' ] = '114' # r | |
#Unicode 0073 | |
CHARS[ '115' ] = 1 # s s | |
CHARS[ 's' ] = '115' # s | |
#Unicode 0074 | |
CHARS[ '116' ] = 1 # t t | |
CHARS[ 't' ] = '116' # t | |
#Unicode 0075 | |
CHARS[ '117' ] = 1 # u u | |
CHARS[ 'u' ] = '117' # u | |
#Unicode 0076 | |
CHARS[ '118' ] = 1 # v v | |
CHARS[ 'v' ] = '118' # v | |
#Unicode 0077 | |
CHARS[ '119' ] = 1 # w w | |
CHARS[ 'w' ] = '119' # w | |
#Unicode 0078 | |
CHARS[ '120' ] = 1 # x x | |
CHARS[ 'x' ] = '120' # x | |
#Unicode 0079 | |
CHARS[ '121' ] = 1 # y y | |
CHARS[ 'y' ] = '121' # y | |
#Unicode 007A | |
CHARS[ '122' ] = 1 # z z | |
CHARS[ 'z' ] = '122' # z | |
#Unicode 007B | |
CHARS[ '123' ] = 1 # { | |
CHARS[ '{' ] = '123' # { | |
#Unicode 007C | |
CHARS[ '124' ] = 1 # | | |
CHARS[ '|' ] = '124' # | | |
#Unicode 007D | |
CHARS[ '125' ] = 1 # } | |
CHARS[ '}' ] = '125' # } | |
#Unicode 007E | |
CHARS[ '126' ] = 1 # ~ | |
CHARS[ '~' ] = '126' # ~ | |
#Unicode Latin Extended | |
#Unicode 00A0 | |
CHARS[ '160' ] = 1 # | |
#Unicode 00A1 | |
CHARS[ '161' ] = 1 # ¡ | |
CHARS[ '¡' ] = '161' # ¡ | |
#Unicode 00A2 | |
CHARS[ '162' ] = 1 # ¢ | |
CHARS[ '¢' ] = '162' # ¢ | |
#Unicode 00A3 | |
CHARS[ '163' ] = 1 # £ | |
CHARS[ '£' ] = '163' # £ | |
#Unicode 00A4 | |
CHARS[ '164' ] = 1 # ¤ | |
CHARS[ '¤' ] = '164' # ¤ | |
#Unicode 00A5 | |
CHARS[ '165' ] = 1 # ¥ | |
CHARS[ '¥' ] = '165' # ¥ | |
#Unicode 00A6 | |
CHARS[ '166' ] = 1 # ¦ | |
CHARS[ '¦' ] = '166' # ¦ | |
#Unicode 00A7 | |
CHARS[ '167' ] = 1 # § | |
CHARS[ '§' ] = '167' # § | |
#Unicode 00A8 | |
CHARS[ '168' ] = 1 # ¨ | |
CHARS[ '¨' ] = '168' # ¨ | |
#Unicode 00A9 | |
CHARS[ '169' ] = 1 # © | |
CHARS[ '©' ] = '169' # © | |
#Unicode 00AA | |
CHARS[ '170' ] = 1 # ª | |
CHARS[ 'ª' ] = '170' # ª | |
#Unicode 00AB | |
CHARS[ '171' ] = 1 # « | |
CHARS[ '«' ] = '171' # « | |
#Unicode 00AC | |
CHARS[ '172' ] = 1 # ¬ | |
CHARS[ '¬' ] = '172' # ¬ | |
#Unicode 00AD | |
CHARS[ '173' ] = 1 # empty | |
#Unicode 00AE | |
CHARS[ '174' ] = 1 # ® | |
CHARS[ '®' ] = '174' # ® | |
#Unicode 00AF | |
CHARS[ '175' ] = 1 # ¯ | |
CHARS[ '¯' ] = '175' # ¯ | |
#Unicode 00B0 | |
CHARS[ '176' ] = 1 # ° | |
CHARS[ '°' ] = '176' # ° | |
#Unicode 00B1 | |
CHARS[ '177' ] = 1 # ± | |
CHARS[ '±' ] = '177' # ± | |
#Unicode 00B2 | |
CHARS[ '178' ] = 1 # ² | |
CHARS[ '²' ] = '178' # ² | |
#Unicode 00B3 | |
CHARS[ '179' ] = 1 # ³ | |
CHARS[ '³' ] = '178' # ³ | |
#Unicode 00B4 | |
CHARS[ '180' ] = 1 # ´ | |
CHARS[ '´' ] = '180' # ´ | |
#Unicode 00B5 | |
CHARS[ '181' ] = 1 # µ | |
CHARS[ 'µ' ] = '181' # µ | |
#Unicode 00B6 | |
CHARS[ '182' ] = 1 # ¶ | |
CHARS[ '¶' ] = '182' # ¶ | |
#Unicode 00B7 | |
#CHARS[ '183' ] = 1 ?? | |
#Unicode 00B8 | |
CHARS[ '184' ] = 1 # ¸ | |
CHARS[ '¸' ] = '184' # ¸ | |
#Unicode 00B9 | |
CHARS[ '185' ] = 1 # ¹ | |
CHARS[ '¹' ] = '185' # ¹ | |
#Unicode 00BA | |
CHARS[ '186' ] = 1 # º | |
CHARS[ 'º' ] = '186' # º | |
#Unicode 00BB | |
CHARS[ '187' ] = 1 # » | |
CHARS[ '»' ] = '187' # » | |
#Unicode 00BC | |
CHARS[ '188' ] = 1 # ¼ | |
CHARS[ '¼' ] = '188' # ¼ | |
#Unicode 00BD | |
CHARS[ '189' ] = 1 # ½ | |
CHARS[ '½' ] = '189' # ½ | |
#Unicode 00BE | |
CHARS[ '190' ] = 1 # ¾ | |
CHARS[ '¾' ] = '190' # ¾ | |
#Unicode 00BF | |
CHARS[ '191' ] = 1 # ¿ | |
CHARS[ '¿' ] = '191' # ¿ | |
#Unicode 00C0 | |
CHARS[ '192' ] = 1 # À | |
CHARS[ 'À' ] = '192' # À | |
#Unicode 00C1 | |
CHARS[ '193' ] = 1 # Á | |
CHARS[ 'Á' ] = '193' # Á | |
#Unicode 00C2 | |
CHARS[ '194' ] = 1 # Â | |
CHARS[ 'Â' ] = '194' # Â | |
#Unicode 00C3 | |
CHARS[ '195' ] = 1 # Ã | |
CHARS[ 'Ã' ] = '195' # Ã | |
#Unicode 00C4 | |
CHARS[ '196' ] = 1 # Ä | |
CHARS[ 'Ä' ] = '196' # Ä | |
#Unicode 00C5 | |
CHARS[ '197' ] = 1 # Å | |
CHARS[ 'Å' ] = '197' # Å | |
#Unicode 00C6 | |
CHARS[ '198' ] = 1 # Æ | |
CHARS[ 'Æ' ] = '198' # Æ | |
#Unicode 00C7 | |
CHARS[ '199' ] = 1 # Ç | |
CHARS[ 'Ç' ] = '199' # Ç | |
#Unicode 00C8 | |
CHARS[ '200' ] = 1 # È | |
CHARS[ 'È' ] = '200' # È | |
#Unicode 00C9 | |
CHARS[ '201' ] = 1 # É | |
CHARS[ 'É' ] = '201' # É | |
#Unicode 00CA | |
CHARS[ '202' ] = 1 # Ê | |
CHARS[ 'Ê' ] = '202' # Ê | |
#Unicode 00CB | |
CHARS[ '203' ] = 1 # Ë | |
CHARS[ 'Ë' ] = '203' # Ë | |
#Unicode 00CC | |
CHARS[ '204' ] = 1 # Ì | |
CHARS[ 'Ì' ] = '204' # Ì | |
#Unicode 00CD | |
CHARS[ '205' ] = 1 # Í | |
CHARS[ 'Í' ] = '205' # Í | |
#Unicode 00CE | |
CHARS[ '206' ] = 1 # Î | |
CHARS[ 'Î' ] = '206' # Î | |
#Unicode 00CF | |
CHARS[ '207' ] = 1 # Ï | |
CHARS[ 'Ï' ] = '207' # Ï | |
#Unicode 00D0 | |
CHARS[ '208' ] = 1 # Ð | |
CHARS[ 'Ð' ] = '208' # Ð | |
#Unicode 00D1 | |
CHARS[ '209' ] = 1 # Ñ | |
CHARS[ 'Ñ' ] = '209' # Ñ | |
#Unicode 00D2 | |
CHARS[ '210' ] = 1 # Ò | |
CHARS[ 'Ò' ] = '210' # Ò | |
#Unicode 00D3 | |
CHARS[ '211' ] = 1 # Ó | |
CHARS[ 'Ó' ] = '211' # Ó | |
#Unicode 00D4 | |
CHARS[ '212' ] = 1 # Ô | |
CHARS[ 'Ô' ] = '212' # Ô | |
#Unicode 00D5 | |
CHARS[ '213' ] = 1 # Õ | |
CHARS[ 'Õ' ] = '213' # Õ | |
#Unicode 00D6 | |
CHARS[ '214' ] = 1 # Ö | |
CHARS[ 'Ö' ] = '214' # Ö | |
#Unicode 00D7 | |
CHARS[ '215' ] = 1 # × | |
CHARS[ '×' ] = '215' # × | |
#Unicode 00D8 | |
CHARS[ '216' ] = 1 # Ø | |
CHARS[ 'Ø' ] = '216' # Ø | |
#Unicode 00D9 | |
CHARS[ '217' ] = 1 # Ù | |
CHARS[ 'Ù' ] = '217' # Ù | |
#Unicode 00DA | |
CHARS[ '218' ] = 1 # Ú | |
CHARS[ 'Ú' ] = '218' # Ú | |
#Unicode 00DB | |
CHARS[ '219' ] = 1 # Û | |
CHARS[ 'Û' ] = '219' # Û | |
#Unicode 00DC | |
CHARS[ '220' ] = 1 # Ü | |
CHARS[ 'Ü' ] = '220' # Ü | |
#Unicode 00DD | |
CHARS[ '221' ] = 1 # Ý | |
CHARS[ 'Ý' ] = '221' # Ý | |
#Unicode 00DE | |
#CHARS[ '222' ] = 1 # Þ | |
CHARS[ 'Þ' ] = '222' # Þ | |
#Unicode 00DF | |
CHARS[ '223' ] = 1 # ß | |
CHARS[ 'ß' ] = '223' # ß | |
#Unicode 00E0 | |
CHARS[ '224' ] = 1 # à | |
CHARS[ 'à' ] = '224' # à | |
#Unicode 00E1 | |
CHARS[ '225' ] = 1 # á | |
CHARS[ 'á' ] = '224' # á | |
#Unicode 00E2 | |
CHARS[ '226' ] = 1 # â | |
CHARS[ 'â' ] = '226' # â | |
#Unicode 00E3 | |
CHARS[ '227' ] = 1 # ã | |
CHARS[ 'ã' ] = '227' # ã | |
#Unicode 00E4 | |
CHARS[ '228' ] = 1 # ä | |
CHARS[ 'ä' ] = '228' # ä | |
#Unicode 00E5 | |
CHARS[ '229' ] = 1 # å | |
CHARS[ 'å' ] = '229' # å | |
#Unicode 00E6 | |
CHARS[ '230' ] = 1 # æ | |
CHARS[ 'æ' ] = '230' # æ | |
#Unicode 00E7 | |
CHARS[ '231' ] = 1 # ç | |
CHARS[ 'ç' ] = '231' # ç | |
#Unicode 00E8 | |
CHARS[ '232' ] = 1 # è | |
CHARS[ 'è' ] = '232' # è | |
#Unicode 00E9 | |
CHARS[ '233' ] = 1 # é | |
CHARS[ 'é' ] = '233' # é | |
#Unicode 00EA | |
CHARS[ '234' ] = 1 # ê | |
CHARS[ 'ê' ] = '234' # ê | |
#Unicode 00EB | |
CHARS[ '235' ] = 1 # ë | |
CHARS[ 'ë' ] = '235' # ë | |
#Unicode 00EC | |
CHARS[ '236' ] = 1 # ì | |
CHARS[ 'ì' ] = '236' # ì | |
#Unicode 00ED | |
CHARS[ '237' ] = 1 # í | |
CHARS[ 'í' ] = '237' # í | |
#Unicode 00EE | |
CHARS[ '238' ] = 1 # î | |
CHARS[ 'î' ] = '238' # î | |
#Unicode 00EF | |
CHARS[ '239' ] = 1 # ï | |
CHARS[ 'ï' ] = '239' # ï | |
#Unicode 00F0 | |
CHARS[ '240' ] = 1 # ð | |
CHARS[ 'ð' ] = '240' # ð | |
#Unicode 00F1 | |
CHARS[ '241' ] = 1 # ñ | |
CHARS[ 'ñ' ] = '241' # ñ | |
#Unicode 00F2 | |
CHARS[ '242' ] = 1 # ò | |
CHARS[ 'ò' ] = '242' # ò | |
#Unicode 00F3 | |
CHARS[ '243' ] = 1 # ó | |
CHARS[ 'ó' ] = '243' # ó | |
#Unicode 00F4 | |
CHARS[ '244' ] = 1 # ô | |
CHARS[ 'ô' ] = '244' # ô | |
#Unicode 00F5 | |
CHARS[ '245' ] = 1 # õ | |
CHARS[ 'õ' ] = '245' # õ | |
#Unicode 00F6 | |
CHARS[ '246' ] = 1 # ö | |
CHARS[ 'ö' ] = '246' # ö | |
#Unicode 00F7 | |
CHARS[ '247' ] = 1 # ÷ | |
CHARS[ '÷' ] = '247' # ÷ | |
#Unicode 00F8 | |
CHARS[ '248' ] = 1 # ø | |
CHARS[ 'ø' ] = '248' # ø | |
#Unicode 00F9 | |
CHARS[ '249' ] = 1 # ù | |
CHARS[ 'ø' ] = '249' # ø | |
#Unicode 00FA | |
CHARS[ '250' ] = 1 # ú | |
CHARS[ 'ú' ] = '250' # ú | |
#Unicode 00FB | |
CHARS[ '251' ] = 1 # û | |
CHARS[ 'û' ] = '251' # û | |
#Unicode 00FC | |
CHARS[ '252' ] = 1 # ü | |
CHARS[ 'ü' ] = '252' # ü | |
#Unicode 00FD | |
CHARS[ '253' ] = 1 # ý | |
CHARS[ 'ý' ] = '253' # ý | |
#Unicode 00FE | |
CHARS[ '254' ] = 1 # þ | |
CHARS[ 'þ' ] = '254' # þ | |
#Unicode 00FF | |
CHARS[ '255' ] = 1 # ÿ | |
CHARS[ 'ÿ' ] = '255' # ÿ | |
#Unicode Punctuation | |
#Unicode 2010 | |
CHARS[ '8208' ] = 1 # ‐ | |
CHARS[ '‐' ] = '8208' # ‐ | |
#Unicode 2011 | |
CHARS[ '8209' ] = 1 # ‑ | |
CHARS[ '‑' ] = '8209' # ‑ | |
#Unicode 2012 | |
CHARS[ '8210' ] = 1 # ‒ | |
CHARS[ '‒' ] = '8210' # ‒ | |
#Unicode 2013 | |
CHARS[ '8211' ] = 1 # – | |
CHARS[ '–' ] = '8211' # – | |
#Unicode 2014 | |
CHARS[ '8212' ] = 1 # — | |
CHARS[ '—' ] = '8212' # — | |
#Unicode 2015 | |
CHARS[ '8213' ] = 1 # ― | |
CHARS[ '―' ] = '8213' # ― | |
#Unicode 2016 | |
CHARS[ '8214' ] = 1 # ‖ | |
CHARS[ '‖' ] = '8214' # ‖ | |
#Unicode 2017 | |
CHARS[ '8215' ] = 1 # ‗ | |
CHARS[ '‗' ] = '8215' # ‗ | |
#Unicode 2018 | |
CHARS[ '8216' ] = 1 # ‘ | |
CHARS[ '‘' ] = '8216' # ‘ | |
#Unicode 2019 | |
CHARS[ '8217' ] = 1 # ’ | |
CHARS[ '’' ] = '8217' # ’ | |
#Unicode 201A | |
CHARS[ '8218' ] = 1 # ‚ | |
CHARS[ '‚' ] = '8218' # ‚ | |
#Unicode 201B | |
CHARS[ '8219' ] = 1 # ‛ | |
CHARS[ '‛' ] = '8219' # ‛ | |
#Unicode 201C | |
CHARS[ '8220' ] = 1 # “ | |
CHARS[ '“' ] = '8220' # “ | |
#Unicode 201D | |
CHARS[ '8221' ] = 1 # ” | |
CHARS[ '”' ] = '8221' # ” | |
#Unicode 201E | |
CHARS[ '8222' ] = 1 # „ | |
CHARS[ '„' ] = '8222' # „ | |
#Unicode 201F | |
CHARS[ '8223' ] = 1 # ‟ | |
CHARS[ '‟' ] = '8223' # ‟ | |
#Unicode 2020 | |
CHARS[ '8224' ] = 1 # † | |
CHARS[ '†' ] = '8224' # † | |
#Unicode 2021 | |
CHARS[ '8225' ] = 1 # ‡ | |
CHARS[ '‡' ] = '8225' # ‡ | |
#Unicode 2022 | |
CHARS[ '8226' ] = 1 # • | |
CHARS[ '•' ] = '8226' # • | |
#Unicode 2023 | |
CHARS[ '8227' ] = 1 # ‣ | |
CHARS[ '‣' ] = '8227' # ‣ | |
#Unicode 2024 | |
CHARS[ '8228' ] = 1 # ․ | |
CHARS[ '․' ] = '8228' # ․ | |
#Unicode 2025 | |
CHARS[ '8229' ] = 1 # ‥ | |
CHARS[ '‥' ] = '8229' # ‥ | |
#Unicode 2026 | |
CHARS[ '8230' ] = 1 # … | |
CHARS[ '…' ] = '8230' # … | |
#Unicode 2027 | |
CHARS[ '8231' ] = 1 # ‧ | |
CHARS[ '‧' ] = '8231' # ‧ | |
#Unicode 2028 | |
#CHARS[ '8232' ] = 1 # | |
#Unicode 2029 | |
#CHARS[ '8233' ] = 1 # | |
#Unicode 202A | |
#CHARS[ '8234' ] = 1 # | |
#Unicode 202B | |
#CHARS[ '8235' ] = 1 # | |
#Unicode 202C | |
#CHARS[ '8236' ] = 1 # | |
#Unicode 202D | |
#CHARS[ '8237' ] = 1 # | |
#Unicode 202E | |
#CHARS[ '8238' ] = 1 # | |
#Unicode 202F | |
#CHARS[ '8239' ] = 1 # | |
#Unicode 2030 | |
CHARS[ '8240' ] = 1 # ‰ | |
CHARS[ '‰' ] = '8240' # ‰ | |
#Unicode 2031 | |
CHARS[ '8241' ] = 1 # ‱ | |
CHARS[ '‱' ] = '8241' # ‱ | |
#Unicode 2032 | |
CHARS[ '8242' ] = 1 # ′ | |
CHARS[ '′' ] = '8242' # ′ | |
#Unicode 2033 | |
CHARS[ '8243' ] = 1 # ″ | |
CHARS[ '″' ] = '8243' # ″ | |
#Unicode 2034 | |
CHARS[ '8244' ] = 1 # ‴ | |
CHARS[ '‴' ] = '8244' # ‴ | |
#Unicode 2035 | |
CHARS[ '8245' ] = 1 # ‵ | |
CHARS[ '‵' ] = '8245' # ‵ | |
#Unicode 2036 | |
CHARS[ '8246' ] = 1 # ‶ | |
CHARS[ '‶' ] = '8246' # ‶ | |
#ligatures | |
#CHARS[ '57359' ] = 'Ch' # Ch | |
#CHARS[ 'Ch' ] = 'Ch' # Ch | |
#CHARS[ '57413' ] = 'On' # On | |
#CHARS[ 'On' ] = 'On' # On | |
#CHARS[ '57437' ] = 'Th' # Th | |
#CHARS[ 'Th' ] = 'Th' # Th | |
#CHARS[ '57455' ] = 'Wh' # Wh | |
#CHARS[ 'Wh' ] = 'Wh' # Wh | |
#CHARS[ '57559' ] = 'bb' # bb | |
#CHARS[ 'bb' ] = 'bb' # bb | |
#CHARS[ '57563' ] = 'be' # be | |
#CHARS[ 'be' ] = 'be' # be | |
#CHARS[ '57573' ] = 'bi' # bi | |
#CHARS[ 'bi' ] = 'bi' # bi | |
#CHARS[ '57577' ] = 'bl' # bl | |
#CHARS[ 'bl' ] = 'bl' # bl | |
#CHARS[ '57580' ] = 'br' # br | |
#CHARS[ 'br' ] = 'br' # br | |
#CHARS[ '57583' ] = 'bs' # bs | |
#CHARS[ 'bs' ] = 'bs' # bs | |
#CHARS[ '57584' ] = 'bu' # bu | |
#CHARS[ '57584' ] = 'bu' # bu | |
#CHARS[ '57588' ] = 'by' # by | |
#CHARS[ 'by' ] = 'by' # by | |
#CHARS[ '57597' ] = 'ch' # ch | |
#CHARS[ 'ch' ] = 'ch' # ch | |
#CHARS[ '57598' ] = 'ck' # ck | |
#CHARS[ 'ck' ] = 'ck' # ck | |
#CHARS[ '57599' ] = 'ct' # ct | |
#CHARS[ 'ct' ] = 'ct' # ct | |
#CHARS[ '57650' ] = 'dd' # dd | |
#CHARS[ 'dd' ] = 'dd' # dd | |
#CHARS[ '57656' ] = 'de' # de | |
#CHARS[ 'de' ] = 'de' # de | |
#CHARS[ '57657' ] = 'di' # di | |
#CHARS[ 'di' ] = 'di' # di | |
#CHARS[ '57661' ] = 'dr' # dr | |
#CHARS[ 'dr' ] = 'dr' # dr | |
#CHARS[ '57662' ] = 'ds' # ds | |
#CHARS[ 'ds' ] = 'ds' # ds | |
#CHARS[ '57663' ] = 'du' # du | |
#CHARS[ 'du' ] = 'du' # du | |
#CHARS[ '57804' ] = 'fb' # fb | |
#CHARS[ 'fb' ] = 'fb' # fb | |
#CHARS[ '57805' ] = 'fe' # fe | |
#CHARS[ 'fe' ] = 'fe' # fe | |
#CHARS[ '57820' ] = 'ffr' # ffr | |
#CHARS[ 'ffr' ] = 'ffr' # ffr | |
#CHARS[ '57821' ] = 'fft' # fft | |
#CHARS[ 'fft' ] = 'fft' # fft | |
#CHARS[ '57822' ] = 'fh' # fh | |
#CHARS[ 'fh' ] = 'fh' # fh | |
#CHARS[ '57826' ] = 'fj' # fj | |
#CHARS[ 'fj' ] = 'fj' # fj | |
#CHARS[ '57831' ] = 'fr' # fr | |
#CHARS[ 'fr' ] = 'fr' # fr | |
#CHARS[ '57833' ] = 'ft' # ft | |
#CHARS[ 'ft' ] = 'ft' # ft | |
#CHARS[ '57989' ] = 'lb' # lb | |
#CHARS[ 'lb' ] = 'lb' # lb | |
#CHARS[ '57990' ] = 'lf' # lf | |
#CHARS[ 'lf' ] = 'lf' # lf | |
#CHARS[ '57991' ] = 'lh' # lh | |
#CHARS[ 'lh' ] = 'lh' # lh | |
#CHARS[ '57992' ] = 'lk' # lk | |
#CHARS[ 'lk' ] = 'lk' # lk | |
#CHARS[ '57993' ] = 'll' # ll | |
#CHARS[ 'll' ] = 'll' # ll | |
#CHARS[ '58103' ] = 'ol' # of | |
#CHARS[ 'ol' ] = 'ol' # of | |
#CHARS[ '58110' ] = 'off' # off | |
#CHARS[ 'off' ] = 'off' # off | |
#CHARS[ '58111' ] = 'offe' # offe | |
#CHARS[ 'offe' ] = 'offe' # offe | |
#CHARS[ '58112' ] = 'offi' # offi | |
#CHARS[ 'offi' ] = 'offi' # offi | |
#CHARS[ '58113' ] = 'ofi' # ofi | |
#CHARS[ 'ofi' ] = 'ofi' # ofi | |
#CHARS[ '58117' ] = 'ol' # ol | |
#CHARS[ 'ol' ] = 'ol' # ol | |
#CHARS[ '58118' ] = 'oo' # oo | |
#CHARS[ 'oo' ] = 'oo' # oo | |
#CHARS[ '58245' ] = 'pe' # pe | |
#CHARS[ 'pe' ] = 'pe' # pe | |
#CHARS[ '58254' ] = 'pl' # pl | |
#CHARS[ 'pl' ] = 'pl' # pl | |
#CHARS[ '58255' ] = 'pp' # pp | |
#CHARS[ 'pp' ] = 'pp' # pp | |
#CHARS[ '58258' ] = 'pr' # pr | |
#CHARS[ 'pr' ] = 'pr' # pr | |
#CHARS[ '58260' ] = 'pt' # pt | |
#CHARS[ 'pt' ] = 'pt' # pt | |
#CHARS[ '58291' ] = 're' # re | |
#CHARS[ 're' ] = 're' # re | |
#CHARS[ '58301' ] = 'rf' # rf | |
#CHARS[ 'rf' ] = 'rf' # rf | |
#CHARS[ '58302' ] = 'rs' # rs | |
#CHARS[ 'rs' ] = 'rs' # rs | |
#CHARS[ '58304' ] = 'rst' # rst | |
#CHARS[ 'rst' ] = 'rst' # rst | |
#CHARS[ '58306' ] = 'rt' # rt | |
#CHARS[ 'rt' ] = 'rt' # rt | |
#CHARS[ '58342' ] = 'sfe' # sfe | |
#CHARS[ 'sfe' ] = 'sfe' # sfe | |
#CHARS[ '58343' ] = 'sh' # sh | |
#CHARS[ 'sh' ] = 'sh' # sh | |
#CHARS[ '58346' ] = 'sk' # sk | |
#CHARS[ 'sk' ] = 'sk' # sk | |
#CHARS[ '58349' ] = 'sp' # sp | |
#CHARS[ 'sp' ] = 'sp' # sp | |
#CHARS[ '58354' ] = 'ss' # ss | |
#CHARS[ 'ss' ] = 'ss' # ss | |
#CHARS[ '58412' ] = 'te' # te | |
#CHARS[ 'te' ] = 'te' # te | |
#CHARS[ '58421' ] = 'th' # th | |
#CHARS[ 'th' ] = 'th' # th | |
#CHARS[ '58429' ] = 'tl' # tl | |
#CHARS[ 'tl' ] = 'tl' # tl | |
#CHARS[ '58430' ] = 'tt' # tt | |
#CHARS[ 'tt' ] = 'tt' # tt | |
#CHARS[ '58576' ] = 'wh' # wh | |
#CHARS[ 'wh' ] = 'wh' # wh | |
#CHARS[ '58611' ] = 'yg' # yg | |
#CHARS[ 'yg' ] = 'yg' # yg | |
#CHARS[ '64256' ] = 'ff' # ff ff | |
#CHARS[ 'ff' ] = 'ff' # ff ff | |
#CHARS[ '64257' ] = 'fi' # fi | |
#CHARS[ 'fi' ] = 'fi' # fi | |
#CHARS[ '64258' ] = 'fl' # fl | |
#CHARS[ 'fl' ] = 'fl' # fl | |
#CHARS[ '64259' ] = 'ffi' # ffi ffi | |
#CHARS[ 'ffi' ] = 'ffi' # ffi ffi | |
#CHARS[ '64260' ] = 'ffl' # ffl ffl | |
#CHARS[ 'ffl' ] = 'ffl' # ffl ffl | |
#CHARS[ '64262' ] = 'st' # st st | |
#CHARS[ 'st' ] = 'st' # st st |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment