Last active
August 29, 2015 14:04
-
-
Save diverted247/ea07f13cabe5460ccb5d to your computer and use it in GitHub Desktop.
Character Whitelist
This file contains 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: utf_8 -*- | |
#use: from characters import CHARS | |
CHARS = {} | |
CHARS[ 32 ] = 1 # | |
CHARS[ 33 ] = 1 # ! | |
CHARS[ 34 ] = 1 # " | |
CHARS[ 35 ] = 1 # # | |
CHARS[ 36 ] = 1 # $ | |
CHARS[ 37 ] = 1 # % | |
CHARS[ 38 ] = 1 # & | |
CHARS[ 39 ] = 1 # ' | |
CHARS[ 40 ] = 1 # ( | |
CHARS[ 41 ] = 1 # ) | |
CHARS[ 42 ] = 1 # * | |
CHARS[ 43 ] = 1 # + | |
CHARS[ 44 ] = 1 # , | |
CHARS[ 45 ] = 1 # - | |
CHARS[ 46 ] = 1 # . | |
CHARS[ 47 ] = 1 # / | |
CHARS[ 48 ] = 1 # 0 | |
CHARS[ 49 ] = 1 # 1 | |
CHARS[ 50 ] = 1 # 2 | |
CHARS[ 51 ] = 1 # 3 | |
CHARS[ 52 ] = 1 # 4 | |
CHARS[ 53 ] = 1 # 5 | |
CHARS[ 54 ] = 1 # 6 | |
CHARS[ 55 ] = 1 # 7 | |
CHARS[ 56 ] = 1 # 8 | |
CHARS[ 57 ] = 1 # 9 | |
CHARS[ 58 ] = 1 # : | |
CHARS[ 59 ] = 1 # ; | |
CHARS[ 60 ] = 1 # < | |
CHARS[ 61 ] = 1 # = | |
CHARS[ 62 ] = 1 # > | |
CHARS[ 63 ] = 1 # ? | |
CHARS[ 64 ] = 1 # @ | |
CHARS[ 65 ] = 1 # A A | |
CHARS[ 66 ] = 1 # B B | |
CHARS[ 67 ] = 1 # C C | |
CHARS[ 68 ] = 1 # D D | |
CHARS[ 69 ] = 1 # E E | |
CHARS[ 70 ] = 1 # F F | |
CHARS[ 71 ] = 1 # G G | |
CHARS[ 72 ] = 1 # H H | |
CHARS[ 73 ] = 1 # I I | |
CHARS[ 74 ] = 1 # J J | |
CHARS[ 75 ] = 1 # K K | |
CHARS[ 76 ] = 1 # L L | |
CHARS[ 77 ] = 1 # M M | |
CHARS[ 78 ] = 1 # N N | |
CHARS[ 79 ] = 1 # O O | |
CHARS[ 80 ] = 1 # P P | |
CHARS[ 81 ] = 1 # Q Q | |
CHARS[ 82 ] = 1 # R R | |
CHARS[ 83 ] = 1 # S S | |
CHARS[ 84 ] = 1 # T T | |
CHARS[ 85 ] = 1 # U U | |
CHARS[ 86 ] = 1 # V V | |
CHARS[ 87 ] = 1 # W W | |
CHARS[ 88 ] = 1 # X X | |
CHARS[ 89 ] = 1 # Y Y | |
CHARS[ 90 ] = 1 # Z Z | |
CHARS[ 91 ] = 1 # [ | |
CHARS[ 92 ] = 1 # \ | |
CHARS[ 93 ] = 1 # ] | |
CHARS[ 94 ] = 1 # ^ | |
CHARS[ 95 ] = 1 # _ | |
CHARS[ 96 ] = 1 # ` | |
CHARS[ 97 ] = 1 # a a | |
CHARS[ 98 ] = 1 # b b | |
CHARS[ 99 ] = 1 # c c | |
CHARS[ 100 ] = 1 # d d | |
CHARS[ 101 ] = 1 # e e | |
CHARS[ 102 ] = 1 # f f | |
CHARS[ 103 ] = 1 # g g | |
CHARS[ 104 ] = 1 # h h | |
CHARS[ 105 ] = 1 # i i | |
CHARS[ 106 ] = 1 # j j | |
CHARS[ 107 ] = 1 # k k | |
CHARS[ 108 ] = 1 # l l | |
CHARS[ 109 ] = 1 # m m | |
CHARS[ 110 ] = 1 # n n | |
CHARS[ 111 ] = 1 # o o | |
CHARS[ 112 ] = 1 # p p | |
CHARS[ 113 ] = 1 # q q | |
CHARS[ 114 ] = 1 # r r | |
CHARS[ 115 ] = 1 # s s | |
CHARS[ 116 ] = 1 # t t | |
CHARS[ 117 ] = 1 # u u | |
CHARS[ 118 ] = 1 # v v | |
CHARS[ 119 ] = 1 # w w | |
CHARS[ 120 ] = 1 # x x | |
CHARS[ 121 ] = 1 # y y | |
CHARS[ 122 ] = 1 # z z | |
CHARS[ 123 ] = 1 # { | |
CHARS[ 124 ] = 1 # | | |
CHARS[ 125 ] = 1 # } | |
CHARS[ 126 ] = 1 # ~ | |
CHARS[ 161 ] = 1 # ¡ | |
CHARS[ 162 ] = 1 # ¢ | |
CHARS[ 163 ] = 1 # £ | |
CHARS[ 164 ] = 1 # ¤ | |
CHARS[ 165 ] = 1 # ¥ | |
CHARS[ 166 ] = 1 # ¦ | |
CHARS[ 167 ] = 1 # § | |
CHARS[ 168 ] = 1 # ¨ | |
CHARS[ 169 ] = 1 # © | |
CHARS[ 170 ] = 1 # ª | |
CHARS[ 171 ] = 1 # « | |
CHARS[ 172 ] = 1 # ¬ | |
CHARS[ 173 ] = 1 # | |
CHARS[ 174 ] = 1 # ® | |
CHARS[ 176 ] = 1 # ° | |
CHARS[ 177 ] = 1 # ± | |
CHARS[ 178 ] = 1 # ² | |
CHARS[ 179 ] = 1 # ³ | |
CHARS[ 180 ] = 1 # ´ | |
CHARS[ 181 ] = 1 # µ | |
CHARS[ 182 ] = 1 # ¶ | |
CHARS[ 184 ] = 1 # ¸ | |
CHARS[ 185 ] = 1 # ¹ | |
CHARS[ 186 ] = 1 # º | |
CHARS[ 187 ] = 1 # » | |
CHARS[ 188 ] = 1 # ¼ | |
CHARS[ 189 ] = 1 # ½ | |
CHARS[ 190 ] = 1 # ¾ | |
CHARS[ 191 ] = 1 # ¿ | |
CHARS[ 192 ] = 1 # À | |
CHARS[ 193 ] = 1 # Á | |
CHARS[ 194 ] = 1 # Â | |
CHARS[ 195 ] = 1 # Ã | |
CHARS[ 196 ] = 1 # Ä | |
CHARS[ 197 ] = 1 # Å | |
CHARS[ 198 ] = 1 # Æ | |
CHARS[ 199 ] = 1 # Ç | |
CHARS[ 200 ] = 1 # È | |
CHARS[ 201 ] = 1 # É | |
CHARS[ 202 ] = 1 # Ê | |
CHARS[ 203 ] = 1 # Ë | |
CHARS[ 204 ] = 1 # Ì | |
CHARS[ 205 ] = 1 # Í | |
CHARS[ 206 ] = 1 # Î | |
CHARS[ 207 ] = 1 # Ï | |
CHARS[ 208 ] = 1 # Ð | |
CHARS[ 209 ] = 1 # Ñ | |
CHARS[ 210 ] = 1 # Ò | |
CHARS[ 211 ] = 1 # Ó | |
CHARS[ 213 ] = 1 # Õ | |
CHARS[ 214 ] = 1 # Ö | |
CHARS[ 215 ] = 1 # × | |
CHARS[ 216 ] = 1 # Ø | |
CHARS[ 217 ] = 1 # Ù | |
CHARS[ 218 ] = 1 # Ú | |
CHARS[ 219 ] = 1 # Û | |
CHARS[ 220 ] = 1 # Ü | |
CHARS[ 221 ] = 1 # Ý | |
CHARS[ 223 ] = 1 # ß | |
CHARS[ 224 ] = 1 # à | |
CHARS[ 225 ] = 1 # á | |
CHARS[ 226 ] = 1 # â | |
CHARS[ 227 ] = 1 # ã | |
CHARS[ 228 ] = 1 # ä | |
CHARS[ 229 ] = 1 # å | |
CHARS[ 230 ] = 1 # æ | |
CHARS[ 231 ] = 1 # ç | |
CHARS[ 232 ] = 1 # è | |
CHARS[ 233 ] = 1 # é | |
CHARS[ 234 ] = 1 # ê | |
CHARS[ 235 ] = 1 # ë | |
CHARS[ 236 ] = 1 # ì | |
CHARS[ 237 ] = 1 # í | |
CHARS[ 238 ] = 1 # î | |
CHARS[ 239 ] = 1 # ï | |
CHARS[ 240 ] = 1 # ð | |
CHARS[ 241 ] = 1 # ñ | |
CHARS[ 242 ] = 1 # ò | |
CHARS[ 243 ] = 1 # ó | |
CHARS[ 244 ] = 1 # ô | |
CHARS[ 245 ] = 1 # õ | |
CHARS[ 246 ] = 1 # ö | |
CHARS[ 247 ] = 1 # ÷ | |
CHARS[ 248 ] = 1 # ø | |
CHARS[ 249 ] = 1 # ù | |
CHARS[ 250 ] = 1 # ú | |
CHARS[ 251 ] = 1 # û | |
CHARS[ 252 ] = 1 # ü | |
CHARS[ 253 ] = 1 # ý | |
CHARS[ 254 ] = 1 # þ | |
CHARS[ 255 ] = 1 # ÿ | |
CHARS[ 338 ] = 1 # Œ | |
CHARS[ 339 ] = 1 # œ | |
CHARS[ 352 ] = 1 # Š | |
CHARS[ 353 ] = 1 # š | |
CHARS[ 376 ] = 1 # Ÿ | |
CHARS[ 382 ] = 1 # ž | |
CHARS[ 402 ] = 1 # ƒ | |
CHARS[ 710 ] = 1 # ˆ | |
CHARS[ 732 ] = 1 # ˜ | |
CHARS[ 8211 ] = 1 # – | |
CHARS[ 8212 ] = 1 # — | |
CHARS[ 8216 ] = 1 # ‘ | |
CHARS[ 8217 ] = 1 # ’ | |
CHARS[ 8220 ] = 1 # “ | |
CHARS[ 8221 ] = 1 # ” | |
CHARS[ 8222 ] = 1 # „ | |
CHARS[ 8224 ] = 1 # † | |
CHARS[ 8225 ] = 1 # ‡ | |
CHARS[ 8226 ] = 1 # • | |
CHARS[ 8230 ] = 1 # … | |
CHARS[ 8240 ] = 1 # ‰ | |
CHARS[ 8249 ] = 1 # ‹ | |
CHARS[ 8250 ] = 1 # › | |
CHARS[ 8364 ] = 1 # € | |
CHARS[ 8482 ] = 1 # ™ | |
#ligatures | |
CHARS[ 57359 ] = 1 # C_h | |
CHARS[ 57413 ] = 1 # O_n | |
CHARS[ 57437 ] = 1 # T_h | |
CHARS[ 57455 ] = 1 # W_h | |
CHARS[ 57559 ] = 1 # b_b | |
CHARS[ 57563 ] = 1 # b_e | |
CHARS[ 57573 ] = 1 # b_i | |
CHARS[ 57577 ] = 1 # b_l | |
CHARS[ 57580 ] = 1 # b_r | |
CHARS[ 57583 ] = 1 # b_s | |
CHARS[ 57584 ] = 1 # b_u | |
CHARS[ 57588 ] = 1 # b_y | |
CHARS[ 57597 ] = 1 # c_h | |
CHARS[ 57598 ] = 1 # c_k | |
CHARS[ 57599 ] = 1 # c_t | |
CHARS[ 57650 ] = 1 # d_d | |
CHARS[ 57656 ] = 1 # d_e | |
CHARS[ 57657 ] = 1 # d_i | |
CHARS[ 57661 ] = 1 # d_r | |
CHARS[ 57662 ] = 1 # d_s | |
CHARS[ 57663 ] = 1 # d_u | |
CHARS[ 57804 ] = 1 # f_b | |
CHARS[ 57805 ] = 1 # f_e | |
CHARS[ 57820 ] = 1 # f_f_r | |
CHARS[ 57821 ] = 1 # f_f_t | |
CHARS[ 57822 ] = 1 # f_h | |
CHARS[ 57826 ] = 1 # f_j | |
CHARS[ 57831 ] = 1 # f_r | |
CHARS[ 57833 ] = 1 # f_t | |
CHARS[ 57989 ] = 1 # l_b | |
CHARS[ 57990 ] = 1 # l_f | |
CHARS[ 57991 ] = 1 # l_h | |
CHARS[ 57992 ] = 1 # l_k | |
CHARS[ 57993 ] = 1 # l_l | |
CHARS[ 58103 ] = 1 # o_f | |
CHARS[ 58110 ] = 1 # o_f_f | |
CHARS[ 58111 ] = 1 # o_f_f_e | |
CHARS[ 58112 ] = 1 # o_f_f_i | |
CHARS[ 58113 ] = 1 # o_f_i | |
CHARS[ 58117 ] = 1 # o_l | |
CHARS[ 58118 ] = 1 # o_o | |
CHARS[ 58245 ] = 1 # p_e | |
CHARS[ 58254 ] = 1 # p_l | |
CHARS[ 58255 ] = 1 # p_p | |
CHARS[ 58258 ] = 1 # p_r | |
CHARS[ 58260 ] = 1 # p_t | |
CHARS[ 58291 ] = 1 # r_e | |
CHARS[ 58301 ] = 1 # r_f | |
CHARS[ 58302 ] = 1 # r_s | |
CHARS[ 58304 ] = 1 # r_s_t | |
CHARS[ 58306 ] = 1 # r_t | |
CHARS[ 58342 ] = 1 # s_f_e | |
CHARS[ 58343 ] = 1 # s_h | |
CHARS[ 58346 ] = 1 # s_k | |
CHARS[ 58349 ] = 1 # s_p | |
CHARS[ 58354 ] = 1 # s_s | |
CHARS[ 58412 ] = 1 # t_e | |
CHARS[ 58421 ] = 1 # t_h | |
CHARS[ 58429 ] = 1 # t_l | |
CHARS[ 58430 ] = 1 # t_t | |
CHARS[ 58576 ] = 1 # w_h | |
CHARS[ 58611 ] = 1 # y_g | |
CHARS[ 64256 ] = 1 # f_f ff | |
CHARS[ 64257 ] = 1 # fi | |
CHARS[ 64258 ] = 1 # fl | |
CHARS[ 64259 ] = 1 # f_f_i ffi | |
CHARS[ 64260 ] = 1 # f_f_l ffl | |
CHARS[ 64262 ] = 1 # s_t st |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment