Guido van Rossum | 0229bf6 | 2000-03-10 23:17:24 +0000 | [diff] [blame] | 1 | """ Encoding Aliases Support |
| 2 | |
| 3 | This module is used by the encodings package search function to |
| 4 | map encodings names to module names. |
| 5 | |
| 6 | Note that the search function converts the encoding names to lower |
Marc-André Lemburg | a0af63b | 2002-02-11 17:43:46 +0000 | [diff] [blame^] | 7 | case and replaces hyphens with underscores *before* performing the |
| 8 | lookup. |
Marc-André Lemburg | 462004e | 2002-02-10 21:36:20 +0000 | [diff] [blame] | 9 | |
| 10 | Contents: |
| 11 | |
| 12 | The following aliases dictionary contains mappings of all IANA |
| 13 | character set names for which the Python core library provides |
| 14 | codecs. In addition to these, a few Python specific codec |
| 15 | aliases have also been added. |
| 16 | |
| 17 | About the CJK codec aliases: |
| 18 | |
| 19 | The codecs for these encodings are not distributed with the |
| 20 | Python core, but are included here for reference, since the |
| 21 | locale module relies on having these aliases available. |
Guido van Rossum | 0229bf6 | 2000-03-10 23:17:24 +0000 | [diff] [blame] | 22 | |
| 23 | """ |
| 24 | aliases = { |
| 25 | |
Marc-André Lemburg | 462004e | 2002-02-10 21:36:20 +0000 | [diff] [blame] | 26 | # ascii codec |
| 27 | '646' : 'ascii', |
Marc-André Lemburg | a0af63b | 2002-02-11 17:43:46 +0000 | [diff] [blame^] | 28 | 'ansi_x3.4_1968' : 'ascii', |
| 29 | 'ansi_x3.4_1986' : 'ascii', |
Marc-André Lemburg | 462004e | 2002-02-10 21:36:20 +0000 | [diff] [blame] | 30 | 'cp367' : 'ascii', |
| 31 | 'csascii' : 'ascii', |
| 32 | 'ibm367' : 'ascii', |
| 33 | 'iso646_us' : 'ascii', |
Marc-André Lemburg | a0af63b | 2002-02-11 17:43:46 +0000 | [diff] [blame^] | 34 | 'iso_646.irv:1991' : 'ascii', |
Marc-André Lemburg | 462004e | 2002-02-10 21:36:20 +0000 | [diff] [blame] | 35 | 'iso_ir_6' : 'ascii', |
| 36 | 'us' : 'ascii', |
| 37 | 'us_ascii' : 'ascii', |
Guido van Rossum | 0229bf6 | 2000-03-10 23:17:24 +0000 | [diff] [blame] | 38 | |
Marc-André Lemburg | 462004e | 2002-02-10 21:36:20 +0000 | [diff] [blame] | 39 | # base64_codec codec |
| 40 | 'base64' : 'base64_codec', |
| 41 | 'base_64' : 'base64_codec', |
Guido van Rossum | 0229bf6 | 2000-03-10 23:17:24 +0000 | [diff] [blame] | 42 | |
Marc-André Lemburg | 462004e | 2002-02-10 21:36:20 +0000 | [diff] [blame] | 43 | # cp037 codec |
| 44 | 'csibm037' : 'cp037', |
| 45 | 'ebcdic_cp_ca' : 'cp037', |
| 46 | 'ebcdic_cp_nl' : 'cp037', |
| 47 | 'ebcdic_cp_us' : 'cp037', |
| 48 | 'ebcdic_cp_wt' : 'cp037', |
| 49 | 'ibm037' : 'cp037', |
| 50 | 'ibm039' : 'cp037', |
Guido van Rossum | 0229bf6 | 2000-03-10 23:17:24 +0000 | [diff] [blame] | 51 | |
Marc-André Lemburg | 462004e | 2002-02-10 21:36:20 +0000 | [diff] [blame] | 52 | # cp1026 codec |
| 53 | 'csibm1026' : 'cp1026', |
| 54 | 'ibm1026' : 'cp1026', |
Guido van Rossum | 0229bf6 | 2000-03-10 23:17:24 +0000 | [diff] [blame] | 55 | |
Marc-André Lemburg | 462004e | 2002-02-10 21:36:20 +0000 | [diff] [blame] | 56 | # cp1140 codec |
| 57 | 'ibm1140' : 'cp1140', |
Mark Hammond | 194bfb2 | 2001-06-04 02:31:23 +0000 | [diff] [blame] | 58 | |
Marc-André Lemburg | 462004e | 2002-02-10 21:36:20 +0000 | [diff] [blame] | 59 | # cp1250 codec |
| 60 | 'windows_1250' : 'cp1250', |
Guido van Rossum | 9e896b3 | 2000-04-05 20:11:21 +0000 | [diff] [blame] | 61 | |
Marc-André Lemburg | 462004e | 2002-02-10 21:36:20 +0000 | [diff] [blame] | 62 | # cp1251 codec |
| 63 | 'windows_1251' : 'cp1251', |
Marc-André Lemburg | 4fd73f0 | 2000-06-07 09:12:30 +0000 | [diff] [blame] | 64 | |
Marc-André Lemburg | 462004e | 2002-02-10 21:36:20 +0000 | [diff] [blame] | 65 | # cp1252 codec |
| 66 | 'windows_1252' : 'cp1252', |
Marc-André Lemburg | 4fd73f0 | 2000-06-07 09:12:30 +0000 | [diff] [blame] | 67 | |
Marc-André Lemburg | 462004e | 2002-02-10 21:36:20 +0000 | [diff] [blame] | 68 | # cp1253 codec |
| 69 | 'windows_1253' : 'cp1253', |
| 70 | |
| 71 | # cp1254 codec |
| 72 | 'windows_1254' : 'cp1254', |
| 73 | |
| 74 | # cp1255 codec |
| 75 | 'windows_1255' : 'cp1255', |
| 76 | |
| 77 | # cp1256 codec |
| 78 | 'windows_1256' : 'cp1256', |
| 79 | |
| 80 | # cp1257 codec |
| 81 | 'windows_1257' : 'cp1257', |
| 82 | |
| 83 | # cp1258 codec |
| 84 | 'windows_1258' : 'cp1258', |
| 85 | |
| 86 | # cp424 codec |
| 87 | 'csibm424' : 'cp424', |
| 88 | 'ebcdic_cp_he' : 'cp424', |
| 89 | 'ibm424' : 'cp424', |
| 90 | |
| 91 | # cp437 codec |
| 92 | '437' : 'cp437', |
| 93 | 'cspc8codepage437' : 'cp437', |
| 94 | 'ibm437' : 'cp437', |
| 95 | |
| 96 | # cp500 codec |
| 97 | 'csibm500' : 'cp500', |
| 98 | 'ebcdic_cp_be' : 'cp500', |
| 99 | 'ebcdic_cp_ch' : 'cp500', |
| 100 | 'ibm500' : 'cp500', |
| 101 | |
| 102 | # cp775 codec |
| 103 | 'cspc775baltic' : 'cp775', |
| 104 | 'ibm775' : 'cp775', |
| 105 | |
| 106 | # cp850 codec |
| 107 | '850' : 'cp850', |
| 108 | 'cspc850multilingual' : 'cp850', |
| 109 | 'ibm850' : 'cp850', |
| 110 | |
| 111 | # cp852 codec |
| 112 | '852' : 'cp852', |
| 113 | 'cspcp852' : 'cp852', |
| 114 | 'ibm852' : 'cp852', |
| 115 | |
| 116 | # cp855 codec |
| 117 | '855' : 'cp855', |
| 118 | 'csibm855' : 'cp855', |
| 119 | 'ibm855' : 'cp855', |
| 120 | |
| 121 | # cp857 codec |
| 122 | '857' : 'cp857', |
| 123 | 'csibm857' : 'cp857', |
| 124 | 'ibm857' : 'cp857', |
| 125 | |
| 126 | # cp860 codec |
| 127 | '860' : 'cp860', |
| 128 | 'csibm860' : 'cp860', |
| 129 | 'ibm860' : 'cp860', |
| 130 | |
| 131 | # cp861 codec |
| 132 | '861' : 'cp861', |
| 133 | 'cp_is' : 'cp861', |
| 134 | 'csibm861' : 'cp861', |
| 135 | 'ibm861' : 'cp861', |
| 136 | |
| 137 | # cp862 codec |
| 138 | '862' : 'cp862', |
| 139 | 'cspc862latinhebrew' : 'cp862', |
| 140 | 'ibm862' : 'cp862', |
| 141 | |
| 142 | # cp863 codec |
| 143 | '863' : 'cp863', |
| 144 | 'csibm863' : 'cp863', |
| 145 | 'ibm863' : 'cp863', |
| 146 | |
| 147 | # cp864 codec |
| 148 | 'csibm864' : 'cp864', |
| 149 | 'ibm864' : 'cp864', |
| 150 | |
| 151 | # cp865 codec |
| 152 | '865' : 'cp865', |
| 153 | 'csibm865' : 'cp865', |
| 154 | 'ibm865' : 'cp865', |
| 155 | |
| 156 | # cp866 codec |
| 157 | '866' : 'cp866', |
| 158 | 'csibm866' : 'cp866', |
| 159 | 'ibm866' : 'cp866', |
| 160 | |
| 161 | # cp869 codec |
| 162 | '869' : 'cp869', |
| 163 | 'cp_gr' : 'cp869', |
| 164 | 'csibm869' : 'cp869', |
| 165 | 'ibm869' : 'cp869', |
| 166 | |
| 167 | # hex_codec codec |
| 168 | 'hex' : 'hex_codec', |
| 169 | |
| 170 | # iso8859_10 codec |
| 171 | 'csisolatin6' : 'iso8859_10', |
| 172 | 'iso_8859_10' : 'iso8859_10', |
| 173 | 'iso_8859_10:1992' : 'iso8859_10', |
| 174 | 'iso_ir_157' : 'iso8859_10', |
| 175 | 'l6' : 'iso8859_10', |
| 176 | 'latin6' : 'iso8859_10', |
| 177 | |
| 178 | # iso8859_13 codec |
| 179 | 'iso_8859_13' : 'iso8859_13', |
| 180 | |
| 181 | # iso8859_14 codec |
| 182 | 'iso_8859_14' : 'iso8859_14', |
| 183 | 'iso_8859_14:1998' : 'iso8859_14', |
| 184 | 'iso_celtic' : 'iso8859_14', |
| 185 | 'iso_ir_199' : 'iso8859_14', |
| 186 | 'l8' : 'iso8859_14', |
| 187 | 'latin8' : 'iso8859_14', |
| 188 | |
| 189 | # iso8859_15 codec |
| 190 | 'iso_8859_15' : 'iso8859_15', |
| 191 | |
| 192 | # iso8859_2 codec |
| 193 | 'csisolatin2' : 'iso8859_2', |
| 194 | 'iso_8859_2' : 'iso8859_2', |
| 195 | 'iso_8859_2:1987' : 'iso8859_2', |
| 196 | 'iso_ir_101' : 'iso8859_2', |
| 197 | 'l2' : 'iso8859_2', |
| 198 | 'latin2' : 'iso8859_2', |
| 199 | |
| 200 | # iso8859_3 codec |
| 201 | 'csisolatin3' : 'iso8859_3', |
| 202 | 'iso_8859_3' : 'iso8859_3', |
| 203 | 'iso_8859_3:1988' : 'iso8859_3', |
| 204 | 'iso_ir_109' : 'iso8859_3', |
| 205 | 'l3' : 'iso8859_3', |
| 206 | 'latin3' : 'iso8859_3', |
| 207 | |
| 208 | # iso8859_4 codec |
| 209 | 'csisolatin4' : 'iso8859_4', |
| 210 | 'iso_8859_4' : 'iso8859_4', |
| 211 | 'iso_8859_4:1988' : 'iso8859_4', |
| 212 | 'iso_ir_110' : 'iso8859_4', |
| 213 | 'l4' : 'iso8859_4', |
| 214 | 'latin4' : 'iso8859_4', |
| 215 | |
| 216 | # iso8859_5 codec |
| 217 | 'csisolatincyrillic' : 'iso8859_5', |
| 218 | 'cyrillic' : 'iso8859_5', |
| 219 | 'iso_8859_5' : 'iso8859_5', |
| 220 | 'iso_8859_5:1988' : 'iso8859_5', |
| 221 | 'iso_ir_144' : 'iso8859_5', |
| 222 | |
| 223 | # iso8859_6 codec |
| 224 | 'arabic' : 'iso8859_6', |
| 225 | 'asmo_708' : 'iso8859_6', |
| 226 | 'csisolatinarabic' : 'iso8859_6', |
| 227 | 'ecma_114' : 'iso8859_6', |
| 228 | 'iso_8859_6' : 'iso8859_6', |
| 229 | 'iso_8859_6:1987' : 'iso8859_6', |
| 230 | 'iso_ir_127' : 'iso8859_6', |
| 231 | |
| 232 | # iso8859_7 codec |
| 233 | 'csisolatingreek' : 'iso8859_7', |
| 234 | 'ecma_118' : 'iso8859_7', |
| 235 | 'elot_928' : 'iso8859_7', |
| 236 | 'greek' : 'iso8859_7', |
| 237 | 'greek8' : 'iso8859_7', |
| 238 | 'iso_8859_7' : 'iso8859_7', |
| 239 | 'iso_8859_7:1987' : 'iso8859_7', |
| 240 | 'iso_ir_126' : 'iso8859_7', |
| 241 | |
| 242 | # iso8859_8 codec |
| 243 | 'csisolatinhebrew' : 'iso8859_8', |
| 244 | 'hebrew' : 'iso8859_8', |
| 245 | 'iso_8859_8' : 'iso8859_8', |
| 246 | 'iso_8859_8:1988' : 'iso8859_8', |
| 247 | 'iso_ir_138' : 'iso8859_8', |
| 248 | |
| 249 | # iso8859_9 codec |
| 250 | 'csisolatin5' : 'iso8859_9', |
| 251 | 'iso_8859_9' : 'iso8859_9', |
| 252 | 'iso_8859_9:1989' : 'iso8859_9', |
| 253 | 'iso_ir_148' : 'iso8859_9', |
| 254 | 'l5' : 'iso8859_9', |
| 255 | 'latin5' : 'iso8859_9', |
| 256 | |
| 257 | # jis_7 codec |
| 258 | 'csiso2022jp' : 'jis_7', |
| 259 | 'iso_2022_jp' : 'jis_7', |
| 260 | |
| 261 | # koi8_r codec |
| 262 | 'cskoi8r' : 'koi8_r', |
| 263 | |
| 264 | # latin_1 codec |
| 265 | '8859' : 'latin_1', |
| 266 | 'cp819' : 'latin_1', |
| 267 | 'csisolatin1' : 'latin_1', |
| 268 | 'ibm819' : 'latin_1', |
| 269 | 'iso8859' : 'latin_1', |
| 270 | 'iso_8859_1' : 'latin_1', |
| 271 | 'iso_8859_1:1987' : 'latin_1', |
| 272 | 'iso_ir_100' : 'latin_1', |
| 273 | 'l1' : 'latin_1', |
| 274 | 'latin' : 'latin_1', |
| 275 | 'latin1' : 'latin_1', |
| 276 | |
| 277 | # mac_cyrillic codec |
| 278 | 'maccyrillic' : 'mac_cyrillic', |
| 279 | |
| 280 | # mac_greek codec |
| 281 | 'macgreek' : 'mac_greek', |
| 282 | |
| 283 | # mac_iceland codec |
| 284 | 'maciceland' : 'mac_iceland', |
| 285 | |
| 286 | # mac_latin2 codec |
| 287 | 'maccentraleurope' : 'mac_latin2', |
| 288 | 'maclatin2' : 'mac_latin2', |
| 289 | |
| 290 | # mac_roman codec |
| 291 | 'macroman' : 'mac_roman', |
| 292 | |
| 293 | # mac_turkish codec |
| 294 | 'macturkish' : 'mac_turkish', |
| 295 | |
| 296 | # mbcs codec |
| 297 | 'dbcs' : 'mbcs', |
| 298 | |
| 299 | # quopri_codec codec |
| 300 | 'quopri' : 'quopri_codec', |
| 301 | 'quoted_printable' : 'quopri_codec', |
| 302 | 'quotedprintable' : 'quopri_codec', |
| 303 | |
| 304 | # rot_13 codec |
| 305 | 'rot13' : 'rot_13', |
| 306 | |
| 307 | # tactis codec |
| 308 | 'tis260' : 'tactis', |
| 309 | |
| 310 | # utf_16 codec |
| 311 | 'u16' : 'utf_16', |
| 312 | 'utf16' : 'utf_16', |
| 313 | |
| 314 | # utf_16_be codec |
| 315 | 'unicodebigunmarked' : 'utf_16_be', |
| 316 | 'utf_16be' : 'utf_16_be', |
| 317 | |
| 318 | # utf_16_le codec |
| 319 | 'unicodelittleunmarked' : 'utf_16_le', |
| 320 | 'utf_16le' : 'utf_16_le', |
| 321 | |
| 322 | # utf_7 codec |
| 323 | 'u7' : 'utf_7', |
| 324 | 'utf7' : 'utf_7', |
| 325 | |
| 326 | # utf_8 codec |
| 327 | 'u8' : 'utf_8', |
| 328 | 'utf' : 'utf_8', |
| 329 | 'utf8' : 'utf_8', |
| 330 | 'utf8@ucs2' : 'utf_8', |
| 331 | 'utf8@ucs4' : 'utf_8', |
| 332 | |
| 333 | # uu_codec codec |
| 334 | 'uu' : 'uu_codec', |
| 335 | |
| 336 | # zlib_codec codec |
| 337 | 'zip' : 'zlib_codec', |
| 338 | 'zlib' : 'zlib_codec', |
Marc-André Lemburg | 2d92041 | 2001-05-15 12:00:02 +0000 | [diff] [blame] | 339 | |
Guido van Rossum | 0229bf6 | 2000-03-10 23:17:24 +0000 | [diff] [blame] | 340 | } |