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 | |
Marc-André Lemburg | a40ea75 | 2002-10-04 11:58:24 +0000 | [diff] [blame] | 6 | Note that the search function normalizes the encoding names before |
| 7 | doing the lookup, so the mapping will have to map normalized |
| 8 | encoding names to module names. |
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', |
Marc-André Lemburg | 8dc5ff2 | 2002-10-04 16:30:42 +0000 | [diff] [blame] | 29 | 'ansi_x3_4_1968' : 'ascii', # some email headers use this non-standard name |
Marc-André Lemburg | a0af63b | 2002-02-11 17:43:46 +0000 | [diff] [blame] | 30 | 'ansi_x3.4_1986' : 'ascii', |
Marc-André Lemburg | 462004e | 2002-02-10 21:36:20 +0000 | [diff] [blame] | 31 | 'cp367' : 'ascii', |
| 32 | 'csascii' : 'ascii', |
| 33 | 'ibm367' : 'ascii', |
| 34 | 'iso646_us' : 'ascii', |
Marc-André Lemburg | 9d158bb | 2002-10-04 11:51:39 +0000 | [diff] [blame] | 35 | 'iso_646.irv_1991' : 'ascii', |
Marc-André Lemburg | 462004e | 2002-02-10 21:36:20 +0000 | [diff] [blame] | 36 | 'iso_ir_6' : 'ascii', |
| 37 | 'us' : 'ascii', |
| 38 | 'us_ascii' : 'ascii', |
Guido van Rossum | 0229bf6 | 2000-03-10 23:17:24 +0000 | [diff] [blame] | 39 | |
Marc-André Lemburg | 462004e | 2002-02-10 21:36:20 +0000 | [diff] [blame] | 40 | # base64_codec codec |
| 41 | 'base64' : 'base64_codec', |
| 42 | 'base_64' : 'base64_codec', |
Guido van Rossum | 0229bf6 | 2000-03-10 23:17:24 +0000 | [diff] [blame] | 43 | |
Marc-André Lemburg | 462004e | 2002-02-10 21:36:20 +0000 | [diff] [blame] | 44 | # cp037 codec |
| 45 | 'csibm037' : 'cp037', |
| 46 | 'ebcdic_cp_ca' : 'cp037', |
| 47 | 'ebcdic_cp_nl' : 'cp037', |
| 48 | 'ebcdic_cp_us' : 'cp037', |
| 49 | 'ebcdic_cp_wt' : 'cp037', |
| 50 | 'ibm037' : 'cp037', |
| 51 | 'ibm039' : 'cp037', |
Guido van Rossum | 0229bf6 | 2000-03-10 23:17:24 +0000 | [diff] [blame] | 52 | |
Marc-André Lemburg | 462004e | 2002-02-10 21:36:20 +0000 | [diff] [blame] | 53 | # cp1026 codec |
| 54 | 'csibm1026' : 'cp1026', |
| 55 | 'ibm1026' : 'cp1026', |
Guido van Rossum | 0229bf6 | 2000-03-10 23:17:24 +0000 | [diff] [blame] | 56 | |
Marc-André Lemburg | 462004e | 2002-02-10 21:36:20 +0000 | [diff] [blame] | 57 | # cp1140 codec |
| 58 | 'ibm1140' : 'cp1140', |
Mark Hammond | 194bfb2 | 2001-06-04 02:31:23 +0000 | [diff] [blame] | 59 | |
Marc-André Lemburg | 462004e | 2002-02-10 21:36:20 +0000 | [diff] [blame] | 60 | # cp1250 codec |
| 61 | 'windows_1250' : 'cp1250', |
Guido van Rossum | 9e896b3 | 2000-04-05 20:11:21 +0000 | [diff] [blame] | 62 | |
Marc-André Lemburg | 462004e | 2002-02-10 21:36:20 +0000 | [diff] [blame] | 63 | # cp1251 codec |
| 64 | 'windows_1251' : 'cp1251', |
Marc-André Lemburg | 4fd73f0 | 2000-06-07 09:12:30 +0000 | [diff] [blame] | 65 | |
Marc-André Lemburg | 462004e | 2002-02-10 21:36:20 +0000 | [diff] [blame] | 66 | # cp1252 codec |
| 67 | 'windows_1252' : 'cp1252', |
Marc-André Lemburg | 4fd73f0 | 2000-06-07 09:12:30 +0000 | [diff] [blame] | 68 | |
Marc-André Lemburg | 462004e | 2002-02-10 21:36:20 +0000 | [diff] [blame] | 69 | # cp1253 codec |
| 70 | 'windows_1253' : 'cp1253', |
| 71 | |
| 72 | # cp1254 codec |
| 73 | 'windows_1254' : 'cp1254', |
| 74 | |
| 75 | # cp1255 codec |
| 76 | 'windows_1255' : 'cp1255', |
| 77 | |
| 78 | # cp1256 codec |
| 79 | 'windows_1256' : 'cp1256', |
| 80 | |
| 81 | # cp1257 codec |
| 82 | 'windows_1257' : 'cp1257', |
| 83 | |
| 84 | # cp1258 codec |
| 85 | 'windows_1258' : 'cp1258', |
| 86 | |
| 87 | # cp424 codec |
| 88 | 'csibm424' : 'cp424', |
| 89 | 'ebcdic_cp_he' : 'cp424', |
| 90 | 'ibm424' : 'cp424', |
| 91 | |
| 92 | # cp437 codec |
| 93 | '437' : 'cp437', |
| 94 | 'cspc8codepage437' : 'cp437', |
| 95 | 'ibm437' : 'cp437', |
| 96 | |
| 97 | # cp500 codec |
| 98 | 'csibm500' : 'cp500', |
| 99 | 'ebcdic_cp_be' : 'cp500', |
| 100 | 'ebcdic_cp_ch' : 'cp500', |
| 101 | 'ibm500' : 'cp500', |
| 102 | |
| 103 | # cp775 codec |
| 104 | 'cspc775baltic' : 'cp775', |
| 105 | 'ibm775' : 'cp775', |
| 106 | |
| 107 | # cp850 codec |
| 108 | '850' : 'cp850', |
| 109 | 'cspc850multilingual' : 'cp850', |
| 110 | 'ibm850' : 'cp850', |
| 111 | |
| 112 | # cp852 codec |
| 113 | '852' : 'cp852', |
| 114 | 'cspcp852' : 'cp852', |
| 115 | 'ibm852' : 'cp852', |
| 116 | |
| 117 | # cp855 codec |
| 118 | '855' : 'cp855', |
| 119 | 'csibm855' : 'cp855', |
| 120 | 'ibm855' : 'cp855', |
| 121 | |
| 122 | # cp857 codec |
| 123 | '857' : 'cp857', |
| 124 | 'csibm857' : 'cp857', |
| 125 | 'ibm857' : 'cp857', |
| 126 | |
| 127 | # cp860 codec |
| 128 | '860' : 'cp860', |
| 129 | 'csibm860' : 'cp860', |
| 130 | 'ibm860' : 'cp860', |
| 131 | |
| 132 | # cp861 codec |
| 133 | '861' : 'cp861', |
| 134 | 'cp_is' : 'cp861', |
| 135 | 'csibm861' : 'cp861', |
| 136 | 'ibm861' : 'cp861', |
| 137 | |
| 138 | # cp862 codec |
| 139 | '862' : 'cp862', |
| 140 | 'cspc862latinhebrew' : 'cp862', |
| 141 | 'ibm862' : 'cp862', |
| 142 | |
| 143 | # cp863 codec |
| 144 | '863' : 'cp863', |
| 145 | 'csibm863' : 'cp863', |
| 146 | 'ibm863' : 'cp863', |
| 147 | |
| 148 | # cp864 codec |
| 149 | 'csibm864' : 'cp864', |
| 150 | 'ibm864' : 'cp864', |
| 151 | |
| 152 | # cp865 codec |
| 153 | '865' : 'cp865', |
| 154 | 'csibm865' : 'cp865', |
| 155 | 'ibm865' : 'cp865', |
| 156 | |
| 157 | # cp866 codec |
| 158 | '866' : 'cp866', |
| 159 | 'csibm866' : 'cp866', |
| 160 | 'ibm866' : 'cp866', |
| 161 | |
| 162 | # cp869 codec |
| 163 | '869' : 'cp869', |
| 164 | 'cp_gr' : 'cp869', |
| 165 | 'csibm869' : 'cp869', |
| 166 | 'ibm869' : 'cp869', |
| 167 | |
| 168 | # hex_codec codec |
| 169 | 'hex' : 'hex_codec', |
| 170 | |
| 171 | # iso8859_10 codec |
| 172 | 'csisolatin6' : 'iso8859_10', |
| 173 | 'iso_8859_10' : 'iso8859_10', |
Marc-André Lemburg | 9d158bb | 2002-10-04 11:51:39 +0000 | [diff] [blame] | 174 | 'iso_8859_10_1992' : 'iso8859_10', |
Marc-André Lemburg | 462004e | 2002-02-10 21:36:20 +0000 | [diff] [blame] | 175 | 'iso_ir_157' : 'iso8859_10', |
| 176 | 'l6' : 'iso8859_10', |
| 177 | 'latin6' : 'iso8859_10', |
| 178 | |
| 179 | # iso8859_13 codec |
| 180 | 'iso_8859_13' : 'iso8859_13', |
| 181 | |
| 182 | # iso8859_14 codec |
| 183 | 'iso_8859_14' : 'iso8859_14', |
Marc-André Lemburg | 9d158bb | 2002-10-04 11:51:39 +0000 | [diff] [blame] | 184 | 'iso_8859_14_1998' : 'iso8859_14', |
Marc-André Lemburg | 462004e | 2002-02-10 21:36:20 +0000 | [diff] [blame] | 185 | 'iso_celtic' : 'iso8859_14', |
| 186 | 'iso_ir_199' : 'iso8859_14', |
| 187 | 'l8' : 'iso8859_14', |
| 188 | 'latin8' : 'iso8859_14', |
| 189 | |
| 190 | # iso8859_15 codec |
| 191 | 'iso_8859_15' : 'iso8859_15', |
| 192 | |
| 193 | # iso8859_2 codec |
| 194 | 'csisolatin2' : 'iso8859_2', |
| 195 | 'iso_8859_2' : 'iso8859_2', |
Marc-André Lemburg | 9d158bb | 2002-10-04 11:51:39 +0000 | [diff] [blame] | 196 | 'iso_8859_2_1987' : 'iso8859_2', |
Marc-André Lemburg | 462004e | 2002-02-10 21:36:20 +0000 | [diff] [blame] | 197 | 'iso_ir_101' : 'iso8859_2', |
| 198 | 'l2' : 'iso8859_2', |
| 199 | 'latin2' : 'iso8859_2', |
| 200 | |
| 201 | # iso8859_3 codec |
| 202 | 'csisolatin3' : 'iso8859_3', |
| 203 | 'iso_8859_3' : 'iso8859_3', |
Marc-André Lemburg | 9d158bb | 2002-10-04 11:51:39 +0000 | [diff] [blame] | 204 | 'iso_8859_3_1988' : 'iso8859_3', |
Marc-André Lemburg | 462004e | 2002-02-10 21:36:20 +0000 | [diff] [blame] | 205 | 'iso_ir_109' : 'iso8859_3', |
| 206 | 'l3' : 'iso8859_3', |
| 207 | 'latin3' : 'iso8859_3', |
| 208 | |
| 209 | # iso8859_4 codec |
| 210 | 'csisolatin4' : 'iso8859_4', |
| 211 | 'iso_8859_4' : 'iso8859_4', |
Marc-André Lemburg | 9d158bb | 2002-10-04 11:51:39 +0000 | [diff] [blame] | 212 | 'iso_8859_4_1988' : 'iso8859_4', |
Marc-André Lemburg | 462004e | 2002-02-10 21:36:20 +0000 | [diff] [blame] | 213 | 'iso_ir_110' : 'iso8859_4', |
| 214 | 'l4' : 'iso8859_4', |
| 215 | 'latin4' : 'iso8859_4', |
| 216 | |
| 217 | # iso8859_5 codec |
| 218 | 'csisolatincyrillic' : 'iso8859_5', |
| 219 | 'cyrillic' : 'iso8859_5', |
| 220 | 'iso_8859_5' : 'iso8859_5', |
Marc-André Lemburg | 9d158bb | 2002-10-04 11:51:39 +0000 | [diff] [blame] | 221 | 'iso_8859_5_1988' : 'iso8859_5', |
Marc-André Lemburg | 462004e | 2002-02-10 21:36:20 +0000 | [diff] [blame] | 222 | 'iso_ir_144' : 'iso8859_5', |
| 223 | |
| 224 | # iso8859_6 codec |
| 225 | 'arabic' : 'iso8859_6', |
| 226 | 'asmo_708' : 'iso8859_6', |
| 227 | 'csisolatinarabic' : 'iso8859_6', |
| 228 | 'ecma_114' : 'iso8859_6', |
| 229 | 'iso_8859_6' : 'iso8859_6', |
Marc-André Lemburg | 9d158bb | 2002-10-04 11:51:39 +0000 | [diff] [blame] | 230 | 'iso_8859_6_1987' : 'iso8859_6', |
Marc-André Lemburg | 462004e | 2002-02-10 21:36:20 +0000 | [diff] [blame] | 231 | 'iso_ir_127' : 'iso8859_6', |
| 232 | |
| 233 | # iso8859_7 codec |
| 234 | 'csisolatingreek' : 'iso8859_7', |
| 235 | 'ecma_118' : 'iso8859_7', |
| 236 | 'elot_928' : 'iso8859_7', |
| 237 | 'greek' : 'iso8859_7', |
| 238 | 'greek8' : 'iso8859_7', |
| 239 | 'iso_8859_7' : 'iso8859_7', |
Marc-André Lemburg | 9d158bb | 2002-10-04 11:51:39 +0000 | [diff] [blame] | 240 | 'iso_8859_7_1987' : 'iso8859_7', |
Marc-André Lemburg | 462004e | 2002-02-10 21:36:20 +0000 | [diff] [blame] | 241 | 'iso_ir_126' : 'iso8859_7', |
| 242 | |
| 243 | # iso8859_8 codec |
| 244 | 'csisolatinhebrew' : 'iso8859_8', |
| 245 | 'hebrew' : 'iso8859_8', |
| 246 | 'iso_8859_8' : 'iso8859_8', |
Marc-André Lemburg | 9d158bb | 2002-10-04 11:51:39 +0000 | [diff] [blame] | 247 | 'iso_8859_8_1988' : 'iso8859_8', |
Marc-André Lemburg | 462004e | 2002-02-10 21:36:20 +0000 | [diff] [blame] | 248 | 'iso_ir_138' : 'iso8859_8', |
| 249 | |
| 250 | # iso8859_9 codec |
| 251 | 'csisolatin5' : 'iso8859_9', |
| 252 | 'iso_8859_9' : 'iso8859_9', |
Marc-André Lemburg | 9d158bb | 2002-10-04 11:51:39 +0000 | [diff] [blame] | 253 | 'iso_8859_9_1989' : 'iso8859_9', |
Marc-André Lemburg | 462004e | 2002-02-10 21:36:20 +0000 | [diff] [blame] | 254 | 'iso_ir_148' : 'iso8859_9', |
| 255 | 'l5' : 'iso8859_9', |
| 256 | 'latin5' : 'iso8859_9', |
| 257 | |
| 258 | # jis_7 codec |
| 259 | 'csiso2022jp' : 'jis_7', |
| 260 | 'iso_2022_jp' : 'jis_7', |
| 261 | |
| 262 | # koi8_r codec |
| 263 | 'cskoi8r' : 'koi8_r', |
| 264 | |
| 265 | # latin_1 codec |
| 266 | '8859' : 'latin_1', |
| 267 | 'cp819' : 'latin_1', |
| 268 | 'csisolatin1' : 'latin_1', |
| 269 | 'ibm819' : 'latin_1', |
| 270 | 'iso8859' : 'latin_1', |
| 271 | 'iso_8859_1' : 'latin_1', |
Marc-André Lemburg | 9d158bb | 2002-10-04 11:51:39 +0000 | [diff] [blame] | 272 | 'iso_8859_1_1987' : 'latin_1', |
Marc-André Lemburg | 462004e | 2002-02-10 21:36:20 +0000 | [diff] [blame] | 273 | 'iso_ir_100' : 'latin_1', |
| 274 | 'l1' : 'latin_1', |
| 275 | 'latin' : 'latin_1', |
| 276 | 'latin1' : 'latin_1', |
| 277 | |
| 278 | # mac_cyrillic codec |
| 279 | 'maccyrillic' : 'mac_cyrillic', |
| 280 | |
| 281 | # mac_greek codec |
| 282 | 'macgreek' : 'mac_greek', |
| 283 | |
| 284 | # mac_iceland codec |
| 285 | 'maciceland' : 'mac_iceland', |
| 286 | |
| 287 | # mac_latin2 codec |
| 288 | 'maccentraleurope' : 'mac_latin2', |
| 289 | 'maclatin2' : 'mac_latin2', |
| 290 | |
| 291 | # mac_roman codec |
| 292 | 'macroman' : 'mac_roman', |
| 293 | |
| 294 | # mac_turkish codec |
| 295 | 'macturkish' : 'mac_turkish', |
| 296 | |
| 297 | # mbcs codec |
| 298 | 'dbcs' : 'mbcs', |
| 299 | |
| 300 | # quopri_codec codec |
| 301 | 'quopri' : 'quopri_codec', |
| 302 | 'quoted_printable' : 'quopri_codec', |
| 303 | 'quotedprintable' : 'quopri_codec', |
| 304 | |
| 305 | # rot_13 codec |
| 306 | 'rot13' : 'rot_13', |
| 307 | |
| 308 | # tactis codec |
| 309 | 'tis260' : 'tactis', |
| 310 | |
| 311 | # utf_16 codec |
| 312 | 'u16' : 'utf_16', |
| 313 | 'utf16' : 'utf_16', |
| 314 | |
| 315 | # utf_16_be codec |
| 316 | 'unicodebigunmarked' : 'utf_16_be', |
| 317 | 'utf_16be' : 'utf_16_be', |
| 318 | |
| 319 | # utf_16_le codec |
| 320 | 'unicodelittleunmarked' : 'utf_16_le', |
| 321 | 'utf_16le' : 'utf_16_le', |
| 322 | |
| 323 | # utf_7 codec |
| 324 | 'u7' : 'utf_7', |
| 325 | 'utf7' : 'utf_7', |
| 326 | |
| 327 | # utf_8 codec |
| 328 | 'u8' : 'utf_8', |
| 329 | 'utf' : 'utf_8', |
| 330 | 'utf8' : 'utf_8', |
Marc-André Lemburg | 9d158bb | 2002-10-04 11:51:39 +0000 | [diff] [blame] | 331 | 'utf8_ucs2' : 'utf_8', |
| 332 | 'utf8_ucs4' : 'utf_8', |
Marc-André Lemburg | 462004e | 2002-02-10 21:36:20 +0000 | [diff] [blame] | 333 | |
| 334 | # uu_codec codec |
| 335 | 'uu' : 'uu_codec', |
| 336 | |
| 337 | # zlib_codec codec |
| 338 | 'zip' : 'zlib_codec', |
| 339 | 'zlib' : 'zlib_codec', |
Marc-André Lemburg | 2d92041 | 2001-05-15 12:00:02 +0000 | [diff] [blame] | 340 | |
Guido van Rossum | 0229bf6 | 2000-03-10 23:17:24 +0000 | [diff] [blame] | 341 | } |