blob: 79f3cc664324ed960759d1d61a801b715f946c72 [file] [log] [blame]
Guido van Rossum0229bf62000-03-10 23:17:24 +00001""" 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 Lemburga40ea752002-10-04 11:58:24 +00006 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 Lemburg462004e2002-02-10 21:36:20 +00009
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
Guido van Rossum0229bf62000-03-10 23:17:24 +000017"""
18aliases = {
19
Marc-André Lemburg462004e2002-02-10 21:36:20 +000020 # ascii codec
21 '646' : 'ascii',
Marc-André Lemburga0af63b2002-02-11 17:43:46 +000022 'ansi_x3.4_1968' : 'ascii',
Marc-André Lemburg8dc5ff22002-10-04 16:30:42 +000023 'ansi_x3_4_1968' : 'ascii', # some email headers use this non-standard name
Marc-André Lemburga0af63b2002-02-11 17:43:46 +000024 'ansi_x3.4_1986' : 'ascii',
Marc-André Lemburg462004e2002-02-10 21:36:20 +000025 'cp367' : 'ascii',
26 'csascii' : 'ascii',
27 'ibm367' : 'ascii',
28 'iso646_us' : 'ascii',
Marc-André Lemburg9d158bb2002-10-04 11:51:39 +000029 'iso_646.irv_1991' : 'ascii',
Marc-André Lemburg462004e2002-02-10 21:36:20 +000030 'iso_ir_6' : 'ascii',
31 'us' : 'ascii',
32 'us_ascii' : 'ascii',
Guido van Rossum0229bf62000-03-10 23:17:24 +000033
Marc-André Lemburg462004e2002-02-10 21:36:20 +000034 # base64_codec codec
35 'base64' : 'base64_codec',
36 'base_64' : 'base64_codec',
Guido van Rossum0229bf62000-03-10 23:17:24 +000037
Hye-Shik Chang3e2a3062004-01-17 14:29:29 +000038 # big5 codec
39 'big5_tw' : 'big5',
40 'csbig5' : 'big5',
41
Hye-Shik Chang2bb146f2004-07-18 03:06:29 +000042 # big5hkscs codec
43 'big5_hkscs' : 'big5hkscs',
44 'hkscs' : 'big5hkscs',
45
Raymond Hettinger9a80c5d2003-09-23 20:21:01 +000046 # bz2_codec codec
47 'bz2' : 'bz2_codec',
48
Marc-André Lemburg462004e2002-02-10 21:36:20 +000049 # cp037 codec
Marc-André Lemburg5c94d332004-01-20 09:38:52 +000050 '037' : 'cp037',
Marc-André Lemburg462004e2002-02-10 21:36:20 +000051 'csibm037' : 'cp037',
52 'ebcdic_cp_ca' : 'cp037',
53 'ebcdic_cp_nl' : 'cp037',
54 'ebcdic_cp_us' : 'cp037',
55 'ebcdic_cp_wt' : 'cp037',
56 'ibm037' : 'cp037',
57 'ibm039' : 'cp037',
Guido van Rossum0229bf62000-03-10 23:17:24 +000058
Marc-André Lemburg462004e2002-02-10 21:36:20 +000059 # cp1026 codec
Marc-André Lemburg5c94d332004-01-20 09:38:52 +000060 '1026' : 'cp1026',
Marc-André Lemburg462004e2002-02-10 21:36:20 +000061 'csibm1026' : 'cp1026',
62 'ibm1026' : 'cp1026',
Guido van Rossum0229bf62000-03-10 23:17:24 +000063
Marc-André Lemburg462004e2002-02-10 21:36:20 +000064 # cp1140 codec
Marc-André Lemburg5c94d332004-01-20 09:38:52 +000065 '1140' : 'cp1140',
Marc-André Lemburg462004e2002-02-10 21:36:20 +000066 'ibm1140' : 'cp1140',
Mark Hammond194bfb22001-06-04 02:31:23 +000067
Marc-André Lemburg462004e2002-02-10 21:36:20 +000068 # cp1250 codec
Marc-André Lemburg5c94d332004-01-20 09:38:52 +000069 '1250' : 'cp1250',
Marc-André Lemburg462004e2002-02-10 21:36:20 +000070 'windows_1250' : 'cp1250',
Guido van Rossum9e896b32000-04-05 20:11:21 +000071
Marc-André Lemburg462004e2002-02-10 21:36:20 +000072 # cp1251 codec
Marc-André Lemburg5c94d332004-01-20 09:38:52 +000073 '1251' : 'cp1251',
Marc-André Lemburg462004e2002-02-10 21:36:20 +000074 'windows_1251' : 'cp1251',
Marc-André Lemburg4fd73f02000-06-07 09:12:30 +000075
Marc-André Lemburg462004e2002-02-10 21:36:20 +000076 # cp1252 codec
Marc-André Lemburg5c94d332004-01-20 09:38:52 +000077 '1252' : 'cp1252',
Marc-André Lemburg462004e2002-02-10 21:36:20 +000078 'windows_1252' : 'cp1252',
Marc-André Lemburg4fd73f02000-06-07 09:12:30 +000079
Marc-André Lemburg462004e2002-02-10 21:36:20 +000080 # cp1253 codec
Marc-André Lemburg5c94d332004-01-20 09:38:52 +000081 '1253' : 'cp1253',
Marc-André Lemburg462004e2002-02-10 21:36:20 +000082 'windows_1253' : 'cp1253',
83
84 # cp1254 codec
Marc-André Lemburg5c94d332004-01-20 09:38:52 +000085 '1254' : 'cp1254',
Marc-André Lemburg462004e2002-02-10 21:36:20 +000086 'windows_1254' : 'cp1254',
87
88 # cp1255 codec
Marc-André Lemburg5c94d332004-01-20 09:38:52 +000089 '1255' : 'cp1255',
Marc-André Lemburg462004e2002-02-10 21:36:20 +000090 'windows_1255' : 'cp1255',
91
92 # cp1256 codec
Marc-André Lemburg5c94d332004-01-20 09:38:52 +000093 '1256' : 'cp1256',
Marc-André Lemburg462004e2002-02-10 21:36:20 +000094 'windows_1256' : 'cp1256',
95
96 # cp1257 codec
Marc-André Lemburg5c94d332004-01-20 09:38:52 +000097 '1257' : 'cp1257',
Marc-André Lemburg462004e2002-02-10 21:36:20 +000098 'windows_1257' : 'cp1257',
99
100 # cp1258 codec
Marc-André Lemburg5c94d332004-01-20 09:38:52 +0000101 '1258' : 'cp1258',
Marc-André Lemburg462004e2002-02-10 21:36:20 +0000102 'windows_1258' : 'cp1258',
103
104 # cp424 codec
Marc-André Lemburg5c94d332004-01-20 09:38:52 +0000105 '424' : 'cp424',
Marc-André Lemburg462004e2002-02-10 21:36:20 +0000106 'csibm424' : 'cp424',
107 'ebcdic_cp_he' : 'cp424',
108 'ibm424' : 'cp424',
109
110 # cp437 codec
111 '437' : 'cp437',
112 'cspc8codepage437' : 'cp437',
113 'ibm437' : 'cp437',
114
115 # cp500 codec
Marc-André Lemburg5c94d332004-01-20 09:38:52 +0000116 '500' : 'cp500',
Marc-André Lemburg462004e2002-02-10 21:36:20 +0000117 'csibm500' : 'cp500',
118 'ebcdic_cp_be' : 'cp500',
119 'ebcdic_cp_ch' : 'cp500',
120 'ibm500' : 'cp500',
121
122 # cp775 codec
Marc-André Lemburg5c94d332004-01-20 09:38:52 +0000123 '775' : 'cp775',
Marc-André Lemburg462004e2002-02-10 21:36:20 +0000124 'cspc775baltic' : 'cp775',
125 'ibm775' : 'cp775',
126
127 # cp850 codec
128 '850' : 'cp850',
129 'cspc850multilingual' : 'cp850',
130 'ibm850' : 'cp850',
131
132 # cp852 codec
133 '852' : 'cp852',
134 'cspcp852' : 'cp852',
135 'ibm852' : 'cp852',
136
137 # cp855 codec
138 '855' : 'cp855',
139 'csibm855' : 'cp855',
140 'ibm855' : 'cp855',
141
142 # cp857 codec
143 '857' : 'cp857',
144 'csibm857' : 'cp857',
145 'ibm857' : 'cp857',
146
147 # cp860 codec
148 '860' : 'cp860',
149 'csibm860' : 'cp860',
150 'ibm860' : 'cp860',
151
152 # cp861 codec
153 '861' : 'cp861',
154 'cp_is' : 'cp861',
155 'csibm861' : 'cp861',
156 'ibm861' : 'cp861',
157
158 # cp862 codec
159 '862' : 'cp862',
160 'cspc862latinhebrew' : 'cp862',
161 'ibm862' : 'cp862',
162
163 # cp863 codec
164 '863' : 'cp863',
165 'csibm863' : 'cp863',
166 'ibm863' : 'cp863',
167
168 # cp864 codec
Marc-André Lemburg5c94d332004-01-20 09:38:52 +0000169 '864' : 'cp864',
Marc-André Lemburg462004e2002-02-10 21:36:20 +0000170 'csibm864' : 'cp864',
171 'ibm864' : 'cp864',
172
173 # cp865 codec
174 '865' : 'cp865',
175 'csibm865' : 'cp865',
176 'ibm865' : 'cp865',
177
178 # cp866 codec
179 '866' : 'cp866',
180 'csibm866' : 'cp866',
181 'ibm866' : 'cp866',
182
183 # cp869 codec
184 '869' : 'cp869',
185 'cp_gr' : 'cp869',
186 'csibm869' : 'cp869',
187 'ibm869' : 'cp869',
188
Hye-Shik Chang3e2a3062004-01-17 14:29:29 +0000189 # cp932 codec
190 '932' : 'cp932',
191 'ms932' : 'cp932',
192 'mskanji' : 'cp932',
193 'ms_kanji' : 'cp932',
194
195 # cp949 codec
196 '949' : 'cp949',
197 'ms949' : 'cp949',
198 'uhc' : 'cp949',
199
200 # cp950 codec
201 '950' : 'cp950',
202 'ms950' : 'cp950',
203
Hye-Shik Chang2bb146f2004-07-18 03:06:29 +0000204 # euc_jis_2004 codec
205 'jisx0213' : 'euc_jis_2004',
206 'eucjis2004' : 'euc_jis_2004',
207 'euc_jis2004' : 'euc_jis_2004',
208
Hye-Shik Chang3e2a3062004-01-17 14:29:29 +0000209 # euc_jisx0213 codec
Hye-Shik Chang3e2a3062004-01-17 14:29:29 +0000210 'eucjisx0213' : 'euc_jisx0213',
211
212 # euc_jp codec
213 'eucjp' : 'euc_jp',
214 'ujis' : 'euc_jp',
215 'u_jis' : 'euc_jp',
216
217 # euc_kr codec
218 'euckr' : 'euc_kr',
219 'korean' : 'euc_kr',
220 'ksc5601' : 'euc_kr',
221 'ks_c_5601' : 'euc_kr',
222 'ks_c_5601_1987' : 'euc_kr',
223 'ksx1001' : 'euc_kr',
224 'ks_x_1001' : 'euc_kr',
225
226 # gb18030 codec
227 'gb18030_2000' : 'gb18030',
228
229 # gb2312 codec
230 'chinese' : 'gb2312',
231 'csiso58gb231280' : 'gb2312',
232 'euc_cn' : 'gb2312',
233 'euccn' : 'gb2312',
234 'eucgb2312_cn' : 'gb2312',
235 'gb2312_1980' : 'gb2312',
236 'gb2312_80' : 'gb2312',
237 'iso_ir_58' : 'gb2312',
238
239 # gbk codec
240 '936' : 'gbk',
241 'cp936' : 'gbk',
242 'ms936' : 'gbk',
243
Marc-André Lemburg462004e2002-02-10 21:36:20 +0000244 # hex_codec codec
245 'hex' : 'hex_codec',
246
Hye-Shik Chang3e2a3062004-01-17 14:29:29 +0000247 # hz codec
248 'hzgb' : 'hz',
249 'hz_gb' : 'hz',
250 'hz_gb_2312' : 'hz',
251
252 # iso2022_jp codec
253 'csiso2022jp' : 'iso2022_jp',
254 'iso2022jp' : 'iso2022_jp',
255 'iso_2022_jp' : 'iso2022_jp',
256
257 # iso2022_jp_1 codec
258 'iso2022jp_1' : 'iso2022_jp_1',
259 'iso_2022_jp_1' : 'iso2022_jp_1',
260
261 # iso2022_jp_2 codec
262 'iso2022jp_2' : 'iso2022_jp_2',
263 'iso_2022_jp_2' : 'iso2022_jp_2',
264
Hye-Shik Chang2bb146f2004-07-18 03:06:29 +0000265 # iso2022_jp_2004 codec
266 'iso_2022_jp_2004' : 'iso2022_jp_2004',
267 'iso2022jp_2004' : 'iso2022_jp_2004',
268
Hye-Shik Changb619e4b2004-01-20 09:33:30 +0000269 # iso2022_jp_3 codec
Hye-Shik Chang3e2a3062004-01-17 14:29:29 +0000270 'iso2022jp_3' : 'iso2022_jp_3',
271 'iso_2022_jp_3' : 'iso2022_jp_3',
272
273 # iso2022_jp_ext codec
274 'iso2022jp_ext' : 'iso2022_jp_ext',
275 'iso_2022_jp_ext' : 'iso2022_jp_ext',
276
277 # iso2022_kr codec
278 'csiso2022kr' : 'iso2022_kr',
279 'iso2022kr' : 'iso2022_kr',
280 'iso_2022_kr' : 'iso2022_kr',
281
Marc-André Lemburg462004e2002-02-10 21:36:20 +0000282 # iso8859_10 codec
283 'csisolatin6' : 'iso8859_10',
284 'iso_8859_10' : 'iso8859_10',
Marc-André Lemburg9d158bb2002-10-04 11:51:39 +0000285 'iso_8859_10_1992' : 'iso8859_10',
Marc-André Lemburg462004e2002-02-10 21:36:20 +0000286 'iso_ir_157' : 'iso8859_10',
287 'l6' : 'iso8859_10',
288 'latin6' : 'iso8859_10',
289
290 # iso8859_13 codec
291 'iso_8859_13' : 'iso8859_13',
292
293 # iso8859_14 codec
294 'iso_8859_14' : 'iso8859_14',
Marc-André Lemburg9d158bb2002-10-04 11:51:39 +0000295 'iso_8859_14_1998' : 'iso8859_14',
Marc-André Lemburg462004e2002-02-10 21:36:20 +0000296 'iso_celtic' : 'iso8859_14',
297 'iso_ir_199' : 'iso8859_14',
298 'l8' : 'iso8859_14',
299 'latin8' : 'iso8859_14',
300
301 # iso8859_15 codec
302 'iso_8859_15' : 'iso8859_15',
303
304 # iso8859_2 codec
305 'csisolatin2' : 'iso8859_2',
306 'iso_8859_2' : 'iso8859_2',
Marc-André Lemburg9d158bb2002-10-04 11:51:39 +0000307 'iso_8859_2_1987' : 'iso8859_2',
Marc-André Lemburg462004e2002-02-10 21:36:20 +0000308 'iso_ir_101' : 'iso8859_2',
309 'l2' : 'iso8859_2',
310 'latin2' : 'iso8859_2',
311
312 # iso8859_3 codec
313 'csisolatin3' : 'iso8859_3',
314 'iso_8859_3' : 'iso8859_3',
Marc-André Lemburg9d158bb2002-10-04 11:51:39 +0000315 'iso_8859_3_1988' : 'iso8859_3',
Marc-André Lemburg462004e2002-02-10 21:36:20 +0000316 'iso_ir_109' : 'iso8859_3',
317 'l3' : 'iso8859_3',
318 'latin3' : 'iso8859_3',
319
320 # iso8859_4 codec
321 'csisolatin4' : 'iso8859_4',
322 'iso_8859_4' : 'iso8859_4',
Marc-André Lemburg9d158bb2002-10-04 11:51:39 +0000323 'iso_8859_4_1988' : 'iso8859_4',
Marc-André Lemburg462004e2002-02-10 21:36:20 +0000324 'iso_ir_110' : 'iso8859_4',
325 'l4' : 'iso8859_4',
326 'latin4' : 'iso8859_4',
327
328 # iso8859_5 codec
329 'csisolatincyrillic' : 'iso8859_5',
330 'cyrillic' : 'iso8859_5',
331 'iso_8859_5' : 'iso8859_5',
Marc-André Lemburg9d158bb2002-10-04 11:51:39 +0000332 'iso_8859_5_1988' : 'iso8859_5',
Marc-André Lemburg462004e2002-02-10 21:36:20 +0000333 'iso_ir_144' : 'iso8859_5',
334
335 # iso8859_6 codec
336 'arabic' : 'iso8859_6',
337 'asmo_708' : 'iso8859_6',
338 'csisolatinarabic' : 'iso8859_6',
339 'ecma_114' : 'iso8859_6',
340 'iso_8859_6' : 'iso8859_6',
Marc-André Lemburg9d158bb2002-10-04 11:51:39 +0000341 'iso_8859_6_1987' : 'iso8859_6',
Marc-André Lemburg462004e2002-02-10 21:36:20 +0000342 'iso_ir_127' : 'iso8859_6',
343
344 # iso8859_7 codec
345 'csisolatingreek' : 'iso8859_7',
346 'ecma_118' : 'iso8859_7',
347 'elot_928' : 'iso8859_7',
348 'greek' : 'iso8859_7',
349 'greek8' : 'iso8859_7',
350 'iso_8859_7' : 'iso8859_7',
Marc-André Lemburg9d158bb2002-10-04 11:51:39 +0000351 'iso_8859_7_1987' : 'iso8859_7',
Marc-André Lemburg462004e2002-02-10 21:36:20 +0000352 'iso_ir_126' : 'iso8859_7',
353
354 # iso8859_8 codec
355 'csisolatinhebrew' : 'iso8859_8',
356 'hebrew' : 'iso8859_8',
357 'iso_8859_8' : 'iso8859_8',
Marc-André Lemburg9d158bb2002-10-04 11:51:39 +0000358 'iso_8859_8_1988' : 'iso8859_8',
Marc-André Lemburg462004e2002-02-10 21:36:20 +0000359 'iso_ir_138' : 'iso8859_8',
360
361 # iso8859_9 codec
362 'csisolatin5' : 'iso8859_9',
363 'iso_8859_9' : 'iso8859_9',
Marc-André Lemburg9d158bb2002-10-04 11:51:39 +0000364 'iso_8859_9_1989' : 'iso8859_9',
Marc-André Lemburg462004e2002-02-10 21:36:20 +0000365 'iso_ir_148' : 'iso8859_9',
366 'l5' : 'iso8859_9',
367 'latin5' : 'iso8859_9',
368
Hye-Shik Chang3e2a3062004-01-17 14:29:29 +0000369 # johab codec
370 'cp1361' : 'johab',
371 'ms1361' : 'johab',
Marc-André Lemburg462004e2002-02-10 21:36:20 +0000372
373 # koi8_r codec
374 'cskoi8r' : 'koi8_r',
375
376 # latin_1 codec
377 '8859' : 'latin_1',
378 'cp819' : 'latin_1',
379 'csisolatin1' : 'latin_1',
380 'ibm819' : 'latin_1',
381 'iso8859' : 'latin_1',
382 'iso_8859_1' : 'latin_1',
Marc-André Lemburg9d158bb2002-10-04 11:51:39 +0000383 'iso_8859_1_1987' : 'latin_1',
Marc-André Lemburg462004e2002-02-10 21:36:20 +0000384 'iso_ir_100' : 'latin_1',
385 'l1' : 'latin_1',
386 'latin' : 'latin_1',
387 'latin1' : 'latin_1',
388
389 # mac_cyrillic codec
390 'maccyrillic' : 'mac_cyrillic',
391
392 # mac_greek codec
393 'macgreek' : 'mac_greek',
394
395 # mac_iceland codec
396 'maciceland' : 'mac_iceland',
397
398 # mac_latin2 codec
399 'maccentraleurope' : 'mac_latin2',
400 'maclatin2' : 'mac_latin2',
401
402 # mac_roman codec
403 'macroman' : 'mac_roman',
404
405 # mac_turkish codec
406 'macturkish' : 'mac_turkish',
407
408 # mbcs codec
409 'dbcs' : 'mbcs',
410
Hye-Shik Chang5c5316f2004-03-19 08:06:07 +0000411 # ptcp154 codec
412 'csptcp154' : 'ptcp154',
413 'pt154' : 'ptcp154',
414 'cp154' : 'ptcp154',
415 'cyrillic-asian' : 'ptcp154',
416
Marc-André Lemburg462004e2002-02-10 21:36:20 +0000417 # quopri_codec codec
418 'quopri' : 'quopri_codec',
419 'quoted_printable' : 'quopri_codec',
420 'quotedprintable' : 'quopri_codec',
421
422 # rot_13 codec
423 'rot13' : 'rot_13',
424
Hye-Shik Chang3e2a3062004-01-17 14:29:29 +0000425 # shift_jis codec
426 'csshiftjis' : 'shift_jis',
427 'shiftjis' : 'shift_jis',
428 'sjis' : 'shift_jis',
429 's_jis' : 'shift_jis',
430
Hye-Shik Chang2bb146f2004-07-18 03:06:29 +0000431 # shift_jis_2004 codec
432 'shiftjis2004' : 'shift_jis_2004',
433 'sjis_2004' : 'shift_jis_2004',
434 's_jis_2004' : 'shift_jis_2004',
435
Hye-Shik Chang3e2a3062004-01-17 14:29:29 +0000436 # shift_jisx0213 codec
437 'shiftjisx0213' : 'shift_jisx0213',
438 'sjisx0213' : 'shift_jisx0213',
439 's_jisx0213' : 'shift_jisx0213',
440
Marc-André Lemburg462004e2002-02-10 21:36:20 +0000441 # tactis codec
442 'tis260' : 'tactis',
443
444 # utf_16 codec
445 'u16' : 'utf_16',
446 'utf16' : 'utf_16',
447
448 # utf_16_be codec
449 'unicodebigunmarked' : 'utf_16_be',
450 'utf_16be' : 'utf_16_be',
451
452 # utf_16_le codec
453 'unicodelittleunmarked' : 'utf_16_le',
454 'utf_16le' : 'utf_16_le',
455
456 # utf_7 codec
457 'u7' : 'utf_7',
458 'utf7' : 'utf_7',
459
460 # utf_8 codec
461 'u8' : 'utf_8',
462 'utf' : 'utf_8',
463 'utf8' : 'utf_8',
Marc-André Lemburg9d158bb2002-10-04 11:51:39 +0000464 'utf8_ucs2' : 'utf_8',
465 'utf8_ucs4' : 'utf_8',
Marc-André Lemburg462004e2002-02-10 21:36:20 +0000466
467 # uu_codec codec
468 'uu' : 'uu_codec',
469
470 # zlib_codec codec
471 'zip' : 'zlib_codec',
472 'zlib' : 'zlib_codec',
Marc-André Lemburg2d920412001-05-15 12:00:02 +0000473
Guido van Rossum0229bf62000-03-10 23:17:24 +0000474}