blob: b304f15638627b693727ace11eeb1bd0268b5fb7 [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
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 Rossum0229bf62000-03-10 23:17:24 +000022
23"""
24aliases = {
25
Marc-André Lemburg462004e2002-02-10 21:36:20 +000026 # ascii codec
27 '646' : 'ascii',
Marc-André Lemburga0af63b2002-02-11 17:43:46 +000028 'ansi_x3.4_1968' : 'ascii',
Marc-André Lemburg8dc5ff22002-10-04 16:30:42 +000029 'ansi_x3_4_1968' : 'ascii', # some email headers use this non-standard name
Marc-André Lemburga0af63b2002-02-11 17:43:46 +000030 'ansi_x3.4_1986' : 'ascii',
Marc-André Lemburg462004e2002-02-10 21:36:20 +000031 'cp367' : 'ascii',
32 'csascii' : 'ascii',
33 'ibm367' : 'ascii',
34 'iso646_us' : 'ascii',
Marc-André Lemburg9d158bb2002-10-04 11:51:39 +000035 'iso_646.irv_1991' : 'ascii',
Marc-André Lemburg462004e2002-02-10 21:36:20 +000036 'iso_ir_6' : 'ascii',
37 'us' : 'ascii',
38 'us_ascii' : 'ascii',
Guido van Rossum0229bf62000-03-10 23:17:24 +000039
Marc-André Lemburg462004e2002-02-10 21:36:20 +000040 # base64_codec codec
41 'base64' : 'base64_codec',
42 'base_64' : 'base64_codec',
Guido van Rossum0229bf62000-03-10 23:17:24 +000043
Raymond Hettinger9a80c5d2003-09-23 20:21:01 +000044 # bz2_codec codec
45 'bz2' : 'bz2_codec',
46
Marc-André Lemburg462004e2002-02-10 21:36:20 +000047 # cp037 codec
48 'csibm037' : 'cp037',
49 'ebcdic_cp_ca' : 'cp037',
50 'ebcdic_cp_nl' : 'cp037',
51 'ebcdic_cp_us' : 'cp037',
52 'ebcdic_cp_wt' : 'cp037',
53 'ibm037' : 'cp037',
54 'ibm039' : 'cp037',
Guido van Rossum0229bf62000-03-10 23:17:24 +000055
Marc-André Lemburg462004e2002-02-10 21:36:20 +000056 # cp1026 codec
57 'csibm1026' : 'cp1026',
58 'ibm1026' : 'cp1026',
Guido van Rossum0229bf62000-03-10 23:17:24 +000059
Marc-André Lemburg462004e2002-02-10 21:36:20 +000060 # cp1140 codec
61 'ibm1140' : 'cp1140',
Mark Hammond194bfb22001-06-04 02:31:23 +000062
Marc-André Lemburg462004e2002-02-10 21:36:20 +000063 # cp1250 codec
64 'windows_1250' : 'cp1250',
Guido van Rossum9e896b32000-04-05 20:11:21 +000065
Marc-André Lemburg462004e2002-02-10 21:36:20 +000066 # cp1251 codec
67 'windows_1251' : 'cp1251',
Marc-André Lemburg4fd73f02000-06-07 09:12:30 +000068
Marc-André Lemburg462004e2002-02-10 21:36:20 +000069 # cp1252 codec
70 'windows_1252' : 'cp1252',
Marc-André Lemburg4fd73f02000-06-07 09:12:30 +000071
Marc-André Lemburg462004e2002-02-10 21:36:20 +000072 # cp1253 codec
73 'windows_1253' : 'cp1253',
74
75 # cp1254 codec
76 'windows_1254' : 'cp1254',
77
78 # cp1255 codec
79 'windows_1255' : 'cp1255',
80
81 # cp1256 codec
82 'windows_1256' : 'cp1256',
83
84 # cp1257 codec
85 'windows_1257' : 'cp1257',
86
87 # cp1258 codec
88 'windows_1258' : 'cp1258',
89
90 # cp424 codec
91 'csibm424' : 'cp424',
92 'ebcdic_cp_he' : 'cp424',
93 'ibm424' : 'cp424',
94
95 # cp437 codec
96 '437' : 'cp437',
97 'cspc8codepage437' : 'cp437',
98 'ibm437' : 'cp437',
99
100 # cp500 codec
101 'csibm500' : 'cp500',
102 'ebcdic_cp_be' : 'cp500',
103 'ebcdic_cp_ch' : 'cp500',
104 'ibm500' : 'cp500',
105
106 # cp775 codec
107 'cspc775baltic' : 'cp775',
108 'ibm775' : 'cp775',
109
110 # cp850 codec
111 '850' : 'cp850',
112 'cspc850multilingual' : 'cp850',
113 'ibm850' : 'cp850',
114
115 # cp852 codec
116 '852' : 'cp852',
117 'cspcp852' : 'cp852',
118 'ibm852' : 'cp852',
119
120 # cp855 codec
121 '855' : 'cp855',
122 'csibm855' : 'cp855',
123 'ibm855' : 'cp855',
124
125 # cp857 codec
126 '857' : 'cp857',
127 'csibm857' : 'cp857',
128 'ibm857' : 'cp857',
129
130 # cp860 codec
131 '860' : 'cp860',
132 'csibm860' : 'cp860',
133 'ibm860' : 'cp860',
134
135 # cp861 codec
136 '861' : 'cp861',
137 'cp_is' : 'cp861',
138 'csibm861' : 'cp861',
139 'ibm861' : 'cp861',
140
141 # cp862 codec
142 '862' : 'cp862',
143 'cspc862latinhebrew' : 'cp862',
144 'ibm862' : 'cp862',
145
146 # cp863 codec
147 '863' : 'cp863',
148 'csibm863' : 'cp863',
149 'ibm863' : 'cp863',
150
151 # cp864 codec
152 'csibm864' : 'cp864',
153 'ibm864' : 'cp864',
154
155 # cp865 codec
156 '865' : 'cp865',
157 'csibm865' : 'cp865',
158 'ibm865' : 'cp865',
159
160 # cp866 codec
161 '866' : 'cp866',
162 'csibm866' : 'cp866',
163 'ibm866' : 'cp866',
164
165 # cp869 codec
166 '869' : 'cp869',
167 'cp_gr' : 'cp869',
168 'csibm869' : 'cp869',
169 'ibm869' : 'cp869',
170
171 # hex_codec codec
172 'hex' : 'hex_codec',
173
174 # iso8859_10 codec
175 'csisolatin6' : 'iso8859_10',
176 'iso_8859_10' : 'iso8859_10',
Marc-André Lemburg9d158bb2002-10-04 11:51:39 +0000177 'iso_8859_10_1992' : 'iso8859_10',
Marc-André Lemburg462004e2002-02-10 21:36:20 +0000178 'iso_ir_157' : 'iso8859_10',
179 'l6' : 'iso8859_10',
180 'latin6' : 'iso8859_10',
181
182 # iso8859_13 codec
183 'iso_8859_13' : 'iso8859_13',
184
185 # iso8859_14 codec
186 'iso_8859_14' : 'iso8859_14',
Marc-André Lemburg9d158bb2002-10-04 11:51:39 +0000187 'iso_8859_14_1998' : 'iso8859_14',
Marc-André Lemburg462004e2002-02-10 21:36:20 +0000188 'iso_celtic' : 'iso8859_14',
189 'iso_ir_199' : 'iso8859_14',
190 'l8' : 'iso8859_14',
191 'latin8' : 'iso8859_14',
192
193 # iso8859_15 codec
194 'iso_8859_15' : 'iso8859_15',
195
196 # iso8859_2 codec
197 'csisolatin2' : 'iso8859_2',
198 'iso_8859_2' : 'iso8859_2',
Marc-André Lemburg9d158bb2002-10-04 11:51:39 +0000199 'iso_8859_2_1987' : 'iso8859_2',
Marc-André Lemburg462004e2002-02-10 21:36:20 +0000200 'iso_ir_101' : 'iso8859_2',
201 'l2' : 'iso8859_2',
202 'latin2' : 'iso8859_2',
203
204 # iso8859_3 codec
205 'csisolatin3' : 'iso8859_3',
206 'iso_8859_3' : 'iso8859_3',
Marc-André Lemburg9d158bb2002-10-04 11:51:39 +0000207 'iso_8859_3_1988' : 'iso8859_3',
Marc-André Lemburg462004e2002-02-10 21:36:20 +0000208 'iso_ir_109' : 'iso8859_3',
209 'l3' : 'iso8859_3',
210 'latin3' : 'iso8859_3',
211
212 # iso8859_4 codec
213 'csisolatin4' : 'iso8859_4',
214 'iso_8859_4' : 'iso8859_4',
Marc-André Lemburg9d158bb2002-10-04 11:51:39 +0000215 'iso_8859_4_1988' : 'iso8859_4',
Marc-André Lemburg462004e2002-02-10 21:36:20 +0000216 'iso_ir_110' : 'iso8859_4',
217 'l4' : 'iso8859_4',
218 'latin4' : 'iso8859_4',
219
220 # iso8859_5 codec
221 'csisolatincyrillic' : 'iso8859_5',
222 'cyrillic' : 'iso8859_5',
223 'iso_8859_5' : 'iso8859_5',
Marc-André Lemburg9d158bb2002-10-04 11:51:39 +0000224 'iso_8859_5_1988' : 'iso8859_5',
Marc-André Lemburg462004e2002-02-10 21:36:20 +0000225 'iso_ir_144' : 'iso8859_5',
226
227 # iso8859_6 codec
228 'arabic' : 'iso8859_6',
229 'asmo_708' : 'iso8859_6',
230 'csisolatinarabic' : 'iso8859_6',
231 'ecma_114' : 'iso8859_6',
232 'iso_8859_6' : 'iso8859_6',
Marc-André Lemburg9d158bb2002-10-04 11:51:39 +0000233 'iso_8859_6_1987' : 'iso8859_6',
Marc-André Lemburg462004e2002-02-10 21:36:20 +0000234 'iso_ir_127' : 'iso8859_6',
235
236 # iso8859_7 codec
237 'csisolatingreek' : 'iso8859_7',
238 'ecma_118' : 'iso8859_7',
239 'elot_928' : 'iso8859_7',
240 'greek' : 'iso8859_7',
241 'greek8' : 'iso8859_7',
242 'iso_8859_7' : 'iso8859_7',
Marc-André Lemburg9d158bb2002-10-04 11:51:39 +0000243 'iso_8859_7_1987' : 'iso8859_7',
Marc-André Lemburg462004e2002-02-10 21:36:20 +0000244 'iso_ir_126' : 'iso8859_7',
245
246 # iso8859_8 codec
247 'csisolatinhebrew' : 'iso8859_8',
248 'hebrew' : 'iso8859_8',
249 'iso_8859_8' : 'iso8859_8',
Marc-André Lemburg9d158bb2002-10-04 11:51:39 +0000250 'iso_8859_8_1988' : 'iso8859_8',
Marc-André Lemburg462004e2002-02-10 21:36:20 +0000251 'iso_ir_138' : 'iso8859_8',
252
253 # iso8859_9 codec
254 'csisolatin5' : 'iso8859_9',
255 'iso_8859_9' : 'iso8859_9',
Marc-André Lemburg9d158bb2002-10-04 11:51:39 +0000256 'iso_8859_9_1989' : 'iso8859_9',
Marc-André Lemburg462004e2002-02-10 21:36:20 +0000257 'iso_ir_148' : 'iso8859_9',
258 'l5' : 'iso8859_9',
259 'latin5' : 'iso8859_9',
260
261 # jis_7 codec
262 'csiso2022jp' : 'jis_7',
263 'iso_2022_jp' : 'jis_7',
264
265 # koi8_r codec
266 'cskoi8r' : 'koi8_r',
267
268 # latin_1 codec
269 '8859' : 'latin_1',
270 'cp819' : 'latin_1',
271 'csisolatin1' : 'latin_1',
272 'ibm819' : 'latin_1',
273 'iso8859' : 'latin_1',
274 'iso_8859_1' : 'latin_1',
Marc-André Lemburg9d158bb2002-10-04 11:51:39 +0000275 'iso_8859_1_1987' : 'latin_1',
Marc-André Lemburg462004e2002-02-10 21:36:20 +0000276 'iso_ir_100' : 'latin_1',
277 'l1' : 'latin_1',
278 'latin' : 'latin_1',
279 'latin1' : 'latin_1',
280
281 # mac_cyrillic codec
282 'maccyrillic' : 'mac_cyrillic',
283
284 # mac_greek codec
285 'macgreek' : 'mac_greek',
286
287 # mac_iceland codec
288 'maciceland' : 'mac_iceland',
289
290 # mac_latin2 codec
291 'maccentraleurope' : 'mac_latin2',
292 'maclatin2' : 'mac_latin2',
293
294 # mac_roman codec
295 'macroman' : 'mac_roman',
296
297 # mac_turkish codec
298 'macturkish' : 'mac_turkish',
299
300 # mbcs codec
301 'dbcs' : 'mbcs',
302
303 # quopri_codec codec
304 'quopri' : 'quopri_codec',
305 'quoted_printable' : 'quopri_codec',
306 'quotedprintable' : 'quopri_codec',
307
308 # rot_13 codec
309 'rot13' : 'rot_13',
310
311 # tactis codec
312 'tis260' : 'tactis',
313
314 # utf_16 codec
315 'u16' : 'utf_16',
316 'utf16' : 'utf_16',
317
318 # utf_16_be codec
319 'unicodebigunmarked' : 'utf_16_be',
320 'utf_16be' : 'utf_16_be',
321
322 # utf_16_le codec
323 'unicodelittleunmarked' : 'utf_16_le',
324 'utf_16le' : 'utf_16_le',
325
326 # utf_7 codec
327 'u7' : 'utf_7',
328 'utf7' : 'utf_7',
329
330 # utf_8 codec
331 'u8' : 'utf_8',
332 'utf' : 'utf_8',
333 'utf8' : 'utf_8',
Marc-André Lemburg9d158bb2002-10-04 11:51:39 +0000334 'utf8_ucs2' : 'utf_8',
335 'utf8_ucs4' : 'utf_8',
Marc-André Lemburg462004e2002-02-10 21:36:20 +0000336
337 # uu_codec codec
338 'uu' : 'uu_codec',
339
340 # zlib_codec codec
341 'zip' : 'zlib_codec',
342 'zlib' : 'zlib_codec',
Marc-André Lemburg2d920412001-05-15 12:00:02 +0000343
Guido van Rossum0229bf62000-03-10 23:17:24 +0000344}