blob: 18079e73ad69388b1c2708e5bacc3158441ce935 [file] [log] [blame]
Senthil Kumarana3c532b2016-04-12 23:14:14 -07001"""Locale support module.
Guido van Rossum4b8c6ea2000-02-04 15:39:30 +00002
Senthil Kumarana3c532b2016-04-12 23:14:14 -07003The module provides low-level access to the C lib's locale APIs and adds high
4level number formatting APIs as well as a locale aliasing engine to complement
5these.
Marc-André Lemburg5431bc32000-06-07 09:11:40 +00006
Senthil Kumarana3c532b2016-04-12 23:14:14 -07007The aliasing engine includes support for many commonly used locale names and
8maps them to values suitable for passing to the C lib's setlocale() function. It
9also includes default encodings for all supported locale names.
Marc-André Lemburg5431bc32000-06-07 09:11:40 +000010
11"""
12
R. David Murraye59482e2009-04-01 03:42:00 +000013import sys
14import encodings
15import encodings.aliases
16import re
Serhiy Storchaka81108372017-09-26 00:55:55 +030017import _collections_abc
Georg Brandl1a3284e2007-12-02 09:40:06 +000018from builtins import str as _builtin_str
Antoine Pitrou83d6a872008-07-25 21:45:08 +000019import functools
Marc-André Lemburg5431bc32000-06-07 09:11:40 +000020
Fredrik Lundh6c86b992000-07-09 17:12:58 +000021# Try importing the _locale module.
22#
23# If this fails, fall back on a basic 'C' locale emulation.
Guido van Rossumeef1d4e1997-11-19 19:01:43 +000024
Tim Peters1baf8292001-01-24 10:13:46 +000025# Yuck: LC_MESSAGES is non-standard: can't tell whether it exists before
26# trying the import. So __all__ is also fiddled at the end of the file.
Guido van Rossum360e4b82007-05-14 22:51:27 +000027__all__ = ["getlocale", "getdefaultlocale", "getpreferredencoding", "Error",
28 "setlocale", "resetlocale", "localeconv", "strcoll", "strxfrm",
29 "str", "atof", "atoi", "format", "format_string", "currency",
30 "normalize", "LC_CTYPE", "LC_COLLATE", "LC_TIME", "LC_MONETARY",
31 "LC_NUMERIC", "LC_ALL", "CHAR_MAX"]
Skip Montanaro17ab1232001-01-24 06:27:27 +000032
Neal Norwitz48b98de2008-03-10 04:49:25 +000033def _strcoll(a,b):
34 """ strcoll(string,string) -> int.
35 Compares two strings according to the locale.
36 """
Mark Dickinsona56c4672009-01-27 18:17:45 +000037 return (a > b) - (a < b)
Neal Norwitz48b98de2008-03-10 04:49:25 +000038
39def _strxfrm(s):
40 """ strxfrm(string) -> string.
41 Returns a string that behaves for cmp locale-aware.
42 """
43 return s
44
Marc-André Lemburg23481142000-06-08 17:49:41 +000045try:
Fredrik Lundh6c86b992000-07-09 17:12:58 +000046
Marc-André Lemburg23481142000-06-08 17:49:41 +000047 from _locale import *
48
Brett Cannoncd171c82013-07-04 17:43:24 -040049except ImportError:
Marc-André Lemburg23481142000-06-08 17:49:41 +000050
Fredrik Lundh6c86b992000-07-09 17:12:58 +000051 # Locale emulation
52
Marc-André Lemburg23481142000-06-08 17:49:41 +000053 CHAR_MAX = 127
54 LC_ALL = 6
55 LC_COLLATE = 3
56 LC_CTYPE = 0
57 LC_MESSAGES = 5
58 LC_MONETARY = 4
59 LC_NUMERIC = 1
60 LC_TIME = 2
61 Error = ValueError
62
63 def localeconv():
Fredrik Lundh6c86b992000-07-09 17:12:58 +000064 """ localeconv() -> dict.
Marc-André Lemburg23481142000-06-08 17:49:41 +000065 Returns numeric and monetary locale-specific parameters.
66 """
67 # 'C' locale default values
68 return {'grouping': [127],
69 'currency_symbol': '',
70 'n_sign_posn': 127,
Fredrik Lundh6c86b992000-07-09 17:12:58 +000071 'p_cs_precedes': 127,
72 'n_cs_precedes': 127,
73 'mon_grouping': [],
Marc-André Lemburg23481142000-06-08 17:49:41 +000074 'n_sep_by_space': 127,
75 'decimal_point': '.',
76 'negative_sign': '',
77 'positive_sign': '',
Fredrik Lundh6c86b992000-07-09 17:12:58 +000078 'p_sep_by_space': 127,
Marc-André Lemburg23481142000-06-08 17:49:41 +000079 'int_curr_symbol': '',
Fredrik Lundh6c86b992000-07-09 17:12:58 +000080 'p_sign_posn': 127,
Marc-André Lemburg23481142000-06-08 17:49:41 +000081 'thousands_sep': '',
Fredrik Lundh6c86b992000-07-09 17:12:58 +000082 'mon_thousands_sep': '',
83 'frac_digits': 127,
Marc-André Lemburg23481142000-06-08 17:49:41 +000084 'mon_decimal_point': '',
85 'int_frac_digits': 127}
Fredrik Lundh6c86b992000-07-09 17:12:58 +000086
Marc-André Lemburg23481142000-06-08 17:49:41 +000087 def setlocale(category, value=None):
Fredrik Lundh6c86b992000-07-09 17:12:58 +000088 """ setlocale(integer,string=None) -> string.
Marc-André Lemburg23481142000-06-08 17:49:41 +000089 Activates/queries locale processing.
90 """
Martin v. Löwis103d6e72003-03-30 15:42:13 +000091 if value not in (None, '', 'C'):
Collin Winterce36ad82007-08-30 01:19:48 +000092 raise Error('_locale emulation only supports "C" locale')
Marc-André Lemburg23481142000-06-08 17:49:41 +000093 return 'C'
94
Neal Norwitz48b98de2008-03-10 04:49:25 +000095# These may or may not exist in _locale, so be sure to set them.
96if 'strxfrm' not in globals():
97 strxfrm = _strxfrm
98if 'strcoll' not in globals():
99 strcoll = _strcoll
Marc-André Lemburg5431bc32000-06-07 09:11:40 +0000100
Antoine Pitrou83d6a872008-07-25 21:45:08 +0000101
102_localeconv = localeconv
103
104# With this dict, you can override some items of localeconv's return value.
105# This is useful for testing purposes.
106_override_localeconv = {}
107
108@functools.wraps(_localeconv)
109def localeconv():
110 d = _localeconv()
111 if _override_localeconv:
112 d.update(_override_localeconv)
113 return d
114
115
Marc-André Lemburg5431bc32000-06-07 09:11:40 +0000116### Number formatting APIs
117
118# Author: Martin von Loewis
Thomas Wouters477c8d52006-05-27 19:21:47 +0000119# improved by Georg Brandl
Guido van Rossumeef1d4e1997-11-19 19:01:43 +0000120
Antoine Pitrou350370c2009-03-14 00:13:13 +0000121# Iterate over grouping intervals
122def _grouping_intervals(grouping):
Mark Dickinsonbbffb252009-08-04 21:57:18 +0000123 last_interval = None
Antoine Pitrou350370c2009-03-14 00:13:13 +0000124 for interval in grouping:
125 # if grouping is -1, we are done
126 if interval == CHAR_MAX:
127 return
128 # 0: re-use last group ad infinitum
129 if interval == 0:
Mark Dickinsonbbffb252009-08-04 21:57:18 +0000130 if last_interval is None:
131 raise ValueError("invalid grouping")
Antoine Pitrou350370c2009-03-14 00:13:13 +0000132 while True:
133 yield last_interval
134 yield interval
135 last_interval = interval
136
Guido van Rossumeef1d4e1997-11-19 19:01:43 +0000137#perform the grouping from right to left
Thomas Wouters477c8d52006-05-27 19:21:47 +0000138def _group(s, monetary=False):
139 conv = localeconv()
140 thousands_sep = conv[monetary and 'mon_thousands_sep' or 'thousands_sep']
141 grouping = conv[monetary and 'mon_grouping' or 'grouping']
142 if not grouping:
143 return (s, 0)
Martin v. Löwis88ad12a2001-04-13 08:09:50 +0000144 if s[-1] == ' ':
Antoine Pitrou350370c2009-03-14 00:13:13 +0000145 stripped = s.rstrip()
146 right_spaces = s[len(stripped):]
147 s = stripped
148 else:
149 right_spaces = ''
150 left_spaces = ''
151 groups = []
152 for interval in _grouping_intervals(grouping):
153 if not s or s[-1] not in "0123456789":
154 # only non-digit characters remain (sign, spaces)
155 left_spaces = s
156 s = ''
Guido van Rossum45e2fbc1998-03-26 21:13:24 +0000157 break
Antoine Pitrou350370c2009-03-14 00:13:13 +0000158 groups.append(s[-interval:])
159 s = s[:-interval]
Marc-André Lemburg5431bc32000-06-07 09:11:40 +0000160 if s:
Antoine Pitrou350370c2009-03-14 00:13:13 +0000161 groups.append(s)
162 groups.reverse()
163 return (
164 left_spaces + thousands_sep.join(groups) + right_spaces,
Antoine Pitrou6cf17aa2009-03-18 20:26:42 +0000165 len(thousands_sep) * (len(groups) - 1)
Antoine Pitrou350370c2009-03-14 00:13:13 +0000166 )
167
168# Strip a given amount of excess padding from the given string
169def _strip_padding(s, amount):
170 lpos = 0
171 while amount and s[lpos] == ' ':
172 lpos += 1
173 amount -= 1
174 rpos = len(s) - 1
175 while amount and s[rpos] == ' ':
176 rpos -= 1
177 amount -= 1
178 return s[lpos:rpos+1]
Guido van Rossumeef1d4e1997-11-19 19:01:43 +0000179
R. David Murraye59482e2009-04-01 03:42:00 +0000180_percent_re = re.compile(r'%(?:\((?P<key>.*?)\))?'
181 r'(?P<modifiers>[-#0-9 +*.hlL]*?)[eEfFgGdiouxXcrs%]')
182
R. David Murraye59482e2009-04-01 03:42:00 +0000183def _format(percent, value, grouping=False, monetary=False, *additional):
Thomas Wouters477c8d52006-05-27 19:21:47 +0000184 if additional:
185 formatted = percent % ((value,) + additional)
186 else:
187 formatted = percent % value
188 # floats and decimal ints need special action!
189 if percent[-1] in 'eEfFgG':
190 seps = 0
191 parts = formatted.split('.')
192 if grouping:
193 parts[0], seps = _group(parts[0], monetary=monetary)
194 decimal_point = localeconv()[monetary and 'mon_decimal_point'
195 or 'decimal_point']
196 formatted = decimal_point.join(parts)
Antoine Pitrou350370c2009-03-14 00:13:13 +0000197 if seps:
198 formatted = _strip_padding(formatted, seps)
Thomas Wouters477c8d52006-05-27 19:21:47 +0000199 elif percent[-1] in 'diu':
Antoine Pitrou350370c2009-03-14 00:13:13 +0000200 seps = 0
Thomas Wouters477c8d52006-05-27 19:21:47 +0000201 if grouping:
Antoine Pitrou350370c2009-03-14 00:13:13 +0000202 formatted, seps = _group(formatted, monetary=monetary)
203 if seps:
204 formatted = _strip_padding(formatted, seps)
Thomas Wouters477c8d52006-05-27 19:21:47 +0000205 return formatted
206
Garvit Khatri1cf93a72017-03-28 23:43:38 +0800207def format_string(f, val, grouping=False, monetary=False):
Thomas Wouters477c8d52006-05-27 19:21:47 +0000208 """Formats a string in the same way that the % formatting would use,
Fredrik Lundh6c86b992000-07-09 17:12:58 +0000209 but takes the current locale into account.
Garvit Khatri1cf93a72017-03-28 23:43:38 +0800210
211 Grouping is applied if the third parameter is true.
212 Conversion uses monetary thousands separator and grouping strings if
213 forth parameter monetary is true."""
Thomas Wouters477c8d52006-05-27 19:21:47 +0000214 percents = list(_percent_re.finditer(f))
215 new_f = _percent_re.sub('%s', f)
216
Serhiy Storchaka81108372017-09-26 00:55:55 +0300217 if isinstance(val, _collections_abc.Mapping):
R. David Murrayad78d152010-04-27 02:45:53 +0000218 new_val = []
219 for perc in percents:
220 if perc.group()[-1]=='%':
221 new_val.append('%')
222 else:
Garvit Khatri1cf93a72017-03-28 23:43:38 +0800223 new_val.append(_format(perc.group(), val, grouping, monetary))
R. David Murrayad78d152010-04-27 02:45:53 +0000224 else:
225 if not isinstance(val, tuple):
226 val = (val,)
227 new_val = []
Thomas Wouters477c8d52006-05-27 19:21:47 +0000228 i = 0
229 for perc in percents:
R. David Murrayad78d152010-04-27 02:45:53 +0000230 if perc.group()[-1]=='%':
231 new_val.append('%')
232 else:
233 starcount = perc.group('modifiers').count('*')
234 new_val.append(_format(perc.group(),
235 val[i],
236 grouping,
Garvit Khatri1cf93a72017-03-28 23:43:38 +0800237 monetary,
R. David Murrayad78d152010-04-27 02:45:53 +0000238 *val[i+1:i+1+starcount]))
239 i += (1 + starcount)
240 val = tuple(new_val)
Fredrik Lundh6c86b992000-07-09 17:12:58 +0000241
Thomas Wouters477c8d52006-05-27 19:21:47 +0000242 return new_f % val
Martin v. Löwis88ad12a2001-04-13 08:09:50 +0000243
Garvit Khatri1cf93a72017-03-28 23:43:38 +0800244def format(percent, value, grouping=False, monetary=False, *additional):
245 """Deprecated, use format_string instead."""
Serhiy Storchaka81108372017-09-26 00:55:55 +0300246 import warnings
Garvit Khatri1cf93a72017-03-28 23:43:38 +0800247 warnings.warn(
Victor Stinner9acc6a02017-04-03 18:09:55 +0200248 "This method will be removed in a future version of Python. "
Garvit Khatri1cf93a72017-03-28 23:43:38 +0800249 "Use 'locale.format_string()' instead.",
250 DeprecationWarning, stacklevel=2
251 )
252
253 match = _percent_re.match(percent)
254 if not match or len(match.group())!= len(percent):
255 raise ValueError(("format() must be given exactly one %%char "
256 "format specifier, %s not valid") % repr(percent))
257 return _format(percent, value, grouping, monetary, *additional)
258
Thomas Wouters477c8d52006-05-27 19:21:47 +0000259def currency(val, symbol=True, grouping=False, international=False):
260 """Formats val according to the currency settings
261 in the current locale."""
262 conv = localeconv()
263
264 # check for illegal values
265 digits = conv[international and 'int_frac_digits' or 'frac_digits']
266 if digits == 127:
267 raise ValueError("Currency formatting is not possible using "
268 "the 'C' locale.")
269
Garvit Khatri1cf93a72017-03-28 23:43:38 +0800270 s = _format('%%.%if' % digits, abs(val), grouping, monetary=True)
Thomas Wouters477c8d52006-05-27 19:21:47 +0000271 # '<' and '>' are markers if the sign must be inserted between symbol and value
272 s = '<' + s + '>'
273
274 if symbol:
275 smb = conv[international and 'int_curr_symbol' or 'currency_symbol']
276 precedes = conv[val<0 and 'n_cs_precedes' or 'p_cs_precedes']
277 separated = conv[val<0 and 'n_sep_by_space' or 'p_sep_by_space']
278
279 if precedes:
280 s = smb + (separated and ' ' or '') + s
281 else:
282 s = s + (separated and ' ' or '') + smb
283
284 sign_pos = conv[val<0 and 'n_sign_posn' or 'p_sign_posn']
285 sign = conv[val<0 and 'negative_sign' or 'positive_sign']
286
287 if sign_pos == 0:
288 s = '(' + s + ')'
289 elif sign_pos == 1:
290 s = sign + s
291 elif sign_pos == 2:
292 s = s + sign
293 elif sign_pos == 3:
294 s = s.replace('<', sign)
295 elif sign_pos == 4:
296 s = s.replace('>', sign)
297 else:
298 # the default if nothing specified;
299 # this should be the most fitting sign position
300 s = sign + s
301
302 return s.replace('<', '').replace('>', '')
Martin v. Löwisdb786872001-01-21 18:52:33 +0000303
Guido van Rossumeef1d4e1997-11-19 19:01:43 +0000304def str(val):
Senthil Kumarana3c532b2016-04-12 23:14:14 -0700305 """Convert float to string, taking the locale into account."""
Garvit Khatri1cf93a72017-03-28 23:43:38 +0800306 return _format("%.12g", val)
Guido van Rossumeef1d4e1997-11-19 19:01:43 +0000307
Antoine Pitroub64bca92014-10-23 22:52:31 +0200308def delocalize(string):
309 "Parses a string as a normalized number according to the locale settings."
Victor Stinner2753a092015-11-03 14:34:51 +0100310
311 conv = localeconv()
312
Guido van Rossumeef1d4e1997-11-19 19:01:43 +0000313 #First, get rid of the grouping
Victor Stinner2753a092015-11-03 14:34:51 +0100314 ts = conv['thousands_sep']
Marc-André Lemburg5431bc32000-06-07 09:11:40 +0000315 if ts:
Skip Montanaro249369c2004-04-10 16:39:32 +0000316 string = string.replace(ts, '')
Victor Stinner2753a092015-11-03 14:34:51 +0100317
Guido van Rossumeef1d4e1997-11-19 19:01:43 +0000318 #next, replace the decimal point with a dot
Victor Stinner2753a092015-11-03 14:34:51 +0100319 dd = conv['decimal_point']
Marc-André Lemburg5431bc32000-06-07 09:11:40 +0000320 if dd:
Skip Montanaro249369c2004-04-10 16:39:32 +0000321 string = string.replace(dd, '.')
Antoine Pitroub64bca92014-10-23 22:52:31 +0200322 return string
Guido van Rossumeef1d4e1997-11-19 19:01:43 +0000323
Antoine Pitroub64bca92014-10-23 22:52:31 +0200324def atof(string, func=float):
325 "Parses a string as a float according to the locale settings."
326 return func(delocalize(string))
327
328def atoi(string):
Guido van Rossumeef1d4e1997-11-19 19:01:43 +0000329 "Converts a string to an integer according to the locale settings."
Antoine Pitroub64bca92014-10-23 22:52:31 +0200330 return int(delocalize(string))
Guido van Rossumeef1d4e1997-11-19 19:01:43 +0000331
Marc-André Lemburg5431bc32000-06-07 09:11:40 +0000332def _test():
Fredrik Lundh6c86b992000-07-09 17:12:58 +0000333 setlocale(LC_ALL, "")
Guido van Rossumeef1d4e1997-11-19 19:01:43 +0000334 #do grouping
Garvit Khatri1cf93a72017-03-28 23:43:38 +0800335 s1 = format_string("%d", 123456789,1)
Guido van Rossumbe19ed72007-02-09 05:37:30 +0000336 print(s1, "is", atoi(s1))
Guido van Rossumeef1d4e1997-11-19 19:01:43 +0000337 #standard formatting
Thomas Wouters477c8d52006-05-27 19:21:47 +0000338 s1 = str(3.14)
Guido van Rossumbe19ed72007-02-09 05:37:30 +0000339 print(s1, "is", atof(s1))
Marc-André Lemburg5431bc32000-06-07 09:11:40 +0000340
341### Locale name aliasing engine
342
343# Author: Marc-Andre Lemburg, mal@lemburg.com
Fredrik Lundh37a09822002-10-19 20:19:10 +0000344# Various tweaks by Fredrik Lundh <fredrik@pythonware.com>
Fredrik Lundh6c86b992000-07-09 17:12:58 +0000345
346# store away the low-level version of setlocale (it's
347# overridden below)
348_setlocale = setlocale
Marc-André Lemburg5431bc32000-06-07 09:11:40 +0000349
Serhiy Storchaka16f02d22013-12-19 21:21:40 +0200350def _replace_encoding(code, encoding):
351 if '.' in code:
352 langname = code[:code.index('.')]
353 else:
354 langname = code
355 # Convert the encoding to a C lib compatible encoding string
356 norm_encoding = encodings.normalize_encoding(encoding)
357 #print('norm encoding: %r' % norm_encoding)
Serhiy Storchaka8c4f57d2013-12-27 00:56:53 +0200358 norm_encoding = encodings.aliases.aliases.get(norm_encoding.lower(),
Serhiy Storchaka16f02d22013-12-19 21:21:40 +0200359 norm_encoding)
360 #print('aliased encoding: %r' % norm_encoding)
Serhiy Storchaka8c4f57d2013-12-27 00:56:53 +0200361 encoding = norm_encoding
362 norm_encoding = norm_encoding.lower()
363 if norm_encoding in locale_encoding_alias:
364 encoding = locale_encoding_alias[norm_encoding]
365 else:
366 norm_encoding = norm_encoding.replace('_', '')
367 norm_encoding = norm_encoding.replace('-', '')
368 if norm_encoding in locale_encoding_alias:
369 encoding = locale_encoding_alias[norm_encoding]
Serhiy Storchaka16f02d22013-12-19 21:21:40 +0200370 #print('found encoding %r' % encoding)
371 return langname + '.' + encoding
372
Serhiy Storchaka8c4f57d2013-12-27 00:56:53 +0200373def _append_modifier(code, modifier):
374 if modifier == 'euro':
375 if '.' not in code:
376 return code + '.ISO8859-15'
377 _, _, encoding = code.partition('.')
378 if encoding in ('ISO8859-15', 'UTF-8'):
379 return code
380 if encoding == 'ISO8859-1':
381 return _replace_encoding(code, 'ISO8859-15')
382 return code + '@' + modifier
383
Marc-André Lemburg5431bc32000-06-07 09:11:40 +0000384def normalize(localename):
385
386 """ Returns a normalized locale code for the given locale
387 name.
388
389 The returned locale code is formatted for use with
390 setlocale().
391
392 If normalization fails, the original name is returned
393 unchanged.
394
395 If the given encoding is not known, the function defaults to
396 the default encoding for the locale code just like setlocale()
397 does.
398
399 """
Serhiy Storchaka16f02d22013-12-19 21:21:40 +0200400 # Normalize the locale name and extract the encoding and modifier
401 code = localename.lower()
402 if ':' in code:
Marc-André Lemburg5431bc32000-06-07 09:11:40 +0000403 # ':' is sometimes used as encoding delimiter.
Serhiy Storchaka16f02d22013-12-19 21:21:40 +0200404 code = code.replace(':', '.')
405 if '@' in code:
406 code, modifier = code.split('@', 1)
Marc-André Lemburg5431bc32000-06-07 09:11:40 +0000407 else:
Serhiy Storchaka16f02d22013-12-19 21:21:40 +0200408 modifier = ''
409 if '.' in code:
410 langname, encoding = code.split('.')[:2]
411 else:
412 langname = code
Marc-André Lemburg5431bc32000-06-07 09:11:40 +0000413 encoding = ''
414
Serhiy Storchaka16f02d22013-12-19 21:21:40 +0200415 # First lookup: fullname (possibly with encoding and modifier)
416 lang_enc = langname
417 if encoding:
418 norm_encoding = encoding.replace('-', '')
419 norm_encoding = norm_encoding.replace('_', '')
420 lang_enc += '.' + norm_encoding
421 lookup_name = lang_enc
422 if modifier:
423 lookup_name += '@' + modifier
Marc-André Lemburgbb4f1bd2004-12-10 21:58:14 +0000424 code = locale_alias.get(lookup_name, None)
Marc-André Lemburg5431bc32000-06-07 09:11:40 +0000425 if code is not None:
426 return code
Serhiy Storchaka16f02d22013-12-19 21:21:40 +0200427 #print('first lookup failed')
Marc-André Lemburg5431bc32000-06-07 09:11:40 +0000428
Serhiy Storchaka16f02d22013-12-19 21:21:40 +0200429 if modifier:
430 # Second try: fullname without modifier (possibly with encoding)
431 code = locale_alias.get(lang_enc, None)
432 if code is not None:
433 #print('lookup without modifier succeeded')
434 if '@' not in code:
Serhiy Storchaka8c4f57d2013-12-27 00:56:53 +0200435 return _append_modifier(code, modifier)
Serhiy Storchaka16f02d22013-12-19 21:21:40 +0200436 if code.split('@', 1)[1].lower() == modifier:
437 return code
438 #print('second lookup failed')
Marc-André Lemburg5431bc32000-06-07 09:11:40 +0000439
Serhiy Storchaka16f02d22013-12-19 21:21:40 +0200440 if encoding:
441 # Third try: langname (without encoding, possibly with modifier)
442 lookup_name = langname
443 if modifier:
444 lookup_name += '@' + modifier
445 code = locale_alias.get(lookup_name, None)
446 if code is not None:
447 #print('lookup without encoding succeeded')
448 if '@' not in code:
449 return _replace_encoding(code, encoding)
450 code, modifier = code.split('@', 1)
451 return _replace_encoding(code, encoding) + '@' + modifier
452
453 if modifier:
454 # Fourth try: langname (without encoding and modifier)
455 code = locale_alias.get(langname, None)
456 if code is not None:
457 #print('lookup without modifier and encoding succeeded')
458 if '@' not in code:
Serhiy Storchaka8c4f57d2013-12-27 00:56:53 +0200459 code = _replace_encoding(code, encoding)
460 return _append_modifier(code, modifier)
Serhiy Storchaka16f02d22013-12-19 21:21:40 +0200461 code, defmod = code.split('@', 1)
462 if defmod.lower() == modifier:
463 return _replace_encoding(code, encoding) + '@' + defmod
464
465 return localename
Marc-André Lemburg5431bc32000-06-07 09:11:40 +0000466
467def _parse_localename(localename):
468
469 """ Parses the locale code for localename and returns the
470 result as tuple (language code, encoding).
471
472 The localename is normalized and passed through the locale
473 alias engine. A ValueError is raised in case the locale name
474 cannot be parsed.
475
476 The language code corresponds to RFC 1766. code and encoding
477 can be None in case the values cannot be determined or are
Jeremy Hyltona05e2932000-06-28 14:48:01 +0000478 unknown to this implementation.
Marc-André Lemburg5431bc32000-06-07 09:11:40 +0000479
480 """
481 code = normalize(localename)
Georg Brandlb709c2c2006-01-20 09:07:35 +0000482 if '@' in code:
Martin v. Löwisf0a46682002-11-03 17:20:12 +0000483 # Deal with locale modifiers
Serhiy Storchaka16f02d22013-12-19 21:21:40 +0200484 code, modifier = code.split('@', 1)
Martin v. Löwisf0a46682002-11-03 17:20:12 +0000485 if modifier == 'euro' and '.' not in code:
486 # Assume Latin-9 for @euro locales. This is bogus,
487 # since some systems may use other encodings for these
488 # locales. Also, we ignore other modifiers.
489 return code, 'iso-8859-15'
Tim Peters230a60c2002-11-09 05:08:07 +0000490
Marc-André Lemburg5431bc32000-06-07 09:11:40 +0000491 if '.' in code:
Raymond Hettinger346e67f2005-01-01 06:10:26 +0000492 return tuple(code.split('.')[:2])
Marc-André Lemburg5431bc32000-06-07 09:11:40 +0000493 elif code == 'C':
494 return None, None
Collin Winterce36ad82007-08-30 01:19:48 +0000495 raise ValueError('unknown locale: %s' % localename)
Marc-André Lemburg5431bc32000-06-07 09:11:40 +0000496
497def _build_localename(localetuple):
498
499 """ Builds a locale code from the given tuple (language code,
500 encoding).
501
502 No aliasing or normalizing takes place.
503
504 """
Petri Lehtinen3c85fe02011-11-04 21:35:07 +0200505 try:
506 language, encoding = localetuple
507
508 if language is None:
509 language = 'C'
510 if encoding is None:
511 return language
512 else:
513 return language + '.' + encoding
514 except (TypeError, ValueError):
Serhiy Storchaka5affd232017-04-05 09:37:24 +0300515 raise TypeError('Locale must be None, a string, or an iterable of '
516 'two strings -- language code, encoding.') from None
Fredrik Lundh6c86b992000-07-09 17:12:58 +0000517
Matthias Klosef3f231f2005-09-20 07:02:49 +0000518def getdefaultlocale(envvars=('LC_ALL', 'LC_CTYPE', 'LANG', 'LANGUAGE')):
Marc-André Lemburg5431bc32000-06-07 09:11:40 +0000519
520 """ Tries to determine the default locale settings and returns
521 them as tuple (language code, encoding).
522
523 According to POSIX, a program which has not called
Fredrik Lundh6c86b992000-07-09 17:12:58 +0000524 setlocale(LC_ALL, "") runs using the portable 'C' locale.
525 Calling setlocale(LC_ALL, "") lets it use the default locale as
Marc-André Lemburg5431bc32000-06-07 09:11:40 +0000526 defined by the LANG variable. Since we don't want to interfere
Thomas Wouters7e474022000-07-16 12:04:32 +0000527 with the current locale setting we thus emulate the behavior
Marc-André Lemburg5431bc32000-06-07 09:11:40 +0000528 in the way described above.
529
530 To maintain compatibility with other platforms, not only the
531 LANG variable is tested, but a list of variables given as
532 envvars parameter. The first found to be defined will be
533 used. envvars defaults to the search path used in GNU gettext;
534 it must always contain the variable name 'LANG'.
535
536 Except for the code 'C', the language code corresponds to RFC
537 1766. code and encoding can be None in case the values cannot
538 be determined.
539
540 """
Fredrik Lundh04661322000-07-09 23:16:10 +0000541
Fredrik Lundh6c86b992000-07-09 17:12:58 +0000542 try:
543 # check if it's supported by the _locale module
544 import _locale
545 code, encoding = _locale._getdefaultlocale()
Fredrik Lundh04661322000-07-09 23:16:10 +0000546 except (ImportError, AttributeError):
547 pass
548 else:
Fredrik Lundh663809e2000-07-10 19:32:19 +0000549 # make sure the code/encoding values are valid
Fredrik Lundh6c86b992000-07-09 17:12:58 +0000550 if sys.platform == "win32" and code and code[:2] == "0x":
551 # map windows language identifier to language name
552 code = windows_locale.get(int(code, 0))
Fredrik Lundh663809e2000-07-10 19:32:19 +0000553 # ...add other platform-specific processing here, if
554 # necessary...
Fredrik Lundh6c86b992000-07-09 17:12:58 +0000555 return code, encoding
Fredrik Lundh04661322000-07-09 23:16:10 +0000556
Fredrik Lundh6c86b992000-07-09 17:12:58 +0000557 # fall back on POSIX behaviour
Marc-André Lemburg5431bc32000-06-07 09:11:40 +0000558 import os
559 lookup = os.environ.get
560 for variable in envvars:
561 localename = lookup(variable,None)
Martin v. Löwisc8ae31d2004-07-26 12:45:18 +0000562 if localename:
Matthias Klosef3f231f2005-09-20 07:02:49 +0000563 if variable == 'LANGUAGE':
564 localename = localename.split(':')[0]
Marc-André Lemburg5431bc32000-06-07 09:11:40 +0000565 break
566 else:
567 localename = 'C'
568 return _parse_localename(localename)
569
Fredrik Lundh6c86b992000-07-09 17:12:58 +0000570
571def getlocale(category=LC_CTYPE):
Marc-André Lemburg5431bc32000-06-07 09:11:40 +0000572
573 """ Returns the current setting for the given locale category as
574 tuple (language code, encoding).
575
576 category may be one of the LC_* value except LC_ALL. It
577 defaults to LC_CTYPE.
578
579 Except for the code 'C', the language code corresponds to RFC
580 1766. code and encoding can be None in case the values cannot
581 be determined.
582
583 """
Fredrik Lundh6c86b992000-07-09 17:12:58 +0000584 localename = _setlocale(category)
Marc-André Lemburg5431bc32000-06-07 09:11:40 +0000585 if category == LC_ALL and ';' in localename:
Collin Winterce36ad82007-08-30 01:19:48 +0000586 raise TypeError('category LC_ALL is not supported')
Marc-André Lemburg5431bc32000-06-07 09:11:40 +0000587 return _parse_localename(localename)
588
Fredrik Lundh6c86b992000-07-09 17:12:58 +0000589def setlocale(category, locale=None):
Marc-André Lemburg5431bc32000-06-07 09:11:40 +0000590
Fredrik Lundh6c86b992000-07-09 17:12:58 +0000591 """ Set the locale for the given category. The locale can be
Petri Lehtinen395ca722011-11-05 10:18:50 +0200592 a string, an iterable of two strings (language code and encoding),
593 or None.
Marc-André Lemburg5431bc32000-06-07 09:11:40 +0000594
Petri Lehtinen395ca722011-11-05 10:18:50 +0200595 Iterables are converted to strings using the locale aliasing
Fredrik Lundh6c86b992000-07-09 17:12:58 +0000596 engine. Locale strings are passed directly to the C lib.
Marc-André Lemburg5431bc32000-06-07 09:11:40 +0000597
Fredrik Lundh6c86b992000-07-09 17:12:58 +0000598 category may be given as one of the LC_* values.
Marc-André Lemburg5431bc32000-06-07 09:11:40 +0000599
600 """
Guido van Rossum3172c5d2007-10-16 18:12:55 +0000601 if locale and not isinstance(locale, _builtin_str):
Fredrik Lundh6c86b992000-07-09 17:12:58 +0000602 # convert to string
603 locale = normalize(_build_localename(locale))
604 return _setlocale(category, locale)
Marc-André Lemburg5431bc32000-06-07 09:11:40 +0000605
Fredrik Lundh6c86b992000-07-09 17:12:58 +0000606def resetlocale(category=LC_ALL):
Marc-André Lemburg5431bc32000-06-07 09:11:40 +0000607
608 """ Sets the locale for category to the default setting.
609
610 The default setting is determined by calling
Fredrik Lundh6c86b992000-07-09 17:12:58 +0000611 getdefaultlocale(). category defaults to LC_ALL.
612
Marc-André Lemburg5431bc32000-06-07 09:11:40 +0000613 """
Fredrik Lundh6c86b992000-07-09 17:12:58 +0000614 _setlocale(category, _build_localename(getdefaultlocale()))
Marc-André Lemburg5431bc32000-06-07 09:11:40 +0000615
Ronald Oussorenfe8a3d62009-06-07 15:29:46 +0000616if sys.platform.startswith("win"):
Martin v. Löwisf0a46682002-11-03 17:20:12 +0000617 # On Win32, this will return the ANSI code page
Martin v. Löwisf0a46682002-11-03 17:20:12 +0000618 def getpreferredencoding(do_setlocale = True):
619 """Return the charset that the user is likely using."""
Victor Stinner91106cd2017-12-13 12:29:09 +0100620 if sys.flags.utf8_mode:
621 return 'UTF-8'
Antoine Pitroufd4722c2013-10-12 00:13:50 +0200622 import _bootlocale
623 return _bootlocale.getpreferredencoding(False)
Martin v. Löwisf0a46682002-11-03 17:20:12 +0000624else:
625 # On Unix, if CODESET is available, use that.
626 try:
627 CODESET
628 except NameError:
Xavier de Gaye6c9dcda2016-12-17 09:19:11 +0100629 if hasattr(sys, 'getandroidapilevel'):
630 # On Android langinfo.h and CODESET are missing, and UTF-8 is
631 # always used in mbstowcs() and wcstombs().
632 def getpreferredencoding(do_setlocale = True):
633 return 'UTF-8'
634 else:
635 # Fall back to parsing environment variables :-(
636 def getpreferredencoding(do_setlocale = True):
637 """Return the charset that the user is likely using,
638 by looking at environment variables."""
Victor Stinner91106cd2017-12-13 12:29:09 +0100639 if sys.flags.utf8_mode:
640 return 'UTF-8'
Xavier de Gaye6c9dcda2016-12-17 09:19:11 +0100641 res = getdefaultlocale()[1]
642 if res is None:
643 # LANG not set, default conservatively to ASCII
644 res = 'ascii'
645 return res
Martin v. Löwisf0a46682002-11-03 17:20:12 +0000646 else:
647 def getpreferredencoding(do_setlocale = True):
648 """Return the charset that the user is likely using,
649 according to the system configuration."""
Victor Stinner91106cd2017-12-13 12:29:09 +0100650 if sys.flags.utf8_mode:
651 return 'UTF-8'
Antoine Pitroufd4722c2013-10-12 00:13:50 +0200652 import _bootlocale
Martin v. Löwisf0a46682002-11-03 17:20:12 +0000653 if do_setlocale:
654 oldloc = setlocale(LC_CTYPE)
Jeroen Ruigrok van der Wervenbcf85062009-05-06 05:33:24 +0000655 try:
656 setlocale(LC_CTYPE, "")
Jeroen Ruigrok van der Werven6ca2e0a2009-05-06 13:18:35 +0000657 except Error:
Jeroen Ruigrok van der Wervenbcf85062009-05-06 05:33:24 +0000658 pass
Antoine Pitroufd4722c2013-10-12 00:13:50 +0200659 result = _bootlocale.getpreferredencoding(False)
660 if do_setlocale:
Martin v. Löwisf0a46682002-11-03 17:20:12 +0000661 setlocale(LC_CTYPE, oldloc)
Antoine Pitrou6a448d42009-10-19 19:43:09 +0000662 return result
Tim Peters230a60c2002-11-09 05:08:07 +0000663
Martin v. Löwisf0a46682002-11-03 17:20:12 +0000664
Marc-André Lemburg5431bc32000-06-07 09:11:40 +0000665### Database
666#
667# The following data was extracted from the locale.alias file which
668# comes with X11 and then hand edited removing the explicit encoding
669# definitions and adding some more aliases. The file is usually
670# available as /usr/lib/X11/locale/locale.alias.
Fredrik Lundh6c86b992000-07-09 17:12:58 +0000671#
Marc-André Lemburg5431bc32000-06-07 09:11:40 +0000672
673#
Marc-André Lemburgbb4f1bd2004-12-10 21:58:14 +0000674# The local_encoding_alias table maps lowercase encoding alias names
675# to C locale encoding names (case-sensitive). Note that normalize()
676# first looks up the encoding in the encodings.aliases dictionary and
677# then applies this mapping to find the correct C lib name for the
678# encoding.
Marc-André Lemburg5431bc32000-06-07 09:11:40 +0000679#
Marc-André Lemburgbb4f1bd2004-12-10 21:58:14 +0000680locale_encoding_alias = {
681
682 # Mappings for non-standard encoding names used in locale names
683 '437': 'C',
684 'c': 'C',
685 'en': 'ISO8859-1',
686 'jis': 'JIS7',
687 'jis7': 'JIS7',
688 'ajec': 'eucJP',
Serhiy Storchaka8c4f57d2013-12-27 00:56:53 +0200689 'koi8c': 'KOI8-C',
690 'microsoftcp1251': 'CP1251',
691 'microsoftcp1255': 'CP1255',
692 'microsoftcp1256': 'CP1256',
693 '88591': 'ISO8859-1',
694 '88592': 'ISO8859-2',
695 '88595': 'ISO8859-5',
696 '885915': 'ISO8859-15',
Marc-André Lemburgbb4f1bd2004-12-10 21:58:14 +0000697
698 # Mappings from Python codec names to C lib encoding names
699 'ascii': 'ISO8859-1',
700 'latin_1': 'ISO8859-1',
701 'iso8859_1': 'ISO8859-1',
702 'iso8859_10': 'ISO8859-10',
703 'iso8859_11': 'ISO8859-11',
704 'iso8859_13': 'ISO8859-13',
705 'iso8859_14': 'ISO8859-14',
706 'iso8859_15': 'ISO8859-15',
Jeroen Ruigrok van der Werven4072ff32009-05-08 14:17:00 +0000707 'iso8859_16': 'ISO8859-16',
Marc-André Lemburgbb4f1bd2004-12-10 21:58:14 +0000708 'iso8859_2': 'ISO8859-2',
709 'iso8859_3': 'ISO8859-3',
710 'iso8859_4': 'ISO8859-4',
711 'iso8859_5': 'ISO8859-5',
712 'iso8859_6': 'ISO8859-6',
713 'iso8859_7': 'ISO8859-7',
714 'iso8859_8': 'ISO8859-8',
715 'iso8859_9': 'ISO8859-9',
716 'iso2022_jp': 'JIS7',
717 'shift_jis': 'SJIS',
718 'tactis': 'TACTIS',
719 'euc_jp': 'eucJP',
720 'euc_kr': 'eucKR',
Ronald Oussoren02a67ac2011-05-17 12:44:54 +0200721 'utf_8': 'UTF-8',
Marc-André Lemburgbb4f1bd2004-12-10 21:58:14 +0000722 'koi8_r': 'KOI8-R',
Serhiy Storchakaf0eeedf2015-05-12 23:24:19 +0300723 'koi8_t': 'KOI8-T',
Marc-André Lemburgbb4f1bd2004-12-10 21:58:14 +0000724 'koi8_u': 'KOI8-U',
Serhiy Storchakaad8a1c32015-05-12 23:16:55 +0300725 'kz1048': 'RK1048',
Serhiy Storchaka8c4f57d2013-12-27 00:56:53 +0200726 'cp1251': 'CP1251',
727 'cp1255': 'CP1255',
728 'cp1256': 'CP1256',
729
Marc-André Lemburgbb4f1bd2004-12-10 21:58:14 +0000730 # XXX This list is still incomplete. If you know more
731 # mappings, please file a bug report. Thanks.
Marc-André Lemburg5431bc32000-06-07 09:11:40 +0000732}
733
Serhiy Storchaka8c4f57d2013-12-27 00:56:53 +0200734for k, v in sorted(locale_encoding_alias.items()):
735 k = k.replace('_', '')
736 locale_encoding_alias.setdefault(k, v)
737
Fredrik Lundh6c86b992000-07-09 17:12:58 +0000738#
Marc-André Lemburg5431bc32000-06-07 09:11:40 +0000739# The locale_alias table maps lowercase alias names to C locale names
740# (case-sensitive). Encodings are always separated from the locale
741# name using a dot ('.'); they should only be given in case the
742# language name is needed to interpret the given encoding alias
743# correctly (CJK codes often have this need).
744#
Marc-André Lemburgbb4f1bd2004-12-10 21:58:14 +0000745# Note that the normalize() function which uses this tables
746# removes '_' and '-' characters from the encoding part of the
747# locale name before doing the lookup. This saves a lot of
748# space in the table.
749#
750# MAL 2004-12-10:
751# Updated alias mapping to most recent locale.alias file
752# from X.org distribution using makelocalealias.py.
753#
754# These are the differences compared to the old mapping (Python 2.4
755# and older):
756#
757# updated 'bg' -> 'bg_BG.ISO8859-5' to 'bg_BG.CP1251'
758# updated 'bg_bg' -> 'bg_BG.ISO8859-5' to 'bg_BG.CP1251'
759# updated 'bulgarian' -> 'bg_BG.ISO8859-5' to 'bg_BG.CP1251'
760# updated 'cz' -> 'cz_CZ.ISO8859-2' to 'cs_CZ.ISO8859-2'
761# updated 'cz_cz' -> 'cz_CZ.ISO8859-2' to 'cs_CZ.ISO8859-2'
762# updated 'czech' -> 'cs_CS.ISO8859-2' to 'cs_CZ.ISO8859-2'
763# updated 'dutch' -> 'nl_BE.ISO8859-1' to 'nl_NL.ISO8859-1'
764# updated 'et' -> 'et_EE.ISO8859-4' to 'et_EE.ISO8859-15'
765# updated 'et_ee' -> 'et_EE.ISO8859-4' to 'et_EE.ISO8859-15'
766# updated 'fi' -> 'fi_FI.ISO8859-1' to 'fi_FI.ISO8859-15'
767# updated 'fi_fi' -> 'fi_FI.ISO8859-1' to 'fi_FI.ISO8859-15'
768# updated 'iw' -> 'iw_IL.ISO8859-8' to 'he_IL.ISO8859-8'
769# updated 'iw_il' -> 'iw_IL.ISO8859-8' to 'he_IL.ISO8859-8'
770# updated 'japanese' -> 'ja_JP.SJIS' to 'ja_JP.eucJP'
771# updated 'lt' -> 'lt_LT.ISO8859-4' to 'lt_LT.ISO8859-13'
772# updated 'lv' -> 'lv_LV.ISO8859-4' to 'lv_LV.ISO8859-13'
773# updated 'sl' -> 'sl_CS.ISO8859-2' to 'sl_SI.ISO8859-2'
774# updated 'slovene' -> 'sl_CS.ISO8859-2' to 'sl_SI.ISO8859-2'
775# updated 'th_th' -> 'th_TH.TACTIS' to 'th_TH.ISO8859-11'
776# updated 'zh_cn' -> 'zh_CN.eucCN' to 'zh_CN.gb2312'
777# updated 'zh_cn.big5' -> 'zh_TW.eucTW' to 'zh_TW.big5'
778# updated 'zh_tw' -> 'zh_TW.eucTW' to 'zh_TW.big5'
779#
Georg Brandlf08a9dd2008-06-10 16:57:31 +0000780# MAL 2008-05-30:
781# Updated alias mapping to most recent locale.alias file
782# from X.org distribution using makelocalealias.py.
783#
784# These are the differences compared to the old mapping (Python 2.5
785# and older):
786#
787# updated 'cs_cs.iso88592' -> 'cs_CZ.ISO8859-2' to 'cs_CS.ISO8859-2'
788# updated 'serbocroatian' -> 'sh_YU.ISO8859-2' to 'sr_CS.ISO8859-2'
789# updated 'sh' -> 'sh_YU.ISO8859-2' to 'sr_CS.ISO8859-2'
790# updated 'sh_hr.iso88592' -> 'sh_HR.ISO8859-2' to 'hr_HR.ISO8859-2'
791# updated 'sh_sp' -> 'sh_YU.ISO8859-2' to 'sr_CS.ISO8859-2'
792# updated 'sh_yu' -> 'sh_YU.ISO8859-2' to 'sr_CS.ISO8859-2'
793# updated 'sp' -> 'sp_YU.ISO8859-5' to 'sr_CS.ISO8859-5'
794# updated 'sp_yu' -> 'sp_YU.ISO8859-5' to 'sr_CS.ISO8859-5'
795# updated 'sr' -> 'sr_YU.ISO8859-5' to 'sr_CS.ISO8859-5'
796# updated 'sr@cyrillic' -> 'sr_YU.ISO8859-5' to 'sr_CS.ISO8859-5'
797# updated 'sr_sp' -> 'sr_SP.ISO8859-2' to 'sr_CS.ISO8859-2'
798# updated 'sr_yu' -> 'sr_YU.ISO8859-5' to 'sr_CS.ISO8859-5'
799# updated 'sr_yu.cp1251@cyrillic' -> 'sr_YU.CP1251' to 'sr_CS.CP1251'
800# updated 'sr_yu.iso88592' -> 'sr_YU.ISO8859-2' to 'sr_CS.ISO8859-2'
801# updated 'sr_yu.iso88595' -> 'sr_YU.ISO8859-5' to 'sr_CS.ISO8859-5'
802# updated 'sr_yu.iso88595@cyrillic' -> 'sr_YU.ISO8859-5' to 'sr_CS.ISO8859-5'
803# updated 'sr_yu.microsoftcp1251@cyrillic' -> 'sr_YU.CP1251' to 'sr_CS.CP1251'
804# updated 'sr_yu.utf8@cyrillic' -> 'sr_YU.UTF-8' to 'sr_CS.UTF-8'
805# updated 'sr_yu@cyrillic' -> 'sr_YU.ISO8859-5' to 'sr_CS.ISO8859-5'
Antoine Pitrou0c70d2d2010-04-11 22:35:34 +0000806#
807# AP 2010-04-12:
808# Updated alias mapping to most recent locale.alias file
809# from X.org distribution using makelocalealias.py.
810#
811# These are the differences compared to the old mapping (Python 2.6.5
812# and older):
813#
814# updated 'ru' -> 'ru_RU.ISO8859-5' to 'ru_RU.UTF-8'
815# updated 'ru_ru' -> 'ru_RU.ISO8859-5' to 'ru_RU.UTF-8'
816# updated 'serbocroatian' -> 'sr_CS.ISO8859-2' to 'sr_RS.UTF-8@latin'
817# updated 'sh' -> 'sr_CS.ISO8859-2' to 'sr_RS.UTF-8@latin'
818# updated 'sh_yu' -> 'sr_CS.ISO8859-2' to 'sr_RS.UTF-8@latin'
819# updated 'sr' -> 'sr_CS.ISO8859-5' to 'sr_RS.UTF-8'
820# updated 'sr@cyrillic' -> 'sr_CS.ISO8859-5' to 'sr_RS.UTF-8'
821# updated 'sr@latn' -> 'sr_CS.ISO8859-2' to 'sr_RS.UTF-8@latin'
822# updated 'sr_cs.utf8@latn' -> 'sr_CS.UTF-8' to 'sr_RS.UTF-8@latin'
823# updated 'sr_cs@latn' -> 'sr_CS.ISO8859-2' to 'sr_RS.UTF-8@latin'
824# updated 'sr_yu' -> 'sr_CS.ISO8859-5' to 'sr_RS.UTF-8@latin'
825# updated 'sr_yu.utf8@cyrillic' -> 'sr_CS.UTF-8' to 'sr_RS.UTF-8'
826# updated 'sr_yu@cyrillic' -> 'sr_CS.ISO8859-5' to 'sr_RS.UTF-8'
827#
Serhiy Storchaka715233c2013-12-20 18:23:26 +0200828# SS 2013-12-20:
829# Updated alias mapping to most recent locale.alias file
830# from X.org distribution using makelocalealias.py.
831#
832# These are the differences compared to the old mapping (Python 3.3.3
833# and older):
834#
835# updated 'a3' -> 'a3_AZ.KOI8-C' to 'az_AZ.KOI8-C'
836# updated 'a3_az' -> 'a3_AZ.KOI8-C' to 'az_AZ.KOI8-C'
837# updated 'a3_az.koi8c' -> 'a3_AZ.KOI8-C' to 'az_AZ.KOI8-C'
838# updated 'cs_cs.iso88592' -> 'cs_CS.ISO8859-2' to 'cs_CZ.ISO8859-2'
839# updated 'hebrew' -> 'iw_IL.ISO8859-8' to 'he_IL.ISO8859-8'
840# updated 'hebrew.iso88598' -> 'iw_IL.ISO8859-8' to 'he_IL.ISO8859-8'
841# updated 'sd' -> 'sd_IN@devanagari.UTF-8' to 'sd_IN.UTF-8'
842# updated 'sr@latn' -> 'sr_RS.UTF-8@latin' to 'sr_CS.UTF-8@latin'
843# updated 'sr_cs' -> 'sr_RS.UTF-8' to 'sr_CS.UTF-8'
844# updated 'sr_cs.utf8@latn' -> 'sr_RS.UTF-8@latin' to 'sr_CS.UTF-8@latin'
845# updated 'sr_cs@latn' -> 'sr_RS.UTF-8@latin' to 'sr_CS.UTF-8@latin'
Serhiy Storchaka9e04eda2014-10-02 10:49:26 +0300846#
847# SS 2014-10-01:
848# Updated alias mapping with glibc 2.19 supported locales.
Georg Brandlf08a9dd2008-06-10 16:57:31 +0000849
Marc-André Lemburg5431bc32000-06-07 09:11:40 +0000850locale_alias = {
Serhiy Storchaka715233c2013-12-20 18:23:26 +0200851 'a3': 'az_AZ.KOI8-C',
852 'a3_az': 'az_AZ.KOI8-C',
Serhiy Storchaka715233c2013-12-20 18:23:26 +0200853 'a3_az.koic': 'az_AZ.KOI8-C',
Serhiy Storchaka99cb41d2014-10-01 23:43:35 +0300854 'aa_dj': 'aa_DJ.ISO8859-1',
855 'aa_er': 'aa_ER.UTF-8',
856 'aa_et': 'aa_ET.UTF-8',
Marc-André Lemburgbb4f1bd2004-12-10 21:58:14 +0000857 'af': 'af_ZA.ISO8859-1',
858 'af_za': 'af_ZA.ISO8859-1',
Marc-André Lemburgbb4f1bd2004-12-10 21:58:14 +0000859 'am': 'am_ET.UTF-8',
Georg Brandlf08a9dd2008-06-10 16:57:31 +0000860 'am_et': 'am_ET.UTF-8',
Marc-André Lemburgbb4f1bd2004-12-10 21:58:14 +0000861 'american': 'en_US.ISO8859-1',
Serhiy Storchaka99cb41d2014-10-01 23:43:35 +0300862 'an_es': 'an_ES.ISO8859-15',
Marc-André Lemburgbb4f1bd2004-12-10 21:58:14 +0000863 'ar': 'ar_AA.ISO8859-6',
864 'ar_aa': 'ar_AA.ISO8859-6',
Marc-André Lemburgbb4f1bd2004-12-10 21:58:14 +0000865 'ar_ae': 'ar_AE.ISO8859-6',
Marc-André Lemburgbb4f1bd2004-12-10 21:58:14 +0000866 'ar_bh': 'ar_BH.ISO8859-6',
Marc-André Lemburgbb4f1bd2004-12-10 21:58:14 +0000867 'ar_dz': 'ar_DZ.ISO8859-6',
Marc-André Lemburgbb4f1bd2004-12-10 21:58:14 +0000868 'ar_eg': 'ar_EG.ISO8859-6',
Serhiy Storchaka715233c2013-12-20 18:23:26 +0200869 'ar_in': 'ar_IN.UTF-8',
Marc-André Lemburgbb4f1bd2004-12-10 21:58:14 +0000870 'ar_iq': 'ar_IQ.ISO8859-6',
Marc-André Lemburgbb4f1bd2004-12-10 21:58:14 +0000871 'ar_jo': 'ar_JO.ISO8859-6',
Marc-André Lemburgbb4f1bd2004-12-10 21:58:14 +0000872 'ar_kw': 'ar_KW.ISO8859-6',
Marc-André Lemburgbb4f1bd2004-12-10 21:58:14 +0000873 'ar_lb': 'ar_LB.ISO8859-6',
Marc-André Lemburgbb4f1bd2004-12-10 21:58:14 +0000874 'ar_ly': 'ar_LY.ISO8859-6',
Marc-André Lemburgbb4f1bd2004-12-10 21:58:14 +0000875 'ar_ma': 'ar_MA.ISO8859-6',
Marc-André Lemburgbb4f1bd2004-12-10 21:58:14 +0000876 'ar_om': 'ar_OM.ISO8859-6',
Marc-André Lemburgbb4f1bd2004-12-10 21:58:14 +0000877 'ar_qa': 'ar_QA.ISO8859-6',
Marc-André Lemburgbb4f1bd2004-12-10 21:58:14 +0000878 'ar_sa': 'ar_SA.ISO8859-6',
Marc-André Lemburgbb4f1bd2004-12-10 21:58:14 +0000879 'ar_sd': 'ar_SD.ISO8859-6',
Marc-André Lemburgbb4f1bd2004-12-10 21:58:14 +0000880 'ar_sy': 'ar_SY.ISO8859-6',
Marc-André Lemburgbb4f1bd2004-12-10 21:58:14 +0000881 'ar_tn': 'ar_TN.ISO8859-6',
Marc-André Lemburgbb4f1bd2004-12-10 21:58:14 +0000882 'ar_ye': 'ar_YE.ISO8859-6',
Marc-André Lemburgbb4f1bd2004-12-10 21:58:14 +0000883 'arabic': 'ar_AA.ISO8859-6',
Antoine Pitrou0c70d2d2010-04-11 22:35:34 +0000884 'as': 'as_IN.UTF-8',
Serhiy Storchaka715233c2013-12-20 18:23:26 +0200885 'as_in': 'as_IN.UTF-8',
Serhiy Storchaka99cb41d2014-10-01 23:43:35 +0300886 'ast_es': 'ast_ES.ISO8859-15',
887 'ayc_pe': 'ayc_PE.UTF-8',
Marc-André Lemburgbb4f1bd2004-12-10 21:58:14 +0000888 'az': 'az_AZ.ISO8859-9E',
Benjamin Petersondf828082017-03-19 23:49:43 -0700889 'az_az': 'az_AZ.ISO8859-9E',
Marc-André Lemburgbb4f1bd2004-12-10 21:58:14 +0000890 'az_az.iso88599e': 'az_AZ.ISO8859-9E',
891 'be': 'be_BY.CP1251',
Antoine Pitrou0c70d2d2010-04-11 22:35:34 +0000892 'be@latin': 'be_BY.UTF-8@latin',
Serhiy Storchaka1de0ba22014-10-02 00:09:37 +0300893 'be_bg.utf8': 'bg_BG.UTF-8',
Marc-André Lemburgbb4f1bd2004-12-10 21:58:14 +0000894 'be_by': 'be_BY.CP1251',
Antoine Pitrou0c70d2d2010-04-11 22:35:34 +0000895 'be_by@latin': 'be_BY.UTF-8@latin',
Serhiy Storchaka99cb41d2014-10-01 23:43:35 +0300896 'bem_zm': 'bem_ZM.UTF-8',
897 'ber_dz': 'ber_DZ.UTF-8',
898 'ber_ma': 'ber_MA.UTF-8',
Marc-André Lemburgbb4f1bd2004-12-10 21:58:14 +0000899 'bg': 'bg_BG.CP1251',
900 'bg_bg': 'bg_BG.CP1251',
Serhiy Storchaka99cb41d2014-10-01 23:43:35 +0300901 'bho_in': 'bho_IN.UTF-8',
902 'bn_bd': 'bn_BD.UTF-8',
Georg Brandlf08a9dd2008-06-10 16:57:31 +0000903 'bn_in': 'bn_IN.UTF-8',
Serhiy Storchaka99cb41d2014-10-01 23:43:35 +0300904 'bo_cn': 'bo_CN.UTF-8',
Serhiy Storchaka715233c2013-12-20 18:23:26 +0200905 'bo_in': 'bo_IN.UTF-8',
Marc-André Lemburgbb4f1bd2004-12-10 21:58:14 +0000906 'bokmal': 'nb_NO.ISO8859-1',
907 'bokm\xe5l': 'nb_NO.ISO8859-1',
908 'br': 'br_FR.ISO8859-1',
909 'br_fr': 'br_FR.ISO8859-1',
Serhiy Storchaka99cb41d2014-10-01 23:43:35 +0300910 'brx_in': 'brx_IN.UTF-8',
Georg Brandlf08a9dd2008-06-10 16:57:31 +0000911 'bs': 'bs_BA.ISO8859-2',
912 'bs_ba': 'bs_BA.ISO8859-2',
Marc-André Lemburgbb4f1bd2004-12-10 21:58:14 +0000913 'bulgarian': 'bg_BG.CP1251',
Serhiy Storchaka99cb41d2014-10-01 23:43:35 +0300914 'byn_er': 'byn_ER.UTF-8',
Marc-André Lemburgbb4f1bd2004-12-10 21:58:14 +0000915 'c': 'C',
916 'c-french': 'fr_CA.ISO8859-1',
Serhiy Storchaka715233c2013-12-20 18:23:26 +0200917 'c.ascii': 'C',
Marc-André Lemburgbb4f1bd2004-12-10 21:58:14 +0000918 'c.en': 'C',
919 'c.iso88591': 'en_US.ISO8859-1',
Serhiy Storchaka1de0ba22014-10-02 00:09:37 +0300920 'c.utf8': 'en_US.UTF-8',
Marc-André Lemburgbb4f1bd2004-12-10 21:58:14 +0000921 'c_c': 'C',
922 'c_c.c': 'C',
923 'ca': 'ca_ES.ISO8859-1',
Benjamin Petersondf828082017-03-19 23:49:43 -0700924 'ca_ad': 'ca_AD.ISO8859-1',
Marc-André Lemburgbb4f1bd2004-12-10 21:58:14 +0000925 'ca_es': 'ca_ES.ISO8859-1',
Serhiy Storchaka9e04eda2014-10-02 10:49:26 +0300926 'ca_es@valencia': 'ca_ES.ISO8859-15@valencia',
Benjamin Petersondf828082017-03-19 23:49:43 -0700927 'ca_fr': 'ca_FR.ISO8859-1',
928 'ca_it': 'ca_IT.ISO8859-1',
Marc-André Lemburgbb4f1bd2004-12-10 21:58:14 +0000929 'catalan': 'ca_ES.ISO8859-1',
930 'cextend': 'en_US.ISO8859-1',
Marc-André Lemburgbb4f1bd2004-12-10 21:58:14 +0000931 'chinese-s': 'zh_CN.eucCN',
932 'chinese-t': 'zh_TW.eucTW',
Serhiy Storchaka99cb41d2014-10-01 23:43:35 +0300933 'crh_ua': 'crh_UA.UTF-8',
Marc-André Lemburgbb4f1bd2004-12-10 21:58:14 +0000934 'croatian': 'hr_HR.ISO8859-2',
935 'cs': 'cs_CZ.ISO8859-2',
936 'cs_cs': 'cs_CZ.ISO8859-2',
Marc-André Lemburgbb4f1bd2004-12-10 21:58:14 +0000937 'cs_cz': 'cs_CZ.ISO8859-2',
Serhiy Storchaka99cb41d2014-10-01 23:43:35 +0300938 'csb_pl': 'csb_PL.UTF-8',
939 'cv_ru': 'cv_RU.UTF-8',
Marc-André Lemburgbb4f1bd2004-12-10 21:58:14 +0000940 'cy': 'cy_GB.ISO8859-1',
Benjamin Petersondf828082017-03-19 23:49:43 -0700941 'cy_gb': 'cy_GB.ISO8859-1',
Marc-André Lemburgbb4f1bd2004-12-10 21:58:14 +0000942 'cz': 'cs_CZ.ISO8859-2',
943 'cz_cz': 'cs_CZ.ISO8859-2',
944 'czech': 'cs_CZ.ISO8859-2',
945 'da': 'da_DK.ISO8859-1',
946 'da_dk': 'da_DK.ISO8859-1',
Marc-André Lemburgbb4f1bd2004-12-10 21:58:14 +0000947 'danish': 'da_DK.ISO8859-1',
Marc-André Lemburgbb4f1bd2004-12-10 21:58:14 +0000948 'dansk': 'da_DK.ISO8859-1',
949 'de': 'de_DE.ISO8859-1',
950 'de_at': 'de_AT.ISO8859-1',
Marc-André Lemburgbb4f1bd2004-12-10 21:58:14 +0000951 'de_be': 'de_BE.ISO8859-1',
Marc-André Lemburgbb4f1bd2004-12-10 21:58:14 +0000952 'de_ch': 'de_CH.ISO8859-1',
Marc-André Lemburgbb4f1bd2004-12-10 21:58:14 +0000953 'de_de': 'de_DE.ISO8859-1',
Serhiy Storchaka9e04eda2014-10-02 10:49:26 +0300954 'de_li.utf8': 'de_LI.UTF-8',
Marc-André Lemburgbb4f1bd2004-12-10 21:58:14 +0000955 'de_lu': 'de_LU.ISO8859-1',
Marc-André Lemburgbb4f1bd2004-12-10 21:58:14 +0000956 'deutsch': 'de_DE.ISO8859-1',
Serhiy Storchaka99cb41d2014-10-01 23:43:35 +0300957 'doi_in': 'doi_IN.UTF-8',
Marc-André Lemburgbb4f1bd2004-12-10 21:58:14 +0000958 'dutch': 'nl_NL.ISO8859-1',
959 'dutch.iso88591': 'nl_BE.ISO8859-1',
Serhiy Storchaka99cb41d2014-10-01 23:43:35 +0300960 'dv_mv': 'dv_MV.UTF-8',
961 'dz_bt': 'dz_BT.UTF-8',
Marc-André Lemburgbb4f1bd2004-12-10 21:58:14 +0000962 'ee': 'ee_EE.ISO8859-4',
963 'ee_ee': 'ee_EE.ISO8859-4',
Marc-André Lemburgbb4f1bd2004-12-10 21:58:14 +0000964 'eesti': 'et_EE.ISO8859-1',
965 'el': 'el_GR.ISO8859-7',
Serhiy Storchaka99cb41d2014-10-01 23:43:35 +0300966 'el_cy': 'el_CY.ISO8859-7',
Marc-André Lemburgbb4f1bd2004-12-10 21:58:14 +0000967 'el_gr': 'el_GR.ISO8859-7',
Marc-André Lemburgbb4f1bd2004-12-10 21:58:14 +0000968 'el_gr@euro': 'el_GR.ISO8859-15',
969 'en': 'en_US.ISO8859-1',
Serhiy Storchaka99cb41d2014-10-01 23:43:35 +0300970 'en_ag': 'en_AG.UTF-8',
Marc-André Lemburgbb4f1bd2004-12-10 21:58:14 +0000971 'en_au': 'en_AU.ISO8859-1',
Marc-André Lemburgbb4f1bd2004-12-10 21:58:14 +0000972 'en_be': 'en_BE.ISO8859-1',
Marc-André Lemburgbb4f1bd2004-12-10 21:58:14 +0000973 'en_bw': 'en_BW.ISO8859-1',
974 'en_ca': 'en_CA.ISO8859-1',
Serhiy Storchaka99cb41d2014-10-01 23:43:35 +0300975 'en_dk': 'en_DK.ISO8859-1',
Serhiy Storchaka1de0ba22014-10-02 00:09:37 +0300976 'en_dl.utf8': 'en_DL.UTF-8',
Marc-André Lemburgbb4f1bd2004-12-10 21:58:14 +0000977 'en_gb': 'en_GB.ISO8859-1',
Marc-André Lemburgbb4f1bd2004-12-10 21:58:14 +0000978 'en_hk': 'en_HK.ISO8859-1',
979 'en_ie': 'en_IE.ISO8859-1',
Benjamin Petersondf828082017-03-19 23:49:43 -0700980 'en_in': 'en_IN.ISO8859-1',
Serhiy Storchaka99cb41d2014-10-01 23:43:35 +0300981 'en_ng': 'en_NG.UTF-8',
Marc-André Lemburgbb4f1bd2004-12-10 21:58:14 +0000982 'en_nz': 'en_NZ.ISO8859-1',
Marc-André Lemburgbb4f1bd2004-12-10 21:58:14 +0000983 'en_ph': 'en_PH.ISO8859-1',
984 'en_sg': 'en_SG.ISO8859-1',
985 'en_uk': 'en_GB.ISO8859-1',
986 'en_us': 'en_US.ISO8859-1',
Marc-André Lemburgbb4f1bd2004-12-10 21:58:14 +0000987 'en_us@euro@euro': 'en_US.ISO8859-15',
988 'en_za': 'en_ZA.ISO8859-1',
Serhiy Storchaka99cb41d2014-10-01 23:43:35 +0300989 'en_zm': 'en_ZM.UTF-8',
Marc-André Lemburgbb4f1bd2004-12-10 21:58:14 +0000990 'en_zw': 'en_ZW.ISO8859-1',
Benjamin Petersondf828082017-03-19 23:49:43 -0700991 'en_zw.utf8': 'en_ZS.UTF-8',
Marc-André Lemburgbb4f1bd2004-12-10 21:58:14 +0000992 'eng_gb': 'en_GB.ISO8859-1',
Marc-André Lemburgbb4f1bd2004-12-10 21:58:14 +0000993 'english': 'en_EN.ISO8859-1',
Marc-André Lemburgbb4f1bd2004-12-10 21:58:14 +0000994 'english_uk': 'en_GB.ISO8859-1',
Marc-André Lemburgbb4f1bd2004-12-10 21:58:14 +0000995 'english_united-states': 'en_US.ISO8859-1',
996 'english_united-states.437': 'C',
997 'english_us': 'en_US.ISO8859-1',
Benjamin Petersondf828082017-03-19 23:49:43 -0700998 'eo': 'eo_XX.ISO8859-3',
999 'eo.utf8': 'eo.UTF-8',
Marc-André Lemburgbb4f1bd2004-12-10 21:58:14 +00001000 'eo_eo': 'eo_EO.ISO8859-3',
Serhiy Storchaka9e04eda2014-10-02 10:49:26 +03001001 'eo_us.utf8': 'eo_US.UTF-8',
Marc-André Lemburgbb4f1bd2004-12-10 21:58:14 +00001002 'eo_xx': 'eo_XX.ISO8859-3',
Marc-André Lemburgbb4f1bd2004-12-10 21:58:14 +00001003 'es': 'es_ES.ISO8859-1',
1004 'es_ar': 'es_AR.ISO8859-1',
Marc-André Lemburgbb4f1bd2004-12-10 21:58:14 +00001005 'es_bo': 'es_BO.ISO8859-1',
Marc-André Lemburgbb4f1bd2004-12-10 21:58:14 +00001006 'es_cl': 'es_CL.ISO8859-1',
Marc-André Lemburgbb4f1bd2004-12-10 21:58:14 +00001007 'es_co': 'es_CO.ISO8859-1',
Marc-André Lemburgbb4f1bd2004-12-10 21:58:14 +00001008 'es_cr': 'es_CR.ISO8859-1',
Serhiy Storchaka99cb41d2014-10-01 23:43:35 +03001009 'es_cu': 'es_CU.UTF-8',
Marc-André Lemburgbb4f1bd2004-12-10 21:58:14 +00001010 'es_do': 'es_DO.ISO8859-1',
Marc-André Lemburgbb4f1bd2004-12-10 21:58:14 +00001011 'es_ec': 'es_EC.ISO8859-1',
Marc-André Lemburgbb4f1bd2004-12-10 21:58:14 +00001012 'es_es': 'es_ES.ISO8859-1',
Marc-André Lemburgbb4f1bd2004-12-10 21:58:14 +00001013 'es_gt': 'es_GT.ISO8859-1',
Marc-André Lemburgbb4f1bd2004-12-10 21:58:14 +00001014 'es_hn': 'es_HN.ISO8859-1',
Marc-André Lemburgbb4f1bd2004-12-10 21:58:14 +00001015 'es_mx': 'es_MX.ISO8859-1',
Marc-André Lemburgbb4f1bd2004-12-10 21:58:14 +00001016 'es_ni': 'es_NI.ISO8859-1',
Marc-André Lemburgbb4f1bd2004-12-10 21:58:14 +00001017 'es_pa': 'es_PA.ISO8859-1',
Marc-André Lemburgbb4f1bd2004-12-10 21:58:14 +00001018 'es_pe': 'es_PE.ISO8859-1',
Marc-André Lemburgbb4f1bd2004-12-10 21:58:14 +00001019 'es_pr': 'es_PR.ISO8859-1',
Marc-André Lemburgbb4f1bd2004-12-10 21:58:14 +00001020 'es_py': 'es_PY.ISO8859-1',
Marc-André Lemburgbb4f1bd2004-12-10 21:58:14 +00001021 'es_sv': 'es_SV.ISO8859-1',
Marc-André Lemburgbb4f1bd2004-12-10 21:58:14 +00001022 'es_us': 'es_US.ISO8859-1',
1023 'es_uy': 'es_UY.ISO8859-1',
Marc-André Lemburgbb4f1bd2004-12-10 21:58:14 +00001024 'es_ve': 'es_VE.ISO8859-1',
Marc-André Lemburgbb4f1bd2004-12-10 21:58:14 +00001025 'estonian': 'et_EE.ISO8859-1',
1026 'et': 'et_EE.ISO8859-15',
Benjamin Petersondf828082017-03-19 23:49:43 -07001027 'et_ee': 'et_EE.ISO8859-15',
Marc-André Lemburgbb4f1bd2004-12-10 21:58:14 +00001028 'eu': 'eu_ES.ISO8859-1',
1029 'eu_es': 'eu_ES.ISO8859-1',
Serhiy Storchaka9e04eda2014-10-02 10:49:26 +03001030 'eu_fr': 'eu_FR.ISO8859-1',
Marc-André Lemburgbb4f1bd2004-12-10 21:58:14 +00001031 'fa': 'fa_IR.UTF-8',
1032 'fa_ir': 'fa_IR.UTF-8',
1033 'fa_ir.isiri3342': 'fa_IR.ISIRI-3342',
Serhiy Storchaka99cb41d2014-10-01 23:43:35 +03001034 'ff_sn': 'ff_SN.UTF-8',
Marc-André Lemburgbb4f1bd2004-12-10 21:58:14 +00001035 'fi': 'fi_FI.ISO8859-15',
Benjamin Petersondf828082017-03-19 23:49:43 -07001036 'fi_fi': 'fi_FI.ISO8859-15',
Serhiy Storchaka99cb41d2014-10-01 23:43:35 +03001037 'fil_ph': 'fil_PH.UTF-8',
Marc-André Lemburgbb4f1bd2004-12-10 21:58:14 +00001038 'finnish': 'fi_FI.ISO8859-1',
Marc-André Lemburgbb4f1bd2004-12-10 21:58:14 +00001039 'fo': 'fo_FO.ISO8859-1',
1040 'fo_fo': 'fo_FO.ISO8859-1',
Marc-André Lemburgbb4f1bd2004-12-10 21:58:14 +00001041 'fr': 'fr_FR.ISO8859-1',
1042 'fr_be': 'fr_BE.ISO8859-1',
Marc-André Lemburgbb4f1bd2004-12-10 21:58:14 +00001043 'fr_ca': 'fr_CA.ISO8859-1',
Marc-André Lemburgbb4f1bd2004-12-10 21:58:14 +00001044 'fr_ch': 'fr_CH.ISO8859-1',
Marc-André Lemburgbb4f1bd2004-12-10 21:58:14 +00001045 'fr_fr': 'fr_FR.ISO8859-1',
Marc-André Lemburgbb4f1bd2004-12-10 21:58:14 +00001046 'fr_lu': 'fr_LU.ISO8859-1',
Marc-André Lemburgbb4f1bd2004-12-10 21:58:14 +00001047 'fran\xe7ais': 'fr_FR.ISO8859-1',
1048 'fre_fr': 'fr_FR.ISO8859-1',
Marc-André Lemburgbb4f1bd2004-12-10 21:58:14 +00001049 'french': 'fr_FR.ISO8859-1',
1050 'french.iso88591': 'fr_CH.ISO8859-1',
1051 'french_france': 'fr_FR.ISO8859-1',
Serhiy Storchaka99cb41d2014-10-01 23:43:35 +03001052 'fur_it': 'fur_IT.UTF-8',
1053 'fy_de': 'fy_DE.UTF-8',
1054 'fy_nl': 'fy_NL.UTF-8',
Marc-André Lemburgbb4f1bd2004-12-10 21:58:14 +00001055 'ga': 'ga_IE.ISO8859-1',
1056 'ga_ie': 'ga_IE.ISO8859-1',
Marc-André Lemburgbb4f1bd2004-12-10 21:58:14 +00001057 'galego': 'gl_ES.ISO8859-1',
1058 'galician': 'gl_ES.ISO8859-1',
1059 'gd': 'gd_GB.ISO8859-1',
Benjamin Petersondf828082017-03-19 23:49:43 -07001060 'gd_gb': 'gd_GB.ISO8859-1',
Marc-André Lemburgbb4f1bd2004-12-10 21:58:14 +00001061 'ger_de': 'de_DE.ISO8859-1',
Marc-André Lemburgbb4f1bd2004-12-10 21:58:14 +00001062 'german': 'de_DE.ISO8859-1',
1063 'german.iso88591': 'de_CH.ISO8859-1',
1064 'german_germany': 'de_DE.ISO8859-1',
Serhiy Storchaka99cb41d2014-10-01 23:43:35 +03001065 'gez_er': 'gez_ER.UTF-8',
1066 'gez_et': 'gez_ET.UTF-8',
Marc-André Lemburgbb4f1bd2004-12-10 21:58:14 +00001067 'gl': 'gl_ES.ISO8859-1',
1068 'gl_es': 'gl_ES.ISO8859-1',
Marc-André Lemburgbb4f1bd2004-12-10 21:58:14 +00001069 'greek': 'el_GR.ISO8859-7',
Georg Brandlf08a9dd2008-06-10 16:57:31 +00001070 'gu_in': 'gu_IN.UTF-8',
Marc-André Lemburgbb4f1bd2004-12-10 21:58:14 +00001071 'gv': 'gv_GB.ISO8859-1',
1072 'gv_gb': 'gv_GB.ISO8859-1',
Serhiy Storchaka99cb41d2014-10-01 23:43:35 +03001073 'ha_ng': 'ha_NG.UTF-8',
Marc-André Lemburgbb4f1bd2004-12-10 21:58:14 +00001074 'he': 'he_IL.ISO8859-8',
1075 'he_il': 'he_IL.ISO8859-8',
Serhiy Storchaka715233c2013-12-20 18:23:26 +02001076 'hebrew': 'he_IL.ISO8859-8',
Marc-André Lemburgbb4f1bd2004-12-10 21:58:14 +00001077 'hi': 'hi_IN.ISCII-DEV',
Benjamin Petersondf828082017-03-19 23:49:43 -07001078 'hi_in': 'hi_IN.ISCII-DEV',
Marc-André Lemburgbb4f1bd2004-12-10 21:58:14 +00001079 'hi_in.isciidev': 'hi_IN.ISCII-DEV',
Antoine Pitrou0c70d2d2010-04-11 22:35:34 +00001080 'hne': 'hne_IN.UTF-8',
Serhiy Storchaka715233c2013-12-20 18:23:26 +02001081 'hne_in': 'hne_IN.UTF-8',
Marc-André Lemburgbb4f1bd2004-12-10 21:58:14 +00001082 'hr': 'hr_HR.ISO8859-2',
1083 'hr_hr': 'hr_HR.ISO8859-2',
Marc-André Lemburgbb4f1bd2004-12-10 21:58:14 +00001084 'hrvatski': 'hr_HR.ISO8859-2',
Serhiy Storchaka99cb41d2014-10-01 23:43:35 +03001085 'hsb_de': 'hsb_DE.ISO8859-2',
1086 'ht_ht': 'ht_HT.UTF-8',
Marc-André Lemburgbb4f1bd2004-12-10 21:58:14 +00001087 'hu': 'hu_HU.ISO8859-2',
1088 'hu_hu': 'hu_HU.ISO8859-2',
Marc-André Lemburgbb4f1bd2004-12-10 21:58:14 +00001089 'hungarian': 'hu_HU.ISO8859-2',
Serhiy Storchaka99cb41d2014-10-01 23:43:35 +03001090 'hy_am': 'hy_AM.UTF-8',
1091 'hy_am.armscii8': 'hy_AM.ARMSCII_8',
Serhiy Storchaka9e04eda2014-10-02 10:49:26 +03001092 'ia': 'ia.UTF-8',
Serhiy Storchaka99cb41d2014-10-01 23:43:35 +03001093 'ia_fr': 'ia_FR.UTF-8',
Marc-André Lemburgbb4f1bd2004-12-10 21:58:14 +00001094 'icelandic': 'is_IS.ISO8859-1',
Marc-André Lemburgbb4f1bd2004-12-10 21:58:14 +00001095 'id': 'id_ID.ISO8859-1',
1096 'id_id': 'id_ID.ISO8859-1',
Serhiy Storchaka99cb41d2014-10-01 23:43:35 +03001097 'ig_ng': 'ig_NG.UTF-8',
1098 'ik_ca': 'ik_CA.UTF-8',
Marc-André Lemburgbb4f1bd2004-12-10 21:58:14 +00001099 'in': 'id_ID.ISO8859-1',
1100 'in_id': 'id_ID.ISO8859-1',
1101 'is': 'is_IS.ISO8859-1',
1102 'is_is': 'is_IS.ISO8859-1',
Marc-André Lemburgbb4f1bd2004-12-10 21:58:14 +00001103 'iso-8859-1': 'en_US.ISO8859-1',
1104 'iso-8859-15': 'en_US.ISO8859-15',
1105 'iso8859-1': 'en_US.ISO8859-1',
1106 'iso8859-15': 'en_US.ISO8859-15',
1107 'iso_8859_1': 'en_US.ISO8859-1',
1108 'iso_8859_15': 'en_US.ISO8859-15',
1109 'it': 'it_IT.ISO8859-1',
1110 'it_ch': 'it_CH.ISO8859-1',
Marc-André Lemburgbb4f1bd2004-12-10 21:58:14 +00001111 'it_it': 'it_IT.ISO8859-1',
Marc-André Lemburgbb4f1bd2004-12-10 21:58:14 +00001112 'italian': 'it_IT.ISO8859-1',
Marc-André Lemburgbb4f1bd2004-12-10 21:58:14 +00001113 'iu': 'iu_CA.NUNACOM-8',
Benjamin Petersondf828082017-03-19 23:49:43 -07001114 'iu_ca': 'iu_CA.NUNACOM-8',
Marc-André Lemburgbb4f1bd2004-12-10 21:58:14 +00001115 'iu_ca.nunacom8': 'iu_CA.NUNACOM-8',
1116 'iw': 'he_IL.ISO8859-8',
1117 'iw_il': 'he_IL.ISO8859-8',
Serhiy Storchaka99cb41d2014-10-01 23:43:35 +03001118 'iw_il.utf8': 'iw_IL.UTF-8',
Marc-André Lemburgbb4f1bd2004-12-10 21:58:14 +00001119 'ja': 'ja_JP.eucJP',
Marc-André Lemburgbb4f1bd2004-12-10 21:58:14 +00001120 'ja_jp': 'ja_JP.eucJP',
Marc-André Lemburgbb4f1bd2004-12-10 21:58:14 +00001121 'ja_jp.euc': 'ja_JP.eucJP',
Marc-André Lemburgbb4f1bd2004-12-10 21:58:14 +00001122 'ja_jp.mscode': 'ja_JP.SJIS',
Antoine Pitrou0c70d2d2010-04-11 22:35:34 +00001123 'ja_jp.pck': 'ja_JP.SJIS',
Marc-André Lemburgbb4f1bd2004-12-10 21:58:14 +00001124 'japan': 'ja_JP.eucJP',
1125 'japanese': 'ja_JP.eucJP',
1126 'japanese-euc': 'ja_JP.eucJP',
1127 'japanese.euc': 'ja_JP.eucJP',
Marc-André Lemburgbb4f1bd2004-12-10 21:58:14 +00001128 'jp_jp': 'ja_JP.eucJP',
1129 'ka': 'ka_GE.GEORGIAN-ACADEMY',
Benjamin Petersondf828082017-03-19 23:49:43 -07001130 'ka_ge': 'ka_GE.GEORGIAN-ACADEMY',
Marc-André Lemburgbb4f1bd2004-12-10 21:58:14 +00001131 'ka_ge.georgianacademy': 'ka_GE.GEORGIAN-ACADEMY',
1132 'ka_ge.georgianps': 'ka_GE.GEORGIAN-PS',
1133 'ka_ge.georgianrs': 'ka_GE.GEORGIAN-ACADEMY',
Serhiy Storchaka9e04eda2014-10-02 10:49:26 +03001134 'kk_kz': 'kk_KZ.RK1048',
Marc-André Lemburgbb4f1bd2004-12-10 21:58:14 +00001135 'kl': 'kl_GL.ISO8859-1',
1136 'kl_gl': 'kl_GL.ISO8859-1',
Georg Brandlf08a9dd2008-06-10 16:57:31 +00001137 'km_kh': 'km_KH.UTF-8',
Antoine Pitrou0c70d2d2010-04-11 22:35:34 +00001138 'kn': 'kn_IN.UTF-8',
Georg Brandlf08a9dd2008-06-10 16:57:31 +00001139 'kn_in': 'kn_IN.UTF-8',
Marc-André Lemburgbb4f1bd2004-12-10 21:58:14 +00001140 'ko': 'ko_KR.eucKR',
1141 'ko_kr': 'ko_KR.eucKR',
1142 'ko_kr.euc': 'ko_KR.eucKR',
Serhiy Storchaka99cb41d2014-10-01 23:43:35 +03001143 'kok_in': 'kok_IN.UTF-8',
Marc-André Lemburgbb4f1bd2004-12-10 21:58:14 +00001144 'korean': 'ko_KR.eucKR',
1145 'korean.euc': 'ko_KR.eucKR',
Antoine Pitrou0c70d2d2010-04-11 22:35:34 +00001146 'ks': 'ks_IN.UTF-8',
Serhiy Storchaka715233c2013-12-20 18:23:26 +02001147 'ks_in': 'ks_IN.UTF-8',
Serhiy Storchaka1de0ba22014-10-02 00:09:37 +03001148 'ks_in@devanagari.utf8': 'ks_IN.UTF-8@devanagari',
Serhiy Storchaka99cb41d2014-10-01 23:43:35 +03001149 'ku_tr': 'ku_TR.ISO8859-9',
Marc-André Lemburgbb4f1bd2004-12-10 21:58:14 +00001150 'kw': 'kw_GB.ISO8859-1',
1151 'kw_gb': 'kw_GB.ISO8859-1',
Georg Brandlf08a9dd2008-06-10 16:57:31 +00001152 'ky': 'ky_KG.UTF-8',
1153 'ky_kg': 'ky_KG.UTF-8',
Serhiy Storchaka99cb41d2014-10-01 23:43:35 +03001154 'lb_lu': 'lb_LU.UTF-8',
1155 'lg_ug': 'lg_UG.ISO8859-10',
1156 'li_be': 'li_BE.UTF-8',
1157 'li_nl': 'li_NL.UTF-8',
1158 'lij_it': 'lij_IT.UTF-8',
Marc-André Lemburgbb4f1bd2004-12-10 21:58:14 +00001159 'lithuanian': 'lt_LT.ISO8859-13',
1160 'lo': 'lo_LA.MULELAO-1',
Benjamin Petersondf828082017-03-19 23:49:43 -07001161 'lo_la': 'lo_LA.MULELAO-1',
Marc-André Lemburgbb4f1bd2004-12-10 21:58:14 +00001162 'lo_la.cp1133': 'lo_LA.IBM-CP1133',
1163 'lo_la.ibmcp1133': 'lo_LA.IBM-CP1133',
1164 'lo_la.mulelao1': 'lo_LA.MULELAO-1',
1165 'lt': 'lt_LT.ISO8859-13',
1166 'lt_lt': 'lt_LT.ISO8859-13',
Marc-André Lemburgbb4f1bd2004-12-10 21:58:14 +00001167 'lv': 'lv_LV.ISO8859-13',
1168 'lv_lv': 'lv_LV.ISO8859-13',
Serhiy Storchaka99cb41d2014-10-01 23:43:35 +03001169 'mag_in': 'mag_IN.UTF-8',
Antoine Pitrou0c70d2d2010-04-11 22:35:34 +00001170 'mai': 'mai_IN.UTF-8',
Serhiy Storchaka715233c2013-12-20 18:23:26 +02001171 'mai_in': 'mai_IN.UTF-8',
Serhiy Storchaka99cb41d2014-10-01 23:43:35 +03001172 'mg_mg': 'mg_MG.ISO8859-15',
1173 'mhr_ru': 'mhr_RU.UTF-8',
Marc-André Lemburgbb4f1bd2004-12-10 21:58:14 +00001174 'mi': 'mi_NZ.ISO8859-1',
Benjamin Petersondf828082017-03-19 23:49:43 -07001175 'mi_nz': 'mi_NZ.ISO8859-1',
Marc-André Lemburgbb4f1bd2004-12-10 21:58:14 +00001176 'mk': 'mk_MK.ISO8859-5',
1177 'mk_mk': 'mk_MK.ISO8859-5',
Antoine Pitrou0c70d2d2010-04-11 22:35:34 +00001178 'ml': 'ml_IN.UTF-8',
Serhiy Storchaka715233c2013-12-20 18:23:26 +02001179 'ml_in': 'ml_IN.UTF-8',
Serhiy Storchaka99cb41d2014-10-01 23:43:35 +03001180 'mn_mn': 'mn_MN.UTF-8',
1181 'mni_in': 'mni_IN.UTF-8',
Antoine Pitrou0c70d2d2010-04-11 22:35:34 +00001182 'mr': 'mr_IN.UTF-8',
Georg Brandlf08a9dd2008-06-10 16:57:31 +00001183 'mr_in': 'mr_IN.UTF-8',
Marc-André Lemburgbb4f1bd2004-12-10 21:58:14 +00001184 'ms': 'ms_MY.ISO8859-1',
1185 'ms_my': 'ms_MY.ISO8859-1',
Marc-André Lemburgbb4f1bd2004-12-10 21:58:14 +00001186 'mt': 'mt_MT.ISO8859-3',
1187 'mt_mt': 'mt_MT.ISO8859-3',
Serhiy Storchaka99cb41d2014-10-01 23:43:35 +03001188 'my_mm': 'my_MM.UTF-8',
Benjamin Petersondf828082017-03-19 23:49:43 -07001189 'nan_tw@latin': 'nan_TW.UTF-8@latin',
Marc-André Lemburgbb4f1bd2004-12-10 21:58:14 +00001190 'nb': 'nb_NO.ISO8859-1',
1191 'nb_no': 'nb_NO.ISO8859-1',
Serhiy Storchaka99cb41d2014-10-01 23:43:35 +03001192 'nds_de': 'nds_DE.UTF-8',
1193 'nds_nl': 'nds_NL.UTF-8',
Serhiy Storchaka715233c2013-12-20 18:23:26 +02001194 'ne_np': 'ne_NP.UTF-8',
Serhiy Storchaka99cb41d2014-10-01 23:43:35 +03001195 'nhn_mx': 'nhn_MX.UTF-8',
1196 'niu_nu': 'niu_NU.UTF-8',
1197 'niu_nz': 'niu_NZ.UTF-8',
Marc-André Lemburgbb4f1bd2004-12-10 21:58:14 +00001198 'nl': 'nl_NL.ISO8859-1',
Serhiy Storchaka99cb41d2014-10-01 23:43:35 +03001199 'nl_aw': 'nl_AW.UTF-8',
Marc-André Lemburgbb4f1bd2004-12-10 21:58:14 +00001200 'nl_be': 'nl_BE.ISO8859-1',
Marc-André Lemburgbb4f1bd2004-12-10 21:58:14 +00001201 'nl_nl': 'nl_NL.ISO8859-1',
Marc-André Lemburgbb4f1bd2004-12-10 21:58:14 +00001202 'nn': 'nn_NO.ISO8859-1',
1203 'nn_no': 'nn_NO.ISO8859-1',
Marc-André Lemburgbb4f1bd2004-12-10 21:58:14 +00001204 'no': 'no_NO.ISO8859-1',
1205 'no@nynorsk': 'ny_NO.ISO8859-1',
1206 'no_no': 'no_NO.ISO8859-1',
Antoine Pitrou0c70d2d2010-04-11 22:35:34 +00001207 'no_no.iso88591@bokmal': 'no_NO.ISO8859-1',
1208 'no_no.iso88591@nynorsk': 'no_NO.ISO8859-1',
Marc-André Lemburgbb4f1bd2004-12-10 21:58:14 +00001209 'norwegian': 'no_NO.ISO8859-1',
Georg Brandlf08a9dd2008-06-10 16:57:31 +00001210 'nr': 'nr_ZA.ISO8859-1',
Benjamin Petersondf828082017-03-19 23:49:43 -07001211 'nr_za': 'nr_ZA.ISO8859-1',
Georg Brandlf08a9dd2008-06-10 16:57:31 +00001212 'nso': 'nso_ZA.ISO8859-15',
Benjamin Petersondf828082017-03-19 23:49:43 -07001213 'nso_za': 'nso_ZA.ISO8859-15',
Marc-André Lemburgbb4f1bd2004-12-10 21:58:14 +00001214 'ny': 'ny_NO.ISO8859-1',
1215 'ny_no': 'ny_NO.ISO8859-1',
Marc-André Lemburgbb4f1bd2004-12-10 21:58:14 +00001216 'nynorsk': 'nn_NO.ISO8859-1',
1217 'oc': 'oc_FR.ISO8859-1',
1218 'oc_fr': 'oc_FR.ISO8859-1',
Serhiy Storchaka99cb41d2014-10-01 23:43:35 +03001219 'om_et': 'om_ET.UTF-8',
1220 'om_ke': 'om_KE.ISO8859-1',
Antoine Pitrou0c70d2d2010-04-11 22:35:34 +00001221 'or': 'or_IN.UTF-8',
Serhiy Storchaka715233c2013-12-20 18:23:26 +02001222 'or_in': 'or_IN.UTF-8',
Serhiy Storchaka99cb41d2014-10-01 23:43:35 +03001223 'os_ru': 'os_RU.UTF-8',
Antoine Pitrou0c70d2d2010-04-11 22:35:34 +00001224 'pa': 'pa_IN.UTF-8',
Georg Brandlf08a9dd2008-06-10 16:57:31 +00001225 'pa_in': 'pa_IN.UTF-8',
Serhiy Storchaka99cb41d2014-10-01 23:43:35 +03001226 'pa_pk': 'pa_PK.UTF-8',
1227 'pap_an': 'pap_AN.UTF-8',
Marc-André Lemburgbb4f1bd2004-12-10 21:58:14 +00001228 'pd': 'pd_US.ISO8859-1',
1229 'pd_de': 'pd_DE.ISO8859-1',
Marc-André Lemburgbb4f1bd2004-12-10 21:58:14 +00001230 'pd_us': 'pd_US.ISO8859-1',
Marc-André Lemburgbb4f1bd2004-12-10 21:58:14 +00001231 'ph': 'ph_PH.ISO8859-1',
1232 'ph_ph': 'ph_PH.ISO8859-1',
Marc-André Lemburgbb4f1bd2004-12-10 21:58:14 +00001233 'pl': 'pl_PL.ISO8859-2',
1234 'pl_pl': 'pl_PL.ISO8859-2',
Marc-André Lemburgbb4f1bd2004-12-10 21:58:14 +00001235 'polish': 'pl_PL.ISO8859-2',
1236 'portuguese': 'pt_PT.ISO8859-1',
Marc-André Lemburgbb4f1bd2004-12-10 21:58:14 +00001237 'portuguese_brazil': 'pt_BR.ISO8859-1',
Marc-André Lemburgbb4f1bd2004-12-10 21:58:14 +00001238 'posix': 'C',
1239 'posix-utf2': 'C',
1240 'pp': 'pp_AN.ISO8859-1',
1241 'pp_an': 'pp_AN.ISO8859-1',
Serhiy Storchaka99cb41d2014-10-01 23:43:35 +03001242 'ps_af': 'ps_AF.UTF-8',
Marc-André Lemburgbb4f1bd2004-12-10 21:58:14 +00001243 'pt': 'pt_PT.ISO8859-1',
1244 'pt_br': 'pt_BR.ISO8859-1',
Marc-André Lemburgbb4f1bd2004-12-10 21:58:14 +00001245 'pt_pt': 'pt_PT.ISO8859-1',
Marc-André Lemburgbb4f1bd2004-12-10 21:58:14 +00001246 'ro': 'ro_RO.ISO8859-2',
1247 'ro_ro': 'ro_RO.ISO8859-2',
Marc-André Lemburgbb4f1bd2004-12-10 21:58:14 +00001248 'romanian': 'ro_RO.ISO8859-2',
Antoine Pitrou0c70d2d2010-04-11 22:35:34 +00001249 'ru': 'ru_RU.UTF-8',
Benjamin Petersondf828082017-03-19 23:49:43 -07001250 'ru_ru': 'ru_RU.UTF-8',
Marc-André Lemburgbb4f1bd2004-12-10 21:58:14 +00001251 'ru_ua': 'ru_UA.KOI8-U',
Marc-André Lemburgbb4f1bd2004-12-10 21:58:14 +00001252 'rumanian': 'ro_RO.ISO8859-2',
Benjamin Petersondf828082017-03-19 23:49:43 -07001253 'russian': 'ru_RU.ISO8859-5',
Georg Brandlf08a9dd2008-06-10 16:57:31 +00001254 'rw': 'rw_RW.ISO8859-1',
Benjamin Petersondf828082017-03-19 23:49:43 -07001255 'rw_rw': 'rw_RW.ISO8859-1',
Serhiy Storchaka99cb41d2014-10-01 23:43:35 +03001256 'sa_in': 'sa_IN.UTF-8',
1257 'sat_in': 'sat_IN.UTF-8',
1258 'sc_it': 'sc_IT.UTF-8',
Serhiy Storchaka715233c2013-12-20 18:23:26 +02001259 'sd': 'sd_IN.UTF-8',
Serhiy Storchaka5eb01532013-12-26 21:20:59 +02001260 'sd_in': 'sd_IN.UTF-8',
Serhiy Storchaka1de0ba22014-10-02 00:09:37 +03001261 'sd_in@devanagari.utf8': 'sd_IN.UTF-8@devanagari',
Serhiy Storchaka9e04eda2014-10-02 10:49:26 +03001262 'sd_pk': 'sd_PK.UTF-8',
Marc-André Lemburgbb4f1bd2004-12-10 21:58:14 +00001263 'se_no': 'se_NO.UTF-8',
Antoine Pitrou0c70d2d2010-04-11 22:35:34 +00001264 'serbocroatian': 'sr_RS.UTF-8@latin',
1265 'sh': 'sr_RS.UTF-8@latin',
1266 'sh_ba.iso88592@bosnia': 'sr_CS.ISO8859-2',
Marc-André Lemburgbb4f1bd2004-12-10 21:58:14 +00001267 'sh_hr': 'sh_HR.ISO8859-2',
Georg Brandlf08a9dd2008-06-10 16:57:31 +00001268 'sh_hr.iso88592': 'hr_HR.ISO8859-2',
1269 'sh_sp': 'sr_CS.ISO8859-2',
Antoine Pitrou0c70d2d2010-04-11 22:35:34 +00001270 'sh_yu': 'sr_RS.UTF-8@latin',
Serhiy Storchaka99cb41d2014-10-01 23:43:35 +03001271 'shs_ca': 'shs_CA.UTF-8',
Georg Brandlf08a9dd2008-06-10 16:57:31 +00001272 'si': 'si_LK.UTF-8',
1273 'si_lk': 'si_LK.UTF-8',
Serhiy Storchaka99cb41d2014-10-01 23:43:35 +03001274 'sid_et': 'sid_ET.UTF-8',
Georg Brandlf08a9dd2008-06-10 16:57:31 +00001275 'sinhala': 'si_LK.UTF-8',
Marc-André Lemburgbb4f1bd2004-12-10 21:58:14 +00001276 'sk': 'sk_SK.ISO8859-2',
1277 'sk_sk': 'sk_SK.ISO8859-2',
Marc-André Lemburgbb4f1bd2004-12-10 21:58:14 +00001278 'sl': 'sl_SI.ISO8859-2',
1279 'sl_cs': 'sl_CS.ISO8859-2',
1280 'sl_si': 'sl_SI.ISO8859-2',
Marc-André Lemburgbb4f1bd2004-12-10 21:58:14 +00001281 'slovak': 'sk_SK.ISO8859-2',
1282 'slovene': 'sl_SI.ISO8859-2',
1283 'slovenian': 'sl_SI.ISO8859-2',
Serhiy Storchaka99cb41d2014-10-01 23:43:35 +03001284 'so_dj': 'so_DJ.ISO8859-1',
1285 'so_et': 'so_ET.UTF-8',
1286 'so_ke': 'so_KE.ISO8859-1',
1287 'so_so': 'so_SO.ISO8859-1',
Georg Brandlf08a9dd2008-06-10 16:57:31 +00001288 'sp': 'sr_CS.ISO8859-5',
1289 'sp_yu': 'sr_CS.ISO8859-5',
Marc-André Lemburgbb4f1bd2004-12-10 21:58:14 +00001290 'spanish': 'es_ES.ISO8859-1',
Marc-André Lemburgbb4f1bd2004-12-10 21:58:14 +00001291 'spanish_spain': 'es_ES.ISO8859-1',
Marc-André Lemburgbb4f1bd2004-12-10 21:58:14 +00001292 'sq': 'sq_AL.ISO8859-2',
Benjamin Petersondf828082017-03-19 23:49:43 -07001293 'sq_al': 'sq_AL.ISO8859-2',
Serhiy Storchaka99cb41d2014-10-01 23:43:35 +03001294 'sq_mk': 'sq_MK.UTF-8',
Antoine Pitrou0c70d2d2010-04-11 22:35:34 +00001295 'sr': 'sr_RS.UTF-8',
1296 'sr@cyrillic': 'sr_RS.UTF-8',
Serhiy Storchaka715233c2013-12-20 18:23:26 +02001297 'sr@latn': 'sr_CS.UTF-8@latin',
1298 'sr_cs': 'sr_CS.UTF-8',
Georg Brandlf08a9dd2008-06-10 16:57:31 +00001299 'sr_cs.iso88592@latn': 'sr_CS.ISO8859-2',
Serhiy Storchaka715233c2013-12-20 18:23:26 +02001300 'sr_cs@latn': 'sr_CS.UTF-8@latin',
Antoine Pitrou0c70d2d2010-04-11 22:35:34 +00001301 'sr_me': 'sr_ME.UTF-8',
1302 'sr_rs': 'sr_RS.UTF-8',
Antoine Pitrou0c70d2d2010-04-11 22:35:34 +00001303 'sr_rs@latn': 'sr_RS.UTF-8@latin',
Georg Brandlf08a9dd2008-06-10 16:57:31 +00001304 'sr_sp': 'sr_CS.ISO8859-2',
Antoine Pitrou0c70d2d2010-04-11 22:35:34 +00001305 'sr_yu': 'sr_RS.UTF-8@latin',
Georg Brandlf08a9dd2008-06-10 16:57:31 +00001306 'sr_yu.cp1251@cyrillic': 'sr_CS.CP1251',
1307 'sr_yu.iso88592': 'sr_CS.ISO8859-2',
1308 'sr_yu.iso88595': 'sr_CS.ISO8859-5',
1309 'sr_yu.iso88595@cyrillic': 'sr_CS.ISO8859-5',
1310 'sr_yu.microsoftcp1251@cyrillic': 'sr_CS.CP1251',
Serhiy Storchaka1de0ba22014-10-02 00:09:37 +03001311 'sr_yu.utf8': 'sr_RS.UTF-8',
1312 'sr_yu.utf8@cyrillic': 'sr_RS.UTF-8',
Antoine Pitrou0c70d2d2010-04-11 22:35:34 +00001313 'sr_yu@cyrillic': 'sr_RS.UTF-8',
Georg Brandlf08a9dd2008-06-10 16:57:31 +00001314 'ss': 'ss_ZA.ISO8859-1',
Benjamin Petersondf828082017-03-19 23:49:43 -07001315 'ss_za': 'ss_ZA.ISO8859-1',
Georg Brandlf08a9dd2008-06-10 16:57:31 +00001316 'st': 'st_ZA.ISO8859-1',
1317 'st_za': 'st_ZA.ISO8859-1',
Marc-André Lemburgbb4f1bd2004-12-10 21:58:14 +00001318 'sv': 'sv_SE.ISO8859-1',
1319 'sv_fi': 'sv_FI.ISO8859-1',
Marc-André Lemburgbb4f1bd2004-12-10 21:58:14 +00001320 'sv_se': 'sv_SE.ISO8859-1',
Serhiy Storchaka99cb41d2014-10-01 23:43:35 +03001321 'sw_ke': 'sw_KE.UTF-8',
1322 'sw_tz': 'sw_TZ.UTF-8',
Marc-André Lemburgbb4f1bd2004-12-10 21:58:14 +00001323 'swedish': 'sv_SE.ISO8859-1',
Serhiy Storchaka99cb41d2014-10-01 23:43:35 +03001324 'szl_pl': 'szl_PL.UTF-8',
Marc-André Lemburgbb4f1bd2004-12-10 21:58:14 +00001325 'ta': 'ta_IN.TSCII-0',
Benjamin Petersondf828082017-03-19 23:49:43 -07001326 'ta_in': 'ta_IN.TSCII-0',
Marc-André Lemburgbb4f1bd2004-12-10 21:58:14 +00001327 'ta_in.tscii': 'ta_IN.TSCII-0',
1328 'ta_in.tscii0': 'ta_IN.TSCII-0',
Serhiy Storchaka99cb41d2014-10-01 23:43:35 +03001329 'ta_lk': 'ta_LK.UTF-8',
Antoine Pitrou0c70d2d2010-04-11 22:35:34 +00001330 'te': 'te_IN.UTF-8',
Serhiy Storchaka99cb41d2014-10-01 23:43:35 +03001331 'te_in': 'te_IN.UTF-8',
Marc-André Lemburgbb4f1bd2004-12-10 21:58:14 +00001332 'tg': 'tg_TJ.KOI8-C',
Benjamin Petersondf828082017-03-19 23:49:43 -07001333 'tg_tj': 'tg_TJ.KOI8-C',
Marc-André Lemburgbb4f1bd2004-12-10 21:58:14 +00001334 'th': 'th_TH.ISO8859-11',
Benjamin Petersondf828082017-03-19 23:49:43 -07001335 'th_th': 'th_TH.ISO8859-11',
Marc-André Lemburgbb4f1bd2004-12-10 21:58:14 +00001336 'th_th.tactis': 'th_TH.TIS620',
1337 'th_th.tis620': 'th_TH.TIS620',
Marc-André Lemburgbb4f1bd2004-12-10 21:58:14 +00001338 'thai': 'th_TH.ISO8859-11',
Serhiy Storchaka99cb41d2014-10-01 23:43:35 +03001339 'ti_er': 'ti_ER.UTF-8',
1340 'ti_et': 'ti_ET.UTF-8',
1341 'tig_er': 'tig_ER.UTF-8',
1342 'tk_tm': 'tk_TM.UTF-8',
Marc-André Lemburgbb4f1bd2004-12-10 21:58:14 +00001343 'tl': 'tl_PH.ISO8859-1',
1344 'tl_ph': 'tl_PH.ISO8859-1',
Georg Brandlf08a9dd2008-06-10 16:57:31 +00001345 'tn': 'tn_ZA.ISO8859-15',
Benjamin Petersondf828082017-03-19 23:49:43 -07001346 'tn_za': 'tn_ZA.ISO8859-15',
Marc-André Lemburgbb4f1bd2004-12-10 21:58:14 +00001347 'tr': 'tr_TR.ISO8859-9',
Serhiy Storchaka99cb41d2014-10-01 23:43:35 +03001348 'tr_cy': 'tr_CY.ISO8859-9',
Marc-André Lemburgbb4f1bd2004-12-10 21:58:14 +00001349 'tr_tr': 'tr_TR.ISO8859-9',
Georg Brandlf08a9dd2008-06-10 16:57:31 +00001350 'ts': 'ts_ZA.ISO8859-1',
Benjamin Petersondf828082017-03-19 23:49:43 -07001351 'ts_za': 'ts_ZA.ISO8859-1',
Marc-André Lemburgbb4f1bd2004-12-10 21:58:14 +00001352 'tt': 'tt_RU.TATAR-CYR',
Benjamin Petersondf828082017-03-19 23:49:43 -07001353 'tt_ru': 'tt_RU.TATAR-CYR',
Marc-André Lemburgbb4f1bd2004-12-10 21:58:14 +00001354 'tt_ru.tatarcyr': 'tt_RU.TATAR-CYR',
Benjamin Petersondf828082017-03-19 23:49:43 -07001355 'tt_ru@iqtelif': 'tt_RU.UTF-8@iqtelif',
Marc-André Lemburgbb4f1bd2004-12-10 21:58:14 +00001356 'turkish': 'tr_TR.ISO8859-9',
Serhiy Storchaka99cb41d2014-10-01 23:43:35 +03001357 'ug_cn': 'ug_CN.UTF-8',
Marc-André Lemburgbb4f1bd2004-12-10 21:58:14 +00001358 'uk': 'uk_UA.KOI8-U',
1359 'uk_ua': 'uk_UA.KOI8-U',
Benjamin Petersondf828082017-03-19 23:49:43 -07001360 'univ': 'en_US.utf',
1361 'universal': 'en_US.utf',
Marc-André Lemburgbb4f1bd2004-12-10 21:58:14 +00001362 'universal.utf8@ucs4': 'en_US.UTF-8',
Serhiy Storchaka99cb41d2014-10-01 23:43:35 +03001363 'unm_us': 'unm_US.UTF-8',
Marc-André Lemburgbb4f1bd2004-12-10 21:58:14 +00001364 'ur': 'ur_PK.CP1256',
Serhiy Storchaka715233c2013-12-20 18:23:26 +02001365 'ur_in': 'ur_IN.UTF-8',
Benjamin Petersondf828082017-03-19 23:49:43 -07001366 'ur_pk': 'ur_PK.CP1256',
Marc-André Lemburgbb4f1bd2004-12-10 21:58:14 +00001367 'uz': 'uz_UZ.UTF-8',
Benjamin Petersondf828082017-03-19 23:49:43 -07001368 'uz_uz': 'uz_UZ.UTF-8',
1369 'uz_uz@cyrillic': 'uz_UZ.UTF-8',
Georg Brandlf08a9dd2008-06-10 16:57:31 +00001370 've': 've_ZA.UTF-8',
1371 've_za': 've_ZA.UTF-8',
Marc-André Lemburgbb4f1bd2004-12-10 21:58:14 +00001372 'vi': 'vi_VN.TCVN',
Benjamin Petersondf828082017-03-19 23:49:43 -07001373 'vi_vn': 'vi_VN.TCVN',
Marc-André Lemburgbb4f1bd2004-12-10 21:58:14 +00001374 'vi_vn.tcvn': 'vi_VN.TCVN',
1375 'vi_vn.tcvn5712': 'vi_VN.TCVN',
Marc-André Lemburgbb4f1bd2004-12-10 21:58:14 +00001376 'vi_vn.viscii': 'vi_VN.VISCII',
1377 'vi_vn.viscii111': 'vi_VN.VISCII',
1378 'wa': 'wa_BE.ISO8859-1',
1379 'wa_be': 'wa_BE.ISO8859-1',
Serhiy Storchaka99cb41d2014-10-01 23:43:35 +03001380 'wae_ch': 'wae_CH.UTF-8',
1381 'wal_et': 'wal_ET.UTF-8',
1382 'wo_sn': 'wo_SN.UTF-8',
Georg Brandlf08a9dd2008-06-10 16:57:31 +00001383 'xh': 'xh_ZA.ISO8859-1',
1384 'xh_za': 'xh_ZA.ISO8859-1',
Marc-André Lemburgbb4f1bd2004-12-10 21:58:14 +00001385 'yi': 'yi_US.CP1255',
1386 'yi_us': 'yi_US.CP1255',
Serhiy Storchaka99cb41d2014-10-01 23:43:35 +03001387 'yo_ng': 'yo_NG.UTF-8',
1388 'yue_hk': 'yue_HK.UTF-8',
Marc-André Lemburgbb4f1bd2004-12-10 21:58:14 +00001389 'zh': 'zh_CN.eucCN',
Benjamin Petersondf828082017-03-19 23:49:43 -07001390 'zh_cn': 'zh_CN.gb2312',
Marc-André Lemburgbb4f1bd2004-12-10 21:58:14 +00001391 'zh_cn.big5': 'zh_TW.big5',
1392 'zh_cn.euc': 'zh_CN.eucCN',
Marc-André Lemburgbb4f1bd2004-12-10 21:58:14 +00001393 'zh_hk': 'zh_HK.big5hkscs',
Antoine Pitrou0c70d2d2010-04-11 22:35:34 +00001394 'zh_hk.big5hk': 'zh_HK.big5hkscs',
Serhiy Storchaka99cb41d2014-10-01 23:43:35 +03001395 'zh_sg': 'zh_SG.GB2312',
1396 'zh_sg.gbk': 'zh_SG.GBK',
Benjamin Petersondf828082017-03-19 23:49:43 -07001397 'zh_tw': 'zh_TW.big5',
Marc-André Lemburgbb4f1bd2004-12-10 21:58:14 +00001398 'zh_tw.euc': 'zh_TW.eucTW',
Benjamin Petersondf828082017-03-19 23:49:43 -07001399 'zh_tw.euctw': 'zh_TW.eucTW',
Georg Brandlf08a9dd2008-06-10 16:57:31 +00001400 'zu': 'zu_ZA.ISO8859-1',
1401 'zu_za': 'zu_ZA.ISO8859-1',
Marc-André Lemburg5431bc32000-06-07 09:11:40 +00001402}
1403
Fredrik Lundh6c86b992000-07-09 17:12:58 +00001404#
Georg Brandlb709c2c2006-01-20 09:07:35 +00001405# This maps Windows language identifiers to locale strings.
Fredrik Lundh6c86b992000-07-09 17:12:58 +00001406#
Tim Peters777f1082006-01-20 20:03:24 +00001407# This list has been updated from
Georg Brandlb709c2c2006-01-20 09:07:35 +00001408# http://msdn.microsoft.com/library/default.asp?url=/library/en-us/intl/nls_238z.asp
Jeroen Ruigrok van der Werven0a866942009-05-08 14:18:00 +00001409# to include every locale up to Windows Vista.
Fredrik Lundh37a09822002-10-19 20:19:10 +00001410#
Georg Brandl5035c1c2006-01-20 13:38:26 +00001411# NOTE: this mapping is incomplete. If your language is missing, please
Éric Araujoa2b89e32011-11-29 16:36:17 +01001412# submit a bug report to the Python bug tracker at http://bugs.python.org/
Georg Brandl5035c1c2006-01-20 13:38:26 +00001413# Make sure you include the missing language identifier and the suggested
1414# locale code.
1415#
Fredrik Lundh6c86b992000-07-09 17:12:58 +00001416
1417windows_locale = {
Georg Brandlb709c2c2006-01-20 09:07:35 +00001418 0x0436: "af_ZA", # Afrikaans
1419 0x041c: "sq_AL", # Albanian
Jeroen Ruigrok van der Werven0a866942009-05-08 14:18:00 +00001420 0x0484: "gsw_FR",# Alsatian - France
1421 0x045e: "am_ET", # Amharic - Ethiopia
Georg Brandlb709c2c2006-01-20 09:07:35 +00001422 0x0401: "ar_SA", # Arabic - Saudi Arabia
1423 0x0801: "ar_IQ", # Arabic - Iraq
1424 0x0c01: "ar_EG", # Arabic - Egypt
1425 0x1001: "ar_LY", # Arabic - Libya
1426 0x1401: "ar_DZ", # Arabic - Algeria
1427 0x1801: "ar_MA", # Arabic - Morocco
1428 0x1c01: "ar_TN", # Arabic - Tunisia
1429 0x2001: "ar_OM", # Arabic - Oman
1430 0x2401: "ar_YE", # Arabic - Yemen
1431 0x2801: "ar_SY", # Arabic - Syria
1432 0x2c01: "ar_JO", # Arabic - Jordan
1433 0x3001: "ar_LB", # Arabic - Lebanon
1434 0x3401: "ar_KW", # Arabic - Kuwait
1435 0x3801: "ar_AE", # Arabic - United Arab Emirates
1436 0x3c01: "ar_BH", # Arabic - Bahrain
1437 0x4001: "ar_QA", # Arabic - Qatar
1438 0x042b: "hy_AM", # Armenian
Jeroen Ruigrok van der Werven0a866942009-05-08 14:18:00 +00001439 0x044d: "as_IN", # Assamese - India
1440 0x042c: "az_AZ", # Azeri - Latin
Georg Brandlb709c2c2006-01-20 09:07:35 +00001441 0x082c: "az_AZ", # Azeri - Cyrillic
Jeroen Ruigrok van der Werven0a866942009-05-08 14:18:00 +00001442 0x046d: "ba_RU", # Bashkir
1443 0x042d: "eu_ES", # Basque - Russia
Georg Brandlb709c2c2006-01-20 09:07:35 +00001444 0x0423: "be_BY", # Belarusian
1445 0x0445: "bn_IN", # Begali
Jeroen Ruigrok van der Werven0a866942009-05-08 14:18:00 +00001446 0x201a: "bs_BA", # Bosnian - Cyrillic
1447 0x141a: "bs_BA", # Bosnian - Latin
Georg Brandlb709c2c2006-01-20 09:07:35 +00001448 0x047e: "br_FR", # Breton - France
1449 0x0402: "bg_BG", # Bulgarian
Jeroen Ruigrok van der Werven0a866942009-05-08 14:18:00 +00001450# 0x0455: "my_MM", # Burmese - Not supported
Georg Brandlb709c2c2006-01-20 09:07:35 +00001451 0x0403: "ca_ES", # Catalan
1452 0x0004: "zh_CHS",# Chinese - Simplified
1453 0x0404: "zh_TW", # Chinese - Taiwan
1454 0x0804: "zh_CN", # Chinese - PRC
1455 0x0c04: "zh_HK", # Chinese - Hong Kong S.A.R.
1456 0x1004: "zh_SG", # Chinese - Singapore
1457 0x1404: "zh_MO", # Chinese - Macao S.A.R.
1458 0x7c04: "zh_CHT",# Chinese - Traditional
Jeroen Ruigrok van der Werven0a866942009-05-08 14:18:00 +00001459 0x0483: "co_FR", # Corsican - France
Georg Brandlb709c2c2006-01-20 09:07:35 +00001460 0x041a: "hr_HR", # Croatian
1461 0x101a: "hr_BA", # Croatian - Bosnia
1462 0x0405: "cs_CZ", # Czech
Fredrik Lundh6c86b992000-07-09 17:12:58 +00001463 0x0406: "da_DK", # Danish
Georg Brandlb709c2c2006-01-20 09:07:35 +00001464 0x048c: "gbz_AF",# Dari - Afghanistan
1465 0x0465: "div_MV",# Divehi - Maldives
1466 0x0413: "nl_NL", # Dutch - The Netherlands
1467 0x0813: "nl_BE", # Dutch - Belgium
1468 0x0409: "en_US", # English - United States
1469 0x0809: "en_GB", # English - United Kingdom
1470 0x0c09: "en_AU", # English - Australia
1471 0x1009: "en_CA", # English - Canada
1472 0x1409: "en_NZ", # English - New Zealand
1473 0x1809: "en_IE", # English - Ireland
1474 0x1c09: "en_ZA", # English - South Africa
1475 0x2009: "en_JA", # English - Jamaica
Martin Panter46f50722016-05-26 05:35:26 +00001476 0x2409: "en_CB", # English - Caribbean
Georg Brandlb709c2c2006-01-20 09:07:35 +00001477 0x2809: "en_BZ", # English - Belize
1478 0x2c09: "en_TT", # English - Trinidad
1479 0x3009: "en_ZW", # English - Zimbabwe
Jeroen Ruigrok van der Werven0a866942009-05-08 14:18:00 +00001480 0x3409: "en_PH", # English - Philippines
1481 0x4009: "en_IN", # English - India
1482 0x4409: "en_MY", # English - Malaysia
1483 0x4809: "en_IN", # English - Singapore
Georg Brandlb709c2c2006-01-20 09:07:35 +00001484 0x0425: "et_EE", # Estonian
1485 0x0438: "fo_FO", # Faroese
1486 0x0464: "fil_PH",# Filipino
Fredrik Lundh6c86b992000-07-09 17:12:58 +00001487 0x040b: "fi_FI", # Finnish
Georg Brandlb709c2c2006-01-20 09:07:35 +00001488 0x040c: "fr_FR", # French - France
1489 0x080c: "fr_BE", # French - Belgium
1490 0x0c0c: "fr_CA", # French - Canada
1491 0x100c: "fr_CH", # French - Switzerland
1492 0x140c: "fr_LU", # French - Luxembourg
1493 0x180c: "fr_MC", # French - Monaco
1494 0x0462: "fy_NL", # Frisian - Netherlands
1495 0x0456: "gl_ES", # Galician
1496 0x0437: "ka_GE", # Georgian
1497 0x0407: "de_DE", # German - Germany
1498 0x0807: "de_CH", # German - Switzerland
1499 0x0c07: "de_AT", # German - Austria
1500 0x1007: "de_LU", # German - Luxembourg
1501 0x1407: "de_LI", # German - Liechtenstein
Fredrik Lundh6c86b992000-07-09 17:12:58 +00001502 0x0408: "el_GR", # Greek
Jeroen Ruigrok van der Werven0a866942009-05-08 14:18:00 +00001503 0x046f: "kl_GL", # Greenlandic - Greenland
Georg Brandlb709c2c2006-01-20 09:07:35 +00001504 0x0447: "gu_IN", # Gujarati
Jeroen Ruigrok van der Werven0a866942009-05-08 14:18:00 +00001505 0x0468: "ha_NG", # Hausa - Latin
Georg Brandlb709c2c2006-01-20 09:07:35 +00001506 0x040d: "he_IL", # Hebrew
1507 0x0439: "hi_IN", # Hindi
1508 0x040e: "hu_HU", # Hungarian
Fredrik Lundh6c86b992000-07-09 17:12:58 +00001509 0x040f: "is_IS", # Icelandic
Georg Brandlb709c2c2006-01-20 09:07:35 +00001510 0x0421: "id_ID", # Indonesian
Jeroen Ruigrok van der Werven0a866942009-05-08 14:18:00 +00001511 0x045d: "iu_CA", # Inuktitut - Syllabics
Georg Brandlb709c2c2006-01-20 09:07:35 +00001512 0x085d: "iu_CA", # Inuktitut - Latin
1513 0x083c: "ga_IE", # Irish - Ireland
Georg Brandlb709c2c2006-01-20 09:07:35 +00001514 0x0410: "it_IT", # Italian - Italy
1515 0x0810: "it_CH", # Italian - Switzerland
1516 0x0411: "ja_JP", # Japanese
1517 0x044b: "kn_IN", # Kannada - India
1518 0x043f: "kk_KZ", # Kazakh
Jeroen Ruigrok van der Werven0a866942009-05-08 14:18:00 +00001519 0x0453: "kh_KH", # Khmer - Cambodia
1520 0x0486: "qut_GT",# K'iche - Guatemala
1521 0x0487: "rw_RW", # Kinyarwanda - Rwanda
Georg Brandlb709c2c2006-01-20 09:07:35 +00001522 0x0457: "kok_IN",# Konkani
1523 0x0412: "ko_KR", # Korean
1524 0x0440: "ky_KG", # Kyrgyz
Jeroen Ruigrok van der Werven0a866942009-05-08 14:18:00 +00001525 0x0454: "lo_LA", # Lao - Lao PDR
Georg Brandlb709c2c2006-01-20 09:07:35 +00001526 0x0426: "lv_LV", # Latvian
1527 0x0427: "lt_LT", # Lithuanian
Jeroen Ruigrok van der Werven0a866942009-05-08 14:18:00 +00001528 0x082e: "dsb_DE",# Lower Sorbian - Germany
Georg Brandlb709c2c2006-01-20 09:07:35 +00001529 0x046e: "lb_LU", # Luxembourgish
Jeroen Ruigrok van der Werven0a866942009-05-08 14:18:00 +00001530 0x042f: "mk_MK", # FYROM Macedonian
Georg Brandlb709c2c2006-01-20 09:07:35 +00001531 0x043e: "ms_MY", # Malay - Malaysia
Jeroen Ruigrok van der Werven0a866942009-05-08 14:18:00 +00001532 0x083e: "ms_BN", # Malay - Brunei Darussalam
Georg Brandlb709c2c2006-01-20 09:07:35 +00001533 0x044c: "ml_IN", # Malayalam - India
1534 0x043a: "mt_MT", # Maltese
1535 0x0481: "mi_NZ", # Maori
1536 0x047a: "arn_CL",# Mapudungun
1537 0x044e: "mr_IN", # Marathi
1538 0x047c: "moh_CA",# Mohawk - Canada
Jeroen Ruigrok van der Werven0a866942009-05-08 14:18:00 +00001539 0x0450: "mn_MN", # Mongolian - Cyrillic
1540 0x0850: "mn_CN", # Mongolian - PRC
Georg Brandlb709c2c2006-01-20 09:07:35 +00001541 0x0461: "ne_NP", # Nepali
1542 0x0414: "nb_NO", # Norwegian - Bokmal
1543 0x0814: "nn_NO", # Norwegian - Nynorsk
1544 0x0482: "oc_FR", # Occitan - France
1545 0x0448: "or_IN", # Oriya - India
1546 0x0463: "ps_AF", # Pashto - Afghanistan
1547 0x0429: "fa_IR", # Persian
1548 0x0415: "pl_PL", # Polish
1549 0x0416: "pt_BR", # Portuguese - Brazil
1550 0x0816: "pt_PT", # Portuguese - Portugal
1551 0x0446: "pa_IN", # Punjabi
1552 0x046b: "quz_BO",# Quechua (Bolivia)
1553 0x086b: "quz_EC",# Quechua (Ecuador)
1554 0x0c6b: "quz_PE",# Quechua (Peru)
1555 0x0418: "ro_RO", # Romanian - Romania
Jeroen Ruigrok van der Werven0a866942009-05-08 14:18:00 +00001556 0x0417: "rm_CH", # Romansh
Georg Brandlb709c2c2006-01-20 09:07:35 +00001557 0x0419: "ru_RU", # Russian
1558 0x243b: "smn_FI",# Sami Finland
1559 0x103b: "smj_NO",# Sami Norway
1560 0x143b: "smj_SE",# Sami Sweden
1561 0x043b: "se_NO", # Sami Northern Norway
1562 0x083b: "se_SE", # Sami Northern Sweden
1563 0x0c3b: "se_FI", # Sami Northern Finland
1564 0x203b: "sms_FI",# Sami Skolt
1565 0x183b: "sma_NO",# Sami Southern Norway
1566 0x1c3b: "sma_SE",# Sami Southern Sweden
1567 0x044f: "sa_IN", # Sanskrit
1568 0x0c1a: "sr_SP", # Serbian - Cyrillic
1569 0x1c1a: "sr_BA", # Serbian - Bosnia Cyrillic
1570 0x081a: "sr_SP", # Serbian - Latin
1571 0x181a: "sr_BA", # Serbian - Bosnia Latin
Jeroen Ruigrok van der Werven0a866942009-05-08 14:18:00 +00001572 0x045b: "si_LK", # Sinhala - Sri Lanka
Georg Brandlb709c2c2006-01-20 09:07:35 +00001573 0x046c: "ns_ZA", # Northern Sotho
1574 0x0432: "tn_ZA", # Setswana - Southern Africa
1575 0x041b: "sk_SK", # Slovak
1576 0x0424: "sl_SI", # Slovenian
1577 0x040a: "es_ES", # Spanish - Spain
1578 0x080a: "es_MX", # Spanish - Mexico
1579 0x0c0a: "es_ES", # Spanish - Spain (Modern)
1580 0x100a: "es_GT", # Spanish - Guatemala
1581 0x140a: "es_CR", # Spanish - Costa Rica
1582 0x180a: "es_PA", # Spanish - Panama
1583 0x1c0a: "es_DO", # Spanish - Dominican Republic
1584 0x200a: "es_VE", # Spanish - Venezuela
1585 0x240a: "es_CO", # Spanish - Colombia
1586 0x280a: "es_PE", # Spanish - Peru
1587 0x2c0a: "es_AR", # Spanish - Argentina
1588 0x300a: "es_EC", # Spanish - Ecuador
1589 0x340a: "es_CL", # Spanish - Chile
1590 0x380a: "es_UR", # Spanish - Uruguay
1591 0x3c0a: "es_PY", # Spanish - Paraguay
1592 0x400a: "es_BO", # Spanish - Bolivia
1593 0x440a: "es_SV", # Spanish - El Salvador
1594 0x480a: "es_HN", # Spanish - Honduras
1595 0x4c0a: "es_NI", # Spanish - Nicaragua
1596 0x500a: "es_PR", # Spanish - Puerto Rico
Jeroen Ruigrok van der Werven0a866942009-05-08 14:18:00 +00001597 0x540a: "es_US", # Spanish - United States
1598# 0x0430: "", # Sutu - Not supported
Georg Brandlb709c2c2006-01-20 09:07:35 +00001599 0x0441: "sw_KE", # Swahili
1600 0x041d: "sv_SE", # Swedish - Sweden
1601 0x081d: "sv_FI", # Swedish - Finland
1602 0x045a: "syr_SY",# Syriac
Jeroen Ruigrok van der Werven0a866942009-05-08 14:18:00 +00001603 0x0428: "tg_TJ", # Tajik - Cyrillic
1604 0x085f: "tmz_DZ",# Tamazight - Latin
Georg Brandlb709c2c2006-01-20 09:07:35 +00001605 0x0449: "ta_IN", # Tamil
1606 0x0444: "tt_RU", # Tatar
1607 0x044a: "te_IN", # Telugu
1608 0x041e: "th_TH", # Thai
Jeroen Ruigrok van der Werven0a866942009-05-08 14:18:00 +00001609 0x0851: "bo_BT", # Tibetan - Bhutan
1610 0x0451: "bo_CN", # Tibetan - PRC
Fredrik Lundh6c86b992000-07-09 17:12:58 +00001611 0x041f: "tr_TR", # Turkish
Jeroen Ruigrok van der Werven0a866942009-05-08 14:18:00 +00001612 0x0442: "tk_TM", # Turkmen - Cyrillic
1613 0x0480: "ug_CN", # Uighur - Arabic
Georg Brandlb709c2c2006-01-20 09:07:35 +00001614 0x0422: "uk_UA", # Ukrainian
Jeroen Ruigrok van der Werven0a866942009-05-08 14:18:00 +00001615 0x042e: "wen_DE",# Upper Sorbian - Germany
Georg Brandlb709c2c2006-01-20 09:07:35 +00001616 0x0420: "ur_PK", # Urdu
1617 0x0820: "ur_IN", # Urdu - India
1618 0x0443: "uz_UZ", # Uzbek - Latin
1619 0x0843: "uz_UZ", # Uzbek - Cyrillic
1620 0x042a: "vi_VN", # Vietnamese
1621 0x0452: "cy_GB", # Welsh
Jeroen Ruigrok van der Werven0a866942009-05-08 14:18:00 +00001622 0x0488: "wo_SN", # Wolof - Senegal
1623 0x0434: "xh_ZA", # Xhosa - South Africa
1624 0x0485: "sah_RU",# Yakut - Cyrillic
1625 0x0478: "ii_CN", # Yi - PRC
1626 0x046a: "yo_NG", # Yoruba - Nigeria
1627 0x0435: "zu_ZA", # Zulu
Fredrik Lundh6c86b992000-07-09 17:12:58 +00001628}
1629
Marc-André Lemburg5431bc32000-06-07 09:11:40 +00001630def _print_locale():
1631
1632 """ Test function.
1633 """
1634 categories = {}
1635 def _init_categories(categories=categories):
1636 for k,v in globals().items():
1637 if k[:3] == 'LC_':
1638 categories[k] = v
1639 _init_categories()
1640 del categories['LC_ALL']
1641
Guido van Rossumbe19ed72007-02-09 05:37:30 +00001642 print('Locale defaults as determined by getdefaultlocale():')
1643 print('-'*72)
Fredrik Lundh6c86b992000-07-09 17:12:58 +00001644 lang, enc = getdefaultlocale()
Guido van Rossumbe19ed72007-02-09 05:37:30 +00001645 print('Language: ', lang or '(undefined)')
1646 print('Encoding: ', enc or '(undefined)')
1647 print()
Marc-André Lemburg5431bc32000-06-07 09:11:40 +00001648
Guido van Rossumbe19ed72007-02-09 05:37:30 +00001649 print('Locale settings on startup:')
1650 print('-'*72)
Marc-André Lemburg5431bc32000-06-07 09:11:40 +00001651 for name,category in categories.items():
Guido van Rossumbe19ed72007-02-09 05:37:30 +00001652 print(name, '...')
Fredrik Lundh6c86b992000-07-09 17:12:58 +00001653 lang, enc = getlocale(category)
Guido van Rossumbe19ed72007-02-09 05:37:30 +00001654 print(' Language: ', lang or '(undefined)')
1655 print(' Encoding: ', enc or '(undefined)')
1656 print()
Marc-André Lemburg5431bc32000-06-07 09:11:40 +00001657
Guido van Rossumbe19ed72007-02-09 05:37:30 +00001658 print()
1659 print('Locale settings after calling resetlocale():')
1660 print('-'*72)
Fredrik Lundh6c86b992000-07-09 17:12:58 +00001661 resetlocale()
Marc-André Lemburg5431bc32000-06-07 09:11:40 +00001662 for name,category in categories.items():
Guido van Rossumbe19ed72007-02-09 05:37:30 +00001663 print(name, '...')
Fredrik Lundh6c86b992000-07-09 17:12:58 +00001664 lang, enc = getlocale(category)
Guido van Rossumbe19ed72007-02-09 05:37:30 +00001665 print(' Language: ', lang or '(undefined)')
1666 print(' Encoding: ', enc or '(undefined)')
1667 print()
Fredrik Lundh6c86b992000-07-09 17:12:58 +00001668
Marc-André Lemburg5431bc32000-06-07 09:11:40 +00001669 try:
Fredrik Lundh6c86b992000-07-09 17:12:58 +00001670 setlocale(LC_ALL, "")
Marc-André Lemburg5431bc32000-06-07 09:11:40 +00001671 except:
Guido van Rossumbe19ed72007-02-09 05:37:30 +00001672 print('NOTE:')
1673 print('setlocale(LC_ALL, "") does not support the default locale')
1674 print('given in the OS environment variables.')
Marc-André Lemburg5431bc32000-06-07 09:11:40 +00001675 else:
Guido van Rossumbe19ed72007-02-09 05:37:30 +00001676 print()
1677 print('Locale settings after calling setlocale(LC_ALL, ""):')
1678 print('-'*72)
Marc-André Lemburg5431bc32000-06-07 09:11:40 +00001679 for name,category in categories.items():
Guido van Rossumbe19ed72007-02-09 05:37:30 +00001680 print(name, '...')
Fredrik Lundh6c86b992000-07-09 17:12:58 +00001681 lang, enc = getlocale(category)
Guido van Rossumbe19ed72007-02-09 05:37:30 +00001682 print(' Language: ', lang or '(undefined)')
1683 print(' Encoding: ', enc or '(undefined)')
1684 print()
Fredrik Lundh6c86b992000-07-09 17:12:58 +00001685
Marc-André Lemburg5431bc32000-06-07 09:11:40 +00001686###
Guido van Rossumeef1d4e1997-11-19 19:01:43 +00001687
Tim Peters1baf8292001-01-24 10:13:46 +00001688try:
1689 LC_MESSAGES
Skip Montanaro0897f0c2002-03-25 21:40:36 +00001690except NameError:
Tim Peters1baf8292001-01-24 10:13:46 +00001691 pass
1692else:
1693 __all__.append("LC_MESSAGES")
1694
Guido van Rossumeef1d4e1997-11-19 19:01:43 +00001695if __name__=='__main__':
Guido van Rossumbe19ed72007-02-09 05:37:30 +00001696 print('Locale aliasing:')
1697 print()
Marc-André Lemburg5431bc32000-06-07 09:11:40 +00001698 _print_locale()
Guido van Rossumbe19ed72007-02-09 05:37:30 +00001699 print()
1700 print('Number formatting:')
1701 print()
Marc-André Lemburg5431bc32000-06-07 09:11:40 +00001702 _test()