Python code coverage for Lib/locale.py

#	count	content
1	n/a	"""Locale support module.
2	n/a
3	n/a	The module provides low-level access to the C lib's locale APIs and adds high
4	n/a	level number formatting APIs as well as a locale aliasing engine to complement
5	n/a	these.
6	n/a
7	n/a	The aliasing engine includes support for many commonly used locale names and
8	n/a	maps them to values suitable for passing to the C lib's setlocale() function. It
9	n/a	also includes default encodings for all supported locale names.
10	n/a
11	n/a	"""
12	n/a
13	n/a	import sys
14	n/a	import encodings
15	n/a	import encodings.aliases
16	n/a	import re
17	n/a	import collections
18	n/a	from builtins import str as _builtin_str
19	n/a	import functools
20	n/a
21	n/a	# Try importing the _locale module.
22	n/a	#
23	n/a	# If this fails, fall back on a basic 'C' locale emulation.
24	n/a
25	n/a	# Yuck: LC_MESSAGES is non-standard: can't tell whether it exists before
26	n/a	# trying the import. So __all__ is also fiddled at the end of the file.
27	n/a	__all__ = ["getlocale", "getdefaultlocale", "getpreferredencoding", "Error",
28	n/a	"setlocale", "resetlocale", "localeconv", "strcoll", "strxfrm",
29	n/a	"str", "atof", "atoi", "format", "format_string", "currency",
30	n/a	"normalize", "LC_CTYPE", "LC_COLLATE", "LC_TIME", "LC_MONETARY",
31	n/a	"LC_NUMERIC", "LC_ALL", "CHAR_MAX"]
32	n/a
33	n/a	def _strcoll(a,b):
34	n/a	""" strcoll(string,string) -> int.
35	n/a	Compares two strings according to the locale.
36	n/a	"""
37	n/a	return (a > b) - (a < b)
38	n/a
39	n/a	def _strxfrm(s):
40	n/a	""" strxfrm(string) -> string.
41	n/a	Returns a string that behaves for cmp locale-aware.
42	n/a	"""
43	n/a	return s
44	n/a
45	n/a	try:
46	n/a
47	n/a	from _locale import *
48	n/a
49	n/a	except ImportError:
50	n/a
51	n/a	# Locale emulation
52	n/a
53	n/a	CHAR_MAX = 127
54	n/a	LC_ALL = 6
55	n/a	LC_COLLATE = 3
56	n/a	LC_CTYPE = 0
57	n/a	LC_MESSAGES = 5
58	n/a	LC_MONETARY = 4
59	n/a	LC_NUMERIC = 1
60	n/a	LC_TIME = 2
61	n/a	Error = ValueError
62	n/a
63	n/a	def localeconv():
64	n/a	""" localeconv() -> dict.
65	n/a	Returns numeric and monetary locale-specific parameters.
66	n/a	"""
67	n/a	# 'C' locale default values
68	n/a	return {'grouping': [127],
69	n/a	'currency_symbol': '',
70	n/a	'n_sign_posn': 127,
71	n/a	'p_cs_precedes': 127,
72	n/a	'n_cs_precedes': 127,
73	n/a	'mon_grouping': [],
74	n/a	'n_sep_by_space': 127,
75	n/a	'decimal_point': '.',
76	n/a	'negative_sign': '',
77	n/a	'positive_sign': '',
78	n/a	'p_sep_by_space': 127,
79	n/a	'int_curr_symbol': '',
80	n/a	'p_sign_posn': 127,
81	n/a	'thousands_sep': '',
82	n/a	'mon_thousands_sep': '',
83	n/a	'frac_digits': 127,
84	n/a	'mon_decimal_point': '',
85	n/a	'int_frac_digits': 127}
86	n/a
87	n/a	def setlocale(category, value=None):
88	n/a	""" setlocale(integer,string=None) -> string.
89	n/a	Activates/queries locale processing.
90	n/a	"""
91	n/a	if value not in (None, '', 'C'):
92	n/a	raise Error('_locale emulation only supports "C" locale')
93	n/a	return 'C'
94	n/a
95	n/a	# These may or may not exist in _locale, so be sure to set them.
96	n/a	if 'strxfrm' not in globals():
97	n/a	strxfrm = _strxfrm
98	n/a	if 'strcoll' not in globals():
99	n/a	strcoll = _strcoll
100	n/a
101	n/a
102	n/a	_localeconv = localeconv
103	n/a
104	n/a	# With this dict, you can override some items of localeconv's return value.
105	n/a	# This is useful for testing purposes.
106	n/a	_override_localeconv = {}
107	n/a
108	n/a	@functools.wraps(_localeconv)
109	n/a	def localeconv():
110	n/a	d = _localeconv()
111	n/a	if _override_localeconv:
112	n/a	d.update(_override_localeconv)
113	n/a	return d
114	n/a
115	n/a
116	n/a	### Number formatting APIs
117	n/a
118	n/a	# Author: Martin von Loewis
119	n/a	# improved by Georg Brandl
120	n/a
121	n/a	# Iterate over grouping intervals
122	n/a	def _grouping_intervals(grouping):
123	n/a	last_interval = None
124	n/a	for interval in grouping:
125	n/a	# if grouping is -1, we are done
126	n/a	if interval == CHAR_MAX:
127	n/a	return
128	n/a	# 0: re-use last group ad infinitum
129	n/a	if interval == 0:
130	n/a	if last_interval is None:
131	n/a	raise ValueError("invalid grouping")
132	n/a	while True:
133	n/a	yield last_interval
134	n/a	yield interval
135	n/a	last_interval = interval
136	n/a
137	n/a	#perform the grouping from right to left
138	n/a	def _group(s, monetary=False):
139	n/a	conv = localeconv()
140	n/a	thousands_sep = conv[monetary and 'mon_thousands_sep' or 'thousands_sep']
141	n/a	grouping = conv[monetary and 'mon_grouping' or 'grouping']
142	n/a	if not grouping:
143	n/a	return (s, 0)
144	n/a	if s[-1] == ' ':
145	n/a	stripped = s.rstrip()
146	n/a	right_spaces = s[len(stripped):]
147	n/a	s = stripped
148	n/a	else:
149	n/a	right_spaces = ''
150	n/a	left_spaces = ''
151	n/a	groups = []
152	n/a	for interval in _grouping_intervals(grouping):
153	n/a	if not s or s[-1] not in "0123456789":
154	n/a	# only non-digit characters remain (sign, spaces)
155	n/a	left_spaces = s
156	n/a	s = ''
157	n/a	break
158	n/a	groups.append(s[-interval:])
159	n/a	s = s[:-interval]
160	n/a	if s:
161	n/a	groups.append(s)
162	n/a	groups.reverse()
163	n/a	return (
164	n/a	left_spaces + thousands_sep.join(groups) + right_spaces,
165	n/a	len(thousands_sep) * (len(groups) - 1)
166	n/a	)
167	n/a
168	n/a	# Strip a given amount of excess padding from the given string
169	n/a	def _strip_padding(s, amount):
170	n/a	lpos = 0
171	n/a	while amount and s[lpos] == ' ':
172	n/a	lpos += 1
173	n/a	amount -= 1
174	n/a	rpos = len(s) - 1
175	n/a	while amount and s[rpos] == ' ':
176	n/a	rpos -= 1
177	n/a	amount -= 1
178	n/a	return s[lpos:rpos+1]
179	n/a
180	n/a	_percent_re = re.compile(r'%(?:\((?P<key>.*?)\))?'
181	n/a	r'(?P<modifiers>[-#0-9 +.hlL]?)[eEfFgGdiouxXcrs%]')
182	n/a
183	n/a	def format(percent, value, grouping=False, monetary=False, *additional):
184	n/a	"""Returns the locale-aware substitution of a %? specifier
185	n/a	(percent).
186	n/a
187	n/a	additional is for format strings which contain one or more
188	n/a	'*' modifiers."""
189	n/a	# this is only for one-percent-specifier strings and this should be checked
190	n/a	match = _percent_re.match(percent)
191	n/a	if not match or len(match.group())!= len(percent):
192	n/a	raise ValueError(("format() must be given exactly one %%char "
193	n/a	"format specifier, %s not valid") % repr(percent))
194	n/a	return _format(percent, value, grouping, monetary, *additional)
195	n/a
196	n/a	def _format(percent, value, grouping=False, monetary=False, *additional):
197	n/a	if additional:
198	n/a	formatted = percent % ((value,) + additional)
199	n/a	else:
200	n/a	formatted = percent % value
201	n/a	# floats and decimal ints need special action!
202	n/a	if percent[-1] in 'eEfFgG':
203	n/a	seps = 0
204	n/a	parts = formatted.split('.')
205	n/a	if grouping:
206	n/a	parts[0], seps = _group(parts[0], monetary=monetary)
207	n/a	decimal_point = localeconv()[monetary and 'mon_decimal_point'
208	n/a	or 'decimal_point']
209	n/a	formatted = decimal_point.join(parts)
210	n/a	if seps:
211	n/a	formatted = _strip_padding(formatted, seps)
212	n/a	elif percent[-1] in 'diu':
213	n/a	seps = 0
214	n/a	if grouping:
215	n/a	formatted, seps = _group(formatted, monetary=monetary)
216	n/a	if seps:
217	n/a	formatted = _strip_padding(formatted, seps)
218	n/a	return formatted
219	n/a
220	n/a	def format_string(f, val, grouping=False):
221	n/a	"""Formats a string in the same way that the % formatting would use,
222	n/a	but takes the current locale into account.
223	n/a	Grouping is applied if the third parameter is true."""
224	n/a	percents = list(_percent_re.finditer(f))
225	n/a	new_f = _percent_re.sub('%s', f)
226	n/a
227	n/a	if isinstance(val, collections.Mapping):
228	n/a	new_val = []
229	n/a	for perc in percents:
230	n/a	if perc.group()[-1]=='%':
231	n/a	new_val.append('%')
232	n/a	else:
233	n/a	new_val.append(format(perc.group(), val, grouping))
234	n/a	else:
235	n/a	if not isinstance(val, tuple):
236	n/a	val = (val,)
237	n/a	new_val = []
238	n/a	i = 0
239	n/a	for perc in percents:
240	n/a	if perc.group()[-1]=='%':
241	n/a	new_val.append('%')
242	n/a	else:
243	n/a	starcount = perc.group('modifiers').count('*')
244	n/a	new_val.append(_format(perc.group(),
245	n/a	val[i],
246	n/a	grouping,
247	n/a	False,
248	n/a	*val[i+1:i+1+starcount]))
249	n/a	i += (1 + starcount)
250	n/a	val = tuple(new_val)
251	n/a
252	n/a	return new_f % val
253	n/a
254	n/a	def currency(val, symbol=True, grouping=False, international=False):
255	n/a	"""Formats val according to the currency settings
256	n/a	in the current locale."""
257	n/a	conv = localeconv()
258	n/a
259	n/a	# check for illegal values
260	n/a	digits = conv[international and 'int_frac_digits' or 'frac_digits']
261	n/a	if digits == 127:
262	n/a	raise ValueError("Currency formatting is not possible using "
263	n/a	"the 'C' locale.")
264	n/a
265	n/a	s = format('%%.%if' % digits, abs(val), grouping, monetary=True)
266	n/a	# '<' and '>' are markers if the sign must be inserted between symbol and value
267	n/a	s = '<' + s + '>'
268	n/a
269	n/a	if symbol:
270	n/a	smb = conv[international and 'int_curr_symbol' or 'currency_symbol']
271	n/a	precedes = conv[val<0 and 'n_cs_precedes' or 'p_cs_precedes']
272	n/a	separated = conv[val<0 and 'n_sep_by_space' or 'p_sep_by_space']
273	n/a
274	n/a	if precedes:
275	n/a	s = smb + (separated and ' ' or '') + s
276	n/a	else:
277	n/a	s = s + (separated and ' ' or '') + smb
278	n/a
279	n/a	sign_pos = conv[val<0 and 'n_sign_posn' or 'p_sign_posn']
280	n/a	sign = conv[val<0 and 'negative_sign' or 'positive_sign']
281	n/a
282	n/a	if sign_pos == 0:
283	n/a	s = '(' + s + ')'
284	n/a	elif sign_pos == 1:
285	n/a	s = sign + s
286	n/a	elif sign_pos == 2:
287	n/a	s = s + sign
288	n/a	elif sign_pos == 3:
289	n/a	s = s.replace('<', sign)
290	n/a	elif sign_pos == 4:
291	n/a	s = s.replace('>', sign)
292	n/a	else:
293	n/a	# the default if nothing specified;
294	n/a	# this should be the most fitting sign position
295	n/a	s = sign + s
296	n/a
297	n/a	return s.replace('<', '').replace('>', '')
298	n/a
299	n/a	def str(val):
300	n/a	"""Convert float to string, taking the locale into account."""
301	n/a	return format("%.12g", val)
302	n/a
303	n/a	def delocalize(string):
304	n/a	"Parses a string as a normalized number according to the locale settings."
305	n/a
306	n/a	conv = localeconv()
307	n/a
308	n/a	#First, get rid of the grouping
309	n/a	ts = conv['thousands_sep']
310	n/a	if ts:
311	n/a	string = string.replace(ts, '')
312	n/a
313	n/a	#next, replace the decimal point with a dot
314	n/a	dd = conv['decimal_point']
315	n/a	if dd:
316	n/a	string = string.replace(dd, '.')
317	n/a	return string
318	n/a
319	n/a	def atof(string, func=float):
320	n/a	"Parses a string as a float according to the locale settings."
321	n/a	return func(delocalize(string))
322	n/a
323	n/a	def atoi(string):
324	n/a	"Converts a string to an integer according to the locale settings."
325	n/a	return int(delocalize(string))
326	n/a
327	n/a	def _test():
328	n/a	setlocale(LC_ALL, "")
329	n/a	#do grouping
330	n/a	s1 = format("%d", 123456789,1)
331	n/a	print(s1, "is", atoi(s1))
332	n/a	#standard formatting
333	n/a	s1 = str(3.14)
334	n/a	print(s1, "is", atof(s1))
335	n/a
336	n/a	### Locale name aliasing engine
337	n/a
338	n/a	# Author: Marc-Andre Lemburg, mal@lemburg.com
339	n/a	# Various tweaks by Fredrik Lundh <fredrik@pythonware.com>
340	n/a
341	n/a	# store away the low-level version of setlocale (it's
342	n/a	# overridden below)
343	n/a	_setlocale = setlocale
344	n/a
345	n/a	def _replace_encoding(code, encoding):
346	n/a	if '.' in code:
347	n/a	langname = code[:code.index('.')]
348	n/a	else:
349	n/a	langname = code
350	n/a	# Convert the encoding to a C lib compatible encoding string
351	n/a	norm_encoding = encodings.normalize_encoding(encoding)
352	n/a	#print('norm encoding: %r' % norm_encoding)
353	n/a	norm_encoding = encodings.aliases.aliases.get(norm_encoding.lower(),
354	n/a	norm_encoding)
355	n/a	#print('aliased encoding: %r' % norm_encoding)
356	n/a	encoding = norm_encoding
357	n/a	norm_encoding = norm_encoding.lower()
358	n/a	if norm_encoding in locale_encoding_alias:
359	n/a	encoding = locale_encoding_alias[norm_encoding]
360	n/a	else:
361	n/a	norm_encoding = norm_encoding.replace('_', '')
362	n/a	norm_encoding = norm_encoding.replace('-', '')
363	n/a	if norm_encoding in locale_encoding_alias:
364	n/a	encoding = locale_encoding_alias[norm_encoding]
365	n/a	#print('found encoding %r' % encoding)
366	n/a	return langname + '.' + encoding
367	n/a
368	n/a	def _append_modifier(code, modifier):
369	n/a	if modifier == 'euro':
370	n/a	if '.' not in code:
371	n/a	return code + '.ISO8859-15'
372	n/a	_, _, encoding = code.partition('.')
373	n/a	if encoding in ('ISO8859-15', 'UTF-8'):
374	n/a	return code
375	n/a	if encoding == 'ISO8859-1':
376	n/a	return _replace_encoding(code, 'ISO8859-15')
377	n/a	return code + '@' + modifier
378	n/a
379	n/a	def normalize(localename):
380	n/a
381	n/a	""" Returns a normalized locale code for the given locale
382	n/a	name.
383	n/a
384	n/a	The returned locale code is formatted for use with
385	n/a	setlocale().
386	n/a
387	n/a	If normalization fails, the original name is returned
388	n/a	unchanged.
389	n/a
390	n/a	If the given encoding is not known, the function defaults to
391	n/a	the default encoding for the locale code just like setlocale()
392	n/a	does.
393	n/a
394	n/a	"""
395	n/a	# Normalize the locale name and extract the encoding and modifier
396	n/a	code = localename.lower()
397	n/a	if ':' in code:
398	n/a	# ':' is sometimes used as encoding delimiter.
399	n/a	code = code.replace(':', '.')
400	n/a	if '@' in code:
401	n/a	code, modifier = code.split('@', 1)
402	n/a	else:
403	n/a	modifier = ''
404	n/a	if '.' in code:
405	n/a	langname, encoding = code.split('.')[:2]
406	n/a	else:
407	n/a	langname = code
408	n/a	encoding = ''
409	n/a
410	n/a	# First lookup: fullname (possibly with encoding and modifier)
411	n/a	lang_enc = langname
412	n/a	if encoding:
413	n/a	norm_encoding = encoding.replace('-', '')
414	n/a	norm_encoding = norm_encoding.replace('_', '')
415	n/a	lang_enc += '.' + norm_encoding
416	n/a	lookup_name = lang_enc
417	n/a	if modifier:
418	n/a	lookup_name += '@' + modifier
419	n/a	code = locale_alias.get(lookup_name, None)
420	n/a	if code is not None:
421	n/a	return code
422	n/a	#print('first lookup failed')
423	n/a
424	n/a	if modifier:
425	n/a	# Second try: fullname without modifier (possibly with encoding)
426	n/a	code = locale_alias.get(lang_enc, None)
427	n/a	if code is not None:
428	n/a	#print('lookup without modifier succeeded')
429	n/a	if '@' not in code:
430	n/a	return _append_modifier(code, modifier)
431	n/a	if code.split('@', 1)[1].lower() == modifier:
432	n/a	return code
433	n/a	#print('second lookup failed')
434	n/a
435	n/a	if encoding:
436	n/a	# Third try: langname (without encoding, possibly with modifier)
437	n/a	lookup_name = langname
438	n/a	if modifier:
439	n/a	lookup_name += '@' + modifier
440	n/a	code = locale_alias.get(lookup_name, None)
441	n/a	if code is not None:
442	n/a	#print('lookup without encoding succeeded')
443	n/a	if '@' not in code:
444	n/a	return _replace_encoding(code, encoding)
445	n/a	code, modifier = code.split('@', 1)
446	n/a	return _replace_encoding(code, encoding) + '@' + modifier
447	n/a
448	n/a	if modifier:
449	n/a	# Fourth try: langname (without encoding and modifier)
450	n/a	code = locale_alias.get(langname, None)
451	n/a	if code is not None:
452	n/a	#print('lookup without modifier and encoding succeeded')
453	n/a	if '@' not in code:
454	n/a	code = _replace_encoding(code, encoding)
455	n/a	return _append_modifier(code, modifier)
456	n/a	code, defmod = code.split('@', 1)
457	n/a	if defmod.lower() == modifier:
458	n/a	return _replace_encoding(code, encoding) + '@' + defmod
459	n/a
460	n/a	return localename
461	n/a
462	n/a	def _parse_localename(localename):
463	n/a
464	n/a	""" Parses the locale code for localename and returns the
465	n/a	result as tuple (language code, encoding).
466	n/a
467	n/a	The localename is normalized and passed through the locale
468	n/a	alias engine. A ValueError is raised in case the locale name
469	n/a	cannot be parsed.
470	n/a
471	n/a	The language code corresponds to RFC 1766. code and encoding
472	n/a	can be None in case the values cannot be determined or are
473	n/a	unknown to this implementation.
474	n/a
475	n/a	"""
476	n/a	code = normalize(localename)
477	n/a	if '@' in code:
478	n/a	# Deal with locale modifiers
479	n/a	code, modifier = code.split('@', 1)
480	n/a	if modifier == 'euro' and '.' not in code:
481	n/a	# Assume Latin-9 for @euro locales. This is bogus,
482	n/a	# since some systems may use other encodings for these
483	n/a	# locales. Also, we ignore other modifiers.
484	n/a	return code, 'iso-8859-15'
485	n/a
486	n/a	if '.' in code:
487	n/a	return tuple(code.split('.')[:2])
488	n/a	elif code == 'C':
489	n/a	return None, None
490	n/a	raise ValueError('unknown locale: %s' % localename)
491	n/a
492	n/a	def _build_localename(localetuple):
493	n/a
494	n/a	""" Builds a locale code from the given tuple (language code,
495	n/a	encoding).
496	n/a
497	n/a	No aliasing or normalizing takes place.
498	n/a
499	n/a	"""
500	n/a	try:
501	n/a	language, encoding = localetuple
502	n/a
503	n/a	if language is None:
504	n/a	language = 'C'
505	n/a	if encoding is None:
506	n/a	return language
507	n/a	else:
508	n/a	return language + '.' + encoding
509	n/a	except (TypeError, ValueError):
510	n/a	raise TypeError('Locale must be None, a string, or an iterable of two strings -- language code, encoding.')
511	n/a
512	n/a	def getdefaultlocale(envvars=('LC_ALL', 'LC_CTYPE', 'LANG', 'LANGUAGE')):
513	n/a
514	n/a	""" Tries to determine the default locale settings and returns
515	n/a	them as tuple (language code, encoding).
516	n/a
517	n/a	According to POSIX, a program which has not called
518	n/a	setlocale(LC_ALL, "") runs using the portable 'C' locale.
519	n/a	Calling setlocale(LC_ALL, "") lets it use the default locale as
520	n/a	defined by the LANG variable. Since we don't want to interfere
521	n/a	with the current locale setting we thus emulate the behavior
522	n/a	in the way described above.
523	n/a
524	n/a	To maintain compatibility with other platforms, not only the
525	n/a	LANG variable is tested, but a list of variables given as
526	n/a	envvars parameter. The first found to be defined will be
527	n/a	used. envvars defaults to the search path used in GNU gettext;
528	n/a	it must always contain the variable name 'LANG'.
529	n/a
530	n/a	Except for the code 'C', the language code corresponds to RFC
531	n/a	1766. code and encoding can be None in case the values cannot
532	n/a	be determined.
533	n/a
534	n/a	"""
535	n/a
536	n/a	try:
537	n/a	# check if it's supported by the _locale module
538	n/a	import _locale
539	n/a	code, encoding = _locale._getdefaultlocale()
540	n/a	except (ImportError, AttributeError):
541	n/a	pass
542	n/a	else:
543	n/a	# make sure the code/encoding values are valid
544	n/a	if sys.platform == "win32" and code and code[:2] == "0x":
545	n/a	# map windows language identifier to language name
546	n/a	code = windows_locale.get(int(code, 0))
547	n/a	# ...add other platform-specific processing here, if
548	n/a	# necessary...
549	n/a	return code, encoding
550	n/a
551	n/a	# fall back on POSIX behaviour
552	n/a	import os
553	n/a	lookup = os.environ.get
554	n/a	for variable in envvars:
555	n/a	localename = lookup(variable,None)
556	n/a	if localename:
557	n/a	if variable == 'LANGUAGE':
558	n/a	localename = localename.split(':')[0]
559	n/a	break
560	n/a	else:
561	n/a	localename = 'C'
562	n/a	return _parse_localename(localename)
563	n/a
564	n/a
565	n/a	def getlocale(category=LC_CTYPE):
566	n/a
567	n/a	""" Returns the current setting for the given locale category as
568	n/a	tuple (language code, encoding).
569	n/a
570	n/a	category may be one of the LC_* value except LC_ALL. It
571	n/a	defaults to LC_CTYPE.
572	n/a
573	n/a	Except for the code 'C', the language code corresponds to RFC
574	n/a	1766. code and encoding can be None in case the values cannot
575	n/a	be determined.
576	n/a
577	n/a	"""
578	n/a	localename = _setlocale(category)
579	n/a	if category == LC_ALL and ';' in localename:
580	n/a	raise TypeError('category LC_ALL is not supported')
581	n/a	return _parse_localename(localename)
582	n/a
583	n/a	def setlocale(category, locale=None):
584	n/a
585	n/a	""" Set the locale for the given category. The locale can be
586	n/a	a string, an iterable of two strings (language code and encoding),
587	n/a	or None.
588	n/a
589	n/a	Iterables are converted to strings using the locale aliasing
590	n/a	engine. Locale strings are passed directly to the C lib.
591	n/a
592	n/a	category may be given as one of the LC_* values.
593	n/a
594	n/a	"""
595	n/a	if locale and not isinstance(locale, _builtin_str):
596	n/a	# convert to string
597	n/a	locale = normalize(_build_localename(locale))
598	n/a	return _setlocale(category, locale)
599	n/a
600	n/a	def resetlocale(category=LC_ALL):
601	n/a
602	n/a	""" Sets the locale for category to the default setting.
603	n/a
604	n/a	The default setting is determined by calling
605	n/a	getdefaultlocale(). category defaults to LC_ALL.
606	n/a
607	n/a	"""
608	n/a	_setlocale(category, _build_localename(getdefaultlocale()))
609	n/a
610	n/a	if sys.platform.startswith("win"):
611	n/a	# On Win32, this will return the ANSI code page
612	n/a	def getpreferredencoding(do_setlocale = True):
613	n/a	"""Return the charset that the user is likely using."""
614	n/a	import _bootlocale
615	n/a	return _bootlocale.getpreferredencoding(False)
616	n/a	else:
617	n/a	# On Unix, if CODESET is available, use that.
618	n/a	try:
619	n/a	CODESET
620	n/a	except NameError:
621	n/a	if hasattr(sys, 'getandroidapilevel'):
622	n/a	# On Android langinfo.h and CODESET are missing, and UTF-8 is
623	n/a	# always used in mbstowcs() and wcstombs().
624	n/a	def getpreferredencoding(do_setlocale = True):
625	n/a	return 'UTF-8'
626	n/a	else:
627	n/a	# Fall back to parsing environment variables :-(
628	n/a	def getpreferredencoding(do_setlocale = True):
629	n/a	"""Return the charset that the user is likely using,
630	n/a	by looking at environment variables."""
631	n/a	res = getdefaultlocale()[1]
632	n/a	if res is None:
633	n/a	# LANG not set, default conservatively to ASCII
634	n/a	res = 'ascii'
635	n/a	return res
636	n/a	else:
637	n/a	def getpreferredencoding(do_setlocale = True):
638	n/a	"""Return the charset that the user is likely using,
639	n/a	according to the system configuration."""
640	n/a	import _bootlocale
641	n/a	if do_setlocale:
642	n/a	oldloc = setlocale(LC_CTYPE)
643	n/a	try:
644	n/a	setlocale(LC_CTYPE, "")
645	n/a	except Error:
646	n/a	pass
647	n/a	result = _bootlocale.getpreferredencoding(False)
648	n/a	if do_setlocale:
649	n/a	setlocale(LC_CTYPE, oldloc)
650	n/a	return result
651	n/a
652	n/a
653	n/a	### Database
654	n/a	#
655	n/a	# The following data was extracted from the locale.alias file which
656	n/a	# comes with X11 and then hand edited removing the explicit encoding
657	n/a	# definitions and adding some more aliases. The file is usually
658	n/a	# available as /usr/lib/X11/locale/locale.alias.
659	n/a	#
660	n/a
661	n/a	#
662	n/a	# The local_encoding_alias table maps lowercase encoding alias names
663	n/a	# to C locale encoding names (case-sensitive). Note that normalize()
664	n/a	# first looks up the encoding in the encodings.aliases dictionary and
665	n/a	# then applies this mapping to find the correct C lib name for the
666	n/a	# encoding.
667	n/a	#
668	n/a	locale_encoding_alias = {
669	n/a
670	n/a	# Mappings for non-standard encoding names used in locale names
671	n/a	'437': 'C',
672	n/a	'c': 'C',
673	n/a	'en': 'ISO8859-1',
674	n/a	'jis': 'JIS7',
675	n/a	'jis7': 'JIS7',
676	n/a	'ajec': 'eucJP',
677	n/a	'koi8c': 'KOI8-C',
678	n/a	'microsoftcp1251': 'CP1251',
679	n/a	'microsoftcp1255': 'CP1255',
680	n/a	'microsoftcp1256': 'CP1256',
681	n/a	'88591': 'ISO8859-1',
682	n/a	'88592': 'ISO8859-2',
683	n/a	'88595': 'ISO8859-5',
684	n/a	'885915': 'ISO8859-15',
685	n/a
686	n/a	# Mappings from Python codec names to C lib encoding names
687	n/a	'ascii': 'ISO8859-1',
688	n/a	'latin_1': 'ISO8859-1',
689	n/a	'iso8859_1': 'ISO8859-1',
690	n/a	'iso8859_10': 'ISO8859-10',
691	n/a	'iso8859_11': 'ISO8859-11',
692	n/a	'iso8859_13': 'ISO8859-13',
693	n/a	'iso8859_14': 'ISO8859-14',
694	n/a	'iso8859_15': 'ISO8859-15',
695	n/a	'iso8859_16': 'ISO8859-16',
696	n/a	'iso8859_2': 'ISO8859-2',
697	n/a	'iso8859_3': 'ISO8859-3',
698	n/a	'iso8859_4': 'ISO8859-4',
699	n/a	'iso8859_5': 'ISO8859-5',
700	n/a	'iso8859_6': 'ISO8859-6',
701	n/a	'iso8859_7': 'ISO8859-7',
702	n/a	'iso8859_8': 'ISO8859-8',
703	n/a	'iso8859_9': 'ISO8859-9',
704	n/a	'iso2022_jp': 'JIS7',
705	n/a	'shift_jis': 'SJIS',
706	n/a	'tactis': 'TACTIS',
707	n/a	'euc_jp': 'eucJP',
708	n/a	'euc_kr': 'eucKR',
709	n/a	'utf_8': 'UTF-8',
710	n/a	'koi8_r': 'KOI8-R',
711	n/a	'koi8_t': 'KOI8-T',
712	n/a	'koi8_u': 'KOI8-U',
713	n/a	'kz1048': 'RK1048',
714	n/a	'cp1251': 'CP1251',
715	n/a	'cp1255': 'CP1255',
716	n/a	'cp1256': 'CP1256',
717	n/a
718	n/a	# XXX This list is still incomplete. If you know more
719	n/a	# mappings, please file a bug report. Thanks.
720	n/a	}
721	n/a
722	n/a	for k, v in sorted(locale_encoding_alias.items()):
723	n/a	k = k.replace('_', '')
724	n/a	locale_encoding_alias.setdefault(k, v)
725	n/a
726	n/a	#
727	n/a	# The locale_alias table maps lowercase alias names to C locale names
728	n/a	# (case-sensitive). Encodings are always separated from the locale
729	n/a	# name using a dot ('.'); they should only be given in case the
730	n/a	# language name is needed to interpret the given encoding alias
731	n/a	# correctly (CJK codes often have this need).
732	n/a	#
733	n/a	# Note that the normalize() function which uses this tables
734	n/a	# removes '_' and '-' characters from the encoding part of the
735	n/a	# locale name before doing the lookup. This saves a lot of
736	n/a	# space in the table.
737	n/a	#
738	n/a	# MAL 2004-12-10:
739	n/a	# Updated alias mapping to most recent locale.alias file
740	n/a	# from X.org distribution using makelocalealias.py.
741	n/a	#
742	n/a	# These are the differences compared to the old mapping (Python 2.4
743	n/a	# and older):
744	n/a	#
745	n/a	# updated 'bg' -> 'bg_BG.ISO8859-5' to 'bg_BG.CP1251'
746	n/a	# updated 'bg_bg' -> 'bg_BG.ISO8859-5' to 'bg_BG.CP1251'
747	n/a	# updated 'bulgarian' -> 'bg_BG.ISO8859-5' to 'bg_BG.CP1251'
748	n/a	# updated 'cz' -> 'cz_CZ.ISO8859-2' to 'cs_CZ.ISO8859-2'
749	n/a	# updated 'cz_cz' -> 'cz_CZ.ISO8859-2' to 'cs_CZ.ISO8859-2'
750	n/a	# updated 'czech' -> 'cs_CS.ISO8859-2' to 'cs_CZ.ISO8859-2'
751	n/a	# updated 'dutch' -> 'nl_BE.ISO8859-1' to 'nl_NL.ISO8859-1'
752	n/a	# updated 'et' -> 'et_EE.ISO8859-4' to 'et_EE.ISO8859-15'
753	n/a	# updated 'et_ee' -> 'et_EE.ISO8859-4' to 'et_EE.ISO8859-15'
754	n/a	# updated 'fi' -> 'fi_FI.ISO8859-1' to 'fi_FI.ISO8859-15'
755	n/a	# updated 'fi_fi' -> 'fi_FI.ISO8859-1' to 'fi_FI.ISO8859-15'
756	n/a	# updated 'iw' -> 'iw_IL.ISO8859-8' to 'he_IL.ISO8859-8'
757	n/a	# updated 'iw_il' -> 'iw_IL.ISO8859-8' to 'he_IL.ISO8859-8'
758	n/a	# updated 'japanese' -> 'ja_JP.SJIS' to 'ja_JP.eucJP'
759	n/a	# updated 'lt' -> 'lt_LT.ISO8859-4' to 'lt_LT.ISO8859-13'
760	n/a	# updated 'lv' -> 'lv_LV.ISO8859-4' to 'lv_LV.ISO8859-13'
761	n/a	# updated 'sl' -> 'sl_CS.ISO8859-2' to 'sl_SI.ISO8859-2'
762	n/a	# updated 'slovene' -> 'sl_CS.ISO8859-2' to 'sl_SI.ISO8859-2'
763	n/a	# updated 'th_th' -> 'th_TH.TACTIS' to 'th_TH.ISO8859-11'
764	n/a	# updated 'zh_cn' -> 'zh_CN.eucCN' to 'zh_CN.gb2312'
765	n/a	# updated 'zh_cn.big5' -> 'zh_TW.eucTW' to 'zh_TW.big5'
766	n/a	# updated 'zh_tw' -> 'zh_TW.eucTW' to 'zh_TW.big5'
767	n/a	#
768	n/a	# MAL 2008-05-30:
769	n/a	# Updated alias mapping to most recent locale.alias file
770	n/a	# from X.org distribution using makelocalealias.py.
771	n/a	#
772	n/a	# These are the differences compared to the old mapping (Python 2.5
773	n/a	# and older):
774	n/a	#
775	n/a	# updated 'cs_cs.iso88592' -> 'cs_CZ.ISO8859-2' to 'cs_CS.ISO8859-2'
776	n/a	# updated 'serbocroatian' -> 'sh_YU.ISO8859-2' to 'sr_CS.ISO8859-2'
777	n/a	# updated 'sh' -> 'sh_YU.ISO8859-2' to 'sr_CS.ISO8859-2'
778	n/a	# updated 'sh_hr.iso88592' -> 'sh_HR.ISO8859-2' to 'hr_HR.ISO8859-2'
779	n/a	# updated 'sh_sp' -> 'sh_YU.ISO8859-2' to 'sr_CS.ISO8859-2'
780	n/a	# updated 'sh_yu' -> 'sh_YU.ISO8859-2' to 'sr_CS.ISO8859-2'
781	n/a	# updated 'sp' -> 'sp_YU.ISO8859-5' to 'sr_CS.ISO8859-5'
782	n/a	# updated 'sp_yu' -> 'sp_YU.ISO8859-5' to 'sr_CS.ISO8859-5'
783	n/a	# updated 'sr' -> 'sr_YU.ISO8859-5' to 'sr_CS.ISO8859-5'
784	n/a	# updated 'sr@cyrillic' -> 'sr_YU.ISO8859-5' to 'sr_CS.ISO8859-5'
785	n/a	# updated 'sr_sp' -> 'sr_SP.ISO8859-2' to 'sr_CS.ISO8859-2'
786	n/a	# updated 'sr_yu' -> 'sr_YU.ISO8859-5' to 'sr_CS.ISO8859-5'
787	n/a	# updated 'sr_yu.cp1251@cyrillic' -> 'sr_YU.CP1251' to 'sr_CS.CP1251'
788	n/a	# updated 'sr_yu.iso88592' -> 'sr_YU.ISO8859-2' to 'sr_CS.ISO8859-2'
789	n/a	# updated 'sr_yu.iso88595' -> 'sr_YU.ISO8859-5' to 'sr_CS.ISO8859-5'
790	n/a	# updated 'sr_yu.iso88595@cyrillic' -> 'sr_YU.ISO8859-5' to 'sr_CS.ISO8859-5'
791	n/a	# updated 'sr_yu.microsoftcp1251@cyrillic' -> 'sr_YU.CP1251' to 'sr_CS.CP1251'
792	n/a	# updated 'sr_yu.utf8@cyrillic' -> 'sr_YU.UTF-8' to 'sr_CS.UTF-8'
793	n/a	# updated 'sr_yu@cyrillic' -> 'sr_YU.ISO8859-5' to 'sr_CS.ISO8859-5'
794	n/a	#
795	n/a	# AP 2010-04-12:
796	n/a	# Updated alias mapping to most recent locale.alias file
797	n/a	# from X.org distribution using makelocalealias.py.
798	n/a	#
799	n/a	# These are the differences compared to the old mapping (Python 2.6.5
800	n/a	# and older):
801	n/a	#
802	n/a	# updated 'ru' -> 'ru_RU.ISO8859-5' to 'ru_RU.UTF-8'
803	n/a	# updated 'ru_ru' -> 'ru_RU.ISO8859-5' to 'ru_RU.UTF-8'
804	n/a	# updated 'serbocroatian' -> 'sr_CS.ISO8859-2' to 'sr_RS.UTF-8@latin'
805	n/a	# updated 'sh' -> 'sr_CS.ISO8859-2' to 'sr_RS.UTF-8@latin'
806	n/a	# updated 'sh_yu' -> 'sr_CS.ISO8859-2' to 'sr_RS.UTF-8@latin'
807	n/a	# updated 'sr' -> 'sr_CS.ISO8859-5' to 'sr_RS.UTF-8'
808	n/a	# updated 'sr@cyrillic' -> 'sr_CS.ISO8859-5' to 'sr_RS.UTF-8'
809	n/a	# updated 'sr@latn' -> 'sr_CS.ISO8859-2' to 'sr_RS.UTF-8@latin'
810	n/a	# updated 'sr_cs.utf8@latn' -> 'sr_CS.UTF-8' to 'sr_RS.UTF-8@latin'
811	n/a	# updated 'sr_cs@latn' -> 'sr_CS.ISO8859-2' to 'sr_RS.UTF-8@latin'
812	n/a	# updated 'sr_yu' -> 'sr_CS.ISO8859-5' to 'sr_RS.UTF-8@latin'
813	n/a	# updated 'sr_yu.utf8@cyrillic' -> 'sr_CS.UTF-8' to 'sr_RS.UTF-8'
814	n/a	# updated 'sr_yu@cyrillic' -> 'sr_CS.ISO8859-5' to 'sr_RS.UTF-8'
815	n/a	#
816	n/a	# SS 2013-12-20:
817	n/a	# Updated alias mapping to most recent locale.alias file
818	n/a	# from X.org distribution using makelocalealias.py.
819	n/a	#
820	n/a	# These are the differences compared to the old mapping (Python 3.3.3
821	n/a	# and older):
822	n/a	#
823	n/a	# updated 'a3' -> 'a3_AZ.KOI8-C' to 'az_AZ.KOI8-C'
824	n/a	# updated 'a3_az' -> 'a3_AZ.KOI8-C' to 'az_AZ.KOI8-C'
825	n/a	# updated 'a3_az.koi8c' -> 'a3_AZ.KOI8-C' to 'az_AZ.KOI8-C'
826	n/a	# updated 'cs_cs.iso88592' -> 'cs_CS.ISO8859-2' to 'cs_CZ.ISO8859-2'
827	n/a	# updated 'hebrew' -> 'iw_IL.ISO8859-8' to 'he_IL.ISO8859-8'
828	n/a	# updated 'hebrew.iso88598' -> 'iw_IL.ISO8859-8' to 'he_IL.ISO8859-8'
829	n/a	# updated 'sd' -> 'sd_IN@devanagari.UTF-8' to 'sd_IN.UTF-8'
830	n/a	# updated 'sr@latn' -> 'sr_RS.UTF-8@latin' to 'sr_CS.UTF-8@latin'
831	n/a	# updated 'sr_cs' -> 'sr_RS.UTF-8' to 'sr_CS.UTF-8'
832	n/a	# updated 'sr_cs.utf8@latn' -> 'sr_RS.UTF-8@latin' to 'sr_CS.UTF-8@latin'
833	n/a	# updated 'sr_cs@latn' -> 'sr_RS.UTF-8@latin' to 'sr_CS.UTF-8@latin'
834	n/a	#
835	n/a	# SS 2014-10-01:
836	n/a	# Updated alias mapping with glibc 2.19 supported locales.
837	n/a
838	n/a	locale_alias = {
839	n/a	'a3': 'az_AZ.KOI8-C',
840	n/a	'a3_az': 'az_AZ.KOI8-C',
841	n/a	'a3_az.koic': 'az_AZ.KOI8-C',
842	n/a	'aa_dj': 'aa_DJ.ISO8859-1',
843	n/a	'aa_er': 'aa_ER.UTF-8',
844	n/a	'aa_et': 'aa_ET.UTF-8',
845	n/a	'af': 'af_ZA.ISO8859-1',
846	n/a	'af_za': 'af_ZA.ISO8859-1',
847	n/a	'am': 'am_ET.UTF-8',
848	n/a	'am_et': 'am_ET.UTF-8',
849	n/a	'american': 'en_US.ISO8859-1',
850	n/a	'an_es': 'an_ES.ISO8859-15',
851	n/a	'ar': 'ar_AA.ISO8859-6',
852	n/a	'ar_aa': 'ar_AA.ISO8859-6',
853	n/a	'ar_ae': 'ar_AE.ISO8859-6',
854	n/a	'ar_bh': 'ar_BH.ISO8859-6',
855	n/a	'ar_dz': 'ar_DZ.ISO8859-6',
856	n/a	'ar_eg': 'ar_EG.ISO8859-6',
857	n/a	'ar_in': 'ar_IN.UTF-8',
858	n/a	'ar_iq': 'ar_IQ.ISO8859-6',
859	n/a	'ar_jo': 'ar_JO.ISO8859-6',
860	n/a	'ar_kw': 'ar_KW.ISO8859-6',
861	n/a	'ar_lb': 'ar_LB.ISO8859-6',
862	n/a	'ar_ly': 'ar_LY.ISO8859-6',
863	n/a	'ar_ma': 'ar_MA.ISO8859-6',
864	n/a	'ar_om': 'ar_OM.ISO8859-6',
865	n/a	'ar_qa': 'ar_QA.ISO8859-6',
866	n/a	'ar_sa': 'ar_SA.ISO8859-6',
867	n/a	'ar_sd': 'ar_SD.ISO8859-6',
868	n/a	'ar_sy': 'ar_SY.ISO8859-6',
869	n/a	'ar_tn': 'ar_TN.ISO8859-6',
870	n/a	'ar_ye': 'ar_YE.ISO8859-6',
871	n/a	'arabic': 'ar_AA.ISO8859-6',
872	n/a	'as': 'as_IN.UTF-8',
873	n/a	'as_in': 'as_IN.UTF-8',
874	n/a	'ast_es': 'ast_ES.ISO8859-15',
875	n/a	'ayc_pe': 'ayc_PE.UTF-8',
876	n/a	'az': 'az_AZ.ISO8859-9E',
877	n/a	'az_az': 'az_AZ.ISO8859-9E',
878	n/a	'az_az.iso88599e': 'az_AZ.ISO8859-9E',
879	n/a	'be': 'be_BY.CP1251',
880	n/a	'be@latin': 'be_BY.UTF-8@latin',
881	n/a	'be_bg.utf8': 'bg_BG.UTF-8',
882	n/a	'be_by': 'be_BY.CP1251',
883	n/a	'be_by@latin': 'be_BY.UTF-8@latin',
884	n/a	'bem_zm': 'bem_ZM.UTF-8',
885	n/a	'ber_dz': 'ber_DZ.UTF-8',
886	n/a	'ber_ma': 'ber_MA.UTF-8',
887	n/a	'bg': 'bg_BG.CP1251',
888	n/a	'bg_bg': 'bg_BG.CP1251',
889	n/a	'bho_in': 'bho_IN.UTF-8',
890	n/a	'bn_bd': 'bn_BD.UTF-8',
891	n/a	'bn_in': 'bn_IN.UTF-8',
892	n/a	'bo_cn': 'bo_CN.UTF-8',
893	n/a	'bo_in': 'bo_IN.UTF-8',
894	n/a	'bokmal': 'nb_NO.ISO8859-1',
895	n/a	'bokm\xe5l': 'nb_NO.ISO8859-1',
896	n/a	'br': 'br_FR.ISO8859-1',
897	n/a	'br_fr': 'br_FR.ISO8859-1',
898	n/a	'brx_in': 'brx_IN.UTF-8',
899	n/a	'bs': 'bs_BA.ISO8859-2',
900	n/a	'bs_ba': 'bs_BA.ISO8859-2',
901	n/a	'bulgarian': 'bg_BG.CP1251',
902	n/a	'byn_er': 'byn_ER.UTF-8',
903	n/a	'c': 'C',
904	n/a	'c-french': 'fr_CA.ISO8859-1',
905	n/a	'c.ascii': 'C',
906	n/a	'c.en': 'C',
907	n/a	'c.iso88591': 'en_US.ISO8859-1',
908	n/a	'c.utf8': 'en_US.UTF-8',
909	n/a	'c_c': 'C',
910	n/a	'c_c.c': 'C',
911	n/a	'ca': 'ca_ES.ISO8859-1',
912	n/a	'ca_ad': 'ca_AD.ISO8859-1',
913	n/a	'ca_es': 'ca_ES.ISO8859-1',
914	n/a	'ca_es@valencia': 'ca_ES.ISO8859-15@valencia',
915	n/a	'ca_fr': 'ca_FR.ISO8859-1',
916	n/a	'ca_it': 'ca_IT.ISO8859-1',
917	n/a	'catalan': 'ca_ES.ISO8859-1',
918	n/a	'cextend': 'en_US.ISO8859-1',
919	n/a	'chinese-s': 'zh_CN.eucCN',
920	n/a	'chinese-t': 'zh_TW.eucTW',
921	n/a	'crh_ua': 'crh_UA.UTF-8',
922	n/a	'croatian': 'hr_HR.ISO8859-2',
923	n/a	'cs': 'cs_CZ.ISO8859-2',
924	n/a	'cs_cs': 'cs_CZ.ISO8859-2',
925	n/a	'cs_cz': 'cs_CZ.ISO8859-2',
926	n/a	'csb_pl': 'csb_PL.UTF-8',
927	n/a	'cv_ru': 'cv_RU.UTF-8',
928	n/a	'cy': 'cy_GB.ISO8859-1',
929	n/a	'cy_gb': 'cy_GB.ISO8859-1',
930	n/a	'cz': 'cs_CZ.ISO8859-2',
931	n/a	'cz_cz': 'cs_CZ.ISO8859-2',
932	n/a	'czech': 'cs_CZ.ISO8859-2',
933	n/a	'da': 'da_DK.ISO8859-1',
934	n/a	'da_dk': 'da_DK.ISO8859-1',
935	n/a	'danish': 'da_DK.ISO8859-1',
936	n/a	'dansk': 'da_DK.ISO8859-1',
937	n/a	'de': 'de_DE.ISO8859-1',
938	n/a	'de_at': 'de_AT.ISO8859-1',
939	n/a	'de_be': 'de_BE.ISO8859-1',
940	n/a	'de_ch': 'de_CH.ISO8859-1',
941	n/a	'de_de': 'de_DE.ISO8859-1',
942	n/a	'de_li.utf8': 'de_LI.UTF-8',
943	n/a	'de_lu': 'de_LU.ISO8859-1',
944	n/a	'deutsch': 'de_DE.ISO8859-1',
945	n/a	'doi_in': 'doi_IN.UTF-8',
946	n/a	'dutch': 'nl_NL.ISO8859-1',
947	n/a	'dutch.iso88591': 'nl_BE.ISO8859-1',
948	n/a	'dv_mv': 'dv_MV.UTF-8',
949	n/a	'dz_bt': 'dz_BT.UTF-8',
950	n/a	'ee': 'ee_EE.ISO8859-4',
951	n/a	'ee_ee': 'ee_EE.ISO8859-4',
952	n/a	'eesti': 'et_EE.ISO8859-1',
953	n/a	'el': 'el_GR.ISO8859-7',
954	n/a	'el_cy': 'el_CY.ISO8859-7',
955	n/a	'el_gr': 'el_GR.ISO8859-7',
956	n/a	'el_gr@euro': 'el_GR.ISO8859-15',
957	n/a	'en': 'en_US.ISO8859-1',
958	n/a	'en_ag': 'en_AG.UTF-8',
959	n/a	'en_au': 'en_AU.ISO8859-1',
960	n/a	'en_be': 'en_BE.ISO8859-1',
961	n/a	'en_bw': 'en_BW.ISO8859-1',
962	n/a	'en_ca': 'en_CA.ISO8859-1',
963	n/a	'en_dk': 'en_DK.ISO8859-1',
964	n/a	'en_dl.utf8': 'en_DL.UTF-8',
965	n/a	'en_gb': 'en_GB.ISO8859-1',
966	n/a	'en_hk': 'en_HK.ISO8859-1',
967	n/a	'en_ie': 'en_IE.ISO8859-1',
968	n/a	'en_in': 'en_IN.ISO8859-1',
969	n/a	'en_ng': 'en_NG.UTF-8',
970	n/a	'en_nz': 'en_NZ.ISO8859-1',
971	n/a	'en_ph': 'en_PH.ISO8859-1',
972	n/a	'en_sg': 'en_SG.ISO8859-1',
973	n/a	'en_uk': 'en_GB.ISO8859-1',
974	n/a	'en_us': 'en_US.ISO8859-1',
975	n/a	'en_us@euro@euro': 'en_US.ISO8859-15',
976	n/a	'en_za': 'en_ZA.ISO8859-1',
977	n/a	'en_zm': 'en_ZM.UTF-8',
978	n/a	'en_zw': 'en_ZW.ISO8859-1',
979	n/a	'en_zw.utf8': 'en_ZS.UTF-8',
980	n/a	'eng_gb': 'en_GB.ISO8859-1',
981	n/a	'english': 'en_EN.ISO8859-1',
982	n/a	'english_uk': 'en_GB.ISO8859-1',
983	n/a	'english_united-states': 'en_US.ISO8859-1',
984	n/a	'english_united-states.437': 'C',
985	n/a	'english_us': 'en_US.ISO8859-1',
986	n/a	'eo': 'eo_XX.ISO8859-3',
987	n/a	'eo.utf8': 'eo.UTF-8',
988	n/a	'eo_eo': 'eo_EO.ISO8859-3',
989	n/a	'eo_us.utf8': 'eo_US.UTF-8',
990	n/a	'eo_xx': 'eo_XX.ISO8859-3',
991	n/a	'es': 'es_ES.ISO8859-1',
992	n/a	'es_ar': 'es_AR.ISO8859-1',
993	n/a	'es_bo': 'es_BO.ISO8859-1',
994	n/a	'es_cl': 'es_CL.ISO8859-1',
995	n/a	'es_co': 'es_CO.ISO8859-1',
996	n/a	'es_cr': 'es_CR.ISO8859-1',
997	n/a	'es_cu': 'es_CU.UTF-8',
998	n/a	'es_do': 'es_DO.ISO8859-1',
999	n/a	'es_ec': 'es_EC.ISO8859-1',
1000	n/a	'es_es': 'es_ES.ISO8859-1',
1001	n/a	'es_gt': 'es_GT.ISO8859-1',
1002	n/a	'es_hn': 'es_HN.ISO8859-1',
1003	n/a	'es_mx': 'es_MX.ISO8859-1',
1004	n/a	'es_ni': 'es_NI.ISO8859-1',
1005	n/a	'es_pa': 'es_PA.ISO8859-1',
1006	n/a	'es_pe': 'es_PE.ISO8859-1',
1007	n/a	'es_pr': 'es_PR.ISO8859-1',
1008	n/a	'es_py': 'es_PY.ISO8859-1',
1009	n/a	'es_sv': 'es_SV.ISO8859-1',
1010	n/a	'es_us': 'es_US.ISO8859-1',
1011	n/a	'es_uy': 'es_UY.ISO8859-1',
1012	n/a	'es_ve': 'es_VE.ISO8859-1',
1013	n/a	'estonian': 'et_EE.ISO8859-1',
1014	n/a	'et': 'et_EE.ISO8859-15',
1015	n/a	'et_ee': 'et_EE.ISO8859-15',
1016	n/a	'eu': 'eu_ES.ISO8859-1',
1017	n/a	'eu_es': 'eu_ES.ISO8859-1',
1018	n/a	'eu_fr': 'eu_FR.ISO8859-1',
1019	n/a	'fa': 'fa_IR.UTF-8',
1020	n/a	'fa_ir': 'fa_IR.UTF-8',
1021	n/a	'fa_ir.isiri3342': 'fa_IR.ISIRI-3342',
1022	n/a	'ff_sn': 'ff_SN.UTF-8',
1023	n/a	'fi': 'fi_FI.ISO8859-15',
1024	n/a	'fi_fi': 'fi_FI.ISO8859-15',
1025	n/a	'fil_ph': 'fil_PH.UTF-8',
1026	n/a	'finnish': 'fi_FI.ISO8859-1',
1027	n/a	'fo': 'fo_FO.ISO8859-1',
1028	n/a	'fo_fo': 'fo_FO.ISO8859-1',
1029	n/a	'fr': 'fr_FR.ISO8859-1',
1030	n/a	'fr_be': 'fr_BE.ISO8859-1',
1031	n/a	'fr_ca': 'fr_CA.ISO8859-1',
1032	n/a	'fr_ch': 'fr_CH.ISO8859-1',
1033	n/a	'fr_fr': 'fr_FR.ISO8859-1',
1034	n/a	'fr_lu': 'fr_LU.ISO8859-1',
1035	n/a	'fran\xe7ais': 'fr_FR.ISO8859-1',
1036	n/a	'fre_fr': 'fr_FR.ISO8859-1',
1037	n/a	'french': 'fr_FR.ISO8859-1',
1038	n/a	'french.iso88591': 'fr_CH.ISO8859-1',
1039	n/a	'french_france': 'fr_FR.ISO8859-1',
1040	n/a	'fur_it': 'fur_IT.UTF-8',
1041	n/a	'fy_de': 'fy_DE.UTF-8',
1042	n/a	'fy_nl': 'fy_NL.UTF-8',
1043	n/a	'ga': 'ga_IE.ISO8859-1',
1044	n/a	'ga_ie': 'ga_IE.ISO8859-1',
1045	n/a	'galego': 'gl_ES.ISO8859-1',
1046	n/a	'galician': 'gl_ES.ISO8859-1',
1047	n/a	'gd': 'gd_GB.ISO8859-1',
1048	n/a	'gd_gb': 'gd_GB.ISO8859-1',
1049	n/a	'ger_de': 'de_DE.ISO8859-1',
1050	n/a	'german': 'de_DE.ISO8859-1',
1051	n/a	'german.iso88591': 'de_CH.ISO8859-1',
1052	n/a	'german_germany': 'de_DE.ISO8859-1',
1053	n/a	'gez_er': 'gez_ER.UTF-8',
1054	n/a	'gez_et': 'gez_ET.UTF-8',
1055	n/a	'gl': 'gl_ES.ISO8859-1',
1056	n/a	'gl_es': 'gl_ES.ISO8859-1',
1057	n/a	'greek': 'el_GR.ISO8859-7',
1058	n/a	'gu_in': 'gu_IN.UTF-8',
1059	n/a	'gv': 'gv_GB.ISO8859-1',
1060	n/a	'gv_gb': 'gv_GB.ISO8859-1',
1061	n/a	'ha_ng': 'ha_NG.UTF-8',
1062	n/a	'he': 'he_IL.ISO8859-8',
1063	n/a	'he_il': 'he_IL.ISO8859-8',
1064	n/a	'hebrew': 'he_IL.ISO8859-8',
1065	n/a	'hi': 'hi_IN.ISCII-DEV',
1066	n/a	'hi_in': 'hi_IN.ISCII-DEV',
1067	n/a	'hi_in.isciidev': 'hi_IN.ISCII-DEV',
1068	n/a	'hne': 'hne_IN.UTF-8',
1069	n/a	'hne_in': 'hne_IN.UTF-8',
1070	n/a	'hr': 'hr_HR.ISO8859-2',
1071	n/a	'hr_hr': 'hr_HR.ISO8859-2',
1072	n/a	'hrvatski': 'hr_HR.ISO8859-2',
1073	n/a	'hsb_de': 'hsb_DE.ISO8859-2',
1074	n/a	'ht_ht': 'ht_HT.UTF-8',
1075	n/a	'hu': 'hu_HU.ISO8859-2',
1076	n/a	'hu_hu': 'hu_HU.ISO8859-2',
1077	n/a	'hungarian': 'hu_HU.ISO8859-2',
1078	n/a	'hy_am': 'hy_AM.UTF-8',
1079	n/a	'hy_am.armscii8': 'hy_AM.ARMSCII_8',
1080	n/a	'ia': 'ia.UTF-8',
1081	n/a	'ia_fr': 'ia_FR.UTF-8',
1082	n/a	'icelandic': 'is_IS.ISO8859-1',
1083	n/a	'id': 'id_ID.ISO8859-1',
1084	n/a	'id_id': 'id_ID.ISO8859-1',
1085	n/a	'ig_ng': 'ig_NG.UTF-8',
1086	n/a	'ik_ca': 'ik_CA.UTF-8',
1087	n/a	'in': 'id_ID.ISO8859-1',
1088	n/a	'in_id': 'id_ID.ISO8859-1',
1089	n/a	'is': 'is_IS.ISO8859-1',
1090	n/a	'is_is': 'is_IS.ISO8859-1',
1091	n/a	'iso-8859-1': 'en_US.ISO8859-1',
1092	n/a	'iso-8859-15': 'en_US.ISO8859-15',
1093	n/a	'iso8859-1': 'en_US.ISO8859-1',
1094	n/a	'iso8859-15': 'en_US.ISO8859-15',
1095	n/a	'iso_8859_1': 'en_US.ISO8859-1',
1096	n/a	'iso_8859_15': 'en_US.ISO8859-15',
1097	n/a	'it': 'it_IT.ISO8859-1',
1098	n/a	'it_ch': 'it_CH.ISO8859-1',
1099	n/a	'it_it': 'it_IT.ISO8859-1',
1100	n/a	'italian': 'it_IT.ISO8859-1',
1101	n/a	'iu': 'iu_CA.NUNACOM-8',
1102	n/a	'iu_ca': 'iu_CA.NUNACOM-8',
1103	n/a	'iu_ca.nunacom8': 'iu_CA.NUNACOM-8',
1104	n/a	'iw': 'he_IL.ISO8859-8',
1105	n/a	'iw_il': 'he_IL.ISO8859-8',
1106	n/a	'iw_il.utf8': 'iw_IL.UTF-8',
1107	n/a	'ja': 'ja_JP.eucJP',
1108	n/a	'ja_jp': 'ja_JP.eucJP',
1109	n/a	'ja_jp.euc': 'ja_JP.eucJP',
1110	n/a	'ja_jp.mscode': 'ja_JP.SJIS',
1111	n/a	'ja_jp.pck': 'ja_JP.SJIS',
1112	n/a	'japan': 'ja_JP.eucJP',
1113	n/a	'japanese': 'ja_JP.eucJP',
1114	n/a	'japanese-euc': 'ja_JP.eucJP',
1115	n/a	'japanese.euc': 'ja_JP.eucJP',
1116	n/a	'jp_jp': 'ja_JP.eucJP',
1117	n/a	'ka': 'ka_GE.GEORGIAN-ACADEMY',
1118	n/a	'ka_ge': 'ka_GE.GEORGIAN-ACADEMY',
1119	n/a	'ka_ge.georgianacademy': 'ka_GE.GEORGIAN-ACADEMY',
1120	n/a	'ka_ge.georgianps': 'ka_GE.GEORGIAN-PS',
1121	n/a	'ka_ge.georgianrs': 'ka_GE.GEORGIAN-ACADEMY',
1122	n/a	'kk_kz': 'kk_KZ.RK1048',
1123	n/a	'kl': 'kl_GL.ISO8859-1',
1124	n/a	'kl_gl': 'kl_GL.ISO8859-1',
1125	n/a	'km_kh': 'km_KH.UTF-8',
1126	n/a	'kn': 'kn_IN.UTF-8',
1127	n/a	'kn_in': 'kn_IN.UTF-8',
1128	n/a	'ko': 'ko_KR.eucKR',
1129	n/a	'ko_kr': 'ko_KR.eucKR',
1130	n/a	'ko_kr.euc': 'ko_KR.eucKR',
1131	n/a	'kok_in': 'kok_IN.UTF-8',
1132	n/a	'korean': 'ko_KR.eucKR',
1133	n/a	'korean.euc': 'ko_KR.eucKR',
1134	n/a	'ks': 'ks_IN.UTF-8',
1135	n/a	'ks_in': 'ks_IN.UTF-8',
1136	n/a	'ks_in@devanagari.utf8': 'ks_IN.UTF-8@devanagari',
1137	n/a	'ku_tr': 'ku_TR.ISO8859-9',
1138	n/a	'kw': 'kw_GB.ISO8859-1',
1139	n/a	'kw_gb': 'kw_GB.ISO8859-1',
1140	n/a	'ky': 'ky_KG.UTF-8',
1141	n/a	'ky_kg': 'ky_KG.UTF-8',
1142	n/a	'lb_lu': 'lb_LU.UTF-8',
1143	n/a	'lg_ug': 'lg_UG.ISO8859-10',
1144	n/a	'li_be': 'li_BE.UTF-8',
1145	n/a	'li_nl': 'li_NL.UTF-8',
1146	n/a	'lij_it': 'lij_IT.UTF-8',
1147	n/a	'lithuanian': 'lt_LT.ISO8859-13',
1148	n/a	'lo': 'lo_LA.MULELAO-1',
1149	n/a	'lo_la': 'lo_LA.MULELAO-1',
1150	n/a	'lo_la.cp1133': 'lo_LA.IBM-CP1133',
1151	n/a	'lo_la.ibmcp1133': 'lo_LA.IBM-CP1133',
1152	n/a	'lo_la.mulelao1': 'lo_LA.MULELAO-1',
1153	n/a	'lt': 'lt_LT.ISO8859-13',
1154	n/a	'lt_lt': 'lt_LT.ISO8859-13',
1155	n/a	'lv': 'lv_LV.ISO8859-13',
1156	n/a	'lv_lv': 'lv_LV.ISO8859-13',
1157	n/a	'mag_in': 'mag_IN.UTF-8',
1158	n/a	'mai': 'mai_IN.UTF-8',
1159	n/a	'mai_in': 'mai_IN.UTF-8',
1160	n/a	'mg_mg': 'mg_MG.ISO8859-15',
1161	n/a	'mhr_ru': 'mhr_RU.UTF-8',
1162	n/a	'mi': 'mi_NZ.ISO8859-1',
1163	n/a	'mi_nz': 'mi_NZ.ISO8859-1',
1164	n/a	'mk': 'mk_MK.ISO8859-5',
1165	n/a	'mk_mk': 'mk_MK.ISO8859-5',
1166	n/a	'ml': 'ml_IN.UTF-8',
1167	n/a	'ml_in': 'ml_IN.UTF-8',
1168	n/a	'mn_mn': 'mn_MN.UTF-8',
1169	n/a	'mni_in': 'mni_IN.UTF-8',
1170	n/a	'mr': 'mr_IN.UTF-8',
1171	n/a	'mr_in': 'mr_IN.UTF-8',
1172	n/a	'ms': 'ms_MY.ISO8859-1',
1173	n/a	'ms_my': 'ms_MY.ISO8859-1',
1174	n/a	'mt': 'mt_MT.ISO8859-3',
1175	n/a	'mt_mt': 'mt_MT.ISO8859-3',
1176	n/a	'my_mm': 'my_MM.UTF-8',
1177	n/a	'nan_tw@latin': 'nan_TW.UTF-8@latin',
1178	n/a	'nb': 'nb_NO.ISO8859-1',
1179	n/a	'nb_no': 'nb_NO.ISO8859-1',
1180	n/a	'nds_de': 'nds_DE.UTF-8',
1181	n/a	'nds_nl': 'nds_NL.UTF-8',
1182	n/a	'ne_np': 'ne_NP.UTF-8',
1183	n/a	'nhn_mx': 'nhn_MX.UTF-8',
1184	n/a	'niu_nu': 'niu_NU.UTF-8',
1185	n/a	'niu_nz': 'niu_NZ.UTF-8',
1186	n/a	'nl': 'nl_NL.ISO8859-1',
1187	n/a	'nl_aw': 'nl_AW.UTF-8',
1188	n/a	'nl_be': 'nl_BE.ISO8859-1',
1189	n/a	'nl_nl': 'nl_NL.ISO8859-1',
1190	n/a	'nn': 'nn_NO.ISO8859-1',
1191	n/a	'nn_no': 'nn_NO.ISO8859-1',
1192	n/a	'no': 'no_NO.ISO8859-1',
1193	n/a	'no@nynorsk': 'ny_NO.ISO8859-1',
1194	n/a	'no_no': 'no_NO.ISO8859-1',
1195	n/a	'no_no.iso88591@bokmal': 'no_NO.ISO8859-1',
1196	n/a	'no_no.iso88591@nynorsk': 'no_NO.ISO8859-1',
1197	n/a	'norwegian': 'no_NO.ISO8859-1',
1198	n/a	'nr': 'nr_ZA.ISO8859-1',
1199	n/a	'nr_za': 'nr_ZA.ISO8859-1',
1200	n/a	'nso': 'nso_ZA.ISO8859-15',
1201	n/a	'nso_za': 'nso_ZA.ISO8859-15',
1202	n/a	'ny': 'ny_NO.ISO8859-1',
1203	n/a	'ny_no': 'ny_NO.ISO8859-1',
1204	n/a	'nynorsk': 'nn_NO.ISO8859-1',
1205	n/a	'oc': 'oc_FR.ISO8859-1',
1206	n/a	'oc_fr': 'oc_FR.ISO8859-1',
1207	n/a	'om_et': 'om_ET.UTF-8',
1208	n/a	'om_ke': 'om_KE.ISO8859-1',
1209	n/a	'or': 'or_IN.UTF-8',
1210	n/a	'or_in': 'or_IN.UTF-8',
1211	n/a	'os_ru': 'os_RU.UTF-8',
1212	n/a	'pa': 'pa_IN.UTF-8',
1213	n/a	'pa_in': 'pa_IN.UTF-8',
1214	n/a	'pa_pk': 'pa_PK.UTF-8',
1215	n/a	'pap_an': 'pap_AN.UTF-8',
1216	n/a	'pd': 'pd_US.ISO8859-1',
1217	n/a	'pd_de': 'pd_DE.ISO8859-1',
1218	n/a	'pd_us': 'pd_US.ISO8859-1',
1219	n/a	'ph': 'ph_PH.ISO8859-1',
1220	n/a	'ph_ph': 'ph_PH.ISO8859-1',
1221	n/a	'pl': 'pl_PL.ISO8859-2',
1222	n/a	'pl_pl': 'pl_PL.ISO8859-2',
1223	n/a	'polish': 'pl_PL.ISO8859-2',
1224	n/a	'portuguese': 'pt_PT.ISO8859-1',
1225	n/a	'portuguese_brazil': 'pt_BR.ISO8859-1',
1226	n/a	'posix': 'C',
1227	n/a	'posix-utf2': 'C',
1228	n/a	'pp': 'pp_AN.ISO8859-1',
1229	n/a	'pp_an': 'pp_AN.ISO8859-1',
1230	n/a	'ps_af': 'ps_AF.UTF-8',
1231	n/a	'pt': 'pt_PT.ISO8859-1',
1232	n/a	'pt_br': 'pt_BR.ISO8859-1',
1233	n/a	'pt_pt': 'pt_PT.ISO8859-1',
1234	n/a	'ro': 'ro_RO.ISO8859-2',
1235	n/a	'ro_ro': 'ro_RO.ISO8859-2',
1236	n/a	'romanian': 'ro_RO.ISO8859-2',
1237	n/a	'ru': 'ru_RU.UTF-8',
1238	n/a	'ru_ru': 'ru_RU.UTF-8',
1239	n/a	'ru_ua': 'ru_UA.KOI8-U',
1240	n/a	'rumanian': 'ro_RO.ISO8859-2',
1241	n/a	'russian': 'ru_RU.ISO8859-5',
1242	n/a	'rw': 'rw_RW.ISO8859-1',
1243	n/a	'rw_rw': 'rw_RW.ISO8859-1',
1244	n/a	'sa_in': 'sa_IN.UTF-8',
1245	n/a	'sat_in': 'sat_IN.UTF-8',
1246	n/a	'sc_it': 'sc_IT.UTF-8',
1247	n/a	'sd': 'sd_IN.UTF-8',
1248	n/a	'sd_in': 'sd_IN.UTF-8',
1249	n/a	'sd_in@devanagari.utf8': 'sd_IN.UTF-8@devanagari',
1250	n/a	'sd_pk': 'sd_PK.UTF-8',
1251	n/a	'se_no': 'se_NO.UTF-8',
1252	n/a	'serbocroatian': 'sr_RS.UTF-8@latin',
1253	n/a	'sh': 'sr_RS.UTF-8@latin',
1254	n/a	'sh_ba.iso88592@bosnia': 'sr_CS.ISO8859-2',
1255	n/a	'sh_hr': 'sh_HR.ISO8859-2',
1256	n/a	'sh_hr.iso88592': 'hr_HR.ISO8859-2',
1257	n/a	'sh_sp': 'sr_CS.ISO8859-2',
1258	n/a	'sh_yu': 'sr_RS.UTF-8@latin',
1259	n/a	'shs_ca': 'shs_CA.UTF-8',
1260	n/a	'si': 'si_LK.UTF-8',
1261	n/a	'si_lk': 'si_LK.UTF-8',
1262	n/a	'sid_et': 'sid_ET.UTF-8',
1263	n/a	'sinhala': 'si_LK.UTF-8',
1264	n/a	'sk': 'sk_SK.ISO8859-2',
1265	n/a	'sk_sk': 'sk_SK.ISO8859-2',
1266	n/a	'sl': 'sl_SI.ISO8859-2',
1267	n/a	'sl_cs': 'sl_CS.ISO8859-2',
1268	n/a	'sl_si': 'sl_SI.ISO8859-2',
1269	n/a	'slovak': 'sk_SK.ISO8859-2',
1270	n/a	'slovene': 'sl_SI.ISO8859-2',
1271	n/a	'slovenian': 'sl_SI.ISO8859-2',
1272	n/a	'so_dj': 'so_DJ.ISO8859-1',
1273	n/a	'so_et': 'so_ET.UTF-8',
1274	n/a	'so_ke': 'so_KE.ISO8859-1',
1275	n/a	'so_so': 'so_SO.ISO8859-1',
1276	n/a	'sp': 'sr_CS.ISO8859-5',
1277	n/a	'sp_yu': 'sr_CS.ISO8859-5',
1278	n/a	'spanish': 'es_ES.ISO8859-1',
1279	n/a	'spanish_spain': 'es_ES.ISO8859-1',
1280	n/a	'sq': 'sq_AL.ISO8859-2',
1281	n/a	'sq_al': 'sq_AL.ISO8859-2',
1282	n/a	'sq_mk': 'sq_MK.UTF-8',
1283	n/a	'sr': 'sr_RS.UTF-8',
1284	n/a	'sr@cyrillic': 'sr_RS.UTF-8',
1285	n/a	'sr@latn': 'sr_CS.UTF-8@latin',
1286	n/a	'sr_cs': 'sr_CS.UTF-8',
1287	n/a	'sr_cs.iso88592@latn': 'sr_CS.ISO8859-2',
1288	n/a	'sr_cs@latn': 'sr_CS.UTF-8@latin',
1289	n/a	'sr_me': 'sr_ME.UTF-8',
1290	n/a	'sr_rs': 'sr_RS.UTF-8',
1291	n/a	'sr_rs@latn': 'sr_RS.UTF-8@latin',
1292	n/a	'sr_sp': 'sr_CS.ISO8859-2',
1293	n/a	'sr_yu': 'sr_RS.UTF-8@latin',
1294	n/a	'sr_yu.cp1251@cyrillic': 'sr_CS.CP1251',
1295	n/a	'sr_yu.iso88592': 'sr_CS.ISO8859-2',
1296	n/a	'sr_yu.iso88595': 'sr_CS.ISO8859-5',
1297	n/a	'sr_yu.iso88595@cyrillic': 'sr_CS.ISO8859-5',
1298	n/a	'sr_yu.microsoftcp1251@cyrillic': 'sr_CS.CP1251',
1299	n/a	'sr_yu.utf8': 'sr_RS.UTF-8',
1300	n/a	'sr_yu.utf8@cyrillic': 'sr_RS.UTF-8',
1301	n/a	'sr_yu@cyrillic': 'sr_RS.UTF-8',
1302	n/a	'ss': 'ss_ZA.ISO8859-1',
1303	n/a	'ss_za': 'ss_ZA.ISO8859-1',
1304	n/a	'st': 'st_ZA.ISO8859-1',
1305	n/a	'st_za': 'st_ZA.ISO8859-1',
1306	n/a	'sv': 'sv_SE.ISO8859-1',
1307	n/a	'sv_fi': 'sv_FI.ISO8859-1',
1308	n/a	'sv_se': 'sv_SE.ISO8859-1',
1309	n/a	'sw_ke': 'sw_KE.UTF-8',
1310	n/a	'sw_tz': 'sw_TZ.UTF-8',
1311	n/a	'swedish': 'sv_SE.ISO8859-1',
1312	n/a	'szl_pl': 'szl_PL.UTF-8',
1313	n/a	'ta': 'ta_IN.TSCII-0',
1314	n/a	'ta_in': 'ta_IN.TSCII-0',
1315	n/a	'ta_in.tscii': 'ta_IN.TSCII-0',
1316	n/a	'ta_in.tscii0': 'ta_IN.TSCII-0',
1317	n/a	'ta_lk': 'ta_LK.UTF-8',
1318	n/a	'te': 'te_IN.UTF-8',
1319	n/a	'te_in': 'te_IN.UTF-8',
1320	n/a	'tg': 'tg_TJ.KOI8-C',
1321	n/a	'tg_tj': 'tg_TJ.KOI8-C',
1322	n/a	'th': 'th_TH.ISO8859-11',
1323	n/a	'th_th': 'th_TH.ISO8859-11',
1324	n/a	'th_th.tactis': 'th_TH.TIS620',
1325	n/a	'th_th.tis620': 'th_TH.TIS620',
1326	n/a	'thai': 'th_TH.ISO8859-11',
1327	n/a	'ti_er': 'ti_ER.UTF-8',
1328	n/a	'ti_et': 'ti_ET.UTF-8',
1329	n/a	'tig_er': 'tig_ER.UTF-8',
1330	n/a	'tk_tm': 'tk_TM.UTF-8',
1331	n/a	'tl': 'tl_PH.ISO8859-1',
1332	n/a	'tl_ph': 'tl_PH.ISO8859-1',
1333	n/a	'tn': 'tn_ZA.ISO8859-15',
1334	n/a	'tn_za': 'tn_ZA.ISO8859-15',
1335	n/a	'tr': 'tr_TR.ISO8859-9',
1336	n/a	'tr_cy': 'tr_CY.ISO8859-9',
1337	n/a	'tr_tr': 'tr_TR.ISO8859-9',
1338	n/a	'ts': 'ts_ZA.ISO8859-1',
1339	n/a	'ts_za': 'ts_ZA.ISO8859-1',
1340	n/a	'tt': 'tt_RU.TATAR-CYR',
1341	n/a	'tt_ru': 'tt_RU.TATAR-CYR',
1342	n/a	'tt_ru.tatarcyr': 'tt_RU.TATAR-CYR',
1343	n/a	'tt_ru@iqtelif': 'tt_RU.UTF-8@iqtelif',
1344	n/a	'turkish': 'tr_TR.ISO8859-9',
1345	n/a	'ug_cn': 'ug_CN.UTF-8',
1346	n/a	'uk': 'uk_UA.KOI8-U',
1347	n/a	'uk_ua': 'uk_UA.KOI8-U',
1348	n/a	'univ': 'en_US.utf',
1349	n/a	'universal': 'en_US.utf',
1350	n/a	'universal.utf8@ucs4': 'en_US.UTF-8',
1351	n/a	'unm_us': 'unm_US.UTF-8',
1352	n/a	'ur': 'ur_PK.CP1256',
1353	n/a	'ur_in': 'ur_IN.UTF-8',
1354	n/a	'ur_pk': 'ur_PK.CP1256',
1355	n/a	'uz': 'uz_UZ.UTF-8',
1356	n/a	'uz_uz': 'uz_UZ.UTF-8',
1357	n/a	'uz_uz@cyrillic': 'uz_UZ.UTF-8',
1358	n/a	've': 've_ZA.UTF-8',
1359	n/a	've_za': 've_ZA.UTF-8',
1360	n/a	'vi': 'vi_VN.TCVN',
1361	n/a	'vi_vn': 'vi_VN.TCVN',
1362	n/a	'vi_vn.tcvn': 'vi_VN.TCVN',
1363	n/a	'vi_vn.tcvn5712': 'vi_VN.TCVN',
1364	n/a	'vi_vn.viscii': 'vi_VN.VISCII',
1365	n/a	'vi_vn.viscii111': 'vi_VN.VISCII',
1366	n/a	'wa': 'wa_BE.ISO8859-1',
1367	n/a	'wa_be': 'wa_BE.ISO8859-1',
1368	n/a	'wae_ch': 'wae_CH.UTF-8',
1369	n/a	'wal_et': 'wal_ET.UTF-8',
1370	n/a	'wo_sn': 'wo_SN.UTF-8',
1371	n/a	'xh': 'xh_ZA.ISO8859-1',
1372	n/a	'xh_za': 'xh_ZA.ISO8859-1',
1373	n/a	'yi': 'yi_US.CP1255',
1374	n/a	'yi_us': 'yi_US.CP1255',
1375	n/a	'yo_ng': 'yo_NG.UTF-8',
1376	n/a	'yue_hk': 'yue_HK.UTF-8',
1377	n/a	'zh': 'zh_CN.eucCN',
1378	n/a	'zh_cn': 'zh_CN.gb2312',
1379	n/a	'zh_cn.big5': 'zh_TW.big5',
1380	n/a	'zh_cn.euc': 'zh_CN.eucCN',
1381	n/a	'zh_hk': 'zh_HK.big5hkscs',
1382	n/a	'zh_hk.big5hk': 'zh_HK.big5hkscs',
1383	n/a	'zh_sg': 'zh_SG.GB2312',
1384	n/a	'zh_sg.gbk': 'zh_SG.GBK',
1385	n/a	'zh_tw': 'zh_TW.big5',
1386	n/a	'zh_tw.euc': 'zh_TW.eucTW',
1387	n/a	'zh_tw.euctw': 'zh_TW.eucTW',
1388	n/a	'zu': 'zu_ZA.ISO8859-1',
1389	n/a	'zu_za': 'zu_ZA.ISO8859-1',
1390	n/a	}
1391	n/a
1392	n/a	#
1393	n/a	# This maps Windows language identifiers to locale strings.
1394	n/a	#
1395	n/a	# This list has been updated from
1396	n/a	# http://msdn.microsoft.com/library/default.asp?url=/library/en-us/intl/nls_238z.asp
1397	n/a	# to include every locale up to Windows Vista.
1398	n/a	#
1399	n/a	# NOTE: this mapping is incomplete. If your language is missing, please
1400	n/a	# submit a bug report to the Python bug tracker at http://bugs.python.org/
1401	n/a	# Make sure you include the missing language identifier and the suggested
1402	n/a	# locale code.
1403	n/a	#
1404	n/a
1405	n/a	windows_locale = {
1406	n/a	0x0436: "af_ZA", # Afrikaans
1407	n/a	0x041c: "sq_AL", # Albanian
1408	n/a	0x0484: "gsw_FR",# Alsatian - France
1409	n/a	0x045e: "am_ET", # Amharic - Ethiopia
1410	n/a	0x0401: "ar_SA", # Arabic - Saudi Arabia
1411	n/a	0x0801: "ar_IQ", # Arabic - Iraq
1412	n/a	0x0c01: "ar_EG", # Arabic - Egypt
1413	n/a	0x1001: "ar_LY", # Arabic - Libya
1414	n/a	0x1401: "ar_DZ", # Arabic - Algeria
1415	n/a	0x1801: "ar_MA", # Arabic - Morocco
1416	n/a	0x1c01: "ar_TN", # Arabic - Tunisia
1417	n/a	0x2001: "ar_OM", # Arabic - Oman
1418	n/a	0x2401: "ar_YE", # Arabic - Yemen
1419	n/a	0x2801: "ar_SY", # Arabic - Syria
1420	n/a	0x2c01: "ar_JO", # Arabic - Jordan
1421	n/a	0x3001: "ar_LB", # Arabic - Lebanon
1422	n/a	0x3401: "ar_KW", # Arabic - Kuwait
1423	n/a	0x3801: "ar_AE", # Arabic - United Arab Emirates
1424	n/a	0x3c01: "ar_BH", # Arabic - Bahrain
1425	n/a	0x4001: "ar_QA", # Arabic - Qatar
1426	n/a	0x042b: "hy_AM", # Armenian
1427	n/a	0x044d: "as_IN", # Assamese - India
1428	n/a	0x042c: "az_AZ", # Azeri - Latin
1429	n/a	0x082c: "az_AZ", # Azeri - Cyrillic
1430	n/a	0x046d: "ba_RU", # Bashkir
1431	n/a	0x042d: "eu_ES", # Basque - Russia
1432	n/a	0x0423: "be_BY", # Belarusian
1433	n/a	0x0445: "bn_IN", # Begali
1434	n/a	0x201a: "bs_BA", # Bosnian - Cyrillic
1435	n/a	0x141a: "bs_BA", # Bosnian - Latin
1436	n/a	0x047e: "br_FR", # Breton - France
1437	n/a	0x0402: "bg_BG", # Bulgarian
1438	n/a	# 0x0455: "my_MM", # Burmese - Not supported
1439	n/a	0x0403: "ca_ES", # Catalan
1440	n/a	0x0004: "zh_CHS",# Chinese - Simplified
1441	n/a	0x0404: "zh_TW", # Chinese - Taiwan
1442	n/a	0x0804: "zh_CN", # Chinese - PRC
1443	n/a	0x0c04: "zh_HK", # Chinese - Hong Kong S.A.R.
1444	n/a	0x1004: "zh_SG", # Chinese - Singapore
1445	n/a	0x1404: "zh_MO", # Chinese - Macao S.A.R.
1446	n/a	0x7c04: "zh_CHT",# Chinese - Traditional
1447	n/a	0x0483: "co_FR", # Corsican - France
1448	n/a	0x041a: "hr_HR", # Croatian
1449	n/a	0x101a: "hr_BA", # Croatian - Bosnia
1450	n/a	0x0405: "cs_CZ", # Czech
1451	n/a	0x0406: "da_DK", # Danish
1452	n/a	0x048c: "gbz_AF",# Dari - Afghanistan
1453	n/a	0x0465: "div_MV",# Divehi - Maldives
1454	n/a	0x0413: "nl_NL", # Dutch - The Netherlands
1455	n/a	0x0813: "nl_BE", # Dutch - Belgium
1456	n/a	0x0409: "en_US", # English - United States
1457	n/a	0x0809: "en_GB", # English - United Kingdom
1458	n/a	0x0c09: "en_AU", # English - Australia
1459	n/a	0x1009: "en_CA", # English - Canada
1460	n/a	0x1409: "en_NZ", # English - New Zealand
1461	n/a	0x1809: "en_IE", # English - Ireland
1462	n/a	0x1c09: "en_ZA", # English - South Africa
1463	n/a	0x2009: "en_JA", # English - Jamaica
1464	n/a	0x2409: "en_CB", # English - Caribbean
1465	n/a	0x2809: "en_BZ", # English - Belize
1466	n/a	0x2c09: "en_TT", # English - Trinidad
1467	n/a	0x3009: "en_ZW", # English - Zimbabwe
1468	n/a	0x3409: "en_PH", # English - Philippines
1469	n/a	0x4009: "en_IN", # English - India
1470	n/a	0x4409: "en_MY", # English - Malaysia
1471	n/a	0x4809: "en_IN", # English - Singapore
1472	n/a	0x0425: "et_EE", # Estonian
1473	n/a	0x0438: "fo_FO", # Faroese
1474	n/a	0x0464: "fil_PH",# Filipino
1475	n/a	0x040b: "fi_FI", # Finnish
1476	n/a	0x040c: "fr_FR", # French - France
1477	n/a	0x080c: "fr_BE", # French - Belgium
1478	n/a	0x0c0c: "fr_CA", # French - Canada
1479	n/a	0x100c: "fr_CH", # French - Switzerland
1480	n/a	0x140c: "fr_LU", # French - Luxembourg
1481	n/a	0x180c: "fr_MC", # French - Monaco
1482	n/a	0x0462: "fy_NL", # Frisian - Netherlands
1483	n/a	0x0456: "gl_ES", # Galician
1484	n/a	0x0437: "ka_GE", # Georgian
1485	n/a	0x0407: "de_DE", # German - Germany
1486	n/a	0x0807: "de_CH", # German - Switzerland
1487	n/a	0x0c07: "de_AT", # German - Austria
1488	n/a	0x1007: "de_LU", # German - Luxembourg
1489	n/a	0x1407: "de_LI", # German - Liechtenstein
1490	n/a	0x0408: "el_GR", # Greek
1491	n/a	0x046f: "kl_GL", # Greenlandic - Greenland
1492	n/a	0x0447: "gu_IN", # Gujarati
1493	n/a	0x0468: "ha_NG", # Hausa - Latin
1494	n/a	0x040d: "he_IL", # Hebrew
1495	n/a	0x0439: "hi_IN", # Hindi
1496	n/a	0x040e: "hu_HU", # Hungarian
1497	n/a	0x040f: "is_IS", # Icelandic
1498	n/a	0x0421: "id_ID", # Indonesian
1499	n/a	0x045d: "iu_CA", # Inuktitut - Syllabics
1500	n/a	0x085d: "iu_CA", # Inuktitut - Latin
1501	n/a	0x083c: "ga_IE", # Irish - Ireland
1502	n/a	0x0410: "it_IT", # Italian - Italy
1503	n/a	0x0810: "it_CH", # Italian - Switzerland
1504	n/a	0x0411: "ja_JP", # Japanese
1505	n/a	0x044b: "kn_IN", # Kannada - India
1506	n/a	0x043f: "kk_KZ", # Kazakh
1507	n/a	0x0453: "kh_KH", # Khmer - Cambodia
1508	n/a	0x0486: "qut_GT",# K'iche - Guatemala
1509	n/a	0x0487: "rw_RW", # Kinyarwanda - Rwanda
1510	n/a	0x0457: "kok_IN",# Konkani
1511	n/a	0x0412: "ko_KR", # Korean
1512	n/a	0x0440: "ky_KG", # Kyrgyz
1513	n/a	0x0454: "lo_LA", # Lao - Lao PDR
1514	n/a	0x0426: "lv_LV", # Latvian
1515	n/a	0x0427: "lt_LT", # Lithuanian
1516	n/a	0x082e: "dsb_DE",# Lower Sorbian - Germany
1517	n/a	0x046e: "lb_LU", # Luxembourgish
1518	n/a	0x042f: "mk_MK", # FYROM Macedonian
1519	n/a	0x043e: "ms_MY", # Malay - Malaysia
1520	n/a	0x083e: "ms_BN", # Malay - Brunei Darussalam
1521	n/a	0x044c: "ml_IN", # Malayalam - India
1522	n/a	0x043a: "mt_MT", # Maltese
1523	n/a	0x0481: "mi_NZ", # Maori
1524	n/a	0x047a: "arn_CL",# Mapudungun
1525	n/a	0x044e: "mr_IN", # Marathi
1526	n/a	0x047c: "moh_CA",# Mohawk - Canada
1527	n/a	0x0450: "mn_MN", # Mongolian - Cyrillic
1528	n/a	0x0850: "mn_CN", # Mongolian - PRC
1529	n/a	0x0461: "ne_NP", # Nepali
1530	n/a	0x0414: "nb_NO", # Norwegian - Bokmal
1531	n/a	0x0814: "nn_NO", # Norwegian - Nynorsk
1532	n/a	0x0482: "oc_FR", # Occitan - France
1533	n/a	0x0448: "or_IN", # Oriya - India
1534	n/a	0x0463: "ps_AF", # Pashto - Afghanistan
1535	n/a	0x0429: "fa_IR", # Persian
1536	n/a	0x0415: "pl_PL", # Polish
1537	n/a	0x0416: "pt_BR", # Portuguese - Brazil
1538	n/a	0x0816: "pt_PT", # Portuguese - Portugal
1539	n/a	0x0446: "pa_IN", # Punjabi
1540	n/a	0x046b: "quz_BO",# Quechua (Bolivia)
1541	n/a	0x086b: "quz_EC",# Quechua (Ecuador)
1542	n/a	0x0c6b: "quz_PE",# Quechua (Peru)
1543	n/a	0x0418: "ro_RO", # Romanian - Romania
1544	n/a	0x0417: "rm_CH", # Romansh
1545	n/a	0x0419: "ru_RU", # Russian
1546	n/a	0x243b: "smn_FI",# Sami Finland
1547	n/a	0x103b: "smj_NO",# Sami Norway
1548	n/a	0x143b: "smj_SE",# Sami Sweden
1549	n/a	0x043b: "se_NO", # Sami Northern Norway
1550	n/a	0x083b: "se_SE", # Sami Northern Sweden
1551	n/a	0x0c3b: "se_FI", # Sami Northern Finland
1552	n/a	0x203b: "sms_FI",# Sami Skolt
1553	n/a	0x183b: "sma_NO",# Sami Southern Norway
1554	n/a	0x1c3b: "sma_SE",# Sami Southern Sweden
1555	n/a	0x044f: "sa_IN", # Sanskrit
1556	n/a	0x0c1a: "sr_SP", # Serbian - Cyrillic
1557	n/a	0x1c1a: "sr_BA", # Serbian - Bosnia Cyrillic
1558	n/a	0x081a: "sr_SP", # Serbian - Latin
1559	n/a	0x181a: "sr_BA", # Serbian - Bosnia Latin
1560	n/a	0x045b: "si_LK", # Sinhala - Sri Lanka
1561	n/a	0x046c: "ns_ZA", # Northern Sotho
1562	n/a	0x0432: "tn_ZA", # Setswana - Southern Africa
1563	n/a	0x041b: "sk_SK", # Slovak
1564	n/a	0x0424: "sl_SI", # Slovenian
1565	n/a	0x040a: "es_ES", # Spanish - Spain
1566	n/a	0x080a: "es_MX", # Spanish - Mexico
1567	n/a	0x0c0a: "es_ES", # Spanish - Spain (Modern)
1568	n/a	0x100a: "es_GT", # Spanish - Guatemala
1569	n/a	0x140a: "es_CR", # Spanish - Costa Rica
1570	n/a	0x180a: "es_PA", # Spanish - Panama
1571	n/a	0x1c0a: "es_DO", # Spanish - Dominican Republic
1572	n/a	0x200a: "es_VE", # Spanish - Venezuela
1573	n/a	0x240a: "es_CO", # Spanish - Colombia
1574	n/a	0x280a: "es_PE", # Spanish - Peru
1575	n/a	0x2c0a: "es_AR", # Spanish - Argentina
1576	n/a	0x300a: "es_EC", # Spanish - Ecuador
1577	n/a	0x340a: "es_CL", # Spanish - Chile
1578	n/a	0x380a: "es_UR", # Spanish - Uruguay
1579	n/a	0x3c0a: "es_PY", # Spanish - Paraguay
1580	n/a	0x400a: "es_BO", # Spanish - Bolivia
1581	n/a	0x440a: "es_SV", # Spanish - El Salvador
1582	n/a	0x480a: "es_HN", # Spanish - Honduras
1583	n/a	0x4c0a: "es_NI", # Spanish - Nicaragua
1584	n/a	0x500a: "es_PR", # Spanish - Puerto Rico
1585	n/a	0x540a: "es_US", # Spanish - United States
1586	n/a	# 0x0430: "", # Sutu - Not supported
1587	n/a	0x0441: "sw_KE", # Swahili
1588	n/a	0x041d: "sv_SE", # Swedish - Sweden
1589	n/a	0x081d: "sv_FI", # Swedish - Finland
1590	n/a	0x045a: "syr_SY",# Syriac
1591	n/a	0x0428: "tg_TJ", # Tajik - Cyrillic
1592	n/a	0x085f: "tmz_DZ",# Tamazight - Latin
1593	n/a	0x0449: "ta_IN", # Tamil
1594	n/a	0x0444: "tt_RU", # Tatar
1595	n/a	0x044a: "te_IN", # Telugu
1596	n/a	0x041e: "th_TH", # Thai
1597	n/a	0x0851: "bo_BT", # Tibetan - Bhutan
1598	n/a	0x0451: "bo_CN", # Tibetan - PRC
1599	n/a	0x041f: "tr_TR", # Turkish
1600	n/a	0x0442: "tk_TM", # Turkmen - Cyrillic
1601	n/a	0x0480: "ug_CN", # Uighur - Arabic
1602	n/a	0x0422: "uk_UA", # Ukrainian
1603	n/a	0x042e: "wen_DE",# Upper Sorbian - Germany
1604	n/a	0x0420: "ur_PK", # Urdu
1605	n/a	0x0820: "ur_IN", # Urdu - India
1606	n/a	0x0443: "uz_UZ", # Uzbek - Latin
1607	n/a	0x0843: "uz_UZ", # Uzbek - Cyrillic
1608	n/a	0x042a: "vi_VN", # Vietnamese
1609	n/a	0x0452: "cy_GB", # Welsh
1610	n/a	0x0488: "wo_SN", # Wolof - Senegal
1611	n/a	0x0434: "xh_ZA", # Xhosa - South Africa
1612	n/a	0x0485: "sah_RU",# Yakut - Cyrillic
1613	n/a	0x0478: "ii_CN", # Yi - PRC
1614	n/a	0x046a: "yo_NG", # Yoruba - Nigeria
1615	n/a	0x0435: "zu_ZA", # Zulu
1616	n/a	}
1617	n/a
1618	n/a	def _print_locale():
1619	n/a
1620	n/a	""" Test function.
1621	n/a	"""
1622	n/a	categories = {}
1623	n/a	def _init_categories(categories=categories):
1624	n/a	for k,v in globals().items():
1625	n/a	if k[:3] == 'LC_':
1626	n/a	categories[k] = v
1627	n/a	_init_categories()
1628	n/a	del categories['LC_ALL']
1629	n/a
1630	n/a	print('Locale defaults as determined by getdefaultlocale():')
1631	n/a	print('-'*72)
1632	n/a	lang, enc = getdefaultlocale()
1633	n/a	print('Language: ', lang or '(undefined)')
1634	n/a	print('Encoding: ', enc or '(undefined)')
1635	n/a	print()
1636	n/a
1637	n/a	print('Locale settings on startup:')
1638	n/a	print('-'*72)
1639	n/a	for name,category in categories.items():
1640	n/a	print(name, '...')
1641	n/a	lang, enc = getlocale(category)
1642	n/a	print(' Language: ', lang or '(undefined)')
1643	n/a	print(' Encoding: ', enc or '(undefined)')
1644	n/a	print()
1645	n/a
1646	n/a	print()
1647	n/a	print('Locale settings after calling resetlocale():')
1648	n/a	print('-'*72)
1649	n/a	resetlocale()
1650	n/a	for name,category in categories.items():
1651	n/a	print(name, '...')
1652	n/a	lang, enc = getlocale(category)
1653	n/a	print(' Language: ', lang or '(undefined)')
1654	n/a	print(' Encoding: ', enc or '(undefined)')
1655	n/a	print()
1656	n/a
1657	n/a	try:
1658	n/a	setlocale(LC_ALL, "")
1659	n/a	except:
1660	n/a	print('NOTE:')
1661	n/a	print('setlocale(LC_ALL, "") does not support the default locale')
1662	n/a	print('given in the OS environment variables.')
1663	n/a	else:
1664	n/a	print()
1665	n/a	print('Locale settings after calling setlocale(LC_ALL, ""):')
1666	n/a	print('-'*72)
1667	n/a	for name,category in categories.items():
1668	n/a	print(name, '...')
1669	n/a	lang, enc = getlocale(category)
1670	n/a	print(' Language: ', lang or '(undefined)')
1671	n/a	print(' Encoding: ', enc or '(undefined)')
1672	n/a	print()
1673	n/a
1674	n/a	###
1675	n/a
1676	n/a	try:
1677	n/a	LC_MESSAGES
1678	n/a	except NameError:
1679	n/a	pass
1680	n/a	else:
1681	n/a	__all__.append("LC_MESSAGES")
1682	n/a
1683	n/a	if __name__=='__main__':
1684	n/a	print('Locale aliasing:')
1685	n/a	print()
1686	n/a	_print_locale()
1687	n/a	print()
1688	n/a	print('Number formatting:')
1689	n/a	print()
1690	n/a	_test()