Repository navigation
Expand file tree
/
Copy pathlocale.py
More file actions
1706 lines (1585 loc) · 73.8 KB
/
Copy pathlocale.py
File metadata and controls
1706 lines (1585 loc) · 73.8 KB
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
483
484
485
486
487
488
489
490
491
492
493
494
495
496
497
498
499
500
501
502
503
504
505
506
507
508
509
510
511
512
513
514
515
516
517
518
519
520
521
522
523
524
525
526
527
528
529
530
531
532
533
534
535
536
537
538
539
540
541
542
543
544
545
546
547
548
549
550
551
552
553
554
555
556
557
558
559
560
561
562
563
564
565
566
567
568
569
570
571
572
573
574
575
576
577
578
579
580
581
582
583
584
585
586
587
588
589
590
591
592
593
594
595
596
597
598
599
600
601
602
603
604
605
606
607
608
609
610
611
612
613
614
615
616
617
618
619
620
621
622
623
624
625
626
627
628
629
630
631
632
633
634
635
636
637
638
639
640
641
642
643
644
645
646
647
648
649
650
651
652
653
654
655
656
657
658
659
660
661
662
663
664
665
666
667
668
669
670
671
672
673
674
675
676
677
678
679
680
681
682
683
684
685
686
687
688
689
690
691
692
693
694
695
696
697
698
699
700
701
702
703
704
705
706
707
708
709
710
711
712
713
714
715
716
717
718
719
720
721
722
723
724
725
726
727
728
729
730
731
732
733
734
735
736
737
738
739
740
741
742
743
744
745
746
747
748
749
750
751
752
753
754
755
756
757
758
759
760
761
762
763
764
765
766
767
768
769
770
771
772
773
774
775
776
777
778
779
780
781
782
783
784
785
786
787
788
789
790
791
792
793
794
795
796
797
798
799
800
801
802
803
804
805
806
807
808
809
810
811
812
813
814
815
816
817
818
819
820
821
822
823
824
825
826
827
828
829
830
831
832
833
834
835
836
837
838
839
840
841
842
843
844
845
846
847
848
849
850
851
852
853
854
855
856
857
858
859
860
861
862
863
864
865
866
867
868
869
870
871
872
873
874
875
876
877
878
879
880
881
882
883
884
885
886
887
888
889
890
891
892
893
894
895
896
897
898
899
900
901
902
903
904
905
906
907
908
909
910
911
912
913
914
915
916
917
918
919
920
921
922
923
924
925
926
927
928
929
930
931
932
933
934
935
936
937
938
939
940
941
942
943
944
945
946
947
948
949
950
951
952
953
954
955
956
957
958
959
960
961
962
963
964
965
966
967
968
969
970
971
972
973
974
975
976
977
978
979
980
981
982
983
984
985
986
987
988
989
990
991
992
993
994
995
996
997
998
999
1000
"""Locale support module.
The module provides low-level access to the C lib's locale APIs and adds high
level number formatting APIs as well as a locale aliasing engine to complement
these.
The aliasing engine includes support for many commonly used locale names and
maps them to values suitable for passing to the C lib's setlocale() function. It
also includes default encodings for all supported locale names.
"""
import sys
import encodings
import encodings.aliases
import re
import _collections_abc
from builtins import str as _builtin_str
import functools
# Try importing the _locale module.
#
# If this fails, fall back on a basic 'C' locale emulation.
# Yuck: LC_MESSAGES is non-standard: can't tell whether it exists before
# trying the import. So __all__ is also fiddled at the end of the file.
__all__ = ["getlocale", "getdefaultlocale", "getpreferredencoding", "Error",
"setlocale", "resetlocale", "localeconv", "strcoll", "strxfrm",
"str", "atof", "atoi", "format", "format_string", "currency",
"normalize", "LC_CTYPE", "LC_COLLATE", "LC_TIME", "LC_MONETARY",
"LC_NUMERIC", "LC_ALL", "CHAR_MAX"]
def _strcoll(a,b):
""" strcoll(string,string) -> int.
Compares two strings according to the locale.
"""
return (a > b) - (a < b)
def _strxfrm(s):
""" strxfrm(string) -> string.
Returns a string that behaves for cmp locale-aware.
"""
return s
try:
from _locale import *
except ImportError:
# Locale emulation
CHAR_MAX = 127
LC_ALL = 6
LC_COLLATE = 3
LC_CTYPE = 0
LC_MESSAGES = 5
LC_MONETARY = 4
LC_NUMERIC = 1
LC_TIME = 2
Error = ValueError
def localeconv():
""" localeconv() -> dict.
Returns numeric and monetary locale-specific parameters.
"""
# 'C' locale default values
return {'grouping': [127],
'currency_symbol': '',
'n_sign_posn': 127,
'p_cs_precedes': 127,
'n_cs_precedes': 127,
'mon_grouping': [],
'n_sep_by_space': 127,
'decimal_point': '.',
'negative_sign': '',
'positive_sign': '',
'p_sep_by_space': 127,
'int_curr_symbol': '',
'p_sign_posn': 127,
'thousands_sep': '',
'mon_thousands_sep': '',
'frac_digits': 127,
'mon_decimal_point': '',
'int_frac_digits': 127}
def setlocale(category, value=None):
""" setlocale(integer,string=None) -> string.
Activates/queries locale processing.
"""
if value not in (None, '', 'C'):
raise Error('_locale emulation only supports "C" locale')
return 'C'
# These may or may not exist in _locale, so be sure to set them.
if 'strxfrm' not in globals():
strxfrm = _strxfrm
if 'strcoll' not in globals():
strcoll = _strcoll
_localeconv = localeconv
# With this dict, you can override some items of localeconv's return value.
# This is useful for testing purposes.
_override_localeconv = {}
@functools.wraps(_localeconv)
def localeconv():
d = _localeconv()
if _override_localeconv:
d.update(_override_localeconv)
return d
### Number formatting APIs
# Author: Martin von Loewis
# improved by Georg Brandl
# Iterate over grouping intervals
def _grouping_intervals(grouping):
last_interval = None
for interval in grouping:
# if grouping is -1, we are done
if interval == CHAR_MAX:
return
# 0: re-use last group ad infinitum
if interval == 0:
if last_interval is None:
raise ValueError("invalid grouping")
while True:
yield last_interval
yield interval
last_interval = interval
#perform the grouping from right to left
def _group(s, monetary=False):
conv = localeconv()
thousands_sep = conv[monetary and 'mon_thousands_sep' or 'thousands_sep']
grouping = conv[monetary and 'mon_grouping' or 'grouping']
if not grouping:
return (s, 0)
if s[-1] == ' ':
stripped = s.rstrip()
right_spaces = s[len(stripped):]
s = stripped
else:
right_spaces = ''
left_spaces = ''
groups = []
for interval in _grouping_intervals(grouping):
if not s or s[-1] not in "0123456789":
# only non-digit characters remain (sign, spaces)
left_spaces = s
s = ''
break
groups.append(s[-interval:])
s = s[:-interval]
if s:
groups.append(s)
groups.reverse()
return (
left_spaces + thousands_sep.join(groups) + right_spaces,
len(thousands_sep) * (len(groups) - 1)
)
# Strip a given amount of excess padding from the given string
def _strip_padding(s, amount):
lpos = 0
while amount and s[lpos] == ' ':
lpos += 1
amount -= 1
rpos = len(s) - 1
while amount and s[rpos] == ' ':
rpos -= 1
amount -= 1
return s[lpos:rpos+1]
_percent_re = re.compile(r'%(?:\((?P<key>.*?)\))?'
r'(?P<modifiers>[-#0-9 +*.hlL]*?)[eEfFgGdiouxXcrs%]')
def _format(percent, value, grouping=False, monetary=False, *additional):
if additional:
formatted = percent % ((value,) + additional)
else:
formatted = percent % value
# floats and decimal ints need special action!
if percent[-1] in 'eEfFgG':
seps = 0
parts = formatted.split('.')
if grouping:
parts[0], seps = _group(parts[0], monetary=monetary)
decimal_point = localeconv()[monetary and 'mon_decimal_point'
or 'decimal_point']
formatted = decimal_point.join(parts)
if seps:
formatted = _strip_padding(formatted, seps)
elif percent[-1] in 'diu':
seps = 0
if grouping:
formatted, seps = _group(formatted, monetary=monetary)
if seps:
formatted = _strip_padding(formatted, seps)
return formatted
def format_string(f, val, grouping=False, monetary=False):
"""Formats a string in the same way that the % formatting would use,
but takes the current locale into account.
Grouping is applied if the third parameter is true.
Conversion uses monetary thousands separator and grouping strings if
forth parameter monetary is true."""
percents = list(_percent_re.finditer(f))
new_f = _percent_re.sub('%s', f)
if isinstance(val, _collections_abc.Mapping):
new_val = []
for perc in percents:
if perc.group()[-1]=='%':
new_val.append('%')
else:
new_val.append(_format(perc.group(), val, grouping, monetary))
else:
if not isinstance(val, tuple):
val = (val,)
new_val = []
i = 0
for perc in percents:
if perc.group()[-1]=='%':
new_val.append('%')
else:
starcount = perc.group('modifiers').count('*')
new_val.append(_format(perc.group(),
val[i],
grouping,
monetary,
*val[i+1:i+1+starcount]))
i += (1 + starcount)
val = tuple(new_val)
return new_f % val
def format(percent, value, grouping=False, monetary=False, *additional):
"""Deprecated, use format_string instead."""
import warnings
warnings.warn(
"This method will be removed in a future version of Python. "
"Use 'locale.format_string()' instead.",
DeprecationWarning, stacklevel=2
)
match = _percent_re.match(percent)
if not match or len(match.group())!= len(percent):
raise ValueError(("format() must be given exactly one %%char "
"format specifier, %s not valid") % repr(percent))
return _format(percent, value, grouping, monetary, *additional)
def currency(val, symbol=True, grouping=False, international=False):
"""Formats val according to the currency settings
in the current locale."""
conv = localeconv()
# check for illegal values
digits = conv[international and 'int_frac_digits' or 'frac_digits']
if digits == 127:
raise ValueError("Currency formatting is not possible using "
"the 'C' locale.")
s = _format('%%.%if' % digits, abs(val), grouping, monetary=True)
# '<' and '>' are markers if the sign must be inserted between symbol and value
s = '<' + s + '>'
if symbol:
smb = conv[international and 'int_curr_symbol' or 'currency_symbol']
precedes = conv[val<0 and 'n_cs_precedes' or 'p_cs_precedes']
separated = conv[val<0 and 'n_sep_by_space' or 'p_sep_by_space']
if precedes:
s = smb + (separated and ' ' or '') + s
else:
s = s + (separated and ' ' or '') + smb
sign_pos = conv[val<0 and 'n_sign_posn' or 'p_sign_posn']
sign = conv[val<0 and 'negative_sign' or 'positive_sign']
if sign_pos == 0:
s = '(' + s + ')'
elif sign_pos == 1:
s = sign + s
elif sign_pos == 2:
s = s + sign
elif sign_pos == 3:
s = s.replace('<', sign)
elif sign_pos == 4:
s = s.replace('>', sign)
else:
# the default if nothing specified;
# this should be the most fitting sign position
s = sign + s
return s.replace('<', '').replace('>', '')
def str(val):
"""Convert float to string, taking the locale into account."""
return _format("%.12g", val)
def delocalize(string):
"Parses a string as a normalized number according to the locale settings."
conv = localeconv()
#First, get rid of the grouping
ts = conv['thousands_sep']
if ts:
string = string.replace(ts, '')
#next, replace the decimal point with a dot
dd = conv['decimal_point']
if dd:
string = string.replace(dd, '.')
return string
def atof(string, func=float):
"Parses a string as a float according to the locale settings."
return func(delocalize(string))
def atoi(string):
"Converts a string to an integer according to the locale settings."
return int(delocalize(string))
def _test():
setlocale(LC_ALL, "")
#do grouping
s1 = format_string("%d", 123456789,1)
print(s1, "is", atoi(s1))
#standard formatting
s1 = str(3.14)
print(s1, "is", atof(s1))
### Locale name aliasing engine
# Author: Marc-Andre Lemburg, mal@lemburg.com
# Various tweaks by Fredrik Lundh <fredrik@pythonware.com>
# store away the low-level version of setlocale (it's
# overridden below)
_setlocale = setlocale
def _replace_encoding(code, encoding):
if '.' in code:
langname = code[:code.index('.')]
else:
langname = code
# Convert the encoding to a C lib compatible encoding string
norm_encoding = encodings.normalize_encoding(encoding)
#print('norm encoding: %r' % norm_encoding)
norm_encoding = encodings.aliases.aliases.get(norm_encoding.lower(),
norm_encoding)
#print('aliased encoding: %r' % norm_encoding)
encoding = norm_encoding
norm_encoding = norm_encoding.lower()
if norm_encoding in locale_encoding_alias:
encoding = locale_encoding_alias[norm_encoding]
else:
norm_encoding = norm_encoding.replace('_', '')
norm_encoding = norm_encoding.replace('-', '')
if norm_encoding in locale_encoding_alias:
encoding = locale_encoding_alias[norm_encoding]
#print('found encoding %r' % encoding)
return langname + '.' + encoding
def _append_modifier(code, modifier):
if modifier == 'euro':
if '.' not in code:
return code + '.ISO8859-15'
_, _, encoding = code.partition('.')
if encoding in ('ISO8859-15', 'UTF-8'):
return code
if encoding == 'ISO8859-1':
return _replace_encoding(code, 'ISO8859-15')
return code + '@' + modifier
def normalize(localename):
""" Returns a normalized locale code for the given locale
name.
The returned locale code is formatted for use with
setlocale().
If normalization fails, the original name is returned
unchanged.
If the given encoding is not known, the function defaults to
the default encoding for the locale code just like setlocale()
does.
"""
# Normalize the locale name and extract the encoding and modifier
code = localename.lower()
if ':' in code:
# ':' is sometimes used as encoding delimiter.
code = code.replace(':', '.')
if '@' in code:
code, modifier = code.split('@', 1)
else:
modifier = ''
if '.' in code:
langname, encoding = code.split('.')[:2]
else:
langname = code
encoding = ''
# First lookup: fullname (possibly with encoding and modifier)
lang_enc = langname
if encoding:
norm_encoding = encoding.replace('-', '')
norm_encoding = norm_encoding.replace('_', '')
lang_enc += '.' + norm_encoding
lookup_name = lang_enc
if modifier:
lookup_name += '@' + modifier
code = locale_alias.get(lookup_name, None)
if code is not None:
return code
#print('first lookup failed')
if modifier:
# Second try: fullname without modifier (possibly with encoding)
code = locale_alias.get(lang_enc, None)
if code is not None:
#print('lookup without modifier succeeded')
if '@' not in code:
return _append_modifier(code, modifier)
if code.split('@', 1)[1].lower() == modifier:
return code
#print('second lookup failed')
if encoding:
# Third try: langname (without encoding, possibly with modifier)
lookup_name = langname
if modifier:
lookup_name += '@' + modifier
code = locale_alias.get(lookup_name, None)
if code is not None:
#print('lookup without encoding succeeded')
if '@' not in code:
return _replace_encoding(code, encoding)
code, modifier = code.split('@', 1)
return _replace_encoding(code, encoding) + '@' + modifier
if modifier:
# Fourth try: langname (without encoding and modifier)
code = locale_alias.get(langname, None)
if code is not None:
#print('lookup without modifier and encoding succeeded')
if '@' not in code:
code = _replace_encoding(code, encoding)
return _append_modifier(code, modifier)
code, defmod = code.split('@', 1)
if defmod.lower() == modifier:
return _replace_encoding(code, encoding) + '@' + defmod
return localename
def _parse_localename(localename):
""" Parses the locale code for localename and returns the
result as tuple (language code, encoding).
The localename is normalized and passed through the locale
alias engine. A ValueError is raised in case the locale name
cannot be parsed.
The language code corresponds to RFC 1766. code and encoding
can be None in case the values cannot be determined or are
unknown to this implementation.
"""
code = normalize(localename)
if '@' in code:
# Deal with locale modifiers
code, modifier = code.split('@', 1)
if modifier == 'euro' and '.' not in code:
# Assume Latin-9 for @euro locales. This is bogus,
# since some systems may use other encodings for these
# locales. Also, we ignore other modifiers.
return code, 'iso-8859-15'
if '.' in code:
return tuple(code.split('.')[:2])
elif code == 'C':
return None, None
raise ValueError('unknown locale: %s' % localename)
def _build_localename(localetuple):
""" Builds a locale code from the given tuple (language code,
encoding).
No aliasing or normalizing takes place.
"""
try:
language, encoding = localetuple
if language is None:
language = 'C'
if encoding is None:
return language
else:
return language + '.' + encoding
except (TypeError, ValueError):
raise TypeError('Locale must be None, a string, or an iterable of '
'two strings -- language code, encoding.') from None
def getdefaultlocale(envvars=('LC_ALL', 'LC_CTYPE', 'LANG', 'LANGUAGE')):
""" Tries to determine the default locale settings and returns
them as tuple (language code, encoding).
According to POSIX, a program which has not called
setlocale(LC_ALL, "") runs using the portable 'C' locale.
Calling setlocale(LC_ALL, "") lets it use the default locale as
defined by the LANG variable. Since we don't want to interfere
with the current locale setting we thus emulate the behavior
in the way described above.
To maintain compatibility with other platforms, not only the
LANG variable is tested, but a list of variables given as
envvars parameter. The first found to be defined will be
used. envvars defaults to the search path used in GNU gettext;
it must always contain the variable name 'LANG'.
Except for the code 'C', the language code corresponds to RFC
1766. code and encoding can be None in case the values cannot
be determined.
"""
try:
# check if it's supported by the _locale module
import _locale
code, encoding = _locale._getdefaultlocale()
except (ImportError, AttributeError):
pass
else:
# make sure the code/encoding values are valid
if sys.platform == "win32" and code and code[:2] == "0x":
# map windows language identifier to language name
code = windows_locale.get(int(code, 0))
# ...add other platform-specific processing here, if
# necessary...
return code, encoding
# fall back on POSIX behaviour
import os
lookup = os.environ.get
for variable in envvars:
localename = lookup(variable,None)
if localename:
if variable == 'LANGUAGE':
localename = localename.split(':')[0]
break
else:
localename = 'C'
return _parse_localename(localename)
def getlocale(category=LC_CTYPE):
""" Returns the current setting for the given locale category as
tuple (language code, encoding).
category may be one of the LC_* value except LC_ALL. It
defaults to LC_CTYPE.
Except for the code 'C', the language code corresponds to RFC
1766. code and encoding can be None in case the values cannot
be determined.
"""
localename = _setlocale(category)
if category == LC_ALL and ';' in localename:
raise TypeError('category LC_ALL is not supported')
return _parse_localename(localename)
def setlocale(category, locale=None):
""" Set the locale for the given category. The locale can be
a string, an iterable of two strings (language code and encoding),
or None.
Iterables are converted to strings using the locale aliasing
engine. Locale strings are passed directly to the C lib.
category may be given as one of the LC_* values.
"""
if locale and not isinstance(locale, _builtin_str):
# convert to string
locale = normalize(_build_localename(locale))
return _setlocale(category, locale)
def resetlocale(category=LC_ALL):
""" Sets the locale for category to the default setting.
The default setting is determined by calling
getdefaultlocale(). category defaults to LC_ALL.
"""
_setlocale(category, _build_localename(getdefaultlocale()))
if sys.platform.startswith("win"):
# On Win32, this will return the ANSI code page
def getpreferredencoding(do_setlocale = True):
"""Return the charset that the user is likely using."""
if sys.flags.utf8_mode:
return 'UTF-8'
import _bootlocale
return _bootlocale.getpreferredencoding(False)
else:
# On Unix, if CODESET is available, use that.
try:
CODESET
except NameError:
if hasattr(sys, 'getandroidapilevel'):
# On Android langinfo.h and CODESET are missing, and UTF-8 is
# always used in mbstowcs() and wcstombs().
def getpreferredencoding(do_setlocale = True):
return 'UTF-8'
else:
# Fall back to parsing environment variables :-(
def getpreferredencoding(do_setlocale = True):
"""Return the charset that the user is likely using,
by looking at environment variables."""
if sys.flags.utf8_mode:
return 'UTF-8'
res = getdefaultlocale()[1]
if res is None:
# LANG not set, default conservatively to ASCII
res = 'ascii'
return res
else:
def getpreferredencoding(do_setlocale = True):
"""Return the charset that the user is likely using,
according to the system configuration."""
if sys.flags.utf8_mode:
return 'UTF-8'
import _bootlocale
if do_setlocale:
oldloc = setlocale(LC_CTYPE)
try:
setlocale(LC_CTYPE, "")
except Error:
pass
result = _bootlocale.getpreferredencoding(False)
if do_setlocale:
setlocale(LC_CTYPE, oldloc)
return result
### Database
#
# The following data was extracted from the locale.alias file which
# comes with X11 and then hand edited removing the explicit encoding
# definitions and adding some more aliases. The file is usually
# available as /usr/lib/X11/locale/locale.alias.
#
#
# The local_encoding_alias table maps lowercase encoding alias names
# to C locale encoding names (case-sensitive). Note that normalize()
# first looks up the encoding in the encodings.aliases dictionary and
# then applies this mapping to find the correct C lib name for the
# encoding.
#
locale_encoding_alias = {
# Mappings for non-standard encoding names used in locale names
'437': 'C',
'c': 'C',
'en': 'ISO8859-1',
'jis': 'JIS7',
'jis7': 'JIS7',
'ajec': 'eucJP',
'koi8c': 'KOI8-C',
'microsoftcp1251': 'CP1251',
'microsoftcp1255': 'CP1255',
'microsoftcp1256': 'CP1256',
'88591': 'ISO8859-1',
'88592': 'ISO8859-2',
'88595': 'ISO8859-5',
'885915': 'ISO8859-15',
# Mappings from Python codec names to C lib encoding names
'ascii': 'ISO8859-1',
'latin_1': 'ISO8859-1',
'iso8859_1': 'ISO8859-1',
'iso8859_10': 'ISO8859-10',
'iso8859_11': 'ISO8859-11',
'iso8859_13': 'ISO8859-13',
'iso8859_14': 'ISO8859-14',
'iso8859_15': 'ISO8859-15',
'iso8859_16': 'ISO8859-16',
'iso8859_2': 'ISO8859-2',
'iso8859_3': 'ISO8859-3',
'iso8859_4': 'ISO8859-4',
'iso8859_5': 'ISO8859-5',
'iso8859_6': 'ISO8859-6',
'iso8859_7': 'ISO8859-7',
'iso8859_8': 'ISO8859-8',
'iso8859_9': 'ISO8859-9',
'iso2022_jp': 'JIS7',
'shift_jis': 'SJIS',
'tactis': 'TACTIS',
'euc_jp': 'eucJP',
'euc_kr': 'eucKR',
'utf_8': 'UTF-8',
'koi8_r': 'KOI8-R',
'koi8_t': 'KOI8-T',
'koi8_u': 'KOI8-U',
'kz1048': 'RK1048',
'cp1251': 'CP1251',
'cp1255': 'CP1255',
'cp1256': 'CP1256',
# XXX This list is still incomplete. If you know more
# mappings, please file a bug report. Thanks.
}
for k, v in sorted(locale_encoding_alias.items()):
k = k.replace('_', '')
locale_encoding_alias.setdefault(k, v)
#
# The locale_alias table maps lowercase alias names to C locale names
# (case-sensitive). Encodings are always separated from the locale
# name using a dot ('.'); they should only be given in case the
# language name is needed to interpret the given encoding alias
# correctly (CJK codes often have this need).
#
# Note that the normalize() function which uses this tables
# removes '_' and '-' characters from the encoding part of the
# locale name before doing the lookup. This saves a lot of
# space in the table.
#
# MAL 2004-12-10:
# Updated alias mapping to most recent locale.alias file
# from X.org distribution using makelocalealias.py.
#
# These are the differences compared to the old mapping (Python 2.4
# and older):
#
# updated 'bg' -> 'bg_BG.ISO8859-5' to 'bg_BG.CP1251'
# updated 'bg_bg' -> 'bg_BG.ISO8859-5' to 'bg_BG.CP1251'
# updated 'bulgarian' -> 'bg_BG.ISO8859-5' to 'bg_BG.CP1251'
# updated 'cz' -> 'cz_CZ.ISO8859-2' to 'cs_CZ.ISO8859-2'
# updated 'cz_cz' -> 'cz_CZ.ISO8859-2' to 'cs_CZ.ISO8859-2'
# updated 'czech' -> 'cs_CS.ISO8859-2' to 'cs_CZ.ISO8859-2'
# updated 'dutch' -> 'nl_BE.ISO8859-1' to 'nl_NL.ISO8859-1'
# updated 'et' -> 'et_EE.ISO8859-4' to 'et_EE.ISO8859-15'
# updated 'et_ee' -> 'et_EE.ISO8859-4' to 'et_EE.ISO8859-15'
# updated 'fi' -> 'fi_FI.ISO8859-1' to 'fi_FI.ISO8859-15'
# updated 'fi_fi' -> 'fi_FI.ISO8859-1' to 'fi_FI.ISO8859-15'
# updated 'iw' -> 'iw_IL.ISO8859-8' to 'he_IL.ISO8859-8'
# updated 'iw_il' -> 'iw_IL.ISO8859-8' to 'he_IL.ISO8859-8'
# updated 'japanese' -> 'ja_JP.SJIS' to 'ja_JP.eucJP'
# updated 'lt' -> 'lt_LT.ISO8859-4' to 'lt_LT.ISO8859-13'
# updated 'lv' -> 'lv_LV.ISO8859-4' to 'lv_LV.ISO8859-13'
# updated 'sl' -> 'sl_CS.ISO8859-2' to 'sl_SI.ISO8859-2'
# updated 'slovene' -> 'sl_CS.ISO8859-2' to 'sl_SI.ISO8859-2'
# updated 'th_th' -> 'th_TH.TACTIS' to 'th_TH.ISO8859-11'
# updated 'zh_cn' -> 'zh_CN.eucCN' to 'zh_CN.gb2312'
# updated 'zh_cn.big5' -> 'zh_TW.eucTW' to 'zh_TW.big5'
# updated 'zh_tw' -> 'zh_TW.eucTW' to 'zh_TW.big5'
#
# MAL 2008-05-30:
# Updated alias mapping to most recent locale.alias file
# from X.org distribution using makelocalealias.py.
#
# These are the differences compared to the old mapping (Python 2.5
# and older):
#
# updated 'cs_cs.iso88592' -> 'cs_CZ.ISO8859-2' to 'cs_CS.ISO8859-2'
# updated 'serbocroatian' -> 'sh_YU.ISO8859-2' to 'sr_CS.ISO8859-2'
# updated 'sh' -> 'sh_YU.ISO8859-2' to 'sr_CS.ISO8859-2'
# updated 'sh_hr.iso88592' -> 'sh_HR.ISO8859-2' to 'hr_HR.ISO8859-2'
# updated 'sh_sp' -> 'sh_YU.ISO8859-2' to 'sr_CS.ISO8859-2'
# updated 'sh_yu' -> 'sh_YU.ISO8859-2' to 'sr_CS.ISO8859-2'
# updated 'sp' -> 'sp_YU.ISO8859-5' to 'sr_CS.ISO8859-5'
# updated 'sp_yu' -> 'sp_YU.ISO8859-5' to 'sr_CS.ISO8859-5'
# updated 'sr' -> 'sr_YU.ISO8859-5' to 'sr_CS.ISO8859-5'
# updated 'sr@cyrillic' -> 'sr_YU.ISO8859-5' to 'sr_CS.ISO8859-5'
# updated 'sr_sp' -> 'sr_SP.ISO8859-2' to 'sr_CS.ISO8859-2'
# updated 'sr_yu' -> 'sr_YU.ISO8859-5' to 'sr_CS.ISO8859-5'
# updated 'sr_yu.cp1251@cyrillic' -> 'sr_YU.CP1251' to 'sr_CS.CP1251'
# updated 'sr_yu.iso88592' -> 'sr_YU.ISO8859-2' to 'sr_CS.ISO8859-2'
# updated 'sr_yu.iso88595' -> 'sr_YU.ISO8859-5' to 'sr_CS.ISO8859-5'
# updated 'sr_yu.iso88595@cyrillic' -> 'sr_YU.ISO8859-5' to 'sr_CS.ISO8859-5'
# updated 'sr_yu.microsoftcp1251@cyrillic' -> 'sr_YU.CP1251' to 'sr_CS.CP1251'
# updated 'sr_yu.utf8@cyrillic' -> 'sr_YU.UTF-8' to 'sr_CS.UTF-8'
# updated 'sr_yu@cyrillic' -> 'sr_YU.ISO8859-5' to 'sr_CS.ISO8859-5'
#
# AP 2010-04-12:
# Updated alias mapping to most recent locale.alias file
# from X.org distribution using makelocalealias.py.
#
# These are the differences compared to the old mapping (Python 2.6.5
# and older):
#
# updated 'ru' -> 'ru_RU.ISO8859-5' to 'ru_RU.UTF-8'
# updated 'ru_ru' -> 'ru_RU.ISO8859-5' to 'ru_RU.UTF-8'
# updated 'serbocroatian' -> 'sr_CS.ISO8859-2' to 'sr_RS.UTF-8@latin'
# updated 'sh' -> 'sr_CS.ISO8859-2' to 'sr_RS.UTF-8@latin'
# updated 'sh_yu' -> 'sr_CS.ISO8859-2' to 'sr_RS.UTF-8@latin'
# updated 'sr' -> 'sr_CS.ISO8859-5' to 'sr_RS.UTF-8'
# updated 'sr@cyrillic' -> 'sr_CS.ISO8859-5' to 'sr_RS.UTF-8'
# updated 'sr@latn' -> 'sr_CS.ISO8859-2' to 'sr_RS.UTF-8@latin'
# updated 'sr_cs.utf8@latn' -> 'sr_CS.UTF-8' to 'sr_RS.UTF-8@latin'
# updated 'sr_cs@latn' -> 'sr_CS.ISO8859-2' to 'sr_RS.UTF-8@latin'
# updated 'sr_yu' -> 'sr_CS.ISO8859-5' to 'sr_RS.UTF-8@latin'
# updated 'sr_yu.utf8@cyrillic' -> 'sr_CS.UTF-8' to 'sr_RS.UTF-8'
# updated 'sr_yu@cyrillic' -> 'sr_CS.ISO8859-5' to 'sr_RS.UTF-8'
#
# SS 2013-12-20:
# Updated alias mapping to most recent locale.alias file
# from X.org distribution using makelocalealias.py.
#
# These are the differences compared to the old mapping (Python 3.3.3
# and older):
#
# updated 'a3' -> 'a3_AZ.KOI8-C' to 'az_AZ.KOI8-C'
# updated 'a3_az' -> 'a3_AZ.KOI8-C' to 'az_AZ.KOI8-C'
# updated 'a3_az.koi8c' -> 'a3_AZ.KOI8-C' to 'az_AZ.KOI8-C'
# updated 'cs_cs.iso88592' -> 'cs_CS.ISO8859-2' to 'cs_CZ.ISO8859-2'
# updated 'hebrew' -> 'iw_IL.ISO8859-8' to 'he_IL.ISO8859-8'
# updated 'hebrew.iso88598' -> 'iw_IL.ISO8859-8' to 'he_IL.ISO8859-8'
# updated 'sd' -> 'sd_IN@devanagari.UTF-8' to 'sd_IN.UTF-8'
# updated 'sr@latn' -> 'sr_RS.UTF-8@latin' to 'sr_CS.UTF-8@latin'
# updated 'sr_cs' -> 'sr_RS.UTF-8' to 'sr_CS.UTF-8'
# updated 'sr_cs.utf8@latn' -> 'sr_RS.UTF-8@latin' to 'sr_CS.UTF-8@latin'
# updated 'sr_cs@latn' -> 'sr_RS.UTF-8@latin' to 'sr_CS.UTF-8@latin'
#
# SS 2014-10-01:
# Updated alias mapping with glibc 2.19 supported locales.
#
# Licht-T 2018-05-05:
# Add en_il mapping, which is added in glibc 2.24.
locale_alias = {
'a3': 'az_AZ.KOI8-C',
'a3_az': 'az_AZ.KOI8-C',
'a3_az.koic': 'az_AZ.KOI8-C',
'aa_dj': 'aa_DJ.ISO8859-1',
'aa_er': 'aa_ER.UTF-8',
'aa_et': 'aa_ET.UTF-8',
'af': 'af_ZA.ISO8859-1',
'af_za': 'af_ZA.ISO8859-1',
'am': 'am_ET.UTF-8',
'am_et': 'am_ET.UTF-8',
'american': 'en_US.ISO8859-1',
'an_es': 'an_ES.ISO8859-15',
'ar': 'ar_AA.ISO8859-6',
'ar_aa': 'ar_AA.ISO8859-6',
'ar_ae': 'ar_AE.ISO8859-6',
'ar_bh': 'ar_BH.ISO8859-6',
'ar_dz': 'ar_DZ.ISO8859-6',
'ar_eg': 'ar_EG.ISO8859-6',
'ar_in': 'ar_IN.UTF-8',
'ar_iq': 'ar_IQ.ISO8859-6',
'ar_jo': 'ar_JO.ISO8859-6',
'ar_kw': 'ar_KW.ISO8859-6',
'ar_lb': 'ar_LB.ISO8859-6',
'ar_ly': 'ar_LY.ISO8859-6',
'ar_ma': 'ar_MA.ISO8859-6',
'ar_om': 'ar_OM.ISO8859-6',
'ar_qa': 'ar_QA.ISO8859-6',
'ar_sa': 'ar_SA.ISO8859-6',
'ar_sd': 'ar_SD.ISO8859-6',
'ar_sy': 'ar_SY.ISO8859-6',
'ar_tn': 'ar_TN.ISO8859-6',
'ar_ye': 'ar_YE.ISO8859-6',
'arabic': 'ar_AA.ISO8859-6',
'as': 'as_IN.UTF-8',
'as_in': 'as_IN.UTF-8',
'ast_es': 'ast_ES.ISO8859-15',
'ayc_pe': 'ayc_PE.UTF-8',
'az': 'az_AZ.ISO8859-9E',
'az_az': 'az_AZ.ISO8859-9E',
'az_az.iso88599e': 'az_AZ.ISO8859-9E',
'be': 'be_BY.CP1251',
'be@latin': 'be_BY.UTF-8@latin',
'be_bg.utf8': 'bg_BG.UTF-8',
'be_by': 'be_BY.CP1251',
'be_by@latin': 'be_BY.UTF-8@latin',
'bem_zm': 'bem_ZM.UTF-8',
'ber_dz': 'ber_DZ.UTF-8',
'ber_ma': 'ber_MA.UTF-8',
'bg': 'bg_BG.CP1251',
'bg_bg': 'bg_BG.CP1251',
'bho_in': 'bho_IN.UTF-8',
'bn_bd': 'bn_BD.UTF-8',
'bn_in': 'bn_IN.UTF-8',
'bo_cn': 'bo_CN.UTF-8',
'bo_in': 'bo_IN.UTF-8',
'bokmal': 'nb_NO.ISO8859-1',
'bokm\xe5l': 'nb_NO.ISO8859-1',
'br': 'br_FR.ISO8859-1',
'br_fr': 'br_FR.ISO8859-1',
'brx_in': 'brx_IN.UTF-8',
'bs': 'bs_BA.ISO8859-2',
'bs_ba': 'bs_BA.ISO8859-2',
'bulgarian': 'bg_BG.CP1251',
'byn_er': 'byn_ER.UTF-8',
'c': 'C',
'c-french': 'fr_CA.ISO8859-1',
'c.ascii': 'C',
'c.en': 'C',
'c.iso88591': 'en_US.ISO8859-1',
'c.utf8': 'en_US.UTF-8',
'c_c': 'C',
'c_c.c': 'C',
'ca': 'ca_ES.ISO8859-1',
'ca_ad': 'ca_AD.ISO8859-1',
'ca_es': 'ca_ES.ISO8859-1',
'ca_es@valencia': 'ca_ES.ISO8859-15@valencia',
'ca_fr': 'ca_FR.ISO8859-1',
'ca_it': 'ca_IT.ISO8859-1',
'catalan': 'ca_ES.ISO8859-1',
'cextend': 'en_US.ISO8859-1',
'chinese-s': 'zh_CN.eucCN',
'chinese-t': 'zh_TW.eucTW',
'crh_ua': 'crh_UA.UTF-8',
'croatian': 'hr_HR.ISO8859-2',
'cs': 'cs_CZ.ISO8859-2',
'cs_cs': 'cs_CZ.ISO8859-2',
'cs_cz': 'cs_CZ.ISO8859-2',
'csb_pl': 'csb_PL.UTF-8',
'cv_ru': 'cv_RU.UTF-8',
'cy': 'cy_GB.ISO8859-1',
'cy_gb': 'cy_GB.ISO8859-1',
'cz': 'cs_CZ.ISO8859-2',
'cz_cz': 'cs_CZ.ISO8859-2',
'czech': 'cs_CZ.ISO8859-2',
'da': 'da_DK.ISO8859-1',
'da_dk': 'da_DK.ISO8859-1',
'danish': 'da_DK.ISO8859-1',
'dansk': 'da_DK.ISO8859-1',
'de': 'de_DE.ISO8859-1',
'de_at': 'de_AT.ISO8859-1',
'de_be': 'de_BE.ISO8859-1',
'de_ch': 'de_CH.ISO8859-1',
'de_de': 'de_DE.ISO8859-1',
'de_li.utf8': 'de_LI.UTF-8',
'de_lu': 'de_LU.ISO8859-1',
'deutsch': 'de_DE.ISO8859-1',
'doi_in': 'doi_IN.UTF-8',
'dutch': 'nl_NL.ISO8859-1',
'dutch.iso88591': 'nl_BE.ISO8859-1',
'dv_mv': 'dv_MV.UTF-8',
'dz_bt': 'dz_BT.UTF-8',
'ee': 'ee_EE.ISO8859-4',
'ee_ee': 'ee_EE.ISO8859-4',
'eesti': 'et_EE.ISO8859-1',
'el': 'el_GR.ISO8859-7',
'el_cy': 'el_CY.ISO8859-7',
'el_gr': 'el_GR.ISO8859-7',
'el_gr@euro': 'el_GR.ISO8859-15',
'en': 'en_US.ISO8859-1',
'en_ag': 'en_AG.UTF-8',
'en_au': 'en_AU.ISO8859-1',
'en_be': 'en_BE.ISO8859-1',
'en_bw': 'en_BW.ISO8859-1',
'en_ca': 'en_CA.ISO8859-1',
'en_dk': 'en_DK.ISO8859-1',
'en_dl.utf8': 'en_DL.UTF-8',
'en_gb': 'en_GB.ISO8859-1',
'en_hk': 'en_HK.ISO8859-1',
'en_ie': 'en_IE.ISO8859-1',
'en_il': 'en_IL.UTF-8',
'en_in': 'en_IN.ISO8859-1',
'en_ng': 'en_NG.UTF-8',
'en_nz': 'en_NZ.ISO8859-1',
'en_ph': 'en_PH.ISO8859-1',
'en_sg': 'en_SG.ISO8859-1',
'en_uk': 'en_GB.ISO8859-1',
'en_us': 'en_US.ISO8859-1',
'en_us@euro@euro': 'en_US.ISO8859-15',
'en_za': 'en_ZA.ISO8859-1',
'en_zm': 'en_ZM.UTF-8',
'en_zw': 'en_ZW.ISO8859-1',
'en_zw.utf8': 'en_ZS.UTF-8',
'eng_gb': 'en_GB.ISO8859-1',
'english': 'en_EN.ISO8859-1',
'english_uk': 'en_GB.ISO8859-1',
'english_united-states': 'en_US.ISO8859-1',
'english_united-states.437': 'C',