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
1001
1002
1003
1004
1005
1006
1007
1008
1009
1010
1011
1012
1013
1014
1015
1016
1017
1018
1019
1020
1021
1022
1023
1024
1025
1026
1027
1028
1029
1030
1031
1032
1033
1034
1035
1036
1037
1038
1039
1040
1041
1042
1043
1044
1045
1046
1047
1048
1049
1050
1051
1052
1053
1054
1055
1056
1057
1058
1059
1060
1061
1062
1063
1064
1065
1066
1067
1068
1069
1070
1071
1072
1073
1074
1075
1076
1077
1078
1079
1080
1081
1082
1083
1084
1085
1086
1087
1088
1089
1090
1091
1092
1093
1094
1095
1096
1097
1098
1099
1100
1101
1102
1103
1104
1105
1106
1107
1108
1109
1110
1111
1112
1113
1114
1115
1116
1117
1118
1119
1120
1121
1122
1123
1124
1125
1126
1127
1128
1129
1130
1131
1132
1133
1134
1135
1136
1137
1138
1139
1140
1141
1142
1143
1144
1145
1146
1147
1148
1149
1150
1151
1152
1153
1154
1155
1156
1157
1158
1159
1160
1161
1162
1163
1164
1165
1166
1167
1168
1169
1170
1171
1172
1173
1174
1175
1176
1177
1178
1179
1180
1181
1182
1183
1184
1185
1186
1187
1188
1189
1190
1191
1192
1193
1194
1195
1196
1197
1198
1199
1200
1201
1202
1203
1204
1205
1206
1207
1208
1209
1210
1211
1212
1213
1214
1215
1216
1217
1218
1219
1220
1221
1222
1223
1224
1225
1226
1227
1228
1229
1230
1231
1232
1233
1234
1235
1236
1237
1238
1239
1240
1241
1242
1243
1244
1245
1246
1247
1248
1249
1250
1251
1252
1253
1254
1255
1256
1257
1258
1259
1260
1261
1262
1263
1264
1265
1266
1267
1268
1269
1270
1271
1272
1273
1274
1275
1276
1277
1278
1279
1280
1281
1282
1283
1284
1285
1286
1287
1288
1289
1290
1291
1292
1293
1294
1295
1296
1297
1298
1299
1300
1301
1302
1303
1304
1305
1306
1307
1308
1309
1310
1311
1312
1313
1314
1315
1316
1317
1318
1319
1320
1321
1322
1323
1324
1325
1326
1327
1328
1329
1330
1331
1332
1333
1334
1335
1336
1337
1338
1339
1340
1341
1342
1343
1344
1345
1346
1347
1348
1349
1350
1351
1352
1353
1354
1355
1356
1357
1358
1359
1360
1361
1362
1363
1364
1365
1366
1367
1368
1369
1370
1371
1372
1373
1374
1375
1376
1377
1378
1379
1380
1381
1382
1383
1384
1385
1386
1387
1388
1389
1390
1391
1392
1393
1394
1395
1396
1397
1398
1399
1400
1401
1402
1403
1404
1405
1406
1407
1408
1409
1410
1411
1412
1413
1414
1415
1416
1417
1418
1419
1420
1421
1422
1423
1424
1425
1426
1427
1428
1429
1430
1431
1432
1433
1434
1435
1436
1437
1438
1439
1440
1441
1442
1443
1444
1445
1446
1447
1448
1449
1450
1451
1452
1453
1454
1455
1456
1457
1458
1459
1460
1461
1462
1463
1464
1465
1466
1467
1468
1469
1470
1471
1472
1473
1474
1475
1476
1477
1478
1479
1480
1481
1482
1483
1484
1485
1486
1487
1488
1489
1490
1491
1492
1493
1494
1495
1496
1497
1498
1499
1500
1501
1502
1503
1504
1505
1506
1507
1508
1509
1510
1511
1512
1513
1514
1515
1516
1517
1518
1519
1520
1521
1522
1523
1524
1525
1526
1527
1528
1529
1530
1531
1532
1533
1534
1535
1536
1537
1538
1539
1540
1541
1542
1543
1544
1545
1546
1547
1548
1549
1550
1551
1552
1553
1554
1555
1556
1557
1558
1559
1560
1561
1562
1563
1564
1565
1566
1567
1568
1569
1570
1571
1572
1573
1574
1575
1576
1577
1578
1579
1580
1581
1582
1583
1584
1585
1586
1587
1588
1589
1590
1591
1592
1593
1594
1595
1596
1597
1598
1599
1600
1601
1602
1603
1604
1605
1606
1607
1608
1609
1610
1611
1612
1613
1614
1615
1616
1617
1618
1619
1620
1621
1622
1623
1624
1625
1626
1627
1628
1629
1630
1631
1632
1633
1634
1635
1636
1637
1638
1639
1640
1641
1642
1643
1644
1645
1646
1647
1648
1649
1650
1651
1652
1653
1654
1655
1656
1657
1658
1659
1660
1661
1662
1663
1664
1665
1666
1667
1668
1669
1670
1671
1672
1673
1674
1675
1676
1677
1678
1679
1680
1681
1682
1683
1684
1685
1686
1687
1688
1689
1690
1691
1692
1693
1694
1695
1696
1697
1698
1699
1700
1701
1702
1703
1704
1705
1706
1707
1708
1709
1710
1711
1712
1713
1714
1715
1716
1717
1718
1719
1720
1721
1722
1723
1724
1725
1726
1727
1728
1729
1730
1731
1732
1733
1734
1735
1736
1737
1738
1739
1740
1741
1742
1743
1744
1745
1746
1747
1748
1749
1750
1751
1752
1753
1754
1755
1756
1757
1758
1759
1760
1761
1762
1763
1764
1765
1766
1767
1768
1769
1770
1771
1772
1773
1774
1775
1776
1777
1778
1779
1780
1781
1782
1783
1784
1785
1786
1787
1788
1789
1790
1791
1792
1793
1794
1795
1796
1797
1798
1799
1800
1801
1802
1803
1804
1805
1806
1807
1808
1809
1810
1811
1812
1813
1814
1815
1816
1817
1818
1819
1820
1821
1822
1823
1824
1825
1826
1827
1828
1829
1830
1831
1832
1833
1834
1835
1836
1837
1838
1839
1840
1841
1842
1843
1844
1845
1846
1847
1848
1849
1850
1851
1852
1853
1854
1855
1856
1857
1858
1859
1860
1861
1862
1863
1864
1865
1866
1867
1868
1869
1870
1871
1872
1873
1874
1875
1876
1877
1878
1879
1880
1881
1882
1883
1884
1885
1886
1887
1888
1889
1890
1891
1892
1893
1894
1895
1896
1897
1898
1899
1900
1901
1902
1903
1904
1905
1906
1907
1908
1909
1910
1911
1912
1913
1914
1915
1916
1917
1918
1919
1920
1921
1922
1923
1924
1925
1926
1927
1928
1929
1930
1931
1932
1933
1934
1935
1936
1937
1938
1939
1940
1941
1942
1943
1944
1945
1946
1947
1948
1949
1950
1951
1952
1953
1954
1955
1956
1957
1958
1959
1960
1961
1962
1963
1964
1965
1966
1967
1968
1969
1970
1971
1972
1973
1974
1975
1976
1977
1978
1979
1980
1981
1982
1983
1984
1985
1986
1987
1988
1989
1990
1991
1992
1993
1994
1995
1996
1997
1998
1999
2000
2001
2002
2003
2004
2005
2006
2007
2008
2009
2010
2011
2012
2013
2014
2015
2016
2017
2018
2019
2020
2021
2022
2023
2024
2025
2026
2027
2028
2029
2030
2031
2032
2033
2034
2035
2036
2037
2038
2039
2040
2041
2042
2043
2044
2045
2046
2047
2048
2049
2050
2051
2052
2053
2054
2055
2056
2057
2058
2059
2060
2061
2062
2063
2064
2065
2066
2067
2068
2069
2070
2071
2072
2073
2074
2075
2076
2077
2078
2079
2080
2081
2082
2083
2084
2085
2086
2087
2088
2089
2090
2091
2092
2093
2094
2095
2096
2097
2098
2099
2100
2101
2102
2103
2104
2105
2106
2107
2108
2109
2110
2111
2112
2113
2114
2115
2116
2117
2118
2119
2120
2121
2122
2123
2124
2125
|
"""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 operator
import functools
# keep a copy of the builtin str type, because 'str' name is overridden
# in globals by a function below
_str = str
try:
_unicode = unicode
except NameError:
# If Python is built without Unicode support, the unicode type
# will not exist. Fake one.
class _unicode(object):
pass
# 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"]
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'
def strcoll(a,b):
""" strcoll(string,string) -> int.
Compares two strings according to the locale.
"""
return cmp(a,b)
def strxfrm(s):
""" strxfrm(string) -> string.
Returns a string that behaves for cmp locale-aware.
"""
return s
_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):
"""Returns the locale-aware substitution of a %? specifier
(percent).
additional is for format strings which contain one or more
'*' modifiers."""
# this is only for one-percent-specifier strings and this should be checked
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 _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):
"""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."""
percents = list(_percent_re.finditer(f))
new_f = _percent_re.sub('%s', f)
if operator.isMappingType(val):
new_val = []
for perc in percents:
if perc.group()[-1]=='%':
new_val.append('%')
else:
new_val.append(format(perc.group(), val, grouping))
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,
False,
*val[i+1:i+1+starcount]))
i += (1 + starcount)
val = tuple(new_val)
return new_f % val
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 atof(string, func=float):
"Parses a string as a float according to the locale settings."
#First, get rid of the grouping
ts = localeconv()['thousands_sep']
if ts:
string = string.replace(ts, '')
#next, replace the decimal point with a dot
dd = localeconv()['decimal_point']
if dd:
string = string.replace(dd, '.')
#finally, parse the string
return func(string)
def atoi(str):
"Converts a string to an integer according to the locale settings."
return atof(str, int)
def _test():
setlocale(LC_ALL, "")
#do grouping
s1 = format("%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
# Avoid relying on the locale-dependent .lower() method
# (see issue #1813).
_ascii_lower_map = ''.join(
chr(x + 32 if x >= ord('A') and x <= ord('Z') else x)
for x in range(256)
)
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,
norm_encoding)
#print('aliased encoding: %r' % norm_encoding)
encoding = locale_encoding_alias.get(norm_encoding,
norm_encoding)
#print('found encoding %r' % encoding)
return langname + '.' + encoding
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
if isinstance(localename, _unicode):
localename = localename.encode('ascii')
code = localename.translate(_ascii_lower_map)
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 code + '@' + modifier
if code.split('@', 1)[1].translate(_ascii_lower_map) == 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:
return _replace_encoding(code, encoding) + '@' + modifier
code, defmod = code.split('@', 1)
if defmod.translate(_ascii_lower_map) == 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.
"""
language, encoding = localetuple
if language is None:
language = 'C'
if encoding is None:
return language
else:
return language + '.' + encoding
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, (_str, _unicode)):
# 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."""
import _locale
return _locale._getdefaultlocale()[1]
else:
# On Unix, if CODESET is available, use that.
try:
CODESET
except NameError:
# 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."""
return getdefaultlocale()[1]
else:
def getpreferredencoding(do_setlocale = True):
"""Return the charset that the user is likely using,
according to the system configuration."""
if do_setlocale:
oldloc = setlocale(LC_CTYPE)
try:
setlocale(LC_CTYPE, "")
except Error:
pass
result = nl_langinfo(CODESET)
setlocale(LC_CTYPE, oldloc)
else:
result = nl_langinfo(CODESET)
if not result and sys.platform == 'darwin':
# nl_langinfo can return an empty string
# when the setting has an invalid value.
# Default to UTF-8 in that case because
# UTF-8 is the default charset on OSX and
# returning nothing will crash the
# interpreter.
result = 'UTF-8'
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',
# 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_u': 'KOI8-U',
# XXX This list is still incomplete. If you know more
# mappings, please file a bug report. Thanks.
}
#
# 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 2.7.6
# 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.
#
# SS 2018-05-05:
# Updated alias mapping with glibc 2.27 supported locales.
#
# These are the differences compared to the old mapping (Python 2.7.15
# and older):
#
# updated 'ca_es@valencia' -> 'ca_ES.ISO8859-15@valencia' to 'ca_ES.UTF-8@valencia'
# updated 'english.iso88591' -> 'en_EN.ISO8859-1' to 'en_US.ISO8859-1'
# updated 'kk_kz' -> 'kk_KZ.RK1048' to 'kk_KZ.ptcp154'
# updated 'russian' -> 'ru_RU.ISO8859-5' to 'ru_RU.KOI8-R'
locale_alias = {
'a3': 'az_AZ.KOI8-C',
'a3_az': 'az_AZ.KOI8-C',
'a3_az.koi8c': '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',
'af_za.iso88591': 'af_ZA.ISO8859-1',
'agr_pe': 'agr_PE.UTF-8',
'ak_gh': 'ak_GH.UTF-8',
'am': 'am_ET.UTF-8',
'am_et': 'am_ET.UTF-8',
'american': 'en_US.ISO8859-1',
'american.iso88591': 'en_US.ISO8859-1',
'an_es': 'an_ES.ISO8859-15',
'anp_in': 'anp_IN.UTF-8',
'ar': 'ar_AA.ISO8859-6',
'ar_aa': 'ar_AA.ISO8859-6',
'ar_aa.iso88596': 'ar_AA.ISO8859-6',
'ar_ae': 'ar_AE.ISO8859-6',
'ar_ae.iso88596': 'ar_AE.ISO8859-6',
'ar_bh': 'ar_BH.ISO8859-6',
'ar_bh.iso88596': 'ar_BH.ISO8859-6',
'ar_dz': 'ar_DZ.ISO8859-6',
'ar_dz.iso88596': 'ar_DZ.ISO8859-6',
'ar_eg': 'ar_EG.ISO8859-6',
'ar_eg.iso88596': 'ar_EG.ISO8859-6',
'ar_in': 'ar_IN.UTF-8',
'ar_iq': 'ar_IQ.ISO8859-6',
'ar_iq.iso88596': 'ar_IQ.ISO8859-6',
'ar_jo': 'ar_JO.ISO8859-6',
'ar_jo.iso88596': 'ar_JO.ISO8859-6',
'ar_kw': 'ar_KW.ISO8859-6',
'ar_kw.iso88596': 'ar_KW.ISO8859-6',
'ar_lb': 'ar_LB.ISO8859-6',
'ar_lb.iso88596': 'ar_LB.ISO8859-6',
'ar_ly': 'ar_LY.ISO8859-6',
'ar_ly.iso88596': 'ar_LY.ISO8859-6',
'ar_ma': 'ar_MA.ISO8859-6',
'ar_ma.iso88596': 'ar_MA.ISO8859-6',
'ar_om': 'ar_OM.ISO8859-6',
'ar_om.iso88596': 'ar_OM.ISO8859-6',
'ar_qa': 'ar_QA.ISO8859-6',
'ar_qa.iso88596': 'ar_QA.ISO8859-6',
'ar_sa': 'ar_SA.ISO8859-6',
'ar_sa.iso88596': 'ar_SA.ISO8859-6',
'ar_sd': 'ar_SD.ISO8859-6',
'ar_sd.iso88596': 'ar_SD.ISO8859-6',
'ar_ss': 'ar_SS.UTF-8',
'ar_sy': 'ar_SY.ISO8859-6',
'ar_sy.iso88596': 'ar_SY.ISO8859-6',
'ar_tn': 'ar_TN.ISO8859-6',
'ar_tn.iso88596': 'ar_TN.ISO8859-6',
'ar_ye': 'ar_YE.ISO8859-6',
'ar_ye.iso88596': 'ar_YE.ISO8859-6',
'arabic': 'ar_AA.ISO8859-6',
'arabic.iso88596': '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',
'az_ir': 'az_IR.UTF-8',
'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.cp1251': 'be_BY.CP1251',
'be_by.microsoftcp1251': 'be_BY.CP1251',
'be_by.utf8@latin': 'be_BY.UTF-8@latin',
'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',
'bg_bg.cp1251': 'bg_BG.CP1251',
'bg_bg.iso88595': 'bg_BG.ISO8859-5',
'bg_bg.koi8r': 'bg_BG.KOI8-R',
'bg_bg.microsoftcp1251': 'bg_BG.CP1251',
'bhb_in.utf8': 'bhb_IN.UTF-8',
'bho_in': 'bho_IN.UTF-8',
'bho_np': 'bho_NP.UTF-8',
'bi_vu': 'bi_VU.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',
'br_fr.iso88591': 'br_FR.ISO8859-1',
'br_fr.iso885914': 'br_FR.ISO8859-14',
'br_fr.iso885915': 'br_FR.ISO8859-15',
'br_fr.iso885915@euro': 'br_FR.ISO8859-15',
'br_fr.utf8@euro': 'br_FR.UTF-8',
'br_fr@euro': 'br_FR.ISO8859-15',
'brx_in': 'brx_IN.UTF-8',
'bs': 'bs_BA.ISO8859-2',
'bs_ba': 'bs_BA.ISO8859-2',
'bs_ba.iso88592': 'bs_BA.ISO8859-2',
'bulgarian': 'bg_BG.CP1251',
'byn_er': 'byn_ER.UTF-8',
'c': 'C',
'c-french': 'fr_CA.ISO8859-1',
'c-french.iso88591': '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_ad.iso88591': 'ca_AD.ISO8859-1',
'ca_ad.iso885915': 'ca_AD.ISO8859-15',
'ca_ad.iso885915@euro': 'ca_AD.ISO8859-15',
'ca_ad.utf8@euro': 'ca_AD.UTF-8',
'ca_ad@euro': 'ca_AD.ISO8859-15',
'ca_es': 'ca_ES.ISO8859-1',
'ca_es.iso88591': 'ca_ES.ISO8859-1',
'ca_es.iso885915': 'ca_ES.ISO8859-15',
'ca_es.iso885915@euro': 'ca_ES.ISO8859-15',
'ca_es.utf8@euro': 'ca_ES.UTF-8',
'ca_es@euro': 'ca_ES.ISO8859-15',
'ca_es@valencia': 'ca_ES.UTF-8@valencia',
'ca_fr': 'ca_FR.ISO8859-1',
'ca_fr.iso88591': 'ca_FR.ISO8859-1',
'ca_fr.iso885915': 'ca_FR.ISO8859-15',
'ca_fr.iso885915@euro': 'ca_FR.ISO8859-15',
'ca_fr.utf8@euro': 'ca_FR.UTF-8',
'ca_fr@euro': 'ca_FR.ISO8859-15',
'ca_it': 'ca_IT.ISO8859-1',
'ca_it.iso88591': 'ca_IT.ISO8859-1',
'ca_it.iso885915': 'ca_IT.ISO8859-15',
'ca_it.iso885915@euro': 'ca_IT.ISO8859-15',
'ca_it.utf8@euro': 'ca_IT.UTF-8',
'ca_it@euro': 'ca_IT.ISO8859-15',
'catalan': 'ca_ES.ISO8859-1',
'ce_ru': 'ce_RU.UTF-8',
'cextend': 'en_US.ISO8859-1',
'cextend.en': 'en_US.ISO8859-1',
'chinese-s': 'zh_CN.eucCN',
'chinese-t': 'zh_TW.eucTW',
'chr_us': 'chr_US.UTF-8',
'ckb_iq': 'ckb_IQ.UTF-8',
'cmn_tw': 'cmn_TW.UTF-8',
'crh_ua': 'crh_UA.UTF-8',
'croatian': 'hr_HR.ISO8859-2',
'cs': 'cs_CZ.ISO8859-2',
'cs_cs': 'cs_CZ.ISO8859-2',
'cs_cs.iso88592': 'cs_CZ.ISO8859-2',
'cs_cz': 'cs_CZ.ISO8859-2',
'cs_cz.iso88592': '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',
'cy_gb.iso88591': 'cy_GB.ISO8859-1',
'cy_gb.iso885914': 'cy_GB.ISO8859-14',
'cy_gb.iso885915': 'cy_GB.ISO8859-15',
'cy_gb@euro': 'cy_GB.ISO8859-15',
'cz': 'cs_CZ.ISO8859-2',
'cz_cz': 'cs_CZ.ISO8859-2',
'czech': 'cs_CZ.ISO8859-2',
'da': 'da_DK.ISO8859-1',
'da.iso885915': 'da_DK.ISO8859-15',
'da_dk': 'da_DK.ISO8859-1',
'da_dk.88591': 'da_DK.ISO8859-1',
'da_dk.885915': 'da_DK.ISO8859-15',
'da_dk.iso88591': 'da_DK.ISO8859-1',
'da_dk.iso885915': 'da_DK.ISO8859-15',
'da_dk@euro': 'da_DK.ISO8859-15',
'danish': 'da_DK.ISO8859-1',
'danish.iso88591': 'da_DK.ISO8859-1',
'dansk': 'da_DK.ISO8859-1',
'de': 'de_DE.ISO8859-1',
'de.iso885915': 'de_DE.ISO8859-15',
'de_at': 'de_AT.ISO8859-1',
'de_at.iso88591': 'de_AT.ISO8859-1',
'de_at.iso885915': 'de_AT.ISO8859-15',
'de_at.iso885915@euro': 'de_AT.ISO8859-15',
'de_at.utf8@euro': 'de_AT.UTF-8',
'de_at@euro': 'de_AT.ISO8859-15',
'de_be': 'de_BE.ISO8859-1',
'de_be.iso88591': 'de_BE.ISO8859-1',
'de_be.iso885915': 'de_BE.ISO8859-15',
'de_be.iso885915@euro': 'de_BE.ISO8859-15',
'de_be.utf8@euro': 'de_BE.UTF-8',
'de_be@euro': 'de_BE.ISO8859-15',
'de_ch': 'de_CH.ISO8859-1',
'de_ch.iso88591': 'de_CH.ISO8859-1',
'de_ch.iso885915': 'de_CH.ISO8859-15',
'de_ch@euro': 'de_CH.ISO8859-15',
'de_de': 'de_DE.ISO8859-1',
'de_de.88591': 'de_DE.ISO8859-1',
'de_de.885915': 'de_DE.ISO8859-15',
'de_de.885915@euro': 'de_DE.ISO8859-15',
'de_de.iso88591': 'de_DE.ISO8859-1',
'de_de.iso885915': 'de_DE.ISO8859-15',
'de_de.iso885915@euro': 'de_DE.ISO8859-15',
'de_de.utf8@euro': 'de_DE.UTF-8',
'de_de@euro': 'de_DE.ISO8859-15',
'de_it': 'de_IT.ISO8859-1',
'de_li.utf8': 'de_LI.UTF-8',
'de_lu': 'de_LU.ISO8859-1',
'de_lu.iso88591': 'de_LU.ISO8859-1',
'de_lu.iso885915': 'de_LU.ISO8859-15',
'de_lu.iso885915@euro': 'de_LU.ISO8859-15',
'de_lu.utf8@euro': 'de_LU.UTF-8',
'de_lu@euro': 'de_LU.ISO8859-15',
'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',
'ee_ee.iso88594': '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.iso88597': 'el_GR.ISO8859-7',
'el_gr@euro': 'el_GR.ISO8859-15',
'en': 'en_US.ISO8859-1',
'en.iso88591': 'en_US.ISO8859-1',
'en_ag': 'en_AG.UTF-8',
'en_au': 'en_AU.ISO8859-1',
'en_au.iso88591': 'en_AU.ISO8859-1',
'en_be': 'en_BE.ISO8859-1',
'en_be@euro': 'en_BE.ISO8859-15',
'en_bw': 'en_BW.ISO8859-1',
'en_bw.iso88591': 'en_BW.ISO8859-1',
'en_ca': 'en_CA.ISO8859-1',
'en_ca.iso88591': 'en_CA.ISO8859-1',
'en_dk': 'en_DK.ISO8859-1',
'en_dk.iso88591': 'en_DK.ISO8859-1',
'en_dk.iso885915': 'en_DK.ISO8859-15',
'en_dl.utf8': 'en_DL.UTF-8',
'en_gb': 'en_GB.ISO8859-1',
'en_gb.88591': 'en_GB.ISO8859-1',
'en_gb.iso88591': 'en_GB.ISO8859-1',
'en_gb.iso885915': 'en_GB.ISO8859-15',
'en_gb@euro': 'en_GB.ISO8859-15',
'en_hk': 'en_HK.ISO8859-1',
'en_hk.iso88591': 'en_HK.ISO8859-1',
'en_ie': 'en_IE.ISO8859-1',
'en_ie.iso88591': 'en_IE.ISO8859-1',
'en_ie.iso885915': 'en_IE.ISO8859-15',
'en_ie.iso885915@euro': 'en_IE.ISO8859-15',
'en_ie.utf8@euro': 'en_IE.UTF-8',
'en_ie@euro': 'en_IE.ISO8859-15',
'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_nz.iso88591': 'en_NZ.ISO8859-1',
'en_ph': 'en_PH.ISO8859-1',
'en_ph.iso88591': 'en_PH.ISO8859-1',
'en_sc.utf8': 'en_SC.UTF-8',
'en_sg': 'en_SG.ISO8859-1',
'en_sg.iso88591': 'en_SG.ISO8859-1',
'en_uk': 'en_GB.ISO8859-1',
'en_us': 'en_US.ISO8859-1',
'en_us.88591': 'en_US.ISO8859-1',
'en_us.885915': 'en_US.ISO8859-15',
'en_us.iso88591': 'en_US.ISO8859-1',
'en_us.iso885915': 'en_US.ISO8859-15',
'en_us.iso885915@euro': 'en_US.ISO8859-15',
'en_us@euro': 'en_US.ISO8859-15',
'en_us@euro@euro': 'en_US.ISO8859-15',
'en_za': 'en_ZA.ISO8859-1',
'en_za.88591': 'en_ZA.ISO8859-1',
'en_za.iso88591': 'en_ZA.ISO8859-1',
'en_za.iso885915': 'en_ZA.ISO8859-15',
'en_za@euro': 'en_ZA.ISO8859-15',
'en_zm': 'en_ZM.UTF-8',
'en_zw': 'en_ZW.ISO8859-1',
'en_zw.iso88591': 'en_ZW.ISO8859-1',
'en_zw.utf8': 'en_ZS.UTF-8',
'eng_gb': 'en_GB.ISO8859-1',
'eng_gb.8859': 'en_GB.ISO8859-1',
'english': 'en_EN.ISO8859-1',
'english.iso88591': 'en_US.ISO8859-1',
'english_uk': 'en_GB.ISO8859-1',
'english_uk.8859': 'en_GB.ISO8859-1',
'english_united-states': 'en_US.ISO8859-1',
'english_united-states.437': 'C',
'english_us': 'en_US.ISO8859-1',
'english_us.8859': 'en_US.ISO8859-1',
'english_us.ascii': 'en_US.ISO8859-1',
'eo': 'eo_XX.ISO8859-3',
'eo.utf8': 'eo.UTF-8',
'eo_eo': 'eo_EO.ISO8859-3',
'eo_eo.iso88593': 'eo_EO.ISO8859-3',
'eo_us.utf8': 'eo_US.UTF-8',
'eo_xx': 'eo_XX.ISO8859-3',
'eo_xx.iso88593': 'eo_XX.ISO8859-3',
'es': 'es_ES.ISO8859-1',
'es_ar': 'es_AR.ISO8859-1',
'es_ar.iso88591': 'es_AR.ISO8859-1',
'es_bo': 'es_BO.ISO8859-1',
'es_bo.iso88591': 'es_BO.ISO8859-1',
'es_cl': 'es_CL.ISO8859-1',
'es_cl.iso88591': 'es_CL.ISO8859-1',
'es_co': 'es_CO.ISO8859-1',
'es_co.iso88591': 'es_CO.ISO8859-1',
'es_cr': 'es_CR.ISO8859-1',
'es_cr.iso88591': 'es_CR.ISO8859-1',
'es_cu': 'es_CU.UTF-8',
'es_do': 'es_DO.ISO8859-1',
'es_do.iso88591': 'es_DO.ISO8859-1',
'es_ec': 'es_EC.ISO8859-1',
'es_ec.iso88591': 'es_EC.ISO8859-1',
'es_es': 'es_ES.ISO8859-1',
'es_es.88591': 'es_ES.ISO8859-1',
'es_es.iso88591': 'es_ES.ISO8859-1',
'es_es.iso885915': 'es_ES.ISO8859-15',
'es_es.iso885915@euro': 'es_ES.ISO8859-15',
'es_es.utf8@euro': 'es_ES.UTF-8',
'es_es@euro': 'es_ES.ISO8859-15',
'es_gt': 'es_GT.ISO8859-1',
'es_gt.iso88591': 'es_GT.ISO8859-1',
'es_hn': 'es_HN.ISO8859-1',
'es_hn.iso88591': 'es_HN.ISO8859-1',
'es_mx': 'es_MX.ISO8859-1',
'es_mx.iso88591': 'es_MX.ISO8859-1',
'es_ni': 'es_NI.ISO8859-1',
'es_ni.iso88591': 'es_NI.ISO8859-1',
'es_pa': 'es_PA.ISO8859-1',
'es_pa.iso88591': 'es_PA.ISO8859-1',
'es_pa.iso885915': 'es_PA.ISO8859-15',
'es_pa@euro': 'es_PA.ISO8859-15',
'es_pe': 'es_PE.ISO8859-1',
'es_pe.iso88591': 'es_PE.ISO8859-1',
'es_pe.iso885915': 'es_PE.ISO8859-15',
'es_pe@euro': 'es_PE.ISO8859-15',
'es_pr': 'es_PR.ISO8859-1',
'es_pr.iso88591': 'es_PR.ISO8859-1',
'es_py': 'es_PY.ISO8859-1',
'es_py.iso88591': 'es_PY.ISO8859-1',
'es_py.iso885915': 'es_PY.ISO8859-15',
'es_py@euro': 'es_PY.ISO8859-15',
'es_sv': 'es_SV.ISO8859-1',
'es_sv.iso88591': 'es_SV.ISO8859-1',
'es_sv.iso885915': 'es_SV.ISO8859-15',
'es_sv@euro': 'es_SV.ISO8859-15',
'es_us': 'es_US.ISO8859-1',
'es_us.iso88591': 'es_US.ISO8859-1',
'es_uy': 'es_UY.ISO8859-1',
'es_uy.iso88591': 'es_UY.ISO8859-1',
'es_uy.iso885915': 'es_UY.ISO8859-15',
'es_uy@euro': 'es_UY.ISO8859-15',
'es_ve': 'es_VE.ISO8859-1',
'es_ve.iso88591': 'es_VE.ISO8859-1',
'es_ve.iso885915': 'es_VE.ISO8859-15',
'es_ve@euro': 'es_VE.ISO8859-15',
'estonian': 'et_EE.ISO8859-1',
'et': 'et_EE.ISO8859-15',
'et_ee': 'et_EE.ISO8859-15',
'et_ee.iso88591': 'et_EE.ISO8859-1',
'et_ee.iso885913': 'et_EE.ISO8859-13',
'et_ee.iso885915': 'et_EE.ISO8859-15',
'et_ee.iso88594': 'et_EE.ISO8859-4',
'et_ee@euro': 'et_EE.ISO8859-15',
'eu': 'eu_ES.ISO8859-1',
'eu_es': 'eu_ES.ISO8859-1',
'eu_es.iso88591': 'eu_ES.ISO8859-1',
'eu_es.iso885915': 'eu_ES.ISO8859-15',
'eu_es.iso885915@euro': 'eu_ES.ISO8859-15',
'eu_es.utf8@euro': 'eu_ES.UTF-8',
'eu_es@euro': 'eu_ES.ISO8859-15',
'eu_fr': 'eu_FR.ISO8859-1',
'fa': 'fa_IR.UTF-8',
'fa_ir': 'fa_IR.UTF-8',
'fa_ir.isiri3342': 'fa_IR.ISIRI-3342',
'ff_sn': 'ff_SN.UTF-8',
'fi': 'fi_FI.ISO8859-15',
'fi.iso885915': 'fi_FI.ISO8859-15',
'fi_fi': 'fi_FI.ISO8859-15',
'fi_fi.88591': 'fi_FI.ISO8859-1',
'fi_fi.iso88591': 'fi_FI.ISO8859-1',
'fi_fi.iso885915': 'fi_FI.ISO8859-15',
'fi_fi.iso885915@euro': 'fi_FI.ISO8859-15',
'fi_fi.utf8@euro': 'fi_FI.UTF-8',
'fi_fi@euro': 'fi_FI.ISO8859-15',
'fil_ph': 'fil_PH.UTF-8',
'finnish': 'fi_FI.ISO8859-1',
'finnish.iso88591': 'fi_FI.ISO8859-1',
'fo': 'fo_FO.ISO8859-1',
'fo_fo': 'fo_FO.ISO8859-1',
'fo_fo.iso88591': 'fo_FO.ISO8859-1',
'fo_fo.iso885915': 'fo_FO.ISO8859-15',
'fo_fo@euro': 'fo_FO.ISO8859-15',
'fr': 'fr_FR.ISO8859-1',
'fr.iso885915': 'fr_FR.ISO8859-15',
'fr_be': 'fr_BE.ISO8859-1',
'fr_be.88591': 'fr_BE.ISO8859-1',
'fr_be.iso88591': 'fr_BE.ISO8859-1',
'fr_be.iso885915': 'fr_BE.ISO8859-15',
'fr_be.iso885915@euro': 'fr_BE.ISO8859-15',
'fr_be.utf8@euro': 'fr_BE.UTF-8',
'fr_be@euro': 'fr_BE.ISO8859-15',
'fr_ca': 'fr_CA.ISO8859-1',
'fr_ca.88591': 'fr_CA.ISO8859-1',
'fr_ca.iso88591': 'fr_CA.ISO8859-1',
'fr_ca.iso885915': 'fr_CA.ISO8859-15',
'fr_ca@euro': 'fr_CA.ISO8859-15',
'fr_ch': 'fr_CH.ISO8859-1',
'fr_ch.88591': 'fr_CH.ISO8859-1',
'fr_ch.iso88591': 'fr_CH.ISO8859-1',
'fr_ch.iso885915': 'fr_CH.ISO8859-15',
'fr_ch@euro': 'fr_CH.ISO8859-15',
'fr_fr': 'fr_FR.ISO8859-1',
'fr_fr.88591': 'fr_FR.ISO8859-1',
'fr_fr.iso88591': 'fr_FR.ISO8859-1',
'fr_fr.iso885915': 'fr_FR.ISO8859-15',
'fr_fr.iso885915@euro': 'fr_FR.ISO8859-15',
'fr_fr.utf8@euro': 'fr_FR.UTF-8',
'fr_fr@euro': 'fr_FR.ISO8859-15',
'fr_lu': 'fr_LU.ISO8859-1',
'fr_lu.88591': 'fr_LU.ISO8859-1',
'fr_lu.iso88591': 'fr_LU.ISO8859-1',
'fr_lu.iso885915': 'fr_LU.ISO8859-15',
'fr_lu.iso885915@euro': 'fr_LU.ISO8859-15',
'fr_lu.utf8@euro': 'fr_LU.UTF-8',
'fr_lu@euro': 'fr_LU.ISO8859-15',
'fran\xe7ais': 'fr_FR.ISO8859-1',
'fre_fr': 'fr_FR.ISO8859-1',
'fre_fr.8859': 'fr_FR.ISO8859-1',
'french': 'fr_FR.ISO8859-1',
'french.iso88591': 'fr_CH.ISO8859-1',
'french_france': 'fr_FR.ISO8859-1',
'french_france.8859': 'fr_FR.ISO8859-1',
'fur_it': 'fur_IT.UTF-8',
'fy_de': 'fy_DE.UTF-8',
'fy_nl': 'fy_NL.UTF-8',
'ga': 'ga_IE.ISO8859-1',
'ga_ie': 'ga_IE.ISO8859-1',
'ga_ie.iso88591': 'ga_IE.ISO8859-1',
'ga_ie.iso885914': 'ga_IE.ISO8859-14',
'ga_ie.iso885915': 'ga_IE.ISO8859-15',
'ga_ie.iso885915@euro': 'ga_IE.ISO8859-15',
'ga_ie.utf8@euro': 'ga_IE.UTF-8',
'ga_ie@euro': 'ga_IE.ISO8859-15',
'galego': 'gl_ES.ISO8859-1',
'galician': 'gl_ES.ISO8859-1',
'gd': 'gd_GB.ISO8859-1',
'gd_gb': 'gd_GB.ISO8859-1',
'gd_gb.iso88591': 'gd_GB.ISO8859-1',
'gd_gb.iso885914': 'gd_GB.ISO8859-14',
'gd_gb.iso885915': 'gd_GB.ISO8859-15',
'gd_gb@euro': 'gd_GB.ISO8859-15',
'ger_de': 'de_DE.ISO8859-1',
'ger_de.8859': 'de_DE.ISO8859-1',
'german': 'de_DE.ISO8859-1',
'german.iso88591': 'de_CH.ISO8859-1',
'german_germany': 'de_DE.ISO8859-1',
'german_germany.8859': 'de_DE.ISO8859-1',
'gez_er': 'gez_ER.UTF-8',
'gez_et': 'gez_ET.UTF-8',
'gl': 'gl_ES.ISO8859-1',
'gl_es': 'gl_ES.ISO8859-1',
'gl_es.iso88591': 'gl_ES.ISO8859-1',
'gl_es.iso885915': 'gl_ES.ISO8859-15',
'gl_es.iso885915@euro': 'gl_ES.ISO8859-15',
'gl_es.utf8@euro': 'gl_ES.UTF-8',
'gl_es@euro': 'gl_ES.ISO8859-15',
'greek': 'el_GR.ISO8859-7',
'greek.iso88597': 'el_GR.ISO8859-7',
'gu_in': 'gu_IN.UTF-8',
'gv': 'gv_GB.ISO8859-1',
'gv_gb': 'gv_GB.ISO8859-1',
'gv_gb.iso88591': 'gv_GB.ISO8859-1',
'gv_gb.iso885914': 'gv_GB.ISO8859-14',
'gv_gb.iso885915': 'gv_GB.ISO8859-15',
'gv_gb@euro': 'gv_GB.ISO8859-15',
'ha_ng': 'ha_NG.UTF-8',
'hak_tw': 'hak_TW.UTF-8',
'he': 'he_IL.ISO8859-8',
'he_il': 'he_IL.ISO8859-8',
'he_il.cp1255': 'he_IL.CP1255',
'he_il.iso88598': 'he_IL.ISO8859-8',
'he_il.microsoftcp1255': 'he_IL.CP1255',
'hebrew': 'he_IL.ISO8859-8',
'hebrew.iso88598': 'he_IL.ISO8859-8',
'hi': 'hi_IN.ISCII-DEV',
'hi_in': 'hi_IN.ISCII-DEV',
'hi_in.isciidev': 'hi_IN.ISCII-DEV',
'hif_fj': 'hif_FJ.UTF-8',
'hne': 'hne_IN.UTF-8',
'hne_in': 'hne_IN.UTF-8',
'hr': 'hr_HR.ISO8859-2',
'hr_hr': 'hr_HR.ISO8859-2',
'hr_hr.iso88592': 'hr_HR.ISO8859-2',
'hrvatski': 'hr_HR.ISO8859-2',
'hsb_de': 'hsb_DE.ISO8859-2',
'ht_ht': 'ht_HT.UTF-8',
'hu': 'hu_HU.ISO8859-2',
'hu_hu': 'hu_HU.ISO8859-2',
'hu_hu.iso88592': 'hu_HU.ISO8859-2',
'hungarian': 'hu_HU.ISO8859-2',
'hy_am': 'hy_AM.UTF-8',
'hy_am.armscii8': 'hy_AM.ARMSCII_8',
'ia': 'ia.UTF-8',
'ia_fr': 'ia_FR.UTF-8',
'icelandic': 'is_IS.ISO8859-1',
'icelandic.iso88591': 'is_IS.ISO8859-1',
'id': 'id_ID.ISO8859-1',
'id_id': 'id_ID.ISO8859-1',
'ig_ng': 'ig_NG.UTF-8',
'ik_ca': 'ik_CA.UTF-8',
'in': 'id_ID.ISO8859-1',
'in_id': 'id_ID.ISO8859-1',
'is': 'is_IS.ISO8859-1',
'is_is': 'is_IS.ISO8859-1',
'is_is.iso88591': 'is_IS.ISO8859-1',
'is_is.iso885915': 'is_IS.ISO8859-15',
'is_is@euro': 'is_IS.ISO8859-15',
'iso-8859-1': 'en_US.ISO8859-1',
'iso-8859-15': 'en_US.ISO8859-15',
'iso8859-1': 'en_US.ISO8859-1',
'iso8859-15': 'en_US.ISO8859-15',
'iso_8859_1': 'en_US.ISO8859-1',
'iso_8859_15': 'en_US.ISO8859-15',
'it': 'it_IT.ISO8859-1',
'it.iso885915': 'it_IT.ISO8859-15',
'it_ch': 'it_CH.ISO8859-1',
'it_ch.iso88591': 'it_CH.ISO8859-1',
'it_ch.iso885915': 'it_CH.ISO8859-15',
'it_ch@euro': 'it_CH.ISO8859-15',
'it_it': 'it_IT.ISO8859-1',
'it_it.88591': 'it_IT.ISO8859-1',
'it_it.iso88591': 'it_IT.ISO8859-1',
'it_it.iso885915': 'it_IT.ISO8859-15',
'it_it.iso885915@euro': 'it_IT.ISO8859-15',
'it_it.utf8@euro': 'it_IT.UTF-8',
'it_it@euro': 'it_IT.ISO8859-15',
'italian': 'it_IT.ISO8859-1',
'italian.iso88591': 'it_IT.ISO8859-1',
'iu': 'iu_CA.NUNACOM-8',
'iu_ca': 'iu_CA.NUNACOM-8',
'iu_ca.nunacom8': 'iu_CA.NUNACOM-8',
'iw': 'he_IL.ISO8859-8',
'iw_il': 'he_IL.ISO8859-8',
'iw_il.iso88598': 'he_IL.ISO8859-8',
'iw_il.utf8': 'iw_IL.UTF-8',
'ja': 'ja_JP.eucJP',
'ja.jis': 'ja_JP.JIS7',
'ja.sjis': 'ja_JP.SJIS',
'ja_jp': 'ja_JP.eucJP',
'ja_jp.ajec': 'ja_JP.eucJP',
'ja_jp.euc': 'ja_JP.eucJP',
'ja_jp.eucjp': 'ja_JP.eucJP',
'ja_jp.iso-2022-jp': 'ja_JP.JIS7',
'ja_jp.iso2022jp': 'ja_JP.JIS7',
'ja_jp.jis': 'ja_JP.JIS7',
'ja_jp.jis7': 'ja_JP.JIS7',
'ja_jp.mscode': 'ja_JP.SJIS',
'ja_jp.pck': 'ja_JP.SJIS',
'ja_jp.sjis': 'ja_JP.SJIS',
'ja_jp.ujis': 'ja_JP.eucJP',
'japan': 'ja_JP.eucJP',
'japanese': 'ja_JP.eucJP',
'japanese-euc': 'ja_JP.eucJP',
'japanese.euc': 'ja_JP.eucJP',
'japanese.sjis': 'ja_JP.SJIS',
'jp_jp': 'ja_JP.eucJP',
'ka': 'ka_GE.GEORGIAN-ACADEMY',
'ka_ge': 'ka_GE.GEORGIAN-ACADEMY',
'ka_ge.georgianacademy': 'ka_GE.GEORGIAN-ACADEMY',
'ka_ge.georgianps': 'ka_GE.GEORGIAN-PS',
'ka_ge.georgianrs': 'ka_GE.GEORGIAN-ACADEMY',
'kab_dz': 'kab_DZ.UTF-8',
'kk_kz': 'kk_KZ.ptcp154',
'kl': 'kl_GL.ISO8859-1',
'kl_gl': 'kl_GL.ISO8859-1',
'kl_gl.iso88591': 'kl_GL.ISO8859-1',
'kl_gl.iso885915': 'kl_GL.ISO8859-15',
'kl_gl@euro': 'kl_GL.ISO8859-15',
'km_kh': 'km_KH.UTF-8',
'kn': 'kn_IN.UTF-8',
'kn_in': 'kn_IN.UTF-8',
'ko': 'ko_KR.eucKR',
'ko_kr': 'ko_KR.eucKR',
'ko_kr.euc': 'ko_KR.eucKR',
'ko_kr.euckr': 'ko_KR.eucKR',
'kok_in': 'kok_IN.UTF-8',
'korean': 'ko_KR.eucKR',
'korean.euc': 'ko_KR.eucKR',
'ks': 'ks_IN.UTF-8',
'ks_in': 'ks_IN.UTF-8',
'ks_in.utf8@devanagari': 'ks_IN.UTF-8@devanagari',
'ks_in@devanagari': 'ks_IN.UTF-8@devanagari',
'ks_in@devanagari.utf8': 'ks_IN.UTF-8@devanagari',
'ku_tr': 'ku_TR.ISO8859-9',
'kw': 'kw_GB.ISO8859-1',
'kw_gb': 'kw_GB.ISO8859-1',
'kw_gb.iso88591': 'kw_GB.ISO8859-1',
'kw_gb.iso885914': 'kw_GB.ISO8859-14',
'kw_gb.iso885915': 'kw_GB.ISO8859-15',
'kw_gb@euro': 'kw_GB.ISO8859-15',
'ky': 'ky_KG.UTF-8',
'ky_kg': 'ky_KG.UTF-8',
'lb_lu': 'lb_LU.UTF-8',
'lg_ug': 'lg_UG.ISO8859-10',
'li_be': 'li_BE.UTF-8',
'li_nl': 'li_NL.UTF-8',
'lij_it': 'lij_IT.UTF-8',
'lithuanian': 'lt_LT.ISO8859-13',
'ln_cd': 'ln_CD.UTF-8',
'lo': 'lo_LA.MULELAO-1',
'lo_la': 'lo_LA.MULELAO-1',
'lo_la.cp1133': 'lo_LA.IBM-CP1133',
'lo_la.ibmcp1133': 'lo_LA.IBM-CP1133',
'lo_la.mulelao1': 'lo_LA.MULELAO-1',
'lt': 'lt_LT.ISO8859-13',
'lt_lt': 'lt_LT.ISO8859-13',
'lt_lt.iso885913': 'lt_LT.ISO8859-13',
'lt_lt.iso88594': 'lt_LT.ISO8859-4',
'lv': 'lv_LV.ISO8859-13',
'lv_lv': 'lv_LV.ISO8859-13',
'lv_lv.iso885913': 'lv_LV.ISO8859-13',
'lv_lv.iso88594': 'lv_LV.ISO8859-4',
'lzh_tw': 'lzh_TW.UTF-8',
'mag_in': 'mag_IN.UTF-8',
'mai': 'mai_IN.UTF-8',
'mai_in': 'mai_IN.UTF-8',
'mai_np': 'mai_NP.UTF-8',
'mfe_mu': 'mfe_MU.UTF-8',
'mg_mg': 'mg_MG.ISO8859-15',
'mhr_ru': 'mhr_RU.UTF-8',
'mi': 'mi_NZ.ISO8859-1',
'mi_nz': 'mi_NZ.ISO8859-1',
'mi_nz.iso88591': 'mi_NZ.ISO8859-1',
'miq_ni': 'miq_NI.UTF-8',
'mjw_in': 'mjw_IN.UTF-8',
'mk': 'mk_MK.ISO8859-5',
'mk_mk': 'mk_MK.ISO8859-5',
'mk_mk.cp1251': 'mk_MK.CP1251',
'mk_mk.iso88595': 'mk_MK.ISO8859-5',
'mk_mk.microsoftcp1251': 'mk_MK.CP1251',
'ml': 'ml_IN.UTF-8',
'ml_in': 'ml_IN.UTF-8',
'mn_mn': 'mn_MN.UTF-8',
'mni_in': 'mni_IN.UTF-8',
'mr': 'mr_IN.UTF-8',
'mr_in': 'mr_IN.UTF-8',
'ms': 'ms_MY.ISO8859-1',
'ms_my': 'ms_MY.ISO8859-1',
'ms_my.iso88591': 'ms_MY.ISO8859-1',
'mt': 'mt_MT.ISO8859-3',
'mt_mt': 'mt_MT.ISO8859-3',
'mt_mt.iso88593': 'mt_MT.ISO8859-3',
'my_mm': 'my_MM.UTF-8',
'nan_tw': 'nan_TW.UTF-8',
'nb': 'nb_NO.ISO8859-1',
'nb_no': 'nb_NO.ISO8859-1',
'nb_no.88591': 'nb_NO.ISO8859-1',
'nb_no.iso88591': 'nb_NO.ISO8859-1',
'nb_no.iso885915': 'nb_NO.ISO8859-15',
'nb_no@euro': 'nb_NO.ISO8859-15',
'nds_de': 'nds_DE.UTF-8',
'nds_nl': 'nds_NL.UTF-8',
'ne_np': 'ne_NP.UTF-8',
'nhn_mx': 'nhn_MX.UTF-8',
'niu_nu': 'niu_NU.UTF-8',
'niu_nz': 'niu_NZ.UTF-8',
'nl': 'nl_NL.ISO8859-1',
'nl.iso885915': 'nl_NL.ISO8859-15',
'nl_aw': 'nl_AW.UTF-8',
'nl_be': 'nl_BE.ISO8859-1',
'nl_be.88591': 'nl_BE.ISO8859-1',
'nl_be.iso88591': 'nl_BE.ISO8859-1',
'nl_be.iso885915': 'nl_BE.ISO8859-15',
'nl_be.iso885915@euro': 'nl_BE.ISO8859-15',
'nl_be.utf8@euro': 'nl_BE.UTF-8',
'nl_be@euro': 'nl_BE.ISO8859-15',
'nl_nl': 'nl_NL.ISO8859-1',
'nl_nl.88591': 'nl_NL.ISO8859-1',
'nl_nl.iso88591': 'nl_NL.ISO8859-1',
'nl_nl.iso885915': 'nl_NL.ISO8859-15',
'nl_nl.iso885915@euro': 'nl_NL.ISO8859-15',
'nl_nl.utf8@euro': 'nl_NL.UTF-8',
'nl_nl@euro': 'nl_NL.ISO8859-15',
'nn': 'nn_NO.ISO8859-1',
'nn_no': 'nn_NO.ISO8859-1',
'nn_no.88591': 'nn_NO.ISO8859-1',
'nn_no.iso88591': 'nn_NO.ISO8859-1',
'nn_no.iso885915': 'nn_NO.ISO8859-15',
'nn_no@euro': 'nn_NO.ISO8859-15',
'no': 'no_NO.ISO8859-1',
'no@nynorsk': 'ny_NO.ISO8859-1',
'no_no': 'no_NO.ISO8859-1',
'no_no.88591': 'no_NO.ISO8859-1',
'no_no.iso88591': 'no_NO.ISO8859-1',
'no_no.iso885915': 'no_NO.ISO8859-15',
'no_no.iso88591@bokmal': 'no_NO.ISO8859-1',
'no_no.iso88591@nynorsk': 'no_NO.ISO8859-1',
'no_no@euro': 'no_NO.ISO8859-15',
'norwegian': 'no_NO.ISO8859-1',
'norwegian.iso88591': 'no_NO.ISO8859-1',
'nr': 'nr_ZA.ISO8859-1',
'nr_za': 'nr_ZA.ISO8859-1',
'nr_za.iso88591': 'nr_ZA.ISO8859-1',
'nso': 'nso_ZA.ISO8859-15',
'nso_za': 'nso_ZA.ISO8859-15',
'nso_za.iso885915': 'nso_ZA.ISO8859-15',
'ny': 'ny_NO.ISO8859-1',
'ny_no': 'ny_NO.ISO8859-1',
'ny_no.88591': 'ny_NO.ISO8859-1',
'ny_no.iso88591': 'ny_NO.ISO8859-1',
'ny_no.iso885915': 'ny_NO.ISO8859-15',
'ny_no@euro': 'ny_NO.ISO8859-15',
'nynorsk': 'nn_NO.ISO8859-1',
'oc': 'oc_FR.ISO8859-1',
'oc_fr': 'oc_FR.ISO8859-1',
'oc_fr.iso88591': 'oc_FR.ISO8859-1',
'oc_fr.iso885915': 'oc_FR.ISO8859-15',
'oc_fr@euro': 'oc_FR.ISO8859-15',
'om_et': 'om_ET.UTF-8',
'om_ke': 'om_KE.ISO8859-1',
'or': 'or_IN.UTF-8',
'or_in': 'or_IN.UTF-8',
'os_ru': 'os_RU.UTF-8',
'pa': 'pa_IN.UTF-8',
'pa_in': 'pa_IN.UTF-8',
'pa_pk': 'pa_PK.UTF-8',
'pap_an': 'pap_AN.UTF-8',
'pap_aw': 'pap_AW.UTF-8',
'pap_cw': 'pap_CW.UTF-8',
'pd': 'pd_US.ISO8859-1',
'pd_de': 'pd_DE.ISO8859-1',
'pd_de.iso88591': 'pd_DE.ISO8859-1',
'pd_de.iso885915': 'pd_DE.ISO8859-15',
'pd_de@euro': 'pd_DE.ISO8859-15',
'pd_us': 'pd_US.ISO8859-1',
'pd_us.iso88591': 'pd_US.ISO8859-1',
'pd_us.iso885915': 'pd_US.ISO8859-15',
'pd_us@euro': 'pd_US.ISO8859-15',
'ph': 'ph_PH.ISO8859-1',
'ph_ph': 'ph_PH.ISO8859-1',
'ph_ph.iso88591': 'ph_PH.ISO8859-1',
'pl': 'pl_PL.ISO8859-2',
'pl_pl': 'pl_PL.ISO8859-2',
'pl_pl.iso88592': 'pl_PL.ISO8859-2',
'polish': 'pl_PL.ISO8859-2',
'portuguese': 'pt_PT.ISO8859-1',
'portuguese.iso88591': 'pt_PT.ISO8859-1',
'portuguese_brazil': 'pt_BR.ISO8859-1',
'portuguese_brazil.8859': 'pt_BR.ISO8859-1',
'posix': 'C',
'posix-utf2': 'C',
'pp': 'pp_AN.ISO8859-1',
'pp_an': 'pp_AN.ISO8859-1',
'pp_an.iso88591': 'pp_AN.ISO8859-1',
'ps_af': 'ps_AF.UTF-8',
'pt': 'pt_PT.ISO8859-1',
'pt.iso885915': 'pt_PT.ISO8859-15',
'pt_br': 'pt_BR.ISO8859-1',
'pt_br.88591': 'pt_BR.ISO8859-1',
'pt_br.iso88591': 'pt_BR.ISO8859-1',
'pt_br.iso885915': 'pt_BR.ISO8859-15',
'pt_br@euro': 'pt_BR.ISO8859-15',
'pt_pt': 'pt_PT.ISO8859-1',
'pt_pt.88591': 'pt_PT.ISO8859-1',
'pt_pt.iso88591': 'pt_PT.ISO8859-1',
'pt_pt.iso885915': 'pt_PT.ISO8859-15',
'pt_pt.iso885915@euro': 'pt_PT.ISO8859-15',
'pt_pt.utf8@euro': 'pt_PT.UTF-8',
'pt_pt@euro': 'pt_PT.ISO8859-15',
'quz_pe': 'quz_PE.UTF-8',
'raj_in': 'raj_IN.UTF-8',
'ro': 'ro_RO.ISO8859-2',
'ro_ro': 'ro_RO.ISO8859-2',
'ro_ro.iso88592': 'ro_RO.ISO8859-2',
'romanian': 'ro_RO.ISO8859-2',
'ru': 'ru_RU.UTF-8',
'ru.koi8r': 'ru_RU.KOI8-R',
'ru_ru': 'ru_RU.UTF-8',
'ru_ru.cp1251': 'ru_RU.CP1251',
'ru_ru.iso88595': 'ru_RU.ISO8859-5',
'ru_ru.koi8r': 'ru_RU.KOI8-R',
'ru_ru.microsoftcp1251': 'ru_RU.CP1251',
'ru_ua': 'ru_UA.KOI8-U',
'ru_ua.cp1251': 'ru_UA.CP1251',
'ru_ua.koi8u': 'ru_UA.KOI8-U',
'ru_ua.microsoftcp1251': 'ru_UA.CP1251',
'rumanian': 'ro_RO.ISO8859-2',
'russian': 'ru_RU.KOI8-R',
'rw': 'rw_RW.ISO8859-1',
'rw_rw': 'rw_RW.ISO8859-1',
'rw_rw.iso88591': 'rw_RW.ISO8859-1',
'sa_in': 'sa_IN.UTF-8',
'sat_in': 'sat_IN.UTF-8',
'sc_it': 'sc_IT.UTF-8',
'sd': 'sd_IN.UTF-8',
'sd@devanagari': 'sd_IN.UTF-8@devanagari',
'sd_in': 'sd_IN.UTF-8',
'sd_in.utf8@devanagari': 'sd_IN.UTF-8@devanagari',
'sd_in@devanagari': 'sd_IN.UTF-8@devanagari',
'sd_in@devanagari.utf8': 'sd_IN.UTF-8@devanagari',
'sd_pk': 'sd_PK.UTF-8',
'se_no': 'se_NO.UTF-8',
'serbocroatian': 'sr_RS.UTF-8@latin',
'sgs_lt': 'sgs_LT.UTF-8',
'sh': 'sr_RS.UTF-8@latin',
'sh_ba.iso88592@bosnia': 'sr_CS.ISO8859-2',
'sh_hr': 'sh_HR.ISO8859-2',
'sh_hr.iso88592': 'hr_HR.ISO8859-2',
'sh_sp': 'sr_CS.ISO8859-2',
'sh_yu': 'sr_RS.UTF-8@latin',
'shn_mm': 'shn_MM.UTF-8',
'shs_ca': 'shs_CA.UTF-8',
'si': 'si_LK.UTF-8',
'si_lk': 'si_LK.UTF-8',
'sid_et': 'sid_ET.UTF-8',
'sinhala': 'si_LK.UTF-8',
'sk': 'sk_SK.ISO8859-2',
'sk_sk': 'sk_SK.ISO8859-2',
'sk_sk.iso88592': 'sk_SK.ISO8859-2',
'sl': 'sl_SI.ISO8859-2',
'sl_cs': 'sl_CS.ISO8859-2',
'sl_si': 'sl_SI.ISO8859-2',
'sl_si.iso88592': 'sl_SI.ISO8859-2',
'slovak': 'sk_SK.ISO8859-2',
'slovene': 'sl_SI.ISO8859-2',
'slovenian': 'sl_SI.ISO8859-2',
'sm_ws': 'sm_WS.UTF-8',
'so_dj': 'so_DJ.ISO8859-1',
'so_et': 'so_ET.UTF-8',
'so_ke': 'so_KE.ISO8859-1',
'so_so': 'so_SO.ISO8859-1',
'sp': 'sr_CS.ISO8859-5',
'sp_yu': 'sr_CS.ISO8859-5',
'spanish': 'es_ES.ISO8859-1',
'spanish.iso88591': 'es_ES.ISO8859-1',
'spanish_spain': 'es_ES.ISO8859-1',
'spanish_spain.8859': 'es_ES.ISO8859-1',
'sq': 'sq_AL.ISO8859-2',
'sq_al': 'sq_AL.ISO8859-2',
'sq_al.iso88592': 'sq_AL.ISO8859-2',
'sq_mk': 'sq_MK.UTF-8',
'sr': 'sr_RS.UTF-8',
'sr@cyrillic': 'sr_RS.UTF-8',
'sr@latin': 'sr_RS.UTF-8@latin',
'sr@latn': 'sr_CS.UTF-8@latin',
'sr_cs': 'sr_CS.UTF-8',
'sr_cs.iso88592': 'sr_CS.ISO8859-2',
'sr_cs.iso88592@latn': 'sr_CS.ISO8859-2',
'sr_cs.iso88595': 'sr_CS.ISO8859-5',
'sr_cs.utf8@latn': 'sr_CS.UTF-8@latin',
'sr_cs@latn': 'sr_CS.UTF-8@latin',
'sr_me': 'sr_ME.UTF-8',
'sr_rs': 'sr_RS.UTF-8',
'sr_rs.utf8@latn': 'sr_RS.UTF-8@latin',
'sr_rs@latin': 'sr_RS.UTF-8@latin',
'sr_rs@latn': 'sr_RS.UTF-8@latin',
'sr_sp': 'sr_CS.ISO8859-2',
'sr_yu': 'sr_RS.UTF-8@latin',
'sr_yu.cp1251@cyrillic': 'sr_CS.CP1251',
'sr_yu.iso88592': 'sr_CS.ISO8859-2',
'sr_yu.iso88595': 'sr_CS.ISO8859-5',
'sr_yu.iso88595@cyrillic': 'sr_CS.ISO8859-5',
'sr_yu.microsoftcp1251@cyrillic': 'sr_CS.CP1251',
'sr_yu.utf8': 'sr_RS.UTF-8',
'sr_yu.utf8@cyrillic': 'sr_RS.UTF-8',
'sr_yu@cyrillic': 'sr_RS.UTF-8',
'ss': 'ss_ZA.ISO8859-1',
'ss_za': 'ss_ZA.ISO8859-1',
'ss_za.iso88591': 'ss_ZA.ISO8859-1',
'st': 'st_ZA.ISO8859-1',
'st_za': 'st_ZA.ISO8859-1',
'st_za.iso88591': 'st_ZA.ISO8859-1',
'sv': 'sv_SE.ISO8859-1',
'sv.iso885915': 'sv_SE.ISO8859-15',
'sv_fi': 'sv_FI.ISO8859-1',
'sv_fi.iso88591': 'sv_FI.ISO8859-1',
'sv_fi.iso885915': 'sv_FI.ISO8859-15',
'sv_fi.iso885915@euro': 'sv_FI.ISO8859-15',
'sv_fi.utf8@euro': 'sv_FI.UTF-8',
'sv_fi@euro': 'sv_FI.ISO8859-15',
'sv_se': 'sv_SE.ISO8859-1',
'sv_se.88591': 'sv_SE.ISO8859-1',
'sv_se.iso88591': 'sv_SE.ISO8859-1',
'sv_se.iso885915': 'sv_SE.ISO8859-15',
'sv_se@euro': 'sv_SE.ISO8859-15',
'sw_ke': 'sw_KE.UTF-8',
'sw_tz': 'sw_TZ.UTF-8',
'swedish': 'sv_SE.ISO8859-1',
'swedish.iso88591': 'sv_SE.ISO8859-1',
'szl_pl': 'szl_PL.UTF-8',
'ta': 'ta_IN.TSCII-0',
'ta_in': 'ta_IN.TSCII-0',
'ta_in.tscii': 'ta_IN.TSCII-0',
'ta_in.tscii0': 'ta_IN.TSCII-0',
'ta_lk': 'ta_LK.UTF-8',
'tcy_in.utf8': 'tcy_IN.UTF-8',
'te': 'te_IN.UTF-8',
'te_in': 'te_IN.UTF-8',
'tg': 'tg_TJ.KOI8-C',
'tg_tj': 'tg_TJ.KOI8-C',
'tg_tj.koi8c': 'tg_TJ.KOI8-C',
'th': 'th_TH.ISO8859-11',
'th_th': 'th_TH.ISO8859-11',
'th_th.iso885911': 'th_TH.ISO8859-11',
'th_th.tactis': 'th_TH.TIS620',
'th_th.tis620': 'th_TH.TIS620',
'thai': 'th_TH.ISO8859-11',
'the_np': 'the_NP.UTF-8',
'ti_er': 'ti_ER.UTF-8',
'ti_et': 'ti_ET.UTF-8',
'tig_er': 'tig_ER.UTF-8',
'tk_tm': 'tk_TM.UTF-8',
'tl': 'tl_PH.ISO8859-1',
'tl_ph': 'tl_PH.ISO8859-1',
'tl_ph.iso88591': 'tl_PH.ISO8859-1',
'tn': 'tn_ZA.ISO8859-15',
'tn_za': 'tn_ZA.ISO8859-15',
'tn_za.iso885915': 'tn_ZA.ISO8859-15',
'to_to': 'to_TO.UTF-8',
'tpi_pg': 'tpi_PG.UTF-8',
'tr': 'tr_TR.ISO8859-9',
'tr_cy': 'tr_CY.ISO8859-9',
'tr_tr': 'tr_TR.ISO8859-9',
'tr_tr.iso88599': 'tr_TR.ISO8859-9',
'ts': 'ts_ZA.ISO8859-1',
'ts_za': 'ts_ZA.ISO8859-1',
'ts_za.iso88591': 'ts_ZA.ISO8859-1',
'tt': 'tt_RU.TATAR-CYR',
'tt_ru': 'tt_RU.TATAR-CYR',
'tt_ru.koi8c': 'tt_RU.KOI8-C',
'tt_ru.tatarcyr': 'tt_RU.TATAR-CYR',
'tt_ru@iqtelif': 'tt_RU.UTF-8@iqtelif',
'turkish': 'tr_TR.ISO8859-9',
'turkish.iso88599': 'tr_TR.ISO8859-9',
'ug_cn': 'ug_CN.UTF-8',
'uk': 'uk_UA.KOI8-U',
'uk_ua': 'uk_UA.KOI8-U',
'uk_ua.cp1251': 'uk_UA.CP1251',
'uk_ua.iso88595': 'uk_UA.ISO8859-5',
'uk_ua.koi8u': 'uk_UA.KOI8-U',
'uk_ua.microsoftcp1251': 'uk_UA.CP1251',
'univ': 'en_US.utf',
'universal': 'en_US.utf',
'universal.utf8@ucs4': 'en_US.UTF-8',
'unm_us': 'unm_US.UTF-8',
'ur': 'ur_PK.CP1256',
'ur_in': 'ur_IN.UTF-8',
'ur_pk': 'ur_PK.CP1256',
'ur_pk.cp1256': 'ur_PK.CP1256',
'ur_pk.microsoftcp1256': 'ur_PK.CP1256',
'uz': 'uz_UZ.UTF-8',
'uz_uz': 'uz_UZ.UTF-8',
'uz_uz.iso88591': 'uz_UZ.ISO8859-1',
'uz_uz.utf8@cyrillic': 'uz_UZ.UTF-8',
'uz_uz@cyrillic': 'uz_UZ.UTF-8',
've': 've_ZA.UTF-8',
've_za': 've_ZA.UTF-8',
'vi': 'vi_VN.TCVN',
'vi_vn': 'vi_VN.TCVN',
'vi_vn.tcvn': 'vi_VN.TCVN',
'vi_vn.tcvn5712': 'vi_VN.TCVN',
'vi_vn.viscii': 'vi_VN.VISCII',
'vi_vn.viscii111': 'vi_VN.VISCII',
'wa': 'wa_BE.ISO8859-1',
'wa_be': 'wa_BE.ISO8859-1',
'wa_be.iso88591': 'wa_BE.ISO8859-1',
'wa_be.iso885915': 'wa_BE.ISO8859-15',
'wa_be.iso885915@euro': 'wa_BE.ISO8859-15',
'wa_be@euro': 'wa_BE.ISO8859-15',
'wae_ch': 'wae_CH.UTF-8',
'wal_et': 'wal_ET.UTF-8',
'wo_sn': 'wo_SN.UTF-8',
'xh': 'xh_ZA.ISO8859-1',
'xh_za': 'xh_ZA.ISO8859-1',
'xh_za.iso88591': 'xh_ZA.ISO8859-1',
'yi': 'yi_US.CP1255',
'yi_us': 'yi_US.CP1255',
'yi_us.cp1255': 'yi_US.CP1255',
'yi_us.microsoftcp1255': 'yi_US.CP1255',
'yo_ng': 'yo_NG.UTF-8',
'yue_hk': 'yue_HK.UTF-8',
'yuw_pg': 'yuw_PG.UTF-8',
'zh': 'zh_CN.eucCN',
'zh_cn': 'zh_CN.gb2312',
'zh_cn.big5': 'zh_TW.big5',
'zh_cn.euc': 'zh_CN.eucCN',
'zh_cn.gb18030': 'zh_CN.gb18030',
'zh_cn.gb2312': 'zh_CN.gb2312',
'zh_cn.gbk': 'zh_CN.gbk',
'zh_hk': 'zh_HK.big5hkscs',
'zh_hk.big5': 'zh_HK.big5',
'zh_hk.big5hk': 'zh_HK.big5hkscs',
'zh_hk.big5hkscs': 'zh_HK.big5hkscs',
'zh_sg': 'zh_SG.GB2312',
'zh_sg.gbk': 'zh_SG.GBK',
'zh_tw': 'zh_TW.big5',
'zh_tw.big5': 'zh_TW.big5',
'zh_tw.euc': 'zh_TW.eucTW',
'zh_tw.euctw': 'zh_TW.eucTW',
'zu': 'zu_ZA.ISO8859-1',
'zu_za': 'zu_ZA.ISO8859-1',
'zu_za.iso88591': 'zu_ZA.ISO8859-1',
}
#
# This maps Windows language identifiers to locale strings.
#
# This list has been updated from
# http://msdn.microsoft.com/library/default.asp?url=/library/en-us/intl/nls_238z.asp
# to include every locale up to Windows Vista.
#
# NOTE: this mapping is incomplete. If your language is missing, please
# submit a bug report to the Python bug tracker at http://bugs.python.org/
# Make sure you include the missing language identifier and the suggested
# locale code.
#
windows_locale = {
0x0436: "af_ZA", # Afrikaans
0x041c: "sq_AL", # Albanian
0x0484: "gsw_FR",# Alsatian - France
0x045e: "am_ET", # Amharic - Ethiopia
0x0401: "ar_SA", # Arabic - Saudi Arabia
0x0801: "ar_IQ", # Arabic - Iraq
0x0c01: "ar_EG", # Arabic - Egypt
0x1001: "ar_LY", # Arabic - Libya
0x1401: "ar_DZ", # Arabic - Algeria
0x1801: "ar_MA", # Arabic - Morocco
0x1c01: "ar_TN", # Arabic - Tunisia
0x2001: "ar_OM", # Arabic - Oman
0x2401: "ar_YE", # Arabic - Yemen
0x2801: "ar_SY", # Arabic - Syria
0x2c01: "ar_JO", # Arabic - Jordan
0x3001: "ar_LB", # Arabic - Lebanon
0x3401: "ar_KW", # Arabic - Kuwait
0x3801: "ar_AE", # Arabic - United Arab Emirates
0x3c01: "ar_BH", # Arabic - Bahrain
0x4001: "ar_QA", # Arabic - Qatar
0x042b: "hy_AM", # Armenian
0x044d: "as_IN", # Assamese - India
0x042c: "az_AZ", # Azeri - Latin
0x082c: "az_AZ", # Azeri - Cyrillic
0x046d: "ba_RU", # Bashkir
0x042d: "eu_ES", # Basque - Russia
0x0423: "be_BY", # Belarusian
0x0445: "bn_IN", # Begali
0x201a: "bs_BA", # Bosnian - Cyrillic
0x141a: "bs_BA", # Bosnian - Latin
0x047e: "br_FR", # Breton - France
0x0402: "bg_BG", # Bulgarian
# 0x0455: "my_MM", # Burmese - Not supported
0x0403: "ca_ES", # Catalan
0x0004: "zh_CHS",# Chinese - Simplified
0x0404: "zh_TW", # Chinese - Taiwan
0x0804: "zh_CN", # Chinese - PRC
0x0c04: "zh_HK", # Chinese - Hong Kong S.A.R.
0x1004: "zh_SG", # Chinese - Singapore
0x1404: "zh_MO", # Chinese - Macao S.A.R.
0x7c04: "zh_CHT",# Chinese - Traditional
0x0483: "co_FR", # Corsican - France
0x041a: "hr_HR", # Croatian
0x101a: "hr_BA", # Croatian - Bosnia
0x0405: "cs_CZ", # Czech
0x0406: "da_DK", # Danish
0x048c: "gbz_AF",# Dari - Afghanistan
0x0465: "div_MV",# Divehi - Maldives
0x0413: "nl_NL", # Dutch - The Netherlands
0x0813: "nl_BE", # Dutch - Belgium
0x0409: "en_US", # English - United States
0x0809: "en_GB", # English - United Kingdom
0x0c09: "en_AU", # English - Australia
0x1009: "en_CA", # English - Canada
0x1409: "en_NZ", # English - New Zealand
0x1809: "en_IE", # English - Ireland
0x1c09: "en_ZA", # English - South Africa
0x2009: "en_JA", # English - Jamaica
0x2409: "en_CB", # English - Caribbean
0x2809: "en_BZ", # English - Belize
0x2c09: "en_TT", # English - Trinidad
0x3009: "en_ZW", # English - Zimbabwe
0x3409: "en_PH", # English - Philippines
0x4009: "en_IN", # English - India
0x4409: "en_MY", # English - Malaysia
0x4809: "en_IN", # English - Singapore
0x0425: "et_EE", # Estonian
0x0438: "fo_FO", # Faroese
0x0464: "fil_PH",# Filipino
0x040b: "fi_FI", # Finnish
0x040c: "fr_FR", # French - France
0x080c: "fr_BE", # French - Belgium
0x0c0c: "fr_CA", # French - Canada
0x100c: "fr_CH", # French - Switzerland
0x140c: "fr_LU", # French - Luxembourg
0x180c: "fr_MC", # French - Monaco
0x0462: "fy_NL", # Frisian - Netherlands
0x0456: "gl_ES", # Galician
0x0437: "ka_GE", # Georgian
0x0407: "de_DE", # German - Germany
0x0807: "de_CH", # German - Switzerland
0x0c07: "de_AT", # German - Austria
0x1007: "de_LU", # German - Luxembourg
0x1407: "de_LI", # German - Liechtenstein
0x0408: "el_GR", # Greek
0x046f: "kl_GL", # Greenlandic - Greenland
0x0447: "gu_IN", # Gujarati
0x0468: "ha_NG", # Hausa - Latin
0x040d: "he_IL", # Hebrew
0x0439: "hi_IN", # Hindi
0x040e: "hu_HU", # Hungarian
0x040f: "is_IS", # Icelandic
0x0421: "id_ID", # Indonesian
0x045d: "iu_CA", # Inuktitut - Syllabics
0x085d: "iu_CA", # Inuktitut - Latin
0x083c: "ga_IE", # Irish - Ireland
0x0410: "it_IT", # Italian - Italy
0x0810: "it_CH", # Italian - Switzerland
0x0411: "ja_JP", # Japanese
0x044b: "kn_IN", # Kannada - India
0x043f: "kk_KZ", # Kazakh
0x0453: "kh_KH", # Khmer - Cambodia
0x0486: "qut_GT",# K'iche - Guatemala
0x0487: "rw_RW", # Kinyarwanda - Rwanda
0x0457: "kok_IN",# Konkani
0x0412: "ko_KR", # Korean
0x0440: "ky_KG", # Kyrgyz
0x0454: "lo_LA", # Lao - Lao PDR
0x0426: "lv_LV", # Latvian
0x0427: "lt_LT", # Lithuanian
0x082e: "dsb_DE",# Lower Sorbian - Germany
0x046e: "lb_LU", # Luxembourgish
0x042f: "mk_MK", # FYROM Macedonian
0x043e: "ms_MY", # Malay - Malaysia
0x083e: "ms_BN", # Malay - Brunei Darussalam
0x044c: "ml_IN", # Malayalam - India
0x043a: "mt_MT", # Maltese
0x0481: "mi_NZ", # Maori
0x047a: "arn_CL",# Mapudungun
0x044e: "mr_IN", # Marathi
0x047c: "moh_CA",# Mohawk - Canada
0x0450: "mn_MN", # Mongolian - Cyrillic
0x0850: "mn_CN", # Mongolian - PRC
0x0461: "ne_NP", # Nepali
0x0414: "nb_NO", # Norwegian - Bokmal
0x0814: "nn_NO", # Norwegian - Nynorsk
0x0482: "oc_FR", # Occitan - France
0x0448: "or_IN", # Oriya - India
0x0463: "ps_AF", # Pashto - Afghanistan
0x0429: "fa_IR", # Persian
0x0415: "pl_PL", # Polish
0x0416: "pt_BR", # Portuguese - Brazil
0x0816: "pt_PT", # Portuguese - Portugal
0x0446: "pa_IN", # Punjabi
0x046b: "quz_BO",# Quechua (Bolivia)
0x086b: "quz_EC",# Quechua (Ecuador)
0x0c6b: "quz_PE",# Quechua (Peru)
0x0418: "ro_RO", # Romanian - Romania
0x0417: "rm_CH", # Romansh
0x0419: "ru_RU", # Russian
0x243b: "smn_FI",# Sami Finland
0x103b: "smj_NO",# Sami Norway
0x143b: "smj_SE",# Sami Sweden
0x043b: "se_NO", # Sami Northern Norway
0x083b: "se_SE", # Sami Northern Sweden
0x0c3b: "se_FI", # Sami Northern Finland
0x203b: "sms_FI",# Sami Skolt
0x183b: "sma_NO",# Sami Southern Norway
0x1c3b: "sma_SE",# Sami Southern Sweden
0x044f: "sa_IN", # Sanskrit
0x0c1a: "sr_SP", # Serbian - Cyrillic
0x1c1a: "sr_BA", # Serbian - Bosnia Cyrillic
0x081a: "sr_SP", # Serbian - Latin
0x181a: "sr_BA", # Serbian - Bosnia Latin
0x045b: "si_LK", # Sinhala - Sri Lanka
0x046c: "ns_ZA", # Northern Sotho
0x0432: "tn_ZA", # Setswana - Southern Africa
0x041b: "sk_SK", # Slovak
0x0424: "sl_SI", # Slovenian
0x040a: "es_ES", # Spanish - Spain
0x080a: "es_MX", # Spanish - Mexico
0x0c0a: "es_ES", # Spanish - Spain (Modern)
0x100a: "es_GT", # Spanish - Guatemala
0x140a: "es_CR", # Spanish - Costa Rica
0x180a: "es_PA", # Spanish - Panama
0x1c0a: "es_DO", # Spanish - Dominican Republic
0x200a: "es_VE", # Spanish - Venezuela
0x240a: "es_CO", # Spanish - Colombia
0x280a: "es_PE", # Spanish - Peru
0x2c0a: "es_AR", # Spanish - Argentina
0x300a: "es_EC", # Spanish - Ecuador
0x340a: "es_CL", # Spanish - Chile
0x380a: "es_UR", # Spanish - Uruguay
0x3c0a: "es_PY", # Spanish - Paraguay
0x400a: "es_BO", # Spanish - Bolivia
0x440a: "es_SV", # Spanish - El Salvador
0x480a: "es_HN", # Spanish - Honduras
0x4c0a: "es_NI", # Spanish - Nicaragua
0x500a: "es_PR", # Spanish - Puerto Rico
0x540a: "es_US", # Spanish - United States
# 0x0430: "", # Sutu - Not supported
0x0441: "sw_KE", # Swahili
0x041d: "sv_SE", # Swedish - Sweden
0x081d: "sv_FI", # Swedish - Finland
0x045a: "syr_SY",# Syriac
0x0428: "tg_TJ", # Tajik - Cyrillic
0x085f: "tmz_DZ",# Tamazight - Latin
0x0449: "ta_IN", # Tamil
0x0444: "tt_RU", # Tatar
0x044a: "te_IN", # Telugu
0x041e: "th_TH", # Thai
0x0851: "bo_BT", # Tibetan - Bhutan
0x0451: "bo_CN", # Tibetan - PRC
0x041f: "tr_TR", # Turkish
0x0442: "tk_TM", # Turkmen - Cyrillic
0x0480: "ug_CN", # Uighur - Arabic
0x0422: "uk_UA", # Ukrainian
0x042e: "wen_DE",# Upper Sorbian - Germany
0x0420: "ur_PK", # Urdu
0x0820: "ur_IN", # Urdu - India
0x0443: "uz_UZ", # Uzbek - Latin
0x0843: "uz_UZ", # Uzbek - Cyrillic
0x042a: "vi_VN", # Vietnamese
0x0452: "cy_GB", # Welsh
0x0488: "wo_SN", # Wolof - Senegal
0x0434: "xh_ZA", # Xhosa - South Africa
0x0485: "sah_RU",# Yakut - Cyrillic
0x0478: "ii_CN", # Yi - PRC
0x046a: "yo_NG", # Yoruba - Nigeria
0x0435: "zu_ZA", # Zulu
}
def _print_locale():
""" Test function.
"""
categories = {}
def _init_categories(categories=categories):
for k,v in globals().items():
if k[:3] == 'LC_':
categories[k] = v
_init_categories()
del categories['LC_ALL']
print 'Locale defaults as determined by getdefaultlocale():'
print '-'*72
lang, enc = getdefaultlocale()
print 'Language: ', lang or '(undefined)'
print 'Encoding: ', enc or '(undefined)'
print
print 'Locale settings on startup:'
print '-'*72
for name,category in categories.items():
print name, '...'
lang, enc = getlocale(category)
print ' Language: ', lang or '(undefined)'
print ' Encoding: ', enc or '(undefined)'
print
print
print 'Locale settings after calling resetlocale():'
print '-'*72
resetlocale()
for name,category in categories.items():
print name, '...'
lang, enc = getlocale(category)
print ' Language: ', lang or '(undefined)'
print ' Encoding: ', enc or '(undefined)'
print
try:
setlocale(LC_ALL, "")
except:
print 'NOTE:'
print 'setlocale(LC_ALL, "") does not support the default locale'
print 'given in the OS environment variables.'
else:
print
print 'Locale settings after calling setlocale(LC_ALL, ""):'
print '-'*72
for name,category in categories.items():
print name, '...'
lang, enc = getlocale(category)
print ' Language: ', lang or '(undefined)'
print ' Encoding: ', enc or '(undefined)'
print
###
try:
LC_MESSAGES
except NameError:
pass
else:
__all__.append("LC_MESSAGES")
if __name__=='__main__':
print 'Locale aliasing:'
print
_print_locale()
print
print 'Number formatting:'
print
_test()
|