3 The module provides low-level access to the C lib's locale APIs
4 and adds high level number formatting APIs as well as a locale
5 aliasing engine to complement these.
7 The aliasing engine includes support for many commonly used locale
8 names and maps them to values suitable for passing to the C lib's
9 setlocale() function. It also includes default encodings for all
10 supported locale names.
14 import sys
, encodings
, encodings
.aliases
16 # Try importing the _locale module.
18 # If this fails, fall back on a basic 'C' locale emulation.
20 # Yuck: LC_MESSAGES is non-standard: can't tell whether it exists before
21 # trying the import. So __all__ is also fiddled at the end of the file.
22 __all__
= ["setlocale","Error","localeconv","strcoll","strxfrm",
23 "format","str","atof","atoi","LC_CTYPE","LC_COLLATE",
24 "LC_TIME","LC_MONETARY","LC_NUMERIC", "LC_ALL","CHAR_MAX"]
45 """ localeconv() -> dict.
46 Returns numeric and monetary locale-specific parameters.
48 # 'C' locale default values
49 return {'grouping': [127],
50 'currency_symbol': '',
55 'n_sep_by_space': 127,
59 'p_sep_by_space': 127,
60 'int_curr_symbol': '',
63 'mon_thousands_sep': '',
65 'mon_decimal_point': '',
66 'int_frac_digits': 127}
68 def setlocale(category
, value
=None):
69 """ setlocale(integer,string=None) -> string.
70 Activates/queries locale processing.
72 if value
not in (None, '', 'C'):
73 raise Error
, '_locale emulation only supports "C" locale'
77 """ strcoll(string,string) -> int.
78 Compares two strings according to the locale.
83 """ strxfrm(string) -> string.
84 Returns a string that behaves for cmp locale-aware.
88 ### Number formatting APIs
90 # Author: Martin von Loewis
91 # improved by Georg Brandl
93 #perform the grouping from right to left
94 def _group(s
, monetary
=False):
96 thousands_sep
= conv
[monetary
and 'mon_thousands_sep' or 'thousands_sep']
97 grouping
= conv
[monetary
and 'mon_grouping' or 'grouping']
107 while s
and grouping
:
108 # if grouping is -1, we are done
109 if grouping
[0] == CHAR_MAX
:
111 # 0: re-use last group ad infinitum
112 elif grouping
[0] != 0:
115 grouping
= grouping
[1:]
117 result
= s
[-group
:] + thousands_sep
+ result
122 if s
and s
[-1] not in "0123456789":
123 # the leading string is only spaces and signs
124 return s
+ result
+ spaces
, seps
126 return s
+ spaces
, seps
128 result
= s
+ thousands_sep
+ result
130 return result
+ spaces
, seps
132 def format(percent
, value
, grouping
=False, monetary
=False, *additional
):
133 """Returns the locale-aware substitution of a %? specifier
136 additional is for format strings which contain one or more
138 # this is only for one-percent-specifier strings and this should be checked
139 if percent
[0] != '%':
140 raise ValueError("format() must be given exactly one %char "
143 formatted
= percent
% ((value
,) + additional
)
145 formatted
= percent
% value
146 # floats and decimal ints need special action!
147 if percent
[-1] in 'eEfFgG':
149 parts
= formatted
.split('.')
151 parts
[0], seps
= _group(parts
[0], monetary
=monetary
)
152 decimal_point
= localeconv()[monetary
and 'mon_decimal_point'
154 formatted
= decimal_point
.join(parts
)
156 sp
= formatted
.find(' ')
158 formatted
= formatted
[:sp
] + formatted
[sp
+1:]
160 elif percent
[-1] in 'diu':
162 formatted
= _group(formatted
, monetary
=monetary
)[0]
166 _percent_re
= re
.compile(r
'%(?:\((?P<key>.*?)\))?'
167 r
'(?P<modifiers>[-#0-9 +*.hlL]*?)[eEfFgGdiouxXcrs%]')
169 def format_string(f
, val
, grouping
=False):
170 """Formats a string in the same way that the % formatting would use,
171 but takes the current locale into account.
172 Grouping is applied if the third parameter is true."""
173 percents
= list(_percent_re
.finditer(f
))
174 new_f
= _percent_re
.sub('%s', f
)
176 if isinstance(val
, tuple):
179 for perc
in percents
:
180 starcount
= perc
.group('modifiers').count('*')
181 new_val
[i
] = format(perc
.group(), new_val
[i
], grouping
, False, *new_val
[i
+1:i
+1+starcount
])
182 del new_val
[i
+1:i
+1+starcount
]
185 elif operator
.isMappingType(val
):
186 for perc
in percents
:
187 key
= perc
.group("key")
188 val
[key
] = format(perc
.group(), val
[key
], grouping
)
190 # val is a single value
191 val
= format(percents
[0].group(), val
, grouping
)
195 def currency(val
, symbol
=True, grouping
=False, international
=False):
196 """Formats val according to the currency settings
197 in the current locale."""
200 # check for illegal values
201 digits
= conv
[international
and 'int_frac_digits' or 'frac_digits']
203 raise ValueError("Currency formatting is not possible using "
206 s
= format('%%.%if' % digits
, abs(val
), grouping
, monetary
=True)
207 # '<' and '>' are markers if the sign must be inserted between symbol and value
211 smb
= conv
[international
and 'int_curr_symbol' or 'currency_symbol']
212 precedes
= conv
[val
<0 and 'n_cs_precedes' or 'p_cs_precedes']
213 separated
= conv
[val
<0 and 'n_sep_by_space' or 'p_sep_by_space']
216 s
= smb
+ (separated
and ' ' or '') + s
218 s
= s
+ (separated
and ' ' or '') + smb
220 sign_pos
= conv
[val
<0 and 'n_sign_posn' or 'p_sign_posn']
221 sign
= conv
[val
<0 and 'negative_sign' or 'positive_sign']
230 s
= s
.replace('<', sign
)
232 s
= s
.replace('>', sign
)
234 # the default if nothing specified;
235 # this should be the most fitting sign position
238 return s
.replace('<', '').replace('>', '')
241 """Convert float to integer, taking the locale into account."""
242 return format("%.12g", val
)
244 def atof(string
, func
=float):
245 "Parses a string as a float according to the locale settings."
246 #First, get rid of the grouping
247 ts
= localeconv()['thousands_sep']
249 string
= string
.replace(ts
, '')
250 #next, replace the decimal point with a dot
251 dd
= localeconv()['decimal_point']
253 string
= string
.replace(dd
, '.')
254 #finally, parse the string
258 "Converts a string to an integer according to the locale settings."
259 return atof(str, int)
262 setlocale(LC_ALL
, "")
264 s1
= format("%d", 123456789,1)
265 print s1
, "is", atoi(s1
)
268 print s1
, "is", atof(s1
)
270 ### Locale name aliasing engine
272 # Author: Marc-Andre Lemburg, mal@lemburg.com
273 # Various tweaks by Fredrik Lundh <fredrik@pythonware.com>
275 # store away the low-level version of setlocale (it's
277 _setlocale
= setlocale
279 def normalize(localename
):
281 """ Returns a normalized locale code for the given locale
284 The returned locale code is formatted for use with
287 If normalization fails, the original name is returned
290 If the given encoding is not known, the function defaults to
291 the default encoding for the locale code just like setlocale()
295 # Normalize the locale name and extract the encoding
296 fullname
= localename
.lower()
298 # ':' is sometimes used as encoding delimiter.
299 fullname
= fullname
.replace(':', '.')
301 langname
, encoding
= fullname
.split('.')[:2]
302 fullname
= langname
+ '.' + encoding
307 # First lookup: fullname (possibly with encoding)
308 norm_encoding
= encoding
.replace('-', '')
309 norm_encoding
= norm_encoding
.replace('_', '')
310 lookup_name
= langname
+ '.' + encoding
311 code
= locale_alias
.get(lookup_name
, None)
314 #print 'first lookup failed'
316 # Second try: langname (without encoding)
317 code
= locale_alias
.get(langname
, None)
319 #print 'langname lookup succeeded'
321 langname
, defenc
= code
.split('.')
326 # Convert the encoding to a C lib compatible encoding string
327 norm_encoding
= encodings
.normalize_encoding(encoding
)
328 #print 'norm encoding: %r' % norm_encoding
329 norm_encoding
= encodings
.aliases
.aliases
.get(norm_encoding
,
331 #print 'aliased encoding: %r' % norm_encoding
332 encoding
= locale_encoding_alias
.get(norm_encoding
,
336 #print 'found encoding %r' % encoding
338 return langname
+ '.' + encoding
345 def _parse_localename(localename
):
347 """ Parses the locale code for localename and returns the
348 result as tuple (language code, encoding).
350 The localename is normalized and passed through the locale
351 alias engine. A ValueError is raised in case the locale name
354 The language code corresponds to RFC 1766. code and encoding
355 can be None in case the values cannot be determined or are
356 unknown to this implementation.
359 code
= normalize(localename
)
361 # Deal with locale modifiers
362 code
, modifier
= code
.split('@')
363 if modifier
== 'euro' and '.' not in code
:
364 # Assume Latin-9 for @euro locales. This is bogus,
365 # since some systems may use other encodings for these
366 # locales. Also, we ignore other modifiers.
367 return code
, 'iso-8859-15'
370 return tuple(code
.split('.')[:2])
373 raise ValueError, 'unknown locale: %s' % localename
375 def _build_localename(localetuple
):
377 """ Builds a locale code from the given tuple (language code,
380 No aliasing or normalizing takes place.
383 language
, encoding
= localetuple
389 return language
+ '.' + encoding
391 def getdefaultlocale(envvars
=('LC_ALL', 'LC_CTYPE', 'LANG', 'LANGUAGE')):
393 """ Tries to determine the default locale settings and returns
394 them as tuple (language code, encoding).
396 According to POSIX, a program which has not called
397 setlocale(LC_ALL, "") runs using the portable 'C' locale.
398 Calling setlocale(LC_ALL, "") lets it use the default locale as
399 defined by the LANG variable. Since we don't want to interfere
400 with the current locale setting we thus emulate the behavior
401 in the way described above.
403 To maintain compatibility with other platforms, not only the
404 LANG variable is tested, but a list of variables given as
405 envvars parameter. The first found to be defined will be
406 used. envvars defaults to the search path used in GNU gettext;
407 it must always contain the variable name 'LANG'.
409 Except for the code 'C', the language code corresponds to RFC
410 1766. code and encoding can be None in case the values cannot
416 # check if it's supported by the _locale module
418 code
, encoding
= _locale
._getdefaultlocale
()
419 except (ImportError, AttributeError):
422 # make sure the code/encoding values are valid
423 if sys
.platform
== "win32" and code
and code
[:2] == "0x":
424 # map windows language identifier to language name
425 code
= windows_locale
.get(int(code
, 0))
426 # ...add other platform-specific processing here, if
428 return code
, encoding
430 # fall back on POSIX behaviour
432 lookup
= os
.environ
.get
433 for variable
in envvars
:
434 localename
= lookup(variable
,None)
436 if variable
== 'LANGUAGE':
437 localename
= localename
.split(':')[0]
441 return _parse_localename(localename
)
444 def getlocale(category
=LC_CTYPE
):
446 """ Returns the current setting for the given locale category as
447 tuple (language code, encoding).
449 category may be one of the LC_* value except LC_ALL. It
450 defaults to LC_CTYPE.
452 Except for the code 'C', the language code corresponds to RFC
453 1766. code and encoding can be None in case the values cannot
457 localename
= _setlocale(category
)
458 if category
== LC_ALL
and ';' in localename
:
459 raise TypeError, 'category LC_ALL is not supported'
460 return _parse_localename(localename
)
462 def setlocale(category
, locale
=None):
464 """ Set the locale for the given category. The locale can be
465 a string, a locale tuple (language code, encoding), or None.
467 Locale tuples are converted to strings the locale aliasing
468 engine. Locale strings are passed directly to the C lib.
470 category may be given as one of the LC_* values.
473 if locale
and type(locale
) is not type(""):
475 locale
= normalize(_build_localename(locale
))
476 return _setlocale(category
, locale
)
478 def resetlocale(category
=LC_ALL
):
480 """ Sets the locale for category to the default setting.
482 The default setting is determined by calling
483 getdefaultlocale(). category defaults to LC_ALL.
486 _setlocale(category
, _build_localename(getdefaultlocale()))
488 if sys
.platform
in ('win32', 'darwin', 'mac'):
489 # On Win32, this will return the ANSI code page
490 # On the Mac, it should return the system encoding;
491 # it might return "ascii" instead
492 def getpreferredencoding(do_setlocale
= True):
493 """Return the charset that the user is likely using."""
495 return _locale
._getdefaultlocale
()[1]
497 # On Unix, if CODESET is available, use that.
501 # Fall back to parsing environment variables :-(
502 def getpreferredencoding(do_setlocale
= True):
503 """Return the charset that the user is likely using,
504 by looking at environment variables."""
505 return getdefaultlocale()[1]
507 def getpreferredencoding(do_setlocale
= True):
508 """Return the charset that the user is likely using,
509 according to the system configuration."""
511 oldloc
= setlocale(LC_CTYPE
)
512 setlocale(LC_CTYPE
, "")
513 result
= nl_langinfo(CODESET
)
514 setlocale(LC_CTYPE
, oldloc
)
517 return nl_langinfo(CODESET
)
522 # The following data was extracted from the locale.alias file which
523 # comes with X11 and then hand edited removing the explicit encoding
524 # definitions and adding some more aliases. The file is usually
525 # available as /usr/lib/X11/locale/locale.alias.
529 # The local_encoding_alias table maps lowercase encoding alias names
530 # to C locale encoding names (case-sensitive). Note that normalize()
531 # first looks up the encoding in the encodings.aliases dictionary and
532 # then applies this mapping to find the correct C lib name for the
535 locale_encoding_alias
= {
537 # Mappings for non-standard encoding names used in locale names
545 # Mappings from Python codec names to C lib encoding names
546 'ascii': 'ISO8859-1',
547 'latin_1': 'ISO8859-1',
548 'iso8859_1': 'ISO8859-1',
549 'iso8859_10': 'ISO8859-10',
550 'iso8859_11': 'ISO8859-11',
551 'iso8859_13': 'ISO8859-13',
552 'iso8859_14': 'ISO8859-14',
553 'iso8859_15': 'ISO8859-15',
554 'iso8859_2': 'ISO8859-2',
555 'iso8859_3': 'ISO8859-3',
556 'iso8859_4': 'ISO8859-4',
557 'iso8859_5': 'ISO8859-5',
558 'iso8859_6': 'ISO8859-6',
559 'iso8859_7': 'ISO8859-7',
560 'iso8859_8': 'ISO8859-8',
561 'iso8859_9': 'ISO8859-9',
562 'iso2022_jp': 'JIS7',
570 # XXX This list is still incomplete. If you know more
571 # mappings, please file a bug report. Thanks.
575 # The locale_alias table maps lowercase alias names to C locale names
576 # (case-sensitive). Encodings are always separated from the locale
577 # name using a dot ('.'); they should only be given in case the
578 # language name is needed to interpret the given encoding alias
579 # correctly (CJK codes often have this need).
581 # Note that the normalize() function which uses this tables
582 # removes '_' and '-' characters from the encoding part of the
583 # locale name before doing the lookup. This saves a lot of
584 # space in the table.
587 # Updated alias mapping to most recent locale.alias file
588 # from X.org distribution using makelocalealias.py.
590 # These are the differences compared to the old mapping (Python 2.4
593 # updated 'bg' -> 'bg_BG.ISO8859-5' to 'bg_BG.CP1251'
594 # updated 'bg_bg' -> 'bg_BG.ISO8859-5' to 'bg_BG.CP1251'
595 # updated 'bulgarian' -> 'bg_BG.ISO8859-5' to 'bg_BG.CP1251'
596 # updated 'cz' -> 'cz_CZ.ISO8859-2' to 'cs_CZ.ISO8859-2'
597 # updated 'cz_cz' -> 'cz_CZ.ISO8859-2' to 'cs_CZ.ISO8859-2'
598 # updated 'czech' -> 'cs_CS.ISO8859-2' to 'cs_CZ.ISO8859-2'
599 # updated 'dutch' -> 'nl_BE.ISO8859-1' to 'nl_NL.ISO8859-1'
600 # updated 'et' -> 'et_EE.ISO8859-4' to 'et_EE.ISO8859-15'
601 # updated 'et_ee' -> 'et_EE.ISO8859-4' to 'et_EE.ISO8859-15'
602 # updated 'fi' -> 'fi_FI.ISO8859-1' to 'fi_FI.ISO8859-15'
603 # updated 'fi_fi' -> 'fi_FI.ISO8859-1' to 'fi_FI.ISO8859-15'
604 # updated 'iw' -> 'iw_IL.ISO8859-8' to 'he_IL.ISO8859-8'
605 # updated 'iw_il' -> 'iw_IL.ISO8859-8' to 'he_IL.ISO8859-8'
606 # updated 'japanese' -> 'ja_JP.SJIS' to 'ja_JP.eucJP'
607 # updated 'lt' -> 'lt_LT.ISO8859-4' to 'lt_LT.ISO8859-13'
608 # updated 'lv' -> 'lv_LV.ISO8859-4' to 'lv_LV.ISO8859-13'
609 # updated 'sl' -> 'sl_CS.ISO8859-2' to 'sl_SI.ISO8859-2'
610 # updated 'slovene' -> 'sl_CS.ISO8859-2' to 'sl_SI.ISO8859-2'
611 # updated 'th_th' -> 'th_TH.TACTIS' to 'th_TH.ISO8859-11'
612 # updated 'zh_cn' -> 'zh_CN.eucCN' to 'zh_CN.gb2312'
613 # updated 'zh_cn.big5' -> 'zh_TW.eucTW' to 'zh_TW.big5'
614 # updated 'zh_tw' -> 'zh_TW.eucTW' to 'zh_TW.big5'
617 'a3': 'a3_AZ.KOI8-C',
618 'a3_az': 'a3_AZ.KOI8-C',
619 'a3_az.koi8c': 'a3_AZ.KOI8-C',
620 'af': 'af_ZA.ISO8859-1',
621 'af_za': 'af_ZA.ISO8859-1',
622 'af_za.iso88591': 'af_ZA.ISO8859-1',
624 'american': 'en_US.ISO8859-1',
625 'american.iso88591': 'en_US.ISO8859-1',
626 'ar': 'ar_AA.ISO8859-6',
627 'ar_aa': 'ar_AA.ISO8859-6',
628 'ar_aa.iso88596': 'ar_AA.ISO8859-6',
629 'ar_ae': 'ar_AE.ISO8859-6',
630 'ar_bh': 'ar_BH.ISO8859-6',
631 'ar_dz': 'ar_DZ.ISO8859-6',
632 'ar_eg': 'ar_EG.ISO8859-6',
633 'ar_eg.iso88596': 'ar_EG.ISO8859-6',
634 'ar_iq': 'ar_IQ.ISO8859-6',
635 'ar_jo': 'ar_JO.ISO8859-6',
636 'ar_kw': 'ar_KW.ISO8859-6',
637 'ar_lb': 'ar_LB.ISO8859-6',
638 'ar_ly': 'ar_LY.ISO8859-6',
639 'ar_ma': 'ar_MA.ISO8859-6',
640 'ar_om': 'ar_OM.ISO8859-6',
641 'ar_qa': 'ar_QA.ISO8859-6',
642 'ar_sa': 'ar_SA.ISO8859-6',
643 'ar_sa.iso88596': 'ar_SA.ISO8859-6',
644 'ar_sd': 'ar_SD.ISO8859-6',
645 'ar_sy': 'ar_SY.ISO8859-6',
646 'ar_tn': 'ar_TN.ISO8859-6',
647 'ar_ye': 'ar_YE.ISO8859-6',
648 'arabic': 'ar_AA.ISO8859-6',
649 'arabic.iso88596': 'ar_AA.ISO8859-6',
650 'az': 'az_AZ.ISO8859-9E',
651 'az_az': 'az_AZ.ISO8859-9E',
652 'az_az.iso88599e': 'az_AZ.ISO8859-9E',
653 'be': 'be_BY.CP1251',
654 'be_by': 'be_BY.CP1251',
655 'be_by.cp1251': 'be_BY.CP1251',
656 'be_by.microsoftcp1251': 'be_BY.CP1251',
657 'bg': 'bg_BG.CP1251',
658 'bg_bg': 'bg_BG.CP1251',
659 'bg_bg.cp1251': 'bg_BG.CP1251',
660 'bg_bg.iso88595': 'bg_BG.ISO8859-5',
661 'bg_bg.koi8r': 'bg_BG.KOI8-R',
662 'bg_bg.microsoftcp1251': 'bg_BG.CP1251',
663 'bokmal': 'nb_NO.ISO8859-1',
664 'bokm\xe5l': 'nb_NO.ISO8859-1',
665 'br': 'br_FR.ISO8859-1',
666 'br_fr': 'br_FR.ISO8859-1',
667 'br_fr.iso88591': 'br_FR.ISO8859-1',
668 'br_fr.iso885914': 'br_FR.ISO8859-14',
669 'br_fr.iso885915': 'br_FR.ISO8859-15',
670 'br_fr@euro': 'br_FR.ISO8859-15',
671 'bulgarian': 'bg_BG.CP1251',
673 'c-french': 'fr_CA.ISO8859-1',
674 'c-french.iso88591': 'fr_CA.ISO8859-1',
676 'c.iso88591': 'en_US.ISO8859-1',
679 'ca': 'ca_ES.ISO8859-1',
680 'ca_es': 'ca_ES.ISO8859-1',
681 'ca_es.iso88591': 'ca_ES.ISO8859-1',
682 'ca_es.iso885915': 'ca_ES.ISO8859-15',
683 'ca_es@euro': 'ca_ES.ISO8859-15',
684 'catalan': 'ca_ES.ISO8859-1',
685 'cextend': 'en_US.ISO8859-1',
686 'cextend.en': 'en_US.ISO8859-1',
687 'chinese-s': 'zh_CN.eucCN',
688 'chinese-t': 'zh_TW.eucTW',
689 'croatian': 'hr_HR.ISO8859-2',
690 'cs': 'cs_CZ.ISO8859-2',
691 'cs_cs': 'cs_CZ.ISO8859-2',
692 'cs_cs.iso88592': 'cs_CZ.ISO8859-2',
693 'cs_cz': 'cs_CZ.ISO8859-2',
694 'cs_cz.iso88592': 'cs_CZ.ISO8859-2',
695 'cy': 'cy_GB.ISO8859-1',
696 'cy_gb': 'cy_GB.ISO8859-1',
697 'cy_gb.iso88591': 'cy_GB.ISO8859-1',
698 'cy_gb.iso885914': 'cy_GB.ISO8859-14',
699 'cy_gb.iso885915': 'cy_GB.ISO8859-15',
700 'cy_gb@euro': 'cy_GB.ISO8859-15',
701 'cz': 'cs_CZ.ISO8859-2',
702 'cz_cz': 'cs_CZ.ISO8859-2',
703 'czech': 'cs_CZ.ISO8859-2',
704 'da': 'da_DK.ISO8859-1',
705 'da_dk': 'da_DK.ISO8859-1',
706 'da_dk.88591': 'da_DK.ISO8859-1',
707 'da_dk.885915': 'da_DK.ISO8859-15',
708 'da_dk.iso88591': 'da_DK.ISO8859-1',
709 'da_dk.iso885915': 'da_DK.ISO8859-15',
710 'da_dk@euro': 'da_DK.ISO8859-15',
711 'danish': 'da_DK.ISO8859-1',
712 'danish.iso88591': 'da_DK.ISO8859-1',
713 'dansk': 'da_DK.ISO8859-1',
714 'de': 'de_DE.ISO8859-1',
715 'de_at': 'de_AT.ISO8859-1',
716 'de_at.iso88591': 'de_AT.ISO8859-1',
717 'de_at.iso885915': 'de_AT.ISO8859-15',
718 'de_at@euro': 'de_AT.ISO8859-15',
719 'de_be': 'de_BE.ISO8859-1',
720 'de_be.iso88591': 'de_BE.ISO8859-1',
721 'de_be.iso885915': 'de_BE.ISO8859-15',
722 'de_be@euro': 'de_BE.ISO8859-15',
723 'de_ch': 'de_CH.ISO8859-1',
724 'de_ch.iso88591': 'de_CH.ISO8859-1',
725 'de_ch.iso885915': 'de_CH.ISO8859-15',
726 'de_ch@euro': 'de_CH.ISO8859-15',
727 'de_de': 'de_DE.ISO8859-1',
728 'de_de.88591': 'de_DE.ISO8859-1',
729 'de_de.885915': 'de_DE.ISO8859-15',
730 'de_de.885915@euro': 'de_DE.ISO8859-15',
731 'de_de.iso88591': 'de_DE.ISO8859-1',
732 'de_de.iso885915': 'de_DE.ISO8859-15',
733 'de_de@euro': 'de_DE.ISO8859-15',
734 'de_lu': 'de_LU.ISO8859-1',
735 'de_lu.iso88591': 'de_LU.ISO8859-1',
736 'de_lu.iso885915': 'de_LU.ISO8859-15',
737 'de_lu@euro': 'de_LU.ISO8859-15',
738 'deutsch': 'de_DE.ISO8859-1',
739 'dutch': 'nl_NL.ISO8859-1',
740 'dutch.iso88591': 'nl_BE.ISO8859-1',
741 'ee': 'ee_EE.ISO8859-4',
742 'ee_ee': 'ee_EE.ISO8859-4',
743 'ee_ee.iso88594': 'ee_EE.ISO8859-4',
744 'eesti': 'et_EE.ISO8859-1',
745 'el': 'el_GR.ISO8859-7',
746 'el_gr': 'el_GR.ISO8859-7',
747 'el_gr.iso88597': 'el_GR.ISO8859-7',
748 'el_gr@euro': 'el_GR.ISO8859-15',
749 'en': 'en_US.ISO8859-1',
750 'en.iso88591': 'en_US.ISO8859-1',
751 'en_au': 'en_AU.ISO8859-1',
752 'en_au.iso88591': 'en_AU.ISO8859-1',
753 'en_be': 'en_BE.ISO8859-1',
754 'en_be@euro': 'en_BE.ISO8859-15',
755 'en_bw': 'en_BW.ISO8859-1',
756 'en_ca': 'en_CA.ISO8859-1',
757 'en_ca.iso88591': 'en_CA.ISO8859-1',
758 'en_gb': 'en_GB.ISO8859-1',
759 'en_gb.88591': 'en_GB.ISO8859-1',
760 'en_gb.iso88591': 'en_GB.ISO8859-1',
761 'en_gb.iso885915': 'en_GB.ISO8859-15',
762 'en_gb@euro': 'en_GB.ISO8859-15',
763 'en_hk': 'en_HK.ISO8859-1',
764 'en_ie': 'en_IE.ISO8859-1',
765 'en_ie.iso88591': 'en_IE.ISO8859-1',
766 'en_ie.iso885915': 'en_IE.ISO8859-15',
767 'en_ie@euro': 'en_IE.ISO8859-15',
768 'en_in': 'en_IN.ISO8859-1',
769 'en_nz': 'en_NZ.ISO8859-1',
770 'en_nz.iso88591': 'en_NZ.ISO8859-1',
771 'en_ph': 'en_PH.ISO8859-1',
772 'en_sg': 'en_SG.ISO8859-1',
773 'en_uk': 'en_GB.ISO8859-1',
774 'en_us': 'en_US.ISO8859-1',
775 'en_us.88591': 'en_US.ISO8859-1',
776 'en_us.885915': 'en_US.ISO8859-15',
777 'en_us.iso88591': 'en_US.ISO8859-1',
778 'en_us.iso885915': 'en_US.ISO8859-15',
779 'en_us.iso885915@euro': 'en_US.ISO8859-15',
780 'en_us@euro': 'en_US.ISO8859-15',
781 'en_us@euro@euro': 'en_US.ISO8859-15',
782 'en_za': 'en_ZA.ISO8859-1',
783 'en_za.88591': 'en_ZA.ISO8859-1',
784 'en_za.iso88591': 'en_ZA.ISO8859-1',
785 'en_za.iso885915': 'en_ZA.ISO8859-15',
786 'en_za@euro': 'en_ZA.ISO8859-15',
787 'en_zw': 'en_ZW.ISO8859-1',
788 'eng_gb': 'en_GB.ISO8859-1',
789 'eng_gb.8859': 'en_GB.ISO8859-1',
790 'english': 'en_EN.ISO8859-1',
791 'english.iso88591': 'en_EN.ISO8859-1',
792 'english_uk': 'en_GB.ISO8859-1',
793 'english_uk.8859': 'en_GB.ISO8859-1',
794 'english_united-states': 'en_US.ISO8859-1',
795 'english_united-states.437': 'C',
796 'english_us': 'en_US.ISO8859-1',
797 'english_us.8859': 'en_US.ISO8859-1',
798 'english_us.ascii': 'en_US.ISO8859-1',
799 'eo': 'eo_XX.ISO8859-3',
800 'eo_eo': 'eo_EO.ISO8859-3',
801 'eo_eo.iso88593': 'eo_EO.ISO8859-3',
802 'eo_xx': 'eo_XX.ISO8859-3',
803 'eo_xx.iso88593': 'eo_XX.ISO8859-3',
804 'es': 'es_ES.ISO8859-1',
805 'es_ar': 'es_AR.ISO8859-1',
806 'es_ar.iso88591': 'es_AR.ISO8859-1',
807 'es_bo': 'es_BO.ISO8859-1',
808 'es_bo.iso88591': 'es_BO.ISO8859-1',
809 'es_cl': 'es_CL.ISO8859-1',
810 'es_cl.iso88591': 'es_CL.ISO8859-1',
811 'es_co': 'es_CO.ISO8859-1',
812 'es_co.iso88591': 'es_CO.ISO8859-1',
813 'es_cr': 'es_CR.ISO8859-1',
814 'es_cr.iso88591': 'es_CR.ISO8859-1',
815 'es_do': 'es_DO.ISO8859-1',
816 'es_do.iso88591': 'es_DO.ISO8859-1',
817 'es_ec': 'es_EC.ISO8859-1',
818 'es_ec.iso88591': 'es_EC.ISO8859-1',
819 'es_es': 'es_ES.ISO8859-1',
820 'es_es.88591': 'es_ES.ISO8859-1',
821 'es_es.iso88591': 'es_ES.ISO8859-1',
822 'es_es.iso885915': 'es_ES.ISO8859-15',
823 'es_es@euro': 'es_ES.ISO8859-15',
824 'es_gt': 'es_GT.ISO8859-1',
825 'es_gt.iso88591': 'es_GT.ISO8859-1',
826 'es_hn': 'es_HN.ISO8859-1',
827 'es_hn.iso88591': 'es_HN.ISO8859-1',
828 'es_mx': 'es_MX.ISO8859-1',
829 'es_mx.iso88591': 'es_MX.ISO8859-1',
830 'es_ni': 'es_NI.ISO8859-1',
831 'es_ni.iso88591': 'es_NI.ISO8859-1',
832 'es_pa': 'es_PA.ISO8859-1',
833 'es_pa.iso88591': 'es_PA.ISO8859-1',
834 'es_pa.iso885915': 'es_PA.ISO8859-15',
835 'es_pa@euro': 'es_PA.ISO8859-15',
836 'es_pe': 'es_PE.ISO8859-1',
837 'es_pe.iso88591': 'es_PE.ISO8859-1',
838 'es_pe.iso885915': 'es_PE.ISO8859-15',
839 'es_pe@euro': 'es_PE.ISO8859-15',
840 'es_pr': 'es_PR.ISO8859-1',
841 'es_pr.iso88591': 'es_PR.ISO8859-1',
842 'es_py': 'es_PY.ISO8859-1',
843 'es_py.iso88591': 'es_PY.ISO8859-1',
844 'es_py.iso885915': 'es_PY.ISO8859-15',
845 'es_py@euro': 'es_PY.ISO8859-15',
846 'es_sv': 'es_SV.ISO8859-1',
847 'es_sv.iso88591': 'es_SV.ISO8859-1',
848 'es_sv.iso885915': 'es_SV.ISO8859-15',
849 'es_sv@euro': 'es_SV.ISO8859-15',
850 'es_us': 'es_US.ISO8859-1',
851 'es_uy': 'es_UY.ISO8859-1',
852 'es_uy.iso88591': 'es_UY.ISO8859-1',
853 'es_uy.iso885915': 'es_UY.ISO8859-15',
854 'es_uy@euro': 'es_UY.ISO8859-15',
855 'es_ve': 'es_VE.ISO8859-1',
856 'es_ve.iso88591': 'es_VE.ISO8859-1',
857 'es_ve.iso885915': 'es_VE.ISO8859-15',
858 'es_ve@euro': 'es_VE.ISO8859-15',
859 'estonian': 'et_EE.ISO8859-1',
860 'et': 'et_EE.ISO8859-15',
861 'et_ee': 'et_EE.ISO8859-15',
862 'et_ee.iso88591': 'et_EE.ISO8859-1',
863 'et_ee.iso885913': 'et_EE.ISO8859-13',
864 'et_ee.iso885915': 'et_EE.ISO8859-15',
865 'et_ee.iso88594': 'et_EE.ISO8859-4',
866 'et_ee@euro': 'et_EE.ISO8859-15',
867 'eu': 'eu_ES.ISO8859-1',
868 'eu_es': 'eu_ES.ISO8859-1',
869 'eu_es.iso88591': 'eu_ES.ISO8859-1',
870 'eu_es.iso885915': 'eu_ES.ISO8859-15',
871 'eu_es@euro': 'eu_ES.ISO8859-15',
873 'fa_ir': 'fa_IR.UTF-8',
874 'fa_ir.isiri3342': 'fa_IR.ISIRI-3342',
875 'fi': 'fi_FI.ISO8859-15',
876 'fi_fi': 'fi_FI.ISO8859-15',
877 'fi_fi.88591': 'fi_FI.ISO8859-1',
878 'fi_fi.iso88591': 'fi_FI.ISO8859-1',
879 'fi_fi.iso885915': 'fi_FI.ISO8859-15',
880 'fi_fi.utf8@euro': 'fi_FI.UTF-8',
881 'fi_fi@euro': 'fi_FI.ISO8859-15',
882 'finnish': 'fi_FI.ISO8859-1',
883 'finnish.iso88591': 'fi_FI.ISO8859-1',
884 'fo': 'fo_FO.ISO8859-1',
885 'fo_fo': 'fo_FO.ISO8859-1',
886 'fo_fo.iso88591': 'fo_FO.ISO8859-1',
887 'fo_fo.iso885915': 'fo_FO.ISO8859-15',
888 'fo_fo@euro': 'fo_FO.ISO8859-15',
889 'fr': 'fr_FR.ISO8859-1',
890 'fr_be': 'fr_BE.ISO8859-1',
891 'fr_be.88591': 'fr_BE.ISO8859-1',
892 'fr_be.iso88591': 'fr_BE.ISO8859-1',
893 'fr_be.iso885915': 'fr_BE.ISO8859-15',
894 'fr_be@euro': 'fr_BE.ISO8859-15',
895 'fr_ca': 'fr_CA.ISO8859-1',
896 'fr_ca.88591': 'fr_CA.ISO8859-1',
897 'fr_ca.iso88591': 'fr_CA.ISO8859-1',
898 'fr_ca.iso885915': 'fr_CA.ISO8859-15',
899 'fr_ca@euro': 'fr_CA.ISO8859-15',
900 'fr_ch': 'fr_CH.ISO8859-1',
901 'fr_ch.88591': 'fr_CH.ISO8859-1',
902 'fr_ch.iso88591': 'fr_CH.ISO8859-1',
903 'fr_ch.iso885915': 'fr_CH.ISO8859-15',
904 'fr_ch@euro': 'fr_CH.ISO8859-15',
905 'fr_fr': 'fr_FR.ISO8859-1',
906 'fr_fr.88591': 'fr_FR.ISO8859-1',
907 'fr_fr.iso88591': 'fr_FR.ISO8859-1',
908 'fr_fr.iso885915': 'fr_FR.ISO8859-15',
909 'fr_fr@euro': 'fr_FR.ISO8859-15',
910 'fr_lu': 'fr_LU.ISO8859-1',
911 'fr_lu.88591': 'fr_LU.ISO8859-1',
912 'fr_lu.iso88591': 'fr_LU.ISO8859-1',
913 'fr_lu.iso885915': 'fr_LU.ISO8859-15',
914 'fr_lu@euro': 'fr_LU.ISO8859-15',
915 'fran\xe7ais': 'fr_FR.ISO8859-1',
916 'fre_fr': 'fr_FR.ISO8859-1',
917 'fre_fr.8859': 'fr_FR.ISO8859-1',
918 'french': 'fr_FR.ISO8859-1',
919 'french.iso88591': 'fr_CH.ISO8859-1',
920 'french_france': 'fr_FR.ISO8859-1',
921 'french_france.8859': 'fr_FR.ISO8859-1',
922 'ga': 'ga_IE.ISO8859-1',
923 'ga_ie': 'ga_IE.ISO8859-1',
924 'ga_ie.iso88591': 'ga_IE.ISO8859-1',
925 'ga_ie.iso885914': 'ga_IE.ISO8859-14',
926 'ga_ie.iso885915': 'ga_IE.ISO8859-15',
927 'ga_ie@euro': 'ga_IE.ISO8859-15',
928 'galego': 'gl_ES.ISO8859-1',
929 'galician': 'gl_ES.ISO8859-1',
930 'gd': 'gd_GB.ISO8859-1',
931 'gd_gb': 'gd_GB.ISO8859-1',
932 'gd_gb.iso88591': 'gd_GB.ISO8859-1',
933 'gd_gb.iso885914': 'gd_GB.ISO8859-14',
934 'gd_gb.iso885915': 'gd_GB.ISO8859-15',
935 'gd_gb@euro': 'gd_GB.ISO8859-15',
936 'ger_de': 'de_DE.ISO8859-1',
937 'ger_de.8859': 'de_DE.ISO8859-1',
938 'german': 'de_DE.ISO8859-1',
939 'german.iso88591': 'de_CH.ISO8859-1',
940 'german_germany': 'de_DE.ISO8859-1',
941 'german_germany.8859': 'de_DE.ISO8859-1',
942 'gl': 'gl_ES.ISO8859-1',
943 'gl_es': 'gl_ES.ISO8859-1',
944 'gl_es.iso88591': 'gl_ES.ISO8859-1',
945 'gl_es.iso885915': 'gl_ES.ISO8859-15',
946 'gl_es@euro': 'gl_ES.ISO8859-15',
947 'greek': 'el_GR.ISO8859-7',
948 'greek.iso88597': 'el_GR.ISO8859-7',
949 'gv': 'gv_GB.ISO8859-1',
950 'gv_gb': 'gv_GB.ISO8859-1',
951 'gv_gb.iso88591': 'gv_GB.ISO8859-1',
952 'gv_gb.iso885914': 'gv_GB.ISO8859-14',
953 'gv_gb.iso885915': 'gv_GB.ISO8859-15',
954 'gv_gb@euro': 'gv_GB.ISO8859-15',
955 'he': 'he_IL.ISO8859-8',
956 'he_il': 'he_IL.ISO8859-8',
957 'he_il.cp1255': 'he_IL.CP1255',
958 'he_il.iso88598': 'he_IL.ISO8859-8',
959 'he_il.microsoftcp1255': 'he_IL.CP1255',
960 'hebrew': 'iw_IL.ISO8859-8',
961 'hebrew.iso88598': 'iw_IL.ISO8859-8',
962 'hi': 'hi_IN.ISCII-DEV',
963 'hi_in': 'hi_IN.ISCII-DEV',
964 'hi_in.isciidev': 'hi_IN.ISCII-DEV',
965 'hr': 'hr_HR.ISO8859-2',
966 'hr_hr': 'hr_HR.ISO8859-2',
967 'hr_hr.iso88592': 'hr_HR.ISO8859-2',
968 'hrvatski': 'hr_HR.ISO8859-2',
969 'hu': 'hu_HU.ISO8859-2',
970 'hu_hu': 'hu_HU.ISO8859-2',
971 'hu_hu.iso88592': 'hu_HU.ISO8859-2',
972 'hungarian': 'hu_HU.ISO8859-2',
973 'icelandic': 'is_IS.ISO8859-1',
974 'icelandic.iso88591': 'is_IS.ISO8859-1',
975 'id': 'id_ID.ISO8859-1',
976 'id_id': 'id_ID.ISO8859-1',
977 'in': 'id_ID.ISO8859-1',
978 'in_id': 'id_ID.ISO8859-1',
979 'is': 'is_IS.ISO8859-1',
980 'is_is': 'is_IS.ISO8859-1',
981 'is_is.iso88591': 'is_IS.ISO8859-1',
982 'is_is.iso885915': 'is_IS.ISO8859-15',
983 'is_is@euro': 'is_IS.ISO8859-15',
984 'iso-8859-1': 'en_US.ISO8859-1',
985 'iso-8859-15': 'en_US.ISO8859-15',
986 'iso8859-1': 'en_US.ISO8859-1',
987 'iso8859-15': 'en_US.ISO8859-15',
988 'iso_8859_1': 'en_US.ISO8859-1',
989 'iso_8859_15': 'en_US.ISO8859-15',
990 'it': 'it_IT.ISO8859-1',
991 'it_ch': 'it_CH.ISO8859-1',
992 'it_ch.iso88591': 'it_CH.ISO8859-1',
993 'it_ch.iso885915': 'it_CH.ISO8859-15',
994 'it_ch@euro': 'it_CH.ISO8859-15',
995 'it_it': 'it_IT.ISO8859-1',
996 'it_it.88591': 'it_IT.ISO8859-1',
997 'it_it.iso88591': 'it_IT.ISO8859-1',
998 'it_it.iso885915': 'it_IT.ISO8859-15',
999 'it_it@euro': 'it_IT.ISO8859-15',
1000 'italian': 'it_IT.ISO8859-1',
1001 'italian.iso88591': 'it_IT.ISO8859-1',
1002 'iu': 'iu_CA.NUNACOM-8',
1003 'iu_ca': 'iu_CA.NUNACOM-8',
1004 'iu_ca.nunacom8': 'iu_CA.NUNACOM-8',
1005 'iw': 'he_IL.ISO8859-8',
1006 'iw_il': 'he_IL.ISO8859-8',
1007 'iw_il.iso88598': 'he_IL.ISO8859-8',
1008 'ja': 'ja_JP.eucJP',
1009 'ja.jis': 'ja_JP.JIS7',
1010 'ja.sjis': 'ja_JP.SJIS',
1011 'ja_jp': 'ja_JP.eucJP',
1012 'ja_jp.ajec': 'ja_JP.eucJP',
1013 'ja_jp.euc': 'ja_JP.eucJP',
1014 'ja_jp.eucjp': 'ja_JP.eucJP',
1015 'ja_jp.iso-2022-jp': 'ja_JP.JIS7',
1016 'ja_jp.iso2022jp': 'ja_JP.JIS7',
1017 'ja_jp.jis': 'ja_JP.JIS7',
1018 'ja_jp.jis7': 'ja_JP.JIS7',
1019 'ja_jp.mscode': 'ja_JP.SJIS',
1020 'ja_jp.sjis': 'ja_JP.SJIS',
1021 'ja_jp.ujis': 'ja_JP.eucJP',
1022 'japan': 'ja_JP.eucJP',
1023 'japanese': 'ja_JP.eucJP',
1024 'japanese-euc': 'ja_JP.eucJP',
1025 'japanese.euc': 'ja_JP.eucJP',
1026 'japanese.sjis': 'ja_JP.SJIS',
1027 'jp_jp': 'ja_JP.eucJP',
1028 'ka': 'ka_GE.GEORGIAN-ACADEMY',
1029 'ka_ge': 'ka_GE.GEORGIAN-ACADEMY',
1030 'ka_ge.georgianacademy': 'ka_GE.GEORGIAN-ACADEMY',
1031 'ka_ge.georgianps': 'ka_GE.GEORGIAN-PS',
1032 'ka_ge.georgianrs': 'ka_GE.GEORGIAN-ACADEMY',
1033 'kl': 'kl_GL.ISO8859-1',
1034 'kl_gl': 'kl_GL.ISO8859-1',
1035 'kl_gl.iso88591': 'kl_GL.ISO8859-1',
1036 'kl_gl.iso885915': 'kl_GL.ISO8859-15',
1037 'kl_gl@euro': 'kl_GL.ISO8859-15',
1038 'ko': 'ko_KR.eucKR',
1039 'ko_kr': 'ko_KR.eucKR',
1040 'ko_kr.euc': 'ko_KR.eucKR',
1041 'ko_kr.euckr': 'ko_KR.eucKR',
1042 'korean': 'ko_KR.eucKR',
1043 'korean.euc': 'ko_KR.eucKR',
1044 'kw': 'kw_GB.ISO8859-1',
1045 'kw_gb': 'kw_GB.ISO8859-1',
1046 'kw_gb.iso88591': 'kw_GB.ISO8859-1',
1047 'kw_gb.iso885914': 'kw_GB.ISO8859-14',
1048 'kw_gb.iso885915': 'kw_GB.ISO8859-15',
1049 'kw_gb@euro': 'kw_GB.ISO8859-15',
1050 'lithuanian': 'lt_LT.ISO8859-13',
1051 'lo': 'lo_LA.MULELAO-1',
1052 'lo_la': 'lo_LA.MULELAO-1',
1053 'lo_la.cp1133': 'lo_LA.IBM-CP1133',
1054 'lo_la.ibmcp1133': 'lo_LA.IBM-CP1133',
1055 'lo_la.mulelao1': 'lo_LA.MULELAO-1',
1056 'lt': 'lt_LT.ISO8859-13',
1057 'lt_lt': 'lt_LT.ISO8859-13',
1058 'lt_lt.iso885913': 'lt_LT.ISO8859-13',
1059 'lt_lt.iso88594': 'lt_LT.ISO8859-4',
1060 'lv': 'lv_LV.ISO8859-13',
1061 'lv_lv': 'lv_LV.ISO8859-13',
1062 'lv_lv.iso885913': 'lv_LV.ISO8859-13',
1063 'lv_lv.iso88594': 'lv_LV.ISO8859-4',
1064 'mi': 'mi_NZ.ISO8859-1',
1065 'mi_nz': 'mi_NZ.ISO8859-1',
1066 'mi_nz.iso88591': 'mi_NZ.ISO8859-1',
1067 'mk': 'mk_MK.ISO8859-5',
1068 'mk_mk': 'mk_MK.ISO8859-5',
1069 'mk_mk.cp1251': 'mk_MK.CP1251',
1070 'mk_mk.iso88595': 'mk_MK.ISO8859-5',
1071 'mk_mk.microsoftcp1251': 'mk_MK.CP1251',
1072 'ms': 'ms_MY.ISO8859-1',
1073 'ms_my': 'ms_MY.ISO8859-1',
1074 'ms_my.iso88591': 'ms_MY.ISO8859-1',
1075 'mt': 'mt_MT.ISO8859-3',
1076 'mt_mt': 'mt_MT.ISO8859-3',
1077 'mt_mt.iso88593': 'mt_MT.ISO8859-3',
1078 'nb': 'nb_NO.ISO8859-1',
1079 'nb_no': 'nb_NO.ISO8859-1',
1080 'nb_no.88591': 'nb_NO.ISO8859-1',
1081 'nb_no.iso88591': 'nb_NO.ISO8859-1',
1082 'nb_no.iso885915': 'nb_NO.ISO8859-15',
1083 'nb_no@euro': 'nb_NO.ISO8859-15',
1084 'nl': 'nl_NL.ISO8859-1',
1085 'nl_be': 'nl_BE.ISO8859-1',
1086 'nl_be.88591': 'nl_BE.ISO8859-1',
1087 'nl_be.iso88591': 'nl_BE.ISO8859-1',
1088 'nl_be.iso885915': 'nl_BE.ISO8859-15',
1089 'nl_be@euro': 'nl_BE.ISO8859-15',
1090 'nl_nl': 'nl_NL.ISO8859-1',
1091 'nl_nl.88591': 'nl_NL.ISO8859-1',
1092 'nl_nl.iso88591': 'nl_NL.ISO8859-1',
1093 'nl_nl.iso885915': 'nl_NL.ISO8859-15',
1094 'nl_nl@euro': 'nl_NL.ISO8859-15',
1095 'nn': 'nn_NO.ISO8859-1',
1096 'nn_no': 'nn_NO.ISO8859-1',
1097 'nn_no.88591': 'nn_NO.ISO8859-1',
1098 'nn_no.iso88591': 'nn_NO.ISO8859-1',
1099 'nn_no.iso885915': 'nn_NO.ISO8859-15',
1100 'nn_no@euro': 'nn_NO.ISO8859-15',
1101 'no': 'no_NO.ISO8859-1',
1102 'no@nynorsk': 'ny_NO.ISO8859-1',
1103 'no_no': 'no_NO.ISO8859-1',
1104 'no_no.88591': 'no_NO.ISO8859-1',
1105 'no_no.iso88591': 'no_NO.ISO8859-1',
1106 'no_no.iso885915': 'no_NO.ISO8859-15',
1107 'no_no@euro': 'no_NO.ISO8859-15',
1108 'norwegian': 'no_NO.ISO8859-1',
1109 'norwegian.iso88591': 'no_NO.ISO8859-1',
1110 'ny': 'ny_NO.ISO8859-1',
1111 'ny_no': 'ny_NO.ISO8859-1',
1112 'ny_no.88591': 'ny_NO.ISO8859-1',
1113 'ny_no.iso88591': 'ny_NO.ISO8859-1',
1114 'ny_no.iso885915': 'ny_NO.ISO8859-15',
1115 'ny_no@euro': 'ny_NO.ISO8859-15',
1116 'nynorsk': 'nn_NO.ISO8859-1',
1117 'oc': 'oc_FR.ISO8859-1',
1118 'oc_fr': 'oc_FR.ISO8859-1',
1119 'oc_fr.iso88591': 'oc_FR.ISO8859-1',
1120 'oc_fr.iso885915': 'oc_FR.ISO8859-15',
1121 'oc_fr@euro': 'oc_FR.ISO8859-15',
1122 'pd': 'pd_US.ISO8859-1',
1123 'pd_de': 'pd_DE.ISO8859-1',
1124 'pd_de.iso88591': 'pd_DE.ISO8859-1',
1125 'pd_de.iso885915': 'pd_DE.ISO8859-15',
1126 'pd_de@euro': 'pd_DE.ISO8859-15',
1127 'pd_us': 'pd_US.ISO8859-1',
1128 'pd_us.iso88591': 'pd_US.ISO8859-1',
1129 'pd_us.iso885915': 'pd_US.ISO8859-15',
1130 'pd_us@euro': 'pd_US.ISO8859-15',
1131 'ph': 'ph_PH.ISO8859-1',
1132 'ph_ph': 'ph_PH.ISO8859-1',
1133 'ph_ph.iso88591': 'ph_PH.ISO8859-1',
1134 'pl': 'pl_PL.ISO8859-2',
1135 'pl_pl': 'pl_PL.ISO8859-2',
1136 'pl_pl.iso88592': 'pl_PL.ISO8859-2',
1137 'polish': 'pl_PL.ISO8859-2',
1138 'portuguese': 'pt_PT.ISO8859-1',
1139 'portuguese.iso88591': 'pt_PT.ISO8859-1',
1140 'portuguese_brazil': 'pt_BR.ISO8859-1',
1141 'portuguese_brazil.8859': 'pt_BR.ISO8859-1',
1144 'pp': 'pp_AN.ISO8859-1',
1145 'pp_an': 'pp_AN.ISO8859-1',
1146 'pp_an.iso88591': 'pp_AN.ISO8859-1',
1147 'pt': 'pt_PT.ISO8859-1',
1148 'pt_br': 'pt_BR.ISO8859-1',
1149 'pt_br.88591': 'pt_BR.ISO8859-1',
1150 'pt_br.iso88591': 'pt_BR.ISO8859-1',
1151 'pt_br.iso885915': 'pt_BR.ISO8859-15',
1152 'pt_br@euro': 'pt_BR.ISO8859-15',
1153 'pt_pt': 'pt_PT.ISO8859-1',
1154 'pt_pt.88591': 'pt_PT.ISO8859-1',
1155 'pt_pt.iso88591': 'pt_PT.ISO8859-1',
1156 'pt_pt.iso885915': 'pt_PT.ISO8859-15',
1157 'pt_pt.utf8@euro': 'pt_PT.UTF-8',
1158 'pt_pt@euro': 'pt_PT.ISO8859-15',
1159 'ro': 'ro_RO.ISO8859-2',
1160 'ro_ro': 'ro_RO.ISO8859-2',
1161 'ro_ro.iso88592': 'ro_RO.ISO8859-2',
1162 'romanian': 'ro_RO.ISO8859-2',
1163 'ru': 'ru_RU.ISO8859-5',
1164 'ru_ru': 'ru_RU.ISO8859-5',
1165 'ru_ru.cp1251': 'ru_RU.CP1251',
1166 'ru_ru.iso88595': 'ru_RU.ISO8859-5',
1167 'ru_ru.koi8r': 'ru_RU.KOI8-R',
1168 'ru_ru.microsoftcp1251': 'ru_RU.CP1251',
1169 'ru_ua': 'ru_UA.KOI8-U',
1170 'ru_ua.cp1251': 'ru_UA.CP1251',
1171 'ru_ua.koi8u': 'ru_UA.KOI8-U',
1172 'ru_ua.microsoftcp1251': 'ru_UA.CP1251',
1173 'rumanian': 'ro_RO.ISO8859-2',
1174 'russian': 'ru_RU.ISO8859-5',
1175 'se_no': 'se_NO.UTF-8',
1176 'serbocroatian': 'sh_YU.ISO8859-2',
1177 'sh': 'sh_YU.ISO8859-2',
1178 'sh_hr': 'sh_HR.ISO8859-2',
1179 'sh_hr.iso88592': 'sh_HR.ISO8859-2',
1180 'sh_sp': 'sh_YU.ISO8859-2',
1181 'sh_yu': 'sh_YU.ISO8859-2',
1182 'sk': 'sk_SK.ISO8859-2',
1183 'sk_sk': 'sk_SK.ISO8859-2',
1184 'sk_sk.iso88592': 'sk_SK.ISO8859-2',
1185 'sl': 'sl_SI.ISO8859-2',
1186 'sl_cs': 'sl_CS.ISO8859-2',
1187 'sl_si': 'sl_SI.ISO8859-2',
1188 'sl_si.iso88592': 'sl_SI.ISO8859-2',
1189 'slovak': 'sk_SK.ISO8859-2',
1190 'slovene': 'sl_SI.ISO8859-2',
1191 'slovenian': 'sl_SI.ISO8859-2',
1192 'sp': 'sp_YU.ISO8859-5',
1193 'sp_yu': 'sp_YU.ISO8859-5',
1194 'spanish': 'es_ES.ISO8859-1',
1195 'spanish.iso88591': 'es_ES.ISO8859-1',
1196 'spanish_spain': 'es_ES.ISO8859-1',
1197 'spanish_spain.8859': 'es_ES.ISO8859-1',
1198 'sq': 'sq_AL.ISO8859-2',
1199 'sq_al': 'sq_AL.ISO8859-2',
1200 'sq_al.iso88592': 'sq_AL.ISO8859-2',
1201 'sr': 'sr_YU.ISO8859-5',
1202 'sr@cyrillic': 'sr_YU.ISO8859-5',
1203 'sr_sp': 'sr_SP.ISO8859-2',
1204 'sr_yu': 'sr_YU.ISO8859-5',
1205 'sr_yu.cp1251@cyrillic': 'sr_YU.CP1251',
1206 'sr_yu.iso88592': 'sr_YU.ISO8859-2',
1207 'sr_yu.iso88595': 'sr_YU.ISO8859-5',
1208 'sr_yu.iso88595@cyrillic': 'sr_YU.ISO8859-5',
1209 'sr_yu.microsoftcp1251@cyrillic': 'sr_YU.CP1251',
1210 'sr_yu.utf8@cyrillic': 'sr_YU.UTF-8',
1211 'sr_yu@cyrillic': 'sr_YU.ISO8859-5',
1212 'sv': 'sv_SE.ISO8859-1',
1213 'sv_fi': 'sv_FI.ISO8859-1',
1214 'sv_fi.iso88591': 'sv_FI.ISO8859-1',
1215 'sv_fi.iso885915': 'sv_FI.ISO8859-15',
1216 'sv_fi@euro': 'sv_FI.ISO8859-15',
1217 'sv_se': 'sv_SE.ISO8859-1',
1218 'sv_se.88591': 'sv_SE.ISO8859-1',
1219 'sv_se.iso88591': 'sv_SE.ISO8859-1',
1220 'sv_se.iso885915': 'sv_SE.ISO8859-15',
1221 'sv_se@euro': 'sv_SE.ISO8859-15',
1222 'swedish': 'sv_SE.ISO8859-1',
1223 'swedish.iso88591': 'sv_SE.ISO8859-1',
1224 'ta': 'ta_IN.TSCII-0',
1225 'ta_in': 'ta_IN.TSCII-0',
1226 'ta_in.tscii': 'ta_IN.TSCII-0',
1227 'ta_in.tscii0': 'ta_IN.TSCII-0',
1228 'tg': 'tg_TJ.KOI8-C',
1229 'tg_tj': 'tg_TJ.KOI8-C',
1230 'tg_tj.koi8c': 'tg_TJ.KOI8-C',
1231 'th': 'th_TH.ISO8859-11',
1232 'th_th': 'th_TH.ISO8859-11',
1233 'th_th.iso885911': 'th_TH.ISO8859-11',
1234 'th_th.tactis': 'th_TH.TIS620',
1235 'th_th.tis620': 'th_TH.TIS620',
1236 'thai': 'th_TH.ISO8859-11',
1237 'tl': 'tl_PH.ISO8859-1',
1238 'tl_ph': 'tl_PH.ISO8859-1',
1239 'tl_ph.iso88591': 'tl_PH.ISO8859-1',
1240 'tr': 'tr_TR.ISO8859-9',
1241 'tr_tr': 'tr_TR.ISO8859-9',
1242 'tr_tr.iso88599': 'tr_TR.ISO8859-9',
1243 'tt': 'tt_RU.TATAR-CYR',
1244 'tt_ru': 'tt_RU.TATAR-CYR',
1245 'tt_ru.koi8c': 'tt_RU.KOI8-C',
1246 'tt_ru.tatarcyr': 'tt_RU.TATAR-CYR',
1247 'turkish': 'tr_TR.ISO8859-9',
1248 'turkish.iso88599': 'tr_TR.ISO8859-9',
1249 'uk': 'uk_UA.KOI8-U',
1250 'uk_ua': 'uk_UA.KOI8-U',
1251 'uk_ua.cp1251': 'uk_UA.CP1251',
1252 'uk_ua.iso88595': 'uk_UA.ISO8859-5',
1253 'uk_ua.koi8u': 'uk_UA.KOI8-U',
1254 'uk_ua.microsoftcp1251': 'uk_UA.CP1251',
1255 'univ': 'en_US.utf',
1256 'universal': 'en_US.utf',
1257 'universal.utf8@ucs4': 'en_US.UTF-8',
1258 'ur': 'ur_PK.CP1256',
1259 'ur_pk': 'ur_PK.CP1256',
1260 'ur_pk.cp1256': 'ur_PK.CP1256',
1261 'ur_pk.microsoftcp1256': 'ur_PK.CP1256',
1262 'uz': 'uz_UZ.UTF-8',
1263 'uz_uz': 'uz_UZ.UTF-8',
1265 'vi_vn': 'vi_VN.TCVN',
1266 'vi_vn.tcvn': 'vi_VN.TCVN',
1267 'vi_vn.tcvn5712': 'vi_VN.TCVN',
1268 'vi_vn.viscii': 'vi_VN.VISCII',
1269 'vi_vn.viscii111': 'vi_VN.VISCII',
1270 'wa': 'wa_BE.ISO8859-1',
1271 'wa_be': 'wa_BE.ISO8859-1',
1272 'wa_be.iso88591': 'wa_BE.ISO8859-1',
1273 'wa_be.iso885915': 'wa_BE.ISO8859-15',
1274 'wa_be@euro': 'wa_BE.ISO8859-15',
1275 'yi': 'yi_US.CP1255',
1276 'yi_us': 'yi_US.CP1255',
1277 'yi_us.cp1255': 'yi_US.CP1255',
1278 'yi_us.microsoftcp1255': 'yi_US.CP1255',
1279 'zh': 'zh_CN.eucCN',
1280 'zh_cn': 'zh_CN.gb2312',
1281 'zh_cn.big5': 'zh_TW.big5',
1282 'zh_cn.euc': 'zh_CN.eucCN',
1283 'zh_cn.gb18030': 'zh_CN.gb18030',
1284 'zh_cn.gb2312': 'zh_CN.gb2312',
1285 'zh_cn.gbk': 'zh_CN.gbk',
1286 'zh_hk': 'zh_HK.big5hkscs',
1287 'zh_hk.big5': 'zh_HK.big5',
1288 'zh_hk.big5hkscs': 'zh_HK.big5hkscs',
1289 'zh_tw': 'zh_TW.big5',
1290 'zh_tw.big5': 'zh_TW.big5',
1291 'zh_tw.euc': 'zh_TW.eucTW',
1295 # This maps Windows language identifiers to locale strings.
1297 # This list has been updated from
1298 # http://msdn.microsoft.com/library/default.asp?url=/library/en-us/intl/nls_238z.asp
1299 # to include every locale up to Windows XP.
1301 # NOTE: this mapping is incomplete. If your language is missing, please
1302 # submit a bug report to Python bug manager, which you can find via:
1303 # http://www.python.org/dev/
1304 # Make sure you include the missing language identifier and the suggested
1309 0x0436: "af_ZA", # Afrikaans
1310 0x041c: "sq_AL", # Albanian
1311 0x0401: "ar_SA", # Arabic - Saudi Arabia
1312 0x0801: "ar_IQ", # Arabic - Iraq
1313 0x0c01: "ar_EG", # Arabic - Egypt
1314 0x1001: "ar_LY", # Arabic - Libya
1315 0x1401: "ar_DZ", # Arabic - Algeria
1316 0x1801: "ar_MA", # Arabic - Morocco
1317 0x1c01: "ar_TN", # Arabic - Tunisia
1318 0x2001: "ar_OM", # Arabic - Oman
1319 0x2401: "ar_YE", # Arabic - Yemen
1320 0x2801: "ar_SY", # Arabic - Syria
1321 0x2c01: "ar_JO", # Arabic - Jordan
1322 0x3001: "ar_LB", # Arabic - Lebanon
1323 0x3401: "ar_KW", # Arabic - Kuwait
1324 0x3801: "ar_AE", # Arabic - United Arab Emirates
1325 0x3c01: "ar_BH", # Arabic - Bahrain
1326 0x4001: "ar_QA", # Arabic - Qatar
1327 0x042b: "hy_AM", # Armenian
1328 0x042c: "az_AZ", # Azeri Latin
1329 0x082c: "az_AZ", # Azeri - Cyrillic
1330 0x042d: "eu_ES", # Basque
1331 0x0423: "be_BY", # Belarusian
1332 0x0445: "bn_IN", # Begali
1333 0x201a: "bs_BA", # Bosnian
1334 0x141a: "bs_BA", # Bosnian - Cyrillic
1335 0x047e: "br_FR", # Breton - France
1336 0x0402: "bg_BG", # Bulgarian
1337 0x0403: "ca_ES", # Catalan
1338 0x0004: "zh_CHS",# Chinese - Simplified
1339 0x0404: "zh_TW", # Chinese - Taiwan
1340 0x0804: "zh_CN", # Chinese - PRC
1341 0x0c04: "zh_HK", # Chinese - Hong Kong S.A.R.
1342 0x1004: "zh_SG", # Chinese - Singapore
1343 0x1404: "zh_MO", # Chinese - Macao S.A.R.
1344 0x7c04: "zh_CHT",# Chinese - Traditional
1345 0x041a: "hr_HR", # Croatian
1346 0x101a: "hr_BA", # Croatian - Bosnia
1347 0x0405: "cs_CZ", # Czech
1348 0x0406: "da_DK", # Danish
1349 0x048c: "gbz_AF",# Dari - Afghanistan
1350 0x0465: "div_MV",# Divehi - Maldives
1351 0x0413: "nl_NL", # Dutch - The Netherlands
1352 0x0813: "nl_BE", # Dutch - Belgium
1353 0x0409: "en_US", # English - United States
1354 0x0809: "en_GB", # English - United Kingdom
1355 0x0c09: "en_AU", # English - Australia
1356 0x1009: "en_CA", # English - Canada
1357 0x1409: "en_NZ", # English - New Zealand
1358 0x1809: "en_IE", # English - Ireland
1359 0x1c09: "en_ZA", # English - South Africa
1360 0x2009: "en_JA", # English - Jamaica
1361 0x2409: "en_CB", # English - Carribbean
1362 0x2809: "en_BZ", # English - Belize
1363 0x2c09: "en_TT", # English - Trinidad
1364 0x3009: "en_ZW", # English - Zimbabwe
1365 0x3409: "en_PH", # English - Phillippines
1366 0x0425: "et_EE", # Estonian
1367 0x0438: "fo_FO", # Faroese
1368 0x0464: "fil_PH",# Filipino
1369 0x040b: "fi_FI", # Finnish
1370 0x040c: "fr_FR", # French - France
1371 0x080c: "fr_BE", # French - Belgium
1372 0x0c0c: "fr_CA", # French - Canada
1373 0x100c: "fr_CH", # French - Switzerland
1374 0x140c: "fr_LU", # French - Luxembourg
1375 0x180c: "fr_MC", # French - Monaco
1376 0x0462: "fy_NL", # Frisian - Netherlands
1377 0x0456: "gl_ES", # Galician
1378 0x0437: "ka_GE", # Georgian
1379 0x0407: "de_DE", # German - Germany
1380 0x0807: "de_CH", # German - Switzerland
1381 0x0c07: "de_AT", # German - Austria
1382 0x1007: "de_LU", # German - Luxembourg
1383 0x1407: "de_LI", # German - Liechtenstein
1384 0x0408: "el_GR", # Greek
1385 0x0447: "gu_IN", # Gujarati
1386 0x040d: "he_IL", # Hebrew
1387 0x0439: "hi_IN", # Hindi
1388 0x040e: "hu_HU", # Hungarian
1389 0x040f: "is_IS", # Icelandic
1390 0x0421: "id_ID", # Indonesian
1391 0x045d: "iu_CA", # Inuktitut
1392 0x085d: "iu_CA", # Inuktitut - Latin
1393 0x083c: "ga_IE", # Irish - Ireland
1394 0x0434: "xh_ZA", # Xhosa - South Africa
1395 0x0435: "zu_ZA", # Zulu
1396 0x0410: "it_IT", # Italian - Italy
1397 0x0810: "it_CH", # Italian - Switzerland
1398 0x0411: "ja_JP", # Japanese
1399 0x044b: "kn_IN", # Kannada - India
1400 0x043f: "kk_KZ", # Kazakh
1401 0x0457: "kok_IN",# Konkani
1402 0x0412: "ko_KR", # Korean
1403 0x0440: "ky_KG", # Kyrgyz
1404 0x0426: "lv_LV", # Latvian
1405 0x0427: "lt_LT", # Lithuanian
1406 0x046e: "lb_LU", # Luxembourgish
1407 0x042f: "mk_MK", # FYRO Macedonian
1408 0x043e: "ms_MY", # Malay - Malaysia
1409 0x083e: "ms_BN", # Malay - Brunei
1410 0x044c: "ml_IN", # Malayalam - India
1411 0x043a: "mt_MT", # Maltese
1412 0x0481: "mi_NZ", # Maori
1413 0x047a: "arn_CL",# Mapudungun
1414 0x044e: "mr_IN", # Marathi
1415 0x047c: "moh_CA",# Mohawk - Canada
1416 0x0450: "mn_MN", # Mongolian
1417 0x0461: "ne_NP", # Nepali
1418 0x0414: "nb_NO", # Norwegian - Bokmal
1419 0x0814: "nn_NO", # Norwegian - Nynorsk
1420 0x0482: "oc_FR", # Occitan - France
1421 0x0448: "or_IN", # Oriya - India
1422 0x0463: "ps_AF", # Pashto - Afghanistan
1423 0x0429: "fa_IR", # Persian
1424 0x0415: "pl_PL", # Polish
1425 0x0416: "pt_BR", # Portuguese - Brazil
1426 0x0816: "pt_PT", # Portuguese - Portugal
1427 0x0446: "pa_IN", # Punjabi
1428 0x046b: "quz_BO",# Quechua (Bolivia)
1429 0x086b: "quz_EC",# Quechua (Ecuador)
1430 0x0c6b: "quz_PE",# Quechua (Peru)
1431 0x0418: "ro_RO", # Romanian - Romania
1432 0x0417: "rm_CH", # Raeto-Romanese
1433 0x0419: "ru_RU", # Russian
1434 0x243b: "smn_FI",# Sami Finland
1435 0x103b: "smj_NO",# Sami Norway
1436 0x143b: "smj_SE",# Sami Sweden
1437 0x043b: "se_NO", # Sami Northern Norway
1438 0x083b: "se_SE", # Sami Northern Sweden
1439 0x0c3b: "se_FI", # Sami Northern Finland
1440 0x203b: "sms_FI",# Sami Skolt
1441 0x183b: "sma_NO",# Sami Southern Norway
1442 0x1c3b: "sma_SE",# Sami Southern Sweden
1443 0x044f: "sa_IN", # Sanskrit
1444 0x0c1a: "sr_SP", # Serbian - Cyrillic
1445 0x1c1a: "sr_BA", # Serbian - Bosnia Cyrillic
1446 0x081a: "sr_SP", # Serbian - Latin
1447 0x181a: "sr_BA", # Serbian - Bosnia Latin
1448 0x046c: "ns_ZA", # Northern Sotho
1449 0x0432: "tn_ZA", # Setswana - Southern Africa
1450 0x041b: "sk_SK", # Slovak
1451 0x0424: "sl_SI", # Slovenian
1452 0x040a: "es_ES", # Spanish - Spain
1453 0x080a: "es_MX", # Spanish - Mexico
1454 0x0c0a: "es_ES", # Spanish - Spain (Modern)
1455 0x100a: "es_GT", # Spanish - Guatemala
1456 0x140a: "es_CR", # Spanish - Costa Rica
1457 0x180a: "es_PA", # Spanish - Panama
1458 0x1c0a: "es_DO", # Spanish - Dominican Republic
1459 0x200a: "es_VE", # Spanish - Venezuela
1460 0x240a: "es_CO", # Spanish - Colombia
1461 0x280a: "es_PE", # Spanish - Peru
1462 0x2c0a: "es_AR", # Spanish - Argentina
1463 0x300a: "es_EC", # Spanish - Ecuador
1464 0x340a: "es_CL", # Spanish - Chile
1465 0x380a: "es_UR", # Spanish - Uruguay
1466 0x3c0a: "es_PY", # Spanish - Paraguay
1467 0x400a: "es_BO", # Spanish - Bolivia
1468 0x440a: "es_SV", # Spanish - El Salvador
1469 0x480a: "es_HN", # Spanish - Honduras
1470 0x4c0a: "es_NI", # Spanish - Nicaragua
1471 0x500a: "es_PR", # Spanish - Puerto Rico
1472 0x0441: "sw_KE", # Swahili
1473 0x041d: "sv_SE", # Swedish - Sweden
1474 0x081d: "sv_FI", # Swedish - Finland
1475 0x045a: "syr_SY",# Syriac
1476 0x0449: "ta_IN", # Tamil
1477 0x0444: "tt_RU", # Tatar
1478 0x044a: "te_IN", # Telugu
1479 0x041e: "th_TH", # Thai
1480 0x041f: "tr_TR", # Turkish
1481 0x0422: "uk_UA", # Ukrainian
1482 0x0420: "ur_PK", # Urdu
1483 0x0820: "ur_IN", # Urdu - India
1484 0x0443: "uz_UZ", # Uzbek - Latin
1485 0x0843: "uz_UZ", # Uzbek - Cyrillic
1486 0x042a: "vi_VN", # Vietnamese
1487 0x0452: "cy_GB", # Welsh
1490 def _print_locale():
1495 def _init_categories(categories
=categories
):
1496 for k
,v
in globals().items():
1500 del categories
['LC_ALL']
1502 print 'Locale defaults as determined by getdefaultlocale():'
1504 lang
, enc
= getdefaultlocale()
1505 print 'Language: ', lang
or '(undefined)'
1506 print 'Encoding: ', enc
or '(undefined)'
1509 print 'Locale settings on startup:'
1511 for name
,category
in categories
.items():
1513 lang
, enc
= getlocale(category
)
1514 print ' Language: ', lang
or '(undefined)'
1515 print ' Encoding: ', enc
or '(undefined)'
1519 print 'Locale settings after calling resetlocale():'
1522 for name
,category
in categories
.items():
1524 lang
, enc
= getlocale(category
)
1525 print ' Language: ', lang
or '(undefined)'
1526 print ' Encoding: ', enc
or '(undefined)'
1530 setlocale(LC_ALL
, "")
1533 print 'setlocale(LC_ALL, "") does not support the default locale'
1534 print 'given in the OS environment variables.'
1537 print 'Locale settings after calling setlocale(LC_ALL, ""):'
1539 for name
,category
in categories
.items():
1541 lang
, enc
= getlocale(category
)
1542 print ' Language: ', lang
or '(undefined)'
1543 print ' Encoding: ', enc
or '(undefined)'
1553 __all__
.append("LC_MESSAGES")
1555 if __name__
=='__main__':
1556 print 'Locale aliasing:'
1560 print 'Number formatting:'