1"""Locale support module.
2
3The module provides low-level access to the C lib's locale APIs and adds high
4level number formatting APIs as well as a locale aliasing engine to complement
5these.
6
7The aliasing engine includes support for many commonly used locale names and
8maps them to values suitable for passing to the C lib's setlocale() function. It
9also includes default encodings for all supported locale names.
10
11"""
12
13import sys
14import encodings
15import encodings.aliases
16import re
17import _collections_abc
18from builtins import str as _builtin_str
19import functools
20
21# Try importing the _locale module.
22#
23# If this fails, fall back on a basic 'C' locale emulation.
24
25# Yuck:  LC_MESSAGES is non-standard:  can't tell whether it exists before
26# trying the import.  So __all__ is also fiddled at the end of the file.
27__all__ = ["getlocale", "getdefaultlocale", "getpreferredencoding", "Error",
28           "setlocale", "resetlocale", "localeconv", "strcoll", "strxfrm",
29           "str", "atof", "atoi", "format", "format_string", "currency",
30           "normalize", "LC_CTYPE", "LC_COLLATE", "LC_TIME", "LC_MONETARY",
31           "LC_NUMERIC", "LC_ALL", "CHAR_MAX"]
32
33def _strcoll(a,b):
34    """ strcoll(string,string) -> int.
35        Compares two strings according to the locale.
36    """
37    return (a > b) - (a < b)
38
39def _strxfrm(s):
40    """ strxfrm(string) -> string.
41        Returns a string that behaves for cmp locale-aware.
42    """
43    return s
44
45try:
46
47    from _locale import *
48
49except ImportError:
50
51    # Locale emulation
52
53    CHAR_MAX = 127
54    LC_ALL = 6
55    LC_COLLATE = 3
56    LC_CTYPE = 0
57    LC_MESSAGES = 5
58    LC_MONETARY = 4
59    LC_NUMERIC = 1
60    LC_TIME = 2
61    Error = ValueError
62
63    def localeconv():
64        """ localeconv() -> dict.
65            Returns numeric and monetary locale-specific parameters.
66        """
67        # 'C' locale default values
68        return {'grouping': [127],
69                'currency_symbol': '',
70                'n_sign_posn': 127,
71                'p_cs_precedes': 127,
72                'n_cs_precedes': 127,
73                'mon_grouping': [],
74                'n_sep_by_space': 127,
75                'decimal_point': '.',
76                'negative_sign': '',
77                'positive_sign': '',
78                'p_sep_by_space': 127,
79                'int_curr_symbol': '',
80                'p_sign_posn': 127,
81                'thousands_sep': '',
82                'mon_thousands_sep': '',
83                'frac_digits': 127,
84                'mon_decimal_point': '',
85                'int_frac_digits': 127}
86
87    def setlocale(category, value=None):
88        """ setlocale(integer,string=None) -> string.
89            Activates/queries locale processing.
90        """
91        if value not in (None, '', 'C'):
92            raise Error('_locale emulation only supports "C" locale')
93        return 'C'
94
95# These may or may not exist in _locale, so be sure to set them.
96if 'strxfrm' not in globals():
97    strxfrm = _strxfrm
98if 'strcoll' not in globals():
99    strcoll = _strcoll
100
101
102_localeconv = localeconv
103
104# With this dict, you can override some items of localeconv's return value.
105# This is useful for testing purposes.
106_override_localeconv = {}
107
108@functools.wraps(_localeconv)
109def localeconv():
110    d = _localeconv()
111    if _override_localeconv:
112        d.update(_override_localeconv)
113    return d
114
115
116### Number formatting APIs
117
118# Author: Martin von Loewis
119# improved by Georg Brandl
120
121# Iterate over grouping intervals
122def _grouping_intervals(grouping):
123    last_interval = None
124    for interval in grouping:
125        # if grouping is -1, we are done
126        if interval == CHAR_MAX:
127            return
128        # 0: re-use last group ad infinitum
129        if interval == 0:
130            if last_interval is None:
131                raise ValueError("invalid grouping")
132            while True:
133                yield last_interval
134        yield interval
135        last_interval = interval
136
137#perform the grouping from right to left
138def _group(s, monetary=False):
139    conv = localeconv()
140    thousands_sep = conv[monetary and 'mon_thousands_sep' or 'thousands_sep']
141    grouping = conv[monetary and 'mon_grouping' or 'grouping']
142    if not grouping:
143        return (s, 0)
144    if s[-1] == ' ':
145        stripped = s.rstrip()
146        right_spaces = s[len(stripped):]
147        s = stripped
148    else:
149        right_spaces = ''
150    left_spaces = ''
151    groups = []
152    for interval in _grouping_intervals(grouping):
153        if not s or s[-1] not in "0123456789":
154            # only non-digit characters remain (sign, spaces)
155            left_spaces = s
156            s = ''
157            break
158        groups.append(s[-interval:])
159        s = s[:-interval]
160    if s:
161        groups.append(s)
162    groups.reverse()
163    return (
164        left_spaces + thousands_sep.join(groups) + right_spaces,
165        len(thousands_sep) * (len(groups) - 1)
166    )
167
168# Strip a given amount of excess padding from the given string
169def _strip_padding(s, amount):
170    lpos = 0
171    while amount and s[lpos] == ' ':
172        lpos += 1
173        amount -= 1
174    rpos = len(s) - 1
175    while amount and s[rpos] == ' ':
176        rpos -= 1
177        amount -= 1
178    return s[lpos:rpos+1]
179
180_percent_re = re.compile(r'%(?:\((?P<key>.*?)\))?'
181                         r'(?P<modifiers>[-#0-9 +*.hlL]*?)[eEfFgGdiouxXcrs%]')
182
183def _format(percent, value, grouping=False, monetary=False, *additional):
184    if additional:
185        formatted = percent % ((value,) + additional)
186    else:
187        formatted = percent % value
188    # floats and decimal ints need special action!
189    if percent[-1] in 'eEfFgG':
190        seps = 0
191        parts = formatted.split('.')
192        if grouping:
193            parts[0], seps = _group(parts[0], monetary=monetary)
194        decimal_point = localeconv()[monetary and 'mon_decimal_point'
195                                              or 'decimal_point']
196        formatted = decimal_point.join(parts)
197        if seps:
198            formatted = _strip_padding(formatted, seps)
199    elif percent[-1] in 'diu':
200        seps = 0
201        if grouping:
202            formatted, seps = _group(formatted, monetary=monetary)
203        if seps:
204            formatted = _strip_padding(formatted, seps)
205    return formatted
206
207def format_string(f, val, grouping=False, monetary=False):
208    """Formats a string in the same way that the % formatting would use,
209    but takes the current locale into account.
210
211    Grouping is applied if the third parameter is true.
212    Conversion uses monetary thousands separator and grouping strings if
213    forth parameter monetary is true."""
214    percents = list(_percent_re.finditer(f))
215    new_f = _percent_re.sub('%s', f)
216
217    if isinstance(val, _collections_abc.Mapping):
218        new_val = []
219        for perc in percents:
220            if perc.group()[-1]=='%':
221                new_val.append('%')
222            else:
223                new_val.append(_format(perc.group(), val, grouping, monetary))
224    else:
225        if not isinstance(val, tuple):
226            val = (val,)
227        new_val = []
228        i = 0
229        for perc in percents:
230            if perc.group()[-1]=='%':
231                new_val.append('%')
232            else:
233                starcount = perc.group('modifiers').count('*')
234                new_val.append(_format(perc.group(),
235                                      val[i],
236                                      grouping,
237                                      monetary,
238                                      *val[i+1:i+1+starcount]))
239                i += (1 + starcount)
240    val = tuple(new_val)
241
242    return new_f % val
243
244def format(percent, value, grouping=False, monetary=False, *additional):
245    """Deprecated, use format_string instead."""
246    import warnings
247    warnings.warn(
248        "This method will be removed in a future version of Python. "
249        "Use 'locale.format_string()' instead.",
250        DeprecationWarning, stacklevel=2
251    )
252
253    match = _percent_re.match(percent)
254    if not match or len(match.group())!= len(percent):
255        raise ValueError(("format() must be given exactly one %%char "
256                         "format specifier, %s not valid") % repr(percent))
257    return _format(percent, value, grouping, monetary, *additional)
258
259def currency(val, symbol=True, grouping=False, international=False):
260    """Formats val according to the currency settings
261    in the current locale."""
262    conv = localeconv()
263
264    # check for illegal values
265    digits = conv[international and 'int_frac_digits' or 'frac_digits']
266    if digits == 127:
267        raise ValueError("Currency formatting is not possible using "
268                         "the 'C' locale.")
269
270    s = _format('%%.%if' % digits, abs(val), grouping, monetary=True)
271    # '<' and '>' are markers if the sign must be inserted between symbol and value
272    s = '<' + s + '>'
273
274    if symbol:
275        smb = conv[international and 'int_curr_symbol' or 'currency_symbol']
276        precedes = conv[val<0 and 'n_cs_precedes' or 'p_cs_precedes']
277        separated = conv[val<0 and 'n_sep_by_space' or 'p_sep_by_space']
278
279        if precedes:
280            s = smb + (separated and ' ' or '') + s
281        else:
282            s = s + (separated and ' ' or '') + smb
283
284    sign_pos = conv[val<0 and 'n_sign_posn' or 'p_sign_posn']
285    sign = conv[val<0 and 'negative_sign' or 'positive_sign']
286
287    if sign_pos == 0:
288        s = '(' + s + ')'
289    elif sign_pos == 1:
290        s = sign + s
291    elif sign_pos == 2:
292        s = s + sign
293    elif sign_pos == 3:
294        s = s.replace('<', sign)
295    elif sign_pos == 4:
296        s = s.replace('>', sign)
297    else:
298        # the default if nothing specified;
299        # this should be the most fitting sign position
300        s = sign + s
301
302    return s.replace('<', '').replace('>', '')
303
304def str(val):
305    """Convert float to string, taking the locale into account."""
306    return _format("%.12g", val)
307
308def delocalize(string):
309    "Parses a string as a normalized number according to the locale settings."
310
311    conv = localeconv()
312
313    #First, get rid of the grouping
314    ts = conv['thousands_sep']
315    if ts:
316        string = string.replace(ts, '')
317
318    #next, replace the decimal point with a dot
319    dd = conv['decimal_point']
320    if dd:
321        string = string.replace(dd, '.')
322    return string
323
324def atof(string, func=float):
325    "Parses a string as a float according to the locale settings."
326    return func(delocalize(string))
327
328def atoi(string):
329    "Converts a string to an integer according to the locale settings."
330    return int(delocalize(string))
331
332def _test():
333    setlocale(LC_ALL, "")
334    #do grouping
335    s1 = format_string("%d", 123456789,1)
336    print(s1, "is", atoi(s1))
337    #standard formatting
338    s1 = str(3.14)
339    print(s1, "is", atof(s1))
340
341### Locale name aliasing engine
342
343# Author: Marc-Andre Lemburg, mal@lemburg.com
344# Various tweaks by Fredrik Lundh <fredrik@pythonware.com>
345
346# store away the low-level version of setlocale (it's
347# overridden below)
348_setlocale = setlocale
349
350def _replace_encoding(code, encoding):
351    if '.' in code:
352        langname = code[:code.index('.')]
353    else:
354        langname = code
355    # Convert the encoding to a C lib compatible encoding string
356    norm_encoding = encodings.normalize_encoding(encoding)
357    #print('norm encoding: %r' % norm_encoding)
358    norm_encoding = encodings.aliases.aliases.get(norm_encoding.lower(),
359                                                  norm_encoding)
360    #print('aliased encoding: %r' % norm_encoding)
361    encoding = norm_encoding
362    norm_encoding = norm_encoding.lower()
363    if norm_encoding in locale_encoding_alias:
364        encoding = locale_encoding_alias[norm_encoding]
365    else:
366        norm_encoding = norm_encoding.replace('_', '')
367        norm_encoding = norm_encoding.replace('-', '')
368        if norm_encoding in locale_encoding_alias:
369            encoding = locale_encoding_alias[norm_encoding]
370    #print('found encoding %r' % encoding)
371    return langname + '.' + encoding
372
373def _append_modifier(code, modifier):
374    if modifier == 'euro':
375        if '.' not in code:
376            return code + '.ISO8859-15'
377        _, _, encoding = code.partition('.')
378        if encoding in ('ISO8859-15', 'UTF-8'):
379            return code
380        if encoding == 'ISO8859-1':
381            return _replace_encoding(code, 'ISO8859-15')
382    return code + '@' + modifier
383
384def normalize(localename):
385
386    """ Returns a normalized locale code for the given locale
387        name.
388
389        The returned locale code is formatted for use with
390        setlocale().
391
392        If normalization fails, the original name is returned
393        unchanged.
394
395        If the given encoding is not known, the function defaults to
396        the default encoding for the locale code just like setlocale()
397        does.
398
399    """
400    # Normalize the locale name and extract the encoding and modifier
401    code = localename.lower()
402    if ':' in code:
403        # ':' is sometimes used as encoding delimiter.
404        code = code.replace(':', '.')
405    if '@' in code:
406        code, modifier = code.split('@', 1)
407    else:
408        modifier = ''
409    if '.' in code:
410        langname, encoding = code.split('.')[:2]
411    else:
412        langname = code
413        encoding = ''
414
415    # First lookup: fullname (possibly with encoding and modifier)
416    lang_enc = langname
417    if encoding:
418        norm_encoding = encoding.replace('-', '')
419        norm_encoding = norm_encoding.replace('_', '')
420        lang_enc += '.' + norm_encoding
421    lookup_name = lang_enc
422    if modifier:
423        lookup_name += '@' + modifier
424    code = locale_alias.get(lookup_name, None)
425    if code is not None:
426        return code
427    #print('first lookup failed')
428
429    if modifier:
430        # Second try: fullname without modifier (possibly with encoding)
431        code = locale_alias.get(lang_enc, None)
432        if code is not None:
433            #print('lookup without modifier succeeded')
434            if '@' not in code:
435                return _append_modifier(code, modifier)
436            if code.split('@', 1)[1].lower() == modifier:
437                return code
438        #print('second lookup failed')
439
440    if encoding:
441        # Third try: langname (without encoding, possibly with modifier)
442        lookup_name = langname
443        if modifier:
444            lookup_name += '@' + modifier
445        code = locale_alias.get(lookup_name, None)
446        if code is not None:
447            #print('lookup without encoding succeeded')
448            if '@' not in code:
449                return _replace_encoding(code, encoding)
450            code, modifier = code.split('@', 1)
451            return _replace_encoding(code, encoding) + '@' + modifier
452
453        if modifier:
454            # Fourth try: langname (without encoding and modifier)
455            code = locale_alias.get(langname, None)
456            if code is not None:
457                #print('lookup without modifier and encoding succeeded')
458                if '@' not in code:
459                    code = _replace_encoding(code, encoding)
460                    return _append_modifier(code, modifier)
461                code, defmod = code.split('@', 1)
462                if defmod.lower() == modifier:
463                    return _replace_encoding(code, encoding) + '@' + defmod
464
465    return localename
466
467def _parse_localename(localename):
468
469    """ Parses the locale code for localename and returns the
470        result as tuple (language code, encoding).
471
472        The localename is normalized and passed through the locale
473        alias engine. A ValueError is raised in case the locale name
474        cannot be parsed.
475
476        The language code corresponds to RFC 1766.  code and encoding
477        can be None in case the values cannot be determined or are
478        unknown to this implementation.
479
480    """
481    code = normalize(localename)
482    if '@' in code:
483        # Deal with locale modifiers
484        code, modifier = code.split('@', 1)
485        if modifier == 'euro' and '.' not in code:
486            # Assume Latin-9 for @euro locales. This is bogus,
487            # since some systems may use other encodings for these
488            # locales. Also, we ignore other modifiers.
489            return code, 'iso-8859-15'
490
491    if '.' in code:
492        return tuple(code.split('.')[:2])
493    elif code == 'C':
494        return None, None
495    raise ValueError('unknown locale: %s' % localename)
496
497def _build_localename(localetuple):
498
499    """ Builds a locale code from the given tuple (language code,
500        encoding).
501
502        No aliasing or normalizing takes place.
503
504    """
505    try:
506        language, encoding = localetuple
507
508        if language is None:
509            language = 'C'
510        if encoding is None:
511            return language
512        else:
513            return language + '.' + encoding
514    except (TypeError, ValueError):
515        raise TypeError('Locale must be None, a string, or an iterable of '
516                        'two strings -- language code, encoding.') from None
517
518def getdefaultlocale(envvars=('LC_ALL', 'LC_CTYPE', 'LANG', 'LANGUAGE')):
519
520    """ Tries to determine the default locale settings and returns
521        them as tuple (language code, encoding).
522
523        According to POSIX, a program which has not called
524        setlocale(LC_ALL, "") runs using the portable 'C' locale.
525        Calling setlocale(LC_ALL, "") lets it use the default locale as
526        defined by the LANG variable. Since we don't want to interfere
527        with the current locale setting we thus emulate the behavior
528        in the way described above.
529
530        To maintain compatibility with other platforms, not only the
531        LANG variable is tested, but a list of variables given as
532        envvars parameter. The first found to be defined will be
533        used. envvars defaults to the search path used in GNU gettext;
534        it must always contain the variable name 'LANG'.
535
536        Except for the code 'C', the language code corresponds to RFC
537        1766.  code and encoding can be None in case the values cannot
538        be determined.
539
540    """
541
542    try:
543        # check if it's supported by the _locale module
544        import _locale
545        code, encoding = _locale._getdefaultlocale()
546    except (ImportError, AttributeError):
547        pass
548    else:
549        # make sure the code/encoding values are valid
550        if sys.platform == "win32" and code and code[:2] == "0x":
551            # map windows language identifier to language name
552            code = windows_locale.get(int(code, 0))
553        # ...add other platform-specific processing here, if
554        # necessary...
555        return code, encoding
556
557    # fall back on POSIX behaviour
558    import os
559    lookup = os.environ.get
560    for variable in envvars:
561        localename = lookup(variable,None)
562        if localename:
563            if variable == 'LANGUAGE':
564                localename = localename.split(':')[0]
565            break
566    else:
567        localename = 'C'
568    return _parse_localename(localename)
569
570
571def getlocale(category=LC_CTYPE):
572
573    """ Returns the current setting for the given locale category as
574        tuple (language code, encoding).
575
576        category may be one of the LC_* value except LC_ALL. It
577        defaults to LC_CTYPE.
578
579        Except for the code 'C', the language code corresponds to RFC
580        1766.  code and encoding can be None in case the values cannot
581        be determined.
582
583    """
584    localename = _setlocale(category)
585    if category == LC_ALL and ';' in localename:
586        raise TypeError('category LC_ALL is not supported')
587    return _parse_localename(localename)
588
589def setlocale(category, locale=None):
590
591    """ Set the locale for the given category.  The locale can be
592        a string, an iterable of two strings (language code and encoding),
593        or None.
594
595        Iterables are converted to strings using the locale aliasing
596        engine.  Locale strings are passed directly to the C lib.
597
598        category may be given as one of the LC_* values.
599
600    """
601    if locale and not isinstance(locale, _builtin_str):
602        # convert to string
603        locale = normalize(_build_localename(locale))
604    return _setlocale(category, locale)
605
606def resetlocale(category=LC_ALL):
607
608    """ Sets the locale for category to the default setting.
609
610        The default setting is determined by calling
611        getdefaultlocale(). category defaults to LC_ALL.
612
613    """
614    _setlocale(category, _build_localename(getdefaultlocale()))
615
616if sys.platform.startswith("win"):
617    # On Win32, this will return the ANSI code page
618    def getpreferredencoding(do_setlocale = True):
619        """Return the charset that the user is likely using."""
620        if sys.flags.utf8_mode:
621            return 'UTF-8'
622        import _bootlocale
623        return _bootlocale.getpreferredencoding(False)
624else:
625    # On Unix, if CODESET is available, use that.
626    try:
627        CODESET
628    except NameError:
629        if hasattr(sys, 'getandroidapilevel'):
630            # On Android langinfo.h and CODESET are missing, and UTF-8 is
631            # always used in mbstowcs() and wcstombs().
632            def getpreferredencoding(do_setlocale = True):
633                return 'UTF-8'
634        else:
635            # Fall back to parsing environment variables :-(
636            def getpreferredencoding(do_setlocale = True):
637                """Return the charset that the user is likely using,
638                by looking at environment variables."""
639                if sys.flags.utf8_mode:
640                    return 'UTF-8'
641                res = getdefaultlocale()[1]
642                if res is None:
643                    # LANG not set, default conservatively to ASCII
644                    res = 'ascii'
645                return res
646    else:
647        def getpreferredencoding(do_setlocale = True):
648            """Return the charset that the user is likely using,
649            according to the system configuration."""
650            if sys.flags.utf8_mode:
651                return 'UTF-8'
652            import _bootlocale
653            if do_setlocale:
654                oldloc = setlocale(LC_CTYPE)
655                try:
656                    setlocale(LC_CTYPE, "")
657                except Error:
658                    pass
659            result = _bootlocale.getpreferredencoding(False)
660            if do_setlocale:
661                setlocale(LC_CTYPE, oldloc)
662            return result
663
664
665### Database
666#
667# The following data was extracted from the locale.alias file which
668# comes with X11 and then hand edited removing the explicit encoding
669# definitions and adding some more aliases. The file is usually
670# available as /usr/lib/X11/locale/locale.alias.
671#
672
673#
674# The local_encoding_alias table maps lowercase encoding alias names
675# to C locale encoding names (case-sensitive). Note that normalize()
676# first looks up the encoding in the encodings.aliases dictionary and
677# then applies this mapping to find the correct C lib name for the
678# encoding.
679#
680locale_encoding_alias = {
681
682    # Mappings for non-standard encoding names used in locale names
683    '437':                          'C',
684    'c':                            'C',
685    'en':                           'ISO8859-1',
686    'jis':                          'JIS7',
687    'jis7':                         'JIS7',
688    'ajec':                         'eucJP',
689    'koi8c':                        'KOI8-C',
690    'microsoftcp1251':              'CP1251',
691    'microsoftcp1255':              'CP1255',
692    'microsoftcp1256':              'CP1256',
693    '88591':                        'ISO8859-1',
694    '88592':                        'ISO8859-2',
695    '88595':                        'ISO8859-5',
696    '885915':                       'ISO8859-15',
697
698    # Mappings from Python codec names to C lib encoding names
699    'ascii':                        'ISO8859-1',
700    'latin_1':                      'ISO8859-1',
701    'iso8859_1':                    'ISO8859-1',
702    'iso8859_10':                   'ISO8859-10',
703    'iso8859_11':                   'ISO8859-11',
704    'iso8859_13':                   'ISO8859-13',
705    'iso8859_14':                   'ISO8859-14',
706    'iso8859_15':                   'ISO8859-15',
707    'iso8859_16':                   'ISO8859-16',
708    'iso8859_2':                    'ISO8859-2',
709    'iso8859_3':                    'ISO8859-3',
710    'iso8859_4':                    'ISO8859-4',
711    'iso8859_5':                    'ISO8859-5',
712    'iso8859_6':                    'ISO8859-6',
713    'iso8859_7':                    'ISO8859-7',
714    'iso8859_8':                    'ISO8859-8',
715    'iso8859_9':                    'ISO8859-9',
716    'iso2022_jp':                   'JIS7',
717    'shift_jis':                    'SJIS',
718    'tactis':                       'TACTIS',
719    'euc_jp':                       'eucJP',
720    'euc_kr':                       'eucKR',
721    'utf_8':                        'UTF-8',
722    'koi8_r':                       'KOI8-R',
723    'koi8_t':                       'KOI8-T',
724    'koi8_u':                       'KOI8-U',
725    'kz1048':                       'RK1048',
726    'cp1251':                       'CP1251',
727    'cp1255':                       'CP1255',
728    'cp1256':                       'CP1256',
729
730    # XXX This list is still incomplete. If you know more
731    # mappings, please file a bug report. Thanks.
732}
733
734for k, v in sorted(locale_encoding_alias.items()):
735    k = k.replace('_', '')
736    locale_encoding_alias.setdefault(k, v)
737
738#
739# The locale_alias table maps lowercase alias names to C locale names
740# (case-sensitive). Encodings are always separated from the locale
741# name using a dot ('.'); they should only be given in case the
742# language name is needed to interpret the given encoding alias
743# correctly (CJK codes often have this need).
744#
745# Note that the normalize() function which uses this tables
746# removes '_' and '-' characters from the encoding part of the
747# locale name before doing the lookup. This saves a lot of
748# space in the table.
749#
750# MAL 2004-12-10:
751# Updated alias mapping to most recent locale.alias file
752# from X.org distribution using makelocalealias.py.
753#
754# These are the differences compared to the old mapping (Python 2.4
755# and older):
756#
757#    updated 'bg' -> 'bg_BG.ISO8859-5' to 'bg_BG.CP1251'
758#    updated 'bg_bg' -> 'bg_BG.ISO8859-5' to 'bg_BG.CP1251'
759#    updated 'bulgarian' -> 'bg_BG.ISO8859-5' to 'bg_BG.CP1251'
760#    updated 'cz' -> 'cz_CZ.ISO8859-2' to 'cs_CZ.ISO8859-2'
761#    updated 'cz_cz' -> 'cz_CZ.ISO8859-2' to 'cs_CZ.ISO8859-2'
762#    updated 'czech' -> 'cs_CS.ISO8859-2' to 'cs_CZ.ISO8859-2'
763#    updated 'dutch' -> 'nl_BE.ISO8859-1' to 'nl_NL.ISO8859-1'
764#    updated 'et' -> 'et_EE.ISO8859-4' to 'et_EE.ISO8859-15'
765#    updated 'et_ee' -> 'et_EE.ISO8859-4' to 'et_EE.ISO8859-15'
766#    updated 'fi' -> 'fi_FI.ISO8859-1' to 'fi_FI.ISO8859-15'
767#    updated 'fi_fi' -> 'fi_FI.ISO8859-1' to 'fi_FI.ISO8859-15'
768#    updated 'iw' -> 'iw_IL.ISO8859-8' to 'he_IL.ISO8859-8'
769#    updated 'iw_il' -> 'iw_IL.ISO8859-8' to 'he_IL.ISO8859-8'
770#    updated 'japanese' -> 'ja_JP.SJIS' to 'ja_JP.eucJP'
771#    updated 'lt' -> 'lt_LT.ISO8859-4' to 'lt_LT.ISO8859-13'
772#    updated 'lv' -> 'lv_LV.ISO8859-4' to 'lv_LV.ISO8859-13'
773#    updated 'sl' -> 'sl_CS.ISO8859-2' to 'sl_SI.ISO8859-2'
774#    updated 'slovene' -> 'sl_CS.ISO8859-2' to 'sl_SI.ISO8859-2'
775#    updated 'th_th' -> 'th_TH.TACTIS' to 'th_TH.ISO8859-11'
776#    updated 'zh_cn' -> 'zh_CN.eucCN' to 'zh_CN.gb2312'
777#    updated 'zh_cn.big5' -> 'zh_TW.eucTW' to 'zh_TW.big5'
778#    updated 'zh_tw' -> 'zh_TW.eucTW' to 'zh_TW.big5'
779#
780# MAL 2008-05-30:
781# Updated alias mapping to most recent locale.alias file
782# from X.org distribution using makelocalealias.py.
783#
784# These are the differences compared to the old mapping (Python 2.5
785# and older):
786#
787#    updated 'cs_cs.iso88592' -> 'cs_CZ.ISO8859-2' to 'cs_CS.ISO8859-2'
788#    updated 'serbocroatian' -> 'sh_YU.ISO8859-2' to 'sr_CS.ISO8859-2'
789#    updated 'sh' -> 'sh_YU.ISO8859-2' to 'sr_CS.ISO8859-2'
790#    updated 'sh_hr.iso88592' -> 'sh_HR.ISO8859-2' to 'hr_HR.ISO8859-2'
791#    updated 'sh_sp' -> 'sh_YU.ISO8859-2' to 'sr_CS.ISO8859-2'
792#    updated 'sh_yu' -> 'sh_YU.ISO8859-2' to 'sr_CS.ISO8859-2'
793#    updated 'sp' -> 'sp_YU.ISO8859-5' to 'sr_CS.ISO8859-5'
794#    updated 'sp_yu' -> 'sp_YU.ISO8859-5' to 'sr_CS.ISO8859-5'
795#    updated 'sr' -> 'sr_YU.ISO8859-5' to 'sr_CS.ISO8859-5'
796#    updated 'sr@cyrillic' -> 'sr_YU.ISO8859-5' to 'sr_CS.ISO8859-5'
797#    updated 'sr_sp' -> 'sr_SP.ISO8859-2' to 'sr_CS.ISO8859-2'
798#    updated 'sr_yu' -> 'sr_YU.ISO8859-5' to 'sr_CS.ISO8859-5'
799#    updated 'sr_yu.cp1251@cyrillic' -> 'sr_YU.CP1251' to 'sr_CS.CP1251'
800#    updated 'sr_yu.iso88592' -> 'sr_YU.ISO8859-2' to 'sr_CS.ISO8859-2'
801#    updated 'sr_yu.iso88595' -> 'sr_YU.ISO8859-5' to 'sr_CS.ISO8859-5'
802#    updated 'sr_yu.iso88595@cyrillic' -> 'sr_YU.ISO8859-5' to 'sr_CS.ISO8859-5'
803#    updated 'sr_yu.microsoftcp1251@cyrillic' -> 'sr_YU.CP1251' to 'sr_CS.CP1251'
804#    updated 'sr_yu.utf8@cyrillic' -> 'sr_YU.UTF-8' to 'sr_CS.UTF-8'
805#    updated 'sr_yu@cyrillic' -> 'sr_YU.ISO8859-5' to 'sr_CS.ISO8859-5'
806#
807# AP 2010-04-12:
808# Updated alias mapping to most recent locale.alias file
809# from X.org distribution using makelocalealias.py.
810#
811# These are the differences compared to the old mapping (Python 2.6.5
812# and older):
813#
814#    updated 'ru' -> 'ru_RU.ISO8859-5' to 'ru_RU.UTF-8'
815#    updated 'ru_ru' -> 'ru_RU.ISO8859-5' to 'ru_RU.UTF-8'
816#    updated 'serbocroatian' -> 'sr_CS.ISO8859-2' to 'sr_RS.UTF-8@latin'
817#    updated 'sh' -> 'sr_CS.ISO8859-2' to 'sr_RS.UTF-8@latin'
818#    updated 'sh_yu' -> 'sr_CS.ISO8859-2' to 'sr_RS.UTF-8@latin'
819#    updated 'sr' -> 'sr_CS.ISO8859-5' to 'sr_RS.UTF-8'
820#    updated 'sr@cyrillic' -> 'sr_CS.ISO8859-5' to 'sr_RS.UTF-8'
821#    updated 'sr@latn' -> 'sr_CS.ISO8859-2' to 'sr_RS.UTF-8@latin'
822#    updated 'sr_cs.utf8@latn' -> 'sr_CS.UTF-8' to 'sr_RS.UTF-8@latin'
823#    updated 'sr_cs@latn' -> 'sr_CS.ISO8859-2' to 'sr_RS.UTF-8@latin'
824#    updated 'sr_yu' -> 'sr_CS.ISO8859-5' to 'sr_RS.UTF-8@latin'
825#    updated 'sr_yu.utf8@cyrillic' -> 'sr_CS.UTF-8' to 'sr_RS.UTF-8'
826#    updated 'sr_yu@cyrillic' -> 'sr_CS.ISO8859-5' to 'sr_RS.UTF-8'
827#
828# SS 2013-12-20:
829# Updated alias mapping to most recent locale.alias file
830# from X.org distribution using makelocalealias.py.
831#
832# These are the differences compared to the old mapping (Python 3.3.3
833# and older):
834#
835#    updated 'a3' -> 'a3_AZ.KOI8-C' to 'az_AZ.KOI8-C'
836#    updated 'a3_az' -> 'a3_AZ.KOI8-C' to 'az_AZ.KOI8-C'
837#    updated 'a3_az.koi8c' -> 'a3_AZ.KOI8-C' to 'az_AZ.KOI8-C'
838#    updated 'cs_cs.iso88592' -> 'cs_CS.ISO8859-2' to 'cs_CZ.ISO8859-2'
839#    updated 'hebrew' -> 'iw_IL.ISO8859-8' to 'he_IL.ISO8859-8'
840#    updated 'hebrew.iso88598' -> 'iw_IL.ISO8859-8' to 'he_IL.ISO8859-8'
841#    updated 'sd' -> 'sd_IN@devanagari.UTF-8' to 'sd_IN.UTF-8'
842#    updated 'sr@latn' -> 'sr_RS.UTF-8@latin' to 'sr_CS.UTF-8@latin'
843#    updated 'sr_cs' -> 'sr_RS.UTF-8' to 'sr_CS.UTF-8'
844#    updated 'sr_cs.utf8@latn' -> 'sr_RS.UTF-8@latin' to 'sr_CS.UTF-8@latin'
845#    updated 'sr_cs@latn' -> 'sr_RS.UTF-8@latin' to 'sr_CS.UTF-8@latin'
846#
847# SS 2014-10-01:
848# Updated alias mapping with glibc 2.19 supported locales.
849#
850# SS 2018-05-05:
851# Updated alias mapping with glibc 2.27 supported locales.
852#
853# These are the differences compared to the old mapping (Python 3.6.5
854# and older):
855#
856#    updated 'ca_es@valencia' -> 'ca_ES.ISO8859-15@valencia' to 'ca_ES.UTF-8@valencia'
857#    updated 'kk_kz' -> 'kk_KZ.RK1048' to 'kk_KZ.ptcp154'
858#    updated 'russian' -> 'ru_RU.ISO8859-5' to 'ru_RU.KOI8-R'
859
860locale_alias = {
861    'a3':                                   'az_AZ.KOI8-C',
862    'a3_az':                                'az_AZ.KOI8-C',
863    'a3_az.koic':                           'az_AZ.KOI8-C',
864    'aa_dj':                                'aa_DJ.ISO8859-1',
865    'aa_er':                                'aa_ER.UTF-8',
866    'aa_et':                                'aa_ET.UTF-8',
867    'af':                                   'af_ZA.ISO8859-1',
868    'af_za':                                'af_ZA.ISO8859-1',
869    'agr_pe':                               'agr_PE.UTF-8',
870    'ak_gh':                                'ak_GH.UTF-8',
871    'am':                                   'am_ET.UTF-8',
872    'am_et':                                'am_ET.UTF-8',
873    'american':                             'en_US.ISO8859-1',
874    'an_es':                                'an_ES.ISO8859-15',
875    'anp_in':                               'anp_IN.UTF-8',
876    'ar':                                   'ar_AA.ISO8859-6',
877    'ar_aa':                                'ar_AA.ISO8859-6',
878    'ar_ae':                                'ar_AE.ISO8859-6',
879    'ar_bh':                                'ar_BH.ISO8859-6',
880    'ar_dz':                                'ar_DZ.ISO8859-6',
881    'ar_eg':                                'ar_EG.ISO8859-6',
882    'ar_in':                                'ar_IN.UTF-8',
883    'ar_iq':                                'ar_IQ.ISO8859-6',
884    'ar_jo':                                'ar_JO.ISO8859-6',
885    'ar_kw':                                'ar_KW.ISO8859-6',
886    'ar_lb':                                'ar_LB.ISO8859-6',
887    'ar_ly':                                'ar_LY.ISO8859-6',
888    'ar_ma':                                'ar_MA.ISO8859-6',
889    'ar_om':                                'ar_OM.ISO8859-6',
890    'ar_qa':                                'ar_QA.ISO8859-6',
891    'ar_sa':                                'ar_SA.ISO8859-6',
892    'ar_sd':                                'ar_SD.ISO8859-6',
893    'ar_ss':                                'ar_SS.UTF-8',
894    'ar_sy':                                'ar_SY.ISO8859-6',
895    'ar_tn':                                'ar_TN.ISO8859-6',
896    'ar_ye':                                'ar_YE.ISO8859-6',
897    'arabic':                               'ar_AA.ISO8859-6',
898    'as':                                   'as_IN.UTF-8',
899    'as_in':                                'as_IN.UTF-8',
900    'ast_es':                               'ast_ES.ISO8859-15',
901    'ayc_pe':                               'ayc_PE.UTF-8',
902    'az':                                   'az_AZ.ISO8859-9E',
903    'az_az':                                'az_AZ.ISO8859-9E',
904    'az_az.iso88599e':                      'az_AZ.ISO8859-9E',
905    'az_ir':                                'az_IR.UTF-8',
906    'be':                                   'be_BY.CP1251',
907    'be@latin':                             'be_BY.UTF-8@latin',
908    'be_bg.utf8':                           'bg_BG.UTF-8',
909    'be_by':                                'be_BY.CP1251',
910    'be_by@latin':                          'be_BY.UTF-8@latin',
911    'bem_zm':                               'bem_ZM.UTF-8',
912    'ber_dz':                               'ber_DZ.UTF-8',
913    'ber_ma':                               'ber_MA.UTF-8',
914    'bg':                                   'bg_BG.CP1251',
915    'bg_bg':                                'bg_BG.CP1251',
916    'bhb_in.utf8':                          'bhb_IN.UTF-8',
917    'bho_in':                               'bho_IN.UTF-8',
918    'bho_np':                               'bho_NP.UTF-8',
919    'bi_vu':                                'bi_VU.UTF-8',
920    'bn_bd':                                'bn_BD.UTF-8',
921    'bn_in':                                'bn_IN.UTF-8',
922    'bo_cn':                                'bo_CN.UTF-8',
923    'bo_in':                                'bo_IN.UTF-8',
924    'bokmal':                               'nb_NO.ISO8859-1',
925    'bokm\xe5l':                            'nb_NO.ISO8859-1',
926    'br':                                   'br_FR.ISO8859-1',
927    'br_fr':                                'br_FR.ISO8859-1',
928    'brx_in':                               'brx_IN.UTF-8',
929    'bs':                                   'bs_BA.ISO8859-2',
930    'bs_ba':                                'bs_BA.ISO8859-2',
931    'bulgarian':                            'bg_BG.CP1251',
932    'byn_er':                               'byn_ER.UTF-8',
933    'c':                                    'C',
934    'c-french':                             'fr_CA.ISO8859-1',
935    'c.ascii':                              'C',
936    'c.en':                                 'C',
937    'c.iso88591':                           'en_US.ISO8859-1',
938    'c.utf8':                               'en_US.UTF-8',
939    'c_c':                                  'C',
940    'c_c.c':                                'C',
941    'ca':                                   'ca_ES.ISO8859-1',
942    'ca_ad':                                'ca_AD.ISO8859-1',
943    'ca_es':                                'ca_ES.ISO8859-1',
944    'ca_es@valencia':                       'ca_ES.UTF-8@valencia',
945    'ca_fr':                                'ca_FR.ISO8859-1',
946    'ca_it':                                'ca_IT.ISO8859-1',
947    'catalan':                              'ca_ES.ISO8859-1',
948    'ce_ru':                                'ce_RU.UTF-8',
949    'cextend':                              'en_US.ISO8859-1',
950    'chinese-s':                            'zh_CN.eucCN',
951    'chinese-t':                            'zh_TW.eucTW',
952    'chr_us':                               'chr_US.UTF-8',
953    'ckb_iq':                               'ckb_IQ.UTF-8',
954    'cmn_tw':                               'cmn_TW.UTF-8',
955    'crh_ua':                               'crh_UA.UTF-8',
956    'croatian':                             'hr_HR.ISO8859-2',
957    'cs':                                   'cs_CZ.ISO8859-2',
958    'cs_cs':                                'cs_CZ.ISO8859-2',
959    'cs_cz':                                'cs_CZ.ISO8859-2',
960    'csb_pl':                               'csb_PL.UTF-8',
961    'cv_ru':                                'cv_RU.UTF-8',
962    'cy':                                   'cy_GB.ISO8859-1',
963    'cy_gb':                                'cy_GB.ISO8859-1',
964    'cz':                                   'cs_CZ.ISO8859-2',
965    'cz_cz':                                'cs_CZ.ISO8859-2',
966    'czech':                                'cs_CZ.ISO8859-2',
967    'da':                                   'da_DK.ISO8859-1',
968    'da_dk':                                'da_DK.ISO8859-1',
969    'danish':                               'da_DK.ISO8859-1',
970    'dansk':                                'da_DK.ISO8859-1',
971    'de':                                   'de_DE.ISO8859-1',
972    'de_at':                                'de_AT.ISO8859-1',
973    'de_be':                                'de_BE.ISO8859-1',
974    'de_ch':                                'de_CH.ISO8859-1',
975    'de_de':                                'de_DE.ISO8859-1',
976    'de_it':                                'de_IT.ISO8859-1',
977    'de_li.utf8':                           'de_LI.UTF-8',
978    'de_lu':                                'de_LU.ISO8859-1',
979    'deutsch':                              'de_DE.ISO8859-1',
980    'doi_in':                               'doi_IN.UTF-8',
981    'dutch':                                'nl_NL.ISO8859-1',
982    'dutch.iso88591':                       'nl_BE.ISO8859-1',
983    'dv_mv':                                'dv_MV.UTF-8',
984    'dz_bt':                                'dz_BT.UTF-8',
985    'ee':                                   'ee_EE.ISO8859-4',
986    'ee_ee':                                'ee_EE.ISO8859-4',
987    'eesti':                                'et_EE.ISO8859-1',
988    'el':                                   'el_GR.ISO8859-7',
989    'el_cy':                                'el_CY.ISO8859-7',
990    'el_gr':                                'el_GR.ISO8859-7',
991    'el_gr@euro':                           'el_GR.ISO8859-15',
992    'en':                                   'en_US.ISO8859-1',
993    'en_ag':                                'en_AG.UTF-8',
994    'en_au':                                'en_AU.ISO8859-1',
995    'en_be':                                'en_BE.ISO8859-1',
996    'en_bw':                                'en_BW.ISO8859-1',
997    'en_ca':                                'en_CA.ISO8859-1',
998    'en_dk':                                'en_DK.ISO8859-1',
999    'en_dl.utf8':                           'en_DL.UTF-8',
1000    'en_gb':                                'en_GB.ISO8859-1',
1001    'en_hk':                                'en_HK.ISO8859-1',
1002    'en_ie':                                'en_IE.ISO8859-1',
1003    'en_il':                                'en_IL.UTF-8',
1004    'en_in':                                'en_IN.ISO8859-1',
1005    'en_ng':                                'en_NG.UTF-8',
1006    'en_nz':                                'en_NZ.ISO8859-1',
1007    'en_ph':                                'en_PH.ISO8859-1',
1008    'en_sc.utf8':                           'en_SC.UTF-8',
1009    'en_sg':                                'en_SG.ISO8859-1',
1010    'en_uk':                                'en_GB.ISO8859-1',
1011    'en_us':                                'en_US.ISO8859-1',
1012    'en_us@euro@euro':                      'en_US.ISO8859-15',
1013    'en_za':                                'en_ZA.ISO8859-1',
1014    'en_zm':                                'en_ZM.UTF-8',
1015    'en_zw':                                'en_ZW.ISO8859-1',
1016    'en_zw.utf8':                           'en_ZS.UTF-8',
1017    'eng_gb':                               'en_GB.ISO8859-1',
1018    'english':                              'en_EN.ISO8859-1',
1019    'english.iso88591':                     'en_US.ISO8859-1',
1020    'english_uk':                           'en_GB.ISO8859-1',
1021    'english_united-states':                'en_US.ISO8859-1',
1022    'english_united-states.437':            'C',
1023    'english_us':                           'en_US.ISO8859-1',
1024    'eo':                                   'eo_XX.ISO8859-3',
1025    'eo.utf8':                              'eo.UTF-8',
1026    'eo_eo':                                'eo_EO.ISO8859-3',
1027    'eo_us.utf8':                           'eo_US.UTF-8',
1028    'eo_xx':                                'eo_XX.ISO8859-3',
1029    'es':                                   'es_ES.ISO8859-1',
1030    'es_ar':                                'es_AR.ISO8859-1',
1031    'es_bo':                                'es_BO.ISO8859-1',
1032    'es_cl':                                'es_CL.ISO8859-1',
1033    'es_co':                                'es_CO.ISO8859-1',
1034    'es_cr':                                'es_CR.ISO8859-1',
1035    'es_cu':                                'es_CU.UTF-8',
1036    'es_do':                                'es_DO.ISO8859-1',
1037    'es_ec':                                'es_EC.ISO8859-1',
1038    'es_es':                                'es_ES.ISO8859-1',
1039    'es_gt':                                'es_GT.ISO8859-1',
1040    'es_hn':                                'es_HN.ISO8859-1',
1041    'es_mx':                                'es_MX.ISO8859-1',
1042    'es_ni':                                'es_NI.ISO8859-1',
1043    'es_pa':                                'es_PA.ISO8859-1',
1044    'es_pe':                                'es_PE.ISO8859-1',
1045    'es_pr':                                'es_PR.ISO8859-1',
1046    'es_py':                                'es_PY.ISO8859-1',
1047    'es_sv':                                'es_SV.ISO8859-1',
1048    'es_us':                                'es_US.ISO8859-1',
1049    'es_uy':                                'es_UY.ISO8859-1',
1050    'es_ve':                                'es_VE.ISO8859-1',
1051    'estonian':                             'et_EE.ISO8859-1',
1052    'et':                                   'et_EE.ISO8859-15',
1053    'et_ee':                                'et_EE.ISO8859-15',
1054    'eu':                                   'eu_ES.ISO8859-1',
1055    'eu_es':                                'eu_ES.ISO8859-1',
1056    'eu_fr':                                'eu_FR.ISO8859-1',
1057    'fa':                                   'fa_IR.UTF-8',
1058    'fa_ir':                                'fa_IR.UTF-8',
1059    'fa_ir.isiri3342':                      'fa_IR.ISIRI-3342',
1060    'ff_sn':                                'ff_SN.UTF-8',
1061    'fi':                                   'fi_FI.ISO8859-15',
1062    'fi_fi':                                'fi_FI.ISO8859-15',
1063    'fil_ph':                               'fil_PH.UTF-8',
1064    'finnish':                              'fi_FI.ISO8859-1',
1065    'fo':                                   'fo_FO.ISO8859-1',
1066    'fo_fo':                                'fo_FO.ISO8859-1',
1067    'fr':                                   'fr_FR.ISO8859-1',
1068    'fr_be':                                'fr_BE.ISO8859-1',
1069    'fr_ca':                                'fr_CA.ISO8859-1',
1070    'fr_ch':                                'fr_CH.ISO8859-1',
1071    'fr_fr':                                'fr_FR.ISO8859-1',
1072    'fr_lu':                                'fr_LU.ISO8859-1',
1073    'fran\xe7ais':                          'fr_FR.ISO8859-1',
1074    'fre_fr':                               'fr_FR.ISO8859-1',
1075    'french':                               'fr_FR.ISO8859-1',
1076    'french.iso88591':                      'fr_CH.ISO8859-1',
1077    'french_france':                        'fr_FR.ISO8859-1',
1078    'fur_it':                               'fur_IT.UTF-8',
1079    'fy_de':                                'fy_DE.UTF-8',
1080    'fy_nl':                                'fy_NL.UTF-8',
1081    'ga':                                   'ga_IE.ISO8859-1',
1082    'ga_ie':                                'ga_IE.ISO8859-1',
1083    'galego':                               'gl_ES.ISO8859-1',
1084    'galician':                             'gl_ES.ISO8859-1',
1085    'gd':                                   'gd_GB.ISO8859-1',
1086    'gd_gb':                                'gd_GB.ISO8859-1',
1087    'ger_de':                               'de_DE.ISO8859-1',
1088    'german':                               'de_DE.ISO8859-1',
1089    'german.iso88591':                      'de_CH.ISO8859-1',
1090    'german_germany':                       'de_DE.ISO8859-1',
1091    'gez_er':                               'gez_ER.UTF-8',
1092    'gez_et':                               'gez_ET.UTF-8',
1093    'gl':                                   'gl_ES.ISO8859-1',
1094    'gl_es':                                'gl_ES.ISO8859-1',
1095    'greek':                                'el_GR.ISO8859-7',
1096    'gu_in':                                'gu_IN.UTF-8',
1097    'gv':                                   'gv_GB.ISO8859-1',
1098    'gv_gb':                                'gv_GB.ISO8859-1',
1099    'ha_ng':                                'ha_NG.UTF-8',
1100    'hak_tw':                               'hak_TW.UTF-8',
1101    'he':                                   'he_IL.ISO8859-8',
1102    'he_il':                                'he_IL.ISO8859-8',
1103    'hebrew':                               'he_IL.ISO8859-8',
1104    'hi':                                   'hi_IN.ISCII-DEV',
1105    'hi_in':                                'hi_IN.ISCII-DEV',
1106    'hi_in.isciidev':                       'hi_IN.ISCII-DEV',
1107    'hif_fj':                               'hif_FJ.UTF-8',
1108    'hne':                                  'hne_IN.UTF-8',
1109    'hne_in':                               'hne_IN.UTF-8',
1110    'hr':                                   'hr_HR.ISO8859-2',
1111    'hr_hr':                                'hr_HR.ISO8859-2',
1112    'hrvatski':                             'hr_HR.ISO8859-2',
1113    'hsb_de':                               'hsb_DE.ISO8859-2',
1114    'ht_ht':                                'ht_HT.UTF-8',
1115    'hu':                                   'hu_HU.ISO8859-2',
1116    'hu_hu':                                'hu_HU.ISO8859-2',
1117    'hungarian':                            'hu_HU.ISO8859-2',
1118    'hy_am':                                'hy_AM.UTF-8',
1119    'hy_am.armscii8':                       'hy_AM.ARMSCII_8',
1120    'ia':                                   'ia.UTF-8',
1121    'ia_fr':                                'ia_FR.UTF-8',
1122    'icelandic':                            'is_IS.ISO8859-1',
1123    'id':                                   'id_ID.ISO8859-1',
1124    'id_id':                                'id_ID.ISO8859-1',
1125    'ig_ng':                                'ig_NG.UTF-8',
1126    'ik_ca':                                'ik_CA.UTF-8',
1127    'in':                                   'id_ID.ISO8859-1',
1128    'in_id':                                'id_ID.ISO8859-1',
1129    'is':                                   'is_IS.ISO8859-1',
1130    'is_is':                                'is_IS.ISO8859-1',
1131    'iso-8859-1':                           'en_US.ISO8859-1',
1132    'iso-8859-15':                          'en_US.ISO8859-15',
1133    'iso8859-1':                            'en_US.ISO8859-1',
1134    'iso8859-15':                           'en_US.ISO8859-15',
1135    'iso_8859_1':                           'en_US.ISO8859-1',
1136    'iso_8859_15':                          'en_US.ISO8859-15',
1137    'it':                                   'it_IT.ISO8859-1',
1138    'it_ch':                                'it_CH.ISO8859-1',
1139    'it_it':                                'it_IT.ISO8859-1',
1140    'italian':                              'it_IT.ISO8859-1',
1141    'iu':                                   'iu_CA.NUNACOM-8',
1142    'iu_ca':                                'iu_CA.NUNACOM-8',
1143    'iu_ca.nunacom8':                       'iu_CA.NUNACOM-8',
1144    'iw':                                   'he_IL.ISO8859-8',
1145    'iw_il':                                'he_IL.ISO8859-8',
1146    'iw_il.utf8':                           'iw_IL.UTF-8',
1147    'ja':                                   'ja_JP.eucJP',
1148    'ja_jp':                                'ja_JP.eucJP',
1149    'ja_jp.euc':                            'ja_JP.eucJP',
1150    'ja_jp.mscode':                         'ja_JP.SJIS',
1151    'ja_jp.pck':                            'ja_JP.SJIS',
1152    'japan':                                'ja_JP.eucJP',
1153    'japanese':                             'ja_JP.eucJP',
1154    'japanese-euc':                         'ja_JP.eucJP',
1155    'japanese.euc':                         'ja_JP.eucJP',
1156    'jp_jp':                                'ja_JP.eucJP',
1157    'ka':                                   'ka_GE.GEORGIAN-ACADEMY',
1158    'ka_ge':                                'ka_GE.GEORGIAN-ACADEMY',
1159    'ka_ge.georgianacademy':                'ka_GE.GEORGIAN-ACADEMY',
1160    'ka_ge.georgianps':                     'ka_GE.GEORGIAN-PS',
1161    'ka_ge.georgianrs':                     'ka_GE.GEORGIAN-ACADEMY',
1162    'kab_dz':                               'kab_DZ.UTF-8',
1163    'kk_kz':                                'kk_KZ.ptcp154',
1164    'kl':                                   'kl_GL.ISO8859-1',
1165    'kl_gl':                                'kl_GL.ISO8859-1',
1166    'km_kh':                                'km_KH.UTF-8',
1167    'kn':                                   'kn_IN.UTF-8',
1168    'kn_in':                                'kn_IN.UTF-8',
1169    'ko':                                   'ko_KR.eucKR',
1170    'ko_kr':                                'ko_KR.eucKR',
1171    'ko_kr.euc':                            'ko_KR.eucKR',
1172    'kok_in':                               'kok_IN.UTF-8',
1173    'korean':                               'ko_KR.eucKR',
1174    'korean.euc':                           'ko_KR.eucKR',
1175    'ks':                                   'ks_IN.UTF-8',
1176    'ks_in':                                'ks_IN.UTF-8',
1177    'ks_in@devanagari.utf8':                'ks_IN.UTF-8@devanagari',
1178    'ku_tr':                                'ku_TR.ISO8859-9',
1179    'kw':                                   'kw_GB.ISO8859-1',
1180    'kw_gb':                                'kw_GB.ISO8859-1',
1181    'ky':                                   'ky_KG.UTF-8',
1182    'ky_kg':                                'ky_KG.UTF-8',
1183    'lb_lu':                                'lb_LU.UTF-8',
1184    'lg_ug':                                'lg_UG.ISO8859-10',
1185    'li_be':                                'li_BE.UTF-8',
1186    'li_nl':                                'li_NL.UTF-8',
1187    'lij_it':                               'lij_IT.UTF-8',
1188    'lithuanian':                           'lt_LT.ISO8859-13',
1189    'ln_cd':                                'ln_CD.UTF-8',
1190    'lo':                                   'lo_LA.MULELAO-1',
1191    'lo_la':                                'lo_LA.MULELAO-1',
1192    'lo_la.cp1133':                         'lo_LA.IBM-CP1133',
1193    'lo_la.ibmcp1133':                      'lo_LA.IBM-CP1133',
1194    'lo_la.mulelao1':                       'lo_LA.MULELAO-1',
1195    'lt':                                   'lt_LT.ISO8859-13',
1196    'lt_lt':                                'lt_LT.ISO8859-13',
1197    'lv':                                   'lv_LV.ISO8859-13',
1198    'lv_lv':                                'lv_LV.ISO8859-13',
1199    'lzh_tw':                               'lzh_TW.UTF-8',
1200    'mag_in':                               'mag_IN.UTF-8',
1201    'mai':                                  'mai_IN.UTF-8',
1202    'mai_in':                               'mai_IN.UTF-8',
1203    'mai_np':                               'mai_NP.UTF-8',
1204    'mfe_mu':                               'mfe_MU.UTF-8',
1205    'mg_mg':                                'mg_MG.ISO8859-15',
1206    'mhr_ru':                               'mhr_RU.UTF-8',
1207    'mi':                                   'mi_NZ.ISO8859-1',
1208    'mi_nz':                                'mi_NZ.ISO8859-1',
1209    'miq_ni':                               'miq_NI.UTF-8',
1210    'mjw_in':                               'mjw_IN.UTF-8',
1211    'mk':                                   'mk_MK.ISO8859-5',
1212    'mk_mk':                                'mk_MK.ISO8859-5',
1213    'ml':                                   'ml_IN.UTF-8',
1214    'ml_in':                                'ml_IN.UTF-8',
1215    'mn_mn':                                'mn_MN.UTF-8',
1216    'mni_in':                               'mni_IN.UTF-8',
1217    'mr':                                   'mr_IN.UTF-8',
1218    'mr_in':                                'mr_IN.UTF-8',
1219    'ms':                                   'ms_MY.ISO8859-1',
1220    'ms_my':                                'ms_MY.ISO8859-1',
1221    'mt':                                   'mt_MT.ISO8859-3',
1222    'mt_mt':                                'mt_MT.ISO8859-3',
1223    'my_mm':                                'my_MM.UTF-8',
1224    'nan_tw':                               'nan_TW.UTF-8',
1225    'nb':                                   'nb_NO.ISO8859-1',
1226    'nb_no':                                'nb_NO.ISO8859-1',
1227    'nds_de':                               'nds_DE.UTF-8',
1228    'nds_nl':                               'nds_NL.UTF-8',
1229    'ne_np':                                'ne_NP.UTF-8',
1230    'nhn_mx':                               'nhn_MX.UTF-8',
1231    'niu_nu':                               'niu_NU.UTF-8',
1232    'niu_nz':                               'niu_NZ.UTF-8',
1233    'nl':                                   'nl_NL.ISO8859-1',
1234    'nl_aw':                                'nl_AW.UTF-8',
1235    'nl_be':                                'nl_BE.ISO8859-1',
1236    'nl_nl':                                'nl_NL.ISO8859-1',
1237    'nn':                                   'nn_NO.ISO8859-1',
1238    'nn_no':                                'nn_NO.ISO8859-1',
1239    'no':                                   'no_NO.ISO8859-1',
1240    'no@nynorsk':                           'ny_NO.ISO8859-1',
1241    'no_no':                                'no_NO.ISO8859-1',
1242    'no_no.iso88591@bokmal':                'no_NO.ISO8859-1',
1243    'no_no.iso88591@nynorsk':               'no_NO.ISO8859-1',
1244    'norwegian':                            'no_NO.ISO8859-1',
1245    'nr':                                   'nr_ZA.ISO8859-1',
1246    'nr_za':                                'nr_ZA.ISO8859-1',
1247    'nso':                                  'nso_ZA.ISO8859-15',
1248    'nso_za':                               'nso_ZA.ISO8859-15',
1249    'ny':                                   'ny_NO.ISO8859-1',
1250    'ny_no':                                'ny_NO.ISO8859-1',
1251    'nynorsk':                              'nn_NO.ISO8859-1',
1252    'oc':                                   'oc_FR.ISO8859-1',
1253    'oc_fr':                                'oc_FR.ISO8859-1',
1254    'om_et':                                'om_ET.UTF-8',
1255    'om_ke':                                'om_KE.ISO8859-1',
1256    'or':                                   'or_IN.UTF-8',
1257    'or_in':                                'or_IN.UTF-8',
1258    'os_ru':                                'os_RU.UTF-8',
1259    'pa':                                   'pa_IN.UTF-8',
1260    'pa_in':                                'pa_IN.UTF-8',
1261    'pa_pk':                                'pa_PK.UTF-8',
1262    'pap_an':                               'pap_AN.UTF-8',
1263    'pap_aw':                               'pap_AW.UTF-8',
1264    'pap_cw':                               'pap_CW.UTF-8',
1265    'pd':                                   'pd_US.ISO8859-1',
1266    'pd_de':                                'pd_DE.ISO8859-1',
1267    'pd_us':                                'pd_US.ISO8859-1',
1268    'ph':                                   'ph_PH.ISO8859-1',
1269    'ph_ph':                                'ph_PH.ISO8859-1',
1270    'pl':                                   'pl_PL.ISO8859-2',
1271    'pl_pl':                                'pl_PL.ISO8859-2',
1272    'polish':                               'pl_PL.ISO8859-2',
1273    'portuguese':                           'pt_PT.ISO8859-1',
1274    'portuguese_brazil':                    'pt_BR.ISO8859-1',
1275    'posix':                                'C',
1276    'posix-utf2':                           'C',
1277    'pp':                                   'pp_AN.ISO8859-1',
1278    'pp_an':                                'pp_AN.ISO8859-1',
1279    'ps_af':                                'ps_AF.UTF-8',
1280    'pt':                                   'pt_PT.ISO8859-1',
1281    'pt_br':                                'pt_BR.ISO8859-1',
1282    'pt_pt':                                'pt_PT.ISO8859-1',
1283    'quz_pe':                               'quz_PE.UTF-8',
1284    'raj_in':                               'raj_IN.UTF-8',
1285    'ro':                                   'ro_RO.ISO8859-2',
1286    'ro_ro':                                'ro_RO.ISO8859-2',
1287    'romanian':                             'ro_RO.ISO8859-2',
1288    'ru':                                   'ru_RU.UTF-8',
1289    'ru_ru':                                'ru_RU.UTF-8',
1290    'ru_ua':                                'ru_UA.KOI8-U',
1291    'rumanian':                             'ro_RO.ISO8859-2',
1292    'russian':                              'ru_RU.KOI8-R',
1293    'rw':                                   'rw_RW.ISO8859-1',
1294    'rw_rw':                                'rw_RW.ISO8859-1',
1295    'sa_in':                                'sa_IN.UTF-8',
1296    'sat_in':                               'sat_IN.UTF-8',
1297    'sc_it':                                'sc_IT.UTF-8',
1298    'sd':                                   'sd_IN.UTF-8',
1299    'sd_in':                                'sd_IN.UTF-8',
1300    'sd_in@devanagari.utf8':                'sd_IN.UTF-8@devanagari',
1301    'sd_pk':                                'sd_PK.UTF-8',
1302    'se_no':                                'se_NO.UTF-8',
1303    'serbocroatian':                        'sr_RS.UTF-8@latin',
1304    'sgs_lt':                               'sgs_LT.UTF-8',
1305    'sh':                                   'sr_RS.UTF-8@latin',
1306    'sh_ba.iso88592@bosnia':                'sr_CS.ISO8859-2',
1307    'sh_hr':                                'sh_HR.ISO8859-2',
1308    'sh_hr.iso88592':                       'hr_HR.ISO8859-2',
1309    'sh_sp':                                'sr_CS.ISO8859-2',
1310    'sh_yu':                                'sr_RS.UTF-8@latin',
1311    'shn_mm':                               'shn_MM.UTF-8',
1312    'shs_ca':                               'shs_CA.UTF-8',
1313    'si':                                   'si_LK.UTF-8',
1314    'si_lk':                                'si_LK.UTF-8',
1315    'sid_et':                               'sid_ET.UTF-8',
1316    'sinhala':                              'si_LK.UTF-8',
1317    'sk':                                   'sk_SK.ISO8859-2',
1318    'sk_sk':                                'sk_SK.ISO8859-2',
1319    'sl':                                   'sl_SI.ISO8859-2',
1320    'sl_cs':                                'sl_CS.ISO8859-2',
1321    'sl_si':                                'sl_SI.ISO8859-2',
1322    'slovak':                               'sk_SK.ISO8859-2',
1323    'slovene':                              'sl_SI.ISO8859-2',
1324    'slovenian':                            'sl_SI.ISO8859-2',
1325    'sm_ws':                                'sm_WS.UTF-8',
1326    'so_dj':                                'so_DJ.ISO8859-1',
1327    'so_et':                                'so_ET.UTF-8',
1328    'so_ke':                                'so_KE.ISO8859-1',
1329    'so_so':                                'so_SO.ISO8859-1',
1330    'sp':                                   'sr_CS.ISO8859-5',
1331    'sp_yu':                                'sr_CS.ISO8859-5',
1332    'spanish':                              'es_ES.ISO8859-1',
1333    'spanish_spain':                        'es_ES.ISO8859-1',
1334    'sq':                                   'sq_AL.ISO8859-2',
1335    'sq_al':                                'sq_AL.ISO8859-2',
1336    'sq_mk':                                'sq_MK.UTF-8',
1337    'sr':                                   'sr_RS.UTF-8',
1338    'sr@cyrillic':                          'sr_RS.UTF-8',
1339    'sr@latn':                              'sr_CS.UTF-8@latin',
1340    'sr_cs':                                'sr_CS.UTF-8',
1341    'sr_cs.iso88592@latn':                  'sr_CS.ISO8859-2',
1342    'sr_cs@latn':                           'sr_CS.UTF-8@latin',
1343    'sr_me':                                'sr_ME.UTF-8',
1344    'sr_rs':                                'sr_RS.UTF-8',
1345    'sr_rs@latn':                           'sr_RS.UTF-8@latin',
1346    'sr_sp':                                'sr_CS.ISO8859-2',
1347    'sr_yu':                                'sr_RS.UTF-8@latin',
1348    'sr_yu.cp1251@cyrillic':                'sr_CS.CP1251',
1349    'sr_yu.iso88592':                       'sr_CS.ISO8859-2',
1350    'sr_yu.iso88595':                       'sr_CS.ISO8859-5',
1351    'sr_yu.iso88595@cyrillic':              'sr_CS.ISO8859-5',
1352    'sr_yu.microsoftcp1251@cyrillic':       'sr_CS.CP1251',
1353    'sr_yu.utf8':                           'sr_RS.UTF-8',
1354    'sr_yu.utf8@cyrillic':                  'sr_RS.UTF-8',
1355    'sr_yu@cyrillic':                       'sr_RS.UTF-8',
1356    'ss':                                   'ss_ZA.ISO8859-1',
1357    'ss_za':                                'ss_ZA.ISO8859-1',
1358    'st':                                   'st_ZA.ISO8859-1',
1359    'st_za':                                'st_ZA.ISO8859-1',
1360    'sv':                                   'sv_SE.ISO8859-1',
1361    'sv_fi':                                'sv_FI.ISO8859-1',
1362    'sv_se':                                'sv_SE.ISO8859-1',
1363    'sw_ke':                                'sw_KE.UTF-8',
1364    'sw_tz':                                'sw_TZ.UTF-8',
1365    'swedish':                              'sv_SE.ISO8859-1',
1366    'szl_pl':                               'szl_PL.UTF-8',
1367    'ta':                                   'ta_IN.TSCII-0',
1368    'ta_in':                                'ta_IN.TSCII-0',
1369    'ta_in.tscii':                          'ta_IN.TSCII-0',
1370    'ta_in.tscii0':                         'ta_IN.TSCII-0',
1371    'ta_lk':                                'ta_LK.UTF-8',
1372    'tcy_in.utf8':                          'tcy_IN.UTF-8',
1373    'te':                                   'te_IN.UTF-8',
1374    'te_in':                                'te_IN.UTF-8',
1375    'tg':                                   'tg_TJ.KOI8-C',
1376    'tg_tj':                                'tg_TJ.KOI8-C',
1377    'th':                                   'th_TH.ISO8859-11',
1378    'th_th':                                'th_TH.ISO8859-11',
1379    'th_th.tactis':                         'th_TH.TIS620',
1380    'th_th.tis620':                         'th_TH.TIS620',
1381    'thai':                                 'th_TH.ISO8859-11',
1382    'the_np':                               'the_NP.UTF-8',
1383    'ti_er':                                'ti_ER.UTF-8',
1384    'ti_et':                                'ti_ET.UTF-8',
1385    'tig_er':                               'tig_ER.UTF-8',
1386    'tk_tm':                                'tk_TM.UTF-8',
1387    'tl':                                   'tl_PH.ISO8859-1',
1388    'tl_ph':                                'tl_PH.ISO8859-1',
1389    'tn':                                   'tn_ZA.ISO8859-15',
1390    'tn_za':                                'tn_ZA.ISO8859-15',
1391    'to_to':                                'to_TO.UTF-8',
1392    'tpi_pg':                               'tpi_PG.UTF-8',
1393    'tr':                                   'tr_TR.ISO8859-9',
1394    'tr_cy':                                'tr_CY.ISO8859-9',
1395    'tr_tr':                                'tr_TR.ISO8859-9',
1396    'ts':                                   'ts_ZA.ISO8859-1',
1397    'ts_za':                                'ts_ZA.ISO8859-1',
1398    'tt':                                   'tt_RU.TATAR-CYR',
1399    'tt_ru':                                'tt_RU.TATAR-CYR',
1400    'tt_ru.tatarcyr':                       'tt_RU.TATAR-CYR',
1401    'tt_ru@iqtelif':                        'tt_RU.UTF-8@iqtelif',
1402    'turkish':                              'tr_TR.ISO8859-9',
1403    'ug_cn':                                'ug_CN.UTF-8',
1404    'uk':                                   'uk_UA.KOI8-U',
1405    'uk_ua':                                'uk_UA.KOI8-U',
1406    'univ':                                 'en_US.utf',
1407    'universal':                            'en_US.utf',
1408    'universal.utf8@ucs4':                  'en_US.UTF-8',
1409    'unm_us':                               'unm_US.UTF-8',
1410    'ur':                                   'ur_PK.CP1256',
1411    'ur_in':                                'ur_IN.UTF-8',
1412    'ur_pk':                                'ur_PK.CP1256',
1413    'uz':                                   'uz_UZ.UTF-8',
1414    'uz_uz':                                'uz_UZ.UTF-8',
1415    'uz_uz@cyrillic':                       'uz_UZ.UTF-8',
1416    've':                                   've_ZA.UTF-8',
1417    've_za':                                've_ZA.UTF-8',
1418    'vi':                                   'vi_VN.TCVN',
1419    'vi_vn':                                'vi_VN.TCVN',
1420    'vi_vn.tcvn':                           'vi_VN.TCVN',
1421    'vi_vn.tcvn5712':                       'vi_VN.TCVN',
1422    'vi_vn.viscii':                         'vi_VN.VISCII',
1423    'vi_vn.viscii111':                      'vi_VN.VISCII',
1424    'wa':                                   'wa_BE.ISO8859-1',
1425    'wa_be':                                'wa_BE.ISO8859-1',
1426    'wae_ch':                               'wae_CH.UTF-8',
1427    'wal_et':                               'wal_ET.UTF-8',
1428    'wo_sn':                                'wo_SN.UTF-8',
1429    'xh':                                   'xh_ZA.ISO8859-1',
1430    'xh_za':                                'xh_ZA.ISO8859-1',
1431    'yi':                                   'yi_US.CP1255',
1432    'yi_us':                                'yi_US.CP1255',
1433    'yo_ng':                                'yo_NG.UTF-8',
1434    'yue_hk':                               'yue_HK.UTF-8',
1435    'yuw_pg':                               'yuw_PG.UTF-8',
1436    'zh':                                   'zh_CN.eucCN',
1437    'zh_cn':                                'zh_CN.gb2312',
1438    'zh_cn.big5':                           'zh_TW.big5',
1439    'zh_cn.euc':                            'zh_CN.eucCN',
1440    'zh_hk':                                'zh_HK.big5hkscs',
1441    'zh_hk.big5hk':                         'zh_HK.big5hkscs',
1442    'zh_sg':                                'zh_SG.GB2312',
1443    'zh_sg.gbk':                            'zh_SG.GBK',
1444    'zh_tw':                                'zh_TW.big5',
1445    'zh_tw.euc':                            'zh_TW.eucTW',
1446    'zh_tw.euctw':                          'zh_TW.eucTW',
1447    'zu':                                   'zu_ZA.ISO8859-1',
1448    'zu_za':                                'zu_ZA.ISO8859-1',
1449}
1450
1451#
1452# This maps Windows language identifiers to locale strings.
1453#
1454# This list has been updated from
1455# http://msdn.microsoft.com/library/default.asp?url=/library/en-us/intl/nls_238z.asp
1456# to include every locale up to Windows Vista.
1457#
1458# NOTE: this mapping is incomplete.  If your language is missing, please
1459# submit a bug report to the Python bug tracker at http://bugs.python.org/
1460# Make sure you include the missing language identifier and the suggested
1461# locale code.
1462#
1463
1464windows_locale = {
1465    0x0436: "af_ZA", # Afrikaans
1466    0x041c: "sq_AL", # Albanian
1467    0x0484: "gsw_FR",# Alsatian - France
1468    0x045e: "am_ET", # Amharic - Ethiopia
1469    0x0401: "ar_SA", # Arabic - Saudi Arabia
1470    0x0801: "ar_IQ", # Arabic - Iraq
1471    0x0c01: "ar_EG", # Arabic - Egypt
1472    0x1001: "ar_LY", # Arabic - Libya
1473    0x1401: "ar_DZ", # Arabic - Algeria
1474    0x1801: "ar_MA", # Arabic - Morocco
1475    0x1c01: "ar_TN", # Arabic - Tunisia
1476    0x2001: "ar_OM", # Arabic - Oman
1477    0x2401: "ar_YE", # Arabic - Yemen
1478    0x2801: "ar_SY", # Arabic - Syria
1479    0x2c01: "ar_JO", # Arabic - Jordan
1480    0x3001: "ar_LB", # Arabic - Lebanon
1481    0x3401: "ar_KW", # Arabic - Kuwait
1482    0x3801: "ar_AE", # Arabic - United Arab Emirates
1483    0x3c01: "ar_BH", # Arabic - Bahrain
1484    0x4001: "ar_QA", # Arabic - Qatar
1485    0x042b: "hy_AM", # Armenian
1486    0x044d: "as_IN", # Assamese - India
1487    0x042c: "az_AZ", # Azeri - Latin
1488    0x082c: "az_AZ", # Azeri - Cyrillic
1489    0x046d: "ba_RU", # Bashkir
1490    0x042d: "eu_ES", # Basque - Russia
1491    0x0423: "be_BY", # Belarusian
1492    0x0445: "bn_IN", # Begali
1493    0x201a: "bs_BA", # Bosnian - Cyrillic
1494    0x141a: "bs_BA", # Bosnian - Latin
1495    0x047e: "br_FR", # Breton - France
1496    0x0402: "bg_BG", # Bulgarian
1497#    0x0455: "my_MM", # Burmese - Not supported
1498    0x0403: "ca_ES", # Catalan
1499    0x0004: "zh_CHS",# Chinese - Simplified
1500    0x0404: "zh_TW", # Chinese - Taiwan
1501    0x0804: "zh_CN", # Chinese - PRC
1502    0x0c04: "zh_HK", # Chinese - Hong Kong S.A.R.
1503    0x1004: "zh_SG", # Chinese - Singapore
1504    0x1404: "zh_MO", # Chinese - Macao S.A.R.
1505    0x7c04: "zh_CHT",# Chinese - Traditional
1506    0x0483: "co_FR", # Corsican - France
1507    0x041a: "hr_HR", # Croatian
1508    0x101a: "hr_BA", # Croatian - Bosnia
1509    0x0405: "cs_CZ", # Czech
1510    0x0406: "da_DK", # Danish
1511    0x048c: "gbz_AF",# Dari - Afghanistan
1512    0x0465: "div_MV",# Divehi - Maldives
1513    0x0413: "nl_NL", # Dutch - The Netherlands
1514    0x0813: "nl_BE", # Dutch - Belgium
1515    0x0409: "en_US", # English - United States
1516    0x0809: "en_GB", # English - United Kingdom
1517    0x0c09: "en_AU", # English - Australia
1518    0x1009: "en_CA", # English - Canada
1519    0x1409: "en_NZ", # English - New Zealand
1520    0x1809: "en_IE", # English - Ireland
1521    0x1c09: "en_ZA", # English - South Africa
1522    0x2009: "en_JA", # English - Jamaica
1523    0x2409: "en_CB", # English - Caribbean
1524    0x2809: "en_BZ", # English - Belize
1525    0x2c09: "en_TT", # English - Trinidad
1526    0x3009: "en_ZW", # English - Zimbabwe
1527    0x3409: "en_PH", # English - Philippines
1528    0x4009: "en_IN", # English - India
1529    0x4409: "en_MY", # English - Malaysia
1530    0x4809: "en_IN", # English - Singapore
1531    0x0425: "et_EE", # Estonian
1532    0x0438: "fo_FO", # Faroese
1533    0x0464: "fil_PH",# Filipino
1534    0x040b: "fi_FI", # Finnish
1535    0x040c: "fr_FR", # French - France
1536    0x080c: "fr_BE", # French - Belgium
1537    0x0c0c: "fr_CA", # French - Canada
1538    0x100c: "fr_CH", # French - Switzerland
1539    0x140c: "fr_LU", # French - Luxembourg
1540    0x180c: "fr_MC", # French - Monaco
1541    0x0462: "fy_NL", # Frisian - Netherlands
1542    0x0456: "gl_ES", # Galician
1543    0x0437: "ka_GE", # Georgian
1544    0x0407: "de_DE", # German - Germany
1545    0x0807: "de_CH", # German - Switzerland
1546    0x0c07: "de_AT", # German - Austria
1547    0x1007: "de_LU", # German - Luxembourg
1548    0x1407: "de_LI", # German - Liechtenstein
1549    0x0408: "el_GR", # Greek
1550    0x046f: "kl_GL", # Greenlandic - Greenland
1551    0x0447: "gu_IN", # Gujarati
1552    0x0468: "ha_NG", # Hausa - Latin
1553    0x040d: "he_IL", # Hebrew
1554    0x0439: "hi_IN", # Hindi
1555    0x040e: "hu_HU", # Hungarian
1556    0x040f: "is_IS", # Icelandic
1557    0x0421: "id_ID", # Indonesian
1558    0x045d: "iu_CA", # Inuktitut - Syllabics
1559    0x085d: "iu_CA", # Inuktitut - Latin
1560    0x083c: "ga_IE", # Irish - Ireland
1561    0x0410: "it_IT", # Italian - Italy
1562    0x0810: "it_CH", # Italian - Switzerland
1563    0x0411: "ja_JP", # Japanese
1564    0x044b: "kn_IN", # Kannada - India
1565    0x043f: "kk_KZ", # Kazakh
1566    0x0453: "kh_KH", # Khmer - Cambodia
1567    0x0486: "qut_GT",# K'iche - Guatemala
1568    0x0487: "rw_RW", # Kinyarwanda - Rwanda
1569    0x0457: "kok_IN",# Konkani
1570    0x0412: "ko_KR", # Korean
1571    0x0440: "ky_KG", # Kyrgyz
1572    0x0454: "lo_LA", # Lao - Lao PDR
1573    0x0426: "lv_LV", # Latvian
1574    0x0427: "lt_LT", # Lithuanian
1575    0x082e: "dsb_DE",# Lower Sorbian - Germany
1576    0x046e: "lb_LU", # Luxembourgish
1577    0x042f: "mk_MK", # FYROM Macedonian
1578    0x043e: "ms_MY", # Malay - Malaysia
1579    0x083e: "ms_BN", # Malay - Brunei Darussalam
1580    0x044c: "ml_IN", # Malayalam - India
1581    0x043a: "mt_MT", # Maltese
1582    0x0481: "mi_NZ", # Maori
1583    0x047a: "arn_CL",# Mapudungun
1584    0x044e: "mr_IN", # Marathi
1585    0x047c: "moh_CA",# Mohawk - Canada
1586    0x0450: "mn_MN", # Mongolian - Cyrillic
1587    0x0850: "mn_CN", # Mongolian - PRC
1588    0x0461: "ne_NP", # Nepali
1589    0x0414: "nb_NO", # Norwegian - Bokmal
1590    0x0814: "nn_NO", # Norwegian - Nynorsk
1591    0x0482: "oc_FR", # Occitan - France
1592    0x0448: "or_IN", # Oriya - India
1593    0x0463: "ps_AF", # Pashto - Afghanistan
1594    0x0429: "fa_IR", # Persian
1595    0x0415: "pl_PL", # Polish
1596    0x0416: "pt_BR", # Portuguese - Brazil
1597    0x0816: "pt_PT", # Portuguese - Portugal
1598    0x0446: "pa_IN", # Punjabi
1599    0x046b: "quz_BO",# Quechua (Bolivia)
1600    0x086b: "quz_EC",# Quechua (Ecuador)
1601    0x0c6b: "quz_PE",# Quechua (Peru)
1602    0x0418: "ro_RO", # Romanian - Romania
1603    0x0417: "rm_CH", # Romansh
1604    0x0419: "ru_RU", # Russian
1605    0x243b: "smn_FI",# Sami Finland
1606    0x103b: "smj_NO",# Sami Norway
1607    0x143b: "smj_SE",# Sami Sweden
1608    0x043b: "se_NO", # Sami Northern Norway
1609    0x083b: "se_SE", # Sami Northern Sweden
1610    0x0c3b: "se_FI", # Sami Northern Finland
1611    0x203b: "sms_FI",# Sami Skolt
1612    0x183b: "sma_NO",# Sami Southern Norway
1613    0x1c3b: "sma_SE",# Sami Southern Sweden
1614    0x044f: "sa_IN", # Sanskrit
1615    0x0c1a: "sr_SP", # Serbian - Cyrillic
1616    0x1c1a: "sr_BA", # Serbian - Bosnia Cyrillic
1617    0x081a: "sr_SP", # Serbian - Latin
1618    0x181a: "sr_BA", # Serbian - Bosnia Latin
1619    0x045b: "si_LK", # Sinhala - Sri Lanka
1620    0x046c: "ns_ZA", # Northern Sotho
1621    0x0432: "tn_ZA", # Setswana - Southern Africa
1622    0x041b: "sk_SK", # Slovak
1623    0x0424: "sl_SI", # Slovenian
1624    0x040a: "es_ES", # Spanish - Spain
1625    0x080a: "es_MX", # Spanish - Mexico
1626    0x0c0a: "es_ES", # Spanish - Spain (Modern)
1627    0x100a: "es_GT", # Spanish - Guatemala
1628    0x140a: "es_CR", # Spanish - Costa Rica
1629    0x180a: "es_PA", # Spanish - Panama
1630    0x1c0a: "es_DO", # Spanish - Dominican Republic
1631    0x200a: "es_VE", # Spanish - Venezuela
1632    0x240a: "es_CO", # Spanish - Colombia
1633    0x280a: "es_PE", # Spanish - Peru
1634    0x2c0a: "es_AR", # Spanish - Argentina
1635    0x300a: "es_EC", # Spanish - Ecuador
1636    0x340a: "es_CL", # Spanish - Chile
1637    0x380a: "es_UR", # Spanish - Uruguay
1638    0x3c0a: "es_PY", # Spanish - Paraguay
1639    0x400a: "es_BO", # Spanish - Bolivia
1640    0x440a: "es_SV", # Spanish - El Salvador
1641    0x480a: "es_HN", # Spanish - Honduras
1642    0x4c0a: "es_NI", # Spanish - Nicaragua
1643    0x500a: "es_PR", # Spanish - Puerto Rico
1644    0x540a: "es_US", # Spanish - United States
1645#    0x0430: "", # Sutu - Not supported
1646    0x0441: "sw_KE", # Swahili
1647    0x041d: "sv_SE", # Swedish - Sweden
1648    0x081d: "sv_FI", # Swedish - Finland
1649    0x045a: "syr_SY",# Syriac
1650    0x0428: "tg_TJ", # Tajik - Cyrillic
1651    0x085f: "tmz_DZ",# Tamazight - Latin
1652    0x0449: "ta_IN", # Tamil
1653    0x0444: "tt_RU", # Tatar
1654    0x044a: "te_IN", # Telugu
1655    0x041e: "th_TH", # Thai
1656    0x0851: "bo_BT", # Tibetan - Bhutan
1657    0x0451: "bo_CN", # Tibetan - PRC
1658    0x041f: "tr_TR", # Turkish
1659    0x0442: "tk_TM", # Turkmen - Cyrillic
1660    0x0480: "ug_CN", # Uighur - Arabic
1661    0x0422: "uk_UA", # Ukrainian
1662    0x042e: "wen_DE",# Upper Sorbian - Germany
1663    0x0420: "ur_PK", # Urdu
1664    0x0820: "ur_IN", # Urdu - India
1665    0x0443: "uz_UZ", # Uzbek - Latin
1666    0x0843: "uz_UZ", # Uzbek - Cyrillic
1667    0x042a: "vi_VN", # Vietnamese
1668    0x0452: "cy_GB", # Welsh
1669    0x0488: "wo_SN", # Wolof - Senegal
1670    0x0434: "xh_ZA", # Xhosa - South Africa
1671    0x0485: "sah_RU",# Yakut - Cyrillic
1672    0x0478: "ii_CN", # Yi - PRC
1673    0x046a: "yo_NG", # Yoruba - Nigeria
1674    0x0435: "zu_ZA", # Zulu
1675}
1676
1677def _print_locale():
1678
1679    """ Test function.
1680    """
1681    categories = {}
1682    def _init_categories(categories=categories):
1683        for k,v in globals().items():
1684            if k[:3] == 'LC_':
1685                categories[k] = v
1686    _init_categories()
1687    del categories['LC_ALL']
1688
1689    print('Locale defaults as determined by getdefaultlocale():')
1690    print('-'*72)
1691    lang, enc = getdefaultlocale()
1692    print('Language: ', lang or '(undefined)')
1693    print('Encoding: ', enc or '(undefined)')
1694    print()
1695
1696    print('Locale settings on startup:')
1697    print('-'*72)
1698    for name,category in categories.items():
1699        print(name, '...')
1700        lang, enc = getlocale(category)
1701        print('   Language: ', lang or '(undefined)')
1702        print('   Encoding: ', enc or '(undefined)')
1703        print()
1704
1705    print()
1706    print('Locale settings after calling resetlocale():')
1707    print('-'*72)
1708    resetlocale()
1709    for name,category in categories.items():
1710        print(name, '...')
1711        lang, enc = getlocale(category)
1712        print('   Language: ', lang or '(undefined)')
1713        print('   Encoding: ', enc or '(undefined)')
1714        print()
1715
1716    try:
1717        setlocale(LC_ALL, "")
1718    except:
1719        print('NOTE:')
1720        print('setlocale(LC_ALL, "") does not support the default locale')
1721        print('given in the OS environment variables.')
1722    else:
1723        print()
1724        print('Locale settings after calling setlocale(LC_ALL, ""):')
1725        print('-'*72)
1726        for name,category in categories.items():
1727            print(name, '...')
1728            lang, enc = getlocale(category)
1729            print('   Language: ', lang or '(undefined)')
1730            print('   Encoding: ', enc or '(undefined)')
1731            print()
1732
1733###
1734
1735try:
1736    LC_MESSAGES
1737except NameError:
1738    pass
1739else:
1740    __all__.append("LC_MESSAGES")
1741
1742if __name__=='__main__':
1743    print('Locale aliasing:')
1744    print()
1745    _print_locale()
1746    print()
1747    print('Number formatting:')
1748    print()
1749    _test()
1750