• Home
  • Line#
  • Scopes#
  • Navigate#
  • Raw
  • Download
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    if percent[-1] in 'eEfFgGdiu':
189        formatted = _localize(formatted, grouping, monetary)
190    return formatted
191
192# Transform formatted as locale number according to the locale settings
193def _localize(formatted, grouping=False, monetary=False):
194    # floats and decimal ints need special action!
195    if '.' in formatted:
196        seps = 0
197        parts = formatted.split('.')
198        if grouping:
199            parts[0], seps = _group(parts[0], monetary=monetary)
200        decimal_point = localeconv()[monetary and 'mon_decimal_point'
201                                              or 'decimal_point']
202        formatted = decimal_point.join(parts)
203        if seps:
204            formatted = _strip_padding(formatted, seps)
205    else:
206        seps = 0
207        if grouping:
208            formatted, seps = _group(formatted, monetary=monetary)
209        if seps:
210            formatted = _strip_padding(formatted, seps)
211    return formatted
212
213def format_string(f, val, grouping=False, monetary=False):
214    """Formats a string in the same way that the % formatting would use,
215    but takes the current locale into account.
216
217    Grouping is applied if the third parameter is true.
218    Conversion uses monetary thousands separator and grouping strings if
219    forth parameter monetary is true."""
220    percents = list(_percent_re.finditer(f))
221    new_f = _percent_re.sub('%s', f)
222
223    if isinstance(val, _collections_abc.Mapping):
224        new_val = []
225        for perc in percents:
226            if perc.group()[-1]=='%':
227                new_val.append('%')
228            else:
229                new_val.append(_format(perc.group(), val, grouping, monetary))
230    else:
231        if not isinstance(val, tuple):
232            val = (val,)
233        new_val = []
234        i = 0
235        for perc in percents:
236            if perc.group()[-1]=='%':
237                new_val.append('%')
238            else:
239                starcount = perc.group('modifiers').count('*')
240                new_val.append(_format(perc.group(),
241                                      val[i],
242                                      grouping,
243                                      monetary,
244                                      *val[i+1:i+1+starcount]))
245                i += (1 + starcount)
246    val = tuple(new_val)
247
248    return new_f % val
249
250def format(percent, value, grouping=False, monetary=False, *additional):
251    """Deprecated, use format_string instead."""
252    import warnings
253    warnings.warn(
254        "This method will be removed in a future version of Python. "
255        "Use 'locale.format_string()' instead.",
256        DeprecationWarning, stacklevel=2
257    )
258
259    match = _percent_re.match(percent)
260    if not match or len(match.group())!= len(percent):
261        raise ValueError(("format() must be given exactly one %%char "
262                         "format specifier, %s not valid") % repr(percent))
263    return _format(percent, value, grouping, monetary, *additional)
264
265def currency(val, symbol=True, grouping=False, international=False):
266    """Formats val according to the currency settings
267    in the current locale."""
268    conv = localeconv()
269
270    # check for illegal values
271    digits = conv[international and 'int_frac_digits' or 'frac_digits']
272    if digits == 127:
273        raise ValueError("Currency formatting is not possible using "
274                         "the 'C' locale.")
275
276    s = _localize(f'{abs(val):.{digits}f}', grouping, monetary=True)
277    # '<' and '>' are markers if the sign must be inserted between symbol and value
278    s = '<' + s + '>'
279
280    if symbol:
281        smb = conv[international and 'int_curr_symbol' or 'currency_symbol']
282        precedes = conv[val<0 and 'n_cs_precedes' or 'p_cs_precedes']
283        separated = conv[val<0 and 'n_sep_by_space' or 'p_sep_by_space']
284
285        if precedes:
286            s = smb + (separated and ' ' or '') + s
287        else:
288            if international and smb[-1] == ' ':
289                smb = smb[:-1]
290            s = s + (separated and ' ' or '') + smb
291
292    sign_pos = conv[val<0 and 'n_sign_posn' or 'p_sign_posn']
293    sign = conv[val<0 and 'negative_sign' or 'positive_sign']
294
295    if sign_pos == 0:
296        s = '(' + s + ')'
297    elif sign_pos == 1:
298        s = sign + s
299    elif sign_pos == 2:
300        s = s + sign
301    elif sign_pos == 3:
302        s = s.replace('<', sign)
303    elif sign_pos == 4:
304        s = s.replace('>', sign)
305    else:
306        # the default if nothing specified;
307        # this should be the most fitting sign position
308        s = sign + s
309
310    return s.replace('<', '').replace('>', '')
311
312def str(val):
313    """Convert float to string, taking the locale into account."""
314    return _format("%.12g", val)
315
316def delocalize(string):
317    "Parses a string as a normalized number according to the locale settings."
318
319    conv = localeconv()
320
321    #First, get rid of the grouping
322    ts = conv['thousands_sep']
323    if ts:
324        string = string.replace(ts, '')
325
326    #next, replace the decimal point with a dot
327    dd = conv['decimal_point']
328    if dd:
329        string = string.replace(dd, '.')
330    return string
331
332def localize(string, grouping=False, monetary=False):
333    """Parses a string as locale number according to the locale settings."""
334    return _localize(string, grouping, monetary)
335
336def atof(string, func=float):
337    "Parses a string as a float according to the locale settings."
338    return func(delocalize(string))
339
340def atoi(string):
341    "Converts a string to an integer according to the locale settings."
342    return int(delocalize(string))
343
344def _test():
345    setlocale(LC_ALL, "")
346    #do grouping
347    s1 = format_string("%d", 123456789,1)
348    print(s1, "is", atoi(s1))
349    #standard formatting
350    s1 = str(3.14)
351    print(s1, "is", atof(s1))
352
353### Locale name aliasing engine
354
355# Author: Marc-Andre Lemburg, mal@lemburg.com
356# Various tweaks by Fredrik Lundh <fredrik@pythonware.com>
357
358# store away the low-level version of setlocale (it's
359# overridden below)
360_setlocale = setlocale
361
362def _replace_encoding(code, encoding):
363    if '.' in code:
364        langname = code[:code.index('.')]
365    else:
366        langname = code
367    # Convert the encoding to a C lib compatible encoding string
368    norm_encoding = encodings.normalize_encoding(encoding)
369    #print('norm encoding: %r' % norm_encoding)
370    norm_encoding = encodings.aliases.aliases.get(norm_encoding.lower(),
371                                                  norm_encoding)
372    #print('aliased encoding: %r' % norm_encoding)
373    encoding = norm_encoding
374    norm_encoding = norm_encoding.lower()
375    if norm_encoding in locale_encoding_alias:
376        encoding = locale_encoding_alias[norm_encoding]
377    else:
378        norm_encoding = norm_encoding.replace('_', '')
379        norm_encoding = norm_encoding.replace('-', '')
380        if norm_encoding in locale_encoding_alias:
381            encoding = locale_encoding_alias[norm_encoding]
382    #print('found encoding %r' % encoding)
383    return langname + '.' + encoding
384
385def _append_modifier(code, modifier):
386    if modifier == 'euro':
387        if '.' not in code:
388            return code + '.ISO8859-15'
389        _, _, encoding = code.partition('.')
390        if encoding in ('ISO8859-15', 'UTF-8'):
391            return code
392        if encoding == 'ISO8859-1':
393            return _replace_encoding(code, 'ISO8859-15')
394    return code + '@' + modifier
395
396def normalize(localename):
397
398    """ Returns a normalized locale code for the given locale
399        name.
400
401        The returned locale code is formatted for use with
402        setlocale().
403
404        If normalization fails, the original name is returned
405        unchanged.
406
407        If the given encoding is not known, the function defaults to
408        the default encoding for the locale code just like setlocale()
409        does.
410
411    """
412    # Normalize the locale name and extract the encoding and modifier
413    code = localename.lower()
414    if ':' in code:
415        # ':' is sometimes used as encoding delimiter.
416        code = code.replace(':', '.')
417    if '@' in code:
418        code, modifier = code.split('@', 1)
419    else:
420        modifier = ''
421    if '.' in code:
422        langname, encoding = code.split('.')[:2]
423    else:
424        langname = code
425        encoding = ''
426
427    # First lookup: fullname (possibly with encoding and modifier)
428    lang_enc = langname
429    if encoding:
430        norm_encoding = encoding.replace('-', '')
431        norm_encoding = norm_encoding.replace('_', '')
432        lang_enc += '.' + norm_encoding
433    lookup_name = lang_enc
434    if modifier:
435        lookup_name += '@' + modifier
436    code = locale_alias.get(lookup_name, None)
437    if code is not None:
438        return code
439    #print('first lookup failed')
440
441    if modifier:
442        # Second try: fullname without modifier (possibly with encoding)
443        code = locale_alias.get(lang_enc, None)
444        if code is not None:
445            #print('lookup without modifier succeeded')
446            if '@' not in code:
447                return _append_modifier(code, modifier)
448            if code.split('@', 1)[1].lower() == modifier:
449                return code
450        #print('second lookup failed')
451
452    if encoding:
453        # Third try: langname (without encoding, possibly with modifier)
454        lookup_name = langname
455        if modifier:
456            lookup_name += '@' + modifier
457        code = locale_alias.get(lookup_name, None)
458        if code is not None:
459            #print('lookup without encoding succeeded')
460            if '@' not in code:
461                return _replace_encoding(code, encoding)
462            code, modifier = code.split('@', 1)
463            return _replace_encoding(code, encoding) + '@' + modifier
464
465        if modifier:
466            # Fourth try: langname (without encoding and modifier)
467            code = locale_alias.get(langname, None)
468            if code is not None:
469                #print('lookup without modifier and encoding succeeded')
470                if '@' not in code:
471                    code = _replace_encoding(code, encoding)
472                    return _append_modifier(code, modifier)
473                code, defmod = code.split('@', 1)
474                if defmod.lower() == modifier:
475                    return _replace_encoding(code, encoding) + '@' + defmod
476
477    return localename
478
479def _parse_localename(localename):
480
481    """ Parses the locale code for localename and returns the
482        result as tuple (language code, encoding).
483
484        The localename is normalized and passed through the locale
485        alias engine. A ValueError is raised in case the locale name
486        cannot be parsed.
487
488        The language code corresponds to RFC 1766.  code and encoding
489        can be None in case the values cannot be determined or are
490        unknown to this implementation.
491
492    """
493    code = normalize(localename)
494    if '@' in code:
495        # Deal with locale modifiers
496        code, modifier = code.split('@', 1)
497        if modifier == 'euro' and '.' not in code:
498            # Assume Latin-9 for @euro locales. This is bogus,
499            # since some systems may use other encodings for these
500            # locales. Also, we ignore other modifiers.
501            return code, 'iso-8859-15'
502
503    if '.' in code:
504        return tuple(code.split('.')[:2])
505    elif code == 'C':
506        return None, None
507    elif code == 'UTF-8':
508        # On macOS "LC_CTYPE=UTF-8" is a valid locale setting
509        # for getting UTF-8 handling for text.
510        return None, 'UTF-8'
511    raise ValueError('unknown locale: %s' % localename)
512
513def _build_localename(localetuple):
514
515    """ Builds a locale code from the given tuple (language code,
516        encoding).
517
518        No aliasing or normalizing takes place.
519
520    """
521    try:
522        language, encoding = localetuple
523
524        if language is None:
525            language = 'C'
526        if encoding is None:
527            return language
528        else:
529            return language + '.' + encoding
530    except (TypeError, ValueError):
531        raise TypeError('Locale must be None, a string, or an iterable of '
532                        'two strings -- language code, encoding.') from None
533
534def getdefaultlocale(envvars=('LC_ALL', 'LC_CTYPE', 'LANG', 'LANGUAGE')):
535
536    """ Tries to determine the default locale settings and returns
537        them as tuple (language code, encoding).
538
539        According to POSIX, a program which has not called
540        setlocale(LC_ALL, "") runs using the portable 'C' locale.
541        Calling setlocale(LC_ALL, "") lets it use the default locale as
542        defined by the LANG variable. Since we don't want to interfere
543        with the current locale setting we thus emulate the behavior
544        in the way described above.
545
546        To maintain compatibility with other platforms, not only the
547        LANG variable is tested, but a list of variables given as
548        envvars parameter. The first found to be defined will be
549        used. envvars defaults to the search path used in GNU gettext;
550        it must always contain the variable name 'LANG'.
551
552        Except for the code 'C', the language code corresponds to RFC
553        1766.  code and encoding can be None in case the values cannot
554        be determined.
555
556    """
557
558    try:
559        # check if it's supported by the _locale module
560        import _locale
561        code, encoding = _locale._getdefaultlocale()
562    except (ImportError, AttributeError):
563        pass
564    else:
565        # make sure the code/encoding values are valid
566        if sys.platform == "win32" and code and code[:2] == "0x":
567            # map windows language identifier to language name
568            code = windows_locale.get(int(code, 0))
569        # ...add other platform-specific processing here, if
570        # necessary...
571        return code, encoding
572
573    # fall back on POSIX behaviour
574    import os
575    lookup = os.environ.get
576    for variable in envvars:
577        localename = lookup(variable,None)
578        if localename:
579            if variable == 'LANGUAGE':
580                localename = localename.split(':')[0]
581            break
582    else:
583        localename = 'C'
584    return _parse_localename(localename)
585
586
587def getlocale(category=LC_CTYPE):
588
589    """ Returns the current setting for the given locale category as
590        tuple (language code, encoding).
591
592        category may be one of the LC_* value except LC_ALL. It
593        defaults to LC_CTYPE.
594
595        Except for the code 'C', the language code corresponds to RFC
596        1766.  code and encoding can be None in case the values cannot
597        be determined.
598
599    """
600    localename = _setlocale(category)
601    if category == LC_ALL and ';' in localename:
602        raise TypeError('category LC_ALL is not supported')
603    return _parse_localename(localename)
604
605def setlocale(category, locale=None):
606
607    """ Set the locale for the given category.  The locale can be
608        a string, an iterable of two strings (language code and encoding),
609        or None.
610
611        Iterables are converted to strings using the locale aliasing
612        engine.  Locale strings are passed directly to the C lib.
613
614        category may be given as one of the LC_* values.
615
616    """
617    if locale and not isinstance(locale, _builtin_str):
618        # convert to string
619        locale = normalize(_build_localename(locale))
620    return _setlocale(category, locale)
621
622def resetlocale(category=LC_ALL):
623
624    """ Sets the locale for category to the default setting.
625
626        The default setting is determined by calling
627        getdefaultlocale(). category defaults to LC_ALL.
628
629    """
630    _setlocale(category, _build_localename(getdefaultlocale()))
631
632
633try:
634    from _locale import _get_locale_encoding
635except ImportError:
636    def _get_locale_encoding():
637        if hasattr(sys, 'getandroidapilevel'):
638            # On Android langinfo.h and CODESET are missing, and UTF-8 is
639            # always used in mbstowcs() and wcstombs().
640            return 'UTF-8'
641        if sys.flags.utf8_mode:
642            return 'UTF-8'
643        encoding = getdefaultlocale()[1]
644        if encoding is None:
645            # LANG not set, default conservatively to ASCII
646            encoding = 'ascii'
647        return encoding
648
649try:
650    CODESET
651except NameError:
652    def getpreferredencoding(do_setlocale=True):
653        """Return the charset that the user is likely using."""
654        return _get_locale_encoding()
655else:
656    # On Unix, if CODESET is available, use that.
657    def getpreferredencoding(do_setlocale=True):
658        """Return the charset that the user is likely using,
659        according to the system configuration."""
660        if sys.flags.utf8_mode:
661            return 'UTF-8'
662
663        if not do_setlocale:
664            return _get_locale_encoding()
665
666        old_loc = setlocale(LC_CTYPE)
667        try:
668            try:
669                setlocale(LC_CTYPE, "")
670            except Error:
671                pass
672            return _get_locale_encoding()
673        finally:
674            setlocale(LC_CTYPE, old_loc)
675
676
677### Database
678#
679# The following data was extracted from the locale.alias file which
680# comes with X11 and then hand edited removing the explicit encoding
681# definitions and adding some more aliases. The file is usually
682# available as /usr/lib/X11/locale/locale.alias.
683#
684
685#
686# The local_encoding_alias table maps lowercase encoding alias names
687# to C locale encoding names (case-sensitive). Note that normalize()
688# first looks up the encoding in the encodings.aliases dictionary and
689# then applies this mapping to find the correct C lib name for the
690# encoding.
691#
692locale_encoding_alias = {
693
694    # Mappings for non-standard encoding names used in locale names
695    '437':                          'C',
696    'c':                            'C',
697    'en':                           'ISO8859-1',
698    'jis':                          'JIS7',
699    'jis7':                         'JIS7',
700    'ajec':                         'eucJP',
701    'koi8c':                        'KOI8-C',
702    'microsoftcp1251':              'CP1251',
703    'microsoftcp1255':              'CP1255',
704    'microsoftcp1256':              'CP1256',
705    '88591':                        'ISO8859-1',
706    '88592':                        'ISO8859-2',
707    '88595':                        'ISO8859-5',
708    '885915':                       'ISO8859-15',
709
710    # Mappings from Python codec names to C lib encoding names
711    'ascii':                        'ISO8859-1',
712    'latin_1':                      'ISO8859-1',
713    'iso8859_1':                    'ISO8859-1',
714    'iso8859_10':                   'ISO8859-10',
715    'iso8859_11':                   'ISO8859-11',
716    'iso8859_13':                   'ISO8859-13',
717    'iso8859_14':                   'ISO8859-14',
718    'iso8859_15':                   'ISO8859-15',
719    'iso8859_16':                   'ISO8859-16',
720    'iso8859_2':                    'ISO8859-2',
721    'iso8859_3':                    'ISO8859-3',
722    'iso8859_4':                    'ISO8859-4',
723    'iso8859_5':                    'ISO8859-5',
724    'iso8859_6':                    'ISO8859-6',
725    'iso8859_7':                    'ISO8859-7',
726    'iso8859_8':                    'ISO8859-8',
727    'iso8859_9':                    'ISO8859-9',
728    'iso2022_jp':                   'JIS7',
729    'shift_jis':                    'SJIS',
730    'tactis':                       'TACTIS',
731    'euc_jp':                       'eucJP',
732    'euc_kr':                       'eucKR',
733    'utf_8':                        'UTF-8',
734    'koi8_r':                       'KOI8-R',
735    'koi8_t':                       'KOI8-T',
736    'koi8_u':                       'KOI8-U',
737    'kz1048':                       'RK1048',
738    'cp1251':                       'CP1251',
739    'cp1255':                       'CP1255',
740    'cp1256':                       'CP1256',
741
742    # XXX This list is still incomplete. If you know more
743    # mappings, please file a bug report. Thanks.
744}
745
746for k, v in sorted(locale_encoding_alias.items()):
747    k = k.replace('_', '')
748    locale_encoding_alias.setdefault(k, v)
749
750#
751# The locale_alias table maps lowercase alias names to C locale names
752# (case-sensitive). Encodings are always separated from the locale
753# name using a dot ('.'); they should only be given in case the
754# language name is needed to interpret the given encoding alias
755# correctly (CJK codes often have this need).
756#
757# Note that the normalize() function which uses this tables
758# removes '_' and '-' characters from the encoding part of the
759# locale name before doing the lookup. This saves a lot of
760# space in the table.
761#
762# MAL 2004-12-10:
763# Updated alias mapping to most recent locale.alias file
764# from X.org distribution using makelocalealias.py.
765#
766# These are the differences compared to the old mapping (Python 2.4
767# and older):
768#
769#    updated 'bg' -> 'bg_BG.ISO8859-5' to 'bg_BG.CP1251'
770#    updated 'bg_bg' -> 'bg_BG.ISO8859-5' to 'bg_BG.CP1251'
771#    updated 'bulgarian' -> 'bg_BG.ISO8859-5' to 'bg_BG.CP1251'
772#    updated 'cz' -> 'cz_CZ.ISO8859-2' to 'cs_CZ.ISO8859-2'
773#    updated 'cz_cz' -> 'cz_CZ.ISO8859-2' to 'cs_CZ.ISO8859-2'
774#    updated 'czech' -> 'cs_CS.ISO8859-2' to 'cs_CZ.ISO8859-2'
775#    updated 'dutch' -> 'nl_BE.ISO8859-1' to 'nl_NL.ISO8859-1'
776#    updated 'et' -> 'et_EE.ISO8859-4' to 'et_EE.ISO8859-15'
777#    updated 'et_ee' -> 'et_EE.ISO8859-4' to 'et_EE.ISO8859-15'
778#    updated 'fi' -> 'fi_FI.ISO8859-1' to 'fi_FI.ISO8859-15'
779#    updated 'fi_fi' -> 'fi_FI.ISO8859-1' to 'fi_FI.ISO8859-15'
780#    updated 'iw' -> 'iw_IL.ISO8859-8' to 'he_IL.ISO8859-8'
781#    updated 'iw_il' -> 'iw_IL.ISO8859-8' to 'he_IL.ISO8859-8'
782#    updated 'japanese' -> 'ja_JP.SJIS' to 'ja_JP.eucJP'
783#    updated 'lt' -> 'lt_LT.ISO8859-4' to 'lt_LT.ISO8859-13'
784#    updated 'lv' -> 'lv_LV.ISO8859-4' to 'lv_LV.ISO8859-13'
785#    updated 'sl' -> 'sl_CS.ISO8859-2' to 'sl_SI.ISO8859-2'
786#    updated 'slovene' -> 'sl_CS.ISO8859-2' to 'sl_SI.ISO8859-2'
787#    updated 'th_th' -> 'th_TH.TACTIS' to 'th_TH.ISO8859-11'
788#    updated 'zh_cn' -> 'zh_CN.eucCN' to 'zh_CN.gb2312'
789#    updated 'zh_cn.big5' -> 'zh_TW.eucTW' to 'zh_TW.big5'
790#    updated 'zh_tw' -> 'zh_TW.eucTW' to 'zh_TW.big5'
791#
792# MAL 2008-05-30:
793# Updated alias mapping to most recent locale.alias file
794# from X.org distribution using makelocalealias.py.
795#
796# These are the differences compared to the old mapping (Python 2.5
797# and older):
798#
799#    updated 'cs_cs.iso88592' -> 'cs_CZ.ISO8859-2' to 'cs_CS.ISO8859-2'
800#    updated 'serbocroatian' -> 'sh_YU.ISO8859-2' to 'sr_CS.ISO8859-2'
801#    updated 'sh' -> 'sh_YU.ISO8859-2' to 'sr_CS.ISO8859-2'
802#    updated 'sh_hr.iso88592' -> 'sh_HR.ISO8859-2' to 'hr_HR.ISO8859-2'
803#    updated 'sh_sp' -> 'sh_YU.ISO8859-2' to 'sr_CS.ISO8859-2'
804#    updated 'sh_yu' -> 'sh_YU.ISO8859-2' to 'sr_CS.ISO8859-2'
805#    updated 'sp' -> 'sp_YU.ISO8859-5' to 'sr_CS.ISO8859-5'
806#    updated 'sp_yu' -> 'sp_YU.ISO8859-5' to 'sr_CS.ISO8859-5'
807#    updated 'sr' -> 'sr_YU.ISO8859-5' to 'sr_CS.ISO8859-5'
808#    updated 'sr@cyrillic' -> 'sr_YU.ISO8859-5' to 'sr_CS.ISO8859-5'
809#    updated 'sr_sp' -> 'sr_SP.ISO8859-2' to 'sr_CS.ISO8859-2'
810#    updated 'sr_yu' -> 'sr_YU.ISO8859-5' to 'sr_CS.ISO8859-5'
811#    updated 'sr_yu.cp1251@cyrillic' -> 'sr_YU.CP1251' to 'sr_CS.CP1251'
812#    updated 'sr_yu.iso88592' -> 'sr_YU.ISO8859-2' to 'sr_CS.ISO8859-2'
813#    updated 'sr_yu.iso88595' -> 'sr_YU.ISO8859-5' to 'sr_CS.ISO8859-5'
814#    updated 'sr_yu.iso88595@cyrillic' -> 'sr_YU.ISO8859-5' to 'sr_CS.ISO8859-5'
815#    updated 'sr_yu.microsoftcp1251@cyrillic' -> 'sr_YU.CP1251' to 'sr_CS.CP1251'
816#    updated 'sr_yu.utf8@cyrillic' -> 'sr_YU.UTF-8' to 'sr_CS.UTF-8'
817#    updated 'sr_yu@cyrillic' -> 'sr_YU.ISO8859-5' to 'sr_CS.ISO8859-5'
818#
819# AP 2010-04-12:
820# Updated alias mapping to most recent locale.alias file
821# from X.org distribution using makelocalealias.py.
822#
823# These are the differences compared to the old mapping (Python 2.6.5
824# and older):
825#
826#    updated 'ru' -> 'ru_RU.ISO8859-5' to 'ru_RU.UTF-8'
827#    updated 'ru_ru' -> 'ru_RU.ISO8859-5' to 'ru_RU.UTF-8'
828#    updated 'serbocroatian' -> 'sr_CS.ISO8859-2' to 'sr_RS.UTF-8@latin'
829#    updated 'sh' -> 'sr_CS.ISO8859-2' to 'sr_RS.UTF-8@latin'
830#    updated 'sh_yu' -> 'sr_CS.ISO8859-2' to 'sr_RS.UTF-8@latin'
831#    updated 'sr' -> 'sr_CS.ISO8859-5' to 'sr_RS.UTF-8'
832#    updated 'sr@cyrillic' -> 'sr_CS.ISO8859-5' to 'sr_RS.UTF-8'
833#    updated 'sr@latn' -> 'sr_CS.ISO8859-2' to 'sr_RS.UTF-8@latin'
834#    updated 'sr_cs.utf8@latn' -> 'sr_CS.UTF-8' to 'sr_RS.UTF-8@latin'
835#    updated 'sr_cs@latn' -> 'sr_CS.ISO8859-2' to 'sr_RS.UTF-8@latin'
836#    updated 'sr_yu' -> 'sr_CS.ISO8859-5' to 'sr_RS.UTF-8@latin'
837#    updated 'sr_yu.utf8@cyrillic' -> 'sr_CS.UTF-8' to 'sr_RS.UTF-8'
838#    updated 'sr_yu@cyrillic' -> 'sr_CS.ISO8859-5' to 'sr_RS.UTF-8'
839#
840# SS 2013-12-20:
841# Updated alias mapping to most recent locale.alias file
842# from X.org distribution using makelocalealias.py.
843#
844# These are the differences compared to the old mapping (Python 3.3.3
845# and older):
846#
847#    updated 'a3' -> 'a3_AZ.KOI8-C' to 'az_AZ.KOI8-C'
848#    updated 'a3_az' -> 'a3_AZ.KOI8-C' to 'az_AZ.KOI8-C'
849#    updated 'a3_az.koi8c' -> 'a3_AZ.KOI8-C' to 'az_AZ.KOI8-C'
850#    updated 'cs_cs.iso88592' -> 'cs_CS.ISO8859-2' to 'cs_CZ.ISO8859-2'
851#    updated 'hebrew' -> 'iw_IL.ISO8859-8' to 'he_IL.ISO8859-8'
852#    updated 'hebrew.iso88598' -> 'iw_IL.ISO8859-8' to 'he_IL.ISO8859-8'
853#    updated 'sd' -> 'sd_IN@devanagari.UTF-8' to 'sd_IN.UTF-8'
854#    updated 'sr@latn' -> 'sr_RS.UTF-8@latin' to 'sr_CS.UTF-8@latin'
855#    updated 'sr_cs' -> 'sr_RS.UTF-8' to 'sr_CS.UTF-8'
856#    updated 'sr_cs.utf8@latn' -> 'sr_RS.UTF-8@latin' to 'sr_CS.UTF-8@latin'
857#    updated 'sr_cs@latn' -> 'sr_RS.UTF-8@latin' to 'sr_CS.UTF-8@latin'
858#
859# SS 2014-10-01:
860# Updated alias mapping with glibc 2.19 supported locales.
861#
862# SS 2018-05-05:
863# Updated alias mapping with glibc 2.27 supported locales.
864#
865# These are the differences compared to the old mapping (Python 3.6.5
866# and older):
867#
868#    updated 'ca_es@valencia' -> 'ca_ES.ISO8859-15@valencia' to 'ca_ES.UTF-8@valencia'
869#    updated 'kk_kz' -> 'kk_KZ.RK1048' to 'kk_KZ.ptcp154'
870#    updated 'russian' -> 'ru_RU.ISO8859-5' to 'ru_RU.KOI8-R'
871
872locale_alias = {
873    'a3':                                   'az_AZ.KOI8-C',
874    'a3_az':                                'az_AZ.KOI8-C',
875    'a3_az.koic':                           'az_AZ.KOI8-C',
876    'aa_dj':                                'aa_DJ.ISO8859-1',
877    'aa_er':                                'aa_ER.UTF-8',
878    'aa_et':                                'aa_ET.UTF-8',
879    'af':                                   'af_ZA.ISO8859-1',
880    'af_za':                                'af_ZA.ISO8859-1',
881    'agr_pe':                               'agr_PE.UTF-8',
882    'ak_gh':                                'ak_GH.UTF-8',
883    'am':                                   'am_ET.UTF-8',
884    'am_et':                                'am_ET.UTF-8',
885    'american':                             'en_US.ISO8859-1',
886    'an_es':                                'an_ES.ISO8859-15',
887    'anp_in':                               'anp_IN.UTF-8',
888    'ar':                                   'ar_AA.ISO8859-6',
889    'ar_aa':                                'ar_AA.ISO8859-6',
890    'ar_ae':                                'ar_AE.ISO8859-6',
891    'ar_bh':                                'ar_BH.ISO8859-6',
892    'ar_dz':                                'ar_DZ.ISO8859-6',
893    'ar_eg':                                'ar_EG.ISO8859-6',
894    'ar_in':                                'ar_IN.UTF-8',
895    'ar_iq':                                'ar_IQ.ISO8859-6',
896    'ar_jo':                                'ar_JO.ISO8859-6',
897    'ar_kw':                                'ar_KW.ISO8859-6',
898    'ar_lb':                                'ar_LB.ISO8859-6',
899    'ar_ly':                                'ar_LY.ISO8859-6',
900    'ar_ma':                                'ar_MA.ISO8859-6',
901    'ar_om':                                'ar_OM.ISO8859-6',
902    'ar_qa':                                'ar_QA.ISO8859-6',
903    'ar_sa':                                'ar_SA.ISO8859-6',
904    'ar_sd':                                'ar_SD.ISO8859-6',
905    'ar_ss':                                'ar_SS.UTF-8',
906    'ar_sy':                                'ar_SY.ISO8859-6',
907    'ar_tn':                                'ar_TN.ISO8859-6',
908    'ar_ye':                                'ar_YE.ISO8859-6',
909    'arabic':                               'ar_AA.ISO8859-6',
910    'as':                                   'as_IN.UTF-8',
911    'as_in':                                'as_IN.UTF-8',
912    'ast_es':                               'ast_ES.ISO8859-15',
913    'ayc_pe':                               'ayc_PE.UTF-8',
914    'az':                                   'az_AZ.ISO8859-9E',
915    'az_az':                                'az_AZ.ISO8859-9E',
916    'az_az.iso88599e':                      'az_AZ.ISO8859-9E',
917    'az_ir':                                'az_IR.UTF-8',
918    'be':                                   'be_BY.CP1251',
919    'be@latin':                             'be_BY.UTF-8@latin',
920    'be_bg.utf8':                           'bg_BG.UTF-8',
921    'be_by':                                'be_BY.CP1251',
922    'be_by@latin':                          'be_BY.UTF-8@latin',
923    'bem_zm':                               'bem_ZM.UTF-8',
924    'ber_dz':                               'ber_DZ.UTF-8',
925    'ber_ma':                               'ber_MA.UTF-8',
926    'bg':                                   'bg_BG.CP1251',
927    'bg_bg':                                'bg_BG.CP1251',
928    'bhb_in.utf8':                          'bhb_IN.UTF-8',
929    'bho_in':                               'bho_IN.UTF-8',
930    'bho_np':                               'bho_NP.UTF-8',
931    'bi_vu':                                'bi_VU.UTF-8',
932    'bn_bd':                                'bn_BD.UTF-8',
933    'bn_in':                                'bn_IN.UTF-8',
934    'bo_cn':                                'bo_CN.UTF-8',
935    'bo_in':                                'bo_IN.UTF-8',
936    'bokmal':                               'nb_NO.ISO8859-1',
937    'bokm\xe5l':                            'nb_NO.ISO8859-1',
938    'br':                                   'br_FR.ISO8859-1',
939    'br_fr':                                'br_FR.ISO8859-1',
940    'brx_in':                               'brx_IN.UTF-8',
941    'bs':                                   'bs_BA.ISO8859-2',
942    'bs_ba':                                'bs_BA.ISO8859-2',
943    'bulgarian':                            'bg_BG.CP1251',
944    'byn_er':                               'byn_ER.UTF-8',
945    'c':                                    'C',
946    'c-french':                             'fr_CA.ISO8859-1',
947    'c.ascii':                              'C',
948    'c.en':                                 'C',
949    'c.iso88591':                           'en_US.ISO8859-1',
950    'c.utf8':                               'en_US.UTF-8',
951    'c_c':                                  'C',
952    'c_c.c':                                'C',
953    'ca':                                   'ca_ES.ISO8859-1',
954    'ca_ad':                                'ca_AD.ISO8859-1',
955    'ca_es':                                'ca_ES.ISO8859-1',
956    'ca_es@valencia':                       'ca_ES.UTF-8@valencia',
957    'ca_fr':                                'ca_FR.ISO8859-1',
958    'ca_it':                                'ca_IT.ISO8859-1',
959    'catalan':                              'ca_ES.ISO8859-1',
960    'ce_ru':                                'ce_RU.UTF-8',
961    'cextend':                              'en_US.ISO8859-1',
962    'chinese-s':                            'zh_CN.eucCN',
963    'chinese-t':                            'zh_TW.eucTW',
964    'chr_us':                               'chr_US.UTF-8',
965    'ckb_iq':                               'ckb_IQ.UTF-8',
966    'cmn_tw':                               'cmn_TW.UTF-8',
967    'crh_ua':                               'crh_UA.UTF-8',
968    'croatian':                             'hr_HR.ISO8859-2',
969    'cs':                                   'cs_CZ.ISO8859-2',
970    'cs_cs':                                'cs_CZ.ISO8859-2',
971    'cs_cz':                                'cs_CZ.ISO8859-2',
972    'csb_pl':                               'csb_PL.UTF-8',
973    'cv_ru':                                'cv_RU.UTF-8',
974    'cy':                                   'cy_GB.ISO8859-1',
975    'cy_gb':                                'cy_GB.ISO8859-1',
976    'cz':                                   'cs_CZ.ISO8859-2',
977    'cz_cz':                                'cs_CZ.ISO8859-2',
978    'czech':                                'cs_CZ.ISO8859-2',
979    'da':                                   'da_DK.ISO8859-1',
980    'da_dk':                                'da_DK.ISO8859-1',
981    'danish':                               'da_DK.ISO8859-1',
982    'dansk':                                'da_DK.ISO8859-1',
983    'de':                                   'de_DE.ISO8859-1',
984    'de_at':                                'de_AT.ISO8859-1',
985    'de_be':                                'de_BE.ISO8859-1',
986    'de_ch':                                'de_CH.ISO8859-1',
987    'de_de':                                'de_DE.ISO8859-1',
988    'de_it':                                'de_IT.ISO8859-1',
989    'de_li.utf8':                           'de_LI.UTF-8',
990    'de_lu':                                'de_LU.ISO8859-1',
991    'deutsch':                              'de_DE.ISO8859-1',
992    'doi_in':                               'doi_IN.UTF-8',
993    'dutch':                                'nl_NL.ISO8859-1',
994    'dutch.iso88591':                       'nl_BE.ISO8859-1',
995    'dv_mv':                                'dv_MV.UTF-8',
996    'dz_bt':                                'dz_BT.UTF-8',
997    'ee':                                   'ee_EE.ISO8859-4',
998    'ee_ee':                                'ee_EE.ISO8859-4',
999    'eesti':                                'et_EE.ISO8859-1',
1000    'el':                                   'el_GR.ISO8859-7',
1001    'el_cy':                                'el_CY.ISO8859-7',
1002    'el_gr':                                'el_GR.ISO8859-7',
1003    'el_gr@euro':                           'el_GR.ISO8859-15',
1004    'en':                                   'en_US.ISO8859-1',
1005    'en_ag':                                'en_AG.UTF-8',
1006    'en_au':                                'en_AU.ISO8859-1',
1007    'en_be':                                'en_BE.ISO8859-1',
1008    'en_bw':                                'en_BW.ISO8859-1',
1009    'en_ca':                                'en_CA.ISO8859-1',
1010    'en_dk':                                'en_DK.ISO8859-1',
1011    'en_dl.utf8':                           'en_DL.UTF-8',
1012    'en_gb':                                'en_GB.ISO8859-1',
1013    'en_hk':                                'en_HK.ISO8859-1',
1014    'en_ie':                                'en_IE.ISO8859-1',
1015    'en_il':                                'en_IL.UTF-8',
1016    'en_in':                                'en_IN.ISO8859-1',
1017    'en_ng':                                'en_NG.UTF-8',
1018    'en_nz':                                'en_NZ.ISO8859-1',
1019    'en_ph':                                'en_PH.ISO8859-1',
1020    'en_sc.utf8':                           'en_SC.UTF-8',
1021    'en_sg':                                'en_SG.ISO8859-1',
1022    'en_uk':                                'en_GB.ISO8859-1',
1023    'en_us':                                'en_US.ISO8859-1',
1024    'en_us@euro@euro':                      'en_US.ISO8859-15',
1025    'en_za':                                'en_ZA.ISO8859-1',
1026    'en_zm':                                'en_ZM.UTF-8',
1027    'en_zw':                                'en_ZW.ISO8859-1',
1028    'en_zw.utf8':                           'en_ZS.UTF-8',
1029    'eng_gb':                               'en_GB.ISO8859-1',
1030    'english':                              'en_EN.ISO8859-1',
1031    'english.iso88591':                     'en_US.ISO8859-1',
1032    'english_uk':                           'en_GB.ISO8859-1',
1033    'english_united-states':                'en_US.ISO8859-1',
1034    'english_united-states.437':            'C',
1035    'english_us':                           'en_US.ISO8859-1',
1036    'eo':                                   'eo_XX.ISO8859-3',
1037    'eo.utf8':                              'eo.UTF-8',
1038    'eo_eo':                                'eo_EO.ISO8859-3',
1039    'eo_us.utf8':                           'eo_US.UTF-8',
1040    'eo_xx':                                'eo_XX.ISO8859-3',
1041    'es':                                   'es_ES.ISO8859-1',
1042    'es_ar':                                'es_AR.ISO8859-1',
1043    'es_bo':                                'es_BO.ISO8859-1',
1044    'es_cl':                                'es_CL.ISO8859-1',
1045    'es_co':                                'es_CO.ISO8859-1',
1046    'es_cr':                                'es_CR.ISO8859-1',
1047    'es_cu':                                'es_CU.UTF-8',
1048    'es_do':                                'es_DO.ISO8859-1',
1049    'es_ec':                                'es_EC.ISO8859-1',
1050    'es_es':                                'es_ES.ISO8859-1',
1051    'es_gt':                                'es_GT.ISO8859-1',
1052    'es_hn':                                'es_HN.ISO8859-1',
1053    'es_mx':                                'es_MX.ISO8859-1',
1054    'es_ni':                                'es_NI.ISO8859-1',
1055    'es_pa':                                'es_PA.ISO8859-1',
1056    'es_pe':                                'es_PE.ISO8859-1',
1057    'es_pr':                                'es_PR.ISO8859-1',
1058    'es_py':                                'es_PY.ISO8859-1',
1059    'es_sv':                                'es_SV.ISO8859-1',
1060    'es_us':                                'es_US.ISO8859-1',
1061    'es_uy':                                'es_UY.ISO8859-1',
1062    'es_ve':                                'es_VE.ISO8859-1',
1063    'estonian':                             'et_EE.ISO8859-1',
1064    'et':                                   'et_EE.ISO8859-15',
1065    'et_ee':                                'et_EE.ISO8859-15',
1066    'eu':                                   'eu_ES.ISO8859-1',
1067    'eu_es':                                'eu_ES.ISO8859-1',
1068    'eu_fr':                                'eu_FR.ISO8859-1',
1069    'fa':                                   'fa_IR.UTF-8',
1070    'fa_ir':                                'fa_IR.UTF-8',
1071    'fa_ir.isiri3342':                      'fa_IR.ISIRI-3342',
1072    'ff_sn':                                'ff_SN.UTF-8',
1073    'fi':                                   'fi_FI.ISO8859-15',
1074    'fi_fi':                                'fi_FI.ISO8859-15',
1075    'fil_ph':                               'fil_PH.UTF-8',
1076    'finnish':                              'fi_FI.ISO8859-1',
1077    'fo':                                   'fo_FO.ISO8859-1',
1078    'fo_fo':                                'fo_FO.ISO8859-1',
1079    'fr':                                   'fr_FR.ISO8859-1',
1080    'fr_be':                                'fr_BE.ISO8859-1',
1081    'fr_ca':                                'fr_CA.ISO8859-1',
1082    'fr_ch':                                'fr_CH.ISO8859-1',
1083    'fr_fr':                                'fr_FR.ISO8859-1',
1084    'fr_lu':                                'fr_LU.ISO8859-1',
1085    'fran\xe7ais':                          'fr_FR.ISO8859-1',
1086    'fre_fr':                               'fr_FR.ISO8859-1',
1087    'french':                               'fr_FR.ISO8859-1',
1088    'french.iso88591':                      'fr_CH.ISO8859-1',
1089    'french_france':                        'fr_FR.ISO8859-1',
1090    'fur_it':                               'fur_IT.UTF-8',
1091    'fy_de':                                'fy_DE.UTF-8',
1092    'fy_nl':                                'fy_NL.UTF-8',
1093    'ga':                                   'ga_IE.ISO8859-1',
1094    'ga_ie':                                'ga_IE.ISO8859-1',
1095    'galego':                               'gl_ES.ISO8859-1',
1096    'galician':                             'gl_ES.ISO8859-1',
1097    'gd':                                   'gd_GB.ISO8859-1',
1098    'gd_gb':                                'gd_GB.ISO8859-1',
1099    'ger_de':                               'de_DE.ISO8859-1',
1100    'german':                               'de_DE.ISO8859-1',
1101    'german.iso88591':                      'de_CH.ISO8859-1',
1102    'german_germany':                       'de_DE.ISO8859-1',
1103    'gez_er':                               'gez_ER.UTF-8',
1104    'gez_et':                               'gez_ET.UTF-8',
1105    'gl':                                   'gl_ES.ISO8859-1',
1106    'gl_es':                                'gl_ES.ISO8859-1',
1107    'greek':                                'el_GR.ISO8859-7',
1108    'gu_in':                                'gu_IN.UTF-8',
1109    'gv':                                   'gv_GB.ISO8859-1',
1110    'gv_gb':                                'gv_GB.ISO8859-1',
1111    'ha_ng':                                'ha_NG.UTF-8',
1112    'hak_tw':                               'hak_TW.UTF-8',
1113    'he':                                   'he_IL.ISO8859-8',
1114    'he_il':                                'he_IL.ISO8859-8',
1115    'hebrew':                               'he_IL.ISO8859-8',
1116    'hi':                                   'hi_IN.ISCII-DEV',
1117    'hi_in':                                'hi_IN.ISCII-DEV',
1118    'hi_in.isciidev':                       'hi_IN.ISCII-DEV',
1119    'hif_fj':                               'hif_FJ.UTF-8',
1120    'hne':                                  'hne_IN.UTF-8',
1121    'hne_in':                               'hne_IN.UTF-8',
1122    'hr':                                   'hr_HR.ISO8859-2',
1123    'hr_hr':                                'hr_HR.ISO8859-2',
1124    'hrvatski':                             'hr_HR.ISO8859-2',
1125    'hsb_de':                               'hsb_DE.ISO8859-2',
1126    'ht_ht':                                'ht_HT.UTF-8',
1127    'hu':                                   'hu_HU.ISO8859-2',
1128    'hu_hu':                                'hu_HU.ISO8859-2',
1129    'hungarian':                            'hu_HU.ISO8859-2',
1130    'hy_am':                                'hy_AM.UTF-8',
1131    'hy_am.armscii8':                       'hy_AM.ARMSCII_8',
1132    'ia':                                   'ia.UTF-8',
1133    'ia_fr':                                'ia_FR.UTF-8',
1134    'icelandic':                            'is_IS.ISO8859-1',
1135    'id':                                   'id_ID.ISO8859-1',
1136    'id_id':                                'id_ID.ISO8859-1',
1137    'ig_ng':                                'ig_NG.UTF-8',
1138    'ik_ca':                                'ik_CA.UTF-8',
1139    'in':                                   'id_ID.ISO8859-1',
1140    'in_id':                                'id_ID.ISO8859-1',
1141    'is':                                   'is_IS.ISO8859-1',
1142    'is_is':                                'is_IS.ISO8859-1',
1143    'iso-8859-1':                           'en_US.ISO8859-1',
1144    'iso-8859-15':                          'en_US.ISO8859-15',
1145    'iso8859-1':                            'en_US.ISO8859-1',
1146    'iso8859-15':                           'en_US.ISO8859-15',
1147    'iso_8859_1':                           'en_US.ISO8859-1',
1148    'iso_8859_15':                          'en_US.ISO8859-15',
1149    'it':                                   'it_IT.ISO8859-1',
1150    'it_ch':                                'it_CH.ISO8859-1',
1151    'it_it':                                'it_IT.ISO8859-1',
1152    'italian':                              'it_IT.ISO8859-1',
1153    'iu':                                   'iu_CA.NUNACOM-8',
1154    'iu_ca':                                'iu_CA.NUNACOM-8',
1155    'iu_ca.nunacom8':                       'iu_CA.NUNACOM-8',
1156    'iw':                                   'he_IL.ISO8859-8',
1157    'iw_il':                                'he_IL.ISO8859-8',
1158    'iw_il.utf8':                           'iw_IL.UTF-8',
1159    'ja':                                   'ja_JP.eucJP',
1160    'ja_jp':                                'ja_JP.eucJP',
1161    'ja_jp.euc':                            'ja_JP.eucJP',
1162    'ja_jp.mscode':                         'ja_JP.SJIS',
1163    'ja_jp.pck':                            'ja_JP.SJIS',
1164    'japan':                                'ja_JP.eucJP',
1165    'japanese':                             'ja_JP.eucJP',
1166    'japanese-euc':                         'ja_JP.eucJP',
1167    'japanese.euc':                         'ja_JP.eucJP',
1168    'jp_jp':                                'ja_JP.eucJP',
1169    'ka':                                   'ka_GE.GEORGIAN-ACADEMY',
1170    'ka_ge':                                'ka_GE.GEORGIAN-ACADEMY',
1171    'ka_ge.georgianacademy':                'ka_GE.GEORGIAN-ACADEMY',
1172    'ka_ge.georgianps':                     'ka_GE.GEORGIAN-PS',
1173    'ka_ge.georgianrs':                     'ka_GE.GEORGIAN-ACADEMY',
1174    'kab_dz':                               'kab_DZ.UTF-8',
1175    'kk_kz':                                'kk_KZ.ptcp154',
1176    'kl':                                   'kl_GL.ISO8859-1',
1177    'kl_gl':                                'kl_GL.ISO8859-1',
1178    'km_kh':                                'km_KH.UTF-8',
1179    'kn':                                   'kn_IN.UTF-8',
1180    'kn_in':                                'kn_IN.UTF-8',
1181    'ko':                                   'ko_KR.eucKR',
1182    'ko_kr':                                'ko_KR.eucKR',
1183    'ko_kr.euc':                            'ko_KR.eucKR',
1184    'kok_in':                               'kok_IN.UTF-8',
1185    'korean':                               'ko_KR.eucKR',
1186    'korean.euc':                           'ko_KR.eucKR',
1187    'ks':                                   'ks_IN.UTF-8',
1188    'ks_in':                                'ks_IN.UTF-8',
1189    'ks_in@devanagari.utf8':                'ks_IN.UTF-8@devanagari',
1190    'ku_tr':                                'ku_TR.ISO8859-9',
1191    'kw':                                   'kw_GB.ISO8859-1',
1192    'kw_gb':                                'kw_GB.ISO8859-1',
1193    'ky':                                   'ky_KG.UTF-8',
1194    'ky_kg':                                'ky_KG.UTF-8',
1195    'lb_lu':                                'lb_LU.UTF-8',
1196    'lg_ug':                                'lg_UG.ISO8859-10',
1197    'li_be':                                'li_BE.UTF-8',
1198    'li_nl':                                'li_NL.UTF-8',
1199    'lij_it':                               'lij_IT.UTF-8',
1200    'lithuanian':                           'lt_LT.ISO8859-13',
1201    'ln_cd':                                'ln_CD.UTF-8',
1202    'lo':                                   'lo_LA.MULELAO-1',
1203    'lo_la':                                'lo_LA.MULELAO-1',
1204    'lo_la.cp1133':                         'lo_LA.IBM-CP1133',
1205    'lo_la.ibmcp1133':                      'lo_LA.IBM-CP1133',
1206    'lo_la.mulelao1':                       'lo_LA.MULELAO-1',
1207    'lt':                                   'lt_LT.ISO8859-13',
1208    'lt_lt':                                'lt_LT.ISO8859-13',
1209    'lv':                                   'lv_LV.ISO8859-13',
1210    'lv_lv':                                'lv_LV.ISO8859-13',
1211    'lzh_tw':                               'lzh_TW.UTF-8',
1212    'mag_in':                               'mag_IN.UTF-8',
1213    'mai':                                  'mai_IN.UTF-8',
1214    'mai_in':                               'mai_IN.UTF-8',
1215    'mai_np':                               'mai_NP.UTF-8',
1216    'mfe_mu':                               'mfe_MU.UTF-8',
1217    'mg_mg':                                'mg_MG.ISO8859-15',
1218    'mhr_ru':                               'mhr_RU.UTF-8',
1219    'mi':                                   'mi_NZ.ISO8859-1',
1220    'mi_nz':                                'mi_NZ.ISO8859-1',
1221    'miq_ni':                               'miq_NI.UTF-8',
1222    'mjw_in':                               'mjw_IN.UTF-8',
1223    'mk':                                   'mk_MK.ISO8859-5',
1224    'mk_mk':                                'mk_MK.ISO8859-5',
1225    'ml':                                   'ml_IN.UTF-8',
1226    'ml_in':                                'ml_IN.UTF-8',
1227    'mn_mn':                                'mn_MN.UTF-8',
1228    'mni_in':                               'mni_IN.UTF-8',
1229    'mr':                                   'mr_IN.UTF-8',
1230    'mr_in':                                'mr_IN.UTF-8',
1231    'ms':                                   'ms_MY.ISO8859-1',
1232    'ms_my':                                'ms_MY.ISO8859-1',
1233    'mt':                                   'mt_MT.ISO8859-3',
1234    'mt_mt':                                'mt_MT.ISO8859-3',
1235    'my_mm':                                'my_MM.UTF-8',
1236    'nan_tw':                               'nan_TW.UTF-8',
1237    'nb':                                   'nb_NO.ISO8859-1',
1238    'nb_no':                                'nb_NO.ISO8859-1',
1239    'nds_de':                               'nds_DE.UTF-8',
1240    'nds_nl':                               'nds_NL.UTF-8',
1241    'ne_np':                                'ne_NP.UTF-8',
1242    'nhn_mx':                               'nhn_MX.UTF-8',
1243    'niu_nu':                               'niu_NU.UTF-8',
1244    'niu_nz':                               'niu_NZ.UTF-8',
1245    'nl':                                   'nl_NL.ISO8859-1',
1246    'nl_aw':                                'nl_AW.UTF-8',
1247    'nl_be':                                'nl_BE.ISO8859-1',
1248    'nl_nl':                                'nl_NL.ISO8859-1',
1249    'nn':                                   'nn_NO.ISO8859-1',
1250    'nn_no':                                'nn_NO.ISO8859-1',
1251    'no':                                   'no_NO.ISO8859-1',
1252    'no@nynorsk':                           'ny_NO.ISO8859-1',
1253    'no_no':                                'no_NO.ISO8859-1',
1254    'no_no.iso88591@bokmal':                'no_NO.ISO8859-1',
1255    'no_no.iso88591@nynorsk':               'no_NO.ISO8859-1',
1256    'norwegian':                            'no_NO.ISO8859-1',
1257    'nr':                                   'nr_ZA.ISO8859-1',
1258    'nr_za':                                'nr_ZA.ISO8859-1',
1259    'nso':                                  'nso_ZA.ISO8859-15',
1260    'nso_za':                               'nso_ZA.ISO8859-15',
1261    'ny':                                   'ny_NO.ISO8859-1',
1262    'ny_no':                                'ny_NO.ISO8859-1',
1263    'nynorsk':                              'nn_NO.ISO8859-1',
1264    'oc':                                   'oc_FR.ISO8859-1',
1265    'oc_fr':                                'oc_FR.ISO8859-1',
1266    'om_et':                                'om_ET.UTF-8',
1267    'om_ke':                                'om_KE.ISO8859-1',
1268    'or':                                   'or_IN.UTF-8',
1269    'or_in':                                'or_IN.UTF-8',
1270    'os_ru':                                'os_RU.UTF-8',
1271    'pa':                                   'pa_IN.UTF-8',
1272    'pa_in':                                'pa_IN.UTF-8',
1273    'pa_pk':                                'pa_PK.UTF-8',
1274    'pap_an':                               'pap_AN.UTF-8',
1275    'pap_aw':                               'pap_AW.UTF-8',
1276    'pap_cw':                               'pap_CW.UTF-8',
1277    'pd':                                   'pd_US.ISO8859-1',
1278    'pd_de':                                'pd_DE.ISO8859-1',
1279    'pd_us':                                'pd_US.ISO8859-1',
1280    'ph':                                   'ph_PH.ISO8859-1',
1281    'ph_ph':                                'ph_PH.ISO8859-1',
1282    'pl':                                   'pl_PL.ISO8859-2',
1283    'pl_pl':                                'pl_PL.ISO8859-2',
1284    'polish':                               'pl_PL.ISO8859-2',
1285    'portuguese':                           'pt_PT.ISO8859-1',
1286    'portuguese_brazil':                    'pt_BR.ISO8859-1',
1287    'posix':                                'C',
1288    'posix-utf2':                           'C',
1289    'pp':                                   'pp_AN.ISO8859-1',
1290    'pp_an':                                'pp_AN.ISO8859-1',
1291    'ps_af':                                'ps_AF.UTF-8',
1292    'pt':                                   'pt_PT.ISO8859-1',
1293    'pt_br':                                'pt_BR.ISO8859-1',
1294    'pt_pt':                                'pt_PT.ISO8859-1',
1295    'quz_pe':                               'quz_PE.UTF-8',
1296    'raj_in':                               'raj_IN.UTF-8',
1297    'ro':                                   'ro_RO.ISO8859-2',
1298    'ro_ro':                                'ro_RO.ISO8859-2',
1299    'romanian':                             'ro_RO.ISO8859-2',
1300    'ru':                                   'ru_RU.UTF-8',
1301    'ru_ru':                                'ru_RU.UTF-8',
1302    'ru_ua':                                'ru_UA.KOI8-U',
1303    'rumanian':                             'ro_RO.ISO8859-2',
1304    'russian':                              'ru_RU.KOI8-R',
1305    'rw':                                   'rw_RW.ISO8859-1',
1306    'rw_rw':                                'rw_RW.ISO8859-1',
1307    'sa_in':                                'sa_IN.UTF-8',
1308    'sat_in':                               'sat_IN.UTF-8',
1309    'sc_it':                                'sc_IT.UTF-8',
1310    'sd':                                   'sd_IN.UTF-8',
1311    'sd_in':                                'sd_IN.UTF-8',
1312    'sd_in@devanagari.utf8':                'sd_IN.UTF-8@devanagari',
1313    'sd_pk':                                'sd_PK.UTF-8',
1314    'se_no':                                'se_NO.UTF-8',
1315    'serbocroatian':                        'sr_RS.UTF-8@latin',
1316    'sgs_lt':                               'sgs_LT.UTF-8',
1317    'sh':                                   'sr_RS.UTF-8@latin',
1318    'sh_ba.iso88592@bosnia':                'sr_CS.ISO8859-2',
1319    'sh_hr':                                'sh_HR.ISO8859-2',
1320    'sh_hr.iso88592':                       'hr_HR.ISO8859-2',
1321    'sh_sp':                                'sr_CS.ISO8859-2',
1322    'sh_yu':                                'sr_RS.UTF-8@latin',
1323    'shn_mm':                               'shn_MM.UTF-8',
1324    'shs_ca':                               'shs_CA.UTF-8',
1325    'si':                                   'si_LK.UTF-8',
1326    'si_lk':                                'si_LK.UTF-8',
1327    'sid_et':                               'sid_ET.UTF-8',
1328    'sinhala':                              'si_LK.UTF-8',
1329    'sk':                                   'sk_SK.ISO8859-2',
1330    'sk_sk':                                'sk_SK.ISO8859-2',
1331    'sl':                                   'sl_SI.ISO8859-2',
1332    'sl_cs':                                'sl_CS.ISO8859-2',
1333    'sl_si':                                'sl_SI.ISO8859-2',
1334    'slovak':                               'sk_SK.ISO8859-2',
1335    'slovene':                              'sl_SI.ISO8859-2',
1336    'slovenian':                            'sl_SI.ISO8859-2',
1337    'sm_ws':                                'sm_WS.UTF-8',
1338    'so_dj':                                'so_DJ.ISO8859-1',
1339    'so_et':                                'so_ET.UTF-8',
1340    'so_ke':                                'so_KE.ISO8859-1',
1341    'so_so':                                'so_SO.ISO8859-1',
1342    'sp':                                   'sr_CS.ISO8859-5',
1343    'sp_yu':                                'sr_CS.ISO8859-5',
1344    'spanish':                              'es_ES.ISO8859-1',
1345    'spanish_spain':                        'es_ES.ISO8859-1',
1346    'sq':                                   'sq_AL.ISO8859-2',
1347    'sq_al':                                'sq_AL.ISO8859-2',
1348    'sq_mk':                                'sq_MK.UTF-8',
1349    'sr':                                   'sr_RS.UTF-8',
1350    'sr@cyrillic':                          'sr_RS.UTF-8',
1351    'sr@latn':                              'sr_CS.UTF-8@latin',
1352    'sr_cs':                                'sr_CS.UTF-8',
1353    'sr_cs.iso88592@latn':                  'sr_CS.ISO8859-2',
1354    'sr_cs@latn':                           'sr_CS.UTF-8@latin',
1355    'sr_me':                                'sr_ME.UTF-8',
1356    'sr_rs':                                'sr_RS.UTF-8',
1357    'sr_rs@latn':                           'sr_RS.UTF-8@latin',
1358    'sr_sp':                                'sr_CS.ISO8859-2',
1359    'sr_yu':                                'sr_RS.UTF-8@latin',
1360    'sr_yu.cp1251@cyrillic':                'sr_CS.CP1251',
1361    'sr_yu.iso88592':                       'sr_CS.ISO8859-2',
1362    'sr_yu.iso88595':                       'sr_CS.ISO8859-5',
1363    'sr_yu.iso88595@cyrillic':              'sr_CS.ISO8859-5',
1364    'sr_yu.microsoftcp1251@cyrillic':       'sr_CS.CP1251',
1365    'sr_yu.utf8':                           'sr_RS.UTF-8',
1366    'sr_yu.utf8@cyrillic':                  'sr_RS.UTF-8',
1367    'sr_yu@cyrillic':                       'sr_RS.UTF-8',
1368    'ss':                                   'ss_ZA.ISO8859-1',
1369    'ss_za':                                'ss_ZA.ISO8859-1',
1370    'st':                                   'st_ZA.ISO8859-1',
1371    'st_za':                                'st_ZA.ISO8859-1',
1372    'sv':                                   'sv_SE.ISO8859-1',
1373    'sv_fi':                                'sv_FI.ISO8859-1',
1374    'sv_se':                                'sv_SE.ISO8859-1',
1375    'sw_ke':                                'sw_KE.UTF-8',
1376    'sw_tz':                                'sw_TZ.UTF-8',
1377    'swedish':                              'sv_SE.ISO8859-1',
1378    'szl_pl':                               'szl_PL.UTF-8',
1379    'ta':                                   'ta_IN.TSCII-0',
1380    'ta_in':                                'ta_IN.TSCII-0',
1381    'ta_in.tscii':                          'ta_IN.TSCII-0',
1382    'ta_in.tscii0':                         'ta_IN.TSCII-0',
1383    'ta_lk':                                'ta_LK.UTF-8',
1384    'tcy_in.utf8':                          'tcy_IN.UTF-8',
1385    'te':                                   'te_IN.UTF-8',
1386    'te_in':                                'te_IN.UTF-8',
1387    'tg':                                   'tg_TJ.KOI8-C',
1388    'tg_tj':                                'tg_TJ.KOI8-C',
1389    'th':                                   'th_TH.ISO8859-11',
1390    'th_th':                                'th_TH.ISO8859-11',
1391    'th_th.tactis':                         'th_TH.TIS620',
1392    'th_th.tis620':                         'th_TH.TIS620',
1393    'thai':                                 'th_TH.ISO8859-11',
1394    'the_np':                               'the_NP.UTF-8',
1395    'ti_er':                                'ti_ER.UTF-8',
1396    'ti_et':                                'ti_ET.UTF-8',
1397    'tig_er':                               'tig_ER.UTF-8',
1398    'tk_tm':                                'tk_TM.UTF-8',
1399    'tl':                                   'tl_PH.ISO8859-1',
1400    'tl_ph':                                'tl_PH.ISO8859-1',
1401    'tn':                                   'tn_ZA.ISO8859-15',
1402    'tn_za':                                'tn_ZA.ISO8859-15',
1403    'to_to':                                'to_TO.UTF-8',
1404    'tpi_pg':                               'tpi_PG.UTF-8',
1405    'tr':                                   'tr_TR.ISO8859-9',
1406    'tr_cy':                                'tr_CY.ISO8859-9',
1407    'tr_tr':                                'tr_TR.ISO8859-9',
1408    'ts':                                   'ts_ZA.ISO8859-1',
1409    'ts_za':                                'ts_ZA.ISO8859-1',
1410    'tt':                                   'tt_RU.TATAR-CYR',
1411    'tt_ru':                                'tt_RU.TATAR-CYR',
1412    'tt_ru.tatarcyr':                       'tt_RU.TATAR-CYR',
1413    'tt_ru@iqtelif':                        'tt_RU.UTF-8@iqtelif',
1414    'turkish':                              'tr_TR.ISO8859-9',
1415    'ug_cn':                                'ug_CN.UTF-8',
1416    'uk':                                   'uk_UA.KOI8-U',
1417    'uk_ua':                                'uk_UA.KOI8-U',
1418    'univ':                                 'en_US.utf',
1419    'universal':                            'en_US.utf',
1420    'universal.utf8@ucs4':                  'en_US.UTF-8',
1421    'unm_us':                               'unm_US.UTF-8',
1422    'ur':                                   'ur_PK.CP1256',
1423    'ur_in':                                'ur_IN.UTF-8',
1424    'ur_pk':                                'ur_PK.CP1256',
1425    'uz':                                   'uz_UZ.UTF-8',
1426    'uz_uz':                                'uz_UZ.UTF-8',
1427    'uz_uz@cyrillic':                       'uz_UZ.UTF-8',
1428    've':                                   've_ZA.UTF-8',
1429    've_za':                                've_ZA.UTF-8',
1430    'vi':                                   'vi_VN.TCVN',
1431    'vi_vn':                                'vi_VN.TCVN',
1432    'vi_vn.tcvn':                           'vi_VN.TCVN',
1433    'vi_vn.tcvn5712':                       'vi_VN.TCVN',
1434    'vi_vn.viscii':                         'vi_VN.VISCII',
1435    'vi_vn.viscii111':                      'vi_VN.VISCII',
1436    'wa':                                   'wa_BE.ISO8859-1',
1437    'wa_be':                                'wa_BE.ISO8859-1',
1438    'wae_ch':                               'wae_CH.UTF-8',
1439    'wal_et':                               'wal_ET.UTF-8',
1440    'wo_sn':                                'wo_SN.UTF-8',
1441    'xh':                                   'xh_ZA.ISO8859-1',
1442    'xh_za':                                'xh_ZA.ISO8859-1',
1443    'yi':                                   'yi_US.CP1255',
1444    'yi_us':                                'yi_US.CP1255',
1445    'yo_ng':                                'yo_NG.UTF-8',
1446    'yue_hk':                               'yue_HK.UTF-8',
1447    'yuw_pg':                               'yuw_PG.UTF-8',
1448    'zh':                                   'zh_CN.eucCN',
1449    'zh_cn':                                'zh_CN.gb2312',
1450    'zh_cn.big5':                           'zh_TW.big5',
1451    'zh_cn.euc':                            'zh_CN.eucCN',
1452    'zh_hk':                                'zh_HK.big5hkscs',
1453    'zh_hk.big5hk':                         'zh_HK.big5hkscs',
1454    'zh_sg':                                'zh_SG.GB2312',
1455    'zh_sg.gbk':                            'zh_SG.GBK',
1456    'zh_tw':                                'zh_TW.big5',
1457    'zh_tw.euc':                            'zh_TW.eucTW',
1458    'zh_tw.euctw':                          'zh_TW.eucTW',
1459    'zu':                                   'zu_ZA.ISO8859-1',
1460    'zu_za':                                'zu_ZA.ISO8859-1',
1461}
1462
1463#
1464# This maps Windows language identifiers to locale strings.
1465#
1466# This list has been updated from
1467# http://msdn.microsoft.com/library/default.asp?url=/library/en-us/intl/nls_238z.asp
1468# to include every locale up to Windows Vista.
1469#
1470# NOTE: this mapping is incomplete.  If your language is missing, please
1471# submit a bug report to the Python bug tracker at http://bugs.python.org/
1472# Make sure you include the missing language identifier and the suggested
1473# locale code.
1474#
1475
1476windows_locale = {
1477    0x0436: "af_ZA", # Afrikaans
1478    0x041c: "sq_AL", # Albanian
1479    0x0484: "gsw_FR",# Alsatian - France
1480    0x045e: "am_ET", # Amharic - Ethiopia
1481    0x0401: "ar_SA", # Arabic - Saudi Arabia
1482    0x0801: "ar_IQ", # Arabic - Iraq
1483    0x0c01: "ar_EG", # Arabic - Egypt
1484    0x1001: "ar_LY", # Arabic - Libya
1485    0x1401: "ar_DZ", # Arabic - Algeria
1486    0x1801: "ar_MA", # Arabic - Morocco
1487    0x1c01: "ar_TN", # Arabic - Tunisia
1488    0x2001: "ar_OM", # Arabic - Oman
1489    0x2401: "ar_YE", # Arabic - Yemen
1490    0x2801: "ar_SY", # Arabic - Syria
1491    0x2c01: "ar_JO", # Arabic - Jordan
1492    0x3001: "ar_LB", # Arabic - Lebanon
1493    0x3401: "ar_KW", # Arabic - Kuwait
1494    0x3801: "ar_AE", # Arabic - United Arab Emirates
1495    0x3c01: "ar_BH", # Arabic - Bahrain
1496    0x4001: "ar_QA", # Arabic - Qatar
1497    0x042b: "hy_AM", # Armenian
1498    0x044d: "as_IN", # Assamese - India
1499    0x042c: "az_AZ", # Azeri - Latin
1500    0x082c: "az_AZ", # Azeri - Cyrillic
1501    0x046d: "ba_RU", # Bashkir
1502    0x042d: "eu_ES", # Basque - Russia
1503    0x0423: "be_BY", # Belarusian
1504    0x0445: "bn_IN", # Begali
1505    0x201a: "bs_BA", # Bosnian - Cyrillic
1506    0x141a: "bs_BA", # Bosnian - Latin
1507    0x047e: "br_FR", # Breton - France
1508    0x0402: "bg_BG", # Bulgarian
1509#    0x0455: "my_MM", # Burmese - Not supported
1510    0x0403: "ca_ES", # Catalan
1511    0x0004: "zh_CHS",# Chinese - Simplified
1512    0x0404: "zh_TW", # Chinese - Taiwan
1513    0x0804: "zh_CN", # Chinese - PRC
1514    0x0c04: "zh_HK", # Chinese - Hong Kong S.A.R.
1515    0x1004: "zh_SG", # Chinese - Singapore
1516    0x1404: "zh_MO", # Chinese - Macao S.A.R.
1517    0x7c04: "zh_CHT",# Chinese - Traditional
1518    0x0483: "co_FR", # Corsican - France
1519    0x041a: "hr_HR", # Croatian
1520    0x101a: "hr_BA", # Croatian - Bosnia
1521    0x0405: "cs_CZ", # Czech
1522    0x0406: "da_DK", # Danish
1523    0x048c: "gbz_AF",# Dari - Afghanistan
1524    0x0465: "div_MV",# Divehi - Maldives
1525    0x0413: "nl_NL", # Dutch - The Netherlands
1526    0x0813: "nl_BE", # Dutch - Belgium
1527    0x0409: "en_US", # English - United States
1528    0x0809: "en_GB", # English - United Kingdom
1529    0x0c09: "en_AU", # English - Australia
1530    0x1009: "en_CA", # English - Canada
1531    0x1409: "en_NZ", # English - New Zealand
1532    0x1809: "en_IE", # English - Ireland
1533    0x1c09: "en_ZA", # English - South Africa
1534    0x2009: "en_JA", # English - Jamaica
1535    0x2409: "en_CB", # English - Caribbean
1536    0x2809: "en_BZ", # English - Belize
1537    0x2c09: "en_TT", # English - Trinidad
1538    0x3009: "en_ZW", # English - Zimbabwe
1539    0x3409: "en_PH", # English - Philippines
1540    0x4009: "en_IN", # English - India
1541    0x4409: "en_MY", # English - Malaysia
1542    0x4809: "en_IN", # English - Singapore
1543    0x0425: "et_EE", # Estonian
1544    0x0438: "fo_FO", # Faroese
1545    0x0464: "fil_PH",# Filipino
1546    0x040b: "fi_FI", # Finnish
1547    0x040c: "fr_FR", # French - France
1548    0x080c: "fr_BE", # French - Belgium
1549    0x0c0c: "fr_CA", # French - Canada
1550    0x100c: "fr_CH", # French - Switzerland
1551    0x140c: "fr_LU", # French - Luxembourg
1552    0x180c: "fr_MC", # French - Monaco
1553    0x0462: "fy_NL", # Frisian - Netherlands
1554    0x0456: "gl_ES", # Galician
1555    0x0437: "ka_GE", # Georgian
1556    0x0407: "de_DE", # German - Germany
1557    0x0807: "de_CH", # German - Switzerland
1558    0x0c07: "de_AT", # German - Austria
1559    0x1007: "de_LU", # German - Luxembourg
1560    0x1407: "de_LI", # German - Liechtenstein
1561    0x0408: "el_GR", # Greek
1562    0x046f: "kl_GL", # Greenlandic - Greenland
1563    0x0447: "gu_IN", # Gujarati
1564    0x0468: "ha_NG", # Hausa - Latin
1565    0x040d: "he_IL", # Hebrew
1566    0x0439: "hi_IN", # Hindi
1567    0x040e: "hu_HU", # Hungarian
1568    0x040f: "is_IS", # Icelandic
1569    0x0421: "id_ID", # Indonesian
1570    0x045d: "iu_CA", # Inuktitut - Syllabics
1571    0x085d: "iu_CA", # Inuktitut - Latin
1572    0x083c: "ga_IE", # Irish - Ireland
1573    0x0410: "it_IT", # Italian - Italy
1574    0x0810: "it_CH", # Italian - Switzerland
1575    0x0411: "ja_JP", # Japanese
1576    0x044b: "kn_IN", # Kannada - India
1577    0x043f: "kk_KZ", # Kazakh
1578    0x0453: "kh_KH", # Khmer - Cambodia
1579    0x0486: "qut_GT",# K'iche - Guatemala
1580    0x0487: "rw_RW", # Kinyarwanda - Rwanda
1581    0x0457: "kok_IN",# Konkani
1582    0x0412: "ko_KR", # Korean
1583    0x0440: "ky_KG", # Kyrgyz
1584    0x0454: "lo_LA", # Lao - Lao PDR
1585    0x0426: "lv_LV", # Latvian
1586    0x0427: "lt_LT", # Lithuanian
1587    0x082e: "dsb_DE",# Lower Sorbian - Germany
1588    0x046e: "lb_LU", # Luxembourgish
1589    0x042f: "mk_MK", # FYROM Macedonian
1590    0x043e: "ms_MY", # Malay - Malaysia
1591    0x083e: "ms_BN", # Malay - Brunei Darussalam
1592    0x044c: "ml_IN", # Malayalam - India
1593    0x043a: "mt_MT", # Maltese
1594    0x0481: "mi_NZ", # Maori
1595    0x047a: "arn_CL",# Mapudungun
1596    0x044e: "mr_IN", # Marathi
1597    0x047c: "moh_CA",# Mohawk - Canada
1598    0x0450: "mn_MN", # Mongolian - Cyrillic
1599    0x0850: "mn_CN", # Mongolian - PRC
1600    0x0461: "ne_NP", # Nepali
1601    0x0414: "nb_NO", # Norwegian - Bokmal
1602    0x0814: "nn_NO", # Norwegian - Nynorsk
1603    0x0482: "oc_FR", # Occitan - France
1604    0x0448: "or_IN", # Oriya - India
1605    0x0463: "ps_AF", # Pashto - Afghanistan
1606    0x0429: "fa_IR", # Persian
1607    0x0415: "pl_PL", # Polish
1608    0x0416: "pt_BR", # Portuguese - Brazil
1609    0x0816: "pt_PT", # Portuguese - Portugal
1610    0x0446: "pa_IN", # Punjabi
1611    0x046b: "quz_BO",# Quechua (Bolivia)
1612    0x086b: "quz_EC",# Quechua (Ecuador)
1613    0x0c6b: "quz_PE",# Quechua (Peru)
1614    0x0418: "ro_RO", # Romanian - Romania
1615    0x0417: "rm_CH", # Romansh
1616    0x0419: "ru_RU", # Russian
1617    0x243b: "smn_FI",# Sami Finland
1618    0x103b: "smj_NO",# Sami Norway
1619    0x143b: "smj_SE",# Sami Sweden
1620    0x043b: "se_NO", # Sami Northern Norway
1621    0x083b: "se_SE", # Sami Northern Sweden
1622    0x0c3b: "se_FI", # Sami Northern Finland
1623    0x203b: "sms_FI",# Sami Skolt
1624    0x183b: "sma_NO",# Sami Southern Norway
1625    0x1c3b: "sma_SE",# Sami Southern Sweden
1626    0x044f: "sa_IN", # Sanskrit
1627    0x0c1a: "sr_SP", # Serbian - Cyrillic
1628    0x1c1a: "sr_BA", # Serbian - Bosnia Cyrillic
1629    0x081a: "sr_SP", # Serbian - Latin
1630    0x181a: "sr_BA", # Serbian - Bosnia Latin
1631    0x045b: "si_LK", # Sinhala - Sri Lanka
1632    0x046c: "ns_ZA", # Northern Sotho
1633    0x0432: "tn_ZA", # Setswana - Southern Africa
1634    0x041b: "sk_SK", # Slovak
1635    0x0424: "sl_SI", # Slovenian
1636    0x040a: "es_ES", # Spanish - Spain
1637    0x080a: "es_MX", # Spanish - Mexico
1638    0x0c0a: "es_ES", # Spanish - Spain (Modern)
1639    0x100a: "es_GT", # Spanish - Guatemala
1640    0x140a: "es_CR", # Spanish - Costa Rica
1641    0x180a: "es_PA", # Spanish - Panama
1642    0x1c0a: "es_DO", # Spanish - Dominican Republic
1643    0x200a: "es_VE", # Spanish - Venezuela
1644    0x240a: "es_CO", # Spanish - Colombia
1645    0x280a: "es_PE", # Spanish - Peru
1646    0x2c0a: "es_AR", # Spanish - Argentina
1647    0x300a: "es_EC", # Spanish - Ecuador
1648    0x340a: "es_CL", # Spanish - Chile
1649    0x380a: "es_UR", # Spanish - Uruguay
1650    0x3c0a: "es_PY", # Spanish - Paraguay
1651    0x400a: "es_BO", # Spanish - Bolivia
1652    0x440a: "es_SV", # Spanish - El Salvador
1653    0x480a: "es_HN", # Spanish - Honduras
1654    0x4c0a: "es_NI", # Spanish - Nicaragua
1655    0x500a: "es_PR", # Spanish - Puerto Rico
1656    0x540a: "es_US", # Spanish - United States
1657#    0x0430: "", # Sutu - Not supported
1658    0x0441: "sw_KE", # Swahili
1659    0x041d: "sv_SE", # Swedish - Sweden
1660    0x081d: "sv_FI", # Swedish - Finland
1661    0x045a: "syr_SY",# Syriac
1662    0x0428: "tg_TJ", # Tajik - Cyrillic
1663    0x085f: "tmz_DZ",# Tamazight - Latin
1664    0x0449: "ta_IN", # Tamil
1665    0x0444: "tt_RU", # Tatar
1666    0x044a: "te_IN", # Telugu
1667    0x041e: "th_TH", # Thai
1668    0x0851: "bo_BT", # Tibetan - Bhutan
1669    0x0451: "bo_CN", # Tibetan - PRC
1670    0x041f: "tr_TR", # Turkish
1671    0x0442: "tk_TM", # Turkmen - Cyrillic
1672    0x0480: "ug_CN", # Uighur - Arabic
1673    0x0422: "uk_UA", # Ukrainian
1674    0x042e: "wen_DE",# Upper Sorbian - Germany
1675    0x0420: "ur_PK", # Urdu
1676    0x0820: "ur_IN", # Urdu - India
1677    0x0443: "uz_UZ", # Uzbek - Latin
1678    0x0843: "uz_UZ", # Uzbek - Cyrillic
1679    0x042a: "vi_VN", # Vietnamese
1680    0x0452: "cy_GB", # Welsh
1681    0x0488: "wo_SN", # Wolof - Senegal
1682    0x0434: "xh_ZA", # Xhosa - South Africa
1683    0x0485: "sah_RU",# Yakut - Cyrillic
1684    0x0478: "ii_CN", # Yi - PRC
1685    0x046a: "yo_NG", # Yoruba - Nigeria
1686    0x0435: "zu_ZA", # Zulu
1687}
1688
1689def _print_locale():
1690
1691    """ Test function.
1692    """
1693    categories = {}
1694    def _init_categories(categories=categories):
1695        for k,v in globals().items():
1696            if k[:3] == 'LC_':
1697                categories[k] = v
1698    _init_categories()
1699    del categories['LC_ALL']
1700
1701    print('Locale defaults as determined by getdefaultlocale():')
1702    print('-'*72)
1703    lang, enc = getdefaultlocale()
1704    print('Language: ', lang or '(undefined)')
1705    print('Encoding: ', enc or '(undefined)')
1706    print()
1707
1708    print('Locale settings on startup:')
1709    print('-'*72)
1710    for name,category in categories.items():
1711        print(name, '...')
1712        lang, enc = getlocale(category)
1713        print('   Language: ', lang or '(undefined)')
1714        print('   Encoding: ', enc or '(undefined)')
1715        print()
1716
1717    print()
1718    print('Locale settings after calling resetlocale():')
1719    print('-'*72)
1720    resetlocale()
1721    for name,category in categories.items():
1722        print(name, '...')
1723        lang, enc = getlocale(category)
1724        print('   Language: ', lang or '(undefined)')
1725        print('   Encoding: ', enc or '(undefined)')
1726        print()
1727
1728    try:
1729        setlocale(LC_ALL, "")
1730    except:
1731        print('NOTE:')
1732        print('setlocale(LC_ALL, "") does not support the default locale')
1733        print('given in the OS environment variables.')
1734    else:
1735        print()
1736        print('Locale settings after calling setlocale(LC_ALL, ""):')
1737        print('-'*72)
1738        for name,category in categories.items():
1739            print(name, '...')
1740            lang, enc = getlocale(category)
1741            print('   Language: ', lang or '(undefined)')
1742            print('   Encoding: ', enc or '(undefined)')
1743            print()
1744
1745###
1746
1747try:
1748    LC_MESSAGES
1749except NameError:
1750    pass
1751else:
1752    __all__.append("LC_MESSAGES")
1753
1754if __name__=='__main__':
1755    print('Locale aliasing:')
1756    print()
1757    _print_locale()
1758    print()
1759    print('Number formatting:')
1760    print()
1761    _test()
1762