Lib/locale.py

   1 """ Locale support.
   2
   3     The module provides low-level access to the C lib's locale APIs
   4     and adds high level number formatting APIs as well as a locale
   5     aliasing engine to complement these.
   6
   7     The aliasing engine includes support for many commonly used locale
   8     names and maps them to values suitable for passing to the C lib's
   9     setlocale() function. It also includes default encodings for all
  10     supported locale names.
  11
  12 """
  13
  14 import string, sys
  15
  16 # Try importing the _locale module.
  17 #
  18 # If this fails, fall back on a basic 'C' locale emulation.
  19 #
  20
  21 try:
  22
  23     from _locale import *
  24
  25 except ImportError:
  26
  27     # Locale emulation
  28
  29     CHAR_MAX = 127
  30     LC_ALL = 6
  31     LC_COLLATE = 3
  32     LC_CTYPE = 0
  33     LC_MESSAGES = 5
  34     LC_MONETARY = 4
  35     LC_NUMERIC = 1
  36     LC_TIME = 2
  37     Error = ValueError
  38
  39     def localeconv():
  40         """ localeconv() -> dict.
  41             Returns numeric and monetary locale-specific parameters.
  42         """
  43         # 'C' locale default values
  44         return {'grouping': [127],
  45                 'currency_symbol': '',
  46                 'n_sign_posn': 127,
  47                 'p_cs_precedes': 127,
  48                 'n_cs_precedes': 127,
  49                 'mon_grouping': [],
  50                 'n_sep_by_space': 127,
  51                 'decimal_point': '.',
  52                 'negative_sign': '',
  53                 'positive_sign': '',
  54                 'p_sep_by_space': 127,
  55                 'int_curr_symbol': '',
  56                 'p_sign_posn': 127,
  57                 'thousands_sep': '',
  58                 'mon_thousands_sep': '',
  59                 'frac_digits': 127,
  60                 'mon_decimal_point': '',
  61                 'int_frac_digits': 127}
  62
  63     def setlocale(category, value=None):
  64         """ setlocale(integer,string=None) -> string.
  65             Activates/queries locale processing.
  66         """
  67         if value is not None and \
  68            value is not 'C':
  69             raise Error, '_locale emulation only supports "C" locale'
  70         return 'C'
  71
  72     def strcoll(a,b):
  73         """ strcoll(string,string) -> int.
  74             Compares two strings according to the locale.
  75         """
  76         return cmp(a,b)
  77
  78     def strxfrm(s):
  79         """ strxfrm(string) -> string.
  80             Returns a string that behaves for cmp locale-aware.
  81         """
  82         return s
  83
  84 ### Number formatting APIs
  85
  86 # Author: Martin von Loewis
  87
  88 #perform the grouping from right to left
  89 def _group(s):
  90     conv=localeconv()
  91     grouping=conv['grouping']
  92     if not grouping:return s
  93     result=""
  94     while s and grouping:
  95         # if grouping is -1, we are done
  96         if grouping[0]==CHAR_MAX:
  97             break
  98         # 0: re-use last group ad infinitum
  99         elif grouping[0]!=0:
 100             #process last group
 101             group=grouping[0]
 102             grouping=grouping[1:]
 103         if result:
 104             result=s[-group:]+conv['thousands_sep']+result
 105         else:
 106             result=s[-group:]
 107         s=s[:-group]
 108     if not result:
 109         return s
 110     if s:
 111         result=s+conv['thousands_sep']+result
 112     return result
 113
 114 def format(f,val,grouping=0):
 115     """Formats a value in the same way that the % formatting would use,
 116     but takes the current locale into account.
 117     Grouping is applied if the third parameter is true."""
 118     result = f % val
 119     fields = string.split(result, ".")
 120     if grouping:
 121         fields[0]=_group(fields[0])
 122     if len(fields)==2:
 123         return fields[0]+localeconv()['decimal_point']+fields[1]
 124     elif len(fields)==1:
 125         return fields[0]
 126     else:
 127         raise Error, "Too many decimal points in result string"
 128
 129 def str(val):
 130     """Convert float to integer, taking the locale into account."""
 131     return format("%.12g",val)
 132
 133 def atof(str,func=string.atof):
 134     "Parses a string as a float according to the locale settings."
 135     #First, get rid of the grouping
 136     ts = localeconv()['thousands_sep']
 137     if ts:
 138         s=string.split(str,ts)
 139         str=string.join(s, "")
 140     #next, replace the decimal point with a dot
 141     dd = localeconv()['decimal_point']
 142     if dd:
 143         s=string.split(str,dd)
 144         str=string.join(s, '.')
 145     #finally, parse the string
 146     return func(str)
 147
 148 def atoi(str):
 149     "Converts a string to an integer according to the locale settings."
 150     return atof(str,string.atoi)
 151
 152 def _test():
 153     setlocale(LC_ALL, "")
 154     #do grouping
 155     s1=format("%d", 123456789,1)
 156     print s1, "is", atoi(s1)
 157     #standard formatting
 158     s1=str(3.14)
 159     print s1, "is", atof(s1)
 160
 161 ### Locale name aliasing engine
 162
 163 # Author: Marc-Andre Lemburg, mal@lemburg.com
 164 # Various tweaks by Fredrik Lundh <effbot@telia.com>
 165
 166 # store away the low-level version of setlocale (it's
 167 # overridden below)
 168 _setlocale = setlocale
 169
 170 def normalize(localename):
 171
 172     """ Returns a normalized locale code for the given locale
 173         name.
 174
 175         The returned locale code is formatted for use with
 176         setlocale().
 177
 178         If normalization fails, the original name is returned
 179         unchanged.
 180
 181         If the given encoding is not known, the function defaults to
 182         the default encoding for the locale code just like setlocale()
 183         does.
 184
 185     """
 186     # Normalize the locale name and extract the encoding
 187     fullname = string.lower(localename)
 188     if ':' in fullname:
 189         # ':' is sometimes used as encoding delimiter.
 190         fullname = string.replace(fullname, ':', '.')
 191     if '.' in fullname:
 192         langname, encoding = string.split(fullname, '.')[:2]
 193         fullname = langname + '.' + encoding
 194     else:
 195         langname = fullname
 196         encoding = ''
 197
 198     # First lookup: fullname (possibly with encoding)
 199     code = locale_alias.get(fullname, None)
 200     if code is not None:
 201         return code
 202
 203     # Second try: langname (without encoding)
 204     code = locale_alias.get(langname, None)
 205     if code is not None:
 206         if '.' in code:
 207             langname, defenc = string.split(code, '.')
 208         else:
 209             langname = code
 210             defenc = ''
 211         if encoding:
 212             encoding = encoding_alias.get(encoding, encoding)
 213         else:
 214             encoding = defenc
 215         if encoding:
 216             return langname + '.' + encoding
 217         else:
 218             return langname
 219
 220     else:
 221         return localename
 222
 223 def _parse_localename(localename):
 224
 225     """ Parses the locale code for localename and returns the
 226         result as tuple (language code, encoding).
 227
 228         The localename is normalized and passed through the locale
 229         alias engine. A ValueError is raised in case the locale name
 230         cannot be parsed.
 231
 232         The language code corresponds to RFC 1766.  code and encoding
 233         can be None in case the values cannot be determined or are
 234         unknown to this implementation.
 235
 236     """
 237     code = normalize(localename)
 238     if '.' in code:
 239         return string.split(code, '.')[:2]
 240     elif code == 'C':
 241         return None, None
 242     else:
 243         raise ValueError, 'unknown locale: %s' % localename
 244     return l
 245
 246 def _build_localename(localetuple):
 247
 248     """ Builds a locale code from the given tuple (language code,
 249         encoding).
 250
 251         No aliasing or normalizing takes place.
 252
 253     """
 254     language, encoding = localetuple
 255     if language is None:
 256         language = 'C'
 257     if encoding is None:
 258         return language
 259     else:
 260         return language + '.' + encoding
 261
 262 def getdefaultlocale(envvars=('LANGUAGE', 'LC_ALL', 'LC_CTYPE', 'LANG')):
 263
 264     """ Tries to determine the default locale settings and returns
 265         them as tuple (language code, encoding).
 266
 267         According to POSIX, a program which has not called
 268         setlocale(LC_ALL, "") runs using the portable 'C' locale.
 269         Calling setlocale(LC_ALL, "") lets it use the default locale as
 270         defined by the LANG variable. Since we don't want to interfere
 271         with the current locale setting we thus emulate the behavior
 272         in the way described above.
 273
 274         To maintain compatibility with other platforms, not only the
 275         LANG variable is tested, but a list of variables given as
 276         envvars parameter. The first found to be defined will be
 277         used. envvars defaults to the search path used in GNU gettext;
 278         it must always contain the variable name 'LANG'.
 279
 280         Except for the code 'C', the language code corresponds to RFC
 281         1766.  code and encoding can be None in case the values cannot
 282         be determined.
 283
 284     """
 285
 286     try:
 287         # check if it's supported by the _locale module
 288         import _locale
 289         code, encoding = _locale._getdefaultlocale()
 290     except (ImportError, AttributeError):
 291         pass
 292     else:
 293         # make sure the code/encoding values are valid
 294         if sys.platform == "win32" and code and code[:2] == "0x":
 295             # map windows language identifier to language name
 296             code = windows_locale.get(int(code, 0))
 297         # ...add other platform-specific processing here, if
 298         # necessary...
 299         return code, encoding
 300
 301     # fall back on POSIX behaviour
 302     import os
 303     lookup = os.environ.get
 304     for variable in envvars:
 305         localename = lookup(variable,None)
 306         if localename is not None:
 307             break
 308     else:
 309         localename = 'C'
 310     return _parse_localename(localename)
 311
 312
 313 def getlocale(category=LC_CTYPE):
 314
 315     """ Returns the current setting for the given locale category as
 316         tuple (language code, encoding).
 317
 318         category may be one of the LC_* value except LC_ALL. It
 319         defaults to LC_CTYPE.
 320
 321         Except for the code 'C', the language code corresponds to RFC
 322         1766.  code and encoding can be None in case the values cannot
 323         be determined.
 324
 325     """
 326     localename = _setlocale(category)
 327     if category == LC_ALL and ';' in localename:
 328         raise TypeError, 'category LC_ALL is not supported'
 329     return _parse_localename(localename)
 330
 331 def setlocale(category, locale=None):
 332
 333     """ Set the locale for the given category.  The locale can be
 334         a string, a locale tuple (language code, encoding), or None.
 335
 336         Locale tuples are converted to strings the locale aliasing
 337         engine.  Locale strings are passed directly to the C lib.
 338
 339         category may be given as one of the LC_* values.
 340
 341     """
 342     if locale and type(locale) is not type(""):
 343         # convert to string
 344         locale = normalize(_build_localename(locale))
 345     return _setlocale(category, locale)
 346
 347 def resetlocale(category=LC_ALL):
 348
 349     """ Sets the locale for category to the default setting.
 350
 351         The default setting is determined by calling
 352         getdefaultlocale(). category defaults to LC_ALL.
 353
 354     """
 355     _setlocale(category, _build_localename(getdefaultlocale()))
 356
 357 ### Database
 358 #
 359 # The following data was extracted from the locale.alias file which
 360 # comes with X11 and then hand edited removing the explicit encoding
 361 # definitions and adding some more aliases. The file is usually
 362 # available as /usr/lib/X11/locale/locale.alias.
 363 #
 364
 365 #
 366 # The encoding_alias table maps lowercase encoding alias names to C
 367 # locale encoding names (case-sensitive).
 368 #
 369 encoding_alias = {
 370         '437':                          'C',
 371         'c':                            'C',
 372         'iso8859':                      'ISO8859-1',
 373         '8859':                         'ISO8859-1',
 374         '88591':                        'ISO8859-1',
 375         'ascii':                        'ISO8859-1',
 376         'en':                           'ISO8859-1',
 377         'iso88591':                     'ISO8859-1',
 378         'iso_8859-1':                   'ISO8859-1',
 379         '885915':                       'ISO8859-15',
 380         'iso885915':                    'ISO8859-15',
 381         'iso_8859-15':                  'ISO8859-15',
 382         'iso8859-2':                    'ISO8859-2',
 383         'iso88592':                     'ISO8859-2',
 384         'iso_8859-2':                   'ISO8859-2',
 385         'iso88595':                     'ISO8859-5',
 386         'iso88596':                     'ISO8859-6',
 387         'iso88597':                     'ISO8859-7',
 388         'iso88598':                     'ISO8859-8',
 389         'iso88599':                     'ISO8859-9',
 390         'iso-2022-jp':                  'JIS7',
 391         'jis':                          'JIS7',
 392         'jis7':                         'JIS7',
 393         'sjis':                         'SJIS',
 394         'tis620':                       'TACTIS',
 395         'ajec':                         'eucJP',
 396         'eucjp':                        'eucJP',
 397         'ujis':                         'eucJP',
 398         'utf-8':                        'utf',
 399         'utf8':                         'utf',
 400         'utf8@ucs4':                    'utf',
 401 }
 402
 403 #
 404 # The locale_alias table maps lowercase alias names to C locale names
 405 # (case-sensitive). Encodings are always separated from the locale
 406 # name using a dot ('.'); they should only be given in case the
 407 # language name is needed to interpret the given encoding alias
 408 # correctly (CJK codes often have this need).
 409 #
 410 locale_alias = {
 411         'american':                      'en_US.ISO8859-1',
 412         'ar':                            'ar_AA.ISO8859-6',
 413         'ar_aa':                         'ar_AA.ISO8859-6',
 414         'ar_sa':                         'ar_SA.ISO8859-6',
 415         'arabic':                        'ar_AA.ISO8859-6',
 416         'bg':                            'bg_BG.ISO8859-5',
 417         'bg_bg':                         'bg_BG.ISO8859-5',
 418         'bulgarian':                     'bg_BG.ISO8859-5',
 419         'c-french':                      'fr_CA.ISO8859-1',
 420         'c':                             'C',
 421         'c_c':                           'C',
 422         'cextend':                       'en_US.ISO8859-1',
 423         'chinese-s':                     'zh_CN.eucCN',
 424         'chinese-t':                     'zh_TW.eucTW',
 425         'croatian':                      'hr_HR.ISO8859-2',
 426         'cs':                            'cs_CZ.ISO8859-2',
 427         'cs_cs':                         'cs_CZ.ISO8859-2',
 428         'cs_cz':                         'cs_CZ.ISO8859-2',
 429         'cz':                            'cz_CZ.ISO8859-2',
 430         'cz_cz':                         'cz_CZ.ISO8859-2',
 431         'czech':                         'cs_CS.ISO8859-2',
 432         'da':                            'da_DK.ISO8859-1',
 433         'da_dk':                         'da_DK.ISO8859-1',
 434         'danish':                        'da_DK.ISO8859-1',
 435         'de':                            'de_DE.ISO8859-1',
 436         'de_at':                         'de_AT.ISO8859-1',
 437         'de_ch':                         'de_CH.ISO8859-1',
 438         'de_de':                         'de_DE.ISO8859-1',
 439         'dutch':                         'nl_BE.ISO8859-1',
 440         'ee':                            'ee_EE.ISO8859-4',
 441         'el':                            'el_GR.ISO8859-7',
 442         'el_gr':                         'el_GR.ISO8859-7',
 443         'en':                            'en_US.ISO8859-1',
 444         'en_au':                         'en_AU.ISO8859-1',
 445         'en_ca':                         'en_CA.ISO8859-1',
 446         'en_gb':                         'en_GB.ISO8859-1',
 447         'en_ie':                         'en_IE.ISO8859-1',
 448         'en_nz':                         'en_NZ.ISO8859-1',
 449         'en_uk':                         'en_GB.ISO8859-1',
 450         'en_us':                         'en_US.ISO8859-1',
 451         'eng_gb':                        'en_GB.ISO8859-1',
 452         'english':                       'en_EN.ISO8859-1',
 453         'english_uk':                    'en_GB.ISO8859-1',
 454         'english_united-states':         'en_US.ISO8859-1',
 455         'english_us':                    'en_US.ISO8859-1',
 456         'es':                            'es_ES.ISO8859-1',
 457         'es_ar':                         'es_AR.ISO8859-1',
 458         'es_bo':                         'es_BO.ISO8859-1',
 459         'es_cl':                         'es_CL.ISO8859-1',
 460         'es_co':                         'es_CO.ISO8859-1',
 461         'es_cr':                         'es_CR.ISO8859-1',
 462         'es_ec':                         'es_EC.ISO8859-1',
 463         'es_es':                         'es_ES.ISO8859-1',
 464         'es_gt':                         'es_GT.ISO8859-1',
 465         'es_mx':                         'es_MX.ISO8859-1',
 466         'es_ni':                         'es_NI.ISO8859-1',
 467         'es_pa':                         'es_PA.ISO8859-1',
 468         'es_pe':                         'es_PE.ISO8859-1',
 469         'es_py':                         'es_PY.ISO8859-1',
 470         'es_sv':                         'es_SV.ISO8859-1',
 471         'es_uy':                         'es_UY.ISO8859-1',
 472         'es_ve':                         'es_VE.ISO8859-1',
 473         'et':                            'et_EE.ISO8859-4',
 474         'et_ee':                         'et_EE.ISO8859-4',
 475         'fi':                            'fi_FI.ISO8859-1',
 476         'fi_fi':                         'fi_FI.ISO8859-1',
 477         'finnish':                       'fi_FI.ISO8859-1',
 478         'fr':                            'fr_FR.ISO8859-1',
 479         'fr_be':                         'fr_BE.ISO8859-1',
 480         'fr_ca':                         'fr_CA.ISO8859-1',
 481         'fr_ch':                         'fr_CH.ISO8859-1',
 482         'fr_fr':                         'fr_FR.ISO8859-1',
 483         'fre_fr':                        'fr_FR.ISO8859-1',
 484         'french':                        'fr_FR.ISO8859-1',
 485         'french_france':                 'fr_FR.ISO8859-1',
 486         'ger_de':                        'de_DE.ISO8859-1',
 487         'german':                        'de_DE.ISO8859-1',
 488         'german_germany':                'de_DE.ISO8859-1',
 489         'greek':                         'el_GR.ISO8859-7',
 490         'hebrew':                        'iw_IL.ISO8859-8',
 491         'hr':                            'hr_HR.ISO8859-2',
 492         'hr_hr':                         'hr_HR.ISO8859-2',
 493         'hu':                            'hu_HU.ISO8859-2',
 494         'hu_hu':                         'hu_HU.ISO8859-2',
 495         'hungarian':                     'hu_HU.ISO8859-2',
 496         'icelandic':                     'is_IS.ISO8859-1',
 497         'id':                            'id_ID.ISO8859-1',
 498         'id_id':                         'id_ID.ISO8859-1',
 499         'is':                            'is_IS.ISO8859-1',
 500         'is_is':                         'is_IS.ISO8859-1',
 501         'iso-8859-1':                    'en_US.ISO8859-1',
 502         'iso-8859-15':                   'en_US.ISO8859-15',
 503         'iso8859-1':                     'en_US.ISO8859-1',
 504         'iso8859-15':                    'en_US.ISO8859-15',
 505         'iso_8859_1':                    'en_US.ISO8859-1',
 506         'iso_8859_15':                   'en_US.ISO8859-15',
 507         'it':                            'it_IT.ISO8859-1',
 508         'it_ch':                         'it_CH.ISO8859-1',
 509         'it_it':                         'it_IT.ISO8859-1',
 510         'italian':                       'it_IT.ISO8859-1',
 511         'iw':                            'iw_IL.ISO8859-8',
 512         'iw_il':                         'iw_IL.ISO8859-8',
 513         'ja':                            'ja_JP.eucJP',
 514         'ja.jis':                        'ja_JP.JIS7',
 515         'ja.sjis':                       'ja_JP.SJIS',
 516         'ja_jp':                         'ja_JP.eucJP',
 517         'ja_jp.ajec':                    'ja_JP.eucJP',
 518         'ja_jp.euc':                     'ja_JP.eucJP',
 519         'ja_jp.eucjp':                   'ja_JP.eucJP',
 520         'ja_jp.iso-2022-jp':             'ja_JP.JIS7',
 521         'ja_jp.jis':                     'ja_JP.JIS7',
 522         'ja_jp.jis7':                    'ja_JP.JIS7',
 523         'ja_jp.mscode':                  'ja_JP.SJIS',
 524         'ja_jp.sjis':                    'ja_JP.SJIS',
 525         'ja_jp.ujis':                    'ja_JP.eucJP',
 526         'japan':                         'ja_JP.eucJP',
 527         'japanese':                      'ja_JP.SJIS',
 528         'japanese-euc':                  'ja_JP.eucJP',
 529         'japanese.euc':                  'ja_JP.eucJP',
 530         'jp_jp':                         'ja_JP.eucJP',
 531         'ko':                            'ko_KR.eucKR',
 532         'ko_kr':                         'ko_KR.eucKR',
 533         'ko_kr.euc':                     'ko_KR.eucKR',
 534         'korean':                        'ko_KR.eucKR',
 535         'lt':                            'lt_LT.ISO8859-4',
 536         'lv':                            'lv_LV.ISO8859-4',
 537         'mk':                            'mk_MK.ISO8859-5',
 538         'mk_mk':                         'mk_MK.ISO8859-5',
 539         'nl':                            'nl_NL.ISO8859-1',
 540         'nl_be':                         'nl_BE.ISO8859-1',
 541         'nl_nl':                         'nl_NL.ISO8859-1',
 542         'no':                            'no_NO.ISO8859-1',
 543         'no_no':                         'no_NO.ISO8859-1',
 544         'norwegian':                     'no_NO.ISO8859-1',
 545         'pl':                            'pl_PL.ISO8859-2',
 546         'pl_pl':                         'pl_PL.ISO8859-2',
 547         'polish':                        'pl_PL.ISO8859-2',
 548         'portuguese':                    'pt_PT.ISO8859-1',
 549         'portuguese_brazil':             'pt_BR.ISO8859-1',
 550         'posix':                         'C',
 551         'posix-utf2':                    'C',
 552         'pt':                            'pt_PT.ISO8859-1',
 553         'pt_br':                         'pt_BR.ISO8859-1',
 554         'pt_pt':                         'pt_PT.ISO8859-1',
 555         'ro':                            'ro_RO.ISO8859-2',
 556         'ro_ro':                         'ro_RO.ISO8859-2',
 557         'ru':                            'ru_RU.ISO8859-5',
 558         'ru_ru':                         'ru_RU.ISO8859-5',
 559         'rumanian':                      'ro_RO.ISO8859-2',
 560         'russian':                       'ru_RU.ISO8859-5',
 561         'serbocroatian':                 'sh_YU.ISO8859-2',
 562         'sh':                            'sh_YU.ISO8859-2',
 563         'sh_hr':                         'sh_HR.ISO8859-2',
 564         'sh_sp':                         'sh_YU.ISO8859-2',
 565         'sh_yu':                         'sh_YU.ISO8859-2',
 566         'sk':                            'sk_SK.ISO8859-2',
 567         'sk_sk':                         'sk_SK.ISO8859-2',
 568         'sl':                            'sl_CS.ISO8859-2',
 569         'sl_cs':                         'sl_CS.ISO8859-2',
 570         'sl_si':                         'sl_SI.ISO8859-2',
 571         'slovak':                        'sk_SK.ISO8859-2',
 572         'slovene':                       'sl_CS.ISO8859-2',
 573         'sp':                            'sp_YU.ISO8859-5',
 574         'sp_yu':                         'sp_YU.ISO8859-5',
 575         'spanish':                       'es_ES.ISO8859-1',
 576         'spanish_spain':                 'es_ES.ISO8859-1',
 577         'sr_sp':                         'sr_SP.ISO8859-2',
 578         'sv':                            'sv_SE.ISO8859-1',
 579         'sv_se':                         'sv_SE.ISO8859-1',
 580         'swedish':                       'sv_SE.ISO8859-1',
 581         'th_th':                         'th_TH.TACTIS',
 582         'tr':                            'tr_TR.ISO8859-9',
 583         'tr_tr':                         'tr_TR.ISO8859-9',
 584         'turkish':                       'tr_TR.ISO8859-9',
 585         'univ':                          'en_US.utf',
 586         'universal':                     'en_US.utf',
 587         'zh':                            'zh_CN.eucCN',
 588         'zh_cn':                         'zh_CN.eucCN',
 589         'zh_cn.big5':                    'zh_TW.eucTW',
 590         'zh_cn.euc':                     'zh_CN.eucCN',
 591         'zh_tw':                         'zh_TW.eucTW',
 592         'zh_tw.euc':                     'zh_TW.eucTW',
 593 }
 594
 595 #
 596 # this maps windows language identifiers (as used on Windows 95 and
 597 # earlier) to locale strings.
 598 #
 599 # NOTE: this mapping is incomplete.  If your language is missing, send
 600 # a note with the missing language identifier and the suggested locale
 601 # code to Fredrik Lundh <effbot@telia.com>.  Thanks /F
 602
 603 windows_locale = {
 604     0x0404: "zh_TW", # Chinese (Taiwan)
 605     0x0804: "zh_CN", # Chinese (PRC)
 606     0x0406: "da_DK", # Danish
 607     0x0413: "nl_NL", # Dutch (Netherlands)
 608     0x0409: "en_US", # English (United States)
 609     0x0809: "en_UK", # English (United Kingdom)
 610     0x0c09: "en_AU", # English (Australian)
 611     0x1009: "en_CA", # English (Canadian)
 612     0x1409: "en_NZ", # English (New Zealand)
 613     0x1809: "en_IE", # English (Ireland)
 614     0x1c09: "en_ZA", # English (South Africa)
 615     0x040b: "fi_FI", # Finnish
 616     0x040c: "fr_FR", # French (Standard)
 617     0x080c: "fr_BE", # French (Belgian)
 618     0x0c0c: "fr_CA", # French (Canadian)
 619     0x100c: "fr_CH", # French (Switzerland)
 620     0x0407: "de_DE", # German (Standard)
 621     0x0408: "el_GR", # Greek
 622     0x040d: "iw_IL", # Hebrew
 623     0x040f: "is_IS", # Icelandic
 624     0x0410: "it_IT", # Italian (Standard)
 625     0x0411: "ja_JA", # Japanese
 626     0x0414: "no_NO", # Norwegian (Bokmal)
 627     0x0816: "pt_PT", # Portuguese (Standard)
 628     0x0c0a: "es_ES", # Spanish (Modern Sort)
 629     0x0441: "sw_KE", # Swahili (Kenya)
 630     0x041d: "sv_SE", # Swedish
 631     0x081d: "sv_FI", # Swedish (Finland)
 632     0x041f: "tr_TR", # Turkish
 633 }
 634
 635 def _print_locale():
 636
 637     """ Test function.
 638     """
 639     categories = {}
 640     def _init_categories(categories=categories):
 641         for k,v in globals().items():
 642             if k[:3] == 'LC_':
 643                 categories[k] = v
 644     _init_categories()
 645     del categories['LC_ALL']
 646
 647     print 'Locale defaults as determined by getdefaultlocale():'
 648     print '-'*72
 649     lang, enc = getdefaultlocale()
 650     print 'Language: ', lang or '(undefined)'
 651     print 'Encoding: ', enc or '(undefined)'
 652     print
 653
 654     print 'Locale settings on startup:'
 655     print '-'*72
 656     for name,category in categories.items():
 657         print name, '...'
 658         lang, enc = getlocale(category)
 659         print '   Language: ', lang or '(undefined)'
 660         print '   Encoding: ', enc or '(undefined)'
 661         print
 662
 663     print
 664     print 'Locale settings after calling resetlocale():'
 665     print '-'*72
 666     resetlocale()
 667     for name,category in categories.items():
 668         print name, '...'
 669         lang, enc = getlocale(category)
 670         print '   Language: ', lang or '(undefined)'
 671         print '   Encoding: ', enc or '(undefined)'
 672         print
 673
 674     try:
 675         setlocale(LC_ALL, "")
 676     except:
 677         print 'NOTE:'
 678         print 'setlocale(LC_ALL, "") does not support the default locale'
 679         print 'given in the OS environment variables.'
 680     else:
 681         print
 682         print 'Locale settings after calling setlocale(LC_ALL, ""):'
 683         print '-'*72
 684         for name,category in categories.items():
 685             print name, '...'
 686             lang, enc = getlocale(category)
 687             print '   Language: ', lang or '(undefined)'
 688             print '   Encoding: ', enc or '(undefined)'
 689             print
 690
 691 ###
 692
 693 if __name__=='__main__':
 694     print 'Locale aliasing:'
 695     print
 696     _print_locale()
 697     print
 698     print 'Number formatting:'
 699     print
 700     _test()