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