/usr/lib/python2.7/dist-packages/babel/core.py is in python-babel 1.3+dfsg.1-5.
This file is owned by root:root, with mode 0o644.
The actual contents of the file can be viewed below.
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 | # -*- coding: utf-8 -*-
"""
babel.core
~~~~~~~~~~
Core locale representation and locale data access.
:copyright: (c) 2013 by the Babel Team.
:license: BSD, see LICENSE for more details.
"""
import os
import six
from babel import localedata
from babel._compat import pickle, string_types
__all__ = ['UnknownLocaleError', 'Locale', 'default_locale', 'negotiate_locale',
'parse_locale']
_global_data = None
def _raise_no_data_error():
raise RuntimeError('The babel data files are not available. '
'This usually happens because you are using '
'a source checkout from Babel and you did '
'not build the data files. Just make sure '
'to run "python setup.py import_cldr" before '
'installing the library.')
def get_global(key):
"""Return the dictionary for the given key in the global data.
The global data is stored in the ``babel/global.dat`` file and contains
information independent of individual locales.
>>> get_global('zone_aliases')['UTC']
u'Etc/GMT'
>>> get_global('zone_territories')['Europe/Berlin']
u'DE'
.. versionadded:: 0.9
:param key: the data key
"""
global _global_data
if _global_data is None:
dirname = os.path.join(os.path.dirname(__file__))
filename = os.path.join(dirname, 'global.dat')
if not os.path.isfile(filename):
_raise_no_data_error()
fileobj = open(filename, 'rb')
try:
_global_data = pickle.load(fileobj)
finally:
fileobj.close()
return _global_data.get(key, {})
LOCALE_ALIASES = {
'ar': 'ar_SY', 'bg': 'bg_BG', 'bs': 'bs_BA', 'ca': 'ca_ES', 'cs': 'cs_CZ',
'da': 'da_DK', 'de': 'de_DE', 'el': 'el_GR', 'en': 'en_US', 'es': 'es_ES',
'et': 'et_EE', 'fa': 'fa_IR', 'fi': 'fi_FI', 'fr': 'fr_FR', 'gl': 'gl_ES',
'he': 'he_IL', 'hu': 'hu_HU', 'id': 'id_ID', 'is': 'is_IS', 'it': 'it_IT',
'ja': 'ja_JP', 'km': 'km_KH', 'ko': 'ko_KR', 'lt': 'lt_LT', 'lv': 'lv_LV',
'mk': 'mk_MK', 'nl': 'nl_NL', 'nn': 'nn_NO', 'no': 'nb_NO', 'pl': 'pl_PL',
'pt': 'pt_PT', 'ro': 'ro_RO', 'ru': 'ru_RU', 'sk': 'sk_SK', 'sl': 'sl_SI',
'sv': 'sv_SE', 'th': 'th_TH', 'tr': 'tr_TR', 'uk': 'uk_UA'
}
class UnknownLocaleError(Exception):
"""Exception thrown when a locale is requested for which no locale data
is available.
"""
def __init__(self, identifier):
"""Create the exception.
:param identifier: the identifier string of the unsupported locale
"""
Exception.__init__(self, 'unknown locale %r' % identifier)
#: The identifier of the locale that could not be found.
self.identifier = identifier
class Locale(object):
"""Representation of a specific locale.
>>> locale = Locale('en', 'US')
>>> repr(locale)
"Locale('en', territory='US')"
>>> locale.display_name
u'English (United States)'
A `Locale` object can also be instantiated from a raw locale string:
>>> locale = Locale.parse('en-US', sep='-')
>>> repr(locale)
"Locale('en', territory='US')"
`Locale` objects provide access to a collection of locale data, such as
territory and language names, number and date format patterns, and more:
>>> locale.number_symbols['decimal']
u'.'
If a locale is requested for which no locale data is available, an
`UnknownLocaleError` is raised:
>>> Locale.parse('en_DE')
Traceback (most recent call last):
...
UnknownLocaleError: unknown locale 'en_DE'
For more information see :rfc:`3066`.
"""
def __init__(self, language, territory=None, script=None, variant=None):
"""Initialize the locale object from the given identifier components.
>>> locale = Locale('en', 'US')
>>> locale.language
'en'
>>> locale.territory
'US'
:param language: the language code
:param territory: the territory (country or region) code
:param script: the script code
:param variant: the variant code
:raise `UnknownLocaleError`: if no locale data is available for the
requested locale
"""
#: the language code
self.language = language
#: the territory (country or region) code
self.territory = territory
#: the script code
self.script = script
#: the variant code
self.variant = variant
self.__data = None
identifier = str(self)
if not localedata.exists(identifier):
raise UnknownLocaleError(identifier)
@classmethod
def default(cls, category=None, aliases=LOCALE_ALIASES):
"""Return the system default locale for the specified category.
>>> for name in ['LANGUAGE', 'LC_ALL', 'LC_CTYPE', 'LC_MESSAGES']:
... os.environ[name] = ''
>>> os.environ['LANG'] = 'fr_FR.UTF-8'
>>> Locale.default('LC_MESSAGES')
Locale('fr', territory='FR')
The following fallbacks to the variable are always considered:
- ``LANGUAGE``
- ``LC_ALL``
- ``LC_CTYPE``
- ``LANG``
:param category: one of the ``LC_XXX`` environment variable names
:param aliases: a dictionary of aliases for locale identifiers
"""
# XXX: use likely subtag expansion here instead of the
# aliases dictionary.
locale_string = default_locale(category, aliases=aliases)
return cls.parse(locale_string)
@classmethod
def negotiate(cls, preferred, available, sep='_', aliases=LOCALE_ALIASES):
"""Find the best match between available and requested locale strings.
>>> Locale.negotiate(['de_DE', 'en_US'], ['de_DE', 'de_AT'])
Locale('de', territory='DE')
>>> Locale.negotiate(['de_DE', 'en_US'], ['en', 'de'])
Locale('de')
>>> Locale.negotiate(['de_DE', 'de'], ['en_US'])
You can specify the character used in the locale identifiers to separate
the differnet components. This separator is applied to both lists. Also,
case is ignored in the comparison:
>>> Locale.negotiate(['de-DE', 'de'], ['en-us', 'de-de'], sep='-')
Locale('de', territory='DE')
:param preferred: the list of locale identifers preferred by the user
:param available: the list of locale identifiers available
:param aliases: a dictionary of aliases for locale identifiers
"""
identifier = negotiate_locale(preferred, available, sep=sep,
aliases=aliases)
if identifier:
return Locale.parse(identifier, sep=sep)
@classmethod
def parse(cls, identifier, sep='_', resolve_likely_subtags=True):
"""Create a `Locale` instance for the given locale identifier.
>>> l = Locale.parse('de-DE', sep='-')
>>> l.display_name
u'Deutsch (Deutschland)'
If the `identifier` parameter is not a string, but actually a `Locale`
object, that object is returned:
>>> Locale.parse(l)
Locale('de', territory='DE')
This also can perform resolving of likely subtags which it does
by default. This is for instance useful to figure out the most
likely locale for a territory you can use ``'und'`` as the
language tag:
>>> Locale.parse('und_AT')
Locale('de', territory='AT')
:param identifier: the locale identifier string
:param sep: optional component separator
:param resolve_likely_subtags: if this is specified then a locale will
have its likely subtag resolved if the
locale otherwise does not exist. For
instance ``zh_TW`` by itself is not a
locale that exists but Babel can
automatically expand it to the full
form of ``zh_hant_TW``. Note that this
expansion is only taking place if no
locale exists otherwise. For instance
there is a locale ``en`` that can exist
by itself.
:raise `ValueError`: if the string does not appear to be a valid locale
identifier
:raise `UnknownLocaleError`: if no locale data is available for the
requested locale
"""
if identifier is None:
return None
elif isinstance(identifier, Locale):
return identifier
elif not isinstance(identifier, string_types):
raise TypeError('Unxpected value for identifier: %r' % (identifier,))
parts = parse_locale(identifier, sep=sep)
input_id = get_locale_identifier(parts)
def _try_load(parts):
try:
return cls(*parts)
except UnknownLocaleError:
return None
def _try_load_reducing(parts):
# Success on first hit, return it.
locale = _try_load(parts)
if locale is not None:
return locale
# Now try without script and variant
locale = _try_load(parts[:2])
if locale is not None:
return locale
locale = _try_load(parts)
if locale is not None:
return locale
if not resolve_likely_subtags:
raise UnknownLocaleError(input_id)
# From here onwards is some very bad likely subtag resolving. This
# whole logic is not entirely correct but good enough (tm) for the
# time being. This has been added so that zh_TW does not cause
# errors for people when they upgrade. Later we should properly
# implement ICU like fuzzy locale objects and provide a way to
# maximize and minimize locale tags.
language, territory, script, variant = parts
language = get_global('language_aliases').get(language, language)
territory = get_global('territory_aliases').get(territory, territory)
script = get_global('script_aliases').get(script, script)
variant = get_global('variant_aliases').get(variant, variant)
if territory == 'ZZ':
territory = None
if script == 'Zzzz':
script = None
parts = language, territory, script, variant
# First match: try the whole identifier
new_id = get_locale_identifier(parts)
likely_subtag = get_global('likely_subtags').get(new_id)
if likely_subtag is not None:
locale = _try_load_reducing(parse_locale(likely_subtag))
if locale is not None:
return locale
# If we did not find anything so far, try again with a
# simplified identifier that is just the language
likely_subtag = get_global('likely_subtags').get(language)
if likely_subtag is not None:
language2, _, script2, variant2 = parse_locale(likely_subtag)
locale = _try_load_reducing((language2, territory, script2, variant2))
if locale is not None:
return locale
raise UnknownLocaleError(input_id)
def __eq__(self, other):
for key in ('language', 'territory', 'script', 'variant'):
if not hasattr(other, key):
return False
return (self.language == other.language) and \
(self.territory == other.territory) and \
(self.script == other.script) and \
(self.variant == other.variant)
def __ne__(self, other):
return not self.__eq__(other)
def __repr__(self):
parameters = ['']
for key in ('territory', 'script', 'variant'):
value = getattr(self, key)
if value is not None:
parameters.append('%s=%r' % (key, value))
parameter_string = '%r' % self.language + ', '.join(parameters)
return 'Locale(%s)' % parameter_string
def __str__(self):
return get_locale_identifier((self.language, self.territory,
self.script, self.variant))
@property
def _data(self):
if self.__data is None:
self.__data = localedata.LocaleDataDict(localedata.load(str(self)))
return self.__data
def get_display_name(self, locale=None):
"""Return the display name of the locale using the given locale.
The display name will include the language, territory, script, and
variant, if those are specified.
>>> Locale('zh', 'CN', script='Hans').get_display_name('en')
u'Chinese (Simplified, China)'
:param locale: the locale to use
"""
if locale is None:
locale = self
locale = Locale.parse(locale)
retval = locale.languages.get(self.language)
if self.territory or self.script or self.variant:
details = []
if self.script:
details.append(locale.scripts.get(self.script))
if self.territory:
details.append(locale.territories.get(self.territory))
if self.variant:
details.append(locale.variants.get(self.variant))
details = filter(None, details)
if details:
retval += ' (%s)' % six.u(', ').join(details)
return retval
display_name = property(get_display_name, doc="""\
The localized display name of the locale.
>>> Locale('en').display_name
u'English'
>>> Locale('en', 'US').display_name
u'English (United States)'
>>> Locale('sv').display_name
u'svenska'
:type: `unicode`
""")
def get_language_name(self, locale=None):
"""Return the language of this locale in the given locale.
>>> Locale('zh', 'CN', script='Hans').get_language_name('de')
u'Chinesisch'
.. versionadded:: 1.0
:param locale: the locale to use
"""
if locale is None:
locale = self
locale = Locale.parse(locale)
return locale.languages.get(self.language)
language_name = property(get_language_name, doc="""\
The localized language name of the locale.
>>> Locale('en', 'US').language_name
u'English'
""")
def get_territory_name(self, locale=None):
"""Return the territory name in the given locale."""
if locale is None:
locale = self
locale = Locale.parse(locale)
return locale.territories.get(self.territory)
territory_name = property(get_territory_name, doc="""\
The localized territory name of the locale if available.
>>> Locale('de', 'DE').territory_name
u'Deutschland'
""")
def get_script_name(self, locale=None):
"""Return the script name in the given locale."""
if locale is None:
locale = self
locale = Locale.parse(locale)
return locale.scripts.get(self.script)
script_name = property(get_script_name, doc="""\
The localized script name of the locale if available.
>>> Locale('ms', 'SG', script='Latn').script_name
u'Latin'
""")
@property
def english_name(self):
"""The english display name of the locale.
>>> Locale('de').english_name
u'German'
>>> Locale('de', 'DE').english_name
u'German (Germany)'
:type: `unicode`"""
return self.get_display_name(Locale('en'))
#{ General Locale Display Names
@property
def languages(self):
"""Mapping of language codes to translated language names.
>>> Locale('de', 'DE').languages['ja']
u'Japanisch'
See `ISO 639 <http://www.loc.gov/standards/iso639-2/>`_ for
more information.
"""
return self._data['languages']
@property
def scripts(self):
"""Mapping of script codes to translated script names.
>>> Locale('en', 'US').scripts['Hira']
u'Hiragana'
See `ISO 15924 <http://www.evertype.com/standards/iso15924/>`_
for more information.
"""
return self._data['scripts']
@property
def territories(self):
"""Mapping of script codes to translated script names.
>>> Locale('es', 'CO').territories['DE']
u'Alemania'
See `ISO 3166 <http://www.iso.org/iso/en/prods-services/iso3166ma/>`_
for more information.
"""
return self._data['territories']
@property
def variants(self):
"""Mapping of script codes to translated script names.
>>> Locale('de', 'DE').variants['1901']
u'Alte deutsche Rechtschreibung'
"""
return self._data['variants']
#{ Number Formatting
@property
def currencies(self):
"""Mapping of currency codes to translated currency names. This
only returns the generic form of the currency name, not the count
specific one. If an actual number is requested use the
:func:`babel.numbers.get_currency_name` function.
>>> Locale('en').currencies['COP']
u'Colombian Peso'
>>> Locale('de', 'DE').currencies['COP']
u'Kolumbianischer Peso'
"""
return self._data['currency_names']
@property
def currency_symbols(self):
"""Mapping of currency codes to symbols.
>>> Locale('en', 'US').currency_symbols['USD']
u'$'
>>> Locale('es', 'CO').currency_symbols['USD']
u'US$'
"""
return self._data['currency_symbols']
@property
def number_symbols(self):
"""Symbols used in number formatting.
>>> Locale('fr', 'FR').number_symbols['decimal']
u','
"""
return self._data['number_symbols']
@property
def decimal_formats(self):
"""Locale patterns for decimal number formatting.
>>> Locale('en', 'US').decimal_formats[None]
<NumberPattern u'#,##0.###'>
"""
return self._data['decimal_formats']
@property
def currency_formats(self):
"""Locale patterns for currency number formatting.
>>> print Locale('en', 'US').currency_formats[None]
<NumberPattern u'\\xa4#,##0.00'>
"""
return self._data['currency_formats']
@property
def percent_formats(self):
"""Locale patterns for percent number formatting.
>>> Locale('en', 'US').percent_formats[None]
<NumberPattern u'#,##0%'>
"""
return self._data['percent_formats']
@property
def scientific_formats(self):
"""Locale patterns for scientific number formatting.
>>> Locale('en', 'US').scientific_formats[None]
<NumberPattern u'#E0'>
"""
return self._data['scientific_formats']
#{ Calendar Information and Date Formatting
@property
def periods(self):
"""Locale display names for day periods (AM/PM).
>>> Locale('en', 'US').periods['am']
u'AM'
"""
return self._data['periods']
@property
def days(self):
"""Locale display names for weekdays.
>>> Locale('de', 'DE').days['format']['wide'][3]
u'Donnerstag'
"""
return self._data['days']
@property
def months(self):
"""Locale display names for months.
>>> Locale('de', 'DE').months['format']['wide'][10]
u'Oktober'
"""
return self._data['months']
@property
def quarters(self):
"""Locale display names for quarters.
>>> Locale('de', 'DE').quarters['format']['wide'][1]
u'1. Quartal'
"""
return self._data['quarters']
@property
def eras(self):
"""Locale display names for eras.
>>> Locale('en', 'US').eras['wide'][1]
u'Anno Domini'
>>> Locale('en', 'US').eras['abbreviated'][0]
u'BC'
"""
return self._data['eras']
@property
def time_zones(self):
"""Locale display names for time zones.
>>> Locale('en', 'US').time_zones['Europe/London']['long']['daylight']
u'British Summer Time'
>>> Locale('en', 'US').time_zones['America/St_Johns']['city']
u'St. John\u2019s'
"""
return self._data['time_zones']
@property
def meta_zones(self):
"""Locale display names for meta time zones.
Meta time zones are basically groups of different Olson time zones that
have the same GMT offset and daylight savings time.
>>> Locale('en', 'US').meta_zones['Europe_Central']['long']['daylight']
u'Central European Summer Time'
.. versionadded:: 0.9
"""
return self._data['meta_zones']
@property
def zone_formats(self):
"""Patterns related to the formatting of time zones.
>>> Locale('en', 'US').zone_formats['fallback']
u'%(1)s (%(0)s)'
>>> Locale('pt', 'BR').zone_formats['region']
u'Hor\\xe1rio %s'
.. versionadded:: 0.9
"""
return self._data['zone_formats']
@property
def first_week_day(self):
"""The first day of a week, with 0 being Monday.
>>> Locale('de', 'DE').first_week_day
0
>>> Locale('en', 'US').first_week_day
6
"""
return self._data['week_data']['first_day']
@property
def weekend_start(self):
"""The day the weekend starts, with 0 being Monday.
>>> Locale('de', 'DE').weekend_start
5
"""
return self._data['week_data']['weekend_start']
@property
def weekend_end(self):
"""The day the weekend ends, with 0 being Monday.
>>> Locale('de', 'DE').weekend_end
6
"""
return self._data['week_data']['weekend_end']
@property
def min_week_days(self):
"""The minimum number of days in a week so that the week is counted as
the first week of a year or month.
>>> Locale('de', 'DE').min_week_days
4
"""
return self._data['week_data']['min_days']
@property
def date_formats(self):
"""Locale patterns for date formatting.
>>> Locale('en', 'US').date_formats['short']
<DateTimePattern u'M/d/yy'>
>>> Locale('fr', 'FR').date_formats['long']
<DateTimePattern u'd MMMM y'>
"""
return self._data['date_formats']
@property
def time_formats(self):
"""Locale patterns for time formatting.
>>> Locale('en', 'US').time_formats['short']
<DateTimePattern u'h:mm a'>
>>> Locale('fr', 'FR').time_formats['long']
<DateTimePattern u'HH:mm:ss z'>
"""
return self._data['time_formats']
@property
def datetime_formats(self):
"""Locale patterns for datetime formatting.
>>> Locale('en').datetime_formats['full']
u"{1} 'at' {0}"
>>> Locale('th').datetime_formats['medium']
u'{1}, {0}'
"""
return self._data['datetime_formats']
@property
def plural_form(self):
"""Plural rules for the locale.
>>> Locale('en').plural_form(1)
'one'
>>> Locale('en').plural_form(0)
'other'
>>> Locale('fr').plural_form(0)
'one'
>>> Locale('ru').plural_form(100)
'many'
"""
return self._data['plural_form']
def default_locale(category=None, aliases=LOCALE_ALIASES):
"""Returns the system default locale for a given category, based on
environment variables.
>>> for name in ['LANGUAGE', 'LC_ALL', 'LC_CTYPE']:
... os.environ[name] = ''
>>> os.environ['LANG'] = 'fr_FR.UTF-8'
>>> default_locale('LC_MESSAGES')
'fr_FR'
The "C" or "POSIX" pseudo-locales are treated as aliases for the
"en_US_POSIX" locale:
>>> os.environ['LC_MESSAGES'] = 'POSIX'
>>> default_locale('LC_MESSAGES')
'en_US_POSIX'
The following fallbacks to the variable are always considered:
- ``LANGUAGE``
- ``LC_ALL``
- ``LC_CTYPE``
- ``LANG``
:param category: one of the ``LC_XXX`` environment variable names
:param aliases: a dictionary of aliases for locale identifiers
"""
varnames = (category, 'LANGUAGE', 'LC_ALL', 'LC_CTYPE', 'LANG')
for name in filter(None, varnames):
locale = os.getenv(name)
if locale:
if name == 'LANGUAGE' and ':' in locale:
# the LANGUAGE variable may contain a colon-separated list of
# language codes; we just pick the language on the list
locale = locale.split(':')[0]
if locale in ('C', 'POSIX'):
locale = 'en_US_POSIX'
elif aliases and locale in aliases:
locale = aliases[locale]
try:
return get_locale_identifier(parse_locale(locale))
except ValueError:
pass
def negotiate_locale(preferred, available, sep='_', aliases=LOCALE_ALIASES):
"""Find the best match between available and requested locale strings.
>>> negotiate_locale(['de_DE', 'en_US'], ['de_DE', 'de_AT'])
'de_DE'
>>> negotiate_locale(['de_DE', 'en_US'], ['en', 'de'])
'de'
Case is ignored by the algorithm, the result uses the case of the preferred
locale identifier:
>>> negotiate_locale(['de_DE', 'en_US'], ['de_de', 'de_at'])
'de_DE'
>>> negotiate_locale(['de_DE', 'en_US'], ['de_de', 'de_at'])
'de_DE'
By default, some web browsers unfortunately do not include the territory
in the locale identifier for many locales, and some don't even allow the
user to easily add the territory. So while you may prefer using qualified
locale identifiers in your web-application, they would not normally match
the language-only locale sent by such browsers. To workaround that, this
function uses a default mapping of commonly used langauge-only locale
identifiers to identifiers including the territory:
>>> negotiate_locale(['ja', 'en_US'], ['ja_JP', 'en_US'])
'ja_JP'
Some browsers even use an incorrect or outdated language code, such as "no"
for Norwegian, where the correct locale identifier would actually be "nb_NO"
(Bokmål) or "nn_NO" (Nynorsk). The aliases are intended to take care of
such cases, too:
>>> negotiate_locale(['no', 'sv'], ['nb_NO', 'sv_SE'])
'nb_NO'
You can override this default mapping by passing a different `aliases`
dictionary to this function, or you can bypass the behavior althogher by
setting the `aliases` parameter to `None`.
:param preferred: the list of locale strings preferred by the user
:param available: the list of locale strings available
:param sep: character that separates the different parts of the locale
strings
:param aliases: a dictionary of aliases for locale identifiers
"""
available = [a.lower() for a in available if a]
for locale in preferred:
ll = locale.lower()
if ll in available:
return locale
if aliases:
alias = aliases.get(ll)
if alias:
alias = alias.replace('_', sep)
if alias.lower() in available:
return alias
parts = locale.split(sep)
if len(parts) > 1 and parts[0].lower() in available:
return parts[0]
return None
def parse_locale(identifier, sep='_'):
"""Parse a locale identifier into a tuple of the form ``(language,
territory, script, variant)``.
>>> parse_locale('zh_CN')
('zh', 'CN', None, None)
>>> parse_locale('zh_Hans_CN')
('zh', 'CN', 'Hans', None)
The default component separator is "_", but a different separator can be
specified using the `sep` parameter:
>>> parse_locale('zh-CN', sep='-')
('zh', 'CN', None, None)
If the identifier cannot be parsed into a locale, a `ValueError` exception
is raised:
>>> parse_locale('not_a_LOCALE_String')
Traceback (most recent call last):
...
ValueError: 'not_a_LOCALE_String' is not a valid locale identifier
Encoding information and locale modifiers are removed from the identifier:
>>> parse_locale('it_IT@euro')
('it', 'IT', None, None)
>>> parse_locale('en_US.UTF-8')
('en', 'US', None, None)
>>> parse_locale('de_DE.iso885915@euro')
('de', 'DE', None, None)
See :rfc:`4646` for more information.
:param identifier: the locale identifier string
:param sep: character that separates the different components of the locale
identifier
:raise `ValueError`: if the string does not appear to be a valid locale
identifier
"""
if '.' in identifier:
# this is probably the charset/encoding, which we don't care about
identifier = identifier.split('.', 1)[0]
if '@' in identifier:
# this is a locale modifier such as @euro, which we don't care about
# either
identifier = identifier.split('@', 1)[0]
parts = identifier.split(sep)
lang = parts.pop(0).lower()
if not lang.isalpha():
raise ValueError('expected only letters, got %r' % lang)
script = territory = variant = None
if parts:
if len(parts[0]) == 4 and parts[0].isalpha():
script = parts.pop(0).title()
if parts:
if len(parts[0]) == 2 and parts[0].isalpha():
territory = parts.pop(0).upper()
elif len(parts[0]) == 3 and parts[0].isdigit():
territory = parts.pop(0)
if parts:
if len(parts[0]) == 4 and parts[0][0].isdigit() or \
len(parts[0]) >= 5 and parts[0][0].isalpha():
variant = parts.pop()
if parts:
raise ValueError('%r is not a valid locale identifier' % identifier)
return lang, territory, script, variant
def get_locale_identifier(tup, sep='_'):
"""The reverse of :func:`parse_locale`. It creates a locale identifier out
of a ``(language, territory, script, variant)`` tuple. Items can be set to
``None`` and trailing ``None``\s can also be left out of the tuple.
>>> get_locale_identifier(('de', 'DE', None, '1999'))
'de_DE_1999'
.. versionadded:: 1.0
:param tup: the tuple as returned by :func:`parse_locale`.
:param sep: the separator for the identifier.
"""
tup = tuple(tup[:4])
lang, territory, script, variant = tup + (None,) * (4 - len(tup))
return sep.join(filter(None, (lang, script, territory, variant)))
|