Source

django / django / utils / translation / trans_real.py

  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
"""Translation helper functions."""

import locale
import os
import re
import sys
import gettext as gettext_module
from threading import local

try:
    from cStringIO import StringIO
except ImportError:
    from StringIO import StringIO

from django.utils.importlib import import_module
from django.utils.safestring import mark_safe, SafeData


# Translations are cached in a dictionary for every language+app tuple.
# The active translations are stored by threadid to make them thread local.
_translations = {}
_active = local()

# The default translation is based on the settings file.
_default = None

# This is a cache for normalized accept-header languages to prevent multiple
# file lookups when checking the same locale on repeated requests.
_accepted = {}

# magic gettext number to separate context from message
CONTEXT_SEPARATOR = u"\x04"

# Format of Accept-Language header values. From RFC 2616, section 14.4 and 3.9.
accept_language_re = re.compile(r'''
        ([A-Za-z]{1,8}(?:-[A-Za-z]{1,8})*|\*)         # "en", "en-au", "x-y-z", "*"
        (?:\s*;\s*q=(0(?:\.\d{,3})?|1(?:.0{,3})?))?   # Optional "q=1.00", "q=0.8"
        (?:\s*,\s*|$)                                 # Multiple accepts per header.
        ''', re.VERBOSE)

language_code_prefix_re = re.compile(r'^/([\w-]+)/')

def to_locale(language, to_lower=False):
    """
    Turns a language name (en-us) into a locale name (en_US). If 'to_lower' is
    True, the last component is lower-cased (en_us).
    """
    p = language.find('-')
    if p >= 0:
        if to_lower:
            return language[:p].lower()+'_'+language[p+1:].lower()
        else:
            # Get correct locale for sr-latn
            if len(language[p+1:]) > 2:
                return language[:p].lower()+'_'+language[p+1].upper()+language[p+2:].lower()
            return language[:p].lower()+'_'+language[p+1:].upper()
    else:
        return language.lower()

def to_language(locale):
    """Turns a locale name (en_US) into a language name (en-us)."""
    p = locale.find('_')
    if p >= 0:
        return locale[:p].lower()+'-'+locale[p+1:].lower()
    else:
        return locale.lower()

class DjangoTranslation(gettext_module.GNUTranslations):
    """
    This class sets up the GNUTranslations context with regard to output
    charset.
    """
    def __init__(self, *args, **kw):
        gettext_module.GNUTranslations.__init__(self, *args, **kw)
        self.set_output_charset('utf-8')
        self.django_output_charset = 'utf-8'
        self.__language = '??'

    def merge(self, other):
        self._catalog.update(other._catalog)

    def set_language(self, language):
        self.__language = language
        self.__to_language = to_language(language)

    def language(self):
        return self.__language

    def to_language(self):
        return self.__to_language

    def __repr__(self):
        return "<DjangoTranslation lang:%s>" % self.__language

def translation(language):
    """
    Returns a translation object.

    This translation object will be constructed out of multiple GNUTranslations
    objects by merging their catalogs. It will construct a object for the
    requested language and add a fallback to the default language, if it's
    different from the requested language.
    """
    global _translations

    t = _translations.get(language, None)
    if t is not None:
        return t

    from django.conf import settings

    globalpath = os.path.join(os.path.dirname(sys.modules[settings.__module__].__file__), 'locale')

    if settings.SETTINGS_MODULE is not None:
        parts = settings.SETTINGS_MODULE.split('.')
        project = import_module(parts[0])
        projectpath = os.path.join(os.path.dirname(project.__file__), 'locale')
    else:
        projectpath = None

    def _fetch(lang, fallback=None):

        global _translations

        res = _translations.get(lang, None)
        if res is not None:
            return res

        loc = to_locale(lang)

        def _translation(path):
            try:
                t = gettext_module.translation('django', path, [loc], DjangoTranslation)
                t.set_language(lang)
                return t
            except IOError:
                return None

        res = _translation(globalpath)

        # We want to ensure that, for example,  "en-gb" and "en-us" don't share
        # the same translation object (thus, merging en-us with a local update
        # doesn't affect en-gb), even though they will both use the core "en"
        # translation. So we have to subvert Python's internal gettext caching.
        base_lang = lambda x: x.split('-', 1)[0]
        if base_lang(lang) in [base_lang(trans) for trans in _translations]:
            res._info = res._info.copy()
            res._catalog = res._catalog.copy()

        def _merge(path):
            t = _translation(path)
            if t is not None:
                if res is None:
                    return t
                else:
                    res.merge(t)
            return res

        for appname in reversed(settings.INSTALLED_APPS):
            app = import_module(appname)
            apppath = os.path.join(os.path.dirname(app.__file__), 'locale')

            if os.path.isdir(apppath):
                res = _merge(apppath)

        localepaths = [os.path.normpath(path) for path in settings.LOCALE_PATHS]
        if (projectpath and os.path.isdir(projectpath) and
                os.path.normpath(projectpath) not in localepaths):
            res = _merge(projectpath)

        for localepath in reversed(settings.LOCALE_PATHS):
            if os.path.isdir(localepath):
                res = _merge(localepath)

        if res is None:
            if fallback is not None:
                res = fallback
            else:
                return gettext_module.NullTranslations()
        _translations[lang] = res
        return res

    default_translation = _fetch(settings.LANGUAGE_CODE)
    current_translation = _fetch(language, fallback=default_translation)

    return current_translation

def activate(language):
    """
    Fetches the translation object for a given tuple of application name and
    language and installs it as the current translation object for the current
    thread.
    """
    _active.value = translation(language)

def deactivate():
    """
    Deinstalls the currently active translation object so that further _ calls
    will resolve against the default translation object, again.
    """
    if hasattr(_active, "value"):
        del _active.value

def deactivate_all():
    """
    Makes the active translation object a NullTranslations() instance. This is
    useful when we want delayed translations to appear as the original string
    for some reason.
    """
    _active.value = gettext_module.NullTranslations()

def get_language():
    """Returns the currently selected language."""
    t = getattr(_active, "value", None)
    if t is not None:
        try:
            return t.to_language()
        except AttributeError:
            pass
    # If we don't have a real translation object, assume it's the default language.
    from django.conf import settings
    return settings.LANGUAGE_CODE

def get_language_bidi():
    """
    Returns selected language's BiDi layout.

    * False = left-to-right layout
    * True = right-to-left layout
    """
    from django.conf import settings

    base_lang = get_language().split('-')[0]
    return base_lang in settings.LANGUAGES_BIDI

def catalog():
    """
    Returns the current active catalog for further processing.
    This can be used if you need to modify the catalog or want to access the
    whole message catalog instead of just translating one string.
    """
    global _default

    t = getattr(_active, "value", None)
    if t is not None:
        return t
    if _default is None:
        from django.conf import settings
        _default = translation(settings.LANGUAGE_CODE)
    return _default

def do_translate(message, translation_function):
    """
    Translates 'message' using the given 'translation_function' name -- which
    will be either gettext or ugettext. It uses the current thread to find the
    translation object to use. If no current translation is activated, the
    message will be run through the default translation object.
    """
    global _default

    eol_message = message.replace('\r\n', '\n').replace('\r', '\n')
    t = getattr(_active, "value", None)
    if t is not None:
        result = getattr(t, translation_function)(eol_message)
    else:
        if _default is None:
            from django.conf import settings
            _default = translation(settings.LANGUAGE_CODE)
        result = getattr(_default, translation_function)(eol_message)
    if isinstance(message, SafeData):
        return mark_safe(result)
    return result

def gettext(message):
    return do_translate(message, 'gettext')

if sys.version_info < (3, 0):
    def ugettext(message):
        return do_translate(message, 'ugettext')
else:
    ugettext = gettext

def pgettext(context, message):
    result = ugettext(
        u"%s%s%s" % (context, CONTEXT_SEPARATOR, message))
    if CONTEXT_SEPARATOR in result:
        # Translation not found
        result = message
    return result

def gettext_noop(message):
    """
    Marks strings for translation but doesn't translate them now. This can be
    used to store strings in global variables that should stay in the base
    language (because they might be used externally) and will be translated
    later.
    """
    return message

def do_ntranslate(singular, plural, number, translation_function):
    global _default

    t = getattr(_active, "value", None)
    if t is not None:
        return getattr(t, translation_function)(singular, plural, number)
    if _default is None:
        from django.conf import settings
        _default = translation(settings.LANGUAGE_CODE)
    return getattr(_default, translation_function)(singular, plural, number)

def ngettext(singular, plural, number):
    """
    Returns a UTF-8 bytestring of the translation of either the singular or
    plural, based on the number.
    """
    return do_ntranslate(singular, plural, number, 'ngettext')

def ungettext(singular, plural, number):
    """
    Returns a unicode strings of the translation of either the singular or
    plural, based on the number.
    """
    return do_ntranslate(singular, plural, number, 'ungettext')
if sys.version_info >= (3,0):
    ungettext = ngettext

def npgettext(context, singular, plural, number):
    result = do_ntranslate(u"%s%s%s" % (context, CONTEXT_SEPARATOR, singular),
                           u"%s%s%s" % (context, CONTEXT_SEPARATOR, plural),
                           number, 'ungettext')
    if CONTEXT_SEPARATOR in result:
        # Translation not found
        result = do_ntranslate(singular, plural, number, 'ungettext')
    return result

def all_locale_paths():
    """
    Returns a list of paths to user-provides languages files.
    """
    from django.conf import settings
    globalpath = os.path.join(
        os.path.dirname(sys.modules[settings.__module__].__file__), 'locale')
    return [globalpath] + list(settings.LOCALE_PATHS)

def check_for_language(lang_code):
    """
    Checks whether there is a global language file for the given language
    code. This is used to decide whether a user-provided language is
    available. This is only used for language codes from either the cookies
    or session and during format localization.
    """
    for path in all_locale_paths():
        if gettext_module.find('django', path, [to_locale(lang_code)]) is not None:
            return True
    return False

def get_language_from_path(path, supported=None):
    """
    Returns the language-code if there is a valid language-code
    found in the `path`.
    """
    if supported is None:
        from django.conf import settings
        supported = dict(settings.LANGUAGES)
    regex_match = language_code_prefix_re.match(path)
    if regex_match:
        lang_code = regex_match.group(1)
        if lang_code in supported and check_for_language(lang_code):
            return lang_code

def get_language_from_request(request):
    """
    Analyzes the request to find what language the user wants the system to
    show. Only languages listed in settings.LANGUAGES are taken into account.
    If the user requests a sublanguage where we have a main language, we send
    out the main language.
    """
    global _accepted
    from django.conf import settings
    supported = dict(settings.LANGUAGES)

    lang_code = get_language_from_path(request.path_info, supported)
    if lang_code is not None:
        return lang_code

    if hasattr(request, 'session'):
        lang_code = request.session.get('django_language', None)
        if lang_code in supported and lang_code is not None and check_for_language(lang_code):
            return lang_code

    lang_code = request.COOKIES.get(settings.LANGUAGE_COOKIE_NAME)

    if lang_code and lang_code not in supported:
        lang_code = lang_code.split('-')[0] # e.g. if fr-ca is not supported fallback to fr

    if lang_code and lang_code in supported and check_for_language(lang_code):
        return lang_code

    accept = request.META.get('HTTP_ACCEPT_LANGUAGE', '')
    for accept_lang, unused in parse_accept_lang_header(accept):
        if accept_lang == '*':
            break

        # We have a very restricted form for our language files (no encoding
        # specifier, since they all must be UTF-8 and only one possible
        # language each time. So we avoid the overhead of gettext.find() and
        # work out the MO file manually.

        # 'normalized' is the root name of the locale in POSIX format (which is
        # the format used for the directories holding the MO files).
        normalized = locale.locale_alias.get(to_locale(accept_lang, True))
        if not normalized:
            continue
        # Remove the default encoding from locale_alias.
        normalized = normalized.split('.')[0]

        if normalized in _accepted:
            # We've seen this locale before and have an MO file for it, so no
            # need to check again.
            return _accepted[normalized]

        for lang, dirname in ((accept_lang, normalized),
                (accept_lang.split('-')[0], normalized.split('_')[0])):
            if lang.lower() not in supported:
                continue
            for path in all_locale_paths():
                if os.path.exists(os.path.join(path, dirname, 'LC_MESSAGES', 'django.mo')):
                    _accepted[normalized] = lang
                    return lang

    return settings.LANGUAGE_CODE

dot_re = re.compile(r'\S')
def blankout(src, char):
    """
    Changes every non-whitespace character to the given char.
    Used in the templatize function.
    """
    return dot_re.sub(char, src)

inline_re = re.compile(r"""^\s*trans\s+((?:".*?")|(?:'.*?'))\s*""")
block_re = re.compile(r"""^\s*blocktrans(?:\s+|$)""")
endblock_re = re.compile(r"""^\s*endblocktrans$""")
plural_re = re.compile(r"""^\s*plural$""")
constant_re = re.compile(r"""_\(((?:".*?")|(?:'.*?'))\)""")

def templatize(src, origin=None):
    """
    Turns a Django template into something that is understood by xgettext. It
    does so by translating the Django translation tags into standard gettext
    function invocations.
    """
    from django.template import (Lexer, TOKEN_TEXT, TOKEN_VAR, TOKEN_BLOCK,
            TOKEN_COMMENT, TRANSLATOR_COMMENT_MARK)
    out = StringIO()
    intrans = False
    inplural = False
    singular = []
    plural = []
    incomment = False
    comment = []
    for t in Lexer(src, origin).tokenize():
        if incomment:
            if t.token_type == TOKEN_BLOCK and t.contents == 'endcomment':
                content = ''.join(comment)
                translators_comment_start = None
                for lineno, line in enumerate(content.splitlines(True)):
                    if line.lstrip().startswith(TRANSLATOR_COMMENT_MARK):
                        translators_comment_start = lineno
                for lineno, line in enumerate(content.splitlines(True)):
                    if translators_comment_start is not None and lineno >= translators_comment_start:
                        out.write(' # %s' % line)
                    else:
                        out.write(' #\n')
                incomment = False
                comment = []
            else:
                comment.append(t.contents)
        elif intrans:
            if t.token_type == TOKEN_BLOCK:
                endbmatch = endblock_re.match(t.contents)
                pluralmatch = plural_re.match(t.contents)
                if endbmatch:
                    if inplural:
                        out.write(' ngettext(%r,%r,count) ' % (''.join(singular), ''.join(plural)))
                        for part in singular:
                            out.write(blankout(part, 'S'))
                        for part in plural:
                            out.write(blankout(part, 'P'))
                    else:
                        out.write(' gettext(%r) ' % ''.join(singular))
                        for part in singular:
                            out.write(blankout(part, 'S'))
                    intrans = False
                    inplural = False
                    singular = []
                    plural = []
                elif pluralmatch:
                    inplural = True
                else:
                    filemsg = ''
                    if origin:
                        filemsg = 'file %s, ' % origin
                    raise SyntaxError("Translation blocks must not include other block tags: %s (%sline %d)" % (t.contents, filemsg, t.lineno))
            elif t.token_type == TOKEN_VAR:
                if inplural:
                    plural.append('%%(%s)s' % t.contents)
                else:
                    singular.append('%%(%s)s' % t.contents)
            elif t.token_type == TOKEN_TEXT:
                contents = t.contents.replace('%', '%%')
                if inplural:
                    plural.append(contents)
                else:
                    singular.append(contents)
        else:
            if t.token_type == TOKEN_BLOCK:
                imatch = inline_re.match(t.contents)
                bmatch = block_re.match(t.contents)
                cmatches = constant_re.findall(t.contents)
                if imatch:
                    g = imatch.group(1)
                    if g[0] == '"': g = g.strip('"')
                    elif g[0] == "'": g = g.strip("'")
                    out.write(' gettext(%r) ' % g)
                elif bmatch:
                    for fmatch in constant_re.findall(t.contents):
                        out.write(' _(%s) ' % fmatch)
                    intrans = True
                    inplural = False
                    singular = []
                    plural = []
                elif cmatches:
                    for cmatch in cmatches:
                        out.write(' _(%s) ' % cmatch)
                elif t.contents == 'comment':
                    incomment = True
                else:
                    out.write(blankout(t.contents, 'B'))
            elif t.token_type == TOKEN_VAR:
                parts = t.contents.split('|')
                cmatch = constant_re.match(parts[0])
                if cmatch:
                    out.write(' _(%s) ' % cmatch.group(1))
                for p in parts[1:]:
                    if p.find(':_(') >= 0:
                        out.write(' %s ' % p.split(':',1)[1])
                    else:
                        out.write(blankout(p, 'F'))
            elif t.token_type == TOKEN_COMMENT:
                out.write(' # %s' % t.contents)
            else:
                out.write(blankout(t.contents, 'X'))
    return out.getvalue()

def parse_accept_lang_header(lang_string):
    """
    Parses the lang_string, which is the body of an HTTP Accept-Language
    header, and returns a list of (lang, q-value), ordered by 'q' values.

    Any format errors in lang_string results in an empty list being returned.
    """
    result = []
    pieces = accept_language_re.split(lang_string)
    if pieces[-1]:
        return []
    for i in range(0, len(pieces) - 1, 3):
        first, lang, priority = pieces[i : i + 3]
        if first:
            return []
        priority = priority and float(priority) or 1.0
        result.append((lang, priority))
    result.sort(key=lambda k: k[1], reverse=True)
    return result