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
|
Closes: http://bugs.debian.org/448838
Comment:
Upstream patch grabbed from http://media.djangoproject.com/patches/2007-10-26-security-fix/i18n-0.95.diff
.
Fixes Denial of Service Vulnerability (CVE-2007-5712).
--- python-django-0.95.1/django/utils/translation/trans_real.py 2006-07-03 20:58:45.000000000 -0700
+++ python-django-0.95.1.new/django/utils/translation/trans_real.py 2008-09-07 11:53:51.000000000 -0700
@@ -1,6 +1,9 @@
"Translation helper functions"
-import os, re, sys
+import locale
+import os
+import re
+import sys
import gettext as gettext_module
from cStringIO import StringIO
from django.utils.functional import lazy
@@ -25,15 +28,25 @@
# The default translation is based on the settings file.
_default = None
-# This is a cache for accept-header to translation object mappings to prevent
-# the accept parser to run multiple times for one user.
+# This is a cache for normalised accept-header languages to prevent multiple
+# file lookups when checking the same locale on repeated requests.
_accepted = {}
-def to_locale(language):
+# 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", "*"
+ (?:;q=(0(?:\.\d{,3})?|1(?:.0{,3})?))? # Optional "q=1.00", "q=0.8"
+ (?:\s*,\s*|$) # Multiple accepts per header.
+ ''', re.VERBOSE)
+
+def to_locale(language, to_lower=False):
"Turns a language name (en-us) into a locale name (en_US)."
p = language.find('-')
if p >= 0:
- return language[:p].lower()+'_'+language[p+1:].upper()
+ if to_lower:
+ return language[:p].lower()+'_'+language[p+1:].lower()
+ else:
+ return language[:p].lower()+'_'+language[p+1:].upper()
else:
return language.lower()
@@ -309,46 +322,40 @@
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('django_language', None)
- if lang_code in supported and lang_code is not None and check_for_language(lang_code):
+ lang_code = request.COOKIES.get('django_language')
+ if lang_code and lang_code in supported and check_for_language(lang_code):
return lang_code
- accept = request.META.get('HTTP_ACCEPT_LANGUAGE', None)
- if accept is not None:
-
- t = _accepted.get(accept, None)
- if t is not None:
- return t
-
- def _parsed(el):
- p = el.find(';q=')
- if p >= 0:
- lang = el[:p].strip()
- order = int(float(el[p+3:].strip())*100)
- else:
- lang = el
- order = 100
- p = lang.find('-')
- if p >= 0:
- mainlang = lang[:p]
- else:
- mainlang = lang
- return (lang, mainlang, order)
-
- langs = [_parsed(el) for el in accept.split(',')]
- langs.sort(lambda a,b: -1*cmp(a[2], b[2]))
-
- for lang, mainlang, order in langs:
- if lang in supported or mainlang in supported:
- langfile = gettext_module.find('django', globalpath, [to_locale(lang)])
- if langfile:
- # reconstruct the actual language from the language
- # filename, because otherwise we might incorrectly
- # report de_DE if we only have de available, but
- # did find de_DE because of language normalization
- lang = langfile[len(globalpath):].split(os.path.sep)[1]
- _accepted[accept] = lang
- return lang
+ accept = request.META.get('HTTP_ACCEPT_LANGUAGE', '')
+ for lang, unused in parse_accept_lang_header(accept):
+ if 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
+ # look up the MO file manually.
+
+ normalized = locale.locale_alias.get(to_locale(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 in (normalized, normalized.split('_')[0]):
+ if lang not in supported:
+ continue
+ langfile = os.path.join(globalpath, lang, 'LC_MESSAGES',
+ 'django.mo')
+ if os.path.exists(langfile):
+ _accepted[normalized] = lang
+ return lang
return settings.LANGUAGE_CODE
@@ -494,3 +501,24 @@
return ''.join([str(el) for el in strings])
string_concat = lazy(string_concat, str)
+
+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(lambda x, y: -cmp(x[1], y[1]))
+ return result
+
|
