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
|
import re
import urllib
import urlparse
from email.Utils import formatdate
from django.utils.encoding import smart_str, force_unicode
from django.utils.functional import allow_lazy
ETAG_MATCH = re.compile(r'(?:W/)?"((?:\\.|[^"])*)"')
def urlquote(url, safe='/'):
"""
A version of Python's urllib.quote() function that can operate on unicode
strings. The url is first UTF-8 encoded before quoting. The returned string
can safely be used as part of an argument to a subsequent iri_to_uri() call
without double-quoting occurring.
"""
return force_unicode(urllib.quote(smart_str(url), safe))
urlquote = allow_lazy(urlquote, unicode)
def urlquote_plus(url, safe=''):
"""
A version of Python's urllib.quote_plus() function that can operate on
unicode strings. The url is first UTF-8 encoded before quoting. The
returned string can safely be used as part of an argument to a subsequent
iri_to_uri() call without double-quoting occurring.
"""
return force_unicode(urllib.quote_plus(smart_str(url), safe))
urlquote_plus = allow_lazy(urlquote_plus, unicode)
def urlencode(query, doseq=0):
"""
A version of Python's urllib.urlencode() function that can operate on
unicode strings. The parameters are first case to UTF-8 encoded strings and
then encoded as per normal.
"""
if hasattr(query, 'items'):
query = query.items()
return urllib.urlencode(
[(smart_str(k),
isinstance(v, (list,tuple)) and [smart_str(i) for i in v] or smart_str(v))
for k, v in query],
doseq)
def cookie_date(epoch_seconds=None):
"""
Formats the time to ensure compatibility with Netscape's cookie standard.
Accepts a floating point number expressed in seconds since the epoch, in
UTC - such as that outputted by time.time(). If set to None, defaults to
the current time.
Outputs a string in the format 'Wdy, DD-Mon-YYYY HH:MM:SS GMT'.
"""
rfcdate = formatdate(epoch_seconds)
return '%s-%s-%s GMT' % (rfcdate[:7], rfcdate[8:11], rfcdate[12:25])
def http_date(epoch_seconds=None):
"""
Formats the time to match the RFC1123 date format as specified by HTTP
RFC2616 section 3.3.1.
Accepts a floating point number expressed in seconds since the epoch, in
UTC - such as that outputted by time.time(). If set to None, defaults to
the current time.
Outputs a string in the format 'Wdy, DD Mon YYYY HH:MM:SS GMT'.
"""
rfcdate = formatdate(epoch_seconds)
return '%s GMT' % rfcdate[:25]
# Base 36 functions: useful for generating compact URLs
def base36_to_int(s):
"""
Converts a base 36 string to an ``int``. To prevent
overconsumption of server resources, raises ``ValueError` if the
input is longer than 13 base36 digits (13 digits is sufficient to
base36-encode any 64-bit integer).
"""
if len(s) > 13:
raise ValueError("Base36 input too large")
return int(s, 36)
def int_to_base36(i):
"""
Converts an integer to a base36 string
"""
digits = "0123456789abcdefghijklmnopqrstuvwxyz"
factor = 0
# Find starting factor
while True:
factor += 1
if i < 36 ** factor:
factor -= 1
break
base36 = []
# Construct base36 representation
while factor >= 0:
j = 36 ** factor
base36.append(digits[i / j])
i = i % j
factor -= 1
return ''.join(base36)
def parse_etags(etag_str):
"""
Parses a string with one or several etags passed in If-None-Match and
If-Match headers by the rules in RFC 2616. Returns a list of etags
without surrounding double quotes (") and unescaped from \<CHAR>.
"""
etags = ETAG_MATCH.findall(etag_str)
if not etags:
# etag_str has wrong format, treat it as an opaque string then
return [etag_str]
etags = [e.decode('string_escape') for e in etags]
return etags
def quote_etag(etag):
"""
Wraps a string in double quotes escaping contents as necesary.
"""
return '"%s"' % etag.replace('\\', '\\\\').replace('"', '\\"')
def is_safe_url(url, host=None):
"""
Return ``True`` if the url is a safe redirection (i.e. it doesn't point to
a different host and uses a safe scheme).
Always returns ``False`` on an empty url.
"""
if not url:
return False
# Chrome treats \ completely as /
url = url.replace('\\', '/')
# Chrome considers any URL with more than two slashes to be absolute, but
# urlaprse is not so flexible. Treat any url with three slashes as unsafe.
if url.startswith('///'):
return False
url_info = urlparse.urlparse(url)
# Forbid URLs like http:///example.com - with a scheme, but without a hostname.
# In that URL, example.com is not the hostname but, a path component. However,
# Chrome will still consider example.com to be the hostname, so we must not
# allow this syntax.
if not url_info[1] and url_info[0]:
return False
return (not url_info[1] or url_info[1] == host) and \
(not url_info[0] or url_info[0] in ['http', 'https'])
|
