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
|
import types
import urllib
import locale
import datetime
import codecs
from decimal import Decimal
from django.utils.functional import Promise
class DjangoUnicodeDecodeError(UnicodeDecodeError):
def __init__(self, obj, *args):
self.obj = obj
UnicodeDecodeError.__init__(self, *args)
def __str__(self):
original = UnicodeDecodeError.__str__(self)
return '%s. You passed in %r (%s)' % (original, self.obj,
type(self.obj))
class StrAndUnicode(object):
"""
A class whose __str__ returns its __unicode__ as a UTF-8 bytestring.
Useful as a mix-in.
"""
def __str__(self):
return self.__unicode__().encode('utf-8')
def smart_unicode(s, encoding='utf-8', strings_only=False, errors='strict'):
"""
Returns a unicode object representing 's'. Treats bytestrings using the
'encoding' codec.
If strings_only is True, don't convert (some) non-string-like objects.
"""
if isinstance(s, Promise):
# The input is the result of a gettext_lazy() call.
return s
return force_unicode(s, encoding, strings_only, errors)
def is_protected_type(obj):
"""Determine if the object instance is of a protected type.
Objects of protected types are preserved as-is when passed to
force_unicode(strings_only=True).
"""
return isinstance(obj, (
types.NoneType,
int, long,
datetime.datetime, datetime.date, datetime.time,
float, Decimal)
)
def force_unicode(s, encoding='utf-8', strings_only=False, errors='strict'):
"""
Similar to smart_unicode, except that lazy instances are resolved to
strings, rather than kept as lazy objects.
If strings_only is True, don't convert (some) non-string-like objects.
"""
if strings_only and is_protected_type(s):
return s
try:
if not isinstance(s, basestring,):
if hasattr(s, '__unicode__'):
s = unicode(s)
else:
try:
s = unicode(str(s), encoding, errors)
except UnicodeEncodeError:
if not isinstance(s, Exception):
raise
# If we get to here, the caller has passed in an Exception
# subclass populated with non-ASCII data without special
# handling to display as a string. We need to handle this
# without raising a further exception. We do an
# approximation to what the Exception's standard str()
# output should be.
s = ' '.join([force_unicode(arg, encoding, strings_only,
errors) for arg in s])
elif not isinstance(s, unicode):
# Note: We use .decode() here, instead of unicode(s, encoding,
# errors), so that if s is a SafeString, it ends up being a
# SafeUnicode at the end.
s = s.decode(encoding, errors)
except UnicodeDecodeError, e:
if not isinstance(s, Exception):
raise DjangoUnicodeDecodeError(s, *e.args)
else:
# If we get to here, the caller has passed in an Exception
# subclass populated with non-ASCII bytestring data without a
# working unicode method. Try to handle this without raising a
# further exception by individually forcing the exception args
# to unicode.
s = ' '.join([force_unicode(arg, encoding, strings_only,
errors) for arg in s])
return s
def smart_str(s, encoding='utf-8', strings_only=False, errors='strict'):
"""
Returns a bytestring version of 's', encoded as specified in 'encoding'.
If strings_only is True, don't convert (some) non-string-like objects.
"""
if strings_only and isinstance(s, (types.NoneType, int)):
return s
if isinstance(s, Promise):
return unicode(s).encode(encoding, errors)
elif not isinstance(s, basestring):
try:
return str(s)
except UnicodeEncodeError:
if isinstance(s, Exception):
# An Exception subclass containing non-ASCII data that doesn't
# know how to print itself properly. We shouldn't raise a
# further exception.
return ' '.join([smart_str(arg, encoding, strings_only,
errors) for arg in s])
return unicode(s).encode(encoding, errors)
elif isinstance(s, unicode):
return s.encode(encoding, errors)
elif s and encoding != 'utf-8':
return s.decode('utf-8', errors).encode(encoding, errors)
else:
return s
def iri_to_uri(iri):
"""
Convert an Internationalized Resource Identifier (IRI) portion to a URI
portion that is suitable for inclusion in a URL.
This is the algorithm from section 3.1 of RFC 3987. However, since we are
assuming input is either UTF-8 or unicode already, we can simplify things a
little from the full method.
Returns an ASCII string containing the encoded result.
"""
# The list of safe characters here is constructed from the "reserved" and
# "unreserved" characters specified in sections 2.2 and 2.3 of RFC 3986:
# reserved = gen-delims / sub-delims
# gen-delims = ":" / "/" / "?" / "#" / "[" / "]" / "@"
# sub-delims = "!" / "$" / "&" / "'" / "(" / ")"
# / "*" / "+" / "," / ";" / "="
# unreserved = ALPHA / DIGIT / "-" / "." / "_" / "~"
# Of the unreserved characters, urllib.quote already considers all but
# the ~ safe.
# The % character is also added to the list of safe characters here, as the
# end of section 3.1 of RFC 3987 specifically mentions that % must not be
# converted.
if iri is None:
return iri
return urllib.quote(smart_str(iri), safe="/#%[]=:;$&()+,!?*@'~")
# The encoding of the default system locale but falls back to the
# given fallback encoding if the encoding is unsupported by python or could
# not be determined. See tickets #10335 and #5846
try:
DEFAULT_LOCALE_ENCODING = locale.getdefaultlocale()[1] or 'ascii'
codecs.lookup(DEFAULT_LOCALE_ENCODING)
except:
DEFAULT_LOCALE_ENCODING = 'ascii'
|
