django1/django/utils/encoding.py

103 lines
3.5 KiB
Python

import types
import urllib
import datetime
from django.utils.functional import Promise
from django.utils.safestring import SafeData, mark_safe
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 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 isinstance(s, (types.NoneType, int, long, datetime.datetime, datetime.date, datetime.time, float)):
return s
try:
if not isinstance(s, basestring,):
if hasattr(s, '__unicode__'):
s = unicode(s)
else:
s = unicode(str(s), encoding, errors)
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:
raise DjangoUnicodeDecodeError(s, *e.args)
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:
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 printable ASCII
# characters that are not explicitly excluded by the list at the end of
# section 3.1 of RFC 3987.
if iri is None:
return iri
return urllib.quote(smart_str(iri), safe='/#%[]=:;$&()+,!?')