103 lines
3.5 KiB
Python
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='/#%[]=:;$&()+,!?*')
|
|
|