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='/#%[]=:;$&()+,!?*')