diff options
Diffstat (limited to 'webapp/django/utils/encoding.py')
-rw-r--r-- | webapp/django/utils/encoding.py | 100 |
1 files changed, 100 insertions, 0 deletions
diff --git a/webapp/django/utils/encoding.py b/webapp/django/utils/encoding.py new file mode 100644 index 0000000000..c54e67610f --- /dev/null +++ b/webapp/django/utils/encoding.py @@ -0,0 +1,100 @@ +import types +import urllib +import datetime +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 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='/#%[]=:;$&()+,!?*') + |