def force_bytes(s, encoding='utf-8', strings_only=False, errors='strict'):
"""
Similar to smart_bytes, 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 isinstance(s, bytes):
if encoding == 'utf-8':
return s
else:
return s.decode('utf-8', errors).encode(encoding, errors)
if strings_only and (s is None or isinstance(s, int)):
return s
if isinstance(s, Promise):
return six.text_type(s).encode(encoding, errors)
if not isinstance(s, six.string_types):
try:
if six.PY3:
return six.text_type(s).encode(encoding)
else:
return bytes(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 b' '.join([force_bytes(arg, encoding, strings_only,
errors) for arg in s])
return six.text_type(s).encode(encoding, errors)
else:
return s.encode(encoding, errors)
def __mod__(self, rhs):
if self._delegate_bytes and not six.PY3:
return bytes(self) % rhs
elif self._delegate_text:
return six.text_type(self) % rhs
else:
raise AssertionError('__mod__ not supported for non-string types')
def force_text(s, encoding='utf-8', strings_only=False, errors='strict'):
"""
Similar to smart_text, 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.
"""
# Handle the common case first, saves 30-40% when s is an instance of
# six.text_type. This function gets called often in that setting.
if isinstance(s, six.text_type):
return s
if strings_only and is_protected_type(s):
return s
try:
if not isinstance(s, six.string_types):
if hasattr(s, '__unicode__'):
s = s.__unicode__()
else:
if six.PY3:
if isinstance(s, bytes):
s = six.text_type(s, encoding, errors)
else:
s = six.text_type(s)
else:
s = six.text_type(bytes(s), encoding, errors)
else:
# Note: We use .decode() here, instead of six.text_type(s, encoding,
# errors), so that if s is a SafeBytes, it ends up being a
# SafeText at the end.
s = s.decode(encoding, errors)
except UnicodeDecodeError as 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_text(arg, encoding, strings_only,
errors) for arg in s])
return s
