def check_in_range(self, from_, to, encode=False):
element = etree.Element('test')
for char_int in range(from_, to + 1):
try:
char = unicode_chr(char_int)
if encode:
char = char.encode('utf-8')
stripped = strip_invalid_characters(char)
element.text = stripped
element.set('some_attr', stripped)
except UnicodeEncodeError as e:
if e.reason != 'surrogates not allowed':
raise
except Exception as e:
self.fail(r'Failed on unicode char \0x{char:x}: {e}'.format(char=char_int, e=e))
def test_not_basestring(self):
self.assertEqual(strip_invalid_characters(5), u'5')
def test_utf8_encoded_str(self):
value = u'\x85 пример utf-8 строки'.encode('utf-8')
res = strip_invalid_characters(value)
self.assertIsInstance(res, unicode_type)
self.assertEqual(res, u'\x85 пример utf-8 строки')
def test_none(self):
self.assertEqual(strip_invalid_characters(None), u'')