test_unicode.py 文件源码

def test_utf8_decode_valid_sequences(self):
        sequences = [
            # single byte
            ('\x00', u'\x00'), ('a', u'a'), ('\x7f', u'\x7f'),
            # 2 bytes
            ('\xc2\x80', u'\x80'), ('\xdf\xbf', u'\u07ff'),
            # 3 bytes
            ('\xe0\xa0\x80', u'\u0800'), ('\xed\x9f\xbf', u'\ud7ff'),
            ('\xee\x80\x80', u'\uE000'), ('\xef\xbf\xbf', u'\uffff'),
            # 4 bytes
            ('\xF0\x90\x80\x80', u'\U00010000'),
            ('\xf4\x8f\xbf\xbf', u'\U0010FFFF')
        ]
        for seq, res in sequences:
            self.assertEqual(seq.decode('utf-8'), res)

        for ch in map(unichr, range(0, sys.maxunicode)):
            self.assertEqual(ch, ch.encode('utf-8').decode('utf-8'))