def test_mbcs_encode(self):
# these are invalid
invalid = [
0x80, 0x82, 0x83, 0x84, 0x85, 0x86, 0x87, 0x88, 0x89, 0x8a, 0x8b,
0x8c, 0x8e, 0x91, 0x92, 0x93, 0x94, 0x95, 0x96, 0x97, 0x98, 0x99,
0x9a, 0x9b, 0x9c, 0x9e, 0x9f
]
uinvalid = ''.join([chr(i) for i in invalid])
uall = ''.join([chr(i) for i in range(256) if i not in invalid])
cpyres = b'\x00\x01\x02\x03\x04\x05\x06\x07\x08\t\n\x0b\x0c\r\x0e\x0f\x10\x11\x12\x13\x14\x15\x16\x17\x18\x19\x1a\x1b\x1c\x1d\x1e\x1f !"#$%&\'()*+,-./0123456789:;<=>?@ABCDEFGHIJKLMNOPQRSTUVWXYZ[\\]^_`abcdefghijklmnopqrstuvwxyz{|}~\x7f\x81\x8d\x8f\x90\x9d\xa0\xa1\xa2\xa3\xa4\xa5\xa6\xa7\xa8\xa9\xaa\xab\xac\xad\xae\xaf\xb0\xb1\xb2\xb3\xb4\xb5\xb6\xb7\xb8\xb9\xba\xbb\xbc\xbd\xbe\xbf\xc0\xc1\xc2\xc3\xc4\xc5\xc6\xc7\xc8\xc9\xca\xcb\xcc\xcd\xce\xcf\xd0\xd1\xd2\xd3\xd4\xd5\xd6\xd7\xd8\xd9\xda\xdb\xdc\xdd\xde\xdf\xe0\xe1\xe2\xe3\xe4\xe5\xe6\xe7\xe8\xe9\xea\xeb\xec\xed\xee\xef\xf0\xf1\xf2\xf3\xf4\xf5\xf6\xf7\xf8\xf9\xfa\xfb\xfc\xfd\xfe\xff'
for mode in ['strict', 'replace', 'ignore', 'badmodethatdoesnotexist']:
self.assertEqual(codecs.mbcs_encode('foo', mode), (b'foo', 3))
ipyres = codecs.mbcs_encode(uall, mode)[0]
self.assertEqual(cpyres, ipyres)
# all weird unicode characters that are supported
chrs = '\u20ac\u201a\u0192\u201e\u2026\u2020\u2021\u02c6\u2030\u0160\u2039\u0152\u017d\u2018\u2019\u201c\u201d\u2022\u2013\u2014\u02dc\u2122\u0161\u203a\u0153\u017e\u0178'
self.assertEqual(codecs.mbcs_encode(chrs, mode), (
b'\x80\x82\x83\x84\x85\x86\x87\x88\x89\x8a\x8b\x8c\x8e\x91\x92\x93\x94\x95\x96\x97\x98\x99\x9a\x9b\x9c\x9e\x9f',
27))
self.assertEqual(codecs.mbcs_encode(uinvalid, 'replace'),
(b'?' * len(uinvalid), len(uinvalid)))
self.assertEqual(codecs.mbcs_encode(uinvalid, 'ignore'),
(b'', len(uinvalid)))
def test_mbcs_encode(self):
for mode in ['strict', 'replace', 'ignore', 'badmodethatdoesnotexist']:
self.assertEqual(codecs.mbcs_encode('foo', mode), ('foo', 3))
uall = u''.join([unichr(i) for i in xrange(256)])
cpyres = '\x00\x01\x02\x03\x04\x05\x06\x07\x08\t\n\x0b\x0c\r\x0e\x0f\x10\x11\x12\x13\x14\x15\x16\x17\x18\x19\x1a\x1b\x1c\x1d\x1e\x1f !"#$%&\'()*+,-./0123456789:;<=>?@ABCDEFGHIJKLMNOPQRSTUVWXYZ[\\]^_`abcdefghijklmnopqrstuvwxyz{|}~\x7f?\x81???????????\x8d?\x8f\x90????????????\x9d??\xa0\xa1\xa2\xa3\xa4\xa5\xa6\xa7\xa8\xa9\xaa\xab\xac\xad\xae\xaf\xb0\xb1\xb2\xb3\xb4\xb5\xb6\xb7\xb8\xb9\xba\xbb\xbc\xbd\xbe\xbf\xc0\xc1\xc2\xc3\xc4\xc5\xc6\xc7\xc8\xc9\xca\xcb\xcc\xcd\xce\xcf\xd0\xd1\xd2\xd3\xd4\xd5\xd6\xd7\xd8\xd9\xda\xdb\xdc\xdd\xde\xdf\xe0\xe1\xe2\xe3\xe4\xe5\xe6\xe7\xe8\xe9\xea\xeb\xec\xed\xee\xef\xf0\xf1\xf2\xf3\xf4\xf5\xf6\xf7\xf8\xf9\xfa\xfb\xfc\xfd\xfe\xff'
ipyres = codecs.mbcs_encode(uall, mode)[0]
self.assertEqual(cpyres, ipyres)
# all weird unicode characters that are supported
chrs = u'\u20ac\u201a\u0192\u201e\u2026\u2020\u2021\u02c6\u2030\u0160\u2039\u0152\u017d\u2018\u2019\u201c\u201d\u2022\u2013\u2014\u02dc\u2122\u0161\u203a\u0153\u017e\u0178'
self.assertEqual(codecs.mbcs_encode(chrs, mode), ('\x80\x82\x83\x84\x85\x86\x87\x88\x89\x8a\x8b\x8c\x8e\x91\x92\x93\x94\x95\x96\x97\x98\x99\x9a\x9b\x9c\x9e\x9f', 27))
def test_mbcs_decode(self):
for mode in ['strict', 'replace', 'ignore', 'badmodethatdoesnotexist']:
self.assertEqual(codecs.mbcs_decode('foo', mode), ('foo', 3))
cpyres = u'\x00\x01\x02\x03\x04\x05\x06\x07\x08\t\n\x0b\x0c\r\x0e\x0f\x10\x11\x12\x13\x14\x15\x16\x17\x18\x19\x1a\x1b\x1c\x1d\x1e\x1f !"#$%&\'()*+,-./0123456789:;<=>?@ABCDEFGHIJKLMNOPQRSTUVWXYZ[\\]^_`abcdefghijklmnopqrstuvwxyz{|}~\x7f\u20ac\x81\u201a\u0192\u201e\u2026\u2020\u2021\u02c6\u2030\u0160\u2039\u0152\x8d\u017d\x8f\x90\u2018\u2019\u201c\u201d\u2022\u2013\u2014\u02dc\u2122\u0161\u203a\u0153\x9d\u017e\u0178\xa0\xa1\xa2\xa3\xa4\xa5\xa6\xa7\xa8\xa9\xaa\xab\xac\xad\xae\xaf\xb0\xb1\xb2\xb3\xb4\xb5\xb6\xb7\xb8\xb9\xba\xbb\xbc\xbd\xbe\xbf\xc0\xc1\xc2\xc3\xc4\xc5\xc6\xc7\xc8\xc9\xca\xcb\xcc\xcd\xce\xcf\xd0\xd1\xd2\xd3\xd4\xd5\xd6\xd7\xd8\xd9\xda\xdb\xdc\xdd\xde\xdf\xe0\xe1\xe2\xe3\xe4\xe5\xe6\xe7\xe8\xe9\xea\xeb\xec\xed\xee\xef\xf0\xf1\xf2\xf3\xf4\xf5\xf6\xf7\xf8\xf9\xfa\xfb\xfc\xfd\xfe\xff'
allchars = ''.join([chr(i) for i in xrange(256)])
self.assertEqual(codecs.mbcs_decode(allchars, mode)[0], cpyres)
# round tripping
self.assertEqual(codecs.mbcs_encode(codecs.mbcs_decode(allchars, mode)[0])[0], allchars)
def test_mbcs_decode(self):
for mode in ['strict', 'replace', 'ignore', 'badmodethatdoesnotexist']:
self.assertEqual(codecs.mbcs_decode('foo', mode), ('foo', 3))
cpyres = u'\x00\x01\x02\x03\x04\x05\x06\x07\x08\t\n\x0b\x0c\r\x0e\x0f\x10\x11\x12\x13\x14\x15\x16\x17\x18\x19\x1a\x1b\x1c\x1d\x1e\x1f !"#$%&\'()*+,-./0123456789:;<=>?@ABCDEFGHIJKLMNOPQRSTUVWXYZ[\\]^_`abcdefghijklmnopqrstuvwxyz{|}~\x7f\u20ac\x81\u201a\u0192\u201e\u2026\u2020\u2021\u02c6\u2030\u0160\u2039\u0152\x8d\u017d\x8f\x90\u2018\u2019\u201c\u201d\u2022\u2013\u2014\u02dc\u2122\u0161\u203a\u0153\x9d\u017e\u0178\xa0\xa1\xa2\xa3\xa4\xa5\xa6\xa7\xa8\xa9\xaa\xab\xac\xad\xae\xaf\xb0\xb1\xb2\xb3\xb4\xb5\xb6\xb7\xb8\xb9\xba\xbb\xbc\xbd\xbe\xbf\xc0\xc1\xc2\xc3\xc4\xc5\xc6\xc7\xc8\xc9\xca\xcb\xcc\xcd\xce\xcf\xd0\xd1\xd2\xd3\xd4\xd5\xd6\xd7\xd8\xd9\xda\xdb\xdc\xdd\xde\xdf\xe0\xe1\xe2\xe3\xe4\xe5\xe6\xe7\xe8\xe9\xea\xeb\xec\xed\xee\xef\xf0\xf1\xf2\xf3\xf4\xf5\xf6\xf7\xf8\xf9\xfa\xfb\xfc\xfd\xfe\xff'
allchars = ''.join([chr(i) for i in xrange(256)])
self.assertEqual(codecs.mbcs_decode(allchars, mode)[0], cpyres)
# round tripping
self.assertEqual(codecs.mbcs_encode(codecs.mbcs_decode(allchars, mode)[0])[0], allchars)
def encode(self, input, final=False):
return mbcs_encode(input, self.errors)[0]
def encode(self, input, final=False):
return mbcs_encode(input, self.errors)[0]
def update_event(self, inp=-1):
self.set_output_val(0, codecs.mbcs_encode(self.input(0),
self.input(1)))
