| 1 |
# |
| 2 |
# test_codecencodings_kr.py |
| 3 |
# Codec encoding tests for ROK encodings. |
| 4 |
# |
| 5 |
|
| 6 |
from test import multibytecodec_support |
| 7 |
import unittest |
| 8 |
|
| 9 |
class Test_CP949(multibytecodec_support.TestBase, unittest.TestCase): |
| 10 |
encoding = 'cp949' |
| 11 |
tstring = multibytecodec_support.load_teststring('cp949') |
| 12 |
codectests = ( |
| 13 |
# invalid bytes |
| 14 |
(b"abc\x80\x80\xc1\xc4", "strict", None), |
| 15 |
(b"abc\xc8", "strict", None), |
| 16 |
(b"abc\x80\x80\xc1\xc4", "replace", "abc\ufffd\ufffd\uc894"), |
| 17 |
(b"abc\x80\x80\xc1\xc4\xc8", "replace", "abc\ufffd\ufffd\uc894\ufffd"), |
| 18 |
(b"abc\x80\x80\xc1\xc4", "ignore", "abc\uc894"), |
| 19 |
) |
| 20 |
|
| 21 |
class Test_EUCKR(multibytecodec_support.TestBase, unittest.TestCase): |
| 22 |
encoding = 'euc_kr' |
| 23 |
tstring = multibytecodec_support.load_teststring('euc_kr') |
| 24 |
codectests = ( |
| 25 |
# invalid bytes |
| 26 |
(b"abc\x80\x80\xc1\xc4", "strict", None), |
| 27 |
(b"abc\xc8", "strict", None), |
| 28 |
(b"abc\x80\x80\xc1\xc4", "replace", 'abc\ufffd\ufffd\uc894'), |
| 29 |
(b"abc\x80\x80\xc1\xc4\xc8", "replace", "abc\ufffd\ufffd\uc894\ufffd"), |
| 30 |
(b"abc\x80\x80\xc1\xc4", "ignore", "abc\uc894"), |
| 31 |
|
| 32 |
# composed make-up sequence errors |
| 33 |
(b"\xa4\xd4", "strict", None), |
| 34 |
(b"\xa4\xd4\xa4", "strict", None), |
| 35 |
(b"\xa4\xd4\xa4\xb6", "strict", None), |
| 36 |
(b"\xa4\xd4\xa4\xb6\xa4", "strict", None), |
| 37 |
(b"\xa4\xd4\xa4\xb6\xa4\xd0", "strict", None), |
| 38 |
(b"\xa4\xd4\xa4\xb6\xa4\xd0\xa4", "strict", None), |
| 39 |
(b"\xa4\xd4\xa4\xb6\xa4\xd0\xa4\xd4", "strict", "\uc4d4"), |
| 40 |
(b"\xa4\xd4\xa4\xb6\xa4\xd0\xa4\xd4x", "strict", "\uc4d4x"), |
| 41 |
(b"a\xa4\xd4\xa4\xb6\xa4", "replace", 'a\ufffd'), |
| 42 |
(b"\xa4\xd4\xa3\xb6\xa4\xd0\xa4\xd4", "strict", None), |
| 43 |
(b"\xa4\xd4\xa4\xb6\xa3\xd0\xa4\xd4", "strict", None), |
| 44 |
(b"\xa4\xd4\xa4\xb6\xa4\xd0\xa3\xd4", "strict", None), |
| 45 |
(b"\xa4\xd4\xa4\xff\xa4\xd0\xa4\xd4", "replace", '\ufffd\u6e21\ufffd\u3160\ufffd'), |
| 46 |
(b"\xa4\xd4\xa4\xb6\xa4\xff\xa4\xd4", "replace", '\ufffd\u6e21\ub544\ufffd\ufffd'), |
| 47 |
(b"\xa4\xd4\xa4\xb6\xa4\xd0\xa4\xff", "replace", '\ufffd\u6e21\ub544\u572d\ufffd'), |
| 48 |
(b"\xa4\xd4\xff\xa4\xd4\xa4\xb6\xa4\xd0\xa4\xd4", "replace", '\ufffd\ufffd\ufffd\uc4d4'), |
| 49 |
(b"\xc1\xc4", "strict", "\uc894"), |
| 50 |
) |
| 51 |
|
| 52 |
class Test_JOHAB(multibytecodec_support.TestBase, unittest.TestCase): |
| 53 |
encoding = 'johab' |
| 54 |
tstring = multibytecodec_support.load_teststring('johab') |
| 55 |
codectests = ( |
| 56 |
# invalid bytes |
| 57 |
(b"abc\x80\x80\xc1\xc4", "strict", None), |
| 58 |
(b"abc\xc8", "strict", None), |
| 59 |
(b"abc\x80\x80\xc1\xc4", "replace", "abc\ufffd\ufffd\ucd27"), |
| 60 |
(b"abc\x80\x80\xc1\xc4\xc8", "replace", "abc\ufffd\ufffd\ucd27\ufffd"), |
| 61 |
(b"abc\x80\x80\xc1\xc4", "ignore", "abc\ucd27"), |
| 62 |
(b"\xD8abc", "replace", "\uFFFDabc"), |
| 63 |
(b"\xD8\xFFabc", "replace", "\uFFFD\uFFFDabc"), |
| 64 |
(b"\x84bxy", "replace", "\uFFFDbxy"), |
| 65 |
(b"\x8CBxy", "replace", "\uFFFDBxy"), |
| 66 |
) |
| 67 |
|
| 68 |
if __name__ == "__main__": |
| 69 |
unittest.main() |