class Test_HZ(multibytecodec_support.TestBase, unittest.TestCase):
encoding = 'hz'
tstring = multibytecodec_support.load_teststring('hz')
codectests = (
# test '~\n' (3 lines)
(b'This sentence is in ASCII.\n'
b'The next sentence is in GB.~{<:Ky2;S{#,~}~\n'
b'~{NpJ)l6HK!#~}Bye.\n', 'strict', 'This sentence is in ASCII.\n'
'The next sentence is in GB.'
'\u5df1\u6240\u4e0d\u6b32\uff0c\u52ff\u65bd\u65bc\u4eba\u3002'
'Bye.\n'),
# test '~\n' (4 lines)
(b'This sentence is in ASCII.\n'
b'The next sentence is in GB.~\n'
b'~{<:Ky2;S{#,NpJ)l6HK!#~}~\n'
b'Bye.\n', 'strict', 'This sentence is in ASCII.\n'
'The next sentence is in GB.'
'\u5df1\u6240\u4e0d\u6b32\uff0c\u52ff\u65bd\u65bc\u4eba\u3002'
'Bye.\n'),
# invalid bytes
(b'ab~cd', 'replace', 'ab\uFFFDcd'),
(b'ab\xffcd', 'replace', 'ab\uFFFDcd'),
(b'ab~{\x81\x81\x41\x44~}cd', 'replace', 'ab\uFFFD\uFFFD\u804Acd'),
(b'ab~{\x41\x44~}cd', 'replace', 'ab\u804Acd'),
(b"ab~{\x79\x79\x41\x44~}cd", "replace", "ab\ufffd\ufffd\u804acd"),
# issue 30003
('ab~cd', 'strict', b'ab~~cd'), # escape ~
(b'~{Dc~~:C~}', 'strict', None), # ~~ only in ASCII mode
(b'~{Dc~\n:C~}', 'strict', None), # ~\n only in ASCII mode
)
class Test_EUCKR(multibytecodec_support.TestBase, unittest.TestCase):
encoding = 'euc_kr'
tstring = multibytecodec_support.load_teststring('euc_kr')
codectests = (
# invalid bytes
(b"abc\x80\x80\xc1\xc4", "strict", None),
(b"abc\xc8", "strict", None),
(b"abc\x80\x80\xc1\xc4", "replace", 'abc\ufffd\ufffd\uc894'),
(b"abc\x80\x80\xc1\xc4\xc8", "replace", "abc\ufffd\ufffd\uc894\ufffd"),
(b"abc\x80\x80\xc1\xc4", "ignore", "abc\uc894"),
# composed make-up sequence errors
(b"\xa4\xd4", "strict", None),
(b"\xa4\xd4\xa4", "strict", None),
(b"\xa4\xd4\xa4\xb6", "strict", None),
(b"\xa4\xd4\xa4\xb6\xa4", "strict", None),
(b"\xa4\xd4\xa4\xb6\xa4\xd0", "strict", None),
(b"\xa4\xd4\xa4\xb6\xa4\xd0\xa4", "strict", None),
(b"\xa4\xd4\xa4\xb6\xa4\xd0\xa4\xd4", "strict", "\uc4d4"),
(b"\xa4\xd4\xa4\xb6\xa4\xd0\xa4\xd4x", "strict", "\uc4d4x"),
(b"a\xa4\xd4\xa4\xb6\xa4", "replace", 'a\ufffd'),
(b"\xa4\xd4\xa3\xb6\xa4\xd0\xa4\xd4", "strict", None),
(b"\xa4\xd4\xa4\xb6\xa3\xd0\xa4\xd4", "strict", None),
(b"\xa4\xd4\xa4\xb6\xa4\xd0\xa3\xd4", "strict", None),
(b"\xa4\xd4\xa4\xff\xa4\xd0\xa4\xd4", "replace", '\ufffd\u6e21\ufffd\u3160\ufffd'),
(b"\xa4\xd4\xa4\xb6\xa4\xff\xa4\xd4", "replace", '\ufffd\u6e21\ub544\ufffd\ufffd'),
(b"\xa4\xd4\xa4\xb6\xa4\xd0\xa4\xff", "replace", '\ufffd\u6e21\ub544\u572d\ufffd'),
(b"\xa4\xd4\xff\xa4\xd4\xa4\xb6\xa4\xd0\xa4\xd4", "replace", '\ufffd\ufffd\ufffd\uc4d4'),
(b"\xc1\xc4", "strict", "\uc894"),
)
class Test_EUC_JP_COMPAT(multibytecodec_support.TestBase, unittest.TestCase):
encoding = 'euc_jp'
tstring = multibytecodec_support.load_teststring('euc_jp')
codectests = euc_commontests + (
("\xa5", "strict", b"\x5c"),
("\u203e", "strict", b"\x7e"),
)
class Test_Big5(multibytecodec_support.TestBase, unittest.TestCase):
encoding = 'big5'
tstring = multibytecodec_support.load_teststring('big5')
codectests = (
# invalid bytes
(b"abc\x80\x80\xc1\xc4", "strict", None),
(b"abc\xc8", "strict", None),
(b"abc\x80\x80\xc1\xc4", "replace", "abc\ufffd\ufffd\u8b10"),
(b"abc\x80\x80\xc1\xc4\xc8", "replace", "abc\ufffd\ufffd\u8b10\ufffd"),
(b"abc\x80\x80\xc1\xc4", "ignore", "abc\u8b10"),
)
class Test_CP949(multibytecodec_support.TestBase, unittest.TestCase):
encoding = 'cp949'
tstring = multibytecodec_support.load_teststring('cp949')
codectests = (
# invalid bytes
(b"abc\x80\x80\xc1\xc4", "strict", None),
(b"abc\xc8", "strict", None),
(b"abc\x80\x80\xc1\xc4", "replace", "abc\ufffd\ufffd\uc894"),
(b"abc\x80\x80\xc1\xc4\xc8", "replace", "abc\ufffd\ufffd\uc894\ufffd"),
(b"abc\x80\x80\xc1\xc4", "ignore", "abc\uc894"),
)
class Test_ISO2022_KR(multibytecodec_support.TestBase, unittest.TestCase):
encoding = 'iso2022_kr'
tstring = multibytecodec_support.load_teststring('iso2022_kr')
codectests = COMMON_CODEC_TESTS + (
(b'ab\x1BNdef', 'replace', 'ab\x1BNdef'), )
# iso2022_kr.txt cannot be used to test "chunk coding": the escape
# sequence is only written on the first line
@unittest.skip('iso2022_kr.txt cannot be used to test "chunk coding"')
def test_chunkcoding(self):
pass
class Test_SJIS_COMPAT(multibytecodec_support.TestBase, unittest.TestCase):
encoding = 'shift_jis'
tstring = multibytecodec_support.load_teststring('shift_jis')
codectests = shiftjis_commonenctests + (
(b"abc\x80\x80\x82\x84", "replace", "abc\ufffd\ufffd\uff44"),
(b"abc\x80\x80\x82\x84\x88", "replace", "abc\ufffd\ufffd\uff44\ufffd"),
(b"\\\x7e", "strict", "\\\x7e"),
(b"\x81\x5f\x81\x61\x81\x7c", "strict", "\uff3c\u2016\u2212"),
(b"abc\x81\x39", "replace", "abc\ufffd9"),
(b"abc\xEA\xFC", "replace", "abc\ufffd\ufffd"),
(b"abc\xFF\x58", "replace", "abc\ufffdX"),
)
class Test_GB2312(multibytecodec_support.TestBase, unittest.TestCase):
encoding = 'gb2312'
tstring = multibytecodec_support.load_teststring('gb2312')
codectests = (
# invalid bytes
(b"abc\x81\x81\xc1\xc4", "strict", None),
(b"abc\xc8", "strict", None),
(b"abc\x81\x81\xc1\xc4", "replace", "abc\ufffd\ufffd\u804a"),
(b"abc\x81\x81\xc1\xc4\xc8", "replace", "abc\ufffd\ufffd\u804a\ufffd"),
(b"abc\x81\x81\xc1\xc4", "ignore", "abc\u804a"),
(b"\xc1\x64", "strict", None),
)
class Test_SJISX0213(multibytecodec_support.TestBase, unittest.TestCase):
encoding = 'shift_jisx0213'
tstring = multibytecodec_support.load_teststring('shift_jisx0213')
codectests = shiftjis_commonenctests + (
(b"abc\x80\x80\x82\x84", "replace", "abc\ufffd\ufffd\uff44"),
(b"abc\x80\x80\x82\x84\x88", "replace", "abc\ufffd\ufffd\uff44\ufffd"),
# sjis vs cp932
(b"\\\x7e", "replace", "\xa5\u203e"),
(b"\x81\x5f\x81\x61\x81\x7c", "replace", "\x5c\u2016\u2212"),
)
xmlcharnametest = ("\xab\u211c\xbb = \u2329\u1234\u232a",
b"\x85Gℜ\x85Q = ⟨ሴ⟩")
class Test_GBK(multibytecodec_support.TestBase, unittest.TestCase):
encoding = 'gbk'
tstring = multibytecodec_support.load_teststring('gbk')
codectests = (
# invalid bytes
(b"abc\x80\x80\xc1\xc4", "strict", None),
(b"abc\xc8", "strict", None),
(b"abc\x80\x80\xc1\xc4", "replace", "abc\ufffd\ufffd\u804a"),
(b"abc\x80\x80\xc1\xc4\xc8", "replace", "abc\ufffd\ufffd\u804a\ufffd"),
(b"abc\x80\x80\xc1\xc4", "ignore", "abc\u804a"),
(b"\x83\x34\x83\x31", "strict", None),
("\u30fb", "strict", None),
)
class Test_JOHAB(multibytecodec_support.TestBase, unittest.TestCase):
encoding = 'johab'
tstring = multibytecodec_support.load_teststring('johab')
codectests = (
# invalid bytes
(b"abc\x80\x80\xc1\xc4", "strict", None),
(b"abc\xc8", "strict", None),
(b"abc\x80\x80\xc1\xc4", "replace", "abc\ufffd\ufffd\ucd27"),
(b"abc\x80\x80\xc1\xc4\xc8", "replace", "abc\ufffd\ufffd\ucd27\ufffd"),
(b"abc\x80\x80\xc1\xc4", "ignore", "abc\ucd27"),
(b"\xD8abc", "replace", "\uFFFDabc"),
(b"\xD8\xFFabc", "replace", "\uFFFD\uFFFDabc"),
(b"\x84bxy", "replace", "\uFFFDbxy"),
(b"\x8CBxy", "replace", "\uFFFDBxy"),
)
class Test_SJIS_2004(multibytecodec_support.TestBase, unittest.TestCase):
encoding = 'shift_jis_2004'
tstring = multibytecodec_support.load_teststring('shift_jis')
codectests = shiftjis_commonenctests + (
(b"\\\x7e", "strict", "\xa5\u203e"),
(b"\x81\x5f\x81\x61\x81\x7c", "strict", "\\\u2016\u2212"),
(b"abc\xEA\xFC", "strict", "abc\u64bf"),
(b"\x81\x39xy", "replace", "\ufffd9xy"),
(b"\xFF\x58xy", "replace", "\ufffdXxy"),
(b"\x80\x80\x82\x84xy", "replace", "\ufffd\ufffd\uff44xy"),
(b"\x80\x80\x82\x84\x88xy", "replace", "\ufffd\ufffd\uff44\u5864y"),
(b"\xFC\xFBxy", "replace", '\ufffd\u95b4y'),
)
xmlcharnametest = ("\xab\u211c\xbb = \u2329\u1234\u232a",
b"\x85Gℜ\x85Q = ⟨ሴ⟩")
class Test_CP932(multibytecodec_support.TestBase, unittest.TestCase):
encoding = 'cp932'
tstring = multibytecodec_support.load_teststring('shift_jis')
codectests = (
# invalid bytes
(b"abc\x81\x00\x81\x00\x82\x84", "strict", None),
(b"abc\xf8", "strict", None),
(b"abc\x81\x00\x82\x84", "replace", "abc\ufffd\x00\uff44"),
(b"abc\x81\x00\x82\x84\x88", "replace", "abc\ufffd\x00\uff44\ufffd"),
(b"abc\x81\x00\x82\x84", "ignore", "abc\x00\uff44"),
(b"ab\xEBxy", "replace", "ab\uFFFDxy"),
(b"ab\xF0\x39xy", "replace", "ab\uFFFD9xy"),
(b"ab\xEA\xF0xy", "replace", 'ab\ufffd\ue038y'),
# sjis vs cp932
(b"\\\x7e", "replace", "\\\x7e"),
(b"\x81\x5f\x81\x61\x81\x7c", "replace", "\uff3c\u2225\uff0d"),
)
class Test_GB18030(multibytecodec_support.TestBase, unittest.TestCase):
encoding = 'gb18030'
tstring = multibytecodec_support.load_teststring('gb18030')
codectests = (
# invalid bytes
(b"abc\x80\x80\xc1\xc4", "strict", None),
(b"abc\xc8", "strict", None),
(b"abc\x80\x80\xc1\xc4", "replace", "abc\ufffd\ufffd\u804a"),
(b"abc\x80\x80\xc1\xc4\xc8", "replace", "abc\ufffd\ufffd\u804a\ufffd"),
(b"abc\x80\x80\xc1\xc4", "ignore", "abc\u804a"),
(b"abc\x84\x39\x84\x39\xc1\xc4", "replace", "abc\ufffd9\ufffd9\u804a"),
("\u30fb", "strict", b"\x819\xa79"),
(b"abc\x84\x32\x80\x80def", "replace", 'abc\ufffd2\ufffd\ufffddef'),
(b"abc\x81\x30\x81\x30def", "strict", 'abc\x80def'),
(b"abc\x86\x30\x81\x30def", "replace", 'abc\ufffd0\ufffd0def'),
# issue29990
(b"\xff\x30\x81\x30", "strict", None),
(b"\x81\x30\xff\x30", "strict", None),
(b"abc\x81\x39\xff\x39\xc1\xc4", "replace",
"abc\ufffd\x39\ufffd\x39\u804a"),
(b"abc\xab\x36\xff\x30def", "replace", 'abc\ufffd\x36\ufffd\x30def'),
(b"abc\xbf\x38\xff\x32\xc1\xc4", "ignore", "abc\x38\x32\u804a"),
)
has_iso10646 = True
class Test_ISO2022_JP2(multibytecodec_support.TestBase, unittest.TestCase):
encoding = 'iso2022_jp_2'
tstring = multibytecodec_support.load_teststring('iso2022_jp')
codectests = COMMON_CODEC_TESTS + ((b'ab\x1BNdef', 'replace', 'abdef'), )
class Test_EUC_JISX0213(multibytecodec_support.TestBase, unittest.TestCase):
encoding = 'euc_jisx0213'
tstring = multibytecodec_support.load_teststring('euc_jisx0213')
codectests = euc_commontests
xmlcharnametest = ("\xab\u211c\xbb = \u2329\u1234\u232a",
b"\xa9\xa8ℜ\xa9\xb2 = ⟨ሴ⟩")
