Debian Codegraph @

Lib/test/test_codecencodings_cn.py

raw
1 #
2 # test_codecencodings_cn.py
3 # Codec encoding tests for PRC encodings.
4 #
5
6 from test import multibytecodec_support
7 import unittest
8
9 class Test_GB2312(multibytecodec_support.TestBase, unittest.TestCase):
10 encoding = 'gb2312'
11 tstring = multibytecodec_support.load_teststring('gb2312')
12 codectests = (
13 # invalid bytes
14 (b"abc\x81\x81\xc1\xc4", "strict", None),
15 (b"abc\xc8", "strict", None),
16 (b"abc\x81\x81\xc1\xc4", "replace", "abc\ufffd\ufffd\u804a"),
17 (b"abc\x81\x81\xc1\xc4\xc8", "replace", "abc\ufffd\ufffd\u804a\ufffd"),
18 (b"abc\x81\x81\xc1\xc4", "ignore", "abc\u804a"),
19 (b"\xc1\x64", "strict", None),
20 )
21
22 class Test_GBK(multibytecodec_support.TestBase, unittest.TestCase):
23 encoding = 'gbk'
24 tstring = multibytecodec_support.load_teststring('gbk')
25 codectests = (
26 # invalid bytes
27 (b"abc\x80\x80\xc1\xc4", "strict", None),
28 (b"abc\xc8", "strict", None),
29 (b"abc\x80\x80\xc1\xc4", "replace", "abc\ufffd\ufffd\u804a"),
30 (b"abc\x80\x80\xc1\xc4\xc8", "replace", "abc\ufffd\ufffd\u804a\ufffd"),
31 (b"abc\x80\x80\xc1\xc4", "ignore", "abc\u804a"),
32 (b"\x83\x34\x83\x31", "strict", None),
33 ("\u30fb", "strict", None),
34 )
35
36 class Test_GB18030(multibytecodec_support.TestBase, unittest.TestCase):
37 encoding = 'gb18030'
38 tstring = multibytecodec_support.load_teststring('gb18030')
39 codectests = (
40 # invalid bytes
41 (b"abc\x80\x80\xc1\xc4", "strict", None),
42 (b"abc\xc8", "strict", None),
43 (b"abc\x80\x80\xc1\xc4", "replace", "abc\ufffd\ufffd\u804a"),
44 (b"abc\x80\x80\xc1\xc4\xc8", "replace", "abc\ufffd\ufffd\u804a\ufffd"),
45 (b"abc\x80\x80\xc1\xc4", "ignore", "abc\u804a"),
46 (b"abc\x84\x39\x84\x39\xc1\xc4", "replace", "abc\ufffd9\ufffd9\u804a"),
47 ("\u30fb", "strict", b"\x819\xa79"),
48 (b"abc\x84\x32\x80\x80def", "replace", 'abc\ufffd2\ufffd\ufffddef'),
49 (b"abc\x81\x30\x81\x30def", "strict", 'abc\x80def'),
50 (b"abc\x86\x30\x81\x30def", "replace", 'abc\ufffd0\ufffd0def'),
51 # issue29990
52 (b"\xff\x30\x81\x30", "strict", None),
53 (b"\x81\x30\xff\x30", "strict", None),
54 (b"abc\x81\x39\xff\x39\xc1\xc4", "replace", "abc\ufffd\x39\ufffd\x39\u804a"),
55 (b"abc\xab\x36\xff\x30def", "replace", 'abc\ufffd\x36\ufffd\x30def'),
56 (b"abc\xbf\x38\xff\x32\xc1\xc4", "ignore", "abc\x38\x32\u804a"),
57 )
58 has_iso10646 = True
59
60 class Test_HZ(multibytecodec_support.TestBase, unittest.TestCase):
61 encoding = 'hz'
62 tstring = multibytecodec_support.load_teststring('hz')
63 codectests = (
64 # test '~\n' (3 lines)
65 (b'This sentence is in ASCII.\n'
66 b'The next sentence is in GB.~{<:Ky2;S{#,~}~\n'
67 b'~{NpJ)l6HK!#~}Bye.\n',
68 'strict',
69 'This sentence is in ASCII.\n'
70 'The next sentence is in GB.'
71 '\u5df1\u6240\u4e0d\u6b32\uff0c\u52ff\u65bd\u65bc\u4eba\u3002'
72 'Bye.\n'),
73 # test '~\n' (4 lines)
74 (b'This sentence is in ASCII.\n'
75 b'The next sentence is in GB.~\n'
76 b'~{<:Ky2;S{#,NpJ)l6HK!#~}~\n'
77 b'Bye.\n',
78 'strict',
79 'This sentence is in ASCII.\n'
80 'The next sentence is in GB.'
81 '\u5df1\u6240\u4e0d\u6b32\uff0c\u52ff\u65bd\u65bc\u4eba\u3002'
82 'Bye.\n'),
83 # invalid bytes
84 (b'ab~cd', 'replace', 'ab\uFFFDcd'),
85 (b'ab\xffcd', 'replace', 'ab\uFFFDcd'),
86 (b'ab~{\x81\x81\x41\x44~}cd', 'replace', 'ab\uFFFD\uFFFD\u804Acd'),
87 (b'ab~{\x41\x44~}cd', 'replace', 'ab\u804Acd'),
88 (b"ab~{\x79\x79\x41\x44~}cd", "replace", "ab\ufffd\ufffd\u804acd"),
89 # issue 30003
90 ('ab~cd', 'strict', b'ab~~cd'), # escape ~
91 (b'~{Dc~~:C~}', 'strict', None), # ~~ only in ASCII mode
92 (b'~{Dc~\n:C~}', 'strict', None), # ~\n only in ASCII mode
93 )
94
95 if __name__ == "__main__":
96 unittest.main()