diff options
Diffstat (limited to 'Lib/test')
| -rw-r--r-- | Lib/test/cjkencodings/hz-utf8.txt | 2 | ||||
| -rw-r--r-- | Lib/test/cjkencodings/hz.txt | 2 | ||||
| -rw-r--r-- | Lib/test/test_codecencodings_cn.py | 29 | 
3 files changed, 33 insertions, 0 deletions
| diff --git a/Lib/test/cjkencodings/hz-utf8.txt b/Lib/test/cjkencodings/hz-utf8.txt new file mode 100644 index 0000000..7c11735 --- /dev/null +++ b/Lib/test/cjkencodings/hz-utf8.txt @@ -0,0 +1,2 @@ +This sentence is in ASCII. +The next sentence is in GB.己所不欲,勿施於人。Bye. diff --git a/Lib/test/cjkencodings/hz.txt b/Lib/test/cjkencodings/hz.txt new file mode 100644 index 0000000..f882d46 --- /dev/null +++ b/Lib/test/cjkencodings/hz.txt @@ -0,0 +1,2 @@ +This sentence is in ASCII. +The next sentence is in GB.~{<:Ky2;S{#,NpJ)l6HK!#~}Bye. diff --git a/Lib/test/test_codecencodings_cn.py b/Lib/test/test_codecencodings_cn.py index 96b0d77..215e8de 100644 --- a/Lib/test/test_codecencodings_cn.py +++ b/Lib/test/test_codecencodings_cn.py @@ -50,6 +50,35 @@ class Test_GB18030(test_multibytecodec_support.TestBase, unittest.TestCase):      )      has_iso10646 = True +class Test_HZ(test_multibytecodec_support.TestBase, unittest.TestCase): +    encoding = 'hz' +    tstring = test_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', +         u'This sentence is in ASCII.\n' +         u'The next sentence is in GB.' +         u'\u5df1\u6240\u4e0d\u6b32\uff0c\u52ff\u65bd\u65bc\u4eba\u3002' +         u'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', +         u'This sentence is in ASCII.\n' +         u'The next sentence is in GB.' +         u'\u5df1\u6240\u4e0d\u6b32\uff0c\u52ff\u65bd\u65bc\u4eba\u3002' +         u'Bye.\n'), +        # invalid bytes +        (b'ab~cd', 'replace', u'ab\uFFFDd'), +        (b'ab\xffcd', 'replace', u'ab\uFFFDcd'), +        (b'ab~{\x81\x81\x41\x44~}cd', 'replace', u'ab\uFFFD\uFFFD\u804Acd'), +    ) +  def test_main():      test_support.run_unittest(__name__) | 
