diff --git a/Lib/test/cjkencodings/hz-utf8.txt b/Lib/test/cjkencodings/hz-utf8.txt new file mode 100644 index 00000000000..7c11735c1f1 --- /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 00000000000..f882d463447 --- /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 a2d97184971..dca9f10b836 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', + '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\uFFFDd'), + (b'ab\xffcd', 'replace', 'ab\uFFFDcd'), + (b'ab~{\x81\x81\x41\x44~}cd', 'replace', 'ab\uFFFD\uFFFD\u804Acd'), + ) + def test_main(): support.run_unittest(__name__)