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 | ||||
| -rw-r--r-- | Lib/test/test_io.py | 9 | ||||
| -rw-r--r-- | Lib/test/test_multibytecodec.py | 30 |
5 files changed, 70 insertions, 2 deletions
diff --git a/Lib/test/cjkencodings/hz-utf8.txt b/Lib/test/cjkencodings/hz-utf8.txt new file mode 100644 index 0000000000..7c11735c1f --- /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 0000000000..f882d46344 --- /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 77bac139cf..9622b63bb0 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__) diff --git a/Lib/test/test_io.py b/Lib/test/test_io.py index 1ec6f93a0e..5333bb6dfd 100644 --- a/Lib/test/test_io.py +++ b/Lib/test/test_io.py @@ -790,14 +790,17 @@ class BufferedReaderTest(unittest.TestCase, CommonBufferedTests): # Inject some None's in there to simulate EWOULDBLOCK rawio = self.MockRawIO((b"abc", b"d", None, b"efg", None, None, None)) bufio = self.tp(rawio) - self.assertEqual(b"abcd", bufio.read(6)) self.assertEqual(b"e", bufio.read(1)) self.assertEqual(b"fg", bufio.read()) self.assertEqual(b"", bufio.peek(1)) - self.assertTrue(None is bufio.read()) + self.assertIsNone(bufio.read()) self.assertEqual(b"", bufio.read()) + rawio = self.MockRawIO((b"a", None, None)) + self.assertEqual(b"a", rawio.readall()) + self.assertIsNone(rawio.readall()) + def test_read_past_eof(self): rawio = self.MockRawIO((b"abc", b"d", b"efg")) bufio = self.tp(rawio) @@ -2467,6 +2470,8 @@ class MiscIOTest(unittest.TestCase): self.assertRaises(ValueError, f.read) if hasattr(f, "read1"): self.assertRaises(ValueError, f.read1, 1024) + if hasattr(f, "readall"): + self.assertRaises(ValueError, f.readall) if hasattr(f, "readinto"): self.assertRaises(ValueError, f.readinto, bytearray(1024)) self.assertRaises(ValueError, f.readline) diff --git a/Lib/test/test_multibytecodec.py b/Lib/test/test_multibytecodec.py index f3c8c615c2..069d09021e 100644 --- a/Lib/test/test_multibytecodec.py +++ b/Lib/test/test_multibytecodec.py @@ -257,6 +257,36 @@ class Test_ISO2022(unittest.TestCase): # Any ISO 2022 codec will cause the segfault myunichr(x).encode('iso_2022_jp', 'ignore') +class TestStateful(unittest.TestCase): + text = '\u4E16\u4E16' + encoding = 'iso-2022-jp' + expected = b'\x1b$B@$@$' + expected_reset = b'\x1b$B@$@$\x1b(B' + + def test_encode(self): + self.assertEqual(self.text.encode(self.encoding), self.expected_reset) + + def test_incrementalencoder(self): + encoder = codecs.getincrementalencoder(self.encoding)() + output = b''.join( + encoder.encode(char) + for char in self.text) + self.assertEqual(output, self.expected) + + def test_incrementalencoder_final(self): + encoder = codecs.getincrementalencoder(self.encoding)() + last_index = len(self.text) - 1 + output = b''.join( + encoder.encode(char, index == last_index) + for index, char in enumerate(self.text)) + self.assertEqual(output, self.expected_reset) + +class TestHZStateful(TestStateful): + text = '\u804a\u804a' + encoding = 'hz' + expected = b'~{ADAD' + expected_reset = b'~{ADAD~}' + def test_main(): support.run_unittest(__name__) |