diff options
Diffstat (limited to 'Lib/test/test_codecs.py')
| -rw-r--r-- | Lib/test/test_codecs.py | 143 |
1 files changed, 133 insertions, 10 deletions
diff --git a/Lib/test/test_codecs.py b/Lib/test/test_codecs.py index b93e0ab0e2..4740b682aa 100644 --- a/Lib/test/test_codecs.py +++ b/Lib/test/test_codecs.py @@ -27,6 +27,7 @@ def coding_checker(self, coder): self.assertEqual(coder(input), (expect, len(input))) return check + class Queue(object): """ queue: write bytes at one end, read bytes from the other end @@ -47,6 +48,7 @@ class Queue(object): self._buffer = self._buffer[size:] return s + class MixInCheckStateHandling: def check_state_handling_decode(self, encoding, u, s): for i in range(len(s)+1): @@ -80,6 +82,7 @@ class MixInCheckStateHandling: part2 = d.encode(u[i:], True) self.assertEqual(s, part1+part2) + class ReadTest(MixInCheckStateHandling): def check_partial(self, input, partialresults): # get a StreamReader for the encoding and feed the bytestring version @@ -358,6 +361,12 @@ class ReadTest(MixInCheckStateHandling): self.assertEqual("[\uDC80]".encode(self.encoding, "replace"), "[?]".encode(self.encoding)) + # sequential surrogate characters + self.assertEqual("[\uD800\uDC80]".encode(self.encoding, "ignore"), + "[]".encode(self.encoding)) + self.assertEqual("[\uD800\uDC80]".encode(self.encoding, "replace"), + "[??]".encode(self.encoding)) + bom = "".encode(self.encoding) for before, after in [("\U00010fff", "A"), ("[", "]"), ("A", "\U00010fff")]: @@ -383,6 +392,7 @@ class ReadTest(MixInCheckStateHandling): self.assertEqual(test_sequence.decode(self.encoding, "backslashreplace"), before + backslashreplace + after) + class UTF32Test(ReadTest, unittest.TestCase): encoding = "utf-32" if sys.byteorder == 'little': @@ -478,6 +488,7 @@ class UTF32Test(ReadTest, unittest.TestCase): self.assertEqual('\U00010000' * 1024, codecs.utf_32_decode(encoded_be)[0]) + class UTF32LETest(ReadTest, unittest.TestCase): encoding = "utf-32-le" ill_formed_sequence = b"\x80\xdc\x00\x00" @@ -523,6 +534,7 @@ class UTF32LETest(ReadTest, unittest.TestCase): self.assertEqual('\U00010000' * 1024, codecs.utf_32_le_decode(encoded)[0]) + class UTF32BETest(ReadTest, unittest.TestCase): encoding = "utf-32-be" ill_formed_sequence = b"\x00\x00\xdc\x80" @@ -747,6 +759,7 @@ class UTF8Test(ReadTest, unittest.TestCase): encoding = "utf-8" ill_formed_sequence = b"\xed\xb2\x80" ill_formed_sequence_replace = "\ufffd" * 3 + BOM = b'' def test_partial(self): self.check_partial( @@ -775,27 +788,49 @@ class UTF8Test(ReadTest, unittest.TestCase): self.check_state_handling_decode(self.encoding, u, u.encode(self.encoding)) + def test_decode_error(self): + for data, error_handler, expected in ( + (b'[\x80\xff]', 'ignore', '[]'), + (b'[\x80\xff]', 'replace', '[\ufffd\ufffd]'), + (b'[\x80\xff]', 'surrogateescape', '[\udc80\udcff]'), + (b'[\x80\xff]', 'backslashreplace', '[\\x80\\xff]'), + ): + with self.subTest(data=data, error_handler=error_handler, + expected=expected): + self.assertEqual(data.decode(self.encoding, error_handler), + expected) + def test_lone_surrogates(self): super().test_lone_surrogates() # not sure if this is making sense for # UTF-16 and UTF-32 - self.assertEqual("[\uDC80]".encode('utf-8', "surrogateescape"), - b'[\x80]') + self.assertEqual("[\uDC80]".encode(self.encoding, "surrogateescape"), + self.BOM + b'[\x80]') + + with self.assertRaises(UnicodeEncodeError) as cm: + "[\uDC80\uD800\uDFFF]".encode(self.encoding, "surrogateescape") + exc = cm.exception + self.assertEqual(exc.object[exc.start:exc.end], '\uD800\uDFFF') def test_surrogatepass_handler(self): - self.assertEqual("abc\ud800def".encode("utf-8", "surrogatepass"), - b"abc\xed\xa0\x80def") - self.assertEqual(b"abc\xed\xa0\x80def".decode("utf-8", "surrogatepass"), + self.assertEqual("abc\ud800def".encode(self.encoding, "surrogatepass"), + self.BOM + b"abc\xed\xa0\x80def") + self.assertEqual("\U00010fff\uD800".encode(self.encoding, "surrogatepass"), + self.BOM + b"\xf0\x90\xbf\xbf\xed\xa0\x80") + self.assertEqual("[\uD800\uDC80]".encode(self.encoding, "surrogatepass"), + self.BOM + b'[\xed\xa0\x80\xed\xb2\x80]') + + self.assertEqual(b"abc\xed\xa0\x80def".decode(self.encoding, "surrogatepass"), "abc\ud800def") - self.assertEqual("\U00010fff\uD800".encode("utf-8", "surrogatepass"), - b"\xf0\x90\xbf\xbf\xed\xa0\x80") - self.assertEqual(b"\xf0\x90\xbf\xbf\xed\xa0\x80".decode("utf-8", "surrogatepass"), + self.assertEqual(b"\xf0\x90\xbf\xbf\xed\xa0\x80".decode(self.encoding, "surrogatepass"), "\U00010fff\uD800") + self.assertTrue(codecs.lookup_error("surrogatepass")) with self.assertRaises(UnicodeDecodeError): - b"abc\xed\xa0".decode("utf-8", "surrogatepass") + b"abc\xed\xa0".decode(self.encoding, "surrogatepass") with self.assertRaises(UnicodeDecodeError): - b"abc\xed\xa0z".decode("utf-8", "surrogatepass") + b"abc\xed\xa0z".decode(self.encoding, "surrogatepass") + @unittest.skipUnless(sys.platform == 'win32', 'cp65001 is a Windows-only codec') @@ -1059,6 +1094,7 @@ class ReadBufferTest(unittest.TestCase): class UTF8SigTest(UTF8Test, unittest.TestCase): encoding = "utf-8-sig" + BOM = codecs.BOM_UTF8 def test_partial(self): self.check_partial( @@ -1194,6 +1230,7 @@ class EscapeDecodeTest(unittest.TestCase): self.assertEqual(decode(br"[\x0]\x0", "ignore"), (b"[]", 8)) self.assertEqual(decode(br"[\x0]\x0", "replace"), (b"[?]?", 8)) + class RecodingTest(unittest.TestCase): def test_recoding(self): f = io.BytesIO() @@ -1313,6 +1350,7 @@ for i in punycode_testcases: if len(i)!=2: print(repr(i)) + class PunycodeTest(unittest.TestCase): def test_encode(self): for uni, puny in punycode_testcases: @@ -1332,6 +1370,7 @@ class PunycodeTest(unittest.TestCase): puny = puny.decode("ascii").encode("ascii") self.assertEqual(uni, puny.decode("punycode")) + class UnicodeInternalTest(unittest.TestCase): @unittest.skipUnless(SIZEOF_WCHAR_T == 4, 'specific to 32-bit wchar_t') def test_bug1251300(self): @@ -1586,6 +1625,7 @@ class NameprepTest(unittest.TestCase): except Exception as e: raise support.TestFailed("Test 3.%d: %s" % (pos+1, str(e))) + class IDNACodecTest(unittest.TestCase): def test_builtin_decode(self): self.assertEqual(str(b"python.org", "idna"), "python.org") @@ -1672,6 +1712,7 @@ class IDNACodecTest(unittest.TestCase): self.assertRaises(Exception, b"python.org".decode, "idna", errors) + class CodecsModuleTest(unittest.TestCase): def test_decode(self): @@ -1780,6 +1821,7 @@ class CodecsModuleTest(unittest.TestCase): self.assertRaises(UnicodeError, codecs.decode, b'abc', 'undefined', errors) + class StreamReaderTest(unittest.TestCase): def setUp(self): @@ -1790,6 +1832,7 @@ class StreamReaderTest(unittest.TestCase): f = self.reader(self.stream) self.assertEqual(f.readlines(), ['\ud55c\n', '\uae00']) + class EncodedFileTest(unittest.TestCase): def test_basic(self): @@ -1920,6 +1963,7 @@ broken_unicode_with_stateful = [ "unicode_internal" ] + class BasicUnicodeTest(unittest.TestCase, MixInCheckStateHandling): def test_basics(self): s = "abc123" # all codecs should be able to encode these @@ -2082,6 +2126,7 @@ class BasicUnicodeTest(unittest.TestCase, MixInCheckStateHandling): self.check_state_handling_decode(encoding, u, u.encode(encoding)) self.check_state_handling_encode(encoding, u, u.encode(encoding)) + class CharmapTest(unittest.TestCase): def test_decode_with_string_map(self): self.assertEqual( @@ -2332,6 +2377,7 @@ class WithStmtTest(unittest.TestCase): info.streamwriter, 'strict') as srw: self.assertEqual(srw.read(), "\xfc") + class TypesTest(unittest.TestCase): def test_decode_unicode(self): # Most decoders don't accept unicode input @@ -2622,6 +2668,7 @@ else: bytes_transform_encodings.append("bz2_codec") transform_aliases["bz2_codec"] = ["bz2"] + class TransformCodecTest(unittest.TestCase): def test_basics(self): @@ -3099,5 +3146,81 @@ class CodePageTest(unittest.TestCase): self.assertEqual(decoded, ('abc', 3)) +class ASCIITest(unittest.TestCase): + def test_encode(self): + self.assertEqual('abc123'.encode('ascii'), b'abc123') + + def test_encode_error(self): + for data, error_handler, expected in ( + ('[\x80\xff\u20ac]', 'ignore', b'[]'), + ('[\x80\xff\u20ac]', 'replace', b'[???]'), + ('[\x80\xff\u20ac]', 'xmlcharrefreplace', b'[€ÿ€]'), + ('[\x80\xff\u20ac\U000abcde]', 'backslashreplace', + b'[\\x80\\xff\\u20ac\\U000abcde]'), + ('[\udc80\udcff]', 'surrogateescape', b'[\x80\xff]'), + ): + with self.subTest(data=data, error_handler=error_handler, + expected=expected): + self.assertEqual(data.encode('ascii', error_handler), + expected) + + def test_encode_surrogateescape_error(self): + with self.assertRaises(UnicodeEncodeError): + # the first character can be decoded, but not the second + '\udc80\xff'.encode('ascii', 'surrogateescape') + + def test_decode(self): + self.assertEqual(b'abc'.decode('ascii'), 'abc') + + def test_decode_error(self): + for data, error_handler, expected in ( + (b'[\x80\xff]', 'ignore', '[]'), + (b'[\x80\xff]', 'replace', '[\ufffd\ufffd]'), + (b'[\x80\xff]', 'surrogateescape', '[\udc80\udcff]'), + (b'[\x80\xff]', 'backslashreplace', '[\\x80\\xff]'), + ): + with self.subTest(data=data, error_handler=error_handler, + expected=expected): + self.assertEqual(data.decode('ascii', error_handler), + expected) + + +class Latin1Test(unittest.TestCase): + def test_encode(self): + for data, expected in ( + ('abc', b'abc'), + ('\x80\xe9\xff', b'\x80\xe9\xff'), + ): + with self.subTest(data=data, expected=expected): + self.assertEqual(data.encode('latin1'), expected) + + def test_encode_errors(self): + for data, error_handler, expected in ( + ('[\u20ac\udc80]', 'ignore', b'[]'), + ('[\u20ac\udc80]', 'replace', b'[??]'), + ('[\u20ac\U000abcde]', 'backslashreplace', + b'[\\u20ac\\U000abcde]'), + ('[\u20ac\udc80]', 'xmlcharrefreplace', b'[€�]'), + ('[\udc80\udcff]', 'surrogateescape', b'[\x80\xff]'), + ): + with self.subTest(data=data, error_handler=error_handler, + expected=expected): + self.assertEqual(data.encode('latin1', error_handler), + expected) + + def test_encode_surrogateescape_error(self): + with self.assertRaises(UnicodeEncodeError): + # the first character can be decoded, but not the second + '\udc80\u20ac'.encode('latin1', 'surrogateescape') + + def test_decode(self): + for data, expected in ( + (b'abc', 'abc'), + (b'[\x80\xff]', '[\x80\xff]'), + ): + with self.subTest(data=data, expected=expected): + self.assertEqual(data.decode('latin1'), expected) + + if __name__ == "__main__": unittest.main() |