Mercurial > cpython-lru_cache-weakref
diff Lib/test/test_codecs.py @ 79108:c64dec45d46f
Issue #15379: Fix passing of non-BMP characters as integers for the charmap decoder (already working as unicode strings).
Patch by Serhiy Storchaka.
| author | Antoine Pitrou <solipsis@pitrou.net> |
|---|---|
| date | Sun, 23 Sep 2012 20:00:04 +0200 |
| parents | 118fe0ee6921 620d23f7ad41 |
| children | fd41c6b4de57 |
line wrap: on
line diff
--- a/Lib/test/test_codecs.py Sun Sep 23 18:20:23 2012 +0200 +++ b/Lib/test/test_codecs.py Sun Sep 23 20:00:04 2012 +0200 @@ -1693,6 +1693,15 @@ ) self.assertEqual( + codecs.charmap_decode(b"\x00\x01\x02", "strict", "\U0010FFFFbc"), + ("\U0010FFFFbc", 3) + ) + + self.assertRaises(UnicodeDecodeError, + codecs.charmap_decode, b"\x00\x01\x02", "strict", "ab" + ) + + self.assertEqual( codecs.charmap_decode(b"\x00\x01\x02", "replace", "ab"), ("ab\ufffd", 3) ) @@ -1718,6 +1727,113 @@ ("", len(allbytes)) ) + def test_decode_with_int2str_map(self): + self.assertEqual( + codecs.charmap_decode(b"\x00\x01\x02", "strict", + {0: 'a', 1: 'b', 2: 'c'}), + ("abc", 3) + ) + + self.assertEqual( + codecs.charmap_decode(b"\x00\x01\x02", "strict", + {0: 'Aa', 1: 'Bb', 2: 'Cc'}), + ("AaBbCc", 3) + ) + + self.assertEqual( + codecs.charmap_decode(b"\x00\x01\x02", "strict", + {0: '\U0010FFFF', 1: 'b', 2: 'c'}), + ("\U0010FFFFbc", 3) + ) + + self.assertEqual( + codecs.charmap_decode(b"\x00\x01\x02", "strict", + {0: 'a', 1: 'b', 2: ''}), + ("ab", 3) + ) + + self.assertRaises(UnicodeDecodeError, + codecs.charmap_decode, b"\x00\x01\x02", "strict", + {0: 'a', 1: 'b'} + ) + + self.assertEqual( + codecs.charmap_decode(b"\x00\x01\x02", "replace", + {0: 'a', 1: 'b'}), + ("ab\ufffd", 3) + ) + + self.assertEqual( + codecs.charmap_decode(b"\x00\x01\x02", "replace", + {0: 'a', 1: 'b', 2: None}), + ("ab\ufffd", 3) + ) + + self.assertEqual( + codecs.charmap_decode(b"\x00\x01\x02", "ignore", + {0: 'a', 1: 'b'}), + ("ab", 3) + ) + + self.assertEqual( + codecs.charmap_decode(b"\x00\x01\x02", "ignore", + {0: 'a', 1: 'b', 2: None}), + ("ab", 3) + ) + + allbytes = bytes(range(256)) + self.assertEqual( + codecs.charmap_decode(allbytes, "ignore", {}), + ("", len(allbytes)) + ) + + def test_decode_with_int2int_map(self): + a = ord('a') + b = ord('b') + c = ord('c') + + self.assertEqual( + codecs.charmap_decode(b"\x00\x01\x02", "strict", + {0: a, 1: b, 2: c}), + ("abc", 3) + ) + + # Issue #15379 + self.assertEqual( + codecs.charmap_decode(b"\x00\x01\x02", "strict", + {0: 0x10FFFF, 1: b, 2: c}), + ("\U0010FFFFbc", 3) + ) + + self.assertEqual( + codecs.charmap_decode(b"\x00\x01\x02", "strict", + {0: sys.maxunicode, 1: b, 2: c}), + (chr(sys.maxunicode) + "bc", 3) + ) + + self.assertRaises(TypeError, + codecs.charmap_decode, b"\x00\x01\x02", "strict", + {0: sys.maxunicode + 1, 1: b, 2: c} + ) + + self.assertRaises(UnicodeDecodeError, + codecs.charmap_decode, b"\x00\x01\x02", "strict", + {0: a, 1: b}, + ) + + self.assertEqual( + codecs.charmap_decode(b"\x00\x01\x02", "replace", + {0: a, 1: b}), + ("ab\ufffd", 3) + ) + + self.assertEqual( + codecs.charmap_decode(b"\x00\x01\x02", "ignore", + {0: a, 1: b}), + ("ab", 3) + ) + + class WithStmtTest(unittest.TestCase): def test_encodedfile(self): f = io.BytesIO(b"\xc3\xbc")