diff options
| author | Walter Dörwald <walter@livinglogic.de> | 2007-04-12 10:35:00 (GMT) |
|---|---|---|
| committer | Walter Dörwald <walter@livinglogic.de> | 2007-04-12 10:35:00 (GMT) |
| commit | 4234827e99eb73adbd387e15619cd6290f80f655 (patch) | |
| tree | b4ab22283f7054598fc18a0f8c2168145c33a0a8 /Lib/test | |
| parent | 9aba6d6905bcf3f3009f71cfa70525eb8b0ad3dc (diff) | |
| download | cpython-4234827e99eb73adbd387e15619cd6290f80f655.zip cpython-4234827e99eb73adbd387e15619cd6290f80f655.tar.gz cpython-4234827e99eb73adbd387e15619cd6290f80f655.tar.bz2 | |
Fix utf-8-sig incremental decoder, which didn't recognise a BOM when the
first chunk fed to the decoder started with a BOM, but was longer than 3 bytes.
Diffstat (limited to 'Lib/test')
| -rw-r--r-- | Lib/test/test_codecs.py | 5 |
1 files changed, 5 insertions, 0 deletions
diff --git a/Lib/test/test_codecs.py b/Lib/test/test_codecs.py index 3c800f8..0389623 100644 --- a/Lib/test/test_codecs.py +++ b/Lib/test/test_codecs.py @@ -429,6 +429,11 @@ class UTF8SigTest(ReadTest): # SF bug #1601501: check that the codec works with a buffer unicode("\xef\xbb\xbf", "utf-8-sig") + def test_bom(self): + d = codecs.getincrementaldecoder("utf-8-sig")() + s = u"spam" + self.assertEqual(d.decode(s.encode("utf-8-sig")), s) + class EscapeDecodeTest(unittest.TestCase): def test_empty(self): self.assertEquals(codecs.escape_decode(""), ("", 0)) |