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.
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 @@
# 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))