[Python-checkins] cpython (3.2): bounds check for bad data (thanks amaury)
philip.jenvey
python-checkins at python.org
Sat Oct 27 02:05:02 CEST 2012
http://hg.python.org/cpython/rev/74d65c746f63
changeset: 79953:74d65c746f63
branch: 3.2
parent: 79941:eb999002916c
user: Philip Jenvey <pjenvey at underboss.org>
date: Fri Oct 26 17:01:53 2012 -0700
summary:
bounds check for bad data (thanks amaury)
files:
Lib/test/test_codecs.py | 2 ++
Python/codecs.c | 7 ++++---
2 files changed, 6 insertions(+), 3 deletions(-)
diff --git a/Lib/test/test_codecs.py b/Lib/test/test_codecs.py
--- a/Lib/test/test_codecs.py
+++ b/Lib/test/test_codecs.py
@@ -645,6 +645,8 @@
self.assertEqual(b"abc\xed\xa0\x80def".decode("utf-8", "surrogatepass"),
"abc\ud800def")
self.assertTrue(codecs.lookup_error("surrogatepass"))
+ with self.assertRaises(UnicodeDecodeError):
+ b"abc\xed\xa0".decode("utf-8", "surrogatepass")
class UTF7Test(ReadTest):
encoding = "utf-7"
diff --git a/Python/codecs.c b/Python/codecs.c
--- a/Python/codecs.c
+++ b/Python/codecs.c
@@ -821,9 +821,10 @@
/* Try decoding a single surrogate character. If
there are more, let the codec call us again. */
p += start;
- if ((p[0] & 0xf0) == 0xe0 ||
- (p[1] & 0xc0) == 0x80 ||
- (p[2] & 0xc0) == 0x80) {
+ if (strlen(p) > 2 &&
+ ((p[0] & 0xf0) == 0xe0 ||
+ (p[1] & 0xc0) == 0x80 ||
+ (p[2] & 0xc0) == 0x80)) {
/* it's a three-byte code */
ch = ((p[0] & 0x0f) << 12) + ((p[1] & 0x3f) << 6) + (p[2] & 0x3f);
if (ch < 0xd800 || ch > 0xdfff)
--
Repository URL: http://hg.python.org/cpython
More information about the Python-checkins
mailing list