[Python-checkins] cpython (merge default -> default): Branch merge
eric.araujo
python-checkins at python.org
Sat Nov 3 22:10:15 CET 2012
http://hg.python.org/cpython/rev/2a58d406e5c5
changeset: 80222:2a58d406e5c5
parent: 80220:458bf8dffe83
parent: 80218:e4aedd239e45
user: Éric Araujo <merwok at netwok.org>
date: Sat Nov 03 17:09:37 2012 -0400
summary:
Branch merge
files:
Lib/test/test_codecs.py | 2 ++
Misc/NEWS | 3 +++
Python/codecs.c | 8 ++++----
3 files changed, 9 insertions(+), 4 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
@@ -668,6 +668,8 @@
self.assertTrue(codecs.lookup_error("surrogatepass"))
with self.assertRaises(UnicodeDecodeError):
b"abc\xed\xa0".decode("utf-8", "surrogatepass")
+ with self.assertRaises(UnicodeDecodeError):
+ b"abc\xed\xa0z".decode("utf-8", "surrogatepass")
@unittest.skipUnless(sys.platform == 'win32',
'cp65001 is a Windows-only codec')
diff --git a/Misc/NEWS b/Misc/NEWS
--- a/Misc/NEWS
+++ b/Misc/NEWS
@@ -10,6 +10,9 @@
Core and Builtins
-----------------
+- Issue #16336: fix input checking in the surrogatepass error handler.
+ Patch by Serhiy Storchaka.
+
- Issue #8401: assigning an int to a bytearray slice (e.g. b[3:4] = 5) now
raises an error.
diff --git a/Python/codecs.c b/Python/codecs.c
--- a/Python/codecs.c
+++ b/Python/codecs.c
@@ -791,10 +791,10 @@
/* Try decoding a single surrogate character. If
there are more, let the codec call us again. */
p += start;
- if (strlen(p) > 2 &&
- ((p[0] & 0xf0) == 0xe0 ||
- (p[1] & 0xc0) == 0x80 ||
- (p[2] & 0xc0) == 0x80)) {
+ if (PyBytes_GET_SIZE(object) - start >= 3 &&
+ (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 (!Py_UNICODE_IS_SURROGATE(ch))
--
Repository URL: http://hg.python.org/cpython
More information about the Python-checkins
mailing list