#16336: fix input checking in the surrogatepass error handler. Patch by Serhiy Storchaka.

ezio-melotti · ezio-melotti · commit 540da76115f4 · 2012-11-03T23:03:39.000+02:00
diff --git a/Lib/test/test_codecs.py b/Lib/test/test_codecs.py
@@ -647,6 +647,8 @@ def test_surrogatepass_handler(self):
         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")
 
 class UTF7Test(ReadTest):
     encoding = "utf-7"
diff --git a/Misc/NEWS b/Misc/NEWS
@@ -10,6 +10,9 @@ What's New in Python 3.2.4
 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
@@ -821,10 +821,10 @@ PyCodec_SurrogatePassErrors(PyObject *exc)
         /* 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 (ch < 0xd800 || ch > 0xdfff)
