commit c4b82c037e95fe2fe77352e8a4a54be7b209df2a
author Serhiy Storchaka <storchaka@gmail.com> Tue Jan 08 23:12:00 2013 +0200
committer Serhiy Storchaka <storchaka@gmail.com> Tue Jan 08 23:12:00 2013 +0200
tree 3a56936d881f41dbcd05cbf5d43afc76161e67f3
parent c9631a14d77bd34a7c0ecf1cb1e5f8983b76d48f

Issue #11461: Fix the incremental UTF-16 decoder. Original patch by
Amaury Forgeot d'Arc. Added tests for partial decoding of non-BMP
characters.

Objects/unicodeobject.c

diff --git a/Objects/unicodeobject.c b/Objects/unicodeobject.c
index 7713b54..1c6e55d 100644
--- a/Objects/unicodeobject.c
+++ b/Objects/unicodeobject.c
@@ -2565,8 +2565,11 @@
 
         /* UTF-16 code pair: */
         if (e - q < 2) {
+            q -= 2;
+            if (consumed)
+                break;
             errmsg = "unexpected end of data";
-            startinpos = (((const char *)q)-2)-starts;
+            startinpos = ((const char *)q)-starts;
             endinpos = ((const char *)e)-starts;
             goto utf16Error;
         }