commit 48e188e57313813bd048e25b8fa6123b8cd5c9a0
author Serhiy Storchaka <storchaka@gmail.com> Tue Jan 08 23:14:24 2013 +0200
committer Serhiy Storchaka <storchaka@gmail.com> Tue Jan 08 23:14:24 2013 +0200
tree 3d5b4dacb7995a82e1057a7fa4dc1ed7d8dc8c5c
parent dec798eb46f7edfe0995ce1b8966097fb7567eb7

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 7cd0399..7f86bfd 100644
--- a/Objects/unicodeobject.c
+++ b/Objects/unicodeobject.c
@@ -3573,8 +3573,11 @@
 
         /* 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;
         }