From 7a465cb5ee7e298cae626ace1fc3e7d97df79f2e Mon Sep 17 00:00:00 2001
From: Serhiy Storchaka <storchaka@gmail.com>
Date: Sat, 30 Mar 2019 08:23:38 +0200
Subject: bpo-24214: Fixed the UTF-8 incremental decoder. (GH-12603)

The bug occurred when the encoded surrogate character is passed
to the incremental decoder in two chunks.
---
 Objects/unicodeobject.c | 3 +++
 1 file changed, 3 insertions(+)

(limited to 'Objects')

diff --git a/Objects/unicodeobject.c b/Objects/unicodeobject.c
index 8ab3943e61..c0b345be7e 100644
--- a/Objects/unicodeobject.c
+++ b/Objects/unicodeobject.c
@@ -4883,6 +4883,9 @@ PyUnicode_DecodeUTF8Stateful(const char *s,
         case 2:
         case 3:
         case 4:
+            if (s == end || consumed) {
+                goto End;
+            }
             errmsg = "invalid continuation byte";
             startinpos = s - starts;
             endinpos = startinpos + ch - 1;
-- 
cgit v1.2.1