lxml should only ever return an ASCII string as a str

gsnedders · gsnedders · commit 816eaf4eca91 · 2016-05-11T09:25:57.000-07:00
See <http://lxml.de/FAQ.html#why-does-lxml-sometimes-return-str-values-for-text-in-python-2>
diff --git a/html5lib/treewalkers/lxmletree.py b/html5lib/treewalkers/lxmletree.py
@@ -15,7 +15,7 @@ def ensure_str(s):
     elif isinstance(s, text_type):
         return s
     else:
-        return s.decode("utf-8", "strict")
+        return s.decode("ascii", "strict")
 
 
 class Root(object):
