From 0e060bc34e87b397b4f7b1fb275f15867fe506d2 Mon Sep 17 00:00:00 2001
From: Helmut Merz <helmutm@cy55.de>
Date: Thu, 10 May 2012 10:19:12 +0200
Subject: [PATCH] sanitize HTML before stripping tags in order to avoid empty
 results with certain Word formattings

---
 util/html.py | 1 +
 1 file changed, 1 insertion(+)

diff --git a/util/html.py b/util/html.py
index 51b15df..69aade7 100644
--- a/util/html.py
+++ b/util/html.py
@@ -79,6 +79,7 @@ def checkStyle(k):
 
 
 def stripAll(value):
+    value = sanitize(value)
     def collectText(tags):
         for tag in tags:
             if type(tag) is NavigableString: