From 4fc0538e30786f18b75a01583948e8acf7a7cce8 Mon Sep 17 00:00:00 2001
From: Helmut Merz <helmutm@cy55.de>
Date: Fri, 1 Mar 2013 16:31:02 +0100
Subject: [PATCH] remove special HTML comments from MS Word even when escaped

---
 util/html.py | 11 +++++++++--
 1 file changed, 9 insertions(+), 2 deletions(-)

diff --git a/util/html.py b/util/html.py
index f3dba46..56abd5a 100644
--- a/util/html.py
+++ b/util/html.py
@@ -20,6 +20,8 @@
 Strip HTML tags and other HTML-related utilities.
 """
 
+import re
+
 from cybertools.text.lib.BeautifulSoup import BeautifulSoup, Comment
 from cybertools.text.lib.BeautifulSoup import Declaration, NavigableString
 
@@ -32,9 +34,11 @@ validAttrs = ('align alt border cellpadding cellspacing class colspan '
 validStyles = 'font-style font-weight'.split()
 validStyleParts = 'border padding'.split()
 
+escCommPattern = re.compile(r'&lt;\!--\[if .*?\!\[endif\]--&gt;', re.DOTALL)
+
 
 def sanitize(value, validTags=validTags, validAttrs=validAttrs,
-                    validStyles=validStyles):
+                    validStyles=validStyles, stripEscapedComments=True):
     soup = BeautifulSoup(value)
     for comment in soup.findAll(text=lambda text: isinstance(text, Comment)):
         comment.extract()
@@ -51,7 +55,10 @@ def sanitize(value, validTags=validTags, validAttrs=validAttrs,
             if val:
                 attrs.append((attr, val))
         tag.attrs = attrs
-    return soup.renderContents().decode('utf8')
+    result = soup.renderContents()
+    if stripEscapedComments:
+        result = escCommPattern.sub(u'', result)
+    return result.decode('utf8')
 
 
 def sanitizeStyle(value, validStyles=validStyles):