From 68aa6195e03a84ee63b427cbbc0f09c080e1ee01 Mon Sep 17 00:00:00 2001
From: Kovid Goyal <kovid@kovidgoyal.net>
Date: Thu, 13 Oct 2011 10:05:17 +0530
Subject: [PATCH] MOBI Input: Remove invalid tags of the form <xyz: > Fixes
 #872883 (fatal error in converting mobi to rtf)

---
 src/calibre/ebooks/mobi/reader.py | 4 ++++
 1 file changed, 4 insertions(+)

diff --git a/src/calibre/ebooks/mobi/reader.py b/src/calibre/ebooks/mobi/reader.py
index 04637ffa89..e4b40616ba 100644
--- a/src/calibre/ebooks/mobi/reader.py
+++ b/src/calibre/ebooks/mobi/reader.py
@@ -325,6 +325,10 @@ class MobiReader(object):
         self.processed_html = self.processed_html.replace('</</', '</')
         self.processed_html = re.sub(r'</([a-zA-Z]+)<', r'</\1><',
                 self.processed_html)
+        # Remove tags of the form <xyz: ...> as they can cause issues further
+        # along the pipeline
+        self.processed_html = re.sub(r'</{0,1}[a-zA-Z]+:\s+[^>]*>', '',
+                self.processed_html)
 
         for pat in ENCODING_PATS:
             self.processed_html = pat.sub('', self.processed_html)