From 575b021f48ea9cab351648999bc69737ea2aafa0 Mon Sep 17 00:00:00 2001
From: John Schember <john@nachtimwald.com>
Date: Wed, 15 Apr 2009 20:11:00 -0400
Subject: [PATCH] pdftohtml preprocess rules work

---
 src/calibre/ebooks/conversion/preprocess.py | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/src/calibre/ebooks/conversion/preprocess.py b/src/calibre/ebooks/conversion/preprocess.py
index 6b58d2d18d..632a7a3291 100644
--- a/src/calibre/ebooks/conversion/preprocess.py
+++ b/src/calibre/ebooks/conversion/preprocess.py
@@ -73,7 +73,7 @@ class HTMLPreProcessor(object):
                   (re.compile(r'<br.*?>'), lambda match : '<p>'),
                   
                   # Un wrap lines
-                  (re.compile(r'(?<=\w)\s*</i>\s*<p.*?>\s*<i>\s*(?=\w)'), lambda match: ' '),
+                  (re.compile(r'(?<=\w)\s*</(i|b|u)>\s*<p.*?>\s*<(i|b|u)>\s*(?=\w)'), lambda match: ' '),
                   (re.compile(r'(?<=\w)\s*<p.*?>\s*(?=\w)', re.UNICODE), lambda match: ' '),
                   # Clean up spaces
                   (re.compile(u'(?<=\.|,|:|;|\?|!|”|"|\')[\s^ ]*(?=<)'), lambda match: ' '),