From 78dc53abae36e2c2fa3a40ab72e558ad0abcd000 Mon Sep 17 00:00:00 2001
From: John Schember <john@nachtimwald.com>
Date: Wed, 24 Aug 2011 18:20:43 -0400
Subject: [PATCH] Add more characters referecned by bug #822744 to the line
 unwrap lookahead character list.

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

diff --git a/src/calibre/ebooks/conversion/utils.py b/src/calibre/ebooks/conversion/utils.py
index 7488df4609..e17aad50d8 100644
--- a/src/calibre/ebooks/conversion/utils.py
+++ b/src/calibre/ebooks/conversion/utils.py
@@ -315,7 +315,7 @@ class HeuristicProcessor(object):
         supports a range of html markup and text files
         '''
         # define the pieces of the regex
-        lookahead = "(?<=.{"+str(length)+u"}([a-zäëïöüàèìòùáćéíóńśúâêîôûçąężıãõñæøþðßě,:)\IA\u00DF]|(?<!\&\w{4});))" # (?<!\&\w{4});) is a semicolon not part of an entity
+        lookahead = "(?<=.{"+str(length)+u"}([a-zäëïöüàèìòùáćéíóńśúâêîôûçąężıãõñæøþðßôľščťžňďěřů,:)\IA\u00DF]|(?<!\&\w{4});))" # (?<!\&\w{4});) is a semicolon not part of an entity
         em_en_lookahead = "(?<=.{"+str(length)+u"}[\u2013\u2014])"
         soft_hyphen = u"\xad"
         line_ending = "\s*</(span|[iubp]|div)>\s*(</(span|[iubp]|div)>)?"