From ea37193b6824767e4087d63ba8204611f5118878 Mon Sep 17 00:00:00 2001
From: Kovid Goyal <kovid@kovidgoyal.net>
Date: Sat, 19 Jul 2014 00:56:47 +0530
Subject: [PATCH] Fix #1344061 [erroneus regex in
 preprocess.py](https://bugs.launchpad.net/calibre/+bug/1344061)

---
 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 22e7c09cb2..d28cd7058b 100644
--- a/src/calibre/ebooks/conversion/preprocess.py
+++ b/src/calibre/ebooks/conversion/preprocess.py
@@ -271,7 +271,7 @@ class Dehyphenator(object):
         elif format == 'txt':
             intextmatch = re.compile(u'(?<=.{%i})(?P<firstpart>[^\W\-]+)(-|‐)(\u0020|\u0009)*(?P<wraptags>(\n(\u0020|\u0009)*)+)(?P<secondpart>[\w\d]+)'% length)  # noqa
         elif format == 'individual_words':
-            intextmatch = re.compile(u'(?!<)(?P<firstpart>[^\W\-]+)(-|‐)\s*(?P<secondpart>\w+)(?![^<]*?>)')
+            intextmatch = re.compile(u'(?!<)(?P<firstpart>[^\W\-]+)(-|‐)\s*(?P<secondpart>\w+)(?![^<]*?>)', re.UNICODE)
         elif format == 'html_cleanup':
             intextmatch = re.compile(u'(?P<firstpart>[^\W\-]+)(-|‐)\s*(?=<)(?P<wraptags></span>\s*(</[iubp]>\s*<[iubp][^>]*>\s*)?<span[^>]*>|</[iubp]>\s*<[iubp][^>]*>)?\s*(?P<secondpart>[\w\d]+)')  # noqa
         elif format == 'txt_cleanup':