From b4c5cd0122b0afd540862c1eee7708a3be1d9baa Mon Sep 17 00:00:00 2001
From: ldolse <ldolse@yahoo.com>
Date: Wed, 19 Jan 2011 00:41:59 +0800
Subject: [PATCH] fix calls to create_oebbook, mark several strings as unicode

---
 src/calibre/ebooks/chm/input.py        | 2 +-
 src/calibre/ebooks/conversion/utils.py | 6 +++---
 src/calibre/ebooks/html/input.py       | 2 +-
 src/calibre/ebooks/snb/input.py        | 2 +-
 4 files changed, 6 insertions(+), 6 deletions(-)

diff --git a/src/calibre/ebooks/chm/input.py b/src/calibre/ebooks/chm/input.py
index c4b124fe98..89efa2b4d1 100644
--- a/src/calibre/ebooks/chm/input.py
+++ b/src/calibre/ebooks/chm/input.py
@@ -75,7 +75,7 @@ class CHMInput(InputFormatPlugin):
     def _create_oebbook(self, hhcpath, basedir, opts, log, mi):
         from calibre.ebooks.conversion.plumber import create_oebbook
         from calibre.ebooks.oeb.base import DirContainer
-        oeb = create_oebbook(log, None, opts, self,
+        oeb = create_oebbook(log, None, opts,
                 encoding=opts.input_encoding, populate=False)
         self.oeb = oeb
 
diff --git a/src/calibre/ebooks/conversion/utils.py b/src/calibre/ebooks/conversion/utils.py
index 812a863717..9ae8e5ab6f 100644
--- a/src/calibre/ebooks/conversion/utils.py
+++ b/src/calibre/ebooks/conversion/utils.py
@@ -299,9 +299,9 @@ class HeuristicProcessor(object):
         supports a range of html markup and text files
         '''
         # define the pieces of the regex
-        lookahead = "(?<=.{"+str(length)+"}([a-zäëïöüàèìòùáćéíóńśúâêîôûçąężıãõñæøþðßě,:)\IA\u00DF]|(?<!\&\w{4});))" # (?<!\&\w{4});) is a semicolon not part of an entity
-        em_en_lookahead = "(?<=.{"+str(length)+"}[\u2013\u2014])"
-        soft_hyphen = "\xad"
+        lookahead = "(?<=.{"+str(length)+u"}([a-zäëïöüàèìòùáćéíóńśúâêîôûçąężıãõñæøþðßě,:)\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)>)?"
         blanklines = "\s*(?P<up2threeblanks><(p|span|div)[^>]*>\s*(<(p|span|div)[^>]*>\s*</(span|p|div)>\s*)</(span|p|div)>\s*){0,3}\s*"
         line_opening = "<(span|[iubp]|div)[^>]*>\s*(<(span|[iubp]|div)[^>]*>)?\s*"
diff --git a/src/calibre/ebooks/html/input.py b/src/calibre/ebooks/html/input.py
index ed0bf7b3ef..080faffae6 100644
--- a/src/calibre/ebooks/html/input.py
+++ b/src/calibre/ebooks/html/input.py
@@ -295,7 +295,7 @@ class HTMLInput(InputFormatPlugin):
             return oeb
 
         from calibre.ebooks.conversion.plumber import create_oebbook
-        return create_oebbook(log, stream.name, opts, self,
+        return create_oebbook(log, stream.name, opts,
                 encoding=opts.input_encoding)
 
     def is_case_sensitive(self, path):
diff --git a/src/calibre/ebooks/snb/input.py b/src/calibre/ebooks/snb/input.py
index d2acb257aa..100ac1447f 100755
--- a/src/calibre/ebooks/snb/input.py
+++ b/src/calibre/ebooks/snb/input.py
@@ -41,7 +41,7 @@ class SNBInput(InputFormatPlugin):
             raise ValueError("Invalid SNB file")
         log.debug("Handle meta data ...")
         from calibre.ebooks.conversion.plumber import create_oebbook
-        oeb = create_oebbook(log, None, options, self,
+        oeb = create_oebbook(log, None, options,
                 encoding=options.input_encoding, populate=False)
         meta = snbFile.GetFileStream('snbf/book.snbf')
         if meta != None: