From f7ec532d578f874bf915c5f2bbd5077e667c074c Mon Sep 17 00:00:00 2001
From: John Schember <john@nachtimwald.com>
Date: Thu, 9 Apr 2009 17:31:07 -0400
Subject: [PATCH] pdftohtml processing: better line re-wrapping

---
 src/calibre/ebooks/conversion/preprocess.py | 8 ++++++++
 1 file changed, 8 insertions(+)

diff --git a/src/calibre/ebooks/conversion/preprocess.py b/src/calibre/ebooks/conversion/preprocess.py
index bb8ee90364..3fbbb47d13 100644
--- a/src/calibre/ebooks/conversion/preprocess.py
+++ b/src/calibre/ebooks/conversion/preprocess.py
@@ -48,6 +48,8 @@ class HTMLPreProcessor(object):
 
     # Fix pdftohtml markup
     PDFTOHTML  = [
+                  # Remove page links
+                  (re.compile(r'<a name=\d+></a>', re.IGNORECASE), lambda match: ''),
                   # Remove <hr> tags
                   (re.compile(r'<hr.*?>', re.IGNORECASE), lambda match: '<br />'),
                   # Remove page numbers
@@ -69,6 +71,12 @@ class HTMLPreProcessor(object):
                   
                   # Have paragraphs show better
                   (re.compile(r'<br.*?>'), lambda match : '<p>'),
+                  
+                  # Re wrap lines
+                  (re.compile(r'(?<=\w)\s*</i>\s*<p.*?>\s*<i>\s*(?=\w)'), lambda match: ' '),
+                  (re.compile(r'(?<=\w)\s*<p.*?>\s*(?=\w)', re.UNICODE), lambda match: ' '),
+                  # Clean up spaces
+                  (re.compile(ru'(?<=\.|,|:|;|\?|!|”|"|\')[\s^ ]*(?=<)'), lambda match: ' '),
                   ]
 
     # Fix Book Designer markup