From 267eebb9aa489cc443e57e90a9353730345af0c3 Mon Sep 17 00:00:00 2001
From: ldolse <ldolse@yahoo.com>
Date: Sun, 21 Nov 2010 15:38:18 +0800
Subject: [PATCH] adjusted preprocessing regexes for hyphen removal and chapter
 marking

---
 src/calibre/ebooks/conversion/preprocess.py |  2 +-
 src/calibre/ebooks/conversion/utils.py      | 10 +++++-----
 2 files changed, 6 insertions(+), 6 deletions(-)

diff --git a/src/calibre/ebooks/conversion/preprocess.py b/src/calibre/ebooks/conversion/preprocess.py
index ef092f7954..3ff816b3bf 100644
--- a/src/calibre/ebooks/conversion/preprocess.py
+++ b/src/calibre/ebooks/conversion/preprocess.py
@@ -220,7 +220,7 @@ class Dehyphenator(object):
         self.html = html
         self.format = format
         if format == 'html':
-            intextmatch = re.compile(u'(?<=.{%i})(?P<firstpart>[^\[\]\\\^\$\.\|\?\*\+\(\)“"\s>]+)(-|‐)\s*(?=<)(?P<wraptags></span>\s*(</[iubp]>\s*<[iubp][^>]*>\s*)?<span[^>]*>|</[iubp]>\s*<[iubp][^>]*>)?\s*(?P<secondpart>[\w\d]+)' % length)
+            intextmatch = re.compile(u'(?<=.{%i})(?P<firstpart>[^\[\]\\\^\$\.\|\?\*\+\(\)“"\s>]+)(-|‐)\s*(?=<)(?P<wraptags>(</span>)?\s*(</[iubp]>\s*){1,2}(?P<up2threeblanks><(p|div)[^>]*>\s*(<p[^>]*>\s*</p>\s*)?</(p|div)>\s+){0,3}\s*(<[iubp][^>]*>\s*){1,2}(<span[^>]*>)?)\s*(?P<secondpart>[\w\d]+)' % length)
         elif format == 'pdf':
             intextmatch = re.compile(u'(?<=.{%i})(?P<firstpart>[^\[\]\\\^\$\.\|\?\*\+\(\)“"\s>]+)(-|‐)\s*(?P<wraptags><p>|</[iub]>\s*<p>\s*<[iub]>)\s*(?P<secondpart>[\w\d]+)'% length)
         elif format == 'individual_words':
diff --git a/src/calibre/ebooks/conversion/utils.py b/src/calibre/ebooks/conversion/utils.py
index 20689c6950..feb74324e8 100644
--- a/src/calibre/ebooks/conversion/utils.py
+++ b/src/calibre/ebooks/conversion/utils.py
@@ -107,7 +107,7 @@ class PreProcessor(object):
         # Arrange line feeds and </p> tags so the line_length and no_markup functions work correctly
         html = re.sub(r"\s*</p>", "</p>\n", html)
         html = re.sub(r"\s*<p>\s*", "\n<p>", html)
-
+        
         ###### Check Markup ######
         #
         # some lit files don't have any <p> tags or equivalent (generally just plain text between
@@ -191,10 +191,10 @@ class PreProcessor(object):
         n_lookahead_close = ")"
 
         default_title = r"(\s*[\w\'\"-]+){1,5}?(?=<)"
-        typical_chapters = r".?(Introduction|Synopsis|Acknowledgements|Chapter|Kapitel|Epilogue|Volume\s|Prologue|Book\s|Part\s|Dedication)\s*([\d\w-]+\:?\s*){0,4}"
-        numeric_chapters = r".?(\d+\.?|(CHAPTER\s*([\dA-Z\-\'\"\?\.!#,]+\s*){1,10}))\s*"
-        uppercase_chapters = r"\s*.?([A-Z#]+(\s|-){0,3}){1,5}\s*"
-        numeric_titles = r".?(\d+\.?\s+([\d\w-]+\:?\'?-?\s?){0,5})\s*"
+        typical_chapters = r"[^'\"]?(Introduction|Synopsis|Acknowledgements|Chapter|Kapitel|Epilogue|Volume\s|Prologue|Book\s|Part\s|Dedication)\s*([\d\w-]+\:?\s*){0,4}"
+        numeric_chapters = r"[^'\"]?(\d+\.?|CHAPTER)\s*([\dA-Z\-\'\"\?\.!#,]+\s*){1,10}\s*"
+        uppercase_chapters = r"\s*[^'\"]?([A-Z#]+(\s|-){0,3}){1,5}\s*"
+        numeric_titles = r"[^'\"]?(\d+\.?\s+([\d\w-]+\:?\'?-?\s?){0,5})\s*"
         emphasized_lines = r"<b[^>]*>\s*(<span[^>]*>)?\s*(?!([*#•]+\s*)+)(\s*(?=[\w#\-*\s]+<)([\w#-*]+\s*){1,5}\s*)(</span>)?\s*</b>"
 
         full_chapter_line = chapter_line_open+chapter_header_open+typical_chapters+chapter_header_close+chapter_line_close