From 74243ac0b9277f5468bcdb58e54b397862da76e1 Mon Sep 17 00:00:00 2001
From: ldolse <ldolse@yahoo.com>
Date: Mon, 10 Jan 2011 17:07:40 +0800
Subject: [PATCH 1/2] preprocess tweaks

---
 src/calibre/ebooks/conversion/preprocess.py | 2 +-
 src/calibre/ebooks/conversion/utils.py      | 4 ++--
 src/calibre/ebooks/txt/processor.py         | 2 +-
 3 files changed, 4 insertions(+), 4 deletions(-)

diff --git a/src/calibre/ebooks/conversion/preprocess.py b/src/calibre/ebooks/conversion/preprocess.py
index 08a46cb8d9..f994888f19 100644
--- a/src/calibre/ebooks/conversion/preprocess.py
+++ b/src/calibre/ebooks/conversion/preprocess.py
@@ -360,7 +360,7 @@ class HTMLPreProcessor(object):
                   (re.compile(r'((?<=</a>)\s*file:////?[A-Z].*<br>|file:////?[A-Z].*<br>(?=\s*<hr>))', re.IGNORECASE), lambda match: ''),
 
                   # Center separator lines
-                  (re.compile(u'<br>\s*(?P<break>([*#•✦]+\s*)+)\s*<br>'), lambda match: '<p>\n<p style="text-align:center">' + match.group(1) + '</p>'),
+                  (re.compile(u'<br>\s*(?P<break>([*#•✦=]+\s*)+)\s*<br>'), lambda match: '<p>\n<p style="text-align:center">' + match.group(1) + '</p>'),
 
                   # Remove page links
                   (re.compile(r'<a name=\d+></a>', re.IGNORECASE), lambda match: ''),
diff --git a/src/calibre/ebooks/conversion/utils.py b/src/calibre/ebooks/conversion/utils.py
index 52d1bcc619..9177b5e53b 100644
--- a/src/calibre/ebooks/conversion/utils.py
+++ b/src/calibre/ebooks/conversion/utils.py
@@ -155,9 +155,9 @@ class PreProcessor(object):
 
         chapter_types = [
             [r"[^'\"]?(Introduction|Synopsis|Acknowledgements|Chapter|Kapitel|Epilogue|Volume\s|Prologue|Book\s|Part\s|Dedication|Preface)\s*([\d\w-]+\:?\'?\s*){0,5}", True, "Searching for common Chapter Headings"],
+            [r"([A-Z]\s+){3,}\s*([\d\w-]+\s*){0,3}\s*", True, "Searching for letter spaced headings"],  # Spaced Lettering
             [r"<b[^>]*>\s*(<span[^>]*>)?\s*(?!([*#•]+\s*)+)(\s*(?=[\d.\w#\-*\s]+<)([\d.\w#-*]+\s*){1,5}\s*)(?!\.)(</span>)?\s*</b>", True, "Searching for emphasized lines"], # Emphasized lines
             [r"[^'\"]?(\d+(\.|:)|CHAPTER)\s*([\dA-Z\-\'\"#,]+\s*){0,7}\s*", True, "Searching for numeric chapter headings"],  # Numeric Chapters
-            [r"([A-Z]\s+){3,}\s*([\d\w-]+\s*){0,3}\s*", True, "Searching for letter spaced headings"],  # Spaced Lettering
             [r"[^'\"]?(\d+\.?\s+([\d\w-]+\:?\'?-?\s?){0,5})\s*", True, "Searching for numeric chapters with titles"], # Numeric Titles
             [r"[^'\"]?(\d+|CHAPTER)\s*([\dA-Z\-\'\"\?!#,]+\s*){0,7}\s*", True, "Searching for simple numeric chapter headings"],  # Numeric Chapters, no dot or colon
             [r"\s*[^'\"]?([A-Z#]+(\s|-){0,3}){1,5}\s*", False, "Searching for chapters with Uppercase Characters" ] # Uppercase Chapters
@@ -357,6 +357,6 @@ class PreProcessor(object):
         html = blankreg.sub('\n'+r'\g<openline>'+u'\u00a0'+r'\g<closeline>', html)
 
         # Center separator lines
-        html = re.sub(u'<(?P<outer>p|div)[^>]*>\s*(<(?P<inner1>font|span|[ibu])[^>]*>)?\s*(<(?P<inner2>font|span|[ibu])[^>]*>)?\s*(<(?P<inner3>font|span|[ibu])[^>]*>)?\s*(?P<break>([*#•]+\s*)+)\s*(</(?P=inner3)>)?\s*(</(?P=inner2)>)?\s*(</(?P=inner1)>)?\s*</(?P=outer)>', '<p style="text-align:center">' + '\g<break>' + '</p>', html)
+        html = re.sub(u'<(?P<outer>p|div)[^>]*>\s*(<(?P<inner1>font|span|[ibu])[^>]*>)?\s*(<(?P<inner2>font|span|[ibu])[^>]*>)?\s*(<(?P<inner3>font|span|[ibu])[^>]*>)?\s*(?P<break>([*#•=✦]+\s*)+)\s*(</(?P=inner3)>)?\s*(</(?P=inner2)>)?\s*(</(?P=inner1)>)?\s*</(?P=outer)>', '<p style="text-align:center">' + '\g<break>' + '</p>', html)
 
         return html
diff --git a/src/calibre/ebooks/txt/processor.py b/src/calibre/ebooks/txt/processor.py
index 6a1a106681..ef9920185f 100644
--- a/src/calibre/ebooks/txt/processor.py
+++ b/src/calibre/ebooks/txt/processor.py
@@ -147,7 +147,7 @@ def detect_paragraph_type(txt):
             if .15 <= print_percent <= .75:
                 return 'print'
         elif .15 <= block_percent <= .75:
-            return 'block'     
+            return 'block'
 
         # Assume unformatted text with hardbreaks if nothing else matches        
         return 'unformatted'

From 9832b7118b592679541ab357de02e426e1f48a19 Mon Sep 17 00:00:00 2001
From: ldolse <ldolse@yahoo.com>
Date: Tue, 11 Jan 2011 11:27:25 +0800
Subject: [PATCH 2/2] chapter detection tweaks

---
 src/calibre/ebooks/conversion/utils.py | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/src/calibre/ebooks/conversion/utils.py b/src/calibre/ebooks/conversion/utils.py
index 9177b5e53b..cfa57a28c3 100644
--- a/src/calibre/ebooks/conversion/utils.py
+++ b/src/calibre/ebooks/conversion/utils.py
@@ -151,11 +151,11 @@ class PreProcessor(object):
         n_lookahead_open = "\s+(?!"
         n_lookahead_close = ")"
 
-        default_title = r"(<[ibu][^>]*>)?\s{0,3}([\w\'\"-]+\s{0,3}){1,5}?(</[ibu][^>]*>)?(?=<)"
+        default_title = r"(<[ibu][^>]*>)?\s{0,3}([\w\:\'\"-]+\s{0,3}){1,5}?(</[ibu][^>]*>)?(?=<)"
 
         chapter_types = [
             [r"[^'\"]?(Introduction|Synopsis|Acknowledgements|Chapter|Kapitel|Epilogue|Volume\s|Prologue|Book\s|Part\s|Dedication|Preface)\s*([\d\w-]+\:?\'?\s*){0,5}", True, "Searching for common Chapter Headings"],
-            [r"([A-Z]\s+){3,}\s*([\d\w-]+\s*){0,3}\s*", True, "Searching for letter spaced headings"],  # Spaced Lettering
+            [r"([A-Z-]\s+){3,}\s*([\d\w-]+\s*){0,3}\s*", True, "Searching for letter spaced headings"],  # Spaced Lettering
             [r"<b[^>]*>\s*(<span[^>]*>)?\s*(?!([*#•]+\s*)+)(\s*(?=[\d.\w#\-*\s]+<)([\d.\w#-*]+\s*){1,5}\s*)(?!\.)(</span>)?\s*</b>", True, "Searching for emphasized lines"], # Emphasized lines
             [r"[^'\"]?(\d+(\.|:)|CHAPTER)\s*([\dA-Z\-\'\"#,]+\s*){0,7}\s*", True, "Searching for numeric chapter headings"],  # Numeric Chapters
             [r"[^'\"]?(\d+\.?\s+([\d\w-]+\:?\'?-?\s?){0,5})\s*", True, "Searching for numeric chapters with titles"], # Numeric Titles