From 59faf929ea97d12cac8f5a7ac75f18bc3b50e164 Mon Sep 17 00:00:00 2001
From: Kovid Goyal <kovid@kovidgoyal.net>
Date: Sat, 6 Oct 2007 02:29:49 +0000
Subject: [PATCH] Initial support for preprocessing BD files

---
 src/libprs500/ebooks/lrf/html/convert_from.py | 13 +++++++++++++
 src/libprs500/gui2/dialogs/lrf_single.py      |  1 +
 2 files changed, 14 insertions(+)

diff --git a/src/libprs500/ebooks/lrf/html/convert_from.py b/src/libprs500/ebooks/lrf/html/convert_from.py
index 6e41b78285..b2fe675cbd 100644
--- a/src/libprs500/ebooks/lrf/html/convert_from.py
+++ b/src/libprs500/ebooks/lrf/html/convert_from.py
@@ -93,6 +93,19 @@ class HTMLConverter(object):
                   
                   ]
     
+    # Fix Book Designer markup
+    BOOK_DESIGNER = [
+                     # Create header tags
+                     (re.compile('<h2.*?id=BookTitle.*?>(.*?)</span>', re.IGNORECASE|re.DOTALL),
+                      lambda match : '<h1 align="center">%s</h1>'%(match.group(1),)),
+                     (re.compile('<h2.*?id=BookAuthor.*?>(.*?)</span>', re.IGNORECASE|re.DOTALL),
+                      lambda match : '<h2 align="right">%s</h2>'%(match.group(1),)),
+                     (re.compile('<span.*?id=title.*?>(.*?)</span>', re.IGNORECASE|re.DOTALL),
+                      lambda match : '<h2>%s</h2>'%(match.group(1),)),
+                     (re.compile('<span.*?id=subtitle.*?>(.*?)</span>', re.IGNORECASE|re.DOTALL),
+                      lambda match : '<h3>%s</h3>'%(match.group(1),)), 
+                     ]
+    
     def __hasattr__(self, attr):
         if hasattr(self.options, attr):
             return True
diff --git a/src/libprs500/gui2/dialogs/lrf_single.py b/src/libprs500/gui2/dialogs/lrf_single.py
index 40d9f468fc..df71096618 100644
--- a/src/libprs500/gui2/dialogs/lrf_single.py
+++ b/src/libprs500/gui2/dialogs/lrf_single.py
@@ -207,6 +207,7 @@ class LRFSingleDialog(QDialog, Ui_LRFSingleDialog):
         ph = 'Preprocess the file before converting to LRF. This is useful if you know that the file is from a specific source. Known sources:'
         ph += '<ol><li><b>baen</b> - Books from BAEN Publishers</li>'
         ph += '<li><b>pdftohtml</b> - HTML files that are the output of the program pdftohtml</li>'
+        ph += '<li><b>book-designer</b> - HTML0 files from Book Designer</li>'
         self.preprocess.setToolTip(ph)
         self.preprocess.setWhatsThis(ph)
         for profile in self.PARSER.get_option('--profile').choices: