Cutlery/calibre
1
0
Fork 0
mirror of https://github.com/kovidgoyal/calibre.git synced 2025-07-09 03:04:10 -04:00
Code Issues Packages Projects Releases Wiki Activity

FB2 output: Sectionize tweaks to match more cases and to bugs where invalid output was being generated.

Browse Source
This commit is contained in:
John Schember 2010-09-04 08:16:23 -04:00
parent 79b1a376ab
commit 46080b27c7
1 changed files with 9 additions and 2 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

11
src/calibre/ebooks/fb2/fb2ml.py
View File

@ -153,8 +153,15 @@ class FB2MLizer(object):
return ''.join(toc)
def sectionize_chapters(self, text):
text = re.sub(r'(?imsu)(?P<anchor><a\s+id="calibre_link-\d+"\s*/>)\s*(?P<strong>(<p>)*\s*<strong>.+?</strong>\s*(</p>)*)', lambda mo: '</section><section>%s<title>%s</title>' % (mo.group('anchor'), mo.group('strong')), text)
text = re.sub(r'(?imsu)<p>\s*(?P<anchor><a\s+id="calibre_link-\d+"\s*/>)\s*</p>\s*(?P<strong>(<p>)*\s*<strong>.+?</strong>\s*(</p>)*)', lambda mo: '</section><section>%s<title>%s</title>' % (mo.group('anchor'), mo.group('strong')), text)
def remove_p(t):
t = t.replace('<p>', '')
t = t.replace('</p>', '')
return t
text = re.sub(r'(?imsu)(<p>)\s*(?P<anchor><a\s+id="calibre_link-\d+"\s*/>)\s*(</p>)\s*(<p>)\s*(?P<strong><strong>.+?</strong>)\s*(</p>)', lambda mo: '</section><section>%s<title><p>%s</p></title>' % (mo.group('anchor'), remove_p(mo.group('strong'))), text)
text = re.sub(r'(?imsu)(<p>)\s*(?P<anchor><a\s+id="calibre_link-\d+"\s*/>)\s*(</p>)\s*(?P<strong><strong>.+?</strong>)', lambda mo: '</section><section>%s<title><p>%s</p></title>' % (mo.group('anchor'), remove_p(mo.group('strong'))), text)
text = re.sub(r'(?imsu)(?P<anchor><a\s+id="calibre_link-\d+"\s*/>)\s*(<p>)\s*(?P<strong><strong>.+?</strong>)\s*(</p>)', lambda mo: '</section><section>%s<title><p>%s</p></title>' % (mo.group('anchor'), remove_p(mo.group('strong'))), text)
text = re.sub(r'(?imsu)(<p>)\s*(?P<anchor><a\s+id="calibre_link-\d+"\s*/>)\s*(?P<strong><strong>.+?</strong>)\s*(</p>)', lambda mo: '</section><section>%s<title><p>%s</p></title>' % (mo.group('anchor'), remove_p(mo.group('strong'))), text)
text = re.sub(r'(?imsu)(?P<anchor><a\s+id="calibre_link-\d+"\s*/>)\s*(?P<strong><strong>.+?</strong>)', lambda mo: '</section><section>%s<title><p>%s</p></title>' % (mo.group('anchor'), remove_p(mo.group('strong'))), text)
return text
def get_text(self):