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

Fix #252

Browse Source
This commit is contained in:
Kovid Goyal 2007-10-20 23:22:08 +00:00
parent bddab5cd0d
commit 02518b3582
1 changed files with 16 additions and 3 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

19
src/libprs500/ebooks/lrf/html/convert_from.py
View File

@ -138,9 +138,9 @@ class HTMLConverter(object):
(re.compile('<h2[^><]*?id=BookAuthor[^><]*?(align=)*(?(1)(\w+))*[^><]*?>[^><]*?</h2>', re.IGNORECASE),
lambda match : '<h2 id="BookAuthor" align="%s">%s</h2>'%(match.group(2) if match.group(2) else 'center', match.group(3))),
(re.compile('<span[^><]*?id=title[^><]*?>(.*?)</span>', re.IGNORECASE|re.DOTALL),
lambda match : '<h2>%s</h2>'%(match.group(1),)),
lambda match : '<h2 class="title">%s</h2>'%(match.group(1),)),
(re.compile('<span[^><]*?id=subtitle[^><]*?>(.*?)</span>', re.IGNORECASE|re.DOTALL),
lambda match : '<h3>%s</h3>'%(match.group(1),)),
lambda match : '<h3 class="subtitle">%s</h3>'%(match.group(1),)),
# Blank lines
(re.compile('<div[^><]*?>(&nbsp;){4}</div>', re.IGNORECASE),
lambda match : '<p></p>'),
@ -206,6 +206,8 @@ class HTMLConverter(object):
self.targets = {} #: <a name=...> and id elements
self.links = deque() #: <a href=...> elements
self.processed_files = []
self.extra_toc_entries = [] #: TOC entries gleaned from semantic information
self.id_counter = 0
self.unused_target_blocks = [] #: Used to remove extra TextBlocks
self.link_level = 0 #: Current link level
self.memory = [] #: Used to ensure that duplicate CSS unhandled erros are not reported
@ -266,6 +268,10 @@ class HTMLConverter(object):
self.link_level += 1
paths = [link['path'] for link in self.links]
for text, tb in self.extra_toc_entries:
ascii_text = text.encode('ascii', 'ignore')
self.book.addTocEntry(ascii_text, tb)
def is_baen(self, soup):
return bool(soup.find('meta', attrs={'name':'Publisher',
'content':re.compile('Baen', re.IGNORECASE)}))
@ -1441,12 +1447,19 @@ class HTMLConverter(object):
elif tagname in ['p', 'div', 'h1', 'h2', 'h3', 'h4', 'h5', 'h6']:
new_block = self.process_block(tag, tag_css)
if self.anchor_ids and tag.has_key('id'):
if (self.anchor_ids and tag.has_key('id')) or \
(self.book_designer and tag.has_key('class') and tag['class']=='title'):
if not tag.has_key('id'):
tag['id'] = 'libprs500_id_'+str(self.id_counter)
self.id_counter += 1
tkey = self.target_prefix+tag['id']
if not new_block:
self.end_current_block()
self.current_block.must_append = True
self.targets[tkey] = self.current_block
if (self.book_designer and tag.has_key('class') and tag['class']=='title'):
self.extra_toc_entries.append((self.get_text(tag, 100), self.current_block))
src = self.get_text(tag, limit=1000)