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

LRF Output:Improve extraction of text from tags for TOC entries and anchors. Fixes #1613 (Converting MS Lit to Lrf problems)

Browse Source
This commit is contained in:
Kovid Goyal 2009-01-14 00:08:42 -08:00
parent d579de1029
commit ab0c2accef
1 changed files with 5 additions and 5 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

10
src/calibre/ebooks/lrf/html/convert_from.py
View File

@ -580,20 +580,20 @@ class HTMLConverter(object, LoggingInterface):
if (css.has_key('display') and css['display'].lower() == 'none') or \ if (css.has_key('display') and css['display'].lower() == 'none') or \
(css.has_key('visibility') and css['visibility'].lower() == 'hidden'): (css.has_key('visibility') and css['visibility'].lower() == 'hidden'):
return '' return ''
text = u'' text, alt_text = u'', u''
for c in tag.contents: for c in tag.contents:
if limit != None and len(text) > limit: if limit != None and len(text) > limit:
break break
if isinstance(c, HTMLConverter.IGNORED_TAGS): if isinstance(c, HTMLConverter.IGNORED_TAGS):
return u'' continue
if isinstance(c, NavigableString): if isinstance(c, NavigableString):
text += unicode(c) text += unicode(c)
elif isinstance(c, Tag): elif isinstance(c, Tag):
if c.name.lower() == 'img' and c.has_key('alt'): if c.name.lower() == 'img' and c.has_key('alt'):
text += c['alt'] alt_text += c['alt']
return text continue
text += self.get_text(c) text += self.get_text(c)
return text return text if text.strip() else alt_text
def process_links(self): def process_links(self):
def add_toc_entry(text, target): def add_toc_entry(text, target):