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 unicode bug and make get_text a little more memory efficient

Browse Source
This commit is contained in:
Kovid Goyal 2007-06-29 06:38:52 +00:00
parent a569112e43
commit 3cf2b17af5
1 changed files with 7 additions and 5 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

12
src/libprs500/ebooks/lrf/html/convert_from.py
View File

@ -483,17 +483,19 @@ class HTMLConverter(object):
raise ConversionError, 'Could not parse ' + self.file_name raise ConversionError, 'Could not parse ' + self.file_name
def get_text(self, tag): def get_text(self, tag, limit=None):
css = self.tag_css(tag) css = self.tag_css(tag)
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 = '' text = u''
for c in tag.contents: for c in tag.contents:
if limit != None and len(text) > limit:
break
if isinstance(c, HTMLConverter.IGNORED_TAGS): if isinstance(c, HTMLConverter.IGNORED_TAGS):
return '' return u''
if isinstance(c, NavigableString): if isinstance(c, NavigableString):
text += str(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'] text += c['alt']
@ -1046,7 +1048,7 @@ class HTMLConverter(object):
self.current_block = self.book.create_text_block(textStyle=pb.textStyle, self.current_block = self.book.create_text_block(textStyle=pb.textStyle,
blockStyle=pb.blockStyle) blockStyle=pb.blockStyle)
elif tagname in ['p', 'div', 'h1', 'h2', 'h3', 'h4', 'h5', 'h6']: elif tagname in ['p', 'div', 'h1', 'h2', 'h3', 'h4', 'h5', 'h6']:
src = self.get_text(tag) src = self.get_text(tag, limit=1000)
if self.chapter_detection and tagname.startswith('h'): if self.chapter_detection and tagname.startswith('h'):
if self.chapter_regex.search(src): if self.chapter_regex.search(src):
if self.verbose: if self.verbose: