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

MOBI Input:Fix handling of numeric entities and convert empty <pre> tags to <div> as they cause incorrect rendering in most HTML renderers

Browse Source
This commit is contained in:
Kovid Goyal 2009-02-13 10:27:12 -08:00
parent 49c1818125
commit 2cca07250b
1 changed files with 5 additions and 0 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

5
src/calibre/ebooks/mobi/reader.py
View File

@ -186,6 +186,8 @@ class MobiReader(object):
self.processed_html = self.processed_html.decode(self.book_header.codec, 'ignore') self.processed_html = self.processed_html.decode(self.book_header.codec, 'ignore')
for pat in ENCODING_PATS: for pat in ENCODING_PATS:
self.processed_html = pat.sub('', self.processed_html) self.processed_html = pat.sub('', self.processed_html)
self.processed_html = re.sub(r'&(\S+?);', entity_to_unicode,
self.processed_html)
self.extract_images(processed_records, output_dir) self.extract_images(processed_records, output_dir)
self.replace_page_breaks() self.replace_page_breaks()
self.cleanup_html() self.cleanup_html()
@ -271,6 +273,8 @@ class MobiReader(object):
for key in tag.attrib.keys(): for key in tag.attrib.keys():
tag.attrib.pop(key) tag.attrib.pop(key)
continue continue
if tag.tag == 'pre' and not tag.text:
tag.tag = 'div'
styles, attrib = [], tag.attrib styles, attrib = [], tag.attrib
if attrib.has_key('style'): if attrib.has_key('style'):
style = attrib.pop('style').strip() style = attrib.pop('style').strip()
@ -452,6 +456,7 @@ class MobiReader(object):
pos = end pos = end
self.processed_html += self.mobi_html[pos:] self.processed_html += self.mobi_html[pos:]
def extract_images(self, processed_records, output_dir): def extract_images(self, processed_records, output_dir):
if self.verbose: if self.verbose:
print 'Extracting images...' print 'Extracting images...'