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 bug 2587: Use WayneD solution because it's cleaner.

Browse Source
This commit is contained in:
John Schember 2009-06-15 20:27:17 -04:00
parent fb92bbbf50
commit d5bf14f1d8
1 changed files with 2 additions and 4 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

6
src/calibre/ebooks/conversion/preprocess.py
View File

@ -21,9 +21,7 @@ _span_pat = re.compile('<span.*?</span>', re.DOTALL|re.IGNORECASE)
def sanitize_head(match): def sanitize_head(match):
x = match.group(1) x = match.group(1)
x = _span_pat.sub('', x) x = _span_pat.sub('', x)
x = ('\n%s' % x) if not x.startswith('\n') else x return '<head>\n%s\n</head>' % x
x += '\n' if not x.endswith('\n') else ''
return '<head>%s</head>' % x
def chap_head(match): def chap_head(match):
chap = match.group('chap') chap = match.group('chap')
@ -86,7 +84,7 @@ class HTMLPreProcessor(object):
PREPROCESS = [ PREPROCESS = [
# Some idiotic HTML generators (Frontpage I'm looking at you) # Some idiotic HTML generators (Frontpage I'm looking at you)
# Put all sorts of crap into <head>. This messes up lxml # Put all sorts of crap into <head>. This messes up lxml
(re.compile(r'<head[^>]*>(.*?)</head>', re.IGNORECASE|re.DOTALL), (re.compile(r'<head[^>]*>\n*(.*?)\n*</head>', re.IGNORECASE|re.DOTALL),
sanitize_head), sanitize_head),
# Convert all entities, since lxml doesn't handle them well # Convert all entities, since lxml doesn't handle them well
(re.compile(r'&(\S+?);'), convert_entities), (re.compile(r'&(\S+?);'), convert_entities),