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 #545

Browse Source
This commit is contained in:
Kovid Goyal 2008-03-06 21:54:06 +00:00
parent 70b2d0bec7
commit 190466ed59
1 changed files with 7 additions and 2 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

9
src/libprs500/ebooks/lrf/html/convert_from.py
View File

@ -79,6 +79,11 @@ def strip_style_comments(match):
src = src[:lindex] + src[rindex+2:] src = src[:lindex] + src[rindex+2:]
return src return src
def tag_regex(tagname):
'''Return non-grouping regular expressions that match the opening and closing tags for tagname'''
return dict(open=r'(?:<\s*%(t)s\s+[^<>]*?>|<\s*%(t)s\s*>)'%dict(t=tagname), \
close=r'</\s*%(t)s\s*>'%dict(t=tagname))
class HTMLConverter(object): class HTMLConverter(object):
SELECTOR_PAT = re.compile(r"([A-Za-z0-9\-\_\:\.]+[A-Za-z0-9\-\_\:\.\s\,]*)\s*\{([^\}]*)\}") SELECTOR_PAT = re.compile(r"([A-Za-z0-9\-\_\:\.]+[A-Za-z0-9\-\_\:\.\s\,]*)\s*\{([^\}]*)\}")
PAGE_BREAK_PAT = re.compile(r'page-break-(?:after|before)\s*:\s*(\w+)', re.IGNORECASE) PAGE_BREAK_PAT = re.compile(r'page-break-(?:after|before)\s*:\s*(\w+)', re.IGNORECASE)
@ -94,8 +99,8 @@ class HTMLConverter(object):
(re.compile(r"<\s*style.*?>(.*?)<\/\s*style\s*>", re.DOTALL|re.IGNORECASE), (re.compile(r"<\s*style.*?>(.*?)<\/\s*style\s*>", re.DOTALL|re.IGNORECASE),
lambda match: match.group().replace('<!--', '').replace('-->', '')), lambda match: match.group().replace('<!--', '').replace('-->', '')),
# remove <p> tags from within <a> tags # remove <p> tags from within <a> tags
(re.compile(r'<a.*?>(.*?)</a\s*>', re.DOTALL|re.IGNORECASE), (re.compile(r'%(open)s(.*?)%(close)s'%tag_regex('a'), re.DOTALL|re.IGNORECASE),
lambda match: re.compile(r'<\s*?p.*?>', re.IGNORECASE).sub('', match.group())), lambda match: re.compile(r'%(open)s|%(close)s'%tag_regex('p'), re.IGNORECASE).sub('', match.group())),
# Replace common line break patterns with line breaks # Replace common line break patterns with line breaks
(re.compile(r'<p>(&nbsp;|\s)*</p>', re.IGNORECASE), lambda m: '<br />'), (re.compile(r'<p>(&nbsp;|\s)*</p>', re.IGNORECASE), lambda m: '<br />'),