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

Revert previous changes, now looking for entities in unwrapping rule

Browse Source
This commit is contained in:
ldolse 2010-09-16 16:44:28 +08:00
parent 66b443adc5
commit 569b84e1cb
1 changed files with 3 additions and 1 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

4
src/calibre/ebooks/conversion/preprocess.py
View File

@ -17,6 +17,8 @@ convert_entities = functools.partial(entity_to_unicode,
result_exceptions = { result_exceptions = {
u'<' : '&lt;', u'<' : '&lt;',
u'>' : '&gt;', u'>' : '&gt;',
u"'" : '&apos;',
u'"' : '&quot;',
u'&' : '&amp;', u'&' : '&amp;',
}) })
_span_pat = re.compile('<span.*?</span>', re.DOTALL|re.IGNORECASE) _span_pat = re.compile('<span.*?</span>', re.DOTALL|re.IGNORECASE)
@ -349,7 +351,7 @@ class HTMLPreProcessor(object):
# print "The pdf line length returned is " + str(length) # print "The pdf line length returned is " + str(length)
end_rules.append( end_rules.append(
# Un wrap using punctuation # Un wrap using punctuation
(re.compile(r'(?<=.{%i}[a-z,;:)\-IA])\s*(?P<ital></(i|b|u)>)?\s*(<p.*?>\s*)+\s*(?=(<(i|b|u)>)?\s*[\w\d$(])' % length, re.UNICODE), wrap_lines), (re.compile(r'(?<=.{%i}([a-z,:)\-IA]|(?<!\&\w{4});))\s*(?P<ital></(i|b|u)>)?\s*(<p.*?>\s*)+\s*(?=(<(i|b|u)>)?\s*[\w\d$(])' % length, re.UNICODE), wrap_lines),
) )
for rule in self.PREPROCESS + start_rules: for rule in self.PREPROCESS + start_rules: