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

Strip comments from within style tags

Browse Source
This commit is contained in:
Kovid Goyal 2007-05-18 15:56:36 +00:00
parent aeb69e9139
commit 44a50922cd
1 changed files with 12 additions and 3 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

15
src/libprs500/ebooks/lrf/html/convert_from.py
View File

@ -218,7 +218,10 @@ class HTMLConverter(object):
IGNORED_TAGS = (Comment, Declaration, ProcessingInstruction) IGNORED_TAGS = (Comment, Declaration, ProcessingInstruction)
# Fix <a /> elements # Fix <a /> elements
MARKUP_MASSAGE = [(re.compile("(<\s*[aA]\s+.*\/)\s*>"), MARKUP_MASSAGE = [(re.compile("(<\s*[aA]\s+.*\/)\s*>"),
lambda match: match.group(1)+"></a>")] lambda match: match.group(1)+"></a>"),
(re.compile(r"<\s*style.*?>.*?(<\!--).*?<.\s*style\s*>", re.DOTALL|re.IGNORECASE),
lambda match: match.group().replace('<!--', '').replace('-->', '')),
]
# Fix Baen markup # Fix Baen markup
BAEN_SANCTIFY = [(re.compile(r'<\s*[Aa]\s+id="p[0-9]+"\s+name="p[0-9]+"\s*>\s*<\/[Aa]>'), BAEN_SANCTIFY = [(re.compile(r'<\s*[Aa]\s+id="p[0-9]+"\s+name="p[0-9]+"\s*>\s*<\/[Aa]>'),
lambda match: ''), lambda match: ''),
@ -428,6 +431,7 @@ class HTMLConverter(object):
self.top = self.current_block self.top = self.current_block
self.process_children(self.soup, {}) self.process_children(self.soup, {})
if self.current_para and self.current_block: if self.current_para and self.current_block:
self.current_para.append_to(self.current_block) self.current_para.append_to(self.current_block)
if self.current_block and self.current_page: if self.current_block and self.current_page:
@ -437,7 +441,10 @@ class HTMLConverter(object):
if not self.top.parent: if not self.top.parent:
if not previous: if not previous:
self.top = get_valid_block(self.book.pages()[0]) try:
previous = get_valid_block(self.book.pages()[0])
except IndexError:
previous = self.current_page
else: else:
found = False found = False
for page in self.book.pages(): for page in self.book.pages():
@ -450,6 +457,8 @@ class HTMLConverter(object):
continue continue
break break
if not self.top.parent: if not self.top.parent:
self.top = get_valid_block(self.current_page)
if not self.top or not self.top.parent:
raise ConversionError, 'Could not parse ' + self.file_name raise ConversionError, 'Could not parse ' + self.file_name
@ -691,7 +700,7 @@ class HTMLConverter(object):
'padding' in test or 'border' in test or 'page-break' in test \ 'padding' in test or 'border' in test or 'page-break' in test \
or test.startswith('mso') or test.startswith('background')\ or test.startswith('mso') or test.startswith('background')\
or test.startswith('line') or test in ['color', 'display', \ or test.startswith('line') or test in ['color', 'display', \
'letter-spacing', 'font-variant']: 'letter-spacing', 'font-variant', 'position']:
css.pop(key) css.pop(key)
return css return css