Cutlery/calibre
1
0
Fork 0
mirror of https://github.com/kovidgoyal/calibre.git synced 2025-08-11 09:13:57 -04:00
Code Issues Packages Projects Releases Wiki Activity

tied rtf input to heuristics, removed option to not include softbreaks, users can combine delete_blank_paragraphs and remove_paragraph_spacing to achieve desired results

Browse Source
This commit is contained in:
ldolse 2011-01-15 10:50:01 +08:00
parent e99ab61dd0
commit 3379337275
1 changed files with 4 additions and 5 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

9
src/calibre/ebooks/rtf/input.py
View File

@ -320,11 +320,10 @@ class RTFInput(InputFormatPlugin):
res = transform.tostring(result)
res = res[:100].replace('xmlns:html', 'xmlns') + res[100:]
# Replace newlines inserted by the 'empty_paragraphs' option in rtf2xml with html blank lines
if not getattr(self.opts, 'remove_paragraph_spacing', False):
res = re.sub('\s*<body>', '<body>', res)
res = re.sub('(?<=\n)\n{2}',
u'<p>\u00a0</p>\n'.encode('utf-8'), res)
if self.opts.preprocess_html:
res = re.sub('\s*<body>', '<body>', res)
res = re.sub('(?<=\n)\n{2}',
u'<p>\u00a0</p>\n'.encode('utf-8'), res)
if self.opts.enable_heuristics:
preprocessor = PreProcessor(self.opts, log=getattr(self, 'log', None))
res = preprocessor(res.decode('utf-8')).encode('utf-8')
f.write(res)