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

scene break detection to detect any repeating non-word character

Browse Source
This commit is contained in:
ldolse 2011-01-31 09:39:28 +08:00
parent e8153d5e69
commit 31c277880e
1 changed files with 2 additions and 2 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

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

@ -580,10 +580,10 @@ class HeuristicProcessor(object):
if blanks_count >= 1: if blanks_count >= 1:
html = self.merge_blanks(html, blanks_count) html = self.merge_blanks(html, blanks_count)
# Center separator lines, use a bit larger margin in this case # Center separator lines, use a bit larger margin in this case
html = re.sub(u'<(?P<outer>p|div)[^>]*>\s*(<(?P<inner1>font|span|[ibu])[^>]*>)?\s*(<(?P<inner2>font|span|[ibu])[^>]*>)?\s*(<(?P<inner3>font|span|[ibu])[^>]*>)?\s*(?P<break>([*#•=✦]+\s*)+)\s*(</(?P=inner3)>)?\s*(</(?P=inner2)>)?\s*(</(?P=inner1)>)?\s*</(?P=outer)>', '<p style="text-align:center; margin-top:.65em; margin-bottom:.65em; page-break-before:avoid">' + '\g<break>' + '</p>', html) html = re.sub(u'<(?P<outer>p|div)[^>]*>\s*(<(?P<inner1>font|span|[ibu])[^>]*>)?\s*(<(?P<inner2>font|span|[ibu])[^>]*>)?\s*(<(?P<inner3>font|span|[ibu])[^>]*>)?\s*(?![\w\'\"])(?P<break>((?P<breakchar>(?!\s)\W)\s*(?P=breakchar)?)+)\s*(</(?P=inner3)>)?\s*(</(?P=inner2)>)?\s*(</(?P=inner1)>)?\s*</(?P=outer)>', '<p style="text-align:center; margin-top:.65em; margin-bottom:.65em; page-break-before:avoid">' + '\g<break>' + '</p>', html)
#html = re.sub('<p\s+class="softbreak"[^>]*>\s*</p>', '<div id="softbreak" style="margin-left: 45%; margin-right: 45%; margin-top:1.5em; margin-bottom:1.5em"><hr style="height: 3px; background:#505050" /></div>', html) #html = re.sub('<p\s+class="softbreak"[^>]*>\s*</p>', '<div id="softbreak" style="margin-left: 45%; margin-right: 45%; margin-top:1.5em; margin-bottom:1.5em"><hr style="height: 3px; background:#505050" /></div>', html)
if self.deleted_nbsps: if self.deleted_nbsps:
# put back non-breaking spaces in empty paragraphs so they render correctly # put back non-breaking spaces in empty paragraphs so they render correctly
html = self.anyblank.sub('\n'+r'\g<openline>'+u'\u00a0'+r'\g<closeline>', html) html = self.anyblank.sub('\n'+r'\g<openline>'+u'\u00a0'+r'\g<closeline>', html)
return html return html