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

Sync to ldolse heuristics branch.

Browse Source
This commit is contained in:
John Schember 2011-01-15 13:40:08 -05:00
commit 4d5384df49
2 changed files with 3 additions and 10 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

5
src/calibre/ebooks/conversion/utils.py
View File

@ -236,7 +236,7 @@ class HeuristicProcessor(object):
print unicode(self.chapters_with_title)+" chapters with titles" print unicode(self.chapters_with_title)+" chapters with titles"
else: else:
html = chapdetect.sub(self.chapter_head, html) html = chapdetect.sub(self.chapter_head, html)
return html return html
recurse_patterns(html, True) recurse_patterns(html, True)
html = recurse_patterns(html, False) html = recurse_patterns(html, False)
@ -322,7 +322,8 @@ class HeuristicProcessor(object):
html = re.sub(ur'\s*<o:p>\s*</o:p>', ' ', html) html = re.sub(ur'\s*<o:p>\s*</o:p>', ' ', html)
# Delete microsoft 'smart' tags # Delete microsoft 'smart' tags
html = re.sub('(?i)</?st1:\w+>', '', html) html = re.sub('(?i)</?st1:\w+>', '', html)
# Get rid of empty span, bold, & italics tags # Get rid of empty span, bold, font, & italics tags
html = re.sub(r'\s*<font[^>]*>\s*</font>\s*', '', html)
html = re.sub(r"\s*<span[^>]*>\s*(<span[^>]*>\s*</span>){0,2}\s*</span>\s*", " ", html) html = re.sub(r"\s*<span[^>]*>\s*(<span[^>]*>\s*</span>){0,2}\s*</span>\s*", " ", html)
html = re.sub(r"\s*<[ibu][^>]*>\s*(<[ibu][^>]*>\s*</[ibu]>\s*){0,2}\s*</[ibu]>", " ", html) html = re.sub(r"\s*<[ibu][^>]*>\s*(<[ibu][^>]*>\s*</[ibu]>\s*){0,2}\s*</[ibu]>", " ", html)
html = re.sub(r"\s*<span[^>]*>\s*(<span[^>]>\s*</span>){0,2}\s*</span>\s*", " ", html) html = re.sub(r"\s*<span[^>]*>\s*(<span[^>]>\s*</span>){0,2}\s*</span>\s*", " ", html)

8
src/calibre/ebooks/mobi/input.py
View File

@ -39,11 +39,3 @@ class MOBIInput(InputFormatPlugin):
accelerators['pagebreaks'] = '//h:div[@class="mbp_pagebreak"]' accelerators['pagebreaks'] = '//h:div[@class="mbp_pagebreak"]'
return mr.created_opf_path return mr.created_opf_path
def heuristics(self, options, html):
# search for places where a first or second level heading is immediately followed by another
# top level heading. demote the second heading to h3 to prevent splitting between chapter
# headings and titles, images, etc
doubleheading = re.compile(r'(?P<firsthead><h(1|2)[^>]*>.+?</h(1|2)>\s*(<(?!h\d)[^>]*>\s*)*)<h(1|2)(?P<secondhead>[^>]*>.+?)</h(1|2)>', re.IGNORECASE)
html = doubleheading.sub('\g<firsthead>'+'\n<h3'+'\g<secondhead>'+'</h3>', html)
return html