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

added option for renumbering heading tags

Browse Source
This commit is contained in:
ldolse 2011-01-15 22:07:20 +08:00
parent 1301fe69d1
commit 946f1cf6c0
3 changed files with 16 additions and 9 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

2
src/calibre/ebooks/conversion/cli.py
View File

@ -137,7 +137,7 @@ def add_pipeline_options(parser, plumber):
'italicize_common_cases', 'fix_indents', 'italicize_common_cases', 'fix_indents',
'html_unwrap_factor', 'unwrap_lines', 'html_unwrap_factor', 'unwrap_lines',
'delete_blank_paragraphs', 'format_scene_breaks', 'delete_blank_paragraphs', 'format_scene_breaks',
'dehyphenate', 'dehyphenate', 'renumber_headings',
] ]
), ),

6
src/calibre/ebooks/conversion/plumber.py
View File

@ -533,6 +533,12 @@ OptionRecommendation(name='dehyphenate',
'document itself is used as a dictionary to determine whether hyphens ' 'document itself is used as a dictionary to determine whether hyphens '
'should be retained or removed.')), 'should be retained or removed.')),
OptionRecommendation(name='renumber_headings',
recommended_value=False, level=OptionRecommendation.LOW,
help=_('Looks for occurences of sequential <h1> or <h2> tags. '
'The tags are renumbered to prevent splitting in the middle '
'of chapter headings.')),
OptionRecommendation(name='sr1_search', OptionRecommendation(name='sr1_search',
recommended_value='', level=OptionRecommendation.LOW, recommended_value='', level=OptionRecommendation.LOW,
help=_('Search pattern (regular expression) to be replaced with ' help=_('Search pattern (regular expression) to be replaced with '

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

@ -416,7 +416,7 @@ class PreProcessor(object):
dehyphenator = Dehyphenator() dehyphenator = Dehyphenator()
html = dehyphenator(html,'html_cleanup', length) html = dehyphenator(html,'html_cleanup', length)
if getattr(self.extra_opts, 'dehyphenate', True): if getattr(self.extra_opts, 'dehyphenate', False):
# dehyphenate in cleanup mode to fix anything previous conversions/editing missed # dehyphenate in cleanup mode to fix anything previous conversions/editing missed
self.log("Fixing hyphenated content") self.log("Fixing hyphenated content")
dehyphenator = Dehyphenator() dehyphenator = Dehyphenator()
@ -429,13 +429,14 @@ class PreProcessor(object):
chapdetect3 = re.compile(r'<(?P<styles>(p|div)[^>]*)>\s*(?P<section>(<span[^>]*>)?\s*(?!([*#•]+\s*)+)(<[ibu][^>]*>){0,2}\s*(<span[^>]*>)?\s*(<[ibu][^>]*>){0,2}\s*(<span[^>]*>)?\s*.?(?=[a-z#\-*\s]+<)([a-z#-*]+\s*){1,5}\s*\s*(</span>)?(</[ibu]>){0,2}\s*(</span>)?\s*(</[ibu]>){0,2}\s*(</span>)?\s*</(p|div)>)', re.IGNORECASE) chapdetect3 = re.compile(r'<(?P<styles>(p|div)[^>]*)>\s*(?P<section>(<span[^>]*>)?\s*(?!([*#•]+\s*)+)(<[ibu][^>]*>){0,2}\s*(<span[^>]*>)?\s*(<[ibu][^>]*>){0,2}\s*(<span[^>]*>)?\s*.?(?=[a-z#\-*\s]+<)([a-z#-*]+\s*){1,5}\s*\s*(</span>)?(</[ibu]>){0,2}\s*(</span>)?\s*(</[ibu]>){0,2}\s*(</span>)?\s*</(p|div)>)', re.IGNORECASE)
html = chapdetect3.sub(self.chapter_break, html) html = chapdetect3.sub(self.chapter_break, html)
if getattr(self.extra_opts, 'renumber_headings', True):
# search for places where a first or second level heading is immediately followed by another # 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 # top level heading. demote the second heading to h3 to prevent splitting between chapter
# headings and titles, images, etc # 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) 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) html = doubleheading.sub('\g<firsthead>'+'\n<h3'+'\g<secondhead>'+'</h3>', html)
if getattr(self.extra_opts, 'format_scene_breaks', True): if getattr(self.extra_opts, 'format_scene_breaks', False):
# Center separator lines # Center separator lines
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:1.25em; margin-bottom:1.25em">' + '\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*(?P<break>([*#•]+\s*)+)\s*(</(?P=inner3)>)?\s*(</(?P=inner2)>)?\s*(</(?P=inner1)>)?\s*</(?P=outer)>', '<p style="text-align:center; margin-top:1.25em; margin-bottom:1.25em">' + '\g<break>' + '</p>', html)