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 10:05:36 -05:00
commit afb72b8a59
3 changed files with 16 additions and 7 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',
'html_unwrap_factor', 'unwrap_lines',
'delete_blank_paragraphs', 'format_scene_breaks',
'dehyphenate',
'dehyphenate', 'renumber_headings',
]
),

8
src/calibre/ebooks/conversion/plumber.py
View File

@ -532,7 +532,13 @@ OptionRecommendation(name='dehyphenate',
help=_('Analyses hyphenated words throughout the document. The '
'document itself is used as a dictionary to determine whether hyphens '
'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',
recommended_value='', level=OptionRecommendation.LOW,
help=_('Search pattern (regular expression) to be replaced with '

13
src/calibre/ebooks/conversion/utils.py
View File

@ -272,9 +272,11 @@ class PreProcessor(object):
unwrap = re.compile(u"%s" % unwrap_regex, re.UNICODE)
em_en_unwrap = re.compile(u"%s" % em_en_unwrap_regex, re.UNICODE)
shy_unwrap = re.compile(u"%s" % shy_unwrap_regex, re.UNICODE)
content = unwrap.sub(' ', content)
content = em_en_unwrap.sub('', content)
content = shy_unwrap.sub('', content)
return content
def txt_process(self, match):
@ -461,11 +463,12 @@ 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)
html = chapdetect3.sub(self.chapter_break, 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)
if getattr(self.extra_opts, 'renumber_headings', False):
# 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)
if getattr(self.extra_opts, 'format_scene_breaks', False):
# Center separator lines