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

initial scene break detection

Browse Source
This commit is contained in:
ldolse 2011-01-29 21:15:44 +08:00
parent 5c988788a0
commit bace283325
1 changed files with 26 additions and 14 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

40
src/calibre/ebooks/conversion/utils.py
View File

@ -24,9 +24,10 @@ class HeuristicProcessor(object):
self.chapters_no_title = 0 self.chapters_no_title = 0
self.chapters_with_title = 0 self.chapters_with_title = 0
self.blanks_deleted = False self.blanks_deleted = False
self.blanks_between_paragraphs = False
self.linereg = re.compile('(?<=<p).*?(?=</p>)', re.IGNORECASE|re.DOTALL) self.linereg = re.compile('(?<=<p).*?(?=</p>)', re.IGNORECASE|re.DOTALL)
self.blankreg = re.compile(r'\s*(?P<openline><p(?!\sclass=\"softbreak\")[^>]*>)\s*(?P<closeline></p>)', re.IGNORECASE) self.blankreg = re.compile(r'\s*(?P<openline><p(?!\sclass=\"(softbreak|spacer)\")[^>]*>)\s*(?P<closeline></p>)', re.IGNORECASE)
self.softbreak = re.compile(r'\s*(?P<openline><p(?=\sclass=\"softbreak\")[^>]*>)\s*(?P<closeline></p>)', re.IGNORECASE) self.anyblank = re.compile(r'\s*(?P<openline><p[^>]*>)\s*(?P<closeline></p>)', re.IGNORECASE)
self.multi_blank = re.compile(r'(\s*<p[^>]*>\s*</p>){2,}(?!\s*<h\d)', re.IGNORECASE) self.multi_blank = re.compile(r'(\s*<p[^>]*>\s*</p>){2,}(?!\s*<h\d)', re.IGNORECASE)
def is_pdftohtml(self, src): def is_pdftohtml(self, src):
@ -419,12 +420,28 @@ class HeuristicProcessor(object):
return False return False
def detect_blank_formatting(self, html): def detect_blank_formatting(self, html):
blanks_before_headings = re.compile(r'(\s*<p[^>]*>\s*</p>){2,}(?=\s*<h\d)', re.IGNORECASE) blanks_before_headings = re.compile(r'(\s*<p[^>]*>\s*</p>){1,}(?=\s*<h\d)', re.IGNORECASE)
blanks_after_headings = re.compile(r'(?<=</h\d>)(\s*<p[^>]*>\s*</p>){1,}', re.IGNORECASE)
def markup_spacers(match):
blanks = match.group(0)
blanks = self.blankreg.sub('\n<p class="spacer"> </p>', blanks)
return blanks
html = blanks_before_headings.sub(markup_spacers, html)
html = blanks_after_headings.sub(markup_spacers, html)
if self.html_preprocess_sections > self.min_chapters:
html = re.sub('(?si)^.*?(?=<h\d)', markup_spacers, html)
return html return html
def detect_soft_breaks(self, html): def detect_soft_breaks(self, html):
if not self.blanks_deleted and self.blanks_between_paragraphs:
html = self.multi_blank.sub('\n<p class="softbreak" style="margin-top:1.25em; margin-bottom:1.25em; page-break-before:avoid"> </p>', html)
else:
html = self.blankreg.sub('\n<p class="softbreak" style="margin-top:1.25em; margin-bottom:1.25em; page-break-before:avoid"> </p>', html)
return html return html
def __call__(self, html): def __call__(self, html):
self.log.debug("********* Heuristic processing HTML *********") self.log.debug("********* Heuristic processing HTML *********")
@ -465,25 +482,23 @@ class HeuristicProcessor(object):
#html = re.sub('<br[^>]*>', u'<p>\u00a0</p>', html) #html = re.sub('<br[^>]*>', u'<p>\u00a0</p>', html)
# Determine whether the document uses interleaved blank lines # Determine whether the document uses interleaved blank lines
blanks_between_paragraphs = self.analyze_blanks(html) self.blanks_between_paragraphs = self.analyze_blanks(html)
#self.dump(html, 'before_chapter_markup') #self.dump(html, 'before_chapter_markup')
# detect chapters/sections to match xpath or splitting logic # detect chapters/sections to match xpath or splitting logic
if getattr(self.extra_opts, 'markup_chapter_headings', False): if getattr(self.extra_opts, 'markup_chapter_headings', False):
html = self.markup_chapters(html, self.totalwords, blanks_between_paragraphs) html = self.markup_chapters(html, self.totalwords, self.blanks_between_paragraphs)
self.dump(html, 'after_chapter_markup')
if getattr(self.extra_opts, 'italicize_common_cases', False): if getattr(self.extra_opts, 'italicize_common_cases', False):
html = self.markup_italicis(html) html = self.markup_italicis(html)
# If more than 40% of the lines are empty paragraphs and the user has enabled delete # If more than 40% of the lines are empty paragraphs and the user has enabled delete
# blank paragraphs then delete blank lines to clean up spacing # blank paragraphs then delete blank lines to clean up spacing
if blanks_between_paragraphs and getattr(self.extra_opts, 'delete_blank_paragraphs', False): if self.blanks_between_paragraphs and getattr(self.extra_opts, 'delete_blank_paragraphs', False):
self.log.debug("deleting blank lines") self.log.debug("deleting blank lines")
self.blanks_deleted = True self.blanks_deleted = True
html = self.multi_blank.sub('\n<p class="softbreak" style="margin-top:1.5em; margin-bottom:1.5em"> </p>', html) html = self.multi_blank.sub('\n<p class="softbreak" style="margin-top:1.25em; margin-bottom:1.25em; page-break-before:avoid"> </p>', html)
html = self.blankreg.sub('', html) html = self.blankreg.sub('', html)
# Determine line ending type # Determine line ending type
@ -538,13 +553,10 @@ class HeuristicProcessor(object):
html = self.detect_blank_formatting(html) html = self.detect_blank_formatting(html)
html = self.detect_soft_breaks(html) html = self.detect_soft_breaks(html)
# 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; page-break-before:avoid">' + '\g<break>' + '</p>', html)
if not self.blanks_deleted:
html = self.multi_blank.sub('\n<p class="softbreak" style="margin-top:1.5em; margin-bottom:1.5em"> </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 to preserve original formatting # put back non-breaking spaces in empty paragraphs to preserve original formatting
html = self.blankreg.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)
html = self.softbreak.sub('\n'+r'\g<openline>'+u'\u00a0'+r'\g<closeline>', html)
return html return html