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

started scene break detection in heuristics, improved text conversion of Sigil compatible chapter titles

Browse Source
This commit is contained in:
ldolse 2011-01-29 19:06:02 +08:00
parent bacfc28d3a
commit 5c988788a0
1 changed files with 15 additions and 3 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

18
src/calibre/ebooks/conversion/utils.py
View File

@ -27,7 +27,7 @@ class HeuristicProcessor(object):
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\")[^>]*>)\s*(?P<closeline></p>)', re.IGNORECASE)
self.softbreak = re.compile(r'\s*(?P<openline><p(?=\sclass=\"softbreak\")[^>]*>)\s*(?P<closeline></p>)', re.IGNORECASE) self.softbreak = re.compile(r'\s*(?P<openline><p(?=\sclass=\"softbreak\")[^>]*>)\s*(?P<closeline></p>)', re.IGNORECASE)
self.multi_blank = re.compile(r'(\s*<p[^>]*>\s*</p>){2,}', 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):
return '<!-- created by calibre\'s pdftohtml -->' in src[:1000] return '<!-- created by calibre\'s pdftohtml -->' in src[:1000]
@ -42,8 +42,10 @@ class HeuristicProcessor(object):
" chapters. - " + unicode(chap)) " chapters. - " + unicode(chap))
return '<h2>'+chap+'</h2>\n' return '<h2>'+chap+'</h2>\n'
else: else:
txt_chap = html2text(chap) delete_whitespace = re.compile('^\s*(?P<c>.*?)\s*$')
txt_title = html2text(title) delete_quotes = re.compile('\'\"')
txt_chap = delete_quotes.sub('', delete_whitespace.sub('\g<c>', html2text(chap)))
txt_title = delete_quotes.sub('', delete_whitespace.sub('\g<c>', html2text(title)))
self.html_preprocess_sections = self.html_preprocess_sections + 1 self.html_preprocess_sections = self.html_preprocess_sections + 1
self.log.debug("marked " + unicode(self.html_preprocess_sections) + self.log.debug("marked " + unicode(self.html_preprocess_sections) +
" chapters & titles. - " + unicode(chap) + ", " + unicode(title)) " chapters & titles. - " + unicode(chap) + ", " + unicode(title))
@ -416,6 +418,12 @@ class HeuristicProcessor(object):
return True return True
return False return False
def detect_blank_formatting(self, html):
blanks_before_headings = re.compile(r'(\s*<p[^>]*>\s*</p>){2,}(?=\s*<h\d)', re.IGNORECASE)
return html
def detect_soft_breaks(self, html):
return html
def __call__(self, html): def __call__(self, html):
self.log.debug("********* Heuristic processing HTML *********") self.log.debug("********* Heuristic processing HTML *********")
@ -465,6 +473,8 @@ class HeuristicProcessor(object):
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, 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)
@ -525,6 +535,8 @@ class HeuristicProcessor(object):
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', False): if getattr(self.extra_opts, 'format_scene_breaks', False):
html = self.detect_blank_formatting(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">' + '\g<break>' + '</p>', html)
if not self.blanks_deleted: if not self.blanks_deleted: