Cutlery/calibre
1
0
Fork 0
mirror of https://github.com/kovidgoyal/calibre.git synced 2025-07-30 21:41:57 -04:00
Code Issues Packages Projects Releases Wiki Activity

work in progress on chapter detection improvements

Browse Source
This commit is contained in:
ldolse 2010-11-16 14:39:53 +08:00
parent ccb683ef09
commit f31a055135
1 changed files with 22 additions and 4 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

26
src/calibre/ebooks/conversion/utils.py
View File

@ -165,6 +165,8 @@ class PreProcessor(object):
title_header_close = ")\s*"
title_line_close = "(</(?P=inner6)>)?\s*(</(?P=inner5)>)?\s*(</(?P=inner4)\s[^>]*>)?\s*</(?P=outer2)>"
opt_title_close = ")?"
n_lookahead_open = "(?!="
n_lookahead_close = ")"
default_title = r"(\s*[\w\'\"-]+){1,5}?(?=<)"
typical_chapters = r".?(Introduction|Synopsis|Acknowledgements|Chapter|Kapitel|Epilogue|Volume\s|Prologue|Book\s|Part\s|Dedication)\s*([\d\w-]+\:?\s*){0,4}"
@ -172,7 +174,11 @@ class PreProcessor(object):
uppercase_chapters = r"\s*.?([A-Z#]+(\s|-){0,3}){1,5}\s*"
numeric_titles = r".?(\d+\.?\s+([\d\w-]+\:?\'?-?\s?){0,5})\s*"
chapter_marker = lookahead+chapter_line_open+chapter_header_open+typical_chapters+chapter_header_close+chapter_line_close+blank_lines+opt_title_open+title_line_open+title_header_open+default_title+title_header_close+title_line_close+opt_title_close
full_chapter_line = chapter_line_open+chapter_header_open+typical_chapters+chapter_header_close+chapter_line_close
n_lookahead = re.sub("(out|inn|cha)", "l", full_chapter_line)
print "n_lookahead is " + n_lookahead
print "Chapter line is " + full_chapter_line + "\n\n"
chapter_marker = lookahead+full_chapter_line+blank_lines+n_lookahead_open+n_lookahead+n_lookahead_close+opt_title_open+title_line_open+title_header_open+default_title+title_header_close+title_line_close+opt_title_close
print chapter_marker
heading = re.compile('<h[1-3][^>]*>', re.IGNORECASE)
self.html_preprocess_sections = len(heading.findall(html))
@ -184,21 +190,33 @@ class PreProcessor(object):
html = chapdetect.sub(self.chapter_head, html)
if self.html_preprocess_sections < 10:
self.log("not enough chapters, only " + unicode(self.html_preprocess_sections) + ", trying numeric chapters")
chapter_marker = lookahead+chapter_line_open+chapter_header_open+numeric_chapters+chapter_header_close+chapter_line_close+blank_lines+opt_title_open+title_line_open+title_header_open+default_title+title_header_close+title_line_close+opt_title_close
full_chapter_line = chapter_line_open+chapter_header_open+numeric_chapters+chapter_header_close+chapter_line_close
n_lookahead = re.sub("(out|inn|cha)", "l", full_chapter_line)
print "n_lookahead is " + n_lookahead
print "Chapter line is " + full_chapter_line + "\n\n"
chapter_marker = lookahead+full_chapter_line+blank_lines+n_lookahead_open+n_lookahead+n_lookahead_close+opt_title_open+title_line_open+title_header_open+default_title+title_header_close+title_line_close+opt_title_close
print chapter_marker
chapdetect2 = re.compile(r'%s' % chapter_marker, re.IGNORECASE)
html = chapdetect2.sub(self.chapter_head, html)
if self.html_preprocess_sections < 10:
self.log("not enough chapters, only " + unicode(self.html_preprocess_sections) + ", trying with uppercase words")
chapter_marker = lookahead+chapter_line_open+chapter_header_open+uppercase_chapters+chapter_header_close+chapter_line_close+blank_lines+opt_title_open+title_line_open+title_header_open+default_title+title_header_close+title_line_close+opt_title_close
full_chapter_line = chapter_line_open+chapter_header_open+uppercase_chapters+chapter_header_close+chapter_line_close
n_lookahead = re.sub("(out|inn|cha)", "l", full_chapter_line)
print "n_lookahead is " + n_lookahead
print "Chapter line is " + full_chapter_line + "\n\n"
chapter_marker = lookahead+full_chapter_line+blank_lines+n_lookahead_open+n_lookahead+n_lookahead_close+opt_title_open+title_line_open+title_header_open+default_title+title_header_close+title_line_close+opt_title_close
print chapter_marker
chapdetect2 = re.compile(r'%s' % chapter_marker, re.UNICODE)
html = chapdetect2.sub(self.chapter_head, html)
if self.html_preprocess_sections < 10:
self.log("not enough chapters, only " + unicode(self.html_preprocess_sections) + ", trying numeric chapters with titles")
chapter_marker = lookahead+chapter_line_open+chapter_header_open+numeric_titles+chapter_header_close+chapter_line_close+blank_lines+opt_title_open+title_line_open+title_header_open+default_title+title_header_close+title_line_close+opt_title_close
full_chapter_line = chapter_line_open+chapter_header_open+numeric_titles+chapter_header_close+chapter_line_close
n_lookahead = re.sub("(out|inn|cha)", "l", full_chapter_line)
print "n_lookahead is " + n_lookahead
print "Chapter line is " + full_chapter_line + "\n\n"
chapter_marker = lookahead+full_chapter_line+blank_lines+n_lookahead_open+n_lookahead+n_lookahead_close+opt_title_open+title_line_open+title_header_open+default_title+title_header_close+title_line_close+opt_title_close
print chapter_marker
chapdetect2 = re.compile(r'%s' % chapter_marker, re.IGNORECASE)
html = chapdetect2.sub(self.chapter_head, html)