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

small tweak

Browse Source
This commit is contained in:
ldolse 2010-10-04 16:16:33 +08:00
parent cc29d2efe8
commit 4a044b8e9d
2 changed files with 7 additions and 5 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

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

@ -146,7 +146,7 @@ class PreProcessor(object):
#print "blanks between paragraphs is marked True" #print "blanks between paragraphs is marked True"
else: else:
blanks_between_paragraphs = False blanks_between_paragraphs = False
#self.log("\n\n\n\n\n\n\n\n\n\n\n"+html+"\n\n\n\n\n\n\n\n\n\n\n\n\n") self.log("\n\n\n\n\n\n\n\n\n\n\n"+html+"\n\n\n\n\n\n\n\n\n\n\n\n\n")
# detect chapters/sections to match xpath or splitting logic # detect chapters/sections to match xpath or splitting logic
# #
# Build the Regular Expressions in pieces # Build the Regular Expressions in pieces
@ -166,13 +166,13 @@ class PreProcessor(object):
title_line_close = "(</(?P=inner6)>)?\s*(</(?P=inner5)>)?\s*(</(?P=inner4)\s[^>]*>)?\s*</(?P=outer2)>" title_line_close = "(</(?P=inner6)>)?\s*(</(?P=inner5)>)?\s*(</(?P=inner4)\s[^>]*>)?\s*</(?P=outer2)>"
opt_title_close = ")?" opt_title_close = ")?"
default_title = r"(\s*[\w\'\"-]+){1,5}(?!<)" 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}" typical_chapters = r".?(Introduction|Synopsis|Acknowledgements|Chapter|Kapitel|Epilogue|Volume\s|Prologue|Book\s|Part\s|Dedication)\s*([\d\w-]+\:?\s*){0,4}"
numeric_chapters = r".?(\d+\.?|(CHAPTER\s*([\dA-Z\-\'\"\?\.!#,]+\s*){1,10}))\s*" numeric_chapters = r".?(\d+\.?|(CHAPTER\s*([\dA-Z\-\'\"\?\.!#,]+\s*){1,10}))\s*"
uppercase_chapters = r"\s*.?([A-Z#]+(\s|-){0,3}){1,5}\s*" uppercase_chapters = r"\s*.?([A-Z#]+(\s|-){0,3}){1,5}\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 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
#print chapter_marker print chapter_marker
heading = re.compile('<h[1-3][^>]*>', re.IGNORECASE) heading = re.compile('<h[1-3][^>]*>', re.IGNORECASE)
self.html_preprocess_sections = len(heading.findall(html)) self.html_preprocess_sections = len(heading.findall(html))
self.log("found " + unicode(self.html_preprocess_sections) + " pre-existing headings") self.log("found " + unicode(self.html_preprocess_sections) + " pre-existing headings")
@ -184,12 +184,14 @@ class PreProcessor(object):
if self.html_preprocess_sections < 10: if self.html_preprocess_sections < 10:
self.log("not enough chapters, only " + unicode(self.html_preprocess_sections) + ", trying numeric chapters") 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 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
print chapter_marker
chapdetect2 = re.compile(r'%s' % chapter_marker, re.IGNORECASE) chapdetect2 = re.compile(r'%s' % chapter_marker, re.IGNORECASE)
html = chapdetect2.sub(self.chapter_head, html) html = chapdetect2.sub(self.chapter_head, html)
if self.html_preprocess_sections < 10: if self.html_preprocess_sections < 10:
self.log("not enough chapters, only " + unicode(self.html_preprocess_sections) + ", trying with uppercase words") 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 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
print chapter_marker
chapdetect2 = re.compile(r'%s' % chapter_marker, re.UNICODE) chapdetect2 = re.compile(r'%s' % chapter_marker, re.UNICODE)
html = chapdetect2.sub(self.chapter_head, html) html = chapdetect2.sub(self.chapter_head, html)
###### Unwrap lines ###### ###### Unwrap lines ######

4
src/calibre/ebooks/mobi/mobiml.py
View File

@ -184,12 +184,12 @@ class MobiMLizer(object):
elif tag in NESTABLE_TAGS and istate.rendered: elif tag in NESTABLE_TAGS and istate.rendered:
para = wrapper = bstate.nested[-1] para = wrapper = bstate.nested[-1]
elif left > 0 and indent >= 0: elif left > 0 and indent >= 0:
para = wrapper = etree.SubElement(parent, XHTML('blockquote')) para = wrapper = etree.SubElement(parent, XHTML('div'))
para = wrapper para = wrapper
emleft = int(round(left / self.profile.fbase)) - 1 emleft = int(round(left / self.profile.fbase)) - 1
emleft = min((emleft, 10)) emleft = min((emleft, 10))
while emleft > 0: while emleft > 0:
para = etree.SubElement(para, XHTML('blockquote')) para = etree.SubElement(para, XHTML('div'))
emleft -= 1 emleft -= 1
else: else:
para = wrapper = etree.SubElement(parent, XHTML('p')) para = wrapper = etree.SubElement(parent, XHTML('p'))