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

Better pdftohtml processing rules based on ldolse from mobileread's work.

Browse Source
This commit is contained in:
John Schember 2009-04-18 13:40:24 -04:00
parent fe3d1f5bc7
commit 3fe2c7a2ed
2 changed files with 22 additions and 6 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

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

@ -23,6 +23,14 @@ def sanitize_head(match):
x = _span_pat.sub('', x) x = _span_pat.sub('', x)
return '<head>\n'+x+'\n</head>' return '<head>\n'+x+'\n</head>'
def chap_head(match):
chap = match.group('chap')
title = match.group('title')
if not title:
return '<h1>'+chap+'</h1><br/>'
else:
return '<h1>'+chap+'<br/>'+title+'</h1><br/>'
class CSSPreProcessor(object): class CSSPreProcessor(object):
@ -54,8 +62,9 @@ class HTMLPreProcessor(object):
(re.compile(r'<hr.*?>', re.IGNORECASE), lambda match: '<br />'), (re.compile(r'<hr.*?>', re.IGNORECASE), lambda match: '<br />'),
# Remove page numbers # Remove page numbers
(re.compile(r'\d+<br>', re.IGNORECASE), lambda match: ''), (re.compile(r'\d+<br>', re.IGNORECASE), lambda match: ''),
# Remove <br> and replace <br><br> with <p> # Replace <br><br> with <p>
(re.compile(r'<br.*?>\s*<br.*?>', re.IGNORECASE), lambda match: '<p>'), (re.compile(r'<br.*?>\s*<br.*?>', re.IGNORECASE), lambda match: '<p>'),
# Remove <br>
(re.compile(r'(.*)<br.*?>', re.IGNORECASE), (re.compile(r'(.*)<br.*?>', re.IGNORECASE),
lambda match: match.group() if \ lambda match: match.group() if \
re.match('<', match.group(1).lstrip()) or \ re.match('<', match.group(1).lstrip()) or \
@ -69,15 +78,22 @@ class HTMLPreProcessor(object):
# Remove non breaking spaces # Remove non breaking spaces
(re.compile(ur'\u00a0'), lambda match : ' '), (re.compile(ur'\u00a0'), lambda match : ' '),
# Detect Chapters to match default XPATH in GUI
(re.compile(r'(<br[^>]*>)?(</?p[^>]*>)?s*(?P<chap>(Chapter|Epilogue|Prologue|Book|Part)\s*(\d+|\w+)?)(</?p[^>]*>|<br[^>]*>)\n?((?=(<i>)?\s*\w+(\s+\w+)?(</i>)?(<br[^>]*>|</?p[^>]*>))((?P<title>.*)(<br[^>]*>|</?p[^>]*>)))?', re.IGNORECASE), chap_head),
(re.compile(r'(<br[^>]*>)?(</?p[^>]*>)?s*(?P<chap>([A-Z \'"!]{5,})\s*(\d+|\w+)?)(</?p[^>]*>|<br[^>]*>)\n?((?=(<i>)?\s*\w+(\s+\w+)?(</i>)?(<br[^>]*>|</?p[^>]*>))((?P<title>.*)(<br[^>]*>|</?p[^>]*>)))?'), chap_head),
# Have paragraphs show better # Have paragraphs show better
(re.compile(r'<br.*?>'), lambda match : '<p>'), (re.compile(r'<br.*?>'), lambda match : '<p>'),
# Un wrap lines # Un wrap lines
(re.compile(r'(?<=\w)\s*</(i|b|u)>\s*<p.*?>\s*<(i|b|u)>\s*(?=\w)'), lambda match: ' '), (re.compile(r'(?<=[^\.^\^?^!^"^”])\s*(</(i|b|u)>)*\s*<p.*?>\s*(<(i|b|u)>)*\s*(?=[a-z0-9I])', re.UNICODE), lambda match: ' '),
(re.compile(r'(?<=\w)\s*<p.*?>\s*(?=\w)', re.UNICODE), lambda match: ' '),
# Clean up spaces # Clean up spaces
(re.compile(u'(?<=\.|,|:|;|\?|!|”|"|\')[\s^ ]*(?=<)'), lambda match: ' '), (re.compile(u'(?<=[\.,:;\?!”"\'])[\s^ ]*(?=<)'), lambda match: ' '),
] # Add space before and after italics
(re.compile(r'(?<!“)<i>'), lambda match: ' <i>'),
(re.compile(r'</i>(?=\w)'), lambda match: '</i> '),
]
# Fix Book Designer markup # Fix Book Designer markup
BOOK_DESIGNER = [ BOOK_DESIGNER = [

2
src/calibre/ebooks/metadata/pdf.py
View File

@ -98,7 +98,7 @@ def get_cover(stream):
data = cStringIO.StringIO() data = cStringIO.StringIO()
try: try:
StreamReadWrapper(stream) as stream: with StreamReadWrapper(stream) as stream:
pdf = PdfFileReader(stream) pdf = PdfFileReader(stream)
output = PdfFileWriter() output = PdfFileWriter()