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

pdftohtml processing: better line re-wrapping

Browse Source
This commit is contained in:
John Schember 2009-04-09 17:31:07 -04:00
parent 2c3e8cccb8
commit f7ec532d57
1 changed files with 8 additions and 0 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

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

@ -48,6 +48,8 @@ class HTMLPreProcessor(object):
# Fix pdftohtml markup
PDFTOHTML = [
# Remove page links
(re.compile(r'<a name=\d+></a>', re.IGNORECASE), lambda match: ''),
# Remove <hr> tags
(re.compile(r'<hr.*?>', re.IGNORECASE), lambda match: '<br />'),
# Remove page numbers
@ -69,6 +71,12 @@ class HTMLPreProcessor(object):
# Have paragraphs show better
(re.compile(r'<br.*?>'), lambda match : '<p>'),
# Re wrap lines
(re.compile(r'(?<=\w)\s*</i>\s*<p.*?>\s*<i>\s*(?=\w)'), lambda match: ' '),
(re.compile(r'(?<=\w)\s*<p.*?>\s*(?=\w)', re.UNICODE), lambda match: ' '),
# Clean up spaces
(re.compile(ru'(?<=\.|,|:|;|\?|!|”|"|\')[\s^ ]*(?=<)'), lambda match: ' '),
]
# Fix Book Designer markup