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

Nicer fix for trailing <br>

Browse Source 
Also handles headings and list items with trailing <br>s
This commit is contained in:
Kovid Goyal 2013-09-08 13:11:22 +05:30
parent 604530e569
commit e9b531584f
1 changed files with 3 additions and 9 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

12
src/calibre/ebooks/docx/cleanup.py
View File

@ -8,8 +8,6 @@ __copyright__ = '2013, Kovid Goyal <kovid at kovidgoyal.net>'
import os import os
from lxml.html.builder import P
from calibre.ebooks.docx.names import XPath from calibre.ebooks.docx.names import XPath
NBSP = '\xa0' NBSP = '\xa0'
@ -166,14 +164,10 @@ def cleanup_markup(log, root, styles, dest_dir, detect_cover):
lift(span) lift(span)
# If a paragraph ends with a <br>, that <br> is not rendered in HTML, but # If a paragraph ends with a <br>, that <br> is not rendered in HTML, but
# it is in Word, so move it out # it is in Word, so add a trailing space to ensure it is rendered.
for br in root.xpath('//p/node()[position()=last()]/self::br'): for br in root.xpath('//*[contains("p,h1,h2,h3,h4,h5,h6,li", name())]/node()[position()=last()]/self::br'):
if not br.tail: if not br.tail:
p = br.getparent() br.tail = NBSP
p.remove(br)
gp = p.getparent()
blank = P(NBSP)
gp.insert(gp.index(p)+1, blank)
if detect_cover: if detect_cover:
# Check if the first image in the document is possibly a cover # Check if the first image in the document is possibly a cover