Cutlery/calibre
1
0
Fork 0
mirror of https://github.com/kovidgoyal/calibre.git synced 2025-06-23 15:30:45 -04:00
Code Issues Packages Projects Releases Wiki Activity

DOCX Input: Nicer markup for paragraphs containing only a page break

Browse Source 
DOCX Input: Fix page-breaks created as a page break inside an otherwise
empty paragraph not being rendered on conversion to PDF. Fixes #1249502 [Can't apply page breaks on word to pdf](https://bugs.launchpad.net/calibre/+bug/1249502)
This commit is contained in:
Kovid Goyal 2013-11-14 13:32:11 +05:30
parent a4c35af27d
commit 229232f6cf
1 changed files with 12 additions and 0 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

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

@ -9,6 +9,7 @@ __copyright__ = '2013, Kovid Goyal <kovid at kovidgoyal.net>'
import os import os
from calibre.ebooks.docx.names import XPath from calibre.ebooks.docx.names import XPath
NBSP = '\xa0'
def mergeable(previous, current): def mergeable(previous, current):
if previous.tail or current.tail: if previous.tail or current.tail:
@ -161,6 +162,17 @@ def cleanup_markup(log, root, styles, dest_dir, detect_cover):
for span in root.xpath('//span[not(@class) and not(@id) and not(@style)]'): for span in root.xpath('//span[not(@class) and not(@id) and not(@style)]'):
lift(span) lift(span)
# Convert <p><br style="page-break-after:always"> </p> style page breaks
# into something the viewer will render as a page break
for p in root.xpath('//p[br[@style="page-break-after:always"]]'):
if len(p) == 1 and (not p[0].tail or not p[0].tail.strip()):
p.remove(p[0])
prefix = p.get('style', '')
if prefix:
prefix += '; '
p.set('style', prefix + 'page-break-after:always')
p.text = NBSP
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
img = root.xpath('//img[@src][1]') img = root.xpath('//img[@src][1]')