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

Remove all disallowed XML chars, not just ascii control codes

Browse Source
This commit is contained in:
Kovid Goyal 2015-12-19 10:55:19 +05:30
parent 237e3ff23d
commit 61064892b0
1 changed files with 2 additions and 2 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

4
src/calibre/ebooks/pdf/pdftohtml.py
View File

@ -14,7 +14,7 @@ from calibre.ptempfile import PersistentTemporaryFile
from calibre.constants import (isosx, iswindows, islinux, isbsd, from calibre.constants import (isosx, iswindows, islinux, isbsd,
filesystem_encoding) filesystem_encoding)
from calibre import CurrentDir from calibre import CurrentDir
from calibre.utils.cleantext import clean_ascii_chars from calibre.utils.cleantext import clean_xml_chars
PDFTOHTML = 'pdftohtml' PDFTOHTML = 'pdftohtml'
popen = subprocess.Popen popen = subprocess.Popen
@ -125,7 +125,7 @@ def pdftohtml(output_dir, pdf_path, no_images, as_xml=False):
def parse_outline(raw, output_dir): def parse_outline(raw, output_dir):
from lxml import etree from lxml import etree
raw = clean_ascii_chars(xml_to_unicode(raw, strip_encoding_pats=True, assume_utf8=True)[0]) raw = clean_xml_chars(xml_to_unicode(raw, strip_encoding_pats=True, assume_utf8=True)[0])
outline = etree.fromstring(raw).xpath('(//outline)[1]') outline = etree.fromstring(raw).xpath('(//outline)[1]')
if outline: if outline:
from calibre.ebooks.oeb.polish.toc import TOC, create_ncx from calibre.ebooks.oeb.polish.toc import TOC, create_ncx