Cutlery/calibre
1
0
Fork 0
mirror of https://github.com/kovidgoyal/calibre.git synced 2025-07-08 10:44:09 -04:00
Code Issues Packages Projects Releases Wiki Activity

PDF Input: Fix conversion of PDF documents that contain ASCII control codes in their outlines not working. Fixes #1527697 [failure to convert book](https://bugs.launchpad.net/calibre/+bug/1527697)

Browse Source
This commit is contained in:
Kovid Goyal 2015-12-19 10:50:30 +05:30
parent f0962dd696
commit 237e3ff23d
1 changed files with 3 additions and 0 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

3
src/calibre/ebooks/pdf/pdftohtml.py
View File

@ -9,10 +9,12 @@ import errno, os, sys, subprocess, shutil, re
from functools import partial from functools import partial
from calibre.ebooks import ConversionError, DRMError from calibre.ebooks import ConversionError, DRMError
from calibre.ebooks.chardet import xml_to_unicode
from calibre.ptempfile import PersistentTemporaryFile 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
PDFTOHTML = 'pdftohtml' PDFTOHTML = 'pdftohtml'
popen = subprocess.Popen popen = subprocess.Popen
@ -123,6 +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])
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