Cutlery/calibre
1
0
Fork 0
mirror of https://github.com/kovidgoyal/calibre.git synced 2025-07-07 18:24:30 -04:00
Code Issues Packages Projects Releases Wiki Activity

HTML Input: Sanitize semi-colons from HTML filenames as they can cause problems with other EPUB consuming software. Fixes #1598719 [Name of linked file containing semicolon](https://bugs.launchpad.net/calibre/+bug/1598719)

Browse Source
This commit is contained in:
Kovid Goyal 2016-07-05 14:54:56 +05:30
parent 1ff02ee830
commit 88e3e0fb9f
1 changed files with 4 additions and 4 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

8
src/calibre/ebooks/conversion/plugins/html_input.py
View File

@ -18,6 +18,8 @@ from calibre.utils.localization import get_lang
from calibre.utils.filenames import ascii_filename from calibre.utils.filenames import ascii_filename
from calibre.utils.imghdr import what from calibre.utils.imghdr import what
def sanitize_file_name(x):
return ascii_filename(x).replace(';', '_')
class HTMLInput(InputFormatPlugin): class HTMLInput(InputFormatPlugin):
@ -145,8 +147,7 @@ class HTMLInput(InputFormatPlugin):
oeb.container = DirContainer(os.path.dirname(path), log, oeb.container = DirContainer(os.path.dirname(path), log,
ignore_opf=True) ignore_opf=True)
bname = os.path.basename(path) bname = os.path.basename(path)
id, href = oeb.manifest.generate(id='html', id, href = oeb.manifest.generate(id='html', href=sanitize_file_name(bname))
href=ascii_filename(bname))
htmlfile_map[path] = href htmlfile_map[path] = href
item = oeb.manifest.add(id, href, 'text/html') item = oeb.manifest.add(id, href, 'text/html')
if path == htmlpath and '%' in path: if path == htmlpath and '%' in path:
@ -260,8 +261,7 @@ class HTMLInput(InputFormatPlugin):
link = link.lower() link = link.lower()
if link not in self.added_resources: if link not in self.added_resources:
bhref = os.path.basename(link) bhref = os.path.basename(link)
id, href = self.oeb.manifest.generate(id='added', id, href = self.oeb.manifest.generate(id='added', href=sanitize_file_name(bhref))
href=bhref)
guessed = self.guess_type(href)[0] guessed = self.guess_type(href)[0]
media_type = guessed or self.BINARY_MIME media_type = guessed or self.BINARY_MIME
if media_type == 'text/plain': if media_type == 'text/plain':