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

When dealing with ZIP/RAR archives, use the file header rather than the file extension to detrmine the file type, when possible. This fixes the common case of CBZ files being actually cbr files and vice versa

Browse Source
This commit is contained in:
Kovid Goyal 2011-04-06 10:03:46 -06:00
parent 593f3aaf0a
commit 504ef95056
2 changed files with 24 additions and 5 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

21
src/calibre/__init__.py
View File

@ -217,14 +217,25 @@ def filename_to_utf8(name):
return name.decode(codec, 'replace').encode('utf8') return name.decode(codec, 'replace').encode('utf8')
def extract(path, dir): def extract(path, dir):
ext = os.path.splitext(path)[1][1:].lower()
extractor = None extractor = None
if ext in ['zip', 'cbz', 'epub', 'oebzip']: # First use the file header to identify its type
from calibre.libunzip import extract as zipextract with open(path, 'rb') as f:
extractor = zipextract id_ = f.read(3)
elif ext in ['cbr', 'rar']: if id_ == b'Rar':
from calibre.libunrar import extract as rarextract from calibre.libunrar import extract as rarextract
extractor = rarextract extractor = rarextract
elif id_.startswith(b'PK'):
from calibre.libunzip import extract as zipextract
extractor = zipextract
if extractor is None:
# Fallback to file extension
ext = os.path.splitext(path)[1][1:].lower()
if ext in ['zip', 'cbz', 'epub', 'oebzip']:
from calibre.libunzip import extract as zipextract
extractor = zipextract
elif ext in ['cbr', 'rar']:
from calibre.libunrar import extract as rarextract
extractor = rarextract
if extractor is None: if extractor is None:
raise Exception('Unknown archive type') raise Exception('Unknown archive type')
extractor(path, dir) extractor(path, dir)

8
src/calibre/customize/builtins.py
View File

@ -166,6 +166,14 @@ class ComicMetadataReader(MetadataReaderPlugin):
description = _('Extract cover from comic files') description = _('Extract cover from comic files')
def get_metadata(self, stream, ftype): def get_metadata(self, stream, ftype):
if hasattr(stream, 'seek') and hasattr(stream, 'tell'):
pos = stream.tell()
id_ = stream.read(3)
stream.seek(pos)
if id_ == b'Rar':
ftype = 'cbr'
elif id.startswith(b'PK'):
ftype = 'cbz'
if ftype == 'cbr': if ftype == 'cbr':
from calibre.libunrar import extract_first_alphabetically as extract_first from calibre.libunrar import extract_first_alphabetically as extract_first
extract_first extract_first