mirrors/cpython
1
0
Fork 0
mirror of https://github.com/python/cpython.git synced 2025-08-30 21:48:47 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions 9

bpo-28080: Add support for the fallback encoding in ZIP files (GH-32007)

Browse source 
* Add the metadata_encoding parameter in the zipfile.ZipFile constructor.
* Add the --metadata-encoding option in the zipfile CLI.

Co-authored-by: Stephen J. Turnbull <stephen@xemacs.org>
This commit is contained in:
Serhiy Storchaka 2022-03-22 11:52:55 +02:00 • committed by GitHub
parent c6cd3cc93c
commit a25a985535
No known key found for this signature in database
GPG key ID: 4AEE18F83AFDEB23
5 changed files with 211 additions and 11 deletions
Download patch file Download diff file Expand all files Collapse all files

31
Lib/zipfile.py
View file

@ -480,7 +480,7 @@ class ZipInfo (object):
def _encodeFilenameFlags(self):
try:
return self.filename.encode('ascii'), self.flag_bits
return self.filename.encode('ascii'), self.flag_bits & ~_MASK_UTF_FILENAME
except UnicodeEncodeError:
return self.filename.encode('utf-8'), self.flag_bits | _MASK_UTF_FILENAME
@ -1240,7 +1240,7 @@ class ZipFile:
_windows_illegal_name_trans_table = None
def __init__(self, file, mode="r", compression=ZIP_STORED, allowZip64=True,
compresslevel=None, *, strict_timestamps=True):
compresslevel=None, *, strict_timestamps=True, metadata_encoding=None):
"""Open the ZIP file with mode read 'r', write 'w', exclusive create 'x',
or append 'a'."""
if mode not in ('r', 'w', 'x', 'a'):
@ -1259,6 +1259,12 @@ class ZipFile:
self.pwd = None
self._comment = b''
self._strict_timestamps = strict_timestamps
self.metadata_encoding = metadata_encoding
# Check that we don't try to write with nonconforming codecs
if self.metadata_encoding and mode != 'r':
raise ValueError(
"metadata_encoding is only supported for reading files")
# Check if we were passed a file-like object
if isinstance(file, os.PathLike):
@ -1389,13 +1395,13 @@ class ZipFile:
if self.debug > 2:
print(centdir)
filename = fp.read(centdir[_CD_FILENAME_LENGTH])
flags = centdir[5]
flags = centdir[_CD_FLAG_BITS]
if flags & _MASK_UTF_FILENAME:
# UTF-8 file names extension
filename = filename.decode('utf-8')
else:
# Historical ZIP filename encoding
filename = filename.decode('cp437')
filename = filename.decode(self.metadata_encoding or 'cp437')
# Create ZipInfo instance to store file information
x = ZipInfo(filename)
x.extra = fp.read(centdir[_CD_EXTRA_FIELD_LENGTH])
@ -1572,7 +1578,7 @@ class ZipFile:
# UTF-8 filename
fname_str = fname.decode("utf-8")
else:
fname_str = fname.decode("cp437")
fname_str = fname.decode(self.metadata_encoding or "cp437")
if fname_str != zinfo.orig_filename:
raise BadZipFile(
@ -2461,11 +2467,15 @@ def main(args=None):
help='Create zipfile from sources')
group.add_argument('-t', '--test', metavar='<zipfile>',
help='Test if a zipfile is valid')
parser.add_argument('--metadata-encoding', metavar='<encoding>',
help='Specify encoding of member names for -l, -e and -t')
args = parser.parse_args(args)
encoding = args.metadata_encoding
if args.test is not None:
src = args.test
with ZipFile(src, 'r') as zf:
with ZipFile(src, 'r', metadata_encoding=encoding) as zf:
badfile = zf.testzip()
if badfile:
print("The following enclosed file is corrupted: {!r}".format(badfile))
@ -2473,15 +2483,20 @@ def main(args=None):
elif args.list is not None:
src = args.list
with ZipFile(src, 'r') as zf:
with ZipFile(src, 'r', metadata_encoding=encoding) as zf:
zf.printdir()
elif args.extract is not None:
src, curdir = args.extract
with ZipFile(src, 'r') as zf:
with ZipFile(src, 'r', metadata_encoding=encoding) as zf:
zf.extractall(curdir)
elif args.create is not None:
if encoding:
print("Non-conforming encodings not supported with -c.",
file=sys.stderr)
sys.exit(1)
zip_name = args.create.pop(0)
files = args.create