Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Disable pickle #1

Merged
merged 3 commits into from
Apr 20, 2023
Merged

Disable pickle #1

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
3 commits
Select commit Hold shift + click to select a range
c533b54
disable allowing pickle
isabella618033 Apr 20, 2023
cc271d9
added test
isabella618033 Apr 20, 2023
122c589
fix test
isabella618033 Apr 20, 2023
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
80 changes: 50 additions & 30 deletions msgpack_numpy.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -51,7 +51,7 @@ def ndarray_to_bytes(obj):
def tostr(x):
return x

def encode(obj, chain=None):
def encode(obj, chain=None, allow_pickle=False):
"""
Data encoder for serializing numpy data types.
"""
Expand All @@ -60,6 +60,8 @@ def encode(obj, chain=None):
# If the dtype is structured, store the interface description;
# otherwise, store the corresponding array protocol type string:
if obj.dtype.kind in ('V', 'O'):
if obj.dtype.kind == 'O' and not allow_pickle:
raise ValueError("Can't pickle object arrays if allow_pickle is False")
kind = bytes(obj.dtype.kind, 'ascii')
descr = obj.dtype.descr
else:
Expand All @@ -81,7 +83,7 @@ def encode(obj, chain=None):
else:
return obj if chain is None else chain(obj)

def decode(obj, chain=None):
def decode(obj, chain=None, allow_pickle=False):
"""
Decoder for deserializing numpy data types.
"""
Expand All @@ -97,6 +99,8 @@ def decode(obj, chain=None):
descr = [tuple(tostr(t) if type(t) is bytes else t for t in d) \
for d in obj[b'type']]
elif b'kind' in obj and obj[b'kind'] == b'O':
if not allow_pickle:
raise ValueError("Can't unpickle object arrays if allow_pickle is False")
return pickle.loads(obj[b'data'])
else:
descr = obj[b'type']
Expand Down Expand Up @@ -138,8 +142,9 @@ def __init__(self, default=None,
encoding='utf-8',
unicode_errors='strict',
use_single_float=False,
autoreset=1):
default = functools.partial(encode, chain=default)
autoreset=1,
allow_pickle=False):
default = functools.partial(encode, chain=default, allow_pickle=allow_pickle)
super(Packer, self).__init__(default=default,
encoding=encoding,
unicode_errors=unicode_errors,
Expand All @@ -149,8 +154,8 @@ class Unpacker(_Unpacker):
def __init__(self, file_like=None, read_size=0, use_list=None,
object_hook=None,
object_pairs_hook=None, list_hook=None, encoding='utf-8',
unicode_errors='strict', max_buffer_size=0):
object_hook = functools.partial(decode, chain=object_hook)
unicode_errors='strict', max_buffer_size=0, allow_pickle=False):
object_hook = functools.partial(decode, chain=object_hook, allow_pickle=allow_pickle)
super(Unpacker, self).__init__(file_like=file_like,
read_size=read_size,
use_list=use_list,
Expand All @@ -168,8 +173,9 @@ def __init__(self, default=None,
use_single_float=False,
autoreset=1,
use_bin_type=True,
strict_types=False):
default = functools.partial(encode, chain=default)
strict_types=False,
allow_pickle=False):
default = functools.partial(encode, chain=default, allow_pickle=allow_pickle)
super(Packer, self).__init__(default=default,
unicode_errors=unicode_errors,
use_single_float=use_single_float,
Expand All @@ -183,8 +189,8 @@ def __init__(self, file_like=None, read_size=0, use_list=None,
object_hook=None,
object_pairs_hook=None, list_hook=None,
unicode_errors='strict', max_buffer_size=0,
ext_hook=msgpack.ExtType):
object_hook = functools.partial(decode, chain=object_hook)
ext_hook=msgpack.ExtType, allow_pickle=False):
object_hook = functools.partial(decode, chain=object_hook, allow_pickle=allow_pickle)
super(Unpacker, self).__init__(file_like=file_like,
read_size=read_size,
use_list=use_list,
Expand All @@ -205,8 +211,9 @@ def __init__(self,
use_bin_type=True,
strict_types=False,
datetime=False,
unicode_errors=None):
default = functools.partial(encode, chain=default)
unicode_errors=None,
allow_pickle=False):
default = functools.partial(encode, chain=default, allow_pickle=allow_pickle)
super(Packer, self).__init__(default=default,
use_single_float=use_single_float,
autoreset=autoreset,
Expand All @@ -233,8 +240,9 @@ def __init__(self,
max_bin_len=-1,
max_array_len=-1,
max_map_len=-1,
max_ext_len=-1):
object_hook = functools.partial(decode, chain=object_hook)
max_ext_len=-1,
allow_pickle=False):
object_hook = functools.partial(decode, chain=object_hook, allow_pickle=allow_pickle)
super(Unpacker, self).__init__(file_like=file_like,
read_size=read_size,
use_list=use_list,
Expand Down Expand Up @@ -268,41 +276,53 @@ def packb(o, **kwargs):

return Packer(**kwargs).pack(o)

def unpack(stream, **kwargs):
def unpack(stream, allow_pickle=False, **kwargs):
"""
Unpack a packed object from a stream.
"""

object_hook = kwargs.get('object_hook')
kwargs['object_hook'] = functools.partial(decode, chain=object_hook)
kwargs['object_hook'] = functools.partial(decode, chain=object_hook, allow_pickle=allow_pickle)
return _unpack(stream, **kwargs)

def unpackb(packed, **kwargs):
def unpackb(packed, allow_pickle=False, **kwargs):
"""
Unpack a packed object.
"""

object_hook = kwargs.get('object_hook')
kwargs['object_hook'] = functools.partial(decode, chain=object_hook)
kwargs['object_hook'] = functools.partial(decode, chain=object_hook, allow_pickle=allow_pickle)
return _unpackb(packed, **kwargs)

load = unpack
loads = unpackb
dump = pack
dumps = packb

def patch():
def patch(allow_pickle=False):
"""
Monkey patch msgpack module to enable support for serializing numpy types.
"""

setattr(msgpack, 'Packer', Packer)
setattr(msgpack, 'Unpacker', Unpacker)
setattr(msgpack, 'load', unpack)
setattr(msgpack, 'loads', unpackb)
setattr(msgpack, 'dump', pack)
setattr(msgpack, 'dumps', packb)
setattr(msgpack, 'pack', pack)
setattr(msgpack, 'packb', packb)
setattr(msgpack, 'unpack', unpack)
setattr(msgpack, 'unpackb', unpackb)
class Packer_(Packer):
def __init__(self, *args, **kws):
super(Packer, self).__init__(*args, **kws, allow_pickle=allow_pickle)

class Unpacker_(Unpacker):
def __init__(self, *args, **kws):
super(Unpacker, self).__init__(*args, **kws, allow_pickle=allow_pickle)

pack_ = functools.partial(pack, allow_pickle=allow_pickle)
packb_ = functools.partial(packb, allow_pickle=allow_pickle)
unpack_ = functools.partial(unpack, allow_pickle=allow_pickle)
unpackb_ = functools.partial(unpackb, allow_pickle=allow_pickle)

setattr(msgpack, 'Packer', Packer_)
setattr(msgpack, 'Unpacker', Unpacker_)
setattr(msgpack, 'load', unpack_)
setattr(msgpack, 'loads', unpackb_)
setattr(msgpack, 'dump', pack_)
setattr(msgpack, 'dumps', packb_)
setattr(msgpack, 'pack', pack_)
setattr(msgpack, 'packb', packb_)
setattr(msgpack, 'unpack', unpack_)
setattr(msgpack, 'unpackb', unpackb_)
10 changes: 9 additions & 1 deletion tests.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -24,7 +24,7 @@ def __eq__(self, other):

class test_numpy_msgpack(TestCase):
def setUp(self):
patch()
patch(allow_pickle=True)

def encode_decode(self, x, use_list=True, max_bin_len=-1):
x_enc = msgpack.packb(x)
Expand Down Expand Up @@ -288,5 +288,13 @@ def test_numpy_nested_structured_array(self):
assert_array_equal(x, x_rec)
self.assertEqual(x.dtype, x_rec.dtype)

class test_numpy_msgpack_no_pickle(test_numpy_msgpack):
def setUp(self):
patch(allow_pickle=False)

def test_numpy_array_object(self):
x = np.random.rand(5).astype(object)
self.assertRaises(ValueError, self.encode_decode, x)

if __name__ == '__main__':
main()