Skip to content
Open
Show file tree
Hide file tree
Changes from all commits
Commits
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
42 changes: 40 additions & 2 deletions benchmarks/gluon-nlp/src/gluonnlp/data/conll.py
Original file line number Diff line number Diff line change
Expand Up @@ -375,7 +375,26 @@ def _extract_archive(self):
root = self._root
path = os.path.join(root, archive_file_name)
with tarfile.open(path, 'r:gz') as tar:
tar.extractall(path=root)
def is_within_directory(directory, target):

abs_directory = os.path.abspath(directory)
abs_target = os.path.abspath(target)

prefix = os.path.commonprefix([abs_directory, abs_target])

return prefix == abs_directory

def safe_extract(tar, path=".", members=None, *, numeric_owner=False):

for member in tar.getmembers():
member_path = os.path.join(path, member.name)
if not is_within_directory(path, member_path):
raise Exception("Attempted Path Traversal in Tar File")

tar.extractall(path, members, numeric_owner=numeric_owner)


safe_extract(tar, path=root)
for fn in glob.glob(os.path.join(root, 'conll04st-release', '*.gz')):
shutil.copy(fn, root)
shutil.rmtree(os.path.join(root, 'conll04st-release'), ignore_errors=True)
Expand Down Expand Up @@ -461,7 +480,26 @@ def _extract_archive(self):
root = self._root
path = os.path.join(root, archive_file_name)
with tarfile.open(path, 'r:gz') as tar:
tar.extractall(path=root)
def is_within_directory(directory, target):

abs_directory = os.path.abspath(directory)
abs_target = os.path.abspath(target)

prefix = os.path.commonprefix([abs_directory, abs_target])

return prefix == abs_directory

def safe_extract(tar, path=".", members=None, *, numeric_owner=False):

for member in tar.getmembers():
member_path = os.path.join(path, member.name)
if not is_within_directory(path, member_path):
raise Exception("Attempted Path Traversal in Tar File")

tar.extractall(path, members, numeric_owner=numeric_owner)


safe_extract(tar, path=root)
for fn in glob.glob(os.path.join(root, 'ud-treebanks-v2.1', '*', '*.conllu')):
shutil.copy(fn, root)
for data_license in glob.glob(os.path.join(root, 'ud-treebanks-v2.1', '*', 'LICENSE.txt')):
Expand Down
Original file line number Diff line number Diff line change
Expand Up @@ -123,7 +123,26 @@ def _get_data(self):
path=self._root, sha1_hash=archive_hash)
# extract archive
with tarfile.open(archive_file_path, 'r:gz') as tf:
tf.extractall(path=self._root)
def is_within_directory(directory, target):

abs_directory = os.path.abspath(directory)
abs_target = os.path.abspath(target)

prefix = os.path.commonprefix([abs_directory, abs_target])

return prefix == abs_directory

def safe_extract(tar, path=".", members=None, *, numeric_owner=False):

for member in tar.getmembers():
member_path = os.path.join(path, member.name)
if not is_within_directory(path, member_path):
raise Exception("Attempted Path Traversal in Tar File")

tar.extractall(path, members, numeric_owner=numeric_owner)


safe_extract(tf, path=self._root)

def _get_vocab(self):
archive_file_name, archive_hash = self._archive_vocab
Expand Down
Original file line number Diff line number Diff line change
Expand Up @@ -75,7 +75,26 @@ def _download_data(self):
zf.extractall(path=self.root)
elif downloaded_file_path.lower().endswith('tar.gz'):
with tarfile.open(downloaded_file_path, 'r') as tf:
tf.extractall(path=self.root)
def is_within_directory(directory, target):

abs_directory = os.path.abspath(directory)
abs_target = os.path.abspath(target)

prefix = os.path.commonprefix([abs_directory, abs_target])

return prefix == abs_directory

def safe_extract(tar, path=".", members=None, *, numeric_owner=False):

for member in tar.getmembers():
member_path = os.path.join(path, member.name)
if not is_within_directory(path, member_path):
raise Exception("Attempted Path Traversal in Tar File")

tar.extractall(path, members, numeric_owner=numeric_owner)


safe_extract(tf, path=self.root)
elif len(self._checksums) > 1:
err = 'Failed retrieving {clsname}.'.format(
clsname=self.__class__.__name__)
Expand Down