Skip to content
Open
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
24 changes: 23 additions & 1 deletion scripts/oxford_dataset_helpers.py
Original file line number Diff line number Diff line change
Expand Up @@ -19,7 +19,29 @@ def fetch_and_untar(uri):

# Expand the archive
with tarfile.open(local_filename) as tar:
tar.extractall()

import os

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)

# The script below will rearrange the files so that all of the photos for a specific breed of dog
# or cat will be stored in its own directory, where the name of the directory is the name of the
Expand Down