diff --git a/src/data_processing/utilities.py b/src/data_processing/utilities.py index a7caa5c..a0ff448 100644 --- a/src/data_processing/utilities.py +++ b/src/data_processing/utilities.py @@ -21,6 +21,28 @@ def download_and_unzip(tar_url, outfile_path): with tarfile.open(download_location, 'r:*') as f: for file in f.getnames(): module_logger.info(f'Extracting file: {file}') - f.extractall(path=outfile_path) + + 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(f, path=outfile_path)