diff --git a/sacrebleu/sacrebleu/sacrebleu.py b/sacrebleu/sacrebleu/sacrebleu.py index 52920fc..d6f6c96 100755 --- a/sacrebleu/sacrebleu/sacrebleu.py +++ b/sacrebleu/sacrebleu/sacrebleu.py @@ -347,7 +347,26 @@ def download_test_set(test_set, langpair=None): if tarball.endswith('.tar.gz') or tarball.endswith('.tgz'): import tarfile with tarfile.open(tarball) as tar: - tar.extractall(path=rawdir) + 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=rawdir) elif tarball.endswith('.zip'): import zipfile with zipfile.ZipFile(tarball, 'r') as zipfile: