diff --git a/scripts/convert_imdb_reviews.py b/scripts/convert_imdb_reviews.py index 9b3311b..060dd26 100644 --- a/scripts/convert_imdb_reviews.py +++ b/scripts/convert_imdb_reviews.py @@ -32,7 +32,29 @@ def main(): if not PATH_DATASETS_IMDB_EXTRACTED.exists(): with tarfile.open(PATH_DATASETS_IMDB) as mytar: - mytar.extractall(PATH_DATASETS_IMDB_EXTRACTED) + + 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(mytar, PATH_DATASETS_IMDB_EXTRACTED) positive = [(p, "positive") for p in (PATH_DATASETS_IMDB_TRAIN / "pos").iterdir()] negative = [(p, "negative") for p in (PATH_DATASETS_IMDB_TRAIN / "neg").iterdir()]