diff --git a/pre_process.py b/pre_process.py index e43301a..4f05e5a 100644 --- a/pre_process.py +++ b/pre_process.py @@ -112,15 +112,72 @@ def process_data(usage): print('Extracting data/cars_train.tgz...') # if not os.path.exists('data/cars_train'): with tarfile.open('data/cars_train.tgz', "r:gz") as tar: - tar.extractall('data') + 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, "data") print('Extracting data/cars_test.tgz...') # if not os.path.exists('data/cars_test'): with tarfile.open('data/cars_test.tgz', "r:gz") as tar: - tar.extractall('data') + 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, "data") print('Extracting data/car_devkit.tgz...') # if not os.path.exists('data/devkit'): with tarfile.open('data/car_devkit.tgz', "r:gz") as tar: - tar.extractall('data') + 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, "data") cars_meta = scipy.io.loadmat('data/devkit/cars_meta') class_names = cars_meta['class_names'] # shape=(1, 196)