diff --git a/python-machine-learning-book-2nd-edition/code/ch08/ch08.py b/python-machine-learning-book-2nd-edition/code/ch08/ch08.py index e30683c..a3d9e28 100644 --- a/python-machine-learning-book-2nd-edition/code/ch08/ch08.py +++ b/python-machine-learning-book-2nd-edition/code/ch08/ch08.py @@ -114,7 +114,26 @@ def reporthook(count, block_size, total_size): if not os.path.isdir('aclImdb'): with tarfile.open(target, 'r:gz') as tar: - tar.extractall() + 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) # ## Preprocessing the movie dataset into more convenient format