Hash paths

hash_paths.py

#!/usr/bin/env python3
"""Utility to produce the hash of a collection of file and directory paths.

Usage::

    ./hash_paths.py --help
"""
import argparse
import hashlib
import io
from tarfile import GNU_FORMAT, TarFile


def hash_paths(*paths: str, algorithm: str = "sha1") -> str:
    """Hash a collection of file and directory paths.

    Calculates the digest by adding the paths to an in-memory archive and hashing the
    contents.
    """
    with io.BytesIO() as f:
        with TarFile(fileobj=f, mode="w", format=GNU_FORMAT) as tar:
            for path in paths:
                tar.add(path)
        f.seek(0)
        return hashlib.new(algorithm, f.read(), usedforsecurity=False).hexdigest()


if __name__ == "__main__":
    parser = argparse.ArgumentParser(
        description="Calculate the collective hash of a series of paths"
    )
    parser.add_argument(
        "path", type=str, nargs="+", help="a file or directory path to add to the hash"
    )
    parser.add_argument(
        "--algorithm",
        type=str,
        metavar="ALGO",
        default="sha1",
        help="openssl algorithm to use for hashing. (default: sha1)",
    )
    args = parser.parse_args()
    print(hash_paths(*args.path, algorithm=args.algorithm))

hash_paths.sh

#!/bin/bash

function hashpaths() {
    HASH_ALGO=${HASH_ALGO:-sha1sum}
    tar cf - "$@"| $HASH_ALGO | cut -f 1 -d ' '
    return 0
}

function usage() {
    cat <<USAGE
$0 [-h] path [path ...]

Calculate the collective hash of a series of paths.

positional arguments:
  path              a file or directory path to add to the hash

options:
  -h, --help        show this help message and exit

env:
  HASH_ALGO         select the hash algorithm. (default sha1sum)

example:
  HASH_ALGO=md5sum $0 foo bar.txt
USAGE
  return 0
}

[[ -z $1 || $1 == "-h" || $1 == "--help" ]] && { usage; } || hashpaths "$@"
exit