Creates a SHA-256 digest of files in a directory

sha256digest.py

# -*- coding: utf-8 -*-
"""
Purpose
=======
Creates a SHA-256 digest of files in a directory


Attributions
============
Based on an answer by Richard Neumann on Code Review
https://codereview.stackexchange.com/a/147191


Based on statement that file digests are considered best-practice as of 2012
https://en.wikipedia.org/wiki/File_verification#File_formats


Creation and Modification Times
===============================
Created on Fri Apr 20 12:07:41 2018
Last Modified on Mon Apr 23 09:50:21 2018


License
=======
License: Creative Commons CC0
License URL: https://creativecommons.org/publicdomain/zero/1.0/legalcode


Changelog
=========
* 0.0.2
    - Added option to request individual files instead of digest
    - Don't output hash of currently running script
    - Added changelog
    - Added last modified date
    - Added example usage by developer and end-user
    - Added Creative Commons CC0 License
* 0.0.1
    - Initial release.


@author: rolandog
@version: 0.0.2
"""


from os import getcwd, listdir
from os.path import join, isfile, basename
from time import strftime
from hashlib import sha256
from textwrap import dedent


def list_files(basedir=None):
    """List only files within the respective directory"""

    if basedir is None:
        basedir = getcwd()

    # gets the name of the running script
    script_name = basename(__file__)

    for item in listdir(basedir):
        path = join(basedir, item)

        # don't make a hash of a hash file or current file
        if "sha256-digest" in item or ".sha256" in item or script_name in item:
            continue

        if isfile(path):
            # changed so that we get the path and the filename
            yield (path, item)


def sha256sum(file_name, block_size=None):
    """Returns the sha256 checksum of the respective file"""

    if block_size is None:
        block_size = 4096

    checksum = sha256()

    with open(file_name, "rb") as file_handle:
        block = file_handle.read(block_size)

        while block:
            checksum.update(block)
            block = file_handle.read(block_size)

    return checksum.hexdigest()


def sha256sums(basedir=None, block_size=None):
    """Yields (<sha256sum>, <file_name>) tuples
    for files within the basedir.
    """

    for file_path, file_name in list_files(basedir=basedir):
        yield (sha256sum(file_path, block_size=block_size), file_name)


def create_sha256_digest(basedir=None,
                         block_size=None,
                         outputdir=None,
                         individual=False):
    """Creates de sha256-digest file with a timestamp"""

    if outputdir is None:
        outputdir = getcwd()

    if individual is False:
        hash_file_name = strftime("sha256-digest_%Y%m%d-%H%M%S")
        hash_file_path = join(outputdir, hash_file_name)

        with open(hash_file_path, "w") as file_handle:
            for file_hash in sha256sums(basedir, block_size):
                file_handle.write(" *".join(file_hash) + "\n")
    else:
        for checksum, file_name in sha256sums(basedir, block_size):
            hash_file_name = file_name + ".sha256"
            hash_file_path = join(outputdir, hash_file_name)
            with open(hash_file_path, "w") as file_handle:
                file_handle.write(" *".join((checksum, file_name)) + "\n")


if __name__ == "__main__":
    from argparse import ArgumentParser, RawDescriptionHelpFormatter
    DESCRIPTION = "Creates a SHA-256 digest of files in a directory"
    EPILOG = """\
        example usage by developer
        --------------------------
        ls
            hello-world.txt  sha256digest.py

        cat hello-world.txt
            Hello, World!

        python sha256digest.py -i

        ls
            hello-world.txt  hello-world.txt.sha256  sha256digest.py

        cat hello-world.txt.sha256
            c98c24b677eff44860afea6f493bbaec5bb1c4cbb209c6fc2bbb47f66ff2ad31 *hello-world.txt


        example usage by end-user
        -------------------------
        ls
            hello-world.txt  hello-world.txt.sha256

        sha256sum -c hello-world.txt.sha256
            hello-world.txt: OK
        """
    PARSER = ArgumentParser(prog="sha256digest.py",
                            description=DESCRIPTION,
                            formatter_class=RawDescriptionHelpFormatter,
                            epilog=dedent(EPILOG))
    PARSER.add_argument("-i",
                        "--individual",
                        default=False,
                        action="store_true",
                        required=False,
                        help="outputs one hash file per file in folder")
    PARSER.add_argument("-d",
                        "--directory",
                        default=None,
                        type=str,
                        required=False,
                        help="path to the folder containing the files")
    PARSER.add_argument("-b",
                        "--blocksize",
                        default=None,
                        type=int,
                        required=False,
                        help="read files in chunks less than BLOCKSIZE bytes")
    PARSER.add_argument("-o",
                        "--outputdir",
                        default=None,
                        type=str,
                        required=False,
                        help="output directory for sha256 digest or files")
    ARGUMENTS = PARSER.parse_args()
    create_sha256_digest(basedir=ARGUMENTS.directory,
                         block_size=ARGUMENTS.blocksize,
                         outputdir=ARGUMENTS.outputdir,
                         individual=ARGUMENTS.individual)