A simple script to compare states between to time, and return it's file difference

get_fdiff.py

import os
import sys
import argparse
import logging
import pickle
from pathlib import Path
import fnmatch

from watchdog.utils.dirsnapshot import DirectorySnapshot, DirectorySnapshotDiff

path_this = os.path.abspath(os.path.dirname(__file__))
path_run = os.path.abspath('.')
path_snapshot = os.path.join(path_run, '.sns.pkl') 
sys.path.append(path_this)

logger = logging.getLogger ('snapshot')
logger.setLevel (logging.DEBUG)

formatter = logging.Formatter (
        '%(asctime)s - %(name)s - %(levelname)s - %(message)s'
    )
ch = logging.StreamHandler ()
ch.setLevel (logging.DEBUG)
ch.setFormatter (formatter)
logger.addHandler (ch)

def get_diff(path, 
        path_snapshot=path_snapshot,
        w_save=False):

    # make it absolute, so it can safely being dumped
    path = os.path.abspath(path)

    logger.debug('Creating snapshot for {}'.format(path))
    new_snapshot = DirectorySnapshot(path)

    # check old snapshot, find diff if exist
    if Path(path_snapshot).is_file():
        logger.debug('Old snapshot exist')
        with open(path_snapshot, 'rb') as f_:
            old_path, old_snapshot = pickle.load(f_)

        if not os.path.samefile(old_path, path):
            logger.warning("Old snapshot is differ from current path, aborting")
            logger.warning("Delete the old snapshot first")
            return []

        diff = DirectorySnapshotDiff(old_snapshot, new_snapshot)
        logger.debug("Found {} new created, {} modified".format(
                len(diff.files_created), len(diff.files_modified)
            ))
        final_data = diff.files_created + diff.files_modified
        final_data += [_[1] for _ in diff.files_moved]

    else:
        logger.warning("Old snapshot doesn't exist")
        final_data = []

    # saving
    if w_save:
        logger.debug("Saving current snapshot to {}".format(path_snapshot))
        with open(path_snapshot, 'wb') as f_:
            pickle.dump((path, new_snapshot), f_)

    return final_data

def parse_args():
    parser = argparse.ArgumentParser(description='Get list of modified files')
    parser.add_argument('path', type=str, help='The path (relative or absoulte) to the directory need to process')
    parser.add_argument('-s', '--snapshot', help='Using this snapshot as comparison, default .sns.pkl', default=path_snapshot, dest='path_snapshot')
    parser.add_argument('-d', '--dry', help='Do not save after comparing snapshot', action='store_false', dest='w_save')
    parser.add_argument('--log-level', choices=['debug', 'none'], default='none', help='Log level of the program')
    parser.add_argument('-m', '--match', help='Match based on this pattern using glob, default *', default='*', dest='pattern')
    args = parser.parse_args()
    return vars(args)

if __name__ == '__main__':
    args = parse_args()

    log_level = args.pop('log_level')
    if log_level.lower() == 'none':
        logger.handlers.clear()

    pattern = args.pop('pattern')

    diff = get_diff(**args)
    diff = fnmatch.filter(diff, pattern)

    if diff: print('\n'.join(diff))