Python script to check whether all the files found anywhere in the source directory are also found somewhere in the dest directory. I use it for, e.g., cleaning up after importing mp3's or photos using a program that changes directory layouts. Checks identity using either md5sum or filename. Run with "--help" for usage.

check_inclusion.py

#!/usr/bin/env python3.2

import os
import sys
import hashlib
import argparse
from functools import partial

def md5sum(filename):
    # http://stackoverflow.com/a/7829658
    with open(filename, mode='rb') as fh:
        d = hashlib.md5()
        for buf in iter(partial(fh.read, 128), b''):
            d.update(buf)
    return d.hexdigest()

def build_md5_tree(directory):
    checksums = {}
    for root, dirs, files in os.walk(directory):
        for filename in files:
            path = os.path.join(root, filename)
            checksums[md5sum(path)] = path
    return checksums

def build_name_tree(directory):
    names = {}
    for root, dirs, files in os.walk(directory):
        for filename in files:
            path = os.path.join(root, filename)
            names[filename] = path
    return names

def find_missing_files(srces, dests, strategy):
    for directories in (srces, dests):
        for directory in directories:
            if not os.path.exists(directory) and os.path.isdir(directory):
                return "{0} is not a directory.".format(directory), []
    if strategy == "names":
        method = build_name_tree
    elif strategy == "md5":
        method = build_md5_tree
    src_tree = {}
    for src in srces:
        src_tree.update(method(src))
    dest_tree = {}
    for dest in dests:
        dest_tree.update(method(dest))
    missing = []
    for checksum, path in src_tree.items():
        if checksum not in dest_tree:
            missing.append((path, checksum))
    return (None, missing)

def run():
    parser = argparse.ArgumentParser(description="Checks to see whether every file descendant of the `src` directory is found somewhere in the `dest` directory or its descendants.")
    parser.add_argument("src", nargs=1, help="Source directory, the contents of which will be sought in the dest directory.")
    parser.add_argument("dest", nargs=1, help="Destination directory, the contents of which will be checked for the files from source directory.")
    parser.add_argument("--names", help="Use names instead of md5 sums.", action='store_const', const=True)
    args = parser.parse_args()

    if args.names:
        strategy = "names"
    else:
        strategy = "md5"

    (error, missing) = find_missing_files(args.src, args.dest, strategy)
    if error:
        sys.stderr.write(error + "\n")
        sys.exit(1)
    elif missing:
        missing.sort()
        sys.stderr.write("Missing files found.\n")
        for path, checksum in missing:
            print(checksum, path)
    else:
        sys.stderr.write("No missing files found.\n")

if __name__ == "__main__":
    run()