sync.py

import hashlib
import os
import shutil
from pathlib import Path


def hash_file(path):
    hasher = hashlib.sha1()
    with path.open("rb") as file:
        while buf:= file.read(hasher.block_size):
            hasher.update(buf)
    return hasher.hexdigest()


def sync(source, dest):
    # Walk the source folder and build a dict of filenames and their hashes
    source_hashes = {}
    for folder, _, files in os.walk(source):
        for fn in files:
            source_hashes[hash_file(Path(folder) / fn)] = fn

    seen = set()  # Keep track of the files we've found in the target

    # Walk the target folder and get the filenames and hashes
    for folder, _, files in os.walk(dest):
        for fn in files:
            dest_path = Path(folder) / fn
            dest_hash = hash_file(dest_path)
            seen.add(dest_hash)

            # if there's a file in target that's not in source, delete it
            if dest_hash not in source_hashes:
                dest_path.remove()

            # if there's a file in target that has a different path in source,
            # move it to the correct path
            elif dest_hash in source_hashes and fn != source_hashes[dest_hash]:
                shutil.move(dest_path, Path(folder) / source_hashes[dest_hash])

    # for every file that appears in source but not target, copy the file to
    # the target
    for src_hash, fn in source_hashes.items():
        if src_hash not in seen:
            shutil.copy(Path(source) / fn, Path(dest) / fn)

test_sync.py

import tempfile
from pathlib import Path
import shutil
from sync import sync


# integration tests

def test_when_a_file_exists_in_the_source_but_not_the_destination():
    try:
        source = tempfile.mkdtemp()
        dest = tempfile.mkdtemp()

        content = "I am a very useful file"
        (Path(source) / 'my-file').write_text(content)

        sync(source, dest)

        expected_path = Path(dest) /  'my-file'
        assert expected_path.exists()
        assert expected_path.read_text() == content

    finally:
        shutil.rmtree(source)
        shutil.rmtree(dest)


def test_when_a_file_has_been_renamed_in_the_source():
    try:
        source = tempfile.mkdtemp()
        dest = tempfile.mkdtemp()

        content = "I am a file that was renamed"
        source_path = Path(source) / 'source-filename'
        old_dest_path = Path(dest) / 'dest-filename'
        expected_dest_path = Path(dest) / 'source-filename'
        source_path.write_text(content)
        old_dest_path.write_text(content)

        sync(source, dest)

        assert old_dest_path.exists() is False
        assert expected_dest_path.read_text() == content


    finally:
        shutil.rmtree(source)
        shutil.rmtree(dest)