sync.py

#!/usr/bin/env python
# -*- coding: utf-8 -*-

'''
This script is meant to perform one-directional sync
Duplicates of the same name and path will be overwritten.
!TODO
	- Check on Windows
	- removal of (some?) files, like *.tmp or .*
	- mask from sync for these kind of files
'''

from watchdog.observers import Observer
from watchdog.events import FileSystemEventHandler
import hashlib, shutil, time, os
import threading

waiting_time = 30 #I/O, download
repeat_time = 60
resync_interval = 3600

#src_dir = r"C:\path\to\dir1"
#dst_dir = r"C:\path\to\dir2"
src_dir = '/home/vasily/test1/'
dst_dir = '/home/vasily/test2/'

def get_file_hash(path, block_size=65536):
	sha = hashlib.sha256()
	try:
		with open(path, 'rb') as f:
			for block in iter(lambda: f.read(block_size), b''):
				sha.update(block)
		return sha.hexdigest()
	except Exception as e:
		print(f"Error hashing {path}: {e}")
		return None

def sync_file(src_path):
	rel_path = os.path.relpath(src_path, src_dir)
	dest_path = os.path.join(dst_dir, rel_path)

	src_hash = get_file_hash(src_path)
	if src_hash is None:
		return

	if os.path.exists(dest_path):
		dest_hash = get_file_hash(dest_path)
		if dest_hash == src_hash:
			print(f"Skipped (already exists with same content): {rel_path}")
			return
		else:
			print(f"Already exists, content differs, overwriting: {rel_path}")

	os.makedirs(os.path.dirname(dest_path), exist_ok=True)
	shutil.copy2(src_path, dest_path)
	print(f"Copied: {src_path} -> {dest_path}")

def full_resync():
	print("🔁 Running full resync...")
	for root, _, files in os.walk(src_dir):
		for fname in files:
			full_path = os.path.join(root, fname)
			sync_file(full_path)
	print("✅ Full resync completed.")
	
def periodic_resync():
	while not stop_event.is_set():
		if stop_event.wait(timeout=waiting_time):
			break
		time.sleep(resync_interval)
		full_resync()
		
class FileHandler(FileSystemEventHandler):
	def on_created(self, event):
		if not event.is_directory: #empty subdir will not be copied?
			time.sleep(waiting_time)
			sync_file(event.src_path)

stop_event = threading.Event()

observer = Observer()
observer.schedule(FileHandler(), path=src_dir, recursive=True)
observer.start()
print("Watching for new files...")

# Initial full sync
full_resync()

resync_thread = threading.Thread(target=periodic_resync)
resync_thread.start()

try:
	while True:
		time.sleep(repeat_time)
except KeyboardInterrupt:
	print("🛑 Stopping...")
	observer.stop()
	stop_event.set()
	resync_thread.join()
	observer.join()
	print("✅ Stopped cleanly.")
	
observer.join()