How to Find Duplicate Files by Size and Hash in Python

import hashlib
from pathlib import Path

def hash_file(path, chunk_size=8192):
    hasher = hashlib.md5()
    with open(path, 'rb') as f:
        while chunk := f.read(chunk_size):
            hasher.update(chunk)
    return hasher.hexdigest()

def find_duplicates(directory):
    size_map = {}
    for path in Path(directory).rglob('*'):
        if path.is_file():
            size = path.stat().st_size
            size_map.setdefault(size, []).append(path)
    
    hash_map = {}
    for size, paths in size_map.items():
        if len(paths) > 1:
            for path in paths:
                file_hash = hash_file(path)
                hash_map.setdefault((size, file_hash), []).append(path)
    
    duplicates = []
    for paths in hash_map.values():
        if len(paths) > 1:
            duplicates.append(paths)
    return duplicates

if __name__ == "__main__":
    test_dir = Path("/tmp/test_duplicates")
    test_dir.mkdir(exist_ok=True)
    (test_dir / "file1.txt").write_text("same content")
    (test_dir / "file2.txt").write_text("same content")
    (test_dir / "file3.txt").write_text("different")
    
    result = find_duplicates(test_dir)
    for group in result:
        print([str(p) for p in group])