#!/usr/bin/env python3
"""Find duplicate files by content hash.
Run: python3 duplicate_finder.py <directory> [max_depth=2]
"""
import hashlib
import os
import sys
from collections import defaultdict
from pathlib import Path


def hash_file(path, algo="sha256", blocksize=65536):
    h = hashlib.new(algo)
    with open(path, "rb") as f:
        for block in iter(lambda: f.read(blocksize), b""):
            h.update(block)
    return h.hexdigest()


def find_duplicates(root_dir, max_depth=2):
    root = Path(root_dir)
    hashes = defaultdict(list)
    
    for p in root.rglob("*"):
        if not p.is_file():
            continue
        if p.name.startswith(".") or p.name.startswith("__pycache__"):
            continue
        
        depth = len(p.relative_to(root).parts) - 1
        if depth > max_depth:
            continue
        
        try:
            h = hash_file(p)
            hashes[h].append(str(p))
        except (PermissionError, OSError) as e:
            print(f"SKIP: {p}: {e}", file=sys.stderr)
    
    return {h: paths for h, paths in hashes.items() if len(paths) > 1}


def main():
    if len(sys.argv) < 2:
        print("Usage: python3 duplicate_finder.py <directory> [max_depth=2]", file=sys.stderr)
        sys.exit(1)
    
    root_dir = sys.argv[1]
    max_depth = int(sys.argv[2]) if len(sys.argv) > 2 else 2
    
    if not os.path.isdir(root_dir):
        print(f"Error: {root_dir} is not a directory", file=sys.stderr)
        sys.exit(1)
    
    dups = find_duplicates(root_dir, max_depth)
    
    if dups:
        print(f"Found {len(dups)} duplicate group(s):")
        for h, paths in dups.items():
            print(f"\n[hash: {h[:12]}...]")
            for p in sorted(paths):
                try:
                    size = os.path.getsize(p)
                    print(f"  {p} ({size} bytes)")
                except OSError:
                    print(f"  {p}")
    else:
        print(f"No duplicates found in {root_dir} (depth <= {max_depth})")


if __name__ == "__main__":
    main()