inference
90482e42d7
Add functionality for the duplicate scanner. This uses the previously-implemented code to derive SHA-256-based hashes and detect duplicates before deleting them. Arguments are provided for a dry-run mode and directory selection.
46 lines
1.4 KiB
Python
46 lines
1.4 KiB
Python
#!/usr/bin/env python
|
|
|
|
# Duplicate Check
|
|
# Version: 0.15.0
|
|
|
|
# Copyright 2025 Jake Winters
|
|
# SPDX-License-Identifier: BSD-3-Clause
|
|
|
|
|
|
import os
|
|
import hashlib
|
|
import argparse
|
|
|
|
|
|
parser = argparse.ArgumentParser(description='Scan directory for duplicate files and delete them.')
|
|
parser.add_argument('--dry-run', '-d', action='store_true', help='Detect duplicates without deletion.')
|
|
parser.add_argument('directory', type=str, help='The directory to scan for duplicate files.')
|
|
args = parser.parse_args()
|
|
|
|
|
|
def hash_file(file_path):
|
|
sha256_hash = hashlib.sha256()
|
|
with open(file_path, 'rb') as f:
|
|
for byte_block in iter(lambda: f.read(65536), b''):
|
|
sha256_hash.update(byte_block)
|
|
return sha256_hash.hexdigest()
|
|
|
|
def find_and_delete_duplicates(directory, dry_run):
|
|
os.chdir(directory)
|
|
file_hashes = {}
|
|
for file in os.listdir():
|
|
file_path = os.path.abspath(file)
|
|
if os.path.isfile(file_path):
|
|
file_hash = hash_file(file_path)
|
|
if file_hash in file_hashes:
|
|
if not dry_run:
|
|
os.remove(file_path)
|
|
print(f"Duplicate detected: {file_path}")
|
|
if not dry_run:
|
|
print(f"Duplicate deleted: {file_path}")
|
|
else:
|
|
file_hashes[file_hash] = file_hash
|
|
os.chdir('..')
|
|
|
|
find_and_delete_duplicates(args.directory, args.dry_run)
|