From c75d875a27f63a48d4bed171d852d5364729f7d0 Mon Sep 17 00:00:00 2001 From: "Antonio J. Delgado" Date: Wed, 25 Jan 2023 14:53:35 +0200 Subject: [PATCH] use crc --- find_duplicate_files/find_duplicate_files.py | 7 +++---- 1 file changed, 3 insertions(+), 4 deletions(-) diff --git a/find_duplicate_files/find_duplicate_files.py b/find_duplicate_files/find_duplicate_files.py index ecafbe0..d374c9b 100644 --- a/find_duplicate_files/find_duplicate_files.py +++ b/find_duplicate_files/find_duplicate_files.py @@ -11,7 +11,7 @@ import logging import click import click_config_file from logging.handlers import SysLogHandler -import hashlib +import zlib class find_duplicate_files: @@ -45,11 +45,10 @@ class find_duplicate_files: for file in os.scandir(path): if not file.name.startswith('.'): if file.is_file(): - hash = hashlib.sha256() with open(file.path, 'rb') as file_pointer: file_content = file_pointer.read() - hash.update(file_content) - files[hash.hexdigest()] = file.path + hash = zlib.adler32(file_content) + files[hash] = file.path elif file.is_dir(follow_symlinks=False): more_files = self.recursive_scandir( file.path,