mirror of
https://github.com/xzb23/check_duplicate_files.git
synced 2026-11-22 01:04:40 +08:00
75 lines
2.7 KiB
Python
75 lines
2.7 KiB
Python
from _in_package import *
|
|
import config
|
|
import common
|
|
import runing_data
|
|
|
|
|
|
def traverse_dir(root_dir):
|
|
print("正在遍历文件ing...")
|
|
for path, dirs, files in os.walk(root_dir):
|
|
path = common.formatting_path(path)
|
|
for filename in files:
|
|
runing_data.file_path_list.append(path + filename)
|
|
print(f"完成\t总计 {len(runing_data.file_path_list)} 个文件")
|
|
|
|
|
|
def hash_files_from_glist(algorithm: function):
|
|
print("正在计算文件散列ing...")
|
|
i = 0
|
|
p_old_i = -1
|
|
for f_path in runing_data.file_path_list:
|
|
with open(f_path, "rb") as f:
|
|
f_hash = hashlib.file_digest(f, algorithm)
|
|
# runing_data.file_hash_results.append(runing_data.FileHashResult(f_path, f_hash.hexdigest(), algorithm.__name__))
|
|
runing_data.hash_to_files[(f_hash.hexdigest(), algorithm.__name__)].append(f_path)
|
|
i += 1
|
|
if i % config.wait_c == 0:
|
|
p_old_i = i
|
|
print(f"\r{i}/{len(runing_data.file_path_list)}", end="")
|
|
if p_old_i != -1 and i != p_old_i:
|
|
print(f"\r{i}/{len(runing_data.file_path_list)}", end="")
|
|
print()
|
|
|
|
|
|
|
|
def print_info(hash_to_files_list: list = runing_data.hash_to_files):
|
|
size_total = 0
|
|
size_if_one = 0
|
|
print_size_total = 0
|
|
print_size_if_one = 0
|
|
for t in runing_data.hash_to_files:
|
|
st_size = os.stat(runing_data.hash_to_files[t][0]).st_size
|
|
size_total += st_size * len(runing_data.hash_to_files[t])
|
|
size_if_one += st_size
|
|
if st_size <= config.flag_size:
|
|
continue
|
|
print_size_total += st_size * len(runing_data.hash_to_files[t])
|
|
print_size_if_one += st_size
|
|
if len(runing_data.hash_to_files[t]) > 1:
|
|
print(t, f"size: {st_size} Byte")
|
|
for fp in runing_data.hash_to_files[t]:
|
|
print("\t", fp)
|
|
print()
|
|
print(f"重复部分占用/总占用:\t{(size_total-size_if_one)//1024}KiB / {size_total//1024}KiB")
|
|
print(f"占用大于 {config.flag_size} Byte 的文件中,重复部分占用/总占用:\t{(print_size_total-print_size_if_one)//1024}KiB / {print_size_total//1024}KiB")
|
|
|
|
|
|
def reg_opts():
|
|
parser = argparse.ArgumentParser()
|
|
parser.add_argument("-P", "--path", default=None, required=False)
|
|
parser.add_argument("--fsize", default=None, required=False, help="只打印文件大小大于fsize Byte的重复文件")
|
|
args = parser.parse_args()
|
|
if args.path != None:
|
|
config.work_dir = args.path
|
|
if args.fsize != None:
|
|
config.flag_size = int(args.fsize)
|
|
|
|
reg_opts()
|
|
|
|
if not os.path.exists(config.work_dir):
|
|
exit(-1)
|
|
|
|
traverse_dir(config.work_dir)
|
|
hash_files_from_glist(hashlib.sha256)
|
|
|
|
print_info() |