Checking the data integrity on t

日常需要传递几G或者十几G的fastq数据，在cp或者rysnc完后，是需要对复制的数据进行md5码检验的。本文先获取源文件md5码再获取目标文件md5码，最后检验两者是否一致，从而判断复制是否完整。更多知识分享请到 https://zouhua.top/。

获取md5码

md5sum  RawData/filename > RawData_md5sum.tsv 
md5sum  Rename/filename > Rename_md5sum.tsv 

主程序

#!/usr/bin/python

import sys
import re
import os
import argparse as ap


def parse_argument(args):
    parser = ap.ArgumentParser(description='check')
    parser.add_argument('-f1', '--file1', metavar='<file1>', type=str)
    parser.add_argument('-f2', '--file2', metavar='<file2>', type=str)
    parser.add_argument('-o', '--out', metavar='<out>', type=str)

    return parser.parse_args()


def main():
    args = parse_argument(sys.argv)

    dict_f1 = {}
    with open(args.file1, 'r') as f:
        lines = f.readlines()
    for line in lines:
        line = line.strip().split()
        dict_f1[line[0]] = line[1]
    out_f = open(args.out, 'w')
    with open(args.file2, 'r') as f2:
        lines2 = f2.readlines()
    for line2 in lines2:
        line2 = line2.strip().split()
        if line2[0] in dict_f1.keys():
            res = "\t".join([line2[1], dict_f1[line2[0]], str(line2[0]), "Correct"])
            out_f.write(res + "\n")
        else:
            res = "\t".join([line2[1], line[0], "Wrong"])
            out_f.write(res + "\n")
    out_f.close()


main()

运行

python check_md5.py -f1 RawData_md5sum.tsv -f2 Rename_md5sum.tsv  -o Checkout_md5.tsv