Python中使用md5sum检查目录中相同文件代码分享

2019-10-05 09:50:27于海丽

            else:
                d[checksum] = [name]

    return d


def check_pairs(names):
    """Checks whether any in a list of files differs from the others.

    names: list of string filenames
    """
    for name1 in names:
        for name2 in names:
            if name1 < name2:
                res, stat = check_diff(name1, name2)
                if res:
                    return False
    return True


def print_duplicates(d):
    """Checks for duplicate files.

    Reports any files with the same checksum and checks whether they
    are, in fact, identical.

    d: map from checksum to list of files with that checksum
    """
    for key, names in d.iteritems():
        if len(names) > 1:
            print 'The following files have the same checksum:'
            for name in names:
                print name

            if check_pairs(names):
                print 'And they are identical.'


if __name__ == '__main__':
    d = compute_checksums(dirname='.', suffix='.py')
    print_duplicates(d)