checksum generation

check.py

import hashlib

def md5sum(source_path, chunk_size=8388608):
    md5s = []
    with open(source_path,'rb') as fp:
        while True:
            data = fp.read(chunk_size)
            if not data:
                break
            md5s.append(hashlib.md5(data))

    if len(md5s) == 1:
        return '"%s"' % (md5s[0].hexdigest())

    digests = b"".join(m.digest() for m in md5s)
    new_md5 = hashlib.md5(digests)
    new_etag = '"%s-%s"' % (new_md5.hexdigest(),len(md5s))
    return new_etag