问在Python3.6中保存/加载大型字符串集合(列表/集合)的最快方法是什么？

EN

import numpy as np

class IndexedBlob:
    def __init__(self, filename):
        index_filename = filename + '.index'
        blob = np.memmap(filename, mode='r')

        try:
            # if there is an existing index
            indices = np.memmap(index_filename, dtype='>i8', mode='r')
        except FileNotFoundError:
            # else, create it
            indices, = np.where(blob == ord('\n'))
            # force dtype to predictable file
            indices = np.array(indices, dtype='>i8')
            with open(index_filename, 'wb') as f:
                # add a virtual newline
                np.array(-1, dtype='>i8').tofile(f)
                indices.tofile(f)
            # then reopen it as a file to reduce memory
            # (and also pick up that -1 we added)
            indices = np.memmap(index_filename, dtype='>i8', mode='r')

        self.blob = blob
        self.indices = indices

    def __getitem__(self, line):
        assert line >= 0

        lo = self.indices[line] + 1
        hi = self.indices[line + 1]

        return self.blob[lo:hi].tobytes().decode()