python 编写一个函数统计语句中有多少个不同的单词, 根据每个单词ASCII码值的和对单词进行从小到大的排序，重复出现的单词只算一次的和，按行输出单词及对应的和

给定如下一段英文:

A major drawback of cross-network recommender solutions is that they can only be applied to users that are overlapped across networks. Thus, the non-overlapped users, which form the majority of users are ignored. As a solution, we propose CnGAN, a novel multi-task learning based recommend architecture。

import re


def func52(sen):
    list_1 = re.findall(r"[^\W\d_]+", sen)
    list_1 = list(set(list_1))
    print('有%d个不同的单词' % len(list_1))
    list_2 = []
    for i in list_1:
        res = 0
        temp_list = re.findall(r'\S', i)
        for j in temp_list:
            res = res + ord(j)
        list_2.append([i, res])
    list_1 = sorted(list_2, key=lambda x: x[1])
    for i in list_1:
        for j in i:
            print(j, end=' ')
        print()


if __name__ == "__main__":
    sentences = "A major drawback of cross-net