【习题1】利用Python分离文件中的英文和中文(3)

优化了一下【习题1】利用Python分离文件中的英文和中文(2)帖子里的代码，并附上了思路的图片

c_list = []
e_list = []
c_index_dict = {}
e_sum_dict = {}


def read_data(file_path):
    with open(file_path, "r", encoding="utf-8") as f:
        all_data = f.readlines()

        for i in all_data:
            data_s = i.split()
            if len(data_s) == 2:
                e_list.append(data_s[0])
                c_list.append(data_s[1])
            else:
                continue

        for j in "".join(c_list):
            if j in c_index_dict:
                continue
            else:
                c_index_dict[j] = len(c_index_dict) + 1

        for k in "".join(e_list):
            if k in e_sum_dict:
                e_sum_dict[k] += 1
            else:
                e_sum_dict[k] = 1



read_data("NLP basic\\data\\test.txt")
print(c_list)
print(e_list)
print(c_index_dict)
print(e_sum_dict)

all_data

i

data_s

len(data_s)

c_list
e_list

j

c_index_dict

k

e_sum_dict