最大正向匹配分词法报错求解

Question

# -*- coding: utf-8 -*-
import codecs
import xlrd2
def read_dic(dic_path):
    words_dic=xlrd2.open_workbook(dic_path)
    #打开工作簿，也就是词表
    sheet=words_dic.sheets()[0]
    dic_list=list(sheet.col_values(1))[1:]
    #通过遍历找出每一列的数据，括号里面的代表只取第几列的值
    return dic_list
#完成字典词表的输入
def read_file(file_path):
    with codecs.open(file_path,"r",encoding="utf8")as f:
        file=f.readlines()
        return file
#完成被处理的文件的输入
def cut_word(raw_sentences,word_dic):
 #设一个切词的函数
    max_length=max(len(word) for word in word_dic)
    new_cut=[]
    #建一个新的空白集合，留着装新切的词
    for sentence in raw_sentences:
        sentence=sentence.strip()
     #把句子两边的空格都删掉
        sent_length=len(sentence)
        cut_word_list=[]
        while sent_length>0:
            cut_length=(min(sent_length,max_length))
            for i in range(cut_length,0,-1):
                #从0到cut_length的范围，步数为-1，即每次都减少1
                new_word = [sent_length]
                if new_word in word_dic:
                    new_cut.append(new_word)#如果切的新词在词典里面有，就把它放进新集合里
                    cut_length=cut_length-i
                    break
                elif i==1:
                    new_cut.append(new_word)
                    sent_length=sent_length-1
        words='/'.join(str(cut_word_list))
        new_cut.append(words.lstrip('/'))
    return  new_cut
def out_file(out_path,sentences):
    with codecs.open(out_path,'a','utf8')as f:
        for sentence in sentences:
            f.write(sentence)
def main():
    file_path=r"C:\Users\Apple\Desktop\7.txt"
    file=read_file(file_path)
    dic_path=r"C:\Users\Apple\Desktop\词表.xlsx"
    words_dic=read_dic(dic_path)
    content_cut=cut_word(file,words_dic)
    out_path=r"C:\Users\Apple\Desktop\分词结果.txt"
    out_file(out_path,content_cut)
if __name__ == '__main__':
    main()



File "C:/Users/Apple/AppData/Roaming/JetBrains/PyCharmCE2020.3/scratches/正向最大匹配运算.py", line 33, in cut_word
    if new_word in word_dic:
TypeError: 'in <string>' requires string as left operand, not list

请教大家，出现这种报错怎么办呀

Answer 1

31行的new_word = [sent_length]，是创建new_word为list。如果想看new_word是否为word_dic的子集，需要循环new_word，确认是否每个元素都在word_dic中，或者使用set()。     没有细看你的代码，但感觉你31行的代码想要实现的，应该是new_word=sentence[i] 这样的。