双向最大匹配法分词

# -*- coding: utf-8 -*-

class  BiMM():
    def __init__(self):
        self.window_size = 3#字典中最长词数

    def MMseg(self, text):
        result = []
        index = 0
        text_length = len(text)
        dict = ['研究', '研究生', '生命', '命', '的', '起源']
        while text_length > index:
            for size in range(self.window_size+index, index, -1):
                piece = text[index:size]
                if piece in dict:
                    index = size - 1
                    break
            index += 1
            result.append(piece)
        return result

    def RMMseg(self, text):
        result = []
        index = len(text)
        dict = ['研究', '研究生', '生命', '命', '的', '起源']
        while index > 0:
            for size in range(index-self.window_size, index):
                piece = text[size:index]
                if piece in dict:
                    index = size + 1
                    break
            index = index - 1
            result.append(piece)
        result.reverse()
        return result

    def main(self, text, r1, r2):
        if len(r1) > len(r2):#正向、逆向分词结果词数不同，取分词数量少的
            print(r2)
        elif len(r1) < len(r2):
            print(r1)
        else:#词数相同
            num1 = len(list(filter(lambda s: isinstance(s, str) and len(s) == 1, r1)))#filter()用于过滤，提取列表中长度为1的字符
            num2 = len(list(filter(lambda s: isinstance(s, str) and len(s) == 1, r2)))
            if num1 == num2:
                print(r1)#分词结果相同，可返回任意一个
            elif num1 > num2:#结果不同，返回单字个数少的
                print(r2)
            else:
                print(r1)

if __name__ == '__main__':
    text = '研究生命的起源'
    tokenizer = BiMM()
    r1 = tokenizer.MMseg(text)#['研究生', '命', '的', '起源']
    r2 = tokenizer.RMMseg(text)#['研究', '生命', '的', '起源']
    tokenizer.main(text, r1, r2)#['研究', '生命', '的', '起源']