中文分词算法：逆向最大匹配法

南京市
南京市长
长江大桥
人民解放军
大桥

#逆向最大匹配
class RMM(object):
    def __init__(self, dic_path):
        self.dictionary = set()
        self.maximum = 0
        #读取词典
        with open(dic_path, 'r', encoding='utf8') as f:
            for line in f:
                #移除字符串头尾指定的字符（默认为空格或换行符）或字符序列
                line = line.strip()
                if not line:
                    continue
                self.dictionary.add(line)
                if len(line) > self.maximum:
                    self.maximum = len(line)
    def cut(self, text):
        result = []
        index = len(text)
        while index > 0:
            word = None
            # 语法 range(start, stop[, step])
            for size in range(self.maximum, 0, -1):
                # 切片开始位置：index - size
                if index - size < 0:
                    continue
                #逆向切片
                piece = text[(index - size):index]
                if piece in self.dictionary:
                    word = piece
                    result.append(word)
                    index -= size
                    break
            if word is None:
                index -= 1
        return result[::-1]

def main():
    text = "南京市长江大桥"
    tokenizer = RMM('./data/rmm_dic.utf8')
    print(tokenizer.cut(text))

main()

['南京市', '长江大桥']