注意:使用前先要下载搜狗词库
# -*- coding:utf-8 -*- #写了一个简单的支持中文的正向最大匹配的机械分词,其它不用解释了,就几十行代码 #附:搜狗词库下载地址:http://vdisk.weibo.com/s/7RlE5 import string __dict = {} def load_dict(dict_file='words.dic'): #加载词库,把词库加载成一个key为首字符,value为相关词的列表的字典 words = [unicode(line, 'utf-8').split() for line in open(dict_file)] for word_len, word in words: first_char = word[0] __dict.setdefault(first_char, []) __dict[first_char].append(word) #按词的长度倒序排列 for first_char, words in __dict.items(): __dict[first_char] = sorted(words, key=lambda x:len(x), reverse=True) def __match_ascii(i, input): #返回连续的英文字母,数字,符号 result = '' for i in range(i, len(input)): if not input[i] in string.ascii_letters: break result += input[i] return result def __match_word(first_char, i , input): #根据当前位置进行分词,ascii的直接读取连续字符,中文的读取词库 if not __dict.has_key(first_char): if first_char in string.ascii_letters: return __match_ascii(i, input) return first_char words = __dict[first_char] for word in words: if input[i:i+len(word)] == word: return word return first_char def tokenize(input): #对input进行分词,input必须是uncode编码 if not input: return [] tokens = [] i = 0 while i
查看更多关于用几十行代码实现python中英文分词的详细内容...
声明:本文来自网络,不代表【好得很程序员自学网】立场,转载请注明出处:http://www.haodehen.cn/did86801