正向最大匹配
# -*- coding:utf-8 -*- CODEC='utf-8' def u(s, encoding): 'converted other encoding to unicode encoding' if isinstance(s, unicode): return s else: return unicode(s, encoding) def fwd_mm_seg(wordDict, maxLen, str): 'forward max match segment' wordList = [] segStr = str segStrLen = len(segStr) for word in wordDict: print 'word: ', word print "\n" while segStrLen > 0: if segStrLen > maxLen: wordLen = maxLen else: wordLen = segStrLen subStr = segStr[0:wordLen] print "subStr: ", subStr while wordLen > 1: if subStr in wordDict: print "subStr1: %r" % subStr break else: print "subStr2: %r" % subStr wordLen = wordLen - 1 subStr = subStr[0:wordLen] # print "subStr3: ", subStr wordList.append(subStr) segStr = segStr[wordLen:] segStrLen = segStrLen - wordLen for wordstr in wordList: print "wordstr: ", wordstr return wordList def main(): fp_dict = open('words.dic') wordDict = {} for eachWord in fp_dict: wordDict[u(eachWord.strip(), 'utf-8')] = 1 segStr = u'你好世界hello world' print segStr wordList = fwd_mm_seg(wordDict, 10, segStr) print "==".join(wordList) if __name__ == '__main__': main()
逆向最大匹配
# -*- coding:utf-8 -*- def u(s, encoding): 'converted other encoding to unicode encoding' if isinstance(s, unicode): return s else: return unicode(s, encoding) CODEC='utf-8' def bwd_mm_seg(wordDict, maxLen, str): 'forward max match segment' wordList = [] segStr = str segStrLen = len(segStr) for word in wordDict: print 'word: ', word print "\n" while segStrLen > 0: if segStrLen > maxLen: wordLen = maxLen else: wordLen = segStrLen subStr = segStr[-wordLen:None] print "subStr: ", subStr while wordLen > 1: if subStr in wordDict: print "subStr1: %r" % subStr break else: print "subStr2: %r" % subStr wordLen = wordLen - 1 subStr = subStr[-wordLen:None] # print "subStr3: ", subStr wordList.append(subStr) segStr = segStr[0: -wordLen] segStrLen = segStrLen - wordLen wordList.reverse() for wordstr in wordList: print "wordstr: ", wordstr return wordList def main(): fp_dict = open('words.dic') wordDict = {} for eachWord in fp_dict: wordDict[u(eachWord.strip(), 'utf-8')] = 1 segStr = ur'你好世界hello world' print segStr wordList = bwd_mm_seg(wordDict, 10, segStr) print "==".join(wordList) if __name__ == '__main__': main()
以上这篇python正向最大匹配分词和逆向最大匹配分词的实例就是小编分享给大家的全部内容了,希望能给大家一个参考,也希望大家多多支持。
免责声明:本站文章均来自网站采集或用户投稿,网站不提供任何软件下载或自行开发的软件!
如有用户或公司发现本站内容信息存在侵权行为,请邮件告知! 858582#qq.com
金钱帮资源网 Copyright www.kbjia.com
暂无“python正向最大匹配分词和逆向最大匹配分词的实例”评论...
更新日志
2024年10月07日
2024年10月07日
- 群星《前途海量 电影原声专辑》[FLAC/分轨][227.78MB]
- 张信哲.1992-知道新曲与精丫巨石】【WAV+CUE】
- 王翠玲.1995-ANGEL【新艺宝】【WAV+CUE】
- 景冈山.1996-我的眼里只有你【大地唱片】【WAV+CUE】
- 群星《八戒 电影原声带》[320K/MP3][188.97MB]
- 群星《我的阿勒泰 影视原声带》[320K/MP3][139.47MB]
- 纪钧瀚《胎教古典音乐 钢琴与大提琴的沉浸时光》[320K/MP3][148.91MB]
- 刘雅丽.2001-丽花皇后·EMI精选王【EMI百代】【FLAC分轨】
- 齐秦.1994-黄金十年1981-1990CHINA.TOUR.LIVE精丫上华】【WAV+CUE】
- 群星.2008-本色·百代音乐人创作专辑【EMI百代】【WAV+CUE】
- 群星.2001-同步过冬AVCD【环球】【WAV+CUE】
- 群星.2020-同步过冬2020冀待晴空【环球】【WAV+CUE】
- 沈雁.1986-四季(2012梦田复刻版)【白云唱片】【WAV+CUE】
- 纪钧瀚《胎教古典音乐 钢琴与大提琴的沉浸时光》[FLAC/分轨][257.88MB]
- 《国语老歌 怀旧篇 3CD》[WAV/分轨][1.6GB]