正向最大匹配
【python|python正向最大匹配分词和逆向最大匹配分词】
# -*- 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 wordListdef 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 wordListdef 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()推荐阅读
- 推荐系统论文进阶|CTR预估 论文精读(十一)--Deep Interest Evolution Network(DIEN)
- Python专栏|数据分析的常规流程
- Python|Win10下 Python开发环境搭建(PyCharm + Anaconda) && 环境变量配置 && 常用工具安装配置
- Python绘制小红花
- Pytorch学习|sklearn-SVM 模型保存、交叉验证与网格搜索
- OpenCV|OpenCV-Python实战（18）——深度学习简介与入门示例
- python|8. 文件系统——文件的删除、移动、复制过程以及链接文件
- 爬虫|若想拿下爬虫大单，怎能不会逆向爬虫，价值过万的逆向爬虫教程限时分享
- 分布式|《Python3网络爬虫开发实战（第二版）》内容介绍
- java|微软认真聆听了开源 .NET 开发社区的炮轰（ 通过CLI 支持 Hot Reload 功能）