对文章进行切分

# -*- coding: utf-8 -*-
import sys
reload(sys)
sys.setdefaultencoding('gbk')


def  replacetxt(fname,char,char1):

 f=file(fname,'r')
 string=f.read()
 line1=string.split(char)
 f=file(fname,'w+')
 
 for i in line1:
   f.write(i+chr(10)+char1+chr(10)+chr(10))
   #print i+"ok"
   #print char

 f.close()


def  cuttxt(fname,char):

 f=file(fname,'r')
 string=f.read()
 
 line1=string.split(char)
 f=file(fname,'w+')
 for i in line1:
   if  len(i)>1:
       #print i[0:7]
       if  not  i[0:7]=="       ":
             print i[0:7]
             f.write(i+chr(10)+"       "+char+"       "+chr(10))
       else:
             f.write(i+chr(10))
   #print i+"ok"
   #print char

 f.close()


def  cuttxtline(fname,char):

 f=file(fname,'r')
 string=f.read()
 
 line1=string.split(char)
 f=file(fname,'w+')
 for i in line1:
   if  len(i)>1:
       #print i[0:7]
       if  not  i[0:7]=="       ":
             print i[0:7]
             f.write(i+chr(10)+"       "+char+"       "+chr(10))
       else:
             f.write(i+chr(10))
   #print i+"ok"
   #print char

 f.close()


import shutil
import os


shutil.copy('readme.txt', 'test.txt') #复制文件






def  fuhaoconghoufenge(fname,char):#从分隔符后面切

 f=file(fname,'r')
 string=f.read()
 
 line1=string.split(char)
 f=file(fname,'w+')
 for i in line1:
   if  len(i)>1:
       
             f.write(i.strip()+char+chr(10))

   #print i+"ok"
   #print char

 f.close()

def  fuhaocongqianhoufenge(fname,char):#从分隔符后面切

 f=file(fname,'r')
 string=f.read()
 
 line1=string.split(char)
 f=file(fname,'w+')
 for i in line1:
   if  len(i)>1:
       
             f.write(i.strip()+chr(10)+char+chr(10))

   #print i+"ok"
   #print char

 f.close()



def  fuhaofengedel(fname,char): #分隔符 去掉，不要了

 f=file(fname,'r')
 string=f.read()
 
 line1=string.split(char)
 f=file(fname,'w+')
 for i in line1:
   if  len(i)>1:
       
             f.write(i.strip()+chr(10))

   #print i+"ok"
   #print char

 f.close()

def  hebing(fname,char1,char2): #分隔符 去掉，不要了

 f=file(fname,'r')
 string=f.read()
 
 line1=string.split(char1+chr(10)+char2)
 f=file(fname,'w+')
 for i in line1:
   if  len(i)>1:
       
             f.write(i.strip()+chr(10)+char1+char2+chr(10))

   #print i+"ok"
   #print char

 f.close()



def lianggecidoubufenkai(fname,char1,char2):

  fuhaocongqianhoufenge(fname,char2)
  hebing(fname,char1,char2)




#s =unicode(str1)  # 将中英文统一成 一个字符， 然后开始处理

#for i  in  range(len(s)+1):

              
            
#         print s[i:i+1]







fuhaofengedel('test.txt','、')

fuhaofengedel('test.txt','（')
fuhaofengedel('test.txt','）')

fuhaofengedel('test.txt','(')
fuhaofengedel('test.txt',')')

fuhaofengedel('test.txt','：')

fuhaofengedel('test.txt','-')

fuhaofengedel('test.txt','“')
fuhaofengedel('test.txt','”')
fuhaofengedel('test.txt',' ')


fuhaocongqianhoufenge('test.txt',',')
fuhaocongqianhoufenge('test.txt','，')
fuhaocongqianhoufenge('test.txt','。')
fuhaocongqianhoufenge('test.txt','是')   #无歧义，或者很少有歧义
fuhaocongqianhoufenge('test.txt','的')
fuhaocongqianhoufenge('test.txt','这些')
fuhaocongqianhoufenge('test.txt','然后')
fuhaocongqianhoufenge('test.txt','利用')
fuhaocongqianhoufenge('test.txt','一个')
fuhaocongqianhoufenge('test.txt','含有')
fuhaocongqianhoufenge('test.txt','例如')
fuhaocongqianhoufenge('test.txt','用来')
fuhaocongqianhoufenge('test.txt','它')
fuhaocongqianhoufenge('test.txt','描述')
fuhaocongqianhoufenge('test.txt','隐含')
fuhaocongqianhoufenge('test.txt','参数')
fuhaocongqianhoufenge('test.txt','基本')
fuhaocongqianhoufenge('test.txt','参数')
fuhaocongqianhoufenge('test.txt','确定')
fuhaocongqianhoufenge('test.txt','进一步')
fuhaocongqianhoufenge('test.txt','来作')
fuhaocongqianhoufenge('test.txt','认为')
fuhaocongqianhoufenge('test.txt','系统')
fuhaocongqianhoufenge('test.txt','作为')

fuhaocongqianhoufenge('test.txt','一种')
fuhaocongqianhoufenge('test.txt','观测')
fuhaocongqianhoufenge('test.txt','观察')
fuhaocongqianhoufenge('test.txt','建模')
fuhaocongqianhoufenge('test.txt','世纪')
fuhaocongqianhoufenge('test.txt','年代')
fuhaocongqianhoufenge('test.txt','得到')
fuhaocongqianhoufenge('test.txt','随机过程')
fuhaocongqianhoufenge('test.txt','数学模型')
#fuhaocongqianhoufenge('test.txt','随机过程')
fuhaocongqianhoufenge('test.txt','奠定')
#fuhaocongqianhoufenge('test.txt','随机过程')
#fuhaocongqianhoufenge('test.txt','随机过程')
#fuhaocongqianhoufenge('test.txt','随机过程')
#fuhaocongqianhoufenge('test.txt','随机过程')
#fuhaocongqianhoufenge('test.txt','随机过程')
#fuhaocongqianhoufenge('test.txt','随机过程')
#fuhaocongqianhoufenge('test.txt','随机过程')
#fuhaocongqianhoufenge('test.txt','随机过程')
#fuhaocongqianhoufenge('test.txt','随机过程')
#fuhaocongqianhoufenge('test.txt','随机过程')
#fuhaocongqianhoufenge('test.txt','随机过程')
#fuhaocongqianhoufenge('test.txt','随机过程')
#fuhaocongqianhoufenge('test.txt','随机过程')
#fuhaocongqianhoufenge('test.txt','随机过程')
#fuhaocongqianhoufenge('test.txt','随机过程')
#fuhaocongqianhoufenge('test.txt','随机过程')
#fuhaocongqianhoufenge('test.txt','随机过程')
#fuhaocongqianhoufenge('test.txt','随机过程')
#fuhaocongqianhoufenge('test.txt','随机过程')
#fuhaocongqianhoufenge('test.txt','随机过程')
#fuhaocongqianhoufenge('test.txt','随机过程')
#fuhaocongqianhoufenge('test.txt','随机过程')
#fuhaocongqianhoufenge('test.txt','随机过程')
#fuhaocongqianhoufenge('test.txt','随机过程')
#fuhaocongqianhoufenge('test.txt','随机过程')


hebing('test.txt','定','义')

hebing('test.txt','应','用')



lianggecidoubufenkai('test.txt','隐','马尔可夫过程')  #  隐马尔可夫过程  与  马尔可夫过程 这两个词，都不分割
lianggecidoubufenkai('test.txt','隐','马尔可夫链')
lianggecidoubufenkai('test.txt','隐','马尔可夫模型')
#lianggecidoubufenkai('test.txt','未知','数') 这个不要随便用，因为它会将所有的“数”字进行拆分，这样不好，后面那个词只适用于长的专业名词，不适合用常用字

fuhaoconghoufenge('test.txt',chr(10))  #放在最后，把行分隔开

#首先可以用结巴分词， 然后 再把分词的结果中不理想的情况，重新处理一下。
#把所有的词都列出来，然后凡是遇到这些词都不拆分，当然如果没有遇到这些词，就按后面的那个字拆分。
#或者可以理解为，全部按字拆分，再按词重组，但是有些专业的词，如果词库中没有，就组不成了。
#所以，有把握再拆分，没把握的，不要拆。
#当你把意思明确的词，全部确定下来，那些不确定的词，也变得确定了。
#当你找到了很多确定的因素，也就把不确定的因素给排除掉了