python 参议院文本预处理的一维数组的间隔空间
#!/usr/bin/python
import re
def pre_process_msg ( msgIn ):
if msgIn=="":
return "msgIn_Input_Error,should'nt Null, it is Strings"
else:
#1 trim
msg = msgIn
msg = msg.strip()
#2 process msg internal special char replace with “ ”
dst_replace_pattern1 = re.compile('\n')
msg = dst_replace_pattern1.sub(" ",msg)
dst_replace_pattern1 = re.compile('\r')
msg = dst_replace_pattern1.sub(" ",msg)
dst_replace_pattern1 = re.compile('\t')
msg = dst_replace_pattern1.sub(" ",msg)
#3 one or more space replaced with one space,to form srings with " " internal
result=""
result=re.sub(" {1,}", " ", msg)
msg=result.strip()
print "'"+msg+"'"
return msg
import re
def pre_process_msg ( msgIn ):
if msgIn=="":
return "msgIn_Input_Error,should'nt Null, it is Strings"
else:
#1 trim
msg = msgIn
msg = msg.strip()
#2 process msg internal special char replace with “ ”
dst_replace_pattern1 = re.compile('\n')
msg = dst_replace_pattern1.sub(" ",msg)
dst_replace_pattern1 = re.compile('\r')
msg = dst_replace_pattern1.sub(" ",msg)
dst_replace_pattern1 = re.compile('\t')
msg = dst_replace_pattern1.sub(" ",msg)
#3 one or more space replaced with one space,to form srings with " " internal
result=""
result=re.sub(" {1,}", " ", msg)
msg=result.strip()
print "'"+msg+"'"
return msg
版权声明:本文博主原创文章,博客,未经同意不得转载。