Last active
May 23, 2016 09:36
-
-
Save tromika/6bc0ddb414b657b8cd1676a981e0d66d to your computer and use it in GitHub Desktop.
Apache Spark SQL INET_NTOA function pyspark dummy version
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
%pyspark | |
import socket,struct | |
import re | |
def inetNtoa(ip,num): | |
ip = re.match("^([0-9]{1,3})\.([0-9]{1,3})\.([0-9]{1,3})\.([0-9]{1,3})$",socket.inet_ntoa(struct.pack('!I', ip))) | |
str = '' | |
if(num==0 or num > 3): | |
return ip.group(0) | |
else: | |
for i in range(1,num+1): | |
str+=ip.group(i)+'.' | |
return str | |
# Usage INET_NTOA(col, number) - Number 0 or number higher than 3 you got the full ip - if number is 1,2,3 you got a subnet ip range. | |
sqlContext.registerFunction("INET_NTOA", lambda x,y: inetNtoa(x,y)) |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment