Powered By Blogger

Sunday, October 20, 2019

UDF in HDFS

package udf_example;

import org.apache.hadoop.hive.ql.exec.UDF;

public class DataStandardization extends UDF{

public String evaluate(String input){
if(input == null){
return null;
}
return (input.toUpperCase());
}

}


rankfunctions.txt
Frank,1150
Frank,1700

CREATE TABLE IF NOT EXISTS rankchcektable(
    col1 string,
    col2 int
 
) ROW FORMAT DELIMITED FIELDS TERMINATED BY ',' line terminated by '\n' STORED AS TEXTFILE


load data local inpath '/Users/basan/rankfunctions.txt' into table rankchcektable


Create jar

//Add the jar to hive
hive>add jar /users/basan/my_udf.jar
It will add jar to classpath

//create the function in hive

create temporary function f1 as 'udf_example.DataStandardization';

create temporary function functionname as 'packagename.classname';

//applying udf function
select f1(col1) from rankchcektable

No comments:

Post a Comment