Hive添加udf

一、引用

<dependency>
    <groupId>org.apache.hive</groupId>
    <artifactId>hive-exec</artifactId>
    <version>1.2.1</version>
</dependency>
<!-- https://mvnrepository.com/artifact/org.apache.hadoop/hadoop-common -->
<dependency>
    <groupId>org.apache.hadoop</groupId>
    <artifactId>hadoop-common</artifactId>
    <version>2.7.3</version>
</dependency>

二、代码

package UDF;
import org.apache.commons.lang.StringUtils;
import org.apache.hadoop.hive.ql.exec.UDF;
import org.apache.hadoop.io.Text;
public class LowerUDF extends UDF{
    /**
     * 1. Implement one or more methods named "evaluate" which will be called by Hive.
     *
     * 2. "evaluate" should never be a void method. However it can return "null" if needed.
     */
    public Text evaluate(Text str){
        // input parameter validate
        if(null == str){
            return null ;
        }
        // validate
        if(StringUtils.isBlank(str.toString())){
            return null ;
        }
        // lower
        return new Text(str.toString().toLowerCase()) ;
    }
    public static void main(String[] args) {
        System.out.println(new LowerUDF().evaluate(new Text("BBB")));
    }
}

引用完写好后，点击maven的package，打包成jar包

三、上传到hdfs

1、创建目录并上传

hadoop fs -mkdir /hive

hadoop fs -put myMavenTest-1.0-SNAPSHOT.jar /hive

hadoop fs -ls /hive

2、hive客户端添加jar包

hive

add jar hdfs://wangshida:8020/hive/myMavenTest-1.0-SNAPSHOT.jar;

3、设置hiveUDF的main主类

create temporary function lower_udf as 'hive.LowerUDF';

4、测试

create table testhive (id int ,name string);

insert into testhive values(1,'WWWWAA');

select lower_udf(name) from testhive;