hive自定义udtf函数

最新推荐文章于 2024-01-23 09:50:48 发布

晚点吧

最新推荐文章于 2024-01-23 09:50:48 发布

阅读量1k

点赞数

分类专栏： hive 文章标签： hive hadoop big data

本文链接：https://blog.csdn.net/weixin_42529756/article/details/121866807

版权

hive 专栏收录该内容

5 篇文章 0 订阅

订阅专栏

hive自定义udtf函数
1、添加依赖

<?xml version="1.0" encoding="UTF-8"?>
<project xmlns="http://maven.apache.org/POM/4.0.0"
         xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance"
         xsi:schemaLocation="http://maven.apache.org/POM/4.0.0 http://maven.apache.org/xsd/maven-4.0.0.xsd">

    <modelVersion>4.0.0</modelVersion>
    <artifactId>hive-demo</artifactId>
 <dependencies>
     <dependency>
         <groupId>org.apache.hive</groupId>
         <artifactId>hive-exec</artifactId>
         <version>3.1.2</version>
     </dependency>
       <dependency>
            <groupId>org.apache.hadoop</groupId>
            <artifactId>hadoop-client</artifactId>
            <version>3.1.3</version>
        </dependency>
 </dependencies>

</project>

2 实现GenericUDTF

mport org.apache.hadoop.hive.ql.exec.UDFArgumentException;
import org.apache.hadoop.hive.ql.metadata.HiveException;
import org.apache.hadoop.hive.ql.udf.generic.GenericUDTF;
import org.apache.hadoop.hive.serde2.objectinspector.ObjectInspector;
import org.apache.hadoop.hive.serde2.objectinspector.ObjectInspectorFactory;
import org.apache.hadoop.hive.serde2.objectinspector.StructObjectInspector;
import org.apache.hadoop.hive.serde2.objectinspector.primitive.PrimitiveObjectInspectorFactory;

import java.util.ArrayList;

public class MyUDTF extends GenericUDTF {
    private ArrayList<String> outPutLists=new ArrayList<>();
    @Override
    public StructObjectInspector initialize(StructObjectInspector argOIs) throws UDFArgumentException {
        ArrayList<String> fieldNames = new ArrayList<>();
        fieldNames.add("word");
        ArrayList<ObjectInspector> fieldOIs = new ArrayList<>();
        fieldOIs.add(PrimitiveObjectInspectorFactory.javaStringObjectInspector);
        return ObjectInspectorFactory.getStandardStructObjectInspector(fieldNames,fieldOIs);

    }

    @Override
    public void process(Object[] objects) throws HiveException {
        String input = objects[0].toString();
        String[] words = input.split(",");

        for (String word:words){
            outPutLists.clear();
            outPutLists.add(word);
            forward(outPutLists);
        }
    }

    @Override
    public void close() throws HiveException {

    }
}

3 测试

1 add jar /opt/module/hive/mylib/hive-demo-1.0-SNAPSHOT.jar
2 create temporary function myudtf as “udf.MyUDTF”;
3 select myudtf(“hello world,haoop,hive,spark,wak”);