hive学习笔记——自定义函数

idea创建maven项目

pom.xml

<dependency>
      <groupId>org.apache.hive</groupId>
      <artifactId>hive-exec</artifactId>
      <version>3.1.0</version>
</dependency>

UDFOne.java

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

/**
 * abcd  -->  Abcd
 * efgH     -->  EfgH
 */

public class UDFOne extends UDF {
    public String evaluate(final String txt){
        String result = txt.substring(0, 1).toUpperCase() + txt.substring(1);
        return result;
    }
}

UDTFOne.java

import 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;
import java.util.List;

/**
 * 输入"hello world,how,are,you"
 * hello world
 * how
 * are
 * you
 */
public class UDTFOne extends GenericUDTF {

    @Override
    public StructObjectInspector initialize(StructObjectInspector argOIs) throws UDFArgumentException {
        // 定义输出数据列
        List<String> fieldNames = new ArrayList<>();
        fieldNames.add("word");

        // 定义输出数据类型
        List<ObjectInspector> fieldOIs = new ArrayList<>();
        fieldOIs.add(PrimitiveObjectInspectorFactory.javaStringObjectInspector);

        return ObjectInspectorFactory.getStandardStructObjectInspector(fieldNames,fieldOIs);
    }

    private List<String> dataList = new ArrayList<>();

    @Override
    public void process(Object[] objects) throws HiveException { //select myfieldudf("","");
        // 获取第一个参数传入的值
        String data = objects[0].toString();

        String splitKey = " ";
        if(objects.length==2){
            splitKey = objects[1].toString();
        }

        String[] words = data.split(splitKey);

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

    @Override
    public void close() throws HiveException {

    }
}

将项目打包放到/opt/tmp/目录下

导入jar包，添加函数

hive> add jar /opt/tmp/hivestu-1.0-SNAPSHOT.jar;
Added [/opt/tmp/hivestu-1.0-SNAPSHOT.jar] to class path
Added resources: [/opt/tmp/hivestu-1.0-SNAPSHOT.jar]

hive> create temporary function myfirstUDF as 'nj.zb.kb15.UDFOne';
OK
Time taken: 0.287 seconds

hive> create temporary function myfirstUDTF as 'nj.zb.kb15.UDTFOne';
OK
Time taken: 0.287 seconds

hive> select myfirstUDF("mihaoyu");
OK
Mihaoyu
Time taken: 0.634 seconds, Fetched: 1 row(s)

hive> select myfirstUDTF("hello world,how,are,you",",");
OK
hello world
how
are
you
Time taken: 0.95 seconds, Fetched: 4 row(s)

hive> drop temporary function myfirstUDTF;
OK
Time taken: 0.011 seconds

hive> delete jar /opt/tmp/hivestu-1.2.jar;
Deleted [/opt/tmp/hivestu-1.2.jar] from class path