Hive---UDTF

UDTF逻辑代码步骤

类 extends GenericUDTF{
 initialize()//初始化
 process()	//业务处理
 close()	//关闭资源
}

例子：splToLines():字符串指定分割符切分

select splToLines(“a,b,c”,",");
结果：
a
b
c

代码

package HiveUDF1.udtf;

import org.apache.hadoop.hive.ql.exec.Description;
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 org.apache.hadoop.hive.serde2.objectinspector.primitive.StringObjectInspector;

import java.util.ArrayList;
import java.util.List;

/**
 * @Author shall潇
 * @Date 2021/4/7
 * @Description
 */
public class TestUDTF extends GenericUDTF {

    @Description(
            name = "splToLines",
            value = "call to the split character,to split the str to lines",
            extended = "select splToLines("a,b,c",","); result is :"+
                    "a\n"+"b\n"+"c\n"
    )
    List<String> outlist = new ArrayList();
    @Override
    public StructObjectInspector initialize(StructObjectInspector argOIs) throws UDFArgumentException {
        List<String> name = new ArrayList<>();              //定义输出列名,为什么是List,因为返回值要求是两个List
        List<ObjectInspector> listOis = new ArrayList<>();  //定义输出类型
        name.add("values");                                 //最后的输出列名为value
        listOis.add(PrimitiveObjectInspectorFactory.javaStringObjectInspector);
        return ObjectInspectorFactory.getStandardStructObjectInspector(name,listOis);
    }

    @Override
    public void process(Object[] o) throws HiveException {
        String arg = o[0].toString();				//第一个参数：字符串
        String  splitKey = o[1].toString();  		//第二个参数：切分符号
        String[] splits = arg.split(splitKey);
        for (String split : splits) {
            outlist.clear();
            outlist.add(split);
            forward(outlist);
        }
    }

    @Override
    public void close() throws HiveException {
    }
}