<dependency>
<groupId>org.apache.hive</groupId>
<artifactId>hive-exec</artifactId>
<version>1.2.2</version>
</dependency>

import org.apache.commons.lang.StringUtils;
import org.apache.hadoop.hive.ql.exec.UDF;public class FirstUDF extends UDF {public String evaluate(String str){String upper=null;//1、检查输入参数if (StringUtils.isEmpty(str)){} else {// 转大写。upper = str.toUpperCase();}return upper;}
}

add jar /UDF.jar;
-- 创建一个临时函数名，要跟上面hive在同一个session里面：
create temporary function toUP as 'FirstUDF';
-- 查看
show functions;

-- 测试
select toUP("abcdef");

-- 删除函数
drop temporary function if exists toUP;

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;public class ParseMapUDTF extends GenericUDTF {//在initializez中初始化要输出字段的名称和类型@Overridepublic StructObjectInspector initialize(ObjectInspector[] argOIs) throws UDFArgumentException {//定义要输出列的名字的List,并且添加要输出的列名List<String> structFieldNames = new ArrayList<>();structFieldNames.add("key");structFieldNames.add("value");
//      定义要输出列的类型的List,并且添加要输出列的类型List<ObjectInspector> objectInspectorList = new ArrayList<>();objectInspectorList.add(PrimitiveObjectInspectorFactory.javaStringObjectInspector);objectInspectorList.add(PrimitiveObjectInspectorFactory.javaStringObjectInspector);return ObjectInspectorFactory.getStandardStructObjectInspector(structFieldNames, objectInspectorList); }@Overridepublic void process(Object[] args) throws HiveException {String strings=args[0].toString();String[] split=strings.split(";");for (String s : split) {String [] kvArray=s.split(":");forward(kvArray);}}@Overridepublic void close() throws HiveException {}
}

-- UDTF格式
add jar /hive_init/UDTF.jar;
-- 创建一个临时函数parseMap
create temporary function parseMap as 'ParseMapUDTF';
show functions ;

-- 测试函数
select parseMap("name:zhang;age:30;address:shenzhen");

package week12.day01;import org.apache.hadoop.hive.ql.exec.Description;
import org.apache.hadoop.hive.ql.exec.UDAF;
import org.apache.hadoop.hive.ql.exec.UDAFEvaluator;
import org.apache.hadoop.hive.serde2.io.DoubleWritable;/*** description: SumValueUDAF* 定义一个UDAF自定义函数，默认要继承与UDAF类*/
@Description(name = "SumValue",value = "Sue For Peace ",extended = "Extension: Find The Sum of col")
public class SumValueUDAF extends UDAF {public static class SumnumDoubleUDAFEvaluator implements UDAFEvaluator {//    在静态列内部定义一个返回值，作为当前UDAF最后的唯一返回值，因为返回值要hive调用，所以必须要使用序列化类型private DoubleWritable result;/*** 初始化是把返回值设为null，避免上传调用时混淆*/@Overridepublic void init() {result = null;}/*** 定义一个函数iterate用来处理遍历多行时，每行值传进来是调用的函数** @param value* @return*/public boolean iterate(DoubleWritable value) {if (value == null) {return true;}if (result == null) {result=new DoubleWritable(value.get());} else {result.set(result.get() + value.get());}return true;}/*** 在map端进行执行后的结果** @return*/public DoubleWritable terminatePartial() {return result;}/*** 接收terminatePartial的返回结果，进行数据merge操作，其返回类型为boolean** @param other* @return*/public boolean merge(DoubleWritable other) {return iterate(other);}/*** 将最终的几个返给hive* @return*/public DoubleWritable terminate() {return result;}}}

add jar /week12.jar;
-- 删除jar包
delete jar /week12.jar;-- 删除内置函数sum_UDAF
create temporary function sum_UDAF as 'week12.day01.SumValueUDAF';
drop temporary function if exists sum_UDAF;
-- 查看添加的函数sum_UDAF
desc function sum_UDAF;select sum_UDAF(cost) --661
from day05.t_order;