Pig中Java编写UDF函数

Pig中Java编写UDF函数

idea中新建Maven项目

1. 添加依赖到pom.xml文件

<dependency>
	<groupId>org.apache.pig</groupId>
    <artifactId>pig</artifactId>
    <version>0.17.0</version>
 </dependency>
 <dependency>
    <groupId>org.apache.hadoop</groupId>
    <artifactId>hadoop-core</artifactId>
    <version>0.20.2</version>
</dependency>

2. 新建Sample_eval.class文件

import org.apache.pig.EvalFunc;
import org.apache.pig.data.Tuple;
import java.io.IOException;
/**
 * @author user
 * @describe 用户自定义函数
 * @create 2021-04-21 8:24
 */
public class Sample_Eval extends EvalFunc<String> {
    @Override
    public String exec(Tuple input) throws IOException {
        if (input == null || input.size() == 0)
            return null;
        String str = (String)input.get(0);
        return str.toUpperCase();
    }
}

3. 导出包
   

将jar包上传到虚拟机进行测试

1. 注册

   register '/home/hduser/SampleEval.jar';
   

   

2. 使用define命令定义别名

   define sample_eval org.qfnu.Sample_Eval();
   

3. 数据文件

   001,Robin,22,newyork
   002,Naya,23,Kolkata
   003,Maya,23,Tokyo
   004,Sara,25,London
   005,David,23,Bhuwaneshwar
   006,Maggy,22,Chennai
   007,Robert,22,newyork
   008,Syam,23,Kolkata
   009,Mary,25,Tokyo
   010,Saran,25,London
   011,Stacy,25,Bhuwaneshwar
   012,Kelly,22,Chennai
   

4. 加载数据

   emp_data = LOAD '/home/hduser/pig/emp1.txt' USING 
   PigStorage(',')as (id:int, name:chararray, age:int, city:chararray);
   

   

5. 调用UDF函数

   Upper_case = FOREACH emp_data GENERATE sample_eval(name);
   

6. 输出结果

   dump Upper_case;