Hive-(UDF和UDTF)

梦里梦外; 2022-12-20 14:55 202阅读 0赞

创建一个Maven工程Hive  
导入依赖

<dependencies>
    		
    		<dependency>
    			<groupId>org.apache.hive</groupId>
    			<artifactId>hive-exec</artifactId>
    			<version>1.2.1</version>
    		</dependency>
    </dependencies>

## UDF ##

import org.apache.hadoop.hive.ql.exec.UDF;
    
    public class MyUDF extends UDF { 
    
        public int evaluate(int data){ 
    
            return data + 5;
        }
    }

hive (default)> add jar /export/servers/hive/lib/udf.jar;
    Added [/export/servers/hive/lib/udf.jar] to class path
    Added resources: [/export/servers/hive/lib/udf.jar]
    hive (default)> create temporary function myudf as 'com.MyUDF';
    OK
    Time taken: 0.011 seconds

![在这里插入图片描述][20201112222533909.png_pic_center]  
![在这里插入图片描述][20201112222604822.png_pic_center]

## UDTF ##

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 MyUDTF extends GenericUDTF { 
    
        private List<String> dataList = new ArrayList<String>();
    
        @Override
        public StructObjectInspector initialize(StructObjectInspector argOIs)
                throws UDFArgumentException { 
    
            //定义输出数据的列名
            List<String> fieldNames = new ArrayList<String>();
            fieldNames.add("word");
    
            //定义输出数据的类型
            List<ObjectInspector> fieldOIs = new ArrayList<ObjectInspector>();
            fieldOIs.add(PrimitiveObjectInspectorFactory.javaStringObjectInspector);
            return ObjectInspectorFactory.getStandardStructObjectInspector(fieldNames, fieldOIs);
        }
    
        public void process(Object[] objects) throws HiveException { 
    
            //1.获取数据
            String data = objects[0].toString();
    
            //2.获取分隔符
            String splitkey = objects[1].toString();
    
            //3.切分数据
            String[] words = data.split(splitkey);
    
            //4.遍历输出
            for (String word : words) { 
    
                //5.将数据放置集合
                dataList.clear();
                dataList.add(word);
    
                //6.写出数据的操作
                forward(dataList);
    
            }
    
    
        }
    
        public void close() throws HiveException { 
    
        }
    }

**`ctrl+f查看继承（目的查看初始化的返回值）`**  
打包  
把jar包放在hive/lib下  
进入hive

add jar /export/servers/hive/lib/xx.jar;
    create temporary function myutdf as '全类名';
    select myutdf('asdas,asdasd,lll',',');

测试成功！

[20201112222533909.png_pic_center]: /images/20221120/8f46ca747a5842ea84b781f29152c4bb.png
[20201112222604822.png_pic_center]: /images/20221120/d010634a2375417ba748c95feed5af5e.png