Hive+GenericUDF示例二

        再来看一个分数统计的小例子。

        在Hive中存在如下一张表：

hive> describe tb_test2;
OK
name	string	
score_list	array>	
Time taken: 0.074 seconds
hive> select * from tb_test2;
OK
A	[{"math":100,"english":90,"history":85}]
B	[{"math":95,"english":80,"history":100}]
C	[{"math":80,"english":90,"histroy":100}]
Time taken: 0.107 seconds

        编写genericUDF.

       

package com.wz.udf;
import org.apache.hadoop.io.Text;
import org.apache.hadoop.io.IntWritable;
import org.apache.hadoop.hive.ql.udf.generic.GenericUDF;
import org.apache.hadoop.hive.ql.exec.UDFArgumentException;
import org.apache.hadoop.hive.ql.exec.UDFArgumentLengthException;
import org.apache.hadoop.hive.ql.exec.UDFArgumentTypeException;
import org.apache.hadoop.hive.ql.metadata.HiveException;
import org.apache.hadoop.hive.serde2.lazy.LazyString;
import org.apache.hadoop.hive.serde2.lazy.LazyMap;
import org.apache.hadoop.hive.serde2.objectinspector.ObjectInspector;
import org.apache.hadoop.hive.serde2.objectinspector.ObjectInspector.Category;
import org.apache.hadoop.hive.serde2.objectinspector.ListObjectInspector;
import org.apache.hadoop.hive.serde2.objectinspector.MapObjectInspector;
import org.apache.hadoop.hive.serde2.objectinspector.StructObjectInspector;
import org.apache.hadoop.hive.serde2.objectinspector.StandardListObjectInspector;
import org.apache.hadoop.hive.serde2.objectinspector.ObjectInspectorFactory;
import org.apache.hadoop.hive.serde2.objectinspector.StructField;
import org.apache.hadoop.hive.serde2.objectinspector.PrimitiveObjectInspector;
import org.apache.hadoop.hive.serde2.objectinspector.primitive.PrimitiveObjectInspectorFactory;
import org.apache.hadoop.hive.serde2.objectinspector.primitive.StringObjectInspector;
import java.util.ArrayList;
 
public class helloGenericUDFNew extends GenericUDF {
     输入变量定义
     private ObjectInspector nameObj;
     private ListObjectInspector listoi;
     private MapObjectInspector mapOI;
     private ArrayList