UDF函数开发

Hive有两个不同的接口编写UDF程序。一个是操作简单数据类型的UDF接口，一个是操作复杂类型的GenericUDF接口。

UDF接口暂不讨论。

下面看一个例子：

ary建表语句：

create table ary(
array1 array>,
array2 array>
)
row format delimited fields terminated by '\t'
map keys terminated by ','; 

ary表中数据如下：

hive > select * from ary;
OK
ary.array1      ary.array2
[{"id":"001","name":"明明"}]    [{"addr":"杨浦","id":"001","dt":"20180703"}]
[{"id":"002","name":"阿达"}]    [{"addr":"黄浦","id":"004","dt":"20180629"}]
[{"id":"003","name":"阿珂"}]    [{"addr":"浦东","id":"003","dt":"20180817"}]
[{"id":"004","name":"小宝"}]    [{"addr":"松江","id":"002","dt":"20180623"}]

我们需要的结果：

hive > select aa(array1,array2,'id') from ary;                
OK
_c0
[{"id":"001","name":"明明","addr":"杨浦","dt":"20180703"}]
[{"id":"NULL","name":"NULL","addr":"NULL","dt":"NULL"}]
[{"id":"003","name":"阿珂","addr":"浦东","dt":"20180817"}]
[{"id":"NULL","name":"NULL","addr":"NULL","dt":"NULL"}]

函数逻辑：

操作一行数据，通过传入的字段名对两个结构体类型的数组中字段值进行匹配，值相等则返回匹配到的全部值（当然id只匹配一个），否则全部置空

编写UDF自定义函数：

package com.paic.gbd.udfarray;
import org.apache.hadoop.io.Text;
import org.apache.hadoop.io.IntWritable;
import org.apache.hadoop.hive.ql.udf.generic.GenericUDF;
import org.apache.commons.logging.LogFactory;
import org.apache.commons.logging.Log;
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.LazyStruct;
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.ObjectInspectorUtils;
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;
import java.util.List;
 
public class GenericArrayUnion extends GenericUDF {

	//定义输出日志，方便调试，在hive.log里面查看，该文件目录在hive-log4j.properties配置文件里查看
	 static final Log LOG = LogFactory.getLog(GenericArrayUnion.class.getName());
     ////输入变量定义
	 private static final int ARG_COUNT = 3; // Number of arguments to this UDF
	 private static final String FUNC_NAME = "array_union"; // External Name
     private ListObjectInspector arrayOI;
     private ListObjectInspector arrayOI2;
     private ObjectInspector strOI;
     
     private StructObjectInspector structOI;
     private StructObjectInspector structOI2;
     private ArrayList