desc function split;
desc function extended split;
split 可以同时对多个分隔符切割
select split(‘zhonagguo-fefei_xiaoming’,’[-_]’);
自定义函数 hive中看行 多行进一行 一行进一行
(1)UDF(User-Defined-Function)
一进一出
(2)UDAF(User-Defined Aggregation Function)
聚集函数,多进一出
类似于:count/max/min
(3)UDTF(User-Defined Table-Generating Functions)
一进多出
如lateral view explore()
package com.myfunction;
import org.apache.hadoop.hive.ql.exec.UDF;
public class MyUDF extends UDF {
//方法名evaluate固定
public int evaluate(int data){
return data + 5;
}
}
hive> add jar /opt/module/hive/lib/hivefunction.jar
hive> create [temporary] function addFive as ‘com.myfunction.MyUDF’;
select addFive(5);
hive> create function myudtf as ‘com.myfunction.MyUDTF’;
package com.myfunction;
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 {
//初始化方法
@Override
public StructObjectInspector initialize(StructObjectInspector argOIs) throws UDFArgumentException {
//定义输出数据的列名
ArrayList fieldNames = new ArrayList();
fieldNames.add(“word”); //控制的是列名类型
//定义输出数据的类型
ArrayList fieldOIs = new ArrayList();
fieldOIs.add(PrimitiveObjectInspectorFactory.javaStringObjectInspector); //控制返回值类型
//返回列名 值
return ObjectInspectorFactory.getStandardStructObjectInspector(fieldNames,fieldOIs );
}
//来的每一条数据都需要处理来 参数多个
private List dataList = new ArrayList();
public void process(Object[] args) throws HiveException {
//1.获取数据
String data = args[0].toString();
//2.获取分隔符
String splitKey = args[1].toString();
//3切分数据
String[] words = data.split(splitKey);
for (String word : words) {
//将数据放置集合
dataList.clear();
dataList.add(word);
//将集合写出去 一进多出 重点 多行 一个集合里面 多次写出
forward(dataList);
}
}
public void close() throws HiveException {
}
}