自定义函数
用户可以通过自定义UDF来方便的扩展(user-defined function)。根据用户自定义函数类别,分别为一下三种:
- UDF,一进一出
- UDAF,聚集函数,多进一出
- UDTF,一进多出
编程步骤
- 继承org.apache.hadoop.hive.ql.UDF
- 实现evaluate函数,实现重载,导成jar包
- 在hive的命令行窗口创建函数,添加jar包,并创建函数
- 在hive的命令行窗口删除函数
自定义DDF函数
//Maven导入依赖
<dependencies>
https://mvnrepository.com/artifact/org.apache.hive/hive-exec -->
<dependency>
<groupId>org.apache.hive</groupId>
<artifactId>hive-exec</artifactId>
<version>1.2.1</version>
</dependency>
</dependencies>
//实现函数重载
package com.atguigu.hive;
import org.apache.hadoop.hive.ql.exec.UDF;
public class Lower extends UDF {
public String evaluate (String s) {
if (s == null) {
return null;
}
return s.toLowerCase();
}
}
//把jar包添加到hive的classpath
hive (default)> add jar /opt/module/datas/udf.jar;
//创建临时函数
hive (default)> create temporary function mylower as
"com.atguigu.hive.Lower";
自定义UDTF函数
其余步骤一致
//代码
package com.atguigu.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 ArrayList<String> outList = new ArrayList<>();
@Override
public StructObjectInspector initialize(StructObjectInspector argOIs) throws UDFArgumentException {
//1.定义输出数据的列名和类型
List<String> fieldNames = new ArrayList<>();
List<ObjectInspector> fieldOIs = new ArrayList<>();
//2.添加输出数据的列名和类型
fieldNames.add("lineToWord");
fieldOIs.add(PrimitiveObjectInspectorFactory.javaStringObjectInspector);
return ObjectInspectorFactory.getStandardStructObjectInspector(fieldNames, fieldOIs);
}
@Override
public void process(Object[] args) throws HiveException {
//1.获取原始数据
String arg = args[0].toString();
//2.获取数据传入的第二个参数, 此处为分隔符
String splitKey = args[1].toString();
//3.将原始数据按照传入的分隔符进行切分
String[] fields = arg.split(splitKey);
//4.遍历切分后的结果,并写出
for (String field : fields) {
//集合为复用的,首先清空集合
outList.clear();
outList.add(field);
//将集合内容写出
forward(outList);
}
}
@Override
public void close() throws HiveException {
}
}