hive自定义udf函数

1 添加依赖

<?xml version="1.0" encoding="UTF-8"?>
<project xmlns="http://maven.apache.org/POM/4.0.0"
         xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance"
         xsi:schemaLocation="http://maven.apache.org/POM/4.0.0 http://maven.apache.org/xsd/maven-4.0.0.xsd">

    <modelVersion>4.0.0</modelVersion>
    <artifactId>hive-demo</artifactId>
 <dependencies>
     <dependency>
         <groupId>org.apache.hive</groupId>
         <artifactId>hive-exec</artifactId>
         <version>3.1.2</version>
     </dependency>
       <dependency>
            <groupId>org.apache.hadoop</groupId>
            <artifactId>hadoop-client</artifactId>
            <version>3.1.3</version>
        </dependency>
 </dependencies>

</project>

2 继承GenericUDF

import org.apache.hadoop.hive.ql.exec.UDFArgumentException;
import org.apache.hadoop.hive.ql.metadata.HiveException;
import org.apache.hadoop.hive.ql.udf.generic.GenericUDF;
import org.apache.hadoop.hive.serde2.objectinspector.ObjectInspector;
import org.apache.hadoop.hive.serde2.objectinspector.primitive.PrimitiveObjectInspectorFactory;

/**
 * 自定义 UDF 函数，需要继承 GenericUDF 类
 * 需求: 计算指定字符串的长度
 */
public class MyUDF extends GenericUDF {
    /**
     *
     * @param  arguments 输入参数类型的鉴别器对象
     * @return 返回值类型的鉴别器对象
     * @throws UDFArgumentException
     */
    @Override
    public ObjectInspector initialize(ObjectInspector[] objectInspectors) throws UDFArgumentException {
       if (objectInspectors.length !=1){
           throw  new UDFArgumentException("参数个数不为1");
       }

        return  PrimitiveObjectInspectorFactory.javaIntObjectInspector;
    }

    @Override
    public Object evaluate(DeferredObject[] arguments) throws HiveException {
        String input = arguments[0].get().toString();
        if (input==null){
            return  0;
        }
        return input.length();
    }

    @Override
    public String getDisplayString(String[] strings) {
        return null;
    }
}

3 打包测试

① add jar /opt/module/hive/mylib/hive-demo-1.0-SNAPSHOT.jar
② create temporary function my_len as “udf.MyUDF”;
③ select name,my_len(name) name_len from test;