Hive-自定义UDF

简介
实现自定义的UDF需要编写Java程序，然后在Hive客户端中加载相关Jar并注册函数后就可以使用了。

示例：实现转化IP地址为二进制格式

import org.apache.hadoop.hive.ql.exec.UDF;
import org.apache.hadoop.io.Text;

public final class IPUnMasker extends UDF {
    public Text evaluate(final Text s) {
        if (s == null) { return null; }

        StringBuilder ret = new StringBuilder();

        String[] items = s.toString().split("\\.");
        if (items.length != 4)
            return null;

        for (String item : items) {
            StringBuilder sb = new StringBuilder();
            int a = Integer.parseInt(item);
            for (int i=0; i<8; i++) {
                sb.insert(0, a%2);
                a = a/2;
            }
            ret.append(sb);
        }

        return new Text(ret.toString());
    }

    public static void main(String[] args) {
        String ip = "172.19.202.12";

        IPUnMasker unmasker = new IPUnMasker();
        System.out.println(unmasker.evaluate(new Text(ip)));
    }
}

打包
mvn package

加载
从本地加载
hive> add jar xxx.jar;

从hdfs加载并注册
create [temporary] function unmask_ip as ‘example.IPUnMasker’ using jar ‘hdfs:///user/zzz/jars/hive_udf-1.0.0.jar’;

删除函数
drop funciton unmask_ip;

使用udf
select unmask_ip(‘172.19.202.12’);

附录
pom依赖

<dependencies>
        <dependency>
            <groupId>org.apache.hadoop</groupId>
            <artifactId>hadoop-core</artifactId>
            <version>1.2.1</version>
        </dependency>

        <dependency>
            <groupId>org.apache.hive</groupId>
            <artifactId>hive-exec</artifactId>
            <version>1.2.1</version>
        </dependency>
    </dependencies>