Hive UDF开发案例

不念不忘少年蓝@ 2022-02-04 19:39 239阅读 0赞

# 创建Maven项目，添加依赖 #

<properties>
            <hadoop.version>2.6.0-cdh5.7.1</hadoop.version>
            <hive.version>1.1.0-cdh5.7.1</hive.version>
        </properties>
        
        
        <repositories>
            <repository>
                <id>cloudera</id>
                <url>http://repository.cloudera.com/artifactory/cloudera-repos</url>
            </repository>
        </repositories>
        <dependencies>
            
            <dependency>
                <groupId>org.apache.hadoop</groupId>
                <artifactId>hadoop-common</artifactId>
                <version>${hadoop.version}</version>
            </dependency>
            <dependency>
                <groupId>org.apache.hive</groupId>
                <artifactId>hive-exec</artifactId>
                <version>${hive.version}</version>
            </dependency>
            
            <dependency>
                <groupId>junit</groupId>
                <artifactId>junit</artifactId>
                <version>4.10</version>
                <scope>test</scope>
            </dependency>
        </dependencies>

## UDF函数开发测试 ##

![SouthEast][]

## 导出jar包： ##

![SouthEast 1][]

## 添加jar到Hive中去，并进行测试 ##

bin/hive中操作：

临时函数的使用：
    
    add jar /home/hadoop/lib/train-1.0-SNAPSHOT.jar;
    -- 将上传的jar包导入到classpath变量里
    list jars;
    -- 查看导入的jar包
    create temporary function say_hello as 'com.vincent.HelloUDF';
    -- 创建一个临时函数，关联该jar包
    -- as 后面的路径就是上一步获得的全路径

select 'lisi',say\_hello('lisi');

永久函数的使用：
    
    create function say_hello2 
      as 'com.vincent.HelloUDF' 
      using jar 'hdfs:///tmp/train-1.0-SNAPSHOT.jar';
    -- 将jar包放到hdfs上，然后创建函数关联路径即可

select 'lisi',say\_hello2('lisi');

[SouthEast]: /images/20220204/524fb041ab77492083baf4314e228bf4.png
[SouthEast 1]: /images/20220204/aa65d2d43656425fb3f0e51f69d3b405.png