Bootstrap

IDEA maven开发hive的udf详细过程(附图片详解)

1.创建maven项目

file->new->project 

填写项目名称。

2.pom文件中添加依赖的jar包

pom.xml文件如下:

<?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>

    <groupId>org.example</groupId>
    <artifactId>udf_test</artifactId>
    <version>1.0-SNAPSHOT</version>

    <dependencies>
        <dependency>
            <groupId>org.apache.hadoop</groupId>
            <artifactId>hadoop-client</artifactId>
            <version>2.7.3</version>
        </dependency>
        <dependency>
            <groupId>org.apache.hive</groupId>
            <artifactId>hive-exec</artifactId>
            <version>1.2.1</version>
        </dependency>
    </dependencies>
    <build>
        <plugins>
            <plugin>
                <groupId>org.apache.maven.plugins</groupId>
                <artifactId>maven-shade-plugin</artifactId>
                <version>2.4.3</version>
                <executions>
                    <execution>
                        <phase>package</phase>
                        <goals>
                            <goal>shade</goal>
                        </goals>
                        <configuration>
                            <filters>
                                <filter>
                                    <artifact>*:*</artifact>
                                    <excludes>
                                        <exclude>META-INF/*.SF</exclude>
                                        <exclude>META-INF/*.DSA</exclude>
                                        <exclude>META-INF/*.RSA</exclude>
                                    </excludes>
                                </filter>
                            </filters>

                            <transformers>
                                <transformer
                                        implementation="org.apache.maven.plugins.shade.resource.AppendingTransformer">
                                    <resource>META-INF/spring.handlers</resource>
                                </transformer>
                                <transformer
                                        implementation="org.apache.maven.plugins.shade.resource.ManifestResourceTransformer">
                                    <mainClass>com.neu.hive.UDF.ToUpperCaseUDF</mainClass>
                                </transformer>
                                <transformer
                                        implementation="org.apache.maven.plugins.shade.resource.AppendingTransformer">
                                    <resource>META-INF/spring.schemas</resource>
                                </transformer>
                            </transformers>
                        </configuration>
                    </execution>
                </executions>
            </plugin>
        </plugins>
    </build>
</project>

 前提是配置好maven环境,导入完毕后左侧多出很多jar包,且右侧边栏没有红报错。

3.udf开发

java文件夹下新建new->package->class 

 代码如下:

package com.test.udf;

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

/**
 * @Author: Lens
 * @Date: 2021/6/18 11:13
 */
public class Udf_Hive_Test extends UDF {
    public Text evaluate(Text input){
        return new Text("hello:"+input);
    }

    public static void main(String[] args) {
        Udf_Hive_Test udf = new Udf_Hive_Test();
        Text result = udf.evaluate(new Text("lens"));
        System.out.println(result.toString());
    }
}

 右键运行成功,结果如下:

4.导出jar包

 5. 上传服务器,加载jar包,创建临时函数

找到该函数,鼠标右键选择copy reference获得该函数的全路径 com.test.udf.Udf_Hive_Test

--- 注册jar包
add jar /root/hadoop/lib/udf_test-1.0-SNAPSHOT.jar;

--- 创建临时函数  包名+类名
create temporary function test_udf as 'com.test.udf.Udf_Hive_Test';   

--- 测试函数
select test_udf(name) from dw.test_table;

--- 创建永久函数
CREATE FUNCTION test_udf2 AS 'com.test.udf.Udf_Hive_Test';  

 

;