大数据_UDF 自增函数

1. 创建maven项目

使用IDEA创建maven工程，步骤：File-》New-》Project-》Maven-》maven-archetype-quickstart-》输入maven坐标完成maven工程创建

2. 添加POM文件

<?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</artifactId>
  <version>1.0-SNAPSHOT</version>

  <name>UDF</name>
  <!-- FIXME change it to the project's website -->
  <url>http://www.example.com</url>

  <properties>
    <project.build.sourceEncoding>UTF-8</project.build.sourceEncoding>
    <hadoop.version>3.0.0-cdh6.3.1</hadoop.version>
    <hive.version>2.1.1</hive.version>
  </properties>

  <!--CDH版本需要添加repository，apache版本不需要-->
  <repositories>
    <repository>
      <id>cloudera</id>
      <url>https://repository.cloudera.com/artifactory/cloudera-repos/</url>
    </repository>
  </repositories>


  <dependencies>
    <!--添加Hadoop依赖-->
    <dependency>
      <groupId>org.apache.hadoop</groupId>
      <artifactId>hadoop-common</artifactId>
      <version>${hadoop.version}</version>
    </dependency>

    <!--添加Hive依赖-->
    <dependency>
      <groupId>org.apache.hive</groupId>
      <artifactId>hive-exec</artifactId>
      <version>${hive.version}</version>
    </dependency>
  </dependencies>


  <build>
    <pluginManagement><!-- lock down plugins versions to avoid using Maven defaults (may be moved to parent pom) -->
      <plugins>
        <!-- clean lifecycle, see https://maven.apache.org/ref/current/maven-core/lifecycles.html#clean_Lifecycle -->
        <plugin>
          <artifactId>maven-clean-plugin</artifactId>
          <version>3.1.0</version>
        </plugin>
        <!-- default lifecycle, jar packaging: see https://maven.apache.org/ref/current/maven-core/default-bindings.html#Plugin_bindings_for_jar_packaging -->
        <plugin>
          <artifactId>maven-resources-plugin</artifactId>
          <version>3.0.2</version>
        </plugin>
        <plugin>
          <artifactId>maven-compiler-plugin</artifactId>
          <version>3.8.0</version>
        </plugin>

        <plugin>
          <artifactId>maven-jar-plugin</artifactId>
          <version>3.0.2</version>
        </plugin>
        <plugin>
          <artifactId>maven-install-plugin</artifactId>
          <version>2.5.2</version>
        </plugin>
        <plugin>
          <artifactId>maven-deploy-plugin</artifactId>
          <version>2.8.2</version>
        </plugin>
        <!-- site lifecycle, see https://maven.apache.org/ref/current/maven-core/lifecycles.html#site_Lifecycle -->
        <plugin>
          <artifactId>maven-site-plugin</artifactId>
          <version>3.7.1</version>
        </plugin>
        <plugin>
          <artifactId>maven-project-info-reports-plugin</artifactId>
          <version>3.0.0</version>
        </plugin>
      </plugins>
    </pluginManagement>
  </build>
</project>

3. 编写UDF函数，并打成JAR包

package udf;

import udf.RowSequence;
import org.apache.hadoop.hive.ql.exec.Description;
import org.apache.hadoop.hive.ql.exec.UDF;
import org.apache.hadoop.hive.ql.udf.UDFType;
import org.apache.hadoop.io.LongWritable;


@Description(name = "auto_sequence",

        value = "_FUNC_() - Returns a generated row sequence number starting from 1")

@UDFType(deterministic = false)

public class RowSequence extends UDF {
    private LongWritable result = new LongWritable();
    public RowSequence(){
        result.set(0);
    }
    public LongWritable evaluate(){
        result.set(result.get() + 1);
        return result;
    }
}

4. hive添加UDF 函数

hive> add jar /opt/UDF-1.0-SNAPSHOT.jar;
hive> create temporary function auto_sequence as 'udf.RowSequence';  -- 注意选择正确的jar包及类
hive> SELECT auto_sequence() ,* FROM STAGE.COL_LIE_01;  -- 测试结果