Spark——Mysql2Hive2Vetica

示例

从Mysql同步数据到Hive，再从Hive同步数据到Vertica

一、pom.xml

<?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>com</groupId>
    <artifactId>SparkSyncTest</artifactId>
    <version>1.0-SNAPSHOT</version>

    <properties>
        <hadoop.version>2.6.0-cdh5.4.0</hadoop.version>
        <guava.version>19.0</guava.version>
        <scala.version.long>2.11.8</scala.version.long>
        <scala.version>2.11</scala.version>
        <spark.version>2.2.0</spark.version>
    </properties>

    <dependencies>
        <dependency>
            <groupId>mysql</groupId>
            <artifactId>mysql-connector-java</artifactId>
            <version>5.1.47</version>
        </dependency>

        <dependency>
            <groupId>org.apache.spark</groupId>
            <artifactId>spark-core_${scala.version}</artifactId>
            <version>${spark.version}</version>
        </dependency>

        <dependency>
            <groupId>org.apache.spark</groupId>
            <artifactId>spark-hive_${scala.version}</artifactId>
            <version>${spark.version}</version>
        </dependency>

        <dependency>
            <groupId>org.scala-lang</groupId>
            <artifactId>scala-library</artifactId>
            <version>${scala.version.long}</version>
        </dependency>

        <dependency>
            <groupId>io.javaslang</groupId>
            <artifactId>javaslang</artifactId>
            <version>2.0.5</version>
        </dependency>

        <dependency>
            <groupId>com.google.guava</groupId>
            <artifactId>guava</artifactId>
            <version>${guava.version}</version>
        </dependency>
    </dependencies>

    <build>
        <plugins>
            <plugin>
                <artifactId>maven-compiler-plugin</artifactId>
                <version>3.6.1</version>
                <configuration>
                    <source>1.8</source>
                    <target>1.8</target>
                </configuration>
            </plugin>
            <plugin>
                <groupId>net.alchim31.maven</groupId>
                <artifactId>scala-maven-plugin</artifactId>
                <version>3.2.2</version>
                <executions>
                    <execution>
                        <id>compile-scala</id>
                        <phase>compile</phase>
                        <goals>
                            <goal>add-source</goal>
                            <goal>compile</goal>
                        </goals>
                    </execution>
                    <execution>
                        <id>test-compile-scala</id>
                        <phase>test-compile</phase>
                        <goals>
                            <goal>add-source</goal>
                            <goal>testCompile</goal>
                        </goals>
                    </execution>
                </executions>
                <configuration>
                    <scalaVersion>2.11.4</scalaVersion>
                </configuration>
            </plugin>
        </plugins>
        <defaultGoal>compile</defaultGoal>
    </build>

</project>

二、Mysql2Hive

首先将hive-site.xml加入resources目录中。

package com

import org.apache.spark.sql.SparkSession

object SyncMysqlToHive {
    def main(args: Array[String]): Unit = {
        val session = SparkSession.builder()
                .appName(this.getClass.getSimpleName)
                .master("local")
                .enableHiveSupport()
                .getOrCreate()

        val url = "jdbc:mysql://01.mysql.hl.com:3306/?useUnicode=true&characterEncoding=utf-8&useSSL=false&zeroDateTimeBehavior=convertToNull"
        val sql = "(select id,job_id,hour,name,table_name,job_type,status,job,created_on,started_on,completed_on,data_source from dmf.running_jobs " +
                "where hour = '2021-05-29 02:00:00') as running_jobs"
        val prop = scala.collection.mutable.Map[String, String]()
        prop.put("user", "root")
        prop.put("password", "mysql")
        prop.put("driver", "com.mysql.jdbc.Driver")
        // dbtable如果为表名，则读取表内所有数据
        prop.put("dbtable", sql)
        prop.put("url", url)
        // 创建视图前先cache可以提升效率
        val df = session.read.format("jdbc").options(prop).load().cache()
        df.createOrReplaceTempView("running_jobs")
        println("------------------- 查询mysql中的数据 -------------------")
        df.show()


        println("------------------- 插入数据到Hive -------------------")
        val hsql =
            """
              |insert into test.running_jobs select * from running_jobs
              |""".stripMargin
        session.sql(hsql)

    }
}

三、Hive2Vertica

package com

import org.apache.spark.sql.SparkSession

import java.util.Properties

object SyncHiveToVertica {
    def main(args: Array[String]): Unit = {
        val session = SparkSession.builder()
                .appName(this.getClass.getSimpleName)
                .master("local")
                .enableHiveSupport()
                .getOrCreate()

        val hsql = "select * from test.running_jobs"
        val df = session.sql(hsql).cache()
        df.createOrReplaceTempView("running_jobs")
        println("------------------- 查询Hive中的数据 -------------------")
        df.show()

        // vertica配置
        val url = "jdbc:vertica://vertica.hl.com:5433/vertica"
        val prop = new Properties()
        prop.put("user", "mydba")
        prop.put("password", "mydba")
        prop.put("driver", "com.vertica.jdbc.Driver")

        println("------------------- 插入数据到Vertica -------------------")
        val vsql =
            """
              |select * from running_jobs
              |""".stripMargin

        session.sql(vsql).write.mode("append").jdbc(url, "report.running_jobs", prop)

    }
}