Spark SQL的jdbc操作

最新推荐文章于 2024-06-01 08:50:02 发布

原创最新推荐文章于 2024-06-01 08:50:02 发布 · 788 阅读

1 ·

CC 4.0 BY-SA版权

文章标签：

#Spark SQL #hadoop

Hadoop 专栏收录该内容

20 篇文章

订阅专栏

本文介绍如何使用Apache Spark通过Scala编程实现与MySQL数据库的数据交互，包括从MySQL加载数据到Spark RDD进行处理，以及将处理后的数据写回MySQL的过程。

1、创建IDEA的Maven工程

2、引入依赖

<?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.motoon</groupId>
    <artifactId>SparkSql_Demo</artifactId>
    <version>1.0</version>

    <properties>
        <maven.compiler.source>1.7</maven.compiler.source>
        <maven.compiler.target>1.7</maven.compiler.target>
        <encoding>UTF-8</encoding>
        <scala.version>2.10.6</scala.version>
        <scala.compat.version>2.10</scala.compat.version>
    </properties>
    <dependencies>
        <dependency>
            <groupId>org.scala-lang</groupId>
            <artifactId>scala-library</artifactId>
            <version>${scala.version}</version>
        </dependency>
        <dependency>
            <groupId>org.apache.spark</groupId>
            <artifactId>spark-core_2.10</artifactId>
            <version>1.5.2</version>
        </dependency>
        <dependency>
            <groupId>org.apache.spark</groupId>
            <artifactId>spark-streaming_2.10</artifactId>
            <version>1.5.2</version>
        </dependency>
        <dependency>
            <groupId>org.apache.spark</groupId>
            <artifactId>spark-sql_2.10</artifactId>
            <version>1.5.2</version>
        </dependency>
        <dependency>
            <groupId>org.apache.hadoop</groupId>
            <artifactId>hadoop-client</artifactId>
            <version>2.6.2</version>
        </dependency>

        <dependency>
            <groupId>mysql</groupId>
            <artifactId>mysql-connector-java</artifactId>
            <version>5.1.39</version>
        </dependency>
    </dependencies>

    <build>
        <sourceDirectory>src/main/scala</sourceDirectory>
        <testSourceDirectory>src/test/scala</testSourceDirectory>
        <plugins>
            <plugin>
                <groupId>net.alchim31.maven</groupId>
                <artifactId>scala-maven-plugin</artifactId>
                <version>3.2.0</version>
                <executions>
                    <execution>
                        <goals>
                            <goal>compile</goal>
                            <goal>testCompile</goal>
                        </goals>
                        <configuration>
                            <args>
                                <arg>-make:transitive</arg>
                                <arg>-dependencyfile</arg>
                                <arg>${project.build.directory}/.scala_dependencies</arg>
                            </args>
                        </configuration>
                    </execution>
                </executions>
            </plugin>
            <plugin>
                <groupId>org.apache.maven.plugins</groupId>
                <artifactId>maven-surefire-plugin</artifactId>
                <version>2.18.1</version>
                <configuration>
                    <useFile>false</useFile>
                    <disableXmlReport>true</disableXmlReport>
                    <includes>
                        <include>**/*Test.*</include>
                        <include>**/*Suite.*</include>
                    </includes>
                </configuration>
            </plugin>

            <plugin>
                <groupId>org.apache.maven.plugins</groupId>
                <artifactId>maven-shade-plugin</artifactId>
                <version>2.3</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>
                        </configuration>
                    </execution>
                </executions>
            </plugin>
        </plugins>
    </build>


</project>

3、从mysql中加载数据，新建scala类

package com.motoon.sparksql

import java.sql.DriverManager
import org.apache.spark.rdd.JdbcRDD
import org.apache.spark.{SparkConf, SparkContext}

/**
  * by rjsong
  */
object JdbcRDDDemo {

  def main(args: Array[String]): Unit = {
    val conf = new SparkConf().setAppName("JdbcRDDDemo").setMaster("local[2]")
    val sc = new SparkContext(conf)
    val connection = () => {
      Class.forName("com.mysql.jdbc.Driver").newInstance()
      DriverManager.getConnection("jdbc:mysql://127.0.0.1:3306/bigdata","root","root")
    }
    //这个地方没有读取数据(数据库表也用的是person)
    val jdbcRDD = new JdbcRDD(
      sc,
      connection,
      "SELECT * FROM person where id >= ? AND id <= ?",
      //这里表示从取数据库中的第1、2、3、4条数据，然后分两个区
      1, 4, 2,
      r => {
        val id = r.getInt(1)
        val code = r.getString(2)
        (id, code)
      }
    )
    //这里相当于是action获取到数据
    val jrdd = jdbcRDD.collect()
    println(jrdd.toBuffer)
    sc.stop()
  }
}

4、将数据写入到mysql中，新建scala类

package com.motoon.sparksql

import java.util.Properties
import org.apache.spark.sql.{SQLContext, Row}
import org.apache.spark.sql.types.{StringType, IntegerType, StructField, StructType}
import org.apache.spark.{SparkConf, SparkContext}

import java.sql.{DriverManager, PreparedStatement, Connection}
import org.apache.spark.{SparkContext, SparkConf}

object RDDToMysql {

  case class Blog(name: String, count: Int)

  def myFun(iterator: Iterator[(String, Int)]): Unit = {
    var conn: Connection = null
    var ps: PreparedStatement = null
    val sql = "insert into blog(name, count) values (?, ?)"
    try {
      conn = DriverManager.getConnection("jdbc:mysql://127.0.0.1:3306/bigdata", "root", "root")
      iterator.foreach(data => {
        ps = conn.prepareStatement(sql)
        ps.setString(1, data._1)
        ps.setInt(2, data._2)
        ps.executeUpdate()
      }
      )
    } catch {
      case e: Exception => println("Mysql Exception")
    } finally {
      if (ps != null) {
        ps.close()
      }
      if (conn != null) {
        conn.close()
      }
    }
  }

  def main(args: Array[String]) {
    val conf = new SparkConf().setAppName("RDDToMysql").setMaster("local")
    val sc = new SparkContext(conf)
    val data = sc.parallelize(List(("www", 10), ("iteblog", 20), ("com", 30)))
    data.foreachPartition(myFun)
  }
}