SparkStreaming 处理端口数据,输出到MySQL

pom文件:

<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/maven-v4_0_0.xsd">
  <modelVersion>4.0.0</modelVersion>
  <groupId>com.imooc.spark</groupId>
  <artifactId>sparktrain</artifactId>
  <version>1.0</version>
  <inceptionYear>2008</inceptionYear>
  <properties>
    <scala.version>2.11.8</scala.version>
    <kafka.version>0.9.0.0</kafka.version>
    <spark.version>2.2.0</spark.version>
    <hadoop.version>2.6.0-cdh5.7.0</hadoop.version>
    <hbase.version>1.2.0-cdh5.7.0</hbase.version>
  </properties>

  <!--添加cloudera的repository-->
  <repositories>
    <repository>
      <id>cloudera</id>
      <url>https://repository.cloudera.com/artifactory/cloudera-repos</url>
    </repository>
  </repositories>

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

    <!-- Kafka 依赖-->
    <!--
    <dependency>
        <groupId>org.apache.kafka</groupId>
        <artifactId>kafka_2.11</artifactId>
        <version>${kafka.version}</version>
    </dependency>
    -->

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

    <!-- HBase 依赖-->
    <!--<dependency>
      <groupId>org.apache.hbase</groupId>
      <artifactId>hbase-client</artifactId>
      <version>${hbase.version}</version>
    </dependency>

    <dependency>
      <groupId>org.apache.hbase</groupId>
      <artifactId>hbase-server</artifactId>
      <version>${hbase.version}</version>
    </dependency>-->

    <!-- Spark Streaming 依赖-->
    <dependency>
      <groupId>org.apache.spark</groupId>
      <artifactId>spark-streaming_2.11</artifactId>
      <version>${spark.version}</version>
    </dependency>


    <!-- Spark Streaming整合Flume 依赖-->
    <dependency>
      <groupId>org.apache.spark</groupId>
      <artifactId>spark-streaming-flume_2.11</artifactId>
      <version>${spark.version}</version>
    </dependency>

    <dependency>
      <groupId>org.apache.spark</groupId>
      <artifactId>spark-streaming-flume-sink_2.11</artifactId>
      <version>${spark.version}</version>
    </dependency>

    <dependency>
      <groupId>org.apache.spark</groupId>
      <artifactId>spark-streaming-kafka-0-8_2.11</artifactId>
      <version>${spark.version}</version>
    </dependency>

    <dependency>
      <groupId>org.apache.commons</groupId>
      <artifactId>commons-lang3</artifactId>
      <version>3.5</version>
    </dependency>

    <!-- Spark SQL 依赖-->
    <dependency>
      <groupId>org.apache.spark</groupId>
      <artifactId>spark-sql_2.11</artifactId>
      <version>${spark.version}</version>
    </dependency>


    <dependency>
      <groupId>com.fasterxml.jackson.module</groupId>
      <artifactId>jackson-module-scala_2.11</artifactId>
      <version>2.6.5</version>
    </dependency>

    <dependency>
      <groupId>net.jpountz.lz4</groupId>
      <artifactId>lz4</artifactId>
      <version>1.3.0</version>
    </dependency>

    <dependency>
      <groupId>mysql</groupId>
      <artifactId>mysql-connector-java</artifactId>
      <version>5.1.38</version>
    </dependency>

    <dependency>
      <groupId>org.apache.flume.flume-ng-clients</groupId>
      <artifactId>flume-ng-log4jappender</artifactId>
      <version>1.6.0</version>
    </dependency>

  </dependencies>

  <build>
    <!--
    <sourceDirectory>src/main/scala</sourceDirectory>
    <testSourceDirectory>src/test/scala</testSourceDirectory>
    -->
    <plugins>
      <plugin>
        <groupId>org.scala-tools</groupId>
        <artifactId>maven-scala-plugin</artifactId>
        <executions>
          <execution>
            <goals>
              <goal>compile</goal>
              <goal>testCompile</goal>
            </goals>
          </execution>
        </executions>
        <configuration>
          <scalaVersion>${scala.version}</scalaVersion>
          <args>
            <arg>-target:jvm-1.5</arg>
          </args>
        </configuration>
      </plugin>
      <plugin>
        <groupId>org.apache.maven.plugins</groupId>
        <artifactId>maven-eclipse-plugin</artifactId>
        <configuration>
          <downloadSources>true</downloadSources>
          <buildcommands>
            <buildcommand>ch.epfl.lamp.sdt.core.scalabuilder</buildcommand>
          </buildcommands>
          <additionalProjectnatures>
            <projectnature>ch.epfl.lamp.sdt.core.scalanature</projectnature>
          </additionalProjectnatures>
          <classpathContainers>
            <classpathContainer>org.eclipse.jdt.launching.JRE_CONTAINER</classpathContainer>
            <classpathContainer>ch.epfl.lamp.sdt.launching.SCALA_CONTAINER</classpathContainer>
          </classpathContainers>
        </configuration>
      </plugin>
    </plugins>
  </build>
  <reporting>
    <plugins>
      <plugin>
        <groupId>org.scala-tools</groupId>
        <artifactId>maven-scala-plugin</artifactId>
        <configuration>
          <scalaVersion>${scala.version}</scalaVersion>
        </configuration>
      </plugin>
    </plugins>
  </reporting>
</project>

建表语句:

create table wordcount(
word varchar(50) default null,
wordcount int(10) default null
);

源码:

package com.imooc

import java.sql.DriverManager

import org.apache.spark.SparkConf
import org.apache.spark.streaming.{Seconds, StreamingContext}

// 运算结果输出到mysql
object ForeachRDDApp {
  def main(args: Array[String]): Unit = {

    val sparkConf = new SparkConf().setMaster("local[*]").setAppName("StatefulWordCount")
    val ssc = new StreamingContext(sparkConf, Seconds(5))

    // 如果使用了stateful的算子,必须要设置checkpoint(因为要存旧的值)
    // 在生产环境中,建议把checkpoint设置到HDFS的某个文件夹中
    ssc.checkpoint(".")

    val lines = ssc.socketTextStream("192.168.108.41", 6789)

    val result = lines.flatMap(_.split(" ")).map((_, 1)).reduceByKey(_ + _)

    // state.print()  // 此处仅仅是将结果输出到控制台

    result.print()
    // 将结果写入到MySQL
    /*这是不正确的,因为这需要将连接对象序列化并从 driver 发送到 worker。
    这种连接对象很少能跨机器转移。此错误可能会显示为序列化错误(连接对象不可序列化),
    初始化错误(连接对象需要在 worker 初始化)等。正确的解决方案是在 worker 创建连接对象。*/
    //    result.foreachRDD(rdd =>{
    //      val connection = createConnection()
    //      rdd.foreach { record =>
    //        val sql = "insert into wordcount(word, wordcount) values('"+record._1 + "'," + record._2 +")"
    //        connection.createStatement().execute(sql)
    //      }
    //    })

    result.foreachRDD { rdd =>
      rdd.foreachPartition { partitionOfRecords =>
        val connection = createConnection()
        partitionOfRecords.foreach(record => {
          val sql = "insert into wordcount(word, wordcount) values('" + record._1 + "'," + record._2 + ")"
          connection.createStatement().execute(sql)
        })
        connection.close()
      }
    }

    ssc.start()
    ssc.awaitTermination()
  }

  // 获取MySQL的连接
  def createConnection() = {
    Class.forName("com.mysql.jdbc.Driver")
    DriverManager.getConnection("jdbc:mysql://localhost:3306/imooc_spark", "root", "root")
  }
}

 

 

发布了63 篇原创文章 · 获赞 15 · 访问量 4万+
展开阅读全文

没有更多推荐了,返回首页

©️2019 CSDN 皮肤主题: 大白 设计师: CSDN官方博客

分享到微信朋友圈

×

扫一扫,手机浏览