Spark TopN

<?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>cn.edu360.spark</groupId>
    <artifactId>SparkTest</artifactId>
    <version>1.0-SNAPSHOT</version>

    <properties>
        <maven.compiler.source>1.8</maven.compiler.source>
        <maven.compiler.target>1.8</maven.compiler.target>
        <scala.version>2.11.8</scala.version>
        <spark.version>2.2.0</spark.version>
        <hadoop.version>2.7.3</hadoop.version>
        <encoding>UTF-8</encoding>
    </properties>

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

        <!-- 导入spark的依赖 -->
        <dependency>
            <groupId>org.apache.spark</groupId>
            <artifactId>spark-core_2.11</artifactId>
            <version>${spark.version}</version>
        </dependency>

        <!-- 指定hadoop-client API的版本 -->
        <dependency>
            <groupId>org.apache.hadoop</groupId>
            <artifactId>hadoop-client</artifactId>
            <version>${hadoop.version}</version>
        </dependency>

        <!-- mysql的连接驱动依赖 -->
        <dependency>
            <groupId>mysql</groupId>
            <artifactId>mysql-connector-java</artifactId>
            <version>5.1.38</version>
        </dependency>

    </dependencies>

    <build>
        <pluginManagement>
            <plugins>
                <!-- 编译scala的插件 -->
                <plugin>
                    <groupId>net.alchim31.maven</groupId>
                    <artifactId>scala-maven-plugin</artifactId>
                    <version>3.2.2</version>
                </plugin>
                <!-- 编译java的插件 -->
                <plugin>
                    <groupId>org.apache.maven.plugins</groupId>
                    <artifactId>maven-compiler-plugin</artifactId>
                    <version>3.5.1</version>
                </plugin>
            </plugins>
        </pluginManagement>
        <plugins>
            <plugin>
                <groupId>net.alchim31.maven</groupId>
                <artifactId>scala-maven-plugin</artifactId>
                <executions>
                    <execution>
                        <id>scala-compile-first</id>
                        <phase>process-resources</phase>
                        <goals>
                            <goal>add-source</goal>
                            <goal>compile</goal>
                        </goals>
                    </execution>
                    <execution>
                        <id>scala-test-compile</id>
                        <phase>process-test-resources</phase>
                        <goals>
                            <goal>testCompile</goal>
                        </goals>
                    </execution>
                </executions>
            </plugin>

            <plugin>
                <groupId>org.apache.maven.plugins</groupId>
                <artifactId>maven-compiler-plugin</artifactId>
                <executions>
                    <execution>
                        <phase>compile</phase>
                        <goals>
                            <goal>compile</goal>
                        </goals>
                    </execution>
                </executions>
            </plugin>


            <!-- 打jar插件 -->
            <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>
                        </configuration>
                    </execution>
                </executions>
            </plugin>
        </plugins>
    </build>

</project>

 

工具类：

package cn.edu360.day4

import java.sql.{Connection, DriverManager, PreparedStatement}

import scala.io.{BufferedSource, Source}

/**
  * Created by lisheng on 2018/9/9.
  */
object MyUtils {

  def ip2Long(ip: String): Long = {
    val fragments = ip.split("[.]")
    var ipNum = 0L
    for (i <- 0 until fragments.length){
      ipNum =  fragments(i).toLong | ipNum << 8L
    }
    ipNum
  }

  def readRules(path: String): Array[(Long, Long, String)] = {
    //读取ip规则
    val bf: BufferedSource = Source.fromFile(path)
    val lines: Iterator[String] = bf.getLines()
    //对ip规则进行整理，并放入到内存
    val rules: Array[(Long, Long, String)] = lines.map(line => {
      val fileds = line.split("[|]")
      val startNum = fileds(2).toLong
      val endNum = fileds(3).toLong
      val province = fileds(6)
      (startNum, endNum, province)
    }).toArray
    rules
  }

  def binarySearch(lines: Array[(Long, Long, String)], ip: Long) : Int = {
    var low = 0
    var high = lines.length - 1
    while (low <= high) {
      val middle = (low + high) / 2
      if ((ip >= lines(middle)._1) && (ip <= lines(middle)._2))
        return middle
      if (ip < lines(middle)._1)
        high = middle - 1
      else {
        low = middle + 1
      }
    }
    -1
  }

  def data2MySQL(it: Iterator[(String, Int)]): Unit = {
    //一个迭代器代表一个分区，分区中有多条数据
    //先获得一个JDBC连接
    val conn: Connection = DriverManager.getConnection("jdbc:mysql://localhost:3306/bigdata?characterEncoding=UTF-8", "root", "123568")
    //将数据通过Connection写入到数据库
    val pstm: PreparedStatement = conn.prepareStatement("INSERT INTO access_log VALUES (?, ?)")
    //将分区中的数据一条一条写入到MySQL中
    it.foreach(tp => {
      pstm.setString(1, tp._1)
      pstm.setInt(2, tp._2)
      pstm.executeUpdate()
    })
    //将分区中的数据全部写完之后，在关闭连接
    if(pstm != null) {
      pstm.close()
    }
    if (conn != null) {
      conn.close()
    }
  }


  def main(args: Array[String]): Unit = {
    //数据是在内存中
    val rules: Array[(Long, Long, String)] = readRules("/Users/zx/Desktop/ip/ip.txt")
    //将ip地址转换成十进制
    val ipNum = ip2Long("114.215.43.42")
    //查找
    val index = binarySearch(rules, ipNum)
    //根据脚本到rules中查找对应的数据
    val tp = rules(index)
    val province = tp._3
    println(province)

  }
}

 

实现

package cn.edu360.day4

import java.sql.{Connection, DriverManager, PreparedStatement}

import org.apache.spark.broadcast.Broadcast
import org.apache.spark.rdd.RDD
import org.apache.spark.{SparkConf, SparkContext}

/**
  * Created by lisheng on 2018/9/9.
  */
object IpLoaction2 {

  def main(args: Array[String]): Unit = {

    val conf = new SparkConf().setAppName("IpLoaction1").setMaster("local[4]")

    val sc = new SparkContext(conf)

    //取到HDFS中的ip规则
    val rulesLines:RDD[String] = sc.textFile(args(0))
    //整理ip规则数据
    val ipRulesRDD: RDD[(Long, Long, String)] = rulesLines.map(line => {
      val fields = line.split("[|]")
      val startNum = fields(2).toLong
      val endNum = fields(3).toLong
      val province = fields(6)
      (startNum, endNum, province)
    })

    //将分散在多个Executor中的部分IP规则收集到Driver端
    val rulesInDriver: Array[(Long, Long, String)] = ipRulesRDD.collect()

    //将Driver端的数据广播到Executor
    //广播变量的引用（还在Driver端）
    val broadcastRef: Broadcast[Array[(Long, Long, String)]] = sc.broadcast(rulesInDriver)

    //创建RDD，读取访问日志
    val accessLines: RDD[String] = sc.textFile(args(1))

    //整理数据
    val proviceAndOne: RDD[(String, Int)] = accessLines.map(log => {
      //将log日志的每一行进行切分
      val fields = log.split("[|]")
      val ip = fields(1)
      //将ip转换成十进制
      val ipNum = MyUtils.ip2Long(ip)
      //进行二分法查找，通过Driver端的引用或取到Executor中的广播变量
      //（该函数中的代码是在Executor中别调用执行的，通过广播变量的引用，就可以拿到当前Executor中的广播的规则了）
      //Driver端广播变量的引用是怎样跑到Executor中的呢？
      //Task是在Driver端生成的，广播变量的引用是伴随着Task被发送到Executor中的
      val rulesInExecutor: Array[(Long, Long, String)] = broadcastRef.value
      //查找
      var province = "未知"
      val index = MyUtils.binarySearch(rulesInExecutor, ipNum)
      if (index != -1) {
        province = rulesInExecutor(index)._3
      }
      (province, 1)
    })

    //聚合
    //val sum = (x: Int, y: Int) => x + y
    val reduced: RDD[(String, Int)] = proviceAndOne.reduceByKey(_+_)

    //将结果打印
    //val r = reduced.collect()
    //println(r.toBuffer)


    /**
    reduced.foreach(tp => {
      //将数据写入到MySQL中
      //问？在哪一端获取到MySQL的链接的？
      //是在Executor中的Task获取的JDBC连接
      val conn: Connection = DriverManager.getConnection("jdbc:mysql://localhost:3306/bigdata?charatorEncoding=utf-8", "root", "123568")
      //写入大量数据的时候，有没有问题？
      val pstm = conn.prepareStatement("...")
      pstm.setString(1, tp._1)
      pstm.setInt(2, tp._2)
      pstm.executeUpdate()
      pstm.close()
      conn.close()
    })
      */

    //一次拿出一个分区(一个分区用一个连接，可以将一个分区中的多条数据写完在释放jdbc连接，这样更节省资源)
//    reduced.foreachPartition(it => {
//      val conn: Connection = DriverManager.getConnection("jdbc:mysql://localhost:3306/bigdata?characterEncoding=UTF-8", "root", "123568")
//      //将数据通过Connection写入到数据库
//      val pstm: PreparedStatement = conn.prepareStatement("INSERT INTO access_log VALUES (?, ?)")
//      //将一个分区中的每一条数据拿出来
//      it.foreach(tp => {
//        pstm.setString(1, tp._1)
//        pstm.setInt(2, tp._2)
//        pstm.executeUpdate()
//      })
//      pstm.close()
//      conn.close()
//    })

    reduced.foreachPartition(it => MyUtils.data2MySQL(it))


    sc.stop()



  }
}