Flink版WordCount（Streaming and Batch）_flink wordcount stream版本-优快云博客

本文链接：https://blog.youkuaiyun.com/weixin_43823423/article/details/89888962

Flink 程序开发步骤

1：获得一个执行环境

2：加载/创建初始化数据

3：指定操作数据的transaction算子

4：指定把计算好的数据放在哪

5：调用execute()触发执行程序

注意：Flink程序是延迟计算的，只有最后调用execute()方法的时候才会真正触发执行程序。

延迟计算好处：你可以开发复杂的程序，但是Flink可以将复杂的程序转成一个Plan，将Plan作为一个整体单元执行！

一、Flink StreamingWindowWordCount

需求分析：

手工通过socket实时产生一些单词，使用flink实时接收数据，对指定时间窗口内(例如：2秒)的数据进行聚合统计，并且把时间窗口内计算的结果打印出来

执行：

在hadoop100上执行 nc -l 9000
在本机启动idea中的代码

执行代码：

import org.apache.flink.api.java.utils.ParameterTool
import org.apache.flink.streaming.api.scala.StreamExecutionEnvironment
import org.apache.flink.streaming.api.windowing.time.Time
/**
  * 滑动窗口计算
  *
  * 每一秒统计最近2秒内的数据，打印到控制台
  *
  * */
object SockWindowCountScala {
  def main(args: Array[String]): Unit = {
    //获取socket端口号
    val port: Int = try{
         ParameterTool.fromArgs(args).getInt("port")
        }catch{
      case e:Exception=>{
        System.err.println("No port set use default port 9000")
      }
       9000
    }
    //获取运行环境
     val env:StreamExecutionEnvironment = StreamExecutionEnvironment.getExecutionEnvironment

    //获取运行环境
    val text = env.socketTextStream("qyl01",port,'\n')

   //解析数据(把数据打平)，分组，窗口计算，并且聚合求sum

    //必须导入隐式转换，否则会报错
    import org.apache.flink.api.scala._
    val windowcounts = text.flatMap(line => line.split("\\s"))
      .map(w => wordwithcount(w, 1))
      .keyBy("word")
      .timeWindow(Time.seconds(2), Time.seconds(1))
      .sum("count")



    //打印到控制台
    windowcounts.print().setParallelism(1)

    //执行任务
    env.execute("scoket window count")

  }
  case class wordwithcount(word:String,count:Long)

}

二、Flink BatchWordCount-scala

需求分析：

将本地文件中的单词进行统计

代码实现：

import org.apache.flink.api.scala.{DataSet, ExecutionEnvironment}

object batchWordCountScala {
  def main(args: Array[String]): Unit = {
    val input = "D:\\data\\file"
    val output = "D:\\data\\result"

    val env = ExecutionEnvironment.getExecutionEnvironment
    val text: DataSet[String] = env.readTextFile(input)

     import org.apache.flink.api.scala._
    val counts = text.flatMap(_.toLowerCase.split("\\s"))
      .filter(_.nonEmpty)
      .map((_, 1))
      .groupBy(0)
      .sum(1)

    counts.writeAsCsv(output,"\n"," ").setParallelism(1)
    env.execute("bath word count")

  }
}

三、Flink Streaming和Batch的区别

流处理Streaming：

StreamExecutionEnvironment

DataStreaming

批处理Batch：

ExecutionEnvironment

DataSet

四、Flink依赖

<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>flink</groupId>
  <artifactId>finkexample</artifactId>
  <version>1.0-SNAPSHOT</version>
  <inceptionYear>2008</inceptionYear>
  <properties>
    <scala.version>2.11.0</scala.version>
  </properties>

  <repositories>
    <repository>
      <id>scala-tools.org</id>
      <name>Scala-Tools Maven2 Repository</name>
      <url>http://scala-tools.org/repo-releases</url>
    </repository>
  </repositories>

  <pluginRepositories>
    <pluginRepository>
      <id>scala-tools.org</id>
      <name>Scala-Tools Maven2 Repository</name>
      <url>http://scala-tools.org/repo-releases</url>
    </pluginRepository>
  </pluginRepositories>

    <dependencies>
        <dependency>
            <groupId>org.apache.flink</groupId>
            <artifactId>flink-java</artifactId>
            <version>1.6.1</version>
            <!-- provided在这表示此依赖只在代码编译的时候使用，运行和打包的时候不使用 -->
            <!--<scope>provided</scope>-->
        </dependency>
        <dependency>
            <groupId>org.apache.flink</groupId>
            <artifactId>flink-streaming-java_2.11</artifactId>
            <version>1.6.1</version>
            <!--<scope>provided</scope>-->
        </dependency>
        <dependency>
            <groupId>org.apache.flink</groupId>
            <artifactId>flink-scala_2.11</artifactId>
            <version>1.6.1</version>
            <!--<scope>provided</scope>-->
        </dependency>
        <dependency>
            <groupId>org.apache.flink</groupId>
            <artifactId>flink-streaming-scala_2.11</artifactId>
            <version>1.6.1</version>
            <!--<scope>provided</scope>-->
        </dependency>

        <dependency>
            <groupId>org.apache.bahir</groupId>
            <artifactId>flink-connector-redis_2.11</artifactId>
            <version>1.0</version>
        </dependency>

        <dependency>
            <groupId>org.apache.flink</groupId>
            <artifactId>flink-statebackend-rocksdb_2.11</artifactId>
            <version>1.6.1</version>
        </dependency>

        <dependency>
            <groupId>org.apache.flink</groupId>
            <artifactId>flink-connector-kafka-0.11_2.11</artifactId>
            <version>1.6.1</version>
        </dependency>

        <dependency>
            <groupId>org.apache.kafka</groupId>
            <artifactId>kafka-clients</artifactId>
            <version>0.11.0.3</version>
        </dependency>

        <dependency>
            <groupId>org.slf4j</groupId>
            <artifactId>slf4j-api</artifactId>
            <version>1.7.25</version>
        </dependency>

        <dependency>
            <groupId>org.slf4j</groupId>
            <artifactId>slf4j-log4j12</artifactId>
            <version>1.7.25</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>