Flink 入门程序WordCount

一 项目依赖

<dependencies>
    <dependency>
        <groupId>org.apache.flink</groupId>
        <artifactId>flink-scala_2.11</artifactId>
        <version>1.7.2</version>
    </dependency>

        <dependency>
            <groupId>org.apache.flink</groupId>
            <artifactId>flink-streaming-scala_2.11</artifactId>
            <version>1.7.2</version>
        </dependency>

    </dependencies>
    <build>
        <plugins>
            <!-- 该插件用于将Scala代码编译成class文件 -->
            <plugin>
                <groupId>net.alchim31.maven</groupId>
                <artifactId>scala-maven-plugin</artifactId>
                <version>3.4.6</version>
                <executions>
                    <execution>
                        <!-- 声明绑定到maven的compile阶段 -->
                        <goals>
                            <goal>testCompile</goal>
                        </goals>
                    </execution>
                </executions>
            </plugin>
            <plugin>
                <groupId>org.apache.maven.plugins</groupId>
                <artifactId>maven-assembly-plugin</artifactId>
                <version>3.0.0</version>
                <configuration>
                    <descriptorRefs>
                        <descriptorRef>jar-with-dependencies</descriptorRef>
                    </descriptorRefs>
                </configuration>
                <executions>
                    <execution>
                        <id>make-assembly</id>
                        <phase>package</phase>
                        <goals>
                            <goal>single</goal>
                        </goals>
                    </execution>
                </executions>
            </plugin>
        </plugins>
    </build>

二 编码

2.1 批处理

从文件读取数据，对数据进行切分求wordcount

package com.gc.wc
import org.apache.flink.api.java.utils.ParameterTool
import org.apache.flink.api.scala._
object BatchWordCount {
  def main(args: Array[String]): Unit = {
    val tool: ParameterTool = ParameterTool.fromArgs(args)
    // 批处理执行环境
    val env: ExecutionEnvironment = ExecutionEnvironment.getExecutionEnvironment
    // dataSet 批处理
    val dataSet: DataSet[String] = env.readTextFile(tool.get("path"))
    var res: AggregateDataSet[(String, Int)] =dataSet.filter(_.nonEmpty)
      .flatMap(_.split("\\W+"))
      .map((_,1))
      .groupBy(0)
      .sum(1)
      res.print()
  }
}

2.2 流式WordCount

从scoket流中持续获取数据，对数据进行累加计算

package com.gc.wc

import org.apache.flink.api.java.utils.ParameterTool
import org.apache.flink.streaming.api.scala._

/**
  * flink 流式处理
  */
object StreamWordCount {
  def main(args: Array[String]): Unit = {
    val params: ParameterTool =  ParameterTool.fromArgs(args)
    val host: String = params.get("host")
    val port: Int = params.getInt("port")
    // 流处理执行环境StreamExecutionEnvironment
    val env: StreamExecutionEnvironment = StreamExecutionEnvironment.getExecutionEnvironment
    // DataStream 
    val dataStream: DataStream[String] = env.socketTextStream(host,port)
    val res: DataStream[(String, Int)] =dataStream.filter(_.nonEmpty)
      .flatMap(_.split("\\W+"))
      .map((_,1))
      .keyBy(0)
      .sum(1)
    res.print() //打印
    env.execute("StreamWordCount") // 执行
  }
}