一、Flink基礎 之 wordcount

---

一、搭建maven工程

1.1 pom 文件

<?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.kino.flnk</groupId>
    <artifactId>flink</artifactId>
    <version>1.0-SNAPSHOT</version>

    <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>
            <!-- 該插件用於將Scala代碼編譯成class文件 -->
            <plugin>
                <groupId>net.alchim31.maven</groupId>
                <artifactId>scala-maven-plugin</artifactId>
                <version>3.4.6</version>
                <executions>
                    <execution>
                        <!-- 聲明綁定到maven的compile階段 -->
                        <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>
</project>

---

1.2 添加scala框架 和 scala文件夾

---

1.3 批處理wordcount

flink\src\main\scala\WordCount.scala

import org.apache.flink.api.scala._

/**
  * @author kino
  * @date 2020/4/9 19:56
  * @version 1.0.0
  */
object WordCount {
    def main(args: Array[String]): Unit = {
        // 創建執行環境
        val env = ExecutionEnvironment.getExecutionEnvironment
        // 從文件中讀取數據
        val inputPath = "D:\\Work\\idea\\flink\\src\\main\\resources\\hello.txt"
        val inputDS: DataSet[String] = env.readTextFile(inputPath)
        // 分詞之後，對單詞進行groupby分組，然後用sum進行聚合
        val wordCountDS =
            inputDS.flatMap(_.split(" "))
          .map((_,1))
        
        // 打印輸出
        wordCountDS.print()
    }
}

---

1.4 流處理 wordcount

flink\src\main\scala\StreamWordCount.scala

import org.apache.flink.api.java.utils.ParameterTool
import org.apache.flink.streaming.api.scala.{DataStream, StreamExecutionEnvironment}

/**
  * @author kino
  * @date 2020/4/9 19:57
  * @version 1.0.0
  */
object StreamWordCount {
    def main(args: Array[String]): Unit = {
        // 從外部命令中獲取參數
        val params: ParameterTool =  ParameterTool.fromArgs(args)
        val host: String = params.get("host")
        val port: Int = params.getInt("port")

        // 創建流處理環境
        val env = StreamExecutionEnvironment.getExecutionEnvironment
        // 接收socket文本流
        val textDstream: DataStream[String] = env.socketTextStream(host, port)

        // flatMap和Map需要引用的隱式轉換
        import org.apache.flink.api.scala._
        val dataStream: DataStream[(String, Int)] = textDstream.flatMap(_.split("\\s")).filter(_.nonEmpty).map((_, 1)).keyBy(0).sum(1)

        dataStream.print().setParallelism(1)

        // 啓動executor，執行任務
        env.execute("Socket stream word count")
    }
}

測試——window用netcat命令進行發送測試