flink03-入门demo

1.pom.xml

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

    <dependencies>
        <dependency>
            <groupId>org.apache.flink</groupId>
            <artifactId>flink-scala_2.11</artifactId>
            <version>1.7.0</version>
        </dependency>

        <!-- https://mvnrepository.com/artifact/org.apache.flink/flink-streaming-scala -->
        <dependency>
            <groupId>org.apache.flink</groupId>
            <artifactId>flink-streaming-scala_2.11</artifactId>
            <version>1.7.0</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>compile</goal>
                    <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>

2.批处理wordcount

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

  //构造执行环境
  val env: ExecutionEnvironment = ExecutionEnvironment.getExecutionEnvironment
  //读取文件
  val input = "file:///d:/temp/hello.txt"
  val ds: DataSet[String] = env.readTextFile(input)
  // 其中flatMap 和Map 中  需要引入隐式转换
  import org.apache.flink.api.scala.createTypeInformation
  //经过groupby进行分组，sum进行聚合
  val aggDs: AggregateDataSet[(String, Int)] = ds.flatMap(_.split(" ")).map((_, 1)).groupBy(0).sum(1)
  // 打印
  aggDs.print()

}

3.流处理

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

object StreamWcApp {

  def main(args: Array[String]): Unit = {
    //从外部命令中获取参数
    val tool: ParameterTool = ParameterTool.fromArgs(args)
    val host: String = tool.get("host")
    val port: Int = tool.get("port").toInt

    //创建流处理环境
    val env: StreamExecutionEnvironment = StreamExecutionEnvironment.getExecutionEnvironment
    //接收socket文本流
    val textDstream: DataStream[String] = env.socketTextStream(host,port)
   // flatMap和Map需要引用的隐式转换
    import org.apache.flink.api.scala._
   //处理 分组并且sum聚合
    val dStream: DataStream[(String, Int)] = textDstream.flatMap(_.split(" ")).filter(_.nonEmpty).map((_,1)).keyBy(0).sum(1)
   //打印
    dStream.print()
    
    env.execute()
  }