ApacheFlink简单的构建一个应用程序

参考链接:https://ververica.cn/developers/build-from-zero/

简单的构建一个ApacheFlink的应用程序

开发环境的准备：

这里我是在Windows上运行的。在本地机器上需要有Java8.x和maven环境
首先我们创建一个Maven工程
pom如下：

<?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>flinkdemo</groupId>
  <artifactId>flinkdemo</artifactId>
  <version>1.0-SNAPSHOT</version>

  <name>flinkdemo</name>
  <!-- FIXME change it to the project's website -->
  <url>http://www.example.com</url>

  <properties>
    <project.build.sourceEncoding>UTF-8</project.build.sourceEncoding>
    <maven.compiler.source>1.7</maven.compiler.source>
    <maven.compiler.target>1.7</maven.compiler.target>
  </properties>

  <dependencies>


    <!-- https://mvnrepository.com/artifact/org.apache.flink/flink-java -->
    <dependency>
      <groupId>org.apache.flink</groupId>
      <artifactId>flink-java</artifactId>
      <version>1.6.1</version>
    </dependency>

    <!-- https://mvnrepository.com/artifact/org.apache.flink/flink-streaming-java -->

    <dependency>
      <groupId>org.apache.flink</groupId>
      <artifactId>flink-streaming-java_2.11</artifactId>
      <version>1.6.1</version>
      <scope>provided</scope>
    </dependency>





    <dependency>
      <groupId>junit</groupId>
      <artifactId>junit</artifactId>
      <version>4.11</version>
      <scope>test</scope>
    </dependency>
    <dependency>
      <groupId>org.slf4j</groupId>
      <artifactId>slf4j-log4j12</artifactId>
      <version>1.7.7</version>
      <scope>runtime</scope>
    </dependency>
    <dependency>
      <groupId>log4j</groupId>
      <artifactId>log4j</artifactId>
      <version>1.2.17</version>
      <scope>runtime</scope>
    </dependency>
  </dependencies>

  <build>
    <pluginManagement><!-- lock down plugins versions to avoid using Maven defaults (may be moved to parent pom) -->
      <plugins>
        <!-- clean lifecycle, see https://maven.apache.org/ref/current/maven-core/lifecycles.html#clean_Lifecycle -->
        <plugin>
          <artifactId>maven-clean-plugin</artifactId>
          <version>3.1.0</version>
        </plugin>
        <!-- default lifecycle, jar packaging: see https://maven.apache.org/ref/current/maven-core/default-bindings.html#Plugin_bindings_for_jar_packaging -->
        <plugin>
          <artifactId>maven-resources-plugin</artifactId>
          <version>3.0.2</version>
        </plugin>
        <plugin>
          <groupId>org.apache.maven.plugins</groupId>
          <artifactId>maven-compiler-plugin</artifactId>
          <version>3.1</version>
          <configuration>
            <source>1.8</source>
            <target>1.8</target>
          </configuration>
        </plugin>
        <plugin>
          <artifactId>maven-compiler-plugin</artifactId>
          <version>3.8.0</version>
        </plugin>
        <plugin>
          <artifactId>maven-surefire-plugin</artifactId>
          <version>2.22.1</version>
        </plugin>
        <plugin>
          <artifactId>maven-jar-plugin</artifactId>
          <version>3.0.2</version>
        </plugin>
        <plugin>
          <artifactId>maven-install-plugin</artifactId>
          <version>2.5.2</version>
        </plugin>
        <plugin>
          <artifactId>maven-deploy-plugin</artifactId>
          <version>2.8.2</version>
        </plugin>
        <!-- site lifecycle, see https://maven.apache.org/ref/current/maven-core/lifecycles.html#site_Lifecycle -->
        <plugin>
          <artifactId>maven-site-plugin</artifactId>
          <version>3.7.1</version>
        </plugin>
        <plugin>
          <artifactId>maven-project-info-reports-plugin</artifactId>
          <version>3.0.0</version>
        </plugin>
      </plugins>
    </pluginManagement>

  </build>
  <profiles>
    <profile>
      <id>add-dependencies-for-IDEA</id>

      <activation>
        <property>
          <name>idea.version</name>
        </property>
      </activation>

      <dependencies>
        <dependency>
          <groupId>org.apache.flink</groupId>
          <artifactId>flink-java</artifactId>
          <version>1.6.1</version>
          <scope>compile</scope>
        </dependency>
        <dependency>
          <groupId>org.apache.flink</groupId>
          <artifactId>flink-streaming-java_2.11</artifactId>
          <version>1.6.1</version>
          <scope>compile</scope>
        </dependency>
      </dependencies>
    </profile>
  </profiles>
</project>

工作目录：
图片说明

编写Flink程序

创建 SocketWindowWordCount.java 文件：

package FlinkDemo;
import org.apache.flink.api.common.functions.FlatMapFunction;
import org.apache.flink.api.java.tuple.Tuple2;
import org.apache.flink.streaming.api.datastream.DataStream;
import org.apache.flink.streaming.api.environment.StreamExecutionEnvironment;
import org.apache.flink.streaming.api.windowing.time.Time;
import org.apache.flink.util.Collector;

public class SocketWindowWordCount {

    public static void main(String[] args) throws Exception {

        // 创建 execution environment
        StreamExecutionEnvironment env = StreamExecutionEnvironment.getExecutionEnvironment();

        // 通过连接 socket 获取输入数据，这里连接到本地9000端口，如果9000端口已被占用，请换一个端口
        DataStream<String> text = env.socketTextStream("localhost", 9000, "\n");

        // 解析数据，按 word 分组，开窗，聚合
        DataStream<Tuple2<String, Integer>> windowCounts = text
                .flatMap(new FlatMapFunction<String, Tuple2<String, Integer>>() {
                    @Override
                    public void flatMap(String value, Collector<Tuple2<String, Integer>> out) {
                        for (String word : value.split("\\s")) {
                            out.collect(Tuple2.of(word, 1));
                        }
                    }
                })
                .keyBy(0)
                .timeWindow(Time.seconds(5))
                .sum(1);

        // 将结果打印到控制台，注意这里使用的是单线程打印，而非多线程
        windowCounts.print().setParallelism(1);

        env.execute("Socket Window WordCount");
    }
}

运行程序

要运行示例程序，首先我们在终端启动 netcat 获得输入流：
nc -lk 9000
然后直接运行SocketWindowWordCount的 main 方法。

只需要在 netcat 控制台输入单词，就能在 SocketWindowWordCount 的输出控制台看到每个单词的词频统计。如果想看到大于1的计数，请在5秒内反复键入相同的单词。
如图：
图片说明