flink入门实例-Windows下本地模式跑SocketWordCount

一、nc工具

配置windows的nc端口，在网上下载nc.exe(https://eternallybored.org/misc/netcat/)
进入解压目录运行如下命令

nc -L -p 9000 -v

使用命令开始nc制定端口为9000（nc -L -p 9000 -v） 启动插件

二、idea中配置，代码以及设置参数

maven配置：

<?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>lims</groupId>
    <artifactId>flink-project</artifactId>
    <version>1.0-SNAPSHOT</version>

    <properties>
        <flink.version>1.7.2</flink.version>
    </properties>

    <dependencies>
        <!--log4j-->
        <dependency>
            <groupId>log4j</groupId>
            <artifactId>log4j</artifactId>
            <version>1.2.17</version>
        </dependency>

        <!--flink-->
        <dependency>
            <groupId>org.apache.flink</groupId>
            <artifactId>flink-java</artifactId>
            <version>${flink.version}</version>
        </dependency>
        <dependency>
            <groupId>org.apache.flink</groupId>
            <artifactId>flink-streaming-java_2.11</artifactId>
            <version>${flink.version}</version>
        </dependency>
        <dependency>
            <groupId>org.apache.flink</groupId>
            <artifactId>flink-clients_2.11</artifactId>
            <version>${flink.version}</version>
        </dependency>
        <dependency>
            <groupId>org.apache.flink</groupId>
            <artifactId>flink-connector-wikiedits_2.11</artifactId>
            <version>${flink.version}</version>
        </dependency>
    </dependencies>

</project>

WordCount的源码：我这里直接把端口写死了

import org.apache.flink.api.common.functions.FlatMapFunction;
import org.apache.flink.api.java.utils.ParameterTool;
import org.apache.flink.streaming.api.datastream.DataStream;
import org.apache.flink.streaming.api.datastream.DataStreamSource;
import org.apache.flink.streaming.api.environment.StreamExecutionEnvironment;
import org.apache.flink.streaming.api.windowing.time.Time;
import org.apache.flink.util.Collector;


/**
 * @Description: TODO
 * @Date: 2019/12/5 20:49
 */
public class WordCount {
    public static void main(String[] args) throws Exception {
       //定义socket的端口号
        int port = 9000;
        /*try{
            ParameterTool parameterTool = ParameterTool.fromArgs(args);
            port = parameterTool.getInt("port");
        }catch (Exception e){
            System.err.println("没有指定port参数，使用默认值9000");
            port = 9000;
        }*/

        //获取运行环境
        StreamExecutionEnvironment env = StreamExecutionEnvironment.getExecutionEnvironment();

        //连接socket获取输入的数据
        DataStreamSource<String> text = env.socketTextStream("127.0.0.1", port, "\n");

        //计算数据
        DataStream<WordWithCount> windowCount = text.flatMap(new FlatMapFunction<String, WordWithCount>() {
            public void flatMap(String value, Collector<WordWithCount> out) throws Exception {
                String[] splits = value.split("\\s");
                for (String word:splits) {
                    out.collect(new WordWithCount(word,1L));
                }
            }
        })//打平操作，把每行的单词转为<word,count>类型的数据
                .keyBy("word")//针对相同的word数据进行分组
                .timeWindow(Time.seconds(2),Time.seconds(1))//指定计算数据的窗口大小和滑动窗口大小
                .sum("count");

        //把数据打印到控制台
        windowCount.print()
                .setParallelism(1);//使用一个并行度
        //注意：因为flink是懒加载的，所以必须调用execute方法，上面的代码才会执行
        env.execute("streaming word count");

    }

    /**
     * 主要为了存储单词以及单词出现的次数
     */
    public static class WordWithCount{
        public String word;
        public long count;
        public WordWithCount(){}
        public WordWithCount(String word, long count) {
            this.word = word;
            this.count = count;
        }

        @Override
        public String toString() {
            return "WordWithCount{" +
                    "word='" + word + '\'' +
                    ", count=" + count +
                    '}';
        }
    }
}

三、运行结果

cmd中输入单词，空格分割，并换行，在idea的控制台中观察输出

IDEA
本地开发调试实例完成

原文地址
https://www.cnblogs.com/limaosheng/p/10434848.html