flink的local模式实现单词计数器(流处理方式)

flink的local模式实现单词计数器(流处理方式)

在idea中创建Java maven项目

导入maven依赖

<?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">
    <parent>
        <artifactId>bigDataCode</artifactId>
        <groupId>org.example</groupId>
        <version>1.0-SNAPSHOT</version>
    </parent>
    <modelVersion>4.0.0</modelVersion>

    <artifactId>flink-wordcount</artifactId>

    <dependencies>
        <dependency>
            <groupId>org.apache.flink</groupId>
            <artifactId>flink-java</artifactId>
            <version>1.12.5</version>
        </dependency>
        <dependency>
            <groupId>org.apache.flink</groupId>
            <artifactId>flink-streaming-java_2.12</artifactId>
            <version>1.12.5</version>
            <!--<scope>provided</scope>-->
        </dependency>
        <dependency>
            <groupId>org.apache.flink</groupId>
            <artifactId>flink-clients_2.12</artifactId>
            <version>1.12.5</version>
        </dependency>
    </dependencies>

    <build>
        <plugins>
            <!-- 编译插件 -->
            <plugin>
                <groupId>org.apache.maven.plugins</groupId>
                <artifactId>maven-compiler-plugin</artifactId>
                <configuration>
                    <source>1.8</source>
                    <target>1.8</target>
                    <encoding>UTF-8</encoding>
                </configuration>
            </plugin>
        </plugins>
    </build>
</project>

关键代码

在192.168.88.161中开启端口监听

安装nc: yum install -y nc

nc -lk 9999

package com.xxx.flink.stream;

import org.apache.flink.api.common.functions.FlatMapFunction;
import org.apache.flink.api.common.functions.MapFunction;
import org.apache.flink.api.java.tuple.Tuple;
import org.apache.flink.api.java.tuple.Tuple2;
import org.apache.flink.streaming.api.datastream.DataStream;
import org.apache.flink.streaming.api.datastream.KeyedStream;
import org.apache.flink.streaming.api.datastream.SingleOutputStreamOperator;
import org.apache.flink.streaming.api.environment.StreamExecutionEnvironment;
import org.apache.flink.util.Collector;

/***
 * 流处理单词计数器
 */
public class StreamWordCount {

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

        //1：获取流处理运行环境
        StreamExecutionEnvironment env = StreamExecutionEnvironment.getExecutionEnvironment();

        //2：构建socket流数据源，并指定IP地址和端口号
        DataStream<String> lines = env.socketTextStream("192.168.88.161", 9999);

        //3：对接收到的数据进行空格拆分
        SingleOutputStreamOperator<String> words = lines.flatMap(new FlatMapFunction<String, String>() {
            @Override
            public void flatMap(String line, Collector<String> out) throws Exception {
                //切分
                String[] words = line.split(" ");
                for (String word : words) {
                    //输出
                    out.collect(word);
                }
            }
        });

        //4：对拆分后的单词，每个单词记一次数
        SingleOutputStreamOperator<Tuple2<String, Integer>> wordAndOne = words.map(new MapFunction<String, Tuple2<String, Integer>>() {
            @Override
            public Tuple2<String, Integer> map(String word) throws Exception {
                return Tuple2.of(word, 1);
            }
        });

        //5：对拆分后的单词进行分组
        KeyedStream<Tuple2<String, Integer>, Tuple> groupedStream = wordAndOne.keyBy(0);

        //6：根据单词的次数进行聚合
        SingleOutputStreamOperator<Tuple2<String, Integer>> summed = groupedStream.sum(1);

        //7：打印输出
        summed.print();

        //8：启动执行
        env.execute("StreamWordCount");
    }
}

idea工具中执行main方法

通过UI界面执行
将项目打包成jar
上传jar包到UI的taskmanager

查看输出

以命令方式提交
将打包好的jar上传到服务器,

运行命令

flink run -c com.xxx.flink.stream.StreamWordCount /export/tmp/flink-wordcount-1.0-SNAPSHOT.jar

在UI界面的task manager查看作业输出