前言

Apache Flink是由Apache软件基金会开发的开源流处理框架，其核心是用Java和Scala编写的分布式流数据流引擎。Flink以数据并行和流水线方式执行任意流数据程序，Flink的流水线运行时系统可以执行批处理和流处理程序。此外，Flink的运行时本身也支持迭代算法的执行。

网上有很多WordCount的demo，但是好多都还是有点小错误（可能是因为版本的问题）或者是对新人来说感觉不太友好，所以自己去官网上找了一下

一、pom

 	<properties>
        <project.build.sourceEncoding>UTF-8</project.build.sourceEncoding>
        <flink.version>1.9.2</flink.version>
        <scala.binary.version>2.11</scala.binary.version>
    </properties>
    <dependencies>
    <!-- Apache Flink dependencies -->
    <dependency>
        <groupId>org.apache.flink</groupId>
        <artifactId>flink-core</artifactId>
        <version>${flink.version}</version>
    </dependency>
    <dependency>
        <groupId>org.apache.flink</groupId>
        <artifactId>flink-java</artifactId>
        <version>${flink.version}</version>
    </dependency>
    <dependency>
        <groupId>org.apache.flink</groupId>
        <artifactId>flink-clients_${scala.binary.version}</artifactId>
        <version>${flink.version}</version>
    </dependency>
    <dependency>
        <groupId>org.apache.flink</groupId>
        <artifactId>flink-table-planner-blink_2.11</artifactId>
        <version>${flink.version}</version>
    </dependency>
    <dependency>
        <groupId>org.apache.flink</groupId>
        <artifactId>flink-table-planner-blink_2.11</artifactId>
        <version>${flink.version}</version>
    </dependency>

二、上代码

package com.ef.spendreport;


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.assigners.TumblingProcessingTimeWindows;
import org.apache.flink.streaming.api.windowing.time.Time;
import org.apache.flink.util.Collector;
/**
 * @program: flink-test
 * @description:
 * @author: ErFeng_V
 * @create: 2021-08-20 14:12
 */
public class WindowWordCount {

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

        StreamExecutionEnvironment env = StreamExecutionEnvironment.getExecutionEnvironment();

        DataStream<Tuple2<String, Integer>> dataStream = env
                .socketTextStream("ip地址", 9999)
                .flatMap(new Splitter())
                .keyBy(value -> value.f0)
                .window(TumblingProcessingTimeWindows.of(Time.seconds(5)))
                .sum(1);

        dataStream.print();

        env.execute("Window WordCount");
    }

    public static class Splitter implements FlatMapFunction<String, Tuple2<String, Integer>> {
        @Override
        public void flatMap(String sentence, Collector<Tuple2<String, Integer>> out) throws Exception {
            for (String word: sentence.split(" ")) {
                out.collect(new Tuple2<String, Integer>(word, 1));
            }
        }
    }

}