Flink入门之DataStream API实现word count

以下是一个从无界数据源读取数据计算word count的示例

pom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">
    <parent>
        <artifactId>simple-demo</artifactId>
        <groupId>org.example</groupId>
        <version>1.0-SNAPSHOT</version>
    </parent>
    <modelVersion>4.0.0</modelVersion>

    <artifactId>flink</artifactId>

    <properties>
        <maven.compiler.source>8</maven.compiler.source>
        <maven.compiler.target>8</maven.compiler.target>
        <flink.version>1.17.0</flink.version>
    </properties>

    <dependencies>
        <dependency>
            <groupId>org.apache.flink</groupId>
            <artifactId>flink-streaming-java</artifactId>
            <version>${flink.version}</version>
        </dependency>

        <dependency>
            <groupId>org.apache.flink</groupId>
            <artifactId>flink-clients</artifactId>
            <version>${flink.version}</version>
        </dependency>

        <dependency>
            <groupId>junit</groupId>
            <artifactId>junit</artifactId>
            <version>4.13.2</version>
            <scope>test</scope>
        </dependency>
    </dependencies>

</project>

java代码

package com.xx.flink.test;

import org.apache.flink.api.common.typeinfo.Types;
import org.apache.flink.api.java.tuple.Tuple2;
import org.apache.flink.streaming.api.datastream.DataStreamSource;
import org.apache.flink.streaming.api.datastream.SingleOutputStreamOperator;
import org.apache.flink.streaming.api.environment.StreamExecutionEnvironment;
import org.apache.flink.util.Collector;
import org.junit.Test;

public class WCTest {

    @Test
    public void dataStreamTest() throws Exception {

        //  1. 创建执行环境
        StreamExecutionEnvironment env = StreamExecutionEnvironment.getExecutionEnvironment();
        env.setParallelism(3);

        //  2. 读取数据： socket
        DataStreamSource<String> socketDS = env.socketTextStream("127.0.0.1", 7777);

        //  3. 处理数据: 切换、转换、分组、聚合
        SingleOutputStreamOperator<Tuple2<String, Integer>> sum = socketDS
                .flatMap(
                        (String value, Collector<Tuple2<String, Integer>> out) -> {
                            String[] words = value.split(" ");
                            for (String word : words) {
                                out.collect(Tuple2.of(word, 1));
                            }
                        }
                )
                .setParallelism(2)
                .returns(Types.TUPLE(Types.STRING, Types.INT))
                .keyBy(value -> value.f0)
                .sum(1);

        //  4. 输出
        sum.print();

        //  5. 执行
        env.execute();
    }
}

over~~