flink流处理测试程序

注：这是flink流处理的测试程序，区别于flink批处理

1.导入pom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">
    <modelVersion>4.0.0</modelVersion>

    <groupId>com.hftfund</groupId>
    <artifactId>flinkdemo</artifactId>
    <version>1.0-SNAPSHOT</version>

    <properties>
        <project.build.sourceEncoding>UTF-8</project.build.sourceEncoding>
    </properties>

    <dependencies>
        <!--flink java-->
        <dependency>
            <groupId>org.apache.flink</groupId>
            <artifactId>flink-java</artifactId>
            <version>1.11.2</version>
        </dependency>
        <dependency>
            <groupId>org.apache.flink</groupId>
            <artifactId>flink-streaming-java_2.11</artifactId>
            <version>1.11.2</version>
        </dependency>

        <dependency>
            <groupId>org.apache.flink</groupId>
            <artifactId>flink-clients_2.11</artifactId>
            <version>1.11.2</version>
        </dependency>

        <!--flink kafka connector-->
        <dependency>
            <groupId>org.apache.flink</groupId>
            <artifactId>flink-connector-kafka-0.11_2.11</artifactId>
            <version>1.11.2</version>
        </dependency>

        <!--日志-->
        <dependency>
            <groupId>org.slf4j</groupId>
            <artifactId>slf4j-log4j12</artifactId>
            <version>1.7.25</version>
        </dependency>
        <dependency>
            <groupId>log4j</groupId>
            <artifactId>log4j</artifactId>
            <version>1.2.17</version>
        </dependency>

        <!--alibaba fastjson-->
        <dependency>
            <groupId>com.alibaba</groupId>
            <artifactId>fastjson</artifactId>
            <version>1.2.51</version>
        </dependency>
    </dependencies>

    <build>
        <plugins>
            <!--下面是打出带依赖包的jar包的配置，不可少-->
            <plugin>
                <artifactId>maven-assembly-plugin</artifactId>
                <configuration>
                    <descriptorRefs>
                        <descriptorRef>jar-with-dependencies</descriptorRef>
                    </descriptorRefs>
                </configuration>
                <executions>
                    <execution>
                        <id>make-assembly</id>
                        <phase>package</phase>
                        <goals>
                            <goal>single</goal>
                        </goals>
                    </execution>
                </executions>
            </plugin>
            <plugin>
                <groupId>org.apache.maven.plugins</groupId>
                <artifactId>maven-compiler-plugin</artifactId>
                <configuration>
                    <source>8</source>
                    <target>8</target>
                </configuration>
            </plugin>
        </plugins>
    </build>

</project>

2.测试
（1）先启动nc

[root@flink01 conf]# nc -lk 9000
123
testone
hello flink      
hello spark
how are you   
fink thank you

（2）运行程序

package com.hftfund.demo;

import org.apache.flink.api.common.functions.FlatMapFunction;
import org.apache.flink.api.java.ExecutionEnvironment;
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;

/**
 * @Author prc
 * @Date 2020/10/12 9:43
 * @Description flink流处理测试程序
 */
public class WindowWordCount {
    public static void main(String[] args) throws Exception {

        // 获取flink批处理执行环境：ExecutionEnvironment
        //ExecutionEnvironment env = ExecutionEnvironment.getExecutionEnvironment();

        // 获取flink流处理执行环境：StreamExecutionEnvironment
        StreamExecutionEnvironment env = StreamExecutionEnvironment.getExecutionEnvironment();
        //env.setParallelism(8);    // 并行度（全局）

        DataStream<Tuple2<String, Integer>> dataStream = env
                .socketTextStream("192.168.110.128", 9000)
                .flatMap(new Splitter())
                .keyBy(value -> value.f0)
                .timeWindow(Time.seconds(5))
                .sum(1);

        dataStream.print();
        //dataStream.print().setParallelism(1); // 并行度（代码级别）

        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));
            }
        }
    }

}

idea运行结果：

"C:\Program Files\Java\jdk1.8.0_131\bin\java.exe" ...
(123,1)
(testone,1)
(flink,1)
(spark,1)
(hello,2)
(how,1)
(you,1)
(are,1)
(thank,1)
(fink,1)
(you,1)