Flink之自定义Source

---

一、Flink 已实现的Source

Flink 已提供的Source

https://nightlies.apache.org/flink/flink-docs-release-1.15/docs/connectors/datastream/overview/

二、Flink 自定义Source

2.1、单并行度Source

1、实现代码（1秒生成一条数据）

 package com.hpsk.flink.source;

import org.apache.flink.streaming.api.functions.source.SourceFunction;

import java.util.Random;

public class MySource implements SourceFunction<String> {
    private boolean isRunning = true;
    private Long flag = 1L;
    @Override
    public void run(SourceContext<String> ctx) throws Exception {
        Random random = new Random();
        while (isRunning) {
            ctx.collect( flag + " " + random.nextInt(999));
            Thread.sleep(1000);
            flag ++;
        }
    }

    @Override
    public void cancel() {
        isRunning = false;
    }
}

2、 调用代码

 package com.hpsk.flink.stream;

import com.hpsk.flink.source.MyParallelSource;
import com.hpsk.flink.source.MyRichParallelSource;
import com.hpsk.flink.source.MySource;
import org.apache.flink.streaming.api.datastream.DataStreamSource;
import org.apache.flink.streaming.api.environment.StreamExecutionEnvironment;

public class SourceFunStream {
    public static void main(String[] args) throws Exception {
        StreamExecutionEnvironment env = StreamExecutionEnvironment.getExecutionEnvironment();
        DataStreamSource<String> inputDS = env.addSource(new MySource());
//        DataStreamSource<String> inputDS = env.addSource(new MyParallelSource());
//        DataStreamSource<String> inputDS = env.addSource(new MyRichParallelSource());
        inputDS.print(env.getParallelism() + ">>");
        env.execute();
    }
}

3、 执行结果

2.2、多并行度Source

1、 实现代码（1秒生成一条数据）

package com.hpsk.flink.source;

import org.apache.flink.streaming.api.functions.source.ParallelSourceFunction;
import java.util.Random;

public class MyParallelSource implements ParallelSourceFunction<String> {
    private boolean isRunning = true;
    private Long flag = 1L;
    @Override
    public void run(SourceContext<String> ctx) throws Exception {
        Random random = new Random();
        while (isRunning) {
            ctx.collect( flag + " " + random.nextInt(999));
            Thread.sleep(1000);
            flag ++;
        }
    }

    @Override
    public void cancel() {
        isRunning = false;
    }
}

2、调用代码

package com.hpsk.flink.stream;

import com.hpsk.flink.source.MyParallelSource;
import com.hpsk.flink.source.MyRichParallelSource;
import com.hpsk.flink.source.MySource;
import org.apache.flink.streaming.api.datastream.DataStreamSource;
import org.apache.flink.streaming.api.environment.StreamExecutionEnvironment;

public class SourceFunStream {
    public static void main(String[] args) throws Exception {
        StreamExecutionEnvironment env = StreamExecutionEnvironment.getExecutionEnvironment();
//        DataStreamSource<String> inputDS = env.addSource(new MySource());
        DataStreamSource<String> inputDS = env.addSource(new MyParallelSource());
//        DataStreamSource<String> inputDS = env.addSource(new MyRichParallelSource());
        inputDS.print(env.getParallelism() + ">>");
        env.execute();
    }
}

3、 执行结果

2.3、富文本多并行度Source

RichParallelSourceFunction
1、继承了AbstractRichFunction
2、实现了ParallelSourceFunction

RichParallelSourceFunction提供了外部连接的open和close方法以及运行时的getRuntimeContext等方法

1、实现代码（1秒生成一条数据）

package com.hpsk.flink.source;

import org.apache.flink.configuration.Configuration;
import org.apache.flink.streaming.api.functions.source.RichParallelSourceFunction;
import java.util.Random;

public class MyRichParallelSource extends RichParallelSourceFunction<String> {
    private boolean isRunning = true;
    private Long flag = 1L;
    @Override
    public void run(SourceContext<String> ctx) throws Exception {
        Random random = new Random();
        while (isRunning) {
            ctx.collect( flag + " " + random.nextInt(999));
            Thread.sleep(1000);
            flag ++;
        }
    }

    @Override
    public void cancel() {
        isRunning = false;
    }

    @Override
    public void open(Configuration parameters) throws Exception {
        System.out.println("连接资源.....");
    }

    @Override
    public void close() throws Exception {
        System.out.println("关闭资源.....");
    }
}

2、 调用代码

package com.hpsk.flink.stream;

import com.hpsk.flink.source.MyParallelSource;
import com.hpsk.flink.source.MyRichParallelSource;
import com.hpsk.flink.source.MySource;
import org.apache.flink.streaming.api.datastream.DataStreamSource;
import org.apache.flink.streaming.api.environment.StreamExecutionEnvironment;

public class SourceFunStream {
    public static void main(String[] args) throws Exception {
        StreamExecutionEnvironment env = StreamExecutionEnvironment.getExecutionEnvironment();
//        DataStreamSource<String> inputDS = env.addSource(new MySource());
//        DataStreamSource<String> inputDS = env.addSource(new MyParallelSource());
        DataStreamSource<String> inputDS = env.addSource(new MyRichParallelSource());
        inputDS.print(env.getParallelism() + ">>");
        env.execute();
    }
}

3、执行结果