Flink 自定义数据源开发流程

1 继承SourceFunction和ParallelSourceFunction

复制代码
import org.apache.flink.streaming.api.functions.source.SourceFunction;

重新run()和cancel()方法

2 AccessSource 代码

复制代码
package com.zyb.flink.basic.source;
import com.zyb.flink.basic.bean.Access;
import org.apache.flink.streaming.api.functions.source.SourceFunction;
import java.util.Random;

public class AccessSource implements SourceFunction<Access> {
    boolean isRunning = true;

    @Override
    public void run(SourceContext<Access> ctx) throws Exception {
        Random random = new Random();
        String[] domains = {"pk1.com","pk2.com","pk3.com","pk4.com","pk5."};

        while (isRunning){
            long time = System.currentTimeMillis();
            ctx.collect(new Access(time,domains[random.nextInt(domains.length)],random.nextInt(1000)));
        }
        Thread.sleep(2000);
    }

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

3 Access代码

复制代码
package com.zyb.flink.basic.bean;

public class Access {
    private long time;
    private String domain;
    private double traffic;

    @Override
    public String toString() {
        return "Access{" +
                "time=" + time +
                ", domain='" + domain + '\'' +
                ", traffic=" + traffic +
                '}';
    }

    public Access() {
    }

    public Access(long time, String domain, double traffic) {
        this.time = time;
        this.domain = domain;
        this.traffic = traffic;
    }

    public long getTime() {
        return time;
    }

    public void setTime(long time) {
        this.time = time;
    }

    public String getDomain() {
        return domain;
    }

    public void setDomain(String domain) {
        this.domain = domain;
    }

    public double getTraffic() {
        return traffic;
    }

    public void setTraffic(double traffic) {
        this.traffic = traffic;
    }
}

4 测试代码

复制代码
package com.zyb.flink.basic.source;
import com.zyb.flink.basic.bean.Access;
import org.apache.flink.streaming.api.functions.source.SourceFunction;
import java.util.Random;

public class AccessSource implements SourceFunction<Access> {
    boolean isRunning = true;

    @Override
    public void run(SourceContext<Access> ctx) throws Exception {
        Random random = new Random();
        String[] domains = {"pk1.com","pk2.com","pk3.com","pk4.com","pk5."};

        while (isRunning){
            long time = System.currentTimeMillis();
            ctx.collect(new Access(time,domains[random.nextInt(domains.length)],random.nextInt(1000)));
        }
        Thread.sleep(2000);
    }

    @Override
    public void cancel() {
        isRunning = false;
    }
}
相关推荐
SelectDB9 分钟前
快手基于 Apache Doris 千亿多模态检索的实践
大数据·数据库·数据分析
SelectDB15 分钟前
StarRocks 迁移至 Apache Doris 完整指南:三步完成结构、数据与业务平滑切换
大数据·数据库·数据分析
mmsx36 分钟前
Android 地图十万要素不卡顿:空间网格 + 渐进式加载的移动端实践
android·大数据·opengl
宁波鹿语心理1 小时前
注意缺陷多动障碍儿童及家庭的心理支持:理解特质,重建价值
大数据
跨境数据猎手1 小时前
反向海淘是什么:2026从系统架构到业务落地
大数据·产品运营·需求分析
TDengine (老段)2 小时前
TDengine 常见问题 TOP7
大数据·数据库·时序数据库·常见问题·tdengine·涛思数据
探数API小喇叭2 小时前
天气 API 接口思路:拆解一套包含 4 个子接口的轻量化气象服务
大数据·api·天气预报
方向研究2 小时前
硬盘健康信息监测
大数据
yt004yt3 小时前
绿岛数字化平台搭建:VOCs 监测与能碳数据一体化方案
大数据·分布式
广州宏帝箱包4 小时前
出口背包的包装有没有防潮、防摔的加固处理
大数据·人工智能