Flink Java 之 Allowed Lateness 容忍迟到数据，侧输出

先上代码

• 添加Watermaker来解决一定程度上的数据延迟和数据乱序问题。
• 使用OutputTag+allowedLateness解决数据丢失问题

package com.daidai.watermarks;

import com.daidai.source.mocksource.domain.Order;
import org.apache.flink.api.common.eventtime.WatermarkStrategy;
import org.apache.flink.api.common.typeinfo.TypeInformation;
import org.apache.flink.streaming.api.datastream.DataStream;
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.streaming.api.functions.source.SourceFunction;
import org.apache.flink.streaming.api.windowing.assigners.TumblingEventTimeWindows;
import org.apache.flink.streaming.api.windowing.time.Time;
import org.apache.flink.util.OutputTag;

import java.time.Duration;
import java.util.Random;
import java.util.UUID;

public class AllowedLateness {
    public static void main(String[] args) throws Exception {
        StreamExecutionEnvironment env = StreamExecutionEnvironment.getExecutionEnvironment();

        DataStreamSource<Order> orderDataStreamSource = env.addSource(new SourceFunction<Order>() {

            private boolean flag = true;

            @Override
            public void run(SourceContext<Order> ctx) throws Exception {
                while (flag) {
                    Random random = new Random();
                    Order order = new Order();
                    order.setId(UUID.randomUUID().toString());
                    order.setUserId(random.nextInt(3));
                    order.setCreateTime(System.currentTimeMillis() - random.nextInt(15) * 1000);
                    order.setMoney(random.nextInt(100));

                    ctx.collect(order);
                }
            }

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


        OutputTag<Order> later = new OutputTag<>("later", TypeInformation.of(Order.class));

        SingleOutputStreamOperator<Order> timestampsAndWatermarks = orderDataStreamSource
                .assignTimestampsAndWatermarks(
                        WatermarkStrategy
                                .<Order>forBoundedOutOfOrderness(Duration.ofSeconds(3))
                                .withTimestampAssigner((context, timestmp) -> context.getCreateTime()));

        SingleOutputStreamOperator<Order> sum = timestampsAndWatermarks.keyBy(Order::getUserId)
                .window(TumblingEventTimeWindows.of(Time.seconds(5)))
                .allowedLateness(Time.seconds(5))
                .sideOutputLateData(later)
                .sum("money");

        sum.print("正常数据");
        DataStream<Order> laterDS = sum.getSideOutput(later);
        laterDS.print("迟到严重数据");

        env.execute();
    }
}