Flink水位线学习

Flink的水位线(顺序增长的数据)

package com.apple.flink.watermark;

import com.apple.flink.func.WaterSensorMapFunction;
import com.apple.flink.model.WaterSensor;
import org.apache.commons.lang3.time.DateFormatUtils;
import org.apache.flink.api.common.eventtime.SerializableTimestampAssigner;
import org.apache.flink.api.common.eventtime.WatermarkStrategy;
import org.apache.flink.streaming.api.datastream.KeyedStream;
import org.apache.flink.streaming.api.datastream.SingleOutputStreamOperator;
import org.apache.flink.streaming.api.datastream.WindowedStream;
import org.apache.flink.streaming.api.environment.StreamExecutionEnvironment;
import org.apache.flink.streaming.api.functions.windowing.ProcessWindowFunction;
import org.apache.flink.streaming.api.windowing.assigners.SlidingProcessingTimeWindows;
import org.apache.flink.streaming.api.windowing.assigners.TumblingEventTimeWindows;
import org.apache.flink.streaming.api.windowing.assigners.TumblingProcessingTimeWindows;
import org.apache.flink.streaming.api.windowing.time.Time;
import org.apache.flink.streaming.api.windowing.windows.TimeWindow;
import org.apache.flink.util.Collector;

/**
 * 水位线基于事件语义
 *  升序的水位线
 */
@SuppressWarnings("all")
public class WaterMarkDemo {
    public static void main(String[] args) throws Exception {
        StreamExecutionEnvironment environment = StreamExecutionEnvironment.getExecutionEnvironment();
        environment.setParallelism(1);
        SingleOutputStreamOperator<WaterSensor> sensorDS = environment.socketTextStream("hadoop102", 7777)
                .map(new WaterSensorMapFunction())
                .assignTimestampsAndWatermarks(WatermarkStrategy.<WaterSensor>forMonotonousTimestamps()
                        .withTimestampAssigner(new SerializableTimestampAssigner<WaterSensor>() {
                            @Override
                            public long extractTimestamp(WaterSensor waterSensor, long l) {
                                System.out.println("数据=" + waterSensor + ",recordTS--->" + l);
                                return waterSensor.getVc() * 1000L;
                            }
                        }));

        WindowedStream<WaterSensor, String, TimeWindow> sensorWS =
                sensorDS.keyBy(WaterSensor::getId)
     //指定事件时间语义的窗口
                .window(TumblingEventTimeWindows.of(Time.seconds(10)));//事件事件 窗口长度为10秒

        SingleOutputStreamOperator<String> processed = sensorWS.process(new ProcessWindowFunction<WaterSensor, String, String, TimeWindow>() {
            @Override
            public void process(String value, ProcessWindowFunction<WaterSensor, String, String, TimeWindow>.Context context, Iterable<WaterSensor> iterable, Collector<String> collector) throws Exception {
                long start = context.window().getStart();
                long end = context.window().getEnd();
                String startFormat = DateFormatUtils.format(start, "yyyy-MM-dd HH:mm:ss.SSS");
                String endFormat = DateFormatUtils.format(end, "yyyy-MM-dd HH:mm:ss.SSS");
                long count = iterable.spliterator().estimateSize();
                collector.collect("key=" + value + "窗口【" + startFormat + "," + endFormat + ")包含" + count + "条数据--->" + iterable.toString());
            }
        });
        processed.print("---->");
        environment.execute();
    }
}

默认是时间语义
升序的时间戳指定为WaterMark