Flink waterMark

waterMark的意义本质就是处理数据延迟及乱序问题，与window结合，数据的延迟是不可避免的，因为各种原因，可能是网络，机器负载等，
我们无法解决数据延迟，但是我们必须自己设置，如果发生了数据延迟我们需要怎么处理，可以直接抛弃也可以通过side output写入文件。
waterMark的意义就是在数据源获取的时候添加waterMark，一旦达到window的触发操作，表示这个waterMark之前的数据已经全部到达。
当然实际不是真的全部达到，只是理论上说到达了。如果之后有小于waterMark的值，会直接抛弃或者写入side output. 
waterMark 可以设置延迟多久，比如5秒，那么触发window同样会延迟，实际的意义在本该触发window操作的时候再延迟5秒，
用白话文就是我再给你5秒时间，数据要是还不来我就不管了。

import org.apache.flink.api.common.functions.FoldFunction;
import org.apache.flink.api.common.functions.MapFunction;
import org.apache.flink.api.java.tuple.Tuple2;
import org.apache.flink.streaming.api.TimeCharacteristic;
import org.apache.flink.streaming.api.datastream.DataStream;
import org.apache.flink.streaming.api.environment.StreamExecutionEnvironment;
import org.apache.flink.streaming.api.functions.AssignerWithPeriodicWatermarks;
import org.apache.flink.streaming.api.watermark.Watermark;
import org.apache.flink.streaming.api.windowing.assigners.TumblingEventTimeWindows;
import org.apache.flink.streaming.api.windowing.time.Time;
import javax.annotation.Nullable;


public class waterMark {

    public static void main(String[] args) throws Exception {
        StreamExecutionEnvironment env = StreamExecutionEnvironment.createLocalEnvironment();
         env.enableCheckpointing(1000);

        env.setStreamTimeCharacteristic(TimeCharacteristic.EventTime);

        DataStream<String> dataStream = env
                .socketTextStream("localhost", 9900).assignTimestampsAndWatermarks(new AssignerWithPeriodicWatermarks<String>() {
                    long currentTimeStamp = 0l;
                    long maxDelayAllowed = 0l;
                    long currentWaterMark;

                    @Nullable
                    @Override
                    public Watermark getCurrentWatermark() {
                        currentWaterMark = currentTimeStamp - maxDelayAllowed;
                        return new Watermark(currentWaterMark);
                    }

                    @Override
                    public long extractTimestamp(String s, long l) {
                        String[] arr = s.split(",");
                        long timeStamp = Long.parseLong(arr[1]);
                        currentTimeStamp = Math.max(timeStamp, currentTimeStamp);
                        System.out.println("Key:" + arr[0] + ",EventTime:" + timeStamp + ",水位线:" + currentWaterMark);
                        return timeStamp;
                    }
                });

        dataStream.map(new MapFunction<String, Tuple2<String, String>>() {
            @Override
            public Tuple2<String, String> map(String s) throws Exception {
                return new Tuple2<String, String>(s.split(",")[0], s.split(",")[1]);
            }
        }).keyBy(0)
                .window(TumblingEventTimeWindows.of(Time.seconds(10)))
                .fold("Start:", new FoldFunction<Tuple2<String, String>, String>() {
                    @Override
                    public String fold(String s, Tuple2<String, String> o) throws Exception {
                        return s + " - " + o.f1;
                    }
                }).print();



        env.execute("WaterMark Test Demo");

    }
}