Flink SideOutPutLateEventCustom

Claroja發表於2020-12-18
IDE
package com.claroja;

import org.apache.flink.api.common.eventtime.SerializableTimestampAssigner;
import org.apache.flink.api.common.eventtime.WatermarkStrategy;
import org.apache.flink.api.common.typeinfo.TypeHint;
import org.apache.flink.api.java.tuple.Tuple2;
import org.apache.flink.streaming.api.TimeCharacteristic;
import org.apache.flink.streaming.api.datastream.SingleOutputStreamOperator;
import org.apache.flink.streaming.api.environment.StreamExecutionEnvironment;
import org.apache.flink.streaming.api.functions.windowing.ProcessWindowFunction;
import org.apache.flink.streaming.api.windowing.time.Time;
import org.apache.flink.streaming.api.windowing.windows.TimeWindow;
import org.apache.flink.util.Collector;
import org.apache.flink.util.OutputTag;
/*
使用flink自帶的遲到元素處理函式
sideOutputLateData(new OutputTag<Tuple2<String, Long>>("late-reading") {
 */
public class SideOutputLateEvent {
    public static void main(String[] args) throws Exception {
        StreamExecutionEnvironment env = StreamExecutionEnvironment.getExecutionEnvironment();
        env.setStreamTimeCharacteristic(TimeCharacteristic.EventTime);
        env.setParallelism(1);

        SingleOutputStreamOperator<Tuple2<String, Long>> stream = env
                .socketTextStream("localhost", 9999)
                .map(r -> Tuple2.of(r.split(" ")[0], Long.parseLong(r.split(" ")[1]) * 1000L))
                .returns(new TypeHint<Tuple2<String, Long>>() {
                })
                .assignTimestampsAndWatermarks(
                        // 升序時間戳抽取
                        WatermarkStrategy.<Tuple2<String, Long>>forMonotonousTimestamps()
                                .withTimestampAssigner(new SerializableTimestampAssigner<Tuple2<String, Long>>() {
                                    @Override
                                    public long extractTimestamp(Tuple2<String, Long> stringLongTuple2, long l) {
                                        return stringLongTuple2.f1;
                                    }
                                })
                );

        SingleOutputStreamOperator<String> process = stream
                .keyBy(r -> r.f0)
                .timeWindow(Time.seconds(10))
                .sideOutputLateData(new OutputTag<Tuple2<String, Long>>("late-reading") {//flink自帶的遲到元素處理
                })
                .process(new ProcessWindowFunction<Tuple2<String, Long>, String, String, TimeWindow>() {
                    @Override
                    public void process(String s, Context context, Iterable<Tuple2<String, Long>> iterable, Collector<String> collector) throws Exception {
                        long count = 0L;
                        for (Tuple2<String, Long> i : iterable) {
                            count += 1;
                        }
                        collector.collect("視窗中共有 " + count + " 條資料");
                    }
                });

        process.print();

        process.getSideOutput(new OutputTag<Tuple2<String, Long>>("late-reading"){}).print();

        env.execute();
    }
}

相關文章