45、Flink 的自定义窗口剔除器 evictor 代码示例

1、代码示例

import org.apache.flink.api.common.eventtime.SerializableTimestampAssigner;
import org.apache.flink.api.common.eventtime.WatermarkStrategy;
import org.apache.flink.api.common.functions.MapFunction;
import org.apache.flink.api.common.state.ListStateDescriptor;
import org.apache.flink.api.java.tuple.Tuple2;
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.windowing.WindowFunction;
import org.apache.flink.streaming.api.windowing.assigners.TumblingEventTimeWindows;
import org.apache.flink.streaming.api.windowing.evictors.Evictor;
import org.apache.flink.streaming.api.windowing.triggers.EventTimeTrigger;
import org.apache.flink.streaming.api.windowing.windows.TimeWindow;
import org.apache.flink.streaming.api.windowing.windows.Window;
import org.apache.flink.streaming.runtime.operators.windowing.TimestampedValue;
import org.apache.flink.util.Collector;

import java.time.Duration;
import java.util.ArrayList;
import java.util.Iterator;
import java.util.List;

public class _13_WindowCustomEvictors {
    public static void main(String[] args) throws Exception {
        StreamExecutionEnvironment env = StreamExecutionEnvironment.getExecutionEnvironment();

        DataStreamSource<String> input = env.socketTextStream("localhost", 8888);

        // 测试时限制了分区数,生产中需要设置空闲数据源
        env.setParallelism(2);

        ArrayList<String> keyWords = new ArrayList<>();
        keyWords.add("a");

        // 事件时间需要设置水位线策略和时间戳
        SingleOutputStreamOperator<Tuple2<String, Long>> map = input.map(new MapFunction<String, Tuple2<String, Long>>() {
            @Override
            public Tuple2<String, Long> map(String input) throws Exception {
                String[] fields = input.split(",");
                return new Tuple2<>(fields[0], Long.parseLong(fields[1]));
            }
        });

        SingleOutputStreamOperator<Tuple2<String, Long>> watermarks = map.assignTimestampsAndWatermarks(WatermarkStrategy.<Tuple2<String, Long>>forBoundedOutOfOrderness(Duration.ofSeconds(0))
                .withTimestampAssigner(new SerializableTimestampAssigner<Tuple2<String, Long>>() {
                    @Override
                    public long extractTimestamp(Tuple2<String, Long> input, long l) {
                        return input.f1;
                    }
                }));

        watermarks.keyBy(e -> e.f0)
                .window(TumblingEventTimeWindows.of(Duration.ofSeconds(5)))
                .trigger(EventTimeTrigger.create())
                .evictor(new MyCustomEvictorDoBefore<>(false, keyWords))
                .apply(new WindowFunction<Tuple2<String, Long>, String, String, TimeWindow>() {
                    @Override
                    public void apply(String s, TimeWindow timeWindow, Iterable<Tuple2<String, Long>> iterable, Collector<String> collector) throws Exception {
                        System.out.println("Window 的开始和结束时间=>" + timeWindow.getStart() + "-" + timeWindow.getEnd());

                        for (Tuple2<String, Long> tuple2 : iterable) {
                            collector.collect(tuple2.f0);
                        }
                    }
                })
                .print();

        env.execute();
    }
}

/**
 * doEvictAfter = false
 * <p>
 * a,1718157600000
 * b,1718157600000
 * c,1718157600000
 * <p>
 * a,1718157602000
 * b,1718157602000
 * c,1718157602000
 * <p>
 * a,1718157604000
 * b,1718157604000
 * c,1718157604000
 * <p>
 * a,1718157605001
 * b,1718157605001
 * <p>
 * Window 的开始和结束时间=>1718157600000-1718157605000
 * 2> a
 * 2> a
 * 2> a
 * Window 的开始和结束时间=>1718157600000-1718157605000
 * Window 的开始和结束时间=>1718157600000-1718157605000
 * <p>
 * c,1718157605001
 */
class MyCustomEvictorDoBefore<W extends Window> implements Evictor<Object, W> {
    private boolean doEvictAfter;

    private List<String> keyWords;

    public MyCustomEvictorDoBefore(boolean doEvictAfter, List<String> keyWords) {
        this.doEvictAfter = doEvictAfter;
        this.keyWords = keyWords;
    }

    @Override
    public void evictBefore(Iterable<TimestampedValue<Object>> elements, int i, W w, EvictorContext evictorContext) {
        if (!this.doEvictAfter) {
            this.evict(elements);
        }
    }

    @Override
    public void evictAfter(Iterable<TimestampedValue<Object>> elements, int i, W w, EvictorContext evictorContext) {
        if (this.doEvictAfter) {
            this.evict(elements);
        }
    }

    private void evict(Iterable<TimestampedValue<Object>> elements) {
        Iterator<TimestampedValue<Object>> iterator = elements.iterator();

        while (iterator.hasNext()) {
            TimestampedValue<Object> record = (TimestampedValue) iterator.next();
            for (String keyWord : keyWords) {
                if (!record.getValue().toString().contains(keyWord)) {
                    iterator.remove();
                }
            }
        }
    }
}

评论
添加红包

请填写红包祝福语或标题

红包个数最小为10个

红包金额最低5元

当前余额3.43前往充值 >
需支付:10.00
成就一亿技术人!
领取后你会自动成为博主和红包主的粉丝 规则
hope_wisdom
发出的红包

打赏作者

猫猫爱吃小鱼粮

你的鼓励将是我创作的最大动力

¥1 ¥2 ¥4 ¥6 ¥10 ¥20
扫码支付:¥1
获取中
扫码支付

您的余额不足,请更换扫码支付或充值

打赏作者

实付
使用余额支付
点击重新获取
扫码支付
钱包余额 0

抵扣说明:

1.余额是钱包充值的虚拟货币,按照1:1的比例进行支付金额的抵扣。
2.余额无法直接购买下载,可以购买VIP、付费专栏及课程。

余额充值