【Flink】Flink中的窗口API、窗口函数以及迟到数据处理问题_tumblingprocessingtimewindows.of

DataStream<Event> stream = env.addSource(...);
OutputTag<Event> outputTag = new OutputTag<Event>("late") {};
winAggStream = stream.keyBy(...)
                     .window(TumblingEventTimeWindows.of(Time.hours(1)))
                     .sideOutputLateData(outputTag)
DataStream<Event> lateStream = winAggStream.getSideOutput(outputTag);

7、窗口的生命周期

（1） 窗口的创建

    // 处理迟到数据的综合案例
    public static void main(String[] args) throws Exception {
        StreamExecutionEnvironment env = StreamExecutionEnvironment.getExecutionEnvironment();
        env.setParallelism(1);
 
        // 读取socket文本流
        SingleOutputStreamOperator<Event> stream = env.socketTextStream("localhost", 7777)
                .map(new MapFunction<String, Event>() {
                    @Override
                    public Event map(String value) throws Exception {
                        String[] fields = value.split(" ");
                        return new Event(fields[0].trim(), fields[1].trim(), Long.valueOf(fields[2].trim()));
                    }
                })
                // 方式一：设置watermark延迟时间，2秒钟
                .assignTimestampsAndWatermarks(WatermarkStrategy.<Event>forBoundedOutOfOrderness(Duration.ofSeconds(2))
                        .withTimestampAssigner(new SerializableTimestampAssigner<Event>() {
                            @Override
                            public long extractTimestamp(Event element, long recordTimestamp) {
                                return element.timestamp;
                            }
                        }));
 
        // 定义侧输出流标签
        OutputTag<Event> outputTag = new OutputTag<Event>("late"){};
 
        SingleOutputStreamOperator<UrlViewCount> result = stream.keyBy(data -> data.url)
                .window(TumblingEventTimeWindows.of(Time.seconds(10)))
                // 方式二：允许窗口处理迟到数据，设置1分钟的等待时间
                .allowedLateness(Time.minutes(1))
                // 方式三：将最后的迟到数据输出到侧输出流
                .sideOutputLateData(outputTag)
                .aggregate(new UrlViewCountAgg(), new UrlViewCountResult());
 
        result.print("result");
        result.getSideOutput(outputTag).print("late");
 
        // 为方便观察，可以将原始数据也输出
        stream.print("input");
 
        env.execute();
    }
 
    public static class UrlViewCountAgg implements AggregateFunction<Event, Long, Long> {
        @Override
        public Long createAccumulator() {
            return 0L;
        }
 
        @Override
        public Long add(Event value, Long accumulator) {
            return accumulator + 1;
        }
 
        @Override
        public Long getResult(Long accumulator) {
            return accumulator;
        }
 
        @Override
        public Long merge(Long a, Long b) {
            return null;
        }
    }
 
    public static class UrlViewCountResult extends ProcessWindowFunction<Long, UrlViewCount, String, TimeWindow> {
 
        @Override
        public void process(String url, Context context, Iterable<Long> elements, Collector<UrlViewCount> out) throws Exception {
            // 结合窗口信息，包装输出内容
            Long start = context.window().getStart();
            Long end = context.window().getEnd();
            out.collect(new UrlViewCount(url, elements.iterator().next(), start, end));
        }
    }