Flink 状态编程（六）聚合状态（AggregatingState）案例

我们举一个简单的例子，对用户点击事件流每 5 个数据统计一次平均时间戳。这是一个类似计数窗口（CountWindow）求平均值的计算，这里我们可以使用一个有聚合状态的RichFlatMapFunction 来实现。

代码展示：

public class AverageTimestampExample {
    public static void main(String[] args) throws Exception {
        StreamExecutionEnvironment env = StreamExecutionEnvironment.getExecutionEnvironment();
        env.setParallelism(1);

        SingleOutputStreamOperator<Event> stream = env.addSource(new ClickSource())
                .assignTimestampsAndWatermarks(
                        WatermarkStrategy.<Event>forBoundedOutOfOrderness(Duration.ZERO)
                                .withTimestampAssigner(new SerializableTimestampAssigner<Event>() {
                                    @Override
                                    public long extractTimestamp(Event element, long recordTimestamp) {
                                        return element.timestamp;
                                    }
                                })
                );

        stream.print("input");

        //自定义实现平均时间戳的统计
        stream.keyBy(data -> data.user)
                .flatMap(new AvgTsResult(5L))
                .print();

        env.execute();
    }

    //自定义实现RichFlatMapFunction
    public static class AvgTsResult extends RichFlatMapFunction<Event, String> {
        //自定义的窗口
        private Long count;

        public AvgTsResult(Long count) {
            this.count = count;
        }

        //定义一个聚合状态，用来保存平均时间戳
        private AggregatingState<Event, Long> avgTsAggState;

        //定义一个值状态，保存用户访问的次数
        private ValueState<Long> countState;

        @Override
        public void open(Configuration parameters) throws Exception {
            //获取运行上下文
            //ACC : Tuple2<Long,Long> : 第一个所有时间戳的和，第二个是当前的个数
            //Out : 平均时间戳
            avgTsAggState = getRuntimeContext().getAggregatingState(new AggregatingStateDescriptor<Event, Tuple2<Long, Long>, Long>(
                    "avg-ts",
                    new AggregateFunction<Event, Tuple2<Long, Long>, Long>() {
                        @Override
                        public Tuple2<Long, Long> createAccumulator() {
                            return Tuple2.of(0L, 0L);
                        }

                        @Override
                        public Tuple2<Long, Long> add(Event value, Tuple2<Long, Long> accumulator) {
                            return Tuple2.of(accumulator.f0 + value.timestamp, accumulator.f1 + 1);
                        }

                        @Override
                        public Long getResult(Tuple2<Long, Long> accumulator) {
                            return accumulator.f0 / accumulator.f1;
                        }

                        @Override
                        public Tuple2<Long, Long> merge(Tuple2<Long, Long> a, Tuple2<Long, Long> b) {
                            return null;
                        }
                    },
                    Types.TUPLE(Types.LONG, Types.LONG)
            ));

            countState = getRuntimeContext().getState(new ValueStateDescriptor<Long>("count", Long.class));
        }

        @Override
        public void flatMap(Event value, Collector<String> out) throws Exception {
            //每来一条数据 count 就 +1
            Long currCount = countState.value();

            //判断，如果状态里面没有值的话，就+1，如果有值的话，就++
            if (currCount == null) {
                currCount = 1L;
            } else {
                currCount++;
            }

            //更新状态
            countState.update(currCount);
            avgTsAggState.add(value);

            //根据count,判断是否达到了累积的技术窗口的长度
            if (currCount.equals(count)){
                out.collect(value.user + "过去"+count+"次访问平均时间戳为："+ new Timestamp(avgTsAggState.get()));

                //清空状态
                avgTsAggState.clear();
                countState.clear();
            }
        }
    }
}

Gitee完整代码展示