package com.hao.chapter06;

import com.hao.chapter05.ClickSource;
import com.hao.chapter05.Event;
import org.apache.flink.api.common.eventtime.SerializableTimestampAssigner;
import org.apache.flink.api.common.eventtime.WatermarkStrategy;
import org.apache.flink.streaming.api.datastream.DataStream;
import org.apache.flink.streaming.api.environment.StreamExecutionEnvironment;
import org.apache.flink.streaming.api.functions.windowing.ProcessWindowFunction;
import org.apache.flink.streaming.api.windowing.assigners.TumblingEventTimeWindows;
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 java.sql.Timestamp;
import java.time.Duration;
import java.util.HashSet;

public class WindowProcessTest {
    public static void main(String[] args) throws Exception{

        StreamExecutionEnvironment env = StreamExecutionEnvironment.getExecutionEnvironment();
        env.setParallelism(1);
        // 读取数据，并提取时间戳、生成水位线
        DataStream<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("data");

        // 统计每5秒的UV次数
        stream.keyBy(data -> true)
                .window(TumblingEventTimeWindows.of(Time.seconds(5)))
                .process(new UvCountByWindow())
                .print();

        env.execute();
    }

    //实现自定义ProcessWindowFunction,输出一条统计信息
    public static class UvCountByWindow extends ProcessWindowFunction<Event,String,Boolean, TimeWindow>{

        @Override
        public void process(Boolean aBoolean, Context context, Iterable<Event> elements, Collector<String> out) throws Exception {
            //用HashSet保存user
            HashSet<String> userSet = new HashSet<>();
            //遍历数据，去重
            for (Event event:elements) {
                userSet.add(event.user);
            }
            //获取UV信息
            Integer uv = userSet.size();
            //获取开始时间和结束时间
            Long start = context.window().getStart();
            Long end = context.window().getEnd();
            //打印
            out.collect("窗口 "+new Timestamp(start) + " ~ " + new Timestamp(end) + " UV值为:" + uv);
        }
    }
}