Flink 窗口小案例， 统计一小时的pv和uv的访问量

1. 统计一小时的pv 统计访问量

1.1标题思路就是：数据分类排序----->分类-----> 开窗一小时----->统计.

1.2 代码如下：

package com.wudl.examples;

import com.wudl.bean.UserBehavior;
import org.apache.flink.api.common.functions.MapFunction;
import org.apache.flink.api.java.tuple.Tuple;
import org.apache.flink.api.java.tuple.Tuple2;
import org.apache.flink.streaming.api.TimeCharacteristic;
import org.apache.flink.streaming.api.datastream.KeyedStream;
import org.apache.flink.streaming.api.datastream.SingleOutputStreamOperator;
import org.apache.flink.streaming.api.datastream.WindowedStream;
import org.apache.flink.streaming.api.environment.StreamExecutionEnvironment;
import org.apache.flink.streaming.api.functions.timestamps.AscendingTimestampExtractor;
import org.apache.flink.streaming.api.windowing.time.Time;
import org.apache.flink.streaming.api.windowing.windows.TimeWindow;

/**
 * @ClassName : PvHour
 * @Description : 一小时 页面的点击量是多少
 * 实现思路 - 先 设置wartemark 时间， 然后在进行开窗多久(例如一小时)， 然后 对一小时中的数据进行统计
 * @Author :wudl
 * @Date: 2020-11-12 22:41
 */
public class PvHour {
    public static void main(String[] args) throws Exception {
        StreamExecutionEnvironment env = StreamExecutionEnvironment.getExecutionEnvironment();
        env.setParallelism(1);
        env.setStreamTimeCharacteristic(TimeCharacteristic.EventTime);
        // 从文件中或者从kafka 中进行读取
        // -- 假如先从文件中读取
        SingleOutputStreamOperator<UserBehavior> operator = env.readTextFile("D:\\ideaWorkSpace\\learning\\Flinklearning\\wudl-flink-java\\input\\UserBehavior.csv").map(new MapFunction<String, UserBehavior>() {
            @Override
            public UserBehavior map(String s) throws Exception {
                String[] datas = s.split(",");
                return new UserBehavior(Long.valueOf(datas[0]), Long.valueOf(datas[1]), Integer.valueOf(datas[2]), datas[3], Long.valueOf(datas[4]));
            }
        })
                //  设置watermark
                .assignTimestampsAndWatermarks(new AscendingTimestampExtractor<UserBehavior>() {
                    @Override
                    public long extractAscendingTimestamp(UserBehavior element) {
                        // Flink 中都是毫秒 ， 所以乘以1000L
                        return element.getTimestamp() * 1000L;
                    }
                });

        // 实现pv 的统计
        // 转化为元祖
        SingleOutputStreamOperator<UserBehavior> userBehaviorFilter = operator.filter(data -> "pv".equals(data.getBehavior()));
        // 转换成 二元组 (pv,1)
        SingleOutputStreamOperator<Tuple2<String, Integer>> pvTuple = userBehaviorFilter.map(new MapFunction<UserBehavior, Tuple2<String, Integer>>() {
            @Override
            public Tuple2<String, Integer> map(UserBehavior userBehavior) throws Exception {
                return Tuple2.of("pv", 1);
            }
        });
        // 按照第一个位置的元素 分组 => 聚合算子只能在分组之后调用，也就是 keyedStream才能调用 sum
        KeyedStream<Tuple2<String, Integer>, Tuple> tupleKeyedStream = pvTuple.keyBy(0);
        // 开窗
        WindowedStream<Tuple2<String, Integer>, Tuple, TimeWindow> windowedStream = tupleKeyedStream.timeWindow(Time.hours(1));
        // 求和
        SingleOutputStreamOperator<Tuple2<String, Integer>> sum = windowedStream.sum(1);
        // 打印
        sum.print();
        env.execute();
    }
}

执行结果如下：