Flink入门第四课：flink的增量聚合函数min/max/minBy/maxBy/reduce

package com.atguigu.Adatastream_api.transformations;

import com.atguigu.Fbeans.SensorReading;
import org.apache.flink.api.common.functions.RichReduceFunction;
import org.apache.flink.streaming.api.TimeCharacteristic;
import org.apache.flink.streaming.api.datastream.DataStream;
import org.apache.flink.streaming.api.datastream.DataStreamSource;
import org.apache.flink.streaming.api.datastream.KeyedStream;
import org.apache.flink.streaming.api.environment.StreamExecutionEnvironment;
/**
 *
 * 测试增量聚合算子，比如max/min/sum/maxBy/minBy/reduce等
 *  这些算子必须在keyBy之后使用，因为只有KeyedDataStream才能调用这些算子。
 *
 * min/max：
 *      会保存当前分组id的第一条记录，将后续到同Key但聚合值更大的记录的聚合值保存在该条记录聚合位置
 *minBy/maxBy:
 *      打印同key下极值最大的记录。
 *sum:
 *      会保存当前分组id的第一条记录，将后续不断更新的同Key的聚合值保存在该条记录的聚合位置
 *
 * reduce：
 *  reduce更加强大，可以对输入数据做任何操作得到输出数据。
 *
 */
public class RollingAggregateText {
    public static void main(String[] args) throws Exception{
        //创建环境
        StreamExecutionEnvironment env = StreamExecutionEnvironment.getExecutionEnvironment();
        env.setParallelism(1);
        env.setStreamTimeCharacteristic(TimeCharacteristic.EventTime);

        //读取数据并包装成pojo
        DataStreamSource<String> inputStream = env.readTextFile("G:\\SoftwareInstall\\idea\\project\\UserBehaviorAnalysis\\BasicKnowledge\\src\\main\\resources\\sensor.txt");
        DataStream<SensorReading> dataStream = inputStream.map(line -> {
            String[] fields = line.split(",");
            return new SensorReading(new String(fields[0]), new Long(fields[1]), new Double(fields[2]));
        });

        /**
         * 处理数据
         * keyBy(SensorReading::getId)  和 keyBy(data -> data.getId())  返回的是Id的类型，这儿是String
         * 直接传keyBy("id")则返回的是tuple类型、新版本即将过期
         * 必须是tuple2类型的数据分组才可以使用keyBy(0)
         */
        KeyedStream<SensorReading, String>  keyedStream = dataStream.keyBy(SensorReading::getId);//方法引用，调用SensorReading类getId方法

        DataStream<SensorReading> result1 = keyedStream.max("temperature");
        DataStream<SensorReading> result2 = keyedStream.maxBy("temperature");
        DataStream<SensorReading> result3 = keyedStream.sum("temperature");
        /**
         * 测试更加强大的reduce算子:
         *      获取最新记录的时间，和最高的温度
         * s1 是之前的记录，v2是新的记录
         */
        DataStream<SensorReading> result4 = keyedStream.reduce(new RichReduceFunction<SensorReading>() {
            @Override
            public SensorReading reduce(SensorReading s1, SensorReading s2) throws Exception {
                return new SensorReading(s1.getId(),s2.getTimestamp(),Math.max(s1.getTemperature(),s2.getTemperature()));
            }
        });
        //输出数据
        result1.print("max输出结果");
        result2.print("maxBy输出结果");
        result3.print("sum输出结果");
        result4.print("reduce输出结果");
        env.execute("测试flink的滚动聚合算子");

    }
}