@Public
@FunctionalInterface
public interface ReduceFunction<T> extends Function, Serializable {
    /**
     * The core method of ReduceFunction, combining two values into one value of the same type. The
     * reduce function is consecutively applied to all values of a group until only a single value
     * remains.
     *
     * @param value1 The first value to combine.
     * @param value2 The second value to combine.
     * @return The combined value of both input values.
     * @throws Exception This method may throw exceptions. Throwing an exception will cause the
     *     operation to fail and may trigger recovery.
     */
    T reduce(T value1, T value2) throws Exception;
}

package com.rosh.flink.test;
import org.apache.flink.api.common.functions.MapFunction;
import org.apache.flink.api.common.functions.ReduceFunction;
import org.apache.flink.api.java.tuple.Tuple2;
import org.apache.flink.streaming.api.datastream.DataStreamSource;
import org.apache.flink.streaming.api.datastream.SingleOutputStreamOperator;
import org.apache.flink.streaming.api.environment.StreamExecutionEnvironment;
import java.util.ArrayList;
import java.util.List;
import java.util.Random;
/**
 * 我們將數(shù)據(jù)流按照用戶 id 進(jìn)行分區(qū)，然后用一個(gè) reduce 算子實(shí)現(xiàn) sum 的功能，統(tǒng)計(jì)每個(gè)
 * 用戶訪問(wèn)的頻次；進(jìn)而將所有統(tǒng)計(jì)結(jié)果分到一組，用另一個(gè) reduce 算子實(shí)現(xiàn) maxBy 的功能，
 * 記錄所有用戶中訪問(wèn)頻次最高的那個(gè)，也就是當(dāng)前訪問(wèn)量最大的用戶是誰(shuí)。
 */
public class TransReduceTest {
    public static void main(String[] args) throws Exception {
        StreamExecutionEnvironment env = StreamExecutionEnvironment.getExecutionEnvironment();
        env.setParallelism(1);
        //隨機(jī)生成數(shù)據(jù)
        Random random = new Random();
        List<Integer> userIds = new ArrayList<>();
        for (int i = 1; i <= 10; i++) {
            userIds.add(random.nextInt(5));
        }
        DataStreamSource<Integer> userIdDS = env.fromCollection(userIds);
        //每個(gè)ID訪問(wèn)記錄一次
        SingleOutputStreamOperator<Tuple2<Integer, Long>> mapDS = userIdDS.map(new MapFunction<Integer, Tuple2<Integer, Long>>() {
            @Override
            public Tuple2<Integer, Long> map(Integer value) throws Exception {
                return new Tuple2<>(value, 1L);
            }
        });
        //統(tǒng)計(jì)每個(gè)user訪問(wèn)多少次
        SingleOutputStreamOperator<Tuple2<Integer, Long>> sumDS = mapDS.keyBy(tuple -> tuple.f0).reduce(new ReduceFunction<Tuple2<Integer, Long>>() {
            @Override
            public Tuple2<Integer, Long> reduce(Tuple2<Integer, Long> value1, Tuple2<Integer, Long> value2) throws Exception {
                return new Tuple2<>(value1.f0, value1.f1 + value2.f1);
            }
        });
        sumDS.print("sumDS  ->>>>>>>>>>>>>");
        //把所有分區(qū)合并，求出最大的訪問(wèn)量
        SingleOutputStreamOperator<Tuple2<Integer, Long>> maxDS = sumDS.keyBy(key -> true).reduce(new ReduceFunction<Tuple2<Integer, Long>>() {
            @Override
            public Tuple2<Integer, Long> reduce(Tuple2<Integer, Long> value1, Tuple2<Integer, Long> value2) throws Exception {
                if (value1.f1 > value2.f1) {
                    return value1;
                } else {
                    return value2;
                }
            }
        });
        maxDS.print("maxDS ->>>>>>>>>>>");
        env.execute("TransReduceTest");
    }
}