flink之分区和分组的区别（模拟上游两个分区向下游四个分区发送数据）

package com.sandra.day03;

import com.atguigu.bean.WaterSensor;
import org.apache.flink.api.common.functions.MapFunction;
import org.apache.flink.api.java.functions.KeySelector;
import org.apache.flink.api.java.tuple.Tuple;
import org.apache.flink.streaming.api.datastream.DataStreamSource;
import org.apache.flink.streaming.api.datastream.KeyedStream;
import org.apache.flink.streaming.api.datastream.SingleOutputStreamOperator;
import org.apache.flink.streaming.api.environment.StreamExecutionEnvironment;

//模拟上游两个分区数据通过keyBy向下游四个分区哪个分区发送

public class Flink04_Transform_KeyBy {
    public static void main(String[] args) throws Exception {
        //todo 1.获取流的执行环境
        StreamExecutionEnvironment env = StreamExecutionEnvironment.getExecutionEnvironment();

        env.setParallelism(4);

        //todo 2.从端口读取数据
        DataStreamSource<String> streamSource = env.socketTextStream("hadoop102", 9999);

        //todo 3.使用map将读取的数据转为WaterSensor
        SingleOutputStreamOperator<WaterSensor> result = streamSource.map(new MapFunction<String, WaterSensor>() {
            @Override
            public WaterSensor map(String line) throws Exception {
                String[] waterSensorWords = line.split(" ");


                return new WaterSensor(waterSensorWords[0], Long.parseLong(waterSensorWords[1]), Integer.parseInt(waterSensorWords[2]));
            }
        }).setParallelism(2);

        //将上游数据打印，看看数据去往上游数据的哪个分区（上游有2个分区）
        result.print("原始数据").setParallelism(2);//map和print的并行度都设置为2，目的是将它们串到一起

        //todo 4.使用keyby将相同的id的数据放到一块
        KeyedStream<WaterSensor, String> keyedStream = result.keyBy(new KeySelector<WaterSensor, String>() {
            @Override
            public String getKey(WaterSensor value) throws Exception {
                return value.getId();
            }
        });

//        KeyedStream<WaterSensor, Tuple> keyedStream1 = result.keyBy("id");

        //将下游的数据打印出来，看看上游两个分区的数据分别去往下游的哪个分区
        keyedStream.print("keyBy");//并行度为4



        env.execute();

    }
}

其中：

package com.sandra.bean;

import lombok.AllArgsConstructor;
import lombok.Data;
import lombok.NoArgsConstructor;

@NoArgsConstructor
@AllArgsConstructor
@Data
public class WaterSensor {
    private String id;
    private Long ts;
    private Integer vc;
}

 总结：相同key的数据必然在同一个分区，一个分区中可能有多个不同的key，一个分组中的key必然是相同的，一个分区可能有多个不同的分组，分组是逻辑上的划分，分区是物理上的划分。