flink:自定义数据分区

amadeus_liu22024-03-09 10:31

shuffle随机地将数据分配到下游的子任务。

rebalance用round robbin模式将数据分配到下游的子任务。

global把所有的数据都分配到一个分区。

partitionCustom: 自定义数据分区。

package cn.edu.tju.demo;

import org.apache.flink.api.common.functions.;
import org.apache.flink.api.common.serialization.SimpleStringSchema;
import org.apache.flink.api.java.tuple.Tuple2;
import org.apache.flink.configuration.Configuration;
import org.apache.flink.streaming.api.collector.selector.OutputSelector;
import org.apache.flink.streaming.api.datastream. ;

import org.apache.flink.streaming.api.environment.StreamExecutionEnvironment;

import org.apache.flink.streaming.api.functions.co.CoMapFunction;

import org.apache.flink.streaming.api.functions.source.SourceFunction;

import org.apache.flink.streaming.connectors.kafka.FlinkKafkaConsumer;

import org.apache.flink.util.Collector;

import org.apache.kafka.clients.consumer.ConsumerConfig;

import org.apache.kafka.clients.producer.ProducerConfig;

import org.apache.kafka.common.serialization.StringDeserializer;

import org.apache.kafka.common.serialization.StringSerializer;

import java.util.*;

public class Test12 {

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

StreamExecutionEnvironment environment = StreamExecutionEnvironment

.getExecutionEnvironment();

复制代码

    DataStreamSource<String> mySource = environment.addSource(new MySourceFunction());
    SingleOutputStreamOperator<Tuple2<String, Integer>> mapStream = mySource.map(new MapFunction<String, Tuple2<String, Integer>>() {
        @Override
        public Tuple2<String, Integer> map(String value) throws Exception {
            return new Tuple2<>(value, new Random().nextInt(10));
        }
    });

    DataStream<Tuple2<String, Integer>> resultStream = mapStream.partitionCustom(new MyPartitioner(), 1);


    resultStream.print();

    environment.execute("my job");

}

public static class MyPartitioner implements Partitioner<Integer>{

    @Override
    public int partition(Integer key, int partitions) {
        return key % partitions;
    }
}



public static class MySourceFunction implements SourceFunction<String> {
    private boolean runningFlag = true;
    @Override
    public void run(SourceContext<String> ctx) throws Exception {
        while (runningFlag){
            ctx.collect("hi world");
            ctx.collect("hello world");
            Thread.sleep(30000);
        }
    }

    @Override
    public void cancel() {
        runningFlag = false;
    }
}

}