资源

【1】flink官方下载：http://flink.apache.org/downloads.html#apache-flink-1140
【2】Flink从入门到真香(16、Flink内置的一些Process Function)：https://blog.51cto.com/mapengfei/2554673

自定义分区

  1. import org.apache.flink.api.common.functions.Partitioner;
  2. import org.apache.flink.api.java.tuple.Tuple2;
  3. import org.apache.flink.streaming.api.datastream.DataStream;
  4. import org.apache.flink.streaming.api.environment.StreamExecutionEnvironment;
  6. import java.util.Arrays;
  8. public class PartitionerTest {
  10.     public static void main(String[] args) throws Exception {
  11.         StreamExecutionEnvironment env = StreamExecutionEnvironment.getExecutionEnvironment();
  12.         DataStream dataStream = env.fromCollection(Arrays.asList(
  13.                 new Tuple2<String, Long>("1", 1L),
  14.                 new Tuple2<String, Long>("2", 2L),
  15.                 new Tuple2<String, Long>("3", 3L),
  16.                 new Tuple2<String, Long>("4", 4L)
  17.         ));
  19.         DataStream partitionData = dataStream.partitionCustom(new MyPartitioner(), 1);
  20.         // 分区数和并行度有关，并行度要大于等于当前数据可以分区的个数
  21.         partitionData.print().setParallelism(2);
  22.         env.execute("PartitionerTest");
  23.     }
  24. }
  26. class MyPartitioner implements Partitioner<Long> {
  27.     @Override
  28.     public int partition(Long s, int i) {
  29.         System.out.println("s = " + s + "i = " + i);
  30.         if(s % 2 == 0) {
  31.             return 0;
  32.         } else {
  33.             return 1;
  34.         }
  35.     }
  36. }
  41. ====> 输出
  42. s = 1i = 2
  43. s = 2i = 2
  44. s = 3i = 2
  45. s = 4i = 2
  46. 1> (2,2)
  47. 2> (1,1)
  48. 1> (4,4)
  49. 2> (3,3)