SparkRDD之collectAsMap

与collect类似，但适用于键值RDD并将它们转换为Map映射以保留其键值结构

java示例如下：

package com.cb.spark.sparkrdd;

import java.util.Arrays;
import java.util.Map;

import org.apache.spark.SparkConf;
import org.apache.spark.api.java.JavaPairRDD;
import org.apache.spark.api.java.JavaRDD;
import org.apache.spark.api.java.JavaSparkContext;

public class CollectAsMapExample {
	public static void main(String[] args) {
		SparkConf conf = new SparkConf().setAppName("CollectAsMap").setMaster("local");
		JavaSparkContext jsc = new JavaSparkContext(conf);
		JavaRDD<Integer>javaRDD=jsc.parallelize(Arrays.asList(1,2,1,3),1);
		JavaPairRDD<Integer, Integer> javaPairRDD=javaRDD.zip(javaRDD);
		Map<Integer, Integer>map=javaPairRDD.collectAsMap();
		System.out.println(map);
		jsc.stop();
	}
}

scala示例如下：

package com.cb.spark.rdd

import org.apache.spark.SparkConf
import org.apache.spark.SparkContext

object CollectAsMap {
  def main(args: Array[String]): Unit = {
    val conf = new SparkConf().setMaster("local[2]").setAppName("CollectAsMap")
    val sc = new SparkContext(conf)
    val a = sc.parallelize(List(1, 2, 3, 1, 2), 1)
    val b = sc.parallelize(List("a", "b", "c", "b", "d"), 1)
    val c = a.zip(b)
    c.foreach(println)
    println()
    c.collectAsMap().foreach(println)
  }
}