【Spark学习笔记】3、Java版-算子系列之map(f:T => U) : RDD[T] => RDD[U]

map算子源码

/**
 * Return a new RDD by applying a function to all elements of this RDD.
 */
def map[U: ClassTag](f: T => U): RDD[U] = withScope {
  val cleanF = sc.clean(f)
  new MapPartitionsRDD[U, T](this, (context, pid, iter) => iter.map(cleanF))
}

java代码demo

public class MapOperator {

	public static void main(String[] args) {
		SparkConf conf = new SparkConf().setAppName("MapOperator").setMaster("local");
		JavaSparkContext sc = new JavaSparkContext(conf);

		List<Integer> numbers = Arrays.asList(1, 2, 3, 4, 5);
		JavaRDD<Integer> numberRDD = sc.parallelize(numbers);
		JavaRDD<Integer> results = numberRDD.map(new Function<Integer, Integer>() {
			private static final long serialVersionUID = 1L;

			@Override
			public Integer call(Integer number) throws Exception {
				return number * 10;
			}
		});
		results.foreach(new VoidFunction<Integer>() {
			private static final long serialVersionUID = 1L;

			@Override
			public void call(Integer result) throws Exception {
				System.out.println(result);
			}
		});
		sc.close();
	}

}

输出

10
20
30
40
50