Spark RDD两种创建方式

1.从集合创建RDD

public class test_list {
    public static void main(String[] args) {
        //1.配置对象
        SparkConf sparkConf = new SparkConf ().setMaster ("local[*]").setAppName ("test_list");
        //2.创建环境
        JavaSparkContext sc = new JavaSparkContext (sparkConf);
        //3.编写逻辑代码
        JavaRDD<String> javaRDD = sc.parallelize (Arrays.asList ("1", "2", "3", "4", "5"));
        List<String> result = javaRDD.collect ();
        result.forEach (s -> System.out.println (s));
        //4.关闭sc
        sc.stop ();
    }
}

2.从文件创建RDD

 public static void main(String[] args) {
        //1.配置对象
        SparkConf sparkConf = new SparkConf ().setMaster ("local[*]").setAppName ("test02_file");
        //2.创建环境
        JavaSparkContext sc = new JavaSparkContext (sparkConf);
        //3.编写逻辑代码
        JavaRDD<String> javaRDD = sc.textFile ("doc/test");
        List<String> result = javaRDD.collect ();
        result.forEach (s -> System.out.println (s));
        //4.关闭sc
        sc.stop ();
    }