RDD — flatmap

  def main(args: Array[String]): Unit = { 
   
    //设置log级别
    Logger.getLogger("org").setLevel(Level.WARN)
    val conf = new SparkConf().setAppName("WordCountDemo").setMaster("local")
    val sc = new SparkContext(conf)
    sc.textFile("hdfs://hadoop001:9000/in/word")
      .flatMap(_.split(" ")).map((_,1)).reduceByKey(_ + _).collect().foreach(println(_))
    sc.stop()
  }

  def main(args: Array[String]): Unit = { 
   
    val spark = SparkSession.builder()
      .config("spark.executor.memory", "2g")
      .appName("WordCount")
      .master("local[6]")
      .getOrCreate()
    val sc = spark.sparkContext
    
    val array = Array((1,"a b c d"),(2,"a b c"),(3,"a b"))
    /** * 第一种写法 */
    val rdd = sc.parallelize(array)
      rdd.flatMap(x => { 
   
        val sub = ArrayBuffer.empty[(Int, String)]
        x._2.split(" ").foreach(e => { 
   
          sub.+=((x._1, e))
        })
        sub.iterator
      }).collect().foreach(println)

    /** * 第二种写法 */
    //rdd.flatMap(x=> x._2.split(" ").map(y =>(x._1,y))).collect().foreach(println)
    sc.stop()
    spark.close()
  }

(1,a)
(1,b)
(1,c)
(1,d)
(2,a)
(2,b)
(2,c)
(3,a)
(3,b)