spark读取hdfs上的json数据

准备数据源people.json数据，并放到hdfs上

{"name":"Michael"}
{"name":"Andy", "age":30}
{"name":"Justin", "age":19}

代码：

object jsonTest{
  def main(args: Array[String]): Unit = {
    val conf: SparkConf = new SparkConf().setAppName("jsonTest").setMaster("local")
    val sc = new SparkContext(conf)
    val jsonStrs: RDD[String] = sc.textFile("hdfs://hdp-1:9000/people.json")
    val result: RDD[Option[Any]] = jsonStrs.map(s => JSON.parseFull(s))
    result.foreach({r => r match {
      case Some (map: Map[String, Any]) => println(map)
      case None => println("Parsing failed")
      case other => println("Unknows data structure:" + other)
    }})
  }
}

运行结果：