194、Spark 2.0之Dataset开发详解-typed操

代码

object TypedOperation {

  case class Employee(name: String, age: Long, depId: Long, gender: String, salary: Long)

  def main(args: Array[String]): Unit = {
    val sparkSession = SparkSession
      .builder()
      .appName("BasicOperation")
      .master("local")
      .getOrCreate()

    import sparkSession.implicits._
    import org.apache.spark.sql.functions._

    val employeePath = this.getClass.getClassLoader.getResource("employee.json").getPath

    val employeeDF = sparkSession.read.json(employeePath)

    val employeeDS = employeeDF.as[Employee]

    employeeDS.sort(employeeDS("salary").desc, employeeDS("age").asc).show()
  }
}