import org.apache.spark.{SparkContext, SparkConf}

/**
 * Created by ESRI on 2017/6/14.
 */

object sqltest2 {
  case class Person(name: String, age: Int)
  def main(args: Array[String]) {
    println("I Love You Scala")

    System.setProperty("hadoop.home.dir", "E:\\bigdataTools\\hadoop\\hadoop-2.6.0\\hadoop-2.6.0")
    val conf = new SparkConf().setMaster("local").setAppName("wordCount")
    val sc = new SparkContext(conf)
    val sqlContext = new org.apache.spark.sql.SQLContext(sc)

    import sqlContext.implicits._

    // Define the schema using a case class.
    // Note: Case classes in Scala 2.10 can support only up to 22 fields. To work around this limit,
    // you can use custom classes that implement the Product interface.


    // Create an RDD of Person objects and register it as a table.
    val people = sc.textFile("E:\\testData\\spark\\spark1.6\\people.txt").map(_.split(",")).map(p => Person(p(0).trim.toString, p(1).trim.toInt)).toDF()
    people.registerTempTable("people")

    // SQL statements can be run by using the sql methods provided by sqlContext.
    val teenagers = sqlContext.sql("SELECT name, age FROM people WHERE age >= 13 AND age <= 19")

    // The results of SQL queries are DataFrames and support all the normal RDD operations.
    // The columns of a row in the result can be accessed by field index:
    teenagers.map(t => "Name: " + t(0)).collect().foreach(println)

    // or by field name:
    teenagers.map(t => "Name: " + t.getAs[String]("name")).collect().foreach(println)

    // row.getValuesMap[T] retrieves multiple columns at once into a Map[String, T]
    //teenagers.map(_.getValuesMap[Any](List("name", "age"))).collect().foreach(println)

  }
}