case class Person(name:String,age:Int)

val rddpeople=sc.textFile("/sparksql/people.txt").map(_.split(",")).map(p=>Person(p(0),p(1).trim.toInt))

rddpeople.registerTempTable("rddTable")

sqlContext.sql("SELECT name FROM rddTable WHERE age >= 13 AND age <= 19").map(t => "Name: " + t(0)).collect().foreach(println)

//RDD2演示//導入SparkSQL的數據類型和Row

import org.apache.spark.sql._//創建于數據結構匹配的schema

val schemaString = "name age"

val schema =? StructType(? ? schemaString.split(" ").map(fieldName => StructField(fieldName, StringType, true)))//創建rowRDD

val rowRDD = sc.textFile("/sparksql/people.txt").map(_.split(",")).map(p => Row(p(0), p(1).trim))//用applySchema將schema應用到rowRDD

val rddpeople2 = sqlContext.applySchema(rowRDD, schema)

rddpeople2.registerTempTable("rddTable2")

sqlContext.sql("SELECT name FROM rddTable2 WHERE age >= 13 AND age <= 19").map(t => "Name: " + t(0)).collect().foreach(println)

//parquet演示

val parquetpeople = sqlContext.parquetFile("/sparksql/people.parquet")

parquetpeople.registerTempTable("parquetTable")

sqlContext.sql("SELECT name FROM parquetTable WHERE age >= 25").map(t => "Name: " + t(0)).collect().foreach(println)

//json演示

val jsonpeople = sqlContext.jsonFile("/sparksql/people.json")

jsonpeople.registerTempTable("jsonTable")

sqlContext.sql("SELECT name FROM jsonTable WHERE age >= 25").map(t => "Name: " + t(0)).collect().foreach(println)

//jsonRdd

//千萬不要先使用cache SchemaRDD，然后registerAsTable

//在默認的情況下，內存列存儲的壓縮功能是關閉的，要使用壓縮功能需要配置變量COMPRESS_CACHED。

//sqlContext的cache使用

sqlContext.cacheTable("rddTable")

sqlContext.sql("SELECT name FROM rddTable WHERE age >= 13 AND age <= 19").map(t => "Name: " + t(0)).collect().foreach(println)

scala2.10.4本身對case class有22列的限制，在使用RDD數據源的時候就會造成不方便；

sqlContext中3個表不能同時join，需要兩兩join后再join一次；

sqlContext中不能直接使用values插入數據；

在編寫sqlContext應用程序的時候，case class要定義在object之外。

sqlContext.sql("SELECT name FROM parquetTable WHERE age >= 13 AND age <= 19").map(t => "Name: " + t(0)).collect().foreach(println)