sparksql语法，通过映射方式读txt

Inferring the Schema Using Reflection（通过映射指定schema）

--声明一个类
scala> case class Person(name: String, age: Int)
defined class Person

--读取txt文件内容，然后映射到类的字段，转化成dataframe
scala> val people = sc.textFile("hdfs://node1:8020/test/input/people.txt").map(_.split(",")).map(p => Person(p(0), p(1).trim.toInt)).toDF()

people: org.apache.spark.sql.DataFrame = [name: string, age: int]

--变量注册成表，表名为people
scala> people.registerTempTable("people");

--执行sql
scala> val teenagers=sqlContext.sql("select name,age from people where age>=13 and age<=19")

teenagers: org.apache.spark.sql.DataFrame = [name: string, age: int]

scala> teenagers.show
+------+---+
|  name|age|
+------+---+
|Justin| 19|
+------+---+

scala> teenagers.select("name").show
+------+
|  name|
+------+
|Justin|
+------+

scala> teenagers.count
res19: Long = 1


--通过位置访问
scala> teenagers.map(t => "Name: " + t(0)).collect().foreach(println)
Name: Justin

--通过字段访问
scala> teenagers.map(t => "Name: " + t.getAs[String]("name")).collect().foreach(println)
Name: Justin

--转化成map对
scala> teenagers.map(_.getValuesMap[Any](List("name", "age"))).collect().foreach(println)
Map(name -> Justin, age -> 19)