-- Spark SQL 以编程方式指定模式

val sqlContext = new org.apache.spark.sql.SQLContext(sc)

val employee = sc.textFile("/root/wangbin/employee.txt")

1201,satish,25

1202,krishna,28

1203,amith,39

1204,javed,23

1205,prudvi,23

val schemaString = "id,name,age"

import org.apache.spark.sql.Row;

import org.apache.spark.sql.types.{StructType, StructField, StringType};

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

val rowRDD = employee.map(_.split(",")).map(e => Row(e(0), e(1), e(2)))

-- 通过使用roRDDdata和模式（SCHEMA）变量创建DataFrame。

val employeeDF = sqlContext.createDataFrame(rowRDD, schema)

-- 使用以下命令将数据帧存储到名为employee的表中。

employeeDF.registerTempTable("employee2")

-- 使用以下语句从employee表中选择所有记录。

val allrecords = sqlContext.sql("SELECT * FROM employee2")

-- 查看所有记录数据帧的结果数据

allrecords.show()

+----+-------+---+

|  id|   name|age|

+----+-------+---+

|1201| satish| 25|

|1202|krishna| 28|

|1203|  amith| 39|

|1204|  javed| 23|

|1205| prudvi| 23|

+----+-------+---+