我想出的最好的解决方案需要对新类进行最少的复制和粘贴,如下所示(不过我仍然希望看到另一个解决方案)
首先,您必须定义您的案例类和(部分)可重用的工厂方法
import org.apache.spark.sql.catalyst.expressions
case class MyClass(fooBar: Long, fred: Long)
// Here you want to auto gen these functions using macros or something
object Factories extends java.io.Serializable {
def longLong[T](fac: (Long, Long) => T)(row: expressions.Row): T =
fac(row(0).asInstanceOf[Long], row(1).asInstanceOf[Long])
}
一些已经可用的样板
import scala.reflect.runtime.universe._
val sqlContext = new org.apache.spark.sql.SQLContext(sc)
import sqlContext.createSchemaRDD
魔法
import scala.reflect.ClassTag
import org.apache.spark.sql.SchemaRDD
def camelToUnderscores(name: String) =
"[A-Z]".r.replaceAllIn(name, "_" + _.group(0).toLowerCase())
def getCaseMethods[T: TypeTag]: List[String] = typeOf[T].members.sorted.collect {
case m: MethodSymbol if m.isCaseAccessor => m
}.toList.map(_.toString)
def caseClassToSQLCols[T: TypeTag]: List[String] =
getCaseMethods[T].map(_.split(" ")(1)).map(camelToUnderscores)
def schemaRDDToRDD[T: TypeTag: ClassTag](schemaRDD: SchemaRDD, fac: expressions.Row => T) = {
val tmpName = "tmpTableName" // Maybe should use a random string
schemaRDD.registerAsTable(tmpName)
sqlContext.sql("SELECT " + caseClassToSQLCols[T].mkString(", ") + " FROM " + tmpName)
.map(fac)
}
示例使用
val parquetFile = sqlContext.parquetFile(path)
val normalRDD: RDD[MyClass] =
schemaRDDToRDD[MyClass](parquetFile, Factories.longLong[MyClass](MyClass.apply))
也可以看看:
http://apache-spark-user-list.1001560.n3.nabble.com/Spark-SQL-Convert-SchemaRDD-back-to-RDD-td9071.html
尽管我没有通过 JIRA 链接找到任何示例或文档。