[SPARK-11258] Converting a Spark DataFrame into an R data.frame is slow / requires a lot of memory

https://issues.apache.org/jira/browse/SPARK-11258

I was not able to locate an existing unit test for this function so I wrote one.

Author: Frank Rosner <frank@fam-rosner.de>

Closes #9222 from FRosner/master.

sql/core/src/main/scala/org/apache/spark/sql/api/r/SQLUtils.scala

@@ -130,16 +130,18 @@ private[r] object SQLUtils {
   }
 
   def dfToCols(df: DataFrame): Array[Array[Any]] = {
-    // localDF is Array[Row]
-    val localDF = df.collect()
+    val localDF: Array[Row] = df.collect()
     val numCols = df.columns.length
+    val numRows = localDF.length
 
-    // result is Array[Array[Any]]
-    (0 until numCols).map { colIdx =>
-      localDF.map { row =>
-        row(colIdx)
+    val colArray = new Array[Array[Any]](numCols)
+    for (colNo <- 0 until numCols) {
+      colArray(colNo) = new Array[Any](numRows)
+      for (rowNo <- 0 until numRows) {
+        colArray(colNo)(rowNo) = localDF(rowNo)(colNo)
       }
-    }.toArray
+    }
+    colArray
   }
 
   def saveMode(mode: String): SaveMode = {

sql/core/src/test/scala/org/apache/spark/sql/api/r/SQLUtilsSuite.scala

+/*
+* Licensed to the Apache Software Foundation (ASF) under one or more
+* contributor license agreements.  See the NOTICE file distributed with
+* this work for additional information regarding copyright ownership.
+* The ASF licenses this file to You under the Apache License, Version 2.0
+* (the "License"); you may not use this file except in compliance with
+* the License.  You may obtain a copy of the License at
+*
+*    http://www.apache.org/licenses/LICENSE-2.0
+*
+* Unless required by applicable law or agreed to in writing, software
+* distributed under the License is distributed on an "AS IS" BASIS,
+* WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+* See the License for the specific language governing permissions and
+* limitations under the License.
+*/
+
+package org.apache.spark.sql.api.r
+
+import org.apache.spark.sql.test.SharedSQLContext
+
+class SQLUtilsSuite extends SharedSQLContext {
+
+  import testImplicits._
+
+  test("dfToCols should collect and transpose a data frame") {
+    val df = Seq(
+      (1, 2, 3),
+      (4, 5, 6)
+    ).toDF
+    assert(SQLUtils.dfToCols(df) === Array(
+      Array(1, 4),
+      Array(2, 5),
+      Array(3, 6)
+    ))
+  }
+
+}