[SPARK-6326][SQL] Improve castStruct to be faster

Current `castStruct` should be very slow. This pr slightly improves it. Author: Liang-Chi Hsieh <[email protected]> Closes apache#5017 from viirya/faster_caststruct and squashes the following commits: 385d5b0 [Liang-Chi Hsieh] Further improved. 746fcfb [Liang-Chi Hsieh] Make castStruct faster.
liancheng · Mar 26, 2015 · 73d5775 · 73d5775
1 parent e6d1406
commit 73d5775
Showing 1 changed file with 11 additions and 4 deletions.
diff --git a/sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/Cast.scala b/sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/Cast.scala
@@ -394,10 +394,17 @@ case class Cast(child: Expression, dataType: DataType) extends UnaryExpression w
     val casts = from.fields.zip(to.fields).map {
       case (fromField, toField) => cast(fromField.dataType, toField.dataType)
     }
-    // TODO: This is very slow!
-    buildCast[Row](_, row => Row(row.toSeq.zip(casts).map {
-      case (v, cast) => if (v == null) null else cast(v)
-    }: _*))
+    // TODO: Could be faster?
+    val newRow = new GenericMutableRow(from.fields.size)
+    buildCast[Row](_, row => {
+      var i = 0
+      while (i < row.length) {
+        val v = row(i)
+        newRow.update(i, if (v == null) null else casts(i)(v))
+        i += 1
+      }
+      newRow.copy()
+    })
   }
 
   private[this] def cast(from: DataType, to: DataType): Any => Any = to match {