Github user davies commented on a diff in the pull request:
https://github.com/apache/spark/pull/11636#discussion_r56691784
--- Diff:
sql/core/src/main/scala/org/apache/spark/sql/execution/ExistingRDD.scala ---
@@ -199,15 +199,20 @@ private[sql] case class DataSourceScan(
// never requires UnsafeRow as input.
override protected def doProduce(ctx: CodegenContext): String = {
val columnarBatchClz =
"org.apache.spark.sql.execution.vectorized.ColumnarBatch"
+ val columnVectorClz =
"org.apache.spark.sql.execution.vectorized.ColumnVector"
val input = ctx.freshName("input")
val idx = ctx.freshName("batchIdx")
+ val rowidx = ctx.freshName("rowIdx")
val batch = ctx.freshName("batch")
// PhysicalRDD always just has one input
ctx.addMutableState("scala.collection.Iterator", input, s"$input =
inputs[0];")
ctx.addMutableState(columnarBatchClz, batch, s"$batch = null;")
ctx.addMutableState("int", idx, s"$idx = 0;")
- val exprs = output.zipWithIndex.map(x => new BoundReference(x._2,
x._1.dataType, true))
+ val exprCols = output.zipWithIndex.map(
+ x => new InputReference(x._2, x._1.dataType, x._1.nullable, rowidx))
+ val exprRows = output.zipWithIndex.map(
+ x => new InputReference(x._2, x._1.dataType, x._1.nullable))
--- End diff --
Should we use BoundReference here?
---
If your project is set up for it, you can reply to this email and have your
reply appear on GitHub as well. If your project does not have this feature
enabled and wishes so, or if the feature is enabled but not working, please
contact infrastructure at infrastruct...@apache.org or file a JIRA ticket
with INFRA.
---
---------------------------------------------------------------------
To unsubscribe, e-mail: reviews-unsubscr...@spark.apache.org
For additional commands, e-mail: reviews-h...@spark.apache.org
