Github user cloud-fan commented on a diff in the pull request:
https://github.com/apache/spark/pull/19136#discussion_r137698996
--- Diff:
sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/v2/DataSourceV2Relation.scala
---
@@ -0,0 +1,39 @@
+/*
+ * 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.execution.datasources.v2
+
+import org.apache.spark.sql.catalyst.expressions.AttributeReference
+import org.apache.spark.sql.catalyst.plans.logical.{LeafNode, Statistics}
+import org.apache.spark.sql.sources.v2.reader.DataSourceV2Reader
+import org.apache.spark.sql.sources.v2.reader.upward.StatisticsSupport
+
+case class DataSourceV2Relation(
+ output: Seq[AttributeReference],
+ reader: DataSourceV2Reader) extends LeafNode {
+
+ override def computeStats(): Statistics = reader match {
+ case r: StatisticsSupport => Statistics(sizeInBytes =
r.getStatistics.sizeInBytes())
+ case _ => Statistics(sizeInBytes = conf.defaultSizeInBytes)
+ }
+}
+
+object DataSourceV2Relation {
+ def apply(reader: DataSourceV2Reader): DataSourceV2Relation = {
+ new DataSourceV2Relation(reader.readSchema().toAttributes, reader)
--- End diff --
In data source V2, we will delegate partition pruning to the data source,
although we need to do some refactoring to make it happen.
> I was just looking into how the data source should provide partition
data, or at least fields that are the same for all rows in a `ReadTask`. It
would be nice to have a way to pass those up instead of materializing them in
each `UnsafeRow`.
This can be achieved by the columnar reader. Think about a data source
having a data column `i` and a partition column `j`, the returned columnar
batch has 2 column vectors for `i` and `j`. Column vector `i` is a normal one
that contains all the values of column `i` within this batch, column vector `j`
is a constant vector that only contains a single value.
---
---------------------------------------------------------------------
To unsubscribe, e-mail: reviews-unsubscr...@spark.apache.org
For additional commands, e-mail: reviews-h...@spark.apache.org
