Github user cloud-fan commented on a diff in the pull request:
https://github.com/apache/spark/pull/19136#discussion_r138554005
--- Diff:
sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/v2/DataSourceV2Strategy.scala
---
@@ -0,0 +1,95 @@
+/*
+ * 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.Strategy
+import org.apache.spark.sql.catalyst.expressions._
+import org.apache.spark.sql.catalyst.planning.PhysicalOperation
+import org.apache.spark.sql.catalyst.plans.logical.LogicalPlan
+import org.apache.spark.sql.execution.{FilterExec, ProjectExec, SparkPlan}
+import org.apache.spark.sql.execution.datasources.DataSourceStrategy
+import org.apache.spark.sql.sources.Filter
+import
org.apache.spark.sql.sources.v2.reader.downward.{CatalystFilterPushDownSupport,
ColumnPruningSupport, FilterPushDownSupport}
+
+object DataSourceV2Strategy extends Strategy {
+ // TODO: write path
+ override def apply(plan: LogicalPlan): Seq[SparkPlan] = plan match {
+ case PhysicalOperation(projects, filters, DataSourceV2Relation(output,
reader)) =>
+ val attrMap = AttributeMap(output.zip(output))
+
+ val projectSet = AttributeSet(projects.flatMap(_.references))
+ val filterSet = AttributeSet(filters.flatMap(_.references))
+
+ // Match original case of attributes.
+ // TODO: nested fields pruning
+ val requiredColumns = (projectSet ++ filterSet).toSeq.map(attrMap)
+ reader match {
+ case r: ColumnPruningSupport =>
+ r.pruneColumns(requiredColumns.toStructType)
+ case _ =>
+ }
+
+ val stayUpFilters: Seq[Expression] = reader match {
+ case r: CatalystFilterPushDownSupport =>
+ r.pushCatalystFilters(filters.toArray)
+
+ case r: FilterPushDownSupport =>
--- End diff --
After some attempts, I went back with 2 individual interfaces. The reason
is that, a) `CatalystFilterPushDownSupport` is an unstable interface, and it
looks weird to let a stable interface extend an unstable one. b) the logic that
converts expressions to public filters belongs to Spark internal, and we may
change it in the future, so we should not put these codes in a public
interface. We may have a risk of breaking compatibility for this interface.
---
---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]
