PHILO-HE commented on code in PR #7842:
URL: https://github.com/apache/incubator-gluten/pull/7842#discussion_r1865318032
##########
gluten-substrait/src/test/scala/org/apache/gluten/execution/WholeStageTransformerSuite.scala:
##########
@@ -176,25 +176,39 @@ abstract class WholeStageTransformerSuite
result
}
+ protected def compareResultsAgainstVanillaSpark(
+ sql: String,
+ compareResult: Boolean = true,
+ customCheck: DataFrame => Unit,
+ noFallBack: Boolean = true,
+ cache: Boolean = false): DataFrame = {
+ compareDfResultsAgainstVanillaSpark(
+ () => spark.sql(sql),
+ compareResult,
+ customCheck,
+ noFallBack,
+ cache)
+ }
+
/**
* run a query with native engine as well as vanilla spark then compare the
result set for
* correctness check
*/
- protected def compareResultsAgainstVanillaSpark(
- sqlStr: String,
+ protected def compareDfResultsAgainstVanillaSpark(
Review Comment:
`Df` means Dataframe? The naming seems not friendly to reader.
##########
gluten-substrait/src/test/scala/org/apache/gluten/execution/WholeStageTransformerSuite.scala:
##########
@@ -176,25 +176,39 @@ abstract class WholeStageTransformerSuite
result
}
+ protected def compareResultsAgainstVanillaSpark(
+ sql: String,
+ compareResult: Boolean = true,
+ customCheck: DataFrame => Unit,
+ noFallBack: Boolean = true,
+ cache: Boolean = false): DataFrame = {
+ compareDfResultsAgainstVanillaSpark(
+ () => spark.sql(sql),
+ compareResult,
+ customCheck,
+ noFallBack,
+ cache)
+ }
+
/**
* run a query with native engine as well as vanilla spark then compare the
result set for
* correctness check
*/
- protected def compareResultsAgainstVanillaSpark(
- sqlStr: String,
+ protected def compareDfResultsAgainstVanillaSpark(
+ dataframe: () => DataFrame,
compareResult: Boolean = true,
customCheck: DataFrame => Unit,
noFallBack: Boolean = true,
cache: Boolean = false): DataFrame = {
var expected: Seq[Row] = null
withSQLConf(vanillaSparkConfs(): _*) {
- val df = spark.sql(sqlStr)
+ val df = dataframe()
expected = df.collect()
}
- // By default we will fallabck complex type scan but here we should allow
+ // By default, we will fallabck complex type scan but here we should allow
Review Comment:
Please also fix typo: `fallabck`.
##########
cpp/velox/substrait/SubstraitToVeloxPlanValidator.h:
##########
@@ -103,9 +106,17 @@ class SubstraitToVeloxPlanValidator {
std::vector<std::string> validateLog_;
- /// Used to get types from advanced extension and validate them.
- bool validateInputTypes(const ::substrait::extensions::AdvancedExtension&
extension, std::vector<TypePtr>& types);
+ /// Used to get types from advanced extension and validate them, then
convert to a Velox type that has arbitrary
+ /// levels of nesting.
+ bool validateInputVeloxType(const
::substrait::extensions::AdvancedExtension& extension, TypePtr& out);
Review Comment:
`validateInputVeloxType` makes me feel that the input is velox type. Can we
use some other name, e.g., `parseToVeloxType`?
##########
gluten-substrait/src/main/scala/org/apache/gluten/extension/columnar/UnionTransformerRule.scala:
##########
@@ -0,0 +1,61 @@
+/*
+ * 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.gluten.extension.columnar
+
+import org.apache.gluten.GlutenConfig
+import org.apache.gluten.execution.{ColumnarUnionExec, UnionExecTransformer}
+
+import org.apache.spark.sql.catalyst.plans.physical.UnknownPartitioning
+import org.apache.spark.sql.catalyst.rules.Rule
+import org.apache.spark.sql.execution.SparkPlan
+
+/**
+ * Replace ColumnarUnionExec with UnionExecTransformer if possible.
+ *
+ * The rule is not included in
[[org.apache.gluten.extension.columnar.heuristic.HeuristicTransform]]
+ * or [[org.apache.gluten.extension.columnar.enumerated.EnumeratedTransform]]
because it relies on
+ * children's output partitioning to be fully provided.
+ */
+case class UnionTransformerRule() extends Rule[SparkPlan] {
+ override def apply(plan: SparkPlan): SparkPlan = {
+ if (!GlutenConfig.getConf.enableNativeUnion) {
+ return plan
+ }
+ plan.transformUp {
+ case plan: ColumnarUnionExec =>
+ val transformer = UnionExecTransformer(plan.children)
+ if (sameNumPartitions(plan.children) && validate(transformer)) {
+ transformer
+ } else {
+ plan
+ }
+ }
+ }
+
+ private def sameNumPartitions(plans: Seq[SparkPlan]): Boolean = {
Review Comment:
Can we move this into the below `validate` function?
--
This is an automated message from the Apache Git Service.
To respond to the message, please log on to GitHub and use the
URL above to go to the specific comment.
To unsubscribe, e-mail: [email protected]
For queries about this service, please contact Infrastructure at:
[email protected]
---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]
