Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Jump to bottom

Fix spark400 build due to LogicalRelation signature changes [databricks] #11695

Merged
merged 1 commit into from
Nov 6, 2024
Merged

Fix spark400 build due to LogicalRelation signature changes [databricks] #11695

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
38 changes: 38 additions & 0 deletions sql-plugin/src/main/spark332db/scala/com/nvidia/spark/rapids/shims/LogicalPlanShims.scala
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -0,0 +1,38 @@
/*
* Copyright (c) 2024, NVIDIA CORPORATION.
*
* Licensed 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.
*/

/*** spark-rapids-shim-json-lines
{"spark": "332db"}
{"spark": "340"}
{"spark": "341"}
{"spark": "341db"}
{"spark": "342"}
{"spark": "343"}
{"spark": "350"}
{"spark": "351"}
{"spark": "352"}
{"spark": "353"}
spark-rapids-shim-json-lines ***/
package com.nvidia.spark.rapids.shims

import org.apache.spark.sql.catalyst.plans.logical.LogicalPlan
import org.apache.spark.sql.execution.datasources.{FileIndex, HadoopFsRelation, LogicalRelation}

object LogicalPlanShims {
def getLocations(plan: LogicalPlan): Seq[FileIndex] = plan.collect {
case LogicalRelation(t: HadoopFsRelation, _, _, _) => t.location
}
}
5 changes: 2 additions & 3 deletions sql-plugin/src/main/spark332db/scala/org/apache/spark/sql/rapids/shims/GpuDataSource.scala
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -29,6 +29,7 @@
spark-rapids-shim-json-lines ***/
package org.apache.spark.sql.rapids

import com.nvidia.spark.rapids.shims.LogicalPlanShims
import org.apache.hadoop.fs.Path

import org.apache.spark.sql._
Expand Down Expand Up @@ -83,9 +84,7 @@ case class GpuDataSource(
PartitioningUtils.validatePartitionColumn(data.schema, partitionColumns, caseSensitive)

val fileIndex = catalogTable.map(_.identifier).map { tableIdent =>
sparkSession.table(tableIdent).queryExecution.analyzed.collect {
case LogicalRelation(t: HadoopFsRelation, _, _, _) => t.location
}.head
LogicalPlanShims.getLocations(sparkSession.table(tableIdent).queryExecution.analyzed).head
Comment on lines -86 to +87
Copy link
Collaborator

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

It is not a nice Scala but I recommend to future-proof and avoid small shim burden:

    val fileIndex = catalogTable.map(_.identifier).map { tableIdent =>
      sparkSession.table(tableIdent).queryExecution.analyzed.collect {
        case lr: LogicalRelation if lr.relation.isInstanceOf[HadoopFsRelation] => 
          lr.relation.asInstanceOf[HadoopFsRelation].location
      }.head
    }

Copy link
Member Author

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

I considered this at first, but I'm not sure this is "future-proof." I think we'd rather prefer to have the compiler and/or runtime inform us if a Spark platform changed this interface, since we may need to do more than just ignore the added parameters. In those cases Spark would have to change this corresponding code, and we would need to change it in a compatible way. Maybe that change is to ignore the added or removed parameters, maybe not.

}

// For partitioned relation r, r.schema's column ordering can be different from the column
Expand Down
29 changes: 29 additions & 0 deletions sql-plugin/src/main/spark400/scala/com/nvidia/spark/rapids/shims/LogicalPlanShims.scala
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -0,0 +1,29 @@
/*
* Copyright (c) 2024, NVIDIA CORPORATION.
*
* Licensed 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.
*/

/*** spark-rapids-shim-json-lines
{"spark": "400"}
spark-rapids-shim-json-lines ***/
package com.nvidia.spark.rapids.shims

import org.apache.spark.sql.catalyst.plans.logical.LogicalPlan
import org.apache.spark.sql.execution.datasources.{FileIndex, HadoopFsRelation, LogicalRelationWithTable}

object LogicalPlanShims {
def getLocations(plan: LogicalPlan): Seq[FileIndex] = plan.collect {
case LogicalRelationWithTable(t: HadoopFsRelation, _) => t.location
}
}