Repository navigation
fix: preserve runtime fields when copying file scan filters #7508
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.
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
Open
danielwei816
wants to merge
6
commits into
apache:main
Choose a base branch
from
danielwei816:codex/fix-scan-copy-emr
base: main
Could not load branches
Branch not found: {{ refName }}
Loading
Could not load tags
Nothing to show
Loading
Are you sure you want to change the base?
Some commits from the old base branch may be removed from the timeline,
and old review comments may become outdated.
Open
Changes from all commits
Commits
Show all changes
6 commits
Select commit
Hold shift + click to select a range
2d0c863
fix: preserve runtime fields when copying file scan filters
danielwei816 2986a9f
fix: handle Spark 3 and 4 scan constructor layouts
danielwei816 c05f349
fix: preserve runtime scan fields during make_date fallback
danielwei816 759231a
test: verify runtime scan fields survive canonicalization
danielwei816 ea4a9d8
ci: trigger fork checks
danielwei816 3bf5df9
fix: rely on Spark to preserve scan logical links
danielwei816 File filter
Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
There are no files selected for viewing
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
86 changes: 86 additions & 0 deletions
86
spark/src/test/spark-3.x/org/apache/spark/sql/comet/ExtendedFileSourceScanExec.scala
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| Original file line number | Diff line number | Diff line change |
|---|---|---|
| @@ -0,0 +1,86 @@ | ||
| /* | ||
| * 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.comet | ||
|
|
||
| import org.apache.spark.sql.catalyst.TableIdentifier | ||
| import org.apache.spark.sql.catalyst.expressions.{Attribute, Expression} | ||
| import org.apache.spark.sql.execution.FileSourceScanExec | ||
| import org.apache.spark.sql.execution.datasources.HadoopFsRelation | ||
| import org.apache.spark.sql.types.{IntegerType, StructType} | ||
| import org.apache.spark.util.collection.BitSet | ||
|
|
||
| private[apache] object ExtendedFileSourceScanExec { | ||
| def apply( | ||
| output: Seq[Attribute], | ||
| partitionFilters: Seq[Expression] = Nil, | ||
| dataFilters: Seq[Expression] = Nil): FileSourceScanExec = { | ||
| new ExtendedFileSourceScanExec( | ||
| null, | ||
| output, | ||
| new StructType().add("id", IntegerType), | ||
| partitionFilters, | ||
| None, | ||
| None, | ||
| dataFilters, | ||
| Some(TableIdentifier("test")), | ||
| true, | ||
| true, | ||
| output) | ||
| } | ||
| } | ||
|
|
||
| // Model a distribution that adds scan fields. An inherited case-class copy would discard them. | ||
| private[apache] class ExtendedFileSourceScanExec( | ||
| relation: HadoopFsRelation, | ||
| output: Seq[Attribute], | ||
| requiredSchema: StructType, | ||
| partitionFilters: Seq[Expression], | ||
| optionalBucketSet: Option[BitSet], | ||
| optionalNumCoalescedBuckets: Option[Int], | ||
| dataFilters: Seq[Expression], | ||
| tableIdentifier: Option[TableIdentifier], | ||
| disableBucketedScan: Boolean, | ||
| val vendorFlag: Boolean, | ||
| val vendorOutput: Seq[Attribute]) | ||
| extends FileSourceScanExec( | ||
| relation, | ||
| output, | ||
| requiredSchema, | ||
| partitionFilters, | ||
| optionalBucketSet, | ||
| optionalNumCoalescedBuckets, | ||
| dataFilters, | ||
| tableIdentifier, | ||
| disableBucketedScan) { | ||
| override def doCanonicalize(): FileSourceScanExec = { | ||
| // Keep the simulated vendor fields observable after Spark normalizes its own fields. | ||
| val args = super.doCanonicalize().productIterator.map(_.asInstanceOf[AnyRef]).toArray | ||
| makeCopy(args ++ Array[AnyRef](Boolean.box(vendorFlag), vendorOutput)) | ||
| .asInstanceOf[FileSourceScanExec] | ||
| } | ||
|
|
||
| override def productArity: Int = 11 | ||
|
|
||
| override def productElement(index: Int): Any = index match { | ||
| case 9 => vendorFlag | ||
| case 10 => vendorOutput | ||
| case _ => super.productElement(index) | ||
| } | ||
| } |
90 changes: 90 additions & 0 deletions
90
spark/src/test/spark-4.x/org/apache/spark/sql/comet/ExtendedFileSourceScanExec.scala
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| Original file line number | Diff line number | Diff line change |
|---|---|---|
| @@ -0,0 +1,90 @@ | ||
| /* | ||
| * 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.comet | ||
|
|
||
| import org.apache.spark.sql.catalyst.TableIdentifier | ||
| import org.apache.spark.sql.catalyst.expressions.{Attribute, Expression} | ||
| import org.apache.spark.sql.connector.read.streaming.SparkDataStream | ||
| import org.apache.spark.sql.execution.FileSourceScanExec | ||
| import org.apache.spark.sql.execution.datasources.HadoopFsRelation | ||
| import org.apache.spark.sql.types.{IntegerType, StructType} | ||
| import org.apache.spark.util.collection.BitSet | ||
|
|
||
| private[apache] object ExtendedFileSourceScanExec { | ||
| def apply( | ||
| output: Seq[Attribute], | ||
| partitionFilters: Seq[Expression] = Nil, | ||
| dataFilters: Seq[Expression] = Nil): FileSourceScanExec = { | ||
| new ExtendedFileSourceScanExec( | ||
| null, | ||
| None, | ||
| output, | ||
| new StructType().add("id", IntegerType), | ||
| partitionFilters, | ||
| None, | ||
| None, | ||
| dataFilters, | ||
| Some(TableIdentifier("test")), | ||
| true, | ||
| true, | ||
| output) | ||
| } | ||
| } | ||
|
|
||
| // Model a distribution that adds scan fields. An inherited case-class copy would discard them. | ||
| private[apache] class ExtendedFileSourceScanExec( | ||
| relation: HadoopFsRelation, | ||
| stream: Option[SparkDataStream], | ||
| output: Seq[Attribute], | ||
| requiredSchema: StructType, | ||
| partitionFilters: Seq[Expression], | ||
| optionalBucketSet: Option[BitSet], | ||
| optionalNumCoalescedBuckets: Option[Int], | ||
| dataFilters: Seq[Expression], | ||
| tableIdentifier: Option[TableIdentifier], | ||
| disableBucketedScan: Boolean, | ||
| val vendorFlag: Boolean, | ||
| val vendorOutput: Seq[Attribute]) | ||
| extends FileSourceScanExec( | ||
| relation, | ||
| stream, | ||
| output, | ||
| requiredSchema, | ||
| partitionFilters, | ||
| optionalBucketSet, | ||
| optionalNumCoalescedBuckets, | ||
| dataFilters, | ||
| tableIdentifier, | ||
| disableBucketedScan) { | ||
| override def doCanonicalize(): FileSourceScanExec = { | ||
| // Keep the simulated vendor fields observable after Spark normalizes its own fields. | ||
| val args = super.doCanonicalize().productIterator.map(_.asInstanceOf[AnyRef]).toArray | ||
| makeCopy(args ++ Array[AnyRef](Boolean.box(vendorFlag), vendorOutput)) | ||
| .asInstanceOf[FileSourceScanExec] | ||
| } | ||
|
|
||
| override def productArity: Int = 12 | ||
|
|
||
| override def productElement(index: Int): Any = index match { | ||
| case 10 => vendorFlag | ||
| case 11 => vendorOutput | ||
| case _ => super.productElement(index) | ||
| } | ||
| } |
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
We should probably have handled this in the shim layer
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
I will create follow on PR