build: Add spark-4.0 profile and shims #407
There are no files selected for viewing
This file contains 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 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 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 +1,81 @@ | ||
| /* | ||
| * 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.shims | ||
|
|
||
| import org.apache.spark.sql.types._ | ||
|
|
||
| trait ShimCometParquetUtils { | ||
| // The following is copied from QueryExecutionErrors | ||
| // TODO: remove after dropping Spark 3.2.0 support and directly use | ||
| // QueryExecutionErrors.foundDuplicateFieldInFieldIdLookupModeError | ||
| def foundDuplicateFieldInFieldIdLookupModeError( | ||
| requiredId: Int, | ||
| matchedFields: String): Throwable = { | ||
| new RuntimeException(s""" | ||
| |Found duplicate field(s) "$requiredId": $matchedFields | ||
| |in id mapping mode | ||
| """.stripMargin.replaceAll("\n", " ")) | ||
| } | ||
|
|
||
| // The followings are copied from org.apache.spark.sql.execution.datasources.parquet.ParquetUtils | ||
| // TODO: remove after dropping Spark 3.2.0 support and directly use ParquetUtils | ||
| /** | ||
| * A StructField metadata key used to set the field id of a column in the Parquet schema. | ||
| */ | ||
| val FIELD_ID_METADATA_KEY = "parquet.field.id" | ||
|
|
||
| /** | ||
| * Whether there exists a field in the schema, whether inner or leaf, has the parquet field ID | ||
| * metadata. | ||
| */ | ||
| def hasFieldIds(schema: StructType): Boolean = { | ||
| def recursiveCheck(schema: DataType): Boolean = { | ||
| schema match { | ||
| case st: StructType => | ||
| st.exists(field => hasFieldId(field) || recursiveCheck(field.dataType)) | ||
|
|
||
| case at: ArrayType => recursiveCheck(at.elementType) | ||
|
|
||
| case mt: MapType => recursiveCheck(mt.keyType) || recursiveCheck(mt.valueType) | ||
|
|
||
| case _ => | ||
| // No need to really check primitive types, just to terminate the recursion | ||
| false | ||
| } | ||
| } | ||
| if (schema.isEmpty) false else recursiveCheck(schema) | ||
| } | ||
|
|
||
| def hasFieldId(field: StructField): Boolean = | ||
| field.metadata.contains(FIELD_ID_METADATA_KEY) | ||
|
|
||
| def getFieldId(field: StructField): Int = { | ||
| require( | ||
| hasFieldId(field), | ||
| s"The key `$FIELD_ID_METADATA_KEY` doesn't exist in the metadata of " + field) | ||
| try { | ||
| Math.toIntExact(field.metadata.getLong(FIELD_ID_METADATA_KEY)) | ||
| } catch { | ||
| case _: ArithmeticException | _: ClassCastException => | ||
| throw new IllegalArgumentException( | ||
| s"The key `$FIELD_ID_METADATA_KEY` must be a 32-bit integer") | ||
| } | ||
| } | ||
| } |
This file contains 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 +1,37 @@ | ||
| /* | ||
| * 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.comet.shims | ||
|
|
||
| import org.apache.spark.paths.SparkPath | ||
| import org.apache.spark.sql.catalyst.InternalRow | ||
| import org.apache.spark.sql.execution.datasources.PartitionedFile | ||
|
|
||
| object ShimBatchReader { | ||
| def newPartitionedFile(partitionValues: InternalRow, file: String): PartitionedFile = | ||
| PartitionedFile( | ||
| partitionValues, | ||
| SparkPath.fromUrlString(file), | ||
| -1, // -1 means we read the entire file | ||
| -1, | ||
kazuyukitanimura marked this conversation as resolved.
Show resolved
Hide resolved
|
||
| Array.empty[String], | ||
| 0, | ||
| 0 | ||
| ) | ||
| } | ||
This file contains 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 +1,33 @@ | ||
| /* | ||
| * 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.comet.shims | ||
|
|
||
| import org.apache.spark.sql.execution.datasources.FileFormat | ||
| import org.apache.spark.sql.execution.datasources.parquet.ParquetFileFormat | ||
|
|
||
| object ShimFileFormat { | ||
| val ROW_INDEX = ParquetFileFormat.ROW_INDEX | ||
|
|
||
| // A name for a temporary column that holds row indexes computed by the file format reader | ||
| // until they can be placed in the _metadata struct. | ||
| val ROW_INDEX_TEMPORARY_COLUMN_NAME = ParquetFileFormat.ROW_INDEX_TEMPORARY_COLUMN_NAME | ||
|
|
||
| val OPTION_RETURNING_BATCH = FileFormat.OPTION_RETURNING_BATCH | ||
kazuyukitanimura marked this conversation as resolved.
Show resolved
Hide resolved
|
||
| } | ||
Oops, something went wrong.
Oops, something went wrong.
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.
Is it necessary to run rust test for Spark 4.0 separately? It should be no difference with 3.4 or 3.3/3.2.
We also don't run rust test for Spark 3.3/3.2 but only for Spark 3.4.
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.
removed