feat: Add aggregate expression fuzz testing in CI #1374
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
| Original file line number | Diff line number | Diff line change |
|---|---|---|
| @@ -0,0 +1,165 @@ | ||
| /* | ||
| * 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 | ||
|
|
||
| import scala.util.Random | ||
|
|
||
| import org.apache.hadoop.fs.Path | ||
| import org.apache.spark.sql.CometTestBase | ||
| import org.apache.spark.sql.execution.adaptive.AdaptiveSparkPlanHelper | ||
| import org.apache.spark.sql.types._ | ||
|
|
||
| import org.apache.comet.testing.{DataGenOptions, ParquetGenerator} | ||
|
|
||
| class CometFuzzTestSuite extends CometTestBase with AdaptiveSparkPlanHelper { | ||
|
|
||
| private val fuzzTestEnabled: Boolean = sys.env.contains("COMET_FUZZ_TEST") | ||
|
|
||
| test("aggregates") { | ||
| assume(fuzzTestEnabled) | ||
| withTempDir { dir => | ||
| val path = new Path(dir.toURI.toString, "test.parquet") | ||
| val filename = path.toString | ||
| val random = new Random(42) | ||
| withSQLConf(CometConf.COMET_ENABLED.key -> "false") { | ||
| ParquetGenerator.makeParquetFile(random, spark, filename, 10000, DataGenOptions()) | ||
| } | ||
| val table = spark.read.parquet(filename).coalesce(1) | ||
| table.createOrReplaceTempView("t1") | ||
|
|
||
| val groupingFields: Array[StructField] = table.schema.fields.filterNot(isNumeric) | ||
|
|
||
| // test grouping by each non-numeric column, grouping by all non-numeric columns, and no grouping | ||
| val groupByIndividualCols: Seq[Seq[String]] = groupingFields.map(f => Seq(f.name)).toSeq | ||
| val groupByAllCols: Seq[Seq[String]] = Seq(groupingFields.map(_.name).toSeq) | ||
| val noGroup: Seq[Seq[String]] = Seq(Seq.empty) | ||
| val groupings: Seq[Seq[String]] = groupByIndividualCols ++ groupByAllCols ++ noGroup | ||
|
|
||
| val scanTypes = Seq( | ||
| CometConf.SCAN_NATIVE_COMET | ||
| /*CometConf.SCAN_NATIVE_DATAFUSION, | ||
| CometConf.SCAN_NATIVE_ICEBERG_COMPAT*/ ) | ||
|
|
||
| for (scan <- scanTypes) { | ||
| for (shuffleMode <- Seq("auto", "jvm", "native")) { | ||
| withSQLConf( | ||
| CometConf.COMET_NATIVE_SCAN_IMPL.key -> scan, | ||
| CometConf.COMET_SHUFFLE_MODE.key -> shuffleMode) { | ||
| for (group <- groupings) { | ||
| for (agg <- Exprs.aggregate) { | ||
|
|
||
| // pick all compatible columns for all input args | ||
| val argFields: Seq[Array[StructField]] = agg.args.map(argType => | ||
| table.schema.fields.filter(f => isMatch(f.dataType, argType))) | ||
|
|
||
| // just pick the first compatible column for each type for now, but should randomize this or | ||
| // test all combinations | ||
| val args: Seq[StructField] = argFields.map(_.head) | ||
|
|
||
| if (agg.name == "_avg" && args.head.dataType.isInstanceOf[DecimalType]) { | ||
| // skip known issue | ||
| } else { | ||
|
|
||
| val aggSql = s"${agg.name}(${args.map(_.name).mkString(",")})" | ||
|
|
||
| val sql = if (group.isEmpty) { | ||
| s"SELECT $aggSql FROM t1" | ||
| } else { | ||
| val groupCols = group.mkString(", ") | ||
| s"SELECT $groupCols, $aggSql FROM t1 GROUP BY $groupCols ORDER BY $groupCols" | ||
| } | ||
| println(sql) | ||
| checkSparkAnswerWithTol(sql) | ||
| // TODO check operators | ||
| } | ||
| } | ||
| } | ||
| } | ||
| } | ||
| } | ||
| } | ||
| } | ||
|
|
||
| private def isNumeric(field: StructField) = { | ||
| field.dataType match { | ||
| case _: ByteType | _: ShortType | _: IntegerType | _: LongType => true | ||
| case _: FloatType | _: DoubleType => true | ||
| case _: DecimalType => true | ||
| case _ => false | ||
| } | ||
| } | ||
|
|
||
| def isMatch(dt: DataType, at: ArgType): Boolean = { | ||
| at match { | ||
| case AnyType => true | ||
| case NumericType => | ||
| dt match { | ||
| case _: ByteType | _: ShortType | _: IntegerType | _: LongType => true | ||
| case _: FloatType | _: DoubleType => true | ||
| case _: DecimalType => true | ||
| case _ => false | ||
| } | ||
| case OrderedTypes => | ||
| // TODO exclude map or other complex types that contain maps | ||
| true | ||
| case _ => false | ||
| } | ||
| } | ||
|
|
||
| } | ||
|
|
||
| object Exprs { | ||
|
|
||
| /** | ||
| * Aggregate expressions. Note that `first` and `last` are excluded because they are | ||
| * non-deterministic. | ||
| */ | ||
| val aggregate: Seq[ExprMeta] = Seq( | ||
| ExprMeta("min", Seq(OrderedTypes)), | ||
| ExprMeta("max", Seq(OrderedTypes)), | ||
| ExprMeta("count", Seq(AnyType)), | ||
| ExprMeta("sum", Seq(NumericType)), | ||
| ExprMeta("avg", Seq(NumericType)), | ||
| ExprMeta("median", Seq(NumericType)), | ||
| ExprMeta("stddev", Seq(NumericType)), | ||
| ExprMeta("stddev_pop", Seq(NumericType)), | ||
| ExprMeta("stddev_samp", Seq(NumericType)), | ||
| ExprMeta("variance", Seq(NumericType)), | ||
| ExprMeta("var_pop", Seq(NumericType)), | ||
| ExprMeta("var_samp", Seq(NumericType)), | ||
| ExprMeta("corr", Seq(NumericType, NumericType)), | ||
| ExprMeta("covar_pop", Seq(NumericType, NumericType)), | ||
| ExprMeta("covar_samp", Seq(NumericType, NumericType))) | ||
| } | ||
|
|
||
| /** Meta-data about a Spark expression */ | ||
| case class ExprMeta(name: String, args: Seq[ArgType]) | ||
|
|
||
| /** Represents that data type(s) that an argument accepts */ | ||
| sealed trait ArgType | ||
|
|
||
| /** Supports any input type */ | ||
| case object AnyType extends ArgType | ||
|
|
||
| /** Integral, floating-point, and decimal */ | ||
| case object NumericType extends ArgType | ||
|
|
||
| /** Types that can ordered. Includes struct and array but excludes maps */ | ||
| case object OrderedTypes extends ArgType | ||
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
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.
Do we plan to have these scan implementations also added to the fuzz testing at some point?
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.
Yes. These are commented out for now because they fail due to timestamp issues.