viirya commented on code in PR #472: URL: https://github.com/apache/datafusion-comet/pull/472#discussion_r1622870392
########## fuzz-testing/src/main/scala/org/apache/comet/fuzz/QueryGen.scala: ########## @@ -0,0 +1,121 @@ +/* + * 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.fuzz + +import java.io.{BufferedWriter, FileWriter} + +import scala.collection.mutable +import scala.util.Random + +import org.apache.spark.sql.SparkSession + +object QueryGen { + + def generateRandomQueries( + r: Random, + spark: SparkSession, + numFiles: Int, + numQueries: Int): Unit = { + for (i <- 0 until numFiles) { + spark.read.parquet(s"test$i.parquet").createTempView(s"test$i") + } + + val w = new BufferedWriter(new FileWriter("queries.sql")) + + val uniqueQueries = mutable.HashSet[String]() + + for (_ <- 0 until numQueries) { + val sql = r.nextInt().abs % 3 match { + case 0 => generateJoin(r, spark, numFiles) + case 1 => generateAggregate(r, spark, numFiles) + case 2 => generateScalar(r, spark, numFiles) + } + if (!uniqueQueries.contains(sql)) { + uniqueQueries += sql + w.write(sql + "\n") + } + } + w.close() + } + + private def generateAggregate(r: Random, spark: SparkSession, numFiles: Int): String = { + val tableName = s"test${r.nextInt(numFiles)}" + val table = spark.table(tableName) + + val func = Utils.randomChoice(Meta.aggFunc, r) + val args = Range(0, func.num_args) + .map(_ => Utils.randomChoice(table.columns, r)) + + val groupingCols = Range(0, 2).map(_ => Utils.randomChoice(table.columns, r)) Review Comment: Do we need to exclude gouping columns from aggregation function arguments? -- 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: github-unsubscr...@datafusion.apache.org For queries about this service, please contact Infrastructure at: us...@infra.apache.org --------------------------------------------------------------------- To unsubscribe, e-mail: github-unsubscr...@datafusion.apache.org For additional commands, e-mail: github-h...@datafusion.apache.org
