viirya commented on a change in pull request #23943: [SPARK-27034][SQL] Nested schema pruning for ORC URL: https://github.com/apache/spark/pull/23943#discussion_r263265164
########## File path: sql/core/src/test/scala/org/apache/spark/sql/execution/datasources/SchemaPruningSuite.scala ########## @@ -0,0 +1,350 @@ +/* + * 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.execution.datasources + +import java.io.File + +import org.scalactic.Equality + +import org.apache.spark.sql.{DataFrame, QueryTest, Row} +import org.apache.spark.sql.catalyst.SchemaPruningTest +import org.apache.spark.sql.catalyst.parser.CatalystSqlParser +import org.apache.spark.sql.execution.FileSourceScanExec +import org.apache.spark.sql.functions._ +import org.apache.spark.sql.internal.SQLConf +import org.apache.spark.sql.test.SharedSQLContext +import org.apache.spark.sql.types.StructType + +abstract class SchemaPruningSuite + extends QueryTest + with FileBasedDataSourceTest + with SchemaPruningTest + with SharedSQLContext { + case class FullName(first: String, middle: String, last: String) + case class Company(name: String, address: String) + case class Employer(id: Int, company: Company) + case class Contact( + id: Int, + name: FullName, + address: String, + pets: Int, + friends: Array[FullName] = Array.empty, + relatives: Map[String, FullName] = Map.empty, + employer: Employer = null) + + val janeDoe = FullName("Jane", "X.", "Doe") + val johnDoe = FullName("John", "Y.", "Doe") + val susanSmith = FullName("Susan", "Z.", "Smith") + + val employer = Employer(0, Company("abc", "123 Business Street")) + val employerWithNullCompany = Employer(1, null) + + val contacts = + Contact(0, janeDoe, "123 Main Street", 1, friends = Array(susanSmith), + relatives = Map("brother" -> johnDoe), employer = employer) :: + Contact(1, johnDoe, "321 Wall Street", 3, relatives = Map("sister" -> janeDoe), + employer = employerWithNullCompany) :: Nil + + case class Name(first: String, last: String) + case class BriefContact(id: Int, name: Name, address: String) + + private val briefContacts = + BriefContact(2, Name("Janet", "Jones"), "567 Maple Drive") :: + BriefContact(3, Name("Jim", "Jones"), "6242 Ash Street") :: Nil + + case class ContactWithDataPartitionColumn( + id: Int, + name: FullName, + address: String, + pets: Int, + friends: Array[FullName] = Array(), + relatives: Map[String, FullName] = Map(), + employer: Employer = null, + p: Int) + + case class BriefContactWithDataPartitionColumn(id: Int, name: Name, address: String, p: Int) + + val contactsWithDataPartitionColumn = + contacts.map { case Contact(id, name, address, pets, friends, relatives, employer) => + ContactWithDataPartitionColumn(id, name, address, pets, friends, relatives, employer, 1) } + val briefContactsWithDataPartitionColumn = + briefContacts.map { case BriefContact(id, name, address) => + BriefContactWithDataPartitionColumn(id, name, address, 2) } + + testSchemaPruning("select a single complex field array and its parent struct array") { Review comment: Yes, we should be able to use all same tests between Parquet and ORC once user specified schema works. ---------------------------------------------------------------- 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. For queries about this service, please contact Infrastructure at: [email protected] With regards, Apache Git Services --------------------------------------------------------------------- To unsubscribe, e-mail: [email protected] For additional commands, e-mail: [email protected]
