viirya commented on a change in pull request #33077: URL: https://github.com/apache/spark/pull/33077#discussion_r669319633
########## File path: sql/core/src/test/scala/org/apache/spark/sql/execution/streaming/MergingSortWithSessionWindowStateIteratorSuite.scala ########## @@ -0,0 +1,231 @@ +/* + * 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.streaming + +import java.util.UUID + +import org.apache.hadoop.conf.Configuration +import org.scalatest.BeforeAndAfter + +import org.apache.spark.sql.SparkSession +import org.apache.spark.sql.catalyst.expressions.{GenericInternalRow, UnsafeProjection, UnsafeRow} +import org.apache.spark.sql.execution.streaming.state.{HDFSBackedStateStoreProvider, RocksDBStateStoreProvider, StateStore, StateStoreConf, StateStoreId, StateStoreProviderId, StreamingSessionWindowStateManager} +import org.apache.spark.sql.internal.SQLConf +import org.apache.spark.sql.streaming.StreamTest +import org.apache.spark.sql.types.{IntegerType, LongType, StringType, StructType} +import org.apache.spark.unsafe.types.UTF8String + +class MergingSortWithSessionWindowStateIteratorSuite extends StreamTest with BeforeAndAfter { + + private val rowSchema = new StructType().add("key1", StringType).add("key2", IntegerType) + .add("session", new StructType().add("start", LongType).add("end", LongType)) + .add("value", LongType) + private val rowAttributes = rowSchema.toAttributes + + private val keysWithoutSessionAttributes = rowAttributes.filter { attr => + List("key1", "key2").contains(attr.name) + } + + private val sessionAttribute = rowAttributes.filter(_.name == "session").head + + private val inputValueGen = UnsafeProjection.create(rowAttributes.map(_.dataType).toArray) + private val inputKeyGen = UnsafeProjection.create( + keysWithoutSessionAttributes.map(_.dataType).toArray) + + before { + SparkSession.setActiveSession(spark) + spark.streams.stateStoreCoordinator // initialize the lazy coordinator + } + + private val providerOptions = Seq( + classOf[HDFSBackedStateStoreProvider].getCanonicalName, + classOf[RocksDBStateStoreProvider].getCanonicalName).map { value => + (SQLConf.STATE_STORE_PROVIDER_CLASS.key, value.stripSuffix("$")) + } + + private val availableOptions = for ( + opt1 <- providerOptions; + opt2 <- StreamingSessionWindowStateManager.supportedVersions + ) yield (opt1, opt2) + + availableOptions.foreach { case (providerOpt, version) => + withSQLConf(providerOpt) { + test(s"StreamingSessionWindowStateManager " + + s"provider ${providerOpt._2} state version v${version} - rows only in state") { + testRowsOnlyInState(version) + } + + test(s"StreamingSessionWindowStateManager " + + s"provider ${providerOpt._2} state version v${version} - rows in both input and state") { + testRowsInBothInputAndState(version) + } + + test(s"StreamingSessionWindowStateManager " + + s"provider ${providerOpt._2} state version v${version} - rows only in input") { + testRowsOnlyInInput(version) + } + } + } + + private def testRowsOnlyInState(stateFormatVersion: Int): Unit = { + withStateManager(stateFormatVersion) { case (stateManager, store) => + val key = createKeyRow("a", 1) + val values = Seq( + createRow("a", 1, 100, 110, 1), + createRow("a", 1, 120, 130, 2), + createRow("a", 1, 140, 150, 3)) + + stateManager.updateSessions(store, key, values) + + val iter = new MergingSortWithSessionWindowStateIterator( + Iterator.empty, + stateManager, + store, + keysWithoutSessionAttributes, + sessionAttribute, + rowAttributes) + + val actual = iter.map(_.copy()).toList + assert(actual.isEmpty) Review comment: Hm? Why it is empty? If input is empty, doesn't it output sorted sessions in the state? -- 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: [email protected] For queries about this service, please contact Infrastructure at: [email protected] --------------------------------------------------------------------- To unsubscribe, e-mail: [email protected] For additional commands, e-mail: [email protected]
