anishshri-db commented on code in PR #43425: URL: https://github.com/apache/spark/pull/43425#discussion_r1376951304
########## sql/core/src/test/scala/org/apache/spark/sql/execution/datasources/v2/state/StateDataSourceReadSuite.scala: ########## @@ -0,0 +1,670 @@ +/* + * 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.v2.state + +import java.io.{File, FileWriter} + +import org.scalatest.Assertions + +import org.apache.spark.io.CompressionCodec +import org.apache.spark.sql.{AnalysisException, DataFrame, Encoders, Row} +import org.apache.spark.sql.catalyst.expressions.{BoundReference, GenericInternalRow} +import org.apache.spark.sql.catalyst.plans.physical.HashPartitioning +import org.apache.spark.sql.execution.datasources.v2.state.utils.SchemaUtil +import org.apache.spark.sql.execution.streaming.{CommitLog, MemoryStream, OffsetSeqLog} +import org.apache.spark.sql.execution.streaming.state.{HDFSBackedStateStoreProvider, RocksDBStateStoreProvider, StateStore} +import org.apache.spark.sql.internal.SQLConf +import org.apache.spark.sql.streaming.OutputMode +import org.apache.spark.sql.types.{IntegerType, StructType} + +class StateDataSourceNegativeTestSuite extends StateDataSourceTestBase { + import testImplicits._ + + test("ERROR: read the state from stateless query") { + withTempDir { tempDir => + val inputData = MemoryStream[Int] + val df = inputData.toDF() + .selectExpr("value", "value % 2 AS value2") + + testStream(df)( + StartStream(checkpointLocation = tempDir.getAbsolutePath), + AddData(inputData, 1, 2, 3, 4, 5), + CheckLastBatch((1, 1), (2, 0), (3, 1), (4, 0), (5, 1)), + AddData(inputData, 6, 7, 8), + CheckLastBatch((6, 0), (7, 1), (8, 0)) + ) + + intercept[IllegalArgumentException] { + spark.read.format("statestore").load(tempDir.getAbsolutePath) + } + } + } + + test("ERROR: no committed batch on default batch ID") { + withTempDir { tempDir => + runLargeDataStreamingAggregationQuery(tempDir.getAbsolutePath) + + val offsetLog = new OffsetSeqLog(spark, + new File(tempDir.getAbsolutePath, "offsets").getAbsolutePath) + val commitLog = new CommitLog(spark, + new File(tempDir.getAbsolutePath, "commits").getAbsolutePath) + + offsetLog.purgeAfter(0) + commitLog.purgeAfter(-1) + + intercept[IllegalStateException] { + spark.read.format("statestore").load(tempDir.getAbsolutePath) + } + } + } + + test("ERROR: corrupted state schema file") { + withTempDir { tempDir => + runLargeDataStreamingAggregationQuery(tempDir.getAbsolutePath) + + def rewriteStateSchemaFileToDummy(): Unit = { + // Refer to the StateSchemaCompatibilityChecker for the path of state schema file + val pathForSchema = Seq( + "state", "0", StateStore.PARTITION_ID_TO_CHECK_SCHEMA.toString, + "_metadata", "schema" + ).foldLeft(tempDir) { case (file, dirName) => + new File(file, dirName) + } + + assert(pathForSchema.exists()) + assert(pathForSchema.delete()) + + val fileWriter = new FileWriter(pathForSchema) + fileWriter.write("lol dummy corrupted schema file") + fileWriter.close() + + assert(pathForSchema.exists()) + } + + rewriteStateSchemaFileToDummy() + + intercept[IllegalArgumentException] { + spark.read.format("statestore").load(tempDir.getAbsolutePath) + } + } + } + + test("ERROR: path is not specified") { + intercept[IllegalArgumentException] { + spark.read.format("statestore").load() + } + } + + test("ERROR: operator ID specified to negative") { + withTempDir { tempDir => + intercept[IllegalArgumentException] { + spark.read.format("statestore") + .option(StateDataSource.PARAM_OPERATOR_ID, -1) + // trick to bypass getting the last committed batch before validating operator ID + .option(StateDataSource.PARAM_BATCH_ID, 0) + .load(tempDir.getAbsolutePath) + } + } + } + + test("ERROR: batch ID specified to negative") { + withTempDir { tempDir => + intercept[IllegalArgumentException] { + spark.read.format("statestore") + .option(StateDataSource.PARAM_BATCH_ID, -1) + .load(tempDir.getAbsolutePath) + } + } + } + + test("ERROR: invalid value for joinSide option") { + withTempDir { tempDir => + intercept[IllegalArgumentException] { + spark.read.format("statestore") + .option(StateDataSource.PARAM_JOIN_SIDE, "both") + // trick to bypass getting the last committed batch before validating operator ID + .option(StateDataSource.PARAM_BATCH_ID, 0) + .load(tempDir.getAbsolutePath) + } + } + } + + test("ERROR: both options `joinSide` and `storeName` are specified") { + withTempDir { tempDir => + intercept[IllegalArgumentException] { + spark.read.format("statestore") + .option(StateDataSource.PARAM_JOIN_SIDE, "right") + .option(StateDataSource.PARAM_STORE_NAME, "right-keyToNumValues") + // trick to bypass getting the last committed batch before validating operator ID + .option(StateDataSource.PARAM_BATCH_ID, 0) + .load(tempDir.getAbsolutePath) + } + } + } +} + +class StateDataSourceSQLConfigSuite extends StateDataSourceTestBase { + // Here we build a combination of test criteria for Review Comment: Should we move up to class level comment ? -- 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: reviews-unsubscr...@spark.apache.org For queries about this service, please contact Infrastructure at: us...@infra.apache.org --------------------------------------------------------------------- To unsubscribe, e-mail: reviews-unsubscr...@spark.apache.org For additional commands, e-mail: reviews-h...@spark.apache.org
