rdblue commented on a change in pull request #24173: URL: https://github.com/apache/spark/pull/24173#discussion_r528891218
########## File path: sql/core/src/test/scala/org/apache/spark/sql/execution/streaming/state/StateSchemaCompatibilityCheckerSuite.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.spark.sql.execution.streaming.state + +import java.util.UUID + +import scala.util.Random + +import org.apache.hadoop.conf.Configuration + +import org.apache.spark.sql.execution.streaming.state.StateStoreTestsHelper.newDir +import org.apache.spark.sql.test.SharedSparkSession +import org.apache.spark.sql.types._ + +class StateSchemaCompatibilityCheckerSuite extends SharedSparkSession { + + testQuietly("changing schema of state when restarting query") { + val opId = Random.nextInt(100000) + val partitionId = -1 + + val hadoopConf: Configuration = new Configuration() + + def runSchemaChecker( + dir: String, + queryId: UUID, + newKeySchema: StructType, + newValueSchema: StructType): Unit = { + // in fact, Spark doesn't support online state schema change, so need to check + // schema only once for each running of JVM + val providerId = StateStoreProviderId( + StateStoreId(dir, opId, partitionId), queryId) + + new StateSchemaCompatibilityChecker(providerId, hadoopConf) + .check(newKeySchema, newValueSchema) + } + + def verifyException( + oldKeySchema: StructType, + oldValueSchema: StructType, + newKeySchema: StructType, + newValueSchema: StructType): Unit = { + val dir = newDir() + val queryId = UUID.randomUUID() + runSchemaChecker(dir, queryId, oldKeySchema, oldValueSchema) + + val e = intercept[StateSchemaNotCompatible] { + runSchemaChecker(dir, queryId, newKeySchema, newValueSchema) + } + + e.getMessage.contains("Provided schema doesn't match to the schema for existing state!") + e.getMessage.contains(newKeySchema.json) + e.getMessage.contains(newValueSchema.json) + e.getMessage.contains(oldKeySchema.json) + e.getMessage.contains(oldValueSchema.json) + } + + def verifySuccess( + oldKeySchema: StructType, + oldValueSchema: StructType, + newKeySchema: StructType, + newValueSchema: StructType): Unit = { + val dir = newDir() + val queryId = UUID.randomUUID() + runSchemaChecker(dir, queryId, oldKeySchema, oldValueSchema) + runSchemaChecker(dir, queryId, newKeySchema, newValueSchema) + } + + val keySchema = new StructType() + .add(StructField("key1", IntegerType, nullable = true)) + .add(StructField("key2", StringType, nullable = true)) + + val valueSchema = new StructType() + .add(StructField("value1", IntegerType, nullable = true)) + .add(StructField("value2", StringType, nullable = true)) + + // adding field should fail + val fieldAddedKeySchema = keySchema.add(StructField("newKey", IntegerType)) + val fieldAddedValueSchema = valueSchema.add(StructField("newValue", IntegerType)) + verifyException(keySchema, valueSchema, fieldAddedKeySchema, fieldAddedValueSchema) Review comment: I think that the changes to both key and value should be tested separately. If I understand correctly, then a change to either one is incompatible and should result in an error, but testing both at the same time could result in the failure for key when value is not checked or vice versa. ---------------------------------------------------------------- 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] --------------------------------------------------------------------- To unsubscribe, e-mail: [email protected] For additional commands, e-mail: [email protected]
