gaborgsomogyi commented on issue #24738: [WIP][SPARK-23098][SQL] Migrate Kafka Batch source to v2. URL: https://github.com/apache/spark/pull/24738#issuecomment-503147770 @rdblue @HeartSaVioR what bothered me is the question how Structured Streaming works so I've had a deeper look. Since Kafka has a fixed schema Structured Streaming is not validating it inside the SQL analyzer but in [KafkaWriter.validateQuery](https://github.com/apache/spark/blob/ed280c23ca396087fc62d5a6412179f6a0103245/external/kafka-0-10-sql/src/main/scala/org/apache/spark/sql/kafka010/KafkaWriter.scala#L45). When a required field is missing then an exception will be thrown and the query won't be started: ``` Required attribute 'value' not found; org.apache.spark.sql.AnalysisException: Required attribute 'value' not found; at org.apache.spark.sql.kafka010.KafkaWriter$.$anonfun$validateQuery$6(KafkaWriter.scala:71) at scala.Option.getOrElse(Option.scala:138) at org.apache.spark.sql.kafka010.KafkaWriter$.validateQuery(KafkaWriter.scala:71) at org.apache.spark.sql.kafka010.KafkaBatchWrite.<init>(KafkaBatchWrite.scala:42) at org.apache.spark.sql.kafka010.KafkaSourceProvider$KafkaTable$$anon$2.buildForBatch(KafkaSourceProvider.scala:383) at org.apache.spark.sql.execution.datasources.v2.AppendDataExec.doExecute(WriteToDataSourceV2Exec.scala:112) at org.apache.spark.sql.execution.SparkPlan.$anonfun$execute$1(SparkPlan.scala:137) at org.apache.spark.sql.execution.SparkPlan.$anonfun$executeQuery$1(SparkPlan.scala:161) at org.apache.spark.rdd.RDDOperationScope$.withScope(RDDOperationScope.scala:151) at org.apache.spark.sql.execution.SparkPlan.executeQuery(SparkPlan.scala:158) at org.apache.spark.sql.execution.SparkPlan.execute(SparkPlan.scala:133) at org.apache.spark.sql.execution.QueryExecution.toRdd$lzycompute(QueryExecution.scala:98) at org.apache.spark.sql.execution.QueryExecution.toRdd(QueryExecution.scala:98) at org.apache.spark.sql.DataFrameWriter.$anonfun$runCommand$1(DataFrameWriter.scala:729) at org.apache.spark.sql.execution.SQLExecution$.$anonfun$withNewExecutionId$4(SQLExecution.scala:100) at org.apache.spark.sql.execution.SQLExecution$.withSQLConfPropagated(SQLExecution.scala:160) at org.apache.spark.sql.execution.SQLExecution$.withNewExecutionId(SQLExecution.scala:87) at org.apache.spark.sql.DataFrameWriter.runCommand(DataFrameWriter.scala:729) at org.apache.spark.sql.DataFrameWriter.save(DataFrameWriter.scala:301) at org.apache.spark.sql.kafka010.KafkaSinkBatchSuiteBase.$anonfun$new$28(KafkaSinkSuite.scala:367) at scala.runtime.java8.JFunction0$mcV$sp.apply(JFunction0$mcV$sp.java:23) at org.scalatest.OutcomeOf.outcomeOf(OutcomeOf.scala:85) at org.scalatest.OutcomeOf.outcomeOf$(OutcomeOf.scala:83) at org.scalatest.OutcomeOf$.outcomeOf(OutcomeOf.scala:104) at org.scalatest.Transformer.apply(Transformer.scala:22) at org.scalatest.Transformer.apply(Transformer.scala:20) at org.scalatest.FunSuiteLike$$anon$1.apply(FunSuiteLike.scala:186) at org.apache.spark.SparkFunSuite.withFixture(SparkFunSuite.scala:149) at org.scalatest.FunSuiteLike.invokeWithFixture$1(FunSuiteLike.scala:184) at org.scalatest.FunSuiteLike.$anonfun$runTest$1(FunSuiteLike.scala:196) at org.scalatest.SuperEngine.runTestImpl(Engine.scala:289) at org.scalatest.FunSuiteLike.runTest(FunSuiteLike.scala:196) at org.scalatest.FunSuiteLike.runTest$(FunSuiteLike.scala:178) at org.apache.spark.SparkFunSuite.org$scalatest$BeforeAndAfterEach$$super$runTest(SparkFunSuite.scala:56) at org.scalatest.BeforeAndAfterEach.runTest(BeforeAndAfterEach.scala:221) at org.scalatest.BeforeAndAfterEach.runTest$(BeforeAndAfterEach.scala:214) at org.apache.spark.SparkFunSuite.runTest(SparkFunSuite.scala:56) at org.scalatest.FunSuiteLike.$anonfun$runTests$1(FunSuiteLike.scala:229) at org.scalatest.SuperEngine.$anonfun$runTestsInBranch$1(Engine.scala:396) at scala.collection.immutable.List.foreach(List.scala:392) at org.scalatest.SuperEngine.traverseSubNodes$1(Engine.scala:384) at org.scalatest.SuperEngine.runTestsInBranch(Engine.scala:379) at org.scalatest.SuperEngine.runTestsImpl(Engine.scala:461) at org.scalatest.FunSuiteLike.runTests(FunSuiteLike.scala:229) at org.scalatest.FunSuiteLike.runTests$(FunSuiteLike.scala:228) at org.scalatest.FunSuite.runTests(FunSuite.scala:1560) at org.scalatest.Suite.run(Suite.scala:1147) at org.scalatest.Suite.run$(Suite.scala:1129) at org.scalatest.FunSuite.org$scalatest$FunSuiteLike$$super$run(FunSuite.scala:1560) at org.scalatest.FunSuiteLike.$anonfun$run$1(FunSuiteLike.scala:233) at org.scalatest.SuperEngine.runImpl(Engine.scala:521) at org.scalatest.FunSuiteLike.run(FunSuiteLike.scala:233) at org.scalatest.FunSuiteLike.run$(FunSuiteLike.scala:232) at org.apache.spark.SparkFunSuite.org$scalatest$BeforeAndAfterAll$$super$run(SparkFunSuite.scala:56) at org.scalatest.BeforeAndAfterAll.liftedTree1$1(BeforeAndAfterAll.scala:213) at org.scalatest.BeforeAndAfterAll.run(BeforeAndAfterAll.scala:210) at org.scalatest.BeforeAndAfterAll.run$(BeforeAndAfterAll.scala:208) at org.apache.spark.SparkFunSuite.run(SparkFunSuite.scala:56) at org.scalatest.tools.SuiteRunner.run(SuiteRunner.scala:45) at org.scalatest.tools.Runner$.$anonfun$doRunRunRunDaDoRunRun$13(Runner.scala:1346) at org.scalatest.tools.Runner$.$anonfun$doRunRunRunDaDoRunRun$13$adapted(Runner.scala:1340) at scala.collection.immutable.List.foreach(List.scala:392) at org.scalatest.tools.Runner$.doRunRunRunDaDoRunRun(Runner.scala:1340) at org.scalatest.tools.Runner$.$anonfun$runOptionallyWithPassFailReporter$24(Runner.scala:1031) at org.scalatest.tools.Runner$.$anonfun$runOptionallyWithPassFailReporter$24$adapted(Runner.scala:1010) at org.scalatest.tools.Runner$.withClassLoaderAndDispatchReporter(Runner.scala:1506) at org.scalatest.tools.Runner$.runOptionallyWithPassFailReporter(Runner.scala:1010) at org.scalatest.tools.Runner$.run(Runner.scala:850) at org.scalatest.tools.Runner.run(Runner.scala) at org.jetbrains.plugins.scala.testingSupport.scalaTest.ScalaTestRunner.runScalaTest2(ScalaTestRunner.java:131) at org.jetbrains.plugins.scala.testingSupport.scalaTest.ScalaTestRunner.main(ScalaTestRunner.java:28) ``` I think the same has to be applied to the batch part.
---------------------------------------------------------------- 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]
