Details
-
Sub-task
-
Status: Resolved
-
Major
-
Resolution: Incomplete
-
2.4.0
-
None
Description
class SourcesTest extends SparkFunSuite { val spark = SparkSession.builder().master("local").getOrCreate() test("Test CREATE TABLE ... USING - v1") { spark.read.format(classOf[SimpleDataSourceV1].getCanonicalName).load() } test("Test DataFrameReader - v1") { spark.sql(s"CREATE TABLE tableA USING ${classOf[SimpleDataSourceV1].getCanonicalName}") } test("Test CREATE TABLE ... USING - v2") { spark.read.format(classOf[SimpleDataSourceV2].getCanonicalName).load() } test("Test DataFrameReader - v2") { spark.sql(s"CREATE TABLE tableB USING ${classOf[SimpleDataSourceV2].getCanonicalName}") } }
org.apache.spark.sql.sources.v2.SimpleDataSourceV2 is not a valid Spark SQL Data Source.; org.apache.spark.sql.AnalysisException: org.apache.spark.sql.sources.v2.SimpleDataSourceV2 is not a valid Spark SQL Data Source.; at org.apache.spark.sql.execution.datasources.DataSource.resolveRelation(DataSource.scala:385) at org.apache.spark.sql.execution.command.CreateDataSourceTableCommand.run(createDataSourceTables.scala:78) at org.apache.spark.sql.execution.command.ExecutedCommandExec.sideEffectResult$lzycompute(commands.scala:70) at org.apache.spark.sql.execution.command.ExecutedCommandExec.sideEffectResult(commands.scala:68) at org.apache.spark.sql.execution.command.ExecutedCommandExec.executeCollect(commands.scala:79) at org.apache.spark.sql.Dataset$$anonfun$6.apply(Dataset.scala:190) at org.apache.spark.sql.Dataset$$anonfun$6.apply(Dataset.scala:190) at org.apache.spark.sql.Dataset$$anonfun$54.apply(Dataset.scala:3296) at org.apache.spark.sql.execution.SQLExecution$$anonfun$withNewExecutionId$1.apply(SQLExecution.scala:78) at org.apache.spark.sql.execution.SQLExecution$.withSQLConfPropagated(SQLExecution.scala:125) at org.apache.spark.sql.execution.SQLExecution$.withNewExecutionId(SQLExecution.scala:73) at org.apache.spark.sql.Dataset.withAction(Dataset.scala:3295) at org.apache.spark.sql.Dataset.<init>(Dataset.scala:190) at org.apache.spark.sql.Dataset$.ofRows(Dataset.scala:75) at org.apache.spark.sql.SparkSession.sql(SparkSession.scala:641) at org.apache.spark.sql.sources.v2.SourcesTest$$anonfun$4.apply(DataSourceV2Suite.scala:45) at org.apache.spark.sql.sources.v2.SourcesTest$$anonfun$4.apply(DataSourceV2Suite.scala:45) at org.scalatest.OutcomeOf$class.outcomeOf(OutcomeOf.scala:85) 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$$anon$1.apply(FunSuiteLike.scala:186) at org.scalatest.TestSuite$class.withFixture(TestSuite.scala:196) at org.scalatest.FunSuite.withFixture(FunSuite.scala:1560) at org.scalatest.FunSuiteLike$class.invokeWithFixture$1(FunSuiteLike.scala:183) at org.scalatest.FunSuiteLike$$anonfun$runTest$1.apply(FunSuiteLike.scala:196) at org.scalatest.FunSuiteLike$$anonfun$runTest$1.apply(FunSuiteLike.scala:196) at org.scalatest.SuperEngine.runTestImpl(Engine.scala:289) at org.scalatest.FunSuiteLike$class.runTest(FunSuiteLike.scala:196) at org.scalatest.FunSuite.runTest(FunSuite.scala:1560) at org.scalatest.FunSuiteLike$$anonfun$runTests$1.apply(FunSuiteLike.scala:229) at org.scalatest.FunSuiteLike$$anonfun$runTests$1.apply(FunSuiteLike.scala:229) at org.scalatest.SuperEngine$$anonfun$traverseSubNodes$1$1.apply(Engine.scala:396) at org.scalatest.SuperEngine$$anonfun$traverseSubNodes$1$1.apply(Engine.scala:384) at scala.collection.immutable.List.foreach(List.scala:392) at org.scalatest.SuperEngine.traverseSubNodes$1(Engine.scala:384) at org.scalatest.SuperEngine.org$scalatest$SuperEngine$$runTestsInBranch(Engine.scala:379) at org.scalatest.SuperEngine.runTestsImpl(Engine.scala:461) at org.scalatest.FunSuiteLike$class.runTests(FunSuiteLike.scala:229) at org.scalatest.FunSuite.runTests(FunSuite.scala:1560) at org.scalatest.Suite$class.run(Suite.scala:1147) at org.scalatest.FunSuite.org$scalatest$FunSuiteLike$$super$run(FunSuite.scala:1560) at org.scalatest.FunSuiteLike$$anonfun$run$1.apply(FunSuiteLike.scala:233) at org.scalatest.FunSuiteLike$$anonfun$run$1.apply(FunSuiteLike.scala:233) at org.scalatest.SuperEngine.runImpl(Engine.scala:521) at org.scalatest.FunSuiteLike$class.run(FunSuiteLike.scala:233) at org.scalatest.FunSuite.run(FunSuite.scala:1560) at org.scalatest.tools.SuiteRunner.run(SuiteRunner.scala:45) at org.scalatest.tools.Runner$$anonfun$doRunRunRunDaDoRunRun$1.apply(Runner.scala:1340) at org.scalatest.tools.Runner$$anonfun$doRunRunRunDaDoRunRun$1.apply(Runner.scala:1334) at scala.collection.immutable.List.foreach(List.scala:392) at org.scalatest.tools.Runner$.doRunRunRunDaDoRunRun(Runner.scala:1334) at org.scalatest.tools.Runner$$anonfun$runOptionallyWithPassFailReporter$2.apply(Runner.scala:1011) at org.scalatest.tools.Runner$$anonfun$runOptionallyWithPassFailReporter$2.apply(Runner.scala:1010) at org.scalatest.tools.Runner$.withClassLoaderAndDispatchReporter(Runner.scala:1500) 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)
Currently, USING syntax does not work with Datasource V2. So that developers (Datasource V1) can easily migrate and users can use USING syntax from Datasource v1, we better support this case as well.
There's a discussion thread about this here as well - http://apache-spark-developers-list.1001551.n3.nabble.com/DISCUSS-USING-syntax-for-Datasource-V2-td24754.html