[jira] [Updated] (CARBONDATA-3198) ALTER ADD COLUMNS does not support datasource table with type carbon

[Akash R Nilugal (Jira)]

     [ https://issues.apache.org/jira/browse/CARBONDATA-3198?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ]

Ravindra Pesala updated CARBONDATA-3198:
----------------------------------------
    Fix Version/s:     (was: 1.5.2)
                   NONE

> ALTER ADD COLUMNS does not support datasource table with type carbon
> --------------------------------------------------------------------
>
>                 Key: CARBONDATA-3198
>                 URL: https://issues.apache.org/jira/browse/CARBONDATA-3198
>             Project: CarbonData
>          Issue Type: Bug
>    Affects Versions: 1.5.1
>            Reporter: xubo245
>            Priority: Major
>             Fix For: NONE
>
>
> code:
> {code:java}
>   test("test add columns for table of using carbon") {
>     import spark.implicits._
>     val df = spark.sparkContext.parallelize(1 to 10)
>       .map(x => ("a" + x % 10, "b", x))
>       .toDF("c1", "c2", "number")
>     spark.sql("drop table if exists testparquet")
>     spark.sql("drop table if exists testformat")
>     // Saves dataframe to carbon file
>     df.write
>       .format("parquet").saveAsTable("testparquet")
>     spark.sql("create table carbon_table(c1 string, c2 string, number int) using carbon")
>     spark.sql("insert into carbon_table select * from testparquet")
>     TestUtil.checkAnswer(spark.sql("select * from carbon_table where c1='a1'"), spark.sql("select * from testparquet where c1='a1'"))
>     if (!spark.sparkContext.version.startsWith("2.1")) {
>       val mapSize = DataMapStoreManager.getInstance().getAllDataMaps.size()
>       DataMapStoreManager.getInstance()
>         .clearDataMaps(AbsoluteTableIdentifier.from(warehouse1 + "/carbon_table"))
>       assert(mapSize > DataMapStoreManager.getInstance().getAllDataMaps.size())
>     }
>     spark.sql("select * from carbon_table").show()
>     spark.sql("ALTER TABLE carbon_table ADD COLUMNS (a1 INT, b1 STRING) ")
>     spark.sql("select * from carbon_table").show()
>     spark.sql("insert into carbon_table values('Bob','xu',12,1,'parquet')")
>     spark.sql("select * from carbon_table").show()
>     spark.sql("drop table if exists testparquet")
>     spark.sql("drop table if exists testformat")
>   }
> {code}
> exception:
> {code:java}
> 2018-12-25 22:22:12 INFO  ContextHandler:781 - Started o.s.j.s.ServletContextHandler@51e0301d{/metrics/json,null,AVAILABLE,@Spark}
> +---+---+------+
> | c1| c2|number|
> +---+---+------+
> | a1|  b|     1|
> | a2|  b|     2|
> | a3|  b|     3|
> | a4|  b|     4|
> | a5|  b|     5|
> | a6|  b|     6|
> | a7|  b|     7|
> | a8|  b|     8|
> | a9|  b|     9|
> | a0|  b|    10|
> +---+---+------+
> ALTER ADD COLUMNS does not support datasource table with type carbon.
> You must drop and re-create the table for adding the new columns. Tables: `carbon_table`
>              ;
> org.apache.spark.sql.AnalysisException:
> ALTER ADD COLUMNS does not support datasource table with type carbon.
> You must drop and re-create the table for adding the new columns. Tables: `carbon_table`
>              ;
> at org.apache.spark.sql.execution.command.AlterTableAddColumnsCommand.verifyAlterTableAddColumn(tables.scala:242)
> at org.apache.spark.sql.execution.command.AlterTableAddColumnsCommand.run(tables.scala:194)
> 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$$anonfun$52.apply(Dataset.scala:3259)
> at org.apache.spark.sql.execution.SQLExecution$.withNewExecutionId(SQLExecution.scala:77)
> at org.apache.spark.sql.Dataset.withAction(Dataset.scala:3258)
> at org.apache.spark.sql.Dataset.<init>(Dataset.scala:190)
> at org.apache.spark.sql.Dataset$.ofRows(Dataset.scala:75)
> at org.apache.spark.sql.SparkSession.sql(SparkSession.scala:642)
> at org.apache.spark.sql.carbondata.datasource.SparkCarbonDataSourceTest$$anonfun$3.apply$mcV$sp(SparkCarbonDataSourceTest.scala:100)
> at org.apache.spark.sql.carbondata.datasource.SparkCarbonDataSourceTest$$anonfun$3.apply(SparkCarbonDataSourceTest.scala:80)
> at org.apache.spark.sql.carbondata.datasource.SparkCarbonDataSourceTest$$anonfun$3.apply(SparkCarbonDataSourceTest.scala:80)
> at org.scalatest.Transformer$$anonfun$apply$1.apply$mcV$sp(Transformer.scala:22)
> at org.scalatest.OutcomeOf$class.outcomeOf(OutcomeOf.scala:85)
> at org.scalatest.OutcomeOf$.outcomeOf(OutcomeOf.scala:104)
> at org.scalatest.Transformer.apply(Transformer.scala:22)
> at org.scalatest.Transformer.apply(Transformer.scala:20)
> at org.scalatest.FunSuiteLike$$anon$1.apply(FunSuiteLike.scala:166)
> at org.scalatest.Suite$class.withFixture(Suite.scala:1122)
> at org.scalatest.FunSuite.withFixture(FunSuite.scala:1555)
> at org.scalatest.FunSuiteLike$class.invokeWithFixture$1(FunSuiteLike.scala:163)
> at org.scalatest.FunSuiteLike$$anonfun$runTest$1.apply(FunSuiteLike.scala:175)
> at org.scalatest.FunSuiteLike$$anonfun$runTest$1.apply(FunSuiteLike.scala:175)
> at org.scalatest.SuperEngine.runTestImpl(Engine.scala:306)
> at org.scalatest.FunSuiteLike$class.runTest(FunSuiteLike.scala:175)
> at org.scalatest.FunSuite.runTest(FunSuite.scala:1555)
> at org.scalatest.FunSuiteLike$$anonfun$runTests$1.apply(FunSuiteLike.scala:208)
> at org.scalatest.FunSuiteLike$$anonfun$runTests$1.apply(FunSuiteLike.scala:208)
> at org.scalatest.SuperEngine$$anonfun$traverseSubNodes$1$1.apply(Engine.scala:413)
> at org.scalatest.SuperEngine$$anonfun$traverseSubNodes$1$1.apply(Engine.scala:401)
> at scala.collection.immutable.List.foreach(List.scala:381)
> at org.scalatest.SuperEngine.traverseSubNodes$1(Engine.scala:401)
> at org.scalatest.SuperEngine.org$scalatest$SuperEngine$$runTestsInBranch(Engine.scala:396)
> at org.scalatest.SuperEngine.runTestsImpl(Engine.scala:483)
> at org.scalatest.FunSuiteLike$class.runTests(FunSuiteLike.scala:208)
> at org.scalatest.FunSuite.runTests(FunSuite.scala:1555)
> at org.scalatest.Suite$class.run(Suite.scala:1424)
> at org.scalatest.FunSuite.org$scalatest$FunSuiteLike$$super$run(FunSuite.scala:1555)
> at org.scalatest.FunSuiteLike$$anonfun$run$1.apply(FunSuiteLike.scala:212)
> at org.scalatest.FunSuiteLike$$anonfun$run$1.apply(FunSuiteLike.scala:212)
> at org.scalatest.SuperEngine.runImpl(Engine.scala:545)
> at org.scalatest.FunSuiteLike$class.run(FunSuiteLike.scala:212)
> at org.apache.spark.sql.carbondata.datasource.SparkCarbonDataSourceTest.org$scalatest$BeforeAndAfterAll$$super$run(SparkCarbonDataSourceTest.scala:39)
> at org.scalatest.BeforeAndAfterAll$class.liftedTree1$1(BeforeAndAfterAll.scala:257)
> at org.scalatest.BeforeAndAfterAll$class.run(BeforeAndAfterAll.scala:256)
> at org.apache.spark.sql.carbondata.datasource.SparkCarbonDataSourceTest.run(SparkCarbonDataSourceTest.scala:39)
> at org.scalatest.tools.SuiteRunner.run(SuiteRunner.scala:55)
> at org.scalatest.tools.Runner$$anonfun$doRunRunRunDaDoRunRun$3.apply(Runner.scala:2563)
> at org.scalatest.tools.Runner$$anonfun$doRunRunRunDaDoRunRun$3.apply(Runner.scala:2557)
> at scala.collection.immutable.List.foreach(List.scala:381)
> at org.scalatest.tools.Runner$.doRunRunRunDaDoRunRun(Runner.scala:2557)
> at org.scalatest.tools.Runner$$anonfun$runOptionallyWithPassFailReporter$2.apply(Runner.scala:1044)
> at org.scalatest.tools.Runner$$anonfun$runOptionallyWithPassFailReporter$2.apply(Runner.scala:1043)
> at org.scalatest.tools.Runner$.withClassLoaderAndDispatchReporter(Runner.scala:2722)
> at org.scalatest.tools.Runner$.runOptionallyWithPassFailReporter(Runner.scala:1043)
> at org.scalatest.tools.Runner$.run(Runner.scala:883)
> 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)
> Process finished with exit code 0
> {code}
> analysis:
> org.apache.spark.sql.execution.command.AlterTableAddColumnsCommand#verifyAlterTableAddColumn
> {code:java}
>  /**
>    * ALTER TABLE ADD COLUMNS command does not support temporary view/table,
>    * view, or datasource table with text, orc formats or external provider.
>    * For datasource table, it currently only supports parquet, json, csv.
>    */
>   private def verifyAlterTableAddColumn(
>       conf: SQLConf,
>       catalog: SessionCatalog,
>       table: TableIdentifier): CatalogTable = {
>     val catalogTable = catalog.getTempViewOrPermanentTableMetadata(table)
>     if (catalogTable.tableType == CatalogTableType.VIEW) {
>       throw new AnalysisException(
>         s"""
>           |ALTER ADD COLUMNS does not support views.
>           |You must drop and re-create the views for adding the new columns. Views: $table
>          """.stripMargin)
>     }
>     if (DDLUtils.isDatasourceTable(catalogTable)) {
>       DataSource.lookupDataSource(catalogTable.provider.get, conf).newInstance() match {
>         // For datasource table, this command can only support the following File format.
>         // TextFileFormat only default to one column "value"
>         // Hive type is already considered as hive serde table, so the logic will not
>         // come in here.
>         case _: JsonFileFormat | _: CSVFileFormat | _: ParquetFileFormat =>
>         case s if s.getClass.getCanonicalName.endsWith("OrcFileFormat") =>
>         case s =>
>           throw new AnalysisException(
>             s"""
>               |ALTER ADD COLUMNS does not support datasource table with type $s.
>               |You must drop and re-create the table for adding the new columns. Tables: $table
>              """.stripMargin)
>       }
>     }
>     catalogTable
>   }
> }
> {code}

--
This message was sent by Atlassian JIRA
(v7.6.3#76005)