Как добавить столбец NULL в новую таблицу на основе существующей дельта-таблицы при использовании ссылок на данные SQL?

#azure-sql-database #databricks #azure-databricks #delta-lake #databricks-sql

Вопрос:

Я попытался создать новую таблицу из дельта-таблицы и добавить новый столбец NULL при использовании ссылок данных SQL. Databricks не может создать нулевой столбец, если я заполню только что созданный столбец, он будет работать нормально. Как добавить столбец NULL в новую таблицу на основе существующей дельта-таблицы?

Не работает, когда значение равно НУЛЮ

Когда я заполняю колонку, это работает.

Он работает при заполнении 1

Он возвращает следующую ошибку:

 com.databricks.backend.common.rpc.DatabricksExceptions$SQLExecutionException: org.apache.spark.sql.catalyst.errors.package$TreeNodeException: Binding attribute, tree: Parent_name#23885  at org.apache.spark.sql.catalyst.errors.package$.attachTree(package.scala:56)  at org.apache.spark.sql.catalyst.expressions.BindReferences$anonfun$bindReference$1.applyOrElse(BoundAttribute.scala:75)  at org.apache.spark.sql.catalyst.expressions.BindReferences$anonfun$bindReference$1.applyOrElse(BoundAttribute.scala:74)  at org.apache.spark.sql.catalyst.trees.TreeNode.$anonfun$transformDownWithPruning$1(TreeNode.scala:484)  at org.apache.spark.sql.catalyst.trees.CurrentOrigin$.withOrigin(TreeNode.scala:86)  at org.apache.spark.sql.catalyst.trees.TreeNode.transformDownWithPruning(TreeNode.scala:484)  at org.apache.spark.sql.catalyst.trees.TreeNode.transformDown(TreeNode.scala:460)  at org.apache.spark.sql.catalyst.trees.TreeNode.transform(TreeNode.scala:428)  at org.apache.spark.sql.catalyst.expressions.BindReferences$.bindReference(BoundAttribute.scala:74)  at org.apache.spark.sql.catalyst.expressions.BindReferences$.$anonfun$bindReferences$1(BoundAttribute.scala:96)  at scala.collection.TraversableLike.$anonfun$map$1(TraversableLike.scala:238)  at scala.collection.immutable.List.foreach(List.scala:392)  at scala.collection.TraversableLike.map(TraversableLike.scala:238)  at scala.collection.TraversableLike.map$(TraversableLike.scala:231)  at scala.collection.immutable.List.map(List.scala:298)  at org.apache.spark.sql.catalyst.expressions.BindReferences$.bindReferences(BoundAttribute.scala:96)  at org.apache.spark.sql.execution.ProjectExec.doConsume(basicPhysicalOperators.scala:68)  at org.apache.spark.sql.execution.CodegenSupport.consume(WholeStageCodegenExec.scala:195)  at org.apache.spark.sql.execution.CodegenSupport.consume$(WholeStageCodegenExec.scala:150)  at org.apache.spark.sql.execution.ColumnarToRowExec.consume(Columnar.scala:66)  at org.apache.spark.sql.execution.ColumnarToRowExec.doProduce(Columnar.scala:191)  at org.apache.spark.sql.execution.CodegenSupport.$anonfun$produce$1(WholeStageCodegenExec.scala:96)  at org.apache.spark.sql.execution.SparkPlan.$anonfun$executeQuery$1(SparkPlan.scala:257)  at org.apache.spark.rdd.RDDOperationScope$.withScope(RDDOperationScope.scala:165)  at org.apache.spark.sql.execution.SparkPlan.executeQuery(SparkPlan.scala:253)  at org.apache.spark.sql.execution.CodegenSupport.produce(WholeStageCodegenExec.scala:91)  at org.apache.spark.sql.execution.CodegenSupport.produce$(WholeStageCodegenExec.scala:91)  at org.apache.spark.sql.execution.ColumnarToRowExec.produce(Columnar.scala:66)  at org.apache.spark.sql.execution.ProjectExec.doProduce(basicPhysicalOperators.scala:53)  at org.apache.spark.sql.execution.CodegenSupport.$anonfun$produce$1(WholeStageCodegenExec.scala:96)  at org.apache.spark.sql.execution.SparkPlan.$anonfun$executeQuery$1(SparkPlan.scala:257)  at org.apache.spark.rdd.RDDOperationScope$.withScope(RDDOperationScope.scala:165)  at org.apache.spark.sql.execution.SparkPlan.executeQuery(SparkPlan.scala:253)  at org.apache.spark.sql.execution.CodegenSupport.produce(WholeStageCodegenExec.scala:91)  at org.apache.spark.sql.execution.CodegenSupport.produce$(WholeStageCodegenExec.scala:91)  at org.apache.spark.sql.execution.ProjectExec.produce(basicPhysicalOperators.scala:43)  at org.apache.spark.sql.execution.WholeStageCodegenExec.doCodeGen(WholeStageCodegenExec.scala:657)  at org.apache.spark.sql.execution.WholeStageCodegenExec.doExecute(WholeStageCodegenExec.scala:720)  at org.apache.spark.sql.execution.SparkPlan.$anonfun$execute$1(SparkPlan.scala:213)  at org.apache.spark.sql.execution.SparkPlan.$anonfun$executeQuery$1(SparkPlan.scala:257)  at org.apache.spark.rdd.RDDOperationScope$.withScope(RDDOperationScope.scala:165)  at org.apache.spark.sql.execution.SparkPlan.executeQuery(SparkPlan.scala:253)  at org.apache.spark.sql.execution.SparkPlan.execute(SparkPlan.scala:209)  at org.apache.spark.sql.execution.collect.Collector$.collect(Collector.scala:79)  at org.apache.spark.sql.execution.collect.Collector$.collect(Collector.scala:88)  at org.apache.spark.sql.execution.collect.InternalRowFormat$.collect(cachedSparkResults.scala:75)  at org.apache.spark.sql.execution.collect.InternalRowFormat$.collect(cachedSparkResults.scala:62)  at org.apache.spark.sql.execution.ResultCacheManager.$anonfun$getOrComputeResultInternal$1(ResultCacheManager.scala:512)  at scala.Option.getOrElse(Option.scala:189)  at org.apache.spark.sql.execution.ResultCacheManager.getOrComputeResultInternal(ResultCacheManager.scala:511)  at org.apache.spark.sql.execution.ResultCacheManager.getOrComputeResult(ResultCacheManager.scala:399)  at org.apache.spark.sql.execution.CollectLimitExec.executeCollectResult(limit.scala:59)  at org.apache.spark.sql.Dataset.collectResult(Dataset.scala:3031)  at org.apache.spark.sql.Dataset.$anonfun$collectResult$1(Dataset.scala:3022)  at org.apache.spark.sql.Dataset.$anonfun$withAction$1(Dataset.scala:3815)  at org.apache.spark.sql.execution.SQLExecution$.$anonfun$withCustomExecutionEnv$5(SQLExecution.scala:126)  at org.apache.spark.sql.execution.SQLExecution$.withSQLConfPropagated(SQLExecution.scala:269)  at org.apache.spark.sql.execution.SQLExecution$.$anonfun$withCustomExecutionEnv$1(SQLExecution.scala:104)  at org.apache.spark.sql.SparkSession.withActive(SparkSession.scala:852)  at org.apache.spark.sql.execution.SQLExecution$.withCustomExecutionEnv(SQLExecution.scala:77)  at org.apache.spark.sql.execution.SQLExecution$.withNewExecutionId(SQLExecution.scala:219)  at org.apache.spark.sql.Dataset.withAction(Dataset.scala:3813)  at org.apache.spark.sql.Dataset.collectResult(Dataset.scala:3021)  at com.databricks.backend.daemon.driver.OutputAggregator$.withOutputAggregation0(OutputAggregator.scala:263)  at com.databricks.backend.daemon.driver.OutputAggregator$.withOutputAggregation(OutputAggregator.scala:97)  at com.databricks.backend.daemon.driver.SQLDriverLocal.executeSql(SQLDriverLocal.scala:115)  at com.databricks.backend.daemon.driver.SQLDriverLocal.repl(SQLDriverLocal.scala:144)  at com.databricks.backend.daemon.driver.DriverLocal.$anonfun$execute$13(DriverLocal.scala:542)  at com.databricks.logging.UsageLogging.$anonfun$withAttributionContext$1(UsageLogging.scala:240)  at scala.util.DynamicVariable.withValue(DynamicVariable.scala:62)  at com.databricks.logging.UsageLogging.withAttributionContext(UsageLogging.scala:235)  at com.databricks.logging.UsageLogging.withAttributionContext$(UsageLogging.scala:232)  at com.databricks.backend.daemon.driver.DriverLocal.withAttributionContext(DriverLocal.scala:51)  at com.databricks.logging.UsageLogging.withAttributionTags(UsageLogging.scala:279)  at com.databricks.logging.UsageLogging.withAttributionTags$(UsageLogging.scala:271)  at com.databricks.backend.daemon.driver.DriverLocal.withAttributionTags(DriverLocal.scala:51)  at com.databricks.backend.daemon.driver.DriverLocal.execute(DriverLocal.scala:519)  at com.databricks.backend.daemon.driver.DriverWrapper.$anonfun$tryExecutingCommand$1(DriverWrapper.scala:689)  at scala.util.Try$.apply(Try.scala:213)  at com.databricks.backend.daemon.driver.DriverWrapper.tryExecutingCommand(DriverWrapper.scala:681)  at com.databricks.backend.daemon.driver.DriverWrapper.getCommandOutputAndError(DriverWrapper.scala:522)  at com.databricks.backend.daemon.driver.DriverWrapper.executeCommand(DriverWrapper.scala:634)  at com.databricks.backend.daemon.driver.DriverWrapper.runInnerLoop(DriverWrapper.scala:427)  at com.databricks.backend.daemon.driver.DriverWrapper.runInner(DriverWrapper.scala:370)  at com.databricks.backend.daemon.driver.DriverWrapper.run(DriverWrapper.scala:221)  at java.lang.Thread.run(Thread.java:748) Caused by: java.lang.RuntimeException: Couldn't find Parent_name#23885 in [Source_id#23886,Rol_code#23887]  at scala.sys.package$.error(package.scala:30)  at org.apache.spark.sql.catalyst.expressions.BindReferences$anonfun$bindReference$1.$anonfun$applyOrElse$1(BoundAttribute.scala:81)  at org.apache.spark.sql.catalyst.errors.package$.attachTree(package.scala:52)  ... 85 more   at com.databricks.backend.daemon.driver.SQLDriverLocal.executeSql(SQLDriverLocal.scala:129)  at com.databricks.backend.daemon.driver.SQLDriverLocal.repl(SQLDriverLocal.scala:144)  at com.databricks.backend.daemon.driver.DriverLocal.$anonfun$execute$13(DriverLocal.scala:542)  at com.databricks.logging.UsageLogging.$anonfun$withAttributionContext$1(UsageLogging.scala:240)  at scala.util.DynamicVariable.withValue(DynamicVariable.scala:62)  at com.databricks.logging.UsageLogging.withAttributionContext(UsageLogging.scala:235)  at com.databricks.logging.UsageLogging.withAttributionContext$(UsageLogging.scala:232)  at com.databricks.backend.daemon.driver.DriverLocal.withAttributionContext(DriverLocal.scala:51)  at com.databricks.logging.UsageLogging.withAttributionTags(UsageLogging.scala:279)  at com.databricks.logging.UsageLogging.withAttributionTags$(UsageLogging.scala:271)  at com.databricks.backend.daemon.driver.DriverLocal.withAttributionTags(DriverLocal.scala:51)  at com.databricks.backend.daemon.driver.DriverLocal.execute(DriverLocal.scala:519)  at com.databricks.backend.daemon.driver.DriverWrapper.$anonfun$tryExecutingCommand$1(DriverWrapper.scala:689)  at scala.util.Try$.apply(Try.scala:213)  at com.databricks.backend.daemon.driver.DriverWrapper.tryExecutingCommand(DriverWrapper.scala:681)  at com.databricks.backend.daemon.driver.DriverWrapper.getCommandOutputAndError(DriverWrapper.scala:522)  at com.databricks.backend.daemon.driver.DriverWrapper.executeCommand(DriverWrapper.scala:634)  at com.databricks.backend.daemon.driver.DriverWrapper.runInnerLoop(DriverWrapper.scala:427)  at com.databricks.backend.daemon.driver.DriverWrapper.runInner(DriverWrapper.scala:370)  at com.databricks.backend.daemon.driver.DriverWrapper.run(DriverWrapper.scala:221)  at java.lang.Thread.run(Thread.java:748) 

Ответ №1:

У вас не может быть столбца со null значением без указания типа для этого столбца, поэтому вам нужно выбрать для него определенный тип и привести null к этому типу.

Измените код с select null as parent_name, .... на select cast(null as string) as parent_name, .... (при необходимости измените тип)