[
https://issues.apache.org/jira/browse/SPARK-36905?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=17427450#comment-17427450
]
Apache Spark commented on SPARK-36905:
--------------------------------------
User 'linhongliu-db' has created a pull request for this issue:
https://github.com/apache/spark/pull/34254
> Reading Hive view without explicit column names fails in Spark
> ---------------------------------------------------------------
>
> Key: SPARK-36905
> URL: https://issues.apache.org/jira/browse/SPARK-36905
> Project: Spark
> Issue Type: Bug
> Components: SQL
> Affects Versions: 3.2.0
> Reporter: Shardul Mahadik
> Priority: Major
>
> Consider a Hive view in which some columns are not explicitly named
> {code:sql}
> CREATE VIEW test_view AS
> SELECT 1
> FROM some_table
> {code}
> Reading this view in Spark leads to an {{AnalysisException}}
> {code:java}
> org.apache.spark.sql.AnalysisException: cannot resolve '`_c0`' given input
> columns: [1]
> at
> org.apache.spark.sql.catalyst.analysis.package$AnalysisErrorAt.failAnalysis(package.scala:42)
> at
> org.apache.spark.sql.catalyst.analysis.CheckAnalysis$$anonfun$$nestedInanonfun$checkAnalysis$1$2.applyOrElse(CheckAnalysis.scala:188)
> at
> org.apache.spark.sql.catalyst.analysis.CheckAnalysis$$anonfun$$nestedInanonfun$checkAnalysis$1$2.applyOrElse(CheckAnalysis.scala:185)
> at
> org.apache.spark.sql.catalyst.trees.TreeNode.$anonfun$transformUp$2(TreeNode.scala:340)
> at
> org.apache.spark.sql.catalyst.trees.CurrentOrigin$.withOrigin(TreeNode.scala:72)
> at
> org.apache.spark.sql.catalyst.trees.TreeNode.transformUp(TreeNode.scala:340)
> at
> org.apache.spark.sql.catalyst.trees.TreeNode.$anonfun$transformUp$1(TreeNode.scala:337)
> at
> org.apache.spark.sql.catalyst.trees.TreeNode.$anonfun$mapChildren$1(TreeNode.scala:406)
> at
> org.apache.spark.sql.catalyst.trees.TreeNode.mapProductIterator(TreeNode.scala:242)
> at
> org.apache.spark.sql.catalyst.trees.TreeNode.mapChildren(TreeNode.scala:404)
> at
> org.apache.spark.sql.catalyst.trees.TreeNode.mapChildren(TreeNode.scala:357)
> at
> org.apache.spark.sql.catalyst.trees.TreeNode.transformUp(TreeNode.scala:337)
> at
> org.apache.spark.sql.catalyst.trees.TreeNode.$anonfun$transformUp$1(TreeNode.scala:337)
> at
> org.apache.spark.sql.catalyst.trees.TreeNode.$anonfun$mapChildren$1(TreeNode.scala:406)
> at
> org.apache.spark.sql.catalyst.trees.TreeNode.mapProductIterator(TreeNode.scala:242)
> at
> org.apache.spark.sql.catalyst.trees.TreeNode.mapChildren(TreeNode.scala:404)
> at
> org.apache.spark.sql.catalyst.trees.TreeNode.mapChildren(TreeNode.scala:357)
> at
> org.apache.spark.sql.catalyst.trees.TreeNode.transformUp(TreeNode.scala:337)
> at
> org.apache.spark.sql.catalyst.plans.QueryPlan.$anonfun$transformExpressionsUp$1(QueryPlan.scala:104)
> at
> org.apache.spark.sql.catalyst.plans.QueryPlan.$anonfun$mapExpressions$1(QueryPlan.scala:116)
> at
> org.apache.spark.sql.catalyst.trees.CurrentOrigin$.withOrigin(TreeNode.scala:72)
> at
> org.apache.spark.sql.catalyst.plans.QueryPlan.transformExpression$1(QueryPlan.scala:116)
> at
> org.apache.spark.sql.catalyst.plans.QueryPlan.recursiveTransform$1(QueryPlan.scala:127)
> at
> org.apache.spark.sql.catalyst.plans.QueryPlan.$anonfun$mapExpressions$3(QueryPlan.scala:132)
> at
> scala.collection.TraversableLike.$anonfun$map$1(TraversableLike.scala:238)
> at scala.collection.mutable.ResizableArray.foreach(ResizableArray.scala:62)
> at scala.collection.mutable.ResizableArray.foreach$(ResizableArray.scala:55)
> at scala.collection.mutable.ArrayBuffer.foreach(ArrayBuffer.scala:49)
> at scala.collection.TraversableLike.map(TraversableLike.scala:238)
> at scala.collection.TraversableLike.map$(TraversableLike.scala:231)
> at scala.collection.AbstractTraversable.map(Traversable.scala:108)
> at
> org.apache.spark.sql.catalyst.plans.QueryPlan.recursiveTransform$1(QueryPlan.scala:132)
> at
> org.apache.spark.sql.catalyst.plans.QueryPlan.$anonfun$mapExpressions$4(QueryPlan.scala:137)
> at
> org.apache.spark.sql.catalyst.trees.TreeNode.mapProductIterator(TreeNode.scala:242)
> at
> org.apache.spark.sql.catalyst.plans.QueryPlan.mapExpressions(QueryPlan.scala:137)
> at
> org.apache.spark.sql.catalyst.plans.QueryPlan.transformExpressionsUp(QueryPlan.scala:104)
> at
> org.apache.spark.sql.catalyst.analysis.CheckAnalysis.$anonfun$checkAnalysis$1(CheckAnalysis.scala:185)
> at
> org.apache.spark.sql.catalyst.analysis.CheckAnalysis.$anonfun$checkAnalysis$1$adapted(CheckAnalysis.scala:94)
> at
> org.apache.spark.sql.catalyst.trees.TreeNode.foreachUp(TreeNode.scala:182)
> at
> org.apache.spark.sql.catalyst.analysis.CheckAnalysis.checkAnalysis(CheckAnalysis.scala:94)
> at
> org.apache.spark.sql.catalyst.analysis.CheckAnalysis.checkAnalysis$(CheckAnalysis.scala:91)
> at
> org.apache.spark.sql.catalyst.analysis.Analyzer.checkAnalysis(Analyzer.scala:155)
> at
> org.apache.spark.sql.catalyst.analysis.Analyzer$ResolveRelations$.resolveViews(Analyzer.scala:1147)
> at
> org.apache.spark.sql.catalyst.analysis.Analyzer$ResolveRelations$.resolveViews(Analyzer.scala:1151)
> at
> org.apache.spark.sql.catalyst.analysis.Analyzer$ResolveRelations$$anonfun$apply$10.$anonfun$applyOrElse$82(Analyzer.scala:1207)
> at scala.Option.map(Option.scala:230)
> at
> org.apache.spark.sql.catalyst.analysis.Analyzer$ResolveRelations$$anonfun$apply$10.applyOrElse(Analyzer.scala:1207)
> at
> org.apache.spark.sql.catalyst.analysis.Analyzer$ResolveRelations$$anonfun$apply$10.applyOrElse(Analyzer.scala:1155)
> at
> org.apache.spark.sql.catalyst.plans.logical.AnalysisHelper.$anonfun$resolveOperatorsUp$3(AnalysisHelper.scala:90)
> at
> org.apache.spark.sql.catalyst.trees.CurrentOrigin$.withOrigin(TreeNode.scala:72)
> at
> org.apache.spark.sql.catalyst.plans.logical.AnalysisHelper.$anonfun$resolveOperatorsUp$1(AnalysisHelper.scala:90)
> at
> org.apache.spark.sql.catalyst.plans.logical.AnalysisHelper$.allowInvokingTransformsInAnalyzer(AnalysisHelper.scala:221)
> at
> org.apache.spark.sql.catalyst.plans.logical.AnalysisHelper.resolveOperatorsUp(AnalysisHelper.scala:86)
> at
> org.apache.spark.sql.catalyst.plans.logical.AnalysisHelper.resolveOperatorsUp$(AnalysisHelper.scala:84)
> at
> org.apache.spark.sql.catalyst.plans.logical.LogicalPlan.resolveOperatorsUp(LogicalPlan.scala:29)
> at
> org.apache.spark.sql.catalyst.analysis.Analyzer$ResolveRelations$.apply(Analyzer.scala:1155)
> at
> org.apache.spark.sql.catalyst.analysis.Analyzer$ResolveRelations$.apply(Analyzer.scala:1116)
> at
> org.apache.spark.sql.catalyst.rules.RuleExecutor.$anonfun$execute$2(RuleExecutor.scala:215)
> at
> scala.collection.LinearSeqOptimized.foldLeft(LinearSeqOptimized.scala:126)
> at
> scala.collection.LinearSeqOptimized.foldLeft$(LinearSeqOptimized.scala:122)
> at scala.collection.immutable.List.foldLeft(List.scala:89)
> at
> org.apache.spark.sql.catalyst.rules.RuleExecutor.$anonfun$execute$1(RuleExecutor.scala:212)
> at
> org.apache.spark.sql.catalyst.rules.RuleExecutor.$anonfun$execute$1$adapted(RuleExecutor.scala:204)
> at scala.collection.immutable.List.foreach(List.scala:392)
> at
> org.apache.spark.sql.catalyst.rules.RuleExecutor.execute(RuleExecutor.scala:204)
> at
> org.apache.spark.sql.catalyst.analysis.Analyzer.org$apache$spark$sql$catalyst$analysis$Analyzer$$executeSameContext(Analyzer.scala:196)
> at
> org.apache.spark.sql.catalyst.analysis.Analyzer.execute(Analyzer.scala:190)
> at
> org.apache.spark.sql.catalyst.analysis.Analyzer.execute(Analyzer.scala:155)
> at
> org.apache.spark.sql.catalyst.rules.RuleExecutor.$anonfun$executeAndTrack$1(RuleExecutor.scala:182)
> at
> org.apache.spark.sql.catalyst.QueryPlanningTracker$.withTracker(QueryPlanningTracker.scala:88)
> at
> org.apache.spark.sql.catalyst.rules.RuleExecutor.executeAndTrack(RuleExecutor.scala:182)
> at
> org.apache.spark.sql.catalyst.analysis.Analyzer.$anonfun$executeAndCheck$1(Analyzer.scala:174)
> at
> org.apache.spark.sql.catalyst.plans.logical.AnalysisHelper$.markInAnalyzer(AnalysisHelper.scala:228)
> at
> org.apache.spark.sql.catalyst.analysis.Analyzer.executeAndCheck(Analyzer.scala:173)
> at
> org.apache.spark.sql.execution.QueryExecution.$anonfun$analyzed$1(QueryExecution.scala:74)
> at
> org.apache.spark.sql.catalyst.QueryPlanningTracker.measurePhase(QueryPlanningTracker.scala:111)
> at
> org.apache.spark.sql.execution.QueryExecution.$anonfun$executePhase$1(QueryExecution.scala:144)
> at org.apache.spark.sql.SparkSession.withActive(SparkSession.scala:771)
> at
> org.apache.spark.sql.execution.QueryExecution.executePhase(QueryExecution.scala:144)
> at
> org.apache.spark.sql.execution.QueryExecution.analyzed$lzycompute(QueryExecution.scala:74)
> at
> org.apache.spark.sql.execution.QueryExecution.analyzed(QueryExecution.scala:72)
> at
> org.apache.spark.sql.execution.QueryExecution.assertAnalyzed(QueryExecution.scala:64)
> at org.apache.spark.sql.Dataset$.$anonfun$ofRows$1(Dataset.scala:90)
> at org.apache.spark.sql.SparkSession.withActive(SparkSession.scala:771)
> at org.apache.spark.sql.Dataset$.ofRows(Dataset.scala:88)
> at org.apache.spark.sql.DataFrameReader.table(DataFrameReader.scala:918)
> at org.apache.spark.sql.SparkSession.table(SparkSession.scala:592)
> ... 47 elided
> {code}
> TRACE level log showing the query plan
> {code:java}
> 21/09/30 10:17:17 TRACE PlanChangeLogger:
> === Result of Batch Cleanup ===
> 'Project [upcast('_c0, IntegerType) AS _c0#3] 'Project
> [upcast('_c0, IntegerType) AS _c0#3]
> +- Project [1 AS 1#4] +- Project [1 AS 1#4]
> +- SubqueryAlias spark_catalog.default.some_table +- SubqueryAlias
> spark_catalog.default.some_table
> +- Relation default.some_table[id#1L] orc +- Relation
> default.some_table[id#1L] orc
> {code}
--
This message was sent by Atlassian Jira
(v8.3.4#803005)
---------------------------------------------------------------------
To unsubscribe, e-mail: issues-unsubscr...@spark.apache.org
For additional commands, e-mail: issues-h...@spark.apache.org
