Major Description
The following test case produces a ClassCastException in the analyzer:
CREATE TABLE t1(a INTEGER); INSERT INTO t1 VALUES(1),(2); CREATE TABLE t2(b INTEGER); INSERT INTO t2 VALUES(1); SELECT a FROM t1 WHERE a NOT IN (SELECT a FROM t2);
Here's the exception:
java.lang.ClassCastException: org.apache.spark.sql.catalyst.expressions.OuterReference cannot be cast to org.apache.spark.sql.catalyst.expressions.NamedExpression at org.apache.spark.sql.catalyst.plans.logical.Project$$anonfun$1.apply(basicLogicalOperators.scala:48) at scala.collection.LinearSeqOptimized$class.exists(LinearSeqOptimized.scala:80) at scala.collection.immutable.List.exists(List.scala:84) at org.apache.spark.sql.catalyst.plans.logical.Project.resolved$lzycompute(basicLogicalOperators.scala:44) at org.apache.spark.sql.catalyst.plans.logical.Project.resolved(basicLogicalOperators.scala:43) at org.apache.spark.sql.catalyst.analysis.Analyzer$ResolveSubquery$.org$apache$spark$sql$catalyst$analysis$Analyzer$ResolveSubquery$$resolveSubQuery(Analyzer.scala:1091) at org.apache.spark.sql.catalyst.analysis.Analyzer$ResolveSubquery$$anonfun$org$apache$spark$sql$catalyst$analysis$Analyzer$ResolveSubquery$$resolveSubQueries$1.applyOrElse(Analyzer.scala:1130) at org.apache.spark.sql.catalyst.analysis.Analyzer$ResolveSubquery$$anonfun$org$apache$spark$sql$catalyst$analysis$Analyzer$ResolveSubquery$$resolveSubQueries$1.applyOrElse(Analyzer.scala:1116) at org.apache.spark.sql.catalyst.trees.TreeNode$$anonfun$3.apply(TreeNode.scala:279) at org.apache.spark.sql.catalyst.trees.TreeNode$$anonfun$3.apply(TreeNode.scala:279) at org.apache.spark.sql.catalyst.trees.CurrentOrigin$.withOrigin(TreeNode.scala:69) at org.apache.spark.sql.catalyst.trees.TreeNode.transformDown(TreeNode.scala:278) at org.apache.spark.sql.catalyst.trees.TreeNode$$anonfun$transformDown$1.apply(TreeNode.scala:284) at org.apache.spark.sql.catalyst.trees.TreeNode$$anonfun$transformDown$1.apply(TreeNode.scala:284) at org.apache.spark.sql.catalyst.trees.TreeNode$$anonfun$5.apply(TreeNode.scala:321) at org.apache.spark.sql.catalyst.trees.TreeNode.mapProductIterator(TreeNode.scala:179) at org.apache.spark.sql.catalyst.trees.TreeNode.transformChildren(TreeNode.scala:319) at org.apache.spark.sql.catalyst.trees.TreeNode.transformDown(TreeNode.scala:284) at org.apache.spark.sql.catalyst.plans.QueryPlan.transformExpressionDown$1(QueryPlan.scala:156) at org.apache.spark.sql.catalyst.plans.QueryPlan.org$apache$spark$sql$catalyst$plans$QueryPlan$$recursiveTransform$1(QueryPlan.scala:166) at org.apache.spark.sql.catalyst.plans.QueryPlan$$anonfun$4.apply(QueryPlan.scala:175) at org.apache.spark.sql.catalyst.trees.TreeNode.mapProductIterator(TreeNode.scala:179) at org.apache.spark.sql.catalyst.plans.QueryPlan.transformExpressionsDown(QueryPlan.scala:175) at org.apache.spark.sql.catalyst.plans.QueryPlan.transformExpressions(QueryPlan.scala:144) at org.apache.spark.sql.catalyst.analysis.Analyzer$ResolveSubquery$.org$apache$spark$sql$catalyst$analysis$Analyzer$ResolveSubquery$$resolveSubQueries(Analyzer.scala:1116) at org.apache.spark.sql.catalyst.analysis.Analyzer$ResolveSubquery$$anonfun$apply$16.applyOrElse(Analyzer.scala:1148) at org.apache.spark.sql.catalyst.analysis.Analyzer$ResolveSubquery$$anonfun$apply$16.applyOrElse(Analyzer.scala:1141) at org.apache.spark.sql.catalyst.plans.logical.LogicalPlan$$anonfun$resolveOperators$1.apply(LogicalPlan.scala:61) at org.apache.spark.sql.catalyst.plans.logical.LogicalPlan$$anonfun$resolveOperators$1.apply(LogicalPlan.scala:61) at org.apache.spark.sql.catalyst.trees.CurrentOrigin$.withOrigin(TreeNode.scala:69) at org.apache.spark.sql.catalyst.plans.logical.LogicalPlan.resolveOperators(LogicalPlan.scala:60) at org.apache.spark.sql.catalyst.plans.logical.LogicalPlan$$anonfun$1.apply(LogicalPlan.scala:58) at org.apache.spark.sql.catalyst.plans.logical.LogicalPlan$$anonfun$1.apply(LogicalPlan.scala:58) at org.apache.spark.sql.catalyst.trees.TreeNode$$anonfun$5.apply(TreeNode.scala:321) at org.apache.spark.sql.catalyst.trees.TreeNode.mapProductIterator(TreeNode.scala:179) at org.apache.spark.sql.catalyst.trees.TreeNode.transformChildren(TreeNode.scala:319) at org.apache.spark.sql.catalyst.plans.logical.LogicalPlan.resolveOperators(LogicalPlan.scala:58) at org.apache.spark.sql.catalyst.analysis.Analyzer$ResolveSubquery$.apply(Analyzer.scala:1141) at org.apache.spark.sql.catalyst.analysis.Analyzer$ResolveSubquery$.apply(Analyzer.scala:909) at org.apache.spark.sql.catalyst.rules.RuleExecutor$$anonfun$execute$1$$anonfun$apply$1.apply(RuleExecutor.scala:85) at org.apache.spark.sql.catalyst.rules.RuleExecutor$$anonfun$execute$1$$anonfun$apply$1.apply(RuleExecutor.scala:82) at scala.collection.LinearSeqOptimized$class.foldLeft(LinearSeqOptimized.scala:111) at scala.collection.immutable.List.foldLeft(List.scala:84) at org.apache.spark.sql.catalyst.rules.RuleExecutor$$anonfun$execute$1.apply(RuleExecutor.scala:82) at org.apache.spark.sql.catalyst.rules.RuleExecutor$$anonfun$execute$1.apply(RuleExecutor.scala:74) at scala.collection.immutable.List.foreach(List.scala:318) at org.apache.spark.sql.catalyst.rules.RuleExecutor.execute(RuleExecutor.scala:74) at org.apache.spark.sql.execution.QueryExecution.analyzed$lzycompute(QueryExecution.scala:65) at org.apache.spark.sql.execution.QueryExecution.analyzed(QueryExecution.scala:63) at org.apache.spark.sql.execution.QueryExecution.assertAnalyzed(QueryExecution.scala:49) at org.apache.spark.sql.Dataset$.ofRows(Dataset.scala:64) at org.apache.spark.sql.SparkSession.sql(SparkSession.scala:582) at org.apache.spark.sql.SQLContext.sql(SQLContext.scala:682)
This bug was discovered while trying to run SQLite bug reports through Spark SQL (see https://www.sqlite.org/src/tktview?name=5e3c886796)
