diff --git a/sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/analysis/Analyzer.scala b/sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/analysis/Analyzer.scala index df8e7f2381fbdfb1a7fdc659e37dbca79a849246..e58f3f64947f37980e3ed96cf76b4f6564c13071 100644 --- a/sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/analysis/Analyzer.scala +++ b/sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/analysis/Analyzer.scala @@ -316,7 +316,7 @@ class Analyzer( ) // Special handling for cases when self-join introduce duplicate expression ids. - case j @ Join(left, right, _, _) if left.outputSet.intersect(right.outputSet).nonEmpty => + case j @ Join(left, right, _, _) if !j.selfJoinResolved => val conflictingAttributes = left.outputSet.intersect(right.outputSet) logDebug(s"Conflicting attributes ${conflictingAttributes.mkString(",")} in $j") diff --git a/sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/analysis/CheckAnalysis.scala b/sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/analysis/CheckAnalysis.scala index 476ac2b7cb4748c42045e0bc38c31c95d9e5f311..c7f9713344c5054f5d7ad34b868703b18bb0e1a2 100644 --- a/sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/analysis/CheckAnalysis.scala +++ b/sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/analysis/CheckAnalysis.scala @@ -109,29 +109,27 @@ trait CheckAnalysis { s"resolved attribute(s) $missingAttributes missing from $input " + s"in operator ${operator.simpleString}") - case o if !o.resolved => - failAnalysis( - s"unresolved operator ${operator.simpleString}") - case p @ Project(exprs, _) if containsMultipleGenerators(exprs) => failAnalysis( s"""Only a single table generating function is allowed in a SELECT clause, found: | ${exprs.map(_.prettyString).mkString(",")}""".stripMargin) + // Special handling for cases when self-join introduce duplicate expression ids. + case j @ Join(left, right, _, _) if left.outputSet.intersect(right.outputSet).nonEmpty => + val conflictingAttributes = left.outputSet.intersect(right.outputSet) + failAnalysis( + s""" + |Failure when resolving conflicting references in Join: + |$plan + |Conflicting attributes: ${conflictingAttributes.mkString(",")} + |""".stripMargin) + + case o if !o.resolved => + failAnalysis( + s"unresolved operator ${operator.simpleString}") case _ => // Analysis successful! } - - // Special handling for cases when self-join introduce duplicate expression ids. - case j @ Join(left, right, _, _) if left.outputSet.intersect(right.outputSet).nonEmpty => - val conflictingAttributes = left.outputSet.intersect(right.outputSet) - failAnalysis( - s""" - |Failure when resolving conflicting references in Join: - |$plan - |Conflicting attributes: ${conflictingAttributes.mkString(",")} - |""".stripMargin) - } extendedCheckRules.foreach(_(plan)) } diff --git a/sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/plans/logical/basicOperators.scala b/sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/plans/logical/basicOperators.scala index fbe104db016d6fb475fd7330f0308e3d4916526f..17a91247327f78747881d1b9ae9ee1ab6ee7c11c 100644 --- a/sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/plans/logical/basicOperators.scala +++ b/sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/plans/logical/basicOperators.scala @@ -123,11 +123,11 @@ case class Join( } } - private def selfJoinResolved: Boolean = left.outputSet.intersect(right.outputSet).isEmpty + def selfJoinResolved: Boolean = left.outputSet.intersect(right.outputSet).isEmpty - // Joins are only resolved if they don't introduce ambiguious expression ids. + // Joins are only resolved if they don't introduce ambiguous expression ids. override lazy val resolved: Boolean = { - childrenResolved && !expressions.exists(!_.resolved) && selfJoinResolved + childrenResolved && expressions.forall(_.resolved) && selfJoinResolved } } diff --git a/sql/catalyst/src/test/scala/org/apache/spark/sql/catalyst/analysis/AnalysisErrorSuite.scala b/sql/catalyst/src/test/scala/org/apache/spark/sql/catalyst/analysis/AnalysisErrorSuite.scala index f0f17103991ef7d505fdd8d6d872371d446ac922..2147d07e09bd30f0608b70f31893e300225ba033 100644 --- a/sql/catalyst/src/test/scala/org/apache/spark/sql/catalyst/analysis/AnalysisErrorSuite.scala +++ b/sql/catalyst/src/test/scala/org/apache/spark/sql/catalyst/analysis/AnalysisErrorSuite.scala @@ -23,10 +23,11 @@ import org.apache.spark.SparkFunSuite import org.apache.spark.sql.AnalysisException import org.apache.spark.sql.catalyst.expressions._ import org.apache.spark.sql.catalyst.plans.logical._ -import org.apache.spark.sql.types._ -import org.apache.spark.sql.catalyst.{InternalRow, SimpleCatalystConf} +import org.apache.spark.sql.catalyst.plans.Inner +import org.apache.spark.sql.catalyst.InternalRow import org.apache.spark.sql.catalyst.dsl.expressions._ import org.apache.spark.sql.catalyst.dsl.plans._ +import org.apache.spark.sql.types._ case class TestFunction( children: Seq[Expression], @@ -164,4 +165,13 @@ class AnalysisErrorSuite extends SparkFunSuite with BeforeAndAfter { assert(message.contains("resolved attribute(s) a#1 missing from a#2")) } + + test("error test for self-join") { + val join = Join(testRelation, testRelation, Inner, None) + val error = intercept[AnalysisException] { + SimpleAnalyzer.checkAnalysis(join) + } + error.message.contains("Failure when resolving conflicting references in Join") + error.message.contains("Conflicting attributes") + } }