[SPARK-32237][SQL][3.0] Resolve hint in CTE

apache · Jul 23, 2020 · b5be044 · b5be044
1 parent ad9e7a2
commit b5be044
Show file tree

Hide file tree

Showing 3 changed files with 41 additions and 6 deletions.
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
@@ -200,16 +200,16 @@ class Analyzer(
   val postHocResolutionRules: Seq[Rule[LogicalPlan]] = Nil
 
   lazy val batches: Seq[Batch] = Seq(
-    Batch("Hints", fixedPoint,
-      new ResolveHints.ResolveJoinStrategyHints(conf),
-      new ResolveHints.ResolveCoalesceHints(conf)),
-    Batch("Simple Sanity Check", Once,
-      LookupFunctions),
     Batch("Substitution", fixedPoint,
       CTESubstitution,
       WindowsSubstitution,
       EliminateUnions,
       new SubstituteUnresolvedOrdinals(conf)),
+    Batch("Hints", fixedPoint,
+      new ResolveHints.ResolveJoinStrategyHints(conf),
+      new ResolveHints.ResolveCoalesceHints(conf)),
+    Batch("Simple Sanity Check", Once,
+      LookupFunctions),
     Batch("Resolution", fixedPoint,
       ResolveTableValuedFunctions ::
       ResolveNamespace(catalogManager) ::

diff --git a/sql/catalyst/src/test/scala/org/apache/spark/sql/catalyst/analysis/AnalysisSuite.scala b/sql/catalyst/src/test/scala/org/apache/spark/sql/catalyst/analysis/AnalysisSuite.scala
@@ -25,7 +25,7 @@ import org.apache.log4j.Level
 import org.scalatest.Matchers
 
 import org.apache.spark.api.python.PythonEvalType
-import org.apache.spark.sql.catalyst.TableIdentifier
+import org.apache.spark.sql.catalyst.{AliasIdentifier, TableIdentifier}
 import org.apache.spark.sql.catalyst.catalog.{CatalogStorageFormat, CatalogTable, CatalogTableType, InMemoryCatalog, SessionCatalog}
 import org.apache.spark.sql.catalyst.dsl.expressions._
 import org.apache.spark.sql.catalyst.dsl.plans._
@@ -879,4 +879,27 @@ class AnalysisSuite extends AnalysisTest with Matchers {
       Seq("Intersect can only be performed on tables with the compatible column types. " +
         "timestamp <> double at the second column of the second table"))
   }
+
+  test("SPARK-32237: Hint in CTE") {
+    val plan = With(
+      Project(
+        Seq(UnresolvedAttribute("cte.a")),
+        UnresolvedRelation(TableIdentifier("cte"))
+      ),
+      Seq(
+        (
+          "cte",
+          SubqueryAlias(
+            AliasIdentifier("cte"),
+            UnresolvedHint(
+              "REPARTITION",
+              Seq(Literal(3)),
+              Project(testRelation.output, testRelation)
+            )
+          )
+        )
+      )
+    )
+    assertAnalysisSuccess(plan)
+  }
 }
diff --git a/sql/core/src/test/scala/org/apache/spark/sql/SQLQuerySuite.scala b/sql/core/src/test/scala/org/apache/spark/sql/SQLQuerySuite.scala
@@ -3467,6 +3467,18 @@ class SQLQuerySuite extends QueryTest with SharedSparkSession with AdaptiveSpark
             |""".stripMargin), Row(1))
     }
   }
+
+  test("SPARK-32237: Hint in CTE") {
+    withTable("t") {
+      sql("CREATE TABLE t USING PARQUET AS SELECT 1 AS id")
+      checkAnswer(
+        sql(s"""
+               |WITH cte AS (SELECT /*+ REPARTITION(3) */ * FROM t)
+               |SELECT * FROM cte
+        """.stripMargin),
+        Row(1) :: Nil)
+    }
+  }
 }
 
 case class Foo(bar: Option[String])