[SPARK-10593] [SQL] fix resolve output of Generate

The output of Generate should not be resolved as Reference.

Author: Davies Liu <davies@databricks.com>

Closes #8755 from davies/view.

4 files changed, 31 insertions, 2 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
index 02f34cbf58..bf72d47ce1 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
@@ -378,6 +378,22 @@ class Analyzer(
         val newOrdering = resolveSortOrders(ordering, child, throws = false)
         Sort(newOrdering, global, child)
 
+      // A special case for Generate, because the output of Generate should not be resolved by
+      // ResolveReferences. Attributes in the output will be resolved by ResolveGenerate.
+      case g @ Generate(generator, join, outer, qualifier, output, child)
+        if child.resolved && !generator.resolved =>
+        val newG = generator transformUp {
+          case u @ UnresolvedAttribute(nameParts) =>
+            withPosition(u) { child.resolve(nameParts, resolver).getOrElse(u) }
+          case UnresolvedExtractValue(child, fieldExpr) =>
+            ExtractValue(child, fieldExpr, resolver)
+        }
+        if (newG.fastEquals(generator)) {
+          g
+        } else {
+          Generate(newG.asInstanceOf[Generator], join, outer, qualifier, output, child)
+        }
+
       case q: LogicalPlan =>
         logTrace(s"Attempting to resolve ${q.simpleString}")
         q transformExpressionsUp  {
diff --git a/sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/plans/QueryPlan.scala b/sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/plans/QueryPlan.scala
index 55286f9f2f..0ec9f08571 100644
--- a/sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/plans/QueryPlan.scala
+++ b/sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/plans/QueryPlan.scala
@@ -18,7 +18,6 @@
 package org.apache.spark.sql.catalyst.plans
 
 import org.apache.spark.sql.catalyst.expressions.{Attribute, AttributeSet, Expression, VirtualColumn}
-import org.apache.spark.sql.catalyst.plans.logical.LogicalPlan
 import org.apache.spark.sql.catalyst.trees.TreeNode
 import org.apache.spark.sql.types.{DataType, StructType}
 
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 722f69cdca..ae9482c10f 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
@@ -68,7 +68,7 @@ case class Generate(
     generator.resolved &&
       childrenResolved &&
       generator.elementTypes.length == generatorOutput.length &&
-      !generatorOutput.exists(!_.resolved)
+      generatorOutput.forall(_.resolved)
   }
 
   // we don't want the gOutput to be taken as part of the expressions
diff --git a/sql/hive/src/test/scala/org/apache/spark/sql/hive/execution/SQLQuerySuite.scala b/sql/hive/src/test/scala/org/apache/spark/sql/hive/execution/SQLQuerySuite.scala
index 8126d02335..bb02473dd1 100644
--- a/sql/hive/src/test/scala/org/apache/spark/sql/hive/execution/SQLQuerySuite.scala
+++ b/sql/hive/src/test/scala/org/apache/spark/sql/hive/execution/SQLQuerySuite.scala
@@ -1170,4 +1170,18 @@ class SQLQuerySuite extends QueryTest with SQLTestUtils with TestHiveSingleton {
       checkAnswer(sqlContext.table("`db.t`"), df)
     }
   }
+
+  test("SPARK-10593 same column names in lateral view") {
+    val df = sqlContext.sql(
+    """
+      |select
+      |insideLayer2.json as a2
+      |from (select '{"layer1": {"layer2": "text inside layer 2"}}' json) test
+      |lateral view json_tuple(json, 'layer1') insideLayer1 as json
+      |lateral view json_tuple(insideLayer1.json, 'layer2') insideLayer2 as json
+    """.stripMargin
+    )
+
+    checkAnswer(df, Row("text inside layer 2") :: Nil)
+  }
 }