cloud-fan commented on a change in pull request #31273:
URL: https://github.com/apache/spark/pull/31273#discussion_r563510450



##########
File path: 
sql/core/src/main/scala/org/apache/spark/sql/execution/command/views.scala
##########
@@ -558,20 +560,27 @@ object ViewHelper {
       catalog: SessionCatalog, child: LogicalPlan): (Seq[Seq[String]], 
Seq[String]) = {
     def collectTempViews(child: LogicalPlan): Seq[Seq[String]] = {
       child.collect {
-        case UnresolvedRelation(nameParts, _, _) if 
catalog.isTempView(nameParts) =>
-          Seq(nameParts)
-        case plan if !plan.resolved => plan.expressions.flatMap(_.collect {
+        case s @ SubqueryAlias(_, view: View) if view.isTempView =>
+          Seq(s.identifier.qualifier :+ s.identifier.name)
+        case s: SubqueryAlias if s.getTagValue(SUBQUERY_TYPE_TAG).exists(_ == 
"tempView") =>

Review comment:
       I think it's expected. The goal is to make SQL temp view and permanent 
view consistent, and forbidding duplicated column names is consistent.

##########
File path: 
sql/core/src/main/scala/org/apache/spark/sql/execution/command/views.scala
##########
@@ -558,20 +560,27 @@ object ViewHelper {
       catalog: SessionCatalog, child: LogicalPlan): (Seq[Seq[String]], 
Seq[String]) = {
     def collectTempViews(child: LogicalPlan): Seq[Seq[String]] = {
       child.collect {
-        case UnresolvedRelation(nameParts, _, _) if 
catalog.isTempView(nameParts) =>
-          Seq(nameParts)
-        case plan if !plan.resolved => plan.expressions.flatMap(_.collect {
+        case s @ SubqueryAlias(_, view: View) if view.isTempView =>
+          Seq(s.identifier.qualifier :+ s.identifier.name)
+        case s: SubqueryAlias if s.getTagValue(SUBQUERY_TYPE_TAG).exists(_ == 
"tempView") =>

Review comment:
       `Seq(1).map(i => (i, i)).toDF("i", "i").createTempView("tv1")` is not 
SQL temp view (but dataframe temp view), so it's still allowed to have 
duplicated column names.

##########
File path: 
sql/core/src/main/scala/org/apache/spark/sql/execution/command/views.scala
##########
@@ -558,20 +560,27 @@ object ViewHelper {
       catalog: SessionCatalog, child: LogicalPlan): (Seq[Seq[String]], 
Seq[String]) = {
     def collectTempViews(child: LogicalPlan): Seq[Seq[String]] = {
       child.collect {
-        case UnresolvedRelation(nameParts, _, _) if 
catalog.isTempView(nameParts) =>
-          Seq(nameParts)
-        case plan if !plan.resolved => plan.expressions.flatMap(_.collect {
+        case s @ SubqueryAlias(_, view: View) if view.isTempView =>
+          Seq(s.identifier.qualifier :+ s.identifier.name)
+        case s: SubqueryAlias if s.getTagValue(SUBQUERY_TYPE_TAG).exists(_ == 
"tempView") =>

Review comment:
       Shall we not wrap dataframe temp view with `View`? The original goal is 
to make SQL temp view and permanent view consistent.

##########
File path: 
sql/core/src/main/scala/org/apache/spark/sql/execution/command/views.scala
##########
@@ -558,20 +560,27 @@ object ViewHelper {
       catalog: SessionCatalog, child: LogicalPlan): (Seq[Seq[String]], 
Seq[String]) = {
     def collectTempViews(child: LogicalPlan): Seq[Seq[String]] = {
       child.collect {
-        case UnresolvedRelation(nameParts, _, _) if 
catalog.isTempView(nameParts) =>
-          Seq(nameParts)
-        case plan if !plan.resolved => plan.expressions.flatMap(_.collect {
+        case s @ SubqueryAlias(_, view: View) if view.isTempView =>
+          Seq(s.identifier.qualifier :+ s.identifier.name)
+        case s: SubqueryAlias if s.getTagValue(SUBQUERY_TYPE_TAG).exists(_ == 
"tempView") =>

Review comment:
       OK I get your point now. If we need a new logical plan, then it's better 
to reuse `View` with some modification. +1 to make `View.desc` optional and set 
it to None for dataframe temp view. Or we can generate column names for 
dataframe temp view in `View.desc`, like `col1, col2, ...`, to bypass the check.




----------------------------------------------------------------
This is an automated message from the Apache Git Service.
To respond to the message, please log on to GitHub and use the
URL above to go to the specific comment.

For queries about this service, please contact Infrastructure at:
[email protected]



---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]

Reply via email to