Skip to content

[SPARK-22350][SQL] select grouping__id from subquery #19573

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Closed
jinxing64 wants to merge 2 commits into from
Closed

[SPARK-22350][SQL] select grouping__id from subquery #19573

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
c0ecbee
select grouping__id from subquery
Oct 24, 2017
a593442
Add alias only when it's grouping analytics operator
Nov 8, 2017
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
12 changes: 10 additions & 2 deletions sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/analysis/Analyzer.scala
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -1161,13 +1161,21 @@ class Analyzer(
* Replaces [[UnresolvedFunction]]s with concrete [[Expression]]s.
*/
object ResolveFunctions extends Rule[LogicalPlan] {
private def isGroupingAnalyticsOp(plan: LogicalPlan): Boolean = plan match {
case Aggregate(Seq(c @ Cube(groupByExprs)), _, _) => true
case Aggregate(Seq(r @ Rollup(groupByExprs)), _, _) => true
case x: GroupingSets => true
case _ => false
}

def apply(plan: LogicalPlan): LogicalPlan = plan.resolveOperators {
case q: LogicalPlan =>
q transformExpressions {
case u if !u.childrenResolved => u // Skip until children are resolved.
case u: UnresolvedAttribute if resolver(u.name, VirtualColumn.hiveGroupingIdName) =>
case u: UnresolvedAttribute
if resolver(u.name, VirtualColumn.groupingIdName) && isGroupingAnalyticsOp(q) =>
withPosition(u) {
Alias(GroupingID(Nil), VirtualColumn.hiveGroupingIdName)()
Alias(GroupingID(Nil), VirtualColumn.groupingIdName)()
}
case u @ UnresolvedGenerator(name, children) =>
withPosition(u) {
Expand Down
4 changes: 1 addition & 3 deletions sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/namedExpressions.scala
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -367,8 +367,6 @@ case class OuterReference(e: NamedExpression)
}

object VirtualColumn {
// The attribute name used by Hive, which has different result than Spark, deprecated.
val hiveGroupingIdName: String = "grouping__id"
val groupingIdName: String = "spark_grouping_id"
val groupingIdName: String = "grouping__id"
val groupingIdAttribute: UnresolvedAttribute = UnresolvedAttribute(groupingIdName)
}
3 changes: 1 addition & 2 deletions ...src/test/scala/org/apache/spark/sql/catalyst/analysis/ResolveGroupingAnalyticsSuite.scala
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -32,8 +32,7 @@ class ResolveGroupingAnalyticsSuite extends AnalysisTest {
lazy val unresolved_a = UnresolvedAttribute("a")
lazy val unresolved_b = UnresolvedAttribute("b")
lazy val unresolved_c = UnresolvedAttribute("c")
lazy val gid = 'spark_grouping_id.int.withNullability(false)
lazy val hive_gid = 'grouping__id.int.withNullability(false)
lazy val gid = 'grouping__id.int.withNullability(false)
lazy val grouping_a = Cast(ShiftRight(gid, 1) & 1, ByteType, Option(TimeZone.getDefault().getID))
lazy val nulInt = Literal(null, IntegerType)
lazy val nulStr = Literal(null, StringType)
Expand Down
21 changes: 21 additions & 0 deletions sql/hive/src/test/scala/org/apache/spark/sql/hive/execution/SQLQuerySuite.scala
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -1497,6 +1497,27 @@ class SQLQuerySuite extends QueryTest with SQLTestUtils with TestHiveSingleton {
}
}

test("select grouping__id from subquery.") {
checkAnswer(
sql(
"""
|SELECT cnt, k2, k3, grouping__id
|FROM
| (SELECT count(*) as cnt, k2, k3, grouping__id
Copy link
Member

@gatorsmile gatorsmile Oct 27, 2017

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more. 

SELECT cnt, k2, k3, alias_grouping__id
FROM
  (SELECT count(*) as cnt, k2, k3, grouping__id as alias_grouping__id
  FROM (SELECT key, key%2 as k2 , key%3 as k3 FROM src) t1
  GROUP BY k2, k3
  GROUPING SETS(k2, k3)) t2
ORDER BY alias_grouping__id, k2, k3

This is the workaround.

| FROM (SELECT key, key%2 as k2 , key%3 as k3 FROM src) t1
| GROUP BY k2, k3
| GROUPING SETS(k2, k3)) t2
|ORDER BY grouping__id, k2, k3
""".stripMargin),
Seq(
(247, 0, null, 1),
(253, 1, null, 1),
(169, null, 0, 2),
(165, null, 1, 2),
(166, null, 2, 2)
).map(i => Row(i._1, i._2, i._3, i._4)))
}

ignore("SPARK-10562: partition by column with mixed case name") {
withTable("tbl10562") {
val df = Seq(2012 -> "a").toDF("Year", "val")
Expand Down