This is an automated email from the ASF dual-hosted git repository.
wenchen pushed a commit to branch branch-3.1
in repository https://gitbox.apache.org/repos/asf/spark.git
The following commit(s) were added to refs/heads/branch-3.1 by this push:
new e1a549c [SPARK-36339][SQL][3.0] References to grouping that not part
of aggregation should be replaced
e1a549c is described below
commit e1a549c721024f0ee3a94c02db1cdb250f9c258d
Author: gaoyajun02 <[email protected]>
AuthorDate: Mon Aug 9 16:53:27 2021 +0800
[SPARK-36339][SQL][3.0] References to grouping that not part of aggregation
should be replaced
Currently, references to grouping sets are reported as errors after
aggregated expressions, e.g.
```
SELECT count(name) c, name
FROM VALUES ('Alice'), ('Bob') people(name)
GROUP BY name GROUPING SETS(name);
```
Error in query: expression 'people.`name`' is neither present in the group
by, nor is it an aggregate function. Add to group by or wrap in first() (or
first_value) if you don't care which value you get.;;
Fix the map anonymous function in the constructAggregateExprs function does
not use underscores to avoid
No
Unit tests.
Closes #33669 from gaoyajun02/branch-3.0.
Authored-by: gaoyajun02 <[email protected]>
Signed-off-by: Wenchen Fan <[email protected]>
(cherry picked from commit e10cc78db4aeacb6e8b16ef19679d8aac82601ea)
Signed-off-by: Wenchen Fan <[email protected]>
---
.../org/apache/spark/sql/catalyst/analysis/Analyzer.scala | 4 ++--
.../src/test/scala/org/apache/spark/sql/SQLQuerySuite.scala | 13 +++++++++++++
2 files changed, 15 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 600a5af..a9ff6ee 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
@@ -539,7 +539,7 @@ class Analyzer(override val catalogManager: CatalogManager)
aggregations: Seq[NamedExpression],
groupByAliases: Seq[Alias],
groupingAttrs: Seq[Expression],
- gid: Attribute): Seq[NamedExpression] = aggregations.map {
+ gid: Attribute): Seq[NamedExpression] = aggregations.map { agg =>
// collect all the found AggregateExpression, so we can check an
expression is part of
// any AggregateExpression or not.
val aggsBuffer = ArrayBuffer[Expression]()
@@ -547,7 +547,7 @@ class Analyzer(override val catalogManager: CatalogManager)
def isPartOfAggregation(e: Expression): Boolean = {
aggsBuffer.exists(a => a.find(_ eq e).isDefined)
}
- replaceGroupingFunc(_, groupByExprs, gid).transformDown {
+ replaceGroupingFunc(agg, groupByExprs, gid).transformDown {
// AggregateExpression should be computed on the unmodified value of
its argument
// expressions, so we should not replace any references to grouping
expression
// inside it.
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
index 903db94..3d66f61 100644
--- a/sql/core/src/test/scala/org/apache/spark/sql/SQLQuerySuite.scala
+++ b/sql/core/src/test/scala/org/apache/spark/sql/SQLQuerySuite.scala
@@ -3472,6 +3472,19 @@ class SQLQuerySuite extends QueryTest with
SharedSparkSession with AdaptiveSpark
}
}
+ test("SPARK-36339: References to grouping attributes should be replaced") {
+ withTempView("t") {
+ Seq("a", "a", "b").toDF("x").createOrReplaceTempView("t")
+ checkAnswer(
+ sql(
+ """
+ |select count(x) c, x from t
+ |group by x grouping sets(x)
+ """.stripMargin),
+ Seq(Row(2, "a"), Row(1, "b")))
+ }
+ }
+
test("SPARK-31166: UNION map<null, null> and other maps should not fail") {
checkAnswer(
sql("(SELECT map()) UNION ALL (SELECT map(1, 2))"),
---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]
