This is an automated email from the ASF dual-hosted git repository.
maxgekk pushed a commit to branch master
in repository https://gitbox.apache.org/repos/asf/spark.git
The following commit(s) were added to refs/heads/master by this push:
new db8468105bdb [SPARK-49659][SQL] Add a nice user-facing error for
scalar subqueries inside VALUES clause
db8468105bdb is described below
commit db8468105bdbd0b6dd8722e169fe39b13a3ee44f
Author: Vladimir Golubev <[email protected]>
AuthorDate: Tue Sep 17 08:15:23 2024 +0200
[SPARK-49659][SQL] Add a nice user-facing error for scalar subqueries
inside VALUES clause
### What changes were proposed in this pull request?
Introduce a new `SCALAR_SUBQUERY_IN_VALUES` error, since we don't support
scalar subqueries in the VALUES clause for now.
### Why are the changes needed?
To make Spark user experience nicer.
### Does this PR introduce _any_ user-facing change?
Yes, the exception type/message will be more descriptive
### How was this patch tested?
- New unit test
- Existing unit tests
### Was this patch authored or co-authored using generative AI tooling?
No
Closes #48118 from
vladimirg-db/vladimirg-db/introduce-user-facing-exception-for-inline-tables-with-scalar-subqueries.
Authored-by: Vladimir Golubev <[email protected]>
Signed-off-by: Max Gekk <[email protected]>
---
.../utils/src/main/resources/error/error-conditions.json | 5 +++++
.../spark/sql/catalyst/analysis/CheckAnalysis.scala | 12 ++++++++++++
.../apache/spark/sql/errors/QueryCompilationErrors.scala | 8 ++++++++
.../test/scala/org/apache/spark/sql/SQLQuerySuite.scala | 15 +++++++++++++++
4 files changed, 40 insertions(+)
diff --git a/common/utils/src/main/resources/error/error-conditions.json
b/common/utils/src/main/resources/error/error-conditions.json
index 38472f44fb59..57b3d33741e9 100644
--- a/common/utils/src/main/resources/error/error-conditions.json
+++ b/common/utils/src/main/resources/error/error-conditions.json
@@ -5330,6 +5330,11 @@
"<treeNode>"
]
},
+ "SCALAR_SUBQUERY_IN_VALUES" : {
+ "message" : [
+ "Scalar subqueries in the VALUES clause."
+ ]
+ },
"UNSUPPORTED_CORRELATED_EXPRESSION_IN_JOIN_CONDITION" : {
"message" : [
"Correlated subqueries in the join predicate cannot reference both
join inputs:",
diff --git
a/sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/analysis/CheckAnalysis.scala
b/sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/analysis/CheckAnalysis.scala
index a9fbe548ba39..752ff49e1f90 100644
---
a/sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/analysis/CheckAnalysis.scala
+++
b/sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/analysis/CheckAnalysis.scala
@@ -250,6 +250,9 @@ trait CheckAnalysis extends PredicateHelper with
LookupCatalog with QueryErrorsB
context = u.origin.getQueryContext,
summary = u.origin.context.summary)
+ case u: UnresolvedInlineTable if
unresolvedInlineTableContainsScalarSubquery(u) =>
+ throw QueryCompilationErrors.inlineTableContainsScalarSubquery(u)
+
case command: V2PartitionCommand =>
command.table match {
case r @ ResolvedTable(_, _, table, _) => table match {
@@ -1559,6 +1562,15 @@ trait CheckAnalysis extends PredicateHelper with
LookupCatalog with QueryErrorsB
case _ =>
}
}
+
+ private def unresolvedInlineTableContainsScalarSubquery(
+ unresolvedInlineTable: UnresolvedInlineTable) = {
+ unresolvedInlineTable.rows.exists { row =>
+ row.exists { expression =>
+ expression.exists(_.isInstanceOf[ScalarSubquery])
+ }
+ }
+ }
}
// a heap of the preempted error that only keeps the top priority element,
representing the sole
diff --git
a/sql/catalyst/src/main/scala/org/apache/spark/sql/errors/QueryCompilationErrors.scala
b/sql/catalyst/src/main/scala/org/apache/spark/sql/errors/QueryCompilationErrors.scala
index f1f8be3d1575..f268ef85ef1d 100644
---
a/sql/catalyst/src/main/scala/org/apache/spark/sql/errors/QueryCompilationErrors.scala
+++
b/sql/catalyst/src/main/scala/org/apache/spark/sql/errors/QueryCompilationErrors.scala
@@ -4112,4 +4112,12 @@ private[sql] object QueryCompilationErrors extends
QueryErrorsBase with Compilat
"expr" -> expr.toString),
origin = expr.origin)
}
+
+ def inlineTableContainsScalarSubquery(inlineTable: LogicalPlan): Throwable =
{
+ new AnalysisException(
+ errorClass =
"UNSUPPORTED_SUBQUERY_EXPRESSION_CATEGORY.SCALAR_SUBQUERY_IN_VALUES",
+ messageParameters = Map.empty,
+ origin = inlineTable.origin
+ )
+ }
}
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 b7d0039446f3..9beceda26379 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
@@ -4909,6 +4909,21 @@ class SQLQuerySuite extends QueryTest with
SharedSparkSession with AdaptiveSpark
)
}
}
+
+ test("SPARK-49659: Unsupported scalar subqueries in VALUES") {
+ checkError(
+ exception = intercept[AnalysisException](
+ sql("SELECT * FROM VALUES ((SELECT 1) + (SELECT 2))")
+ ),
+ condition =
"UNSUPPORTED_SUBQUERY_EXPRESSION_CATEGORY.SCALAR_SUBQUERY_IN_VALUES",
+ parameters = Map(),
+ context = ExpectedContext(
+ fragment = "VALUES ((SELECT 1) + (SELECT 2))",
+ start = 14,
+ stop = 45
+ )
+ )
+ }
}
case class Foo(bar: Option[String])
---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]
