(spark) branch branch-4.1 updated: [SPARK-54336][SQL] Fix `BloomFilterMightContain` input type check with `ScalarSubqueryReference`

[do...@apache.org]

This is an automated email from the ASF dual-hosted git repository.

dongjoon pushed a commit to branch branch-4.1
in repository https://gitbox.apache.org/repos/asf/spark.git


The following commit(s) were added to refs/heads/branch-4.1 by this push:
     new 0c0390468ce3 [SPARK-54336][SQL] Fix `BloomFilterMightContain` input type check with `ScalarSubqueryReference`
0c0390468ce3 is described below

commit 0c0390468ce3d73f54a04f15885c99f39e4847f2
Author: Peter Toth <pe...@gmail.com>
AuthorDate: Thu Nov 13 12:04:34 2025 -0800

    [SPARK-54336][SQL] Fix `BloomFilterMightContain` input type check with `ScalarSubqueryReference`
    
    ### What changes were proposed in this pull request?
    
    This PR fixes the case when a scalar subquery with a `BloomFilterMightContain` expression is added to `PlanMerger`, but its `bloomFilterExpression` contains a merged scalar subquery which was replaced to a `ScalarSubqueryReference` before.
    In this case `BloomFilterMightContain` was unresolved due to its `checkInputDataTypes()` failure.
    
    ### Why are the changes needed?
    To
    
    ### Does this PR introduce _any_ user-facing change?
    
    No.
    
    ### How was this patch tested?
    
    New UT.
    
    ### Was this patch authored or co-authored using generative AI tooling?
    
    No.
    
    Closes #53038 from peter-toth/SPARK-54336-fix-bloomfiltermightcontain-type-check.
    
    Authored-by: Peter Toth <pe...@gmail.com>
    Signed-off-by: Dongjoon Hyun <do...@apache.org>
    (cherry picked from commit 06b3d4c4e7166c3107c7cc95ff0da2d9f256eabd)
    Signed-off-by: Dongjoon Hyun <do...@apache.org>
---
 .../expressions/BloomFilterMightContain.scala         |  2 ++
 .../spark/sql/BloomFilterAggregateQuerySuite.scala    | 19 +++++++++++++++++++
 2 files changed, 21 insertions(+)

diff --git a/sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/BloomFilterMightContain.scala b/sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/BloomFilterMightContain.scala
index 784bea899c4c..e3ff7c5f05f0 100644
--- a/sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/BloomFilterMightContain.scala
+++ b/sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/BloomFilterMightContain.scala
@@ -23,6 +23,7 @@ import org.apache.spark.sql.catalyst.analysis.TypeCheckResult.DataTypeMismatch
 import org.apache.spark.sql.catalyst.expressions.Cast.{toSQLExpr, toSQLId, toSQLType}
 import org.apache.spark.sql.catalyst.expressions.codegen.{CodegenContext, CodeGenerator, ExprCode, JavaCode, TrueLiteral}
 import org.apache.spark.sql.catalyst.expressions.codegen.Block.BlockHelper
+import org.apache.spark.sql.catalyst.optimizer.ScalarSubqueryReference
 import org.apache.spark.sql.catalyst.trees.TreePattern.OUTER_REFERENCE
 import org.apache.spark.sql.types._
 import org.apache.spark.util.sketch.BloomFilter
@@ -58,6 +59,7 @@ case class BloomFilterMightContain(
           case GetStructField(subquery: PlanExpression[_], _, _)
             if !subquery.containsPattern(OUTER_REFERENCE) =>
             TypeCheckResult.TypeCheckSuccess
+          case _: ScalarSubqueryReference => TypeCheckResult.TypeCheckSuccess
           case _ =>
             DataTypeMismatch(
               errorSubClass = "BLOOM_FILTER_BINARY_OP_WRONG_TYPE",
diff --git a/sql/core/src/test/scala/org/apache/spark/sql/BloomFilterAggregateQuerySuite.scala b/sql/core/src/test/scala/org/apache/spark/sql/BloomFilterAggregateQuerySuite.scala
index fb279b1db6fc..0a8e31b6bac4 100644
--- a/sql/core/src/test/scala/org/apache/spark/sql/BloomFilterAggregateQuerySuite.scala
+++ b/sql/core/src/test/scala/org/apache/spark/sql/BloomFilterAggregateQuerySuite.scala
@@ -367,4 +367,23 @@ class BloomFilterAggregateQuerySuite extends QueryTest with SharedSparkSession {
     checkNumBits(100, 2935)
     checkNumBits(1, 38)
   }
+
+  test("SPARK-54336: Fix BloomFilterMightContain type check with ScalarSubqueryReference") {
+    val table = "bloom_filter_test"
+    withTempView(table) {
+      Seq(0).toDF("col").createOrReplaceTempView(table)
+      val df = sql(
+        s"""
+          |SELECT
+          |  (SELECT
+          |    first(might_contain(
+          |      (SELECT bloom_filter_agg(col) FROM $table),
+          |      0L
+          |    ))
+          |  FROM $table)
+          |FROM $table
+          |""".stripMargin)
+      checkAnswer(df, Row(true))
+    }
+  }
 }


---------------------------------------------------------------------
To unsubscribe, e-mail: commits-unsubscribe@spark.apache.org
For additional commands, e-mail: commits-help@spark.apache.org