You are viewing a plain text version of this content. The canonical link for it is here.
Posted to commits@datafusion.apache.org by gi...@apache.org on 2026/10/08 16:03:42 UTC

(datafusion-comet) 01/01: test: enable SPARK-57298 collect_set tests (#5228)

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

github-merge-queue[bot] pushed a commit to branch gh-readonly-queue/main/pr-5228-27b388f6202fbc5303b283843396e55c956330da
in repository https://gitbox.apache.org/repos/asf/datafusion-comet.git

commit 7a1c042f37c0a4e0cad97ba16aaf558ad30dcb69
Author: Peter Lee <pe...@gmail.com>
AuthorDate: Thu Oct 8 16:03:17 2026 +0000

    test: enable SPARK-57298 collect_set tests (#5228)
---
 dev/diffs/4.2.0.diff | 19 ++++---------------
 1 file changed, 4 insertions(+), 15 deletions(-)

diff --git a/dev/diffs/4.2.0.diff b/dev/diffs/4.2.0.diff
index 3335dfb371..e53ec96c3f 100644
--- a/dev/diffs/4.2.0.diff
+++ b/dev/diffs/4.2.0.diff
@@ -464,7 +464,7 @@ index 085dbcd8046..3090d321b6c 100644
  
        withTempView("t0", "t1", "t2") {
 diff --git a/sql/core/src/test/scala/org/apache/spark/sql/DataFrameAggregateSuite.scala b/sql/core/src/test/scala/org/apache/spark/sql/DataFrameAggregateSuite.scala
-index 5b8154d2900..eb3de47f387 100644
+index 5b8154d2900..d42374b127f 100644
 --- a/sql/core/src/test/scala/org/apache/spark/sql/DataFrameAggregateSuite.scala
 +++ b/sql/core/src/test/scala/org/apache/spark/sql/DataFrameAggregateSuite.scala
 @@ -30,8 +30,9 @@ import org.apache.spark.sql.catalyst.util.AUTO_GENERATED_ALIAS
@@ -478,18 +478,7 @@ index 5b8154d2900..eb3de47f387 100644
  import org.apache.spark.sql.expressions.Window
  import org.apache.spark.sql.functions._
  import org.apache.spark.sql.internal.SQLConf
-@@ -667,7 +668,9 @@ class DataFrameAggregateSuite extends SharedSparkSession
-       df.selectExpr("sort_array(collect_set(b) RESPECT NULLS)"), Seq(Row(Seq(null, 2))))
-   }
- 
--  test("SPARK-57298: collect_set normalizes NaN and -0.0 for floating-point types") {
-+  test("SPARK-57298: collect_set normalizes NaN and -0.0 for floating-point types",
-+    // Comet's native collect_set does not yet normalize NaN / -0.0.
-+    IgnoreComet("https://github.com/apache/datafusion-comet/issues/4966")) {
-     checkAnswer(
-       sql("SELECT collect_set(v) FROM VALUES (double('NaN')), (double('NaN')) AS t(v)"),
-       Row(Seq(Double.NaN)))
-@@ -932,7 +935,9 @@ class DataFrameAggregateSuite extends SharedSparkSession
+@@ -932,7 +933,9 @@ class DataFrameAggregateSuite extends SharedSparkSession
              case _ => false
            }.isDefined)
          } else {
@@ -500,7 +489,7 @@ index 5b8154d2900..eb3de47f387 100644
          }
  
          // test case for ObjectHashAggregate and SortAggregate
-@@ -941,7 +946,8 @@ class DataFrameAggregateSuite extends SharedSparkSession
+@@ -941,7 +944,8 @@ class DataFrameAggregateSuite extends SharedSparkSession
          val objHashAggOrSortAggPlan =
            stripAQEPlan(objHashAggOrSortAggDF.queryExecution.executedPlan)
          if (useObjectHashAgg) {
@@ -510,7 +499,7 @@ index 5b8154d2900..eb3de47f387 100644
          } else {
            assert(objHashAggOrSortAggPlan.isInstanceOf[SortAggregateExec])
          }
-@@ -991,12 +997,12 @@ class DataFrameAggregateSuite extends SharedSparkSession
+@@ -991,12 +995,12 @@ class DataFrameAggregateSuite extends SharedSparkSession
        assert(sortAggPlans.isEmpty)
  
        val objHashAggPlans = collect(aggPlan) {


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