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

peter-toth 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 84db3edbee2a [SPARK-60702][SQL][FOLLOWUP] Expect no bloom filter from 
a non-deterministic creation side without DPP
84db3edbee2a is described below

commit 84db3edbee2abc76d2892c3cc980bbdaaf954aa9
Author: Peter Toth <[email protected]>
AuthorDate: Sat Nov 7 19:16:00 2026 +0100

    [SPARK-60702][SQL][FOLLOWUP] Expect no bloom filter from a 
non-deterministic creation side without DPP
    
    ### What changes were proposed in this pull request?
    
    This fixes two tests of #59916 that fail on master. Both check with DPP off 
that master still adds the bloom filter from a non-deterministic creation side. 
SPARK-60808 (#60176), merged before #59916, keeps that bloom filter out now, so 
the tests now expect none:
    - "SPARK-60702: do not add bloom filter if the creation side that the 
subquery reads is not deterministic";
    - "SPARK-60702: do not add bloom filter whose creation side is a 
non-deterministic pruned side".
    
    ### Why are the changes needed?
    
    `InjectRuntimeFilterSuite` fails on master. #59916 was tested on a base 
without SPARK-60808.
    
    ### Does this PR introduce _any_ user-facing change?
    
    No. Test only.
    
    ### How was this patch tested?
    
    `InjectRuntimeFilterSuite` passes, 62 of 62. On master `da165c1c658` the 
two tests fail with `List() had size 0 instead of expected size 1`.
    
    ### Was this patch authored or co-authored using generative AI tooling?
    
    Generated-by: Claude Code with Claude Opus 5.5
    
    Closes #60206 from peter-toth/SPARK-60702-followup-tests-after-60808.
    
    Authored-by: Peter Toth <[email protected]>
    Signed-off-by: Peter Toth <[email protected]>
    
    
    skip-checks: true
---
 .../scala/org/apache/spark/sql/InjectRuntimeFilterSuite.scala     | 8 ++++----
 1 file changed, 4 insertions(+), 4 deletions(-)

diff --git 
a/sql/core/src/test/scala/org/apache/spark/sql/InjectRuntimeFilterSuite.scala 
b/sql/core/src/test/scala/org/apache/spark/sql/InjectRuntimeFilterSuite.scala
index 07c6e66d8c6c..4e5541adaf1c 100644
--- 
a/sql/core/src/test/scala/org/apache/spark/sql/InjectRuntimeFilterSuite.scala
+++ 
b/sql/core/src/test/scala/org/apache/spark/sql/InjectRuntimeFilterSuite.scala
@@ -1352,11 +1352,11 @@ class InjectRuntimeFilterSuite extends 
SharedSparkSession
     "deterministic") {
     // The build plan of the DPP filter would be the creation side of the 
bloom filter. A bloom
     // filter would evaluate it again, apart from the join, and could drop 
rows (SPARK-60808).
-    // Cleanup drops such a DPP filter.
+    // Cleanup drops such a DPP filter. Without DPP, SPARK-60808 keeps the 
bloom filter out too.
     val query = "select * from bf5part join (select * from bf2 where a2 = 36 
and " +
       "cast(reflect('java.lang.Math', 'random') as double) < 2.0) d on 
bf5part.f5 = d.c2"
     withDppTestConf() {
-      assertBloomFilterWithoutDpp(query)
+      assertBloomFilterWithoutDpp(query, 0)
       assert(bloomFilterKeys(query).isEmpty)
       assert(dynamicPruningFilters(query).isEmpty)
     }
@@ -1366,7 +1366,7 @@ class InjectRuntimeFilterSuite extends SharedSparkSession
     "side") {
     // Nothing broadcasts `f`, the deterministic build plan of the DPP filter 
on `d.k`, so that
     // filter is dropped. `d` is too small to take a bloom filter, so `f` 
would take one, built
-    // from `d`, which is not deterministic (SPARK-60808).
+    // from `d`, which is not deterministic (SPARK-60808). Without DPP, 
SPARK-60808 keeps it out.
     withTable("ndd", "ndf") {
       spark.range(40).selectExpr("id as k", "id as 
w").write.partitionBy("k").saveAsTable("ndd")
       spark.range(40000).selectExpr("id % 40 as k", "id as 
v").write.saveAsTable("ndf")
@@ -1380,7 +1380,7 @@ class InjectRuntimeFilterSuite extends SharedSparkSession
           
SQLConf.RUNTIME_BLOOM_FILTER_APPLICATION_SIDE_SCAN_SIZE_THRESHOLD.key ->
             (nddSize + 1).toString,
           SQLConf.ADAPTIVE_EXECUTION_ENABLED.key -> "false") {
-        assertBloomFilterWithoutDpp(query)
+        assertBloomFilterWithoutDpp(query, 0)
         assert(bloomFilterKeys(query).isEmpty)
       }
     }


---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]

Reply via email to