From 29fd3104bb92cef1bef9280a64ebc897d7bc0759 Mon Sep 17 00:00:00 2001
From: discord9 <discord9@163.com>
Date: Wed, 15 Jul 2026 19:31:27 +0800
Subject: [PATCH] fix: treat NULL sort merge join filters as unmatched

---
 .../src/joins/sort_merge_join/stream.rs       | 10 +--
 .../src/joins/sort_merge_join/tests.rs        | 84 ++++++++++++++++++-
 2 files changed, 84 insertions(+), 10 deletions(-)

diff --git a/datafusion/physical-plan/src/joins/sort_merge_join/stream.rs b/datafusion/physical-plan/src/joins/sort_merge_join/stream.rs
index 4dcbe1f647990..b1ec5a2fc8621 100644
--- a/datafusion/physical-plan/src/joins/sort_merge_join/stream.rs
+++ b/datafusion/physical-plan/src/joins/sort_merge_join/stream.rs
@@ -1412,16 +1412,10 @@ impl SortMergeJoinStream {
 
                     if needs_deferred_filtering {
                         // Outer/semi/anti/mark joins: push unfiltered batch with metadata for deferred filtering
-                        let mask_to_use = if self.join_type != JoinType::Full {
-                            &mask
-                        } else {
-                            pre_mask
-                        };
-
                         self.joined_record_batches.push_batch_with_filter_metadata(
                             output_batch,
                             &left_indices,
-                            mask_to_use,
+                            &mask,
                             self.streamed_batch_counter.load(Relaxed),
                             self.join_type,
                         );
@@ -1455,7 +1449,7 @@ impl SortMergeJoinStream {
                                     .join_filter_not_matched_map
                                     .get(&buffered_index)
                                     .unwrap_or(&true)
-                                    && !pre_mask.value(i),
+                                    && !mask.value(i),
                             );
                         }
                     }
diff --git a/datafusion/physical-plan/src/joins/sort_merge_join/tests.rs b/datafusion/physical-plan/src/joins/sort_merge_join/tests.rs
index b16ad59abc5b1..c71923f32a4b2 100644
--- a/datafusion/physical-plan/src/joins/sort_merge_join/tests.rs
+++ b/datafusion/physical-plan/src/joins/sort_merge_join/tests.rs
@@ -48,7 +48,7 @@ use datafusion_common::{
     test_util::{batches_to_sort_string, batches_to_string},
 };
 use datafusion_common::{
-    JoinType, NullEquality, Result, assert_batches_eq, assert_contains,
+    JoinType, NullEquality, Result, ScalarValue, assert_batches_eq, assert_contains,
 };
 use datafusion_common_runtime::JoinSet;
 use datafusion_execution::config::SessionConfig;
@@ -56,7 +56,7 @@ use datafusion_execution::disk_manager::{DiskManagerBuilder, DiskManagerMode};
 use datafusion_execution::runtime_env::RuntimeEnvBuilder;
 use datafusion_execution::{SendableRecordBatchStream, TaskContext};
 use datafusion_expr::Operator;
-use datafusion_physical_expr::expressions::BinaryExpr;
+use datafusion_physical_expr::expressions::{BinaryExpr, Literal};
 use futures::StreamExt;
 use insta::{allow_duplicates, assert_snapshot};
 use itertools::Itertools;
@@ -2040,6 +2040,86 @@ async fn join_full_multiple_batches() -> Result<()> {
     Ok(())
 }
 
+#[tokio::test]
+async fn join_full_null_filter_result() -> Result<()> {
+    let left = build_table_two_cols(
+        ("a1", &vec![1, 1, 2, 2, 3, 3]),
+        ("b1", &vec![1, 2, 1, 2, 1, 2]),
+    );
+    let right = build_table_from_batches(vec![RecordBatch::try_new(
+        Arc::new(Schema::new(vec![
+            Field::new("a2", DataType::Int32, false),
+            Field::new("b2", DataType::Int32, true),
+        ])),
+        vec![
+            Arc::new(Int32Array::from(vec![1, 2])),
+            Arc::new(Int32Array::from(vec![None, Some(2)])),
+        ],
+    )?]);
+    let on = vec![(
+        Arc::new(Column::new_with_schema("a1", &left.schema())?) as _,
+        Arc::new(Column::new_with_schema("a2", &right.schema())?) as _,
+    )];
+    let filter = JoinFilter::new(
+        Arc::new(BinaryExpr::new(
+            Arc::new(BinaryExpr::new(
+                Arc::new(Column::new("b1", 0)),
+                Operator::Lt,
+                Arc::new(BinaryExpr::new(
+                    Arc::new(Column::new("b2", 1)),
+                    Operator::Plus,
+                    Arc::new(Literal::new(ScalarValue::Int32(Some(1)))),
+                )),
+            )),
+            Operator::And,
+            Arc::new(BinaryExpr::new(
+                Arc::new(Column::new("b1", 0)),
+                Operator::Lt,
+                Arc::new(BinaryExpr::new(
+                    Arc::new(Column::new("a2", 2)),
+                    Operator::Plus,
+                    Arc::new(Literal::new(ScalarValue::Int32(Some(1)))),
+                )),
+            )),
+        )),
+        vec![
+            ColumnIndex {
+                index: 1,
+                side: JoinSide::Left,
+            },
+            ColumnIndex {
+                index: 1,
+                side: JoinSide::Right,
+            },
+            ColumnIndex {
+                index: 0,
+                side: JoinSide::Right,
+            },
+        ],
+        Arc::new(Schema::new(vec![
+            Field::new("b1", DataType::Int32, true),
+            Field::new("b2", DataType::Int32, true),
+            Field::new("a2", DataType::Int32, true),
+        ])),
+    );
+
+    let (_, batches) = join_collect_with_filter(left, right, on, filter, Full).await?;
+    assert_snapshot!(batches_to_sort_string(&batches), @r"
+    +----+----+----+----+
+    | a1 | b1 | a2 | b2 |
+    +----+----+----+----+
+    |    |    | 1  |    |
+    | 1  | 1  |    |    |
+    | 1  | 2  |    |    |
+    | 2  | 1  | 2  | 2  |
+    | 2  | 2  | 2  | 2  |
+    | 3  | 1  |    |    |
+    | 3  | 2  |    |    |
+    +----+----+----+----+
+    ");
+    Ok(())
+}
+
 #[tokio::test]
 async fn overallocation_single_batch_no_spill() -> Result<()> {
     let left = build_table(