Fix: Align sort_merge_join filter output with join schema to fix right-anti panic (#18800)

## Which issue does this PR close?

<!--
We generally require a GitHub issue to be filed for all bug fixes and
enhancements and this helps us generate change logs for our releases.
You can link an issue to this PR using the GitHub syntax. For example
`Closes #123` indicates that this PR will close issue #123.
-->

- Closes #18787.

## Rationale for this change

Sort-merge joins assumed both inputs had the same width when applying
filter results. With different column counts (like right-anti joins) we
built batches that no longer matched the output schema, so Arrow
panicked during concat_batches.

<!--
Why are you proposing this change? If this is already explained clearly
in the issue then this section is not needed.
Explaining clearly why changes are proposed helps reviewers understand
your changes and offer better suggestions for fixes.
-->

## What changes are included in this PR?

- Fix the null-row and filtered-row builders in SortMergeJoinStream to
slice the streamed vs buffered columns using the correct widths, keeping
every batch consistent with self.schema.
- Merge the semi/anti projection branch so it always projects the
streamed-side columns expected in the output.

<!--
There is no need to duplicate the description in the issue here but it
is sometimes worth providing a summary of the individual changes in this
PR.
-->

## Are these changes tested?

Manual testing and ran previous tests. 

<img width="1092" height="552" alt="Screenshot 2025-11-18 at 5 04 20 PM"
src="https://github.com/user-attachments/assets/1272a368-f694-4d7b-907b-b605a4996419"
/>

<!--
We typically require tests for all PRs in order to:
1. Prevent the code from being accidentally broken by subsequent changes
2. Serve as another way to document the expected behavior of the code

If tests are not included in your PR, please explain why (for example,
are they covered by existing tests)?
-->

## Are there any user-facing changes?

<!--
If there are user-facing changes then we may require documentation to be
updated before approving the PR.
-->

<!--
If there are any breaking changes to public APIs, please add the `api
change` label.
-->

---------

Co-authored-by: Raz Luvaton <16746759+rluvaton@users.noreply.github.com>

Author: kumarUjjawal

datafusion/core/tests/fuzz_cases/join_fuzz.rs

@@ -245,14 +245,16 @@ async fn test_right_semi_join_1k() {
 
 #[tokio::test]
 async fn test_right_semi_join_1k_filtered() {
-    JoinFuzzTestCase::new(
-        make_staggered_batches_i32(1000, false),
-        make_staggered_batches_i32(1000, false),
-        JoinType::RightSemi,
-        Some(Box::new(col_lt_col_filter)),
-    )
-    .run_test(&[HjSmj, NljHj], false)
-    .await
+    for (left_extra, right_extra) in [(true, true), (false, true), (true, false)] {
+        JoinFuzzTestCase::new(
+            make_staggered_batches_i32(1000, left_extra),
+            make_staggered_batches_i32(1000, right_extra),
+            JoinType::RightSemi,
+            Some(Box::new(col_lt_col_filter)),
+        )
+        .run_test(&[HjSmj, NljHj], false)
+        .await
+    }
 }
 
 #[tokio::test]
@@ -299,14 +301,16 @@ async fn test_right_anti_join_1k() {
 
 #[tokio::test]
 async fn test_right_anti_join_1k_filtered() {
-    JoinFuzzTestCase::new(
-        make_staggered_batches_i32(1000, false),
-        make_staggered_batches_i32(1000, false),
-        JoinType::RightAnti,
-        Some(Box::new(col_lt_col_filter)),
-    )
-    .run_test(&[HjSmj, NljHj], false)
-    .await
+    for (left_extra, right_extra) in [(true, true), (false, true), (true, false)] {
+        JoinFuzzTestCase::new(
+            make_staggered_batches_i32(1000, left_extra),
+            make_staggered_batches_i32(1000, right_extra),
+            JoinType::RightAnti,
+            Some(Box::new(col_lt_col_filter)),
+        )
+        .run_test(&[HjSmj, NljHj], false)
+        .await
+    }
 }
 
 #[tokio::test]
@@ -564,26 +568,30 @@ async fn test_left_anti_join_1k_binary_filtered() {
 
 #[tokio::test]
 async fn test_right_anti_join_1k_binary() {
-    JoinFuzzTestCase::new(
-        make_staggered_batches_binary(1000, false),
-        make_staggered_batches_binary(1000, false),
-        JoinType::RightAnti,
-        None,
-    )
-    .run_test(&[HjSmj, NljHj], false)
-    .await
+    for (left_extra, right_extra) in [(true, true), (false, true), (true, false)] {
+        JoinFuzzTestCase::new(
+            make_staggered_batches_binary(1000, left_extra),
+            make_staggered_batches_binary(1000, right_extra),
+            JoinType::RightAnti,
+            None,
+        )
+        .run_test(&[HjSmj, NljHj], false)
+        .await
+    }
 }
 
 #[tokio::test]
 async fn test_right_anti_join_1k_binary_filtered() {
-    JoinFuzzTestCase::new(
-        make_staggered_batches_binary(1000, false),
-        make_staggered_batches_binary(1000, false),
-        JoinType::RightAnti,
-        Some(Box::new(col_lt_col_filter)),
-    )
-    .run_test(&[HjSmj, NljHj], false)
-    .await
+    for (left_extra, right_extra) in [(true, true), (false, true), (true, false)] {
+        JoinFuzzTestCase::new(
+            make_staggered_batches_binary(1000, left_extra),
+            make_staggered_batches_binary(1000, right_extra),
+            JoinType::RightAnti,
+            Some(Box::new(col_lt_col_filter)),
+        )
+        .run_test(&[HjSmj, NljHj], false)
+        .await
+    }
 }
 
 #[tokio::test]

datafusion/physical-plan/src/joins/sort_merge_join/stream.rs

@@ -1595,14 +1595,16 @@ impl SortMergeJoinStream {
                 &self.schema,
                 &[filtered_record_batch, null_joined_streamed_batch],
             )?;
-        } else if matches!(self.join_type, JoinType::LeftSemi | JoinType::LeftAnti) {
+        } else if matches!(
+            self.join_type,
+            JoinType::LeftSemi
+                | JoinType::LeftAnti
+                | JoinType::RightAnti
+                | JoinType::RightSemi
+        ) {
             let output_column_indices = (0..left_columns_length).collect::<Vec<_>>();
             filtered_record_batch =
                 filtered_record_batch.project(&output_column_indices)?;
-        } else if matches!(self.join_type, JoinType::RightAnti | JoinType::RightSemi) {
-            let output_column_indices = (0..right_columns_length).collect::<Vec<_>>();
-            filtered_record_batch =
-                filtered_record_batch.project(&output_column_indices)?;
         } else if matches!(self.join_type, JoinType::Full)
             && corrected_mask.false_count() > 0
         {

datafusion/physical-plan/src/joins/sort_merge_join/tests.rs

@@ -1109,6 +1109,61 @@ async fn join_right_anti_two_with_filter() -> Result<()> {
     Ok(())
 }
 
+#[tokio::test]
+async fn join_right_anti_filtered_with_mismatched_columns() -> Result<()> {
+    let left = build_table_two_cols(("a1", &vec![31, 31]), ("b1", &vec![32, 33]));
+    let right = build_table(
+        ("a2", &vec![31, 31]),
+        ("b2", &vec![32, 35]),
+        ("c2", &vec![108, 109]),
+    );
+    let on = vec![
+        (
+            Arc::new(Column::new_with_schema("a1", &left.schema())?) as _,
+            Arc::new(Column::new_with_schema("a2", &right.schema())?) as _,
+        ),
+        (
+            Arc::new(Column::new_with_schema("b1", &left.schema())?) as _,
+            Arc::new(Column::new_with_schema("b2", &right.schema())?) as _,
+        ),
+    ];
+
+    let filter = JoinFilter::new(
+        Arc::new(BinaryExpr::new(
+            Arc::new(Column::new("b1", 0)),
+            Operator::LtEq,
+            Arc::new(Column::new("c2", 1)),
+        )),
+        vec![
+            ColumnIndex {
+                index: 1,
+                side: JoinSide::Left,
+            },
+            ColumnIndex {
+                index: 2,
+                side: JoinSide::Right,
+            },
+        ],
+        Arc::new(Schema::new(vec![
+            Field::new("b1", DataType::Int32, false),
+            Field::new("c2", DataType::Int32, false),
+        ])),
+    );
+
+    let (_, batches) =
+        join_collect_with_filter(left, right, on, filter, RightAnti).await?;
+
+    let expected = [
+        "+----+----+-----+",
+        "| a2 | b2 | c2  |",
+        "+----+----+-----+",
+        "| 31 | 35 | 109 |",
+        "+----+----+-----+",
+    ];
+    assert_batches_eq!(expected, &batches);
+    Ok(())
+}
+
 #[tokio::test]
 async fn join_right_anti_with_nulls() -> Result<()> {
     let left = build_table_i32_nullable(