refactor: keep the hash join NOT IN rules in one module

datafusion/core/tests/physical_optimizer/join_selection.rs

@@ -481,7 +481,7 @@ async fn test_join_with_swap_semi() {
 /// `PartitionMode::Partitioned` is deliberately not a case here: a null-aware
 /// `LeftAnti` cannot be constructed in that mode at all, so there is no input
 /// plan to optimize. See
-/// `HashJoinExec::null_aware_mode`/`NullAwareMode::try_new`.
+/// `HashJoinExec::not_in`/`NotIn::try_new`.
 #[rstest]
 #[case::collect_left(PartitionMode::CollectLeft, 1, 1, false)]
 #[case::auto(PartitionMode::Auto, 1, 1, false)]

datafusion/physical-optimizer/src/join_selection.rs

@@ -320,7 +320,7 @@ fn statistical_join_selection_subrule(
                         && should_swap_join_order(left, right, context)?
                     {
                         // A null-aware join is never in `Partitioned` mode
-                        // (`NullAwareMode::try_new` rejects it), so the swap
+                        // (`NotIn::try_new` rejects it), so the swap
                         // keeps the mode this arm matched on.
                         hash_join
                             .swap_inputs(PartitionMode::Partitioned)

datafusion/physical-plan/src/joins/hash_join/exec/prepared.rs

@@ -70,12 +70,10 @@ impl PreparedHashJoinBuild {
     pub(super) fn probe_data(&self, probe_threads: usize) -> JoinLeftData {
         JoinLeftData {
             build: Arc::clone(&self.build),
-            null_aware_scope_map: None,
-            null_value_build_rows: None,
+            // Prepared builds exclude null-aware joins.
+            not_in: None,
             visited_indices_bitmap: Mutex::new(BooleanBufferBuilder::new(0)),
-            null_indices_bitmap: Mutex::new(BooleanBufferBuilder::new(0)),
             probe_completion: ProbeCompletion::new(probe_threads),
-            build_side_has_null: false,
         }
     }
 

datafusion/physical-plan/src/joins/hash_join/mod.rs

@@ -29,6 +29,7 @@ pub use partitioned_hash_eval::{HashExpr, SeededRandomState};
 
 mod exec;
 mod inlist_builder;
+mod not_in;
 mod partitioned_hash_eval;
 mod probe_completion;
 mod shared_bounds;