[GitHub] [arrow-datafusion] liukun4515 commented on a diff in pull request #4327: fix bug: right semi join can't support the filter

[GitBox <gi...@apache.org>]

liukun4515 commented on code in PR #4327:
URL: https://github.com/apache/arrow-datafusion/pull/4327#discussion_r1029352241


##########
datafusion/core/src/physical_plan/joins/hash_join.rs:
##########
@@ -2371,6 +2431,65 @@ mod tests {
         Ok(())
     }
 
+    #[tokio::test]
+    async fn join_right_semi_with_filter() -> Result<()> {
+        let session_ctx = SessionContext::new();
+        let task_ctx = session_ctx.task_ctx();
+        let left = build_table(
+            ("a2", &vec![10, 20, 30, 40]),
+            ("b2", &vec![4, 5, 6, 5]), // 5 is double on the left
+            ("c2", &vec![70, 80, 90, 100]),
+        );
+        let right = build_table(
+            ("a1", &vec![1, 2, 2, 3]),
+            ("b1", &vec![4, 5, 5, 7]), // 7 does not exist on the left
+            ("c1", &vec![7, 8, 8, 9]),
+        );
+
+        let on = vec![(
+            Column::new_with_schema("b2", &left.schema())?,
+            Column::new_with_schema("b1", &right.schema())?,
+        )];
+
+        // build filter left.b2 > 4
+        let column_indices = vec![ColumnIndex {
+            index: 1,
+            side: JoinSide::Left,
+        }];
+        let intermediate_schema =
+            Schema::new(vec![Field::new("x", DataType::Int32, true)]);
+
+        let filter_expression = Arc::new(BinaryExpr::new(
+            Arc::new(Column::new("x", 0)),
+            Operator::Gt,
+            Arc::new(Literal::new(ScalarValue::Int32(Some(4)))),
+        )) as Arc<dyn PhysicalExpr>;
+
+        let filter =
+            JoinFilter::new(filter_expression, column_indices, intermediate_schema);
+
+        let join =
+            join_with_filter(left, right, on, filter, &JoinType::RightSemi, false)?;
+
+        let columns = columns(&join.schema());
+        assert_eq!(columns, vec!["a1", "b1", "c1"]);
+
+        let stream = join.execute(0, task_ctx)?;
+        let batches = common::collect(stream).await?;
+
+        let expected = vec![

Review Comment:
   If not fix this bug, the result will be
   ```
   [
       "+----+----+----+",
       "| a1 | b1 | c1 |",
       "+----+----+----+",
       "+----+----+----+",
   ]
   ```



-- 
This is an automated message from the Apache Git Service.
To respond to the message, please log on to GitHub and use the
URL above to go to the specific comment.

To unsubscribe, e-mail: github-unsubscribe@arrow.apache.org

For queries about this service, please contact Infrastructure at:
users@infra.apache.org