viirya commented on code in PR #11232:
URL: https://github.com/apache/datafusion/pull/11232#discussion_r1663181226
##########
datafusion/physical-plan/src/joins/hash_join.rs:
##########
@@ -3844,6 +3851,103 @@ mod tests {
Ok(())
}
+ pub fn build_table_struct(
+ struct_name: &str,
+ a: (&str, &Vec<Option<i32>>),
+ nulls: Option<NullBuffer>,
+ ) -> Arc<dyn ExecutionPlan> {
+ let inner_fields = vec![Field::new(a.0, DataType::Int32, true)];
+ let schema = Schema::new(vec![Field::new(
+ struct_name,
+ DataType::Struct(inner_fields.clone().into()),
+ nulls.is_some(),
+ )]);
+
+ let batch = RecordBatch::try_new(
+ Arc::new(schema),
+ vec![Arc::new(StructArray::new(
+ inner_fields.into(),
+ vec![Arc::new(Int32Array::from(a.1.clone()))],
+ nulls,
+ ))],
+ )
+ .unwrap();
+ let schema_ref = batch.schema();
+ Arc::new(MemoryExec::try_new(&[vec![batch]], schema_ref,
None).unwrap())
+ }
+
+ #[tokio::test]
+ async fn join_on_struct() -> Result<()> {
+ let task_ctx = Arc::new(TaskContext::default());
+ let left =
+ build_table_struct("n1", ("a", &vec![None, Some(1), Some(2),
Some(3)]), None);
+ let right =
+ build_table_struct("n2", ("a", &vec![None, Some(1), Some(2),
Some(4)]), None);
+ let on = vec![(
+ Arc::new(Column::new_with_schema("n1", &left.schema())?) as _,
+ Arc::new(Column::new_with_schema("n2", &right.schema())?) as _,
+ )];
+
+ let (columns, batches) =
+ join_collect(left, right, on, &JoinType::Inner, false,
task_ctx).await?;
+
+ assert_eq!(columns, vec!["n1", "n2"]);
+
+ let expected = [
+ "+--------+--------+",
+ "| n1 | n2 |",
+ "+--------+--------+",
+ "| {a: } | {a: } |",
+ "| {a: 1} | {a: 1} |",
+ "| {a: 2} | {a: 2} |",
+ "+--------+--------+",
+ ];
+ assert_batches_eq!(expected, &batches);
+
+ Ok(())
+ }
+
+ #[tokio::test]
+ async fn join_on_struct_with_nulls() -> Result<()> {
Review Comment:
Can we also add a test case for `Operator::Eq`?
--
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-unsubscr...@datafusion.apache.org
For queries about this service, please contact Infrastructure at:
us...@infra.apache.org
---------------------------------------------------------------------
To unsubscribe, e-mail: github-unsubscr...@datafusion.apache.org
For additional commands, e-mail: github-h...@datafusion.apache.org
