mingmwang commented on code in PR #4043:
URL: https://github.com/apache/arrow-datafusion/pull/4043#discussion_r1014764494
##########
datafusion/core/src/dataframe.rs:
##########
@@ -1605,4 +1607,74 @@ mod tests {
Partitioning::UnknownPartitioning(partition_count) if
partition_count == default_partition_count * 2));
Ok(())
}
+
+ #[tokio::test]
+ async fn verify_join_output_partitioning() -> Result<()> {
+ let left = test_table().await?.select_columns(&["c1", "c2"])?;
+ let right = test_table_with_name("c2")
+ .await?
+ .select_columns(&["c1", "c2"])?
+ .with_column_renamed("c2.c1", "c2_c1")?
+ .with_column_renamed("c2.c2", "c2_c2")?;
+
+ let all_join_types = vec![
+ JoinType::Inner,
+ JoinType::Left,
+ JoinType::Right,
+ JoinType::Full,
+ JoinType::LeftSemi,
+ JoinType::RightSemi,
+ JoinType::LeftAnti,
+ JoinType::RightAnti,
+ ];
+
+ let default_partition_count =
+ SessionContext::new().copied_config().target_partitions;
+
+ for join_type in all_join_types {
+ let join = left.join(
+ right.clone(),
+ join_type,
+ &["c1", "c2"],
+ &["c2_c1", "c2_c2"],
+ None,
+ )?;
+ let physical_plan = join.create_physical_plan().await?;
+ let out_partitioning = physical_plan.output_partitioning();
+ let join_schema = physical_plan.schema();
+
+ match join_type {
+ JoinType::Inner
+ | JoinType::Left
+ | JoinType::LeftSemi
+ | JoinType::LeftAnti => {
+ let left_exprs: Vec<Arc<dyn PhysicalExpr>> = vec![
+ Arc::new(Column::new_with_schema("c1",
&join_schema).unwrap()),
+ Arc::new(Column::new_with_schema("c2",
&join_schema).unwrap()),
+ ];
+ assert_eq!(
Review Comment:
https://github.com/apache/arrow-datafusion/issues/4116
https://github.com/apache/arrow-datafusion/issues/4117
https://github.com/apache/arrow-datafusion/issues/4118
--
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: [email protected]
For queries about this service, please contact Infrastructure at:
[email protected]
