kosiew commented on code in PR #19653:
URL: https://github.com/apache/datafusion/pull/19653#discussion_r2689397962
##########
datafusion/core/benches/topk_aggregate.rs:
##########
@@ -133,6 +165,84 @@ async fn aggregate_string(
Ok(())
}
+async fn aggregate_distinct(
+ ctx: SessionContext,
+ limit: usize,
+ use_topk: bool,
+ asc: bool,
+) -> Result<()> {
+ let order_direction = if asc { "asc" } else { "desc" };
+ let sql = format!(
+ "select id from traces group by id order by id {order_direction} limit
{limit};"
+ );
+ let df = ctx.sql(sql.as_str()).await?;
+ let plan = df.create_physical_plan().await?;
+ let actual_phys_plan = displayable(plan.as_ref()).indent(true).to_string();
+ assert_eq!(
+ actual_phys_plan.contains(&format!("lim=[{limit}]")),
+ use_topk
+ );
+ let batches = collect(plan, ctx.task_ctx()).await?;
+ assert_eq!(batches.len(), 1);
+ let batch = batches.first().unwrap();
+ assert_eq!(batch.num_rows(), 10);
Review Comment:
LIMIT
instead of
10
--
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]
---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]
