mingmwang commented on code in PR #6457:
URL: https://github.com/apache/arrow-datafusion/pull/6457#discussion_r1227896111
##########
datafusion/core/tests/sql/subqueries.rs:
##########
@@ -657,6 +924,73 @@ async fn support_limit_subquery() -> Result<()> {
Ok(())
}
+#[tokio::test]
+async fn in_non_correlated_subquery_with_limit() -> Result<()> {
+ let ctx = create_join_context("t1_id", "t2_id", true)?;
+
+ let sql =
+ "SELECT t1_id, t1_name FROM t1 WHERE t1_id in (SELECT t2_id FROM t2
limit 10)";
+ let msg = format!("Creating logical plan for '{sql}'");
+ let dataframe = ctx.sql(sql).await.expect(&msg);
+ let plan = dataframe.into_optimized_plan()?;
+
+ // de-correlated, limit is kept
+ let expected = vec![
+ "LeftSemi Join: t1.t1_id = __correlated_sq_1.t2_id [t1_id:UInt32;N,
t1_name:Utf8;N]",
+ " TableScan: t1 projection=[t1_id, t1_name] [t1_id:UInt32;N,
t1_name:Utf8;N]",
+ " SubqueryAlias: __correlated_sq_1 [t2_id:UInt32;N]",
+ " Limit: skip=0, fetch=10 [t2_id:UInt32;N]",
+ " TableScan: t2 projection=[t2_id], fetch=10 [t2_id:UInt32;N]",
+ ];
+ let formatted = plan.display_indent_schema().to_string();
+ let actual: Vec<&str> = formatted.trim().lines().collect();
+ assert_eq!(
+ expected, actual,
+ "\n\nexpected:\n\n{expected:#?}\nactual:\n\n{actual:#?}\n\n"
+ );
+
Review Comment:
I do not add result checking in all the new added UTs. Some UTs are used to
verify the plans are expected.
I added result checking for those that might have `count` bugs.
--
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]
