jonathanc-n commented on code in PR #17431:
URL: https://github.com/apache/datafusion/pull/17431#discussion_r2324191348
##########
datafusion/physical-plan/src/joins/sort_merge_join/exec.rs:
##########
@@ -1923,6 +1974,100 @@ mod tests {
Ok(())
}
+ #[tokio::test]
+ async fn join_binary() -> Result<()> {
+ let left = build_binary_table(
+ (
+ "a1",
+ &vec![
+ &[0xc0, 0xff, 0xee],
+ &[0xde, 0xca, 0xde],
+ &[0xfa, 0xca, 0xde],
+ ],
+ ),
+ ("b1", &vec![5, 10, 15]), // this has a repetition
+ ("c1", &vec![7, 8, 9]),
+ );
+ let right = build_binary_table(
+ (
+ "a1",
+ &vec![
+ &[0xc0, 0xff, 0xee],
+ &[0xde, 0xca, 0xde],
+ &[0xfa, 0xca, 0xde],
+ ],
+ ),
+ ("b2", &vec![105, 110, 115]),
+ ("c2", &vec![70, 80, 90]),
+ );
+
+ let on = vec![(
+ Arc::new(Column::new_with_schema("a1", &left.schema())?) as _,
+ Arc::new(Column::new_with_schema("a1", &right.schema())?) as _,
+ )];
+
+ let (_, batches) = join_collect(left, right, on, Inner).await?;
+
+ // The output order is important as SMJ preserves sortedness
+ assert_snapshot!(batches_to_string(&batches), @r#"
+ +--------+----+----+--------+-----+----+
+ | a1 | b1 | c1 | a1 | b2 | c2 |
+ +--------+----+----+--------+-----+----+
+ | c0ffee | 5 | 7 | c0ffee | 105 | 70 |
+ | decade | 10 | 8 | decade | 110 | 80 |
+ | facade | 15 | 9 | facade | 115 | 90 |
+ +--------+----+----+--------+-----+----+
+ "#);
+ Ok(())
+ }
+
+ #[tokio::test]
+ async fn join_fixed_size_binary() -> Result<()> {
Review Comment:
Maybe we should include large binary test as well? 🤔 I noticed the amount of
unit tests were getting out of hand, maybe I'll look into separating the tests
into the other SMJ files.
--
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
