alamb commented on a change in pull request #9116:
URL: https://github.com/apache/arrow/pull/9116#discussion_r558531603
##########
File path: rust/datafusion/src/physical_plan/hash_join.rs
##########
@@ -936,4 +1096,53 @@ mod tests {
Ok(())
}
+
+ #[test]
+ fn join_with_hash_collision() -> Result<()> {
+ let mut hashmap_left = HashMap::with_hasher(IdHashBuilder {});
+ let left = build_table_i32(
+ ("a", &vec![10, 20]),
+ ("x", &vec![100, 200]),
+ ("y", &vec![200, 300]),
+ );
+
+ let random_state = RandomState::new();
+
+ let hashes = create_hashes(&[left.columns()[0].clone()],
&random_state)?;
+
+ // Create hash collisions
+ hashmap_left.insert(hashes[0], vec![0, 1]);
+ hashmap_left.insert(hashes[1], vec![0, 1]);
+
+ let right = build_table_i32(
+ ("a", &vec![10, 20]),
+ ("b", &vec![0, 0]),
+ ("c", &vec![30, 40]),
+ );
+
+ let left_data = JoinLeftData::new((hashmap_left, left));
+ let (l, r) = build_join_indexes(
+ &left_data,
+ &right,
+ JoinType::Inner,
Review comment:
I recommend adding a test that covers collisions for all the `JoinType`
variants -- the path for collision handling is different for those different
join type variants.
----------------------------------------------------------------
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.
For queries about this service, please contact Infrastructure at:
[email protected]
