martin-g commented on code in PR #18718:
URL: https://github.com/apache/datafusion/pull/18718#discussion_r2539616019
##########
datafusion/common/src/hash_utils.rs:
##########
@@ -329,6 +329,40 @@ where
Ok(())
}
+#[cfg(not(feature = "force_hash_collisions"))]
+fn hash_union_array(
+ array: &UnionArray,
+ random_state: &RandomState,
+ hashes_buffer: &mut [u64],
+) -> Result<()> {
+ use std::collections::HashMap;
+
+ let DataType::Union(union_fields, _mode) = array.data_type() else {
+ unreachable!()
+ };
+
+ let mut child_hashes = HashMap::with_capacity(union_fields.len());
+
+ for (type_id, _field) in union_fields.iter() {
+ let child = array.child(type_id);
+ let mut child_hash_buffer = vec![0; child.len()];
+ create_hashes([child], random_state, &mut child_hash_buffer)?;
+
+ child_hashes.insert(type_id, child_hash_buffer);
+ }
+
+ #[allow(clippy::needless_range_loop)]
Review Comment:
```suggestion
#[expect(clippy::needless_range_loop)]
```
--
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]
