Jefffrey commented on code in PR #20168:
URL: https://github.com/apache/datafusion/pull/20168#discussion_r2796421335
##########
datafusion/common/src/hash_utils.rs:
##########
@@ -427,22 +416,93 @@ fn hash_dictionary<K: ArrowDictionaryKeyType>(
let mut dict_hashes = vec![0; dict_values.len()];
create_hashes([dict_values], random_state, &mut dict_hashes)?;
- // combine hash for each index in values
- for (hash, key) in hashes_buffer.iter_mut().zip(array.keys().iter()) {
- if let Some(key) = key {
+ if HAS_NULL_KEYS {
+ for (hash, key) in hashes_buffer.iter_mut().zip(array.keys().iter()) {
+ if let Some(key) = key {
+ let idx = key.as_usize();
+ if !HAS_NULL_VALUES || dict_values.is_valid(idx) {
+ if MULTI_COL {
+ *hash = combine_hashes(dict_hashes[idx], *hash);
+ } else {
+ *hash = dict_hashes[idx];
+ }
+ }
+ }
+ }
+ } else {
+ for (hash, key) in hashes_buffer.iter_mut().zip(array.keys().iter()) {
+ // SAFETY: Keys are guaranteed to be non-null because we checked
nucll_count = 0
+ let key = key.unwrap();
Review Comment:
```suggestion
for (hash, key) in
hashes_buffer.iter_mut().zip(array.keys().values()) {
```
Can directly go to the values buffer here
--
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]
