viirya commented on code in PR #424:
URL: https://github.com/apache/datafusion-comet/pull/424#discussion_r1600504627
##########
core/src/execution/datafusion/spark_hash.rs:
##########
@@ -238,55 +241,67 @@ macro_rules! hash_array_decimal {
fn create_hashes_dictionary<K: ArrowDictionaryKeyType>(
array: &ArrayRef,
hashes_buffer: &mut [u32],
+ multi_col: bool,
) -> Result<()> {
let dict_array =
array.as_any().downcast_ref::<DictionaryArray<K>>().unwrap();
-
- // Hash each dictionary value once, and then use that computed
- // hash for each key value to avoid a potentially expensive
- // redundant hashing for large dictionary elements (e.g. strings)
- let dict_values = Arc::clone(dict_array.values());
- let mut dict_hashes = vec![0; dict_values.len()];
- create_hashes(&[dict_values], &mut dict_hashes)?;
-
- for (hash, key) in hashes_buffer.iter_mut().zip(dict_array.keys().iter()) {
- if let Some(key) = key {
- let idx = key.to_usize().ok_or_else(|| {
- DataFusionError::Internal(format!(
- "Can not convert key value {:?} to usize in dictionary of
type {:?}",
- key,
- dict_array.data_type()
- ))
- })?;
- *hash = dict_hashes[idx]
- } // no update for Null, consistent with other hashes
+ if multi_col {
+ // unpack the dictionary array as each row may have a different hash
input
+ let unpacked = take(dict_array.values().as_ref(), dict_array.keys(),
None)?;
+ create_hashes(&[unpacked], hashes_buffer)?;
+ } else {
Review Comment:
Ah, I see. Because `hashes_buffer` has hashed result for previous columns.
--
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]
