advancedxy commented on code in PR #424: URL: https://github.com/apache/datafusion-comet/pull/424#discussion_r1601584368
########## core/src/execution/datafusion/spark_hash.rs: ########## @@ -193,27 +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(); + 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 { + // 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()); + // same initial seed as Spark + let mut dict_hashes = vec![42; dict_values.len()]; + create_hashes(&[dict_values], &mut dict_hashes)?; Review Comment: No worries. -- 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