kazuyukitanimura commented on code in PR #433:
URL: https://github.com/apache/datafusion-comet/pull/433#discussion_r1602020418
##########
core/src/execution/datafusion/spark_hash.rs:
##########
@@ -227,27 +248,11 @@ pub fn create_hashes<'a>(
arrays: &[ArrayRef],
hashes_buffer: &'a mut [u32],
) -> Result<&'a mut [u32]> {
- for col in arrays {
+ for (i, col) in arrays.iter().enumerate() {
+ let multi_col = i >= 1;
match col.data_type() {
DataType::Boolean => {
- let array =
col.as_any().downcast_ref::<BooleanArray>().unwrap();
- if array.null_count() == 0 {
- for (i, hash) in hashes_buffer.iter_mut().enumerate() {
- *hash = spark_compatible_murmur3_hash(
- i32::from(array.value(i)).to_le_bytes(),
- *hash,
- );
- }
- } else {
- for (i, hash) in hashes_buffer.iter_mut().enumerate() {
- if !array.is_null(i) {
- *hash = spark_compatible_murmur3_hash(
- i32::from(array.value(i)).to_le_bytes(),
- *hash,
- );
- }
- }
- }
+ hash_array_boolean!(BooleanArray, col, i32, hashes_buffer);
Review Comment:
I am wondering why this is a macro. It looks like this is the only use case?
##########
spark/src/main/scala/org/apache/comet/expressions/CometCast.scala:
##########
@@ -108,7 +108,7 @@ object CometCast {
Compatible()
case DataTypes.ByteType | DataTypes.ShortType | DataTypes.IntegerType |
DataTypes.LongType =>
- Compatible()
+ Incompatible(Some("Not all invalid inputs are detected"))
Review Comment:
Will this be gone after rebasing/merging with main?
--
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
