Dandandan commented on code in PR #21817:
URL: https://github.com/apache/datafusion/pull/21817#discussion_r3135535504
##########
datafusion/physical-plan/src/joins/hash_join/stream.rs:
##########
@@ -723,6 +725,54 @@ impl HashJoinStream {
next_offset,
)
}
+ Map::RoaringMap(bitmap) => {
+ let key_col = &state.values[0];
+ let is_semi = matches!(self.join_type, JoinType::RightSemi);
+ let mask: BooleanArray = match key_col.data_type() {
+ DataType::Int32 => {
+ let arr =
key_col.as_any().downcast_ref::<Int32Array>().unwrap();
+ arr.iter()
Review Comment:
Operating over `.values()` directly and using `collect_bool` method is quite
a bit more performant
--
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]
