UBarney commented on code in PR #16443:
URL: https://github.com/apache/datafusion/pull/16443#discussion_r2173635381
##########
datafusion/physical-plan/src/joins/nested_loop_join.rs:
##########
@@ -828,13 +833,127 @@ impl<T: BatchTransformer> NestedLoopJoinStream<T> {
handle_state!(self.process_probe_batch())
}
NestedLoopJoinStreamState::ExhaustedProbeSide => {
- handle_state!(self.process_unmatched_build_batch())
+ handle_state!(self.prepare_unmatched_output_indices())
+ }
+ NestedLoopJoinStreamState::OutputUnmatchedBuildRows(_) => {
+ handle_state!(self.build_unmatched_output())
}
NestedLoopJoinStreamState::Completed => Poll::Ready(None),
};
}
}
+ fn get_next_join_result(&mut self) -> Result<Option<RecordBatch>> {
+ let (left_indices, right_indices, start) =
+ self.join_result_status.as_mut().ok_or_else(|| {
+ datafusion_common::_internal_datafusion_err!(
+ "should have join_result_status"
+ )
+ })?;
+
+ let left_batch = self
+ .left_data
+ .as_ref()
+ .ok_or_else(|| {
+ datafusion_common::_internal_datafusion_err!("should have
left_batch")
+ })?
+ .batch();
+
+ let right_batch = match &self.state {
+ NestedLoopJoinStreamState::ProcessProbeBatch(record_batch) =>
record_batch,
+ NestedLoopJoinStreamState::OutputUnmatchedBuildRows(record_batch)
=> {
+ record_batch
+ }
+ _ => {
+ return internal_err!(
+ "state should be ProcessProbeBatch or OutputUnmatchBatch"
+ )
+ }
+ };
+
+ let current_start = *start;
+
+ if left_indices.is_empty() && right_indices.is_empty() &&
current_start == 0 {
Review Comment:
That was my initial approach. However, it resulted in an output with 0 rows
and 0 columns, which seems to be incorrect and caused the test to fail.
You can see the failed CI run here:
https://github.com/apache/datafusion/actions/runs/15734253347/job/44343070926?pr=16443#step:5:1208
--
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
