saadtajwar commented on code in PR #23957:
URL: https://github.com/apache/datafusion/pull/23957#discussion_r3744596424
##########
datafusion/physical-plan/src/joins/hash_join/stream.rs:
##########
@@ -742,40 +742,58 @@ impl HashJoinStream {
let timer = self.join_metrics.join_time.timer();
// Null-aware anti join semantics:
+
// For LeftAnti: output LEFT (build) rows where LEFT.key NOT IN
RIGHT.key
// 1. If RIGHT (probe) contains NULL in any batch, no LEFT rows should
be output
// 2. LEFT rows with NULL keys should not be output (handled in final
stage)
+
+ // For RightAnti: output RIGHT (probe) rows where RIGHT.key NOT IN
LEFT.key
+ // 1. If LEFT (build) contains NULL, no RIGHT rows should be output
+ // 2. RIGHT rows with NULL keys should not be output
+ // 3. If LEFT (build) is empty, all RIGHT rows should be output
if self.null_aware {
- // Mark that we've seen a probe batch with actual rows (probe side
is non-empty)
- // Only set this if batch has rows - empty batches don't count
- // Use shared atomic state so all partitions can see this global
information
- if state.batch.num_rows() > 0 {
- build_side
- .left_data
- .probe_side_non_empty
- .store(true, Ordering::Relaxed);
- }
+ match self.join_type {
+ JoinType::RightAnti => {
+ if build_side.left_data.build_side_has_null {
+ timer.done();
+ self.state = HashJoinStreamState::FetchProbeBatch;
+ return Ok(StatefulStreamResult::Continue);
+ }
+ }
+ JoinType::LeftAnti => {
+ // Mark that we've seen a probe batch with actual rows
(probe side is non-empty)
+ // Only set this if batch has rows - empty batches don't
count
+ // Use shared atomic state so all partitions can see this
global information
+ if state.batch.num_rows() > 0 {
+ build_side
+ .left_data
+ .probe_side_non_empty
+ .store(true, Ordering::Relaxed);
+ }
- // Check if probe side (RIGHT) contains NULL
- // Since null_aware validation ensures single column join, we only
check the first column
- let probe_key_column = &state.values[0];
- if probe_key_column.null_count() > 0 {
- // Found NULL in probe side - set shared flag to prevent any
output
- build_side
- .left_data
- .probe_side_has_null
- .store(true, Ordering::Relaxed);
- }
+ // Check if probe side (RIGHT) contains NULL
+ // Since null_aware validation ensures single column join,
we only check the first column
+ let probe_key_column = &state.values[0];
+ if probe_key_column.logical_null_count() > 0 {
Review Comment:
Ah I see - limited to unfiltered, thank you for the catch
--
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]
