This is an automated email from the ASF dual-hosted git repository.
github-bot pushed a commit to branch main
in repository https://gitbox.apache.org/repos/asf/datafusion.git
The following commit(s) were added to refs/heads/main by this push:
new 00e36e8b72 fix: Return `probe_side.len()` for RightMark/Anti count(*)
queries (#20710)
00e36e8b72 is described below
commit 00e36e8b721b743ad33c82ff49c8da51719caa1a
Author: Jonathan Chen <[email protected]>
AuthorDate: Thu Mar 5 10:02:35 2026 -0600
fix: Return `probe_side.len()` for RightMark/Anti count(*) queries (#20710)
## Which issue does this PR close?
<!--
We generally require a GitHub issue to be filed for all bug fixes and
enhancements and this helps us generate change logs for our releases.
You can link an issue to this PR using the GitHub syntax. For example
`Closes #123` indicates that this PR will close issue #123.
-->
- Closes #20669 .
## Rationale for this change
Return probe_side.len() for count(*) queries
<!--
Why are you proposing this change? If this is already explained clearly
in the issue then this section is not needed.
Explaining clearly why changes are proposed helps reviewers understand
your changes and offer better suggestions for fixes.
-->
<!--
There is no need to duplicate the description in the issue here but it
is sometimes worth providing a summary of the individual changes in this
PR.
-->
## Are these changes tested?
slt tests
<!--
We typically require tests for all PRs in order to:
1. Prevent the code from being accidentally broken by subsequent changes
2. Serve as another way to document the expected behavior of the code
If tests are not included in your PR, please explain why (for example,
are they covered by existing tests)?
-->
## Are there any user-facing changes?
<!--
If there are user-facing changes then we may require documentation to be
updated before approving the PR.
-->
<!--
If there are any breaking changes to public APIs, please add the `api
change` label.
-->
---
.../physical-plan/src/joins/hash_join/stream.rs | 3 ++
.../physical-plan/src/joins/symmetric_hash_join.rs | 3 ++
datafusion/physical-plan/src/joins/utils.rs | 15 +++++++-
datafusion/sqllogictest/test_files/joins.slt | 43 ++++++++++++++++++++++
4 files changed, 63 insertions(+), 1 deletion(-)
diff --git a/datafusion/physical-plan/src/joins/hash_join/stream.rs
b/datafusion/physical-plan/src/joins/hash_join/stream.rs
index 8af26c1b8a..b31982ea3b 100644
--- a/datafusion/physical-plan/src/joins/hash_join/stream.rs
+++ b/datafusion/physical-plan/src/joins/hash_join/stream.rs
@@ -713,6 +713,7 @@ impl HashJoinStream {
filter,
JoinSide::Left,
None,
+ self.join_type,
)?
} else {
(left_indices, right_indices)
@@ -781,6 +782,7 @@ impl HashJoinStream {
&right_indices,
&self.column_indices,
join_side,
+ self.join_type,
)?;
let push_status = self.output_buffer.push_batch(batch)?;
@@ -899,6 +901,7 @@ impl HashJoinStream {
&right_side,
&self.column_indices,
JoinSide::Left,
+ self.join_type,
)?;
let push_status = self.output_buffer.push_batch(batch)?;
diff --git a/datafusion/physical-plan/src/joins/symmetric_hash_join.rs
b/datafusion/physical-plan/src/joins/symmetric_hash_join.rs
index eeb160ae51..4429d1e3fb 100644
--- a/datafusion/physical-plan/src/joins/symmetric_hash_join.rs
+++ b/datafusion/physical-plan/src/joins/symmetric_hash_join.rs
@@ -959,6 +959,7 @@ pub(crate) fn build_side_determined_results(
&probe_indices,
column_indices,
build_hash_joiner.build_side,
+ join_type,
)
.map(|batch| (batch.num_rows() > 0).then_some(batch))
} else {
@@ -1022,6 +1023,7 @@ pub(crate) fn join_with_probe_batch(
filter,
build_hash_joiner.build_side,
None,
+ join_type,
)?
} else {
(build_indices, probe_indices)
@@ -1060,6 +1062,7 @@ pub(crate) fn join_with_probe_batch(
&probe_indices,
column_indices,
build_hash_joiner.build_side,
+ join_type,
)
.map(|batch| (batch.num_rows() > 0).then_some(batch))
}
diff --git a/datafusion/physical-plan/src/joins/utils.rs
b/datafusion/physical-plan/src/joins/utils.rs
index 34993fcdbd..cf4bf2cd16 100644
--- a/datafusion/physical-plan/src/joins/utils.rs
+++ b/datafusion/physical-plan/src/joins/utils.rs
@@ -910,6 +910,7 @@ pub(crate) fn get_final_indices_from_bit_map(
(left_indices, right_indices)
}
+#[expect(clippy::too_many_arguments)]
pub(crate) fn apply_join_filter_to_indices(
build_input_buffer: &RecordBatch,
probe_batch: &RecordBatch,
@@ -918,6 +919,7 @@ pub(crate) fn apply_join_filter_to_indices(
filter: &JoinFilter,
build_side: JoinSide,
max_intermediate_size: Option<usize>,
+ join_type: JoinType,
) -> Result<(UInt64Array, UInt32Array)> {
if build_indices.is_empty() && probe_indices.is_empty() {
return Ok((build_indices, probe_indices));
@@ -938,6 +940,7 @@ pub(crate) fn apply_join_filter_to_indices(
&probe_indices.slice(i, len),
filter.column_indices(),
build_side,
+ join_type,
)?;
let filter_result = filter
.expression()
@@ -959,6 +962,7 @@ pub(crate) fn apply_join_filter_to_indices(
&probe_indices,
filter.column_indices(),
build_side,
+ join_type,
)?;
filter
@@ -990,6 +994,7 @@ fn new_empty_schema_batch(schema: &Schema, row_count:
usize) -> Result<RecordBat
/// Returns a new [RecordBatch] by combining the `left` and `right` according
to `indices`.
/// The resulting batch has [Schema] `schema`.
+#[expect(clippy::too_many_arguments)]
pub(crate) fn build_batch_from_indices(
schema: &Schema,
build_input_buffer: &RecordBatch,
@@ -998,9 +1003,17 @@ pub(crate) fn build_batch_from_indices(
probe_indices: &UInt32Array,
column_indices: &[ColumnIndex],
build_side: JoinSide,
+ join_type: JoinType,
) -> Result<RecordBatch> {
if schema.fields().is_empty() {
- return new_empty_schema_batch(schema, build_indices.len());
+ // For RightAnti and RightSemi joins, after
`adjust_indices_by_join_type`
+ // the build_indices were untouched so only probe_indices hold the
actual
+ // row count.
+ let row_count = match join_type {
+ JoinType::RightAnti | JoinType::RightSemi => probe_indices.len(),
+ _ => build_indices.len(),
+ };
+ return new_empty_schema_batch(schema, row_count);
}
// build the columns of the new [RecordBatch]:
diff --git a/datafusion/sqllogictest/test_files/joins.slt
b/datafusion/sqllogictest/test_files/joins.slt
index 282d7c374b..228918c385 100644
--- a/datafusion/sqllogictest/test_files/joins.slt
+++ b/datafusion/sqllogictest/test_files/joins.slt
@@ -5318,3 +5318,46 @@ DROP TABLE issue_20437_small;
statement count 0
DROP TABLE issue_20437_large;
+
+# Test count(*) with right semi/anti joins returns correct row counts
+# issue: https://github.com/apache/datafusion/issues/20669
+
+statement ok
+CREATE TABLE t1 (k INT, v INT);
+
+statement ok
+CREATE TABLE t2 (k INT, v INT);
+
+statement ok
+INSERT INTO t1 SELECT i AS k, i AS v FROM generate_series(1, 100) t(i);
+
+statement ok
+INSERT INTO t2 VALUES (1, 1);
+
+query I
+WITH t AS (
+ SELECT *
+ FROM t1
+ LEFT ANTI JOIN t2 ON t1.k = t2.k
+)
+SELECT count(*)
+FROM t;
+----
+99
+
+query I
+WITH t AS (
+ SELECT *
+ FROM t1
+ LEFT SEMI JOIN t2 ON t1.k = t2.k
+)
+SELECT count(*)
+FROM t;
+----
+1
+
+statement count 0
+DROP TABLE t1;
+
+statement count 0
+DROP TABLE t2;
---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]
