This is an automated email from the ASF dual-hosted git repository.
alamb 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 9e90e17a61 fix: Add additional required expression for natural join
(#11713)
9e90e17a61 is described below
commit 9e90e17a61444b77d7d0de416a33857d1a5105b5
Author: Lordworms <[email protected]>
AuthorDate: Sat Aug 3 03:57:52 2024 -0700
fix: Add additional required expression for natural join (#11713)
* adding test file
* replace expand_wildcard
* refine test
---------
Co-authored-by: jonahgao <[email protected]>
---
datafusion/expr/src/logical_plan/builder.rs | 7 ++++-
datafusion/sqllogictest/test_files/join.slt | 49 ++++++++++++++++++++++++++++-
2 files changed, 54 insertions(+), 2 deletions(-)
diff --git a/datafusion/expr/src/logical_plan/builder.rs
b/datafusion/expr/src/logical_plan/builder.rs
index 98e262f0b1..736310c7ac 100644
--- a/datafusion/expr/src/logical_plan/builder.rs
+++ b/datafusion/expr/src/logical_plan/builder.rs
@@ -1531,7 +1531,12 @@ pub fn wrap_projection_for_join_if_necessary(
let need_project = join_keys.iter().any(|key| !matches!(key,
Expr::Column(_)));
let plan = if need_project {
- let mut projection = expand_wildcard(input_schema, &input, None)?;
+ // Include all columns from the input and extend them with the join
keys
+ let mut projection = input_schema
+ .columns()
+ .into_iter()
+ .map(Expr::Column)
+ .collect::<Vec<_>>();
let join_key_items = alias_join_keys
.iter()
.flat_map(|expr| expr.try_as_col().is_none().then_some(expr))
diff --git a/datafusion/sqllogictest/test_files/join.slt
b/datafusion/sqllogictest/test_files/join.slt
index 29f1c4384d..21fea4ad10 100644
--- a/datafusion/sqllogictest/test_files/join.slt
+++ b/datafusion/sqllogictest/test_files/join.slt
@@ -1130,4 +1130,51 @@ SELECT * FROM
(SELECT * FROM t1 CROSS JOIN t2)
WHERE t1.a + t2.a IS NULL;
----
-NULL NULL
\ No newline at end of file
+NULL NULL
+
+statement ok
+CREATE TABLE t5(v0 BIGINT, v1 STRING, v2 BIGINT, v3 STRING, v4 BOOLEAN);
+
+statement ok
+CREATE TABLE t1(v0 BIGINT, v1 STRING);
+
+statement ok
+CREATE TABLE t0(v0 BIGINT, v1 DOUBLE);
+
+query TT
+explain SELECT *
+FROM t1
+NATURAL JOIN t5
+INNER JOIN t0 ON (t0.v1 + t5.v0) > 0
+WHERE t0.v1 = t1.v0;
+----
+logical_plan
+01)Projection: t1.v0, t1.v1, t5.v2, t5.v3, t5.v4, t0.v0, t0.v1
+02)--Inner Join: CAST(t1.v0 AS Float64) = t0.v1 Filter: t0.v1 + CAST(t5.v0 AS
Float64) > Float64(0)
+03)----Projection: t1.v0, t1.v1, t5.v0, t5.v2, t5.v3, t5.v4
+04)------Inner Join: Using t1.v0 = t5.v0, t1.v1 = t5.v1
+05)--------TableScan: t1 projection=[v0, v1]
+06)--------TableScan: t5 projection=[v0, v1, v2, v3, v4]
+07)----TableScan: t0 projection=[v0, v1]
+physical_plan
+01)CoalesceBatchesExec: target_batch_size=8192
+02)--HashJoinExec: mode=CollectLeft, join_type=Inner, on=[(CAST(t1.v0 AS
Float64)@6, v1@1)], filter=v1@1 + CAST(v0@0 AS Float64) > 0, projection=[v0@0,
v1@1, v2@3, v3@4, v4@5, v0@7, v1@8]
+03)----CoalescePartitionsExec
+04)------ProjectionExec: expr=[v0@0 as v0, v1@1 as v1, v0@2 as v0, v2@3 as v2,
v3@4 as v3, v4@5 as v4, CAST(v0@0 AS Float64) as CAST(t1.v0 AS Float64)]
+05)--------RepartitionExec: partitioning=RoundRobinBatch(4), input_partitions=1
+06)----------CoalesceBatchesExec: target_batch_size=8192
+07)------------HashJoinExec: mode=CollectLeft, join_type=Inner, on=[(v0@0,
v0@0), (v1@1, v1@1)], projection=[v0@0, v1@1, v0@2, v2@4, v3@5, v4@6]
+08)--------------MemoryExec: partitions=1, partition_sizes=[0]
+09)--------------MemoryExec: partitions=1, partition_sizes=[0]
+10)----MemoryExec: partitions=1, partition_sizes=[0]
+
+
+
+statement ok
+drop table t5;
+
+statement ok
+drop table t1;
+
+statement ok
+drop table t0;
---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]
