ORCA: don't push LOJ ON-pred onto its own outer in PushThruOuterChild

contrib/pax_storage/src/test/regress/expected/bfv_joins.out

@@ -4190,6 +4190,36 @@ INSERT INTO ext_stats_tbl VALUES('tC', true);
 ANALYZE ext_stats_tbl;
 explain SELECT 1 FROM ext_stats_tbl t11 FULL JOIN ext_stats_tbl t12 ON t12.c2;
 ERROR:  FULL JOIN is only supported with merge-joinable or hash-joinable join conditions
+-- ORCA bug: a boolean ON-clause of a LEFT JOIN must not be pushed down as a
+-- scan filter on the outer relation. When the same outer relation feeds
+-- multiple LEFT JOINs whose ON-clauses use the same boolean column AND there
+-- is a WHERE on top, the normalizer used to push the ON-pred onto the LOJ's
+-- own outer child, discarding outer rows that should be null-padded.
+create table loj_bool_x(c1 boolean);
+NOTICE:  Table doesn't have 'DISTRIBUTED BY' clause -- Using column named 'c1' as the Apache Cloudberry data distribution key for this table.
+HINT:  The 'DISTRIBUTED BY' clause determines the distribution of data. Make sure column(s) chosen are the optimal data distribution key to minimize skew.
+create table loj_bool_y1(c1 boolean);
+NOTICE:  Table doesn't have 'DISTRIBUTED BY' clause -- Using column named 'c1' as the Apache Cloudberry data distribution key for this table.
+HINT:  The 'DISTRIBUTED BY' clause determines the distribution of data. Make sure column(s) chosen are the optimal data distribution key to minimize skew.
+create table loj_bool_y2(c1 boolean);
+NOTICE:  Table doesn't have 'DISTRIBUTED BY' clause -- Using column named 'c1' as the Apache Cloudberry data distribution key for this table.
+HINT:  The 'DISTRIBUTED BY' clause determines the distribution of data. Make sure column(s) chosen are the optimal data distribution key to minimize skew.
+insert into loj_bool_x values (true), (false), (false);
+insert into loj_bool_y1 values (true);
+insert into loj_bool_y2 values (true);
+-- Expect 2 rows: the two FALSE rows in loj_bool_x, with NULL from loj_bool_y2.
+-- The plan must NOT contain "Filter: c1" on Seq Scan of loj_bool_x.
+select loj_bool_x.c1, loj_bool_y2.c1 as y2c1
+  from loj_bool_x left join loj_bool_y1 on loj_bool_x.c1
+                  left join loj_bool_y2 on loj_bool_x.c1
+ where loj_bool_y2.c1 is null
+ order by 1, 2;
+ c1 | y2c1 
+----+------
+ f  | 
+ f  | 
+(2 rows)
+
 -- Clean up. None of the objects we create are very interesting to keep around.
 reset search_path;
 set client_min_messages='warning';

contrib/pax_storage/src/test/regress/expected/bfv_joins_optimizer.out

@@ -4215,6 +4215,36 @@ INSERT INTO ext_stats_tbl VALUES('tC', true);
 ANALYZE ext_stats_tbl;
 explain SELECT 1 FROM ext_stats_tbl t11 FULL JOIN ext_stats_tbl t12 ON t12.c2;
 ERROR:  FULL JOIN is only supported with merge-joinable or hash-joinable join conditions
+-- ORCA bug: a boolean ON-clause of a LEFT JOIN must not be pushed down as a
+-- scan filter on the outer relation. When the same outer relation feeds
+-- multiple LEFT JOINs whose ON-clauses use the same boolean column AND there
+-- is a WHERE on top, the normalizer used to push the ON-pred onto the LOJ's
+-- own outer child, discarding outer rows that should be null-padded.
+create table loj_bool_x(c1 boolean);
+NOTICE:  Table doesn't have 'DISTRIBUTED BY' clause -- Using column named 'c1' as the Apache Cloudberry data distribution key for this table.
+HINT:  The 'DISTRIBUTED BY' clause determines the distribution of data. Make sure column(s) chosen are the optimal data distribution key to minimize skew.
+create table loj_bool_y1(c1 boolean);
+NOTICE:  Table doesn't have 'DISTRIBUTED BY' clause -- Using column named 'c1' as the Apache Cloudberry data distribution key for this table.
+HINT:  The 'DISTRIBUTED BY' clause determines the distribution of data. Make sure column(s) chosen are the optimal data distribution key to minimize skew.
+create table loj_bool_y2(c1 boolean);
+NOTICE:  Table doesn't have 'DISTRIBUTED BY' clause -- Using column named 'c1' as the Apache Cloudberry data distribution key for this table.
+HINT:  The 'DISTRIBUTED BY' clause determines the distribution of data. Make sure column(s) chosen are the optimal data distribution key to minimize skew.
+insert into loj_bool_x values (true), (false), (false);
+insert into loj_bool_y1 values (true);
+insert into loj_bool_y2 values (true);
+-- Expect 2 rows: the two FALSE rows in loj_bool_x, with NULL from loj_bool_y2.
+-- The plan must NOT contain "Filter: c1" on Seq Scan of loj_bool_x.
+select loj_bool_x.c1, loj_bool_y2.c1 as y2c1
+  from loj_bool_x left join loj_bool_y1 on loj_bool_x.c1
+                  left join loj_bool_y2 on loj_bool_x.c1
+ where loj_bool_y2.c1 is null
+ order by 1, 2;
+ c1 | y2c1 
+----+------
+ f  | 
+ f  | 
+(2 rows)
+
 -- Clean up. None of the objects we create are very interesting to keep around.
 reset search_path;
 set client_min_messages='warning';

contrib/pax_storage/src/test/regress/sql/bfv_joins.sql

@@ -604,6 +604,26 @@ ANALYZE ext_stats_tbl;
 
 explain SELECT 1 FROM ext_stats_tbl t11 FULL JOIN ext_stats_tbl t12 ON t12.c2;
 
+-- ORCA bug: a boolean ON-clause of a LEFT JOIN must not be pushed down as a
+-- scan filter on the outer relation. When the same outer relation feeds
+-- multiple LEFT JOINs whose ON-clauses use the same boolean column AND there
+-- is a WHERE on top, the normalizer used to push the ON-pred onto the LOJ's
+-- own outer child, discarding outer rows that should be null-padded.
+create table loj_bool_x(c1 boolean);
+create table loj_bool_y1(c1 boolean);
+create table loj_bool_y2(c1 boolean);
+insert into loj_bool_x values (true), (false), (false);
+insert into loj_bool_y1 values (true);
+insert into loj_bool_y2 values (true);
+
+-- Expect 2 rows: the two FALSE rows in loj_bool_x, with NULL from loj_bool_y2.
+-- The plan must NOT contain "Filter: c1" on Seq Scan of loj_bool_x.
+select loj_bool_x.c1, loj_bool_y2.c1 as y2c1
+  from loj_bool_x left join loj_bool_y1 on loj_bool_x.c1
+                  left join loj_bool_y2 on loj_bool_x.c1
+ where loj_bool_y2.c1 is null
+ order by 1, 2;
+
 -- Clean up. None of the objects we create are very interesting to keep around.
 reset search_path;
 set client_min_messages='warning';

src/backend/gporca/libgpopt/src/xforms/CJoinOrderDPv2.cpp

@@ -767,7 +767,7 @@ CJoinOrderDPv2::AddSelectNodeForRemainingEdges(CExpression *join_expr)
 			// we will have to repeat this check
 			pedge->m_fUsed = false;
 		}
-		else
+		else if (0 == pedge->m_loj_num)
 		{
 			// found an unused edge, this one will need to go into
 			// a select node on top of the join

src/test/regress/expected/bfv_joins.out

@@ -4235,6 +4235,36 @@ select (trunc(extract(epoch from now())) - :unix_time1) < 100 is_ok;
 (1 row)
 
 reset optimizer;
+-- ORCA bug: a boolean ON-clause of a LEFT JOIN must not be pushed down as a
+-- scan filter on the outer relation. When the same outer relation feeds
+-- multiple LEFT JOINs whose ON-clauses use the same boolean column AND there
+-- is a WHERE on top, the normalizer used to push the ON-pred onto the LOJ's
+-- own outer child, discarding outer rows that should be null-padded.
+create table loj_bool_x(c1 boolean);
+NOTICE:  Table doesn't have 'DISTRIBUTED BY' clause -- Using column named 'c1' as the Apache Cloudberry data distribution key for this table.
+HINT:  The 'DISTRIBUTED BY' clause determines the distribution of data. Make sure column(s) chosen are the optimal data distribution key to minimize skew.
+create table loj_bool_y1(c1 boolean);
+NOTICE:  Table doesn't have 'DISTRIBUTED BY' clause -- Using column named 'c1' as the Apache Cloudberry data distribution key for this table.
+HINT:  The 'DISTRIBUTED BY' clause determines the distribution of data. Make sure column(s) chosen are the optimal data distribution key to minimize skew.
+create table loj_bool_y2(c1 boolean);
+NOTICE:  Table doesn't have 'DISTRIBUTED BY' clause -- Using column named 'c1' as the Apache Cloudberry data distribution key for this table.
+HINT:  The 'DISTRIBUTED BY' clause determines the distribution of data. Make sure column(s) chosen are the optimal data distribution key to minimize skew.
+insert into loj_bool_x values (true), (false), (false);
+insert into loj_bool_y1 values (true);
+insert into loj_bool_y2 values (true);
+-- Expect 2 rows: the two FALSE rows in loj_bool_x, with NULL from loj_bool_y2.
+-- The plan must NOT contain "Filter: c1" on Seq Scan of loj_bool_x.
+select loj_bool_x.c1, loj_bool_y2.c1 as y2c1
+  from loj_bool_x left join loj_bool_y1 on loj_bool_x.c1
+                  left join loj_bool_y2 on loj_bool_x.c1
+ where loj_bool_y2.c1 is null
+ order by 1, 2;
+ c1 | y2c1 
+----+------
+ f  | 
+ f  | 
+(2 rows)
+
 -- Clean up. None of the objects we create are very interesting to keep around.
 reset search_path;
 set client_min_messages='warning';

src/test/regress/expected/bfv_joins_optimizer.out

@@ -4252,6 +4252,36 @@ select (trunc(extract(epoch from now())) - :unix_time1) < 100 is_ok;
 (1 row)
 
 reset optimizer;
+-- ORCA bug: a boolean ON-clause of a LEFT JOIN must not be pushed down as a
+-- scan filter on the outer relation. When the same outer relation feeds
+-- multiple LEFT JOINs whose ON-clauses use the same boolean column AND there
+-- is a WHERE on top, the normalizer used to push the ON-pred onto the LOJ's
+-- own outer child, discarding outer rows that should be null-padded.
+create table loj_bool_x(c1 boolean);
+NOTICE:  Table doesn't have 'DISTRIBUTED BY' clause -- Using column named 'c1' as the Apache Cloudberry data distribution key for this table.
+HINT:  The 'DISTRIBUTED BY' clause determines the distribution of data. Make sure column(s) chosen are the optimal data distribution key to minimize skew.
+create table loj_bool_y1(c1 boolean);
+NOTICE:  Table doesn't have 'DISTRIBUTED BY' clause -- Using column named 'c1' as the Apache Cloudberry data distribution key for this table.
+HINT:  The 'DISTRIBUTED BY' clause determines the distribution of data. Make sure column(s) chosen are the optimal data distribution key to minimize skew.
+create table loj_bool_y2(c1 boolean);
+NOTICE:  Table doesn't have 'DISTRIBUTED BY' clause -- Using column named 'c1' as the Apache Cloudberry data distribution key for this table.
+HINT:  The 'DISTRIBUTED BY' clause determines the distribution of data. Make sure column(s) chosen are the optimal data distribution key to minimize skew.
+insert into loj_bool_x values (true), (false), (false);
+insert into loj_bool_y1 values (true);
+insert into loj_bool_y2 values (true);
+-- Expect 2 rows: the two FALSE rows in loj_bool_x, with NULL from loj_bool_y2.
+-- The plan must NOT contain "Filter: c1" on Seq Scan of loj_bool_x.
+select loj_bool_x.c1, loj_bool_y2.c1 as y2c1
+  from loj_bool_x left join loj_bool_y1 on loj_bool_x.c1
+                  left join loj_bool_y2 on loj_bool_x.c1
+ where loj_bool_y2.c1 is null
+ order by 1, 2;
+ c1 | y2c1 
+----+------
+ f  | 
+ f  | 
+(2 rows)
+
 -- Clean up. None of the objects we create are very interesting to keep around.
 reset search_path;
 set client_min_messages='warning';

src/test/regress/sql/bfv_joins.sql

@@ -649,6 +649,26 @@ select (trunc(extract(epoch from now())) - :unix_time1) < 100 is_ok;
 
 reset optimizer;
 
+-- ORCA bug: a boolean ON-clause of a LEFT JOIN must not be pushed down as a
+-- scan filter on the outer relation. When the same outer relation feeds
+-- multiple LEFT JOINs whose ON-clauses use the same boolean column AND there
+-- is a WHERE on top, the normalizer used to push the ON-pred onto the LOJ's
+-- own outer child, discarding outer rows that should be null-padded.
+create table loj_bool_x(c1 boolean);
+create table loj_bool_y1(c1 boolean);
+create table loj_bool_y2(c1 boolean);
+insert into loj_bool_x values (true), (false), (false);
+insert into loj_bool_y1 values (true);
+insert into loj_bool_y2 values (true);
+
+-- Expect 2 rows: the two FALSE rows in loj_bool_x, with NULL from loj_bool_y2.
+-- The plan must NOT contain "Filter: c1" on Seq Scan of loj_bool_x.
+select loj_bool_x.c1, loj_bool_y2.c1 as y2c1
+  from loj_bool_x left join loj_bool_y1 on loj_bool_x.c1
+                  left join loj_bool_y2 on loj_bool_x.c1
+ where loj_bool_y2.c1 is null
+ order by 1, 2;
+
 -- Clean up. None of the objects we create are very interesting to keep around.
 reset search_path;
 set client_min_messages='warning';