[SPARK-46179][SQL] Add CrossDbmsQueryTestSuites, which runs other DBMS against golden files, starting with Postgres

sql/core/src/test/resources/sql-tests/results/subquery/exists-subquery/exists-having.sql.out → sql/core/src/test/resources/sql-tests/crossdbms-results/exists-subquery/exists-having.sql.out

@@ -1,50 +1,41 @@
--- Automatically generated by SQLQueryTestSuite
+-- Automatically generated by PostgreSQLQueryTestSuite with postgres
 -- !query
-CREATE TEMPORARY VIEW EMP AS SELECT * FROM VALUES
-  (100, "emp 1", date "2005-01-01", 100.00D, 10),
-  (100, "emp 1", date "2005-01-01", 100.00D, 10),
-  (200, "emp 2", date "2003-01-01", 200.00D, 10),
-  (300, "emp 3", date "2002-01-01", 300.00D, 20),
-  (400, "emp 4", date "2005-01-01", 400.00D, 30),
-  (500, "emp 5", date "2001-01-01", 400.00D, NULL),
-  (600, "emp 6 - no dept", date "2001-01-01", 400.00D, 100),
-  (700, "emp 7", date "2010-01-01", 400.00D, 100),
-  (800, "emp 8", date "2016-01-01", 150.00D, 70)
-AS EMP(id, emp_name, hiredate, salary, dept_id)
--- !query schema
-struct<>
+CREATE TEMPORARY VIEW EMP(id, emp_name, hiredate, salary, dept_id) AS VALUES
+  (100, 'emp 1', date '2005-01-01', double(100.00), 10),
+  (100, 'emp 1', date '2005-01-01', double(100.00), 10),
+  (200, 'emp 2', date '2003-01-01', double(200.00), 10),
+  (300, 'emp 3', date '2002-01-01', double(300.00), 20),
+  (400, 'emp 4', date '2005-01-01', double(400.00), 30),
+  (500, 'emp 5', date '2001-01-01', double(400.00), NULL),
+  (600, 'emp 6 - no dept', date '2001-01-01', double(400.00), 100),
+  (700, 'emp 7', date '2010-01-01', double(400.00), 100),
+  (800, 'emp 8', date '2016-01-01', double(150.00), 70)
 -- !query output
 
 
 
 -- !query
-CREATE TEMPORARY VIEW DEPT AS SELECT * FROM VALUES
-  (10, "dept 1", "CA"),
-  (20, "dept 2", "NY"),
-  (30, "dept 3", "TX"),
-  (40, "dept 4 - unassigned", "OR"),
-  (50, "dept 5 - unassigned", "NJ"),
-  (70, "dept 7", "FL")
-AS DEPT(dept_id, dept_name, state)
--- !query schema
-struct<>
+CREATE TEMPORARY VIEW DEPT(dept_id, dept_name, state) AS VALUES
+  (10, 'dept 1', 'CA'),
+  (20, 'dept 2', 'NY'),
+  (30, 'dept 3', 'TX'),
+  (40, 'dept 4 - unassigned', 'OR'),
+  (50, 'dept 5 - unassigned', 'NJ'),
+  (70, 'dept 7', 'FL')
 -- !query output
 
 
 
 -- !query
-CREATE TEMPORARY VIEW BONUS AS SELECT * FROM VALUES
-  ("emp 1", 10.00D),
-  ("emp 1", 20.00D),
-  ("emp 2", 300.00D),
-  ("emp 2", 100.00D),
-  ("emp 3", 300.00D),
-  ("emp 4", 100.00D),
-  ("emp 5", 1000.00D),
-  ("emp 6 - no dept", 500.00D)
-AS BONUS(emp_name, bonus_amt)
--- !query schema
-struct<>
+CREATE TEMPORARY VIEW BONUS(emp_name, bonus_amt) AS VALUES
+  ('emp 1', double(10.00)),
+  ('emp 1', double(20.00)),
+  ('emp 2', double(300.00)),
+  ('emp 2', double(100.00)),
+  ('emp 3', double(300.00)),
+  ('emp 4', double(100.00)),
+  ('emp 5', double(1000.00)),
+  ('emp 6 - no dept', double(500.00))
 -- !query output
 
 
@@ -56,8 +47,6 @@ GROUP  BY dept_id
 HAVING EXISTS (SELECT 1 
                FROM   bonus 
                WHERE  bonus_amt < min(emp.salary))
--- !query schema
-struct<dept_id:int,count(1):bigint>
 -- !query output
 10	3
 100	2
@@ -77,8 +66,6 @@ WHERE  EXISTS (SELECT dept_id,
                HAVING EXISTS (SELECT 1 
                               FROM   bonus 
                               WHERE bonus_amt < Min(emp.salary)))
--- !query schema
-struct<dept_id:int,dept_name:string,state:string>
 -- !query output
 10	dept 1	CA
 20	dept 2	NY
@@ -100,8 +87,6 @@ WHERE  EXISTS (SELECT dept_id,
                               FROM   bonus 
                               WHERE  bonus_amt < Min(p.salary))) 
 GROUP  BY gp.dept_id
--- !query schema
-struct<dept_id:int,max(salary):double>
 -- !query output
 10	200.0
 100	400.0
@@ -121,8 +106,6 @@ WHERE  EXISTS (SELECT dept_id,
                  HAVING EXISTS (SELECT 1 
                                 FROM   bonus 
                                 WHERE  bonus_amt > Min(emp.salary)))
--- !query schema
-struct<dept_id:int,dept_name:string,state:string>
 -- !query output
 10	dept 1	CA
 20	dept 2	NY
@@ -144,7 +127,5 @@ WHERE  EXISTS (SELECT dept_id,
                               FROM   bonus 
                               WHERE  ( bonus_amt > min(emp.salary) 
                                        AND count(emp.dept_id) > 1 )))
--- !query schema
-struct<dept_id:int,dept_name:string,state:string>
 -- !query output
 10	dept 1	CA

sql/core/src/test/resources/sql-tests/inputs/subquery/README.md

@@ -0,0 +1,10 @@
+
+## Note on PostgreSQLQueryTestSuite
+
+The SQL files in this directory are automatically opted into `PostgreSQLQueryTestSuite`, which
+generates golden files with Postgres and runs Spark against these golden files. If you added a new
+SQL test file, please generate the golden files with `PostgreSQLQueryTestSuite`. It is likely to
+fail because of incompatibility between the SQL dialects of Spark and Postgres. To have queries that
+are compatible for both systems, keep your SQL queries simple by using basic types like INTs and
+strings only, if possible, and using functions that are present in both Spark and Postgres. Refer
+to the header comment for `PostgreSQLQueryTestSuite` for more information.

sql/core/src/test/resources/sql-tests/inputs/subquery/exists-subquery/exists-aggregate.sql

@@ -4,6 +4,7 @@
 --CONFIG_DIM1 spark.sql.codegen.wholeStage=true
 --CONFIG_DIM1 spark.sql.codegen.wholeStage=false,spark.sql.codegen.factoryMode=CODEGEN_ONLY
 --CONFIG_DIM1 spark.sql.codegen.wholeStage=false,spark.sql.codegen.factoryMode=NO_CODEGEN
+--ONLY_IF spark
 
 CREATE TEMPORARY VIEW EMP AS SELECT * FROM VALUES
   (100, "emp 1", date "2005-01-01", 100.00D, 10),

sql/core/src/test/resources/sql-tests/inputs/subquery/exists-subquery/exists-basic.sql

@@ -1,5 +1,6 @@
 -- Tests EXISTS subquery support. Tests basic form 
 -- of EXISTS subquery (both EXISTS and NOT EXISTS)
+--ONLY_IF spark
 
 CREATE TEMPORARY VIEW EMP AS SELECT * FROM VALUES
   (100, "emp 1", date "2005-01-01", 100.00D, 10),

sql/core/src/test/resources/sql-tests/inputs/subquery/exists-subquery/exists-count-bug.sql

@@ -1,3 +1,4 @@
+--ONLY_IF spark
 create temporary view t1(c1, c2) as values (0, 1), (1, 2);
 create temporary view t2(c1, c2) as values (0, 2), (0, 3);
 create temporary view t3(c1, c2) as values (0, 3), (1, 4), (2, 5);

sql/core/src/test/resources/sql-tests/inputs/subquery/exists-subquery/exists-cte.sql

@@ -1,5 +1,6 @@
 -- Tests EXISTS subquery used along with 
 -- Common Table Expressions(CTE)
+--ONLY_IF spark
 
 CREATE TEMPORARY VIEW EMP AS SELECT * FROM VALUES
   (100, "emp 1", date "2005-01-01", 100.00D, 10),

sql/core/src/test/resources/sql-tests/inputs/subquery/exists-subquery/exists-having.sql

@@ -1,36 +1,33 @@
 -- Tests HAVING clause in subquery.
 
-CREATE TEMPORARY VIEW EMP AS SELECT * FROM VALUES
-  (100, "emp 1", date "2005-01-01", 100.00D, 10),
-  (100, "emp 1", date "2005-01-01", 100.00D, 10),
-  (200, "emp 2", date "2003-01-01", 200.00D, 10),
-  (300, "emp 3", date "2002-01-01", 300.00D, 20),
-  (400, "emp 4", date "2005-01-01", 400.00D, 30),
-  (500, "emp 5", date "2001-01-01", 400.00D, NULL),
-  (600, "emp 6 - no dept", date "2001-01-01", 400.00D, 100),
-  (700, "emp 7", date "2010-01-01", 400.00D, 100),
-  (800, "emp 8", date "2016-01-01", 150.00D, 70)
-AS EMP(id, emp_name, hiredate, salary, dept_id);
+CREATE TEMPORARY VIEW EMP(id, emp_name, hiredate, salary, dept_id) AS VALUES
+  (100, 'emp 1', date '2005-01-01', double(100.00), 10),
+  (100, 'emp 1', date '2005-01-01', double(100.00), 10),
+  (200, 'emp 2', date '2003-01-01', double(200.00), 10),
+  (300, 'emp 3', date '2002-01-01', double(300.00), 20),
+  (400, 'emp 4', date '2005-01-01', double(400.00), 30),
+  (500, 'emp 5', date '2001-01-01', double(400.00), NULL),
+  (600, 'emp 6 - no dept', date '2001-01-01', double(400.00), 100),
+  (700, 'emp 7', date '2010-01-01', double(400.00), 100),
+  (800, 'emp 8', date '2016-01-01', double(150.00), 70);
 
-CREATE TEMPORARY VIEW DEPT AS SELECT * FROM VALUES
-  (10, "dept 1", "CA"),
-  (20, "dept 2", "NY"),
-  (30, "dept 3", "TX"),
-  (40, "dept 4 - unassigned", "OR"),
-  (50, "dept 5 - unassigned", "NJ"),
-  (70, "dept 7", "FL")
-AS DEPT(dept_id, dept_name, state);
+CREATE TEMPORARY VIEW DEPT(dept_id, dept_name, state) AS VALUES
+  (10, 'dept 1', 'CA'),
+  (20, 'dept 2', 'NY'),
+  (30, 'dept 3', 'TX'),
+  (40, 'dept 4 - unassigned', 'OR'),
+  (50, 'dept 5 - unassigned', 'NJ'),
+  (70, 'dept 7', 'FL');
 
-CREATE TEMPORARY VIEW BONUS AS SELECT * FROM VALUES
-  ("emp 1", 10.00D),
-  ("emp 1", 20.00D),
-  ("emp 2", 300.00D),
-  ("emp 2", 100.00D),
-  ("emp 3", 300.00D),
-  ("emp 4", 100.00D),
-  ("emp 5", 1000.00D),
-  ("emp 6 - no dept", 500.00D)
-AS BONUS(emp_name, bonus_amt);
+CREATE TEMPORARY VIEW BONUS(emp_name, bonus_amt) AS VALUES
+  ('emp 1', double(10.00)),
+  ('emp 1', double(20.00)),
+  ('emp 2', double(300.00)),
+  ('emp 2', double(100.00)),
+  ('emp 3', double(300.00)),
+  ('emp 4', double(100.00)),
+  ('emp 5', double(1000.00)),
+  ('emp 6 - no dept', double(500.00));
 
 -- simple having in subquery. 
 -- TC.01.01

sql/core/src/test/resources/sql-tests/inputs/subquery/exists-subquery/exists-in-join-condition.sql

@@ -6,6 +6,7 @@
 -- 3. Join type: inner / left outer / right outer / full outer / left semi / left anti
 -- 4. AND or OR for the join condition
 
+--ONLY_IF spark
 CREATE TEMP VIEW x(x1, x2) AS VALUES
     (2, 1),
     (1, 1),

sql/core/src/test/resources/sql-tests/inputs/subquery/exists-subquery/exists-joins-and-set-ops.sql

@@ -13,6 +13,7 @@
 --CONFIG_DIM2 spark.sql.codegen.wholeStage=false,spark.sql.codegen.factoryMode=CODEGEN_ONLY
 --CONFIG_DIM2 spark.sql.codegen.wholeStage=false,spark.sql.codegen.factoryMode=NO_CODEGEN
 
+--ONLY_IF spark
 CREATE TEMPORARY VIEW EMP AS SELECT * FROM VALUES
   (100, "emp 1", date "2005-01-01", 100.00D, 10),
   (100, "emp 1", date "2005-01-01", 100.00D, 10),

sql/core/src/test/resources/sql-tests/inputs/subquery/exists-subquery/exists-orderby-limit.sql

@@ -5,6 +5,7 @@
 --CONFIG_DIM1 spark.sql.codegen.wholeStage=false,spark.sql.codegen.factoryMode=CODEGEN_ONLY
 --CONFIG_DIM1 spark.sql.codegen.wholeStage=false,spark.sql.codegen.factoryMode=NO_CODEGEN
 
+--ONLY_IF spark
 CREATE TEMPORARY VIEW EMP AS SELECT * FROM VALUES
   (100, "emp 1", date "2005-01-01", 100.00D, 10),
   (100, "emp 1", date "2005-01-01", 100.00D, 10),

sql/core/src/test/resources/sql-tests/inputs/subquery/exists-subquery/exists-outside-filter.sql

@@ -1,5 +1,6 @@
 -- Tests EXISTS subquery support where the subquery is used outside the WHERE clause.
 
+--ONLY_IF spark
 
 CREATE TEMPORARY VIEW EMP AS SELECT * FROM VALUES
   (100, "emp 1", date "2005-01-01", 100.00D, 10),

sql/core/src/test/resources/sql-tests/inputs/subquery/exists-subquery/exists-within-and-or.sql

@@ -1,6 +1,7 @@
 -- Tests EXISTS subquery support. Tests EXISTS 
 -- subquery within a AND or OR expression.
 
+--ONLY_IF spark
 CREATE TEMPORARY VIEW EMP AS SELECT * FROM VALUES
   (100, "emp 1", date "2005-01-01", 100.00D, 10),
   (100, "emp 1", date "2005-01-01", 100.00D, 10),

sql/core/src/test/resources/sql-tests/inputs/subquery/in-subquery/in-basic.sql

@@ -1,5 +1,6 @@
 --CONFIG_DIM1 spark.sql.optimizeNullAwareAntiJoin=true
 --CONFIG_DIM1 spark.sql.optimizeNullAwareAntiJoin=false
+--ONLY_IF spark
 
 create temporary view tab_a as select * from values (1, 1) as tab_a(a1, b1);
 create temporary view tab_b as select * from values (1, 1) as tab_b(a2, b2);

sql/core/src/test/resources/sql-tests/inputs/subquery/in-subquery/in-count-bug.sql

@@ -1,3 +1,4 @@
+--ONLY_IF spark
 create temporary view t1(c1, c2) as values (0, 1), (1, 2);
 create temporary view t2(c1, c2) as values (0, 2), (0, 3);
 create temporary view t3(c1, c2) as values (0, 3), (1, 4), (2, 5);

sql/core/src/test/resources/sql-tests/inputs/subquery/in-subquery/in-group-by.sql

@@ -6,6 +6,7 @@
 --CONFIG_DIM1 spark.sql.codegen.wholeStage=false,spark.sql.codegen.factoryMode=CODEGEN_ONLY
 --CONFIG_DIM1 spark.sql.codegen.wholeStage=false,spark.sql.codegen.factoryMode=NO_CODEGEN
 
+--ONLY_IF spark
 create temporary view t1 as select * from values
   ("t1a", 6S, 8, 10L, float(15.0), 20D, 20E2BD, timestamp '2014-04-04 01:00:00.000', date '2014-04-04'),
   ("t1b", 8S, 16, 19L, float(17.0), 25D, 26E2BD, timestamp '2014-05-04 01:01:00.000', date '2014-05-04'),

sql/core/src/test/resources/sql-tests/inputs/subquery/in-subquery/in-having.sql

@@ -4,6 +4,7 @@
 --CONFIG_DIM1 spark.sql.optimizeNullAwareAntiJoin=true
 --CONFIG_DIM1 spark.sql.optimizeNullAwareAntiJoin=false
 
+--ONLY_IF spark
 create temporary view t1 as select * from values
   ("val1a", 6S, 8, 10L, float(15.0), 20D, 20E2, timestamp '2014-04-04 01:00:00.000', date '2014-04-04'),
   ("val1b", 8S, 16, 19L, float(17.0), 25D, 26E2, timestamp '2014-05-04 01:01:00.000', date '2014-05-04'),

sql/core/src/test/resources/sql-tests/inputs/subquery/in-subquery/in-joins.sql

@@ -16,6 +16,7 @@
 --CONFIG_DIM3 spark.sql.optimizeNullAwareAntiJoin=true
 --CONFIG_DIM3 spark.sql.optimizeNullAwareAntiJoin=false
 
+--ONLY_IF spark
 create temporary view t1 as select * from values
   ("val1a", 6S, 8, 10L, float(15.0), 20D, 20E2, timestamp '2014-04-04 01:00:00.000', date '2014-04-04'),
   ("val1b", 8S, 16, 19L, float(17.0), 25D, 26E2, timestamp '2014-05-04 01:01:00.000', date '2014-05-04'),

sql/core/src/test/resources/sql-tests/inputs/subquery/in-subquery/in-limit.sql

@@ -4,6 +4,7 @@
 --CONFIG_DIM1 spark.sql.optimizeNullAwareAntiJoin=true
 --CONFIG_DIM1 spark.sql.optimizeNullAwareAntiJoin=false
 
+--ONLY_IF spark
 create temporary view t1 as select * from values
   ("val1a", 6S, 8, 10L, float(15.0), 20D, 20E2BD, timestamp '2014-04-04 01:00:00.000', date '2014-04-04'),
   ("val1b", 8S, 16, 19L, float(17.0), 25D, 26E2BD, timestamp '2014-05-04 01:01:00.000', date '2014-05-04'),

sql/core/src/test/resources/sql-tests/inputs/subquery/in-subquery/in-multiple-columns.sql

@@ -4,6 +4,7 @@
 --CONFIG_DIM1 spark.sql.optimizeNullAwareAntiJoin=true
 --CONFIG_DIM1 spark.sql.optimizeNullAwareAntiJoin=false
 
+--ONLY_IF spark
 create temporary view t1 as select * from values
   ("val1a", 6S, 8, 10L, float(15.0), 20D, 20E2, timestamp '2014-04-04 01:00:00.000', date '2014-04-04'),
   ("val1b", 8S, 16, 19L, float(17.0), 25D, 26E2, timestamp '2014-05-04 01:01:00.000', date '2014-05-04'),

sql/core/src/test/resources/sql-tests/inputs/subquery/in-subquery/in-null-semantics.sql

@@ -1,3 +1,4 @@
+--ONLY_IF spark
 create temp view v (c) as values (1), (null);
 create temp view v_empty (e) as select 1 where false;
 

sql/core/src/test/resources/sql-tests/inputs/subquery/in-subquery/in-nullability.sql

@@ -1,4 +1,5 @@
 -- SPARK-43413: Tests for IN subquery nullability
+--ONLY_IF spark
 
 create temp view t0 as select 1 as a_nonnullable;
 create temp view t1 as select cast(null as int) as b_nullable;

sql/core/src/test/resources/sql-tests/inputs/subquery/in-subquery/in-order-by.sql

@@ -8,6 +8,7 @@
 
 --CONFIG_DIM2 spark.sql.optimizeNullAwareAntiJoin=true
 --CONFIG_DIM2 spark.sql.optimizeNullAwareAntiJoin=false
+--ONLY_IF spark
 
 create temporary view t1 as select * from values
   ("val1a", 6S, 8, 10L, float(15.0), 20D, 20E2BD, timestamp '2014-04-04 01:00:00.000', date '2014-04-04'),

sql/core/src/test/resources/sql-tests/inputs/subquery/in-subquery/in-set-operations.sql

@@ -1,5 +1,6 @@
 -- A test suite for set-operations in parent side, subquery, and both predicate subquery
 -- It includes correlated cases.
+--ONLY_IF spark
 
 create temporary view t1 as select * from values
   ("val1a", 6S, 8, 10L, float(15.0), 20D, 20E2BD, timestamp '2014-04-04 01:00:00.000', date '2014-04-04'),

sql/core/src/test/resources/sql-tests/inputs/subquery/in-subquery/in-subquery-in-join-condition.sql

@@ -1,4 +1,5 @@
 -- Test that correlated EXISTS subqueries in join conditions are supported.
+--ONLY_IF spark
 
 -- Permutations of the test:
 -- 1. In / Not In

sql/core/src/test/resources/sql-tests/inputs/subquery/in-subquery/in-with-cte.sql

@@ -1,5 +1,6 @@
 -- A test suite for in with cte in parent side, subquery, and both predicate subquery
 -- It includes correlated cases.
+--ONLY_IF spark
 
 --CONFIG_DIM1 spark.sql.optimizeNullAwareAntiJoin=true
 --CONFIG_DIM1 spark.sql.optimizeNullAwareAntiJoin=false

sql/core/src/test/resources/sql-tests/inputs/subquery/in-subquery/nested-not-in.sql

@@ -1,4 +1,5 @@
 -- Tests NOT-IN subqueries nested inside OR expression(s).
+--ONLY_IF spark
 
 --CONFIG_DIM1 spark.sql.optimizeNullAwareAntiJoin=true
 --CONFIG_DIM1 spark.sql.optimizeNullAwareAntiJoin=false

sql/core/src/test/resources/sql-tests/inputs/subquery/in-subquery/not-in-group-by.sql

@@ -1,5 +1,6 @@
 -- A test suite for NOT IN GROUP BY in parent side, subquery, and both predicate subquery
 -- It includes correlated cases.
+--ONLY_IF spark
 
 -- Test aggregate operator with codegen on and off.
 --CONFIG_DIM1 spark.sql.codegen.wholeStage=true

sql/core/src/test/resources/sql-tests/inputs/subquery/in-subquery/not-in-joins.sql

@@ -1,5 +1,6 @@
 -- A test suite for not-in-joins in parent side, subquery, and both predicate subquery
 -- It includes correlated cases.
+--ONLY_IF spark
 
 --CONFIG_DIM1 spark.sql.optimizeNullAwareAntiJoin=true
 --CONFIG_DIM1 spark.sql.optimizeNullAwareAntiJoin=false

sql/core/src/test/resources/sql-tests/inputs/subquery/in-subquery/not-in-unit-tests-multi-column-literal.sql

@@ -6,6 +6,7 @@
 
 --CONFIG_DIM1 spark.sql.optimizeNullAwareAntiJoin=true
 --CONFIG_DIM1 spark.sql.optimizeNullAwareAntiJoin=false
+--ONLY_IF spark
 
 CREATE TEMPORARY VIEW m AS SELECT * FROM VALUES
   (null, null),

sql/core/src/test/resources/sql-tests/inputs/subquery/in-subquery/not-in-unit-tests-multi-column.sql

@@ -15,6 +15,7 @@
 -- This can be generalized to include more tests for more columns, but it covers the main cases
 -- when there is more than one column.
 
+--ONLY_IF spark
 --CONFIG_DIM1 spark.sql.optimizeNullAwareAntiJoin=true
 --CONFIG_DIM1 spark.sql.optimizeNullAwareAntiJoin=false
 

sql/core/src/test/resources/sql-tests/inputs/subquery/in-subquery/not-in-unit-tests-single-column-literal.sql

@@ -6,6 +6,7 @@
 
 --CONFIG_DIM1 spark.sql.optimizeNullAwareAntiJoin=true
 --CONFIG_DIM1 spark.sql.optimizeNullAwareAntiJoin=false
+--ONLY_IF spark
 
 CREATE TEMPORARY VIEW m AS SELECT * FROM VALUES
   (null, 1.0),