apply fix

Signed-off-by: Yuan <[email protected]>

Author: zhouyuan

gluten-ut/spark40/src/test/resources/backends-velox/sql-tests/inputs/charvarchar.sql

@@ -107,7 +107,9 @@ select split(c7, 'e'), split(c8, 'e'), split(v, 'a'), split(s, 'e') from char_tb
 select substring(c7, 2), substring(c8, 2), substring(v, 3), substring(s, 2) from char_tbl4;
 select left(c7, 2), left(c8, 2), left(v, 3), left(s, 2) from char_tbl4;
 select right(c7, 2), right(c8, 2), right(v, 3), right(s, 2) from char_tbl4;
+set spark.sql.optimizer.excludedRules=org.apache.spark.sql.catalyst.optimizer.ConvertToLocalRelation,org.apache.spark.sql.catalyst.optimizer.NullPropagation;
 select typeof(c7), typeof(c8), typeof(v), typeof(s) from char_tbl4 limit 1;
+set spark.sql.optimizer.excludedRules=org.apache.spark.sql.catalyst.optimizer.ConvertToLocalRelation,org.apache.spark.sql.catalyst.optimizer.ConstantFolding,org.apache.spark.sql.catalyst.optimizer.NullPropagation;
 select cast(c7 as char(1)), cast(c8 as char(10)), cast(v as char(1)), cast(v as varchar(1)), cast(s as char(5)) from char_tbl4;
 
 -- char_tbl has renamed to char_tbl1

gluten-ut/spark40/src/test/resources/backends-velox/sql-tests/inputs/count.sql

@@ -38,10 +38,12 @@ SELECT count(distinct 0.8), percentile_approx(distinct a, 0.8) FROM testData;
 
 -- legacy behavior: allow calling function count without parameters
 set spark.sql.legacy.allowParameterlessCount=true;
+set spark.sql.optimizer.excludedRules=org.apache.spark.sql.catalyst.optimizer.ConvertToLocalRelation,org.apache.spark.sql.catalyst.optimizer.ConstantFolding;
 SELECT count() FROM testData;
 
 -- count without expressions
 set spark.sql.legacy.allowParameterlessCount=false;
+set spark.sql.optimizer.excludedRules=org.apache.spark.sql.catalyst.optimizer.ConvertToLocalRelation,org.apache.spark.sql.catalyst.optimizer.ConstantFolding,org.apache.spark.sql.catalyst.optimizer.NullPropagation;
 SELECT count() FROM testData;
 
 -- legacy behavior: allow count(testData.*)

gluten-ut/spark40/src/test/resources/backends-velox/sql-tests/inputs/cte.sql

@@ -98,10 +98,12 @@ SELECT * FROM same_name, (SELECT 10) AS same_name;
 WITH same_name(x) AS (SELECT 42)
 SELECT same_name.x FROM (SELECT 10) AS same_name(x), same_name;
 
+set spark.sql.optimizer.excludedRules=org.apache.spark.sql.catalyst.optimizer.ConvertToLocalRelation,org.apache.spark.sql.catalyst.optimizer.NullPropagation;
 -- Test behavior with an unknown-type literal in the WITH
 WITH q AS (SELECT 'foo' AS x)
 SELECT x, typeof(x) FROM q;
 
+set spark.sql.optimizer.excludedRules=org.apache.spark.sql.catalyst.optimizer.ConvertToLocalRelation,org.apache.spark.sql.catalyst.optimizer.ConstantFolding,org.apache.spark.sql.catalyst.optimizer.NullPropagation;
 -- The following tests are ported from ZetaSQL
 -- Alias inside the with hides the underlying column name, should fail
 with cte as (select id as id_alias from t)

gluten-ut/spark40/src/test/resources/backends-velox/sql-tests/inputs/date.sql

@@ -27,11 +27,6 @@ select UNIX_DATE(DATE('1970-01-01')), UNIX_DATE(DATE('2020-12-04')), UNIX_DATE(n
 
 select to_date(null), to_date('2016-12-31'), to_date('2016-12-31', 'yyyy-MM-dd');
 
--- missing fields in `to_date`
-select to_date("16", "dd");
--- invalid: there is no 29 in February, 1970
-select to_date("02-29", "MM-dd");
-
 -- `dayofweek` accepts both date and timestamp ltz/ntz inputs.
 select dayofweek('2007-02-03'), dayofweek('2009-07-30'), dayofweek('2017-05-27'), dayofweek(null),
   dayofweek('1582-10-15 13:10:15'), dayofweek(timestamp_ltz'1582-10-15 13:10:15'), dayofweek(timestamp_ntz'1582-10-15 13:10:15');

gluten-ut/spark40/src/test/resources/backends-velox/sql-tests/inputs/misc-functions.sql

@@ -1,4 +1,5 @@
 -- test for misc functions
+set spark.sql.optimizer.excludedRules=org.apache.spark.sql.catalyst.optimizer.ConvertToLocalRelation,org.apache.spark.sql.catalyst.optimizer.NullPropagation;
 
 -- typeof
 select typeof(null);
@@ -9,6 +10,7 @@ select typeof(date '1986-05-23'),  typeof(timestamp '1986-05-23'), typeof(interv
 select typeof(x'ABCD'), typeof('SPARK');
 select typeof(array(1, 2)), typeof(map(1, 2)), typeof(named_struct('a', 1, 'b', 'spark'));
 
+set spark.sql.optimizer.excludedRules=org.apache.spark.sql.catalyst.optimizer.ConvertToLocalRelation,org.apache.spark.sql.catalyst.optimizer.ConstantFolding,org.apache.spark.sql.catalyst.optimizer.NullPropagation;
 -- Spark-32793: Rewrite AssertTrue with RaiseError
 SELECT assert_true(true), assert_true(boolean(1));
 SELECT assert_true(false);
@@ -40,4 +42,4 @@ SELECT raise_error(1);
 SET spark.sql.legacy.raiseErrorWithoutErrorClass=true;
 SELECT assert_true(false);
 SELECT raise_error('hello');
-SET spark.sql.legacy.raiseErrorWithoutErrorClass=false;
+SET spark.sql.legacy.raiseErrorWithoutErrorClass=false;

gluten-ut/spark40/src/test/resources/backends-velox/sql-tests/inputs/postgreSQL/window_part1.sql

@@ -214,6 +214,7 @@ FROM tenk1 WHERE unique1 < 10;
 SELECT sum(unique1) over (rows between current row and unbounded following),
 unique1, four
 FROM tenk1 WHERE unique1 < 10;
+set spark.sql.optimizer.excludedRules=org.apache.spark.sql.catalyst.optimizer.ConvertToLocalRelation,org.apache.spark.sql.catalyst.optimizer.NullPropagation;
 
 SELECT sum(unique1) over (rows between 2 preceding and 2 following),
 unique1, four
@@ -272,6 +273,7 @@ FROM tenk1 WHERE unique1 < 10;
 SELECT sum(unique1) over (rows between 2 preceding and 1 preceding),
 unique1, four
 FROM tenk1 WHERE unique1 < 10;
+set spark.sql.optimizer.excludedRules=org.apache.spark.sql.catalyst.optimizer.ConvertToLocalRelation,org.apache.spark.sql.catalyst.optimizer.ConstantFolding,org.apache.spark.sql.catalyst.optimizer.NullPropagation;
 
 SELECT sum(unique1) over (rows between 1 following and 3 following),
 unique1, four
@@ -319,8 +321,10 @@ CREATE TEMP VIEW v_window AS
 SELECT i.id, sum(i.id) over (order by i.id rows between 1 preceding and 1 following) as sum_rows
 FROM range(1, 11) i;
 
+set spark.sql.optimizer.excludedRules=org.apache.spark.sql.catalyst.optimizer.ConvertToLocalRelation,org.apache.spark.sql.catalyst.optimizer.NullPropagation;
 SELECT * FROM v_window;
 
+set spark.sql.optimizer.excludedRules=org.apache.spark.sql.catalyst.optimizer.ConvertToLocalRelation,org.apache.spark.sql.catalyst.optimizer.ConstantFolding,org.apache.spark.sql.catalyst.optimizer.NullPropagation;
 -- [SPARK-28428] Spark `exclude` always expecting `()`
 -- CREATE OR REPLACE TEMP VIEW v_window AS
 -- SELECT i, sum(i) over (order by i rows between 1 preceding and 1 following

gluten-ut/spark40/src/test/resources/backends-velox/sql-tests/inputs/postgreSQL/window_part3.sql

@@ -262,12 +262,14 @@ insert into datetimes values
 -- salary, enroll_date from empsalary;
 
 -- Show differences in offset interpretation between ROWS, RANGE, and GROUPS
+set spark.sql.optimizer.excludedRules=org.apache.spark.sql.catalyst.optimizer.ConvertToLocalRelation,org.apache.spark.sql.catalyst.optimizer.NullPropagation;
 WITH cte (x) AS (
         SELECT * FROM range(1, 36, 2)
 )
 SELECT x, (sum(x) over w)
 FROM cte
 WINDOW w AS (ORDER BY x rows between 1 preceding and 1 following);
+set spark.sql.optimizer.excludedRules=org.apache.spark.sql.catalyst.optimizer.ConvertToLocalRelation,org.apache.spark.sql.catalyst.optimizer.ConstantFolding,org.apache.spark.sql.catalyst.optimizer.NullPropagation;
 
 WITH cte (x) AS (
         SELECT * FROM range(1, 36, 2)
@@ -284,6 +286,7 @@ WINDOW w AS (ORDER BY x range between 1 preceding and 1 following);
 -- FROM cte
 -- WINDOW w AS (ORDER BY x groups between 1 preceding and 1 following);
 
+set spark.sql.optimizer.excludedRules=org.apache.spark.sql.catalyst.optimizer.ConvertToLocalRelation,org.apache.spark.sql.catalyst.optimizer.NullPropagation;
 WITH cte (x) AS (
         select 1 union all select 1 union all select 1 union all
         SELECT * FROM range(5, 50, 2)
@@ -292,6 +295,7 @@ SELECT x, (sum(x) over w)
 FROM cte
 WINDOW w AS (ORDER BY x rows between 1 preceding and 1 following);
 
+set spark.sql.optimizer.excludedRules=org.apache.spark.sql.catalyst.optimizer.ConvertToLocalRelation,org.apache.spark.sql.catalyst.optimizer.ConstantFolding,org.apache.spark.sql.catalyst.optimizer.NullPropagation;
 WITH cte (x) AS (
         select 1 union all select 1 union all select 1 union all
         SELECT * FROM range(5, 50, 2)

gluten-ut/spark40/src/test/resources/backends-velox/sql-tests/inputs/postgreSQL/window_part4.sql

@@ -362,10 +362,12 @@ SELECT i,SUM(v) OVER (ORDER BY i ROWS BETWEEN CURRENT ROW AND CURRENT ROW)
 
 SELECT i,SUM(v) OVER (ORDER BY i ROWS BETWEEN CURRENT ROW AND 1 FOLLOWING)
   FROM (VALUES(1,1),(2,2),(3,NULL),(4,NULL)) t(i,v);
+set spark.sql.optimizer.excludedRules=org.apache.spark.sql.catalyst.optimizer.ConvertToLocalRelation,org.apache.spark.sql.catalyst.optimizer.NullPropagation;
 
 SELECT i,SUM(v) OVER (ORDER BY i ROWS BETWEEN 1 PRECEDING AND 1 FOLLOWING)
   FROM (VALUES(1,1),(2,2),(3,3),(4,4)) t(i,v);
 
+set spark.sql.optimizer.excludedRules=org.apache.spark.sql.catalyst.optimizer.ConvertToLocalRelation,org.apache.spark.sql.catalyst.optimizer.ConstantFolding,org.apache.spark.sql.catalyst.optimizer.NullPropagation;
 -- [SPARK-29638] Spark handles 'NaN' as 0 in sums
 -- ensure aggregate over numeric properly recovers from NaN values
 SELECT a, b,

gluten-ut/spark40/src/test/resources/backends-velox/sql-tests/inputs/subquery/in-subquery/in-null-semantics.sql

@@ -22,12 +22,14 @@ select c, c not in (select e from t_empty) from t;
 select c, c not in (select e from v_empty) from v;
 
 -- constant null IN (empty subquery) - rewritten by NullPropagation rule
+set spark.sql.optimizer.excludedRules=org.apache.spark.sql.catalyst.optimizer.ConvertToLocalRelation,org.apache.spark.sql.catalyst.optimizer.ConstantFolding;
 
 select null in (select e from t_empty);
 select null in (select e from v_empty);
 select null not in (select e from t_empty);
 select null not in (select e from v_empty);
 
+set spark.sql.optimizer.excludedRules=org.apache.spark.sql.catalyst.optimizer.ConvertToLocalRelation,org.apache.spark.sql.catalyst.optimizer.ConstantFolding,org.apache.spark.sql.catalyst.optimizer.NullPropagation;
 -- IN subquery which is not rewritten to join - here we use IN in the ON condition because that is a case that doesn't get rewritten to join in RewritePredicateSubquery, so we can observe the execution behavior of InSubquery directly
 -- Correct results: column t2.d should be NULL because the ON condition is always false
 select * from t left join t2 on (t.c in (select e from t_empty)) is null;
@@ -45,12 +47,14 @@ set spark.sql.legacy.nullInEmptyListBehavior = true;
 set spark.sql.optimizer.optimizeUncorrelatedInSubqueriesInJoinCondition.enabled=false;
 
 -- constant null IN (empty subquery) - rewritten by NullPropagation rule
+set spark.sql.optimizer.excludedRules=org.apache.spark.sql.catalyst.optimizer.ConvertToLocalRelation,org.apache.spark.sql.catalyst.optimizer.ConstantFolding;
 
 select null in (select e from t_empty);
 select null in (select e from v_empty);
 select null not in (select e from t_empty);
 select null not in (select e from v_empty);
 
+set spark.sql.optimizer.excludedRules=org.apache.spark.sql.catalyst.optimizer.ConvertToLocalRelation,org.apache.spark.sql.catalyst.optimizer.ConstantFolding,org.apache.spark.sql.catalyst.optimizer.NullPropagation;
 -- IN subquery which is not rewritten to join - here we use IN in the ON condition because that is a case that doesn't get rewritten to join in RewritePredicateSubquery, so we can observe the execution behavior of InSubquery directly
 -- Correct results: column t2.d should be NULL because the ON condition is always false
 select * from t left join t2 on (t.c in (select e from t_empty)) is null;