branch-3.0: [fix](orc) dont't push down null aware predicate #47625

be/src/vec/exec/format/orc/vorc_reader.cpp

@@ -716,7 +716,10 @@ bool OrcReader::_check_expr_can_push_down(const VExprSPtr& expr) {
     case TExprOpcode::NE:
     case TExprOpcode::FILTER_IN:
     case TExprOpcode::FILTER_NOT_IN:
-        return _check_slot_can_push_down(expr) && _check_rest_children_can_push_down(expr);
+        // can't push down if expr is null aware predicate
+        return expr->node_type() != TExprNodeType::NULL_AWARE_BINARY_PRED &&
+               expr->node_type() != TExprNodeType::NULL_AWARE_IN_PRED &&
+               _check_slot_can_push_down(expr) && _check_rest_children_can_push_down(expr);
 
     case TExprOpcode::INVALID_OPCODE:
         if (expr->node_type() == TExprNodeType::FUNCTION_CALL) {

docker/thirdparties/docker-compose/hive/scripts/data/multi_catalog/orc_predicate/orc_predicate_table.hql

@@ -14,3 +14,25 @@ create table type_changed_table (
 ) stored as orc;
 insert into type_changed_table values (1, 'Alice'), (2, 'Bob'), (3, 'Charlie');
 ALTER TABLE type_changed_table CHANGE COLUMN id id STRING;
+
+CREATE TABLE table_a (
+    id INT,
+    age INT
+) STORED AS ORC;
+
+INSERT INTO table_a VALUES
+(1, null),
+(2, 18),
+(3, null),
+(4, 25);
+
+CREATE TABLE table_b (
+    id INT,
+    age INT
+) STORED AS ORC;
+
+INSERT INTO table_b VALUES
+(1, null),
+(2, null),
+(3, 1000000),
+(4, 100);

regression-test/data/external_table_p0/hive/test_hive_orc_predicate.out

@@ -13,6 +13,10 @@
 -- !predicate_changed_type3 --
 3	Charlie
 
+-- !predicate_null_aware_equal_in_rt --
+1	\N	1	\N
+3	\N	1	\N
+
 -- !predicate_fixed_char1 --
 1	a
 
@@ -27,3 +31,7 @@
 -- !predicate_changed_type3 --
 3	Charlie
 
+-- !predicate_null_aware_equal_in_rt --
+1	\N	1	\N
+3	\N	1	\N
+

regression-test/suites/external_table_p0/hive/test_hive_orc_predicate.groovy

@@ -43,6 +43,8 @@ suite("test_hive_orc_predicate", "p0,external,hive,external_docker,external_dock
             qt_predicate_changed_type2 """ select * from type_changed_table where id = '2';"""
             qt_predicate_changed_type3 """ select * from type_changed_table where id = '3';"""
 
+            qt_predicate_null_aware_equal_in_rt """select * from table_a inner join table_b on table_a.age <=> table_b.age and table_b.id in (1,3);"""
+
             sql """drop catalog if exists ${catalog_name}"""
         } finally {
         }