Fix TOTALS/ROLLUP/CUBE for aggregate functions with -State and Nullable arguments #12163

src/AggregateFunctions/AggregateFunctionNull.cpp

@@ -2,6 +2,7 @@
 #include <AggregateFunctions/AggregateFunctionNull.h>
 #include <AggregateFunctions/AggregateFunctionNothing.h>
 #include <AggregateFunctions/AggregateFunctionCount.h>
+#include <AggregateFunctions/AggregateFunctionState.h>
 #include <AggregateFunctions/AggregateFunctionCombinatorFactory.h>
 #include "registerAggregateFunctions.h"
 
@@ -36,6 +37,19 @@ public:
         const DataTypes & arguments,
         const Array & params) const override
     {
+        /// If applied to aggregate function with -State combinator, we apply -Null combinator to it's nested_function instead of itself.
+        /// Because Nullable AggregateFunctionState does not make sense and ruins the logic of managing aggregate function states.
+
+        if (const AggregateFunctionState * function_state = typeid_cast<const AggregateFunctionState *>(nested_function.get()))
+        {
+            auto transformed_nested_function = transformAggregateFunction(function_state->getNestedFunction(), properties, arguments, params);
+
+            return std::make_shared<AggregateFunctionState>(
+                transformed_nested_function,
+                transformed_nested_function->getArgumentTypes(),
+                transformed_nested_function->getParameters());
+        }
+
         bool has_nullable_types = false;
         bool has_null_types = false;
         for (const auto & arg_type : arguments)

src/Functions/FunctionsBitmap.cpp

@@ -1,7 +1,6 @@
 #include <Functions/FunctionFactory.h>
 
-// TODO include this last because of a broken roaring header. See the comment
+// TODO include this last because of a broken roaring header. See the comment inside.
-// inside.
 #include <Functions/FunctionsBitmap.h>
 
 

tests/queries/0_stateless/01380_nullable_state.reference

@@ -0,0 +1,64 @@
+0100012CCBC234
+
+0100012CCBC234
+---
+0100012CCBC234
+
+0100012CCBC234
+---
+0100012CCBC234
+
+0100012CCBC234
+---
+0100012CCBC234
+
+0100012CCBC234
+---
+0100012CCBC234
+
+0100012CCBC234
+---
+0100012CCBC234
+
+0100012CCBC234
+---
+1
+
+1
+---
+0	1
+1	1
+2	1
+3	1
+4	1
+
+0	1
+---
+0	1
+1	1
+2	1
+3	1
+4	1
+
+0	1
+---
+0	[0]
+1	[0]
+2	[0]
+3	[0]
+4	[0]
+
+0	[0]
+---
+0	[0]
+1	[0]
+2	[0]
+3	[0]
+4	[0]
+
+\N	[0]
+---
+0100012CCBC234
+---
+0100012CCBC234
+---

tests/queries/0_stateless/01380_nullable_state.sql

@@ -0,0 +1,26 @@
+SELECT hex(toString(uniqState(toNullable(1)))) WITH TOTALS;
+SELECT '---';
+SELECT hex(toString(uniqState(x))) FROM (SELECT toNullable(1) AS x) WITH TOTALS;
+SELECT '---';
+SELECT DISTINCT hex(toString(uniqState(x))) FROM (SELECT materialize(1) AS k, toNullable(1) AS x FROM numbers(1)) GROUP BY k WITH TOTALS ORDER BY k;
+SELECT '---';
+SELECT DISTINCT hex(toString(uniqState(x))) FROM (SELECT materialize(1) AS k, toNullable(1) AS x FROM numbers(10)) GROUP BY k WITH TOTALS ORDER BY k;
+SELECT '---';
+SELECT DISTINCT hex(toString(uniqState(x))) FROM (SELECT intDiv(number, 3) AS k, toNullable(1) AS x FROM numbers(10)) GROUP BY k WITH TOTALS ORDER BY k;
+SELECT '---';
+SELECT DISTINCT hex(toString(uniqState(x))) FROM (SELECT intDiv(number, 3) AS k, toNullable(1) AS x FROM system.numbers LIMIT 100000) GROUP BY k WITH TOTALS ORDER BY k;
+SELECT '---';
+SELECT DISTINCT arrayUniq(finalizeAggregation(groupArrayState(x))) FROM (SELECT intDiv(number, 3) AS k, toNullable(1) AS x FROM system.numbers LIMIT 100000) GROUP BY k WITH TOTALS ORDER BY k;
+SELECT '---';
+SELECT k, finalizeAggregation(uniqState(x)) FROM (SELECT intDiv(number, 3) AS k, toNullable(1) AS x FROM system.numbers LIMIT 100000) GROUP BY k WITH TOTALS ORDER BY k LIMIT 5;
+SELECT '---';
+SELECT k, finalizeAggregation(uniqState(x)) FROM (WITH toNullable(number = 3 ? 3 : 1) AS d SELECT intDiv(number, 3) AS k, number % d AS x FROM system.numbers LIMIT 100000) GROUP BY k WITH TOTALS ORDER BY k LIMIT 5;
+SELECT '---';
+SELECT k, finalizeAggregation(quantilesTimingState(0.5)(x)) FROM (WITH toNullable(number = 3 ? 3 : 1) AS d SELECT intDiv(number, 3) AS k, number % d AS x FROM system.numbers LIMIT 100000) GROUP BY k WITH TOTALS ORDER BY k LIMIT 5;
+SELECT '---';
+SELECT k, finalizeAggregation(quantilesTimingState(0.5)(x)) FROM (SELECT intDiv(number, if(number = 9223372036854775807, -2, if(number = 3, number = if(number = 1, NULL, 3), 1)) AS d) AS k, number % d AS x FROM system.numbers LIMIT 100000) GROUP BY k WITH TOTALS ORDER BY k ASC LIMIT 5;
+SELECT '---';
+SELECT DISTINCT hex(toString(uniqState(x))) FROM (SELECT materialize(1) AS k, toNullable(1) AS x FROM numbers(1)) GROUP BY k WITH ROLLUP ORDER BY k;
+SELECT '---';
+SELECT DISTINCT hex(toString(uniqState(x))) FROM (SELECT materialize(1) AS k, toNullable(1) AS x FROM numbers(1)) GROUP BY k WITH CUBE ORDER BY k;
+SELECT '---';