Rewrite countDistinctIf with count_distinct_implementation configuration.

src/Core/Settings.h

@@ -25,7 +25,7 @@ class IColumn;
 
 /** List of settings: type, name, default value, description, flags
   *
-  * This looks rather unconvenient. It is done that way to avoid repeating settings in different places.
+  * This looks rather inconvenient. It is done that way to avoid repeating settings in different places.
   * Note: as an alternative, we could implement settings to be completely dynamic in form of map: String -> Field,
   *  but we are not going to do it, because settings is used everywhere as static struct fields.
   *
@@ -488,6 +488,7 @@ class IColumn;
     M(Bool, optimize_move_functions_out_of_any, false, "Move functions out of aggregate functions 'any', 'anyLast'.", 0) \
     M(Bool, optimize_normalize_count_variants, true, "Rewrite aggregate functions that semantically equals to count() as count().", 0) \
     M(Bool, optimize_injective_functions_inside_uniq, true, "Delete injective functions of one argument inside uniq*() functions.", 0) \
+    M(Bool, optimize_rewrite_count_distinct_if, false, "Rewrite countDistinctIf with count_distinct_implementation configuration", 0) \
     M(Bool, convert_query_to_cnf, false, "Convert SELECT query to CNF", 0) \
     M(Bool, optimize_or_like_chain, false, "Optimize multiple OR LIKE into multiMatchAny. This optimization should not be enabled by default, because it defies index analysis in some cases.", 0) \
     M(Bool, optimize_arithmetic_operations_in_aggregate_functions, true, "Move arithmetic operations out of aggregation functions", 0) \

src/Core/SettingsChangesHistory.h

@@ -85,7 +85,8 @@ static std::map<ClickHouseVersion, SettingsChangesHistory::SettingsChanges> sett
               {"input_format_csv_detect_header", false, true, "Detect header in CSV format by default"},
               {"input_format_tsv_detect_header", false, true, "Detect header in TSV format by default"},
               {"input_format_custom_detect_header", false, true, "Detect header in CustomSeparated format by default"},
-              {"query_plan_remove_redundant_sorting", false, true, "Remove redundant sorting in query plan. For example, sorting steps related to ORDER BY clauses in subqueries"}}},
+              {"query_plan_remove_redundant_sorting", false, true, "Remove redundant sorting in query plan. For example, sorting steps related to ORDER BY clauses in subqueries"},
+              {"optimize_rewrite_count_distinct_if", false, true, "Rewrite countDistinctIf with count_distinct_implementation configuration"}}},
     {"22.12", {{"max_size_to_preallocate_for_aggregation", 10'000'000, 100'000'000, "This optimizes performance"},
                {"query_plan_aggregation_in_order", 0, 1, "Enable some refactoring around query plan"},
                {"format_binary_max_string_size", 0, 1_GiB, "Prevent allocating large amount of memory"}}},

src/Interpreters/TreeRewriter.cpp

@@ -109,6 +109,9 @@ using CustomizeCountDistinctVisitor = InDepthNodeVisitor<OneTypeMatcher<Customiz
 char countifdistinct[] = "countifdistinct";
 using CustomizeCountIfDistinctVisitor = InDepthNodeVisitor<OneTypeMatcher<CustomizeFunctionsData<countifdistinct>>, true>;
 
+char countdistinctif[] = "countdistinctif";
+using CustomizeCountDistinctIfVisitor = InDepthNodeVisitor<OneTypeMatcher<CustomizeFunctionsData<countdistinctif>>, true>;
+
 char in[] = "in";
 using CustomizeInVisitor = InDepthNodeVisitor<OneTypeMatcher<CustomizeFunctionsData<in>>, true>;
 
@@ -1410,6 +1413,12 @@ void TreeRewriter::normalize(
     CustomizeIfDistinctVisitor::Data data_distinct_if{"DistinctIf"};
     CustomizeIfDistinctVisitor(data_distinct_if).visit(query);
 
+    if (settings.optimize_rewrite_count_distinct_if)
+    {
+        CustomizeCountDistinctIfVisitor::Data data_count_distinct_if{settings.count_distinct_implementation.toString() + "If"};
+        CustomizeCountDistinctIfVisitor(data_count_distinct_if).visit(query);
+    }
+
     ExistsExpressionVisitor::Data exists;
     ExistsExpressionVisitor(exists).visit(query);
 

tests/queries/0_stateless/02541_optimize_rewrite_count_distinct_if.reference

@@ -0,0 +1,6 @@
+2
+SELECT countDistinctIf(number % 10, (number % 5) = 2)
+FROM numbers_mt(1000000)
+2
+SELECT uniqExactIf(number % 10, (number % 5) = 2)
+FROM numbers_mt(1000000)

tests/queries/0_stateless/02541_optimize_rewrite_count_distinct_if.sql

@@ -0,0 +1,8 @@
+SET optimize_rewrite_count_distinct_if = FALSE;
+SELECT countDistinctIf(number % 10, number % 5 = 2) FROM numbers_mt(1000000);
+EXPLAIN SYNTAX SELECT countDistinctIf(number % 10, number % 5 = 2) FROM numbers_mt(1000000);
+
+SET optimize_rewrite_count_distinct_if = TRUE;
+SELECT countDistinctIf(number % 10, number % 5 = 2) FROM numbers_mt(1000000);
+EXPLAIN SYNTAX SELECT countDistinctIf(number % 10, number % 5 = 2) FROM numbers_mt(1000000);
+