YQL-19747 Enable custom NameSet and FrequencyData

Clients might want to use custom `NameSet` and `FrequencyData` in their environment, for example, to get their private UDFs and to have more relevant ranking that includes their private UDF and respect their usage pattern.

To achieve this goal I decided to load pure `NameSet` and `FrequencyData` and provide functions for pruning. Also I checked defaults and decided that it is more common for a client to create a `StaticNameService` from pure `NameSet` and `FrequencyData` to keep their pruning consistent.

I also extracted a separate module `ranking`. It will be needed when I will implement `UnionNameService` to union `StaticNameService` and `SchemaNameService`. `UnionNameService` will load `Limit` names from each child and then crop them to sorted prefix of length `Limit` using `IRanking`.

---

- Related to `YQL-19747`
- Related to https://github.com/ydb-platform/ydb/issues/9056
- Related to https://github.com/vityaman/ydb/issues/14

---

Pull Request resolved: https://github.com/ytsaurus/ytsaurus/pull/1246

Co-authored-by: vvvv <[email protected]>
Co-authored-by: vvvv <[email protected]>
commit_hash:cdca301a58a34e56d537a447b4ff779cd70faea6

1 files changed, 10 insertions, 11 deletions

diff --git a/yql/essentials/sql/v1/complete/sql_complete_ut.cpp b/yql/essentials/sql/v1/complete/sql_complete_ut.cpp
index b614f561492..54bcc35233f 100644
--- a/yql/essentials/sql/v1/complete/sql_complete_ut.cpp
+++ b/yql/essentials/sql/v1/complete/sql_complete_ut.cpp
@@ -1,8 +1,8 @@
 #include "sql_complete.h"
 
-#include <yql/essentials/sql/v1/complete/name/service/static/frequency.h>
+#include <yql/essentials/sql/v1/complete/name/service/ranking/frequency.h>
+#include <yql/essentials/sql/v1/complete/name/service/ranking/ranking.h>
 #include <yql/essentials/sql/v1/complete/name/service/static/name_service.h>
-#include <yql/essentials/sql/v1/complete/name/service/static/ranking.h>
 
 #include <yql/essentials/sql/v1/lexer/lexer.h>
 #include <yql/essentials/sql/v1/lexer/antlr4_pure/lexer.h>
@@ -49,7 +49,7 @@ Y_UNIT_TEST_SUITE(SqlCompleteTests) {
 
     ISqlCompletionEngine::TPtr MakeSqlCompletionEngineUT() {
         TLexerSupplier lexer = MakePureLexerSupplier();
-        NameSet names = {
+        TNameSet names = {
             .Pragmas = {"yson.CastToString"},
             .Types = {"Uint64"},
             .Functions = {"StartsWith", "DateTime::Split"},
@@ -58,8 +58,8 @@ Y_UNIT_TEST_SUITE(SqlCompleteTests) {
                 {EStatementKind::Insert, {"EXPIRATION"}},
             },
         };
-        auto ranking = MakeDefaultRanking({});
-        INameService::TPtr service = MakeStaticNameService(std::move(names), std::move(ranking));
+        TFrequencyData frequency = {};
+        INameService::TPtr service = MakeStaticNameService(std::move(names), std::move(frequency));
         return MakeSqlCompletionEngine(std::move(lexer), std::move(service));
     }
 
@@ -669,8 +669,7 @@ Y_UNIT_TEST_SUITE(SqlCompleteTests) {
     }
 
     Y_UNIT_TEST(DefaultNameService) {
-        auto set = MakeDefaultNameSet();
-        auto service = MakeStaticNameService(std::move(set), MakeDefaultRanking());
+        auto service = MakeStaticNameService(LoadDefaultNameSet(), LoadFrequencyData());
         auto engine = MakeSqlCompletionEngine(MakePureLexerSupplier(), std::move(service));
         {
             TVector<TCandidate> expected = {
@@ -711,10 +710,8 @@ Y_UNIT_TEST_SUITE(SqlCompleteTests) {
     }
 
     Y_UNIT_TEST(NameNormalization) {
-        auto set = MakeDefaultNameSet();
-        auto service = MakeStaticNameService(std::move(set), MakeDefaultRanking());
+        auto service = MakeStaticNameService(LoadDefaultNameSet(), LoadFrequencyData());
         auto engine = MakeSqlCompletionEngine(MakePureLexerSupplier(), std::move(service));
-
         TVector<TCandidate> expected = {
             {HintName, "IGNORE_TYPE_V3"},
         };
@@ -749,7 +746,9 @@ Y_UNIT_TEST_SUITE(SqlCompleteTests) {
                 {"unordered", 2},
             },
         };
-        auto service = MakeStaticNameService(MakeDefaultNameSet(), MakeDefaultRanking(frequency));
+        auto service = MakeStaticNameService(
+            Pruned(LoadDefaultNameSet(), LoadFrequencyData()),
+            std::move(frequency));
         auto engine = MakeSqlCompletionEngine(MakePureLexerSupplier(), std::move(service));
         {
             TVector<TCandidate> expected = {