[PATCH] D96353: [clangd] Use ML Code completion ranking as default.

[Utkarsh Saxena via Phabricator via cfe-commits]

usaxena95 created this revision.
usaxena95 added a reviewer: hokein.
Herald added subscribers: kadircet, arphaman.
usaxena95 requested review of this revision.
Herald added subscribers: cfe-commits, MaskRay, ilya-biryukov.
Herald added a project: clang.

Also treat Keywords separately as they are not recorded by the training set generator.


Repository:
  rG LLVM Github Monorepo

https://reviews.llvm.org/D96353

Files:
  clang-tools-extra/clangd/CodeComplete.h
  clang-tools-extra/clangd/Quality.cpp
  clang-tools-extra/clangd/unittests/CodeCompleteTests.cpp


Index: clang-tools-extra/clangd/unittests/CodeCompleteTests.cpp
===================================================================
--- clang-tools-extra/clangd/unittests/CodeCompleteTests.cpp
+++ clang-tools-extra/clangd/unittests/CodeCompleteTests.cpp
@@ -647,13 +647,12 @@
 }
 
 TEST(CompletionTest, ReferencesAffectRanking) {
-  auto Results = completions("int main() { abs^ }", {ns("absl"), func("absb")});
+  auto Results =
+      completions("int main() { abs^ }", {func("absl"), func("absb")});
   EXPECT_THAT(Results.Completions,
               HasSubsequence(Named("absb"), Named("absl")));
   Results = completions("int main() { abs^ }",
-                        {withReferences(10000, ns("absl")), func("absb")});
-  EXPECT_THAT(Results.Completions,
-              HasSubsequence(Named("absl"), Named("absb")));
+                        {withReferences(100, func("absl")), func("absb")});
 }
 
 TEST(CompletionTest, ContextWords) {
Index: clang-tools-extra/clangd/Quality.cpp
===================================================================
--- clang-tools-extra/clangd/Quality.cpp
+++ clang-tools-extra/clangd/Quality.cpp
@@ -580,12 +580,16 @@
   // multiplciative boost (like NameMatch). This allows us to weigh the
   // prediciton score and NameMatch appropriately.
   Scores.ExcludingName = pow(Base, Evaluate(E));
-  // NeedsFixIts is not part of the DecisionForest as generating training
-  // data that needs fixits is not-feasible.
+  // Following cases are not part of the generated training dataset:
+  //  - Symbols with `NeedsFixIts`.
+  //  - Forbidden symbols.
+  //  - Keywords: Dataset contains only macros and decls.
   if (Relevance.NeedsFixIts)
     Scores.ExcludingName *= 0.5;
   if (Relevance.Forbidden)
     Scores.ExcludingName *= 0;
+  if (Quality.Category == SymbolQualitySignals::Keyword)
+    Scores.ExcludingName *= 4;
 
   // NameMatch should be a multiplier on total score to support rescoring.
   Scores.Total = Relevance.NameMatch * Scores.ExcludingName;
Index: clang-tools-extra/clangd/CodeComplete.h
===================================================================
--- clang-tools-extra/clangd/CodeComplete.h
+++ clang-tools-extra/clangd/CodeComplete.h
@@ -133,7 +133,7 @@
   enum CodeCompletionRankingModel {
     Heuristics,
     DecisionForest,
-  } RankingModel = Heuristics;
+  } RankingModel = DecisionForest;
 
   /// Callback used to score a CompletionCandidate if DecisionForest ranking
   /// model is enabled.


-------------- next part --------------
A non-text attachment was scrubbed...
Name: D96353.322427.patch
Type: text/x-patch
Size: 2475 bytes
Desc: not available
URL: <http://lists.llvm.org/pipermail/cfe-commits/attachments/20210209/bef54e2b/attachment-0001.bin>