[PATCH] D46751: [clangd] Filter out private proto symbols in SymbolCollector.

[Eric Liu via Phabricator via cfe-commits]

ioeric created this revision.
ioeric added a reviewer: ilya-biryukov.
Herald added subscribers: cfe-commits, jkorous, MaskRay, klimek.

This uses heuristics to identify private proto symbols. For example,
top-level symbols whose name contains "_" are considered private. These symbols
are not expected to be used by users.


Repository:
  rCTE Clang Tools Extra

https://reviews.llvm.org/D46751

Files:
  clangd/index/SymbolCollector.cpp
  unittests/clangd/SymbolCollectorTests.cpp


Index: unittests/clangd/SymbolCollectorTests.cpp
===================================================================
--- unittests/clangd/SymbolCollectorTests.cpp
+++ unittests/clangd/SymbolCollectorTests.cpp
@@ -697,6 +697,23 @@
                            AllOf(QName("pörk"), DeclRange(Header.range()))));
 }
 
+TEST_F(SymbolCollectorTest, FilterPrivateProtoSymbols) {
+  TestHeaderName = testPath("x.proto.h");
+  const std::string Header = R"(
+  namespace nx {
+    class Top_Level {};
+    class TopLevel {};
+    enum Kind {
+      KIND_OK,
+      Kind_Not_Ok,
+    };
+  }
+  )";
+  runSymbolCollector(Header, /*Main=*/"");
+  EXPECT_THAT(Symbols, UnorderedElementsAre(QName("nx"), QName("nx::TopLevel"),
+                                            QName("nx::Kind"),
+                                            QName("nx::KIND_OK")));
+}
 
 } // namespace
 } // namespace clangd
Index: clangd/index/SymbolCollector.cpp
===================================================================
--- clangd/index/SymbolCollector.cpp
+++ clangd/index/SymbolCollector.cpp
@@ -90,6 +90,28 @@
   return llvm::None;
 }
 
+bool isPrivateProtoSymbol(const NamedDecl *ND, const SourceManager &SM) {
+  auto FileName = SM.getFilename(findNameLoc(ND));
+  if (FileName.endswith(".proto.h") || FileName.endswith(".pb.h")) {
+    auto Name = ND->getName();
+    // Nested proto entities (e.g. Message::Nested) have top-level decls
+    // that shouldn't be used (Message_Nested). Ignore them completely.
+    // The nested entities are dangling type aliases, we may want to reconsider
+    // including them in the future
+    if (Name.contains('_')) {
+      if (ND->getKind() == Decl::EnumConstant) {
+        // SOME_ENUM_CONSTANT is not private and should be indexed.
+        // Outer_INNER is private.
+        // This heuristic relies on naming style, it will include OUTER_INNER
+        // and exclude some_enum_constant.
+        return std::any_of(Name.begin(), Name.end(), islower);
+      }
+      return true;
+    }
+  }
+  return false;
+}
+
 bool shouldFilterDecl(const NamedDecl *ND, ASTContext *ASTCtx,
                       const SymbolCollector::Options &Opts) {
   using namespace clang::ast_matchers;
@@ -130,6 +152,9 @@
           .empty())
     return true;
 
+  if (isPrivateProtoSymbol(ND, ASTCtx->getSourceManager()))
+    return true;
+
   return false;
 }
 


-------------- next part --------------
A non-text attachment was scrubbed...
Name: D46751.146313.patch
Type: text/x-patch
Size: 2381 bytes
Desc: not available
URL: <http://lists.llvm.org/pipermail/cfe-commits/attachments/20180511/96a197a6/attachment.bin>