1 files changed, 43 insertions, 0 deletions
diff --git a/clang-tools-extra/clangd/index/SymbolCollector.cpp b/clang-tools-extra/clangd/index/SymbolCollector.cpp
index 9e9df7fd9d5..6af4a4ead01 100644
--- a/clang-tools-extra/clangd/index/SymbolCollector.cpp
+++ b/clang-tools-extra/clangd/index/SymbolCollector.cpp
@@ -89,6 +89,46 @@ llvm::Optional<std::string> toURI(const SourceManager &SM, StringRef Path,
   return llvm::None;
 }
 
+// All proto generated headers should start with this line.
+static const char *PROTO_HEADER_COMMENT =
+    "// Generated by the protocol buffer compiler.  DO NOT EDIT!";
+
+// Checks whether the decl is a private symbol in a header generated by
+// protobuf compiler.
+// To identify whether a proto header is actually generated by proto compiler,
+// we check whether it starts with PROTO_HEADER_COMMENT.
+// FIXME: make filtering extensible when there are more use cases for symbol
+// filters.
+bool isPrivateProtoDecl(const NamedDecl &ND) {
+  const auto &SM = ND.getASTContext().getSourceManager();
+  auto Loc = findNameLoc(&ND);
+  auto FileName = SM.getFilename(Loc);
+  if (!FileName.endswith(".proto.h") && !FileName.endswith(".pb.h"))
+    return false;
+  auto FID = SM.getFileID(Loc);
+  // Double check that this is an actual protobuf header.
+  if (!SM.getBufferData(FID).startswith(PROTO_HEADER_COMMENT))
+    return false;
+
+  // ND without identifier can be operators.
+  if (ND.getIdentifier() == nullptr)
+    return false;
+  auto Name = ND.getIdentifier()->getName();
+  if (!Name.contains('_'))
+    return false;
+  // 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.
+  // For enum constants, 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.
+  // FIXME: the heuristic relies on naming style (i.e. no underscore in
+  // user-defined names) and can be improved.
+  return (ND.getKind() != Decl::EnumConstant) ||
+         std::any_of(Name.begin(), Name.end(), islower);
+}
+
 bool shouldFilterDecl(const NamedDecl *ND, ASTContext *ASTCtx,
                       const SymbolCollector::Options &Opts) {
   using namespace clang::ast_matchers;
@@ -129,6 +169,9 @@ bool shouldFilterDecl(const NamedDecl *ND, ASTContext *ASTCtx,
           .empty())
     return true;
 
+  // Avoid indexing internal symbols in protobuf generated headers.
+  if (isPrivateProtoDecl(*ND))
+    return true;
   return false;
 }