diff --git a/clang-tools-extra/clangd/CMakeLists.txt b/clang-tools-extra/clangd/CMakeLists.txt
--- a/clang-tools-extra/clangd/CMakeLists.txt
+++ b/clang-tools-extra/clangd/CMakeLists.txt
@@ -63,6 +63,7 @@
   JSONTransport.cpp
   Logger.cpp
   PathMapping.cpp
+  Protobuf.cpp
   Protocol.cpp
   Quality.cpp
   ParsedAST.cpp
diff --git a/clang-tools-extra/clangd/Protobuf.h b/clang-tools-extra/clangd/Protobuf.h
new file mode 100644
--- /dev/null
+++ b/clang-tools-extra/clangd/Protobuf.h
@@ -0,0 +1,24 @@
+//===--- Protobuf.h -  ------------------------------------------*- C++ -*-===//
+//
+// Part of the LLVM Project, under the Apache License v2.0 with LLVM Exceptions.
+// See https://llvm.org/LICENSE.txt for license information.
+// SPDX-License-Identifier: Apache-2.0 WITH LLVM-exception
+//
+//===----------------------------------------------------------------------===//
+
+#ifndef LLVM_CLANG_TOOLS_EXTRA_CLANGD_PROTOBUF_H
+#define LLVM_CLANG_TOOLS_EXTRA_CLANGD_PROTOBUF_H
+
+#include "clang/AST/Decl.h"
+
+namespace clang {
+namespace clangd {
+
+/// Checks whether the decl is a private symbol in a header generated by
+/// protobuf compiler.
+bool isPrivateProtoDecl(const NamedDecl &ND);
+
+} // namespace clangd
+} // namespace clang
+
+#endif // LLVM_CLANG_TOOLS_EXTRA_CLANGD_PROTOBUF_H
diff --git a/clang-tools-extra/clangd/Protobuf.cpp b/clang-tools-extra/clangd/Protobuf.cpp
new file mode 100644
--- /dev/null
+++ b/clang-tools-extra/clangd/Protobuf.cpp
@@ -0,0 +1,54 @@
+//===--- Protobuf.cpp -------------------------------------------*- C++ -*-===//
+//
+// Part of the LLVM Project, under the Apache License v2.0 with LLVM Exceptions.
+// See https://llvm.org/LICENSE.txt for license information.
+// SPDX-License-Identifier: Apache-2.0 WITH LLVM-exception
+//
+//===----------------------------------------------------------------------===//
+
+#include "Protobuf.h"
+#include "AST.h"
+#include "clang/AST/ASTContext.h"
+#include "clang/AST/Decl.h"
+
+namespace clang {
+namespace clangd {
+
+// All proto generated headers should start with this line.
+static const char *PROTO_HEADER_COMMENT =
+    "// Generated by the protocol buffer compiler.  DO NOT EDIT!";
+
+// 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 = nameLocation(ND, SM);
+  auto FileName = SM.getFilename(Loc);
+  if (!FileName.endswith(".proto.h") && !FileName.endswith(".pb.h"))
+    return false;
+  auto FID = SM.getFileID(Loc);
+  // To identify whether a proto header is actually generated by proto compiler,
+  // we check whether it starts with PROTO_HEADER_COMMENT.
+  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) || llvm::any_of(Name, islower);
+}
+
+} // namespace clangd
+} // namespace clang
diff --git a/clang-tools-extra/clangd/index/SymbolCollector.cpp b/clang-tools-extra/clangd/index/SymbolCollector.cpp
--- a/clang-tools-extra/clangd/index/SymbolCollector.cpp
+++ b/clang-tools-extra/clangd/index/SymbolCollector.cpp
@@ -13,6 +13,7 @@
 #include "CodeCompletionStrings.h"
 #include "ExpectedTypes.h"
 #include "Logger.h"
+#include "Protobuf.h"
 #include "SourceCode.h"
 #include "SymbolLocation.h"
 #include "URI.h"
@@ -70,45 +71,6 @@
   return URI::create(AbsolutePath).toString();
 }
 
-// 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 = nameLocation(ND, SM);
-  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) || llvm::any_of(Name, islower);
-}
-
 // We only collect #include paths for symbols that are suitable for global code
 // completion, except for namespaces since #include path for a namespace is hard
 // to define.