[clang-doc] Improve clang-doc performance through memoization (#96809)

Author: PeterChou1

clang-tools-extra/clang-doc/Mapper.cpp

@@ -12,16 +12,28 @@
 #include "clang/AST/Comment.h"
 #include "clang/Index/USRGeneration.h"
 #include "llvm/ADT/StringExtras.h"
-#include "llvm/Support/Error.h"
+#include "llvm/ADT/StringSet.h"
+#include "llvm/Support/Mutex.h"
 
 namespace clang {
 namespace doc {
 
+static llvm::StringSet<> USRVisited;
+static llvm::sys::Mutex USRVisitedGuard;
+
+template <typename T> bool isTypedefAnonRecord(const T *D) {
+  if (const auto *C = dyn_cast<CXXRecordDecl>(D)) {
+    return C->getTypedefNameForAnonDecl();
+  }
+  return false;
+}
+
 void MapASTVisitor::HandleTranslationUnit(ASTContext &Context) {
   TraverseDecl(Context.getTranslationUnitDecl());
 }
 
-template <typename T> bool MapASTVisitor::mapDecl(const T *D) {
+template <typename T>
+bool MapASTVisitor::mapDecl(const T *D, bool IsDefinition) {
   // If we're looking a decl not in user files, skip this decl.
   if (D->getASTContext().getSourceManager().isInSystemHeader(D->getLocation()))
     return true;
@@ -34,6 +46,16 @@ template <typename T> bool MapASTVisitor::mapDecl(const T *D) {
   // If there is an error generating a USR for the decl, skip this decl.
   if (index::generateUSRForDecl(D, USR))
     return true;
+  // Prevent Visiting USR twice
+  {
+    std::lock_guard<llvm::sys::Mutex> Guard(USRVisitedGuard);
+    StringRef Visited = USR.str();
+    if (USRVisited.count(Visited) && !isTypedefAnonRecord<T>(D))
+      return true;
+    // We considered a USR to be visited only when its defined
+    if (IsDefinition)
+      USRVisited.insert(Visited);
+  }
   bool IsFileInRootDir;
   llvm::SmallString<128> File =
       getFile(D, D->getASTContext(), CDCtx.SourceRoot, IsFileInRootDir);
@@ -53,30 +75,34 @@ template <typename T> bool MapASTVisitor::mapDecl(const T *D) {
 }
 
 bool MapASTVisitor::VisitNamespaceDecl(const NamespaceDecl *D) {
-  return mapDecl(D);
+  return mapDecl(D, /*isDefinition=*/true);
 }
 
-bool MapASTVisitor::VisitRecordDecl(const RecordDecl *D) { return mapDecl(D); }
+bool MapASTVisitor::VisitRecordDecl(const RecordDecl *D) {
+  return mapDecl(D, D->isThisDeclarationADefinition());
+}
 
-bool MapASTVisitor::VisitEnumDecl(const EnumDecl *D) { return mapDecl(D); }
+bool MapASTVisitor::VisitEnumDecl(const EnumDecl *D) {
+  return mapDecl(D, D->isThisDeclarationADefinition());
+}
 
 bool MapASTVisitor::VisitCXXMethodDecl(const CXXMethodDecl *D) {
-  return mapDecl(D);
+  return mapDecl(D, D->isThisDeclarationADefinition());
 }
 
 bool MapASTVisitor::VisitFunctionDecl(const FunctionDecl *D) {
   // Don't visit CXXMethodDecls twice
   if (isa<CXXMethodDecl>(D))
     return true;
-  return mapDecl(D);
+  return mapDecl(D, D->isThisDeclarationADefinition());
 }
 
 bool MapASTVisitor::VisitTypedefDecl(const TypedefDecl *D) {
-  return mapDecl(D);
+  return mapDecl(D, /*isDefinition=*/true);
 }
 
 bool MapASTVisitor::VisitTypeAliasDecl(const TypeAliasDecl *D) {
-  return mapDecl(D);
+  return mapDecl(D, /*isDefinition=*/true);
 }
 
 comments::FullComment *

clang-tools-extra/clang-doc/Mapper.h

@@ -43,7 +43,7 @@ class MapASTVisitor : public clang::RecursiveASTVisitor<MapASTVisitor>,
   bool VisitTypeAliasDecl(const TypeAliasDecl *D);
 
 private:
-  template <typename T> bool mapDecl(const T *D);
+  template <typename T> bool mapDecl(const T *D, bool IsDefinition);
 
   int getLine(const NamedDecl *D, const ASTContext &Context) const;
   llvm::SmallString<128> getFile(const NamedDecl *D, const ASTContext &Context,

clang-tools-extra/clang-doc/tool/ClangDocMain.cpp

@@ -303,7 +303,6 @@ Example usage for a project using a compile commands database:
   for (auto &Group : USRToBitcode) {
     Pool.async([&]() {
       std::vector<std::unique_ptr<doc::Info>> Infos;
-
       for (auto &Bitcode : Group.getValue()) {
         llvm::BitstreamCursor Stream(Bitcode);
         doc::ClangDocBitcodeReader Reader(Stream);