[clang][modules] NFCI: Extract optionality out of `Module::{Header,DirectoryName}`

[jansvoboda11]

Summary

Most users of Module::Header already assume its Entry is populated. Enforce this assumption in the type system and handle the only case where this is not the case by wrapping the whole struct in std::optional. Do the same for Module::DirectoryName.

Depends on D151584.

[benlangmuir]

clang/lib/Basic/Module.cpp

486

These are on the edge, but I think I would lean towards spelling the typename here since it's not obvious from the name of the API what exactly it would be

[jansvoboda11]

Change auto to std::optional<...> in all places

clang-tools-extra/modularize/CoverageChecker.cpp

 }
 
 // Collect referenced headers from one module.
 // Collects the headers referenced in the given module into
 // ModuleMapHeadersSet.
 // FIXME: Doesn't collect files from umbrella header.
 bool CoverageChecker::collectModuleHeaders(const Module &Mod) {
 
-  if (const FileEntry *UmbrellaHeader =
-          Mod.getUmbrellaHeaderAsWritten().Entry) {
+  if (std::optional<Module::Header> UmbrellaHeader =
+          Mod.getUmbrellaHeaderAsWritten()) {
     // Collect umbrella header.
-    ModuleMapHeadersSet.insert(ModularizeUtilities::getCanonicalPath(
-      UmbrellaHeader->getName()));
+    ModuleMapHeadersSet.insert(
+        ModularizeUtilities::getCanonicalPath(UmbrellaHeader->Entry.getName()));
     // Preprocess umbrella header and collect the headers it references.
-    if (!collectUmbrellaHeaderHeaders(UmbrellaHeader->getName()))
+    if (!collectUmbrellaHeaderHeaders(UmbrellaHeader->Entry.getName()))
       return false;
-  } else if (const DirectoryEntry *UmbrellaDir =
-                 Mod.getUmbrellaDirAsWritten().Entry) {
+  } else if (std::optional<Module::DirectoryName> UmbrellaDir =
+                 Mod.getUmbrellaDirAsWritten()) {
     // Collect headers in umbrella directory.
-    if (!collectUmbrellaHeaders(UmbrellaDir->getName()))
+    if (!collectUmbrellaHeaders(UmbrellaDir->Entry.getName()))
       return false;
   }
 
   for (auto &HeaderKind : Mod.Headers)
     for (auto &Header : HeaderKind)
-      ModuleMapHeadersSet.insert(ModularizeUtilities::getCanonicalPath(
-        Header.Entry->getName()));
+      ModuleMapHeadersSet.insert(
+          ModularizeUtilities::getCanonicalPath(Header.Entry.getName()));
 
   for (auto *Submodule : Mod.submodules())
     collectModuleHeaders(*Submodule);
 
   return true;
 }
 
 // Collect headers from an umbrella directory.

clang-tools-extra/modularize/ModularizeUtilities.cpp

bool ModularizeUtilities::collectModuleHeaders(const clang::Module &Mod) {
 
   // Treat headers in umbrella directory as dependencies.
   DependentsVector UmbrellaDependents;
 
   // Recursively do submodules.
   for (auto *Submodule : Mod.submodules())
     collectModuleHeaders(*Submodule);
 
-  if (const FileEntry *UmbrellaHeader =
-          Mod.getUmbrellaHeaderAsWritten().Entry) {
-    std::string HeaderPath = getCanonicalPath(UmbrellaHeader->getName());
+  if (std::optional<Module::Header> UmbrellaHeader =
+          Mod.getUmbrellaHeaderAsWritten()) {
+    std::string HeaderPath = getCanonicalPath(UmbrellaHeader->Entry.getName());
     // Collect umbrella header.
     HeaderFileNames.push_back(HeaderPath);
 
     // FUTURE: When needed, umbrella header header collection goes here.
-  } else if (const DirectoryEntry *UmbrellaDir =
-                 Mod.getUmbrellaDirAsWritten().Entry) {
+  } else if (std::optional<Module::DirectoryName> UmbrellaDir =
+                 Mod.getUmbrellaDirAsWritten()) {
     // If there normal headers, assume these are umbrellas and skip collection.
     if (Mod.Headers->size() == 0) {
       // Collect headers in umbrella directory.
-      if (!collectUmbrellaHeaders(UmbrellaDir->getName(), UmbrellaDependents))
+      if (!collectUmbrellaHeaders(UmbrellaDir->Entry.getName(),
+                                  UmbrellaDependents))
         return false;
     }
   }
 
   // We ignore HK_Private, HK_Textual, HK_PrivateTextual, and HK_Excluded,
   // assuming they are marked as such either because of unsuitability for
   // modules or because they are meant to be included by another header,
   // and thus should be ignored by modularize.
 
   int NormalHeaderCount = Mod.Headers[clang::Module::HK_Normal].size();
 
   for (int Index = 0; Index < NormalHeaderCount; ++Index) {
     DependentsVector NormalDependents;
     // Collect normal header.
     const clang::Module::Header &Header(
       Mod.Headers[clang::Module::HK_Normal][Index]);
-    std::string HeaderPath = getCanonicalPath(Header.Entry->getName());
+    std::string HeaderPath = getCanonicalPath(Header.Entry.getName());
     HeaderFileNames.push_back(HeaderPath);
   }
 
   int MissingCountThisModule = Mod.MissingHeaders.size();
 
   for (int Index = 0; Index < MissingCountThisModule; ++Index) {
     std::string MissingFile = Mod.MissingHeaders[Index].FileName;
     SourceLocation Loc = Mod.MissingHeaders[Index].FileNameLoc;

clang/include/clang/Basic/Module.h

public:
   };
   static const int NumHeaderKinds = HK_Excluded + 1;
 
   /// Information about a header directive as found in the module map
   /// file.
   struct Header {
     std::string NameAsWritten;
     std::string PathRelativeToRootModuleDirectory;
-    OptionalFileEntryRefDegradesToFileEntryPtr Entry;
-
-    explicit operator bool() { return Entry.has_value(); }
+    FileEntryRef Entry;
   };
 
   /// Information about a directory name as found in the module map
   /// file.
   struct DirectoryName {
     std::string NameAsWritten;
     std::string PathRelativeToRootModuleDirectory;
-    OptionalDirectoryEntryRefDegradesToDirectoryEntryPtr Entry;
-
-    explicit operator bool() { return Entry.has_value(); }
+    DirectoryEntryRef Entry;
   };
 
   /// The headers that are part of this module.
   SmallVector<Header, 2> Headers[5];
 
   /// Stored information about a header directive that was found in the
   /// module map file but has not been resolved to a file.
   struct UnresolvedHeaderDirective {
public:
 
   /// Set the serialized AST file for the top-level module of this module.
   void setASTFile(OptionalFileEntryRef File) {
     assert((!getASTFile() || getASTFile() == File) && "file path changed");
     getTopLevelModule()->ASTFile = File;
   }
 
   /// Retrieve the umbrella directory as written.
-  DirectoryName getUmbrellaDirAsWritten() const {
+  std::optional<DirectoryName> getUmbrellaDirAsWritten() const {
     if (const auto *ME =
             Umbrella.dyn_cast<const DirectoryEntryRef::MapEntry *>())
       return DirectoryName{UmbrellaAsWritten,
                            UmbrellaRelativeToRootModuleDirectory,
                            DirectoryEntryRef(*ME)};
-    return DirectoryName{};
+    return std::nullopt;
   }
 
   /// Retrieve the umbrella header as written.
-  Header getUmbrellaHeaderAsWritten() const {
+  std::optional<Header> getUmbrellaHeaderAsWritten() const {
     if (const auto *ME = Umbrella.dyn_cast<const FileEntryRef::MapEntry *>())
       return Header{UmbrellaAsWritten, UmbrellaRelativeToRootModuleDirectory,
                     FileEntryRef(*ME)};
-    return Header{};
+    return std::nullopt;
   }
 
   /// Get the effective umbrella directory for this module: either the one
   /// explicitly written in the module map file, or the parent of the umbrella
   /// header.
   OptionalDirectoryEntryRef getEffectiveUmbrellaDir() const;
 
   /// Add a top-level header associated with this module.

clang/lib/Basic/Module.cpp

for (unsigned I = 0, N = Requirements.size(); I != N; ++I) {
         OS << ", ";
       if (!Requirements[I].second)
         OS << "!";
       OS << Requirements[I].first;
     }
     OS << "\n";
   }
 
-  if (Header H = getUmbrellaHeaderAsWritten()) {
+  if (std::optional<Header> H = getUmbrellaHeaderAsWritten()) {
     OS.indent(Indent + 2);
     OS << "umbrella header \"";
-    OS.write_escaped(H.NameAsWritten);
+    OS.write_escaped(H->NameAsWritten);
     OS << "\"\n";
-  } else if (DirectoryName D = getUmbrellaDirAsWritten()) {
+  } else if (std::optional<DirectoryName> D = getUmbrellaDirAsWritten()) {
     OS.indent(Indent + 2);
     OS << "umbrella \"";
-    OS.write_escaped(D.NameAsWritten);
+    OS.write_escaped(D->NameAsWritten);
     OS << "\"\n";
   }
 
   if (!ConfigMacros.empty() || ConfigMacrosExhaustive) {
     OS.indent(Indent + 2);
     OS << "config_macros ";
     if (ConfigMacrosExhaustive)
       OS << "[exhaustive]";
HeaderKind Kind;
                {"exclude ", HK_Excluded}};
 
   for (auto &K : Kinds) {
     assert(&K == &Kinds[K.Kind] && "kinds in wrong order");
     for (auto &H : Headers[K.Kind]) {
       OS.indent(Indent + 2);
       OS << K.Prefix << "header \"";
       OS.write_escaped(H.NameAsWritten);
-      OS << "\" { size " << H.Entry->getSize()
-         << " mtime " << H.Entry->getModificationTime() << " }\n";
+      OS << "\" { size " << H.Entry.getSize()
+         << " mtime " << H.Entry.getModificationTime() << " }\n";
     }
   }
   for (auto *Unresolved : {&UnresolvedHeaders, &MissingHeaders}) {
     for (auto &U : *Unresolved) {
       OS.indent(Indent + 2);
       OS << Kinds[U.Kind].Prefix << "header \"";
       OS.write_escaped(U.FileName);
       OS << "\"";

clang/lib/Frontend/FrontendAction.cpp

for (Module::Header &H : Module->Headers[HK]) {
       // the module map file) so this will find the same file that we found
       // while parsing the module map.
       addHeaderInclude(H.PathRelativeToRootModuleDirectory, Includes, LangOpts,
                        Module->IsExternC);
     }
   }
   // Note that Module->PrivateHeaders will not be a TopHeader.
 
-  if (Module::Header UmbrellaHeader = Module->getUmbrellaHeaderAsWritten()) {
-    Module->addTopHeader(UmbrellaHeader.Entry);
+  if (std::optional<Module::Header> UmbrellaHeader =
+          Module->getUmbrellaHeaderAsWritten()) {
+    Module->addTopHeader(UmbrellaHeader->Entry);
     if (Module->Parent)
       // Include the umbrella header for submodules.
-      addHeaderInclude(UmbrellaHeader.PathRelativeToRootModuleDirectory,
+      addHeaderInclude(UmbrellaHeader->PathRelativeToRootModuleDirectory,
                        Includes, LangOpts, Module->IsExternC);
-  } else if (Module::DirectoryName UmbrellaDir =
+  } else if (std::optional<Module::DirectoryName> UmbrellaDir =
                  Module->getUmbrellaDirAsWritten()) {
     // Add all of the headers we find in this subdirectory.
     std::error_code EC;
     SmallString<128> DirNative;
-    llvm::sys::path::native(UmbrellaDir.Entry->getName(), DirNative);
+    llvm::sys::path::native(UmbrellaDir->Entry.getName(), DirNative);
 
     llvm::vfs::FileSystem &FS = FileMgr.getVirtualFileSystem();
     SmallVector<
         std::pair<std::string, OptionalFileEntryRefDegradesToFileEntryPtr>, 8>
         Headers;
     for (llvm::vfs::recursive_directory_iterator Dir(FS, DirNative, EC), End;
          Dir != End && !EC; Dir.increment(EC)) {
       // Check whether this entry has an extension typically associated with
for (llvm::vfs::recursive_directory_iterator Dir(FS, DirNative, EC), End;
         continue;
 
       // Compute the relative path from the directory to this file.
       SmallVector<StringRef, 16> Components;
       auto PathIt = llvm::sys::path::rbegin(Dir->path());
       for (int I = 0; I != Dir.level() + 1; ++I, ++PathIt)
         Components.push_back(*PathIt);
       SmallString<128> RelativeHeader(
-          UmbrellaDir.PathRelativeToRootModuleDirectory);
+          UmbrellaDir->PathRelativeToRootModuleDirectory);
       for (auto It = Components.rbegin(), End = Components.rend(); It != End;
            ++It)
         llvm::sys::path::append(RelativeHeader, *It);
 
       std::string RelName = RelativeHeader.c_str();
       Headers.push_back(std::make_pair(RelName, *Header));
     }
 

 /// Compute the input buffer that should be used to build the specified module.
 static std::unique_ptr<llvm::MemoryBuffer>
 getInputBufferForModule(CompilerInstance &CI, Module *M) {
   FileManager &FileMgr = CI.getFileManager();
 
   // Collect the set of #includes we need to build the module.
   SmallString<256> HeaderContents;
   std::error_code Err = std::error_code();
-  if (Module::Header UmbrellaHeader = M->getUmbrellaHeaderAsWritten())
-    addHeaderInclude(UmbrellaHeader.PathRelativeToRootModuleDirectory,
+  if (std::optional<Module::Header> UmbrellaHeader =
+          M->getUmbrellaHeaderAsWritten())
+    addHeaderInclude(UmbrellaHeader->PathRelativeToRootModuleDirectory,
                      HeaderContents, CI.getLangOpts(), M->IsExternC);
   Err = collectModuleHeaderIncludes(
       CI.getLangOpts(), FileMgr, CI.getDiagnostics(),
       CI.getPreprocessor().getHeaderSearchInfo().getModuleMap(), M,
       HeaderContents);
 
   if (Err) {
     CI.getDiagnostics().Report(diag::err_module_cannot_create_includes)

clang/lib/Lex/ModuleMap.cpp

if (!Imported || isCompilingModuleHeader) {
     // When we import HeaderFileInfo, the external source is expected to
     // set the isModuleHeader flag itself.
     HeaderInfo.MarkFileModuleHeader(Header.Entry, Role,
                                     isCompilingModuleHeader);
   }
 
   // Notify callbacks that we just added a new header.
   for (const auto &Cb : Callbacks)
-    Cb->moduleMapAddHeader(Header.Entry->getName());
+    Cb->moduleMapAddHeader(Header.Entry.getName());
 }
 
 OptionalFileEntryRef
 ModuleMap::getContainingModuleMapFile(const Module *Module) const {
   if (Module->DefinitionLoc.isInvalid())
     return std::nullopt;
 
   return SourceMgr.getFileEntryRefForID(
if (UsesRequiresExcludedHack.count(ActiveModule)) {
     // uncommonly used Tcl module on Darwin platforms.
     std::error_code EC;
     SmallVector<Module::Header, 6> Headers;
     llvm::vfs::FileSystem &FS =
         SourceMgr.getFileManager().getVirtualFileSystem();
     for (llvm::vfs::recursive_directory_iterator I(FS, Dir->getName(), EC), E;
          I != E && !EC; I.increment(EC)) {
       if (auto FE = SourceMgr.getFileManager().getOptionalFileRef(I->path())) {
-        Module::Header Header = {"", std::string(I->path()), FE};
+        Module::Header Header = {"", std::string(I->path()), *FE};
         Headers.push_back(std::move(Header));
       }
     }
 
     // Sort header paths so that the pcm doesn't depend on iteration order.
     llvm::array_pod_sort(Headers.begin(), Headers.end(), compareModuleHeaders);
 
     for (auto &Header : Headers)

clang/lib/Lex/PPLexerChange.cpp

static void collectAllSubModulesWithUmbrellaHeader(
     const Module &Mod, SmallVectorImpl<const Module *> &SubMods) {
   if (Mod.getUmbrellaHeaderAsWritten())
     SubMods.push_back(&Mod);
   for (auto *M : Mod.submodules())
     collectAllSubModulesWithUmbrellaHeader(*M, SubMods);
 }
 
 void Preprocessor::diagnoseMissingHeaderInUmbrellaDir(const Module &Mod) {
-  Module::Header UmbrellaHeader = Mod.getUmbrellaHeaderAsWritten();
-  assert(UmbrellaHeader.Entry && "Module must use umbrella header");
-  const FileID &File = SourceMgr.translateFile(UmbrellaHeader.Entry);
+  std::optional<Module::Header> UmbrellaHeader =
+      Mod.getUmbrellaHeaderAsWritten();
+  assert(UmbrellaHeader && "Module must use umbrella header");
+  const FileID &File = SourceMgr.translateFile(UmbrellaHeader->Entry);
   SourceLocation ExpectedHeadersLoc = SourceMgr.getLocForEndOfFile(File);
   if (getDiagnostics().isIgnored(diag::warn_uncovered_module_header,
                                  ExpectedHeadersLoc))
     return;
 
   ModuleMap &ModMap = getHeaderSearchInfo().getModuleMap();
   OptionalDirectoryEntryRef Dir = Mod.getEffectiveUmbrellaDir();
   llvm::vfs::FileSystem &FS = FileMgr.getVirtualFileSystem();

clang/lib/Serialization/ASTReader.cpp

while (d != End) {
     Module *Mod = Reader.getSubmodule(GlobalSMID);
     FileManager &FileMgr = Reader.getFileManager();
     ModuleMap &ModMap =
         Reader.getPreprocessor().getHeaderSearchInfo().getModuleMap();
 
     std::string Filename = std::string(key.Filename);
     if (key.Imported)
       Reader.ResolveImportedPath(M, Filename);
+    if (auto FE = FileMgr.getOptionalFileRef(Filename)) {
       // FIXME: NameAsWritten
-    Module::Header H = {std::string(key.Filename), "",
-                        FileMgr.getOptionalFileRef(Filename)};
-    ModMap.addHeader(Mod, H, HeaderRole, /*Imported*/true);
+      Module::Header H = {std::string(key.Filename), "", *FE};
+      ModMap.addHeader(Mod, H, HeaderRole, /*Imported=*/true);
+    }
     HFI.isModuleHeader |= ModuleMap::isModular(HeaderRole);
   }
 
   // This HeaderFileInfo was externally loaded.
   HFI.External = true;
   HFI.IsValid = true;
   return HFI;
 }

clang/lib/Serialization/ASTWriter.cpp

while (!Q.empty()) {
 
     // Emit the requirements.
     for (const auto &R : Mod->Requirements) {
       RecordData::value_type Record[] = {SUBMODULE_REQUIRES, R.second};
       Stream.EmitRecordWithBlob(RequiresAbbrev, Record, R.first);
     }
 
     // Emit the umbrella header, if there is one.
-    if (Module::Header UmbrellaHeader = Mod->getUmbrellaHeaderAsWritten()) {
+    if (std::optional<Module::Header> UmbrellaHeader =
+            Mod->getUmbrellaHeaderAsWritten()) {
       RecordData::value_type Record[] = {SUBMODULE_UMBRELLA_HEADER};
       Stream.EmitRecordWithBlob(UmbrellaAbbrev, Record,
-                                UmbrellaHeader.NameAsWritten);
-    } else if (Module::DirectoryName UmbrellaDir =
+                                UmbrellaHeader->NameAsWritten);
+    } else if (std::optional<Module::DirectoryName> UmbrellaDir =
                    Mod->getUmbrellaDirAsWritten()) {
       RecordData::value_type Record[] = {SUBMODULE_UMBRELLA_DIR};
       Stream.EmitRecordWithBlob(UmbrellaDirAbbrev, Record,
-                                UmbrellaDir.NameAsWritten);
+                                UmbrellaDir->NameAsWritten);
     }
 
     // Emit the headers.
     struct {
       unsigned RecordKind;
       unsigned Abbrev;
       Module::HeaderKind HeaderKind;
     } HeaderLists[] = {