SemaModule.cpp

Go to the documentation of this file.

//===--- SemaModule.cpp - Semantic Analysis for Modules -------------------===//
//
// 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
//
//===----------------------------------------------------------------------===//
//
//  This file implements semantic analysis for modules (C++ modules syntax,
//  Objective-C modules syntax, and Clang header modules).
//
//===----------------------------------------------------------------------===//
 
#include "clang/AST/ASTConsumer.h"
#include "clang/AST/ASTMutationListener.h"
#include "clang/Lex/HeaderSearch.h"
#include "clang/Lex/Preprocessor.h"
#include "clang/Sema/SemaInternal.h"
#include "llvm/ADT/StringExtras.h"
 
using namespace clang;
using namespace sema;
 
static void checkModuleImportContext(Sema &S, Module *M,
                                     SourceLocation ImportLoc, DeclContext *DC,
                                     bool FromInclude = false) {
  SourceLocation ExternCLoc;
 
  if (auto *LSD = dyn_cast<LinkageSpecDecl>(DC)) {
    switch (LSD->getLanguage()) {
    case LinkageSpecLanguageIDs::C:
      if (ExternCLoc.isInvalid())
        ExternCLoc = LSD->getBeginLoc();
      break;
    case LinkageSpecLanguageIDs::CXX:
      break;
    }
    DC = LSD->getParent();
  }
 
  while (isa<LinkageSpecDecl>(DC) || isa<ExportDecl>(DC))
    DC = DC->getParent();
 
  if (!isa<TranslationUnitDecl>(DC)) {
    S.Diag(ImportLoc, (FromInclude && S.isModuleVisible(M))
                          ? diag::ext_module_import_not_at_top_level_noop
                          : diag::err_module_import_not_at_top_level_fatal)
        << M->getFullModuleName() << DC;
    S.Diag(cast<Decl>(DC)->getBeginLoc(),
           diag::note_module_import_not_at_top_level)
        << DC;
  } else if (!M->IsExternC && ExternCLoc.isValid()) {
    S.Diag(ImportLoc, diag::ext_module_import_in_extern_c)
      << M->getFullModuleName();
    S.Diag(ExternCLoc, diag::note_extern_c_begins_here);
  }
}
 
// We represent the primary and partition names as 'Paths' which are sections
// of the hierarchical access path for a clang module.  However for C++20
// the periods in a name are just another character, and we will need to
// flatten them into a string.
static std::string stringFromPath(ModuleIdPath Path) {
  std::string Name;
  if (Path.empty())
    return Name;
 
  for (auto &Piece : Path) {
    if (!Name.empty())
      Name += ".";
    Name += Piece.first->getName();
  }
  return Name;
}
 
/// Helper function for makeTransitiveImportsVisible to decide whether
/// the \param Imported module unit is in the same module with the \param
/// CurrentModule.
/// \param FoundPrimaryModuleInterface is a helper parameter to record the
/// primary module interface unit corresponding to the module \param
/// CurrentModule. Since currently it is expensive to decide whether two module
/// units come from the same module by comparing the module name.
static bool
isImportingModuleUnitFromSameModule(ASTContext &Ctx, Module *Imported,
                                    Module *CurrentModule,
                                    Module *&FoundPrimaryModuleInterface) {
  if (!Imported->isNamedModule())
    return false;
 
  // The a partition unit we're importing must be in the same module of the
  // current module.
  if (Imported->isModulePartition())
    return true;
 
  // If we found the primary module interface during the search process, we can
  // return quickly to avoid expensive string comparison.
  if (FoundPrimaryModuleInterface)
    return Imported == FoundPrimaryModuleInterface;
 
  if (!CurrentModule)
    return false;
 
  // Then the imported module must be a primary module interface unit.  It
  // is only allowed to import the primary module interface unit from the same
  // module in the implementation unit and the implementation partition unit.
 
  // Since we'll handle implementation unit above. We can only care
  // about the implementation partition unit here.
  if (!CurrentModule->isModulePartitionImplementation())
    return false;
 
  if (Ctx.isInSameModule(Imported, CurrentModule)) {
    assert(!FoundPrimaryModuleInterface ||
           FoundPrimaryModuleInterface == Imported);
    FoundPrimaryModuleInterface = Imported;
    return true;
  }
 
  return false;
}
 
/// [module.import]p7:
///   Additionally, when a module-import-declaration in a module unit of some
///   module M imports another module unit U of M, it also imports all
///   translation units imported by non-exported module-import-declarations in
///   the module unit purview of U. These rules can in turn lead to the
///   importation of yet more translation units.
static void
makeTransitiveImportsVisible(ASTContext &Ctx, VisibleModuleSet &VisibleModules,
                             Module *Imported, Module *CurrentModule,
                             SourceLocation ImportLoc,
                             bool IsImportingPrimaryModuleInterface = false) {
  assert(Imported->isNamedModule() &&
         "'makeTransitiveImportsVisible()' is intended for standard C++ named "
         "modules only.");
 
  llvm::SmallVector<Module *, 4> Worklist;
  Worklist.push_back(Imported);
 
  Module *FoundPrimaryModuleInterface =
      IsImportingPrimaryModuleInterface ? Imported : nullptr;
 
  while (!Worklist.empty()) {
    Module *Importing = Worklist.pop_back_val();
 
    if (VisibleModules.isVisible(Importing))
      continue;
 
    // FIXME: The ImportLoc here is not meaningful. It may be problematic if we
    // use the sourcelocation loaded from the visible modules.
    VisibleModules.setVisible(Importing, ImportLoc);
 
    if (isImportingModuleUnitFromSameModule(Ctx, Importing, CurrentModule,
                                            FoundPrimaryModuleInterface))
      for (Module *TransImported : Importing->Imports)
        if (!VisibleModules.isVisible(TransImported))
          Worklist.push_back(TransImported);
  }
}
 
Sema::DeclGroupPtrTy
Sema::ActOnGlobalModuleFragmentDecl(SourceLocation ModuleLoc) {
  // We start in the global module;
  Module *GlobalModule =
      PushGlobalModuleFragment(ModuleLoc);
 
  // All declarations created from now on are owned by the global module.
  auto *TU = Context.getTranslationUnitDecl();
  // [module.global.frag]p2
  // A global-module-fragment specifies the contents of the global module
  // fragment for a module unit. The global module fragment can be used to
  // provide declarations that are attached to the global module and usable
  // within the module unit.
  //
  // So the declations in the global module shouldn't be visible by default.
  TU->setModuleOwnershipKind(Decl::ModuleOwnershipKind::ReachableWhenImported);
  TU->setLocalOwningModule(GlobalModule);
 
  // FIXME: Consider creating an explicit representation of this declaration.
  return nullptr;
}
 
void Sema::HandleStartOfHeaderUnit() {
  assert(getLangOpts().CPlusPlusModules &&
         "Header units are only valid for C++20 modules");
  SourceLocation StartOfTU =
      SourceMgr.getLocForStartOfFile(SourceMgr.getMainFileID());
 
  StringRef HUName = getLangOpts().CurrentModule;
  if (HUName.empty()) {
    HUName =
        SourceMgr.getFileEntryRefForID(SourceMgr.getMainFileID())->getName();
    const_cast<LangOptions &>(getLangOpts()).CurrentModule = HUName.str();
  }
 
  // TODO: Make the C++20 header lookup independent.
  // When the input is pre-processed source, we need a file ref to the original
  // file for the header map.
  auto F = SourceMgr.getFileManager().getOptionalFileRef(HUName);
  // For the sake of error recovery (if someone has moved the original header
  // after creating the pre-processed output) fall back to obtaining the file
  // ref for the input file, which must be present.
  if (!F)
    F = SourceMgr.getFileEntryRefForID(SourceMgr.getMainFileID());
  assert(F && "failed to find the header unit source?");
  Module::Header H{HUName.str(), HUName.str(), *F};
  auto &Map = PP.getHeaderSearchInfo().getModuleMap();
  Module *Mod = Map.createHeaderUnit(StartOfTU, HUName, H);
  assert(Mod && "module creation should not fail");
  ModuleScopes.push_back({}); // No GMF
  ModuleScopes.back().BeginLoc = StartOfTU;
  ModuleScopes.back().Module = Mod;
  VisibleModules.setVisible(Mod, StartOfTU);
 
  // From now on, we have an owning module for all declarations we see.
  // All of these are implicitly exported.
  auto *TU = Context.getTranslationUnitDecl();
  TU->setModuleOwnershipKind(Decl::ModuleOwnershipKind::Visible);
  TU->setLocalOwningModule(Mod);
}
 
/// Tests whether the given identifier is reserved as a module name and
/// diagnoses if it is. Returns true if a diagnostic is emitted and false
/// otherwise.
static bool DiagReservedModuleName(Sema &S, const IdentifierInfo *II,
                                   SourceLocation Loc) {
  enum {
    Valid = -1,
    Invalid = 0,
    Reserved = 1,
  } Reason = Valid;
 
  if (II->isStr("module") || II->isStr("import"))
    Reason = Invalid;
  else if (II->isReserved(S.getLangOpts()) !=
           ReservedIdentifierStatus::NotReserved)
    Reason = Reserved;
 
  // If the identifier is reserved (not invalid) but is in a system header,
  // we do not diagnose (because we expect system headers to use reserved
  // identifiers).
  if (Reason == Reserved && S.getSourceManager().isInSystemHeader(Loc))
    Reason = Valid;
 
  switch (Reason) {
  case Valid:
    return false;
  case Invalid:
    return S.Diag(Loc, diag::err_invalid_module_name) << II;
  case Reserved:
    S.Diag(Loc, diag::warn_reserved_module_name) << II;
    return false;
  }
  llvm_unreachable("fell off a fully covered switch");
}
 
Sema::DeclGroupPtrTy
Sema::ActOnModuleDecl(SourceLocation StartLoc, SourceLocation ModuleLoc,
                      ModuleDeclKind MDK, ModuleIdPath Path,
                      ModuleIdPath Partition, ModuleImportState &ImportState) {
  assert(getLangOpts().CPlusPlusModules &&
         "should only have module decl in standard C++ modules");
 
  bool IsFirstDecl = ImportState == ModuleImportState::FirstDecl;
  bool SeenGMF = ImportState == ModuleImportState::GlobalFragment;
  // If any of the steps here fail, we count that as invalidating C++20
  // module state;
  ImportState = ModuleImportState::NotACXX20Module;
 
  bool IsPartition = !Partition.empty();
  if (IsPartition)
    switch (MDK) {
    case ModuleDeclKind::Implementation:
      MDK = ModuleDeclKind::PartitionImplementation;
      break;
    case ModuleDeclKind::Interface:
      MDK = ModuleDeclKind::PartitionInterface;
      break;
    default:
      llvm_unreachable("how did we get a partition type set?");
    }
 
  // A (non-partition) module implementation unit requires that we are not
  // compiling a module of any kind.  A partition implementation emits an
  // interface (and the AST for the implementation), which will subsequently
  // be consumed to emit a binary.
  // A module interface unit requires that we are not compiling a module map.
  switch (getLangOpts().getCompilingModule()) {
  case LangOptions::CMK_None:
    // It's OK to compile a module interface as a normal translation unit.
    break;
 
  case LangOptions::CMK_ModuleInterface:
    if (MDK != ModuleDeclKind::Implementation)
      break;
 
    // We were asked to compile a module interface unit but this is a module
    // implementation unit.
    Diag(ModuleLoc, diag::err_module_interface_implementation_mismatch)
      << FixItHint::CreateInsertion(ModuleLoc, "export ");
    MDK = ModuleDeclKind::Interface;
    break;
 
  case LangOptions::CMK_ModuleMap:
    Diag(ModuleLoc, diag::err_module_decl_in_module_map_module);
    return nullptr;
 
  case LangOptions::CMK_HeaderUnit:
    Diag(ModuleLoc, diag::err_module_decl_in_header_unit);
    return nullptr;
  }
 
  assert(ModuleScopes.size() <= 1 && "expected to be at global module scope");
 
  // FIXME: Most of this work should be done by the preprocessor rather than
  // here, in order to support macro import.
 
  // Only one module-declaration is permitted per source file.
  if (isCurrentModulePurview()) {
    Diag(ModuleLoc, diag::err_module_redeclaration);
    Diag(VisibleModules.getImportLoc(ModuleScopes.back().Module),
         diag::note_prev_module_declaration);
    return nullptr;
  }
 
  assert((!getLangOpts().CPlusPlusModules ||
          SeenGMF == (bool)this->TheGlobalModuleFragment) &&
         "mismatched global module state");
 
  // In C++20, the module-declaration must be the first declaration if there
  // is no global module fragment.
  if (getLangOpts().CPlusPlusModules && !IsFirstDecl && !SeenGMF) {
    Diag(ModuleLoc, diag::err_module_decl_not_at_start);
    SourceLocation BeginLoc =
        ModuleScopes.empty()
            ? SourceMgr.getLocForStartOfFile(SourceMgr.getMainFileID())
            : ModuleScopes.back().BeginLoc;
    if (BeginLoc.isValid()) {
      Diag(BeginLoc, diag::note_global_module_introducer_missing)
          << FixItHint::CreateInsertion(BeginLoc, "module;\n");
    }
  }
 
  // C++23 [module.unit]p1: ... The identifiers module and import shall not
  // appear as identifiers in a module-name or module-partition. All
  // module-names either beginning with an identifier consisting of std
  // followed by zero or more digits or containing a reserved identifier
  // ([lex.name]) are reserved and shall not be specified in a
  // module-declaration; no diagnostic is required.
 
  // Test the first part of the path to see if it's std[0-9]+ but allow the
  // name in a system header.
  StringRef FirstComponentName = Path[0].first->getName();
  if (!getSourceManager().isInSystemHeader(Path[0].second) &&
      (FirstComponentName == "std" ||
       (FirstComponentName.starts_with("std") &&
        llvm::all_of(FirstComponentName.drop_front(3), &llvm::isDigit))))
    Diag(Path[0].second, diag::warn_reserved_module_name) << Path[0].first;
 
  // Then test all of the components in the path to see if any of them are
  // using another kind of reserved or invalid identifier.
  for (auto Part : Path) {
    if (DiagReservedModuleName(*this, Part.first, Part.second))
      return nullptr;
  }
 
  // Flatten the dots in a module name. Unlike Clang's hierarchical module map
  // modules, the dots here are just another character that can appear in a
  // module name.
  std::string ModuleName = stringFromPath(Path);
  if (IsPartition) {
    ModuleName += ":";
    ModuleName += stringFromPath(Partition);
  }
  // If a module name was explicitly specified on the command line, it must be
  // correct.
  if (!