[clang] [C++20][Modules] Implement P1857R3 Modules Dependency Discovery (PR #107168)

[via cfe-commits]

================
@@ -1178,186 +1289,39 @@ bool Preprocessor::LexAfterModuleImport(Token &Result) {
   // Figure out what kind of lexer we actually have.
   recomputeCurLexerKind();
 
-  // Lex the next token. The header-name lexing rules are used at the start of
-  // a pp-import.
-  //
-  // For now, we only support header-name imports in C++20 mode.
-  // FIXME: Should we allow this in all language modes that support an import
-  // declaration as an extension?
-  if (NamedModuleImportPath.empty() && getLangOpts().CPlusPlusModules) {
-    if (LexHeaderName(Result))
-      return true;
-
-    if (Result.is(tok::colon) && ModuleDeclState.isNamedModule()) {
-      std::string Name = ModuleDeclState.getPrimaryName().str();
-      Name += ":";
-      NamedModuleImportPath.emplace_back(Result.getLocation(),
-                                         getIdentifierInfo(Name));
-      CurLexerCallback = CLK_LexAfterModuleImport;
-      return true;
-    }
-  } else {
-    Lex(Result);
-  }
-
-  // Allocate a holding buffer for a sequence of tokens and introduce it into
-  // the token stream.
-  auto EnterTokens = [this](ArrayRef<Token> Toks) {
-    auto ToksCopy = std::make_unique<Token[]>(Toks.size());
-    std::copy(Toks.begin(), Toks.end(), ToksCopy.get());
-    EnterTokenStream(std::move(ToksCopy), Toks.size(),
-                     /*DisableMacroExpansion*/ true, /*IsReinject*/ false);
-  };
-
-  bool ImportingHeader = Result.is(tok::header_name);
-  // Check for a header-name.
   SmallVector<Token, 32> Suffix;
-  if (ImportingHeader) {
-    // Enter the header-name token into the token stream; a Lex action cannot
-    // both return a token and cache tokens (doing so would corrupt the token
-    // cache if the call to Lex comes from CachingLex / PeekAhead).
-    Suffix.push_back(Result);
-
-    // Consume the pp-import-suffix and expand any macros in it now. We'll add
-    // it back into the token stream later.
-    CollectPpImportSuffix(Suffix);
-    if (Suffix.back().isNot(tok::semi)) {
-      // This is not a pp-import after all.
-      EnterTokens(Suffix);
-      return false;
-    }
-
-    // C++2a [cpp.module]p1:
-    //   The ';' preprocessing-token terminating a pp-import shall not have
-    //   been produced by macro replacement.
-    SourceLocation SemiLoc = Suffix.back().getLocation();
-    if (SemiLoc.isMacroID())
-      Diag(SemiLoc, diag::err_header_import_semi_in_macro);
-
-    // Reconstitute the import token.
-    Token ImportTok;
-    ImportTok.startToken();
-    ImportTok.setKind(tok::kw_import);
-    ImportTok.setLocation(ModuleImportLoc);
-    ImportTok.setIdentifierInfo(getIdentifierInfo("import"));
-    ImportTok.setLength(6);
-
-    auto Action = HandleHeaderIncludeOrImport(
-        /*HashLoc*/ SourceLocation(), ImportTok, Suffix.front(), SemiLoc);
-    switch (Action.Kind) {
-    case ImportAction::None:
-      break;
-
-    case ImportAction::ModuleBegin:
-      // Let the parser know we're textually entering the module.
-      Suffix.emplace_back();
-      Suffix.back().startToken();
-      Suffix.back().setKind(tok::annot_module_begin);
-      Suffix.back().setLocation(SemiLoc);
-      Suffix.back().setAnnotationEndLoc(SemiLoc);
-      Suffix.back().setAnnotationValue(Action.ModuleForHeader);
-      [[fallthrough]];
-
-    case ImportAction::ModuleImport:
-    case ImportAction::HeaderUnitImport:
-    case ImportAction::SkippedModuleImport:
-      // We chose to import (or textually enter) the file. Convert the
-      // header-name token into a header unit annotation token.
-      Suffix[0].setKind(tok::annot_header_unit);
-      Suffix[0].setAnnotationEndLoc(Suffix[0].getLocation());
-      Suffix[0].setAnnotationValue(Action.ModuleForHeader);
-      // FIXME: Call the moduleImport callback?
-      break;
-    case ImportAction::Failure:
-      assert(TheModuleLoader.HadFatalFailure &&
-             "This should be an early exit only to a fatal error");
-      Result.setKind(tok::eof);
-      CurLexer->cutOffLexing();
-      EnterTokens(Suffix);
-      return true;
-    }
-
-    EnterTokens(Suffix);
-    return false;
-  }
-
-  // The token sequence
-  //
-  //   import identifier (. identifier)*
-  //
-  // indicates a module import directive. We already saw the 'import'
-  // contextual keyword, so now we're looking for the identifiers.
-  if (ModuleImportExpectsIdentifier && Result.getKind() == tok::identifier) {
-    // We expected to see an identifier here, and we did; continue handling
-    // identifiers.
-    NamedModuleImportPath.emplace_back(Result.getLocation(),
-                                       Result.getIdentifierInfo());
-    ModuleImportExpectsIdentifier = false;
-    CurLexerCallback = CLK_LexAfterModuleImport;
-    return true;
-  }
-
-  // If we're expecting a '.' or a ';', and we got a '.', then wait until we
-  // see the next identifier. (We can also see a '[[' that begins an
-  // attribute-specifier-seq here under the Standard C++ Modules.)
-  if (!ModuleImportExpectsIdentifier && Result.getKind() == tok::period) {
-    ModuleImportExpectsIdentifier = true;
-    CurLexerCallback = CLK_LexAfterModuleImport;
-    return true;
-  }
-
-  // If we didn't recognize a module name at all, this is not a (valid) import.
-  if (NamedModuleImportPath.empty() || Result.is(tok::eof))
-    return true;
+  SmallVector<IdentifierLoc, 2> Path;
----------------
yronglin wrote:

Fixed.

https://github.com/llvm/llvm-project/pull/107168