[C++20][Modules] Implement P1857R3 Modules Dependency Discovery

clang/examples/AnnotateFunctions/AnnotateFunctions.cpp

@@ -65,7 +65,7 @@ class PragmaAnnotateHandler : public PragmaHandler {
     Token Tok;
     PP.LexUnexpandedToken(Tok);
     if (Tok.isNot(tok::eod))
-      PP.Diag(Tok, diag::ext_pp_extra_tokens_at_eol) << "pragma";
+      PP.Diag(Tok, diag::ext_pp_extra_tokens_at_eol) << "#pragma";
 
     if (HandledDecl) {
       DiagnosticsEngine &D = PP.getDiagnostics();

clang/include/clang/Basic/DiagnosticLexKinds.td

@@ -466,6 +466,9 @@ def err_pp_embed_device_file : Error<
 
 def ext_pp_extra_tokens_at_eol : ExtWarn<
   "extra tokens at end of #%0 directive">, InGroup<ExtraTokens>;
+def ext_pp_extra_tokens_at_module_directive_eol
+    : ExtWarn<"extra tokens at end of '%0' directive">,
+      InGroup<ExtraTokens>;
 
 def ext_pp_comma_expr : Extension<"comma operator in operand of #if">;
 def ext_pp_bad_vaargs_use : Extension<
@@ -495,8 +498,8 @@ def warn_cxx98_compat_variadic_macro : Warning<
   InGroup<CXX98CompatPedantic>, DefaultIgnore;
 def ext_named_variadic_macro : Extension<
   "named variadic macros are a GNU extension">, InGroup<VariadicMacros>;
-def err_embedded_directive : Error<
-  "embedding a #%0 directive within macro arguments is not supported">;
+def err_embedded_directive : Error<"embedding a %select{#|C++ }0%1 directive "
+                                   "within macro arguments is not supported">;
 def ext_embedded_directive : Extension<
   "embedding a directive within macro arguments has undefined behavior">,
   InGroup<DiagGroup<"embedded-directive">>;
@@ -983,6 +986,19 @@ def warn_module_conflict : Warning<
   InGroup<ModuleConflict>;
 
 // C++20 modules
+def err_pp_expected_module_name_or_header_name
+    : Error<"expected module name or header name">;
+def err_pp_expected_semi_after_module_or_import
+    : Error<"'%select{module|import}0' directive must end with a ';' on the "
+            "same line">;
+def err_module_decl_in_header
+    : Error<"module declaration must not come from an #include directive">;
+def err_pp_cond_span_module_decl
+    : Error<"preprocessor conditionals shall not span a module declaration">;
+def err_pp_module_expected_ident
+    : Error<"expected a module name after '%select{module|import}0'">;
+def err_pp_unsupported_module_partition
+    : Error<"module partitions are only supported for C++20 onwards">;
 def err_header_import_semi_in_macro : Error<
   "semicolon terminating header import declaration cannot be produced "
   "by a macro">;

clang/include/clang/Basic/DiagnosticParseKinds.td

@@ -1762,38 +1762,36 @@ def ext_bit_int : Extension<
 } // end of Parse Issue category.
 
 let CategoryName = "Modules Issue" in {
-def err_unexpected_module_decl : Error<
-  "module declaration can only appear at the top level">;
-def err_module_expected_ident : Error<
-  "expected a module name after '%select{module|import}0'">;
-def err_attribute_not_module_attr : Error<
-  "%0 attribute cannot be applied to a module">;
-def err_keyword_not_module_attr : Error<
-  "%0 cannot be applied to a module">;
-def err_attribute_not_import_attr : Error<
-  "%0 attribute cannot be applied to a module import">;
-def err_keyword_not_import_attr : Error<
-  "%0 cannot be applied to a module import">;
-def err_module_expected_semi : Error<
-  "expected ';' after module name">;
-def err_global_module_introducer_not_at_start : Error<
-  "'module;' introducing a global module fragment can appear only "
-  "at the start of the translation unit">;
-def err_module_fragment_exported : Error<
-  "%select{global|private}0 module fragment cannot be exported">;
-def err_private_module_fragment_expected_semi : Error<
-  "expected ';' after private module fragment declaration">;
-def err_missing_before_module_end : Error<"expected %0 at end of module">;
-def err_unsupported_module_partition : Error<
-  "module partitions are only supported for C++20 onwards">;
-def err_import_not_allowed_here : Error<
-  "imports must immediately follow the module declaration">;
-def err_partition_import_outside_module : Error<
-  "module partition imports must be within a module purview">;
-def err_import_in_wrong_fragment : Error<
-  "module%select{| partition}0 imports cannot be in the %select{global|private}1 module fragment">;
-
-def err_export_empty : Error<"export declaration cannot be empty">;
+  def err_unexpected_module_import_decl
+      : Error<"%select{module|import}0 declaration can only appear at the top "
+              "level">;
+  def err_module_expected_ident
+      : Error<"expected a module name after '%select{module|import}0'">;
+  def err_attribute_not_module_attr
+      : Error<"%0 attribute cannot be applied to a module">;
+  def err_keyword_not_module_attr : Error<"%0 cannot be applied to a module">;
+  def err_attribute_not_import_attr
+      : Error<"%0 attribute cannot be applied to a module import">;
+  def err_keyword_not_import_attr
+      : Error<"%0 cannot be applied to a module import">;
+  def err_module_expected_semi : Error<"expected ';' after module name">;
+  def err_global_module_introducer_not_at_start
+      : Error<"'module;' introducing a global module fragment can appear only "
+              "at the start of the translation unit">;
+  def err_module_fragment_exported
+      : Error<"%select{global|private}0 module fragment cannot be exported">;
+  def err_private_module_fragment_expected_semi
+      : Error<"expected ';' after private module fragment declaration">;
+  def err_missing_before_module_end : Error<"expected %0 at end of module">;
+  def err_import_not_allowed_here
+      : Error<"imports must immediately follow the module declaration">;
+  def err_partition_import_outside_module
+      : Error<"module partition imports must be within a module purview">;
+  def err_import_in_wrong_fragment
+      : Error<"module%select{| partition}0 imports cannot be in the "
+              "%select{global|private}1 module fragment">;
+
+  def err_export_empty : Error<"export declaration cannot be empty">;
 }
 
 let CategoryName = "Generics Issue" in {

clang/include/clang/Basic/IdentifierTable.h

@@ -179,6 +179,10 @@ class alignas(IdentifierInfoAlignment) IdentifierInfo {
   LLVM_PREFERRED_TYPE(bool)
   unsigned IsModulesImport : 1;
 
+  // True if this is the 'module' contextual keyword.
+  LLVM_PREFERRED_TYPE(bool)
+  unsigned IsModulesDecl : 1;
+
   // True if this is a mangled OpenMP variant name.
   LLVM_PREFERRED_TYPE(bool)
   unsigned IsMangledOpenMPVariantName : 1;
@@ -215,8 +219,9 @@ class alignas(IdentifierInfoAlignment) IdentifierInfo {
         IsCPPOperatorKeyword(false), NeedsHandleIdentifier(false),
         IsFromAST(false), ChangedAfterLoad(false), FEChangedAfterLoad(false),
         RevertedTokenID(false), OutOfDate(false), IsModulesImport(false),
-        IsMangledOpenMPVariantName(false), IsDeprecatedMacro(false),
-        IsRestrictExpansion(false), IsFinal(false), IsKeywordInCpp(false) {}
+        IsModulesDecl(false), IsMangledOpenMPVariantName(false),
+        IsDeprecatedMacro(false), IsRestrictExpansion(false), IsFinal(false),
+        IsKeywordInCpp(false) {}
 
 public:
   IdentifierInfo(const IdentifierInfo &) = delete;
@@ -528,6 +533,18 @@ class alignas(IdentifierInfoAlignment) IdentifierInfo {
       RecomputeNeedsHandleIdentifier();
   }
 
+  /// Determine whether this is the contextual keyword \c module.
+  bool isModulesDeclaration() const { return IsModulesDecl; }
+
+  /// Set whether this identifier is the contextual keyword \c module.
+  void setModulesDeclaration(bool I) {
+    IsModulesDecl = I;
+    if (I)
+      NeedsHandleIdentifier = true;
+    else
+      RecomputeNeedsHandleIdentifier();
+  }
+
   /// Determine whether this is the mangled name of an OpenMP variant.
   bool isMangledOpenMPVariantName() const { return IsMangledOpenMPVariantName; }
 
@@ -745,10 +762,11 @@ class IdentifierTable {
     // contents.
     II->Entry = &Entry;
 
-    // If this is the 'import' contextual keyword, mark it as such.
+    // If this is the 'import' or 'module' contextual keyword, mark it as such.
     if (Name == "import")
       II->setModulesImport(true);
-
+    else if (Name == "module")
+      II->setModulesDeclaration(true);
     return *II;
   }
 

clang/include/clang/Basic/TokenKinds.def

@@ -133,6 +133,9 @@ PPKEYWORD(pragma)
 // C23 & C++26 #embed
 PPKEYWORD(embed)
 
+// C++20 Module Directive
+PPKEYWORD(module)
+
 // GNU Extensions.
 PPKEYWORD(import)
 PPKEYWORD(include_next)
@@ -1023,6 +1026,9 @@ ANNOTATION(module_include)
 ANNOTATION(module_begin)
 ANNOTATION(module_end)
 
+// Annotations for C++, Clang and Objective-C named modules.
+ANNOTATION(module_name)
+
 // Annotation for a header_name token that has been looked up and transformed
 // into the name of a header unit.
 ANNOTATION(header_unit)

clang/include/clang/Frontend/CompilerInstance.h

@@ -863,7 +863,7 @@ class CompilerInstance : public ModuleLoader {
   /// load it.
   ModuleLoadResult findOrCompileModuleAndReadAST(StringRef ModuleName,
                                                  SourceLocation ImportLoc,
-                                                 SourceLocation ModuleNameLoc,
+                                                 SourceRange ModuleNameRange,
                                                  bool IsInclusionDirective);
 
   /// Creates a \c CompilerInstance for compiling a module.

clang/include/clang/Lex/CodeCompletionHandler.h

@@ -13,12 +13,15 @@
 #ifndef LLVM_CLANG_LEX_CODECOMPLETIONHANDLER_H
 #define LLVM_CLANG_LEX_CODECOMPLETIONHANDLER_H
 
+#include "clang/Basic/IdentifierTable.h"
+#include "clang/Basic/SourceLocation.h"
 #include "llvm/ADT/StringRef.h"
 
 namespace clang {
 
 class IdentifierInfo;
 class MacroInfo;
+using ModuleIdPath = ArrayRef<IdentifierLoc>;
 
 /// Callback handler that receives notifications when performing code
 /// completion within the preprocessor.
@@ -70,6 +73,11 @@ class CodeCompletionHandler {
   /// file where we expect natural language, e.g., a comment, string, or
   /// \#error directive.
   virtual void CodeCompleteNaturalLanguage() { }
+
+  /// Callback invoked when performing code completion inside the module name
+  /// part of an import directive.
+  virtual void CodeCompleteModuleImport(SourceLocation ImportLoc,
+                                        ModuleIdPath Path) {}
 };
 
 }

clang/include/clang/Lex/Lexer.h

@@ -124,7 +124,7 @@ class Lexer : public PreprocessorLexer {
   //===--------------------------------------------------------------------===//
   // Context that changes as the file is lexed.
   // NOTE: any state that mutates when in raw mode must have save/restore code
-  // in Lexer::isNextPPTokenLParen.
+  // in Lexer::peekNextPPToken.
 
   // BufferPtr - Current pointer into the buffer.  This is the next character
   // to be lexed.
@@ -645,10 +645,10 @@ class Lexer : public PreprocessorLexer {
     BufferPtr = TokEnd;
   }
 
-  /// isNextPPTokenLParen - Return 1 if the next unexpanded token will return a
-  /// tok::l_paren token, 0 if it is something else and 2 if there are no more
-  /// tokens in the buffer controlled by this lexer.
-  unsigned isNextPPTokenLParen();
+  /// peekNextPPToken - Return std::nullopt if there are no more tokens in the
+  /// buffer controlled by this lexer, otherwise return the next unexpanded
+  /// token.
+  std::optional<Token> peekNextPPToken();
 
   //===--------------------------------------------------------------------===//
   // Lexer character reading interfaces.