[clang-format] Update FormatToken::isSimpleTypeSpecifier()

clang/include/clang/Format/Format.h

@@ -5160,6 +5160,8 @@ tooling::Replacements sortUsingDeclarations(const FormatStyle &Style,
                                             ArrayRef<tooling::Range> Ranges,
                                             StringRef FileName = "<stdin>");
 
+extern LangOptions LangOpts;
+
 /// Returns the ``LangOpts`` that the formatter expects you to set.
 ///
 /// \param Style determines specific settings for lexing mode.

clang/include/clang/Lex/Token.h

@@ -13,6 +13,7 @@
 #ifndef LLVM_CLANG_LEX_TOKEN_H
 #define LLVM_CLANG_LEX_TOKEN_H
 
+#include "clang/Basic/LangOptions.h"
 #include "clang/Basic/SourceLocation.h"
 #include "clang/Basic/TokenKinds.h"
 #include "llvm/ADT/ArrayRef.h"
@@ -288,6 +289,8 @@ class Token {
   /// Return the ObjC keyword kind.
   tok::ObjCKeywordKind getObjCKeywordID() const;
 
+  bool isSimpleTypeSpecifier(const LangOptions &LangOpts) const;
+
   /// Return true if this token has trigraphs or escaped newlines in it.
   bool needsCleaning() const { return getFlag(NeedsCleaning); }
 

clang/include/clang/Sema/Sema.h

@@ -2683,8 +2683,6 @@ class Sema final {
 
   void DiagnoseUseOfUnimplementedSelectors();
 
-  bool isSimpleTypeSpecifier(const Token &Tok) const;
-
   ParsedType getTypeName(const IdentifierInfo &II, SourceLocation NameLoc,
                          Scope *S, CXXScopeSpec *SS = nullptr,
                          bool isClassName = false, bool HasTrailingDot = false,

clang/lib/Format/FormatToken.cpp

@@ -34,41 +34,8 @@ const char *getTokenTypeName(TokenType Type) {
   return nullptr;
 }
 
-// FIXME: This is copy&pasted from Sema. Put it in a common place and remove
-// duplication.
 bool FormatToken::isSimpleTypeSpecifier() const {
-  switch (Tok.getKind()) {
-  case tok::kw_short:
-  case tok::kw_long:
-  case tok::kw___int64:
-  case tok::kw___int128:
-  case tok::kw_signed:
-  case tok::kw_unsigned:
-  case tok::kw_void:
-  case tok::kw_char:
-  case tok::kw_int:
-  case tok::kw_half:
-  case tok::kw_float:
-  case tok::kw_double:
-  case tok::kw___bf16:
-  case tok::kw__Float16:
-  case tok::kw___float128:
-  case tok::kw___ibm128:
-  case tok::kw_wchar_t:
-  case tok::kw_bool:
-#define TRANSFORM_TYPE_TRAIT_DEF(_, Trait) case tok::kw___##Trait:
-#include "clang/Basic/TransformTypeTraits.def"
-  case tok::annot_typename:
-  case tok::kw_char8_t:
-  case tok::kw_char16_t:
-  case tok::kw_char32_t:
-  case tok::kw_typeof:
-  case tok::kw_decltype:
-  case tok::kw__Atomic:
-    return true;
-  default:
-    return false;
-  }
+  return Tok.isSimpleTypeSpecifier(LangOpts);
 }
 
 bool FormatToken::isTypeOrIdentifier() const {

clang/lib/Format/FormatTokenLexer.cpp

@@ -22,18 +22,20 @@
 namespace clang {
 namespace format {
 
+LangOptions LangOpts;
+
 FormatTokenLexer::FormatTokenLexer(
     const SourceManager &SourceMgr, FileID ID, unsigned Column,
     const FormatStyle &Style, encoding::Encoding Encoding,
     llvm::SpecificBumpPtrAllocator<FormatToken> &Allocator,
     IdentifierTable &IdentTable)
     : FormatTok(nullptr), IsFirstToken(true), StateStack({LexerState::NORMAL}),
-      Column(Column), TrailingWhitespace(0),
-      LangOpts(getFormattingLangOpts(Style)), SourceMgr(SourceMgr), ID(ID),
+      Column(Column), TrailingWhitespace(0), SourceMgr(SourceMgr), ID(ID),
       Style(Style), IdentTable(IdentTable), Keywords(IdentTable),
       Encoding(Encoding), Allocator(Allocator), FirstInLineIndex(0),
       FormattingDisabled(false), MacroBlockBeginRegex(Style.MacroBlockBegin),
       MacroBlockEndRegex(Style.MacroBlockEnd) {
+  LangOpts = getFormattingLangOpts(Style);
   Lex.reset(new Lexer(ID, SourceMgr.getBufferOrFake(ID), SourceMgr, LangOpts));
   Lex->SetKeepWhitespaceMode(true);
 
@@ -1442,7 +1444,6 @@ void FormatTokenLexer::readRawToken(FormatToken &Tok) {
 
 void FormatTokenLexer::resetLexer(unsigned Offset) {
   StringRef Buffer = SourceMgr.getBufferData(ID);
-  LangOpts = getFormattingLangOpts(Style);
   Lex.reset(new Lexer(SourceMgr.getLocForStartOfFile(ID), LangOpts,
                       Buffer.begin(), Buffer.begin() + Offset, Buffer.end()));
   Lex->SetKeepWhitespaceMode(true);

clang/lib/Format/FormatTokenLexer.h

@@ -120,7 +120,6 @@ class FormatTokenLexer {
   unsigned Column;
   unsigned TrailingWhitespace;
   std::unique_ptr<Lexer> Lex;
-  LangOptions LangOpts;
   const SourceManager &SourceMgr;
   FileID ID;
   const FormatStyle &Style;

clang/lib/Lex/Lexer.cpp

@@ -74,6 +74,51 @@ tok::ObjCKeywordKind Token::getObjCKeywordID() const {
   return specId ? specId->getObjCKeywordID() : tok::objc_not_keyword;
 }
 
+/// Determine whether the token kind starts a simple-type-specifier.
+bool Token::isSimpleTypeSpecifier(const LangOptions &LangOpts) const {
+  switch (getKind()) {
+  case tok::annot_typename:
+  case tok::annot_decltype:
+  case tok::annot_pack_indexing_type:
+    return true;
+
+  case tok::kw_short:
+  case tok::kw_long:
+  case tok::kw___int64:
+  case tok::kw___int128:
+  case tok::kw_signed:
+  case tok::kw_unsigned:
+  case tok::kw_void:
+  case tok::kw_char:
+  case tok::kw_int:
+  case tok::kw_half:
+  case tok::kw_float:
+  case tok::kw_double:
+  case tok::kw___bf16:
+  case tok::kw__Float16:
+  case tok::kw___float128:
+  case tok::kw___ibm128:
+  case tok::kw_wchar_t:
+  case tok::kw_bool:
+  case tok::kw__Bool:
+  case tok::kw__Accum:
+  case tok::kw__Fract:
+  case tok::kw__Sat:
+#define TRANSFORM_TYPE_TRAIT_DEF(_, Trait) case tok::kw___##Trait:
+#include "clang/Basic/TransformTypeTraits.def"
+  case tok::kw___auto_type:
+  case tok::kw_char16_t:
+  case tok::kw_char32_t:
+  case tok::kw_typeof:
+  case tok::kw_decltype:
+  case tok::kw_char8_t:
+    return getIdentifierInfo()->isKeyword(LangOpts);
+
+  default:
+    return false;
+  }
+}
+
 //===----------------------------------------------------------------------===//
 // Lexer Class Implementation
 //===----------------------------------------------------------------------===//

clang/lib/Parse/ParseExpr.cpp

@@ -1609,7 +1609,7 @@ ExprResult Parser::ParseCastExpression(CastParseKind ParseKind,
       if (TryAnnotateTypeOrScopeToken())
         return ExprError();
 
-      if (!Actions.isSimpleTypeSpecifier(Tok))
+      if (!Tok.isSimpleTypeSpecifier(getLangOpts()))
         // We are trying to parse a simple-type-specifier but might not get such
         // a token after error recovery.
         return ExprError();

clang/lib/Parse/ParseObjc.cpp

@@ -2971,7 +2971,7 @@ bool Parser::ParseObjCXXMessageReceiver(bool &IsExpr, void *&TypeOrExpr) {
                   tok::annot_cxxscope))
     TryAnnotateTypeOrScopeToken();
 
-  if (!Actions.isSimpleTypeSpecifier(Tok)) {
+  if (!Tok.isSimpleTypeSpecifier(getLangOpts())) {
     //   objc-receiver:
     //     expression
     // Make sure any typos in the receiver are corrected or diagnosed, so that

clang/lib/Sema/SemaDecl.cpp

@@ -127,51 +127,6 @@ class TypeNameValidatorCCC final : public CorrectionCandidateCallback {
 
 } // end anonymous namespace
 
-/// Determine whether the token kind starts a simple-type-specifier.
-bool Sema::isSimpleTypeSpecifier(const Token &Tok) const {
-  switch (Tok.getKind()) {
-  case tok::annot_typename:
-  case tok::annot_decltype:
-  case tok::annot_pack_indexing_type:
-    return true;
-
-  case tok::kw_short:
-  case tok::kw_long:
-  case tok::kw___int64:
-  case tok::kw___int128:
-  case tok::kw_signed:
-  case tok::kw_unsigned:
-  case tok::kw_void:
-  case tok::kw_char:
-  case tok::kw_int:
-  case tok::kw_half:
-  case tok::kw_float:
-  case tok::kw_double:
-  case tok::kw___bf16:
-  case tok::kw__Float16:
-  case tok::kw___float128:
-  case tok::kw___ibm128:
-  case tok::kw_wchar_t:
-  case tok::kw_bool:
-  case tok::kw__Bool:
-  case tok::kw__Accum:
-  case tok::kw__Fract:
-  case tok::kw__Sat:
-#define TRANSFORM_TYPE_TRAIT_DEF(_, Trait) case tok::kw___##Trait:
-#include "clang/Basic/TransformTypeTraits.def"
-  case tok::kw___auto_type:
-  case tok::kw_char16_t:
-  case tok::kw_char32_t:
-  case tok::kw_typeof:
-  case tok::kw_decltype:
-  case tok::kw_char8_t:
-    return Tok.getIdentifierInfo()->isKeyword(getLangOpts());
-
-  default:
-    return false;
-  }
-}
-
 namespace {
 enum class UnqualifiedTypeNameLookupResult {
   NotFound,