[clang] [clang-format] Update FormatToken::isSimpleTypeSpecifier() (PR #79115)

[Owen Pan via cfe-commits]

https://github.com/owenca updated https://github.com/llvm/llvm-project/pull/79115

>From 6d11eaa2c9b5de0b42b82c6b52b35eca44b5d772 Mon Sep 17 00:00:00 2001
From: Owen Pan <owenpiano at gmail.com>
Date: Tue, 23 Jan 2024 02:35:09 -0800
Subject: [PATCH] [clang-format] Update FormatToken::isSimpleTypeSpecifier()

---
 clang/include/clang/Format/Format.h   |  2 ++
 clang/lib/Format/FormatToken.cpp      | 36 ++-------------------------
 clang/lib/Format/FormatTokenLexer.cpp |  7 +++---
 clang/lib/Format/FormatTokenLexer.h   |  1 -
 4 files changed, 8 insertions(+), 38 deletions(-)

diff --git a/clang/include/clang/Format/Format.h b/clang/include/clang/Format/Format.h
index bc9eecd42f9ebf..2800f6db4a9786 100644
--- a/clang/include/clang/Format/Format.h
+++ b/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.
diff --git a/clang/lib/Format/FormatToken.cpp b/clang/lib/Format/FormatToken.cpp
index b791c5a26bbe3a..a030d91d5589a5 100644
--- a/clang/lib/Format/FormatToken.cpp
+++ b/clang/lib/Format/FormatToken.cpp
@@ -34,41 +34,9 @@ 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;
-  }
+  const auto *IdentifierInfo = Tok.getIdentifierInfo();
+  return IdentifierInfo && IdentifierInfo->isSimpleTypeSpecifier(LangOpts);
 }
 
 bool FormatToken::isTypeOrIdentifier() const {
diff --git a/clang/lib/Format/FormatTokenLexer.cpp b/clang/lib/Format/FormatTokenLexer.cpp
index 52a55ea23b5f2f..e6575dd417438a 100644
--- a/clang/lib/Format/FormatTokenLexer.cpp
+++ b/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);
 
@@ -1411,7 +1413,6 @@ 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);
diff --git a/clang/lib/Format/FormatTokenLexer.h b/clang/lib/Format/FormatTokenLexer.h
index 65dd733bd53352..52838f1d8a17f5 100644
--- a/clang/lib/Format/FormatTokenLexer.h
+++ b/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;