[clang-format] Lex C++ only keywords as identifiers in C

[owenca]

Fix #128847

[llvmbot]

@llvm/pr-subscribers-clang-format

Author: Owen Pan (owenca)

Changes

Fix #128847

---

Full diff: https://github.com/llvm/llvm-project/pull/129426.diff

2 Files Affected:

• (modified) clang/lib/Format/Format.cpp (+25-17)
• (modified) clang/unittests/Format/TokenAnnotatorTest.cpp (+9)

diff --git a/clang/lib/Format/Format.cpp b/clang/lib/Format/Format.cpp
index 92678a031178a..7aa23cb8498fe 100644
--- a/clang/lib/Format/Format.cpp
+++ b/clang/lib/Format/Format.cpp
@@ -3941,34 +3941,42 @@ tooling::Replacements sortUsingDeclarations(const FormatStyle &Style,
 LangOptions getFormattingLangOpts(const FormatStyle &Style) {
   LangOptions LangOpts;
 
-  FormatStyle::LanguageStandard LexingStd = Style.Standard;
-  if (LexingStd == FormatStyle::LS_Auto)
-    LexingStd = FormatStyle::LS_Latest;
-  if (LexingStd == FormatStyle::LS_Latest)
+  auto LexingStd = Style.Standard;
+  if (LexingStd == FormatStyle::LS_Auto || LexingStd == FormatStyle::LS_Latest)
     LexingStd = FormatStyle::LS_Cpp20;
-  LangOpts.CPlusPlus = 1;
-  LangOpts.CPlusPlus11 = LexingStd >= FormatStyle::LS_Cpp11;
-  LangOpts.CPlusPlus14 = LexingStd >= FormatStyle::LS_Cpp14;
-  LangOpts.CPlusPlus17 = LexingStd >= FormatStyle::LS_Cpp17;
-  LangOpts.CPlusPlus20 = LexingStd >= FormatStyle::LS_Cpp20;
-  LangOpts.Char8 = LexingStd >= FormatStyle::LS_Cpp20;
+
+  const bool SinceCpp11 = LexingStd >= FormatStyle::LS_Cpp11;
+  const bool SinceCpp20 = LexingStd >= FormatStyle::LS_Cpp20;
+
+  switch (Style.Language) {
+  case FormatStyle::LK_C:
+    LangOpts.C17 = 1;
+    break;
+  case FormatStyle::LK_Cpp:
+  case FormatStyle::LK_ObjC:
+    LangOpts.CXXOperatorNames = 1;
+    LangOpts.CPlusPlus11 = SinceCpp11;
+    LangOpts.CPlusPlus14 = LexingStd >= FormatStyle::LS_Cpp14;
+    LangOpts.CPlusPlus17 = LexingStd >= FormatStyle::LS_Cpp17;
+    LangOpts.CPlusPlus20 = SinceCpp20;
+    [[fallthrough]];
+  default:
+    LangOpts.CPlusPlus = 1;
+  }
+
+  LangOpts.Char8 = SinceCpp20;
   // Turning on digraphs in standards before C++0x is error-prone, because e.g.
   // the sequence "<::" will be unconditionally treated as "[:".
   // Cf. Lexer::LexTokenInternal.
-  LangOpts.Digraphs = LexingStd >= FormatStyle::LS_Cpp11;
+  LangOpts.Digraphs = SinceCpp11;
 
   LangOpts.LineComment = 1;
-
-  const auto Language = Style.Language;
-  LangOpts.C17 = Language == FormatStyle::LK_C;
-  LangOpts.CXXOperatorNames =
-      Language == FormatStyle::LK_Cpp || Language == FormatStyle::LK_ObjC;
-
   LangOpts.Bool = 1;
   LangOpts.ObjC = 1;
   LangOpts.MicrosoftExt = 1;    // To get kw___try, kw___finally.
   LangOpts.DeclSpecKeyword = 1; // To get __declspec.
   LangOpts.C99 = 1; // To get kw_restrict for non-underscore-prefixed restrict.
+
   return LangOpts;
 }
 
diff --git a/clang/unittests/Format/TokenAnnotatorTest.cpp b/clang/unittests/Format/TokenAnnotatorTest.cpp
index 1e1774ba5b3b5..b44a369f77d92 100644
--- a/clang/unittests/Format/TokenAnnotatorTest.cpp
+++ b/clang/unittests/Format/TokenAnnotatorTest.cpp
@@ -3705,6 +3705,15 @@ TEST_F(TokenAnnotatorTest, CppAltOperatorKeywords) {
   EXPECT_TOKEN(Tokens[1], tok::identifier, TT_StartOfName);
 }
 
+TEST_F(TokenAnnotatorTest, CppOnlyKeywordInC) {
+  auto Tokens = annotate("int maximized = new & STATE_MAXIMIZED;",
+                         getLLVMStyle(FormatStyle::LK_C));
+  ASSERT_EQ(Tokens.size(), 8u) << Tokens;
+  EXPECT_TOKEN(Tokens[3], tok::identifier, TT_Unknown); // Not tok::kw_new
+  EXPECT_TOKEN(Tokens[4], tok::amp, TT_BinaryOperator);
+  EXPECT_TOKEN(Tokens[3], tok::identifier, TT_Unknown); // Not TT_StartOfName
+}
+
 TEST_F(TokenAnnotatorTest, FunctionTryBlock) {
   auto Tokens =
       annotate("Foo::Foo(int x, int y) try\n"