[Clang] Warn with -Wpre-c23-compat instead of -Wpre-c++17-compat for u8 character literals in C23 (#97210)

Co-authored-by: cor3ntin <[email protected]>

Author: MitalAshok

clang/docs/ReleaseNotes.rst

@@ -278,6 +278,8 @@ Improvements to Clang's diagnostics
 - The lifetimebound and GSL analysis in clang are coherent, allowing clang to
   detect more use-after-free bugs. (#GH100549).
 
+- Clang now warns for u8 character literals used in C23 with ``-Wpre-c23-compat`` instead of ``-Wpre-c++17-compat``.
+
 Improvements to Clang's time-trace
 ----------------------------------
 

clang/include/clang/Basic/DiagnosticLexKinds.td

@@ -283,6 +283,9 @@ def warn_cxx98_compat_unicode_literal : Warning<
 def warn_cxx14_compat_u8_character_literal : Warning<
   "unicode literals are incompatible with C++ standards before C++17">,
   InGroup<CXXPre17Compat>, DefaultIgnore;
+def warn_c17_compat_u8_character_literal : Warning<
+  "unicode literals are incompatible with C standards before C23">,
+  InGroup<CPre23Compat>, DefaultIgnore;
 def warn_cxx11_compat_user_defined_literal : Warning<
   "identifier after literal will be treated as a user-defined literal suffix "
   "in C++11">, InGroup<CXX11Compat>, DefaultIgnore;

clang/lib/Lex/Lexer.cpp

@@ -2428,7 +2428,9 @@ bool Lexer::LexCharConstant(Token &Result, const char *CurPtr,
                           ? diag::warn_cxx98_compat_unicode_literal
                           : diag::warn_c99_compat_unicode_literal);
     else if (Kind == tok::utf8_char_constant)
-      Diag(BufferPtr, diag::warn_cxx14_compat_u8_character_literal);
+      Diag(BufferPtr, LangOpts.CPlusPlus
+                          ? diag::warn_cxx14_compat_u8_character_literal
+                          : diag::warn_c17_compat_u8_character_literal);
   }
 
   char C = getAndAdvanceChar(CurPtr, Result);

clang/test/Sema/pre-c2x-compat.c

@@ -1,3 +1,4 @@
 // RUN: %clang_cc1 %s -std=c2x -Wpre-c2x-compat -pedantic -fsyntax-only -verify
 
 int digit_seps = 123'456; // expected-warning {{digit separators are incompatible with C standards before C23}}
+unsigned char u8_char = u8'x'; // expected-warning {{unicode literals are incompatible with C standards before C23}}