[c++20] Implement P0482R6: enable -fchar8_t by default in C++20 mode.

This unfortunately results in a substantial breaking change when
switching to C++20, but it's not yet clear what / how much we should
do about that. We may want to add a compatibility conversion from
u8 string literals to const char*, similar to how C++98 provided a
compatibility conversion from string literals to non-const char*,
but that's not handled by this patch.

The feature can be disabled in C++20 mode with -fno-char8_t.

llvm-svn: 346892

1 files changed, 26 insertions, 0 deletions

diff --git a/clang/lib/Sema/SemaExpr.cpp b/clang/lib/Sema/SemaExpr.cpp
index c549514da83..980dbf9921f 100644
--- a/clang/lib/Sema/SemaExpr.cpp
+++ b/clang/lib/Sema/SemaExpr.cpp
@@ -1559,6 +1559,32 @@ Sema::ActOnStringLiteral(ArrayRef<Token> StringToks, Scope *UDLScope) {
     CharTy = Context.UnsignedCharTy;
   }
 
+  // Warn on initializing an array of char from a u8 string literal; this
+  // becomes ill-formed in C++2a.
+  if (getLangOpts().CPlusPlus && !getLangOpts().CPlusPlus2a &&
+      !getLangOpts().Char8 && Kind == StringLiteral::UTF8) {
+    Diag(StringTokLocs.front(), diag::warn_cxx2a_compat_utf8_string);
+
+    // Create removals for all 'u8' prefixes in the string literal(s). This
+    // ensures C++2a compatibility (but may change the program behavior when
+    // built by non-Clang compilers for which the execution character set is
+    // not always UTF-8).
+    auto RemovalDiag = PDiag(diag::note_cxx2a_compat_utf8_string_remove_u8);
+    SourceLocation RemovalDiagLoc;
+    for (const Token &Tok : StringToks) {
+      if (Tok.getKind() == tok::utf8_string_literal) {
+        if (RemovalDiagLoc.isInvalid())
+          RemovalDiagLoc = Tok.getLocation();
+        RemovalDiag << FixItHint::CreateRemoval(CharSourceRange::getCharRange(
+            Tok.getLocation(),
+            Lexer::AdvanceToTokenCharacter(Tok.getLocation(), 2,
+                                           getSourceManager(), getLangOpts())));
+      }
+    }
+    Diag(RemovalDiagLoc, RemovalDiag);
+  }
+
+
   QualType CharTyConst = CharTy;
   // A C++ string literal has a const-qualified element type (C++ 2.13.4p1).
   if (getLangOpts().CPlusPlus || getLangOpts().ConstStrings)