[clang][lexer] Allow u8 character literal prefixes in C2x

Implement N2418 for C2x.

Differential Revision: https://reviews.llvm.org/D119221

clang/docs/ReleaseNotes.rst

@@ -226,6 +226,7 @@ C2x Feature Support
 - Implemented `WG14 N2775 Literal suffixes for bit-precise integers <http://www.open-std.org/jtc1/sc22/wg14/www/docs/n2775.pdf>`_.
 - Implemented the `*_WIDTH` macros to complete support for
   `WG14 N2412 Two's complement sign representation for C2x <https://www9.open-std.org/jtc1/sc22/wg14/www/docs/n2412.pdf>`_.
+- Implemented `WG14 N2418 Adding the u8 character prefix <http://www.open-std.org/jtc1/sc22/wg14/www/docs/n2418.pdf>`_.
 
 C++ Language Changes in Clang
 -----------------------------

clang/lib/Lex/Lexer.cpp

@@ -3459,7 +3459,10 @@ LexNextToken:
     MIOpt.ReadToken();
     return LexNumericConstant(Result, CurPtr);
 
-  case 'u':   // Identifier (uber) or C11/C++11 UTF-8 or UTF-16 string literal
+  // Identifier (e.g., uber), or
+  // UTF-8 (C2x/C++17) or UTF-16 (C11/C++11) character literal, or
+  // UTF-8 or UTF-16 string literal (C11/C++11).
+  case 'u':
     // Notify MIOpt that we read a non-whitespace/non-comment token.
     MIOpt.ReadToken();
 
@@ -3493,7 +3496,7 @@ LexNextToken:
                                ConsumeChar(ConsumeChar(CurPtr, SizeTmp, Result),
                                            SizeTmp2, Result),
                                tok::utf8_string_literal);
-        if (Char2 == '\'' && LangOpts.CPlusPlus17)
+        if (Char2 == '\'' && (LangOpts.CPlusPlus17 || LangOpts.C2x))
           return LexCharConstant(
               Result, ConsumeChar(ConsumeChar(CurPtr, SizeTmp, Result),
                                   SizeTmp2, Result),
@@ -3517,7 +3520,7 @@ LexNextToken:
     // treat u like the start of an identifier.
     return LexIdentifierContinue(Result, CurPtr);
 
-  case 'U':   // Identifier (Uber) or C11/C++11 UTF-32 string literal
+  case 'U': // Identifier (e.g. Uber) or C11/C++11 UTF-32 string literal
     // Notify MIOpt that we read a non-whitespace/non-comment token.
     MIOpt.ReadToken();
 

clang/lib/Sema/SemaExpr.cpp

@@ -3609,6 +3609,8 @@ ExprResult Sema::ActOnCharacterConstant(const Token &Tok, Scope *UDLScope) {
   QualType Ty;
   if (Literal.isWide())
     Ty = Context.WideCharTy; // L'x' -> wchar_t in C and C++.
+  else if (Literal.isUTF8() && getLangOpts().C2x)
+    Ty = Context.UnsignedCharTy; // u8'x' -> unsigned char in C2x
   else if (Literal.isUTF8() && getLangOpts().Char8)
     Ty = Context.Char8Ty; // u8'x' -> char8_t when it exists.
   else if (Literal.isUTF16())
@@ -3618,7 +3620,8 @@ ExprResult Sema::ActOnCharacterConstant(const Token &Tok, Scope *UDLScope) {
   else if (!getLangOpts().CPlusPlus || Literal.isMultiChar())
     Ty = Context.IntTy;   // 'x' -> int in C, 'wxyz' -> int in C++.
   else
-    Ty = Context.CharTy;  // 'x' -> char in C++
+    Ty = Context.CharTy; // 'x' -> char in C++;
+                         // u8'x' -> char in C11-C17 and in C++ without char8_t.
 
   CharacterLiteral::CharacterKind Kind = CharacterLiteral::Ascii;
   if (Literal.isWide())

clang/test/Lexer/utf8-char-literal.cpp

@@ -1,5 +1,6 @@
 // RUN: %clang_cc1 -triple x86_64-apple-darwin -std=c++11 -fsyntax-only -verify %s
 // RUN: %clang_cc1 -triple x86_64-apple-darwin -std=c11 -x c -fsyntax-only -verify %s
+// RUN: %clang_cc1 -triple x86_64-apple-darwin -std=c2x -x c -fsyntax-only -verify %s
 // RUN: %clang_cc1 -triple x86_64-apple-darwin -std=c++1z -fsyntax-only -verify %s
 
 int array0[u'ñ' == u'\xf1'? 1 : -1];
@@ -12,4 +13,16 @@ char c = u8'\u0080'; // expected-error {{character too large for enclosing chara
 char d = u8'\u1234'; // expected-error {{character too large for enclosing character literal type}}
 char e = u8'ሴ'; // expected-error {{character too large for enclosing character literal type}}
 char f = u8'ab'; // expected-error {{Unicode character literals may not contain multiple characters}}
+#elif __STDC_VERSION__ > 202000L
+char a = u8'ñ';      // expected-error {{character too large for enclosing character literal type}}
+char b = u8'\x80';   // ok
+char c = u8'\u0080'; // expected-error {{universal character name refers to a control character}}
+char d = u8'\u1234'; // expected-error {{character too large for enclosing character literal type}}
+char e = u8'ሴ';      // expected-error {{character too large for enclosing character literal type}}
+char f = u8'ab';     // expected-error {{Unicode character literals may not contain multiple characters}}
+_Static_assert(
+    _Generic(u8'a',
+             default : 0,
+             unsigned char : 1),
+    "Surprise!");
 #endif

clang/www/c_status.html

@@ -720,7 +720,7 @@ conformance.</p>
     <tr>
       <td>Adding the u8 character prefix</td>
       <td><a href="http://www.open-std.org/jtc1/sc22/wg14/www/docs/n2418.pdf">N2418</a></td>
-      <td class="none" align="center">No</td>
+      <td class="unreleased" align="center">Clang 15</td>
     </tr>
     <tr>
       <td>Remove support for function definitions with identifier lists</td>