Update the support for escape sequences

Author: AaronBallman

clang/include/clang/Basic/DiagnosticLexKinds.td

@@ -148,14 +148,14 @@ def ext_mathematical_notation : ExtWarn<
   InGroup<DiagGroup<"mathematical-notation-identifier-extension">>;
 
 def ext_delimited_escape_sequence : Extension<
-  "%select{delimited|named}0 escape sequences are a "
-  "%select{Clang|C++23}1 extension">,
-  InGroup<DiagGroup<"delimited-escape-sequence-extension">>;
-
+  "%select{delimited|named}0 escape sequences are a %select{C++23|C2y}1 "
+  "extension">, InGroup<DiagGroup<"delimited-escape-sequence-extension">>;
 def warn_cxx23_delimited_escape_sequence : Warning<
-  "%select{delimited|named}0 escape sequences are "
-  "incompatible with C++ standards before C++23">,
-  InGroup<CXXPre23Compat>, DefaultIgnore;
+  "%select{delimited|named}0 escape sequences are incompatible with C++ "
+  "standards before C++23">, InGroup<CXXPre23Compat>, DefaultIgnore;
+def warn_c2y_delimited_escape_sequence : Warning<
+  "delimited escape sequences are incompatible with C standards before C2y">,
+  InGroup<CPre2yCompat>, DefaultIgnore;
 
 def err_delimited_escape_empty : Error<
   "delimited escape sequence cannot be empty">;

clang/include/clang/Lex/Lexer.h

@@ -582,6 +582,12 @@ class Lexer : public PreprocessorLexer {
   /// sequence.
   static bool isNewLineEscaped(const char *BufferStart, const char *Str);
 
+  /// Diagnose use of a delimited or named escape sequence.
+  static void DiagnoseDelimitedOrNamedEscapeSequence(SourceLocation Loc,
+                                                     bool Named,
+                                                     const LangOptions &Opts,
+                                                     DiagnosticsEngine &Diags);
+
   /// Represents a char and the number of bytes parsed to produce it.
   struct SizedChar {
     char Char;

clang/lib/Lex/Lexer.cpp

@@ -3405,6 +3405,24 @@ bool Lexer::isCodeCompletionPoint(const char *CurPtr) const {
   return false;
 }
 
+void Lexer::DiagnoseDelimitedOrNamedEscapeSequence(SourceLocation Loc,
+                                                   bool Named,
+                                                   const LangOptions &Opts,
+                                                   DiagnosticsEngine &Diags) {
+  unsigned DiagId;
+  if (Opts.CPlusPlus23)
+    DiagId = diag::warn_cxx23_delimited_escape_sequence;
+  else if (Opts.C2y)
+    DiagId = diag::warn_c2y_delimited_escape_sequence;
+  else
+    DiagId = diag::ext_delimited_escape_sequence;
+
+  // The trailing arguments are only used by the extension warning; either this
+  // is a C2y extension or a C++23 extension.
+  Diags.Report(Loc, DiagId) << Named << !Opts.CPlusPlus;
+}
+
+
 std::optional<uint32_t> Lexer::tryReadNumericUCN(const char *&StartPtr,
                                                  const char *SlashLoc,
                                                  Token *Result) {
@@ -3496,12 +3514,10 @@ std::optional<uint32_t> Lexer::tryReadNumericUCN(const char *&StartPtr,
     return std::nullopt;
   }
 
-  if (Delimited && PP) {
-    Diag(SlashLoc, PP->getLangOpts().CPlusPlus23
-                       ? diag::warn_cxx23_delimited_escape_sequence
-                       : diag::ext_delimited_escape_sequence)
-        << /*delimited*/ 0 << (PP->getLangOpts().CPlusPlus ? 1 : 0);
-  }
+  if (Delimited && PP)
+    DiagnoseDelimitedOrNamedEscapeSequence(getSourceLocation(SlashLoc), false,
+                                           PP->getLangOpts(),
+                                           PP->getDiagnostics());
 
   if (Result) {
     Result->setFlag(Token::HasUCN);
@@ -3585,10 +3601,9 @@ std::optional<uint32_t> Lexer::tryReadNamedUCN(const char *&StartPtr,
   }
 
   if (Diagnose && Match)
-    Diag(SlashLoc, PP->getLangOpts().CPlusPlus23
-                       ? diag::warn_cxx23_delimited_escape_sequence
-                       : diag::ext_delimited_escape_sequence)
-        << /*named*/ 1 << (PP->getLangOpts().CPlusPlus ? 1 : 0);
+    DiagnoseDelimitedOrNamedEscapeSequence(getSourceLocation(SlashLoc), true,
+                                           PP->getLangOpts(),
+                                           PP->getDiagnostics());
 
   // If no diagnostic has been emitted yet, likely because we are doing a
   // tentative lexing, we do not want to recover here to make sure the token

clang/lib/Lex/LiteralSupport.cpp

@@ -354,10 +354,8 @@ static unsigned ProcessCharEscape(const char *ThisTokBegin,
            diag::err_expected)
           << tok::r_brace;
     else if (!HadError) {
-      Diag(Diags, Features, Loc, ThisTokBegin, EscapeBegin, ThisTokBuf,
-           Features.CPlusPlus23 ? diag::warn_cxx23_delimited_escape_sequence
-                                : diag::ext_delimited_escape_sequence)
-          << /*delimited*/ 0 << (Features.CPlusPlus ? 1 : 0);
+      Lexer::DiagnoseDelimitedOrNamedEscapeSequence(Loc, false, Features,
+                                                    *Diags);
     }
   }
 
@@ -710,11 +708,8 @@ static bool ProcessUCNEscape(const char *ThisTokBegin, const char *&ThisTokBuf,
          diag::warn_ucn_not_valid_in_c89_literal);
 
   if ((IsDelimitedEscapeSequence || IsNamedEscapeSequence) && Diags)
-    Diag(Diags, Features, Loc, ThisTokBegin, UcnBegin, ThisTokBuf,
-         Features.CPlusPlus23 ? diag::warn_cxx23_delimited_escape_sequence
-                              : diag::ext_delimited_escape_sequence)
-        << (IsNamedEscapeSequence ? 1 : 0) << (Features.CPlusPlus ? 1 : 0);
-
+    Lexer::DiagnoseDelimitedOrNamedEscapeSequence(Loc, IsNamedEscapeSequence,
+                                                  Features, *Diags);
   return true;
 }
 

clang/test/C/C2y/n3353.c

@@ -92,6 +92,13 @@ int r = M;  /* compat-warning {{octal integer literals are incompatible with sta
                cpp-warning {{octal integer literals are a Clang extension}}
              */
 
+// Also, test delimited escape sequences. Note, this paper added a delimited
+// escape sequence for octal *and* hex.
+auto a = "\x{12}\o{12}";   /* compat-warning 2 {{delimited escape sequences are incompatible with C standards before C2y}}
+                              ext-warning 2 {{delimited escape sequences are a C2y extension}}
+                              cpp-warning 2 {{delimited escape sequences are a C++23 extension}}
+                            */
+
 #ifdef __cplusplus
 template <unsigned N>
 struct S {