[clang] [clang] Improve diagnostics for invalid named-universal-characters (PR #206326)

[Corentin Jabot via cfe-commits]

================
@@ -550,6 +556,44 @@ static void DiagnoseInvalidUnicodeCharacterName(
 
   namespace u = llvm::sys::unicode;
 
+  auto StringifyCodePoint = [](llvm::UTF32 CodePoint) -> llvm::SmallString<16> {
+    llvm::SmallString<16> Result;
+    if (u::isPrintable(CodePoint)) {
+      std::string CharUTF8;
+      llvm::convertUTF32ToUTF8String(llvm::ArrayRef<llvm::UTF32>(&CodePoint, 1),
+                                     CharUTF8);
+      Result.append("'");
+      Result.append(CharUTF8);
+      Result.append("' U+");
+    } else {
+      Result.append("U+");
+    }
+    llvm::raw_svector_ostream OS(Result);
+    llvm::write_hex(OS, CodePoint, llvm::HexPrintStyle::Upper, 4);
+    return Result;
+  };
----------------
cor3ntin wrote:

You should be able to use `FormatUTFCodeUnitAsCodepoint` (for a single char32) - or `EscapeStringForDiagnostic` (taking a utf-8 string so you'd first need to find the length of the codepoint with `getUTF8SequenceSize`

https://github.com/llvm/llvm-project/pull/206326