[clang] Fix preprocessor output from #embed (llvm#126742)

When bytes with negative signed char values appear in the data, make
sure to use raw bytes from the data string when preprocessing, not char
values.

Fixes llvm#102798

Author: Fznamznon

clang/docs/ReleaseNotes.rst

@@ -147,6 +147,9 @@ Improvements to Coverage Mapping
 Bug Fixes in This Version
 -------------------------
 
+- Clang now outputs correct values when #embed data contains bytes with negative
+  signed char values (#GH102798).
+
 Bug Fixes to Compiler Builtins
 ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
 

clang/lib/Frontend/PrintPreprocessedOutput.cpp

@@ -974,11 +974,10 @@ static void PrintPreprocessedTokens(Preprocessor &PP, Token &Tok,
       // Loop over the contents and print them as a comma-delimited list of
       // values.
       bool PrintComma = false;
-      for (auto Iter = Data->BinaryData.begin(), End = Data->BinaryData.end();
-           Iter != End; ++Iter) {
+      for (unsigned char Byte : Data->BinaryData.bytes()) {
         if (PrintComma)
           *Callbacks->OS << ", ";
-        *Callbacks->OS << static_cast<unsigned>(*Iter);
+        *Callbacks->OS << static_cast<int>(Byte);
         PrintComma = true;
       }
     } else if (Tok.isAnnotation()) {

clang/test/Preprocessor/embed_preprocess_to_file.c

@@ -37,3 +37,11 @@ const char even_more[] = {
 // DIRECTIVE-NEXT: #embed <jk.txt> prefix(4, 5,) suffix(, 6, 7) /* clang -E -dE */
 // DIRECTIVE-NEXT:  , 8, 9, 10
 // DIRECTIVE-NEXT: };
+
+constexpr char big_one[] = {
+#embed <big_char.txt>
+};
+
+// EXPANDED: constexpr char big_one[] = {255
+// DIRECTIVE: constexpr char big_one[] = {
+// DIRECTIVE-NEXT: #embed <big_char.txt>