[clang] Introduce "binary" StringLiteral for #embed data (#127629)

StringLiteral is used as internal data of EmbedExpr and we directly use
it as an initializer if a single EmbedExpr appears in the initializer
list of a char array. It is fast and convenient, but it is causing
problems when string literal character values are checked because #embed
data values are within a range [0-2^(char width)] but ordinary
StringLiteral is of maybe signed char type.
This PR introduces new kind of StringLiteral to hold binary data coming
from an embedded resource to mitigate these problems. The new kind of
StringLiteral is not assumed to have signed char type. The new kind of
StringLiteral also helps to prevent crashes when trying to find
StringLiteral token locations since these simply do not exist for binary
data.

Fixes #119256

Author: Fznamznon

clang/include/clang/AST/Expr.h

@@ -1756,7 +1756,14 @@ enum class StringLiteralKind {
   UTF8,
   UTF16,
   UTF32,
-  Unevaluated
+  Unevaluated,
+  // Binary kind of string literal is used for the data coming via #embed
+  // directive. File's binary contents is transformed to a special kind of
+  // string literal that in some cases may be used directly as an initializer
+  // and some features of classic string literals are not applicable to this
+  // kind of a string literal, for example finding a particular byte's source
+  // location for better diagnosing.
+  Binary
 };
 
 /// StringLiteral - This represents a string literal expression, e.g. "foo"
@@ -1888,6 +1895,8 @@ class StringLiteral final
   int64_t getCodeUnitS(size_t I, uint64_t BitWidth) const {
     int64_t V = getCodeUnit(I);
     if (isOrdinary() || isWide()) {
+      // Ordinary and wide string literals have types that can be signed.
+      // It is important for checking C23 constexpr initializers.
       unsigned Width = getCharByteWidth() * BitWidth;
       llvm::APInt AInt(Width, (uint64_t)V);
       V = AInt.getSExtValue();
@@ -5029,9 +5038,9 @@ class EmbedExpr final : public Expr {
       assert(EExpr && CurOffset != ULLONG_MAX &&
              "trying to dereference an invalid iterator");
       IntegerLiteral *N = EExpr->FakeChildNode;
-      StringRef DataRef = EExpr->Data->BinaryData->getBytes();
       N->setValue(*EExpr->Ctx,
-                  llvm::APInt(N->getValue().getBitWidth(), DataRef[CurOffset],
+                  llvm::APInt(N->getValue().getBitWidth(),
+                              EExpr->Data->BinaryData->getCodeUnit(CurOffset),
                               N->getType()->isSignedIntegerType()));
       // We want to return a reference to the fake child node in the
       // EmbedExpr, not the local variable N.

clang/lib/AST/Expr.cpp

@@ -1104,6 +1104,7 @@ unsigned StringLiteral::mapCharByteWidth(TargetInfo const &Target,
   switch (SK) {
   case StringLiteralKind::Ordinary:
   case StringLiteralKind::UTF8:
+  case StringLiteralKind::Binary:
     CharByteWidth = Target.getCharWidth();
     break;
   case StringLiteralKind::Wide:
@@ -1216,6 +1217,7 @@ void StringLiteral::outputString(raw_ostream &OS) const {
   switch (getKind()) {
   case StringLiteralKind::Unevaluated:
   case StringLiteralKind::Ordinary:
+  case StringLiteralKind::Binary:
     break; // no prefix.
   case StringLiteralKind::Wide:
     OS << 'L';
@@ -1332,6 +1334,11 @@ StringLiteral::getLocationOfByte(unsigned ByteNo, const SourceManager &SM,
                                  const LangOptions &Features,
                                  const TargetInfo &Target, unsigned *StartToken,
                                  unsigned *StartTokenByteOffset) const {
+  // No source location of bytes for binary literals since they don't come from
+  // source.
+  if (getKind() == StringLiteralKind::Binary)
+    return getStrTokenLoc(0);
+
   assert((getKind() == StringLiteralKind::Ordinary ||
           getKind() == StringLiteralKind::UTF8 ||
           getKind() == StringLiteralKind::Unevaluated) &&

clang/lib/Parse/ParseInit.cpp

@@ -445,7 +445,7 @@ ExprResult Parser::createEmbedExpr() {
           Context.MakeIntValue(Str.size(), Context.getSizeType());
       QualType ArrayTy = Context.getConstantArrayType(
           Ty, ArraySize, nullptr, ArraySizeModifier::Normal, 0);
-      return StringLiteral::Create(Context, Str, StringLiteralKind::Ordinary,
+      return StringLiteral::Create(Context, Str, StringLiteralKind::Binary,
                                    false, ArrayTy, StartLoc);
     };
 

clang/lib/Sema/SemaInit.cpp

@@ -106,6 +106,7 @@ static StringInitFailureKind IsStringInit(Expr *Init, const ArrayType *AT,
       return SIF_None;
     [[fallthrough]];
   case StringLiteralKind::Ordinary:
+  case StringLiteralKind::Binary:
     // char array can be initialized with a narrow string.
     // Only allow char x[] = "foo";  not char x[] = L"foo";
     if (ElemTy->isCharType())

clang/test/Preprocessor/embed_constexpr.c

@@ -0,0 +1,21 @@
+// RUN: %clang_cc1 %s -fsyntax-only --embed-dir=%S/Inputs -verify -std=c23
+
+static constexpr unsigned char data[] = {
+#embed "big_char.txt"
+};
+
+static constexpr char data1[] = {
+#embed "big_char.txt" // expected-error {{constexpr initializer evaluates to 255 which is not exactly representable in type 'const char'}}
+};
+
+static constexpr int data2[] = {
+#embed "big_char.txt"
+};
+
+static constexpr unsigned data3[] = {
+#embed "big_char.txt" suffix(, -1) // expected-error {{constexpr initializer evaluates to -1 which is not exactly representable in type 'const unsigned int'}}
+};
+
+static constexpr int data4[] = {
+#embed "big_char.txt" suffix(, -1)
+};