[clang] [clang] Constant-evaluate format strings as last resort (PR #135864)

[via cfe-commits]

================
@@ -6331,26 +6321,79 @@ static StringLiteralCheckType checkFormatStringExpr(
       }
     }
 
-    return SLCT_NotALiteral;
+    // try to constant-evaluate the string
+    break;
   }
 
   default:
+    // try to constant-evaluate the string
+    break;
+  }
+
+  const StringLiteral *FakeLiteral = nullptr;
+  switch (constEvalStringAsLiteral(S, E, FakeLiteral)) {
+  case SLCER_NotEvaluated:
     return SLCT_NotALiteral;
+
+  case SLCER_NotNullTerminated:
+    S.Diag(Args[format_idx]->getBeginLoc(),
+           diag::warn_printf_format_string_not_null_terminated)
+        << Args[format_idx]->getSourceRange();
+    if (!InFunctionCall)
+      S.Diag(E->getBeginLoc(), diag::note_format_string_defined);
+    // Stop checking, as this might just mean we're missing a chunk of the
+    // format string and there would be other spurious format issues.
+    return SLCT_UncheckedLiteral;
+
+  case SLCER_Evaluated:
+    InFunctionCall = false;
+    E = FakeLiteral;
+    goto tryAgain;
   }
 }
 
-// If this expression can be evaluated at compile-time,
-// check if the result is a StringLiteral and return it
-// otherwise return nullptr
-static const Expr *maybeConstEvalStringLiteral(ASTContext &Context,
-                                               const Expr *E) {
+static StringLiteralConstEvalResult
+constEvalStringAsLiteral(Sema &S, const Expr *E, const StringLiteral *&SL) {
+  // As a last resort, try to constant-evaluate the format string. If it
+  // evaluates to a string literal in the first place, we can point to that
+  // string literal in source and use that.
   Expr::EvalResult Result;
-  if (E->EvaluateAsRValue(Result, Context) && Result.Val.isLValue()) {
+  if (E->EvaluateAsRValue(Result, S.Context) && Result.Val.isLValue()) {
     const auto *LVE = Result.Val.getLValueBase().dyn_cast<const Expr *>();
-    if (isa_and_nonnull<StringLiteral>(LVE))
-      return LVE;
+    if (auto *BaseSL = dyn_cast_or_null<StringLiteral>(LVE)) {
+      SL = BaseSL;
+      return SLCER_Evaluated;
+    }
   }
-  return nullptr;
+
+  // Otherwise, try to evaluate the expression as a string constant.
+  std::string FormatString;
+  if (!E->tryEvaluateString(S.Context, FormatString)) {
+    return FormatString.empty() ? SLCER_NotEvaluated : SLCER_NotNullTerminated;
+  }
+
+  std::unique_ptr<llvm::MemoryBuffer> MemBuf;
+  {
+    llvm::SmallString<80> EscapedString;
+    {
+      llvm::raw_svector_ostream OS(EscapedString);
+      OS << '"';
+      OS.write_escaped(FormatString);
----------------
apple-fcloutier wrote:

No, I really do need the escaping, otherwise format strings containing quotes, newlines and probably other characters will print incorrectly. For instance, the format string `hello "%s"` will print as `"hello "%s""` in the scratch space when it needs to be `"hello \"%s\""`. Keep in mind that this is essentially synthesized source code, not text being piped into a diagnostic.

I don't know how to add a test for it because I don't know how to get clang -verify to surface the code in a `<scratch space>` file.

https://github.com/llvm/llvm-project/pull/135864