[clang] [analyzer] Check the correct first and last elements in cstring.UninitializedRead (PR #95408)

[Donát Nagy via cfe-commits]

================
@@ -393,6 +401,162 @@ ProgramStateRef CStringChecker::checkNonNull(CheckerContext &C,
   return stateNonNull;
 }
 
+static std::optional<NonLoc> getIndex(ProgramStateRef State,
+                                      const ElementRegion *ER, CharKind CK) {
+  SValBuilder &SVB = State->getStateManager().getSValBuilder();
+  ASTContext &Ctx = SVB.getContext();
+
+  if (CK == CharKind::Regular) {
+    if (ER->getValueType() != Ctx.CharTy)
+      return {};
+    return ER->getIndex();
+  }
+
+  if (ER->getValueType() != Ctx.WideCharTy)
+    return {};
+
+  QualType SizeTy = Ctx.getSizeType();
+  NonLoc WideSize =
+      SVB.makeIntVal(Ctx.getTypeSizeInChars(Ctx.WideCharTy).getQuantity(),
+                     SizeTy)
+          .castAs<NonLoc>();
+  SVal Offset =
+      SVB.evalBinOpNN(State, BO_Mul, ER->getIndex(), WideSize, SizeTy);
+  if (Offset.isUnknown())
+    return {};
+  return Offset.castAs<NonLoc>();
+}
+
+// Try to get hold of the origin region (e.g. the actual array region from an
+// element region).
+static const TypedValueRegion *getOriginRegion(const ElementRegion *ER) {
+  const MemRegion *MR = ER->getSuperRegion();
+  const MemRegion *Ret = MR;
+  assert(MR);
+  if (const auto *sym = MR->getAs<SymbolicRegion>()) {
+    SymbolRef sym2 = sym->getSymbol();
+    if (!sym2)
+      return nullptr;
+    Ret = sym2->getOriginRegion();
+  }
+  return dyn_cast_or_null<TypedValueRegion>(Ret);
+}
+
+// Basically 1 -> 1st, 12 -> 12th, etc.
+static void printIdxWithOrdinalSuffix(llvm::raw_ostream &Os, unsigned Idx) {
+  Os << Idx << llvm::getOrdinalSuffix(Idx);
----------------
NagyDonat wrote:

```suggestion
  switch (Idx) {
    case 1:
      Os << "first";
      break;
    case 2:
      Os << "second";
      break;
    case 3:
      Os << "third";
      break;
    default:
      Os << Idx << llvm::getOrdinalSuffix(Idx);
  }
```
Consider printing "first", "second" and "third" instead of "1st", "2nd" and "3rd" because IMO it makes the diagnostics easier to read -- and this function will be used for argument indices in builtin functions, so these cases will be very common.

https://github.com/llvm/llvm-project/pull/95408