Fix #756 (##: pasting a name or number with a string or character literal is an error)

Co-Authored-By: Claude Sonnet 5.5 <noreply@anthropic.com>

Author: dmcppcheck

simplecpp.cpp

@@ -2831,12 +2831,12 @@ namespace simplecpp {
                         strAB = ",";
                     }
                     else {
-                        checkPunctuatorPaste(tok->location, name(), A, tokensB.cfront());
+                        checkPaste(tok->location, name(), A, tokensB.cfront());
                         strAB = A->str() + tokensB.cfront()->str();
                         tokensB.deleteToken(tokensB.front());
                     }
                 } else {
-                    checkPunctuatorPaste(tok->location, name(), A, B);
+                    checkPaste(tok->location, name(), A, B);
                     strAB = A->str() + B->str();
                 }
 
@@ -2907,16 +2907,21 @@ namespace simplecpp {
         }
 
         /**
-         * When A is a punctuator, check that pasting A and B gives a valid token.
+         * Check that pasting A and B gives a valid token, when A is a punctuator
+         * or B is a string or character literal.
          * @param loc       the location of the ##
          * @param macroName the macro that is expanded
          * @param A         the token before ##
          * @param B         the first token after ##, after expansion
          * @throws invalidHashHash if the result is not a valid token
          */
-        static void checkPunctuatorPaste(const Location &loc, const std::string &macroName, const Token *A, const Token *B) {
+        static void checkPaste(const Location &loc, const std::string &macroName, const Token *A, const Token *B) {
             if (isPunctuatorOperand(A) && !isValidPunctuatorPaste(A->str() + B->str()))
                 throw invalidHashHash::cannotCombine(loc, macroName, A, B);
+            // a name or number followed by a literal: only an encoding prefix such as L or u8 is valid
+            if ((A->name || A->number) && (isStringLiteral(B->str()) || isCharLiteral(B->str())) &&
+                !(A->name && isStringLiteralPrefix(A->str())))
+                throw invalidHashHash::cannotCombine(loc, macroName, A, B);
         }
 
         /**

test.cpp

@@ -2554,9 +2554,29 @@ static void hashhash_invalid_name_string()
         "#define cat(a,b) a##b\n"
         "cat(a,\"s\")\n";
     simplecpp::OutputList outputList;
-    // TODO: a"s" is not a valid token, gcc reports an error
-    TODO_ASSERT_EQUALS("", "\na\"s\"", preprocess(code, &outputList));
-    TODO_ASSERT_EQUALS("file0,1,syntax_error,failed to expand 'cat', Invalid ## usage when expanding 'cat': Combining 'a' and '\"s\"' yields an invalid token.\n", "", toString(outputList));
+    ASSERT_EQUALS("", preprocess(code, &outputList));
+    ASSERT_EQUALS("file0,1,syntax_error,failed to expand 'cat', Invalid ## usage when expanding 'cat': Combining 'a' and '\"s\"' yields an invalid token.\n", toString(outputList));
+}
+
+static void hashhash_invalid_number_string()
+{
+    const char code[] =
+        "#define cat(a,b) a##b\n"
+        "cat(1,\"s\")\n";
+    simplecpp::OutputList outputList;
+    ASSERT_EQUALS("", preprocess(code, &outputList));
+    ASSERT_EQUALS("file0,1,syntax_error,failed to expand 'cat', Invalid ## usage when expanding 'cat': Combining '1' and '\"s\"' yields an invalid token.\n", toString(outputList));
+}
+
+static void hashhash_encoding_prefix()
+{
+    const char code[] =
+        "#define cat(a,b) a##b\n"
+        "#define WIDE(s) L ## s\n"
+        "cat(L,\"s\") cat(u8,\"s\") cat(R,\"(x)\") cat(L,'c') WIDE(\"s\")\n";
+    simplecpp::OutputList outputList;
+    ASSERT_EQUALS("\n\nL\"s\" u8\"s\" R\"(x)\" L'c' L\"s\"", preprocess(code, &outputList));
+    ASSERT_EQUALS("", toString(outputList));
 }
 
 static void hashhash_va_args_unexpected()
@@ -5689,6 +5709,8 @@ static void runTests(int argc, char **argv, Input input)
     TEST_CASE(hashhash_empty_placemarker);
     TEST_CASE(hashhash_invalid_dotdot);
     TEST_CASE(hashhash_invalid_name_string);
+    TEST_CASE(hashhash_invalid_number_string);
+    TEST_CASE(hashhash_encoding_prefix);
     TEST_CASE(hashhash_va_args_unexpected);
 
     // C standard, 5.1.1.2, paragraph 4: