schemagen: escape control characters in generated C++ string literals

Fixes #35.

Add a helper to escape C++ string literals so that JSON control characters
(\n, \r, \t, and other bytes below 0x20) are emitted as escape sequences
instead of raw bytes. Use it for:

- field comments that include the JSON property key
- object key comparison literals in matchKey()
- enum name arrays

Also add regression tests that generate and syntax-check headers for
schemas containing newlines and other control characters in property keys
and enum values.

contrib/schemagen/test_schemagen.py

@@ -518,5 +518,100 @@ class SchemagenIntegerBoundaryTest(unittest.TestCase):
             self._compile_harness(tmpdir, {"type": "integer"}, harness)
 
 
+class SchemagenStringEscapeTest(unittest.TestCase):
+    """Regression tests for issue #35: control characters in string literals."""
+
+    def setUp(self):
+        self.repo_root = os.path.dirname(
+            os.path.dirname(os.path.dirname(os.path.abspath(__file__)))
+        )
+        self.include_dir = os.path.join(self.repo_root, "include")
+        self.compiler = shutil.which("c++")
+
+    def generate_and_compile(self, schema):
+        """Run schemagen on schema and syntax-check the resulting header."""
+        with tempfile.TemporaryDirectory() as tmpdir:
+            schema_path = os.path.join(tmpdir, "schema.json")
+            with open(schema_path, "w") as fp:
+                json.dump(schema, fp)
+            header_path = os.path.join(tmpdir, "gen.h")
+            cmd = [
+                sys.executable,
+                SCRIPT,
+                schema_path,
+                "-o",
+                header_path,
+                "--namespace",
+                "test_schema",
+            ]
+            result = subprocess.run(cmd, capture_output=True, text=True, check=False)
+            self.assertEqual(result.returncode, 0, msg=result.stderr)
+
+            if self.compiler:
+                cpp_path = os.path.join(tmpdir, "test.cpp")
+                with open(cpp_path, "w") as fp:
+                    fp.write(
+                        '#include "gen.h"\n'
+                        "int main() {\n"
+                        "  test_schema::RootBuilder b;\n"
+                        "  test_schema::Root r = b.take();\n"
+                        "  (void)r;\n"
+                        "}\n"
+                    )
+                comp = subprocess.run(
+                    [
+                        self.compiler,
+                        "-std=c++20",
+                        "-fsyntax-only",
+                        "-I",
+                        self.include_dir,
+                        "-I",
+                        tmpdir,
+                        cpp_path,
+                    ],
+                    capture_output=True,
+                    text=True,
+                    check=False,
+                )
+                self.assertEqual(comp.returncode, 0, msg=comp.stderr)
+
+            with open(header_path) as fp:
+                return fp.read()
+
+    def test_newline_in_property_key(self):
+        """A JSON key containing a newline must become a valid C++ literal."""
+        schema = {"type": "object", "properties": {"a\nb": {"type": "string"}}}
+        out = self.generate_and_compile(schema)
+        self.assertIn('// "a\\nb"', out)
+        self.assertIn('if (key == "a\\nb") return 0;', out)
+
+    def test_newline_in_enum_value(self):
+        """An enum value containing a newline must become a valid C++ literal."""
+        schema = {"type": "object", "properties": {"x": {"enum": ["a\nb"]}}}
+        out = self.generate_and_compile(schema)
+        self.assertIn('static constexpr const char *X_names[] = { "a\\nb" };', out)
+
+    def test_mixed_control_chars_in_enum_value(self):
+        """Mixed control characters in an enum value must be escaped."""
+        schema = {
+            "type": "object",
+            "properties": {
+                "x": {"enum": ["x\ny\rz\tw\vq\x00\x01"]},
+            },
+        }
+        out = self.generate_and_compile(schema)
+        self.assertIn(
+            'static constexpr const char *X_names[] = { "x\\ny\\rz\\tw\\vq\\u0000\\u0001" };',
+            out,
+        )
+
+    def test_backslash_and_quote_still_escaped(self):
+        """Existing escaping for backslash and double quote must remain correct."""
+        schema = {"type": "object", "properties": {'a"b\\c': {"type": "string"}}}
+        out = self.generate_and_compile(schema)
+        self.assertIn('// "a\\"b\\\\c"', out)
+        self.assertIn('if (key == "a\\"b\\\\c") return 0;', out)
+
+
 if __name__ == "__main__":
     unittest.main()