gh-117709: Add vectorcall support for str() with positional-only arguments (#117746)

Fall back to tp_call() for cases when arguments are passed by name.

Co-authored-by: Donghee Na <[email protected]>
Co-authored-by: Victor Stinner <[email protected]>

Author: 3 people

Lib/test/test_str.py

@@ -2651,6 +2651,24 @@ def test_check_encoding_errors(self):
         proc = assert_python_failure('-X', 'dev', '-c', code)
         self.assertEqual(proc.rc, 10, proc)
 
+    def test_str_invalid_call(self):
+        check = lambda *a, **kw: self.assertRaises(TypeError, str, *a, **kw)
+
+        # too many args
+        check(1, "", "", 1)
+
+        # no such kw arg
+        check(test=1)
+
+        # 'encoding' must be str
+        check(1, encoding=1)
+        check(1, 1)
+
+        # 'errors' must be str
+        check(1, errors=1)
+        check(1, "", errors=1)
+        check(1, 1, 1)
+
 
 class StringModuleTest(unittest.TestCase):
     def test_formatter_parser(self):

Misc/NEWS.d/next/Core and Builtins/2024-04-10-22-16-18.gh-issue-117709.-_1YL0.rst

@@ -0,0 +1,3 @@
+Speed up calls to :func:`str` with positional-only argument,
+by using the :pep:`590` ``vectorcall`` calling convention.
+Patch by Erlend Aasland.

Objects/unicodeobject.c

@@ -14617,6 +14617,56 @@ unicode_new_impl(PyTypeObject *type, PyObject *x, const char *encoding,
     return unicode;
 }
 
+static const char *
+arg_as_utf8(PyObject *obj, const char *name)
+{
+    if (!PyUnicode_Check(obj)) {
+        PyErr_Format(PyExc_TypeError,
+                     "str() argument '%s' must be str, not %T",
+                     name, obj);
+        return NULL;
+    }
+    return _PyUnicode_AsUTF8NoNUL(obj);
+}
+
+static PyObject *
+unicode_vectorcall(PyObject *type, PyObject *const *args,
+                   size_t nargsf, PyObject *kwnames)
+{
+    assert(Py_Is(_PyType_CAST(type), &PyUnicode_Type));
+
+    Py_ssize_t nargs = PyVectorcall_NARGS(nargsf);
+    if (kwnames != NULL && PyTuple_GET_SIZE(kwnames) != 0) {
+        // Fallback to unicode_new()
+        PyObject *tuple = _PyTuple_FromArray(args, nargs);
+        if (tuple == NULL) {
+            return NULL;
+        }
+        PyObject *dict = _PyStack_AsDict(args + nargs, kwnames);
+        if (dict == NULL) {
+            Py_DECREF(tuple);
+            return NULL;
+        }
+        PyObject *ret = unicode_new(_PyType_CAST(type), tuple, dict);
+        Py_DECREF(tuple);
+        Py_DECREF(dict);
+        return ret;
+    }
+    if (!_PyArg_CheckPositional("str", nargs, 0, 3)) {
+        return NULL;
+    }
+    if (nargs == 0) {
+        return unicode_get_empty();
+    }
+    PyObject *object = args[0];
+    if (nargs == 1) {
+        return PyObject_Str(object);
+    }
+    const char *encoding = arg_as_utf8(args[1], "encoding");
+    const char *errors = (nargs == 3) ? arg_as_utf8(args[2], "errors") : NULL;
+    return PyUnicode_FromEncodedObject(object, encoding, errors);
+}
+
 static PyObject *
 unicode_subtype_new(PyTypeObject *type, PyObject *unicode)
 {
@@ -14758,6 +14808,7 @@ PyTypeObject PyUnicode_Type = {
     0,                            /* tp_alloc */
     unicode_new,                  /* tp_new */
     PyObject_Del,                 /* tp_free */
+    .tp_vectorcall = unicode_vectorcall,
 };
 
 /* Initialize the Unicode implementation */