pythongh-124502: Add PyUnicode_Equal() function

Author: vstinner

Doc/c-api/unicode.rst

@@ -1423,6 +1423,24 @@ They all return ``NULL`` or ``-1`` if an exception occurs.
    This function returns ``-1`` upon failure, so one should call
    :c:func:`PyErr_Occurred` to check for errors.
 
+   See also :c:func:`PyUnicode_Equal`.
+
+
+.. c:function:: int PyUnicode_Equal(PyObject *a, PyObject *b)
+
+   Test if two strings are equal:
+
+   * Return ``1`` if *a* is equal to *b*.
+   * Return ``0`` if *a* is not equal to *b*.
+   * Set a :exc:`TypeError` exception and return ``-1`` if *a* or *b* is not a
+     Python :class:`str` object.
+
+   The function always succeed if *a* and *b* are Python :class:`str` objects.
+
+   See also :c:func:`PyUnicode_Compare`.
+
+   .. versionadded:: 3.14
+
 
 .. c:function:: int PyUnicode_EqualToUTF8AndSize(PyObject *unicode, const char *string, Py_ssize_t size)
 

Doc/data/stable_abi.dat

@@ -646,6 +646,9 @@ New Features
   <https://peps.python.org/pep-0630/#type-checking>`__ mentioned in :pep:`630`
   (:gh:`124153`).
 
+* Add :c:func:`PyUnicode_Equal` function to test if two strings are equal.
+  (Contributed by Victor Stinner in :gh:`124502`.)
+
 
 Porting to Python 3.14
 ----------------------

Doc/whatsnew/3.14.rst

@@ -966,6 +966,10 @@ PyAPI_FUNC(int) PyUnicode_EqualToUTF8(PyObject *, const char *);
 PyAPI_FUNC(int) PyUnicode_EqualToUTF8AndSize(PyObject *, const char *, Py_ssize_t);
 #endif
 
+#if !defined(Py_LIMITED_API) || Py_LIMITED_API+0 >= 0x030e0000
+PyAPI_FUNC(int) PyUnicode_Equal(PyObject *str1, PyObject *str2);
+#endif
+
 /* Rich compare two strings and return one of the following:
 
    - NULL in case an exception was raised

Include/unicodeobject.h

@@ -1903,6 +1903,33 @@ def test_recover_error(self):
 
         self.assertEqual(writer.finish(), 'Hello World.')
 
+    def test_unicode_equal(self):
+        unicode_equal = _testlimitedcapi.unicode_equal
+
+        def copy(text):
+            return text.encode().decode()
+
+        self.assertTrue(unicode_equal("", ""))
+        self.assertTrue(unicode_equal("abc", "abc"))
+        self.assertTrue(unicode_equal("abc", copy("abc")))
+        self.assertTrue(unicode_equal("\u20ac", copy("\u20ac")))
+        self.assertTrue(unicode_equal("\U0010ffff", copy("\U0010ffff")))
+
+        self.assertFalse(unicode_equal("abc", "abcd"))
+        self.assertFalse(unicode_equal("\u20ac", "\u20ad"))
+        self.assertFalse(unicode_equal("\U0010ffff", "\U0010fffe"))
+
+        # invalid type
+        for invalid_type in (b'bytes', 123, ("tuple",)):
+            with self.subTest(invalid_type=invalid_type):
+                with self.assertRaises(TypeError):
+                    unicode_equal("abc", invalid_type)
+                with self.assertRaises(TypeError):
+                    unicode_equal(invalid_type, "abc")
+
+        # CRASHES unicode_equal("abc", NULL)
+        # CRASHES unicode_equal(NULL, "abc")
+
 
 if __name__ == "__main__":
     unittest.main()

Lib/test/test_capi/test_unicode.py

@@ -0,0 +1,2 @@
+Add :c:func:`PyUnicode_Equal` function to test if two strings are equal.
+Patch by Victor Stinner.

Lib/test/test_stable_abi_ctypes.py

@@ -2536,3 +2536,5 @@
     added = '3.14'
 [const.Py_TP_USE_SPEC]
     added = '3.14'
+[function.PyUnicode_Equal]
+    added = '3.14'

Misc/NEWS.d/next/C_API/2024-09-25-11-44-02.gh-issue-124502.qWuDjT.rst

@@ -1837,6 +1837,23 @@ test_string_from_format(PyObject *self, PyObject *Py_UNUSED(ignored))
 #undef CHECK_FORMAT_0
 }
 
+
+/* Test PyUnicode_Equal() */
+static PyObject *
+unicode_equal(PyObject *module, PyObject *args)
+{
+    PyObject *str1, *str2;
+    if (!PyArg_ParseTuple(args, "OO", &str1, &str2)) {
+        return NULL;
+    }
+
+    NULLABLE(str1);
+    NULLABLE(str2);
+    RETURN_INT(PyUnicode_Equal(str1, str2));
+}
+
+
+
 static PyMethodDef TestMethods[] = {
     {"codec_incrementalencoder", codec_incrementalencoder,       METH_VARARGS},
     {"codec_incrementaldecoder", codec_incrementaldecoder,       METH_VARARGS},
@@ -1924,6 +1941,7 @@ static PyMethodDef TestMethods[] = {
     {"unicode_format",           unicode_format,                 METH_VARARGS},
     {"unicode_contains",         unicode_contains,               METH_VARARGS},
     {"unicode_isidentifier",     unicode_isidentifier,           METH_O},
+    {"unicode_equal",            unicode_equal,                  METH_VARARGS},
     {NULL},
 };
 

Misc/stable_abi.toml

@@ -11009,6 +11009,23 @@ _PyUnicode_Equal(PyObject *str1, PyObject *str2)
 }
 
 
+int
+PyUnicode_Equal(PyObject *str1, PyObject *str2)
+{
+    if (!PyUnicode_Check(str1)) {
+        PyErr_Format(PyExc_TypeError,
+                     "first argument must be str, not %T", str1);
+        return -1;
+    }
+    if (!PyUnicode_Check(str2)) {
+        PyErr_Format(PyExc_TypeError,
+                     "second argument must be str, not %T", str2);
+        return -1;
+    }
+    return _PyUnicode_Equal(str1, str2);
+}
+
+
 int
 PyUnicode_Compare(PyObject *left, PyObject *right)
 {