gh-108314: Add PyDict_ContainsString() function

vstinner · vstinner · commit b142bf9502bc · 2023-08-22T19:05:27.000+02:00
Use PyDict_ContainsString() in pylifecycle.c and pythonrun.c.
diff --git a/Doc/c-api/dict.rst b/Doc/c-api/dict.rst
@@ -55,6 +55,15 @@ Dictionary Objects
    This is equivalent to the Python expression ``key in p``.
 
 
+.. c:function:: int PyDict_ContainsString(PyObject *p, const char *key)
+
+   This is the same as :c:func:`PyDict_Contains`, but *key* is specified as a
+   :c:expr:`const char*` UTF-8 encoded bytes string, rather than a
+   :c:expr:`PyObject*`.
+
+   .. versionadded:: 3.13
+
+
 .. c:function:: PyObject* PyDict_Copy(PyObject *p)
 
    Return a new dictionary that contains the same key-value pairs as *p*.
@@ -73,7 +82,7 @@ Dictionary Objects
    .. index:: single: PyUnicode_FromString()
 
    Insert *val* into the dictionary *p* using *key* as a key. *key* should
-   be a :c:expr:`const char*`.  The key object is created using
+   be a :c:expr:`const char*` UTF-8 encoded bytes string.  The key object is created using
    ``PyUnicode_FromString(key)``.  Return ``0`` on success or ``-1`` on
    failure.  This function *does not* steal a reference to *val*.
 
@@ -88,7 +97,8 @@ Dictionary Objects
 
 .. c:function:: int PyDict_DelItemString(PyObject *p, const char *key)
 
-   Remove the entry in dictionary *p* which has a key specified by the string *key*.
+   Remove the entry in dictionary *p* which has a key specified by the UTF-8
+   encoded bytes string *key*.
    If *key* is not in the dictionary, :exc:`KeyError` is raised.
    Return ``0`` on success or ``-1`` on failure.
 
@@ -136,7 +146,8 @@ Dictionary Objects
 .. c:function:: PyObject* PyDict_GetItemString(PyObject *p, const char *key)
 
    This is the same as :c:func:`PyDict_GetItem`, but *key* is specified as a
-   :c:expr:`const char*`, rather than a :c:expr:`PyObject*`.
+   :c:expr:`const char*` UTF-8 encoded bytes string, rather than a
+   :c:expr:`PyObject*`.
 
    .. note::
 
@@ -150,7 +161,8 @@ Dictionary Objects
 .. c:function:: int PyDict_GetItemStringRef(PyObject *p, const char *key, PyObject **result)
 
    Similar than :c:func:`PyDict_GetItemRef`, but *key* is specified as a
-   :c:expr:`const char*`, rather than a :c:expr:`PyObject*`.
+   :c:expr:`const char*` UTF-8 encoded bytes string, rather than a
+   :c:expr:`PyObject*`.
 
    .. versionadded:: 3.13
 
diff --git a/Doc/data/stable_abi.dat b/Doc/data/stable_abi.dat
diff --git a/Doc/whatsnew/3.13.rst b/Doc/whatsnew/3.13.rst
@@ -862,6 +862,11 @@ New Features
   not needed.
   (Contributed by Victor Stinner in :gh:`106004`.)
 
+* Added :c:func:`PyDict_ContainsString` function: same as
+  :c:func:`PyDict_Contains`, but *key* is specified as a :c:expr:`const char*`
+  UTF-8 encoded bytes string, rather than a :c:expr:`PyObject*`.
+  (Contributed by Victor Stinner in :gh:`108314`.)
+
 * Add :c:func:`Py_IsFinalizing` function: check if the main Python interpreter is
   :term:`shutting down <interpreter shutdown>`.
   (Contributed by Victor Stinner in :gh:`108014`.)
diff --git a/Include/dictobject.h b/Include/dictobject.h
@@ -32,6 +32,7 @@ PyAPI_FUNC(PyObject *) PyDict_Items(PyObject *mp);
 PyAPI_FUNC(Py_ssize_t) PyDict_Size(PyObject *mp);
 PyAPI_FUNC(PyObject *) PyDict_Copy(PyObject *mp);
 PyAPI_FUNC(int) PyDict_Contains(PyObject *mp, PyObject *key);
+PyAPI_FUNC(int) PyDict_ContainsString(PyObject *mp, const char *key);
 
 /* PyDict_Update(mp, other) is equivalent to PyDict_Merge(mp, other, 1). */
 PyAPI_FUNC(int) PyDict_Update(PyObject *mp, PyObject *other);
diff --git a/Lib/test/test_capi/test_dict.py b/Lib/test/test_capi/test_dict.py
@@ -213,6 +213,20 @@ def test_dict_contains(self):
         # CRASHES contains(42, 'a')
         # CRASHES contains(NULL, 'a')
 
+    def test_dict_contains_string(self):
+        contains_string = _testcapi.dict_containsstring
+        dct = {'a': 1, '\U0001f40d': 2}
+        self.assertTrue(contains_string(dct, b'a'))
+        self.assertFalse(contains_string(dct, b'b'))
+        self.assertTrue(contains_string(dct, '\U0001f40d'.encode()))
+
+        dct2 = DictSubclass(dct)
+        self.assertTrue(contains_string(dct2, b'a'))
+        self.assertFalse(contains_string(dct2, b'b'))
+
+        # CRASHES contains({}, NULL)
+        # CRASHES contains(NULL, b'a')
+
     def test_dict_setitem(self):
         setitem = _testcapi.dict_setitem
         dct = {}
diff --git a/Lib/test/test_stable_abi_ctypes.py b/Lib/test/test_stable_abi_ctypes.py
diff --git a/Misc/NEWS.d/next/C API/2023-08-22-18-45-20.gh-issue-108314.nOlmwq.rst b/Misc/NEWS.d/next/C API/2023-08-22-18-45-20.gh-issue-108314.nOlmwq.rst
@@ -0,0 +1,4 @@
+Add :c:func:`PyDict_ContainsString` function: same as
+:c:func:`PyDict_Contains`, but *key* is specified as a :c:expr:`const char*`
+UTF-8 encoded bytes string, rather than a :c:expr:`PyObject*`.
+Patch by Victor Stinner.
diff --git a/Misc/stable_abi.toml b/Misc/stable_abi.toml
@@ -2450,3 +2450,5 @@
     added = '3.13'
 [function.PyDict_GetItemStringRef]
     added = '3.13'
+[function.PyDict_ContainsString]
+    added = '3.13'
diff --git a/Modules/_testcapi/dict.c b/Modules/_testcapi/dict.c
@@ -74,6 +74,19 @@ dict_contains(PyObject *self, PyObject *args)
     RETURN_INT(PyDict_Contains(obj, key));
 }
 
+static PyObject *
+dict_containsstring(PyObject *self, PyObject *args)
+{
+    PyObject *obj;
+    const char *key;
+    Py_ssize_t size;
+    if (!PyArg_ParseTuple(args, "Oz#", &obj, &key, &size)) {
+        return NULL;
+    }
+    NULLABLE(obj);
+    RETURN_INT(PyDict_ContainsString(obj, key));
+}
+
 static PyObject *
 dict_size(PyObject *self, PyObject *obj)
 {
@@ -349,6 +362,7 @@ static PyMethodDef test_methods[] = {
     {"dict_getitemref", dict_getitemref, METH_VARARGS},
     {"dict_getitemstringref", dict_getitemstringref, METH_VARARGS},
     {"dict_contains", dict_contains, METH_VARARGS},
+    {"dict_containsstring", dict_containsstring, METH_VARARGS},
     {"dict_setitem", dict_setitem, METH_VARARGS},
     {"dict_setitemstring", dict_setitemstring, METH_VARARGS},
     {"dict_delitem", dict_delitem, METH_VARARGS},
diff --git a/Objects/dictobject.c b/Objects/dictobject.c
@@ -3741,6 +3741,18 @@ PyDict_Contains(PyObject *op, PyObject *key)
     return (ix != DKIX_EMPTY && value != NULL);
 }
 
+int
+PyDict_ContainsString(PyObject *op, const char *key)
+{
+    PyObject *key_obj = PyUnicode_FromString(key);
+    if (key_obj == NULL) {
+        return -1;
+    }
+    int res = PyDict_Contains(op, key_obj);
+    Py_DECREF(key_obj);
+    return res;
+}
+
 /* Internal version of PyDict_Contains used when the hash value is already known */
 int
 _PyDict_Contains_KnownHash(PyObject *op, PyObject *key, Py_hash_t hash)
diff --git a/PC/python3dll.c b/PC/python3dll.c
diff --git a/Python/pylifecycle.c b/Python/pylifecycle.c
@@ -2208,10 +2208,11 @@ add_main_module(PyInterpreterState *interp)
     }
     Py_DECREF(ann_dict);
 
-    if (_PyDict_GetItemStringWithError(d, "__builtins__") == NULL) {
-        if (PyErr_Occurred()) {
-            return _PyStatus_ERR("Failed to test __main__.__builtins__");
-        }
+    int has_builtins = PyDict_ContainsString(d, "__builtins__");
+    if (has_builtins < 0) {
+        return _PyStatus_ERR("Failed to test __main__.__builtins__");
+    }
+    if (!has_builtins) {
         PyObject *bimod = PyImport_ImportModule("builtins");
         if (bimod == NULL) {
             return _PyStatus_ERR("Failed to retrieve builtins module");
diff --git a/Python/pythonrun.c b/Python/pythonrun.c
@@ -413,10 +413,11 @@ _PyRun_SimpleFileObject(FILE *fp, PyObject *filename, int closeit,
     PyObject *dict = PyModule_GetDict(main_module);  // borrowed ref
 
     int set_file_name = 0;
-    if (_PyDict_GetItemStringWithError(dict, "__file__") == NULL) {
-        if (PyErr_Occurred()) {
-            goto done;
-        }
+    int has_file = PyDict_ContainsString(dict, "__file__");
+    if (has_file < 0) {
+        goto done;
+    }
+    if (!has_file) {
         if (PyDict_SetItemString(dict, "__file__", filename) < 0) {
             goto done;
         }
@@ -1713,12 +1714,16 @@ run_eval_code_obj(PyThreadState *tstate, PyCodeObject *co, PyObject *globals, Py
     _PyRuntime.signals.unhandled_keyboard_interrupt = 0;
 
     /* Set globals['__builtins__'] if it doesn't exist */
-    if (globals != NULL && _PyDict_GetItemStringWithError(globals, "__builtins__") == NULL) {
-        if (PyErr_Occurred() ||
-            PyDict_SetItemString(globals, "__builtins__",
-                                 tstate->interp->builtins) < 0)
-        {
-            return NULL;
+    if (globals != NULL) {
+        int has_builtins = PyDict_ContainsString(globals, "__builtins__");
+        if (has_builtins < 0) {
+                return NULL;
+        }
+        if (!has_builtins) {
+            if (PyDict_SetItemString(globals, "__builtins__",
+                                     tstate->interp->builtins) < 0) {
+                return NULL;
+            }
         }
     }
 
