bpo-36290: Fix keytword collision handling in AST node constructors (GH-12382)

Lib/ast.py

@@ -524,6 +524,13 @@ class _ABC(type):
         return type.__instancecheck__(cls, inst)
 
 def _new(cls, *args, **kwargs):
+    for key in kwargs:
+        if key not in cls._fields:
+            # arbitrary keyword arguments are accepted
+            continue
+        pos = cls._fields.index(key)
+        if pos < len(args):
+            raise TypeError(f"{cls.__name__} got multiple values for argument {key!r}")
     if cls in _const_types:
         return Constant(*args, **kwargs)
     return Constant.__new__(cls, *args, **kwargs)

Lib/test/test_ast.py

@@ -402,6 +402,15 @@ class AST_Tests(unittest.TestCase):
         self.assertRaises(TypeError, ast.Num, 1, None, 2)
         self.assertRaises(TypeError, ast.Num, 1, None, 2, lineno=0)
 
+        # Arbitrary keyword arguments are supported
+        self.assertEqual(ast.Constant(1, foo='bar').foo, 'bar')
+        self.assertEqual(ast.Num(1, foo='bar').foo, 'bar')
+
+        with self.assertRaisesRegex(TypeError, "Num got multiple values for argument 'n'"):
+            ast.Num(1, n=2)
+        with self.assertRaisesRegex(TypeError, "Constant got multiple values for argument 'value'"):
+            ast.Constant(1, value=2)
+
         self.assertEqual(ast.Num(42).n, 42)
         self.assertEqual(ast.Num(4.25).n, 4.25)
         self.assertEqual(ast.Num(4.25j).n, 4.25j)

Misc/NEWS.d/next/Library/2019-03-17-19-01-53.bpo-36290.7VXo_K.rst

@@ -0,0 +1,2 @@
+AST nodes are now raising :exc:`TypeError` on conflicting keyword arguments.
+Patch contributed by Rémi Lapeyre.

Parser/asdl_c.py

@@ -695,8 +695,9 @@ ast_type_init(PyObject *self, PyObject *args, PyObject *kw)
     }
     if (fields) {
         numfields = PySequence_Size(fields);
-        if (numfields == -1)
+        if (numfields == -1) {
             goto cleanup;
+        }
     }
 
     res = 0; /* if no error occurs, this stays 0 to the end */
@@ -717,15 +718,35 @@ ast_type_init(PyObject *self, PyObject *args, PyObject *kw)
         }
         res = PyObject_SetAttr(self, name, PyTuple_GET_ITEM(args, i));
         Py_DECREF(name);
-        if (res < 0)
+        if (res < 0) {
             goto cleanup;
+        }
     }
     if (kw) {
         i = 0;  /* needed by PyDict_Next */
         while (PyDict_Next(kw, &i, &key, &value)) {
-            res = PyObject_SetAttr(self, key, value);
+            int contains = PySequence_Contains(fields, key);
-            if (res < 0)
+            if (contains == -1) {
+                res = -1;
                 goto cleanup;
+            } else if (contains == 1) {
+                Py_ssize_t p = PySequence_Index(fields, key);
+                if (p == -1) {
+                    res = -1;
+                    goto cleanup;
+                }
+                if (p < PyTuple_GET_SIZE(args)) {
+                    PyErr_Format(PyExc_TypeError,
+                        "%.400s got multiple values for argument '%U'",
+                        Py_TYPE(self)->tp_name, key);
+                    res = -1;
+                    goto cleanup;
+                }
+            }
+            res = PyObject_SetAttr(self, key, value);
+            if (res < 0) {
+                goto cleanup;
+            }
         }
     }
   cleanup:

Python/Python-ast.c

@@ -1131,8 +1131,9 @@ ast_type_init(PyObject *self, PyObject *args, PyObject *kw)
     }
     if (fields) {
         numfields = PySequence_Size(fields);
-        if (numfields == -1)
+        if (numfields == -1) {
             goto cleanup;
+        }
     }
 
     res = 0; /* if no error occurs, this stays 0 to the end */
@@ -1153,15 +1154,35 @@ ast_type_init(PyObject *self, PyObject *args, PyObject *kw)
         }
         res = PyObject_SetAttr(self, name, PyTuple_GET_ITEM(args, i));
         Py_DECREF(name);
-        if (res < 0)
+        if (res < 0) {
             goto cleanup;
+        }
     }
     if (kw) {
         i = 0;  /* needed by PyDict_Next */
         while (PyDict_Next(kw, &i, &key, &value)) {
-            res = PyObject_SetAttr(self, key, value);
+            int contains = PySequence_Contains(fields, key);
-            if (res < 0)
+            if (contains == -1) {
+                res = -1;
                 goto cleanup;
+            } else if (contains == 1) {
+                Py_ssize_t p = PySequence_Index(fields, key);
+                if (p == -1) {
+                    res = -1;
+                    goto cleanup;
+                }
+                if (p < PyTuple_GET_SIZE(args)) {
+                    PyErr_Format(PyExc_TypeError,
+                        "%.400s got multiple values for argument '%U'",
+                        Py_TYPE(self)->tp_name, key);
+                    res = -1;
+                    goto cleanup;
+                }
+            }
+            res = PyObject_SetAttr(self, key, value);
+            if (res < 0) {
+                goto cleanup;
+            }
         }
     }
   cleanup: