ENH: PyArray_FromInterface checks descr if typestr is np.void

When the 'typestr' member of the __array_interface__ dictionary defines
a np.void dtype, check the 'descr' member, and if it is a valid dtype
description and it is not the default one, use it to construct the
dtype for the array to return.

This fixes #5081, as as_strided no longer has to worry about changing
the dtype of the return.

3 files changed, 88 insertions, 7 deletions

diff --git a/numpy/core/src/multiarray/ctors.c b/numpy/core/src/multiarray/ctors.c
index 010420826..e88e17028 100644
--- a/numpy/core/src/multiarray/ctors.c
+++ b/numpy/core/src/multiarray/ctors.c
@@ -2069,6 +2069,51 @@ PyArray_FromStructInterface(PyObject *input)
     return NULL;
 }
 
+/*
+ * Checks if the object in descr is the default 'descr' member for the
+ * __array_interface__ dictionary with 'typestr' member typestr.
+ */
+NPY_NO_EXPORT int
+_is_default_descr(PyObject *descr, PyObject *typestr) {
+    PyObject *tuple, *name, *typestr2;
+#if defined(NPY_PY3K)
+    PyObject *tmp = NULL;
+#endif
+    int ret = 0;
+
+    if (!PyList_Check(descr) || PyList_GET_SIZE(descr) != 1) {
+        return 0;
+    }
+    tuple = PyList_GET_ITEM(descr, 0);
+    if (!(PyTuple_Check(tuple) && PyTuple_GET_SIZE(tuple) == 2)) {
+        return 0;
+    }
+    name = PyTuple_GET_ITEM(tuple, 0);
+    if (!(PyUString_Check(name) && PyUString_GET_SIZE(name) == 0)) {
+        return 0;
+    }
+    typestr2 = PyTuple_GET_ITEM(tuple, 1);
+#if defined(NPY_PY3K)
+    /* Allow unicode type strings */
+    if (PyUnicode_Check(typestr2)) {
+        tmp = PyUnicode_AsASCIIString(typestr2);
+        if (tmp == NULL) {
+            return 0;
+        }
+        typestr2 = tmp;
+    }
+#endif
+    if (PyBytes_Check(typestr2) &&
+            PyObject_RichCompareBool(typestr, typestr2, Py_EQ)) {
+        ret = 1;
+    }
+#if defined(NPY_PY3K)
+    Py_XDECREF(tmp);
+#endif
+
+    return ret;
+}
+
 #define PyIntOrLong_Check(obj) (PyInt_Check(obj) || PyLong_Check(obj))
 
 /*NUMPY_API*/
@@ -2087,11 +2132,6 @@ PyArray_FromInterface(PyObject *origin)
     npy_intp dims[NPY_MAXDIMS], strides[NPY_MAXDIMS];
     int dataflags = NPY_ARRAY_BEHAVED;
 
-    /* Get the typestring -- ignore array_descr */
-    /* Get the shape */
-    /* Get the memory from __array_data__ and __array_offset__ */
-    /* Get the strides */
-
     iface = PyArray_GetAttrString_SuppressException(origin,
                                                     "__array_interface__");
     if (iface == NULL) {
@@ -2135,6 +2175,22 @@ PyArray_FromInterface(PyObject *origin)
         goto fail;
     }
 
+    /*
+     * If the dtype is NPY_VOID, see if there is extra information in
+     * the 'descr' attribute.
+     */
+    if (dtype->type_num == NPY_VOID) {
+        PyObject *descr = PyDict_GetItemString(iface, "descr");
+        PyArray_Descr *new_dtype = NULL;
+
+        if (descr != NULL && !_is_default_descr(descr, attr) &&
+                PyArray_DescrConverter2(descr, &new_dtype) == NPY_SUCCEED &&
+                new_dtype != NULL) {
+            Py_DECREF(dtype);
+            dtype = new_dtype;
+        }
+    }
+
     /* Get shape tuple from interface specification */
     attr = PyDict_GetItemString(iface, "shape");
     if (attr == NULL) {
diff --git a/numpy/lib/stride_tricks.py b/numpy/lib/stride_tricks.py
index 0f46ed335..e9ba97413 100644
--- a/numpy/lib/stride_tricks.py
+++ b/numpy/lib/stride_tricks.py
@@ -46,9 +46,11 @@ def as_strided(x, shape=None, strides=None, subok=False):
     if strides is not None:
         interface['strides'] = tuple(strides)
     array = np.asarray(DummyArray(interface, base=x))
-    # Make sure dtype is correct in case of custom dtype
-    if array.dtype.kind == 'V':
+
+    if array.dtype.fields is None and x.dtype.fields is not None:
+        # This should only happen if x.dtype is [('', 'Vx')]
         array.dtype = x.dtype
+
     return _maybe_view_as_subclass(x, array)
 
 
diff --git a/numpy/lib/tests/test_stride_tricks.py b/numpy/lib/tests/test_stride_tricks.py
index 0b73109bc..9744401fb 100644
--- a/numpy/lib/tests/test_stride_tricks.py
+++ b/numpy/lib/tests/test_stride_tricks.py
@@ -290,6 +290,29 @@ def test_as_strided():
     expected = np.array([[1, 2, 3, 4], [1, 2, 3, 4], [1, 2, 3, 4]])
     assert_array_equal(a_view, expected)
 
+    # Regression test for gh-5081
+    dt = np.dtype([('num', 'i4'), ('obj', 'O')])
+    a = np.empty((4,), dtype=dt)
+    a['num'] = np.arange(1, 5)
+    a_view = as_strided(a, shape=(3, 4), strides=(0, a.itemsize))
+    expected_num = [[1, 2, 3, 4]] * 3
+    expected_obj = [[None]*4]*3
+    assert_equal(a_view.dtype, dt)
+    assert_array_equal(expected_num, a_view['num'])
+    assert_array_equal(expected_obj, a_view['obj'])
+
+    # Make sure that void types without fields are kept unchanged
+    a = np.empty((4,), dtype='V4')
+    a_view = as_strided(a, shape=(3, 4), strides=(0, a.itemsize))
+    assert_equal(a.dtype, a_view.dtype)
+
+    # Make sure that the only type that could fail is properly handled
+    dt = np.dtype({'names': [''], 'formats': ['V4']})
+    a = np.empty((4,), dtype=dt)
+    a_view = as_strided(a, shape=(3, 4), strides=(0, a.itemsize))
+    assert_equal(a.dtype, a_view.dtype)
+
+
 
 class VerySimpleSubClass(np.ndarray):
     def __new__(cls, *args, **kwargs):