FIX: Make object comparison ufuncs not include identity check

The issue here is that PyObject_RichCompareBool does an identity
check before doing any other checks. This is good, and is the
way for example list comparisons are handled. However in numpy
comparisons are elementwise, so that the identitycheck should
not be expected. The example for this is as follows:
obj_array = np.arange(3)
a = np.array([obj_array, 0], dtype=object)
np.equal(a, a)
If an identity check is done, this returns [True, True]. But
obj_array == obj_array itself cannot be cast to a bool.

While this is slightly slower, not doing the identity check seems
more logical in the light of elementwise operations.

Closes gh-2117.

1 files changed, 10 insertions, 1 deletions

diff --git a/numpy/core/src/umath/loops.c.src b/numpy/core/src/umath/loops.c.src
index ee7e7652d..c1e2dc1c5 100644
--- a/numpy/core/src/umath/loops.c.src
+++ b/numpy/core/src/umath/loops.c.src
@@ -2568,9 +2568,18 @@ OBJECT_@kind@(char **args, npy_intp *dimensions, npy_intp *steps, void *NPY_UNUS
     BINARY_LOOP {
         PyObject *in1 = *(PyObject **)ip1;
         PyObject *in2 = *(PyObject **)ip2;
-        int ret = PyObject_RichCompareBool(
+        /*
+         * Do not use RichCompareBool because it includes an identity check.
+         * But this is wrong for elementwise behaviour, since i.e. it says
+         * that NaN can be equal to NaN, and an array is equal to itself.
+         */
+        PyObject *ret_obj = PyObject_RichCompare(
                             in1 ? in1 : Py_None,
                             in2 ? in2 : Py_None, Py_@OP@);
+        if (ret_obj == NULL) {
+            return;
+        }
+        int ret = PyObject_IsTrue(ret_obj);
         if (ret == -1) {
             return;
         }