In order to maintain forward compatibility it is necessary to keep the
size of PyArray_ArrFuncs struct fixed. The usual trick of adding new
elements to the end of the structure is not available in this case
because the struct may be instanciated by user types and we have no way
to know whether the new or old struct is in play.

The solution adopted here is the reuse the (a)mergesort slots for stable
sorts of all kinds, with the actual kind set when the struct is
initialized. The '(a)mergesort' option thus becomes an alias for
'stable', but we keep it for backwards compatibility.

Some of the arguments were not being expanded in parens. Should be a pretty straightforward fix. This is not an exhaustive fix, but most of the other macros in this file look OK.

This implements cyclic support by adding `tp_traverse` to ufuns which may contain
a user provided object function (`np.frompyfunc`). Ufuncs that do not add this are not
added to the circular reference count tracking.

The ufunc does not need to implement `tp_clear` because it is an immutable object.

Fix PyArray_FillFunc function definitions

ENH: Allow ufunc.identity to be any python object

There is a problem with the way in which we handle
errors which occur in the call to `PyArray_FromFile`
in `np.fromfile`.

The problem here is twofold.

 1. The return value isn't checked, therefore if we reach
    the fail block, we will attempt a DECREF on a NULL and
    go down in flames.

 2. The cleanup code on the filepointers (most notabily the
    call to `npy_PyFile_DupClose2`) assumes that there is no
    error set to work.

This PR addresses these issues
 1. By adding a NULL check to the fail block to ensure we don't
    attempt a DECREF on a NULL.

 2. By saving the error state before attempting the cleanup code
    on the file descriptor, and then restoring it after.

Fixes: #12300