BUG: Do not accidentally store dtype metadata in np.save

seberg · charris · commit 451516de729c · 2024-08-08T18:40:10.000-06:00
We had logic in place to drop (most) metadata, but the change had a small bug: During saving, we were still using the one with metadata... Maybe doesn't quite close it, but big enough of an improvement for now, I think, so Closes gh-14142
diff --git a/numpy/lib/format.py b/numpy/lib/format.py
@@ -271,6 +271,8 @@ def dtype_to_descr(dtype):
         warnings.warn("metadata on a dtype is not saved to an npy/npz. "
                       "Use another format (such as pickle) to store it.",
                       UserWarning, stacklevel=2)
+    dtype = new_dtype
+
     if dtype.names is not None:
         # This is a record array. The .descr is fine.  XXX: parts of the
         # record array with an empty name, like padding bytes, still get
diff --git a/numpy/lib/tests/test_format.py b/numpy/lib/tests/test_format.py
@@ -998,32 +998,30 @@ def test_header_growth_axis():
 
             assert len(fp.getvalue()) == expected_header_length
 
-@pytest.mark.parametrize('dt, fail', [
-    (np.dtype({'names': ['a', 'b'], 'formats':  [float, np.dtype('S3',
-                 metadata={'some': 'stuff'})]}), True),
-    (np.dtype(int, metadata={'some': 'stuff'}), False),
-    (np.dtype([('subarray', (int, (2,)))], metadata={'some': 'stuff'}), False),
+@pytest.mark.parametrize('dt', [
+    np.dtype({'names': ['a', 'b'], 'formats':  [float, np.dtype('S3',
+                 metadata={'some': 'stuff'})]}),
+    np.dtype(int, metadata={'some': 'stuff'}),
+    np.dtype([('subarray', (int, (2,)))], metadata={'some': 'stuff'}),
     # recursive: metadata on the field of a dtype
-    (np.dtype({'names': ['a', 'b'], 'formats': [
+    np.dtype({'names': ['a', 'b'], 'formats': [
         float, np.dtype({'names': ['c'], 'formats': [np.dtype(int, metadata={})]})
-    ]}), False)
+    ]}),
     ])
 @pytest.mark.skipif(IS_PYPY and sys.implementation.version <= (7, 3, 8),
         reason="PyPy bug in error formatting")
-def test_metadata_dtype(dt, fail):
+def test_metadata_dtype(dt):
     # gh-14142
     arr = np.ones(10, dtype=dt)
     buf = BytesIO()
     with assert_warns(UserWarning):
         np.save(buf, arr)
     buf.seek(0)
-    if fail:
-        with assert_raises(ValueError):
-            np.load(buf)
-    else:
-        arr2 = np.load(buf)
-        # BUG: assert_array_equal does not check metadata
-        from numpy.lib._utils_impl import drop_metadata
-        assert_array_equal(arr, arr2)
-        assert drop_metadata(arr.dtype) is not arr.dtype
-        assert drop_metadata(arr2.dtype) is arr2.dtype
+
+    # Loading should work (metadata was stripped):
+    arr2 = np.load(buf)
+    # BUG: assert_array_equal does not check metadata
+    from numpy.lib._utils_impl import drop_metadata
+    assert_array_equal(arr, arr2)
+    assert drop_metadata(arr.dtype) is not arr.dtype
+    assert drop_metadata(arr2.dtype) is arr2.dtype
diff --git a/numpy/lib/tests/test_utils.py b/numpy/lib/tests/test_utils.py
@@ -43,7 +43,7 @@ def _compare_dtypes(dt1, dt2):
     assert dt_m.metadata is None
     assert dt_m['l1'].metadata is None
     assert dt_m['l1']['l2'].metadata is None
-    
+
     # alignment
     dt = np.dtype([('x', '<f8'), ('y', '<i4')],
                   align=True,
