Ensure that DatetimeArray keeps reference to original data (#23956)

Author: TomAugspurger

pandas/_libs/tslibs/conversion.pyx

@@ -99,10 +99,13 @@ def ensure_datetime64ns(arr: ndarray, copy: bool=True):
 
     ivalues = arr.view(np.int64).ravel()
 
-    result = np.empty(shape, dtype='M8[ns]')
+    result = np.empty(shape, dtype=NS_DTYPE)
     iresult = result.ravel().view(np.int64)
 
     if len(iresult) == 0:
+        result = arr.view(NS_DTYPE)
+        if copy:
+            result = result.copy()
         return result
 
     unit = get_datetime64_unit(arr.flat[0])

pandas/tests/arrays/test_datetimelike.py

@@ -167,6 +167,15 @@ def test_array_i8_dtype(self, tz_naive_fixture):
         assert result.base is expected.base
         assert result.base is not None
 
+    def test_from_array_keeps_base(self):
+        # Ensure that DatetimeArray._data.base isn't lost.
+        arr = np.array(['2000-01-01', '2000-01-02'], dtype='M8[ns]')
+        dta = DatetimeArray(arr)
+
+        assert dta._data is arr
+        dta = DatetimeArray(arr[:0])
+        assert dta._data.base is arr
+
     def test_from_dti(self, tz_naive_fixture):
         tz = tz_naive_fixture
         dti = pd.date_range('2016-01-01', periods=3, tz=tz)

pandas/tests/tslibs/test_conversion.py

@@ -57,3 +57,15 @@ def test_tz_convert_corner(self, arr):
                                        timezones.maybe_get_tz('US/Eastern'),
                                        timezones.maybe_get_tz('Asia/Tokyo'))
         tm.assert_numpy_array_equal(result, arr)
+
+
+class TestEnsureDatetime64NS(object):
+    @pytest.mark.parametrize('copy', [True, False])
+    @pytest.mark.parametrize('dtype', ['M8[ns]', 'M8[s]'])
+    def test_length_zero_copy(self, dtype, copy):
+        arr = np.array([], dtype=dtype)
+        result = conversion.ensure_datetime64ns(arr, copy=copy)
+        if copy:
+            assert result.base is None
+        else:
+            assert result.base is arr