Avoid duplicate storage of info in serialized columns.

astropy/table/serialize.py

@@ -134,7 +134,8 @@ def _represent_mixin_as_column(col, name, new_cols, mixin_cols,
         # MaskedColumn).  For primary data, we attempt to store any info on
         # the format, etc., on the column, but not for ancillary data (e.g.,
         # no sense to use a float format for a mask).
-        if data_attr == col.info._represent_as_dict_primary_data:
+        is_primary = data_attr == col.info._represent_as_dict_primary_data
+        if is_primary:
             new_name = name
             new_info = info
         else:
@@ -146,6 +147,10 @@ def _represent_mixin_as_column(col, name, new_cols, mixin_cols,
                                        and np.any(data.mask)) else Column
             new_cols.append(col_cls(data, name=new_name, **new_info))
             obj_attrs[data_attr] = SerializedColumn({'name': new_name})
+            if is_primary:
+                # Don't store info in the __serialized_columns__ dict for this column
+                # since this is redundant with info stored on the new column.
+                info = {}
         else:
             # recurse. This will define obj_attrs[new_name].
             _represent_mixin_as_column(data, new_name, new_cols, obj_attrs)

astropy/table/tests/test_mixin.py

@@ -817,6 +817,20 @@ def test_represent_mixins_as_columns_unit_fix():
     serialize.represent_mixins_as_columns(t)
 
 
+def test_primary_data_column_gets_description():
+    """
+    If the mixin defines a primary data column, that should get the
+    description, format, etc., so no __info__ should be needed.
+    """
+    t = QTable({'a': [1, 2] * u.m})
+    t['a'].info.description = 'parrot'
+    t['a'].info.format = '7.2f'
+    tser = serialize.represent_mixins_as_columns(t)
+    assert '__info__' not in tser.meta['__serialized_columns__']['a']
+    assert tser['a'].format == '7.2f'
+    assert tser['a'].description == 'parrot'
+
+
 def test_skycoord_with_velocity():
     # Regression test for gh-6447
     sc = SkyCoord([1], [2], unit='deg', galcen_v_sun=None)

astropy/utils/masked/core.py

@@ -352,9 +352,12 @@ def _represent_as_dict(self):
         return out
 
     def _construct_from_dict(self, map):
-        # 'data' may be a Column or a MaskedColumn.  In the former case,
-        # there will also be a 'mask'.
-        return Masked(map.pop('data').data, mask=map.pop('mask', None))
+        # Override usual handling, since MaskedNDArray takes shape and buffer
+        # as input, which is less useful here.
+        # The map can contain either a MaskedColumn or a Column and a mask.
+        # Extract the mask for the former case.
+        map.setdefault('mask', getattr(map['data'], 'mask', False))
+        return self._parent_cls.from_unmasked(**map)
 
 
 class MaskedArraySubclassInfo(MaskedInfoBase):

docs/changes/table/12607.bugfix.rst

@@ -0,0 +1,2 @@
+Avoid duplicate storage of info in serialized columns if the column
+used to serialize already can hold that information.