Add set_data_io to Data

CHANGELOG.md

@@ -1,6 +1,9 @@
 # HDMF Changelog
 
-## HDMF 3.11.1 (Upcoming)
+## HDMF 3.12.0 (Upcoming)
+
+### Enhancements
+- Add Data.set_data_io allows(), which allows for setting a DataIO to a data object after-the-fact. @bendichter and @CodyCBakerPhD [#1013](https://github.com/hdmf-dev/hdmf/pull/1013)
 
 ### Minor Improvements
 - Updated `__gather_columns` to ignore the order of bases when generating columns from the super class. @mavaylon1 [#991](https://github.com/hdmf-dev/hdmf/pull/991)

src/hdmf/container.py

@@ -747,22 +747,34 @@ def __smart_str_dict(d, num_indent):
         out += '\n' + indent + right_br
         return out
 
-    def set_data_io(self, dataset_name: str, data_io_class: Type[DataIO], **kwargs) -> None:
+    def set_data_io(self, dataset_name: str, data_io_class: Type[DataIO], data_io_kwargs: dict = None, **kwargs):
         """
+        Apply DataIO object to a dataset field of the Container.
 
         Parameters
         ----------
         dataset_name: str
             Name of dataset to wrap in DataIO
         data_io_class: Type[DataIO]
             Class to use for DataIO, e.g. H5DataIO or ZarrDataIO
+        data_io_kwargs: dict
+            keyword arguments passed to the constructor of the DataIO class.
         **kwargs:
-            kwargs are passed to the constructor of the DataIO class
+            DEPRECATED. Use data_io_kwargs instead.
+            kwargs are passed to the constructor of the DataIO class.
         """
+        if kwargs or (data_io_kwargs is None):
+            warn(
+                "Use of **kwargs in Container.set_data_io() is deprecated. Please pass the DataIO kwargs as a "
+                "dictionary to the `data_io_kwargs` parameter instead.",
+                DeprecationWarning,
+                stacklevel=2
+            )
+            data_io_kwargs = kwargs
         data = self.fields.get(dataset_name)
         if data is None:
             raise ValueError(f"{dataset_name} is None and cannot be wrapped in a DataIO class")
-        self.fields[dataset_name] = data_io_class(data=data, **kwargs)
+        self.fields[dataset_name] = data_io_class(data=data, **data_io_kwargs)
 
 
 class Data(AbstractContainer):
@@ -797,10 +809,28 @@ def set_dataio(self, **kwargs):
         """
         Apply DataIO object to the data held by this Data object
         """
+        warn(
+            "Data.set_dataio() is deprecated. Please use Data.set_data_io() instead.",
+            DeprecationWarning,
+            stacklevel=2,
+        )
         dataio = getargs('dataio', kwargs)
         dataio.data = self.__data
         self.__data = dataio
 
+    def set_data_io(self, data_io_class: Type[DataIO], data_io_kwargs: dict) -> None:
+        """
+        Apply DataIO object to the data held by this Data object.
+
+        Parameters
+        ----------
+        data_io_class: Type[DataIO]
+            The DataIO to apply to the data held by this Data.
+        data_io_kwargs: dict
+            The keyword arguments to pass to the DataIO.
+        """
+        self.__data = data_io_class(data=self.__data, **data_io_kwargs)
+
     @docval({'name': 'func', 'type': types.FunctionType, 'doc': 'a function to transform *data*'})
     def transform(self, **kwargs):
         """

tests/unit/test_container.py

@@ -2,7 +2,6 @@
 from uuid import uuid4, UUID
 import os
 
-from hdmf.backends.hdf5 import H5DataIO
 from hdmf.container import AbstractContainer, Container, Data, HERDManager
 from hdmf.common.resources import HERD
 from hdmf.testing import TestCase
@@ -397,28 +396,6 @@ def test_get_ancestors(self):
         self.assertTupleEqual(parent_obj.get_ancestors(), (grandparent_obj, ))
         self.assertTupleEqual(child_obj.get_ancestors(), (parent_obj, grandparent_obj))
 
-    def test_set_data_io(self):
-
-        class ContainerWithData(Container):
-            __fields__ = ('data1', 'data2')
-
-            @docval(
-                {"name": "name", "doc": "name", "type": str},
-                {'name': 'data1', 'doc': 'field1 doc', 'type': list},
-                {'name': 'data2', 'doc': 'field2 doc', 'type':  list, 'default': None}
-            )
-            def __init__(self, **kwargs):
-                super().__init__(name=kwargs["name"])
-                self.data1 = kwargs["data1"]
-                self.data2 = kwargs["data2"]
-
-        obj = ContainerWithData("name", [1, 2, 3, 4, 5], None)
-        obj.set_data_io("data1", H5DataIO, chunks=True)
-        assert isinstance(obj.data1, H5DataIO)
-
-        with self.assertRaises(ValueError):
-            obj.set_data_io("data2", H5DataIO, chunks=True)
-
 
 class TestHTMLRepr(TestCase):
 

tests/unit/test_io_hdf5_h5tools.py

@@ -20,7 +20,7 @@
 from hdmf.backends.errors import UnsupportedOperation
 from hdmf.build import GroupBuilder, DatasetBuilder, BuildManager, TypeMap, OrphanContainerBuildError, LinkBuilder
 from hdmf.container import Container
-from hdmf import Data
+from hdmf import Data, docval
 from hdmf.data_utils import DataChunkIterator, GenericDataChunkIterator, InvalidDataIOError
 from hdmf.spec.catalog import SpecCatalog
 from hdmf.spec.namespace import NamespaceCatalog, SpecNamespace
@@ -3671,3 +3671,57 @@ def test_hdf5io_can_read():
     assert not HDF5IO.can_read("not_a_file")
     assert HDF5IO.can_read("tests/unit/back_compat_tests/1.0.5.h5")
     assert not HDF5IO.can_read(__file__)  # this file is not an HDF5 file
+
+
+class TestContainerSetDataIO(TestCase):
+
+    def setUp(self) -> None:
+        class ContainerWithData(Container):
+            __fields__ = ('data1', 'data2')
+
+            @docval(
+                {"name": "name", "doc": "name", "type": str},
+                {'name': 'data1', 'doc': 'field1 doc', 'type': list},
+                {'name': 'data2', 'doc': 'field2 doc', 'type':  list, 'default': None}
+            )
+            def __init__(self, **kwargs):
+                super().__init__(name=kwargs["name"])
+                self.data1 = kwargs["data1"]
+                self.data2 = kwargs["data2"]
+
+        self.obj = ContainerWithData("name", [1, 2, 3, 4, 5], None)
+
+    def test_set_data_io(self):
+        self.obj.set_data_io("data1", H5DataIO, data_io_kwargs=dict(chunks=True))
+        assert isinstance(self.obj.data1, H5DataIO)
+        assert self.obj.data1.io_settings["chunks"]
+
+    def test_fail_set_data_io(self):
+        """Attempt to set a DataIO for a dataset that is missing."""
+        with self.assertRaisesWith(ValueError, "data2 is None and cannot be wrapped in a DataIO class"):
+            self.obj.set_data_io("data2", H5DataIO, data_io_kwargs=dict(chunks=True))
+
+    def test_set_data_io_old_api(self):
+        """Test that using the kwargs still works but throws a warning."""
+        msg = (
+            "Use of **kwargs in Container.set_data_io() is deprecated. Please pass the DataIO kwargs as a dictionary to"
+            " the `data_io_kwargs` parameter instead."
+        )
+        with self.assertWarnsWith(DeprecationWarning, msg):
+            self.obj.set_data_io("data1", H5DataIO, chunks=True)
+        self.assertIsInstance(self.obj.data1, H5DataIO)
+        self.assertTrue(self.obj.data1.io_settings["chunks"])
+
+
+class TestDataSetDataIO(TestCase):
+
+    def setUp(self):
+        class MyData(Data):
+            pass
+
+        self.data = MyData("my_data", [1, 2, 3])
+
+    def test_set_data_io(self):
+        self.data.set_data_io(H5DataIO, dict(chunks=True))
+        assert isinstance(self.data.data, H5DataIO)
+        assert self.data.data.io_settings["chunks"]