>> follow up review comments from gdmenten (15/01/2020)

Author: alixdamman

larray/inout/common.py

@@ -16,6 +16,8 @@
 # only for HDF5 and pickle formats
 # support list, tuple and dict?
 _supported_scalars_types = (int, float, bool, basestring, date, time, datetime)
+_supported_types = _supported_larray_types + _supported_scalars_types
+_supported_typenames = {cls.__name__ for cls in _supported_types}
 
 
 def _get_index_col(nb_axes=None, index_col=None, wide=True):

larray/inout/hdf.py

@@ -13,30 +13,11 @@
 from larray.core.metadata import Metadata
 from larray.util.misc import LHDFStore
 from larray.inout.session import register_file_handler
-from larray.inout.common import FileHandler, _supported_larray_types, _supported_scalars_types
+from larray.inout.common import FileHandler, _supported_typenames, _supported_scalars_types
 from larray.inout.pandas import df_asarray
 from larray.example import get_example_filepath
 
 
-_hdf_supported_types = _supported_larray_types + _supported_scalars_types
-
-
-class ScalarHDF(object):
-    def __init__(self, value):
-        _type = type(value).__name__
-        if not isinstance(value, _supported_scalars_types):
-            raise TypeError("Type {} which is not currently supported by the HDF5 format".format(_type))
-        self.value = value
-        self._type = _type
-
-    def to_hdf(self, filepath, key):
-        key = _translate_group_key_hdf(key)
-        s = pd.Series(data=self.value)
-        with LHDFStore(filepath) as store:
-            store.put(key, s)
-            store.get_storer(key).attrs.type = self._type
-
-
 # for backward compatibility (larray < 0.29) but any object read from an hdf file should have
 # an attribute 'type'
 def _get_type_from_attrs(attrs):
@@ -139,7 +120,7 @@ def read_hdf(filepath_or_buffer, key, fill_value=nan, na=nan, sort_rows=False, s
                 key = np.char.decode(key, 'utf-8')
             axis = read_hdf(filepath_or_buffer, attrs['axis_key'])
             res = LGroup(key=key, name=name, axis=axis)
-        elif _type in {cls.__name__ for cls in _supported_scalars_types}:
+        elif _type in _supported_typenames:
             res = pd_obj.values
             assert len(res) == 1
             res = res[0]
@@ -167,26 +148,29 @@ def list_items(self):
         items += [(key.split('/')[-1], 'Group_Backward_Comp') for key in keys if '__groups__' in key]
         return items
 
-    def _read_item(self, key, type, *args, **kwargs):
-        if type in {cls.__name__ for cls in _hdf_supported_types}:
+    def _read_item(self, key, typename, *args, **kwargs):
+        if typename in _supported_typenames:
             hdf_key = '/' + key
         # ---- for backward compatibility (LArray < 0.33) ----
-        elif type == 'Axis_Backward_Comp':
+        elif typename == 'Axis_Backward_Comp':
             hdf_key = '__axes__/' + key
-        elif type == 'Group_Backward_Comp':
+        elif typename == 'Group_Backward_Comp':
             hdf_key = '__groups__/' + key
         else:
             raise TypeError()
         return read_hdf(self.handle, hdf_key, *args, **kwargs)
 
     def _dump_item(self, key, value, *args, **kwargs):
-        if isinstance(value, _supported_scalars_types):
-            value = ScalarHDF(value)
-        elif isinstance(value, Group):
-            kwargs['axis_key'] = '/' + value.axis.name
-        if hasattr(value, 'to_hdf'):
-            hdf_key = '/' + key
+        hdf_key = '/' + key
+        if isinstance(value, (Array, Axis)):
             value.to_hdf(self.handle, hdf_key, *args, **kwargs)
+        elif isinstance(value, Group):
+            hdf_axis_key = '/' + value.axis.name
+            value.to_hdf(self.handle, hdf_key, hdf_axis_key, *args, **kwargs)
+        elif isinstance(value, _supported_scalars_types):
+            s = pd.Series(data=value)
+            self.handle.put(hdf_key, s)
+            self.handle.get_storer(hdf_key).attrs.type = type(value).__name__
         else:
             raise TypeError()
 

larray/inout/pickle.py

@@ -9,10 +9,7 @@
 from larray.core.metadata import Metadata
 from larray.util.compat import pickle
 from larray.inout.session import register_file_handler
-from larray.inout.common import FileHandler, _supported_larray_types, _supported_scalars_types
-
-
-_pickle_supported_types = _supported_larray_types + _supported_scalars_types
+from larray.inout.common import FileHandler, _supported_types, _supported_typenames, _supported_scalars_types
 
 
 @register_file_handler('pickle', ['pkl', 'pickle'])
@@ -39,14 +36,14 @@ def list_items(self):
         items += [(key, 'Array') for key, value in self.data.items() if isinstance(value, Array)]
         return items
 
-    def _read_item(self, key, type, *args, **kwargs):
-        if type in {cls.__name__ for cls in _pickle_supported_types}:
+    def _read_item(self, key, typename, *args, **kwargs):
+        if typename in _supported_typenames:
             return self.data[key]
         else:
             raise TypeError()
 
     def _dump_item(self, key, value, *args, **kwargs):
-        if isinstance(value, _pickle_supported_types):
+        if isinstance(value, _supported_types):
             self.data[key] = value
         else:
             raise TypeError()