checkpoint

docs/gallery/read.py

@@ -30,15 +30,32 @@
 from pynwb import NWBHDF5IO
 from hdmf_zarr.nwb import NWBZarrIO
 
-with NWBHDF5IO(filename, 'r', load_namespaces=False) as read_io:
-    file = read_io.read()
+# with NWBHDF5IO(filename, 'r', load_namespaces=False) as read_io:
+#     file = read_io.read()
 #
 with NWBHDF5IO(filename, 'r', load_namespaces=False) as read_io:  # Create HDF5 IO object for read
     with NWBZarrIO(zarr_filename, mode='w') as export_io:         # Create Zarr IO object for write
         export_io.export(src_io=read_io, write_args=dict(link_data=False))   # Export from HDF5 to Zarr
+#
+# with NWBZarrIO(path=zarr_filename, mode="r") as io:
+#     infile = io.read()
+
+# group = infile.electrodes.group.data[0]
+# breakpoint()
+#########
+with NWBZarrIO(zarr_filename, mode='r') as read_io:  # Create Zarr IO object for read
+    with NWBHDF5IO(hdf_filename, 'w') as export_io:  # Create HDF5 IO object for write
+        export_io.export(src_io=read_io, write_args=dict(link_data=False))  # Export from Zarr to HDF5
 
-with NWBZarrIO(path=zarr_filename, mode="r") as io:
-    infile = io.read()
+###############################################################################
+# Read the new HDF5 file back
+# ---------------------------
+#
+# Now our file has been converted from HDF5 to Zarr and back again to HDF5.
+# Here we check that we can still read that file.
 
-group = infile.electrodes.group.data[0]
+with NWBHDF5IO(hdf_filename, 'r') as hr:
+    hf = hr.read()
+    breakpoint()
+    hf.electrodes.group.data
 breakpoint()

src/hdmf_zarr/backend.py

@@ -300,6 +300,7 @@ def get_builder_disk_path(self, **kwargs):
     def write_builder(self, **kwargs):
         """Write a builder to disk"""
         f_builder, link_data, exhaust_dci = getargs('builder', 'link_data', 'exhaust_dci', kwargs)
+        breakpoint()
         for name, gbldr in f_builder.groups.items():
             self.write_group(parent=self.__file,
                              builder=gbldr,
@@ -530,10 +531,14 @@ def resolve_ref(self, zarr_ref):
         else:
             target_name = ROOT_NAME
         target_zarr_obj = zarr.open(source_file, mode='r')
+        # if target_name=='baz0':
+        #     breakpoint()
         if object_path is not None:
             try:
                 target_zarr_obj = target_zarr_obj[object_path]
             except Exception:
+                # breakpoint()
+
                 raise ValueError("Found bad link to object %s in file %s" % (object_path, source_file))
         # Return the create path
         return target_name, target_zarr_obj
@@ -699,6 +704,7 @@ def __setup_chunked_dataset__(cls, parent, name, data, options=None):
             returns='the Zarr array that was created', rtype=Array)
     def write_dataset(self, **kwargs):  # noqa: C901
         parent, builder, link_data, exhaust_dci = getargs('parent', 'builder', 'link_data', 'exhaust_dci', kwargs)
+        # breakpoint()
         force_data = getargs('force_data', kwargs)
         if self.get_written(builder):
             return None
@@ -1086,8 +1092,8 @@ def __read_group(self, zarr_obj, name=None):
             ret.set_group(sub_builder)
         # breakpoint()
         # read sub datasets
+        # breakpoint()
         for sub_name, sub_array in zarr_obj.arrays():
-            # breakpoint()
             sub_builder = self.__read_dataset(sub_array, sub_name)
             ret.set_dataset(sub_builder)
 
@@ -1125,6 +1131,7 @@ def __read_links(self, zarr_obj, parent):
     def __read_dataset(self, zarr_obj, name):
         # breakpoint()
         ret = self.__get_built(zarr_obj)
+        # breakpoint()
         if ret is not None:
             return ret
 
@@ -1156,7 +1163,6 @@ def __read_dataset(self, zarr_obj, name):
         reg_refs = False
         has_reference = False
         if isinstance(dtype, list):
-            breakpoint()
             # compound data type
             obj_refs = list()
             reg_refs = list()
@@ -1176,10 +1182,12 @@ def __read_dataset(self, zarr_obj, name):
             data = BuilderZarrTableDataset(zarr_obj, self, retrieved_dtypes)
             # d = BuilderH5TableDataset(zarr_obj, self, dtype)
         elif self.__is_ref(dtype):
+            # breakpoint()
             # reference array
-            has_reference = True
+            has_reference = True #TODO: REMOVE
             if dtype == 'object': # wrap with dataset ref
                 # obj_refs = True
+                breakpoint()
                 data = BuilderZarrReferenceDataset(data, self)
             elif dtype == 'region':
                 reg_refs = True