Implemented metadata append, rename, delete, and update operations on the hdf5 manager object and refactored metadata update script based on yaml file to use said operations.

pipelines/metadata_revision.py

@@ -190,32 +190,71 @@ def load_yaml(yaml_review_file):
             print(exc)
             return None
 
-def update_hdf5_attributes(input_hdf5_file, yaml_dict):
+#def update_hdf5_attributes(input_hdf5_file, yaml_dict):
 
-    def update_attributes(hdf5_obj, yaml_obj):
-        for attr_name, attr_value in yaml_obj['attributes'].items():
-
-            if not isinstance(attr_value, dict):
-                attr_value = {'rename_as': attr_name, 'value': attr_value}
-            
-            if (attr_name in hdf5_obj.attrs.keys()): # delete or update
-                if attr_value.get('delete'): # delete when True
-                    hdf5_obj.attrs.__delitem__(attr_name)                        
-                elif not (attr_value.get('rename_as') == attr_name): # update when true
-                    hdf5_obj.attrs[attr_value.get('rename_as')] = hdf5_obj.attrs[attr_name] # convert_attrdict_to_np_structured_array(attr_value)  
-                    hdf5_obj.attrs.__delitem__(attr_name)  
-            else: # add a new attribute
-                hdf5_obj.attrs.update({attr_name : utils.convert_attrdict_to_np_structured_array(attr_value)})  
-
-    with h5py.File(input_hdf5_file, 'r+') as f:
-        for key in yaml_dict.keys():
-            hdf5_obj = f[key]
-            yaml_obj = yaml_dict[key]
-            update_attributes(hdf5_obj, yaml_obj)
 
 def update_hdf5_file_with_review(input_hdf5_file, yaml_review_file):
+    
+    """
+    Updates, appends, or deletes metadata attributes in an HDF5 file based on a provided YAML dictionary.
+    
+    Parameters:
+    -----------
+    input_hdf5_file : str
+        Path to the HDF5 file.
+    
+    yaml_dict : dict
+        Dictionary specifying objects and their attributes with operations. Example format:
+        {
+            "object_name": {
+                "attr_name": {
+                    "value": attr_value,
+                    "delete": True/False
+                }
+            }
+        }
+    """
     yaml_dict = load_yaml(yaml_review_file)
-    update_hdf5_attributes(input_hdf5_file, yaml_dict)
+
+    # Initialize HDF5 operations manager
+    DataOpsAPI = hdf5_ops.HDF5DataOpsManager(input_hdf5_file)
+    DataOpsAPI.open_file()
+
+    # Iterate over each object in the YAML dictionary
+    for obj_name, attr_dict in yaml_dict.items():
+        # Prepare dictionaries for append, update, and delete actions
+        append_dict = {}
+        update_dict = {}
+        delete_dict = {}
+
+        if not obj_name in DataOpsAPI.file_obj:
+            continue  # Skip if the object does not exist
+
+        # Iterate over each attribute in the current object
+        for attr_name, attr_props in attr_dict['attributes'].items():
+            if not isinstance(attr_props, dict):
+                #attr_props = {'value': attr_props}
+                # Check if the attribute exists (for updating)
+                if attr_name in DataOpsAPI.file_obj[obj_name].attrs: 
+                    update_dict[attr_name] = attr_props
+                # Otherwise, it's a new attribute to append
+                else:
+                    append_dict[attr_name] = attr_props
+            else:
+                # Check if the attribute is marked for deletion
+                if attr_props.get('delete', False):
+                    delete_dict[attr_name] = attr_props 
+
+        # Perform a single pass for all three operations
+        if append_dict:
+            DataOpsAPI.append_metadata(obj_name, append_dict)
+        if update_dict:
+            DataOpsAPI.update_metadata(obj_name, update_dict)
+        if delete_dict:
+            DataOpsAPI.delete_metadata(obj_name, delete_dict)
+    
+    # Close hdf5 file
+    DataOpsAPI.close_file()
     # Regenerate yaml snapshot of updated HDF5 file
     output_yml_filename_path = hdf5_ops.serialize_metadata(input_hdf5_file)
     print(f'{output_yml_filename_path} was successfully regenerated from the updated version of{input_hdf5_file}')