From 2a9d69c757a3b506dc8ef6693e5d25db7bb71dc8 Mon Sep 17 00:00:00 2001
From: Florez Ospina Juan Felipe <juan.florez-ospina@psi.ch>
Date: Thu, 10 Oct 2024 11:28:23 +0200
Subject: [PATCH] Robustified metadata and dataset extraction methods by
 requiring explicit load of file obj before their use. Renamed a few functions
 and fixed types in print statements.

---
 src/hdf5_ops.py | 49 ++++++++++++++++++++++++++++++++++---------------
 1 file changed, 34 insertions(+), 15 deletions(-)

diff --git a/src/hdf5_ops.py b/src/hdf5_ops.py
index 50c0fb3..61b43e0 100644
--- a/src/hdf5_ops.py
+++ b/src/hdf5_ops.py
@@ -54,29 +54,44 @@ class HDF5DataOpsManager():
             self.file_obj.close()
             self.file_obj = None
   
-    def load_dataset_metadata(self):
+    def extract_and_load_dataset_metadata(self):
 
         def __get_datasets(name, obj, list_of_datasets):
             if isinstance(obj,h5py.Dataset):
                 list_of_datasets.append(name)  
                 #print(f'Adding dataset: {name}') #tail: {head} head: {tail}')
         list_of_datasets = []
-        with h5py.File(self.file_path,'r') as file:
+
+        if self.file_obj is None:
+           raise RuntimeError("File object is not loaded. Please load the HDF5 file using the 'load_file_obj' method before attempting to extract datasets.")
+
+        try: 
+            
             list_of_datasets = []
-            file.visititems(lambda name, obj: __get_datasets(name, obj, list_of_datasets))
 
-        dataset_metadata_df = pd.DataFrame({'dataset_name': list_of_datasets})
-        dataset_metadata_df['parent_instrument'] = dataset_metadata_df['dataset_name'].apply(lambda x: x.split('/')[-3])
-        dataset_metadata_df['parent_file'] = dataset_metadata_df['dataset_name'].apply(lambda x: x.split('/')[-2])
+            self.file_obj.visititems(lambda name, obj: __get_datasets(name, obj, list_of_datasets))
+
+            dataset_metadata_df = pd.DataFrame({'dataset_name': list_of_datasets})
+            dataset_metadata_df['parent_instrument'] = dataset_metadata_df['dataset_name'].apply(lambda x: x.split('/')[-3])
+            dataset_metadata_df['parent_file'] = dataset_metadata_df['dataset_name'].apply(lambda x: x.split('/')[-2])
+
+            self.dataset_metadata_df = dataset_metadata_df
+
+        except Exception as e:
+
+            self.unload_file_obj()
+            print(f"An unexpected error occurred: {e}. File object will be unloaded.")
+            
+
+
 
-        self.dataset_metadata_df = dataset_metadata_df
     
-    def read_dataset_as_dataframe(self,dataset_name):
+    def extract_dataset_as_dataframe(self,dataset_name):
         """ 
         returns a copy of the dataset content in the form of dataframe when possible or numpy array 
         """
         if self.file_obj is None:
-            self.load_file_obj()
+           raise RuntimeError("File object is not loaded. Please load the HDF5 file using the 'load_file_obj' method before attempting to extract datasets.")
 
         dataset_obj = self.file_obj[dataset_name]
         # Read dataset content from dataset obj
@@ -88,9 +103,13 @@ class HDF5DataOpsManager():
 
         try:
             return pd.DataFrame(data)
-        except ValueError as exp:
-            logging.error(f"Failed to convert dataset '{dataset_name}' to DataFrame: {exp}. Instead, dataset will be returned as Numpy array.")
+        except ValueError as e:
+            logging.error(f"Failed to convert dataset '{dataset_name}' to DataFrame: {e}. Instead, dataset will be returned as Numpy array.")
             return data  # 'data' is a NumPy array here
+        except Exception as e:
+            self.unload_file_obj()
+            print(f"An unexpected error occurred: {e}. Returning None and unloading file object")
+            return None
         
     # Define metadata revision methods: append(), update(), delete(), and rename().
 
@@ -126,7 +145,7 @@ class HDF5DataOpsManager():
         """
 
         if self.file_obj is None:
-            raise RuntimeError("File object is not loaded. Please load the HDF5 file using the 'load_file' method before attempting to modify it.")
+            raise RuntimeError("File object is not loaded. Please load the HDF5 file using the 'load_file_obj' method before attempting to modify it.")
 
         # Create a copy of annotation_dict to avoid modifying the original
         annotation_dict_copy = copy.deepcopy(annotation_dict)
@@ -184,7 +203,7 @@ class HDF5DataOpsManager():
         """
 
         if self.file_obj is None:
-            raise RuntimeError("File object is not loaded. Please load the HDF5 file using the 'load_file' method before attempting to modify it.")
+            raise RuntimeError("File object is not loaded. Please load the HDF5 file using the 'load_file_obj' method before attempting to modify it.")
 
         update_dict = {}
 
@@ -231,7 +250,7 @@ class HDF5DataOpsManager():
         """
         
         if self.file_obj is None:
-            raise RuntimeError("File object is not loaded. Please load the HDF5 file using the 'load_file' method before attempting to modify it.")
+            raise RuntimeError("File object is not loaded. Please load the HDF5 file using the 'load_file_obj' method before attempting to modify it.")
 
         try:
             obj = self.file_obj[obj_name]
@@ -273,7 +292,7 @@ class HDF5DataOpsManager():
         """
 
         if self.file_obj is None:
-            raise RuntimeError("File object is not loaded. Please load the HDF5 file using the 'load_file' method before attempting to modify it.")
+            raise RuntimeError("File object is not loaded. Please load the HDF5 file using the 'load_file_obj' method before attempting to modify it.")
 
         try:
             obj = self.file_obj[obj_name]