Implemented hdf5_file_reader.py and updated register.yaml and hdf5_writer.py. This replaces previous function __copy_file_in_group().

instruments/readers/hdf5_file_reader.py

@@ -0,0 +1,79 @@
+import sys
+import os
+
+try:
+    thisFilePath = os.path.abspath(__file__)
+except NameError:
+    print("Error: __file__ is not available. Ensure the script is being run from a file.")
+    print("[Notice] Path to DIMA package may not be resolved properly.")
+    thisFilePath = os.getcwd()  # Use current directory or specify a default
+
+dimaPath = os.path.normpath(os.path.join(thisFilePath, "..",'..','..'))  # Move up to project root
+
+if dimaPath not in sys.path:  # Avoid duplicate entries
+    sys.path.insert(0,dimaPath)
+    
+import pandas as pd
+import collections
+import yaml
+import h5py
+import argparse
+import logging
+import utils.g5505_utils as utils
+import src.hdf5_ops as hdf5_ops
+import instruments.filereader_registry as filereader_registry
+
+ 
+   
+
+def hdf5_file_reader(dest_file_obj_or_path, src_file_path=None, dest_group_name=None, work_with_copy: bool = True):
+    """
+    Reads an HDF5 file and copies its contents to a destination group.
+    If an HDF5 file object is provided, it skips reading from a file path.
+    """
+    # Determine if dest_file_obj_or_path is a file path or an HDF5 file object
+    if isinstance(dest_file_obj_or_path, h5py.File):
+        dest_file_obj = dest_file_obj_or_path
+    else:
+        dest_file_obj = h5py.File(dest_file_obj_or_path, mode='r+', track_order=True)
+    
+    try:
+        if work_with_copy:
+            tmp_src_file_path = utils.make_file_copy(src_file_path)
+        else:
+            tmp_src_file_path = src_file_path
+        
+        # Open source HDF5 file
+        with h5py.File(tmp_src_file_path, 'r') as src_file:
+            dest_file_obj.copy(source=src_file['/'], dest=dest_group_name)
+        
+        # Remove temporary file if created
+        if 'tmp_files' in tmp_src_file_path:
+            os.remove(tmp_src_file_path)
+    
+        print(f'Completed transfer for /{dest_group_name}')
+    
+    finally:
+        if not isinstance(dest_file_obj_or_path, h5py.File):
+            dest_file_obj.close()
+    
+    return 0
+
+if __name__ == "__main__":
+
+    # Set up argument parsing
+    parser = argparse.ArgumentParser(description="Data ingestion process to HDF5 files.")
+    parser.add_argument('dst_file_path', type=str, help="Path to the target HDF5 file.")
+    parser.add_argument('src_file_path', type=str, help="Path to source HDF5 file to be saved to target HDF5 file.")
+    parser.add_argument('dst_group_name', type=str, help="Group name '/instFolder/[category]/fileName' in the target HDF5 file.")
+
+    args = parser.parse_args()
+
+    dst_file_path = args.dst_file_path
+    src_file_path = args.src_file_path
+    dst_group_name = args.dst_group_name
+    default_mode = 'r+'
+
+    status = hdf5_file_reader(dst_file_path, src_file_path, dst_group_name)
+
+    print('Return status: {status}')

instruments/registry.yaml

@@ -6,7 +6,7 @@ instruments:
 
   - instrumentFolderName: NEXAFS
     fileExtension: h5
-    fileReaderPath: null
+    fileReaderPath: instruments/readers/hdf5_file_reader.py
     InstrumentDictionaryPath: null
 
   - instrumentFolderName: SES