Split instruments/readers/g5505_file_reader.py into a fileregistry.py and independent file readers. This is to improve instrument modularity and additions

instruments/readers/filereader_registry.py

@@ -0,0 +1,68 @@
+import sys
+import os
+root_dir = os.path.abspath(os.curdir)
+sys.path.append(root_dir)
+
+from instruments.readers.xps_ibw_reader import read_xps_ibw_file_as_dict
+from instruments.readers.g5505_text_reader import read_txt_files_as_dict
+
+
+file_extensions = ['.ibw','.txt','.dat','.h5','.TXT','.csv']
+
+# Define the instruments directory (modify this as needed or set to None)
+default_instruments_dir = None  # or provide an absolute path
+
+file_readers = {
+    'ibw': lambda a1: read_xps_ibw_file_as_dict(a1),
+    'txt': lambda a1: read_txt_files_as_dict(a1, instruments_dir=default_instruments_dir, work_with_copy=False),
+    'TXT': lambda a1: read_txt_files_as_dict(a1, instruments_dir=default_instruments_dir, work_with_copy=False),
+    'dat': lambda a1: read_txt_files_as_dict(a1, instruments_dir=default_instruments_dir, work_with_copy=False),
+    #'h5': lambda a1, a2, a3: copy_file_in_group(a1, a2, a3, work_with_copy=False),
+    'ACSM_TOFWARE_txt': lambda a1: read_txt_files_as_dict(a1, instruments_dir=default_instruments_dir, work_with_copy=False),
+    'ACSM_TOFWARE_csv': lambda a1: read_txt_files_as_dict(a1, instruments_dir=default_instruments_dir, work_with_copy=False)
+}
+
+def compute_filereader_key_from_path(hdf5_file_path):
+    """Constructs the key 'instrumentname_ext' based on hdf5_file_path, structured as
+    /instrumentname/to/filename.ext, which access the file reader that should be used to read such a file. 
+
+    Parameters
+    ----------
+    hdf5_file_path : str
+        _description_
+
+    Returns
+    -------
+    _type_
+        _description_
+    """
+
+    parts = hdf5_file_path.strip('/').split('/')
+
+    # Extract the filename and its extension
+    filename, file_extension = os.path.splitext(parts[-1])
+    
+    # Extract the first directory directly under the root directory '/' in the hdf5 file
+    subfolder_name = parts[0] if len(parts) > 1 else ""
+    
+    # Remove leading dot from the file extension
+    file_extension = file_extension.lstrip('.')
+    
+    # Construct the resulting string
+    full_string = f"{subfolder_name}_{file_extension}"
+    
+    return full_string, file_extension
+
+def select_file_reader(path):
+    full_string, extension = compute_filereader_key_from_path(path)
+    
+    # First, try to match the full string
+    if full_string in file_readers:
+        return file_readers[full_string]
+    
+    # If no match, try to match the reader using only the extension
+    if extension in file_readers:
+        return file_readers[extension]
+    
+    # Default case if no reader is found
+    return None