def parse_and_format_filenames(directory): # Define possible sample names sample_names = [ "SSB1", "SSB2", "SSBD1", "SSBD2", "SSW1", "SSW2", "SSW3", "SSW4", "SSWO31", "SSWO32", "SSWO33", "SSWO34" ] # Set to store formatted filenames formatted_filenames = set() # List all files in the directory for filename in os.listdir(directory): if filename.endswith('.csv'): # Extract the basename without extension base_filename = os.path.splitext(filename)[0] # Determine the sample name and format the filename for sample_name in sample_names: if base_filename.startswith(sample_name): # Extract zone and energy zone_energy_part = base_filename[len(sample_name):] # Remainder after sample name zone = 'z' + zone_energy_part[0] # First digit after sample name is zone energy = zone_energy_part[1:] # Remainder is energy with 'kV' reformatted_sample_name = sample_name formatted_filename = f"{reformatted_sample_name}-{zone}-{energy}" formatted_filenames.add(formatted_filename) break # Stop looking through sample names once a match is found return formatted_filenames