def main()

in pdf-splitter-python/main.py [0:0]

• 35 lines of code
• 5 McCabe index (conditional complexity)

def main(args: argparse.Namespace) -> int:
    """This project splits a PDF document using the Document AI API to identify split points"""
    if not args.project_id:
        _, project_id = google.auth.default()
        args.project_id = project_id

    file_path = os.path.abspath(args.input)

    if not os.path.isfile(file_path):
        print(f"Could not find file at {file_path}")
        return 1

    if PDF_EXTENSION not in args.input:
        print(f"Input file {args.input} is not a PDF")
        return 1

    if not args.output_dir:
        args.output_dir = os.path.dirname(file_path)

    client = DocumentProcessorServiceClient(
        client_options=ClientOptions(
            api_endpoint=f"{args.multi_region_location}-documentai.googleapis.com"
        )
    )

    processor_name = get_or_create_processor(
        client, args.project_id, args.multi_region_location, args.split_processor_type
    )

    print(
        "Using:\n"
        f'* Project ID: "{args.project_id}"\n'
        f'* Location: "{args.multi_region_location}"\n'
        f'* Processor Name "{processor_name}"\n'
        f'* Input PDF "{os.path.basename(file_path)}"\n'
        f'* Output directory: "{args.output_dir}"\n'
    )

    document = online_process(client, processor_name, file_path)

    document_json = write_document_json(document, file_path, output_dir=args.output_dir)
    print(f"Document AI Output: {document_json}")

    split_pdf(document.entities, file_path, output_dir=args.output_dir)

    print("Done.")
    return 0