Adding config file for postprocessing steps execution

#from file_helper import get_all_files_from_dir

DEFAULT_FORMAT_STYLE_UPDATES = {

    "update_figure_captions": True,

    "update_heading_styles": True,

    "update_figure_style": True,

    "update_table_captions": True,

    "update_abbreviations": True,

    "update_table_rows": True,

    "update_notes": True,

    "update_references": True,

    "update_lists": True,

    "update_body_text_style": True,

    "add_no_break_hyphens": True,

    "update_references_style": True,

    "update_source_code_style": True,

    "add_break_after_code_blocks_and_tables": True,

    "update_equation_style": True,

    "correct_quotes_docx": True,

    "sanitize_document_xml": True

}

def load_format_style_updates_config(config_path=None):

    """

    Load optional JSON config for update_format_styles step toggles.

    Expected JSON format:

    {

      "updates": {

        "update_figure_captions": true,

        "update_heading_styles": false

      }

    }

    The root object can also directly contain step names.

    Unknown keys are ignored.

    """

    config = DEFAULT_FORMAT_STYLE_UPDATES.copy()

    if not config_path:

        return config

    with open(config_path, "r", encoding="utf-8") as config_file:

        raw_config = json.load(config_file)

    update_toggles = raw_config.get("updates", raw_config)

    if not isinstance(update_toggles, dict):

        raise ValueError("Style config must be a JSON object or contain an 'updates' object.")

    unknown_keys = []

    for key, value in update_toggles.items():

        if key not in config:

            unknown_keys.append(key)

            continue

        if not isinstance(value, bool):

            raise ValueError(f"Config value for '{key}' must be a boolean.")

        config[key] = value

    if unknown_keys:

        print(f"Ignoring unknown update toggle(s): {', '.join(sorted(unknown_keys))}")

    return config

def sanitize_xml_text(text):

    """

    Remove invalid XML control characters from text.

    parser = argparse.ArgumentParser(description="Update format styles in a DOCX file.")

    parser.add_argument("docx_input", help="Path to input DOCX file")

    parser.add_argument("docx_output", help="Path to output DOCX file")

    parser.add_argument(

        "--style-config",

        help="Path to JSON config file with format-style update toggles",

        default=None

    )

    args = parser.parse_args()

    update_figure_captions(args.docx_input, args.docx_output)

    update_heading_styles(args.docx_input, args.docx_output)

    update_figure_style(args.docx_input, args.docx_output)

    update_table_captions(args.docx_input, args.docx_output)

    update_abbreviations(args.docx_input, args.docx_output)

    update_table_rows(args.docx_input, args.docx_output)

    update_notes(args.docx_input, args.docx_output)

    update_references(args.docx_input, args.docx_output)

    update_lists(args.docx_input, args.docx_output)

    update_body_text_style(args.docx_input, args.docx_output)

    add_no_break_hyphens(args.docx_input, args.docx_output)

    update_references_style(args.docx_input, args.docx_output)

    update_source_code_style(args.docx_input, args.docx_output)

    add_break_after_code_blocks_and_tables(args.docx_input, args.docx_output)

    update_equation_style(args.docx_input, args.docx_output)

    correct_quotes_docx(args.docx_input, args.docx_output)

    style_updates_config = load_format_style_updates_config(args.style_config)

    format_style_steps = [

        ("update_figure_captions", update_figure_captions),

        ("update_heading_styles", update_heading_styles),

        ("update_figure_style", update_figure_style),

        ("update_table_captions", update_table_captions),

        ("update_abbreviations", update_abbreviations),

        ("update_table_rows", update_table_rows),

        ("update_notes", update_notes),

        ("update_references", update_references),

        ("update_lists", update_lists),

        ("update_body_text_style", update_body_text_style),

        ("add_no_break_hyphens", add_no_break_hyphens),

        ("update_references_style", update_references_style),

        ("update_source_code_style", update_source_code_style),

        ("add_break_after_code_blocks_and_tables", add_break_after_code_blocks_and_tables),

        ("update_equation_style", update_equation_style),

        ("correct_quotes_docx", correct_quotes_docx)

    ]

    for step_name, step_func in format_style_steps:

        if style_updates_config[step_name]:

            step_func(args.docx_input, args.docx_output)

        else:

            print(f'Skipped "{step_name}" (disabled in style config)')

    # Final sanitization: remove invalid XML characters

    if style_updates_config["sanitize_document_xml"]:

        ns = {"w": "http://schemas.openxmlformats.org/wordprocessingml/2006/main"}

        with zipfile.ZipFile(args.docx_output, 'r') as zin:

            xml_data = zin.read("word/document.xml")

        finally:

            if os.path.exists(tmp_path):

                os.remove(tmp_path)

    else:

        print('Skipped "sanitize_document_xml" (disabled in style config)')

 No newline at end of file