Adding sanitize helpers

#from file_helper import get_all_files_from_dir

#from file_helper import get_all_files_from_dir

def sanitize_xml_text(text):

    """

    Remove invalid XML control characters from text.

    XML 1.0 allows only: tab (0x09), line feed (0x0A), carriage return (0x0D)

    All other control characters (0x00-0x08, 0x0B-0x0C, 0x0E-0x1F) are invalid.

    Parameters

    ----------

    text : str

        Text that may contain invalid XML characters

    Returns

    -------

    str

        Text with invalid control characters removed

    """

    if text is None:

        return None

    # Remove invalid control characters (keep tab, LF, CR)

    # Invalid: 0x00-0x08, 0x0B-0x0C, 0x0E-0x1F

    # Valid: 0x09 (tab), 0x0A (LF), 0x0D (CR)

    sanitized = ''.join(char for char in text if ord(char) >= 32 or char in '\t\n\r')

    return sanitized

def sanitize_document_xml(root, ns):

    """

    Sanitize all text elements in a document XML tree by removing invalid control characters.

    Parameters

    ----------

    root : lxml.etree.Element

        Root element of the document XML

    ns : dict

        Namespace dictionary

    """

    # Find all text elements

    text_elems = root.xpath('.//w:t', namespaces=ns)

    for text_elem in text_elems:

        if text_elem.text:

            text_elem.text = sanitize_xml_text(text_elem.text)

def apply_standard_style_to_unformatted_paragraphs(config):

def apply_standard_style_to_unformatted_paragraphs(config):

    docx_path = config.get("output_docx")

    docx_path = config.get("output_docx")

    update_source_code_style(args.docx_input, args.docx_output)

    update_source_code_style(args.docx_input, args.docx_output)

    update_equation_style(args.docx_input, args.docx_output)

    update_equation_style(args.docx_input, args.docx_output)

    correct_quotes_docx(args.docx_input, args.docx_output)

    correct_quotes_docx(args.docx_input, args.docx_output)

    # Final sanitization: remove invalid XML characters

    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")

    root = etree.fromstring(xml_data)

    sanitize_document_xml(root, ns)

    xml_data = etree.tostring(root, xml_declaration=True, encoding="UTF-8", standalone="yes")

    # Write sanitized document back

    tmp_fd, tmp_path = tempfile.mkstemp(suffix=".docx")

    os.close(tmp_fd)

    try:

        with zipfile.ZipFile(args.docx_output, 'r') as zin, zipfile.ZipFile(tmp_path, 'w', zipfile.ZIP_DEFLATED) as zout:

            for item in zin.infolist():

                if item.filename != "word/document.xml":

                    data = zin.read(item.filename)

                    zout.writestr(item.filename, data)

            zout.writestr("word/document.xml", xml_data)

        shutil.move(tmp_path, args.docx_output)

        os.chmod(args.docx_output, 0o644)

        print('Sanitized document: removed invalid XML characters')

    finally:

        if os.path.exists(tmp_path):

            os.remove(tmp_path)

 No newline at end of file