Gradio_UI.py

def upload_file(
    self,
    file,
    file_uploads_log,
    allowed_file_types=[
        "application/pdf",
        "application/vnd.openxmlformats-officedocument.wordprocessingml.document",
        "text/plain",
    ],
):
    """
    Handle file uploads, default allowed types are .pdf, .docx, and .txt
    """
    import gradio as gr

    if file is None:
        return gr.Textbox("No file uploaded", visible=True), file_uploads_log

    try:
        mime_type, _ = mimetypes.guess_type(file.name)
    except Exception as e:
        return gr.Textbox(f"Error: {e}", visible=True), file_uploads_log

    if mime_type not in allowed_file_types:
        return gr.Textbox("File type disallowed", visible=True), file_uploads_log

    # Sanitize file name
    original_name = os.path.basename(file.name)
    sanitized_name = re.sub(r"[^\w\-.]", "_", original_name)

    # Map mime type to extension
    type_to_ext = {}
    for ext, t in mimetypes.types_map.items():
        if t not in type_to_ext:
            type_to_ext[t] = ext

    name_without_ext = ".".join(sanitized_name.split(".")[:-1])
    ext = type_to_ext.get(mime_type, "")
    if not ext.startswith("."):
        ext = "." + ext if ext else ""
    sanitized_name = f"{name_without_ext}{ext}"

    # Save file
    file_path = os.path.join(self.file_upload_folder, sanitized_name)
    with open(file_path, "wb") as f:
        f.write(file.read())

    # Update log or return success message
    file_uploads_log.append(file_path)
    return gr.Textbox(f"File uploaded: {sanitized_name}", visible=True), file_uploads_log