class Dataset(TimestampModel):

    # Choices matched with the ComputedFile/Library models
    class FileFormats:
        ANN_DATA = "ANN_DATA"
        SINGLE_CELL_EXPERIMENT = "SINGLE_CELL_EXPERIMENT"

        CHOICES = (
            (ANN_DATA, "AnnData"),
            (SINGLE_CELL_EXPERIMENT, "Single cell experiment"),
        )
    
    id: UUIDField()

    # User editable fields (with validation)
    format: TextField(choices=FileFormats.CHOICES)
    data: JSONField(default={})   
    regenerated_from: ForeignKey('self', null=True) # validation required
    email: EmailField(null=True) # validation required
    start: BooleanField(null=True) # validation required (with a serializer)

    # On-request fields - values assigned on requests
    token: OneToOneField(Token) # Used to process the dataset
    download_tokens: ManyToManyField(Token) # Used to create download urls

    # Dataset status fields - values set during the processing workflow
    started_at: DateTimeField(null=True)
    is_started: Boolean(default=False)
    is_processing: Boolean(default=False)

    processed_at: DateTimeField(null=True)
    is_processed: Boolean(default=False)
            
    expires_at: DateTimeField(null=True)
    is_expired: Boolean(default=False) # If expires_at exists and has passed
    
    errored_at: DateTimeField(null=True)
    is_errored: Boolean(default=False)
    error_message: TextField(null=True)

    computed_file: OneToOneField(ComputedFile)

    # Implement later
    # Process information fields        
    api_release: CharField() # A commit hash from Docker
    last_edit_hash: CharField() # A hash for original files when the data attribute was last modified
    input_bucket_sync: DateTimeField() # The last time the original files were synced with the input bucket
    job_id: CharField() # The batch job ID

    # Dynamic model properties
    @property
    stats: Dict # For client UI presentation
    original_files # The result of getting the original files from the data attribtue