create_classification_job async ¶

async def create_classification_job(
    self,
    *,
    config_overrides: Optional[AsyncMacie2ClientConfig] = None,
    allow_list_ids: Optional[
        "capo_macie2.types.__list_of__string.__listOf__string"
    ] = None,
    client_token: Optional["capo_macie2.types.__string.__string"] = None,
    custom_data_identifier_ids: Optional[
        "capo_macie2.types.__list_of__string.__listOf__string"
    ] = None,
    description: Optional["capo_macie2.types.__string.__string"] = None,
    initial_run: Optional["capo_macie2.types.__boolean.__boolean"] = None,
    job_type: Optional["capo_macie2.types.job_type.JobType"] = None,
    managed_data_identifier_ids: Optional[
        "capo_macie2.types.__list_of__string.__listOf__string"
    ] = None,
    managed_data_identifier_selector: Optional[
        "capo_macie2.types.managed_data_identifier_selector.ManagedDataIdentifierSelector"
    ] = None,
    name: Optional["capo_macie2.types.__string.__string"] = None,
    s3_job_definition: Optional[
        "capo_macie2.types.s3_job_definition.S3JobDefinition"
    ] = None,
    sampling_percentage: Optional["capo_macie2.types.__integer.__integer"] = None,
    schedule_frequency: Optional[
        "capo_macie2.types.job_schedule_frequency.JobScheduleFrequency"
    ] = None,
    tags: Optional["capo_macie2.types.tag_map.TagMap"] = None,
) -> "capo_macie2.types.create_classification_job_response.CreateClassificationJobResponse":
    """<p>Creates and defines the settings for a classification job.</p>

    Args:
        allow_list_ids: <p>An array of unique identifiers, one for each allow list for the job to use when it analyzes data.</p>
        client_token: <p>A unique, case-sensitive token that you provide to ensure the idempotency of the request.</p>
        custom_data_identifier_ids: <p>An array of unique identifiers, one for each custom data identifier for the job to use when it analyzes data. To use only managed data identifiers, don't specify a value for this property and specify a value other than NONE for the managedDataIdentifierSelector property.</p>
        description: <p>A custom description of the job. The description can contain as many as 200 characters.</p>
        initial_run: <p>For a recurring job, specifies whether to analyze all existing, eligible objects immediately after the job is created (true). To analyze only those objects that are created or changed after you create the job and before the job's first scheduled run, set this value to false.</p> <p>If you configure the job to run only once, don't specify a value for this property.</p>
        job_type: <p>The schedule for running the job. Valid values are:</p> <ul><li><p>ONE_TIME - Run the job only once. If you specify this value, don't specify a value for the scheduleFrequency property.</p></li> <li><p>SCHEDULED - Run the job on a daily, weekly, or monthly basis. If you specify this value, use the scheduleFrequency property to specify the recurrence pattern for the job.</p></li></ul>
        managed_data_identifier_ids: <p>An array of unique identifiers, one for each managed data identifier for the job to include (use) or exclude (not use) when it analyzes data. Inclusion or exclusion depends on the managed data identifier selection type that you specify for the job (managedDataIdentifierSelector).</p> <p>To retrieve a list of valid values for this property, use the ListManagedDataIdentifiers operation.</p>
        managed_data_identifier_selector: <p>The selection type to apply when determining which managed data identifiers the job uses to analyze data. Valid values are:</p> <ul><li><p>ALL - Use all managed data identifiers. If you specify this value, don't specify any values for the managedDataIdentifierIds property.</p></li> <li><p>EXCLUDE - Use all managed data identifiers except the ones specified by the managedDataIdentifierIds property.</p></li> <li><p>INCLUDE - Use only the managed data identifiers specified by the managedDataIdentifierIds property.</p></li> <li><p>NONE - Don't use any managed data identifiers. If you specify this value, specify at least one value for the customDataIdentifierIds property and don't specify any values for the managedDataIdentifierIds property.</p></li> <li><p>RECOMMENDED (default) - Use the recommended set of managed data identifiers. If you specify this value, don't specify any values for the managedDataIdentifierIds property.</p></li></ul> <p>If you don't specify a value for this property, the job uses the recommended set of managed data identifiers.</p> <p>If the job is a recurring job and you specify ALL or EXCLUDE, each job run automatically uses new managed data identifiers that are released. If you don't specify a value for this property or you specify RECOMMENDED for a recurring job, each job run automatically uses all the managed data identifiers that are in the recommended set when the run starts.</p> <p>To learn about individual managed data identifiers or determine which ones are in the recommended set, see <a href="https://docs.aws.amazon.com/macie/latest/user/managed-data-identifiers.html">Using managed data identifiers</a> or <a href="https://docs.aws.amazon.com/macie/latest/user/discovery-jobs-mdis-recommended.html">Recommended managed data identifiers</a> in the <i>Amazon Macie User Guide</i>.</p>
        name: <p>A custom name for the job. The name can contain as many as 500 characters.</p>
        s3_job_definition: <p>The S3 buckets that contain the objects to analyze, and the scope of that analysis.</p>
        sampling_percentage: <p>The sampling depth, as a percentage, for the job to apply when processing objects. This value determines the percentage of eligible objects that the job analyzes. If this value is less than 100, Amazon Macie selects the objects to analyze at random, up to the specified percentage, and analyzes all the data in those objects.</p>
        schedule_frequency: <p>The recurrence pattern for running the job. To run the job only once, don't specify a value for this property and set the value for the jobType property to ONE_TIME.</p>
        tags: <p>A map of key-value pairs that specifies the tags to associate with the job.</p> <p>A job can have a maximum of 50 tags. Each tag consists of a tag key and an associated tag value. The maximum length of a tag key is 128 characters. The maximum length of a tag value is 256 characters.</p>

    Raises:
        capo_macie2.errors.access_denied_exception.AccessDeniedException: <p>Provides information about an error that occurred due to insufficient access to a specified resource.</p>
        capo_macie2.errors.conflict_exception.ConflictException: <p>Provides information about an error that occurred due to a versioning conflict for a specified resource.</p>
        capo_macie2.errors.internal_server_exception.InternalServerException: <p>Provides information about an error that occurred due to an unknown internal server error, exception, or failure.</p>
        capo_macie2.errors.resource_not_found_exception.ResourceNotFoundException: <p>Provides information about an error that occurred because a specified resource wasn't found.</p>
        capo_macie2.errors.service_quota_exceeded_exception.ServiceQuotaExceededException: <p>Provides information about an error that occurred due to one or more service quotas for an account.</p>
        capo_macie2.errors.throttling_exception.ThrottlingException: <p>Provides information about an error that occurred because too many requests were sent during a certain amount of time.</p>
        capo_macie2.errors.validation_exception.ValidationException: <p>Provides information about an error that occurred due to a syntax error in a request.</p>
        capo_macie2.errors.UnknownServiceError: The service returned an error code this client does not model.
    """

    async def _handler(
        req: "AsyncOperationRequest[capo_macie2.types.create_classification_job_request.CreateClassificationJobRequest]",
    ) -> AsyncOperationResponse[
        "capo_macie2.types.create_classification_job_response.CreateClassificationJobResponse"
    ]:
        import capo_macie2._operations.macie2.create_classification_job

        (
            output,
            http_response,
        ) = await capo_macie2._operations.macie2.create_classification_job.async_create_classification_job(
            req.options, req.input
        )
        return AsyncOperationResponse(output=output, response=http_response)

    interceptors_, options_ = self.operation_options(
        config_overrides, OperationLogging("CreateClassificationJob")
    )
    input_: capo_macie2.types.create_classification_job_request.CreateClassificationJobRequest = {}
    if allow_list_ids is not None:
        input_["allow_list_ids"] = allow_list_ids
    if client_token is None:
        client_token = str(uuid.uuid4())
    input_["client_token"] = client_token
    if custom_data_identifier_ids is not None:
        input_["custom_data_identifier_ids"] = custom_data_identifier_ids
    if description is not None:
        input_["description"] = description
    if initial_run is not None:
        input_["initial_run"] = initial_run
    if job_type is not None:
        input_["job_type"] = job_type
    if managed_data_identifier_ids is not None:
        input_["managed_data_identifier_ids"] = managed_data_identifier_ids
    if managed_data_identifier_selector is not None:
        input_["managed_data_identifier_selector"] = (
            managed_data_identifier_selector
        )
    if name is not None:
        input_["name"] = name
    if s3_job_definition is not None:
        input_["s3_job_definition"] = s3_job_definition
    if sampling_percentage is not None:
        input_["sampling_percentage"] = sampling_percentage
    if schedule_frequency is not None:
        input_["schedule_frequency"] = schedule_frequency
    if tags is not None:
        input_["tags"] = tags

    response = await aexecute_pipeline(
        AsyncOperationRequest(input=input_, options=options_),
        handler=_handler,
        interceptors=list(interceptors_),
    )
    await response.response.aclose()
    return response.output