start_expense_analysis ¶

def start_expense_analysis(
    self,
    document_location: "capo_textract.types.document_location.DocumentLocation",
    *,
    config_overrides: Optional[TextractClientConfig] = None,
    client_request_token: Optional[
        "capo_textract.types.client_request_token.ClientRequestToken"
    ] = None,
    job_tag: Optional["capo_textract.types.job_tag.JobTag"] = None,
    notification_channel: Optional[
        "capo_textract.types.notification_channel.NotificationChannel"
    ] = None,
    output_config: Optional[
        "capo_textract.types.output_config.OutputConfig"
    ] = None,
    kms_key_id: Optional["capo_textract.types.kms_key_id.KMSKeyId"] = None,
) -> "capo_textract.types.start_expense_analysis_response.StartExpenseAnalysisResponse":
    """<p>Starts the asynchronous analysis of invoices or receipts for data like contact information, items purchased, and vendor names.</p> <p> <code>StartExpenseAnalysis</code> can analyze text in documents that are in JPEG, PNG, and PDF format. The documents must be stored in an Amazon S3 bucket. Use the <a>DocumentLocation</a> parameter to specify the name of your S3 bucket and the name of the document in that bucket. </p> <p> <code>StartExpenseAnalysis</code> returns a job identifier (<code>JobId</code>) that you will provide to <code>GetExpenseAnalysis</code> to retrieve the results of the operation. When the analysis of the input invoices/receipts is finished, Amazon Textract publishes a completion status to the Amazon Simple Notification Service (Amazon SNS) topic that you provide to the <code>NotificationChannel</code>. To obtain the results of the invoice and receipt analysis operation, ensure that the status value published to the Amazon SNS topic is <code>SUCCEEDED</code>. If so, call <a>GetExpenseAnalysis</a>, and pass the job identifier (<code>JobId</code>) that was returned by your call to <code>StartExpenseAnalysis</code>.</p> <p>For more information, see <a href="https://docs.aws.amazon.com/textract/latest/dg/invoice-receipts.html">Analyzing Invoices and Receipts</a>.</p>

    Args:
        document_location: <p>The location of the document to be processed.</p>
        client_request_token: <p>The idempotent token that's used to identify the start request. If you use the same token with multiple <code>StartDocumentTextDetection</code> requests, the same <code>JobId</code> is returned. Use <code>ClientRequestToken</code> to prevent the same job from being accidentally started more than once. For more information, see <a href="https://docs.aws.amazon.com/textract/latest/dg/api-async.html">Calling Amazon Textract Asynchronous Operations</a> </p>
        job_tag: <p>An identifier you specify that's included in the completion notification published to the Amazon SNS topic. For example, you can use <code>JobTag</code> to identify the type of document that the completion notification corresponds to (such as a tax form or a receipt).</p>
        notification_channel: <p>The Amazon SNS topic ARN that you want Amazon Textract to publish the completion status of the operation to. </p>
        output_config: <p>Sets if the output will go to a customer defined bucket. By default, Amazon Textract will save the results internally to be accessed by the <code>GetExpenseAnalysis</code> operation.</p>
        kms_key_id: <p>The KMS key used to encrypt the inference results. This can be in either Key ID or Key Alias format. When a KMS key is provided, the KMS key will be used for server-side encryption of the objects in the customer bucket. When this parameter is not enabled, the result will be encrypted server side,using SSE-S3.</p>

    Raises:
        capo_textract.errors.access_denied_exception.AccessDeniedException: <p>You aren't authorized to perform the action. Use the Amazon Resource Name (ARN) of an authorized user or IAM role to perform the operation.</p>
        capo_textract.errors.bad_document_exception.BadDocumentException: <p>Amazon Textract isn't able to read the document. For more information on the document limits in Amazon Textract, see <a href="https://docs.aws.amazon.com/textract/latest/dg/limits.html">Hard limits</a>.</p>
        capo_textract.errors.document_too_large_exception.DocumentTooLargeException: <p>The document can't be processed because it's too large. The maximum document size for synchronous operations 10 MB. The maximum document size for asynchronous operations is 500 MB for PDF files.</p>
        capo_textract.errors.idempotent_parameter_mismatch_exception.IdempotentParameterMismatchException: <p>A <code>ClientRequestToken</code> input parameter was reused with an operation, but at least one of the other input parameters is different from the previous call to the operation. </p>
        capo_textract.errors.internal_server_error.InternalServerError: <p>Amazon Textract experienced a service issue. Try your call again.</p>
        capo_textract.errors.invalid_kms_key_exception.InvalidKMSKeyException: <p> Indicates you do not have decrypt permissions with the KMS key entered, or the KMS key was entered incorrectly. </p>
        capo_textract.errors.invalid_parameter_exception.InvalidParameterException: <p>An input parameter violated a constraint. For example, in synchronous operations, an <code>InvalidParameterException</code> exception occurs when neither of the <code>S3Object</code> or <code>Bytes</code> values are supplied in the <code>Document</code> request parameter. Validate your parameter before calling the API operation again.</p>
        capo_textract.errors.invalid_s3_object_exception.InvalidS3ObjectException: <p>Amazon Textract is unable to access the S3 object that's specified in the request. for more information, <a href="https://docs.aws.amazon.com/AmazonS3/latest/dev/s3-access-control.html">Configure Access to Amazon S3</a> For troubleshooting information, see <a href="https://docs.aws.amazon.com/AmazonS3/latest/dev/troubleshooting.html">Troubleshooting Amazon S3</a> </p>
        capo_textract.errors.limit_exceeded_exception.LimitExceededException: <p>An Amazon Textract service limit was exceeded. For example, if you start too many asynchronous jobs concurrently, calls to start operations (<code>StartDocumentTextDetection</code>, for example) raise a LimitExceededException exception (HTTP status code: 400) until the number of concurrently running jobs is below the Amazon Textract service limit. </p>
        capo_textract.errors.provisioned_throughput_exceeded_exception.ProvisionedThroughputExceededException: <p>The number of requests exceeded your throughput limit. If you want to increase this limit, contact Amazon Textract.</p>
        capo_textract.errors.throttling_exception.ThrottlingException: <p>Amazon Textract is temporarily unable to process the request. Try your call again.</p>
        capo_textract.errors.unsupported_document_exception.UnsupportedDocumentException: <p>The format of the input document isn't supported. Documents for operations can be in PNG, JPEG, PDF, or TIFF format.</p>
        capo_textract.errors.UnknownServiceError: The service returned an error code this client does not model.
    """

    def _handler(
        req: "OperationRequest[capo_textract.types.start_expense_analysis_request.StartExpenseAnalysisRequest]",
    ) -> OperationResponse[
        "capo_textract.types.start_expense_analysis_response.StartExpenseAnalysisResponse"
    ]:
        import capo_textract._operations.textract.start_expense_analysis

        output, http_response = (
            capo_textract._operations.textract.start_expense_analysis.start_expense_analysis(
                req.options, req.input
            )
        )
        return OperationResponse(output=output, response=http_response)

    interceptors_, options_ = self.operation_options(
        config_overrides, OperationLogging("StartExpenseAnalysis")
    )
    input_: capo_textract.types.start_expense_analysis_request.StartExpenseAnalysisRequest = {
        "document_location": document_location
    }
    if client_request_token is not None:
        input_["client_request_token"] = client_request_token
    if job_tag is not None:
        input_["job_tag"] = job_tag
    if notification_channel is not None:
        input_["notification_channel"] = notification_channel
    if output_config is not None:
        input_["output_config"] = output_config
    if kms_key_id is not None:
        input_["kms_key_id"] = kms_key_id

    response = execute_pipeline(
        OperationRequest(input=input_, options=options_),
        handler=_handler,
        interceptors=list(interceptors_),
    )
    response.response.close()
    return response.output