get_document_text_detection ¶

def get_document_text_detection(
    self,
    job_id: "capo_textract.types.job_id.JobId",
    *,
    config_overrides: Optional[TextractClientConfig] = None,
    max_results: Optional["capo_textract.types.max_results.MaxResults"] = None,
    next_token: Optional[
        "capo_textract.types.pagination_token.PaginationToken"
    ] = None,
) -> "capo_textract.types.get_document_text_detection_response.GetDocumentTextDetectionResponse":
    """<p>Gets the results for an Amazon Textract asynchronous operation that detects text in a document. Amazon Textract can detect lines of text and the words that make up a line of text.</p> <p>You start asynchronous text detection by calling <a>StartDocumentTextDetection</a>, which returns a job identifier (<code>JobId</code>). When the text detection operation finishes, Amazon Textract publishes a completion status to the Amazon Simple Notification Service (Amazon SNS) topic that's registered in the initial call to <code>StartDocumentTextDetection</code>. To get the results of the text-detection operation, first check that the status value published to the Amazon SNS topic is <code>SUCCEEDED</code>. If so, call <code>GetDocumentTextDetection</code>, and pass the job identifier (<code>JobId</code>) from the initial call to <code>StartDocumentTextDetection</code>.</p> <p> <code>GetDocumentTextDetection</code> returns an array of <a>Block</a> objects. </p> <p>Each document page has as an associated <code>Block</code> of type PAGE. Each PAGE <code>Block</code> object is the parent of LINE <code>Block</code> objects that represent the lines of detected text on a page. A LINE <code>Block</code> object is a parent for each word that makes up the line. Words are represented by <code>Block</code> objects of type WORD.</p> <p>Use the MaxResults parameter to limit the number of blocks that are returned. If there are more results than specified in <code>MaxResults</code>, the value of <code>NextToken</code> in the operation response contains a pagination token for getting the next set of results. To get the next page of results, call <code>GetDocumentTextDetection</code>, and populate the <code>NextToken</code> request parameter with the token value that's returned from the previous call to <code>GetDocumentTextDetection</code>.</p> <p>For more information, see <a href="https://docs.aws.amazon.com/textract/latest/dg/how-it-works-detecting.html">Document Text Detection</a>.</p>

    Args:
        job_id: <p>A unique identifier for the text detection job. The <code>JobId</code> is returned from <code>StartDocumentTextDetection</code>. A <code>JobId</code> value is only valid for 7 days.</p>
        max_results: <p>The maximum number of results to return per paginated call. The largest value you can specify is 1,000. If you specify a value greater than 1,000, a maximum of 1,000 results is returned. The default value is 1,000.</p>
        next_token: <p>If the previous response was incomplete (because there are more blocks to retrieve), Amazon Textract returns a pagination token in the response. You can use this pagination token to retrieve the next set of blocks.</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.internal_server_error.InternalServerError: <p>Amazon Textract experienced a service issue. Try your call again.</p>
        capo_textract.errors.invalid_job_id_exception.InvalidJobIdException: <p>An invalid job identifier was passed to an asynchronous analysis operation.</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.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.UnknownServiceError: The service returned an error code this client does not model.
    """

    def _handler(
        req: "OperationRequest[capo_textract.types.get_document_text_detection_request.GetDocumentTextDetectionRequest]",
    ) -> OperationResponse[
        "capo_textract.types.get_document_text_detection_response.GetDocumentTextDetectionResponse"
    ]:
        import capo_textract._operations.textract.get_document_text_detection

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

    interceptors_, options_ = self.operation_options(
        config_overrides, OperationLogging("GetDocumentTextDetection")
    )
    input_: capo_textract.types.get_document_text_detection_request.GetDocumentTextDetectionRequest = {
        "job_id": job_id
    }
    if max_results is not None:
        input_["max_results"] = max_results
    if next_token is not None:
        input_["next_token"] = next_token

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