get_document_analysis async ¶

async def get_document_analysis(
    self,
    job_id: "capo_textract.types.job_id.JobId",
    *,
    config_overrides: Optional[AsyncTextractClientConfig] = 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_analysis_response.GetDocumentAnalysisResponse"
):
    """<p>Gets the results for an Amazon Textract asynchronous operation that analyzes text in a document.</p> <p>You start asynchronous text analysis by calling <a>StartDocumentAnalysis</a>, which returns a job identifier (<code>JobId</code>). When the text analysis 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>StartDocumentAnalysis</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>GetDocumentAnalysis</code>, and pass the job identifier (<code>JobId</code>) from the initial call to <code>StartDocumentAnalysis</code>.</p> <p> <code>GetDocumentAnalysis</code> returns an array of <a>Block</a> objects. The following types of information are returned: </p> <ul> <li> <p>Form data (key-value pairs). The related information is returned in two <a>Block</a> objects, each of type <code>KEY_VALUE_SET</code>: a KEY <code>Block</code> object and a VALUE <code>Block</code> object. For example, <i>Name: Ana Silva Carolina</i> contains a key and value. <i>Name:</i> is the key. <i>Ana Silva Carolina</i> is the value.</p> </li> <li> <p>Table and table cell data. A TABLE <code>Block</code> object contains information about a detected table. A CELL <code>Block</code> object is returned for each cell in a table.</p> </li> <li> <p>Lines and words of text. A LINE <code>Block</code> object contains one or more WORD <code>Block</code> objects. All lines and words that are detected in the document are returned (including text that doesn't have a relationship with the value of the <code>StartDocumentAnalysis</code> <code>FeatureTypes</code> input parameter). </p> </li> <li> <p>Query. A QUERY Block object contains the query text, alias and link to the associated Query results block object.</p> </li> <li> <p>Query Results. A QUERY_RESULT Block object contains the answer to the query and an ID that connects it to the query asked. This Block also contains a confidence score.</p> </li> </ul> <note> <p>While processing a document with queries, look out for <code>INVALID_REQUEST_PARAMETERS</code> output. This indicates that either the per page query limit has been exceeded or that the operation is trying to query a page in the document which doesn’t exist. </p> </note> <p>Selection elements such as check boxes and option buttons (radio buttons) can be detected in form data and in tables. A SELECTION_ELEMENT <code>Block</code> object contains information about a selection element, including the selection status.</p> <p>Use the <code>MaxResults</code> 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>GetDocumentAnalysis</code>, and populate the <code>NextToken</code> request parameter with the token value that's returned from the previous call to <code>GetDocumentAnalysis</code>.</p> <p>For more information, see <a href="https://docs.aws.amazon.com/textract/latest/dg/how-it-works-analyzing.html">Document Text Analysis</a>.</p>

    Args:
        job_id: <p>A unique identifier for the text-detection job. The <code>JobId</code> is returned from <code>StartDocumentAnalysis</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 that 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.
    """

    async def _handler(
        req: "AsyncOperationRequest[capo_textract.types.get_document_analysis_request.GetDocumentAnalysisRequest]",
    ) -> AsyncOperationResponse[
        "capo_textract.types.get_document_analysis_response.GetDocumentAnalysisResponse"
    ]:
        import capo_textract._operations.textract.get_document_analysis

        (
            output,
            http_response,
        ) = await capo_textract._operations.textract.get_document_analysis.async_get_document_analysis(
            req.options, req.input
        )
        return AsyncOperationResponse(output=output, response=http_response)

    interceptors_, options_ = self.operation_options(
        config_overrides, OperationLogging("GetDocumentAnalysis")
    )
    input_: capo_textract.types.get_document_analysis_request.GetDocumentAnalysisRequest = {
        "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 = await aexecute_pipeline(
        AsyncOperationRequest(input=input_, options=options_),
        handler=_handler,
        interceptors=list(interceptors_),
    )
    await response.response.aclose()
    return response.output