detect_document_text ¶

def detect_document_text(
    self,
    document: "capo_textract.types.document.Document",
    *,
    config_overrides: Optional[TextractClientConfig] = None,
) -> "capo_textract.types.detect_document_text_response.DetectDocumentTextResponse":
    """<p>Detects text in the input document. Amazon Textract can detect lines of text and the words that make up a line of text. The input document must be in one of the following image formats: JPEG, PNG, PDF, or TIFF. <code>DetectDocumentText</code> returns the detected text in 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> <code>DetectDocumentText</code> is a synchronous operation. To analyze documents asynchronously, use <a>StartDocumentTextDetection</a>.</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:
        document: <p>The input document as base64-encoded bytes or an Amazon S3 object. If you use the AWS CLI to call Amazon Textract operations, you can't pass image bytes. The document must be an image in JPEG or PNG format.</p> <p>If you're using an AWS SDK to call Amazon Textract, you might not need to base64-encode image bytes that are passed using the <code>Bytes</code> field. </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.internal_server_error.InternalServerError: <p>Amazon Textract experienced a service issue. Try your call again.</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.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.detect_document_text_request.DetectDocumentTextRequest]",
    ) -> OperationResponse[
        "capo_textract.types.detect_document_text_response.DetectDocumentTextResponse"
    ]:
        import capo_textract._operations.textract.detect_document_text

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

    interceptors_, options_ = self.operation_options(
        config_overrides, OperationLogging("DetectDocumentText")
    )
    input_: capo_textract.types.detect_document_text_request.DetectDocumentTextRequest = {
        "document": document
    }

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