/* * Copyright 2018-2023 Amazon.com, Inc. or its affiliates. All Rights Reserved. * * Licensed under the Apache License, Version 2.0 (the "License"). You may not use this file except in compliance with * the License. A copy of the License is located at * * http://aws.amazon.com/apache2.0 * * or in the "license" file accompanying this file. This file is distributed on an "AS IS" BASIS, WITHOUT WARRANTIES OR * CONDITIONS OF ANY KIND, either express or implied. See the License for the specific language governing permissions * and limitations under the License. */ package com.amazonaws.services.textract; import org.w3c.dom.*; import java.net.*; import java.util.*; import javax.annotation.Generated; import org.apache.commons.logging.*; import com.amazonaws.*; import com.amazonaws.annotation.SdkInternalApi; import com.amazonaws.auth.*; import com.amazonaws.handlers.*; import com.amazonaws.http.*; import com.amazonaws.internal.*; import com.amazonaws.internal.auth.*; import com.amazonaws.metrics.*; import com.amazonaws.regions.*; import com.amazonaws.transform.*; import com.amazonaws.util.*; import com.amazonaws.protocol.json.*; import com.amazonaws.util.AWSRequestMetrics.Field; import com.amazonaws.annotation.ThreadSafe; import com.amazonaws.client.AwsSyncClientParams; import com.amazonaws.client.builder.AdvancedConfig; import com.amazonaws.services.textract.AmazonTextractClientBuilder; import com.amazonaws.AmazonServiceException; import com.amazonaws.services.textract.model.*; import com.amazonaws.services.textract.model.transform.*; /** * Client for accessing Amazon Textract. All service calls made using this client are blocking, and will not return * until the service call completes. *

*

* Amazon Textract detects and analyzes text in documents and converts it into machine-readable text. This is the API * reference documentation for Amazon Textract. *

*/ @ThreadSafe @Generated("com.amazonaws:aws-java-sdk-code-generator") public class AmazonTextractClient extends AmazonWebServiceClient implements AmazonTextract { /** Provider for AWS credentials. */ private final AWSCredentialsProvider awsCredentialsProvider; private static final Log log = LogFactory.getLog(AmazonTextract.class); /** Default signing name for the service. */ private static final String DEFAULT_SIGNING_NAME = "textract"; /** Client configuration factory providing ClientConfigurations tailored to this client */ protected static final ClientConfigurationFactory configFactory = new ClientConfigurationFactory(); private final AdvancedConfig advancedConfig; private static final com.amazonaws.protocol.json.SdkJsonProtocolFactory protocolFactory = new com.amazonaws.protocol.json.SdkJsonProtocolFactory( new JsonClientMetadata() .withProtocolVersion("1.1") .withSupportsCbor(false) .withSupportsIon(false) .addErrorMetadata( new JsonErrorShapeMetadata().withErrorCode("AccessDeniedException").withExceptionUnmarshaller( com.amazonaws.services.textract.model.transform.AccessDeniedExceptionUnmarshaller.getInstance())) .addErrorMetadata( new JsonErrorShapeMetadata().withErrorCode("BadDocumentException").withExceptionUnmarshaller( com.amazonaws.services.textract.model.transform.BadDocumentExceptionUnmarshaller.getInstance())) .addErrorMetadata( new JsonErrorShapeMetadata().withErrorCode("InvalidParameterException").withExceptionUnmarshaller( com.amazonaws.services.textract.model.transform.InvalidParameterExceptionUnmarshaller.getInstance())) .addErrorMetadata( new JsonErrorShapeMetadata().withErrorCode("InvalidKMSKeyException").withExceptionUnmarshaller( com.amazonaws.services.textract.model.transform.InvalidKMSKeyExceptionUnmarshaller.getInstance())) .addErrorMetadata( new JsonErrorShapeMetadata().withErrorCode("ThrottlingException").withExceptionUnmarshaller( com.amazonaws.services.textract.model.transform.ThrottlingExceptionUnmarshaller.getInstance())) .addErrorMetadata( new JsonErrorShapeMetadata().withErrorCode("IdempotentParameterMismatchException").withExceptionUnmarshaller( com.amazonaws.services.textract.model.transform.IdempotentParameterMismatchExceptionUnmarshaller.getInstance())) .addErrorMetadata( new JsonErrorShapeMetadata().withErrorCode("HumanLoopQuotaExceededException").withExceptionUnmarshaller( com.amazonaws.services.textract.model.transform.HumanLoopQuotaExceededExceptionUnmarshaller.getInstance())) .addErrorMetadata( new JsonErrorShapeMetadata().withErrorCode("DocumentTooLargeException").withExceptionUnmarshaller( com.amazonaws.services.textract.model.transform.DocumentTooLargeExceptionUnmarshaller.getInstance())) .addErrorMetadata( new JsonErrorShapeMetadata().withErrorCode("ProvisionedThroughputExceededException").withExceptionUnmarshaller( com.amazonaws.services.textract.model.transform.ProvisionedThroughputExceededExceptionUnmarshaller.getInstance())) .addErrorMetadata( new JsonErrorShapeMetadata().withErrorCode("UnsupportedDocumentException").withExceptionUnmarshaller( com.amazonaws.services.textract.model.transform.UnsupportedDocumentExceptionUnmarshaller.getInstance())) .addErrorMetadata( new JsonErrorShapeMetadata().withErrorCode("InvalidJobIdException").withExceptionUnmarshaller( com.amazonaws.services.textract.model.transform.InvalidJobIdExceptionUnmarshaller.getInstance())) .addErrorMetadata( new JsonErrorShapeMetadata().withErrorCode("InvalidS3ObjectException").withExceptionUnmarshaller( com.amazonaws.services.textract.model.transform.InvalidS3ObjectExceptionUnmarshaller.getInstance())) .addErrorMetadata( new JsonErrorShapeMetadata().withErrorCode("InternalServerError").withExceptionUnmarshaller( com.amazonaws.services.textract.model.transform.InternalServerErrorExceptionUnmarshaller.getInstance())) .addErrorMetadata( new JsonErrorShapeMetadata().withErrorCode("LimitExceededException").withExceptionUnmarshaller( com.amazonaws.services.textract.model.transform.LimitExceededExceptionUnmarshaller.getInstance())) .withBaseServiceExceptionClass(com.amazonaws.services.textract.model.AmazonTextractException.class)); public static AmazonTextractClientBuilder builder() { return AmazonTextractClientBuilder.standard(); } /** * Constructs a new client to invoke service methods on Amazon Textract using the specified parameters. * *

* All service calls made using this new client object are blocking, and will not return until the service call * completes. * * @param clientParams * Object providing client parameters. */ AmazonTextractClient(AwsSyncClientParams clientParams) { this(clientParams, false); } /** * Constructs a new client to invoke service methods on Amazon Textract using the specified parameters. * *

* All service calls made using this new client object are blocking, and will not return until the service call * completes. * * @param clientParams * Object providing client parameters. */ AmazonTextractClient(AwsSyncClientParams clientParams, boolean endpointDiscoveryEnabled) { super(clientParams); this.awsCredentialsProvider = clientParams.getCredentialsProvider(); this.advancedConfig = clientParams.getAdvancedConfig(); init(); } private void init() { setServiceNameIntern(DEFAULT_SIGNING_NAME); setEndpointPrefix(ENDPOINT_PREFIX); // calling this.setEndPoint(...) will also modify the signer accordingly setEndpoint("textract.us-east-1.amazonaws.com"); HandlerChainFactory chainFactory = new HandlerChainFactory(); requestHandler2s.addAll(chainFactory.newRequestHandlerChain("/com/amazonaws/services/textract/request.handlers")); requestHandler2s.addAll(chainFactory.newRequestHandler2Chain("/com/amazonaws/services/textract/request.handler2s")); requestHandler2s.addAll(chainFactory.getGlobalHandlers()); } /** *

* Analyzes an input document for relationships between detected items. *

*

* The types of information returned are as follows: *

* *

* Selection elements such as check boxes and option buttons (radio buttons) can be detected in form data and in * tables. A SELECTION_ELEMENT Block object contains information about a selection element, including * the selection status. *

*

* You can choose which type of analysis to perform by specifying the FeatureTypes list. *

*

* The output is returned in a list of Block objects. *

*

* AnalyzeDocument is a synchronous operation. To analyze documents asynchronously, use * StartDocumentAnalysis. *

*

* For more information, see Document Text Analysis. *

* * @param analyzeDocumentRequest * @return Result of the AnalyzeDocument operation returned by the service. * @throws InvalidParameterException * An input parameter violated a constraint. For example, in synchronous operations, an * InvalidParameterException exception occurs when neither of the S3Object or * Bytes values are supplied in the Document request parameter. Validate your * parameter before calling the API operation again. * @throws InvalidS3ObjectException * Amazon Textract is unable to access the S3 object that's specified in the request. for more information, * Configure Access to * Amazon S3 For troubleshooting information, see Troubleshooting Amazon S3 * @throws UnsupportedDocumentException * The format of the input document isn't supported. Documents for operations can be in PNG, JPEG, PDF, or * TIFF format. * @throws DocumentTooLargeException * 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. * @throws BadDocumentException * Amazon Textract isn't able to read the document. For more information on the document limits in Amazon * Textract, see limits. * @throws AccessDeniedException * 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. * @throws ProvisionedThroughputExceededException * The number of requests exceeded your throughput limit. If you want to increase this limit, contact Amazon * Textract. * @throws InternalServerErrorException * Amazon Textract experienced a service issue. Try your call again. * @throws ThrottlingException * Amazon Textract is temporarily unable to process the request. Try your call again. * @throws HumanLoopQuotaExceededException * Indicates you have exceeded the maximum number of active human in the loop workflows available * @sample AmazonTextract.AnalyzeDocument * @see AWS API * Documentation */ @Override public AnalyzeDocumentResult analyzeDocument(AnalyzeDocumentRequest request) { request = beforeClientExecution(request); return executeAnalyzeDocument(request); } @SdkInternalApi final AnalyzeDocumentResult executeAnalyzeDocument(AnalyzeDocumentRequest analyzeDocumentRequest) { ExecutionContext executionContext = createExecutionContext(analyzeDocumentRequest); AWSRequestMetrics awsRequestMetrics = executionContext.getAwsRequestMetrics(); awsRequestMetrics.startEvent(Field.ClientExecuteTime); Request request = null; Response response = null; try { awsRequestMetrics.startEvent(Field.RequestMarshallTime); try { request = new AnalyzeDocumentRequestProtocolMarshaller(protocolFactory).marshall(super.beforeMarshalling(analyzeDocumentRequest)); // Binds the request metrics to the current request. request.setAWSRequestMetrics(awsRequestMetrics); request.addHandlerContext(HandlerContextKey.CLIENT_ENDPOINT, endpoint); request.addHandlerContext(HandlerContextKey.ENDPOINT_OVERRIDDEN, isEndpointOverridden()); request.addHandlerContext(HandlerContextKey.SIGNING_REGION, getSigningRegion()); request.addHandlerContext(HandlerContextKey.SERVICE_ID, "Textract"); request.addHandlerContext(HandlerContextKey.OPERATION_NAME, "AnalyzeDocument"); request.addHandlerContext(HandlerContextKey.ADVANCED_CONFIG, advancedConfig); } finally { awsRequestMetrics.endEvent(Field.RequestMarshallTime); } HttpResponseHandler> responseHandler = protocolFactory.createResponseHandler( new JsonOperationMetadata().withPayloadJson(true).withHasStreamingSuccessResponse(false), new AnalyzeDocumentResultJsonUnmarshaller()); response = invoke(request, responseHandler, executionContext); return response.getAwsResponse(); } finally { endClientExecution(awsRequestMetrics, request, response); } } /** *

* AnalyzeExpense synchronously analyzes an input document for financially related relationships * between text. *

*

* Information is returned as ExpenseDocuments and seperated as follows: *

*
    *
  • *

    * LineItemGroups- A data set containing LineItems which store information about the lines * of text, such as an item purchased and its price on a receipt. *

    *
    • *
  • *

    * SummaryFields- Contains all other information a receipt, such as header information or the vendors * name. *

    *
    • *
* * @param analyzeExpenseRequest * @return Result of the AnalyzeExpense operation returned by the service. * @throws InvalidParameterException * An input parameter violated a constraint. For example, in synchronous operations, an * InvalidParameterException exception occurs when neither of the S3Object or * Bytes values are supplied in the Document request parameter. Validate your * parameter before calling the API operation again. * @throws InvalidS3ObjectException * Amazon Textract is unable to access the S3 object that's specified in the request. for more information, * Configure Access to * Amazon S3 For troubleshooting information, see Troubleshooting Amazon S3 * @throws UnsupportedDocumentException * The format of the input document isn't supported. Documents for operations can be in PNG, JPEG, PDF, or * TIFF format. * @throws DocumentTooLargeException * 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. * @throws BadDocumentException * Amazon Textract isn't able to read the document. For more information on the document limits in Amazon * Textract, see limits. * @throws AccessDeniedException * 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. * @throws ProvisionedThroughputExceededException * The number of requests exceeded your throughput limit. If you want to increase this limit, contact Amazon * Textract. * @throws InternalServerErrorException * Amazon Textract experienced a service issue. Try your call again. * @throws ThrottlingException * Amazon Textract is temporarily unable to process the request. Try your call again. * @sample AmazonTextract.AnalyzeExpense * @see AWS API * Documentation */ @Override public AnalyzeExpenseResult analyzeExpense(AnalyzeExpenseRequest request) { request = beforeClientExecution(request); return executeAnalyzeExpense(request); } @SdkInternalApi final AnalyzeExpenseResult executeAnalyzeExpense(AnalyzeExpenseRequest analyzeExpenseRequest) { ExecutionContext executionContext = createExecutionContext(analyzeExpenseRequest); AWSRequestMetrics awsRequestMetrics = executionContext.getAwsRequestMetrics(); awsRequestMetrics.startEvent(Field.ClientExecuteTime); Request request = null; Response response = null; try { awsRequestMetrics.startEvent(Field.RequestMarshallTime); try { request = new AnalyzeExpenseRequestProtocolMarshaller(protocolFactory).marshall(super.beforeMarshalling(analyzeExpenseRequest)); // Binds the request metrics to the current request. request.setAWSRequestMetrics(awsRequestMetrics); request.addHandlerContext(HandlerContextKey.CLIENT_ENDPOINT, endpoint); request.addHandlerContext(HandlerContextKey.ENDPOINT_OVERRIDDEN, isEndpointOverridden()); request.addHandlerContext(HandlerContextKey.SIGNING_REGION, getSigningRegion()); request.addHandlerContext(HandlerContextKey.SERVICE_ID, "Textract"); request.addHandlerContext(HandlerContextKey.OPERATION_NAME, "AnalyzeExpense"); request.addHandlerContext(HandlerContextKey.ADVANCED_CONFIG, advancedConfig); } finally { awsRequestMetrics.endEvent(Field.RequestMarshallTime); } HttpResponseHandler> responseHandler = protocolFactory.createResponseHandler( new JsonOperationMetadata().withPayloadJson(true).withHasStreamingSuccessResponse(false), new AnalyzeExpenseResultJsonUnmarshaller()); response = invoke(request, responseHandler, executionContext); return response.getAwsResponse(); } finally { endClientExecution(awsRequestMetrics, request, response); } } /** *

* Analyzes identity documents for relevant information. This information is extracted and returned as * IdentityDocumentFields, which records both the normalized field and value of the extracted text. * Unlike other Amazon Textract operations, AnalyzeID doesn't return any Geometry data. *

* * @param analyzeIDRequest * @return Result of the AnalyzeID operation returned by the service. * @throws InvalidParameterException * An input parameter violated a constraint. For example, in synchronous operations, an * InvalidParameterException exception occurs when neither of the S3Object or * Bytes values are supplied in the Document request parameter. Validate your * parameter before calling the API operation again. * @throws InvalidS3ObjectException * Amazon Textract is unable to access the S3 object that's specified in the request. for more information, * Configure Access to * Amazon S3 For troubleshooting information, see Troubleshooting Amazon S3 * @throws UnsupportedDocumentException * The format of the input document isn't supported. Documents for operations can be in PNG, JPEG, PDF, or * TIFF format. * @throws DocumentTooLargeException * 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. * @throws BadDocumentException * Amazon Textract isn't able to read the document. For more information on the document limits in Amazon * Textract, see limits. * @throws AccessDeniedException * 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. * @throws ProvisionedThroughputExceededException * The number of requests exceeded your throughput limit. If you want to increase this limit, contact Amazon * Textract. * @throws InternalServerErrorException * Amazon Textract experienced a service issue. Try your call again. * @throws ThrottlingException * Amazon Textract is temporarily unable to process the request. Try your call again. * @sample AmazonTextract.AnalyzeID * @see AWS API * Documentation */ @Override public AnalyzeIDResult analyzeID(AnalyzeIDRequest request) { request = beforeClientExecution(request); return executeAnalyzeID(request); } @SdkInternalApi final AnalyzeIDResult executeAnalyzeID(AnalyzeIDRequest analyzeIDRequest) { ExecutionContext executionContext = createExecutionContext(analyzeIDRequest); AWSRequestMetrics awsRequestMetrics = executionContext.getAwsRequestMetrics(); awsRequestMetrics.startEvent(Field.ClientExecuteTime); Request request = null; Response response = null; try { awsRequestMetrics.startEvent(Field.RequestMarshallTime); try { request = new AnalyzeIDRequestProtocolMarshaller(protocolFactory).marshall(super.beforeMarshalling(analyzeIDRequest)); // Binds the request metrics to the current request. request.setAWSRequestMetrics(awsRequestMetrics); request.addHandlerContext(HandlerContextKey.CLIENT_ENDPOINT, endpoint); request.addHandlerContext(HandlerContextKey.ENDPOINT_OVERRIDDEN, isEndpointOverridden()); request.addHandlerContext(HandlerContextKey.SIGNING_REGION, getSigningRegion()); request.addHandlerContext(HandlerContextKey.SERVICE_ID, "Textract"); request.addHandlerContext(HandlerContextKey.OPERATION_NAME, "AnalyzeID"); request.addHandlerContext(HandlerContextKey.ADVANCED_CONFIG, advancedConfig); } finally { awsRequestMetrics.endEvent(Field.RequestMarshallTime); } HttpResponseHandler> responseHandler = protocolFactory.createResponseHandler(new JsonOperationMetadata() .withPayloadJson(true).withHasStreamingSuccessResponse(false), new AnalyzeIDResultJsonUnmarshaller()); response = invoke(request, responseHandler, executionContext); return response.getAwsResponse(); } finally { endClientExecution(awsRequestMetrics, request, response); } } /** *

* 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. * DetectDocumentText returns the detected text in an array of Block objects. *

*

* Each document page has as an associated Block of type PAGE. Each PAGE Block object is * the parent of LINE Block objects that represent the lines of detected text on a page. A LINE * Block object is a parent for each word that makes up the line. Words are represented by * Block objects of type WORD. *

*

* DetectDocumentText is a synchronous operation. To analyze documents asynchronously, use * StartDocumentTextDetection. *

*

* For more information, see Document Text Detection. *

* * @param detectDocumentTextRequest * @return Result of the DetectDocumentText operation returned by the service. * @throws InvalidParameterException * An input parameter violated a constraint. For example, in synchronous operations, an * InvalidParameterException exception occurs when neither of the S3Object or * Bytes values are supplied in the Document request parameter. Validate your * parameter before calling the API operation again. * @throws InvalidS3ObjectException * Amazon Textract is unable to access the S3 object that's specified in the request. for more information, * Configure Access to * Amazon S3 For troubleshooting information, see Troubleshooting Amazon S3 * @throws UnsupportedDocumentException * The format of the input document isn't supported. Documents for operations can be in PNG, JPEG, PDF, or * TIFF format. * @throws DocumentTooLargeException * 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. * @throws BadDocumentException * Amazon Textract isn't able to read the document. For more information on the document limits in Amazon * Textract, see limits. * @throws AccessDeniedException * 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. * @throws ProvisionedThroughputExceededException * The number of requests exceeded your throughput limit. If you want to increase this limit, contact Amazon * Textract. * @throws InternalServerErrorException * Amazon Textract experienced a service issue. Try your call again. * @throws ThrottlingException * Amazon Textract is temporarily unable to process the request. Try your call again. * @sample AmazonTextract.DetectDocumentText * @see AWS * API Documentation */ @Override public DetectDocumentTextResult detectDocumentText(DetectDocumentTextRequest request) { request = beforeClientExecution(request); return executeDetectDocumentText(request); } @SdkInternalApi final DetectDocumentTextResult executeDetectDocumentText(DetectDocumentTextRequest detectDocumentTextRequest) { ExecutionContext executionContext = createExecutionContext(detectDocumentTextRequest); AWSRequestMetrics awsRequestMetrics = executionContext.getAwsRequestMetrics(); awsRequestMetrics.startEvent(Field.ClientExecuteTime); Request request = null; Response response = null; try { awsRequestMetrics.startEvent(Field.RequestMarshallTime); try { request = new DetectDocumentTextRequestProtocolMarshaller(protocolFactory).marshall(super.beforeMarshalling(detectDocumentTextRequest)); // Binds the request metrics to the current request. request.setAWSRequestMetrics(awsRequestMetrics); request.addHandlerContext(HandlerContextKey.CLIENT_ENDPOINT, endpoint); request.addHandlerContext(HandlerContextKey.ENDPOINT_OVERRIDDEN, isEndpointOverridden()); request.addHandlerContext(HandlerContextKey.SIGNING_REGION, getSigningRegion()); request.addHandlerContext(HandlerContextKey.SERVICE_ID, "Textract"); request.addHandlerContext(HandlerContextKey.OPERATION_NAME, "DetectDocumentText"); request.addHandlerContext(HandlerContextKey.ADVANCED_CONFIG, advancedConfig); } finally { awsRequestMetrics.endEvent(Field.RequestMarshallTime); } HttpResponseHandler> responseHandler = protocolFactory.createResponseHandler( new JsonOperationMetadata().withPayloadJson(true).withHasStreamingSuccessResponse(false), new DetectDocumentTextResultJsonUnmarshaller()); response = invoke(request, responseHandler, executionContext); return response.getAwsResponse(); } finally { endClientExecution(awsRequestMetrics, request, response); } } /** *

* Gets the results for an Amazon Textract asynchronous operation that analyzes text in a document. *

*

* You start asynchronous text analysis by calling StartDocumentAnalysis, which returns a job identifier ( * JobId). 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 * StartDocumentAnalysis. To get the results of the text-detection operation, first check that the * status value published to the Amazon SNS topic is SUCCEEDED. If so, call * GetDocumentAnalysis, and pass the job identifier (JobId) from the initial call to * StartDocumentAnalysis. *

*

* GetDocumentAnalysis returns an array of Block objects. The following types of information are * returned: *

*
    *
  • *

    * Form data (key-value pairs). The related information is returned in two Block objects, each of type * KEY_VALUE_SET: a KEY Block object and a VALUE Block object. For example, * Name: Ana Silva Carolina contains a key and value. Name: is the key. Ana Silva Carolina is * the value. *

    *
    • *
  • *

    * Table and table cell data. A TABLE Block object contains information about a detected table. A CELL * Block object is returned for each cell in a table. *

    *
    • *
  • *

    * Lines and words of text. A LINE Block object contains one or more WORD Block 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 StartDocumentAnalysis FeatureTypes input parameter). *

    *
    • *
  • *

    * Query. A QUERY Block object contains the query text, alias and link to the associated Query results block object. *

    *
    • *
  • *

    * 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. *

    *
    • *
* *

* While processing a document with queries, look out for INVALID_REQUEST_PARAMETERS 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. *

* *

* Selection elements such as check boxes and option buttons (radio buttons) can be detected in form data and in * tables. A SELECTION_ELEMENT Block object contains information about a selection element, including * the selection status. *

*

* Use the MaxResults parameter to limit the number of blocks that are returned. If there are more * results than specified in MaxResults, the value of NextToken in the operation response * contains a pagination token for getting the next set of results. To get the next page of results, call * GetDocumentAnalysis, and populate the NextToken request parameter with the token value * that's returned from the previous call to GetDocumentAnalysis. *

*

* For more information, see Document Text Analysis. *

* * @param getDocumentAnalysisRequest * @return Result of the GetDocumentAnalysis operation returned by the service. * @throws InvalidParameterException * An input parameter violated a constraint. For example, in synchronous operations, an * InvalidParameterException exception occurs when neither of the S3Object or * Bytes values are supplied in the Document request parameter. Validate your * parameter before calling the API operation again. * @throws AccessDeniedException * 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. * @throws ProvisionedThroughputExceededException * The number of requests exceeded your throughput limit. If you want to increase this limit, contact Amazon * Textract. * @throws InvalidJobIdException * An invalid job identifier was passed to an asynchronous analysis operation. * @throws InternalServerErrorException * Amazon Textract experienced a service issue. Try your call again. * @throws ThrottlingException * Amazon Textract is temporarily unable to process the request. Try your call again. * @throws InvalidS3ObjectException * Amazon Textract is unable to access the S3 object that's specified in the request. for more information, * Configure Access to * Amazon S3 For troubleshooting information, see Troubleshooting Amazon S3 * @throws InvalidKMSKeyException * Indicates you do not have decrypt permissions with the KMS key entered, or the KMS key was entered * incorrectly. * @sample AmazonTextract.GetDocumentAnalysis * @see AWS * API Documentation */ @Override public GetDocumentAnalysisResult getDocumentAnalysis(GetDocumentAnalysisRequest request) { request = beforeClientExecution(request); return executeGetDocumentAnalysis(request); } @SdkInternalApi final GetDocumentAnalysisResult executeGetDocumentAnalysis(GetDocumentAnalysisRequest getDocumentAnalysisRequest) { ExecutionContext executionContext = createExecutionContext(getDocumentAnalysisRequest); AWSRequestMetrics awsRequestMetrics = executionContext.getAwsRequestMetrics(); awsRequestMetrics.startEvent(Field.ClientExecuteTime); Request request = null; Response response = null; try { awsRequestMetrics.startEvent(Field.RequestMarshallTime); try { request = new GetDocumentAnalysisRequestProtocolMarshaller(protocolFactory).marshall(super.beforeMarshalling(getDocumentAnalysisRequest)); // Binds the request metrics to the current request. request.setAWSRequestMetrics(awsRequestMetrics); request.addHandlerContext(HandlerContextKey.CLIENT_ENDPOINT, endpoint); request.addHandlerContext(HandlerContextKey.ENDPOINT_OVERRIDDEN, isEndpointOverridden()); request.addHandlerContext(HandlerContextKey.SIGNING_REGION, getSigningRegion()); request.addHandlerContext(HandlerContextKey.SERVICE_ID, "Textract"); request.addHandlerContext(HandlerContextKey.OPERATION_NAME, "GetDocumentAnalysis"); request.addHandlerContext(HandlerContextKey.ADVANCED_CONFIG, advancedConfig); } finally { awsRequestMetrics.endEvent(Field.RequestMarshallTime); } HttpResponseHandler> responseHandler = protocolFactory.createResponseHandler( new JsonOperationMetadata().withPayloadJson(true).withHasStreamingSuccessResponse(false), new GetDocumentAnalysisResultJsonUnmarshaller()); response = invoke(request, responseHandler, executionContext); return response.getAwsResponse(); } finally { endClientExecution(awsRequestMetrics, request, response); } } /** *

* 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. *

*

* You start asynchronous text detection by calling StartDocumentTextDetection, which returns a job * identifier (JobId). 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 StartDocumentTextDetection. To get the results of the text-detection operation, first check * that the status value published to the Amazon SNS topic is SUCCEEDED. If so, call * GetDocumentTextDetection, and pass the job identifier (JobId) from the initial call to * StartDocumentTextDetection. *

*

* GetDocumentTextDetection returns an array of Block objects. *

*

* Each document page has as an associated Block of type PAGE. Each PAGE Block object is * the parent of LINE Block objects that represent the lines of detected text on a page. A LINE * Block object is a parent for each word that makes up the line. Words are represented by * Block objects of type WORD. *

*

* Use the MaxResults parameter to limit the number of blocks that are returned. If there are more results than * specified in MaxResults, the value of NextToken in the operation response contains a * pagination token for getting the next set of results. To get the next page of results, call * GetDocumentTextDetection, and populate the NextToken request parameter with the token * value that's returned from the previous call to GetDocumentTextDetection. *

*

* For more information, see Document Text Detection. *

* * @param getDocumentTextDetectionRequest * @return Result of the GetDocumentTextDetection operation returned by the service. * @throws InvalidParameterException * An input parameter violated a constraint. For example, in synchronous operations, an * InvalidParameterException exception occurs when neither of the S3Object or * Bytes values are supplied in the Document request parameter. Validate your * parameter before calling the API operation again. * @throws AccessDeniedException * 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. * @throws ProvisionedThroughputExceededException * The number of requests exceeded your throughput limit. If you want to increase this limit, contact Amazon * Textract. * @throws InvalidJobIdException * An invalid job identifier was passed to an asynchronous analysis operation. * @throws InternalServerErrorException * Amazon Textract experienced a service issue. Try your call again. * @throws ThrottlingException * Amazon Textract is temporarily unable to process the request. Try your call again. * @throws InvalidS3ObjectException * Amazon Textract is unable to access the S3 object that's specified in the request. for more information, * Configure Access to * Amazon S3 For troubleshooting information, see Troubleshooting Amazon S3 * @throws InvalidKMSKeyException * Indicates you do not have decrypt permissions with the KMS key entered, or the KMS key was entered * incorrectly. * @sample AmazonTextract.GetDocumentTextDetection * @see AWS API Documentation */ @Override public GetDocumentTextDetectionResult getDocumentTextDetection(GetDocumentTextDetectionRequest request) { request = beforeClientExecution(request); return executeGetDocumentTextDetection(request); } @SdkInternalApi final GetDocumentTextDetectionResult executeGetDocumentTextDetection(GetDocumentTextDetectionRequest getDocumentTextDetectionRequest) { ExecutionContext executionContext = createExecutionContext(getDocumentTextDetectionRequest); AWSRequestMetrics awsRequestMetrics = executionContext.getAwsRequestMetrics(); awsRequestMetrics.startEvent(Field.ClientExecuteTime); Request request = null; Response response = null; try { awsRequestMetrics.startEvent(Field.RequestMarshallTime); try { request = new GetDocumentTextDetectionRequestProtocolMarshaller(protocolFactory).marshall(super .beforeMarshalling(getDocumentTextDetectionRequest)); // Binds the request metrics to the current request. request.setAWSRequestMetrics(awsRequestMetrics); request.addHandlerContext(HandlerContextKey.CLIENT_ENDPOINT, endpoint); request.addHandlerContext(HandlerContextKey.ENDPOINT_OVERRIDDEN, isEndpointOverridden()); request.addHandlerContext(HandlerContextKey.SIGNING_REGION, getSigningRegion()); request.addHandlerContext(HandlerContextKey.SERVICE_ID, "Textract"); request.addHandlerContext(HandlerContextKey.OPERATION_NAME, "GetDocumentTextDetection"); request.addHandlerContext(HandlerContextKey.ADVANCED_CONFIG, advancedConfig); } finally { awsRequestMetrics.endEvent(Field.RequestMarshallTime); } HttpResponseHandler> responseHandler = protocolFactory.createResponseHandler( new JsonOperationMetadata().withPayloadJson(true).withHasStreamingSuccessResponse(false), new GetDocumentTextDetectionResultJsonUnmarshaller()); response = invoke(request, responseHandler, executionContext); return response.getAwsResponse(); } finally { endClientExecution(awsRequestMetrics, request, response); } } /** *

* Gets the results for an Amazon Textract asynchronous operation that analyzes invoices and receipts. Amazon * Textract finds contact information, items purchased, and vendor name, from input invoices and receipts. *

*

* You start asynchronous invoice/receipt analysis by calling StartExpenseAnalysis, which returns a job * identifier (JobId). Upon completion of the invoice/receipt analysis, Amazon Textract publishes the * completion status to the Amazon Simple Notification Service (Amazon SNS) topic. This topic must be registered in * the initial call to StartExpenseAnalysis. To get the results of the invoice/receipt analysis * operation, first ensure that the status value published to the Amazon SNS topic is SUCCEEDED. If so, * call GetExpenseAnalysis, and pass the job identifier (JobId) from the initial call to * StartExpenseAnalysis. *

*

* Use the MaxResults parameter to limit the number of blocks that are returned. If there are more results than * specified in MaxResults, the value of NextToken in the operation response contains a * pagination token for getting the next set of results. To get the next page of results, call * GetExpenseAnalysis, and populate the NextToken request parameter with the token value * that's returned from the previous call to GetExpenseAnalysis. *

*

* For more information, see Analyzing Invoices and Receipts. *

* * @param getExpenseAnalysisRequest * @return Result of the GetExpenseAnalysis operation returned by the service. * @throws InvalidParameterException * An input parameter violated a constraint. For example, in synchronous operations, an * InvalidParameterException exception occurs when neither of the S3Object or * Bytes values are supplied in the Document request parameter. Validate your * parameter before calling the API operation again. * @throws AccessDeniedException * 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. * @throws ProvisionedThroughputExceededException * The number of requests exceeded your throughput limit. If you want to increase this limit, contact Amazon * Textract. * @throws InvalidJobIdException * An invalid job identifier was passed to an asynchronous analysis operation. * @throws InternalServerErrorException * Amazon Textract experienced a service issue. Try your call again. * @throws ThrottlingException * Amazon Textract is temporarily unable to process the request. Try your call again. * @throws InvalidS3ObjectException * Amazon Textract is unable to access the S3 object that's specified in the request. for more information, * Configure Access to * Amazon S3 For troubleshooting information, see Troubleshooting Amazon S3 * @throws InvalidKMSKeyException * Indicates you do not have decrypt permissions with the KMS key entered, or the KMS key was entered * incorrectly. * @sample AmazonTextract.GetExpenseAnalysis * @see AWS * API Documentation */ @Override public GetExpenseAnalysisResult getExpenseAnalysis(GetExpenseAnalysisRequest request) { request = beforeClientExecution(request); return executeGetExpenseAnalysis(request); } @SdkInternalApi final GetExpenseAnalysisResult executeGetExpenseAnalysis(GetExpenseAnalysisRequest getExpenseAnalysisRequest) { ExecutionContext executionContext = createExecutionContext(getExpenseAnalysisRequest); AWSRequestMetrics awsRequestMetrics = executionContext.getAwsRequestMetrics(); awsRequestMetrics.startEvent(Field.ClientExecuteTime); Request request = null; Response response = null; try { awsRequestMetrics.startEvent(Field.RequestMarshallTime); try { request = new GetExpenseAnalysisRequestProtocolMarshaller(protocolFactory).marshall(super.beforeMarshalling(getExpenseAnalysisRequest)); // Binds the request metrics to the current request. request.setAWSRequestMetrics(awsRequestMetrics); request.addHandlerContext(HandlerContextKey.CLIENT_ENDPOINT, endpoint); request.addHandlerContext(HandlerContextKey.ENDPOINT_OVERRIDDEN, isEndpointOverridden()); request.addHandlerContext(HandlerContextKey.SIGNING_REGION, getSigningRegion()); request.addHandlerContext(HandlerContextKey.SERVICE_ID, "Textract"); request.addHandlerContext(HandlerContextKey.OPERATION_NAME, "GetExpenseAnalysis"); request.addHandlerContext(HandlerContextKey.ADVANCED_CONFIG, advancedConfig); } finally { awsRequestMetrics.endEvent(Field.RequestMarshallTime); } HttpResponseHandler> responseHandler = protocolFactory.createResponseHandler( new JsonOperationMetadata().withPayloadJson(true).withHasStreamingSuccessResponse(false), new GetExpenseAnalysisResultJsonUnmarshaller()); response = invoke(request, responseHandler, executionContext); return response.getAwsResponse(); } finally { endClientExecution(awsRequestMetrics, request, response); } } /** *

* Gets the results for an Amazon Textract asynchronous operation that analyzes text in a lending document. *

*

* You start asynchronous text analysis by calling StartLendingAnalysis, which returns a job identifier * (JobId). 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 * StartLendingAnalysis. *

*

* To get the results of the text analysis operation, first check that the status value published to the Amazon SNS * topic is SUCCEEDED. If so, call GetLendingAnalysis, and pass the job identifier (JobId) from the * initial call to StartLendingAnalysis. *

* * @param getLendingAnalysisRequest * @return Result of the GetLendingAnalysis operation returned by the service. * @throws InvalidParameterException * An input parameter violated a constraint. For example, in synchronous operations, an * InvalidParameterException exception occurs when neither of the S3Object or * Bytes values are supplied in the Document request parameter. Validate your * parameter before calling the API operation again. * @throws AccessDeniedException * 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. * @throws ProvisionedThroughputExceededException * The number of requests exceeded your throughput limit. If you want to increase this limit, contact Amazon * Textract. * @throws InvalidJobIdException * An invalid job identifier was passed to an asynchronous analysis operation. * @throws InternalServerErrorException * Amazon Textract experienced a service issue. Try your call again. * @throws ThrottlingException * Amazon Textract is temporarily unable to process the request. Try your call again. * @throws InvalidS3ObjectException * Amazon Textract is unable to access the S3 object that's specified in the request. for more information, * Configure Access to * Amazon S3 For troubleshooting information, see Troubleshooting Amazon S3 * @throws InvalidKMSKeyException * Indicates you do not have decrypt permissions with the KMS key entered, or the KMS key was entered * incorrectly. * @sample AmazonTextract.GetLendingAnalysis * @see AWS * API Documentation */ @Override public GetLendingAnalysisResult getLendingAnalysis(GetLendingAnalysisRequest request) { request = beforeClientExecution(request); return executeGetLendingAnalysis(request); } @SdkInternalApi final GetLendingAnalysisResult executeGetLendingAnalysis(GetLendingAnalysisRequest getLendingAnalysisRequest) { ExecutionContext executionContext = createExecutionContext(getLendingAnalysisRequest); AWSRequestMetrics awsRequestMetrics = executionContext.getAwsRequestMetrics(); awsRequestMetrics.startEvent(Field.ClientExecuteTime); Request request = null; Response response = null; try { awsRequestMetrics.startEvent(Field.RequestMarshallTime); try { request = new GetLendingAnalysisRequestProtocolMarshaller(protocolFactory).marshall(super.beforeMarshalling(getLendingAnalysisRequest)); // Binds the request metrics to the current request. request.setAWSRequestMetrics(awsRequestMetrics); request.addHandlerContext(HandlerContextKey.CLIENT_ENDPOINT, endpoint); request.addHandlerContext(HandlerContextKey.ENDPOINT_OVERRIDDEN, isEndpointOverridden()); request.addHandlerContext(HandlerContextKey.SIGNING_REGION, getSigningRegion()); request.addHandlerContext(HandlerContextKey.SERVICE_ID, "Textract"); request.addHandlerContext(HandlerContextKey.OPERATION_NAME, "GetLendingAnalysis"); request.addHandlerContext(HandlerContextKey.ADVANCED_CONFIG, advancedConfig); } finally { awsRequestMetrics.endEvent(Field.RequestMarshallTime); } HttpResponseHandler> responseHandler = protocolFactory.createResponseHandler( new JsonOperationMetadata().withPayloadJson(true).withHasStreamingSuccessResponse(false), new GetLendingAnalysisResultJsonUnmarshaller()); response = invoke(request, responseHandler, executionContext); return response.getAwsResponse(); } finally { endClientExecution(awsRequestMetrics, request, response); } } /** *

* Gets summarized results for the StartLendingAnalysis operation, which analyzes text in a lending * document. The returned summary consists of information about documents grouped together by a common document * type. Information like detected signatures, page numbers, and split documents is returned with respect to the * type of grouped document. *

*

* You start asynchronous text analysis by calling StartLendingAnalysis, which returns a job identifier * (JobId). 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 * StartLendingAnalysis. *

*

* To get the results of the text analysis operation, first check that the status value published to the Amazon SNS * topic is SUCCEEDED. If so, call GetLendingAnalysisSummary, and pass the job identifier ( * JobId) from the initial call to StartLendingAnalysis. *

* * @param getLendingAnalysisSummaryRequest * @return Result of the GetLendingAnalysisSummary operation returned by the service. * @throws InvalidParameterException * An input parameter violated a constraint. For example, in synchronous operations, an * InvalidParameterException exception occurs when neither of the S3Object or * Bytes values are supplied in the Document request parameter. Validate your * parameter before calling the API operation again. * @throws AccessDeniedException * 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. * @throws ProvisionedThroughputExceededException * The number of requests exceeded your throughput limit. If you want to increase this limit, contact Amazon * Textract. * @throws InvalidJobIdException * An invalid job identifier was passed to an asynchronous analysis operation. * @throws InternalServerErrorException * Amazon Textract experienced a service issue. Try your call again. * @throws ThrottlingException * Amazon Textract is temporarily unable to process the request. Try your call again. * @throws InvalidS3ObjectException * Amazon Textract is unable to access the S3 object that's specified in the request. for more information, * Configure Access to * Amazon S3 For troubleshooting information, see Troubleshooting Amazon S3 * @throws InvalidKMSKeyException * Indicates you do not have decrypt permissions with the KMS key entered, or the KMS key was entered * incorrectly. * @sample AmazonTextract.GetLendingAnalysisSummary * @see AWS API Documentation */ @Override public GetLendingAnalysisSummaryResult getLendingAnalysisSummary(GetLendingAnalysisSummaryRequest request) { request = beforeClientExecution(request); return executeGetLendingAnalysisSummary(request); } @SdkInternalApi final GetLendingAnalysisSummaryResult executeGetLendingAnalysisSummary(GetLendingAnalysisSummaryRequest getLendingAnalysisSummaryRequest) { ExecutionContext executionContext = createExecutionContext(getLendingAnalysisSummaryRequest); AWSRequestMetrics awsRequestMetrics = executionContext.getAwsRequestMetrics(); awsRequestMetrics.startEvent(Field.ClientExecuteTime); Request request = null; Response response = null; try { awsRequestMetrics.startEvent(Field.RequestMarshallTime); try { request = new GetLendingAnalysisSummaryRequestProtocolMarshaller(protocolFactory).marshall(super .beforeMarshalling(getLendingAnalysisSummaryRequest)); // Binds the request metrics to the current request. request.setAWSRequestMetrics(awsRequestMetrics); request.addHandlerContext(HandlerContextKey.CLIENT_ENDPOINT, endpoint); request.addHandlerContext(HandlerContextKey.ENDPOINT_OVERRIDDEN, isEndpointOverridden()); request.addHandlerContext(HandlerContextKey.SIGNING_REGION, getSigningRegion()); request.addHandlerContext(HandlerContextKey.SERVICE_ID, "Textract"); request.addHandlerContext(HandlerContextKey.OPERATION_NAME, "GetLendingAnalysisSummary"); request.addHandlerContext(HandlerContextKey.ADVANCED_CONFIG, advancedConfig); } finally { awsRequestMetrics.endEvent(Field.RequestMarshallTime); } HttpResponseHandler> responseHandler = protocolFactory.createResponseHandler( new JsonOperationMetadata().withPayloadJson(true).withHasStreamingSuccessResponse(false), new GetLendingAnalysisSummaryResultJsonUnmarshaller()); response = invoke(request, responseHandler, executionContext); return response.getAwsResponse(); } finally { endClientExecution(awsRequestMetrics, request, response); } } /** *

* Starts the asynchronous analysis of an input document for relationships between detected items such as key-value * pairs, tables, and selection elements. *

*

* StartDocumentAnalysis can analyze text in documents that are in JPEG, PNG, TIFF, and PDF format. The * documents are stored in an Amazon S3 bucket. Use DocumentLocation to specify the bucket name and file name * of the document. *

*

* StartDocumentAnalysis returns a job identifier (JobId) that you use to get the results * of the operation. When text analysis is finished, Amazon Textract publishes a completion status to the Amazon * Simple Notification Service (Amazon SNS) topic that you specify in NotificationChannel. To get the * results of the text analysis operation, first check that the status value published to the Amazon SNS topic is * SUCCEEDED. If so, call GetDocumentAnalysis, and pass the job identifier (JobId) * from the initial call to StartDocumentAnalysis. *

*

* For more information, see Document Text Analysis. *

* * @param startDocumentAnalysisRequest * @return Result of the StartDocumentAnalysis operation returned by the service. * @throws InvalidParameterException * An input parameter violated a constraint. For example, in synchronous operations, an * InvalidParameterException exception occurs when neither of the S3Object or * Bytes values are supplied in the Document request parameter. Validate your * parameter before calling the API operation again. * @throws InvalidS3ObjectException * Amazon Textract is unable to access the S3 object that's specified in the request. for more information, * Configure Access to * Amazon S3 For troubleshooting information, see Troubleshooting Amazon S3 * @throws InvalidKMSKeyException * Indicates you do not have decrypt permissions with the KMS key entered, or the KMS key was entered * incorrectly. * @throws UnsupportedDocumentException * The format of the input document isn't supported. Documents for operations can be in PNG, JPEG, PDF, or * TIFF format. * @throws DocumentTooLargeException * 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. * @throws BadDocumentException * Amazon Textract isn't able to read the document. For more information on the document limits in Amazon * Textract, see limits. * @throws AccessDeniedException * 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. * @throws ProvisionedThroughputExceededException * The number of requests exceeded your throughput limit. If you want to increase this limit, contact Amazon * Textract. * @throws InternalServerErrorException * Amazon Textract experienced a service issue. Try your call again. * @throws IdempotentParameterMismatchException * A ClientRequestToken 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. * @throws ThrottlingException * Amazon Textract is temporarily unable to process the request. Try your call again. * @throws LimitExceededException * An Amazon Textract service limit was exceeded. For example, if you start too many asynchronous jobs * concurrently, calls to start operations (StartDocumentTextDetection, for example) raise a * LimitExceededException exception (HTTP status code: 400) until the number of concurrently running jobs is * below the Amazon Textract service limit. * @sample AmazonTextract.StartDocumentAnalysis * @see AWS * API Documentation */ @Override public StartDocumentAnalysisResult startDocumentAnalysis(StartDocumentAnalysisRequest request) { request = beforeClientExecution(request); return executeStartDocumentAnalysis(request); } @SdkInternalApi final StartDocumentAnalysisResult executeStartDocumentAnalysis(StartDocumentAnalysisRequest startDocumentAnalysisRequest) { ExecutionContext executionContext = createExecutionContext(startDocumentAnalysisRequest); AWSRequestMetrics awsRequestMetrics = executionContext.getAwsRequestMetrics(); awsRequestMetrics.startEvent(Field.ClientExecuteTime); Request request = null; Response response = null; try { awsRequestMetrics.startEvent(Field.RequestMarshallTime); try { request = new StartDocumentAnalysisRequestProtocolMarshaller(protocolFactory).marshall(super.beforeMarshalling(startDocumentAnalysisRequest)); // Binds the request metrics to the current request. request.setAWSRequestMetrics(awsRequestMetrics); request.addHandlerContext(HandlerContextKey.CLIENT_ENDPOINT, endpoint); request.addHandlerContext(HandlerContextKey.ENDPOINT_OVERRIDDEN, isEndpointOverridden()); request.addHandlerContext(HandlerContextKey.SIGNING_REGION, getSigningRegion()); request.addHandlerContext(HandlerContextKey.SERVICE_ID, "Textract"); request.addHandlerContext(HandlerContextKey.OPERATION_NAME, "StartDocumentAnalysis"); request.addHandlerContext(HandlerContextKey.ADVANCED_CONFIG, advancedConfig); } finally { awsRequestMetrics.endEvent(Field.RequestMarshallTime); } HttpResponseHandler> responseHandler = protocolFactory .createResponseHandler(new JsonOperationMetadata().withPayloadJson(true).withHasStreamingSuccessResponse(false), new StartDocumentAnalysisResultJsonUnmarshaller()); response = invoke(request, responseHandler, executionContext); return response.getAwsResponse(); } finally { endClientExecution(awsRequestMetrics, request, response); } } /** *

* Starts the asynchronous detection of text in a document. Amazon Textract can detect lines of text and the words * that make up a line of text. *

*

* StartDocumentTextDetection can analyze text in documents that are in JPEG, PNG, TIFF, and PDF * format. The documents are stored in an Amazon S3 bucket. Use DocumentLocation to specify the bucket name * and file name of the document. *

*

* StartTextDetection returns a job identifier (JobId) that you use to get the results of * the operation. When text detection is finished, Amazon Textract publishes a completion status to the Amazon * Simple Notification Service (Amazon SNS) topic that you specify in NotificationChannel. To get the * results of the text detection operation, first check that the status value published to the Amazon SNS topic is * SUCCEEDED. If so, call GetDocumentTextDetection, and pass the job identifier ( * JobId) from the initial call to StartDocumentTextDetection. *

*

* For more information, see Document Text Detection. *

* * @param startDocumentTextDetectionRequest * @return Result of the StartDocumentTextDetection operation returned by the service. * @throws InvalidParameterException * An input parameter violated a constraint. For example, in synchronous operations, an * InvalidParameterException exception occurs when neither of the S3Object or * Bytes values are supplied in the Document request parameter. Validate your * parameter before calling the API operation again. * @throws InvalidS3ObjectException * Amazon Textract is unable to access the S3 object that's specified in the request. for more information, * Configure Access to * Amazon S3 For troubleshooting information, see Troubleshooting Amazon S3 * @throws InvalidKMSKeyException * Indicates you do not have decrypt permissions with the KMS key entered, or the KMS key was entered * incorrectly. * @throws UnsupportedDocumentException * The format of the input document isn't supported. Documents for operations can be in PNG, JPEG, PDF, or * TIFF format. * @throws DocumentTooLargeException * 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. * @throws BadDocumentException * Amazon Textract isn't able to read the document. For more information on the document limits in Amazon * Textract, see limits. * @throws AccessDeniedException * 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. * @throws ProvisionedThroughputExceededException * The number of requests exceeded your throughput limit. If you want to increase this limit, contact Amazon * Textract. * @throws InternalServerErrorException * Amazon Textract experienced a service issue. Try your call again. * @throws IdempotentParameterMismatchException * A ClientRequestToken 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. * @throws ThrottlingException * Amazon Textract is temporarily unable to process the request. Try your call again. * @throws LimitExceededException * An Amazon Textract service limit was exceeded. For example, if you start too many asynchronous jobs * concurrently, calls to start operations (StartDocumentTextDetection, for example) raise a * LimitExceededException exception (HTTP status code: 400) until the number of concurrently running jobs is * below the Amazon Textract service limit. * @sample AmazonTextract.StartDocumentTextDetection * @see AWS API Documentation */ @Override public StartDocumentTextDetectionResult startDocumentTextDetection(StartDocumentTextDetectionRequest request) { request = beforeClientExecution(request); return executeStartDocumentTextDetection(request); } @SdkInternalApi final StartDocumentTextDetectionResult executeStartDocumentTextDetection(StartDocumentTextDetectionRequest startDocumentTextDetectionRequest) { ExecutionContext executionContext = createExecutionContext(startDocumentTextDetectionRequest); AWSRequestMetrics awsRequestMetrics = executionContext.getAwsRequestMetrics(); awsRequestMetrics.startEvent(Field.ClientExecuteTime); Request request = null; Response response = null; try { awsRequestMetrics.startEvent(Field.RequestMarshallTime); try { request = new StartDocumentTextDetectionRequestProtocolMarshaller(protocolFactory).marshall(super .beforeMarshalling(startDocumentTextDetectionRequest)); // Binds the request metrics to the current request. request.setAWSRequestMetrics(awsRequestMetrics); request.addHandlerContext(HandlerContextKey.CLIENT_ENDPOINT, endpoint); request.addHandlerContext(HandlerContextKey.ENDPOINT_OVERRIDDEN, isEndpointOverridden()); request.addHandlerContext(HandlerContextKey.SIGNING_REGION, getSigningRegion()); request.addHandlerContext(HandlerContextKey.SERVICE_ID, "Textract"); request.addHandlerContext(HandlerContextKey.OPERATION_NAME, "StartDocumentTextDetection"); request.addHandlerContext(HandlerContextKey.ADVANCED_CONFIG, advancedConfig); } finally { awsRequestMetrics.endEvent(Field.RequestMarshallTime); } HttpResponseHandler> responseHandler = protocolFactory.createResponseHandler( new JsonOperationMetadata().withPayloadJson(true).withHasStreamingSuccessResponse(false), new StartDocumentTextDetectionResultJsonUnmarshaller()); response = invoke(request, responseHandler, executionContext); return response.getAwsResponse(); } finally { endClientExecution(awsRequestMetrics, request, response); } } /** *

* Starts the asynchronous analysis of invoices or receipts for data like contact information, items purchased, and * vendor names. *

*

* StartExpenseAnalysis 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 DocumentLocation parameter to specify the name of * your S3 bucket and the name of the document in that bucket. *

*

* StartExpenseAnalysis returns a job identifier (JobId) that you will provide to * GetExpenseAnalysis 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 NotificationChannel. To obtain the results of the * invoice and receipt analysis operation, ensure that the status value published to the Amazon SNS topic is * SUCCEEDED. If so, call GetExpenseAnalysis, and pass the job identifier (JobId) * that was returned by your call to StartExpenseAnalysis. *

*

* For more information, see Analyzing Invoices and Receipts. *

* * @param startExpenseAnalysisRequest * @return Result of the StartExpenseAnalysis operation returned by the service. * @throws InvalidParameterException * An input parameter violated a constraint. For example, in synchronous operations, an * InvalidParameterException exception occurs when neither of the S3Object or * Bytes values are supplied in the Document request parameter. Validate your * parameter before calling the API operation again. * @throws InvalidS3ObjectException * Amazon Textract is unable to access the S3 object that's specified in the request. for more information, * Configure Access to * Amazon S3 For troubleshooting information, see Troubleshooting Amazon S3 * @throws InvalidKMSKeyException * Indicates you do not have decrypt permissions with the KMS key entered, or the KMS key was entered * incorrectly. * @throws UnsupportedDocumentException * The format of the input document isn't supported. Documents for operations can be in PNG, JPEG, PDF, or * TIFF format. * @throws DocumentTooLargeException * 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. * @throws BadDocumentException * Amazon Textract isn't able to read the document. For more information on the document limits in Amazon * Textract, see limits. * @throws AccessDeniedException * 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. * @throws ProvisionedThroughputExceededException * The number of requests exceeded your throughput limit. If you want to increase this limit, contact Amazon * Textract. * @throws InternalServerErrorException * Amazon Textract experienced a service issue. Try your call again. * @throws IdempotentParameterMismatchException * A ClientRequestToken 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. * @throws ThrottlingException * Amazon Textract is temporarily unable to process the request. Try your call again. * @throws LimitExceededException * An Amazon Textract service limit was exceeded. For example, if you start too many asynchronous jobs * concurrently, calls to start operations (StartDocumentTextDetection, for example) raise a * LimitExceededException exception (HTTP status code: 400) until the number of concurrently running jobs is * below the Amazon Textract service limit. * @sample AmazonTextract.StartExpenseAnalysis * @see AWS * API Documentation */ @Override public StartExpenseAnalysisResult startExpenseAnalysis(StartExpenseAnalysisRequest request) { request = beforeClientExecution(request); return executeStartExpenseAnalysis(request); } @SdkInternalApi final StartExpenseAnalysisResult executeStartExpenseAnalysis(StartExpenseAnalysisRequest startExpenseAnalysisRequest) { ExecutionContext executionContext = createExecutionContext(startExpenseAnalysisRequest); AWSRequestMetrics awsRequestMetrics = executionContext.getAwsRequestMetrics(); awsRequestMetrics.startEvent(Field.ClientExecuteTime); Request request = null; Response response = null; try { awsRequestMetrics.startEvent(Field.RequestMarshallTime); try { request = new StartExpenseAnalysisRequestProtocolMarshaller(protocolFactory).marshall(super.beforeMarshalling(startExpenseAnalysisRequest)); // Binds the request metrics to the current request. request.setAWSRequestMetrics(awsRequestMetrics); request.addHandlerContext(HandlerContextKey.CLIENT_ENDPOINT, endpoint); request.addHandlerContext(HandlerContextKey.ENDPOINT_OVERRIDDEN, isEndpointOverridden()); request.addHandlerContext(HandlerContextKey.SIGNING_REGION, getSigningRegion()); request.addHandlerContext(HandlerContextKey.SERVICE_ID, "Textract"); request.addHandlerContext(HandlerContextKey.OPERATION_NAME, "StartExpenseAnalysis"); request.addHandlerContext(HandlerContextKey.ADVANCED_CONFIG, advancedConfig); } finally { awsRequestMetrics.endEvent(Field.RequestMarshallTime); } HttpResponseHandler> responseHandler = protocolFactory.createResponseHandler( new JsonOperationMetadata().withPayloadJson(true).withHasStreamingSuccessResponse(false), new StartExpenseAnalysisResultJsonUnmarshaller()); response = invoke(request, responseHandler, executionContext); return response.getAwsResponse(); } finally { endClientExecution(awsRequestMetrics, request, response); } } /** *

* Starts the classification and analysis of an input document. StartLendingAnalysis initiates the * classification and analysis of a packet of lending documents. StartLendingAnalysis operates on a * document file located in an Amazon S3 bucket. *

*

* StartLendingAnalysis can analyze text in documents that are in one of the following formats: JPEG, * PNG, TIFF, PDF. Use DocumentLocation to specify the bucket name and the file name of the document. *

*

* StartLendingAnalysis returns a job identifier (JobId) that you use to get the results * of the operation. When the text analysis is finished, Amazon Textract publishes a completion status to the Amazon * Simple Notification Service (Amazon SNS) topic that you specify in NotificationChannel. To get the * results of the text analysis operation, first check that the status value published to the Amazon SNS topic is * SUCCEEDED. If the status is SUCCEEDED you can call either GetLendingAnalysis or * GetLendingAnalysisSummary and provide the JobId to obtain the results of the analysis. *

*

* If using OutputConfig to specify an Amazon S3 bucket, the output will be contained within the * specified prefix in a directory labeled with the job-id. In the directory there are 3 sub-directories: *

*
    *
  • *

    * detailedResponse (contains the GetLendingAnalysis response) *

    *
    • *
  • *

    * summaryResponse (for the GetLendingAnalysisSummary response) *

    *
    • *
  • *

    * splitDocuments (documents split across logical boundaries) *

    *
    • *
* * @param startLendingAnalysisRequest * @return Result of the StartLendingAnalysis operation returned by the service. * @throws InvalidParameterException * An input parameter violated a constraint. For example, in synchronous operations, an * InvalidParameterException exception occurs when neither of the S3Object or * Bytes values are supplied in the Document request parameter. Validate your * parameter before calling the API operation again. * @throws InvalidS3ObjectException * Amazon Textract is unable to access the S3 object that's specified in the request. for more information, * Configure Access to * Amazon S3 For troubleshooting information, see Troubleshooting Amazon S3 * @throws InvalidKMSKeyException * Indicates you do not have decrypt permissions with the KMS key entered, or the KMS key was entered * incorrectly. * @throws UnsupportedDocumentException * The format of the input document isn't supported. Documents for operations can be in PNG, JPEG, PDF, or * TIFF format. * @throws DocumentTooLargeException * 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. * @throws BadDocumentException * Amazon Textract isn't able to read the document. For more information on the document limits in Amazon * Textract, see limits. * @throws AccessDeniedException * 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. * @throws ProvisionedThroughputExceededException * The number of requests exceeded your throughput limit. If you want to increase this limit, contact Amazon * Textract. * @throws InternalServerErrorException * Amazon Textract experienced a service issue. Try your call again. * @throws IdempotentParameterMismatchException * A ClientRequestToken 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. * @throws ThrottlingException * Amazon Textract is temporarily unable to process the request. Try your call again. * @throws LimitExceededException * An Amazon Textract service limit was exceeded. For example, if you start too many asynchronous jobs * concurrently, calls to start operations (StartDocumentTextDetection, for example) raise a * LimitExceededException exception (HTTP status code: 400) until the number of concurrently running jobs is * below the Amazon Textract service limit. * @sample AmazonTextract.StartLendingAnalysis * @see AWS * API Documentation */ @Override public StartLendingAnalysisResult startLendingAnalysis(StartLendingAnalysisRequest request) { request = beforeClientExecution(request); return executeStartLendingAnalysis(request); } @SdkInternalApi final StartLendingAnalysisResult executeStartLendingAnalysis(StartLendingAnalysisRequest startLendingAnalysisRequest) { ExecutionContext executionContext = createExecutionContext(startLendingAnalysisRequest); AWSRequestMetrics awsRequestMetrics = executionContext.getAwsRequestMetrics(); awsRequestMetrics.startEvent(Field.ClientExecuteTime); Request request = null; Response response = null; try { awsRequestMetrics.startEvent(Field.RequestMarshallTime); try { request = new StartLendingAnalysisRequestProtocolMarshaller(protocolFactory).marshall(super.beforeMarshalling(startLendingAnalysisRequest)); // Binds the request metrics to the current request. request.setAWSRequestMetrics(awsRequestMetrics); request.addHandlerContext(HandlerContextKey.CLIENT_ENDPOINT, endpoint); request.addHandlerContext(HandlerContextKey.ENDPOINT_OVERRIDDEN, isEndpointOverridden()); request.addHandlerContext(HandlerContextKey.SIGNING_REGION, getSigningRegion()); request.addHandlerContext(HandlerContextKey.SERVICE_ID, "Textract"); request.addHandlerContext(HandlerContextKey.OPERATION_NAME, "StartLendingAnalysis"); request.addHandlerContext(HandlerContextKey.ADVANCED_CONFIG, advancedConfig); } finally { awsRequestMetrics.endEvent(Field.RequestMarshallTime); } HttpResponseHandler> responseHandler = protocolFactory.createResponseHandler( new JsonOperationMetadata().withPayloadJson(true).withHasStreamingSuccessResponse(false), new StartLendingAnalysisResultJsonUnmarshaller()); response = invoke(request, responseHandler, executionContext); return response.getAwsResponse(); } finally { endClientExecution(awsRequestMetrics, request, response); } } /** * Returns additional metadata for a previously executed successful, request, typically used for debugging issues * where a service isn't acting as expected. This data isn't considered part of the result data returned by an * operation, so it's available through this separate, diagnostic interface. *

* Response metadata is only cached for a limited period of time, so if you need to access this extra diagnostic * information for an executed request, you should use this method to retrieve it as soon as possible after * executing the request. * * @param request * The originally executed request * * @return The response metadata for the specified request, or null if none is available. */ public ResponseMetadata getCachedResponseMetadata(AmazonWebServiceRequest request) { return client.getResponseMetadataForRequest(request); } /** * Normal invoke with authentication. Credentials are required and may be overriden at the request level. **/ private Response invoke(Request request, HttpResponseHandler> responseHandler, ExecutionContext executionContext) { return invoke(request, responseHandler, executionContext, null, null); } /** * Normal invoke with authentication. Credentials are required and may be overriden at the request level. **/ private Response invoke(Request request, HttpResponseHandler> responseHandler, ExecutionContext executionContext, URI cachedEndpoint, URI uriFromEndpointTrait) { executionContext.setCredentialsProvider(CredentialUtils.getCredentialsProvider(request.getOriginalRequest(), awsCredentialsProvider)); return doInvoke(request, responseHandler, executionContext, cachedEndpoint, uriFromEndpointTrait); } /** * Invoke with no authentication. Credentials are not required and any credentials set on the client or request will * be ignored for this operation. **/ private Response anonymousInvoke(Request request, HttpResponseHandler> responseHandler, ExecutionContext executionContext) { return doInvoke(request, responseHandler, executionContext, null, null); } /** * Invoke the request using the http client. Assumes credentials (or lack thereof) have been configured in the * ExecutionContext beforehand. **/ private Response doInvoke(Request request, HttpResponseHandler> responseHandler, ExecutionContext executionContext, URI discoveredEndpoint, URI uriFromEndpointTrait) { if (discoveredEndpoint != null) { request.setEndpoint(discoveredEndpoint); request.getOriginalRequest().getRequestClientOptions().appendUserAgent("endpoint-discovery"); } else if (uriFromEndpointTrait != null) { request.setEndpoint(uriFromEndpointTrait); } else { request.setEndpoint(endpoint); } request.setTimeOffset(timeOffset); HttpResponseHandler errorResponseHandler = protocolFactory.createErrorResponseHandler(new JsonErrorResponseMetadata()); return client.execute(request, responseHandler, errorResponseHandler, executionContext); } @com.amazonaws.annotation.SdkInternalApi static com.amazonaws.protocol.json.SdkJsonProtocolFactory getProtocolFactory() { return protocolFactory; } @Override public void shutdown() { super.shutdown(); } }