aws-sdk-comprehend 1.67.0 → 1.68.0

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA256:
-  metadata.gz: 98cca79ad616409a627fb408bf9d57dde00f6ae9f610d0b2347cb53172595630
-  data.tar.gz: 37bf33b746207ed09a41855ec47bac27e7bf7d9618ef40927f7ad89234d2d4ab
+  metadata.gz: 2795339a1b5ff7154a977a6f4921117728519249538628c2e430ff0439de0778
+  data.tar.gz: 91f757f8d8a73726513ba2a7b526c5991ff24ea62cc072938a85395cfd96b431
 SHA512:
-  metadata.gz: ee8117be4044e5ded7fd37ff794c2de556a4f47beec32abee11ffb61a9f7a82ea440c21cec9f1ab7389ad67a8ede376e975cb2b54bf0065e2e224c0ba005aa04
-  data.tar.gz: ff0b87b8396361b18eaf86b3b907b99e20ca83f1777216fa1446dfe6debac2f6ac769e50d066d0c47474472e408d404a85277ad9224db88833303b00148d1eb0
+  metadata.gz: 460952c4bc9f3eee19662f76e4421bf4105807f1c6d0e54e9efea4c501201d382652a87dc5e1a01613e1105c6b5250c0f494015545e5d88f33d2eacef57deeaa
+  data.tar.gz: da511f2b66c64df9893d055713dc490716ec475a9050d7b2214fd2a82243a8ec073a04d300418bd14264e8673ab5836dd2ddf77aa48546a0d31947a9c06063b5

data/CHANGELOG.md

@@ -1,6 +1,11 @@
 Unreleased Changes
 ------------------
 
+1.68.0 (2023-04-19)
+------------------
+
+* Feature - This release supports native document models for custom classification, in addition to plain-text models. You train native document models using documents (PDF, Word, images) in their native format.
+
 1.67.0 (2023-03-24)
 ------------------
 

data/VERSION

@@ -1 +1 @@
-1.67.0
+1.68.0

data/lib/aws-sdk-comprehend/client.rb

@@ -765,6 +765,7 @@ module Aws::Comprehend
     #   * {Types::ClassifyDocumentResponse#document_metadata #document_metadata} => Types::DocumentMetadata
     #   * {Types::ClassifyDocumentResponse#document_type #document_type} => Array<Types::DocumentTypeListItem>
     #   * {Types::ClassifyDocumentResponse#errors #errors} => Array<Types::ErrorsListItem>
+    #   * {Types::ClassifyDocumentResponse#warnings #warnings} => Array<Types::WarningsListItem>
     #
     # @example Request syntax with placeholder values
     #
@@ -800,6 +801,10 @@ module Aws::Comprehend
     #   resp.errors[0].page #=> Integer
     #   resp.errors[0].error_code #=> String, one of "TEXTRACT_BAD_PAGE", "TEXTRACT_PROVISIONED_THROUGHPUT_EXCEEDED", "PAGE_CHARACTERS_EXCEEDED", "PAGE_SIZE_EXCEEDED", "INTERNAL_SERVER_ERROR"
     #   resp.errors[0].error_message #=> String
+    #   resp.warnings #=> Array
+    #   resp.warnings[0].page #=> Integer
+    #   resp.warnings[0].warn_code #=> String, one of "INFERENCING_PLAINTEXT_WITH_NATIVE_TRAINED_MODEL", "INFERENCING_NATIVE_DOCUMENT_WITH_PLAINTEXT_TRAINED_MODEL"
+    #   resp.warnings[0].warn_message #=> String
     #
     # @see http://docs.aws.amazon.com/goto/WebAPI/comprehend-2017-11-27/ClassifyDocument AWS API Documentation
     #
@@ -947,14 +952,13 @@ module Aws::Comprehend
 
     # Creates a new document classifier that you can use to categorize
     # documents. To create a classifier, you provide a set of training
-    # documents that labeled with the categories that you want to use. After
-    # the classifier is trained you can use it to categorize a set of
-    # labeled documents into the categories. For more information, see
-    # [Document Classification][1] in the Comprehend Developer Guide.
+    # documents that are labeled with the categories that you want to use.
+    # For more information, see [Training classifier models][1] in the
+    # Comprehend Developer Guide.
     #
     #
     #
-    # [1]: https://docs.aws.amazon.com/comprehend/latest/dg/how-document-classification.html
+    # [1]: https://docs.aws.amazon.com/comprehend/latest/dg/training-classifier-model.html
     #
     # @option params [required, String] :document_classifier_name
     #   The name of the document classifier.
@@ -980,8 +984,9 @@ module Aws::Comprehend
     #   Specifies the format and location of the input data for the job.
     #
     # @option params [Types::DocumentClassifierOutputDataConfig] :output_data_config
-    #   Enables the addition of output results configuration parameters for
-    #   custom classifier jobs.
+    #   Specifies the location for the output files from a custom classifier
+    #   job. This parameter is required for a request that creates a native
+    #   classifier model.
     #
     # @option params [String] :client_request_token
     #   A unique identifier for the request. If you don't set the client
@@ -1082,6 +1087,16 @@ module Aws::Comprehend
     #           document_type: "PLAIN_TEXT_DOCUMENT", # accepts PLAIN_TEXT_DOCUMENT, SEMI_STRUCTURED_DOCUMENT
     #         },
     #       ],
+    #       document_type: "PLAIN_TEXT_DOCUMENT", # accepts PLAIN_TEXT_DOCUMENT, SEMI_STRUCTURED_DOCUMENT
+    #       documents: {
+    #         s3_uri: "S3Uri", # required
+    #         test_s3_uri: "S3Uri",
+    #       },
+    #       document_reader_config: {
+    #         document_read_action: "TEXTRACT_DETECT_DOCUMENT_TEXT", # required, accepts TEXTRACT_DETECT_DOCUMENT_TEXT, TEXTRACT_ANALYZE_DOCUMENT
+    #         document_read_mode: "SERVICE_DEFAULT", # accepts SERVICE_DEFAULT, FORCE_DOCUMENT_READ_ACTION
+    #         feature_types: ["TABLES"], # accepts TABLES, FORMS
+    #       },
     #     },
     #     output_data_config: {
     #       s3_uri: "S3Uri",
@@ -1760,6 +1775,13 @@ module Aws::Comprehend
     #   resp.document_classifier_properties.input_data_config.augmented_manifests[0].annotation_data_s3_uri #=> String
     #   resp.document_classifier_properties.input_data_config.augmented_manifests[0].source_documents_s3_uri #=> String
     #   resp.document_classifier_properties.input_data_config.augmented_manifests[0].document_type #=> String, one of "PLAIN_TEXT_DOCUMENT", "SEMI_STRUCTURED_DOCUMENT"
+    #   resp.document_classifier_properties.input_data_config.document_type #=> String, one of "PLAIN_TEXT_DOCUMENT", "SEMI_STRUCTURED_DOCUMENT"
+    #   resp.document_classifier_properties.input_data_config.documents.s3_uri #=> String
+    #   resp.document_classifier_properties.input_data_config.documents.test_s3_uri #=> String
+    #   resp.document_classifier_properties.input_data_config.document_reader_config.document_read_action #=> String, one of "TEXTRACT_DETECT_DOCUMENT_TEXT", "TEXTRACT_ANALYZE_DOCUMENT"
+    #   resp.document_classifier_properties.input_data_config.document_reader_config.document_read_mode #=> String, one of "SERVICE_DEFAULT", "FORCE_DOCUMENT_READ_ACTION"
+    #   resp.document_classifier_properties.input_data_config.document_reader_config.feature_types #=> Array
+    #   resp.document_classifier_properties.input_data_config.document_reader_config.feature_types[0] #=> String, one of "TABLES", "FORMS"
     #   resp.document_classifier_properties.output_data_config.s3_uri #=> String
     #   resp.document_classifier_properties.output_data_config.kms_key_id #=> String
     #   resp.document_classifier_properties.output_data_config.flywheel_stats_s3_prefix #=> String
@@ -3201,6 +3223,13 @@ module Aws::Comprehend
     #   resp.document_classifier_properties_list[0].input_data_config.augmented_manifests[0].annotation_data_s3_uri #=> String
     #   resp.document_classifier_properties_list[0].input_data_config.augmented_manifests[0].source_documents_s3_uri #=> String
     #   resp.document_classifier_properties_list[0].input_data_config.augmented_manifests[0].document_type #=> String, one of "PLAIN_TEXT_DOCUMENT", "SEMI_STRUCTURED_DOCUMENT"
+    #   resp.document_classifier_properties_list[0].input_data_config.document_type #=> String, one of "PLAIN_TEXT_DOCUMENT", "SEMI_STRUCTURED_DOCUMENT"
+    #   resp.document_classifier_properties_list[0].input_data_config.documents.s3_uri #=> String
+    #   resp.document_classifier_properties_list[0].input_data_config.documents.test_s3_uri #=> String
+    #   resp.document_classifier_properties_list[0].input_data_config.document_reader_config.document_read_action #=> String, one of "TEXTRACT_DETECT_DOCUMENT_TEXT", "TEXTRACT_ANALYZE_DOCUMENT"
+    #   resp.document_classifier_properties_list[0].input_data_config.document_reader_config.document_read_mode #=> String, one of "SERVICE_DEFAULT", "FORCE_DOCUMENT_READ_ACTION"
+    #   resp.document_classifier_properties_list[0].input_data_config.document_reader_config.feature_types #=> Array
+    #   resp.document_classifier_properties_list[0].input_data_config.document_reader_config.feature_types[0] #=> String, one of "TABLES", "FORMS"
     #   resp.document_classifier_properties_list[0].output_data_config.s3_uri #=> String
     #   resp.document_classifier_properties_list[0].output_data_config.kms_key_id #=> String
     #   resp.document_classifier_properties_list[0].output_data_config.flywheel_stats_s3_prefix #=> String
@@ -5786,7 +5815,7 @@ module Aws::Comprehend
         params: params,
         config: config)
       context[:gem_name] = 'aws-sdk-comprehend'
-      context[:gem_version] = '1.67.0'
+      context[:gem_version] = '1.68.0'
       Seahorse::Client::Request.new(handlers, context)
     end
 

data/lib/aws-sdk-comprehend/client_api.rb

@@ -151,6 +151,8 @@ module Aws::Comprehend
     DocumentClassifierArn = Shapes::StringShape.new(name: 'DocumentClassifierArn')
     DocumentClassifierAugmentedManifestsList = Shapes::ListShape.new(name: 'DocumentClassifierAugmentedManifestsList')
     DocumentClassifierDataFormat = Shapes::StringShape.new(name: 'DocumentClassifierDataFormat')
+    DocumentClassifierDocumentTypeFormat = Shapes::StringShape.new(name: 'DocumentClassifierDocumentTypeFormat')
+    DocumentClassifierDocuments = Shapes::StructureShape.new(name: 'DocumentClassifierDocuments')
     DocumentClassifierEndpointArn = Shapes::StringShape.new(name: 'DocumentClassifierEndpointArn')
     DocumentClassifierFilter = Shapes::StructureShape.new(name: 'DocumentClassifierFilter')
     DocumentClassifierInputDataConfig = Shapes::StructureShape.new(name: 'DocumentClassifierInputDataConfig')
@@ -305,6 +307,7 @@ module Aws::Comprehend
     ListOfRelationships = Shapes::ListShape.new(name: 'ListOfRelationships')
     ListOfSyntaxTokens = Shapes::ListShape.new(name: 'ListOfSyntaxTokens')
     ListOfTargetedSentimentEntities = Shapes::ListShape.new(name: 'ListOfTargetedSentimentEntities')
+    ListOfWarnings = Shapes::ListShape.new(name: 'ListOfWarnings')
     ListPiiEntitiesDetectionJobsRequest = Shapes::StructureShape.new(name: 'ListPiiEntitiesDetectionJobsRequest')
     ListPiiEntitiesDetectionJobsResponse = Shapes::StructureShape.new(name: 'ListPiiEntitiesDetectionJobsResponse')
     ListSentimentDetectionJobsRequest = Shapes::StructureShape.new(name: 'ListSentimentDetectionJobsRequest')
@@ -324,6 +327,7 @@ module Aws::Comprehend
     NumberOfTopicsInteger = Shapes::IntegerShape.new(name: 'NumberOfTopicsInteger')
     OutputDataConfig = Shapes::StructureShape.new(name: 'OutputDataConfig')
     PageBasedErrorCode = Shapes::StringShape.new(name: 'PageBasedErrorCode')
+    PageBasedWarningCode = Shapes::StringShape.new(name: 'PageBasedWarningCode')
     PartOfSpeechTag = Shapes::StructureShape.new(name: 'PartOfSpeechTag')
     PartOfSpeechTagType = Shapes::StringShape.new(name: 'PartOfSpeechTagType')
     PiiEntitiesDetectionJobFilter = Shapes::StructureShape.new(name: 'PiiEntitiesDetectionJobFilter')
@@ -434,6 +438,7 @@ module Aws::Comprehend
     UpdateFlywheelResponse = Shapes::StructureShape.new(name: 'UpdateFlywheelResponse')
     VersionName = Shapes::StringShape.new(name: 'VersionName')
     VpcConfig = Shapes::StructureShape.new(name: 'VpcConfig')
+    WarningsListItem = Shapes::StructureShape.new(name: 'WarningsListItem')
 
     AttributeNamesList.member = Shapes::ShapeRef.new(shape: AttributeNamesListItem)
 
@@ -579,6 +584,7 @@ module Aws::Comprehend
     ClassifyDocumentResponse.add_member(:document_metadata, Shapes::ShapeRef.new(shape: DocumentMetadata, location_name: "DocumentMetadata"))
     ClassifyDocumentResponse.add_member(:document_type, Shapes::ShapeRef.new(shape: ListOfDocumentType, location_name: "DocumentType"))
     ClassifyDocumentResponse.add_member(:errors, Shapes::ShapeRef.new(shape: ListOfErrors, location_name: "Errors"))
+    ClassifyDocumentResponse.add_member(:warnings, Shapes::ShapeRef.new(shape: ListOfWarnings, location_name: "Warnings"))
     ClassifyDocumentResponse.struct_class = Types::ClassifyDocumentResponse
 
     ConcurrentModificationException.add_member(:message, Shapes::ShapeRef.new(shape: String, location_name: "Message"))
@@ -944,6 +950,10 @@ module Aws::Comprehend
 
     DocumentClassifierAugmentedManifestsList.member = Shapes::ShapeRef.new(shape: AugmentedManifestsListItem)
 
+    DocumentClassifierDocuments.add_member(:s3_uri, Shapes::ShapeRef.new(shape: S3Uri, required: true, location_name: "S3Uri"))
+    DocumentClassifierDocuments.add_member(:test_s3_uri, Shapes::ShapeRef.new(shape: S3Uri, location_name: "TestS3Uri"))
+    DocumentClassifierDocuments.struct_class = Types::DocumentClassifierDocuments
+
     DocumentClassifierFilter.add_member(:status, Shapes::ShapeRef.new(shape: ModelStatus, location_name: "Status"))
     DocumentClassifierFilter.add_member(:document_classifier_name, Shapes::ShapeRef.new(shape: ComprehendArnName, location_name: "DocumentClassifierName"))
     DocumentClassifierFilter.add_member(:submit_time_before, Shapes::ShapeRef.new(shape: Timestamp, location_name: "SubmitTimeBefore"))
@@ -955,6 +965,9 @@ module Aws::Comprehend
     DocumentClassifierInputDataConfig.add_member(:test_s3_uri, Shapes::ShapeRef.new(shape: S3Uri, location_name: "TestS3Uri"))
     DocumentClassifierInputDataConfig.add_member(:label_delimiter, Shapes::ShapeRef.new(shape: LabelDelimiter, location_name: "LabelDelimiter"))
     DocumentClassifierInputDataConfig.add_member(:augmented_manifests, Shapes::ShapeRef.new(shape: DocumentClassifierAugmentedManifestsList, location_name: "AugmentedManifests"))
+    DocumentClassifierInputDataConfig.add_member(:document_type, Shapes::ShapeRef.new(shape: DocumentClassifierDocumentTypeFormat, location_name: "DocumentType"))
+    DocumentClassifierInputDataConfig.add_member(:documents, Shapes::ShapeRef.new(shape: DocumentClassifierDocuments, location_name: "Documents"))
+    DocumentClassifierInputDataConfig.add_member(:document_reader_config, Shapes::ShapeRef.new(shape: DocumentReaderConfig, location_name: "DocumentReaderConfig"))
     DocumentClassifierInputDataConfig.struct_class = Types::DocumentClassifierInputDataConfig
 
     DocumentClassifierOutputDataConfig.add_member(:s3_uri, Shapes::ShapeRef.new(shape: S3Uri, location_name: "S3Uri"))
@@ -1518,6 +1531,8 @@ module Aws::Comprehend
 
     ListOfTargetedSentimentEntities.member = Shapes::ShapeRef.new(shape: TargetedSentimentEntity)
 
+    ListOfWarnings.member = Shapes::ShapeRef.new(shape: WarningsListItem)
+
     ListPiiEntitiesDetectionJobsRequest.add_member(:filter, Shapes::ShapeRef.new(shape: PiiEntitiesDetectionJobFilter, location_name: "Filter"))
     ListPiiEntitiesDetectionJobsRequest.add_member(:next_token, Shapes::ShapeRef.new(shape: String, location_name: "NextToken"))
     ListPiiEntitiesDetectionJobsRequest.add_member(:max_results, Shapes::ShapeRef.new(shape: MaxResultsInteger, location_name: "MaxResults"))
@@ -2026,6 +2041,11 @@ module Aws::Comprehend
     VpcConfig.add_member(:subnets, Shapes::ShapeRef.new(shape: Subnets, required: true, location_name: "Subnets"))
     VpcConfig.struct_class = Types::VpcConfig
 
+    WarningsListItem.add_member(:page, Shapes::ShapeRef.new(shape: Integer, location_name: "Page"))
+    WarningsListItem.add_member(:warn_code, Shapes::ShapeRef.new(shape: PageBasedWarningCode, location_name: "WarnCode"))
+    WarningsListItem.add_member(:warn_message, Shapes::ShapeRef.new(shape: String, location_name: "WarnMessage"))
+    WarningsListItem.struct_class = Types::WarningsListItem
+
 
     # @api private
     API = Seahorse::Model::Api.new.tap do |api|
@@ -2924,6 +2944,7 @@ module Aws::Comprehend
         o.errors << Shapes::ShapeRef.new(shape: ResourceUnavailableException)
         o.errors << Shapes::ShapeRef.new(shape: KmsKeyValidationException)
         o.errors << Shapes::ShapeRef.new(shape: TooManyTagsException)
+        o.errors << Shapes::ShapeRef.new(shape: ResourceInUseException)
         o.errors << Shapes::ShapeRef.new(shape: InternalServerException)
       end)
 
@@ -2937,6 +2958,7 @@ module Aws::Comprehend
         o.errors << Shapes::ShapeRef.new(shape: TooManyRequestsException)
         o.errors << Shapes::ShapeRef.new(shape: KmsKeyValidationException)
         o.errors << Shapes::ShapeRef.new(shape: TooManyTagsException)
+        o.errors << Shapes::ShapeRef.new(shape: ResourceInUseException)
         o.errors << Shapes::ShapeRef.new(shape: InternalServerException)
       end)
 
@@ -2952,6 +2974,7 @@ module Aws::Comprehend
         o.errors << Shapes::ShapeRef.new(shape: ResourceUnavailableException)
         o.errors << Shapes::ShapeRef.new(shape: KmsKeyValidationException)
         o.errors << Shapes::ShapeRef.new(shape: TooManyTagsException)
+        o.errors << Shapes::ShapeRef.new(shape: ResourceInUseException)
         o.errors << Shapes::ShapeRef.new(shape: InternalServerException)
       end)
 
@@ -2965,6 +2988,7 @@ module Aws::Comprehend
         o.errors << Shapes::ShapeRef.new(shape: TooManyRequestsException)
         o.errors << Shapes::ShapeRef.new(shape: KmsKeyValidationException)
         o.errors << Shapes::ShapeRef.new(shape: TooManyTagsException)
+        o.errors << Shapes::ShapeRef.new(shape: ResourceInUseException)
         o.errors << Shapes::ShapeRef.new(shape: InternalServerException)
       end)
 
@@ -2991,6 +3015,7 @@ module Aws::Comprehend
         o.errors << Shapes::ShapeRef.new(shape: TooManyRequestsException)
         o.errors << Shapes::ShapeRef.new(shape: KmsKeyValidationException)
         o.errors << Shapes::ShapeRef.new(shape: TooManyTagsException)
+        o.errors << Shapes::ShapeRef.new(shape: ResourceInUseException)
         o.errors << Shapes::ShapeRef.new(shape: InternalServerException)
       end)
 
@@ -3004,6 +3029,7 @@ module Aws::Comprehend
         o.errors << Shapes::ShapeRef.new(shape: TooManyRequestsException)
         o.errors << Shapes::ShapeRef.new(shape: KmsKeyValidationException)
         o.errors << Shapes::ShapeRef.new(shape: TooManyTagsException)
+        o.errors << Shapes::ShapeRef.new(shape: ResourceInUseException)
         o.errors << Shapes::ShapeRef.new(shape: InternalServerException)
       end)
 
@@ -3017,6 +3043,7 @@ module Aws::Comprehend
         o.errors << Shapes::ShapeRef.new(shape: TooManyRequestsException)
         o.errors << Shapes::ShapeRef.new(shape: KmsKeyValidationException)
         o.errors << Shapes::ShapeRef.new(shape: TooManyTagsException)
+        o.errors << Shapes::ShapeRef.new(shape: ResourceInUseException)
         o.errors << Shapes::ShapeRef.new(shape: InternalServerException)
       end)
 
@@ -3030,6 +3057,7 @@ module Aws::Comprehend
         o.errors << Shapes::ShapeRef.new(shape: TooManyRequestsException)
         o.errors << Shapes::ShapeRef.new(shape: KmsKeyValidationException)
         o.errors << Shapes::ShapeRef.new(shape: TooManyTagsException)
+        o.errors << Shapes::ShapeRef.new(shape: ResourceInUseException)
         o.errors << Shapes::ShapeRef.new(shape: InternalServerException)
       end)
 
@@ -3043,6 +3071,7 @@ module Aws::Comprehend
         o.errors << Shapes::ShapeRef.new(shape: TooManyRequestsException)
         o.errors << Shapes::ShapeRef.new(shape: KmsKeyValidationException)
         o.errors << Shapes::ShapeRef.new(shape: TooManyTagsException)
+        o.errors << Shapes::ShapeRef.new(shape: ResourceInUseException)
         o.errors << Shapes::ShapeRef.new(shape: InternalServerException)
       end)
 

data/lib/aws-sdk-comprehend/types.rb

@@ -856,6 +856,16 @@ module Aws::Comprehend
     #   errors.
     #   @return [Array<Types::ErrorsListItem>]
     #
+    # @!attribute [rw] warnings
+    #   Warnings detected while processing the input document. The response
+    #   includes a warning if there is a mismatch between the input document
+    #   type and the model type associated with the endpoint that you
+    #   specified. The response can also include warnings for individual
+    #   pages that have a mismatch.
+    #
+    #   The field is empty if the system generated no warnings.
+    #   @return [Array<Types::WarningsListItem>]
+    #
     # @see http://docs.aws.amazon.com/goto/WebAPI/comprehend-2017-11-27/ClassifyDocumentResponse AWS API Documentation
     #
     class ClassifyDocumentResponse < Struct.new(
@@ -863,7 +873,8 @@ module Aws::Comprehend
       :labels,
       :document_metadata,
       :document_type,
-      :errors)
+      :errors,
+      :warnings)
       SENSITIVE = []
       include Aws::Structure
     end
@@ -1004,8 +1015,9 @@ module Aws::Comprehend
     #   @return [Types::DocumentClassifierInputDataConfig]
     #
     # @!attribute [rw] output_data_config
-    #   Enables the addition of output results configuration parameters for
-    #   custom classifier jobs.
+    #   Specifies the location for the output files from a custom classifier
+    #   job. This parameter is required for a request that creates a native
+    #   classifier model.
     #   @return [Types::DocumentClassifierOutputDataConfig]
     #
     # @!attribute [rw] client_request_token
@@ -2830,6 +2842,29 @@ module Aws::Comprehend
       include Aws::Structure
     end
 
+    # The location of the training documents. This parameter is required in
+    # a request to create a native classifier model.
+    #
+    # @!attribute [rw] s3_uri
+    #   The S3 URI location of the training documents specified in the S3Uri
+    #   CSV file.
+    #   @return [String]
+    #
+    # @!attribute [rw] test_s3_uri
+    #   The S3 URI location of the test documents included in the TestS3Uri
+    #   CSV file. This field is not required if you do not specify a test
+    #   CSV file.
+    #   @return [String]
+    #
+    # @see http://docs.aws.amazon.com/goto/WebAPI/comprehend-2017-11-27/DocumentClassifierDocuments AWS API Documentation
+    #
+    class DocumentClassifierDocuments < Struct.new(
+      :s3_uri,
+      :test_s3_uri)
+      SENSITIVE = []
+      include Aws::Structure
+    end
+
     # Provides information for filtering a list of document classifiers. You
     # can only specify one filtering parameter in a request. For more
     # information, see the `ListDocumentClassifiers` operation.
@@ -2936,6 +2971,45 @@ module Aws::Comprehend
     #   `AUGMENTED_MANIFEST`.
     #   @return [Array<Types::AugmentedManifestsListItem>]
     #
+    # @!attribute [rw] document_type
+    #   The type of input documents for training the model. Provide
+    #   plain-text documents to create a plain-text model, and provide
+    #   semi-structured documents to create a native model.
+    #   @return [String]
+    #
+    # @!attribute [rw] documents
+    #   The S3 location of the training documents. This parameter is
+    #   required in a request to create a native classifier model.
+    #   @return [Types::DocumentClassifierDocuments]
+    #
+    # @!attribute [rw] document_reader_config
+    #   Provides configuration parameters to override the default actions
+    #   for extracting text from PDF documents and image files.
+    #
+    #   By default, Amazon Comprehend performs the following actions to
+    #   extract text from files, based on the input file type:
+    #
+    #   * **Word files** - Amazon Comprehend parser extracts the text.
+    #
+    #   * **Digital PDF files** - Amazon Comprehend parser extracts the
+    #     text.
+    #
+    #   * **Image files and scanned PDF files** - Amazon Comprehend uses the
+    #     Amazon Textract `DetectDocumentText` API to extract the text.
+    #
+    #   `DocumentReaderConfig` does not apply to plain text files or Word
+    #   files.
+    #
+    #   For image files and PDF documents, you can override these default
+    #   actions using the fields listed below. For more information, see [
+    #   Setting text extraction options][1] in the Comprehend Developer
+    #   Guide.
+    #
+    #
+    #
+    #   [1]: https://docs.aws.amazon.com/comprehend/latest/dg/idp-set-textract-options.html
+    #   @return [Types::DocumentReaderConfig]
+    #
     # @see http://docs.aws.amazon.com/goto/WebAPI/comprehend-2017-11-27/DocumentClassifierInputDataConfig AWS API Documentation
     #
     class DocumentClassifierInputDataConfig < Struct.new(
@@ -2943,20 +3017,24 @@ module Aws::Comprehend
       :s3_uri,
       :test_s3_uri,
       :label_delimiter,
-      :augmented_manifests)
+      :augmented_manifests,
+      :document_type,
+      :documents,
+      :document_reader_config)
       SENSITIVE = []
       include Aws::Structure
     end
 
-    # Provides output results configuration parameters for custom classifier
-    # jobs.
+    # Provide the location for output data from a custom classifier job.
+    # This field is mandatory if you are training a native classifier model.
     #
     # @!attribute [rw] s3_uri
     #   When you use the `OutputDataConfig` object while creating a custom
     #   classifier, you specify the Amazon S3 location where you want to
-    #   write the confusion matrix. The URI must be in the same Region as
-    #   the API endpoint that you are calling. The location is used as the
-    #   prefix for the actual location of this output file.
+    #   write the confusion matrix and other output files. The URI must be
+    #   in the same Region as the API endpoint that you are calling. The
+    #   location is used as the prefix for the actual location of this
+    #   output file.
     #
     #   When the custom classifier job is finished, the service creates the
     #   output file in a directory specific to the job. The `S3Uri` field
@@ -3009,9 +3087,13 @@ module Aws::Comprehend
     #
     # @!attribute [rw] status
     #   The status of the document classifier. If the status is `TRAINED`
-    #   the classifier is ready to use. If the status is `FAILED` you can
-    #   see additional information about why the classifier wasn't trained
-    #   in the `Message` field.
+    #   the classifier is ready to use. If the status is
+    #   `TRAINED_WITH_WARNINGS` the classifier training succeeded, but you
+    #   should review the warnings returned in the
+    #   `CreateDocumentClassifier` response.
+    #
+    #   If the status is `FAILED` you can see additional information about
+    #   why the classifier wasn't trained in the `Message` field.
     #   @return [String]
     #
     # @!attribute [rw] message
@@ -3241,11 +3323,11 @@ module Aws::Comprehend
     #
     # For image files and PDF documents, you can override these default
     # actions using the fields listed below. For more information, see [
-    # Setting text extraction options][1].
+    # Setting text extraction options][1] in the Comprehend Developer Guide.
     #
     #
     #
-    # [1]: https://docs.aws.amazon.com/comprehend/latest/dg/detecting-cer.html#detecting-cer-pdf
+    # [1]: https://docs.aws.amazon.com/comprehend/latest/dg/idp-set-textract-options.html
     #
     # @!attribute [rw] document_read_action
     #   This field defines the Amazon Textract API operation that Amazon
@@ -8731,5 +8813,36 @@ module Aws::Comprehend
       include Aws::Structure
     end
 
+    # The system identified one of the following warnings while processing
+    # the input document:
+    #
+    # * The document to classify is plain text, but the classifier is a
+    #   native model.
+    #
+    # * The document to classify is semi-structured, but the classifier is a
+    #   plain-text model.
+    #
+    # @!attribute [rw] page
+    #   Page number in the input document.
+    #   @return [Integer]
+    #
+    # @!attribute [rw] warn_code
+    #   The type of warning.
+    #   @return [String]
+    #
+    # @!attribute [rw] warn_message
+    #   Text message associated with the warning.
+    #   @return [String]
+    #
+    # @see http://docs.aws.amazon.com/goto/WebAPI/comprehend-2017-11-27/WarningsListItem AWS API Documentation
+    #
+    class WarningsListItem < Struct.new(
+      :page,
+      :warn_code,
+      :warn_message)
+      SENSITIVE = []
+      include Aws::Structure
+    end
+
   end
 end

data/lib/aws-sdk-comprehend.rb

@@ -52,6 +52,6 @@ require_relative 'aws-sdk-comprehend/customizations'
 # @!group service
 module Aws::Comprehend
 
-  GEM_VERSION = '1.67.0'
+  GEM_VERSION = '1.68.0'
 
 end

metadata

@@ -1,14 +1,14 @@
 --- !ruby/object:Gem::Specification
 name: aws-sdk-comprehend
 version: !ruby/object:Gem::Version
-  version: 1.67.0
+  version: 1.68.0
 platform: ruby
 authors:
 - Amazon Web Services
 autorequire: 
 bindir: bin
 cert_chain: []
-date: 2023-03-24 00:00:00.000000000 Z
+date: 2023-04-19 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: aws-sdk-core