@twin.org/document-management-service 0.0.1-next.9 → 0.0.1

package/dist/esm/index.mjs

@@ -1,10 +1,10 @@
+import { AuditableItemGraphTypes, AuditableItemGraphContexts } from '@twin.org/auditable-item-graph-models';
 import { Guards, ComponentFactory, Converter, Coerce, Is, BaseError, GeneralError, Urn, NotFoundError, ObjectHelper } from '@twin.org/core';
 import { DocumentTypes, DocumentContexts } from '@twin.org/document-management-models';
-import { SchemaOrgContexts, SchemaOrgDataTypes } from '@twin.org/standards-schema-org';
+import { SchemaOrgContexts, SchemaOrgTypes, SchemaOrgDataTypes } from '@twin.org/standards-schema-org';
 import { UneceDocumentCodes } from '@twin.org/standards-unece';
 import { HttpStatusCode, HeaderTypes, MimeTypes } from '@twin.org/web';
 import { AttestationContexts } from '@twin.org/attestation-models';
-import { AuditableItemGraphTypes, AuditableItemGraphContexts } from '@twin.org/auditable-item-graph-models';
 import { BlobStorageContexts } from '@twin.org/blob-storage-models';
 import { Sha256 } from '@twin.org/crypto';
 import { JsonLdProcessor } from '@twin.org/data-json-ld';
@@ -145,9 +145,13 @@ function generateRestRoutesDocumentManagement(baseRouteName, componentName) {
                         id: "DocumentManagementGetResponseExample",
                         response: {
                             body: {
-                                "@context": [DocumentContexts.ContextRoot, DocumentContexts.ContextRootCommon],
-                                type: DocumentTypes.DocumentList,
-                                documents: [
+                                "@context": [
+                                    SchemaOrgContexts.ContextRoot,
+                                    DocumentContexts.ContextRoot,
+                                    DocumentContexts.ContextRootCommon
+                                ],
+                                type: SchemaOrgTypes.ItemList,
+                                [SchemaOrgTypes.ItemListElement]: [
                                     {
                                         "@context": [
                                             DocumentContexts.ContextRoot,
@@ -185,9 +189,13 @@ function generateRestRoutesDocumentManagement(baseRouteName, componentName) {
                         id: "DocumentManagementGetResponseExample",
                         response: {
                             body: {
-                                "@context": [DocumentContexts.ContextRoot, DocumentContexts.ContextRootCommon],
-                                type: DocumentTypes.DocumentList,
-                                documents: [
+                                "@context": [
+                                    SchemaOrgContexts.ContextRoot,
+                                    DocumentContexts.ContextRoot,
+                                    DocumentContexts.ContextRootCommon
+                                ],
+                                type: SchemaOrgTypes.ItemList,
+                                [SchemaOrgTypes.ItemListElement]: [
                                     {
                                         "@context": [
                                             DocumentContexts.ContextRoot,
@@ -222,7 +230,101 @@ function generateRestRoutesDocumentManagement(baseRouteName, componentName) {
             }
         ]
     };
-    const documentManagementRemoveRoute = {
+    const documentManagementGetRevisionRoute = {
+        operationId: "DocumentManagementGetRevision",
+        summary: "Get the data for a document revision from document management",
+        tag: tagsDocumentManagement[0].name,
+        method: "GET",
+        path: `${baseRouteName}/:auditableItemGraphDocumentId/:revision`,
+        handler: async (httpRequestContext, request) => documentManagementGetRevision(httpRequestContext, componentName, request),
+        requestType: {
+            type: "IDocumentManagementGetRequest",
+            examples: [
+                {
+                    id: "DocumentManagementGetRevisionRequestExample",
+                    request: {
+                        pathParams: {
+                            auditableItemGraphDocumentId: "aig:123456",
+                            revision: "1"
+                        }
+                    }
+                }
+            ]
+        },
+        responseType: [
+            {
+                type: "IDocumentManagementGetRevisionResponse",
+                examples: [
+                    {
+                        id: "DocumentManagementGetRevisionResponseExample",
+                        response: {
+                            body: {
+                                "@context": [
+                                    DocumentContexts.ContextRoot,
+                                    DocumentContexts.ContextRootCommon,
+                                    SchemaOrgContexts.ContextRoot
+                                ],
+                                type: DocumentTypes.Document,
+                                id: "2721000:0",
+                                documentId: "2721000",
+                                documentIdFormat: "bol",
+                                documentCode: UneceDocumentCodes.BillOfLading,
+                                documentRevision: 1,
+                                blobStorageId: "blob-memory:c57d94b088f4c6d2cb32ded014813d0c786aa00134c8ee22f84b1e2545602a70",
+                                blobHash: "sha256:123456",
+                                dateCreated: "2024-01-01T00:00:00Z",
+                                annotationObject: {
+                                    "@context": "https://schema.org",
+                                    "@type": "DigitalDocument",
+                                    name: "myfile.pdf"
+                                },
+                                nodeIdentity: "did:entity-storage:0x6363636363636363636363636363636363636363636363636363636363636363",
+                                userIdentity: "did:entity-storage:0x6363636363636363636363636363636363636363636363636363636363636363"
+                            }
+                        }
+                    }
+                ]
+            },
+            {
+                type: "IDocumentManagementGetRevisionResponse",
+                mimeType: MimeTypes.JsonLd,
+                examples: [
+                    {
+                        id: "DocumentManagementGetRevisionResponseExample",
+                        response: {
+                            body: {
+                                "@context": [
+                                    DocumentContexts.ContextRoot,
+                                    DocumentContexts.ContextRootCommon,
+                                    SchemaOrgContexts.ContextRoot
+                                ],
+                                type: DocumentTypes.Document,
+                                id: "2721000:0",
+                                documentId: "2721000",
+                                documentIdFormat: "bol",
+                                documentCode: UneceDocumentCodes.BillOfLading,
+                                documentRevision: 1,
+                                blobStorageId: "blob-memory:c57d94b088f4c6d2cb32ded014813d0c786aa00134c8ee22f84b1e2545602a70",
+                                blobHash: "sha256:123456",
+                                dateCreated: "2024-01-01T00:00:00Z",
+                                annotationObject: {
+                                    "@context": "https://schema.org",
+                                    "@type": "DigitalDocument",
+                                    name: "myfile.pdf"
+                                },
+                                nodeIdentity: "did:entity-storage:0x6363636363636363636363636363636363636363636363636363636363636363",
+                                userIdentity: "did:entity-storage:0x6363636363636363636363636363636363636363636363636363636363636363"
+                            }
+                        }
+                    }
+                ]
+            },
+            {
+                type: "INotFoundResponse"
+            }
+        ]
+    };
+    const documentManagementRemoveRevisionRoute = {
         operationId: "DocumentManagementRemove",
         summary: "Remove an document from an auditable item graph vertex",
         tag: tagsDocumentManagement[0].name,
@@ -273,98 +375,76 @@ function generateRestRoutesDocumentManagement(baseRouteName, componentName) {
             ]
         },
         responseType: [
-        // {
-        // 	type: nameof<IDocumentManagementQueryResponse>(),
-        // 	examples: [
-        // 		{
-        // 			id: "DocumentManagementQueryResponseExample",
-        // 			response: {
-        // 				body: {
-        // 					"@context": [DocumentContexts.ContextRoot, DocumentContexts.ContextRootCommon],
-        // 					type: DocumentTypes.DocumentList,
-        // 					documents: [
-        // 						{
-        // 							"@context": [
-        // 								DocumentContexts.ContextRoot,
-        // 								DocumentContexts.ContextRootCommon,
-        // 								SchemaOrgContexts.ContextRoot
-        // 							],
-        // 							type: DocumentTypes.Document,
-        // 							id: "2721000:0",
-        // 							documentId: "2721000",
-        // 							documentIdFormat: "bol",
-        // 							documentCode: UneceDocumentCodes.BillOfLading,
-        // 							documentRevision: 0,
-        // 							blobStorageId:
-        // 								"blob-memory:c57d94b088f4c6d2cb32ded014813d0c786aa00134c8ee22f84b1e2545602a70",
-        // 							blobHash: "sha256:123456",
-        // 							dateCreated: "2024-01-01T00:00:00Z",
-        // 							annotationObject: {
-        // 								"@context": "https://schema.org",
-        // 								"@type": "DigitalDocument",
-        // 								name: "myfile.pdf"
-        // 							},
-        // 							nodeIdentity:
-        // 								"did:entity-storage:0x6363636363636363636363636363636363636363636363636363636363636363",
-        // 							userIdentity:
-        // 								"did:entity-storage:0x6363636363636363636363636363636363636363636363636363636363636363"
-        // 						}
-        // 					]
-        // 				}
-        // 			}
-        // 		}
-        // 	]
-        // },
-        // {
-        // 	type: nameof<IDocumentManagementQueryResponse>(),
-        // 	mimeType: MimeTypes.JsonLd,
-        // 	examples: [
-        // 		{
-        // 			id: "DocumentManagementListResponseJsonLdExample",
-        // 			response: {
-        // 				body: {
-        // 					"@context": [DocumentContexts.ContextRoot, DocumentContexts.ContextRootCommon],
-        // 					type: DocumentTypes.DocumentList,
-        // 					documents: [
-        // 						{
-        // 							"@context": [
-        // 								DocumentContexts.ContextRoot,
-        // 								DocumentContexts.ContextRootCommon,
-        // 								SchemaOrgContexts.ContextRoot
-        // 							],
-        // 							type: DocumentTypes.Document,
-        // 							id: "2721000:0",
-        // 							documentId: "2721000",
-        // 							documentIdFormat: "bol",
-        // 							documentCode: UneceDocumentCodes.BillOfLading,
-        // 							documentRevision: 0,
-        // 							blobStorageId:
-        // 								"blob-memory:c57d94b088f4c6d2cb32ded014813d0c786aa00134c8ee22f84b1e2545602a70",
-        // 							blobHash: "sha256:123456",
-        // 							dateCreated: "2024-01-01T00:00:00Z",
-        // 							annotationObject: {
-        // 								"@context": "https://schema.org",
-        // 								"@type": "DigitalDocument",
-        // 								name: "myfile.pdf"
-        // 							},
-        // 							nodeIdentity:
-        // 								"did:entity-storage:0x6363636363636363636363636363636363636363636363636363636363636363",
-        // 							userIdentity:
-        // 								"did:entity-storage:0x6363636363636363636363636363636363636363636363636363636363636363"
-        // 						}
-        // 					]
-        // 				}
-        // 			}
-        // 		}
-        // 	]
-        // }
+            {
+                type: "IDocumentManagementQueryResponse",
+                examples: [
+                    {
+                        id: "DocumentManagementQueryResponseExample",
+                        response: {
+                            body: {
+                                "@context": [SchemaOrgContexts.ContextRoot, AuditableItemGraphContexts.ContextRoot],
+                                type: [SchemaOrgTypes.ItemList, AuditableItemGraphTypes.VertexList],
+                                [SchemaOrgTypes.ItemListElement]: [
+                                    {
+                                        "@context": [
+                                            AuditableItemGraphContexts.ContextRoot,
+                                            AuditableItemGraphContexts.ContextRootCommon
+                                        ],
+                                        id: "aig:c7c7c7c7c7c7c7c7c7c7c7c7c7c7c7c7c7c7c7c7c7c7c7c7c7c7c7c7c7c7c7c7",
+                                        type: AuditableItemGraphTypes.Vertex,
+                                        dateCreated: "2024-08-22T04:13:20.000Z",
+                                        aliases: [
+                                            {
+                                                "@context": [AuditableItemGraphContexts.ContextRoot],
+                                                id: "test-id-0",
+                                                type: AuditableItemGraphTypes.Alias,
+                                                dateCreated: "2024-08-22T04:13:20.000Z"
+                                            }
+                                        ],
+                                        resources: [
+                                            {
+                                                "@context": AuditableItemGraphContexts.ContextRoot,
+                                                type: AuditableItemGraphTypes.Resource,
+                                                dateCreated: "2024-08-22T04:13:20.000Z",
+                                                resourceObject: {
+                                                    "@context": [
+                                                        "https://schema.twindev.org/documents/",
+                                                        "https://schema.twindev.org/common/",
+                                                        "https://schema.org"
+                                                    ],
+                                                    type: "Document",
+                                                    id: "test-id-0:0",
+                                                    documentId: "test-id-0",
+                                                    documentCode: "unece:DocumentCodeList#705",
+                                                    documentRevision: 0,
+                                                    annotationObject: {
+                                                        "@context": "https://schema.org",
+                                                        type: "DigitalDocument",
+                                                        name: "bill-of-lading"
+                                                    },
+                                                    blobHash: "sha256:E3Duqrp6bHojSx+CzDttAToAiP1eFkCDAPBbKLABVGM=",
+                                                    blobStorageId: "blob:memory:1370eeaaba7a6c7a234b1f82cc3b6d013a0088fd5e16408300f05b28b0015463",
+                                                    dateCreated: "2024-08-22T04:13:20.000Z",
+                                                    nodeIdentity: "did:entity-storage:0x0101010101010101010101010101010101010101010101010101010101010101",
+                                                    userIdentity: "did:entity-storage:0x0404040404040404040404040404040404040404040404040404040404040404"
+                                                }
+                                            }
+                                        ]
+                                    }
+                                ]
+                            }
+                        }
+                    }
+                ]
+            }
         ]
     };
     return [
         documentManagementCreateRoute,
         documentManagementUpdateRoute,
         documentManagementGetRoute,
-        documentManagementRemoveRoute,
+        documentManagementGetRevisionRoute,
+        documentManagementRemoveRevisionRoute,
         documentManagementQueryRoute
     ];
 }
@@ -409,7 +489,9 @@ async function documentManagementGet(httpRequestContext, componentName, request)
         includeBlobStorageMetadata: Coerce.boolean(request.query?.includeBlobStorageMetadata),
         includeBlobStorageData: Coerce.boolean(request.query?.includeBlobStorageData),
         includeAttestation: Coerce.boolean(request.query?.includeAttestation),
-        includeRemoved: Coerce.boolean(request.query?.includeRemoved)
+        includeRemoved: Coerce.boolean(request.query?.includeRemoved),
+        extractRuleGroupId: request.query?.extractRuleGroupId,
+        extractMimeType: request.query?.extractMimeType
     }, request.query?.cursor, Coerce.integer(request.query?.pageSize), httpRequestContext.userIdentity, httpRequestContext.nodeIdentity);
     return {
         headers: {
@@ -419,7 +501,36 @@ async function documentManagementGet(httpRequestContext, componentName, request)
     };
 }
 /**
- * UPdate the document from the auditable item graph vertex.
+ * Get the document revision from the auditable item graph vertex.
+ * @param httpRequestContext The request context for the API.
+ * @param componentName The name of the component to use in the routes.
+ * @param request The request.
+ * @returns The response object with additional http response properties.
+ */
+async function documentManagementGetRevision(httpRequestContext, componentName, request) {
+    Guards.object(ROUTES_SOURCE, "request", request);
+    Guards.object(ROUTES_SOURCE, "request.pathParams", request.pathParams);
+    Guards.stringValue(ROUTES_SOURCE, "request.pathParams.auditableItemGraphDocumentId", request.pathParams.auditableItemGraphDocumentId);
+    const revision = Coerce.integer(request.pathParams.revision);
+    Guards.integer(ROUTES_SOURCE, "revision", revision);
+    const mimeType = request.headers?.[HeaderTypes.Accept] === MimeTypes.JsonLd ? "jsonld" : "json";
+    const component = ComponentFactory.get(componentName);
+    const result = await component.getRevision(request.pathParams.auditableItemGraphDocumentId, revision, {
+        includeBlobStorageMetadata: Coerce.boolean(request.query?.includeBlobStorageMetadata),
+        includeBlobStorageData: Coerce.boolean(request.query?.includeBlobStorageData),
+        includeAttestation: Coerce.boolean(request.query?.includeAttestation),
+        extractRuleGroupId: request.query?.extractRuleGroupId,
+        extractMimeType: request.query?.extractMimeType
+    }, httpRequestContext.userIdentity, httpRequestContext.nodeIdentity);
+    return {
+        headers: {
+            [HeaderTypes.ContentType]: mimeType === "json" ? MimeTypes.Json : MimeTypes.JsonLd
+        },
+        body: result
+    };
+}
+/**
+ * Update the document from the auditable item graph vertex.
  * @param httpRequestContext The request context for the API.
  * @param componentName The name of the component to use in the routes.
  * @param request The request.
@@ -503,6 +614,11 @@ class DocumentManagementService {
      * @internal
      */
     _attestationComponent;
+    /**
+     * The connector for the data processing.
+     * @internal
+     */
+    _dataProcessingComponent;
     /**
      * Create a new instance of DocumentManagementService.
      * @param options The options for the service.
@@ -511,6 +627,7 @@ class DocumentManagementService {
         this._auditableItemGraphComponent = ComponentFactory.get(options?.auditableItemGraphComponentType ?? "auditable-item-graph");
         this._blobStorageComponent = ComponentFactory.get(options?.blobStorageComponentType ?? "blob-storage");
         this._attestationComponent = ComponentFactory.get(options?.attestationComponentType ?? "attestation");
+        this._dataProcessingComponent = ComponentFactory.get(options?.dataProcessingComponentType ?? "data-processing");
         SchemaOrgDataTypes.registerRedirects();
     }
     /**
@@ -565,7 +682,7 @@ class DocumentManagementService {
                     SchemaOrgContexts.ContextRoot
                 ],
                 type: DocumentTypes.Document,
-                id: `${documentId}:0`,
+                id: this.createDocumentId(documentId, 0),
                 documentId,
                 documentIdFormat,
                 documentCode,
@@ -619,12 +736,13 @@ class DocumentManagementService {
         Guards.stringValue(this.CLASS_NAME, "userIdentity", userIdentity);
         Guards.stringValue(this.CLASS_NAME, "nodeIdentity", nodeIdentity);
         try {
-            const documentVertex = await this._auditableItemGraphComponent.get(auditableItemGraphDocumentId);
+            const documentVertex = await this._auditableItemGraphComponent.get(auditableItemGraphDocumentId, { includeDeleted: true });
             if (Is.empty(documentVertex.resources)) {
                 throw new NotFoundError(this.CLASS_NAME, "documentRevisionNone");
             }
             const documents = await this.getDocumentsFromVertex(documentVertex);
-            const latestRevision = documents.documents[0];
+            const latestRevision = documents.itemListElement[0];
+            documentVertex.resources = documentVertex.resources.filter(r => Is.empty(r.dateDeleted));
             if (Is.empty(latestRevision)) {
                 throw new NotFoundError(this.CLASS_NAME, "documentRevisionNone");
             }
@@ -655,7 +773,7 @@ class DocumentManagementService {
                     const blobStorageId = await this._blobStorageComponent.create(Converter.bytesToBase64(blob), undefined, undefined, undefined, undefined, userIdentity, nodeIdentity);
                     const newRevision = ObjectHelper.clone(latestRevision);
                     newRevision.documentRevision++;
-                    newRevision.id = `${newRevision.documentId}:${newRevision.documentRevision}`;
+                    newRevision.id = this.createDocumentId(newRevision.documentId, newRevision.documentRevision);
                     newRevision.blobHash = newBlobHash;
                     newRevision.blobStorageId = blobStorageId;
                     newRevision.annotationObject = annotationObject;
@@ -706,6 +824,8 @@ class DocumentManagementService {
      * @param options.includeBlobStorageData Flag to include the blob storage data for the document, defaults to false.
      * @param options.includeAttestation Flag to include the attestation information for the document, defaults to false.
      * @param options.includeRemoved Flag to include deleted documents, defaults to false.
+     * @param options.extractRuleGroupId If provided will extract data from the document using the specified rule group id.
+     * @param options.extractMimeType By default extraction will auto detect the mime type of the document, this can be used to override the detection.
      * @param cursor The cursor to get the next chunk of revisions.
      * @param pageSize Page size of items to return, defaults to 1 so only most recent is returned.
      * @param userIdentity The identity to perform the auditable item graph operation with.
@@ -727,6 +847,43 @@ class DocumentManagementService {
             throw new GeneralError(this.CLASS_NAME, "getFailed", undefined, error);
         }
     }
+    /**
+     * Get a document revision using it's auditable item graph vertex id.
+     * @param auditableItemGraphDocumentId The auditable item graph vertex id which contains the document.
+     * @param revision The revision id for the document.
+     * @param options Additional options for the get operation.
+     * @param options.includeBlobStorageMetadata Flag to include the blob storage metadata for the document, defaults to false.
+     * @param options.includeBlobStorageData Flag to include the blob storage data for the document, defaults to false.
+     * @param options.includeAttestation Flag to include the attestation information for the document, defaults to false.
+     * @param options.extractRuleGroupId If provided will extract data from the document using the specified rule group id.
+     * @param options.extractMimeType By default extraction will auto detect the mime type of the document, this can be used to override the detection.
+     * @param userIdentity The identity to perform the auditable item graph operation with.
+     * @param nodeIdentity The node identity to use for vault operations.
+     * @returns The documents and revisions if requested, ordered by revision descending, cursor is set if there are more document revisions.
+     */
+    async getRevision(auditableItemGraphDocumentId, revision, options, userIdentity, nodeIdentity) {
+        Urn.guard(this.CLASS_NAME, "auditableItemGraphDocumentId", auditableItemGraphDocumentId);
+        Guards.integer(this.CLASS_NAME, "revision", revision);
+        try {
+            const documentVertex = await this._auditableItemGraphComponent.get(auditableItemGraphDocumentId, { includeDeleted: true });
+            if (Is.empty(documentVertex.resources)) {
+                throw new NotFoundError(this.CLASS_NAME, "documentRevisionNone");
+            }
+            documentVertex.resources = documentVertex.resources.filter(d => d.resourceObject?.documentRevision === revision);
+            if (documentVertex.resources.length === 0) {
+                throw new NotFoundError(this.CLASS_NAME, "documentRevisionNotFound", revision.toString());
+            }
+            // Populate the document and revisions with the options set
+            const docList = await this.getDocumentsFromVertex(documentVertex, options, undefined, undefined, userIdentity, nodeIdentity);
+            return JsonLdProcessor.compact(docList.itemListElement[0], docList.itemListElement[0]["@context"]);
+        }
+        catch (error) {
+            if (BaseError.someErrorName(error, "NotFoundError")) {
+                throw error;
+            }
+            throw new GeneralError(this.CLASS_NAME, "getRevisionFailed", undefined, error);
+        }
+    }
     /**
      * Remove an auditable item graph vertex using it's id.
      * The document dateDeleted will be set, but can still be queried with the includeRemoved flag.
@@ -939,7 +1096,8 @@ class DocumentManagementService {
      * @param options.includeBlobStorageMetadata Flag to include the blob storage metadata for the document, defaults to false.
      * @param options.includeBlobStorageData Flag to include the blob storage data for the document, defaults to false.
      * @param options.includeAttestation Flag to include the attestation information for the document, defaults to false.
-     * @param options.includeRemoved Flag to include deleted documents, defaults to false.
+     * @param options.extractRuleGroupId If provided will extract data from the document using the specified rule group id.
+     * @param options.extractMimeType By default extraction will auto detect the mime type of the document, this can be used to override the detection.
      * @param cursor The cursor to get the next chunk of revisions.
      * @param pageSize Page size of items to return, defaults to 1 so only most recent is returned.
      * @param userIdentity The identity to perform the auditable item graph operation with.
@@ -950,12 +1108,12 @@ class DocumentManagementService {
     async getDocumentsFromVertex(documentVertex, options, cursor, pageSize, userIdentity, nodeIdentity) {
         const docList = {
             "@context": [
+                SchemaOrgContexts.ContextRoot,
                 DocumentContexts.ContextRoot,
-                DocumentContexts.ContextRootCommon,
-                SchemaOrgContexts.ContextRoot
+                DocumentContexts.ContextRootCommon
             ],
-            type: DocumentTypes.DocumentList,
-            documents: []
+            type: SchemaOrgTypes.ItemList,
+            [SchemaOrgTypes.ItemListElement]: []
         };
         if (Is.arrayValue(documentVertex.resources)) {
             // Sort by newest revision first
@@ -964,20 +1122,39 @@ class DocumentManagementService {
             const startIndex = Coerce.integer(cursor) ?? 0;
             const endIndex = Math.min(startIndex + (pageSize ?? 1), documentVertex.resources.length);
             const slicedResources = documentVertex.resources.slice(startIndex, endIndex);
-            docList.cursor =
+            docList[SchemaOrgTypes.NextItem] =
                 documentVertex.resources.length > endIndex ? (endIndex + 1).toString() : undefined;
             const includeBlobStorageMetadata = options?.includeBlobStorageMetadata ?? false;
             const includeBlobStorageData = options?.includeBlobStorageData ?? false;
             const includeAttestation = options?.includeAttestation ?? false;
+            const extractData = Is.stringValue(options?.extractRuleGroupId);
             for (let i = 0; i < slicedResources.length; i++) {
                 const document = slicedResources[i].resourceObject;
                 if (Is.object(document)) {
-                    docList.documents.push(document);
-                    if (includeBlobStorageMetadata || includeBlobStorageData) {
-                        const blobEntry = await this._blobStorageComponent.get(document.blobStorageId, includeBlobStorageData, userIdentity, nodeIdentity);
-                        document.blobStorageEntry = blobEntry;
-                        if (!docList["@context"].includes(BlobStorageContexts.ContextRoot)) {
-                            docList["@context"].push(BlobStorageContexts.ContextRoot);
+                    document.dateDeleted = slicedResources[i].dateDeleted;
+                    docList[SchemaOrgTypes.ItemListElement].push(document);
+                    const blobRequired = includeBlobStorageMetadata || includeBlobStorageData;
+                    if (blobRequired || extractData) {
+                        const blobEntry = await this._blobStorageComponent.get(document.blobStorageId, {
+                            includeContent: includeBlobStorageData || extractData
+                        }, userIdentity, nodeIdentity);
+                        if (blobRequired) {
+                            document.blobStorageEntry = blobEntry;
+                            if (!docList["@context"].includes(BlobStorageContexts.ContextRoot)) {
+                                docList["@context"].push(BlobStorageContexts.ContextRoot);
+                            }
+                        }
+                        if (Is.stringValue(options?.extractRuleGroupId) && Is.stringValue(blobEntry.blob)) {
+                            const binaryBlob = Converter.base64ToBytes(blobEntry.blob);
+                            document.extractedData = await this._dataProcessingComponent.extract(options.extractRuleGroupId, binaryBlob, undefined, options?.extractMimeType);
+                        }
+                        // If we have the blob data due to extraction but we weren't asked for it
+                        // then we remove it from the document
+                        if (!blobRequired) {
+                            delete document.blobStorageEntry;
+                        }
+                        else if (!includeBlobStorageData) {
+                            delete document.blobStorageEntry?.blob;
                         }
                     }
                     if (includeAttestation && Is.stringValue(document.attestationId)) {
@@ -1024,15 +1201,26 @@ class DocumentManagementService {
         };
         return this._attestationComponent.create(documentAttestation, undefined, userIdentity, nodeIdentity);
     }
+    /**
+     * Create a document id from the document id and revision.
+     * @param documentId The document id to create.
+     * @param revision The revision of the document.
+     * @returns The document id.
+     * @internal
+     */
+    createDocumentId(documentId, revision) {
+        const documentIdHash = Converter.bytesToBase64Url(Sha256.sum256(Converter.utf8ToBytes(documentId)));
+        return `document:${documentIdHash}:${revision}`;
+    }
 }
 
 const restEntryPoints = [
     {
-        name: "documents",
-        defaultBaseRoute: "documents",
+        name: "document-management",
+        defaultBaseRoute: "document-management",
         tags: tagsDocumentManagement,
         generateRoutes: generateRestRoutesDocumentManagement
     }
 ];
 
-export { DocumentManagementService, documentManagementCreate, documentManagementGet, documentManagementQuery, documentManagementRemove, documentManagementUpdate, generateRestRoutesDocumentManagement, restEntryPoints, tagsDocumentManagement };
+export { DocumentManagementService, documentManagementCreate, documentManagementGet, documentManagementGetRevision, documentManagementQuery, documentManagementRemove, documentManagementUpdate, generateRestRoutesDocumentManagement, restEntryPoints, tagsDocumentManagement };

package/dist/types/documentManagementRoutes.d.ts

@@ -1,5 +1,5 @@
 import type { ICreatedResponse, IHttpRequestContext, INoContentResponse, IRestRoute, ITag } from "@twin.org/api-models";
-import { type IDocumentManagementCreateRequest, type IDocumentManagementGetRequest, type IDocumentManagementGetResponse, type IDocumentManagementQueryRequest, type IDocumentManagementQueryResponse, type IDocumentManagementRemoveRequest, type IDocumentManagementUpdateRequest } from "@twin.org/document-management-models";
+import { type IDocumentManagementGetRevisionRequest, type IDocumentManagementGetRevisionResponse, type IDocumentManagementCreateRequest, type IDocumentManagementGetRequest, type IDocumentManagementGetResponse, type IDocumentManagementQueryRequest, type IDocumentManagementQueryResponse, type IDocumentManagementRemoveRequest, type IDocumentManagementUpdateRequest } from "@twin.org/document-management-models";
 /**
  * The tag to associate with the routes.
  */
@@ -28,7 +28,15 @@ export declare function documentManagementCreate(httpRequestContext: IHttpReques
  */
 export declare function documentManagementGet(httpRequestContext: IHttpRequestContext, componentName: string, request: IDocumentManagementGetRequest): Promise<IDocumentManagementGetResponse>;
 /**
- * UPdate the document from the auditable item graph vertex.
+ * Get the document revision from the auditable item graph vertex.
+ * @param httpRequestContext The request context for the API.
+ * @param componentName The name of the component to use in the routes.
+ * @param request The request.
+ * @returns The response object with additional http response properties.
+ */
+export declare function documentManagementGetRevision(httpRequestContext: IHttpRequestContext, componentName: string, request: IDocumentManagementGetRevisionRequest): Promise<IDocumentManagementGetRevisionResponse>;
+/**
+ * Update the document from the auditable item graph vertex.
  * @param httpRequestContext The request context for the API.
  * @param componentName The name of the component to use in the routes.
  * @param request The request.

package/dist/types/documentManagementService.d.ts

@@ -1,6 +1,6 @@
 import { type IAuditableItemGraphVertexList } from "@twin.org/auditable-item-graph-models";
 import { type IJsonLdNodeObject } from "@twin.org/data-json-ld";
-import { type IDocumentList, type IDocumentManagementComponent } from "@twin.org/document-management-models";
+import { type IDocument, type IDocumentList, type IDocumentManagementComponent } from "@twin.org/document-management-models";
 import { UneceDocumentCodes } from "@twin.org/standards-unece";
 import type { IDocumentManagementServiceConstructorOptions } from "./models/IDocumentManagementStorageServiceConstructorOptions";
 /**
@@ -72,6 +72,8 @@ export declare class DocumentManagementService implements IDocumentManagementCom
      * @param options.includeBlobStorageData Flag to include the blob storage data for the document, defaults to false.
      * @param options.includeAttestation Flag to include the attestation information for the document, defaults to false.
      * @param options.includeRemoved Flag to include deleted documents, defaults to false.
+     * @param options.extractRuleGroupId If provided will extract data from the document using the specified rule group id.
+     * @param options.extractMimeType By default extraction will auto detect the mime type of the document, this can be used to override the detection.
      * @param cursor The cursor to get the next chunk of revisions.
      * @param pageSize Page size of items to return, defaults to 1 so only most recent is returned.
      * @param userIdentity The identity to perform the auditable item graph operation with.
@@ -83,7 +85,30 @@ export declare class DocumentManagementService implements IDocumentManagementCom
         includeBlobStorageData?: boolean;
         includeAttestation?: boolean;
         includeRemoved?: boolean;
+        extractRuleGroupId?: string;
+        extractMimeType?: string;
     }, cursor?: string, pageSize?: number, userIdentity?: string, nodeIdentity?: string): Promise<IDocumentList>;
+    /**
+     * Get a document revision using it's auditable item graph vertex id.
+     * @param auditableItemGraphDocumentId The auditable item graph vertex id which contains the document.
+     * @param revision The revision id for the document.
+     * @param options Additional options for the get operation.
+     * @param options.includeBlobStorageMetadata Flag to include the blob storage metadata for the document, defaults to false.
+     * @param options.includeBlobStorageData Flag to include the blob storage data for the document, defaults to false.
+     * @param options.includeAttestation Flag to include the attestation information for the document, defaults to false.
+     * @param options.extractRuleGroupId If provided will extract data from the document using the specified rule group id.
+     * @param options.extractMimeType By default extraction will auto detect the mime type of the document, this can be used to override the detection.
+     * @param userIdentity The identity to perform the auditable item graph operation with.
+     * @param nodeIdentity The node identity to use for vault operations.
+     * @returns The documents and revisions if requested, ordered by revision descending, cursor is set if there are more document revisions.
+     */
+    getRevision(auditableItemGraphDocumentId: string, revision: number, options?: {
+        includeBlobStorageMetadata?: boolean;
+        includeBlobStorageData?: boolean;
+        includeAttestation?: boolean;
+        extractRuleGroupId?: string;
+        extractMimeType?: string;
+    }, userIdentity?: string, nodeIdentity?: string): Promise<IDocument>;
     /**
      * Remove an auditable item graph vertex using it's id.
      * The document dateDeleted will be set, but can still be queried with the includeRemoved flag.