@twin.org/document-management-service 0.0.1-next.10 → 0.0.1-next.11

package/dist/cjs/index.cjs

@@ -482,6 +482,11 @@ 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.
@@ -490,6 +495,7 @@ class DocumentManagementService {
         this._auditableItemGraphComponent = core.ComponentFactory.get(options?.auditableItemGraphComponentType ?? "auditable-item-graph");
         this._blobStorageComponent = core.ComponentFactory.get(options?.blobStorageComponentType ?? "blob-storage");
         this._attestationComponent = core.ComponentFactory.get(options?.attestationComponentType ?? "attestation");
+        this._dataProcessingComponent = core.ComponentFactory.get(options?.dataProcessingComponentType ?? "data-processing");
         standardsSchemaOrg.SchemaOrgDataTypes.registerRedirects();
     }
     /**
@@ -685,6 +691,8 @@ 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.
@@ -918,7 +926,8 @@ 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.
@@ -948,15 +957,31 @@ class DocumentManagementService {
             const includeBlobStorageMetadata = options?.includeBlobStorageMetadata ?? false;
             const includeBlobStorageData = options?.includeBlobStorageData ?? false;
             const includeAttestation = options?.includeAttestation ?? false;
+            const extractData = core.Is.stringValue(options?.extractRuleGroupId);
             for (let i = 0; i < slicedResources.length; i++) {
                 const document = slicedResources[i].resourceObject;
                 if (core.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(blobStorageModels.BlobStorageContexts.ContextRoot)) {
-                            docList["@context"].push(blobStorageModels.BlobStorageContexts.ContextRoot);
+                    const blobRequired = includeBlobStorageMetadata || includeBlobStorageData;
+                    if (blobRequired || extractData) {
+                        const blobEntry = await this._blobStorageComponent.get(document.blobStorageId, includeBlobStorageData || extractData, userIdentity, nodeIdentity);
+                        if (blobRequired) {
+                            document.blobStorageEntry = blobEntry;
+                            if (!docList["@context"].includes(blobStorageModels.BlobStorageContexts.ContextRoot)) {
+                                docList["@context"].push(blobStorageModels.BlobStorageContexts.ContextRoot);
+                            }
+                        }
+                        if (core.Is.stringValue(options?.extractRuleGroupId) && core.Is.stringValue(blobEntry.blob)) {
+                            const binaryBlob = core.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 && core.Is.stringValue(document.attestationId)) {

package/dist/esm/index.mjs

@@ -480,6 +480,11 @@ 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.
@@ -488,6 +493,7 @@ 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();
     }
     /**
@@ -683,6 +689,8 @@ 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.
@@ -916,7 +924,8 @@ 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.
@@ -946,15 +955,31 @@ class DocumentManagementService {
             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);
+                    const blobRequired = includeBlobStorageMetadata || includeBlobStorageData;
+                    if (blobRequired || extractData) {
+                        const blobEntry = await this._blobStorageComponent.get(document.blobStorageId, 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)) {

package/dist/types/documentManagementService.d.ts

@@ -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.
@@ -83,6 +85,8 @@ 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>;
     /**
      * Remove an auditable item graph vertex using it's id.

package/dist/types/models/IDocumentManagementStorageServiceConstructorOptions.d.ts

@@ -18,6 +18,11 @@ export interface IDocumentManagementServiceConstructorOptions {
      * @default attestation
      */
     attestationComponentType?: string;
+    /**
+     * The type of the data processing component.
+     * @default data-processing
+     */
+    dataProcessingComponentType?: string;
     /**
      * The configuration for the service.
      */

package/docs/changelog.md

@@ -1,5 +1,19 @@
 # @twin.org/document-management-service - Changelog
 
+## [0.0.1-next.11](https://github.com/twinfoundation/document-management/compare/document-management-service-v0.0.1-next.10...document-management-service-v0.0.1-next.11) (2025-04-28)
+
+
+### Features
+
+* document get can perform extraction ([#6](https://github.com/twinfoundation/document-management/issues/6)) ([5ce6d37](https://github.com/twinfoundation/document-management/commit/5ce6d37432ad271ca5783f422846f4be98ec2215))
+
+
+### Dependencies
+
+* The following workspace dependencies were updated
+  * dependencies
+    * @twin.org/document-management-models bumped from 0.0.1-next.10 to 0.0.1-next.11
+
 ## [0.0.1-next.10](https://github.com/twinfoundation/document-management/compare/document-management-service-v0.0.1-next.9...document-management-service-v0.0.1-next.10) (2025-04-25)
 
 

package/docs/open-api/spec.json

@@ -477,6 +477,24 @@
 							"type": "boolean"
 						}
 					},
+					{
+						"name": "extractRuleGroupId",
+						"description": "If provided will extract data from the document using the specified rule group id.",
+						"in": "query",
+						"required": false,
+						"schema": {
+							"type": "string"
+						}
+					},
+					{
+						"name": "extractMimeType",
+						"description": "By default extraction will auto detect the mime type of the document, this can be used to override the detection.",
+						"in": "query",
+						"required": false,
+						"schema": {
+							"type": "string"
+						}
+					},
 					{
 						"name": "pageSize",
 						"description": "Page size of items to return, defaults to 1 so only most recent is returned.",
@@ -1467,6 +1485,9 @@
 					"blobStorageEntry": {
 						"$ref": "#/components/schemas/BlobStorageEntry"
 					},
+					"extractedData": {
+						"description": "The data extracted from the document using data extraction services."
+					},
 					"attestationId": {
 						"type": "string",
 						"description": "The attestation for the document if one was created."

package/docs/reference/classes/DocumentManagementService.md

@@ -240,6 +240,18 @@ Flag to include the attestation information for the document, defaults to false.
 
 Flag to include deleted documents, defaults to false.
 
+###### extractRuleGroupId?
+
+`string`
+
+If provided will extract data from the document using the specified rule group id.
+
+###### extractMimeType?
+
+`string`
+
+By default extraction will auto detect the mime type of the document, this can be used to override the detection.
+
 ##### cursor?
 
 `string`

package/docs/reference/interfaces/IDocumentManagementServiceConstructorOptions.md

@@ -46,6 +46,20 @@ attestation
 
 ***
 
+### dataProcessingComponentType?
+
+> `optional` **dataProcessingComponentType**: `string`
+
+The type of the data processing component.
+
+#### Default
+
+```ts
+data-processing
+```
+
+***
+
 ### config?
 
 > `optional` **config**: [`IDocumentManagementServiceConfig`](IDocumentManagementServiceConfig.md)

package/package.json

@@ -1,6 +1,6 @@
 {
 	"name": "@twin.org/document-management-service",
-	"version": "0.0.1-next.10",
+	"version": "0.0.1-next.11",
 	"description": "Document management contract implementation and REST endpoint definitions",
 	"repository": {
 		"type": "git",
@@ -21,7 +21,8 @@
 		"@twin.org/core": "next",
 		"@twin.org/crypto": "next",
 		"@twin.org/data-json-ld": "next",
-		"@twin.org/document-management-models": "0.0.1-next.10",
+		"@twin.org/data-processing-models": "next",
+		"@twin.org/document-management-models": "0.0.1-next.11",
 		"@twin.org/entity": "next",
 		"@twin.org/entity-storage-models": "next",
 		"@twin.org/nameof": "next",