Skip to content

armgit / papra

Public Imported from GitHub
0

The minimalistic document archiving platform.

feat(documents): add content extraction option (#930)

Corentin Thomasset41e9f33b06de
diff --git a/.changeset/major-papers-know.md b/.changeset/major-papers-know.md
new file mode 100644
index 00000000..e3257959
--- /dev/null
+++ b/.changeset/major-papers-know.md
@@ -0,0 +1,5 @@
+---
+"@papra/app": patch
+---
+
+Added an option to fully disable the content extraction feature.
diff --git a/apps/papra-server/src/modules/documents/documents.config.ts b/apps/papra-server/src/modules/documents/documents.config.ts
index c862b0d3..8f7da465 100644
--- a/apps/papra-server/src/modules/documents/documents.config.ts
+++ b/apps/papra-server/src/modules/documents/documents.config.ts
@@ -1,5 +1,6 @@
import type { ConfigDefinition } from 'figue';
import { z } from 'zod';
+import { booleanishSchema } from '../config/config.schemas';
import { ocrLanguagesSchema, stringCoercedOcrLanguagesSchema } from './documents.schemas';
export const documentsConfig = {
@@ -18,4 +19,10 @@ export const documentsConfig = {
default: ['eng'],
env: 'DOCUMENTS_OCR_LANGUAGES',
},
+ isContentExtractionEnabled: {
+ doc: 'Whether to enable content extraction (OCR and text extraction) for uploaded documents',
+ schema: booleanishSchema,
+ default: true,
+ env: 'DOCUMENTS_CONTENT_EXTRACTION_ENABLED',
+ },
} as const satisfies ConfigDefinition;
diff --git a/apps/papra-server/src/modules/documents/documents.usecases.ts b/apps/papra-server/src/modules/documents/documents.usecases.ts
index fcb8960b..61fc672c 100644
--- a/apps/papra-server/src/modules/documents/documents.usecases.ts
+++ b/apps/papra-server/src/modules/documents/documents.usecases.ts
@@ -48,6 +48,7 @@ export async function createDocument({
userId,
organizationId,
ocrLanguages = [],
+ isContentExtractionEnabled = true,
documentsRepository,
documentsStorageService,
generateDocumentId = generateDocumentIdImpl,
@@ -67,6 +68,7 @@ export async function createDocument({
userId?: string;
organizationId: string;
ocrLanguages?: string[];
+ isContentExtractionEnabled?: boolean;
documentsRepository: DocumentsRepository;
documentsStorageService: DocumentStorageService;
generateDocumentId?: () => string;
@@ -157,6 +159,7 @@ export async function createDocument({
documentId,
taskServices,
ocrLanguages,
+ isContentExtractionEnabled,
logger,
});
@@ -195,6 +198,7 @@ export function createDocumentCreationUsecase({
documentActivityRepository: initialDeps.documentActivityRepository ?? createDocumentActivityRepository({ db }),
ocrLanguages: initialDeps.ocrLanguages ?? config.documents.ocrLanguages,
+ isContentExtractionEnabled: initialDeps.isContentExtractionEnabled ?? config.documents.isContentExtractionEnabled,
generateDocumentId: initialDeps.generateDocumentId,
logger: initialDeps.logger,
};
@@ -269,6 +273,7 @@ async function createNewDocument({
documentId,
taskServices,
ocrLanguages = [],
+ isContentExtractionEnabled = true,
logger,
}: {
fileName: string;
@@ -285,6 +290,7 @@ async function createNewDocument({
newFileStorageContext: DocumentStorageContext;
taskServices: TaskServices;
ocrLanguages?: string[];
+ isContentExtractionEnabled?: boolean;
logger: Logger;
}) {
// TODO: wrap in a transaction
@@ -327,10 +333,12 @@ async function createNewDocument({
const { document } = result;
- await taskServices.scheduleJob({
- taskName: 'extract-document-file-content',
- data: { documentId, organizationId, ocrLanguages },
- });
+ if (isContentExtractionEnabled) {
+ await taskServices.scheduleJob({
+ taskName: 'extract-document-file-content',
+ data: { documentId, organizationId, ocrLanguages },
+ });
+ }
logger.info({ documentId, userId, organizationId, mimeType }, 'Document created');