Merge branch 'dev' into feature-remote-ocr-2

[ci skip]

docs/configuration.md

@@ -1800,3 +1800,23 @@ password. All of these options come from their similarly-named [Django settings]
 #### [`PAPERLESS_EMAIL_USE_SSL=<bool>`](#PAPERLESS_EMAIL_USE_SSL) {#PAPERLESS_EMAIL_USE_SSL}
 
 : Defaults to false.
+
+## Remote OCR
+
+#### [`PAPERLESS_REMOTE_OCR_ENGINE=<str>`](#PAPERLESS_REMOTE_OCR_ENGINE) {#PAPERLESS_REMOTE_OCR_ENGINE}
+
+: The remote OCR engine to use. Currently only Azure AI is supported as "azureai".
+
+    Defaults to None, which disables remote OCR.
+
+#### [`PAPERLESS_REMOTE_OCR_API_KEY=<str>`](#PAPERLESS_REMOTE_OCR_API_KEY) {#PAPERLESS_REMOTE_OCR_API_KEY}
+
+: The API key to use for the remote OCR engine.
+
+    Defaults to None.
+
+#### [`PAPERLESS_REMOTE_OCR_ENDPOINT=<str>`](#PAPERLESS_REMOTE_OCR_ENDPOINT) {#PAPERLESS_REMOTE_OCR_ENDPOINT}
+
+: The endpoint to use for the remote OCR engine. This is required for Azure AI.
+
+    Defaults to None.

docs/index.md

@@ -25,9 +25,10 @@ physical documents into a searchable online archive so you can keep, well, _less
 ## Features
 
 -   **Organize and index** your scanned documents with tags, correspondents, types, and more.
--   _Your_ data is stored locally on _your_ server and is never transmitted or shared in any way.
+-   _Your_ data is stored locally on _your_ server and is never transmitted or shared in any way, unless you explicitly choose to do so.
 -   Performs **OCR** on your documents, adding searchable and selectable text, even to documents scanned with only images.
--   Utilizes the open-source Tesseract engine to recognize more than 100 languages.
+    -   Utilizes the open-source Tesseract engine to recognize more than 100 languages.
+    -   _New!_ Supports remote OCR with Azure AI (opt-in).
 -   Documents are saved as PDF/A format which is designed for long term storage, alongside the unaltered originals.
 -   Uses machine-learning to automatically add tags, correspondents and document types to your documents.
 -   Supports PDF documents, images, plain text files, Office documents (Word, Excel, PowerPoint, and LibreOffice equivalents)[^1] and more.

docs/usage.md

@@ -850,6 +850,21 @@ how regularly you intend to scan documents and use paperless.
     performed the task associated with the document, move it to the
     inbox.
 
+## Remote OCR
+
+!!! important
+
+    This feature is disabled by default and will always remain strictly "opt-in".
+
+Paperless-ngx supports performing OCR on documents using remote services. At the moment, this is limited to
+[Microsoft's Azure "Document Intelligence" service](https://azure.microsoft.com/en-us/products/ai-services/ai-document-intelligence).
+This is of course a paid service (with a free tier) which requires an Azure account and subscription. Azure AI is not affiliated with
+Paperless-ngx in any way. When enabled, Paperless-ngx will automatically send appropriate documents to Azure for OCR processing, bypassing
+the local OCR engine. See the [configuration](configuration.md#PAPERLESS_REMOTE_OCR_ENGINE) options for more details.
+
+Additionally, when using a commercial service with this feature, consider both potential costs as well as any associated file size
+or page limitations (e.g. with a free tier).
+
 ## Architecture
 
 Paperless-ngx consists of the following components:

pyproject.toml

@@ -15,6 +15,7 @@ classifiers = [
 # This will allow testing to not install a webserver, mysql, etc
 
 dependencies = [
+  "azure-ai-documentintelligence>=1.0.2",
   "babel>=2.17",
   "bleach~=6.2.0",
   "celery[redis]~=5.5.1",
@@ -239,6 +240,7 @@ testpaths = [
   "src/paperless_tesseract/tests/",
   "src/paperless_tika/tests",
   "src/paperless_text/tests/",
+  "src/paperless_remote/tests/",
 ]
 addopts = [
   "--pythonwarnings=all",

src-ui/messages.xlf

@@ -7671,7 +7671,7 @@
         </context-group>
         <context-group purpose="location">
           <context context-type="sourcefile">src/app/components/document-list/document-list.component.ts</context>
-          <context context-type="linenumber">311</context>
+          <context context-type="linenumber">313</context>
         </context-group>
       </trans-unit>
       <trans-unit id="1494518490116523821" datatype="html">
@@ -7682,7 +7682,7 @@
         </context-group>
         <context-group purpose="location">
           <context context-type="sourcefile">src/app/components/document-list/document-list.component.ts</context>
-          <context context-type="linenumber">304</context>
+          <context context-type="linenumber">306</context>
         </context-group>
       </trans-unit>
       <trans-unit id="8461842260159597706" datatype="html">
@@ -7925,49 +7925,49 @@
         <source>Reset filters / selection</source>
         <context-group purpose="location">
           <context context-type="sourcefile">src/app/components/document-list/document-list.component.ts</context>
-          <context context-type="linenumber">292</context>
+          <context context-type="linenumber">294</context>
         </context-group>
       </trans-unit>
       <trans-unit id="4135055128446167640" datatype="html">
         <source>Open first [selected] document</source>
         <context-group purpose="location">
           <context context-type="sourcefile">src/app/components/document-list/document-list.component.ts</context>
-          <context context-type="linenumber">320</context>
+          <context context-type="linenumber">322</context>
         </context-group>
       </trans-unit>
       <trans-unit id="3629960544875360046" datatype="html">
         <source>Previous page</source>
         <context-group purpose="location">
           <context context-type="sourcefile">src/app/components/document-list/document-list.component.ts</context>
-          <context context-type="linenumber">336</context>
+          <context context-type="linenumber">338</context>
         </context-group>
       </trans-unit>
       <trans-unit id="3337301694210287595" datatype="html">
         <source>Next page</source>
         <context-group purpose="location">
           <context context-type="sourcefile">src/app/components/document-list/document-list.component.ts</context>
-          <context context-type="linenumber">348</context>
+          <context context-type="linenumber">350</context>
         </context-group>
       </trans-unit>
       <trans-unit id="2155249406916744630" datatype="html">
         <source>View &quot;<x id="PH" equiv-text="this.list.activeSavedViewTitle"/>&quot; saved successfully.</source>
         <context-group purpose="location">
           <context context-type="sourcefile">src/app/components/document-list/document-list.component.ts</context>
-          <context context-type="linenumber">381</context>
+          <context context-type="linenumber">383</context>
         </context-group>
       </trans-unit>
       <trans-unit id="4646273665293421938" datatype="html">
         <source>Failed to save view &quot;<x id="PH" equiv-text="this.list.activeSavedViewTitle"/>&quot;.</source>
         <context-group purpose="location">
           <context context-type="sourcefile">src/app/components/document-list/document-list.component.ts</context>
-          <context context-type="linenumber">387</context>
+          <context context-type="linenumber">389</context>
         </context-group>
       </trans-unit>
       <trans-unit id="6837554170707123455" datatype="html">
         <source>View &quot;<x id="PH" equiv-text="savedView.name"/>&quot; created successfully.</source>
         <context-group purpose="location">
           <context context-type="sourcefile">src/app/components/document-list/document-list.component.ts</context>
-          <context context-type="linenumber">431</context>
+          <context context-type="linenumber">435</context>
         </context-group>
       </trans-unit>
       <trans-unit id="739880801667335279" datatype="html">

src-ui/src/app/components/dashboard/dashboard.component.spec.ts

@@ -106,6 +106,7 @@ describe('DashboardComponent', () => {
               }),
             dashboardViews: saved_views.filter((v) => v.show_on_dashboard),
             allViews: saved_views,
+            setDocumentCount: jest.fn(),
           },
         },
         provideHttpClient(withInterceptorsFromDi()),

src-ui/src/app/components/dashboard/widgets/saved-view-widget/saved-view-widget.component.ts

@@ -52,6 +52,7 @@ import {
 } from 'src/app/services/permissions.service'
 import { CustomFieldsService } from 'src/app/services/rest/custom-fields.service'
 import { DocumentService } from 'src/app/services/rest/document.service'
+import { SavedViewService } from 'src/app/services/rest/saved-view.service'
 import { SettingsService } from 'src/app/services/settings.service'
 import { WebsocketStatusService } from 'src/app/services/websocket-status.service'
 import { WidgetFrameComponent } from '../widget-frame/widget-frame.component'
@@ -94,6 +95,7 @@ export class SavedViewWidgetComponent
   permissionsService = inject(PermissionsService)
   private settingsService = inject(SettingsService)
   private customFieldService = inject(CustomFieldsService)
+  private savedViewService = inject(SavedViewService)
 
   public DisplayMode = DisplayMode
   public DisplayField = DisplayField
@@ -181,6 +183,7 @@ export class SavedViewWidgetComponent
           this.show = true
           this.documents = result.results
           this.count = result.count
+          this.savedViewService.setDocumentCount(this.savedView, result.count)
         }),
         delay(500)
       )

src-ui/src/app/components/document-detail/document-detail.component.html

@@ -1,9 +1,4 @@
 <pngx-page-header [(title)]="title">
-  @if (document?.in_process) {
-    <span class="badge bg-danger text-dark ms-2 d-flex align-items-center">
-      <div class="spinner-border spinner-border-sm me-1" role="status"></div><span i18n>Processing...</span>
-    </span>
-  }
   @if (archiveContentRenderType === ContentRenderType.PDF && !useNativePdfViewer) {
     @if (previewNumPages) {
       <div class="input-group input-group-sm d-none d-md-flex">
@@ -55,7 +50,7 @@
       <div class="d-none d-sm-inline">&nbsp;<ng-container i18n>Actions</ng-container></div>
     </button>
     <div ngbDropdownMenu aria-labelledby="actionsDropdown" class="shadow">
-      <button ngbDropdownItem (click)="reprocess()" [disabled]="!userCanEdit || !userIsOwner || document?.in_process">
+      <button ngbDropdownItem (click)="reprocess()" [disabled]="!userCanEdit || !userIsOwner">
         <i-bs width="1em" height="1em" name="arrow-counterclockwise"></i-bs>&nbsp;<span i18n>Reprocess</span>
       </button>
 
@@ -63,7 +58,7 @@
         <i-bs width="1em" height="1em" name="diagram-3"></i-bs>&nbsp;<span i18n>More like this</span>
       </button>
 
-      <button ngbDropdownItem (click)="editPdf()" [disabled]="!userIsOwner || !userCanEdit || originalContentRenderType !== ContentRenderType.PDF || document?.in_process">
+      <button ngbDropdownItem (click)="editPdf()" [disabled]="!userIsOwner || !userCanEdit || originalContentRenderType !== ContentRenderType.PDF">
         <i-bs name="pencil"></i-bs>&nbsp;<ng-container i18n>PDF Editor</ng-container>
       </button>
     </div>
@@ -95,6 +90,7 @@
       }
     </div>
   </div>
+
 </pngx-page-header>
 
 <div class="row">

src-ui/src/app/components/document-detail/document-detail.component.ts

@@ -21,8 +21,9 @@ import { dirtyCheck, DirtyComponent } from '@ngneat/dirty-check-forms'
 import { PDFDocumentProxy, PdfViewerModule } from 'ng2-pdf-viewer'
 import { NgxBootstrapIconsModule } from 'ngx-bootstrap-icons'
 import { DeviceDetectorService } from 'ngx-device-detector'
-import { BehaviorSubject, Observable, Subject } from 'rxjs'
+import { BehaviorSubject, Observable, of, Subject } from 'rxjs'
 import {
+  catchError,
   debounceTime,
   distinctUntilChanged,
   filter,
@@ -327,19 +328,163 @@ export class DocumentDetailComponent
     }
   }
 
+  private mapDocToForm(doc: Document): any {
+    return {
+      ...doc,
+      permissions_form: { owner: doc.owner, set_permissions: doc.permissions },
+    }
+  }
+
+  private mapFormToDoc(value: any): any {
+    const docValues = { ...value }
+    docValues['owner'] = value['permissions_form']?.owner
+    docValues['set_permissions'] = value['permissions_form']?.set_permissions
+    delete docValues['permissions_form']
+    return docValues
+  }
+
+  private prepareForm(doc: Document): void {
+    this.documentForm.reset(this.mapDocToForm(doc), { emitEvent: false })
+    if (!this.userCanEditDoc(doc)) {
+      this.documentForm.disable({ emitEvent: false })
+    } else {
+      this.documentForm.enable({ emitEvent: false })
+    }
+    if (doc.__changedFields) {
+      doc.__changedFields.forEach((field) => {
+        if (field === 'owner' || field === 'set_permissions') {
+          this.documentForm.get('permissions_form')?.markAsDirty()
+        } else {
+          this.documentForm.get(field)?.markAsDirty()
+        }
+      })
+    }
+  }
+
+  private setupDirtyTracking(
+    currentDocument: Document,
+    originalDocument: Document
+  ): void {
+    this.store = new BehaviorSubject({
+      title: originalDocument.title,
+      content: originalDocument.content,
+      created: originalDocument.created,
+      correspondent: originalDocument.correspondent,
+      document_type: originalDocument.document_type,
+      storage_path: originalDocument.storage_path,
+      archive_serial_number: originalDocument.archive_serial_number,
+      tags: [...originalDocument.tags],
+      permissions_form: {
+        owner: originalDocument.owner,
+        set_permissions: originalDocument.permissions,
+      },
+      custom_fields: [...originalDocument.custom_fields],
+    })
+    this.isDirty$ = dirtyCheck(this.documentForm, this.store.asObservable())
+    this.isDirty$
+      .pipe(
+        takeUntil(this.unsubscribeNotifier),
+        takeUntil(this.docChangeNotifier)
+      )
+      .subscribe((dirty) =>
+        this.openDocumentService.setDirty(
+          currentDocument,
+          dirty,
+          this.getChangedFields()
+        )
+      )
+  }
+
+  private loadDocument(documentId: number): void {
+    this.previewUrl = this.documentsService.getPreviewUrl(documentId)
+    this.http
+      .get(this.previewUrl, { responseType: 'text' })
+      .pipe(
+        first(),
+        takeUntil(this.unsubscribeNotifier),
+        takeUntil(this.docChangeNotifier)
+      )
+      .subscribe({
+        next: (res) => (this.previewText = res.toString()),
+        error: (err) =>
+          (this.previewText = $localize`An error occurred loading content: ${
+            err.message ?? err.toString()
+          }`),
+      })
+    this.thumbUrl = this.documentsService.getThumbUrl(documentId)
+    this.documentsService
+      .get(documentId)
+      .pipe(
+        catchError(() => {
+          // 404 is handled in the subscribe below
+          return of(null)
+        }),
+        first(),
+        takeUntil(this.unsubscribeNotifier),
+        takeUntil(this.docChangeNotifier)
+      )
+      .subscribe({
+        next: (doc) => {
+          if (!doc) {
+            this.router.navigate(['404'], { replaceUrl: true })
+            return
+          }
+          this.documentId = doc.id
+          this.suggestions = null
+          const openDocument = this.openDocumentService.getOpenDocument(
+            this.documentId
+          )
+          const useDoc = openDocument || doc
+          if (openDocument) {
+            if (
+              new Date(doc.modified) > new Date(openDocument.modified) &&
+              !this.modalService.hasOpenModals()
+            ) {
+              const modal = this.modalService.open(ConfirmDialogComponent)
+              modal.componentInstance.title = $localize`Document changes detected`
+              modal.componentInstance.messageBold = $localize`The version of this document in your browser session appears older than the existing version.`
+              modal.componentInstance.message = $localize`Saving the document here may overwrite other changes that were made. To restore the existing version, discard your changes or close the document.`
+              modal.componentInstance.cancelBtnClass = 'visually-hidden'
+              modal.componentInstance.btnCaption = $localize`Ok`
+              modal.componentInstance.confirmClicked.subscribe(() =>
+                modal.close()
+              )
+            }
+          } else {
+            this.openDocumentService
+              .openDocument(doc)
+              .pipe(
+                first(),
+                takeUntil(this.unsubscribeNotifier),
+                takeUntil(this.docChangeNotifier)
+              )
+              .subscribe()
+          }
+          this.updateComponent(useDoc)
+          this.titleSubject
+            .pipe(
+              debounceTime(1000),
+              distinctUntilChanged(),
+              takeUntil(this.docChangeNotifier),
+              takeUntil(this.unsubscribeNotifier)
+            )
+            .subscribe((titleValue) => {
+              if (titleValue !== this.titleInput.value) return
+              this.title = titleValue
+              this.documentForm.patchValue({ title: titleValue })
+            })
+          this.setupDirtyTracking(useDoc, doc)
+        },
+      })
+  }
+
   ngOnInit(): void {
     this.setZoom(this.settings.get(SETTINGS_KEYS.PDF_VIEWER_ZOOM_SETTING))
     this.documentForm.valueChanges
       .pipe(takeUntil(this.unsubscribeNotifier))
-      .subscribe(() => {
+      .subscribe((values) => {
         this.error = null
-        const docValues = Object.assign({}, this.documentForm.value)
+        Object.assign(this.document, this.mapFormToDoc(values))
-        docValues['owner'] =
-          this.documentForm.get('permissions_form').value['owner']
-        docValues['set_permissions'] =
-          this.documentForm.get('permissions_form').value['set_permissions']
-        delete docValues['permissions_form']
-        Object.assign(this.document, docValues)
       })
 
     if (
@@ -391,171 +536,36 @@ export class DocumentDetailComponent
 
     this.route.paramMap
       .pipe(
-        filter((paramMap) => {
+        filter(
-          // only init when changing docs & section is set
+          (paramMap) =>
-          return (
             +paramMap.get('id') !== this.documentId &&
             paramMap.get('section')?.length > 0
-          )
+        ),
-        }),
+        takeUntil(this.unsubscribeNotifier)
-        takeUntil(this.unsubscribeNotifier),
-        switchMap((paramMap) => {
-          const documentId = +paramMap.get('id')
-          this.docChangeNotifier.next(documentId)
-          // Dont wait to get the preview
-          this.previewUrl = this.documentsService.getPreviewUrl(documentId)
-          this.http.get(this.previewUrl, { responseType: 'text' }).subscribe({
-            next: (res) => {
-              this.previewText = res.toString()
-            },
-            error: (err) => {
-              this.previewText = $localize`An error occurred loading content: ${
-                err.message ?? err.toString()
-              }`
-            },
-          })
-          this.thumbUrl = this.documentsService.getThumbUrl(documentId)
-          return this.documentsService.get(documentId)
-        })
       )
-      .pipe(
+      .subscribe((paramMap) => {
-        switchMap((doc) => {
+        const documentId = +paramMap.get('id')
-          this.documentId = doc.id
+        this.docChangeNotifier.next(documentId)
-          this.suggestions = null
+        this.loadDocument(documentId)
-          const openDocument = this.openDocumentService.getOpenDocument(
-            this.documentId
-          )
-
-          if (openDocument) {
-            if (
-              new Date(doc.modified) > new Date(openDocument.modified) &&
-              !this.modalService.hasOpenModals()
-            ) {
-              let modal = this.modalService.open(ConfirmDialogComponent)
-              modal.componentInstance.title = $localize`Document changes detected`
-              modal.componentInstance.messageBold = $localize`The version of this document in your browser session appears older than the existing version.`
-              modal.componentInstance.message = $localize`Saving the document here may overwrite other changes that were made. To restore the existing version, discard your changes or close the document.`
-              modal.componentInstance.cancelBtnClass = 'visually-hidden'
-              modal.componentInstance.btnCaption = $localize`Ok`
-              modal.componentInstance.confirmClicked.subscribe(() =>
-                modal.close()
-              )
-            }
-
-            // Prevent mutating stale form values into the next document: only sync if it still matches the active document.
-            if (
-              this.documentForm.dirty &&
-              (this.document?.id === openDocument.id || !this.document)
-            ) {
-              Object.assign(openDocument, this.documentForm.value)
-              openDocument['owner'] =
-                this.documentForm.get('permissions_form').value['owner']
-              openDocument['permissions'] =
-                this.documentForm.get('permissions_form').value[
-                  'set_permissions'
-                ]
-              delete openDocument['permissions_form']
-            }
-            if (openDocument.__changedFields) {
-              openDocument.__changedFields.forEach((field) => {
-                if (field === 'owner' || field === 'set_permissions') {
-                  this.documentForm.get('permissions_form').markAsDirty()
-                } else {
-                  this.documentForm.get(field)?.markAsDirty()
-                }
-              })
-            }
-            this.updateComponent(openDocument)
-          } else {
-            this.openDocumentService.openDocument(doc)
-            this.updateComponent(doc)
-          }
-
-          this.titleSubject
-            .pipe(
-              debounceTime(1000),
-              distinctUntilChanged(),
-              takeUntil(this.docChangeNotifier),
-              takeUntil(this.unsubscribeNotifier)
-            )
-            .subscribe({
-              next: (titleValue) => {
-                // In the rare case when the field changed just after debounced event was fired.
-                // We dont want to overwrite what's actually in the text field, so just return
-                if (titleValue !== this.titleInput.value) return
-
-                this.title = titleValue
-                this.documentForm.patchValue({ title: titleValue })
-              },
-              complete: () => {
-                // doc changed so we manually check dirty in case title was changed
-                if (
-                  this.store.getValue().title !==
-                  this.documentForm.get('title').value
-                ) {
-                  this.openDocumentService.setDirty(
-                    doc,
-                    true,
-                    this.getChangedFields()
-                  )
-                }
-              },
-            })
-
-          // Initialize dirtyCheck
-          this.store = new BehaviorSubject({
-            title: doc.title,
-            content: doc.content,
-            created: doc.created,
-            correspondent: doc.correspondent,
-            document_type: doc.document_type,
-            storage_path: doc.storage_path,
-            archive_serial_number: doc.archive_serial_number,
-            tags: [...doc.tags],
-            permissions_form: {
-              owner: doc.owner,
-              set_permissions: doc.permissions,
-            },
-            custom_fields: [...doc.custom_fields],
-          })
-
-          this.isDirty$ = dirtyCheck(
-            this.documentForm,
-            this.store.asObservable()
-          )
-
-          return this.isDirty$.pipe(
-            takeUntil(this.unsubscribeNotifier),
-            map((dirty) => ({ doc, dirty }))
-          )
-        })
-      )
-      .subscribe({
-        next: ({ doc, dirty }) => {
-          this.openDocumentService.setDirty(doc, dirty, this.getChangedFields())
-        },
-        error: (error) => {
-          this.router.navigate(['404'], {
-            replaceUrl: true,
-          })
-        },
       })
 
-    this.route.paramMap.subscribe((paramMap) => {
+    this.route.paramMap
-      const section = paramMap.get('section')
+      .pipe(takeUntil(this.unsubscribeNotifier))
-      if (section) {
+      .subscribe((paramMap) => {
-        const navIDKey: string = Object.keys(DocumentDetailNavIDs).find(
+        const section = paramMap.get('section')
-          (navID) => navID.toLowerCase() == section
+        if (section) {
-        )
+          const navIDKey: string = Object.keys(DocumentDetailNavIDs).find(
-        if (navIDKey) {
+            (navID) => navID.toLowerCase() == section
-          this.activeNavID = DocumentDetailNavIDs[navIDKey]
+          )
+          if (navIDKey) {
+            this.activeNavID = DocumentDetailNavIDs[navIDKey]
+          }
+        } else if (paramMap.get('id')) {
+          this.router.navigate(['documents', +paramMap.get('id'), 'details'], {
+            replaceUrl: true,
+          })
         }
-      } else if (paramMap.get('id')) {
+      })
-        this.router.navigate(['documents', +paramMap.get('id'), 'details'], {
-          replaceUrl: true,
-        })
-      }
-    })
 
     this.hotKeyService
       .addShortcut({
@@ -682,19 +692,7 @@ export class DocumentDetailComponent
         })
     }
     this.title = this.documentTitlePipe.transform(doc.title)
-    const docFormValues = Object.assign({}, doc)
+    this.prepareForm(doc)
-    docFormValues['permissions_form'] = {
-      owner: doc.owner,
-      set_permissions: doc.permissions,
-    }
-
-    this.documentForm.patchValue(docFormValues, { emitEvent: false })
-    if (!this.userCanEdit) this.documentForm.disable()
-    setTimeout(() => {
-      // check again after a tick in case form was dirty
-      if (!this.userCanEdit) this.documentForm.disable()
-      else this.documentForm.enable()
-    }, 10)
   }
 
   get customFieldFormFields(): FormArray {
@@ -797,7 +795,11 @@ export class DocumentDetailComponent
   discard() {
     this.documentsService
       .get(this.documentId)
-      .pipe(first())
+      .pipe(
+        first(),
+        takeUntil(this.unsubscribeNotifier),
+        takeUntil(this.docChangeNotifier)
+      )
       .subscribe({
         next: (doc) => {
           Object.assign(this.document, doc)
@@ -900,9 +902,10 @@ export class DocumentDetailComponent
       .patch(this.getChangedFields())
       .pipe(
         switchMap((updateResult) => {
-          return this.documentListViewService
+          return this.documentListViewService.getNext(this.documentId).pipe(
-            .getNext(this.documentId)
+            map((nextDocId) => ({ nextDocId, updateResult })),
-            .pipe(map((nextDocId) => ({ nextDocId, updateResult })))
+            takeUntil(this.unsubscribeNotifier)
+          )
         })
       )
       .pipe(
@@ -912,7 +915,10 @@ export class DocumentDetailComponent
             return this.openDocumentService
               .closeDocument(this.document)
               .pipe(
-                map((closeResult) => ({ updateResult, nextDocId, closeResult }))
+                map(
+                  (closeResult) => ({ updateResult, nextDocId, closeResult }),
+                  takeUntil(this.unsubscribeNotifier)
+                )
               )
           }
         })
@@ -1238,16 +1244,19 @@ export class DocumentDetailComponent
     ) {
       doc.owner = this.store.value.permissions_form.owner
     }
+    return !this.document || this.userCanEditDoc(doc)
+  }
+
+  private userCanEditDoc(doc: Document): boolean {
     return (
-      !this.document ||
+      this.permissionsService.currentUserCan(
-      (this.permissionsService.currentUserCan(
         PermissionAction.Change,
         PermissionType.Document
       ) &&
-        this.permissionsService.currentUserHasObjectPermissions(
+      this.permissionsService.currentUserHasObjectPermissions(
-          PermissionAction.Change,
+        PermissionAction.Change,
-          doc
+        doc
-        ))
+      )
     )
   }
 
@@ -1429,43 +1438,50 @@ export class DocumentDetailComponent
   }
 
   private tryRenderTiff() {
-    this.http.get(this.previewUrl, { responseType: 'arraybuffer' }).subscribe({
+    this.http
-      next: (res) => {
+      .get(this.previewUrl, { responseType: 'arraybuffer' })
-        /* istanbul ignore next */
+      .pipe(
-        try {
+        first(),
-          // See UTIF.js > _imgLoaded
+        takeUntil(this.unsubscribeNotifier),
-          const tiffIfds: any[] = UTIF.decode(res)
+        takeUntil(this.docChangeNotifier)
-          var vsns = tiffIfds,
+      )
-            ma = 0,
+      .subscribe({
-            page = vsns[0]
+        next: (res) => {
-          if (tiffIfds[0].subIFD) vsns = vsns.concat(tiffIfds[0].subIFD)
+          /* istanbul ignore next */
-          for (var i = 0; i < vsns.length; i++) {
+          try {
-            var img = vsns[i]
+            // See UTIF.js > _imgLoaded
-            if (img['t258'] == null || img['t258'].length < 3) continue
+            const tiffIfds: any[] = UTIF.decode(res)
-            var ar = img['t256'] * img['t257']
+            var vsns = tiffIfds,
-            if (ar > ma) {
+              ma = 0,
-              ma = ar
+              page = vsns[0]
-              page = img
+            if (tiffIfds[0].subIFD) vsns = vsns.concat(tiffIfds[0].subIFD)
+            for (var i = 0; i < vsns.length; i++) {
+              var img = vsns[i]
+              if (img['t258'] == null || img['t258'].length < 3) continue
+              var ar = img['t256'] * img['t257']
+              if (ar > ma) {
+                ma = ar
+                page = img
+              }
             }
+            UTIF.decodeImage(res, page, tiffIfds)
+            const rgba = UTIF.toRGBA8(page)
+            const { width: w, height: h } = page
+            var cnv = document.createElement('canvas')
+            cnv.width = w
+            cnv.height = h
+            var ctx = cnv.getContext('2d'),
+              imgd = ctx.createImageData(w, h)
+            for (var i = 0; i < rgba.length; i++) imgd.data[i] = rgba[i]
+            ctx.putImageData(imgd, 0, 0)
+            this.tiffURL = cnv.toDataURL()
+          } catch (err) {
+            this.tiffError = $localize`An error occurred loading tiff: ${err.toString()}`
           }
-          UTIF.decodeImage(res, page, tiffIfds)
+        },
-          const rgba = UTIF.toRGBA8(page)
+        error: (err) => {
-          const { width: w, height: h } = page
-          var cnv = document.createElement('canvas')
-          cnv.width = w
-          cnv.height = h
-          var ctx = cnv.getContext('2d'),
-            imgd = ctx.createImageData(w, h)
-          for (var i = 0; i < rgba.length; i++) imgd.data[i] = rgba[i]
-          ctx.putImageData(imgd, 0, 0)
-          this.tiffURL = cnv.toDataURL()
-        } catch (err) {
           this.tiffError = $localize`An error occurred loading tiff: ${err.toString()}`
-        }
+        },
-      },
+      })
-      error: (err) => {
-        this.tiffError = $localize`An error occurred loading tiff: ${err.toString()}`
-      },
-    })
   }
 }

src-ui/src/app/components/document-list/document-card-large/document-card-large.component.html

@@ -15,13 +15,8 @@
       }
 
     </div>
-  <div class="col col-md-10">
+    <div class="col col-md-10">
       <div class="card-body">
-        @if (document?.in_process) {
-          <span class="badge bg-secondary text-light mb-2">
-            <div class="spinner-border spinner-border-sm me-1" role="status"></div><span i18n>Processing...</span>
-          </span>
-        }
         <div class="d-flex justify-content-between align-items-center">
           <h5 class="card-title w-100">
             @if (document) {

src-ui/src/app/components/document-list/document-card-small/document-card-small.component.html

@@ -37,11 +37,6 @@
     }
 
     <div class="card-body bg-light p-2">
-      @if (document?.in_process) {
-        <span class="badge bg-secondary text-light mb-2">
-          <div class="spinner-border spinner-border-sm me-1" role="status"></div><span i18n>Processing...</span>
-        </span>
-      }
       <p class="card-text">
         @if (document) {
           @if (displayFields.includes(DisplayField.CORRESPONDENT) && document.correspondent) {

src-ui/src/app/components/document-list/document-list.component.html

@@ -301,11 +301,6 @@
                 }
                 @if (activeDisplayFields.includes(DisplayField.TITLE) || activeDisplayFields.includes(DisplayField.TAGS)) {
                   <td width="30%">
-                    @if (d.in_process) {
-                      <span class="badge bg-secondary text-light me-1">
-                        <div class="spinner-border spinner-border-sm me-1" role="status"></div><span i18n>Processing...</span>
-                      </span>
-                    }
                     @if (activeDisplayFields.includes(DisplayField.TITLE)) {
                       <div class="d-inline-block" (mouseleave)="popupPreview.close()">
                         <a routerLink="/documents/{{d.id}}" title="Edit document" i18n-title style="overflow-wrap: anywhere;">{{d.title | documentTitle}}</a>

src-ui/src/app/components/document-list/document-list.component.spec.ts

@@ -199,6 +199,14 @@ describe('DocumentListComponent', () => {
     }
     const queryParams = { id: view.id.toString() }
     const getSavedViewSpy = jest.spyOn(savedViewService, 'getCached')
+    const setCountSpy = jest.spyOn(savedViewService, 'setDocumentCount')
+    jest.spyOn(documentService, 'listFiltered').mockReturnValue(
+      of({
+        results: docs,
+        count: 3,
+        all: docs.map((d) => d.id),
+      })
+    )
     getSavedViewSpy.mockReturnValue(of(view))
     const activateSavedViewSpy = jest.spyOn(
       documentListService,
@@ -215,6 +223,7 @@ describe('DocumentListComponent', () => {
       view,
       convertToParamMap(queryParams)
     )
+    expect(setCountSpy).toHaveBeenCalledWith(view, 3)
   })
 
   it('should 404 on load saved view from URL if no view', () => {
@@ -248,6 +257,34 @@ describe('DocumentListComponent', () => {
     expect(getSavedViewSpy).toHaveBeenCalledWith(view.id)
   })
 
+  it('should update saved view document count on load saved view from query params', () => {
+    jest.spyOn(savedViewService, 'getCached').mockReturnValue(
+      of({
+        id: 10,
+        sort_field: 'added',
+        sort_reverse: true,
+        filter_rules: [],
+      })
+    )
+    jest.spyOn(documentService, 'listFiltered').mockReturnValue(
+      of({
+        results: docs,
+        count: 3,
+        all: docs.map((d) => d.id),
+      })
+    )
+    const setCountSpy = jest.spyOn(savedViewService, 'setDocumentCount')
+    jest.spyOn(documentService, 'listFiltered').mockReturnValue(
+      of({
+        results: docs,
+        count: 3,
+        all: docs.map((d) => d.id),
+      })
+    )
+    component.loadViewConfig(10)
+    expect(setCountSpy).toHaveBeenCalledWith(expect.any(Object), 3)
+  })
+
   it('should support 3 different display modes', () => {
     jest.spyOn(documentListService, 'documents', 'get').mockReturnValue(docs)
     fixture.detectChanges()

src-ui/src/app/components/document-list/document-list.component.ts

@@ -264,7 +264,9 @@ export class DocumentListComponent
           view,
           convertToParamMap(this.route.snapshot.queryParams)
         )
-        this.list.reload()
+        this.list.reload(() => {
+          this.savedViewService.setDocumentCount(view, this.list.collectionSize)
+        })
         this.updateDisplayCustomFields()
         this.unmodifiedFilterRules = view.filter_rules
       })
@@ -399,7 +401,9 @@ export class DocumentListComponent
       .subscribe((view) => {
         this.unmodifiedSavedView = view
         this.list.activateSavedView(view)
-        this.list.reload()
+        this.list.reload(() => {
+          this.savedViewService.setDocumentCount(view, this.list.collectionSize)
+        })
       })
   }
 

src-ui/src/app/data/document.ts

@@ -159,8 +159,6 @@ export interface Document extends ObjectWithPermissions {
 
   page_count?: number
 
-  in_process?: boolean
-
   // Frontend only
   __changedFields?: string[]
 }

src-ui/src/app/services/rest/saved-view.service.ts

@@ -140,11 +140,15 @@ export class SavedViewService extends AbstractPaperlessService<SavedView> {
         )
         .pipe(takeUntil(this.unsubscribeNotifier))
         .subscribe((results: Results<Document>) => {
-          this.savedViewDocumentCounts.set(view.id, results.count)
+          this.setDocumentCount(view, results.count)
         })
     })
   }
 
+  public setDocumentCount(view: SavedView, count: number) {
+    this.savedViewDocumentCounts.set(view.id, count)
+  }
+
   public getDocumentCount(view: SavedView): number {
     return this.savedViewDocumentCounts.get(view.id)
   }

src/documents/bulk_edit.py

@@ -283,7 +283,6 @@ def rotate(doc_ids: list[int], degrees: int) -> Literal["OK"]:
         f"Attempting to rotate {len(doc_ids)} documents by {degrees} degrees.",
     )
     qs = Document.objects.filter(id__in=doc_ids)
-    Document.objects.filter(pk__in=doc_ids).update(in_process=True)
     affected_docs: list[int] = []
     import pikepdf
 
@@ -310,9 +309,7 @@ def rotate(doc_ids: list[int], degrees: int) -> Literal["OK"]:
                     f"Rotated document {doc.id} by {degrees} degrees",
                 )
                 affected_docs.append(doc.id)
-                Document.objects.filter(pk__in=doc_ids).update(in_process=False)
         except Exception as e:
-            Document.objects.filter(pk__in=doc_ids).update(in_process=False)
             logger.exception(f"Error rotating document {doc.id}: {e}")
 
     if len(affected_docs) > 0:
@@ -477,7 +474,6 @@ def delete_pages(doc_ids: list[int], pages: list[int]) -> Literal["OK"]:
         f"Attempting to delete pages {pages} from {len(doc_ids)} documents",
     )
     doc = Document.objects.get(id=doc_ids[0])
-    Document.objects.filter(pk=doc.id).update(in_process=True)
     pages = sorted(pages)  # sort pages to avoid index issues
     import pikepdf
 
@@ -496,7 +492,6 @@ def delete_pages(doc_ids: list[int], pages: list[int]) -> Literal["OK"]:
             update_document_content_maybe_archive_file.delay(document_id=doc.id)
             logger.info(f"Deleted pages {pages} from document {doc.id}")
     except Exception as e:
-        Document.objects.filter(pk=doc.id).update(in_process=False)
         logger.exception(f"Error deleting pages from document {doc.id}: {e}")
 
     return "OK"
@@ -523,7 +518,6 @@ def edit_pdf(
         f"Editing PDF of document {doc_ids[0]} with {len(operations)} operations",
     )
     doc = Document.objects.get(id=doc_ids[0])
-    Document.objects.filter(pk=doc.id).update(in_process=True)
     import pikepdf
 
     pdf_docs: list[pikepdf.Pdf] = []
@@ -593,7 +587,6 @@ def edit_pdf(
 
     except Exception as e:
         logger.exception(f"Error editing document {doc.id}: {e}")
-        Document.objects.filter(pk=doc.id).update(in_process=False)
         raise ValueError(
             f"An error occurred while editing the document: {e}",
         ) from e

src/documents/migrations/1069_document_in_process.py

@@ -1,23 +0,0 @@
-# Generated by Django 5.2.5 on 2025-08-26 07:54
-
-from django.db import migrations
-from django.db import models
-
-
-class Migration(migrations.Migration):
-    dependencies = [
-        ("documents", "1068_alter_document_created"),
-    ]
-
-    operations = [
-        migrations.AddField(
-            model_name="document",
-            name="in_process",
-            field=models.BooleanField(
-                db_index=True,
-                default=False,
-                help_text="Whether the document is currently being processed.",
-                verbose_name="in process",
-            ),
-        ),
-    ]

src/documents/models.py

@@ -289,13 +289,6 @@ class Document(SoftDeleteModel, ModelWithOwner):
         ),
     )
 
-    in_process = models.BooleanField(
-        _("in process"),
-        default=False,
-        db_index=True,
-        help_text=_("Whether the document is currently being processed."),
-    )
-
     class Meta:
         ordering = ("-created",)
         verbose_name = _("document")

src/documents/serialisers.py

@@ -935,8 +935,6 @@ class DocumentSerializer(
         required=False,
     )
 
-    in_process = serializers.BooleanField(read_only=True)
-
     def get_page_count(self, obj) -> int | None:
         return obj.page_count
 
@@ -1105,7 +1103,6 @@ class DocumentSerializer(
             "remove_inbox_tags",
             "page_count",
             "mime_type",
-            "in_process",
         )
         list_serializer_class = OwnedObjectListSerializer
 

src/documents/tasks.py

@@ -250,7 +250,6 @@ def update_document_content_maybe_archive_file(document_id):
     it exists.
     """
     document = Document.objects.get(id=document_id)
-    Document.objects.filter(pk=document_id).update(in_process=True)
 
     mime_type = document.mime_type
 
@@ -350,7 +349,6 @@ def update_document_content_maybe_archive_file(document_id):
         )
     finally:
         parser.cleanup()
-        Document.objects.filter(pk=document_id).update(in_process=False)
 
 
 @shared_task

src/paperless/settings.py

@@ -324,6 +324,7 @@ INSTALLED_APPS = [
     "paperless_tesseract.apps.PaperlessTesseractConfig",
     "paperless_text.apps.PaperlessTextConfig",
     "paperless_mail.apps.PaperlessMailConfig",
+    "paperless_remote.apps.PaperlessRemoteParserConfig",
     "django.contrib.admin",
     "rest_framework",
     "rest_framework.authtoken",
@@ -1443,3 +1444,10 @@ WEBHOOKS_ALLOW_INTERNAL_REQUESTS = __get_boolean(
     "PAPERLESS_WEBHOOKS_ALLOW_INTERNAL_REQUESTS",
     "true",
 )
+
+###############################################################################
+# Remote Parser                                                               #
+###############################################################################
+REMOTE_OCR_ENGINE = os.getenv("PAPERLESS_REMOTE_OCR_ENGINE")
+REMOTE_OCR_API_KEY = os.getenv("PAPERLESS_REMOTE_OCR_API_KEY")
+REMOTE_OCR_ENDPOINT = os.getenv("PAPERLESS_REMOTE_OCR_ENDPOINT")

src/paperless_remote/__init__.py

@@ -0,0 +1,4 @@
+# this is here so that django finds the checks.
+from paperless_remote.checks import check_remote_parser_configured
+
+__all__ = ["check_remote_parser_configured"]

src/paperless_remote/apps.py

@@ -0,0 +1,14 @@
+from django.apps import AppConfig
+
+from paperless_remote.signals import remote_consumer_declaration
+
+
+class PaperlessRemoteParserConfig(AppConfig):
+    name = "paperless_remote"
+
+    def ready(self):
+        from documents.signals import document_consumer_declaration
+
+        document_consumer_declaration.connect(remote_consumer_declaration)
+
+        AppConfig.ready(self)

src/paperless_remote/checks.py

@@ -0,0 +1,15 @@
+from django.conf import settings
+from django.core.checks import Error
+from django.core.checks import register
+
+
+@register()
+def check_remote_parser_configured(app_configs, **kwargs):
+    if settings.REMOTE_OCR_ENGINE == "azureai" and not settings.REMOTE_OCR_ENDPOINT:
+        return [
+            Error(
+                "Azure AI remote parser requires endpoint to be configured.",
+            ),
+        ]
+
+    return []

src/paperless_remote/parsers.py

@@ -0,0 +1,113 @@
+from pathlib import Path
+
+from django.conf import settings
+
+from paperless_tesseract.parsers import RasterisedDocumentParser
+
+
+class RemoteEngineConfig:
+    def __init__(
+        self,
+        engine: str,
+        api_key: str | None = None,
+        endpoint: str | None = None,
+    ):
+        self.engine = engine
+        self.api_key = api_key
+        self.endpoint = endpoint
+
+    def engine_is_valid(self):
+        valid = self.engine in ["azureai"] and self.api_key is not None
+        if self.engine == "azureai":
+            valid = valid and self.endpoint is not None
+        return valid
+
+
+class RemoteDocumentParser(RasterisedDocumentParser):
+    """
+    This parser uses a remote OCR engine to parse documents. Currently, it supports Azure AI Vision
+    as this is the only service that provides a remote OCR API with text-embedded PDF output.
+    """
+
+    logging_name = "paperless.parsing.remote"
+
+    def get_settings(self) -> RemoteEngineConfig:
+        """
+        Returns the configuration for the remote OCR engine, loaded from Django settings.
+        """
+        return RemoteEngineConfig(
+            engine=settings.REMOTE_OCR_ENGINE,
+            api_key=settings.REMOTE_OCR_API_KEY,
+            endpoint=settings.REMOTE_OCR_ENDPOINT,
+        )
+
+    def supported_mime_types(self):
+        if self.settings.engine_is_valid():
+            return {
+                "application/pdf": ".pdf",
+                "image/png": ".png",
+                "image/jpeg": ".jpg",
+                "image/tiff": ".tiff",
+                "image/bmp": ".bmp",
+                "image/gif": ".gif",
+                "image/webp": ".webp",
+            }
+        else:
+            return {}
+
+    def azure_ai_vision_parse(
+        self,
+        file: Path,
+    ) -> str | None:
+        """
+        Uses Azure AI Vision to parse the document and return the text content.
+        It requests a searchable PDF output with embedded text.
+        The PDF is saved to the archive_path attribute.
+        Returns the text content extracted from the document.
+        If the parsing fails, it returns None.
+        """
+        from azure.ai.documentintelligence import DocumentIntelligenceClient
+        from azure.ai.documentintelligence.models import AnalyzeDocumentRequest
+        from azure.ai.documentintelligence.models import AnalyzeOutputOption
+        from azure.ai.documentintelligence.models import DocumentContentFormat
+        from azure.core.credentials import AzureKeyCredential
+
+        client = DocumentIntelligenceClient(
+            endpoint=self.settings.endpoint,
+            credential=AzureKeyCredential(self.settings.api_key),
+        )
+
+        with file.open("rb") as f:
+            analyze_request = AnalyzeDocumentRequest(bytes_source=f.read())
+            poller = client.begin_analyze_document(
+                model_id="prebuilt-read",
+                body=analyze_request,
+                output_content_format=DocumentContentFormat.TEXT,
+                output=[AnalyzeOutputOption.PDF],  # request searchable PDF output
+                content_type="application/json",
+            )
+
+        poller.wait()
+        result_id = poller.details["operation_id"]
+        result = poller.result()
+
+        # Download the PDF with embedded text
+        self.archive_path = Path(self.tempdir) / "archive.pdf"
+        with self.archive_path.open("wb") as f:
+            for chunk in client.get_analyze_result_pdf(
+                model_id="prebuilt-read",
+                result_id=result_id,
+            ):
+                f.write(chunk)
+
+        return result.content
+
+    def parse(self, document_path: Path, mime_type, file_name=None):
+        if not self.settings.engine_is_valid():
+            self.log.warning(
+                "No valid remote parser engine is configured, content will be empty.",
+            )
+            self.text = ""
+            return
+        elif self.settings.engine == "azureai":
+            self.text = self.azure_ai_vision_parse(document_path)

src/paperless_remote/signals.py

@@ -0,0 +1,18 @@
+def get_parser(*args, **kwargs):
+    from paperless_remote.parsers import RemoteDocumentParser
+
+    return RemoteDocumentParser(*args, **kwargs)
+
+
+def get_supported_mime_types():
+    from paperless_remote.parsers import RemoteDocumentParser
+
+    return RemoteDocumentParser(None).supported_mime_types()
+
+
+def remote_consumer_declaration(sender, **kwargs):
+    return {
+        "parser": get_parser,
+        "weight": 5,
+        "mime_types": get_supported_mime_types(),
+    }

src/paperless_remote/tests/test_checks.py

@@ -0,0 +1,29 @@
+from django.test import TestCase
+from django.test import override_settings
+
+from paperless_remote import check_remote_parser_configured
+
+
+class TestChecks(TestCase):
+    @override_settings(REMOTE_OCR_ENGINE=None)
+    def test_no_engine(self):
+        msgs = check_remote_parser_configured(None)
+        self.assertEqual(len(msgs), 0)
+
+    @override_settings(REMOTE_OCR_ENGINE="azureai")
+    @override_settings(REMOTE_OCR_API_KEY="somekey")
+    @override_settings(REMOTE_OCR_ENDPOINT=None)
+    def test_azure_no_endpoint(self):
+        msgs = check_remote_parser_configured(None)
+        self.assertEqual(len(msgs), 1)
+        self.assertTrue(
+            msgs[0].msg.startswith(
+                "Azure AI remote parser requires endpoint to be configured.",
+            ),
+        )
+
+    @override_settings(REMOTE_OCR_ENGINE="something")
+    @override_settings(REMOTE_OCR_API_KEY="somekey")
+    def test_valid_configuration(self):
+        msgs = check_remote_parser_configured(None)
+        self.assertEqual(len(msgs), 0)

src/paperless_remote/tests/test_parser.py

@@ -0,0 +1,101 @@
+import uuid
+from pathlib import Path
+from unittest import mock
+
+from django.test import TestCase
+from django.test import override_settings
+
+from documents.tests.utils import DirectoriesMixin
+from documents.tests.utils import FileSystemAssertsMixin
+from paperless_remote.parsers import RemoteDocumentParser
+from paperless_remote.signals import get_parser
+
+
+class TestParser(DirectoriesMixin, FileSystemAssertsMixin, TestCase):
+    SAMPLE_FILES = Path(__file__).resolve().parent / "samples"
+
+    def assertContainsStrings(self, content, strings):
+        # Asserts that all strings appear in content, in the given order.
+        indices = []
+        for s in strings:
+            if s in content:
+                indices.append(content.index(s))
+            else:
+                self.fail(f"'{s}' is not in '{content}'")
+        self.assertListEqual(indices, sorted(indices))
+
+    @mock.patch("paperless_tesseract.parsers.run_subprocess")
+    @mock.patch("azure.ai.documentintelligence.DocumentIntelligenceClient")
+    def test_get_text_with_azure(self, mock_client_cls, mock_subprocess):
+        # Arrange mock Azure client
+        mock_client = mock.Mock()
+        mock_client_cls.return_value = mock_client
+
+        # Simulate poller result and its `.details`
+        mock_poller = mock.Mock()
+        mock_poller.wait.return_value = None
+        mock_poller.details = {"operation_id": "fake-op-id"}
+        mock_client.begin_analyze_document.return_value = mock_poller
+        mock_poller.result.return_value.content = "This is a test document."
+
+        # Return dummy PDF bytes
+        mock_client.get_analyze_result_pdf.return_value = [
+            b"%PDF-",
+            b"1.7 ",
+            b"FAKEPDF",
+        ]
+
+        # Simulate pdftotext by writing dummy text to sidecar file
+        def fake_run(cmd, *args, **kwargs):
+            with Path(cmd[-1]).open("w", encoding="utf-8") as f:
+                f.write("This is a test document.")
+
+        mock_subprocess.side_effect = fake_run
+
+        with override_settings(
+            REMOTE_OCR_ENGINE="azureai",
+            REMOTE_OCR_API_KEY="somekey",
+            REMOTE_OCR_ENDPOINT="https://endpoint.cognitiveservices.azure.com",
+        ):
+            parser = get_parser(uuid.uuid4())
+            parser.parse(
+                self.SAMPLE_FILES / "simple-digital.pdf",
+                "application/pdf",
+            )
+
+            self.assertContainsStrings(
+                parser.text.strip(),
+                ["This is a test document."],
+            )
+
+    @override_settings(
+        REMOTE_OCR_ENGINE="azureai",
+        REMOTE_OCR_API_KEY="key",
+        REMOTE_OCR_ENDPOINT="https://endpoint.cognitiveservices.azure.com",
+    )
+    def test_supported_mime_types_valid_config(self):
+        parser = RemoteDocumentParser(uuid.uuid4())
+        expected_types = {
+            "application/pdf": ".pdf",
+            "image/png": ".png",
+            "image/jpeg": ".jpg",
+            "image/tiff": ".tiff",
+            "image/bmp": ".bmp",
+            "image/gif": ".gif",
+            "image/webp": ".webp",
+        }
+        self.assertEqual(parser.supported_mime_types(), expected_types)
+
+    def test_supported_mime_types_invalid_config(self):
+        parser = get_parser(uuid.uuid4())
+        self.assertEqual(parser.supported_mime_types(), {})
+
+    @override_settings(
+        REMOTE_OCR_ENGINE=None,
+        REMOTE_OCR_API_KEY=None,
+        REMOTE_OCR_ENDPOINT=None,
+    )
+    def test_parse_with_invalid_config(self):
+        parser = get_parser(uuid.uuid4())
+        parser.parse(self.SAMPLE_FILES / "simple-digital.pdf", "application/pdf")
+        self.assertEqual(parser.text, "")

uv.lock

@@ -95,6 +95,34 @@ wheels = [
     { url = "https://files.pythonhosted.org/packages/af/cc/55a32a2c98022d88812b5986d2a92c4ff3ee087e83b712ebc703bba452bf/Automat-24.8.1-py3-none-any.whl", hash = "sha256:bf029a7bc3da1e2c24da2343e7598affaa9f10bf0ab63ff808566ce90551e02a", size = 42585, upload-time = "2024-08-19T17:31:56.729Z" },
 ]
 
+[[package]]
+name = "azure-ai-documentintelligence"
+version = "1.0.2"
+source = { registry = "https://pypi.org/simple" }
+dependencies = [
+    { name = "azure-core", marker = "sys_platform == 'darwin' or sys_platform == 'linux'" },
+    { name = "isodate", marker = "sys_platform == 'darwin' or sys_platform == 'linux'" },
+    { name = "typing-extensions", marker = "sys_platform == 'darwin' or sys_platform == 'linux'" },
+]
+sdist = { url = "https://files.pythonhosted.org/packages/44/7b/8115cd713e2caa5e44def85f2b7ebd02a74ae74d7113ba20bdd41fd6dd80/azure_ai_documentintelligence-1.0.2.tar.gz", hash = "sha256:4d75a2513f2839365ebabc0e0e1772f5601b3a8c9a71e75da12440da13b63484", size = 170940 }
+wheels = [
+    { url = "https://files.pythonhosted.org/packages/d9/75/c9ec040f23082f54ffb1977ff8f364c2d21c79a640a13d1c1809e7fd6b1a/azure_ai_documentintelligence-1.0.2-py3-none-any.whl", hash = "sha256:e1fb446abbdeccc9759d897898a0fe13141ed29f9ad11fc705f951925822ed59", size = 106005 },
+]
+
+[[package]]
+name = "azure-core"
+version = "1.33.0"
+source = { registry = "https://pypi.org/simple" }
+dependencies = [
+    { name = "requests", marker = "sys_platform == 'darwin' or sys_platform == 'linux'" },
+    { name = "six", marker = "sys_platform == 'darwin' or sys_platform == 'linux'" },
+    { name = "typing-extensions", marker = "sys_platform == 'darwin' or sys_platform == 'linux'" },
+]
+sdist = { url = "https://files.pythonhosted.org/packages/75/aa/7c9db8edd626f1a7d99d09ef7926f6f4fb34d5f9fa00dc394afdfe8e2a80/azure_core-1.33.0.tar.gz", hash = "sha256:f367aa07b5e3005fec2c1e184b882b0b039910733907d001c20fb08ebb8c0eb9", size = 295633 }
+wheels = [
+    { url = "https://files.pythonhosted.org/packages/07/b7/76b7e144aa53bd206bf1ce34fa75350472c3f69bf30e5c8c18bc9881035d/azure_core-1.33.0-py3-none-any.whl", hash = "sha256:9b5b6d0223a1d38c37500e6971118c1e0f13f54951e6893968b38910bc9cda8f", size = 207071 },
+]
+
 [[package]]
 name = "babel"
 version = "2.17.0"
@@ -1402,6 +1430,15 @@ wheels = [
     { url = "https://files.pythonhosted.org/packages/c7/fc/4e5a141c3f7c7bed550ac1f69e599e92b6be449dd4677ec09f325cad0955/inotifyrecursive-0.3.5-py3-none-any.whl", hash = "sha256:7e5f4a2e1dc2bef0efa3b5f6b339c41fb4599055a2b54909d020e9e932cc8d2f", size = 8009, upload-time = "2020-11-20T12:38:46.981Z" },
 ]
 
+[[package]]
+name = "isodate"
+version = "0.7.2"
+source = { registry = "https://pypi.org/simple" }
+sdist = { url = "https://files.pythonhosted.org/packages/54/4d/e940025e2ce31a8ce1202635910747e5a87cc3a6a6bb2d00973375014749/isodate-0.7.2.tar.gz", hash = "sha256:4cd1aa0f43ca76f4a6c6c0292a85f40b35ec2e43e315b59f06e6d32171a953e6", size = 29705 }
+wheels = [
+    { url = "https://files.pythonhosted.org/packages/15/aa/0aca39a37d3c7eb941ba736ede56d689e7be91cab5d9ca846bde3999eba6/isodate-0.7.2-py3-none-any.whl", hash = "sha256:28009937d8031054830160fce6d409ed342816b543597cece116d966c6d99e15", size = 22320 },
+]
+
 [[package]]
 name = "jinja2"
 version = "3.1.6"
@@ -2010,6 +2047,7 @@ name = "paperless-ngx"
 version = "2.18.2"
 source = { virtual = "." }
 dependencies = [
+    { name = "azure-ai-documentintelligence", marker = "sys_platform == 'darwin' or sys_platform == 'linux'" },
     { name = "babel", marker = "sys_platform == 'darwin' or sys_platform == 'linux'" },
     { name = "bleach", marker = "sys_platform == 'darwin' or sys_platform == 'linux'" },
     { name = "celery", extra = ["redis"], marker = "sys_platform == 'darwin' or sys_platform == 'linux'" },
@@ -2144,6 +2182,7 @@ typing = [
 
 [package.metadata]
 requires-dist = [
+    { name = "azure-ai-documentintelligence", specifier = ">=1.0.2" },
     { name = "babel", specifier = ">=2.17" },
     { name = "bleach", specifier = "~=6.2.0" },
     { name = "celery", extras = ["redis"], specifier = "~=5.5.1" },