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

[ci skip]

.github/workflows/translate-strings.yml

@@ -12,9 +12,11 @@ jobs:
     steps:
       - name: Checkout code
         uses: actions/checkout@v6
+        env:
+          GH_REF: ${{ github.ref }} # sonar rule:githubactions:S7630 - avoid injection
         with:
           token: ${{ secrets.PNGX_BOT_PAT }}
-          ref: ${{ github.head_ref }}
+          ref: ${{ env.GH_REF }}
       - name: Set up Python
         id: setup-python
         uses: actions/setup-python@v6

docs/api.md

@@ -294,13 +294,6 @@ The following methods are supported:
         -   `"delete_original": true` to delete the original documents after editing.
         -   `"update_document": true` to update the existing document with the edited PDF.
         -   `"include_metadata": true` to copy metadata from the original document to the edited document.
--   `remove_password`
-    -   Requires `parameters`:
-        -   `"password": "PASSWORD_STRING"` The password to remove from the PDF documents.
-    -   Optional `parameters`:
-        -   `"update_document": true` to replace the existing document with the password-less PDF.
-        -   `"delete_original": true` to delete the original document after editing.
-        -   `"include_metadata": true` to copy metadata from the original document to the new password-less document.
 -   `merge`
     -   No additional `parameters` required.
     -   The ordering of the merged document is determined by the list of IDs.

docs/configuration.md

@@ -1804,3 +1804,23 @@ 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

@@ -901,6 +901,21 @@ 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

@@ -16,6 +16,7 @@ classifiers = [
 # This will allow testing to not install a webserver, mysql, etc
 
 dependencies = [
+  "azure-ai-documentintelligence>=1.0.2",
   "babel>=2.17",
   "bleach~=6.3.0",
   "celery[redis]~=5.5.1",
@@ -253,6 +254,7 @@ testpaths = [
   "src/paperless_tesseract/tests/",
   "src/paperless_tika/tests",
   "src/paperless_text/tests/",
+  "src/paperless_remote/tests/",
 ]
 addopts = [
   "--pythonwarnings=all",

src-ui/src/app/components/common/confirm-dialog/password-removal-confirm-dialog/password-removal-confirm-dialog.component.html

@@ -1,75 +0,0 @@
-<div class="modal-header">
-  <h4 class="modal-title" id="modal-basic-title">{{title}}</h4>
-  <button type="button" class="btn-close" aria-label="Close" (click)="cancel()">
-  </button>
-</div>
-<div class="modal-body">
-  @if (message) {
-    <p class="mb-3" [innerHTML]="message"></p>
-  }
-  <div class="btn-group mb-3" role="group">
-    <input
-      type="radio"
-      class="btn-check"
-      name="passwordRemoveMode"
-      id="removeReplace"
-      [(ngModel)]="updateDocument"
-      [value]="true"
-      (ngModelChange)="onUpdateDocumentChange($event)"
-    />
-    <label class="btn btn-outline-primary btn-sm" for="removeReplace">
-      <i-bs name="pencil"></i-bs>
-      <span class="ms-2" i18n>Replace current document</span>
-    </label>
-    <input
-      type="radio"
-      class="btn-check"
-      name="passwordRemoveMode"
-      id="removeCreate"
-      [(ngModel)]="updateDocument"
-      [value]="false"
-      (ngModelChange)="onUpdateDocumentChange($event)"
-    />
-    <label class="btn btn-outline-primary btn-sm" for="removeCreate">
-      <i-bs name="plus"></i-bs>
-      <span class="ms-2" i18n>Create new document</span>
-    </label>
-  </div>
-  @if (!updateDocument) {
-    <div class="d-flex flex-column flex-md-row w-100 gap-3 align-items-center">
-      <div class="form-group d-flex">
-        <div class="form-check">
-          <input class="form-check-input" type="checkbox" id="copyMetaRemove" [(ngModel)]="includeMetadata" />
-          <label class="form-check-label" for="copyMetaRemove" i18n> Copy metadata
-          </label>
-        </div>
-        <div class="form-check ms-3">
-          <input class="form-check-input" type="checkbox" id="deleteOriginalRemove" [(ngModel)]="deleteOriginal" />
-          <label class="form-check-label" for="deleteOriginalRemove" i18n> Delete original</label>
-        </div>
-      </div>
-    </div>
-  }
-</div>
-<div class="modal-footer flex-nowrap gap-2">
-  <button
-    type="button"
-    class="btn"
-    [class]="cancelBtnClass"
-    (click)="cancel()"
-    [disabled]="!buttonsEnabled"
-  >
-    <span class="d-inline-block" style="padding-bottom: 1px;">
-      {{cancelBtnCaption}}
-    </span>
-  </button>
-  <button
-    type="button"
-    class="btn"
-    [class]="btnClass"
-    (click)="confirm()"
-    [disabled]="!confirmButtonEnabled || !buttonsEnabled"
-  >
-    {{btnCaption}}
-  </button>
-</div>

src-ui/src/app/components/common/confirm-dialog/password-removal-confirm-dialog/password-removal-confirm-dialog.component.spec.ts

@@ -1,53 +0,0 @@
-import { ComponentFixture, TestBed } from '@angular/core/testing'
-import { By } from '@angular/platform-browser'
-import { NgbActiveModal } from '@ng-bootstrap/ng-bootstrap'
-import { NgxBootstrapIconsModule, allIcons } from 'ngx-bootstrap-icons'
-import { PasswordRemovalConfirmDialogComponent } from './password-removal-confirm-dialog.component'
-
-describe('PasswordRemovalConfirmDialogComponent', () => {
-  let component: PasswordRemovalConfirmDialogComponent
-  let fixture: ComponentFixture<PasswordRemovalConfirmDialogComponent>
-
-  beforeEach(async () => {
-    await TestBed.configureTestingModule({
-      providers: [NgbActiveModal],
-      imports: [
-        NgxBootstrapIconsModule.pick(allIcons),
-        PasswordRemovalConfirmDialogComponent,
-      ],
-    }).compileComponents()
-
-    fixture = TestBed.createComponent(PasswordRemovalConfirmDialogComponent)
-    component = fixture.componentInstance
-    fixture.detectChanges()
-  })
-
-  it('should default to replacing the document', () => {
-    expect(component.updateDocument).toBe(true)
-    expect(
-      fixture.debugElement.query(By.css('#removeReplace')).nativeElement.checked
-    ).toBe(true)
-  })
-
-  it('should allow creating a new document with metadata and delete toggle', () => {
-    component.onUpdateDocumentChange(false)
-    fixture.detectChanges()
-
-    expect(component.updateDocument).toBe(false)
-    expect(fixture.debugElement.query(By.css('#copyMetaRemove'))).not.toBeNull()
-
-    component.includeMetadata = false
-    component.deleteOriginal = true
-    component.onUpdateDocumentChange(true)
-    expect(component.updateDocument).toBe(true)
-    expect(component.includeMetadata).toBe(true)
-    expect(component.deleteOriginal).toBe(false)
-  })
-
-  it('should emit confirm when confirmed', () => {
-    let confirmed = false
-    component.confirmClicked.subscribe(() => (confirmed = true))
-    component.confirm()
-    expect(confirmed).toBe(true)
-  })
-})

src-ui/src/app/components/common/confirm-dialog/password-removal-confirm-dialog/password-removal-confirm-dialog.component.ts

@@ -1,38 +0,0 @@
-import { Component, Input } from '@angular/core'
-import { FormsModule } from '@angular/forms'
-import { NgxBootstrapIconsModule } from 'ngx-bootstrap-icons'
-import { ConfirmDialogComponent } from '../confirm-dialog.component'
-
-@Component({
-  selector: 'pngx-password-removal-confirm-dialog',
-  templateUrl: './password-removal-confirm-dialog.component.html',
-  styleUrls: ['./password-removal-confirm-dialog.component.scss'],
-  imports: [FormsModule, NgxBootstrapIconsModule],
-})
-export class PasswordRemovalConfirmDialogComponent extends ConfirmDialogComponent {
-  updateDocument: boolean = true
-  includeMetadata: boolean = true
-  deleteOriginal: boolean = false
-
-  @Input()
-  override title = $localize`Remove password protection`
-
-  @Input()
-  override message =
-    $localize`Create an unprotected copy or replace the existing file.`
-
-  @Input()
-  override btnCaption = $localize`Start`
-
-  constructor() {
-    super()
-  }
-
-  onUpdateDocumentChange(updateDocument: boolean) {
-    this.updateDocument = updateDocument
-    if (this.updateDocument) {
-      this.deleteOriginal = false
-      this.includeMetadata = true
-    }
-  }
-}

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

@@ -65,12 +65,6 @@
       <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>
-
-      @if (userIsOwner && (requiresPassword || password)) {
-        <button ngbDropdownItem (click)="removePassword()" [disabled]="!password">
-          <i-bs name="unlock"></i-bs>&nbsp;<ng-container i18n>Remove Password</ng-container>
-        </button>
-      }
     </div>
   </div>
 

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

@@ -66,7 +66,6 @@ import { SettingsService } from 'src/app/services/settings.service'
 import { ToastService } from 'src/app/services/toast.service'
 import { environment } from 'src/environments/environment'
 import { ConfirmDialogComponent } from '../common/confirm-dialog/confirm-dialog.component'
-import { PasswordRemovalConfirmDialogComponent } from '../common/confirm-dialog/password-removal-confirm-dialog/password-removal-confirm-dialog.component'
 import { CustomFieldsDropdownComponent } from '../common/custom-fields-dropdown/custom-fields-dropdown.component'
 import {
   DocumentDetailComponent,
@@ -1210,88 +1209,6 @@ describe('DocumentDetailComponent', () => {
     expect(closeSpy).toHaveBeenCalled()
   })
 
-  it('should support removing password protection from pdfs', () => {
-    let modal: NgbModalRef
-    modalService.activeInstances.subscribe((m) => (modal = m[0]))
-    initNormally()
-    component.password = 'secret'
-    component.removePassword()
-    const dialog =
-      modal.componentInstance as PasswordRemovalConfirmDialogComponent
-    dialog.updateDocument = false
-    dialog.includeMetadata = false
-    dialog.deleteOriginal = true
-    dialog.confirm()
-    const req = httpTestingController.expectOne(
-      `${environment.apiBaseUrl}documents/bulk_edit/`
-    )
-    expect(req.request.body).toEqual({
-      documents: [doc.id],
-      method: 'remove_password',
-      parameters: {
-        password: 'secret',
-        update_document: false,
-        include_metadata: false,
-        delete_original: true,
-      },
-    })
-    req.flush(true)
-  })
-
-  it('should require the current password before removing it', () => {
-    initNormally()
-    const errorSpy = jest.spyOn(toastService, 'showError')
-    component.requiresPassword = true
-    component.password = ''
-
-    component.removePassword()
-
-    expect(errorSpy).toHaveBeenCalled()
-    httpTestingController.expectNone(
-      `${environment.apiBaseUrl}documents/bulk_edit/`
-    )
-  })
-
-  it('should handle failures when removing password protection', () => {
-    let modal: NgbModalRef
-    modalService.activeInstances.subscribe((m) => (modal = m[0]))
-    initNormally()
-    const errorSpy = jest.spyOn(toastService, 'showError')
-    component.password = 'secret'
-
-    component.removePassword()
-    const dialog =
-      modal.componentInstance as PasswordRemovalConfirmDialogComponent
-    dialog.confirm()
-    const req = httpTestingController.expectOne(
-      `${environment.apiBaseUrl}documents/bulk_edit/`
-    )
-    req.error(new ErrorEvent('failed'))
-
-    expect(errorSpy).toHaveBeenCalled()
-    expect(component.networkActive).toBe(false)
-    expect(dialog.buttonsEnabled).toBe(true)
-  })
-
-  it('should refresh the document when removing password in update mode', () => {
-    let modal: NgbModalRef
-    modalService.activeInstances.subscribe((m) => (modal = m[0]))
-    const refreshSpy = jest.spyOn(openDocumentsService, 'refreshDocument')
-    initNormally()
-    component.password = 'secret'
-
-    component.removePassword()
-    const dialog =
-      modal.componentInstance as PasswordRemovalConfirmDialogComponent
-    dialog.confirm()
-    const req = httpTestingController.expectOne(
-      `${environment.apiBaseUrl}documents/bulk_edit/`
-    )
-    req.flush(true)
-
-    expect(refreshSpy).toHaveBeenCalledWith(doc.id)
-  })
-
   it('should support keyboard shortcuts', () => {
     initNormally()
 

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

@@ -83,7 +83,6 @@ import { getFilenameFromContentDisposition } from 'src/app/utils/http'
 import { ISODateAdapter } from 'src/app/utils/ngb-iso-date-adapter'
 import * as UTIF from 'utif'
 import { ConfirmDialogComponent } from '../common/confirm-dialog/confirm-dialog.component'
-import { PasswordRemovalConfirmDialogComponent } from '../common/confirm-dialog/password-removal-confirm-dialog/password-removal-confirm-dialog.component'
 import { CustomFieldsDropdownComponent } from '../common/custom-fields-dropdown/custom-fields-dropdown.component'
 import { CorrespondentEditDialogComponent } from '../common/edit-dialog/correspondent-edit-dialog/correspondent-edit-dialog.component'
 import { DocumentTypeEditDialogComponent } from '../common/edit-dialog/document-type-edit-dialog/document-type-edit-dialog.component'
@@ -176,7 +175,6 @@ export enum ZoomSetting {
     NgxBootstrapIconsModule,
     PdfViewerModule,
     TextAreaComponent,
-    PasswordRemovalConfirmDialogComponent,
   ],
 })
 export class DocumentDetailComponent
@@ -1430,63 +1428,6 @@ export class DocumentDetailComponent
       })
   }
 
-  removePassword() {
-    if (this.requiresPassword || !this.password) {
-      this.toastService.showError(
-        $localize`Please enter the current password before attempting to remove it.`
-      )
-      return
-    }
-    const modal = this.modalService.open(
-      PasswordRemovalConfirmDialogComponent,
-      {
-        backdrop: 'static',
-      }
-    )
-    modal.componentInstance.title = $localize`Remove password protection`
-    modal.componentInstance.message = $localize`Create an unprotected copy or replace the existing file.`
-    modal.componentInstance.btnCaption = $localize`Start`
-
-    modal.componentInstance.confirmClicked
-      .pipe(takeUntil(this.unsubscribeNotifier))
-      .subscribe(() => {
-        const dialog =
-          modal.componentInstance as PasswordRemovalConfirmDialogComponent
-        dialog.buttonsEnabled = false
-        this.networkActive = true
-        this.documentsService
-          .bulkEdit([this.document.id], 'remove_password', {
-            password: this.password,
-            update_document: dialog.updateDocument,
-            include_metadata: dialog.includeMetadata,
-            delete_original: dialog.deleteOriginal,
-          })
-          .pipe(first(), takeUntil(this.unsubscribeNotifier))
-          .subscribe({
-            next: () => {
-              this.toastService.showInfo(
-                $localize`Password removal operation for "${this.document.title}" will begin in the background.`
-              )
-              this.networkActive = false
-              modal.close()
-              if (!dialog.updateDocument && dialog.deleteOriginal) {
-                this.openDocumentService.closeDocument(this.document)
-              } else if (dialog.updateDocument) {
-                this.openDocumentService.refreshDocument(this.documentId)
-              }
-            },
-            error: (error) => {
-              dialog.buttonsEnabled = true
-              this.networkActive = false
-              this.toastService.showError(
-                $localize`Error executing password removal operation`,
-                error
-              )
-            },
-          })
-      })
-  }
-
   printDocument() {
     const printUrl = this.documentsService.getDownloadUrl(
       this.document.id,

src-ui/src/main.ts

@@ -132,7 +132,6 @@ import {
   threeDotsVertical,
   trash,
   uiRadios,
-  unlock,
   upcScan,
   windowStack,
   x,
@@ -349,7 +348,6 @@ const icons = {
   threeDotsVertical,
   trash,
   uiRadios,
-  unlock,
   upcScan,
   windowStack,
   x,

src/documents/bulk_edit.py

@@ -646,77 +646,6 @@ def edit_pdf(
     return "OK"
 
 
-def remove_password(
-    doc_ids: list[int],
-    password: str,
-    *,
-    update_document: bool = False,
-    delete_original: bool = False,
-    include_metadata: bool = True,
-    user: User | None = None,
-) -> Literal["OK"]:
-    """
-    Remove password protection from PDF documents.
-    """
-    import pikepdf
-
-    for doc_id in doc_ids:
-        doc = Document.objects.get(id=doc_id)
-        try:
-            logger.info(
-                f"Attempting password removal from document {doc_ids[0]}",
-            )
-            with pikepdf.open(doc.source_path, password=password) as pdf:
-                temp_path = doc.source_path.with_suffix(".tmp.pdf")
-                pdf.remove_unreferenced_resources()
-                pdf.save(temp_path)
-
-                if update_document:
-                    # replace the original document with the unprotected one
-                    temp_path.replace(doc.source_path)
-                    doc.checksum = hashlib.md5(doc.source_path.read_bytes()).hexdigest()
-                    doc.page_count = len(pdf.pages)
-                    doc.save()
-                    update_document_content_maybe_archive_file.delay(document_id=doc.id)
-                else:
-                    consume_tasks = []
-                    overrides = (
-                        DocumentMetadataOverrides().from_document(doc)
-                        if include_metadata
-                        else DocumentMetadataOverrides()
-                    )
-                    if user is not None:
-                        overrides.owner_id = user.id
-
-                    filepath: Path = (
-                        Path(tempfile.mkdtemp(dir=settings.SCRATCH_DIR))
-                        / f"{doc.id}_unprotected.pdf"
-                    )
-                    temp_path.replace(filepath)
-                    consume_tasks.append(
-                        consume_file.s(
-                            ConsumableDocument(
-                                source=DocumentSource.ConsumeFolder,
-                                original_file=filepath,
-                            ),
-                            overrides,
-                        ),
-                    )
-
-                    if delete_original:
-                        chord(header=consume_tasks, body=delete.si([doc.id])).delay()
-                    else:
-                        group(consume_tasks).delay()
-
-        except Exception as e:
-            logger.exception(f"Error removing password from document {doc.id}: {e}")
-            raise ValueError(
-                f"An error occurred while removing the password: {e}",
-            ) from e
-
-    return "OK"
-
-
 def reflect_doclinks(
     document: Document,
     field: CustomField,

src/documents/serialisers.py

@@ -18,6 +18,8 @@ from django.core.exceptions import ValidationError
 from django.core.validators import DecimalValidator
 from django.core.validators import EmailValidator
 from django.core.validators import MaxLengthValidator
+from django.core.validators import MaxValueValidator
+from django.core.validators import MinValueValidator
 from django.core.validators import RegexValidator
 from django.core.validators import integer_validator
 from django.db.models import Count
@@ -875,6 +877,13 @@ class CustomFieldInstanceSerializer(serializers.ModelSerializer):
                 uri_validator(data["value"])
             elif field.data_type == CustomField.FieldDataType.INT:
                 integer_validator(data["value"])
+                try:
+                    value_int = int(data["value"])
+                except (TypeError, ValueError):
+                    raise serializers.ValidationError("Enter a valid integer.")
+                # Keep values within the PostgreSQL integer range
+                MinValueValidator(-2147483648)(value_int)
+                MaxValueValidator(2147483647)(value_int)
             elif (
                 field.data_type == CustomField.FieldDataType.MONETARY
                 and data["value"] != ""
@@ -1421,7 +1430,6 @@ class BulkEditSerializer(
             "split",
             "delete_pages",
             "edit_pdf",
-            "remove_password",
         ],
         label="Method",
         write_only=True,
@@ -1497,8 +1505,6 @@ class BulkEditSerializer(
             return bulk_edit.delete_pages
         elif method == "edit_pdf":
             return bulk_edit.edit_pdf
-        elif method == "remove_password":
-            return bulk_edit.remove_password
         else:  # pragma: no cover
             # This will never happen as it is handled by the ChoiceField
             raise serializers.ValidationError("Unsupported method.")
@@ -1695,12 +1701,6 @@ class BulkEditSerializer(
                         f"Page {op['page']} is out of bounds for document with {doc.page_count} pages.",
                     )
 
-    def validate_parameters_remove_password(self, parameters):
-        if "password" not in parameters:
-            raise serializers.ValidationError("password not specified")
-        if not isinstance(parameters["password"], str):
-            raise serializers.ValidationError("password must be a string")
-
     def validate(self, attrs):
         method = attrs["method"]
         parameters = attrs["parameters"]
@@ -1741,8 +1741,6 @@ class BulkEditSerializer(
                     "Edit PDF method only supports one document",
                 )
             self._validate_parameters_edit_pdf(parameters, attrs["documents"][0])
-        elif method == bulk_edit.remove_password:
-            self.validate_parameters_remove_password(parameters)
 
         return attrs
 

src/documents/tests/test_api_bulk_edit.py

@@ -1582,58 +1582,6 @@ class TestBulkEditAPI(DirectoriesMixin, APITestCase):
         self.assertEqual(response.status_code, status.HTTP_400_BAD_REQUEST)
         self.assertIn(b"out of bounds", response.content)
 
-    @mock.patch("documents.serialisers.bulk_edit.remove_password")
-    def test_remove_password(self, m):
-        self.setup_mock(m, "remove_password")
-        response = self.client.post(
-            "/api/documents/bulk_edit/",
-            json.dumps(
-                {
-                    "documents": [self.doc2.id],
-                    "method": "remove_password",
-                    "parameters": {"password": "secret", "update_document": True},
-                },
-            ),
-            content_type="application/json",
-        )
-
-        self.assertEqual(response.status_code, status.HTTP_200_OK)
-        m.assert_called_once()
-        args, kwargs = m.call_args
-        self.assertCountEqual(args[0], [self.doc2.id])
-        self.assertEqual(kwargs["password"], "secret")
-        self.assertTrue(kwargs["update_document"])
-        self.assertEqual(kwargs["user"], self.user)
-
-    def test_remove_password_invalid_params(self):
-        response = self.client.post(
-            "/api/documents/bulk_edit/",
-            json.dumps(
-                {
-                    "documents": [self.doc2.id],
-                    "method": "remove_password",
-                    "parameters": {},
-                },
-            ),
-            content_type="application/json",
-        )
-        self.assertEqual(response.status_code, status.HTTP_400_BAD_REQUEST)
-        self.assertIn(b"password not specified", response.content)
-
-        response = self.client.post(
-            "/api/documents/bulk_edit/",
-            json.dumps(
-                {
-                    "documents": [self.doc2.id],
-                    "method": "remove_password",
-                    "parameters": {"password": 123},
-                },
-            ),
-            content_type="application/json",
-        )
-        self.assertEqual(response.status_code, status.HTTP_400_BAD_REQUEST)
-        self.assertIn(b"password must be a string", response.content)
-
     @override_settings(AUDIT_LOG_ENABLED=True)
     def test_bulk_edit_audit_log_enabled_simple_field(self):
         """

src/documents/tests/test_api_documents.py

@@ -1664,6 +1664,44 @@ class TestDocumentApi(DirectoriesMixin, DocumentConsumeDelayMixin, APITestCase):
 
         self.consume_file_mock.assert_not_called()
 
+    def test_patch_document_integer_custom_field_out_of_range(self):
+        """
+        GIVEN:
+            - An integer custom field
+            - A document
+        WHEN:
+            - Patching the document with an integer value exceeding PostgreSQL's range
+        THEN:
+            - HTTP 400 is returned (validation catches the overflow)
+            - No custom field instance is created
+        """
+        cf_int = CustomField.objects.create(
+            name="intfield",
+            data_type=CustomField.FieldDataType.INT,
+        )
+        doc = Document.objects.create(
+            title="Doc",
+            checksum="123",
+            mime_type="application/pdf",
+        )
+
+        response = self.client.patch(
+            f"/api/documents/{doc.pk}/",
+            {
+                "custom_fields": [
+                    {
+                        "field": cf_int.pk,
+                        "value": 2**31,  # overflow for PostgreSQL integer fields
+                    },
+                ],
+            },
+            format="json",
+        )
+
+        self.assertEqual(response.status_code, status.HTTP_400_BAD_REQUEST)
+        self.assertIn("custom_fields", response.data)
+        self.assertEqual(CustomFieldInstance.objects.count(), 0)
+
     def test_upload_with_webui_source(self):
         """
         GIVEN: A document with a source file

src/documents/tests/test_bulk_edit.py

@@ -1,4 +1,3 @@
-import hashlib
 import shutil
 from datetime import date
 from pathlib import Path
@@ -1067,147 +1066,3 @@ class TestPDFActions(DirectoriesMixin, TestCase):
                 bulk_edit.edit_pdf(doc_ids, operations, update_document=True)
         mock_group.assert_not_called()
         mock_consume_file.assert_not_called()
-
-    @mock.patch("documents.bulk_edit.update_document_content_maybe_archive_file.delay")
-    @mock.patch("pikepdf.open")
-    def test_remove_password_update_document(self, mock_open, mock_update_document):
-        doc = self.doc1
-        original_checksum = doc.checksum
-
-        fake_pdf = mock.MagicMock()
-        fake_pdf.pages = [mock.Mock(), mock.Mock(), mock.Mock()]
-
-        def save_side_effect(target_path):
-            Path(target_path).write_bytes(b"new pdf content")
-
-        fake_pdf.save.side_effect = save_side_effect
-        mock_open.return_value.__enter__.return_value = fake_pdf
-
-        result = bulk_edit.remove_password(
-            [doc.id],
-            password="secret",
-            update_document=True,
-        )
-
-        self.assertEqual(result, "OK")
-        mock_open.assert_called_once_with(doc.source_path, password="secret")
-        fake_pdf.remove_unreferenced_resources.assert_called_once()
-        doc.refresh_from_db()
-        self.assertNotEqual(doc.checksum, original_checksum)
-        expected_checksum = hashlib.md5(doc.source_path.read_bytes()).hexdigest()
-        self.assertEqual(doc.checksum, expected_checksum)
-        self.assertEqual(doc.page_count, len(fake_pdf.pages))
-        mock_update_document.assert_called_once_with(document_id=doc.id)
-
-    @mock.patch("documents.bulk_edit.chord")
-    @mock.patch("documents.bulk_edit.group")
-    @mock.patch("documents.tasks.consume_file.s")
-    @mock.patch("documents.bulk_edit.tempfile.mkdtemp")
-    @mock.patch("pikepdf.open")
-    def test_remove_password_creates_consumable_document(
-        self,
-        mock_open,
-        mock_mkdtemp,
-        mock_consume_file,
-        mock_group,
-        mock_chord,
-    ):
-        doc = self.doc2
-        temp_dir = self.dirs.scratch_dir / "remove-password"
-        temp_dir.mkdir(parents=True, exist_ok=True)
-        mock_mkdtemp.return_value = str(temp_dir)
-
-        fake_pdf = mock.MagicMock()
-        fake_pdf.pages = [mock.Mock(), mock.Mock()]
-
-        def save_side_effect(target_path):
-            Path(target_path).write_bytes(b"password removed")
-
-        fake_pdf.save.side_effect = save_side_effect
-        mock_open.return_value.__enter__.return_value = fake_pdf
-        mock_group.return_value.delay.return_value = None
-
-        user = User.objects.create(username="owner")
-
-        result = bulk_edit.remove_password(
-            [doc.id],
-            password="secret",
-            include_metadata=False,
-            update_document=False,
-            delete_original=False,
-            user=user,
-        )
-
-        self.assertEqual(result, "OK")
-        mock_open.assert_called_once_with(doc.source_path, password="secret")
-        mock_consume_file.assert_called_once()
-        consume_args, _ = mock_consume_file.call_args
-        consumable_document = consume_args[0]
-        overrides = consume_args[1]
-        expected_path = temp_dir / f"{doc.id}_unprotected.pdf"
-        self.assertTrue(expected_path.exists())
-        self.assertEqual(
-            Path(consumable_document.original_file).resolve(),
-            expected_path.resolve(),
-        )
-        self.assertEqual(overrides.owner_id, user.id)
-        mock_group.assert_called_once_with([mock_consume_file.return_value])
-        mock_group.return_value.delay.assert_called_once()
-        mock_chord.assert_not_called()
-
-    @mock.patch("documents.bulk_edit.delete")
-    @mock.patch("documents.bulk_edit.chord")
-    @mock.patch("documents.bulk_edit.group")
-    @mock.patch("documents.tasks.consume_file.s")
-    @mock.patch("documents.bulk_edit.tempfile.mkdtemp")
-    @mock.patch("pikepdf.open")
-    def test_remove_password_deletes_original(
-        self,
-        mock_open,
-        mock_mkdtemp,
-        mock_consume_file,
-        mock_group,
-        mock_chord,
-        mock_delete,
-    ):
-        doc = self.doc2
-        temp_dir = self.dirs.scratch_dir / "remove-password-delete"
-        temp_dir.mkdir(parents=True, exist_ok=True)
-        mock_mkdtemp.return_value = str(temp_dir)
-
-        fake_pdf = mock.MagicMock()
-        fake_pdf.pages = [mock.Mock(), mock.Mock()]
-
-        def save_side_effect(target_path):
-            Path(target_path).write_bytes(b"password removed")
-
-        fake_pdf.save.side_effect = save_side_effect
-        mock_open.return_value.__enter__.return_value = fake_pdf
-        mock_chord.return_value.delay.return_value = None
-
-        result = bulk_edit.remove_password(
-            [doc.id],
-            password="secret",
-            include_metadata=False,
-            update_document=False,
-            delete_original=True,
-        )
-
-        self.assertEqual(result, "OK")
-        mock_open.assert_called_once_with(doc.source_path, password="secret")
-        mock_consume_file.assert_called_once()
-        mock_group.assert_not_called()
-        mock_chord.assert_called_once()
-        mock_chord.return_value.delay.assert_called_once()
-        mock_delete.si.assert_called_once_with([doc.id])
-
-    @mock.patch("pikepdf.open")
-    def test_remove_password_open_failure(self, mock_open):
-        mock_open.side_effect = RuntimeError("wrong password")
-
-        with self.assertLogs("paperless.bulk_edit", level="ERROR") as cm:
-            with self.assertRaises(ValueError) as exc:
-                bulk_edit.remove_password([self.doc1.id], password="secret")
-
-        self.assertIn("wrong password", str(exc.exception))
-        self.assertIn("Error removing password from document", cm.output[0])

src/documents/views.py

@@ -1504,7 +1504,6 @@ class BulkEditView(PassUserMixin):
         "merge": None,
         "edit_pdf": "checksum",
         "reprocess": "checksum",
-        "remove_password": "checksum",
     }
 
     permission_classes = (IsAuthenticated,)
@@ -1523,7 +1522,6 @@ class BulkEditView(PassUserMixin):
             bulk_edit.split,
             bulk_edit.merge,
             bulk_edit.edit_pdf,
-            bulk_edit.remove_password,
         ]:
             parameters["user"] = user
 
@@ -1552,7 +1550,6 @@ class BulkEditView(PassUserMixin):
                         bulk_edit.rotate,
                         bulk_edit.delete_pages,
                         bulk_edit.edit_pdf,
-                        bulk_edit.remove_password,
                     ]
                 )
                 or (
@@ -1569,7 +1566,7 @@ class BulkEditView(PassUserMixin):
                 and (
                     method in [bulk_edit.split, bulk_edit.merge]
                     or (
-                        method in [bulk_edit.edit_pdf, bulk_edit.remove_password]
+                        method == bulk_edit.edit_pdf
                         and not parameters["update_document"]
                     )
                 )

src/locale/en_US/LC_MESSAGES/django.po

@@ -2,7 +2,7 @@ msgid ""
 msgstr ""
 "Project-Id-Version: paperless-ngx\n"
 "Report-Msgid-Bugs-To: \n"
-"POT-Creation-Date: 2025-12-24 05:27+0000\n"
+"POT-Creation-Date: 2025-12-29 14:49+0000\n"
 "PO-Revision-Date: 2022-02-17 04:17\n"
 "Last-Translator: \n"
 "Language-Team: English\n"
@@ -1219,35 +1219,35 @@ msgstr ""
 msgid "workflow runs"
 msgstr ""
 
-#: documents/serialisers.py:640
+#: documents/serialisers.py:642
 msgid "Invalid color."
 msgstr ""
 
-#: documents/serialisers.py:1826
+#: documents/serialisers.py:1835
 #, python-format
 msgid "File type %(type)s not supported"
 msgstr ""
 
-#: documents/serialisers.py:1870
+#: documents/serialisers.py:1879
 #, python-format
 msgid "Custom field id must be an integer: %(id)s"
 msgstr ""
 
-#: documents/serialisers.py:1877
+#: documents/serialisers.py:1886
 #, python-format
 msgid "Custom field with id %(id)s does not exist"
 msgstr ""
 
-#: documents/serialisers.py:1894 documents/serialisers.py:1904
+#: documents/serialisers.py:1903 documents/serialisers.py:1913
 msgid ""
 "Custom fields must be a list of integers or an object mapping ids to values."
 msgstr ""
 
-#: documents/serialisers.py:1899
+#: documents/serialisers.py:1908
 msgid "Some custom fields don't exist or were specified twice."
 msgstr ""
 
-#: documents/serialisers.py:2014
+#: documents/serialisers.py:2023
 msgid "Invalid variable detected."
 msgstr ""
 

src/paperless/settings.py

@@ -322,6 +322,7 @@ 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",
@@ -1402,3 +1403,10 @@ 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 +1,17 @@
+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 and settings.REMOTE_OCR_API_KEY
+    ):
+        return [
+            Error(
+                "Azure AI remote parser requires endpoint and API key to be configured.",
+            ),
+        ]
+
+    return []

src/paperless_remote/parsers.py

@@ -0,0 +1,118 @@
+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),
+        )
+
+        try:
+            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 = 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
+        except Exception as e:
+            self.log.error(f"Azure AI Vision parsing failed: {e}")
+        finally:
+            client.close()
+
+        return None
+
+    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 = ""
+        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 +1,24 @@
+from unittest 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 and API key to be configured.",
+            ),
+        )

src/paperless_remote/tests/test_parser.py

@@ -0,0 +1,128 @@
+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: str, strings: list[str]):
+        # 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."],
+            )
+
+    @mock.patch("azure.ai.documentintelligence.DocumentIntelligenceClient")
+    def test_get_text_with_azure_error_logged_and_returns_none(self, mock_client_cls):
+        mock_client = mock.Mock()
+        mock_client.begin_analyze_document.side_effect = RuntimeError("fail")
+        mock_client_cls.return_value = mock_client
+
+        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())
+            with mock.patch.object(parser.log, "error") as mock_log_error:
+                parser.parse(
+                    self.SAMPLE_FILES / "simple-digital.pdf",
+                    "application/pdf",
+                )
+
+        self.assertIsNone(parser.text)
+        mock_client.begin_analyze_document.assert_called_once()
+        mock_client.close.assert_called_once()
+        mock_log_error.assert_called_once()
+        self.assertIn(
+            "Azure AI Vision parsing failed",
+            mock_log_error.call_args[0][0],
+        )
+
+    @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/02/ff/1175b0b7371e46244032d43a56862d0af455823b5280a50c63d99cc50f18/automat-25.4.16-py3-none-any.whl", hash = "sha256:04e9bce696a8d5671ee698005af6e5a9fa15354140a87f4870744604dcdd3ba1", size = 42842, upload-time = "2025-04-16T20:12:14.447Z" },
 ]
 
+[[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"
@@ -1451,6 +1479,15 @@ 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"
@@ -2118,6 +2155,7 @@ name = "paperless-ngx"
 version = "2.20.3"
 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'" },
@@ -2255,6 +2293,7 @@ typing = [
 
 [package.metadata]
 requires-dist = [
+    { name = "azure-ai-documentintelligence", specifier = ">=1.0.2" },
     { name = "babel", specifier = ">=2.17" },
     { name = "bleach", specifier = "~=6.3.0" },
     { name = "celery", extras = ["redis"], specifier = "~=5.5.1" },