Fix: move re-index after workflow runs on doc edit

---------

Co-authored-by: shamoon <4887959+shamoon@users.noreply.github.com>

pyproject.toml

@@ -256,8 +256,8 @@ isort.force-single-line = true
 [tool.codespell]
 ignore-words-list = "criterias,afterall,valeu,ureue,equest,ure,assertIn,Oktober,commitish,NIN,nin,reprot"
 skip = """\
-  src-ui/src/locale/*,src-ui/pnpm-lock.yaml,src-ui/e2e/*,src/paperless/tests/samples/mail/*,src/documents/tests/samples\
-  /*,src/paperless_testing/sample_files/*,*.po,*.json\
+  src-ui/src/locale/*,src-ui/pnpm-lock.yaml,src-ui/e2e/*,src/paperless_mail/tests/samples/*,src/paperless/tests/samples\
+  /mail/*,src/documents/tests/samples/*,*.po,*.json\
   """
 write-changes = true
 

src-ui/e2e/backend.py

@@ -134,9 +134,7 @@ def seed_database() -> None:
     originals.mkdir(parents=True)
     thumbnails = Path(os.environ["PAPERLESS_MEDIA_ROOT"]) / "documents" / "thumbnails"
     thumbnails.mkdir(parents=True)
-    sample_pdf = (
-        SOURCE_ROOT / "paperless_testing" / "sample_files" / "simple-digital.pdf"
-    )
+    sample_pdf = SOURCE_ROOT / "documents" / "tests" / "samples" / "simple.pdf"
     for document in documents:
         shutil.copyfile(sample_pdf, originals / document.filename)
         shutil.copyfile(

src-ui/src/app/components/admin/tasks/tasks.component.spec.ts

@@ -19,7 +19,6 @@ import {
   PaperlessTaskTriggerSource,
   PaperlessTaskType,
 } from 'src/app/data/paperless-task'
-import { Results } from 'src/app/data/results'
 import { IfPermissionsDirective } from 'src/app/directives/if-permissions.directive'
 import { PermissionsGuard } from 'src/app/guards/permissions.guard'
 import { CustomDatePipe } from 'src/app/pipes/custom-date.pipe'
@@ -153,11 +152,6 @@ const tasks: PaperlessTask[] = [
   },
 ]
 
-const paginatedTasks: Results<PaperlessTask> = {
-  count: tasks.length,
-  results: tasks,
-}
-
 const sectionCountResponse = {
   all: 7,
   needs_attention: 2,
@@ -204,7 +198,7 @@ describe('TasksComponent', () => {
     }).compileComponents()
 
     tasksService = TestBed.inject(TasksService)
-    reloadSpy = jest.spyOn(tasksService, 'reload')
+    reloadSpy = jest.spyOn(tasksService, 'reload').mockImplementation(() => {})
     httpTestingController = TestBed.inject(HttpTestingController)
     modalService = TestBed.inject(NgbModal)
     router = TestBed.inject(Router)
@@ -214,15 +208,6 @@ describe('TasksComponent', () => {
     jest.useFakeTimers()
     fixture.detectChanges()
 
-    httpTestingController
-      .expectOne(
-        (req) =>
-          req.url === `${environment.apiBaseUrl}tasks/` &&
-          req.params.get('acknowledged') === 'false' &&
-          req.params.get('page_size') === '1000'
-      )
-      .flush(paginatedTasks)
-
     httpTestingController
       .expectOne(
         (req) =>

src-ui/src/app/components/app-frame/app-frame.component.html

@@ -344,11 +344,11 @@
                 ngbPopover="Tasks" i18n-ngbPopover [disablePopover]="!slimSidebarPopoversEnabled" placement="end"
                 container="body" triggers="mouseenter:mouseleave" popoverClass="popover-slim">
                 <i-bs class="me-2" name="list-task"></i-bs><span class="nav-link-label"><ng-container i18n>Tasks</ng-container></span>
-                @if (tasksService.needsAttentionTasks.length > 0 && !slimSidebarEnabled) {
-                  <span class="badge bg-danger ms-2 d-inline flex-shrink-0">{{tasksService.needsAttentionTasks.length}}</span>
+                @if (tasksService.needsAttentionTasksCount > 0 && !slimSidebarEnabled) {
+                  <span class="badge bg-danger ms-2 d-inline flex-shrink-0">{{tasksService.needsAttentionTasksCount}}</span>
                 }
-                @if (tasksService.needsAttentionTasks.length > 0 && slimSidebarEnabled) {
-                  <span class="badge bg-danger position-absolute top-0 end-0 d-none d-md-block">{{tasksService.needsAttentionTasks.length}}</span>
+                @if (tasksService.needsAttentionTasksCount > 0 && slimSidebarEnabled) {
+                  <span class="badge bg-danger position-absolute top-0 end-0 d-none d-md-block">{{tasksService.needsAttentionTasksCount}}</span>
                 }
               </a>
             </li>

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

@@ -588,8 +588,8 @@ describe('AppFrameComponent', () => {
 
   it('should show tasks badge for needs-attention tasks', () => {
     jest
-      .spyOn(tasksService, 'needsAttentionTasks', 'get')
-      .mockReturnValue([{} as any, {} as any])
+      .spyOn(tasksService, 'needsAttentionTasksCount', 'get')
+      .mockReturnValue(2)
 
     fixture.detectChanges()
 

src-ui/src/app/services/tasks.service.spec.ts

@@ -9,11 +9,7 @@ import {
 } from '@angular/common/http/testing'
 import { TestBed } from '@angular/core/testing'
 import { environment } from 'src/environments/environment'
-import {
-  PaperlessTaskStatus,
-  PaperlessTaskTriggerSource,
-  PaperlessTaskType,
-} from '../data/paperless-task'
+import { PaperlessTaskType } from '../data/paperless-task'
 import { TasksService } from './tasks.service'
 
 describe('TasksService', () => {
@@ -38,23 +34,23 @@ describe('TasksService', () => {
     httpTestingController.verify()
   })
 
-  it('calls tasks api endpoint on reload', () => {
+  it('calls tasks status counts api endpoint on reload', () => {
     tasksService.reload()
     const req = httpTestingController.expectOne(
       (req: HttpRequest<unknown>) =>
-        req.url === `${environment.apiBaseUrl}tasks/` &&
-        req.params.get('acknowledged') === 'false' &&
-        req.params.get('page_size') === '1000'
+        req.url === `${environment.apiBaseUrl}tasks/status_counts/` &&
+        req.params.get('acknowledged') === 'false'
     )
     expect(req.request.method).toEqual('GET')
-    req.flush({ count: 0, results: [] })
+    req.flush({ all: 5, needs_attention: 3, in_progress: 1, completed: 1 })
+    expect(tasksService.needsAttentionTasksCount).toEqual(3)
   })
 
   it('cancels an in-progress reload when reloading again', () => {
     tasksService.reload()
     const staleReload = httpTestingController.expectOne(
       (req: HttpRequest<unknown>) =>
-        req.url === `${environment.apiBaseUrl}tasks/`
+        req.url === `${environment.apiBaseUrl}tasks/status_counts/`
     )
     tasksService.reload()
 
@@ -62,9 +58,9 @@ describe('TasksService', () => {
     httpTestingController
       .expectOne(
         (req: HttpRequest<unknown>) =>
-          req.url === `${environment.apiBaseUrl}tasks/`
+          req.url === `${environment.apiBaseUrl}tasks/status_counts/`
       )
-      .flush({ count: 0, results: [] })
+      .flush({ all: 0, needs_attention: 0, in_progress: 0, completed: 0 })
   })
 
   it('continues reloading after a reload request fails', () => {
@@ -72,7 +68,7 @@ describe('TasksService', () => {
     httpTestingController
       .expectOne(
         (req: HttpRequest<unknown>) =>
-          req.url === `${environment.apiBaseUrl}tasks/`
+          req.url === `${environment.apiBaseUrl}tasks/status_counts/`
       )
       .flush('error', { status: 500, statusText: 'error' })
 
@@ -82,16 +78,16 @@ describe('TasksService', () => {
     httpTestingController
       .expectOne(
         (req: HttpRequest<unknown>) =>
-          req.url === `${environment.apiBaseUrl}tasks/`
+          req.url === `${environment.apiBaseUrl}tasks/status_counts/`
       )
-      .flush({ count: 0, results: [] })
+      .flush({ all: 0, needs_attention: 0, in_progress: 0, completed: 0 })
   })
 
   it('reloads after dismissing a task while a reload is already in progress', () => {
     tasksService.reload()
     const staleReload = httpTestingController.expectOne(
       (req: HttpRequest<unknown>) =>
-        req.url === `${environment.apiBaseUrl}tasks/` &&
+        req.url === `${environment.apiBaseUrl}tasks/status_counts/` &&
         req.params.get('acknowledged') === 'false'
     )
 
@@ -104,12 +100,12 @@ describe('TasksService', () => {
     httpTestingController
       .expectOne(
         (req: HttpRequest<unknown>) =>
-          req.url === `${environment.apiBaseUrl}tasks/` &&
+          req.url === `${environment.apiBaseUrl}tasks/status_counts/` &&
           req.params.get('acknowledged') === 'false'
       )
-      .flush({ count: 0, results: [] })
+      .flush({ all: 50, needs_attention: 42, in_progress: 3, completed: 5 })
 
-    expect(tasksService.needsAttentionTasks).toHaveLength(0)
+    expect(tasksService.needsAttentionTasksCount).toEqual(42)
   })
 
   it('calls acknowledge_tasks api endpoint on dismiss and reloads', () => {
@@ -126,11 +122,10 @@ describe('TasksService', () => {
     httpTestingController
       .expectOne(
         (req: HttpRequest<unknown>) =>
-          req.url === `${environment.apiBaseUrl}tasks/` &&
-          req.params.get('acknowledged') === 'false' &&
-          req.params.get('page_size') === '1000'
+          req.url === `${environment.apiBaseUrl}tasks/status_counts/` &&
+          req.params.get('acknowledged') === 'false'
       )
-      .flush({ count: 0, results: [] })
+      .flush({ all: 0, needs_attention: 0, in_progress: 0, completed: 0 })
   })
 
   it('calls acknowledge_tasks api endpoint on dismiss all and reloads', () => {
@@ -147,65 +142,10 @@ describe('TasksService', () => {
     httpTestingController
       .expectOne(
         (req: HttpRequest<unknown>) =>
-          req.url === `${environment.apiBaseUrl}tasks/` &&
-          req.params.get('acknowledged') === 'false' &&
-          req.params.get('page_size') === '1000'
+          req.url === `${environment.apiBaseUrl}tasks/status_counts/` &&
+          req.params.get('acknowledged') === 'false'
       )
-      .flush({ count: 0, results: [] })
-  })
-
-  it('includes revoked tasks in needs attention', () => {
-    const mockTasks = [
-      {
-        task_type: PaperlessTaskType.SanityCheck,
-        trigger_source: PaperlessTaskTriggerSource.System,
-        status: PaperlessTaskStatus.Failure,
-        acknowledged: false,
-        task_id: '1235',
-        input_data: {},
-        date_created: new Date(),
-        related_document_ids: [],
-      },
-      {
-        task_type: PaperlessTaskType.MailFetch,
-        trigger_source: PaperlessTaskTriggerSource.Scheduled,
-        status: PaperlessTaskStatus.Revoked,
-        acknowledged: false,
-        task_id: '1236',
-        input_data: {},
-        date_created: new Date(),
-        related_document_ids: [],
-      },
-      {
-        task_type: PaperlessTaskType.EmptyTrash,
-        trigger_source: PaperlessTaskTriggerSource.Manual,
-        status: PaperlessTaskStatus.Success,
-        acknowledged: false,
-        task_id: '1238',
-        input_data: {},
-        date_created: new Date(),
-        related_document_ids: [],
-      },
-    ]
-
-    tasksService.reload()
-
-    const req = httpTestingController.expectOne(
-      (req: HttpRequest<unknown>) =>
-        req.url === `${environment.apiBaseUrl}tasks/` &&
-        req.params.get('acknowledged') === 'false' &&
-        req.params.get('page_size') === '1000'
-    )
-
-    req.flush({ count: mockTasks.length, results: mockTasks })
-
-    expect(tasksService.needsAttentionTasks).toHaveLength(2)
-    expect(tasksService.needsAttentionTasks.map((task) => task.status)).toEqual(
-      expect.arrayContaining([
-        PaperlessTaskStatus.Failure,
-        PaperlessTaskStatus.Revoked,
-      ])
-    )
+      .flush({ all: 0, needs_attention: 0, in_progress: 0, completed: 0 })
   })
 
   it('supports running tasks', () => {

src-ui/src/app/services/tasks.service.ts

@@ -5,14 +5,12 @@ import {
   catchError,
   finalize,
   first,
-  map,
   switchMap,
   takeUntil,
   tap,
 } from 'rxjs/operators'
 import {
   PaperlessTask,
-  PaperlessTaskStatus,
   PaperlessTaskStatusCounts,
   PaperlessTaskType,
 } from 'src/app/data/paperless-task'
@@ -27,50 +25,42 @@ export class TasksService {
 
   private baseUrl: string = environment.apiBaseUrl
   private endpoint: string = 'tasks'
-  private readonly defaultReloadPageSize = 1000
 
   public loading: boolean = false
 
-  private readonly tasks = signal<PaperlessTask[]>([])
+  private readonly tasksStatusCounts = signal<PaperlessTaskStatusCounts>({
+    all: 0,
+    needs_attention: 0,
+    in_progress: 0,
+    completed: 0,
+  })
   private readonly reloadNotifier = new Subject<void>()
 
   private unsubscribeNotifer: Subject<any> = new Subject()
 
   constructor() {
     this.reloadNotifier
-      .pipe(
-        switchMap(() => {
-          this.loading = true
-          return this.http
-            .get<Results<PaperlessTask>>(`${this.baseUrl}${this.endpoint}/`, {
-              params: {
-                acknowledged: 'false',
-                page_size: this.defaultReloadPageSize,
-              },
-            })
-            .pipe(
-              map((response) => response.results),
-              takeUntil(this.unsubscribeNotifer),
-              catchError(() => EMPTY),
-              finalize(() => {
-                this.loading = false
-              })
-            )
-        })
-      )
-      .subscribe((tasks) => {
-        this.tasks.set(tasks)
+      .pipe(switchMap(() => this.fetchUnacknowledgedTasksCounts()))
+      .subscribe((taskStatusCounts) => {
+        this.tasksStatusCounts.set(taskStatusCounts)
       })
   }
 
-  public get needsAttentionTasks(): PaperlessTask[] {
-    return this.tasks().filter((t) =>
-      [PaperlessTaskStatus.Failure, PaperlessTaskStatus.Revoked].includes(
-        t.status
-      )
+  private fetchUnacknowledgedTasksCounts(): Observable<PaperlessTaskStatusCounts> {
+    this.loading = true
+    return this.statusCounts({ acknowledged: false }).pipe(
+      takeUntil(this.unsubscribeNotifer),
+      catchError(() => EMPTY),
+      finalize(() => {
+        this.loading = false
+      })
     )
   }
 
+  public get needsAttentionTasksCount(): number {
+    return this.tasksStatusCounts().needs_attention
+  }
+
   public reload() {
     this.reloadNotifier.next()
   }
@@ -105,7 +95,7 @@ export class TasksService {
 
   public dismissTasks(task_ids: Set<number>): Observable<any> {
     return this.http
-      .post(`${this.baseUrl}tasks/acknowledge/`, {
+      .post(`${this.baseUrl}${this.endpoint}/acknowledge/`, {
         tasks: [...task_ids],
       })
       .pipe(
@@ -119,7 +109,7 @@ export class TasksService {
 
   public dismissAllTasks(): Observable<any> {
     return this.http
-      .post(`${this.baseUrl}tasks/acknowledge/`, {
+      .post(`${this.baseUrl}${this.endpoint}/acknowledge/`, {
         all: true,
       })
       .pipe(

src/conftest.py

@@ -11,8 +11,6 @@ from typing import TYPE_CHECKING
 
 import pytest
 
-from paperless_testing import samples
-
 if TYPE_CHECKING:
     from collections.abc import Generator
     from pathlib import Path
@@ -151,39 +149,3 @@ def fake_progress_manager(
 
     monkeypatch.setattr("documents.tasks.ProgressManager", FakeProgressManager)
     return FakeProgressManager
-
-
-@pytest.fixture(scope="session")
-def shared_samples_dir() -> Path:
-    """Directory of sample files used by more than one app's tests."""
-    return samples.SHARED_SAMPLES_DIR
-
-
-@pytest.fixture(scope="session")
-def simple_digital_pdf_file() -> Path:
-    """One-page PDF with a text layer."""
-    return samples.SIMPLE_DIGITAL_PDF
-
-
-@pytest.fixture(scope="session")
-def multi_page_digital_pdf_file() -> Path:
-    """Three-page PDF with a text layer."""
-    return samples.MULTI_PAGE_DIGITAL_PDF
-
-
-@pytest.fixture(scope="session")
-def with_form_pdf_file() -> Path:
-    """PDF containing a fillable form."""
-    return samples.WITH_FORM_PDF
-
-
-@pytest.fixture(scope="session")
-def multi_page_images_pdf_file() -> Path:
-    """Multi-page PDF of scanned images, no text layer."""
-    return samples.MULTI_PAGE_IMAGES_PDF
-
-
-@pytest.fixture(scope="session")
-def thumbnail_webp_file() -> Path:
-    """Small WebP thumbnail."""
-    return samples.THUMBNAIL_WEBP

src/documents/tests/conftest.py

@@ -12,25 +12,29 @@ if TYPE_CHECKING:
     from paperless_testing.dirs import PaperlessDirs
 
 
+@pytest.fixture(scope="session")
+def document_samples_dir() -> Path:
+    """Path to the shared test sample documents."""
+    return Path(__file__).parent / "samples" / "documents"
+
+
 @pytest.fixture()
 def sample_doc(
     paperless_dirs: "PaperlessDirs",
-    simple_digital_pdf_file: Path,
-    multi_page_images_pdf_file: Path,
-    thumbnail_webp_file: Path,
+    document_samples_dir: Path,
 ) -> "Document":
     """Create a document with valid files and matching checksums."""
     with filelock.FileLock(paperless_dirs.media_lock):
         shutil.copy(
-            simple_digital_pdf_file,
+            document_samples_dir / "originals" / "0000001.pdf",
             paperless_dirs.originals_dir / "0000001.pdf",
         )
         shutil.copy(
-            multi_page_images_pdf_file,
+            document_samples_dir / "archive" / "0000001.pdf",
             paperless_dirs.archive_dir / "0000001.pdf",
         )
         shutil.copy(
-            thumbnail_webp_file,
+            document_samples_dir / "thumbnails" / "0000001.webp",
             paperless_dirs.thumbnail_dir / "0000001.webp",
         )
 

src/documents/tests/samples/simple.txt

@@ -0,0 +1 @@
+This is a test file.

src/documents/tests/test_api_bulk_download.py

@@ -53,7 +53,7 @@ class TestBulkDownload(DirectoriesMixin, SampleDirMixin, APITestCase):
             archive_checksum="D",
         )
 
-        shutil.copy(self.SIMPLE_PDF, self.doc2.source_path)
+        shutil.copy(self.SAMPLE_DIR / "simple.pdf", self.doc2.source_path)
         shutil.copy(self.SAMPLE_DIR / "simple.png", self.doc2b.source_path)
         shutil.copy(self.SAMPLE_DIR / "simple.jpg", self.doc3.source_path)
         shutil.copy(self.SAMPLE_DIR / "test_with_bom.pdf", self.doc3.archive_path)

src/documents/tests/test_api_documents.py

@@ -46,6 +46,7 @@ from documents.models import UiSettings
 from documents.models import Workflow
 from documents.models import WorkflowAction
 from documents.models import WorkflowTrigger
+from documents.search import get_backend
 from documents.signals.handlers import run_workflows
 from documents.tests.utils import ConsumeTaskMixin
 from paperless_testing.dirs import DirectoriesMixin
@@ -56,8 +57,6 @@ from paperless_testing.http import read_streaming_response
 from paperless_testing.permissions import grant_all_global
 from paperless_testing.permissions import grant_global
 from paperless_testing.permissions import grant_object
-from paperless_testing.samples import SIMPLE_DIGITAL_PDF
-from paperless_testing.samples import THUMBNAIL_WEBP
 
 
 class TestDocumentApi(DirectoriesMixin, ConsumeTaskMixin, APITestCase):
@@ -68,6 +67,70 @@ class TestDocumentApi(DirectoriesMixin, ConsumeTaskMixin, APITestCase):
         self.client.force_authenticate(user=self.user)
         cache.clear()
 
+    def test_detail_save_indexes_final_workflow_state(self) -> None:
+        viewer = UserFactory()
+        grant_global(viewer, "view_document")
+        inbox = TagFactory(is_inbox_tag=True)
+        doc = DocumentFactory(owner=self.user, content="distinctiveword")
+        doc.tags.add(inbox)
+        trigger = WorkflowTrigger.objects.create(
+            type=WorkflowTrigger.WorkflowTriggerType.DOCUMENT_UPDATED,
+        )
+        action = WorkflowAction.objects.create(assign_title="Workflow title")
+        action.assign_view_users.add(viewer)
+        action.remove_view_users.add(viewer)
+        workflow = Workflow.objects.create(name="Update document")
+        workflow.triggers.add(trigger)
+        workflow.actions.add(action)
+        backend = get_backend()
+        backend.add_or_update(doc)
+
+        for action_type in (
+            WorkflowAction.WorkflowActionType.ASSIGNMENT,
+            WorkflowAction.WorkflowActionType.REMOVAL,
+            WorkflowAction.WorkflowActionType.MOVE_TO_TRASH,
+        ):
+            with self.subTest(action_type=action_type):
+                grant = action_type == WorkflowAction.WorkflowActionType.ASSIGNMENT
+                action.type = action_type
+                action.save()
+                trigger.filter_has_not_tags.set([inbox] if grant else [])
+                trigger.filter_has_tags.set([] if grant else [inbox])
+                self.client.force_authenticate(self.user)
+                response = self.client.patch(
+                    f"/api/documents/{doc.pk}/",
+                    {"tags": [] if grant else [inbox.pk]},
+                    format="json",
+                )
+                self.assertEqual(response.status_code, status.HTTP_200_OK)
+                self.client.force_authenticate(viewer)
+                self.assertEqual(
+                    self.client.get(f"/api/documents/{doc.pk}/").status_code,
+                    status.HTTP_200_OK if grant else status.HTTP_404_NOT_FOUND,
+                )
+                # Check the index directly: the API's DB permission filtering
+                # would otherwise hide stale grants and trashed index entries.
+                self.assertEqual(
+                    list(backend.search_ids("distinctiveword", user=viewer)),
+                    [doc.pk] if grant else [],
+                )
+                if grant:
+                    response = self.client.get(
+                        "/api/documents/",
+                        {"query": "distinctiveword AND title:workflow"},
+                    )
+                    self.assertEqual(response.status_code, status.HTTP_200_OK)
+                    self.assertEqual(
+                        [result["id"] for result in response.data["results"]],
+                        [doc.pk],
+                    )
+                elif action_type == WorkflowAction.WorkflowActionType.MOVE_TO_TRASH:
+                    self.assertFalse(Document.objects.filter(pk=doc.pk).exists())
+                    self.assertEqual(
+                        list(backend.search_ids("distinctiveword", user=None)),
+                        [],
+                    )
+
     def testDocuments(self) -> None:
         response = self.client.get("/api/documents/").data
 
@@ -1854,11 +1917,7 @@ class TestDocumentApi(DirectoriesMixin, ConsumeTaskMixin, APITestCase):
             id=str(uuid.uuid4()),
         )
 
-        with SimpleUploadedFile(
-            "simple.pdf",
-            SIMPLE_DIGITAL_PDF.read_bytes(),
-            content_type="application/pdf",
-        ) as f:
+        with (Path(__file__).parent / "samples" / "simple.pdf").open("rb") as f:
             response = self.client.post(
                 "/api/documents/post_document/",
                 {"document": f},
@@ -1886,7 +1945,7 @@ class TestDocumentApi(DirectoriesMixin, ConsumeTaskMixin, APITestCase):
 
         payload = SimpleUploadedFile(
             "../../outside.pdf",
-            SIMPLE_DIGITAL_PDF.read_bytes(),
+            (Path(__file__).parent / "samples" / "simple.pdf").read_bytes(),
             content_type="application/pdf",
         )
 
@@ -1915,7 +1974,7 @@ class TestDocumentApi(DirectoriesMixin, ConsumeTaskMixin, APITestCase):
             id=str(uuid.uuid4()),
         )
 
-        pdf_bytes = SIMPLE_DIGITAL_PDF.read_bytes()
+        pdf_bytes = (Path(__file__).parent / "samples" / "simple.pdf").read_bytes()
         boundary = "paperless-boundary"
         payload = (
             (
@@ -1991,7 +2050,7 @@ class TestDocumentApi(DirectoriesMixin, ConsumeTaskMixin, APITestCase):
     def test_upload_insufficient_permissions(self) -> None:
         self.client.force_authenticate(user=UserFactory(username="testuser2"))
 
-        with SIMPLE_DIGITAL_PDF.open("rb") as f:
+        with (Path(__file__).parent / "samples" / "simple.pdf").open("rb") as f:
             response = self.client.post(
                 "/api/documents/post_document/",
                 {"document": f},
@@ -2004,11 +2063,7 @@ class TestDocumentApi(DirectoriesMixin, ConsumeTaskMixin, APITestCase):
             id=str(uuid.uuid4()),
         )
 
-        with SimpleUploadedFile(
-            "simple.pdf",
-            SIMPLE_DIGITAL_PDF.read_bytes(),
-            content_type="application/pdf",
-        ) as f:
+        with (Path(__file__).parent / "samples" / "simple.pdf").open("rb") as f:
             response = self.client.post(
                 "/api/documents/post_document/",
                 {
@@ -2041,7 +2096,7 @@ class TestDocumentApi(DirectoriesMixin, ConsumeTaskMixin, APITestCase):
             id=str(uuid.uuid4()),
         )
 
-        with SIMPLE_DIGITAL_PDF.open("rb") as f:
+        with (Path(__file__).parent / "samples" / "simple.pdf").open("rb") as f:
             response = self.client.post(
                 "/api/documents/post_document/",
                 {"documenst": f},
@@ -2067,7 +2122,7 @@ class TestDocumentApi(DirectoriesMixin, ConsumeTaskMixin, APITestCase):
             id=str(uuid.uuid4()),
         )
 
-        with SIMPLE_DIGITAL_PDF.open("rb") as f:
+        with (Path(__file__).parent / "samples" / "simple.pdf").open("rb") as f:
             response = self.client.post(
                 "/api/documents/post_document/",
                 {"document": f, "title": "my custom title"},
@@ -2087,7 +2142,7 @@ class TestDocumentApi(DirectoriesMixin, ConsumeTaskMixin, APITestCase):
         )
 
         c = Correspondent.objects.create(name="test-corres")
-        with SIMPLE_DIGITAL_PDF.open("rb") as f:
+        with (Path(__file__).parent / "samples" / "simple.pdf").open("rb") as f:
             response = self.client.post(
                 "/api/documents/post_document/",
                 {"document": f, "correspondent": c.id},
@@ -2106,7 +2161,7 @@ class TestDocumentApi(DirectoriesMixin, ConsumeTaskMixin, APITestCase):
             id=str(uuid.uuid4()),
         )
 
-        with SIMPLE_DIGITAL_PDF.open("rb") as f:
+        with (Path(__file__).parent / "samples" / "simple.pdf").open("rb") as f:
             response = self.client.post(
                 "/api/documents/post_document/",
                 {"document": f, "correspondent": 3456},
@@ -2121,7 +2176,7 @@ class TestDocumentApi(DirectoriesMixin, ConsumeTaskMixin, APITestCase):
         )
 
         dt = DocumentType.objects.create(name="invoice")
-        with SIMPLE_DIGITAL_PDF.open("rb") as f:
+        with (Path(__file__).parent / "samples" / "simple.pdf").open("rb") as f:
             response = self.client.post(
                 "/api/documents/post_document/",
                 {"document": f, "document_type": dt.id},
@@ -2140,7 +2195,7 @@ class TestDocumentApi(DirectoriesMixin, ConsumeTaskMixin, APITestCase):
             id=str(uuid.uuid4()),
         )
 
-        with SIMPLE_DIGITAL_PDF.open("rb") as f:
+        with (Path(__file__).parent / "samples" / "simple.pdf").open("rb") as f:
             response = self.client.post(
                 "/api/documents/post_document/",
                 {"document": f, "document_type": 34578},
@@ -2155,7 +2210,7 @@ class TestDocumentApi(DirectoriesMixin, ConsumeTaskMixin, APITestCase):
         )
 
         sp = StoragePath.objects.create(name="invoices")
-        with SIMPLE_DIGITAL_PDF.open("rb") as f:
+        with (Path(__file__).parent / "samples" / "simple.pdf").open("rb") as f:
             response = self.client.post(
                 "/api/documents/post_document/",
                 {"document": f, "storage_path": sp.id},
@@ -2174,7 +2229,7 @@ class TestDocumentApi(DirectoriesMixin, ConsumeTaskMixin, APITestCase):
             id=str(uuid.uuid4()),
         )
 
-        with SIMPLE_DIGITAL_PDF.open("rb") as f:
+        with (Path(__file__).parent / "samples" / "simple.pdf").open("rb") as f:
             response = self.client.post(
                 "/api/documents/post_document/",
                 {"document": f, "storage_path": 34578},
@@ -2190,7 +2245,7 @@ class TestDocumentApi(DirectoriesMixin, ConsumeTaskMixin, APITestCase):
 
         t1 = Tag.objects.create(name="tag1")
         t2 = Tag.objects.create(name="tag2")
-        with SIMPLE_DIGITAL_PDF.open("rb") as f:
+        with (Path(__file__).parent / "samples" / "simple.pdf").open("rb") as f:
             response = self.client.post(
                 "/api/documents/post_document/",
                 {"document": f, "tags": [t2.id, t1.id]},
@@ -2211,7 +2266,7 @@ class TestDocumentApi(DirectoriesMixin, ConsumeTaskMixin, APITestCase):
 
         t1 = Tag.objects.create(name="tag1")
         t2 = Tag.objects.create(name="tag2")
-        with SIMPLE_DIGITAL_PDF.open("rb") as f:
+        with (Path(__file__).parent / "samples" / "simple.pdf").open("rb") as f:
             response = self.client.post(
                 "/api/documents/post_document/",
                 {"document": f, "tags": [t2.id, t1.id, 734563]},
@@ -2235,7 +2290,7 @@ class TestDocumentApi(DirectoriesMixin, ConsumeTaskMixin, APITestCase):
             0,
             tzinfo=zoneinfo.ZoneInfo("America/Los_Angeles"),
         )
-        with SIMPLE_DIGITAL_PDF.open("rb") as f:
+        with (Path(__file__).parent / "samples" / "simple.pdf").open("rb") as f:
             response = self.client.post(
                 "/api/documents/post_document/",
                 {"document": f, "created": created},
@@ -2251,11 +2306,7 @@ class TestDocumentApi(DirectoriesMixin, ConsumeTaskMixin, APITestCase):
             id=str(uuid.uuid4()),
         )
 
-        with SimpleUploadedFile(
-            "simple.pdf",
-            SIMPLE_DIGITAL_PDF.read_bytes(),
-            content_type="application/pdf",
-        ) as f:
+        with (Path(__file__).parent / "samples" / "simple.pdf").open("rb") as f:
             response = self.client.post(
                 "/api/documents/post_document/",
                 {"document": f, "archive_serial_number": 500},
@@ -2282,11 +2333,7 @@ class TestDocumentApi(DirectoriesMixin, ConsumeTaskMixin, APITestCase):
             data_type=CustomField.FieldDataType.STRING,
         )
 
-        with SimpleUploadedFile(
-            "simple.pdf",
-            SIMPLE_DIGITAL_PDF.read_bytes(),
-            content_type="application/pdf",
-        ) as f:
+        with (Path(__file__).parent / "samples" / "simple.pdf").open("rb") as f:
             response = self.client.post(
                 "/api/documents/post_document/",
                 {
@@ -2341,7 +2388,7 @@ class TestDocumentApi(DirectoriesMixin, ConsumeTaskMixin, APITestCase):
         w1.actions.add(action1)
         w1.save()
 
-        with SIMPLE_DIGITAL_PDF.open("rb") as f:
+        with (Path(__file__).parent / "samples" / "simple.pdf").open("rb") as f:
             response = self.client.post(
                 "/api/documents/post_document/",
                 {
@@ -2382,11 +2429,7 @@ class TestDocumentApi(DirectoriesMixin, ConsumeTaskMixin, APITestCase):
             data_type=CustomField.FieldDataType.INT,
         )
 
-        with SimpleUploadedFile(
-            "simple.pdf",
-            SIMPLE_DIGITAL_PDF.read_bytes(),
-            content_type="application/pdf",
-        ) as f:
+        with (Path(__file__).parent / "samples" / "simple.pdf").open("rb") as f:
             response = self.client.post(
                 "/api/documents/post_document/",
                 {
@@ -2435,7 +2478,7 @@ class TestDocumentApi(DirectoriesMixin, ConsumeTaskMixin, APITestCase):
         ]
 
         for payload in error_payloads:
-            with SIMPLE_DIGITAL_PDF.open("rb") as f:
+            with (Path(__file__).parent / "samples" / "simple.pdf").open("rb") as f:
                 data = {"document": f, **payload}
                 response = self.client.post(
                     "/api/documents/post_document/",
@@ -2493,7 +2536,7 @@ class TestDocumentApi(DirectoriesMixin, ConsumeTaskMixin, APITestCase):
             id=str(uuid.uuid4()),
         )
 
-        with SIMPLE_DIGITAL_PDF.open("rb") as f:
+        with (Path(__file__).parent / "samples" / "simple.pdf").open("rb") as f:
             response = self.client.post(
                 "/api/documents/post_document/",
                 {"document": f, "from_webui": True},
@@ -2532,8 +2575,14 @@ class TestDocumentApi(DirectoriesMixin, ConsumeTaskMixin, APITestCase):
             archive_filename="archive.pdf",
         )
 
-        source_file: Path = THUMBNAIL_WEBP
-        archive_file: Path = SIMPLE_DIGITAL_PDF
+        source_file: Path = (
+            Path(__file__).parent
+            / "samples"
+            / "documents"
+            / "thumbnails"
+            / "0000001.webp"
+        )
+        archive_file: Path = Path(__file__).parent / "samples" / "simple.pdf"
 
         shutil.copy(source_file, doc.source_path)
         shutil.copy(archive_file, doc.archive_path)
@@ -2566,7 +2615,7 @@ class TestDocumentApi(DirectoriesMixin, ConsumeTaskMixin, APITestCase):
             mime_type="application/pdf",
         )
 
-        shutil.copy(SIMPLE_DIGITAL_PDF, doc.source_path)
+        shutil.copy(Path(__file__).parent / "samples" / "simple.pdf", doc.source_path)
 
         response = self.client.get(f"/api/documents/{doc.pk}/metadata/")
         self.assertEqual(response.status_code, status.HTTP_200_OK)
@@ -4332,8 +4381,8 @@ class TestDocumentApi(DirectoriesMixin, ConsumeTaskMixin, APITestCase):
             filename="test2.pdf",
         )
 
-        archive_file = SIMPLE_DIGITAL_PDF
-        source_file = SIMPLE_DIGITAL_PDF
+        archive_file = Path(__file__).parent / "samples" / "simple.pdf"
+        source_file = Path(__file__).parent / "samples" / "simple.pdf"
 
         shutil.copy(archive_file, doc.archive_path)
         shutil.copy(source_file, doc2.source_path)

src/documents/tests/test_api_email.py

@@ -12,9 +12,6 @@ from documents.tests.utils import SampleDirMixin
 from paperless_testing.dirs import DirectoriesMixin
 from paperless_testing.factories import UserFactory
 from paperless_testing.permissions import grant_global
-from paperless_testing.samples import MULTI_PAGE_DIGITAL_PDF
-from paperless_testing.samples import SIMPLE_DIGITAL_PDF
-from paperless_testing.samples import WITH_FORM_PDF
 
 
 class TestEmail(DirectoriesMixin, SampleDirMixin, APITestCase):
@@ -45,15 +42,15 @@ class TestEmail(DirectoriesMixin, SampleDirMixin, APITestCase):
 
         # Copy sample files to document paths (using different files to distinguish versions)
         shutil.copy(
-            SIMPLE_DIGITAL_PDF,
+            self.SAMPLE_DIR / "documents" / "originals" / "0000001.pdf",
             self.doc1.archive_path,
         )
         shutil.copy(
-            MULTI_PAGE_DIGITAL_PDF,
+            self.SAMPLE_DIR / "documents" / "originals" / "0000002.pdf",
             self.doc1.source_path,
         )
         shutil.copy(
-            WITH_FORM_PDF,
+            self.SAMPLE_DIR / "documents" / "originals" / "0000003.pdf",
             self.doc2.source_path,
         )
 
@@ -380,7 +377,7 @@ class TestEmail(DirectoriesMixin, SampleDirMixin, APITestCase):
             checksum="3",
             filename="test3.pdf",
         )
-        shutil.copy(self.SIMPLE_PDF, doc3.source_path)
+        shutil.copy(self.SAMPLE_DIR / "simple.pdf", doc3.source_path)
 
         doc4 = Document.objects.create(
             title="test1",
@@ -389,7 +386,7 @@ class TestEmail(DirectoriesMixin, SampleDirMixin, APITestCase):
             checksum="4",
             filename="test4.pdf",
         )
-        shutil.copy(self.SIMPLE_PDF, doc4.source_path)
+        shutil.copy(self.SAMPLE_DIR / "simple.pdf", doc4.source_path)
 
         response = self.client.post(
             self.ENDPOINT,

src/documents/tests/test_barcodes.py

@@ -169,7 +169,7 @@ class TestBarcode(
             - No barcodes detected
             - No pages to split on
         """
-        test_file = self.SIMPLE_PDF
+        test_file = self.SAMPLE_DIR / "simple.pdf"
         with self.get_reader(test_file) as reader:
             reader.detect()
             separator_page_numbers = reader.get_separation_pages()
@@ -461,7 +461,7 @@ class TestBarcode(
         THEN:
             - Nothing happens
         """
-        test_file = self.SIMPLE_PDF
+        test_file = self.SAMPLE_DIR / "simple.pdf"
 
         with self.get_reader(test_file) as reader:
             try:

src/documents/tests/test_bulk_edit.py

@@ -29,9 +29,6 @@ from documents.permissions import set_permissions_for_objects
 from paperless_testing.dirs import DirectoriesMixin
 from paperless_testing.factories import DocumentFactory
 from paperless_testing.permissions import grant_object
-from paperless_testing.samples import MULTI_PAGE_DIGITAL_PDF
-from paperless_testing.samples import SIMPLE_DIGITAL_PDF
-from paperless_testing.samples import WITH_FORM_PDF
 
 
 class TestBulkEdit(DirectoriesMixin, TestCase):
@@ -709,27 +706,47 @@ class TestPDFActions(DirectoriesMixin, TestCase):
         super().setUp()
         sample1 = self.dirs.scratch_dir / "sample.pdf"
         shutil.copy(
-            SIMPLE_DIGITAL_PDF,
+            Path(__file__).parent
+            / "samples"
+            / "documents"
+            / "originals"
+            / "0000001.pdf",
             sample1,
         )
         sample1_archive = self.dirs.archive_dir / "sample_archive.pdf"
         shutil.copy(
-            SIMPLE_DIGITAL_PDF,
+            Path(__file__).parent
+            / "samples"
+            / "documents"
+            / "originals"
+            / "0000001.pdf",
             sample1_archive,
         )
         sample2 = self.dirs.scratch_dir / "sample2.pdf"
         shutil.copy(
-            MULTI_PAGE_DIGITAL_PDF,
+            Path(__file__).parent
+            / "samples"
+            / "documents"
+            / "originals"
+            / "0000002.pdf",
             sample2,
         )
         sample2_archive = self.dirs.archive_dir / "sample2_archive.pdf"
         shutil.copy(
-            MULTI_PAGE_DIGITAL_PDF,
+            Path(__file__).parent
+            / "samples"
+            / "documents"
+            / "originals"
+            / "0000002.pdf",
             sample2_archive,
         )
         sample3 = self.dirs.scratch_dir / "sample3.pdf"
         shutil.copy(
-            WITH_FORM_PDF,
+            Path(__file__).parent
+            / "samples"
+            / "documents"
+            / "originals"
+            / "0000003.pdf",
             sample3,
         )
         self.doc1 = Document.objects.create(
@@ -763,7 +780,11 @@ class TestPDFActions(DirectoriesMixin, TestCase):
         )
         img_doc_archive = self.dirs.archive_dir / "sample_image.pdf"
         shutil.copy(
-            SIMPLE_DIGITAL_PDF,
+            Path(__file__).parent
+            / "samples"
+            / "documents"
+            / "originals"
+            / "0000001.pdf",
             img_doc_archive,
         )
         self.img_doc = Document.objects.create(

src/documents/tests/test_consumer.py

@@ -39,9 +39,6 @@ from paperless_testing.factories import TagFactory
 from paperless_testing.factories import UserFactory
 from paperless_testing.fakes.progress import FakeProgressManager
 from paperless_testing.permissions import grant_object
-from paperless_testing.samples import MULTI_PAGE_DIGITAL_PDF
-from paperless_testing.samples import MULTI_PAGE_IMAGES_PDF
-from paperless_testing.samples import SIMPLE_DIGITAL_PDF
 
 
 class _BaseNewStyleParser:
@@ -118,7 +115,9 @@ class _BaseNewStyleParser:
 
 
 class DummyParser(_BaseNewStyleParser):
-    _ARCHIVE_SRC = MULTI_PAGE_IMAGES_PDF
+    _ARCHIVE_SRC = (
+        Path(__file__).parent / "samples" / "documents" / "archive" / "0000001.pdf"
+    )
 
     def parse(self, document_path, mime_type, *, produce_archive: bool = True) -> None:
         self._text = "The Text"
@@ -204,19 +203,33 @@ class TestConsumer(
         self.addCleanup(patcher.stop)
 
     def get_test_file(self):
-        src = SIMPLE_DIGITAL_PDF
+        src = (
+            Path(__file__).parent
+            / "samples"
+            / "documents"
+            / "originals"
+            / "0000001.pdf"
+        )
         dst = self.dirs.scratch_dir / "sample.pdf"
         shutil.copy(src, dst)
         return dst
 
     def get_test_file2(self):
-        src = MULTI_PAGE_DIGITAL_PDF
+        src = (
+            Path(__file__).parent
+            / "samples"
+            / "documents"
+            / "originals"
+            / "0000002.pdf"
+        )
         dst = self.dirs.scratch_dir / "sample2.pdf"
         shutil.copy(src, dst)
         return dst
 
     def get_test_archive_file(self):
-        src = MULTI_PAGE_IMAGES_PDF
+        src = (
+            Path(__file__).parent / "samples" / "documents" / "archive" / "0000001.pdf"
+        )
         dst = self.dirs.scratch_dir / "sample_archive.pdf"
         shutil.copy(src, dst)
         return dst
@@ -1111,7 +1124,7 @@ class TestConsumer(
     @mock.patch("documents.consumer.get_parser_registry")
     def test_similar_filenames(self, m) -> None:
         shutil.copy(
-            SIMPLE_DIGITAL_PDF,
+            Path(__file__).parent / "samples" / "simple.pdf",
             settings.CONSUMPTION_DIR / "simple.pdf",
         )
         shutil.copy(
@@ -1652,7 +1665,13 @@ class TestConsumerRemoteOCR(
         self.addCleanup(patcher.stop)
 
     def _consume(self, *, overrides: DocumentMetadataOverrides | None = None) -> bool:
-        src = SIMPLE_DIGITAL_PDF
+        src = (
+            Path(__file__).parent
+            / "samples"
+            / "documents"
+            / "originals"
+            / "0000001.pdf"
+        )
         dst = self.dirs.scratch_dir / "sample.pdf"
         shutil.copy(src, dst)
 

src/documents/tests/test_double_sided.py

@@ -37,15 +37,12 @@ class TestDoubleSided(
         self.double_sided_dir.mkdir()
         self.staging_file = self.dirs.scratch_dir / STAGING_FILE_NAME
 
-    def _sample(self, name: str) -> Path:
-        return self.SIMPLE_PDF if name == "simple.pdf" else self.SAMPLE_DIR / name
-
     def consume_file(self, srcname, dstname: str | Path = "foo.pdf"):
         """
         Starts the consume process and also ensures the
         destination file does not exist afterwards
         """
-        src = self._sample(srcname)
+        src = self.SAMPLE_DIR / srcname
         dst = self.double_sided_dir / dstname
         dst.parent.mkdir(parents=True, exist_ok=True)
         shutil.copy(src, dst)
@@ -60,7 +57,7 @@ class TestDoubleSided(
         return msg
 
     def create_staging_file(self, src="double-sided-odd.pdf", datetime=None) -> None:
-        shutil.copy(self._sample(src), self.staging_file)
+        shutil.copy(self.SAMPLE_DIR / src, self.staging_file)
         if datetime is None:
             datetime = dt.datetime.now()
         os.utime(str(self.staging_file), (datetime.timestamp(),) * 2)

src/documents/tests/test_management.py

@@ -23,9 +23,8 @@ from documents.tasks import update_document_content_maybe_archive_file
 from paperless_testing.assertions import FileSystemAssertsMixin
 from paperless_testing.dirs import DirectoriesMixin
 from paperless_testing.factories import DocumentFactory
-from paperless_testing.samples import SIMPLE_DIGITAL_PDF
 
-sample_file: Path = SIMPLE_DIGITAL_PDF
+sample_file: Path = Path(__file__).parent / "samples" / "simple.pdf"
 
 
 @pytest.mark.management

src/documents/tests/test_management_exporter.py

@@ -59,7 +59,6 @@ from paperless_testing.dirs import paperless_environment
 from paperless_testing.factories import DocumentBarcodeFactory
 from paperless_testing.factories import DocumentFactory
 from paperless_testing.permissions import grant_object
-from paperless_testing.samples import install_document_samples
 
 
 @pytest.mark.management
@@ -205,7 +204,10 @@ class TestExportImport(
 
     def test_exporter(self, *, use_filename_format=False) -> None:
         shutil.rmtree(Path(self.dirs.media_dir) / "documents")
-        install_document_samples(Path(self.dirs.media_dir) / "documents")
+        shutil.copytree(
+            Path(__file__).parent / "samples" / "documents",
+            Path(self.dirs.media_dir) / "documents",
+        )
 
         num_permission_objects = Permission.objects.count()
 
@@ -309,7 +311,10 @@ class TestExportImport(
 
     def test_exporter_with_filename_format(self) -> None:
         shutil.rmtree(Path(self.dirs.media_dir) / "documents")
-        install_document_samples(Path(self.dirs.media_dir) / "documents")
+        shutil.copytree(
+            Path(__file__).parent / "samples" / "documents",
+            Path(self.dirs.media_dir) / "documents",
+        )
 
         with override_settings(
             FILENAME_FORMAT="{created_year}/{correspondent}/{title}",
@@ -318,7 +323,10 @@ class TestExportImport(
 
     def test_exporter_includes_share_links_and_bundles(self) -> None:
         shutil.rmtree(Path(self.dirs.media_dir) / "documents")
-        install_document_samples(Path(self.dirs.media_dir) / "documents")
+        shutil.copytree(
+            Path(__file__).parent / "samples" / "documents",
+            Path(self.dirs.media_dir) / "documents",
+        )
 
         share_link = ShareLink.objects.create(
             slug="share-link-slug",
@@ -417,7 +425,10 @@ class TestExportImport(
 
     def test_update_export_changed_time(self) -> None:
         shutil.rmtree(Path(self.dirs.media_dir) / "documents")
-        install_document_samples(Path(self.dirs.media_dir) / "documents")
+        shutil.copytree(
+            Path(__file__).parent / "samples" / "documents",
+            Path(self.dirs.media_dir) / "documents",
+        )
 
         self._do_export()
         self.assertIsFile(self.target / "manifest.json")
@@ -453,7 +464,10 @@ class TestExportImport(
 
     def test_update_export_changed_checksum(self) -> None:
         shutil.rmtree(Path(self.dirs.media_dir) / "documents")
-        install_document_samples(Path(self.dirs.media_dir) / "documents")
+        shutil.copytree(
+            Path(__file__).parent / "samples" / "documents",
+            Path(self.dirs.media_dir) / "documents",
+        )
 
         self._do_export()
 
@@ -480,7 +494,10 @@ class TestExportImport(
 
     def test_update_export_deleted_document(self) -> None:
         shutil.rmtree(Path(self.dirs.media_dir) / "documents")
-        install_document_samples(Path(self.dirs.media_dir) / "documents")
+        shutil.copytree(
+            Path(__file__).parent / "samples" / "documents",
+            Path(self.dirs.media_dir) / "documents",
+        )
 
         manifest = self._do_export()
 
@@ -512,7 +529,10 @@ class TestExportImport(
     @override_settings(FILENAME_FORMAT="{title}/{correspondent}")
     def test_update_export_changed_location(self) -> None:
         shutil.rmtree(Path(self.dirs.media_dir) / "documents")
-        install_document_samples(Path(self.dirs.media_dir) / "documents")
+        shutil.copytree(
+            Path(__file__).parent / "samples" / "documents",
+            Path(self.dirs.media_dir) / "documents",
+        )
 
         self._do_export(use_filename_format=True)
         self.assertIsFile(self.target / "wow1" / "c.pdf")
@@ -554,7 +574,10 @@ class TestExportImport(
             - Zipfile contains exported files
         """
         shutil.rmtree(Path(self.dirs.media_dir) / "documents")
-        install_document_samples(Path(self.dirs.media_dir) / "documents")
+        shutil.copytree(
+            Path(__file__).parent / "samples" / "documents",
+            Path(self.dirs.media_dir) / "documents",
+        )
 
         args = ["document_exporter", self.target, "--zip"]
 
@@ -583,7 +606,10 @@ class TestExportImport(
             - Zipfile contains exported files
         """
         shutil.rmtree(Path(self.dirs.media_dir) / "documents")
-        install_document_samples(Path(self.dirs.media_dir) / "documents")
+        shutil.copytree(
+            Path(__file__).parent / "samples" / "documents",
+            Path(self.dirs.media_dir) / "documents",
+        )
 
         args = ["document_exporter", self.target, "--zip", "--use-filename-format"]
 
@@ -619,7 +645,10 @@ class TestExportImport(
             - The existing file and directory in target are removed
         """
         shutil.rmtree(Path(self.dirs.media_dir) / "documents")
-        install_document_samples(Path(self.dirs.media_dir) / "documents")
+        shutil.copytree(
+            Path(__file__).parent / "samples" / "documents",
+            Path(self.dirs.media_dir) / "documents",
+        )
 
         # Create stuff in target directory
         existing_file = self.target / "test.txt"
@@ -715,7 +744,10 @@ class TestExportImport(
             - Documents can be imported again
         """
         shutil.rmtree(Path(self.dirs.media_dir) / "documents")
-        install_document_samples(Path(self.dirs.media_dir) / "documents")
+        shutil.copytree(
+            Path(__file__).parent / "samples" / "documents",
+            Path(self.dirs.media_dir) / "documents",
+        )
 
         manifest = self._do_export()
         has_archive = False
@@ -758,7 +790,10 @@ class TestExportImport(
             - Documents can be imported again
         """
         shutil.rmtree(Path(self.dirs.media_dir) / "documents")
-        install_document_samples(Path(self.dirs.media_dir) / "documents")
+        shutil.copytree(
+            Path(__file__).parent / "samples" / "documents",
+            Path(self.dirs.media_dir) / "documents",
+        )
 
         manifest = self._do_export()
         has_thumbnail = False
@@ -803,7 +838,10 @@ class TestExportImport(
             - Documents can be imported again
         """
         shutil.rmtree(Path(self.dirs.media_dir) / "documents")
-        install_document_samples(Path(self.dirs.media_dir) / "documents")
+        shutil.copytree(
+            Path(__file__).parent / "samples" / "documents",
+            Path(self.dirs.media_dir) / "documents",
+        )
 
         manifest = self._do_export(split_manifest=True)
         has_document = False
@@ -828,7 +866,10 @@ class TestExportImport(
 
     def _export_import_barcodes(self, *, split_manifest: bool) -> None:
         shutil.rmtree(Path(self.dirs.media_dir) / "documents")
-        install_document_samples(Path(self.dirs.media_dir) / "documents")
+        shutil.copytree(
+            Path(__file__).parent / "samples" / "documents",
+            Path(self.dirs.media_dir) / "documents",
+        )
         DocumentBarcodeFactory(document=self.d1, value="https://example.com")
         DocumentBarcodeFactory(document=self.d2, page=2, value="DE8937")
 
@@ -864,7 +905,10 @@ class TestExportImport(
             - Documents can be imported again
         """
         shutil.rmtree(Path(self.dirs.media_dir) / "documents")
-        install_document_samples(Path(self.dirs.media_dir) / "documents")
+        shutil.copytree(
+            Path(__file__).parent / "samples" / "documents",
+            Path(self.dirs.media_dir) / "documents",
+        )
 
         self._do_export(use_folder_prefix=True)
 
@@ -891,7 +935,10 @@ class TestExportImport(
             - Documents can be imported again
         """
         shutil.rmtree(Path(self.dirs.media_dir) / "documents")
-        install_document_samples(Path(self.dirs.media_dir) / "documents")
+        shutil.copytree(
+            Path(__file__).parent / "samples" / "documents",
+            Path(self.dirs.media_dir) / "documents",
+        )
 
         self._do_export(use_folder_prefix=True, split_manifest=True)
 
@@ -918,7 +965,10 @@ class TestExportImport(
         """
 
         shutil.rmtree(Path(self.dirs.media_dir) / "documents")
-        install_document_samples(Path(self.dirs.media_dir) / "documents")
+        shutil.copytree(
+            Path(__file__).parent / "samples" / "documents",
+            Path(self.dirs.media_dir) / "documents",
+        )
 
         num_content_type_objects = ContentType.objects.count()
         num_permission_objects = Permission.objects.count()
@@ -955,7 +1005,10 @@ class TestExportImport(
 
     def test_exporter_with_auditlog_disabled(self) -> None:
         shutil.rmtree(Path(self.dirs.media_dir) / "documents")
-        install_document_samples(Path(self.dirs.media_dir) / "documents")
+        shutil.copytree(
+            Path(__file__).parent / "samples" / "documents",
+            Path(self.dirs.media_dir) / "documents",
+        )
 
         with override_settings(
             AUDIT_LOG_ENABLED=False,
@@ -975,7 +1028,10 @@ class TestExportImport(
               survive the round-trip with deleted_at preserved
         """
         shutil.rmtree(Path(self.dirs.media_dir) / "documents")
-        install_document_samples(Path(self.dirs.media_dir) / "documents")
+        shutil.copytree(
+            Path(__file__).parent / "samples" / "documents",
+            Path(self.dirs.media_dir) / "documents",
+        )
 
         # d1 has self.note and self.cfi1 attached via setUp
         self.d1.delete()
@@ -1019,7 +1075,10 @@ class TestExportImport(
         """
 
         shutil.rmtree(self.dirs.media_dir / "documents")
-        install_document_samples(self.dirs.media_dir / "documents")
+        shutil.copytree(
+            self.SAMPLE_DIR / "documents",
+            self.dirs.media_dir / "documents",
+        )
 
         _ = self._do_export(data_only=True)
 

src/documents/tests/test_management_thumbnails.py

@@ -11,7 +11,6 @@ from documents.models import Document
 from documents.parsers import get_default_thumbnail
 from paperless_testing.assertions import FileSystemAssertsMixin
 from paperless_testing.dirs import DirectoriesMixin
-from paperless_testing.samples import SIMPLE_DIGITAL_PDF
 
 
 @pytest.mark.management
@@ -25,7 +24,7 @@ class TestMakeThumbnails(DirectoriesMixin, FileSystemAssertsMixin, TestCase):
             filename="test.pdf",
         )
         shutil.copy(
-            SIMPLE_DIGITAL_PDF,
+            Path(__file__).parent / "samples" / "simple.pdf",
             self.d1.source_path,
         )
 
@@ -37,7 +36,7 @@ class TestMakeThumbnails(DirectoriesMixin, FileSystemAssertsMixin, TestCase):
             filename="test2.pdf",
         )
         shutil.copy(
-            SIMPLE_DIGITAL_PDF,
+            Path(__file__).parent / "samples" / "simple.pdf",
             self.d2.source_path,
         )
 

src/documents/tests/test_tasks.py

@@ -21,7 +21,6 @@ from documents.tests.helpers import dummy_preprocess
 from paperless_testing.assertions import FileSystemAssertsMixin
 from paperless_testing.dirs import DirectoriesMixin
 from paperless_testing.factories import DocumentFactory
-from paperless_testing.samples import SIMPLE_DIGITAL_PDF
 
 
 @pytest.mark.django_db
@@ -230,12 +229,20 @@ class TestUpdateContent(DirectoriesMixin, TestCase):
         """
         sample1 = self.dirs.scratch_dir / "sample.pdf"
         shutil.copy(
-            SIMPLE_DIGITAL_PDF,
+            Path(__file__).parent
+            / "samples"
+            / "documents"
+            / "originals"
+            / "0000001.pdf",
             sample1,
         )
         sample1_archive = self.dirs.archive_dir / "sample_archive.pdf"
         shutil.copy(
-            SIMPLE_DIGITAL_PDF,
+            Path(__file__).parent
+            / "samples"
+            / "documents"
+            / "originals"
+            / "0000001.pdf",
             sample1_archive,
         )
         doc = Document.objects.create(
@@ -263,7 +270,11 @@ class TestUpdateContent(DirectoriesMixin, TestCase):
         """
         sample1 = self.dirs.scratch_dir / "sample.pdf"
         shutil.copy(
-            SIMPLE_DIGITAL_PDF,
+            Path(__file__).parent
+            / "samples"
+            / "documents"
+            / "originals"
+            / "0000001.pdf",
             sample1,
         )
         doc = Document.objects.create(
@@ -279,7 +290,14 @@ class TestUpdateContent(DirectoriesMixin, TestCase):
 
     def _create_root_with_version(self) -> tuple[Document, Document]:
         sample1 = self.dirs.scratch_dir / "sample.pdf"
-        shutil.copy(SIMPLE_DIGITAL_PDF, sample1)
+        shutil.copy(
+            Path(__file__).parent
+            / "samples"
+            / "documents"
+            / "originals"
+            / "0000001.pdf",
+            sample1,
+        )
         root = DocumentFactory(content="root content", mime_type="application/pdf")
         version = DocumentFactory(
             content="my document",

src/documents/tests/test_workflows.py

@@ -178,7 +178,7 @@ class TestWorkflows(
         self.assertEqual(action.__str__(), "WorkflowAction 1")
 
         test_file = shutil.copy(
-            self.SIMPLE_PDF,
+            self.SAMPLE_DIR / "simple.pdf",
             self.dirs.scratch_dir / "simple.pdf",
         )
 
@@ -290,7 +290,7 @@ class TestWorkflows(
         w.save()
 
         test_file = shutil.copy(
-            self.SIMPLE_PDF,
+            self.SAMPLE_DIR / "simple.pdf",
             self.dirs.scratch_dir / "simple.pdf",
         )
 
@@ -409,7 +409,7 @@ class TestWorkflows(
         w2.save()
 
         test_file = shutil.copy(
-            self.SIMPLE_PDF,
+            self.SAMPLE_DIR / "simple.pdf",
             self.dirs.scratch_dir / "simple.pdf",
         )
 
@@ -478,7 +478,7 @@ class TestWorkflows(
         w.save()
 
         test_file = shutil.copy(
-            self.SIMPLE_PDF,
+            self.SAMPLE_DIR / "simple.pdf",
             self.dirs.scratch_dir / "simple.pdf",
         )
 
@@ -531,7 +531,7 @@ class TestWorkflows(
         w.save()
 
         test_file = shutil.copy(
-            self.SIMPLE_PDF,
+            self.SAMPLE_DIR / "simple.pdf",
             self.dirs.scratch_dir / "simple.pdf",
         )
 
@@ -608,7 +608,7 @@ class TestWorkflows(
         w.save()
 
         test_file = shutil.copy(
-            self.SIMPLE_PDF,
+            self.SAMPLE_DIR / "simple.pdf",
             self.dirs.scratch_dir / "simple.pdf",
         )
 
@@ -687,7 +687,7 @@ class TestWorkflows(
         w.save()
 
         test_file = shutil.copy(
-            self.SIMPLE_PDF,
+            self.SAMPLE_DIR / "simple.pdf",
             self.dirs.scratch_dir / "simple.pdf",
         )
 
@@ -765,7 +765,7 @@ class TestWorkflows(
         w.save()
 
         test_file = shutil.copy(
-            self.SIMPLE_PDF,
+            self.SAMPLE_DIR / "simple.pdf",
             self.dirs.scratch_dir / "simple.pdf",
         )
 
@@ -876,7 +876,7 @@ class TestWorkflows(
         w.save()
 
         test_file = shutil.copy(
-            self.SIMPLE_PDF,
+            self.SAMPLE_DIR / "simple.pdf",
             self.dirs.scratch_dir / "simple.pdf",
         )
 
@@ -928,7 +928,7 @@ class TestWorkflows(
         generated = generate_unique_filename(doc)
         destination = (settings.ORIGINALS_DIR / generated).resolve()
         create_source_path_directory(destination)
-        shutil.copy(self.SIMPLE_PDF, destination)
+        shutil.copy(self.SAMPLE_DIR / "simple.pdf", destination)
         Document.objects.filter(pk=doc.pk).update(filename=generated.as_posix())
         doc.refresh_from_db()
 
@@ -2023,7 +2023,7 @@ class TestWorkflows(
         superuser = UserFactory(username="superuser", superuser=True)
         self.client.force_authenticate(user=superuser)
         test_file = shutil.copy(
-            self.SIMPLE_PDF,
+            self.SAMPLE_DIR / "simple.pdf",
             self.dirs.scratch_dir / "simple.pdf",
         )
         tasks.consume_file(
@@ -3009,7 +3009,7 @@ class TestWorkflows(
         generated = generate_unique_filename(doc)
         destination = (settings.ORIGINALS_DIR / generated).resolve()
         create_source_path_directory(destination)
-        shutil.copy(self.SIMPLE_PDF, destination)
+        shutil.copy(self.SAMPLE_DIR / "simple.pdf", destination)
         Document.objects.filter(pk=doc.pk).update(filename=generated.as_posix())
         doc.refresh_from_db()
         doc.tags.set([self.t1, self.t2])
@@ -3073,7 +3073,7 @@ class TestWorkflows(
         generated = generate_unique_filename(doc)
         destination = (settings.ORIGINALS_DIR / generated).resolve()
         create_source_path_directory(destination)
-        shutil.copy(self.SIMPLE_PDF, destination)
+        shutil.copy(self.SAMPLE_DIR / "simple.pdf", destination)
         Document.objects.filter(pk=doc.pk).update(filename=generated.as_posix())
         doc.refresh_from_db()
         doc.tags.set([self.t1])
@@ -3222,7 +3222,7 @@ class TestWorkflows(
         w.save()
 
         test_file = shutil.copy(
-            self.SIMPLE_PDF,
+            self.SAMPLE_DIR / "simple.pdf",
             self.dirs.scratch_dir / "simple.pdf",
         )
 
@@ -3346,7 +3346,7 @@ class TestWorkflows(
         w.save()
 
         test_file = shutil.copy(
-            self.SIMPLE_PDF,
+            self.SAMPLE_DIR / "simple.pdf",
             self.dirs.scratch_dir / "simple.pdf",
         )
 
@@ -3496,7 +3496,7 @@ class TestWorkflows(
         workflow.actions.set([assignment_action, email_action])
 
         temp_working_copy = shutil.copy(
-            self.SIMPLE_PDF,
+            self.SAMPLE_DIR / "simple.pdf",
             self.dirs.scratch_dir / "working-copy.pdf",
         )
 
@@ -3596,7 +3596,7 @@ class TestWorkflows(
 
         # move the file
         test_file = shutil.copy(
-            self.SIMPLE_PDF,
+            self.SAMPLE_DIR / "simple.pdf",
             self.dirs.scratch_dir / "simple.pdf",
         )
 
@@ -3704,7 +3704,7 @@ class TestWorkflows(
         generated = generate_unique_filename(doc)
         destination = (settings.ORIGINALS_DIR / generated).resolve()
         create_source_path_directory(destination)
-        shutil.copy(self.SIMPLE_PDF, destination)
+        shutil.copy(self.SAMPLE_DIR / "simple.pdf", destination)
         Document.objects.filter(pk=doc.pk).update(filename=generated.as_posix())
 
         run_workflows(WorkflowTrigger.WorkflowTriggerType.DOCUMENT_UPDATED, doc)
@@ -3915,7 +3915,7 @@ class TestWorkflows(
         w.save()
 
         test_file = shutil.copy(
-            self.SIMPLE_PDF,
+            self.SAMPLE_DIR / "simple.pdf",
             self.dirs.scratch_dir / "simple.pdf",
         )
 
@@ -4036,7 +4036,7 @@ class TestWorkflows(
         w.save()
 
         test_file = shutil.copy(
-            self.SIMPLE_PDF,
+            self.SAMPLE_DIR / "simple.pdf",
             self.dirs.scratch_dir / "simple.pdf",
         )
 
@@ -4387,7 +4387,7 @@ class TestWorkflows(
         w.save()
 
         test_file = shutil.copy(
-            self.SIMPLE_PDF,
+            self.SAMPLE_DIR / "simple.pdf",
             self.dirs.scratch_dir / "simple.pdf",
         )
 
@@ -4835,7 +4835,7 @@ class TestWorkflows(
         w.save()
 
         test_file = shutil.copy(
-            self.SIMPLE_PDF,
+            self.SAMPLE_DIR / "simple.pdf",
             self.dirs.scratch_dir / "simple.pdf",
         )
 
@@ -5027,7 +5027,7 @@ class TestWorkflows(
 
         # Create a test file to be consumed
         test_file = shutil.copy(
-            self.SIMPLE_PDF,
+            self.SAMPLE_DIR / "simple.pdf",
             self.dirs.scratch_dir / "simple.pdf",
         )
         test_file_path = Path(test_file)
@@ -5091,7 +5091,7 @@ class TestWorkflows(
 
         # Create a test file to be consumed
         test_file = shutil.copy(
-            self.SIMPLE_PDF,
+            self.SAMPLE_DIR / "simple.pdf",
             self.dirs.scratch_dir / "simple2.pdf",
         )
         test_file_path = Path(test_file)
@@ -5529,7 +5529,7 @@ class TestDateWorkflowLocalization(
         )
 
         test_file = shutil.copy(
-            self.SIMPLE_PDF,
+            self.SAMPLE_DIR / "simple.pdf",
             tmp_path / "simple.pdf",
         )
 
@@ -5596,7 +5596,7 @@ class TestRemoteOCRWorkflowAction(DirectoriesMixin, SampleDirMixin, APITestCase)
         self._make_workflow(WorkflowTrigger.WorkflowTriggerType.CONSUMPTION)
 
         test_file = shutil.copy(
-            self.SIMPLE_PDF,
+            self.SAMPLE_DIR / "simple.pdf",
             self.dirs.scratch_dir / "simple.pdf",
         )
         overrides = DocumentMetadataOverrides()
@@ -5814,7 +5814,7 @@ class TestApplyAISuggestionsWorkflowAction(
         )
 
         test_file = shutil.copy(
-            self.SIMPLE_PDF,
+            self.SAMPLE_DIR / "simple.pdf",
             self.dirs.scratch_dir / "simple.pdf",
         )
 

src/documents/tests/utils.py

@@ -11,7 +11,6 @@ from documents.data_models import ConsumableDocument
 from documents.data_models import DocumentMetadataOverrides
 from documents.data_models import DocumentSource
 from paperless_testing.fakes.progress import FakeProgressManager
-from paperless_testing.samples import SIMPLE_DIGITAL_PDF
 
 
 class ConsumeTaskMixin:
@@ -54,8 +53,6 @@ class SampleDirMixin:
 
     BARCODE_SAMPLE_DIR = SAMPLE_DIR / "barcodes"
 
-    SIMPLE_PDF = SIMPLE_DIGITAL_PDF
-
 
 class GetConsumerMixin:
     @contextmanager

src/documents/views.py

@@ -1304,13 +1304,19 @@ class DocumentViewSet(
 
         from documents.search import get_backend
 
-        get_backend().add_or_update(refreshed_doc)
-
         document_updated.send(
             sender=self.__class__,
             document=refreshed_doc,
         )
 
+        # Index the final workflow state, including deletion.
+        backend = get_backend()
+        final_doc = Document.objects.filter(pk=root_doc.pk).first()
+        if final_doc is None:
+            backend.remove(root_doc.pk)
+        else:
+            backend.add_or_update(final_doc)
+
         return response
 
     def list(self, request, *args, **kwargs):

src/paperless/tests/parsers/conftest.py

@@ -432,6 +432,30 @@ def tesseract_samples_dir(parser_samples_dir: Path) -> Path:
     return parser_samples_dir / "tesseract"
 
 
+@pytest.fixture(scope="session")
+def multi_page_images_pdf_file(tesseract_samples_dir: Path) -> Path:
+    """Path to a multi-page PDF with images.
+
+    Returns
+    -------
+    Path
+        Absolute path to ``tesseract/multi-page-images.pdf``.
+    """
+    return tesseract_samples_dir / "multi-page-images.pdf"
+
+
+@pytest.fixture(scope="session")
+def simple_digital_pdf_file(tesseract_samples_dir: Path) -> Path:
+    """Path to a simple digital PDF sample file.
+
+    Returns
+    -------
+    Path
+        Absolute path to ``tesseract/simple-digital.pdf``.
+    """
+    return tesseract_samples_dir / "simple-digital.pdf"
+
+
 @pytest.fixture(scope="session")
 def simple_no_dpi_png_file(tesseract_samples_dir: Path) -> Path:
     """Path to a simple PNG without DPI information.
@@ -456,18 +480,6 @@ def simple_png_file(tesseract_samples_dir: Path) -> Path:
     return tesseract_samples_dir / "simple.png"
 
 
-@pytest.fixture(scope="session")
-def rotated_pdf_file(tesseract_samples_dir: Path) -> Path:
-    """Path to a landscape (rotated) PDF sample file.
-
-    Returns
-    -------
-    Path
-        Absolute path to ``tesseract/rotated.pdf``.
-    """
-    return tesseract_samples_dir / "rotated.pdf"
-
-
 # ------------------------------------------------------------------
 # Tesseract parser instance and settings helpers
 # ------------------------------------------------------------------

src/paperless/tests/parsers/test_tesseract_parser.py

@@ -161,11 +161,11 @@ class TestGetPageCount:
     def test_single_page_pdf(
         self,
         tesseract_parser: RasterisedDocumentParser,
-        simple_digital_pdf_file: Path,
+        tesseract_samples_dir: Path,
     ) -> None:
         assert (
             tesseract_parser.get_page_count(
-                simple_digital_pdf_file,
+                tesseract_samples_dir / "simple-digital.pdf",
                 "application/pdf",
             )
             == 1
@@ -188,7 +188,7 @@ class TestGetPageCount:
         self,
         mocker: MockerFixture,
         tesseract_parser: RasterisedDocumentParser,
-        simple_digital_pdf_file: Path,
+        tesseract_samples_dir: Path,
         caplog,
     ) -> None:
         """
@@ -204,7 +204,7 @@ class TestGetPageCount:
 
         with caplog.at_level(logging.WARNING):
             page_count = tesseract_parser.get_page_count(
-                simple_digital_pdf_file,
+                tesseract_samples_dir / "simple-digital.pdf",
                 "application/pdf",
             )
         assert page_count is None
@@ -273,26 +273,26 @@ class TestGetThumbnail:
     def test_thumbnail_is_file(
         self,
         tesseract_parser: RasterisedDocumentParser,
-        simple_digital_pdf_file: Path,
+        tesseract_samples_dir: Path,
     ) -> None:
         thumb = tesseract_parser.get_thumbnail(
-            simple_digital_pdf_file,
+            tesseract_samples_dir / "simple-digital.pdf",
             "application/pdf",
         )
         assert thumb.is_file()
 
     @pytest.mark.parametrize(
-        ("sample_fixture", "expected_height"),
+        ("filename", "expected_height"),
         [
-            pytest.param("simple_digital_pdf_file", 647, id="portrait-letter"),
-            pytest.param("rotated_pdf_file", 386, id="landscape"),
+            pytest.param("simple-digital.pdf", 647, id="portrait-letter"),
+            pytest.param("rotated.pdf", 386, id="landscape"),
         ],
     )
     def test_thumbnail_is_correct_format_and_size(
         self,
         tesseract_parser: RasterisedDocumentParser,
-        request: pytest.FixtureRequest,
-        sample_fixture: str,
+        tesseract_samples_dir: Path,
+        filename: str,
         expected_height: int,
     ) -> None:
         """
@@ -304,7 +304,7 @@ class TestGetThumbnail:
             - A 500px wide WebP keeping the page's aspect ratio
         """
         thumb = tesseract_parser.get_thumbnail(
-            request.getfixturevalue(sample_fixture),
+            tesseract_samples_dir / filename,
             "application/pdf",
         )
         with Image.open(thumb) as im:
@@ -316,7 +316,7 @@ class TestGetThumbnail:
         self,
         mocker: MockerFixture,
         tesseract_parser: RasterisedDocumentParser,
-        simple_digital_pdf_file: Path,
+        tesseract_samples_dir: Path,
     ) -> None:
         """
         GIVEN:
@@ -326,7 +326,7 @@ class TestGetThumbnail:
         THEN:
             - The PDF is repaired with qpdf and a real thumbnail is rendered
         """
-        original = simple_digital_pdf_file
+        original = tesseract_samples_dir / "simple-digital.pdf"
 
         def _fail_on_original(in_path: Path, out_path: Path, **kwargs) -> None:
             if in_path == original:
@@ -368,11 +368,11 @@ class TestExtractText:
     def test_extract_text_from_digital_pdf(
         self,
         tesseract_parser: RasterisedDocumentParser,
-        simple_digital_pdf_file: Path,
+        tesseract_samples_dir: Path,
     ) -> None:
         text = tesseract_parser.extract_text(
             None,
-            simple_digital_pdf_file,
+            tesseract_samples_dir / "simple-digital.pdf",
         )
         assert text is not None
         assert "This is a test document." in text.strip()
@@ -387,7 +387,7 @@ class TestParsePdf:
     def test_simple_digital_creates_archive(
         self,
         tesseract_parser: RasterisedDocumentParser,
-        multi_page_digital_pdf_file: Path,
+        tesseract_samples_dir: Path,
     ) -> None:
         """
         GIVEN:
@@ -401,7 +401,7 @@ class TestParsePdf:
             - Text is extracted
         """
         tesseract_parser.parse(
-            multi_page_digital_pdf_file,
+            tesseract_samples_dir / "multi-page-digital.pdf",
             "application/pdf",
         )
         assert tesseract_parser.archive_path is not None
@@ -416,10 +416,10 @@ class TestParsePdf:
     def test_with_form_default(
         self,
         tesseract_parser: RasterisedDocumentParser,
-        with_form_pdf_file: Path,
+        tesseract_samples_dir: Path,
     ) -> None:
         tesseract_parser.parse(
-            with_form_pdf_file,
+            tesseract_samples_dir / "with-form.pdf",
             "application/pdf",
         )
         assert tesseract_parser.archive_path is not None
@@ -432,11 +432,11 @@ class TestParsePdf:
     def test_with_form_redo_no_archive_when_not_requested(
         self,
         tesseract_parser: RasterisedDocumentParser,
-        with_form_pdf_file: Path,
+        tesseract_samples_dir: Path,
     ) -> None:
         tesseract_parser.settings.mode = ModeChoices.REDO
         tesseract_parser.parse(
-            with_form_pdf_file,
+            tesseract_samples_dir / "with-form.pdf",
             "application/pdf",
             produce_archive=False,
         )
@@ -449,11 +449,11 @@ class TestParsePdf:
     def test_with_form_force(
         self,
         tesseract_parser: RasterisedDocumentParser,
-        with_form_pdf_file: Path,
+        tesseract_samples_dir: Path,
     ) -> None:
         tesseract_parser.settings.mode = ModeChoices.FORCE
         tesseract_parser.parse(
-            with_form_pdf_file,
+            tesseract_samples_dir / "with-form.pdf",
             "application/pdf",
         )
         assert_ordered_substrings(
@@ -494,7 +494,7 @@ class TestParsePdf:
         self,
         mocker: MockerFixture,
         tesseract_parser: RasterisedDocumentParser,
-        simple_digital_pdf_file: Path,
+        tesseract_samples_dir: Path,
     ) -> None:
         mocker.patch(
             "ocrmypdf.ocr",
@@ -502,7 +502,7 @@ class TestParsePdf:
         )
         with pytest.raises(ParseError):
             tesseract_parser.parse(
-                simple_digital_pdf_file,
+                tesseract_samples_dir / "simple-digital.pdf",
                 "application/pdf",
             )
 
@@ -578,10 +578,10 @@ class TestParseMultiPage:
     def test_multi_page_digital(
         self,
         tesseract_parser: RasterisedDocumentParser,
-        multi_page_digital_pdf_file: Path,
+        tesseract_samples_dir: Path,
     ) -> None:
         tesseract_parser.parse(
-            multi_page_digital_pdf_file,
+            tesseract_samples_dir / "multi-page-digital.pdf",
             "application/pdf",
         )
         assert tesseract_parser.archive_path is not None
@@ -605,12 +605,12 @@ class TestParseMultiPage:
         self,
         mode: str,
         tesseract_parser: RasterisedDocumentParser,
-        multi_page_digital_pdf_file: Path,
+        tesseract_samples_dir: Path,
     ) -> None:
         tesseract_parser.settings.pages = 2
         tesseract_parser.settings.mode = mode
         tesseract_parser.parse(
-            multi_page_digital_pdf_file,
+            tesseract_samples_dir / "multi-page-digital.pdf",
             "application/pdf",
         )
         assert tesseract_parser.archive_path is not None
@@ -624,11 +624,11 @@ class TestParseMultiPage:
     def test_multi_page_images_skip(
         self,
         tesseract_parser: RasterisedDocumentParser,
-        multi_page_images_pdf_file: Path,
+        tesseract_samples_dir: Path,
     ) -> None:
         tesseract_parser.settings.mode = ModeChoices.AUTO
         tesseract_parser.parse(
-            multi_page_images_pdf_file,
+            tesseract_samples_dir / "multi-page-images.pdf",
             "application/pdf",
         )
         assert tesseract_parser.archive_path is not None
@@ -642,7 +642,7 @@ class TestParseMultiPage:
     def test_multi_page_images_redo_pages_2(
         self,
         tesseract_parser: RasterisedDocumentParser,
-        multi_page_images_pdf_file: Path,
+        tesseract_samples_dir: Path,
     ) -> None:
         """
         GIVEN:
@@ -657,7 +657,7 @@ class TestParseMultiPage:
         tesseract_parser.settings.pages = 2
         tesseract_parser.settings.mode = ModeChoices.REDO
         tesseract_parser.parse(
-            multi_page_images_pdf_file,
+            tesseract_samples_dir / "multi-page-images.pdf",
             "application/pdf",
         )
         assert tesseract_parser.archive_path is not None
@@ -670,7 +670,7 @@ class TestParseMultiPage:
     def test_multi_page_images_force_page_1(
         self,
         tesseract_parser: RasterisedDocumentParser,
-        multi_page_images_pdf_file: Path,
+        tesseract_samples_dir: Path,
     ) -> None:
         """
         GIVEN:
@@ -685,7 +685,7 @@ class TestParseMultiPage:
         tesseract_parser.settings.pages = 1
         tesseract_parser.settings.mode = ModeChoices.FORCE
         tesseract_parser.parse(
-            multi_page_images_pdf_file,
+            tesseract_samples_dir / "multi-page-images.pdf",
             "application/pdf",
         )
         assert tesseract_parser.archive_path is not None
@@ -781,7 +781,7 @@ class TestSkipArchive:
     def test_skip_noarchive_with_text_layer(
         self,
         tesseract_parser: RasterisedDocumentParser,
-        multi_page_digital_pdf_file: Path,
+        tesseract_samples_dir: Path,
     ) -> None:
         """
         GIVEN:
@@ -795,7 +795,7 @@ class TestSkipArchive:
         """
         tesseract_parser.settings.mode = ModeChoices.AUTO
         tesseract_parser.parse(
-            multi_page_digital_pdf_file,
+            tesseract_samples_dir / "multi-page-digital.pdf",
             "application/pdf",
             produce_archive=False,
         )
@@ -810,7 +810,7 @@ class TestSkipArchive:
     def test_skip_noarchive_image_only_creates_archive(
         self,
         tesseract_parser: RasterisedDocumentParser,
-        multi_page_images_pdf_file: Path,
+        tesseract_samples_dir: Path,
     ) -> None:
         """
         GIVEN:
@@ -823,7 +823,7 @@ class TestSkipArchive:
         """
         tesseract_parser.settings.mode = ModeChoices.AUTO
         tesseract_parser.parse(
-            multi_page_images_pdf_file,
+            tesseract_samples_dir / "multi-page-images.pdf",
             "application/pdf",
         )
         assert tesseract_parser.archive_path is not None
@@ -835,29 +835,29 @@ class TestSkipArchive:
         )
 
     @pytest.mark.parametrize(
-        ("produce_archive", "sample_fixture", "expect_archive"),
+        ("produce_archive", "filename", "expect_archive"),
         [
             pytest.param(
                 True,
-                "multi_page_digital_pdf_file",
+                "multi-page-digital.pdf",
                 True,
                 id="produce-archive-with-text",
             ),
             pytest.param(
                 True,
-                "multi_page_images_pdf_file",
+                "multi-page-images.pdf",
                 True,
                 id="produce-archive-no-text",
             ),
             pytest.param(
                 False,
-                "multi_page_digital_pdf_file",
+                "multi-page-digital.pdf",
                 False,
                 id="no-archive-with-text-layer",
             ),
             pytest.param(
                 False,
-                "multi_page_images_pdf_file",
+                "multi-page-images.pdf",
                 False,
                 id="no-archive-no-text-layer",
             ),
@@ -866,10 +866,10 @@ class TestSkipArchive:
     def test_produce_archive_flag(
         self,
         produce_archive: bool,  # noqa: FBT001
-        sample_fixture: str,
+        filename: str,
         expect_archive: bool,  # noqa: FBT001
         tesseract_parser: RasterisedDocumentParser,
-        request: pytest.FixtureRequest,
+        tesseract_samples_dir: Path,
     ) -> None:
         """
         GIVEN:
@@ -882,9 +882,8 @@ class TestSkipArchive:
             - Text is always extracted
         """
         tesseract_parser.settings.mode = ModeChoices.AUTO
-        sample = request.getfixturevalue(sample_fixture)
         tesseract_parser.parse(
-            sample,
+            tesseract_samples_dir / filename,
             "application/pdf",
             produce_archive=produce_archive,
         )
@@ -901,7 +900,7 @@ class TestSkipArchive:
         self,
         mocker: MockerFixture,
         tesseract_parser: RasterisedDocumentParser,
-        simple_digital_pdf_file: Path,
+        tesseract_samples_dir: Path,
     ) -> None:
         """
         GIVEN:
@@ -917,7 +916,7 @@ class TestSkipArchive:
         tesseract_parser.settings.mode = ModeChoices.AUTO
         mock_ocr = mocker.patch("ocrmypdf.ocr")
         tesseract_parser.parse(
-            simple_digital_pdf_file,
+            tesseract_samples_dir / "simple-digital.pdf",
             "application/pdf",
             produce_archive=False,
         )
@@ -956,7 +955,7 @@ class TestSkipArchive:
     def test_tagged_pdf_produces_pdfa_archive_without_ocr(
         self,
         tesseract_parser: RasterisedDocumentParser,
-        simple_digital_pdf_file: Path,
+        tesseract_samples_dir: Path,
     ) -> None:
         """
         GIVEN:
@@ -971,7 +970,7 @@ class TestSkipArchive:
         """
         tesseract_parser.settings.mode = ModeChoices.AUTO
         tesseract_parser.parse(
-            simple_digital_pdf_file,
+            tesseract_samples_dir / "simple-digital.pdf",
             "application/pdf",
             produce_archive=True,
         )

src/paperless/tests/samples/mail/sample.html

@@ -0,0 +1,19 @@
+ <html>
+    <head>
+      <meta http-equiv="content-type" content="text/html; charset=UTF-8">
+    </head>
+    <body>
+      <p>Some Text</p>
+      <p>
+				<img src="cid:part1.pNdUSz0s.D3NqVtPg@example.de" alt="Has to be rewritten to work..">
+				<img src="http://localhost:8080/assets/logo_full_white.svg" alt="This image should not be shown.">
+			</p>
+
+      <p>and an embedded image.<br>
+      </p>
+      <p id="changeme">Paragraph unchanged.</p>
+      <scRipt>
+          document.getElementById("changeme").innerHTML = "Paragraph changed via Java Script.";
+      </script>
+    </body>
+  </html>

src/paperless/tests/test_parser_utils.py

@@ -18,6 +18,8 @@ from paperless.parsers.utils import read_file_handle_unicode_errors
 if TYPE_CHECKING:
     from pytest_mock import MockerFixture
 
+SAMPLES = Path(__file__).parent / "samples" / "tesseract"
+
 
 class TestReadFileHandleUnicodeErrors:
     def test_plain_utf8(self, tmp_path: Path) -> None:
@@ -55,11 +57,11 @@ class TestReadFileHandleUnicodeErrors:
 
 
 class TestIsTaggedPdf:
-    def test_tagged_pdf_returns_true(self, simple_digital_pdf_file: Path) -> None:
-        assert is_tagged_pdf(simple_digital_pdf_file) is True
+    def test_tagged_pdf_returns_true(self) -> None:
+        assert is_tagged_pdf(SAMPLES / "simple-digital.pdf") is True
 
-    def test_untagged_pdf_returns_false(self, multi_page_images_pdf_file: Path) -> None:
-        assert is_tagged_pdf(multi_page_images_pdf_file) is False
+    def test_untagged_pdf_returns_false(self) -> None:
+        assert is_tagged_pdf(SAMPLES / "multi-page-images.pdf") is False
 
     def test_nonexistent_path_returns_false(self) -> None:
         assert is_tagged_pdf(Path("/nonexistent/file.pdf")) is False
@@ -93,7 +95,7 @@ class TestGetPdfFirstPageSizePoints:
         pdf.save(path)
         return path
 
-    def test_letter_sample(self, simple_digital_pdf_file: Path) -> None:
+    def test_letter_sample(self) -> None:
         """
         GIVEN:
             - A US Letter sample PDF with no CropBox and no rotation
@@ -102,7 +104,7 @@ class TestGetPdfFirstPageSizePoints:
         THEN:
             - The MediaBox size in points is returned
         """
-        assert get_pdf_first_page_size_points(simple_digital_pdf_file) == (
+        assert get_pdf_first_page_size_points(SAMPLES / "simple-digital.pdf") == (
             612.0,
             792.0,
         )
@@ -197,7 +199,6 @@ class TestGetPdfFirstPageSizePoints:
     def test_pdfinfo_not_installed_returns_none(
         self,
         mocker: MockerFixture,
-        simple_digital_pdf_file: Path,
     ) -> None:
         """
         GIVEN:
@@ -208,7 +209,7 @@ class TestGetPdfFirstPageSizePoints:
             - None is returned and nothing is raised
         """
         mocker.patch("subprocess.run", side_effect=FileNotFoundError("pdfinfo"))
-        assert get_pdf_first_page_size_points(simple_digital_pdf_file) is None
+        assert get_pdf_first_page_size_points(SAMPLES / "simple-digital.pdf") is None
 
     def test_degenerate_box_returns_none(self, tmp_path: Path) -> None:
         """
@@ -250,7 +251,7 @@ class TestGetPdfFirstPageSizePoints:
         bad.write_bytes(b"not a pdf")
         assert get_pdf_first_page_size_points(bad) is None
 
-    def test_encrypted_pdf_returns_none(self, parser_samples_dir: Path) -> None:
+    def test_encrypted_pdf_returns_none(self) -> None:
         """
         GIVEN:
             - A password protected PDF
@@ -259,8 +260,7 @@ class TestGetPdfFirstPageSizePoints:
         THEN:
             - None is returned and nothing is raised
         """
-        encrypted = parser_samples_dir / "tesseract" / "encrypted.pdf"
-        assert get_pdf_first_page_size_points(encrypted) is None
+        assert get_pdf_first_page_size_points(SAMPLES / "encrypted.pdf") is None
 
 
 class TestPostProcessText:

src/paperless_testing/samples.py

@@ -1,48 +0,0 @@
-"""Test sample files shared across tests.
-
-A sample used by a single app stays in that app's ``tests/samples`` tree.
-Samples needed by more than one app, or stored under more than one name, live
-here exactly once.
-"""
-
-import shutil
-from pathlib import Path
-
-SHARED_SAMPLES_DIR = (Path(__file__).parent / "sample_files").resolve()
-
-SIMPLE_DIGITAL_PDF = SHARED_SAMPLES_DIR / "simple-digital.pdf"
-MULTI_PAGE_DIGITAL_PDF = SHARED_SAMPLES_DIR / "multi-page-digital.pdf"
-WITH_FORM_PDF = SHARED_SAMPLES_DIR / "with-form.pdf"
-MULTI_PAGE_IMAGES_PDF = SHARED_SAMPLES_DIR / "multi-page-images.pdf"
-THUMBNAIL_WEBP = SHARED_SAMPLES_DIR / "thumbnail.webp"
-
-# The fake media tree under documents/tests/samples/documents keeps only the
-# files unique to it. The files that duplicate a shared sample are laid back
-# down under their historical opaque names (DB rows and exporter manifests
-# refer to them) by install_document_samples().
-_DOCUMENT_SAMPLES_DIR = (
-    Path(__file__).parent.parent / "documents" / "tests" / "samples" / "documents"
-).resolve()
-
-_SHARED_AS_MEDIA = (
-    ("originals/0000001.pdf", SIMPLE_DIGITAL_PDF),
-    ("originals/0000002.pdf", MULTI_PAGE_DIGITAL_PDF),
-    ("originals/0000003.pdf", WITH_FORM_PDF),
-    ("archive/0000001.pdf", MULTI_PAGE_IMAGES_PDF),
-    ("thumbnails/0000001.webp", THUMBNAIL_WEBP),
-    ("thumbnails/0000002.webp", THUMBNAIL_WEBP),
-    ("thumbnails/0000003.webp", THUMBNAIL_WEBP),
-    ("thumbnails/0000004.webp", THUMBNAIL_WEBP),
-)
-
-
-def install_document_samples(dest: Path) -> None:
-    """Populate ``dest`` with the full fake media tree.
-
-    Replaces ``shutil.copytree(<samples>/documents, dest)`` in tests.
-    """
-    shutil.copytree(_DOCUMENT_SAMPLES_DIR, dest, dirs_exist_ok=True)
-    for relpath, source in _SHARED_AS_MEDIA:
-        target = dest / relpath
-        target.parent.mkdir(parents=True, exist_ok=True)
-        shutil.copy2(source, target)