Drop the custom replace, let marked escape it

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/jest.config.js

@@ -26,7 +26,7 @@ module.exports = {
     'abstract-paperless-service',
   ],
   transformIgnorePatterns: [
-    'node_modules/(?!.*(\\.mjs$|tslib|lodash-es|normalize-diacritics|@angular/common/locales/.*\\.js$))',
+    'node_modules/(?!.*(\\.mjs$|tslib|lodash-es|normalize-diacritics|marked|@angular/common/locales/.*\\.js$))',
   ],
   moduleNameMapper: {
     ...esmPreset.moduleNameMapper,

src-ui/package.json

@@ -30,6 +30,7 @@
     "bootstrap": "^5.3.8",
     "file-saver": "^2.0.5",
     "lodash-es": "^4.18.1",
+    "marked": "~18.0.14",
     "mime-names": "^1.0.0",
     "ngx-bootstrap-icons": "^1.9.3",
     "ngx-color": "^10.1.0",

src-ui/pnpm-lock.yaml

@@ -53,6 +53,9 @@ importers:
       lodash-es:
         specifier: ^4.18.1
         version: 4.18.1
+      marked:
+        specifier: ~18.0.14
+        version: 18.0.14
       mime-names:
         specifier: ^1.0.0
         version: 1.0.0
@@ -3226,6 +3229,11 @@ packages:
   make-error@1.3.6:
     resolution: {integrity: sha512-s8UhlNe7vPKomQhC1qFelMokr/Sc3AgNbso3n74mVPA5LTZwkB9NlXf4XPamLxJE8h0gh73rM94xvwRT2CVInw==}
 
+  marked@18.0.14:
+    resolution: {integrity: sha512-mBHK6FBHuBAlhgRe88w9F0O1AbwwXJUcQibUbC/QcdTbVGAD7aWza+xt3N6oT/jCZx3/OMeS+8rnuiHZcQ9s7A==}
+    engines: {node: '>= 20'}
+    hasBin: true
+
   material-colors@1.2.6:
     resolution: {integrity: sha512-6qE4B9deFBIa9YSpOc9O0Sgc43zTeVYbgDT5veRKSlB2+ZuHNoVVxA1L/ckMUayV9Ay9y7Z/SZCLcGteW9i7bg==}
 
@@ -7409,6 +7417,8 @@ snapshots:
 
   make-error@1.3.6: {}
 
+  marked@18.0.14: {}
+
   material-colors@1.2.6: {}
 
   merge-stream@2.0.0: {}

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

@@ -5,14 +5,16 @@
   </button>
   <div ngbDropdownMenu class="dropdown-menu-end shadow p-3" aria-labelledby="chatDropdown">
     <div class="chat-container bg-light p-2">
-      <div class="chat-messages font-monospace small">
+      <div class="chat-messages small">
         @for (message of messages(); track message) {
           <div class="message d-flex flex-row small" [class.justify-content-end]="message.role === 'user'">
             <div class="p-2 m-2" [class.bg-body]="message.role === 'user'">
-              <span class="text-break">
-                {{ message.content }}
+              @if (message.role === 'assistant') {
+                <div class="chat-markdown text-break text-wrap" [innerHTML]="message.content | markdown"></div>
                 @if (message.isStreaming) { <span class="blinking-cursor">|</span> }
-              </span>
+              } @else {
+                <span class="text-break">{{ message.content }}</span>
+              }
               @if (message.role === 'assistant' && message.references?.length) {
                 <div class="chat-references list-group mt-3">
                   @for (reference of message.references; track reference.id) {

src-ui/src/app/components/chat/chat/chat.component.scss

@@ -8,10 +8,6 @@
   white-space: pre-wrap;
 }
 
-.chat-references {
-  font-family: var(--bs-font-sans-serif);
-}
-
 .dropdown-toggle::after {
   display: none;
 }
@@ -40,3 +36,19 @@
     opacity: 1;
   }
 }
+
+.chat-markdown ::ng-deep {
+  h1, h2, h3, h4, h5, h6 {
+    font-size: 1em;
+    font-weight: bold;
+  }
+
+  th, td {
+    padding: 0.15rem 0.4rem;
+    border: 1px solid var(--bs-border-color);
+  }
+
+  > :last-child {
+    margin-bottom: 0;
+  }
+}

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

@@ -207,4 +207,33 @@ describe('ChatComponent', () => {
     component.searchInputKeyDown(event)
     expect(component.sendMessage).not.toHaveBeenCalled()
   })
+
+  it('should render markdown for assistant messages only', () => {
+    component.messages.set([
+      { role: 'user', content: '**user**' },
+      { role: 'assistant', content: '**assistant** <script>x</script>' },
+    ])
+    fixture.detectChanges()
+    const el: HTMLElement = fixture.nativeElement
+    expect(el.querySelector('.chat-markdown strong')?.textContent).toBe(
+      'assistant'
+    )
+    expect(el.querySelector('.chat-markdown script')).toBeNull()
+    expect(el.textContent).toContain('**user**')
+  })
+
+  it('should keep the destination hostname visible after sanitizing chat links', () => {
+    component.messages.set([
+      {
+        role: 'assistant',
+        content:
+          '[View original document](https://otherdomain.example/?data=secret)',
+      },
+    ])
+    fixture.detectChanges()
+    const el: HTMLElement = fixture.nativeElement
+    const link = el.querySelector('.chat-markdown a')
+    expect(link?.textContent).toBe('View original document')
+    expect(link?.nextElementSibling?.textContent).toBe('(otherdomain.example)')
+  })
 })

src-ui/src/app/components/chat/chat/chat.component.ts

@@ -10,6 +10,7 @@ import { FormsModule, ReactiveFormsModule } from '@angular/forms'
 import { NavigationEnd, Router, RouterModule } from '@angular/router'
 import { NgbDropdownModule } from '@ng-bootstrap/ng-bootstrap'
 import { NgxBootstrapIconsModule } from 'ngx-bootstrap-icons'
+import { MarkdownPipe } from 'src/app/pipes/markdown.pipe'
 import { filter, map } from 'rxjs'
 import {
   ChatMessage,
@@ -25,6 +26,7 @@ import {
     RouterModule,
     NgxBootstrapIconsModule,
     NgbDropdownModule,
+    MarkdownPipe,
   ],
   templateUrl: './chat.component.html',
   styleUrl: './chat.component.scss',

src-ui/src/app/pipes/markdown.pipe.spec.ts

@@ -0,0 +1,90 @@
+import { MarkdownPipe } from './markdown.pipe'
+
+describe('MarkdownPipe', () => {
+  const pipe = new MarkdownPipe()
+
+  it('should return empty string for empty input', () => {
+    expect(pipe.transform(null)).toEqual('')
+    expect(pipe.transform(undefined)).toEqual('')
+    expect(pipe.transform('')).toEqual('')
+  })
+
+  it('should render basic markdown', () => {
+    const html = pipe.transform(
+      '**bold** _em_ `code`\n\n- one\n- two\n\n| a | b |\n|---|---|\n| 1 | 2 |'
+    )
+    expect(html).toContain('<strong>bold</strong>')
+    expect(html).toContain('<em>em</em>')
+    expect(html).toContain('<code>code</code>')
+    expect(html).toContain('<li>one</li>')
+    expect(html).toContain('<table>')
+  })
+
+  it('should escape raw html', () => {
+    const html = pipe.transform(
+      'hi <img src=x onerror="alert(1)"> <b>x</b>\n\n<script>alert(1)</script>'
+    )
+    expect(html).not.toContain('<img')
+    expect(html).not.toContain('<script')
+    expect(html).not.toContain('<b>')
+    expect(html).toContain('&lt;script&gt;')
+  })
+
+  it('should not render images', () => {
+    const html = pipe.transform(
+      '![secret](https://otherdomain.example/x.png?d=1)'
+    )
+    expect(html).not.toContain('<img')
+    expect(html).not.toContain('otherdomain.example')
+    expect(html).toContain('secret')
+  })
+
+  it('should render safe links with target and rel', () => {
+    const html = pipe.transform('[docs](https://docs.paperless-ngx.com "Docs")')
+    expect(html).toContain(
+      '<a target="_blank" rel="noopener noreferrer nofollow" href="https://docs.paperless-ngx.com" title="Docs">docs</a>'
+    )
+    expect(pipe.transform('[mail](mailto:a@b.c)')).toContain(
+      'href="mailto:a@b.c"'
+    )
+  })
+
+  it('should drop unsafe or relative links but keep their text', () => {
+    for (const href of [
+      'javascript:alert(1)',
+      'JaVaScRiPt:alert(1)',
+      'data:text/html,<script>alert(1)</script>',
+      'vbscript:msgbox',
+      '/api/documents/',
+    ]) {
+      const html = pipe.transform(`[click](${href})`)
+      expect(html).not.toContain('<a')
+      expect(html).toContain('click')
+    }
+  })
+
+  it('should show the actual hostname beside web links with misleading labels', () => {
+    for (const protocol of ['http', 'https']) {
+      const html = pipe.transform(
+        `[docs.paperless-ngx.com](${protocol}://docs.paperless-ngx.com@otherdomain.example/path?secret=1)`
+      )
+      expect(html).toContain(
+        '</a> <span class="text-muted small">(otherdomain.example)</span>'
+      )
+      expect(html).not.toContain('(docs.paperless-ngx.com)')
+    }
+  })
+
+  it('should omit the hostname label for mailto links', () => {
+    expect(pipe.transform('[mail](mailto:a@b.c)')).toBe(
+      '<p><a target="_blank" rel="noopener noreferrer nofollow" href="mailto:a@b.c">mail</a></p>\n'
+    )
+  })
+
+  it('should escape link titles', () => {
+    const html = pipe.transform(
+      '[x](https://a.example "a\\" onmouseover=\\"1")'
+    )
+    expect(html).not.toMatch(/"\s*onmouseover=/)
+  })
+})

src-ui/src/app/pipes/markdown.pipe.ts

@@ -0,0 +1,52 @@
+import { Pipe, PipeTransform } from '@angular/core'
+import { Marked, Renderer, Tokens } from 'marked'
+
+const ALLOWED_LINK_PROTOCOLS = new Set(['http:', 'https:', 'mailto:'])
+
+function allowedUrl(href: string): URL | null {
+  try {
+    const url = new URL(href)
+    return ALLOWED_LINK_PROTOCOLS.has(url.protocol) ? url : null
+  } catch {
+    return null
+  }
+}
+
+// Treat chat content as untrusted: no raw HTML, no images, and only
+// absolute links. All escaping is done by marked's default renderer, and
+// Angular's sanitizer runs on top of this as well.
+const renderer: Partial<Renderer> = {
+  html(this: Renderer, { raw, text }: Tokens.HTML | Tokens.Tag): string {
+    return this.text({ type: 'text', raw, text })
+  },
+  image(this: Renderer, { raw, text }: Tokens.Image): string {
+    return this.text({ type: 'text', raw, text })
+  },
+  link(this: Renderer, token: Tokens.Link): string {
+    const url = allowedUrl(token.href)
+    if (!url) return this.parser.parseInline(token.tokens)
+    const anchor = Renderer.prototype.link
+      .call(this, token)
+      .replace('<a ', '<a target="_blank" rel="noopener noreferrer nofollow" ')
+    if (!url.hostname) return anchor
+    const hostname = this.text({ type: 'text', raw: '', text: url.hostname })
+    return `${anchor} <span class="text-muted small">(${hostname})</span>`
+  },
+}
+
+const markdown = new Marked({
+  async: false,
+  gfm: true,
+  breaks: true,
+  renderer,
+})
+
+@Pipe({
+  name: 'markdown',
+})
+export class MarkdownPipe implements PipeTransform {
+  transform(value: string | null | undefined): string {
+    if (!value) return ''
+    return markdown.parse(value) as string
+  }
+}

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

@@ -56,8 +56,6 @@ 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):
@@ -1854,11 +1852,7 @@ 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 +1880,7 @@ 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 +1909,7 @@ 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 +1985,7 @@ 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 +1998,7 @@ 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 +2031,7 @@ 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 +2057,7 @@ 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 +2077,7 @@ 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 +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/",
                 {"document": f, "correspondent": 3456},
@@ -2121,7 +2111,7 @@ 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 +2130,7 @@ 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 +2145,7 @@ 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 +2164,7 @@ 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 +2180,7 @@ 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 +2201,7 @@ 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 +2225,7 @@ 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 +2241,7 @@ 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 +2268,7 @@ 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 +2323,7 @@ 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 +2364,7 @@ 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 +2413,7 @@ 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 +2471,7 @@ 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 +2510,14 @@ 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 +2550,7 @@ 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)
@@ -4304,8 +4288,8 @@ 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

@@ -167,7 +167,7 @@ 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()
@@ -459,7 +459,7 @@ 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

@@ -27,9 +27,6 @@ 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):
@@ -707,27 +704,47 @@ 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(
@@ -761,7 +778,11 @@ 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

@@ -36,9 +36,6 @@ from paperless_testing.assertions import FileSystemAssertsMixin
 from paperless_testing.dirs import DirectoriesMixin
 from paperless_testing.factories import UserFactory
 from paperless_testing.fakes.progress import FakeProgressManager
-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:
@@ -115,7 +112,9 @@ 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"
@@ -201,19 +200,33 @@ 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
@@ -1049,7 +1062,7 @@ 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(
@@ -1590,7 +1603,13 @@ 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

@@ -22,9 +22,8 @@ from documents.models import Document
 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.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

@@ -53,7 +53,6 @@ from paperless_testing.dirs import DirectoriesMixin
 from paperless_testing.dirs import paperless_environment
 from paperless_testing.factories import DocumentBarcodeFactory
 from paperless_testing.permissions import grant_object
-from paperless_testing.samples import install_document_samples
 
 
 @pytest.mark.management
@@ -199,7 +198,10 @@ 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()
 
@@ -303,7 +305,10 @@ 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}",
@@ -312,7 +317,10 @@ 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",
@@ -411,7 +419,10 @@ 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")
@@ -447,7 +458,10 @@ 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()
 
@@ -474,7 +488,10 @@ 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()
 
@@ -506,7 +523,10 @@ 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")
@@ -548,7 +568,10 @@ 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"]
 
@@ -577,7 +600,10 @@ 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"]
 
@@ -613,7 +639,10 @@ 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"
@@ -709,7 +738,10 @@ 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
@@ -752,7 +784,10 @@ 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
@@ -797,7 +832,10 @@ 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
@@ -822,7 +860,10 @@ 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")
 
@@ -858,7 +899,10 @@ 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)
 
@@ -885,7 +929,10 @@ 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)
 
@@ -912,7 +959,10 @@ 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()
@@ -949,7 +999,10 @@ 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,
@@ -969,7 +1022,10 @@ 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()
@@ -1013,7 +1069,10 @@ 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_sample_files.py

@@ -1,61 +0,0 @@
-import hashlib
-from collections import defaultdict
-from pathlib import Path
-
-from paperless_testing.samples import SHARED_SAMPLES_DIR
-from paperless_testing.samples import SIMPLE_DIGITAL_PDF
-from paperless_testing.samples import install_document_samples
-
-EXPECTED_MEDIA_FILES = [
-    "originals/0000001.pdf",
-    "originals/0000002.pdf",
-    "originals/0000003.pdf",
-    "originals/0000004.pdf",
-    "originals/0000005.pdf",
-    "originals/0000006.pdf",
-    "archive/0000001.pdf",
-    "thumbnails/0000001.webp",
-    "thumbnails/0000002.webp",
-    "thumbnails/0000003.webp",
-    "thumbnails/0000004.webp",
-]
-
-
-def _sha(path: Path) -> str:
-    return hashlib.sha256(path.read_bytes()).hexdigest()
-
-
-def test_install_recreates_every_historical_opaque_name(tmp_path: Path) -> None:
-    install_document_samples(tmp_path)
-    for relpath in EXPECTED_MEDIA_FILES:
-        assert (tmp_path / relpath).is_file(), relpath
-
-
-def test_install_uses_the_shared_bytes(tmp_path: Path) -> None:
-    install_document_samples(tmp_path)
-    assert _sha(tmp_path / "originals" / "0000001.pdf") == _sha(SIMPLE_DIGITAL_PDF)
-
-
-APP_SAMPLE_TREES = [
-    Path(__file__).parent / "samples",
-    Path(__file__).parents[2] / "paperless" / "tests" / "samples",
-    SHARED_SAMPLES_DIR,
-]
-
-
-def test_no_two_sample_files_have_identical_bytes() -> None:
-    by_hash: dict[str, list[Path]] = defaultdict(list)
-    for tree in APP_SAMPLE_TREES:
-        assert tree.is_dir(), f"Sample tree does not exist: {tree}"
-        for path in tree.rglob("*"):
-            # Skip empty placeholders, which would all hash identically
-            if path.is_file() and path.stat().st_size > 0:
-                by_hash[_sha(path)].append(path)
-    assert by_hash, "No sample files were found to compare"
-    duplicates = {h: ps for h, ps in by_hash.items() if len(ps) > 1}
-    lines = ["  " + ", ".join(str(p) for p in ps) for ps in duplicates.values()]
-    message = (
-        "Duplicate sample files, move one to paperless_testing/sample_files:\n"
-        + "\n".join(lines)
-    )
-    assert not duplicates, message

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/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.

src/paperless/tests/parsers/test_tesseract_parser.py

@@ -160,11 +160,11 @@ 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
@@ -187,7 +187,7 @@ class TestGetPageCount:
         self,
         mocker: MockerFixture,
         tesseract_parser: RasterisedDocumentParser,
-        simple_digital_pdf_file: Path,
+        tesseract_samples_dir: Path,
         caplog,
     ) -> None:
         """
@@ -203,7 +203,7 @@ 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
@@ -272,10 +272,10 @@ 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()
@@ -284,7 +284,7 @@ class TestGetThumbnail:
         self,
         mocker: MockerFixture,
         tesseract_parser: RasterisedDocumentParser,
-        simple_digital_pdf_file: Path,
+        tesseract_samples_dir: Path,
     ) -> None:
         def _raise_on_pdf(input_file, output_file, **kwargs) -> None:
             if ".pdf" in str(input_file):
@@ -294,7 +294,7 @@ class TestGetThumbnail:
         mocker.patch("documents.parsers.run_convert", side_effect=_raise_on_pdf)
 
         thumb = tesseract_parser.get_thumbnail(
-            simple_digital_pdf_file,
+            tesseract_samples_dir / "simple-digital.pdf",
             "application/pdf",
         )
         assert thumb.is_file()
@@ -320,11 +320,11 @@ 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()
@@ -339,7 +339,7 @@ class TestParsePdf:
     def test_simple_digital_creates_archive(
         self,
         tesseract_parser: RasterisedDocumentParser,
-        multi_page_digital_pdf_file: Path,
+        tesseract_samples_dir: Path,
     ) -> None:
         """
         GIVEN:
@@ -353,7 +353,7 @@ 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
@@ -368,10 +368,10 @@ 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
@@ -384,11 +384,11 @@ 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,
         )
@@ -401,11 +401,11 @@ 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(
@@ -446,7 +446,7 @@ class TestParsePdf:
         self,
         mocker: MockerFixture,
         tesseract_parser: RasterisedDocumentParser,
-        simple_digital_pdf_file: Path,
+        tesseract_samples_dir: Path,
     ) -> None:
         mocker.patch(
             "ocrmypdf.ocr",
@@ -454,7 +454,7 @@ class TestParsePdf:
         )
         with pytest.raises(ParseError):
             tesseract_parser.parse(
-                simple_digital_pdf_file,
+                tesseract_samples_dir / "simple-digital.pdf",
                 "application/pdf",
             )
 
@@ -530,10 +530,10 @@ 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
@@ -557,12 +557,12 @@ 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
@@ -576,11 +576,11 @@ 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
@@ -594,7 +594,7 @@ 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:
@@ -609,7 +609,7 @@ 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
@@ -622,7 +622,7 @@ 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:
@@ -637,7 +637,7 @@ 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
@@ -733,7 +733,7 @@ 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:
@@ -747,7 +747,7 @@ 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,
         )
@@ -762,7 +762,7 @@ 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:
@@ -775,7 +775,7 @@ 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
@@ -787,29 +787,29 @@ 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",
             ),
@@ -818,10 +818,10 @@ 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:
@@ -834,9 +834,8 @@ 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,
         )
@@ -853,7 +852,7 @@ class TestSkipArchive:
         self,
         mocker: MockerFixture,
         tesseract_parser: RasterisedDocumentParser,
-        simple_digital_pdf_file: Path,
+        tesseract_samples_dir: Path,
     ) -> None:
         """
         GIVEN:
@@ -869,7 +868,7 @@ 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,
         )
@@ -908,7 +907,7 @@ 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:
@@ -923,7 +922,7 @@ 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

@@ -16,6 +16,8 @@ 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:
@@ -53,11 +55,11 @@ 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

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)