Chore: Tidy leftover parentheses and the samples module docstring

Co-Authored-By: Claude Sonnet 5.5 <noreply@anthropic.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_mail/tests/samples/*,src/paperless/tests/samples\
-  /mail/*,src/documents/tests/samples/*,*.po,*.json\
+  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\
   """
 write-changes = true
 

src/conftest.py

@@ -11,6 +11,8 @@ from typing import TYPE_CHECKING
 
 import pytest
 
+from paperless_testing import samples
+
 if TYPE_CHECKING:
     from collections.abc import Generator
     from pathlib import Path
@@ -149,3 +151,39 @@ 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

@@ -12,29 +12,25 @@ 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",
-    document_samples_dir: Path,
+    simple_digital_pdf_file: Path,
+    multi_page_images_pdf_file: Path,
+    thumbnail_webp_file: Path,
 ) -> "Document":
     """Create a document with valid files and matching checksums."""
     with filelock.FileLock(paperless_dirs.media_lock):
         shutil.copy(
-            document_samples_dir / "originals" / "0000001.pdf",
+            simple_digital_pdf_file,
             paperless_dirs.originals_dir / "0000001.pdf",
         )
         shutil.copy(
-            document_samples_dir / "archive" / "0000001.pdf",
+            multi_page_images_pdf_file,
             paperless_dirs.archive_dir / "0000001.pdf",
         )
         shutil.copy(
-            document_samples_dir / "thumbnails" / "0000001.webp",
+            thumbnail_webp_file,
             paperless_dirs.thumbnail_dir / "0000001.webp",
         )
 

src/documents/tests/samples/simple.txt

@@ -1 +0,0 @@
-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.SAMPLE_DIR / "simple.pdf", self.doc2.source_path)
+        shutil.copy(self.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

@@ -56,6 +56,8 @@ 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):
@@ -1852,7 +1854,11 @@ class TestDocumentApi(DirectoriesMixin, ConsumeTaskMixin, APITestCase):
             id=str(uuid.uuid4()),
         )
 
-        with (Path(__file__).parent / "samples" / "simple.pdf").open("rb") as f:
+        with SimpleUploadedFile(
+            "simple.pdf",
+            SIMPLE_DIGITAL_PDF.read_bytes(),
+            content_type="application/pdf",
+        ) as f:
             response = self.client.post(
                 "/api/documents/post_document/",
                 {"document": f},
@@ -1880,7 +1886,7 @@ class TestDocumentApi(DirectoriesMixin, ConsumeTaskMixin, APITestCase):
 
         payload = SimpleUploadedFile(
             "../../outside.pdf",
-            (Path(__file__).parent / "samples" / "simple.pdf").read_bytes(),
+            SIMPLE_DIGITAL_PDF.read_bytes(),
             content_type="application/pdf",
         )
 
@@ -1909,7 +1915,7 @@ class TestDocumentApi(DirectoriesMixin, ConsumeTaskMixin, APITestCase):
             id=str(uuid.uuid4()),
         )
 
-        pdf_bytes = (Path(__file__).parent / "samples" / "simple.pdf").read_bytes()
+        pdf_bytes = SIMPLE_DIGITAL_PDF.read_bytes()
         boundary = "paperless-boundary"
         payload = (
             (
@@ -1985,7 +1991,7 @@ class TestDocumentApi(DirectoriesMixin, ConsumeTaskMixin, APITestCase):
     def test_upload_insufficient_permissions(self) -> None:
         self.client.force_authenticate(user=UserFactory(username="testuser2"))
 
-        with (Path(__file__).parent / "samples" / "simple.pdf").open("rb") as f:
+        with SIMPLE_DIGITAL_PDF.open("rb") as f:
             response = self.client.post(
                 "/api/documents/post_document/",
                 {"document": f},
@@ -1998,7 +2004,11 @@ class TestDocumentApi(DirectoriesMixin, ConsumeTaskMixin, APITestCase):
             id=str(uuid.uuid4()),
         )
 
-        with (Path(__file__).parent / "samples" / "simple.pdf").open("rb") as f:
+        with SimpleUploadedFile(
+            "simple.pdf",
+            SIMPLE_DIGITAL_PDF.read_bytes(),
+            content_type="application/pdf",
+        ) as f:
             response = self.client.post(
                 "/api/documents/post_document/",
                 {
@@ -2031,7 +2041,7 @@ class TestDocumentApi(DirectoriesMixin, ConsumeTaskMixin, APITestCase):
             id=str(uuid.uuid4()),
         )
 
-        with (Path(__file__).parent / "samples" / "simple.pdf").open("rb") as f:
+        with SIMPLE_DIGITAL_PDF.open("rb") as f:
             response = self.client.post(
                 "/api/documents/post_document/",
                 {"documenst": f},
@@ -2057,7 +2067,7 @@ class TestDocumentApi(DirectoriesMixin, ConsumeTaskMixin, APITestCase):
             id=str(uuid.uuid4()),
         )
 
-        with (Path(__file__).parent / "samples" / "simple.pdf").open("rb") as f:
+        with SIMPLE_DIGITAL_PDF.open("rb") as f:
             response = self.client.post(
                 "/api/documents/post_document/",
                 {"document": f, "title": "my custom title"},
@@ -2077,7 +2087,7 @@ class TestDocumentApi(DirectoriesMixin, ConsumeTaskMixin, APITestCase):
         )
 
         c = Correspondent.objects.create(name="test-corres")
-        with (Path(__file__).parent / "samples" / "simple.pdf").open("rb") as f:
+        with SIMPLE_DIGITAL_PDF.open("rb") as f:
             response = self.client.post(
                 "/api/documents/post_document/",
                 {"document": f, "correspondent": c.id},
@@ -2096,7 +2106,7 @@ class TestDocumentApi(DirectoriesMixin, ConsumeTaskMixin, APITestCase):
             id=str(uuid.uuid4()),
         )
 
-        with (Path(__file__).parent / "samples" / "simple.pdf").open("rb") as f:
+        with SIMPLE_DIGITAL_PDF.open("rb") as f:
             response = self.client.post(
                 "/api/documents/post_document/",
                 {"document": f, "correspondent": 3456},
@@ -2111,7 +2121,7 @@ class TestDocumentApi(DirectoriesMixin, ConsumeTaskMixin, APITestCase):
         )
 
         dt = DocumentType.objects.create(name="invoice")
-        with (Path(__file__).parent / "samples" / "simple.pdf").open("rb") as f:
+        with SIMPLE_DIGITAL_PDF.open("rb") as f:
             response = self.client.post(
                 "/api/documents/post_document/",
                 {"document": f, "document_type": dt.id},
@@ -2130,7 +2140,7 @@ class TestDocumentApi(DirectoriesMixin, ConsumeTaskMixin, APITestCase):
             id=str(uuid.uuid4()),
         )
 
-        with (Path(__file__).parent / "samples" / "simple.pdf").open("rb") as f:
+        with SIMPLE_DIGITAL_PDF.open("rb") as f:
             response = self.client.post(
                 "/api/documents/post_document/",
                 {"document": f, "document_type": 34578},
@@ -2145,7 +2155,7 @@ class TestDocumentApi(DirectoriesMixin, ConsumeTaskMixin, APITestCase):
         )
 
         sp = StoragePath.objects.create(name="invoices")
-        with (Path(__file__).parent / "samples" / "simple.pdf").open("rb") as f:
+        with SIMPLE_DIGITAL_PDF.open("rb") as f:
             response = self.client.post(
                 "/api/documents/post_document/",
                 {"document": f, "storage_path": sp.id},
@@ -2164,7 +2174,7 @@ class TestDocumentApi(DirectoriesMixin, ConsumeTaskMixin, APITestCase):
             id=str(uuid.uuid4()),
         )
 
-        with (Path(__file__).parent / "samples" / "simple.pdf").open("rb") as f:
+        with SIMPLE_DIGITAL_PDF.open("rb") as f:
             response = self.client.post(
                 "/api/documents/post_document/",
                 {"document": f, "storage_path": 34578},
@@ -2180,7 +2190,7 @@ class TestDocumentApi(DirectoriesMixin, ConsumeTaskMixin, APITestCase):
 
         t1 = Tag.objects.create(name="tag1")
         t2 = Tag.objects.create(name="tag2")
-        with (Path(__file__).parent / "samples" / "simple.pdf").open("rb") as f:
+        with SIMPLE_DIGITAL_PDF.open("rb") as f:
             response = self.client.post(
                 "/api/documents/post_document/",
                 {"document": f, "tags": [t2.id, t1.id]},
@@ -2201,7 +2211,7 @@ class TestDocumentApi(DirectoriesMixin, ConsumeTaskMixin, APITestCase):
 
         t1 = Tag.objects.create(name="tag1")
         t2 = Tag.objects.create(name="tag2")
-        with (Path(__file__).parent / "samples" / "simple.pdf").open("rb") as f:
+        with SIMPLE_DIGITAL_PDF.open("rb") as f:
             response = self.client.post(
                 "/api/documents/post_document/",
                 {"document": f, "tags": [t2.id, t1.id, 734563]},
@@ -2225,7 +2235,7 @@ class TestDocumentApi(DirectoriesMixin, ConsumeTaskMixin, APITestCase):
             0,
             tzinfo=zoneinfo.ZoneInfo("America/Los_Angeles"),
         )
-        with (Path(__file__).parent / "samples" / "simple.pdf").open("rb") as f:
+        with SIMPLE_DIGITAL_PDF.open("rb") as f:
             response = self.client.post(
                 "/api/documents/post_document/",
                 {"document": f, "created": created},
@@ -2241,7 +2251,11 @@ class TestDocumentApi(DirectoriesMixin, ConsumeTaskMixin, APITestCase):
             id=str(uuid.uuid4()),
         )
 
-        with (Path(__file__).parent / "samples" / "simple.pdf").open("rb") as f:
+        with SimpleUploadedFile(
+            "simple.pdf",
+            SIMPLE_DIGITAL_PDF.read_bytes(),
+            content_type="application/pdf",
+        ) as f:
             response = self.client.post(
                 "/api/documents/post_document/",
                 {"document": f, "archive_serial_number": 500},
@@ -2268,7 +2282,11 @@ class TestDocumentApi(DirectoriesMixin, ConsumeTaskMixin, APITestCase):
             data_type=CustomField.FieldDataType.STRING,
         )
 
-        with (Path(__file__).parent / "samples" / "simple.pdf").open("rb") as f:
+        with SimpleUploadedFile(
+            "simple.pdf",
+            SIMPLE_DIGITAL_PDF.read_bytes(),
+            content_type="application/pdf",
+        ) as f:
             response = self.client.post(
                 "/api/documents/post_document/",
                 {
@@ -2323,7 +2341,7 @@ class TestDocumentApi(DirectoriesMixin, ConsumeTaskMixin, APITestCase):
         w1.actions.add(action1)
         w1.save()
 
-        with (Path(__file__).parent / "samples" / "simple.pdf").open("rb") as f:
+        with SIMPLE_DIGITAL_PDF.open("rb") as f:
             response = self.client.post(
                 "/api/documents/post_document/",
                 {
@@ -2364,7 +2382,11 @@ class TestDocumentApi(DirectoriesMixin, ConsumeTaskMixin, APITestCase):
             data_type=CustomField.FieldDataType.INT,
         )
 
-        with (Path(__file__).parent / "samples" / "simple.pdf").open("rb") as f:
+        with SimpleUploadedFile(
+            "simple.pdf",
+            SIMPLE_DIGITAL_PDF.read_bytes(),
+            content_type="application/pdf",
+        ) as f:
             response = self.client.post(
                 "/api/documents/post_document/",
                 {
@@ -2413,7 +2435,7 @@ class TestDocumentApi(DirectoriesMixin, ConsumeTaskMixin, APITestCase):
         ]
 
         for payload in error_payloads:
-            with (Path(__file__).parent / "samples" / "simple.pdf").open("rb") as f:
+            with SIMPLE_DIGITAL_PDF.open("rb") as f:
                 data = {"document": f, **payload}
                 response = self.client.post(
                     "/api/documents/post_document/",
@@ -2471,7 +2493,7 @@ class TestDocumentApi(DirectoriesMixin, ConsumeTaskMixin, APITestCase):
             id=str(uuid.uuid4()),
         )
 
-        with (Path(__file__).parent / "samples" / "simple.pdf").open("rb") as f:
+        with SIMPLE_DIGITAL_PDF.open("rb") as f:
             response = self.client.post(
                 "/api/documents/post_document/",
                 {"document": f, "from_webui": True},
@@ -2510,14 +2532,8 @@ class TestDocumentApi(DirectoriesMixin, ConsumeTaskMixin, APITestCase):
             archive_filename="archive.pdf",
         )
 
-        source_file: Path = (
-            Path(__file__).parent
-            / "samples"
-            / "documents"
-            / "thumbnails"
-            / "0000001.webp"
-        )
-        archive_file: Path = Path(__file__).parent / "samples" / "simple.pdf"
+        source_file: Path = THUMBNAIL_WEBP
+        archive_file: Path = SIMPLE_DIGITAL_PDF
 
         shutil.copy(source_file, doc.source_path)
         shutil.copy(archive_file, doc.archive_path)
@@ -2550,7 +2566,7 @@ class TestDocumentApi(DirectoriesMixin, ConsumeTaskMixin, APITestCase):
             mime_type="application/pdf",
         )
 
-        shutil.copy(Path(__file__).parent / "samples" / "simple.pdf", doc.source_path)
+        shutil.copy(SIMPLE_DIGITAL_PDF, doc.source_path)
 
         response = self.client.get(f"/api/documents/{doc.pk}/metadata/")
         self.assertEqual(response.status_code, status.HTTP_200_OK)
@@ -4288,8 +4304,8 @@ class TestDocumentApi(DirectoriesMixin, ConsumeTaskMixin, APITestCase):
             filename="test2.pdf",
         )
 
-        archive_file = Path(__file__).parent / "samples" / "simple.pdf"
-        source_file = Path(__file__).parent / "samples" / "simple.pdf"
+        archive_file = SIMPLE_DIGITAL_PDF
+        source_file = SIMPLE_DIGITAL_PDF
 
         shutil.copy(archive_file, doc.archive_path)
         shutil.copy(source_file, doc2.source_path)

src/documents/tests/test_api_email.py

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

src/documents/tests/test_barcodes.py

@@ -150,7 +150,7 @@ class TestBarcode(
             - No barcodes detected
             - No pages to split on
         """
-        test_file = self.SAMPLE_DIR / "simple.pdf"
+        test_file = self.SIMPLE_PDF
         with self.get_reader(test_file) as reader:
             reader.detect()
             separator_page_numbers = reader.get_separation_pages()
@@ -442,7 +442,7 @@ class TestBarcode(
         THEN:
             - Nothing happens
         """
-        test_file = self.SAMPLE_DIR / "simple.pdf"
+        test_file = self.SIMPLE_PDF
 
         with self.get_reader(test_file) as reader:
             try:

src/documents/tests/test_bulk_edit.py

@@ -24,6 +24,9 @@ from documents.models import Tag
 from documents.permissions import set_permissions_for_objects
 from paperless_testing.dirs import DirectoriesMixin
 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):
@@ -701,47 +704,27 @@ class TestPDFActions(DirectoriesMixin, TestCase):
         super().setUp()
         sample1 = self.dirs.scratch_dir / "sample.pdf"
         shutil.copy(
-            Path(__file__).parent
-            / "samples"
-            / "documents"
-            / "originals"
-            / "0000001.pdf",
+            SIMPLE_DIGITAL_PDF,
             sample1,
         )
         sample1_archive = self.dirs.archive_dir / "sample_archive.pdf"
         shutil.copy(
-            Path(__file__).parent
-            / "samples"
-            / "documents"
-            / "originals"
-            / "0000001.pdf",
+            SIMPLE_DIGITAL_PDF,
             sample1_archive,
         )
         sample2 = self.dirs.scratch_dir / "sample2.pdf"
         shutil.copy(
-            Path(__file__).parent
-            / "samples"
-            / "documents"
-            / "originals"
-            / "0000002.pdf",
+            MULTI_PAGE_DIGITAL_PDF,
             sample2,
         )
         sample2_archive = self.dirs.archive_dir / "sample2_archive.pdf"
         shutil.copy(
-            Path(__file__).parent
-            / "samples"
-            / "documents"
-            / "originals"
-            / "0000002.pdf",
+            MULTI_PAGE_DIGITAL_PDF,
             sample2_archive,
         )
         sample3 = self.dirs.scratch_dir / "sample3.pdf"
         shutil.copy(
-            Path(__file__).parent
-            / "samples"
-            / "documents"
-            / "originals"
-            / "0000003.pdf",
+            WITH_FORM_PDF,
             sample3,
         )
         self.doc1 = Document.objects.create(
@@ -775,11 +758,7 @@ class TestPDFActions(DirectoriesMixin, TestCase):
         )
         img_doc_archive = self.dirs.archive_dir / "sample_image.pdf"
         shutil.copy(
-            Path(__file__).parent
-            / "samples"
-            / "documents"
-            / "originals"
-            / "0000001.pdf",
+            SIMPLE_DIGITAL_PDF,
             img_doc_archive,
         )
         self.img_doc = Document.objects.create(

src/documents/tests/test_consumer.py

@@ -36,6 +36,9 @@ 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:
@@ -112,9 +115,7 @@ class _BaseNewStyleParser:
 
 
 class DummyParser(_BaseNewStyleParser):
-    _ARCHIVE_SRC = (
-        Path(__file__).parent / "samples" / "documents" / "archive" / "0000001.pdf"
-    )
+    _ARCHIVE_SRC = MULTI_PAGE_IMAGES_PDF
 
     def parse(self, document_path, mime_type, *, produce_archive: bool = True) -> None:
         self._text = "The Text"
@@ -200,33 +201,19 @@ class TestConsumer(
         self.addCleanup(patcher.stop)
 
     def get_test_file(self):
-        src = (
-            Path(__file__).parent
-            / "samples"
-            / "documents"
-            / "originals"
-            / "0000001.pdf"
-        )
+        src = SIMPLE_DIGITAL_PDF
         dst = self.dirs.scratch_dir / "sample.pdf"
         shutil.copy(src, dst)
         return dst
 
     def get_test_file2(self):
-        src = (
-            Path(__file__).parent
-            / "samples"
-            / "documents"
-            / "originals"
-            / "0000002.pdf"
-        )
+        src = MULTI_PAGE_DIGITAL_PDF
         dst = self.dirs.scratch_dir / "sample2.pdf"
         shutil.copy(src, dst)
         return dst
 
     def get_test_archive_file(self):
-        src = (
-            Path(__file__).parent / "samples" / "documents" / "archive" / "0000001.pdf"
-        )
+        src = MULTI_PAGE_IMAGES_PDF
         dst = self.dirs.scratch_dir / "sample_archive.pdf"
         shutil.copy(src, dst)
         return dst
@@ -1062,7 +1049,7 @@ class TestConsumer(
     @mock.patch("documents.consumer.get_parser_registry")
     def test_similar_filenames(self, m) -> None:
         shutil.copy(
-            Path(__file__).parent / "samples" / "simple.pdf",
+            SIMPLE_DIGITAL_PDF,
             settings.CONSUMPTION_DIR / "simple.pdf",
         )
         shutil.copy(
@@ -1603,13 +1590,7 @@ class TestConsumerRemoteOCR(
         self.addCleanup(patcher.stop)
 
     def _consume(self, *, overrides: DocumentMetadataOverrides | None = None) -> bool:
-        src = (
-            Path(__file__).parent
-            / "samples"
-            / "documents"
-            / "originals"
-            / "0000001.pdf"
-        )
+        src = SIMPLE_DIGITAL_PDF
         dst = self.dirs.scratch_dir / "sample.pdf"
         shutil.copy(src, dst)
 

src/documents/tests/test_double_sided.py

@@ -37,12 +37,15 @@ 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_DIR / srcname
+        src = self._sample(srcname)
         dst = self.double_sided_dir / dstname
         dst.parent.mkdir(parents=True, exist_ok=True)
         shutil.copy(src, dst)
@@ -57,7 +60,7 @@ class TestDoubleSided(
         return msg
 
     def create_staging_file(self, src="double-sided-odd.pdf", datetime=None) -> None:
-        shutil.copy(self.SAMPLE_DIR / src, self.staging_file)
+        shutil.copy(self._sample(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

@@ -22,8 +22,9 @@ 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 = Path(__file__).parent / "samples" / "simple.pdf"
+sample_file: Path = SIMPLE_DIGITAL_PDF
 
 
 @pytest.mark.management

src/documents/tests/test_management_exporter.py

@@ -51,6 +51,7 @@ from paperless_testing.assertions import FileSystemAssertsMixin
 from paperless_testing.dirs import DirectoriesMixin
 from paperless_testing.dirs import paperless_environment
 from paperless_testing.permissions import grant_object
+from paperless_testing.samples import install_document_samples
 
 
 @pytest.mark.management
@@ -196,10 +197,7 @@ class TestExportImport(
 
     def test_exporter(self, *, use_filename_format=False) -> None:
         shutil.rmtree(Path(self.dirs.media_dir) / "documents")
-        shutil.copytree(
-            Path(__file__).parent / "samples" / "documents",
-            Path(self.dirs.media_dir) / "documents",
-        )
+        install_document_samples(Path(self.dirs.media_dir) / "documents")
 
         num_permission_objects = Permission.objects.count()
 
@@ -303,10 +301,7 @@ class TestExportImport(
 
     def test_exporter_with_filename_format(self) -> None:
         shutil.rmtree(Path(self.dirs.media_dir) / "documents")
-        shutil.copytree(
-            Path(__file__).parent / "samples" / "documents",
-            Path(self.dirs.media_dir) / "documents",
-        )
+        install_document_samples(Path(self.dirs.media_dir) / "documents")
 
         with override_settings(
             FILENAME_FORMAT="{created_year}/{correspondent}/{title}",
@@ -315,10 +310,7 @@ class TestExportImport(
 
     def test_exporter_includes_share_links_and_bundles(self) -> None:
         shutil.rmtree(Path(self.dirs.media_dir) / "documents")
-        shutil.copytree(
-            Path(__file__).parent / "samples" / "documents",
-            Path(self.dirs.media_dir) / "documents",
-        )
+        install_document_samples(Path(self.dirs.media_dir) / "documents")
 
         share_link = ShareLink.objects.create(
             slug="share-link-slug",
@@ -417,10 +409,7 @@ class TestExportImport(
 
     def test_update_export_changed_time(self) -> None:
         shutil.rmtree(Path(self.dirs.media_dir) / "documents")
-        shutil.copytree(
-            Path(__file__).parent / "samples" / "documents",
-            Path(self.dirs.media_dir) / "documents",
-        )
+        install_document_samples(Path(self.dirs.media_dir) / "documents")
 
         self._do_export()
         self.assertIsFile(self.target / "manifest.json")
@@ -456,10 +445,7 @@ class TestExportImport(
 
     def test_update_export_changed_checksum(self) -> None:
         shutil.rmtree(Path(self.dirs.media_dir) / "documents")
-        shutil.copytree(
-            Path(__file__).parent / "samples" / "documents",
-            Path(self.dirs.media_dir) / "documents",
-        )
+        install_document_samples(Path(self.dirs.media_dir) / "documents")
 
         self._do_export()
 
@@ -486,10 +472,7 @@ class TestExportImport(
 
     def test_update_export_deleted_document(self) -> None:
         shutil.rmtree(Path(self.dirs.media_dir) / "documents")
-        shutil.copytree(
-            Path(__file__).parent / "samples" / "documents",
-            Path(self.dirs.media_dir) / "documents",
-        )
+        install_document_samples(Path(self.dirs.media_dir) / "documents")
 
         manifest = self._do_export()
 
@@ -521,10 +504,7 @@ class TestExportImport(
     @override_settings(FILENAME_FORMAT="{title}/{correspondent}")
     def test_update_export_changed_location(self) -> None:
         shutil.rmtree(Path(self.dirs.media_dir) / "documents")
-        shutil.copytree(
-            Path(__file__).parent / "samples" / "documents",
-            Path(self.dirs.media_dir) / "documents",
-        )
+        install_document_samples(Path(self.dirs.media_dir) / "documents")
 
         self._do_export(use_filename_format=True)
         self.assertIsFile(self.target / "wow1" / "c.pdf")
@@ -566,10 +546,7 @@ class TestExportImport(
             - Zipfile contains exported files
         """
         shutil.rmtree(Path(self.dirs.media_dir) / "documents")
-        shutil.copytree(
-            Path(__file__).parent / "samples" / "documents",
-            Path(self.dirs.media_dir) / "documents",
-        )
+        install_document_samples(Path(self.dirs.media_dir) / "documents")
 
         args = ["document_exporter", self.target, "--zip"]
 
@@ -598,10 +575,7 @@ class TestExportImport(
             - Zipfile contains exported files
         """
         shutil.rmtree(Path(self.dirs.media_dir) / "documents")
-        shutil.copytree(
-            Path(__file__).parent / "samples" / "documents",
-            Path(self.dirs.media_dir) / "documents",
-        )
+        install_document_samples(Path(self.dirs.media_dir) / "documents")
 
         args = ["document_exporter", self.target, "--zip", "--use-filename-format"]
 
@@ -637,10 +611,7 @@ class TestExportImport(
             - The existing file and directory in target are removed
         """
         shutil.rmtree(Path(self.dirs.media_dir) / "documents")
-        shutil.copytree(
-            Path(__file__).parent / "samples" / "documents",
-            Path(self.dirs.media_dir) / "documents",
-        )
+        install_document_samples(Path(self.dirs.media_dir) / "documents")
 
         # Create stuff in target directory
         existing_file = self.target / "test.txt"
@@ -736,10 +707,7 @@ class TestExportImport(
             - Documents can be imported again
         """
         shutil.rmtree(Path(self.dirs.media_dir) / "documents")
-        shutil.copytree(
-            Path(__file__).parent / "samples" / "documents",
-            Path(self.dirs.media_dir) / "documents",
-        )
+        install_document_samples(Path(self.dirs.media_dir) / "documents")
 
         manifest = self._do_export()
         has_archive = False
@@ -782,10 +750,7 @@ class TestExportImport(
             - Documents can be imported again
         """
         shutil.rmtree(Path(self.dirs.media_dir) / "documents")
-        shutil.copytree(
-            Path(__file__).parent / "samples" / "documents",
-            Path(self.dirs.media_dir) / "documents",
-        )
+        install_document_samples(Path(self.dirs.media_dir) / "documents")
 
         manifest = self._do_export()
         has_thumbnail = False
@@ -830,10 +795,7 @@ class TestExportImport(
             - Documents can be imported again
         """
         shutil.rmtree(Path(self.dirs.media_dir) / "documents")
-        shutil.copytree(
-            Path(__file__).parent / "samples" / "documents",
-            Path(self.dirs.media_dir) / "documents",
-        )
+        install_document_samples(Path(self.dirs.media_dir) / "documents")
 
         manifest = self._do_export(split_manifest=True)
         has_document = False
@@ -866,10 +828,7 @@ class TestExportImport(
             - Documents can be imported again
         """
         shutil.rmtree(Path(self.dirs.media_dir) / "documents")
-        shutil.copytree(
-            Path(__file__).parent / "samples" / "documents",
-            Path(self.dirs.media_dir) / "documents",
-        )
+        install_document_samples(Path(self.dirs.media_dir) / "documents")
 
         self._do_export(use_folder_prefix=True)
 
@@ -896,10 +855,7 @@ class TestExportImport(
             - Documents can be imported again
         """
         shutil.rmtree(Path(self.dirs.media_dir) / "documents")
-        shutil.copytree(
-            Path(__file__).parent / "samples" / "documents",
-            Path(self.dirs.media_dir) / "documents",
-        )
+        install_document_samples(Path(self.dirs.media_dir) / "documents")
 
         self._do_export(use_folder_prefix=True, split_manifest=True)
 
@@ -926,10 +882,7 @@ class TestExportImport(
         """
 
         shutil.rmtree(Path(self.dirs.media_dir) / "documents")
-        shutil.copytree(
-            Path(__file__).parent / "samples" / "documents",
-            Path(self.dirs.media_dir) / "documents",
-        )
+        install_document_samples(Path(self.dirs.media_dir) / "documents")
 
         num_content_type_objects = ContentType.objects.count()
         num_permission_objects = Permission.objects.count()
@@ -966,10 +919,7 @@ class TestExportImport(
 
     def test_exporter_with_auditlog_disabled(self) -> None:
         shutil.rmtree(Path(self.dirs.media_dir) / "documents")
-        shutil.copytree(
-            Path(__file__).parent / "samples" / "documents",
-            Path(self.dirs.media_dir) / "documents",
-        )
+        install_document_samples(Path(self.dirs.media_dir) / "documents")
 
         with override_settings(
             AUDIT_LOG_ENABLED=False,
@@ -989,10 +939,7 @@ class TestExportImport(
               survive the round-trip with deleted_at preserved
         """
         shutil.rmtree(Path(self.dirs.media_dir) / "documents")
-        shutil.copytree(
-            Path(__file__).parent / "samples" / "documents",
-            Path(self.dirs.media_dir) / "documents",
-        )
+        install_document_samples(Path(self.dirs.media_dir) / "documents")
 
         # d1 has self.note and self.cfi1 attached via setUp
         self.d1.delete()
@@ -1036,10 +983,7 @@ class TestExportImport(
         """
 
         shutil.rmtree(self.dirs.media_dir / "documents")
-        shutil.copytree(
-            self.SAMPLE_DIR / "documents",
-            self.dirs.media_dir / "documents",
-        )
+        install_document_samples(self.dirs.media_dir / "documents")
 
         _ = self._do_export(data_only=True)
 

src/documents/tests/test_management_thumbnails.py

@@ -11,6 +11,7 @@ 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
@@ -24,7 +25,7 @@ class TestMakeThumbnails(DirectoriesMixin, FileSystemAssertsMixin, TestCase):
             filename="test.pdf",
         )
         shutil.copy(
-            Path(__file__).parent / "samples" / "simple.pdf",
+            SIMPLE_DIGITAL_PDF,
             self.d1.source_path,
         )
 
@@ -36,7 +37,7 @@ class TestMakeThumbnails(DirectoriesMixin, FileSystemAssertsMixin, TestCase):
             filename="test2.pdf",
         )
         shutil.copy(
-            Path(__file__).parent / "samples" / "simple.pdf",
+            SIMPLE_DIGITAL_PDF,
             self.d2.source_path,
         )
 

src/documents/tests/test_sample_files.py

@@ -0,0 +1,61 @@
+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

@@ -20,6 +20,7 @@ from documents.sanity_checker import SanityCheckMessages
 from documents.tests.helpers import dummy_preprocess
 from paperless_testing.assertions import FileSystemAssertsMixin
 from paperless_testing.dirs import DirectoriesMixin
+from paperless_testing.samples import SIMPLE_DIGITAL_PDF
 
 
 @pytest.mark.django_db
@@ -228,20 +229,12 @@ class TestUpdateContent(DirectoriesMixin, TestCase):
         """
         sample1 = self.dirs.scratch_dir / "sample.pdf"
         shutil.copy(
-            Path(__file__).parent
-            / "samples"
-            / "documents"
-            / "originals"
-            / "0000001.pdf",
+            SIMPLE_DIGITAL_PDF,
             sample1,
         )
         sample1_archive = self.dirs.archive_dir / "sample_archive.pdf"
         shutil.copy(
-            Path(__file__).parent
-            / "samples"
-            / "documents"
-            / "originals"
-            / "0000001.pdf",
+            SIMPLE_DIGITAL_PDF,
             sample1_archive,
         )
         doc = Document.objects.create(
@@ -269,11 +262,7 @@ class TestUpdateContent(DirectoriesMixin, TestCase):
         """
         sample1 = self.dirs.scratch_dir / "sample.pdf"
         shutil.copy(
-            Path(__file__).parent
-            / "samples"
-            / "documents"
-            / "originals"
-            / "0000001.pdf",
+            SIMPLE_DIGITAL_PDF,
             sample1,
         )
         doc = Document.objects.create(

src/documents/tests/test_workflows.py

@@ -178,7 +178,7 @@ class TestWorkflows(
         self.assertEqual(action.__str__(), "WorkflowAction 1")
 
         test_file = shutil.copy(
-            self.SAMPLE_DIR / "simple.pdf",
+            self.SIMPLE_PDF,
             self.dirs.scratch_dir / "simple.pdf",
         )
 
@@ -290,7 +290,7 @@ class TestWorkflows(
         w.save()
 
         test_file = shutil.copy(
-            self.SAMPLE_DIR / "simple.pdf",
+            self.SIMPLE_PDF,
             self.dirs.scratch_dir / "simple.pdf",
         )
 
@@ -409,7 +409,7 @@ class TestWorkflows(
         w2.save()
 
         test_file = shutil.copy(
-            self.SAMPLE_DIR / "simple.pdf",
+            self.SIMPLE_PDF,
             self.dirs.scratch_dir / "simple.pdf",
         )
 
@@ -478,7 +478,7 @@ class TestWorkflows(
         w.save()
 
         test_file = shutil.copy(
-            self.SAMPLE_DIR / "simple.pdf",
+            self.SIMPLE_PDF,
             self.dirs.scratch_dir / "simple.pdf",
         )
 
@@ -531,7 +531,7 @@ class TestWorkflows(
         w.save()
 
         test_file = shutil.copy(
-            self.SAMPLE_DIR / "simple.pdf",
+            self.SIMPLE_PDF,
             self.dirs.scratch_dir / "simple.pdf",
         )
 
@@ -608,7 +608,7 @@ class TestWorkflows(
         w.save()
 
         test_file = shutil.copy(
-            self.SAMPLE_DIR / "simple.pdf",
+            self.SIMPLE_PDF,
             self.dirs.scratch_dir / "simple.pdf",
         )
 
@@ -687,7 +687,7 @@ class TestWorkflows(
         w.save()
 
         test_file = shutil.copy(
-            self.SAMPLE_DIR / "simple.pdf",
+            self.SIMPLE_PDF,
             self.dirs.scratch_dir / "simple.pdf",
         )
 
@@ -765,7 +765,7 @@ class TestWorkflows(
         w.save()
 
         test_file = shutil.copy(
-            self.SAMPLE_DIR / "simple.pdf",
+            self.SIMPLE_PDF,
             self.dirs.scratch_dir / "simple.pdf",
         )
 
@@ -876,7 +876,7 @@ class TestWorkflows(
         w.save()
 
         test_file = shutil.copy(
-            self.SAMPLE_DIR / "simple.pdf",
+            self.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.SAMPLE_DIR / "simple.pdf", destination)
+        shutil.copy(self.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.SAMPLE_DIR / "simple.pdf",
+            self.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.SAMPLE_DIR / "simple.pdf", destination)
+        shutil.copy(self.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.SAMPLE_DIR / "simple.pdf", destination)
+        shutil.copy(self.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.SAMPLE_DIR / "simple.pdf",
+            self.SIMPLE_PDF,
             self.dirs.scratch_dir / "simple.pdf",
         )
 
@@ -3346,7 +3346,7 @@ class TestWorkflows(
         w.save()
 
         test_file = shutil.copy(
-            self.SAMPLE_DIR / "simple.pdf",
+            self.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.SAMPLE_DIR / "simple.pdf",
+            self.SIMPLE_PDF,
             self.dirs.scratch_dir / "working-copy.pdf",
         )
 
@@ -3596,7 +3596,7 @@ class TestWorkflows(
 
         # move the file
         test_file = shutil.copy(
-            self.SAMPLE_DIR / "simple.pdf",
+            self.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.SAMPLE_DIR / "simple.pdf", destination)
+        shutil.copy(self.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.SAMPLE_DIR / "simple.pdf",
+            self.SIMPLE_PDF,
             self.dirs.scratch_dir / "simple.pdf",
         )
 
@@ -4036,7 +4036,7 @@ class TestWorkflows(
         w.save()
 
         test_file = shutil.copy(
-            self.SAMPLE_DIR / "simple.pdf",
+            self.SIMPLE_PDF,
             self.dirs.scratch_dir / "simple.pdf",
         )
 
@@ -4387,7 +4387,7 @@ class TestWorkflows(
         w.save()
 
         test_file = shutil.copy(
-            self.SAMPLE_DIR / "simple.pdf",
+            self.SIMPLE_PDF,
             self.dirs.scratch_dir / "simple.pdf",
         )
 
@@ -4835,7 +4835,7 @@ class TestWorkflows(
         w.save()
 
         test_file = shutil.copy(
-            self.SAMPLE_DIR / "simple.pdf",
+            self.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.SAMPLE_DIR / "simple.pdf",
+            self.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.SAMPLE_DIR / "simple.pdf",
+            self.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.SAMPLE_DIR / "simple.pdf",
+            self.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.SAMPLE_DIR / "simple.pdf",
+            self.SIMPLE_PDF,
             self.dirs.scratch_dir / "simple.pdf",
         )
         overrides = DocumentMetadataOverrides()
@@ -5814,7 +5814,7 @@ class TestApplyAISuggestionsWorkflowAction(
         )
 
         test_file = shutil.copy(
-            self.SAMPLE_DIR / "simple.pdf",
+            self.SIMPLE_PDF,
             self.dirs.scratch_dir / "simple.pdf",
         )
 

src/documents/tests/utils.py

@@ -11,6 +11,7 @@ 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:
@@ -53,6 +54,8 @@ class SampleDirMixin:
 
     BARCODE_SAMPLE_DIR = SAMPLE_DIR / "barcodes"
 
+    SIMPLE_PDF = SIMPLE_DIGITAL_PDF
+
 
 class GetConsumerMixin:
     @contextmanager

src/paperless/tests/parsers/conftest.py

@@ -432,30 +432,6 @@ 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,
-        tesseract_samples_dir: Path,
+        simple_digital_pdf_file: Path,
     ) -> None:
         assert (
             tesseract_parser.get_page_count(
-                tesseract_samples_dir / "simple-digital.pdf",
+                simple_digital_pdf_file,
                 "application/pdf",
             )
             == 1
@@ -187,7 +187,7 @@ class TestGetPageCount:
         self,
         mocker: MockerFixture,
         tesseract_parser: RasterisedDocumentParser,
-        tesseract_samples_dir: Path,
+        simple_digital_pdf_file: Path,
         caplog,
     ) -> None:
         """
@@ -203,7 +203,7 @@ class TestGetPageCount:
 
         with caplog.at_level(logging.WARNING):
             page_count = tesseract_parser.get_page_count(
-                tesseract_samples_dir / "simple-digital.pdf",
+                simple_digital_pdf_file,
                 "application/pdf",
             )
         assert page_count is None
@@ -272,10 +272,10 @@ class TestGetThumbnail:
     def test_thumbnail_is_file(
         self,
         tesseract_parser: RasterisedDocumentParser,
-        tesseract_samples_dir: Path,
+        simple_digital_pdf_file: Path,
     ) -> None:
         thumb = tesseract_parser.get_thumbnail(
-            tesseract_samples_dir / "simple-digital.pdf",
+            simple_digital_pdf_file,
             "application/pdf",
         )
         assert thumb.is_file()
@@ -284,7 +284,7 @@ class TestGetThumbnail:
         self,
         mocker: MockerFixture,
         tesseract_parser: RasterisedDocumentParser,
-        tesseract_samples_dir: Path,
+        simple_digital_pdf_file: 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(
-            tesseract_samples_dir / "simple-digital.pdf",
+            simple_digital_pdf_file,
             "application/pdf",
         )
         assert thumb.is_file()
@@ -320,11 +320,11 @@ class TestExtractText:
     def test_extract_text_from_digital_pdf(
         self,
         tesseract_parser: RasterisedDocumentParser,
-        tesseract_samples_dir: Path,
+        simple_digital_pdf_file: Path,
     ) -> None:
         text = tesseract_parser.extract_text(
             None,
-            tesseract_samples_dir / "simple-digital.pdf",
+            simple_digital_pdf_file,
         )
         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,
-        tesseract_samples_dir: Path,
+        multi_page_digital_pdf_file: Path,
     ) -> None:
         """
         GIVEN:
@@ -353,7 +353,7 @@ class TestParsePdf:
             - Text is extracted
         """
         tesseract_parser.parse(
-            tesseract_samples_dir / "multi-page-digital.pdf",
+            multi_page_digital_pdf_file,
             "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,
-        tesseract_samples_dir: Path,
+        with_form_pdf_file: Path,
     ) -> None:
         tesseract_parser.parse(
-            tesseract_samples_dir / "with-form.pdf",
+            with_form_pdf_file,
             "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,
-        tesseract_samples_dir: Path,
+        with_form_pdf_file: Path,
     ) -> None:
         tesseract_parser.settings.mode = ModeChoices.REDO
         tesseract_parser.parse(
-            tesseract_samples_dir / "with-form.pdf",
+            with_form_pdf_file,
             "application/pdf",
             produce_archive=False,
         )
@@ -401,11 +401,11 @@ class TestParsePdf:
     def test_with_form_force(
         self,
         tesseract_parser: RasterisedDocumentParser,
-        tesseract_samples_dir: Path,
+        with_form_pdf_file: Path,
     ) -> None:
         tesseract_parser.settings.mode = ModeChoices.FORCE
         tesseract_parser.parse(
-            tesseract_samples_dir / "with-form.pdf",
+            with_form_pdf_file,
             "application/pdf",
         )
         assert_ordered_substrings(
@@ -446,7 +446,7 @@ class TestParsePdf:
         self,
         mocker: MockerFixture,
         tesseract_parser: RasterisedDocumentParser,
-        tesseract_samples_dir: Path,
+        simple_digital_pdf_file: Path,
     ) -> None:
         mocker.patch(
             "ocrmypdf.ocr",
@@ -454,7 +454,7 @@ class TestParsePdf:
         )
         with pytest.raises(ParseError):
             tesseract_parser.parse(
-                tesseract_samples_dir / "simple-digital.pdf",
+                simple_digital_pdf_file,
                 "application/pdf",
             )
 
@@ -530,10 +530,10 @@ class TestParseMultiPage:
     def test_multi_page_digital(
         self,
         tesseract_parser: RasterisedDocumentParser,
-        tesseract_samples_dir: Path,
+        multi_page_digital_pdf_file: Path,
     ) -> None:
         tesseract_parser.parse(
-            tesseract_samples_dir / "multi-page-digital.pdf",
+            multi_page_digital_pdf_file,
             "application/pdf",
         )
         assert tesseract_parser.archive_path is not None
@@ -557,12 +557,12 @@ class TestParseMultiPage:
         self,
         mode: str,
         tesseract_parser: RasterisedDocumentParser,
-        tesseract_samples_dir: Path,
+        multi_page_digital_pdf_file: Path,
     ) -> None:
         tesseract_parser.settings.pages = 2
         tesseract_parser.settings.mode = mode
         tesseract_parser.parse(
-            tesseract_samples_dir / "multi-page-digital.pdf",
+            multi_page_digital_pdf_file,
             "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,
-        tesseract_samples_dir: Path,
+        multi_page_images_pdf_file: Path,
     ) -> None:
         tesseract_parser.settings.mode = ModeChoices.AUTO
         tesseract_parser.parse(
-            tesseract_samples_dir / "multi-page-images.pdf",
+            multi_page_images_pdf_file,
             "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,
-        tesseract_samples_dir: Path,
+        multi_page_images_pdf_file: Path,
     ) -> None:
         """
         GIVEN:
@@ -609,7 +609,7 @@ class TestParseMultiPage:
         tesseract_parser.settings.pages = 2
         tesseract_parser.settings.mode = ModeChoices.REDO
         tesseract_parser.parse(
-            tesseract_samples_dir / "multi-page-images.pdf",
+            multi_page_images_pdf_file,
             "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,
-        tesseract_samples_dir: Path,
+        multi_page_images_pdf_file: Path,
     ) -> None:
         """
         GIVEN:
@@ -637,7 +637,7 @@ class TestParseMultiPage:
         tesseract_parser.settings.pages = 1
         tesseract_parser.settings.mode = ModeChoices.FORCE
         tesseract_parser.parse(
-            tesseract_samples_dir / "multi-page-images.pdf",
+            multi_page_images_pdf_file,
             "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,
-        tesseract_samples_dir: Path,
+        multi_page_digital_pdf_file: Path,
     ) -> None:
         """
         GIVEN:
@@ -747,7 +747,7 @@ class TestSkipArchive:
         """
         tesseract_parser.settings.mode = ModeChoices.AUTO
         tesseract_parser.parse(
-            tesseract_samples_dir / "multi-page-digital.pdf",
+            multi_page_digital_pdf_file,
             "application/pdf",
             produce_archive=False,
         )
@@ -762,7 +762,7 @@ class TestSkipArchive:
     def test_skip_noarchive_image_only_creates_archive(
         self,
         tesseract_parser: RasterisedDocumentParser,
-        tesseract_samples_dir: Path,
+        multi_page_images_pdf_file: Path,
     ) -> None:
         """
         GIVEN:
@@ -775,7 +775,7 @@ class TestSkipArchive:
         """
         tesseract_parser.settings.mode = ModeChoices.AUTO
         tesseract_parser.parse(
-            tesseract_samples_dir / "multi-page-images.pdf",
+            multi_page_images_pdf_file,
             "application/pdf",
         )
         assert tesseract_parser.archive_path is not None
@@ -787,29 +787,29 @@ class TestSkipArchive:
         )
 
     @pytest.mark.parametrize(
-        ("produce_archive", "filename", "expect_archive"),
+        ("produce_archive", "sample_fixture", "expect_archive"),
         [
             pytest.param(
                 True,
-                "multi-page-digital.pdf",
+                "multi_page_digital_pdf_file",
                 True,
                 id="produce-archive-with-text",
             ),
             pytest.param(
                 True,
-                "multi-page-images.pdf",
+                "multi_page_images_pdf_file",
                 True,
                 id="produce-archive-no-text",
             ),
             pytest.param(
                 False,
-                "multi-page-digital.pdf",
+                "multi_page_digital_pdf_file",
                 False,
                 id="no-archive-with-text-layer",
             ),
             pytest.param(
                 False,
-                "multi-page-images.pdf",
+                "multi_page_images_pdf_file",
                 False,
                 id="no-archive-no-text-layer",
             ),
@@ -818,10 +818,10 @@ class TestSkipArchive:
     def test_produce_archive_flag(
         self,
         produce_archive: bool,  # noqa: FBT001
-        filename: str,
+        sample_fixture: str,
         expect_archive: bool,  # noqa: FBT001
         tesseract_parser: RasterisedDocumentParser,
-        tesseract_samples_dir: Path,
+        request: pytest.FixtureRequest,
     ) -> None:
         """
         GIVEN:
@@ -834,8 +834,9 @@ class TestSkipArchive:
             - Text is always extracted
         """
         tesseract_parser.settings.mode = ModeChoices.AUTO
+        sample = request.getfixturevalue(sample_fixture)
         tesseract_parser.parse(
-            tesseract_samples_dir / filename,
+            sample,
             "application/pdf",
             produce_archive=produce_archive,
         )
@@ -852,7 +853,7 @@ class TestSkipArchive:
         self,
         mocker: MockerFixture,
         tesseract_parser: RasterisedDocumentParser,
-        tesseract_samples_dir: Path,
+        simple_digital_pdf_file: Path,
     ) -> None:
         """
         GIVEN:
@@ -868,7 +869,7 @@ class TestSkipArchive:
         tesseract_parser.settings.mode = ModeChoices.AUTO
         mock_ocr = mocker.patch("ocrmypdf.ocr")
         tesseract_parser.parse(
-            tesseract_samples_dir / "simple-digital.pdf",
+            simple_digital_pdf_file,
             "application/pdf",
             produce_archive=False,
         )
@@ -907,7 +908,7 @@ class TestSkipArchive:
     def test_tagged_pdf_produces_pdfa_archive_without_ocr(
         self,
         tesseract_parser: RasterisedDocumentParser,
-        tesseract_samples_dir: Path,
+        simple_digital_pdf_file: Path,
     ) -> None:
         """
         GIVEN:
@@ -922,7 +923,7 @@ class TestSkipArchive:
         """
         tesseract_parser.settings.mode = ModeChoices.AUTO
         tesseract_parser.parse(
-            tesseract_samples_dir / "simple-digital.pdf",
+            simple_digital_pdf_file,
             "application/pdf",
             produce_archive=True,
         )

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

@@ -1,19 +0,0 @@
- <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

@@ -16,8 +16,6 @@ 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 +53,11 @@ class TestReadFileHandleUnicodeErrors:
 
 
 class TestIsTaggedPdf:
-    def test_tagged_pdf_returns_true(self) -> None:
-        assert is_tagged_pdf(SAMPLES / "simple-digital.pdf") is True
+    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_untagged_pdf_returns_false(self) -> None:
-        assert is_tagged_pdf(SAMPLES / "multi-page-images.pdf") is False
+    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_nonexistent_path_returns_false(self) -> None:
         assert is_tagged_pdf(Path("/nonexistent/file.pdf")) is False

src/paperless_testing/samples.py

@@ -0,0 +1,48 @@
+"""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)