diff --git a/pyproject.toml b/pyproject.toml
index 5967a6fda..401f0bdb0 100644
--- a/pyproject.toml
+++ b/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
diff --git a/src-ui/e2e/backend.py b/src-ui/e2e/backend.py
index e706b0f8a..0a4ed8fa3 100644
--- a/src-ui/e2e/backend.py
+++ b/src-ui/e2e/backend.py
@@ -134,7 +134,9 @@ def seed_database() -> None:
originals.mkdir(parents=True)
thumbnails = Path(os.environ["PAPERLESS_MEDIA_ROOT"]) / "documents" / "thumbnails"
thumbnails.mkdir(parents=True)
- sample_pdf = SOURCE_ROOT / "documents" / "tests" / "samples" / "simple.pdf"
+ sample_pdf = (
+ SOURCE_ROOT / "paperless_testing" / "sample_files" / "simple-digital.pdf"
+ )
for document in documents:
shutil.copyfile(sample_pdf, originals / document.filename)
shutil.copyfile(
diff --git a/src/conftest.py b/src/conftest.py
index 781cdff61..91f5635a2 100644
--- a/src/conftest.py
+++ b/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
diff --git a/src/documents/tests/conftest.py b/src/documents/tests/conftest.py
index 567342dcc..c41f200a2 100644
--- a/src/documents/tests/conftest.py
+++ b/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",
)
diff --git a/src/documents/tests/examples/no-text.png b/src/documents/tests/examples/no-text.png
deleted file mode 100644
index e78b22bfb..000000000
Binary files a/src/documents/tests/examples/no-text.png and /dev/null differ
diff --git a/src/documents/tests/samples/barcodes/barcode-128-asn-too-large.pdf b/src/documents/tests/samples/barcodes/barcode-128-asn-too-large.pdf
deleted file mode 100644
index 2d190c876..000000000
Binary files a/src/documents/tests/samples/barcodes/barcode-128-asn-too-large.pdf and /dev/null differ
diff --git a/src/documents/tests/samples/documents/archive/0000001.pdf b/src/documents/tests/samples/documents/archive/0000001.pdf
deleted file mode 100644
index ea08363bf..000000000
Binary files a/src/documents/tests/samples/documents/archive/0000001.pdf and /dev/null differ
diff --git a/src/documents/tests/samples/documents/originals/0000001.pdf b/src/documents/tests/samples/documents/originals/0000001.pdf
deleted file mode 100644
index e450de482..000000000
Binary files a/src/documents/tests/samples/documents/originals/0000001.pdf and /dev/null differ
diff --git a/src/documents/tests/samples/documents/originals/0000002.pdf b/src/documents/tests/samples/documents/originals/0000002.pdf
deleted file mode 100644
index 5e75266ca..000000000
Binary files a/src/documents/tests/samples/documents/originals/0000002.pdf and /dev/null differ
diff --git a/src/documents/tests/samples/documents/originals/0000003.pdf b/src/documents/tests/samples/documents/originals/0000003.pdf
deleted file mode 100644
index afbeef5c8..000000000
Binary files a/src/documents/tests/samples/documents/originals/0000003.pdf and /dev/null differ
diff --git a/src/documents/tests/samples/documents/thumbnails/0000002.webp b/src/documents/tests/samples/documents/thumbnails/0000002.webp
deleted file mode 100644
index a7ff623b2..000000000
Binary files a/src/documents/tests/samples/documents/thumbnails/0000002.webp and /dev/null differ
diff --git a/src/documents/tests/samples/documents/thumbnails/0000003.webp b/src/documents/tests/samples/documents/thumbnails/0000003.webp
deleted file mode 100644
index a7ff623b2..000000000
Binary files a/src/documents/tests/samples/documents/thumbnails/0000003.webp and /dev/null differ
diff --git a/src/documents/tests/samples/documents/thumbnails/0000004.webp b/src/documents/tests/samples/documents/thumbnails/0000004.webp
deleted file mode 100644
index a7ff623b2..000000000
Binary files a/src/documents/tests/samples/documents/thumbnails/0000004.webp and /dev/null differ
diff --git a/src/documents/tests/samples/simple.pdf b/src/documents/tests/samples/simple.pdf
deleted file mode 100644
index e450de482..000000000
Binary files a/src/documents/tests/samples/simple.pdf and /dev/null differ
diff --git a/src/documents/tests/samples/simple.txt b/src/documents/tests/samples/simple.txt
deleted file mode 100644
index 6de7b8c69..000000000
--- a/src/documents/tests/samples/simple.txt
+++ /dev/null
@@ -1 +0,0 @@
-This is a test file.
diff --git a/src/documents/tests/test_api_bulk_download.py b/src/documents/tests/test_api_bulk_download.py
index b031a5105..0f8dc7afe 100644
--- a/src/documents/tests/test_api_bulk_download.py
+++ b/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)
diff --git a/src/documents/tests/test_api_documents.py b/src/documents/tests/test_api_documents.py
index c37a8d3ee..eeb1ab59a 100644
--- a/src/documents/tests/test_api_documents.py
+++ b/src/documents/tests/test_api_documents.py
@@ -57,6 +57,8 @@ 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):
@@ -1917,7 +1919,11 @@ 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},
@@ -1945,7 +1951,7 @@ 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",
)
@@ -1974,7 +1980,7 @@ 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 = (
(
@@ -2050,7 +2056,7 @@ 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},
@@ -2063,7 +2069,11 @@ 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/",
{
@@ -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/",
{"documenst": f},
@@ -2122,7 +2132,7 @@ 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"},
@@ -2142,7 +2152,7 @@ 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},
@@ -2161,7 +2171,7 @@ 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},
@@ -2176,7 +2186,7 @@ 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},
@@ -2195,7 +2205,7 @@ 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},
@@ -2210,7 +2220,7 @@ 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},
@@ -2229,7 +2239,7 @@ 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},
@@ -2245,7 +2255,7 @@ 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]},
@@ -2266,7 +2276,7 @@ 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]},
@@ -2290,7 +2300,7 @@ 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},
@@ -2306,7 +2316,11 @@ 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},
@@ -2333,7 +2347,11 @@ 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/",
{
@@ -2388,7 +2406,7 @@ 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/",
{
@@ -2429,7 +2447,11 @@ 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/",
{
@@ -2478,7 +2500,7 @@ 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/",
@@ -2536,7 +2558,7 @@ 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},
@@ -2575,14 +2597,8 @@ 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)
@@ -2615,7 +2631,7 @@ 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)
@@ -4381,8 +4397,8 @@ 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)
diff --git a/src/documents/tests/test_api_email.py b/src/documents/tests/test_api_email.py
index d26f26d85..c0a3fc9ac 100644
--- a/src/documents/tests/test_api_email.py
+++ b/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,
diff --git a/src/documents/tests/test_barcodes.py b/src/documents/tests/test_barcodes.py
index 36322d2ab..9dc8f2353 100644
--- a/src/documents/tests/test_barcodes.py
+++ b/src/documents/tests/test_barcodes.py
@@ -169,7 +169,7 @@ 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()
@@ -461,7 +461,7 @@ 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:
diff --git a/src/documents/tests/test_bulk_edit.py b/src/documents/tests/test_bulk_edit.py
index 9688b5cad..b341f5744 100644
--- a/src/documents/tests/test_bulk_edit.py
+++ b/src/documents/tests/test_bulk_edit.py
@@ -29,6 +29,9 @@ 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):
@@ -706,47 +709,27 @@ 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(
@@ -780,11 +763,7 @@ 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(
diff --git a/src/documents/tests/test_consumer.py b/src/documents/tests/test_consumer.py
index b9afd61a0..7c607e1e3 100644
--- a/src/documents/tests/test_consumer.py
+++ b/src/documents/tests/test_consumer.py
@@ -39,6 +39,9 @@ from paperless_testing.factories import TagFactory
from paperless_testing.factories import UserFactory
from paperless_testing.fakes.progress import FakeProgressManager
from paperless_testing.permissions import grant_object
+from paperless_testing.samples import MULTI_PAGE_DIGITAL_PDF
+from paperless_testing.samples import MULTI_PAGE_IMAGES_PDF
+from paperless_testing.samples import SIMPLE_DIGITAL_PDF
class _BaseNewStyleParser:
@@ -115,9 +118,7 @@ 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"
@@ -203,33 +204,19 @@ 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
@@ -1124,7 +1111,7 @@ 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(
@@ -1665,13 +1652,7 @@ 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)
diff --git a/src/documents/tests/test_double_sided.py b/src/documents/tests/test_double_sided.py
index 7ea806e93..c35b82486 100644
--- a/src/documents/tests/test_double_sided.py
+++ b/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)
diff --git a/src/documents/tests/test_management.py b/src/documents/tests/test_management.py
index 19ab4e269..0fe5d7eb5 100644
--- a/src/documents/tests/test_management.py
+++ b/src/documents/tests/test_management.py
@@ -23,8 +23,9 @@ from documents.tasks import update_document_content_maybe_archive_file
from paperless_testing.assertions import FileSystemAssertsMixin
from paperless_testing.dirs import DirectoriesMixin
from paperless_testing.factories import DocumentFactory
+from paperless_testing.samples import SIMPLE_DIGITAL_PDF
-sample_file: Path = Path(__file__).parent / "samples" / "simple.pdf"
+sample_file: Path = SIMPLE_DIGITAL_PDF
@pytest.mark.management
diff --git a/src/documents/tests/test_management_exporter.py b/src/documents/tests/test_management_exporter.py
index b4cee95da..ec6a21b77 100644
--- a/src/documents/tests/test_management_exporter.py
+++ b/src/documents/tests/test_management_exporter.py
@@ -59,6 +59,7 @@ from paperless_testing.dirs import paperless_environment
from paperless_testing.factories import DocumentBarcodeFactory
from paperless_testing.factories import DocumentFactory
from paperless_testing.permissions import grant_object
+from paperless_testing.samples import install_document_samples
@pytest.mark.management
@@ -204,10 +205,7 @@ 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()
@@ -311,10 +309,7 @@ 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}",
@@ -323,10 +318,7 @@ 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",
@@ -425,10 +417,7 @@ 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")
@@ -464,10 +453,7 @@ 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()
@@ -494,10 +480,7 @@ 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()
@@ -529,10 +512,7 @@ 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")
@@ -574,10 +554,7 @@ 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"]
@@ -606,10 +583,7 @@ 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"]
@@ -645,10 +619,7 @@ 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"
@@ -744,10 +715,7 @@ 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
@@ -790,10 +758,7 @@ 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
@@ -838,10 +803,7 @@ 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(
def _export_import_barcodes(self, *, split_manifest: bool) -> 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")
DocumentBarcodeFactory(document=self.d1, value="https://example.com")
DocumentBarcodeFactory(document=self.d2, page=2, value="DE8937")
@@ -905,10 +864,7 @@ 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)
@@ -935,10 +891,7 @@ 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)
@@ -965,10 +918,7 @@ 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()
@@ -1005,10 +955,7 @@ 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,
@@ -1028,10 +975,7 @@ 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()
@@ -1075,10 +1019,7 @@ 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)
diff --git a/src/documents/tests/test_management_thumbnails.py b/src/documents/tests/test_management_thumbnails.py
index 4da0caf5a..595aedc64 100644
--- a/src/documents/tests/test_management_thumbnails.py
+++ b/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,
)
diff --git a/src/documents/tests/test_pdf_ops.py b/src/documents/tests/test_pdf_ops.py
index eb4cf7005..632ebc927 100644
--- a/src/documents/tests/test_pdf_ops.py
+++ b/src/documents/tests/test_pdf_ops.py
@@ -15,10 +15,11 @@ import pytest
from documents import pdf_ops
from documents.pdf_ops import PageSpec
+from paperless_testing.samples import MULTI_PAGE_DIGITAL_PDF
SRC_ROOT = Path(__file__).parents[2]
SAMPLES = Path(__file__).parent / "samples"
-THREE_PAGES = SAMPLES / "documents" / "originals" / "0000002.pdf"
+THREE_PAGES = MULTI_PAGE_DIGITAL_PDF
TWELVE_PAGES = SAMPLES / "barcodes" / "split-by-asn-2.pdf"
ENCRYPTED = SAMPLES / "password-is-test.pdf"
SIGNED = SRC_ROOT / "paperless" / "tests" / "samples" / "tesseract" / "signed.pdf"
diff --git a/src/documents/tests/test_tasks.py b/src/documents/tests/test_tasks.py
index 50d16233b..a5def0944 100644
--- a/src/documents/tests/test_tasks.py
+++ b/src/documents/tests/test_tasks.py
@@ -21,6 +21,7 @@ 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
@@ -229,20 +230,12 @@ 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(
@@ -270,11 +263,7 @@ 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(
@@ -290,14 +279,7 @@ class TestUpdateContent(DirectoriesMixin, TestCase):
def _create_root_with_version(self) -> tuple[Document, Document]:
sample1 = self.dirs.scratch_dir / "sample.pdf"
- shutil.copy(
- Path(__file__).parent
- / "samples"
- / "documents"
- / "originals"
- / "0000001.pdf",
- sample1,
- )
+ shutil.copy(SIMPLE_DIGITAL_PDF, sample1)
root = DocumentFactory(content="root content", mime_type="application/pdf")
version = DocumentFactory(
content="my document",
diff --git a/src/documents/tests/test_workflows.py b/src/documents/tests/test_workflows.py
index 506fa6872..820882b49 100644
--- a/src/documents/tests/test_workflows.py
+++ b/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()
@@ -2067,7 +2067,7 @@ 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(
@@ -3053,7 +3053,7 @@ 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])
@@ -3117,7 +3117,7 @@ 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])
@@ -3266,7 +3266,7 @@ class TestWorkflows(
w.save()
test_file = shutil.copy(
- self.SAMPLE_DIR / "simple.pdf",
+ self.SIMPLE_PDF,
self.dirs.scratch_dir / "simple.pdf",
)
@@ -3390,7 +3390,7 @@ class TestWorkflows(
w.save()
test_file = shutil.copy(
- self.SAMPLE_DIR / "simple.pdf",
+ self.SIMPLE_PDF,
self.dirs.scratch_dir / "simple.pdf",
)
@@ -3540,7 +3540,7 @@ 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",
)
@@ -3640,7 +3640,7 @@ class TestWorkflows(
# move the file
test_file = shutil.copy(
- self.SAMPLE_DIR / "simple.pdf",
+ self.SIMPLE_PDF,
self.dirs.scratch_dir / "simple.pdf",
)
@@ -3748,7 +3748,7 @@ 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)
@@ -3959,7 +3959,7 @@ class TestWorkflows(
w.save()
test_file = shutil.copy(
- self.SAMPLE_DIR / "simple.pdf",
+ self.SIMPLE_PDF,
self.dirs.scratch_dir / "simple.pdf",
)
@@ -4080,7 +4080,7 @@ class TestWorkflows(
w.save()
test_file = shutil.copy(
- self.SAMPLE_DIR / "simple.pdf",
+ self.SIMPLE_PDF,
self.dirs.scratch_dir / "simple.pdf",
)
@@ -4431,7 +4431,7 @@ class TestWorkflows(
w.save()
test_file = shutil.copy(
- self.SAMPLE_DIR / "simple.pdf",
+ self.SIMPLE_PDF,
self.dirs.scratch_dir / "simple.pdf",
)
@@ -4879,7 +4879,7 @@ class TestWorkflows(
w.save()
test_file = shutil.copy(
- self.SAMPLE_DIR / "simple.pdf",
+ self.SIMPLE_PDF,
self.dirs.scratch_dir / "simple.pdf",
)
@@ -5071,7 +5071,7 @@ 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)
@@ -5135,7 +5135,7 @@ 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)
@@ -5639,7 +5639,7 @@ class TestDateWorkflowLocalization(
)
test_file = shutil.copy(
- self.SAMPLE_DIR / "simple.pdf",
+ self.SIMPLE_PDF,
tmp_path / "simple.pdf",
)
@@ -5706,7 +5706,7 @@ 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()
@@ -5924,7 +5924,7 @@ class TestApplyAISuggestionsWorkflowAction(
)
test_file = shutil.copy(
- self.SAMPLE_DIR / "simple.pdf",
+ self.SIMPLE_PDF,
self.dirs.scratch_dir / "simple.pdf",
)
diff --git a/src/documents/tests/utils.py b/src/documents/tests/utils.py
index 63e907855..18769dfc9 100644
--- a/src/documents/tests/utils.py
+++ b/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
diff --git a/src/paperless/tests/parsers/conftest.py b/src/paperless/tests/parsers/conftest.py
index 343e9ea8a..5e834e959 100644
--- a/src/paperless/tests/parsers/conftest.py
+++ b/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.
@@ -480,6 +456,18 @@ def simple_png_file(tesseract_samples_dir: Path) -> Path:
return tesseract_samples_dir / "simple.png"
+@pytest.fixture(scope="session")
+def rotated_pdf_file(tesseract_samples_dir: Path) -> Path:
+ """Path to a landscape (rotated) PDF sample file.
+
+ Returns
+ -------
+ Path
+ Absolute path to ``tesseract/rotated.pdf``.
+ """
+ return tesseract_samples_dir / "rotated.pdf"
+
+
# ------------------------------------------------------------------
# Tesseract parser instance and settings helpers
# ------------------------------------------------------------------
diff --git a/src/paperless/tests/parsers/test_tesseract_parser.py b/src/paperless/tests/parsers/test_tesseract_parser.py
index f057ad086..a44d23bec 100644
--- a/src/paperless/tests/parsers/test_tesseract_parser.py
+++ b/src/paperless/tests/parsers/test_tesseract_parser.py
@@ -161,11 +161,11 @@ 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
@@ -188,7 +188,7 @@ class TestGetPageCount:
self,
mocker: MockerFixture,
tesseract_parser: RasterisedDocumentParser,
- tesseract_samples_dir: Path,
+ simple_digital_pdf_file: Path,
caplog,
) -> None:
"""
@@ -204,7 +204,7 @@ 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
@@ -273,26 +273,26 @@ 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()
@pytest.mark.parametrize(
- ("filename", "expected_height"),
+ ("sample_fixture", "expected_height"),
[
- pytest.param("simple-digital.pdf", 647, id="portrait-letter"),
- pytest.param("rotated.pdf", 386, id="landscape"),
+ pytest.param("simple_digital_pdf_file", 647, id="portrait-letter"),
+ pytest.param("rotated_pdf_file", 386, id="landscape"),
],
)
def test_thumbnail_is_correct_format_and_size(
self,
tesseract_parser: RasterisedDocumentParser,
- tesseract_samples_dir: Path,
- filename: str,
+ request: pytest.FixtureRequest,
+ sample_fixture: str,
expected_height: int,
) -> None:
"""
@@ -304,7 +304,7 @@ class TestGetThumbnail:
- A 500px wide WebP keeping the page's aspect ratio
"""
thumb = tesseract_parser.get_thumbnail(
- tesseract_samples_dir / filename,
+ request.getfixturevalue(sample_fixture),
"application/pdf",
)
with Image.open(thumb) as im:
@@ -316,7 +316,7 @@ class TestGetThumbnail:
self,
mocker: MockerFixture,
tesseract_parser: RasterisedDocumentParser,
- tesseract_samples_dir: Path,
+ simple_digital_pdf_file: Path,
) -> None:
"""
GIVEN:
@@ -326,7 +326,7 @@ class TestGetThumbnail:
THEN:
- The PDF is repaired with qpdf and a real thumbnail is rendered
"""
- original = tesseract_samples_dir / "simple-digital.pdf"
+ original = simple_digital_pdf_file
def _fail_on_original(in_path: Path, out_path: Path, **kwargs) -> None:
if in_path == original:
@@ -368,11 +368,11 @@ class TestExtractText:
def test_extract_text_from_digital_pdf(
self,
tesseract_parser: RasterisedDocumentParser,
- 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()
@@ -387,7 +387,7 @@ class TestParsePdf:
def test_simple_digital_creates_archive(
self,
tesseract_parser: RasterisedDocumentParser,
- tesseract_samples_dir: Path,
+ multi_page_digital_pdf_file: Path,
) -> None:
"""
GIVEN:
@@ -401,7 +401,7 @@ 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
@@ -416,10 +416,10 @@ 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
@@ -432,11 +432,11 @@ 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,
)
@@ -449,11 +449,11 @@ 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(
@@ -494,7 +494,7 @@ class TestParsePdf:
self,
mocker: MockerFixture,
tesseract_parser: RasterisedDocumentParser,
- tesseract_samples_dir: Path,
+ simple_digital_pdf_file: Path,
) -> None:
mocker.patch(
"ocrmypdf.ocr",
@@ -502,7 +502,7 @@ class TestParsePdf:
)
with pytest.raises(ParseError):
tesseract_parser.parse(
- tesseract_samples_dir / "simple-digital.pdf",
+ simple_digital_pdf_file,
"application/pdf",
)
@@ -578,10 +578,10 @@ 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
@@ -605,12 +605,12 @@ 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
@@ -624,11 +624,11 @@ 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
@@ -642,7 +642,7 @@ 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:
@@ -657,7 +657,7 @@ 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
@@ -670,7 +670,7 @@ 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:
@@ -685,7 +685,7 @@ 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
@@ -781,7 +781,7 @@ 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:
@@ -795,7 +795,7 @@ 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,
)
@@ -810,7 +810,7 @@ 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:
@@ -823,7 +823,7 @@ 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
@@ -835,29 +835,29 @@ 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",
),
@@ -866,10 +866,10 @@ 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:
@@ -882,8 +882,9 @@ 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,
)
@@ -900,7 +901,7 @@ class TestSkipArchive:
self,
mocker: MockerFixture,
tesseract_parser: RasterisedDocumentParser,
- tesseract_samples_dir: Path,
+ simple_digital_pdf_file: Path,
) -> None:
"""
GIVEN:
@@ -916,7 +917,7 @@ 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,
)
@@ -955,7 +956,7 @@ 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:
@@ -970,7 +971,7 @@ 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,
)
diff --git a/src/paperless/tests/samples/mail/sample.html b/src/paperless/tests/samples/mail/sample.html
deleted file mode 100644
index 9d535dba6..000000000
--- a/src/paperless/tests/samples/mail/sample.html
+++ /dev/null
@@ -1,19 +0,0 @@
-
-
-
-
-
- Some Text
-
- 
- 
-
-
- and an embedded image.
-
- Paragraph unchanged.
-
-
-
diff --git a/src/paperless/tests/samples/mail/sample.html.pdf b/src/paperless/tests/samples/mail/sample.html.pdf
deleted file mode 100644
index 24c2dbf87..000000000
Binary files a/src/paperless/tests/samples/mail/sample.html.pdf and /dev/null differ
diff --git a/src/paperless/tests/samples/mail/sample.html.pdf.webp b/src/paperless/tests/samples/mail/sample.html.pdf.webp
deleted file mode 100644
index 534157660..000000000
Binary files a/src/paperless/tests/samples/mail/sample.html.pdf.webp and /dev/null differ
diff --git a/src/paperless/tests/samples/mail/sample.png b/src/paperless/tests/samples/mail/sample.png
deleted file mode 100644
index 162aadad0..000000000
Binary files a/src/paperless/tests/samples/mail/sample.png and /dev/null differ
diff --git a/src/paperless/tests/samples/tesseract/no-text-alpha.png b/src/paperless/tests/samples/tesseract/no-text-alpha.png
deleted file mode 100644
index e78b22bfb..000000000
Binary files a/src/paperless/tests/samples/tesseract/no-text-alpha.png and /dev/null differ
diff --git a/src/paperless/tests/test_parser_utils.py b/src/paperless/tests/test_parser_utils.py
index 7bae1f78d..ed20a024b 100644
--- a/src/paperless/tests/test_parser_utils.py
+++ b/src/paperless/tests/test_parser_utils.py
@@ -18,8 +18,6 @@ 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:
@@ -57,11 +55,11 @@ 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
@@ -95,7 +93,7 @@ class TestGetPdfFirstPageSizePoints:
pdf.save(path)
return path
- def test_letter_sample(self) -> None:
+ def test_letter_sample(self, simple_digital_pdf_file: Path) -> None:
"""
GIVEN:
- A US Letter sample PDF with no CropBox and no rotation
@@ -104,7 +102,7 @@ class TestGetPdfFirstPageSizePoints:
THEN:
- The MediaBox size in points is returned
"""
- assert get_pdf_first_page_size_points(SAMPLES / "simple-digital.pdf") == (
+ assert get_pdf_first_page_size_points(simple_digital_pdf_file) == (
612.0,
792.0,
)
@@ -199,6 +197,7 @@ class TestGetPdfFirstPageSizePoints:
def test_pdfinfo_not_installed_returns_none(
self,
mocker: MockerFixture,
+ simple_digital_pdf_file: Path,
) -> None:
"""
GIVEN:
@@ -209,7 +208,7 @@ class TestGetPdfFirstPageSizePoints:
- None is returned and nothing is raised
"""
mocker.patch("subprocess.run", side_effect=FileNotFoundError("pdfinfo"))
- assert get_pdf_first_page_size_points(SAMPLES / "simple-digital.pdf") is None
+ assert get_pdf_first_page_size_points(simple_digital_pdf_file) is None
def test_degenerate_box_returns_none(self, tmp_path: Path) -> None:
"""
@@ -251,7 +250,7 @@ class TestGetPdfFirstPageSizePoints:
bad.write_bytes(b"not a pdf")
assert get_pdf_first_page_size_points(bad) is None
- def test_encrypted_pdf_returns_none(self) -> None:
+ def test_encrypted_pdf_returns_none(self, parser_samples_dir: Path) -> None:
"""
GIVEN:
- A password protected PDF
@@ -260,7 +259,8 @@ class TestGetPdfFirstPageSizePoints:
THEN:
- None is returned and nothing is raised
"""
- assert get_pdf_first_page_size_points(SAMPLES / "encrypted.pdf") is None
+ encrypted = parser_samples_dir / "tesseract" / "encrypted.pdf"
+ assert get_pdf_first_page_size_points(encrypted) is None
class TestPostProcessText:
diff --git a/src/paperless/tests/samples/tesseract/multi-page-digital.pdf b/src/paperless_testing/sample_files/multi-page-digital.pdf
similarity index 100%
rename from src/paperless/tests/samples/tesseract/multi-page-digital.pdf
rename to src/paperless_testing/sample_files/multi-page-digital.pdf
diff --git a/src/paperless/tests/samples/tesseract/multi-page-images.pdf b/src/paperless_testing/sample_files/multi-page-images.pdf
similarity index 100%
rename from src/paperless/tests/samples/tesseract/multi-page-images.pdf
rename to src/paperless_testing/sample_files/multi-page-images.pdf
diff --git a/src/paperless/tests/samples/tesseract/simple-digital.pdf b/src/paperless_testing/sample_files/simple-digital.pdf
similarity index 100%
rename from src/paperless/tests/samples/tesseract/simple-digital.pdf
rename to src/paperless_testing/sample_files/simple-digital.pdf
diff --git a/src/documents/tests/samples/documents/thumbnails/0000001.webp b/src/paperless_testing/sample_files/thumbnail.webp
similarity index 100%
rename from src/documents/tests/samples/documents/thumbnails/0000001.webp
rename to src/paperless_testing/sample_files/thumbnail.webp
diff --git a/src/paperless/tests/samples/tesseract/with-form.pdf b/src/paperless_testing/sample_files/with-form.pdf
similarity index 100%
rename from src/paperless/tests/samples/tesseract/with-form.pdf
rename to src/paperless_testing/sample_files/with-form.pdf
diff --git a/src/paperless_testing/samples.py b/src/paperless_testing/samples.py
new file mode 100644
index 000000000..2e823041a
--- /dev/null
+++ b/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(/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)