paradizelost/paperless-ngx
1
0
Fork 0
mirror of https://github.com/paperless-ngx/paperless-ngx.git synced 2025-09-22 00:52:42 -05:00
Code Issues Packages Projects Releases Wiki Activity

Merge branch 'dev' into feature-ai

Browse Source
This commit is contained in:
shamoon
2025-08-17 07:49:01 -07:00
committed by GitHub
parent 867c7d9e62 521fd1c957
commit 4c719948d9
123 changed files with 42275 additions and 39408 deletions
Download Patch File Download Diff File Expand all files Collapse all files

4
src/documents/tests/samples/malicious.svg Normal file
View File

@@ -0,0 +1,4 @@
<svg xmlns="http://www.w3.org/2000/svg" width="100" height="100">
<text x="10" y="20">Hello</text>
<script>alert('XSS')</script>
</svg>
Side by Side

After

Width:  |  Height:  |  Size: 140 B

70
src/documents/tests/test_api_app_config.py
View File

@@ -3,6 +3,7 @@ from pathlib import Path
from unittest.mock import patch
from django.contrib.auth.models import User
from django.core.files.uploadedfile import SimpleUploadedFile
from rest_framework import status
from rest_framework.test import APITestCase
@@ -157,25 +158,66 @@ class TestApiAppConfig(DirectoriesMixin, APITestCase):
THEN:
- old app_logo file is deleted
"""
with (Path(__file__).parent / "samples" / "simple.jpg").open("rb") as f:
self.client.patch(
f"{self.ENDPOINT}1/",
{
"app_logo": f,
},
)
admin = User.objects.create_superuser(username="admin")
self.client.force_login(user=admin)
response = self.client.get("/logo/")
self.assertEqual(response.status_code, status.HTTP_404_NOT_FOUND)
self.client.patch(
f"{self.ENDPOINT}1/",
{
"app_logo": SimpleUploadedFile(
name="simple.jpg",
content=(
Path(__file__).parent / "samples" / "simple.jpg"
).read_bytes(),
content_type="image/jpeg",
),
},
)
# Logo exists at /logo/simple.jpg
response = self.client.get("/logo/simple.jpg")
self.assertEqual(response.status_code, status.HTTP_200_OK)
self.assertIn("image/jpeg", response["Content-Type"])
config = ApplicationConfiguration.objects.first()
old_logo = config.app_logo
self.assertTrue(Path(old_logo.path).exists())
with (Path(__file__).parent / "samples" / "simple.png").open("rb") as f:
self.client.patch(
f"{self.ENDPOINT}1/",
{
"app_logo": f,
},
)
self.client.patch(
f"{self.ENDPOINT}1/",
{
"app_logo": SimpleUploadedFile(
name="simple.png",
content=(
Path(__file__).parent / "samples" / "simple.png"
).read_bytes(),
content_type="image/png",
),
},
)
self.assertFalse(Path(old_logo.path).exists())
def test_api_rejects_malicious_svg_logo(self):
"""
GIVEN:
- An SVG logo containing a <script> tag
WHEN:
- Uploaded via PATCH to app config
THEN:
- SVG is rejected with 400
"""
path = Path(__file__).parent / "samples" / "malicious.svg"
with path.open("rb") as f:
response = self.client.patch(
f"{self.ENDPOINT}1/",
{"app_logo": f},
format="multipart",
)
self.assertEqual(response.status_code, status.HTTP_400_BAD_REQUEST)
self.assertIn("disallowed", str(response.data).lower())
def test_create_not_allowed(self):
"""
GIVEN:

196
src/documents/tests/test_file_handling.py
View File

@@ -4,6 +4,7 @@ import tempfile
from pathlib import Path
from unittest import mock
import pytest
from auditlog.context import disable_auditlog
from django.conf import settings
from django.contrib.auth.models import User
@@ -22,6 +23,8 @@ from documents.models import Document
from documents.models import DocumentType
from documents.models import StoragePath
from documents.tasks import empty_trash
from documents.templating.filepath import localize_date
from documents.tests.factories import DocumentFactory
from documents.tests.utils import DirectoriesMixin
from documents.tests.utils import FileSystemAssertsMixin
@@ -1586,3 +1589,196 @@ class TestFilenameGeneration(DirectoriesMixin, TestCase):
generate_filename(doc),
Path("brussels-belgium/some-title-with-special-characters.pdf"),
)
class TestDateLocalization:
"""
Groups all tests related to the `localize_date` function.
"""
TEST_DATE = datetime.date(2023, 10, 26)
TEST_DATETIME = datetime.datetime(
2023,
10,
26,
14,
30,
5,
tzinfo=datetime.timezone.utc,
)
@pytest.mark.parametrize(
"value, format_style, locale_str, expected_output",
[
pytest.param(
TEST_DATE,
"EEEE, MMM d, yyyy",
"en_US",
"Thursday, Oct 26, 2023",
id="date-en_US-custom",
),
pytest.param(
TEST_DATE,
"dd.MM.yyyy",
"de_DE",
"26.10.2023",
id="date-de_DE-custom",
),
# German weekday and month name translation
pytest.param(
TEST_DATE,
"EEEE",
"de_DE",
"Donnerstag",
id="weekday-de_DE",
),
pytest.param(
TEST_DATE,
"MMMM",
"de_DE",
"Oktober",
id="month-de_DE",
),
# French weekday and month name translation
pytest.param(
TEST_DATE,
"EEEE",
"fr_FR",
"jeudi",
id="weekday-fr_FR",
),
pytest.param(
TEST_DATE,
"MMMM",
"fr_FR",
"octobre",
id="month-fr_FR",
),
],
)
def test_localize_date_with_date_objects(
self,
value: datetime.date,
format_style: str,
locale_str: str,
expected_output: str,
):
"""
Tests `localize_date` with `date` objects across different locales and formats.
"""
assert localize_date(value, format_style, locale_str) == expected_output
@pytest.mark.parametrize(
"value, format_style, locale_str, expected_output",
[
pytest.param(
TEST_DATETIME,
"yyyy.MM.dd G 'at' HH:mm:ss zzz",
"en_US",
"2023.10.26 AD at 14:30:05 UTC",
id="datetime-en_US-custom",
),
pytest.param(
TEST_DATETIME,
"dd.MM.yyyy",
"fr_FR",
"26.10.2023",
id="date-fr_FR-custom",
),
# Spanish weekday and month translation
pytest.param(
TEST_DATETIME,
"EEEE",
"es_ES",
"jueves",
id="weekday-es_ES",
),
pytest.param(
TEST_DATETIME,
"MMMM",
"es_ES",
"octubre",
id="month-es_ES",
),
# Italian weekday and month translation
pytest.param(
TEST_DATETIME,
"EEEE",
"it_IT",
"giovedì",
id="weekday-it_IT",
),
pytest.param(
TEST_DATETIME,
"MMMM",
"it_IT",
"ottobre",
id="month-it_IT",
),
],
)
def test_localize_date_with_datetime_objects(
self,
value: datetime.datetime,
format_style: str,
locale_str: str,
expected_output: str,
):
# To handle the non-breaking space in French and other locales
result = localize_date(value, format_style, locale_str)
assert result.replace("\u202f", " ") == expected_output.replace("\u202f", " ")
@pytest.mark.parametrize(
"invalid_value",
[
"2023-10-26",
1698330605,
None,
[],
{},
],
)
def test_localize_date_raises_type_error_for_invalid_input(self, invalid_value):
with pytest.raises(TypeError) as excinfo:
localize_date(invalid_value, "medium", "en_US")
assert f"Unsupported type {type(invalid_value)}" in str(excinfo.value)
def test_localize_date_raises_error_for_invalid_locale(self):
with pytest.raises(ValueError) as excinfo:
localize_date(self.TEST_DATE, "medium", "invalid_locale_code")
assert "Invalid locale identifier" in str(excinfo.value)
@pytest.mark.django_db
@pytest.mark.parametrize(
"filename_format,expected_filename",
[
pytest.param(
"{{title}}_{{ document.created | localize_date('MMMM', 'es_ES')}}",
"My Document_octubre.pdf",
id="spanish_month_name",
),
pytest.param(
"{{title}}_{{ document.created | localize_date('EEEE', 'fr_FR')}}",
"My Document_jeudi.pdf",
id="french_day_of_week",
),
pytest.param(
"{{title}}_{{ document.created | localize_date('dd/MM/yyyy', 'en_GB')}}",
"My Document_26/10/2023.pdf",
id="uk_date_format",
),
],
)
def test_localize_date_path_building(self, filename_format, expected_filename):
document = DocumentFactory.create(
title="My Document",
mime_type="application/pdf",
storage_type=Document.STORAGE_TYPE_UNENCRYPTED,
created=self.TEST_DATE, # 2023-10-26 (which is a Thursday)
)
with override_settings(FILENAME_FORMAT=filename_format):
filename = generate_filename(document)
assert filename == Path(expected_filename)

2
src/documents/tests/test_management_exporter.py
View File

@@ -123,7 +123,7 @@ class TestExportImport(
self.trigger = WorkflowTrigger.objects.create(
type=WorkflowTrigger.WorkflowTriggerType.CONSUMPTION,
sources=[1],
sources=[str(WorkflowTrigger.DocumentSourceChoices.CONSUME_FOLDER.value)],
filter_filename="*",
)
self.action = WorkflowAction.objects.create(assign_title="new title")

21
src/documents/tests/test_management_fuzzy.py
View File

@@ -87,7 +87,7 @@ class TestFuzzyMatchCommand(TestCase):
filename="other_test.pdf",
)
stdout, _ = self.call_command()
self.assertEqual(stdout, "No matches found\n")
self.assertIn("No matches found", stdout)
def test_with_matches(self):
"""
@@ -116,7 +116,7 @@ class TestFuzzyMatchCommand(TestCase):
filename="other_test.pdf",
)
stdout, _ = self.call_command("--processes", "1")
self.assertRegex(stdout, self.MSG_REGEX + "\n")
self.assertRegex(stdout, self.MSG_REGEX)
def test_with_3_matches(self):
"""
@@ -152,11 +152,10 @@ class TestFuzzyMatchCommand(TestCase):
filename="final_test.pdf",
)
stdout, _ = self.call_command()
lines = [x.strip() for x in stdout.split("\n") if len(x.strip())]
lines = [x.strip() for x in stdout.splitlines() if x.strip()]
self.assertEqual(len(lines), 3)
self.assertRegex(lines[0], self.MSG_REGEX)
self.assertRegex(lines[1], self.MSG_REGEX)
self.assertRegex(lines[2], self.MSG_REGEX)
for line in lines:
self.assertRegex(line, self.MSG_REGEX)
def test_document_deletion(self):
"""
@@ -197,14 +196,12 @@ class TestFuzzyMatchCommand(TestCase):
stdout, _ = self.call_command("--delete")
lines = [x.strip() for x in stdout.split("\n") if len(x.strip())]
self.assertEqual(len(lines), 3)
self.assertEqual(
lines[0],
self.assertIn(
"The command is configured to delete documents. Use with caution",
stdout,
)
self.assertRegex(lines[1], self.MSG_REGEX)
self.assertEqual(lines[2], "Deleting 1 documents based on ratio matches")
self.assertRegex(stdout, self.MSG_REGEX)
self.assertIn("Deleting 1 documents based on ratio matches", stdout)
self.assertEqual(Document.objects.count(), 2)
self.assertIsNotNone(Document.objects.get(pk=1))

2
src/documents/tests/test_migration_workflows.py
View File

@@ -104,7 +104,7 @@ class TestReverseMigrateWorkflow(TestMigrations):
trigger = WorkflowTrigger.objects.create(
type=0,
sources=[DocumentSource.ConsumeFolder],
sources=[str(DocumentSource.ConsumeFolder)],
filter_path="*/path/*",
filter_filename="*file*",
)