A community-supported supercharged document management system: scan, index and archive all your documents
Python aiangulararchivingdjangodmsdocument-managementdocument-management-systemllmmachine-learningocroptical-character-recognitionpdf
Development: improve test portability (#12187)
Jan Kleine0bc032a67d64
diff --git a/src/documents/tests/test_api_uisettings.py b/src/documents/tests/test_api_uisettings.pyindex ec973e2f1..811b77286 100644--- a/src/documents/tests/test_api_uisettings.py+++ b/src/documents/tests/test_api_uisettings.py@@ -21,6 +21,16 @@ class TestApiUiSettings(DirectoriesMixin, APITestCase):self.test_user.save()self.client.force_authenticate(user=self.test_user)+ @override_settings(+ APP_TITLE=None,+ APP_LOGO=None,+ AUDIT_LOG_ENABLED=True,+ EMPTY_TRASH_DELAY=30,+ ENABLE_UPDATE_CHECK="default",+ EMAIL_ENABLED=False,+ GMAIL_OAUTH_ENABLED=False,+ OUTLOOK_OAUTH_ENABLED=False,+ )def test_api_get_ui_settings(self) -> None:response = self.client.get(self.ENDPOINT, format="json")self.assertEqual(response.status_code, status.HTTP_200_OK)diff --git a/src/documents/tests/test_barcodes.py b/src/documents/tests/test_barcodes.pyindex 2d9ac58f0..b1847f2b4 100644--- a/src/documents/tests/test_barcodes.py+++ b/src/documents/tests/test_barcodes.py@@ -919,6 +919,7 @@ class TestTagBarcode(DirectoriesMixin, SampleDirMixin, GetReaderPluginMixin, Tes@override_settings(CONSUMER_ENABLE_TAG_BARCODE=True,CONSUMER_TAG_BARCODE_MAPPING={"ASN(.*)": "\\g<1>"},+ CONSUMER_ENABLE_ASN_BARCODE=False,)def test_scan_file_for_many_custom_tags(self) -> None:"""diff --git a/src/documents/tests/test_file_handling.py b/src/documents/tests/test_file_handling.pyindex 9b6f96ce1..1e35b96bc 100644--- a/src/documents/tests/test_file_handling.py+++ b/src/documents/tests/test_file_handling.py@@ -329,14 +329,14 @@ class TestFileHandling(DirectoriesMixin, FileSystemAssertsMixin, TestCase):FILENAME_FORMAT="{added_year}-{added_month}-{added_day}",)def test_added_year_month_day(self) -> None:- d1 = timezone.make_aware(datetime.datetime(232, 1, 9, 1, 1, 1))+ d1 = timezone.make_aware(datetime.datetime(1232, 1, 9, 1, 1, 1))doc1 = Document.objects.create(title="doc1",mime_type="application/pdf",added=d1,)- self.assertEqual(generate_filename(doc1), Path("232-01-09.pdf"))+ self.assertEqual(generate_filename(doc1), Path("1232-01-09.pdf"))doc1.added = timezone.make_aware(datetime.datetime(2020, 11, 16, 1, 1, 1))diff --git a/src/documents/tests/test_management_fuzzy.py b/src/documents/tests/test_management_fuzzy.pyindex b3d03ecea..195a3450d 100644--- a/src/documents/tests/test_management_fuzzy.py+++ b/src/documents/tests/test_management_fuzzy.py@@ -140,7 +140,7 @@ class TestFuzzyMatchCommand(TestCase):mime_type="application/pdf",filename="final_test.pdf",)- stdout, _ = self.call_command("--no-progress-bar")+ stdout, _ = self.call_command("--no-progress-bar", "--processes", "1")lines = [x.strip() for x in stdout.splitlines() if x.strip()]self.assertEqual(len(lines), 3)for line in lines:@@ -183,7 +183,12 @@ class TestFuzzyMatchCommand(TestCase):self.assertEqual(Document.objects.count(), 3)- stdout, _ = self.call_command("--delete", "--no-progress-bar")+ stdout, _ = self.call_command(+ "--delete",+ "--no-progress-bar",+ "--processes",+ "1",+ )self.assertIn("The command is configured to delete documents. Use with caution",diff --git a/src/documents/tests/utils.py b/src/documents/tests/utils.pyindex f099cd92e..346d895aa 100644--- a/src/documents/tests/utils.py+++ b/src/documents/tests/utils.py@@ -33,11 +33,11 @@ from documents.plugins.helpers import ProgressStatusOptionsdef setup_directories():dirs = namedtuple("Dirs", ())- dirs.data_dir = Path(tempfile.mkdtemp())- dirs.scratch_dir = Path(tempfile.mkdtemp())- dirs.media_dir = Path(tempfile.mkdtemp())- dirs.consumption_dir = Path(tempfile.mkdtemp())- dirs.static_dir = Path(tempfile.mkdtemp())+ dirs.data_dir = Path(tempfile.mkdtemp()).resolve()+ dirs.scratch_dir = Path(tempfile.mkdtemp()).resolve()+ dirs.media_dir = Path(tempfile.mkdtemp()).resolve()+ dirs.consumption_dir = Path(tempfile.mkdtemp()).resolve()+ dirs.static_dir = Path(tempfile.mkdtemp()).resolve()dirs.index_dir = dirs.data_dir / "index"dirs.originals_dir = dirs.media_dir / "documents" / "originals"dirs.thumbnail_dir = dirs.media_dir / "documents" / "thumbnails"diff --git a/src/paperless/tests/test_adapter.py b/src/paperless/tests/test_adapter.pyindex 767749dd2..fcbd21b12 100644--- a/src/paperless/tests/test_adapter.py+++ b/src/paperless/tests/test_adapter.py@@ -78,11 +78,15 @@ class TestCustomAccountAdapter(TestCase):adapter = get_adapter()# Test when PAPERLESS_URL is None- expected_url = f"https://foo.org{reverse('account_reset_password_from_key', kwargs={'uidb36': 'UID', 'key': 'KEY'})}"- self.assertEqual(- adapter.get_reset_password_from_key_url("UID-KEY"),- expected_url,- )+ with override_settings(+ PAPERLESS_URL=None,+ ACCOUNT_DEFAULT_HTTP_PROTOCOL="https",+ ):+ expected_url = f"https://foo.org{reverse('account_reset_password_from_key', kwargs={'uidb36': 'UID', 'key': 'KEY'})}"+ self.assertEqual(+ adapter.get_reset_password_from_key_url("UID-KEY"),+ expected_url,+ )# Test when PAPERLESS_URL is not Nonewith override_settings(PAPERLESS_URL="https://bar.com"):diff --git a/src/paperless/tests/test_views.py b/src/paperless/tests/test_views.pyindex 76bf694fc..ab8941538 100644--- a/src/paperless/tests/test_views.py+++ b/src/paperless/tests/test_views.py@@ -1,7 +1,7 @@import tempfilefrom pathlib import Path-from django.conf import settings+from django.test import override_settingsdef test_favicon_view(client):@@ -11,15 +11,14 @@ def test_favicon_view(client):favicon_path.parent.mkdir(parents=True, exist_ok=True)favicon_path.write_bytes(b"FAKE ICON DATA")- settings.STATIC_ROOT = static_dir-- response = client.get("/favicon.ico")- assert response.status_code == 200- assert response["Content-Type"] == "image/x-icon"- assert b"".join(response.streaming_content) == b"FAKE ICON DATA"+ with override_settings(STATIC_ROOT=static_dir):+ response = client.get("/favicon.ico")+ assert response.status_code == 200+ assert response["Content-Type"] == "image/x-icon"+ assert b"".join(response.streaming_content) == b"FAKE ICON DATA"def test_favicon_view_missing_file(client):- settings.STATIC_ROOT = Path(tempfile.mkdtemp())- response = client.get("/favicon.ico")- assert response.status_code == 404+ with override_settings(STATIC_ROOT=Path(tempfile.mkdtemp())):+ response = client.get("/favicon.ico")+ assert response.status_code == 404diff --git a/src/paperless_mail/parsers.py b/src/paperless_mail/parsers.pyindex 22835de89..86cba23ab 100644--- a/src/paperless_mail/parsers.py+++ b/src/paperless_mail/parsers.py@@ -5,6 +5,7 @@ from pathlib import Pathfrom bleach import cleanfrom bleach import linkifyfrom django.conf import settings+from django.utils import timezonefrom django.utils.timezone import is_naivefrom django.utils.timezone import make_awarefrom gotenberg_client import GotenbergClient@@ -332,7 +333,9 @@ class MailDocumentParser(DocumentParser):if data["attachments"]:data["attachments_label"] = "Attachments"- data["date"] = clean_html(mail.date.astimezone().strftime("%Y-%m-%d %H:%M"))+ data["date"] = clean_html(+ timezone.localtime(mail.date).strftime("%Y-%m-%d %H:%M"),+ )data["content"] = clean_html(mail.text.strip())from django.template.loader import render_to_stringdiff --git a/src/paperless_mail/tests/test_parsers.py b/src/paperless_mail/tests/test_parsers.pyindex 061771d47..9746731f8 100644--- a/src/paperless_mail/tests/test_parsers.py+++ b/src/paperless_mail/tests/test_parsers.py@@ -6,6 +6,7 @@ from unittest import mockimport httpximport pytestfrom django.test.html import parse_html+from django.utils import timezonefrom pytest_django.fixtures import SettingsWrapperfrom pytest_httpx import HTTPXMockfrom pytest_mock import MockerFixture@@ -634,13 +635,14 @@ class TestParser:THEN:- Resulting HTML is as expected"""- mail = mail_parser.parse_file_to_message(html_email_file)- html_file = mail_parser.mail_to_html(mail)+ with timezone.override("UTC"):+ mail = mail_parser.parse_file_to_message(html_email_file)+ html_file = mail_parser.mail_to_html(mail)- expected_html = parse_html(html_email_html_file.read_text())- actual_html = parse_html(html_file.read_text())+ expected_html = parse_html(html_email_html_file.read_text())+ actual_html = parse_html(html_file.read_text())- assert expected_html == actual_html+ assert expected_html == actual_htmldef test_generate_pdf_from_mail(self,diff --git a/src/paperless_tesseract/tests/test_parser.py b/src/paperless_tesseract/tests/test_parser.pyindex ce8ef4c9e..e9c05b03e 100644--- a/src/paperless_tesseract/tests/test_parser.py+++ b/src/paperless_tesseract/tests/test_parser.py@@ -1,5 +1,6 @@import shutilimport tempfile+import unicodedataimport uuidfrom pathlib import Pathfrom unittest import mock@@ -847,8 +848,18 @@ class TestParser(DirectoriesMixin, FileSystemAssertsMixin, TestCase):"application/pdf",)- # Copied from the PDF to here. Don't even look at it- self.assertIn("ةﯾﻠﺧﺎدﻻ ةرازو", parser.get_text())+ # OCR output for RTL text varies across platforms/versions due to+ # bidi controls and presentation forms; normalize before assertion.+ normalized_text = "".join(+ char+ for char in unicodedata.normalize("NFKC", parser.get_text())+ if unicodedata.category(char) != "Cf" and not char.isspace()+ )++ self.assertIn("ةرازو", normalized_text)+ self.assertTrue(+ any(token in normalized_text for token in ("ةیلخادلا", "الاخليد")),+ )@mock.patch("ocrmypdf.ocr")def test_gs_rendering_error(self, m) -> None: