Merge branch 'dev' into feature/ocr-templates

This commit is contained in:
shamoon committed 2026-11-02 21:44:11 -08:00
commit 2b620a2823
408 files changed
+6392 -5987

No files matched your search

+7 -3
View File
@@ -10,9 +10,6 @@ from typing import TYPE_CHECKING
import regex as regex_mod
from django.conf import settings
from pdf2image import convert_from_path
from pikepdf import Page
from pikepdf import PasswordError
from pikepdf import Pdf
from documents.converters import convert_from_tiff_to_pdf
from documents.data_models import ConsumableDocument
@@ -34,6 +31,7 @@ from documents.utils import maybe_override_pixel_limit
from paperless.config import BarcodeConfig
if TYPE_CHECKING:
from pikepdf import Page
from PIL import Image
logger = logging.getLogger("paperless.barcodes")
@@ -282,6 +280,8 @@ class BarcodePlugin(ConsumeTaskPlugin):
# No op if not a TIFF
self.convert_from_tiff_to_pdf()
from pikepdf import PasswordError
try:
self.barcodes = scan_pdf(
self.pdf_file,
@@ -433,6 +433,8 @@ class BarcodePlugin(ConsumeTaskPlugin):
document_paths = []
fname: str = self.input_doc.original_file.stem
from pikepdf import Pdf
with Pdf.open(self.pdf_file) as input_pdf:
# Start with an empty document
current_document: list[Page] = []
@@ -516,6 +518,8 @@ def scan_pdf(pdf_path: Path, settings: BarcodeConfig, work_dir: Path) -> list[Ba
"""
barcodes: list[Barcode] = []
from pikepdf import Pdf
with Pdf.open(pdf_path) as pdf:
num_of_pages = len(pdf.pages)
logger.debug(f"PDF has {num_of_pages} pages")
+2 -1
View File
@@ -1,6 +1,5 @@
from pathlib import Path
import img2pdf
from PIL import Image
from documents.utils import copy_basic_file_stats
@@ -17,6 +16,8 @@ def convert_from_tiff_to_pdf(tiff_path: Path, target_directory: Path) -> Path:
Returns the path of the PDF created.
"""
import img2pdf
# override pixel setting if needed
maybe_override_pixel_limit()
+2 -1
View File
@@ -6,7 +6,6 @@ from pathlib import Path
from typing import Final
from django.conf import settings
from pikepdf import Pdf
from documents.consumer import ConsumerError
from documents.converters import convert_from_tiff_to_pdf
@@ -85,6 +84,8 @@ class CollatePlugin(NoCleanupPluginMixin, NoSetupPluginMixin, ConsumeTaskPlugin)
valid_staging_exists = True
if valid_staging_exists:
from pikepdf import Pdf
try:
# Collate pages from second PDF in reverse order
with Pdf.open(staging) as pdf1, Pdf.open(pdf_file) as pdf2:
+2 -1
View File
@@ -11,7 +11,6 @@ from decimal import InvalidOperation
from typing import TYPE_CHECKING
from typing import Any
import dateparser
from django.conf import settings
from django.contrib.contenttypes.models import ContentType
from django.db.models import Case
@@ -350,6 +349,8 @@ class DateQueryField(serializers.DateField):
if not isinstance(value, str):
raise
import dateparser
try:
parsed = dateparser.parse(
value,
+14 -2
View File
@@ -14,8 +14,6 @@ from __future__ import annotations
from typing import TYPE_CHECKING
from typing import NamedTuple
import pikepdf
if TYPE_CHECKING:
from collections.abc import Callable
from collections.abc import Iterable
@@ -43,6 +41,8 @@ def rotate_pdf(src: Path, dst: Path, degrees: int) -> None:
Rotate every page relatively on the opened document, not a rebuild, so Info,
XMP and outlines are kept. ``src`` is not modified.
"""
import pikepdf
with pikepdf.open(src) as pdf:
for page in pdf.pages:
page.rotate(degrees, relative=True)
@@ -58,6 +58,8 @@ def remove_pages(src: Path, dst: Path, pages: Iterable[int]) -> None:
Duplicates are ignored. Pages are removed highest first so earlier removals
never shift the index of later ones.
"""
import pikepdf
unique = sorted(set(pages))
_require_positive(unique)
with pikepdf.open(src) as pdf:
@@ -81,6 +83,8 @@ def build_pdfs(
(Info, XMP, outlines) is not carried over. Returns the written paths in output
order.
"""
import pikepdf
for specs, _ in outputs:
_require_positive(spec.page for spec in specs)
@@ -140,6 +144,8 @@ def needs_decrypt(src: Path) -> bool:
True if ``src`` is encrypted. A PDF that needs a password to open at all
counts as encrypted.
"""
import pikepdf
try:
with pikepdf.open(src) as pdf:
return bool(pdf.is_encrypted)
@@ -154,6 +160,8 @@ def decrypt_pdf(src: Path, make_dst: Callable[[], Path], password: str) -> Path:
``make_dst`` is only called once the password has been accepted, so a wrong
password never leaves a destination behind.
"""
import pikepdf
with pikepdf.open(src, password=password) as pdf:
pdf.remove_unreferenced_resources()
dst = make_dst()
@@ -170,6 +178,8 @@ class PdfMerger:
"""
def __init__(self) -> None:
import pikepdf
self._pdf = pikepdf.new()
self._version: str = self._pdf.pdf_version
@@ -185,6 +195,8 @@ class PdfMerger:
self._pdf.close()
def add(self, path: Path) -> None:
import pikepdf
with pikepdf.open(str(path)) as pdf:
self._version = max(self._version, pdf.pdf_version)
self._pdf.pages.extend(pdf.pages)
+2 -2
View File
@@ -7,8 +7,6 @@ from dataclasses import dataclass
from types import TracebackType
from typing import Self
import dateparser
logger = logging.getLogger(__name__)
@@ -80,6 +78,8 @@ class DateParserPluginBase(ABC):
Uses configuration from `self.config`.
"""
import dateparser
try:
return dateparser.parse(
date_string,
+6 -6
View File
@@ -476,13 +476,13 @@ def update_filename_and_move_files(
return
with FileLock(settings.MEDIA_LOCK):
try:
# If this was waiting for the lock, the filename or archive_filename
# of this document may have been updated. This happens if multiple updates
# get queued from the UI for the same document
# So freshen up the data before doing anything
instance.refresh_from_db()
# If this was waiting for the lock, the filename or archive_filename
# of this document may have been updated. This happens if multiple updates
# get queued from the UI for the same document
# So freshen up the data before doing anything
instance.refresh_from_db()
try:
old_filename = instance.filename
old_source_path = instance.source_path
move_original = False
+8 -3
View File
@@ -78,9 +78,6 @@ from paperless.logging import consume_task_id
from paperless.parsers import ParserContext
from paperless.parsers.registry import get_parser_registry
from paperless_ai.exceptions import LLMTimeoutError
from paperless_ai.indexing import llm_index_add_or_update_document
from paperless_ai.indexing import llm_index_remove_document
from paperless_ai.indexing import update_llm_index
if settings.AUDIT_LOG_ENABLED:
from auditlog.models import LogEntry
@@ -341,6 +338,8 @@ def bulk_update_documents(document_ids) -> None:
ai_config = AIConfig()
if ai_config.llm_index_enabled:
from paperless_ai.indexing import update_llm_index
update_llm_index(
rebuild=False,
document_ids=document_ids,
@@ -526,6 +525,8 @@ def update_document_content_maybe_archive_file(
ai_config = AIConfig()
if ai_config.llm_index_enabled:
from paperless_ai.indexing import llm_index_add_or_update_document
llm_index_add_or_update_document(document)
clear_document_caches(document.pk)
@@ -827,11 +828,15 @@ def apply_ai_suggestions(self, action_id: int, document_id: int) -> None:
@shared_task
def update_document_in_llm_index(document) -> None:
from paperless_ai.indexing import llm_index_add_or_update_document
llm_index_add_or_update_document(document)
@shared_task
def remove_document_from_llm_index(document) -> None:
from paperless_ai.indexing import llm_index_remove_document
llm_index_remove_document(document)
+4 -1
View File
@@ -44,7 +44,10 @@ def localize_date(value: date | datetime | str, format: str, locale: str) -> str
def format_datetime(value: str | datetime, format: str) -> str:
if isinstance(value, str):
value = parse_date(value)
parsed = parse_datetime(value) or parse_date(value)
if parsed is None:
raise ValueError(f"Invalid date or datetime string: {value!r}")
return parsed.strftime(format=format)
return value.strftime(format=format)
@@ -71,7 +71,7 @@ class TestParseString:
):
# We still need to mock dateparser.parse to force the exception
mocker.patch(
"documents.plugins.date_parsing.base.dateparser.parse",
"dateparser.parse",
side_effect=ValueError(
"Parsing error: 01/01/2024",
),
@@ -260,7 +260,7 @@ class TestRegexDateParser:
parser = RegexDateParserPlugin(base_config)
# Patch the dateparser.parse
target = "documents.plugins.date_parsing.base.dateparser.parse"
target = "dateparser.parse"
def fake_parse(
date_string: str,
@@ -335,7 +335,7 @@ class TestRegexDateParser:
)
parser = RegexDateParserPlugin(cfg)
target = "documents.plugins.date_parsing.base.dateparser.parse"
target = "dateparser.parse"
def fake_parse(
date_string: str,
@@ -400,7 +400,7 @@ class TestRegexDateParser:
parser = RegexDateParserPlugin(cfg)
# Patch the module's dateparser.parse so we can inspect calls
target = "documents.plugins.date_parsing.base.dateparser.parse"
target = "dateparser.parse"
def fake_parse(
date_string: str,
+5 -5
View File
@@ -1070,7 +1070,7 @@ class TestApiAppConfig(DirectoriesMixin, APITestCase):
with (
patch("documents.tasks.llmindex_index.apply_async") as mock_update,
patch("paperless.views.llm_index_exists") as mock_exists,
patch("paperless_ai.indexing.llm_index_exists") as mock_exists,
):
mock_exists.return_value = False
self.client.patch(
@@ -1095,7 +1095,7 @@ class TestApiAppConfig(DirectoriesMixin, APITestCase):
with (
patch("documents.tasks.llmindex_index.apply_async") as mock_update,
patch("paperless.views.llm_index_exists", return_value=False),
patch("paperless_ai.indexing.llm_index_exists", return_value=False),
):
self.client.patch(
f"{self.ENDPOINT}1/",
@@ -1115,7 +1115,7 @@ class TestApiAppConfig(DirectoriesMixin, APITestCase):
with (
patch("documents.tasks.llmindex_index.apply_async") as mock_update,
patch("paperless.views.llm_index_exists") as mock_exists,
patch("paperless_ai.indexing.llm_index_exists") as mock_exists,
):
mock_exists.return_value = True
self.client.patch(
@@ -1136,7 +1136,7 @@ class TestApiAppConfig(DirectoriesMixin, APITestCase):
with (
patch("documents.tasks.llmindex_index.apply_async") as mock_update,
patch("paperless.views.llm_index_exists") as mock_exists,
patch("paperless_ai.indexing.llm_index_exists") as mock_exists,
):
mock_exists.return_value = True
self.client.patch(
@@ -1174,7 +1174,7 @@ class TestApiAppConfig(DirectoriesMixin, APITestCase):
with (
patch("documents.tasks.llmindex_index.apply_async") as mock_update,
patch("paperless.views.llm_index_exists") as mock_exists,
patch("paperless_ai.indexing.llm_index_exists") as mock_exists,
):
mock_exists.return_value = True
self.client.patch(
+2 -2
View File
@@ -61,7 +61,7 @@ class TestChatStreamingViewInputValidation(APITestCase):
return_value=self._mock_ai_enabled(),
),
mock.patch(
"documents.views.stream_chat_with_documents",
"paperless_ai.chat.stream_chat_with_documents",
return_value=iter(chunks),
),
):
@@ -104,7 +104,7 @@ class TestChatStreamingViewUnrestrictedFlag:
"""
mocker.patch("documents.views.AIConfig").return_value.ai_enabled = True
return mocker.patch(
"documents.views.stream_chat_with_documents",
"paperless_ai.chat.stream_chat_with_documents",
return_value=iter(()),
)
@@ -1110,7 +1110,7 @@ class TestVersionActionPermissions(DirectoriesMixin, APITestCase):
self.assertEqual(response.status_code, 403)
with (
mock.patch("documents.views.AIConfig") as ai_config,
mock.patch("documents.views.stream_chat_with_documents") as chat,
mock.patch("paperless_ai.chat.stream_chat_with_documents") as chat,
):
ai_config.return_value.ai_enabled = True
response = self.client.post(
+1 -1
View File
@@ -2686,7 +2686,7 @@ class TestDocumentApi(DirectoriesMixin, ConsumeTaskMixin, APITestCase):
response = self.client.get("/api/documents/34676/suggestions/")
self.assertEqual(response.status_code, status.HTTP_404_NOT_FOUND)
@mock.patch("documents.views.get_ai_document_classification")
@mock.patch("paperless_ai.ai_classifier.get_ai_document_classification")
@override_settings(AI_ENABLED=True)
def test_suggestions_still_uses_classifier_when_ai_enabled(
self,
+29
View File
@@ -308,3 +308,32 @@ class TestBulkDownloadSchema:
def test_bulk_download_response_403(self, api_schema: SchemaGenerator) -> None:
op = api_schema["paths"]["/api/documents/bulk_download/"]["post"]
assert "403" in op["responses"]
class TestDocumentListObjectFilterSchema:
"""documents_list: comma-separated ObjectFilter params must be typed as integer arrays."""
@pytest.mark.parametrize(
"param_name",
[
"tags__id__all",
"tags__id__none",
"tags__id__in",
"correspondent__id__none",
"document_type__id__none",
"storage_path__id__none",
"owner__id__none",
"custom_fields__id__all",
"custom_fields__id__none",
"custom_fields__id__in",
],
)
def test_object_filter_param_is_integer_array(
self,
api_schema: SchemaGenerator,
param_name: str,
) -> None:
params = api_schema["paths"]["/api/documents/"]["get"]["parameters"]
param = next(p for p in params if p["name"] == param_name)
assert param["schema"] == {"type": "array", "items": {"type": "integer"}}
assert param["explode"] is False
+47
View File
@@ -539,3 +539,50 @@ class TestSystemStatus(APITestCase):
self.assertEqual(response.data["tasks"]["summary"]["success_count"], 1)
self.assertEqual(response.data["tasks"]["summary"]["failure_count"], 1)
self.assertEqual(response.data["tasks"]["summary"]["pending_count"], 1)
def test_system_status_reports_database_error(self) -> None:
"""
GIVEN:
- Reading the migration state fails
WHEN:
- The system status is requested
THEN:
- The response reports the database error rather than a server error
"""
self.client.force_login(self.user)
with mock.patch(
"documents.views.MigrationLoader",
side_effect=Exception("database is down"),
):
response = self.client.get(self.ENDPOINT)
self.assertEqual(response.status_code, status.HTTP_200_OK)
database = response.data["database"]
self.assertEqual(database["status"], "ERROR")
self.assertIsNotNone(database["error"])
self.assertEqual(
database["migration_status"],
{"latest_migration": None, "unapplied_migrations": []},
)
def test_system_status_migration_query_error(self) -> None:
"""
GIVEN:
- The migration graph loads but reading the applied migrations fails
WHEN:
- The system status is requested
THEN:
- No migrations are reported as unapplied, since the state is unknown
"""
self.client.force_login(self.user)
with mock.patch("documents.views.MigrationRecorder") as recorder:
recorder.Migration.objects.all.side_effect = Exception("query failed")
response = self.client.get(self.ENDPOINT)
self.assertEqual(response.status_code, status.HTTP_200_OK)
database = response.data["database"]
self.assertEqual(database["status"], "ERROR")
self.assertEqual(
database["migration_status"],
{"latest_migration": None, "unapplied_migrations": []},
)
+26
View File
@@ -31,6 +31,7 @@ from documents.serialisers import DocumentSerializer
from documents.tasks import empty_trash
from paperless_testing.assertions import FileSystemAssertsMixin
from paperless_testing.dirs import DirectoriesMixin
from paperless_testing.dirs import PaperlessDirs
from paperless_testing.factories import DocumentFactory
from paperless_testing.factories import UserFactory
@@ -2134,3 +2135,28 @@ class TestPathDateLocalization:
with override_settings(FILENAME_FORMAT=filename_format):
filename = generate_filename(document)
assert filename == Path(expected_filename)
@pytest.mark.django_db
def test_refresh_failure_surfaces_database_error(
paperless_dirs: PaperlessDirs,
) -> None:
"""
GIVEN:
- A document with a stored filename
WHEN:
- Saving it triggers a filename update and refreshing it from the database fails
THEN:
- The database error is raised, not an unbound variable error from the rollback
"""
document = DocumentFactory(filename="some.pdf")
with (
mock.patch.object(
Document,
"refresh_from_db",
side_effect=DatabaseError("database is locked"),
),
pytest.raises(DatabaseError, match="database is locked"),
):
document.save()
+21
View File
@@ -4,6 +4,7 @@ from typing import Literal
import pytest
from documents.templating.filters import format_datetime
from documents.templating.filters import localize_date
@@ -294,3 +295,23 @@ class TestDateLocalization:
Tests `localize_date` with `date` string across different locales and formats.
"""
assert localize_date(value, format_style, locale_str) == expected_output
class TestFormatDatetime:
@pytest.mark.parametrize(
("value", "expected"),
[
pytest.param("2026-09-21", "2026-09-21 00:00", id="date"),
pytest.param(
"2026-09-21T13:45:00+00:00",
"2026-09-21 13:45",
id="datetime",
),
],
)
def test_parses_iso_strings(self, value: str, expected: str) -> None:
assert format_datetime(value, "%Y-%m-%d %H:%M") == expected
def test_rejects_unparseable_string(self) -> None:
with pytest.raises(ValueError, match="not a date"):
format_datetime("not a date", "%Y")
@@ -572,7 +572,7 @@ class TestAiChatAllDocumentsPermissionBoundary:
ENDPOINT = "/api/documents/chat/"
@override_settings(AI_ENABLED=True)
@patch("documents.views.stream_chat_with_documents")
@patch("paperless_ai.chat.stream_chat_with_documents")
def test_chat_all_documents_excludes_unshared_document(self, mock_stream_chat):
mock_stream_chat.return_value = iter([b"data"])
+4 -4
View File
@@ -322,7 +322,7 @@ class TestUpdateContent(DirectoriesMixin, TestCase):
)
@override_settings(AI_ENABLED=True, LLM_EMBEDDING_BACKEND="huggingface")
@mock.patch("documents.tasks.llm_index_add_or_update_document")
@mock.patch("paperless_ai.indexing.llm_index_add_or_update_document")
@mock.patch("documents.search.get_backend")
def test_update_content_version_updates_llm_index(
self,
@@ -450,7 +450,7 @@ class TestAIIndex(DirectoriesMixin, TestCase):
checksum="wow",
)
with mock.patch(
"documents.tasks.llm_index_add_or_update_document",
"paperless_ai.indexing.llm_index_add_or_update_document",
) as llm_index_add_or_update_document:
tasks.update_document_in_llm_index(doc)
llm_index_add_or_update_document.assert_called_once_with(doc)
@@ -470,7 +470,7 @@ class TestAIIndex(DirectoriesMixin, TestCase):
checksum="wow",
)
with mock.patch(
"documents.tasks.llm_index_remove_document",
"paperless_ai.indexing.llm_index_remove_document",
) as llm_index_remove_document:
tasks.remove_document_from_llm_index(doc)
llm_index_remove_document.assert_called_once_with(doc)
@@ -495,7 +495,7 @@ class TestAIIndex(DirectoriesMixin, TestCase):
"documents.tasks.update_document_in_llm_index",
) as update_document_in_llm_index,
mock.patch(
"documents.tasks.update_llm_index",
"paperless_ai.indexing.update_llm_index",
) as update_llm_index,
):
doc_ids = [doc.pk for doc in docs]
+16 -16
View File
@@ -474,7 +474,7 @@ class TestAISuggestions(DirectoriesMixin, TestCase):
self.assertEqual(response.json()["tags"], [])
self.assertEqual(response.json()["suggested_tags"], [])
@patch("documents.views.get_ai_document_classification")
@patch("paperless_ai.ai_classifier.get_ai_document_classification")
@override_settings(
AI_ENABLED=True,
LLM_BACKEND="mock_backend",
@@ -524,7 +524,7 @@ class TestAISuggestions(DirectoriesMixin, TestCase):
None,
)
@patch("documents.views.get_ai_document_classification")
@patch("paperless_ai.ai_classifier.get_ai_document_classification")
@override_settings(
AI_ENABLED=True,
LLM_BACKEND="mock_backend",
@@ -562,7 +562,7 @@ class TestAISuggestions(DirectoriesMixin, TestCase):
"KI Title",
)
@patch("documents.views.get_ai_document_classification")
@patch("paperless_ai.ai_classifier.get_ai_document_classification")
@override_settings(
AI_ENABLED=True,
LLM_BACKEND="mock_backend",
@@ -601,7 +601,7 @@ class TestAISuggestions(DirectoriesMixin, TestCase):
"Titre IA",
)
@patch("documents.views.get_ai_document_classification")
@patch("paperless_ai.ai_classifier.get_ai_document_classification")
@override_settings(
AI_ENABLED=True,
LLM_BACKEND="mock_backend",
@@ -637,7 +637,7 @@ class TestAISuggestions(DirectoriesMixin, TestCase):
),
)
@patch("documents.views.get_ai_document_classification")
@patch("paperless_ai.ai_classifier.get_ai_document_classification")
@override_settings(
AI_ENABLED=True,
LLM_BACKEND="mock_backend",
@@ -709,7 +709,7 @@ class TestAISuggestions(DirectoriesMixin, TestCase):
),
)
@patch("documents.views.get_ai_document_classification")
@patch("paperless_ai.ai_classifier.get_ai_document_classification")
@override_settings(
AI_ENABLED=True,
LLM_BACKEND="openai-like",
@@ -738,7 +738,7 @@ class TestAISuggestions(DirectoriesMixin, TestCase):
get_llm_suggestion_cache(self.document.pk, backend="openai-like"),
)
@patch("documents.views.get_ai_document_classification")
@patch("paperless_ai.ai_classifier.get_ai_document_classification")
@override_settings(
AI_ENABLED=True,
LLM_BACKEND="openai-like",
@@ -765,7 +765,7 @@ class TestAISuggestions(DirectoriesMixin, TestCase):
get_llm_suggestion_cache(self.document.pk, backend="openai-like"),
)
@patch("documents.views.get_ai_document_classification")
@patch("paperless_ai.ai_classifier.get_ai_document_classification")
@override_settings(
AI_ENABLED=True,
LLM_BACKEND="openai-like",
@@ -797,7 +797,7 @@ class TestAISuggestions(DirectoriesMixin, TestCase):
get_llm_suggestion_cache(self.document.pk, backend="openai-like"),
)
@patch("documents.views.get_ai_document_classification")
@patch("paperless_ai.ai_classifier.get_ai_document_classification")
@override_settings(
AI_ENABLED=True,
LLM_BACKEND="mock_backend",
@@ -835,7 +835,7 @@ class TestAISuggestions(DirectoriesMixin, TestCase):
self.assertEqual(response.json()["tags"], [self.tag1.pk])
self.assertEqual(response.json()["suggested_tags"], ["Follow-up"])
@patch("documents.views.get_ai_document_classification")
@patch("paperless_ai.ai_classifier.get_ai_document_classification")
@override_settings(
AI_ENABLED=True,
LLM_BACKEND="mock_backend",
@@ -874,7 +874,7 @@ class TestAISuggestions(DirectoriesMixin, TestCase):
self.assertEqual(response.json()["tags"], [self.tag1.pk])
self.assertEqual(response.json()["suggested_tags"], [])
@patch("documents.views.get_ai_document_classification")
@patch("paperless_ai.ai_classifier.get_ai_document_classification")
@override_settings(
AI_ENABLED=True,
LLM_BACKEND="mock_backend",
@@ -996,7 +996,7 @@ class TestAIChatStreamingView(DirectoriesMixin, TestCase):
self.assertEqual(response.status_code, 400)
self.assertIn(b"AI is required for this feature", response.content)
@patch("documents.views.stream_chat_with_documents")
@patch("paperless_ai.chat.stream_chat_with_documents")
@patch("documents.views.permitted_document_ids")
@override_settings(AI_ENABLED=True)
def test_post_no_document_id(self, mock_permitted_ids, mock_stream_chat) -> None:
@@ -1016,7 +1016,7 @@ class TestAIChatStreamingView(DirectoriesMixin, TestCase):
self.assertEqual(list(call_kwargs["documents"]), [self.document])
self.assertIsNone(call_kwargs["output_language"])
@patch("documents.views.stream_chat_with_documents")
@patch("paperless_ai.chat.stream_chat_with_documents")
@patch("documents.views.permitted_document_ids")
@override_settings(AI_ENABLED=True)
def test_post_uses_user_display_language(
@@ -1042,7 +1042,7 @@ class TestAIChatStreamingView(DirectoriesMixin, TestCase):
self.assertEqual(list(call_kwargs["documents"]), [self.document])
self.assertEqual(call_kwargs["output_language"], "de-de")
@patch("documents.views.stream_chat_with_documents")
@patch("paperless_ai.chat.stream_chat_with_documents")
@override_settings(AI_ENABLED=True)
def test_post_with_document_id(self, mock_stream_chat) -> None:
self.grant_view_document_permission()
@@ -1079,7 +1079,7 @@ class TestAIChatStreamingView(DirectoriesMixin, TestCase):
self.assertEqual(response.status_code, 403)
self.assertIn(b"Insufficient permissions", response.content)
@patch("documents.views.stream_chat_with_documents")
@patch("paperless_ai.chat.stream_chat_with_documents")
@override_settings(AI_ENABLED=True)
def test_post_no_document_id_requires_view_document_permission(
self,
@@ -1093,7 +1093,7 @@ class TestAIChatStreamingView(DirectoriesMixin, TestCase):
self.assertEqual(response.status_code, 403)
mock_stream_chat.assert_not_called()
@patch("documents.views.stream_chat_with_documents")
@patch("paperless_ai.chat.stream_chat_with_documents")
@override_settings(AI_ENABLED=True)
def test_post_with_document_id_requires_view_document_permission(
self,
+36 -28
View File
@@ -259,20 +259,8 @@ from paperless.parsers.remote import RemoteEngineConfig
from paperless.serialisers import GroupSerializer
from paperless.serialisers import UserSerializer
from paperless.views import StandardPagination
from paperless_ai.ai_classifier import get_ai_document_classification
from paperless_ai.ai_classifier import get_llm_output_language
from paperless_ai.chat import stream_chat_with_documents
from paperless_ai.exceptions import LLMProviderError
from paperless_ai.exceptions import LLMTimeoutError
from paperless_ai.matching import extract_unmatched_names
from paperless_ai.matching import match_correspondents_by_name
from paperless_ai.matching import match_document_types_by_name
from paperless_ai.matching import match_storage_paths_by_name
from paperless_ai.matching import match_tags_by_name
from paperless_ai.matching import resolve_correspondent_ids
from paperless_ai.matching import resolve_document_type_ids
from paperless_ai.matching import resolve_storage_path_ids
from paperless_ai.matching import resolve_tag_ids
from paperless_mail.models import MailAccount
from paperless_mail.models import MailRule
from paperless_mail.oauth import PaperlessMailOAuth2Manager
@@ -708,19 +696,6 @@ class EmailDocumentDetailSchema(EmailSerializer):
@extend_schema_view(
list=extend_schema(
parameters=[
OpenApiParameter(
name=name,
type=OpenApiTypes.INT,
many=True,
style="form",
explode=False,
)
for name, field in DocumentFilterSet.base_filters.items()
if isinstance(field, ObjectFilter)
],
),
retrieve=extend_schema(
description="Retrieve a single document",
responses={
@@ -1622,6 +1597,18 @@ class DocumentViewSet(
if not ai_config.ai_enabled:
return HttpResponseBadRequest("AI is required for this feature")
from paperless_ai.ai_classifier import get_ai_document_classification
from paperless_ai.ai_classifier import get_llm_output_language
from paperless_ai.matching import extract_unmatched_names
from paperless_ai.matching import match_correspondents_by_name
from paperless_ai.matching import match_document_types_by_name
from paperless_ai.matching import match_storage_paths_by_name
from paperless_ai.matching import match_tags_by_name
from paperless_ai.matching import resolve_correspondent_ids
from paperless_ai.matching import resolve_document_type_ids
from paperless_ai.matching import resolve_storage_path_ids
from paperless_ai.matching import resolve_tag_ids
output_language = get_llm_output_language(
ai_config=ai_config,
user=request.user,
@@ -2525,6 +2512,9 @@ class ChatStreamingView(GenericAPIView[Any]):
)
unrestricted = user_is_unrestricted(request.user)
from paperless_ai.ai_classifier import get_llm_output_language
from paperless_ai.chat import stream_chat_with_documents
output_language = get_llm_output_language(
ai_config=ai_config,
user=request.user,
@@ -2546,6 +2536,17 @@ class ChatStreamingView(GenericAPIView[Any]):
list=extend_schema(
description="Document views including search",
parameters=[
*(
OpenApiParameter(
name=name,
type=OpenApiTypes.INT,
many=True,
style="form",
explode=False,
)
for name, field in DocumentFilterSet.base_filters.items()
if isinstance(field, ObjectFilter)
),
OpenApiParameter(
name="text",
type=OpenApiTypes.STR,
@@ -5380,7 +5381,9 @@ class CustomFieldViewSet(PermissionsAwareDocumentCountMixin, ModelViewSet[Custom
"migration_status": inline_serializer(
name="MigrationStatus",
fields={
"latest_migration": serializers.CharField(),
"latest_migration": serializers.CharField(
allow_null=True,
),
"unapplied_migrations": serializers.ListSerializer(
child=serializers.CharField(),
),
@@ -5455,6 +5458,8 @@ class SystemStatusView(PassUserMixin):
db_conn = connections["default"]
db_url = str(db_conn.settings_dict["NAME"])
db_error = None
all_migrations: list[str] = []
applied_migrations: list[str] = []
try:
db_conn.ensure_connection()
@@ -5465,7 +5470,8 @@ class SystemStatusView(PassUserMixin):
f"{m.app}.{m.name}"
for m in MigrationRecorder.Migration.objects.all().order_by("id")
]
except Exception as e: # pragma: no cover
except Exception as e:
all_migrations = []
applied_migrations = []
db_status = "ERROR"
logger.exception(
@@ -5661,7 +5667,9 @@ class SystemStatusView(PassUserMixin):
"status": db_status,
"error": db_error,
"migration_status": {
"latest_migration": applied_migrations[-1],
"latest_migration": (
applied_migrations[-1] if applied_migrations else None
),
"unapplied_migrations": [
m for m in all_migrations if m not in applied_migrations
],