mirror of
https://github.com/paperless-ngx/paperless-ngx.git
synced 2026-11-05 06:19:25 +00:00
stumpylog
7d5e7b1625
Passing task_cls to Celery replaces the Django fixup's default DjangoTask, so FileMoveScopedTask, built on the plain Task, left every task without delay_on_commit. The workflow AI suggestions trigger failed with an AttributeError. FileMoveScopedTask now subclasses DjangoTask, which only needs django.db.transaction and is safe to import before apps load. The task scope test also asserts tasks are DjangoTask instances.
77 lines
2.7 KiB
Python
77 lines
2.7 KiB
Python
import os
|
|
|
|
from celery import Celery
|
|
from celery.contrib.django.task import DjangoTask
|
|
from celery.signals import worker_process_init
|
|
from kombu.serialization import register
|
|
|
|
from paperless.signed_pickle import signed_pickle_dumps
|
|
from paperless.signed_pickle import signed_pickle_loads
|
|
|
|
# Set the default Django settings module for the 'celery' program.
|
|
os.environ.setdefault("DJANGO_SETTINGS_MODULE", "paperless.settings")
|
|
|
|
# ---------------------------------------------------------------------------
|
|
# Signed-pickle serializer: pickle with HMAC-SHA256 integrity verification.
|
|
#
|
|
# Protects against malicious pickle injection via an exposed Redis broker.
|
|
# Messages are signed on the producer side and verified before deserialization
|
|
# on the worker side using Django's SECRET_KEY.
|
|
# ---------------------------------------------------------------------------
|
|
|
|
register(
|
|
"signed-pickle",
|
|
signed_pickle_dumps,
|
|
signed_pickle_loads,
|
|
content_type="application/x-signed-pickle",
|
|
content_encoding="binary",
|
|
)
|
|
|
|
|
|
class FileMoveScopedTask(DjangoTask):
|
|
"""
|
|
Run every task inside a document file move scope, so each document a task
|
|
changes is moved once when the task ends, after its writes have committed.
|
|
The scope also flushes when the task raises, for writes that committed
|
|
before the failure.
|
|
|
|
Subclasses DjangoTask because a custom task_cls replaces the Django fixup's
|
|
default, and delay_on_commit lives there.
|
|
"""
|
|
|
|
def __call__(self, *args, **kwargs):
|
|
# Function-local: this module is imported by paperless/__init__.py
|
|
# before Django apps are loaded.
|
|
from documents.file_moves import defer_file_moves
|
|
|
|
with defer_file_moves():
|
|
return super().__call__(*args, **kwargs)
|
|
|
|
|
|
app = Celery("paperless", task_cls=FileMoveScopedTask)
|
|
|
|
# Using a string here means the worker doesn't have to serialize
|
|
# the configuration object to child processes.
|
|
# - namespace='CELERY' means all celery-related configuration keys
|
|
# should have a `CELERY_` prefix.
|
|
app.config_from_object("django.conf:settings", namespace="CELERY")
|
|
|
|
# Load task modules from all registered Django apps.
|
|
app.autodiscover_tasks()
|
|
|
|
|
|
@worker_process_init.connect
|
|
def on_worker_process_init(**kwargs) -> None: # pragma: no cover
|
|
"""
|
|
Register built-in parsers eagerly in each Celery worker process.
|
|
|
|
This registers only the built-in parsers (no entrypoint discovery) so
|
|
that workers can begin consuming documents immediately. Entrypoint
|
|
discovery for third-party parsers is deferred to the first call of
|
|
get_parser_registry() inside a task, keeping worker_process_init
|
|
well within its 4-second timeout budget.
|
|
"""
|
|
from paperless.parsers.registry import init_builtin_parsers
|
|
|
|
init_builtin_parsers()
|