Files
Evection/apps/articles/tasks.py
T
ksmithandClaude Sonnet 5.5 37e658c49a Add configurable article retention (C7)
Articles and full HTML bodies accumulated forever, growing the
database, search index, and backups without bound. Site settings gets
a "Retention days" field (0, the default, keeps everything); a nightly
beat task deletes articles fetched longer ago than that in bounded
chunks, always keeping anything a user starred or saved for later.
Read state and tags cascade with the article and the FTS triggers drop
search entries. The dashboard shows the article count and oldest
article's age, and docs/install.md covers retention, the readiness
check, and SQLite's WAL tuning.

Co-Authored-By: Claude Sonnet 5.5 <noreply@anthropic.com>
2026-11-01 08:51:20 -07:00

96 lines
3.5 KiB
Python

from datetime import timedelta
from celery import shared_task
from django.utils import timezone
from apps.core.models import SiteSettings
from apps.feeds.models import Subscription
from apps.rules.engine import evaluate_rules_for_article
from apps.rules.models import FilterRule
from .models import Article, ArticleTag, SubscriptionTag
@shared_task
def apply_filter_rules_for_feed(feed_id: int, article_ids: list[int]):
"""For every subscriber of ``feed_id``, evaluate their enabled
FilterRules (scoped to this feed/tag or unscoped) against the given
articles. Dispatched by the fetch pipeline after new/updated articles
are committed for a feed.
Per-rule scoping is left to evaluate_rules_for_article/rule_in_scope
rather than filtered into this query, so this and the backlog
re-apply task (apps.rules.tasks) can't scope rules differently.
Rules and subscription tags are fetched once for every subscriber of
this feed, not once per subscriber (C9) — a popular feed with many
subscribers previously issued 2 queries per subscriber here.
"""
if not article_ids:
return 0
articles = list(Article.objects.filter(pk__in=article_ids).select_related("feed"))
if not articles:
return 0
subscriptions = list(Subscription.objects.filter(feed_id=feed_id).select_related("user"))
if not subscriptions:
return 0
rules_by_user_id: dict[int, list[FilterRule]] = {}
for rule in FilterRule.objects.filter(
user_id__in={s.user_id for s in subscriptions}, is_enabled=True
).order_by("priority", "id"):
rules_by_user_id.setdefault(rule.user_id, []).append(rule)
tag_ids_by_subscription_id: dict[int, set[int]] = {}
for subscription_id, tag_id in SubscriptionTag.objects.filter(
subscription_id__in=[s.pk for s in subscriptions]
).values_list("subscription_id", "tag_id"):
tag_ids_by_subscription_id.setdefault(subscription_id, set()).add(tag_id)
evaluated = 0
for subscription in subscriptions:
rules = rules_by_user_id.get(subscription.user_id)
if not rules:
continue
subscription_tag_ids = tag_ids_by_subscription_id.get(subscription.pk, set())
for article in articles:
evaluate_rules_for_article(subscription.user, article, rules, subscription_tag_ids)
evaluated += 1
return evaluated
PURGE_CHUNK_SIZE = 500
@shared_task
def purge_old_articles():
"""Deletes articles older than SiteSettings.retention_days (C7), in
chunks so one run never holds a huge delete in a single transaction.
Anything a user starred or saved for later (a system ArticleTag) is
kept — those are explicit "keep this" signals. UserArticleState and
ArticleTag rows go with their article via ON DELETE CASCADE, and the
SQLite FTS triggers drop the search entries. 0 days means keep
everything forever (the default).
"""
retention_days = SiteSettings.load().retention_days
if retention_days <= 0:
return 0
cutoff = timezone.now() - timedelta(days=retention_days)
keep = ArticleTag.objects.filter(tag__is_system=True).values("article_id")
deleted_total = 0
while True:
chunk = list(
Article.objects.filter(fetched_at__lt=cutoff)
.exclude(pk__in=keep)
.values_list("pk", flat=True)[:PURGE_CHUNK_SIZE]
)
if not chunk:
return deleted_total
Article.objects.filter(pk__in=chunk).delete()
deleted_total += len(chunk)