Private
Public Access
Compare commits
4
Commits
| Author | SHA1 | Date | |
|---|---|---|---|
|
|
cb0ce5a336 | ||
|
|
abf4cef55b | ||
|
|
b33fe905d2 | ||
|
|
b84cfe6474 |
No files matched your search
@@ -1,5 +1,8 @@
|
|||||||
|
from django.core.cache import cache
|
||||||
from django.db.models import Count
|
from django.db.models import Count
|
||||||
|
|
||||||
|
from apps.core.cache_utils import SIDEBAR_UNREAD_CACHE_TTL_SECONDS, sidebar_unread_cache_key
|
||||||
|
|
||||||
from .models import SAVED_TAG_NAME, STARRED_TAG_NAME, Article, ArticleTag, UserArticleState
|
from .models import SAVED_TAG_NAME, STARRED_TAG_NAME, Article, ArticleTag, UserArticleState
|
||||||
|
|
||||||
|
|
||||||
@@ -44,9 +47,19 @@ def with_user_state(articles, user):
|
|||||||
|
|
||||||
|
|
||||||
def unread_counts_by_feed(user):
|
def unread_counts_by_feed(user):
|
||||||
"""{feed_id: unread_count} for every feed the user subscribes to, in one
|
"""{feed_id: unread_count} for every feed the user subscribes to — used
|
||||||
query — used by the sidebar, so it must stay cheap regardless of how
|
by the sidebar's context processor, which runs on every authenticated
|
||||||
many feeds/articles exist."""
|
page render, so the underlying join/group-by over the user's whole
|
||||||
|
article corpus is cached for a short TTL rather than recomputed on
|
||||||
|
every single page view (C3). apps.core.cache_utils.
|
||||||
|
invalidate_sidebar_unread_cache is called wherever a request changes
|
||||||
|
the current user's own read state, so this is rarely visibly stale.
|
||||||
|
"""
|
||||||
|
cache_key = sidebar_unread_cache_key(user.pk)
|
||||||
|
counts = cache.get(cache_key)
|
||||||
|
if counts is not None:
|
||||||
|
return counts
|
||||||
|
|
||||||
rows = (
|
rows = (
|
||||||
Article.objects.filter(feed__subscriptions__user=user)
|
Article.objects.filter(feed__subscriptions__user=user)
|
||||||
.exclude(user_states__user=user, user_states__is_read=True)
|
.exclude(user_states__user=user, user_states__is_read=True)
|
||||||
@@ -54,4 +67,6 @@ def unread_counts_by_feed(user):
|
|||||||
.values("feed_id")
|
.values("feed_id")
|
||||||
.annotate(unread=Count("id"))
|
.annotate(unread=Count("id"))
|
||||||
)
|
)
|
||||||
return {row["feed_id"]: row["unread"] for row in rows}
|
counts = {row["feed_id"]: row["unread"] for row in rows}
|
||||||
|
cache.set(cache_key, counts, SIDEBAR_UNREAD_CACHE_TTL_SECONDS)
|
||||||
|
return counts
|
||||||
+21
-11
@@ -17,6 +17,10 @@ def apply_filter_rules_for_feed(feed_id: int, article_ids: list[int]):
|
|||||||
Per-rule scoping is left to evaluate_rules_for_article/rule_in_scope
|
Per-rule scoping is left to evaluate_rules_for_article/rule_in_scope
|
||||||
rather than filtered into this query, so this and the backlog
|
rather than filtered into this query, so this and the backlog
|
||||||
re-apply task (apps.rules.tasks) can't scope rules differently.
|
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:
|
if not article_ids:
|
||||||
return 0
|
return 0
|
||||||
@@ -25,22 +29,28 @@ def apply_filter_rules_for_feed(feed_id: int, article_ids: list[int]):
|
|||||||
if not articles:
|
if not articles:
|
||||||
return 0
|
return 0
|
||||||
|
|
||||||
subscriptions = Subscription.objects.filter(feed_id=feed_id).select_related("user")
|
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
|
evaluated = 0
|
||||||
for subscription in subscriptions:
|
for subscription in subscriptions:
|
||||||
rules = list(
|
rules = rules_by_user_id.get(subscription.user_id)
|
||||||
FilterRule.objects.filter(user=subscription.user, is_enabled=True).order_by(
|
|
||||||
"priority", "id"
|
|
||||||
)
|
|
||||||
)
|
|
||||||
if not rules:
|
if not rules:
|
||||||
continue
|
continue
|
||||||
subscription_tag_ids = set(
|
subscription_tag_ids = tag_ids_by_subscription_id.get(subscription.pk, set())
|
||||||
SubscriptionTag.objects.filter(
|
|
||||||
user=subscription.user, subscription=subscription
|
|
||||||
).values_list("tag_id", flat=True)
|
|
||||||
)
|
|
||||||
|
|
||||||
for article in articles:
|
for article in articles:
|
||||||
evaluate_rules_for_article(subscription.user, article, rules, subscription_tag_ids)
|
evaluate_rules_for_article(subscription.user, article, rules, subscription_tag_ids)
|
||||||
|
|||||||
@@ -0,0 +1,60 @@
|
|||||||
|
import pytest
|
||||||
|
from django.contrib.auth import get_user_model
|
||||||
|
|
||||||
|
from apps.core.cache_utils import invalidate_sidebar_unread_cache
|
||||||
|
from apps.feeds.models import Feed, Subscription
|
||||||
|
|
||||||
|
from .models import Article
|
||||||
|
from .queries import unread_counts_by_feed
|
||||||
|
|
||||||
|
User = get_user_model()
|
||||||
|
|
||||||
|
|
||||||
|
@pytest.fixture
|
||||||
|
def alice(db):
|
||||||
|
return User.objects.create_user("alice", password="pw-alice-123")
|
||||||
|
|
||||||
|
|
||||||
|
@pytest.fixture
|
||||||
|
def feed(db):
|
||||||
|
return Feed.objects.create(feed_url="https://example.com/feed.xml")
|
||||||
|
|
||||||
|
|
||||||
|
@pytest.mark.django_db
|
||||||
|
def test_unread_counts_by_feed_is_cached_across_calls(alice, feed):
|
||||||
|
"""unread_counts_by_feed (C3) caches its result — a second call right
|
||||||
|
after a new unread article appears must still see the stale cached
|
||||||
|
value until invalidated or the TTL elapses, proving it isn't
|
||||||
|
recomputing the query every time."""
|
||||||
|
Subscription.objects.create(user=alice, feed=feed)
|
||||||
|
Article.objects.create(feed=feed, guid="a-1")
|
||||||
|
|
||||||
|
first = unread_counts_by_feed(alice)
|
||||||
|
assert first == {feed.pk: 1}
|
||||||
|
|
||||||
|
Article.objects.create(feed=feed, guid="a-2")
|
||||||
|
second = unread_counts_by_feed(alice)
|
||||||
|
assert second == {feed.pk: 1}, "expected the cached count, not a fresh recount"
|
||||||
|
|
||||||
|
|
||||||
|
@pytest.mark.django_db
|
||||||
|
def test_invalidate_sidebar_unread_cache_forces_a_recount(alice, feed):
|
||||||
|
Subscription.objects.create(user=alice, feed=feed)
|
||||||
|
Article.objects.create(feed=feed, guid="a-1")
|
||||||
|
unread_counts_by_feed(alice)
|
||||||
|
|
||||||
|
Article.objects.create(feed=feed, guid="a-2")
|
||||||
|
invalidate_sidebar_unread_cache(alice.pk)
|
||||||
|
|
||||||
|
assert unread_counts_by_feed(alice) == {feed.pk: 2}
|
||||||
|
|
||||||
|
|
||||||
|
@pytest.mark.django_db
|
||||||
|
def test_unread_counts_by_feed_cache_is_per_user(alice, feed):
|
||||||
|
bob = User.objects.create_user("bob", password="pw-bob-123")
|
||||||
|
Subscription.objects.create(user=alice, feed=feed)
|
||||||
|
Subscription.objects.create(user=bob, feed=feed)
|
||||||
|
Article.objects.create(feed=feed, guid="a-1")
|
||||||
|
|
||||||
|
assert unread_counts_by_feed(alice) == {feed.pk: 1}
|
||||||
|
assert unread_counts_by_feed(bob) == {feed.pk: 1}
|
||||||
@@ -150,3 +150,40 @@ def test_disabled_rule_does_not_apply(feed, alice):
|
|||||||
@pytest.mark.django_db
|
@pytest.mark.django_db
|
||||||
def test_dispatch_with_empty_article_ids_is_a_noop(feed):
|
def test_dispatch_with_empty_article_ids_is_a_noop(feed):
|
||||||
assert apply_filter_rules_for_feed(feed.id, []) == 0
|
assert apply_filter_rules_for_feed(feed.id, []) == 0
|
||||||
|
|
||||||
|
|
||||||
|
@pytest.mark.django_db
|
||||||
|
def test_dispatch_fetches_rules_and_tags_once_per_feed_not_once_per_subscriber(feed):
|
||||||
|
"""Rules/subscription tags are batched across every subscriber of the
|
||||||
|
feed in one query each (C9), not re-queried per subscriber — assert
|
||||||
|
this by checking the query count stays flat as subscribers grow."""
|
||||||
|
from django.db import connection
|
||||||
|
from django.test.utils import CaptureQueriesContext
|
||||||
|
|
||||||
|
users = [User.objects.create_user(f"user{i}", password="pw-123456") for i in range(5)]
|
||||||
|
for user in users:
|
||||||
|
sub = Subscription.objects.create(user=user, feed=feed)
|
||||||
|
tag = Tag.objects.create(user=user, name="Tech")
|
||||||
|
SubscriptionTag.objects.create(user=user, subscription=sub, tag=tag)
|
||||||
|
FilterRule.objects.create(
|
||||||
|
user=user,
|
||||||
|
tag=tag,
|
||||||
|
match_field=FilterRule.FIELD_TITLE,
|
||||||
|
match_type=FilterRule.MATCH_CONTAINS,
|
||||||
|
match_value="Python",
|
||||||
|
action=FilterRule.ACTION_STAR,
|
||||||
|
)
|
||||||
|
article = Article.objects.create(feed=feed, guid="guid-1", title="Python news")
|
||||||
|
|
||||||
|
with CaptureQueriesContext(connection) as ctx:
|
||||||
|
apply_filter_rules_for_feed(feed.id, [article.pk])
|
||||||
|
|
||||||
|
# Exactly one SELECT against each table regardless of subscriber
|
||||||
|
# count (5 here) — a regression back to per-subscription querying
|
||||||
|
# would show up as 5 of each instead of 1.
|
||||||
|
rule_selects = [q for q in ctx.captured_queries if "rules_filterrule" in q["sql"]]
|
||||||
|
tag_selects = [q for q in ctx.captured_queries if "articles_subscriptiontag" in q["sql"]]
|
||||||
|
assert len(rule_selects) == 1
|
||||||
|
assert len(tag_selects) == 1
|
||||||
|
for user in users:
|
||||||
|
assert is_starred(user, article) is True
|
||||||
@@ -0,0 +1,22 @@
|
|||||||
|
from django.core.cache import cache
|
||||||
|
|
||||||
|
# Short enough that a missed invalidation point self-heals within one
|
||||||
|
# page load's worth of staleness; long enough to actually absorb repeat
|
||||||
|
# authenticated-page renders (apps.core.context_processors.sidebar runs
|
||||||
|
# on every one) without recomputing unread_counts_by_feed's join/group-by
|
||||||
|
# over the user's whole article corpus each time (C3).
|
||||||
|
SIDEBAR_UNREAD_CACHE_TTL_SECONDS = 30
|
||||||
|
|
||||||
|
|
||||||
|
def sidebar_unread_cache_key(user_id: int) -> str:
|
||||||
|
return f"sidebar-unread:{user_id}"
|
||||||
|
|
||||||
|
|
||||||
|
def invalidate_sidebar_unread_cache(user_id: int) -> None:
|
||||||
|
"""Call this wherever a request changes the current user's own
|
||||||
|
read/unread state (toggle_read, mark_all_read, viewing an article) so
|
||||||
|
the sidebar reflects it on the very next render instead of waiting
|
||||||
|
out the TTL above. Rule-driven state changes during background feed
|
||||||
|
ingestion aren't invalidated this way — those self-heal within the
|
||||||
|
TTL, same as a missed call site here would."""
|
||||||
|
cache.delete(sidebar_unread_cache_key(user_id))
|
||||||
@@ -1,13 +1,6 @@
|
|||||||
from datetime import timedelta
|
|
||||||
from unittest.mock import patch
|
|
||||||
|
|
||||||
import pytest
|
import pytest
|
||||||
from django.contrib.auth import get_user_model
|
from django.contrib.auth import get_user_model
|
||||||
from django.urls import reverse
|
from django.urls import reverse
|
||||||
from django.utils import timezone
|
|
||||||
|
|
||||||
from apps.feeds.models import Feed
|
|
||||||
from apps.feeds.tasks import poll_due_feeds
|
|
||||||
|
|
||||||
from .models import SiteSettings
|
from .models import SiteSettings
|
||||||
|
|
||||||
@@ -30,26 +23,6 @@ def test_load_returns_the_existing_row_without_creating_a_second_one():
|
|||||||
assert SiteSettings.objects.count() == 1
|
assert SiteSettings.objects.count() == 1
|
||||||
|
|
||||||
|
|
||||||
@pytest.mark.django_db
|
|
||||||
def test_poll_due_feeds_uses_the_site_wide_interval_for_every_feed():
|
|
||||||
SiteSettings.objects.create(fetch_interval_minutes=120)
|
|
||||||
due = Feed.objects.create(
|
|
||||||
feed_url="https://a.example.com/feed.xml",
|
|
||||||
last_fetched_at=timezone.now() - timedelta(minutes=150),
|
|
||||||
)
|
|
||||||
not_due = Feed.objects.create(
|
|
||||||
feed_url="https://b.example.com/feed.xml",
|
|
||||||
last_fetched_at=timezone.now() - timedelta(minutes=90),
|
|
||||||
)
|
|
||||||
|
|
||||||
with patch("apps.feeds.tasks.fetch_feed.delay") as mock_delay:
|
|
||||||
poll_due_feeds()
|
|
||||||
|
|
||||||
dispatched_ids = {call.args[0] for call in mock_delay.call_args_list}
|
|
||||||
assert dispatched_ids == {due.id}
|
|
||||||
assert not_due.id not in dispatched_ids
|
|
||||||
|
|
||||||
|
|
||||||
@pytest.mark.django_db
|
@pytest.mark.django_db
|
||||||
def test_admin_changelist_redirects_straight_to_the_change_form(client):
|
def test_admin_changelist_redirects_straight_to_the_change_form(client):
|
||||||
assert not SiteSettings.objects.exists()
|
assert not SiteSettings.objects.exists()
|
||||||
|
|||||||
@@ -0,0 +1,24 @@
|
|||||||
|
# Generated by Django 5.2.18 on 2026-10-31 22:00
|
||||||
|
|
||||||
|
from django.db import migrations, models
|
||||||
|
|
||||||
|
|
||||||
|
class Migration(migrations.Migration):
|
||||||
|
|
||||||
|
dependencies = [
|
||||||
|
("feeds", "0004_remove_feed_fetch_interval_minutes"),
|
||||||
|
]
|
||||||
|
|
||||||
|
operations = [
|
||||||
|
migrations.AddField(
|
||||||
|
model_name="feed",
|
||||||
|
name="next_fetch_at",
|
||||||
|
field=models.DateTimeField(blank=True, null=True),
|
||||||
|
),
|
||||||
|
migrations.AddIndex(
|
||||||
|
model_name="feed",
|
||||||
|
index=models.Index(
|
||||||
|
fields=["is_active", "next_fetch_at"], name="feeds_feed_is_acti_5c232e_idx"
|
||||||
|
),
|
||||||
|
),
|
||||||
|
]
|
||||||
@@ -0,0 +1,49 @@
|
|||||||
|
from datetime import timedelta
|
||||||
|
|
||||||
|
from django.conf import settings
|
||||||
|
from django.db import migrations
|
||||||
|
|
||||||
|
|
||||||
|
def backfill_next_fetch_at(apps, schema_editor):
|
||||||
|
"""One-time backfill for feeds that existed before next_fetch_at (C1) —
|
||||||
|
everything created after this migration gets it set by fetch_feed
|
||||||
|
itself. Mirrors the exact formula apps.feeds.services.fetcher.
|
||||||
|
effective_interval_minutes used to compute on every poll tick, just
|
||||||
|
run once here instead of forever after.
|
||||||
|
"""
|
||||||
|
Feed = apps.get_model("feeds", "Feed")
|
||||||
|
SiteSettings = apps.get_model("core", "SiteSettings")
|
||||||
|
|
||||||
|
configured_interval = 60
|
||||||
|
settings_row = SiteSettings.objects.filter(pk=1).first()
|
||||||
|
if settings_row is not None:
|
||||||
|
configured_interval = settings_row.fetch_interval_minutes
|
||||||
|
|
||||||
|
floor = getattr(settings, "EVECTION_MIN_FETCH_INTERVAL_MINUTES", 15)
|
||||||
|
base = max(configured_interval, floor)
|
||||||
|
max_backoff = 24 * 60
|
||||||
|
|
||||||
|
for feed in Feed.objects.filter(last_fetched_at__isnull=False).only(
|
||||||
|
"id", "last_fetched_at", "fetch_error_count"
|
||||||
|
):
|
||||||
|
if feed.fetch_error_count <= 0:
|
||||||
|
interval = base
|
||||||
|
else:
|
||||||
|
interval = min(base * (2**feed.fetch_error_count), max_backoff)
|
||||||
|
feed.next_fetch_at = feed.last_fetched_at + timedelta(minutes=interval)
|
||||||
|
feed.save(update_fields=["next_fetch_at"])
|
||||||
|
|
||||||
|
|
||||||
|
def noop_reverse(apps, schema_editor):
|
||||||
|
pass
|
||||||
|
|
||||||
|
|
||||||
|
class Migration(migrations.Migration):
|
||||||
|
dependencies = [
|
||||||
|
("feeds", "0005_feed_next_fetch_at_and_more"),
|
||||||
|
("core", "0001_initial"),
|
||||||
|
]
|
||||||
|
|
||||||
|
operations = [
|
||||||
|
migrations.RunPython(backfill_next_fetch_at, noop_reverse),
|
||||||
|
]
|
||||||
@@ -42,6 +42,15 @@ class Feed(models.Model):
|
|||||||
fetch_error_count = models.PositiveIntegerField(default=0)
|
fetch_error_count = models.PositiveIntegerField(default=0)
|
||||||
is_active = models.BooleanField(default=True)
|
is_active = models.BooleanField(default=True)
|
||||||
|
|
||||||
|
# Set by fetch_feed right after every fetch attempt (success or error)
|
||||||
|
# to last_fetched_at + effective_interval_minutes — precomputed once,
|
||||||
|
# at write time, instead of poll_due_feeds re-deriving due-ness (which
|
||||||
|
# depends on fetch_error_count's exponential backoff) for every active
|
||||||
|
# feed on every tick (C1). NULL means "due now", same as a feed that's
|
||||||
|
# never been fetched. Indexed with is_active below so the scheduler's
|
||||||
|
# query is a direct index range scan, not a full table scan.
|
||||||
|
next_fetch_at = models.DateTimeField(null=True, blank=True)
|
||||||
|
|
||||||
# Set by poll_due_feeds' atomic claim (an UPDATE ... WHERE clause, not
|
# Set by poll_due_feeds' atomic claim (an UPDATE ... WHERE clause, not
|
||||||
# select_for_update — Celery Beat and fetch_feed run in separate
|
# select_for_update — Celery Beat and fetch_feed run in separate
|
||||||
# transactions) and cleared once fetch_feed finishes, so overlapping
|
# transactions) and cleared once fetch_feed finishes, so overlapping
|
||||||
@@ -53,6 +62,9 @@ class Feed(models.Model):
|
|||||||
|
|
||||||
created_at = models.DateTimeField(auto_now_add=True)
|
created_at = models.DateTimeField(auto_now_add=True)
|
||||||
|
|
||||||
|
class Meta:
|
||||||
|
indexes = [models.Index(fields=["is_active", "next_fetch_at"])]
|
||||||
|
|
||||||
def __str__(self):
|
def __str__(self):
|
||||||
return self.title or self.feed_url
|
return self.title or self.feed_url
|
||||||
|
|
||||||
|
|||||||
+34
-23
@@ -22,27 +22,31 @@ logger = logging.getLogger(__name__)
|
|||||||
# while a worker that died mid-fetch doesn't wedge the feed forever.
|
# while a worker that died mid-fetch doesn't wedge the feed forever.
|
||||||
CLAIM_STALE_MINUTES = 10
|
CLAIM_STALE_MINUTES = 10
|
||||||
|
|
||||||
|
# Caps how many feeds one poll_due_feeds tick will claim/dispatch, so a
|
||||||
|
# large backlog (first run after a long outage, a huge import) spreads
|
||||||
|
# across several beat ticks instead of enqueuing everything — and every
|
||||||
|
# bounded Feed query below stays index-only work, not a full scan (C1).
|
||||||
|
POLL_BATCH_SIZE = 500
|
||||||
|
|
||||||
|
|
||||||
@shared_task
|
@shared_task
|
||||||
def poll_due_feeds():
|
def poll_due_feeds():
|
||||||
"""Find every active Feed whose polling interval has elapsed, atomically
|
"""Find a bounded batch of active Feeds whose next_fetch_at has
|
||||||
claim it (so overlapping beat ticks or a slow-running previous fetch
|
elapsed (set by fetch_feed itself after every attempt — see Feed.
|
||||||
can't dispatch the same feed twice), and dispatch a fetch_feed task for
|
next_fetch_at), atomically claim them (so overlapping beat ticks or a
|
||||||
each claimed feed — fan-out happens here, not via one Celery Beat entry
|
slow-running previous fetch can't dispatch the same feed twice), and
|
||||||
per feed.
|
dispatch a fetch_feed task for each claimed feed — fan-out happens
|
||||||
|
here, not via one Celery Beat entry per feed.
|
||||||
"""
|
"""
|
||||||
now = timezone.now()
|
now = timezone.now()
|
||||||
claim_stale_before = now - timedelta(minutes=CLAIM_STALE_MINUTES)
|
claim_stale_before = now - timedelta(minutes=CLAIM_STALE_MINUTES)
|
||||||
# Loaded once per call, not per feed — the interval is site-wide
|
due_feed_ids = list(
|
||||||
# (apps.core.models.SiteSettings), so every feed below shares it.
|
Feed.objects.filter(is_active=True)
|
||||||
configured_interval = SiteSettings.load().fetch_interval_minutes
|
.filter(Q(next_fetch_at__isnull=True) | Q(next_fetch_at__lte=now))
|
||||||
due_feed_ids = [
|
.filter(Q(claimed_at__isnull=True) | Q(claimed_at__lt=claim_stale_before))
|
||||||
feed.id
|
.order_by("next_fetch_at")
|
||||||
for feed in Feed.objects.filter(is_active=True).only(
|
.values_list("id", flat=True)[:POLL_BATCH_SIZE]
|
||||||
"id", "last_fetched_at", "fetch_error_count"
|
)
|
||||||
)
|
|
||||||
if _is_due(feed, configured_interval)
|
|
||||||
]
|
|
||||||
claimed_ids = []
|
claimed_ids = []
|
||||||
for feed_id in due_feed_ids:
|
for feed_id in due_feed_ids:
|
||||||
# The UPDATE's WHERE clause re-checks staleness at the database
|
# The UPDATE's WHERE clause re-checks staleness at the database
|
||||||
@@ -61,11 +65,14 @@ def poll_due_feeds():
|
|||||||
return len(claimed_ids)
|
return len(claimed_ids)
|
||||||
|
|
||||||
|
|
||||||
def _is_due(feed: Feed, configured_interval_minutes: int) -> bool:
|
def _schedule_next_fetch(feed: Feed) -> None:
|
||||||
if feed.last_fetched_at is None:
|
"""Sets feed.next_fetch_at from its (just-updated) fetch_error_count —
|
||||||
return True
|
called right before every feed.save() in fetch_feed, so the next
|
||||||
interval = effective_interval_minutes(feed, configured_interval_minutes)
|
poll_due_feeds tick can find it with a plain indexed range query
|
||||||
return feed.last_fetched_at <= timezone.now() - timedelta(minutes=interval)
|
instead of recomputing every active feed's backoff in Python (C1)."""
|
||||||
|
configured_interval = SiteSettings.load().fetch_interval_minutes
|
||||||
|
interval = effective_interval_minutes(feed, configured_interval)
|
||||||
|
feed.next_fetch_at = timezone.now() + timedelta(minutes=interval)
|
||||||
|
|
||||||
|
|
||||||
# Bounds a single feed's fetch+parse+ingest, independent of
|
# Bounds a single feed's fetch+parse+ingest, independent of
|
||||||
@@ -102,10 +109,12 @@ def fetch_feed(feed_id: int):
|
|||||||
record_fetch_error(feed, "Unexpected error — see worker logs")
|
record_fetch_error(feed, "Unexpected error — see worker logs")
|
||||||
feed.last_fetched_at = timezone.now()
|
feed.last_fetched_at = timezone.now()
|
||||||
feed.claimed_at = None
|
feed.claimed_at = None
|
||||||
|
_schedule_next_fetch(feed)
|
||||||
feed.save()
|
feed.save()
|
||||||
raise
|
raise
|
||||||
|
|
||||||
feed.claimed_at = None
|
feed.claimed_at = None
|
||||||
|
_schedule_next_fetch(feed)
|
||||||
feed.save()
|
feed.save()
|
||||||
|
|
||||||
changed_article_ids = result.new_article_ids + result.updated_article_ids
|
changed_article_ids = result.new_article_ids + result.updated_article_ids
|
||||||
@@ -127,9 +136,11 @@ def fetch_feed(feed_id: int):
|
|||||||
|
|
||||||
@shared_task
|
@shared_task
|
||||||
def reset_feed_backoff(feed_id: int):
|
def reset_feed_backoff(feed_id: int):
|
||||||
"""Admin-triggered: clear a feed's error count so it's retried at its
|
"""Admin-triggered: clear a feed's error count and due-date backoff so
|
||||||
normal configured interval instead of the backed-off one."""
|
it's retried at its normal configured interval instead of the backed-
|
||||||
Feed.objects.filter(pk=feed_id).update(fetch_error_count=0)
|
off one (next_fetch_at=None also makes it immediately due for the
|
||||||
|
next poll_due_feeds tick, same as a feed that's never been fetched)."""
|
||||||
|
Feed.objects.filter(pk=feed_id).update(fetch_error_count=0, next_fetch_at=None)
|
||||||
|
|
||||||
|
|
||||||
@shared_task
|
@shared_task
|
||||||
|
|||||||
@@ -12,18 +12,23 @@ from apps.feeds.tasks import fetch_feed, poll_due_feeds
|
|||||||
|
|
||||||
@pytest.mark.django_db
|
@pytest.mark.django_db
|
||||||
def test_poll_due_feeds_dispatches_only_due_feeds():
|
def test_poll_due_feeds_dispatches_only_due_feeds():
|
||||||
|
# next_fetch_at (set by fetch_feed itself, C1), not last_fetched_at,
|
||||||
|
# is what poll_due_feeds' query filters on now.
|
||||||
never_fetched = Feed.objects.create(feed_url="https://a.example.com/feed.xml")
|
never_fetched = Feed.objects.create(feed_url="https://a.example.com/feed.xml")
|
||||||
recently_fetched = Feed.objects.create(
|
recently_fetched = Feed.objects.create(
|
||||||
feed_url="https://b.example.com/feed.xml",
|
feed_url="https://b.example.com/feed.xml",
|
||||||
last_fetched_at=timezone.now(),
|
last_fetched_at=timezone.now(),
|
||||||
|
next_fetch_at=timezone.now() + timedelta(hours=1),
|
||||||
)
|
)
|
||||||
overdue = Feed.objects.create(
|
overdue = Feed.objects.create(
|
||||||
feed_url="https://c.example.com/feed.xml",
|
feed_url="https://c.example.com/feed.xml",
|
||||||
last_fetched_at=timezone.now() - timedelta(hours=2),
|
last_fetched_at=timezone.now() - timedelta(hours=2),
|
||||||
|
next_fetch_at=timezone.now() - timedelta(hours=1),
|
||||||
)
|
)
|
||||||
inactive_but_overdue = Feed.objects.create(
|
inactive_but_overdue = Feed.objects.create(
|
||||||
feed_url="https://d.example.com/feed.xml",
|
feed_url="https://d.example.com/feed.xml",
|
||||||
last_fetched_at=timezone.now() - timedelta(hours=2),
|
last_fetched_at=timezone.now() - timedelta(hours=2),
|
||||||
|
next_fetch_at=timezone.now() - timedelta(hours=1),
|
||||||
is_active=False,
|
is_active=False,
|
||||||
)
|
)
|
||||||
|
|
||||||
@@ -45,6 +50,7 @@ def test_poll_due_feeds_does_not_reclaim_a_feed_it_just_claimed():
|
|||||||
overdue = Feed.objects.create(
|
overdue = Feed.objects.create(
|
||||||
feed_url="https://c.example.com/feed.xml",
|
feed_url="https://c.example.com/feed.xml",
|
||||||
last_fetched_at=timezone.now() - timedelta(hours=2),
|
last_fetched_at=timezone.now() - timedelta(hours=2),
|
||||||
|
next_fetch_at=timezone.now() - timedelta(hours=1),
|
||||||
)
|
)
|
||||||
|
|
||||||
with patch("apps.feeds.tasks.fetch_feed.delay") as mock_delay:
|
with patch("apps.feeds.tasks.fetch_feed.delay") as mock_delay:
|
||||||
@@ -65,6 +71,7 @@ def test_poll_due_feeds_reclaims_a_stale_claim():
|
|||||||
overdue = Feed.objects.create(
|
overdue = Feed.objects.create(
|
||||||
feed_url="https://c.example.com/feed.xml",
|
feed_url="https://c.example.com/feed.xml",
|
||||||
last_fetched_at=timezone.now() - timedelta(hours=2),
|
last_fetched_at=timezone.now() - timedelta(hours=2),
|
||||||
|
next_fetch_at=timezone.now() - timedelta(hours=1),
|
||||||
claimed_at=timezone.now() - timedelta(minutes=CLAIM_STALE_MINUTES + 1),
|
claimed_at=timezone.now() - timedelta(minutes=CLAIM_STALE_MINUTES + 1),
|
||||||
)
|
)
|
||||||
|
|
||||||
@@ -141,3 +148,63 @@ def test_fetch_feed_task_records_error_and_clears_claim_on_unexpected_exception(
|
|||||||
assert feed.fetch_error_count == 1
|
assert feed.fetch_error_count == 1
|
||||||
assert feed.claimed_at is None
|
assert feed.claimed_at is None
|
||||||
assert feed.last_fetched_at is not None
|
assert feed.last_fetched_at is not None
|
||||||
|
assert feed.next_fetch_at is not None
|
||||||
|
|
||||||
|
|
||||||
|
@pytest.mark.django_db
|
||||||
|
@responses.activate
|
||||||
|
def test_fetch_feed_task_sets_next_fetch_at_so_poll_due_feeds_can_find_it_later():
|
||||||
|
"""next_fetch_at (C1) is what poll_due_feeds' query filters on — a
|
||||||
|
feed fetch_feed just succeeded on must come back due again only after
|
||||||
|
the configured interval, not immediately."""
|
||||||
|
feed = Feed.objects.create(feed_url="https://example.com/feed.xml")
|
||||||
|
responses.add(responses.GET, feed.feed_url, body=GOOD_FEED_XML, status=200)
|
||||||
|
|
||||||
|
fetch_feed(feed.id)
|
||||||
|
|
||||||
|
feed.refresh_from_db()
|
||||||
|
assert feed.next_fetch_at is not None
|
||||||
|
assert feed.next_fetch_at > timezone.now()
|
||||||
|
|
||||||
|
with patch("apps.feeds.tasks.fetch_feed.delay") as mock_delay:
|
||||||
|
poll_due_feeds()
|
||||||
|
mock_delay.assert_not_called()
|
||||||
|
|
||||||
|
|
||||||
|
@pytest.mark.django_db
|
||||||
|
def test_reset_feed_backoff_makes_the_feed_immediately_due():
|
||||||
|
from apps.feeds.tasks import reset_feed_backoff
|
||||||
|
|
||||||
|
feed = Feed.objects.create(
|
||||||
|
feed_url="https://example.com/feed.xml",
|
||||||
|
fetch_error_count=5,
|
||||||
|
last_fetched_at=timezone.now(),
|
||||||
|
next_fetch_at=timezone.now() + timedelta(hours=12),
|
||||||
|
)
|
||||||
|
|
||||||
|
reset_feed_backoff(feed.id)
|
||||||
|
|
||||||
|
feed.refresh_from_db()
|
||||||
|
assert feed.fetch_error_count == 0
|
||||||
|
assert feed.next_fetch_at is None
|
||||||
|
|
||||||
|
|
||||||
|
@pytest.mark.django_db
|
||||||
|
@responses.activate
|
||||||
|
def test_fetch_feed_schedules_the_next_fetch_using_the_site_wide_interval():
|
||||||
|
"""fetch_feed (not poll_due_feeds — see apps.feeds.tasks.
|
||||||
|
_schedule_next_fetch, C1) is what reads SiteSettings' site-wide
|
||||||
|
interval and sets Feed.next_fetch_at from it after every fetch."""
|
||||||
|
from apps.core.models import SiteSettings
|
||||||
|
|
||||||
|
SiteSettings.objects.create(fetch_interval_minutes=120)
|
||||||
|
feed = Feed.objects.create(feed_url="https://example.com/feed.xml")
|
||||||
|
responses.add(responses.GET, feed.feed_url, body=GOOD_FEED_XML, status=200)
|
||||||
|
|
||||||
|
before = timezone.now()
|
||||||
|
fetch_feed(feed.id)
|
||||||
|
feed.refresh_from_db()
|
||||||
|
|
||||||
|
assert feed.next_fetch_at is not None
|
||||||
|
expected = before + timedelta(minutes=120)
|
||||||
|
assert abs((feed.next_fetch_at - expected).total_seconds()) < 5
|
||||||
@@ -289,3 +289,57 @@ def test_stream_exposes_the_latest_article_id_and_scope_for_the_banner(client, a
|
|||||||
|
|
||||||
assert f"since={article.pk}" in content
|
assert f"since={article.pk}" in content
|
||||||
assert "filter=all" in content
|
assert "filter=all" in content
|
||||||
|
|
||||||
|
|
||||||
|
@pytest.mark.django_db
|
||||||
|
def test_sidebar_unread_count_updates_immediately_after_reading_an_article(client, alice):
|
||||||
|
"""unread_counts_by_feed caches its result for a short TTL (C3) — the
|
||||||
|
reader views that change the current user's own read state must
|
||||||
|
invalidate it, or the sidebar would show a stale count until the TTL
|
||||||
|
elapses on every one of these very common actions."""
|
||||||
|
feed = Feed.objects.create(feed_url="https://example.com/feed.xml")
|
||||||
|
Subscription.objects.create(user=alice, feed=feed)
|
||||||
|
article = Article.objects.create(feed=feed, guid="a-1", title="Hello")
|
||||||
|
|
||||||
|
client.login(username="alice", password="pw-alice-123")
|
||||||
|
|
||||||
|
response = client.get(reverse("reader:stream"))
|
||||||
|
assert '<span class="unread-count">1</span>' in response.content.decode()
|
||||||
|
|
||||||
|
client.get(reverse("reader:article_detail", args=[article.pk]))
|
||||||
|
|
||||||
|
response = client.get(reverse("reader:stream"))
|
||||||
|
assert "unread-count" not in response.content.decode()
|
||||||
|
|
||||||
|
|
||||||
|
@pytest.mark.django_db
|
||||||
|
def test_sidebar_unread_count_updates_immediately_after_toggle_read(client, alice):
|
||||||
|
feed = Feed.objects.create(feed_url="https://example.com/feed.xml")
|
||||||
|
Subscription.objects.create(user=alice, feed=feed)
|
||||||
|
article = Article.objects.create(feed=feed, guid="a-1", title="Hello")
|
||||||
|
UserArticleState.objects.create(user=alice, article=article, is_read=True)
|
||||||
|
|
||||||
|
client.login(username="alice", password="pw-alice-123")
|
||||||
|
response = client.get(reverse("reader:stream"))
|
||||||
|
assert "unread-count" not in response.content.decode()
|
||||||
|
|
||||||
|
client.post(reverse("reader:toggle_read", args=[article.pk]))
|
||||||
|
|
||||||
|
response = client.get(reverse("reader:stream"))
|
||||||
|
assert '<span class="unread-count">1</span>' in response.content.decode()
|
||||||
|
|
||||||
|
|
||||||
|
@pytest.mark.django_db
|
||||||
|
def test_sidebar_unread_count_updates_immediately_after_mark_all_read(client, alice):
|
||||||
|
feed = Feed.objects.create(feed_url="https://example.com/feed.xml")
|
||||||
|
Subscription.objects.create(user=alice, feed=feed)
|
||||||
|
Article.objects.create(feed=feed, guid="a-1", title="Hello")
|
||||||
|
|
||||||
|
client.login(username="alice", password="pw-alice-123")
|
||||||
|
response = client.get(reverse("reader:stream"))
|
||||||
|
assert '<span class="unread-count">1</span>' in response.content.decode()
|
||||||
|
|
||||||
|
client.post(reverse("reader:mark_all_read"))
|
||||||
|
|
||||||
|
response = client.get(reverse("reader:stream"))
|
||||||
|
assert "unread-count" not in response.content.decode()
|
||||||
@@ -19,6 +19,7 @@ from apps.articles.models import (
|
|||||||
get_system_tag,
|
get_system_tag,
|
||||||
)
|
)
|
||||||
from apps.articles.queries import with_user_state
|
from apps.articles.queries import with_user_state
|
||||||
|
from apps.core.cache_utils import invalidate_sidebar_unread_cache
|
||||||
from apps.feeds.models import Feed
|
from apps.feeds.models import Feed
|
||||||
|
|
||||||
FILTER_CHOICES = [
|
FILTER_CHOICES = [
|
||||||
@@ -240,6 +241,7 @@ def mark_all_read(request):
|
|||||||
for aid in new_article_ids
|
for aid in new_article_ids
|
||||||
]
|
]
|
||||||
)
|
)
|
||||||
|
invalidate_sidebar_unread_cache(request.user.pk)
|
||||||
|
|
||||||
stream_url = reverse("reader:stream")
|
stream_url = reverse("reader:stream")
|
||||||
query = request.GET.urlencode()
|
query = request.GET.urlencode()
|
||||||
@@ -254,6 +256,7 @@ def _load_article_and_mark_read(user, article_id):
|
|||||||
state.is_read = True
|
state.is_read = True
|
||||||
state.read_at = timezone.now()
|
state.read_at = timezone.now()
|
||||||
state.save(update_fields=["is_read", "read_at"])
|
state.save(update_fields=["is_read", "read_at"])
|
||||||
|
invalidate_sidebar_unread_cache(user.pk)
|
||||||
|
|
||||||
article.is_read = state.is_read
|
article.is_read = state.is_read
|
||||||
article.is_starred, article.is_saved_for_later = _article_tag_flags(user, article)
|
article.is_starred, article.is_saved_for_later = _article_tag_flags(user, article)
|
||||||
@@ -285,6 +288,7 @@ def toggle_read(request, article_id):
|
|||||||
state.is_read = not state.is_read
|
state.is_read = not state.is_read
|
||||||
state.read_at = timezone.now() if state.is_read else None
|
state.read_at = timezone.now() if state.is_read else None
|
||||||
state.save(update_fields=["is_read", "read_at"])
|
state.save(update_fields=["is_read", "read_at"])
|
||||||
|
invalidate_sidebar_unread_cache(request.user.pk)
|
||||||
|
|
||||||
article.is_read = state.is_read
|
article.is_read = state.is_read
|
||||||
article.is_starred, article.is_saved_for_later = _article_tag_flags(request.user, article)
|
article.is_starred, article.is_saved_for_later = _article_tag_flags(request.user, article)
|
||||||
|
|||||||
@@ -0,0 +1,23 @@
|
|||||||
|
# Generated by Django 5.2.18 on 2026-10-31 22:05
|
||||||
|
|
||||||
|
from django.conf import settings
|
||||||
|
from django.db import migrations, models
|
||||||
|
|
||||||
|
|
||||||
|
class Migration(migrations.Migration):
|
||||||
|
|
||||||
|
dependencies = [
|
||||||
|
("articles", "0004_starred_saved_as_system_tags"),
|
||||||
|
("feeds", "0006_backfill_feed_next_fetch_at"),
|
||||||
|
("rules", "0002_folder_scope_to_tag_scope"),
|
||||||
|
migrations.swappable_dependency(settings.AUTH_USER_MODEL),
|
||||||
|
]
|
||||||
|
|
||||||
|
operations = [
|
||||||
|
migrations.AddIndex(
|
||||||
|
model_name="filterrule",
|
||||||
|
index=models.Index(
|
||||||
|
fields=["user", "is_enabled", "priority"], name="rules_filte_user_id_dcb19b_idx"
|
||||||
|
),
|
||||||
|
),
|
||||||
|
]
|
||||||
@@ -75,6 +75,16 @@ class FilterRule(models.Model):
|
|||||||
|
|
||||||
class Meta:
|
class Meta:
|
||||||
ordering = ["priority", "id"]
|
ordering = ["priority", "id"]
|
||||||
|
indexes = [
|
||||||
|
# Matches the ingest-time query shape exactly (C9): every
|
||||||
|
# caller — apps.articles.tasks.apply_filter_rules_for_feed,
|
||||||
|
# apps.rules.tasks.reapply_rules_for_user_backlog — filters by
|
||||||
|
# (user, is_enabled) and orders by priority. `user` alone
|
||||||
|
# already has an index from the ForeignKey, but it doesn't
|
||||||
|
# cover is_enabled or let the database satisfy the ORDER BY
|
||||||
|
# from the index itself.
|
||||||
|
models.Index(fields=["user", "is_enabled", "priority"]),
|
||||||
|
]
|
||||||
|
|
||||||
def __str__(self):
|
def __str__(self):
|
||||||
label = self.name or f"{self.get_match_field_display()} {self.get_match_type_display()}"
|
label = self.name or f"{self.get_match_field_display()} {self.get_match_type_display()}"
|
||||||
|
|||||||
+14
@@ -1,8 +1,22 @@
|
|||||||
import pytest
|
import pytest
|
||||||
|
from django.core.cache import cache
|
||||||
|
|
||||||
from apps.accounts.middleware import SetupWizardMiddleware
|
from apps.accounts.middleware import SetupWizardMiddleware
|
||||||
|
|
||||||
|
|
||||||
|
@pytest.fixture(autouse=True)
|
||||||
|
def _reset_django_cache():
|
||||||
|
"""config.settings.test overrides CACHES to LocMemCache, which — like
|
||||||
|
SetupWizardMiddleware's own cache below — lives in process memory and
|
||||||
|
survives Django's per-test DB rollback. Without this, a cached
|
||||||
|
sidebar unread count (apps.core.cache_utils) keyed by a user's pk
|
||||||
|
could leak into a later, unrelated test that happens to create a user
|
||||||
|
with the same auto-incrementing pk."""
|
||||||
|
cache.clear()
|
||||||
|
yield
|
||||||
|
cache.clear()
|
||||||
|
|
||||||
|
|
||||||
@pytest.fixture(autouse=True)
|
@pytest.fixture(autouse=True)
|
||||||
def _reset_setup_wizard_cache():
|
def _reset_setup_wizard_cache():
|
||||||
"""SetupWizardMiddleware caches "does any User exist" on the class
|
"""SetupWizardMiddleware caches "does any User exist" on the class
|
||||||
|
|||||||
@@ -274,6 +274,25 @@ next paragraph for why it matters). Whichever proxy you use,
|
|||||||
headers that need forwarding either way, including that overwrite-not-
|
headers that need forwarding either way, including that overwrite-not-
|
||||||
append distinction for `X-Forwarded-For`.
|
append distinction for `X-Forwarded-For`.
|
||||||
|
|
||||||
|
**Nginx Proxy Manager specifically:** NPM's generated config already sets
|
||||||
|
`X-Forwarded-For` to the appending (unsafe) form by default — override it
|
||||||
|
per proxy host rather than editing NPM's own templates: open the proxy
|
||||||
|
host entry for Evection, go to its **Advanced** tab, and add this to the
|
||||||
|
**Custom Nginx Configuration** box:
|
||||||
|
|
||||||
|
```nginx
|
||||||
|
proxy_set_header X-Forwarded-For $remote_addr;
|
||||||
|
```
|
||||||
|
|
||||||
|
This lands inside NPM's own `location` block, after its default headers,
|
||||||
|
so nginx uses this one (the last `proxy_set_header` for a given name in
|
||||||
|
the same block wins) — no edit to any file NPM manages, and it survives
|
||||||
|
NPM regenerating its config. Save, and NPM reloads nginx for you. If
|
||||||
|
something else sits in front of NPM itself (a CDN, another load balancer,
|
||||||
|
Cloudflare, ...), `$remote_addr` at NPM's layer is that upstream's
|
||||||
|
address, not the original client — forward whatever *that* layer's own
|
||||||
|
trusted client-IP header says instead.
|
||||||
|
|
||||||
Either way, the proxy must set `X-Forwarded-Proto: https` on requests it
|
Either way, the proxy must set `X-Forwarded-Proto: https` on requests it
|
||||||
forwards once it's terminating TLS — Evection's `prod` settings
|
forwards once it's terminating TLS — Evection's `prod` settings
|
||||||
(`SECURE_PROXY_SSL_HEADER` in `config/settings/prod.py`) trust that header to
|
(`SECURE_PROXY_SSL_HEADER` in `config/settings/prod.py`) trust that header to
|
||||||
|
|||||||
Reference in new issue
Block a user