Private
Public Access
Compare commits
6
Commits
| Author | SHA1 | Date | |
|---|---|---|---|
|
|
fd494a9c08 | ||
|
|
f8cd1eb33e | ||
|
|
73dbee9400 | ||
|
|
6c6227af57 | ||
|
|
c339d456e4 | ||
|
|
7afda7d0ba |
No files matched your search
@@ -54,6 +54,18 @@ ruff check .
|
||||
black --check .
|
||||
```
|
||||
|
||||
### Testing against PostgreSQL
|
||||
|
||||
The suite runs on SQLite by default; the Postgres-only tests (search backend)
|
||||
are skipped there. To run everything against a real Postgres:
|
||||
|
||||
```bash
|
||||
docker run -d --name evection-pg-test -e POSTGRES_PASSWORD=testpw -e POSTGRES_DB=evection \
|
||||
-p 127.0.0.1:55432:5432 postgres:16
|
||||
DATABASE_URL=postgres://postgres:testpw@127.0.0.1:55432/evection pytest
|
||||
docker rm -f evection-pg-test
|
||||
```
|
||||
|
||||
## License
|
||||
|
||||
[GNU AGPL-3.0-or-later](LICENSE) — if you run a modified version of Evection as
|
||||
|
||||
@@ -0,0 +1,27 @@
|
||||
# Generated by Django 5.2.18 on 2026-11-01 16:28
|
||||
|
||||
import django.db.models.deletion
|
||||
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'),
|
||||
]
|
||||
|
||||
operations = [
|
||||
migrations.CreateModel(
|
||||
name='PurgedArticle',
|
||||
fields=[
|
||||
('id', models.BigAutoField(auto_created=True, primary_key=True, serialize=False, verbose_name='ID')),
|
||||
('guid', models.CharField(max_length=1000)),
|
||||
('purged_at', models.DateTimeField(auto_now_add=True)),
|
||||
('feed', models.ForeignKey(on_delete=django.db.models.deletion.CASCADE, related_name='purged_articles', to='feeds.feed')),
|
||||
],
|
||||
options={
|
||||
'unique_together': {('feed', 'guid')},
|
||||
},
|
||||
),
|
||||
]
|
||||
@@ -32,6 +32,23 @@ class Article(models.Model):
|
||||
return self.title or self.guid
|
||||
|
||||
|
||||
class PurgedArticle(models.Model):
|
||||
"""Tombstone left by the retention purge (apps.articles.tasks.
|
||||
purge_old_articles) for every article it deletes: a feed that still
|
||||
lists an entry after we purged it would otherwise be re-inserted as a
|
||||
brand-new, unread article on its next poll. Ingestion skips any guid
|
||||
that has a tombstone here. Only the (feed, guid) pair is kept — a
|
||||
small fraction of the article it replaces.
|
||||
"""
|
||||
|
||||
feed = models.ForeignKey(Feed, on_delete=models.CASCADE, related_name="purged_articles")
|
||||
guid = models.CharField(max_length=1000)
|
||||
purged_at = models.DateTimeField(auto_now_add=True)
|
||||
|
||||
class Meta:
|
||||
unique_together = [("feed", "guid")]
|
||||
|
||||
|
||||
class UserArticleState(models.Model):
|
||||
"""Per-user read/hide state for an Article.
|
||||
|
||||
|
||||
+13
-3
@@ -1,6 +1,7 @@
|
||||
from datetime import timedelta
|
||||
|
||||
from celery import shared_task
|
||||
from django.db import transaction
|
||||
from django.utils import timezone
|
||||
|
||||
from apps.core.models import SiteSettings
|
||||
@@ -8,7 +9,7 @@ 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
|
||||
from .models import Article, ArticleTag, PurgedArticle, SubscriptionTag
|
||||
|
||||
|
||||
@shared_task
|
||||
@@ -75,6 +76,10 @@ def purge_old_articles():
|
||||
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).
|
||||
|
||||
Each deleted article leaves a PurgedArticle tombstone first, so a feed
|
||||
that still lists the entry can't bring it back as a new, unread
|
||||
article on its next poll (see apps.feeds.services.fetcher).
|
||||
"""
|
||||
retention_days = SiteSettings.load().retention_days
|
||||
if retention_days <= 0:
|
||||
@@ -87,9 +92,14 @@ def purge_old_articles():
|
||||
chunk = list(
|
||||
Article.objects.filter(fetched_at__lt=cutoff)
|
||||
.exclude(pk__in=keep)
|
||||
.values_list("pk", flat=True)[:PURGE_CHUNK_SIZE]
|
||||
.values_list("pk", "feed_id", "guid")[:PURGE_CHUNK_SIZE]
|
||||
)
|
||||
if not chunk:
|
||||
return deleted_total
|
||||
Article.objects.filter(pk__in=chunk).delete()
|
||||
with transaction.atomic():
|
||||
PurgedArticle.objects.bulk_create(
|
||||
[PurgedArticle(feed_id=feed_id, guid=guid) for _pk, feed_id, guid in chunk],
|
||||
ignore_conflicts=True,
|
||||
)
|
||||
Article.objects.filter(pk__in=[pk for pk, _feed_id, _guid in chunk]).delete()
|
||||
deleted_total += len(chunk)
|
||||
@@ -72,3 +72,20 @@ def test_purge_works_through_more_than_one_chunk(feed, monkeypatch):
|
||||
|
||||
assert purge_old_articles() == 5
|
||||
assert Article.objects.count() == 0
|
||||
|
||||
|
||||
@pytest.mark.django_db
|
||||
def test_purge_leaves_a_tombstone_per_deleted_article(feed):
|
||||
from .models import PurgedArticle
|
||||
|
||||
SiteSettings.objects.create(retention_days=30)
|
||||
_article(feed, "gone-1", age_days=60)
|
||||
_article(feed, "gone-2", age_days=60)
|
||||
_article(feed, "kept", age_days=1)
|
||||
|
||||
purge_old_articles()
|
||||
|
||||
assert set(PurgedArticle.objects.filter(feed=feed).values_list("guid", flat=True)) == {
|
||||
"gone-1",
|
||||
"gone-2",
|
||||
}
|
||||
@@ -0,0 +1,83 @@
|
||||
from datetime import timedelta
|
||||
|
||||
import redis
|
||||
from django.conf import settings
|
||||
from django.db.models import Max, Min
|
||||
from django.utils import timezone
|
||||
|
||||
from apps.feeds.models import Feed
|
||||
|
||||
from .models import SiteSettings
|
||||
|
||||
# More than this many tasks waiting means workers aren't keeping up (or
|
||||
# aren't running) — fetches are piling up faster than they complete.
|
||||
MAX_QUEUE_DEPTH = 1000
|
||||
|
||||
# Past this share of active feeds failing, it's far more likely something
|
||||
# on our side (DNS, outbound network, a bad deploy) than every publisher
|
||||
# breaking at once. Needs a handful of feeds first so one broken feed out
|
||||
# of two doesn't read as an outage.
|
||||
MAX_FAILING_RATIO = 0.5
|
||||
MIN_FEEDS_FOR_RATIO = 4
|
||||
|
||||
MIN_SUCCESS_WINDOW_MINUTES = 30
|
||||
|
||||
|
||||
def queue_depth() -> int | None:
|
||||
"""Tasks waiting in Celery's default queue, or None if the broker
|
||||
can't be reached. Celery's Redis transport keeps each queue as a Redis
|
||||
list named after the queue."""
|
||||
try:
|
||||
client = redis.Redis.from_url(
|
||||
settings.CELERY_BROKER_URL, socket_connect_timeout=2, socket_timeout=2
|
||||
)
|
||||
return int(client.llen("celery"))
|
||||
except Exception:
|
||||
return None
|
||||
|
||||
|
||||
def _success_window() -> timedelta:
|
||||
floor = getattr(settings, "EVECTION_MIN_FETCH_INTERVAL_MINUTES", 15)
|
||||
base = max(SiteSettings.load().fetch_interval_minutes, floor)
|
||||
return timedelta(minutes=max(3 * base, MIN_SUCCESS_WINDOW_MINUTES))
|
||||
|
||||
|
||||
def fetch_pipeline_status(now=None) -> tuple[dict[str, bool], dict]:
|
||||
"""Checks that fetching is actually *succeeding*, not just scheduled
|
||||
(the poll heartbeat only proves beat and a worker are alive): returns
|
||||
({check: passed}, detail) covering queue depth, whether any feed has
|
||||
been fetched successfully recently, and the share of feeds failing.
|
||||
"""
|
||||
now = now or timezone.now()
|
||||
detail: dict = {}
|
||||
|
||||
depth = queue_depth()
|
||||
detail["queue_depth"] = depth
|
||||
checks = {"queue_depth": depth is not None and depth <= MAX_QUEUE_DEPTH}
|
||||
|
||||
active = Feed.objects.filter(is_active=True)
|
||||
active_count = active.count()
|
||||
failing = active.filter(fetch_error_count__gt=0).count()
|
||||
detail["active_feeds"] = active_count
|
||||
detail["failing_feeds"] = failing
|
||||
|
||||
window = _success_window()
|
||||
last_success = active.filter(
|
||||
last_fetch_status__in=[Feed.STATUS_OK, Feed.STATUS_NOT_MODIFIED]
|
||||
).aggregate(latest=Max("last_fetched_at"))["latest"]
|
||||
if last_success is not None:
|
||||
detail["last_successful_fetch_age_seconds"] = int((now - last_success).total_seconds())
|
||||
recent_success = now - last_success <= window
|
||||
elif active_count == 0:
|
||||
recent_success = True
|
||||
else:
|
||||
# Nothing has ever fetched successfully — only a problem once
|
||||
# the oldest feed has had a full window to be fetched.
|
||||
oldest = active.aggregate(oldest=Min("created_at"))["oldest"]
|
||||
recent_success = now - oldest <= window
|
||||
checks["recent_fetch_success"] = recent_success
|
||||
|
||||
checks["feed_failures"] = not (
|
||||
active_count >= MIN_FEEDS_FOR_RATIO and failing / active_count > MAX_FAILING_RATIO
|
||||
)
|
||||
return checks, detail
|
||||
+137
-4
@@ -22,8 +22,17 @@ def test_health_check_works_before_first_run_setup(client):
|
||||
assert response.status_code == 200
|
||||
|
||||
|
||||
@pytest.fixture
|
||||
def broker_queue(monkeypatch):
|
||||
"""Stands in for the Redis broker's queue length (tests have no Redis):
|
||||
set `broker_queue["depth"]` to a number, or None for "unreachable"."""
|
||||
state = {"depth": 0}
|
||||
monkeypatch.setattr("apps.core.health.queue_depth", lambda: state["depth"])
|
||||
return state
|
||||
|
||||
|
||||
@pytest.mark.django_db
|
||||
def test_health_ready_is_degraded_until_a_poll_tick_has_happened(client):
|
||||
def test_health_ready_is_degraded_until_a_poll_tick_has_happened(client, broker_queue):
|
||||
response = client.get(reverse("core:health_ready"))
|
||||
assert response.status_code == 503
|
||||
body = response.json()
|
||||
@@ -34,22 +43,26 @@ def test_health_ready_is_degraded_until_a_poll_tick_has_happened(client):
|
||||
|
||||
|
||||
@pytest.mark.django_db
|
||||
def test_health_ready_is_ok_after_poll_due_feeds_runs(client):
|
||||
def test_health_ready_is_ok_after_poll_due_feeds_runs(client, broker_queue):
|
||||
from apps.feeds.tasks import poll_due_feeds
|
||||
|
||||
poll_due_feeds()
|
||||
|
||||
response = client.get(reverse("core:health_ready"))
|
||||
assert response.status_code == 200
|
||||
assert response.json()["checks"] == {
|
||||
checks = response.json()["checks"]
|
||||
assert checks == {
|
||||
"database": True,
|
||||
"redis": True,
|
||||
"poll_heartbeat": True,
|
||||
"queue_depth": True,
|
||||
"recent_fetch_success": True,
|
||||
"feed_failures": True,
|
||||
}
|
||||
|
||||
|
||||
@pytest.mark.django_db
|
||||
def test_health_ready_flags_a_stale_poll_heartbeat(client):
|
||||
def test_health_ready_flags_a_stale_poll_heartbeat(client, broker_queue):
|
||||
from datetime import timedelta
|
||||
|
||||
from django.core.cache import cache
|
||||
@@ -119,3 +132,123 @@ def test_retry_feed_resets_backoff_and_requeues(client, django_user_model):
|
||||
assert response.status_code == 302
|
||||
mock_reset.assert_called_once_with(feed.id)
|
||||
mock_fetch.assert_called_once_with(feed.id)
|
||||
|
||||
|
||||
def _ready(client):
|
||||
from django.core.cache import cache
|
||||
from django.utils import timezone
|
||||
|
||||
from apps.feeds.tasks import POLL_HEARTBEAT_CACHE_KEY
|
||||
|
||||
# Record the heartbeat directly: running poll_due_feeds here would
|
||||
# execute fetches eagerly (CELERY_TASK_ALWAYS_EAGER) and rewrite the
|
||||
# feed states each test sets up.
|
||||
cache.set(POLL_HEARTBEAT_CACHE_KEY, timezone.now())
|
||||
response = client.get(reverse("core:health_ready"))
|
||||
return response.status_code, response.json()
|
||||
|
||||
|
||||
@pytest.mark.django_db
|
||||
def test_health_ready_flags_a_backed_up_queue(client, broker_queue):
|
||||
from .health import MAX_QUEUE_DEPTH
|
||||
|
||||
broker_queue["depth"] = MAX_QUEUE_DEPTH + 1
|
||||
|
||||
status, body = _ready(client)
|
||||
|
||||
assert status == 503
|
||||
assert body["checks"]["queue_depth"] is False
|
||||
assert body["queue_depth"] == MAX_QUEUE_DEPTH + 1
|
||||
|
||||
|
||||
@pytest.mark.django_db
|
||||
def test_health_ready_flags_an_unreachable_broker_queue(client, broker_queue):
|
||||
broker_queue["depth"] = None
|
||||
|
||||
status, body = _ready(client)
|
||||
|
||||
assert status == 503
|
||||
assert body["checks"]["queue_depth"] is False
|
||||
|
||||
|
||||
@pytest.mark.django_db
|
||||
def test_health_ready_flags_no_recent_successful_fetch(client, broker_queue):
|
||||
from datetime import timedelta
|
||||
|
||||
from django.utils import timezone
|
||||
|
||||
feed = Feed.objects.create(
|
||||
feed_url="https://a.example.com/feed.xml",
|
||||
last_fetch_status=Feed.STATUS_OK,
|
||||
last_fetched_at=timezone.now() - timedelta(days=2),
|
||||
)
|
||||
Feed.objects.filter(pk=feed.pk).update(created_at=timezone.now() - timedelta(days=30))
|
||||
|
||||
status, body = _ready(client)
|
||||
|
||||
assert status == 503
|
||||
assert body["checks"]["recent_fetch_success"] is False
|
||||
assert body["last_successful_fetch_age_seconds"] > 86400
|
||||
|
||||
|
||||
@pytest.mark.django_db
|
||||
def test_health_ready_is_ok_with_a_recent_successful_fetch(client, broker_queue):
|
||||
from django.utils import timezone
|
||||
|
||||
Feed.objects.create(
|
||||
feed_url="https://a.example.com/feed.xml",
|
||||
last_fetch_status=Feed.STATUS_NOT_MODIFIED,
|
||||
last_fetched_at=timezone.now(),
|
||||
)
|
||||
|
||||
status, body = _ready(client)
|
||||
|
||||
assert status == 200
|
||||
assert body["active_feeds"] == 1
|
||||
assert body["failing_feeds"] == 0
|
||||
|
||||
|
||||
@pytest.mark.django_db
|
||||
def test_health_ready_gives_a_brand_new_feed_time_before_it_counts_as_stale(client, broker_queue):
|
||||
Feed.objects.create(feed_url="https://new.example.com/feed.xml")
|
||||
|
||||
status, body = _ready(client)
|
||||
|
||||
assert status == 200
|
||||
assert body["checks"]["recent_fetch_success"] is True
|
||||
|
||||
|
||||
@pytest.mark.django_db
|
||||
def test_health_ready_flags_most_feeds_failing_but_not_a_single_broken_one(client, broker_queue):
|
||||
from django.utils import timezone
|
||||
|
||||
now = timezone.now()
|
||||
healthy = Feed.objects.create(
|
||||
feed_url="https://ok.example.com/feed.xml",
|
||||
last_fetch_status=Feed.STATUS_OK,
|
||||
last_fetched_at=now,
|
||||
)
|
||||
broken = [
|
||||
Feed.objects.create(
|
||||
feed_url=f"https://bad{i}.example.com/feed.xml",
|
||||
last_fetch_status=Feed.STATUS_ERROR,
|
||||
fetch_error_count=3,
|
||||
last_fetched_at=now,
|
||||
)
|
||||
for i in range(2)
|
||||
]
|
||||
|
||||
status, body = _ready(client)
|
||||
assert status == 200, "2 of 3 failing is below the minimum feed count for the ratio"
|
||||
|
||||
Feed.objects.create(
|
||||
feed_url="https://bad9.example.com/feed.xml",
|
||||
last_fetch_status=Feed.STATUS_ERROR,
|
||||
fetch_error_count=1,
|
||||
last_fetched_at=now,
|
||||
)
|
||||
status, body = _ready(client)
|
||||
assert status == 503
|
||||
assert body["checks"]["feed_failures"] is False
|
||||
assert body["failing_feeds"] == 3
|
||||
assert healthy.pk and broken
|
||||
+10
-1
@@ -12,6 +12,8 @@ from apps.articles.models import Article
|
||||
from apps.feeds.models import Feed, Subscription
|
||||
from apps.feeds.tasks import POLL_HEARTBEAT_CACHE_KEY, fetch_feed, reset_feed_backoff
|
||||
|
||||
from .health import fetch_pipeline_status
|
||||
|
||||
is_admin = user_passes_test(lambda u: u.is_authenticated and u.is_staff)
|
||||
|
||||
|
||||
@@ -37,7 +39,9 @@ def health_ready(request):
|
||||
"""Readiness: liveness plus everything background fetching depends on
|
||||
(C8) — the database, the Redis cache/broker, and a recent
|
||||
poll_due_feeds tick, which proves beat is scheduling AND a worker is
|
||||
consuming. /health/ above stays DB-only on purpose: scripts/upgrade.sh
|
||||
consuming. Beyond that tick, apps.core.health checks fetching is
|
||||
actually succeeding: queue depth, a recent successful fetch, and the
|
||||
share of feeds failing. /health/ above stays DB-only on purpose: scripts/upgrade.sh
|
||||
gates a deploy on it right after restart, before beat has had a
|
||||
chance to tick. Point an uptime monitor at this one instead."""
|
||||
checks = {"database": False, "redis": False, "poll_heartbeat": False}
|
||||
@@ -65,6 +69,11 @@ def health_ready(request):
|
||||
detail["poll_heartbeat_age_seconds"] = int(age)
|
||||
checks["poll_heartbeat"] = age <= POLL_HEARTBEAT_MAX_AGE_SECONDS
|
||||
|
||||
if checks["database"]:
|
||||
pipeline_checks, pipeline_detail = fetch_pipeline_status()
|
||||
checks.update(pipeline_checks)
|
||||
detail.update(pipeline_detail)
|
||||
|
||||
ok = all(checks.values())
|
||||
return JsonResponse(
|
||||
{"status": "ok" if ok else "degraded", "checks": checks, **detail},
|
||||
|
||||
@@ -11,7 +11,7 @@ import hashlib
|
||||
import logging
|
||||
from calendar import timegm
|
||||
from dataclasses import dataclass
|
||||
from datetime import datetime
|
||||
from datetime import datetime, timedelta
|
||||
from datetime import timezone as dt_timezone
|
||||
|
||||
import feedparser
|
||||
@@ -21,7 +21,8 @@ from django.conf import settings
|
||||
from django.db import IntegrityError, transaction
|
||||
from django.utils import timezone
|
||||
|
||||
from apps.articles.models import Article
|
||||
from apps.articles.models import Article, PurgedArticle
|
||||
from apps.core.models import SiteSettings
|
||||
from apps.feeds.models import Feed
|
||||
|
||||
from .ssrf_guard import SSRFBlocked, safe_get
|
||||
@@ -263,6 +264,24 @@ def fetch_and_ingest(feed: Feed) -> FetchResult:
|
||||
"content_hash": _content_hash(title, link, author, summary, content_html, published_at),
|
||||
}
|
||||
|
||||
# Entries the retention purge already deleted (tombstoned) and, when
|
||||
# retention is on, entries so old by their own publish date that the
|
||||
# next purge would delete them again, are not (re-)ingested — see
|
||||
# apps.articles.tasks.purge_old_articles.
|
||||
retention_days = SiteSettings.load().retention_days
|
||||
if retention_days > 0:
|
||||
too_old_before = timezone.now() - timedelta(days=retention_days)
|
||||
for guid in [
|
||||
g
|
||||
for g, f in parsed_entries.items()
|
||||
if f["published_at"] is not None and f["published_at"] < too_old_before
|
||||
]:
|
||||
del parsed_entries[guid]
|
||||
for guid in PurgedArticle.objects.filter(feed=feed, guid__in=parsed_entries).values_list(
|
||||
"guid", flat=True
|
||||
):
|
||||
del parsed_entries[guid]
|
||||
|
||||
existing = {a.guid: a for a in Article.objects.filter(feed=feed, guid__in=parsed_entries)}
|
||||
|
||||
to_create = [
|
||||
|
||||
@@ -338,3 +338,64 @@ def test_ingest_falls_back_to_row_by_row_when_a_concurrent_insert_wins(feed):
|
||||
|
||||
assert len(result.new_article_ids) == 3
|
||||
assert Article.objects.filter(feed=feed).count() == 3
|
||||
|
||||
|
||||
@pytest.mark.django_db
|
||||
@responses.activate
|
||||
def test_purged_article_is_not_resurrected_by_a_feed_that_still_lists_it(feed):
|
||||
"""#29: a feed still listing an entry the retention purge deleted must
|
||||
not bring it back as a brand-new, unread article."""
|
||||
from apps.articles.tasks import purge_old_articles
|
||||
from apps.core.models import SiteSettings
|
||||
|
||||
SiteSettings.objects.create(retention_days=30)
|
||||
responses.add(responses.GET, FEED_URL, body=_feed_xml(3), status=200)
|
||||
fetch_and_ingest(feed)
|
||||
Article.objects.filter(feed=feed, guid="guid-0").update(
|
||||
fetched_at=timezone.now() - dt.timedelta(days=90)
|
||||
)
|
||||
assert purge_old_articles() == 1
|
||||
assert not Article.objects.filter(feed=feed, guid="guid-0").exists()
|
||||
|
||||
result = fetch_and_ingest(feed)
|
||||
|
||||
assert result.new_article_ids == []
|
||||
assert not Article.objects.filter(feed=feed, guid="guid-0").exists()
|
||||
assert Article.objects.filter(feed=feed).count() == 2
|
||||
|
||||
|
||||
@pytest.mark.django_db
|
||||
@responses.activate
|
||||
def test_entries_older_than_the_retention_window_are_not_ingested(feed):
|
||||
"""With retention on, a feed's long archive isn't ingested only to be
|
||||
purged (and tombstoned) the same night."""
|
||||
from apps.core.models import SiteSettings
|
||||
|
||||
SiteSettings.objects.create(retention_days=30)
|
||||
xml = (
|
||||
'<?xml version="1.0"?><rss version="2.0"><channel><title>T</title>'
|
||||
"<item><title>Ancient</title><guid>old</guid>"
|
||||
"<pubDate>Mon, 01 Jan 2024 00:00:00 GMT</pubDate></item>"
|
||||
"<item><title>Undated</title><guid>undated</guid></item>"
|
||||
"</channel></rss>"
|
||||
)
|
||||
responses.add(responses.GET, FEED_URL, body=xml, status=200)
|
||||
|
||||
result = fetch_and_ingest(feed)
|
||||
|
||||
assert len(result.new_article_ids) == 1
|
||||
assert Article.objects.filter(feed=feed).get().guid == "undated"
|
||||
|
||||
|
||||
@pytest.mark.django_db
|
||||
@responses.activate
|
||||
def test_old_entries_are_ingested_normally_when_retention_is_off(feed):
|
||||
xml = (
|
||||
'<?xml version="1.0"?><rss version="2.0"><channel><title>T</title>'
|
||||
"<item><title>Ancient</title><guid>old</guid>"
|
||||
"<pubDate>Mon, 01 Jan 2024 00:00:00 GMT</pubDate></item>"
|
||||
"</channel></rss>"
|
||||
)
|
||||
responses.add(responses.GET, FEED_URL, body=xml, status=200)
|
||||
|
||||
assert len(fetch_and_ingest(feed).new_article_ids) == 1
|
||||
+68
-3
@@ -204,7 +204,7 @@ def test_article_rows_carry_their_utc_instant_for_client_side_date_grouping(clie
|
||||
dated = Article.objects.create(
|
||||
feed=feed, guid="dated", title="Dated", published_at=timezone.now()
|
||||
)
|
||||
undated = Article.objects.create(feed=feed, guid="undated", title="Undated")
|
||||
undated = Article.objects.create(feed=feed, guid="undated", title="No publish date")
|
||||
|
||||
client.login(username="alice", password="pw-alice-123")
|
||||
response = client.get(reverse("reader:stream"), {"filter": "all"})
|
||||
@@ -214,9 +214,15 @@ def test_article_rows_carry_their_utc_instant_for_client_side_date_grouping(clie
|
||||
assert f'id="article-{dated.pk}"' in content
|
||||
assert f'data-published-utc="{expected_iso}"' in content
|
||||
|
||||
undated_row = re.search(rf'<li id="article-{undated.pk}".*?>', content, flags=re.DOTALL)
|
||||
# A feed that gave no publish date falls back to when it was fetched
|
||||
# (the same fallback the stream's sort order uses), so the row still
|
||||
# carries a time and groups under a real date, not "Undated".
|
||||
undated_row = re.search(rf'<li id="article-{undated.pk}".*?</li>', content, flags=re.DOTALL)
|
||||
assert undated_row is not None
|
||||
assert 'data-published-utc=""' in undated_row.group(0)
|
||||
row_html = undated_row.group(0)
|
||||
assert f'data-published-utc="{undated.fetched_at.isoformat()}"' in row_html
|
||||
assert 'class="article-time"' in row_html
|
||||
assert "Undated" not in content
|
||||
|
||||
|
||||
@pytest.mark.django_db
|
||||
@@ -438,3 +444,62 @@ def test_stream_pagination_links_keep_the_feed_scope(client, alice):
|
||||
_, content = _stream_article_ids(client, {"filter": "all", "feed": feed.pk})
|
||||
|
||||
assert _link_query(content, "Older")["feed"] == str(feed.pk)
|
||||
|
||||
|
||||
def test_templates_use_no_inline_event_handlers():
|
||||
"""Production's CSP (script-src 'self') blocks inline on*= handlers —
|
||||
they work in dev, where no CSP is sent, and silently do nothing in
|
||||
production. Behavior belongs in static/js."""
|
||||
from pathlib import Path
|
||||
|
||||
from django.conf import settings
|
||||
|
||||
pattern = re.compile(r"""<[^>]+\s(on[a-z]+)\s*=""", re.IGNORECASE)
|
||||
offenders = []
|
||||
for template in Path(settings.BASE_DIR, "templates").rglob("*.html"):
|
||||
for match in pattern.finditer(template.read_text()):
|
||||
offenders.append(f"{template.name}: {match.group(1)}")
|
||||
assert offenders == []
|
||||
|
||||
|
||||
@pytest.mark.django_db
|
||||
def test_article_detail_back_link_keeps_the_stream_scope(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="g1", title="Hello")
|
||||
|
||||
client.login(username="alice", password="pw-alice-123")
|
||||
stream = client.get(
|
||||
reverse("reader:stream"), {"filter": "all", "feed": feed.pk}
|
||||
).content.decode()
|
||||
link = re.search(r'href="(/articles/\d+/\?[^"]+)"', stream)
|
||||
assert link is not None
|
||||
|
||||
detail = client.get(link.group(1).replace("&", "&")).content.decode()
|
||||
assert f"filter=all&feed={feed.pk}" in detail
|
||||
assert "Back to stream" in detail
|
||||
assert article.title in detail
|
||||
|
||||
|
||||
@pytest.mark.django_db
|
||||
def test_article_with_no_publish_date_shows_when_it_was_fetched(client, alice):
|
||||
"""A feed that gives no date is treated as published when we fetched
|
||||
it — in the list row, its group header, and the open article's header
|
||||
— without storing an invented value on the article itself."""
|
||||
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="g1", title="No publish date")
|
||||
assert article.published_at is None
|
||||
|
||||
client.login(username="alice", password="pw-alice-123")
|
||||
iso = article.fetched_at.isoformat()
|
||||
|
||||
stream = client.get(reverse("reader:stream"), {"filter": "all"}).content.decode()
|
||||
assert f'datetime="{iso}"' in stream
|
||||
assert "Received today" in stream
|
||||
|
||||
detail = client.get(reverse("reader:article_detail", args=[article.pk])).content.decode()
|
||||
assert f'datetime="{iso}"' in detail
|
||||
|
||||
article.refresh_from_db()
|
||||
assert article.published_at is None
|
||||
+11
-2
@@ -113,7 +113,8 @@ def _group_by_date(articles):
|
||||
today = timezone.localdate()
|
||||
|
||||
def day_of(article):
|
||||
return timezone.localtime(article.published_at).date() if article.published_at else None
|
||||
when = article.published_at or article.fetched_at
|
||||
return timezone.localtime(when).date() if when else None
|
||||
|
||||
return [
|
||||
{"label": _date_label(day, today), "articles": list(items)}
|
||||
@@ -238,6 +239,7 @@ def stream(request):
|
||||
# regardless of how a feed backdates an entry's published date.
|
||||
"latest_article_id": queryset.aggregate(Max("id"))["id__max"] or 0,
|
||||
"new_check_qs": urlencode(scope_params),
|
||||
"scope_qs": urlencode(scope_params),
|
||||
}
|
||||
return render(request, "reader/stream.html", context)
|
||||
|
||||
@@ -311,7 +313,14 @@ def _load_article_and_mark_read(user, article_id):
|
||||
@login_required
|
||||
def article_detail(request, article_id):
|
||||
article = _load_article_and_mark_read(request.user, article_id)
|
||||
return render(request, "reader/article_detail.html", {"article": article})
|
||||
# The stream passes its filter/tag/feed scope through the link so
|
||||
# "Back to stream" returns to it instead of resetting to every feed.
|
||||
back_params = {k: request.GET[k] for k in ("filter", "tag", "feed") if request.GET.get(k)}
|
||||
return render(
|
||||
request,
|
||||
"reader/article_detail.html",
|
||||
{"article": article, "back_qs": urlencode(back_params)},
|
||||
)
|
||||
|
||||
|
||||
@login_required
|
||||
|
||||
+22
-6
@@ -314,17 +314,33 @@ misconfigured feed or an outage at the source.
|
||||
|
||||
`/health/` is an unauthenticated liveness check (DB connectivity only) —
|
||||
`scripts/upgrade.sh` uses it to confirm a deploy actually came back up.
|
||||
Point an external uptime monitor at `/health/ready/` instead: it also checks
|
||||
Redis and that the background poller has ticked in the last five minutes
|
||||
(proving Celery beat is scheduling *and* a worker is consuming), and returns
|
||||
503 with a per-check breakdown when any of them fails — so "the site loads
|
||||
but nothing is being fetched" actually alerts.
|
||||
Point an external uptime monitor at `/health/ready/` instead. It returns 503
|
||||
with a per-check breakdown when any of these fail:
|
||||
|
||||
- `database` and `redis` — reachable.
|
||||
- `poll_heartbeat` — the background poller ticked in the last five minutes
|
||||
(proves Celery beat is scheduling *and* a worker is consuming).
|
||||
- `queue_depth` — no more than 1000 tasks waiting in the Celery queue
|
||||
(workers aren't keeping up, or aren't running).
|
||||
- `recent_fetch_success` — at least one feed has been fetched successfully
|
||||
within three poll intervals (minimum 30 minutes), so "scheduled but every
|
||||
fetch is failing" is caught. A brand-new install gets that long before it
|
||||
counts as stale.
|
||||
- `feed_failures` — no more than half of your active feeds are failing, once
|
||||
you have at least four (a handful of dead feeds is normal; most of them
|
||||
failing at once points at your server, DNS, or outbound network).
|
||||
|
||||
The payload also reports `queue_depth`, `active_feeds`, `failing_feeds`, and
|
||||
the age of the last successful fetch, so you can graph them.
|
||||
|
||||
**Retention.** By default every fetched article is kept forever. In the Django
|
||||
admin, "Site settings" has a *Retention days* field: set it to delete articles
|
||||
fetched longer ago than that, nightly (03:30 UTC, via Celery beat). Articles
|
||||
anyone has starred or saved for later are always kept; read state and tags for
|
||||
deleted articles go with them. The dashboard shows the article count and the
|
||||
deleted articles go with them. A small record (feed and entry id) is kept for
|
||||
each deleted article so a feed that still lists it can't bring it back as new
|
||||
and unread, and entries whose own publish date is already older than the window
|
||||
aren't fetched in the first place. The dashboard shows the article count and the
|
||||
age of the oldest one, so you can see what retention is doing.
|
||||
|
||||
**SQLite.** SQLite installs run in WAL mode with a 20-second busy timeout (set
|
||||
|
||||
@@ -559,6 +559,7 @@ form p {
|
||||
font-size: 0.8rem;
|
||||
color: var(--text-dim);
|
||||
flex: 0 0 auto;
|
||||
white-space: nowrap;
|
||||
}
|
||||
|
||||
.article-actions {
|
||||
|
||||
@@ -4,7 +4,7 @@
|
||||
// instant plus a UTC-formatted fallback as their initial text, and this
|
||||
// reformats them using the browser's own timezone, client-side, so the
|
||||
// server never needs to know (or guess) where the viewer actually is.
|
||||
var SHORT_OPTIONS = { hour: "numeric", minute: "2-digit" };
|
||||
var SHORT_OPTIONS = { month: "short", day: "numeric", hour: "numeric", minute: "2-digit" };
|
||||
var LONG_OPTIONS = {
|
||||
year: "numeric",
|
||||
month: "short",
|
||||
@@ -21,6 +21,10 @@
|
||||
var date = new Date(iso);
|
||||
if (isNaN(date.getTime())) return;
|
||||
var options = el.dataset.localFormat === "short" ? SHORT_OPTIONS : LONG_OPTIONS;
|
||||
if (options === SHORT_OPTIONS && date.getFullYear() !== new Date().getFullYear()) {
|
||||
// Date-only rows from a previous year would otherwise be ambiguous.
|
||||
options = Object.assign({ year: "numeric" }, SHORT_OPTIONS);
|
||||
}
|
||||
try {
|
||||
el.textContent = date.toLocaleString(undefined, options);
|
||||
} catch (e) {
|
||||
|
||||
+23
-5
@@ -1,8 +1,11 @@
|
||||
function toggleArticle(event, id) {
|
||||
event.preventDefault();
|
||||
var link = event.currentTarget;
|
||||
// Delegated listeners, not inline onclick="" attributes: production's
|
||||
// Content Security Policy (config/settings/prod.py, script-src 'self')
|
||||
// blocks inline event handlers, which silently turned the title click into
|
||||
// a plain link to the detail page and the new-articles banner into a no-op.
|
||||
|
||||
function toggleArticle(link) {
|
||||
var row = link.closest("li.article-row");
|
||||
var body = document.getElementById("article-body-" + id);
|
||||
var body = row.querySelector(".article-inline-body");
|
||||
var wasOpen = row.classList.contains("is-expanded");
|
||||
|
||||
document.querySelectorAll("li.article-row.is-expanded").forEach(function (openRow) {
|
||||
@@ -25,5 +28,20 @@ function toggleArticle(event, id) {
|
||||
);
|
||||
}
|
||||
}
|
||||
return false;
|
||||
}
|
||||
|
||||
document.addEventListener("click", function (event) {
|
||||
var link = event.target.closest("a.article-title[data-inline-url]");
|
||||
if (link) {
|
||||
// Leave modified clicks alone so "open in new tab" still works.
|
||||
if (event.button !== 0 || event.ctrlKey || event.metaKey || event.shiftKey || event.altKey) {
|
||||
return;
|
||||
}
|
||||
event.preventDefault();
|
||||
toggleArticle(link);
|
||||
return;
|
||||
}
|
||||
if (event.target.closest(".new-articles-banner")) {
|
||||
location.reload();
|
||||
}
|
||||
});
|
||||
@@ -3,9 +3,8 @@
|
||||
<p class="article-meta">
|
||||
{% if article.feed.favicon_url %}<img src="{{ article.feed.favicon_url }}" alt="" class="feed-favicon">{% endif %}
|
||||
{{ article.feed.title }}
|
||||
{% if article.published_at %}
|
||||
· <time datetime="{{ article.published_at|date:"c" }}" data-local-format="long">{{ article.published_at|date:"M j, Y H:i" }}</time>
|
||||
{% endif %}
|
||||
{# fetched_at stands in when the feed gave no publish date #}
|
||||
· <time datetime="{{ article.published_at|default:article.fetched_at|date:"c" }}" data-local-format="long">{{ article.published_at|default:article.fetched_at|date:"M j, Y H:i" }}</time>
|
||||
{% if article.author %} · {{ article.author }}{% endif %}
|
||||
{% if article.link %} · <a href="{{ article.link }}" target="_blank" rel="noopener noreferrer">Original ↗</a>{% endif %}
|
||||
</p>
|
||||
|
||||
@@ -1,17 +1,15 @@
|
||||
<li id="article-{{ article.pk }}" class="article-row{% if article.is_read %} is-read{% endif %}"
|
||||
data-published-utc="{% if article.published_at %}{{ article.published_at|date:"c" }}{% endif %}">
|
||||
data-published-utc="{{ article.published_at|default:article.fetched_at|date:"c" }}">
|
||||
<div class="article-row-main">
|
||||
{% include "reader/_article_actions.html" %}
|
||||
{% if article.feed.favicon_url %}
|
||||
<img src="{{ article.feed.favicon_url }}" alt="" class="feed-favicon">
|
||||
{% endif %}
|
||||
<span class="article-feed-name">{{ article.feed.title|default:article.feed.feed_url }}</span>
|
||||
<a href="{% url 'reader:article_detail' article.pk %}" class="article-title"
|
||||
data-inline-url="{% url 'reader:article_inline' article.pk %}"
|
||||
onclick="return toggleArticle(event, {{ article.pk }})">{{ article.title|default:"(untitled)" }}</a>
|
||||
{% if article.published_at %}
|
||||
<time class="article-time" datetime="{{ article.published_at|date:"c" }}" data-local-format="short">{{ article.published_at|date:"g:i A" }}</time>
|
||||
{% endif %}
|
||||
<a href="{% url 'reader:article_detail' article.pk %}{% if scope_qs %}?{{ scope_qs }}{% endif %}" class="article-title"
|
||||
data-inline-url="{% url 'reader:article_inline' article.pk %}">{{ article.title|default:"(untitled)" }}</a>
|
||||
{# fetched_at stands in when a feed gives no publish date — same fallback the stream's sort order uses #}
|
||||
<time class="article-time" datetime="{{ article.published_at|default:article.fetched_at|date:"c" }}" data-local-format="short">{{ article.published_at|default:article.fetched_at|date:"M j, g:i A" }}</time>
|
||||
</div>
|
||||
<div id="article-body-{{ article.pk }}" class="article-inline-body" hidden></div>
|
||||
</li>
|
||||
@@ -1,5 +1,5 @@
|
||||
{% if new_count %}
|
||||
<button type="button" class="new-articles-banner" onclick="location.reload()">
|
||||
<button type="button" class="new-articles-banner">
|
||||
{{ new_count }} new article{{ new_count|pluralize }} — click to show
|
||||
</button>
|
||||
{% endif %}
|
||||
@@ -1,7 +1,7 @@
|
||||
{% extends "base.html" %}
|
||||
{% block title %}{{ article.title|default:"Article" }} — Evection{% endblock %}
|
||||
{% block content %}
|
||||
<p><a href="{% url 'reader:stream' %}">← Back to stream</a></p>
|
||||
<p><a href="{% url 'reader:stream' %}{% if back_qs %}?{{ back_qs }}{% endif %}">← Back to stream</a></p>
|
||||
<article>
|
||||
{% include "reader/_article_actions.html" %}
|
||||
{% include "reader/_article_content.html" %}
|
||||
|
||||
Reference in new issue
Block a user