Private
Public Access
Compare commits
5
Commits
| Author | SHA1 | Date | |
|---|---|---|---|
|
|
90837b339c | ||
|
|
dc8b9ff83b | ||
|
|
a1ea2e5662 | ||
|
|
9241a54958 | ||
|
|
64f25789f5 |
No files matched your search
@@ -0,0 +1,74 @@
|
||||
import pytest
|
||||
from django.contrib.auth import get_user_model
|
||||
from django.core.cache import cache
|
||||
from django.urls import reverse
|
||||
|
||||
from .views import (
|
||||
LOGIN_RATE_LIMIT_MAX_ATTEMPTS_PER_ADDRESS,
|
||||
LOGIN_RATE_LIMIT_MAX_ATTEMPTS_PER_USERNAME,
|
||||
)
|
||||
|
||||
User = get_user_model()
|
||||
|
||||
|
||||
@pytest.fixture(autouse=True)
|
||||
def _clear_rate_limit_cache():
|
||||
cache.clear()
|
||||
yield
|
||||
cache.clear()
|
||||
|
||||
|
||||
@pytest.fixture
|
||||
def alice(db):
|
||||
return User.objects.create_user("alice", password="pw-alice-123")
|
||||
|
||||
|
||||
def _bad_login(client, username="alice"):
|
||||
return client.post(reverse("accounts:login"), {"username": username, "password": "wrong"})
|
||||
|
||||
|
||||
@pytest.mark.django_db
|
||||
def test_a_single_failed_login_still_shows_the_normal_error(client, alice):
|
||||
response = _bad_login(client)
|
||||
assert response.status_code == 200
|
||||
assert b"Please enter a correct" in response.content or response.context["form"].errors
|
||||
|
||||
|
||||
@pytest.mark.django_db
|
||||
def test_correct_credentials_succeed_before_the_limit_is_hit(client, alice):
|
||||
for _ in range(3):
|
||||
_bad_login(client)
|
||||
|
||||
response = client.post(
|
||||
reverse("accounts:login"), {"username": "alice", "password": "pw-alice-123"}
|
||||
)
|
||||
assert response.status_code == 302
|
||||
|
||||
|
||||
@pytest.mark.django_db
|
||||
def test_too_many_failed_attempts_from_one_address_blocks_further_tries(client, alice):
|
||||
for _ in range(LOGIN_RATE_LIMIT_MAX_ATTEMPTS_PER_ADDRESS):
|
||||
_bad_login(client)
|
||||
|
||||
# Even the correct password is now refused — the throttle runs
|
||||
# before the form is ever validated.
|
||||
response = client.post(
|
||||
reverse("accounts:login"), {"username": "alice", "password": "pw-alice-123"}
|
||||
)
|
||||
assert response.status_code == 302
|
||||
assert response.url == reverse("accounts:login")
|
||||
assert not response.wsgi_request.user.is_authenticated
|
||||
|
||||
|
||||
@pytest.mark.django_db
|
||||
def test_too_many_failed_attempts_against_one_username_blocks_that_username(client, alice):
|
||||
bob = User.objects.create_user("bob", password="pw-bob-123")
|
||||
|
||||
for _ in range(LOGIN_RATE_LIMIT_MAX_ATTEMPTS_PER_USERNAME):
|
||||
_bad_login(client, username="alice")
|
||||
|
||||
# Same client address, different username — the per-username
|
||||
# throttle for "alice" shouldn't affect bob logging in.
|
||||
response = client.post(reverse("accounts:login"), {"username": "bob", "password": "pw-bob-123"})
|
||||
assert response.status_code == 302
|
||||
assert response.wsgi_request.user == bob
|
||||
@@ -7,11 +7,7 @@ app_name = "accounts"
|
||||
|
||||
urlpatterns = [
|
||||
path("setup/", views.setup, name="setup"),
|
||||
path(
|
||||
"login/",
|
||||
auth_views.LoginView.as_view(template_name="accounts/login.html"),
|
||||
name="login",
|
||||
),
|
||||
path("login/", views.LoginView.as_view(), name="login"),
|
||||
path("logout/", auth_views.LogoutView.as_view(), name="logout"),
|
||||
path("users/", views.manage_users, name="manage_users"),
|
||||
path("users/create/", views.create_user, name="create_user"),
|
||||
|
||||
@@ -1,6 +1,8 @@
|
||||
from django.contrib import messages
|
||||
from django.contrib.auth import login
|
||||
from django.contrib.auth.decorators import user_passes_test
|
||||
from django.contrib.auth.views import LoginView as DjangoLoginView
|
||||
from django.core.cache import cache
|
||||
from django.db import IntegrityError, transaction
|
||||
from django.shortcuts import redirect, render
|
||||
|
||||
@@ -10,6 +12,68 @@ from .models import SetupLock, User
|
||||
|
||||
is_admin = user_passes_test(lambda u: u.is_authenticated and u.is_staff)
|
||||
|
||||
# Two independent throttles, either of which can block an attempt: by
|
||||
# client address (catches one attacker spraying many usernames) and by
|
||||
# the submitted username (catches a distributed/low-and-slow attack on
|
||||
# one specific account from many addresses). Both are generous enough
|
||||
# not to lock out a user who's just fat-fingered their own password a
|
||||
# few times.
|
||||
LOGIN_RATE_LIMIT_WINDOW_SECONDS = 5 * 60
|
||||
LOGIN_RATE_LIMIT_MAX_ATTEMPTS_PER_ADDRESS = 15
|
||||
LOGIN_RATE_LIMIT_MAX_ATTEMPTS_PER_USERNAME = 8
|
||||
|
||||
|
||||
def _client_address(request) -> str:
|
||||
# gunicorn is always run behind a reverse proxy in every deployment
|
||||
# (see docs/install.md) and its bind address is never meant to be
|
||||
# reachable from outside that proxy — the same trust boundary
|
||||
# config.settings.prod already relies on for X-Forwarded-Proto. A
|
||||
# direct request (e.g. local dev) has no X-Forwarded-For and falls
|
||||
# back to REMOTE_ADDR.
|
||||
forwarded_for = request.META.get("HTTP_X_FORWARDED_FOR", "")
|
||||
if forwarded_for:
|
||||
return forwarded_for.split(",")[0].strip()
|
||||
return request.META.get("REMOTE_ADDR", "unknown")
|
||||
|
||||
|
||||
def _attempts_key(kind: str, value: str) -> str:
|
||||
return f"login-attempts:{kind}:{value}"
|
||||
|
||||
|
||||
def _too_many_attempts(key: str, limit: int) -> bool:
|
||||
return cache.get(key, 0) >= limit
|
||||
|
||||
|
||||
def _record_failed_attempt(key: str) -> None:
|
||||
try:
|
||||
cache.incr(key)
|
||||
except ValueError:
|
||||
cache.set(key, 1, LOGIN_RATE_LIMIT_WINDOW_SECONDS)
|
||||
|
||||
|
||||
class LoginView(DjangoLoginView):
|
||||
"""Wraps Django's own LoginView with the throttle above — everything
|
||||
else (form, template, redirect behavior) is unchanged."""
|
||||
|
||||
template_name = "accounts/login.html"
|
||||
|
||||
def post(self, request, *args, **kwargs):
|
||||
address_key = _attempts_key("addr", _client_address(request))
|
||||
username_key = _attempts_key("user", request.POST.get("username", "")[:150])
|
||||
if _too_many_attempts(
|
||||
address_key, LOGIN_RATE_LIMIT_MAX_ATTEMPTS_PER_ADDRESS
|
||||
) or _too_many_attempts(username_key, LOGIN_RATE_LIMIT_MAX_ATTEMPTS_PER_USERNAME):
|
||||
messages.error(
|
||||
request, "Too many login attempts. Please wait a few minutes and try again."
|
||||
)
|
||||
return redirect("accounts:login")
|
||||
return super().post(request, *args, **kwargs)
|
||||
|
||||
def form_invalid(self, form):
|
||||
_record_failed_attempt(_attempts_key("addr", _client_address(self.request)))
|
||||
_record_failed_attempt(_attempts_key("user", self.request.POST.get("username", "")[:150]))
|
||||
return super().form_invalid(form)
|
||||
|
||||
|
||||
def setup(request):
|
||||
if User.objects.exists():
|
||||
|
||||
+28
-1
@@ -1 +1,28 @@
|
||||
# Register your models here.
|
||||
from django.contrib import admin
|
||||
from django.shortcuts import redirect
|
||||
from django.urls import reverse
|
||||
|
||||
from .models import SiteSettings
|
||||
|
||||
|
||||
@admin.register(SiteSettings)
|
||||
class SiteSettingsAdmin(admin.ModelAdmin):
|
||||
"""A true singleton, not a collection — browsing a changelist to pick
|
||||
the one row and click into it is an extra, pointless step, so
|
||||
"Core > Site settings" in the sidebar goes straight to the (only)
|
||||
change form instead, creating the row first if this is a fresh
|
||||
install. No changelist/add/delete views exist at all here.
|
||||
"""
|
||||
|
||||
fields = ["fetch_interval_minutes"]
|
||||
|
||||
def has_add_permission(self, request):
|
||||
return False
|
||||
|
||||
def has_delete_permission(self, request, obj=None):
|
||||
return False
|
||||
|
||||
def changelist_view(self, request, extra_context=None):
|
||||
settings_row = SiteSettings.load()
|
||||
url = reverse("admin:core_sitesettings_change", args=[settings_row.pk])
|
||||
return redirect(url)
|
||||
@@ -0,0 +1,33 @@
|
||||
# Generated by Django 5.2.18 on 2026-10-31 18:56
|
||||
|
||||
from django.db import migrations, models
|
||||
|
||||
|
||||
class Migration(migrations.Migration):
|
||||
|
||||
initial = True
|
||||
|
||||
dependencies = []
|
||||
|
||||
operations = [
|
||||
migrations.CreateModel(
|
||||
name="SiteSettings",
|
||||
fields=[
|
||||
(
|
||||
"id",
|
||||
models.PositiveSmallIntegerField(default=1, primary_key=True, serialize=False),
|
||||
),
|
||||
(
|
||||
"fetch_interval_minutes",
|
||||
models.PositiveIntegerField(
|
||||
default=60,
|
||||
help_text="How often, in minutes, every feed is polled for new articles. Can't be set lower than EVECTION_MIN_FETCH_INTERVAL_MINUTES (see .env).",
|
||||
),
|
||||
),
|
||||
],
|
||||
options={
|
||||
"verbose_name": "Site settings",
|
||||
"verbose_name_plural": "Site settings",
|
||||
},
|
||||
),
|
||||
]
|
||||
+35
-1
@@ -1 +1,35 @@
|
||||
# Create your models here.
|
||||
from django.db import models
|
||||
|
||||
|
||||
class SiteSettings(models.Model):
|
||||
"""Singleton row (pk=1, same pattern as accounts.SetupLock) holding
|
||||
instance-wide configuration an operator reasonably wants to change
|
||||
without touching the server or .env — editable via Django admin.
|
||||
Currently just the feed-poll interval, which used to be a per-feed
|
||||
field; it's site-wide now (see apps.feeds.tasks.poll_due_feeds).
|
||||
"""
|
||||
|
||||
id = models.PositiveSmallIntegerField(primary_key=True, default=1)
|
||||
fetch_interval_minutes = models.PositiveIntegerField(
|
||||
default=60,
|
||||
help_text=(
|
||||
"How often, in minutes, every feed is polled for new articles. "
|
||||
"Can't be set lower than EVECTION_MIN_FETCH_INTERVAL_MINUTES (see .env)."
|
||||
),
|
||||
)
|
||||
|
||||
class Meta:
|
||||
verbose_name = "Site settings"
|
||||
verbose_name_plural = "Site settings"
|
||||
|
||||
def __str__(self):
|
||||
return "Site settings"
|
||||
|
||||
@classmethod
|
||||
def load(cls):
|
||||
"""Returns the singleton row, creating it with defaults on first
|
||||
use so callers never need to special-case "no row exists yet"
|
||||
(e.g. a fresh install whose first poll_due_feeds run hasn't
|
||||
created it, and whose admin hasn't visited the settings page)."""
|
||||
obj, _ = cls.objects.get_or_create(pk=1)
|
||||
return obj
|
||||
@@ -0,0 +1,84 @@
|
||||
from datetime import timedelta
|
||||
from unittest.mock import patch
|
||||
|
||||
import pytest
|
||||
from django.contrib.auth import get_user_model
|
||||
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
|
||||
|
||||
User = get_user_model()
|
||||
|
||||
|
||||
@pytest.mark.django_db
|
||||
def test_load_creates_the_singleton_row_with_defaults():
|
||||
assert not SiteSettings.objects.exists()
|
||||
settings_row = SiteSettings.load()
|
||||
assert settings_row.fetch_interval_minutes == 60
|
||||
assert SiteSettings.objects.count() == 1
|
||||
|
||||
|
||||
@pytest.mark.django_db
|
||||
def test_load_returns_the_existing_row_without_creating_a_second_one():
|
||||
SiteSettings.objects.create(fetch_interval_minutes=30)
|
||||
settings_row = SiteSettings.load()
|
||||
assert settings_row.fetch_interval_minutes == 30
|
||||
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
|
||||
def test_admin_changelist_redirects_straight_to_the_change_form(client):
|
||||
assert not SiteSettings.objects.exists()
|
||||
User.objects.create_superuser("admin", password="pw-admin-123")
|
||||
client.login(username="admin", password="pw-admin-123")
|
||||
|
||||
changelist_url = reverse("admin:core_sitesettings_changelist")
|
||||
response = client.get(changelist_url)
|
||||
|
||||
settings_row = SiteSettings.objects.get() # created by the redirect itself
|
||||
assert response.status_code == 302
|
||||
assert response.url == reverse("admin:core_sitesettings_change", args=[settings_row.pk])
|
||||
|
||||
|
||||
@pytest.mark.django_db
|
||||
def test_admin_never_offers_add_or_delete(client):
|
||||
# ModelAdmin.has_add_permission/has_delete_permission returning False
|
||||
# makes Django raise PermissionDenied rather than build a 403 response
|
||||
# directly — the test client's default behavior re-raises that for
|
||||
# debugging convenience instead of returning it as a response.
|
||||
client.raise_request_exception = False
|
||||
|
||||
User.objects.create_superuser("admin", password="pw-admin-123")
|
||||
client.login(username="admin", password="pw-admin-123")
|
||||
|
||||
response = client.get(reverse("admin:core_sitesettings_add"))
|
||||
assert response.status_code == 403
|
||||
|
||||
settings_row = SiteSettings.load()
|
||||
delete_url = reverse("admin:core_sitesettings_delete", args=[settings_row.pk])
|
||||
response = client.get(delete_url)
|
||||
assert response.status_code == 403
|
||||
@@ -0,0 +1,17 @@
|
||||
# Generated by Django 5.2.18 on 2026-10-31 18:56
|
||||
|
||||
from django.db import migrations
|
||||
|
||||
|
||||
class Migration(migrations.Migration):
|
||||
|
||||
dependencies = [
|
||||
("feeds", "0003_feed_claimed_at"),
|
||||
]
|
||||
|
||||
operations = [
|
||||
migrations.RemoveField(
|
||||
model_name="feed",
|
||||
name="fetch_interval_minutes",
|
||||
),
|
||||
]
|
||||
@@ -35,8 +35,10 @@ class Feed(models.Model):
|
||||
)
|
||||
last_error_message = models.TextField(blank=True)
|
||||
|
||||
# Instance-wide, not a per-user preference — see class docstring.
|
||||
fetch_interval_minutes = models.PositiveIntegerField(default=60)
|
||||
# The poll interval itself is site-wide now (apps.core.models.
|
||||
# SiteSettings), not per-feed — only the error-driven backoff on top
|
||||
# of it still varies per feed (see apps.feeds.services.fetcher.
|
||||
# effective_interval_minutes).
|
||||
fetch_error_count = models.PositiveIntegerField(default=0)
|
||||
is_active = models.BooleanField(default=True)
|
||||
|
||||
|
||||
@@ -31,6 +31,15 @@ FETCH_TIMEOUT_SECONDS = 15
|
||||
MAX_BACKOFF_MINUTES = 24 * 60
|
||||
USER_AGENT = "Evection/0.1 (+https://github.com/; self-hosted RSS reader)"
|
||||
|
||||
# ssrf_guard.MAX_RESPONSE_BYTES already bounds the raw download; these
|
||||
# bound what a single poll does *with* that response — a feed within the
|
||||
# byte cap can still carry an unreasonable number of entries, or one
|
||||
# entry with an unreasonably large body, and both cost real CPU/DB time
|
||||
# (nh3 sanitization, an Article row/UPDATE) per entry processed.
|
||||
MAX_ENTRIES_PER_POLL = 200
|
||||
MAX_CONTENT_HTML_INPUT_CHARS = 200_000 # bounds sanitizer cost, not just storage
|
||||
MAX_CONTENT_HTML_CHARS = 50_000 # bounds what's actually stored/rendered
|
||||
|
||||
ALLOWED_TAGS = {
|
||||
"a",
|
||||
"p",
|
||||
@@ -83,7 +92,9 @@ class FetchResult:
|
||||
def sanitize_html(raw_html: str) -> str:
|
||||
if not raw_html:
|
||||
return ""
|
||||
return nh3.clean(raw_html, tags=ALLOWED_TAGS, attributes=ALLOWED_ATTRIBUTES, link_rel=None)
|
||||
bounded = raw_html[:MAX_CONTENT_HTML_INPUT_CHARS]
|
||||
cleaned = nh3.clean(bounded, tags=ALLOWED_TAGS, attributes=ALLOWED_ATTRIBUTES, link_rel=None)
|
||||
return cleaned[:MAX_CONTENT_HTML_CHARS]
|
||||
|
||||
|
||||
def _content_hash(title: str, content_html: str) -> str:
|
||||
@@ -113,14 +124,17 @@ def _entry_content_html(entry) -> str:
|
||||
return getattr(entry, "summary", "") or ""
|
||||
|
||||
|
||||
def effective_interval_minutes(feed: Feed) -> int:
|
||||
"""The actual polling interval to use, applying exponential backoff on
|
||||
top of the admin-configured ``fetch_interval_minutes`` for feeds that
|
||||
are currently erroring. ``fetch_interval_minutes`` itself is never
|
||||
mutated by the fetcher — it's the admin's chosen baseline.
|
||||
def effective_interval_minutes(feed: Feed, configured_interval_minutes: int) -> int:
|
||||
"""The actual polling interval to use for `feed`, applying exponential
|
||||
backoff on top of the site-wide `configured_interval_minutes` (see
|
||||
apps.core.models.SiteSettings) for a feed that's currently erroring.
|
||||
Takes the configured value as a parameter rather than querying
|
||||
SiteSettings itself, since this runs once per feed (apps.feeds.tasks
|
||||
calls it from a list comprehension over every active feed) and the
|
||||
site-wide value doesn't vary by feed.
|
||||
"""
|
||||
floor = getattr(settings, "EVECTION_MIN_FETCH_INTERVAL_MINUTES", 15)
|
||||
base = max(feed.fetch_interval_minutes, floor)
|
||||
base = max(configured_interval_minutes, floor)
|
||||
if feed.fetch_error_count <= 0:
|
||||
return base
|
||||
backoff = base * (2**feed.fetch_error_count)
|
||||
@@ -144,10 +158,10 @@ def fetch_and_ingest(feed: Feed) -> FetchResult:
|
||||
response = safe_get(feed.feed_url, headers=headers, timeout=FETCH_TIMEOUT_SECONDS)
|
||||
except SSRFBlocked as exc:
|
||||
feed.last_fetched_at = timezone.now()
|
||||
return _record_error(feed, f"Refused to fetch: {exc}")
|
||||
return record_fetch_error(feed, f"Refused to fetch: {exc}")
|
||||
except requests.RequestException as exc:
|
||||
feed.last_fetched_at = timezone.now()
|
||||
return _record_error(feed, f"Request failed: {exc}")
|
||||
return record_fetch_error(feed, f"Request failed: {exc}")
|
||||
|
||||
feed.last_fetched_at = timezone.now()
|
||||
|
||||
@@ -159,12 +173,12 @@ def fetch_and_ingest(feed: Feed) -> FetchResult:
|
||||
)
|
||||
|
||||
if response.status_code >= 400:
|
||||
return _record_error(feed, f"HTTP {response.status_code}")
|
||||
return record_fetch_error(feed, f"HTTP {response.status_code}")
|
||||
|
||||
parsed = feedparser.parse(response.content)
|
||||
|
||||
if parsed.bozo and not parsed.entries:
|
||||
return _record_error(feed, f"Unparseable feed: {parsed.get('bozo_exception')}")
|
||||
return record_fetch_error(feed, f"Unparseable feed: {parsed.get('bozo_exception')}")
|
||||
|
||||
if parsed.bozo:
|
||||
logger.warning(
|
||||
@@ -186,7 +200,17 @@ def fetch_and_ingest(feed: Feed) -> FetchResult:
|
||||
new_ids: list[int] = []
|
||||
updated_ids: list[int] = []
|
||||
|
||||
for entry in parsed.entries:
|
||||
entries = parsed.entries
|
||||
if len(entries) > MAX_ENTRIES_PER_POLL:
|
||||
logger.warning(
|
||||
"Feed %s: %d entries in one poll, only processing the first %d",
|
||||
feed.feed_url,
|
||||
len(entries),
|
||||
MAX_ENTRIES_PER_POLL,
|
||||
)
|
||||
entries = entries[:MAX_ENTRIES_PER_POLL]
|
||||
|
||||
for entry in entries:
|
||||
guid = _entry_guid(entry)
|
||||
title = (getattr(entry, "title", "") or "")[:1000]
|
||||
content_html = sanitize_html(_entry_content_html(entry))
|
||||
@@ -220,7 +244,7 @@ def fetch_and_ingest(feed: Feed) -> FetchResult:
|
||||
)
|
||||
|
||||
|
||||
def _record_error(feed: Feed, message: str) -> FetchResult:
|
||||
def record_fetch_error(feed: Feed, message: str) -> FetchResult:
|
||||
feed.last_fetch_status = Feed.STATUS_ERROR
|
||||
feed.last_error_message = message[:2000]
|
||||
feed.fetch_error_count += 1
|
||||
|
||||
+39
-6
@@ -8,10 +8,11 @@ from django.db.models import Q
|
||||
from django.utils import timezone
|
||||
|
||||
from apps.articles.tasks import apply_filter_rules_for_feed
|
||||
from apps.core.models import SiteSettings
|
||||
|
||||
from .models import Feed
|
||||
from .opml import import_opml
|
||||
from .services.fetcher import effective_interval_minutes, fetch_and_ingest
|
||||
from .services.fetcher import effective_interval_minutes, fetch_and_ingest, record_fetch_error
|
||||
|
||||
logger = logging.getLogger(__name__)
|
||||
|
||||
@@ -32,12 +33,15 @@ def poll_due_feeds():
|
||||
"""
|
||||
now = timezone.now()
|
||||
claim_stale_before = now - timedelta(minutes=CLAIM_STALE_MINUTES)
|
||||
# Loaded once per call, not per feed — the interval is site-wide
|
||||
# (apps.core.models.SiteSettings), so every feed below shares it.
|
||||
configured_interval = SiteSettings.load().fetch_interval_minutes
|
||||
due_feed_ids = [
|
||||
feed.id
|
||||
for feed in Feed.objects.filter(is_active=True).only(
|
||||
"id", "last_fetched_at", "fetch_interval_minutes", "fetch_error_count"
|
||||
"id", "last_fetched_at", "fetch_error_count"
|
||||
)
|
||||
if _is_due(feed)
|
||||
if _is_due(feed, configured_interval)
|
||||
]
|
||||
claimed_ids = []
|
||||
for feed_id in due_feed_ids:
|
||||
@@ -57,21 +61,50 @@ def poll_due_feeds():
|
||||
return len(claimed_ids)
|
||||
|
||||
|
||||
def _is_due(feed: Feed) -> bool:
|
||||
def _is_due(feed: Feed, configured_interval_minutes: int) -> bool:
|
||||
if feed.last_fetched_at is None:
|
||||
return True
|
||||
interval = effective_interval_minutes(feed)
|
||||
interval = effective_interval_minutes(feed, configured_interval_minutes)
|
||||
return feed.last_fetched_at <= timezone.now() - timedelta(minutes=interval)
|
||||
|
||||
|
||||
@shared_task
|
||||
# Bounds a single feed's fetch+parse+ingest, independent of
|
||||
# FETCH_TIMEOUT_SECONDS (apps.feeds.services.fetcher) which only covers
|
||||
# the HTTP request itself: parsing/sanitizing/writing a large-but-under-
|
||||
# the-byte-cap feed could still run long. soft_time_limit lets the
|
||||
# except-Exception handler below record a normal feed error (and clear
|
||||
# the claim) before the hard time_limit kills the worker process outright.
|
||||
FETCH_FEED_SOFT_TIME_LIMIT = 60
|
||||
FETCH_FEED_TIME_LIMIT = 90
|
||||
|
||||
|
||||
@shared_task(time_limit=FETCH_FEED_TIME_LIMIT, soft_time_limit=FETCH_FEED_SOFT_TIME_LIMIT)
|
||||
def fetch_feed(feed_id: int):
|
||||
try:
|
||||
feed = Feed.objects.get(pk=feed_id, is_active=True)
|
||||
except Feed.DoesNotExist:
|
||||
return None
|
||||
|
||||
try:
|
||||
result = fetch_and_ingest(feed)
|
||||
except Exception:
|
||||
# fetch_and_ingest already handles the expected failure modes
|
||||
# (network errors, SSRF-blocked targets, unparseable feeds) by
|
||||
# returning an error FetchResult rather than raising — anything
|
||||
# that reaches here is unexpected (a parser/sanitizer bug, a DB
|
||||
# error, this task's own soft time limit), so it's recorded the
|
||||
# same way a handled failure would be rather than silently
|
||||
# leaving the feed's status stale, the claim held for the full
|
||||
# CLAIM_STALE_MINUTES, and no record of what happened. Re-raised
|
||||
# afterward so Celery still marks the task FAILED (visible in
|
||||
# worker logs/monitoring) instead of swallowing it.
|
||||
logger.exception("Feed %s: unexpected error during fetch", feed.feed_url)
|
||||
record_fetch_error(feed, "Unexpected error — see worker logs")
|
||||
feed.last_fetched_at = timezone.now()
|
||||
feed.claimed_at = None
|
||||
feed.save()
|
||||
raise
|
||||
|
||||
feed.claimed_at = None
|
||||
feed.save()
|
||||
|
||||
|
||||
@@ -5,7 +5,13 @@ from django.utils import timezone
|
||||
|
||||
from apps.articles.models import Article, UserArticleState
|
||||
from apps.feeds.models import Feed
|
||||
from apps.feeds.services.fetcher import effective_interval_minutes, fetch_and_ingest
|
||||
from apps.feeds.services.fetcher import (
|
||||
MAX_CONTENT_HTML_CHARS,
|
||||
MAX_ENTRIES_PER_POLL,
|
||||
effective_interval_minutes,
|
||||
fetch_and_ingest,
|
||||
sanitize_html,
|
||||
)
|
||||
|
||||
FEED_URL = "https://example.com/feed.xml"
|
||||
|
||||
@@ -130,7 +136,7 @@ def test_unparseable_feed_records_error_and_backs_off(feed):
|
||||
|
||||
assert result.status == Feed.STATUS_ERROR
|
||||
assert feed.fetch_error_count == 1
|
||||
assert effective_interval_minutes(feed) > feed.fetch_interval_minutes
|
||||
assert effective_interval_minutes(feed, 60) > 60
|
||||
|
||||
|
||||
@pytest.mark.django_db
|
||||
@@ -196,3 +202,29 @@ def test_refetching_updated_content_does_not_reset_user_state():
|
||||
state.refresh_from_db()
|
||||
assert state.is_read is True
|
||||
assert ArticleTag.objects.filter(user=user, article=article, tag=starred_tag).exists()
|
||||
|
||||
|
||||
def test_sanitize_html_caps_stored_output_length():
|
||||
huge = "<p>" + ("a" * (MAX_CONTENT_HTML_CHARS + 10_000)) + "</p>"
|
||||
cleaned = sanitize_html(huge)
|
||||
assert len(cleaned) <= MAX_CONTENT_HTML_CHARS
|
||||
|
||||
|
||||
@pytest.mark.django_db
|
||||
@responses.activate
|
||||
def test_fetch_only_processes_the_first_max_entries_per_poll(feed):
|
||||
items = "".join(
|
||||
f"<item><title>Item {i}</title><guid>guid-{i}</guid></item>"
|
||||
for i in range(MAX_ENTRIES_PER_POLL + 5)
|
||||
)
|
||||
xml = f"""<?xml version="1.0"?>
|
||||
<rss version="2.0"><channel><title>Big feed</title>{items}</channel></rss>
|
||||
"""
|
||||
responses.add(responses.GET, FEED_URL, body=xml, status=200)
|
||||
|
||||
result = fetch_and_ingest(feed)
|
||||
feed.save()
|
||||
|
||||
assert len(result.new_article_ids) == MAX_ENTRIES_PER_POLL
|
||||
assert Article.objects.filter(feed=feed).count() == MAX_ENTRIES_PER_POLL
|
||||
assert not Article.objects.filter(feed=feed, guid=f"guid-{MAX_ENTRIES_PER_POLL}").exists()
|
||||
@@ -16,17 +16,14 @@ def test_poll_due_feeds_dispatches_only_due_feeds():
|
||||
recently_fetched = Feed.objects.create(
|
||||
feed_url="https://b.example.com/feed.xml",
|
||||
last_fetched_at=timezone.now(),
|
||||
fetch_interval_minutes=60,
|
||||
)
|
||||
overdue = Feed.objects.create(
|
||||
feed_url="https://c.example.com/feed.xml",
|
||||
last_fetched_at=timezone.now() - timedelta(hours=2),
|
||||
fetch_interval_minutes=60,
|
||||
)
|
||||
inactive_but_overdue = Feed.objects.create(
|
||||
feed_url="https://d.example.com/feed.xml",
|
||||
last_fetched_at=timezone.now() - timedelta(hours=2),
|
||||
fetch_interval_minutes=60,
|
||||
is_active=False,
|
||||
)
|
||||
|
||||
@@ -48,7 +45,6 @@ def test_poll_due_feeds_does_not_reclaim_a_feed_it_just_claimed():
|
||||
overdue = Feed.objects.create(
|
||||
feed_url="https://c.example.com/feed.xml",
|
||||
last_fetched_at=timezone.now() - timedelta(hours=2),
|
||||
fetch_interval_minutes=60,
|
||||
)
|
||||
|
||||
with patch("apps.feeds.tasks.fetch_feed.delay") as mock_delay:
|
||||
@@ -69,7 +65,6 @@ def test_poll_due_feeds_reclaims_a_stale_claim():
|
||||
overdue = Feed.objects.create(
|
||||
feed_url="https://c.example.com/feed.xml",
|
||||
last_fetched_at=timezone.now() - timedelta(hours=2),
|
||||
fetch_interval_minutes=60,
|
||||
claimed_at=timezone.now() - timedelta(minutes=CLAIM_STALE_MINUTES + 1),
|
||||
)
|
||||
|
||||
@@ -127,3 +122,22 @@ def test_fetch_feed_task_skips_inactive_feed():
|
||||
@pytest.mark.django_db
|
||||
def test_fetch_feed_task_skips_missing_feed():
|
||||
assert fetch_feed(999999) is None
|
||||
|
||||
|
||||
@pytest.mark.django_db
|
||||
def test_fetch_feed_task_records_error_and_clears_claim_on_unexpected_exception():
|
||||
feed = Feed.objects.create(
|
||||
feed_url="https://example.com/feed.xml",
|
||||
claimed_at=timezone.now(),
|
||||
fetch_error_count=0,
|
||||
)
|
||||
|
||||
with patch("apps.feeds.tasks.fetch_and_ingest", side_effect=RuntimeError("boom")):
|
||||
with pytest.raises(RuntimeError, match="boom"):
|
||||
fetch_feed(feed.id)
|
||||
|
||||
feed.refresh_from_db()
|
||||
assert feed.last_fetch_status == Feed.STATUS_ERROR
|
||||
assert feed.fetch_error_count == 1
|
||||
assert feed.claimed_at is None
|
||||
assert feed.last_fetched_at is not None
|
||||
@@ -106,9 +106,34 @@ EVECTION_SIGNUP_ENABLED = env.bool("EVECTION_SIGNUP_ENABLED", default=False)
|
||||
EVECTION_MIN_FETCH_INTERVAL_MINUTES = env.int("EVECTION_MIN_FETCH_INTERVAL_MINUTES", default=15)
|
||||
EVECTION_PWA_CACHE_VERSION = env.str("EVECTION_PWA_CACHE_VERSION", default="v1")
|
||||
|
||||
# Redis-backed rather than Django's default per-process LocMemCache: login
|
||||
# rate limiting (apps.accounts.views) must share counters across every
|
||||
# gunicorn worker, not just whichever one happened to handle a given
|
||||
# request. Redis is already a hard install requirement for Celery, so
|
||||
# this adds no new infrastructure — just a distinct key prefix so cache
|
||||
# keys can't collide with anything else sharing that Redis instance.
|
||||
CACHES = {
|
||||
"default": {
|
||||
"BACKEND": "django.core.cache.backends.redis.RedisCache",
|
||||
"LOCATION": env.str("REDIS_URL", default="redis://localhost:6379/0"),
|
||||
"KEY_PREFIX": "evection-cache",
|
||||
}
|
||||
}
|
||||
|
||||
# Celery
|
||||
CELERY_BROKER_URL = env.str("REDIS_URL", default="redis://localhost:6379/0")
|
||||
CELERY_RESULT_BACKEND = None
|
||||
CELERY_TASK_SERIALIZER = "json"
|
||||
CELERY_ACCEPT_CONTENT = ["json"]
|
||||
CELERY_TIMEZONE = TIME_ZONE
|
||||
|
||||
# Without these, a worker process killed mid-task (OOM, deploy restart,
|
||||
# crash) silently loses that task: the default is to ack a message the
|
||||
# moment a worker *starts* it, not when it finishes. acks_late + reject-
|
||||
# on-worker-lost means the message is only consumed on completion (success
|
||||
# or a handled failure) and is redelivered to another worker otherwise.
|
||||
# prefetch_multiplier=1 keeps a worker from grabbing a batch of tasks it
|
||||
# could similarly lose all at once.
|
||||
CELERY_TASK_ACKS_LATE = True
|
||||
CELERY_TASK_REJECT_ON_WORKER_LOST = True
|
||||
CELERY_WORKER_PREFETCH_MULTIPLIER = 1
|
||||
@@ -5,3 +5,10 @@ CELERY_TASK_ALWAYS_EAGER = True
|
||||
CELERY_TASK_EAGER_PROPAGATES = True
|
||||
|
||||
PASSWORD_HASHERS = ["django.contrib.auth.hashers.MD5PasswordHasher"]
|
||||
|
||||
# base.py's CACHES needs a real Redis instance — tests must not depend on
|
||||
# one being available, and a plain per-process cache is also what keeps
|
||||
# login-rate-limit tests isolated from each other (LocMemCache's default
|
||||
# location is per-process but shared across tests in that process; see
|
||||
# apps.accounts.test_rate_limit's cache.clear() fixture).
|
||||
CACHES = {"default": {"BACKEND": "django.core.cache.backends.locmem.LocMemCache"}}
|
||||
+5
-1
@@ -66,7 +66,7 @@ and 4 below first — prerequisites and what `.env` controls.
|
||||
|
||||
- Python 3.11 or 3.12, with its `venv` module (Debian/Ubuntu split this into a
|
||||
separate `python3.X-venv` package — see below)
|
||||
- Redis (Celery's broker)
|
||||
- Redis (Celery's broker, and the app's cache — e.g. login rate limiting)
|
||||
- **Postgres only**: a PostgreSQL server (12+) and its client headers if you're not
|
||||
using the bundled `psycopg[binary]` wheel (most platforms are covered by the wheel,
|
||||
so this is rarely needed)
|
||||
@@ -143,6 +143,10 @@ At minimum, set the following in `.env`:
|
||||
- `EVECTION_GUNICORN_BIND` — the `address:port` gunicorn listens on; see
|
||||
"Reverse proxy" below for how to pick this
|
||||
|
||||
How often every feed is polled is a site-wide setting (Django admin → Site
|
||||
settings), not a `.env` value — `EVECTION_MIN_FETCH_INTERVAL_MINUTES` only sets
|
||||
a floor under it, so it can't be configured lower than that without editing `.env`.
|
||||
|
||||
Evection reads `config.settings.prod` when run via the commands below (see each
|
||||
systemd unit's `DJANGO_SETTINGS_MODULE`). That module turns on HTTPS-only cookies,
|
||||
HSTS, and a Content-Security-Policy header on top of the base settings, and
|
||||
|
||||
Reference in new issue
Block a user