Private
Public Access
Compare commits
13
Commits
| Author | SHA1 | Date | |
|---|---|---|---|
|
|
e760eeda1d | ||
|
|
9439f9cc59 | ||
|
|
fd8eeb605e | ||
|
|
91c0b1dd26 | ||
|
|
f2ee793cf8 | ||
|
|
b7d9ee672c | ||
|
|
d7b433e580 | ||
|
|
b52ba2be8a | ||
|
|
56eb2bc498 | ||
|
|
9d91da6fc6 | ||
|
|
c316f411f8 | ||
|
|
e1907ff587 | ||
|
|
b0d62c91f8 |
No files matched your search
@@ -0,0 +1,22 @@
|
|||||||
|
# Generated by Django 5.2.18 on 2026-10-31 18:00
|
||||||
|
|
||||||
|
from django.db import migrations, models
|
||||||
|
|
||||||
|
|
||||||
|
class Migration(migrations.Migration):
|
||||||
|
|
||||||
|
dependencies = [
|
||||||
|
("accounts", "0001_initial"),
|
||||||
|
]
|
||||||
|
|
||||||
|
operations = [
|
||||||
|
migrations.CreateModel(
|
||||||
|
name="SetupLock",
|
||||||
|
fields=[
|
||||||
|
(
|
||||||
|
"id",
|
||||||
|
models.PositiveSmallIntegerField(default=1, primary_key=True, serialize=False),
|
||||||
|
),
|
||||||
|
],
|
||||||
|
),
|
||||||
|
]
|
||||||
@@ -5,3 +5,15 @@ from django.db import models
|
|||||||
class User(AbstractUser):
|
class User(AbstractUser):
|
||||||
timezone = models.CharField(max_length=64, default="UTC")
|
timezone = models.CharField(max_length=64, default="UTC")
|
||||||
created_at = models.DateTimeField(auto_now_add=True)
|
created_at = models.DateTimeField(auto_now_add=True)
|
||||||
|
|
||||||
|
|
||||||
|
class SetupLock(models.Model):
|
||||||
|
"""Singleton row that gates first-run setup against a race between
|
||||||
|
concurrent requests. The setup view always tries to INSERT the row
|
||||||
|
with pk=1 in the same transaction as creating the first admin user:
|
||||||
|
the database's primary-key uniqueness makes exactly one of those
|
||||||
|
INSERTs win even under concurrent requests, so only one admin account
|
||||||
|
can ever be created this way, instead of the User.objects.exists()
|
||||||
|
check alone (which has a window between the check and the save)."""
|
||||||
|
|
||||||
|
id = models.PositiveSmallIntegerField(primary_key=True, default=1)
|
||||||
+23
-1
@@ -1,7 +1,7 @@
|
|||||||
import pytest
|
import pytest
|
||||||
from django.urls import reverse
|
from django.urls import reverse
|
||||||
|
|
||||||
from .models import User
|
from .models import SetupLock, User
|
||||||
|
|
||||||
# SetupWizardMiddleware's cache is reset around every test by the autouse
|
# SetupWizardMiddleware's cache is reset around every test by the autouse
|
||||||
# fixture in the top-level conftest.py, not just here.
|
# fixture in the top-level conftest.py, not just here.
|
||||||
@@ -43,6 +43,28 @@ def test_setup_creates_admin_and_logs_in(client):
|
|||||||
assert stream_response.status_code == 200
|
assert stream_response.status_code == 200
|
||||||
|
|
||||||
|
|
||||||
|
@pytest.mark.django_db
|
||||||
|
def test_setup_refuses_a_second_concurrent_submission(client):
|
||||||
|
# Simulates two requests racing the setup form: the first claims the
|
||||||
|
# SetupLock row directly (standing in for a request that's already
|
||||||
|
# past the User.objects.exists() check), so a second submission's
|
||||||
|
# INSERT must lose instead of also creating an admin account.
|
||||||
|
SetupLock.objects.create()
|
||||||
|
|
||||||
|
response = client.post(
|
||||||
|
reverse("accounts:setup"),
|
||||||
|
{
|
||||||
|
"username": "raced",
|
||||||
|
"email": "raced@example.com",
|
||||||
|
"password": "correct-horse-battery",
|
||||||
|
"password_confirm": "correct-horse-battery",
|
||||||
|
},
|
||||||
|
)
|
||||||
|
assert response.status_code == 302
|
||||||
|
assert response.url == reverse("accounts:login")
|
||||||
|
assert not User.objects.filter(username="raced").exists()
|
||||||
|
|
||||||
|
|
||||||
@pytest.mark.django_db
|
@pytest.mark.django_db
|
||||||
def test_setup_is_unreachable_once_a_user_exists(client):
|
def test_setup_is_unreachable_once_a_user_exists(client):
|
||||||
User.objects.create_user("existing", password="irrelevant")
|
User.objects.create_user("existing", password="irrelevant")
|
||||||
|
|||||||
+12
-1
@@ -1,11 +1,12 @@
|
|||||||
from django.contrib import messages
|
from django.contrib import messages
|
||||||
from django.contrib.auth import login
|
from django.contrib.auth import login
|
||||||
from django.contrib.auth.decorators import user_passes_test
|
from django.contrib.auth.decorators import user_passes_test
|
||||||
|
from django.db import IntegrityError, transaction
|
||||||
from django.shortcuts import redirect, render
|
from django.shortcuts import redirect, render
|
||||||
|
|
||||||
from .forms import CreateUserForm, SetupForm
|
from .forms import CreateUserForm, SetupForm
|
||||||
from .middleware import SetupWizardMiddleware
|
from .middleware import SetupWizardMiddleware
|
||||||
from .models import User
|
from .models import SetupLock, User
|
||||||
|
|
||||||
is_admin = user_passes_test(lambda u: u.is_authenticated and u.is_staff)
|
is_admin = user_passes_test(lambda u: u.is_authenticated and u.is_staff)
|
||||||
|
|
||||||
@@ -16,11 +17,21 @@ def setup(request):
|
|||||||
|
|
||||||
form = SetupForm(request.POST or None)
|
form = SetupForm(request.POST or None)
|
||||||
if request.method == "POST" and form.is_valid():
|
if request.method == "POST" and form.is_valid():
|
||||||
|
try:
|
||||||
|
with transaction.atomic():
|
||||||
|
# Claims the one-time setup slot: the first of any
|
||||||
|
# concurrent requests to reach this INSERT wins it, and
|
||||||
|
# every other one raises IntegrityError instead of also
|
||||||
|
# creating an admin account. See SetupLock's docstring.
|
||||||
|
SetupLock.objects.create()
|
||||||
user = form.save(commit=False)
|
user = form.save(commit=False)
|
||||||
user.set_password(form.cleaned_data["password"])
|
user.set_password(form.cleaned_data["password"])
|
||||||
user.is_staff = True
|
user.is_staff = True
|
||||||
user.is_superuser = True
|
user.is_superuser = True
|
||||||
user.save()
|
user.save()
|
||||||
|
except IntegrityError:
|
||||||
|
messages.info(request, "Setup was already completed. Log in with that account.")
|
||||||
|
return redirect("accounts:login")
|
||||||
SetupWizardMiddleware._a_user_exists = True
|
SetupWizardMiddleware._a_user_exists = True
|
||||||
login(request, user)
|
login(request, user)
|
||||||
messages.success(request, "Welcome to Evection! Your admin account is ready.")
|
messages.success(request, "Welcome to Evection! Your admin account is ready.")
|
||||||
|
|||||||
+12
-12
@@ -1,5 +1,4 @@
|
|||||||
from celery import shared_task
|
from celery import shared_task
|
||||||
from django.db.models import Q
|
|
||||||
|
|
||||||
from apps.feeds.models import Subscription
|
from apps.feeds.models import Subscription
|
||||||
from apps.rules.engine import evaluate_rules_for_article
|
from apps.rules.engine import evaluate_rules_for_article
|
||||||
@@ -14,6 +13,10 @@ def apply_filter_rules_for_feed(feed_id: int, article_ids: list[int]):
|
|||||||
FilterRules (scoped to this feed/tag or unscoped) against the given
|
FilterRules (scoped to this feed/tag or unscoped) against the given
|
||||||
articles. Dispatched by the fetch pipeline after new/updated articles
|
articles. Dispatched by the fetch pipeline after new/updated articles
|
||||||
are committed for a feed.
|
are committed for a feed.
|
||||||
|
|
||||||
|
Per-rule scoping is left to evaluate_rules_for_article/rule_in_scope
|
||||||
|
rather than filtered into this query, so this and the backlog
|
||||||
|
re-apply task (apps.rules.tasks) can't scope rules differently.
|
||||||
"""
|
"""
|
||||||
if not article_ids:
|
if not article_ids:
|
||||||
return 0
|
return 0
|
||||||
@@ -26,24 +29,21 @@ def apply_filter_rules_for_feed(feed_id: int, article_ids: list[int]):
|
|||||||
|
|
||||||
evaluated = 0
|
evaluated = 0
|
||||||
for subscription in subscriptions:
|
for subscription in subscriptions:
|
||||||
rules = FilterRule.objects.filter(user=subscription.user, is_enabled=True).filter(
|
rules = list(
|
||||||
Q(feed_id=feed_id) | Q(feed__isnull=True)
|
FilterRule.objects.filter(user=subscription.user, is_enabled=True).order_by(
|
||||||
|
"priority", "id"
|
||||||
)
|
)
|
||||||
subscription_tag_ids = list(
|
)
|
||||||
|
if not rules:
|
||||||
|
continue
|
||||||
|
subscription_tag_ids = set(
|
||||||
SubscriptionTag.objects.filter(
|
SubscriptionTag.objects.filter(
|
||||||
user=subscription.user, subscription=subscription
|
user=subscription.user, subscription=subscription
|
||||||
).values_list("tag_id", flat=True)
|
).values_list("tag_id", flat=True)
|
||||||
)
|
)
|
||||||
if subscription_tag_ids:
|
|
||||||
rules = rules.filter(Q(tag_id__in=subscription_tag_ids) | Q(tag__isnull=True))
|
|
||||||
else:
|
|
||||||
rules = rules.filter(tag__isnull=True)
|
|
||||||
rules = list(rules.order_by("priority", "id"))
|
|
||||||
if not rules:
|
|
||||||
continue
|
|
||||||
|
|
||||||
for article in articles:
|
for article in articles:
|
||||||
evaluate_rules_for_article(subscription.user, article, rules)
|
evaluate_rules_for_article(subscription.user, article, rules, subscription_tag_ids)
|
||||||
evaluated += 1
|
evaluated += 1
|
||||||
|
|
||||||
return evaluated
|
return evaluated
|
||||||
@@ -44,7 +44,19 @@ def sidebar(request):
|
|||||||
|
|
||||||
return {
|
return {
|
||||||
"sidebar_tag_groups": [
|
"sidebar_tag_groups": [
|
||||||
{"tag": tag, "subscriptions": feeds_by_tag.get(tag.pk, [])} for tag in tags
|
{
|
||||||
|
"tag": tag,
|
||||||
|
"subscriptions": feeds_by_tag.get(tag.pk, []),
|
||||||
|
# A feed can carry more than one tag, so this is a sum
|
||||||
|
# over whichever of the user's feeds this tag happens to
|
||||||
|
# cover right now — not a separately-tracked counter — and
|
||||||
|
# reuses the per-feed counts already computed above rather
|
||||||
|
# than a second query.
|
||||||
|
"unread_count": sum(
|
||||||
|
subscription.unread_count for subscription in feeds_by_tag.get(tag.pk, [])
|
||||||
|
),
|
||||||
|
}
|
||||||
|
for tag in tags
|
||||||
],
|
],
|
||||||
"sidebar_untagged": untagged,
|
"sidebar_untagged": untagged,
|
||||||
"sidebar_starred_count": ArticleTag.objects.filter(
|
"sidebar_starred_count": ArticleTag.objects.filter(
|
||||||
|
|||||||
@@ -0,0 +1,82 @@
|
|||||||
|
import pytest
|
||||||
|
from django.contrib.auth import get_user_model
|
||||||
|
from django.test import RequestFactory
|
||||||
|
from django.urls import reverse
|
||||||
|
|
||||||
|
from apps.articles.models import Article, SubscriptionTag, Tag
|
||||||
|
from apps.feeds.models import Feed, Subscription
|
||||||
|
|
||||||
|
from .context_processors import sidebar
|
||||||
|
|
||||||
|
User = get_user_model()
|
||||||
|
|
||||||
|
|
||||||
|
@pytest.fixture
|
||||||
|
def alice(db):
|
||||||
|
return User.objects.create_user("alice", password="pw-alice-123")
|
||||||
|
|
||||||
|
|
||||||
|
def _sidebar_context(user):
|
||||||
|
request = RequestFactory().get("/")
|
||||||
|
request.user = user
|
||||||
|
return sidebar(request)
|
||||||
|
|
||||||
|
|
||||||
|
@pytest.mark.django_db
|
||||||
|
def test_tag_unread_count_sums_its_feeds(alice):
|
||||||
|
feed_a = Feed.objects.create(feed_url="https://a.example.com/feed.xml")
|
||||||
|
feed_b = Feed.objects.create(feed_url="https://b.example.com/feed.xml")
|
||||||
|
sub_a = Subscription.objects.create(user=alice, feed=feed_a)
|
||||||
|
sub_b = Subscription.objects.create(user=alice, feed=feed_b)
|
||||||
|
tag = Tag.objects.create(user=alice, name="work")
|
||||||
|
SubscriptionTag.objects.create(user=alice, subscription=sub_a, tag=tag)
|
||||||
|
SubscriptionTag.objects.create(user=alice, subscription=sub_b, tag=tag)
|
||||||
|
|
||||||
|
for i in range(3):
|
||||||
|
Article.objects.create(feed=feed_a, guid=f"a-{i}", title=f"A{i}")
|
||||||
|
for i in range(4):
|
||||||
|
Article.objects.create(feed=feed_b, guid=f"b-{i}", title=f"B{i}")
|
||||||
|
|
||||||
|
context = _sidebar_context(alice)
|
||||||
|
[group] = context["sidebar_tag_groups"]
|
||||||
|
assert group["tag"] == tag
|
||||||
|
assert group["unread_count"] == 7
|
||||||
|
|
||||||
|
|
||||||
|
@pytest.mark.django_db
|
||||||
|
def test_tag_unread_count_is_zero_with_no_unread_articles(alice):
|
||||||
|
feed = Feed.objects.create(feed_url="https://example.com/feed.xml")
|
||||||
|
sub = Subscription.objects.create(user=alice, feed=feed)
|
||||||
|
tag = Tag.objects.create(user=alice, name="empty")
|
||||||
|
SubscriptionTag.objects.create(user=alice, subscription=sub, tag=tag)
|
||||||
|
|
||||||
|
context = _sidebar_context(alice)
|
||||||
|
[group] = context["sidebar_tag_groups"]
|
||||||
|
assert group["unread_count"] == 0
|
||||||
|
|
||||||
|
|
||||||
|
@pytest.mark.django_db
|
||||||
|
def test_sidebar_sections_carry_a_stable_collapse_state_key(client, alice):
|
||||||
|
feed = Feed.objects.create(feed_url="https://example.com/feed.xml")
|
||||||
|
sub = Subscription.objects.create(user=alice, feed=feed)
|
||||||
|
tag = Tag.objects.create(user=alice, name="work")
|
||||||
|
SubscriptionTag.objects.create(user=alice, subscription=sub, tag=tag)
|
||||||
|
|
||||||
|
other_feed = Feed.objects.create(feed_url="https://other.example.com/feed.xml")
|
||||||
|
Subscription.objects.create(user=alice, feed=other_feed) # untagged
|
||||||
|
|
||||||
|
client.login(username="alice", password="pw-alice-123")
|
||||||
|
response = client.get(reverse("reader:stream"))
|
||||||
|
content = response.content.decode()
|
||||||
|
|
||||||
|
# static/js/sidebar-state.js reads these to restore/persist each
|
||||||
|
# section's collapsed state across page loads.
|
||||||
|
assert f'data-sidebar-key="tag-{tag.pk}"' in content
|
||||||
|
assert 'data-sidebar-key="untagged"' in content
|
||||||
|
|
||||||
|
|
||||||
|
@pytest.mark.django_db
|
||||||
|
def test_base_template_loads_the_sidebar_state_script(client, alice):
|
||||||
|
client.login(username="alice", password="pw-alice-123")
|
||||||
|
response = client.get(reverse("reader:stream"))
|
||||||
|
assert "sidebar-state.js" in response.content.decode()
|
||||||
@@ -0,0 +1,21 @@
|
|||||||
|
import socket
|
||||||
|
|
||||||
|
import pytest
|
||||||
|
|
||||||
|
|
||||||
|
@pytest.fixture(autouse=True)
|
||||||
|
def _fake_public_dns(monkeypatch):
|
||||||
|
"""apps.feeds.services.ssrf_guard resolves a feed's real hostname via
|
||||||
|
socket.getaddrinfo before every fetch. Tests use made-up hostnames
|
||||||
|
like example.com/a.example.com purely as fixture data — they must
|
||||||
|
not depend on real DNS/network access to pass that check, and must
|
||||||
|
resolve deterministically regardless of this sandbox's network
|
||||||
|
access. Every lookup here resolves to a fixed, definitely-public IP;
|
||||||
|
tests that specifically exercise the "resolves to a non-public
|
||||||
|
address" rejection path patch socket.getaddrinfo themselves instead.
|
||||||
|
"""
|
||||||
|
|
||||||
|
def _fake_getaddrinfo(host, *args, **kwargs):
|
||||||
|
return [(socket.AF_INET, socket.SOCK_STREAM, 6, "", ("93.184.216.34", 0))]
|
||||||
|
|
||||||
|
monkeypatch.setattr(socket, "getaddrinfo", _fake_getaddrinfo)
|
||||||
@@ -0,0 +1,18 @@
|
|||||||
|
# Generated by Django 5.2.18 on 2026-10-31 18:00
|
||||||
|
|
||||||
|
from django.db import migrations, models
|
||||||
|
|
||||||
|
|
||||||
|
class Migration(migrations.Migration):
|
||||||
|
|
||||||
|
dependencies = [
|
||||||
|
("feeds", "0002_remove_folder"),
|
||||||
|
]
|
||||||
|
|
||||||
|
operations = [
|
||||||
|
migrations.AddField(
|
||||||
|
model_name="feed",
|
||||||
|
name="claimed_at",
|
||||||
|
field=models.DateTimeField(blank=True, null=True),
|
||||||
|
),
|
||||||
|
]
|
||||||
@@ -40,6 +40,15 @@ 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 poll_due_feeds' atomic claim (an UPDATE ... WHERE clause, not
|
||||||
|
# select_for_update — Celery Beat and fetch_feed run in separate
|
||||||
|
# transactions) and cleared once fetch_feed finishes, so overlapping
|
||||||
|
# beat ticks or a fetch that runs long can't both dispatch the same
|
||||||
|
# feed. A claim older than CLAIM_STALE_MINUTES (tasks.py) is treated as
|
||||||
|
# abandoned and can be reclaimed, so a worker dying mid-fetch doesn't
|
||||||
|
# wedge the feed forever.
|
||||||
|
claimed_at = models.DateTimeField(null=True, blank=True)
|
||||||
|
|
||||||
created_at = models.DateTimeField(auto_now_add=True)
|
created_at = models.DateTimeField(auto_now_add=True)
|
||||||
|
|
||||||
def __str__(self):
|
def __str__(self):
|
||||||
|
|||||||
@@ -23,6 +23,8 @@ from django.utils import timezone
|
|||||||
from apps.articles.models import Article
|
from apps.articles.models import Article
|
||||||
from apps.feeds.models import Feed
|
from apps.feeds.models import Feed
|
||||||
|
|
||||||
|
from .ssrf_guard import SSRFBlocked, safe_get
|
||||||
|
|
||||||
logger = logging.getLogger(__name__)
|
logger = logging.getLogger(__name__)
|
||||||
|
|
||||||
FETCH_TIMEOUT_SECONDS = 15
|
FETCH_TIMEOUT_SECONDS = 15
|
||||||
@@ -139,7 +141,10 @@ def fetch_and_ingest(feed: Feed) -> FetchResult:
|
|||||||
headers["If-Modified-Since"] = feed.last_modified
|
headers["If-Modified-Since"] = feed.last_modified
|
||||||
|
|
||||||
try:
|
try:
|
||||||
response = requests.get(feed.feed_url, headers=headers, timeout=FETCH_TIMEOUT_SECONDS)
|
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}")
|
||||||
except requests.RequestException as exc:
|
except requests.RequestException as exc:
|
||||||
feed.last_fetched_at = timezone.now()
|
feed.last_fetched_at = timezone.now()
|
||||||
return _record_error(feed, f"Request failed: {exc}")
|
return _record_error(feed, f"Request failed: {exc}")
|
||||||
|
|||||||
@@ -0,0 +1,121 @@
|
|||||||
|
"""Rejects feed-fetch targets that could turn this server/worker's own
|
||||||
|
network access into an SSRF vector.
|
||||||
|
|
||||||
|
Feed URLs are entirely attacker-controlled (any authenticated user via
|
||||||
|
"add feed", or an uploaded OPML file — see apps.feeds.opml) and this app
|
||||||
|
fetches them from the server's own network position. fetch_and_ingest
|
||||||
|
(apps.feeds.services.fetcher) is the single chokepoint every feed URL
|
||||||
|
passes through before any HTTP request is made, regardless of which
|
||||||
|
path created the Feed row, so enforcing this here covers all of them.
|
||||||
|
|
||||||
|
This validates the resolved address before connecting and again before
|
||||||
|
following each redirect hop, denying by default anything that isn't a
|
||||||
|
globally routable address (ip.is_global) — covering loopback, RFC1918
|
||||||
|
private ranges, link-local (including the 169.254.169.254 cloud
|
||||||
|
metadata address), and so on, for both IPv4 and IPv6.
|
||||||
|
|
||||||
|
What this does *not* close: the TCP connection isn't pinned to the
|
||||||
|
specific IP that was validated, so a DNS answer that changes between
|
||||||
|
the validation lookup and the actual connect (classic DNS rebinding)
|
||||||
|
could still slip through. Closing that fully needs a custom transport
|
||||||
|
that connects to the exact validated IP while still verifying TLS
|
||||||
|
against the original hostname — more machinery than this self-hosted
|
||||||
|
app's threat model currently justifies; this stops the much more
|
||||||
|
common case of a feed URL (or a redirect) simply pointing straight at
|
||||||
|
an internal address.
|
||||||
|
"""
|
||||||
|
|
||||||
|
from __future__ import annotations
|
||||||
|
|
||||||
|
import ipaddress
|
||||||
|
import socket
|
||||||
|
from dataclasses import dataclass
|
||||||
|
from urllib.parse import urljoin, urlparse
|
||||||
|
|
||||||
|
import requests
|
||||||
|
from requests.structures import CaseInsensitiveDict
|
||||||
|
|
||||||
|
ALLOWED_SCHEMES = {"http", "https"}
|
||||||
|
MAX_REDIRECTS = 5
|
||||||
|
MAX_RESPONSE_BYTES = 10 * 1024 * 1024 # 10 MB — generous for an RSS/Atom feed
|
||||||
|
READ_CHUNK_BYTES = 65536
|
||||||
|
|
||||||
|
|
||||||
|
class SSRFBlocked(Exception):
|
||||||
|
"""Raised when a fetch target — or one of its redirects — isn't safe
|
||||||
|
to connect to on a user's behalf."""
|
||||||
|
|
||||||
|
|
||||||
|
@dataclass
|
||||||
|
class BoundedResponse:
|
||||||
|
status_code: int
|
||||||
|
# requests' own CaseInsensitiveDict — server header casing varies
|
||||||
|
# (ETag/Etag/etag) and fetcher.py looks these up by a fixed-case key.
|
||||||
|
headers: CaseInsensitiveDict
|
||||||
|
content: bytes
|
||||||
|
|
||||||
|
|
||||||
|
def validate_fetch_url(url: str) -> None:
|
||||||
|
"""Raises SSRFBlocked unless `url` has an http(s) scheme, a hostname,
|
||||||
|
and every address that hostname resolves to is globally routable."""
|
||||||
|
parsed = urlparse(url)
|
||||||
|
if parsed.scheme not in ALLOWED_SCHEMES:
|
||||||
|
raise SSRFBlocked(f"Unsupported URL scheme: {parsed.scheme!r}")
|
||||||
|
if not parsed.hostname:
|
||||||
|
raise SSRFBlocked("URL has no hostname")
|
||||||
|
|
||||||
|
try:
|
||||||
|
addrinfo = socket.getaddrinfo(parsed.hostname, None)
|
||||||
|
except OSError as exc:
|
||||||
|
raise SSRFBlocked(f"Could not resolve {parsed.hostname!r}: {exc}") from exc
|
||||||
|
|
||||||
|
for *_, sockaddr in addrinfo:
|
||||||
|
ip = ipaddress.ip_address(sockaddr[0])
|
||||||
|
if not ip.is_global:
|
||||||
|
raise SSRFBlocked(f"{parsed.hostname!r} resolves to a non-public address: {ip}")
|
||||||
|
|
||||||
|
|
||||||
|
def safe_get(url: str, *, headers: dict, timeout: float) -> BoundedResponse:
|
||||||
|
"""GETs `url` the way fetch_and_ingest needs it: every redirect hop is
|
||||||
|
validated and followed manually (never left to requests/urllib3, so
|
||||||
|
a redirect can't bypass validate_fetch_url), capped at MAX_REDIRECTS,
|
||||||
|
and the body is read in bounded chunks rather than trusting
|
||||||
|
Content-Length or buffering an unbounded response.
|
||||||
|
"""
|
||||||
|
current_url = url
|
||||||
|
with requests.Session() as session:
|
||||||
|
for _ in range(MAX_REDIRECTS + 1):
|
||||||
|
validate_fetch_url(current_url)
|
||||||
|
response = session.get(
|
||||||
|
current_url,
|
||||||
|
headers=headers,
|
||||||
|
timeout=timeout,
|
||||||
|
stream=True,
|
||||||
|
allow_redirects=False,
|
||||||
|
)
|
||||||
|
try:
|
||||||
|
if response.is_redirect or response.is_permanent_redirect:
|
||||||
|
location = response.headers.get("Location")
|
||||||
|
if not location:
|
||||||
|
raise SSRFBlocked("Redirect response had no Location header")
|
||||||
|
current_url = urljoin(current_url, location)
|
||||||
|
continue
|
||||||
|
return BoundedResponse(
|
||||||
|
status_code=response.status_code,
|
||||||
|
headers=response.headers,
|
||||||
|
content=_read_bounded(response),
|
||||||
|
)
|
||||||
|
finally:
|
||||||
|
response.close()
|
||||||
|
raise SSRFBlocked(f"Too many redirects (> {MAX_REDIRECTS})")
|
||||||
|
|
||||||
|
|
||||||
|
def _read_bounded(response: requests.Response) -> bytes:
|
||||||
|
chunks = []
|
||||||
|
total = 0
|
||||||
|
for chunk in response.iter_content(chunk_size=READ_CHUNK_BYTES):
|
||||||
|
total += len(chunk)
|
||||||
|
if total > MAX_RESPONSE_BYTES:
|
||||||
|
raise SSRFBlocked(f"Response exceeded {MAX_RESPONSE_BYTES} bytes")
|
||||||
|
chunks.append(chunk)
|
||||||
|
return b"".join(chunks)
|
||||||
+29
-4
@@ -4,6 +4,7 @@ from io import BytesIO
|
|||||||
|
|
||||||
from celery import shared_task
|
from celery import shared_task
|
||||||
from django.contrib.auth import get_user_model
|
from django.contrib.auth import get_user_model
|
||||||
|
from django.db.models import Q
|
||||||
from django.utils import timezone
|
from django.utils import timezone
|
||||||
|
|
||||||
from apps.articles.tasks import apply_filter_rules_for_feed
|
from apps.articles.tasks import apply_filter_rules_for_feed
|
||||||
@@ -14,13 +15,23 @@ from .services.fetcher import effective_interval_minutes, fetch_and_ingest
|
|||||||
|
|
||||||
logger = logging.getLogger(__name__)
|
logger = logging.getLogger(__name__)
|
||||||
|
|
||||||
|
# How long a claimed-but-unfinished fetch blocks the same feed from being
|
||||||
|
# claimed again — must comfortably exceed FETCH_TIMEOUT_SECONDS plus parse/
|
||||||
|
# ingest time, so a slow-but-healthy fetch is never raced by the next tick,
|
||||||
|
# while a worker that died mid-fetch doesn't wedge the feed forever.
|
||||||
|
CLAIM_STALE_MINUTES = 10
|
||||||
|
|
||||||
|
|
||||||
@shared_task
|
@shared_task
|
||||||
def poll_due_feeds():
|
def poll_due_feeds():
|
||||||
"""Find every active Feed whose polling interval has elapsed and
|
"""Find every active Feed whose polling interval has elapsed, atomically
|
||||||
dispatch a fetch_feed task for each — fan-out happens here, not via one
|
claim it (so overlapping beat ticks or a slow-running previous fetch
|
||||||
Celery Beat entry per feed.
|
can't dispatch the same feed twice), and dispatch a fetch_feed task for
|
||||||
|
each claimed feed — fan-out happens here, not via one Celery Beat entry
|
||||||
|
per feed.
|
||||||
"""
|
"""
|
||||||
|
now = timezone.now()
|
||||||
|
claim_stale_before = now - timedelta(minutes=CLAIM_STALE_MINUTES)
|
||||||
due_feed_ids = [
|
due_feed_ids = [
|
||||||
feed.id
|
feed.id
|
||||||
for feed in Feed.objects.filter(is_active=True).only(
|
for feed in Feed.objects.filter(is_active=True).only(
|
||||||
@@ -28,9 +39,22 @@ def poll_due_feeds():
|
|||||||
)
|
)
|
||||||
if _is_due(feed)
|
if _is_due(feed)
|
||||||
]
|
]
|
||||||
|
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
|
||||||
|
# level: it only claims rows nobody else has already claimed more
|
||||||
|
# recently than CLAIM_STALE_MINUTES ago, so two workers racing this
|
||||||
|
# same loop can't both get rowcount=1 for the same feed.
|
||||||
|
claimed = (
|
||||||
|
Feed.objects.filter(id=feed_id, is_active=True)
|
||||||
|
.filter(Q(claimed_at__isnull=True) | Q(claimed_at__lt=claim_stale_before))
|
||||||
|
.update(claimed_at=now)
|
||||||
|
)
|
||||||
|
if claimed:
|
||||||
|
claimed_ids.append(feed_id)
|
||||||
|
for feed_id in claimed_ids:
|
||||||
fetch_feed.delay(feed_id)
|
fetch_feed.delay(feed_id)
|
||||||
return len(due_feed_ids)
|
return len(claimed_ids)
|
||||||
|
|
||||||
|
|
||||||
def _is_due(feed: Feed) -> bool:
|
def _is_due(feed: Feed) -> bool:
|
||||||
@@ -48,6 +72,7 @@ def fetch_feed(feed_id: int):
|
|||||||
return None
|
return None
|
||||||
|
|
||||||
result = fetch_and_ingest(feed)
|
result = fetch_and_ingest(feed)
|
||||||
|
feed.claimed_at = None
|
||||||
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
|
||||||
|
|||||||
@@ -0,0 +1,138 @@
|
|||||||
|
import socket
|
||||||
|
|
||||||
|
import pytest
|
||||||
|
import responses
|
||||||
|
|
||||||
|
from apps.feeds.services.ssrf_guard import (
|
||||||
|
MAX_REDIRECTS,
|
||||||
|
MAX_RESPONSE_BYTES,
|
||||||
|
SSRFBlocked,
|
||||||
|
safe_get,
|
||||||
|
validate_fetch_url,
|
||||||
|
)
|
||||||
|
|
||||||
|
# apps/feeds/conftest.py's autouse _fake_public_dns fixture pins every
|
||||||
|
# hostname to this address unless a test below overrides it directly.
|
||||||
|
PUBLIC_IP = "93.184.216.34"
|
||||||
|
|
||||||
|
|
||||||
|
def _patch_dns(monkeypatch, ip: str):
|
||||||
|
def _fake_getaddrinfo(host, *args, **kwargs):
|
||||||
|
return [(socket.AF_INET, socket.SOCK_STREAM, 6, "", (ip, 0))]
|
||||||
|
|
||||||
|
monkeypatch.setattr(socket, "getaddrinfo", _fake_getaddrinfo)
|
||||||
|
|
||||||
|
|
||||||
|
class TestValidateFetchUrl:
|
||||||
|
def test_allows_a_public_https_url(self):
|
||||||
|
validate_fetch_url("https://example.com/feed.xml")
|
||||||
|
|
||||||
|
def test_rejects_a_non_http_scheme(self):
|
||||||
|
with pytest.raises(SSRFBlocked, match="scheme"):
|
||||||
|
validate_fetch_url("file:///etc/passwd")
|
||||||
|
|
||||||
|
def test_rejects_a_url_with_no_hostname(self):
|
||||||
|
with pytest.raises(SSRFBlocked, match="hostname"):
|
||||||
|
validate_fetch_url("https:///feed.xml")
|
||||||
|
|
||||||
|
@pytest.mark.parametrize(
|
||||||
|
"ip",
|
||||||
|
[
|
||||||
|
"127.0.0.1", # loopback
|
||||||
|
"10.0.0.5", # RFC1918 private
|
||||||
|
"192.168.1.1", # RFC1918 private
|
||||||
|
"169.254.169.254", # link-local / cloud metadata
|
||||||
|
"0.0.0.0", # unspecified
|
||||||
|
"::1", # IPv6 loopback
|
||||||
|
"fc00::1", # IPv6 unique local
|
||||||
|
],
|
||||||
|
)
|
||||||
|
def test_rejects_a_url_resolving_to_a_non_public_address(self, monkeypatch, ip):
|
||||||
|
_patch_dns(monkeypatch, ip)
|
||||||
|
with pytest.raises(SSRFBlocked, match="non-public"):
|
||||||
|
validate_fetch_url("https://internal.example.com/feed.xml")
|
||||||
|
|
||||||
|
def test_rejects_a_url_whose_hostname_does_not_resolve(self, monkeypatch):
|
||||||
|
def _raise(*args, **kwargs):
|
||||||
|
raise socket.gaierror("nope")
|
||||||
|
|
||||||
|
monkeypatch.setattr(socket, "getaddrinfo", _raise)
|
||||||
|
with pytest.raises(SSRFBlocked, match="Could not resolve"):
|
||||||
|
validate_fetch_url("https://nowhere.example.com/feed.xml")
|
||||||
|
|
||||||
|
|
||||||
|
class TestSafeGet:
|
||||||
|
@responses.activate
|
||||||
|
def test_returns_the_response_body_for_a_normal_feed(self):
|
||||||
|
responses.add(responses.GET, "https://example.com/feed.xml", body="<rss></rss>")
|
||||||
|
response = safe_get("https://example.com/feed.xml", headers={}, timeout=5)
|
||||||
|
assert response.status_code == 200
|
||||||
|
assert response.content == b"<rss></rss>"
|
||||||
|
|
||||||
|
@responses.activate
|
||||||
|
def test_follows_a_safe_redirect(self):
|
||||||
|
responses.add(
|
||||||
|
responses.GET,
|
||||||
|
"https://example.com/feed.xml",
|
||||||
|
status=302,
|
||||||
|
headers={"Location": "https://example.com/final.xml"},
|
||||||
|
)
|
||||||
|
responses.add(responses.GET, "https://example.com/final.xml", body="<rss>final</rss>")
|
||||||
|
|
||||||
|
response = safe_get("https://example.com/feed.xml", headers={}, timeout=5)
|
||||||
|
assert response.content == b"<rss>final</rss>"
|
||||||
|
|
||||||
|
@responses.activate
|
||||||
|
def test_blocks_a_redirect_to_a_private_address(self, monkeypatch):
|
||||||
|
responses.add(
|
||||||
|
responses.GET,
|
||||||
|
"https://example.com/feed.xml",
|
||||||
|
status=302,
|
||||||
|
headers={"Location": "http://internal.example.com/secret"},
|
||||||
|
)
|
||||||
|
|
||||||
|
real_getaddrinfo = socket.getaddrinfo
|
||||||
|
|
||||||
|
def _fake_getaddrinfo(host, *args, **kwargs):
|
||||||
|
if host == "internal.example.com":
|
||||||
|
return [(socket.AF_INET, socket.SOCK_STREAM, 6, "", ("127.0.0.1", 0))]
|
||||||
|
return real_getaddrinfo(host, *args, **kwargs)
|
||||||
|
|
||||||
|
monkeypatch.setattr(socket, "getaddrinfo", _fake_getaddrinfo)
|
||||||
|
|
||||||
|
with pytest.raises(SSRFBlocked, match="non-public"):
|
||||||
|
safe_get("https://example.com/feed.xml", headers={}, timeout=5)
|
||||||
|
|
||||||
|
@responses.activate
|
||||||
|
def test_blocks_a_redirect_loop_past_max_redirects(self):
|
||||||
|
for _ in range(MAX_REDIRECTS + 2):
|
||||||
|
responses.add(
|
||||||
|
responses.GET,
|
||||||
|
"https://example.com/feed.xml",
|
||||||
|
status=302,
|
||||||
|
headers={"Location": "https://example.com/feed.xml"},
|
||||||
|
)
|
||||||
|
|
||||||
|
with pytest.raises(SSRFBlocked, match="Too many redirects"):
|
||||||
|
safe_get("https://example.com/feed.xml", headers={}, timeout=5)
|
||||||
|
|
||||||
|
@responses.activate
|
||||||
|
def test_blocks_a_response_over_the_size_cap(self):
|
||||||
|
responses.add(
|
||||||
|
responses.GET,
|
||||||
|
"https://example.com/feed.xml",
|
||||||
|
body=b"x" * (MAX_RESPONSE_BYTES + 1),
|
||||||
|
)
|
||||||
|
with pytest.raises(SSRFBlocked, match="exceeded"):
|
||||||
|
safe_get("https://example.com/feed.xml", headers={}, timeout=5)
|
||||||
|
|
||||||
|
@responses.activate
|
||||||
|
def test_preserves_case_insensitive_header_lookup(self):
|
||||||
|
responses.add(
|
||||||
|
responses.GET,
|
||||||
|
"https://example.com/feed.xml",
|
||||||
|
body="<rss></rss>",
|
||||||
|
headers={"etag": "abc123"},
|
||||||
|
)
|
||||||
|
response = safe_get("https://example.com/feed.xml", headers={}, timeout=5)
|
||||||
|
assert response.headers.get("ETag") == "abc123"
|
||||||
@@ -40,6 +40,58 @@ def test_poll_due_feeds_dispatches_only_due_feeds():
|
|||||||
assert inactive_but_overdue.id not in dispatched_ids
|
assert inactive_but_overdue.id not in dispatched_ids
|
||||||
|
|
||||||
|
|
||||||
|
@pytest.mark.django_db
|
||||||
|
def test_poll_due_feeds_does_not_reclaim_a_feed_it_just_claimed():
|
||||||
|
# Models a second beat tick (or an overlapping worker) running
|
||||||
|
# poll_due_feeds before the first claimed fetch_feed has finished —
|
||||||
|
# the feed must only be dispatched once.
|
||||||
|
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:
|
||||||
|
first_count = poll_due_feeds()
|
||||||
|
second_count = poll_due_feeds()
|
||||||
|
|
||||||
|
assert first_count == 1
|
||||||
|
assert second_count == 0
|
||||||
|
assert mock_delay.call_count == 1
|
||||||
|
overdue.refresh_from_db()
|
||||||
|
assert overdue.claimed_at is not None
|
||||||
|
|
||||||
|
|
||||||
|
@pytest.mark.django_db
|
||||||
|
def test_poll_due_feeds_reclaims_a_stale_claim():
|
||||||
|
from apps.feeds.tasks import CLAIM_STALE_MINUTES
|
||||||
|
|
||||||
|
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),
|
||||||
|
)
|
||||||
|
|
||||||
|
with patch("apps.feeds.tasks.fetch_feed.delay") as mock_delay:
|
||||||
|
dispatched_count = poll_due_feeds()
|
||||||
|
|
||||||
|
assert dispatched_count == 1
|
||||||
|
assert mock_delay.call_args.args[0] == overdue.id
|
||||||
|
|
||||||
|
|
||||||
|
@pytest.mark.django_db
|
||||||
|
@responses.activate
|
||||||
|
def test_fetch_feed_task_clears_its_claim():
|
||||||
|
feed = Feed.objects.create(feed_url="https://example.com/feed.xml", claimed_at=timezone.now())
|
||||||
|
responses.add(responses.GET, feed.feed_url, body=GOOD_FEED_XML, status=200)
|
||||||
|
|
||||||
|
fetch_feed(feed.id)
|
||||||
|
|
||||||
|
feed.refresh_from_db()
|
||||||
|
assert feed.claimed_at is None
|
||||||
|
|
||||||
|
|
||||||
GOOD_FEED_XML = """<?xml version="1.0"?>
|
GOOD_FEED_XML = """<?xml version="1.0"?>
|
||||||
<rss version="2.0"><channel>
|
<rss version="2.0"><channel>
|
||||||
<title>Example Blog</title>
|
<title>Example Blog</title>
|
||||||
|
|||||||
@@ -32,6 +32,11 @@ def test_service_worker_is_served_at_root_with_correct_type_and_scope(client):
|
|||||||
assert 'self.addEventListener("fetch"' in body
|
assert 'self.addEventListener("fetch"' in body
|
||||||
# Mutations must stay network-only, never intercepted.
|
# Mutations must stay network-only, never intercepted.
|
||||||
assert 'request.method !== "GET"' in body
|
assert 'request.method !== "GET"' in body
|
||||||
|
# Logging out must purge PAGES_CACHE so a later offline navigation on
|
||||||
|
# a shared/account-switched device can't serve another user's
|
||||||
|
# previously cached authenticated pages.
|
||||||
|
assert "caches.delete(PAGES_CACHE)" in body
|
||||||
|
assert reverse("accounts:logout") in body
|
||||||
|
|
||||||
|
|
||||||
@pytest.mark.django_db
|
@pytest.mark.django_db
|
||||||
|
|||||||
@@ -164,3 +164,27 @@ def test_saved_filter_only_shows_saved_articles(client, alice, alices_article):
|
|||||||
|
|
||||||
response = client.get(reverse("reader:stream"), {"filter": "starred"})
|
response = client.get(reverse("reader:stream"), {"filter": "starred"})
|
||||||
assert alices_article.title not in response.content.decode()
|
assert alices_article.title not in response.content.decode()
|
||||||
|
|
||||||
|
|
||||||
|
@pytest.mark.django_db
|
||||||
|
def test_sidebar_shows_a_tags_total_unread_count(client, alice):
|
||||||
|
from apps.articles.models import SubscriptionTag, Tag
|
||||||
|
|
||||||
|
feed_a = Feed.objects.create(feed_url="https://a.example.com/feed.xml")
|
||||||
|
feed_b = Feed.objects.create(feed_url="https://b.example.com/feed.xml")
|
||||||
|
sub_a = Subscription.objects.create(user=alice, feed=feed_a)
|
||||||
|
sub_b = Subscription.objects.create(user=alice, feed=feed_b)
|
||||||
|
tag = Tag.objects.create(user=alice, name="work")
|
||||||
|
SubscriptionTag.objects.create(user=alice, subscription=sub_a, tag=tag)
|
||||||
|
SubscriptionTag.objects.create(user=alice, subscription=sub_b, tag=tag)
|
||||||
|
for i in range(3):
|
||||||
|
Article.objects.create(feed=feed_a, guid=f"a-{i}", title=f"A{i}")
|
||||||
|
for i in range(4):
|
||||||
|
Article.objects.create(feed=feed_b, guid=f"b-{i}", title=f"B{i}")
|
||||||
|
|
||||||
|
client.login(username="alice", password="pw-alice-123")
|
||||||
|
response = client.get(reverse("reader:stream"))
|
||||||
|
|
||||||
|
# The only "7" on the page — the individual feeds show 3 and 4.
|
||||||
|
content = response.content.decode()
|
||||||
|
assert '<span class="unread-count">7</span>' in content
|
||||||
+68
-4
@@ -9,6 +9,7 @@ from __future__ import annotations
|
|||||||
|
|
||||||
import logging
|
import logging
|
||||||
import re
|
import re
|
||||||
|
import signal
|
||||||
|
|
||||||
from django.utils import timezone
|
from django.utils import timezone
|
||||||
|
|
||||||
@@ -27,6 +28,42 @@ logger = logging.getLogger(__name__)
|
|||||||
|
|
||||||
_TAG_RE = re.compile(r"<[^>]+>")
|
_TAG_RE = re.compile(r"<[^>]+>")
|
||||||
|
|
||||||
|
# Bounds how much CPU/time a single user-authored regex rule can burn
|
||||||
|
# against one article. re has no built-in match timeout, so this uses
|
||||||
|
# SIGALRM to interrupt a runaway match (catastrophic backtracking) —
|
||||||
|
# only effective on the main thread of a process with SIGALRM available,
|
||||||
|
# which covers gunicorn's sync workers and Celery's (default) prefork
|
||||||
|
# pool; elsewhere it's skipped and MAX_REGEX_HAYSTACK_CHARS is the only
|
||||||
|
# bound. reapply_rules_for_user (apps.rules.tasks) also carries a Celery
|
||||||
|
# task time_limit as a second, coarser backstop.
|
||||||
|
REGEX_TIMEOUT_SECONDS = 1
|
||||||
|
MAX_REGEX_HAYSTACK_CHARS = 20_000
|
||||||
|
|
||||||
|
|
||||||
|
class _RegexTimeout(Exception):
|
||||||
|
pass
|
||||||
|
|
||||||
|
|
||||||
|
def _raise_regex_timeout(signum, frame):
|
||||||
|
raise _RegexTimeout()
|
||||||
|
|
||||||
|
|
||||||
|
def _regex_search_with_timeout(pattern: str, haystack: str, flags: int):
|
||||||
|
if not hasattr(signal, "SIGALRM"):
|
||||||
|
return re.search(pattern, haystack, flags)
|
||||||
|
try:
|
||||||
|
previous_handler = signal.signal(signal.SIGALRM, _raise_regex_timeout)
|
||||||
|
except ValueError:
|
||||||
|
# Not the main thread (e.g. a threaded dev server) — signal
|
||||||
|
# timers only work there.
|
||||||
|
return re.search(pattern, haystack, flags)
|
||||||
|
signal.setitimer(signal.ITIMER_REAL, REGEX_TIMEOUT_SECONDS)
|
||||||
|
try:
|
||||||
|
return re.search(pattern, haystack, flags)
|
||||||
|
finally:
|
||||||
|
signal.setitimer(signal.ITIMER_REAL, 0)
|
||||||
|
signal.signal(signal.SIGALRM, previous_handler)
|
||||||
|
|
||||||
|
|
||||||
def _haystack(article: Article, match_field: str) -> str:
|
def _haystack(article: Article, match_field: str) -> str:
|
||||||
if match_field == FilterRule.FIELD_TITLE:
|
if match_field == FilterRule.FIELD_TITLE:
|
||||||
@@ -47,8 +84,12 @@ def rule_matches(rule: FilterRule, article: Article) -> bool:
|
|||||||
|
|
||||||
if rule.match_type == FilterRule.MATCH_REGEX:
|
if rule.match_type == FilterRule.MATCH_REGEX:
|
||||||
flags = 0 if rule.case_sensitive else re.IGNORECASE
|
flags = 0 if rule.case_sensitive else re.IGNORECASE
|
||||||
|
haystack = raw_haystack[:MAX_REGEX_HAYSTACK_CHARS]
|
||||||
try:
|
try:
|
||||||
return re.search(rule.match_value, raw_haystack, flags) is not None
|
return _regex_search_with_timeout(rule.match_value, haystack, flags) is not None
|
||||||
|
except _RegexTimeout:
|
||||||
|
logger.warning("Regex timed out for rule %s", rule.pk)
|
||||||
|
return False
|
||||||
except re.error as exc:
|
except re.error as exc:
|
||||||
logger.warning("Invalid regex in rule %s: %s", rule.pk, exc)
|
logger.warning("Invalid regex in rule %s: %s", rule.pk, exc)
|
||||||
return False
|
return False
|
||||||
@@ -100,13 +141,36 @@ def apply_rule_action(rule: FilterRule, user, article: Article, state: UserArtic
|
|||||||
return False
|
return False
|
||||||
|
|
||||||
|
|
||||||
def evaluate_rules_for_article(user, article: Article, rules) -> None:
|
def rule_in_scope(rule: FilterRule, feed_id, subscription_tag_ids) -> bool:
|
||||||
"""Evaluates an ordered iterable of rules (already scoped/enabled)
|
"""Whether `rule`'s own feed/tag scope (see FilterRule's docstring)
|
||||||
against one article for one user, applying actions as they match."""
|
covers an article from `feed_id`, given the user's subscription-tag
|
||||||
|
ids for that feed.
|
||||||
|
|
||||||
|
Centralized here — rather than left for each caller to re-derive via
|
||||||
|
its own query filters — so ingest-time dispatch and backlog re-apply
|
||||||
|
can't drift into scoping rules differently (see apps.articles.tasks
|
||||||
|
and apps.rules.tasks).
|
||||||
|
"""
|
||||||
|
if rule.feed_id is not None and rule.feed_id != feed_id:
|
||||||
|
return False
|
||||||
|
if rule.tag_id is not None and rule.tag_id not in subscription_tag_ids:
|
||||||
|
return False
|
||||||
|
return True
|
||||||
|
|
||||||
|
|
||||||
|
def evaluate_rules_for_article(user, article: Article, rules, subscription_tag_ids=()) -> None:
|
||||||
|
"""Evaluates an ordered iterable of a user's enabled rules against one
|
||||||
|
article, applying actions as they match. `rules` doesn't need to be
|
||||||
|
pre-scoped to this article's feed/tags — out-of-scope rules (per
|
||||||
|
rule_in_scope) are skipped here, so callers can pass one user's whole
|
||||||
|
enabled ruleset regardless of which feed(s) the article(s) belong to.
|
||||||
|
"""
|
||||||
matched_any = False
|
matched_any = False
|
||||||
state = None
|
state = None
|
||||||
|
|
||||||
for rule in rules:
|
for rule in rules:
|
||||||
|
if not rule_in_scope(rule, article.feed_id, subscription_tag_ids):
|
||||||
|
continue
|
||||||
if not rule_matches(rule, article):
|
if not rule_matches(rule, article):
|
||||||
continue
|
continue
|
||||||
if state is None:
|
if state is None:
|
||||||
|
|||||||
+24
-6
@@ -1,6 +1,6 @@
|
|||||||
from celery import shared_task
|
from celery import shared_task
|
||||||
|
|
||||||
from apps.articles.models import Article
|
from apps.articles.models import Article, SubscriptionTag
|
||||||
from apps.feeds.models import Subscription
|
from apps.feeds.models import Subscription
|
||||||
|
|
||||||
from .engine import evaluate_rules_for_article
|
from .engine import evaluate_rules_for_article
|
||||||
@@ -12,9 +12,20 @@ def reapply_rules_for_user_backlog(rule_id: int) -> int:
|
|||||||
rule, so priority/short-circuit ordering stays correct) against their
|
rule, so priority/short-circuit ordering stays correct) against their
|
||||||
unread backlog, scoped by the triggering rule's own feed/tag scope.
|
unread backlog, scoped by the triggering rule's own feed/tag scope.
|
||||||
|
|
||||||
Exists as a plain function so it can be called synchronously for
|
The *backlog* is narrowed to the triggering rule's own feed/tag scope
|
||||||
immediate feedback (e.g. from a "Re-apply" view) or wrapped in a task
|
(re-applying a feed-scoped rule has no reason to touch other feeds'
|
||||||
for background use — see reapply_rules_for_user below.
|
articles), but which of the user's *other* rules apply to each of
|
||||||
|
those articles is still per-article/per-feed — evaluate_rules_for_article
|
||||||
|
checks that via rule_in_scope, so a feed- or tag-scoped rule for a
|
||||||
|
different feed can't fire on this backlog just because it happened to
|
||||||
|
match (see apps.rules.engine.rule_in_scope).
|
||||||
|
|
||||||
|
Exists as a plain function, separate from the reapply_rules_for_user
|
||||||
|
task below, so it's unit-testable without Celery — but every caller
|
||||||
|
should go through that task (see apps.rules.views.reapply_rule), not
|
||||||
|
call this directly from a request: a large backlog or a pathological
|
||||||
|
regex (bounded but not eliminated by apps.rules.engine's timeout
|
||||||
|
guard) could otherwise tie up a web worker for a long time.
|
||||||
"""
|
"""
|
||||||
try:
|
try:
|
||||||
rule = FilterRule.objects.select_related("user").get(pk=rule_id)
|
rule = FilterRule.objects.select_related("user").get(pk=rule_id)
|
||||||
@@ -45,13 +56,20 @@ def reapply_rules_for_user_backlog(rule_id: int) -> int:
|
|||||||
|
|
||||||
rules = list(FilterRule.objects.filter(user=user, is_enabled=True).order_by("priority", "id"))
|
rules = list(FilterRule.objects.filter(user=user, is_enabled=True).order_by("priority", "id"))
|
||||||
|
|
||||||
|
subscription_tag_ids_by_feed: dict[int, set[int]] = {}
|
||||||
|
for feed_id, tag_id in SubscriptionTag.objects.filter(
|
||||||
|
user=user, subscription__feed_id__in=feed_ids
|
||||||
|
).values_list("subscription__feed_id", "tag_id"):
|
||||||
|
subscription_tag_ids_by_feed.setdefault(feed_id, set()).add(tag_id)
|
||||||
|
|
||||||
count = 0
|
count = 0
|
||||||
for article in backlog:
|
for article in backlog:
|
||||||
evaluate_rules_for_article(user, article, rules)
|
subscription_tag_ids = subscription_tag_ids_by_feed.get(article.feed_id, set())
|
||||||
|
evaluate_rules_for_article(user, article, rules, subscription_tag_ids)
|
||||||
count += 1
|
count += 1
|
||||||
return count
|
return count
|
||||||
|
|
||||||
|
|
||||||
@shared_task
|
@shared_task(time_limit=120, soft_time_limit=90)
|
||||||
def reapply_rules_for_user(rule_id: int):
|
def reapply_rules_for_user(rule_id: int):
|
||||||
return reapply_rules_for_user_backlog(rule_id)
|
return reapply_rules_for_user_backlog(rule_id)
|
||||||
@@ -1,3 +1,5 @@
|
|||||||
|
import time
|
||||||
|
|
||||||
import pytest
|
import pytest
|
||||||
from django.contrib.auth import get_user_model
|
from django.contrib.auth import get_user_model
|
||||||
|
|
||||||
@@ -10,7 +12,7 @@ from apps.articles.models import (
|
|||||||
)
|
)
|
||||||
from apps.feeds.models import Feed
|
from apps.feeds.models import Feed
|
||||||
|
|
||||||
from .engine import evaluate_rules_for_article, rule_matches
|
from .engine import evaluate_rules_for_article, rule_in_scope, rule_matches
|
||||||
from .models import FilterRule
|
from .models import FilterRule
|
||||||
|
|
||||||
User = get_user_model()
|
User = get_user_model()
|
||||||
@@ -87,6 +89,22 @@ class TestRuleMatches:
|
|||||||
rule = make_rule(user, match_type=FilterRule.MATCH_REGEX, match_value="(unclosed")
|
rule = make_rule(user, match_type=FilterRule.MATCH_REGEX, match_value="(unclosed")
|
||||||
assert rule_matches(rule, article) is False
|
assert rule_matches(rule, article) is False
|
||||||
|
|
||||||
|
def test_catastrophic_backtracking_regex_times_out_instead_of_hanging(self, user, article):
|
||||||
|
# (a+)+$ against a long run of a's followed by a non-matching
|
||||||
|
# character is a textbook ReDoS pattern — left unguarded this
|
||||||
|
# takes on the order of a minute (confirmed locally); the
|
||||||
|
# REGEX_TIMEOUT_SECONDS guard in apps.rules.engine must interrupt
|
||||||
|
# it well before that instead of hanging the caller.
|
||||||
|
article.title = "a" * 30 + "!"
|
||||||
|
rule = make_rule(user, match_type=FilterRule.MATCH_REGEX, match_value=r"(a+)+$")
|
||||||
|
|
||||||
|
start = time.monotonic()
|
||||||
|
result = rule_matches(rule, article)
|
||||||
|
elapsed = time.monotonic() - start
|
||||||
|
|
||||||
|
assert result is False
|
||||||
|
assert elapsed < 5
|
||||||
|
|
||||||
def test_content_field_strips_html_tags(self, user, article):
|
def test_content_field_strips_html_tags(self, user, article):
|
||||||
rule = make_rule(user, match_field=FilterRule.FIELD_CONTENT, match_value="Lots of details")
|
rule = make_rule(user, match_field=FilterRule.FIELD_CONTENT, match_value="Lots of details")
|
||||||
assert rule_matches(rule, article) is True
|
assert rule_matches(rule, article) is True
|
||||||
@@ -104,6 +122,24 @@ class TestRuleMatches:
|
|||||||
assert rule_matches(rule, article) is True
|
assert rule_matches(rule, article) is True
|
||||||
|
|
||||||
|
|
||||||
|
@pytest.mark.django_db
|
||||||
|
class TestRuleInScope:
|
||||||
|
def test_unscoped_rule_applies_to_any_feed(self, user):
|
||||||
|
rule = make_rule(user)
|
||||||
|
assert rule_in_scope(rule, feed_id=999, subscription_tag_ids=set()) is True
|
||||||
|
|
||||||
|
def test_feed_scoped_rule_only_applies_to_its_own_feed(self, user, feed):
|
||||||
|
rule = make_rule(user, feed=feed)
|
||||||
|
assert rule_in_scope(rule, feed_id=feed.id, subscription_tag_ids=set()) is True
|
||||||
|
assert rule_in_scope(rule, feed_id=feed.id + 1, subscription_tag_ids=set()) is False
|
||||||
|
|
||||||
|
def test_tag_scoped_rule_only_applies_when_the_feed_carries_that_tag(self, user):
|
||||||
|
tag = Tag.objects.create(user=user, name="work")
|
||||||
|
rule = make_rule(user, tag=tag)
|
||||||
|
assert rule_in_scope(rule, feed_id=1, subscription_tag_ids={tag.id}) is True
|
||||||
|
assert rule_in_scope(rule, feed_id=1, subscription_tag_ids=set()) is False
|
||||||
|
|
||||||
|
|
||||||
@pytest.mark.django_db
|
@pytest.mark.django_db
|
||||||
class TestApplyRuleAction:
|
class TestApplyRuleAction:
|
||||||
def test_star_action(self, user, article):
|
def test_star_action(self, user, article):
|
||||||
|
|||||||
+103
-1
@@ -1,8 +1,17 @@
|
|||||||
|
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 apps.articles.models import STARRED_TAG_NAME, Article, ArticleTag, UserArticleState
|
from apps.articles.models import (
|
||||||
|
STARRED_TAG_NAME,
|
||||||
|
Article,
|
||||||
|
ArticleTag,
|
||||||
|
SubscriptionTag,
|
||||||
|
Tag,
|
||||||
|
UserArticleState,
|
||||||
|
)
|
||||||
from apps.feeds.models import Feed, Subscription
|
from apps.feeds.models import Feed, Subscription
|
||||||
|
|
||||||
from .models import FilterRule
|
from .models import FilterRule
|
||||||
@@ -119,6 +128,28 @@ def test_reapply_rule_view_applies_to_unread_backlog(client, alice, feed):
|
|||||||
assert is_starred(alice, article) is True
|
assert is_starred(alice, article) is True
|
||||||
|
|
||||||
|
|
||||||
|
@pytest.mark.django_db
|
||||||
|
def test_reapply_rule_view_always_queues_through_celery_never_runs_inline(client, alice, feed):
|
||||||
|
# A large backlog or a pathological regex must not be able to tie up
|
||||||
|
# the request/response cycle — the view should dispatch a task, not
|
||||||
|
# call reapply_rules_for_user_backlog directly.
|
||||||
|
Subscription.objects.create(user=alice, feed=feed)
|
||||||
|
rule = FilterRule.objects.create(
|
||||||
|
user=alice,
|
||||||
|
match_field=FilterRule.FIELD_TITLE,
|
||||||
|
match_type=FilterRule.MATCH_CONTAINS,
|
||||||
|
match_value="Python",
|
||||||
|
action=FilterRule.ACTION_STAR,
|
||||||
|
)
|
||||||
|
client.login(username="alice", password="pw-alice-123")
|
||||||
|
|
||||||
|
with patch("apps.rules.views.reapply_rules_for_user.delay") as mock_delay:
|
||||||
|
response = client.post(reverse("rules:reapply_rule", args=[rule.pk]))
|
||||||
|
|
||||||
|
assert response.status_code == 302
|
||||||
|
mock_delay.assert_called_once_with(rule.pk)
|
||||||
|
|
||||||
|
|
||||||
@pytest.mark.django_db
|
@pytest.mark.django_db
|
||||||
def test_reapply_skips_already_read_articles(alice, feed):
|
def test_reapply_skips_already_read_articles(alice, feed):
|
||||||
article = Article.objects.create(feed=feed, guid="guid-1", title="Python 4 released")
|
article = Article.objects.create(feed=feed, guid="guid-1", title="Python 4 released")
|
||||||
@@ -160,3 +191,74 @@ def test_reapply_respects_feed_scope(alice):
|
|||||||
|
|
||||||
assert is_starred(alice, article_a) is True
|
assert is_starred(alice, article_a) is True
|
||||||
assert not UserArticleState.objects.filter(user=alice, article=article_b).exists()
|
assert not UserArticleState.objects.filter(user=alice, article=article_b).exists()
|
||||||
|
|
||||||
|
|
||||||
|
@pytest.mark.django_db
|
||||||
|
def test_reapply_does_not_apply_a_different_feeds_scoped_rule_to_the_backlog():
|
||||||
|
# Regression test for a bug where re-applying one feed-scoped rule
|
||||||
|
# loaded *every* enabled rule and ran it against the whole backlog
|
||||||
|
# with no scope check — so a same-matching rule scoped to a feed
|
||||||
|
# the user isn't re-applying would still fire on this backlog.
|
||||||
|
feed_a = Feed.objects.create(feed_url="https://a.example.com/feed.xml")
|
||||||
|
feed_b = Feed.objects.create(feed_url="https://b.example.com/feed.xml")
|
||||||
|
alice = User.objects.create_user("alice", password="pw-alice-123")
|
||||||
|
Subscription.objects.create(user=alice, feed=feed_a)
|
||||||
|
Subscription.objects.create(user=alice, feed=feed_b)
|
||||||
|
article_a = Article.objects.create(feed=feed_a, guid="guid-1", title="Python in A")
|
||||||
|
|
||||||
|
triggering_rule = FilterRule.objects.create(
|
||||||
|
user=alice,
|
||||||
|
feed=feed_a,
|
||||||
|
match_field=FilterRule.FIELD_TITLE,
|
||||||
|
match_type=FilterRule.MATCH_CONTAINS,
|
||||||
|
match_value="Python",
|
||||||
|
action=FilterRule.ACTION_STAR,
|
||||||
|
)
|
||||||
|
FilterRule.objects.create(
|
||||||
|
user=alice,
|
||||||
|
feed=feed_b,
|
||||||
|
match_field=FilterRule.FIELD_TITLE,
|
||||||
|
match_type=FilterRule.MATCH_CONTAINS,
|
||||||
|
match_value="Python",
|
||||||
|
action=FilterRule.ACTION_TAG,
|
||||||
|
action_value="feed-b-only",
|
||||||
|
)
|
||||||
|
|
||||||
|
reapply_rules_for_user_backlog(triggering_rule.pk)
|
||||||
|
|
||||||
|
assert is_starred(alice, article_a) is True
|
||||||
|
assert not Tag.objects.filter(user=alice, name="feed-b-only").exists()
|
||||||
|
|
||||||
|
|
||||||
|
@pytest.mark.django_db
|
||||||
|
def test_reapply_applies_a_tag_scoped_rule_only_to_that_tags_feeds():
|
||||||
|
feed_a = Feed.objects.create(feed_url="https://a.example.com/feed.xml")
|
||||||
|
feed_b = Feed.objects.create(feed_url="https://b.example.com/feed.xml")
|
||||||
|
alice = User.objects.create_user("alice", password="pw-alice-123")
|
||||||
|
sub_a = Subscription.objects.create(user=alice, feed=feed_a)
|
||||||
|
Subscription.objects.create(user=alice, feed=feed_b)
|
||||||
|
tag = Tag.objects.create(user=alice, name="work")
|
||||||
|
SubscriptionTag.objects.create(user=alice, subscription=sub_a, tag=tag)
|
||||||
|
article_a = Article.objects.create(feed=feed_a, guid="guid-1", title="Python in A")
|
||||||
|
article_b = Article.objects.create(feed=feed_b, guid="guid-2", title="Python in B")
|
||||||
|
|
||||||
|
unscoped_trigger = FilterRule.objects.create(
|
||||||
|
user=alice,
|
||||||
|
match_field=FilterRule.FIELD_TITLE,
|
||||||
|
match_type=FilterRule.MATCH_CONTAINS,
|
||||||
|
match_value="unrelated-trigger-value",
|
||||||
|
action=FilterRule.ACTION_MARK_READ,
|
||||||
|
)
|
||||||
|
FilterRule.objects.create(
|
||||||
|
user=alice,
|
||||||
|
tag=tag,
|
||||||
|
match_field=FilterRule.FIELD_TITLE,
|
||||||
|
match_type=FilterRule.MATCH_CONTAINS,
|
||||||
|
match_value="Python",
|
||||||
|
action=FilterRule.ACTION_STAR,
|
||||||
|
)
|
||||||
|
|
||||||
|
reapply_rules_for_user_backlog(unscoped_trigger.pk)
|
||||||
|
|
||||||
|
assert is_starred(alice, article_a) is True
|
||||||
|
assert is_starred(alice, article_b) is False
|
||||||
+6
-5
@@ -5,7 +5,7 @@ from django.views.decorators.http import require_POST
|
|||||||
|
|
||||||
from .forms import FilterRuleForm
|
from .forms import FilterRuleForm
|
||||||
from .models import FilterRule
|
from .models import FilterRule
|
||||||
from .tasks import reapply_rules_for_user_backlog
|
from .tasks import reapply_rules_for_user
|
||||||
|
|
||||||
|
|
||||||
@login_required
|
@login_required
|
||||||
@@ -48,8 +48,9 @@ def delete_rule(request, rule_id):
|
|||||||
@require_POST
|
@require_POST
|
||||||
def reapply_rule(request, rule_id):
|
def reapply_rule(request, rule_id):
|
||||||
rule = get_object_or_404(FilterRule, user=request.user, pk=rule_id)
|
rule = get_object_or_404(FilterRule, user=request.user, pk=rule_id)
|
||||||
# Run synchronously for immediate feedback, same pattern as add_feed —
|
# Always queued, never run inline from the request/response cycle —
|
||||||
# a Celery worker isn't required for this to work.
|
# a large backlog or a pathological regex could otherwise tie up a
|
||||||
count = reapply_rules_for_user_backlog(rule.pk)
|
# web worker for a long time (see apps.rules.tasks).
|
||||||
messages.success(request, f"Re-applied your rules to {count} unread article(s).")
|
reapply_rules_for_user.delay(rule.pk)
|
||||||
|
messages.success(request, "Re-applying your rules to your unread backlog…")
|
||||||
return redirect("rules:rule_list")
|
return redirect("rules:rule_list")
|
||||||
+28
-1
@@ -1,8 +1,30 @@
|
|||||||
|
from django.core.exceptions import ImproperlyConfigured
|
||||||
|
|
||||||
from .base import * # noqa: F403
|
from .base import * # noqa: F403
|
||||||
from .base import env
|
from .base import SECRET_KEY, env
|
||||||
|
|
||||||
DEBUG = False
|
DEBUG = False
|
||||||
|
|
||||||
|
# base.py falls back to a publicly known placeholder if SECRET_KEY isn't
|
||||||
|
# set — fine for a throwaway dev DB, but production must never sign
|
||||||
|
# sessions/CSRF tokens with a key anyone can read in this repo's history.
|
||||||
|
# Fail startup rather than quietly running with a known key.
|
||||||
|
if not SECRET_KEY or SECRET_KEY == "django-insecure-change-me-in-production":
|
||||||
|
raise ImproperlyConfigured(
|
||||||
|
"SECRET_KEY is missing or still the placeholder default. Set a unique, "
|
||||||
|
"random SECRET_KEY in .env before running with prod settings — generate "
|
||||||
|
'one with: python -c "from django.core.management.utils import '
|
||||||
|
'get_random_secret_key; print(get_random_secret_key())"'
|
||||||
|
)
|
||||||
|
|
||||||
|
# Health checks (scripts/upgrade.sh, an external uptime monitor, ...) hit
|
||||||
|
# gunicorn directly over loopback, bypassing the reverse proxy entirely —
|
||||||
|
# that request's Host header is "127.0.0.1:<port>", not the public domain
|
||||||
|
# in ALLOWED_HOSTS, so without this Django 400s it. Harmless to always
|
||||||
|
# allow: gunicorn's bind address is never reachable from outside this host
|
||||||
|
# in the first place (see docs/install.md's "Reverse proxy" section).
|
||||||
|
ALLOWED_HOSTS = [*ALLOWED_HOSTS, "localhost", "127.0.0.1", "::1"] # noqa: F405
|
||||||
|
|
||||||
# A reverse proxy (nginx, Caddy, Traefik, Nginx Proxy Manager on another
|
# A reverse proxy (nginx, Caddy, Traefik, Nginx Proxy Manager on another
|
||||||
# host, ...) is required in front of gunicorn in every deployment — see
|
# host, ...) is required in front of gunicorn in every deployment — see
|
||||||
# docs/install.md — and it's always the one terminating TLS. This tells
|
# docs/install.md — and it's always the one terminating TLS. This tells
|
||||||
@@ -10,6 +32,11 @@ DEBUG = False
|
|||||||
# sets, and the redirect/cookie/HSTS settings below assume it's set.
|
# sets, and the redirect/cookie/HSTS settings below assume it's set.
|
||||||
SECURE_SSL_REDIRECT = env.bool("SECURE_SSL_REDIRECT", default=True)
|
SECURE_SSL_REDIRECT = env.bool("SECURE_SSL_REDIRECT", default=True)
|
||||||
SECURE_PROXY_SSL_HEADER = ("HTTP_X_FORWARDED_PROTO", "https")
|
SECURE_PROXY_SSL_HEADER = ("HTTP_X_FORWARDED_PROTO", "https")
|
||||||
|
# /health/ is also exempted from the HTTPS redirect above: hit directly
|
||||||
|
# over loopback (see ALLOWED_HOSTS above) it has no X-Forwarded-Proto
|
||||||
|
# header to prove it's "secure", and there's no TLS listener on gunicorn's
|
||||||
|
# own port to redirect to anyway.
|
||||||
|
SECURE_REDIRECT_EXEMPT = [r"^health/$"]
|
||||||
|
|
||||||
# WhiteNoise serves /static/ directly from gunicorn instead of relying on
|
# WhiteNoise serves /static/ directly from gunicorn instead of relying on
|
||||||
# the reverse proxy to alias the staticfiles directory on disk — the proxy
|
# the reverse proxy to alias the staticfiles directory on disk — the proxy
|
||||||
|
|||||||
+5
-4
@@ -295,6 +295,7 @@ git fetch --tags --force
|
|||||||
LATEST_TAG="$(git tag --sort=-creatordate | head -n1)"
|
LATEST_TAG="$(git tag --sort=-creatordate | head -n1)"
|
||||||
git checkout --detach "$LATEST_TAG"
|
git checkout --detach "$LATEST_TAG"
|
||||||
chown -R evection:evection /opt/evection/app
|
chown -R evection:evection /opt/evection/app
|
||||||
|
sed -i "s/^EVECTION_PWA_CACHE_VERSION=.*/EVECTION_PWA_CACHE_VERSION=$LATEST_TAG/" .env
|
||||||
sudo -u evection -H /opt/evection/venv/bin/pip install .
|
sudo -u evection -H /opt/evection/venv/bin/pip install .
|
||||||
sudo -u evection -H env DJANGO_SETTINGS_MODULE=config.settings.prod \
|
sudo -u evection -H env DJANGO_SETTINGS_MODULE=config.settings.prod \
|
||||||
/opt/evection/venv/bin/python manage.py migrate
|
/opt/evection/venv/bin/python manage.py migrate
|
||||||
@@ -311,7 +312,7 @@ git tag v$(date +%Y.%m.%d)
|
|||||||
git push --tags
|
git push --tags
|
||||||
```
|
```
|
||||||
|
|
||||||
Bump `EVECTION_PWA_CACHE_VERSION` in `.env` whenever a release changes cached
|
`upgrade.sh` sets `EVECTION_PWA_CACHE_VERSION` in `.env` to the deployed tag on every
|
||||||
static assets (CSS/JS/icons) — it's baked into the service worker's cache name, so
|
run — it's baked into the service worker's cache name, so this forces every installed
|
||||||
changing it forces every installed PWA to drop its old cache instead of serving
|
PWA to drop its old cache instead of serving stale assets after the upgrade. You don't
|
||||||
stale assets after the upgrade.
|
need to bump it by hand.
|
||||||
+40
-4
@@ -63,9 +63,45 @@ if ! "$PYTHON_BIN" -c 'import ensurepip' >/dev/null 2>&1; then
|
|||||||
exit 1
|
exit 1
|
||||||
fi
|
fi
|
||||||
|
|
||||||
if ! command -v redis-cli >/dev/null 2>&1; then
|
# Celery (and therefore all feed fetching) is entirely dependent on Redis
|
||||||
echo "Warning: 'redis-cli' not found on PATH. Install it before going live" \
|
# being reachable — it fails silently from the installer's point of view
|
||||||
"(see docs/install.md's prerequisites section: apt install redis-server)." >&2
|
# (the worker/beat processes just retry forever in the background), so this
|
||||||
|
# has to be a hard failure here, not a warning that's easy to miss while
|
||||||
|
# every later step "succeeds" at installing an app that can never fetch a
|
||||||
|
# single feed. Check the actual REDIS_URL that will end up in .env (an
|
||||||
|
# explicit EVECTION_REDIS_URL override, if set — the default local Redis
|
||||||
|
# otherwise), not just whether some redis-cli happens to be on PATH.
|
||||||
|
REDIS_URL_TO_CHECK="${EVECTION_REDIS_URL:-redis://localhost:6379/0}"
|
||||||
|
check_redis() {
|
||||||
|
"$PYTHON_BIN" -c "
|
||||||
|
import sys, socket, urllib.parse
|
||||||
|
u = urllib.parse.urlparse('$REDIS_URL_TO_CHECK')
|
||||||
|
try:
|
||||||
|
with socket.create_connection((u.hostname or 'localhost', u.port or 6379), timeout=3):
|
||||||
|
pass
|
||||||
|
except OSError as e:
|
||||||
|
print(e, file=sys.stderr)
|
||||||
|
sys.exit(1)
|
||||||
|
"
|
||||||
|
}
|
||||||
|
REDIS_HOST="$("$PYTHON_BIN" -c "import urllib.parse; print(urllib.parse.urlparse('$REDIS_URL_TO_CHECK').hostname or 'localhost')")"
|
||||||
|
if ! check_redis; then
|
||||||
|
if [[ "$REDIS_HOST" =~ ^(localhost|127\.0\.0\.1|::1)$ ]] && command -v apt-get >/dev/null 2>&1; then
|
||||||
|
echo "==> Redis isn't reachable at $REDIS_URL_TO_CHECK — installing redis-server"
|
||||||
|
apt-get install -y redis-server
|
||||||
|
systemctl enable --now redis-server
|
||||||
|
if ! check_redis; then
|
||||||
|
echo "Redis still isn't reachable after installing redis-server —" \
|
||||||
|
"check: systemctl status redis-server" >&2
|
||||||
|
exit 1
|
||||||
|
fi
|
||||||
|
else
|
||||||
|
echo "Redis isn't reachable at $REDIS_URL_TO_CHECK. Evection's background" \
|
||||||
|
"feed-fetching depends on it entirely, so this has to be fixed before" \
|
||||||
|
"continuing — either start/install Redis there, or set" \
|
||||||
|
"EVECTION_REDIS_URL to point at wherever it actually runs." >&2
|
||||||
|
exit 1
|
||||||
|
fi
|
||||||
fi
|
fi
|
||||||
|
|
||||||
# --- 2. System user -----------------------------------------------------
|
# --- 2. System user -----------------------------------------------------
|
||||||
@@ -168,7 +204,7 @@ REDIS_URL=${EVECTION_REDIS_URL:-redis://localhost:6379/0}
|
|||||||
EVECTION_GUNICORN_BIND=$GUNICORN_BIND
|
EVECTION_GUNICORN_BIND=$GUNICORN_BIND
|
||||||
EVECTION_SIGNUP_ENABLED=False
|
EVECTION_SIGNUP_ENABLED=False
|
||||||
EVECTION_MIN_FETCH_INTERVAL_MINUTES=15
|
EVECTION_MIN_FETCH_INTERVAL_MINUTES=15
|
||||||
EVECTION_PWA_CACHE_VERSION=v1
|
EVECTION_PWA_CACHE_VERSION=${LATEST_TAG:-v1}
|
||||||
EOF
|
EOF
|
||||||
chown "$EVECTION_USER:$EVECTION_USER" "$ENV_FILE"
|
chown "$EVECTION_USER:$EVECTION_USER" "$ENV_FILE"
|
||||||
chmod 600 "$ENV_FILE"
|
chmod 600 "$ENV_FILE"
|
||||||
|
|||||||
+22
-4
@@ -72,6 +72,18 @@ echo "Deploying $LATEST_TAG (currently on: $CURRENT_REF)"
|
|||||||
git checkout --quiet --detach "$LATEST_TAG"
|
git checkout --quiet --detach "$LATEST_TAG"
|
||||||
chown -R "$EVECTION_USER:$EVECTION_USER" "$APP_DIR"
|
chown -R "$EVECTION_USER:$EVECTION_USER" "$APP_DIR"
|
||||||
|
|
||||||
|
# Bump the PWA's cache-busting version to this release's tag on every
|
||||||
|
# deploy, not just ones that happened to touch static assets — a missed
|
||||||
|
# manual bump otherwise leaves installed PWAs serving a stale cached
|
||||||
|
# shell/pages indefinitely. Cheap even when nothing cacheable changed:
|
||||||
|
# it just makes the service worker open a fresh cache name next time it
|
||||||
|
# activates.
|
||||||
|
if grep -q '^EVECTION_PWA_CACHE_VERSION=' "$APP_DIR/.env"; then
|
||||||
|
sed -i "s/^EVECTION_PWA_CACHE_VERSION=.*/EVECTION_PWA_CACHE_VERSION=$LATEST_TAG/" "$APP_DIR/.env"
|
||||||
|
else
|
||||||
|
echo "EVECTION_PWA_CACHE_VERSION=$LATEST_TAG" >> "$APP_DIR/.env"
|
||||||
|
fi
|
||||||
|
|
||||||
echo "==> Installing updated dependencies"
|
echo "==> Installing updated dependencies"
|
||||||
sudo -u "$EVECTION_USER" -H "$VENV_DIR/bin/pip" install --upgrade "$APP_DIR"
|
sudo -u "$EVECTION_USER" -H "$VENV_DIR/bin/pip" install --upgrade "$APP_DIR"
|
||||||
|
|
||||||
@@ -112,7 +124,16 @@ HEALTH_PORT="${HEALTH_BIND##*:}"
|
|||||||
if [ "$HEALTH_HOST" = "0.0.0.0" ]; then
|
if [ "$HEALTH_HOST" = "0.0.0.0" ]; then
|
||||||
HEALTH_HOST="127.0.0.1"
|
HEALTH_HOST="127.0.0.1"
|
||||||
fi
|
fi
|
||||||
if curl -sf "http://$HEALTH_HOST:$HEALTH_PORT/health/" >/dev/null; then
|
# Use the venv's own Python rather than curl — curl isn't guaranteed to be
|
||||||
|
# installed on a minimal host, but the venv obviously already is.
|
||||||
|
if "$VENV_DIR/bin/python" -c "
|
||||||
|
import sys, urllib.request
|
||||||
|
try:
|
||||||
|
urllib.request.urlopen('http://$HEALTH_HOST:$HEALTH_PORT/health/', timeout=5)
|
||||||
|
except Exception as e:
|
||||||
|
print(e, file=sys.stderr)
|
||||||
|
sys.exit(1)
|
||||||
|
"; then
|
||||||
echo "Health check OK"
|
echo "Health check OK"
|
||||||
else
|
else
|
||||||
echo "Health check FAILED — check: journalctl -u evection-gunicorn -n 50" >&2
|
echo "Health check FAILED — check: journalctl -u evection-gunicorn -n 50" >&2
|
||||||
@@ -122,7 +143,4 @@ systemctl status evection-gunicorn --no-pager -l | head -10
|
|||||||
|
|
||||||
echo
|
echo
|
||||||
echo "==> Deployed $LATEST_TAG."
|
echo "==> Deployed $LATEST_TAG."
|
||||||
echo " If this release changed cached static assets (CSS/JS/icons), bump"
|
|
||||||
echo " EVECTION_PWA_CACHE_VERSION in $APP_DIR/.env and restart evection-gunicorn"
|
|
||||||
echo " again so installed PWAs drop their old cache instead of serving stale assets."
|
|
||||||
echo " journalctl -u evection-gunicorn -f to watch logs."
|
echo " journalctl -u evection-gunicorn -f to watch logs."
|
||||||
+17
-1
@@ -299,13 +299,29 @@ form p {
|
|||||||
letter-spacing: 0.04em;
|
letter-spacing: 0.04em;
|
||||||
}
|
}
|
||||||
|
|
||||||
|
/* An inner wrapper, not `summary` itself — `summary`'s native disclosure
|
||||||
|
triangle only renders with its default `display: list-item`, so the
|
||||||
|
flex layout for the tag name + unread count lives one level in. */
|
||||||
|
.sidebar-tag-row {
|
||||||
|
display: flex;
|
||||||
|
align-items: center;
|
||||||
|
justify-content: space-between;
|
||||||
|
gap: 0.4rem;
|
||||||
|
}
|
||||||
|
|
||||||
.sidebar-tag-link {
|
.sidebar-tag-link {
|
||||||
|
display: inline-block;
|
||||||
|
padding: 0.15rem 0.4rem;
|
||||||
|
margin: -0.15rem -0.4rem;
|
||||||
|
border-radius: 0.375rem;
|
||||||
color: inherit;
|
color: inherit;
|
||||||
text-decoration: none;
|
text-decoration: none;
|
||||||
}
|
}
|
||||||
|
|
||||||
.sidebar-tag-link.active {
|
.sidebar-tag-link.active {
|
||||||
color: var(--accent);
|
background: var(--bg-row-selected);
|
||||||
|
color: var(--text);
|
||||||
|
font-weight: 600;
|
||||||
}
|
}
|
||||||
|
|
||||||
.sidebar-item-list {
|
.sidebar-item-list {
|
||||||
|
|||||||
@@ -0,0 +1,46 @@
|
|||||||
|
(function () {
|
||||||
|
// Remembers which sidebar <details> sections (one per tag, plus
|
||||||
|
// "Untagged" — see templates/core/_sidebar.html's data-sidebar-key)
|
||||||
|
// the user has collapsed, so a full page navigation (this isn't an
|
||||||
|
// SPA — every click re-renders the sidebar server-side) doesn't keep
|
||||||
|
// snapping them back open. Per-browser via localStorage, same pattern
|
||||||
|
// as theme.js/theme-init.js — not synced across devices/accounts.
|
||||||
|
var STORAGE_KEY = "evection-sidebar-collapsed";
|
||||||
|
|
||||||
|
function readCollapsed() {
|
||||||
|
try {
|
||||||
|
var raw = localStorage.getItem(STORAGE_KEY);
|
||||||
|
return raw ? JSON.parse(raw) : [];
|
||||||
|
} catch (e) {
|
||||||
|
return [];
|
||||||
|
}
|
||||||
|
}
|
||||||
|
|
||||||
|
function writeCollapsed(keys) {
|
||||||
|
try {
|
||||||
|
localStorage.setItem(STORAGE_KEY, JSON.stringify(keys));
|
||||||
|
} catch (e) {
|
||||||
|
/* localStorage unavailable (private mode, etc.) — state just won't persist */
|
||||||
|
}
|
||||||
|
}
|
||||||
|
|
||||||
|
var collapsed = readCollapsed();
|
||||||
|
|
||||||
|
document.querySelectorAll(".sidebar-section[data-sidebar-key]").forEach(function (details) {
|
||||||
|
var key = details.dataset.sidebarKey;
|
||||||
|
if (collapsed.indexOf(key) !== -1) {
|
||||||
|
details.open = false;
|
||||||
|
}
|
||||||
|
|
||||||
|
details.addEventListener("toggle", function () {
|
||||||
|
var current = readCollapsed();
|
||||||
|
var index = current.indexOf(key);
|
||||||
|
if (details.open) {
|
||||||
|
if (index !== -1) current.splice(index, 1);
|
||||||
|
} else if (index === -1) {
|
||||||
|
current.push(key);
|
||||||
|
}
|
||||||
|
writeCollapsed(current);
|
||||||
|
});
|
||||||
|
});
|
||||||
|
})();
|
||||||
+4
-1
@@ -53,7 +53,10 @@
|
|||||||
{% endif %}
|
{% endif %}
|
||||||
|
|
||||||
<script src="{% static 'js/stream.js' %}" defer></script>
|
<script src="{% static 'js/stream.js' %}" defer></script>
|
||||||
{% if user.is_authenticated %}<script src="{% static 'js/theme.js' %}" defer></script>{% endif %}
|
{% if user.is_authenticated %}
|
||||||
|
<script src="{% static 'js/theme.js' %}" defer></script>
|
||||||
|
<script src="{% static 'js/sidebar-state.js' %}" defer></script>
|
||||||
|
{% endif %}
|
||||||
<script src="{% static 'js/register-sw.js' %}" defer></script>
|
<script src="{% static 'js/register-sw.js' %}" defer></script>
|
||||||
</body>
|
</body>
|
||||||
</html>
|
</html>
|
||||||
@@ -31,10 +31,13 @@
|
|||||||
</ul>
|
</ul>
|
||||||
|
|
||||||
{% for entry in sidebar_tag_groups %}
|
{% for entry in sidebar_tag_groups %}
|
||||||
<details class="sidebar-section" open>
|
<details class="sidebar-section" data-sidebar-key="tag-{{ entry.tag.pk }}" open>
|
||||||
<summary>
|
<summary>
|
||||||
|
<span class="sidebar-tag-row">
|
||||||
<a href="{% url 'reader:stream' %}?tag={{ entry.tag.pk }}"
|
<a href="{% url 'reader:stream' %}?tag={{ entry.tag.pk }}"
|
||||||
class="sidebar-tag-link{% if request.GET.tag == entry.tag.pk|stringformat:'s' %} active{% endif %}">{{ entry.tag.name }}</a>
|
class="sidebar-tag-link{% if request.GET.tag == entry.tag.pk|stringformat:'s' %} active{% endif %}">{{ entry.tag.name }}</a>
|
||||||
|
{% if entry.unread_count %}<span class="unread-count">{{ entry.unread_count }}</span>{% endif %}
|
||||||
|
</span>
|
||||||
</summary>
|
</summary>
|
||||||
{% if entry.subscriptions %}
|
{% if entry.subscriptions %}
|
||||||
<ul class="sidebar-item-list">
|
<ul class="sidebar-item-list">
|
||||||
@@ -54,7 +57,7 @@
|
|||||||
{% endfor %}
|
{% endfor %}
|
||||||
|
|
||||||
{% if sidebar_untagged %}
|
{% if sidebar_untagged %}
|
||||||
<details class="sidebar-section" open>
|
<details class="sidebar-section" data-sidebar-key="untagged" open>
|
||||||
<summary>Untagged</summary>
|
<summary>Untagged</summary>
|
||||||
<ul class="sidebar-item-list">
|
<ul class="sidebar-item-list">
|
||||||
{% for subscription in sidebar_untagged %}
|
{% for subscription in sidebar_untagged %}
|
||||||
|
|||||||
+15
-1
@@ -66,8 +66,23 @@ async function cacheFirstForAsset(request) {
|
|||||||
return response;
|
return response;
|
||||||
}
|
}
|
||||||
|
|
||||||
|
const LOGOUT_PATH = "{% url 'accounts:logout' %}";
|
||||||
|
|
||||||
self.addEventListener("fetch", (event) => {
|
self.addEventListener("fetch", (event) => {
|
||||||
const { request } = event;
|
const { request } = event;
|
||||||
|
const url = new URL(request.url);
|
||||||
|
|
||||||
|
// Logging out ends this device's session, so any authenticated HTML
|
||||||
|
// sitting in PAGES_CACHE must not outlive it — otherwise a later
|
||||||
|
// offline navigation (shared device, different account logging in
|
||||||
|
// next) could still serve a previous user's cached article pages.
|
||||||
|
// Purging it synchronously with the logout request itself, rather
|
||||||
|
// than via a postMessage from the page, means there's no race with
|
||||||
|
// the navigation that follows.
|
||||||
|
if (request.method === "POST" && url.pathname === LOGOUT_PATH) {
|
||||||
|
event.respondWith(caches.delete(PAGES_CACHE).then(() => fetch(request)));
|
||||||
|
return;
|
||||||
|
}
|
||||||
|
|
||||||
// Mutations (mark-read, star, OPML upload, forms...) are always
|
// Mutations (mark-read, star, OPML upload, forms...) are always
|
||||||
// network-only — never intercept anything but GET.
|
// network-only — never intercept anything but GET.
|
||||||
@@ -78,7 +93,6 @@ self.addEventListener("fetch", (event) => {
|
|||||||
return;
|
return;
|
||||||
}
|
}
|
||||||
|
|
||||||
const url = new URL(request.url);
|
|
||||||
if (url.pathname.startsWith("/static/")) {
|
if (url.pathname.startsWith("/static/")) {
|
||||||
event.respondWith(cacheFirstForAsset(request));
|
event.respondWith(cacheFirstForAsset(request));
|
||||||
}
|
}
|
||||||
|
|||||||
Reference in new issue
Block a user