Files
Evection/apps/feeds/test_fetcher.py
T
ksmithandClaude Sonnet 5 9241a54958 Cap entries per poll and stored content size (T4)
ssrf_guard.MAX_RESPONSE_BYTES (S1) already bounds the raw download, but
a feed within that byte cap can still carry an unreasonable number of
entries, or one entry with an unreasonably large body — both cost real
CPU/DB time (nh3 sanitization, an Article row/UPDATE) per entry.
fetch_and_ingest now processes at most MAX_ENTRIES_PER_POLL (200)
entries per poll (logging a warning when truncated) and sanitize_html
bounds both its input (sanitizer cost) and output (what's actually
stored/rendered) length.

Co-Authored-By: Claude Sonnet 5 <noreply@anthropic.com>
2026-10-31 12:46:40 -06:00

231 lines
6.8 KiB
Python

import pytest
import requests
import responses
from django.utils import timezone
from apps.articles.models import Article, UserArticleState
from apps.feeds.models import Feed
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"
GOOD_FEED_XML = """<?xml version="1.0"?>
<rss version="2.0"><channel>
<title>Example Blog</title>
<link>https://example.com</link>
<item>
<title>First post</title>
<link>https://example.com/1</link>
<guid>https://example.com/1</guid>
<pubDate>Mon, 01 Jan 2024 00:00:00 GMT</pubDate>
<description>&lt;p&gt;Hello &lt;script&gt;alert(1)&lt;/script&gt;world&lt;/p&gt;</description>
</item>
</channel></rss>
"""
NO_GUID_FEED_XML = """<?xml version="1.0"?>
<rss version="2.0"><channel>
<title>No Guid Blog</title>
<item>
<title>Only a link</title>
<link>https://example.com/only-link</link>
<pubDate>Mon, 01 Jan 2024 00:00:00 GMT</pubDate>
<description>Body</description>
</item>
</channel></rss>
"""
MALFORMED_BUT_SALVAGEABLE_XML = """<?xml version="1.0"?>
<rss version="2.0"><channel>
<title>Slightly Broken</title>
<item>
<title>Unescaped & ampersand but still has entries</title>
<guid>guid-1</guid>
</item>
</channel></rss>
"""
TOTAL_GARBAGE = "this is not xml at all {{{"
@pytest.fixture
def feed(db):
return Feed.objects.create(feed_url=FEED_URL)
@pytest.mark.django_db
@responses.activate
def test_fetch_ingests_new_articles_and_sanitizes_html(feed):
responses.add(
responses.GET,
FEED_URL,
body=GOOD_FEED_XML,
status=200,
headers={"ETag": '"abc123"', "Last-Modified": "Mon, 01 Jan 2024 00:00:00 GMT"},
)
result = fetch_and_ingest(feed)
feed.save()
assert result.status == Feed.STATUS_OK
assert len(result.new_article_ids) == 1
assert feed.title == "Example Blog"
assert feed.etag == '"abc123"'
assert feed.last_modified == "Mon, 01 Jan 2024 00:00:00 GMT"
article = Article.objects.get(feed=feed, guid="https://example.com/1")
assert "<script>" not in article.content_html
assert "world" in article.content_html
@pytest.mark.django_db
@responses.activate
def test_second_poll_with_304_does_not_duplicate_or_error(feed):
responses.add(responses.GET, FEED_URL, body=GOOD_FEED_XML, status=200)
fetch_and_ingest(feed)
feed.save()
assert Article.objects.filter(feed=feed).count() == 1
responses.add(responses.GET, FEED_URL, status=304)
result = fetch_and_ingest(feed)
feed.save()
assert result.status == Feed.STATUS_NOT_MODIFIED
assert Article.objects.filter(feed=feed).count() == 1
assert feed.fetch_error_count == 0
@pytest.mark.django_db
@responses.activate
def test_entry_without_guid_falls_back_to_link(feed):
responses.add(responses.GET, FEED_URL, body=NO_GUID_FEED_XML, status=200)
result = fetch_and_ingest(feed)
feed.save()
assert len(result.new_article_ids) == 1
article = Article.objects.get(pk=result.new_article_ids[0])
assert article.guid == "https://example.com/only-link"
@pytest.mark.django_db
@responses.activate
def test_bozo_feed_with_entries_still_ingests(feed):
responses.add(responses.GET, FEED_URL, body=MALFORMED_BUT_SALVAGEABLE_XML, status=200)
result = fetch_and_ingest(feed)
feed.save()
assert result.status == Feed.STATUS_OK
assert len(result.new_article_ids) == 1
@pytest.mark.django_db
@responses.activate
def test_unparseable_feed_records_error_and_backs_off(feed):
responses.add(responses.GET, FEED_URL, body=TOTAL_GARBAGE, status=200)
result = fetch_and_ingest(feed)
feed.save()
assert result.status == Feed.STATUS_ERROR
assert feed.fetch_error_count == 1
assert effective_interval_minutes(feed) > feed.fetch_interval_minutes
@pytest.mark.django_db
@responses.activate
def test_http_500_records_error(feed):
responses.add(responses.GET, FEED_URL, status=500)
result = fetch_and_ingest(feed)
feed.save()
assert result.status == Feed.STATUS_ERROR
assert feed.last_fetch_status == Feed.STATUS_ERROR
assert feed.fetch_error_count == 1
@pytest.mark.django_db
@responses.activate
def test_connection_error_still_updates_last_fetched_at(feed):
responses.add(
responses.GET,
FEED_URL,
body=requests.exceptions.ConnectionError("boom"),
)
before = timezone.now()
result = fetch_and_ingest(feed)
feed.save()
assert result.status == Feed.STATUS_ERROR
assert feed.last_fetched_at is not None
assert feed.last_fetched_at >= before
@pytest.mark.django_db
@responses.activate
def test_refetching_updated_content_does_not_reset_user_state():
from django.contrib.auth import get_user_model
User = get_user_model()
user = User.objects.create_user("alice", password="pw-alice-123")
feed = Feed.objects.create(feed_url=FEED_URL)
responses.add(responses.GET, FEED_URL, body=GOOD_FEED_XML, status=200)
fetch_and_ingest(feed)
feed.save()
from apps.articles.models import STARRED_TAG_NAME, ArticleTag, get_system_tag
article = Article.objects.get(feed=feed)
state = UserArticleState.objects.create(user=user, article=article, is_read=True)
starred_tag = get_system_tag(user, STARRED_TAG_NAME)
ArticleTag.objects.create(user=user, article=article, tag=starred_tag)
updated_xml = GOOD_FEED_XML.replace("First post", "First post (edited)")
responses.add(responses.GET, FEED_URL, body=updated_xml, status=200)
result = fetch_and_ingest(feed)
feed.save()
assert result.updated_article_ids == [article.pk]
article.refresh_from_db()
assert article.title == "First post (edited)"
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()