Private
Public Access
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>
This commit is contained in:
1 parent
64f25789f5
commit
9241a54958
1 file changed
+33
-1
@@ -5,7 +5,13 @@ from django.utils import timezone
|
|||||||
|
|
||||||
from apps.articles.models import Article, UserArticleState
|
from apps.articles.models import Article, UserArticleState
|
||||||
from apps.feeds.models import Feed
|
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"
|
FEED_URL = "https://example.com/feed.xml"
|
||||||
|
|
||||||
@@ -196,3 +202,29 @@ def test_refetching_updated_content_does_not_reset_user_state():
|
|||||||
state.refresh_from_db()
|
state.refresh_from_db()
|
||||||
assert state.is_read is True
|
assert state.is_read is True
|
||||||
assert ArticleTag.objects.filter(user=user, article=article, tag=starred_tag).exists()
|
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()
|
||||||
Reference in new issue
Block a user