Update link/author/summary/published_at on refetch, not just title (T6)

A changed guid's article only ever had its title/content_html/
content_hash refreshed on a subsequent poll — legitimate feed edits to
an entry's link, author, summary, or publication date were silently
ignored forever, which can affect navigation, ordering, and rules that
key off those fields.

content_hash is now computed over every mutable field feedparser gives
us for an entry (title, link, author, summary, content_html,
published_at), and all of them are written together when the hash
changes. Per-user read/star state is untouched either way, same as
before.

Co-Authored-By: Claude Sonnet 5 <noreply@anthropic.com>
This commit is contained in:
ksmithandClaude Sonnet 5 committed 2026-10-31 14:44:15 -06:00
1 parent 0bfe9c8076
commit 17e7f63e61
2 files changed
+69 -8

No files matched your search

+36
View File
@@ -1,3 +1,5 @@
import datetime as dt
import pytest
import requests
import responses
@@ -204,6 +206,40 @@ def test_refetching_updated_content_does_not_reset_user_state():
assert ArticleTag.objects.filter(user=user, article=article, tag=starred_tag).exists()
@pytest.mark.django_db
@responses.activate
def test_refetching_picks_up_link_author_summary_and_published_at_changes():
"""Previously only title/content_html/content_hash were updated on
refetch (T6) — a feed correcting its link, author, summary, or
publication date without touching the title went unnoticed forever."""
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()
article = Article.objects.get(feed=feed)
assert article.link == "https://example.com/1"
assert article.author == ""
edited_xml = GOOD_FEED_XML.replace(
"<link>https://example.com/1</link>",
"<link>https://example.com/1-moved</link>",
).replace(
"<pubDate>Mon, 01 Jan 2024 00:00:00 GMT</pubDate>",
"<pubDate>Tue, 02 Jan 2024 00:00:00 GMT</pubDate>\n <author>jane@example.com</author>",
)
responses.add(responses.GET, FEED_URL, body=edited_xml, status=200)
result = fetch_and_ingest(feed)
feed.save()
assert result.updated_article_ids == [article.pk]
article.refresh_from_db()
assert article.link == "https://example.com/1-moved"
assert article.author == "jane@example.com"
assert article.published_at == dt.datetime(2024, 1, 2, tzinfo=dt.timezone.utc)
def test_sanitize_html_caps_stored_output_length():
huge = "<p>" + ("a" * (MAX_CONTENT_HTML_CHARS + 10_000)) + "</p>"
cleaned = sanitize_html(huge)