thejayman77
1c1ecefde8
Codex's two non-blocking hardening items, folded in before cutover: - _candidate_articles() now excludes paywalled sources IN-QUERY (before LIMIT 50), so flagged stories can't consume candidate slots and leave a full brief thin. Dropped the now-redundant post-fetch filter in build_daily_brief. - Regressions: history retains a viewed paywalled article; sitemap omits a paywalled source AND restores it under override="free". - Aligned test_brief_paywall to the source-level model (paywalled sources carry a paywalled homepage, as in production) — it had relied on article-URL detection. 425 backend tests green. Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
71 lines
3.3 KiB
Python
71 lines
3.3 KiB
Python
import pytest
|
|
from fastapi.testclient import TestClient
|
|
|
|
|
|
@pytest.fixture
|
|
def client(tmp_path, monkeypatch):
|
|
db = tmp_path / "t.sqlite3"
|
|
monkeypatch.setenv("GOODNEWS_DB", str(db))
|
|
monkeypatch.setenv("GOODNEWS_PUBLIC_BASE_URL", "https://upbeatbytes.com")
|
|
import importlib
|
|
import goodnews.api as api
|
|
importlib.reload(api)
|
|
from goodnews.db import connect, init_db
|
|
c = connect(str(db)); init_db(c)
|
|
c.execute("INSERT INTO sources (id,name,feed_url,trust_score) VALUES (1,'BBC','http://s/f',5)")
|
|
c.execute("INSERT INTO articles (id,source_id,canonical_url,title,url_hash,published_at) "
|
|
"VALUES (1,1,'https://bbc.com/x','Bees are back','h1','2026-06-05T08:00:00')")
|
|
c.execute("INSERT INTO article_scores (article_id,accepted,reason_text) VALUES (1,1,'Hopeful.')")
|
|
c.execute("INSERT INTO article_summaries (article_id,summary) VALUES (1,'Bee numbers recovered after a restoration effort.')")
|
|
c.execute("INSERT INTO daily_briefs (id,brief_date,title) VALUES (1,'2026-06-05','B')")
|
|
c.execute("INSERT INTO daily_brief_items (brief_id,article_id,rank) VALUES (1,1,1)")
|
|
c.commit(); c.close()
|
|
return api.create_app()
|
|
|
|
|
|
def test_today_digest(client):
|
|
r = TestClient(client).get("/today")
|
|
assert r.status_code == 200
|
|
html = r.text
|
|
assert "Bees are back" in html
|
|
assert "Bee numbers recovered" in html # our summary
|
|
assert 'href="/a/1"' in html and "bbc.com/x" in html # summary + source links
|
|
assert 'rel="canonical" href="https://upbeatbytes.com/today"' in html
|
|
assert 'property="og:title"' in html
|
|
|
|
|
|
def test_sitemap(client):
|
|
r = TestClient(client).get("/sitemap.xml")
|
|
assert r.status_code == 200
|
|
assert "application/xml" in r.headers["content-type"]
|
|
xml = r.text
|
|
assert "<urlset" in xml
|
|
assert "https://upbeatbytes.com/a/1" in xml
|
|
assert "https://upbeatbytes.com/today" in xml
|
|
assert "<lastmod>2026-06-05</lastmod>" in xml
|
|
|
|
|
|
def test_sitemap_excludes_paywalled_and_restores_on_free(tmp_path, monkeypatch):
|
|
db = tmp_path / "sm.sqlite3"
|
|
monkeypatch.setenv("GOODNEWS_DB", str(db))
|
|
monkeypatch.setenv("GOODNEWS_PUBLIC_BASE_URL", "https://upbeatbytes.com")
|
|
import importlib
|
|
import goodnews.api as api
|
|
importlib.reload(api)
|
|
from goodnews.db import connect, init_db
|
|
c = connect(str(db)); init_db(c)
|
|
c.execute("INSERT INTO sources (id,name,feed_url,trust_score,content_visible) VALUES (1,'Free','http://f',5,1)")
|
|
c.execute("INSERT INTO sources (id,name,feed_url,trust_score,content_visible,paywall_override) "
|
|
"VALUES (2,'Pay','http://p',5,1,'paywalled')")
|
|
for aid, sid in [(1, 1), (2, 2)]:
|
|
c.execute("INSERT INTO articles (id,source_id,canonical_url,title,url_hash,published_at) VALUES (?,?,?,?,?,?)",
|
|
(aid, sid, f"http://x/{aid}", f"t{aid}", f"h{aid}", "2026-06-05T08:00:00"))
|
|
c.execute("INSERT INTO article_scores (article_id,accepted) VALUES (?,1)", (aid,))
|
|
c.commit()
|
|
tc = TestClient(api.create_app())
|
|
xml = tc.get("/sitemap.xml").text
|
|
assert "/a/1</loc>" in xml and "/a/2</loc>" not in xml # paywalled source omitted
|
|
c.execute("UPDATE sources SET paywall_override='free' WHERE id=2"); c.commit()
|
|
assert "/a/2</loc>" in tc.get("/sitemap.xml").text # restored under 'free'
|
|
c.close()
|