thejayman77
db967bb7fa
Hardening before it runs further on the cycle: - DB-lock/network: all HTTP (metadata + image) happens before any write; the write txn opens only at the brief INSERT and commits immediately. Images download to a temp file then atomic os.replace into cache (a reader never sees a half-written file). - Site-timezone "daily" already used local_today() (same rhythm as the Brief) — confirmed. - Attribution from day one: store + return title/artist/date/medium/department/credit/ source_url/object_id/source + museum name + is_public_domain license marker + the full- res source URL (for a richer /art view later). UI can show: Title · Artist · The Met. - "highlight != always beautiful": added a manual `blocked` flag on art_pool (excluded from picks) as the cheap curation lever; a featured override can follow. Schema migrated (existing art tables get the new columns). 373 tests green. Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
86 lines
3.6 KiB
Python
86 lines
3.6 KiB
Python
"""Daily Art: curated harvest, bulletproof daily pick (skips non-public-domain / bad
|
|
images, falls through candidates), local image cache, and never-empty get_today."""
|
|
import pytest
|
|
|
|
from goodnews import art
|
|
from goodnews.db import connect, init_db
|
|
|
|
OBJECTS = {
|
|
1: {"objectID": 1, "isPublicDomain": True, "title": "Sunflowers", "artistDisplayName": "Van Gogh",
|
|
"objectDate": "1887", "medium": "Oil on canvas", "department": "European Paintings",
|
|
"creditLine": "Gift", "objectURL": "https://met/1",
|
|
"primaryImageSmall": "https://img/1-web.jpg", "primaryImage": "https://img/1.jpg"},
|
|
2: {"objectID": 2, "isPublicDomain": False, "primaryImageSmall": "https://img/2.jpg"}, # not CC0 -> skip
|
|
3: {"objectID": 3, "isPublicDomain": True, "title": "Irises", "artistDisplayName": "Van Gogh",
|
|
"primaryImageSmall": "https://img/3-web.jpg"},
|
|
}
|
|
|
|
|
|
def _fake_json(url, timeout=20):
|
|
if "/search" in url:
|
|
return {"total": 3, "objectIDs": [1, 2, 3]}
|
|
if "/objects/" in url:
|
|
return OBJECTS[int(url.rstrip("/").split("/")[-1])]
|
|
raise AssertionError(url)
|
|
|
|
|
|
def _fake_bytes(url, timeout=30):
|
|
return (b"\xff\xd8\xff" + b"x" * 5000, "image/jpeg") # a valid-looking jpeg
|
|
|
|
|
|
@pytest.fixture
|
|
def conn(tmp_path, monkeypatch):
|
|
monkeypatch.setenv("GOODNEWS_ART_CACHE", str(tmp_path / "art"))
|
|
monkeypatch.setattr(art, "_http_json", _fake_json)
|
|
monkeypatch.setattr(art, "_http_bytes", _fake_bytes)
|
|
c = connect(":memory:"); init_db(c)
|
|
yield c
|
|
c.close()
|
|
|
|
|
|
def test_harvest_dedupes_into_pool(conn):
|
|
r = art.harvest_pool(conn)
|
|
assert r["pool"] == 3 and r["added"] == 3
|
|
assert art.harvest_pool(conn)["added"] == 0 # idempotent
|
|
|
|
|
|
def test_pick_caches_image_metadata_and_marks_shown(conn):
|
|
art.harvest_pool(conn)
|
|
a = art.pick_daily(conn, art_date="2026-06-21")
|
|
assert a and a["object_id"] in (1, 3) and a["title"] in ("Sunflowers", "Irises")
|
|
assert a["artist"] == "Van Gogh" and a["image_file"]
|
|
assert a["is_public_domain"] == 1 # license marker stored
|
|
assert list(art.cache_dir().glob(f"{a['object_id']}.*")) # image cached locally
|
|
assert not list(art.cache_dir().glob("*.tmp")) # atomic write left no temp file
|
|
|
|
|
|
def test_blocked_pieces_are_never_picked(conn):
|
|
art.harvest_pool(conn)
|
|
conn.execute("UPDATE art_pool SET blocked=1 WHERE object_id=1") # block the good one
|
|
conn.commit()
|
|
a = art.pick_daily(conn, art_date="2026-06-21")
|
|
assert a is None or a["object_id"] != 1 # never the blocked piece
|
|
shown = conn.execute("SELECT shown_at FROM art_pool WHERE object_id=?", (a["object_id"],)).fetchone()[0]
|
|
assert shown == "2026-06-21"
|
|
|
|
|
|
def test_pick_skips_non_public_domain(conn):
|
|
conn.execute("INSERT INTO art_pool (source, object_id) VALUES ('met', 2)") # only the non-CC0 one
|
|
conn.commit()
|
|
assert art.pick_daily(conn, art_date="2026-06-21") is None # nothing fetched, not an error
|
|
|
|
|
|
def test_pick_is_idempotent_and_get_today_never_empty(conn):
|
|
art.harvest_pool(conn)
|
|
a1 = art.pick_daily(conn, art_date="2026-06-21")
|
|
a2 = art.pick_daily(conn, art_date="2026-06-21") # same day -> unchanged
|
|
assert a1["object_id"] == a2["object_id"]
|
|
assert art.get_today(conn, "2026-06-21")["object_id"] == a1["object_id"]
|
|
# an unknown date falls back to the most recent cached piece (room never empty)
|
|
assert art.get_today(conn, "2099-01-01")["object_id"] == a1["object_id"]
|
|
|
|
|
|
def test_run_daily_bootstraps_pool_then_picks(conn):
|
|
r = art.run_daily(conn)
|
|
assert r["pool"] == 3 and r["picked_object"] in (1, 3)
|