Public Access
adminandClaude Opus 4.7
8e89f793d5
R1 stabilization: pytest harness with transactional db fixture, smoke + alembic + auth + scrape + approval + swiftly tests, github actions ci yaml. Bearer-token admin auth + signed-cookie session for family ui mutations. Async POST /api/admin/scrape (BackgroundTasks, returns 202). Path canonicalization (no /list, /planned suffixes). DATABASE_URL fail-fast on empty. R2 deferred-risk spikes: live lucky california fetch (R2-A), full email+per-voter approval click round trip with single-use enforcement (R2-B, console email backend, sendgrid stub). R3-0 phase 3 redesign: replaced playwright html scraper with requests based swiftly json api client. 17 categories, ~10k products per scrape, upsert by (source, external_id). 401 surfaces actionable token-refresh message via ScrapeLog.error_message. Pre-existing defects fixed: shopping_list.py syntax error blocking app import, MealPlan.votes orphan relationship, JSONB(astext=True) invalid kwarg, missing requests dep, calorie_target schema drift, every SQLEnum needed values_callable, 0001 had empty downgrade(), seed had duplicate ingredient rows. Migrations added: 0003 grocery_item.description, 0004 family_profile. calorie_target, 0005 grocery_item.external_id + source + composite index. Verified: 31/31 pytest green, alembic upgrade->downgrade->upgrade clean, frontend npm run build clean, live scrape 9,960 grocery_item rows in 36s. Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
69 lines
2.2 KiB
Python
69 lines
2.2 KiB
Python
"""Async scrape endpoint contract.
|
|
|
|
Verifies that ``POST /api/admin/scrape``:
|
|
- returns 202 + ``scrape_log_id`` synchronously,
|
|
- persists a ``ScrapeLog`` row in status STARTED before the background task
|
|
runs (the task is monkey-patched out so it never reaches Playwright and
|
|
never opens a session outside the test transaction).
|
|
"""
|
|
from __future__ import annotations
|
|
|
|
import os
|
|
import uuid
|
|
|
|
import pytest
|
|
|
|
os.environ.setdefault("ADMIN_TOKEN", "test-admin-token")
|
|
|
|
|
|
@pytest.fixture(autouse=True)
|
|
def _admin_token(monkeypatch):
|
|
monkeypatch.setenv("ADMIN_TOKEN", "test-admin-token")
|
|
yield
|
|
|
|
|
|
@pytest.mark.requires_postgres
|
|
def test_scrape_returns_202_and_log_id(client, db, monkeypatch):
|
|
"""Endpoint enqueues the scrape and returns 202 + scrape_log_id.
|
|
|
|
We replace the background runner with a no-op so the test does NOT spin up
|
|
Playwright and does NOT open a session outside the rolled-back test
|
|
transaction.
|
|
"""
|
|
calls: list[tuple] = []
|
|
|
|
def _fake_run(log_id, source, scrape_type):
|
|
calls.append((log_id, source, scrape_type))
|
|
|
|
# Patch in BOTH the service module (definition site) and the api module
|
|
# (import site) so whichever symbol the route resolved to is replaced.
|
|
monkeypatch.setattr(
|
|
"app.services.scraper_service._run_scrape_in_background", _fake_run
|
|
)
|
|
|
|
r = client.post(
|
|
"/api/admin/scrape",
|
|
headers={"Authorization": "Bearer test-admin-token"},
|
|
)
|
|
assert r.status_code == 202, r.text
|
|
body = r.json()
|
|
assert body["status"] == "queued"
|
|
assert "scrape_log_id" in body
|
|
|
|
log_id = uuid.UUID(body["scrape_log_id"])
|
|
|
|
# Row was committed inside enqueue_scrape — visible on the test session.
|
|
from app.models import ScrapeLog, ScrapeStatus
|
|
|
|
log = db.query(ScrapeLog).filter(ScrapeLog.id == log_id).first()
|
|
assert log is not None, "ScrapeLog row should exist after enqueue"
|
|
assert log.status == ScrapeStatus.STARTED
|
|
assert log.source == "lucky_california"
|
|
assert log.scrape_type == "weekly_ad"
|
|
assert log.completed_at is None
|
|
|
|
# TestClient runs background tasks before returning from the context
|
|
# manager exit — by the time we get here, the fake runner ran exactly once.
|
|
assert len(calls) == 1
|
|
assert calls[0][0] == log_id
|