feat: implement scoped dataset catalog and template input drafts

This commit is contained in:
yuxuanhui
2026-09-08 09:22:53 +08:00
parent 404a4d8a04
commit 01d169d118
30 changed files with 3024 additions and 37 deletions
+124
View File
@@ -0,0 +1,124 @@
"""One-off acceptance against the dedicated local PostgreSQL catalog_test database."""
import asyncio
import os
import re
from alembic import command
from alembic.config import Config
from cryptography.fernet import Fernet
from sqlalchemy import text
from sqlalchemy.ext.asyncio import create_async_engine
database_name = os.environ.get("WQ_CATALOG_ACCEPTANCE_DATABASE", "catalog_flow_test")
if not re.fullmatch(r"catalog_[a-z0-9_]{1,40}", database_name):
raise ValueError("Acceptance requires a dedicated catalog_* database")
URL = f"postgresql+asyncpg://postgres:catalog-test-only@127.0.0.1:18436/{database_name}"
os.environ.update(
DATABASE_URL=URL, ADMIN_PASSWORD="migration-test-only", ENCRYPTION_KEY=Fernet.generate_key().decode()
)
async def sql(statement):
engine = create_async_engine(URL)
async with engine.begin() as connection:
result = await connection.execute(text(statement))
value = result.fetchall() if result.returns_rows else None
await engine.dispose()
return value
if __name__ == "__main__":
config = Config("alembic.ini")
if asyncio.run(sql("SELECT tablename FROM pg_tables WHERE schemaname='public'")):
raise RuntimeError("Acceptance database must be empty; existing data will not be overwritten")
command.upgrade(config, "0002")
asyncio.run(
sql(
"INSERT INTO alphas (id, hidden, settings, is_metrics, os_metrics, checks, synced_at, raw) VALUES ('MIGRATION_TEST', false, '{}', '{}', '{}', '[]', now(), '{}');"
)
)
asyncio.run(
sql(
"INSERT INTO research (alpha_id, note, tags, favorite, state, updated_at, version) VALUES ('MIGRATION_TEST', 'preserve research', '[]', false, 'inbox', now(), 7);"
)
)
command.upgrade(config, "head")
command.check(config)
assert asyncio.run(sql("SELECT note, version FROM research WHERE alpha_id='MIGRATION_TEST'")) == [
("preserve research", 7)
]
assert asyncio.run(sql("SELECT count(*) FROM catalog_batches")) == [(0,)]
command.downgrade(config, "0002")
command.upgrade(config, "head")
command.check(config)
assert asyncio.run(sql("SELECT note, version FROM research WHERE alpha_id='MIGRATION_TEST'")) == [
("preserve research", 7)
]
print(
"PostgreSQL 17: 0002 → 0003, downgrade/re-upgrade, metadata check, Alpha/research preservation passed"
)
async def flow():
import httpx
from app.config import Settings
from app.main import create_app
from app.worldquant import WqClient
from tests.catalog_fake import catalog_response
from tests.test_catalog import SCOPE, prepare, search, sync
def upstream(request):
if request.url.path == "/authentication":
return httpx.Response(201, json={"token": {"expiry": 14400}})
if request.url.path == "/users/self":
return httpx.Response(200, json={"id": "PG_TEST_USER"})
assert request.method == "GET"
return catalog_response(request) or httpx.Response(404)
settings = Settings(_env_file=None, enable_runner=False, public_origin="http://testserver")
app = create_app(settings, WqClient(settings, transport=httpx.MockTransport(upstream)))
async with app.router.lifespan_context(app):
async with httpx.AsyncClient(
transport=httpx.ASGITransport(app=app),
base_url="http://testserver",
headers={"X-WQ-Request": "1"},
) as client:
assert (
await client.post(
"/api/v1/auth/login", json={"username": "admin", "password": "migration-test-only"}
)
).status_code == 200
await client.put(
"/api/v1/account/credentials",
json={"email": "pg@example.com", "password": "synthetic-only"},
)
job = (await client.post("/api/v1/account/connect")).json()
await app.state.runner.execute(job["id"])
catalog = (client, app.state.runner, {})
assert (await sync(catalog))["status"] == "completed"
version = (await sync(catalog, "TEST_FIN"))["id"]
result = await search(client, "/datasets/TEST_FIN/fields")
assert result["complete_count"] == 123
draft = (await prepare(client, version)).json()
assert len(draft["field_ids"]) == 123
responses = await asyncio.gather(
*[
client.patch(
"/api/v1/catalog/datasets/TEST_FIN/research",
params=SCOPE,
json={"version": 1, "note": value},
)
for value in ["one", "two"]
]
)
assert sorted(r.status_code for r in responses) == [200, 409]
await sync(catalog, "TEST_FIN")
assert (await prepare(client, version)).status_code == 409
persisted = (await client.get("/api/v1/catalog/inputs/" + draft["id"])).json()
assert persisted == draft
print(
"PostgreSQL: real API/runner multi-page dedupe, immutable draft, refresh conflict and concurrent note CAS passed"
)
asyncio.run(flow())