77 lines
2.4 KiB
Python
77 lines
2.4 KiB
Python
|
"""Phase 3 crawl job API tests."""
|
||
|
|
|
||
|
|
from __future__ import annotations
|
||
|
|
|
||
|
|
import importlib
|
||
|
|
from collections.abc import Generator
|
||
|
|
from contextlib import asynccontextmanager
|
||
|
|
|
||
|
|
from fastapi.testclient import TestClient
|
||
|
|
from ont_platform.api import db_deps
|
||
|
|
from ont_platform.storage.models import Base
|
||
|
|
from sqlalchemy import create_engine
|
||
|
|
from sqlalchemy.orm import Session, sessionmaker
|
||
|
|
from sqlalchemy.pool import StaticPool
|
||
|
|
|
||
|
|
main_module = importlib.import_module("ont_platform.api.main")
|
||
|
|
|
||
|
|
|
||
|
|
@asynccontextmanager
|
||
|
|
async def _noop_lifespan(app):
|
||
|
|
yield
|
||
|
|
|
||
|
|
|
||
|
|
def _phase3_client(monkeypatch) -> TestClient:
|
||
|
|
monkeypatch.setenv("PHASE", "3")
|
||
|
|
engine = create_engine(
|
||
|
|
"sqlite://",
|
||
|
|
connect_args={"check_same_thread": False},
|
||
|
|
poolclass=StaticPool,
|
||
|
|
)
|
||
|
|
Base.metadata.create_all(engine)
|
||
|
|
session_factory = sessionmaker(bind=engine)
|
||
|
|
|
||
|
|
def override_get_db() -> Generator[Session, None, None]:
|
||
|
|
db = session_factory()
|
||
|
|
try:
|
||
|
|
yield db
|
||
|
|
finally:
|
||
|
|
db.close()
|
||
|
|
|
||
|
|
app = main_module.create_app()
|
||
|
|
app.router.lifespan_context = _noop_lifespan
|
||
|
|
app.dependency_overrides[db_deps.get_db] = override_get_db
|
||
|
|
return TestClient(app, raise_server_exceptions=True, backend="asyncio")
|
||
|
|
|
||
|
|
|
||
|
|
def test_phase3_crawl_job_accepts_inline_html_and_persists_progress(monkeypatch) -> None:
|
||
|
|
html = """
|
||
|
|
<html lang="en">
|
||
|
|
<head><title>Ontology Job</title></head>
|
||
|
|
<body><article><h1>Ontology Job</h1><p>Alice works at Acme in Berlin.</p></article></body>
|
||
|
|
</html>
|
||
|
|
"""
|
||
|
|
|
||
|
|
with _phase3_client(monkeypatch) as client:
|
||
|
|
response = client.post(
|
||
|
|
"/api/v1/crawl/jobs",
|
||
|
|
json={
|
||
|
|
"project_id": "proj_crawl",
|
||
|
|
"url": "https://example.test/job",
|
||
|
|
"html": html,
|
||
|
|
"profile": "dynamic_page",
|
||
|
|
},
|
||
|
|
)
|
||
|
|
body = response.json()
|
||
|
|
job_id = body["job"]["id"]
|
||
|
|
status = client.get(f"/api/v1/crawl/jobs/{job_id}")
|
||
|
|
|
||
|
|
assert response.status_code == 200, response.text
|
||
|
|
assert body["job"]["status"] == "completed"
|
||
|
|
assert body["job"]["document_id"].startswith("doc_")
|
||
|
|
assert body["job"]["entity_count"] >= 1
|
||
|
|
assert body["job"]["metadata"]["progress"]["profile"] == "dynamic_page"
|
||
|
|
assert body["job"]["metadata"]["progress"]["pages_completed"] == 1
|
||
|
|
assert status.status_code == 200
|
||
|
|
assert status.json()["job"]["id"] == job_id
|