Rain-Bus/daily-paper
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

refactor: split monolithic phase tests into per-module test files

Browse Source 
- rename test_admin_phase4.py -> test_admin.py, test_search.py -> test_searcher.py
- split test_phase5.py into test_cleaner, test_embedder, test_image_extractor, test_pages
- move schema tests from test_summarizer.py into dedicated test_schemas.py
- add sample_papers_range and sample_papers_with_summary fixtures in conftest
- update .gitignore to exclude all of data/
This commit is contained in:
Rain&Bus
2026-06-06 00:34:30 +08:00
parent 85c4cfb9e8
commit f7f1a4c0cb
11 changed files with 1245 additions and 1249 deletions
Download Patch File Download Diff File Expand all files Collapse all files
tests/test_admin.py
+390
View File
@@ -0,0 +1,390 @@
"""管理接口测试 — admin routes、auth、scheduler、task locks。"""
from __future__ import annotations
import logging
from datetime import date, datetime, timezone
from unittest.mock import AsyncMock, patch
import pytest
from sqlalchemy import select
from app.config import settings
from app.models import (
CrawlLog,
TaskLock,
)
# ── Fixtures ────────────────────────────────────────────────────────────
ADMIN_TOKEN = "test-admin-token-12345"
@pytest.fixture
def auth_client(client, monkeypatch):
"""带 admin token monkeypatch 的 TestClient。"""
monkeypatch.setattr(settings, "ADMIN_TOKEN", ADMIN_TOKEN)
monkeypatch.setattr(settings, "CHROMA_ENABLED", False)
return client
# ═══════════════════════════════════════════════════════════════════════
# Admin Routes — 鉴权测试
# ═══════════════════════════════════════════════════════════════════════
class TestAdminAuth:
"""管理接口鉴权测试。"""
def test_no_token_returns_403(self, auth_client):
"""无 token 时请求管理接口应返回 403。"""
resp = auth_client.post("/admin/crawl")
assert resp.status_code in (403, 401)
def test_wrong_token_returns_401(self, auth_client, wrong_admin_headers):
"""错误 token 应返回 401。"""
resp = auth_client.post("/admin/crawl", headers=wrong_admin_headers)
assert resp.status_code == 401
def test_correct_token_accepted(self, auth_client, admin_headers):
"""正确 token 应被接受（crawl 可能会失败但不是 401）。"""
with patch("app.routes.admin.crawl_daily", new_callable=AsyncMock) as mock_crawl:
mock_crawl.return_value = {"found": 0, "new": 0, "status": "success"}
resp = auth_client.post("/admin/crawl", headers=admin_headers)
assert resp.status_code != 401
# ── summarize route auth ────────────────────────────────────────
def test_no_token_returns_401_for_summarize(self, client):
"""无 Bearer token 返回 401。"""
resp = client.post("/admin/summarize")
assert resp.status_code in (401, 403)
def test_wrong_token_returns_401_for_summarize(self, client):
resp = client.post(
"/admin/summarize",
headers={"Authorization": "Bearer wrong-token"},
)
assert resp.status_code == 401
def test_correct_token_batch_summarize(self, client, admin_headers):
"""正确 token 调用 batch summarize，mock 掉服务层。"""
import app.config as config_mod
original = config_mod.settings.ADMIN_TOKEN
config_mod.settings.ADMIN_TOKEN = ADMIN_TOKEN
try:
with patch("app.routes.admin.summarize_batch", new_callable=AsyncMock) as mock:
mock.return_value = {"status": "success", "done": 0, "failed": 0, "total": 0}
resp = client.post("/admin/summarize", headers=admin_headers)
assert resp.status_code == 200
assert resp.json()["status"] == "success"
finally:
config_mod.settings.ADMIN_TOKEN = original
def test_single_paper_not_found(self, client, admin_headers):
"""单篇总结不存在的论文返回 404。"""
import app.config as config_mod
original = config_mod.settings.ADMIN_TOKEN
config_mod.settings.ADMIN_TOKEN = ADMIN_TOKEN
try:
with patch(
"app.routes.admin.summarize_single",
new_callable=AsyncMock,
return_value={"status": "not_found", "arxiv_id": "nonexistent.99999"},
):
resp = client.post(
"/admin/summarize/nonexistent.99999",
headers=admin_headers,
)
assert resp.status_code == 404
finally:
config_mod.settings.ADMIN_TOKEN = original
# ═══════════════════════════════════════════════════════════════════════
# Admin Routes — Crawl
# ═══════════════════════════════════════════════════════════════════════
class TestAdminCrawl:
"""POST /admin/crawl 测试。"""
def test_crawl_default_today(self, auth_client, admin_headers):
"""不指定日期时默认抓取今天。"""
with patch("app.routes.admin.crawl_daily", new_callable=AsyncMock) as mock_crawl:
mock_crawl.return_value = {"found": 5, "new": 3, "status": "success"}
resp = auth_client.post("/admin/crawl", headers=admin_headers)
assert resp.status_code == 200
data = resp.json()
assert data["status"] == "success"
mock_crawl.assert_called_once()
def test_crawl_specific_date(self, auth_client, admin_headers):
"""指定日期抓取。"""
with patch("app.routes.admin.crawl_daily", new_callable=AsyncMock) as mock_crawl:
mock_crawl.return_value = {"found": 2, "new": 1, "status": "success"}
resp = auth_client.post("/admin/crawl?date=2024-01-15", headers=admin_headers)
assert resp.status_code == 200
mock_crawl.assert_called_once()
call_args = mock_crawl.call_args
assert call_args[0][1] == "2024-01-15"
# ═══════════════════════════════════════════════════════════════════════
# Admin Routes — Cleanup
# ═══════════════════════════════════════════════════════════════════════
class TestAdminCleanup:
"""POST /admin/cleanup 测试。"""
def test_cleanup_returns_stats(self, auth_client, admin_headers):
"""清理应返回统计信息。"""
with patch("app.routes.admin.cleanup_tmp") as mock_cleanup:
mock_cleanup.return_value = {"scanned": 3, "removed": 1, "errors": []}
resp = auth_client.post("/admin/cleanup", headers=admin_headers)
assert resp.status_code == 200
data = resp.json()
assert data["scanned"] == 3
assert data["removed"] == 1
def test_cleanup_writes_log(self, auth_client, admin_headers, db_session):
"""清理应写入 crawl_logs。"""
with patch("app.routes.admin.cleanup_tmp") as mock_cleanup:
mock_cleanup.return_value = {"scanned": 0, "removed": 0, "errors": []}
auth_client.post("/admin/cleanup", headers=admin_headers)
logs = db_session.execute(
select(CrawlLog).where(CrawlLog.task == "cleanup")
).scalars().all()
assert len(logs) >= 1
assert logs[-1].status == "success"
# ═══════════════════════════════════════════════════════════════════════
# Admin Routes — Delete
# ═══════════════════════════════════════════════════════════════════════
class TestAdminDelete:
"""POST /admin/delete 测试。"""
def test_delete_requires_confirm(self, auth_client, admin_headers):
"""confirm 不是 'DELETE' 时应返回 422。"""
resp = auth_client.post(
"/admin/delete",
json={
"date_start": "2024-01-10",
"date_end": "2024-01-12",
"include_notes": True,
"confirm": "WRONG",
},
headers=admin_headers,
)
assert resp.status_code == 422
def test_delete_with_confirm(self, auth_client, admin_headers, db_session, sample_papers_range):
"""confirm='DELETE' 时应执行删除。"""
resp = auth_client.post(
"/admin/delete",
json={
"date_start": "2024-01-10",
"date_end": "2024-01-12",
"include_notes": True,
"confirm": "DELETE",
},
headers=admin_headers,
)
assert resp.status_code == 200
data = resp.json()
assert data["deleted"] == 3
def test_delete_invalid_date_range(self, auth_client, admin_headers):
"""date_start > date_end 应返回 400。"""
resp = auth_client.post(
"/admin/delete",
json={
"date_start": "2024-01-15",
"date_end": "2024-01-10",
"confirm": "DELETE",
},
headers=admin_headers,
)
assert resp.status_code == 400
def test_delete_without_confirm_field(self, auth_client, admin_headers):
"""缺少 confirm 字段应返回 422。"""
resp = auth_client.post(
"/admin/delete",
json={
"date_start": "2024-01-10",
"date_end": "2024-01-12",
},
headers=admin_headers,
)
assert resp.status_code == 422
# ═══════════════════════════════════════════════════════════════════════
# Admin Routes — Logs
# ═══════════════════════════════════════════════════════════════════════
class TestAdminLogs:
"""GET /admin/logs 测试。"""
def test_logs_returns_page(self, auth_client, admin_headers):
"""应返回管理日志页面。"""
resp = auth_client.get("/admin/logs", headers=admin_headers)
assert resp.status_code == 200
assert "text/html" in resp.headers.get("content-type", "")
def test_logs_requires_auth(self, auth_client):
"""日志页面需要鉴权。"""
resp = auth_client.get("/admin/logs")
assert resp.status_code in (403, 401)
def test_logs_contains_data(self, auth_client, admin_headers, db_session, sample_papers_range):
"""日志页面应包含日志数据。"""
# 先创建一条日志
now = datetime.now(timezone.utc)
db_session.add(CrawlLog(
task="crawl", status="success", started_at=now, completed_at=now,
))
db_session.commit()
resp = auth_client.get("/admin/logs", headers=admin_headers)
assert resp.status_code == 200
assert "crawl" in resp.text.lower() or "日志" in resp.text
# ═══════════════════════════════════════════════════════════════════════
# Scheduler 测试
# ═══════════════════════════════════════════════════════════════════════
class TestScheduler:
"""app/services/scheduler.py 测试。"""
def test_scheduler_disabled_by_default(self, monkeypatch):
"""SCHEDULER_ENABLED=false 时不应启动调度器。"""
monkeypatch.setattr(settings, "SCHEDULER_ENABLED", False)
import app.services.scheduler as sched_mod
sched_mod._scheduler = None
from app.services.scheduler import start_scheduler
result = start_scheduler()
assert result is None
@pytest.mark.asyncio
async def test_scheduler_start_stop(self, monkeypatch):
"""调度器应能正常启动和停止。"""
monkeypatch.setattr(settings, "SCHEDULER_ENABLED", True)
monkeypatch.setattr(settings, "APP_WORKERS", 1)
import app.services.scheduler as sched_mod
sched_mod._scheduler = None
from app.services.scheduler import start_scheduler, stop_scheduler
scheduler = start_scheduler()
assert scheduler is not None
# 验证 job 已添加
jobs = scheduler.get_jobs()
assert len(jobs) >= 1
assert jobs[0].id == "daily_pipeline"
stop_scheduler()
assert sched_mod._scheduler is None
@pytest.mark.asyncio
async def test_scheduler_warns_multi_worker(self, monkeypatch, caplog):
"""APP_WORKERS > 1 时应打印警告。"""
monkeypatch.setattr(settings, "SCHEDULER_ENABLED", True)
monkeypatch.setattr(settings, "APP_WORKERS", 4)
import app.services.scheduler as sched_mod
sched_mod._scheduler = None
from app.services.scheduler import start_scheduler, stop_scheduler
with caplog.at_level(logging.WARNING):
scheduler = start_scheduler()
assert scheduler is not None
assert any("APP_WORKERS" in r.message for r in caplog.records)
stop_scheduler()
@pytest.mark.asyncio
async def test_daily_pipeline_lock_prevents_reentry(self, db_session):
"""pipeline 使用 task_locks 防重入。"""
now = datetime.now(timezone.utc)
lock = TaskLock(
task="scheduler",
lock_key="pipeline-2024-01-15",
status="running",
owner="test",
acquired_at=now,
)
db_session.add(lock)
db_session.commit()
# 第二次获取锁应失败
lock2 = TaskLock(
task="scheduler",
lock_key="pipeline-2024-01-15",
status="running",
owner="test2",
acquired_at=now,
)
db_session.add(lock2)
with pytest.raises(Exception):
db_session.commit()
db_session.rollback()
# ═══════════════════════════════════════════════════════════════════════
# TaskLock 集成测试
# ═══════════════════════════════════════════════════════════════════════
class TestTaskLocks:
"""task_locks 防重入机制测试。"""
def test_unique_running_lock(self, db_session):
"""同一 task + lock_key 只能有一个 running 锁。"""
now = datetime.now(timezone.utc)
lock1 = TaskLock(
task="crawl", lock_key="2024-01-15",
status="running", owner="test1", acquired_at=now,
)
db_session.add(lock1)
db_session.commit()
lock2 = TaskLock(
task="crawl", lock_key="2024-01-15",
status="running", owner="test2", acquired_at=now,
)
db_session.add(lock2)
with pytest.raises(Exception):
db_session.commit()
db_session.rollback()
def test_released_lock_allows_new(self, db_session):
"""已释放的锁允许新的 running 锁。"""
now = datetime.now(timezone.utc)
lock1 = TaskLock(
task="crawl", lock_key="2024-01-16",
status="finished", owner="test1",
acquired_at=now, released_at=now,
)
db_session.add(lock1)
db_session.commit()
lock2 = TaskLock(
task="crawl", lock_key="2024-01-16",
status="running", owner="test2", acquired_at=now,
)
db_session.add(lock2)
db_session.commit() # 应成功