Files
bid-doctor/server/tests/conftest.py
YANG JIANKUAN e3f234ca0b feat: 读标可以走完一份文件;审计待确认区,修规则缺陷、提示词出新版本
读标操作(FR-M2-07、08)
- 后端:清单项详情(ETag)、修改(If-Match 选填,记 edited_fields 和 AI 原值)、
  采纳(补出处或声明「人工确认、无出处」,可带修改)、删除 / 丢弃与恢复、人工新增、
  替换出处、人工建出处(选同一页的句子)、修改记录(来自审计)、确认清单(不可变版本,
  内容没变复用上一版)、版本列表;正式清单有变化时已确认的清单回到草稿;项目已递交只读
- 重新解析不推翻人工决定:丢弃的不再冒出来,采纳的留在正式清单,人工补过的出处不被覆盖
- 前端:待确认区采纳 / 补上出处后采纳 / 修改后采纳 / 丢弃,正式清单修改、补出处、删除
  (可撤销)、修改记录、新增条目、确认清单;pdf.js 原文查看器(点出处跳页、按坐标框高亮、
  选句补出处),整屏对照布局,J / K 上下条;跨页的一句话合成一处出处显示

待确认审计(架构 §13 SK11)
- 规则只修真正的缺陷:表格框线不算下划线(文字层 v3);句号后的右括号并进同一句
  (切句 s3-v3);中文编号小节和冒号编号条目的上级条款,依据沿上级链核对;取值认中文
  数字、同一行单元格和评分因素标题;补几种无效写法;比对引文前去掉我们加进输入的标记
- 不放宽:引文最短 8 个字、编号必须对、证据全部通过
- 提示词新版本:substantive v3,qualification / scoring / schedule / tech_param v2;
  引文复制整句、并列多项不拆、跨页只引上一行,除实质性条款外输入改成纯文本
- BD_AI_MODELS 按提示词声明的能力选模型;离线评测工具 evals/run_extract.py
- 待确认:国动 46 → 4,S02 17 → 13,S06 174 → 57

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
2026-11-03 21:32:15 +08:00

159 lines
5.8 KiB
Python
Raw Blame History

This file contains ambiguous Unicode characters

This file contains Unicode characters that might be confused with other characters. If you think that this is intentional, you can safely ignore this warning. Use the Escape button to reveal them.

"""接口集成测试:跑在真实的 PostgreSQL 上(行级安全策略生效),Valkey 用第 1 号库。
需要先起依赖:docker compose -f deploy/compose/compose.yaml up -d postgres valkey gotenberg
每次测试会话重建 bid_doctor_test 库并跑全部迁移。
"""
from __future__ import annotations
import itertools
import os
import tempfile
from collections.abc import AsyncIterator
from pathlib import Path
from typing import Any
PG = os.environ.get("BD_TEST_PG", "127.0.0.1:54329")
os.environ.update(
{
"BD_ENV": "test",
"BD_DATABASE_URL": f"postgresql+psycopg://bd_app:dev-app@{PG}/bid_doctor_test",
"BD_MIGRATE_DATABASE_URL": f"postgresql+psycopg://bd_owner:dev-owner@{PG}/bid_doctor_test",
"BD_VALKEY_URL": os.environ.get("BD_TEST_VALKEY", "redis://127.0.0.1:63799/1"),
"BD_STORAGE_DIR": tempfile.mkdtemp(prefix="bd-test-objects-"),
"BD_AI_PROVIDER": "fake",
"BD_SMS_PROVIDER": "dev",
}
)
import httpx # noqa: E402
import psycopg # noqa: E402
import pytest # noqa: E402
FIXTURES = Path(__file__).parent / "fixtures"
_phones = itertools.count(13900000001)
def _recreate_database() -> None:
with psycopg.connect(f"postgresql://bd_owner:dev-owner@{PG}/postgres", autocommit=True) as conn:
conn.execute("DROP DATABASE IF EXISTS bid_doctor_test WITH (FORCE)")
conn.execute("CREATE DATABASE bid_doctor_test")
conn.execute("GRANT CONNECT ON DATABASE bid_doctor_test TO bd_app")
@pytest.fixture(scope="session", autouse=True)
def database() -> None:
_recreate_database()
from alembic import command
from alembic.config import Config
command.upgrade(Config(str(Path(__file__).resolve().parents[1] / "alembic.ini")), "head")
@pytest.fixture(scope="session", autouse=True)
async def _valkey() -> AsyncIterator[None]:
from bid_doctor.core.valkey import valkey
await valkey().flushdb()
yield
await valkey().flushdb()
@pytest.fixture(scope="session")
async def app_client() -> AsyncIterator[httpx.AsyncClient]:
from bid_doctor.app import create_app
transport = httpx.ASGITransport(app=create_app())
async with httpx.AsyncClient(transport=transport, base_url="http://test/api/v1") as c:
yield c
class User:
"""一个注册好的企业用户(桌面版 Bearer 令牌)。"""
def __init__(self, client: httpx.AsyncClient, token: str, me: dict[str, Any], phone: str) -> None:
self.client, self.token, self.me, self.phone = client, token, me, phone
self.headers = {"Authorization": f"Bearer {token}"}
async def get(self, path: str, **kw: Any) -> httpx.Response:
return await self.client.get(path, headers=self.headers, **kw)
async def post(self, path: str, **kw: Any) -> httpx.Response:
return await self.client.post(path, headers=self.headers, **kw)
async def put(self, path: str, **kw: Any) -> httpx.Response:
return await self.client.put(path, headers=self.headers, **kw)
async def patch(self, path: str, **kw: Any) -> httpx.Response:
return await self.client.patch(path, headers={**self.headers, **kw.pop("headers", {})}, **kw)
async def delete(self, path: str) -> httpx.Response:
return await self.client.delete(path, headers=self.headers)
@property
def tenant_id(self) -> str:
return str(self.me["tenant"]["id"])
async def register(client: httpx.AsyncClient, name: str = "测试集成公司") -> User:
phone = str(next(_phones))
assert (await client.post("/auth/sms-codes", json={"phone": phone, "purpose": "register"})).status_code == 202
r = await client.post(
"/auth/register",
json={
"phone": phone,
"sms_code": "000000",
"tenant_name": name,
"display_name": "张工",
"terms_version": "v1",
"client_kind": "desktop",
},
)
assert r.status_code == 201, r.text
body = r.json()
return User(client, body["token"], body["me"], phone)
@pytest.fixture
async def user(app_client: httpx.AsyncClient) -> User:
return await register(app_client)
async def upload(u: User, filename: str, data: bytes) -> httpx.Response:
r = await u.post("/uploads", json={"filename": filename, "size_bytes": len(data), "purpose": "project_document"})
assert r.status_code == 201, r.text
up = r.json()
size = up["part_size"]
for n in range(1, up["part_count"] + 1):
assert (
await u.put(f"/uploads/{up['id']}/parts/{n}", content=data[(n - 1) * size : n * size])
).status_code == 204
return await u.post(f"/uploads/{up['id']}/complete")
async def project_with_tender(u: User, fixture: str = "tender-mini.pdf") -> tuple[str, str]:
"""建项目并挂上一份招标文件,返回 (项目编号, 文档编号)。"""
project = (await u.post("/projects", json={})).json()
done = await upload(u, fixture, (FIXTURES / fixture).read_bytes())
assert done.status_code == 200, done.text
r = await u.post(f"/projects/{project['id']}/documents", json={"upload_id": done.json()["id"], "role": "tender"})
assert r.status_code == 201, r.text
return project["id"], r.json()["id"]
async def run_parse(u: User, document_id: str) -> dict[str, Any]:
"""发起解析,并在测试进程里直接跑流水线(不经过 worker)。"""
from uuid import UUID
from bid_doctor.document.pipeline import runner
r = await u.post(f"/documents/{document_id}/parse-jobs", json={"expected_charge": 1})
assert r.status_code == 201, r.text
await runner.run(UUID(u.tenant_id), UUID(r.json()["id"]))
return (await u.get(f"/parse-jobs/{r.json()['id']}")).json()
async def balance(u: User) -> int:
accounts = (await u.get("/quota")).json()["accounts"]
return next(a["balance"] for a in accounts if a["unit"] == "parse")