- 全链路:多源JD接入/清洗交叉验证/结构化抽取(星火+离线双通道)/时序知识图谱/新岗位发现/演化分析/人岗匹配/学习路径 - WebUI 五视图:驾驶舱/图谱工作台/岗位演化/匹配(单人+批量)/学习路径 - 设置中心(config.json)/Token鉴权/SQLite状态库/语义向量通道(BGE-M3本地或联网API) - 71 个 pytest 用例;数据目录仅保留结构(.gitkeep),数据由 scripts/generate_dataset.py 复现
49 lines
1.5 KiB
Python
49 lines
1.5 KiB
Python
"""pytest 共享夹具:确保数据与图谱存在(数据已随工程提交,缺失时现场生成)。"""
|
|
from __future__ import annotations
|
|
|
|
import subprocess
|
|
import sys
|
|
from pathlib import Path
|
|
|
|
import pytest
|
|
|
|
ROOT = Path(__file__).resolve().parents[1]
|
|
sys.path.insert(0, str(ROOT))
|
|
|
|
PY = sys.executable
|
|
|
|
|
|
@pytest.fixture(scope="session", autouse=True)
|
|
def ensure_data() -> None:
|
|
if not (ROOT / "data" / "jd_raw").exists():
|
|
subprocess.run([PY, str(ROOT / "scripts" / "generate_dataset.py")], check=True)
|
|
|
|
|
|
@pytest.fixture(scope="session")
|
|
def graph_path() -> Path:
|
|
path = ROOT / "data" / "graph.json"
|
|
if not path.exists():
|
|
subprocess.run([PY, str(ROOT / "scripts" / "run_demo.py")], check=True)
|
|
return path
|
|
|
|
|
|
@pytest.fixture(scope="session", autouse=True)
|
|
def isolated_state_db(tmp_path_factory):
|
|
"""整个测试会话把 SQLite 状态库重定向到临时目录,避免污染真实 data/careernexus.db。
|
|
|
|
audit_path/pending_path 仅作为旧文件迁移种子,指向不存在的临时路径即跳过迁移。
|
|
"""
|
|
from app.api import routes
|
|
tmp = tmp_path_factory.mktemp("state_db")
|
|
keys = ("state_db_path", "audit_path", "pending_path")
|
|
originals = {k: routes._cfg.get(k) for k in keys}
|
|
routes._cfg["state_db_path"] = str(tmp / "state.db")
|
|
routes._cfg["audit_path"] = str(tmp / "audit.jsonl")
|
|
routes._cfg["pending_path"] = str(tmp / "pending.json")
|
|
yield
|
|
for k, v in originals.items():
|
|
if v is None:
|
|
routes._cfg.pop(k, None)
|
|
else:
|
|
routes._cfg[k] = v
|