feature: add MIEM employees parser service with admin UI and MCP

tests/conftest.py

@@ -0,0 +1,23 @@
+import pytest
+from sqlalchemy import create_engine
+from sqlalchemy.orm import sessionmaker
+from sqlalchemy.pool import StaticPool
+
+from app.db import Base
+
+
+@pytest.fixture()
+def db_session():
+    engine = create_engine(
+        "sqlite:///:memory:",
+        connect_args={"check_same_thread": False},
+        poolclass=StaticPool,
+    )
+    Base.metadata.create_all(engine)
+    Session = sessionmaker(bind=engine)
+    session = Session()
+    try:
+        yield session
+    finally:
+        session.close()
+        Base.metadata.drop_all(engine)

tests/test_api_mcp.py

@@ -0,0 +1,107 @@
+from datetime import datetime, timezone
+
+from fastapi.testclient import TestClient
+from sqlalchemy import create_engine
+from sqlalchemy.orm import sessionmaker
+from sqlalchemy.pool import StaticPool
+
+from app.config import Settings, get_settings
+from app.db import Base, get_db
+from app.main import app
+from app.models import Employee
+
+
+def test_health_returns_versions():
+    client = TestClient(app)
+
+    response = client.get("/api/health")
+
+    assert response.status_code == 200
+    assert response.json()["backend_version"] == "0.1.0"
+
+
+def test_mcp_requires_token_and_lists_tools():
+    engine = create_engine(
+        "sqlite:///:memory:",
+        connect_args={"check_same_thread": False},
+        poolclass=StaticPool,
+    )
+    Base.metadata.create_all(engine)
+    Session = sessionmaker(bind=engine)
+
+    def override_db():
+        session = Session()
+        try:
+            yield session
+        finally:
+            session.close()
+
+    app.dependency_overrides[get_db] = override_db
+    app.dependency_overrides[get_settings] = lambda: Settings(mcp_token="secret", session_secret="session-secret")
+    client = TestClient(app)
+
+    unauthorized = client.post("/mcp", json={"jsonrpc": "2.0", "id": 1, "method": "tools/list", "params": {}})
+    authorized = client.post(
+        "/mcp",
+        headers={"Authorization": "Bearer secret"},
+        json={"jsonrpc": "2.0", "id": 1, "method": "tools/list", "params": {}},
+    )
+
+    assert unauthorized.status_code == 401
+    assert authorized.status_code == 200
+    assert authorized.json()["result"]["tools"][0]["name"] == "search_employees"
+
+    app.dependency_overrides.clear()
+
+
+def test_mcp_search_employees_returns_matching_employee():
+    engine = create_engine(
+        "sqlite:///:memory:",
+        connect_args={"check_same_thread": False},
+        poolclass=StaticPool,
+    )
+    Base.metadata.create_all(engine)
+    Session = sessionmaker(bind=engine)
+    session = Session()
+    session.add(
+        Employee(
+            profile_key="staff:avsergeev",
+            profile_type="staff",
+            profile_id="avsergeev",
+            canonical_url="https://www.hse.ru/staff/avsergeev",
+            full_name="Сергеев Алексей Викторович",
+            status="active",
+            first_seen_at=datetime.now(timezone.utc),
+            last_seen_at=datetime.now(timezone.utc),
+            current_data={"sections": []},
+        )
+    )
+    session.commit()
+    session.close()
+
+    def override_db():
+        db = Session()
+        try:
+            yield db
+        finally:
+            db.close()
+
+    app.dependency_overrides[get_db] = override_db
+    app.dependency_overrides[get_settings] = lambda: Settings(mcp_token="secret", session_secret="session-secret")
+    client = TestClient(app)
+
+    response = client.post(
+        "/mcp",
+        headers={"Authorization": "Bearer secret"},
+        json={
+            "jsonrpc": "2.0",
+            "id": 1,
+            "method": "tools/call",
+            "params": {"name": "search_employees", "arguments": {"query": "Сергеев"}},
+        },
+    )
+
+    assert response.status_code == 200
+    assert "Сергеев Алексей Викторович" in response.json()["result"]["content"][0]["text"]
+
+    app.dependency_overrides.clear()

tests/test_crawler.py

@@ -0,0 +1,34 @@
+from datetime import datetime, timezone
+
+from app.models import Employee
+from app.services.crawler import _mark_dismissed
+
+
+def test_mark_dismissed_only_marks_missing_active_employees(db_session):
+    db_session.add(
+        Employee(
+            profile_key="staff:kept",
+            canonical_url="https://www.hse.ru/staff/kept",
+            status="active",
+            first_seen_at=datetime.now(timezone.utc),
+            last_seen_at=datetime.now(timezone.utc),
+        )
+    )
+    db_session.add(
+        Employee(
+            profile_key="staff:gone",
+            canonical_url="https://www.hse.ru/staff/gone",
+            status="active",
+            first_seen_at=datetime.now(timezone.utc),
+            last_seen_at=datetime.now(timezone.utc),
+        )
+    )
+    db_session.commit()
+
+    dismissed = _mark_dismissed(db_session, {"staff:kept"})
+
+    assert dismissed == 1
+    assert db_session.query(Employee).filter_by(profile_key="staff:kept").one().status == "active"
+    gone = db_session.query(Employee).filter_by(profile_key="staff:gone").one()
+    assert gone.status == "dismissed"
+    assert gone.dismissed_at is not None

tests/test_parser.py

@@ -0,0 +1,28 @@
+from bs4 import BeautifulSoup
+
+from app.parser.profile import extract_person_tabs
+from app.parser.profile_url import normalize_profile_url, parse_profile_identity
+
+
+def test_normalize_profile_url_supports_staff_and_org_persons():
+    assert normalize_profile_url("/staff/avsergeev#sci") == "https://www.hse.ru/staff/avsergeev"
+    assert normalize_profile_url("https://www.hse.ru/org/persons/123/") == "https://www.hse.ru/org/persons/123"
+    assert parse_profile_identity("https://www.hse.ru/staff/avsergeev") == ("staff", "avsergeev")
+
+
+def test_extract_person_tabs_prefers_person_menu_addition():
+    soup = BeautifulSoup(
+        """
+        <div class="person-menu is-desktop small person-menu-addition">
+          <a href="#main">Домашняя страница</a>
+          <a href="#sci" data-index="1">Публикации</a>
+        </div>
+        <a href="/org/persons/999">Other person</a>
+        """,
+        "html.parser",
+    )
+
+    tabs = extract_person_tabs(soup, "https://www.hse.ru/staff/avsergeev")
+
+    assert [tab["title"] for tab in tabs] == ["Домашняя страница", "Публикации"]
+    assert tabs[1]["href"] == "https://www.hse.ru/staff/avsergeev#sci"