Compare commits

...

3 Commits

12 changed files with 98 additions and 10 deletions

View File

@@ -1,5 +1,9 @@
# Changelog
## 0.7.3
- Восстановлена проверка профилей сотрудников и хранение истории URL профиля.
## 0.7.2
- В каталоге сотрудников добавлены фильтр и колонка учёной степени.

View File

@@ -147,4 +147,4 @@ docker compose exec postgres pg_dump -U miem miem_workers > backup.sql
docker compose down
```
Версия сервиса: `0.7.1`. Админка всегда показывает версии backend и frontend в footer.
Версия сервиса: `0.7.3`. Админка всегда показывает версии backend и frontend в footer.

View File

@@ -41,6 +41,20 @@ def _ensure_runtime_schema() -> None:
models.EmployeeNewsLink.__table__.create(bind=engine, checkfirst=True)
inspector = inspect(engine)
table_names = set(inspector.get_table_names())
if "employees" in table_names and "employee_profile_urls" not in table_names:
models.EmployeeProfileUrl.__table__.create(bind=engine, checkfirst=True)
inspector = inspect(engine)
if "employees" in table_names:
employee_columns = {column["name"] for column in inspector.get_columns("employees")}
missing_columns = []
if "profile_unavailable_streak" not in employee_columns:
missing_columns.append("profile_unavailable_streak INTEGER NOT NULL DEFAULT 0")
if "last_profile_check_at" not in employee_columns:
missing_columns.append("last_profile_check_at TIMESTAMPTZ")
if missing_columns:
with engine.begin() as connection:
for column in missing_columns:
connection.execute(text(f"ALTER TABLE employees ADD COLUMN {column}"))
if "crawl_runs" not in table_names:
return
crawl_run_columns = {column["name"] for column in inspector.get_columns("crawl_runs")}

View File

@@ -33,6 +33,8 @@ class Employee(Base):
first_seen_at: Mapped[datetime] = mapped_column(DateTime(timezone=True), default=utcnow, nullable=False)
last_seen_at: Mapped[datetime] = mapped_column(DateTime(timezone=True), default=utcnow, nullable=False)
dismissed_at: Mapped[datetime | None] = mapped_column(DateTime(timezone=True))
profile_unavailable_streak: Mapped[int] = mapped_column(Integer, default=0, nullable=False)
last_profile_check_at: Mapped[datetime | None] = mapped_column(DateTime(timezone=True))
parser_version: Mapped[str | None] = mapped_column(String(32))
current_data: Mapped[dict | None] = mapped_column(json_type)
current_checksum: Mapped[str | None] = mapped_column(String(64))
@@ -40,12 +42,29 @@ class Employee(Base):
updated_at: Mapped[datetime] = mapped_column(DateTime(timezone=True), default=utcnow, onupdate=utcnow, nullable=False)
snapshots: Mapped[list["EmployeeSnapshot"]] = relationship(back_populates="employee")
profile_urls: Mapped[list["EmployeeProfileUrl"]] = relationship(back_populates="employee", cascade="all, delete-orphan")
tabs: Mapped[list["ProfileTab"]] = relationship(back_populates="employee", cascade="all, delete-orphan")
publications: Mapped[list["EmployeePublication"]] = relationship(back_populates="employee", cascade="all, delete-orphan")
news_links: Mapped[list["EmployeeNewsLink"]] = relationship(back_populates="employee", cascade="all, delete-orphan")
crawl_run_changes: Mapped[list["CrawlRunEmployeeChange"]] = relationship(back_populates="employee")
class EmployeeProfileUrl(Base):
__tablename__ = "employee_profile_urls"
__table_args__ = (
UniqueConstraint("employee_id", "url", name="uq_employee_profile_urls_employee_url"),
Index("ix_employee_profile_urls_employee_id", "employee_id"),
)
id: Mapped[int] = mapped_column(Integer, primary_key=True)
employee_id: Mapped[int] = mapped_column(ForeignKey("employees.id", ondelete="CASCADE"), nullable=False)
url: Mapped[str] = mapped_column(Text, nullable=False)
first_seen_at: Mapped[datetime] = mapped_column(DateTime(timezone=True), default=utcnow, nullable=False)
last_seen_at: Mapped[datetime] = mapped_column(DateTime(timezone=True), default=utcnow, nullable=False)
employee: Mapped[Employee] = relationship(back_populates="profile_urls")
class EmployeeSnapshot(Base):
__tablename__ = "employee_snapshots"
__table_args__ = (Index("ix_employee_snapshots_employee_id", "employee_id"),)

View File

@@ -162,6 +162,10 @@ def stats_payload(db: Session) -> dict[str, Any]:
return {
"total": db.scalar(select(func.count()).select_from(Employee)) or 0,
"active": db.scalar(select(func.count()).select_from(Employee).where(Employee.status == "active")) or 0,
"verification_required": db.scalar(
select(func.count()).select_from(Employee).where(Employee.status == "verification_required")
)
or 0,
"dismissed": db.scalar(select(func.count()).select_from(Employee).where(Employee.status == "dismissed")) or 0,
"new_in_last_run": latest_run.new_count if latest_run else 0,
"latest_added": employee_display_payload(latest_added) if latest_added else None,
@@ -205,7 +209,7 @@ def run_detail_payload(db: Session, run: CrawlRun | None) -> dict[str, Any] | No
.order_by(CrawlRunEmployeeChange.created_at, CrawlRunEmployeeChange.id)
).all()
errors = db.scalars(select(CrawlError).where(CrawlError.crawl_run_id == run.id).order_by(CrawlError.created_at)).all()
grouped_changes = {"new": [], "missing_from_source": [], "dismissed": []}
grouped_changes = {"new": [], "missing_from_source": [], "verification_required": [], "dismissed": []}
for change in changes:
grouped_changes.setdefault(change.change_type, []).append(_change_payload(change))
return {
@@ -262,7 +266,7 @@ def _json_text_contains(data_text: Any, value: str) -> Any:
def _employee_status_display(status: str | None) -> str:
labels = {"active": "Работает", "dismissed": "Уволен"}
labels = {"active": "Работает", "verification_required": "Требует проверки", "dismissed": "Уволен"}
return labels.get(status or "", status or "Не указано")

View File

@@ -15,6 +15,7 @@
<select class="directory__input" name="status">
<option value="" {% if not filters.status %}selected{% endif %}>Все статусы</option>
<option value="active" {% if filters.status == "active" %}selected{% endif %}>Работает</option>
<option value="verification_required" {% if filters.status == "verification_required" %}selected{% endif %}>Требует проверки</option>
<option value="dismissed" {% if filters.status == "dismissed" %}selected{% endif %}>Уволен</option>
</select>
<select class="directory__input" name="has_email">

View File

@@ -23,7 +23,7 @@
{% endif %}
</section>
{% for group, title in [("new", "Новые сотрудники"), ("missing_from_source", "Потеряшки"), ("dismissed", "Уволенные")] %}
{% for group, title in [("new", "Новые сотрудники"), ("missing_from_source", "Потеряшки"), ("verification_required", "Требуют проверки"), ("dismissed", "Уволенные")] %}
<section class="panel"{% if group == "new" %} id="new-employees"{% endif %}>
<h2 class="panel__title">{{ title }}</h2>
{% set items = run.changes[group] %}

View File

@@ -1,3 +1,3 @@
APP_VERSION = "0.7.2"
FRONTEND_VERSION = "0.7.2"
BACKEND_VERSION = "0.7.2"
APP_VERSION = "0.7.3"
FRONTEND_VERSION = "0.7.3"
BACKEND_VERSION = "0.7.3"

View File

@@ -0,0 +1,17 @@
ALTER TABLE employees
ADD COLUMN IF NOT EXISTS profile_unavailable_streak INTEGER NOT NULL DEFAULT 0;
ALTER TABLE employees
ADD COLUMN IF NOT EXISTS last_profile_check_at TIMESTAMPTZ;
CREATE TABLE IF NOT EXISTS employee_profile_urls (
id SERIAL PRIMARY KEY,
employee_id INTEGER NOT NULL REFERENCES employees(id) ON DELETE CASCADE,
url TEXT NOT NULL,
first_seen_at TIMESTAMPTZ NOT NULL DEFAULT now(),
last_seen_at TIMESTAMPTZ NOT NULL DEFAULT now(),
CONSTRAINT uq_employee_profile_urls_employee_url UNIQUE (employee_id, url)
);
CREATE INDEX IF NOT EXISTS ix_employee_profile_urls_employee_id
ON employee_profile_urls (employee_id);

View File

@@ -1,6 +1,6 @@
[project]
name = "miem-workers"
version = "0.7.2"
version = "0.7.3"
description = "MIEM employees parser, admin API, and MCP server"
requires-python = ">=3.11"
dependencies = [

View File

@@ -20,7 +20,7 @@ def test_health_returns_versions():
response = client.get("/api/health")
assert response.status_code == 200
assert response.json()["backend_version"] == "0.7.1"
assert response.json()["backend_version"] == "0.7.3"
def test_mcp_lists_tools_without_auth_and_ignores_auth_header():
@@ -154,7 +154,7 @@ def test_mcp_service_info_returns_tools_and_dataset_hash():
assert response.status_code == 200
payload = json.loads(response.json()["result"]["content"][0]["text"])
assert payload["service_name"] == "miem-employees"
assert payload["backend_version"] == "0.7.1"
assert payload["backend_version"] == "0.7.3"
assert payload["dataset"]["hash"]
assert any(tool["name"] == "sync_employees" for tool in payload["tools"])

View File

@@ -113,3 +113,32 @@ def test_runtime_schema_creates_employee_news_links_table_when_employees_exist(m
assert "employee_news_links" in inspector.get_table_names()
columns = {column["name"] for column in inspector.get_columns("employee_news_links")}
assert {"employee_id", "title", "url", "summary", "published_at", "published_year", "source_hash", "raw_data"}.issubset(columns)
def test_runtime_schema_adds_profile_verification_fields(monkeypatch):
engine = create_engine("sqlite:///:memory:")
with engine.begin() as connection:
connection.execute(
text(
"""
CREATE TABLE employees (
id INTEGER PRIMARY KEY,
profile_key VARCHAR(255) NOT NULL UNIQUE,
canonical_url TEXT NOT NULL,
status VARCHAR(32) NOT NULL DEFAULT 'active',
first_seen_at DATETIME NOT NULL,
last_seen_at DATETIME NOT NULL,
created_at DATETIME NOT NULL,
updated_at DATETIME NOT NULL
)
"""
)
)
monkeypatch.setattr("app.db.engine", engine)
_ensure_runtime_schema()
inspector = inspect(engine)
columns = {column["name"] for column in inspector.get_columns("employees")}
assert {"profile_unavailable_streak", "last_profile_check_at"}.issubset(columns)
assert "employee_profile_urls" in inspector.get_table_names()