feat: filter employees by professional development courses

app/admin.py

@@ -1,6 +1,7 @@
 from copy import deepcopy
+from typing import Literal
 from pydantic import BaseModel, Field, ConfigDict
-from fastapi import APIRouter, BackgroundTasks, Depends, Form, Request, HTTPException
+from fastapi import APIRouter, BackgroundTasks, Depends, Form, Query, Request, HTTPException
 from fastapi.responses import HTMLResponse, RedirectResponse, Response
 from fastapi.templating import Jinja2Templates
 from sqlalchemy import desc, func, select, update
@@ -114,6 +115,8 @@ def directory(
     has_email: str | None = None,
     has_academic_degree: str | None = None,
     pps: bool = False,
+    has_training: Literal["", "true", "false"] = "",
+    training_since_year: str = Query(default="", pattern=r"^([1-9][0-9]{3})?$"),
     sort: str = "full_name",
     direction: str = "asc",
     limit: int = 50,
@@ -136,6 +139,8 @@ def directory(
             has_email=parsed_has_email,
             has_academic_degree=parsed_has_academic_degree,
             pps=pps,
+            has_training=has_training == "true" if has_training else None,
+            training_since_year=int(training_since_year) if training_since_year else None,
             sort=sort,
             direction=direction,
             limit=limit,
@@ -157,6 +162,8 @@ def directory(
                 "has_email": has_email or "",
                 "has_academic_degree": has_academic_degree or "",
                 "pps": pps,
+                "has_training": has_training,
+                "training_since_year": training_since_year,
                 "sort": sort,
                 "direction": direction,
                 "limit": page["limit"],

app/api.py

@@ -1,6 +1,6 @@
 from datetime import date
 
-from fastapi import APIRouter, BackgroundTasks, Depends, Request
+from fastapi import APIRouter, BackgroundTasks, Depends, Query, Request
 from sqlalchemy import desc, select
 from sqlalchemy.orm import Session
 
@@ -30,6 +30,8 @@ def list_employees(
     has_email: bool | None = None,
     has_academic_degree: bool | None = None,
     pps: bool = False,
+    has_training: bool | None = None,
+    training_since_year: int | None = Query(default=None, ge=1000, le=9999),
     sort: str = "full_name",
     direction: str = "asc",
     limit: int = 50,
@@ -47,6 +49,8 @@ def list_employees(
         has_email=has_email,
         has_academic_degree=has_academic_degree,
         pps=pps,
+        has_training=has_training,
+        training_since_year=training_since_year,
         sort=sort,
         direction=direction,
         limit=limit,

app/services/admin_data.py

@@ -1,5 +1,6 @@
 from __future__ import annotations
 
+import re
 from datetime import date, datetime, time
 from math import ceil
 from typing import Any
@@ -20,6 +21,27 @@ EMPLOYEE_SORTS = {
     "hse_start_year": Employee.current_data["hse_start_year"].as_integer(),
 }
 
+_TRAINING_LABEL = "повышение квалификации"
+_TRAINING_KIND = re.compile(r",\s*повышение квалификации\s*(?:,|$)", re.IGNORECASE)
+
+
+def _has_training(data: dict[str, Any], since_year: int | None) -> bool:
+    for value in _as_list(data.get("sections")):
+        section = _as_dict(value)
+        title = str(section.get("title") or "").casefold().strip()
+        if _TRAINING_LABEL not in (part.strip() for part in title.split("/")):
+            continue
+        for value in _as_list(section.get("year_entries")):
+            entry = _as_dict(value)
+            year = entry.get("year")
+            text = str(entry.get("text") or "").strip()
+            if since_year is not None and (type(year) is not int or year < since_year):
+                continue
+            if text and (title == _TRAINING_LABEL or _TRAINING_KIND.search(text)):
+                return True
+    return False
+
+
 def employee_display_payload(employee: Employee) -> dict[str, Any]:
     data = _as_dict(employee.current_data)
     contacts = _as_dict(data.get("contacts"))
@@ -117,6 +139,8 @@ def list_employees_page(
     has_email: bool | None = None,
     has_academic_degree: bool | None = None,
     pps: bool = False,
+    has_training: bool | None = None,
+    training_since_year: int | None = None,
     sort: str = "full_name",
     direction: str = "asc",
     limit: int = 50,
@@ -135,15 +159,28 @@ def list_employees_page(
     sort_column = EMPLOYEE_SORTS.get(sort, Employee.full_name)
     order = desc(sort_column) if direction == "desc" else sort_column
     ordered_stmt = base_stmt.order_by(order)
-    if pps:
-        # Match decoded position strings consistently in PostgreSQL and SQLite.
-        employees = [employee for employee in db.scalars(ordered_stmt).all()
-                     if any("кафедра" in position.casefold() or "департамент" in position.casefold()
-                            for position in _clean_list(_as_dict(employee.current_data).get("positions")))]
-        total = len(employees)
+    if has_training is None and training_since_year is not None:
+        has_training = True
+    if pps or has_training is not None:
+        # Apply profile filters to decoded data before pagination on both databases.
+        employees = []
+        first_page = []
+        total = 0
+        for employee in db.scalars(ordered_stmt.execution_options(yield_per=100)):
+            data = _as_dict(employee.current_data)
+            if pps and not any("кафедра" in position.casefold() or "департамент" in position.casefold()
+                               for position in _clean_list(data.get("positions"))):
+                continue
+            if has_training is not None and _has_training(data, training_since_year) != has_training:
+                continue
+            if offset and total < limit:
+                first_page.append(employee)
+            if offset <= total < offset + limit:
+                employees.append(employee)
+            total += 1
         if offset >= total:
+            employees = first_page
             offset = 0
-        employees = employees[offset:offset + limit]
     else:
         total = db.scalar(select(func.count()).select_from(base_stmt.subquery())) or 0
         if offset >= total:

app/static/admin.css

@@ -558,9 +558,17 @@
   color: #6b7280;
 }
 
+.directory__filter-panel > summary {
+  width: fit-content;
+  min-height: 44px;
+  align-content: center;
+  cursor: pointer;
+  font-weight: 600;
+}
+
 .directory__filters {
   display: grid;
-  grid-template-columns: minmax(0, 1.1fr) minmax(0, 2fr) minmax(0, 1.25fr) minmax(0, 2fr);
+  grid-template-columns: repeat(5, minmax(0, 1fr));
   gap: 10px;
   padding: 16px;
   background: #ffffff;
@@ -600,6 +608,10 @@
   font-weight: 700;
 }
 
+.directory__filter-hint {
+  color: #4b5563;
+}
+
 .directory__input {
   box-sizing: border-box;
   width: 100%;

app/static/guide.js

@@ -8,17 +8,17 @@
   const steps = [
     {id: 'welcome', title: 'Познакомьтесь с Workers',
       intro: 'Найдите сотрудника, подберите кандидатов в диссовет и проверьте публикации. Подсказки можно повторить из меню «Как пользоваться».'},
-    {id: 'employee-search', path: directory, title: 'Найдите сотрудника', region: '.directory__filters', tips: [
+    {id: 'employee-search', path: directory, title: 'Найдите сотрудника', region: '.directory__filter-panel', tips: [
       ['[name="q"]', 'Введите фамилию, часть ФИО или ссылку на профиль ВШЭ.'],
       ['[name="status"]', '«Требует проверки» означает, что профиль недоступен, а увольнение ещё не подтверждено.'],
       ['[name="has_email"]', 'Чтобы найти рабочие контакты, выберите «Есть email».'],
     ]},
-    {id: 'employee-filters', path: directory, title: 'Уточните список', region: '.directory__filters', tips: [
+    {id: 'employee-filters', path: directory, title: 'Уточните список', region: '.directory__filter-panel', tips: [
       ['[name="has_academic_degree"]', 'Звание профессора или доцента само по себе не считается учёной степенью.'],
       ['[name="pps"]', 'Оставьте сотрудников профессорско-преподавательского состава.'],
       ['[name="started_to"]', '«От» и «До» задают период первого обнаружения профиля системой.'],
     ]},
-    {id: 'employee-sort', path: directory, title: 'Настройте порядок списка', region: '.directory__filters', tips: [
+    {id: 'employee-sort', path: directory, title: 'Настройте порядок списка', region: '.directory__filter-panel', tips: [
       ['[name="sort"]', '«Год начала» — начало работы в ВШЭ. «Впервые найден» — когда профиль обнаружила система.'],
       ['[name="direction"]', 'Чтобы увидеть новые записи первыми, выберите «По убыванию».'],
       ['[name="limit"]', 'Выберите число строк и нажмите «Применить фильтры».'],
@@ -130,6 +130,7 @@
     paused = Boolean(step.path && step.path !== location.pathname);
     clearTips();
     const region = !paused && step.region && main.querySelector(step.region);
+    if (region instanceof HTMLDetailsElement) region.open = true;
     if (region) region.before(guide);
     else main.prepend(guide);
     heading.textContent = paused ? 'Продолжите обучение' : step.title;

app/templates/directory.html

@@ -12,6 +12,9 @@
     <button class="button" type="button" data-columns-open aria-controls="columns-dialog" aria-expanded="false">Настроить колонки</button>
   </div>
 
+  {% set has_filters = filters.q or filters.status or filters.has_email or filters.has_academic_degree or filters.pps or filters.started_from or filters.started_to or filters.has_training or filters.training_since_year %}
+  <details class="directory__filter-panel">
+    <summary>Фильтры{% if has_filters %} · применены{% endif %}</summary>
   <form class="directory__filters" method="get" action="/admin/directory">
     <fieldset class="directory__filter-group directory__filter-group--search">
       <legend class="directory__filter-legend">Поиск</legend>
@@ -37,6 +40,18 @@
       </select></label>
       <label class="directory__checkbox"><input type="checkbox" name="pps" value="true" {% if filters.pps %}checked{% endif %}> ППС</label>
     </fieldset>
+    <fieldset class="directory__filter-group">
+      <legend class="directory__filter-legend">Повышение квалификации</legend>
+      <label class="directory__field">Курсы в профиле<select class="directory__input" name="has_training">
+        <option value="" {% if not filters.has_training %}selected{% endif %}>Любое</option>
+        <option value="true" {% if filters.has_training == "true" %}selected{% endif %}>Есть курсы</option>
+        <option value="false" {% if filters.has_training == "false" %}selected{% endif %}>Нет курсов</option>
+      </select></label>
+      <label class="directory__field">С какого года включительно
+        <input class="directory__input" name="training_since_year" inputmode="numeric" pattern="[1-9][0-9]{3}" maxlength="4" value="{{ filters.training_since_year }}" placeholder="Например, 2024" aria-describedby="training-year-hint">
+      </label>
+      <small class="directory__filter-hint" id="training-year-hint">Если указан только год, будут показаны сотрудники с курсами.</small>
+    </fieldset>
     <fieldset class="directory__filter-group">
       <legend class="directory__filter-legend">Период обнаружения</legend>
       <label class="directory__field">От<input class="directory__input" type="date" name="started_from" value="{{ filters.started_from }}"></label>
@@ -64,6 +79,7 @@
       <a class="button button--ghost" href="/admin/directory">Сбросить</a>
     </div>
   </form>
+  </details>
 
   <details class="directory__help">
     <summary>Что означают даты и статусы</summary>
@@ -113,7 +129,7 @@
         {% else %}
         <tr><td class="directory-table__empty" colspan="15">
           <strong>Сотрудники не найдены</strong>
-          {% if filters.q or filters.status or filters.has_email or filters.has_academic_degree or filters.pps or filters.started_from or filters.started_to %}
+          {% if has_filters %}
           <span>Попробуйте изменить запрос или сбросить фильтры.</span>
           <a class="admin__link" href="/admin/directory">Сбросить фильтры</a>
           {% else %}

app/version.py

@@ -1,3 +1,3 @@
-APP_VERSION = "1.6.2"
-FRONTEND_VERSION = "1.6.2"
-BACKEND_VERSION = "1.6.2"
+APP_VERSION = "1.7.0"
+FRONTEND_VERSION = "1.7.0"
+BACKEND_VERSION = "1.7.0"

pyproject.toml

@@ -1,6 +1,6 @@
 [project]
 name = "miem-workers"
-version = "1.6.2"
+version = "1.7.0"
 description = "MIEM employees parser, admin API, and web admin"
 requires-python = ">=3.11"
 dependencies = [

tests/browser_admin.py

@@ -75,6 +75,12 @@ def main():
             page.keyboard.press("Tab")
             assert skip_link.evaluate("e => getComputedStyle(e).left === '-999px'")
 
+            filters = page.locator(".directory__filter-panel")
+            expect(filters).not_to_have_attribute("open", "")
+            expect(page.get_by_label("ФИО или ссылка")).to_be_hidden()
+            filters.locator("summary").focus()
+            page.keyboard.press("Enter")
+            expect(page.get_by_label("ФИО или ссылка")).to_be_visible()
             for width in (1440, 1024, 921, 920, 768, 621, 620, 390, 320):
                 page.set_viewport_size({"width": width, "height": 844})
                 assert page.locator(".directory__filters").evaluate("e => e.scrollWidth <= e.clientWidth")
@@ -88,6 +94,7 @@ def main():
             page.get_by_role("button", name="Применить фильтры").click()
             expect(page.get_by_role("status")).to_have_text("Показаны 1–1 из 1")
             assert "offset=" not in page.url
+            expect(filters).not_to_have_attribute("open", "")
             trigger = page.get_by_role("button", name="Настроить колонки")
             trigger.focus()
             page.keyboard.press("Enter")
@@ -116,6 +123,7 @@ def main():
             assert dialog.evaluate("e => e.getBoundingClientRect().right <= innerWidth")
             page.screenshot(path=str(output / "mobile-dialog.png"), full_page=True)
             page.keyboard.press("Escape")
+            filters.locator("summary").click()
             page.get_by_label("ФИО или ссылка").fill("Нет совпадений")
             page.get_by_role("button", name="Применить фильтры").click()
             expect(page.get_by_text("Сотрудники не найдены", exact=True)).to_be_visible()

tests/test_api.py

@@ -18,7 +18,7 @@ def test_health_returns_versions():
     response = TestClient(app).get("/api/health")
 
     assert response.status_code == 200
-    assert response.json()["backend_version"] == "1.6.2"
+    assert response.json()["backend_version"] == "1.7.0"
 
 
 def test_api_employees_and_stats_require_admin_session():

tests/test_council.py

@@ -230,7 +230,7 @@ def test_public_page_data_minimization_and_safe_links(db_session, export):
         assert "javascript:" not in fragment.text and "private@example.org" not in fragment.text
         assert "javascript:" not in response.text and "private@example.org" not in response.text
         assert "/admin/employees/" not in response.text and "/admin/logout" not in response.text
-        assert "Backend 1.6.2 · Frontend 1.6.2" in response.text
+        assert "Backend 1.7.0 · Frontend 1.7.0" in response.text
         assert "Вход в систему" in response.text
         assert client.get("/admin/directory", follow_redirects=False).status_code in (302, 303, 401, 403)
         assert "Сотрудники не найдены" in client.get("/admin/council?q=missing").text

tests/test_training_filter.py

@@ -0,0 +1,79 @@
+from bs4 import BeautifulSoup
+from fastapi.testclient import TestClient
+
+from app.config import Settings, get_settings
+from app.db import get_db
+from app.main import app
+from app.models import Employee
+from app.parser.profile import extract_sections
+from app.security import SESSION_COOKIE, sign_session
+from app.services.admin_data import list_employees_page
+
+
+def test_training_filter_uses_course_year_and_kind_before_pagination(db_session):
+    title = "Дополнительное образование / Повышение квалификации / Стажировки"
+    profiles = [
+        (title, "2023", "«Курс 2024», повышение квалификации"),
+        (title, "2024", "«Курс», повышение квалификации, НИУ ВШЭ"),
+        (title, "2025", "«Курс», Повышение квалификации"),
+        (title, "2025", "«Стажировка», стажировка"),
+        ("Конференции", "2025", "«Доклад», повышение квалификации"),
+        (title, "", "«Курс без года», повышение квалификации"),
+    ]
+    for index, (section_title, year, text) in enumerate(profiles):
+        soup = BeautifulSoup(
+            f'<h2>{section_title}</h2><div><div class="with-indent">'
+            f'<div class="person-list-hangover">{year}</div><span>{text}</span></div></div>',
+            "html.parser",
+        )
+        url = f"https://example.test/{index}"
+        db_session.add(Employee(
+            profile_key=f"training:{index}", canonical_url=url, full_name=f"Person {index}",
+            current_data={
+                "sections": extract_sections(soup, url),
+                "positions": ["Доцент: кафедра"] if index == 1 else ["Инженер"],
+            },
+        ))
+    db_session.add(Employee(profile_key="training:6", canonical_url="https://example.test/6", full_name="Person 6"))
+    db_session.commit()
+
+    def names(**filters):
+        return [item["full_name"] for item in list_employees_page(db_session, **filters)["employees"]]
+
+    assert names(has_training=True) == ["Person 0", "Person 1", "Person 2", "Person 5"]
+    assert names(has_training=False) == ["Person 3", "Person 4", "Person 6"]
+    assert names(training_since_year=2024) == ["Person 1", "Person 2"]
+    assert names(training_since_year=2024, has_training=False) == [
+        "Person 0", "Person 3", "Person 4", "Person 5", "Person 6",
+    ]
+    assert names(training_since_year=2024, pps=True) == ["Person 1"]
+    assert names(training_since_year=2024, offset=1) == ["Person 2"]
+    assert names(training_since_year=2024, offset=25) == ["Person 1", "Person 2"]
+
+    settings = Settings(_env_file=None, admin_username="admin", admin_password="password", session_secret="test-training")
+    app.dependency_overrides[get_db] = lambda: db_session
+    app.dependency_overrides[get_settings] = lambda: settings
+    try:
+        with TestClient(app) as client:
+            client.cookies.set(SESSION_COOKIE, sign_session("admin", settings))
+            response = client.get("/api/employees?has_training=false&training_since_year=2024")
+            assert response.status_code == 200
+            assert response.json()["total"] == 5
+
+            response = client.get("/admin/directory?has_training=true&training_since_year=2024&offset=1")
+            assert response.status_code == 200
+            page = BeautifulSoup(response.text, "html.parser")
+            panel = page.select_one(".directory__filter-panel")
+            assert not panel.has_attr("open")
+            assert panel.summary.get_text(strip=True) == "Фильтры · применены"
+            assert panel.select_one('select[name="has_training"] option[selected]')["value"] == "true"
+            assert panel.select_one('input[name="training_since_year"]')["value"] == "2024"
+            assert "Person 1" not in response.text
+            assert "Person 2" in response.text
+            previous = page.select_one(".directory__pagination a")["href"]
+            assert "has_training=true" in previous
+            assert "training_since_year=2024" in previous
+            assert client.get("/admin/directory?has_training=&training_since_year=").status_code == 200
+            assert client.get("/admin/directory?training_since_year=bad").status_code == 422
+    finally:
+        app.dependency_overrides.clear()