import csv from datetime import date from io import BytesIO from zipfile import ZipFile import pytest from fastapi.testclient import TestClient from openpyxl import Workbook, load_workbook from openpyxl.worksheet.worksheet import Worksheet from sqlalchemy.exc import OperationalError from app.db import get_db from app.main import app from app.models import Employee, EmployeePublication from app.services import council from app.services.council_export import _append, council_xlsx def selection_results(db, result): branches = list(dict.fromkeys(b for item in result["specialties"] for b in item["branches"])) return [result if b == result["branch"] and not result["q"] and not result["specialty"] else council.council_candidates(db, result["end"], sort=result["sort"], direction=result["direction"], paginate=False, branch=b) for b in branches] @pytest.fixture() def export(monkeypatch, tmp_path): path = tmp_path / "articles.csv" prepared = tmp_path / "articles.json" def write(rows): fields = ["Название публикации", "Год", "DOI", "EID (Scopus)", "UT (WoS)", "Название журнала", "Авторы НИУ ВШЭ", "Квартиль scopus", "Квартиль wos"] with path.open("w", encoding="utf-8-sig", newline="") as output: writer = csv.DictWriter(output, fieldnames=fields, delimiter=";") writer.writeheader() writer.writerows(rows) from app.services.council_source import prepare_reference import json prepared.write_text(json.dumps(prepare_reference(path), ensure_ascii=False), encoding="utf-8") council._articles_by_author.cache_clear() monkeypatch.setattr(council, "EXPORT", prepared) write([]) yield write council._articles_by_author.cache_clear() def employee(db, name="Иванов Иван Иванович", degree="Доктор технических наук", status="active", key="doctor"): person = Employee(profile_key=key, canonical_url="https://www.hse.ru/staff/test", full_name=name, status=status, current_data={"contacts": {"emails": ["private@example.org"]}, "sections": [{"title": "Учёные степени", "items": [degree] if degree else []}]}) db.add(person) db.flush() return person def publication(db, person, title="Shared work", doi=None, year=2024, kind=None, **extra): item = EmployeePublication(employee_id=person.id, title=title, year=year, doi_url=doi, publication_type=kind, source_hash=f"hash-{len(db.new)}-{title}-{doi}", **extra) db.add(item) return item def row(title="Shared work", doi="10.1234/shared", year="2024", author="Иванов Иван Иванович", **extra): return {"Название публикации": title, "Год": year, "DOI": doi, "Авторы НИУ ВШЭ": author, "Квартиль scopus": "Q1", **extra} def test_council_union_counts_provenance_and_types(db_session, export): export([row(), row(**{"Квартиль scopus": "", "Квартиль wos": "Q2"}), row(title="CSV only", doi="", year="2022"), row(title="Not eligible", doi="10.1234/old", year="2019")]) person = employee(db_session, degree="Доктор технических наук") publication(db_session, person, doi="https://dx.doi.org/10.1234/SHARED", kind="ARTICLE", publication_id="100", url="https://publications.hse.ru/view/100") publication(db_session, person, title=" shared WORK ", kind="ARTICLE") publication(db_session, person, title="Book only", kind="BOOK", year=2020) publication(db_session, person, title="Imported", doi="https://doi.org/10.1234/imported", raw_data={"csv_enrichment": {"Квартиль wos": "Q2", "DOI": "10.1234/imported"}}) db_session.commit() result = council.council_candidates(db_session, date(2026, 9, 30)) assert result["total"] == 1 candidate = result["candidates"][0] assert (candidate["total_count"], candidate["db_count"], candidate["count"]) == (3, 2, 5) shared = next(a for a in candidate["articles"] if a["doi"] == "10.1234/shared") assert shared["type_label"] == "Статья" assert shared["quartiles"] == ["Scopus Q1", "Web of Science Q2"] assert shared["rows"] == [2, 3] assert "Данные ВШЭ" in shared["origins"] and "ЛК сотрудника ВШЭ" in shared["origins"] imported = next(a for a in candidate["articles"] if a["title"] == "Imported") assert imported["origins"] == ["Данные ВШЭ"] assert imported["qualifies"] and imported["q2"] assert "Тип не указан" in imported["type_label"] assert council.period(date(2024, 2, 29))[0] == date(2020, 1, 1) def test_all_degree_levels_and_missing_publications_remain_visible(db_session, export): export([row(author="Доктор", title="Single qualifying"), row(author="Без степени", title="No degree"), row(author="Кандидат", title="Candidate work"), row(author="PhD", title="PhD work"), row(author="Две степени", title="Mixed degrees", **{"Квартиль scopus": "Q3"}), row(author="Уволен", title="Old", year="2010")]) employee(db_session, "Доктор", key="csv-only") for name, degree in [("Без степени", None), ("Кандидат", "Кандидат технических наук"), ("PhD", "Ph.D.")]: person = employee(db_session, name, degree, key=name) publication(db_session, person) employee(db_session, "Две степени", "Кандидат технических наук; Доктор физико-математических наук", key="mixed") employee(db_session, "Уволен", status="dismissed", key="dismissed") only_db = employee(db_session, "Только БД", key="database") publication(db_session, only_db, kind="PATENT") employee(db_session, "Без публикаций", key="empty") db_session.commit() items = council.council_candidates(db_session, date(2026, 9, 30))["candidates"] assert {c["name"] for c in items} == {"Доктор", "Две степени", "Уволен", "Только БД", "Кандидат", "PhD", "Без публикаций"} assert next(c for c in items if c["name"] == "Кандидат")["minimum"] == 20 assert next(c for c in items if c["name"] == "PhD")["clause"] == 6 assert next(c for c in items if c["name"] == "Без публикаций")["assessment_status"] == "Требует проверки" assert next(c for c in items if c["name"] == "Доктор")["total_count"] == 1 assert next(c for c in items if c["name"] == "Только БД")["db_count"] == 1 assert next(c for c in items if c["name"] == "Две степени")["total_count"] == 0 assert next(c for c in items if c["name"] == "Уволен")["dismissed"] def test_no_false_merge_when_title_has_conflicting_dois(db_session, export): export([row(doi="10.1234/one"), row(doi="10.1234/two"), row(doi="")]) person = employee(db_session) publication(db_session, person, title="Renamed work", doi="https://doi.org/10.1234/one") db_session.commit() item = council.council_candidates(db_session, date(2026, 9, 30))["candidates"][0] assert item["count"] == 3 assert item["total_count"] == 3 and item["db_count"] == 1 def test_csv_same_name_does_not_attribute_to_wrong_employee(db_session, export): export([row()]) for key in ["one", "two"]: person = employee(db_session, key=key) publication(db_session, person, title=key) db_session.commit() items = council.council_candidates(db_session, date(2026, 9, 30))["candidates"] assert len(items) == 2 assert all(c["ambiguous"] and c["total_count"] == 0 and c["count"] == 1 for c in items) def test_missing_database_year_merges_only_unambiguous_title_and_non_article_excluded(db_session, export): export([row(title="Known book"), row(title="Article", doi="10.1234/article")]) person = employee(db_session) publication(db_session, person, title="Known book", year=None, kind="BOOK") publication(db_session, person, title="Article", year=None, kind="ARTICLE") db_session.commit() candidate = council.council_candidates(db_session, date(2026, 9, 30))["candidates"][0] assert (candidate["count"], candidate["total_count"], candidate["db_count"]) == (2, 1, 2) book = next(a for a in candidate["articles"] if a["type_label"] == "Книга") assert not book["qualifies"] assert "не включён в счётчики Q1/Q2/К1" in book["criteria"][-1] def test_search_and_pagination_include_all_workers(db_session, export): for number in range(28): person = employee(db_session, f"Петров {number:02d}", key=f"person-{number}") publication(db_session, person, title=f"Work {number}") db_session.commit() first = council.council_candidates(db_session) last = council.council_candidates(db_session, offset=25) assert first["total"] == 28 and len(first["candidates"]) == 25 assert len(last["candidates"]) == 3 assert {c["name"] for c in first["candidates"]}.isdisjoint(c["name"] for c in last["candidates"]) assert council.council_candidates(db_session, q="петров 27")["matched"] == 1 assert council.council_candidates(db_session, offset=-1)["offset"] == 0 assert council.council_candidates(db_session, offset=999)["offset"] == 25 descending = council.council_candidates(db_session, sort="full_name", direction="desc") last_descending = council.council_candidates(db_session, sort="full_name", direction="desc", offset=25) assert descending["candidates"][0]["name"] == "Петров 27" assert [c["name"] for c in last_descending["candidates"]] == ["Петров 02", "Петров 01", "Петров 00"] def test_sort_by_name_and_each_unique_publication_count(db_session, export): export([row(author="Анна", title=f"CSV {number}", doi=f"10.1234/csv-{number}") for number in range(3)] + [row(author="Борис", title="CSV Boris", doi="10.1234/boris")]) anna = employee(db_session, "Анна", key="anna") publication(db_session, anna, title="CSV 0", doi="https://doi.org/10.1234/csv-0") for name, count in [("Борис", 2), ("Вера", 4)]: person = employee(db_session, name, key=name) for number in range(count): publication(db_session, person, title=f"DB {name} {number}") db_session.commit() expected = { "full_name": {"asc": ["Анна", "Борис", "Вера"], "desc": ["Вера", "Борис", "Анна"]}, "total_count": {"asc": ["Вера", "Борис", "Анна"], "desc": ["Анна", "Борис", "Вера"]}, "db_count": {"asc": ["Анна", "Борис", "Вера"], "desc": ["Вера", "Борис", "Анна"]}, "count": {"asc": ["Анна", "Борис", "Вера"], "desc": ["Вера", "Анна", "Борис"]}, } for sort, directions in expected.items(): for direction, names in directions.items(): result = council.council_candidates(db_session, sort=sort, direction=direction) assert [c["name"] for c in result["candidates"]] == names invalid = council.council_candidates(db_session, sort="unknown", direction="unknown") assert (invalid["sort"], invalid["direction"]) == ("total_count", "desc") assert [c["name"] for c in invalid["candidates"]] == expected["total_count"]["desc"] app.dependency_overrides[get_db] = lambda: db_session try: response = TestClient(app).get("/admin/council?sort=full_name&direction=desc") assert response.status_code == 200 assert response.text.index("Вера") < response.text.index("Борис") < response.text.index("Анна") assert '