miem_workers/tests/test_admin_data.py

from datetime import datetime, timezone

from app.models import CrawlError, CrawlRun, CrawlRunEmployeeChange, Employee, EmployeeNewsLink
from app.services.admin_data import (
    employee_detail_payload,
    employee_display_payload,
    format_admin_datetime,
    list_employees_page,
    run_detail_payload,
    run_payload,
    stats_payload,
)


def test_format_admin_datetime_handles_datetime_string_and_none():
    value = datetime(2026, 4, 28, 17, 13, 34, tzinfo=timezone.utc)

    assert format_admin_datetime(value) == "28.04.2026 20:13"
    assert format_admin_datetime("2026-04-28T17:13:34.448605+00:00") == "28.04.2026 20:13"
    assert format_admin_datetime(None) == "Не указано"


def test_employee_display_payload_extracts_common_fields(db_session):
    employee = Employee(
        profile_key="staff:person",
        canonical_url="https://www.hse.ru/staff/person",
        full_name="Person Name",
        status="active",
        first_seen_at=datetime.now(timezone.utc),
        last_seen_at=datetime.now(timezone.utc),
        current_data={
            "positions": ["Professor"],
            "hse_start_year": 2024,
            "contacts": {"emails": ["person@hse.ru"], "phones": ["+79990000000"], "address": "Moscow"},
            "sections": [
                {"type": "publications", "publications": [{"title": "Paper"}]},
                {"type": "courses_by_year", "courses": [{"title": "Course"}]},
                {"type": "news", "news_links": [{"title": "News", "url": "https://example.test/news"}]},
            ],
        },
    )

    payload = employee_display_payload(employee)

    assert payload["positions_text"] == "Professor"
    assert payload["status_display"] == "Работает"
    assert payload["email_text"] == "person@hse.ru"
    assert payload["publications_count"] == 1
    assert payload["courses_count"] == 1
    assert payload["news_count"] == 1
    assert payload["first_seen_display"] != "Не указано"


def test_employee_detail_payload_normalizes_human_readable_sections(db_session):
    employee = Employee(
        profile_key="staff:person",
        profile_type="staff",
        profile_id="person",
        canonical_url="https://www.hse.ru/staff/person",
        full_name="Person Name",
        status="active",
        first_seen_at=datetime.now(timezone.utc),
        last_seen_at=datetime.now(timezone.utc),
        current_data={
            "positions": ["Professor"],
            "hse_start_year": 2024,
            "contacts": {
                "emails": ["person@hse.ru"],
                "phones": ["+79990000000"],
                "address": "Moscow",
                "items": [{"raw": "consultation hours"}],
            },
            "external_ids": [{"system": "ORCID", "value": "0000", "url": "https://orcid.org/0000"}],
            "sections": [
                {
                    "title": "Education",
                    "type": "year_blocks",
                    "year_entries": [{"year": 2020, "text": "Master degree"}],
                },
                {
                    "title": "Publications",
                    "type": "publications",
                    "publications": [{"title": "Paper", "text": "Paper details", "url": "https://example.test/paper"}],
                },
                {
                    "title": "Courses",
                    "type": "courses_by_year",
                    "academic_year": "2025/2026",
                    "courses": [{"title": "Course", "url": "https://example.test/course"}],
                },
                {
                    "title": "ВКР",
                    "type": "graduation_theses",
                    "theses_count": 1,
                    "theses": [
                        {
                            "student": "Student Name",
                            "title": "Thesis title",
                            "defense_year": 2025,
                            "project_url": "https://www.hse.ru/edu/vkr/1",
                        }
                    ],
                },
                {
                    "title": "Fallback",
                    "type": "generic",
                    "raw_text": "Fallback text",
                },
                {
                    "title": "В новостях",
                    "type": "news",
                    "news_links": [
                        {
                            "title": "News title",
                            "url": "https://example.test/news",
                            "summary": "News summary",
                            "published_at": "2026-04-28T00:00:00+00:00",
                            "published_year": 2026,
                        }
                    ],
                },
            ],
        },
    )

    payload = employee_detail_payload(employee)

    assert payload["contacts"]["emails"] == ["person@hse.ru"]
    assert payload["contacts"]["contact_items"] == ["consultation hours"]
    assert payload["external_ids"][0]["system"] == "ORCID"
    assert payload["sections"][0]["year_entries"][0]["text"] == "Master degree"
    assert payload["sections"][1]["publications"][0]["title"] == "Paper"
    assert payload["sections"][2]["courses"][0]["title"] == "Course"
    assert payload["sections"][3]["theses"][0]["student"] == "Student Name"
    assert payload["sections"][4]["paragraphs"] == ["Fallback text"]
    assert payload["sections"][5]["news_links"][0]["title"] == "News title"
    assert payload["news_links"][0]["published_display"] == "28.04.2026"


def test_employee_payload_prefers_stored_news_links(db_session):
    employee = Employee(
        profile_key="staff:news",
        canonical_url="https://www.hse.ru/staff/news",
        full_name="News Person",
        status="active",
        first_seen_at=datetime.now(timezone.utc),
        last_seen_at=datetime.now(timezone.utc),
        current_data={"sections": [{"type": "news", "news_links": [{"title": "Old news"}]}]},
    )
    db_session.add(employee)
    db_session.commit()
    db_session.add(
        EmployeeNewsLink(
            employee_id=employee.id,
            title="Stored news",
            url="https://example.test/stored",
            summary="Stored summary",
            published_at=datetime(2026, 4, 28, tzinfo=timezone.utc),
            published_year=2026,
            source_hash="b" * 64,
        )
    )
    db_session.commit()

    display = employee_display_payload(employee)
    detail = employee_detail_payload(employee)

    assert display["news_count"] == 1
    assert detail["news_links"][0]["title"] == "Stored news"
    assert detail["news_links"][0]["published_display"] == "28.04.2026"


def test_employee_payloads_tolerate_malformed_current_data(db_session):
    employee = Employee(
        profile_key="staff:broken",
        canonical_url="https://www.hse.ru/staff/broken",
        full_name="Broken Data",
        status="active",
        first_seen_at=datetime.now(timezone.utc),
        last_seen_at=datetime.now(timezone.utc),
        current_data="not-a-dict",
    )

    display = employee_display_payload(employee)
    detail = employee_detail_payload(employee)

    assert display["positions"] == []
    assert display["email_text"] == ""
    assert detail["contacts"]["emails"] == []
    assert detail["contacts"]["contact_items"] == []
    assert detail["sections"] == []


def test_list_employees_page_filters_sorts_and_paginates(db_session):
    db_session.add(
        Employee(
            profile_key="staff:b",
            canonical_url="https://www.hse.ru/staff/b",
            full_name="Beta",
            status="dismissed",
            first_seen_at=datetime.now(timezone.utc),
            last_seen_at=datetime.now(timezone.utc),
            current_data={"contacts": {"emails": []}},
        )
    )
    db_session.add(
        Employee(
            profile_key="staff:a",
            canonical_url="https://www.hse.ru/staff/a",
            full_name="Alpha",
            status="active",
            first_seen_at=datetime.now(timezone.utc),
            last_seen_at=datetime.now(timezone.utc),
            current_data={"contacts": {"emails": ["alpha@hse.ru"]}},
        )
    )
    db_session.commit()

    page = list_employees_page(db_session, status="active", sort="full_name", direction="asc", limit=10)

    assert page["total"] == 1
    assert page["employees"][0]["full_name"] == "Alpha"
    assert page["limit"] == 50


def test_stats_payload_uses_latest_run_new_count(db_session):
    db_session.add(
        Employee(
            profile_key="staff:a",
            canonical_url="https://www.hse.ru/staff/a",
            full_name="Alpha",
            status="active",
            first_seen_at=datetime.now(timezone.utc),
            last_seen_at=datetime.now(timezone.utc),
        )
    )
    db_session.add(CrawlRun(source_url="https://miem.hse.ru/persons", status="completed", new_count=3))
    db_session.commit()

    payload = stats_payload(db_session)

    assert payload["total"] == 1
    assert payload["active"] == 1
    assert payload["new_in_last_run"] == 3


def test_run_payload_calculates_progress():
    run = CrawlRun(
        source_url="https://miem.hse.ru/persons",
        status="running",
        found_count=10,
        parsed_count=4,
        skipped_count=2,
        error_count=1,
    )

    payload = run_payload(run)

    assert payload["processed_count"] == 7
    assert payload["progress_percent"] == 70.0
    assert payload["status_display"] == "Выполняется"


def test_run_detail_payload_groups_changes_and_handles_old_runs(db_session):
    old_run = CrawlRun(source_url="https://miem.hse.ru/persons", status="completed")
    run = CrawlRun(source_url="https://miem.hse.ru/persons", status="completed", new_count=1)
    employee = Employee(
        profile_key="staff:new",
        canonical_url="https://www.hse.ru/staff/new",
        full_name="New Person",
        status="active",
        first_seen_at=datetime.now(timezone.utc),
        last_seen_at=datetime.now(timezone.utc),
    )
    db_session.add_all([old_run, run, employee])
    db_session.commit()
    db_session.add(
        CrawlRunEmployeeChange(
            crawl_run_id=run.id,
            employee_id=employee.id,
            profile_key=employee.profile_key,
            profile_url=employee.canonical_url,
            full_name=employee.full_name,
            change_type="new",
            profile_available=True,
            message="added",
        )
    )
    db_session.add(
        CrawlError(crawl_run_id=run.id, profile_url=employee.canonical_url, error_type="ValueError", message="bad")
    )
    db_session.commit()

    payload = run_detail_payload(db_session, run)
    old_payload = run_detail_payload(db_session, old_run)

    assert payload["changes_detail_available"] is True
    assert payload["changes"]["new"][0]["full_name"] == "New Person"
    assert payload["errors"][0]["error_type"] == "ValueError"
    assert old_payload["changes_detail_available"] is False
    assert old_payload["changes"]["new"] == []