feat: track crawl run employee changes and verify dismissals

This commit is contained in:
Anton
2026-05-06 15:13:15 +03:00
parent 2331c7a28d
commit d0459a2c30
16 changed files with 517 additions and 27 deletions

View File

@@ -1,11 +1,12 @@
from datetime import datetime, timezone
from app.models import CrawlRun, Employee
from app.models import CrawlError, CrawlRun, CrawlRunEmployeeChange, Employee
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,
)
@@ -207,3 +208,43 @@ def test_run_payload_calculates_progress():
assert payload["processed_count"] == 5
assert payload["progress_percent"] == 50.0
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"] == []