Files
school_compare/backend/tests/test_search_completeness.py
T
TudorandClaude Opus 5 9b75f54206 fix(api): publish a validated dataset, and stop truncating search
Reload cleared the caches first and rebuilt afterwards, so any failure
left the API serving nothing, and requests arriving mid-reload saw a
half-swapped state. It now builds and validates the replacement frames,
place registry, reverse index and sitemaps off the request loop, then
publishes them in one synchronous step under a lock. A failed reload
returns 503 and keeps the previous data. Sitemap regeneration takes the
same path rather than clearing the live registry up front.

Typesense search returned at most one page of hits and used an empty
list for both "no matches" and "search is down", so a genuine empty
result silently fell back to substring matching. It now pages through
every candidate and returns None only on failure; the fallback matches
literally, since a query containing regex metacharacters used to throw.

Empty datasets answer 503 rather than 200-with-nothing or a misleading
404, so callers can tell an outage from an absent school. Adds
/api/release, which reports the build identity baked into the image.

Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
2026-09-15 10:16:58 +01:00

74 lines
3.2 KiB
Python

from types import SimpleNamespace
import pytest
from fastapi.testclient import TestClient
from backend import app as api, data_loader
from backend.tests.test_sixth_form_flag import _schools_df
def client_for(monkeypatch, search):
client = SimpleNamespace(collections={'schools': SimpleNamespace(documents=SimpleNamespace(search=search))})
monkeypatch.setattr(data_loader, '_get_typesense_client', lambda: client)
def test_search_returns_matches_beyond_first_page(monkeypatch):
pages = []
def search(params):
pages.append(params['page'])
urns = range(100000, 100250) if params['page'] == 1 else [100999]
return {'found': 251, 'hits': [{'document': {'urn': u}} for u in urns]}
client_for(monkeypatch, search)
result = data_loader.search_schools_typesense('academy')
assert len(result) == 251
assert result[-1] == 100999
assert pages == [1, 2]
def test_later_page_failure_does_not_return_partial_results(monkeypatch):
def search(params):
if params['page'] == 2:
raise RuntimeError('timeout')
return {'found': 251, 'hits': [{'document': {'urn': u}} for u in range(100000, 100250)]}
client_for(monkeypatch, search)
assert data_loader.search_schools_typesense('academy') is None
def test_zero_matches_are_distinct_from_unavailable(monkeypatch):
client_for(monkeypatch, lambda _: {'found': 0, 'hits': []})
assert data_loader.search_schools_typesense('academy') == []
monkeypatch.setattr(data_loader, '_get_typesense_client', lambda: None)
assert data_loader.search_schools_typesense('academy') is None
@pytest.mark.parametrize('matches, expected', [([], []), (None, [100001])])
def test_fallback_only_on_dependency_failure(monkeypatch, matches, expected):
monkeypatch.setattr(api.limiter, 'enabled', False)
monkeypatch.setattr(api, 'load_latest_school_data', _schools_df)
monkeypatch.setattr(api, 'search_schools_typesense', lambda _: matches)
response = TestClient(api.app).get('/api/schools?search=Alpha')
assert response.status_code == 200
assert [s['urn'] for s in response.json()['schools']] == expected
def test_filtered_api_keeps_match_from_second_search_page(monkeypatch):
monkeypatch.setattr(api.limiter, 'enabled', False)
df = _schools_df()
monkeypatch.setattr(api, 'load_latest_school_data', lambda: df)
def search(params):
urns = range(200000, 200250) if params['page'] == 1 else [100001]
return {'found': 251, 'hits': [{'document': {'urn': u}} for u in urns]}
client_for(monkeypatch, search)
response = TestClient(api.app).get('/api/schools?search=Alpha&local_authority=Testshire')
assert response.status_code == 200
assert response.json()['total'] == 1
assert response.json()['schools'][0]['urn'] == 100001
def test_unavailable_dataset_is_not_a_missing_school_or_empty_search(monkeypatch):
import pandas as pd
monkeypatch.setattr(api.limiter, 'enabled', False)
monkeypatch.setattr(api, 'load_school_data', lambda: pd.DataFrame())
monkeypatch.setattr(api, 'load_latest_school_data', lambda: pd.DataFrame())
client = TestClient(api.app)
assert client.get('/api/schools/100001').status_code == 503
assert client.get('/api/schools?search=school').status_code == 503