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>
This commit is contained in:
TudorandClaude Opus 5 committed 2026-09-15 10:16:58 +01:00
1 parent 38bc17cab3
commit 9b75f54206
4 files changed
+253 -47

No files matched your search

+68
View File
@@ -0,0 +1,68 @@
"""Publication must preserve the current dataset until every replacement is ready."""
import asyncio
import pandas as pd
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
@pytest.fixture
def client(monkeypatch):
old = _schools_df()
monkeypatch.setattr(data_loader, '_df_cache', old)
monkeypatch.setattr(data_loader, '_df_latest_cache', old)
monkeypatch.setattr(api, '_place_registry', {'old': 'registry'})
monkeypatch.setattr(api, '_place_index', {'old': 'index'})
monkeypatch.setattr(api, '_place_index_source', api._place_registry)
monkeypatch.setattr(api, '_sitemaps', {'old.xml': 'old sitemap'})
monkeypatch.setattr(api, '_publication_lock', asyncio.Lock())
monkeypatch.setattr(api.limiter, 'enabled', False)
api.app.dependency_overrides[api.verify_admin_api_key] = lambda: True
yield TestClient(api.app, raise_server_exceptions=False)
api.app.dependency_overrides.clear()
def state():
return (data_loader._df_cache, data_loader._df_latest_cache, api._place_registry,
api._place_index, api._place_index_source, api._sitemaps)
@pytest.mark.parametrize('failure', ['empty', 'database', 'sitemap', 'duplicate'])
def test_failed_reload_preserves_every_published_object(client, monkeypatch, failure):
before = state()
df = _schools_df()
if failure == 'empty':
df = pd.DataFrame()
if failure == 'duplicate':
df = pd.concat([df, df.iloc[:1]], ignore_index=True)
def load():
if failure == 'database':
raise RuntimeError('database unavailable')
return df
monkeypatch.setattr(api, 'load_school_data_as_dataframe', load)
if failure == 'sitemap':
monkeypatch.setattr(api, 'build_sitemaps', lambda *args: (_ for _ in ()).throw(RuntimeError('bad XML')))
response = client.post('/api/admin/reload')
assert response.status_code == 503
assert all(a is b for a, b in zip(before, state()))
def test_success_publishes_school_data_places_and_sitemaps(client, monkeypatch):
df = _schools_df()
df.loc[0, 'school_name'] = 'Replacement School'
monkeypatch.setattr(api, 'load_school_data_as_dataframe', lambda: df)
response = client.post('/api/admin/reload')
assert response.status_code == 200
assert data_loader.load_school_data() is df
assert data_loader.load_latest_school_data().iloc[0].school_name == 'Replacement School'
assert api._place_index_source is api._place_registry
assert 'old.xml' not in api._sitemaps
assert 'replacement-school' in api._sitemaps['schools-1.xml']
def test_failed_sitemap_regeneration_keeps_existing_publication(client, monkeypatch):
before = state()
monkeypatch.setattr(api, 'build_sitemaps', lambda *args: (_ for _ in ()).throw(RuntimeError('bad XML')))
assert client.post('/api/admin/regenerate-sitemap').status_code == 503
assert all(a is b for a, b in zip(before, state()))