TudorandClaude Opus 5
1a6d349dad
A dedicated endpoint rather than a mode of /api/schools, because that path filters and sorts 25,000 pandas rows per query while holding the GIL — affordable once per search, not once per keystroke. A test asserts the distinction directly by making load_school_data raise and requiring the endpoint to answer anyway. Nothing errors on ordinary input: a short query, no matches, or Typesense being down are all 200 with an empty list. Cached deliberately. Prefix queries repeat enormously across users and school names change once a year, so s-maxage plus the existing ETag middleware turns most keystrokes into 304s. Co-Authored-By: Claude Opus 5 <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_015mWQnpye9F299NVRCCSRvj
129 lines
4.8 KiB
Python
129 lines
4.8 KiB
Python
"""Tests for school autosuggest (spec 2026-08-26)."""
|
|
|
|
from backend import data_loader
|
|
|
|
|
|
class _FakeDocs:
|
|
def __init__(self, hits, explode=False):
|
|
self._hits = hits
|
|
self._explode = explode
|
|
self.last_params = None
|
|
|
|
def search(self, params):
|
|
self.last_params = params
|
|
if self._explode:
|
|
raise RuntimeError("typesense is down")
|
|
return {"hits": [{"document": d} for d in self._hits]}
|
|
|
|
|
|
class _FakeClient:
|
|
def __init__(self, hits, explode=False):
|
|
self.docs = _FakeDocs(hits, explode)
|
|
self.collections = {"schools": type("C", (), {"documents": self.docs})()}
|
|
|
|
|
|
_HIT = {
|
|
"urn": 100010, "school_name": "Brecknock Primary School",
|
|
"local_authority": "Camden", "postcode": "NW1 1AA",
|
|
"phase": "Primary", "school_type": "Community school",
|
|
}
|
|
|
|
|
|
def _use(monkeypatch, client):
|
|
monkeypatch.setattr(data_loader, "_get_typesense_client", lambda: client)
|
|
|
|
|
|
def test_returns_the_fields_a_suggestion_needs(monkeypatch):
|
|
# Local authority is not decoration: there are many schools called
|
|
# "St Mary's", and a list without it cannot be chosen between.
|
|
_use(monkeypatch, _FakeClient([_HIT]))
|
|
out = data_loader.suggest_schools_typesense("breck")
|
|
assert out == [{
|
|
"urn": 100010, "school_name": "Brecknock Primary School",
|
|
"local_authority": "Camden", "postcode": "NW1 1AA",
|
|
"phase": "Primary", "school_type": "Community school",
|
|
}]
|
|
|
|
|
|
def test_a_missing_optional_field_becomes_an_empty_string(monkeypatch):
|
|
# phase and school_type are optional in the Typesense schema. A missing
|
|
# key must not KeyError in the keystroke path.
|
|
_use(monkeypatch, _FakeClient([{"urn": 1, "school_name": "X",
|
|
"local_authority": "Y", "postcode": "Z"}]))
|
|
out = data_loader.suggest_schools_typesense("x")
|
|
assert out[0]["phase"] == "" and out[0]["school_type"] == ""
|
|
|
|
|
|
def test_typesense_unavailable_gives_no_suggestions_rather_than_raising(monkeypatch):
|
|
_use(monkeypatch, None)
|
|
assert data_loader.suggest_schools_typesense("anything") == []
|
|
|
|
|
|
def test_a_typesense_error_gives_no_suggestions_rather_than_raising(monkeypatch):
|
|
_use(monkeypatch, _FakeClient([], explode=True))
|
|
assert data_loader.suggest_schools_typesense("anything") == []
|
|
|
|
|
|
def test_the_limit_is_passed_through_and_clamped(monkeypatch):
|
|
client = _FakeClient([])
|
|
_use(monkeypatch, client)
|
|
data_loader.suggest_schools_typesense("x", limit=500)
|
|
assert client.docs.last_params["per_page"] == 20
|
|
|
|
|
|
def _client(monkeypatch, rows, *, blow_up_dataframe=False):
|
|
from fastapi.testclient import TestClient
|
|
from backend import app as app_module
|
|
|
|
monkeypatch.setattr(app_module, "suggest_schools_typesense",
|
|
lambda q, limit=8: rows)
|
|
if blow_up_dataframe:
|
|
def _boom():
|
|
raise AssertionError("the suggest path must not load the DataFrame")
|
|
monkeypatch.setattr(app_module, "load_school_data", _boom)
|
|
monkeypatch.setattr(app_module, "load_latest_school_data", _boom)
|
|
return TestClient(app_module.app, raise_server_exceptions=False)
|
|
|
|
|
|
def test_the_endpoint_returns_suggestions(monkeypatch):
|
|
body = _client(monkeypatch, [_HIT]).get("/api/suggest?q=breck").json()
|
|
assert body["suggestions"][0]["school_name"] == "Brecknock Primary School"
|
|
|
|
|
|
def test_the_endpoint_never_touches_the_dataframe(monkeypatch):
|
|
"""The whole reason this is not a mode of /api/schools.
|
|
|
|
That endpoint filters and sorts 25,000 rows of pandas per query, holding
|
|
the GIL. Per keystroke, that is the cost this endpoint exists to avoid.
|
|
"""
|
|
res = _client(monkeypatch, [_HIT], blow_up_dataframe=True).get("/api/suggest?q=breck")
|
|
assert res.status_code == 200
|
|
assert res.json()["suggestions"]
|
|
|
|
|
|
def test_a_one_character_query_returns_nothing_and_does_not_error(monkeypatch):
|
|
# The keystroke path never errors on ordinary input.
|
|
res = _client(monkeypatch, [_HIT]).get("/api/suggest?q=b")
|
|
assert res.status_code == 200
|
|
assert res.json() == {"suggestions": []}
|
|
|
|
|
|
def test_a_blank_query_returns_nothing_and_does_not_error(monkeypatch):
|
|
res = _client(monkeypatch, [_HIT]).get("/api/suggest?q=")
|
|
assert res.status_code == 200
|
|
assert res.json() == {"suggestions": []}
|
|
|
|
|
|
def test_typesense_down_is_an_empty_list_not_a_500(monkeypatch):
|
|
res = _client(monkeypatch, []).get("/api/suggest?q=breck")
|
|
assert res.status_code == 200
|
|
assert res.json() == {"suggestions": []}
|
|
|
|
|
|
def test_the_response_is_cacheable(monkeypatch):
|
|
# Prefix queries repeat enormously across users, and school names change
|
|
# once a year. Without this the endpoint pays full price every keystroke.
|
|
res = _client(monkeypatch, [_HIT]).get("/api/suggest?q=breck")
|
|
assert "s-maxage" in res.headers.get("cache-control", "")
|
|
assert res.headers.get("etag")
|