perfect-postcode/finder/test_rightmove_concurrency.py

"""Tests for Rightmove's accurate-pin skip and concurrent detail fetching."""

import threading

import rightmove
from rightmove import _needs_detail_fetch, _paginate, _prime_detail_postcodes


def _prop(pid, pin=None):
    loc = {"latitude": 51.5, "longitude": -0.1}
    if pin is not None:
        loc["pinType"] = pin
    return {"id": pid, "location": loc}


# ---------------------------------------------------------------------------
# _needs_detail_fetch: accurate-pin skip
# ---------------------------------------------------------------------------


def test_needs_detail_fetch_skips_only_accurate_pins(monkeypatch):
    monkeypatch.setattr(rightmove, "RIGHTMOVE_SKIP_DETAILS_FOR_ACCURATE_PINS", True)
    assert _needs_detail_fetch(_prop("1", "ACCURATE_POINT")) is False
    assert _needs_detail_fetch(_prop("2", "APPROXIMATE_POINT")) is True
    assert _needs_detail_fetch(_prop("3")) is True  # no pinType -> fetch
    assert _needs_detail_fetch({"id": "4"}) is True  # no location -> fetch


def test_needs_detail_fetch_disabled_always_fetches(monkeypatch):
    monkeypatch.setattr(rightmove, "RIGHTMOVE_SKIP_DETAILS_FOR_ACCURATE_PINS", False)
    assert _needs_detail_fetch(_prop("1", "ACCURATE_POINT")) is True


# ---------------------------------------------------------------------------
# _prime_detail_postcodes: worklist selection + concurrent fetch
# ---------------------------------------------------------------------------


def _record_fetcher(monkeypatch):
    fetched = []
    lock = threading.Lock()

    def fake_fetch(_client, pid):
        with lock:
            fetched.append(pid)
        rightmove._detail_postcode_cache[pid] = f"PC-{pid}"
        return f"PC-{pid}"

    monkeypatch.setattr(rightmove, "_fetch_detail_postcode", fake_fetch)
    return fetched


def test_prime_skips_cached_accurate_and_dedups(monkeypatch):
    rightmove._detail_postcode_cache.clear()
    rightmove._detail_postcode_cache["cached"] = "SW9 9ZZ"
    monkeypatch.setattr(rightmove, "RIGHTMOVE_SKIP_DETAILS_FOR_ACCURATE_PINS", True)
    fetched = _record_fetcher(monkeypatch)

    props = [
        _prop("cached", "APPROXIMATE_POINT"),  # already cached -> skip
        _prop("acc", "ACCURATE_POINT"),  # accurate pin -> skip
        _prop("a", "APPROXIMATE_POINT"),  # fetch
        _prop("a", "APPROXIMATE_POINT"),  # duplicate id -> skip
        _prop("b"),  # no pinType -> fetch
        {"id": ""},  # no id -> skip
    ]
    _prime_detail_postcodes(object(), props, True, 10)

    assert sorted(fetched) == ["a", "b"]
    assert rightmove._detail_postcode_cache["a"] == "PC-a"
    assert rightmove._detail_postcode_cache["b"] == "PC-b"
    rightmove._detail_postcode_cache.clear()


def test_prime_respects_detail_cap(monkeypatch):
    rightmove._detail_postcode_cache.clear()
    monkeypatch.setattr(rightmove, "RIGHTMOVE_SKIP_DETAILS_FOR_ACCURATE_PINS", True)
    fetched = _record_fetcher(monkeypatch)

    props = [_prop(str(i), "APPROXIMATE_POINT") for i in range(10)]
    _prime_detail_postcodes(object(), props, True, 3)

    assert sorted(fetched) == ["0", "1", "2"]
    rightmove._detail_postcode_cache.clear()


def test_prime_is_a_noop_when_disabled_or_cap_zero(monkeypatch):
    rightmove._detail_postcode_cache.clear()

    def _boom(*_a):  # pragma: no cover - must never be called
        raise AssertionError("must not fetch when disabled")

    monkeypatch.setattr(rightmove, "_fetch_detail_postcode", _boom)
    _prime_detail_postcodes(object(), [_prop("a")], False, 10)  # fetch_details off
    _prime_detail_postcodes(object(), [_prop("a")], True, 0)  # cap 0
    assert rightmove._detail_postcode_cache == {}


# ---------------------------------------------------------------------------
# _paginate end-to-end (network stubbed): accurate pins fall back to
# coordinates, approximate pins use the detail postcode.
# ---------------------------------------------------------------------------


class _StubIndex:
    def __init__(self, postcode):
        self._postcode = postcode

    def nearest(self, _lat, _lng):
        return self._postcode


def _full_prop(pid, pin):
    return {
        "id": pid,
        "location": {"latitude": 51.477, "longitude": -0.116, "pinType": pin},
        "price": {"amount": 500000, "displayPrices": []},
        "displayAddress": "Caldwell Street, Stockwell, London, SW9",
        "propertySubType": "Flat",
        "bedrooms": 2,
        "bathrooms": 1,
        "propertyUrl": f"/properties/{pid}",
    }


def test_paginate_uses_detail_for_approximate_and_coords_for_accurate(monkeypatch):
    rightmove._detail_postcode_cache.clear()
    monkeypatch.setattr(rightmove, "RIGHTMOVE_SKIP_DETAILS_FOR_ACCURATE_PINS", True)

    raw = [
        _full_prop("approx", "APPROXIMATE_POINT"),
        _full_prop("acc", "ACCURATE_POINT"),
    ]
    monkeypatch.setattr(
        rightmove, "_collect_search_props", lambda *a, **k: (raw, len(raw))
    )

    fetched = []

    def fake_fetch(_client, pid):
        fetched.append(pid)
        rightmove._detail_postcode_cache[pid] = "SW9 0HD"
        return "SW9 0HD"

    monkeypatch.setattr(rightmove, "_fetch_detail_postcode", fake_fetch)

    props, count = _paginate(
        object(),
        "1",
        "SW9",
        {"channel": "BUY", "transactionType": "BUY", "sortType": "2"},
        _StubIndex("SW9 1AA"),
        fetch_details=True,
        detail_cap=10,
    )

    assert count == 2
    assert fetched == ["approx"]  # accurate pin was never fetched
    by_id = {p["id"]: p for p in props}
    assert by_id["approx"]["Postcode"] == "SW9 0HD"
    assert by_id["approx"]["Postcode source"] == "detail_address"
    # Accurate pin keeps the coordinate-nearest postcode.
    assert by_id["acc"]["Postcode"] == "SW9 1AA"
    assert by_id["acc"]["Postcode source"] != "detail_address"
    rightmove._detail_postcode_cache.clear()