gendesign/tradein-mvp/backend/tests/scrapers/test_avito_imv_kit_parity.py

"""Config-footgun regression for kit `evaluate_via_imv` — issue #2334.

Group E1 of the scraper_kit migration epic (#2277 → #2308 → #2334 → final deletion
step). Legacy `app/services/scrapers/avito_imv.py` was deleted once the kit provider
(`scraper_kit.providers.avito.imv`) reached golden parity and no runtime caller
referenced the legacy module anymore — the legacy-vs-kit comparison tests that used
to live here were removed together with the legacy import.

What remains is a standalone kit-only regression, still worth keeping on its own:

**Config-footgun regression** — CONFIRMED by recon before issue #2334 started:
kit `evaluate_via_imv(config: ScraperConfig | None = None, ...)` only reads
`config.scraper_proxy_url` when `config is not None`; the deleted legacy module
unconditionally read `settings.scraper_proxy_url` itself. Call the kit fn WITHOUT
`config=` → own curl_cffi session gets built with NO proxy (`proxies=None`) even
though a real proxy is configured — a silent behaviour change vs the old code. WITH
`config=RealScraperConfig()` (the established DI pattern, see
`app/services/cian_price_history.py` / `tests/test_scraper_kit_pricehistory_session_parity.py::
test_fetch_detail_own_session_proxy_wiring_parity` for precedent) the proxy is wired
correctly. NOTE: neither `estimator.py` nor `house_imv_backfill.py` needs this
config= kwarg wired for `evaluate_via_imv` specifically — these tests exist to prove
the KIT SIDE stays safe against a "simplify away the config kwarg" regression.
"""

from __future__ import annotations

import asyncio
import os
from typing import Any
from unittest.mock import AsyncMock, MagicMock, patch

import pytest

# app.core.config.Settings() requires DATABASE_URL at import time; app.services.
# scraper_adapters (RealScraperConfig) imports app.core.config transitively.
# Mirror tests/test_scraper_kit_pricehistory_session_parity.py.
os.environ.setdefault("DATABASE_URL", "postgresql+psycopg://test:test@localhost/test_db")

from scraper_kit.providers._base import DEFAULT_IMPERSONATE, DOCUMENT_HEADERS
from scraper_kit.providers.avito.imv import (
    IMVAddressNotFoundError as KitIMVAddressNotFoundError,
)
from scraper_kit.providers.avito.imv import evaluate_via_imv as kit_evaluate_via_imv

from app.core.config import settings
from app.services.scraper_adapters import RealScraperConfig

# ---------------------------------------------------------------------------
# Config-footgun regression (#2334 CONFIRMED recon finding)
# ---------------------------------------------------------------------------
#
# evaluate_via_imv's own-curl_cffi-session path (browser_fetcher=None, the default)
# is the one that reads proxy config. Mirrors
# tests/test_scraper_proxy.py::test_avito_imv_own_session_receives_proxies (legacy
# reference, now gone with the legacy module) and
# tests/test_scraper_kit_pricehistory_session_parity.py::
# test_fetch_detail_own_session_proxy_wiring_parity (kit config= precedent for a
# sibling provider, #2306).


def _mock_own_session_flow() -> MagicMock:
    """Session double that lets warm-up + geocode-A pass, then fails at geocode-B
    (missing geoFieldsHash) — raises IMVAddressNotFoundError AFTER the curl_cffi
    session constructor already ran, which is all these tests need to capture.
    """
    mock_session = MagicMock()
    mock_warmup_resp = MagicMock(status_code=200)
    mock_session.get = AsyncMock(return_value=mock_warmup_resp)  # warm-up + geocode A
    mock_geo_resp = MagicMock(status_code=200)
    mock_geo_resp.json = MagicMock(return_value={"result": {"point": None}})  # no geoFieldsHash
    mock_session.post = AsyncMock(return_value=mock_geo_resp)  # geocode B
    mock_session.close = AsyncMock()
    return mock_session


async def _call_kit_own_session(*, config: Any = None) -> None:
    with pytest.raises(KitIMVAddressNotFoundError):
        await kit_evaluate_via_imv(
            address="ул. Тургенева, 4",
            rooms=2,
            area_m2=50.0,
            floor=3,
            floor_at_home=9,
            house_type="panel",
            renovation_type="cosmetic",
            has_balcony=False,
            has_loggia=False,
            config=config,
        )


def test_kit_evaluate_via_imv_without_config_drops_proxy(monkeypatch: pytest.MonkeyPatch) -> None:
    """CONFIRMED footgun: kit evaluate_via_imv called WITHOUT config= builds its own
    curl_cffi session with proxies=None — even though a real proxy IS configured in
    settings — because `_env = config.scraper_proxy_url if config is not None else None`
    never reads settings when config is absent (no fallback to env/settings inside kit).
    """
    monkeypatch.setattr(settings, "scraper_proxy_url_env", "http://test-proxy.local:8080")
    mock_session = _mock_own_session_flow()
    captured: dict[str, Any] = {}

    def _fake_session(*args: Any, **kwargs: Any) -> MagicMock:
        captured.update(kwargs)
        return mock_session

    with patch("scraper_kit.providers._base.AsyncSession", _fake_session):
        asyncio.run(_call_kit_own_session(config=None))

    assert captured.get("proxies") is None


def test_kit_evaluate_via_imv_with_config_uses_proxy(monkeypatch: pytest.MonkeyPatch) -> None:
    """With config=RealScraperConfig() (the established DI pattern for this epic) the
    kit path reads the SAME settings.scraper_proxy_url as legacy used to and wires it
    into the curl_cffi session identically — this is the regression guard: if someone
    later "simplifies away" the config kwarg threading in evaluate_via_imv, this test
    fails on `captured.get("proxies") is None` instead of the expected proxy dict.
    """
    monkeypatch.setattr(settings, "scraper_proxy_url_env", "http://test-proxy.local:8080")
    mock_session = _mock_own_session_flow()
    captured: dict[str, Any] = {}

    def _fake_session(*args: Any, **kwargs: Any) -> MagicMock:
        captured.update(kwargs)
        return mock_session

    with patch("scraper_kit.providers._base.AsyncSession", _fake_session):
        asyncio.run(_call_kit_own_session(config=RealScraperConfig()))

    assert captured.get("proxies") == {
        "http": "http://test-proxy.local:8080",
        "https": "http://test-proxy.local:8080",
    }
    # #2386: сессия строится общей build_document_session — параметры те же, что были у
    # собственной (impersonate/timeout=25/document-заголовки).
    assert captured.get("impersonate") == DEFAULT_IMPERSONATE
    assert captured.get("timeout") == 25
    assert captured.get("headers") == DOCUMENT_HEADERS