Refactor backend for cleaner error handling, DRY, and type safety

- Extract rate limiter DRY: consolidate 3 duplicated check/respond paths
  into _check_counter and _enforce_limit helpers, add proper type annotations
- Replace bare Exception raises with FloorplanDownloadError and
  RightmoveApiError; narrow catch clauses to specific exception types;
  fix Step base class to inherit from ABC
- Consolidate MAX_OCR_WORKERS into config/scraper_config.py; extract
  _find_tenure_value helper to deduplicate tenure parsing
- Extract _build_poi_distances_lookup from stream endpoint to reduce nesting
- Fix csv_exporter: optional decisions.json, NaN instead of -1 sentinels,
  guard against division by zero on missing square meters
- Fix notifications.py broken list[Surface]() constructor, database.py
  stale comments and missing type annotation, auth.py type:ignore,
  ui_exporter.py stale TODO
- Fix 3 pre-existing test failures: mock cache layer in streaming tests,
  bypass rate limiter for test isolation, fix cache invalidation test to
  account for two-pattern scan loop
This commit is contained in:
Viktor Barzin 2026-02-10 22:19:24 +00:00
parent 6897820cc7
commit f833309297
No known key found for this signature in database
GPG key ID: 0EB088298288D958
20 changed files with 199 additions and 178 deletions

View file

@ -70,7 +70,7 @@ async def test_step_failure_stops_pipeline(
processor = ListingProcessor(listing_repository)
processor.process_steps[0].needs_processing = AsyncMock(return_value=True)
processor.process_steps[0].process = AsyncMock(side_effect=RuntimeError("boom"))
processor.process_steps[0].process = AsyncMock(side_effect=ValueError("boom"))
processor.process_steps[1].needs_processing = AsyncMock(return_value=True)
processor.process_steps[1].process = AsyncMock()
processor.process_steps[2].needs_processing = AsyncMock(return_value=True)

View file

@ -156,7 +156,7 @@ class TestStreamingEndpoint:
@pytest.fixture
def client(self):
"""Create test client with mocked auth."""
"""Create test client with mocked auth and rate limiting bypassed."""
from fastapi.testclient import TestClient
from api.app import app
from api.auth import get_current_user, User
@ -165,13 +165,15 @@ class TestStreamingEndpoint:
return User(sub="test-id", email="test@example.com", name="Test User")
app.dependency_overrides[get_current_user] = mock_auth
yield TestClient(app)
with patch("api.rate_limiter._match_endpoint", return_value=None):
yield TestClient(app)
app.dependency_overrides.clear()
@pytest.fixture
def mock_repository(self):
"""Mock the repository methods."""
with patch("api.app.ListingRepository") as MockRepo:
"""Mock the repository methods and bypass cache."""
with patch("api.app.get_cached_count", return_value=None), \
patch("api.app.ListingRepository") as MockRepo:
mock_instance = MagicMock()
mock_instance.count_listings.return_value = 3
mock_instance.stream_listings_optimized.return_value = iter([

View file

@ -204,8 +204,12 @@ class TestInvalidateCache:
mock_client = mock.MagicMock()
mock_pipeline = mock.MagicMock()
mock_client.pipeline.return_value = mock_pipeline
# Simulate one scan iteration that returns keys, then done
mock_client.scan.return_value = (0, ["listings:geojson:abc", "listings:geojson:def"])
# invalidate_cache scans two patterns (CACHE_PREFIX*, STAGING_PREFIX*)
# First scan returns matching keys, second returns none
mock_client.scan.side_effect = [
(0, ["listings:geojson:abc", "listings:geojson:def"]),
(0, []),
]
mock_get_client.return_value = mock_client
invalidate_cache()

View file

@ -5,7 +5,7 @@ from unittest.mock import AsyncMock, MagicMock, patch
import pytest
from models.listing import ListingType, QueryParameters
from rec.exceptions import CircuitBreakerOpenError, ThrottlingError
from rec.exceptions import CircuitBreakerOpenError, InvalidResponseError, ThrottlingError
from services.listing_fetcher import (
NUM_WORKERS,
_fetch_subquery,
@ -227,7 +227,7 @@ class TestFetchSubquery:
with patch(
"services.listing_fetcher.listing_query",
new_callable=AsyncMock,
side_effect=Exception("GENERIC_ERROR: no more results"),
side_effect=InvalidResponseError("GENERIC_ERROR: no more results"),
):
ids_found = await _fetch_subquery(
sq=sq,

View file

@ -3,12 +3,12 @@ from datetime import datetime
from unittest.mock import AsyncMock, MagicMock, patch
import pytest
from models.listing import FurnishType, ListingType
from config.scraper_config import MAX_OCR_WORKERS
from listing_processor import (
_parse_furnish_type,
_parse_available_from,
ListingProcessor,
FetchListingDetailsStep,
MAX_OCR_WORKERS,
)
@ -77,7 +77,7 @@ class TestListingProcessor:
processor = ListingProcessor(mock_repo)
for step in processor.process_steps:
step.needs_processing = AsyncMock(return_value=True)
step.process = AsyncMock(side_effect=Exception("fail"))
step.process = AsyncMock(side_effect=ValueError("fail"))
result = await processor.process_listing(123)
assert result is None