f833309297
- 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
44 lines
1.5 KiB
Python
44 lines
1.5 KiB
Python
"""Floorplan detector service - OCR-based square meter detection."""
|
|
import asyncio
|
|
from config.scraper_config import MAX_OCR_WORKERS
|
|
from models import Listing
|
|
from rec import floorplan
|
|
from repositories.listing_repository import ListingRepository
|
|
from tqdm.asyncio import tqdm
|
|
|
|
|
|
async def detect_floorplan(repository: ListingRepository) -> None:
|
|
"""Detect square meters from floorplan images for all listings."""
|
|
listings = await repository.get_listings()
|
|
semaphore = asyncio.Semaphore(MAX_OCR_WORKERS)
|
|
|
|
updated_listings = [
|
|
listing
|
|
for listing in await tqdm.gather(
|
|
*[_calculate_sqm_ocr(listing, semaphore) for listing in listings]
|
|
)
|
|
if listing is not None
|
|
]
|
|
await repository.upsert_listings(updated_listings)
|
|
|
|
|
|
async def _calculate_sqm_ocr(
|
|
listing: Listing, semaphore: asyncio.Semaphore
|
|
) -> Listing | None:
|
|
"""Calculate square meters from floorplan images using OCR."""
|
|
if listing.square_meters is not None:
|
|
return None
|
|
if not listing.floorplan_image_paths:
|
|
listing.square_meters = 0
|
|
return listing
|
|
sqms: list[float] = []
|
|
for floorplan_path in listing.floorplan_image_paths:
|
|
async with semaphore:
|
|
estimated_sqm, _ = await asyncio.to_thread(
|
|
floorplan.calculate_ocr, floorplan_path
|
|
)
|
|
if estimated_sqm is not None:
|
|
sqms.append(estimated_sqm)
|
|
max_sqm = max(sqms, default=0) # try once, if we fail, keep as 0
|
|
listing.square_meters = max_sqm
|
|
return listing
|