54dbc77348
ОТКРЫТИЕ: stdlib urllib проходит WAF nspd.gov.ru (TLS-fingerprint stdlib отличается от mainstream HTTP-clients). Это позволяет полностью убрать Playwright + Chromium для NSPD-задач. * nspd_lite.py: urllib + ssl._create_unverified_context(). 4 публичных fetcher'а (geoportal/quarter/parcel/building) + fetch_via_rosreestr2coord fallback на community-lib * schema 77: nspd_geo_jobs (журнал) + nspd_geo_targets (cad-номера со статусом pending/done/failed). Resume-state в БД. * tasks/nspd_geo.py: Celery task process_nspd_geo_job(job_id). Heartbeat каждые 5 items, WAF backoff 30s × 2^N (max 8 → paused). UPSERT в cad_quarters_geom / cad_buildings → идемпотентно. * worker_ready hook: stale jobs (>10min без heartbeat) автоматически re-enqueue после redeploy. Никаких потерь прогресса. * 4 admin endpoint + UI /admin/scrape/geo с формой запуска (manual_list / rosreestr_pending для авто-наполнения из ДДУ-кварталов), progress-bars и cancel/resume кнопками per job. * settings: use_nspd_lite=True, nspd_lite_rate_ms=600. * dep: rosreestr2coord>=4.0.0 (community lib для fallback). TODO следующих шагов: - smoke-test на проде через SSH (validation RU-IP не банит urllib) - feature toggle USE_NSPD_LITE в scrape_nspd.py для переключения с старого Playwright-пути - docker lean image (-300 MB после убирания Chromium) - расширение SCRAPE_NSPD_DEFAULT_REGIONS на 66,74,72,59 (Челябинск/Тюмень/Пермь)
81 lines
2.1 KiB
TOML
81 lines
2.1 KiB
TOML
[project]
|
|
name = "gendesign-backend"
|
|
version = "0.1.0"
|
|
description = "Generative Design + Site Finder backend (FastAPI)"
|
|
requires-python = ">=3.12"
|
|
dependencies = [
|
|
"fastapi>=0.115.0",
|
|
"uvicorn[standard]>=0.30.0",
|
|
"sqlalchemy>=2.0.30",
|
|
"geoalchemy2>=0.15.0",
|
|
"alembic>=1.13.0",
|
|
"pydantic>=2.7.0",
|
|
"pydantic-settings>=2.3.0",
|
|
"psycopg[binary]>=3.2.0",
|
|
"shapely>=2.0.0",
|
|
"geopandas>=1.0.0",
|
|
"pyproj>=3.6.0",
|
|
"httpx>=0.27.0",
|
|
"redis>=5.0.0",
|
|
"celery>=5.4.0",
|
|
"playwright>=1.45.0",
|
|
"tenacity>=9.0.0",
|
|
"pillow>=10.4.0",
|
|
"weasyprint>=62.0",
|
|
"ezdxf>=1.3.0",
|
|
"openpyxl>=3.1.0",
|
|
"pandas>=2.2.0",
|
|
"numpy>=2.0.0",
|
|
"scikit-learn>=1.5.0",
|
|
"sentry-sdk[fastapi]>=2.10.0",
|
|
"rosreestr2coord>=4.0.0",
|
|
]
|
|
|
|
[dependency-groups]
|
|
dev = [
|
|
"pytest>=8.0.0",
|
|
"pytest-asyncio>=0.23.0",
|
|
"ruff>=0.5.0",
|
|
"mypy>=1.10.0",
|
|
"types-redis>=4.6.0",
|
|
"pre-commit>=3.7.0",
|
|
]
|
|
|
|
[tool.uv]
|
|
package = true
|
|
|
|
# Tell setuptools which directory IS the Python package.
|
|
# Without this, having both `app/`, `alembic/`, `db/` at top level confuses
|
|
# auto-discovery: "Multiple top-level packages discovered in a flat-layout".
|
|
# We only want to package `app/`. `alembic/` and `db/` are operational, not Python packages.
|
|
[tool.setuptools.packages.find]
|
|
include = ["app*"]
|
|
|
|
[tool.ruff]
|
|
target-version = "py312"
|
|
line-length = 100
|
|
|
|
[tool.ruff.lint]
|
|
select = ["E", "F", "I", "B", "UP", "N", "RUF", "ASYNC"]
|
|
# RUF001/002/003 — ambiguous Unicode (Cyrillic vs Latin lookalikes).
|
|
# Off because the project is Russian-language; comments/docstrings legitimately use Cyrillic.
|
|
ignore = ["RUF001", "RUF002", "RUF003"]
|
|
|
|
[tool.mypy]
|
|
python_version = "3.12"
|
|
strict_optional = true
|
|
warn_unused_ignores = true
|
|
|
|
# strict только для core-модулей (правило из памяти Validation_Findings_Apr25)
|
|
[[tool.mypy.overrides]]
|
|
module = [
|
|
"app.services.generative.geometry",
|
|
"app.services.generative.teap",
|
|
"app.services.generative.financial",
|
|
"app.services.site_finder.scorer",
|
|
]
|
|
strict = true
|
|
|
|
[tool.pytest.ini_options]
|
|
testpaths = ["tests"]
|
|
asyncio_mode = "auto"
|