Mass ruff auto-fix:
- ruff check --fix: 109 issues fixed (F401 unused imports,
I001 unsorted imports, UP037 quoted annotations, SIM105
suppressible exception, RUF100 unused-noqa)
- ruff check --fix --unsafe-fixes: 22 additional issues
- ruff format: 70 files reformatted
- Manual pass: fix 16 misplaced import httpx lines
- Manual pass: fix remaining E402 (import-after-docstring)
Result: 283 errors -> 30 errors.
The remaining 30 are real issues that need manual review:
5 F401 unused-import (likely auto-generated stubs)
5 F821 undefined-name (real bugs in code that references
redis/pydantic/LLMRegistry without imports)
3 BLE001 (the compliance LLM fallback is intentional; the
other two are real)
3 RUF012 mutable-class-default
3 SIM105, 3 SIM117, 2 E722, 2 E741
1 B007, 1 B025, 1 E402, 1 RUF200 (pyproject.toml issue)
Tests: 436/437 pass (1 pre-existing SSE sandbox failure).
format check + import sort: now clean.
make ci: still gated on the 30 remaining real issues.
Follow-up: triage the 30 issues file-by-file.
79 lines
2 KiB
Python
79 lines
2 KiB
Python
"""Pry - centralized data-directory resolution.
|
|
|
|
Single source of truth for the on-disk data root. Override at runtime via
|
|
the PRY_DATA_DIR environment variable.
|
|
|
|
Examples:
|
|
PRY_DATA_DIR=/var/lib/pry # systemd / docker production
|
|
PRY_DATA_DIR=/tmp/pry-test-$$ # CI scratch space
|
|
|
|
All other modules should import PRY_DATA_DIR (or use subdir(name)) instead
|
|
of hardcoding Path("~/.pry/x").
|
|
|
|
Part of Pry - https://git.rugmunch.io/RugMunchMedia/pryscraper
|
|
Licensed under MIT. See LICENSE.
|
|
"""
|
|
|
|
# SPDX-License-Identifier: MIT
|
|
# Copyright (c) 2026 Rug Munch Media LLC
|
|
#
|
|
# Part of Pry - https://git.rugmunch.io/RugMunchMedia/pryscraper
|
|
# Licensed under MIT. See LICENSE.
|
|
from __future__ import annotations
|
|
|
|
import os
|
|
from pathlib import Path
|
|
|
|
# Single source of truth. Override with PRY_DATA_DIR env var.
|
|
PRY_DATA_DIR: Path = Path(os.getenv("PRY_DATA_DIR", "~/.pry")).expanduser().resolve()
|
|
|
|
# Known subdirectories. Not enforced - subdir() accepts any name - but
|
|
# useful for documentation and tooling that wants to enumerate them.
|
|
SUBDIRS: tuple[str, ...] = (
|
|
"accounts",
|
|
"actors",
|
|
"agency",
|
|
"commerce",
|
|
"costing",
|
|
"freshness",
|
|
"gdpr",
|
|
"gdpr_real",
|
|
"intel",
|
|
"jobs",
|
|
"llm_usage",
|
|
"monitors",
|
|
"pipelines",
|
|
"proxies",
|
|
"quality",
|
|
"referrals",
|
|
"reports",
|
|
"reports_real",
|
|
"reviews",
|
|
"seo",
|
|
"sessions",
|
|
"structure",
|
|
"training",
|
|
"vault",
|
|
"webhooks",
|
|
"x402",
|
|
)
|
|
|
|
|
|
def subdir(name: str) -> Path:
|
|
"""Get a subdirectory under PRY_DATA_DIR, creating it if needed.
|
|
|
|
Use this in modules that write files: `from paths import subdir; d = subdir("quality")`.
|
|
"""
|
|
path = PRY_DATA_DIR / name
|
|
path.mkdir(parents=True, exist_ok=True)
|
|
return path
|
|
|
|
|
|
def ensure_data_dir() -> Path:
|
|
"""Ensure PRY_DATA_DIR itself exists. Returns the path.
|
|
|
|
Call once at process startup if you want the root created eagerly
|
|
(e.g., before any subdir access).
|
|
"""
|
|
PRY_DATA_DIR.mkdir(parents=True, exist_ok=True)
|
|
return PRY_DATA_DIR
|