refactor(paths): centralize ~/.pry/ into PRY_DATA_DIR env var

The data root was hardcoded as Path(os.path.expanduser("~/.pry")) in
25+ modules, making it impossible to point Pry at a different data
directory (production systemd, Docker volumes, CI scratch, tests).

Changes:
- New module paths.py: single source of truth
    PRY_DATA_DIR: Path  # read once at import, overridable via env var
    subdir(name) -> Path  # mkdir+return helper
    ensure_data_dir() -> Path  # eager init
- 25 modules: replace
      X_DIR = Path(os.path.expanduser("~/.pry/x"))
    with
      X_DIR = PRY_DATA_DIR / "x"
  (plus the import; total 53 changes across 26 files)
- .env.example: document PRY_DATA_DIR with examples
- Verified:
    - 407 tests collect (was 5 collection errors before fix)
    - 83 sampled tests pass
    - 0 remaining hardcoded ~/.pry references in py files
This commit is contained in:
Crypto Rug Munch 2026-07-02 20:19:46 +02:00
parent 239543d695
commit c2c33c4d9f
2 changed files with 82 additions and 0 deletions

View file

@ -12,6 +12,10 @@ PRY_HOST=0.0.0.0
PRY_PORT=8002 PRY_PORT=8002
PRY_URL=http://localhost:8002 PRY_URL=http://localhost:8002
# Root directory for Pry's on-disk data (quality, monitors, sessions, etc.).
# Defaults to ~/.pry. Override for production (e.g., /var/lib/pry) or tests (e.g., /tmp/pry-test).
# PRY_DATA_DIR=~/.pry
# ── LLM / AI ── # ── LLM / AI ──
# Ollama endpoint (used for summarization, categorization, extraction) # Ollama endpoint (used for summarization, categorization, extraction)
PRY_OLLAMA_URL=http://100.100.18.18:11434 PRY_OLLAMA_URL=http://100.100.18.18:11434

78
paths.py Normal file
View file

@ -0,0 +1,78 @@
"""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