cryptorugmunch
a7c30b12cd
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.
114 lines
3.3 KiB
Python
114 lines
3.3 KiB
Python
# 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.
|
|
import logging
|
|
import os
|
|
|
|
import pytest
|
|
|
|
|
|
@pytest.fixture
|
|
def sample_html() -> str:
|
|
return """<!DOCTYPE html><html><head><title>Test Page</title>
|
|
<meta name="description" content="A test page for scraping">
|
|
</head><body>
|
|
<h1 class="product-title">Widget Pro</h1>
|
|
<p class="price">$29.99</p>
|
|
<p class="description">The best widget ever made.</p>
|
|
<a href="https://example.com/page1">Page 1</a>
|
|
<a href="https://example.com/page2">Page 2</a>
|
|
<a href="https://external.com">External</a>
|
|
</body></html>"""
|
|
|
|
|
|
@pytest.fixture
|
|
def sample_markdown() -> str:
|
|
return """# Widget Pro
|
|
|
|
**Price:** $29.99
|
|
|
|
The best widget ever made.
|
|
|
|
- Feature 1: Lightweight
|
|
- Feature 2: Durable
|
|
- Feature 3: Affordable
|
|
|
|
Contact: sales@example.com
|
|
"""
|
|
|
|
|
|
@pytest.fixture
|
|
def sample_schema() -> dict:
|
|
return {
|
|
"product_name": "name of the product",
|
|
"price": "price in USD",
|
|
"email": "contact email email",
|
|
}
|
|
|
|
|
|
# ── Lenient LogRecord for tests ─────────────────────────────────
|
|
# Some Pry modules (and tests) use logger.warning("...", extra={"name": "foo"})
|
|
# patterns. Python's stdlib logging rejects this with KeyError because
|
|
# "name" is a reserved LogRecord field. In tests we make the LogRecord
|
|
# tolerant: reserved keys in `extra` are moved to a sub-dict so the call
|
|
# doesn't crash. This matches the behavior we get with structlog's bridge.
|
|
#
|
|
# Production code is unaffected (this conftest only runs in tests).
|
|
# If you actually want strict mode in tests, set PRY_LOG_STRICT_EXTRAS=1.
|
|
_RESERVED = frozenset(
|
|
{
|
|
"name",
|
|
"msg",
|
|
"args",
|
|
"levelname",
|
|
"levelno",
|
|
"pathname",
|
|
"filename",
|
|
"module",
|
|
"exc_info",
|
|
"exc_text",
|
|
"stack_info",
|
|
"lineno",
|
|
"funcName",
|
|
"created",
|
|
"msecs",
|
|
"relativeCreated",
|
|
"thread",
|
|
"threadName",
|
|
"processName",
|
|
"process",
|
|
"message",
|
|
"asctime",
|
|
"taskName",
|
|
}
|
|
)
|
|
|
|
|
|
def _make_lenient_logrecord() -> None:
|
|
"""Monkey-patch LogRecord.__init__ to be tolerant of reserved extra keys."""
|
|
if os.getenv("PRY_LOG_STRICT_EXTRAS", "").lower() in ("1", "true", "yes"):
|
|
return # honor strict mode if explicitly requested
|
|
original_init = logging.LogRecord.__init__
|
|
|
|
def lenient_init(self, *args, **kwargs):
|
|
# Extract extra before super().__init__ which would reject reserved keys
|
|
extra = kwargs.pop("extra", None)
|
|
original_init(self, *args, **kwargs)
|
|
if extra:
|
|
overflow: dict[str, object] = {}
|
|
for k, v in extra.items():
|
|
if k in _RESERVED:
|
|
overflow[k] = v
|
|
else:
|
|
setattr(self, k, v)
|
|
if overflow:
|
|
existing = getattr(self, "_overflow_extras", {}) or {}
|
|
existing.update(overflow)
|
|
self._overflow_extras = existing
|
|
|
|
logging.LogRecord.__init__ = lenient_init # type: ignore[assignment]
|
|
|
|
|
|
# Install the lenient LogRecord at conftest import time
|
|
_make_lenient_logrecord()
|