mirror of
https://github.com/yogeshojha/rengine.git
synced 2026-10-20 07:11:28 +02:00
Yogesh OjhaandClaude Opus 5
2cb8d73280
The comment rule in CLAUDE.md is one line maximum, never narration: no multi-line blocks, no module-header explainers, no sentences that explain or justify the code to the reader. The tree had drifted a long way from it, and most of the drift is mine. Removed: 232 lines of multi-line comment blocks 203 single-line comments that argued instead of stating 154 comments joined by so/because/otherwise/rather-than 143 narrating comments in the frontend 112 test docstrings (the test name already says what it asserts) 25 test module docstrings and 25 decorative section dividers Collapsed: 324 multi-line docstrings to one factual line 271 one-line docstrings that had a justifying clause bolted on Kept: functional directives, section dividers, short field labels, alembic revision headers, and the eight FastAPI route docstrings that render in /docs. Where a fact was load-bearing it is in CLAUDE.md, which is where it belongs. 284 python tests and 34 frontend tests pass, ruff and ruff-format clean across ten packages, svelte-check 0 errors, prettier and eslint clean, app.main imports. Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_013dKUV96WkQQETZBMoAG98C
52 lines
1.5 KiB
Python
52 lines
1.5 KiB
Python
#!/usr/bin/env python3
|
|
"""Regenerate tools/data/subdomains.txt from SecLists' DNS discovery list."""
|
|
|
|
from __future__ import annotations
|
|
|
|
import argparse
|
|
import re
|
|
import sys
|
|
import urllib.request
|
|
from pathlib import Path
|
|
|
|
SOURCE = (
|
|
"https://raw.githubusercontent.com/danielmiessler/SecLists/master/"
|
|
"Discovery/DNS/subdomains-top1million-{size}.txt"
|
|
)
|
|
SIZES = (5000, 20000, 110000)
|
|
OUTPUT = Path(__file__).resolve().parent.parent / "tools" / "data" / "subdomains.txt"
|
|
|
|
_LABEL = re.compile(r"^[a-z0-9_](?:[a-z0-9_-]{0,61}[a-z0-9_])?$")
|
|
|
|
|
|
def fetch(size: int) -> list[str]:
|
|
with urllib.request.urlopen(SOURCE.format(size=size), timeout=60) as response: # noqa: S310
|
|
body = response.read().decode("utf-8", errors="replace")
|
|
seen: set[str] = set()
|
|
labels: list[str] = []
|
|
for raw in body.splitlines():
|
|
label = raw.strip().lower()
|
|
if not label or label in seen or not _LABEL.match(label):
|
|
continue
|
|
seen.add(label)
|
|
labels.append(label)
|
|
return labels
|
|
|
|
|
|
def main() -> int:
|
|
parser = argparse.ArgumentParser()
|
|
parser.add_argument("--size", type=int, default=5000, choices=SIZES)
|
|
args = parser.parse_args()
|
|
|
|
labels = fetch(args.size)
|
|
if len(labels) < args.size // 2:
|
|
print(f"only {len(labels)} usable labels, refusing to write", file=sys.stderr)
|
|
return 1
|
|
OUTPUT.write_text("\n".join(labels) + "\n")
|
|
print(f"wrote {OUTPUT} ({len(labels)} labels)")
|
|
return 0
|
|
|
|
|
|
if __name__ == "__main__":
|
|
raise SystemExit(main())
|