mirror of
https://github.com/yogeshojha/rengine.git
synced 2026-10-20 23:31:31 +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
74 lines
2.3 KiB
Python
Executable File
74 lines
2.3 KiB
Python
Executable File
#!/usr/bin/env python3
|
|
"""Regenerate shared/definitions/data/port_registry.json from the IANA port registry."""
|
|
|
|
from __future__ import annotations
|
|
|
|
import csv
|
|
import io
|
|
import json
|
|
import re
|
|
import sys
|
|
import urllib.request
|
|
from pathlib import Path
|
|
|
|
SOURCE = (
|
|
"https://www.iana.org/assignments/service-names-port-numbers/"
|
|
"service-names-port-numbers.csv"
|
|
)
|
|
TARGET = (
|
|
Path(__file__).resolve().parents[1] / "shared/definitions/data/port_registry.json"
|
|
)
|
|
PROTOCOLS = ("tcp",)
|
|
MAX_DESCRIPTION = 120
|
|
UNASSIGNED = {"", "reserved", "unassigned", "de-registered", "deregistered"}
|
|
|
|
_ALNUM = re.compile(r"[^a-z0-9]")
|
|
_HOUSEKEEPING = re.compile(
|
|
r"\s*IANA assigned this well-formed service name as a replacement for.*$", re.I
|
|
)
|
|
|
|
|
|
def _same(a: str, b: str) -> bool:
|
|
return _ALNUM.sub("", a.lower()) == _ALNUM.sub("", b.lower())
|
|
|
|
|
|
def build(raw: str) -> dict[str, list[str]]:
|
|
out: dict[str, list[str]] = {}
|
|
for row in csv.DictReader(io.StringIO(raw)):
|
|
if (row["Transport Protocol"] or "").strip().lower() not in PROTOCOLS:
|
|
continue
|
|
number = (row["Port Number"] or "").strip()
|
|
name = (row["Service Name"] or "").strip().lower()
|
|
description = _HOUSEKEEPING.sub(
|
|
"", " ".join((row["Description"] or "").split())
|
|
)
|
|
if not number.isdigit() or not name or number in out:
|
|
continue
|
|
if description.lower() in UNASSIGNED or len(description) > MAX_DESCRIPTION:
|
|
continue
|
|
out[number] = [name] if _same(description, name) else [name, description]
|
|
return out
|
|
|
|
|
|
def main() -> int:
|
|
with urllib.request.urlopen(SOURCE, timeout=60) as response: # noqa: S310
|
|
raw = response.read().decode("utf-8")
|
|
registry = build(raw)
|
|
if len(registry) < 4000: # noqa: PLR2004
|
|
print(
|
|
f"refusing to write a suspiciously small registry ({len(registry)} ports)"
|
|
)
|
|
return 1
|
|
TARGET.parent.mkdir(parents=True, exist_ok=True)
|
|
TARGET.write_text(
|
|
json.dumps(registry, separators=(",", ":"), sort_keys=True) + "\n",
|
|
encoding="utf-8",
|
|
)
|
|
described = sum(1 for entry in registry.values() if len(entry) > 1)
|
|
print(f"{TARGET}: {len(registry)} ports, {described} with a description")
|
|
return 0
|
|
|
|
|
|
if __name__ == "__main__":
|
|
sys.exit(main())
|