policy-nexus/tools/build_site.py
tegwick c1b60f322e
All checks were successful
Build and publish policy-nexus image / build-and-push (push) Successful in 1m10s
feat: publish Risk Nexus findings and methods
Assistant: codex
Assistant-Model: gpt-5.6-sol
Assistant-Session: 01a058f3-8ba0-7692-a042-9a870fc3d663
2026-09-01 01:56:46 +02:00

339 lines
14 KiB
Python

#!/usr/bin/env python3
"""Build the policy site atomically from an explicit source manifest."""
from __future__ import annotations
import argparse
import datetime as dt
import hashlib
import html
import json
import os
from pathlib import Path, PurePosixPath
import re
import shutil
import subprocess
import tempfile
from typing import Any
from render import STYLE, render_page, split_frontmatter
SOURCE_REVISION = re.compile(
r'<meta name="policy-source-revision" content="([^"]+)">'
)
SOURCE_DIGEST = re.compile(r'<meta name="policy-source-digest" content="([^"]+)">')
CLEAN_GIT_REVISION = re.compile(r"^[a-f0-9]{40}$")
def _safe_path(value: str) -> PurePosixPath:
path = PurePosixPath(value)
if path.is_absolute() or ".." in path.parts or not path.parts:
raise ValueError(f"unsafe publication path: {value!r}")
return path
def _source_revision(repo: Path, source: Path) -> str:
digest = hashlib.sha256(source.read_bytes()).hexdigest()
revision_env = "POLICY_NEXUS_SOURCE_REVISION_" + re.sub(
r"[^A-Z0-9]+", "_", repo.name.upper()
)
supplied_revision = os.environ.get(revision_env, "")
if supplied_revision:
if not CLEAN_GIT_REVISION.fullmatch(supplied_revision):
raise ValueError(
f"{revision_env} must be a clean 40-hex Git commit, got {supplied_revision!r}"
)
return supplied_revision
source_root = os.environ.get("POLICY_NEXUS_SOURCE_ROOT", "")
if source_root:
root = Path(source_root).resolve()
lock_path = root / "source-lock.json"
try:
lock = json.loads(lock_path.read_text(encoding="utf-8"))
locked_revision = lock["repositories"][repo.name]["revision"]
except (KeyError, OSError, TypeError, json.JSONDecodeError) as exc:
raise ValueError(
f"{repo.name}: source revision is missing from {lock_path}"
) from exc
if not isinstance(locked_revision, str) or not CLEAN_GIT_REVISION.fullmatch(
locked_revision
):
raise ValueError(
f"{repo.name}: locked source revision must be a clean 40-hex Git commit, "
f"got {locked_revision!r}"
)
return locked_revision
try:
head = subprocess.run(
["git", "-C", str(repo), "rev-parse", "HEAD"],
check=True,
capture_output=True,
text=True,
).stdout.strip()
relative = source.relative_to(repo)
dirty = subprocess.run(
["git", "-C", str(repo), "status", "--porcelain", "--", str(relative)],
check=True,
capture_output=True,
text=True,
).stdout.strip()
return f"{head}+working-tree.{digest[:12]}" if dirty else head
except (OSError, subprocess.CalledProcessError, ValueError):
return f"sha256:{digest}"
def _add_interval(reviewed: str, interval: str) -> dt.date:
date = dt.date.fromisoformat(reviewed)
match = re.fullmatch(r"([1-9][0-9]*)([dmy])", interval)
if not match:
raise ValueError(f"invalid review interval {interval!r}; expected Nd, Nm or Ny")
amount, unit = int(match.group(1)), match.group(2)
if unit == "d":
return date + dt.timedelta(days=amount)
months = amount * (12 if unit == "y" else 1)
month_index = date.month - 1 + months
year, month = date.year + month_index // 12, month_index % 12 + 1
month_lengths = (31, 29 if year % 4 == 0 and (year % 100 != 0 or year % 400 == 0) else 28,
31, 30, 31, 30, 31, 31, 30, 31, 30, 31)
return date.replace(year=year, month=month, day=min(date.day, month_lengths[month - 1]))
def load_manifest(path: Path) -> dict[str, Any]:
manifest = json.loads(path.read_text(encoding="utf-8"))
if manifest.get("schema_version") != 1:
raise ValueError("publication manifest schema_version must be 1")
if not manifest.get("documents"):
raise ValueError("publication manifest has no documents")
seen: set[PurePosixPath] = set()
for document in manifest["documents"]:
for raw in (
document["canonical_path"],
document["revision_path"].replace("{revision}", "revision"),
*document.get("legacy_paths", []),
):
path_value = _safe_path(raw)
if path_value in seen:
raise ValueError(f"duplicate publication path: {path_value}")
seen.add(path_value)
return manifest
def _redirect(target: str, title: str) -> str:
escaped = html.escape(target, quote=True)
return (
"<!doctype html><html lang=\"en\"><meta charset=\"utf-8\">"
f'<meta http-equiv="refresh" content="0; url={escaped}">'
f"<title>{html.escape(title)}</title>"
f'<p>Moved permanently to <a href="{escaped}">{escaped}</a>.</p></html>\n'
)
def repository_paths(manifest_path: Path, manifest: dict[str, Any]) -> dict[str, Path]:
"""Resolve local or fetched source checkouts for a publication manifest."""
source_root = os.environ.get("POLICY_NEXUS_SOURCE_ROOT")
paths: dict[str, Path] = {}
for name, config in manifest["repositories"].items():
fetched = (Path(source_root) / name).resolve() if source_root else None
paths[name] = (
fetched
if fetched is not None and fetched.is_dir()
else (manifest_path.parent / config["path"]).resolve()
)
return paths
def _index_page(site: dict[str, Any], records: list[dict[str, str]]) -> str:
rows = []
for record in records:
rows.append(
"<tr>"
f'<td><a href="/{html.escape(record["canonical_path"], quote=True)}">'
f'{html.escape(record["title"])}</a></td>'
f'<td>{html.escape(record["status"])}</td>'
f'<td>{html.escape(record["lifecycle"])}</td>'
f'<td>{html.escape(record["revision"])}</td>'
f'<td>{html.escape(record["owner"])}</td>'
f'<td>{html.escape(record["last_reviewed"])}</td>'
f'<td>{html.escape(record["review_due"])}</td>'
f'<td>{html.escape(record["currency"])}</td>'
"</tr>"
)
return (
"<!doctype html><html lang=\"en\"><meta charset=\"utf-8\">"
f"<title>{html.escape(site['title'])}</title><style>{STYLE.read_text()}</style>"
'<div class="wrap"><header><div class="eyebrow"><span>policy surface</span>'
"<span>generated from canonical sources — do not edit</span></div>"
f"<h1>{html.escape(site['title'])}</h1>"
'<p class="sub">Governing documents and public risk records at stable addresses, with visible currency.</p>'
"</header><main><table><thead><tr><th>Document</th><th>Status</th>"
"<th>Lifecycle</th><th>Revision</th><th>Owner</th><th>Reviewed</th>"
"<th>Review due</th><th>Currency</th>"
f"</tr></thead><tbody>{''.join(rows)}</tbody></table></main></div></html>\n"
)
def build(
manifest_path: Path,
output: Path,
*,
as_of: dt.date | None = None,
) -> list[dict[str, str]]:
manifest_path = manifest_path.resolve()
manifest = load_manifest(manifest_path)
as_of = as_of or dt.date.today()
resolved_repositories = repository_paths(manifest_path, manifest)
output_parent = output.resolve().parent
output_parent.mkdir(parents=True, exist_ok=True)
temporary = Path(tempfile.mkdtemp(prefix=f".{output.name}-", dir=output_parent))
if output.exists():
shutil.copytree(output, temporary, dirs_exist_ok=True)
records: list[dict[str, str]] = []
try:
for document in manifest["documents"]:
repo = resolved_repositories[document["source_repo"]]
source = (repo / document["source_path"]).resolve()
if not source.is_file() or repo not in source.parents:
raise FileNotFoundError(f"canonical source unavailable: {source}")
meta, _markdown = split_frontmatter(source.read_text(encoding="utf-8"))
if meta.get("id") != document["id"]:
raise ValueError(
f"{source}: manifest id {document['id']!r} does not match {meta.get('id')!r}"
)
if (
document["source_repo"] == "risk-nexus"
and meta.get("disclosure") != "public"
):
raise ValueError(
f"{source}: risk-nexus publications require disclosure: public"
)
for required_field in ("title", "status", "owner"):
if not meta.get(required_field):
raise ValueError(f"{source}: {required_field} is required for publication")
revision = meta.get("revision") or meta.get("version")
if not revision:
raise ValueError(f"{source}: revision or version is required")
source_revision = _source_revision(repo, source)
source_digest = hashlib.sha256(source.read_bytes()).hexdigest()
reviewed = meta.get("last_reviewed") or meta.get("updated")
interval = document.get("review_interval") or meta.get("review_interval")
if not reviewed or not interval:
raise ValueError(f"{source}: review date and interval are required")
review_due = _add_interval(reviewed, interval)
lifecycle = document.get("lifecycle", "active")
if lifecycle not in {"active", "superseded", "withdrawn"}:
raise ValueError(
f"{document['id']}: lifecycle must be active, superseded or withdrawn"
)
successor = document.get("successor", "")
if lifecycle == "superseded" and not successor:
raise ValueError(f"{document['id']}: superseded documents require successor")
publication = {
"source_repo": document["source_repo"],
"source_path": document["source_path"],
"source_revision": source_revision,
"source_digest": source_digest,
"review_due": review_due.isoformat() if review_due else "",
}
revision_page, meta, _sections = render_page(
source,
subtitle=document.get("subtitle", ""),
publication=publication,
)
current_publication = publication | {
"lifecycle": lifecycle,
"successor": successor,
"stale": "true" if review_due and review_due < as_of else "false",
}
current_page, _current_meta, _current_sections = render_page(
source,
subtitle=document.get("subtitle", ""),
publication=current_publication,
)
canonical = _safe_path(document["canonical_path"])
revision_path = _safe_path(document["revision_path"].format(revision=revision))
revision_target = temporary / revision_path
if revision_target.exists():
existing_revision = revision_target.read_text(encoding="utf-8")
old_revision = SOURCE_REVISION.search(existing_revision)
old_digest = SOURCE_DIGEST.search(existing_revision)
if not old_revision or not old_digest:
raise RuntimeError(
f"immutable revision {revision_path} has incomplete source metadata"
)
if html.unescape(old_digest.group(1)) != source_digest:
raise RuntimeError(
f"immutable revision {revision_path} already records content digest "
f"{old_digest.group(1)}; source is now {source_digest}. "
"Publish a new revision id."
)
canonical_target = temporary / canonical
canonical_target.parent.mkdir(parents=True, exist_ok=True)
canonical_target.write_text(current_page, encoding="utf-8")
if not revision_target.exists():
revision_target.parent.mkdir(parents=True, exist_ok=True)
revision_target.write_text(revision_page, encoding="utf-8")
for legacy in document.get("legacy_paths", []):
target = temporary / _safe_path(legacy)
target.parent.mkdir(parents=True, exist_ok=True)
canonical_url = "/" + canonical.as_posix()
target.write_text(_redirect(canonical_url, meta["title"]), encoding="utf-8")
records.append(
{
"id": document["id"],
"title": meta["title"],
"status": meta["status"],
"revision": revision,
"owner": meta["owner"],
"last_reviewed": reviewed,
"review_due": review_due.isoformat(),
"currency": "stale" if review_due < as_of else "current",
"lifecycle": lifecycle,
"canonical_path": canonical.as_posix(),
"revision_path": revision_path.as_posix(),
"source_repo": document["source_repo"],
"source_path": document["source_path"],
"source_revision": source_revision,
"source_digest": source_digest,
}
)
(temporary / "index.html").write_text(
_index_page(manifest["site"], records), encoding="utf-8"
)
(temporary / "publication-manifest.json").write_text(
json.dumps(
{
"schema_version": 1,
"generated_as_of": as_of.isoformat(),
"documents": records,
},
indent=2,
sort_keys=True,
)
+ "\n",
encoding="utf-8",
)
if output.exists():
shutil.rmtree(output)
os.replace(temporary, output)
except BaseException:
shutil.rmtree(temporary, ignore_errors=True)
raise
return records
def main() -> int:
parser = argparse.ArgumentParser()
parser.add_argument("manifest", type=Path)
parser.add_argument("--output", type=Path, default=Path("build"))
parser.add_argument("--as-of", type=dt.date.fromisoformat)
args = parser.parse_args()
records = build(args.manifest, args.output, as_of=args.as_of)
print(f"{args.output}: published {len(records)} document(s)")
return 0
if __name__ == "__main__":
raise SystemExit(main())