prometheus/service/server.js
Local Dev 9f16ce3128 prometheus: weekly s3 snapshot of the browse surface to bns/prometheus
scripts/snapshot.mjs renders every public page (home, browse, publish,
boundaries, 8 categories, every active listing) to <out>/<path>/index.html,
plus /sitemap.xml, /robots.txt, and the two static assets. Writing to a
directory next to the service AND uploading via `aws s3 sync` are two
flags on the same command: --out to pick the directory, --upload to push.

Live routes added for /sitemap.xml and /robots.txt so a crawler hitting
the live service sees the same enumeration the snapshot bakes into the
bucket. renderSitemap / renderRobots in service/seo.js are the single
rendering path both call sites use.

Scope deliberately limited to the browse surface — /submit and the API
routes depend on the live backend and were never going to work on a
static mirror. The browse surface IS what the fallback is for: readers
survive an outage, publishers can't.

systemd unit + timer under deploy/ run the snapshot weekly on Sunday
04:00 UTC with 30 min jitter and Persistent=yes so a missed run after a
reboot catches up. Unit uses the sia-storage AWS profile per
[[sia-storage-credentials-location]] and the per-process endpoint URL
baked in via Environment=.

Local dry-run against an empty DB produced 14 HTML files + sitemap +
robots + the two assets.
2026-10-08 21:42:54 +02:00

281 lines
9 KiB
JavaScript

/**
* Prometheus HTTP server.
*
* One `node:http` listener, a map-based router for page routes, and a tiny
* static-file handler for /static/*. No framework, no templating engine —
* the response-rendering path for a page is: look up the handler, call it,
* wrap the result in `layout()`, flush. If any step of that stops reading
* at a glance, we have gotten too clever.
*
* Dynamic routes land here later: /api/upload, /api/manifest, /api/publish,
* /api/pay, /admin/*. For now the server is only serving pages, so the
* router is only pages.
*/
import { createServer } from 'node:http';
import { createReadStream, statSync } from 'node:fs';
import { fileURLToPath } from 'node:url';
import { dirname, normalize, resolve } from 'node:path';
import { layout } from './layout.js';
import * as pages from './pages.js';
import { handleUpload } from './uploads.js';
import { clamdPing } from './clamd.js';
import { publicKeyBase64, loadServiceKey } from './signing.js';
import {
handleListingCreate,
handleListingIndex,
handleListingGet,
} from './listings.js';
import { categoryPage, appPage, CATEGORIES } from './pages-browse.js';
import { handleAdmin } from './admin.js';
import { renderSitemap, renderRobots } from './seo.js';
import { allActiveListings } from './db.js';
const PORT = Number(process.env.PORT) || 3700;
const BIND = process.env.BIND || '127.0.0.1';
// Load the service key on startup so a missing-key problem shows up in the
// terminal when the operator reads the launch log, not under a POST later.
loadServiceKey();
const SELF = fileURLToPath(import.meta.url);
const SERVICE_DIR = dirname(SELF);
const PUBLIC_DIR = resolve(SERVICE_DIR, '..', 'public');
/**
* The page router.
*
* Exact-match paths first. Patterns (category pages, listing detail) will
* attach here when the browse milestone lands.
*/
const PAGE_ROUTES = {
'/': pages.home,
'/publish': pages.publish,
'/browse': pages.browse,
'/submit': pages.submit,
'/boundaries': pages.boundaries,
};
/**
* Content types for static files. Deliberately short — if the server
* learns to serve a type that is not here, add it here rather than
* reaching for `mime-types`.
*/
const MIME = {
'.css': 'text/css; charset=utf-8',
'.svg': 'image/svg+xml',
'.js': 'text/javascript; charset=utf-8',
'.png': 'image/png',
'.ico': 'image/x-icon',
'.woff2': 'font/woff2',
'.txt': 'text/plain; charset=utf-8',
};
/* ============ server ============ */
const server = createServer(async (req, res) => {
const started = Date.now();
const url = normalizeRequestUrl(req.url);
try {
if (url.startsWith('/static/')) {
await serveStatic(url.slice('/static/'.length), res);
} else if (url === '/api/upload') {
await handleUpload(req, res);
} else if (url === '/api/listing') {
await handleListingCreate(req, res);
} else if (url === '/api/listings') {
handleListingIndex(req, res, req.url);
} else if (url.startsWith('/api/listings/')) {
handleListingGet(req, res, req.url);
} else if (url === '/healthz') {
await serveHealth(res);
} else if (url === '/.well-known/prometheus-service-key.json') {
serveServiceKey(res);
} else if (url === '/sitemap.xml') {
serveSitemap(res);
} else if (url === '/robots.txt') {
serveRobots(res);
} else if (url === '/admin' || url.startsWith('/admin/')) {
await handleAdmin(req, res, url);
} else if (url.startsWith('/c/')) {
const slug = url.slice('/c/'.length);
servePageFn(() => categoryPage(req, slug), res);
} else if (url.startsWith('/app/')) {
// /app/<publisher>/<slug>
const parts = url.slice('/app/'.length).split('/').filter(Boolean);
if (parts.length === 2) {
servePageFn(() => appPage(req, parts[0], parts[1]), res);
} else {
servePage(pages.notFound, res, 404, req);
}
} else if (PAGE_ROUTES[url]) {
servePage(PAGE_ROUTES[url], res);
} else {
servePage(pages.notFound, res, 404, req);
}
} catch (err) {
// The response-level error log is intentionally short — a stack trace
// in the terminal is for the operator, not every reader.
console.error('[prometheus] 500', req.method, url, err?.message || err);
if (!res.headersSent) {
res.writeHead(500, { 'content-type': 'text/plain; charset=utf-8' });
}
res.end('internal error\n');
}
res.on('close', () => {
const ms = Date.now() - started;
console.log(`[prometheus] ${res.statusCode} ${req.method} ${url} ${ms}ms`);
});
});
server.listen(PORT, BIND, () => {
console.log(`[prometheus] listening on http://${BIND}:${PORT}`);
});
/* ============ helpers ============ */
/**
* Trim query/hash, decode once, collapse any `..` to its parent.
* Returns a leading-slash path.
*/
function normalizeRequestUrl(raw) {
const [path] = String(raw || '/').split('?');
const decoded = decodeURIComponent(path);
// normalize + leading-slash enforcement means `/foo/..//bar` → `/bar`.
// On Windows, node:path/normalize uses backslashes; convert back.
const normalized = normalize(decoded).replaceAll('\\', '/');
return normalized.startsWith('/') ? normalized : '/' + normalized;
}
/**
* Render a page function to the response.
*/
function servePage(fn, res, status = 200, req = null) {
const page = fn(req);
renderPage(page, res, status);
}
/**
* Render a page object (not a function). Used by routes that take extra
* arguments to produce the page (category slug, app publisher/slug) and
* therefore need to call the generator themselves rather than hand a bare
* reference to servePage.
*/
function servePageFn(produce, res) {
const page = produce();
// A `notFound()` return has this exact title; routes use it as the convention
// for "the thing you asked for does not exist" so we don't need a parallel
// status plumbing path.
const status = page.title === 'Not here' ? 404 : 200;
renderPage(page, res, status);
}
function renderPage(page, res, status) {
const html = layout(page);
res.writeHead(status, {
'content-type': 'text/html; charset=utf-8',
'cache-control': 'public, max-age=60',
});
res.end(html);
}
/**
* `/healthz` — JSON probe for operators and uptime checks. Says whether
* clamd (or the mock) is reachable; the HTTP status alone is enough for
* an opinionated monitor.
*/
async function serveHealth(res) {
const scanner = await clamdPing();
const ok = scanner.ok === true;
const body = JSON.stringify({ ok, scanner });
res.writeHead(ok ? 200 : 503, {
'content-type': 'application/json; charset=utf-8',
'cache-control': 'no-store',
'content-length': Buffer.byteLength(body),
});
res.end(body);
}
/**
* `/.well-known/prometheus-service-key.json` — the public key callers use to
* verify scan reports. Lives at a well-known path so clients can cache it by
* origin.
*/
function serveSitemap(res) {
const listings = allActiveListings().map((r) => ({
publisher: r.publisher, slug: r.slug, lastmod: r.created_at,
}));
const xml = renderSitemap({ categories: CATEGORIES.map((c) => c.slug), listings });
res.writeHead(200, {
'content-type': 'application/xml; charset=utf-8',
'cache-control': 'public, max-age=600',
'content-length': Buffer.byteLength(xml),
});
res.end(xml);
}
function serveRobots(res) {
const body = renderRobots();
res.writeHead(200, {
'content-type': 'text/plain; charset=utf-8',
'cache-control': 'public, max-age=600',
'content-length': Buffer.byteLength(body),
});
res.end(body);
}
function serveServiceKey(res) {
const body = JSON.stringify({
service: 'prometheus',
alg: 'ed25519',
pubkey: publicKeyBase64(),
issued_by: 'https://prometheus.x',
}, null, 2);
res.writeHead(200, {
'content-type': 'application/json; charset=utf-8',
'cache-control': 'public, max-age=3600',
'content-length': Buffer.byteLength(body),
});
res.end(body);
}
/**
* Serve a file from PUBLIC_DIR by relative path. The caller passes a
* path with no leading slash and no `..`; this double-checks via
* path.resolve against PUBLIC_DIR and refuses anything that escapes.
*/
async function serveStatic(relPath, res) {
const full = resolve(PUBLIC_DIR, relPath);
if (!full.startsWith(PUBLIC_DIR + '\\') && !full.startsWith(PUBLIC_DIR + '/')) {
res.writeHead(400, { 'content-type': 'text/plain' });
res.end('bad path\n');
return;
}
let st;
try {
st = statSync(full);
} catch {
res.writeHead(404, { 'content-type': 'text/plain' });
res.end('not found\n');
return;
}
if (!st.isFile()) {
res.writeHead(404, { 'content-type': 'text/plain' });
res.end('not found\n');
return;
}
const ext = '.' + relPath.split('.').pop();
const mime = MIME[ext] || 'application/octet-stream';
res.writeHead(200, {
'content-type': mime,
// Static assets are versioned in the URL (`?v=1`), so a long cache is
// safe and the only way to make the viewport snappy on repeat visits.
'cache-control': 'public, max-age=31536000, immutable',
'content-length': st.size,
});
createReadStream(full).pipe(res);
}