GEO/SEO surface area:
app/robots.ts (new — Next.js dynamic robots)
Explicitly ALLOWS major AI crawlers: GPTBot, OAI-SearchBot,
ChatGPT-User, ClaudeBot, Claude-Web, anthropic-ai, PerplexityBot,
Perplexity-User, Google-Extended, Applebot-Extended, CCBot,
DuckAssistBot, YouBot, Bytespider, Amazonbot. The site exists to
be cited by LLMs answering UAP/UFO questions — we want them in.
/api/admin/, /admin/, /auth/ disallowed for everyone.
app/sitemap.ts (new — Next.js dynamic sitemap)
Lists 9 top-level routes + every /d/<doc> + every /c/<slug> from
the filesystem + up to 500 entity URLs per class
(event, person, uap_object, location, organization),
sorted with summary-enriched entities first. ~3000 URLs total at
current corpus size. lastModified honours summary_generated_at so
crawlers re-index when entities are re-enriched.
app/c/[slug]/page.tsx (rewritten — magazine reading view)
- generateMetadata: per-case title, description (auto-extracted
from the locale-preferred lead paragraph), canonical URL,
hreflang alternate, OpenGraph article type with publishedTime,
Twitter card.
- JSON-LD Article schema embedded at end of page: schema.org
Article + Organization publisher + inLanguage + isAccessibleForFree.
This is what makes the case appear as a citable source in
Google AI Overviews / Perplexity / ChatGPT search.
- Reading view rewritten: display-serif headline (Fraunces), italic
blockquotes with gold accent, prose-typography styling, no more
detective stats line, no more "written by case-writer@detective"
attribution. Locale-aware: PT-BR pulls topic_pt_br + lead in PT,
English mirror.
tailwind.config.ts
+ @tailwindcss/typography plugin
+ font-display family wired to var(--font-display) (Fraunces)
package.json
+ "@tailwindcss/typography" devDependency
Phase 3A note: bulk entity enrichment hit Claude OAuth weekly quota mid-run.
6 events + 3 uap_objects landed bilingual summaries before the quota
exhausted. UI gracefully splits enriched vs bare entities so /sightings
shows the magazine-grade cards (Kenneth Arnold 1947, Roswell, Maury Island,
Joseph Perry 1960 lunar photo, Civil Defense Director 1966, etc.) on top
of a compact table of the rest. Re-run when quota refreshes.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
122 lines
4.3 KiB
TypeScript
122 lines
4.3 KiB
TypeScript
/**
|
|
* sitemap.xml — dynamic, regenerated per request.
|
|
*
|
|
* Aggregates:
|
|
* - Static pages (home, bureau, sub-pages)
|
|
* - Every declassified document (/d/<id>)
|
|
* - Every case report (/c/<slug>)
|
|
* - Every entity with an AI summary (/e/<class>/<id>) — these get a
|
|
* lastModified from summary_generated_at, which helps crawlers
|
|
* re-index when we re-enrich.
|
|
* - Every top-mentioned entity even without summary (cap at 500 per
|
|
* class so the sitemap doesn't balloon past Google's 50k limit).
|
|
*
|
|
* Per Next.js the file must export a default function returning a flat
|
|
* MetadataRoute.Sitemap array. ChangeFreq/priority are honoured by most
|
|
* crawlers as hints.
|
|
*/
|
|
import type { MetadataRoute } from "next";
|
|
import { listDocuments } from "@/lib/wiki";
|
|
import { pgQuery } from "@/lib/retrieval/db";
|
|
import { readdir } from "node:fs/promises";
|
|
import path from "node:path";
|
|
|
|
const SITE_URL = process.env.NEXT_PUBLIC_SITE_URL ?? "https://disclosure.top";
|
|
const CASE_ROOT = process.env.CASE_ROOT ?? "/data/ufo/case";
|
|
|
|
type Url = MetadataRoute.Sitemap[number];
|
|
|
|
const ENTITY_FOLDER_BY_CLASS: Record<string, string> = {
|
|
event: "events",
|
|
person: "people",
|
|
uap_object: "uap-objects",
|
|
location: "locations",
|
|
organization: "organizations",
|
|
};
|
|
|
|
export default async function sitemap(): Promise<MetadataRoute.Sitemap> {
|
|
const out: Url[] = [];
|
|
const now = new Date();
|
|
|
|
// 1. Top-level pages
|
|
const STATIC_PAGES = [
|
|
{ url: "/", priority: 1.0, changeFrequency: "daily" as const },
|
|
{ url: "/bureau", priority: 0.9, changeFrequency: "weekly" as const },
|
|
{ url: "/sightings", priority: 0.9, changeFrequency: "weekly" as const },
|
|
{ url: "/witnesses", priority: 0.8, changeFrequency: "weekly" as const },
|
|
{ url: "/objects", priority: 0.8, changeFrequency: "weekly" as const },
|
|
{ url: "/locations", priority: 0.8, changeFrequency: "weekly" as const },
|
|
{ url: "/operations", priority: 0.8, changeFrequency: "weekly" as const },
|
|
{ url: "/documents", priority: 0.8, changeFrequency: "weekly" as const },
|
|
{ url: "/search", priority: 0.5, changeFrequency: "monthly" as const },
|
|
];
|
|
for (const p of STATIC_PAGES) {
|
|
out.push({
|
|
url: `${SITE_URL}${p.url}`,
|
|
lastModified: now,
|
|
changeFrequency: p.changeFrequency,
|
|
priority: p.priority,
|
|
});
|
|
}
|
|
|
|
// 2. Documents
|
|
try {
|
|
const docIds = await listDocuments();
|
|
for (const id of docIds) {
|
|
out.push({
|
|
url: `${SITE_URL}/d/${id}`,
|
|
lastModified: now,
|
|
changeFrequency: "monthly",
|
|
priority: 0.7,
|
|
});
|
|
}
|
|
} catch { /* fs failure — skip docs */ }
|
|
|
|
// 3. Case reports — read filesystem for /c/[slug]
|
|
try {
|
|
const dir = path.join(CASE_ROOT, "reports");
|
|
const files = await readdir(dir);
|
|
for (const f of files.filter((x) => x.endsWith(".md"))) {
|
|
out.push({
|
|
url: `${SITE_URL}/c/${f.replace(/\.md$/, "")}`,
|
|
lastModified: now,
|
|
changeFrequency: "monthly",
|
|
priority: 0.95,
|
|
});
|
|
}
|
|
} catch { /* no case files yet */ }
|
|
|
|
// 4. Entities — surface those with summaries first (high priority), plus
|
|
// the top by mention count up to 500/class. Cap per class avoids blowing
|
|
// past sitemap size limits (Google: 50k urls, 50MB).
|
|
for (const [klass, folder] of Object.entries(ENTITY_FOLDER_BY_CLASS)) {
|
|
try {
|
|
const rows = await pgQuery<{
|
|
entity_id: string;
|
|
summary_generated_at: string | null;
|
|
summary_status: string | null;
|
|
total_mentions: number;
|
|
}>(
|
|
`SELECT entity_id, summary_generated_at, summary_status, total_mentions
|
|
FROM public.entities
|
|
WHERE entity_class = $1
|
|
AND total_mentions >= 1
|
|
ORDER BY (summary_status IN ('ai_generated','curated')) DESC,
|
|
total_mentions DESC, entity_id ASC
|
|
LIMIT 500`,
|
|
[klass],
|
|
);
|
|
for (const r of rows) {
|
|
const hasSummary = r.summary_status === "ai_generated" || r.summary_status === "curated";
|
|
out.push({
|
|
url: `${SITE_URL}/e/${folder}/${r.entity_id}`,
|
|
lastModified: r.summary_generated_at ? new Date(r.summary_generated_at) : now,
|
|
changeFrequency: "monthly",
|
|
priority: hasSummary ? 0.7 : 0.4,
|
|
});
|
|
}
|
|
} catch { /* db unavailable for this class — skip */ }
|
|
}
|
|
|
|
return out;
|
|
}
|