a7e9dce6d2
Add reextract pipeline (scripts/reextract/) that rebuilds doc-level entity JSON from Sonnet-vision chunks via Opus, replacing the noisy per-page extraction. Add synthesize scripts to regenerate wiki/entities from the 116 _reextract.json (30), aggregate missing page.md from chunks (31), and reprocess 805 pages the doc-rebuilder agent dropped on context overflow (32). Add maintain scripts 43-56 for chunk-page sync, dedup, generic-entity marking, and typed relation extraction. Web: wire relations API + entity-relations component; entity/timeline/doc pages consume the rebuilt layer. Note: raw/, processing/, wiki/ remain gitignored (bulk data managed separately); the 116 reextract JSONs and 7,798 rebuilt entity files live on disk only. The 27 curated anchor events under wiki/entities/events/ are preserved. Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>
370 lines
16 KiB
TypeScript
370 lines
16 KiB
TypeScript
/**
|
||
* Entity detail page — DB-first (live data from public.entity_mentions + chunks).
|
||
* Wiki frontmatter usado só como fallback estático (aliases, narrativa).
|
||
*/
|
||
import Link from "next/link";
|
||
import { notFound } from "next/navigation";
|
||
import Image from "next/image";
|
||
import { readEntity, classKeyToFolder, type EntityClass } from "@/lib/wiki";
|
||
import { MarkdownBody } from "@/components/markdown-body";
|
||
import { ChatBubble } from "@/components/chat-bubble";
|
||
import { AuthBar } from "@/components/auth-bar";
|
||
import { EntityGraphMini } from "@/components/entity-graph-mini";
|
||
import { EntityRelations } from "@/components/entity-relations";
|
||
import {
|
||
getEntityCore,
|
||
getEntityMentionsByDoc,
|
||
getEntityChunks,
|
||
} from "@/lib/retrieval/entity-pages";
|
||
|
||
const CLASS_TO_SINGULAR: Record<string, string> = {
|
||
people: "person",
|
||
organizations: "organization",
|
||
locations: "location",
|
||
events: "event",
|
||
"uap-objects": "uap_object",
|
||
vehicles: "vehicle",
|
||
operations: "operation",
|
||
concepts: "concept",
|
||
};
|
||
|
||
export const dynamic = "force-dynamic";
|
||
|
||
const CLASS_TITLE: Record<EntityClass, string> = {
|
||
people: "Pessoa",
|
||
organizations: "Organização",
|
||
locations: "Local",
|
||
events: "Evento",
|
||
"uap-objects": "Objeto UAP",
|
||
vehicles: "Veículo",
|
||
operations: "Operação",
|
||
concepts: "Conceito",
|
||
};
|
||
|
||
const CLASS_COLOR: Record<EntityClass, string> = {
|
||
people: "text-[#ff6ec7] border-[#ff6ec7]",
|
||
organizations: "text-[#ff8a4d] border-[#ff8a4d]",
|
||
locations: "text-[#3fde6a] border-[#3fde6a]",
|
||
events: "text-[#ffa500] border-[#ffa500]",
|
||
"uap-objects": "text-[#ff3344] border-[#ff3344]",
|
||
vehicles: "text-[#5b9bd5] border-[#5b9bd5]",
|
||
operations: "text-[#9b5de5] border-[#9b5de5]",
|
||
concepts: "text-[#06d6a0] border-[#06d6a0]",
|
||
};
|
||
|
||
const CLASS_BG: Record<EntityClass, string> = {
|
||
people: "from-[rgba(255,110,199,0.10)]",
|
||
organizations: "from-[rgba(255,138,77,0.10)]",
|
||
locations: "from-[rgba(63,222,106,0.10)]",
|
||
events: "from-[rgba(255,165,0,0.10)]",
|
||
"uap-objects": "from-[rgba(255,51,68,0.10)]",
|
||
vehicles: "from-[rgba(91,155,213,0.10)]",
|
||
operations: "from-[rgba(155,93,229,0.10)]",
|
||
concepts: "from-[rgba(6,214,160,0.10)]",
|
||
};
|
||
|
||
function pageOcurrencesText(pages: number[]): string {
|
||
if (pages.length === 0) return "—";
|
||
if (pages.length <= 5) return `p${pages.join(", p")}`;
|
||
return `p${pages.slice(0, 4).join(", p")} +${pages.length - 4}`;
|
||
}
|
||
|
||
export default async function EntityPage({
|
||
params,
|
||
}: {
|
||
params: Promise<{ cls: string; id: string }>;
|
||
}) {
|
||
const { cls, id } = await params;
|
||
const folder = classKeyToFolder(cls);
|
||
if (!folder) notFound();
|
||
|
||
const entityClassSingular = CLASS_TO_SINGULAR[folder as string] ?? folder;
|
||
|
||
// YAML-first: every count comes from the entity's frontmatter (kept in sync
|
||
// by scripts/maintain/42_sync_entity_stats.py). The DB is consulted ONLY for
|
||
// chunk previews, not for counts.
|
||
const core = await getEntityCore(entityClassSingular, id).catch(() => null);
|
||
const wiki = await readEntity(folder as EntityClass, id);
|
||
if (!core && !wiki) notFound();
|
||
|
||
const canonical = core?.canonical_name ?? (wiki?.fm.canonical_name as string) ?? id;
|
||
const aliases = (core?.aliases ?? (wiki?.fm.aliases as string[]) ?? []).filter(
|
||
(a) => a !== canonical,
|
||
);
|
||
|
||
const mentionGroups = core
|
||
? await getEntityMentionsByDoc(entityClassSingular, id, 100).catch(() => [])
|
||
: [];
|
||
const sampleChunks = core
|
||
? await getEntityChunks(core.entity_pk, 12).catch(() => [])
|
||
: [];
|
||
|
||
const totalMentions = core?.total_mentions ?? 0;
|
||
const documentsCount = core?.documents_count ?? 0;
|
||
const strength = core?.signal_strength ?? "unverified";
|
||
const sigs = core?.signal_sources ?? { db_chunks: 0, page_refs: 0, cross_refs: 0, text_refs: 0 };
|
||
// Derived display class: orphan + curated narrative is not noise — it's a
|
||
// knowledge-curated entity the corpus simply doesn't mention. Label it apart.
|
||
const displayStrength: "strong" | "weak" | "curated" | "orphan" | "unverified" =
|
||
strength === "orphan" && core?.summary_status === "curated" ? "curated" : (strength as any);
|
||
|
||
const classColor = CLASS_COLOR[folder as EntityClass];
|
||
const classBg = CLASS_BG[folder as EntityClass];
|
||
|
||
return (
|
||
<main className="min-h-screen p-6 md:p-10 max-w-6xl mx-auto">
|
||
<div className="flex items-start justify-between gap-4 mb-6">
|
||
<div className="flex items-center gap-3">
|
||
<Link href="/" className="font-mono text-xs text-[#7fdbff] hover:text-[#00ff9c]">
|
||
← home
|
||
</Link>
|
||
<Link href={`/e/${folder}`} className="font-mono text-xs text-[#7fdbff] hover:text-[#00ff9c]">
|
||
← todos {folder}
|
||
</Link>
|
||
<Link href="/graph" className="font-mono text-xs text-[#7fdbff] hover:text-[#00ff9c]">
|
||
🕸 ver no grafo
|
||
</Link>
|
||
</div>
|
||
<AuthBar />
|
||
</div>
|
||
|
||
{/* Hero header */}
|
||
<header
|
||
className={`mb-8 p-6 rounded-lg border-2 bg-gradient-to-br to-[#040810] ${classBg} ${classColor.split(" ")[1]}`}
|
||
>
|
||
<div className="font-mono text-[10px] text-[#5a6678] tracking-widest uppercase mb-2 flex items-center gap-3 flex-wrap">
|
||
<span className={`px-2 py-0.5 border rounded ${classColor}`}>
|
||
{CLASS_TITLE[folder as EntityClass]}
|
||
</span>
|
||
<span>· /e/{folder}/{id}</span>
|
||
</div>
|
||
<h1 className="font-mono text-3xl md:text-4xl text-[#00ff9c] mb-3 leading-tight">
|
||
▍ {canonical}
|
||
</h1>
|
||
|
||
{aliases.length > 0 && (
|
||
<div className="mb-4 flex flex-wrap gap-1.5">
|
||
{aliases.slice(0, 12).map((a) => (
|
||
<span
|
||
key={a}
|
||
className="font-mono text-[11px] px-2 py-0.5 bg-[rgba(127,219,255,0.06)] border border-[rgba(127,219,255,0.20)] text-[#7fdbff] rounded"
|
||
>
|
||
{a}
|
||
</span>
|
||
))}
|
||
</div>
|
||
)}
|
||
|
||
<div className="flex flex-wrap gap-3 mt-4">
|
||
<div className="px-4 py-3 bg-[#0a121e] border border-[rgba(0,255,156,0.20)] rounded">
|
||
<div className="font-mono text-[10px] uppercase tracking-widest text-[#5a6678]">menções</div>
|
||
<div className="font-mono text-2xl text-[#00ff9c] mt-0.5 tabular-nums">{totalMentions}</div>
|
||
</div>
|
||
<div className="px-4 py-3 bg-[#0a121e] border border-[rgba(127,219,255,0.20)] rounded">
|
||
<div className="font-mono text-[10px] uppercase tracking-widest text-[#5a6678]">documentos</div>
|
||
<div className="font-mono text-2xl text-[#7fdbff] mt-0.5 tabular-nums">{documentsCount}</div>
|
||
</div>
|
||
{core?.enrichment_status && core.enrichment_status !== "none" && (
|
||
<div className="px-4 py-3 bg-[#0a121e] border border-[rgba(167,139,250,0.20)] rounded">
|
||
<div className="font-mono text-[10px] uppercase tracking-widest text-[#5a6678]">enrichment</div>
|
||
<div className="font-mono text-sm text-[#a78bfa] mt-0.5">{core.enrichment_status}</div>
|
||
</div>
|
||
)}
|
||
<div
|
||
className={`px-4 py-3 bg-[#0a121e] border rounded ${
|
||
displayStrength === "strong"
|
||
? "border-[#00ff9c]"
|
||
: displayStrength === "weak"
|
||
? "border-[#ffa500]"
|
||
: displayStrength === "curated"
|
||
? "border-[#a78bfa]"
|
||
: displayStrength === "orphan"
|
||
? "border-[#ff6b6b]"
|
||
: "border-[#5a6678]"
|
||
}`}
|
||
title="Cruzamento dos sinais que confirmam esta entidade no corpus."
|
||
>
|
||
<div className="font-mono text-[10px] uppercase tracking-widest text-[#5a6678]">
|
||
força do sinal
|
||
</div>
|
||
<div
|
||
className={`font-mono text-sm mt-0.5 ${
|
||
displayStrength === "strong"
|
||
? "text-[#00ff9c]"
|
||
: displayStrength === "weak"
|
||
? "text-[#ffa500]"
|
||
: displayStrength === "curated"
|
||
? "text-[#a78bfa]"
|
||
: displayStrength === "orphan"
|
||
? "text-[#ff6b6b]"
|
||
: "text-[#8896aa]"
|
||
}`}
|
||
>
|
||
{displayStrength === "strong" && "forte"}
|
||
{displayStrength === "weak" && "fraca"}
|
||
{displayStrength === "curated" && "curado"}
|
||
{displayStrength === "orphan" && "órfã"}
|
||
{displayStrength === "unverified" && "não verificada"}
|
||
</div>
|
||
<div className="font-mono text-[9px] text-[#5a6678] mt-1 leading-tight">
|
||
{sigs.db_chunks} chunks · {sigs.page_refs} págs · {sigs.cross_refs} backlinks · {sigs.text_refs} textuais
|
||
</div>
|
||
</div>
|
||
</div>
|
||
|
||
{strength === "orphan" && core?.summary_status === "curated" && (
|
||
<p className="mt-4 text-xs text-[#a78bfa] font-mono leading-relaxed">
|
||
📚 conhecimento curado · este evento/entidade faz parte do registro UAP/UFO
|
||
mundial mas <strong>não foi mencionado</strong> nos PDFs deste corpus (war.gov/ufo).
|
||
Narrativa abaixo vem de fonte curada manualmente, não de extração.
|
||
</p>
|
||
)}
|
||
{strength === "orphan" && core?.summary_status !== "curated" && (
|
||
<p className="mt-4 text-xs text-[#ff6b6b] font-mono">
|
||
⚠ entidade não confirmada: nenhuma página, chunk ou outra entidade aponta para
|
||
ela. Pode ser extração ruidosa do pipeline original.
|
||
</p>
|
||
)}
|
||
</header>
|
||
|
||
<div className="grid grid-cols-1 lg:grid-cols-[1fr_320px] gap-8">
|
||
{/* MAIN — narrative + chunks live */}
|
||
<article>
|
||
{/* Live chunk previews — most impactful section */}
|
||
{sampleChunks.length > 0 && (
|
||
<section className="mb-10">
|
||
<h2 className="font-mono text-sm text-[#7fdbff] uppercase tracking-widest mb-3 border-l-2 border-[#7fdbff] pl-3">
|
||
Aparece em {sampleChunks.length}+ trechos · top {sampleChunks.length}
|
||
</h2>
|
||
<div className="space-y-2">
|
||
{sampleChunks.map((c) => {
|
||
const text = (c.content_pt || c.content_en || "").trim();
|
||
const docPretty = c.doc_id.replace(/^doc-/, "").replace(/-/g, " ").slice(0, 60);
|
||
const cropUrl = c.bbox
|
||
? `/api/crop?doc=${encodeURIComponent(c.doc_id)}&page=${c.page}&x=${c.bbox.x}&y=${c.bbox.y}&w=${c.bbox.w}&h=${c.bbox.h}&w_px=200`
|
||
: null;
|
||
return (
|
||
<Link
|
||
key={c.chunk_pk}
|
||
href={`/d/${c.doc_id}#${c.chunk_id}`}
|
||
className="flex items-start gap-3 p-3 bg-[#0a121e] border border-[rgba(127,219,255,0.15)] hover:border-[#00ff9c] rounded transition"
|
||
>
|
||
{cropUrl && (
|
||
<Image
|
||
src={cropUrl}
|
||
alt=""
|
||
width={120}
|
||
height={80}
|
||
unoptimized
|
||
className="block w-28 h-20 object-cover bg-black rounded flex-shrink-0"
|
||
/>
|
||
)}
|
||
<div className="flex-1 min-w-0">
|
||
<div className="flex items-center gap-2 text-[10px] font-mono mb-1 flex-wrap">
|
||
<span className="text-[#00ff9c]">{c.chunk_id}</span>
|
||
<span className="text-[#5a6678]">p{c.page}</span>
|
||
<span className="text-[#5a6678]">{c.type}</span>
|
||
{c.classification && (
|
||
<span className="text-[#ff6b6b]">{c.classification}</span>
|
||
)}
|
||
{c.ufo_anomaly && (
|
||
<span className="text-[#00ff9c]">🛸 {c.ufo_anomaly_type ?? "UAP"}</span>
|
||
)}
|
||
</div>
|
||
<div className="text-sm text-[#c8d4e6] line-clamp-3 leading-snug">{text}</div>
|
||
<div className="text-[10px] font-mono text-[#5a6678] truncate mt-1">
|
||
{docPretty}
|
||
</div>
|
||
</div>
|
||
</Link>
|
||
);
|
||
})}
|
||
</div>
|
||
</section>
|
||
)}
|
||
|
||
{/* Narrative body (Haiku stub OK quando rico) */}
|
||
{wiki?.body && wiki.body.trim().length > 30 && (
|
||
<section className="pt-6 border-t border-[rgba(0,255,156,0.12)]">
|
||
<h2 className="font-mono text-sm text-[#7fdbff] uppercase tracking-widest mb-3 border-l-2 border-[#7fdbff] pl-3">
|
||
Narrativa
|
||
</h2>
|
||
<MarkdownBody>{wiki.body}</MarkdownBody>
|
||
</section>
|
||
)}
|
||
|
||
{sampleChunks.length === 0 && (!wiki?.body || wiki.body.trim().length === 0) && (
|
||
<div className="text-[#5a6678] italic text-sm p-6 border border-[rgba(255,165,0,0.30)] bg-[rgba(255,165,0,0.05)] rounded">
|
||
Entidade ainda sem chunks indexados na DB. Aguarde o indexer terminar.
|
||
</div>
|
||
)}
|
||
</article>
|
||
|
||
{/* SIDEBAR — documentos onde aparece (DB live) + grafo mini */}
|
||
<aside className="lg:sticky lg:top-6 lg:self-start space-y-6">
|
||
<section>
|
||
<h3 className="font-mono text-[10px] text-[#8896aa] uppercase tracking-widest mb-2">
|
||
Aparece em {mentionGroups.length} documento(s)
|
||
</h3>
|
||
{mentionGroups.length === 0 ? (
|
||
displayStrength === "curated" ? (
|
||
<p className="text-[#a78bfa] text-xs italic leading-relaxed">
|
||
Não documentado nos PDFs deste corpus. Conteúdo abaixo vem de fonte
|
||
curada (registro UAP mundial), não de extração de documentos.
|
||
</p>
|
||
) : (
|
||
<p className="text-[#5a6678] text-xs italic">Sem dados de mention ainda.</p>
|
||
)
|
||
) : (
|
||
<ul className="space-y-1 max-h-[50vh] overflow-y-auto pr-1">
|
||
{mentionGroups.map((m) => (
|
||
<li key={m.doc_id}>
|
||
<Link
|
||
href={`/d/${m.doc_id}`}
|
||
className="group block p-2 border border-transparent hover:border-[rgba(0,255,156,0.32)] hover:bg-[rgba(0,255,156,0.04)] rounded transition"
|
||
>
|
||
<div className="flex items-baseline gap-2 font-mono text-[11px]">
|
||
<span className="text-[#7fdbff] group-hover:text-[#00ff9c] truncate flex-1">
|
||
{m.canonical_title ?? m.doc_id}
|
||
</span>
|
||
{m.text_only && (
|
||
<span
|
||
title="Menção textual encontrada via back-fill (alias dentro do corpo narrativo); pipeline estruturado não pegou."
|
||
className="text-[9px] text-[#a78bfa] border border-[rgba(167,139,250,0.40)] px-1 rounded shrink-0"
|
||
>
|
||
texto
|
||
</span>
|
||
)}
|
||
<span className="text-[#00ff9c] tabular-nums shrink-0">{m.mention_count}×</span>
|
||
</div>
|
||
<div className="flex items-center gap-2 mt-0.5 font-mono text-[10px] text-[#5a6678]">
|
||
{m.classification && (
|
||
<span className="text-[#ff6b6b]">{m.classification}</span>
|
||
)}
|
||
<span>· {pageOcurrencesText(m.pages ?? [])}</span>
|
||
</div>
|
||
</Link>
|
||
</li>
|
||
))}
|
||
</ul>
|
||
)}
|
||
</section>
|
||
|
||
<section className="border-t border-[rgba(0,255,156,0.12)] pt-4">
|
||
<h3 className="font-mono text-[10px] text-[#8896aa] uppercase tracking-widest mb-3">
|
||
Relações tipadas
|
||
</h3>
|
||
<EntityRelations entityClass={entityClassSingular} entityId={id} />
|
||
</section>
|
||
|
||
<EntityGraphMini
|
||
entityClassSingular={entityClassSingular}
|
||
entityId={id}
|
||
/>
|
||
</aside>
|
||
</div>
|
||
|
||
<ChatBubble context={{ doc_id: mentionGroups[0]?.doc_id }} />
|
||
</main>
|
||
);
|
||
}
|