feat(captura): fold recibo OCR into Captura as an automatic mode
Build and Push Images / Build jorgecuadros-web (push) Successful in 1m46s
Build and Push Images / Build jorgecuadros-api (push) Successful in 2m17s

Scanning a stack of bills and keying them in are the same daily job, ending
in the same ledger path, so OCR intake becomes a mode of the capture screen
instead of a second menu entry:

- components/Captura.tsx holds the mode switch; the manual check form moves
  verbatim to components/ManualCheckCapture.tsx and the OCR intake to
  components/StatementIntake.tsx.
- /estado-cuenta/lote opens on manual, /recibos on automatic — both render
  Captura, so batch-review links and old bookmarks still land right.
- Nav drops "Recibos (OCR)"; "Captura" covers both, with a NavLink.aliases
  field so /recibos still highlights it.

Also fixes the "El almacenamiento de documentos no está configurado" failure
staff hit on upload. Uploading with no object storage configured used to
succeed, then die on the first put minutes later, leaving a FAILED batch
whose only explanation was that string. createBatch now refuses up front,
GET /statements/status reports storageAvailable alongside ocrAvailable, and
the intake tab explains the situation instead of offering an upload that
cannot work. S3_* documented in .env.example (deploy stacks already set it).

Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
This commit is contained in:
2026-08-01 01:04:09 -07:00
co-authored by Claude Opus 5
parent 4d5008b545
commit b59abda895
13 changed files with 981 additions and 824 deletions
+272
View File
@@ -0,0 +1,272 @@
"use client";
import { useCallback, useEffect, useState } from "react";
import Link from "next/link";
import {
getStatementStatus,
listStatementBatches,
uploadStatementBatch,
} from "@/lib/api";
import { useCan } from "@/lib/abilities";
import { formatDate, SERVICE_KIND_LABELS, serviceKindLabel } from "@/lib/labels";
import type { ServiceKind, StatementBatch, StatementBatchStatus } from "@/lib/types";
/**
* Automatic capture — statement OCR intake (docs/RECEIPT_CAPTURE_SPEC.md §2).
*
* Each utility company mails 300+ paper bills a month, one per customer, which
* staff otherwise key in by hand on the manual tab of the same "Captura"
* screen. Here they scan the stack instead, and the machine proposes customer +
* amount for every page; a human still confirms before anything reaches the
* ledger. Same daily job, same ledger path — only the input differs, which is
* why it lives as a mode of Captura rather than a screen of its own.
*
* One batch = one service kind, because the matcher is scoped per kind: a
* water account number and a phone number are compared against different
* columns, and mixing them in one upload is how a bill gets posted to the
* wrong customer.
*/
/** The kinds the parsers actually recognise today. */
const SUPPORTED: ServiceKind[] = ["ELECTRIC", "WATER", "TELEPHONE"];
/** Uploadable, but every page will land in review until a parser learns it. */
const OTHER_KINDS: ServiceKind[] = ["GAS", "PROPERTY_TAX", "FEDERAL_ZONE", "CABLE"];
const STATUS_LABEL: Record<StatementBatchStatus, string> = {
UPLOADED: "Recibido",
PROCESSING: "Procesando…",
READY_FOR_REVIEW: "Listo para revisar",
COMPLETED: "Registrado",
FAILED: "Falló",
};
export function StatementIntake() {
const canIngest = useCan("statement:ingest");
const [batches, setBatches] = useState<StatementBatch[]>([]);
const [ocrAvailable, setOcrAvailable] = useState<boolean | null>(null);
const [storageAvailable, setStorageAvailable] = useState<boolean | null>(null);
const [loading, setLoading] = useState(true);
const [error, setError] = useState<string | null>(null);
const load = useCallback(async () => {
try {
const [list, status] = await Promise.all([
listStatementBatches(),
getStatementStatus(),
]);
setBatches(list.items);
setOcrAvailable(status.ocrAvailable);
setStorageAvailable(status.storageAvailable);
setError(null);
} catch (e) {
setError((e as Error)?.message ?? "No se pudieron cargar los lotes.");
} finally {
setLoading(false);
}
}, []);
useEffect(() => {
void load();
}, [load]);
// A batch of 300 pages takes minutes to OCR, so the list refreshes itself
// while anything is still working rather than making staff reload.
const working = batches.some(
(b) => b.status === "PROCESSING" || b.status === "UPLOADED",
);
useEffect(() => {
if (!working) return;
const t = setInterval(() => void load(), 4000);
return () => clearInterval(t);
}, [working, load]);
const ready = ocrAvailable === true && storageAvailable === true;
return (
<div className="stack">
{ocrAvailable === false && (
<div className="state-box state-error">
Este servidor no tiene OCR instalado, así que no se pueden leer recibos
escaneados. Usa la captura manual; el resto del sistema funciona con
normalidad.
</div>
)}
{storageAvailable === false && (
<div className="state-box state-error">
Este servidor no tiene configurado el almacenamiento de documentos, así
que no hay dónde guardar los recibos escaneados. Usa la captura manual
mientras se configura.
</div>
)}
{canIngest && ready && <UploadCard onDone={load} />}
{error && <div className="state-box state-error">{error}</div>}
<section className="card" style={{ padding: 16 }}>
<h2 className="section-title" style={{ marginTop: 0 }}>
Lotes
</h2>
{loading ? (
<div className="state-box">Cargando</div>
) : batches.length === 0 ? (
<div className="state-box">Todavía no hay lotes de recibos.</div>
) : (
<div className="tx-scroll">
<table className="tx-table">
<thead>
<tr>
<th>Fecha</th>
<th>Servicio</th>
<th>Referencia</th>
<th>Estado</th>
<th className="num">Páginas</th>
<th>Subido por</th>
<th />
</tr>
</thead>
<tbody>
{batches.map((b) => (
<tr key={b.id}>
<td style={{ whiteSpace: "nowrap" }}>{formatDate(b.createdAt)}</td>
<td>{serviceKindLabel(b.serviceKind)}</td>
<td>{b.label || "—"}</td>
<td>
<StatusTag status={b.status} />
{b.error && (
<div className="page-sub" style={{ marginTop: 4 }}>
{b.error}
</div>
)}
</td>
<td className="num">{b._count?.documents ?? 0}</td>
<td>{b.uploadedBy?.name ?? "—"}</td>
<td>
<Link className="btn btn-ghost" href={`/recibos/${b.id}`}>
Revisar
</Link>
</td>
</tr>
))}
</tbody>
</table>
</div>
)}
</section>
</div>
);
}
function StatusTag({ status }: { status: StatementBatchStatus }) {
return <span className="tag">{STATUS_LABEL[status] ?? status}</span>;
}
function UploadCard({ onDone }: { onDone: () => void }) {
const [files, setFiles] = useState<File[]>([]);
const [serviceKind, setServiceKind] = useState<ServiceKind>("ELECTRIC");
const [label, setLabel] = useState("");
const [busy, setBusy] = useState(false);
const [error, setError] = useState<string | null>(null);
async function submit() {
if (!files.length) return;
setBusy(true);
setError(null);
try {
await uploadStatementBatch(files, serviceKind, label.trim() || undefined);
setFiles([]);
setLabel("");
onDone();
} catch (e) {
setError((e as Error)?.message ?? "No se pudo subir el lote.");
} finally {
setBusy(false);
}
}
const unsupported = !SUPPORTED.includes(serviceKind);
return (
<section className="card" style={{ padding: 16 }}>
<h2 className="section-title" style={{ marginTop: 0 }}>
Subir recibos escaneados
</h2>
<div className="inline-form" style={{ flexWrap: "wrap", gap: 12 }}>
<label>
<span className="page-sub">Servicio</span>
<select
className="input"
value={serviceKind}
onChange={(e) => setServiceKind(e.target.value as ServiceKind)}
>
<optgroup label="Con lectura automática">
{SUPPORTED.map((k) => (
<option key={k} value={k}>
{SERVICE_KIND_LABELS[k] ?? k}
</option>
))}
</optgroup>
<optgroup label="Sin lectura automática (revisión manual)">
{OTHER_KINDS.map((k) => (
<option key={k} value={k}>
{SERVICE_KIND_LABELS[k] ?? k}
</option>
))}
</optgroup>
</select>
</label>
<label>
<span className="page-sub">Referencia (opcional)</span>
<input
className="input"
placeholder="ej. CFE julio 2026"
value={label}
onChange={(e) => setLabel(e.target.value)}
/>
</label>
<label>
<span className="page-sub">Archivos PDF</span>
<input
type="file"
className="input"
accept="application/pdf"
multiple
onChange={(e) => setFiles(Array.from(e.target.files ?? []))}
/>
</label>
<button
type="button"
className="btn btn-primary"
disabled={!files.length || busy}
onClick={submit}
>
{busy ? "Subiendo…" : `Procesar ${files.length || ""}`.trim()}
</button>
</div>
{error && (
<div className="state-box state-error" style={{ marginTop: 12 }}>
{error}
</div>
)}
{unsupported && (
<div className="state-box" style={{ marginTop: 12 }}>
Todavía no hay lectura automática para{" "}
{SERVICE_KIND_LABELS[serviceKind] ?? serviceKind}: cada página quedará
para revisión manual. Al confirmarlas se guarda el número de cuenta,
así que los recibos del mes siguiente se reconocerán solos.
</div>
)}
<p className="page-sub" style={{ marginTop: 12 }}>
Un lote es de un solo servicio. Cada página del PDF se trata como un
recibo distinto, salvo que el proveedor imprima varias hojas por cliente.
</p>
</section>
);
}