evidence-source/src/browser/upload.ts

/**
 * Upload-side ingest path.
 *
 * BROWSER SURFACE — not part of the headless ingest core. This is a thin
 * wrapper over the headless `ingestPdf` that additionally pushes the bytes
 * into a per-session `PdfByteStore`, which mints a `blob:` URL and stamps it
 * onto `document.uri` so a viewer adapter can mount the PDF directly.
 *
 *   1. Read `file.arrayBuffer()` once into a `Uint8Array`.
 *   2. Run the existing `ingestPdf(bytes, { filename })` pipeline to produce
 *      `{document, representation}`.
 *   3. Push the bytes into the per-session `PdfByteStore`.
 *   4. Hand the engine inputs back to the caller, which wires them via
 *      `engine.documents.register(...)`.
 *
 * Keeping URL-minting inside the byte store (rather than at the call site)
 * means there is exactly one place that creates `blob:` URLs and exactly one
 * place that revokes them.
 */

import { ingestPdf, type IngestPdfResult } from "../pdf/ingest";
import type { PdfByteStore } from "./byte-store";

export interface IngestPdfFromFileOptions {
  /** Override the filename used as the document title. */
  readonly title?: string;
}

export async function ingestPdfFromFile(
  file: File | Blob,
  store: PdfByteStore,
  options: IngestPdfFromFileOptions = {},
): Promise<IngestPdfResult> {
  const bytes = new Uint8Array(await file.arrayBuffer());
  const filename = "name" in file && typeof file.name === "string" ? file.name : undefined;
  const ingested = await ingestPdf(bytes, {
    ...(filename !== undefined ? { filename } : {}),
    ...(options.title !== undefined ? { title: options.title } : {}),
  });
  const record = store.put(ingested.document.id, bytes);
  const document = { ...ingested.document, uri: record.blobUrl };
  return { document, representation: ingested.representation };
}