feat(pdf): extract standalone PDF ingest package (ESRC-WP-0001)
All checks were successful
CI Smoke / host-smoke (push) Successful in 0s
CI Smoke / container-smoke (push) Successful in 2s

Bootstrap evidence-source from the citation-evidence src/source PDF slice.

- Headless core (src/pdf): ingest/extract/fingerprint, importing domain
  contracts from @citation-evidence/engine/shared (no local copies)
- Browser upload helpers isolated under src/browser behind a ./browser
  entry point, with an eslint boundary keeping the core browser-free
- pnpm/TS/vitest/eslint scaffold; 52 tests (contract + determinism)
- Fixtures resolved from the sibling citation-evidence checkout, not
  duplicated (real PII) — see docs/ADR-0002; suites skip when absent
- Boundary + fixture decisions recorded as docs/ADR-0001 / ADR-0002
- README/SCOPE rewritten; capability.infotech.pdf-evidence-ingest
  registered, NO_CAPABILITIES removed
- Follow-on workplans ESRC-WP-0002..0004 queued; ESRC-WP-0001 finished

Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
This commit is contained in:
tegwick 2026-07-08 20:55:28 +02:00
parent 2fd715ba45
commit cb93c322c0
31 changed files with 5066 additions and 105 deletions

115
src/browser/byte-store.ts Normal file
View file

@ -0,0 +1,115 @@
/**
* `PdfByteStore` in-memory store for uploaded PDF bytes, keyed by
* `DocumentId`.
*
* BROWSER SURFACE not part of the headless ingest core. This mints and
* revokes `blob:` URLs and is meant to back an interactive upload/viewer
* session. Headless callers should use `src/pdf/` directly and never import
* this module.
*
* Uploaded PDFs are stored in memory only. Bytes survive within a tab
* session; reloading the page loses them unless the session was exported.
*
* One store instance per active session. The session-management layer is
* responsible for swapping the active store when the user switches sessions.
* The store also owns a small registry of issued `blob:` URLs so it can
* revoke them on delete/clear no cross-cutting cleanup at the app layer.
*/
import type { DocumentId } from "@citation-evidence/engine/shared";
export interface PdfByteRecord {
readonly bytes: Uint8Array;
/** A `blob:` URL the viewer can consume directly. */
readonly blobUrl: string;
}
export interface PdfByteStore {
put(documentId: DocumentId, bytes: Uint8Array): PdfByteRecord;
get(documentId: DocumentId): PdfByteRecord | null;
has(documentId: DocumentId): boolean;
delete(documentId: DocumentId): boolean;
list(): readonly DocumentId[];
/** Revoke every blob URL and clear the store. */
clear(): void;
/** Total bytes currently held — useful for UI dashboards. */
size(): number;
}
export interface CreatePdfByteStoreOptions {
/**
* Mint a URL for the given bytes. Defaults to `URL.createObjectURL` in
* environments that have it; tests can inject a deterministic stub.
*/
readonly createObjectURL?: (blob: Blob) => string;
/** Revoke a URL previously minted by `createObjectURL`. */
readonly revokeObjectURL?: (url: string) => void;
}
export function createPdfByteStore(
options: CreatePdfByteStoreOptions = {},
): PdfByteStore {
const createUrl =
options.createObjectURL ??
((blob: Blob) => {
if (typeof URL === "undefined" || typeof URL.createObjectURL !== "function") {
throw new Error(
"createPdfByteStore: URL.createObjectURL not available — inject a stub via options",
);
}
return URL.createObjectURL(blob);
});
const revokeUrl =
options.revokeObjectURL ??
((url: string) => {
if (typeof URL !== "undefined" && typeof URL.revokeObjectURL === "function") {
URL.revokeObjectURL(url);
}
});
const records = new Map<DocumentId, PdfByteRecord>();
return {
put(documentId, bytes) {
// Replace previous record (revoking the prior URL) if any.
const prior = records.get(documentId);
if (prior) revokeUrl(prior.blobUrl);
// Cast: Blob() does accept Uint8Array at runtime, but TS narrows the
// buffer type to ArrayBufferLike (could be SharedArrayBuffer) and
// refuses without help. The bytes here always come from a fresh
// arrayBuffer() call, so a regular ArrayBuffer is guaranteed.
const blob = new Blob([bytes as unknown as ArrayBuffer], {
type: "application/pdf",
});
const blobUrl = createUrl(blob);
const record: PdfByteRecord = { bytes, blobUrl };
records.set(documentId, record);
return record;
},
get(documentId) {
return records.get(documentId) ?? null;
},
has(documentId) {
return records.has(documentId);
},
delete(documentId) {
const record = records.get(documentId);
if (!record) return false;
revokeUrl(record.blobUrl);
records.delete(documentId);
return true;
},
list() {
return [...records.keys()];
},
clear() {
for (const record of records.values()) revokeUrl(record.blobUrl);
records.clear();
},
size() {
let total = 0;
for (const r of records.values()) total += r.bytes.byteLength;
return total;
},
};
}