Prepare scanner branch for merge

src/eval/corpus/index.ts

@@ -0,0 +1,24 @@
+import { confirmedReviewCorpus, type ConfirmedReviewEvalCase } from "./confirmedReviewCorpus";
+import { seedCorpus } from "./seedCorpus";
+import type { OcrEvalCase } from "../ocrEvalHarness";
+
+export { confirmedReviewCorpus, seedCorpus };
+export type { ConfirmedReviewEvalCase };
+
+export const ocrEvalCorpus: OcrEvalCase[] = [...seedCorpus, ...confirmedReviewCorpus];
+
+export function validateConfirmedReviewCorpus(corpus: readonly ConfirmedReviewEvalCase[] = confirmedReviewCorpus) {
+  const errors: string[] = [];
+  const seen = new Set<string>();
+  for (const entry of corpus) {
+    if (seen.has(entry.id)) errors.push(`${entry.id}: duplicate id`);
+    seen.add(entry.id);
+    if (entry.confirmed !== true) errors.push(`${entry.id}: confirmed must be true`);
+    if (entry.meta.source !== "review-sample") errors.push(`${entry.id}: meta.source must be review-sample`);
+    if (!entry.meta.note?.trim()) errors.push(`${entry.id}: meta.note must describe the review source/reason`);
+    if (Object.keys(entry.expect).length === 0) errors.push(`${entry.id}: expect must label at least one field`);
+    if (Object.keys(entry.ocr).length === 0) errors.push(`${entry.id}: ocr must contain at least one field`);
+  }
+  return errors;
+}
+