feat(13-01): add TenderSource model + Tender.fingerprint, backfill 2851 rows

Additive schema change (SCHEMA-03/D-03/D-04): new model TenderSource (1:n Tender, @@unique[sourcePortal, sourceNoticeId], onDelete Cascade) and a nullable Tender.fingerprint column + index. dedupKey stays unchanged as the SCHEMA-02 upsert target. Migration 20260723120000_add_tender_source applies in strict order (Pitfall 5): table+column create, then one TenderSource row per pre-existing Tender via SQL INSERT/SELECT, then the unique constraint. Applied locally against the tessera dev DB (container IP, no host port) — verified via psql: TenderSource count == Tender count == 2851. backfill-tender-source.ts is a one-time script that computes Tender.fingerprint via the Task-1 tenderFingerprint() function (Decimal->number conversion for estimatedValue, T-13-01-03) — run via the compiled dist/ output (source uses standard extensionless TS imports for tsc compatibility). Confirmed: 2851/2851 rows backfilled, idempotent re-run verified. Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
2026-07-23 08:38:26 +02:00
parent c6cac696ff
commit 447fb74e0c
3 changed files with 136 additions and 0 deletions
@@ -0,0 +1,67 @@
+/**
+ * One-time backfill script (SCHEMA-03, D-05) — computes and persists
+ * `Tender.fingerprint` for every pre-existing row.
+ *
+ * The TenderSource row backfill itself lives in the migration SQL
+ * (20260723120000_add_tender_source/migration.sql) because it's a pure
+ * column copy. The fingerprint backfill does NOT belong in SQL: it needs
+ * the umlaut/CPV-normalization logic in tender-fingerprint.ts, which is
+ * code, not SQL (13-RESEARCH.md "Backfill-Migration").
+ *
+ * Run once, manually, after the migration has been applied (compiled first
+ * — this file uses standard extensionless TS imports, so it must run as
+ * built CommonJS, not as a raw .ts file):
+ *   pnpm --filter @tessera/api build
+ *   DATABASE_URL=... node dist/tenders/backfill-tender-source.js
+ *
+ * Idempotent: recomputes and overwrites fingerprint for every row it reads,
+ * so re-running is safe (same deterministic output for unchanged inputs).
+ */
+import { PrismaClient, Prisma } from '@prisma/client';
+import { tenderFingerprint } from './tender-fingerprint';
+
+async function main(): Promise<void> {
+  const prisma = new PrismaClient();
+  try {
+    const tenders = await prisma.tender.findMany({
+      select: {
+        id: true,
+        title: true,
+        buyerName: true,
+        cpvDivisions: true,
+        deadlineAt: true,
+        estimatedValue: true,
+      },
+    });
+
+    let updated = 0;
+    for (const t of tenders) {
+      const fingerprint = tenderFingerprint({
+        buyerName: t.buyerName,
+        title: t.title,
+        cpvDivisions: t.cpvDivisions,
+        deadlineAt: t.deadlineAt,
+        // estimatedValue is Decimal? — convert to number|null before bucketing (T-13-01-03).
+        estimatedValue: decimalToNumberOrNull(t.estimatedValue),
+      });
+      await prisma.tender.update({
+        where: { id: t.id },
+        data: { fingerprint },
+      });
+      updated += 1;
+    }
+
+    console.log(`backfill-tender-source: fingerprint set on ${updated}/${tenders.length} tenders`);
+  } finally {
+    await prisma.$disconnect();
+  }
+}
+
+function decimalToNumberOrNull(v: Prisma.Decimal | null): number | null {
+  return v === null ? null : Number(v);
+}
+
+main().catch((err) => {
+  console.error('backfill-tender-source failed:', err);
+  process.exitCode = 1;
+});