feat: protect sensitive catalog samples

backend/test/catalog-synthetic-sample-value.test.ts

@@ -0,0 +1,29 @@
+import { expect, test } from "vitest";
+import { syntheticSampleValue } from "../src/catalog/synthetic-sample-value.js";
+
+test.each([
+  ["text[]", "tags", 1, "{tags_001,tags_002}"],
+  ["json", "payload", 2, '{"example":"payload_002","sequence":2}'],
+  ["jsonb", "attributes", 3, '{"example":"attributes_003","sequence":3}'],
+  ["inet", "client_ip", 4, "192.0.2.4"],
+  ["cidr", "network", 5, "192.0.2.0/24"],
+  ["time without time zone", "opening_time", 6, "10:30:06"],
+  ["interval", "duration", 7, "7 days 07:00:00"],
+  ["bytea", "digest", 8, "\\x00000008"],
+] as const)(
+  "creates a deterministic PostgreSQL-shaped value for %s",
+  (dataType, name, index, expected) => {
+    const column = { name, dataType };
+
+    expect(syntheticSampleValue(column, index)).toBe(expected);
+    expect(syntheticSampleValue(column, index)).toBe(expected);
+  },
+);
+
+test("uses the PostgreSQL type before birth-related name hints", () => {
+  expect(syntheticSampleValue({ name: "birth_year", dataType: "integer" }, 2)).toBe(1002);
+  expect(syntheticSampleValue({ name: "birth_date", dataType: "date" }, 2))
+    .toBe("1982-01-02");
+  expect(syntheticSampleValue({ name: "birth_recorded_at", dataType: "timestamp" }, 2))
+    .toBe("2024-01-02T10:30:00.000Z");
+});