Unicode and localization

Status

type-checked

Industry

Cross-industry

Language

TypeScript

Framework

Vitest

CI

any

Fulfilment

BUILD_DATASET

Profile

edge-cases-core

About this example

All data is synthetic. DataNivra provisions approved test data into a customer-controlled target; it does not run these tests. Credentials for the target are never returned by DataNivra — your runner holds its own.

Why test data matters

Length limits, collation and truncation break on multi-byte text.

What is requested

300 core boundary records (field-length and type boundaries).

Policy gates

Within the profile.

What is provisioned

A certified synthetic dataset.

Expected output

AUTO_APPROVED. Which scripts and alphabets appear depends on the generators of your estate; check them in a plan before relying on a specific script.

Cleanup

afterAll releases.

Files

• request.yaml
• unicode.test.ts

Run

1. A tenant administrator defines and a second person approves the profile (datanivra test-data define ../../profiles/edge-cases-core.yaml --submit, then datanivra policies approve).
2. datanivra test-data validate request.yaml && datanivra test-data plan request.yaml
3. Run the example with DATANIVRA_BASE_URL and a session or workload token.

# yaml-language-server: $schema=../../../../packages/contracts/schemas/v1/manifests/test-data-request.schema.json
# DataNivra test-data-request manifest (apiVersion datanivra.io/v1alpha1). Validate: datanivra test-data validate <file>
apiVersion: datanivra.io/v1alpha1
kind: TestDataRequest
metadata:
  name: unicode-boundaries
spec:
  profile: { name: edge-cases-core, version: 1 }
  scenarios:
    - { scenario_code: CORE_BOUNDARY, count: 300 }

/**
 * Unicode boundaries — Vitest suite that acquires approved test data before the tests and always releases it.
 * DataNivra provisions data into the approved target; your tests use their own database access.
 */
import { readFileSync } from 'node:fs';
import type { TestDataRequest } from '@datanivra/contracts';
import { createDataNivraClient } from '@datanivra/sdk';
import { TestDataClient } from '@datanivra/sdk/testdata';
import { afterAll, beforeAll, describe, expect, it } from 'vitest';

const api = createDataNivraClient({
  baseUrl: process.env.DATANIVRA_BASE_URL ?? 'https://api.example.test',
  getAccessToken: () => process.env.DATANIVRA_TOKEN,
});
const testData = new TestDataClient(api);
let request: TestDataRequest | undefined;

beforeAll(async () => {
  const manifest = readFileSync(new URL('./request.yaml', import.meta.url), 'utf8');
  const created = await testData.request(manifest, { idempotencyKey: process.env.CI_RUN_KEY });
  request = await testData.wait(created.id, { timeoutMs: 600_000 });
}, 660_000);

afterAll(async () => {
  if (request) await testData.release(request.id, 'TEST_RUN_FINISHED');
});

describe('text handling', () => {
  it('runs against approved, certified test data', () => {
    expect(request?.state).toBe('READY');
    // assert length limits and sorting on the generated text fields
  });
});

# yaml-language-server: $schema=../../../packages/contracts/schemas/v1/manifests/test-data-profile.schema.json
# DataNivra test-data-profile manifest (apiVersion datanivra.io/v1alpha1). Validate: datanivra test-data validate <file>
# Placeholder ids (00000000-0000-4000-8000-0000000000NN): replace with your ids.
# 01 = approved target environment, 11 = certified dataset, 21 = customer agent,
# 99 = workload identity trust (datanivra workload-identities list).
apiVersion: datanivra.io/v1alpha1
kind: TestDataProfile
metadata:
  name: edge-cases-core
  description: Core synthetic edge cases (no industry pack)
spec:
  fulfilment: BUILD_DATASET
  build:
    business_domain: generic records
    dataset_kind: SYNTHETIC_ONLY
    target_environment_id: 00000000-0000-4000-8000-000000000001
    retention_days: 1
    max_total_records: 50000
    scenarios:
      - { scenario_code: CORE_NORMAL, kind: NORMAL, default_count: 200, max_count: 1000 }
      - { scenario_code: CORE_BOUNDARY, kind: BOUNDARY, default_count: 100, max_count: 500 }
      - {
          scenario_code: CORE_TEMPORAL_SEQUENCE,
          kind: TEMPORAL_SEQUENCE,
          default_count: 100,
          max_count: 500,
          included_by_default: false,
        }
      - {
          scenario_code: CORE_NULL_HEAVY,
          kind: NULL_HEAVY,
          default_count: 50,
          max_count: 200,
          included_by_default: false,
        }
      - {
          scenario_code: CORE_INVALID,
          kind: INVALID,
          default_count: 50,
          max_count: 200,
          included_by_default: false,
        }
      - {
          scenario_code: CORE_DUPLICATE,
          kind: DUPLICATE,
          default_count: 50,
          max_count: 200,
          included_by_default: false,
        }
      - {
          scenario_code: CORE_HIGH_VOLUME,
          kind: HIGH_VOLUME,
          default_count: 1000,
          max_count: 50000,
          included_by_default: false,
        }