hanzo.ai/e2e/unit/robots.spec.ts

import { test, expect } from '@playwright/test'
import { readdirSync, readFileSync, statSync } from 'node:fs'
import { join } from 'node:path'

/**
 * NO PAGE DECLARES ITS OWN ROBOTS TAG.
 *
 * lib/publish decides which routes are withheld from indexing, and
 * scripts/noindex.mjs writes that tag into the export — refusing, and failing
 * the build, on a page that already carries one. A `robots` field in a page's
 * metadata is that second declaration; this finds it in the source, in a
 * second, instead of at the end of the export.
 */

function files(dir: string): string[] {
  return readdirSync(dir).flatMap((name) => {
    const p = join(dir, name)
    if (statSync(p).isDirectory()) return files(p)
    return /(page|layout)\.tsx?$/.test(name) ? [p] : []
  })
}

test('no page or layout declares robots in its metadata', () => {
  const declared = files(join(import.meta.dirname, '..', '..', 'app')).filter((f) => /^\s*robots\s*:/m.test(readFileSync(f, 'utf8')))
  expect(declared).toEqual([])
})