vue-seo-layer/app/utils/seo.ts

// Pure helpers of the SEO layer: which URLs are resolved, how an answer
// becomes head tags, a redirect target and a robots value. No Nuxt imports,
// so `node --test` drives them directly. Names start with `seo` because
// app/utils is auto-imported into the consuming app.

import type { SeoResolveAnswer } from './types.ts'

const ACTIONS = new Set(['ok', 'not_found', 'redirect', 'gone'])

/** The robots value of every page outside the backend's production environment. */
export const SEO_STAGING_ROBOTS = 'noindex, nofollow'

/**
 * The URL to resolve for a route's full path: the path and query without
 * the hash, or null for internal paths (/_nuxt, /__nuxt_error, /_journal …,
 * /api/…) that are never pages.
 */
export function seoResolvableUrl(fullPath: string): string | null {
  const url = fullPath.split('#')[0] ?? ''
  if (!url.startsWith('/') || url.startsWith('//')) return null
  if (url.startsWith('/_') || url === '/api' || url.startsWith('/api/') || url.startsWith('/api?')) return null
  return url
}

/** The answer when `value` has the shape of a resolve answer, else null. */
export function seoAnswer(value: unknown): SeoResolveAnswer | null {
  if (!value || typeof value !== 'object') return null
  const v = value as Partial<SeoResolveAnswer>
  if (typeof v.action !== 'string' || !ACTIONS.has(v.action) || typeof v.status !== 'number') return null
  if (v.seo !== null && v.seo !== undefined && typeof v.seo !== 'object') return null
  return { ...v, url: typeof v.url === 'string' ? v.url : '', staging: v.staging === true, seo: v.seo ?? null } as SeoResolveAnswer
}

/**
 * Where a redirect answer sends the visitor. A target on the site's own
 * origin (the origin of answer.url) becomes a path, so a staging or preview
 * host keeps the visitor even when the backend's site URL names production;
 * any other target stays absolute and external. Null when the answer is not
 * a redirect or has no usable location.
 */
export function seoRedirectTarget(answer: SeoResolveAnswer): { to: string; external: boolean; code: number } | null {
  if (answer.action !== 'redirect' || !answer.location) return null
  const code = answer.status === 302 ? 302 : 301
  let target: URL
  try {
    target = new URL(answer.location, answer.url || 'http://site.invalid')
  } catch {
    return null
  }
  if (target.protocol !== 'http:' && target.protocol !== 'https:') return null
  let site: URL | null = null
  try {
    site = answer.url ? new URL(answer.url) : null
  } catch {
    site = null
  }
  if (!site || target.origin === site.origin || target.origin === 'http://site.invalid') {
    return { to: `${target.pathname}${target.search}${target.hash}`, external: false, code }
  }
  return { to: target.href, external: true, code }
}

/** The robots value for the page: noindex everywhere on staging, else the answer's robots on ok, else "". */
export function seoRobots(answer: SeoResolveAnswer | null): string {
  if (!answer) return ''
  if (answer.staging) return SEO_STAGING_ROBOTS
  if (answer.action === 'ok' && answer.seo?.robots) return answer.seo.robots
  return ''
}

/** The X-Robots-Tag header value, "" for none. */
export function seoXRobotsTag(answer: SeoResolveAnswer | null): string {
  if (!answer) return ''
  if (answer.staging) return SEO_STAGING_ROBOTS
  if (answer.action === 'ok' && answer.seo?.x_robots_tag) return answer.seo.x_robots_tag
  return ''
}

interface SeoHeadInput {
  title?: string
  titleTemplate?: string
  meta: Array<{ name?: string; property?: string; content: string }>
  link: Array<{ rel: string; href: string }>
}

/**
 * `value` made absolute on `origin` when it is a path ("/x"); anything else
 * is returned as it is. The plugin answers paths when the backend has no
 * site URL (golem15.seo.site_url, app.url), and a canonical or social URL
 * must be absolute.
 */
export function seoAbsolute(value: string, origin: string | undefined): string {
  if (!origin || !value.startsWith('/') || value.startsWith('//')) return value
  return origin.replace(/\/+$/, '') + value
}

/**
 * The head of an answer. Only non-empty values become tags, so the page's
 * own tag stays wherever the answer has none. The title is final (the
 * plugin applies its templates), hence the plain titleTemplate. A not_found
 * answer, or no answer, contributes only the staging robots. A canonical,
 * og:url or og:image that is a path is made absolute on `origin` (the
 * request's origin).
 */
export function seoHeadInput(answer: SeoResolveAnswer | null, origin?: string): SeoHeadInput {
  const head: SeoHeadInput = { meta: [], link: [] }
  const robots = seoRobots(answer)
  if (robots) head.meta.push({ name: 'robots', content: robots })
  const seo = answer?.action === 'ok' ? answer.seo : null
  if (!seo) return head
  const name = (n: string, content: string | undefined) => {
    if (content) head.meta.push({ name: n, content })
  }
  const property = (p: string, content: string | undefined) => {
    if (content) head.meta.push({ property: p, content })
  }
  if (seo.title) {
    head.title = seo.title
    head.titleTemplate = '%s'
  }
  name('description', seo.description)
  property('og:title', seo.og?.title)
  property('og:description', seo.og?.description)
  property('og:image', seo.og?.image && seoAbsolute(seo.og.image, origin))
  property('og:url', seo.og?.url && seoAbsolute(seo.og.url, origin))
  name('twitter:card', seo.twitter?.card)
  name('twitter:site', seo.twitter?.site)
  for (const tag of Array.isArray(seo.verification) ? seo.verification : []) {
    if (tag && typeof tag.name === 'string' && tag.name && typeof tag.content === 'string' && tag.content) {
      head.meta.push({ name: tag.name, content: tag.content })
    }
  }
  if (seo.canonical) head.link.push({ rel: 'canonical', href: seoAbsolute(seo.canonical, origin) })
  return head
}

/** A verification file name the plugin serves: [A-Za-z0-9._-]+ ending .html, .txt or .xml. */
export const SEO_VERIFICATION_FILE = /^\/([A-Za-z0-9][A-Za-z0-9._-]*\.(?:html|txt|xml))$/

/**
 * The verification file name of a request path, or null. Names the site
 * serves itself (robots.txt, sitemap.xml, rss.xml and the like) are never
 * looked up.
 */
export function seoVerificationName(path: string, reserved: readonly string[]): string | null {
  const m = SEO_VERIFICATION_FILE.exec(path.split('?')[0] ?? '')
  if (!m || !m[1]) return null
  return reserved.includes(m[1].toLowerCase()) ? null : m[1]
}