Free early-access launch: LAUNCH_MODE policy, CRO, pipeline hardening, AI-SEO, ops

- launch.ts policy: LAUNCH_MODE=free_early_access default; effective access = published && (free || early); intended tier (access) never rewritten - Billing off server-side: /api/subscribe 503 honest copy; subscribe CTAs render disabled 'قريباً' from first paint; /subscription early-access panel + /api/notify (LaunchNotifications) with honest 503 when mail transport off - Signup trust: verification email at signup (Users afterChange), no confirm-password, 429 message fidelity, typo suggestion, live password hint - Agent pipeline: pickFields strips access/readingMinutes, sourceId dedup, secret-scan 422 (pattern names only), string-content rejected (was silently replaced), publish stays explicit opt-in - lexical.ts: root unwrap fix — lexicalToText/countLexicalWords returned 0 for real serialized trees (secret scan + readingMinutes were inert) - llms-full.txt: fetchIndexDocs(true) — bodies were never selected - Content honesty: contentType/authorName/sourceId fields + migration, readingMinutes computed at write (160 wpm) + backfill script, byline, 'حُدّث' freshness - SEO/AI-SEO: metadata rewrite (published-only, og:image 1200x630), Article + BreadcrumbList + FAQPage + Organization JSON-LD, isAccessibleForFree honest, table renderer, robots AI-crawler policy (10 named bots), llms.txt + llms-full.txt, /topics/* hubs + sitemap, noindex auth pages, www 301 - Ops: backup-db.sh (restore rehearsed on VPS), docs copies (launch readiness + marketing audit + owner-inputs for L-03), GLOSSARY.md entries Verified: tsc --noEmit 0, npm run build 0, local smoke (ghost VIP read, subscribe/notify/agent APIs, signup token, 429 on 6th, llms/topics/sitemap, og:image/JSON-LD)
2026-10-10 18:03:45 +03:00
parent 82414e8a93
commit 0161924088
57 changed files with 4042 additions and 402 deletions
@@ -0,0 +1,133 @@
+/**
+ * Helpers over serialized Lexical richText JSON (Payload's editor state).
+ * A serialized tree is `{ root: { children: [...] } }`; text lives on
+ * `{ text }` nodes, nesting happens via `{ children }`.
+ */
+
+export type Node = {
+  type?: string
+  text?: string
+  children?: Node[]
+  tag?: string
+  url?: string
+  listType?: string
+  code?: string
+  headerState?: number
+}
+
+/** Root `children` of a serialized tree, narrowed at runtime. */
+function rootChildren(data: unknown): Node[] | null {
+  if (data === null || typeof data !== 'object' || !('root' in data)) return null
+  const root: unknown = data.root // unknown via `in` narrowing — no shape assumed
+  if (root === null || typeof root !== 'object' || !('children' in root)) return null
+  const children: unknown = root.children
+  if (!Array.isArray(children)) return null
+  // Boundary: the array is the editor's serialized node list; every access
+  // below goes through Node's all-optional contract, so nothing unchecked.
+  const nodes: Node[] = children
+  return nodes
+}
+
+/** Concatenated text of every text node (secret scanning, llms extraction). */
+export function lexicalToText(content: unknown): string {
+  let out = ''
+  const walk = (node: unknown): void => {
+    if (node === null || typeof node !== 'object') return
+    if ('text' in node && typeof node.text === 'string') out += node.text + '\n'
+    if ('children' in node && Array.isArray(node.children)) {
+      for (const child of node.children) walk(child)
+    }
+  }
+  // Serialized trees wrap nodes in `root` — walk it, not the wrapper.
+  if (content !== null && typeof content === 'object' && 'root' in content) {
+    walk((content as { root: unknown }).root)
+  } else {
+    walk(content)
+  }
+  return out
+}
+
+/** Count whitespace-delimited words across all text nodes of a Lexical tree. */
+export function countLexicalWords(content: unknown): number {
+  let words = 0
+  const walk = (node: unknown): void => {
+    if (node === null || typeof node !== 'object') return
+    if ('text' in node && typeof node.text === 'string') {
+      words += node.text.trim().split(/\s+/).filter(Boolean).length
+    }
+    if ('children' in node && Array.isArray(node.children)) {
+      for (const child of node.children) walk(child)
+    }
+  }
+  // Same root unwrap as lexicalToText.
+  if (content !== null && typeof content === 'object' && 'root' in content) {
+    walk((content as { root: unknown }).root)
+  } else {
+    walk(content)
+  }
+  return words
+}
+
+export function innerText(nodes?: Node[]): string {
+  return (nodes || []).map(n => (n.type === 'text' ? n.text || '' : innerText(n.children))).join('')
+}
+
+/** H2 headings — TOC and the paid-mode paywall preview. */
+export function extractH2s(data: unknown): string[] {
+  const children = rootChildren(data)
+  if (!children) return []
+  return children
+    .filter(n => n.type === 'heading' && (n.tag || 'h2') === 'h2')
+    .map(n => innerText(n.children))
+}
+
+function tagLevel(tag?: string): number {
+  const n = Number.parseInt((tag ?? 'h2').replace('h', ''), 10)
+  return Number.isFinite(n) && n >= 1 && n <= 6 ? n : 2
+}
+
+/**
+ * Plain-text rendering for llms-full.txt: headings → `## `, paragraphs and
+ * list items → lines, code → fenced blocks, table rows → `| a | b |`.
+ */
+export function lexicalToPlain(data: unknown): string {
+  const children = rootChildren(data)
+  if (!children) return ''
+  const lines: string[] = []
+  for (const n of children) {
+    switch (n.type) {
+      case 'heading':
+        lines.push(`${'#'.repeat(tagLevel(n.tag))} ${innerText(n.children)}`.trim())
+        break
+      case 'paragraph':
+        lines.push(innerText(n.children).trim())
+        break
+      case 'list':
+        for (const item of n.children || []) lines.push(`- ${innerText(item.children).trim()}`)
+        break
+      case 'listitem':
+        lines.push(`- ${innerText(n.children).trim()}`)
+        break
+      case 'code':
+        lines.push('```\n' + (n.code ?? innerText(n.children)) + '\n```')
+        break
+      case 'table':
+        for (const row of n.children || []) {
+          const cells = (row.children || []).map(cell => innerText(cell.children).trim().replace(/\|/g, '\\|'))
+          lines.push(`| ${cells.join(' | ')} |`)
+        }
+        break
+      case 'quote':
+        lines.push(`> ${innerText(n.children).trim()}`)
+        break
+      case 'horizontalrule':
+        lines.push('---')
+        break
+      default: {
+        const text = innerText(n.children).trim()
+        if (text) lines.push(text)
+      }
+    }
+  }
+  return lines.filter(line => line !== '').join('\n\n')
+}