feat: convert site to astro via codex

www/tools/audit-links.mjs

@@ -0,0 +1,110 @@
+import fs from 'node:fs/promises';
+import path from 'node:path';
+import fg from 'fast-glob';
+import matter from 'gray-matter';
+
+const root = path.resolve(new URL('..', import.meta.url).pathname);
+const dist = path.join(root, 'dist');
+const normalizePath = (value) => {
+  const decoded = decodeURIComponent(value).replace(/\/index(?:\.html)?$/, '/').replace(/\.html$/, '');
+  return decoded !== '/' ? decoded.replace(/\/$/, '') : decoded;
+};
+const contentRoute = (file, data) => {
+  if (!data.slug || data.draft) return null;
+  const languagePrefix = data.lang === 'en' ? '' : `/${data.lang}`;
+  if (file.includes('/blog/')) return `${languagePrefix}/library/${data.slug}`;
+  if (data.slug === 'index') return languagePrefix || '/';
+  if (data.slug === 'library') return `${languagePrefix}/library`;
+  return `${languagePrefix}/${data.slug}`;
+};
+const resolveInternalReference = (reference, route) => {
+  const cleaned = reference.trim().replace(/^<|>$/g, '');
+  if (!cleaned || cleaned.startsWith('#') || /^[a-z][a-z\d+.-]*:/i.test(cleaned) || cleaned.startsWith('//')) return null;
+  try {
+    const base = new URL(route, 'https://audit.local');
+    const resolved = new URL(cleaned, base);
+    return normalizePath(resolved.pathname);
+  } catch {
+    return cleaned;
+  }
+};
+async function walk(dir) {
+  const output = [];
+  for (const entry of await fs.readdir(dir, { withFileTypes: true })) {
+    const target = path.join(dir, entry.name);
+    if (entry.isDirectory()) output.push(...await walk(target));
+    else if (entry.name.endsWith('.html')) output.push(path.relative(dist, target));
+  }
+  return output;
+}
+const distExists = await fs.access(dist).then(() => true).catch(() => false);
+if (!distExists) {
+  const routes = new Set(['/', '/library', '/es', '/es/library', '/ar', '/ar/library']);
+  const contentFiles = await fg('src/content/**/*.{md,mdx}', { cwd: root, absolute: true });
+  const contentRecords = [];
+  for (const file of contentFiles) {
+    const parsed = matter(await fs.readFile(file, 'utf8'));
+    const route = contentRoute(file, parsed.data);
+    if (!route) continue;
+    routes.add(normalizePath(route));
+    contentRecords.push({ file, route: normalizePath(route), text: parsed.content });
+  }
+  const publicFiles = new Set((await fg('public/**/*', { cwd: root, onlyFiles: true })).map((file) => `/${file.replace(/^public\//, '')}`));
+  const broken = [];
+
+  for (const { file, route, text } of contentRecords) {
+    if (file.includes('/pages/') && ['/library', '/es/library', '/ar/library', '/', '/es', '/ar'].includes(route)) continue;
+    const references = [...text.matchAll(/\]\(([^)\s]+)(?:\s+["'][^)]*)?\)/g)].map((match) => match[1]);
+    for (const rawReference of references) {
+      const reference = resolveInternalReference(rawReference, route);
+      if (!reference) continue;
+      if (reference.startsWith('/assets/')) {
+        if (!publicFiles.has(reference)) broken.push(`${path.relative(root, file)}: ${rawReference} -> ${reference}`);
+      } else if (!routes.has(reference)) {
+        broken.push(`${path.relative(root, file)}: ${rawReference} -> ${reference}`);
+      }
+    }
+  }
+
+  const sourceFiles = await fg('src/**/*.{astro,ts,js,json}', { cwd: root, absolute: true });
+  for (const file of sourceFiles) {
+    const text = await fs.readFile(file, 'utf8');
+    const references = [
+      ...text.matchAll(/(?:href|src)=["'](\/[^"'#?{]*)/g),
+      ...text.matchAll(/\]\((\/[^)#?]*)/g)
+    ].map((match) => normalizePath(match[1]));
+    for (const reference of references) {
+      if (reference.startsWith('/assets/') || reference === '/robots.txt' || reference === '/sitemap.xml') {
+        if (!publicFiles.has(reference)) broken.push(`${path.relative(root, file)}: ${reference}`);
+      } else if (!routes.has(reference)) {
+        broken.push(`${path.relative(root, file)}: ${reference}`);
+      }
+    }
+  }
+  const unique = [...new Set(broken)].sort();
+  const report = unique.length
+    ? `# Broken Links\n\nRendered output is unavailable in the sandbox; source routes and public assets were audited.\n\n${unique.map((item) => `- ${item}`).join('\n')}\n`
+    : '# Broken Links\n\nRendered output is unavailable in the sandbox; source routes and public assets were audited. No broken internal source links were detected.\n';
+  await fs.writeFile(path.join(root, 'reports/broken-links.md'), report);
+  console.log(`${unique.length} broken internal source links.`);
+  if (unique.length) process.exitCode = 1;
+  process.exit();
+}
+const files = await walk(dist);
+const broken = [];
+for (const file of files) {
+  const html = await fs.readFile(path.join(dist, file), 'utf8');
+  for (const match of html.matchAll(/(?:href|src)="(\/[^"#?]*)/g)) {
+    const url = match[1];
+    if (url.startsWith('/assets/')) {
+      if (!await fs.access(path.join(dist, url)).then(() => true).catch(() => false)) broken.push(`${file}: ${url}`);
+      continue;
+    }
+    const candidates = [path.join(dist, url, 'index.html'), path.join(dist, `${url}.html`), path.join(dist, url)];
+    if (!await Promise.any(candidates.map((candidate) => fs.access(candidate))).then(() => true).catch(() => false)) broken.push(`${file}: ${url}`);
+  }
+}
+const report = broken.length ? `# Broken Links\n\n${broken.map((item) => `- ${item}`).join('\n')}\n` : '# Broken Links\n\nNo broken internal build links detected.\n';
+await fs.writeFile(path.join(root, 'reports/broken-links.md'), report);
+console.log(`${broken.length} broken internal links.`);
+if (broken.length) process.exitCode = 1;

www/tools/crawl-live-site.mjs

@@ -0,0 +1,14 @@
+import fs from 'node:fs/promises';
+
+const start = 'https://www.azinstitute4autism.com';
+const output = new URL('../reports/live-crawl.json', import.meta.url);
+try {
+  const response = await fetch(start, { redirect: 'follow' });
+  const result = { url: start, status: response.status, checkedAt: new Date().toISOString() };
+  await fs.writeFile(output, `${JSON.stringify(result, null, 2)}\n`);
+  console.log(`Live site returned ${response.status}.`);
+} catch (error) {
+  await fs.writeFile(output, `${JSON.stringify({ url: start, error: String(error) }, null, 2)}\n`);
+  console.error(`Live crawl unavailable: ${error.message}`);
+  process.exitCode = 1;
+}

www/tools/extract-fallback.mjs

@@ -0,0 +1,203 @@
+import fs from 'node:fs/promises';
+import path from 'node:path';
+import { fileURLToPath } from 'node:url';
+
+const root = path.resolve(path.dirname(fileURLToPath(import.meta.url)), '..');
+const mirror = path.resolve(root, '../www.azinstitute4autism.com');
+const content = path.join(root, 'src/content');
+const assets = path.join(root, 'public/assets');
+const reports = path.join(root, 'reports');
+const site = 'https://www.azinstitute4autism.com';
+const mkdir = (value) => fs.mkdir(value, { recursive: true });
+const quote = (value = '') => JSON.stringify(String(value).replace(/\s+/g, ' ').trim());
+const csv = (value = '') => `"${String(value).replaceAll('"', '""')}"`;
+
+async function walk(dir, prefix = '') {
+  const output = [];
+  for (const entry of await fs.readdir(dir, { withFileTypes: true })) {
+    const relative = path.join(prefix, entry.name);
+    if (entry.isDirectory()) output.push(...await walk(path.join(dir, entry.name), relative));
+    else output.push(relative);
+  }
+  return output;
+}
+
+function logical(file) {
+  return file.replace(/(?:\.html)?\?(?:hsLang=[^.]+|hs_amp=true)\.html$/, '.html');
+}
+
+function selectCanonical(files) {
+  const map = new Map();
+  for (const file of files) {
+    if (!file.endsWith('.html') || file.includes('hs_amp=true') || /\/(?:page|author)\//.test(file)) continue;
+    const target = logical(file);
+    const key = `${target.startsWith('ar/') ? 'ar' : target.startsWith('es/') ? 'es' : 'en'}:${target}`;
+    if (!map.has(key) || (!file.includes('?') && map.get(key).includes('?'))) map.set(key, file);
+  }
+  return [...map.values()];
+}
+
+function decode(value = '') {
+  return value
+    .replace(/&#(\d+);/g, (_, code) => String.fromCodePoint(Number(code)))
+    .replace(/&#x([\da-f]+);/gi, (_, code) => String.fromCodePoint(parseInt(code, 16)))
+    .replaceAll('&', '&').replaceAll('"', '"').replaceAll(''', "'")
+    .replaceAll('&lt;', '<').replaceAll('&gt;', '>').replaceAll('&nbsp;', ' ');
+}
+
+function text(value = '') {
+  return decode(value.replace(/<[^>]+>/g, ' ')).replace(/\s+/g, ' ').trim();
+}
+
+function normalizeHref(value = '') {
+  return decode(value)
+    .replace(/^https?:\/\/www\.azinstitute4autism\.com/, '')
+    .replace(/(?:\.html)?(?:%3F|\?)(?:hsLang=[^.#]+|hs_amp=true)(?:\.html)?$/, '')
+    .replace(/\.html$/, '')
+    .replace(/^index$/, '/');
+}
+
+function inline(value = '') {
+  return text(value.replace(/<a[^>]+href=["']([^"']+)["'][^>]*>([\s\S]*?)<\/a>/gi, (_, href, label) => {
+    const cleanLabel = text(label);
+    return cleanLabel ? `[${cleanLabel}](${normalizeHref(href)})` : '';
+  }));
+}
+
+function meta(html, name, property = false) {
+  const key = property ? 'property' : 'name';
+  const pattern = new RegExp(`<meta[^>]+${key}=["']${name}["'][^>]+content=["']([^"']*)`, 'i');
+  const reverse = new RegExp(`<meta[^>]+content=["']([^"']*)["'][^>]+${key}=["']${name}["']`, 'i');
+  return decode(html.match(pattern)?.[1] || html.match(reverse)?.[1] || '');
+}
+
+function asset(value = '') {
+  const match = value.match(/(?:hs-fs\/)?hubfs\/([^?#]+)/);
+  return match ? `/assets/images/${path.basename(decodeURIComponent(match[1])).split('?')[0]}` : undefined;
+}
+
+function markdownFrom(html) {
+  let body = html.match(/<main[\s\S]*?<\/main>/i)?.[0] ||
+    html.match(/blog-post__body[\s\S]*?(?=<footer|blog-post__tags|<\/article>)/i)?.[0] ||
+    '';
+  body = body
+    .replace(/<(script|style|noscript|header|footer|nav|form)\b[\s\S]*?<\/\1>/gi, '')
+    .replace(/<img[^>]+src=["']([^"']+)["'][^>]*alt=["']([^"']*)["'][^>]*>/gi, (_, src, alt) => {
+      const local = asset(src);
+      return local ? `\n\n![${text(alt)}](${local})\n\n` : '';
+    })
+    .replace(/<h([1-6])[^>]*>([\s\S]*?)<\/h\1>/gi, (_, level, value) => `\n\n${'#'.repeat(Number(level))} ${inline(value)}\n\n`)
+    .replace(/<li[^>]*>([\s\S]*?)<\/li>/gi, (_, value) => `\n- ${inline(value)}`)
+    .replace(/<p[^>]*>([\s\S]*?)<\/p>/gi, (_, value) => `\n\n${inline(value)}\n\n`)
+    .replace(/<br\s*\/?>/gi, '\n')
+    .replace(/<[^>]+>/g, ' ');
+  return decode(body).replace(/[ \t]+/g, ' ').replace(/^\s+$/gm, '').replace(/\n{3,}/g, '\n\n').trim();
+}
+
+function record(file, html) {
+  const target = logical(file);
+  const lang = target.startsWith('ar/') ? 'ar' : target.startsWith('es/') ? 'es' : 'en';
+  const url = target === 'index.html' ? '/' : `/${target.replace(/\/index\.html$/, '').replace(/\.html$/, '')}`;
+  const title = text(html.match(/<title[^>]*>([\s\S]*?)<\/title>/i)?.[1] || url);
+  const h1 = text(html.match(/<h1[^>]*>([\s\S]*?)<\/h1>/i)?.[1] || title);
+  const published = meta(html, 'article:published_time', true) ||
+    html.match(/<time[^>]+datetime=["']([^"']+)/i)?.[1] || '';
+  return {
+    file, lang, url, title, h1,
+    description: meta(html, 'description'),
+    image: asset(meta(html, 'og:image', true)),
+    date: /^\d{4}-\d{2}-\d{2}/.test(published) ? published.slice(0, 10) : '2024-01-01',
+    markdown: markdownFrom(html)
+  };
+}
+
+function frontmatter(item, blog) {
+  const slug = ['/', '/ar', '/es'].includes(item.url) ? 'index' : item.url.split('/').filter(Boolean).at(-1);
+  const lines = [
+    '---',
+    `title: ${quote(item.title)}`,
+    `description: ${quote(item.description)}`,
+    `slug: ${quote(slug)}`,
+    `canonical: ${quote(`${site}${item.url}`)}`,
+    `lang: ${quote(item.lang)}`,
+    `translationKey: ${quote(slug)}`,
+    item.image ? `featuredImage: ${quote(item.image)}` : '',
+    blog ? `date: "${item.date}"` : '',
+    blog ? 'author: "rula-diab"' : '',
+    blog ? 'category: "Library"' : '',
+    blog ? 'tags: []' : '',
+    'draft: false',
+    '---',
+    '',
+    item.markdown || `# ${item.h1}`,
+    ''
+  ].filter((line) => line !== '');
+  return `${lines.join('\n')}\n`;
+}
+
+async function copySourceAssets(files) {
+  const rows = ['source,target,size,kind'];
+  const seen = new Set();
+  await Promise.all(['images', 'fonts', 'downloads'].map((kind) => fs.rm(path.join(assets, kind), { recursive: true, force: true })));
+  for (const file of files.filter((name) => name.startsWith('hubfs/') || name.startsWith('hs-fs/hubfs/') || name.startsWith('_hcms/googlefonts/'))) {
+    const font = file.startsWith('_hcms/googlefonts/');
+    const raw = font ? file.replace('_hcms/googlefonts/', '') : path.basename(file).split('?')[0];
+    if (!font && !/\.(?:avif|gif|jpe?g|png|svg|webp|pdf)$/i.test(raw)) continue;
+    const key = `${font}:${raw}`;
+    if (!raw || seen.has(key)) continue;
+    seen.add(key);
+    const kind = font ? 'fonts' : raw.endsWith('.pdf') ? 'downloads' : 'images';
+    const target = path.join(assets, kind, raw);
+    await mkdir(path.dirname(target));
+    await fs.copyFile(path.join(mirror, file), target);
+    const size = (await fs.stat(target)).size;
+    rows.push([file, path.relative(root, target), size, kind].map(csv).join(','));
+  }
+  await fs.writeFile(path.join(reports, 'asset-inventory.csv'), `${rows.join('\n')}\n`);
+}
+
+async function removeMissingFeaturedImages() {
+  for (const type of ['pages', 'blog']) {
+    for (const file of await walk(path.join(content, type))) {
+      const target = path.join(content, type, file);
+      let source = await fs.readFile(target, 'utf8');
+      const image = source.match(/^featuredImage:\s*"\/assets\/images\/([^"]+)"/m)?.[1];
+      if (!image) continue;
+      if (!await fs.access(path.join(assets, 'images', image)).then(() => true).catch(() => false)) {
+        source = source.replace(/^featuredImage:.*\n/m, '');
+        await fs.writeFile(target, source);
+      }
+    }
+  }
+}
+
+async function main() {
+  const files = await walk(mirror);
+  const selected = selectCanonical(files);
+  const records = [];
+  for (const file of selected) records.push(record(file, await fs.readFile(path.join(mirror, file), 'utf8')));
+  await Promise.all(['pages', 'blog', 'authors'].map((type) => fs.rm(path.join(content, type), { recursive: true, force: true })));
+  for (const lang of ['en', 'ar', 'es']) {
+    for (const type of ['pages', 'blog', 'authors']) await mkdir(path.join(content, type, lang));
+  }
+  for (const item of records) {
+    const blog = item.url.includes('/library/') && !item.url.endsWith('/library');
+    const slug = ['/', '/ar', '/es'].includes(item.url) ? 'index' : item.url.split('/').filter(Boolean).at(-1);
+    await fs.writeFile(path.join(content, blog ? 'blog' : 'pages', item.lang, `${slug}.md`), frontmatter(item, blog));
+  }
+  for (const lang of ['en', 'ar', 'es']) {
+    await fs.writeFile(path.join(content, 'authors', lang, 'rula-diab.md'), `---\nname: "Rula Diab"\nslug: "rula-diab"\ndescription: "Founder and clinical leader at Arizona Institute for Autism."\navatar: "/assets/images/rula-diab-avatar.jpg"\nlang: "${lang}"\ntranslationKey: "rula-diab"\n---\n`);
+  }
+  if (!records.some((item) => item.lang === 'ar' && item.url === '/ar')) {
+    await fs.writeFile(path.join(content, 'pages/ar/index.md'), `---\ntitle: "معهد أريزونا للتوحد"\ndescription: "صفحة عربية تمهيدية لمعهد أريزونا للتوحد."\nslug: "index"\ncanonical: "https://www.azinstitute4autism.com/ar"\nlang: "ar"\ntranslationKey: "home"\ndraft: false\n---\n\n<!-- TODO: Replace this placeholder with reviewed Arabic content. -->\n\nتتوفر المقالات العربية الحالية في المكتبة. يرجى مراجعة المحتوى العربي قبل النشر.\n`);
+  }
+  const rows = ['source_file,url,language,type,title,description,h1'];
+  for (const item of records) rows.push([item.file, item.url, item.lang, item.url.includes('/library/') ? 'blog' : 'page', item.title, item.description, item.h1].map(csv).join(','));
+  await mkdir(reports);
+  await fs.writeFile(path.join(reports, 'url-inventory.csv'), `${rows.join('\n')}\n`);
+  await copySourceAssets(files);
+  await removeMissingFeaturedImages();
+  console.log(`Fallback extraction completed: ${records.length} canonical records.`);
+}
+
+await main();

www/tools/extract-site.mjs

@@ -0,0 +1,178 @@
+import fs from 'node:fs/promises';
+import path from 'node:path';
+import { fileURLToPath } from 'node:url';
+import fg from 'fast-glob';
+import { load } from 'cheerio';
+import TurndownService from 'turndown';
+import matter from 'gray-matter';
+
+const root = path.resolve(path.dirname(fileURLToPath(import.meta.url)), '..');
+const mirror = path.resolve(root, '../www.azinstitute4autism.com');
+const site = 'https://www.azinstitute4autism.com';
+const contentRoot = path.join(root, 'src/content');
+const publicRoot = path.join(root, 'public/assets');
+const reportsRoot = path.join(root, 'reports');
+const turndown = new TurndownService({ headingStyle: 'atx', bulletListMarker: '-' });
+turndown.remove(['script', 'style', 'noscript', 'iframe']);
+
+const mkdir = (dir) => fs.mkdir(dir, { recursive: true });
+const clean = (value = '') => value.replace(/\s+/g, ' ').trim();
+const csv = (value = '') => `"${String(value).replaceAll('"', '""')}"`;
+const yaml = (value = '') => JSON.stringify(String(value));
+function logicalFile(file) {
+  return file.replace(/(?:\.html)?\?(?:hsLang=[^.]+|hs_amp=true)\.html$/, '.html');
+}
+
+function canonicalFiles(files) {
+  const selected = new Map();
+  for (const file of files) {
+    if (!file.endsWith('.html') || /\/(?:page|author)\//.test(file) || file.includes('hs_amp=true')) continue;
+    const logical = logicalFile(file);
+    const lang = logical.startsWith('ar/') ? 'ar' : logical.startsWith('es/') ? 'es' : 'en';
+    const key = `${lang}:${logical}`;
+    const current = selected.get(key);
+    if (!current || (!file.includes('?') && current.includes('?'))) selected.set(key, file);
+  }
+  return [...selected.values()];
+}
+
+function sourceUrl(file) {
+  const logical = logicalFile(file);
+  if (logical === 'index.html') return '/';
+  return `/${logical.replace(/\/index\.html$/, '').replace(/\.html$/, '')}`;
+}
+
+function languageFor(file, $) {
+  if (file.startsWith('ar/')) return 'ar';
+  if (file.startsWith('es/')) return 'es';
+  return $('html').attr('lang')?.split('-')[0] || 'en';
+}
+
+function localizeAsset(value = '') {
+  const decoded = value.replace(/^https?:\/\/[^/]+/, '').replace(/^\.\.\//, '/');
+  const match = decoded.match(/(?:\/)?(?:hs-fs\/)?hubfs\/([^?#]+)/);
+  if (!match) return undefined;
+  return `/assets/images/${path.basename(decodeURIComponent(match[1])).split('?')[0]}`;
+}
+
+function extractRecord(file, html) {
+  const $ = load(html);
+  const lang = languageFor(file, $);
+  const url = sourceUrl(file);
+  const title = clean($('title').first().text()) || clean($('h1').first().text()) || url;
+  const description = $('meta[name="description"]').attr('content') || '';
+  const h1 = clean($('h1').first().text());
+  const image = localizeAsset(
+    $('meta[property="og:image"]').attr('content') ||
+    $('.blog-post__body img, main img, .body-container-wrapper img').first().attr('src') ||
+    ''
+  );
+  const alt = clean($('.blog-post__body img, main img, .body-container-wrapper img').first().attr('alt') || '');
+  const dateText = $('meta[property="article:published_time"]').attr('content') ||
+    $('time').first().attr('datetime') || '2024-01-01';
+  const date = /^\d{4}-\d{2}-\d{2}/.test(dateText) ? dateText.slice(0, 10) : '2024-01-01';
+  const selector = file.includes('/library/') ? '.blog-post__body' : 'main, .body-container-wrapper';
+  const body = $(selector).first().clone();
+  body.find('header, footer, nav, form, script, style, noscript, .hs_cos_wrapper_type_form').remove();
+  body.find('*').removeAttr('style').removeAttr('id').removeAttr('data-hs-cos-general-type').removeAttr('data-hs-cos-type');
+  body.find('a').each((_, element) => {
+    const href = $(element).attr('href');
+    if (!href) return;
+    $(element).attr('href', href
+      .replace(/\.html(?:%3F|\?)[^"]*$/, '')
+      .replace(/\.html$/, '')
+      .replace(/^index$/, '/'));
+  });
+  body.find('img').each((_, element) => {
+    const src = localizeAsset($(element).attr('src'));
+    if (src) $(element).attr('src', src);
+  });
+  const markdown = turndown.turndown(body.html() || '').replace(/\n{3,}/g, '\n\n').trim();
+  return { file, lang, url, title, description, h1, image, alt, date, markdown };
+}
+
+function frontmatter(record, type) {
+  const slug = ['/', '/ar', '/es'].includes(record.url) ? 'index' : record.url.split('/').filter(Boolean).at(-1);
+  const data = {
+    title: record.title,
+    description: record.description,
+    slug,
+    canonical: `${site}${record.url}`,
+    lang: record.lang,
+    translationKey: slug,
+    draft: false
+  };
+  if (record.image) data.featuredImage = record.image;
+  if (record.alt) data.alt = record.alt;
+  if (type === 'blog') Object.assign(data, {
+    date: record.date,
+    author: 'rula-diab',
+    category: 'Library',
+    tags: []
+  });
+  return matter.stringify(record.markdown || `# ${record.h1 || record.title}\n`, data);
+}
+
+async function copyAssets() {
+  const assets = await fg(['hubfs/*', 'hs-fs/hubfs/*', '_hcms/googlefonts/**/*'], { cwd: mirror, onlyFiles: true });
+  const inventory = ['source,target,size,kind'];
+  const seen = new Set();
+  await Promise.all(['images', 'fonts', 'downloads'].map((kind) => fs.rm(path.join(publicRoot, kind), { recursive: true, force: true })));
+  for (const source of assets) {
+    const original = path.join(mirror, source);
+    const stat = await fs.stat(original);
+    const isFont = source.startsWith('_hcms/googlefonts/');
+    const rawName = isFont ? source.replace('_hcms/googlefonts/', '') : path.basename(source).split('?')[0];
+    if (!isFont && !/\.(?:avif|gif|jpe?g|png|svg|webp|pdf)$/i.test(rawName)) continue;
+    if (!rawName || seen.has(`${isFont}:${rawName}`)) continue;
+    seen.add(`${isFont}:${rawName}`);
+    const target = path.join(publicRoot, isFont ? 'fonts' : rawName.endsWith('.pdf') ? 'downloads' : 'images', rawName);
+    await mkdir(path.dirname(target));
+    await fs.copyFile(original, target);
+    inventory.push([source, path.relative(root, target), stat.size, isFont ? 'font' : path.extname(rawName).slice(1)].map(csv).join(','));
+  }
+  await fs.writeFile(path.join(reportsRoot, 'asset-inventory.csv'), `${inventory.join('\n')}\n`);
+}
+
+async function main() {
+  await Promise.all([
+    mkdir(contentRoot), mkdir(publicRoot), mkdir(reportsRoot),
+    ...['en', 'ar', 'es'].flatMap((lang) => [
+      mkdir(path.join(contentRoot, 'pages', lang)),
+      mkdir(path.join(contentRoot, 'blog', lang)),
+      mkdir(path.join(contentRoot, 'authors', lang))
+    ])
+  ]);
+  const files = canonicalFiles(await fg(['**/*.html'], { cwd: mirror, onlyFiles: true }));
+  const records = [];
+  for (const file of files) records.push(extractRecord(file, await fs.readFile(path.join(mirror, file), 'utf8')));
+  const corePages = new Set(records.filter((r) => !r.file.includes('/library/') && !r.file.startsWith('library/')).map((r) => r.file));
+  for (const record of records) {
+    const isBlog = record.file.includes('/library/') || record.file.startsWith('library/');
+    if (!isBlog && !corePages.has(record.file)) continue;
+    const slug = ['/', '/ar', '/es'].includes(record.url) ? 'index' : record.url.split('/').filter(Boolean).at(-1);
+    const target = path.join(contentRoot, isBlog ? 'blog' : 'pages', record.lang, `${slug}.md`);
+    await fs.writeFile(target, frontmatter(record, isBlog ? 'blog' : 'page'));
+  }
+  for (const lang of ['en', 'ar', 'es']) {
+    await fs.writeFile(path.join(contentRoot, 'authors', lang, 'rula-diab.md'), matter.stringify('', {
+      name: 'Rula Diab',
+      slug: 'rula-diab',
+      description: 'Founder and clinical leader at Arizona Institute for Autism.',
+      avatar: '/assets/images/rula-diab-avatar.jpg',
+      lang,
+      translationKey: 'rula-diab'
+    }));
+  }
+  const urlRows = ['source_file,url,language,type,title,description,h1'];
+  for (const record of records) urlRows.push([
+    record.file, record.url, record.lang,
+    record.file.includes('/library/') || record.file.startsWith('library/') ? 'blog' : 'page',
+    record.title, record.description, record.h1
+  ].map(csv).join(','));
+  await fs.writeFile(path.join(reportsRoot, 'url-inventory.csv'), `${urlRows.join('\n')}\n`);
+  await copyAssets();
+  console.log(`Extracted ${records.length} canonical pages and posts.`);
+}
+
+await main();

www/tools/generate-redirects.mjs

@@ -0,0 +1,12 @@
+import fs from 'node:fs/promises';
+
+const redirects = [
+  { from: '/aba', to: '/aba-therapy', status: 301, reason: 'Brief alias to preserved mirror URL' },
+  { from: '/autismevaluations', to: '/autism-evaluations', status: 301, reason: 'Brief alias to preserved mirror URL' },
+  { from: '/learnersocialclub', to: '/learner-social-club', status: 301, reason: 'Brief alias to preserved mirror URL' }
+];
+await fs.writeFile(new URL('../src/data/redirects.json', import.meta.url), `${JSON.stringify(redirects, null, 2)}\n`);
+await fs.writeFile(new URL('../reports/redirect-map.csv', import.meta.url),
+  `from,to,status,reason\n${redirects.map((r) => `"${r.from}","${r.to}",${r.status},"${r.reason}"`).join('\n')}\n`);
+await fs.writeFile(new URL('../reports/nginx-rewrites.conf', import.meta.url),
+  `${redirects.map((r) => `rewrite ^${r.from}$ ${r.to} permanent;`).join('\n')}\n`);

www/tools/generate-sitemap.mjs

@@ -0,0 +1,24 @@
+import fs from 'node:fs/promises';
+import path from 'node:path';
+
+const root = path.resolve(new URL('..', import.meta.url).pathname);
+async function walk(dir) {
+  const output = [];
+  for (const entry of await fs.readdir(dir, { withFileTypes: true })) {
+    const target = path.join(dir, entry.name);
+    if (entry.isDirectory()) output.push(...await walk(target));
+    else if (entry.name.endsWith('.md')) output.push(target);
+  }
+  return output;
+}
+const files = [...await walk(path.join(root, 'src/content/pages')), ...await walk(path.join(root, 'src/content/blog'))];
+const urls = [];
+for (const file of files) {
+  const source = await fs.readFile(file, 'utf8');
+  const canonical = source.match(/^canonical:\s*["']?([^"'\n]+)["']?/m)?.[1];
+  const draft = source.match(/^draft:\s*(true|false)/m)?.[1] === 'true';
+  if (canonical && !draft) urls.push(canonical);
+}
+const xml = `<?xml version="1.0" encoding="UTF-8"?>\n<urlset xmlns="http://www.sitemaps.org/schemas/sitemap/0.9">\n${urls.sort().map((url) => `  <url><loc>${url}</loc></url>`).join('\n')}\n</urlset>\n`;
+await fs.writeFile(path.join(root, 'public/sitemap.xml'), xml);
+console.log(`Generated sitemap with ${urls.length} URLs.`);

www/tools/localhost-dns.cjs

@@ -0,0 +1,24 @@
+// Sandbox-only validation helper: the autonomous profile cannot read /etc/hosts.
+const dns = require('node:dns');
+
+const originalLookup = dns.lookup;
+dns.lookup = function lookup(hostname, options, callback) {
+  if (hostname !== 'localhost') return originalLookup.apply(this, arguments);
+
+  if (typeof options === 'function') {
+    callback = options;
+    options = {};
+  }
+
+  if (options?.all) {
+    return process.nextTick(callback, null, [{ address: '127.0.0.1', family: 4 }]);
+  }
+  return process.nextTick(callback, null, '127.0.0.1', 4);
+};
+
+const originalPromiseLookup = dns.promises.lookup;
+dns.promises.lookup = async function lookup(hostname, options) {
+  if (hostname !== 'localhost') return originalPromiseLookup.call(this, hostname, options);
+  if (options?.all) return [{ address: '127.0.0.1', family: 4 }];
+  return { address: '127.0.0.1', family: 4 };
+};