crm-backend-matt/.scratch/lanhu-latest/extract-html-text.mjs

// 最终验证：从 Axure 页面 HTML 提取全部文本（解码 &#xHHHH; 实体），按控件类型分组
import fs from 'node:fs';
const html = fs.readFileSync('e:/code/crm-backend-matt/.scratch/lanhu-latest/team-page.html', 'utf8');

// 解码 HTML 实体
const decode = (s) => s
  .replace(/&#x([0-9A-Fa-f]+);/g, (_, h) => String.fromCodePoint(parseInt(h, 16)))
  .replace(/&#(\d+);/g, (_, d) => String.fromCodePoint(parseInt(d, 10)))
  .replace(/&nbsp;/g, ' ').replace(/&amp;/g, '&').replace(/&lt;/g, '<').replace(/&gt;/g, '>').replace(/&quot;/g, '"');

// 按 Axure 控件注释分组提取：<!-- 名称 (类型) --> 后跟 <div id="uNNN"...>...<div id="uNNN_text"...><p><span>文本</span></p>
const re = /<!--\s*(.*?)\s*-->\s*<div id="(u\d+)"[^>]*>/g;
const items = [];
let m;
while ((m = re.exec(html)) !== null) {
  const [full, comment, id] = m;
  const typeMatch = comment.match(/^(.*?)\s*[（(](.+?)[）)]$/);
  const name = typeMatch ? typeMatch[1] : comment;
  const type = typeMatch ? typeMatch[2] : '其他';
  // 在该控件开始的后续 600 字符里找 uNNN_text 的内容
  const after = html.slice(m.index, m.index + 700);
  const textRe = new RegExp(`id="${id}_text"[^>]*>[\\s\\S]*?</div>`);
  const tm = after.match(textRe);
  let text = '';
  if (tm) {
    text = (tm[0].match(/<p><span>([\s\S]*?)<\/span><\/p>/g) || [])
      .map(p => decode(p.replace(/<\/?p>/g, '').replace(/<\/?span>/g, '')))
      .join(' | ');
  }
  items.push({ id, name: decode(name), type: decode(type), text: text.trim() });
}

console.log('总控件数:', items.length);
console.log('有文本的控件:', items.filter(i => i.text).length);
console.log('\n=== 全部有文本的控件（id | 类型 | 名称 | 文本）===');
for (const i of items) {
  if (i.text) console.log(`${i.id.padEnd(7)} ${i.type.padEnd(6)} ${i.name.slice(0, 12).padEnd(12)} ${i.text.slice(0, 70)}`);
}
console.log('\n=== 类型分布 ===');
const dist = {};
items.forEach(i => dist[i.type] = (dist[i.type] || 0) + 1);
console.log(JSON.stringify(dist, null, 0));