// 提取新增商机页需求批注区关键单元格的完整文本（解码实体）
import fs from 'node:fs';

const html = fs.readFileSync('e:/code/crm-backend-matt/.scratch/lanhu-latest/v29-customer-pages/a3-1-1-2-1_raw.html', 'utf8');

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, '"');

// 需求批注六个小节的内容单元格（新建商机皮肤）
const IDS = ['u654', 'u657', 'u665', 'u673', 'u681', 'u689'];
for (const id of IDS) {
  // 匹配整个控件 div（含 _text 的嵌套 p），贪婪到该 div 结束前抓全部 <p>
  const re = new RegExp(`<div id="${id}"[\\s\\S]*?id="${id}_text"[\\s\\S]*?</div>\\s*</div>`);
  const m = html.match(re);
  if (!m) { console.log(`\n### ${id}: NOT FOUND`); continue; }
  const paras = (m[0].match(/<p><span[^>]*>[\s\S]*?<\/span><\/p>/g) || [])
    .map(p => decode(p.replace(/<\/?p>/g, '').replace(/<\/?span[^>]*>/g, '')))
    .join('\n');
  console.log(`\n===== ${id} =====\n${paras}`);
}