fix bugs

scripts/diag-news.cjs

@@ -0,0 +1,33 @@
+// 临时诊断: 检查 News 表 content/summary 的换行与长度情况 (用完即删)
+require('dotenv').config()
+const mysql = require('mysql2/promise')
+
+function parseUrl(url) {
+  const u = new URL(url)
+  return { host: u.hostname, port: Number(u.port) || 3306, user: decodeURIComponent(u.username), password: decodeURIComponent(u.password), database: u.pathname.replace(/^\//, '') }
+}
+
+async function main() {
+  const conn = await mysql.createConnection(parseUrl(process.env.DATABASE_URL))
+  const [rows] = await conn.execute(
+    'SELECT id, title, summary, content, CHAR_LENGTH(content) AS clen, CHAR_LENGTH(summary) AS slen FROM `News` ORDER BY id DESC LIMIT 10'
+  )
+  console.log('总条数检查:')
+  const [[cnt]] = await conn.execute('SELECT COUNT(*) AS c, SUM(content IS NULL) AS nullContent FROM `News`')
+  console.log(JSON.stringify(cnt))
+  for (const r of rows) {
+    const content = r.content || ''
+    const summary = r.summary || ''
+    const lf = (content.match(/\n/g) || []).length
+    const cr = (content.match(/\r/g) || []).length
+    const sLf = (summary.match(/\n/g) || []).length
+    console.log('---')
+    console.log('id=' + r.id + ' clen=' + r.clen + ' slen=' + r.slen + ' contentLF=' + lf + ' contentCR=' + cr + ' summaryLF=' + sLf)
+    console.log('title: ' + r.title)
+    console.log('summary: ' + JSON.stringify(summary.slice(0, 120)))
+    console.log('content(hex首200): ' + content.slice(0, 200).replace(/[^\x20-\x7E\u4e00-\u9fa5]/g, (c) => '\\x' + c.charCodeAt(0).toString(16)))
+    console.log('content(带转义首300): ' + JSON.stringify(content.slice(0, 300)))
+  }
+  await conn.end()
+}
+main().catch((e) => { console.error(e); process.exit(1) })

scripts/fetchers/news.fetcher.js

@@ -55,6 +55,12 @@ function parseNewsSheet(sheet, impactBase = 0) {
     const publishedAt = parsePublishedAt(r[2])
     if (!publishedAt) continue
     const body = String(r[1] || '').trim()
+      // 数据源段落间用全角空格连接, 入库前统一转成换行, 保证详情页有段落感
+      .replace(/\u3000+/g, '\n')
+      .replace(/\u00a0/g, ' ')
+      .replace(/[ \t]+\n/g, '\n')
+      .replace(/\n{3,}/g, '\n\n')
+      .trim()
     out.push({
       title,
       summary: body.slice(0, 180),