feat(insights): fix DBSCAN, Persian embeddings crash, D3 physics layouts, and D3 node not found runtime error

memento-note/app/api/clip/analyze/route.ts

@@ -0,0 +1,101 @@
+import { NextRequest, NextResponse } from 'next/server'
+import { auth } from '@/auth'
+import { extractArticleFromHtml } from '@/lib/clip/extract-article'
+import { analyzeClipContent } from '@/lib/clip/analyze-clip'
+import { resolveClipLocale, wrapClipPlainParagraph } from '@/lib/clip/rtl-content'
+
+function isBlockedUrl(url: string): boolean {
+  try {
+    const parsed = new URL(url)
+    const hostname = parsed.hostname.toLowerCase()
+    const blocked = ['localhost', '127.0.0.1', '0.0.0.0', '::1', '169.254.169.254']
+    if (blocked.includes(hostname)) return true
+    if (hostname.startsWith('10.') || hostname.startsWith('172.') || hostname.startsWith('192.168.')) return true
+    if (parsed.protocol !== 'http:' && parsed.protocol !== 'https:') return true
+    return false
+  } catch {
+    return true
+  }
+}
+
+async function fetchPageHtml(url: string): Promise<string | null> {
+  const controller = new AbortController()
+  const timeoutId = setTimeout(() => controller.abort(), 15000)
+  try {
+    const response = await fetch(url, {
+      headers: {
+        'User-Agent': 'Mozilla/5.0 (compatible; MementoClipper/1.0)',
+        Accept: 'text/html,application/xhtml+xml',
+      },
+      signal: controller.signal,
+      redirect: 'follow',
+    })
+    if (!response.ok) return null
+    const ct = response.headers.get('content-type') || ''
+    if (!ct.includes('text/html') && !ct.includes('application/xhtml')) return null
+    return await response.text()
+  } catch {
+    return null
+  } finally {
+    clearTimeout(timeoutId)
+  }
+}
+
+export async function POST(request: NextRequest) {
+  try {
+    const session = await auth()
+    if (!session?.user?.id) {
+      return NextResponse.json({ error: 'Unauthorized' }, { status: 401 })
+    }
+
+    const body = await request.json()
+    const url = typeof body.url === 'string' ? body.url.trim() : ''
+    const htmlInput = typeof body.html === 'string' ? body.html : ''
+    const selection = typeof body.selection === 'string' ? body.selection.trim() : ''
+
+    if (!url || isBlockedUrl(url)) {
+      return NextResponse.json({ error: 'Invalid URL' }, { status: 400 })
+    }
+
+    let title = ''
+    let textContent = ''
+    let contentHtml = ''
+
+    if (body.mode === 'link') {
+      title = new URL(url).hostname
+      textContent = url
+      contentHtml = `<p><a href="${url}" rel="noopener noreferrer">${url}</a></p>`
+    } else if (body.mode === 'selection' && selection) {
+      title = typeof body.title === 'string' ? body.title : new URL(url).hostname
+      textContent = selection
+      const locale = resolveClipLocale(url, title, selection)
+      contentHtml = wrapClipPlainParagraph(selection, locale)
+    } else {
+      const html = htmlInput || (await fetchPageHtml(url))
+      if (!html) {
+        return NextResponse.json({ error: 'Could not fetch page content' }, { status: 422 })
+      }
+      const extracted = extractArticleFromHtml(html, url)
+      if (!extracted) {
+        return NextResponse.json({ error: 'Could not extract readable article' }, { status: 422 })
+      }
+      title = extracted.title || (typeof body.title === 'string' ? body.title : '')
+      textContent = extracted.textContent
+      contentHtml = extracted.content
+    }
+
+    const analysis = await analyzeClipContent({ url, title, textContent })
+
+    return NextResponse.json({
+      title: analysis.title,
+      summary: analysis.summary,
+      tags: analysis.tags,
+      readingTime: analysis.readingTimeMinutes,
+      content: contentHtml,
+      excerpt: textContent.slice(0, 500),
+    })
+  } catch (error) {
+    console.error('[POST /api/clip/analyze]', error)
+    return NextResponse.json({ error: 'Analysis failed' }, { status: 500 })
+  }
+}