@chenchaolong/plugin-trade-compliance-workbench 1.0.127 → 1.0.129

package/dist/lib/remote-components/trade-compliance-workbench/preview-source.mjs

@@ -2,6 +2,8 @@ import { getDocument, GlobalWorkerOptions } from 'pdfjs-dist/legacy/build/pdf.mj
 import * as mammoth from 'mammoth'
 import * as XLSX from 'xlsx'
 
+const MAX_PDF_PAGES = 8
+
 let workerUrl = ''
 function pdfWorkerUrl() {
   if (!workerUrl) workerUrl = URL.createObjectURL(new Blob([__TCW_PDF_WORKER_SOURCE__], { type: 'text/javascript' }))
@@ -12,13 +14,29 @@ window.TradeComplianceSourcePreview = {
   async renderPdf(url) {
     const response = await fetch(url); if (!response.ok) throw new Error(`PDF 文件读取失败（${response.status}）`)
     const document = await getDocument({ data: new Uint8Array(await response.arrayBuffer()) }).promise
-    const pageCount = document.numPages; const pageNumbers = selectPages(pageCount, 12); const pages = []
-    for (const pageNumber of pageNumbers) { const page = await document.getPage(pageNumber); const base = page.getViewport({ scale: 1 }); const viewport = page.getViewport({ scale: Math.min(1.5, 1000 / Math.max(1, base.width)) }); const canvas = window.document.createElement('canvas'); canvas.width = Math.ceil(viewport.width); canvas.height = Math.ceil(viewport.height); await page.render({ canvas, canvasContext: canvas.getContext('2d'), viewport }).promise; pages.push(canvas.toDataURL('image/png')) }
-    await document.destroy(); return { pages, pageNumbers, pageCount }
+    const pageCount = document.numPages
+    const pageNumbers = selectPages(pageCount, MAX_PDF_PAGES)
+    const pages = []
+    try {
+      for (const pageNumber of pageNumbers) {
+        const page = await document.getPage(pageNumber)
+        const base = page.getViewport({ scale: 1 })
+        const viewport = page.getViewport({ scale: Math.min(1.15, 900 / Math.max(1, base.width)) })
+        const canvas = window.document.createElement('canvas')
+        canvas.width = Math.ceil(viewport.width)
+        canvas.height = Math.ceil(viewport.height)
+        await page.render({ canvas, canvasContext: canvas.getContext('2d'), viewport }).promise
+        pages.push(await canvasToObjectUrl(canvas))
+        page.cleanup?.()
+      }
+      return { pages, pageNumbers, pageCount }
+    } finally {
+      await document.destroy()
+    }
   },
   async readSpreadsheet(url) {
     const response = await fetch(url); if (!response.ok) throw new Error(`表格文件读取失败（${response.status}）`)
-    const workbook = XLSX.read(await response.arrayBuffer(), { type: 'array', cellDates: true, raw: false })
+    const workbook = XLSX.read(await response.arrayBuffer(), { type: 'array', cellDates: true, raw: false, sheetRows: 200 })
     return workbook.SheetNames.map(name => ({ name, rows: XLSX.utils.sheet_to_json(workbook.Sheets[name], { header: 1, defval: '', raw: false }).slice(0, 200).map(row => Array.isArray(row) ? row.slice(0, 30).map(cell => String(cell ?? '')) : []) })).filter(sheet => sheet.rows.some(row => row.some(Boolean)))
   },
   async convertDocx(url) {
@@ -27,3 +45,7 @@ window.TradeComplianceSourcePreview = {
   }
 }
 function selectPages(pageCount, maxPages) { if (pageCount <= maxPages) return Array.from({ length: pageCount }, (_, index) => index + 1); return [...Array.from({ length: maxPages - 2 }, (_, index) => index + 1), pageCount - 1, pageCount] }
+async function canvasToObjectUrl(canvas) {
+  const blob = await new Promise((resolve, reject) => canvas.toBlob(value => value ? resolve(value) : reject(new Error('PDF 页面转码失败')), 'image/png'))
+  return URL.createObjectURL(blob)
+}