@chenchaolong/plugin-trade-compliance-workbench 1.0.117 → 1.0.119

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

@@ -0,0 +1,25 @@
+import { getDocument } from 'pdfjs-dist/legacy/build/pdf.mjs'
+import * as pdfjsWorker from 'pdfjs-dist/legacy/build/pdf.worker.mjs'
+import * as mammoth from 'mammoth'
+import * as XLSX from 'xlsx'
+
+globalThis.pdfjsWorker = pdfjsWorker
+window.TradeComplianceSourcePreview = {
+  async renderPdf(url) {
+    const response = await fetch(url); if (!response.ok) throw new Error(`PDF 文件读取失败（${response.status}）`)
+    const document = await getDocument({ data: new Uint8Array(await response.arrayBuffer()), disableWorker: true }).promise
+    const pageCount = document.numPages; const pageNumbers = selectPages(pageCount, 12); const pages = []
+    for (const pageNumber of pageNumbers) { const page = await document.getPage(pageNumber); const base = page.getViewport({ scale: 1 }); const viewport = page.getViewport({ scale: Math.min(1.5, 1000 / Math.max(1, base.width)) }); const canvas = window.document.createElement('canvas'); canvas.width = Math.ceil(viewport.width); canvas.height = Math.ceil(viewport.height); await page.render({ canvas, canvasContext: canvas.getContext('2d'), viewport }).promise; pages.push(canvas.toDataURL('image/png')) }
+    await document.destroy(); return { pages, pageNumbers, pageCount }
+  },
+  async readSpreadsheet(url) {
+    const response = await fetch(url); if (!response.ok) throw new Error(`表格文件读取失败（${response.status}）`)
+    const workbook = XLSX.read(await response.arrayBuffer(), { type: 'array', cellDates: true, raw: false })
+    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) {
+    const response = await fetch(url); if (!response.ok) throw new Error(`Word 文件读取失败（${response.status}）`)
+    const result = await mammoth.convertToHtml({ arrayBuffer: await response.arrayBuffer() }); return result.value.replace(/<script[\s\S]*?<\/script>/gi, '').replace(/<style[\s\S]*?<\/style>/gi, '').replace(/\son\w+=(?:"[^"]*"|'[^']*')/gi, '')
+  }
+}
+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] }