const fs = require('fs') const path = require('path') const { DOMMatrix, ImageData, Path2D } = require('@napi-rs/canvas') global.DOMMatrix = DOMMatrix global.ImageData = ImageData global.Path2D = Path2D if (!process.getBuiltinModule) process.getBuiltinModule = name => require(name) async function main() { const pdfjs = await import('pdfjs-dist/legacy/build/pdf.mjs') const root = path.resolve(__dirname, '..', '..') const pdfPath = path.resolve(root, 'doc', '大连元利流体技术有限公司MES系统用户操作手册_V1.1_2026-07-23.pdf') const terms = process.argv.slice(2) const pdf = await pdfjs.getDocument({ data: new Uint8Array(fs.readFileSync(pdfPath)), disableWorker: true }).promise console.log(`PDF pages: ${pdf.numPages}`) for (let pageNumber = 1; pageNumber <= pdf.numPages; pageNumber++) { const page = await pdf.getPage(pageNumber) const content = await page.getTextContent() const text = content.items.map(item => item.str).join(' ').replace(/\s+/g, ' ').trim() if (terms.length === 0 || terms.some(term => text.includes(term))) { console.log(`${pageNumber}\t${text.slice(0, 220)}`) } } } main().catch(error => { console.error(error.stack || error.message) process.exitCode = 1 })