Processing Documents

Processing Documents

Quick Start

import { PDFDocument } from 'pdf-lib';
import ExcelJS from 'exceljs';
import { Document, Packer, Paragraph, TextRun } from 'docx';

// Extract text from PDF
async function extractPDFText(buffer: Buffer): Promise<string> {
  const pdfDoc = await PDFDocument.load(buffer);
  const pages = pdfDoc.getPages();
  return pages.map(page => page.getTextContent()).join('\n\n');
}

// Read Excel spreadsheet
async function readExcel(buffer: Buffer) {
  const workbook = new ExcelJS.Workbook();
  await workbook.xlsx.load(buffer);
  return workbook.worksheets.map(sheet => ({
    name: sheet.name,
    rows: sheet.getSheetValues(),
  }));
}

// Generate Word document
async function generateDOCX(title: string, content: string[]): Promise<Buffer> {
  const doc = new Document({
    sections: [{
      children: [
        new Paragraph({ children: [new TextRun({ text: title, bold: true, size: 48 })] }),
        ...content.map(text => new Paragraph({ children: [new TextRun(text)] })),
      ],
    }],
  });
  return await Packer.toBuffer(doc);
}

Features

Common Patterns

Batch Document Processing

import PQueue from 'p-queue';

async function processBatch(files: string[], transform: (buffer: Buffer) => Promise<Buffer>) {
  const queue = new PQueue({ concurrency: 4 });
  const results: { file: string; success: boolean; error?: string }[] = [];

  for (const file of files) {
    queue.add(async () => {
      try {
        const buffer = await fs.readFile(file);
        const output = await transform(buffer);
        await fs.writeFile(file.replace(/\.\w+$/, '_processed.pdf'), output);
        results.push({ file, success: true });
      } catch (error) {
        results.push({ file, success: false, error: error.message });
      }
    });
  }

  await queue.onIdle();
  return results;
}

Excel Report Generation

async function generateReport(data: Record<string, any>[]): Promise<Buffer> {
  const workbook = new ExcelJS.Workbook();
  const sheet = workbook.addWorksheet('Report');

  // Add headers with styling
  const headers = Object.keys(data[0] || {});
  sheet.addRow(headers);
  sheet.getRow(1).font = { bold: true };
  sheet.getRow(1).fill = { type: 'pattern', pattern: 'solid', fgColor: { argb: 'FFE0E0E0' } };

  // Add data rows
  data.forEach(row => sheet.addRow(headers.map(h => row[h])));

  // Auto-fit columns
  sheet.columns.forEach(col => { col.width = 15; });

  return Buffer.from(await workbook.xlsx.writeBuffer());
}

Invoice Generation from Template

import Docxtemplater from 'docxtemplater';
import PizZip from 'pizzip';

async function generateInvoice(templatePath: string, invoiceData: InvoiceData): Promise<Buffer> {
  const templateBuffer = await fs.readFile(templatePath);
  const zip = new PizZip(templateBuffer);
  const doc = new Docxtemplater(zip, { paragraphLoop: true, linebreaks: true });

  doc.render({
    invoiceNumber: invoiceData.number,
    date: invoiceData.date,
    customer: invoiceData.customer,
    items: invoiceData.items,
    total: invoiceData.total,
  });

  return doc.getZip().generate({ type: 'nodebuffer', compression: 'DEFLATE' });
}

PDF Table Extraction

async function extractTables(pdfBuffer: Buffer): Promise<ExtractedTable[]> {
  const pdfDoc = await PDFDocument.load(pdfBuffer);
  const tables: ExtractedTable[] = [];

  for (let i = 0; i < pdfDoc.getPageCount(); i++) {
    const page = pdfDoc.getPage(i);
    const content = await extractPageContent(page);
    const detectedTables = detectTableStructures(content);
    tables.push(...detectedTables.map(t => ({ ...t, pageNumber: i + 1 })));
  }

  return tables;
}

Best Practices

Related Skills

• media-processing - Video and audio processing
• image-processing - Image manipulation with Sharp
• typescript - Type-safe document handling

References

• pdf-lib Documentation
• ExcelJS Documentation
• docx Documentation
• PptxGenJS Documentation

Converted and distributed by TomeVault — claim your Tome and manage your conversions.