NodeJS: Merge two PDF files into one using the buffer obtained by reading them

Question

I am using fill-pdf npm module for filling template pdf's and it creates new file which is read from the disk and returned as buffer to callback. I have two files for which i do the same operation. I want to combine the two buffers there by to form a single pdf file which i can send back to the client. I tried different methods of buffer concatenation. The buffer can be concatenated using Buffer.concat, like,

var newBuffer = Buffer.concat([result_pdf.output, result_pdf_new.output]);

The size of new buffer is also the sum of the size of the input buffers. But still when the newBuffer is sent to client as response, it shows only the file mentioned last in the array.

res.type("application/pdf");
return res.send(buffer);

Any idea ?

Answer 1

As mentioned by @MechaCode, the creator has ended support for HummusJS.

So I would like to give you 2 solutions.

1. Using node-pdftk npm module

   The Following sample code uses node-pdftk npm module to combine two pdf buffers seamlessly.

   const pdftk = require('node-pdftk');
   
   var pdfBuffer1 = fs.readFileSync("./pdf1.pdf");
   var pdfBuffer2 = fs.readFileSync("./pdf2.pdf");
   
   pdftk
       .input([pdfBuffer1, pdfBuffer2])
       .output()
       .then(buf => {
           let path = 'merged.pdf';
           fs.open(path, 'w', function (err, fd) {
               fs.write(fd, buf, 0, buf.length, null, function (err) {
                   fs.close(fd, function () {
                       console.log('wrote the file successfully');
                   });
               });
           });
       });
   

   The requirement for node-pdftk npm module is you need to install the PDFtk library. Some of you may find this overhead / tedious. So I have another solution using pdf-lib library.

2. Using pdf-lib npm module

   const PDFDocument = require('pdf-lib').PDFDocument
   
   var pdfBuffer1 = fs.readFileSync("./pdf1.pdf"); 
   var pdfBuffer2 = fs.readFileSync("./pdf2.pdf");
   
   var pdfsToMerge = [pdfBuffer1, pdfBuffer2]
   
   const mergedPdf = await PDFDocument.create(); 
   for (const pdfBytes of pdfsToMerge) { 
       const pdf = await PDFDocument.load(pdfBytes); 
       const copiedPages = await mergedPdf.copyPages(pdf, pdf.getPageIndices());
       copiedPages.forEach((page) => {
            mergedPdf.addPage(page); 
       }); 
   } 
   
   const buf = await mergedPdf.save();        // Uint8Array
   
   let path = 'merged.pdf'; 
   fs.open(path, 'w', function (err, fd) {
       fs.write(fd, buf, 0, buf.length, null, function (err) {
           fs.close(fd, function () {
               console.log('wrote the file successfully');
           }); 
       }); 
   }); 
   
   

Personally I prefer to use pdf-lib npm module.

Answer 2

HummusJS supports combining PDFs using its appendPDFPagesFromPDF method

Example using streams to work with buffers:

const hummus = require('hummus');
const memoryStreams = require('memory-streams');

/**
 * Concatenate two PDFs in Buffers
 * @param {Buffer} firstBuffer 
 * @param {Buffer} secondBuffer 
 * @returns {Buffer} - a Buffer containing the concactenated PDFs
 */
const combinePDFBuffers = (firstBuffer, secondBuffer) => {
    var outStream = new memoryStreams.WritableStream();

    try {
        var firstPDFStream = new hummus.PDFRStreamForBuffer(firstBuffer);
        var secondPDFStream = new hummus.PDFRStreamForBuffer(secondBuffer);

        var pdfWriter = hummus.createWriterToModify(firstPDFStream, new hummus.PDFStreamForResponse(outStream));
        pdfWriter.appendPDFPagesFromPDF(secondPDFStream);
        pdfWriter.end();
        var newBuffer = outStream.toBuffer();
        outStream.end();

        return newBuffer;
    }
    catch(e){
        outStream.end();
        throw new Error('Error during PDF combination: ' + e.message);
    }
};

combinePDFBuffers(PDFBuffer1, PDFBuffer2);

Answer 3

Here's what we use in our Express server to merge a list of PDF blobs.

const { PDFRStreamForBuffer, createWriterToModify, PDFStreamForResponse } = require('hummus');
const { WritableStream } = require('memory-streams');

// Merge the pages of the pdfBlobs (Javascript buffers) into a single PDF blob                                                                                                                                                                  
const mergePdfs = pdfBlobs => {
  if (pdfBlobs.length === 0) throw new Error('mergePdfs called with empty list of PDF blobs');
  // This optimization is not necessary, but it avoids the churn down below                                                                                                                                                
  if (pdfBlobs.length === 1) return pdfBlobs[0];

  // Adapted from: https://stackoverflow.com/questions/36766234/nodejs-merge-two-pdf-files-into-one-using-the-buffer-obtained-by-reading-them?answertab=active#tab-top                                                     
  // Hummus is useful, but with poor interfaces -- E.g. createWriterToModify shouldn't require any PDF stream                                                                                                              
  // And Hummus has many Issues: https://github.com/galkahana/HummusJS/issues                                                                                                                                              
  const [firstPdfRStream, ...restPdfRStreams] = pdfBlobs.map(pdfBlob => new PDFRStreamForBuffer(pdfBlob));
  const outStream = new WritableStream();
  const pdfWriter = createWriterToModify(firstPdfRStream, new PDFStreamForResponse(outStream));
  restPdfRStreams.forEach(pdfRStream => pdfWriter.appendPDFPagesFromPDF(pdfRStream));
  pdfWriter.end();
  outStream.end();
  return outStream.toBuffer();
};

module.exports = exports = {
  mergePdfs,
};