How do I replace a string in a PDF file using NodeJS?

Question

I have a template PDF file, and I want to replace some marker strings to generate new PDF files and save them. What's the best/simplest way to do this? I don't need to add graphics or anything fancy, just a simple text replacement, so I don't want anything too complicated.

Thanks!

Edit: Just found HummusJS, I'll see if I can make progress and post it here.

Answer 1

I found this question by searching, so I think it deserves the answer. I found the answer by BrighTide here: https://github.com/galkahana/HummusJS/issues/71#issuecomment-275956347

Basically, there is this very powerful Hummus package which uses library written in C++ (crossplatform of course). I think the answer given in that github comment can be functionalized like this:

var hummus = require('hummus');

/**
 * Returns a byteArray string
 * 
 * @param {string} str - input string
 */
function strToByteArray(str) {
  var myBuffer = [];
  var buffer = new Buffer(str);
  for (var i = 0; i < buffer.length; i++) {
      myBuffer.push(buffer[i]);
  }
  return myBuffer;
}

function replaceText(sourceFile, targetFile, pageNumber, findText, replaceText) {  
    var writer = hummus.createWriterToModify(sourceFile, {
        modifiedFilePath: targetFile
    });
    var sourceParser = writer.createPDFCopyingContextForModifiedFile().getSourceDocumentParser();
    var pageObject = sourceParser.parsePage(pageNumber);
    var textObjectId = pageObject.getDictionary().toJSObject().Contents.getObjectID();
    var textStream = sourceParser.queryDictionaryObject(pageObject.getDictionary(), 'Contents');
    //read the original block of text data
    var data = [];
    var readStream = sourceParser.startReadingFromStream(textStream);
    while(readStream.notEnded()){
        Array.prototype.push.apply(data, readStream.read(10000));
    }
    var string = new Buffer(data).toString().replace(findText, replaceText);

    //Create and write our new text object
    var objectsContext = writer.getObjectsContext();
    objectsContext.startModifiedIndirectObject(textObjectId);

    var stream = objectsContext.startUnfilteredPDFStream();
    stream.getWriteStream().write(strToByteArray(string));
    objectsContext.endPDFStream(stream);

    objectsContext.endIndirectObject();

    writer.end();
}

// replaceText('source.pdf', 'output.pdf', 0, /REPLACEME/g, 'My New Custom Text');

UPDATE:
The version used at the time of writing an example was 1.0.83, things might change recently.

UPDATE 2: Recently I got an issue with another PDF file which had a different font. For some reason the text got split into small chunks, i.e. string QWERTYUIOPASDFGHJKLZXCVBNM1234567890- got represented as -286(Q)9(WER)24(T)-8(YUIOP)116(ASDF)19(GHJKLZX)15(CVBNM1234567890-) I had no idea what else to do rather than make up a regex.. So instead of this one line:

var string = new Buffer(data).toString().replace(findText, replaceText);

I have something like this now:

var string = Buffer.from(data).toString();

var characters = REPLACE_ME;
var match = [];
for (var a = 0; a < characters.length; a++) {
    match.push('(-?[0-9]+)?(\\()?' + characters[a] + '(\\))?');
}

string = string.replace(new RegExp(match.join('')), function(m, m1) {
    // m1 holds the first item which is a space
    return m1 + '( ' + REPLACE_WITH_THIS + ')';
});