Using pdf.js to render a PDF but it doesn't work and I don't get any error messages to help me debug the issue

Question

I'm trying to build a Flask app where I upload pdf's and I'm working on previewing them before submitting to the back-end.

The script I'm using is as follows:

const imageUploadValidation = (function () {
  "use strict";

  pdfjsLib.GlobalWorkerOptions.workerSrc =
    "https://mozilla.github.io/pdf.js/build/pdf.js";

  const onFilePicked = function (event) {
    // Select file Nodelist containing 1 file
    const files = event.target.files;
    const filename = files[0].name;
    if (filename.lastIndexOf(".") <= 0) {
      return alert("Please add a valid file!");
    }

    const fileReader = new FileReader();

    fileReader.onload = function (e) {
      const pdfData = e.target.result;

      let loadingTask = pdfjsLib.getDocument({ data: pdfData })
      loadingTask.promise.then(function (pdf) {
          console.log("PDF loaded", pdf);

          pdf.getPage(1).then((page) => {
            console.log("page loaded", page);
            // var scale = 1.5;
            // var viewport = page.getViewport({ scale: scale });

            var iframe = document.getElementById("image-preview");
            iframe.src = page
            // var context = canvas.getContext("2d");
            // canvas.height = viewport.height;
            // canvas.width = viewport.width;

            // var renderContext = {
            //   canvasContext: context,
            //   viewport: viewport,
            // };

            // var renderTask = page.render(renderContext);
            // renderTask.promise.then(function () {
            //   console.log("Page rendered");
            // });
          });
        })
        .catch((error) => {
          console.log(error);
        });
    };
    const pdf = fileReader.readAsArrayBuffer(files[0]);
    console.log("read as Data URL", pdf);
  };

  const Constructor = function (selector) {
    const publicAPI = {};

    const changeHandler = (e) => {
      // console.log(e)
      onFilePicked(e);
    };

    publicAPI.init = function (selector) {
      // Check for errors.
      const fileInput = document.querySelector(selector);
      if (!selector || typeof selector !== "string") {
        throw new Error("Please provide a valid selector");
      }

      fileInput.addEventListener("change", changeHandler);
    };

    publicAPI.init(selector);
    return publicAPI;
  };

  return Constructor;
})();

imageUploadValidation("form input[type=file]");

The loading task promise never seems to run. Everything seems to work up until that point. I'm not familiar with this Promise syntax, so I can't be sure if the problem is there or how I'm passing in the pdf file.

P.S. The commented out code is the original way I had this setup, what s uncommented was just me testing a different way.

Answer 1

Check Datatype

First you might want to check what your getting back from your FileReader, specifically what is the datatype for pdfData. If you have a look at the documentation (direct link) getDocument is expecting a Unit8Array or a binary string.

Add Missing Parameters

The next problem you have is your missing required parameters in your call to getDocument. Here is the minimum required arguments:

var args = {
    url: 'https://example.com/the-pdf-to-load.pdf',
    cMapUrl: "./cmaps/",
    cMapPacked: true,
}

I have never used the data argument in place of the url but as long as you supply the correct datatype you should be fine. Notice that cMapUrl should be a relative or absolute path to the cmap folder. PDFJS often needs these files to actually interpret a PDF file. Here are all the files from the demo repository (GitHub pages): cmaps You'll need to add these to your project.

Instead of using data I would recommend uploading your files as blobs and then all you have to do is supply the blob URL as url. I am not familiar with how to do that, I just know its possible in modern browsers.

Where Is Your Viewer / You Don't Need iFrame or Canvas

PDFJS just needs a div to place the PDF inside of. It's picky about some of the CSS rules, for exmaple it MUST be positioned absolute, otherwise PDFJS generates the pages as 0px height.

I don't see PDFViewer or PDFLinkService in your code. It looks like you are trying to build the entire viewer from scratch yourself. This is no small endeavor. When you get loadingTask working correctly the response should be handled something like this:

loadingTask.promise.then(
    // Success function.
    function( doc ) {
        // viewer is holding: new pdfjsViewer.PDFViewer()
        // linkService is: new pdfjsViewer.PDFLinkService()
        viewer.setDocument( doc );
        linkService.setDocument( doc );
    },
    // Error function.
    function( exception ) {
        // What type of error occurred?
        if ( exception.name == 'PasswordException' ) {
            // Password missing, prompt the user and try again.
            elem.appendChild( getPdfPasswordBox() );
        } else {
            // Some other error, stop trying to load this PDF.
            console.error( exception );
        }
        /**
         * Additional exceptions can be reversed engineered from here:
         * https://github.com/mozilla/pdf.js/blob/master/examples/mobile-viewer/viewer.js
         */
    }
);

Notice that PDFViewer does all the hard work for you. PDFLinkService is needed if you want links in the PDF to work. You really should checkout the live demo and the example files.

Its a lot of work but these example files specifically can teach you all you need to know about PDFJS.

Example / Sample Code

Here is some sample code from a project I did with PDFJS. The code is a bit advanced but it should help you reverse engineer how PDFJS is working under the hood a bit better.

pdfObj = An object to store all the info and objects for this PDF file. I load multiple PDFs on a single page so I need this to keep them separate from each other.

updatePageInfo = My custome function that is called by PDFJS's eventBus when the user changes pages in the PDF; this happens as they scroll from page to page.

pdfjsViewer.DownloadManager = I allow users to download the PDFs so I need to use this.

pdfjsViewer.EventBus = Handles events like loading, page changing, and so on for the PDF. I am not 100% certain but I think the PDFViewer requires this.

pdfjsViewer.PDFViewer = What handles actually showing your PDF to users. container is the element on the page to render in, remember it must be positioned absolute.

// Create a new PDF object for this PDF.
var pdfObj = {
    'container': elem.querySelector('.pdf-view-wrapper'),
    'document': null,
    'download': new pdfjsViewer.DownloadManager(),
    'eventBus': new pdfjsViewer.EventBus(),
    'history': null,
    'id': id,
    'linkService': null,
    'loaded': 0,
    'loader': null,
    'pageTotal': 0,
    'src': elem.dataset.pdf,
    'timeoutCount': 0,
    'viewer': null
};

// Update the eventBus to dispatch page change events to our own function.
pdfObj.eventBus.on( 'pagechanging', function pagechange(evt) { 
    updatePageInfo( evt );
} );

// Create and attach the PDFLinkService that handles links and navigation in the viewer.
var linkService = new pdfjsViewer.PDFLinkService( {
    'eventBus': pdfObj.eventBus,
    'externalLinkEnabled': true,
    'externalLinkRel': 'noopener noreferrer nofollow',
    'externalLinkTarget': 2 // Blank
} );
pdfObj.linkService = linkService;

// Create the actual PDFViewer that shows the PDF to the user.
var pdfViewer = new pdfjsViewer.PDFViewer(
    {
        'container': pdfObj.container,
        'enableScripting': false, // Block embeded scripts for security
        'enableWebGL': true,
        'eventBus': pdfObj.eventBus,
        'linkService': pdfObj.linkService,
        'renderInteractiveForms': true, // Allow form fields to be editable
        'textLayerMode': 2
    }
);
pdfObj.viewer = pdfViewer;
pdfObj.linkService.setViewer( pdfObj.viewer );