Passing a pdf file to a function when it requires a path or link

Question

I am working on a web application for an online library. I want to extract metadata from the PDF's that will be uploaded and for that I am using the nodejs library pdf.js-extract and multer-gridfs-storage for the upload. The problem is that I am receiving a PDF file (req.file) and the function requires a path or link to the PDF file and therefore shows the error

"TypeError [ERR_INVALID_ARG_TYPE]: The "path" argument must be one of type string, Buffer, or URL. Received type object"

I would like to know if there is a way to pass a file as a link, save the file locally temporarily or find another library that fits my needs.

This is my current code.

const PDFExtract  = require('pdf.js-extract').PDFExtract;

app.post('/upload', upload.single('file'), (req, res) => {
  const pdfExtract = new PDFExtract();
  const options = {};

  pdfExtract.extract(req.file, options, (err, data) => {
      if (err){
        res.status(404).send({ message: err });
      }
      res.status(200).send({ message: data });
  });
});

(Edit for clarification) I am using multer with gridFS to upload a file to mongoose.

const multer = require('multer');
const GridFsStorage = require('multer-gridfs-storage');

// Create storage engine
const storage = new GridFsStorage({
  url: mongoURI,
  file: (req, file) => {
    return new Promise((resolve, reject) => {
      crypto.randomBytes(16, (err, buf) => {
        if (err) {
          return reject(err);
        }
        const filename = buf.toString('hex') + path.extname(file.originalname);
        const fileInfo = {
          filename: filename,
          bucketName: 'uploads'
        };
        resolve(fileInfo);
      });
    });
  }
});
const upload = multer({ storage });

Solution inspired by Oliver Nybo

app.post('/upload', upload.single('file'), (req, res) => {
  const pdfExtract = new PDFExtract();
  const options = {};

  var readableStream = gfs.createReadStream({ filename : req.file.filename });
  var buff;

  var bufferArray = [];
  readableStream.on('data',function(chunk){  
      bufferArray.push(chunk);
  });
  readableStream.on('end',function(){
      var buffer = Buffer.concat(bufferArray);
      buff=buffer;
      pdfExtract.extractBuffer(buff, options, (err, data) => {
        if (err) {
          res.status(404).send({ message: err });
        }
        res.status(200).send({ message: data });
      });
  })
});

Answer 1

According to multer's api documentation, you can use req.file.path to get the full path of the uploaded file.

const PDFExtract  = require('pdf.js-extract').PDFExtract;

app.post('/upload', upload.single('file'), (req, res) => {
  const pdfExtract = new PDFExtract();
  const options = {};

  pdfExtract.extract(req.file.path, options, (err, data) => {
      if (err){
        res.status(404).send({ message: err });
      }
      res.status(200).send({ message: data });
  });
});

Edit: I just read the multer options and there is an option called preservePath.

preservePath - Keep the full path of files instead of just the base name

Edit 2: I think you need to extract the file from the database with gridfs-stream, then convert it into a buffer (like in this thread), and then use PDFExtract's extractBuffer function.