modesty / modesty/pdf2json

details:"Error: PDFDocument: stream must have data"

Open
#143 0 comments 0 reactions 0 assignees View on GitHub

Nobody has claimed this yet.

Dominant language
Java
Stars
2.2k
Forks
394
Avg merge
3d 5h
Merged PRs (30d)
7

Description

I am uploading the pdf file first and then trying to parse it using pdf.js but I get this error " details:"Error: PDFDocument: stream must have data". on console I am getting the file and file size is also fine after uploading it.

Code I Used :
var parse = function(payload,callback){
var data = payload;
if(data.file){
var name = data.file.hapi.filename;
var ext = name.split('.');
var extension = ext[1];
if(extension == "pdf"){
var path = __dirname + "/uploads/" + name;
checkFileExist();
var file = fs.createWriteStream(path);
file.on('error', function (err) {
console.error(err)
});
data.file.pipe(file);
var fileName = data.file.hapi.filename;
console.log(fileName);
var fileAbsolutepath = __dirname + "/uploads/" + fileName ;
console.log(fileAbsolutepath);
var parser = script.pdfParser(fileAbsolutepath,function(err,resp){
if(err){
callback(err);
}
else {
callback(resp);
}
})
callback(JSON.stringify(fileName));
}
else{
console.log("Invalid fileType");
callback(JSON.stringify("Invalid FileType"));
}
}
}

var checkFileExist = function() {
var path = __dirname + '/uploads';
fs.exists(path, function(exists) {
if (exists === false) fs.mkdirSync(path);
});
};
module.exports = {
parse: parse
}

Contributor guide

No contributing guide indexed for this repository

First steps

  1. Read the whole issue, then the project's contributing guide.
  2. Comment on the issue to say you are picking it up — it saves two people doing the same work.
  3. Fork the repository and make your change on a branch.
  4. Open a pull request that references the issue number.

Research direction

Reproduce the upload flow through the parse entry point and the referenced script.pdfParser call, checking when the write stream finishes relative to parsing. Use the reported error and the provided file path handling to define the fix; done means an uploaded PDF is parsed without the “stream must have data” error.

Written by the indexing model from the issue text.

Assessment

Tech stack
javascript, node.js
Domain
backend
Issue type
Bug
Difficulty
3/5
Estimated time
1-2 days
Activity status
Stale
Clarity
Needs clarification
Newbie friendliness
35/100

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.