The difference between res.download() and createReadStream() in downloading files - node.js

I learned two ways of downloading files in node js and express, but I couldn't find out what the difference between them is: res.download(path) and createReadStream(path).
I know that createReadStream() is creating a stream to know overflow the server and it's good way, but what about the other one?
These are the two examples:
const orderId = req.params.orderId;
const invoiceName = 'invoice-' + orderId + '.pdf';
const invoicePath = path.join('data', 'invoices', invoiceName)
res.download(invoicePath, (err) => {
if (err) {
return next(err);
}
});
and
const readStream = fs.createReadStream(invoicePath);
res.setHeader('Content-type', 'application/pdf');
res.setHeader('Content-Dispoition', 'attachment; filename=' + invoiceName);
readStream
.on('open', function () {
// This just pipes the read stream to the response object (which goes to the client)
readStream.pipe(res);
})
.on('end', function () {
readStream.unpipe(res);
console.log('All the data in the file has been read');
})
.on('close', function (err) {
console.log('Stream has been Closed');
next(err)
});

Briefly looking at express res.download() source code, it essentially automates what you are doing manually with the alternative example. This includes relying on streams for efficient transfer and minimizing memory footprint.
https://github.com/expressjs/express/blob/master/lib/response.js
It actually ends up calling the sendfile() function defined at line 1016 - which ends up calling file.pipe(res).

Related

How to combine video upload chunks Node.js

I'm trying to upload a large (8.3GB) video to my Node.js (Express) server by chunking using busboy. How to I receive each chunk (busboy is doing this part) and piece it together as one whole video?
I have been looking into readable and writable streams but I'm not ever getting the whole video. I keep overwriting parts of it, resulting in about 1 GB.
Here's my code:
req.busboy.on('file', (fieldname, file, filename) => {
logger.info(`Upload of '${filename}' started`);
const video = fs.createReadStream(path.join(`${process.cwd()}/uploads`, filename));
const fstream = fs.createWriteStream(path.join(`${process.cwd()}/uploads`, filename));
if (video) {
video.pipe(fstream);
}
file.pipe(fstream);
fstream.on('close', () => {
logger.info(`Upload of '${filename}' finished`);
res.status(200).send(`Upload of '${filename}' finished`);
});
});
After 12+ hours, I got it figured out using pieces from this article that was given to me. I came up with this code:
//busboy is middleware on my index.js
const fs = require('fs-extra');
const streamToBuffer = require('fast-stream-to-buffer');
//API function called first
uploadVideoChunks(req, res) {
req.pipe(req.busboy);
req.busboy.on('file', (fieldname, file, filename, encoding, mimetype) => {
const fileNameBase = filename.replace(/\.[^/.]+$/, '');
//save all the chunks to a temp folder with .tmp extensions
streamToBuffer(file, function (error, buffer) {
const chunkDir = `${process.cwd()}/uploads/${fileNameBase}`;
fs.outputFileSync(path.join(chunkDir, `${Date.now()}-${fileNameBase}.tmp`), buffer);
});
});
req.busboy.on('finish', () => {
res.status(200).send(`Finshed uploading chunk`);
});
}
//API function called once all chunks are uploaded
saveToFile(req, res) {
const { filename, profileId, movieId } = req.body;
const uploadDir = `${process.cwd()}/uploads`;
const fileNameBase = filename.replace(/\.[^/.]+$/, '');
const chunkDir = `${uploadDir}/${fileNameBase}`;
let outputFile = fs.createWriteStream(path.join(uploadDir, filename));
fs.readdir(chunkDir, function(error, filenames) {
if (error) {
throw new Error('Cannot get upload chunks!');
}
//loop through the temp dir and write to the stream to create a new file
filenames.forEach(function(tempName) {
const data = fs.readFileSync(`${chunkDir}/${tempName}`);
outputFile.write(data);
//delete the chunk we just handled
fs.removeSync(`${chunkDir}/${tempName}`);
});
outputFile.end();
});
outputFile.on('finish', async function () {
//delete the temp folder once the file is written
fs.removeSync(chunkDir);
}
});
}
Use streams
multer allow you to easily handle file uploads as part of an express route. This works great for small files that don’t leave a significant memory footprint.
The problem with loading a large file into memory is that you can actually run out of memory and cause your application to crash.
use multipart/form-data request. This can be handled by assigning the readStream to that field instead in your request options
streams are extremely valuable for optimizing performance.
Try with this code sample, I think it will work for you.
busboy.on("file", function(fieldName, file, filename, encoding, mimetype){
const writeStream = fs.createWriteStream(writePath);
file.pipe(writeStream);
file.on("data", data => {
totalSize += data.length;
cb(totalSize);
});
file.on("end", () => {
console.log("File "+ fieldName +" finished");
});
});
You can refer this link also for resolve this problem
https://github.com/mscdex/busboy/issues/143
I think multer is good with this, did you try multer?

Node.js in aws callback variable

Hi im trying to use callback for variable external use outside the function but something is wrong, i think my callback is not so correct as i think:
function latitude(callback){
var mylat;
const https = require('https');
https.get('https://url_of_my_json', (resp) => {
let data = '';
// A chunk of data has been recieved.
resp.on('data', (chunk) => {
data += chunk;
});
// The whole response has been received. Print out the result.
resp.on('end', () => {
mylat = JSON.parse(data).results[0].geometry.location.lat;
callback(mylat);
});
}).on("error", (err) => {
console.log("Error: " + err.message);
});
}
var mylat = latitude(); // variable i want to use for the rest of code
Thanks
The syntax of the callback is incorrect.
here is the example, for better understanding of callback Try this example as simple as you can read, just copy save newfile.js do node newfile to run the application.
function myNew(next){
console.log("Im the one who initates callback");
next("nope", "success");
}
myNew(function(err, res){
console.log("I got back from callback",err, res);
});
happy coding :)

Nodejs: How to send a readable stream to the browser

If I query the box REST API and get back a readable stream, what is the best way to handle it? How do you send it to the browser?? (DISCLAIMER: I'm new to streams and buffers, so some of this code is pretty theoretical)
Can you pass the readStream in the response and let the browser handle it? Or do you have to stream the chunks into a buffer and then send the buffer??
export function getFileStream(req, res) {
const fileId = req.params.fileId;
console.log('fileId', fileId);
req.sdk.files.getReadStream(fileId, null, (err, stream) => {
if (err) {
console.log('error', err);
return res.status(500).send(err);
}
res.type('application/octet-stream');
console.log('stream', stream);
return res.status(200).send(stream);
});
}
Will ^^ work, or do you need to do something like:
export function downloadFile(req, res) {
const fileId = req.params.fileId;
console.log('fileId', fileId);
req.sdk.files.getReadStream(fileId, null, (err, stream) => {
if (err) {
console.log('error', err);
return res.status(500).send(err);
}
const buffers = [];
const document = new Buffer();
console.log('stream', stream);
stream.on('data', (chunk) => {
buffers.push(buffer);
})
.on('end', function(){
const finalBuffer = Buffer.concat(buffers);
return res.status(200).send(finalBuffer);
});
});
}
The first example would work if you changed you theoretical line to:
- return res.status(200).send(stream);
+ res.writeHead(200, {header: here})
+ stream.pipe(res);
That's the nicest thing about node stream. The other case would (in essence) work too, but it would accumulate lots of unnecessary memory.
If you'd like to check a working example, here's one I wrote based on scramjet, express and browserify:
https://github.com/MichalCz/scramjet/blob/master/samples/browser/browser.js
Where your streams go from the server to the browser. With minor mods it'll fit your problem.

Why does node webkit crash when downloading a big file?

Im using node webkit 0.7.5 (which is the only version so far which allows me to display video in a correct way).
I'm trying to download a big video file (200+ mb) and sometimes, not always, node webkit crashes when the file is done downloading. Writestream.end() is called, and that is when the crash happens.
My code:
var fs = require('fs');
var request = require("request");
var req = request(self.requestOptions(), function (err) {
if (err) {
//handle error
}
});
req.on("response", function (response) {
writeFile(response);
});
function writeFile(response) {
var file = fs.createWriteStream(filename);
var self = this;
response.on('data', function (data) {
file.write(data);
});
response.on('end', function () {
log.debug("response end");
file.end();//crash happens after calling this
});
response.on('error', function (err) {
//handle error, not called in this situation
});
file.on('finish', function () {
log.debug("file finish");
});
}
In general this method works excellent, but with some files and situations node webkit just decides to call it quits.
Am I doing something obviously wrong? I've searched the net for possible clues or solutions, but I haven't found anything.

Node - how to wait on async operations?

Sorry, just starting with node. This might be a very novice question.
Let's say I have some code which reads some files from a directory in the file system:
var fs = require('fs');
fs.readdir(__dirname + '/myfiles', function (err, files) {
if (err) throw err;
files.forEach(function (fileName) {
fs.readFile(__dirname + '/myfiles/' + fileName, function (err, data) {
if (err) throw err;
console.log('finished reading file ' + fileName + ': ' + data);
module.exports.files.push(data);
});
});
});
Note that all of this occurs asynchronously. Let's also say I have a Mocha test which executes this code:
describe('fileProvider', function () {
describe('#files', function () {
it.only('files array not empty', function () {
assert(fileProvider.files.length > 0, 'files.length is zero');
});
});
});
The mocha test runs before the files are finished being read. I know this because I see the console.log statement after I see the little dot that indicates a mocha test being run (at least I think that is what is being indicated). Also, if I surround the assert with a setTimeout, the assert passes.
How should I structure my code so that I can ensure the async file operations are completed? Note that this is not just a problem with testing - I need the files to be loaded fully before I can do real work in my app as well.
I don't think the right answer is to read files synchronously, because that will block the Node request / response loop, right?
Bonus question:
Even if I put the assert in a setTimeout with a 0 timeout value, the test still passes. Is this because just putting it in a setTimeout kicks it to the end of the processing chain or something so the filesystem work finishes first?
You can implement a complete callback after all files have been read.
exports.files = [];
exports.initialize = initialize;
function initialize(callback) {
var fs = require('fs');
fs.readdir(__dirname + '/myfiles', function (err, files) {
if (err) throw err;
files.forEach(function (fileName) {
fs.readFile(__dirname + '/myfiles/' + fileName, function (err, data) {
if (err) throw err;
console.log('finished reading file ' + fileName + ': ' + data);
exports.files.push(data);
if (exports.files.length == files.length) {
callback();
}
});
});
}
You can call the file operation method by doing something like:
var f = require('./files.js');
if (f.files.length < 1) {
console.log('initializing');
f.initialize(function () {
console.log('After: ' + f.files.length);
var another = require('./files.js');
console.log('Another module: ' + another.files.length);
});
}
EDIT: Since you want to only have to call this once, you could initialize it once when the application loads. According to Node.js documentation, modules are cached after the first time they are loaded. The two above examples have been edited as well.
To avoid being caught up in nested callbacks. You might want to use async's each that will allow you to do the tasks asynchronously in a non-blocking manner:
https://github.com/caolan/async#each
I think that's a good test, the same thing would happen in any app that used your module, i.e. it's code could be run before files is set. What you need to do is create a callback like #making3 suggests, or use promises. I haven't used mocha, but there's a section on ascynchronous calls. You could export the promise itself:
module.exports.getFiles = new Promise((resolve, reject) => {
datas = [];
fs.readdir(__dirname + '/myfiles', function (err, files) {
if (err) {
reject(err);
return;
}
files.forEach(function (fileName) {
fs.readFile(__dirname + '/myfiles/' + fileName, function (err, data) {
if (err) {
reject(err);
return;
}
console.log('finished reading file ' + fileName + ': ' + data);
datas.push(data);
if (datas.length == files.length) {
resolve(datas);
}
});
});
});
}
chai-as-promissed lets you work directly with promises using eventually, or you can use the callback passed to your test I think:
describe('fileProvider', function () {
describe('#files', function () {
it.only('files array not empty', function (done) {
fileProvider.getFiles.then(function(value) {
assert(value.length > 0, 'files.length is zero');
done();
}, function(err) {
done(err);
})
});
});
});

Resources