Secure random token in Node.js - javascript

In this question Erik needs to generate a secure random token in Node.js. There's the method crypto.randomBytes that generates a random Buffer. However, the base64 encoding in node is not url-safe, it includes / and + instead of - and _. Therefore, the easiest way to generate such token I've found is
require('crypto').randomBytes(48, function(ex, buf) {
token = buf.toString('base64').replace(/\//g,'_').replace(/\+/g,'-');
});
Is there a more elegant way?

Try crypto.randomBytes():
require('crypto').randomBytes(48, function(err, buffer) {
var token = buffer.toString('hex');
});
The 'hex' encoding works in node v0.6.x or newer.

Synchronous option in-case if you are not a JS expert like me. Had to spend some time on how to access the inline function variable
var token = crypto.randomBytes(64).toString('hex');

1. Using nanoid third party library [NEW!]
A tiny, secure, URL-friendly, unique string ID generator for JavaScript
https://github.com/ai/nanoid
import { nanoid } from "nanoid";
const id = nanoid(48);
2. Base 64 Encoding with URL and Filename Safe Alphabet
Page 7 of RCF 4648 describes how to encode in base 64 with URL safety.
You can use an existing library like base64url to do the job.
The function will be:
var crypto = require('crypto');
var base64url = require('base64url');
/** Sync */
function randomStringAsBase64Url(size) {
return base64url(crypto.randomBytes(size));
}
Usage example:
randomStringAsBase64Url(20);
// Returns 'AXSGpLVjne_f7w5Xg-fWdoBwbfs' which is 27 characters length.
Note that the returned string length will not match with the size argument (size != final length).
3. Crypto random values from limited set of characters
Beware that with this solution the generated random string is not uniformly distributed.
You can also build a strong random string from a limited set of characters like that:
var crypto = require('crypto');
/** Sync */
function randomString(length, chars) {
if (!chars) {
throw new Error('Argument \'chars\' is undefined');
}
const charsLength = chars.length;
if (charsLength > 256) {
throw new Error('Argument \'chars\' should not have more than 256 characters'
+ ', otherwise unpredictability will be broken');
}
const randomBytes = crypto.randomBytes(length);
let result = new Array(length);
let cursor = 0;
for (let i = 0; i < length; i++) {
cursor += randomBytes[i];
result[i] = chars[cursor % charsLength];
}
return result.join('');
}
/** Sync */
function randomAsciiString(length) {
return randomString(length,
'abcdefghijklmnopqrstuvwxyzABCDEFGHIJKLMNOPQRSTUVWXYZ0123456789');
}
Usage example:
randomAsciiString(20);
// Returns 'rmRptK5niTSey7NlDk5y' which is 20 characters length.
randomString(20, 'ABCDEFG');
// Returns 'CCBAAGDGBBEGBDBECDCE' which is 20 characters length.

The up-to-date right way to do this asynchronously using ES 2016 standards of async and await (as of Node 7) would be the following:
const crypto = require('crypto');
function generateToken({ stringBase = 'base64', byteLength = 48 } = {}) {
return new Promise((resolve, reject) => {
crypto.randomBytes(byteLength, (err, buffer) => {
if (err) {
reject(err);
} else {
resolve(buffer.toString(stringBase));
}
});
});
}
async function handler(req, res) {
// default token length
const newToken = await generateToken();
console.log('newToken', newToken);
// pass in parameters - adjust byte length
const shortToken = await generateToken({byteLength: 20});
console.log('newToken', shortToken);
}
This works out of the box in Node 7 without any Babel transformations

Random URL and filename string safe (1 liner)
Crypto.randomBytes(48).toString('base64').replace(/\+/g, '-').replace(/\//g, '_').replace(/\=/g, '');

As of Node.js 14.18 and 15.7, url-safe base64 encoding support is built-in:
const token = crypto.randomBytes(48).toString('base64url');
If you want to use the async version (because the function may have to wait for entropy), it can be promisified to align better with modern patterns:
const randomBytesAsync = util.promisify(crypto.randomBytes);
const token = (await randomBytesAsync(48)).toString('base64url');

With async/await and promisification.
const crypto = require('crypto')
const randomBytes = Util.promisify(crypto.randomBytes)
const plain = (await randomBytes(24)).toString('base64').replace(/\W/g, '')
Generates something similar to VjocVHdFiz5vGHnlnwqJKN0NdeHcz8eM

Check out:
var crypto = require('crypto');
crypto.randomBytes(Math.ceil(length/2)).toString('hex').slice(0,length);

crypto-random-string is a nice module for this.
const cryptoRandomString = require('crypto-random-string');
cryptoRandomString({length: 10}); // => '2cf05d94db'
cryptoRandomString({length: 10, type: 'base64'}); // => 'YMiMbaQl6I'
cryptoRandomString({length: 10, type: 'url-safe'}); // => 'YN-tqc8pOw'
cryptoRandomString({length: 10, type: 'numeric'}); // => '8314659141'
cryptoRandomString({length: 6, type: 'distinguishable'}); // => 'CDEHKM'
cryptoRandomString({length: 10, type: 'ascii-printable'}); // => '`#Rt8$IK>B'
cryptoRandomString({length: 10, type: 'alphanumeric'}); // => 'DMuKL8YtE7'
cryptoRandomString({length: 10, characters: 'abc'}); // => 'abaaccabac'
cryptoRandomString.async(options) add .async if you want to get a promise.

Look at real_ates ES2016 way, it's more correct.
ECMAScript 2016 (ES7) way
import crypto from 'crypto';
function spawnTokenBuf() {
return function(callback) {
crypto.randomBytes(48, callback);
};
}
async function() {
console.log((await spawnTokenBuf()).toString('base64'));
};
Generator/Yield Way
var crypto = require('crypto');
var co = require('co');
function spawnTokenBuf() {
return function(callback) {
crypto.randomBytes(48, callback);
};
}
co(function* () {
console.log((yield spawnTokenBuf()).toString('base64'));
});

https://www.npmjs.com/package/crypto-extra has a method for it :)
var value = crypto.random(/* desired length */)

The npm module anyid provides flexible API to generate various kinds of string ID / code.
To generate random string in A-Za-z0-9 using 48 random bytes:
const id = anyid().encode('Aa0').bits(48 * 8).random().id();
// G4NtiI9OYbSgVl3EAkkoxHKyxBAWzcTI7aH13yIUNggIaNqPQoSS7SpcalIqX0qGZ
To generate fixed length alphabet only string filled by random bytes:
const id = anyid().encode('Aa').length(20).random().id();
// qgQBBtDwGMuFHXeoVLpt
Internally it uses crypto.randomBytes() to generate random.

Simple function that gets you a token that is URL safe and has base64 encoding! It's a combination of 2 answers from above.
const randomToken = () => {
crypto.randomBytes(64).toString('base64').replace(/\//g,'_').replace(/\+/g,'-');
}

in your terminal just write
node -e "console.log(crypto.randomBytes(48).toString('hex'))"
Or in your code use:
const randomToken = () => {
crypto.randomBytes(48).toString('hex');
}

0 dependency free solution... Works in browsers, deno & nodejs (with new global web crypto)
const random = size => btoa(
String.fromCharCode(
...crypto.getRandomValues(
new Uint8Array(size)
)
)
).replaceAll('+', 'x').replaceAll('/', 'I').slice(0, size)
for (let i = 5; i--;) console.log(random(16))
All doe I would just have used one single uint8array \w predefined length and called crypto.getRandomValues whenever I need something uniq (and slice it if i have to) and never deal with strings or base64, base64 is just unnecessary overhead.
(allocating lots of buffer to fast can be costly)
const buf256 = new Uint8Array(256)
const random = crypto.getRandomValues.bind(crypto, buf256)
for (let i = 5; i--;) random()//.slice()

You can use the random-token lib. it's very easy to use . :)
var randomToken = require('random-token').create('abcdefghijklmnopqrstuvwxzyABCDEFGHIJKLMNOPQRSTUVWXYZ0123456789');
var token = randomToken(16);
And also you can not use different salt
var randomToken = require('random-token');
var token = randomToken(16); // output -> d8d4kd29c40f021 ```

Related

Firebase Storage: string does not match format base64: invalid character found. Only when debug is off

I'm trying to upload an image file to firebase storage, save the download URL, and load it after the upload is completed. When I run the app with debug js remotely on it works fine. When I turn off debug mode it stops working with the invalid format exception. The same happens when I run in a real device (both iOS and Android)
The base64 response data from React Native Image Picker seems to be correct
Here's my code
...
import * as ImagePicker from 'react-native-image-picker'; //0.26.10
import firebase from 'firebase'; //4.9.1
...
handleImagePicker = () => {
const { me } = this.props;
const options = {
title: 'Select pic',
storageOptions: {
skipBackup: true,
path: 'images'
},
mediaType: 'photo',
quality: 0.5,
};
ImagePicker.showImagePicker(options, async (response) => {
const storageRef = firebase.storage().ref(`/profile-images/user_${me.id}.jpg`);
const metadata = {
contentType: 'image/jpeg',
};
const task = storageRef.putString(response.data, 'base64', metadata);
return new Promise((resolve, reject) => {
task.on(
'state_changed',
(snapshot) => {
var progress = (snapshot.bytesTransferred / snapshot.totalBytes) * 100;
console.log('Upload is ' + progress + '% done');
},
(error) =>
console.log(error),
() => {
this.onChangeProfileImage();
}
);
});
}
}
onChangeProfileImage = async () => {
const { me } = this.props;
const storageRef = firebase.storage().ref(`/profile-images/user_${me.id}.jpg`);
const profileImageUrl = await new Promise((resolve, reject) => {
storageRef.getDownloadURL()
.then((url) => {
resolve(url);
})
.catch((error) => {
console.log(error);
});
});
// some more logic to store profileImageUrl in the database
}
Any idea how to solve this?
Thanks in advance.
After some research and debug I found the cause of the issue and a solution for it.
Why does it happen?
Firebase uses atob method to decode the base64 string sent by putstring method.
However, since JavaScriptCore doesn't have a default support to atob and btoa, the base64 string can't be converted, so this exception is triggered.
When we run the app in debug javascript remotely mode, all javascript code is run under chrome environment, where atob and btoa are supported. That's why the code works when debug is on and doesn't when its off.
How to solve?
To handle atob and btoa in React Native, we should either write our own encode/decode method, or install a lib to handle it for us.
In my case I preferred to install base-64 lib
But here's an example of a encode/decode script:
const chars = 'ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz0123456789+/=';
const Base64 = {
btoa: (input:string = '') => {
let str = input;
let output = '';
for (let block = 0, charCode, i = 0, map = chars;
str.charAt(i | 0) || (map = '=', i % 1);
output += map.charAt(63 & block >> 8 - i % 1 * 8)) {
charCode = str.charCodeAt(i += 3/4);
if (charCode > 0xFF) {
throw new Error("'btoa' failed: The string to be encoded contains characters outside of the Latin1 range.");
}
block = block << 8 | charCode;
}
return output;
},
atob: (input:string = '') => {
let str = input.replace(/=+$/, '');
let output = '';
if (str.length % 4 == 1) {
throw new Error("'atob' failed: The string to be decoded is not correctly encoded.");
}
for (let bc = 0, bs = 0, buffer, i = 0;
buffer = str.charAt(i++);
~buffer && (bs = bc % 4 ? bs * 64 + buffer : buffer,
bc++ % 4) ? output += String.fromCharCode(255 & bs >> (-2 * bc & 6)) : 0
) {
buffer = chars.indexOf(buffer);
}
return output;
}
};
export default Base64;
Usage:
import Base64 from '[path to your script]';
const stringToEncode = 'xxxx';
Base64.btoa(scriptToEncode);
const stringToDecode = 'xxxx';
Base64.atob(stringToDecode);
After choosing either to use the custom script or the lib, now we must add the following code to the index.js file:
import { decode, encode } from 'base-64';
if (!global.btoa) {
global.btoa = encode;
}
if (!global.atob) {
global.atob = decode;
}
AppRegistry.registerComponent(appName, () => App);
This will declare atob and btoa globally. So whenever in the app those functions are called, React Native will use the global scope to handle it, and then trigger the encode and decode methods from base-64 lib.
So this is the solution for Base64 issue.
However, after this is solved, I found another issue Firebase Storage: Max retry time for operation exceed. Please try again when trying to upload larger images. It seems that firebase has some limitation on support to React Native uploads, as this issue suggests.
I believe that react-native-firebase may not struggle on this since it's already prepared to run natively, instead of using the web environment as firebase does. I didn't test it yet to confirm, but it looks like this will be the best approach to handle it.
Hope this can be helpful for someone else.
The problem is now solved using fetch() API. The promise returned can be converted to blob which you can upload to firebase/storage
Here is an example
let storageRef = storage().ref();
let imageName = data.name + "image";
let imagesRef = storageRef.child(`images/${imageName}`);
const response = await fetch(image);
const blob = await response.blob(); // Here is the trick
imagesRef
.put(blob)
.then((snapshot) => {
console.log("uploaded an image.");
})
.catch((err) => console.log(err));

Validate Facebook signed_request signature in Javascript

I'm building a Facebook Page app in Classic ASP. I've been unable to match the signature that Facebook passes into the app as the first part of the POSTed signed_request.
Because there are few libraries for cryptography in VBScript, I'm using server side Javascript and the crypto-js library from https://code.google.com/archive/p/crypto-js/
I've tried to translate the PHP code example from Facebook's docs at https://developers.facebook.com/docs/games/gamesonfacebook/login#parsingsr into Javascript. I can generate an HMAC SHA256 hash of the signed_request payload but that doesn't match the signed_request signature.
I think the problem is that Facebook's signature is in a different format. It looks to be binary (~1抚Ö.....) while the HMAC SHA256 hash I'm generating is a hexadecimal string (7f7e8f5f.....). In Facebook's PHP example the hash_hmac function uses the raw binary parameter. So I think I need to either convert Facebook's signature to hexadecimal or my signature to binary in order to do an "apples-to-apples" comparison and get a match.
Here's my code:
/* Use the libraries from https://code.google.com/archive/p/crypto-js/
crypto-js/crypto-js.min.js
crypto-js/hmac-sha256.min.js
crypto-js/enc-base64.min.js
*/
var signedRequest = Request.queryString("signed_request")
var FB_APP_SECRET = "459f038.....";
var arSR = signedRequest.split(".");
var encodedSig = arSR[0];
var encodedPayload = arSR[1];
var payload = base64UrlDecode(encodedPayload);
var sig = base64UrlDecode(encodedSig);
var expectedSig;
expectedSig = CryptoJS.HmacSHA256(encodedPayload, FB_APP_SECRET); // Unaltered payload string; no match
expectedSig = CryptoJS.HmacSHA256(payload, FB_APP_SECRET); // base64-decoded payload string; no match
if (sig == expectedSig) {
Response.write(payload);
} else {
Response.write("Bad signature");
}
function base64UrlDecode(input) {
// Replace characters and convert from base64.
return Base64.decode(input.replace("-", "+").replace("_", "/"));
}
After looking into the crypto-js documentation about encoding I found the solution. The de-/encoding methods provided by crypto-js are listed under 'Encoders' at the bottom of https://code.google.com/archive/p/crypto-js/ (Thanks for the nudge, CBroe.)
The solution was to use .toString() on the signatures. It seems like crypto-js uses a word format that was preventing a comparison match. I did also switch to using the base64 decoding provided by crypto-js in order to stick with one library.
Here's my updated code:
/* Use the libraries from https://code.google.com/archive/p/crypto-js/
crypto-js/crypto-js.min.js
crypto-js/hmac-sha256.min.js
crypto-js/enc-base64.min.js
*/
var signedRequest = Request.queryString("signed_request")
var FB_APP_SECRET = "459f038.....";
var arSR = signedRequest.split(".");
var encodedSig = arSR[0];
var encodedPayload = arSR[1];
var payload = base64UrlDecode(encodedPayload);
var sig = base64UrlDecode(encodedSig);
var expectedSig = CryptoJS.HmacSHA256(encodedPayload, FB_APP_SECRET); /******** Correct payload */
if (sig.toString() != expectedSig.toString()) { /******* Use .toString() to convert to normal strings */
Response.write(payload);
} else {
Response.write("Bad signature");
}
function base64UrlDecode(input) {
return CryptoJS.enc.Base64.parse( /******** Decode */
input.replace("-", "+").replace("_", "/") // Replace characters
);
}
I recently implemented this for their required user data deletion webhook. No external dependencies needed anymore:
const crypto = require('crypto');
function parseSignedRequest(signedRequest, secret) {
const [signatureReceived, encodedPayload] = signedRequest.split('.', 2);
const payload = b64decode(encodedPayload)
const data = JSON.parse(payload);
const hmac = crypto.createHmac('sha256', secret).update(payload);
const expectedSignature = hmac.digest('base64');
if (signatureReceived === expectedSignature) {
return data;
} else {
throw new Error("Signature mismatch");
}
}
function b64decode(data) {
const buff = Buffer.from(data, 'base64');
return buff.toString('ascii');
}
It's a translation of their example PHP code. I also have a repo setup with tests.
I found this worked for me.
const crypto = require('crypto')
const _atob = (str) => Buffer.from(str, 'base64').toString('binary')
const parseSignedRequest = (signed_request, app_secret) => {
const [encoded_sig, payload] = signed_request.split('.')
const json = _atob(payload)
const data = JSON.parse(json)
if (!data.algorithm || data.algorithm.toUpperCase() !== 'HMAC-SHA256') {
return {error: true, type: 'Unknown algorithm. Expected HMAC-SHA256'}
}
// check sig
const expected_sig = crypto.createHmac('sha256', config.facebook.app_secret)
.update(payload).digest('base64')
.replace(/\+/g, '-').replace(/\//g, '_')
.replace(/=/g, '')
if (encoded_sig !== expected_sig) {
return ({error: true, type: 'invalid_signature'})
}
return {error: false, parsedRequest: data}
}
const {error, type, parsedRequest} = parseSignedRequest(signed_request)

using buffer& streams to search for string in multiple text file & also to find line number in nodejs

please help me to search a string across multiple files, I need to print the line number of that particular string with filename using buffer & streams concept in node.js.
for example:
there are 5 text files and there is " hello " string in 10 and 15th line of the 3rd file. same hello string in the 50th line of the 5th file. now I need to print line number of file name 3 with the line number of that searched string "hello"
same as for the 5th file.
help me to write this program in buffer concept in node.js
const readline = require("readline");
const fs = require("fs");
// Start methods implementation
const beginSearch = (readStream, filePath, queries) => {
let lineCount = 0;
let matches = new Map();
queries.forEach(query => matches.set(query, []));
return new Promise((resolve, reject) => {
readStream.on("line", line => {
lineCount++;
for (query of matches.keys()) {
if (searchForTerm(line, query))
matches.set(query, [...matches.get(query), lineCount]);
}
});
readStream.on("close", () => resolve({
filePath,
matches
}));
});
};
const searchForTerm = (line, query) => line.match(query);
const createLineInterfaces = filePaths =>
filePaths.map(filePath => {
const readStream = readline.createInterface({
input: fs.createReadStream(filePath),
crlfDelay: Infinity
});
return {
filePath,
readStream
};
});
// End methods implementation
// Start main function
const filesToSearch = ["sample.txt", "sample2.txt"];
const queriesToSeatch = ["hello"];
let searchProms = createLineInterfaces(filesToSearch).map(
({
readStream,
filePath
}) =>
beginSearch(readStream, filePath, queriesToSeatch)
);
Promise.all(searchProms).then(searchResults =>
searchResults.forEach(result => console.log(result))
);
// End main function
A little explain
I am using the readline module to split each file into lines. Keep in mind the whole implementation is with streams. Then i am attaching a listener to the line event and I am searching each line for a specific query. The search method is a simple regexp. You could use a fuzzy search method if you want. Then the matched lines are saved in a Map which keys are the queries and values the arrays of lineNumbers that the query has found.
I am assuming that you are familiar with the stream concept and you know about ES6 stuff.

How to get HMAC with Crypto Web API

How can I get HMAC-SHA512(key, data) in the browser using Crypto Web API (window.crypto)?
Currently I am using CryptoJS library and it is pretty simple:
CryptoJS.HmacSHA512("myawesomedata", "mysecretkey").toString();
Result is 91c14b8d3bcd48be0488bfb8d96d52db6e5f07e5fc677ced2c12916dc87580961f422f9543c786eebfb5797bc3febf796b929efac5c83b4ec69228927f21a03a.
I want to get rid of extra dependencies and start using Crypto Web API instead. How can I get the same result with it?
Answering my own question. The code below returns the same result as CryptoJS.HmacSHA512("myawesomedata", "mysecretkey").toString();
There are promises everywhere as WebCrypto is asynchronous:
// encoder to convert string to Uint8Array
var enc = new TextEncoder("utf-8");
window.crypto.subtle.importKey(
"raw", // raw format of the key - should be Uint8Array
enc.encode("mysecretkey"),
{ // algorithm details
name: "HMAC",
hash: {name: "SHA-512"}
},
false, // export = false
["sign", "verify"] // what this key can do
).then( key => {
window.crypto.subtle.sign(
"HMAC",
key,
enc.encode("myawesomedata")
).then(signature => {
var b = new Uint8Array(signature);
var str = Array.prototype.map.call(b, x => x.toString(16).padStart(2, '0')).join("")
console.log(str);
});
});
Async/Await Crypto Subtle HMAC SHA-256/512 with Base64 Digest
The following is a copy of the ✅ answer. This time we are using async/await for clean syntax. This approach also offers a base64 encoded digest.
secret is the secret key that will be used to sign the body.
body is the string-to-sign.
enc is a text encoder that converts the UTF-8 to JavaScript byte arrays.
algorithm is a JS object which is used to identify the signature methods.
key is a CryptoKey.
signature is the byte array hash.
digest is the base64 encoded signature.
The JavaScript code follows:
(async ()=>{
'use strict';
let secret = "sec-demo"; // the secret key
let enc = new TextEncoder("utf-8");
let body = "GET\npub-demo\n/v2/auth/grant/sub-key/sub-demo\nauth=myAuthKey&g=1&target-uuid=user-1&timestamp=1595619509&ttl=300";
let algorithm = { name: "HMAC", hash: "SHA-256" };
let key = await crypto.subtle.importKey("raw", enc.encode(secret), algorithm, false, ["sign", "verify"]);
let signature = await crypto.subtle.sign(algorithm.name, key, enc.encode(body));
let digest = btoa(String.fromCharCode(...new Uint8Array(signature)));
console.log(digest);
})();
The original answer on this page was helpful in a debugging effort earlier today. We're using it to help identify a bug in our documentation for creating signatures for granting access tokens to use APIs with read/write permissions.
Somehow #StephenBlum's answer doesn't work for me.
I rewrite #StepanSnigirev' answer as async below instead.
"use strict";
(async () => {
const secret = "mysecretkey";
const enc = new TextEncoder();
const body = "myawesomedata";
const algorithm = { name: "HMAC", hash: "SHA-512" };
const key = await crypto.subtle.importKey(
"raw",
enc.encode(secret),
algorithm,
false,
["sign", "verify"]
);
const signature = await crypto.subtle.sign(
algorithm.name,
key,
enc.encode(body)
);
// convert buffer to byte array
const hashArray = Array.from(new Uint8Array(signature));
// convert bytes to hex string
const digest = hashArray
.map((b) => b.toString(16).padStart(2, "0"))
.join("");
console.log(digest);
})();

Read a file one line at a time in node.js?

I am trying to read a large file one line at a time. I found a question on Quora that dealt with the subject but I'm missing some connections to make the whole thing fit together.
var Lazy=require("lazy");
new Lazy(process.stdin)
.lines
.forEach(
function(line) {
console.log(line.toString());
}
);
process.stdin.resume();
The bit that I'd like to figure out is how I might read one line at a time from a file instead of STDIN as in this sample.
I tried:
fs.open('./VeryBigFile.csv', 'r', '0666', Process);
function Process(err, fd) {
if (err) throw err;
// DO lazy read
}
but it's not working. I know that in a pinch I could fall back to using something like PHP, but I would like to figure this out.
I don't think the other answer would work as the file is much larger than the server I'm running it on has memory for.
Since Node.js v0.12 and as of Node.js v4.0.0, there is a stable readline core module. Here's the easiest way to read lines from a file, without any external modules:
const fs = require('fs');
const readline = require('readline');
async function processLineByLine() {
const fileStream = fs.createReadStream('input.txt');
const rl = readline.createInterface({
input: fileStream,
crlfDelay: Infinity
});
// Note: we use the crlfDelay option to recognize all instances of CR LF
// ('\r\n') in input.txt as a single line break.
for await (const line of rl) {
// Each line in input.txt will be successively available here as `line`.
console.log(`Line from file: ${line}`);
}
}
processLineByLine();
Or alternatively:
var lineReader = require('readline').createInterface({
input: require('fs').createReadStream('file.in')
});
lineReader.on('line', function (line) {
console.log('Line from file:', line);
});
The last line is read correctly (as of Node v0.12 or later), even if there is no final \n.
UPDATE: this example has been added to Node's API official documentation.
For such a simple operation there shouldn't be any dependency on third-party modules. Go easy.
var fs = require('fs'),
readline = require('readline');
var rd = readline.createInterface({
input: fs.createReadStream('/path/to/file'),
output: process.stdout,
console: false
});
rd.on('line', function(line) {
console.log(line);
});
Update in 2019
An awesome example is already posted on official Nodejs documentation. here
This requires the latest Nodejs is installed on your machine. >11.4
const fs = require('fs');
const readline = require('readline');
async function processLineByLine() {
const fileStream = fs.createReadStream('input.txt');
const rl = readline.createInterface({
input: fileStream,
crlfDelay: Infinity
});
// Note: we use the crlfDelay option to recognize all instances of CR LF
// ('\r\n') in input.txt as a single line break.
for await (const line of rl) {
// Each line in input.txt will be successively available here as `line`.
console.log(`Line from file: ${line}`);
}
}
processLineByLine();
You don't have to open the file, but instead, you have to create a ReadStream.
fs.createReadStream
Then pass that stream to Lazy
require('fs').readFileSync('file.txt', 'utf-8').split(/\r?\n/).forEach(function(line){
console.log(line);
})
there is a very nice module for reading a file line by line, it's called line-reader
with it you simply just write:
var lineReader = require('line-reader');
lineReader.eachLine('file.txt', function(line, last) {
console.log(line);
// do whatever you want with line...
if(last){
// or check if it's the last one
}
});
you can even iterate the file with a "java-style" interface, if you need more control:
lineReader.open('file.txt', function(reader) {
if (reader.hasNextLine()) {
reader.nextLine(function(line) {
console.log(line);
});
}
});
Old topic, but this works:
var rl = readline.createInterface({
input : fs.createReadStream('/path/file.txt'),
output: process.stdout,
terminal: false
})
rl.on('line',function(line){
console.log(line) //or parse line
})
Simple. No need for an external module.
You can always roll your own line reader. I have'nt benchmarked this snippet yet, but it correctly splits the incoming stream of chunks into lines without the trailing '\n'
var last = "";
process.stdin.on('data', function(chunk) {
var lines, i;
lines = (last+chunk).split("\n");
for(i = 0; i < lines.length - 1; i++) {
console.log("line: " + lines[i]);
}
last = lines[i];
});
process.stdin.on('end', function() {
console.log("line: " + last);
});
process.stdin.resume();
I did come up with this when working on a quick log parsing script that needed to accumulate data during the log parsing and I felt that it would nice to try doing this using js and node instead of using perl or bash.
Anyway, I do feel that small nodejs scripts should be self contained and not rely on third party modules so after reading all the answers to this question, each using various modules to handle line parsing, a 13 SLOC native nodejs solution might be of interest .
With the carrier module:
var carrier = require('carrier');
process.stdin.resume();
carrier.carry(process.stdin, function(line) {
console.log('got one line: ' + line);
});
I ended up with a massive, massive memory leak using Lazy to read line by line when trying to then process those lines and write them to another stream due to the way drain/pause/resume in node works (see: http://elegantcode.com/2011/04/06/taking-baby-steps-with-node-js-pumping-data-between-streams/ (i love this guy btw)). I haven't looked closely enough at Lazy to understand exactly why, but I couldn't pause my read stream to allow for a drain without Lazy exiting.
I wrote the code to process massive csv files into xml docs, you can see the code here: https://github.com/j03m/node-csv2xml
If you run the previous revisions with Lazy line it leaks. The latest revision doesn't leak at all and you can probably use it as the basis for a reader/processor. Though I have some custom stuff in there.
Edit: I guess I should also note that my code with Lazy worked fine until I found myself writing large enough xml fragments that drain/pause/resume because a necessity. For smaller chunks it was fine.
In most cases this should be enough:
const fs = require("fs")
fs.readFile('./file', 'utf-8', (err, file) => {
const lines = file.split('\n')
for (let line of lines)
console.log(line)
});
Edit:
Use a transform stream.
With a BufferedReader you can read lines.
new BufferedReader ("lorem ipsum", { encoding: "utf8" })
.on ("error", function (error){
console.log ("error: " + error);
})
.on ("line", function (line){
console.log ("line: " + line);
})
.on ("end", function (){
console.log ("EOF");
})
.read ();
I was frustrated by the lack of a comprehensive solution for this, so I put together my own attempt (git / npm). Copy-pasted list of features:
Interactive line processing (callback-based, no loading the entire file into RAM)
Optionally, return all lines in an array (detailed or raw mode)
Interactively interrupt streaming, or perform map/filter like processing
Detect any newline convention (PC/Mac/Linux)
Correct eof / last line treatment
Correct handling of multi-byte UTF-8 characters
Retrieve byte offset and byte length information on per-line basis
Random access, using line-based or byte-based offsets
Automatically map line-offset information, to speed up random access
Zero dependencies
Tests
NIH? You decide :-)
Since posting my original answer, I found that split is a very easy to use node module for line reading in a file; Which also accepts optional parameters.
var split = require('split');
fs.createReadStream(file)
.pipe(split())
.on('data', function (line) {
//each chunk now is a seperate line!
});
Haven't tested on very large files. Let us know if you do.
function createLineReader(fileName){
var EM = require("events").EventEmitter
var ev = new EM()
var stream = require("fs").createReadStream(fileName)
var remainder = null;
stream.on("data",function(data){
if(remainder != null){//append newly received data chunk
var tmp = new Buffer(remainder.length+data.length)
remainder.copy(tmp)
data.copy(tmp,remainder.length)
data = tmp;
}
var start = 0;
for(var i=0; i<data.length; i++){
if(data[i] == 10){ //\n new line
var line = data.slice(start,i)
ev.emit("line", line)
start = i+1;
}
}
if(start<data.length){
remainder = data.slice(start);
}else{
remainder = null;
}
})
stream.on("end",function(){
if(null!=remainder) ev.emit("line",remainder)
})
return ev
}
//---------main---------------
fileName = process.argv[2]
lineReader = createLineReader(fileName)
lineReader.on("line",function(line){
console.log(line.toString())
//console.log("++++++++++++++++++++")
})
I wanted to tackle this same problem, basically what in Perl would be:
while (<>) {
process_line($_);
}
My use case was just a standalone script, not a server, so synchronous was fine. These were my criteria:
The minimal synchronous code that could reuse in many projects.
No limits on file size or number of lines.
No limits on length of lines.
Able to handle full Unicode in UTF-8, including characters beyond the BMP.
Able to handle *nix and Windows line endings (old-style Mac not needed for me).
Line endings character(s) to be included in lines.
Able to handle last line with or without end-of-line characters.
Not use any external libraries not included in the node.js distribution.
This is a project for me to get a feel for low-level scripting type code in node.js and decide how viable it is as a replacement for other scripting languages like Perl.
After a surprising amount of effort and a couple of false starts this is the code I came up with. It's pretty fast but less trivial than I would've expected: (fork it on GitHub)
var fs = require('fs'),
StringDecoder = require('string_decoder').StringDecoder,
util = require('util');
function lineByLine(fd) {
var blob = '';
var blobStart = 0;
var blobEnd = 0;
var decoder = new StringDecoder('utf8');
var CHUNK_SIZE = 16384;
var chunk = new Buffer(CHUNK_SIZE);
var eolPos = -1;
var lastChunk = false;
var moreLines = true;
var readMore = true;
// each line
while (moreLines) {
readMore = true;
// append more chunks from the file onto the end of our blob of text until we have an EOL or EOF
while (readMore) {
// do we have a whole line? (with LF)
eolPos = blob.indexOf('\n', blobStart);
if (eolPos !== -1) {
blobEnd = eolPos;
readMore = false;
// do we have the last line? (no LF)
} else if (lastChunk) {
blobEnd = blob.length;
readMore = false;
// otherwise read more
} else {
var bytesRead = fs.readSync(fd, chunk, 0, CHUNK_SIZE, null);
lastChunk = bytesRead !== CHUNK_SIZE;
blob += decoder.write(chunk.slice(0, bytesRead));
}
}
if (blobStart < blob.length) {
processLine(blob.substring(blobStart, blobEnd + 1));
blobStart = blobEnd + 1;
if (blobStart >= CHUNK_SIZE) {
// blobStart is in characters, CHUNK_SIZE is in octets
var freeable = blobStart / CHUNK_SIZE;
// keep blob from growing indefinitely, not as deterministic as I'd like
blob = blob.substring(CHUNK_SIZE);
blobStart -= CHUNK_SIZE;
blobEnd -= CHUNK_SIZE;
}
} else {
moreLines = false;
}
}
}
It could probably be cleaned up further, it was the result of trial and error.
Generator based line reader: https://github.com/neurosnap/gen-readlines
var fs = require('fs');
var readlines = require('gen-readlines');
fs.open('./file.txt', 'r', function(err, fd) {
if (err) throw err;
fs.fstat(fd, function(err, stats) {
if (err) throw err;
for (var line of readlines(fd, stats.size)) {
console.log(line.toString());
}
});
});
A new function was added in Node.js v18.11.0 to read files line by line
filehandle.readLines([options])
This is how you use this with a text file you want to read
import { open } from 'node:fs/promises';
myFileReader();
async function myFileReader() {
const file = await open('./TextFileName.txt');
for await (const line of file.readLines()) {
console.log(line)
}
}
To understand more read Node.js documentation here is the link for file system readlines():
https://nodejs.org/api/fs.html#filehandlereadlinesoptions
If you want to read a file line by line and writing this in another:
var fs = require('fs');
var readline = require('readline');
var Stream = require('stream');
function readFileLineByLine(inputFile, outputFile) {
var instream = fs.createReadStream(inputFile);
var outstream = new Stream();
outstream.readable = true;
outstream.writable = true;
var rl = readline.createInterface({
input: instream,
output: outstream,
terminal: false
});
rl.on('line', function (line) {
fs.appendFileSync(outputFile, line + '\n');
});
};
var fs = require('fs');
function readfile(name,online,onend,encoding) {
var bufsize = 1024;
var buffer = new Buffer(bufsize);
var bufread = 0;
var fd = fs.openSync(name,'r');
var position = 0;
var eof = false;
var data = "";
var lines = 0;
encoding = encoding || "utf8";
function readbuf() {
bufread = fs.readSync(fd,buffer,0,bufsize,position);
position += bufread;
eof = bufread ? false : true;
data += buffer.toString(encoding,0,bufread);
}
function getLine() {
var nl = data.indexOf("\r"), hasnl = nl !== -1;
if (!hasnl && eof) return fs.closeSync(fd), online(data,++lines), onend(lines);
if (!hasnl && !eof) readbuf(), nl = data.indexOf("\r"), hasnl = nl !== -1;
if (!hasnl) return process.nextTick(getLine);
var line = data.substr(0,nl);
data = data.substr(nl+1);
if (data[0] === "\n") data = data.substr(1);
online(line,++lines);
process.nextTick(getLine);
}
getLine();
}
I had the same problem and came up with above solution
looks simular to others but is aSync and can read large files very quickly
Hopes this helps
Two questions we must ask ourselves while doing such operations are:
What's the amount of memory used to perform it?
Is the memory consumption increasing drastically with the file size?
Solutions like require('fs').readFileSync() loads the whole file into memory. That means that the amount of memory required to perform operations will be almost equivalent to the file size. We should avoid these for anything larger than 50mbs
We can easily track the amount of memory used by a function by placing these lines of code after the function invocation :
const used = process.memoryUsage().heapUsed / 1024 / 1024;
console.log(
`The script uses approximately ${Math.round(used * 100) / 100} MB`
);
Right now the best way to read particular lines from a large file is using node's readline. The documentation has amazing examples.
This is my favorite way of going through a file, a simple native solution for a progressive (as in not a "slurp" or all-in-memory way) file read with modern async/await. It's a solution that I find "natural" when processing large text files without having to resort to the readline package or any non-core dependency.
let buf = '';
for await ( const chunk of fs.createReadStream('myfile') ) {
const lines = buf.concat(chunk).split(/\r?\n/);
buf = lines.pop() ?? '';
for( const line of lines ) {
console.log(line);
}
}
if(buf.length) console.log(buf); // last line, if file does not end with newline
You can adjust encoding in the fs.createReadStream or use chunk.toString(<arg>). Also this let's you better fine-tune the line splitting to your taste, ie. use .split(/\n+/) to skip empty lines and control the chunk size with fs.createReadStream('myfile', { highWaterMark: <chunkSize> }).
Don't forget to create a function like processLine(line) to avoid repeating the line processing code twice due to the ending buf leftover. Unfortunately, the ReadStream instance does not update its end-of-file flags in this setup, so there's no way, afaik, to detect within the loop that we're in the last iteration without some more verbose tricks like comparing the file size from a fs.Stats() with .bytesRead. Hence the final buf processing solution, unless you're absolutely sure your file ends with a newline \n, in which case the for await loop should suffice.
Performance Considerations
Chunk sizes are important for performance, the default is 64k for text files and, for multi MB files, larger chunks can improve speed by an order of magnitude.
The above snippet runs at least the same speed (or even 5% faster sometimes) as code based on NodeJS v18's fs.readLine() or based on the readline module (the accepted answer), once you tune highWaterMark to something that your machine can handle, ie. setting it to the same size as the file, if your available memory allows it, is the fastest.
In any case, any of NodeJS line-reading answers here are an order of magnitude slower than the Perl or native *Nix solutions.
Similar alternatives
★ If you prefer the evented asynchronous version, this would be it:
let buf = '';
fs.createReadStream('myfile')
.on('data', chunk => {
const lines = buf.concat(chunk).split(/\r?\n/);
buf = lines.pop();
for( const line of lines ) {
console.log(line);
}
})
.on('end', () => buf.length && console.log(buf) );
★ Now if you don't mind importing the stream core package, then this is the equivalent piped stream version, which allows for chaining transforms like gzip decompression:
const { Writable } = require('stream');
let buf = '';
fs.createReadStream('myfile').pipe(
new Writable({
write: (chunk, enc, next) => {
const lines = buf.concat(chunk).split(/\r?\n/);
buf = lines.pop();
for (const line of lines) {
console.log(line);
}
next();
}
})
).on('finish', () => buf.length && console.log(buf) );
I have a little module which does this well and is used by quite a few other projects npm readline Note thay in node v10 there is a native readline module so I republished my module as linebyline https://www.npmjs.com/package/linebyline
if you dont want to use the module the function is very simple:
var fs = require('fs'),
EventEmitter = require('events').EventEmitter,
util = require('util'),
newlines = [
13, // \r
10 // \n
];
var readLine = module.exports = function(file, opts) {
if (!(this instanceof readLine)) return new readLine(file);
EventEmitter.call(this);
opts = opts || {};
var self = this,
line = [],
lineCount = 0,
emit = function(line, count) {
self.emit('line', new Buffer(line).toString(), count);
};
this.input = fs.createReadStream(file);
this.input.on('open', function(fd) {
self.emit('open', fd);
})
.on('data', function(data) {
for (var i = 0; i < data.length; i++) {
if (0 <= newlines.indexOf(data[i])) { // Newline char was found.
lineCount++;
if (line.length) emit(line, lineCount);
line = []; // Empty buffer.
} else {
line.push(data[i]); // Buffer new line data.
}
}
}).on('error', function(err) {
self.emit('error', err);
}).on('end', function() {
// Emit last line if anything left over since EOF won't trigger it.
if (line.length){
lineCount++;
emit(line, lineCount);
}
self.emit('end');
}).on('close', function() {
self.emit('close');
});
};
util.inherits(readLine, EventEmitter);
Another solution is to run logic via sequential executor nsynjs. It reads file line-by-line using node readline module, and it doesn't use promises or recursion, therefore not going to fail on large files. Here is how the code will looks like:
var nsynjs = require('nsynjs');
var textFile = require('./wrappers/nodeReadline').textFile; // this file is part of nsynjs
function process(textFile) {
var fh = new textFile();
fh.open('path/to/file');
var s;
while (typeof(s = fh.readLine(nsynjsCtx).data) != 'undefined')
console.log(s);
fh.close();
}
var ctx = nsynjs.run(process,{},textFile,function () {
console.log('done');
});
Code above is based on this exampe: https://github.com/amaksr/nsynjs/blob/master/examples/node-readline/index.js
i use this:
function emitLines(stream, re){
re = re && /\n/;
var buffer = '';
stream.on('data', stream_data);
stream.on('end', stream_end);
function stream_data(data){
buffer += data;
flush();
}//stream_data
function stream_end(){
if(buffer) stream.emmit('line', buffer);
}//stream_end
function flush(){
var re = /\n/;
var match;
while(match = re.exec(buffer)){
var index = match.index + match[0].length;
stream.emit('line', buffer.substring(0, index));
buffer = buffer.substring(index);
re.lastIndex = 0;
}
}//flush
}//emitLines
use this function on a stream and listen to the line events that is will emit.
gr-
While you should probably use the readline module as the top answer suggests, readline appears to be oriented toward command line interfaces rather than line reading. It's also a little bit more opaque regarding buffering. (Anyone who needs a streaming line oriented reader probably will want to tweak buffer sizes). The readline module is ~1000 lines while this, with stats and tests, is 34.
const EventEmitter = require('events').EventEmitter;
class LineReader extends EventEmitter{
constructor(f, delim='\n'){
super();
this.totalChars = 0;
this.totalLines = 0;
this.leftover = '';
f.on('data', (chunk)=>{
this.totalChars += chunk.length;
let lines = chunk.split(delim);
if (lines.length === 1){
this.leftover += chunk;
return;
}
lines[0] = this.leftover + lines[0];
this.leftover = lines[lines.length-1];
if (this.leftover) lines.pop();
this.totalLines += lines.length;
for (let l of lines) this.onLine(l);
});
// f.on('error', ()=>{});
f.on('end', ()=>{console.log('chars', this.totalChars, 'lines', this.totalLines)});
}
onLine(l){
this.emit('line', l);
}
}
//Command line test
const f = require('fs').createReadStream(process.argv[2], 'utf8');
const delim = process.argv[3];
const lineReader = new LineReader(f, delim);
lineReader.on('line', (line)=> console.log(line));
Here's an even shorter version, without the stats, at 19 lines:
class LineReader extends require('events').EventEmitter{
constructor(f, delim='\n'){
super();
this.leftover = '';
f.on('data', (chunk)=>{
let lines = chunk.split(delim);
if (lines.length === 1){
this.leftover += chunk;
return;
}
lines[0] = this.leftover + lines[0];
this.leftover = lines[lines.length-1];
if (this.leftover)
lines.pop();
for (let l of lines)
this.emit('line', l);
});
}
}
const fs = require("fs")
fs.readFile('./file', 'utf-8', (err, data) => {
var innerContent;
console.log("Asynchronous read: " + data.toString());
const lines = data.toString().split('\n')
for (let line of lines)
innerContent += line + '<br>';
});
I wrap the whole logic of daily line processing as a npm module: line-kit
https://www.npmjs.com/package/line-kit
// example
var count = 0
require('line-kit')(require('fs').createReadStream('/etc/issue'),
(line) => { count++; },
() => {console.log(`seen ${count} lines`)})
I use below code the read lines after verify that its not a directory and its not included in the list of files need not to be check.
(function () {
var fs = require('fs');
var glob = require('glob-fs')();
var path = require('path');
var result = 0;
var exclude = ['LICENSE',
path.join('e2e', 'util', 'db-ca', 'someother-file'),
path.join('src', 'favicon.ico')];
var files = [];
files = glob.readdirSync('**');
var allFiles = [];
var patternString = [
'trade',
'order',
'market',
'securities'
];
files.map((file) => {
try {
if (!fs.lstatSync(file).isDirectory() && exclude.indexOf(file) === -1) {
fs.readFileSync(file).toString().split(/\r?\n/).forEach(function(line){
patternString.map((pattern) => {
if (line.indexOf(pattern) !== -1) {
console.log(file + ' contain `' + pattern + '` in in line "' + line +'";');
result = 1;
}
});
});
}
} catch (e) {
console.log('Error:', e.stack);
}
});
process.exit(result);
})();
I have looked through all above answers, all of them use third-party library to solve it. It's have a simple solution in Node's API. e.g
const fs= require('fs')
let stream = fs.createReadStream('<filename>', { autoClose: true })
stream.on('data', chunk => {
let row = chunk.toString('ascii')
}))

Categories