I'm using unzip2 module https://github.com/glebdmitriew/node-unzip-2 to do zip file stream unzipping, but on getting zip entries, I got a problem.
My code is as below:
var fs = require('fs');
var entries = [];
var srcStream = fs.createReadStream('test.zip');
srcStream.pipe(unzip.Parse())
.on('entry', function(entry) {
entries.push(entry.path);
entry.autodrain();
})
.on('finish', function() {
console.log(entries);
});
But the output is always "[]", it seems when "finish" event got, the operation on "entry" event is not finished.
Is there any solutions that I can get all the entry list?
Use "close" event instead of "finish" may solve this issue.
var fs = require('fs');
var entries = [];
var srcStream = fs.createReadStream('test.zip');
srcStream.pipe(unzip.Parse())
.on('entry', function(entry) {
entries.push(entry.path);
entry.autodrain();
})
.on('close', function() {
console.log(entries);
});
I'm trying implement a stream which returns one symbol from file on each 'data' event.
I finished with code bellow:
var util = require('util'),
fs = require('fs'),
Readable = require('stream').Readable;
var util = require('util');
var Readable = require('stream').Readable;
var SymbolReadStream = function(filename, options) {
Readable.call(this);
this._readable = fs.createReadStream(filename, options).pause();
self = this;
this._readable.on('readable', function() {
var chunk;
chunk = self._readable.read(1);
// I believe the problem is here
self._readable.pause();
});
};
util.inherits(SymbolReadStream, Readable); // inherit the prototype methods
SymbolReadStream.prototype._read = function() {
this._readable.resume();
};
var r = new SymbolReadStream("test.txt", {
encoding: 'utf8',
});
r.on('data', function(el) {
console.log(el);
});
but this code doesn't work. Please help.
Is there an easier way to achieve the behavior?
This post give a great clue how to answer your question.
Also, you should take a loop at pipe that would be a cleaner way to accomplish what you're trying to do: piping an adapter to the filestream instead of wrapping it up
That said, personaly I wont reinvent the wheel here, and would just search for modules that can accomplish that. Especially "split" modules, making them split on every char, instead on new lines. As an example, event-stream has a split method that "takes the same arguments as string.split except it defaults to '\n' instead of ','". So the logic would be to try myStream.pipe(es.split('')) but the modules takes this like myStream.pipe(es.split()) which breaks on lines. So here's my solution, using a regex to say "break on each char"
var es = require('event-stream');
var fs = require('fs');
var symbolStream = fs.createReadStream(filename, options).pipe(es.split(/(?!$)/));
EDIT: event-stream seems to use split module internally, so you can even try
var split = require('split');
var fs = require('fs');
var symbolStream = fs.createReadStream(filename, options).pipe(split(/(?!$)/));
(this loose test is responsible of converting '' to \r\n)
In you stream implementation there is no emitting 'data' event to handler. Because of it, console.log are never called. After adding events, they will be streamed symbol by symbol. Example below:
var util = require('util'),
fs = require('fs'),
Readable = require('stream').Readable;
function SymbolReadStream(filename, options) {
if (!(this instanceof SymbolReadStream)) {
return new SymbolReadStream(length, options);
}
Readable.call(this);
this._readable = fs.createReadStream(filename, options);
}
util.inherits(SymbolReadStream, Readable); // inherit the prototype methods
SymbolReadStream.prototype._read = function() {
var self = this;
this._readable.on('readable', function() {
var chunk;
while (null !== (chunk = self._readable.read(1))) {
self.emit('data', chunk);
}
});
this._readable.on('end', function() {
self.emit('end');
});
};
var r = new SymbolReadStream("test.txt", {
encoding: 'utf8',
});
r.on('data', function(el) {
console.log(el);
});
r.on('end', function(el) {
console.log('done');
});
I have a MongoDB collection that I am querying based on a time frame and address number. If the query is successful, then the server will return a CSV file with a number of attributes stored in each query entry. This part is working fine.
The problem is that one of the attributes in my CSV file is the timestamp. I'd like it to return the local date time (ie. "Time":"2014-02-09T06:00:02.000Z")... however the CSV file is returning the date object in milliseconds (ie. "Time":1392040717774). Is there an easy way to transform the query entry before it's written to the CSV file to a local date string? Here's my code snippet:
var JSONStream = require('JSONStream');
var httpserver = http.createServer(function(req, res) {
var pathname = url.parse(req.url).pathname;
if (pathname=="/DownloadUCData") {
var requestData = '';
req.on('data', function (data) {
requestData += data;
});
req.on('end', function () {
var json = JSON.parse(requestData);
var st = new Date(json.startDate);
var et = new Date(json.endDate);
st.setHours(st.getHours()-4); //compensate for GMT offset
et.setHours(et.getHours()-4);
st=st.getTime();
et=et.getTime();
var proj=JSON.parse('{"state":1, "temperature":1, "mode":1, "speed":1, "time":1}');
var cursor = userControlCollection.find({"addr": json.addr.toString(), "time": {$gte:st, $lte:et}}, proj);
var dbstream = cursor.stream();
var tempname = json.type+".csv";
var wstream = fs.createWriteStream(tempname);
wstream.on('error', function(e){console.error(e);});
dbstream.on("end", function() {
wstream.end();
console.log("write end");
res.writeHead(200, {"Content-Type": "application/json"});
res.write(JSON.stringify({fname:tempname}));
res.end();
return;
});
var jsonToStrings = JSONStream.stringify(false);
dbstream.pipe(jsonToStrings).pipe(wstream);
});
}
So, I figured out one way to solve this problem (although there may be others). Basically, I had to add a transformation into the piping system to convert the .getTime() data into a new Date() object. Here's the code snippet which seemed to resolve the issue:
var Transform = require('stream').Transform;
var parser = new Transform({objectMode: true});
parser._transform = function(data, encoding, done) {
if(data.time) data.time = new Date(data.time);
this.push(data);
done();
};
var jsonToStrings = JSONStream.stringify(false);
dbstream.pipe(parser).pipe(jsonToStrings).pipe(wstream);
I'm making simple Node.js app and I need to delete first line in file. Please is any way how to do it? I think that It will be possible with fs.write, but how?
Here is streamed version of removing first line from file.
As it uses streams, means you don't need to load whole file in memory, so it is way more efficient and fast, as well can work on very large files without filling memory on your hardware.
var Transform = require('stream').Transform;
var util = require('util');
// Transform sctreamer to remove first line
function RemoveFirstLine(args) {
if (! (this instanceof RemoveFirstLine)) {
return new RemoveFirstLine(args);
}
Transform.call(this, args);
this._buff = '';
this._removed = false;
}
util.inherits(RemoveFirstLine, Transform);
RemoveFirstLine.prototype._transform = function(chunk, encoding, done) {
if (this._removed) { // if already removed
this.push(chunk); // just push through buffer
} else {
// collect string into buffer
this._buff += chunk.toString();
// check if string has newline symbol
if (this._buff.indexOf('\n') !== -1) {
// push to stream skipping first line
this.push(this._buff.slice(this._buff.indexOf('\n') + 2));
// clear string buffer
this._buff = null;
// mark as removed
this._removed = true;
}
}
done();
};
And use it like so:
var fs = require('fs');
var input = fs.createReadStream('test.txt'); // read file
var output = fs.createWriteStream('test_.txt'); // write file
input // take input
.pipe(RemoveFirstLine()) // pipe through line remover
.pipe(output); // save to file
Another way, which is not recommended.
If your files are not large, and you don't mind loading them into memory, load file, remove line, save file, but it is slower and wont work well on large files.
var fs = require('fs');
var filePath = './test.txt'; // path to file
fs.readFile(filePath, function(err, data) { // read file to memory
if (!err) {
data = data.toString(); // stringify buffer
var position = data.toString().indexOf('\n'); // find position of new line element
if (position != -1) { // if new line element found
data = data.substr(position + 1); // subtract string based on first line length
fs.writeFile(filePath, data, function(err) { // write file
if (err) { // if error, report
console.log (err);
}
});
} else {
console.log('no lines found');
}
} else {
console.log(err);
}
});
Here is another way:
const fs = require('fs');
const filePath = './table.csv';
let csvContent = fs.readFileSync(filePath).toString().split('\n'); // read file and convert to array by line break
csvContent.shift(); // remove the the first element from array
csvContent = csvContent.join('\n'); // convert array back to string
fs.writeFileSync(filePath, csvContent);
Thanks to #Lilleman 's comment, I've made an amendment to the original solution, which requires a 3rd-party module "line-by-line" and can prevent memory overflow and racing condition while processing very large file.
const fs = require('fs');
const LineReader = require('line-by-line');
const removeLines = function(srcPath, destPath, count, cb) {
if(count <= 0) {
return cb();
}
var reader = new LineReader(srcPath);
var output = fs.createWriteStream(destPath);
var linesRemoved = 0;
var isFirstLine = true;
reader.on('line', (line) => {
if(linesRemoved < count) {
linesRemoved++;
return;
}
reader.pause();
var newLine;
if(isFirstLine) {
newLine = line;
isFirstLine = false;
} else {
newLine = '\n' + line;
}
output.write(newLine, () => {
reader.resume();
});
})
.on('error', (err) => {
reader.pause();
return cb(err);
})
.on('close', () => {
return cb();
})
}
---------------- original solution below---------------
Inspired by another answer, here is a revised stream version:
const fs = require('fs');
const readline = require('readline');
const removeFirstLine = function(srcPath, destPath, done) {
var rl = readline.createInterface({
input: fs.createReadStream(srcPath)
});
var output = fs.createWriteStream(destPath);
var firstRemoved = false;
rl.on('line', (line) => {
if(!firstRemoved) {
firstRemoved = true;
return;
}
output.write(line + '\n');
}).on('close', () => {
return done();
})
}
and it can be easily modified to remove certain amount of lines, by changing the 'firstRemoved' into a counter:
var linesRemoved = 0;
...
if(linesRemoved < LINES_TO_BE_REMOVED) {
linesRemoved++;
return;
}
...
Here is a naive solution using the Promise-based file system APIs.
const fs = require('node:fs/promises')
const os = require('node:os')
async function removeLines(path, numLinesToRemove) {
const data = await fs.readFile(path, { encoding: 'utf-8' })
const newData = data
.split(os.EOL) // split data into array of strings
.slice(numLinesToRemove) // remove first N lines of array
.join(os.EOL) // join array into a single string
// overwrite original file with new data
return fs.writeFile(path, newData)
}
I need to do some parsing of large (5-10 Gb)logfiles in Javascript/Node.js (I'm using Cube).
The logline looks something like:
10:00:43.343423 I'm a friendly log message. There are 5 cats, and 7 dogs. We are in state "SUCCESS".
We need to read each line, do some parsing (e.g. strip out 5, 7 and SUCCESS), then pump this data into Cube (https://github.com/square/cube) using their JS client.
Firstly, what is the canonical way in Node to read in a file, line by line?
It seems to be fairly common question online:
http://www.quora.com/What-is-the-best-way-to-read-a-file-line-by-line-in-node-js
Read a file one line at a time in node.js?
A lot of the answers seem to point to a bunch of third-party modules:
https://github.com/nickewing/line-reader
https://github.com/jahewson/node-byline
https://github.com/pkrumins/node-lazy
https://github.com/Gagle/Node-BufferedReader
However, this seems like a fairly basic task - surely, there's a simple way within the stdlib to read in a textfile, line-by-line?
Secondly, I then need to process each line (e.g. convert the timestamp into a Date object, and extract useful fields).
What's the best way to do this, maximising throughput? Is there some way that won't block on either reading in each line, or on sending it to Cube?
Thirdly - I'm guessing using string splits, and the JS equivalent of contains (IndexOf != -1?) will be a lot faster than regexes? Has anybody had much experience in parsing massive amounts of text data in Node.js?
I searched for a solution to parse very large files (gbs) line by line using a stream. All the third-party libraries and examples did not suit my needs since they processed the files not line by line (like 1 , 2 , 3 , 4 ..) or read the entire file to memory
The following solution can parse very large files, line by line using stream & pipe. For testing I used a 2.1 gb file with 17.000.000 records. Ram usage did not exceed 60 mb.
First, install the event-stream package:
npm install event-stream
Then:
var fs = require('fs')
, es = require('event-stream');
var lineNr = 0;
var s = fs.createReadStream('very-large-file.csv')
.pipe(es.split())
.pipe(es.mapSync(function(line){
// pause the readstream
s.pause();
lineNr += 1;
// process line here and call s.resume() when rdy
// function below was for logging memory usage
logMemoryUsage(lineNr);
// resume the readstream, possibly from a callback
s.resume();
})
.on('error', function(err){
console.log('Error while reading file.', err);
})
.on('end', function(){
console.log('Read entire file.')
})
);
Please let me know how it goes!
You can use the inbuilt readline package, see docs here. I use stream to create a new output stream.
var fs = require('fs'),
readline = require('readline'),
stream = require('stream');
var instream = fs.createReadStream('/path/to/file');
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) {
console.log(line);
//Do your stuff ...
//Then write to output stream
rl.write(line);
});
Large files will take some time to process. Do tell if it works.
I really liked #gerard answer which is actually deserves to be the correct answer here. I made some improvements:
Code is in a class (modular)
Parsing is included
Ability to resume is given to the outside in case there is an asynchronous job is chained to reading the CSV like inserting to DB, or a HTTP request
Reading in chunks/batche sizes that
user can declare. I took care of encoding in the stream too, in case
you have files in different encoding.
Here's the code:
'use strict'
const fs = require('fs'),
util = require('util'),
stream = require('stream'),
es = require('event-stream'),
parse = require("csv-parse"),
iconv = require('iconv-lite');
class CSVReader {
constructor(filename, batchSize, columns) {
this.reader = fs.createReadStream(filename).pipe(iconv.decodeStream('utf8'))
this.batchSize = batchSize || 1000
this.lineNumber = 0
this.data = []
this.parseOptions = {delimiter: '\t', columns: true, escape: '/', relax: true}
}
read(callback) {
this.reader
.pipe(es.split())
.pipe(es.mapSync(line => {
++this.lineNumber
parse(line, this.parseOptions, (err, d) => {
this.data.push(d[0])
})
if (this.lineNumber % this.batchSize === 0) {
callback(this.data)
}
})
.on('error', function(){
console.log('Error while reading file.')
})
.on('end', function(){
console.log('Read entirefile.')
}))
}
continue () {
this.data = []
this.reader.resume()
}
}
module.exports = CSVReader
So basically, here is how you will use it:
let reader = CSVReader('path_to_file.csv')
reader.read(() => reader.continue())
I tested this with a 35GB CSV file and it worked for me and that's why I chose to build it on #gerard's answer, feedbacks are welcomed.
I used https://www.npmjs.com/package/line-by-line for reading more than 1 000 000 lines from a text file. In this case, an occupied capacity of RAM was about 50-60 megabyte.
const LineByLineReader = require('line-by-line'),
lr = new LineByLineReader('big_file.txt');
lr.on('error', function (err) {
// 'err' contains error object
});
lr.on('line', function (line) {
// pause emitting of lines...
lr.pause();
// ...do your asynchronous line processing..
setTimeout(function () {
// ...and continue emitting lines.
lr.resume();
}, 100);
});
lr.on('end', function () {
// All lines are read, file is closed now.
});
The Node.js Documentation offers a very elegant example using the Readline module.
Example: Read File Stream Line-by-Line
const { once } = require('node:events');
const fs = require('fs');
const readline = require('readline');
const rl = readline.createInterface({
input: fs.createReadStream('sample.txt'),
crlfDelay: Infinity
});
rl.on('line', (line) => {
console.log(`Line from file: ${line}`);
});
await once(rl, 'close');
Note: we use the crlfDelay option to recognize all instances of CR LF ('\r\n') as a single line break.
Apart from read the big file line by line, you also can read it chunk by chunk. For more refer to this article
var offset = 0;
var chunkSize = 2048;
var chunkBuffer = new Buffer(chunkSize);
var fp = fs.openSync('filepath', 'r');
var bytesRead = 0;
while(bytesRead = fs.readSync(fp, chunkBuffer, 0, chunkSize, offset)) {
offset += bytesRead;
var str = chunkBuffer.slice(0, bytesRead).toString();
var arr = str.split('\n');
if(bytesRead = chunkSize) {
// the last item of the arr may be not a full line, leave it to the next chunk
offset -= arr.pop().length;
}
lines.push(arr);
}
console.log(lines);
I had the same problem yet. After comparing several modules that seem to have this feature, I decided to do it myself, it's simpler than I thought.
gist: https://gist.github.com/deemstone/8279565
var fetchBlock = lineByline(filepath, onEnd);
fetchBlock(function(lines, start){ ... }); //lines{array} start{int} lines[0] No.
It cover the file opened in a closure, that fetchBlock() returned will fetch a block from the file, end split to array (will deal the segment from last fetch).
I've set the block size to 1024 for each read operation. This may have bugs, but code logic is obvious, try it yourself.
Reading / Writing files using stream with the native nodejs modules (fs, readline):
const fs = require('fs');
const readline = require('readline');
const rl = readline.createInterface({
input: fs.createReadStream('input.json'),
output: fs.createWriteStream('output.json')
});
rl.on('line', function(line) {
console.log(line);
// Do any 'line' processing if you want and then write to the output file
this.output.write(`${line}\n`);
});
rl.on('close', function() {
console.log(`Created "${this.output.path}"`);
});
Based on this questions answer I implemented a class you can use to read a file synchronously line-by-line with fs.readSync(). You can make this "pause" and "resume" by using a Q promise (jQuery seems to require a DOM so cant run it with nodejs):
var fs = require('fs');
var Q = require('q');
var lr = new LineReader(filenameToLoad);
lr.open();
var promise;
workOnLine = function () {
var line = lr.readNextLine();
promise = complexLineTransformation(line).then(
function() {console.log('ok');workOnLine();},
function() {console.log('error');}
);
}
workOnLine();
complexLineTransformation = function (line) {
var deferred = Q.defer();
// ... async call goes here, in callback: deferred.resolve('done ok'); or deferred.reject(new Error(error));
return deferred.promise;
}
function LineReader (filename) {
this.moreLinesAvailable = true;
this.fd = undefined;
this.bufferSize = 1024*1024;
this.buffer = new Buffer(this.bufferSize);
this.leftOver = '';
this.read = undefined;
this.idxStart = undefined;
this.idx = undefined;
this.lineNumber = 0;
this._bundleOfLines = [];
this.open = function() {
this.fd = fs.openSync(filename, 'r');
};
this.readNextLine = function () {
if (this._bundleOfLines.length === 0) {
this._readNextBundleOfLines();
}
this.lineNumber++;
var lineToReturn = this._bundleOfLines[0];
this._bundleOfLines.splice(0, 1); // remove first element (pos, howmany)
return lineToReturn;
};
this.getLineNumber = function() {
return this.lineNumber;
};
this._readNextBundleOfLines = function() {
var line = "";
while ((this.read = fs.readSync(this.fd, this.buffer, 0, this.bufferSize, null)) !== 0) { // read next bytes until end of file
this.leftOver += this.buffer.toString('utf8', 0, this.read); // append to leftOver
this.idxStart = 0
while ((this.idx = this.leftOver.indexOf("\n", this.idxStart)) !== -1) { // as long as there is a newline-char in leftOver
line = this.leftOver.substring(this.idxStart, this.idx);
this._bundleOfLines.push(line);
this.idxStart = this.idx + 1;
}
this.leftOver = this.leftOver.substring(this.idxStart);
if (line !== "") {
break;
}
}
};
}
node-byline uses streams, so i would prefer that one for your huge files.
for your date-conversions i would use moment.js.
for maximising your throughput you could think about using a software-cluster. there are some nice-modules which wrap the node-native cluster-module quite well. i like cluster-master from isaacs. e.g. you could create a cluster of x workers which all compute a file.
for benchmarking splits vs regexes use benchmark.js. i havent tested it until now. benchmark.js is available as a node-module
import * as csv from 'fast-csv';
import * as fs from 'fs';
interface Row {
[s: string]: string;
}
type RowCallBack = (data: Row, index: number) => object;
export class CSVReader {
protected file: string;
protected csvOptions = {
delimiter: ',',
headers: true,
ignoreEmpty: true,
trim: true
};
constructor(file: string, csvOptions = {}) {
if (!fs.existsSync(file)) {
throw new Error(`File ${file} not found.`);
}
this.file = file;
this.csvOptions = Object.assign({}, this.csvOptions, csvOptions);
}
public read(callback: RowCallBack): Promise < Array < object >> {
return new Promise < Array < object >> (resolve => {
const readStream = fs.createReadStream(this.file);
const results: Array < any > = [];
let index = 0;
const csvStream = csv.parse(this.csvOptions).on('data', async (data: Row) => {
index++;
results.push(await callback(data, index));
}).on('error', (err: Error) => {
console.error(err.message);
throw err;
}).on('end', () => {
resolve(results);
});
readStream.pipe(csvStream);
});
}
}
import { CSVReader } from '../src/helpers/CSVReader';
(async () => {
const reader = new CSVReader('./database/migrations/csv/users.csv');
const users = await reader.read(async data => {
return {
username: data.username,
name: data.name,
email: data.email,
cellPhone: data.cell_phone,
homePhone: data.home_phone,
roleId: data.role_id,
description: data.description,
state: data.state,
};
});
console.log(users);
})();
I have made a node module to read large file asynchronously text or JSON.
Tested on large files.
var fs = require('fs')
, util = require('util')
, stream = require('stream')
, es = require('event-stream');
module.exports = FileReader;
function FileReader(){
}
FileReader.prototype.read = function(pathToFile, callback){
var returnTxt = '';
var s = fs.createReadStream(pathToFile)
.pipe(es.split())
.pipe(es.mapSync(function(line){
// pause the readstream
s.pause();
//console.log('reading line: '+line);
returnTxt += line;
// resume the readstream, possibly from a callback
s.resume();
})
.on('error', function(){
console.log('Error while reading file.');
})
.on('end', function(){
console.log('Read entire file.');
callback(returnTxt);
})
);
};
FileReader.prototype.readJSON = function(pathToFile, callback){
try{
this.read(pathToFile, function(txt){callback(JSON.parse(txt));});
}
catch(err){
throw new Error('json file is not valid! '+err.stack);
}
};
Just save the file as file-reader.js, and use it like this:
var FileReader = require('./file-reader');
var fileReader = new FileReader();
fileReader.readJSON(__dirname + '/largeFile.json', function(jsonObj){/*callback logic here*/});