Parsing huge logfiles in Node.js - read in line-by-line

Question

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 outstream
    rl.write(cubestuff);
});

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 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}`);
});

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);