Created
November 20, 2017 10:08
-
-
Save NorikDavtian/2e41dfcfb9c09434b1d491309914af9e to your computer and use it in GitHub Desktop.
Small handy utility script to break large jsonl files to smaller json files.
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
// COUNT=3 INPUT=large_file.jsonl node jsonl-to-multiple-json-files.js | |
const fs = require('fs'); | |
const readline = require('readline'); | |
const COUNT = parseInt(process.env.COUNT); // Numer of lines to get from the large file | |
const input = fs.createReadStream(process.env.INPUT.toString()); // input .jsonl file | |
const rl = readline.createInterface({ input }); | |
let counter = 0; | |
rl.on('line', (line) => { | |
rl.pause(); | |
if (counter >= COUNT) { | |
return rl.close(); | |
} | |
counter++; | |
const output = fs.openSync(`./output/file_${counter}.json`, 'w'); | |
fs.write(output, JSON.stringify(JSON.parse(line), null, 2)); | |
rl.resume(); | |
}).on('close', () => { | |
console.log(`${counter} lines were processed.`); | |
process.exit(0); | |
}).on('error', (error) => { | |
console.error(error); | |
}); |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment