Last active
April 28, 2016 18:57
-
-
Save caferrari/1f9d2a751dccd8ddff66464f561daf23 to your computer and use it in GitHub Desktop.
Detect and convert file charsets
This file contains 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
const exec = require('child_process').exec; | |
const fs = require('fs'); | |
const iconv = (from, to, encoding, isFallback) => { | |
return new Promise((resolve, reject) => { | |
exec(`iconv -f ${encoding.trim()} -t utf-8 ${from} > ${to}`, (err) => { | |
if (err && !isFallback) { | |
return resolve(iconv(from, to, 'ISO_8859-1', true)); | |
} | |
if (err) return reject(err); | |
resolve(); | |
}); | |
}); | |
}; | |
const detect = (file) => { | |
return new Promise((resolve, reject) => { | |
if (!fs.existsSync(file)) { | |
reject(new Error(`file ${file} not found`)) ; | |
} | |
exec(`uchardet ${file}`, (err, encoding) => { | |
if (err) reject(err); | |
resolve(encoding.trim()); | |
}); | |
}); | |
}; | |
const convert = (from, to) => { | |
return new Promise((resolve, reject) => { | |
detect(from).then((encoding) => { | |
resolve(iconv(from, to, encoding)); | |
}).catch(reject); | |
}); | |
}; | |
module.exports = { | |
convert, | |
detect, | |
iconv | |
}; |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment