UNPKG

cetem-publico

Version:

A wrapper for CETEMPúblico, an European Portuguese corpus of news extracts from the newspaper Público, with 180 million words tagged automatically using PALAVRAS.

20 lines (17 loc) 736 B
var zlib = require('zlib'); var gunzip = zlib.createGunzip().on('error', err => { console.warn(`Could not read file`); console.warn(err); }); var readChunk = require('read-chunk'); var fileType = require('file-type'); var buffer = readChunk.sync('/home/andrefs/.cetem-publico/CETEMPublicoAnotado2019.gz', 0, fileType.minimumBytes); var ft = fileType(buffer); var isGzip = ft && /application\/gzip/.test(ft.mime); var input = isGzip ? fs.createReadStream('/home/andrefs/.cetem-publico/CETEMPublicoAnotado2019.gz').pipe(gunzip) : fs.createReadStream('/home/andrefs/.cetem-publico/CETEMPublicoAnotado2019.gz'); var rl = readline.createInterface({input}); rl.on('line', (line) => { console.log(`Line from file: ${line}`); });