The list of all the words in Portuguese, including all possible combinations and variations (masculine, feminine, plural, singular, verbal conjugations, etc.). This is based on the great work from the professors of the University of Minho, and the all the files can be accessed here.
how to use
Install it
npm i words-pt
and then use the API
const wordsPt = require('words-pt')
// { removeNames: true } removes names such as 'Lisboa' or 'António'
wordsPt.init({ removeNames: true }, err => {
if (err) {
// handle the error
return
}
wordsPt.isWord('ser') // true
wordsPt.isWord('serei') // true
wordsPt.isWord('abafar-nos-ão') // true
wordsPt.isWord('hello') // false
wordsPt.randomWord() // grafonolas (any random word)
wordsPt.randomWord('a') // amealhará (starting with 'a')
wordsPt.randomWord('abc') // abcissa (starting with 'abc')
// words.Pt.randomWord('abc') is equivalent to words.Pt.randomWord('abc', '*', '*')
// words.Pt.randomWord(beginningPart, middlePart, endPart)
wordsPt.randomWord('ab', '*', '*') // 'abcesso'
wordsPt.randomWord('a', 'e', '*') // 'abcesso' but not 'abade'
wordsPt.randomWord('*', 's', '*') // 'espesso' but not 'sapato' nor 'mamas'
wordsPt.randomWord('*', '*', 's') // 'mamas'
wordsPt.randomWord('t', '*', 's') // 'tetas'
wordsPt.randomWord('t', 'et', 'as') // 'tetanizarias'
wordsPt.randomWord('se', 'o', 's') // 'seios'
wordsPt.randomWord('sa', 'a', 'to') // 'salteamento'
// exactly the same as randomWord, but gets all the words
wordsPt.getArray() // array with all the words
wordsPt.getArray('abc') // ['abcesso', 'abcessos', 'abcissa', 'abcissas']
wordsPt.getArray('t', 'et', 'as') // ['tabuletas', 'tchetchenas', 'telefotometrias', 'telemetrias', ... ]
wordsPt.getArray('tet', 'a', 's') // ['tetanizadas', 'tetanizados', 'tetanizais' , 'tetanizamos', ... ]
words.Pt.biggestWord() // constitucionalizar-lhes-íamos
// do something more
})just the file
If you simply want for the plain file, wherein the words are separated by newlines \n, check the present file wordsList.zip. The corresponding unzipped file is encoded in iso-8859-1.