Created
January 30, 2024 18:01
-
-
Save SimonBrandner/7c96c70c141c7e0e6c6b5febb69c79d2 to your computer and use it in GitHub Desktop.
Creates all possible n-grams from a string
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 MAX_NGRAM_LENGTH = 5; | |
const inputString = "Hello Alice how are you doing at the moment"; | |
const findNgram = ( | |
words: String[], | |
length: number, | |
startIndex: number | |
): String | undefined => { | |
if (startIndex + length > words.length) return; | |
return words.slice(startIndex, startIndex + length).join(" "); | |
}; | |
const findNgrams = (inputString: String): String[] => { | |
const words = inputString.split(" "); | |
const ngrams: String[] = []; | |
for (let wordIndex = 0; wordIndex < words.length; wordIndex++) { | |
for ( | |
let ngram_length = 1; | |
ngram_length <= MAX_NGRAM_LENGTH; | |
ngram_length++ | |
) { | |
const ngram = findNgram(words, ngram_length, wordIndex); | |
if (ngram) { | |
ngrams.push(ngram); | |
} | |
} | |
} | |
return ngrams; | |
}; | |
const ngrams = findNgrams(inputString); | |
console.log(ngrams); |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment