Created
July 28, 2018 13:18
-
-
Save tankala/a5e446aaf593ac929eac12c2f4e334b8 to your computer and use it in GitHub Desktop.
Word Wizard code for calculating words count and sorting in Desc
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
const stopWordsSet = new Set(["a", "about", "above", "after", "again", "against", "all", "am", "an", "and", "any", "are", "as", "at", "be", "because", "been", "before", "being", "below", "between", "both", "but", "by", "could", "did", "do", "does", "doing", "down", "during", "each", "few", "for", "from", "further", "had", "has", "have", "having", "he", "he'd", "he'll", "he's", "her", "here", "here's", "hers", "herself", "him", "himself", "his", "how", "how's", "i", "i'd", "i'll", "i'm", "i've", "if", "in", "into", "is", "it", "it's", "its", "itself", "let's", "me", "more", "most", "my", "myself", "nor", "of", "on", "once", "only", "or", "other", "ought", "our", "ours", "ourselves", "out", "over", "own", "same", "she", "she'd", "she'll", "she's", "should", "so", "some", "such", "than", "that", "that's", "the", "their", "theirs", "them", "themselves", "then", "there", "there's", "these", "they", "they'd", "they'll", "they're", "they've", "this", "those", "through", "to", "too", "under", "until", "up", "very", "was", "we", "we'd", "we'll", "we're", "we've", "were", "what", "what's", "when", "when's", "where", "where's", "which", "while", "who", "who's", "whom", "why", "why's", "with", "would", "you", "you'd", "you'll", "you're", "you've", "your", "yours", "yourself", "yourselves"]); | |
exports.getWordsCountInDesc = function (sentence, callBack) { | |
let words = getWordsFromSentence(sentence); | |
let wordsWithCount = getWordsWithCount(words); | |
let wordsWithCountInDesc = getWordsWithCountInDescendingOrder(wordsWithCount); | |
callBack(null, wordsWithCountInDesc); | |
} | |
//Sort words in descending order based on counts | |
var getWordsWithCountInDescendingOrder = function (wordsWithCount) { | |
return Object.keys(wordsWithCount) | |
.sort((word, anotherWord) => wordsWithCount[anotherWord] - wordsWithCount[word]) | |
.reduce((wordsWithCountInDesc, word) => { | |
wordsWithCountInDesc[word] = wordsWithCount[word]; | |
return wordsWithCountInDesc; | |
}, {}); | |
} | |
// Gives words array after convering to lower case replacing characters like comma, full stop & etc | |
var getWordsFromSentence = function (sentence) { | |
sentence = sentence.toLowerCase(); | |
sentence = sentence.replace('/./g', ' '); | |
sentence = sentence.replace('/,/g', ' '); | |
sentence = sentence.replace('/ /g', ' '); | |
sentence = sentence.trim(); | |
let words = sentence.split(' '); | |
return words; | |
} | |
// Returns words with count after removing stop words | |
var getWordsWithCount = function (words) { | |
let wordsWithCount = {}; | |
words.forEach(word => { | |
if (!isItStopWord(word)) { | |
if (wordsWithCount[word]) { | |
wordsWithCount[word] += 1; | |
} else { | |
wordsWithCount[word] = 1; | |
} | |
} | |
}); | |
return wordsWithCount; | |
} | |
//Returns wether word is a stop word or not | |
var isItStopWord = function (word) { | |
return stopWordsSet.has(word); | |
} |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment