Last active
November 2, 2016 15:54
-
-
Save ebachter/a3410b77fc93da3cbe32b34ccb39bb06 to your computer and use it in GitHub Desktop.
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
<!doctype html> | |
<html> | |
<head> | |
<meta charset="utf-8"> | |
<title>Solution</title> | |
</head> | |
<body> | |
<article></article> | |
<section id="result"> | |
<ol></ol> | |
</section> | |
<script> | |
const parseFile = (() => { | |
let resultList; | |
const removeTags = (textWithTags) => textWithTags.replace(/<(?:.|\n)*?>/gm, ''); | |
const getWords = (textWithoutTags) => textWithoutTags.match(/\b[^\d\W]+\b/g); | |
const countWords = (arrayOfWords) => arrayOfWords.reduce((o, value) => { | |
!o[value] ? o[value]=1 : o[value] = o[value] + 1; | |
return o; | |
}, []); | |
const makeSortableArray = (objectOfCountedWords)=> Object.keys(objectOfCountedWords).map((k) => ({ word:k, counter: objectOfCountedWords[k] }) ); | |
const sortArray = (sortableArray)=> sortableArray.sort((a, b) => a.counter < b.counter ? 1 : -1); | |
return { | |
parseList: function (textWithTags) { | |
const lowerCaseTextWithoutTags = removeTags(textWithTags).toLowerCase(); | |
const arrayOfWords = getWords(lowerCaseTextWithoutTags); | |
const objectOfCountedWords = countWords(arrayOfWords); | |
const sortableArray = makeSortableArray(objectOfCountedWords); | |
const sortedArray = sortArray(sortableArray); | |
resultList = sortedArray.map((o) => `<li>${o.word} (${o.counter})</li>`).join(''); | |
}, | |
getFileData: function(path){ | |
return new Promise(function (resolve, reject) { | |
const xhr = new XMLHttpRequest(); | |
xhr.onload = function() { | |
resolve(this.responseXML); | |
} | |
xhr.open("GET", path); | |
xhr.responseType = "document"; | |
xhr.send(); | |
}); | |
}, | |
getList: function(){ | |
return resultList; | |
}, | |
} | |
})(); | |
parseFile.getFileData("index.html") | |
.then(function(doc) { | |
const textWithTags = doc.body.getElementsByTagName("article")[0].innerHTML; | |
document.body.getElementsByTagName("article")[0].innerHTML = textWithTags; | |
parseFile.parseList(textWithTags); | |
document.querySelector("#result ol").innerHTML = parseFile.getList(); | |
}); | |
</script> | |
</body> | |
</html> |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment