CODEWITHSUNDEEP
javascriptregexstring
bagofmilk
bagofmilk

Reputation: 1550

Javascript RegEx Remove Multiple words from string

Using Javascript. (note there is a similar post, but the OP requested Java, this is for Javascript)

I'm trying to remove a list of words from an entire string without looping (preferably using Regular Expressions).

This is what I have so far, and it removes some of the words but not all of them. Can someone help identify what I'm doing wrong with my RegEx function?

   //Remove all instances of the words in the array
  var removeUselessWords = function(txt) {

	var uselessWordsArray = 
        [
          "a", "at", "be", "can", "cant", "could", "couldnt", 
          "do", "does", "how", "i", "in", "is", "many", "much", "of", 
          "on", "or", "should", "shouldnt", "so", "such", "the", 
          "them", "they", "to", "us",  "we", "what", "who", "why", 
          "with", "wont", "would", "wouldnt", "you"
        ];
			
	var expStr = uselessWordsArray.join(" | ");
	return txt.replace(new RegExp(expStr, 'gi'), ' ');
  }

  var str = "The person is going on a walk in the park. The person told us to do what we need to do in the park";
  
  console.log(removeUselessWords(str));

//The result should be: "person going walk park. person told need park."

Upvotes: 10

Views: 13264

Answers (2)

terry.qiao
terry.qiao

Reputation: 2045

May be this is what you want:

   //Remove all instances of the words in the array
  var removeUselessWords = function(txt) {

	var uselessWordsArray = 
        [
          "a", "at", "be", "can", "cant", "could", "couldnt", 
          "do", "does", "how", "i", "in", "is", "many", "much", "of", 
          "on", "or", "should", "shouldnt", "so", "such", "the", 
          "them", "they", "to", "us",  "we", "what", "who", "why", 
          "with", "wont", "would", "wouldnt", "you"
        ];
			
	var expStr = uselessWordsArray.join("\\b|\\b");
	return txt.replace(new RegExp(expStr, 'gi'), '').trim().replace(/ +/g, ' ');
  }

  var str = "The person is going on a walk in the park. The person told us to do what we need to do in the park";
  
  console.log(removeUselessWords(str));

//The result should be: "person going walk park. person told need park."

Upvotes: 2

RomanPerekhrest
RomanPerekhrest

Reputation: 92894

Three moments:

  • join array items with | without side spaces
  • enclose regex alternation group into parentheses (...|...)
  • specify word boundary \b to match a separate words 

var removeUselessWords = function(txt) {
    var uselessWordsArray = 
        [
          "a", "at", "be", "can", "cant", "could", "couldnt", 
          "do", "does", "how", "i", "in", "is", "many", "much", "of", 
          "on", "or", "should", "shouldnt", "so", "such", "the", 
          "them", "they", "to", "us",  "we", "what", "who", "why", 
          "with", "wont", "would", "wouldnt", "you"
        ];
			
	  var expStr = uselessWordsArray.join("|");
	  return txt.replace(new RegExp('\\b(' + expStr + ')\\b', 'gi'), ' ')
                    .replace(/\s{2,}/g, ' ');
  }

var str = "The person is going on a walk in the park. The person told us to do what we need to do in the park";
  
console.log(removeUselessWords(str));

Upvotes: 13

Related Questions