How to find indices of all occurrences of one string in another in JavaScript?

Question

I'm trying to find the positions of all occurrences of a string in another string, case-insensitive.

For example, given the string:

I learned to play the Ukulele in Lebanon.

and the search string le, I want to obtain the array:

[2, 25, 27, 33]

Both strings will be variables - i.e., I can't hard-code their values.

I figured that this was an easy task for regular expressions, but after struggling for a while to find one that would work, I've had no luck.

I found this example of how to accomplish this using .indexOf(), but surely there has to be a more concise way to do it?

Answer 1

var str = "I learned to play the Ukulele in Lebanon."
var regex = /le/gi, result, indices = [];
while ( (result = regex.exec(str)) ) {
    indices.push(result.index);
}

UPDATE

I failed to spot in the original question that the search string needs to be a variable. I've written another version to deal with this case that uses indexOf, so you're back to where you started. As pointed out by Wrikken in the comments, to do this for the general case with regular expressions you would need to escape special regex characters, at which point I think the regex solution becomes more of a headache than it's worth.

function getIndicesOf(searchStr, str, caseSensitive) {
    var searchStrLen = searchStr.length;
    if (searchStrLen == 0) {
        return [];
    }
    var startIndex = 0, index, indices = [];
    if (!caseSensitive) {
        str = str.toLowerCase();
        searchStr = searchStr.toLowerCase();
    }
    while ((index = str.indexOf(searchStr, startIndex)) > -1) {
        indices.push(index);
        startIndex = index + searchStrLen;
    }
    return indices;
}

var indices = getIndicesOf("le", "I learned to play the Ukulele in Lebanon.");

document.getElementById("output").innerHTML = indices + "";

<div id="output"></div>

Answer 2

Here is regex free version:

function indexes(source, find) {
  if (!source) {
    return [];
  }
  // if find is empty string return all indexes.
  if (!find) {
    // or shorter arrow function:
    // return source.split('').map((_,i) => i);
    return source.split('').map(function(_, i) { return i; });
  }
  var result = [];
  for (i = 0; i < source.length; ++i) {
    // If you want to search case insensitive use 
    // if (source.substring(i, i + find.length).toLowerCase() == find) {
    if (source.substring(i, i + find.length) == find) {
      result.push(i);
    }
  }
  return result;
}

indexes("I learned to play the Ukulele in Lebanon.", "le")

EDIT: and if you want to match strings like 'aaaa' and 'aa' to find [0, 2] use this version:

function indexes(source, find) {
  if (!source) {
    return [];
  }
  if (!find) {
      return source.split('').map(function(_, i) { return i; });
  }
  var result = [];
  var i = 0;
  while(i < source.length) {
    if (source.substring(i, i + find.length) == find) {
      result.push(i);
      i += find.length;
    } else {
      i++;
    }
  }
  return result;
}

Answer 3

You sure can do this!

//make a regular expression out of your needle
var needle = 'le'
var re = new RegExp(needle,'gi');
var haystack = 'I learned to play the Ukulele';

var results = new Array();//this is the results you want
while (re.exec(haystack)){
  results.push(re.lastIndex);
}

Edit: learn to spell RegExp

Also, I realized this isn't exactly what you want, as lastIndex tells us the end of the needle not the beginning, but it's close - you could push re.lastIndex-needle.length into the results array...

Edit: adding link

@Tim Down's answer uses the results object from RegExp.exec(), and all my Javascript resources gloss over its use (apart from giving you the matched string). So when he uses result.index, that's some sort of unnamed Match Object. In the MDC description of exec, they actually describe this object in decent detail.

Answer 4

If you just want to find the position of all matches I'd like to point you to a little hack:

haystack = 'I learned to play the Ukulele in Lebanon.'
needle = 'le'
splitOnFound = haystack.split(needle).map(function (culm) {
  return this.pos += culm.length + needle.length
}, {pos: -needle.length}).slice(0, -1)

it might not be applikable if you have a RegExp with variable length but for some it might be helpful.

Answer 5

Use String.prototype.match.

Here is an example from the MDN docs itself:

var str = 'ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz';
var regexp = /[A-E]/gi;
var matches_array = str.match(regexp);

console.log(matches_array);
// ['A', 'B', 'C', 'D', 'E', 'a', 'b', 'c', 'd', 'e']

Answer 6

Follow the answer of @jcubic, his solution caused a small confuse for my case
For example var result = indexes('aaaa', 'aa') it will return [0, 1, 2] instead of [0, 2]
So I updated a bit his solution as below to match my case

function indexes(text, subText, caseSensitive) {
    var _source = text;
    var _find = subText;
    if (caseSensitive != true) {
        _source = _source.toLowerCase();
        _find = _find.toLowerCase();
    }
    var result = [];
    for (var i = 0; i < _source.length;) {
        if (_source.substring(i, i + _find.length) == _find) {
            result.push(i);
            i += _find.length;  // found a subText, skip to next position
        } else {
            i += 1;
        }
    }
    return result;
}

Answer 7

Here is a simple Code

function getIndexOfSubStr(str, serchToken, preIndex, output){
		 var result = str.match(serchToken);
     if(result){
     output.push(result.index +preIndex);
     str=str.substring(result.index+serchToken.length);
     getIndexOfSubStr(str, serchToken, preIndex, output)
     }
     return output;
  };

var str = "my name is 'xyz' and my school name is 'xyz' and my area name is 'xyz' ";
var  serchToken ="my";
var preIndex = 0;

console.log(getIndexOfSubStr(str, serchToken, preIndex, []));

Answer 8

Thanks for all the replies. I went through all of them and came up with a function that gives the first an last index of each occurrence of the 'needle' substring . I am posting it here in case it will help someone.

Please note, it is not the same as the original request for only the beginning of each occurrence. It suits my usecase better because you don't need to keep the needle length.

function findRegexIndices(text, needle, caseSensitive){
  var needleLen = needle.length,
    reg = new RegExp(needle, caseSensitive ? 'gi' : 'g'),
    indices = [],
    result;

  while ( (result = reg.exec(text)) ) {
    indices.push([result.index, result.index + needleLen]);
  }
  return indices
}

Answer 9

the below code will do the job for you :

function indexes(source, find) {
  var result = [];
  for(i=0;i<str.length; ++i) {
    // If you want to search case insensitive use 
    // if (source.substring(i, i + find.length).toLowerCase() == find) {
    if (source.substring(i, i + find.length) == find) {
      result.push(i);
    }
  }
  return result;
}

indexes("hello, how are you", "ar")

Answer 10

function countInString(searchFor,searchIn){

 var results=0;
 var a=searchIn.indexOf(searchFor)

 while(a!=-1){
   searchIn=searchIn.slice(a*1+searchFor.length);
   results++;
   a=searchIn.indexOf(searchFor);
 }

return results;

}