Get index of each capture in a JavaScript regex

Question

I want to match a regex like /(a).(b)(c.)d/ with \"aabccde\", and get the following information back:

\"a\" at index = 0
\"b\" at i         


        

Answer 1

So, you have a text and a regular expression:

txt = "aabccde";
re = /(a).(b)(c.)d/;

The first step is to get the list of all substrings that match the regular expression:

subs = re.exec(txt);

Then, you can do a simple search on the text for each substring. You will have to keep in a variable the position of the last substring. I've named this variable cursor.

var cursor = subs.index;
for (var i = 1; i < subs.length; i++){
    sub = subs[i];
    index = txt.indexOf(sub, cursor);
    cursor = index + sub.length;


    console.log(sub + ' at index ' + index);
}

EDIT: Thanks to @nhahtdh, I've improved the mechanism and made a complete function:

String.prototype.matchIndex = function(re){
    var res  = [];
    var subs = this.match(re);

    for (var cursor = subs.index, l = subs.length, i = 1; i < l; i++){
        var index = cursor;

        if (i+1 !== l && subs[i] !== subs[i+1]) {
            nextIndex = this.indexOf(subs[i+1], cursor);
            while (true) {
                currentIndex = this.indexOf(subs[i], index);
                if (currentIndex !== -1 && currentIndex <= nextIndex)
                    index = currentIndex + 1;
                else
                    break;
            }
            index--;
        } else {
            index = this.indexOf(subs[i], cursor);
        }
        cursor = index + subs[i].length;

        res.push([subs[i], index]);
    }
    return res;
}


console.log("aabccde".matchIndex(/(a).(b)(c.)d/));
// [ [ 'a', 1 ], [ 'b', 2 ], [ 'cc', 3 ] ]

console.log("aaa".matchIndex(/(a).(.)/));
// [ [ 'a', 0 ], [ 'a', 1 ] ] <-- problem here

console.log("bababaaaaa".matchIndex(/(ba)+.(a*)/));
// [ [ 'ba', 4 ], [ 'aaa', 6 ] ]