Substring text with HTML tags in Javascript

Question

Do you have solution to substring text with HTML tags in Javascript?

For example:

var str = 'Lorem ipsum <a href="#">dolor <strong>sit</strong> amet</a>, consectetur adipiscing elit.'

html_substr(str, 20)
// return Lorem ipsum <a href="#">dolor <strong>si</strong></a>

html_substr(str, 30)
// return Lorem ipsum <a href="#">dolor <strong>sit</strong> amet</a>, co

Answer 1

Taking into consideration that parsing html with regex is a bad idea, here is a solution that does just that :)

EDIT: Just to be clear: This is not a valid solution, it was meant as an exercise that made very lenient assumptions about the input string, and as such should be taken with a grain of salt. Read the link above and see why parsing html with regex can never be done.

function htmlSubstring(s, n) {
    var m, r = /<([^>\s]*)[^>]*>/g,
        stack = [],
        lasti = 0,
        result = '';

    //for each tag, while we don't have enough characters
    while ((m = r.exec(s)) && n) {
        //get the text substring between the last tag and this one
        var temp = s.substring(lasti, m.index).substr(0, n);
        //append to the result and count the number of characters added
        result += temp;
        n -= temp.length;
        lasti = r.lastIndex;

        if (n) {
            result += m[0];
            if (m[1].indexOf('/') === 0) {
                //if this is a closing tag, than pop the stack (does not account for bad html)
                stack.pop();
            } else if (m[1].lastIndexOf('/') !== m[1].length - 1) {
                //if this is not a self closing tag than push it in the stack
                stack.push(m[1]);
            }
        }
    }

    //add the remainder of the string, if needed (there are no more tags in here)
    result += s.substr(lasti, n);

    //fix the unclosed tags
    while (stack.length) {
        result += '</' + stack.pop() + '>';
    }

    return result;

}

Example: http://jsfiddle.net/danmana/5mNNU/

Note: patrick dw's solution may be safer regarding bad html, but I'm not sure how well it handles white spaces.

Answer 2

Usage:

var str = 'Lorem ipsum <a href="#">dolor <strong>sit</strong> amet</a>, consectetur adipiscing elit.';

var res1 = html_substr( str, 20 );
var res2 = html_substr( str, 30 );

alert( res1 ); // Lorem ipsum <a href="#">dolor <strong>si</strong></a>
alert( res2 ); // Lorem ipsum <a href="#">dolor <strong>sit</strong> amet</a>, co

Example: http://jsfiddle.net/2ULbK/4/

---

Function:

function html_substr( str, count ) {

    var div = document.createElement('div');
    div.innerHTML = str;

    walk( div, track );

    function track( el ) {
        if( count > 0 ) {
            var len = el.data.length;
            count -= len;
            if( count <= 0 ) {
                el.data = el.substringData( 0, el.data.length + count );
            }
        } else {
            el.data = '';
        }
    }

    function walk( el, fn ) {
        var node = el.firstChild;
        do {
            if( node.nodeType === 3 ) {
                fn(node);
                    //          Added this >>------------------------------------<<
            } else if( node.nodeType === 1 && node.childNodes && node.childNodes[0] ) {
                walk( node, fn );
            }
        } while( node = node.nextSibling );
    }
    return div.innerHTML;
}