Algorithm to get changes between two arrays

Question

I needed to create an algorithm which will (efficiently) take an old array and a new array and give me back the changes between the two (which items added, which removed). It ha

Answer 1

I created a speed test between two possible implementations.

Source code:

function diff1 (o, n) { 
  // deal with empty lists 
  if (o == undefined) o = []; 
  if (n == undefined) n = []; 

  // sort both arrays (or this won't work) 
  o.sort(); n.sort(); 

  // don't compare if either list is empty 
  if (o.length == 0 || n.length == 0) return {added: n, removed: o}; 

  // declare temporary variables 
  var op = 0; var np = 0; 
  var a = []; var r = []; 

  // compare arrays and add to add or remove lists 
  while (op < o.length && np < n.length) { 
      if (o[op] < n[np]) { 
          // push to diff? 
          r.push(o[op]); 
          op++; 
      } 
      else if (o[op] > n[np]) { 
          // push to diff? 
          a.push(n[np]); 
          np++; 
      } 
      else { 
          op++;np++; 
      } 
  } 

  // add remaining items 
  if( np < n.length ) 
    a = a.concat(n.slice(np, n.length)); 
  if( op < o.length ) 
    r = r.concat(o.slice(op, o.length)); 

  return {added: a, removed: r};  
}

function diff2 (o, n) {
        // convert array items to object members
    var objO = {}, objN = {};
    for (var i = 0; i < o.length; i++) {
        objO[o[i]] = 1;
    }
    for (var i = 0; i < n.length; i++) {
        objN[n[i]] = 1;
    }

    var a = []; var r = []; 

    for (var i in objO) {
        if (i in objN) {
            delete objN[i];
        }
        else {
            r.push (i);
        }
    }
    for (var i in objN) {
        a.push (i);
    }
    return {added: a, removed: r};
}

var o = [], n = [];
for (var i = 0; i < 300000; i++) {
    if (i % 2 == 0) {
        o.push (i);
    }
    if (i % 3 == 0) {
        n.push (i);
    }
}

var start = new Date ();
diff1 (o, n);
var end1 = new Date ();
diff2 (o, n);
var end2 = new Date ();

alert ((end1 - start) + ", " + (end2 - end1));

The disadvantage of diff2 that the returned arrays (added, removed) are not sorted.

Speed Test:

IE7: diff1: 2578ms, diff2: 1906ms

IE8: diff1: 1953ms, diff2: 1152ms

Firefox: diff1: 254ms, diff2: 527ms

Opera: diff1: 143ms, diff2: 253ms

Safari: diff1: 466ms, diff2: 657ms

Chrome: diff1: 734ms, diff2: 581ms

Conclusion: diff1 is faster in Firefox, Opera and Safari, diff2 is faster in IE and Chrome.