Determine if two strings are similar in Javascript?

Question

Let's say I have two strings, is there any way to check if they are at least 90% similar? var string1 = "theBoardmeetstoday,tomorrow51"; var string2 = "Board meets today, tomorrow"; Thanks, Tegan

Answer 1

There are add-on libraries that perform this. One interesting attempt to do this without an add-on library can be found here: https://codepad.co/snippet/javascript-calculating-similarity-between-two-strings. It attempts to employ a Levenshtein distance calculation, which is effectively what you are seeking.

One very simple approach to this might involve stripping out white spaces, converting everything to lowercase, then summing and comparing the ascii values of the content of the strings. The closer the sum, the more (likely) similar the two strings are. This could be augmented by taking the character-by-character content of the smaller string, removing that from the larger string, comparing the difference, etc.

The L-D version is pasted, below, in the event that the codepad snippet is deleted:

function similarity(s1, s2) {

var longer = s1;

var shorter = s2;

if (s1.length < s2.length) {

longer = s2;

shorter = s1;

}

var longerLength = longer.length;

if (longerLength === 0) {

return 1.0;

}

return (longerLength - editDistance(longer, shorter)) / parseFloat(longerLength);

}

function editDistance(s1, s2) {

s1 = s1.toLowerCase();

s2 = s2.toLowerCase();

var costs = new Array();

for (var i = 0; i <= s1.length; i++) {

var lastValue = i;

for (var j = 0; j <= s2.length; j++) {

if (i == 0)

costs[j] = j;

else {

if (j > 0) {

var newValue = costs[j - 1];

if (s1.charAt(i - 1) != s2.charAt(j - 1))

newValue = Math.min(Math.min(newValue, lastValue),

costs[j]) + 1;

costs[j - 1] = lastValue;

lastValue = newValue;

}

}

}

if (i > 0)

costs[s2.length] = lastValue;

}

return costs[s2.length];

}

var $str1="Marco Antonio Piñero Lopez";

var $str2="marco antonio Pineda lópez";

var perc=Math.round(similarity($str1,$str2)*10000)/100;

var txt="The strings: <span class=\"str\">'"+$str1+"'</span> and <span class=\"str\">'"+$str2+"'</span>";

txt+="<br>are similar <span class=\"perc\">"+perc+"%</span>";

document.write(txt);

Answer 2

It can only check if there it is true or false. There isn't a way to check if there are partially correct.