Created
March 4, 2012 20:35
-
-
Save olegp/1974682 to your computer and use it in GitHub Desktop.
String Similarity
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
// JS port of http://www.catalysoft.com/articles/StrikeAMatch.html | |
function similarity(str1, str2) { | |
function letterPairs(str) { | |
var pairs = []; | |
for ( var i = 0; i < str.length - 1; i++) { | |
pairs.push(str.substr(i, i + 2)); | |
} | |
return pairs; | |
} | |
function wordLetterPairs(str) { | |
var allPairs = []; | |
var words = str.split("\\s"); | |
for ( var w = 0; w < words.length; w++) { | |
var pairsInWord = letterPairs(words[w]); | |
for ( var p = 0; p < pairsInWord.length; p++) { | |
allPairs.push(pairsInWord[p]); | |
} | |
} | |
return allPairs; | |
} | |
var pairs1 = wordLetterPairs(str1.toUpperCase()); | |
var pairs2 = wordLetterPairs(str2.toUpperCase()); | |
var intersection = 0; | |
var union = pairs1.length + pairs2.length; | |
for ( var i = 0; i < pairs1.length; i++) { | |
var pair1 = pairs1[i]; | |
for ( var j = 0; j < pairs2.length; j++) { | |
var pair2 = pairs2[j]; | |
if (pair1[0] == pair2[0] && pair1[1] == pair2[1]) { | |
intersection++; | |
pairs2.slice(j, 1); | |
break; | |
} | |
} | |
} | |
return (2.0 * intersection) / union; | |
} |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment