String comparing algorithm

SimilarityTool.class.php

<?php

  /**
   * This class implements string comparison algorithm
   * based on character pair similarity
   *
   * @link http://www.catalysoft.com/articles/StrikeAMatch.html
   * @author Ilya Sabelnikov <[email protected]>
   */
  class SimilarityTool
  {
    /**
     * Compares the two strings based on letter pair matches
     *
     * @param string $str1
     * @param string $str2
     * @return float
     */
    public static function compareStrings ($str1, $str2)
    {
      if (0 == strlen($str1) + strlen($str2) || 0 == strcmp($str1, $str2))
      {
        return 1.0;
      }
      
      $pairs1 = self::wordLetterPairs($str1);
      $pairs2 = self::wordLetterPairs($str2);

      $pairs1Count = count($pairs1);
      $pairs2Count = count($pairs2);

      $union = $pairs1Count + $pairs2Count;
      
      if (0 == $union) 
      {
        return 0.0;
      }

      $intersection = 0;

      for ($i = 0; $i < $pairs1Count; $i ++ )
      {
        for ($j = 0; $j < $pairs2Count; $j ++ )
        {
          if (isset($pairs2[$j]))
          {
            if ($pairs1[$i] == $pairs2[$j])
            {
              $intersection ++;

              unset($pairs2[$j]);
              break;
            }
          }
        }
      }

      return (2 * $intersection) / $union;
    }

    /**
     * Gets all letter pairs for each individual word in the string
     *
     * @param string $str
     * @return array
     */
    private static function wordLetterPairs ($str)
    {
      $allPairs = array();

      // Tokenize the string and put the tokens/words into an array
      $words = explode(' ', $str);

      // For each word
      foreach ($words as $word)
      {
        if (! $word) 
        {
          continue;
        }
        
        // Find the pairs of characters
        $numPairs = mb_strlen($word, 'UTF-8') - 1;

        for ($i = 0; $i < $numPairs; $i ++)
        {
          $allPairs[] = mb_substr($word, $i, 2, 'UTF-8');
        }
      }

      return $allPairs;
    }
  }