当前位置:爱推吧 » php教程 » PHP类:比较两个字符串的相似度

PHP类:比较两个字符串的相似度

从网上找到的,试了下,还是比较精确。

<?php
/* vim: set expandtab tabstop=4 shiftwidth=4: */
// +----------------------------------------------------------------------+
// | PHP version 5 |
// +----------------------------------------------------------------------+
// | Copyright (c) 1997-2004 The PHP Group |
// +----------------------------------------------------------------------+
// | This source file is subject to version 3.0 of the PHP license, |
// | that is bundled with this package in the file LICENSE, and is |
// | available through the world-wide-web at the following url: |
// | http://www.php.net/license/3_0.txt. |
// | If you did not receive a copy of the PHP license and are unable to |
// | obtain it through the world-wide-web, please send a note to |
// | license@php.net so we can mail you a copy immediately. |
// +----------------------------------------------------------------------+
// | Authors: Original Author <author@example.com> |
// | Your Name <you@example.com> |
// +----------------------------------------------------------------------+
//
// $Id:$

class LCS {
 var $str1;
 var $str2;
 var $c = array();
 /*返回串一和串二的最长公共子序列*/
 function getLCS($str1, $str2, $len1 = 0, $len2 = 0) {
 $this->str1 = $str1;
 $this->str2 = $str2;
 if ($len1 == 0) $len1 = strlen($str1);
 if ($len2 == 0) $len2 = strlen($str2);
 $this->initC($len1, $len2);
 return $this->printLCS($this->c, $len1 - 1, $len2 - 1);
 }
 /*返回两个串的相似度
 */
 function getSimilar($str1, $str2) {
 $len1 = strlen($str1);
 $len2 = strlen($str2);
 $len = strlen($this->getLCS($str1, $str2, $len1, $len2));
 return $len * 2 / ($len1 + $len2);
 }
 function initC($len1, $len2) {
 for ($i = 0; $i < $len1; $i++) $this->c[$i][0] = 0;
 for ($j = 0; $j < $len2; $j++) $this->c[0][$j] = 0;
 for ($i = 1; $i < $len1; $i++) {
 for ($j = 1; $j < $len2; $j++) {
 if ($this->str1[$i] == $this->str2[$j]) {
 $this->c[$i][$j] = $this->c[$i - 1][$j - 1] + 1;
 } elseif ($this->c[$i - 1][$j] >= $this->c[$i][$j - 1]) {
 $this->c[$i][$j] = $this->c[$i - 1][$j];
 } else {
 $this->c[$i][$j] = $this->c[$i][$j - 1];
 }
 }
 }
 }
 function printLCS($c, $i, $j) {
 if ($i == 0 || $j == 0) {
 if ($this->str1[$i] == $this->str2[$j]) return $this->str2[$j];
 else return "";
 }
 if ($this->str1[$i] == $this->str2[$j]) {
 return $this->printLCS($this->c, $i - 1, $j - 1).$this->str2[$j];
 } elseif ($this->c[$i - 1][$j] >= $this->c[$i][$j - 1]) {
 return $this->printLCS($this->c, $i - 1, $j);
 } else {
 return $this->printLCS($this->c, $i, $j - 1);
 }
 }
}
$lcs = new LCS();
//返回最长公共子序列
$lcs->getLCS("hello word", "hello china");
//返回相似度
echo $lcs->getSimilar("新日程(上)", "新日程(下)");
?>

发表评论

电子邮件地址不会被公开。 必填项已用*标注