MarkJane
4/12/2017 - 7:42 AM

计算字符相似度.php

计算字符相似度.php

<?php
class LCS {
  public $str1;
  public $str2;
  public $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][$j - 1] + 1;
        } else if ($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[$j];
    } else if ($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
$url_1 = "https://play.google.com/store/apps/details?id=com.dotc.ime.latin.flash&referrer=pid%3Davazu_int%26c%3DGlobal_Nativeads%26clickid%3Dsq5qdfxc03o9%26af_siteid%3D10152%26af_sub1%3D_nw_1118109";
$url_2 = "https://play.google.com/store/apps/details?id=com.dotc.ime.latin.flash&referrer=pid%3Davazu_int%26c%3DGlobal_Nativeads%26clickid%3Dsqu1xlve8ihn%26af_siteid%3D10152%26af_sub1%3D_nw_1118109";
echo $lcs->getLCS($url_1,$url_2)."<br /><br />";
//返回相似度
echo $lcs->getSimilar($url_1,$url_2);
/*问题:如何解决 Maximum function nesting level of ‘100’ reached
PHP 中当函数调用层数超过限制的时候就会出现 Maximum function nesting level of ‘100’ reached
默认情况下函数嵌套不能超过 100 层
我们可以通过修改配置文件来解决此问题
修改 php.ini
添加
xdebug.max_nesting_level=600
*/