php相似度比较的方法:
- 使用php函数
similar_text(string1,string2,percent)
参数 | 描述 |
---|---|
string1 | 必需。规定要比较的第一个字符串。 |
string2 | 必需。规定要比较的第二个字符串。 |
percent | 可选。规定供存储百分比相似度的变量名。 |
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][$j - 1] + 1;
} else if ($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();
方法2会有字数限制,超出一定字数会报错(函数调用层数超过限制)
( ! ) Fatal error: Maximum function nesting level of ‘256’ reached, aborting!
$string1="hello world!";
$string2="hello php!";
$lcs = new LCS();
echo $lcs->getSimilar($string1,$string2); //0.70967741935484
echo "<br/>";
echo $lcs->getLCS($string1,$string2); //hello !
echo "<br/>";
similar_text($string1,$string2,$similar) ;
echo $similar; //70.967741935484