php判断两个中文字符串相似度
php相关 /
2022年02月23日 17时07分 /
3770人浏览
php判断两个中文字符串相似度,以百分比输出相似度。
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, $len2 - 1);
}
/* 返回两个串的相似度
*/
public function getSimilar($str1, $str2) {
$len1 = strlen($str1);
$len2 = strlen($str2);
$len = strlen($this->getLCS($str1, $str2, $len1, $len2));
return round($len * 2 / ($len1 + $len2),2);
}
private function initC($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][$j - 1];
}
}
}
}
private function printLCS($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);
}
}
}
$c = new LCS();
$t = $c->getSimilar('春秋航空:拟5000万元-1亿元回购股份', '春秋航空:拟5000万元-1亿元回购公司股份');
var_dump($t);
//float(0.94)