PHP中文关键词匹配

Posted 2020-10-21 cnsr

以关键词为key，构建字典数组，对每个关键词可实现常数级别的查找。使用最长匹配算法，具体代码如下：

 

 1 class WordMatcher {
 2     public $dict = [];
 3     public $wordMaxLen = 0;
 4 
 5     function __construct(){
 6         if(! extension_loaded(‘mbstring‘)) {
 7             exit(‘extension mbstring is not loaded‘);
 8         }
 9     }
10 
11     function addWord($word) {
12         $len = mb_strlen($word);
13         $this->wordMaxLen = $len > $this->wordMaxLen ? $len : $this->wordMaxLen;
14         $this->dict[$word] = 1;
15     }
16 
17     function removeWord($word) {
18         unset($this->dict[$word]);
19     }
20 
21     function match($str, &$matched) {
22         if(mb_strlen($str) < 1) {
23             return;
24         }
25 
26         $len = $this->wordMaxLen;
27         while($len>0) {
28             $substr = mb_substr($str, 0, $len);
29             if(isset($this->dict[$substr])) {
30                 $matched[] = $substr;
31                 break;
32             } else {
33                 $len--;
34             }
35         }
36         if($len == 0) {
37             $len = 1;
38         }
39         $str = mb_substr($str, $len);
40         $this->match($str, $matched);
41     }
42 }
43 
44 $matcher = new WordMatcher;
45 $matcher->addWord(‘php‘);
46 $matcher->addWord(‘语言‘);
47 
48 
49 $matcher->match(‘PHP是最好的语言‘, $matched);