php關鍵詞替換算法

<?php
/*

關鍵詞匹配類
$str = "是是是是是范德薩下一年,下一年誰誰誰水水水水的灑落開是是是是軍";
$key = new KeyReplace($str,array("下一年1"=>'http://baidu.com',"下一年"=>'baidu.com'));
echo $key->getResultText();
echo $key->getRuntime();
*/

$str = <<<ST
  做開眼角手術需要開刀。開眼角手術材料的韓式技術,根計開眼角手術方案。
ST;

$g=file_get_contents("t");
$kw=unserialize($g);

$nkw=array();

foreach ($kw as $k=>$g){

if(strpos($k,"開眼角")!==false)
    $nkw[$k]=str_replace("php?", "g", $g);

}

// $nkw=array("開眼角"=>"http://hurl1","開眼角手術"=>"http://hurl2");

$key = new KeyWordReplace($str,$nkw);
echo $key->getResultText();

/*

url 中的特殊符號 如 ? . {} 需要做轉義處理 ,替換完成之後再替換回來

  • 關鍵詞匹配類
  • $str = "是是是是是范德薩下一年,下一年誰誰誰水水水水的灑落開是是是是軍";
  • $key = new KeyReplace($str,array("下一年1"=>'http://baidu.com',"下一年"=>'baidu.com'));
  • echo $key->getResultText();
  • echo $key->getRuntime();
    */
    function cmp2($a, $b){

    $len_a=mb_strlen($a,"utf-8");
    $len_b=mb_strlen($b,"utf-8");

    if ($len_a == $len_b) return 0;
    return ($len_a< $len_b) ? 1 : -1;
    }

class KeyWordReplace
{
public $keys = array();
public $text = "";
private $runtime = 0;
public $url = true;
public $stopkeys = array();
public $all = false;
/**

  • @access public
  • @param string $text 指定被處理的文章
  • @param array $keys 指定字典詞組array(key=>url,...) url可以是數組,如果是數組將隨機替換其中的一個
  • @param array $stopkeys 指定停止詞array(key,...) 這裏面的詞將不會被處理
  • @param boolean $url true 表示替換成鏈接否則只替換
  • @param boolean $all true 表示替換所有找到的詞,否則只替換第一次
    */
    public function __construct($text='',$keys=array(),$url=true,$stopkeys=array(),$all=true) {
    $this->keys = $keys;
    $this->text = $text;
    $this->url = $url;
    $this->stopkeys = $stopkeys;
    $this->all = $all;
    }

    /**

  • 獲取處理好的文章
  • @access public
  • @return string text
    */
    public function getResultText() {
    $start = microtime(true);
    $keys = $this->hits_keys();

    $keys_tmp = array_keys($keys);
    
    usort($keys_tmp,"cmp2");
    
    foreach($keys_tmp as $key){
    
        if(is_array($keys[$key])){
            $url = $keys[$key][rand(0,count($keys[$key])-1)];
        }else
            $url = $keys[$key];
    
            $this->text = $this->r_s($this->text,$key,$url);
    }
    $this->runtime = microtime(true)-$start;
    
    return $this->text;

    }
    /**

  • 獲取處理時間
  • @access public
  • @return float
    */
    public function getRuntime() {

    return $this->runtime;

    }

    /**

  • 設置關鍵詞
  • @access public
  • @param array $keys array(key=>url,...)
    */
    public function setKeys($keys) {

    $this->keys = $keys;

    }
    /**

  • 設置停止詞
  • @access public
  • @param array $keys array(key,...)
    */
    public function setStopKeys($keys) {

    $this->stopkeys = $keys;

    }
    /**

  • 設置文章
  • @access public
  • @param string $text
    */
    public function setText($text) {

    $this->text = $text;

    }

    /**

  • 用來找到字符串裏面命中的關鍵詞
  • @access public
  • @return array $keys 返回匹配到的詞array(key=>url,...)
    */
    public function hits_keys(){
    $ar = $this->keys;
    $ar = $ar?$ar:array();
    $result=array();
    $str = $this->text;
    foreach($ar as $k=>$url){
    $k = trim($k);
    if(!$k)
    continue;
    if(strpos($str,$k)!==false && !in_array($k,$this->stopkeys)){
    $result[$k] = $url;
    }
    }
    return $result?$result:array();
    }

    /**

  • 用來找到字符串裏面命中的停止詞
  • @access public
  • @return array $keys 返回匹配到的詞array(key,...)
    */
    public function hits_stop_keys(){
    $ar = $this->stopkeys;
    $ar = $ar?$ar:array();
    $result=array();
    $str = $this->text;
    foreach($ar as $k){
    $k = trim($k);
    if(!$k)
    continue;
    if(strpos($str,$k)!==false && in_array($k,$this->stopkeys)){
    $result[] = $k;
    }
    }
    return $result?$result:array();
    }

    /**

  • 處理替換過程
  • @access private
  • @param string $text 被替換者
  • @param string $key 關鍵詞
  • @param string $url 鏈接
  • @return string $text 處理好的文章
    */
    private function r_s($text,$key,$url){

    $tmp_text = $text;
    
    $stop_keys = $this->hits_stop_keys();
    
    $stopkeys = $tags = $a = array();
    if(preg_match_all("#<a[^>]+>[^<]*</a[^>]*>#su",$tmp_text,$m)){
        $a=$m[0];
    
        foreach($m[0] as $k=>$z){
            $z = preg_replace("#\##s","\#",$z);
            $tmp_text = preg_replace('#'.$z.'#s',"[_a".$k."_]",$tmp_text,1);
        }
    };
    
    if(preg_match_all("#<[^>]+>#s",$tmp_text,$m)){
        $tags = $m[0];
        foreach($m[0] as $k=>$z){
            $z = preg_replace("#\##s","\#",$z);
            $tmp_text = preg_replace('#'.$z.'#s',"[_tag".$k."_]",$tmp_text,1);
        }
    }
    if(!empty($stop_keys)){
        if(preg_match_all("#".implode("|",$stop_keys)."#s",$tmp_text,$m)){
            $stopkeys = $m[0];
            foreach($m[0] as $k=>$z){
                $z = preg_replace("#\##s","\#",$z);
                $tmp_text = preg_replace('#'.$z.'#s',"[_s".$k."_]",$tmp_text,1);
            }
        }
    }
    $key1 = preg_replace("#([\#\(\)\[\]\*])#s","\\\\$1",$key);
    
    if($this->url)
        $tmp_text = preg_replace("#(?!\[_s|\[_a|\[_|\[_t|\[_ta|\[_tag)".$key1."(?!ag\d+_\]|g\d+_\]|\d+_\]|s\d+_\]|_\])#us",'<a href="'.$url.'">'.$key.'</a>',$tmp_text,$this->all?-1:1);
    else
        $tmp_text = preg_replace("#(?!\[_s|\[_a|\[_|\[_t|\[_ta|\[_tag)".$key1."(?!ag\d+_\]|g\d+_\]|\d+_\]|s\d+_\]|_\])#us",$url,$tmp_text,$this->all?-1:1);
    
            if(!empty($a)){
    
                foreach($a as $n=>$at){
    
                    $tmp_text = str_replace("[_a".$n."_]",$at,$tmp_text);
    
                }
    
            }
            if(!empty($tags)){
    
                foreach($tags as $n=>$at){
    
                    $tmp_text = str_replace("[_tag".$n."_]",$at,$tmp_text);
    
                }
    
            }
            if(!empty($stopkeys)){
    
                foreach($stopkeys as $n=>$at){
    
                    $tmp_text = str_replace("[_s".$n."_]",$at,$tmp_text);
    
                }
            }
            return $tmp_text;

    }
    }

發表評論
所有評論
還沒有人評論,想成為第一個評論的人麼? 請在上方評論欄輸入並且點擊發布.
相關文章