-
-
/* - * Keyword matching class
- * @author ylx
- * @packet mipang
- * Usage examples
- * $str = "The green-shelled laying hen spreads Van der Sar next year, and the next year 1 spreads open the room Lucas local army";
- * $key = new KeyReplace($str,array("xxxx"=>"sadf", "Next year 1" =>'http://baidu.com',"Next year" =>'google.com'));
- * echo $key->getResultText();
- * echo $key->getRuntime();
- */
- class KeyReplace
- {
- private $keys = array();
- private $text = "";
- private $runtime = 0;
- private $url = true;
- private $stopkeys = array();
- private $all = false;
- /**
- * @access public
- * @param string $text specifies the article to be processed
- * @param array $keys specifies the dictionary phrase array(key=>url,...) url can be an array, if it is an array it will be replaced randomly One of them
- * @param array $stopkeys specifies stop words array(key,...) The words in this will not be processed
- * @param boolean $url true means to replace it with a link, otherwise it will only be replaced
- * @param boolean $all true means replace all found words, otherwise only replace the first time
- */
- public function __construct($text='',$keys=array(),$url=true,$stopkeys=array (),$all=false) {
- $this->keys = $keys;
- $this->text = $text;
- $this->url = $url;
- $this->stopkeys = $stopkeys;
- $this->all = $all;
- }
/**
- * Get the processed article
- * @access public
- * @return string text
- */
- public function getResultText() {
- $start = microtime(true);
- $keys = $this->hits_keys();
$keys_tmp = array_keys($keys);
function cmp($a, $b ){
- if (mb_strlen($a) == mb_strlen($b)) {
- return 0;
- }
- return (mb_strlen($a) < mb_strlen($b)) ? 1 : -1;
- }< ;/p>
usort($keys_tmp,"cmp");
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);
- < p> }
- $this->runtime = microtime(true)-$start;
return $this->text;
- }
- /**
- * Get processing time
- * @access public
- * @return float
- */
- public function getRuntime() {
return $this->runtime;
}
/**
- * Set keywords
- * @access public
- * @param array $keys array(key=>url,...)
- */
- public function setKeys($keys) {
$this->keys = $keys;
}
- /**
- * Set stop words
- * @access public
- * @param array $keys array(key,...)
- * /
- public function setStopKeys($keys) {
$this->stopkeys = $keys;
}
- /**
- * Set article
- * @access public
- * @param string $text
- */
- public function setText($text) {
$this->text = $text;
}
/**
- * Used to find the hit keywords in the string
- * @access public
- * @return array $keys Returns the matched word 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( );
- }
/**
- * Used to find the hit stop words in the string
- * @access public
- * @return array $keys Returns the matched word 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();
- }
/**
- * Handle the replacement process
- * @access private
- * @param string $text The person being replaced
- * @param string $key Keywords
- * @param string $url Link
- * @return string $text The processed article
- */
- private function r_s($text,$key,$url){
$tmp = $text;
$stop_keys = $this->hits_stop_keys();
$stopkeys = $tags = $a = array();
- if(preg_match_all("#]+>[^<]*]*>#su",$tmp,$m)){
- $a=$m[0];
foreach($m[0] as $k=>$z){
- $z = preg_replace("###s","#",$z);
$tmp = preg_replace('#'.$z.'#s',"[_a".$k."_]",$tmp,1);
- }
};
if(preg_match_all("#<[^>]+>#s",$tmp,$m)){
- $tags = $m[0];
- foreach($m[0] as $k=>$z){
- $z = preg_replace("###s","#",$z);
- $tmp = preg_replace('#'.$z.'#s',"[_tag".$k."_]",$tmp,1);
- }
- }
- if(!empty($stop_keys)){
- if(preg_match_all("#".implode("|",$stop_keys)."#s",$tmp,$m)){
- $stopkeys = $m[0];
- foreach($m[0] as $k=>$z){
- $z = preg_replace("###s","#",$z);
- $tmp = preg_replace('#'.$z.'#s',"[_s".$k."_]",$tmp,1);
- }
- }
- }
- $key1 = preg_replace("#([#()[]*])#s","\\$1",$key);
if($this->url)
- $tmp = preg_replace("#(?![_s|[_a|[_|[_t|[_ta|[_tag)".$key1."(?!agd+_]|gd+_]|d+_]|sd+_]|_])#us",''.$key.'',$tmp,$this->all?-1:1);
- else
- $tmp = preg_replace("#(?![_s|[_a|[_|[_t|[_ta|[_tag)".$key1."(?!agd+_]|gd+_]|d+_]|sd+_]|_])#us",$url,$tmp,$this->all?-1:1);
if(!empty($a)){
foreach($a as $n=>$at){
$tmp = str_replace("[_a".$n."_]",$at,$tmp);
}
}
- if(!empty($tags)){
foreach($tags as $n=>$at){
$tmp = str_replace("[_tag".$n."_]",$at,$tmp);
}
}
- if(!empty($stopkeys)){
foreach($stopkeys as $n=>$at){
$tmp = str_replace("[_s".$n."_]",$at,$tmp);
}
}
- return $tmp;
- }
- }
-
复制代码
|