对字符串进行正则表达式归纳

function getNames($names){

    foreach ($names as $key => $name) {
        $ysname = $name;

        $name = str_replace('）',')', $name);
        $name = str_replace('（','(', $name);    
        $name = str_replace('　',' ', $name);
        $name = trim( $name );
        $name = trim( $name , ',' );

        if($name == '') continue;

        $str  = $name;
        
        $tempReg = [];

        for($i=0;$i<strlen($name);$i++){
            $lastReg = end($tempReg);
            $lastRegIndex = count($tempReg) - 1;

            if(preg_match('/^[\x{4e00}-\x{9fa5}].*?/u',$str)){
                $str = substr($str, 3);
                
                if($lastReg == '([\x{4e00}-\x{9fa5}])'){
                    $tempReg[ $lastRegIndex ] = '([\x{4e00}-\x{9fa5}]{2})';
                }else if( preg_match('/9fa5\}\]\{(\d+)\}\)$/', $lastReg , $match ) ){
                    $tempReg[ $lastRegIndex ] = '([\x{4e00}-\x{9fa5}]{'. ( $match[1] + 1 ) .'})';
                }else{
                    $tempReg[] = '([\x{4e00}-\x{9fa5}])';
                }

                $i = $i + 2;
            }else if(preg_match('/^、.*?/u',$str)){
                $str = substr($str, 3);
                $tempReg[] = '(、)';
                $i = $i + 2;
            }else if(preg_match('/^（.*?/u',$str)){
                $str = substr($str, 3);
                $tempReg[] = '(（)';
                $i = $i + 2;
            }else if(preg_match('/^）.*?/u',$str)){
                $str = substr($str, 3);
                $tempReg[] = '(）)';
                $i = $i + 2;
            }else if(preg_match('/^　.*?/u',$str)){
                $str = substr($str, 3);
                $tempReg[] = '(　)';
                $i = $i + 2;
            }else if(preg_match('/^：.*?/u',$str)){
                $str = substr($str, 3);
                $tempReg[] = '(：)';
                $i = $i + 2;
            }else if(preg_match('/^，.*?/u',$str)){
                $str = substr($str, 3);
                $tempReg[] = '(，)';
                $i = $i + 2;
            }else if(preg_match('/^；.*?/u',$str)){
                $str = substr($str, 3);
                $tempReg[] = '(；)';
                $i = $i + 2;
            }else if(preg_match('/^【.*?/u',$str)){
                $str = substr($str, 3);
                $tempReg[] = '(【)';
                $i = $i + 2;
            }else if(preg_match('/^】.*?/u',$str)){
                $str = substr($str, 3);
                $tempReg[] = '(】)';
                $i = $i + 2;
            }else if(preg_match('/^。.*?/u',$str)){
                $str = substr($str, 3);
                $tempReg[] = '(。)';
                $i = $i + 2;
            }else if(preg_match('/^＃.*?/u',$str)){
                $str = substr($str, 3);
                $tempReg[] = '(＃)';
                $i = $i + 2;
            }else if(preg_match('/^[a-zA-Z].*?/',$str)){
                $str = substr($str, 1);

                if($lastReg == '([a-zA-Z])'){
                    $tempReg[ $lastRegIndex ] = '([a-zA-Z]{2})';
                }else if( preg_match('/^\(\[a-zA-Z\]\{(\d+)\}\)$/', $lastReg , $match ) ){
                    $tempReg[ $lastRegIndex ] = '([a-zA-Z]{'. ( $match[1] + 1 ) .'})';
                }else{
                    $tempReg[] = '([a-zA-Z])';
                }

            }else if(preg_match('/^\d.*?/',$str)){
                $str = substr($str, 1);
 
                if($lastReg == '(\d)'){
                    $tempReg[ $lastRegIndex ] = '(\d{2})';
                }else if( preg_match('/\(\\\d\{(\d+)\}\)$/', $lastReg , $match ) ){
                    $tempReg[ $lastRegIndex ] = '(\d{'. ( $match[1] + 1 ) .'})';
                }else{
                    $tempReg[] = '(\d)';
                }

            }else if(preg_match('/^_.*?/',$str)){
                $str = substr($str, 1);
                $tempReg[] = '(_)';
            }else if(preg_match('/^-.*?/',$str)){
                $str = substr($str, 1);
                $tempReg[] = '(-)';
            }else if(preg_match('/^\(.*?/',$str)){
                $str = substr($str, 1);
                $tempReg[] = '(\()';
            }else if(preg_match('/^\).*?/',$str)){
                $str = substr($str, 1);
                $tempReg[] = '(\))';
            }else if(preg_match('/^\..*?/',$str)){
                $str = substr($str, 1);
                $tempReg[] = '(\.)';
            }else if(preg_match('/^\[.*?/',$str)){
                $str = substr($str, 1);
                $tempReg[] = '(\[)';
            }else if(preg_match('/^\].*?/',$str)){
                $str = substr($str, 1);
                $tempReg[] = '(\])';
            }else if(preg_match('/^\/.*?/',$str)){
                $str = substr($str, 1);
                $tempReg[] = '(\/)';
            }else if(preg_match('/^,.*?/',$str)){
                $str = substr($str, 1);
                $tempReg[] = '(,)';
            }else if(preg_match('/^:.*?/',$str)){
                $str = substr($str, 1);
                $tempReg[] = '(:)';
            }else if(preg_match('/^;.*?/',$str)){
                $str = substr($str, 1);
                $tempReg[] = '(;)';
            }else if(preg_match('/^ .*?/',$str)){
                $str = substr($str, 1);
                $tempReg[] = '( )';
            }else if(preg_match('/^＃*?/',$str)){
                $str = substr($str, 1);
                $tempReg[] = '(＃)';
            }else if(preg_match('/^·.*?/',$str)){
                $str = substr($str, 2);
                $tempReg[] = '(·)';
                $i = $i + 1;
            }else{
                var_dump($ysname);
                echo $str . " weizhi\n";
                var_dump($str);
                $tempReg[] = '(未知)';
            }
        }

        $tempReg = implode('', $tempReg);
        $allRegData[$tempReg][] = $ysname;
    }

    return $allRegData;
}

上述代码的功能主要是对数量较大、单条字符长度不长的文字进行正则表达式分类归纳。