汉字html实体的反转换

 

$a = '华诺国际';

echo html2char($a);

 

 

file_put_contents('test.txt',_htmltochar($a));

exit;

 

//将html汉字实体数字编码转换为汉字

//yangyu{at}sina.cn
function html2char($html){
 return preg_replace('/(/&/#)(/d{5});/mise',"iconv('UCS-2','GBK',pack('H4',dechex(//2)) )", $html);
}

function _htmltochar($dec){
 $dec = str_replace(array('&','#'),'',$dec);
 $dec = split('[;；]',rtrim($dec,';'));
 $utf = '';
 foreach ($dec as $v){
  $utf .= chr(224 + (($v - ($v % 4096)) / 4096));
  $utf .= chr(128 + ((($v % 4096) - ($v % 64)) / 64));
  $utf .= chr(128 + ($v % 64));
 }
    return $utf;
}

function phpunescape($str) {
         $str = rawurldecode($str);
         preg_match_all("/%u.{4}|&#x.{4};|&#d+;|.+/U",$str,$r);
         $ar = $r[0];
         foreach($ar as $k=>$v) {
                  if(substr($v,0,2) == "%u")
                           $ar[$k] = iconv("UCS-2","utf-8",pack("H4",substr($v,-4)));
                  elseif(substr($v,0,3) == "&#x")
                           $ar[$k] = iconv("UCS-2","utf-8",pack("H4",substr($v,3,-1)));
                  elseif(substr($v,0,2) == "&#") {
                           $ar[$k] = iconv("UCS-2","utf-8",pack("n",substr($v,2,-1)));
                    }
           }
         return join("",$ar);
}