下面的例子是利用php将"全"这中编码转换为gb2312. <?php $str = "TTL全天候自动聚焦"; $str = preg_replace("|&#([0-9]{1,5});|", "\".u2utf82gb(\\1).\"", $str); $str = "\$str=\"$str\";";
eval($str); echo $str;
function u2utf82gb($c){ $str=""; if ($c < 0x80) { $str.=$c; } else if ($c < 0x800) { $str.=chr(0xC0 | $c>>6); $str.=chr(0x80 | $c & 0x3F); } else if ($c < 0x10000) { $str.=chr(0xE0 | $c>>12); $str.=chr(0x80 | $c>>6 & 0x3F); $str.=chr(0x80 | $c & 0x3F); } else if ($c < 0x200000) { $str.=chr(0xF0 | $c>>18); $str.=chr(0x80 | $c>>12 & 0x3F); $str.=chr(0x80 | $c>>6 & 0x3F); $str.=chr(0x80 | $c & 0x3F); } return iconv('UTF-8', 'GB2312', $str); } ?>
或者是
function unescape($str) { $str = rawurldecode($str); preg_match_all("/(?:%u.{4})|&#x.{4};|&#\d+;|.+/U",$str,$r); $ar = $r[0]; print_r($ar); foreach($ar as $k=>$v) { if(substr($v,0,2) == "%u") $ar[$k] = iconv("UCS-2","GB2312",pack("H4",substr($v,-4))); elseif(substr($v,0,3) == "&#x") $ar[$k] = iconv("UCS-2","GB2312",pack("H4",substr($v,3,-1))); elseif(substr($v,0,2) == "&#") { echo substr($v,2,-1)."<br>"; $ar[$k] = iconv("UCS-2","GB2312",pack("n",substr($v,2,-1))); } } return join("",$ar); }
(编辑:aniston)
|