假如使用 iconv() 函数转换编码就相比比较简单了,不过很多虚拟主机里并不支持这个组件,我在网上找半天,才找到一个gb2312转utf-8的方法,但不能逆向转换。
这个函数如下:
/*******************************
//GB转UTF-8编码
*******************************/
function gb2utf8($gbstr) {
global $CODETABLE;
if(trim($gbstr)=="") return $gbstr;
if(empty($CODETABLE)){
$filename = dirname(__FILE__)."/gb2312-utf8.table";
$fp = fopen($filename,"r");
while ($l = fgets($fp,15))
{ $CODETABLE[hexdec(substr($l, 0, 6))] = substr($l, 7, 6); }
fclose($fp);
}
$ret = "";
$utf8 = "";
while ($gbstr) {
if (ord(substr($gbstr, 0, 1)) > 127) {
$thisW = substr($gbstr, 0, 2);
$gbstr = substr($gbstr, 2, strlen($gbstr));
$utf8 = "";
@$utf8 = u2utf8(hexdec($CODETABLE[hexdec(bin2hex($thisW)) - 0x8080]));
if($utf8!=""){
for ($i = 0;$i
$ret .= chr(substr($utf8, $i, 3));
}
}
else
{
$ret .= substr($gbstr, 0, 1);
$gbstr = substr($gbstr, 1, strlen($gbstr));
}
}
return $ret;
}
//Unicode转utf8
function u2utf8($c) {
for ($i = 0;$i
$str = "";
if ($c
$str .= $c;
} else if ($c
$str .= (0xC0 | $c >> 6);
$str .= (0x80 | $c & 0x3F);
} else if ($c
$str .= (0xE0 | $c >> 12);
$str .= (0x80 | $c >> 6 & 0x3F);
$str .= (0x80 | $c & 0x3F);
} else if ($c
$str .= (0xF0 | $c >> 18);
$str .= (0x80 | $c >> 12 & 0x3F);
$str .= (0x80 | $c >> 6 & 0x3F);
$str .= (0x80 | $c & 0x3F);
}