转换unicode十进制内码为utf-8编码

转换unicode十进制内码为utf-8编码

 

function u2utf8($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 $str;
}

$source = "&#20013&#22269&#20154&#27665";

preg_match_all("/&#([0-9]+)/", $source, $regs);

foreach ($regs[1] as $v) {
    $source = str_replace("&#$v", u2utf8($v), $source);
}

echo $source;
// 中国人民 //