首页 > 代码库 > php汉字转Unicode编码函数

php汉字转Unicode编码函数

/**
 * $str 原始字符串
 * $encoding 原始字符串的编码,默认GBK
 * $prefix 编码后的前缀,默认"&#"
 * $postfix 编码后的后缀,默认";"
 */
function unicode_encode($str, $encoding = ‘GBK‘, $prefix = ‘&#‘, $postfix = ‘;‘) {
    $str = iconv($encoding, ‘UCS-2‘, $str);
    $arrstr = str_split($str, 2);
    $unistr = ‘‘;
    for($i = 0, $len = count($arrstr); $i < $len; $i++) {
        $dec = hexdec(bin2hex($arrstr[$i]));
        $unistr .= $prefix . $dec . $postfix;
    } 
    return $unistr;
} 
?
/**
 * $str Unicode编码后的字符串
 * $encoding 原始字符串的编码,默认GBK
 * $prefix 编码字符串的前缀,默认"&#"
 * $postfix 编码字符串的后缀,默认";"
 */
function unicode_decode($unistr, $encoding = ‘GBK‘, $prefix = ‘&#‘, $postfix = ‘;‘) {
    $arruni = explode($prefix, $unistr);
    $unistr = ‘‘;
    for($i = 1, $len = count($arruni); $i < $len; $i++) {
        if (strlen($postfix) > 0) {
            $arruni[$i] = substr($arruni[$i], 0, strlen($arruni[$i]) - strlen($postfix));
        } 
        $temp = intval($arruni[$i]);
        $unistr .= ($temp < 256) ? chr(0) . chr($temp) : chr($temp / 256) . chr($temp % 256);
    } 
    return iconv(‘UCS-2‘, $encoding, $unistr);
}

使用:
//GBK字符串测试
$str = ‘<b>哈哈</b>‘;
echo $str.‘<br />‘;
?
$unistr = unicode_encode($str);
echo $unistr.‘<br />‘; // &#60;&#98;&#62;&#21704;&#21704;&#60;&#47;&#98;&#62;
?
$str2 = unicode_decode($unistr);
echo $str2.‘<br />‘; //<b>哈哈</b>
?
//UTF-8字符串测试
$utf8_str = iconv(‘GBK‘, ‘UTF-8‘, $str);
echo $utf8_str.‘<br />‘; // <b>鍝堝搱</b> 注:UTF在GBK下显示的乱码!可切换浏览器的编码测试
?
$utf8_unistr = unicode_encode($utf8_str, ‘UTF-8‘);
echo $utf8_unistr.‘<br />‘; // &#60;&#98;&#62;&#21704;&#21704;&#60;&#47;&#98;&#62;
?
$utf8_str2 = unicode_decode($utf8_unistr, ‘UTF-8‘);
echo $utf8_str2.‘<br />‘; // <b>鍝堝搱</b>
?
//其它后缀、前缀测试
$prefix_unistr = unicode_encode($str, ‘GBK‘, "\\u", ‘‘);
echo $prefix_unistr.‘<br />‘; // \u60\u98\u62\u21704\u21704\u60\u47\u98\u62
?
$profix_unistr2 = unicode_decode($prefix_unistr, ‘GBK‘, "\\u", ‘‘);
echo $profix_unistr2.‘<br />‘; //<b>哈哈</b>