在JS中一般将汉字编码成为unicode进行输出,这样可以避免一些中文的问题。PHP中如何处理unicode,这里转一个文章给大家。
UNICODE编码在PHP中使用UCS-2编码,之前还真是没有发现,一直还以为是UTF-8就行了。贴出代码:
function unicode_encode($name){
$name = iconv('UTF-8', 'UCS-2', $name);
$len = strlen($name);
$str = '';
//for ($i = 0; $i < $len – 1; $i = $i + 2){
for($i=0;$i<$len-1;$i=$i+2){
$c = $name[$i];
$c2 = $name[$i + 1];
if (ord($c) > 0){ // 两个字节的文字
$str .= '\u'.base_convert(ord($c), 10, 16).base_convert(ord($c2), 10, 16);
}else{
$str .= $c2;
}
}
return $str;
}
function unicode_decode($name){
// 转换编码,将Unicode编码转换成可以浏览的utf-8编码
$pattern = '/([\w]+)|(\\\u([\w]{4}))/i';
preg_match_all($pattern, $name, $matches);
if (!empty($matches)){
$name = '';
for ($j = 0; $j < count($matches[0]); $j++){
$str = $matches[0][$j];
if (strpos($str, '\\u') === 0){
$code = base_convert(substr($str, 2, 2), 16, 10);
$code2 = base_convert(substr($str, 4), 16, 10);
$c = chr($code).chr($code2);
$c = iconv('UCS-2', 'UTF-8', $c);
$name .= $c;
}else{
$name .= $str;
}
}
}
return $name;
}
$name='我的地盘';
$names='\u6211\u7684\u5730\u76d8';
//echo unicode_encode($name);
echo unicode_decode($names);