//将内容进行unicode编码,编码后的内容格式:yoka\u738b (原始:yoka王) - function unicode_encode($name)
- {
- $name = iconv('utf-8', 'ucs-2', $name);
- $len = strlen($name);
- $str = '';
- for ($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 $str;
- } // (脚本学堂 bbs.it-home.org 编辑整理)
// 将unicode编码后的内容进行解码,编码后的内容格式:yoka\u738b (原始:yoka王) - function unicode_decode($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;
- }
测试:
- echo '
yoka\u738b -> '.unicode_decode('yoka\u738b').''; - $name = 'yoka王';
- echo '
'.unicode_encode($name).'';
注意:新浪博客的编辑器把/ ** * /全都给过滤了 |