分享PHP UTF-8和Unicode编码互转(多语言)
2015年9月27日星期日 | | |PHP UTF-8和Unicode编码互转
/** * //将内容进行UNICODE编码 * utf-8 转unicode * * @param string $name * @return string */ function utf8_unicode($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).str_pad(base_convert(ord($c2), 10, 16), 2, 0, STR_PAD_LEFT); //$str .= base_convert(ord($c), 10, 16).str_pad(base_convert(ord($c2), 10, 16), 2, 0, STR_PAD_LEFT); } else { $str .= '\u'.str_pad(base_convert(ord($c2), 10, 16), 4, 0, STR_PAD_LEFT); //$str .= str_pad(base_convert(ord($c2), 10, 16), 4, 0, STR_PAD_LEFT); } } $str = strtoupper($str);//转换为大写 return $str; } /** * unicode 转 utf-8 * * @param string $name * @return string */ function unicode_decodessss($name) { $name = strtolower($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; }
调用及结果:
$utf8_str = '我'; //这是汉字"你"的Unicode编码 $unicode_str = '\u4f60'; //输出 6211 echo utf8_unicode($utf8_str) . "<br/>"; //输出汉字"你" echo unicode_decodes($unicode_str);
\U6211<br/> 你