php删除不可见的Unicode字符 \u200e php字符串转Unicode编码, Unicode编码转php字符

发布时间:2019-09-26 23:39:47编辑:丝画阁阅读(179)

php字符串转Unicode编码, Unicode编码转php字符

百度了很多,都一样, 要么不对, 要不就是只是把字符串的汉字转Unicode

经过多次试验查找, 找到了如下方法,

注意:字符串编码必须是utf-8,如果不是自行用icon转一下
复制代码

//字符串转Unicode编码
function unicode_encode($strLong) {
$strArr = preg_split('/(? $resUnicode = '';
foreach ($strArr as $str)
{
$bin_str = '';
$arr = is_array($str) ? $str : str_split($str);//获取字符内部数组表示,此时$arr应类似array(228, 189, 160)
foreach ($arr as $value)
{
$bin_str .= decbin(ord($value));//转成数字再转成二进制字符串,$bin_str应类似111001001011110110100000,如果是汉字"你"
}
$bin_str = preg_replace('/^.{4}(.{4}).{2}(.{6}).{2}(.{6})$/', '$1$2$3', $bin_str);//正则截取, $bin_str应类似0100111101100000,如果是汉字"你"
$unicode = dechex(bindec($bin_str));//返回unicode十六进制
$_sup = '';
for ($i = 0; $i < 4 - strlen($unicode); $i++)
{
$_sup .= '0';//补位高字节 0
}
$str =  '\\u' . $_sup . $unicode; //加上 \u  返回
$resUnicode .= $str;
}
return $resUnicode;
}
//Unicode编码转字符串方法1
function unicode_decode($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 $name;
}
//Unicode编码转字符串
function unicode_decode2($str){
$json = '{"str":"' . $str . '"}';
$arr = json_decode($json, true);
if (empty($arr)) return '';
return $arr['str'];
}


echo unicode_encode('xx丫:qq1263667812'),'
';
//结果\u82e5\u6c34\u5c0f\u7ad9\u003a\u0071\u0071\u0039\u0036\u0033\u0030\u0038\u0037\u0033\u0032\u0036

echo unicode_decode('\u82e5\u6c34\u5c0f\u7ad9\u003a\u0071\u0071\u0039\u0036\u0033\u0030\u0038\u0037\u0033\u0032\u0036');

//结果xx丫:qq1263667812



关键字