UNICODE的一些處理方式

/* 將 文字 轉換成 '12345' 或 '〹' */

// 使用 iconv
$unicode = base_convert(bin2hex(iconv('UTF-8', 'UCS-4', $string)), 16, 10);

// 使用 mb_convert_encoding
$unicode = base_convert(bin2hex(mb_convert_encoding($string, 'ucs-4', 'utf-8')), 16, 10);

// 補上 &#xxxxx;
$unicode = '&#' . base_convert(bin2hex(iconv("utf-8", "ucs-4", $str)), 16, 10) . ';'; 

// 將 &#12345 轉回 文字
$string = mb_convert_encoding($unicode, 'UTF-8', 'HTML-ENTITIES'); 

$str = "温"; $unicodeHtml = base_convert(bin2hex(iconv("utf-8", "ucs-2", $str)), 16, 10); print "&#".$unicodeHTML.";" // 顯示結果 温

unicode html 轉回文字，由於 php 沒有 hex2bin 的函式，所以我們自己簡單的寫一個來用。

<?php function hex2bin($string) {     $len = strlen($string);     retunr pack("H".$len, $string); } $str = "28201"; $unicodeHtml = iconv("ucs-2", "utf-8", hex2bin(base_convert($str, 10, 16))); print $unicodeHtml; // 顯示結果 温

?>

線上轉換網站

http://konieczny.be/unicode.html

/////////////////////////////////////////////////////////////////////////

//

// UTF-8轉換為UNICODE

//

//

/////////////////////////////////////////////////////////////////////////

function numeric_code_utf8($utf8_string) { 

$out = ""; 

$ns = strlen ($utf8_string); 

for ($nn = 0; $nn < $ns; $nn++) { 

$ch = $utf8_string[$nn]; 

$ii = ord ($ch); 

if ($ii < 128) 

        $out .= $ch; 

else if ($ii >>5 == 6) { 

$b1 = ($ii & 31); 

$nn++; 

$ch = $utf8_string [$nn]; 

$ii = ord ($ch); 

$b2 = ($ii & 63); 

$ii = ($b1 * 64) + $b2; 

$ent = sprintf ("&#%d;", $ii); 

$out .= $ent; 

} 

else if ($ii >>4 == 14) { 

$b1 = ($ii & 31); 

$nn++; 

$ch = $utf8_string [$nn]; 

$ii = ord ($ch); 

$b2 = ($ii & 63); 

$nn++; 

$ch = $utf8_string [$nn]; 

$ii = ord ($ch); 

$b3 = ($ii & 63); 

$ii = ((($b1 * 64) + $b2) * 64) + $b3; 

$ent = sprintf ("&#%d;", $ii); 

$out .= $ent; 

} 

else if ($ii >>3 == 30) { 

$b1 = ($ii & 31); 

$nn++; 

$ch = $utf8_string [$nn]; 

$ii = ord ($ch); 

$b2 = ($ii & 63); 

$nn++; 

$ch = $utf8_string [$nn]; 

$ii = ord ($ch); 

$b3 = ($ii & 63); 

$nn++; 

$ch = $utf8_string [$nn]; 

$ii = ord ($ch); 

$b4 = ($ii & 63); 

$ii = ((((($b1 * 64) + $b2) * 64) + $b3) * 64) + $b4; 

$ent = sprintf ("&#%d;", $ii); 

$out .= $ent; 

} 

} 

return $out; 

}

function BIG5_string($name){

 //判別中文是否能轉換為BIG5碼，若不行則以unicode&#XXXX顯示

 

$tname=@iconv("utf-8","big5",$name);

if( mb_strlen($name,"utf-8")  <>  mb_strlen($tname,"big5")  )

{

$per_name_big5="";

for($ai=0;$ai < mb_strlen($name,"UTF-8");$ai++)

{

$str_tmp=mb_substr($name,$ai,1,"UTF-8");

$str_tmp_big5=@iconv("utf-8","big5",$str_tmp);

if( mb_strlen($str_tmp_big5,"big5") ==0 )

{

echo "$str_tmp <br>";

$per_name_big5 .=  "&#".base_convert(bin2hex(iconv("utf-8", "ucs-2", $str_tmp)), 16, 10);

}

else $per_name_big5 .=$str_tmp_big5;    

}

}else $per_name_big5=$name;

  return $per_name_big5;

}