怎么用PHP把unicode转成utf8

unicode的字符串在浏览器里可以正常显示，但是如果把它放到<input type="text" />里就会变的不知所云了

所以需要在有些时候将unicode转成编码前的状态如UTF8，下面是根据Unicode/Utf8编码区别写的一段程序。

目的将:

&#12527&#12531&#12524&#12505&#12523&#12450&#12489&#12524&#12473&#44&#49&#12524&#12505&#12523&#12450&#12489&#12524&#12473

转成:

ワンレベルアドレス,1レベルアドレス

 

代码：

<?php

// arg: the integer value of one unicode char
function unicode2utf8($unicode_c)
{
 $unicode_c_val = intval($unicode_c);
 $f=0x80; // 10000000
 $str = "";
 // U-00000000 - U-0000007F:   0xxxxxxx
 if($unicode_c_val <= 0x7F)
 {
  $str = chr($unicode_c_val);
 }
 //U-00000080 - U-000007FF:  110xxxxx 10xxxxxx
 else if($unicode_c_val >= 0x80 && $unicode_c_val <= 0x7FF)
 {
  $h=0xC0; // 11000000
  $c1 = $unicode_c_val >> 6 | $h;
  $c2 = ($unicode_c_val & 0x3F) | $f;
  $str = chr($c1).chr($c2);
 }
 //U-00000800 - U-0000FFFF:  1110xxxx 10xxxxxx 10xxxxxx
 else if($unicode_c_val >= 0x800 && $unicode_c_val <= 0xFFFF)
 {
  $h=0xE0; // 11100000
  $c1 = $unicode_c_val >> 12 | $h;
  $c2 = (($unicode_c_val & 0xFC0) >> 6) | $f;
  $c3 = ($unicode_c_val & 0x3F) | $f;
  $str=chr($c1).chr($c2).chr($c3);  
 }
 //U-00010000 - U-001FFFFF:  11110xxx 10xxxxxx 10xxxxxx 10xxxxxx
 else if($unicode_c_val >= 0x10000 && $unicode_c_val <= 0x1FFFFF)
 {
  $h=0xF0; // 11110000
  $c1 = $unicode_c_val >> 18 | $h;
  $c2 = (($unicode_c_val & 0x3F000) >>12) | $f;
  $c3 = (($unicode_c_val & 0xFC0) >>6) | $f;
  $c4 = ($unicode_c_val & 0x3F) | $f;
  $str = chr($c1).chr($c2).chr($c3).chr($c4);
 }
 //U-00200000 - U-03FFFFFF:  111110xx 10xxxxxx 10xxxxxx 10xxxxxx 10xxxxxx
 else if($unicode_c_val >= 0x200000 && $unicode_c_val <= 0x3FFFFFF)
 {
  $h=0xF8; // 11111000
  $c1 = $unicode_c_val >> 24 | $h;
  $c2 = (($unicode_c_val & 0xFC0000)>>18) | $f;
  $c3 = (($unicode_c_val & 0x3F000) >>12) | $f;
  $c4 = (($unicode_c_val & 0xFC0) >>6) | $f;
  $c5 = ($unicode_c_val & 0x3F) | $f;
  $str = chr($c1).chr($c2).chr($c3).chr($c4).chr($c5);
 }
 //U-04000000 - U-7FFFFFFF:  1111110x 10xxxxxx 10xxxxxx 10xxxxxx 10xxxxxx 10xxxxxx
 else if($unicode_c_val >= 0x4000000 && $unicode_c_val <= 0x7FFFFFFF)
 {
  $h=0xFC; // 11111100
  $c1 = $unicode_c_val >> 30 | $h;
  $c2 = (($unicode_c_val & 0x3F000000)>>24) | $f;
  $c3 = (($unicode_c_val & 0xFC0000)>>18) | $f;
  $c4 = (($unicode_c_val & 0x3F000) >>12) | $f;
  $c5 = (($unicode_c_val & 0xFC0) >>6) | $f;
  $c6 = ($unicode_c_val & 0x3F) | $f;
  $str = chr($c1).chr($c2).chr($c3).chr($c4).chr($c5).chr($c6);
 }
 
 return $str;
}
 
$str = "&#12527&#12531&#12524&#12505&#12523&#12450&#12489&#12524&#12473&#44&#49&#12524&#12505&#12523&#12450&#12489&#12524&#12473";
$intArr = explode("&#", $str);

$retr = "";
foreach($intArr as $cval)
{
 if(!empty($cval))
 {
  $retr .= unicode2utf8($cval);
 }
}

echo $retr;

?>