gb2312 -> UTF-8 的函数

[Tony]

以下是一段gb2312 -> UTF-8 的函数，西西，我抄了
unicode -> UTF-8 的算法，所以实际比GB2312->unicode
没多多少东西,请大家注意调用gb2utf8()时不能中英文混用



程序需要的GB2312.txt文件

gb2utf8.php
<?

//Program writen by sadly www.phpx.com

function gb2utf8($gb)
{
if(!trim($gb))
return $gb;
$filename="gb2312.txt";
$tmp=file($filename);
$codetable=array();
while(list($key,$value)=each($tmp))
$codetable[hexdec(substr($value,0,6))]=substr($value,7,6);

$utf8="";
while($gb)
{
if (ord(substr($gb,0,1))>127)
{
$this=substr($gb,0,2);
$gb=substr($gb,2,strlen($gb));
$utf8.=u2utf8(hexdec($codetable[hexdec(bin2hex($this))-0x8080]));
}
else
{
$gb=substr($gb,1,strlen($gb));
$utf8.=u2utf8(substr($gb,0,1));
}
}

$ret="";
for($i=0;$i<strlen($utf8);$i+=3)
$ret.=chr(substr($utf8,$i,3));

return $ret;
}

function u2utf8($c)
{
for($i=0;$i<count($c);$i++)
$str="";
if ($c < 0x80) {
$str.=$c;
}
else if ($c < 0x800) {
$str.=(0xC0 | $c>>6);
$str.=(0x80 | $c & 0x3F);
}
else if ($c < 0x10000) {
$str.=(0xE0 | $c>>12);
$str.=(0x80 | $c>>6 & 0x3F);
$str.=(0x80 | $c & 0x3F);
}
else if ($c < 0x200000) {
$str.=(0xF0 | $c>>18);
$str.=(0x80 | $c>>12 & 0x3F);
$str.=(0x80 | $c>>6 & 0x3F);
$str.=(0x80 | $c & 0x3F);
}
return $str;
}
?>



调用举例:通过GD输出 "中国" 两个汉字
example.php

<?
//Header("Content-type: image/gif");
$im = imagecreate(400,300);
$bkg = ImageColorAllocate($im, 0,0,0);
$clr = ImageColorAllocate($im, 255,255,255);
$fnt = "d:/winnt/fonts/simhei.ttf";
include("gb2utf8.php");
$str = gb2utf8("中国");
ImageTTFText($im, 20, 0, 10, 20, $clr, $fnt, $str);
ImageGif($im);
ImageDestroy($im);
?>