当前位置:网络资源中心文章中心网络编程PHP教程 → 文章内容

用php实现gb2312和unicode间的编码转换 (1)

减小字体 增大字体 作者:Qesy  来源:0423tv.com  发布时间:2008-5-16 9:07:53

gb2312 和 unicode 间的编码转换

下面的例子是将 gb2312 转换为 "%26amp;#20840;"这种形式

php4.3.1以后的iconv函数很好用的,只是需要自己写一个uft8到unicode的转换函数
查表(gb2312.txt)也行
%26lt;?
$text = "电子书库";
preg_match_all("/[\x80-\xff]?./",$text,$ar);
foreach($ar[0] as $v)
echo "%26amp;#".utf8_unicode(iconv("GB2312","UTF-8",$v)).";";
?%26gt;
%26lt;?
// utf8 -%26gt; unicode
function utf8_unicode($c) {
switch(strlen($c)) {
case 1:
return ord($c);
case 2:
$n = (ord($c[0]) %26amp; 0x3f) %26lt;%26lt; 6;
$n += ord($c[1]) %26amp; 0x3f;
return $n;
case 3:
$n = (ord($c[0]) %26amp; 0x1f) %26lt;%26lt; 12;
$n += (ord($c[1]) %26amp; 0x3f) %26lt;%26lt; 6;
$n += ord($c[2]) %26amp; 0x3f;
return $n;
case 4:
$n = (ord($c[0]) %26amp; 0x0f) %26lt;%26lt; 18;
$n += (ord($c[1]) %26amp; 0x3f) %26lt;%26lt; 12;
$n += (ord($c[2]) %26amp; 0x3f) %26lt;%26lt; 6;
$n += ord($c[3]) %26amp; 0x3f;
return $n;
}
}
?%26gt;


下面的例子是利用php将"%26amp;#20840;"这中编码转换为gb2312.
%26lt;?php
$str = "TTL%26amp;#20840;%26amp;#22825;%26amp;#20505;%26amp;#33258;%26amp;#21160;%26amp;#32858;%26amp;#28966;";
$str = preg_replace("|%26amp;#([0-9]{1,5});|", "\".u2utf82gb(\\1).\"", $str);
$str = "\$str=\"$str\";";

eval($str);
echo $str;

function u2utf82gb($c){
$str="";
if ($c %26lt; 0x80) {
$str.=$c;
} else if ($c %26lt; 0x800) {
$str.=chr(0xC0 | $c%26gt;%26gt;6);
$str.=chr(0x80 | $c %26amp; 0x3F);
} else if ($c %26lt; 0x10000) {
$str.=chr(0xE0 | $c%26gt;%26gt;12);
$str.=chr(0x80 | $c%26gt;%26gt;6 %26amp; 0x3F);
$str.=chr(0x80 | $c %26amp; 0x3F);
} else if ($c %26lt; 0x200000) {
$str.=chr(0xF0 | $c%26gt;%26gt;18);
$str.=chr(0x80 | $c%26gt;%26gt;12 %26amp; 0x3F);
$str.=chr(0x80 | $c%26gt;%26gt;6 %26amp; 0x3F);
$str.=chr(0x80 | $c %26amp; 0x3F);
}
return iconv('UTF-8', 'GB2312', $str);
}
?%26gt;

或者是

function unescape($str) {
$str = rawurldecode($str);
preg_match_all("/(?:%u.{4})|%26amp;#x.{4};|%26amp;#\d+;|.+/U",$str,$r);
$ar = $r[0];
print_r($ar);
foreach($ar as $k=%26gt;$v) {
if(substr($v,0,2) == "%u")
$ar[$k] = iconv("UCS-2","GB2312",pack("H4",substr($v,-4)));
elseif(substr($v,0,3) == "%26amp;#x")
$ar[$k] = iconv("UCS-2","GB2312",pack("H4",substr($v,3,-1)));
elseif(substr($v,0,2) == "%26amp;#") {
echo substr($v,2,-1)."%26lt;br%26gt;";
$ar[$k] = iconv("UCS-2","GB2312",pack("n",substr($v,2,-1)));
}
}
return join("",$ar);
}

$str = "TTL%26amp;#20840;%26amp;#22825;%26amp;#20505;%26amp;#33258;%26amp;#21160;%26amp;#32858;%26amp;#28966;";
echo unescape($str); //out TTL全天候自动聚焦

利用javascript来转换

%26lt;style%26gt;
BODY {
FONT-SIZE: 9pt; PADDING-RIGHT: 0px; PADDING-LEFT: 0px; PADDING-BOTTOM: 0px; PADDING-TOP: 0px;
}
input {
FONT-SIZE: 9pt; height: 13pt;
}
%26lt;/style%26gt;

%26lt;script language="JavaScript1.2"%26gt;
/*
This following code are designed and writen by Windy_sk %26lt;seasonx@163.net%26gt;
You can use it freely, but u must held all the copyright items!
*/

function Str2Unicode(str){
var arr = new Array();
for(var i=0;i%26lt;str.length;i++){
arr[i]="%26amp;#" + str.charCodeAt(i) + ";";
}
return(arr.toString().replace(/,/g,""));
}

function Unicode2oStr(str){
var re=/%26amp;#[\da-fA-F]{1,5};/ig;
var arr=str.match(re);
if(arr==null)return("");
for(var i=0;i%26lt;arr.length;i++){
arr[i]=String.fromCharCode(arr[i].replace(/[%26amp;#;]/g,""));
}
return(arr.toString().replace(/,/g,""))
}

function modi_str(){
if(document.all.text.method.checked){
if(document.all.text.decode.value!=""){
document.all.text.encode.value = Str2Unicode(document.all.text.decode.value);
}else{
document.all.text.decode.value = Unicode2oStr(document.all.text.encode.value);
}
}else{
if(document.all.text.encode.value!=""){
document.all.text.decode.value = Unicode2oStr(document.all.text.encode.value);
}else{
document.all.text.encode.value = Str2Unicode(document.all.text.decode.value);
}
}
}
%26lt;/script%26gt;
%26lt;title%26gt;Unicode%26lt;/title%26gt;
%26lt;form name=text%26gt;
文本原型%26lt;br%26gt;
%26lt;textarea name="decode" cols="100" rows="10"%26gt;%26lt;/textarea%26gt;
%26lt;br%26gt;
转换代码%26lt;br%26gt;
%26lt;textarea name="encode" cols="100" rows="10"%26gt;%26lt;/textarea%26gt;
%26lt;br%26gt;
%26lt;input type="checkbox" name="method" checked%26gt; 正向转换
%26lt;input type=button value=" 确 定 "%26gt;
%26lt;input type=reset value=" 清 空 "%26gt;
%26lt;input type=button value=" 全 选 "%26gt;
%26lt;/form%26gt;


下面是一个显示所有全角半角的字体的查看例子

%26lt;style%26gt;
BODY {
FONT-SIZE: 9pt; PADDING-RIGHT: 0px; PADDING-LEFT: 0px; PADDING-BOTTOM: 0px; PADDING-TOP: 0px;
}
input {
FONT-SIZE: 9pt; height: 13pt;
}
%26lt;/style%26gt;
%26lt;script%26gt;
function showUni(min,max){
show.document.open();
show.document.writeln("%26lt;style%26gt;body{font-size:9pt;word-break:break-all;}%26lt;/style%26gt;");
show.document.writeln(min + " - " + max + "%26lt;br%26gt;%26lt;br%26gt;");
var i=0;
for(i=min;i%26lt;=max;i++){
show.document.write("%26amp;#" + i + ";");
}
show.document.close();
}
%26lt;/script%26gt;
%26lt;input type=button value="半角" onclick=showUni(32,126)%26gt;
%26lt;input type=button value="全角" onclick=showUni(65281,65374)%26gt;
%26lt;input type=button value="中文1" onclick=showUni(19968,40869)%26gt;
%26lt;input type=button value="中文2" onclick=showUni(63744,64045)%26gt;
%26lt;input type=button value="日文平" onclick=showUni(12353,12435)%26gt;
%26lt;input type=button value="日文片" onclick=showUni(12449,12534)%26gt;
%26lt;input type=button value="韩文" onclick=showUni(44032,55203)%26gt;
%26lt;br%26gt;自定义%26lt;input name=min%26gt; - %26lt;input name=max%26gt;
%26lt;input type=button value="察看" onclick=showUni(parseInt(document.all.min.value),parseInt(document.all.max.value))%26gt;
%26lt;br%26gt;
%26lt;iframe src="about:blank" id=show width=100% height=70% scroll=no%26gt;%26lt;/iframe%26gt;


下面是一个查表(gb2312),转换gb2312到utf8的例子, 现在有iconv函数,这个已经没有太大的意义了,

%26lt;?
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))%26gt;127) {
$this=substr($gb,0,2);
$gb=substr($gb,2,strlen($gb)-2);
$utf8.=u2utf8(hexdec($codetable[hexdec(bin2hex($this))-0x8080]));
}else{
$this=substr($gb,0,1);
$gb=substr($gb,1,strlen($gb)-1);
$utf8.=u2utf8($this);
}
}
return $utf8;
}

function u2utf8($c){
$str="";
if ($c %26lt; 0x80) {
$str.=$c;
} else if ($c %26lt; 0x800) {
$str.=chr(0xC0 | $c%26gt;%26gt;6);
$str.=chr(0x80 | $c %26amp; 0x3F);
} else if ($c %26lt; 0x10000) {
$str.=chr(0xE0 | $c%26gt;%26gt;12);
$str.=chr(0x80 | $c%26gt;%26gt;6 %26amp; 0x3F);
$str.=chr(0x80 | $c %26amp; 0x3F);
} else if ($c %26lt; 0x200000) {
$str.=chr(0xF0 | $c%26gt;%26gt;18);
$str.=chr(0x80 | $c%26gt;%26gt;12 %26amp; 0x3F);
$str.=chr(0x80 | $c%26gt;%26gt;6 %26amp; 0x3F);
$str.=chr(0x80 | $c %26amp; 0x3F);
}
return $str;
}

?%26gt;