用php实现gb2312和unicode(UTF-8)间的编码转换_[PHP教程]

下面的例子是将 gb2312 转换为 uft-8 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

text = "电子书库";
preg_match_all("/[\x80-\xff]?./",text,ar);
foreach(ar[0] as v)
echo "&#".utf8_unicode(iconv("GB2312","UTF-8",v)).";";
?>
// utf8 -> unicode
function utf8_unicode(c) {
switch(strlen(c)) {
case 1:
return ord(c);
case 2:
n = (ord(c[0]) & 0x3f) << 6;
n += ord(c[1]) & 0x3f;
return n;
case 3:
n = (ord(c[0]) & 0x1f) << 12;
n += (ord(c[1]) & 0x3f) << 6;
n += ord(c[2]) & 0x3f;
return n;
case 4:
n = (ord(c[0]) & 0x0f) << 18;
n += (ord(c[1]) & 0x3f) << 12;
n += (ord(c[2]) & 0x3f) << 6;
n += ord(c[3]) & 0x3f;
return n;
}
}
?>

下面的例子是利用php将uft-8这中编码转换为gb2312.

str = "TTL&#20840;&#22825;&#20505;&#33258;&#21160;&#32858;&#28966;";
str = preg_replace("|&#([0-9]{1,5});|", "\".u2utf82gb(\\1).\"", str);
str = "\str=\"str\";";
eval(str);
echo str;
function u2utf82gb(c){
str="";
if (c < 0x80) {
str.=c;
} else if (c < 0x800) {
str.=chr(0xC0 | c>>6);
str.=chr(0x80 | c & 0x3F);
} else if (c < 0x10000) {
str.=chr(0xE0 | c>>12);
str.=chr(0x80 | c>>6 & 0x3F);
str.=chr(0x80 | c & 0x3F);
} else if (c < 0x200000) {
str.=chr(0xF0 | c>>18);
str.=chr(0x80 | c>>12 & 0x3F);
str.=chr(0x80 | c>>6 & 0x3F);
str.=chr(0x80 | c & 0x3F);
}
return iconv('UTF-8', 'GB2312', str);
}
?>

或者是

function unescape(str) {
str = rawurldecode(str);
preg_match_all("/(?:%u.{4})|&#x.{4};|&#\d+;|.+/U",str,r);
ar = r[0];
print_r(ar);
foreach(ar as k=>v) {
if(substr(v,0,2) == "%u")
ar[k] = iconv("UCS-2","GB2312",pack("H4",substr(v,-4)));
elseif(substr(v,0,3) == "&#x")
ar[k] = iconv("UCS-2","GB2312",pack("H4",substr(v,3,-1)));
elseif(substr(v,0,2) == "&#") {
echo substr(v,2,-1)."
";
ar[k] = iconv("UCS-2","GB2312",pack("n",substr(v,2,-1)));
}
}
return join("",ar);
}
str = "TTL&#20840;&#22825;&#20505;&#33258;&#21160;&#32858;&#28966;";
echo unescape(str); file://out TTL全天候自动聚焦

利用javascript来转换

文本原型：




转换代码：




正向转换
onclick="modi_str()" value=" 确 定 ">

onclick="document.all.text.method.checked?document.all.text.encode.select():document.all.text.decode.select()" value=" 全 选 ">

下面是一个显示所有全角半角的字体的查看例子

onclick=showUni(32,126)>
onclick=showUni(65281,65374)>
onclick=showUni(19968,40869)>
onclick=showUni(63744,64045)>
onclick=showUni(12353,12435)>
onclick=showUni(12449,12534)>
onclick=showUni(44032,55203)>

自定义： -
onclick=showUni(parseInt(document.all.min.value),parseInt(document.all.max.value))>

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,

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)-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 < 0x80) {
str.=c;
} else if (c < 0x800) {
str.=chr(0xC0 | c>>6);
str.=chr(0x80 | c & 0x3F);
} else if (c < 0x10000) {
str.=chr(0xE0 | c>>12);
str.=chr(0x80 | c>>6 & 0x3F);
str.=chr(0x80 | c & 0x3F);
} else if (c < 0x200000) {
str.=chr(0xF0 | c>>18);
str.=chr(0x80 | c>>12 & 0x3F);
str.=chr(0x80 | c>>6 & 0x3F);
str.=chr(0x80 | c & 0x3F);
}
return str;
}
?>