|
|
| 用php实现gb2312和unicode间的编码转换(1) |
| 作者:不详 来源:不详 发布时间:2006-8-14 10:18:29 发布人:chinazhan |
减小字体
增大字体
gb2312 和 unicode 间的编码转换 下面的例子是将 gb2312 转换为 "全"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"全"这中编码转换为gb2312. <?php $str = "TTL全天候自动聚焦"; $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})|.{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) == "") $ar[$k] = iconv("UCS-2","GB2312",pack("H4",substr($v,3,-1))); elseif(substr($v,0,2) == "") { echo substr($v,2,-1)."<br>"; $ar[$k] = iconv("UCS-2","GB2312",pack("n",substr($v,2,-1))); } } return join("",$ar); } $str = "TTL全天候自动聚焦"; echo unescape($str); //out TTL全天候自动聚焦 利用javascript来转换 <style> BODY { FONT-SIZE: 9pt; PADDING-RIGHT: 0px; PADDING-LEFT: 0px; PADDING-BOTTOM: 0px; PADDING-TOP: 0px; } input { FONT-SIZE: 9pt; height: 13pt; } </style> <script language="JavaScript1.2"> /* This following code are designed and writen by Windy_sk <seasonx@163.net> 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<str.length;i++){ arr[i]="" + str.charCodeAt(i) + ";"; } return(arr.toString().replace(/,/g,"")); } function Unicode2oStr(str){ var re=/[\da-fA-F]{1,5};/ig; var arr=str.match(re); if(arr==null)return(""); for(var i=0;i<arr.length;i++){ arr[i]=String.fromCharCode(arr[i].replace(/[]/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); } } } </script> <title>Unicode</title> <form name=text> 文本原型:<br> <textarea name="decode" cols="100" rows="10"></textarea> <br> 转换代码:<br> <textarea name="encode" cols="100" rows="10"></textarea> <br> <input type="checkbox" name="method" checked> 正向转换 <input type=button onclick="modi_str()" value=" 确 定 "> <input type=reset value=" 清 空 "> <input type=button onclick="document.all.text.method.checked?document.all.text.encode.select():document.all.text.decode.select()" value=" 全 选 "> </form> 做人要厚道,请注明转自chinazhan中国站长(www.ChinaZhan.com)。
|
| |
|
[]
[返回上一页]
[打 印]
[收 藏] |
|
| ∷相关文章评论∷ (评论内容只代表网友观点,与本站立场无关!) [更多评论...] |
|
|