国产探花免费观看_亚洲丰满少妇自慰呻吟_97日韩有码在线_资源在线日韩欧美_一区二区精品毛片,辰东完美世界有声小说,欢乐颂第一季,yy玄幻小说排行榜完本

首頁 > 開發(fā) > PHP > 正文

用php實(shí)現(xiàn)gb2312和unicode(UTF-8)間的編碼轉(zhuǎn)換

2024-05-04 23:04:03
字體:
供稿:網(wǎng)友

下面的例子是將 gb2312 轉(zhuǎn)換為 uft-8 這種形式
php4.3.1以后的iconv函數(shù)很好用的,只是需要自己寫一個(gè)uft8到unicode的轉(zhuǎn)換函數(shù)
查表(gb2312.txt)也行

<?
$text = "電子書庫";
preg_match_all("/[/x80-/xff]?./",$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將uft-8這中編碼轉(zhuǎn)換為gb2312.

<?php
$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)."<br>";
      $ar[$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全天候自動(dòng)聚焦


利用javascript來轉(zhuǎn)換

<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 <[email protected]>
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>
轉(zhuǎn)換代碼:<br>
  <textarea name="encode" cols="100" rows="10"></textarea>
  <br>
  <input type="checkbox" name="method" checked> 正向轉(zhuǎn)換
  <input type=button value=" 確 定 ">
  <input type=reset value=" 清 空 ">
  <input type=button value=" 全 選 ">
</form>

下面是一個(gè)顯示所有全角半角的字體的查看例子

<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>
function showuni(min,max){
show.document.open();
show.document.writeln("<style>body{font-size:9pt;word-break:break-all;}</style>");
show.document.writeln(min + " - " + max + "<br><br>");
var i=0;
for(i=min;i<=max;i++){
  show.document.write("&#" + i + ";");
}
show.document.close();
}
</script>
<input type=button value="半角"  onclick=showuni(32,126)>
<input type=button value="全角"  onclick=showuni(65281,65374)>
<input type=button value="中文1" onclick=showuni(19968,40869)>
<input type=button value="中文2" onclick=showuni(63744,64045)>
<input type=button value="日文平"  onclick=showuni(12353,12435)>
<input type=button value="日文片"  onclick=showuni(12449,12534)>
<input type=button value="韓文"  onclick=showuni(44032,55203)>
<br>自定義:<input name=min> - <input name=max>
<input type=button value="察看" onclick=showuni(parseint(document.all.min.value),parseint(document.all.max.value))>
<br>
<iframe src="about:blank" id=show width=100% height=70% scroll=no></iframe>

下面是一個(gè)查表(gb2312),轉(zhuǎn)換gb2312到utf8的例子, 現(xiàn)在有iconv函數(shù),這個(gè)已經(jīng)沒有太大的意義了,

<?
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;
}
?>

發(fā)表評(píng)論 共有條評(píng)論
用戶名: 密碼:
驗(yàn)證碼: 匿名發(fā)表
主站蜘蛛池模板: 阜康市| 娱乐| 吉木萨尔县| 南丹县| 革吉县| 阜新市| 筠连县| 濮阳县| 沙洋县| 佳木斯市| 井冈山市| 多伦县| 沁水县| 芒康县| 阳高县| 梁河县| 靖安县| 绥阳县| 鄂尔多斯市| 灌云县| 开平市| 射阳县| 宿松县| 咸丰县| 雅江县| 离岛区| 岐山县| 曲麻莱县| 衡水市| 长治市| 上蔡县| 分宜县| 同江市| 抚顺县| 天柱县| 临洮县| 旬阳县| 抚宁县| 东乡族自治县| 湄潭县| 资中县|