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})|&#x.{4};|&#\d+;|.+/U",$str,$r); $ar = $r[0]; print_r($ar); foreach($ar as $k=>$v) { if(substr($v,0,2) == "%u") &nbs |