preg_replace_callback 實現比較優雅的替換

下面兩種方法用於將相似한這樣的片斷轉換成正常的文字

第一種方法先用正則將須要替換的片斷找到,而後循環處理, 第二種方法使用了preg_replace_callback ,第二種方法代碼量較少,看起來更加優雅.

方法一

<?php
$test_str="曾&#54620;李&#44397;&#50612;" ;
echo unescape($test_str);
function unescape($str) {
    preg_match_all("/(?:%u.{4})|&#x.{4};|&#\d+;|.+/U",$str,$r);
    $ar = $r[0];
    foreach($ar as $k=>$v) {
        if(substr($v,0,2) == "%u"){
            $ar[$k] = iconv("UCS-2BE","UTF-8",pack("H4",substr($v,-4)));
      }
        elseif(substr($v,0,3) == "&#x"){
            $ar[$k] = iconv("UCS-2BE","UTF-8",pack("H4",substr($v,3,-1)));
      }
        elseif(substr($v,0,2) == "&#") {
            $ar[$k] = iconv("UCS-2BE","UTF-8",pack("n",substr($v,2,-1)));
        }
    }
    return join("",$ar);
}
?>

方法二

<?php
$test_str="曾&#54620;李&#44397;&#50612;" ;
echo preg_replace_callback("/(%u.{4})|&#x.{4};|&#\d+;/ i", "unescape", $test_str);
function unescape($str_org) {    
    $str_org=$str_org[0];
        if(substr($str_org,0,2) == "%u"){
            $str_fin = iconv("UCS-2BE","UTF-8",pack("H4",substr($str_org,-4)));
      }
        elseif(substr($str_org,0,3) == "&#x"){
            $str_fin = iconv("UCS-2BE","UTF-8",pack("H4",substr($str_org,3,-1)));
      }
        elseif(substr($str_org,0,2) == "&#") {
            $str_fin = iconv("UCS-2BE","UTF-8",pack("n",substr($str_org,2,-1)));
        }
        return $str_fin ;
}
?>