This article mainly introduces how to implement the escape and unescape function code in PHP. This article provides two implementation versions. if you need it, you can refer to this class for reference. why? PHP uses JSON to pass GBK characters, such as Chinese characters, Japanese characters, and Unicode characters of Korean gods and horses ..
<? Phpclasscoding {// simulate functions of the javascript escape and UNESCAPE functions functionunescape scape ($ str) {$ text = preg_replace_callback ("/% u [0-9A-Za-z] {4 }/", array (& $ this, 'toutf8'), $ str); returnmb_convert_encoding ($ text, "gb2312", "UTF-8");} functiontoUtf8 ($ ar) {foreach ($ aras $ val) {$ val = intval (substr ($ val, 2), 16); if ($ val <0x7F) {// minutes -007f $ c. = chr ($ val);} elseif ($ val <0x800) {// 0080-0800 $ c. = chr (0xC0 | ($ val/64); $ c. = chr (0x80 | ($ val % 64);} else {// 0800-FFFF $ c. = chr (0xE0 | ($ val/64)/64); $ c. = chr (0x80 | ($ val/64) % 64); $ c. = chr (0x80 | ($ val % 64) ;}return $ c ;}functionescape ($ string, $ encoding = 'gb2312') {$ return = ''; for ($ x = 0; $ x
1) {// multi-byte character $ return. = '% u '. strtoupper (bin2hex (mb_convert_encoding ($ str, 'ucs-2', $ encoding);} else {$ return. = '% '. strtoupper (bin2hex ($ str) ;}return $ return;} functiongb2utf8 ($ string, $ encoding = 'utf-8', $ from_encode = 'gb2312 ') {returnmb_convert_encoding ($ string, $ encoding, $ from_encode) ;}}?>
Another similar script found on google code
<?php functionphpescape($str) { $sublen=strlen($str); $retrunString=""; for($i=0;$i<$sublen;$i++) { if(ord($str[$i])>=127) { $tmpString=bin2hex(iconv("gbk","ucs-2",substr($str,$i,2))); $tmpString=substr($tmpString,2,2).substr($tmpString,0,2); $retrunString.="%u".$tmpString; $i++; }else{ $retrunString.="%".dechex(ord($str[$i])); } } return$retrunString; } functionescape($str) { preg_match_all("/[\x80-\xff].|[\x01-\x7f]+/",$str,$r); $ar=$r[0]; foreach($aras$k=>$v) { if(ord($v[0])<128) $ar[$k]=rawurlencode($v); else $ar[$k]="%u".bin2hex(iconv("UTF-8","UCS-2",$v)); } returnjoin("",$ar); } functionphpunescape($source) { $decodedStr=""; $pos=0; $len=strlen($source); while($pos<$len) { $charAt=substr($source,$pos,1); if($charAt=='%') { $pos++; $charAt=substr($source,$pos,1); if($charAt=='u') { // we got a unicode character $pos++; $unicodeHexVal=substr($source,$pos,4); $unicode=hexdec($unicodeHexVal); $entity="&#".$unicode.';'; $decodedStr.=utf8_encode($entity); $pos+=4; }else{ // we have an escaped ascii character $hexVal=substr($source,$pos,2); $decodedStr.=chr(hexdec($hexVal)); $pos+=2; } }else{ $decodedStr.=$charAt; $pos++; } } return$decodedStr; } functionunescape($str) { $str=rawurldecode($str); preg_match_all("/(?:%u.{4})|&#x.{4};|&#\d+;|.+/U",$str,$r); $ar=$r[0]; #print_r($ar); foreach($aras$k=>$v) { if(substr($v,0,2)=="%u") $ar[$k]=iconv("UCS-2","UTF-8",pack("H4",substr($v,-4))); elseif(substr($v,0,3)=="&#x") $ar[$k]=iconv("UCS-2","UTF-8",pack("H4",substr($v,3,-1))); elseif(substr($v,0,2)=="&#") { //echo substr($v,2,-1).""; $ar[$k]=iconv("UCS-2","UTF-8",pack("n",substr($v,2,-1))); } } returnjoin("",$ar); } ?>