note 105247 added to function.htmlentities
| From: | josh at fuxupyo dot us | Date: | Thu, 04 Aug 2011 21:36:48 +0000 |
| Subject: | note 105247 added to function.htmlentities | ||
| Groups: | php.notes | ||
| Request: | Send a blank email to php-notes+get-182235@lists.php.net to get a copy of this message | ||
h_guillaume at hotmail dot com's xml_entities() function below did not work for me exactly as
entered. The regex needs to be modified to begin with "(?:" not "(?".
<?php
function xml_entity_decode($text, $charset = 'Windows-1252'){
// Double decode, so if the value was &trade; it will become Trademark
$text = html_entity_decode($text, ENT_COMPAT, $charset);
$text = html_entity_decode($text, ENT_COMPAT, $charset);
return $text;
}
function xml_entities($text, $charset = 'Windows-1252'){
// Debug and Test
// $text = "test & ™ &trade; abc ® &reg;
-";
// First we encode html characters that are also invalid in xml
$text = htmlentities($text, ENT_COMPAT, $charset, false);
// XML character entity array from Wiki
// Note: ' is useless in UTF-8 or in UTF-16
$arr_xml_special_char =
array(""","&","'","<",">");
// Building the regex string to exclude all strings with xml special char
$arr_xml_special_char_regex = "(?";
foreach($arr_xml_special_char as $key => $value){
$arr_xml_special_char_regex .= "(?!$value)";
}
$arr_xml_special_char_regex .= ")";
// Scan the array for &something_not_xml; syntax
$pattern = "/$arr_xml_special_char_regex&([a-zA-Z0-9]+;)/";
// Replace the &something_not_xml; with &something_not_xml;
$replacement = '&${1}';
return preg_replace($pattern, $replacement, $text);
}
?>
----
Server IP: 69.147.83.197
Probable Submitter: 173.10.33.62
----
Manual Page -- http://www.php.net/manual/en/function.htmlentities.php
Edit -- https://master.php.net/note/edit/105247
Del: integrated -- https://master.php.net/note/delete/105247/integrated
Del: useless -- https://master.php.net/note/delete/105247/useless
Del: bad code -- https://master.php.net/note/delete/105247/bad+code
Del: spam -- https://master.php.net/note/delete/105247/spam
Del: non-english -- https://master.php.net/note/delete/105247/non-english
Del: in docs -- https://master.php.net/note/delete/105247/in+docs
Del: other reasons-- https://master.php.net/note/delete/105247
Reject -- https://master.php.net/note/reject/105247
Search -- https://master.php.net/manage/user-notes.php