note 71672 added to function.preg-match
| From: | zohar at zohararad dot com | Date: | Mon, 11 Dec 2006 06:03:50 +0000 |
| Subject: | note 71672 added to function.preg-match | ||
| Groups: | php.notes | ||
| Request: | Send a blank email to php-notes+get-120500@lists.php.net to get a copy of this message | ||
After a lot of work I finally managed to write a function that closes open HTML tags in a string.
Its not perfect but it works OK on simple strings. Hope it helps anyone.
<?php
function cleanOpenTags($str){
//clean up tabs and new lines
$str = preg_replace("/\s\s+|\t\t+|\n\r+|\n\n+|\r\r+/","",$str);
$pattern = "/(<[^>]+>).*>?/smU";
//split into HTML tags
$text = preg_split($pattern,$str,-1,PREG_SPLIT_DELIM_CAPTURE | PREG_SPLIT_NO_EMPTY);
$i = -1;
$ordered = array();
$otag = "/<([a-z]+)[^>]*>/";
$noclose = "/<[a-z]{2}\s\/>/";
$block = "/<(p|div)>/";
//order the string into HTML elements and place in array
foreach($text as $part){
if(preg_match($otag,$part) && !preg_match($noclose,$part)) $i++;
$ordered[$i] .= $part;
}
//now iterate through new array and find unclosed elements
$clean = "";
foreach($ordered as $key => $part){
preg_match($otag,$part,$m);
$ctag = "</$m[1]>";
if(!preg_match($ctag,$part)) { //if no closing tag is present
//find out if there are any other closing tags in the part.
//if yes, append close tag before them
if(preg_match("/(<\/[a-z]+>)/",$part,$m1, PREG_OFFSET_CAPTURE)){
$pos = $m1[0][1]; //get str position of the close tag
$ctag = $ctag.$m1[0][0];
$ordered[$key] = substr_replace($part,$ctag,$pos,strlen($ctag));
//otherwise append at end of string
} else $ordered[$key] .= $ctag;
}
//remove duplicate close tags
if(preg_match("/<\/([a-z]+)><\/([a-z]+)>/",$ordered[$key], $m2,
PREG_OFFSET_CAPTURE)){
if($m2[1][0] == $m2[2][0]) {
$ordered[$key] = substr($ordered[$key],0,$m2[2][1]-2);
}
}
$clean .= $ordered[$key];
}
return $clean;
}
?>
----
Server IP: 212.199.163.191
Probable Submitter: 62.90.246.190
----
Manual Page -- http://www.php.net/manual/en/function.preg-match.php
Edit -- https://master.php.net/note/edit/71672
Del: integrated -- https://master.php.net/note/delete/71672/integrated
Del: useless -- https://master.php.net/note/delete/71672/useless
Del: bad code -- https://master.php.net/note/delete/71672/bad+code
Del: spam -- https://master.php.net/note/delete/71672/spam
Del: non-english -- https://master.php.net/note/delete/71672/non-english
Del: in docs -- https://master.php.net/note/delete/71672/in+docs
Del: other reasons-- https://master.php.net/note/delete/71672
Reject -- https://master.php.net/note/reject/71672
Search -- https://master.php.net/manage/user-notes.php