Created
April 11, 2011 11:24
-
-
Save supermethod/913378 to your computer and use it in GitHub Desktop.
Close open tags and remove certain html for CDATA inclusion
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
//from http://codesnippets.joyent.com/posts/show/959 | |
function close_dangling_tags($html){ | |
#put all opened tags into an array | |
preg_match_all("#<([a-z]+)( .*)?(?!/)>#iU",$html,$result); | |
$openedtags=$result[1]; | |
#put all closed tags into an array | |
preg_match_all("#</([a-z]+)>#iU",$html,$result); | |
$closedtags=$result[1]; | |
$len_opened = count($openedtags); | |
# all tags are closed | |
if(count($closedtags) == $len_opened){ | |
return $html; | |
} | |
$openedtags = array_reverse($openedtags); | |
# close tags | |
for($i=0;$i < $len_opened;$i++) { | |
if (!in_array($openedtags[$i],$closedtags)){ | |
$html .= '</'.$openedtags[$i].'>'; | |
} else { | |
unset($closedtags[array_search($openedtags[$i],$closedtags)]); | |
} | |
} | |
return $html; | |
} | |
//remove html and wrap remaining in CDATA | |
function removeHTML($string) { | |
$string = strip_tags($string, '<p><span class="intro"><h3><h4><h5><li>'); | |
$string = close_dangling_tags($string); | |
return '<![CDATA['.$string.']]>'; | |
} |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment