Close open HTML tags in a string

Question

Situation is a string that results in something like this:

This is some text and here is a bold text then the post stop here....


        

Answer 1

I've done this code witch doest the job quite correctly...

It's old school but efficient and I've added a flag to remove the unfinished tags such as " blah blah http://stackoverfl"

public function getOpennedTags(&$string, $removeInclompleteTagEndTagIfExists = true) {

    $tags = array();
    $tagOpened = false;
    $tagName = '';
    $tagNameLogged = false;
    $closingTag = false;

    foreach (str_split($string) as $c) {
        if ($tagOpened && $c == '>') {
            $tagOpened = false;
            if ($closingTag) {
                array_pop($tags);
                $closingTag = false;
                $tagName = '';
            }
            if ($tagName) {
                array_push($tags, $tagName);
            }
        }
        if ($tagOpened && $c == ' ') {
            $tagNameLogged = true;
        }
        if ($tagOpened && $c == '/') {
            if ($tagName) {
                //orphan tag
                $tagOpened = false;
                $tagName = '';
            } else {
                //closingTag
                $closingTag = true;
            }
        }
        if ($tagOpened && !$tagNameLogged) {
            $tagName .= $c;
        }
        if (!$tagOpened && $c == '<') {
            $tagNameLogged = false;
            $tagName = '';
            $tagOpened = true;
            $closingTag = false;
        }
    }

    if ($removeInclompleteTagEndTagIfExists && $tagOpened) {
        // an tag has been cut for exemaple ' blabh blah <a href="sdfoefzofk' so closing the tag will not help...
        // let's remove this ugly piece of tag
        $pos = strrpos($string, '<');
        $string = substr($string, 0, $pos);
    }

    return $tags;
}

Usage example :

$tagsToClose = $stringHelper->getOpennedTags($val);
$tagsToClose = array_reverse($tagsToClose);

foreach ($tagsToClose as $tag) {
    $val .= "</$tag>";
}

Answer 2

if tidy module is installed, use php tidy extension:

tidy_repair_string($html)

reference

Answer 3

This is works for me to close any open HTML tags in a script.

<?php
function closetags($html) {
preg_match_all('#<([a-z]+)(?: .*)?(?<![/|/ ])>#iU', $html, $result);
$openedtags = $result[1];
preg_match_all('#</([a-z]+)>#iU', $html, $result);
$closedtags = $result[1];
$len_opened = count($openedtags);
if (count($closedtags) == $len_opened) {
    return $html;
}
$openedtags = array_reverse($openedtags);
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;
}