[wp-trac] [WordPress Trac] #37672: wpautop adds a closing p-tag without an opening p-tag

[WordPress Trac]

#37672: wpautop adds a closing p-tag without an opening p-tag
--------------------------+------------------------------
 Reporter:  TBarregren    |       Owner:
     Type:  defect (bug)  |      Status:  new
 Priority:  normal        |   Milestone:  Awaiting Review
Component:  Formatting    |     Version:  4.5.3
 Severity:  normal        |  Resolution:
 Keywords:                |     Focuses:
--------------------------+------------------------------

Comment (by TBarregren):

 If it is to any help, this is my function.php code to solve this (and
 related) problem(s).

 {{{#!php
 <?php
 add_filter('the_content', function ($html) {

   $html_pos = 0;
   $last_html_pos = strlen($html) - 1;

   $opening_pos = null;
   $text_pos = null;

   // See http://w3c.github.io/html/single-page.html#elementdef-p
   // and http://w3c.github.io/html/single-page.html#kinds-of-content-
 phrasing-content
   $self_closing_tags_allowed_in_p = explode(' ', 'area br embed img input
 link wbr');
   $not_self_closing_tags_allowed_in_p = explode(' ', 'a abbr audio b bdi
 bdo button canvas cite code data datalist del dfn em i iframe ins kbd
 label map mark math meter noscript object output picture progress q ruby s
 samp script select small span strong sub sup svg template textarea time u
 var video text');


   while (($html_pos = strpos($html, '<', $html_pos)) !== false) {
     if (substr($html, $html_pos, 4) === '<!--') {
       $html_pos = strpos($html, '-->', $html_pos + 4);
       if ($html_pos === false) return $html; // Too messy, don't do
 anything further.
       $html_pos += 3;
     }
     elseif ($opening_pos === null) {
       if (substr($html, $html_pos, 4) === '<pre') {
         $html_pos = strpos($html, '</pre>', $html_pos + 6);
         if ($html_pos === false) return $html; // Too messy, don't do
 anything further.
         $html_pos += 6;
       }
       elseif (strtolower(substr($html, $html_pos, 2)) === '<p') {
         $opening_pos = $html_pos;
         $html_pos = strpos($html, '>', $html_pos + 2);
         if ($html_pos === false) return $html; // Too messy, don't do
 anything further.
         $text_pos = ++$html_pos;
       }
       elseif (strtolower(substr($html, $html_pos, 4)) === '</p>') {
         // See https://core.trac.wordpress.org/ticket/37672
         $html = substr($html, 0, $html_pos) . substr($html, $html_pos +
 4);
         $last_html_pos -= 4;
       }
       else {
         $html_pos += 1;
       }
     }
     else {
       if (strtolower(substr($html, $html_pos, 4)) === '</p>') {
         if (trim(substr($html, $text_pos, $html_pos - $text_pos)) === '')
 {
           $html = substr($html, 0, $opening_pos) . substr($html, $html_pos
 + 4);
           $html_pos = $opening_pos;
           $last_html_pos = strlen($html) - 1;
         }
         else {
           $html_pos += 4;
         }
         $opening_pos = null;
       }
       else {
         $tag_end_pos = $html_pos + 1;
         while ($html{$tag_end_pos} !== '>' &&
 !ctype_space($html{$tag_end_pos})) {
           ++$tag_end_pos;
         }
         $tag = strtolower(substr($html, $html_pos + 1, $tag_end_pos -
 $html_pos - 1));
         if (in_array($tag, $self_closing_tags_allowed_in_p)) {
           $html_pos = strpos($html, '>', $tag_end_pos);
           if ($html_pos === false) return $html; // Too messy, don't do
 anything further.
           $html_pos += 1;
         }
         elseif (in_array($tag, $not_self_closing_tags_allowed_in_p)) {
           $html_pos = strpos($html, "</$tag", $tag_end_pos);
           if ($html_pos === false) return $html; // Too messy, don't do
 anything further.
           $html_pos += 1;
         }
         else {
           $tag_end_pos = strpos($html, "</$tag>", $tag_end_pos);
           if ($tag_end_pos === false) return $html; // Too messy, don't do
 anything further.
           $tag_end_pos += strlen("</$tag>");
           $html = substr($html, 0, $html_pos) . '</p>' . substr($html,
 $html_pos, $tag_end_pos - $html_pos) . '<p>' . substr($html,
 $tag_end_pos);
         }
       }
     }
   }
   if ($opening_pos !== null) {
     $html .= '</p>';
   }

   return $html;

 });
 }}}

--
Ticket URL: <https://core.trac.wordpress.org/ticket/37672#comment:1>
WordPress Trac <https://core.trac.wordpress.org/>
WordPress publishing platform