Same name and namespace in other branches
  1. 4.6.x modules/filter.module \_filter_autop()
  2. 4.7.x modules/filter.module \_filter_autop()
  3. 6.x modules/filter/filter.module \_filter_autop()
  4. 7.x modules/filter/filter.module \_filter_autop()
  5. 8.9.x core/modules/filter/filter.module \_filter_autop()
  6. 9 core/modules/filter/filter.module \_filter_autop()

Convert line breaks into <p> and <br> in an intelligent fashion. Based on: http://photomatt.net/scripts/autop

File

modules/filter/filter.module, line 1187
Framework for handling filtering of content.

Code

function _filter_autop($text) {

  // All block level tags
  $block = '(?:table|thead|tfoot|caption|colgroup|tbody|tr|td|th|div|dl|dd|dt|ul|ol|li|pre|select|form|blockquote|address|p|h[1-6]|hr)';

  // Split at <pre>, <script>, <style> and </pre>, </script>, </style> tags.
  // We don't apply any processing to the contents of these tags to avoid messing
  // up code. We look for matched pairs and allow basic nesting. For example:
  // "processed <pre> ignored <script> ignored </script> ignored </pre> processed"
  $chunks = preg_split('@(</?(?:pre|script|style|object)[^>]*>)@i', $text, -1, PREG_SPLIT_DELIM_CAPTURE);

  // Note: PHP ensures the array consists of alternating delimiters and literals
  // and begins and ends with a literal (inserting NULL as required).
  $ignore = FALSE;
  $ignoretag = '';
  $output = '';
  foreach ($chunks as $i => $chunk) {
    if ($i % 2) {

      // Opening or closing tag?
      $open = $chunk[1] != '/';
      list($tag) = split('[ >]', substr($chunk, 2 - $open), 2);
      if (!$ignore) {
        if ($open) {
          $ignore = TRUE;
          $ignoretag = $tag;
        }
      }
      else {
        if (!$open && $ignoretag == $tag) {
          $ignore = FALSE;
          $ignoretag = '';
        }
      }
    }
    else {
      if (!$ignore) {
        $chunk = preg_replace('|\\n*$|', '', $chunk) . "\n\n";

        // just to make things a little easier, pad the end
        $chunk = preg_replace('|<br />\\s*<br />|', "\n\n", $chunk);
        $chunk = preg_replace('!(<' . $block . '[^>]*>)!', "\n\$1", $chunk);

        // Space things out a little
        $chunk = preg_replace('!(</' . $block . '>)!', "\$1\n\n", $chunk);

        // Space things out a little
        $chunk = preg_replace("/\n\n+/", "\n\n", $chunk);

        // take care of duplicates
        $chunk = preg_replace('/\\n?(.+?)(?:\\n\\s*\\n|\\z)/s', "<p>\$1</p>\n", $chunk);

        // make paragraphs, including one at the end
        $chunk = preg_replace('|<p>\\s*</p>\\n|', '', $chunk);

        // under certain strange conditions it could create a P of entirely whitespace
        $chunk = preg_replace("|<p>(<li.+?)</p>|", "\$1", $chunk);

        // problem with nested lists
        $chunk = preg_replace('|<p><blockquote([^>]*)>|i', "<blockquote\$1><p>", $chunk);
        $chunk = str_replace('</blockquote></p>', '</p></blockquote>', $chunk);
        $chunk = preg_replace('!<p>\\s*(</?' . $block . '[^>]*>)!', "\$1", $chunk);
        $chunk = preg_replace('!(</?' . $block . '[^>]*>)\\s*</p>!', "\$1", $chunk);
        $chunk = preg_replace('|(?<!<br />)\\s*\\n|', "<br />\n", $chunk);

        // make line breaks
        $chunk = preg_replace('!(</?' . $block . '[^>]*>)\\s*<br />!', "\$1", $chunk);
        $chunk = preg_replace('!<br />(\\s*</?(?:p|li|div|th|pre|td|ul|ol)>)!', '$1', $chunk);
        $chunk = preg_replace('/&([^#])(?![A-Za-z0-9]{1,8};)/', '&amp;$1', $chunk);
      }
    }
    $output .= $chunk;
  }
  return $output;
}