path: root/modules/filter/filter.module

<?php
// $Id$

/**
 * @file
 * Framework for handling filtering of content.
 */

/**
 * Special format ID which means "use the default format".
 *
 * This value can be passed to the filter APIs as a format ID: this is
 * equivalent to not passing an explicit format at all.
 */
define('FILTER_FORMAT_DEFAULT', 0);

/**
 * Implement hook_help().
 */
function filter_help($path, $arg) {
  switch ($path) {
    case 'admin/help#filter':
      $output = '<p>' . t("The filter module allows administrators to configure text formats for use on your site. A text format defines the HTML tags, codes, and other input allowed in both content and comments, and is a key feature in guarding against potentially damaging input from malicious users. Two formats included by default are <em>Filtered HTML</em> (which allows only an administrator-approved subset of HTML tags) and <em>Full HTML</em> (which allows the full set of HTML tags). Additional formats may be created by an administrator.") . '</p>';
      $output .= '<p>' . t('Each text format uses filters to manipulate text, and most formats apply several different filters to text in a specific order. Each filter is designed for a specific purpose, and generally either adds, removes or transforms elements within user-entered text before it is displayed. A filter does not change the actual content of a post, but instead, modifies it temporarily before it is displayed. A filter may remove unapproved HTML tags, for instance, while another automatically adds HTML to make links referenced in text clickable.') . '</p>';
      $output .= '<p>' . t('Users with access to more than one text format can use the <em>Text format</em> fieldset to choose between available text formats when creating or editing multi-line content. Administrators determine the text formats available to each user role, select a default text format, and control the order of formats listed in the <em>Text format</em> fieldset.') . '</p>';
      $output .= '<p>' . t('For more information, see the online handbook entry for <a href="@filter">Filter module</a>.', array('@filter' => 'http://drupal.org/handbook/modules/filter/')) . '</p>';
      return $output;
    case 'admin/settings/formats':
      $output = '<p>' . t('Use the list below to review the text formats available to each user role, to select a default text format, and to control the order of formats listed in the <em>Text format</em> fieldset. (The <em>Text format</em> fieldset is displayed below textareas when users with access to more than one text format create multi-line content.) The text format selected as <em>Default</em> is available to all users and, unless another format is selected, is applied to all content. All text formats are available to users in roles with the "administer filters" permission.') . '</p>';
      $output .= '<p>' . t('Since text formats, if available, are presented in the same order as the list below, it may be helpful to arrange the formats in descending order of your preference for their use. Remember that your changes will not be saved until you click the <em>Save changes</em> button at the bottom of the page.') . '</p>';
      return $output;
    case 'admin/settings/formats/%':
      return '<p>' . t('Every <em>filter</em> performs one particular change on the user input, for example stripping out malicious HTML or making URLs clickable. Choose which filters you want to apply to text in this format. If you notice some filters are causing conflicts in the output, you can <a href="@rearrange">rearrange them</a>.', array('@rearrange' => url('admin/settings/formats/' . $arg[3] . '/order'))) . '</p>';
    case 'admin/settings/formats/%/configure':
      return '<p>' . t('If you cannot find the settings for a certain filter, make sure you have enabled it on the <a href="@url">edit tab</a> first.', array('@url' => url('admin/settings/formats/' . $arg[3]))) . '</p>';
    case 'admin/settings/formats/%/order':
      $output = '<p>' . t('Because of the flexible filtering system, you might encounter a situation where one filter prevents another from doing its job. For example: a word in an URL gets converted into a glossary term, before the URL can be converted to a clickable link. When this happens, rearrange the order of the filters.') . '</p>';
      $output .= '<p>' . t("Filters are executed from top-to-bottom. To change the order of the filters, modify the values in the <em>Weight</em> column or grab a drag-and-drop handle under the <em>Name</em> column and drag filters to new locations in the list. (Grab a handle by clicking and holding the mouse while hovering over a handle icon.) Remember that your changes will not be saved until you click the <em>Save configuration</em> button at the bottom of the page.") . '</p>';
      return $output;
  }
}

/**
 * Implement hook_theme().
 */
function filter_theme() {
  return array(
    'filter_admin_overview' => array(
      'arguments' => array('form' => NULL),
      'file' => 'filter.admin.inc',
    ),
    'filter_admin_order' => array(
      'arguments' => array('form' => NULL),
      'file' => 'filter.admin.inc',
    ),
    'filter_tips' => array(
      'arguments' => array('tips' => NULL, 'long' => FALSE),
      'file' => 'filter.pages.inc',
    ),
    'filter_tips_more_info' => array(
      'arguments' => array(),
    ),
    'filter_guidelines' => array(
      'arguments' => array('format' => NULL),
    ),
  );
}

/**
 * Implement hook_menu().
 */
function filter_menu() {
  $items['admin/settings/formats'] = array(
    'title' => 'Text formats',
    'description' => 'Configure how content input by users is filtered, including allowed HTML tags. Also allows enabling of module-provided filters.',
    'page callback' => 'drupal_get_form',
    'page arguments' => array('filter_admin_overview'),
    'access arguments' => array('administer filters'),
    'file' => 'filter.admin.inc',
  );
  $items['admin/settings/formats/list'] = array(
    'title' => 'List',
    'type' => MENU_DEFAULT_LOCAL_TASK,
  );
  $items['admin/settings/formats/add'] = array(
    'title' => 'Add text format',
    'page callback' => 'filter_admin_format_page',
    'access arguments' => array('administer filters'),
    'type' => MENU_LOCAL_ACTION,
    'weight' => 1,
    'file' => 'filter.admin.inc',
  );
  $items['admin/settings/formats/delete'] = array(
    'title' => 'Delete text format',
    'page callback' => 'drupal_get_form',
    'page arguments' => array('filter_admin_delete'),
    'access arguments' => array('administer filters'),
    'type' => MENU_CALLBACK,
    'file' => 'filter.admin.inc',
  );
  $items['filter/tips'] = array(
    'title' => 'Compose tips',
    'page callback' => 'filter_tips_long',
    'access callback' => TRUE,
    'type' => MENU_SUGGESTED_ITEM,
    'file' => 'filter.pages.inc',
  );
  $items['admin/settings/formats/%filter_format'] = array(
    'type' => MENU_CALLBACK,
    'title callback' => 'filter_admin_format_title',
    'title arguments' => array(3),
    'page callback' => 'filter_admin_format_page',
    'page arguments' => array(3),
    'access arguments' => array('administer filters'),
    'file' => 'filter.admin.inc',
  );
  $items['admin/settings/formats/%filter_format/edit'] = array(
    'title' => 'Edit',
    'type' => MENU_DEFAULT_LOCAL_TASK,
    'weight' => 0,
  );
  $items['admin/settings/formats/%filter_format/configure'] = array(
    'title' => 'Configure',
    'page callback' => 'filter_admin_configure_page',
    'page arguments' => array(3),
    'access arguments' => array('administer filters'),
    'type' => MENU_LOCAL_TASK,
    'weight' => 1,
    'file' => 'filter.admin.inc',
  );
  $items['admin/settings/formats/%filter_format/order'] = array(
    'title' => 'Rearrange',
    'page callback' => 'filter_admin_order_page',
    'page arguments' => array(3),
    'access arguments' => array('administer filters'),
    'type' => MENU_LOCAL_TASK,
    'weight' => 2,
    'file' => 'filter.admin.inc',
  );
  return $items;
}

function filter_format_load($arg) {
  return filter_formats($arg);
}

/**
 * Display a text format form title.
 */
function filter_admin_format_title($format) {
  return $format->name;
}

/**
 * Implement hook_permission().
 */
function filter_permission() {
  return array(
    'administer filters' => array(
      'title' => t('Administer filters'),
      'description' => t('Manage text formats and filters, and select which roles may use them. %warning', array('%warning' => t('Warning: Give to trusted roles only; this permission has security implications.'))),
    ),
  );
}

/**
 * Implement hook_cron().
 *
 * Expire outdated filter cache entries
 */
function filter_cron() {
  cache_clear_all(NULL, 'cache_filter');
}

/**
 * @name Tips callbacks for filters.
 * @{
 * Filters implemented by the filter.module.
 */
function _filter_html_tips($format, $long = FALSE) {
  global $base_url;
  if ($allowed_html = variable_get("allowed_html_$format", '<a> <em> <strong> <cite> <blockquote> <code> <ul> <ol> <li> <dl> <dt> <dd>')) {
    if ($long) {
      $output = '<p>' . t('Allowed HTML tags: @tags', array('@tags' => $allowed_html)) . '</p>';
      if (!variable_get("filter_html_help_$format", 1)) {
        return $output;
      }

      $output .= '<p>' . t('This site allows HTML content. While learning all of HTML may feel intimidating, learning how to use a very small number of the most basic HTML "tags" is very easy. This table provides examples for each tag that is enabled on this site.') . '</p>';
      $output .= '<p>' . t('For more information see W3C\'s <a href="@html-specifications">HTML Specifications</a> or use your favorite search engine to find other sites that explain HTML.', array('@html-specifications' => 'http://www.w3.org/TR/html/')) . '</p>';
      $tips = array(
        'a' => array( t('Anchors are used to make links to other pages.'), '<a href="' . $base_url . '">' . variable_get('site_name', 'Drupal') . '</a>'),
        'br' => array( t('By default line break tags are automatically added, so use this tag to add additional ones. Use of this tag is different because it is not used with an open/close pair like all the others. Use the extra " /" inside the tag to maintain XHTML 1.0 compatibility'), t('Text with <br />line break')),
        'p' => array( t('By default paragraph tags are automatically added, so use this tag to add additional ones.'), '<p>' . t('Paragraph one.') . '</p> <p>' . t('Paragraph two.') . '</p>'),
        'strong' => array( t('Strong'), '<strong>' . t('Strong') . '</strong>'),
        'em' => array( t('Emphasized'), '<em>' . t('Emphasized') . '</em>'),
        'cite' => array( t('Cited'), '<cite>' . t('Cited') . '</cite>'),
        'code' => array( t('Coded text used to show programming source code'), '<code>' . t('Coded') . '</code>'),
        'b' => array( t('Bolded'), '<b>' . t('Bolded') . '</b>'),
        'u' => array( t('Underlined'), '<u>' . t('Underlined') . '</u>'),
        'i' => array( t('Italicized'), '<i>' . t('Italicized') . '</i>'),
        'sup' => array( t('Superscripted'), t('<sup>Super</sup>scripted')),
        'sub' => array( t('Subscripted'), t('<sub>Sub</sub>scripted')),
        'pre' => array( t('Preformatted'), '<pre>' . t('Preformatted') . '</pre>'),
        'abbr' => array( t('Abbreviation'), t('<abbr title="Abbreviation">Abbrev.</abbr>')),
        'acronym' => array( t('Acronym'), t('<acronym title="Three-Letter Acronym">TLA</acronym>')),
        'blockquote' => array( t('Block quoted'), '<blockquote>' . t('Block quoted') . '</blockquote>'),
        'q' => array( t('Quoted inline'), '<q>' . t('Quoted inline') . '</q>'),
        // Assumes and describes tr, td, th.
        'table' => array( t('Table'), '<table> <tr><th>' . t('Table header') . '</th></tr> <tr><td>' . t('Table cell') . '</td></tr> </table>'),
        'tr' => NULL, 'td' => NULL, 'th' => NULL,
        'del' => array( t('Deleted'), '<del>' . t('Deleted') . '</del>'),
        'ins' => array( t('Inserted'), '<ins>' . t('Inserted') . '</ins>'),
         // Assumes and describes li.
        'ol' => array( t('Ordered list - use the &lt;li&gt; to begin each list item'), '<ol> <li>' . t('First item') . '</li> <li>' . t('Second item') . '</li> </ol>'),
        'ul' => array( t('Unordered list - use the &lt;li&gt; to begin each list item'), '<ul> <li>' . t('First item') . '</li> <li>' . t('Second item') . '</li> </ul>'),
        'li' => NULL,
        // Assumes and describes dt and dd.
        'dl' => array( t('Definition lists are similar to other HTML lists. &lt;dl&gt; begins the definition list, &lt;dt&gt; begins the definition term and &lt;dd&gt; begins the definition description.'), '<dl> <dt>' . t('First term') . '</dt> <dd>' . t('First definition') . '</dd> <dt>' . t('Second term') . '</dt> <dd>' . t('Second definition') . '</dd> </dl>'),
        'dt' => NULL, 'dd' => NULL,
        'h1' => array( t('Heading'), '<h1>' . t('Title') . '</h1>'),
        'h2' => array( t('Heading'), '<h2>' . t('Subtitle') . '</h2>'),
        'h3' => array( t('Heading'), '<h3>' . t('Subtitle three') . '</h3>'),
        'h4' => array( t('Heading'), '<h4>' . t('Subtitle four') . '</h4>'),
        'h5' => array( t('Heading'), '<h5>' . t('Subtitle five') . '</h5>'),
        'h6' => array( t('Heading'), '<h6>' . t('Subtitle six') . '</h6>')
      );
      $header = array(t('Tag Description'), t('You Type'), t('You Get'));
      preg_match_all('/<([a-z0-9]+)[^a-z0-9]/i', $allowed_html, $out);
      foreach ($out[1] as $tag) {
        if (array_key_exists($tag, $tips)) {
          if ($tips[$tag]) {
            $rows[] = array(
              array('data' => $tips[$tag][0], 'class' => array('description')),
              array('data' => '<code>' . check_plain($tips[$tag][1]) . '</code>', 'class' => array('type')),
              array('data' => $tips[$tag][1], 'class' => array('get'))
            );
          }
        }
        else {
          $rows[] = array(
            array('data' => t('No help provided for tag %tag.', array('%tag' => $tag)), 'class' => array('description'), 'colspan' => 3),
          );
        }
      }
      $output .= theme('table', $header, $rows);

      $output .= '<p>' . t('Most unusual characters can be directly entered without any problems.') . '</p>';
      $output .= '<p>' . t('If you do encounter problems, try using HTML character entities. A common example looks like &amp;amp; for an ampersand &amp; character. For a full list of entities see HTML\'s <a href="@html-entities">entities</a> page. Some of the available characters include:', array('@html-entities' => 'http://www.w3.org/TR/html4/sgml/entities.html')) . '</p>';

      $entities = array(
        array( t('Ampersand'), '&amp;'),
        array( t('Greater than'), '&gt;'),
        array( t('Less than'), '&lt;'),
        array( t('Quotation mark'), '&quot;'),
      );
      $header = array(t('Character Description'), t('You Type'), t('You Get'));
      unset($rows);
      foreach ($entities as $entity) {
        $rows[] = array(
          array('data' => $entity[0], 'class' => array('description')),
          array('data' => '<code>' . check_plain($entity[1]) . '</code>', 'class' => array('type')),
          array('data' => $entity[1], 'class' => array('get'))
        );
      }
      $output .= theme('table', $header, $rows);
      return $output;
    }

    else {
      return t('Allowed HTML tags: @tags', array('@tags' => $allowed_html));
    }
  }
}

function _filter_autop_tips($format, $long = FALSE) {
  if ($long) {
    return t('Lines and paragraphs are automatically recognized. The &lt;br /&gt; line break, &lt;p&gt; paragraph and &lt;/p&gt; close paragraph tags are inserted automatically. If paragraphs are not recognized simply add a couple blank lines.');
  }
  else {
    return t('Lines and paragraphs break automatically.');
  }
}

function _filter_url_tips() {
  return t('Web page addresses and e-mail addresses turn into links automatically.');
}

function _filter_html_escape_tips() {
  return t('No HTML tags allowed.');
}

/**
 * @} End of "Tips callback for filters".
 */
/**
 * Retrieve a list of text formats.
 */
function filter_formats($index = NULL) {
  global $user;
  static $formats;

  // Administrators can always use all text formats.
  $all = user_access('administer filters');

  if (!isset($formats)) {
    $formats = array();

    $query = db_select('filter_format', 'f');
    $query->addField('f', 'format', 'format');
    $query->addField('f', 'name', 'name');
    $query->addField('f', 'roles', 'roles');
    $query->addField('f', 'cache', 'cache');
    $query->addField('f', 'weight', 'weight');
    $query->orderBy('weight');

    // Build query for selecting the format(s) based on the user's roles.
    if (!$all) {
      $or = db_or()->condition('format', variable_get('filter_default_format', 1));
      foreach ($user->roles as $rid => $role) {
        $or->condition('roles', '%' . (int)$rid . '%', 'LIKE');
      }
      $query->condition($or);
    }

    $formats = $query->execute()->fetchAllAssoc('format');
  }
  if (isset($index)) {
    return isset($formats[$index]) ? $formats[$index] : FALSE;
  }
  return $formats;
}

/**
 * Build a list of all filters.
 */
function filter_list_all() {
  $filters = array();

  foreach (module_implements('filter_info') as $module) {
    $function = $module . '_filter_info';
    $info = $function('list');
    if (isset($info) && is_array($info)) {
      foreach ($info as $name => $filter) {
        $filters[$module . '/' . $name] = (object)($filter + array(
          'module' => $module,
          'name' => $name,
        ));
      }
    }
  }

  uasort($filters, '_filter_list_cmp');

  return $filters;
}

/**
 * Helper function for sorting the filter list by filter name.
 */
function _filter_list_cmp($a, $b) {
  return strcmp($a->name, $b->name);
}

/**
 * Resolve a format id, including the default format.
 */
function filter_resolve_format($format) {
  return $format == FILTER_FORMAT_DEFAULT ? variable_get('filter_default_format', 1) : $format;
}
/**
 * Check if text in a certain text format is allowed to be cached.
 */
function filter_format_allowcache($format) {
  static $cache = array();
  $format = filter_resolve_format($format);
  if (!isset($cache[$format])) {
    $cache[$format] = db_query('SELECT cache FROM {filter_format} WHERE format = :format', array(':format' => $format))->fetchField();
  }
  return $cache[$format];
}

/**
 * Retrieve a list of filters for a certain format.
 */
function filter_list_format($format) {
  static $filters = array();

  if (!isset($filters[$format])) {
    $filters[$format] = array();
    $result = db_query("SELECT * FROM {filter} WHERE format = :format ORDER BY weight, module, name", array(':format' => (int) $format));
    foreach ($result as $filter) {
      $info = module_invoke($filter->module, 'filter_info');
      if (isset($info) && is_array($info) && isset($info[$filter->name])) {
        $filter->title = $info[$filter->name]['title'];
        $filters[$format][$filter->module . '/' . $filter->name] = $filter;
      }
    }
  }

  return $filters[$format];
}

/**
 * @name Filtering functions
 * @{
 * Modules which need to have content filtered can use these functions to
 * interact with the filter system.
 *
 * For more info, see the hook_filter() documentation.
 *
 * Note: because filters can inject JavaScript or execute PHP code, security is
 * vital here. When a user supplies a $format, you should validate it with
 * filter_access($format) before accepting/using it. This is normally done in
 * the validation stage of the node system. You should for example never make a
 * preview of content in a disallowed format.
 */

/**
 * Run all the enabled filters on a piece of text.
 *
 * @param $text
 *   The text to be filtered.
 * @param $format
 *   The format of the text to be filtered. Specify FILTER_FORMAT_DEFAULT for
 *   the default format.
 * @param $langcode
 *   Optional: the language code of the text to be filtered, e.g. 'en' for
 *   English. This allows filters to be language aware so language specific
 *   text replacement can be implemented.
 * @param $cache
 *   Boolean whether to cache the filtered output in the {cache_filter} table.
 *   The caller may set this to FALSE when the output is already cached
 *   elsewhere to avoid duplicate cache lookups and storage.
 */
function check_markup($text, $format = FILTER_FORMAT_DEFAULT, $langcode = '', $cache = TRUE) {
  if (isset($text)) {
    $format = filter_resolve_format($format);

    // Check for a cached version of this piece of text.
    $cache_id = $format . ':' . $langcode . ':' . md5($text);
    if ($cache && $cached = cache_get($cache_id, 'cache_filter')) {
      return $cached->data;
    }

    // Convert all Windows and Mac newlines to a single newline,
    // so filters only need to deal with one possibility.
    $text = str_replace(array("\r\n", "\r"), "\n", $text);

    // Get a complete list of filters, ordered properly.
    $filters = filter_list_format($format);

    // Give filters the chance to escape HTML-like data such as code or formulas.
    foreach ($filters as $filter) {
      $filter_info = module_invoke($filter->module, 'filter_info');
      if (isset($filter_info[$filter->name]['prepare callback']) && function_exists($filter_info[$filter->name]['prepare callback'])) {
        $text = call_user_func($filter_info[$filter->name]['prepare callback'], $text, $format, $langcode, $cache_id);
      }
    }

    // Perform filtering.
    foreach ($filters as $filter) {
      $filter_info = module_invoke($filter->module, 'filter_info');
      if (isset($filter_info[$filter->name]['process callback']) && function_exists($filter_info[$filter->name]['process callback'])) {
        $text = call_user_func($filter_info[$filter->name]['process callback'], $text, $format, $langcode, $cache_id);
      }
    }

    // Store in cache with a minimum expiration time of 1 day.
    if ($cache && filter_format_allowcache($format)) {
      cache_set($cache_id, $text, 'cache_filter', REQUEST_TIME + (60 * 60 * 24));
    }
  }
  else {
    $text = t('n/a');
  }

  return $text;
}

/**
 * Generate a selector for choosing a format in a form.
 *
 * @ingroup forms
 * @param $value
 *   The ID of the format that is currently selected.
 * @param $weight
 *   The weight of the text format.
 * @param $parents
 *   Required when defining multiple text formats on a single node or having a different parent than 'format'.
 * @return
 *   HTML for the form element.
 */
function filter_form($value = FILTER_FORMAT_DEFAULT, $weight = NULL, $parents = array('format')) {
  $value = filter_resolve_format($value);
  $formats = filter_formats();

  drupal_add_js('misc/form.js');
  drupal_add_css(drupal_get_path('module', 'filter') . '/filter.css');
  $element_id = form_clean_id('edit-' . implode('-', $parents));

  $form = array(
    '#type' => 'fieldset',
    '#weight' => $weight,
    '#attributes' => array('class' => array('filter-wrapper')),
  );
  $form['format_guidelines'] = array(
    '#prefix' => '<div id="' . $element_id . '-guidelines" class="filter-guidelines">',
    '#suffix' => '</div>',
    '#weight' => 2,
  );
  foreach ($formats as $format) {
    $options[$format->format] = $format->name;
    $form['format_guidelines'][$format->format] = array(
      '#markup' => theme('filter_guidelines', $format),
    );
  }
  $form['format'] = array(
    '#type' => 'select',
    '#title' => t('Text format'),
    '#options' => $options,
    '#default_value' => $value,
    '#parents' => $parents,
    '#access' => count($formats) > 1,
    '#id' => $element_id,
    '#attributes' => array('class' => array('filter-list')),
  );
  $form['format_help'] = array(
    '#prefix' => '<div id="' . $element_id . '-help" class="filter-help">',
    '#markup' => theme('filter_tips_more_info'),
    '#suffix' => '</div>',
    '#weight' => 1,
  );

  return $form;
}

/**
 * Returns TRUE if the user is allowed to access this format.
 */
function filter_access($format) {
  $format = filter_resolve_format($format);
  if (user_access('administer filters') || ($format == variable_get('filter_default_format', 1))) {
    return TRUE;
  }
  else {
    $formats = filter_formats();
    return isset($formats[$format]);
  }
}

/**
 * @} End of "Filtering functions".
 */


/**
 * Helper function for fetching filter tips.
 */
function _filter_tips($format, $long = FALSE) {
  $formats = filter_formats();

  $tips = array();

  // If only listing one format, extract it from the $formats array.
  if ($format != -1) {
    $formats = array($formats[$format]);
  }

  foreach ($formats as $format) {
    $filters = filter_list_format($format->format);

    $tips[$format->name] = array();
    foreach ($filters as $id => $filter) {
      $filter_info = module_invoke($filter->module, 'filter_info');
      if (isset($filter_info[$filter->name]['tips callback']) && function_exists($filter_info[$filter->name]['tips callback'])) {
        $tip = call_user_func($filter_info[$filter->name]['tips callback'],$format->format, $long);
        $tips[$format->name][] = array('tip' => $tip, 'id' => $id);
      }
    }
  }

  return $tips;
}

/**
 * Parses an HTML snippet and returns it as a DOM object.
 *
 * This function loads the body part of a partial (X)HTML document
 * and returns a full DOMDocument object that represents this document.
 * You can use filter_dom_serialize() to serialize this DOMDocument
 * back to a XHTML snippet.
 *
 * @param $text
 *   The partial (X)HTML snippet to load. Invalid mark-up
 *   will be corrected on import.
 * @return
 *   A DOMDocument that represents the loaded (X)HTML snippet.
 */
function filter_dom_load($text) {
  // Ignore warnings during HTML soup loading.
  $dom_document = @DOMDocument::loadHTML('<html><head><meta http-equiv="Content-Type" content="text/html; charset=utf-8" /></head><body>' . $text . '</body></html>');

  return $dom_document;
}

/**
 * Converts a DOM object back to an HTML snippet.
 *
 * The function serializes the body part of a DOMDocument
 * back to an XHTML snippet.
 *
 * The resulting XHTML snippet will be properly formatted
 * to be compatible with HTML user agents.
 *
 * @param $dom_document
 *   A DOMDocument object to serialize, only the tags below
 *   the first <body> node will be converted.
 * @return
 *   A valid (X)HTML snippet, as a string.
 */
function filter_dom_serialize($dom_document) {
  $body_node = $dom_document->getElementsByTagName('body')->item(0);
  $body_content = '';
  foreach ($body_node->childNodes as $child_node) {
    $body_content .= $dom_document->saveXML($child_node);
  }
  return preg_replace('|<([^>]*)/>|i', '<$1 />', $body_content);
}

/**
 * Format a link to the more extensive filter tips.
 *
 * @ingroup themeable
 */
function theme_filter_tips_more_info() {
  return '<p>' . l(t('More information about text formats'), 'filter/tips') . '</p>';
}

/**
 * Format guidelines for a text format.
 *
 * @ingroup themeable
 */
function theme_filter_guidelines($format) {
  $name = isset($format->name) ? '<label>' . $format->name . ':</label>' : '';
  return '<div id="filter-guidelines-' . $format->format . '" class="filter-guidelines-item">' . $name . theme('filter_tips', _filter_tips($format->format, FALSE)) . '</div>';
}

/**
 * @name Standard filters
 * @{
 * Filters implemented by the filter.module.
 */

function filter_filter_info() {
  $filters['filter_html'] = array(
    'title' => t('Limit allowed HTML tags'),
    'description' => t('Allows you to restrict the HTML tags the user can use. It will also remove harmful content such as JavaScript events, JavaScript URLs and CSS styles from those tags that are not removed.'),
    'process callback' => '_filter_html',
    'settings callback' => '_filter_html_settings',
    'tips callback'  => '_filter_html_tips'
  );
  $filters['filter_autop'] = array(
    'title' => t('Convert line breaks'),
    'description' => t('Converts line breaks into HTML (i.e. &lt;br&gt; and &lt;p&gt;) tags.'),
    'process callback' => '_filter_autop',
    'tips callback' => '_filter_autop_tips'
  );
  $filters['filter_url'] = array(
    'title' => t('Convert URLs into links'),
    'description' => t('Turns web and e-mail addresses into clickable links.'),
    'process callback' => '_filter_url',
    'settings callback' => '_filter_url_settings',
    'tips callback' => '_filter_url_tips'
  );
  $filters['filter_htmlcorrector'] = array(
    'title' =>  t('Correct broken HTML'),
    'description' => t('Corrects faulty and chopped off HTML in postings.'),
    'process callback' => '_filter_htmlcorrector',
  );
  $filters['filter_html_escape'] = array(
    'title' => t('Escape all HTML'),
    'description' => t('Escapes all HTML tags, so they will be visible instead of being effective.'),
    'process callback' => '_filter_html_escape',
    'tips callback' => '_filter_html_escape_tips'
  );
  return $filters;
}

/**
 * Settings for the HTML filter.
 */
function _filter_html_settings($format) {
  $form['filter_html'] = array(
    '#type' => 'fieldset',
    '#title' => t('HTML filter'),
    '#collapsible' => TRUE,
  );
  $form['filter_html']["allowed_html_$format"] = array(
    '#type' => 'textfield',
    '#title' => t('Allowed HTML tags'),
    '#default_value' => variable_get("allowed_html_$format", '<a> <em> <strong> <cite> <blockquote> <code> <ul> <ol> <li> <dl> <dt> <dd>'),
    '#size' => 64,
    '#maxlength' => 1024,
    '#description' => t('Specify a list of tags which should not be stripped. (Note that JavaScript event attributes are always stripped.)'),
  );
  $form['filter_html']["filter_html_help_$format"] = array(
    '#type' => 'checkbox',
    '#title' => t('Display HTML help'),
    '#default_value' => variable_get("filter_html_help_$format", 1),
    '#description' => t('If enabled, Drupal will display some basic HTML help in the long filter tips.'),
  );
  $form['filter_html']["filter_html_nofollow_$format"] = array(
    '#type' => 'checkbox',
    '#title' => t('Spam link deterrent'),
    '#default_value' => variable_get("filter_html_nofollow_$format", FALSE),
    '#description' => t('If enabled, Drupal will add rel="nofollow" to all links, as a measure to reduce the effectiveness of spam links. Note: this will also prevent valid links from being followed by search engines, therefore it is likely most effective when enabled for anonymous users.'),
  );
  return $form;
}

/**
 * HTML filter. Provides filtering of input into accepted HTML.
 */
function _filter_html($text, $format) {
  $allowed_tags = preg_split('/\s+|<|>/', variable_get("allowed_html_$format", '<a> <em> <strong> <cite> <blockquote> <code> <ul> <ol> <li> <dl> <dt> <dd>'), -1, PREG_SPLIT_NO_EMPTY);
  $text = filter_xss($text, $allowed_tags);

  if (variable_get("filter_html_nofollow_$format", FALSE)) {
    $html_dom = filter_dom_load($text);
    $links = $html_dom->getElementsByTagName('a');
    foreach($links as $link) {
      $link->setAttribute('rel', 'nofollow');
    }
    $text = filter_dom_serialize($html_dom);
  }

  return trim($text);
}

/**
 * Settings for URL filter.
 */
function _filter_url_settings($format) {
  $form['filter_urlfilter'] = array(
    '#type' => 'fieldset',
    '#title' => t('URL filter'),
    '#collapsible' => TRUE,
  );
  $form['filter_urlfilter']['filter_url_length_' . $format] = array(
    '#type' => 'textfield',
    '#title' => t('Maximum link text length'),
    '#default_value' => variable_get('filter_url_length_' . $format, 72),
    '#maxlength' => 4,
    '#description' => t('URLs longer than this number of characters will be truncated to prevent long strings that break formatting. The link itself will be retained; just the text portion of the link will be truncated.'),
  );
  return $form;
}

/**
 * URL filter. Automatically converts text web addresses (URLs, e-mail addresses,
 * ftp links, etc.) into hyperlinks.
 */
function _filter_url($text, $format) {
  // Pass length to regexp callback
  _filter_url_trim(NULL, variable_get('filter_url_length_' . $format, 72));

  $text = ' ' . $text . ' ';

  // Match absolute URLs.
  $text = preg_replace_callback("`(<p>|<li>|<br\s*/?>|[ \n\r\t\(])((http://|https://|ftp://|mailto:|smb://|afp://|file://|gopher://|news://|ssl://|sslv2://|sslv3://|tls://|tcp://|udp://)([a-zA-Z0-9@:%_+*~#?&=.,/;-]*[a-zA-Z0-9@:%_+*~#&=/;-]))([.,?!]*?)(?=(</p>|</li>|<br\s*/?>|[ \n\r\t\)]))`i", '_filter_url_parse_full_links', $text);

  // Match e-mail addresses.
  $text = preg_replace("`(<p>|<li>|<br\s*/?>|[ \n\r\t\(])([A-Za-z0-9._-]+@[A-Za-z0-9._+-]+\.[A-Za-z]{2,4})([.,?!]*?)(?=(</p>|</li>|<br\s*/?>|[ \n\r\t\)]))`i", '\1<a href="mailto:\2">\2</a>\3', $text);

  // Match www domains/addresses.
  $text = preg_replace_callback("`(<p>|<li>|[ \n\r\t\(])(www\.[a-zA-Z0-9@:%_+*~#?&=.,/;-]*[a-zA-Z0-9@:%_+~#\&=/;-])([.,?!]*?)(?=(</p>|</li>|<br\s*/?>|[ \n\r\t\)]))`i", '_filter_url_parse_partial_links', $text);
  $text = substr($text, 1, -1);

  return $text;
}

/**
 * Scan input and make sure that all HTML tags are properly closed and nested.
 */
function _filter_htmlcorrector($text) {
  return filter_dom_serialize(filter_dom_load($text));
}

/**
 * Make links out of absolute URLs.
 */
function _filter_url_parse_full_links($match) {
  $match[2] = decode_entities($match[2]);
  $caption = check_plain(_filter_url_trim($match[2]));
  $match[2] = check_url($match[2]);
  return $match[1] . '<a href="' . $match[2] . '" title="' . $match[2] . '">' . $caption . '</a>' . $match[5];
}

/**
 * Make links out of domain names starting with "www."
 */
function _filter_url_parse_partial_links($match) {
  $match[2] = decode_entities($match[2]);
  $caption = check_plain(_filter_url_trim($match[2]));
  $match[2] = check_plain($match[2]);
  return $match[1] . '<a href="http://' . $match[2] . '" title="' . $match[2] . '">' . $caption . '</a>' . $match[3];
}

/**
 * Shortens long URLs to http://www.example.com/long/url...
 */
function _filter_url_trim($text, $length = NULL) {
  static $_length;
  if ($length !== NULL) {
    $_length = $length;
  }

  // Use +3 for '...' string length.
  if (strlen($text) > $_length + 3) {
    $text = substr($text, 0, $_length) . '...';
  }

  return $text;
}

/**
 * Convert line breaks into <p> and <br> in an intelligent fashion.
 * Based on: http://photomatt.net/scripts/autop
 */
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($tag) = preg_split('/[ >]/', substr($chunk, 2 - $open), 2);
      if (!$ignore) {
        if ($open) {
          $ignore = TRUE;
          $ignoretag = $tag;
        }
      }
      // Only allow a matching tag to close it.
      elseif (!$open && $ignoretag == $tag) {
        $ignore = FALSE;
        $ignoretag = '';
      }
    }
    elseif (!$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
      $chunk = preg_replace('/^\n|\n\s*\n$/', '', $chunk);
      $chunk = '<p>' . preg_replace('/\n\s*\n\n?(.)/', "</p>\n<p>$1", $chunk) . "</p>\n"; // make paragraphs, including one at the end
      $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*</p>\n?|', '', $chunk); // under certain strange conditions it could create a P of entirely whitespace
      $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;
}

/**
 * @} End of "Standard filters".
 */