1. ')) { switch ($long) { case 0: return t('Allowed HTML tags: @tags', array('@tags' => $allowed_html)); case 1: $output = '

   ' . t('Allowed HTML tags: @tags', array('@tags' => $allowed_html)) . '

   '; if (!variable_get("filter_html_help_$format", 1)) { return $output; } $output .= '

   ' . 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.') . '

   '; $output .= '

   ' . t('For more information see W3C\'s HTML Specifications or use your favorite search engine to find other sites that explain HTML.', array('@html-specifications' => 'http://www.w3.org/TR/html/')) . '

   '; $tips = array( 'a' => array( t('Anchors are used to make links to other pages.'), '' . variable_get('site_name', 'Drupal') . ''), '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
   line break')), 'p' => array( t('By default paragraph tags are automatically added, so use this tag to add additional ones.'), '

   ' . t('Paragraph one.') . '

   ' . t('Paragraph two.') . '

   '), 'strong' => array( t('Strong'), '' . t('Strong') . ''), 'em' => array( t('Emphasized'), '' . t('Emphasized') . ''), 'cite' => array( t('Cited'), '' . t('Cited') . ''), 'code' => array( t('Coded text used to show programming source code'), '' . t('Coded') . ''), 'b' => array( t('Bolded'), '' . t('Bolded') . ''), 'u' => array( t('Underlined'), '' . t('Underlined') . ''), 'i' => array( t('Italicized'), '' . t('Italicized') . ''), 'sup' => array( t('Superscripted'), t('^Superscripted')), 'sub' => array( t('Subscripted'), t('_Subscripted')), 'pre' => array( t('Preformatted'), '

   ' . t('Preformatted') . '

   '), 'abbr' => array( t('Abbreviation'), t('Abbrev.')), 'acronym' => array( t('Acronym'), t('TLA')), 'blockquote' => array( t('Block quoted'), '

   ' . t('Block quoted') . '

   '), 'q' => array( t('Quoted inline'), '' . t('Quoted inline') . ''), // Assumes and describes tr, td, th. 'table' => array( t('Table'), '

   ' . t('Table header') . '
   ' . t('Table cell') . '

   '), 'tr' => NULL, 'td' => NULL, 'th' => NULL, 'del' => array( t('Deleted'), '' . t('Deleted') . ''), 'ins' => array( t('Inserted'), '' . t('Inserted') . ''), // Assumes and describes li. 'ol' => array( t('Ordered list - use the <li> to begin each list item'), '

   1. ' . t('First item') . '
   2. ' . t('Second item') . '

   '), 'ul' => array( t('Unordered list - use the <li> to begin each list item'), '

   • ' . t('First item') . '
   • ' . t('Second item') . '

   '), 'li' => NULL, // Assumes and describes dt and dd. 'dl' => array( t('Definition lists are similar to other HTML lists. <dl> begins the definition list, <dt> begins the definition term and <dd> begins the definition description.'), '

   ' . t('First term') . '

   ' . t('First definition') . '

   ' . t('Second term') . '

   ' . t('Second definition') . '

   '), 'dt' => NULL, 'dd' => NULL, 'h1' => array( t('Heading'), '

   ' . t('Title') . '

   '), 'h2' => array( t('Heading'), '

   ' . t('Subtitle') . '

   '), 'h3' => array( t('Heading'), '

   ' . t('Subtitle three') . '

   '), 'h4' => array( t('Heading'), '

   ' . t('Subtitle four') . '

   '), 'h5' => array( t('Heading'), '

   ' . t('Subtitle five') . '

   '), 'h6' => array( t('Heading'), '

   ' . t('Subtitle six') . '

   ') ); $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' => 'description'), array('data' => '' . check_plain($tips[$tag][1]) . '', 'class' => 'type'), array('data' => $tips[$tag][1], 'class' => 'get') ); } } else { $rows[] = array( array('data' => t('No help provided for tag %tag.', array('%tag' => $tag)), 'class' => 'description', 'colspan' => 3), ); } } $output .= theme('table', $header, $rows); $output .= '

   ' . t('Most unusual characters can be directly entered without any problems.') . '

   '; $output .= '

   ' . t('If you do encounter problems, try using HTML character entities. A common example looks like &amp; for an ampersand & character. For a full list of entities see HTML\'s entities page. Some of the available characters include:', array('@html-entities' => 'http://www.w3.org/TR/html4/sgml/entities.html')) . '

   '; $entities = array( array( t('Ampersand'), '&'), array( t('Greater than'), '>'), array( t('Less than'), '<'), array( t('Quotation mark'), '"'), ); $header = array(t('Character Description'), t('You Type'), t('You Get')); unset($rows); foreach ($entities as $entity) { $rows[] = array( array('data' => $entity[0], 'class' => 'description'), array('data' => '' . check_plain($entity[1]) . '', 'class' => 'type'), array('data' => $entity[1], 'class' => 'get') ); } $output .= theme('table', $header, $rows); return $output; } } break; case 1: switch ($long) { case 0: return t('Lines and paragraphs break automatically.'); case 1: return t('Lines and paragraphs are automatically recognized. The <br /> line break, <p> paragraph and </p> close paragraph tags are inserted automatically. If paragraphs are not recognized simply add a couple blank lines.'); } break; case 2: return t('Web page addresses and e-mail addresses turn into links automatically.'); break; case 4: return t('No HTML tags allowed'); break; } } /** * Retrieve a list of input formats. */ function filter_formats($index = NULL) { global $user; static $formats; // Administrators can always use all input 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') as $module) { $function = $module . '_filter'; $list = $function('list'); if (isset($list) && is_array($list)) { foreach ($list as $delta => $name) { $filters[$module . '/' . $delta] = (object)array('module' => $module, 'delta' => $delta, '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) : $format; } /** * Check if text in a certain input format is allowed to be cached. */ function filter_format_allowcache($format) { static $cache = array(); $format = filter_resolve_format($format); if (!isset($cache[$format])) { $cache[$format] = db_result(db_query('SELECT cache FROM {filter_format} WHERE format = %d', $format)); } 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 = %d ORDER BY weight, module, delta", $format); while ($filter = db_fetch_object($result)) { $list = module_invoke($filter->module, 'filter', 'list'); if (isset($list) && is_array($list) && isset($list[$filter->delta])) { $filter->name = $list[$filter->delta]; $filters[$format][$filter->module . '/' . $filter->delta] = $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 $check * Whether to check the $format with filter_access() first. Defaults to TRUE. * Note that this will check the permissions of the current user, so you * should specify $check = FALSE when viewing other people's content. When * showing content that is not (yet) stored in the database (eg. upon preview), * set to TRUE so the user's permissions are checked. */ function check_markup($text, $format = FILTER_FORMAT_DEFAULT, $langcode = '', $check = TRUE) { // When $check = TRUE, do an access check on $format. if (isset($text) && (!$check || filter_access($format))) { $format = filter_resolve_format($format); // Check for a cached version of this piece of text. $cache_id = $format . ':' . $langcode . ':' . md5($text); if ($cached = cache_get($cache_id, 'cache_filter')) { return $cached->data; } // See if caching is allowed for this format. $cache = filter_format_allowcache($format); // 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) { $text = module_invoke($filter->module, 'filter', 'prepare', $filter->delta, $format, $text, $langcode, $cache_id); } // Perform filtering. foreach ($filters as $filter) { $text = module_invoke($filter->module, 'filter', 'process', $filter->delta, $format, $text, $langcode, $cache_id); } // Store in cache with a minimum expiration time of 1 day. if ($cache) { 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 * @see filter_form_validate() * @param $value * The ID of the format that is currently selected. * @param $weight * The weight of the input format. * @param $parents * Required when defining multiple input formats on a single node or having a different parent than 'format'. * @return * HTML for the form element. */ function filter_form($value = FILTER_FORMAT_DEFAULT, $weight = NULL, $parents = array('format')) { $value = filter_resolve_format($value); $formats = filter_formats(); $extra = theme('filter_tips_more_info'); if (count($formats) > 1) { $form = array( '#type' => 'fieldset', '#title' => t('Input format'), '#collapsible' => TRUE, '#collapsed' => TRUE, '#weight' => $weight, '#element_validate' => array('filter_form_validate'), ); // Multiple formats available: display radio buttons with tips. foreach ($formats as $format) { // Generate the parents as the autogenerator does, so we will have a // unique id for each radio button. $parents_for_id = array_merge($parents, array($format->format)); $form[$format->format] = array( '#type' => 'radio', '#title' => $format->name, '#default_value' => $value, '#return_value' => $format->format, '#parents' => $parents, '#description' => theme('filter_tips', _filter_tips($format->format, FALSE)), '#id' => form_clean_id('edit-' . implode('-', $parents_for_id)), ); } } else { // Only one format available: use a hidden form item and only show tips. $format = array_shift($formats); $form[$format->format] = array('#type' => 'value', '#value' => $format->format, '#parents' => $parents); $tips = _filter_tips(variable_get('filter_default_format', 1), FALSE); $form['format']['guidelines'] = array( '#title' => t('Formatting guidelines'), '#markup' => theme('filter_tips', $tips, FALSE), ); } $form[] = array('#markup' => $extra); return $form; } function filter_form_validate($form) { foreach (element_children($form) as $key) { if ($form[$key]['#value'] == $form[$key]['#return_value']) { return; } } form_error($form, t('An illegal choice has been detected. Please contact the site administrator.')); watchdog('form', 'Illegal choice %choice in %name element.', array('%choice' => $form[$key]['#value'], '%name' => empty($form['#title']) ? $form['#parents'][0] : $form['#title']), WATCHDOG_ERROR); } /** * Returns TRUE if the user is allowed to access this format. */ function filter_access($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, $long = FALSE) { if ($format == -1) { $formats = filter_formats(); } else { $formats = array(db_fetch_object(db_query("SELECT * FROM {filter_format} WHERE format = %d", $format))); } $tips = array(); foreach ($formats as $format) { $filters = filter_list_format($format->format); $tips[$format->name] = array(); foreach ($filters as $id => $filter) { if ($tip = module_invoke($filter->module, 'filter_tips', $filter->delta, $format->format, $long)) { $tips[$format->name][] = array('tip' => $tip, 'id' => $id); } } } return $tips; } /** * Format a link to the more extensive filter tips. * * @ingroup themeable */ function theme_filter_tips_more_info() { return '

   ' . l(t('More information about formatting options'), 'filter/tips') . '

   '; } /** * @name Standard filters * @{ * Filters implemented by the filter.module. */ /** * Implementation of hook_filter(). Contains a basic set of essential filters. * - HTML filter: * Validates user-supplied HTML, transforming it as necessary. * - Line break converter: * Converts newlines into paragraph and break tags. * - URL and e-mail address filter: * Converts newlines into paragraph and break tags. */ function filter_filter($op, $delta = 0, $format = -1, $text = '') { switch ($op) { case 'list': return array(0 => t('Limit allowed HTML tags'), 1 => t('Convert line breaks'), 2 => t('Convert URLs into links'), 3 => t('Correct broken HTML'), 4 => t('Escape all HTML')); case 'description': switch ($delta) { case 0: return t('Allows you to restrict the HTML tags the user can use. It will also remove harmful content such as JavaScript events, JavaScript URLs and CSS styles from those tags that are not removed.'); case 1: return t('Converts line breaks into HTML (i.e. <br> and <p>) tags.'); case 2: return t('Turns web and e-mail addresses into clickable links.'); case 3: return t('Corrects faulty and chopped off HTML in postings.'); case 4: return t('Escapes all HTML tags, so they will be visible instead of being effective.'); default: return; } case 'process': switch ($delta) { case 0: return _filter_html($text, $format); case 1: return _filter_autop($text); case 2: return _filter_url($text, $format); case 3: return _filter_htmlcorrector($text); case 4: return trim(check_plain($text)); default: return $text; } case 'settings': switch ($delta) { case 0: return _filter_html_settings($format); case 2: return _filter_url_settings($format); default: return; } default: return $text; } } /** * Settings for the HTML filter. */ function _filter_html_settings($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", '

   1. '), '#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", '

      1. '), -1, PREG_SPLIT_NO_EMPTY); $text = filter_xss($text, $allowed_tags); if (variable_get("filter_html_nofollow_$format", FALSE)) { $text = preg_replace('/]+)>/i', '', $text); } return trim($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("`(

         |

         ||[ \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@:%_+*~#&=/;-]))([.,?!]*?)(?=(

         |

         ||[ \n\r\t\)]))`i", '_filter_url_parse_full_links', $text); // Match e-mail addresses. $text = preg_replace("`(

         |

         ||[ \n\r\t\(])([A-Za-z0-9._-]+@[A-Za-z0-9._+-]+\.[A-Za-z]{2,4})([.,?!]*?)(?=(

         |

         ||[ \n\r\t\)]))`i", '\1\2\3', $text); // Match www domains/addresses. $text = preg_replace_callback("`(

         |

         |[ \n\r\t\(])(www\.[a-zA-Z0-9@:%_+*~#?&=.,/;-]*[a-zA-Z0-9@:%_+~#\&=/;-])([.,?!]*?)(?=(

         |

         ||[ \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) { // Prepare tag lists. static $no_nesting, $single_use; if (!isset($no_nesting)) { // Tags which cannot be nested but are typically left unclosed. $no_nesting = drupal_map_assoc(array('li', 'p')); // Single use tags in HTML4 $single_use = drupal_map_assoc(array('base', 'meta', 'link', 'hr', 'br', 'param', 'img', 'area', 'input', 'col', 'frame')); } // Properly entify angles. $text = preg_replace('!<([^a-zA-Z/])!', '<\1', $text); // Split tags from text. $split = preg_split('/<([^>]+?)>/', $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). $tag = FALSE; // Odd/even counter. Tag or no tag. $stack = array(); $output = ''; foreach ($split as $value) { // Process HTML tags. if ($tag) { list($tagname) = explode(' ', strtolower($value), 2); // Closing tag if ($tagname{0} == '/') { $tagname = substr($tagname, 1); // Discard XHTML closing tags for single use tags. if (!isset($single_use[$tagname])) { // See if we possibly have a matching opening tag on the stack. if (in_array($tagname, $stack)) { // Close other tags lingering first. do { $output .= ''; } while (array_shift($stack) != $tagname); } // Otherwise, discard it. } } // Opening tag else { // See if we have an identical 'no nesting' tag already open and close it if found. if (count($stack) && ($stack[0] == $tagname) && isset($no_nesting[$stack[0]])) { $output .= ''; } // Push non-single-use tags onto the stack if (!isset($single_use[$tagname])) { array_unshift($stack, $tagname); } // Add trailing slash to single-use tags as per X(HT)ML. else { $value = rtrim($value, ' /') . ' /'; } $output .= '<' . $value . '>'; } } else { // Passthrough all text. $output .= $value; } $tag = !$tag; } // Close remaining tags. while (count($stack) > 0) { $output .= ''; } return $output; } /** * Make links out of absolute URLs. */ function _filter_url_parse_full_links($match) { $match[2] = decode_entities($match[2]); $caption = check_plain(_filter_url_trim($match[2])); $match[2] = check_url($match[2]); return $match[1] . '' . $caption . '' . $match[5]; } /** * Make links out of domain names starting with "www." */ function _filter_url_parse_partial_links($match) { $match[2] = decode_entities($match[2]); $caption = check_plain(_filter_url_trim($match[2])); $match[2] = check_plain($match[2]); return $match[1] . '' . $caption . '' . $match[3]; } /** * Shortens long URLs to http://www.example.com/long/url... */ function _filter_url_trim($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

         and
         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

         , ,  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 
          ignored  ignored 
          processed"
           $chunks = preg_split('@(]*>)@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('|
         \s*
         |', "\n\n", $chunk);
               $chunk = preg_replace('!(<' . $block . '[^>]*>)!', "\n$1", $chunk); // Space things out a little
               $chunk = preg_replace('!()!', "$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', "
         $1
         \n", $chunk); // make paragraphs, including one at the end
               $chunk = preg_replace("|
         (|", "$1", $chunk); // problem with nested lists
               $chunk = preg_replace('|
         ]*)>|i', "
         ", $chunk);
               $chunk = str_replace('

      ', '

   ', $chunk); $chunk = preg_replace('|

   \s*

   \n?|', '', $chunk); // under certain strange conditions it could create a P of entirely whitespace $chunk = preg_replace('!

   \s*(]*>)!', "$1", $chunk); $chunk = preg_replace('!(]*>)\s*

   !', "$1", $chunk); $chunk = preg_replace('|(?)\s*\n|', "
   \n", $chunk); // make line breaks $chunk = preg_replace('!(]*>)\s*
   !', "$1", $chunk); $chunk = preg_replace('!
   (\s*)!', '$1', $chunk); $chunk = preg_replace('/&([^#])(?![A-Za-z0-9]{1,8};)/', '&$1', $chunk); } $output .= $chunk; } return $output; } /** * Very permissive XSS/HTML filter for admin-only use. * * Use only for fields where it is impractical to use the * whole filter system, but where some (mainly inline) mark-up * is desired (so check_plain() is not acceptable). * * Allows all tags that can be used inside an HTML body, save * for scripts and styles. */ function filter_xss_admin($string) { return filter_xss($string, array('a', 'abbr', 'acronym', 'address', 'b', 'bdo', 'big', 'blockquote', 'br', 'caption', 'cite', 'code', 'col', 'colgroup', 'dd', 'del', 'dfn', 'div', 'dl', 'dt', 'em', 'h1', 'h2', 'h3', 'h4', 'h5', 'h6', 'hr', 'i', 'img', 'ins', 'kbd', 'li', 'ol', 'p', 'pre', 'q', 'samp', 'small', 'span', 'strong', 'sub', 'sup', 'table', 'tbody', 'td', 'tfoot', 'th', 'thead', 'tr', 'tt', 'ul', 'var')); } /** * Filters XSS. Based on kses by Ulf Harnhammar, see * http://sourceforge.net/projects/kses * * For examples of various XSS attacks, see: * http://ha.ckers.org/xss.html * * This code does four things: * - Removes characters and constructs that can trick browsers * - Makes sure all HTML entities are well-formed * - Makes sure all HTML tags and attributes are well-formed * - Makes sure no HTML tags contain URLs with a disallowed protocol (e.g. javascript:) * * @param $string * The string with raw HTML in it. It will be stripped of everything that can cause * an XSS attack. * @param $allowed_tags * An array of allowed tags. */ function filter_xss($string, $allowed_tags = array('a', 'em', 'strong', 'cite', 'blockquote', 'code', 'ul', 'ol', 'li', 'dl', 'dt', 'dd')) { // Only operate on valid UTF-8 strings. This is necessary to prevent cross // site scripting issues on Internet Explorer 6. if (!drupal_validate_utf8($string)) { return ''; } // Store the input format _filter_xss_split($allowed_tags, TRUE); // Remove NULL characters (ignored by some browsers) $string = str_replace(chr(0), '', $string); // Remove Netscape 4 JS entities $string = preg_replace('%&\s*\{[^}]*(\}\s*;?|$)%', '', $string); // Defuse all HTML entities $string = str_replace('&', '&', $string); // Change back only well-formed entities in our whitelist // Named entities $string = preg_replace('/&([A-Za-z][A-Za-z0-9]*;)/', '&\1', $string); // Decimal numeric entities $string = preg_replace('/&#([0-9]+;)/', '&#\1', $string); // Hexadecimal numeric entities $string = preg_replace('/&#[Xx]0*((?:[0-9A-Fa-f]{2})+;)/', '&#x\1', $string); return preg_replace_callback('% ( <(?=[^a-zA-Z!/]) # a lone < | # or <[^>]*(>|$) # a string that starts with a <, up until the > or the end of the string | # or > # just a > )%x', '_filter_xss_split', $string); } /** * Processes an HTML tag. * * @param $m * An array with various meaning depending on the value of $store. * If $store is TRUE then the array contains the allowed tags. * If $store is FALSE then the array has one element, the HTML tag to process. * @param $store * Whether to store $m. * @return * If the element isn't allowed, an empty string. Otherwise, the cleaned up * version of the HTML element. */ function _filter_xss_split($m, $store = FALSE) { static $allowed_html; if ($store) { $allowed_html = array_flip($m); return; } $string = $m[1]; if (substr($string, 0, 1) != '<') { // We matched a lone ">" character return '>'; } elseif (strlen($string) == 1) { // We matched a lone "<" character return '<'; } if (!preg_match('%^<\s*(/\s*)?([a-zA-Z0-9]+)([^>]*)>?$%', $string, $matches)) { // Seriously malformed return ''; } $slash = trim($matches[1]); $elem = &$matches[2]; $attrlist = &$matches[3]; if (!isset($allowed_html[strtolower($elem)])) { // Disallowed HTML element return ''; } if ($slash != '') { return ""; } // Is there a closing XHTML slash at the end of the attributes? $attrlist = preg_replace('%(\s?)/\s*$%', '\1', $attrlist, -1, $count); $xhtml_slash = $count ? ' /' : ''; // Clean up attributes $attr2 = implode(' ', _filter_xss_attributes($attrlist)); $attr2 = preg_replace('/[<>]/', '', $attr2); $attr2 = strlen($attr2) ? ' ' . $attr2 : ''; return "<$elem$attr2$xhtml_slash>"; } /** * Processes a string of HTML attributes. * * @return * Cleaned up version of the HTML attributes. */ function _filter_xss_attributes($attr) { $attrarr = array(); $mode = 0; $attrname = ''; while (strlen($attr) != 0) { // Was the last operation successful? $working = 0; switch ($mode) { case 0: // Attribute name, href for instance if (preg_match('/^([-a-zA-Z]+)/', $attr, $match)) { $attrname = strtolower($match[1]); $skip = ($attrname == 'style' || substr($attrname, 0, 2) == 'on'); $working = $mode = 1; $attr = preg_replace('/^[-a-zA-Z]+/', '', $attr); } break; case 1: // Equals sign or valueless ("selected") if (preg_match('/^\s*=\s*/', $attr)) { $working = 1; $mode = 2; $attr = preg_replace('/^\s*=\s*/', '', $attr); break; } if (preg_match('/^\s+/', $attr)) { $working = 1; $mode = 0; if (!$skip) { $attrarr[] = $attrname; } $attr = preg_replace('/^\s+/', '', $attr); } break; case 2: // Attribute value, a URL after href= for instance if (preg_match('/^"([^"]*)"(\s+|$)/', $attr, $match)) { $thisval = filter_xss_bad_protocol($match[1]); if (!$skip) { $attrarr[] = "$attrname=\"$thisval\""; } $working = 1; $mode = 0; $attr = preg_replace('/^"[^"]*"(\s+|$)/', '', $attr); break; } if (preg_match("/^'([^']*)'(\s+|$)/", $attr, $match)) { $thisval = filter_xss_bad_protocol($match[1]); if (!$skip) { $attrarr[] = "$attrname='$thisval'"; } $working = 1; $mode = 0; $attr = preg_replace("/^'[^']*'(\s+|$)/", '', $attr); break; } if (preg_match("%^([^\s\"']+)(\s+|$)%", $attr, $match)) { $thisval = filter_xss_bad_protocol($match[1]); if (!$skip) { $attrarr[] = "$attrname=\"$thisval\""; } $working = 1; $mode = 0; $attr = preg_replace("%^[^\s\"']+(\s+|$)%", '', $attr); } break; } if ($working == 0) { // not well formed, remove and try again $attr = preg_replace('/ ^ ( "[^"]*("|$) # - a string that starts with a double quote, up until the next double quote or the end of the string | # or \'[^\']*(\'|$)| # - a string that starts with a quote, up until the next quote or the end of the string | # or \S # - a non-whitespace character )* # any number of the above three \s* # any number of whitespaces /x', '', $attr); $mode = 0; } } // the attribute list ends with a valueless attribute like "selected" if ($mode == 1) { $attrarr[] = $attrname; } return $attrarr; } /** * Processes an HTML attribute value and ensures it does not contain an URL * with a disallowed protocol (e.g. javascript:) * * @param $string * The string with the attribute value. * @param $decode * Whether to decode entities in the $string. Set to FALSE if the $string * is in plain text, TRUE otherwise. Defaults to TRUE. * @return * Cleaned up and HTML-escaped version of $string. */ function filter_xss_bad_protocol($string, $decode = TRUE) { static $allowed_protocols; if (!isset($allowed_protocols)) { $allowed_protocols = array_flip(variable_get('filter_allowed_protocols', array('ftp', 'http', 'https', 'irc', 'mailto', 'news', 'nntp', 'rtsp', 'sftp', 'ssh', 'telnet', 'webcal'))); } // Get the plain text representation of the attribute value (i.e. its meaning). if ($decode) { $string = decode_entities($string); } // Iteratively remove any invalid protocol found. do { $before = $string; $colonpos = strpos($string, ':'); if ($colonpos > 0) { // We found a colon, possibly a protocol. Verify. $protocol = substr($string, 0, $colonpos); // If a colon is preceded by a slash, question mark or hash, it cannot // possibly be part of the URL scheme. This must be a relative URL, // which inherits the (safe) protocol of the base document. if (preg_match('![/?#]!', $protocol)) { break; } // Per RFC2616, section 3.2.3 (URI Comparison) scheme comparison must be case-insensitive // Check if this is a disallowed protocol. if (!isset($allowed_protocols[strtolower($protocol)])) { $string = substr($string, $colonpos + 1); } } } while ($before != $string); return check_plain($string); } /** * @} End of "Standard filters". */