filter.module 53.3 KB
Newer Older
1 2 3
<?php
// $Id$

Dries's avatar
Dries committed
4 5 6 7 8
/**
 * @file
 * Framework for handling filtering of content.
 */

9 10 11
// This is a 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.
12 13
define('FILTER_FORMAT_DEFAULT', 0);

14 15 16
define('FILTER_HTML_STRIP', 1);
define('FILTER_HTML_ESCAPE', 2);

17 18 19 20
/**
 * Implementation of hook_help().
 */
function filter_help($section) {
21
  switch ($section) {
22 23 24 25 26 27 28 29 30
    case 'admin/help#filter':
      $output = '<p>'. t('The filter module allows administrators to configure  text input formats for the site.  For example, an administrator may want a filter to strip out malicious HTML from user\'s comments.  Administrators may also want to make URLs linkable even if they are only entered in an unlinked format.') .'</p>';
      $output .= '<p>'. t('Users can choose between the available input formats when creating or editing content.  Administrators can configure which input formats are available to which user roles, as well as choose a default input format.  Administrators can also create new input formats.  Each input format can be configured to use a selection of filters.') .'</p>';
      $output .= t('<p>You can</p>
<ul>
<li>administer input format permissions and settings  at <a href="%admin-filters">administer &gt;&gt; input formats</a>.</li>
<li>configure the filters for each input format at <a href="%admin-filters">administer &gt;&gt; input formats &gt;&gt; configure</a>.</li>
</ul>
', array('%admin-filters' => url('admin/filters')));
31
      $output .= '<p>'. t('For more information please read the configuration and customization handbook <a href="%filter">Filter page</a>.', array('%filter' => 'http://drupal.org/handbook/modules/filter/')) .'</p>';
32
      return $output;
Dries's avatar
Dries committed
33
    case 'admin/modules#description':
34
      return t('Handles the filtering of content in preparation for display.');
35

Dries's avatar
Dries committed
36
    case 'admin/filters':
37
      return t('
Dries's avatar
Dries committed
38
<p><em>Input formats</em> define a way of processing user-supplied text in Drupal. Every input format has its own settings of which <em>filters</em> to apply. Possible filters include stripping out malicious HTML and making URLs clickable.</p>
39
<p>Users can choose between the available input formats when submitting content.</p>
40 41
<p>Below you can configure which input formats are available to which roles, as well as choose a default input format (used for imported content, for example).</p>
<p>Note that (1) the default format is always available to all roles, and (2) all filter formats can always be used by roles with the "administer filters" permission even if they are not explicitly listed in the Roles column of this table.</p>');
42

43
    case 'admin/filters/'. arg(2):
44
      return t('
Dries's avatar
Dries committed
45
<p>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 input format.</p>
46
<p>If you notice some filters are causing conflicts in the output, you can <a href="%rearrange">rearrange them</a>.</p>', array('%rearrange' => url('admin/filters/'. arg(2) .'/order')));
47

48
    case 'admin/filters/'. arg(2) .'/configure':
49
      return t('
50
<p>If you cannot find the settings for a certain filter, make sure you\'ve enabled it on the <a href="%url">view tab</a> first.</p>', array('%url' => url('admin/filters/'. arg(2))));
51

52
    case 'admin/filters/'. arg(2) .'/order':
53
      return t('
Dries's avatar
Dries committed
54
<p>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 in a clickable link. When this happens, you will need to rearrange the order in which filters get executed.</p>
55 56 57 58
<p>Filters are executed from top-to-bottom. You can use the weight column to rearrange them: heavier filters \'sink\' to the bottom.</p>');
  }
}

59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145
/**
 * Implementation of hook_menu().
 */
function filter_menu($may_cache) {
  $items = array();

  if ($may_cache) {
    $items[] = array('path' => 'admin/filters',
      'title' => t('input formats'),
      'callback' => 'filter_admin_overview',
      'access' => user_access('administer filters'),
    );
    $items[] = array('path' => 'admin/filters/list',
      'title' => t('list'),
      'callback' => 'filter_admin_overview',
      'type' => MENU_DEFAULT_LOCAL_TASK,
      'access' => user_access('administer filters'),
    );
    $items[] = array('path' => 'admin/filters/add',
      'title' => t('add input format'),
      'callback' => 'filter_admin_format_form',
      'type' => MENU_LOCAL_TASK,
      'weight' => 1,
      'access' => user_access('administer filters'),
    );
    $items[] = array('path' => 'admin/filters/delete',
      'title' => t('delete input format'),
      'callback' => 'filter_admin_delete',
      'type' => MENU_CALLBACK,
      'access' => user_access('administer filters'),
    );
    $items[] = array('path' => 'filter/tips',
      'title' => t('compose tips'),
      'callback' => 'filter_tips_long',
      'access' => TRUE,
      'type' => MENU_SUGGESTED_ITEM,
    );
  }
  else {
    if (arg(0) == 'admin' && arg(1) == 'filters' && is_numeric(arg(2))) {
      $formats = filter_formats();

      if (isset($formats[arg(2)])) {
        $items[] = array('path' => 'admin/filters/'. arg(2),
          'title' => t("'%format' input format", array('%format' => $formats[arg(2)]->name)),
          'callback' => 'filter_admin_format_form',
          'callback arguments' => array('format' => $formats[arg(2)]),
          'type' => MENU_CALLBACK,
          'access' => user_access('administer filters'),
        );
        $items[] = array('path' => 'admin/filters/'. arg(2) .'/list',
          'title' => t('view'),
          'callback' => 'filter_admin_format_form',
          'callback arguments' => array('format' => $formats[arg(2)]),
          'type' => MENU_DEFAULT_LOCAL_TASK,
          'weight' => 0,
          'access' => user_access('administer filters'),
        );
        $items[] = array('path' => 'admin/filters/'. arg(2) .'/configure',
          'title' => t('configure'),
          'callback' => 'filter_admin_configure',
          'type' => MENU_LOCAL_TASK,
          'weight' => 1,
          'access' => user_access('administer filters'),
        );
        $items[] = array('path' => 'admin/filters/'. arg(2) .'/order',
          'title' => t('rearrange'),
          'callback' => 'filter_admin_order',
          'callback arguments' => array('format' => $formats[arg(2)]),
          'type' => MENU_LOCAL_TASK,
          'weight' => 2,
          'access' => user_access('administer filters'),
        );
      }
    }
  }

  return $items;
}

/**
 * Implementation of hook_perm().
 */
function filter_perm() {
  return array('administer filters');
}

146
/**
147
 * Implementation of hook_filter_tips().
148
 */
149
function filter_filter_tips($delta, $format, $long = false) {
150
  global $base_url;
151 152
  switch ($delta) {
    case 0:
153 154 155 156 157 158 159 160 161 162
      if (variable_get("filter_html_$format", FILTER_HTML_STRIP) ==  FILTER_HTML_STRIP) {
        if ($allowed_html = variable_get("allowed_html_$format", '<a> <em> <strong> <cite> <code> <ul> <ol> <li> <dl> <dt> <dd>')) {
          switch ($long) {
            case 0:
              return t('Allowed HTML tags') .': '. check_plain($allowed_html);
            case 1:
              $output = '<p>'. t('Allowed HTML tags') .': '. check_plain($allowed_html) .'</p>';
              if (!variable_get("filter_html_help_$format", 1)) {
                return $output;
              }
163

164
              $output .= t('
165
<p>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>
166
<p>For more information see W3C\'s <a href="http://www.w3.org/TR/html/">HTML Specifications</a> or use your favorite search engine to find other sites that explain HTML.</p>');
167 168 169 170 171 172 173 174 175 176 177 178 179 180
              $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>'),
181 182
                'abbr' => array( t('Abbreviation'), t('<abbr title="Abbreviation">Abbrev.</abbr>')),
                'acronym' => array( t('Acronym'), t('<acronym title="Three-Letter Acronym">TLA</acronym>')),
183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208
                '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('Header'), '<h1>'. t('Title') .'</h1>'),
                'h2' => array( t('Header'), '<h2>'. t('Subtitle') .'</h2>'),
                'h3' => array( t('Header'), '<h3>'. t('Subtitle three') .'</h3>'),
                'h4' => array( t('Header'), '<h4>'. t('Subtitle four') .'</h4>'),
                'h5' => array( t('Header'), '<h5>'. t('Subtitle five') .'</h5>'),
                'h6' => array( t('Header'), '<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]) {
209
                    $rows[] = array(
210 211 212
                      array('data' => $tips[$tag][0], 'class' => 'description'),
                      array('data' => '<code>'. check_plain($tips[$tag][1]) .'</code>', 'class' => 'type'),
                      array('data' => $tips[$tag][1], 'class' => 'get')
213 214 215
                    );
                  }
                }
216 217 218 219 220 221 222
                else {
                  $rows[] = array(
                    array('data' => t('No help provided for tag %tag.', array('%tag' => check_plain($tag))), 'class' => 'description', 'colspan' => 3),
                  );
                }
              }
              $output .= theme('table', $header, $rows);
223

224
              $output .= t('
225
<p>Most unusual characters can be directly entered without any problems.</p>
226
<p>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="http://www.w3.org/TR/html4/sgml/entities.html">entities</a> page. Some of the available characters include:</p>');
227 228 229 230 231 232 233 234 235 236 237 238 239
              $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' => $entity[0], 'class' => 'description'),
                  array('data' => '<code>'. check_plain($entity[1]) .'</code>', 'class' => 'type'),
                  array('data' => $entity[1], 'class' => 'get')
240
                );
241 242 243
              }
              $output .= theme('table', $header, $rows);
              return $output;
Dries's avatar
Dries committed
244
          }
245 246
        }
        else {
247
          return t('No HTML tags allowed');
248
        }
Dries's avatar
Dries committed
249 250
      }
      break;
251 252

    case 1:
Dries's avatar
Dries committed
253
      switch ($long) {
254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279
        case 0:
          return t('You may post PHP code. You should include &lt;?php ?&gt; tags.');
        case 1:
          return t('
<h4>Using custom PHP code</h4>
<p>If you know how to script in PHP, Drupal gives you the power to embed any script you like. It will be executed when the page is viewed and dynamically embedded into the page. This gives you amazing flexibility and power, but of course with that comes danger and insecurity if you don\'t write good code. If you are not familiar with PHP, SQL or with the site engine, avoid experimenting with PHP because you can corrupt your database or render your site insecure or even unusable! If you don\'t plan to do fancy stuff with your content then you\'re probably better off with straight HTML.</p>
<p>Remember that the code within each PHP item must be valid PHP code - including things like correctly terminating statements with a semicolon. It is highly recommended that you develop your code separately using a simple test script on top of a test database before migrating to your production environment.</p>
<p>Notes:</p><ul><li>You can use global variables, such as configuration parameters, within the scope of your PHP code but remember that global variables which have been given values in your code will retain these values in the engine afterwards.</li><li>register_globals is now set to <strong>off</strong> by default. If you need form information you need to get it from the "superglobals" $_POST, $_GET, etc.</li><li>You can either use the <code>print</code> or <code>return</code> statement to output the actual content for your item.</li></ul>
<p>A basic example:</p>
<blockquote><p>You want to have a box with the title "Welcome" that you use to greet your visitors. The content for this box could be created by going:</p>
<pre>
  print t("Welcome visitor, ... welcome message goes here ...");
</pre>
<p>If we are however dealing with a registered user, we can customize the message by using:</p>
<pre>
  global $user;
  if ($user->uid) {
    print t("Welcome $user->name, ... welcome message goes here ...");
  }
  else {
    print t("Welcome visitor, ... welcome message goes here ...");
  }
</pre></blockquote>
<p>For more in-depth examples, we recommend that you check the existing Drupal code and use it as a starting point, especially for sidebar boxes.</p>');
      }

280
    case 2:
281 282 283 284 285 286
      switch ($long) {
        case 0:
          return t('Lines and paragraphs break automatically.');
        case 1:
          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.');
      }
287 288 289
  }
}

290
/**
291
 * Displays a list of all input formats and which one is the default
292 293
 */
function filter_admin_overview() {
294

295
  // Overview of all formats.
296 297 298 299 300
  $formats = filter_formats();
  $error = false;

  $rows = array();
  foreach ($formats as $id => $format) {
301 302
    $roles = array();
    foreach (user_roles() as $rid => $name) {
303
      // Prepare a roles array with roles that may access the filter
304
      if (strstr($format->roles, ",$rid,")) {
305 306 307
        $roles[] = $name;
      }
    }
308 309
    $row = array();
    $default = ($id == variable_get('filter_default_format', 1));
310
    $options[$id] = '';
311 312 313 314
    $form[$format->name]['id'] = array('#value' => $id);
    $form[$format->name]['roles'] = array('#value' => $default ? t('All roles may use default format') : ($roles ? implode(', ',$roles) : t('No roles may use this format')));
    $form[$format->name]['configure'] = array('#value' => l(t('configure'), 'admin/filters/'. $id));
    $form[$format->name]['delete'] = array('#value' => $default ? '' : l(t('delete'), 'admin/filters/delete/'. $id));
315
  }
316 317
  $form['default'] = array('#type' => 'radios', '#options' => $options, '#default_value' => variable_get('filter_default_format', 1));
  $form['submit'] = array('#type' => 'submit', '#value' => t('Set default format'));
318 319
  return drupal_get_form('filter_admin_overview', $form);
}
320

321 322 323 324 325 326 327 328
function filter_admin_overview_submit($form_id, $form_values) {
  // Process form submission to set the default format
  if (is_numeric($form_values['default'])) {
    drupal_set_message(t('Default format updated.'));
    variable_set('filter_default_format', $form_values['default']);
  }
}

329 330 331 332
function theme_filter_admin_overview($form) {
  foreach ($form as $name => $element) {
    if (isset($element['roles']) && is_array($element['roles'])) {
      $rows[] = array(
333
        form_render($form['default'][$element['id']['#value']]),
334
        check_plain($name),
335 336 337 338 339 340 341 342 343 344
        form_render($element['roles']),
        form_render($element['configure']),
        form_render($element['delete'])
      );
      unset($form[$name]);
    }
  }
  $header = array(t('Default'), t('Name'), t('Roles'), array('data' => t('Operations'), 'colspan' => 2));
  $output = theme('table', $header, $rows);
  $output .= form_render($form);
345

Dries's avatar
Dries committed
346
  return $output;
347 348 349
}

/**
350
 * Menu callback; confirm deletion of a format.
351 352 353 354 355
 */
function filter_admin_delete() {
  $format = arg(3);
  $format = db_fetch_object(db_query('SELECT * FROM {filter_formats} WHERE format = %d', $format));

356 357 358 359
  if ($format) {
    if ($format->format != variable_get('filter_default_format', 1)) {
      $form['format'] = array('#type' => 'hidden', '#value' => $format->format);
      $form['name'] = array('#type' => 'hidden', '#value' => $format->name);
360

361 362 363 364 365 366 367 368 369 370
      return confirm_form('filter_admin_delete', $form, t('Are you sure you want to delete the input format %format?', array('%format' => theme('placeholder', $format->name))), 'admin/filters', t('If you have any content left in this input format, it will be switched to the default input format. This action cannot be undone.'), t('Delete'), t('Cancel'));
    }
    else {
      drupal_set_message('The default format cannot be deleted.');
      drupal_goto('admin/filters');
    }
  }
  else {
    drupal_not_found();
  }
371 372 373
}

/**
374
 * Process filter delete form submission.
375
 */
376 377 378
function filter_admin_delete_submit($form_id, $form_values) {
  db_query("DELETE FROM {filter_formats} WHERE format = %d", $form_values['format']);
  db_query("DELETE FROM {filters} WHERE format = %d", $form_values['format']);
379

380 381 382 383 384
  $default = variable_get('filter_default_format', 1);
  // Replace existing instances of the deleted format with the default format.
  db_query("UPDATE {node_revisions} SET format = %d WHERE format = %d", $default, $form_values['format']);
  db_query("UPDATE {comments} SET format = %d WHERE format = %d", $default, $form_values['format']);
  db_query("UPDATE {boxes} SET format = %d WHERE format = %d", $default, $form_values['format']);
385

386 387
  cache_clear_all('filter:'. $form_values['format'], true);
  drupal_set_message(t('Deleted input format %format.', array('%format' => theme('placeholder', $form_values['name']))));
388

389
  return 'admin/filters';
390 391
}

392
/**
393
 * Generate a filter format form.
394
 */
395
function filter_admin_format_form($format = NULL) {
396
  $default = ($format->format == variable_get('filter_default_format', 1));
397 398
  if ($default) {
    $help = t('All roles for the default format must be enabled and cannot be changed.');
399
    $form['default_format'] = array('#type' => 'hidden', '#value' => 1);
400
  }
401

402 403 404 405 406 407 408 409 410 411 412 413 414
  $form['name'] = array('#type' => 'textfield',
    '#title' => 'Name',
    '#default_value' => $format->name,
    '#description' => t('Specify a unique name for this filter format.'),
    '#required' => TRUE,
  );

  // Add a row of checkboxes for form group.
  $form['roles'] = array('#type' => 'fieldset',
    '#title' => t('Roles'),
    '#description' => $default ? $help : t('Choose which roles may use this filter format. Note that roles with the "administer filters" permission can always use all the filter formats.'),
    '#tree' => TRUE,
  );
415 416 417

  foreach (user_roles() as $rid => $name) {
    $checked = strstr($format->roles, ",$rid,");
418 419 420 421
    $form['roles'][$rid] = array('#type' => 'checkbox',
      '#title' => $name,
      '#default_value' => ($default || $checked),
    );
422
    if ($default) {
423
      $form['roles'][$rid]['#attributes'] = array('disabled' => 'disabled');
424
    }
425 426 427 428 429
  }
  // Table with filters
  $all = filter_list_all();
  $enabled = filter_list_format($format->format);

430 431 432 433 434
  $form['filters'] = array('#type' => 'fieldset',
    '#title' => t('Filters'),
    '#description' => t('Choose the filters that will be used in this filter format.'),
    '#tree' => TRUE,
  );
435
  foreach ($all as $id => $filter) {
436 437 438 439 440
    $form['filters'][$id] = array('#type' => 'checkbox',
      '#title' => $filter->name,
      '#default_value' => isset($enabled[$id]),
      '#description' => module_invoke($filter->module, 'filter', 'description', $filter->delta),
    );
441
  }
442
  $form['submit'] = array('#type' => 'submit', '#value' => t('Save configuration'));
443

444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460
  if (isset($format)) {
    $form['format'] = array('#type' => 'hidden', '#value' => $format->format);

    // Composition tips (guidelines)
    $tips = _filter_tips($format->format, false);
    $extra = l(t('More information about formatting options'), 'filter/tips');
    $tiplist = theme('filter_tips', $tips, false, $extra);
    if (!$tiplist) {
      $tiplist = t('<p>No guidelines available.</p>');
    }
    $group = t('<p>These are the guidelines that users will see for posting in this input format. They are automatically generated from the filter settings.</p>');
    $group .= $tiplist;
    $output = '<h2>'. t('Formatting guidelines') .'</h2>'. $group;
  }
  $output = drupal_get_form('filter_admin_format_form', $form) . $output;

  return $output;
461 462
}

463
/**
464
 * Validate filter format form submissions.
465
 */
466 467 468 469 470 471 472
function filter_admin_format_form_validate($form_id, $form_values) {
  if (!isset($form_values['format'])) {
    $name = trim($form_values['name']);
    $result = db_fetch_object(db_query("SELECT format FROM {filter_formats} WHERE name='%s'", $name));
    if ($result) {
      form_set_error('name', t('Filter format names need to be unique. A format named %name already exists.', array('%name' => theme('placeholder', $name))));
    }
473
  }
474
}
475

476 477 478 479 480 481 482 483 484 485 486 487
/**
 * Process filter format form submissions.
 */
function filter_admin_format_form_submit($form_id, $form_values) {
  $format = isset($form_values['format']) ? $form_values['format'] : NULL;
  $current = filter_list_format($format);
  $name = trim($form_values['name']);
  $cache = TRUE;

  // Add a new filter format.
  if (!$format) {
    $new = TRUE;
488 489 490
    db_query("INSERT INTO {filter_formats} (name) VALUES ('%s')", $name);
    $result = db_fetch_object(db_query("SELECT MAX(format) AS format FROM {filter_formats}"));
    $format = $result->format;
491
    drupal_set_message(t('Added input format %format.', array('%format' => theme('placeholder', $name))));
492 493 494 495 496
  }
  else {
    drupal_set_message(t('The input format settings have been updated.'));
  }

497
  db_query("DELETE FROM {filters} WHERE format = %d", $format);
498
  foreach ($form_values['filters'] as $id => $checked) {
499 500
    if ($checked) {
      list($module, $delta) = explode('/', $id);
501
      // Add new filters to the bottom.
502 503 504
      $weight = isset($current[$id]->weight) ? $current[$id]->weight : 10;
      db_query("INSERT INTO {filters} (format, module, delta, weight) VALUES (%d, '%s', %d, %d)", $format, $module, $delta, $weight);

505
      // Check if there are any 'no cache' filters.
506 507 508 509
      $cache &= !module_invoke($module, 'filter', 'no cache', $delta);
    }
  }

510
  // We store the roles as a string for ease of use.
511
  // We should always set all roles to true when saving a default role.
512
  // We use leading and trailing comma's to allow easy substring matching.
513 514 515 516 517 518 519 520 521
  $roles = array();
  if (isset($form_values['roles'])) {
    foreach ($form_values['roles'] as $id => $checked) {
      if ($checked) {
        $roles[] = $id;
      }
    }
  }
  $roles = ','. implode(',', ($form_values['default_format'] ? user_roles() : $roles)) .',';
522 523

  db_query("UPDATE {filter_formats} SET cache = %d, name='%s', roles = '%s' WHERE format = %d", $cache, $name, $roles, $format);
524 525 526

  cache_clear_all('filter:'. $format, true);

527
  // If a new filter was added, return to the main list of filters. Otherwise, stay on edit filter page to show new changes.
528
  if ($new) {
529
    return 'admin/filters/';
530 531
  }
  else {
532
    return 'admin/filters/'. $format;
533
  }
534 535 536
}

/**
537
 * Menu callback; display form for ordering filters for a format.
538
 */
539
function filter_admin_order($format = NULL) {
Dries's avatar
Dries committed
540
  // Get list (with forced refresh)
541
  $filters = filter_list_format($format->format);
Dries's avatar
Dries committed
542

543
  $form['weights'] = array('#tree' => TRUE);
544
  foreach ($filters as $id => $filter) {
545 546
    $form['names'][$id] = array('#value' => $filter->name);
    $form['weights'][$id] = array('#type' => 'weight', '#default_value' => $filter->weight);
Dries's avatar
Dries committed
547
  }
548
  $form['format'] = array('#type' => 'hidden', '#value' => $format->format);
549
  $form['submit'] = array('#type' => 'submit', '#value' => t('Save configuration'));
Dries's avatar
Dries committed
550

551 552
  return drupal_get_form('filter_admin_order', $form);
}
Dries's avatar
Dries committed
553

554 555 556
/**
 * Theme filter order configuration form.
 */
557 558 559
function theme_filter_admin_order($form) {
  $header = array(t('Name'), t('Weight'));
  $rows = array();
560
  foreach (element_children($form['names']) as $id) {
561
    // Don't take form control structures
562 563
    if (is_array($form['names'][$id])) {
      $rows[] = array(form_render($form['names'][$id]), form_render($form['weights'][$id]));
564 565 566 567 568
    }
  }

  $output = theme('table', $header, $rows);
  $output .= form_render($form);
569

Dries's avatar
Dries committed
570
  return $output;
Dries's avatar
Dries committed
571 572
}

573
/**
574
 * Process filter order configuration form submission.
575
 */
576 577
function filter_admin_order_submit($form_id, $form_values) {
  foreach ($form_values['weights'] as $id => $weight) {
578
    list($module, $delta) = explode('/', $id);
579
    db_query("UPDATE {filters} SET weight = %d WHERE format = %d AND module = '%s' AND delta = %d", $weight, $form_values['format'], $module, $delta);
580
  }
581
  drupal_set_message(t('The filter ordering has been saved.'));
582

583
  cache_clear_all('filter:'. $form_values['format'], true);
584 585 586
}

/**
587
 * Menu callback; display settings defined by filters.
588
 */
589 590 591 592
function filter_admin_configure() {
  $format = arg(2);

  $list = filter_list_format($format);
593
  $form = array();
594
  foreach ($list as $filter) {
595
    $form_module = module_invoke($filter->module, 'filter', 'settings', $filter->delta, $format);
596
    if (isset($form_module) && is_array($form_module)) {
597 598
      $form = array_merge($form, $form_module);
    }
599
  }
Dries's avatar
Dries committed
600

601 602
  if (!empty($form)) {
    $output = system_settings_form('filter_admin_configure', $form);
603 604 605 606
  }
  else {
    $output = t('No settings are available.');
  }
Dries's avatar
Dries committed
607

Dries's avatar
Dries committed
608
  return $output;
609 610
}

611
/**
612
 * Retrieve a list of input formats.
613
 */
614 615 616 617 618 619 620 621 622 623
function filter_formats() {
  global $user;
  static $formats;

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

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

624
    $query = 'SELECT * FROM {filter_formats}';
625

626
    // Build query for selecting the format(s) based on the user's roles.
627 628 629 630
    if (!$all) {
      $where = array();
      foreach ($user->roles as $rid => $role) {
        $where[] = "roles LIKE '%%,%d,%%'";
631
        $args[] = $rid;
632
      }
633 634
      $query .= ' WHERE '. implode(' OR ', $where) . ' OR format = %d';
      $args[] = variable_get('filter_default_format', 1);
635 636
    }

637
    $result = db_query($query, $args);
638 639 640 641 642 643
    while ($format = db_fetch_object($result)) {
      $formats[$format->format] = $format;
    }
  }
  return $formats;
}
644

645 646 647 648 649 650 651 652
/**
 * Build a list of all filters.
 */
function filter_list_all() {
  $filters = array();

  foreach (module_list() as $module) {
    $list = module_invoke($module, 'filter', 'list');
653
    if (isset($list) && is_array($list)) {
654 655 656
      foreach ($list as $delta => $name) {
        $filters[$module .'/'. $delta] = (object)array('module' => $module, 'delta' => $delta, 'name' => $name);
      }
Dries's avatar
Dries committed
657 658 659
    }
  }

660 661 662 663 664 665 666 667 668 669
  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);
Dries's avatar
Dries committed
670 671
}

672 673 674 675 676 677
/**
 * Resolve a format id, including the default format.
 */
function filter_resolve_format($format) {
  return $format == FILTER_FORMAT_DEFAULT ? variable_get('filter_default_format', 1) : $format;
}
678
/**
679
 * Check if text in a certain input format is allowed to be cached.
680
 */
681 682
function filter_format_allowcache($format) {
  static $cache = array();
683
  $format = filter_resolve_format($format);
684 685 686 687 688 689 690 691 692 693 694 695
  if (!isset($cache[$format])) {
    $cache[$format] = db_result(db_query('SELECT cache FROM {filter_formats} WHERE format = %d', $format));
  }
  return $cache[$format];
}

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

696
  if (!isset($filters[$format])) {
697 698 699 700
    $filters[$format] = array();
    $result = db_query("SELECT * FROM {filters} WHERE format = %d ORDER BY weight ASC", $format);
    while ($filter = db_fetch_object($result)) {
      $list = module_invoke($filter->module, 'filter', 'list');
701
      if (isset($list) && is_array($list) && isset($list[$filter->delta])) {
702 703
        $filter->name = $list[$filter->delta];
        $filters[$format][$filter->module .'/'. $filter->delta] = $filter;
Dries's avatar
Dries committed
704 705 706 707
      }
    }
  }

708
  return $filters[$format];
709 710
}

711 712
/**
 * @name Filtering functions
Dries's avatar
Dries committed
713
 * @{
714 715
 * Modules which need to have content filtered can use these functions to
 * interact with the filter system.
716 717 718 719 720 721 722 723
 *
 * 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.
724 725
 */

726 727
/**
 * Run all the enabled filters on a piece of text.
728 729 730 731 732 733 734 735 736 737 738 739
 *
 * @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 $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 $check = FALSE when viewing other people's content.  When
 *    showing content that is not (yet) stored in the database (eg. upon preview),
 *    set to TRUE so the user's permissions are checked.
740
 */
741
function check_markup($text, $format = FILTER_FORMAT_DEFAULT, $check = TRUE) {
742 743
  // When $check = true, do an access check on $format.
  if (isset($text) && (!$check || filter_access($format))) {
744
    $format = filter_resolve_format($format);
745

746
    // Check for a cached version of this piece of text.
747 748 749 750 751
    $id = 'filter:'. $format .':'. md5($text);
    if ($cached = cache_get($id)) {
      return $cached->data;
    }

752
    // See if caching is allowed for this format.
753
    $cache = filter_format_allowcache($format);
754 755

    // Convert all Windows and Mac newlines to a single newline,
756
    // so filters only need to deal with one possibility.
757 758
    $text = str_replace(array("\r\n", "\r"), "\n", $text);

759
    // Get a complete list of filters, ordered properly.
760
    $filters = filter_list_format($format);
Dries's avatar
Dries committed
761

762
    // Give filters the chance to escape HTML-like data such as code or formulas.
763 764
    foreach ($filters as $filter) {
      $text = module_invoke($filter->module, 'filter', 'prepare', $filter->delta, $format, $text);
Dries's avatar
Dries committed
765
    }
766

767
    // Perform filtering.
768 769
    foreach ($filters as $filter) {
      $text = module_invoke($filter->module, 'filter', 'process', $filter->delta, $format, $text);
770 771
    }

772
    // Store in cache with a minimum expiration time of 1 day.
Dries's avatar
Dries committed
773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788
    if ($cache) {
      cache_set($id, $text, time() + (60 * 60 * 24));
    }
  }
  else {
    $text = message_na();
  }

  return $text;
}

/**
 * Generate a selector for choosing a format in a form.
 *
 * @param $value
 *   The ID of the format that is currently selected.
789 790 791 792
 * @param $weight
 *   The weight of the input format.
 * @param $parents
 *   Required when defining multiple input formats on a single node or having a different parent than 'format'.
Dries's avatar
Dries committed
793 794 795
 * @return
 *   HTML for the form element.
 */
796
function filter_form($value = FILTER_FORMAT_DEFAULT, $weight = NULL, $parents = array('format')) {
Steven Wittens's avatar
Steven Wittens committed
797
  $value = filter_resolve_format($value);
Dries's avatar
Dries committed
798 799 800 801 802
  $formats = filter_formats();

  $extra = l(t('More information about formatting options'), 'filter/tips');

  if (count($formats) > 1) {
803
    $form = array(
804 805 806 807 808
      '#type' => 'fieldset',
      '#title' => t('Input format'),
      '#collapsible' => TRUE,
      '#collapsed' => TRUE,
      '#weight' => $weight,
809
      '#validate' => array('filter_form_validate' => array()),
810
    );
Dries's avatar
Dries committed
811 812
    // Multiple formats available: display radio buttons with tips.
    foreach ($formats as $format) {
813
      $form[$format->format] = array(
814
        '#type' => 'radio',
815 816 817
        '#title' => $format->name,
        '#default_value' => $value,
        '#return_value' => $format->format,
818
        '#parents' => $parents,
819 820
        '#description' => theme('filter_tips', _filter_tips($format->format, false)),
      );
Dries's avatar
Dries committed
821
    }
822 823 824 825
    $form[] = array(
      '#type' => 'markup',
      '#value' => $extra,
    );
Dries's avatar
Dries committed
826 827 828 829
  }
  else {
    // Only one format available: use a hidden form item and only show tips.
    $format = array_shift($formats);
830
    $form[$format->format] = array('#type' => 'value', '#value' => $format->format, '#parents' => $parents);
Dries's avatar
Dries committed
831
    $tips = _filter_tips(variable_get('filter_default_format', 1), false);
832
    $form['format']['guidelines'] = array(
833 834 835
      '#title' => t('Formatting guidelines'),
      '#value' => theme('filter_tips', $tips, false, $extra),
    );
Dries's avatar
Dries committed
836
  }
837
  return $form;
Dries's avatar
Dries committed
838 839
}

840 841 842 843 844 845 846
function filter_form_validate($form) {
  foreach (element_children($form) as $key) {
    if ($form[$key]['#value'] == $form[$key]['#return_value']) {
      return;
    }
  }
  form_error($form, t('An illegal choice has been detected. Please contact the site administrator.'));
847
  watchdog('form', t('Illegal choice %choice in %name element.', array('%choice' => theme('placeholder', check_plain($v)), '%name' => theme('placeholder', empty($form['#title']) ? $form['#parents'][0] : $form['#title'])), WATCHDOG_ERROR));
848 849
}

Dries's avatar
Dries committed
850 851 852 853
/**
 * Returns true if the user is allowed to access this format.
 */
function filter_access($format) {
854 855
  $format = filter_resolve_format($format);
  if (user_access('administer filters') || ($format == variable_get('filter_default_format', 1))) {
Dries's avatar
Dries committed
856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917
    return true;
  }
  else {
    $formats = filter_formats();
    return isset($formats[$format]);
  }
}
/**
 * @} End of "Filtering functions".
 */

/**
 * Menu callback; show a page with long filter tips.
 */
function filter_tips_long() {
  $format = arg(2);
  if ($format) {
    $output = theme('filter_tips', _filter_tips($format, true), true);
  }
  else {
    $output = theme('filter_tips', _filter_tips(-1, true), true);
  }
  return $output;
}

/**
 * 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_formats} 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 set of filter tips.
 *
 * @ingroup themeable
 */
function theme_filter_tips($tips, $long = false, $extra = '') {
  $output = '';

  $multiple = count($tips) > 1;
  if ($multiple) {
918
    $output = t('input formats') .':';
Dries's avatar
Dries committed
919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015
  }

  if (count($tips)) {
    if ($multiple) {
      $output .= '<ul>';
    }
    foreach ($tips as $name => $tiplist) {
      if ($multiple) {
        $output .= '<li>';
        $output .= '<strong>'. $name .'</strong>:<br />';
      }

      $tips = '';
      foreach ($tiplist as $tip) {
        $tips .= '<li'. ($long ? ' id="filter-'. str_replace("/", "-", $tip['id']) .'">' : '>') . $tip['tip'] . '</li>';
      }

      if ($tips) {
        $output .= "<ul class=\"tips\">$tips</ul>";
      }

      if ($multiple) {
        $output .= '</li>';
      }
    }
    if ($multiple) {
      $output .= '</ul>';
    }
  }

  return $output;
}

/**
 * @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.
 * - PHP evaluator:
 *     Executes PHP code.
 * - Line break converter:
 *     Converts newlines into paragraph and break tags.
 */
function filter_filter($op, $delta = 0, $format = -1, $text = '') {
  switch ($op) {
    case 'list':
      return array(0 => t('HTML filter'), 1 => t('PHP evaluator'), 2 => t('Line break converter'));

    case 'no cache':
      return $delta == 1; // No caching for the PHP evaluator.

    case 'description':
      switch ($delta) {
        case 0:
          return t('Allows you to restrict if users can post HTML and which tags to filter out.');
        case 1:
          return t('Runs a piece of PHP code. The usage of this filter should be restricted to administrators only!');
        case 2:
          return t('Converts line breaks into HTML (i.e. &lt;br&gt; and &lt;p&gt; tags).');
        default:
          return;
      }

    case 'process':
      switch ($delta) {
        case 0:
          return _filter_html($text, $format);
        case 1:
          return drupal_eval($text);
        case 2:
          return _filter_autop($text);
        default:
          return $text;
      }

    case 'settings':
      switch ($delta) {
        case 0:
          return _filter_html_settings($format);
        default:
          return;
      }

    default:
      return $text;
  }
}

/**
 * Settings for the HTML filter.
 */
function _filter_html_settings($format) {
1016
  $form['filter_html'] = array('#type' => 'fieldset', '#title' => t('HTML filter'), '#collapsible' => TRUE, '#collapsed' => TRUE);
1017
  $form['filter_html']["filter_html_$format"] = array('#type' => 'radios', '#title' => t('Filter HTML tags'), '#default_value' => variable_get("filter_html_$format", FILTER_HTML_STRIP), '#options' => array(FILTER_HTML_STRIP => t('Strip disallowed tags'), FILTER_HTML_ESCAPE => t('Escape all tags')), '#description' => t('How to deal with HTML tags in user-contributed content. If set to "Strip disallowed tags", dangerous tags are removed (see below). If set to "Escape tags", all HTML is escaped and presented as it was typed.'));
1018
  $form['filter_html']["allowed_html_$format"] = array('#type' => 'textfield', '#title' => t('Allowed HTML tags'), '#default_value' => variable_get("allowed_html_$format", '<a> <em> <strong> <cite> <code> <ul> <ol> <li> <dl> <dt> <dd>'), '#size' => 64, '#maxlength' => 255, '#description' => t('If "Strip disallowed tags" is selected, optionally specify tags which should not be stripped. JavaScript event attributes are always stripped.'));
1019 1020
  $form['filter_html']["filter_html_help_$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.'));
1021
  return $form;
Dries's avatar
Dries committed
1022 1023 1024 1025 1026 1027 1028
}

/**
 * HTML filter. Provides filtering of input into accepted HTML.
 */
function _filter_html($text, $format) {
  if (variable_get("filter_html_$format", FILTER_HTML_STRIP) == FILTER_HTML_STRIP) {
Dries's avatar
Dries committed
1029 1030
    $allowed_tags = preg_split('/\s+|<|>/', variable_get("allowed_html_$format", '<a> <em> <strong> <cite> <code> <ul> <ol> <li> <dl> <dt> <dd>'), -1, PREG_SPLIT_NO_EMPTY);
    $text = filter_xss($text, $allowed_tags);
Dries's avatar
Dries committed
1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062
  }

  if (variable_get("filter_html_$format", FILTER_HTML_STRIP) == FILTER_HTML_ESCAPE) {
    // Escape HTML
    $text = check_plain($text);
  }

  if (variable_get("filter_html_nofollow_$format", FALSE)) {
    $text = preg_replace('/<a([^>]+)>/i', '<a\\1 rel="nofollow">', $text);
  }

  return trim($text);
}

/**
 * Convert line breaks into <p> and <br> in an intelligent fashion.
 * Based on: http://photomatt.net/scripts/autop
 */
function _filter_autop($text) {
  // 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)[^>]*>)@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?
1063
      $open = ($chunk[1] != '/');
Dries's avatar
Dries committed
1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092
      list($tag) = split('[ >]', substr($chunk, 2 - $open), 2);
      if (!$ignore) {
        if ($open) {
          $ignore = true;
          $ignoretag = $tag;
        }
      }
      // Only allow a matching tag to close it.
      else if (!$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('!(<(?:table|ul|ol|li|pre|form|blockquote|h[1-6])[^>]*>)!', "\n$1", $chunk); // Space things out a little
      $chunk = preg_replace('!(</(?:table|ul|ol|li|pre|form|blockquote|h[1-6])>)!', "$1\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>|', '', $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*(</?(?:table|tr|td|th|div|ul|ol|li|pre|select|form|blockquote|p|h[1-6])[^>]*>)!', "$1", $chunk);
      $chunk = preg_replace('!(</?(?:table|tr|td|th|div|ul|ol|li|pre|select|form|blockquote|p|h[1-6])[^>]*>)\s*</p>!', "$1", $chunk);
      $chunk = preg_replace('|(?<!<br />)\s*\n|', "<br />\n", $chunk); // make line breaks
      $chunk = preg_replace('!(</?(?:table|tr|td|th|div|dl|dd|dt|ul|ol|li|pre|select|form|blockquote|p|h[1-6])[^>]*>)\s*<br />!', "$1", $chunk);
      $chunk = preg_replace('!<br />(\s*</?(?:p|li|div|th|pre|td|ul|ol)>)!', '$1', $chunk);
1093
      $chunk = preg_replace('/&([^#])(?![A-Za-z0-9]{1,8};)/', '&amp;$1', $chunk);
Dries's avatar
Dries committed
1094 1095 1096 1097 1098 1099
    }
    $output .= $chunk;
  }
  return $output;
}

1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113
/**
 * 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', 'h', 'h', 'h', 'h', 'h', 'h', 'hr', 'i', 'img', 'ins', 'kbd', 'li', 'object', 'ol', 'p', 'param', 'pre', 'q', 'samp', 'small', 'span', 'strong', 'sub', 'sup', 'table', 'tbody', 'td', 'tfoot', 'th', 'thead', 'tr', 'tt', 'ul', 'var'));
}

1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129
/**
 * 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.
Dries's avatar
Dries committed
1130 1131
 * @param $allowed_tags
 *   An array of allowed tags.
1132 1133 1134
 * @param $format
 *   The format to use.
 */
Dries's avatar
Dries committed
1135
function filter_xss($string, $allowed_tags = array('a', 'em', 'strong', 'cite', 'code', 'ul', 'ol', 'li', 'dl', 'dt', 'dd')) {
1136
  // Store the input format
Dries's avatar
Dries committed
1137
  _filter_xss_split($allowed_tags, TRUE);
1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157
  // Remove NUL 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('&', '&amp;', $string);
  // Change back only well-formed entities in our whitelist
  // Named entities
  $string = preg_replace('/&amp;([A-Za-z][A-Za-z0-9]*;)/', '&\1', $string);
  // Decimal numeric entities
  $string = preg_replace('/&amp;#([0-9]+;)/', '&#\1', $string);
  // Hexadecimal numeric entities
  $string = preg_replace('/&amp;#[Xx]0*((?:[0-9A-Fa-f]{2})+;)/', '&#x\1', $string);

  return preg_replace_callback('%
    (
    <[^>]*.(>|$)  # a string that starts with a <, up until the > or the end of the string
    |             # or
    >             # just a >
1158
    )%x', '_filter_xss_split', $string);
1159 1160 1161 1162 1163
}

/**
 * Processes an HTML tag.
 *
Dries's avatar
Dries committed
1164 1165 1166 1167 1168 1169
 * @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 $m.
1170
 * @return
Dries's avatar
Dries committed
1171 1172
 *   If the element isn't allowed, an empty string. Otherwise, the cleaned up
 *   version of the HTML element.
1173
 */
Dries's avatar
Dries committed
1174
function _filter_xss_split($m, $store = FALSE) {
1175 1176
  static $allowed_html;

Dries's avatar
Dries committed
1177 1178
  if ($store) {
    $allowed_html = array_flip($m);
1179 1180 1181
    return;
  }

1182
  $string = $m[1];
1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205

  if (substr($string, 0, 1) != '<') {
    // We matched a lone ">" character
    return '&gt;';
  }

  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 ($slash != '') {
    return "</$elem>";
  }
1206

1207
  // Is there a closing XHTML slash at the end of the attributes?
1208
  // In PHP 5.1.0+ we could count the changes, currently we need a separate match
1209
  $xhtml_slash = preg_match('%\s?/\s*$%', $attrlist) ? ' /' : '';
1210
  $attrlist = preg_replace('%(\s?)/\s*$%', '\1', $attrlist);
1211 1212 1213 1214

  // Clean up attributes
  $attr2 = implode(' ', _filter_xss_attributes($attrlist));
  $attr2 = preg_replace('/[<>]/', '', $attr2);
1215
  $attr2 = strlen($attr2) ? ' '. $attr2 : '';
1216

1217
  return "<$elem$attr2$xhtml_slash>";
1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 1308 1309 1310 1311 1312 1313 1314 1315 1316 1317 1318 1319 1320 1321 1322 1323 1324 1325 1326 1327 1328 1329 1330 1331 1332 1333 1334 1335 1336 1337 1338 1339
}

/**
 * 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) {
1340 1341 1342 1343 1344
  static $allowed_protocols;
  if (!isset($allowed_protocols)) {
    $allowed_protocols = array_flip(variable_get('filter_allowed_protocols', array('http', 'https', 'ftp', 'news', 'nntp', 'telnet', 'mailto', 'irc', 'ssh', 'sftp', 'webcal')));
  }

1345 1346 1347 1348 1349 1350 1351
  // Get the plain text representation of the attribute value (i.e. its meaning)
  if ($decode) {
    $string = decode_entities($string);
  }
  // Remove soft hyphen
  $string = str_replace(chr(194) . chr(173), '', $string);
  // Strip protocols
1352

1353 1354
  do {
    $before = $string;
1355 1356 1357 1358 1359 1360 1361
    $colonpos = strpos($string, ':');
    if ($colonpos > 0) {
      $protocol = substr($string, 0, $colonpos);
      if (!isset($allowed_protocols[$protocol])) {
        $string = substr($string, $colonpos + 1);
      }
    }
1362 1363 1364 1365
  } while ($before != $string);
  return check_plain($string);
}

Dries's avatar
Dries committed
1366 1367 1368 1369
/**
 * @} End of "Standard filters".
 */