summaryrefslogtreecommitdiffstats
path: root/modules/filter/filter.module
blob: a98423418bd542a1c686a0eb57597efe2b0aed7e (plain)
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
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
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
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
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
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
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
483
484
485
486
487
488
489
490
491
492
493
494
495
496
497
498
499
500
501
502
503
504
505
506
507
508
509
510
511
512
513
514
515
516
517
518
519
520
521
522
523
524
525
526
527
528
529
530
531
532
533
534
535
536
537
538
539
540
541
542
543
544
545
546
547
548
549
550
551
552
553
554
555
556
557
558
559
560
561
562
563
564
565
566
567
568
569
570
571
572
573
574
575
576
577
578
579
580
581
582
583
584
585
586
587
588
589
590
591
592
593
594
595
596
597
598
599
600
601
602
603
604
605
606
607
608
609
610
611
612
613
614
615
616
617
618
619
620
621
622
623
624
625
626
627
628
629
630
631
632
633
634
635
636
637
638
639
640
641
642
643
644
645
646
647
648
649
650
651
652
653
654
655
656
657
658
659
660
661
662
663
664
665
666
667
668
669
670
671
672
673
674
675
676
677
678
679
680
681
682
683
684
685
686
687
688
689
690
691
692
693
694
695
696
697
698
699
700
701
702
703
704
705
706
707
708
709
710
711
712
713
714
715
716
717
718
719
720
721
722
723
724
725
726
727
728
729
730
731
732
733
734
735
736
737
738
739
740
741
742
743
744
745
746
747
748
749
750
751
752
753
754
755
756
757
758
759
760
761
762
763
764
765
766
767
768
769
770
771
772
773
774
775
776
777
778
779
780
781
782
783
784
785
786
787
788
789
790
791
792
793
794
795
796
797
798
799
800
801
802
803
804
805
806
807
808
809
810
811
812
813
814
815
816
817
818
819
820
821
822
823
824
825
826
827
828
829
830
831
832
833
834
835
836
837
838
839
840
841
842
843
844
845
846
847
848
849
850
851
852
853
854
855
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
918
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
1016
1017
1018
1019
1020
1021
1022
1023
1024
1025
1026
1027
1028
1029
1030
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
1063
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
1093
1094
1095
1096
1097
1098
1099
1100
1101
1102
1103
1104
1105
1106
1107
1108
1109
1110
1111
1112
1113
1114
1115
1116
1117
1118
1119
1120
1121
1122
1123
1124
1125
1126
1127
1128
1129
1130
1131
1132
1133
1134
1135
1136
1137
1138
1139
1140
1141
1142
1143
1144
1145
1146
1147
1148
1149
1150
1151
1152
1153
1154
1155
1156
1157
1158
1159
1160
1161
1162
1163
1164
1165
1166
1167
1168
1169
1170
1171
1172
1173
1174
1175
1176
1177
1178
1179
1180
1181
1182
1183
1184
1185
1186
1187
1188
1189
1190
1191
1192
1193
1194
1195
1196
1197
1198
1199
1200
<?php
// $Id$

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

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

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

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

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

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

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

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

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

/**
 * Implementation of hook_filter_tips().
 */
function filter_filter_tips($delta, $format, $long = FALSE) {
  global $base_url;
  switch ($delta) {
    case 0:
      if ($allowed_html = variable_get("allowed_html_$format", '<a> <em> <strong> <cite> <blockquote> <code> <ul> <ol> <li> <dl> <dt> <dd>')) {
        switch ($long) {
          case 0:
            return t('Allowed HTML tags: @tags', array('@tags' => $allowed_html));
          case 1:
            $output = '<p>' . t('Allowed HTML tags: @tags', array('@tags' => $allowed_html)) . '</p>';
            if (!variable_get("filter_html_help_$format", 1)) {
              return $output;
            }

            $output .= '<p>' . t('This site allows HTML content. While learning all of HTML may feel intimidating, learning how to use a very small number of the most basic HTML "tags" is very easy. This table provides examples for each tag that is enabled on this site.') . '</p>';
            $output .= '<p>' . t('For more information see W3C\'s <a href="@html-specifications">HTML Specifications</a> or use your favorite search engine to find other sites that explain HTML.', array('@html-specifications' => 'http://www.w3.org/TR/html/')) . '</p>';
            $tips = array(
              'a' => array( t('Anchors are used to make links to other pages.'), '<a href="' . $base_url . '">' . variable_get('site_name', 'Drupal') . '</a>'),
              'br' => array( t('By default line break tags are automatically added, so use this tag to add additional ones. Use of this tag is different because it is not used with an open/close pair like all the others. Use the extra " /" inside the tag to maintain XHTML 1.0 compatibility'), t('Text with <br />line break')),
              'p' => array( t('By default paragraph tags are automatically added, so use this tag to add additional ones.'), '<p>' . t('Paragraph one.') . '</p> <p>' . t('Paragraph two.') . '</p>'),
              'strong' => array( t('Strong'), '<strong>' . t('Strong') . '</strong>'),
              'em' => array( t('Emphasized'), '<em>' . t('Emphasized') . '</em>'),
              'cite' => array( t('Cited'), '<cite>' . t('Cited') . '</cite>'),
              'code' => array( t('Coded text used to show programming source code'), '<code>' . t('Coded') . '</code>'),
              'b' => array( t('Bolded'), '<b>' . t('Bolded') . '</b>'),
              'u' => array( t('Underlined'), '<u>' . t('Underlined') . '</u>'),
              'i' => array( t('Italicized'), '<i>' . t('Italicized') . '</i>'),
              'sup' => array( t('Superscripted'), t('<sup>Super</sup>scripted')),
              'sub' => array( t('Subscripted'), t('<sub>Sub</sub>scripted')),
              'pre' => array( t('Preformatted'), '<pre>' . t('Preformatted') . '</pre>'),
              'abbr' => array( t('Abbreviation'), t('<abbr title="Abbreviation">Abbrev.</abbr>')),
              'acronym' => array( t('Acronym'), t('<acronym title="Three-Letter Acronym">TLA</acronym>')),
              'blockquote' => array( t('Block quoted'), '<blockquote>' . t('Block quoted') . '</blockquote>'),
              'q' => array( t('Quoted inline'), '<q>' . t('Quoted inline') . '</q>'),
              // Assumes and describes tr, td, th.
              'table' => array( t('Table'), '<table> <tr><th>' . t('Table header') . '</th></tr> <tr><td>' . t('Table cell') . '</td></tr> </table>'),
              'tr' => NULL, 'td' => NULL, 'th' => NULL,
              'del' => array( t('Deleted'), '<del>' . t('Deleted') . '</del>'),
              'ins' => array( t('Inserted'), '<ins>' . t('Inserted') . '</ins>'),
               // Assumes and describes li.
              'ol' => array( t('Ordered list - use the &lt;li&gt; to begin each list item'), '<ol> <li>' . t('First item') . '</li> <li>' . t('Second item') . '</li> </ol>'),
              'ul' => array( t('Unordered list - use the &lt;li&gt; to begin each list item'), '<ul> <li>' . t('First item') . '</li> <li>' . t('Second item') . '</li> </ul>'),
              'li' => NULL,
              // Assumes and describes dt and dd.
              'dl' => array( t('Definition lists are similar to other HTML lists. &lt;dl&gt; begins the definition list, &lt;dt&gt; begins the definition term and &lt;dd&gt; begins the definition description.'), '<dl> <dt>' . t('First term') . '</dt> <dd>' . t('First definition') . '</dd> <dt>' . t('Second term') . '</dt> <dd>' . t('Second definition') . '</dd> </dl>'),
              'dt' => NULL, 'dd' => NULL,
              'h1' => array( t('Heading'), '<h1>' . t('Title') . '</h1>'),
              'h2' => array( t('Heading'), '<h2>' . t('Subtitle') . '</h2>'),
              'h3' => array( t('Heading'), '<h3>' . t('Subtitle three') . '</h3>'),
              'h4' => array( t('Heading'), '<h4>' . t('Subtitle four') . '</h4>'),
              'h5' => array( t('Heading'), '<h5>' . t('Subtitle five') . '</h5>'),
              'h6' => array( t('Heading'), '<h6>' . t('Subtitle six') . '</h6>')
            );
            $header = array(t('Tag Description'), t('You Type'), t('You Get'));
            preg_match_all('/<([a-z0-9]+)[^a-z0-9]/i', $allowed_html, $out);
            foreach ($out[1] as $tag) {
              if (array_key_exists($tag, $tips)) {
                if ($tips[$tag]) {
                  $rows[] = array(
                    array('data' => $tips[$tag][0], 'class' => 'description'),
                    array('data' => '<code>' . check_plain($tips[$tag][1]) . '</code>', '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 .= '<p>' . t('Most unusual characters can be directly entered without any problems.') . '</p>';
            $output .= '<p>' . t('If you do encounter problems, try using HTML character entities. A common example looks like &amp;amp; for an ampersand &amp; character. For a full list of entities see HTML\'s <a href="@html-entities">entities</a> page. Some of the available characters include:', array('@html-entities' => 'http://www.w3.org/TR/html4/sgml/entities.html')) . '</p>';

            $entities = array(
              array( t('Ampersand'), '&amp;'),
              array( t('Greater than'), '&gt;'),
              array( t('Less than'), '&lt;'),
              array( t('Quotation mark'), '&quot;'),
            );
            $header = array(t('Character Description'), t('You Type'), t('You Get'));
            unset($rows);
            foreach ($entities as $entity) {
              $rows[] = array(
                array('data' => $entity[0], 'class' => 'description'),
                array('data' => '<code>' . check_plain($entity[1]) . '</code>', '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 &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.');
      }
      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 text formats.
 */
function filter_formats($index = NULL) {
  global $user;
  static $formats;

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

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

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

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

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

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

  foreach (module_implements('filter') 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) : $format;
}
/**
 * Check if text in a certain text format is allowed to be cached.
 */
function filter_format_allowcache($format) {
  static $cache = array();
  $format = filter_resolve_format($format);
  if (!isset($cache[$format])) {
    $cache[$format] = db_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 text format.
 * @param $parents
 *   Required when defining multiple text formats on a single node or having a different parent than 'format'.
 * @return
 *   HTML for the form element.
 */
function filter_form($value = FILTER_FORMAT_DEFAULT, $weight = NULL, $parents = array('format')) {
  $value = filter_resolve_format($value);
  $formats = filter_formats();

  $extra = theme('filter_tips_more_info');

  if (count($formats) > 1) {
    $form = array(
      '#type' => 'fieldset',
      '#title' => t('Text 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 '<p>' . l(t('More information about formatting options'), 'filter/tips') . '</p>';
}

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

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

  if (variable_get("filter_html_nofollow_$format", FALSE)) {
    $text = preg_replace('/<a([^>]+)>/i', '<a\\1 rel="nofollow">', $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("`(<p>|<li>|<br\s*/?>|[ \n\r\t\(])((http://|https://|ftp://|mailto:|smb://|afp://|file://|gopher://|news://|ssl://|sslv2://|sslv3://|tls://|tcp://|udp://)([a-zA-Z0-9@:%_+*~#?&=.,/;-]*[a-zA-Z0-9@:%_+*~#&=/;-]))([.,?!]*?)(?=(</p>|</li>|<br\s*/?>|[ \n\r\t\)]))`i", '_filter_url_parse_full_links', $text);

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

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

  return $text;
}

/**
 * Scan input and make sure that all HTML tags are properly closed and nested.
 */
function _filter_htmlcorrector($text) {
  // 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/])!', '&lt;\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 .= '</' . $stack[0] . '>';
            } while (array_shift($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]])) {
          $output .= '</' . array_shift($stack) . '>';
        }
        // 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) {
    $output .= '</' . array_shift($stack) . '>';
  }
  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] . '<a href="' . $match[2] . '" title="' . $match[2] . '">' . $caption . '</a>' . $match[5];
}

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

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

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

  return $text;
}

/**
 * Convert line breaks into <p> and <br> in an intelligent fashion.
 * Based on: http://photomatt.net/scripts/autop
 */
function _filter_autop($text) {
  // All block level tags
  $block = '(?:table|thead|tfoot|caption|colgroup|tbody|tr|td|th|div|dl|dd|dt|ul|ol|li|pre|select|form|blockquote|address|p|h[1-6]|hr)';

  // Split at <pre>, <script>, <style> and </pre>, </script>, </style> tags.
  // We don't apply any processing to the contents of these tags to avoid messing
  // up code. We look for matched pairs and allow basic nesting. For example:
  // "processed <pre> ignored <script> ignored </script> ignored </pre> processed"
  $chunks = preg_split('@(</?(?:pre|script|style|object)[^>]*>)@i', $text, -1, PREG_SPLIT_DELIM_CAPTURE);
  // Note: PHP ensures the array consists of alternating delimiters and literals
  // and begins and ends with a literal (inserting NULL as required).
  $ignore = FALSE;
  $ignoretag = '';
  $output = '';
  foreach ($chunks as $i => $chunk) {
    if ($i % 2) {
      // Opening or closing tag?
      $open = ($chunk[1] != '/');
      list($tag) = preg_split('/[ >]/', substr($chunk, 2 - $open), 2);
      if (!$ignore) {
        if ($open) {
          $ignore = TRUE;
          $ignoretag = $tag;
        }
      }
      // Only allow a matching tag to close it.
      elseif (!$open && $ignoretag == $tag) {
        $ignore = FALSE;
        $ignoretag = '';
      }
    }
    elseif (!$ignore) {
      $chunk = preg_replace('|\n*$|', '', $chunk) . "\n\n"; // just to make things a little easier, pad the end
      $chunk = preg_replace('|<br />\s*<br />|', "\n\n", $chunk);
      $chunk = preg_replace('!(<' . $block . '[^>]*>)!', "\n$1", $chunk); // Space things out a little
      $chunk = preg_replace('!(</' . $block . '>)!', "$1\n\n", $chunk); // Space things out a little
      $chunk = preg_replace("/\n\n+/", "\n\n", $chunk); // take care of duplicates
      $chunk = preg_replace('/\n?(.+?)(?:\n\s*\n|\z)/s', "<p>$1</p>\n", $chunk); // make paragraphs, including one at the end
      $chunk = preg_replace("|<p>(<li.+?)</p>|", "$1", $chunk); // problem with nested lists
      $chunk = preg_replace('|<p><blockquote([^>]*)>|i', "<blockquote$1><p>", $chunk);
      $chunk = str_replace('</blockquote></p>', '</p></blockquote>', $chunk);
      $chunk = preg_replace('|<p>\s*</p>\n?|', '', $chunk); // under certain strange conditions it could create a P of entirely whitespace
      $chunk = preg_replace('!<p>\s*(</?' . $block . '[^>]*>)!', "$1", $chunk);
      $chunk = preg_replace('!(</?' . $block . '[^>]*>)\s*</p>!', "$1", $chunk);
      $chunk = preg_replace('|(?<!<br />)\s*\n|', "<br />\n", $chunk); // make line breaks
      $chunk = preg_replace('!(</?' . $block . '[^>]*>)\s*<br />!', "$1", $chunk);
      $chunk = preg_replace('!<br />(\s*</?(?:p|li|div|th|pre|td|ul|ol)>)!', '$1', $chunk);
      $chunk = preg_replace('/&([^#])(?![A-Za-z0-9]{1,8};)/', '&amp;$1', $chunk);
    }
    $output .= $chunk;
  }
  return $output;
}

/**
 * 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 text 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('&', '&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-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($string, 0, 1) != '<') {
    // We matched a lone ">" character
    return '&gt;';
  }
  elseif (strlen($string) == 1) {
    // We matched a lone "<" character
    return '&lt;';
  }

  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>";
  }

  // 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".
 */