-
Notifications
You must be signed in to change notification settings - Fork 6
/
Sanitizer.php
1384 lines (1278 loc) · 38.7 KB
/
Sanitizer.php
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
<?php
/**
* XHTML sanitizer for MediaWiki
*
* Copyright (C) 2002-2005 Brion Vibber <[email protected]> et al
* http://www.mediawiki.org/
*
* This program is free software; you can redistribute it and/or modify
* it under the terms of the GNU General Public License as published by
* the Free Software Foundation; either version 2 of the License, or
* (at your option) any later version.
*
* This program is distributed in the hope that it will be useful,
* but WITHOUT ANY WARRANTY; without even the implied warranty of
* MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
* GNU General Public License for more details.
*
* You should have received a copy of the GNU General Public License along
* with this program; if not, write to the Free Software Foundation, Inc.,
* 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301, USA.
* http://www.gnu.org/copyleft/gpl.html
*
* @file
* @ingroup Parser
*/
/**
* Regular expression to match various types of character references in
* Sanitizer::normalizeCharReferences and Sanitizer::decodeCharReferences
*/
define( 'MW_CHAR_REFS_REGEX',
'/&([A-Za-z0-9\x80-\xff]+);
|&\#([0-9]+);
|&\#x([0-9A-Za-z]+);
|&\#X([0-9A-Za-z]+);
|(&)/x' );
/**
* Regular expression to match HTML/XML attribute pairs within a tag.
* Allows some... latitude.
* Used in Sanitizer::fixTagAttributes and Sanitizer::decodeTagAttributes
*/
$attrib = '[A-Za-z0-9]';
$space = '[\x09\x0a\x0d\x20]';
define( 'MW_ATTRIBS_REGEX',
"/(?:^|$space)($attrib+)
($space*=$space*
(?:
# The attribute value: quoted or alone
\"([^<\"]*)\"
| '([^<']*)'
| ([a-zA-Z0-9!#$%&()*,\\-.\\/:;<>?@[\\]^_`{|}~]+)
| (\#[0-9a-fA-F]+) # Technically wrong, but lots of
# colors are specified like this.
# We'll be normalizing it.
)
)?(?=$space|\$)/sx" );
/**
* List of all named character entities defined in HTML 4.01
* http://www.w3.org/TR/html4/sgml/entities.html
* @private
*/
global $wgHtmlEntities;
$wgHtmlEntities = array(
'Aacute' => 193,
'aacute' => 225,
'Acirc' => 194,
'acirc' => 226,
'acute' => 180,
'AElig' => 198,
'aelig' => 230,
'Agrave' => 192,
'agrave' => 224,
'alefsym' => 8501,
'Alpha' => 913,
'alpha' => 945,
'amp' => 38,
'and' => 8743,
'ang' => 8736,
'Aring' => 197,
'aring' => 229,
'asymp' => 8776,
'Atilde' => 195,
'atilde' => 227,
'Auml' => 196,
'auml' => 228,
'bdquo' => 8222,
'Beta' => 914,
'beta' => 946,
'brvbar' => 166,
'bull' => 8226,
'cap' => 8745,
'Ccedil' => 199,
'ccedil' => 231,
'cedil' => 184,
'cent' => 162,
'Chi' => 935,
'chi' => 967,
'circ' => 710,
'clubs' => 9827,
'cong' => 8773,
'copy' => 169,
'crarr' => 8629,
'cup' => 8746,
'curren' => 164,
'dagger' => 8224,
'Dagger' => 8225,
'darr' => 8595,
'dArr' => 8659,
'deg' => 176,
'Delta' => 916,
'delta' => 948,
'diams' => 9830,
'divide' => 247,
'Eacute' => 201,
'eacute' => 233,
'Ecirc' => 202,
'ecirc' => 234,
'Egrave' => 200,
'egrave' => 232,
'empty' => 8709,
'emsp' => 8195,
'ensp' => 8194,
'Epsilon' => 917,
'epsilon' => 949,
'equiv' => 8801,
'Eta' => 919,
'eta' => 951,
'ETH' => 208,
'eth' => 240,
'Euml' => 203,
'euml' => 235,
'euro' => 8364,
'exist' => 8707,
'fnof' => 402,
'forall' => 8704,
'frac12' => 189,
'frac14' => 188,
'frac34' => 190,
'frasl' => 8260,
'Gamma' => 915,
'gamma' => 947,
'ge' => 8805,
'gt' => 62,
'harr' => 8596,
'hArr' => 8660,
'hearts' => 9829,
'hellip' => 8230,
'Iacute' => 205,
'iacute' => 237,
'Icirc' => 206,
'icirc' => 238,
'iexcl' => 161,
'Igrave' => 204,
'igrave' => 236,
'image' => 8465,
'infin' => 8734,
'int' => 8747,
'Iota' => 921,
'iota' => 953,
'iquest' => 191,
'isin' => 8712,
'Iuml' => 207,
'iuml' => 239,
'Kappa' => 922,
'kappa' => 954,
'Lambda' => 923,
'lambda' => 955,
'lang' => 9001,
'laquo' => 171,
'larr' => 8592,
'lArr' => 8656,
'lceil' => 8968,
'ldquo' => 8220,
'le' => 8804,
'lfloor' => 8970,
'lowast' => 8727,
'loz' => 9674,
'lrm' => 8206,
'lsaquo' => 8249,
'lsquo' => 8216,
'lt' => 60,
'macr' => 175,
'mdash' => 8212,
'micro' => 181,
'middot' => 183,
'minus' => 8722,
'Mu' => 924,
'mu' => 956,
'nabla' => 8711,
'nbsp' => 160,
'ndash' => 8211,
'ne' => 8800,
'ni' => 8715,
'not' => 172,
'notin' => 8713,
'nsub' => 8836,
'Ntilde' => 209,
'ntilde' => 241,
'Nu' => 925,
'nu' => 957,
'Oacute' => 211,
'oacute' => 243,
'Ocirc' => 212,
'ocirc' => 244,
'OElig' => 338,
'oelig' => 339,
'Ograve' => 210,
'ograve' => 242,
'oline' => 8254,
'Omega' => 937,
'omega' => 969,
'Omicron' => 927,
'omicron' => 959,
'oplus' => 8853,
'or' => 8744,
'ordf' => 170,
'ordm' => 186,
'Oslash' => 216,
'oslash' => 248,
'Otilde' => 213,
'otilde' => 245,
'otimes' => 8855,
'Ouml' => 214,
'ouml' => 246,
'para' => 182,
'part' => 8706,
'permil' => 8240,
'perp' => 8869,
'Phi' => 934,
'phi' => 966,
'Pi' => 928,
'pi' => 960,
'piv' => 982,
'plusmn' => 177,
'pound' => 163,
'prime' => 8242,
'Prime' => 8243,
'prod' => 8719,
'prop' => 8733,
'Psi' => 936,
'psi' => 968,
'quot' => 34,
'radic' => 8730,
'rang' => 9002,
'raquo' => 187,
'rarr' => 8594,
'rArr' => 8658,
'rceil' => 8969,
'rdquo' => 8221,
'real' => 8476,
'reg' => 174,
'rfloor' => 8971,
'Rho' => 929,
'rho' => 961,
'rlm' => 8207,
'rsaquo' => 8250,
'rsquo' => 8217,
'sbquo' => 8218,
'Scaron' => 352,
'scaron' => 353,
'sdot' => 8901,
'sect' => 167,
'shy' => 173,
'Sigma' => 931,
'sigma' => 963,
'sigmaf' => 962,
'sim' => 8764,
'spades' => 9824,
'sub' => 8834,
'sube' => 8838,
'sum' => 8721,
'sup' => 8835,
'sup1' => 185,
'sup2' => 178,
'sup3' => 179,
'supe' => 8839,
'szlig' => 223,
'Tau' => 932,
'tau' => 964,
'there4' => 8756,
'Theta' => 920,
'theta' => 952,
'thetasym' => 977,
'thinsp' => 8201,
'THORN' => 222,
'thorn' => 254,
'tilde' => 732,
'times' => 215,
'trade' => 8482,
'Uacute' => 218,
'uacute' => 250,
'uarr' => 8593,
'uArr' => 8657,
'Ucirc' => 219,
'ucirc' => 251,
'Ugrave' => 217,
'ugrave' => 249,
'uml' => 168,
'upsih' => 978,
'Upsilon' => 933,
'upsilon' => 965,
'Uuml' => 220,
'uuml' => 252,
'weierp' => 8472,
'Xi' => 926,
'xi' => 958,
'Yacute' => 221,
'yacute' => 253,
'yen' => 165,
'Yuml' => 376,
'yuml' => 255,
'Zeta' => 918,
'zeta' => 950,
'zwj' => 8205,
'zwnj' => 8204 );
/**
* Character entity aliases accepted by MediaWiki
*/
global $wgHtmlEntityAliases;
$wgHtmlEntityAliases = array(
'רלמ' => 'rlm',
'رلم' => 'rlm',
);
/**
* XHTML sanitizer for MediaWiki
* @ingroup Parser
*/
class Sanitizer {
/**
* Cleans up HTML, removes dangerous tags and attributes, and
* removes HTML comments
* @private
* @param $text String
* @param $processCallback Callback to do any variable or parameter replacements in HTML attribute values
* @param $args Array for the processing callback
* @param $extratags Array for any extra tags to include
* @param $removetags Array for any tags (default or extra) to exclude
* @return string
*/
static function removeHTMLtags( $text, $processCallback = null, $args = array(), $extratags = array(), $removetags = array() ) {
global $wgUseTidy;
static $htmlpairsStatic, $htmlsingle, $htmlsingleonly, $htmlnest, $tabletags,
$htmllist, $listtags, $htmlsingleallowed, $htmlelementsStatic, $staticInitialised;
wfProfileIn( __METHOD__ );
if ( !$staticInitialised ) {
$htmlpairsStatic = array( # Tags that must be closed
'b', 'del', 'i', 'ins', 'u', 'font', 'big', 'small', 'sub', 'sup', 'h1',
'h2', 'h3', 'h4', 'h5', 'h6', 'cite', 'code', 'em', 's',
'strike', 'strong', 'tt', 'var', 'div', 'center',
'blockquote', 'ol', 'ul', 'dl', 'table', 'caption', 'pre',
'ruby', 'rt' , 'rb' , 'rp', 'p', 'span', 'u', 'abbr'
);
$htmlsingle = array(
'br', 'hr', 'li', 'dt', 'dd'
);
$htmlsingleonly = array( # Elements that cannot have close tags
'br', 'hr'
);
$htmlnest = array( # Tags that can be nested--??
'table', 'tr', 'td', 'th', 'div', 'blockquote', 'ol', 'ul',
'dl', 'font', 'big', 'small', 'sub', 'sup', 'span'
);
$tabletags = array( # Can only appear inside table, we will close them
'td', 'th', 'tr',
);
$htmllist = array( # Tags used by list
'ul','ol',
);
$listtags = array( # Tags that can appear in a list
'li',
);
$htmlsingleallowed = array_unique( array_merge( $htmlsingle, $tabletags ) );
$htmlelementsStatic = array_unique( array_merge( $htmlsingle, $htmlpairsStatic, $htmlnest ) );
# Convert them all to hashtables for faster lookup
$vars = array( 'htmlpairsStatic', 'htmlsingle', 'htmlsingleonly', 'htmlnest', 'tabletags',
'htmllist', 'listtags', 'htmlsingleallowed', 'htmlelementsStatic' );
foreach ( $vars as $var ) {
$$var = array_flip( $$var );
}
$staticInitialised = true;
}
# Populate $htmlpairs and $htmlelements with the $extratags and $removetags arrays
$extratags = array_flip( $extratags );
$removetags = array_flip( $removetags );
$htmlpairs = array_merge( $extratags, $htmlpairsStatic );
$htmlelements = array_diff_key( array_merge( $extratags, $htmlelementsStatic ) , $removetags );
# Remove HTML comments
$text = Sanitizer::removeHTMLcomments( $text );
$bits = explode( '<', $text );
$text = str_replace( '>', '>', array_shift( $bits ) );
if(!$wgUseTidy) {
$tagstack = $tablestack = array();
foreach ( $bits as $x ) {
$regs = array();
if( preg_match( '!^(/?)(\\w+)([^>]*?)(/{0,1}>)([^<]*)$!', $x, $regs ) ) {
list( /* $qbar */, $slash, $t, $params, $brace, $rest ) = $regs;
} else {
$slash = $t = $params = $brace = $rest = null;
}
$badtag = 0 ;
if ( isset( $htmlelements[$t = strtolower( $t )] ) ) {
# Check our stack
if ( $slash ) {
# Closing a tag...
if( isset( $htmlsingleonly[$t] ) ) {
$badtag = 1;
} elseif ( ( $ot = @array_pop( $tagstack ) ) != $t ) {
if ( isset( $htmlsingleallowed[$ot] ) ) {
# Pop all elements with an optional close tag
# and see if we find a match below them
$optstack = array();
array_push ($optstack, $ot);
while ( ( ( $ot = @array_pop( $tagstack ) ) != $t ) &&
isset( $htmlsingleallowed[$ot] ) )
{
array_push ($optstack, $ot);
}
if ( $t != $ot ) {
# No match. Push the optinal elements back again
$badtag = 1;
while ( $ot = @array_pop( $optstack ) ) {
array_push( $tagstack, $ot );
}
}
} else {
@array_push( $tagstack, $ot );
# <li> can be nested in <ul> or <ol>, skip those cases:
if(!(isset( $htmllist[$ot] ) && isset( $listtags[$t] ) )) {
$badtag = 1;
}
}
} else {
if ( $t == 'table' ) {
$tagstack = array_pop( $tablestack );
}
}
$newparams = '';
} else {
# Keep track for later
if ( isset( $tabletags[$t] ) &&
! in_array( 'table', $tagstack ) ) {
$badtag = 1;
} else if ( in_array( $t, $tagstack ) &&
! isset( $htmlnest [$t ] ) ) {
$badtag = 1 ;
# Is it a self closed htmlpair ? (bug 5487)
} else if( $brace == '/>' &&
isset( $htmlpairs[$t] ) ) {
$badtag = 1;
} elseif( isset( $htmlsingleonly[$t] ) ) {
# Hack to force empty tag for uncloseable elements
$brace = '/>';
} else if( isset( $htmlsingle[$t] ) ) {
# Hack to not close $htmlsingle tags
$brace = NULL;
} else if( isset( $tabletags[$t] )
&& in_array($t ,$tagstack) ) {
// New table tag but forgot to close the previous one
$text .= "</$t>";
} else {
if ( $t == 'table' ) {
array_push( $tablestack, $tagstack );
$tagstack = array();
}
array_push( $tagstack, $t );
}
# Replace any variables or template parameters with
# plaintext results.
if( is_callable( $processCallback ) ) {
call_user_func_array( $processCallback, array( &$params, $args ) );
}
# Strip non-approved attributes from the tag
$newparams = Sanitizer::fixTagAttributes( $params, $t );
}
if ( ! $badtag ) {
$rest = str_replace( '>', '>', $rest );
$close = ( $brace == '/>' && !$slash ) ? ' /' : '';
$text .= "<$slash$t$newparams$close>$rest";
continue;
}
}
$text .= '<' . str_replace( '>', '>', $x);
}
# Close off any remaining tags
while ( is_array( $tagstack ) && ($t = array_pop( $tagstack )) ) {
$text .= "</$t>\n";
if ( $t == 'table' ) { $tagstack = array_pop( $tablestack ); }
}
} else {
# this might be possible using tidy itself
foreach ( $bits as $x ) {
preg_match( '/^(\\/?)(\\w+)([^>]*?)(\\/{0,1}>)([^<]*)$/',
$x, $regs );
@list( /* $qbar */, $slash, $t, $params, $brace, $rest ) = $regs;
if ( isset( $htmlelements[$t = strtolower( $t )] ) ) {
if( is_callable( $processCallback ) ) {
call_user_func_array( $processCallback, array( &$params, $args ) );
}
$newparams = Sanitizer::fixTagAttributes( $params, $t );
$rest = str_replace( '>', '>', $rest );
$text .= "<$slash$t$newparams$brace$rest";
} else {
$text .= '<' . str_replace( '>', '>', $x);
}
}
}
wfProfileOut( __METHOD__ );
return $text;
}
/**
* Remove '<!--', '-->', and everything between.
* To avoid leaving blank lines, when a comment is both preceded
* and followed by a newline (ignoring spaces), trim leading and
* trailing spaces and one of the newlines.
*
* @private
* @param $text String
* @return string
*/
static function removeHTMLcomments( $text ) {
wfProfileIn( __METHOD__ );
while (($start = strpos($text, '<!--')) !== false) {
$end = strpos($text, '-->', $start + 4);
if ($end === false) {
# Unterminated comment; bail out
break;
}
$end += 3;
# Trim space and newline if the comment is both
# preceded and followed by a newline
$spaceStart = max($start - 1, 0);
$spaceLen = $end - $spaceStart;
while (substr($text, $spaceStart, 1) === ' ' && $spaceStart > 0) {
$spaceStart--;
$spaceLen++;
}
while (substr($text, $spaceStart + $spaceLen, 1) === ' ')
$spaceLen++;
if (substr($text, $spaceStart, 1) === "\n" and substr($text, $spaceStart + $spaceLen, 1) === "\n") {
# Remove the comment, leading and trailing
# spaces, and leave only one newline.
$text = substr_replace($text, "\n", $spaceStart, $spaceLen + 1);
}
else {
# Remove just the comment.
$text = substr_replace($text, '', $start, $end - $start);
}
}
wfProfileOut( __METHOD__ );
return $text;
}
/**
* Take an array of attribute names and values and normalize or discard
* illegal values for the given element type.
*
* - Discards attributes not on a whitelist for the given element
* - Unsafe style attributes are discarded
* - Invalid id attributes are reencoded
*
* @param $attribs Array
* @param $element String
* @return Array
*
* @todo Check for legal values where the DTD limits things.
* @todo Check for unique id attribute :P
*/
static function validateTagAttributes( $attribs, $element ) {
return Sanitizer::validateAttributes( $attribs,
Sanitizer::attributeWhitelist( $element ) );
}
/**
* Take an array of attribute names and values and normalize or discard
* illegal values for the given whitelist.
*
* - Discards attributes not the given whitelist
* - Unsafe style attributes are discarded
* - Invalid id attributes are reencoded
*
* @param $attribs Array
* @param $whitelist Array: list of allowed attribute names
* @return Array
*
* @todo Check for legal values where the DTD limits things.
* @todo Check for unique id attribute :P
*/
static function validateAttributes( $attribs, $whitelist ) {
$whitelist = array_flip( $whitelist );
$out = array();
foreach( $attribs as $attribute => $value ) {
if( !isset( $whitelist[$attribute] ) ) {
continue;
}
# Strip javascript "expression" from stylesheets.
# http://msdn.microsoft.com/workshop/author/dhtml/overview/recalc.asp
if( $attribute == 'style' ) {
$value = Sanitizer::checkCss( $value );
if( $value === false ) {
# haxx0r
continue;
}
}
if ( $attribute === 'id' ) {
global $wgEnforceHtmlIds;
$value = Sanitizer::escapeId( $value,
$wgEnforceHtmlIds ? 'noninitial' : 'xml' );
}
// If this attribute was previously set, override it.
// Output should only have one attribute of each name.
$out[$attribute] = $value;
}
return $out;
}
/**
* Merge two sets of HTML attributes. Conflicting items in the second set
* will override those in the first, except for 'class' attributes which
* will be combined (if they're both strings).
*
* @todo implement merging for other attributes such as style
* @param $a Array
* @param $b Array
* @return array
*/
static function mergeAttributes( $a, $b ) {
$out = array_merge( $a, $b );
if( isset( $a['class'] ) && isset( $b['class'] )
&& is_string( $a['class'] ) && is_string( $b['class'] )
&& $a['class'] !== $b['class'] ) {
$classes = preg_split( '/\s+/', "{$a['class']} {$b['class']}",
-1, PREG_SPLIT_NO_EMPTY );
$out['class'] = implode( ' ', array_unique( $classes ) );
}
return $out;
}
/**
* Pick apart some CSS and check it for forbidden or unsafe structures.
* Returns a sanitized string, or false if it was just too evil.
*
* Currently URL references, 'expression', 'tps' are forbidden.
*
* @param $value String
* @return Mixed
*/
static function checkCss( $value ) {
$stripped = Sanitizer::decodeCharReferences( $value );
// Remove any comments; IE gets token splitting wrong
$stripped = StringUtils::delimiterReplace( '/*', '*/', ' ', $stripped );
$value = $stripped;
// ... and continue checks
$stripped = preg_replace( '!\\\\([0-9A-Fa-f]{1,6})[ \\n\\r\\t\\f]?!e',
'codepointToUtf8(hexdec("$1"))', $stripped );
$stripped = str_replace( '\\', '', $stripped );
if( preg_match( '/(?:expression|tps*:\/\/|url\\s*\().*/is',
$stripped ) ) {
# haxx0r
return false;
}
return $value;
}
/**
* Take a tag soup fragment listing an HTML element's attributes
* and normalize it to well-formed XML, discarding unwanted attributes.
* Output is safe for further wikitext processing, with escaping of
* values that could trigger problems.
*
* - Normalizes attribute names to lowercase
* - Discards attributes not on a whitelist for the given element
* - Turns broken or invalid entities into plaintext
* - Double-quotes all attribute values
* - Attributes without values are given the name as attribute
* - Double attributes are discarded
* - Unsafe style attributes are discarded
* - Prepends space if there are attributes.
*
* @param $text String
* @param $element String
* @return String
*/
static function fixTagAttributes( $text, $element ) {
if( trim( $text ) == '' ) {
return '';
}
$stripped = Sanitizer::validateTagAttributes(
Sanitizer::decodeTagAttributes( $text ), $element );
$attribs = array();
foreach( $stripped as $attribute => $value ) {
$encAttribute = htmlspecialchars( $attribute );
$encValue = Sanitizer::safeEncodeAttribute( $value );
$attribs[] = "$encAttribute=\"$encValue\"";
}
return count( $attribs ) ? ' ' . implode( ' ', $attribs ) : '';
}
/**
* Encode an attribute value for HTML output.
* @param $text String
* @return HTML-encoded text fragment
*/
static function encodeAttribute( $text ) {
$encValue = htmlspecialchars( $text, ENT_QUOTES );
// Whitespace is normalized during attribute decoding,
// so if we've been passed non-spaces we must encode them
// ahead of time or they won't be preserved.
$encValue = strtr( $encValue, array(
"\n" => ' ',
"\r" => ' ',
"\t" => '	',
) );
return $encValue;
}
/**
* Encode an attribute value for HTML tags, with extra armoring
* against further wiki processing.
* @param $text String
* @return HTML-encoded text fragment
*/
static function safeEncodeAttribute( $text ) {
$encValue = Sanitizer::encodeAttribute( $text );
# Templates and links may be expanded in later parsing,
# creating invalid or dangerous output. Suppress this.
$encValue = strtr( $encValue, array(
'<' => '<', // This should never happen,
'>' => '>', // we've received invalid input
'"' => '"', // which should have been escaped.
'{' => '{',
'[' => '[',
"''" => '''',
'ISBN' => 'ISBN',
'RFC' => 'RFC',
'PMID' => 'PMID',
'|' => '|',
'__' => '__',
) );
# Stupid hack
$encValue = preg_replace_callback(
'/(' . wfUrlProtocols() . ')/',
array( 'Sanitizer', 'armorLinksCallback' ),
$encValue );
return $encValue;
}
/**
* Given a value escape it so that it can be used in an id attribute and
* return it, this does not validate the value however (see first link)
*
* @see http://www.w3.org/TR/html401/types.html#type-name Valid characters
* in the id and
* name attributes
* @see http://www.w3.org/TR/html401/struct/links.html#h-12.2.3 Anchors with the id attribute
*
* @param $id String: id to validate
* @param $options Mixed: string or array of strings (default is array()):
* 'noninitial': This is a non-initial fragment of an id, not a full id,
* so don't pay attention if the first character isn't valid at the
* beginning of an id.
* 'xml': Don't restrict the id to be HTML4-compatible. This option
* allows any alphabetic character to be used, per the XML standard.
* Therefore, it also completely changes the type of escaping: instead
* of weird dot-encoding, runs of invalid characters (mostly
* whitespace) are just compressed into a single underscore.
* @return String
*/
static function escapeId( $id, $options = array() ) {
$options = (array)$options;
if ( !in_array( 'xml', $options ) ) {
# HTML4-style escaping
static $replace = array(
'%3A' => ':',
'%' => '.'
);
$id = urlencode( Sanitizer::decodeCharReferences( strtr( $id, ' ', '_' ) ) );
$id = str_replace( array_keys( $replace ), array_values( $replace ), $id );
if ( !preg_match( '/^[a-zA-Z]/', $id )
&& !in_array( 'noninitial', $options ) ) {
// Initial character must be a letter!
$id = "x$id";
}
return $id;
}
# XML-style escaping. For the patterns used, see the XML 1.0 standard,
# 5th edition, NameStartChar and NameChar: <http://www.w3.org/TR/REC-xml/>
$nameStartChar = ':a-zA-Z_\xC0-\xD6\xD8-\xF6\xF8-\x{2FF}\x{370}-\x{37D}'
. '\x{37F}-\x{1FFF}\x{200C}-\x{200D}\x{2070}-\x{218F}\x{2C00}-\x{2FEF}'
. '\x{3001}-\x{D7FF}\x{F900}-\x{FDCF}\x{FDF0}-\x{FFFD}\x{10000}-\x{EFFFF}';
$nameChar = $nameStartChar . '.\-0-9\xB7\x{0300}-\x{036F}'
. '\x{203F}-\x{2040}';
# Replace _ as well so we don't get multiple consecutive underscores
$id = preg_replace( "/([^$nameChar]|_)+/u", '_', $id );
$id = trim( $id, '_' );
if ( !preg_match( "/^[$nameStartChar]/u", $id )
&& !in_array( 'noninitial', $options ) ) {
$id = "_$id";
}
return $id;
}
/**
* Given a value, escape it so that it can be used as a CSS class and
* return it.
*
* @todo For extra validity, input should be validated UTF-8.
*
* @see http://www.w3.org/TR/CSS21/syndata.html Valid characters/format
*
* @param $class String
* @return String
*/
static function escapeClass( $class ) {
// Convert ugly stuff to underscores and kill underscores in ugly places
return rtrim(preg_replace(
array('/(^[0-9\\-])|[\\x00-\\x20!"#$%&\'()*+,.\\/:;<=>?@[\\]^`{|}~]|\\xC2\\xA0/','/_+/'),
'_',
$class ), '_');
}
/**
* Given HTML input, escape with htmlspecialchars but un-escape entites.
* This allows (generally harmless) entities like to survive.
*
* @param $html String to escape
* @return String: escaped input
*/
static function escapeHtmlAllowEntities( $html ) {
# It seems wise to escape ' as well as ", as a matter of course. Can't
# hurt.
$html = htmlspecialchars( $html, ENT_QUOTES );
$html = str_replace( '&', '&', $html );
$html = Sanitizer::normalizeCharReferences( $html );
return $html;
}
/**
* Regex replace callback for armoring links against further processing.
* @param $matches Array
* @return string
*/
private static function armorLinksCallback( $matches ) {
return str_replace( ':', ':', $matches[1] );
}
/**
* Return an associative array of attribute names and values from
* a partial tag string. Attribute names are forces to lowercase,
* character references are decoded to UTF-8 text.
*
* @param $text String
* @return Array
*/
public static function decodeTagAttributes( $text ) {
$attribs = array();
if( trim( $text ) == '' ) {
return $attribs;
}
$pairs = array();
if( !preg_match_all(
MW_ATTRIBS_REGEX,
$text,
$pairs,
PREG_SET_ORDER ) ) {
return $attribs;
}
foreach( $pairs as $set ) {
$attribute = strtolower( $set[1] );
$value = Sanitizer::getTagAttributeCallback( $set );
// Normalize whitespace
$value = preg_replace( '/[\t\r\n ]+/', ' ', $value );
$value = trim( $value );
// Decode character references
$attribs[$attribute] = Sanitizer::decodeCharReferences( $value );
}
return $attribs;
}
/**
* Pick the appropriate attribute value from a match set from the
* MW_ATTRIBS_REGEX matches.
*
* @param $set Array
* @return String
*/
private static function getTagAttributeCallback( $set ) {
if( isset( $set[6] ) ) {
# Illegal #XXXXXX color with no quotes.
return $set[6];
} elseif( isset( $set[5] ) ) {
# No quotes.
return $set[5];
} elseif( isset( $set[4] ) ) {
# Single-quoted
return $set[4];
} elseif( isset( $set[3] ) ) {
# Double-quoted
return $set[3];
} elseif( !isset( $set[2] ) ) {
# In XHTML, attributes must have a value.
# For 'reduced' form, return explicitly the attribute name here.
return $set[1];
} else {
throw new MWException( "Tag conditions not met. This should never happen and is a bug." );
}
}
/**
* Normalize whitespace and character references in an XML source-
* encoded text for an attribute value.
*
* See http://www.w3.org/TR/REC-xml/#AVNormalize for background,
* but note that we're not returning the value, but are returning
* XML source fragments that will be slapped into output.
*
* @param $text String
* @return String
*/
private static function normalizeAttributeValue( $text ) {
return str_replace( '"', '"',
self::normalizeWhitespace(
Sanitizer::normalizeCharReferences( $text ) ) );
}
private static function normalizeWhitespace( $text ) {
return preg_replace(
'/\r\n|[\x20\x0d\x0a\x09]/',
' ',
$text );
}
/**
* Ensure that any entities and character references are legal
* for XML and XHTML specifically. Any stray bits will be
* &-escaped to result in a valid text fragment.
*
* a. any named char refs must be known in XHTML
* b. any numeric char refs must be legal chars, not invalid or forbidden
* c. use &#x, not &#X
* d. fix or reject non-valid attributes
*
* @param $text String
* @return String
* @private
*/
static function normalizeCharReferences( $text ) {
return preg_replace_callback(
MW_CHAR_REFS_REGEX,
array( 'Sanitizer', 'normalizeCharReferencesCallback' ),
$text );
}
/**
* @param $matches String
* @return String
*/
static function normalizeCharReferencesCallback( $matches ) {
$ret = null;
if( $matches[1] != '' ) {