1 package com.android.mail.utils;
2 
3 import android.test.AndroidTestCase;
4 import android.test.suitebuilder.annotation.SmallTest;
5 
6 /**
7  * These test cases verify that each white listed element and attribute is accepted by the sanitizer
8  * and everything else is correctly discarded.
9  */
10 @SmallTest
11 public class BasicHtmlSanitizerTest extends AndroidTestCase {
testAttributeDir()12     public void testAttributeDir() {
13         sanitize("<div dir=\"ltr\">something</div>", "<div dir=\"ltr\">something</div>");
14         sanitize("<div dir=\"rtl\">something</div>", "<div dir=\"rtl\">something</div>");
15         sanitize("<div dir=\"LTR\">something</div>", "<div dir=\"ltr\">something</div>");
16         sanitize("<div dir=\"RTL\">something</div>", "<div dir=\"rtl\">something</div>");
17         sanitize("<div dir=\"blah\">something</div>", "<div>something</div>");
18     }
19 
testA()20     public void testA() {
21         // allowed attributes
22         sanitize("<a coords=\"something\"></a>", "<a coords=\"something\"></a>");
23         sanitize("<a href=\"http://www.here.com\"></a>", "<a href=\"http://www.here.com\"></a>");
24         sanitize("<a href=\"https://www.here.com\"></a>", "<a href=\"https://www.here.com\"></a>");
25         sanitize("<a name=\"something\"></a>", "<a name=\"something\"></a>");
26         sanitize("<a shape=\"something\"></a>", "<a shape=\"something\"></a>");
27 
28         // disallowed attributes (all links should launch a browser so we don't need these)
29         sanitize("<a charset=\"something\"></a>", "");
30         sanitize("<a datafld=\"something\"></a>", "");
31         sanitize("<a datasrc=\"something\"></a>", "");
32         sanitize("<a download=\"something\"></a>", "");
33         sanitize("<a href=\"javascript:badness()\"></a>", "");
34         sanitize("<a href=\"cid:ii_hyw5v8ej0\"></a>", "");
35         sanitize("<a hreflang=\"something\"></a>", "");
36         sanitize("<a media=\"something\"></a>", "");
37         sanitize("<a methods=\"something\"></a>", "");
38         sanitize("<a ping=\"something\"></a>", "");
39         sanitize("<a rel=\"something\"></a>", "");
40         sanitize("<a rev=\"something\"></a>", "");
41         sanitize("<a target=\"_top\"></a>", "");
42         sanitize("<a type=\"_top\"></a>", "");
43         sanitize("<a urn=\"_top\"></a>", "");
44         sanitize("<a onmouseout=\"alert(document.cookie)\">xxs link</a>", "xxs link");
45         sanitize("<a onmouseover=\"alert(document.cookie)\">xxs link</a>", "xxs link");
46         sanitize("<a onmouseover=alert(document.cookie)>xxs link</a>", "xxs link");
47         sanitize("exp/*<a style='no\\xss:noxss(\"*//*\");\n" +
48                 "xss:ex/*XSS*//*/*/pression(alert(\"XSS\"))'>", "exp/*");
49     }
50 
testAbbr()51     public void testAbbr() {
52         sanitize("<abbr title=\"United Kingdom\">UK</abbr>",
53                 "<abbr title=\"United Kingdom\">UK</abbr>");
54     }
55 
testAcronym()56     public void testAcronym() {
57         sanitize("<acronym title=\"World Wide Web\">WWW</acronym>",
58                 "<acronym title=\"World Wide Web\">WWW</acronym>");
59     }
60 
testAddress()61     public void testAddress() {
62         sanitize("<address>something</address>", "<address>something</address>");
63     }
64 
testApplet()65     public void testApplet() {
66         // todo Gmail would also strip "malicious applet" as well... is this a problem?
67         sanitize("<applet>malicious applet</applet>", "malicious applet");
68     }
69 
testArea()70     public void testArea() {
71         // allowed attributes
72         sanitize("<area alt=\"something\"/>", "<area alt=\"something\" />");
73         sanitize("<area coords=\"something\"/>", "<area coords=\"something\" />");
74         sanitize("<area href=\"http://www.here.com\"/>", "<area href=\"http://www.here.com\" />");
75         sanitize("<area href=\"https://www.here.com\"/>", "<area href=\"https://www.here.com\" />");
76         sanitize("<area name=\"something\"/>", "<area name=\"something\" />");
77         sanitize("<area nohref />", "<area nohref=\"nohref\" />");
78         sanitize("<area shape=\"something\"/>", "<area shape=\"something\" />");
79 
80         // disallowed attributes (all links launch a browser so we don't need these attributes)
81         sanitize("<area accessKey=\"A\"/>", "<area />");
82         sanitize("<area download=\"something\"/>", "<area />");
83         sanitize("<area href=\"javascript:badness()\"/>", "<area />");
84         sanitize("<area href=\"cid:ii_hyw5v8ej0\"/>", "<area />");
85         sanitize("<area hreflang=\"something\"/>", "<area />");
86         sanitize("<area media=\"something\"/>", "<area />");
87         sanitize("<area rel=\"something\"/>", "<area />");
88         sanitize("<area target=\"something\"/>", "<area />");
89         sanitize("<area tabindex=\"something\"/>", "<area />");
90         sanitize("<area type=\"something\"/>", "<area />");
91     }
92 
testArticle()93     public void testArticle() {
94         sanitize("<article></article>", "<article></article>");
95     }
96 
testAside()97     public void testAside() {
98         sanitize("<aside></aside>", "<aside></aside>");
99     }
100 
testAudio()101     public void testAudio() {
102         sanitize("<audio>not supported</audio>", "not supported");
103     }
104 
testB()105     public void testB() {
106         sanitize("<b>something</b>", "<b>something</b>");
107     }
108 
testBase()109     public void testBase() {
110         // allowed attributes
111         sanitize("<base href=\"http://www.example.com/\">",
112                 "<base href=\"http://www.example.com/\" />");
113         sanitize("<base href=\"https://www.example.com/\">",
114                 "<base href=\"https://www.example.com/\" />");
115 
116         // disallowed attributes
117         sanitize("<base target=\"_blank\">", "<base />");
118         sanitize("<base href=\"javascript:badness()\">", "<base />");
119         sanitize("<base href=\"cid:ii_hyw5v8ej0\">", "<base />");
120         sanitize("<base href=\"javascript:alert('XSS');//\">", "<base />");
121     }
122 
testBasefont()123     public void testBasefont() {
124         sanitize("<basefont color=\"something\"/>", "");
125         sanitize("<basefont face=\"something\"/>", "");
126         sanitize("<basefont size=\"something\"/>", "");
127     }
128 
testBdi()129     public void testBdi() {
130         sanitize("<bdi>something</bdi>", "<bdi>something</bdi>");
131         sanitize("<bdi dir=\"ltr\">something</bdi>", "<bdi dir=\"ltr\">something</bdi>");
132     }
133 
testBdo()134     public void testBdo() {
135         sanitize("<bdo>something</bdo>", "<bdo>something</bdo>");
136         sanitize("<bdo dir=\"ltr\">something</bdo>", "<bdo dir=\"ltr\">something</bdo>");
137     }
138 
testBgsound()139     public void testBgsound() {
140         sanitize("<bgsound src=\"sound1.mid\">", "");
141         sanitize("<bgsound src=\"javascript:alert('XSS');\">", "");
142     }
143 
testBig()144     public void testBig() {
145         sanitize("<big>something</big>", "<big>something</big>");
146     }
147 
testBlink()148     public void testBlink() {
149         sanitize("<blink>something</blink>", "something");
150     }
151 
testBlockquote()152     public void testBlockquote() {
153         sanitize("<blockquote>something</blockquote>", "<blockquote>something</blockquote>");
154         sanitize("<blockquote cite=\"http://www.here.com\">something</blockquote>",
155                 "<blockquote cite=\"http://www.here.com\">something</blockquote>");
156         sanitize("<blockquote cite=\"javascript:badness()\">something</blockquote>",
157                 "<blockquote>something</blockquote>");
158 
159         sanitize("<blockquote style=\"margin:0;margin-left:0.8ex;border-left:1px #ccc solid;" +
160                 "padding-left:1ex\">",
161                 "<blockquote style=\"margin:0;margin-left:0.8ex;border-left:1px #ccc solid;" +
162                         "padding-left:1ex\"></blockquote>");
163     }
164 
165     /**
166      * The body tag will be supplied by code that wraps this email with other formatting logic.
167      * So, any body tags appearing within the email are translated to div tags.
168      */
testBody()169     public void testBody() {
170         sanitize("<body alink=\"something\"></body>", "<div></div>");
171         sanitize("<body background=\"something\"></body>", "<div></div>");
172         sanitize("<body bgcolor=\"something\"></body>", "<div></div>");
173         sanitize("<body link=\"something\"></body>", "<div></div>");
174         sanitize("<body text=\"something\"></body>", "<div></div>");
175         sanitize("<body vlink=\"something\"></body>", "<div></div>");
176 
177         // take extra care to ensure that these scripting callbacks don't survive
178         sanitize("<body onafterprint=\"something\"></body>", "<div></div>");
179         sanitize("<body onbeforeprint=\"something\"></body>", "<div></div>");
180         sanitize("<body onbeforeunload=\"something\"></body>", "<div></div>");
181         sanitize("<body onblur=\"something\"></body>", "<div></div>");
182         sanitize("<body onerror=\"something\"></body>", "<div></div>");
183         sanitize("<body onfocus=\"something\"></body>", "<div></div>");
184         sanitize("<body onhashchange=\"something\"></body>", "<div></div>");
185         sanitize("<body onload=\"something\"></body>", "<div></div>");
186         sanitize("<body onmessage=\"something\"></body>", "<div></div>");
187         sanitize("<body onoffline=\"something\"></body>", "<div></div>");
188         sanitize("<body ononline=\"something\"></body>", "<div></div>");
189         sanitize("<body onpopstate=\"something\"></body>", "<div></div>");
190         sanitize("<body onredo=\"something\"></body>", "<div></div>");
191         sanitize("<body onresize=\"something\"></body>", "<div></div>");
192         sanitize("<body onstorage=\"something\"></body>", "<div></div>");
193         sanitize("<body onundo=\"something\"></body>", "<div></div>");
194         sanitize("<body onunload=\"something\"></body>", "<div></div>");
195         sanitize("<body onload!#$%&()*~+-_.,:;?@[/|\\]^`=alert(\"XSS\")>", "<div></div>");
196         sanitize("<body background=\"javascript:alert('XSS')\">", "<div></div>");
197         sanitize("<body onload=alert('XSS')>", "<div></div>");
198         sanitize("<body onload =alert('XSS')>", "<div></div>");
199     }
200 
testBr()201     public void testBr() {
202         sanitize("something<br>something", "something<br />something");
203         sanitize("something<br clear=\"all\">something", "something<br clear=\"all\" />something");
204     }
205 
testButton()206     public void testButton() {
207         sanitize("<button>Click Me!</button>", "<button>Click Me!</button>");
208         sanitize("<button autofocus=\"true\">Click Me!</button>",
209                 "<button autofocus=\"true\">Click Me!</button>");
210         sanitize("<button disabled=\"true\">Click Me!</button>",
211                 "<button disabled=\"true\">Click Me!</button>");
212         sanitize("<button formenctype=\"text/plain\">Click Me!</button>",
213                 "<button formenctype=\"text/plain\">Click Me!</button>");
214         sanitize("<button formmethod=\"post\">Click Me!</button>",
215                 "<button formmethod=\"post\">Click Me!</button>");
216         sanitize("<button formnovalidate=\"formnovalidate\">Click Me!</button>",
217                 "<button formnovalidate=\"formnovalidate\">Click Me!</button>");
218         sanitize("<button formtarget=\"_top\">Click Me!</button>",
219                 "<button formtarget=\"_top\">Click Me!</button>");
220         sanitize("<button name=\"something\">Click Me!</button>",
221                 "<button name=\"something\">Click Me!</button>");
222         sanitize("<button type=\"button\">Click Me!</button>",
223                 "<button type=\"button\">Click Me!</button>");
224         sanitize("<button value=\"something\">Click Me!</button>",
225                 "<button value=\"something\">Click Me!</button>");
226         sanitize("<button formaction=\"http://www.overhere.com/\">Click Me!</button>",
227                 "<button formaction=\"http://www.overhere.com/\">Click Me!</button>");
228 
229         sanitize("<button formaction=\"javascript:badness()\">Click Me!</button>",
230                 "<button>Click Me!</button>");
231     }
232 
testCanvas()233     public void testCanvas() {
234         sanitize("<canvas></canvas>", "<canvas></canvas>");
235         sanitize("<canvas width=\"500\"></canvas>", "<canvas width=\"500\"></canvas>");
236         sanitize("<canvas height=\"500\"></canvas>", "<canvas height=\"500\"></canvas>");
237     }
238 
testCaption()239     public void testCaption() {
240         sanitize("<caption>something</caption>", "<caption>something</caption>");
241         sanitize("<caption align=\"left\">something</caption>",
242                 "<caption align=\"left\">something</caption>");
243     }
244 
testCenter()245     public void testCenter() {
246         sanitize("<center>something</center>", "<center>something</center>");
247     }
248 
testCite()249     public void testCite() {
250         sanitize("<cite>something</cite>", "<cite>something</cite>");
251     }
252 
testCode()253     public void testCode() {
254         sanitize("<code>something</code>", "<code>something</code>");
255     }
256 
testCol()257     public void testCol() {
258         sanitize("<col>", "<col />");
259         sanitize("<col align=\"left\">", "<col align=\"left\" />");
260         sanitize("<col bgcolor=\"something\">", "<col bgcolor=\"something\" />");
261         sanitize("<col char=\"something\">", "<col char=\"something\" />");
262         sanitize("<col charoff=\"something\">", "<col charoff=\"something\" />");
263         sanitize("<col span=\"something\">", "<col span=\"something\" />");
264         sanitize("<col valign=\"something\">", "<col valign=\"something\" />");
265         sanitize("<col width=\"something\">", "<col width=\"something\" />");
266     }
267 
testColgroup()268     public void testColgroup() {
269         sanitize("<colgroup></colgroup>", "<colgroup></colgroup>");
270         sanitize("<colgroup align=\"left\"></colgroup>", "<colgroup align=\"left\"></colgroup>");
271         sanitize("<colgroup char=\"something\"></colgroup>",
272                 "<colgroup char=\"something\"></colgroup>");
273         sanitize("<colgroup charoff=\"something\"></colgroup>",
274                 "<colgroup charoff=\"something\"></colgroup>");
275         sanitize("<colgroup span=\"something\"></colgroup>",
276                 "<colgroup span=\"something\"></colgroup>");
277         sanitize("<colgroup valign=\"something\"></colgroup>",
278                 "<colgroup valign=\"something\"></colgroup>");
279         sanitize("<colgroup width=\"something\"></colgroup>",
280                 "<colgroup width=\"something\"></colgroup>");
281     }
282 
testDatalist()283     public void testDatalist() {
284         sanitize("<datalist></datalist>", "<datalist></datalist>");
285     }
286 
testDd()287     public void testDd() {
288         sanitize("<dd>something</dd>", "<dd>something</dd>");
289     }
290 
testDel()291     public void testDel() {
292         sanitize("<del>something</del>", "<del>something</del>");
293         sanitize("<del cite=\"javascript:badness();\">something</del>", "<del>something</del>");
294         sanitize("<del cite=\"http://www.reason.com/\">something</del>",
295                 "<del cite=\"http://www.reason.com/\">something</del>");
296         sanitize("<del datetime=\"something\">something</del>",
297                 "<del datetime=\"something\">something</del>");
298     }
299 
testDetails()300     public void testDetails() {
301         sanitize("<details>something</details>", "<details>something</details>");
302     }
303 
testDfn()304     public void testDfn() {
305         sanitize("<dfn>something</dfn>", "<dfn>something</dfn>");
306     }
307 
testDialog()308     public void testDialog() {
309         sanitize("<dialog open>This is an open dialog window</dialog>",
310                 "This is an open dialog window");
311     }
312 
testDir()313     public void testDir() {
314         sanitize("<dir><li>something</li></dir>", "<dir><li>something</li></dir>");
315         sanitize("<dir compact=\"compact\"><li>something</li></dir>",
316                 "<dir compact=\"compact\"><li>something</li></dir>");
317     }
318 
testDiv()319     public void testDiv() {
320         sanitize("<div></div>", "<div></div>");
321         sanitize("<div align=\"left\"></div>", "<div align=\"left\"></div>");
322         sanitize("<div background=\"http://www.random.com/mypng.gif\"></div>",
323                 "<div background=\"http://www.random.com/mypng.gif\"></div>");
324 
325         sanitize("<div background=\"javascript:badness();\"></div>", "<div></div>");
326         sanitize("<div style=\"width: expression(alert('XSS'));\">", "<div></div>");
327         sanitize("<div style=\"background-image: url(javascript:alert('XSS'))\">", "<div></div>");
328         sanitize("<div style=\"background-image:\\0075\\0072\\006C\\0028'\\006a\\0061\\0076\\0061" +
329                 "\\0073\\0063\\0072\\0069\\0070\\0074\\003a\\0061\\006c\\0065\\0072\\0074" +
330                 "\\0028.1027\\0058.1053\\0053\\0027\\0029'\\0029\">", "<div></div>");
331         sanitize("<div style=\"background-image: url(&#1;javascript:alert('XSS'))\">",
332                 "<div></div>");
333     }
334 
testDl()335     public void testDl() {
336         sanitize("<dl></dl>", "<dl></dl>");
337     }
338 
testDt()339     public void testDt() {
340         sanitize("<dt></dt>", "<dt></dt>");
341     }
342 
testEm()343     public void testEm() {
344         sanitize("<em>something</em>", "<em>something</em>");
345     }
346 
testEmbed()347     public void testEmbed() {
348         sanitize("<embed src=\"helloworld.swf\">", "");
349     }
350 
testFieldset()351     public void testFieldset() {
352         sanitize("<fieldset>something</fieldset>", "<fieldset>something</fieldset>");
353         sanitize("<fieldset disabled=\"true\">something</fieldset>",
354                 "<fieldset disabled=\"true\">something</fieldset>");
355         sanitize("<fieldset form=\"formId\">something</fieldset>",
356                 "<fieldset form=\"formId\">something</fieldset>");
357         sanitize("<fieldset name=\"something\">something</fieldset>",
358                 "<fieldset name=\"something\">something</fieldset>");
359     }
360 
testFigcaption()361     public void testFigcaption() {
362         sanitize("<figcaption>Fig1. something</figcaption>",
363                 "<figcaption>Fig1. something</figcaption>");
364     }
365 
testFigure()366     public void testFigure() {
367         sanitize("<figure>something</figure>", "<figure>something</figure>");
368     }
369 
testFont()370     public void testFont() {
371         sanitize("<font>something</font>", "something");
372         sanitize("<font size=\"3\">something</font>", "<font size=\"3\">something</font>");
373         sanitize("<font face=\"verdana\">something</font>",
374                 "<font face=\"verdana\">something</font>");
375         sanitize("<font color=\"red\">something</font>", "<font color=\"red\">something</font>");
376     }
377 
testFooter()378     public void testFooter() {
379         sanitize("<footer>something</footer>", "<footer>something</footer>");
380     }
381 
testForm()382     public void testForm() {
383         sanitize("<form></form>", "<form></form>");
384         sanitize("<form accept=\"something\"></form>", "<form accept=\"something\"></form>");
385         sanitize("<form accept-charset=\"something\"></form>",
386                 "<form accept-charset=\"something\"></form>");
387         sanitize("<form autocomplete=\"on\"></form>", "<form autocomplete=\"on\"></form>");
388         sanitize("<form enctype=\"text/plain\"></form>", "<form enctype=\"text/plain\"></form>");
389         sanitize("<form method=\"get\"></form>", "<form method=\"get\"></form>");
390         sanitize("<form name=\"something\"></form>", "<form name=\"something\"></form>");
391         sanitize("<form novalidate=\"novalidate\"></form>",
392                 "<form novalidate=\"novalidate\"></form>");
393         sanitize("<form target=\"_top\"></form>", "<form target=\"_top\"></form>");
394         sanitize("<form action=\"http://www.overhere.com/\"></form>",
395                 "<form action=\"http://www.overhere.com/\"></form>");
396 
397         sanitize("<form action=\"javascript:badness()\"></form>", "<form></form>");
398         sanitize("<form onsubmit=\"javascript:badness()\"></form>", "<form></form>");
399         sanitize("<form onreset=\"javascript:badness()\"></form>", "<form></form>");
400     }
401 
testFrame()402     public void testFrame() {
403         sanitize("<frame src=\"frame_a.htm\">", "");
404     }
405 
testFrameset()406     public void testFrameset() {
407         sanitize("<frameset cols=\"25%,*,25%\"></frameset>", "");
408         sanitize("<frameset><frame src=\"javascript:alert('XSS');\"></frameset>", "");
409     }
410 
testHead()411     public void testHead() {
412         sanitize("<head></head>", "");
413         sanitize("<head profile=\"http://www.overhere.com/\"></head>", "");
414         sanitize("<head profile=\"javascript:badness()\"></head>", "");
415     }
416 
testHeader()417     public void testHeader() {
418         sanitize("<header></header>", "<header></header>");
419     }
420 
testH1()421     public void testH1() {
422         sanitize("<h1>something</h1>", "<h1>something</h1>");
423         sanitize("<h1 align=\"left\">something</h1>", "<h1 align=\"left\">something</h1>");
424     }
425 
testH2()426     public void testH2() {
427         sanitize("<h2>something</h2>", "<h2>something</h2>");
428         sanitize("<h2 align=\"left\">something</h2>", "<h2 align=\"left\">something</h2>");
429     }
430 
testH3()431     public void testH3() {
432         sanitize("<h3>something</h3>", "<h3>something</h3>");
433         sanitize("<h3 align=\"left\">something</h3>", "<h3 align=\"left\">something</h3>");
434     }
435 
testH4()436     public void testH4() {
437         sanitize("<h4>something</h4>", "<h4>something</h4>");
438         sanitize("<h4 align=\"left\">something</h4>", "<h4 align=\"left\">something</h4>");
439     }
440 
testH5()441     public void testH5() {
442         sanitize("<h5>something</h5>", "<h5>something</h5>");
443         sanitize("<h5 align=\"left\">something</h5>", "<h5 align=\"left\">something</h5>");
444     }
445 
testH6()446     public void testH6() {
447         sanitize("<h6>something</h6>", "<h6>something</h6>");
448         sanitize("<h6 align=\"left\">something</h6>", "<h6 align=\"left\">something</h6>");
449     }
450 
testHr()451     public void testHr() {
452         sanitize("<hr/>", "<hr />");
453         sanitize("<hr align=\"left\"/>", "<hr align=\"left\" />");
454         sanitize("<hr noshade=\"noshade\"/>", "<hr noshade=\"noshade\" />");
455         sanitize("<hr size=\"11\"/>", "<hr size=\"11\" />");
456         sanitize("<hr width=\"666\"/>", "<hr width=\"666\" />");
457     }
458 
testHtml()459     public void testHtml() {
460         sanitize("<html></html>", "");
461         sanitize("<html xmlns=\"http://www.w3.org/1999/xhtml\"></html>", "");
462         sanitize("<html manifest=\"http://www.overhere.com/\"></html>", "");
463         sanitize("<html manifest=\"javascript:badness()\"></html>", "");
464     }
465 
testI()466     public void testI() {
467         sanitize("<i></i>", "<i></i>");
468     }
469 
testIframe()470     public void testIframe() {
471         sanitize("<iframe src=\"http://www.w3schools.com\"></iframe>", "");
472         sanitize("<iframe src=http://ha.ckers.org/scriptlet.html <", "");
473         sanitize("<iframe src=\"javascript:alert('XSS');\"></iframe>", "");
474         sanitize("<iframe src=# onmouseover=\"alert(document.cookie)\"></iframe>", "");
475     }
476 
testIsindex()477     public void testIsindex() {
478         sanitize("<isindex prompt=\"Search Document... \"/>", "");
479     }
480 
testImg()481     public void testImg() {
482         sanitize("<img/>", "");
483         sanitize("<img align=\"left\"/>", "<img align=\"left\" />");
484         sanitize("<img alt=\"something\"/>", "<img alt=\"something\" />");
485         sanitize("<img border=\"22\"/>", "<img border=\"22\" />");
486         sanitize("<img crossorigin=\"anonymous \"/>", "<img crossorigin=\"anonymous \" />");
487         sanitize("<img height=\"22\"/>", "<img height=\"22\" />");
488         sanitize("<img hspace=\"22\"/>", "<img hspace=\"22\" />");
489         sanitize("<img ismap=\"ismap\"/>", "<img ismap=\"ismap\" />");
490         sanitize("<img usemap=\"something\"/>", "<img usemap=\"something\" />");
491         sanitize("<img vspace=\"22\"/>", "<img vspace=\"22\" />");
492         sanitize("<img width=\"22\"/>", "<img width=\"22\" />");
493         sanitize("<img src=\"http://www.overhere.com/\"></img>",
494                 "<img src=\"http://www.overhere.com/\" />");
495         sanitize("<img src=\"https://www.overhere.com/\"></img>",
496                 "<img src=\"https://www.overhere.com/\" />");
497         sanitize("<img src=\"cid:ii_hyw5v8ej0\"></img>",
498                 "<img src=\"cid:ii_hyw5v8ej0\" />");
499         sanitize("<img longdesc=\"http://www.overhere.com/\"></img>",
500                 "<img longdesc=\"http://www.overhere.com/\" />");
501         sanitize("<img longdesc=\"https://www.overhere.com/\"></img>",
502                 "<img longdesc=\"https://www.overhere.com/\" />");
503 
504         sanitize("<img src=\"javascript:badness()\"></img>", "");
505         sanitize("<img longdesc=\"javascript:badness()\"></img>", "");
506         sanitize("<img longdesc=\"cid:ii_hyw5v8ej0\"></img>", "");
507         sanitize("<img src=javascript:alert('XSS')>", "");
508         sanitize("<img src=JaVaScRiPt:alert('XSS')>", "");
509         sanitize("<img src=javascript:alert(\"XSS\")>", "");
510         sanitize("<img src=`javascript:alert(\"RSnake says, 'XSS'\")`>", "");
511         sanitize("<img \"\"\"><script>alert(\"XSS\")</script>\">", "&#34;&gt;");
512         sanitize("<img src=# onmouseover=\"alert('xxs')\">", "<img src=\"#\" />");
513         sanitize("<img src= onmouseover=\"alert('xxs')\">", "<img src=\"onmouseover&#61;\" />");
514         sanitize("<img onmouseover=\"alert('xxs')\">", "");
515         sanitize("<img src=/ onerror=\"alert(String.fromCharCode(88,83,83))\"></img>",
516                 "<img src=\"/\" />");
517         sanitize("<img src=&#106;&#97;&#118;&#97;&#115;&#99;&#114;&#105;&#112;&#116;&#58;&#97;" +
518                 "&#108;&#101;&#114;&#116;&#40;\n&#39;&#88;&#83;&#83;&#39;&#41;>",
519                 "");
520         sanitize("<img src=&#0000106&#0000097&#0000118&#0000097&#0000115&#0000099&#0000114" +
521                 "&#0000105&#0000112&#0000116&#0000058&#0000097&\n" +
522                 "#0000108&#0000101&#0000114&#0000116&#0000040&#0000039&#0000088&#0000083&#0000083" +
523                 "&#0000039&#0000041>", "");
524         sanitize("<img src=&#x6A&#x61&#x76&#x61&#x73&#x63&#x72&#x69&#x70&#x74&#x3A&#x61&#x6C&#x65" +
525                 "&#x72&#x74&#x28&#x27&#x58&#x53&#x53&#x27&#x29>", "");
526         sanitize("<img src=\"jav\tascript:alert('XSS');\">", "");
527         sanitize("<img src=\"jav&#x09;ascript:alert('XSS');\">", "");
528         sanitize("<img src=\"jav&#x0A;ascript:alert('XSS');\">", "");
529         sanitize("<img src=\"jav&#x0D;ascript:alert('XSS');\">", "");
530         sanitize("<img src=java\0script:alert(\\\"XSS\\\")>", "");
531         sanitize("<img src=\" &#14;  javascript:alert('XSS');\">", "");
532         sanitize("<img src=\"javascript:alert('XSS')\"", "");
533         sanitize("<img dynsrc=\"javascript:alert('XSS')\">", "");
534         sanitize("<img lowsrc=\"javascript:alert('XSS')\">", "");
535         sanitize("<img src='vbscript:msgbox(\"XSS\")'>", "");
536         sanitize("<img src=\"livescript:[code]\">", "");
537         sanitize("<img style=\"xss:expr/*XSS*/ession(alert('XSS'))\">", "");
538     }
539 
testInput()540     public void testInput() {
541         sanitize("<input accept=\"image/*\"/>", "<input accept=\"image/*\" />");
542         sanitize("<input align=\"left\"/>", "<input align=\"left\" />");
543         sanitize("<input alt=\"something\"/>", "<input alt=\"something\" />");
544         sanitize("<input autocomplete=\"on\"/>", "<input autocomplete=\"on\" />");
545         sanitize("<input autofocus=\"autofocus\"/>", "<input autofocus=\"autofocus\" />");
546         sanitize("<input checked=\"checked\"/>", "<input checked=\"checked\" />");
547         sanitize("<input disabled=\"disabled\"/>", "<input disabled=\"disabled\" />");
548         sanitize("<input form=\"1\"/>", "<input form=\"1\" />");
549         sanitize("<input formenctype=\"text/plain\"/>", "<input formenctype=\"text/plain\" />");
550         sanitize("<input formmethod=\"post\"/>", "<input formmethod=\"post\" />");
551         sanitize("<input formnovalidate=\"formnovalidate\"/>",
552                 "<input formnovalidate=\"formnovalidate\" />");
553         sanitize("<input formtarget=\"_top\"/>", "<input formtarget=\"_top\" />");
554         sanitize("<input height=\"22\"/>", "<input height=\"22\" />");
555         sanitize("<input list=\"something\"/>", "<input list=\"something\" />");
556         sanitize("<input max=\"1000\"/>", "<input max=\"1000\" />");
557         sanitize("<input maxlength=\"10\"/>", "<input maxlength=\"10\" />");
558         sanitize("<input min=\"10\"/>", "<input min=\"10\" />");
559         sanitize("<input multiple=\"multiple\"/>", "<input multiple=\"multiple\" />");
560         sanitize("<input name=\"herman\"/>", "<input name=\"herman\" />");
561         sanitize("<input pattern=\"*.*\"/>", "<input pattern=\"*.*\" />");
562         sanitize("<input placeholder=\"something\"/>", "<input placeholder=\"something\" />");
563         sanitize("<input readonly=\"readonly\"/>", "<input readonly=\"readonly\" />");
564         sanitize("<input required=\"required\"/>", "<input required=\"required\" />");
565         sanitize("<input size=\"22\"/>", "<input size=\"22\" />");
566         sanitize("<input step=\"5\"/>", "<input step=\"5\" />");
567         sanitize("<input type=\"button\"/>", "<input type=\"button\" />");
568         sanitize("<input value=\"something\"/>", "<input value=\"something\" />");
569         sanitize("<input width=\"50\"/>", "<input width=\"50\" />");
570         sanitize("<input src=\"http://www.overhere.com/\"></input>",
571                 "<input src=\"http://www.overhere.com/\" />");
572         sanitize("<input src=\"https://www.overhere.com/\"></input>",
573                 "<input src=\"https://www.overhere.com/\" />");
574         sanitize("<input formaction=\"http://www.overhere.com/\"></input>",
575                 "<input formaction=\"http://www.overhere.com/\" />");
576         sanitize("<input formaction=\"https://www.overhere.com/\"></input>",
577                 "<input formaction=\"https://www.overhere.com/\" />");
578 
579         sanitize("<input src=\"cid:ii_hyw5v8ej0\"></input>", "");
580         sanitize("<input src=\"javascript:badness()\"></input>", "");
581         sanitize("<input formaction=\"cid:ii_hyw5v8ej0\"></input>", "");
582         sanitize("<input formaction=\"javascript:badness()\"></input>", "");
583         sanitize("<input type=\"image\" src=\"javascript:alert('XSS');\">",
584                 "<input type=\"image\" />");
585         sanitize("<input type=\"text\" onchange=\"javascript:alert('XSS');\">",
586                 "<input type=\"text\" />");
587         sanitize("<input type=\"button\" onclick=\"javascript:alert('XSS');\">",
588                 "<input type=\"button\" />");
589         sanitize("<input type=\"button\" ondblclick=\"javascript:alert('XSS');\">",
590                 "<input type=\"button\" />");
591     }
592 
testIns()593     public void testIns() {
594         sanitize("<ins>something</ins>", "<ins>something</ins>");
595         sanitize("<ins cite=\"javascript:badness();\">something</ins>", "<ins>something</ins>");
596         sanitize("<ins cite=\"http://www.reason.com/\">something</ins>",
597                 "<ins cite=\"http://www.reason.com/\">something</ins>");
598         sanitize("<ins cite=\"https://www.reason.com/\">something</ins>",
599                 "<ins cite=\"https://www.reason.com/\">something</ins>");
600         sanitize("<ins datetime=\"something\">something</ins>",
601                 "<ins datetime=\"something\">something</ins>");
602 
603         sanitize("<ins cite=\"cid:ii_hyw5v8ej0\">something</ins>",
604                 "<ins>something</ins>");
605     }
606 
testKbd()607     public void testKbd() {
608         sanitize("<kbd>something</kbd>", "<kbd>something</kbd>");
609     }
610 
testKeygen()611     public void testKeygen() {
612         sanitize("<keygen/>", "<keygen />");
613         sanitize("<keygen autofocus=\"autofocus\"/>", "<keygen autofocus=\"autofocus\" />");
614         sanitize("<keygen challenge=\"challenge\"/>", "<keygen challenge=\"challenge\" />");
615         sanitize("<keygen disabled=\"disabled\"/>", "<keygen disabled=\"disabled\" />");
616         sanitize("<keygen form=\"formId\"/>", "<keygen form=\"formId\" />");
617         sanitize("<keygen keytype=\"rsa\"/>", "<keygen keytype=\"rsa\" />");
618         sanitize("<keygen name=\"herman\"/>", "<keygen name=\"herman\" />");
619     }
620 
testLabel()621     public void testLabel() {
622         sanitize("<label for=\"elementId\">Something:</label>", "<label>Something:</label>");
623         sanitize("<label form=\"formId\">Something:</label>",
624                 "<label form=\"formId\">Something:</label>");
625     }
626 
testLegend()627     public void testLegend() {
628         sanitize("<legend>Something:</legend>", "<legend>Something:</legend>");
629         sanitize("<legend align=\"left\">Something:</legend>",
630                 "<legend align=\"left\">Something:</legend>");
631     }
632 
testLi()633     public void testLi() {
634         sanitize("<li>Something:</li>", "<li>Something:</li>");
635         sanitize("<li type=\"a\">Something:</li>", "<li type=\"a\">Something:</li>");
636         sanitize("<li value=\"11\">Something:</li>", "<li value=\"11\">Something:</li>");
637     }
638 
testLink()639     public void testLink() {
640         sanitize("<link charset=\"utf8\"/>", "");
641         sanitize("<link href=\"http://www.reason.com/\"/>", "");
642         sanitize("<link href=\"https://www.reason.com/\"/>", "");
643         sanitize("<link href=\"cid:ii_hyw5v8ej0\"/>", "");
644         sanitize("<link hreflang=\"fr_CA\"/>", "");
645         sanitize("<link media=\"tv\"/>", "");
646         sanitize("<link rel=\"alternate\"/>", "");
647         sanitize("<link rev=\"something\"/>", "");
648         sanitize("<link sizes=\"500x400\"/>", "");
649         sanitize("<link target=\"_top\"/>", "");
650         sanitize("<link type=\"mimeType\"/>", "");
651         sanitize("<link href=\"javascript:alert('XSS');\">", "");
652     }
653 
testMain()654     public void testMain() {
655         sanitize("<main>something</main>", "<main>something</main>");
656     }
657 
testMap()658     public void testMap() {
659         sanitize("<map></map>", "<map></map>");
660         sanitize("<map name=\"mapname\"></map>", "<map name=\"mapname\"></map>");
661     }
662 
testMark()663     public void testMark() {
664         sanitize("<mark>something</mark>", "<mark>something</mark>");
665     }
666 
testMenu()667     public void testMenu() {
668         sanitize("<menu></menu>", "<menu></menu>");
669         sanitize("<menu label=\"Edit\"></menu>", "<menu label=\"Edit\"></menu>");
670         sanitize("<menu type=\"popup\"></menu>", "<menu type=\"popup\"></menu>");
671     }
672 
testMenuitem()673     public void testMenuitem() {
674         sanitize("<menuitem></menuitem>", "<menuitem></menuitem>");
675         sanitize("<menuitem checked=\"checked\"></menuitem>",
676                 "<menuitem checked=\"checked\"></menuitem>");
677         sanitize("<menuitem command=\"something\"></menuitem>",
678                 "<menuitem command=\"something\"></menuitem>");
679         sanitize("<menuitem default=\"default\"></menuitem>",
680                 "<menuitem default=\"default\"></menuitem>");
681         sanitize("<menuitem disabled=\"disabled\"></menuitem>",
682                 "<menuitem disabled=\"disabled\"></menuitem>");
683         sanitize("<menuitem icon=\"http://www.reason.com/\"></menuitem>",
684                 "<menuitem icon=\"http://www.reason.com/\"></menuitem>");
685         sanitize("<menuitem icon=\"https://www.reason.com/\"></menuitem>",
686                 "<menuitem icon=\"https://www.reason.com/\"></menuitem>");
687         sanitize("<menuitem label=\"something\"></menuitem>",
688                 "<menuitem label=\"something\"></menuitem>");
689         sanitize("<menuitem type=\"checkbox\"></menuitem>",
690                 "<menuitem type=\"checkbox\"></menuitem>");
691         sanitize("<menuitem radiogroup=\"something\"></menuitem>",
692                 "<menuitem radiogroup=\"something\"></menuitem>");
693 
694         sanitize("<menuitem icon=\"cid:ii_hyw5v8ej0\"></menuitem>", "<menuitem></menuitem>");
695         sanitize("<menuitem icon=\"javascript:badness()\"></menuitem>", "<menuitem></menuitem>");
696     }
697 
testMeta()698     public void testMeta() {
699         sanitize("<meta/>", "");
700         sanitize("<meta charset=\"utf8\" />", "");
701         sanitize("<meta content=\"something\" />", "");
702         sanitize("<meta http-equiv=\"refresh\" />", "");
703         sanitize("<meta name=\"description\" />", "");
704         sanitize("<meta scheme=\"YYYY-MM-DD\" />", "");
705         sanitize("<meta http-equiv=\"Link\" content=\"<http://ha.ckers.org/xss.css>; " +
706                 "REL=stylesheet\">", "");
707         sanitize("<meta http-equiv=\"refresh\" content=\"0;url=javascript:alert('XSS');\">", "");
708         sanitize("<meta http-equiv=\"refresh\" content=\"0;url=data:text/html " +
709                 "base64,PHNjcmlwdD5hbGVydCgnWFNTJyk8L3NjcmlwdD4K\">", "");
710         sanitize("<meta http-equiv=\"refresh\" CONTENT=\"0; url=http://;" +
711                 "URL=javascript:alert('XSS');\">", "");
712     }
713 
testMeter()714     public void testMeter() {
715         sanitize("<meter>2 out of 10</meter>", "<meter>2 out of 10</meter>");
716         sanitize("<meter form=\"formId\">2 out of 10</meter>",
717                 "<meter form=\"formId\">2 out of 10</meter>");
718         sanitize("<meter high=\"10\">2 out of 10</meter>",
719                 "<meter high=\"10\">2 out of 10</meter>");
720         sanitize("<meter low=\"10\">2 out of 10</meter>", "<meter low=\"10\">2 out of 10</meter>");
721         sanitize("<meter max=\"10\">2 out of 10</meter>", "<meter max=\"10\">2 out of 10</meter>");
722         sanitize("<meter min=\"10\">2 out of 10</meter>", "<meter min=\"10\">2 out of 10</meter>");
723         sanitize("<meter optimum=\"10\">2 out of 10</meter>",
724                 "<meter optimum=\"10\">2 out of 10</meter>");
725         sanitize("<meter value=\"10\">2 out of 10</meter>",
726                 "<meter value=\"10\">2 out of 10</meter>");
727     }
728 
testNav()729     public void testNav() {
730         sanitize("<nav>something</nav>", "<nav>something</nav>");
731     }
732 
testNoframes()733     public void testNoframes() {
734         sanitize("<noframes>No frames!</noframes>", "");
735     }
736 
testNoscript()737     public void testNoscript() {
738         sanitize("<noscript>No JavaScript!</noscript>", "");
739     }
740 
testObject()741     public void testObject() {
742         sanitize("<object>No Objects!</object>", "");
743         sanitize("<object type=\"text/x-scriptlet\" data=\"http://ha.ckers.org/scriptlet.html\">" +
744                 "</object>", "");
745     }
746 
testOl()747     public void testOl() {
748         sanitize("<ol></ol>", "<ol></ol>");
749         sanitize("<ol compact=\"compact\"></ol>", "<ol compact=\"compact\"></ol>");
750         sanitize("<ol reversed=\"reversed\"></ol>", "<ol reversed=\"reversed\"></ol>");
751         sanitize("<ol start=\"11\"></ol>", "<ol start=\"11\"></ol>");
752         sanitize("<ol type=\"a\"></ol>", "<ol type=\"a\"></ol>");
753     }
754 
testOptgroup()755     public void testOptgroup() {
756         sanitize("<optgroup></optgroup>", "<optgroup></optgroup>");
757         sanitize("<optgroup disabled=\"disabled\"></optgroup>",
758                 "<optgroup disabled=\"disabled\"></optgroup>");
759         sanitize("<optgroup label=\"something\"></optgroup>",
760                 "<optgroup label=\"something\"></optgroup>");
761     }
762 
testOption()763     public void testOption() {
764         sanitize("<option>something</option>", "<option>something</option>");
765         sanitize("<option disabled=\"disabled\">something</option>",
766                 "<option disabled=\"disabled\">something</option>");
767         sanitize("<option label=\"something\">something</option>",
768                 "<option label=\"something\">something</option>");
769         sanitize("<option selected=\"selected\">something</option>",
770                 "<option selected=\"selected\">something</option>");
771         sanitize("<option value=\"volvo\">something</option>",
772                 "<option value=\"volvo\">something</option>");
773     }
774 
testOutput()775     public void testOutput() {
776         sanitize("<output></output>", "<output></output>");
777         sanitize("<output for=\"elementId\"></output>", "<output></output>");
778         sanitize("<output form=\"formId\"></output>", "<output form=\"formId\"></output>");
779         sanitize("<output name=\"something\"></output>", "<output name=\"something\"></output>");
780     }
781 
testP()782     public void testP() {
783         sanitize("<p>something</p>", "<p>something</p>");
784         sanitize("<p align=\"left\">something</p>", "<p align=\"left\">something</p>");
785     }
786 
testParam()787     public void testParam() {
788         sanitize("<param name=\"autoplay\" value=\"true\">", "");
789     }
790 
testPre()791     public void testPre() {
792         sanitize("<pre>something</pre>", "<pre>something</pre>");
793         sanitize("<pre width=\"400\">something</pre>", "<pre width=\"400\">something</pre>");
794     }
795 
testProgress()796     public void testProgress() {
797         sanitize("<progress></progress>", "<progress></progress>");
798         sanitize("<progress value=\"22\"></progress>", "<progress value=\"22\"></progress>");
799         sanitize("<progress max=\"100\"></progress>", "<progress max=\"100\"></progress>");
800     }
801 
testQ()802     public void testQ() {
803         sanitize("<q>something</q>", "<q>something</q>");
804         sanitize("<q cite=\"http://www.reason.com/\">something</q>",
805                 "<q cite=\"http://www.reason.com/\">something</q>");
806         sanitize("<q cite=\"https://www.reason.com/\">something</q>",
807                 "<q cite=\"https://www.reason.com/\">something</q>");
808 
809         sanitize("<q cite=\"cid:ii_hyw5v8ej0\">something</q>", "<q>something</q>");
810         sanitize("<q cite=\"javascript:badness()\">something</q>", "<q>something</q>");
811     }
812 
testRp()813     public void testRp() {
814         sanitize("<rp>something</rp>", "<rp>something</rp>");
815     }
816 
testRt()817     public void testRt() {
818         sanitize("<rt>something</rt>", "<rt>something</rt>");
819     }
820 
testRuby()821     public void testRuby() {
822         sanitize("<ruby></ruby>", "<ruby></ruby>");
823     }
824 
testS()825     public void testS() {
826         sanitize("<s>old skool strikethrough</s>", "<s>old skool strikethrough</s>");
827     }
828 
testSamp()829     public void testSamp() {
830         sanitize("<samp>something</samp>", "<samp>something</samp>");
831     }
832 
testScript()833     public void testScript() {
834         sanitize("<script>malicious script</script>", "");
835         sanitize("<<script>alert(\"XSS\");//<</script>", "&lt;");
836         sanitize("<script src=http://ha.ckers.org/xss.js></script>", "");
837         sanitize("<script/XSS src=\"http://ha.ckers.org/xss.js\"></script>", "");
838         sanitize("<script/src=\"http://ha.ckers.org/xss.js\"></script>", "");
839         sanitize("<script src=http://ha.ckers.org/xss.js?< B >", "");
840         sanitize("<script src=//ha.ckers.org/.j>", "");
841         sanitize("</title><script>alert(\"XSS\");</script>", "");
842         sanitize("<script src=\"http://ha.ckers.org/xss.jpg\"></script>", "");
843 
844         String attack = "';alert(String.fromCharCode(88,83,83))//';" +
845                 "alert(String.fromCharCode(88,83,83))//\";\n" +
846                 "alert(String.fromCharCode(88,83,83))//\";" +
847                 "alert(String.fromCharCode(88,83,83))//--\n" +
848                 "></SCRIPT>\">'><SCRIPT>alert(String.fromCharCode(88,83,83))</SCRIPT>";
849         String defend = "&#39;;alert(String.fromCharCode(88,83,83))//&#39;;" +
850                 "alert(String.fromCharCode(88,83,83))//&#34;;\n" +
851                 "alert(String.fromCharCode(88,83,83))//&#34;;" +
852                 "alert(String.fromCharCode(88,83,83))//--\n" +
853                 "&gt;&#34;&gt;&#39;&gt;";
854         sanitize(attack, defend);
855     }
856 
testSection()857     public void testSection() {
858         sanitize("<section>something</section>", "<section>something</section>");
859     }
860 
testSelect()861     public void testSelect() {
862         sanitize("<select></select>", "<select></select>");
863         sanitize("<select autofocus=\"autofocus\"></select>",
864                 "<select autofocus=\"autofocus\"></select>");
865         sanitize("<select disabled=\"disabled\"></select>",
866                 "<select disabled=\"disabled\"></select>");
867         sanitize("<select form=\"formId\"></select>", "<select form=\"formId\"></select>");
868         sanitize("<select multiple=\"multiple\"></select>",
869                 "<select multiple=\"multiple\"></select>");
870         sanitize("<select required=\"required\"></select>",
871                 "<select required=\"required\"></select>");
872         sanitize("<select size=\"11\"></select>", "<select size=\"11\"></select>");
873     }
874 
testSmall()875     public void testSmall() {
876         sanitize("<small>something</small>", "<small>something</small>");
877     }
878 
testSource()879     public void testSource() {
880         sanitize("<source/>", "");
881         sanitize("<source></source>", "");
882     }
883 
testSpan()884     public void testSpan() {
885         sanitize("<span style=\"color:blue\">something</span>",
886                 "<span style=\"color:blue\">something</span>");
887     }
888 
testStrike()889     public void testStrike() {
890         sanitize("<strike>something</strike>", "<strike>something</strike>");
891     }
892 
testStrong()893     public void testStrong() {
894         sanitize("<strong>something</strong>", "<strong>something</strong>");
895     }
896 
testStyle()897     public void testStyle() {
898         sanitize("<style>something</style>", "");
899         sanitize("<style media=\"something\">something</style>", "");
900         sanitize("<style scoped=\"scoped\">something</style>", "");
901         sanitize("<style type=\"text/css\">something</style>", "");
902         sanitize("<style>li {list-style-image: url(\"javascript:alert('XSS')\");}</style>", "");
903         sanitize("<style>@im\\port'\\ja\\vasc\\ript:alert(\"XSS\")';</style>", "");
904         sanitize("<style>body{-moz-binding:url(\"http://ha.ckers.org/xssmoz.xml#xss\")}</style>",
905                 "");
906         sanitize("<style>@import'http://ha.ckers.org/xss.css';</style>", "");
907         sanitize("<style type=\"text/javascript\">alert('XSS');</style>", "");
908         sanitize("<style>.XSS{background-image:url(\"javascript:alert('XSS')\");}</style>" +
909                 "<a class=XSS></a>", "");
910         sanitize("<style type=\"text/css\">body{background:url(\"javascript:alert('XSS')\")}" +
911                 "</style>", "");
912     }
913 
testSub()914     public void testSub() {
915         sanitize("<sub>something</sub>", "<sub>something</sub>");
916     }
917 
testSummary()918     public void testSummary() {
919         sanitize("<summary>something</summary>", "<summary>something</summary>");
920     }
921 
testSup()922     public void testSup() {
923         sanitize("<sup>something</sup>", "<sup>something</sup>");
924     }
925 
testTable()926     public void testTable() {
927         sanitize("<table></table>", "<table></table>");
928         sanitize("<table align=\"left\"></table>", "<table align=\"left\"></table>");
929         sanitize("<table bgcolor=\"red\"></table>", "<table bgcolor=\"red\"></table>");
930         sanitize("<table border=\"1\"></table>", "<table border=\"1\"></table>");
931         sanitize("<table cellpadding=\"1\"></table>", "<table cellpadding=\"1\"></table>");
932         sanitize("<table cellspacing=\"1\"></table>", "<table cellspacing=\"1\"></table>");
933         sanitize("<table frame=\"void\"></table>", "<table frame=\"void\"></table>");
934         sanitize("<table rules=\"none\"></table>", "<table rules=\"none\"></table>");
935         sanitize("<table sortable=\"sortable\"></table>", "<table sortable=\"sortable\"></table>");
936         sanitize("<table summary=\"something\"></table>", "<table summary=\"something\"></table>");
937         sanitize("<table width=\"11\"></table>", "<table width=\"11\"></table>");
938 
939         sanitize("<table background=\"javascript:alert('XSS')\">", "<table></table>");
940     }
941 
testTbody()942     public void testTbody() {
943         sanitize("<tbody></tbody>", "<tbody></tbody>");
944         sanitize("<tbody char=\"something\"></tbody>", "<tbody char=\"something\"></tbody>");
945         sanitize("<tbody charoff=\"11\"></tbody>", "<tbody charoff=\"11\"></tbody>");
946         sanitize("<tbody valign=\"top\"></tbody>", "<tbody valign=\"top\"></tbody>");
947     }
948 
testTd()949     public void testTd() {
950         sanitize("<td></td>", "<td></td>");
951         sanitize("<td abbr=\"something\"></td>", "<td abbr=\"something\"></td>");
952         sanitize("<td align=\"left\"></td>", "<td align=\"left\"></td>");
953         sanitize("<td axis=\"something\"></td>", "<td axis=\"something\"></td>");
954         sanitize("<td bgcolor=\"red\"></td>", "<td bgcolor=\"red\"></td>");
955         sanitize("<td char=\"something\"></td>", "<td char=\"something\"></td>");
956         sanitize("<td charoff=\"22\"></td>", "<td charoff=\"22\"></td>");
957         sanitize("<td colspan=\"33\"></td>", "<td colspan=\"33\"></td>");
958         sanitize("<td height=\"44\"></td>", "<td height=\"44\"></td>");
959         sanitize("<td nowrap=\"nowrap\"></td>", "<td nowrap=\"nowrap\"></td>");
960         sanitize("<td rowspan=\"3\"></td>", "<td rowspan=\"3\"></td>");
961         sanitize("<td scope=\"col\"></td>", "<td scope=\"col\"></td>");
962         sanitize("<td valign=\"top\"></td>", "<td valign=\"top\"></td>");
963         sanitize("<td width=\"55\"></td>", "<td width=\"55\"></td>");
964 
965         sanitize("<td headers=\"headerId\"></td>", "<td></td>");
966         sanitize("<td background=\"javascript:alert('XSS')\">", "<td></td>");
967     }
968 
testTextarea()969     public void testTextarea() {
970         sanitize("<textarea></textarea>", "<textarea></textarea>");
971         sanitize("<textarea autofocus=\"autofocus\"></textarea>",
972                 "<textarea autofocus=\"autofocus\"></textarea>");
973         sanitize("<textarea cols=\"1\"></textarea>", "<textarea cols=\"1\"></textarea>");
974         sanitize("<textarea disabled=\"disabled\"></textarea>",
975                 "<textarea disabled=\"disabled\"></textarea>");
976         sanitize("<textarea form=\"formId\"></textarea>", "<textarea form=\"formId\"></textarea>");
977         sanitize("<textarea maxlength=\"2\"></textarea>", "<textarea maxlength=\"2\"></textarea>");
978         sanitize("<textarea name=\"something\"></textarea>",
979                 "<textarea name=\"something\"></textarea>");
980         sanitize("<textarea placeholder=\"something\"></textarea>",
981                 "<textarea placeholder=\"something\"></textarea>");
982         sanitize("<textarea readonly=\"readonly\"></textarea>",
983                 "<textarea readonly=\"readonly\"></textarea>");
984         sanitize("<textarea required=\"required\"></textarea>",
985                 "<textarea required=\"required\"></textarea>");
986         sanitize("<textarea rows=\"3\"></textarea>", "<textarea rows=\"3\"></textarea>");
987         sanitize("<textarea wrap=\"soft\"></textarea>", "<textarea wrap=\"soft\"></textarea>");
988     }
989 
testTfoot()990     public void testTfoot() {
991         sanitize("<tfoot></tfoot>", "<tfoot></tfoot>");
992         sanitize("<tfoot align=\"left\"></tfoot>", "<tfoot align=\"left\"></tfoot>");
993         sanitize("<tfoot char=\"something\"></tfoot>", "<tfoot char=\"something\"></tfoot>");
994         sanitize("<tfoot charoff=\"1\"></tfoot>", "<tfoot charoff=\"1\"></tfoot>");
995         sanitize("<tfoot valign=\"top\"></tfoot>", "<tfoot valign=\"top\"></tfoot>");
996     }
997 
testTh()998     public void testTh() {
999         sanitize("<th></th>", "<th></th>");
1000         sanitize("<th abbr=\"something\"></th>", "<th abbr=\"something\"></th>");
1001         sanitize("<th align=\"left\"></th>", "<th align=\"left\"></th>");
1002         sanitize("<th axis=\"something\"></th>", "<th axis=\"something\"></th>");
1003         sanitize("<th bgcolor=\"red\"></th>", "<th bgcolor=\"red\"></th>");
1004         sanitize("<th char=\"something\"></th>", "<th char=\"something\"></th>");
1005         sanitize("<th charoff=\"22\"></th>", "<th charoff=\"22\"></th>");
1006         sanitize("<th colspan=\"33\"></th>", "<th colspan=\"33\"></th>");
1007         sanitize("<th height=\"44\"></th>", "<th height=\"44\"></th>");
1008         sanitize("<th nowrap=\"nowrap\"></th>", "<th nowrap=\"nowrap\"></th>");
1009         sanitize("<th rowspan=\"3\"></th>", "<th rowspan=\"3\"></th>");
1010         sanitize("<th scope=\"col\"></th>", "<th scope=\"col\"></th>");
1011         sanitize("<th sorted=\"reversed\"></th>", "<th sorted=\"reversed\"></th>");
1012         sanitize("<th valign=\"top\"></th>", "<th valign=\"top\"></th>");
1013         sanitize("<th width=\"55\"></th>", "<th width=\"55\"></th>");
1014 
1015         sanitize("<th headers=\"headerId\"></th>", "<th></th>");
1016     }
1017 
testThead()1018     public void testThead() {
1019         sanitize("<thead></thead>", "<thead></thead>");
1020         sanitize("<thead align=\"left\"></thead>", "<thead align=\"left\"></thead>");
1021         sanitize("<thead char=\"something\"></thead>", "<thead char=\"something\"></thead>");
1022         sanitize("<thead charoff=\"1\"></thead>", "<thead charoff=\"1\"></thead>");
1023         sanitize("<thead valign=\"top\"></thead>", "<thead valign=\"top\"></thead>");
1024     }
1025 
testTime()1026     public void testTime() {
1027         sanitize("<time></time>", "<time></time>");
1028         sanitize("<time datetime=\"datetime\"></time>", "<time datetime=\"datetime\"></time>");
1029     }
1030 
testTitle()1031     public void testTitle() {
1032         sanitize("<title>something</title>", "");
1033     }
1034 
testTr()1035     public void testTr() {
1036         sanitize("<tr></tr>", "<tr></tr>");
1037         sanitize("<tr align=\"left\"></tr>", "<tr align=\"left\"></tr>");
1038         sanitize("<tr bgcolor=\"red\"></tr>", "<tr bgcolor=\"red\"></tr>");
1039         sanitize("<tr char=\"something\"></tr>", "<tr char=\"something\"></tr>");
1040         sanitize("<tr charoff=\"1\"></tr>", "<tr charoff=\"1\"></tr>");
1041         sanitize("<tr valign=\"top\"></tr>", "<tr valign=\"top\"></tr>");
1042     }
1043 
testTrack()1044     public void testTrack() {
1045         sanitize("<track/>", "");
1046         sanitize("<track></track>", "");
1047     }
1048 
testTt()1049     public void testTt() {
1050         sanitize("<tt>something</tt>", "<tt>something</tt>");
1051     }
1052 
testU()1053     public void testU() {
1054         sanitize("<u>something</u>", "<u>something</u>");
1055     }
1056 
testUl()1057     public void testUl() {
1058         sanitize("<ul compact=\"compact\"></ul>", "<ul compact=\"compact\"></ul>");
1059         sanitize("<ul type=\"disc\"></ul>", "<ul type=\"disc\"></ul>");
1060     }
1061 
testVar()1062     public void testVar() {
1063         sanitize("<var>something</var>", "<var>something</var>");
1064     }
1065 
testVideo()1066     public void testVideo() {
1067         sanitize("<video></video>", "");
1068     }
1069 
testWbr()1070     public void testWbr() {
1071         sanitize("word1<wbr/>word2", "word1<wbr />word2");
1072     }
1073 
sanitize(String dirtyHTML, String expectedHTML)1074     private void sanitize(String dirtyHTML, String expectedHTML) {
1075         final String cleansedHTML = HtmlSanitizer.sanitizeHtml(dirtyHTML);
1076         assertEquals(expectedHTML, cleansedHTML);
1077     }
1078 }
1079