[ Index ]

PHP Cross Reference of Unnamed Project

title

Body

[close]

/lib/tests/ -> htmlpurifier_test.php (source)

   1  <?php
   2  // This file is part of Moodle - http://moodle.org/
   3  //
   4  // Moodle is free software: you can redistribute it and/or modify
   5  // it under the terms of the GNU General Public License as published by
   6  // the Free Software Foundation, either version 3 of the License, or
   7  // (at your option) any later version.
   8  //
   9  // Moodle is distributed in the hope that it will be useful,
  10  // but WITHOUT ANY WARRANTY; without even the implied warranty of
  11  // MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
  12  // GNU General Public License for more details.
  13  //
  14  // You should have received a copy of the GNU General Public License
  15  // along with Moodle.  If not, see <http://www.gnu.org/licenses/>.
  16  
  17  /**
  18   * Unit tests for the HTMLPurifier integration
  19   *
  20   * @package    core
  21   * @category   phpunit
  22   * @copyright  2012 Petr Skoda {@link http://skodak.org}
  23   * @license    http://www.gnu.org/copyleft/gpl.html GNU GPL v3 or later
  24   */
  25  
  26  defined('MOODLE_INTERNAL') || die();
  27  
  28  
  29  /**
  30   * HTMLPurifier test case
  31   *
  32   * @package    core
  33   * @category   phpunit
  34   * @copyright  2012 Petr Skoda {@link http://skodak.org}
  35   * @license    http://www.gnu.org/copyleft/gpl.html GNU GPL v3 or later
  36   */
  37  class core_htmlpurifier_testcase extends basic_testcase {
  38  
  39      /**
  40       * Verify _blank target is allowed.
  41       */
  42      public function test_allow_blank_target() {
  43          // See MDL-52651 for an explanation as to why the rel="noreferrer" attribute is expected here.
  44          // Also note we do not need to test links with an existing rel attribute as the HTML Purifier is configured to remove
  45          // the rel attribute.
  46          $text = '<a href="http://moodle.org" target="_blank">Some link</a>';
  47          $expected = '<a href="http://moodle.org" target="_blank" rel="noreferrer">Some link</a>';
  48          $result = format_text($text, FORMAT_HTML);
  49          $this->assertSame($expected, $result);
  50  
  51          $result = format_text('<a href="http://moodle.org" target="some">Some link</a>', FORMAT_HTML);
  52          $this->assertSame('<a href="http://moodle.org">Some link</a>', $result);
  53      }
  54  
  55      /**
  56       * Verify our nolink tag accepted.
  57       */
  58      public function test_nolink() {
  59          // We can not use format text because nolink changes result.
  60          $text = '<nolink><div>no filters</div></nolink>';
  61          $result = purify_html($text, array());
  62          $this->assertSame($text, $result);
  63  
  64          $text = '<nolink>xxx<em>xx</em><div>xxx</div></nolink>';
  65          $result = purify_html($text, array());
  66          $this->assertSame($text, $result);
  67      }
  68  
  69      /**
  70       * Verify our tex tag accepted.
  71       */
  72      public function test_tex() {
  73          $text = '<tex>a+b=c</tex>';
  74          $result = purify_html($text, array());
  75          $this->assertSame($text, $result);
  76      }
  77  
  78      /**
  79       * Verify our algebra tag accepted.
  80       */
  81      public function test_algebra() {
  82          $text = '<algebra>a+b=c</algebra>';
  83          $result = purify_html($text, array());
  84          $this->assertSame($text, $result);
  85      }
  86  
  87      /**
  88       * Verify our hacky multilang works.
  89       */
  90      public function test_multilang() {
  91          $text = '<lang lang="en">hmmm</lang><lang lang="anything">hm</lang>';
  92          $result = purify_html($text, array());
  93          $this->assertSame($text, $result);
  94  
  95          $text = '<span lang="en" class="multilang">hmmm</span><span lang="anything" class="multilang">hm</span>';
  96          $result = purify_html($text, array());
  97          $this->assertSame($text, $result);
  98  
  99          $text = '<span lang="en">hmmm</span>';
 100          $result = purify_html($text, array());
 101          $this->assertNotSame($text, $result);
 102  
 103          // Keep standard lang tags.
 104  
 105          $text = '<span lang="de_DU" class="multilang">asas</span>';
 106          $result = purify_html($text, array());
 107          $this->assertSame($text, $result);
 108  
 109          $text = '<lang lang="de_DU">xxxxxx</lang>';
 110          $result = purify_html($text, array());
 111          $this->assertSame($text, $result);
 112      }
 113  
 114      /**
 115       * Tests the 'allowid' option for format_text.
 116       */
 117      public function test_format_text_allowid() {
 118          // Start off by not allowing ids (default).
 119          $options = array(
 120              'nocache' => true
 121          );
 122          $result = format_text('<div id="example">Frog</div>', FORMAT_HTML, $options);
 123          $this->assertSame('<div>Frog</div>', $result);
 124  
 125          // Now allow ids.
 126          $options['allowid'] = true;
 127          $result = format_text('<div id="example">Frog</div>', FORMAT_HTML, $options);
 128          $this->assertSame('<div id="example">Frog</div>', $result);
 129      }
 130  
 131      public function test_allowobjectembed() {
 132          global $CFG;
 133  
 134          $this->assertSame('0', $CFG->allowobjectembed);
 135  
 136          $text = '<object width="425" height="350">
 137  <param name="movie" value="http://www.youtube.com/v/AyPzM5WK8ys" />
 138  <param name="wmode" value="transparent" />
 139  <embed src="http://www.youtube.com/v/AyPzM5WK8ys" type="application/x-shockwave-flash" wmode="transparent" width="425" height="350" />
 140  </object>hmmm';
 141          $result = purify_html($text, array());
 142          $this->assertSame('hmmm', trim($result));
 143  
 144          $CFG->allowobjectembed = '1';
 145  
 146          $expected = '<object width="425" height="350" data="http://www.youtube.com/v/AyPzM5WK8ys" type="application/x-shockwave-flash">
 147  <param name="allowScriptAccess" value="never" />
 148  <param name="allowNetworking" value="internal" />
 149  <param name="movie" value="http://www.youtube.com/v/AyPzM5WK8ys" />
 150  <param name="wmode" value="transparent" />
 151  <embed src="http://www.youtube.com/v/AyPzM5WK8ys" type="application/x-shockwave-flash" wmode="transparent" width="425" height="350" allowscriptaccess="never" allownetworking="internal" />
 152  </object>hmmm';
 153          $result = purify_html($text, array());
 154          $this->assertSame(str_replace("\n", '', $expected), str_replace("\n", '', $result));
 155  
 156          $CFG->allowobjectembed = '0';
 157  
 158          $result = purify_html($text, array());
 159          $this->assertSame('hmmm', trim($result));
 160      }
 161  
 162      /**
 163       * Test if linebreaks kept unchanged.
 164       */
 165      public function test_line_breaking() {
 166          $text = "\n\raa\rsss\nsss\r";
 167          $this->assertSame($text, purify_html($text));
 168      }
 169  
 170      /**
 171       * Test fixing of strict problems.
 172       */
 173      public function test_tidy() {
 174          $text = "<p>xx";
 175          $this->assertSame('<p>xx</p>', purify_html($text));
 176  
 177          $text = "<P>xx</P>";
 178          $this->assertSame('<p>xx</p>', purify_html($text));
 179  
 180          $text = "xx<br>";
 181          $this->assertSame('xx<br />', purify_html($text));
 182      }
 183  
 184      /**
 185       * Test nesting - this used to cause problems in earlier versions.
 186       */
 187      public function test_nested_lists() {
 188          $text = "<ul><li>One<ul><li>Two</li></ul></li><li>Three</li></ul>";
 189          $this->assertSame($text, purify_html($text));
 190      }
 191  
 192      /**
 193       * Test that XSS protection works, complete smoke tests are in htmlpurifier itself.
 194       */
 195      public function test_cleaning_nastiness() {
 196          $text = "x<SCRIPT>alert('XSS')</SCRIPT>x";
 197          $this->assertSame('xx', purify_html($text));
 198  
 199          $text = '<DIV STYLE="background-image:url(javascript:alert(\'XSS\'))">xx</DIV>';
 200          $this->assertSame('<div>xx</div>', purify_html($text));
 201  
 202          $text = '<DIV STYLE="width:expression(alert(\'XSS\'));">xx</DIV>';
 203          $this->assertSame('<div>xx</div>', purify_html($text));
 204  
 205          $text = 'x<IFRAME SRC="javascript:alert(\'XSS\');"></IFRAME>x';
 206          $this->assertSame('xx', purify_html($text));
 207  
 208          $text = 'x<OBJECT TYPE="text/x-scriptlet" DATA="http://ha.ckers.org/scriptlet.html"></OBJECT>x';
 209          $this->assertSame('xx', purify_html($text));
 210  
 211          $text = 'x<EMBED SRC="http://ha.ckers.org/xss.swf" AllowScriptAccess="always"></EMBED>x';
 212          $this->assertSame('xx', purify_html($text));
 213  
 214          $text = 'x<form></form>x';
 215          $this->assertSame('xx', purify_html($text));
 216      }
 217  
 218      /**
 219       * Test internal function used for clean_text() speedup.
 220       */
 221      public function test_is_purify_html_necessary() {
 222          // First our shortcuts.
 223          $text = "";
 224          $this->assertFalse(is_purify_html_necessary($text));
 225          $this->assertSame($text, purify_html($text));
 226  
 227          $text = "666";
 228          $this->assertFalse(is_purify_html_necessary($text));
 229          $this->assertSame($text, purify_html($text));
 230  
 231          $text = "abc\ndef \" ' ";
 232          $this->assertFalse(is_purify_html_necessary($text));
 233          $this->assertSame($text, purify_html($text));
 234  
 235          $text = "abc\n<p>def</p>efg<p>hij</p>";
 236          $this->assertFalse(is_purify_html_necessary($text));
 237          $this->assertSame($text, purify_html($text));
 238  
 239          $text = "<br />abc\n<p>def<em>efg</em><strong>hi<br />j</strong></p>";
 240          $this->assertFalse(is_purify_html_necessary($text));
 241          $this->assertSame($text, purify_html($text));
 242  
 243          // Now failures.
 244          $text = "&nbsp;";
 245          $this->assertTrue(is_purify_html_necessary($text));
 246  
 247          $text = "Gin & Tonic";
 248          $this->assertTrue(is_purify_html_necessary($text));
 249  
 250          $text = "Gin > Tonic";
 251          $this->assertTrue(is_purify_html_necessary($text));
 252  
 253          $text = "Gin < Tonic";
 254          $this->assertTrue(is_purify_html_necessary($text));
 255  
 256          $text = "<div>abc</div>";
 257          $this->assertTrue(is_purify_html_necessary($text));
 258  
 259          $text = "<span>abc</span>";
 260          $this->assertTrue(is_purify_html_necessary($text));
 261  
 262          $text = "<br>abc";
 263          $this->assertTrue(is_purify_html_necessary($text));
 264  
 265          $text = "<p class='xxx'>abc</p>";
 266          $this->assertTrue(is_purify_html_necessary($text));
 267  
 268          $text = "<p>abc<em></p></em>";
 269          $this->assertTrue(is_purify_html_necessary($text));
 270  
 271          $text = "<p>abc";
 272          $this->assertTrue(is_purify_html_necessary($text));
 273      }
 274  
 275      public function test_allowed_schemes() {
 276          // First standard schemas.
 277          $text = '<a href="http://www.example.com/course/view.php?id=5">link</a>';
 278          $this->assertSame($text, purify_html($text));
 279  
 280          $text = '<a href="https://www.example.com/course/view.php?id=5">link</a>';
 281          $this->assertSame($text, purify_html($text));
 282  
 283          $text = '<a href="ftp://user@ftp.example.com/some/file.txt">link</a>';
 284          $this->assertSame($text, purify_html($text));
 285  
 286          $text = '<a href="nntp://example.com/group/123">link</a>';
 287          $this->assertSame($text, purify_html($text));
 288  
 289          $text = '<a href="news:groupname">link</a>';
 290          $this->assertSame($text, purify_html($text));
 291  
 292          $text = '<a href="mailto:user@example.com">link</a>';
 293          $this->assertSame($text, purify_html($text));
 294  
 295          // Extra schemes allowed in moodle.
 296          $text = '<a href="irc://irc.example.com/3213?pass">link</a>';
 297          $this->assertSame($text, purify_html($text));
 298  
 299          $text = '<a href="rtsp://www.example.com/movie.mov">link</a>';
 300          $this->assertSame($text, purify_html($text));
 301  
 302          $text = '<a href="rtmp://www.example.com/video.f4v">link</a>';
 303          $this->assertSame($text, purify_html($text));
 304  
 305          $text = '<a href="teamspeak://speak.example.com/?par=val?par2=val2">link</a>';
 306          $this->assertSame($text, purify_html($text));
 307  
 308          $text = '<a href="gopher://gopher.example.com/resource">link</a>';
 309          $this->assertSame($text, purify_html($text));
 310  
 311          $text = '<a href="mms://www.example.com/movie.mms">link</a>';
 312          $this->assertSame($text, purify_html($text));
 313  
 314          // Now some borked or dangerous schemes.
 315          $text = '<a href="javascript://www.example.com">link</a>';
 316          $this->assertSame('<a>link</a>', purify_html($text));
 317  
 318          $text = '<a href="hmmm://www.example.com">link</a>';
 319          $this->assertSame('<a>link</a>', purify_html($text));
 320      }
 321  
 322      /**
 323       * Tests media tags.
 324       *
 325       * @dataProvider media_tags_provider
 326       * @param string $mediatag HTML media tag
 327       * @param string $expected expected result
 328       */
 329      public function test_media_tags($mediatag, $expected) {
 330          $actual = format_text($mediatag, FORMAT_MOODLE, ['filter' => false, 'noclean' => true]);
 331          $this->assertEquals($expected, $actual);
 332      }
 333  
 334      /**
 335       * Test cases for the test_media_tags test.
 336       */
 337      public function media_tags_provider() {
 338          // Takes an array of attributes, then generates a test for each of them.
 339          $generatetestcases = function($prefix, array $attrs, array $templates) {
 340              return array_reduce($attrs, function($carry, $attr) use ($prefix, $templates) {
 341                  $testcase = [$prefix . '/' . $attr => [
 342                      sprintf($templates[0], $attr),
 343                      sprintf($templates[1], $attr)
 344                  ]];
 345                  return empty(array_values($carry)[0]) ? $testcase : $carry + $testcase;
 346              }, [[]]);
 347          };
 348  
 349          $audioattrs = [
 350              'preload="auto"', 'autoplay=""', 'loop=""', 'muted=""', 'controls=""',
 351              'crossorigin="anonymous"', 'crossorigin="use-credentials"'
 352          ];
 353          $videoattrs = [
 354              'crossorigin="anonymous"', 'crossorigin="use-credentials"',
 355              'poster="https://upload.wikimedia.org/wikipedia/en/1/14/Space_jam.jpg"',
 356              'preload=""', 'autoplay=""', 'playsinline=""', 'loop=""', 'muted=""',
 357              'controls=""', 'width="420px"', 'height="69px"'
 358          ];
 359          return $generatetestcases('Plain audio', $audioattrs + ['src="http://example.com/jam.wav"'], [
 360                  '<audio %1$s>Looks like you can\'t slam the jams.</audio>',
 361                  '<div class="text_to_html"><audio %1$s>Looks like you can\'t slam the jams.</audio></div>'
 362              ]) + $generatetestcases('Audio with one source', $audioattrs, [
 363                  '<audio %1$s><source src="http://example.com/getup.wav">No tasty jams for you.</audio>',
 364                  '<div class="text_to_html">' .
 365                      '<audio %1$s>' .
 366                          '<source src="http://example.com/getup.wav">' .
 367                          'No tasty jams for you.' .
 368                      '</audio>' .
 369                  '</div>'
 370              ]) + $generatetestcases('Audio with multiple sources', $audioattrs, [
 371                  '<audio %1$s>' .
 372                      '<source src="http://example.com/getup.wav" type="audio/wav">' .
 373                      '<source src="http://example.com/getup.mp3" type="audio/mpeg">' .
 374                      '<source src="http://example.com/getup.ogg" type="audio/ogg">' .
 375                      'No tasty jams for you.' .
 376                  '</audio>',
 377                  '<div class="text_to_html">' .
 378                       '<audio %1$s>' .
 379                          '<source src="http://example.com/getup.wav" type="audio/wav">' .
 380                          '<source src="http://example.com/getup.mp3" type="audio/mpeg">' .
 381                          '<source src="http://example.com/getup.ogg" type="audio/ogg">' .
 382                          'No tasty jams for you.' .
 383                      '</audio>' .
 384                  '</div>'
 385              ]) + $generatetestcases('Plain video', $videoattrs + ['src="http://example.com/prettygood.mp4'], [
 386                  '<video %1$s>Oh, that\'s pretty bad 😦</video>',
 387                  '<div class="text_to_html"><video %1$s>Oh, that\'s pretty bad 😦</video></div>'
 388              ]) + $generatetestcases('Video with one source', $videoattrs, [
 389                  '<video %1$s><source src="http://example.com/prettygood.mp4">Oh, that\'s pretty bad 😦</video>',
 390                  '<div class="text_to_html">' .
 391                      '<video %1$s>' .
 392                          '<source src="http://example.com/prettygood.mp4">' .
 393                          'Oh, that\'s pretty bad 😦' .
 394                      '</video>' .
 395                  '</div>'
 396              ]) + $generatetestcases('Video with multiple sources', $videoattrs, [
 397                  '<video %1$s>' .
 398                      '<source src="http://example.com/prettygood.mp4" type="video/mp4">' .
 399                      '<source src="http://example.com/eljefe.mp4" type="video/mp4">' .
 400                      '<source src="http://example.com/turnitup.mov type="video/mov"' .
 401                      'Oh, that\'s pretty bad 😦' .
 402                  '</video>',
 403                  '<div class="text_to_html">' .
 404                      '<video %1$s>' .
 405                          '<source src="http://example.com/prettygood.mp4" type="video/mp4">' .
 406                          '<source src="http://example.com/eljefe.mp4" type="video/mp4">' .
 407                          '<source src="http://example.com/turnitup.mov type="video/mov"' .
 408                          'Oh, that\'s pretty bad 😦' .
 409                      '</video>' .
 410                  '</div>'
 411              ] + [
 412                  'Video with invalid crossorigin' => [
 413                      '<video src="http://example.com/turnitup.mov type="video/mov crossorigin="can i pls hab?">' .
 414                          'Oh, that\'s pretty bad 😦' .
 415                      '</video>',
 416                      '<div class="text_to_html">' .
 417                         '<video src="http://example.com/turnitup.mov type="video/mov">' .
 418                             'Oh, that\'s pretty bad 😦' .
 419                          '</video>',
 420                      '</div>'
 421                  ],
 422                  'Audio with invalid crossorigin' => [
 423                      '<audio src="http://example.com/getup.wav" type="audio/wav" crossorigin="give me. the jams.">' .
 424                          'nyemnyemnyem' .
 425                      '</audio>',
 426                      '<div class="text_to_html">' .
 427                          '<audio src="http://example.com/getup.wav" type="audio/wav" crossorigin="give me. the jams.">' .
 428                              'nyemnyemnyem' .
 429                          '</audio>' .
 430                      '</div>'
 431                  ]
 432              ]);
 433      }
 434  }


Generated: Thu Aug 11 10:00:09 2016 Cross-referenced by PHPXref 0.7.1