tests/phpunit/includes/SanitizerTest.php

   1 <?php
   2
   3 class SanitizerTest extends MediaWikiTestCase {
   4
   5         protected function setUp() {
   6                 parent::setUp();
   7
   8                 $this->setMwGlobals( 'wgCleanupPresentationalAttributes', true );
   9
  10                 AutoLoader::loadClass( 'Sanitizer' );
  11         }
  12
  13         function testDecodeNamedEntities() {
  14                 $this->assertEquals(
  15                         "\xc3\xa9cole",
  16                         Sanitizer::decodeCharReferences( '&eacute;cole' ),
  17                         'decode named entities'
  18                 );
  19         }
  20
  21         function testDecodeNumericEntities() {
  22                 $this->assertEquals(
  23                         "\xc4\x88io bonas dans l'\xc3\xa9cole!",
  24                         Sanitizer::decodeCharReferences( "&#x108;io bonas dans l'&#233;cole!" ),
  25                         'decode numeric entities'
  26                 );
  27         }
  28
  29         function testDecodeMixedEntities() {
  30                 $this->assertEquals(
  31                         "\xc4\x88io bonas dans l'\xc3\xa9cole!",
  32                         Sanitizer::decodeCharReferences( "&#x108;io bonas dans l'&eacute;cole!" ),
  33                         'decode mixed numeric/named entities'
  34                 );
  35         }
  36
  37         function testDecodeMixedComplexEntities() {
  38                 $this->assertEquals(
  39                         "\xc4\x88io bonas dans l'\xc3\xa9cole! (mais pas &#x108;io dans l'&eacute;cole)",
  40                         Sanitizer::decodeCharReferences(
  41                                 "&#x108;io bonas dans l'&eacute;cole! (mais pas &amp;#x108;io dans l'&#38;eacute;cole)"
  42                         ),
  43                         'decode mixed complex entities'
  44                 );
  45         }
  46
  47         function testInvalidAmpersand() {
  48                 $this->assertEquals(
  49                         'a & b',
  50                         Sanitizer::decodeCharReferences( 'a & b' ),
  51                         'Invalid ampersand'
  52                 );
  53         }
  54
  55         function testInvalidEntities() {
  56                 $this->assertEquals(
  57                         '&foo;',
  58                         Sanitizer::decodeCharReferences( '&foo;' ),
  59                         'Invalid named entity'
  60                 );
  61         }
  62
  63         function testInvalidNumberedEntities() {
  64                 $this->assertEquals( UTF8_REPLACEMENT, Sanitizer::decodeCharReferences( "&#88888888888888;" ), 'Invalid numbered entity' );
  65         }
  66
  67         /**
  68          * @cover Sanitizer::removeHTMLtags
  69          * @dataProvider provideHtml5Tags
  70          *
  71          * @param String $tag Name of an HTML5 element (ie: 'video')
  72          * @param Boolean $escaped Wheter sanitizer let the tag in or escape it (ie: '&lt;video&gt;')
  73          */
  74         function testRemovehtmltagsOnHtml5Tags( $tag, $escaped ) {
  75
  76                 # Enable HTML5 mode
  77                 global $wgHTML5;
  78                 $save = $wgHTML5;
  79                 $wgHTML5 = true;
  80
  81                 if( $escaped ) {
  82                         $this->assertEquals( "&lt;$tag&gt;",
  83                                 Sanitizer::removeHTMLtags( "<$tag>" )
  84                         );
  85                 } else {
  86                         $this->assertEquals( "<$tag></$tag>\n",
  87                                 Sanitizer::removeHTMLtags( "<$tag>" )
  88                         );
  89                 }
  90                 $wgHTML5 = $save;
  91         }
  92
  93         /**
  94          * Provide HTML5 tags
  95          */
  96         function provideHtml5Tags() {
  97                 $ESCAPED  = true; # We want tag to be escaped
  98                 $VERBATIM = false;  # We want to keep the tag
  99                 return array(
 100                         array( 'data', $VERBATIM ),
 101                         array( 'mark', $VERBATIM ),
 102                         array( 'time', $VERBATIM ),
 103                         array( 'video', $ESCAPED ),
 104                 );
 105         }
 106
 107         function testSelfClosingTag() {
 108                 $GLOBALS['wgUseTidy'] = false;
 109                 $this->assertEquals(
 110                         '<div>Hello world</div>',
 111                         Sanitizer::removeHTMLtags( '<div>Hello world</div />' ),
 112                         'Self-closing closing div'
 113                 );
 114         }
 115
 116         function testDecodeTagAttributes() {
 117                 $this->assertEquals( Sanitizer::decodeTagAttributes( 'foo=bar' ), array( 'foo' => 'bar' ), 'Unquoted attribute' );
 118                 $this->assertEquals( Sanitizer::decodeTagAttributes( '    foo   =   bar    ' ), array( 'foo' => 'bar' ), 'Spaced attribute' );
 119                 $this->assertEquals( Sanitizer::decodeTagAttributes( 'foo="bar"' ), array( 'foo' => 'bar' ), 'Double-quoted attribute' );
 120                 $this->assertEquals( Sanitizer::decodeTagAttributes( 'foo=\'bar\'' ), array( 'foo' => 'bar' ), 'Single-quoted attribute' );
 121                 $this->assertEquals( Sanitizer::decodeTagAttributes( 'foo=\'bar\'   baz="foo"' ), array( 'foo' => 'bar', 'baz' => 'foo' ), 'Several attributes' );
 122
 123                 $this->assertEquals( Sanitizer::decodeTagAttributes( 'foo=\'bar\'   baz="foo"' ), array( 'foo' => 'bar', 'baz' => 'foo' ), 'Several attributes' );
 124                 $this->assertEquals( Sanitizer::decodeTagAttributes( 'foo=\'bar\'   baz="foo"' ), array( 'foo' => 'bar', 'baz' => 'foo' ), 'Several attributes' );
 125
 126                 $this->assertEquals( Sanitizer::decodeTagAttributes( ':foo=\'bar\'' ), array( ':foo' => 'bar' ), 'Leading :' );
 127                 $this->assertEquals( Sanitizer::decodeTagAttributes( '_foo=\'bar\'' ), array( '_foo' => 'bar' ), 'Leading _' );
 128                 $this->assertEquals( Sanitizer::decodeTagAttributes( 'Foo=\'bar\'' ), array( 'foo' => 'bar' ), 'Leading capital' );
 129                 $this->assertEquals( Sanitizer::decodeTagAttributes( 'FOO=BAR' ), array( 'foo' => 'BAR' ), 'Attribute keys are normalized to lowercase' );
 130
 131                 # Invalid beginning
 132                 $this->assertEquals( Sanitizer::decodeTagAttributes( '-foo=bar' ), array(), 'Leading - is forbidden' );
 133                 $this->assertEquals( Sanitizer::decodeTagAttributes( '.foo=bar' ), array(), 'Leading . is forbidden' );
 134                 $this->assertEquals( Sanitizer::decodeTagAttributes( 'foo-bar=bar' ), array( 'foo-bar' => 'bar' ), 'A - is allowed inside the attribute' );
 135                 $this->assertEquals( Sanitizer::decodeTagAttributes( 'foo-=bar' ), array( 'foo-' => 'bar' ), 'A - is allowed inside the attribute' );
 136
 137                 $this->assertEquals( Sanitizer::decodeTagAttributes( 'foo.bar=baz' ), array( 'foo.bar' => 'baz' ), 'A . is allowed inside the attribute' );
 138                 $this->assertEquals( Sanitizer::decodeTagAttributes( 'foo.=baz' ), array( 'foo.' => 'baz' ), 'A . is allowed as last character' );
 139
 140                 $this->assertEquals( Sanitizer::decodeTagAttributes( 'foo6=baz' ), array( 'foo6' => 'baz' ), 'Numbers are allowed' );
 141
 142                 # This bit is more relaxed than XML rules, but some extensions use it, like ProofreadPage (see bug 27539)
 143                 $this->assertEquals( Sanitizer::decodeTagAttributes( '1foo=baz' ), array( '1foo' => 'baz' ), 'Leading numbers are allowed' );
 144
 145                 $this->assertEquals( Sanitizer::decodeTagAttributes( 'foo$=baz' ), array(), 'Symbols are not allowed' );
 146                 $this->assertEquals( Sanitizer::decodeTagAttributes( 'foo@=baz' ), array(), 'Symbols are not allowed' );
 147                 $this->assertEquals( Sanitizer::decodeTagAttributes( 'foo~=baz' ), array(), 'Symbols are not allowed' );
 148
 149
 150                 $this->assertEquals( Sanitizer::decodeTagAttributes( 'foo=1[#^`*%w/(' ), array( 'foo' => '1[#^`*%w/(' ), 'All kind of characters are allowed as values' );
 151                 $this->assertEquals( Sanitizer::decodeTagAttributes( 'foo="1[#^`*%\'w/("' ), array( 'foo' => '1[#^`*%\'w/(' ), 'Double quotes are allowed if quoted by single quotes' );
 152                 $this->assertEquals( Sanitizer::decodeTagAttributes( 'foo=\'1[#^`*%"w/(\'' ), array( 'foo' => '1[#^`*%"w/(' ), 'Single quotes are allowed if quoted by double quotes' );
 153                 $this->assertEquals( Sanitizer::decodeTagAttributes( 'foo=&amp;&quot;' ), array( 'foo' => '&"' ), 'Special chars can be provided as entities' );
 154                 $this->assertEquals( Sanitizer::decodeTagAttributes( 'foo=&foobar;' ), array( 'foo' => '&foobar;' ), 'Entity-like items are accepted' );
 155         }
 156
 157         /**
 158          * @dataProvider provideDeprecatedAttributes
 159          */
 160         function testDeprecatedAttributes( $input, $tag, $expected, $message = null ) {
 161                 $this->assertEquals( $expected, Sanitizer::fixTagAttributes( $input, $tag ), $message );
 162         }
 163
 164         function testDeprecatedAttributesDisabled() {
 165                 global $wgCleanupPresentationalAttributes;
 166
 167                 $wgCleanupPresentationalAttributes = false;
 168
 169                 $this->assertEquals( ' clear="left"', Sanitizer::fixTagAttributes( 'clear="left"', 'br' ), 'Deprecated attributes are not converted to styles when enabled.' );
 170         }
 171
 172         public static function provideDeprecatedAttributes() {
 173                 return array(
 174                         array( 'clear="left"', 'br', ' style="clear: left;"', 'Deprecated attributes are converted to styles when enabled.' ),
 175                         array( 'clear="all"', 'br', ' style="clear: both;"', 'clear=all is converted to clear: both; not clear: all;' ),
 176                         array( 'CLEAR="ALL"', 'br', ' style="clear: both;"', 'clear=ALL is not treated differently from clear=all' ),
 177                         array( 'width="100"', 'td', ' style="width: 100px;"', 'Numeric sizes use pixels instead of numbers.' ),
 178                         array( 'width="100%"', 'td', ' style="width: 100%;"', 'Units are allowed in sizes.' ),
 179                         array( 'WIDTH="100%"', 'td', ' style="width: 100%;"', 'Uppercase WIDTH is treated as lowercase width.' ),
 180                         array( 'WiDTh="100%"', 'td', ' style="width: 100%;"', 'Mixed case does not break WiDTh.' ),
 181                         array( 'nowrap="true"', 'td', ' style="white-space: nowrap;"', 'nowrap attribute is output as white-space: nowrap; not something else.' ),
 182                         array( 'nowrap=""', 'td', ' style="white-space: nowrap;"', 'nowrap="" is considered true, not false' ),
 183                         array( 'NOWRAP="true"', 'td', ' style="white-space: nowrap;"', 'nowrap attribute works when uppercase.' ),
 184                         array( 'NoWrAp="true"', 'td', ' style="white-space: nowrap;"', 'nowrap attribute works when mixed-case.' ),
 185                         array( 'align="right"', 'td', ' style="text-align: right;"'   , 'align on table cells gets converted to text-align' ),
 186                         array( 'align="center"', 'td', ' style="text-align: center;"' , 'align on table cells gets converted to text-align' ),
 187                         array( 'align="left"'  , 'div', ' style="text-align: left;"'  , 'align=(left|right) on div elements gets converted to text-align' ),
 188                         array( 'align="center"', 'div', ' style="text-align: center;"', 'align="center" on div elements gets converted to text-align' ),
 189                         array( 'align="left"'  , 'p',   ' style="text-align: left;"'  , 'align on p elements gets converted to text-align' ),
 190                         array( 'align="left"'  , 'h1',  ' style="text-align: left;"'  , 'align on h1 elements gets converted to text-align' ),
 191                         array( 'align="left"'  , 'h1',  ' style="text-align: left;"'  , 'align on h1 elements gets converted to text-align' ),
 192                         array( 'align="left"'  , 'caption',' style="text-align: left;"','align on caption elements gets converted to text-align' ),
 193                         array( 'align="left"'  , 'tfoot',' style="text-align: left;"' , 'align on tfoot elements gets converted to text-align' ),
 194                         array( 'align="left"'  , 'tbody',' style="text-align: left;"' , 'align on tbody elements gets converted to text-align' ),
 195
 196                         # <tr>
 197                         array( 'align="right"' , 'tr', ' style="text-align: right;"' , 'align on table row get converted to text-align' ),
 198                         array( 'align="center"', 'tr', ' style="text-align: center;"', 'align on table row get converted to text-align' ),
 199                         array( 'align="left"'  , 'tr', ' style="text-align: left;"'  , 'align on table row get converted to text-align' ),
 200
 201                         #table
 202                         array( 'align="left"'  , 'table', ' style="float: left;"'    , 'align on table converted to float' ),
 203                         array( 'align="center"', 'table', ' style="margin-left: auto; margin-right: auto;"', 'align center on table converted to margins' ),
 204                         array( 'align="right"' , 'table', ' style="float: right;"'   , 'align on table converted to float' ),
 205                 );
 206         }
 207
 208         /**
 209          * @dataProvider provideCssCommentsFixtures
 210          */
 211         function testCssCommentsChecking( $expected, $css, $message = '' ) {
 212                 $this->assertEquals(
 213                         $expected,
 214                         Sanitizer::checkCss( $css ),
 215                         $message
 216                 );
 217         }
 218
 219         public static function provideCssCommentsFixtures() {
 220                 /** array( <expected>, <css>, [message] ) */
 221                 return array(
 222                         array( ' ', '/**/' ),
 223                         array( ' ', '/****/' ),
 224                         array( ' ', '/* comment */' ),
 225                         array( ' ', "\\2f\\2a foo \\2a\\2f",
 226                                 'Backslash-escaped comments must be stripped (bug 28450)' ),
 227                         array( '', '/* unfinished comment structure',
 228                                 'Remove anything after a comment-start token' ),
 229                         array( '', "\\2f\\2a unifinished comment'",
 230                                 'Remove anything after a backslash-escaped comment-start token' ),
 231                         array( '/* insecure input */', 'filter: progid:DXImageTransform.Microsoft.AlphaImageLoader(src=\'asdf.png\',sizingMethod=\'scale\');'),
 232                         array( '/* insecure input */', '-ms-filter: "progid:DXImageTransform.Microsoft.AlphaImageLoader(src=\'asdf.png\',sizingMethod=\'scale\')";'),
 233                         array( '/* insecure input */', 'width: expression(1+1);'),
 234                         array( '/* insecure input */', 'background-image: image(asdf.png);'),
 235                         array( '/* insecure input */', 'background-image: -webkit-image(asdf.png);'),
 236                         array( '/* insecure input */', 'background-image: -moz-image(asdf.png);'),
 237                         array( '/* insecure input */', 'background-image: image-set("asdf.png" 1x, "asdf.png" 2x);'),
 238                         array( '/* insecure input */', 'background-image: -webkit-image-set("asdf.png" 1x, "asdf.png" 2x);'),
 239                         array( '/* insecure input */', 'background-image: -moz-image-set("asdf.png" 1x, "asdf.png" 2x);'),
 240                 );
 241         }
 242 }
 243