tests/phpunit/includes/SanitizerTest.php

   1 <?php
   2
   3 class SanitizerTest extends MediaWikiTestCase {
   4
   5         function setUp() {
   6                 AutoLoader::loadClass( 'Sanitizer' );
   7         }
   8
   9         function testDecodeNamedEntities() {
  10                 $this->assertEquals(
  11                         "\xc3\xa9cole",
  12                         Sanitizer::decodeCharReferences( '&eacute;cole' ),
  13                         'decode named entities'
  14                 );
  15         }
  16
  17         function testDecodeNumericEntities() {
  18                 $this->assertEquals(
  19                         "\xc4\x88io bonas dans l'\xc3\xa9cole!",
  20                         Sanitizer::decodeCharReferences( "&#x108;io bonas dans l'&#233;cole!" ),
  21                         'decode numeric entities'
  22                 );
  23         }
  24
  25         function testDecodeMixedEntities() {
  26                 $this->assertEquals(
  27                         "\xc4\x88io bonas dans l'\xc3\xa9cole!",
  28                         Sanitizer::decodeCharReferences( "&#x108;io bonas dans l'&eacute;cole!" ),
  29                         'decode mixed numeric/named entities'
  30                 );
  31         }
  32
  33         function testDecodeMixedComplexEntities() {
  34                 $this->assertEquals(
  35                         "\xc4\x88io bonas dans l'\xc3\xa9cole! (mais pas &#x108;io dans l'&eacute;cole)",
  36                         Sanitizer::decodeCharReferences(
  37                                 "&#x108;io bonas dans l'&eacute;cole! (mais pas &amp;#x108;io dans l'&#38;eacute;cole)"
  38                         ),
  39                         'decode mixed complex entities'
  40                 );
  41         }
  42
  43         function testInvalidAmpersand() {
  44                 $this->assertEquals(
  45                         'a & b',
  46                         Sanitizer::decodeCharReferences( 'a & b' ),
  47                         'Invalid ampersand'
  48                 );
  49         }
  50
  51         function testInvalidEntities() {
  52                 $this->assertEquals(
  53                         '&foo;',
  54                         Sanitizer::decodeCharReferences( '&foo;' ),
  55                         'Invalid named entity'
  56                 );
  57         }
  58
  59         function testInvalidNumberedEntities() {
  60                 $this->assertEquals( UTF8_REPLACEMENT, Sanitizer::decodeCharReferences( "&#88888888888888;" ), 'Invalid numbered entity' );
  61         }
  62
  63         function testSelfClosingTag() {
  64                 $GLOBALS['wgUseTidy'] = false;
  65                 $this->assertEquals(
  66                         '<div>Hello world</div>',
  67                         Sanitizer::removeHTMLtags( '<div>Hello world</div />' ),
  68                         'Self-closing closing div'
  69                 );
  70         }
  71
  72         function testDecodeTagAttributes() {
  73                 $this->assertEquals( Sanitizer::decodeTagAttributes( 'foo=bar' ), array( 'foo' => 'bar' ), 'Unquoted attribute' );
  74                 $this->assertEquals( Sanitizer::decodeTagAttributes( '    foo   =   bar    ' ), array( 'foo' => 'bar' ), 'Spaced attribute' );
  75                 $this->assertEquals( Sanitizer::decodeTagAttributes( 'foo="bar"' ), array( 'foo' => 'bar' ), 'Double-quoted attribute' );
  76                 $this->assertEquals( Sanitizer::decodeTagAttributes( 'foo=\'bar\'' ), array( 'foo' => 'bar' ), 'Single-quoted attribute' );
  77                 $this->assertEquals( Sanitizer::decodeTagAttributes( 'foo=\'bar\'   baz="foo"' ), array( 'foo' => 'bar', 'baz' => 'foo' ), 'Several attributes' );
  78
  79                 $this->assertEquals( Sanitizer::decodeTagAttributes( 'foo=\'bar\'   baz="foo"' ), array( 'foo' => 'bar', 'baz' => 'foo' ), 'Several attributes' );
  80                 $this->assertEquals( Sanitizer::decodeTagAttributes( 'foo=\'bar\'   baz="foo"' ), array( 'foo' => 'bar', 'baz' => 'foo' ), 'Several attributes' );
  81
  82                 $this->assertEquals( Sanitizer::decodeTagAttributes( ':foo=\'bar\'' ), array( ':foo' => 'bar' ), 'Leading :' );
  83                 $this->assertEquals( Sanitizer::decodeTagAttributes( '_foo=\'bar\'' ), array( '_foo' => 'bar' ), 'Leading _' );
  84                 $this->assertEquals( Sanitizer::decodeTagAttributes( 'Foo=\'bar\'' ), array( 'foo' => 'bar' ), 'Leading capital' );
  85                 $this->assertEquals( Sanitizer::decodeTagAttributes( 'FOO=BAR' ), array( 'foo' => 'BAR' ), 'Attribute keys are normalized to lowercase' );
  86
  87                 # Invalid beginning
  88                 $this->assertEquals( Sanitizer::decodeTagAttributes( '-foo=bar' ), array(), 'Leading - is forbidden' );
  89                 $this->assertEquals( Sanitizer::decodeTagAttributes( '.foo=bar' ), array(), 'Leading . is forbidden' );
  90                 $this->assertEquals( Sanitizer::decodeTagAttributes( 'foo-bar=bar' ), array( 'foo-bar' => 'bar' ), 'A - is allowed inside the attribute' );
  91                 $this->assertEquals( Sanitizer::decodeTagAttributes( 'foo-=bar' ), array( 'foo-' => 'bar' ), 'A - is allowed inside the attribute' );
  92
  93                 $this->assertEquals( Sanitizer::decodeTagAttributes( 'foo.bar=baz' ), array( 'foo.bar' => 'baz' ), 'A . is allowed inside the attribute' );
  94                 $this->assertEquals( Sanitizer::decodeTagAttributes( 'foo.=baz' ), array( 'foo.' => 'baz' ), 'A . is allowed as last character' );
  95
  96                 $this->assertEquals( Sanitizer::decodeTagAttributes( 'foo6=baz' ), array( 'foo6' => 'baz' ), 'Numbers are allowed' );
  97
  98                 # This bit is more relaxed than XML rules, but some extensions use it, like ProofreadPage (see bug 27539)
  99                 $this->assertEquals( Sanitizer::decodeTagAttributes( '1foo=baz' ), array( '1foo' => 'baz' ), 'Leading numbers are allowed' );
 100
 101                 $this->assertEquals( Sanitizer::decodeTagAttributes( 'foo$=baz' ), array(), 'Symbols are not allowed' );
 102                 $this->assertEquals( Sanitizer::decodeTagAttributes( 'foo@=baz' ), array(), 'Symbols are not allowed' );
 103                 $this->assertEquals( Sanitizer::decodeTagAttributes( 'foo~=baz' ), array(), 'Symbols are not allowed' );
 104
 105
 106                 $this->assertEquals( Sanitizer::decodeTagAttributes( 'foo=1[#^`*%w/(' ), array( 'foo' => '1[#^`*%w/(' ), 'All kind of characters are allowed as values' );
 107                 $this->assertEquals( Sanitizer::decodeTagAttributes( 'foo="1[#^`*%\'w/("' ), array( 'foo' => '1[#^`*%\'w/(' ), 'Double quotes are allowed if quoted by single quotes' );
 108                 $this->assertEquals( Sanitizer::decodeTagAttributes( 'foo=\'1[#^`*%"w/(\'' ), array( 'foo' => '1[#^`*%"w/(' ), 'Single quotes are allowed if quoted by double quotes' );
 109                 $this->assertEquals( Sanitizer::decodeTagAttributes( 'foo=&amp;&quot;' ), array( 'foo' => '&"' ), 'Special chars can be provided as entities' );
 110                 $this->assertEquals( Sanitizer::decodeTagAttributes( 'foo=&foobar;' ), array( 'foo' => '&foobar;' ), 'Entity-like items are accepted' );
 111         }
 112
 113         function testDeprecatedAttributesDisabled() {
 114                 $GLOBALS['wgCleanupPresentationalAttributes'] = false;
 115                 $this->assertEquals( ' clear="left"', Sanitizer::fixTagAttributes( 'clear="left"', 'br' ), 'Deprecated attributes are not converted to styles when enabled.' );
 116         }
 117
 118         /**
 119          * @dataProvider provideDeprecatedAttributes
 120          */
 121         function testDeprecatedAttributes( $input, $tag, $expected, $message = null ) {
 122                 $GLOBALS['wgCleanupPresentationalAttributes'] = true;
 123                 $this->assertEquals( $expected, Sanitizer::fixTagAttributes( $input, $tag ), $message );
 124         }
 125
 126         function provideDeprecatedAttributes() {
 127                 return array(
 128                         array( 'clear="left"', 'br', ' style="clear: left;"', 'Deprecated attributes are converted to styles when enabled.' ),
 129                         array( 'clear="all"', 'br', ' style="clear: both;"', 'clear=all is converted to clear: both; not clear: all;' ),
 130                         array( 'CLEAR="ALL"', 'br', ' style="clear: both;"', 'clear=ALL is not treated differently from clear=all' ),
 131                         array( 'width="100"', 'td', ' style="width: 100px;"', 'Numeric sizes use pixels instead of numbers.' ),
 132                         array( 'width="100%"', 'td', ' style="width: 100%;"', 'Units are allowed in sizes.' ),
 133                         array( 'WIDTH="100%"', 'td', ' style="width: 100%;"', 'Uppercase WIDTH is treated as lowercase width.' ),
 134                         array( 'WiDTh="100%"', 'td', ' style="width: 100%;"', 'Mixed case does not break WiDTh.' ),
 135                         array( 'nowrap="true"', 'td', ' style="white-space: nowrap;"', 'nowrap attribute is output as white-space: nowrap; not something else.' ),
 136                         array( 'nowrap=""', 'td', ' style="white-space: nowrap;"', 'nowrap="" is considered true, not false' ),
 137                         array( 'NOWRAP="true"', 'td', ' style="white-space: nowrap;"', 'nowrap attribute works when uppercase.' ),
 138                         array( 'NoWrAp="true"', 'td', ' style="white-space: nowrap;"', 'nowrap attribute works when mixed-case.' ),
 139                         array( 'align="right"', 'td', ' style="text-align: right;"', 'align on table cells gets converted to text-align' ),
 140                         array( 'align="center"', 'td', ' style="text-align: center;"', 'align on table cells gets converted to text-align' ),
 141                         array( 'align="left"', 'div', ' style="float: left;"', 'align=(left|right) on non-cells gets converted to float' ),
 142                         array( 'align="center"', 'div', ' style="margin-left: auto; margin-right: auto;"', 'align="center" on non-cells' ),
 143                 );
 144         }
 145
 146         /**
 147          * @dataProvider provideCssCommentsFixtures
 148          */
 149         function testCssCommentsChecking( $expected, $css, $message = '' ) {
 150                 $this->assertEquals(
 151                         $expected,
 152                         Sanitizer::checkCss( $css ),
 153                         $message
 154                 );
 155         }
 156
 157         function provideCssCommentsFixtures() {
 158                 /** array( <expected>, <css>, [message] ) */
 159                 return array(
 160                         array( ' ', '/**/' ),
 161                         array( ' ', '/****/' ),
 162                         array( ' ', '/* comment */' ),
 163                         array( ' ', "\\2f\\2a foo \\2a\\2f",
 164                                 'Backslash-escaped comments must be stripped (bug 28450)' ),
 165                         array( '', '/* unfinished comment structure',
 166                                 'Remove anything after a comment-start token' ),
 167                         array( '', "\\2f\\2a unifinished comment'",
 168                                 'Remove anything after a backslash-escaped comment-start token' ),
 169                 );
 170         }
 171 }
 172