From ca32f08966f1b51fcb19460f0996bb0c4048e6fe Mon Sep 17 00:00:00 2001 From: Pierre Schmitz Date: Sat, 3 Dec 2011 13:29:22 +0100 Subject: Update to MediaWiki 1.18.0 * also update ArchLinux skin to chagnes in MonoBook * Use only css to hide our menu bar when printing --- tests/phpunit/includes/SanitizerTest.php | 113 +++++++++++++++++++++++++++++++ 1 file changed, 113 insertions(+) create mode 100644 tests/phpunit/includes/SanitizerTest.php (limited to 'tests/phpunit/includes/SanitizerTest.php') diff --git a/tests/phpunit/includes/SanitizerTest.php b/tests/phpunit/includes/SanitizerTest.php new file mode 100644 index 00000000..40d6cf77 --- /dev/null +++ b/tests/phpunit/includes/SanitizerTest.php @@ -0,0 +1,113 @@ +assertEquals( + "\xc3\xa9cole", + Sanitizer::decodeCharReferences( 'école' ), + 'decode named entities' + ); + } + + function testDecodeNumericEntities() { + $this->assertEquals( + "\xc4\x88io bonas dans l'\xc3\xa9cole!", + Sanitizer::decodeCharReferences( "Ĉio bonas dans l'école!" ), + 'decode numeric entities' + ); + } + + function testDecodeMixedEntities() { + $this->assertEquals( + "\xc4\x88io bonas dans l'\xc3\xa9cole!", + Sanitizer::decodeCharReferences( "Ĉio bonas dans l'école!" ), + 'decode mixed numeric/named entities' + ); + } + + function testDecodeMixedComplexEntities() { + $this->assertEquals( + "\xc4\x88io bonas dans l'\xc3\xa9cole! (mais pas Ĉio dans l'école)", + Sanitizer::decodeCharReferences( + "Ĉio bonas dans l'école! (mais pas Ĉio dans l'école)" + ), + 'decode mixed complex entities' + ); + } + + function testInvalidAmpersand() { + $this->assertEquals( + 'a & b', + Sanitizer::decodeCharReferences( 'a & b' ), + 'Invalid ampersand' + ); + } + + function testInvalidEntities() { + $this->assertEquals( + '&foo;', + Sanitizer::decodeCharReferences( '&foo;' ), + 'Invalid named entity' + ); + } + + function testInvalidNumberedEntities() { + $this->assertEquals( UTF8_REPLACEMENT, Sanitizer::decodeCharReferences( "�" ), 'Invalid numbered entity' ); + } + + function testSelfClosingTag() { + $GLOBALS['wgUseTidy'] = false; + $this->assertEquals( + '
Hello world
', + Sanitizer::removeHTMLtags( '
Hello world
' ), + 'Self-closing closing div' + ); + } + + function testDecodeTagAttributes() { + $this->assertEquals( Sanitizer::decodeTagAttributes( 'foo=bar' ), array( 'foo' => 'bar' ), 'Unquoted attribute' ); + $this->assertEquals( Sanitizer::decodeTagAttributes( ' foo = bar ' ), array( 'foo' => 'bar' ), 'Spaced attribute' ); + $this->assertEquals( Sanitizer::decodeTagAttributes( 'foo="bar"' ), array( 'foo' => 'bar' ), 'Double-quoted attribute' ); + $this->assertEquals( Sanitizer::decodeTagAttributes( 'foo=\'bar\'' ), array( 'foo' => 'bar' ), 'Single-quoted attribute' ); + $this->assertEquals( Sanitizer::decodeTagAttributes( 'foo=\'bar\' baz="foo"' ), array( 'foo' => 'bar', 'baz' => 'foo' ), 'Several attributes' ); + + $this->assertEquals( Sanitizer::decodeTagAttributes( 'foo=\'bar\' baz="foo"' ), array( 'foo' => 'bar', 'baz' => 'foo' ), 'Several attributes' ); + $this->assertEquals( Sanitizer::decodeTagAttributes( 'foo=\'bar\' baz="foo"' ), array( 'foo' => 'bar', 'baz' => 'foo' ), 'Several attributes' ); + + $this->assertEquals( Sanitizer::decodeTagAttributes( ':foo=\'bar\'' ), array( ':foo' => 'bar' ), 'Leading :' ); + $this->assertEquals( Sanitizer::decodeTagAttributes( '_foo=\'bar\'' ), array( '_foo' => 'bar' ), 'Leading _' ); + $this->assertEquals( Sanitizer::decodeTagAttributes( 'Foo=\'bar\'' ), array( 'foo' => 'bar' ), 'Leading capital' ); + $this->assertEquals( Sanitizer::decodeTagAttributes( 'FOO=BAR' ), array( 'foo' => 'BAR' ), 'Attribute keys are normalized to lowercase' ); + + # Invalid beginning + $this->assertEquals( Sanitizer::decodeTagAttributes( '-foo=bar' ), array(), 'Leading - is forbidden' ); + $this->assertEquals( Sanitizer::decodeTagAttributes( '.foo=bar' ), array(), 'Leading . is forbidden' ); + $this->assertEquals( Sanitizer::decodeTagAttributes( 'foo-bar=bar' ), array( 'foo-bar' => 'bar' ), 'A - is allowed inside the attribute' ); + $this->assertEquals( Sanitizer::decodeTagAttributes( 'foo-=bar' ), array( 'foo-' => 'bar' ), 'A - is allowed inside the attribute' ); + + $this->assertEquals( Sanitizer::decodeTagAttributes( 'foo.bar=baz' ), array( 'foo.bar' => 'baz' ), 'A . is allowed inside the attribute' ); + $this->assertEquals( Sanitizer::decodeTagAttributes( 'foo.=baz' ), array( 'foo.' => 'baz' ), 'A . is allowed as last character' ); + + $this->assertEquals( Sanitizer::decodeTagAttributes( 'foo6=baz' ), array( 'foo6' => 'baz' ), 'Numbers are allowed' ); + + # This bit is more relaxed than XML rules, but some extensions use it, like ProofreadPage (see bug 27539) + $this->assertEquals( Sanitizer::decodeTagAttributes( '1foo=baz' ), array( '1foo' => 'baz' ), 'Leading numbers are allowed' ); + + $this->assertEquals( Sanitizer::decodeTagAttributes( 'foo$=baz' ), array(), 'Symbols are not allowed' ); + $this->assertEquals( Sanitizer::decodeTagAttributes( 'foo@=baz' ), array(), 'Symbols are not allowed' ); + $this->assertEquals( Sanitizer::decodeTagAttributes( 'foo~=baz' ), array(), 'Symbols are not allowed' ); + + + $this->assertEquals( Sanitizer::decodeTagAttributes( 'foo=1[#^`*%w/(' ), array( 'foo' => '1[#^`*%w/(' ), 'All kind of characters are allowed as values' ); + $this->assertEquals( Sanitizer::decodeTagAttributes( 'foo="1[#^`*%\'w/("' ), array( 'foo' => '1[#^`*%\'w/(' ), 'Double quotes are allowed if quoted by single quotes' ); + $this->assertEquals( Sanitizer::decodeTagAttributes( 'foo=\'1[#^`*%"w/(\'' ), array( 'foo' => '1[#^`*%"w/(' ), 'Single quotes are allowed if quoted by double quotes' ); + $this->assertEquals( Sanitizer::decodeTagAttributes( 'foo=&"' ), array( 'foo' => '&"' ), 'Special chars can be provided as entities' ); + $this->assertEquals( Sanitizer::decodeTagAttributes( 'foo=&foobar;' ), array( 'foo' => '&foobar;' ), 'Entity-like items are accepted' ); + } +} + -- cgit v1.2.3-54-g00ecf