diff options
author | Asmir Mustafic <[email protected]> | 2017-08-28 14:44:01 +0200 |
---|---|---|
committer | Asmir Mustafic <[email protected]> | 2017-08-28 14:44:01 +0200 |
commit | 2a38f56f3772f943be436c7b411c2ae5fac6cee6 (patch) | |
tree | 2b1cec9a30b2301afeda759a16341972b5a492bd /test/HTML5 | |
parent | e965886a79a560b4b00a4c471e2bdfafea23fdcb (diff) |
Fixes https://github.com/Masterminds/html5-php/issues/124
Reference: https://www.w3.org/TR/html52/syntax.html#character-reference-state
If the character reference was consumed as part of an attribute (return state is either attribute value (double-quoted) state, attribute value (single-quoted) state or attribute value (unquoted) state), and the last character matched is not a U+003B SEMICOLON character (;), and the next input character is either a U+003D EQUALS SIGN character (=) or an alphanumeric ASCII character, then, for historical reasons, switch to the character reference end state.
If the last character matched is not a U+003B SEMICOLON character (;), this is a parse error.
Diffstat (limited to 'test/HTML5')
-rw-r--r-- | test/HTML5/Parser/DOMTreeBuilderTest.php | 74 | ||||
-rw-r--r-- | test/HTML5/Parser/TokenizerTest.php | 27 |
2 files changed, 91 insertions, 10 deletions
diff --git a/test/HTML5/Parser/DOMTreeBuilderTest.php b/test/HTML5/Parser/DOMTreeBuilderTest.php index 3e1a58f..a441af8 100644 --- a/test/HTML5/Parser/DOMTreeBuilderTest.php +++ b/test/HTML5/Parser/DOMTreeBuilderTest.php @@ -58,6 +58,80 @@ class DOMTreeBuilderTest extends \Masterminds\HTML5\Tests\TestCase $this->assertEquals('http://www.w3.org/1999/xhtml', $doc->documentElement->namespaceURI); } + public function testBareAmpersand() + { + $html = "<!doctype html> + <html> + <body> + <img src='a&b' /> + <img src='a&=' /> + <img src='a&=c' /> + <img src='a&=9' /> + </body> + </html>"; + $doc = $this->parse($html); + + $this->assertEmpty($this->errors); + $this->assertXmlStringEqualsXmlString(' + <!DOCTYPE html> + <html xmlns="http://www.w3.org/1999/xhtml"><body> + <img src="a&b"/> + <img src="a&="/> + <img src="a&=c"/> + <img src="a&=9"/> + </body> + </html>', $doc->saveXML()); + } + + public function testBareAmpersandNotAllowedInAttributes() + { + $html = "<!doctype html> + <html> + <body> + <img src='a&' /> + <img src='a&+' /> + </body> + </html>"; + $doc = $this->parse($html); + + $this->assertCount(2, $this->errors); + $this->assertXmlStringEqualsXmlString(' + <!DOCTYPE html> + <html xmlns="http://www.w3.org/1999/xhtml"><body> + <img src="a&"/> + <img src="a&+"/> + </body> + </html>', $doc->saveXML()); + } + public function testBareAmpersandNotAllowedInBody() + { + $html = "<!doctype html> + <html> + <body> + a&b + a&= + a&=c + a&=9 + a&+ + a& -- valid + </body> + </html>"; + $doc = $this->parse($html); + + $this->assertCount(5, $this->errors); + $this->assertXmlStringEqualsXmlString(' + <!DOCTYPE html> + <html xmlns="http://www.w3.org/1999/xhtml"><body> + a&b + a&= + a&=c + a&=9 + a&+ + a& -- valid + </body> + </html>', $doc->saveXML()); + } + public function testStrangeCapitalization() { $html = "<!doctype html> diff --git a/test/HTML5/Parser/TokenizerTest.php b/test/HTML5/Parser/TokenizerTest.php index f2f612c..5e52722 100644 --- a/test/HTML5/Parser/TokenizerTest.php +++ b/test/HTML5/Parser/TokenizerTest.php @@ -622,6 +622,13 @@ class TokenizerTest extends \Masterminds\HTML5\Tests\TestCase ), false ), + "<foo a='blue&red'>" => array( + 'foo', + array( + 'a' => 'blue&red' + ), + false + ), "<foo a='blue&red'>" => array( 'foo', array( @@ -629,6 +636,13 @@ class TokenizerTest extends \Masterminds\HTML5\Tests\TestCase ), false ), + "<foo a='blue&&&red'>" => array( + 'foo', + array( + 'a' => 'blue&&&red' + ), + false + ), "<foo a='blue&&red'>" => array( 'foo', array( @@ -725,18 +739,11 @@ class TokenizerTest extends \Masterminds\HTML5\Tests\TestCase // Cause a parse error. $bad = array( - // This will emit an entity lookup failure for &red. - "<foo a='blue&red'>" => array( + // This will emit an entity lookup failure for &+dark. + "<foo a='blue&+dark'>" => array( 'foo', array( - 'a' => 'blue&red' - ), - false - ), - "<foo a='blue&&&red'>" => array( - 'foo', - array( - 'a' => 'blue&&&red' + 'a' => 'blue&+dark' ), false ), |