1
0
mirror of https://github.com/ezyang/htmlpurifier.git synced 2025-10-17 06:56:06 +02:00

Remove trailing whitespace.

Signed-off-by: Edward Z. Yang <edwardzyang@thewritingpot.com>
This commit is contained in:
Edward Z. Yang
2008-12-06 02:28:20 -05:00
parent 3a6b63dff1
commit 2c955af135
476 changed files with 5595 additions and 5547 deletions

View File

@@ -2,52 +2,52 @@
/**
* Proof-of-concept lexer that uses the PEAR package XML_HTMLSax3 to parse HTML.
*
*
* PEAR, not suprisingly, also has a SAX parser for HTML. I don't know
* very much about implementation, but it's fairly well written. However, that
* abstraction comes at a price: performance. You need to have it installed,
* and if the API changes, it might break our adapter. Not sure whether or not
* it's UTF-8 aware, but it has some entity parsing trouble (in all areas,
* text and attributes).
*
*
* Quite personally, I don't recommend using the PEAR class, and the defaults
* don't use it. The unit tests do perform the tests on the SAX parser too, but
* whatever it does for poorly formed HTML is up to it.
*
*
* @todo Generalize so that XML_HTMLSax is also supported.
*
*
* @warning Entity-resolution inside attributes is broken.
*/
class HTMLPurifier_Lexer_PEARSax3 extends HTMLPurifier_Lexer
{
/**
* Internal accumulator array for SAX parsers.
*/
protected $tokens = array();
public function tokenizeHTML($string, $config, $context) {
$this->tokens = array();
$string = $this->normalize($string, $config, $context);
$parser = new XML_HTMLSax3();
$parser->set_object($this);
$parser->set_element_handler('openHandler','closeHandler');
$parser->set_data_handler('dataHandler');
$parser->set_escape_handler('escapeHandler');
// doesn't seem to work correctly for attributes
$parser->set_option('XML_OPTION_ENTITIES_PARSED', 1);
$parser->parse($string);
return $this->tokens;
}
/**
* Open tag event handler, interface is defined by PEAR package.
*/
@@ -63,7 +63,7 @@ class HTMLPurifier_Lexer_PEARSax3 extends HTMLPurifier_Lexer
}
return true;
}
/**
* Close tag event handler, interface is defined by PEAR package.
*/
@@ -77,7 +77,7 @@ class HTMLPurifier_Lexer_PEARSax3 extends HTMLPurifier_Lexer
$this->tokens[] = new HTMLPurifier_Token_End($name);
return true;
}
/**
* Data event handler, interface is defined by PEAR package.
*/
@@ -85,7 +85,7 @@ class HTMLPurifier_Lexer_PEARSax3 extends HTMLPurifier_Lexer
$this->tokens[] = new HTMLPurifier_Token_Text($data);
return true;
}
/**
* Escaped text handler, interface is defined by PEAR package.
*/
@@ -100,6 +100,6 @@ class HTMLPurifier_Lexer_PEARSax3 extends HTMLPurifier_Lexer
//}
return true;
}
}