mirror of
https://github.com/ezyang/htmlpurifier.git
synced 2025-07-30 19:00:10 +02:00
Finish documenting PEARSax3, touch up the other docs. Nuke the original lexer.txt document.
git-svn-id: http://htmlpurifier.org/svnroot/htmlpurifier/trunk@102 48356398-32a2-884e-a903-53898d9a118a
This commit is contained in:
@@ -3,14 +3,32 @@
|
||||
require_once 'XML/HTMLSax3.php'; // PEAR
|
||||
require_once 'HTMLPurifier/Lexer.php';
|
||||
|
||||
// uses the PEAR class XML_HTMLSax3 to parse XML
|
||||
/**
|
||||
* Lexer that uses the PEAR package XML_HTMLSax3 to parse
|
||||
*
|
||||
* 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.
|
||||
*
|
||||
* 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.
|
||||
*/
|
||||
|
||||
class HTMLPurifier_Lexer_PEARSax3 extends HTMLPurifier_Lexer
|
||||
{
|
||||
|
||||
var $tokens;
|
||||
/**
|
||||
* Internal accumulator array for SAX parsers.
|
||||
* @protected
|
||||
*/
|
||||
var $tokens = array();
|
||||
|
||||
function tokenizeHTML($html) {
|
||||
$this->tokens = array();
|
||||
$parser=& new XML_HTMLSax3();
|
||||
$parser->set_object($this);
|
||||
$parser->set_element_handler('openHandler','closeHandler');
|
||||
@@ -18,9 +36,14 @@ class HTMLPurifier_Lexer_PEARSax3 extends HTMLPurifier_Lexer
|
||||
$parser->set_escape_handler('escapeHandler');
|
||||
$parser->set_option('XML_OPTION_ENTITIES_PARSED', 1);
|
||||
$parser->parse($html);
|
||||
return $this->tokens;
|
||||
$tokens = $this->tokens;
|
||||
$this->tokens = array();
|
||||
return $tokens;
|
||||
}
|
||||
|
||||
/**
|
||||
* Open tag event handler, interface is defined by PEAR package.
|
||||
*/
|
||||
function openHandler(&$parser, $name, $attrs, $closed) {
|
||||
if ($closed) {
|
||||
$this->tokens[] = new HTMLPurifier_Token_Empty($name, $attrs);
|
||||
@@ -30,6 +53,9 @@ class HTMLPurifier_Lexer_PEARSax3 extends HTMLPurifier_Lexer
|
||||
return true;
|
||||
}
|
||||
|
||||
/**
|
||||
* Close tag event handler, interface is defined by PEAR package.
|
||||
*/
|
||||
function closeHandler(&$parser, $name) {
|
||||
// HTMLSax3 seems to always send empty tags an extra close tag
|
||||
// check and ignore if you see it:
|
||||
@@ -41,11 +67,17 @@ class HTMLPurifier_Lexer_PEARSax3 extends HTMLPurifier_Lexer
|
||||
return true;
|
||||
}
|
||||
|
||||
/**
|
||||
* Data event handler, interface is defined by PEAR package.
|
||||
*/
|
||||
function dataHandler(&$parser, $data) {
|
||||
$this->tokens[] = new HTMLPurifier_Token_Text($data);
|
||||
return true;
|
||||
}
|
||||
|
||||
/**
|
||||
* Escaped text handler,interface is defined by PEAR package.
|
||||
*/
|
||||
function escapeHandler(&$parser, $data) {
|
||||
if (strpos($data, '-') === 0) {
|
||||
$this->tokens[] = new HTMLPurifier_Token_Comment($data);
|
||||
|
Reference in New Issue
Block a user