mirror/php-htmlpurifier
1
0
Fork 0
mirror of https://github.com/ezyang/htmlpurifier.git synced 2025-07-31 03:10:09 +02:00
Code Issues Releases Wiki Activity

Add CDATA support to the Lexers, as well as give PEARSax3 entity replacement.

Browse Source 
git-svn-id: http://htmlpurifier.org/svnroot/htmlpurifier/trunk@106 48356398-32a2-884e-a903-53898d9a118a
This commit is contained in:
Edward Z. Yang
2006-07-23 23:04:34 +00:00
parent 5ce0ae7056
commit 609977f9f5
6 changed files with 165 additions and 65 deletions
Download Patch File Download Diff File Expand all files Collapse all files

9
library/HTMLPurifier/Lexer/DOMLex.php
View File

@@ -27,8 +27,14 @@ class HTMLPurifier_Lexer_DOMLex extends HTMLPurifier_Lexer
public function tokenizeHTML($string) {
$doc = new DOMDocument();
// preprocess string
$string = '<html><body><div>'.$string.'</div></body></html>';
// replace and escape the CDATA sections, since parsing under HTML
// mode won't get 'em.
$string = $this->escapeCDATA($string);
@$doc->loadHTML($string); // mute all errors, handle it transparently
return $this->tokenizeDOM(
$doc->childNodes->item(1)-> // html
@@ -55,7 +61,8 @@ class HTMLPurifier_Lexer_DOMLex extends HTMLPurifier_Lexer
if ( !($node instanceof DOMElement) ) {
if ($node instanceof DOMComment) {
$tokens[] = new HTMLPurifier_Token_Comment($node->data);
} elseif ($node instanceof DOMText) {
} elseif ($node instanceof DOMText ||
$node instanceof DOMCharacterData) {
$tokens[] = new HTMLPurifier_Token_Text($node->data);
}
// quite possibly, the object wasn't handled, that's fine

40
library/HTMLPurifier/Lexer/DirectLex.php
View File

@@ -61,43 +61,6 @@ class HTMLPurifier_Lexer_DirectLex extends HTMLPurifier_Lexer
*/
var $_whitespace = "\x20\x09\x0D\x0A";
/**
* Decimal to parsed string conversion table for special entities.
* @protected
*/
var $_special_dec2str = array(
34 => '"', // quote
38 => '&', // ampersand
39 => "'", // apostrophe
60 => '<', // less than sign
62 => '>' // greater than sign
);
/**
* Stripped entity names to decimal conversion table for special entities.
* @protected
*/
var $_special_ent2dec = array(
'quot' => 34,
'amp' => 38,
'lt' => 60,
'gt' => 62,
);
/**
* Most common entity to raw value conversion table for special entities.
* @protected
*/
var $_special_entity2str = array(
'&quot;' => '"',
'&amp;' => '&',
'&lt;' => '<',
'&gt;' => '>',
'&#39;' => "'",
'&#039;' => "'",
'&#x27;' => "'",
);
/**
* Substitutes only special entities with their parsed equivalents.
*
@@ -153,6 +116,9 @@ class HTMLPurifier_Lexer_DirectLex extends HTMLPurifier_Lexer
$inside_tag = false; // whether or not we're parsing the inside of a tag
$array = array(); // result array
// escape CDATA
$string = $this->escapeCDATA($string);
// expand entities THAT AREN'T THE BIG FIVE
$string = $this->substituteNonSpecialEntities($string);

9
library/HTMLPurifier/Lexer/PEARSax3.php
View File

@@ -29,6 +29,8 @@ class HTMLPurifier_Lexer_PEARSax3 extends HTMLPurifier_Lexer
var $tokens = array();
function tokenizeHTML($html) {
$html = $this->escapeCDATA($html);
$html = $this->substituteNonSpecialEntities($html);
$parser=& new XML_HTMLSax3();
$parser->set_object($this);
$parser->set_element_handler('openHandler','closeHandler');
@@ -79,9 +81,14 @@ class HTMLPurifier_Lexer_PEARSax3 extends HTMLPurifier_Lexer
* Escaped text handler, interface is defined by PEAR package.
*/
function escapeHandler(&$parser, $data) {
if (strpos($data, '-') === 0) {
if (strpos($data, '--') === 0) {
$this->tokens[] = new HTMLPurifier_Token_Comment($data);
}
// CDATA is handled elsewhere, but if it was handled here:
//if (strpos($data, '[CDATA[') === 0) {
// $this->tokens[] = new HTMLPurifier_Token_Text(
// substr($data, 7, strlen($data) - 9) );
//}
return true;
}