mirror/php-htmlpurifier
1
0
Fork 0
mirror of https://github.com/ezyang/htmlpurifier.git synced 2025-07-30 19:00:10 +02:00
Code Issues Releases Wiki Activity

Remove trailing whitespace.

Browse Source 
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
Download Patch File Download Diff File Expand all files Collapse all files

58
library/HTMLPurifier/Lexer/DOMLex.php
View File

@@ -2,20 +2,20 @@
/**
* Parser that uses PHP 5's DOM extension (part of the core).
*
*
* In PHP 5, the DOM XML extension was revamped into DOM and added to the core.
* It gives us a forgiving HTML parser, which we use to transform the HTML
* into a DOM, and then into the tokens. It is blazingly fast (for large
* documents, it performs twenty times faster than
* HTMLPurifier_Lexer_DirectLex,and is the default choice for PHP 5.
*
* HTMLPurifier_Lexer_DirectLex,and is the default choice for PHP 5.
*
* @note Any empty elements will have empty tokens associated with them, even if
* this is prohibited by the spec. This is cannot be fixed until the spec
* comes into play.
*
*
* @note PHP's DOM extension does not actually parse any entities, we use
* our own function to do that.
*
*
* @warning DOM tends to drop whitespace, which may wreak havoc on indenting.
* If this is a huge problem, due to the fact that HTML is hand
* edited and you are unable to get a parser cache that caches the
@@ -26,19 +26,19 @@
class HTMLPurifier_Lexer_DOMLex extends HTMLPurifier_Lexer
{
private $factory;
public function __construct() {
// setup the factory
parent::__construct();
$this->factory = new HTMLPurifier_TokenFactory();
}
public function tokenizeHTML($html, $config, $context) {
$html = $this->normalize($html, $config, $context);
// attempt to armor stray angled brackets that cannot possibly
// form tags and thus are probably being used as emoticons
if ($config->get('Core', 'AggressivelyFixLt')) {
@@ -51,17 +51,17 @@ class HTMLPurifier_Lexer_DOMLex extends HTMLPurifier_Lexer
} while ($html !== $old);
$html = preg_replace_callback($comment, array($this, 'callbackUndoCommentSubst'), $html); // fix comments
}
// preprocess html, essential for UTF-8
$html = $this->wrapHTML($html, $config, $context);
$doc = new DOMDocument();
$doc->encoding = 'UTF-8'; // theoretically, the above has this covered
set_error_handler(array($this, 'muteErrorHandler'));
$doc->loadHTML($html);
restore_error_handler();
$tokens = array();
$this->tokenizeDOM(
$doc->getElementsByTagName('html')->item(0)-> // <html>
@@ -70,10 +70,10 @@ class HTMLPurifier_Lexer_DOMLex extends HTMLPurifier_Lexer
, $tokens);
return $tokens;
}
/**
* Recursive function that tokenizes a node, putting it into an accumulator.
*
*
* @param $node DOMNode to be tokenized.
* @param $tokens Array-list of already tokenized tokens.
* @param $collect Says whether or start and close are collected, set to
@@ -82,7 +82,7 @@ class HTMLPurifier_Lexer_DOMLex extends HTMLPurifier_Lexer
* @returns Tokens of node appended to previously passed tokens.
*/
protected function tokenizeDOM($node, &$tokens, $collect = false) {
// intercept non element nodes. WE MUST catch all of them,
// but we're not getting the character reference nodes because
// those should have been preprocessed
@@ -119,11 +119,11 @@ class HTMLPurifier_Lexer_DOMLex extends HTMLPurifier_Lexer
) {
return;
}
$attr = $node->hasAttributes() ?
$this->transformAttrToAssoc($node->attributes) :
array();
// We still have to make sure that the element actually IS empty
if (!$node->childNodes->length) {
if ($collect) {
@@ -145,12 +145,12 @@ class HTMLPurifier_Lexer_DOMLex extends HTMLPurifier_Lexer
$tokens[] = $this->factory->createEnd($tag_name);
}
}
}
/**
* Converts a DOMNamedNodeMap of DOMAttr objects into an assoc array.
*
*
* @param $attribute_list DOMNamedNodeMap of DOMAttr objects.
* @returns Associative array of attributes.
*/
@@ -165,12 +165,12 @@ class HTMLPurifier_Lexer_DOMLex extends HTMLPurifier_Lexer
}
return $array;
}
/**
* An error handler that mutes all errors
*/
public function muteErrorHandler($errno, $errstr) {}
/**
* Callback function for undoing escaping of stray angled brackets
* in comments
@@ -178,7 +178,7 @@ class HTMLPurifier_Lexer_DOMLex extends HTMLPurifier_Lexer
public function callbackUndoCommentSubst($matches) {
return '<!--' . strtr($matches[1], array('&amp;'=>'&','&lt;'=>'<')) . $matches[2];
}
/**
* Callback function that entity-izes ampersands in comments so that
* callbackUndoCommentSubst doesn't clobber them
@@ -186,27 +186,27 @@ class HTMLPurifier_Lexer_DOMLex extends HTMLPurifier_Lexer
public function callbackArmorCommentEntities($matches) {
return '<!--' . str_replace('&', '&amp;', $matches[1]) . $matches[2];
}
/**
* Wraps an HTML fragment in the necessary HTML
*/
protected function wrapHTML($html, $config, $context) {
$def = $config->getDefinition('HTML');
$ret = '';
if (!empty($def->doctype->dtdPublic) || !empty($def->doctype->dtdSystem)) {
$ret .= '<!DOCTYPE html ';
if (!empty($def->doctype->dtdPublic)) $ret .= 'PUBLIC "' . $def->doctype->dtdPublic . '" ';
if (!empty($def->doctype->dtdSystem)) $ret .= '"' . $def->doctype->dtdSystem . '" ';
$ret .= '>';
}
$ret .= '<html><head>';
$ret .= '<meta http-equiv="Content-Type" content="text/html; charset=utf-8" />';
// No protection if $html contains a stray </div>!
$ret .= '</head><body><div>'.$html.'</div></body></html>';
return $ret;
}
}