mirror of
https://github.com/ezyang/htmlpurifier.git
synced 2025-08-08 07:06:46 +02:00
Release 2.0.0, merged in 1026 to HEAD.
git-svn-id: http://htmlpurifier.org/svnroot/htmlpurifier/branches/strict@1179 48356398-32a2-884e-a903-53898d9a118a
This commit is contained in:
@@ -1,59 +1,65 @@
|
||||
<?php
|
||||
|
||||
require_once 'HTMLPurifier/Lexer.php';
|
||||
|
||||
HTMLPurifier_ConfigSchema::define(
|
||||
'Core', 'CleanUTF8DuringGeneration', false, 'bool',
|
||||
'When true, HTMLPurifier_Generator will also check all strings it '.
|
||||
'escapes for UTF-8 well-formedness as a defense in depth measure. '.
|
||||
'This could cause a considerable performance impact, and is not '.
|
||||
'strictly necessary due to the fact that the Lexers should have '.
|
||||
'ensured that all the UTF-8 strings were well-formed. Note that '.
|
||||
'the configuration value is only read at the beginning of '.
|
||||
'generateFromTokens.'
|
||||
);
|
||||
|
||||
HTMLPurifier_ConfigSchema::define(
|
||||
'Core', 'XHTML', true, 'bool',
|
||||
'Determines whether or not output is XHTML or not. When disabled, HTML '.
|
||||
'Purifier goes into HTML 4.01 removes XHTML-specific markup constructs, '.
|
||||
'such as boolean attribute expansion and trailing slashes in empty tags. '.
|
||||
'This directive was available since 1.1.'
|
||||
'Output', 'CommentScriptContents', true, 'bool',
|
||||
'Determines whether or not HTML Purifier should attempt to fix up '.
|
||||
'the contents of script tags for legacy browsers with comments. This '.
|
||||
'directive was available since 1.7.'
|
||||
);
|
||||
HTMLPurifier_ConfigSchema::defineAlias('Core', 'CommentScriptContents', 'Output', 'CommentScriptContents');
|
||||
|
||||
// extension constraints could be factored into ConfigSchema
|
||||
HTMLPurifier_ConfigSchema::define(
|
||||
'Core', 'TidyFormat', false, 'bool',
|
||||
'<p>Determines whether or not to run Tidy on the final output for pretty '.
|
||||
'formatting reasons, such as indentation and wrap.</p><p>This can greatly '.
|
||||
'improve readability for editors who are hand-editing the HTML, but is '.
|
||||
'by no means necessary as HTML Purifier has already fixed all major '.
|
||||
'errors the HTML may have had. Tidy is a non-default extension, and this directive '.
|
||||
'will silently fail if Tidy is not available.</p><p>If you are looking to make '.
|
||||
'the overall look of your page\'s source better, I recommend running Tidy '.
|
||||
'on the entire page rather than just user-content (after all, the '.
|
||||
'indentation relative to the containing blocks will be incorrect).</p><p>This '.
|
||||
'directive was available since 1.1.1.</p>'
|
||||
'Output', 'TidyFormat', false, 'bool', <<<HTML
|
||||
<p>
|
||||
Determines whether or not to run Tidy on the final output for pretty
|
||||
formatting reasons, such as indentation and wrap.
|
||||
</p>
|
||||
<p>
|
||||
This can greatly improve readability for editors who are hand-editing
|
||||
the HTML, but is by no means necessary as HTML Purifier has already
|
||||
fixed all major errors the HTML may have had. Tidy is a non-default
|
||||
extension, and this directive will silently fail if Tidy is not
|
||||
available.
|
||||
</p>
|
||||
<p>
|
||||
If you are looking to make the overall look of your page's source
|
||||
better, I recommend running Tidy on the entire page rather than just
|
||||
user-content (after all, the indentation relative to the containing
|
||||
blocks will be incorrect).
|
||||
</p>
|
||||
<p>
|
||||
This directive was available since 1.1.1.
|
||||
</p>
|
||||
HTML
|
||||
);
|
||||
HTMLPurifier_ConfigSchema::defineAlias('Core', 'TidyFormat', 'Output', 'TidyFormat');
|
||||
|
||||
/**
|
||||
* Generates HTML from tokens.
|
||||
* @todo Create a configuration-wide instance that all objects retrieve
|
||||
*/
|
||||
class HTMLPurifier_Generator
|
||||
{
|
||||
|
||||
/**
|
||||
* Bool cache of %Core.CleanUTF8DuringGeneration
|
||||
* @private
|
||||
*/
|
||||
var $_clean_utf8 = false;
|
||||
|
||||
/**
|
||||
* Bool cache of %Core.XHTML
|
||||
* Bool cache of %HTML.XHTML
|
||||
* @private
|
||||
*/
|
||||
var $_xhtml = true;
|
||||
|
||||
/**
|
||||
* Bool cache of %Output.CommentScriptContents
|
||||
* @private
|
||||
*/
|
||||
var $_scriptFix = false;
|
||||
|
||||
/**
|
||||
* Cache of HTMLDefinition
|
||||
* @private
|
||||
*/
|
||||
var $_def;
|
||||
|
||||
/**
|
||||
* Generates HTML from an array of tokens.
|
||||
* @param $tokens Array of HTMLPurifier_Token
|
||||
@@ -63,13 +69,24 @@ class HTMLPurifier_Generator
|
||||
function generateFromTokens($tokens, $config, &$context) {
|
||||
$html = '';
|
||||
if (!$config) $config = HTMLPurifier_Config::createDefault();
|
||||
$this->_clean_utf8 = $config->get('Core', 'CleanUTF8DuringGeneration');
|
||||
$this->_xhtml = $config->get('Core', 'XHTML');
|
||||
$this->_scriptFix = $config->get('Output', 'CommentScriptContents');
|
||||
|
||||
$this->_def = $config->getHTMLDefinition();
|
||||
$this->_xhtml = $this->_def->doctype->xml;
|
||||
|
||||
if (!$tokens) return '';
|
||||
foreach ($tokens as $token) {
|
||||
$html .= $this->generateFromToken($token);
|
||||
for ($i = 0, $size = count($tokens); $i < $size; $i++) {
|
||||
if ($this->_scriptFix && $tokens[$i]->name === 'script') {
|
||||
// script special case
|
||||
$html .= $this->generateFromToken($tokens[$i++]);
|
||||
$html .= $this->generateScriptFromToken($tokens[$i++]);
|
||||
while ($tokens[$i]->name != 'script') {
|
||||
$html .= $this->generateScriptFromToken($tokens[$i++]);
|
||||
}
|
||||
}
|
||||
$html .= $this->generateFromToken($tokens[$i]);
|
||||
}
|
||||
if ($config->get('Core', 'TidyFormat') && extension_loaded('tidy')) {
|
||||
if ($config->get('Output', 'TidyFormat') && extension_loaded('tidy')) {
|
||||
|
||||
$tidy_options = array(
|
||||
'indent'=> true,
|
||||
@@ -104,14 +121,14 @@ class HTMLPurifier_Generator
|
||||
function generateFromToken($token) {
|
||||
if (!isset($token->type)) return '';
|
||||
if ($token->type == 'start') {
|
||||
$attr = $this->generateAttributes($token->attr);
|
||||
$attr = $this->generateAttributes($token->attr, $token->name);
|
||||
return '<' . $token->name . ($attr ? ' ' : '') . $attr . '>';
|
||||
|
||||
} elseif ($token->type == 'end') {
|
||||
return '</' . $token->name . '>';
|
||||
|
||||
} elseif ($token->type == 'empty') {
|
||||
$attr = $this->generateAttributes($token->attr);
|
||||
$attr = $this->generateAttributes($token->attr, $token->name);
|
||||
return '<' . $token->name . ($attr ? ' ' : '') . $attr .
|
||||
( $this->_xhtml ? ' /': '' )
|
||||
. '>';
|
||||
@@ -125,18 +142,33 @@ class HTMLPurifier_Generator
|
||||
}
|
||||
}
|
||||
|
||||
/**
|
||||
* Special case processor for the contents of script tags
|
||||
* @warning This runs into problems if there's already a literal
|
||||
* --> somewhere inside the script contents.
|
||||
*/
|
||||
function generateScriptFromToken($token) {
|
||||
if (!$token->type == 'text') return $this->generateFromToken($token);
|
||||
return '<!--' . PHP_EOL . $token->data . PHP_EOL . '// -->';
|
||||
// more advanced version:
|
||||
// return '<!--//--><![CDATA[//><!--' . PHP_EOL . $token->data . PHP_EOL . '//--><!]]>';
|
||||
}
|
||||
|
||||
/**
|
||||
* Generates attribute declarations from attribute array.
|
||||
* @param $assoc_array_of_attributes Attribute array
|
||||
* @return Generate HTML fragment for insertion.
|
||||
*/
|
||||
function generateAttributes($assoc_array_of_attributes) {
|
||||
function generateAttributes($assoc_array_of_attributes, $element) {
|
||||
$html = '';
|
||||
foreach ($assoc_array_of_attributes as $key => $value) {
|
||||
if (!$this->_xhtml) {
|
||||
// remove namespaced attributes
|
||||
if (strpos($key, ':') !== false) continue;
|
||||
// also needed: check for attribute minimization
|
||||
if (!empty($this->_def->info[$element]->attr[$key]->minimized)) {
|
||||
$html .= $key . ' ';
|
||||
continue;
|
||||
}
|
||||
}
|
||||
$html .= $key.'="'.$this->escape($value).'" ';
|
||||
}
|
||||
@@ -149,7 +181,6 @@ class HTMLPurifier_Generator
|
||||
* @return String escaped data.
|
||||
*/
|
||||
function escape($string) {
|
||||
if ($this->_clean_utf8) $string = HTMLPurifier_Lexer::cleanUTF8($string);
|
||||
return htmlspecialchars($string, ENT_COMPAT, 'UTF-8');
|
||||
}
|
||||
|
||||
|
Reference in New Issue
Block a user