L-electron-Rare/moodle
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

MDL-22537 new html purifier backported to stable, unfortunately PHP5 only

Browse Source
This commit is contained in:
Petr Skoda
2010-05-21 11:39:22 +00:00
parent f8502768a2
commit db359e6369
330 changed files with 13929 additions and 10060 deletions
Download Patch File Download Diff File Expand all files Collapse all files
lib/htmlpurifier/HTMLPurifier/AttrDef/HTML/Bool.php
+11 -12
View File
@@ -1,29 +1,28 @@
<?php
require_once 'HTMLPurifier/AttrDef.php';
/**
* Validates a boolean attribute
*/
class HTMLPurifier_AttrDef_HTML_Bool extends HTMLPurifier_AttrDef
{
var $name;
var $minimized = true;
function HTMLPurifier_AttrDef_HTML_Bool($name = false) {$this->name = $name;}
function validate($string, $config, &$context) {
protected $name;
public $minimized = true;
public function __construct($name = false) {$this->name = $name;}
public function validate($string, $config, $context) {
if (empty($string)) return false;
return $this->name;
}
/**
* @param $string Name of attribute
*/
function make($string) {
public function make($string) {
return new HTMLPurifier_AttrDef_HTML_Bool($string);
}
}
// vim: et sw=4 sts=4
lib/htmlpurifier/HTMLPurifier/AttrDef/HTML/Class.php
+34
View File
@@ -0,0 +1,34 @@
<?php
/**
* Implements special behavior for class attribute (normally NMTOKENS)
*/
class HTMLPurifier_AttrDef_HTML_Class extends HTMLPurifier_AttrDef_HTML_Nmtokens
{
protected function split($string, $config, $context) {
// really, this twiddle should be lazy loaded
$name = $config->getDefinition('HTML')->doctype->name;
if ($name == "XHTML 1.1" || $name == "XHTML 2.0") {
return parent::split($string, $config, $context);
} else {
return preg_split('/\s+/', $string);
}
}
protected function filter($tokens, $config, $context) {
$allowed = $config->get('Attr.AllowedClasses');
$forbidden = $config->get('Attr.ForbiddenClasses');
$ret = array();
foreach ($tokens as $token) {
if (
($allowed === null || isset($allowed[$token])) &&
!isset($forbidden[$token]) &&
// We need this O(n) check because of PHP's array
// implementation that casts -0 to 0.
!in_array($token, $ret, true)
) {
$ret[] = $token;
}
}
return $ret;
}
}
lib/htmlpurifier/HTMLPurifier/AttrDef/HTML/Color.php
+11 -13
View File
@@ -1,34 +1,32 @@
<?php
require_once 'HTMLPurifier/AttrDef.php';
require_once 'HTMLPurifier/AttrDef/CSS/Color.php'; // for %Core.ColorKeywords
/**
* Validates a color according to the HTML spec.
*/
class HTMLPurifier_AttrDef_HTML_Color extends HTMLPurifier_AttrDef
{
function validate($string, $config, &$context) {
public function validate($string, $config, $context) {
static $colors = null;
if ($colors === null) $colors = $config->get('Core', 'ColorKeywords');
if ($colors === null) $colors = $config->get('Core.ColorKeywords');
$string = trim($string);
if (empty($string)) return false;
if (isset($colors[$string])) return $colors[$string];
if ($string[0] === '#') $hex = substr($string, 1);
else $hex = $string;
$length = strlen($hex);
if ($length !== 3 && $length !== 6) return false;
if (!ctype_xdigit($hex)) return false;
if ($length === 3) $hex = $hex[0].$hex[0].$hex[1].$hex[1].$hex[2].$hex[2];
return "#$hex";
}
}
// vim: et sw=4 sts=4
lib/htmlpurifier/HTMLPurifier/AttrDef/HTML/FrameTarget.php
+10 -22
View File
@@ -1,33 +1,21 @@
<?php
HTMLPurifier_ConfigSchema::define(
'Attr', 'AllowedFrameTargets', array(), 'lookup',
'Lookup table of all allowed link frame targets. Some commonly used '.
'link targets include _blank, _self, _parent and _top. Values should '.
'be lowercase, as validation will be done in a case-sensitive manner '.
'despite W3C\'s recommendation. XHTML 1.0 Strict does not permit '.
'the target attribute so this directive will have no effect in that '.
'doctype. XHTML 1.1 does not enable the Target module by default, you '.
'will have to manually enable it (see the module documentation for more details.)'
);
require_once 'HTMLPurifier/AttrDef/Enum.php';
/**
* Special-case enum attribute definition that lazy loads allowed frame targets
*/
class HTMLPurifier_AttrDef_HTML_FrameTarget extends HTMLPurifier_AttrDef_Enum
{
var $valid_values = false; // uninitialized value
var $case_sensitive = false;
function HTMLPurifier_AttrDef_HTML_FrameTarget() {}
function validate($string, $config, &$context) {
if ($this->valid_values === false) $this->valid_values = $config->get('Attr', 'AllowedFrameTargets');
public $valid_values = false; // uninitialized value
protected $case_sensitive = false;
public function __construct() {}
public function validate($string, $config, $context) {
if ($this->valid_values === false) $this->valid_values = $config->get('Attr.AllowedFrameTargets');
return parent::validate($string, $config, $context);
}
}
// vim: et sw=4 sts=4
lib/htmlpurifier/HTMLPurifier/AttrDef/HTML/ID.php
+21 -71
View File
@@ -1,56 +1,5 @@
<?php
require_once 'HTMLPurifier/AttrDef.php';
require_once 'HTMLPurifier/IDAccumulator.php';
HTMLPurifier_ConfigSchema::define(
'Attr', 'EnableID', false, 'bool',
'Allows the ID attribute in HTML. This is disabled by default '.
'due to the fact that without proper configuration user input can '.
'easily break the validation of a webpage by specifying an ID that is '.
'already on the surrounding HTML. If you don\'t mind throwing caution to '.
'the wind, enable this directive, but I strongly recommend you also '.
'consider blacklisting IDs you use (%Attr.IDBlacklist) or prefixing all '.
'user supplied IDs (%Attr.IDPrefix). This directive has been available '.
'since 1.2.0, and when set to true reverts to the behavior of pre-1.2.0 '.
'versions.'
);
HTMLPurifier_ConfigSchema::defineAlias(
'HTML', 'EnableAttrID', 'Attr', 'EnableID'
);
HTMLPurifier_ConfigSchema::define(
'Attr', 'IDPrefix', '', 'string',
'String to prefix to IDs. If you have no idea what IDs your pages '.
'may use, you may opt to simply add a prefix to all user-submitted ID '.
'attributes so that they are still usable, but will not conflict with '.
'core page IDs. Example: setting the directive to \'user_\' will result in '.
'a user submitted \'foo\' to become \'user_foo\' Be sure to set '.
'%HTML.EnableAttrID to true before using '.
'this. This directive was available since 1.2.0.'
);
HTMLPurifier_ConfigSchema::define(
'Attr', 'IDPrefixLocal', '', 'string',
'Temporary prefix for IDs used in conjunction with %Attr.IDPrefix. If '.
'you need to allow multiple sets of '.
'user content on web page, you may need to have a seperate prefix that '.
'changes with each iteration. This way, seperately submitted user content '.
'displayed on the same page doesn\'t clobber each other. Ideal values '.
'are unique identifiers for the content it represents (i.e. the id of '.
'the row in the database). Be sure to add a seperator (like an underscore) '.
'at the end. Warning: this directive will not work unless %Attr.IDPrefix '.
'is set to a non-empty value! This directive was available since 1.2.0.'
);
HTMLPurifier_ConfigSchema::define(
'Attr', 'IDBlacklistRegexp', null, 'string/null',
'PCRE regular expression to be matched against all IDs. If the expression '.
'is matches, the ID is rejected. Use this with care: may cause '.
'significant degradation. ID matching is done after all other '.
'validation. This directive was available since 1.6.0.'
);
/**
* Validates the HTML attribute ID.
* @warning Even though this is the id processor, it
@@ -62,35 +11,35 @@ HTMLPurifier_ConfigSchema::define(
class HTMLPurifier_AttrDef_HTML_ID extends HTMLPurifier_AttrDef
{
// ref functionality disabled, since we also have to verify
// whether or not the ID it refers to exists
function validate($id, $config, &$context) {
if (!$config->get('Attr', 'EnableID')) return false;
public function validate($id, $config, $context) {
if (!$config->get('Attr.EnableID')) return false;
$id = trim($id); // trim it first
if ($id === '') return false;
$prefix = $config->get('Attr', 'IDPrefix');
$prefix = $config->get('Attr.IDPrefix');
if ($prefix !== '') {
$prefix .= $config->get('Attr', 'IDPrefixLocal');
$prefix .= $config->get('Attr.IDPrefixLocal');
// prevent re-appending the prefix
if (strpos($id, $prefix) !== 0) $id = $prefix . $id;
} elseif ($config->get('Attr', 'IDPrefixLocal') !== '') {
} elseif ($config->get('Attr.IDPrefixLocal') !== '') {
trigger_error('%Attr.IDPrefixLocal cannot be used unless '.
'%Attr.IDPrefix is set', E_USER_WARNING);
}
//if (!$this->ref) {
$id_accumulator =& $context->get('IDAccumulator');
if (isset($id_accumulator->ids[$id])) return false;
//}
// we purposely avoid using regex, hopefully this is faster
if (ctype_alpha($id)) {
$result = true;
} else {
@@ -101,20 +50,21 @@ class HTMLPurifier_AttrDef_HTML_ID extends HTMLPurifier_AttrDef
);
$result = ($trim === '');
}
$regexp = $config->get('Attr', 'IDBlacklistRegexp');
$regexp = $config->get('Attr.IDBlacklistRegexp');
if ($regexp && preg_match($regexp, $id)) {
return false;
}
if (/*!$this->ref && */$result) $id_accumulator->add($id);
// if no change was made to the ID, return the result
// else, return the new id if stripping whitespace made it
// valid, or return false.
return $result ? $id : false;
}
}
// vim: et sw=4 sts=4
lib/htmlpurifier/HTMLPurifier/AttrDef/HTML/Length.php
+15 -17
View File
@@ -1,43 +1,41 @@
<?php
require_once 'HTMLPurifier/AttrDef.php';
require_once 'HTMLPurifier/AttrDef/HTML/Pixels.php';
/**
* Validates the HTML type length (not to be confused with CSS's length).
*
*
* This accepts integer pixels or percentages as lengths for certain
* HTML attributes.
*/
class HTMLPurifier_AttrDef_HTML_Length extends HTMLPurifier_AttrDef_HTML_Pixels
{
function validate($string, $config, &$context) {
public function validate($string, $config, $context) {
$string = trim($string);
if ($string === '') return false;
$parent_result = parent::validate($string, $config, $context);
if ($parent_result !== false) return $parent_result;
$length = strlen($string);
$last_char = $string[$length - 1];
if ($last_char !== '%') return false;
$points = substr($string, 0, $length - 1);
if (!is_numeric($points)) return false;
$points = (int) $points;
if ($points < 0) return '0%';
if ($points > 100) return '100%';
return ((string) $points) . '%';
}
}
// vim: et sw=4 sts=4
lib/htmlpurifier/HTMLPurifier/AttrDef/HTML/LinkTypes.php
+16 -35
View File
@@ -1,22 +1,5 @@
<?php
require_once 'HTMLPurifier/AttrDef.php';
HTMLPurifier_ConfigSchema::define(
'Attr', 'AllowedRel', array(), 'lookup',
'List of allowed forward document relationships in the rel attribute. '.
'Common values may be nofollow or print. By default, this is empty, '.
'meaning that no document relationships are allowed. This directive '.
'was available since 1.6.0.'
);
HTMLPurifier_ConfigSchema::define(
'Attr', 'AllowedRev', array(), 'lookup',
'List of allowed reverse document relationships in the rev attribute. '.
'This attribute is a bit of an edge-case; if you don\'t know what it '.
'is for, stay away. This directive was available since 1.6.0.'
);
/**
* Validates a rel/rev link attribute against a directive of allowed values
* @note We cannot use Enum because link types allow multiple
@@ -25,11 +8,11 @@ HTMLPurifier_ConfigSchema::define(
*/
class HTMLPurifier_AttrDef_HTML_LinkTypes extends HTMLPurifier_AttrDef
{
/** Name config attribute to pull. */
var $name;
function HTMLPurifier_AttrDef_HTML_LinkTypes($name) {
protected $name;
public function __construct($name) {
$configLookup = array(
'rel' => 'AllowedRel',
'rev' => 'AllowedRev'
@@ -41,15 +24,15 @@ class HTMLPurifier_AttrDef_HTML_LinkTypes extends HTMLPurifier_AttrDef
}
$this->name = $configLookup[$name];
}
function validate($string, $config, &$context) {
$allowed = $config->get('Attr', $this->name);
public function validate($string, $config, $context) {
$allowed = $config->get('Attr.' . $this->name);
if (empty($allowed)) return false;
$string = $this->parseCDATA($string);
$parts = explode(' ', $string);
// lookup to prevent duplicates
$ret_lookup = array();
foreach ($parts as $part) {
@@ -57,16 +40,14 @@ class HTMLPurifier_AttrDef_HTML_LinkTypes extends HTMLPurifier_AttrDef
if (!isset($allowed[$part])) continue;
$ret_lookup[$part] = true;
}
if (empty($ret_lookup)) return false;
$ret_array = array();
foreach ($ret_lookup as $part => $bool) $ret_array[] = $part;
$string = implode(' ', $ret_array);
$string = implode(' ', array_keys($ret_lookup));
return $string;
}
}
// vim: et sw=4 sts=4
lib/htmlpurifier/HTMLPurifier/AttrDef/HTML/MultiLength.php
+14 -16
View File
@@ -1,43 +1,41 @@
<?php
require_once 'HTMLPurifier/AttrDef.php';
require_once 'HTMLPurifier/AttrDef/HTML/Length.php';
/**
* Validates a MultiLength as defined by the HTML spec.
*
*
* A multilength is either a integer (pixel count), a percentage, or
* a relative number.
*/
class HTMLPurifier_AttrDef_HTML_MultiLength extends HTMLPurifier_AttrDef_HTML_Length
{
function validate($string, $config, &$context) {
public function validate($string, $config, $context) {
$string = trim($string);
if ($string === '') return false;
$parent_result = parent::validate($string, $config, $context);
if ($parent_result !== false) return $parent_result;
$length = strlen($string);
$last_char = $string[$length - 1];
if ($last_char !== '*') return false;
$int = substr($string, 0, $length - 1);
if ($int == '') return '*';
if (!is_numeric($int)) return false;
$int = (int) $int;
if ($int < 0) return false;
if ($int == 0) return '0';
if ($int == 1) return '*';
return ((string) $int) . '*';
}
}
// vim: et sw=4 sts=4
lib/htmlpurifier/HTMLPurifier/AttrDef/HTML/Nmtokens.php
+29 -27
View File
@@ -1,50 +1,52 @@
<?php
require_once 'HTMLPurifier/AttrDef.php';
require_once 'HTMLPurifier/Config.php';
/**
* Validates contents based on NMTOKENS attribute type.
* @note The only current use for this is the class attribute in HTML
* @note Could have some functionality factored out into Nmtoken class
* @warning We cannot assume this class will be used only for 'class'
* attributes. Not sure how to hook in magic behavior, then.
*/
class HTMLPurifier_AttrDef_HTML_Nmtokens extends HTMLPurifier_AttrDef
{
function validate($string, $config, &$context) {
public function validate($string, $config, $context) {
$string = trim($string);
// early abort: '' and '0' (strings that convert to false) are invalid
if (!$string) return false;
$tokens = $this->split($string, $config, $context);
$tokens = $this->filter($tokens, $config, $context);
if (empty($tokens)) return false;
return implode(' ', $tokens);
}
/**
* Splits a space separated list of tokens into its constituent parts.
*/
protected function split($string, $config, $context) {
// OPTIMIZABLE!
// do the preg_match, capture all subpatterns for reformulation
// we don't support U+00A1 and up codepoints or
// escaping because I don't know how to do that with regexps
// and plus it would complicate optimization efforts (you never
// see that anyway).
$matches = array();
$pattern = '/(?:(?<=\s)|\A)'. // look behind for space or string start
'((?:--|-?[A-Za-z_])[A-Za-z_\-0-9]*)'.
'(?:(?=\s)|\z)/'; // look ahead for space or string end
preg_match_all($pattern, $string, $matches);
if (empty($matches[1])) return false;
// reconstruct string
$new_string = '';
foreach ($matches[1] as $token) {
$new_string .= $token . ' ';
}
$new_string = rtrim($new_string);
return $new_string;
return $matches[1];
}
/**
* Template method for removing certain tokens based on arbitrary criteria.
* @note If we wanted to be really functional, we'd do an array_filter
* with a callback. But... we're not.
*/
protected function filter($tokens, $config, $context) {
return $tokens;
}
}
// vim: et sw=4 sts=4
lib/htmlpurifier/HTMLPurifier/AttrDef/HTML/Pixels.php
+16 -17
View File
@@ -1,21 +1,19 @@
<?php
require_once 'HTMLPurifier/AttrDef.php';
/**
* Validates an integer representation of pixels according to the HTML spec.
*/
class HTMLPurifier_AttrDef_HTML_Pixels extends HTMLPurifier_AttrDef
{
var $max;
function HTMLPurifier_AttrDef_HTML_Pixels($max = null) {
protected $max;
public function __construct($max = null) {
$this->max = $max;
}
function validate($string, $config, &$context) {
public function validate($string, $config, $context) {
$string = trim($string);
if ($string === '0') return $string;
if ($string === '') return false;
@@ -25,25 +23,26 @@ class HTMLPurifier_AttrDef_HTML_Pixels extends HTMLPurifier_AttrDef
}
if (!is_numeric($string)) return false;
$int = (int) $string;
if ($int < 0) return '0';
// upper-bound value, extremely high values can
// crash operating systems, see <http://ha.ckers.org/imagecrash.html>
// WARNING, above link WILL crash you if you're using Windows
if ($this->max !== null && $int > $this->max) return (string) $this->max;
return (string) $int;
}
function make($string) {
public function make($string) {
if ($string === '') $max = null;
else $max = (int) $string;
$class = get_class($this);
return new $class($max);
}
}
// vim: et sw=4 sts=4