keith/friendica
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity

Update HTMLPurifier to v4.7.0

Browse source
This commit is contained in:
Fabrixxm 2016-02-09 11:06:17 +01:00
parent 3c97a6703c
commit c28109ca94
465 changed files with 22433 additions and 10865 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

21
library/HTMLPurifier/AttrDef/CSS/AlphaValue.php
View file

@ -1,21 +0,0 @@
<?php
class HTMLPurifier_AttrDef_CSS_AlphaValue extends HTMLPurifier_AttrDef_CSS_Number
{
public function __construct() {
parent::__construct(false); // opacity is non-negative, but we will clamp it
}
public function validate($number, $config, $context) {
$result = parent::validate($number, $config, $context);
if ($result === false) return $result;
$float = (float) $result;
if ($float < 0.0) $result = '0';
if ($float > 1.0) $result = '1';
return $result;
}
}
// vim: et sw=4 sts=4

28
library/HTMLPurifier/AttrDef/CSS/DenyElementDecorator.php
View file

@ -1,28 +0,0 @@
<?php
/**
* Decorator which enables CSS properties to be disabled for specific elements.
*/
class HTMLPurifier_AttrDef_CSS_DenyElementDecorator extends HTMLPurifier_AttrDef
{
public $def, $element;
/**
* @param $def Definition to wrap
* @param $element Element to deny
*/
public function __construct($def, $element) {
$this->def = $def;
$this->element = $element;
}
/**
* Checks if CurrentToken is set and equal to $this->element
*/
public function validate($string, $config, $context) {
$token = $context->get('CurrentToken', true);
if ($token && $token->name == $this->element) return false;
return $this->def->validate($string, $config, $context);
}
}
// vim: et sw=4 sts=4

72
library/HTMLPurifier/AttrDef/CSS/FontFamily.php
View file

@ -1,72 +0,0 @@
<?php
/**
* Validates a font family list according to CSS spec
* @todo whitelisting allowed fonts would be nice
*/
class HTMLPurifier_AttrDef_CSS_FontFamily extends HTMLPurifier_AttrDef
{
public function validate($string, $config, $context) {
static $generic_names = array(
'serif' => true,
'sans-serif' => true,
'monospace' => true,
'fantasy' => true,
'cursive' => true
);
// assume that no font names contain commas in them
$fonts = explode(',', $string);
$final = '';
foreach($fonts as $font) {
$font = trim($font);
if ($font === '') continue;
// match a generic name
if (isset($generic_names[$font])) {
$final .= $font . ', ';
continue;
}
// match a quoted name
if ($font[0] === '"' || $font[0] === "'") {
$length = strlen($font);
if ($length <= 2) continue;
$quote = $font[0];
if ($font[$length - 1] !== $quote) continue;
$font = substr($font, 1, $length - 2);
}
$font = $this->expandCSSEscape($font);
// $font is a pure representation of the font name
if (ctype_alnum($font) && $font !== '') {
// very simple font, allow it in unharmed
$final .= $font . ', ';
continue;
}
// bugger out on whitespace. form feed (0C) really
// shouldn't show up regardless
$font = str_replace(array("\n", "\t", "\r", "\x0C"), ' ', $font);
// These ugly transforms don't pose a security
// risk (as \\ and \" might). We could try to be clever and
// use single-quote wrapping when there is a double quote
// present, but I have choosen not to implement that.
// (warning: this code relies on the selection of quotation
// mark below)
$font = str_replace('\\', '\\5C ', $font);
$font = str_replace('"', '\\22 ', $font);
// complicated font, requires quoting
$final .= "\"$font\", "; // note that this will later get turned into &quot;
}
$final = rtrim($final, ', ');
if ($final === '') return false;
return $final;
}
}
// vim: et sw=4 sts=4

47
library/HTMLPurifier/AttrDef/CSS/Length.php
View file

@ -1,47 +0,0 @@
<?php
/**
* Represents a Length as defined by CSS.
*/
class HTMLPurifier_AttrDef_CSS_Length extends HTMLPurifier_AttrDef
{
protected $min, $max;
/**
* @param HTMLPurifier_Length $max Minimum length, or null for no bound. String is also acceptable.
* @param HTMLPurifier_Length $max Maximum length, or null for no bound. String is also acceptable.
*/
public function __construct($min = null, $max = null) {
$this->min = $min !== null ? HTMLPurifier_Length::make($min) : null;
$this->max = $max !== null ? HTMLPurifier_Length::make($max) : null;
}
public function validate($string, $config, $context) {
$string = $this->parseCDATA($string);
// Optimizations
if ($string === '') return false;
if ($string === '0') return '0';
if (strlen($string) === 1) return false;
$length = HTMLPurifier_Length::make($string);
if (!$length->isValid()) return false;
if ($this->min) {
$c = $length->compareTo($this->min);
if ($c === false) return false;
if ($c < 0) return false;
}
if ($this->max) {
$c = $length->compareTo($this->max);
if ($c === false) return false;
if ($c > 0) return false;
}
return $length->toString();
}
}
// vim: et sw=4 sts=4

78
library/HTMLPurifier/AttrDef/CSS/ListStyle.php
View file

@ -1,78 +0,0 @@
<?php
/**
* Validates shorthand CSS property list-style.
* @warning Does not support url tokens that have internal spaces.
*/
class HTMLPurifier_AttrDef_CSS_ListStyle extends HTMLPurifier_AttrDef
{
/**
* Local copy of component validators.
* @note See HTMLPurifier_AttrDef_CSS_Font::$info for a similar impl.
*/
protected $info;
public function __construct($config) {
$def = $config->getCSSDefinition();
$this->info['list-style-type'] = $def->info['list-style-type'];
$this->info['list-style-position'] = $def->info['list-style-position'];
$this->info['list-style-image'] = $def->info['list-style-image'];
}
public function validate($string, $config, $context) {
// regular pre-processing
$string = $this->parseCDATA($string);
if ($string === '') return false;
// assumes URI doesn't have spaces in it
$bits = explode(' ', strtolower($string)); // bits to process
$caught = array();
$caught['type'] = false;
$caught['position'] = false;
$caught['image'] = false;
$i = 0; // number of catches
$none = false;
foreach ($bits as $bit) {
if ($i >= 3) return; // optimization bit
if ($bit === '') continue;
foreach ($caught as $key => $status) {
if ($status !== false) continue;
$r = $this->info['list-style-' . $key]->validate($bit, $config, $context);
if ($r === false) continue;
if ($r === 'none') {
if ($none) continue;
else $none = true;
if ($key == 'image') continue;
}
$caught[$key] = $r;
$i++;
break;
}
}
if (!$i) return false;
$ret = array();
// construct type
if ($caught['type']) $ret[] = $caught['type'];
// construct image
if ($caught['image']) $ret[] = $caught['image'];
// construct position
if ($caught['position']) $ret[] = $caught['position'];
if (empty($ret)) return false;
return implode(' ', $ret);
}
}
// vim: et sw=4 sts=4

40
library/HTMLPurifier/AttrDef/CSS/Percentage.php
View file

@ -1,40 +0,0 @@
<?php
/**
* Validates a Percentage as defined by the CSS spec.
*/
class HTMLPurifier_AttrDef_CSS_Percentage extends HTMLPurifier_AttrDef
{
/**
* Instance of HTMLPurifier_AttrDef_CSS_Number to defer number validation
*/
protected $number_def;
/**
* @param Bool indicating whether to forbid negative values
*/
public function __construct($non_negative = false) {
$this->number_def = new HTMLPurifier_AttrDef_CSS_Number($non_negative);
}
public function validate($string, $config, $context) {
$string = $this->parseCDATA($string);
if ($string === '') return false;
$length = strlen($string);
if ($length === 1) return false;
if ($string[$length - 1] !== '%') return false;
$number = substr($string, 0, $length - 1);
$number = $this->number_def->validate($number, $config, $context);
if ($number === false) return false;
return "$number%";
}
}
// vim: et sw=4 sts=4

28
library/HTMLPurifier/AttrDef/HTML/Bool.php
View file

@ -1,28 +0,0 @@
<?php
/**
* Validates a boolean attribute
*/
class HTMLPurifier_AttrDef_HTML_Bool extends HTMLPurifier_AttrDef
{
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 $string Name of attribute
*/
public function make($string) {
return new HTMLPurifier_AttrDef_HTML_Bool($string);
}
}
// vim: et sw=4 sts=4

32
library/HTMLPurifier/AttrDef/HTML/Color.php
View file

@ -1,32 +0,0 @@
<?php
/**
* Validates a color according to the HTML spec.
*/
class HTMLPurifier_AttrDef_HTML_Color extends HTMLPurifier_AttrDef
{
public function validate($string, $config, $context) {
static $colors = null;
if ($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

21
library/HTMLPurifier/AttrDef/HTML/FrameTarget.php
View file

@ -1,21 +0,0 @@
<?php
/**
* Special-case enum attribute definition that lazy loads allowed frame targets
*/
class HTMLPurifier_AttrDef_HTML_FrameTarget extends HTMLPurifier_AttrDef_Enum
{
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

70
library/HTMLPurifier/AttrDef/HTML/ID.php
View file

@ -1,70 +0,0 @@
<?php
/**
* Validates the HTML attribute ID.
* @warning Even though this is the id processor, it
* will ignore the directive Attr:IDBlacklist, since it will only
* go according to the ID accumulator. Since the accumulator is
* automatically generated, it will have already absorbed the
* blacklist. If you're hacking around, make sure you use load()!
*/
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
public function validate($id, $config, $context) {
if (!$config->get('Attr.EnableID')) return false;
$id = trim($id); // trim it first
if ($id === '') return false;
$prefix = $config->get('Attr.IDPrefix');
if ($prefix !== '') {
$prefix .= $config->get('Attr.IDPrefixLocal');
// prevent re-appending the prefix
if (strpos($id, $prefix) !== 0) $id = $prefix . $id;
} elseif ($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)) {
$result = true;
} else {
if (!ctype_alpha(@$id[0])) return false;
$trim = trim( // primitive style of regexps, I suppose
$id,
'A..Za..z0..9:-._'
);
$result = ($trim === '');
}
$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

41
library/HTMLPurifier/AttrDef/HTML/Length.php
View file

@ -1,41 +0,0 @@
<?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
{
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

41
library/HTMLPurifier/AttrDef/HTML/MultiLength.php
View file

@ -1,41 +0,0 @@
<?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
{
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

48
library/HTMLPurifier/AttrDef/HTML/Pixels.php
View file

@ -1,48 +0,0 @@
<?php
/**
* Validates an integer representation of pixels according to the HTML spec.
*/
class HTMLPurifier_AttrDef_HTML_Pixels extends HTMLPurifier_AttrDef
{
protected $max;
public function __construct($max = null) {
$this->max = $max;
}
public function validate($string, $config, $context) {
$string = trim($string);
if ($string === '0') return $string;
if ($string === '') return false;
$length = strlen($string);
if (substr($string, $length - 2) == 'px') {
$string = substr($string, 0, $length - 2);
}
if (!is_numeric($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) $int;
}
public function make($string) {
if ($string === '') $max = null;
else $max = (int) $string;
$class = get_class($this);
return new $class($max);
}
}
// vim: et sw=4 sts=4

15
library/HTMLPurifier/AttrDef/Text.php
View file

@ -1,15 +0,0 @@
<?php
/**
* Validates arbitrary text according to the HTML spec.
*/
class HTMLPurifier_AttrDef_Text extends HTMLPurifier_AttrDef
{
public function validate($string, $config, $context) {
return $this->parseCDATA($string);
}
}
// vim: et sw=4 sts=4

62
library/HTMLPurifier/AttrDef/URI/Host.php
View file

@ -1,62 +0,0 @@
<?php
/**
* Validates a host according to the IPv4, IPv6 and DNS (future) specifications.
*/
class HTMLPurifier_AttrDef_URI_Host extends HTMLPurifier_AttrDef
{
/**
* Instance of HTMLPurifier_AttrDef_URI_IPv4 sub-validator
*/
protected $ipv4;
/**
* Instance of HTMLPurifier_AttrDef_URI_IPv6 sub-validator
*/
protected $ipv6;
public function __construct() {
$this->ipv4 = new HTMLPurifier_AttrDef_URI_IPv4();
$this->ipv6 = new HTMLPurifier_AttrDef_URI_IPv6();
}
public function validate($string, $config, $context) {
$length = strlen($string);
if ($string === '') return '';
if ($length > 1 && $string[0] === '[' && $string[$length-1] === ']') {
//IPv6
$ip = substr($string, 1, $length - 2);
$valid = $this->ipv6->validate($ip, $config, $context);
if ($valid === false) return false;
return '['. $valid . ']';
}
// need to do checks on unusual encodings too
$ipv4 = $this->ipv4->validate($string, $config, $context);
if ($ipv4 !== false) return $ipv4;
// A regular domain name.
// This breaks I18N domain names, but we don't have proper IRI support,
// so force users to insert Punycode. If there's complaining we'll
// try to fix things into an international friendly form.
// The productions describing this are:
$a = '[a-z]'; // alpha
$an = '[a-z0-9]'; // alphanum
$and = '[a-z0-9-]'; // alphanum | "-"
// domainlabel = alphanum | alphanum *( alphanum | "-" ) alphanum
$domainlabel = "$an($and*$an)?";
// toplabel = alpha | alpha *( alphanum | "-" ) alphanum
$toplabel = "$a($and*$an)?";
// hostname = *( domainlabel "." ) toplabel [ "." ]
$match = preg_match("/^($domainlabel\.)*$toplabel\.?$/i", $string);
if (!$match) return false;
return $string;
}
}
// vim: et sw=4 sts=4

99
library/HTMLPurifier/AttrDef/URI/IPv6.php
View file

@ -1,99 +0,0 @@
<?php
/**
* Validates an IPv6 address.
* @author Feyd @ forums.devnetwork.net (public domain)
* @note This function requires brackets to have been removed from address
* in URI.
*/
class HTMLPurifier_AttrDef_URI_IPv6 extends HTMLPurifier_AttrDef_URI_IPv4
{
public function validate($aIP, $config, $context) {
if (!$this->ip4) $this->_loadRegex();
$original = $aIP;
$hex = '[0-9a-fA-F]';
$blk = '(?:' . $hex . '{1,4})';
$pre = '(?:/(?:12[0-8]|1[0-1][0-9]|[1-9][0-9]|[0-9]))'; // /0 - /128
// prefix check
if (strpos($aIP, '/') !== false)
{
if (preg_match('#' . $pre . '$#s', $aIP, $find))
{
$aIP = substr($aIP, 0, 0-strlen($find[0]));
unset($find);
}
else
{
return false;
}
}
// IPv4-compatiblity check
if (preg_match('#(?<=:'.')' . $this->ip4 . '$#s', $aIP, $find))
{
$aIP = substr($aIP, 0, 0-strlen($find[0]));
$ip = explode('.', $find[0]);
$ip = array_map('dechex', $ip);
$aIP .= $ip[0] . $ip[1] . ':' . $ip[2] . $ip[3];
unset($find, $ip);
}
// compression check
$aIP = explode('::', $aIP);
$c = count($aIP);
if ($c > 2)
{
return false;
}
elseif ($c == 2)
{
list($first, $second) = $aIP;
$first = explode(':', $first);
$second = explode(':', $second);
if (count($first) + count($second) > 8)
{
return false;
}
while(count($first) < 8)
{
array_push($first, '0');
}
array_splice($first, 8 - count($second), 8, $second);
$aIP = $first;
unset($first,$second);
}
else
{
$aIP = explode(':', $aIP[0]);
}
$c = count($aIP);
if ($c != 8)
{
return false;
}
// All the pieces should be 16-bit hex strings. Are they?
foreach ($aIP as $piece)
{
if (!preg_match('#^[0-9a-fA-F]{4}$#s', sprintf('%04s', $piece)))
{
return false;
}
}
return $original;
}
}
// vim: et sw=4 sts=4

36
library/HTMLPurifier/AttrTransform/BoolToCSS.php
View file

@ -1,36 +0,0 @@
<?php
/**
* Pre-transform that changes converts a boolean attribute to fixed CSS
*/
class HTMLPurifier_AttrTransform_BoolToCSS extends HTMLPurifier_AttrTransform {
/**
* Name of boolean attribute that is trigger
*/
protected $attr;
/**
* CSS declarations to add to style, needs trailing semicolon
*/
protected $css;
/**
* @param $attr string attribute name to convert from
* @param $css string CSS declarations to add to style (needs semicolon)
*/
public function __construct($attr, $css) {
$this->attr = $attr;
$this->css = $css;
}
public function transform($attr, $config, $context) {
if (!isset($attr[$this->attr])) return $attr;
unset($attr[$this->attr]);
$this->prependCSS($attr, $this->css);
return $attr;
}
}
// vim: et sw=4 sts=4

58
library/HTMLPurifier/AttrTransform/EnumToCSS.php
View file

@ -1,58 +0,0 @@
<?php
/**
* Generic pre-transform that converts an attribute with a fixed number of
* values (enumerated) to CSS.
*/
class HTMLPurifier_AttrTransform_EnumToCSS extends HTMLPurifier_AttrTransform {
/**
* Name of attribute to transform from
*/
protected $attr;
/**
* Lookup array of attribute values to CSS
*/
protected $enumToCSS = array();
/**
* Case sensitivity of the matching
* @warning Currently can only be guaranteed to work with ASCII
* values.
*/
protected $caseSensitive = false;
/**
* @param $attr String attribute name to transform from
* @param $enumToCSS Lookup array of attribute values to CSS
* @param $case_sensitive Boolean case sensitivity indicator, default false
*/
public function __construct($attr, $enum_to_css, $case_sensitive = false) {
$this->attr = $attr;
$this->enumToCSS = $enum_to_css;
$this->caseSensitive = (bool) $case_sensitive;
}
public function transform($attr, $config, $context) {
if (!isset($attr[$this->attr])) return $attr;
$value = trim($attr[$this->attr]);
unset($attr[$this->attr]);
if (!$this->caseSensitive) $value = strtolower($value);
if (!isset($this->enumToCSS[$value])) {
return $attr;
}
$this->prependCSS($attr, $this->enumToCSS[$value]);
return $attr;
}
}
// vim: et sw=4 sts=4

27
library/HTMLPurifier/AttrTransform/Length.php
View file

@ -1,27 +0,0 @@
<?php
/**
* Class for handling width/height length attribute transformations to CSS
*/
class HTMLPurifier_AttrTransform_Length extends HTMLPurifier_AttrTransform
{
protected $name;
protected $cssName;
public function __construct($name, $css_name = null) {
$this->name = $name;
$this->cssName = $css_name ? $css_name : $name;
}
public function transform($attr, $config, $context) {
if (!isset($attr[$this->name])) return $attr;
$length = $this->confiscateAttr($attr, $this->name);
if(ctype_digit($length)) $length .= 'px';
$this->prependCSS($attr, $this->cssName . ":$length;");
return $attr;
}
}
// vim: et sw=4 sts=4

21
library/HTMLPurifier/AttrTransform/Name.php
View file

@ -1,21 +0,0 @@
<?php
/**
* Pre-transform that changes deprecated name attribute to ID if necessary
*/
class HTMLPurifier_AttrTransform_Name extends HTMLPurifier_AttrTransform
{
public function transform($attr, $config, $context) {
// Abort early if we're using relaxed definition of name
if ($config->get('HTML.Attr.Name.UseCDATA')) return $attr;
if (!isset($attr['name'])) return $attr;
$id = $this->confiscateAttr($attr, 'name');
if ( isset($attr['id'])) return $attr;
$attr['id'] = $id;
return $attr;
}
}
// vim: et sw=4 sts=4

27
library/HTMLPurifier/AttrTransform/NameSync.php
View file

@ -1,27 +0,0 @@
<?php
/**
* Post-transform that performs validation to the name attribute; if
* it is present with an equivalent id attribute, it is passed through;
* otherwise validation is performed.
*/
class HTMLPurifier_AttrTransform_NameSync extends HTMLPurifier_AttrTransform
{
public function __construct() {
$this->idDef = new HTMLPurifier_AttrDef_HTML_ID();
}
public function transform($attr, $config, $context) {
if (!isset($attr['name'])) return $attr;
$name = $attr['name'];
if (isset($attr['id']) && $attr['id'] === $name) return $attr;
$result = $this->idDef->validate($name, $config, $context);
if ($result === false) unset($attr['name']);
else $attr['name'] = $result;
return $attr;
}
}
// vim: et sw=4 sts=4

16
library/HTMLPurifier/AttrTransform/SafeObject.php
View file

@ -1,16 +0,0 @@
<?php
/**
* Writes default type for all objects. Currently only supports flash.
*/
class HTMLPurifier_AttrTransform_SafeObject extends HTMLPurifier_AttrTransform
{
public $name = "SafeObject";
function transform($attr, $config, $context) {
if (!isset($attr['type'])) $attr['type'] = 'application/x-shockwave-flash';
return $attr;
}
}
// vim: et sw=4 sts=4

18
library/HTMLPurifier/AttrTransform/Textarea.php
View file

@ -1,18 +0,0 @@
<?php
/**
* Sets height/width defaults for <textarea>
*/
class HTMLPurifier_AttrTransform_Textarea extends HTMLPurifier_AttrTransform
{
public function transform($attr, $config, $context) {
// Calculated from Firefox
if (!isset($attr['cols'])) $attr['cols'] = '22';
if (!isset($attr['rows'])) $attr['rows'] = '3';
return $attr;
}
}
// vim: et sw=4 sts=4

98
library/HTMLPurifier/Bootstrap.php
View file

@ -1,98 +0,0 @@
<?php
// constants are slow, so we use as few as possible
if (!defined('HTMLPURIFIER_PREFIX')) {
define('HTMLPURIFIER_PREFIX', realpath(dirname(__FILE__) . '/..'));
}
// accomodations for versions earlier than 5.0.2
// borrowed from PHP_Compat, LGPL licensed, by Aidan Lister <aidan@php.net>
if (!defined('PHP_EOL')) {
switch (strtoupper(substr(PHP_OS, 0, 3))) {
case 'WIN':
define('PHP_EOL', "\r\n");
break;
case 'DAR':
define('PHP_EOL', "\r");
break;
default:
define('PHP_EOL', "\n");
}
}
/**
* Bootstrap class that contains meta-functionality for HTML Purifier such as
* the autoload function.
*
* @note
* This class may be used without any other files from HTML Purifier.
*/
class HTMLPurifier_Bootstrap
{
/**
* Autoload function for HTML Purifier
* @param $class Class to load
*/
public static function autoload($class) {
$file = HTMLPurifier_Bootstrap::getPath($class);
if (!$file) return false;
require HTMLPURIFIER_PREFIX . '/' . $file;
return true;
}
/**
* Returns the path for a specific class.
*/
public static function getPath($class) {
if (strncmp('HTMLPurifier', $class, 12) !== 0) return false;
// Custom implementations
if (strncmp('HTMLPurifier_Language_', $class, 22) === 0) {
$code = str_replace('_', '-', substr($class, 22));
$file = 'HTMLPurifier/Language/classes/' . $code . '.php';
} else {
$file = str_replace('_', '/', $class) . '.php';
}
if (!file_exists(HTMLPURIFIER_PREFIX . '/' . $file)) return false;
return $file;
}
/**
* "Pre-registers" our autoloader on the SPL stack.
*/
public static function registerAutoload() {
$autoload = array('HTMLPurifier_Bootstrap', 'autoload');
if ( ($funcs = spl_autoload_functions()) === false ) {
spl_autoload_register($autoload);
} elseif (function_exists('spl_autoload_unregister')) {
$compat = version_compare(PHP_VERSION, '5.1.2', '<=') &&
version_compare(PHP_VERSION, '5.1.0', '>=');
foreach ($funcs as $func) {
if (is_array($func)) {
// :TRICKY: There are some compatibility issues and some
// places where we need to error out
$reflector = new ReflectionMethod($func[0], $func[1]);
if (!$reflector->isStatic()) {
throw new Exception('
HTML Purifier autoloader registrar is not compatible
with non-static object methods due to PHP Bug #44144;
Please do not use HTMLPurifier.autoload.php (or any
file that includes this file); instead, place the code:
spl_autoload_register(array(\'HTMLPurifier_Bootstrap\', \'autoload\'))
after your own autoloaders.
');
}
// Suprisingly, spl_autoload_register supports the
// Class::staticMethod callback format, although call_user_func doesn't
if ($compat) $func = implode('::', $func);
}
spl_autoload_unregister($func);
}
spl_autoload_register($autoload);
foreach ($funcs as $func) spl_autoload_register($func);
}
}
}
// vim: et sw=4 sts=4

292
library/HTMLPurifier/CSSDefinition.php
View file

@ -1,292 +0,0 @@
<?php
/**
* Defines allowed CSS attributes and what their values are.
* @see HTMLPurifier_HTMLDefinition
*/
class HTMLPurifier_CSSDefinition extends HTMLPurifier_Definition
{
public $type = 'CSS';
/**
* Assoc array of attribute name to definition object.
*/
public $info = array();
/**
* Constructs the info array. The meat of this class.
*/
protected function doSetup($config) {
$this->info['text-align'] = new HTMLPurifier_AttrDef_Enum(
array('left', 'right', 'center', 'justify'), false);
$border_style =
$this->info['border-bottom-style'] =
$this->info['border-right-style'] =
$this->info['border-left-style'] =
$this->info['border-top-style'] = new HTMLPurifier_AttrDef_Enum(
array('none', 'hidden', 'dotted', 'dashed', 'solid', 'double',
'groove', 'ridge', 'inset', 'outset'), false);
$this->info['border-style'] = new HTMLPurifier_AttrDef_CSS_Multiple($border_style);
$this->info['clear'] = new HTMLPurifier_AttrDef_Enum(
array('none', 'left', 'right', 'both'), false);
$this->info['float'] = new HTMLPurifier_AttrDef_Enum(
array('none', 'left', 'right'), false);
$this->info['font-style'] = new HTMLPurifier_AttrDef_Enum(
array('normal', 'italic', 'oblique'), false);
$this->info['font-variant'] = new HTMLPurifier_AttrDef_Enum(
array('normal', 'small-caps'), false);
$uri_or_none = new HTMLPurifier_AttrDef_CSS_Composite(
array(
new HTMLPurifier_AttrDef_Enum(array('none')),
new HTMLPurifier_AttrDef_CSS_URI()
)
);
$this->info['list-style-position'] = new HTMLPurifier_AttrDef_Enum(
array('inside', 'outside'), false);
$this->info['list-style-type'] = new HTMLPurifier_AttrDef_Enum(
array('disc', 'circle', 'square', 'decimal', 'lower-roman',
'upper-roman', 'lower-alpha', 'upper-alpha', 'none'), false);
$this->info['list-style-image'] = $uri_or_none;
$this->info['list-style'] = new HTMLPurifier_AttrDef_CSS_ListStyle($config);
$this->info['text-transform'] = new HTMLPurifier_AttrDef_Enum(
array('capitalize', 'uppercase', 'lowercase', 'none'), false);
$this->info['color'] = new HTMLPurifier_AttrDef_CSS_Color();
$this->info['background-image'] = $uri_or_none;
$this->info['background-repeat'] = new HTMLPurifier_AttrDef_Enum(
array('repeat', 'repeat-x', 'repeat-y', 'no-repeat')
);
$this->info['background-attachment'] = new HTMLPurifier_AttrDef_Enum(
array('scroll', 'fixed')
);
$this->info['background-position'] = new HTMLPurifier_AttrDef_CSS_BackgroundPosition();
$border_color =
$this->info['border-top-color'] =
$this->info['border-bottom-color'] =
$this->info['border-left-color'] =
$this->info['border-right-color'] =
$this->info['background-color'] = new HTMLPurifier_AttrDef_CSS_Composite(array(
new HTMLPurifier_AttrDef_Enum(array('transparent')),
new HTMLPurifier_AttrDef_CSS_Color()
));
$this->info['background'] = new HTMLPurifier_AttrDef_CSS_Background($config);
$this->info['border-color'] = new HTMLPurifier_AttrDef_CSS_Multiple($border_color);
$border_width =
$this->info['border-top-width'] =
$this->info['border-bottom-width'] =
$this->info['border-left-width'] =
$this->info['border-right-width'] = new HTMLPurifier_AttrDef_CSS_Composite(array(
new HTMLPurifier_AttrDef_Enum(array('thin', 'medium', 'thick')),
new HTMLPurifier_AttrDef_CSS_Length('0') //disallow negative
));
$this->info['border-width'] = new HTMLPurifier_AttrDef_CSS_Multiple($border_width);
$this->info['letter-spacing'] = new HTMLPurifier_AttrDef_CSS_Composite(array(
new HTMLPurifier_AttrDef_Enum(array('normal')),
new HTMLPurifier_AttrDef_CSS_Length()
));
$this->info['word-spacing'] = new HTMLPurifier_AttrDef_CSS_Composite(array(
new HTMLPurifier_AttrDef_Enum(array('normal')),
new HTMLPurifier_AttrDef_CSS_Length()
));
$this->info['font-size'] = new HTMLPurifier_AttrDef_CSS_Composite(array(
new HTMLPurifier_AttrDef_Enum(array('xx-small', 'x-small',
'small', 'medium', 'large', 'x-large', 'xx-large',
'larger', 'smaller')),
new HTMLPurifier_AttrDef_CSS_Percentage(),
new HTMLPurifier_AttrDef_CSS_Length()
));
$this->info['line-height'] = new HTMLPurifier_AttrDef_CSS_Composite(array(
new HTMLPurifier_AttrDef_Enum(array('normal')),
new HTMLPurifier_AttrDef_CSS_Number(true), // no negatives
new HTMLPurifier_AttrDef_CSS_Length('0'),
new HTMLPurifier_AttrDef_CSS_Percentage(true)
));
$margin =
$this->info['margin-top'] =
$this->info['margin-bottom'] =
$this->info['margin-left'] =
$this->info['margin-right'] = new HTMLPurifier_AttrDef_CSS_Composite(array(
new HTMLPurifier_AttrDef_CSS_Length(),
new HTMLPurifier_AttrDef_CSS_Percentage(),
new HTMLPurifier_AttrDef_Enum(array('auto'))
));
$this->info['margin'] = new HTMLPurifier_AttrDef_CSS_Multiple($margin);
// non-negative
$padding =
$this->info['padding-top'] =
$this->info['padding-bottom'] =
$this->info['padding-left'] =
$this->info['padding-right'] = new HTMLPurifier_AttrDef_CSS_Composite(array(
new HTMLPurifier_AttrDef_CSS_Length('0'),
new HTMLPurifier_AttrDef_CSS_Percentage(true)
));
$this->info['padding'] = new HTMLPurifier_AttrDef_CSS_Multiple($padding);
$this->info['text-indent'] = new HTMLPurifier_AttrDef_CSS_Composite(array(
new HTMLPurifier_AttrDef_CSS_Length(),
new HTMLPurifier_AttrDef_CSS_Percentage()
));
$trusted_wh = new HTMLPurifier_AttrDef_CSS_Composite(array(
new HTMLPurifier_AttrDef_CSS_Length('0'),
new HTMLPurifier_AttrDef_CSS_Percentage(true),
new HTMLPurifier_AttrDef_Enum(array('auto'))
));
$max = $config->get('CSS.MaxImgLength');
$this->info['width'] =
$this->info['height'] =
$max === null ?
$trusted_wh :
new HTMLPurifier_AttrDef_Switch('img',
// For img tags:
new HTMLPurifier_AttrDef_CSS_Composite(array(
new HTMLPurifier_AttrDef_CSS_Length('0', $max),
new HTMLPurifier_AttrDef_Enum(array('auto'))
)),
// For everyone else:
$trusted_wh
);
$this->info['text-decoration'] = new HTMLPurifier_AttrDef_CSS_TextDecoration();
$this->info['font-family'] = new HTMLPurifier_AttrDef_CSS_FontFamily();
// this could use specialized code
$this->info['font-weight'] = new HTMLPurifier_AttrDef_Enum(
array('normal', 'bold', 'bolder', 'lighter', '100', '200', '300',
'400', '500', '600', '700', '800', '900'), false);
// MUST be called after other font properties, as it references
// a CSSDefinition object
$this->info['font'] = new HTMLPurifier_AttrDef_CSS_Font($config);
// same here
$this->info['border'] =
$this->info['border-bottom'] =
$this->info['border-top'] =
$this->info['border-left'] =
$this->info['border-right'] = new HTMLPurifier_AttrDef_CSS_Border($config);
$this->info['border-collapse'] = new HTMLPurifier_AttrDef_Enum(array(
'collapse', 'separate'));
$this->info['caption-side'] = new HTMLPurifier_AttrDef_Enum(array(
'top', 'bottom'));
$this->info['table-layout'] = new HTMLPurifier_AttrDef_Enum(array(
'auto', 'fixed'));
$this->info['vertical-align'] = new HTMLPurifier_AttrDef_CSS_Composite(array(
new HTMLPurifier_AttrDef_Enum(array('baseline', 'sub', 'super',
'top', 'text-top', 'middle', 'bottom', 'text-bottom')),
new HTMLPurifier_AttrDef_CSS_Length(),
new HTMLPurifier_AttrDef_CSS_Percentage()
));
$this->info['border-spacing'] = new HTMLPurifier_AttrDef_CSS_Multiple(new HTMLPurifier_AttrDef_CSS_Length(), 2);
// partial support
$this->info['white-space'] = new HTMLPurifier_AttrDef_Enum(array('nowrap'));
if ($config->get('CSS.Proprietary')) {
$this->doSetupProprietary($config);
}
if ($config->get('CSS.AllowTricky')) {
$this->doSetupTricky($config);
}
$allow_important = $config->get('CSS.AllowImportant');
// wrap all attr-defs with decorator that handles !important
foreach ($this->info as $k => $v) {
$this->info[$k] = new HTMLPurifier_AttrDef_CSS_ImportantDecorator($v, $allow_important);
}
$this->setupConfigStuff($config);
}
protected function doSetupProprietary($config) {
// Internet Explorer only scrollbar colors
$this->info['scrollbar-arrow-color'] = new HTMLPurifier_AttrDef_CSS_Color();
$this->info['scrollbar-base-color'] = new HTMLPurifier_AttrDef_CSS_Color();
$this->info['scrollbar-darkshadow-color'] = new HTMLPurifier_AttrDef_CSS_Color();
$this->info['scrollbar-face-color'] = new HTMLPurifier_AttrDef_CSS_Color();
$this->info['scrollbar-highlight-color'] = new HTMLPurifier_AttrDef_CSS_Color();
$this->info['scrollbar-shadow-color'] = new HTMLPurifier_AttrDef_CSS_Color();
// technically not proprietary, but CSS3, and no one supports it
$this->info['opacity'] = new HTMLPurifier_AttrDef_CSS_AlphaValue();
$this->info['-moz-opacity'] = new HTMLPurifier_AttrDef_CSS_AlphaValue();
$this->info['-khtml-opacity'] = new HTMLPurifier_AttrDef_CSS_AlphaValue();
// only opacity, for now
$this->info['filter'] = new HTMLPurifier_AttrDef_CSS_Filter();
}
protected function doSetupTricky($config) {
$this->info['display'] = new HTMLPurifier_AttrDef_Enum(array(
'inline', 'block', 'list-item', 'run-in', 'compact',
'marker', 'table', 'inline-table', 'table-row-group',
'table-header-group', 'table-footer-group', 'table-row',
'table-column-group', 'table-column', 'table-cell', 'table-caption', 'none'
));
$this->info['visibility'] = new HTMLPurifier_AttrDef_Enum(array(
'visible', 'hidden', 'collapse'
));
$this->info['overflow'] = new HTMLPurifier_AttrDef_Enum(array('visible', 'hidden', 'auto', 'scroll'));
}
/**
* Performs extra config-based processing. Based off of
* HTMLPurifier_HTMLDefinition.
* @todo Refactor duplicate elements into common class (probably using
* composition, not inheritance).
*/
protected function setupConfigStuff($config) {
// setup allowed elements
$support = "(for information on implementing this, see the ".
"support forums) ";
$allowed_attributes = $config->get('CSS.AllowedProperties');
if ($allowed_attributes !== null) {
foreach ($this->info as $name => $d) {
if(!isset($allowed_attributes[$name])) unset($this->info[$name]);
unset($allowed_attributes[$name]);
}
// emit errors
foreach ($allowed_attributes as $name => $d) {
// :TODO: Is this htmlspecialchars() call really necessary?
$name = htmlspecialchars($name);
trigger_error("Style attribute '$name' is not supported $support", E_USER_WARNING);
}
}
}
}
// vim: et sw=4 sts=4

26
library/HTMLPurifier/ChildDef/Optional.php
View file

@ -1,26 +0,0 @@
<?php
/**
* Definition that allows a set of elements, and allows no children.
* @note This is a hack to reuse code from HTMLPurifier_ChildDef_Required,
* really, one shouldn't inherit from the other. Only altered behavior
* is to overload a returned false with an array. Thus, it will never
* return false.
*/
class HTMLPurifier_ChildDef_Optional extends HTMLPurifier_ChildDef_Required
{
public $allow_empty = true;
public $type = 'optional';
public function validateChildren($tokens_of_children, $config, $context) {
$result = parent::validateChildren($tokens_of_children, $config, $context);
// we assume that $tokens_of_children is not modified
if ($result === false) {
if (empty($tokens_of_children)) return true;
elseif ($this->whitespace) return $tokens_of_children;
else return array();
}
return $result;
}
}
// vim: et sw=4 sts=4

117
library/HTMLPurifier/ChildDef/Required.php
View file

@ -1,117 +0,0 @@
<?php
/**
* Definition that allows a set of elements, but disallows empty children.
*/
class HTMLPurifier_ChildDef_Required extends HTMLPurifier_ChildDef
{
/**
* Lookup table of allowed elements.
* @public
*/
public $elements = array();
/**
* Whether or not the last passed node was all whitespace.
*/
protected $whitespace = false;
/**
* @param $elements List of allowed element names (lowercase).
*/
public function __construct($elements) {
if (is_string($elements)) {
$elements = str_replace(' ', '', $elements);
$elements = explode('|', $elements);
}
$keys = array_keys($elements);
if ($keys == array_keys($keys)) {
$elements = array_flip($elements);
foreach ($elements as $i => $x) {
$elements[$i] = true;
if (empty($i)) unset($elements[$i]); // remove blank
}
}
$this->elements = $elements;
}
public $allow_empty = false;
public $type = 'required';
public function validateChildren($tokens_of_children, $config, $context) {
// Flag for subclasses
$this->whitespace = false;
// if there are no tokens, delete parent node
if (empty($tokens_of_children)) return false;
// the new set of children
$result = array();
// current depth into the nest
$nesting = 0;
// whether or not we're deleting a node
$is_deleting = false;
// whether or not parsed character data is allowed
// this controls whether or not we silently drop a tag
// or generate escaped HTML from it
$pcdata_allowed = isset($this->elements['#PCDATA']);
// a little sanity check to make sure it's not ALL whitespace
$all_whitespace = true;
// some configuration
$escape_invalid_children = $config->get('Core.EscapeInvalidChildren');
// generator
$gen = new HTMLPurifier_Generator($config, $context);
foreach ($tokens_of_children as $token) {
if (!empty($token->is_whitespace)) {
$result[] = $token;
continue;
}
$all_whitespace = false; // phew, we're not talking about whitespace
$is_child = ($nesting == 0);
if ($token instanceof HTMLPurifier_Token_Start) {
$nesting++;
} elseif ($token instanceof HTMLPurifier_Token_End) {
$nesting--;
}
if ($is_child) {
$is_deleting = false;
if (!isset($this->elements[$token->name])) {
$is_deleting = true;
if ($pcdata_allowed && $token instanceof HTMLPurifier_Token_Text) {
$result[] = $token;
} elseif ($pcdata_allowed && $escape_invalid_children) {
$result[] = new HTMLPurifier_Token_Text(
$gen->generateFromToken($token)
);
}
continue;
}
}
if (!$is_deleting || ($pcdata_allowed && $token instanceof HTMLPurifier_Token_Text)) {
$result[] = $token;
} elseif ($pcdata_allowed && $escape_invalid_children) {
$result[] =
new HTMLPurifier_Token_Text(
$gen->generateFromToken($token)
);
} else {
// drop silently
}
}
if (empty($result)) return false;
if ($all_whitespace) {
$this->whitespace = true;
return false;
}
if ($tokens_of_children == $result) return true;
return $result;
}
}
// vim: et sw=4 sts=4

88
library/HTMLPurifier/ChildDef/StrictBlockquote.php
View file

@ -1,88 +0,0 @@
<?php
/**
* Takes the contents of blockquote when in strict and reformats for validation.
*/
class HTMLPurifier_ChildDef_StrictBlockquote extends HTMLPurifier_ChildDef_Required
{
protected $real_elements;
protected $fake_elements;
public $allow_empty = true;
public $type = 'strictblockquote';
protected $init = false;
/**
* @note We don't want MakeWellFormed to auto-close inline elements since
* they might be allowed.
*/
public function getAllowedElements($config) {
$this->init($config);
return $this->fake_elements;
}
public function validateChildren($tokens_of_children, $config, $context) {
$this->init($config);
// trick the parent class into thinking it allows more
$this->elements = $this->fake_elements;
$result = parent::validateChildren($tokens_of_children, $config, $context);
$this->elements = $this->real_elements;
if ($result === false) return array();
if ($result === true) $result = $tokens_of_children;
$def = $config->getHTMLDefinition();
$block_wrap_start = new HTMLPurifier_Token_Start($def->info_block_wrapper);
$block_wrap_end = new HTMLPurifier_Token_End( $def->info_block_wrapper);
$is_inline = false;
$depth = 0;
$ret = array();
// assuming that there are no comment tokens
foreach ($result as $i => $token) {
$token = $result[$i];
// ifs are nested for readability
if (!$is_inline) {
if (!$depth) {
if (
($token instanceof HTMLPurifier_Token_Text && !$token->is_whitespace) ||
(!$token instanceof HTMLPurifier_Token_Text && !isset($this->elements[$token->name]))
) {
$is_inline = true;
$ret[] = $block_wrap_start;
}
}
} else {
if (!$depth) {
// starting tokens have been inline text / empty
if ($token instanceof HTMLPurifier_Token_Start || $token instanceof HTMLPurifier_Token_Empty) {
if (isset($this->elements[$token->name])) {
// ended
$ret[] = $block_wrap_end;
$is_inline = false;
}
}
}
}
$ret[] = $token;
if ($token instanceof HTMLPurifier_Token_Start) $depth++;
if ($token instanceof HTMLPurifier_Token_End) $depth--;
}
if ($is_inline) $ret[] = $block_wrap_end;
return $ret;
}
private function init($config) {
if (!$this->init) {
$def = $config->getHTMLDefinition();
// allow all inline elements
$this->real_elements = $this->elements;
$this->fake_elements = $def->info_content_sets['Flow'];
$this->fake_elements['#PCDATA'] = true;
$this->init = true;
}
}
}
// vim: et sw=4 sts=4

142
library/HTMLPurifier/ChildDef/Table.php
View file

@ -1,142 +0,0 @@
<?php
/**
* Definition for tables
*/
class HTMLPurifier_ChildDef_Table extends HTMLPurifier_ChildDef
{
public $allow_empty = false;
public $type = 'table';
public $elements = array('tr' => true, 'tbody' => true, 'thead' => true,
'tfoot' => true, 'caption' => true, 'colgroup' => true, 'col' => true);
public function __construct() {}
public function validateChildren($tokens_of_children, $config, $context) {
if (empty($tokens_of_children)) return false;
// this ensures that the loop gets run one last time before closing
// up. It's a little bit of a hack, but it works! Just make sure you
// get rid of the token later.
$tokens_of_children[] = false;
// only one of these elements is allowed in a table
$caption = false;
$thead = false;
$tfoot = false;
// as many of these as you want
$cols = array();
$content = array();
$nesting = 0; // current depth so we can determine nodes
$is_collecting = false; // are we globbing together tokens to package
// into one of the collectors?
$collection = array(); // collected nodes
$tag_index = 0; // the first node might be whitespace,
// so this tells us where the start tag is
foreach ($tokens_of_children as $token) {
$is_child = ($nesting == 0);
if ($token === false) {
// terminating sequence started
} elseif ($token instanceof HTMLPurifier_Token_Start) {
$nesting++;
} elseif ($token instanceof HTMLPurifier_Token_End) {
$nesting--;
}
// handle node collection
if ($is_collecting) {
if ($is_child) {
// okay, let's stash the tokens away
// first token tells us the type of the collection
switch ($collection[$tag_index]->name) {
case 'tr':
case 'tbody':
$content[] = $collection;
break;
case 'caption':
if ($caption !== false) break;
$caption = $collection;
break;
case 'thead':
case 'tfoot':
// access the appropriate variable, $thead or $tfoot
$var = $collection[$tag_index]->name;
if ($$var === false) {
$$var = $collection;
} else {
// transmutate the first and less entries into
// tbody tags, and then put into content
$collection[$tag_index]->name = 'tbody';
$collection[count($collection)-1]->name = 'tbody';
$content[] = $collection;
}
break;
case 'colgroup':
$cols[] = $collection;
break;
}
$collection = array();
$is_collecting = false;
$tag_index = 0;
} else {
// add the node to the collection
$collection[] = $token;
}
}
// terminate
if ($token === false) break;
if ($is_child) {
// determine what we're dealing with
if ($token->name == 'col') {
// the only empty tag in the possie, we can handle it
// immediately
$cols[] = array_merge($collection, array($token));
$collection = array();
$tag_index = 0;
continue;
}
switch($token->name) {
case 'caption':
case 'colgroup':
case 'thead':
case 'tfoot':
case 'tbody':
case 'tr':
$is_collecting = true;
$collection[] = $token;
continue;
default:
if (!empty($token->is_whitespace)) {
$collection[] = $token;
$tag_index++;
}
continue;
}
}
}
if (empty($content)) return false;
$ret = array();
if ($caption !== false) $ret = array_merge($ret, $caption);
if ($cols !== false) foreach ($cols as $token_array) $ret = array_merge($ret, $token_array);
if ($thead !== false) $ret = array_merge($ret, $thead);
if ($tfoot !== false) $ret = array_merge($ret, $tfoot);
foreach ($content as $token_array) $ret = array_merge($ret, $token_array);
if (!empty($collection) && $is_collecting == false){
// grab the trailing space
$ret = array_merge($ret, $collection);
}
array_pop($tokens_of_children); // remove phantom token
return ($ret === $tokens_of_children) ? true : $ret;
}
}
// vim: et sw=4 sts=4

580
library/HTMLPurifier/Config.php
View file

@ -1,580 +0,0 @@
<?php
/**
* Configuration object that triggers customizable behavior.
*
* @warning This class is strongly defined: that means that the class
* will fail if an undefined directive is retrieved or set.
*
* @note Many classes that could (although many times don't) use the
* configuration object make it a mandatory parameter. This is
* because a configuration object should always be forwarded,
* otherwise, you run the risk of missing a parameter and then
* being stumped when a configuration directive doesn't work.
*
* @todo Reconsider some of the public member variables
*/
class HTMLPurifier_Config
{
/**
* HTML Purifier's version
*/
public $version = '4.1.1';
/**
* Bool indicator whether or not to automatically finalize
* the object if a read operation is done
*/
public $autoFinalize = true;
// protected member variables
/**
* Namespace indexed array of serials for specific namespaces (see
* getSerial() for more info).
*/
protected $serials = array();
/**
* Serial for entire configuration object
*/
protected $serial;
/**
* Parser for variables
*/
protected $parser;
/**
* Reference HTMLPurifier_ConfigSchema for value checking
* @note This is public for introspective purposes. Please don't
* abuse!
*/
public $def;
/**
* Indexed array of definitions
*/
protected $definitions;
/**
* Bool indicator whether or not config is finalized
*/
protected $finalized = false;
/**
* Property list containing configuration directives.
*/
protected $plist;
/**
* Whether or not a set is taking place due to an
* alias lookup.
*/
private $aliasMode;
/**
* Set to false if you do not want line and file numbers in errors
* (useful when unit testing)
*/
public $chatty = true;
/**
* Current lock; only gets to this namespace are allowed.
*/
private $lock;
/**
* @param $definition HTMLPurifier_ConfigSchema that defines what directives
* are allowed.
*/
public function __construct($definition, $parent = null) {
$parent = $parent ? $parent : $definition->defaultPlist;
$this->plist = new HTMLPurifier_PropertyList($parent);
$this->def = $definition; // keep a copy around for checking
$this->parser = new HTMLPurifier_VarParser_Flexible();
}
/**
* Convenience constructor that creates a config object based on a mixed var
* @param mixed $config Variable that defines the state of the config
* object. Can be: a HTMLPurifier_Config() object,
* an array of directives based on loadArray(),
* or a string filename of an ini file.
* @param HTMLPurifier_ConfigSchema Schema object
* @return Configured HTMLPurifier_Config object
*/
public static function create($config, $schema = null) {
if ($config instanceof HTMLPurifier_Config) {
// pass-through
return $config;
}
if (!$schema) {
$ret = HTMLPurifier_Config::createDefault();
} else {
$ret = new HTMLPurifier_Config($schema);
}
if (is_string($config)) $ret->loadIni($config);
elseif (is_array($config)) $ret->loadArray($config);
return $ret;
}
/**
* Creates a new config object that inherits from a previous one.
* @param HTMLPurifier_Config $config Configuration object to inherit
* from.
* @return HTMLPurifier_Config object with $config as its parent.
*/
public static function inherit(HTMLPurifier_Config $config) {
return new HTMLPurifier_Config($config->def, $config->plist);
}
/**
* Convenience constructor that creates a default configuration object.
* @return Default HTMLPurifier_Config object.
*/
public static function createDefault() {
$definition = HTMLPurifier_ConfigSchema::instance();
$config = new HTMLPurifier_Config($definition);
return $config;
}
/**
* Retreives a value from the configuration.
* @param $key String key
*/
public function get($key, $a = null) {
if ($a !== null) {
$this->triggerError("Using deprecated API: use \$config->get('$key.$a') instead", E_USER_WARNING);
$key = "$key.$a";
}
if (!$this->finalized) $this->autoFinalize();
if (!isset($this->def->info[$key])) {
// can't add % due to SimpleTest bug
$this->triggerError('Cannot retrieve value of undefined directive ' . htmlspecialchars($key),
E_USER_WARNING);
return;
}
if (isset($this->def->info[$key]->isAlias)) {
$d = $this->def->info[$key];
$this->triggerError('Cannot get value from aliased directive, use real name ' . $d->key,
E_USER_ERROR);
return;
}
if ($this->lock) {
list($ns) = explode('.', $key);
if ($ns !== $this->lock) {
$this->triggerError('Cannot get value of namespace ' . $ns . ' when lock for ' . $this->lock . ' is active, this probably indicates a Definition setup method is accessing directives that are not within its namespace', E_USER_ERROR);
return;
}
}
return $this->plist->get($key);
}
/**
* Retreives an array of directives to values from a given namespace
* @param $namespace String namespace
*/
public function getBatch($namespace) {
if (!$this->finalized) $this->autoFinalize();
$full = $this->getAll();
if (!isset($full[$namespace])) {
$this->triggerError('Cannot retrieve undefined namespace ' . htmlspecialchars($namespace),
E_USER_WARNING);
return;
}
return $full[$namespace];
}
/**
* Returns a md5 signature of a segment of the configuration object
* that uniquely identifies that particular configuration
* @note Revision is handled specially and is removed from the batch
* before processing!
* @param $namespace Namespace to get serial for
*/
public function getBatchSerial($namespace) {
if (empty($this->serials[$namespace])) {
$batch = $this->getBatch($namespace);
unset($batch['DefinitionRev']);
$this->serials[$namespace] = md5(serialize($batch));
}
return $this->serials[$namespace];
}
/**
* Returns a md5 signature for the entire configuration object
* that uniquely identifies that particular configuration
*/
public function getSerial() {
if (empty($this->serial)) {
$this->serial = md5(serialize($this->getAll()));
}
return $this->serial;
}
/**
* Retrieves all directives, organized by namespace
* @warning This is a pretty inefficient function, avoid if you can
*/
public function getAll() {
if (!$this->finalized) $this->autoFinalize();
$ret = array();
foreach ($this->plist->squash() as $name => $value) {
list($ns, $key) = explode('.', $name, 2);
$ret[$ns][$key] = $value;
}
return $ret;
}
/**
* Sets a value to configuration.
* @param $key String key
* @param $value Mixed value
*/
public function set($key, $value, $a = null) {
if (strpos($key, '.') === false) {
$namespace = $key;
$directive = $value;
$value = $a;
$key = "$key.$directive";
$this->triggerError("Using deprecated API: use \$config->set('$key', ...) instead", E_USER_NOTICE);
} else {
list($namespace) = explode('.', $key);
}
if ($this->isFinalized('Cannot set directive after finalization')) return;
if (!isset($this->def->info[$key])) {
$this->triggerError('Cannot set undefined directive ' . htmlspecialchars($key) . ' to value',
E_USER_WARNING);
return;
}
$def = $this->def->info[$key];
if (isset($def->isAlias)) {
if ($this->aliasMode) {
$this->triggerError('Double-aliases not allowed, please fix '.
'ConfigSchema bug with' . $key, E_USER_ERROR);
return;
}
$this->aliasMode = true;
$this->set($def->key, $value);
$this->aliasMode = false;
$this->triggerError("$key is an alias, preferred directive name is {$def->key}", E_USER_NOTICE);
return;
}
// Raw type might be negative when using the fully optimized form
// of stdclass, which indicates allow_null == true
$rtype = is_int($def) ? $def : $def->type;
if ($rtype < 0) {
$type = -$rtype;
$allow_null = true;
} else {
$type = $rtype;
$allow_null = isset($def->allow_null);
}
try {
$value = $this->parser->parse($value, $type, $allow_null);
} catch (HTMLPurifier_VarParserException $e) {
$this->triggerError('Value for ' . $key . ' is of invalid type, should be ' . HTMLPurifier_VarParser::getTypeName($type), E_USER_WARNING);
return;
}
if (is_string($value) && is_object($def)) {
// resolve value alias if defined
if (isset($def->aliases[$value])) {
$value = $def->aliases[$value];
}
// check to see if the value is allowed
if (isset($def->allowed) && !isset($def->allowed[$value])) {
$this->triggerError('Value not supported, valid values are: ' .
$this->_listify($def->allowed), E_USER_WARNING);
return;
}
}
$this->plist->set($key, $value);
// reset definitions if the directives they depend on changed
// this is a very costly process, so it's discouraged
// with finalization
if ($namespace == 'HTML' || $namespace == 'CSS' || $namespace == 'URI') {
$this->definitions[$namespace] = null;
}
$this->serials[$namespace] = false;
}
/**
* Convenience function for error reporting
*/
private function _listify($lookup) {
$list = array();
foreach ($lookup as $name => $b) $list[] = $name;
return implode(', ', $list);
}
/**
* Retrieves object reference to the HTML definition.
* @param $raw Return a copy that has not been setup yet. Must be
* called before it's been setup, otherwise won't work.
*/
public function getHTMLDefinition($raw = false) {
return $this->getDefinition('HTML', $raw);
}
/**
* Retrieves object reference to the CSS definition
* @param $raw Return a copy that has not been setup yet. Must be
* called before it's been setup, otherwise won't work.
*/
public function getCSSDefinition($raw = false) {
return $this->getDefinition('CSS', $raw);
}
/**
* Retrieves a definition
* @param $type Type of definition: HTML, CSS, etc
* @param $raw Whether or not definition should be returned raw
*/
public function getDefinition($type, $raw = false) {
if (!$this->finalized) $this->autoFinalize();
// temporarily suspend locks, so we can handle recursive definition calls
$lock = $this->lock;
$this->lock = null;
$factory = HTMLPurifier_DefinitionCacheFactory::instance();
$cache = $factory->create($type, $this);
$this->lock = $lock;
if (!$raw) {
// see if we can quickly supply a definition
if (!empty($this->definitions[$type])) {
if (!$this->definitions[$type]->setup) {
$this->definitions[$type]->setup($this);
$cache->set($this->definitions[$type], $this);
}
return $this->definitions[$type];
}
// memory check missed, try cache
$this->definitions[$type] = $cache->get($this);
if ($this->definitions[$type]) {
// definition in cache, return it
return $this->definitions[$type];
}
} elseif (
!empty($this->definitions[$type]) &&
!$this->definitions[$type]->setup
) {
// raw requested, raw in memory, quick return
return $this->definitions[$type];
}
// quick checks failed, let's create the object
if ($type == 'HTML') {
$this->definitions[$type] = new HTMLPurifier_HTMLDefinition();
} elseif ($type == 'CSS') {
$this->definitions[$type] = new HTMLPurifier_CSSDefinition();
} elseif ($type == 'URI') {
$this->definitions[$type] = new HTMLPurifier_URIDefinition();
} else {
throw new HTMLPurifier_Exception("Definition of $type type not supported");
}
// quick abort if raw
if ($raw) {
if (is_null($this->get($type . '.DefinitionID'))) {
// fatally error out if definition ID not set
throw new HTMLPurifier_Exception("Cannot retrieve raw version without specifying %$type.DefinitionID");
}
return $this->definitions[$type];
}
// set it up
$this->lock = $type;
$this->definitions[$type]->setup($this);
$this->lock = null;
// save in cache
$cache->set($this->definitions[$type], $this);
return $this->definitions[$type];
}
/**
* Loads configuration values from an array with the following structure:
* Namespace.Directive => Value
* @param $config_array Configuration associative array
*/
public function loadArray($config_array) {
if ($this->isFinalized('Cannot load directives after finalization')) return;
foreach ($config_array as $key => $value) {
$key = str_replace('_', '.', $key);
if (strpos($key, '.') !== false) {
$this->set($key, $value);
} else {
$namespace = $key;
$namespace_values = $value;
foreach ($namespace_values as $directive => $value) {
$this->set($namespace .'.'. $directive, $value);
}
}
}
}
/**
* Returns a list of array(namespace, directive) for all directives
* that are allowed in a web-form context as per an allowed
* namespaces/directives list.
* @param $allowed List of allowed namespaces/directives
*/
public static function getAllowedDirectivesForForm($allowed, $schema = null) {
if (!$schema) {
$schema = HTMLPurifier_ConfigSchema::instance();
}
if ($allowed !== true) {
if (is_string($allowed)) $allowed = array($allowed);
$allowed_ns = array();
$allowed_directives = array();
$blacklisted_directives = array();
foreach ($allowed as $ns_or_directive) {
if (strpos($ns_or_directive, '.') !== false) {
// directive
if ($ns_or_directive[0] == '-') {
$blacklisted_directives[substr($ns_or_directive, 1)] = true;
} else {
$allowed_directives[$ns_or_directive] = true;
}
} else {
// namespace
$allowed_ns[$ns_or_directive] = true;
}
}
}
$ret = array();
foreach ($schema->info as $key => $def) {
list($ns, $directive) = explode('.', $key, 2);
if ($allowed !== true) {
if (isset($blacklisted_directives["$ns.$directive"])) continue;
if (!isset($allowed_directives["$ns.$directive"]) && !isset($allowed_ns[$ns])) continue;
}
if (isset($def->isAlias)) continue;
if ($directive == 'DefinitionID' || $directive == 'DefinitionRev') continue;
$ret[] = array($ns, $directive);
}
return $ret;
}
/**
* Loads configuration values from $_GET/$_POST that were posted
* via ConfigForm
* @param $array $_GET or $_POST array to import
* @param $index Index/name that the config variables are in
* @param $allowed List of allowed namespaces/directives
* @param $mq_fix Boolean whether or not to enable magic quotes fix
* @param $schema Instance of HTMLPurifier_ConfigSchema to use, if not global copy
*/
public static function loadArrayFromForm($array, $index = false, $allowed = true, $mq_fix = true, $schema = null) {
$ret = HTMLPurifier_Config::prepareArrayFromForm($array, $index, $allowed, $mq_fix, $schema);
$config = HTMLPurifier_Config::create($ret, $schema);
return $config;
}
/**
* Merges in configuration values from $_GET/$_POST to object. NOT STATIC.
* @note Same parameters as loadArrayFromForm
*/
public function mergeArrayFromForm($array, $index = false, $allowed = true, $mq_fix = true) {
$ret = HTMLPurifier_Config::prepareArrayFromForm($array, $index, $allowed, $mq_fix, $this->def);
$this->loadArray($ret);
}
/**
* Prepares an array from a form into something usable for the more
* strict parts of HTMLPurifier_Config
*/
public static function prepareArrayFromForm($array, $index = false, $allowed = true, $mq_fix = true, $schema = null) {
if ($index !== false) $array = (isset($array[$index]) && is_array($array[$index])) ? $array[$index] : array();
$mq = $mq_fix && function_exists('get_magic_quotes_gpc') && get_magic_quotes_gpc();
$allowed = HTMLPurifier_Config::getAllowedDirectivesForForm($allowed, $schema);
$ret = array();
foreach ($allowed as $key) {
list($ns, $directive) = $key;
$skey = "$ns.$directive";
if (!empty($array["Null_$skey"])) {
$ret[$ns][$directive] = null;
continue;
}
if (!isset($array[$skey])) continue;
$value = $mq ? stripslashes($array[$skey]) : $array[$skey];
$ret[$ns][$directive] = $value;
}
return $ret;
}
/**
* Loads configuration values from an ini file
* @param $filename Name of ini file
*/
public function loadIni($filename) {
if ($this->isFinalized('Cannot load directives after finalization')) return;
$array = parse_ini_file($filename, true);
$this->loadArray($array);
}
/**
* Checks whether or not the configuration object is finalized.
* @param $error String error message, or false for no error
*/
public function isFinalized($error = false) {
if ($this->finalized && $error) {
$this->triggerError($error, E_USER_ERROR);
}
return $this->finalized;
}
/**
* Finalizes configuration only if auto finalize is on and not
* already finalized
*/
public function autoFinalize() {
if ($this->autoFinalize) {
$this->finalize();
} else {
$this->plist->squash(true);
}
}
/**
* Finalizes a configuration object, prohibiting further change
*/
public function finalize() {
$this->finalized = true;
unset($this->parser);
}
/**
* Produces a nicely formatted error message by supplying the
* stack frame information from two levels up and OUTSIDE of
* HTMLPurifier_Config.
*/
protected function triggerError($msg, $no) {
// determine previous stack frame
$backtrace = debug_backtrace();
if ($this->chatty && isset($backtrace[1])) {
$frame = $backtrace[1];
$extra = " on line {$frame['line']} in file {$frame['file']}";
} else {
$extra = '';
}
trigger_error($msg . $extra, $no);
}
/**
* Returns a serialized form of the configuration object that can
* be reconstituted.
*/
public function serialize() {
$this->getDefinition('HTML');
$this->getDefinition('CSS');
$this->getDefinition('URI');
return serialize($this);
}
}
// vim: et sw=4 sts=4

66
library/HTMLPurifier/ConfigSchema/ValidatorAtom.php
View file

@ -1,66 +0,0 @@
<?php
/**
* Fluent interface for validating the contents of member variables.
* This should be immutable. See HTMLPurifier_ConfigSchema_Validator for
* use-cases. We name this an 'atom' because it's ONLY for validations that
* are independent and usually scalar.
*/
class HTMLPurifier_ConfigSchema_ValidatorAtom
{
protected $context, $obj, $member, $contents;
public function __construct($context, $obj, $member) {
$this->context = $context;
$this->obj = $obj;
$this->member = $member;
$this->contents =& $obj->$member;
}
public function assertIsString() {
if (!is_string($this->contents)) $this->error('must be a string');
return $this;
}
public function assertIsBool() {
if (!is_bool($this->contents)) $this->error('must be a boolean');
return $this;
}
public function assertIsArray() {
if (!is_array($this->contents)) $this->error('must be an array');
return $this;
}
public function assertNotNull() {
if ($this->contents === null) $this->error('must not be null');
return $this;
}
public function assertAlnum() {
$this->assertIsString();
if (!ctype_alnum($this->contents)) $this->error('must be alphanumeric');
return $this;
}
public function assertNotEmpty() {
if (empty($this->contents)) $this->error('must not be empty');
return $this;
}
public function assertIsLookup() {
$this->assertIsArray();
foreach ($this->contents as $v) {
if ($v !== true) $this->error('must be a lookup array');
}
return $this;
}
protected function error($msg) {
throw new HTMLPurifier_ConfigSchema_Exception(ucfirst($this->member) . ' in ' . $this->context . ' ' . $msg);
}
}
// vim: et sw=4 sts=4

BIN
library/HTMLPurifier/ConfigSchema/schema.ser
View file

Binary file not shown.

18
library/HTMLPurifier/ConfigSchema/schema/HTML.AllowedElements.txt
View file

@ -1,18 +0,0 @@
HTML.AllowedElements
TYPE: lookup/null
VERSION: 1.3.0
DEFAULT: NULL
--DESCRIPTION--
<p>
If HTML Purifier's tag set is unsatisfactory for your needs, you
can overload it with your own list of tags to allow. Note that this
method is subtractive: it does its job by taking away from HTML Purifier
usual feature set, so you cannot add a tag that HTML Purifier never
supported in the first place (like embed, form or head). If you
change this, you probably also want to change %HTML.AllowedAttributes.
</p>
<p>
<strong>Warning:</strong> If another directive conflicts with the
elements here, <em>that</em> directive will win and override.
</p>
--# vim: et sw=4 sts=4

82
library/HTMLPurifier/Context.php
View file

@ -1,82 +0,0 @@
<?php
/**
* Registry object that contains information about the current context.
* @warning Is a bit buggy when variables are set to null: it thinks
* they don't exist! So use false instead, please.
* @note Since the variables Context deals with may not be objects,
* references are very important here! Do not remove!
*/
class HTMLPurifier_Context
{
/**
* Private array that stores the references.
*/
private $_storage = array();
/**
* Registers a variable into the context.
* @param $name String name
* @param $ref Reference to variable to be registered
*/
public function register($name, &$ref) {
if (isset($this->_storage[$name])) {
trigger_error("Name $name produces collision, cannot re-register",
E_USER_ERROR);
return;
}
$this->_storage[$name] =& $ref;
}
/**
* Retrieves a variable reference from the context.
* @param $name String name
* @param $ignore_error Boolean whether or not to ignore error
*/
public function &get($name, $ignore_error = false) {
if (!isset($this->_storage[$name])) {
if (!$ignore_error) {
trigger_error("Attempted to retrieve non-existent variable $name",
E_USER_ERROR);
}
$var = null; // so we can return by reference
return $var;
}
return $this->_storage[$name];
}
/**
* Destorys a variable in the context.
* @param $name String name
*/
public function destroy($name) {
if (!isset($this->_storage[$name])) {
trigger_error("Attempted to destroy non-existent variable $name",
E_USER_ERROR);
return;
}
unset($this->_storage[$name]);
}
/**
* Checks whether or not the variable exists.
* @param $name String name
*/
public function exists($name) {
return isset($this->_storage[$name]);
}
/**
* Loads a series of variables from an associative array
* @param $context_array Assoc array of variables to load
*/
public function loadArray($context_array) {
foreach ($context_array as $key => $discard) {
$this->register($key, $context_array[$key]);
}
}
}
// vim: et sw=4 sts=4

39
library/HTMLPurifier/Definition.php
View file

@ -1,39 +0,0 @@
<?php
/**
* Super-class for definition datatype objects, implements serialization
* functions for the class.
*/
abstract class HTMLPurifier_Definition
{
/**
* Has setup() been called yet?
*/
public $setup = false;
/**
* What type of definition is it?
*/
public $type;
/**
* Sets up the definition object into the final form, something
* not done by the constructor
* @param $config HTMLPurifier_Config instance
*/
abstract protected function doSetup($config);
/**
* Setup function that aborts if already setup
* @param $config HTMLPurifier_Config instance
*/
public function setup($config) {
if ($this->setup) return;
$this->setup = true;
$this->doSetup($config);
}
}
// vim: et sw=4 sts=4

62
library/HTMLPurifier/DefinitionCache/Decorator.php
View file

@ -1,62 +0,0 @@
<?php
class HTMLPurifier_DefinitionCache_Decorator extends HTMLPurifier_DefinitionCache
{
/**
* Cache object we are decorating
*/
public $cache;
public function __construct() {}
/**
* Lazy decorator function
* @param $cache Reference to cache object to decorate
*/
public function decorate(&$cache) {
$decorator = $this->copy();
// reference is necessary for mocks in PHP 4
$decorator->cache =& $cache;
$decorator->type = $cache->type;
return $decorator;
}
/**
* Cross-compatible clone substitute
*/
public function copy() {
return new HTMLPurifier_DefinitionCache_Decorator();
}
public function add($def, $config) {
return $this->cache->add($def, $config);
}
public function set($def, $config) {
return $this->cache->set($def, $config);
}
public function replace($def, $config) {
return $this->cache->replace($def, $config);
}
public function get($config) {
return $this->cache->get($config);
}
public function remove($config) {
return $this->cache->remove($config);
}
public function flush($config) {
return $this->cache->flush($config);
}
public function cleanup($config) {
return $this->cache->cleanup($config);
}
}
// vim: et sw=4 sts=4

43
library/HTMLPurifier/DefinitionCache/Decorator/Cleanup.php
View file

@ -1,43 +0,0 @@
<?php
/**
* Definition cache decorator class that cleans up the cache
* whenever there is a cache miss.
*/
class HTMLPurifier_DefinitionCache_Decorator_Cleanup extends
HTMLPurifier_DefinitionCache_Decorator
{
public $name = 'Cleanup';
public function copy() {
return new HTMLPurifier_DefinitionCache_Decorator_Cleanup();
}
public function add($def, $config) {
$status = parent::add($def, $config);
if (!$status) parent::cleanup($config);
return $status;
}
public function set($def, $config) {
$status = parent::set($def, $config);
if (!$status) parent::cleanup($config);
return $status;
}
public function replace($def, $config) {
$status = parent::replace($def, $config);
if (!$status) parent::cleanup($config);
return $status;
}
public function get($config) {
$ret = parent::get($config);
if (!$ret) parent::cleanup($config);
return $ret;
}
}
// vim: et sw=4 sts=4

46
library/HTMLPurifier/DefinitionCache/Decorator/Memory.php
View file

@ -1,46 +0,0 @@
<?php
/**
* Definition cache decorator class that saves all cache retrievals
* to PHP's memory; good for unit tests or circumstances where
* there are lots of configuration objects floating around.
*/
class HTMLPurifier_DefinitionCache_Decorator_Memory extends
HTMLPurifier_DefinitionCache_Decorator
{
protected $definitions;
public $name = 'Memory';
public function copy() {
return new HTMLPurifier_DefinitionCache_Decorator_Memory();
}
public function add($def, $config) {
$status = parent::add($def, $config);
if ($status) $this->definitions[$this->generateKey($config)] = $def;
return $status;
}
public function set($def, $config) {
$status = parent::set($def, $config);
if ($status) $this->definitions[$this->generateKey($config)] = $def;
return $status;
}
public function replace($def, $config) {
$status = parent::replace($def, $config);
if ($status) $this->definitions[$this->generateKey($config)] = $def;
return $status;
}
public function get($config) {
$key = $this->generateKey($config);
if (isset($this->definitions[$key])) return $this->definitions[$key];
$this->definitions[$key] = parent::get($config);
return $this->definitions[$key];
}
}
// vim: et sw=4 sts=4

47
library/HTMLPurifier/DefinitionCache/Decorator/Template.php.in
View file

@ -1,47 +0,0 @@
<?php
require_once 'HTMLPurifier/DefinitionCache/Decorator.php';
/**
* Definition cache decorator template.
*/
class HTMLPurifier_DefinitionCache_Decorator_Template extends
HTMLPurifier_DefinitionCache_Decorator
{
var $name = 'Template'; // replace this
function copy() {
// replace class name with yours
return new HTMLPurifier_DefinitionCache_Decorator_Template();
}
// remove methods you don't need
function add($def, $config) {
return parent::add($def, $config);
}
function set($def, $config) {
return parent::set($def, $config);
}
function replace($def, $config) {
return parent::replace($def, $config);
}
function get($config) {
return parent::get($config);
}
function flush() {
return parent::flush();
}
function cleanup($config) {
return parent::cleanup($config);
}
}
// vim: et sw=4 sts=4

39
library/HTMLPurifier/DefinitionCache/Null.php
View file

@ -1,39 +0,0 @@
<?php
/**
* Null cache object to use when no caching is on.
*/
class HTMLPurifier_DefinitionCache_Null extends HTMLPurifier_DefinitionCache
{
public function add($def, $config) {
return false;
}
public function set($def, $config) {
return false;
}
public function replace($def, $config) {
return false;
}
public function remove($config) {
return false;
}
public function get($config) {
return false;
}
public function flush($config) {
return false;
}
public function cleanup($config) {
return false;
}
}
// vim: et sw=4 sts=4

172
library/HTMLPurifier/DefinitionCache/Serializer.php
View file

@ -1,172 +0,0 @@
<?php
class HTMLPurifier_DefinitionCache_Serializer extends
HTMLPurifier_DefinitionCache
{
public function add($def, $config) {
if (!$this->checkDefType($def)) return;
$file = $this->generateFilePath($config);
if (file_exists($file)) return false;
if (!$this->_prepareDir($config)) return false;
return $this->_write($file, serialize($def));
}
public function set($def, $config) {
if (!$this->checkDefType($def)) return;
$file = $this->generateFilePath($config);
if (!$this->_prepareDir($config)) return false;
return $this->_write($file, serialize($def));
}
public function replace($def, $config) {
if (!$this->checkDefType($def)) return;
$file = $this->generateFilePath($config);
if (!file_exists($file)) return false;
if (!$this->_prepareDir($config)) return false;
return $this->_write($file, serialize($def));
}
public function get($config) {
$file = $this->generateFilePath($config);
if (!file_exists($file)) return false;
return unserialize(file_get_contents($file));
}
public function remove($config) {
$file = $this->generateFilePath($config);
if (!file_exists($file)) return false;
return unlink($file);
}
public function flush($config) {
if (!$this->_prepareDir($config)) return false;
$dir = $this->generateDirectoryPath($config);
$dh = opendir($dir);
while (false !== ($filename = readdir($dh))) {
if (empty($filename)) continue;
if ($filename[0] === '.') continue;
unlink($dir . '/' . $filename);
}
}
public function cleanup($config) {
if (!$this->_prepareDir($config)) return false;
$dir = $this->generateDirectoryPath($config);
$dh = opendir($dir);
while (false !== ($filename = readdir($dh))) {
if (empty($filename)) continue;
if ($filename[0] === '.') continue;
$key = substr($filename, 0, strlen($filename) - 4);
if ($this->isOld($key, $config)) unlink($dir . '/' . $filename);
}
}
/**
* Generates the file path to the serial file corresponding to
* the configuration and definition name
* @todo Make protected
*/
public function generateFilePath($config) {
$key = $this->generateKey($config);
return $this->generateDirectoryPath($config) . '/' . $key . '.ser';
}
/**
* Generates the path to the directory contain this cache's serial files
* @note No trailing slash
* @todo Make protected
*/
public function generateDirectoryPath($config) {
$base = $this->generateBaseDirectoryPath($config);
return $base . '/' . $this->type;
}
/**
* Generates path to base directory that contains all definition type
* serials
* @todo Make protected
*/
public function generateBaseDirectoryPath($config) {
$base = $config->get('Cache.SerializerPath');
$base = is_null($base) ? HTMLPURIFIER_PREFIX . '/HTMLPurifier/DefinitionCache/Serializer' : $base;
return $base;
}
/**
* Convenience wrapper function for file_put_contents
* @param $file File name to write to
* @param $data Data to write into file
* @return Number of bytes written if success, or false if failure.
*/
private function _write($file, $data) {
return file_put_contents($file, $data);
}
/**
* Prepares the directory that this type stores the serials in
* @return True if successful
*/
private function _prepareDir($config) {
$directory = $this->generateDirectoryPath($config);
if (!is_dir($directory)) {
$base = $this->generateBaseDirectoryPath($config);
if (!is_dir($base)) {
trigger_error('Base directory '.$base.' does not exist,
please create or change using %Cache.SerializerPath',
E_USER_WARNING);
return false;
} elseif (!$this->_testPermissions($base)) {
return false;
}
$old = umask(0022); // disable group and world writes
mkdir($directory);
umask($old);
} elseif (!$this->_testPermissions($directory)) {
return false;
}
return true;
}
/**
* Tests permissions on a directory and throws out friendly
* error messages and attempts to chmod it itself if possible
*/
private function _testPermissions($dir) {
// early abort, if it is writable, everything is hunky-dory
if (is_writable($dir)) return true;
if (!is_dir($dir)) {
// generally, you'll want to handle this beforehand
// so a more specific error message can be given
trigger_error('Directory '.$dir.' does not exist',
E_USER_WARNING);
return false;
}
if (function_exists('posix_getuid')) {
// POSIX system, we can give more specific advice
if (fileowner($dir) === posix_getuid()) {
// we can chmod it ourselves
chmod($dir, 0755);
return true;
} elseif (filegroup($dir) === posix_getgid()) {
$chmod = '775';
} else {
// PHP's probably running as nobody, so we'll
// need to give global permissions
$chmod = '777';
}
trigger_error('Directory '.$dir.' not writable, '.
'please chmod to ' . $chmod,
E_USER_WARNING);
} else {
// generic error message
trigger_error('Directory '.$dir.' not writable, '.
'please alter file permissions',
E_USER_WARNING);
}
return false;
}
}
// vim: et sw=4 sts=4

1
library/HTMLPurifier/EntityLookup/entities.ser
View file

File diff suppressed because one or more lines are too long

135
library/HTMLPurifier/Filter/ExtractStyleBlocks.php
View file

@ -1,135 +0,0 @@
<?php
/**
* This filter extracts <style> blocks from input HTML, cleans them up
* using CSSTidy, and then places them in $purifier->context->get('StyleBlocks')
* so they can be used elsewhere in the document.
*
* @note
* See tests/HTMLPurifier/Filter/ExtractStyleBlocksTest.php for
* sample usage.
*
* @note
* This filter can also be used on stylesheets not included in the
* document--something purists would probably prefer. Just directly
* call HTMLPurifier_Filter_ExtractStyleBlocks->cleanCSS()
*/
class HTMLPurifier_Filter_ExtractStyleBlocks extends HTMLPurifier_Filter
{
public $name = 'ExtractStyleBlocks';
private $_styleMatches = array();
private $_tidy;
public function __construct() {
$this->_tidy = new csstidy();
}
/**
* Save the contents of CSS blocks to style matches
* @param $matches preg_replace style $matches array
*/
protected function styleCallback($matches) {
$this->_styleMatches[] = $matches[1];
}
/**
* Removes inline <style> tags from HTML, saves them for later use
* @todo Extend to indicate non-text/css style blocks
*/
public function preFilter($html, $config, $context) {
$tidy = $config->get('Filter.ExtractStyleBlocks.TidyImpl');
if ($tidy !== null) $this->_tidy = $tidy;
$html = preg_replace_callback('#<style(?:\s.*)?>(.+)</style>#isU', array($this, 'styleCallback'), $html);
$style_blocks = $this->_styleMatches;
$this->_styleMatches = array(); // reset
$context->register('StyleBlocks', $style_blocks); // $context must not be reused
if ($this->_tidy) {
foreach ($style_blocks as &$style) {
$style = $this->cleanCSS($style, $config, $context);
}
}
return $html;
}
/**
* Takes CSS (the stuff found in <style>) and cleans it.
* @warning Requires CSSTidy <http://csstidy.sourceforge.net/>
* @param $css CSS styling to clean
* @param $config Instance of HTMLPurifier_Config
* @param $context Instance of HTMLPurifier_Context
* @return Cleaned CSS
*/
public function cleanCSS($css, $config, $context) {
// prepare scope
$scope = $config->get('Filter.ExtractStyleBlocks.Scope');
if ($scope !== null) {
$scopes = array_map('trim', explode(',', $scope));
} else {
$scopes = array();
}
// remove comments from CSS
$css = trim($css);
if (strncmp('<!--', $css, 4) === 0) {
$css = substr($css, 4);
}
if (strlen($css) > 3 && substr($css, -3) == '-->') {
$css = substr($css, 0, -3);
}
$css = trim($css);
$this->_tidy->parse($css);
$css_definition = $config->getDefinition('CSS');
foreach ($this->_tidy->css as $k => $decls) {
// $decls are all CSS declarations inside an @ selector
$new_decls = array();
foreach ($decls as $selector => $style) {
$selector = trim($selector);
if ($selector === '') continue; // should not happen
if ($selector[0] === '+') {
if ($selector !== '' && $selector[0] === '+') continue;
}
if (!empty($scopes)) {
$new_selector = array(); // because multiple ones are possible
$selectors = array_map('trim', explode(',', $selector));
foreach ($scopes as $s1) {
foreach ($selectors as $s2) {
$new_selector[] = "$s1 $s2";
}
}
$selector = implode(', ', $new_selector); // now it's a string
}
foreach ($style as $name => $value) {
if (!isset($css_definition->info[$name])) {
unset($style[$name]);
continue;
}
$def = $css_definition->info[$name];
$ret = $def->validate($value, $config, $context);
if ($ret === false) unset($style[$name]);
else $style[$name] = $ret;
}
$new_decls[$selector] = $style;
}
$this->_tidy->css[$k] = $new_decls;
}
// remove stuff that shouldn't be used, could be reenabled
// after security risks are analyzed
$this->_tidy->import = array();
$this->_tidy->charset = null;
$this->_tidy->namespace = null;
$css = $this->_tidy->print->plain();
// we are going to escape any special characters <>& to ensure
// that no funny business occurs (i.e. </style> in a font-family prop).
if ($config->get('Filter.ExtractStyleBlocks.Escaping')) {
$css = str_replace(
array('<', '>', '&'),
array('\3C ', '\3E ', '\26 '),
$css
);
}
return $css;
}
}
// vim: et sw=4 sts=4

39
library/HTMLPurifier/Filter/YouTube.php
View file

@ -1,39 +0,0 @@
<?php
class HTMLPurifier_Filter_YouTube extends HTMLPurifier_Filter
{
public $name = 'YouTube';
public function preFilter($html, $config, $context) {
$pre_regex = '#<object[^>]+>.+?'.
'http://www.youtube.com/((?:v|cp)/[A-Za-z0-9\-_=]+).+?</object>#s';
$pre_replace = '<span class="youtube-embed">\1</span>';
return preg_replace($pre_regex, $pre_replace, $html);
}
public function postFilter($html, $config, $context) {
$post_regex = '#<span class="youtube-embed">((?:v|cp)/[A-Za-z0-9\-_=]+)</span>#';
return preg_replace_callback($post_regex, array($this, 'postFilterCallback'), $html);
}
protected function armorUrl($url) {
return str_replace('--', '-&#45;', $url);
}
protected function postFilterCallback($matches) {
$url = $this->armorUrl($matches[1]);
return '<object width="425" height="350" type="application/x-shockwave-flash" '.
'data="http://www.youtube.com/'.$url.'">'.
'<param name="movie" value="http://www.youtube.com/'.$url.'"></param>'.
'<!--[if IE]>'.
'<embed src="http://www.youtube.com/'.$url.'"'.
'type="application/x-shockwave-flash"'.
'wmode="transparent" width="425" height="350" />'.
'<![endif]-->'.
'</object>';
}
}
// vim: et sw=4 sts=4

118
library/HTMLPurifier/HTMLModule/Forms.php
View file

@ -1,118 +0,0 @@
<?php
/**
* XHTML 1.1 Forms module, defines all form-related elements found in HTML 4.
*/
class HTMLPurifier_HTMLModule_Forms extends HTMLPurifier_HTMLModule
{
public $name = 'Forms';
public $safe = false;
public $content_sets = array(
'Block' => 'Form',
'Inline' => 'Formctrl',
);
public function setup($config) {
$form = $this->addElement('form', 'Form',
'Required: Heading | List | Block | fieldset', 'Common', array(
'accept' => 'ContentTypes',
'accept-charset' => 'Charsets',
'action*' => 'URI',
'method' => 'Enum#get,post',
// really ContentType, but these two are the only ones used today
'enctype' => 'Enum#application/x-www-form-urlencoded,multipart/form-data',
));
$form->excludes = array('form' => true);
$input = $this->addElement('input', 'Formctrl', 'Empty', 'Common', array(
'accept' => 'ContentTypes',
'accesskey' => 'Character',
'alt' => 'Text',
'checked' => 'Bool#checked',
'disabled' => 'Bool#disabled',
'maxlength' => 'Number',
'name' => 'CDATA',
'readonly' => 'Bool#readonly',
'size' => 'Number',
'src' => 'URI#embeds',
'tabindex' => 'Number',
'type' => 'Enum#text,password,checkbox,button,radio,submit,reset,file,hidden,image',
'value' => 'CDATA',
));
$input->attr_transform_post[] = new HTMLPurifier_AttrTransform_Input();
$this->addElement('select', 'Formctrl', 'Required: optgroup | option', 'Common', array(
'disabled' => 'Bool#disabled',
'multiple' => 'Bool#multiple',
'name' => 'CDATA',
'size' => 'Number',
'tabindex' => 'Number',
));
$this->addElement('option', false, 'Optional: #PCDATA', 'Common', array(
'disabled' => 'Bool#disabled',
'label' => 'Text',
'selected' => 'Bool#selected',
'value' => 'CDATA',
));
// It's illegal for there to be more than one selected, but not
// be multiple. Also, no selected means undefined behavior. This might
// be difficult to implement; perhaps an injector, or a context variable.
$textarea = $this->addElement('textarea', 'Formctrl', 'Optional: #PCDATA', 'Common', array(
'accesskey' => 'Character',
'cols*' => 'Number',
'disabled' => 'Bool#disabled',
'name' => 'CDATA',
'readonly' => 'Bool#readonly',
'rows*' => 'Number',
'tabindex' => 'Number',
));
$textarea->attr_transform_pre[] = new HTMLPurifier_AttrTransform_Textarea();
$button = $this->addElement('button', 'Formctrl', 'Optional: #PCDATA | Heading | List | Block | Inline', 'Common', array(
'accesskey' => 'Character',
'disabled' => 'Bool#disabled',
'name' => 'CDATA',
'tabindex' => 'Number',
'type' => 'Enum#button,submit,reset',
'value' => 'CDATA',
));
// For exclusions, ideally we'd specify content sets, not literal elements
$button->excludes = $this->makeLookup(
'form', 'fieldset', // Form
'input', 'select', 'textarea', 'label', 'button', // Formctrl
'a' // as per HTML 4.01 spec, this is omitted by modularization
);
// Extra exclusion: img usemap="" is not permitted within this element.
// We'll omit this for now, since we don't have any good way of
// indicating it yet.
// This is HIGHLY user-unfriendly; we need a custom child-def for this
$this->addElement('fieldset', 'Form', 'Custom: (#WS?,legend,(Flow|#PCDATA)*)', 'Common');
$label = $this->addElement('label', 'Formctrl', 'Optional: #PCDATA | Inline', 'Common', array(
'accesskey' => 'Character',
// 'for' => 'IDREF', // IDREF not implemented, cannot allow
));
$label->excludes = array('label' => true);
$this->addElement('legend', false, 'Optional: #PCDATA | Inline', 'Common', array(
'accesskey' => 'Character',
));
$this->addElement('optgroup', false, 'Required: option', 'Common', array(
'disabled' => 'Bool#disabled',
'label*' => 'Text',
));
// Don't forget an injector for <isindex>. This one's a little complex
// because it maps to multiple elements.
}
}
// vim: et sw=4 sts=4

21
library/HTMLPurifier/HTMLModule/Tidy/Strict.php
View file

@ -1,21 +0,0 @@
<?php
class HTMLPurifier_HTMLModule_Tidy_Strict extends HTMLPurifier_HTMLModule_Tidy_XHTMLAndHTML4
{
public $name = 'Tidy_Strict';
public $defaultLevel = 'light';
public function makeFixes() {
$r = parent::makeFixes();
$r['blockquote#content_model_type'] = 'strictblockquote';
return $r;
}
public $defines_child_def = true;
public function getChildDef($def) {
if ($def->content_model_type != 'strictblockquote') return parent::getChildDef($def);
return new HTMLPurifier_ChildDef_StrictBlockquote($def->content_model);
}
}
// vim: et sw=4 sts=4

51
library/HTMLPurifier/Injector/RemoveEmpty.php
View file

@ -1,51 +0,0 @@
<?php
class HTMLPurifier_Injector_RemoveEmpty extends HTMLPurifier_Injector
{
private $context, $config, $attrValidator, $removeNbsp, $removeNbspExceptions;
public function prepare($config, $context) {
parent::prepare($config, $context);
$this->config = $config;
$this->context = $context;
$this->removeNbsp = $config->get('AutoFormat.RemoveEmpty.RemoveNbsp');
$this->removeNbspExceptions = $config->get('AutoFormat.RemoveEmpty.RemoveNbsp.Exceptions');
$this->attrValidator = new HTMLPurifier_AttrValidator();
}
public function handleElement(&$token) {
if (!$token instanceof HTMLPurifier_Token_Start) return;
$next = false;
for ($i = $this->inputIndex + 1, $c = count($this->inputTokens); $i < $c; $i++) {
$next = $this->inputTokens[$i];
if ($next instanceof HTMLPurifier_Token_Text) {
if ($next->is_whitespace) continue;
if ($this->removeNbsp && !isset($this->removeNbspExceptions[$token->name])) {
$plain = str_replace("\xC2\xA0", "", $next->data);
$isWsOrNbsp = $plain === '' || ctype_space($plain);
if ($isWsOrNbsp) continue;
}
}
break;
}
if (!$next || ($next instanceof HTMLPurifier_Token_End && $next->name == $token->name)) {
if ($token->name == 'colgroup') return;
$this->attrValidator->validateToken($token, $this->config, $this->context);
$token->armor['ValidateAttributes'] = true;
if (isset($token->attr['id']) || isset($token->attr['name'])) return;
$token = $i - $this->inputIndex + 1;
for ($b = $this->inputIndex - 1; $b > 0; $b--) {
$prev = $this->inputTokens[$b];
if ($prev instanceof HTMLPurifier_Token_Text && $prev->is_whitespace) continue;
break;
}
// This is safe because we removed the token that triggered this.
$this->rewind($b - 1);
return;
}
}
}
// vim: et sw=4 sts=4

63
library/HTMLPurifier/Language/messages/en.php
View file

@ -1,63 +0,0 @@
<?php
$fallback = false;
$messages = array(
'HTMLPurifier' => 'HTML Purifier',
// for unit testing purposes
'LanguageFactoryTest: Pizza' => 'Pizza',
'LanguageTest: List' => '$1',
'LanguageTest: Hash' => '$1.Keys; $1.Values',
'Item separator' => ', ',
'Item separator last' => ' and ', // non-Harvard style
'ErrorCollector: No errors' => 'No errors detected. However, because error reporting is still incomplete, there may have been errors that the error collector was not notified of; please inspect the output HTML carefully.',
'ErrorCollector: At line' => ' at line $line',
'ErrorCollector: Incidental errors' => 'Incidental errors',
'Lexer: Unclosed comment' => 'Unclosed comment',
'Lexer: Unescaped lt' => 'Unescaped less-than sign (<) should be &lt;',
'Lexer: Missing gt' => 'Missing greater-than sign (>), previous less-than sign (<) should be escaped',
'Lexer: Missing attribute key' => 'Attribute declaration has no key',
'Lexer: Missing end quote' => 'Attribute declaration has no end quote',
'Lexer: Extracted body' => 'Removed document metadata tags',
'Strategy_RemoveForeignElements: Tag transform' => '<$1> element transformed into $CurrentToken.Serialized',
'Strategy_RemoveForeignElements: Missing required attribute' => '$CurrentToken.Compact element missing required attribute $1',
'Strategy_RemoveForeignElements: Foreign element to text' => 'Unrecognized $CurrentToken.Serialized tag converted to text',
'Strategy_RemoveForeignElements: Foreign element removed' => 'Unrecognized $CurrentToken.Serialized tag removed',
'Strategy_RemoveForeignElements: Comment removed' => 'Comment containing "$CurrentToken.Data" removed',
'Strategy_RemoveForeignElements: Foreign meta element removed' => 'Unrecognized $CurrentToken.Serialized meta tag and all descendants removed',
'Strategy_RemoveForeignElements: Token removed to end' => 'Tags and text starting from $1 element where removed to end',
'Strategy_RemoveForeignElements: Trailing hyphen in comment removed' => 'Trailing hyphen(s) in comment removed',
'Strategy_RemoveForeignElements: Hyphens in comment collapsed' => 'Double hyphens in comments are not allowed, and were collapsed into single hyphens',
'Strategy_MakeWellFormed: Unnecessary end tag removed' => 'Unnecessary $CurrentToken.Serialized tag removed',
'Strategy_MakeWellFormed: Unnecessary end tag to text' => 'Unnecessary $CurrentToken.Serialized tag converted to text',
'Strategy_MakeWellFormed: Tag auto closed' => '$1.Compact started on line $1.Line auto-closed by $CurrentToken.Compact',
'Strategy_MakeWellFormed: Tag carryover' => '$1.Compact started on line $1.Line auto-continued into $CurrentToken.Compact',
'Strategy_MakeWellFormed: Stray end tag removed' => 'Stray $CurrentToken.Serialized tag removed',
'Strategy_MakeWellFormed: Stray end tag to text' => 'Stray $CurrentToken.Serialized tag converted to text',
'Strategy_MakeWellFormed: Tag closed by element end' => '$1.Compact tag started on line $1.Line closed by end of $CurrentToken.Serialized',
'Strategy_MakeWellFormed: Tag closed by document end' => '$1.Compact tag started on line $1.Line closed by end of document',
'Strategy_FixNesting: Node removed' => '$CurrentToken.Compact node removed',
'Strategy_FixNesting: Node excluded' => '$CurrentToken.Compact node removed due to descendant exclusion by ancestor element',
'Strategy_FixNesting: Node reorganized' => 'Contents of $CurrentToken.Compact node reorganized to enforce its content model',
'Strategy_FixNesting: Node contents removed' => 'Contents of $CurrentToken.Compact node removed',
'AttrValidator: Attributes transformed' => 'Attributes on $CurrentToken.Compact transformed from $1.Keys to $2.Keys',
'AttrValidator: Attribute removed' => '$CurrentAttr.Name attribute on $CurrentToken.Compact removed',
);
$errorNames = array(
E_ERROR => 'Error',
E_WARNING => 'Warning',
E_NOTICE => 'Notice'
);
// vim: et sw=4 sts=4

139
library/HTMLPurifier/Lexer/PEARSax3.php
View file

@ -1,139 +0,0 @@
<?php
/**
* Proof-of-concept lexer that uses the PEAR package XML_HTMLSax3 to parse HTML.
*
* 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 (in all areas,
* text and attributes).
*
* 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.
*
* @warning Entity-resolution inside attributes is broken.
*/
class HTMLPurifier_Lexer_PEARSax3 extends HTMLPurifier_Lexer
{
/**
* Internal accumulator array for SAX parsers.
*/
protected $tokens = array();
protected $last_token_was_empty;
private $parent_handler;
private $stack = array();
public function tokenizeHTML($string, $config, $context) {
$this->tokens = array();
$this->last_token_was_empty = false;
$string = $this->normalize($string, $config, $context);
$this->parent_handler = set_error_handler(array($this, 'muteStrictErrorHandler'));
$parser = new XML_HTMLSax3();
$parser->set_object($this);
$parser->set_element_handler('openHandler','closeHandler');
$parser->set_data_handler('dataHandler');
$parser->set_escape_handler('escapeHandler');
// doesn't seem to work correctly for attributes
$parser->set_option('XML_OPTION_ENTITIES_PARSED', 1);
$parser->parse($string);
restore_error_handler();
return $this->tokens;
}
/**
* Open tag event handler, interface is defined by PEAR package.
*/
public function openHandler(&$parser, $name, $attrs, $closed) {
// entities are not resolved in attrs
foreach ($attrs as $key => $attr) {
$attrs[$key] = $this->parseData($attr);
}
if ($closed) {
$this->tokens[] = new HTMLPurifier_Token_Empty($name, $attrs);
$this->last_token_was_empty = true;
} else {
$this->tokens[] = new HTMLPurifier_Token_Start($name, $attrs);
}
$this->stack[] = $name;
return true;
}
/**
* Close tag event handler, interface is defined by PEAR package.
*/
public function closeHandler(&$parser, $name) {
// HTMLSax3 seems to always send empty tags an extra close tag
// check and ignore if you see it:
// [TESTME] to make sure it doesn't overreach
if ($this->last_token_was_empty) {
$this->last_token_was_empty = false;
return true;
}
$this->tokens[] = new HTMLPurifier_Token_End($name);
if (!empty($this->stack)) array_pop($this->stack);
return true;
}
/**
* Data event handler, interface is defined by PEAR package.
*/
public function dataHandler(&$parser, $data) {
$this->last_token_was_empty = false;
$this->tokens[] = new HTMLPurifier_Token_Text($data);
return true;
}
/**
* Escaped text handler, interface is defined by PEAR package.
*/
public function escapeHandler(&$parser, $data) {
if (strpos($data, '--') === 0) {
// remove trailing and leading double-dashes
$data = substr($data, 2);
if (strlen($data) >= 2 && substr($data, -2) == "--") {
$data = substr($data, 0, -2);
}
if (isset($this->stack[sizeof($this->stack) - 1]) &&
$this->stack[sizeof($this->stack) - 1] == "style") {
$this->tokens[] = new HTMLPurifier_Token_Text($data);
} else {
$this->tokens[] = new HTMLPurifier_Token_Comment($data);
}
$this->last_token_was_empty = false;
}
// CDATA is handled elsewhere, but if it was handled here:
//if (strpos($data, '[CDATA[') === 0) {
// $this->tokens[] = new HTMLPurifier_Token_Text(
// substr($data, 7, strlen($data) - 9) );
//}
return true;
}
/**
* An error handler that mutes strict errors
*/
public function muteStrictErrorHandler($errno, $errstr, $errfile=null, $errline=null, $errcontext=null) {
if ($errno == E_STRICT) return;
return call_user_func($this->parent_handler, $errno, $errstr, $errfile, $errline, $errcontext);
}
}
// vim: et sw=4 sts=4

3906
library/HTMLPurifier/Lexer/PH5P.php
View file

File diff suppressed because it is too large Load diff

328
library/HTMLPurifier/Strategy/FixNesting.php
View file

@ -1,328 +0,0 @@
<?php
/**
* Takes a well formed list of tokens and fixes their nesting.
*
* HTML elements dictate which elements are allowed to be their children,
* for example, you can't have a p tag in a span tag. Other elements have
* much more rigorous definitions: tables, for instance, require a specific
* order for their elements. There are also constraints not expressible by
* document type definitions, such as the chameleon nature of ins/del
* tags and global child exclusions.
*
* The first major objective of this strategy is to iterate through all the
* nodes (not tokens) of the list of tokens and determine whether or not
* their children conform to the element's definition. If they do not, the
* child definition may optionally supply an amended list of elements that
* is valid or require that the entire node be deleted (and the previous
* node rescanned).
*
* The second objective is to ensure that explicitly excluded elements of
* an element do not appear in its children. Code that accomplishes this
* task is pervasive through the strategy, though the two are distinct tasks
* and could, theoretically, be seperated (although it's not recommended).
*
* @note Whether or not unrecognized children are silently dropped or
* translated into text depends on the child definitions.
*
* @todo Enable nodes to be bubbled out of the structure.
*/
class HTMLPurifier_Strategy_FixNesting extends HTMLPurifier_Strategy
{
public function execute($tokens, $config, $context) {
//####################################################################//
// Pre-processing
// get a copy of the HTML definition
$definition = $config->getHTMLDefinition();
// insert implicit "parent" node, will be removed at end.
// DEFINITION CALL
$parent_name = $definition->info_parent;
array_unshift($tokens, new HTMLPurifier_Token_Start($parent_name));
$tokens[] = new HTMLPurifier_Token_End($parent_name);
// setup the context variable 'IsInline', for chameleon processing
// is 'false' when we are not inline, 'true' when it must always
// be inline, and an integer when it is inline for a certain
// branch of the document tree
$is_inline = $definition->info_parent_def->descendants_are_inline;
$context->register('IsInline', $is_inline);
// setup error collector
$e =& $context->get('ErrorCollector', true);
//####################################################################//
// Loop initialization
// stack that contains the indexes of all parents,
// $stack[count($stack)-1] being the current parent
$stack = array();
// stack that contains all elements that are excluded
// it is organized by parent elements, similar to $stack,
// but it is only populated when an element with exclusions is
// processed, i.e. there won't be empty exclusions.
$exclude_stack = array();
// variable that contains the start token while we are processing
// nodes. This enables error reporting to do its job
$start_token = false;
$context->register('CurrentToken', $start_token);
//####################################################################//
// Loop
// iterate through all start nodes. Determining the start node
// is complicated so it has been omitted from the loop construct
for ($i = 0, $size = count($tokens) ; $i < $size; ) {
//################################################################//
// Gather information on children
// child token accumulator
$child_tokens = array();
// scroll to the end of this node, report number, and collect
// all children
for ($j = $i, $depth = 0; ; $j++) {
if ($tokens[$j] instanceof HTMLPurifier_Token_Start) {
$depth++;
// skip token assignment on first iteration, this is the
// token we currently are on
if ($depth == 1) continue;
} elseif ($tokens[$j] instanceof HTMLPurifier_Token_End) {
$depth--;
// skip token assignment on last iteration, this is the
// end token of the token we're currently on
if ($depth == 0) break;
}
$child_tokens[] = $tokens[$j];
}
// $i is index of start token
// $j is index of end token
$start_token = $tokens[$i]; // to make token available via CurrentToken
//################################################################//
// Gather information on parent
// calculate parent information
if ($count = count($stack)) {
$parent_index = $stack[$count-1];
$parent_name = $tokens[$parent_index]->name;
if ($parent_index == 0) {
$parent_def = $definition->info_parent_def;
} else {
$parent_def = $definition->info[$parent_name];
}
} else {
// processing as if the parent were the "root" node
// unknown info, it won't be used anyway, in the future,
// we may want to enforce one element only (this is
// necessary for HTML Purifier to clean entire documents
$parent_index = $parent_name = $parent_def = null;
}
// calculate context
if ($is_inline === false) {
// check if conditions make it inline
if (!empty($parent_def) && $parent_def->descendants_are_inline) {
$is_inline = $count - 1;
}
} else {
// check if we're out of inline
if ($count === $is_inline) {
$is_inline = false;
}
}
//################################################################//
// Determine whether element is explicitly excluded SGML-style
// determine whether or not element is excluded by checking all
// parent exclusions. The array should not be very large, two
// elements at most.
$excluded = false;
if (!empty($exclude_stack)) {
foreach ($exclude_stack as $lookup) {
if (isset($lookup[$tokens[$i]->name])) {
$excluded = true;
// no need to continue processing
break;
}
}
}
//################################################################//
// Perform child validation
if ($excluded) {
// there is an exclusion, remove the entire node
$result = false;
$excludes = array(); // not used, but good to initialize anyway
} else {
// DEFINITION CALL
if ($i === 0) {
// special processing for the first node
$def = $definition->info_parent_def;
} else {
$def = $definition->info[$tokens[$i]->name];
}
if (!empty($def->child)) {
// have DTD child def validate children
$result = $def->child->validateChildren(
$child_tokens, $config, $context);
} else {
// weird, no child definition, get rid of everything
$result = false;
}
// determine whether or not this element has any exclusions
$excludes = $def->excludes;
}
// $result is now a bool or array
//################################################################//
// Process result by interpreting $result
if ($result === true || $child_tokens === $result) {
// leave the node as is
// register start token as a parental node start
$stack[] = $i;
// register exclusions if there are any
if (!empty($excludes)) $exclude_stack[] = $excludes;
// move cursor to next possible start node
$i++;
} elseif($result === false) {
// remove entire node
if ($e) {
if ($excluded) {
$e->send(E_ERROR, 'Strategy_FixNesting: Node excluded');
} else {
$e->send(E_ERROR, 'Strategy_FixNesting: Node removed');
}
}
// calculate length of inner tokens and current tokens
$length = $j - $i + 1;
// perform removal
array_splice($tokens, $i, $length);
// update size
$size -= $length;
// there is no start token to register,
// current node is now the next possible start node
// unless it turns out that we need to do a double-check
// this is a rought heuristic that covers 100% of HTML's
// cases and 99% of all other cases. A child definition
// that would be tricked by this would be something like:
// ( | a b c) where it's all or nothing. Fortunately,
// our current implementation claims that that case would
// not allow empty, even if it did
if (!$parent_def->child->allow_empty) {
// we need to do a double-check
$i = $parent_index;
array_pop($stack);
}
// PROJECTED OPTIMIZATION: Process all children elements before
// reprocessing parent node.
} else {
// replace node with $result
// calculate length of inner tokens
$length = $j - $i - 1;
if ($e) {
if (empty($result) && $length) {
$e->send(E_ERROR, 'Strategy_FixNesting: Node contents removed');
} else {
$e->send(E_WARNING, 'Strategy_FixNesting: Node reorganized');
}
}
// perform replacement
array_splice($tokens, $i + 1, $length, $result);
// update size
$size -= $length;
$size += count($result);
// register start token as a parental node start
$stack[] = $i;
// register exclusions if there are any
if (!empty($excludes)) $exclude_stack[] = $excludes;
// move cursor to next possible start node
$i++;
}
//################################################################//
// Scroll to next start node
// We assume, at this point, that $i is the index of the token
// that is the first possible new start point for a node.
// Test if the token indeed is a start tag, if not, move forward
// and test again.
$size = count($tokens);
while ($i < $size and !$tokens[$i] instanceof HTMLPurifier_Token_Start) {
if ($tokens[$i] instanceof HTMLPurifier_Token_End) {
// pop a token index off the stack if we ended a node
array_pop($stack);
// pop an exclusion lookup off exclusion stack if
// we ended node and that node had exclusions
if ($i == 0 || $i == $size - 1) {
// use specialized var if it's the super-parent
$s_excludes = $definition->info_parent_def->excludes;
} else {
$s_excludes = $definition->info[$tokens[$i]->name]->excludes;
}
if ($s_excludes) {
array_pop($exclude_stack);
}
}
$i++;
}
}
//####################################################################//
// Post-processing
// remove implicit parent tokens at the beginning and end
array_shift($tokens);
array_pop($tokens);
// remove context variables
$context->destroy('IsInline');
$context->destroy('CurrentToken');
//####################################################################//
// Return
return $tokens;
}
}
// vim: et sw=4 sts=4

57
library/HTMLPurifier/Token.php
View file

@ -1,57 +0,0 @@
<?php
/**
* Abstract base token class that all others inherit from.
*/
class HTMLPurifier_Token {
public $line; /**< Line number node was on in source document. Null if unknown. */
public $col; /**< Column of line node was on in source document. Null if unknown. */
/**
* Lookup array of processing that this token is exempt from.
* Currently, valid values are "ValidateAttributes" and
* "MakeWellFormed_TagClosedError"
*/
public $armor = array();
/**
* Used during MakeWellFormed.
*/
public $skip;
public $rewind;
public $carryover;
public function __get($n) {
if ($n === 'type') {
trigger_error('Deprecated type property called; use instanceof', E_USER_NOTICE);
switch (get_class($this)) {
case 'HTMLPurifier_Token_Start': return 'start';
case 'HTMLPurifier_Token_Empty': return 'empty';
case 'HTMLPurifier_Token_End': return 'end';
case 'HTMLPurifier_Token_Text': return 'text';
case 'HTMLPurifier_Token_Comment': return 'comment';
default: return null;
}
}
}
/**
* Sets the position of the token in the source document.
*/
public function position($l = null, $c = null) {
$this->line = $l;
$this->col = $c;
}
/**
* Convenience function for DirectLex settings line/col position.
*/
public function rawPosition($l, $c) {
if ($c === -1) $l++;
$this->line = $l;
$this->col = $c;
}
}
// vim: et sw=4 sts=4

22
library/HTMLPurifier/Token/Comment.php
View file

@ -1,22 +0,0 @@
<?php
/**
* Concrete comment token class. Generally will be ignored.
*/
class HTMLPurifier_Token_Comment extends HTMLPurifier_Token
{
public $data; /**< Character data within comment. */
public $is_whitespace = true;
/**
* Transparent constructor.
*
* @param $data String comment data.
*/
public function __construct($data, $line = null, $col = null) {
$this->data = $data;
$this->line = $line;
$this->col = $col;
}
}
// vim: et sw=4 sts=4

94
library/HTMLPurifier/TokenFactory.php
View file

@ -1,94 +0,0 @@
<?php
/**
* Factory for token generation.
*
* @note Doing some benchmarking indicates that the new operator is much
* slower than the clone operator (even discounting the cost of the
* constructor). This class is for that optimization.
* Other then that, there's not much point as we don't
* maintain parallel HTMLPurifier_Token hierarchies (the main reason why
* you'd want to use an abstract factory).
* @todo Port DirectLex to use this
*/
class HTMLPurifier_TokenFactory
{
/**
* Prototypes that will be cloned.
* @private
*/
// p stands for prototype
private $p_start, $p_end, $p_empty, $p_text, $p_comment;
/**
* Generates blank prototypes for cloning.
*/
public function __construct() {
$this->p_start = new HTMLPurifier_Token_Start('', array());
$this->p_end = new HTMLPurifier_Token_End('');
$this->p_empty = new HTMLPurifier_Token_Empty('', array());
$this->p_text = new HTMLPurifier_Token_Text('');
$this->p_comment= new HTMLPurifier_Token_Comment('');
}
/**
* Creates a HTMLPurifier_Token_Start.
* @param $name Tag name
* @param $attr Associative array of attributes
* @return Generated HTMLPurifier_Token_Start
*/
public function createStart($name, $attr = array()) {
$p = clone $this->p_start;
$p->__construct($name, $attr);
return $p;
}
/**
* Creates a HTMLPurifier_Token_End.
* @param $name Tag name
* @return Generated HTMLPurifier_Token_End
*/
public function createEnd($name) {
$p = clone $this->p_end;
$p->__construct($name);
return $p;
}
/**
* Creates a HTMLPurifier_Token_Empty.
* @param $name Tag name
* @param $attr Associative array of attributes
* @return Generated HTMLPurifier_Token_Empty
*/
public function createEmpty($name, $attr = array()) {
$p = clone $this->p_empty;
$p->__construct($name, $attr);
return $p;
}
/**
* Creates a HTMLPurifier_Token_Text.
* @param $data Data of text token
* @return Generated HTMLPurifier_Token_Text
*/
public function createText($data) {
$p = clone $this->p_text;
$p->__construct($data);
return $p;
}
/**
* Creates a HTMLPurifier_Token_Comment.
* @param $data Data of comment token
* @return Generated HTMLPurifier_Token_Comment
*/
public function createComment($data) {
$p = clone $this->p_comment;
$p->__construct($data);
return $p;
}
}
// vim: et sw=4 sts=4

173
library/HTMLPurifier/URI.php
View file

@ -1,173 +0,0 @@
<?php
/**
* HTML Purifier's internal representation of a URI.
* @note
* Internal data-structures are completely escaped. If the data needs
* to be used in a non-URI context (which is very unlikely), be sure
* to decode it first. The URI may not necessarily be well-formed until
* validate() is called.
*/
class HTMLPurifier_URI
{
public $scheme, $userinfo, $host, $port, $path, $query, $fragment;
/**
* @note Automatically normalizes scheme and port
*/
public function __construct($scheme, $userinfo, $host, $port, $path, $query, $fragment) {
$this->scheme = is_null($scheme) || ctype_lower($scheme) ? $scheme : strtolower($scheme);
$this->userinfo = $userinfo;
$this->host = $host;
$this->port = is_null($port) ? $port : (int) $port;
$this->path = $path;
$this->query = $query;
$this->fragment = $fragment;
}
/**
* Retrieves a scheme object corresponding to the URI's scheme/default
* @param $config Instance of HTMLPurifier_Config
* @param $context Instance of HTMLPurifier_Context
* @return Scheme object appropriate for validating this URI
*/
public function getSchemeObj($config, $context) {
$registry = HTMLPurifier_URISchemeRegistry::instance();
if ($this->scheme !== null) {
$scheme_obj = $registry->getScheme($this->scheme, $config, $context);
if (!$scheme_obj) return false; // invalid scheme, clean it out
} else {
// no scheme: retrieve the default one
$def = $config->getDefinition('URI');
$scheme_obj = $registry->getScheme($def->defaultScheme, $config, $context);
if (!$scheme_obj) {
// something funky happened to the default scheme object
trigger_error(
'Default scheme object "' . $def->defaultScheme . '" was not readable',
E_USER_WARNING
);
return false;
}
}
return $scheme_obj;
}
/**
* Generic validation method applicable for all schemes. May modify
* this URI in order to get it into a compliant form.
* @param $config Instance of HTMLPurifier_Config
* @param $context Instance of HTMLPurifier_Context
* @return True if validation/filtering succeeds, false if failure
*/
public function validate($config, $context) {
// ABNF definitions from RFC 3986
$chars_sub_delims = '!$&\'()*+,;=';
$chars_gen_delims = ':/?#[]@';
$chars_pchar = $chars_sub_delims . ':@';
// validate scheme (MUST BE FIRST!)
if (!is_null($this->scheme) && is_null($this->host)) {
$def = $config->getDefinition('URI');
if ($def->defaultScheme === $this->scheme) {
$this->scheme = null;
}
}
// validate host
if (!is_null($this->host)) {
$host_def = new HTMLPurifier_AttrDef_URI_Host();
$this->host = $host_def->validate($this->host, $config, $context);
if ($this->host === false) $this->host = null;
}
// validate username
if (!is_null($this->userinfo)) {
$encoder = new HTMLPurifier_PercentEncoder($chars_sub_delims . ':');
$this->userinfo = $encoder->encode($this->userinfo);
}
// validate port
if (!is_null($this->port)) {
if ($this->port < 1 || $this->port > 65535) $this->port = null;
}
// validate path
$path_parts = array();
$segments_encoder = new HTMLPurifier_PercentEncoder($chars_pchar . '/');
if (!is_null($this->host)) {
// path-abempty (hier and relative)
$this->path = $segments_encoder->encode($this->path);
} elseif ($this->path !== '' && $this->path[0] === '/') {
// path-absolute (hier and relative)
if (strlen($this->path) >= 2 && $this->path[1] === '/') {
// This shouldn't ever happen!
$this->path = '';
} else {
$this->path = $segments_encoder->encode($this->path);
}
} elseif (!is_null($this->scheme) && $this->path !== '') {
// path-rootless (hier)
// Short circuit evaluation means we don't need to check nz
$this->path = $segments_encoder->encode($this->path);
} elseif (is_null($this->scheme) && $this->path !== '') {
// path-noscheme (relative)
// (once again, not checking nz)
$segment_nc_encoder = new HTMLPurifier_PercentEncoder($chars_sub_delims . '@');
$c = strpos($this->path, '/');
if ($c !== false) {
$this->path =
$segment_nc_encoder->encode(substr($this->path, 0, $c)) .
$segments_encoder->encode(substr($this->path, $c));
} else {
$this->path = $segment_nc_encoder->encode($this->path);
}
} else {
// path-empty (hier and relative)
$this->path = ''; // just to be safe
}
// qf = query and fragment
$qf_encoder = new HTMLPurifier_PercentEncoder($chars_pchar . '/?');
if (!is_null($this->query)) {
$this->query = $qf_encoder->encode($this->query);
}
if (!is_null($this->fragment)) {
$this->fragment = $qf_encoder->encode($this->fragment);
}
return true;
}
/**
* Convert URI back to string
* @return String URI appropriate for output
*/
public function toString() {
// reconstruct authority
$authority = null;
if (!is_null($this->host)) {
$authority = '';
if(!is_null($this->userinfo)) $authority .= $this->userinfo . '@';
$authority .= $this->host;
if(!is_null($this->port)) $authority .= ':' . $this->port;
}
// reconstruct the result
$result = '';
if (!is_null($this->scheme)) $result .= $this->scheme . ':';
if (!is_null($authority)) $result .= '//' . $authority;
$result .= $this->path;
if (!is_null($this->query)) $result .= '?' . $this->query;
if (!is_null($this->fragment)) $result .= '#' . $this->fragment;
return $result;
}
}
// vim: et sw=4 sts=4

45
library/HTMLPurifier/URIFilter.php
View file

@ -1,45 +0,0 @@
<?php
/**
* Chainable filters for custom URI processing.
*
* These filters can perform custom actions on a URI filter object,
* including transformation or blacklisting.
*
* @warning This filter is called before scheme object validation occurs.
* Make sure, if you require a specific scheme object, you
* you check that it exists. This allows filters to convert
* proprietary URI schemes into regular ones.
*/
abstract class HTMLPurifier_URIFilter
{
/**
* Unique identifier of filter
*/
public $name;
/**
* True if this filter should be run after scheme validation.
*/
public $post = false;
/**
* Performs initialization for the filter
*/
public function prepare($config) {return true;}
/**
* Filter a URI object
* @param $uri Reference to URI object variable
* @param $config Instance of HTMLPurifier_Config
* @param $context Instance of HTMLPurifier_Context
* @return bool Whether or not to continue processing: false indicates
* URL is no good, true indicates continue processing. Note that
* all changes are committed directly on the URI object
*/
abstract public function filter(&$uri, $config, $context);
}
// vim: et sw=4 sts=4

23
library/HTMLPurifier/URIFilter/DisableExternal.php
View file

@ -1,23 +0,0 @@
<?php
class HTMLPurifier_URIFilter_DisableExternal extends HTMLPurifier_URIFilter
{
public $name = 'DisableExternal';
protected $ourHostParts = false;
public function prepare($config) {
$our_host = $config->getDefinition('URI')->host;
if ($our_host !== null) $this->ourHostParts = array_reverse(explode('.', $our_host));
}
public function filter(&$uri, $config, $context) {
if (is_null($uri->host)) return true;
if ($this->ourHostParts === false) return false;
$host_parts = array_reverse(explode('.', $uri->host));
foreach ($this->ourHostParts as $i => $x) {
if (!isset($host_parts[$i])) return false;
if ($host_parts[$i] != $this->ourHostParts[$i]) return false;
}
return true;
}
}
// vim: et sw=4 sts=4

12
library/HTMLPurifier/URIFilter/DisableExternalResources.php
View file

@ -1,12 +0,0 @@
<?php
class HTMLPurifier_URIFilter_DisableExternalResources extends HTMLPurifier_URIFilter_DisableExternal
{
public $name = 'DisableExternalResources';
public function filter(&$uri, $config, $context) {
if (!$context->get('EmbeddedURI', true)) return true;
return parent::filter($uri, $config, $context);
}
}
// vim: et sw=4 sts=4

21
library/HTMLPurifier/URIFilter/HostBlacklist.php
View file

@ -1,21 +0,0 @@
<?php
class HTMLPurifier_URIFilter_HostBlacklist extends HTMLPurifier_URIFilter
{
public $name = 'HostBlacklist';
protected $blacklist = array();
public function prepare($config) {
$this->blacklist = $config->get('URI.HostBlacklist');
return true;
}
public function filter(&$uri, $config, $context) {
foreach($this->blacklist as $blacklisted_host_fragment) {
if (strpos($uri->host, $blacklisted_host_fragment) !== false) {
return false;
}
}
return true;
}
}
// vim: et sw=4 sts=4

58
library/HTMLPurifier/URIFilter/Munge.php
View file

@ -1,58 +0,0 @@
<?php
class HTMLPurifier_URIFilter_Munge extends HTMLPurifier_URIFilter
{
public $name = 'Munge';
public $post = true;
private $target, $parser, $doEmbed, $secretKey;
protected $replace = array();
public function prepare($config) {
$this->target = $config->get('URI.' . $this->name);
$this->parser = new HTMLPurifier_URIParser();
$this->doEmbed = $config->get('URI.MungeResources');
$this->secretKey = $config->get('URI.MungeSecretKey');
return true;
}
public function filter(&$uri, $config, $context) {
if ($context->get('EmbeddedURI', true) && !$this->doEmbed) return true;
$scheme_obj = $uri->getSchemeObj($config, $context);
if (!$scheme_obj) return true; // ignore unknown schemes, maybe another postfilter did it
if (is_null($uri->host) || empty($scheme_obj->browsable)) {
return true;
}
// don't redirect if target host is our host
if ($uri->host === $config->getDefinition('URI')->host) {
return true;
}
$this->makeReplace($uri, $config, $context);
$this->replace = array_map('rawurlencode', $this->replace);
$new_uri = strtr($this->target, $this->replace);
$new_uri = $this->parser->parse($new_uri);
// don't redirect if the target host is the same as the
// starting host
if ($uri->host === $new_uri->host) return true;
$uri = $new_uri; // overwrite
return true;
}
protected function makeReplace($uri, $config, $context) {
$string = $uri->toString();
// always available
$this->replace['%s'] = $string;
$this->replace['%r'] = $context->get('EmbeddedURI', true);
$token = $context->get('CurrentToken', true);
$this->replace['%n'] = $token ? $token->name : null;
$this->replace['%m'] = $context->get('CurrentAttr', true);
$this->replace['%p'] = $context->get('CurrentCSSProperty', true);
// not always available
if ($this->secretKey) $this->replace['%t'] = sha1($this->secretKey . ':' . $string);
}
}
// vim: et sw=4 sts=4

42
library/HTMLPurifier/URIScheme.php
View file

@ -1,42 +0,0 @@
<?php
/**
* Validator for the components of a URI for a specific scheme
*/
class HTMLPurifier_URIScheme
{
/**
* Scheme's default port (integer)
*/
public $default_port = null;
/**
* Whether or not URIs of this schem are locatable by a browser
* http and ftp are accessible, while mailto and news are not.
*/
public $browsable = false;
/**
* Whether or not the URI always uses <hier_part>, resolves edge cases
* with making relative URIs absolute
*/
public $hierarchical = false;
/**
* Validates the components of a URI
* @note This implementation should be called by children if they define
* a default port, as it does port processing.
* @param $uri Instance of HTMLPurifier_URI
* @param $config HTMLPurifier_Config object
* @param $context HTMLPurifier_Context object
* @return Bool success or failure
*/
public function validate(&$uri, $config, $context) {
if ($this->default_port == $uri->port) $uri->port = null;
return true;
}
}
// vim: et sw=4 sts=4

22
library/HTMLPurifier/URIScheme/news.php
View file

@ -1,22 +0,0 @@
<?php
/**
* Validates news (Usenet) as defined by generic RFC 1738
*/
class HTMLPurifier_URIScheme_news extends HTMLPurifier_URIScheme {
public $browsable = false;
public function validate(&$uri, $config, $context) {
parent::validate($uri, $config, $context);
$uri->userinfo = null;
$uri->host = null;
$uri->port = null;
$uri->query = null;
// typecode check needed on path
return true;
}
}
// vim: et sw=4 sts=4

20
library/HTMLPurifier/URIScheme/nntp.php
View file

@ -1,20 +0,0 @@
<?php
/**
* Validates nntp (Network News Transfer Protocol) as defined by generic RFC 1738
*/
class HTMLPurifier_URIScheme_nntp extends HTMLPurifier_URIScheme {
public $default_port = 119;
public $browsable = false;
public function validate(&$uri, $config, $context) {
parent::validate($uri, $config, $context);
$uri->userinfo = null;
$uri->query = null;
return true;
}
}
// vim: et sw=4 sts=4

154
library/HTMLPurifier/VarParser.php
View file

@ -1,154 +0,0 @@
<?php
/**
* Parses string representations into their corresponding native PHP
* variable type. The base implementation does a simple type-check.
*/
class HTMLPurifier_VarParser
{
const STRING = 1;
const ISTRING = 2;
const TEXT = 3;
const ITEXT = 4;
const INT = 5;
const FLOAT = 6;
const BOOL = 7;
const LOOKUP = 8;
const ALIST = 9;
const HASH = 10;
const MIXED = 11;
/**
* Lookup table of allowed types. Mainly for backwards compatibility, but
* also convenient for transforming string type names to the integer constants.
*/
static public $types = array(
'string' => self::STRING,
'istring' => self::ISTRING,
'text' => self::TEXT,
'itext' => self::ITEXT,
'int' => self::INT,
'float' => self::FLOAT,
'bool' => self::BOOL,
'lookup' => self::LOOKUP,
'list' => self::ALIST,
'hash' => self::HASH,
'mixed' => self::MIXED
);
/**
* Lookup table of types that are string, and can have aliases or
* allowed value lists.
*/
static public $stringTypes = array(
self::STRING => true,
self::ISTRING => true,
self::TEXT => true,
self::ITEXT => true,
);
/**
* Validate a variable according to type. Throws
* HTMLPurifier_VarParserException if invalid.
* It may return NULL as a valid type if $allow_null is true.
*
* @param $var Variable to validate
* @param $type Type of variable, see HTMLPurifier_VarParser->types
* @param $allow_null Whether or not to permit null as a value
* @return Validated and type-coerced variable
*/
final public function parse($var, $type, $allow_null = false) {
if (is_string($type)) {
if (!isset(HTMLPurifier_VarParser::$types[$type])) {
throw new HTMLPurifier_VarParserException("Invalid type '$type'");
} else {
$type = HTMLPurifier_VarParser::$types[$type];
}
}
$var = $this->parseImplementation($var, $type, $allow_null);
if ($allow_null && $var === null) return null;
// These are basic checks, to make sure nothing horribly wrong
// happened in our implementations.
switch ($type) {
case (self::STRING):
case (self::ISTRING):
case (self::TEXT):
case (self::ITEXT):
if (!is_string($var)) break;
if ($type == self::ISTRING || $type == self::ITEXT) $var = strtolower($var);
return $var;
case (self::INT):
if (!is_int($var)) break;
return $var;
case (self::FLOAT):
if (!is_float($var)) break;
return $var;
case (self::BOOL):
if (!is_bool($var)) break;
return $var;
case (self::LOOKUP):
case (self::ALIST):
case (self::HASH):
if (!is_array($var)) break;
if ($type === self::LOOKUP) {
foreach ($var as $k) if ($k !== true) $this->error('Lookup table contains value other than true');
} elseif ($type === self::ALIST) {
$keys = array_keys($var);
if (array_keys($keys) !== $keys) $this->error('Indices for list are not uniform');
}
return $var;
case (self::MIXED):
return $var;
default:
$this->errorInconsistent(get_class($this), $type);
}
$this->errorGeneric($var, $type);
}
/**
* Actually implements the parsing. Base implementation is to not
* do anything to $var. Subclasses should overload this!
*/
protected function parseImplementation($var, $type, $allow_null) {
return $var;
}
/**
* Throws an exception.
*/
protected function error($msg) {
throw new HTMLPurifier_VarParserException($msg);
}
/**
* Throws an inconsistency exception.
* @note This should not ever be called. It would be called if we
* extend the allowed values of HTMLPurifier_VarParser without
* updating subclasses.
*/
protected function errorInconsistent($class, $type) {
throw new HTMLPurifier_Exception("Inconsistency in $class: ".HTMLPurifier_VarParser::getTypeName($type)." not implemented");
}
/**
* Generic error for if a type didn't work.
*/
protected function errorGeneric($var, $type) {
$vtype = gettype($var);
$this->error("Expected type ".HTMLPurifier_VarParser::getTypeName($type).", got $vtype");
}
static public function getTypeName($type) {
static $lookup;
if (!$lookup) {
// Lazy load the alternative lookup table
$lookup = array_flip(HTMLPurifier_VarParser::$types);
}
if (!isset($lookup[$type])) return 'unknown';
return $lookup[$type];
}
}
// vim: et sw=4 sts=4

9
library/ezyang/htmlpurifier/CREDITS Normal file
View file

@ -0,0 +1,9 @@
CREDITS
Almost everything written by Edward Z. Yang (Ambush Commander). Lots of thanks
to the DevNetwork Community for their help (see docs/ref-devnetwork.html for
more details), Feyd especially (namely IPv6 and optimization). Thanks to RSnake
for letting me package his fantastic XSS cheatsheet for a smoketest.
vim: et sw=4 sts=4

374
library/ezyang/htmlpurifier/INSTALL Normal file
View file

@ -0,0 +1,374 @@
Install
How to install HTML Purifier
HTML Purifier is designed to run out of the box, so actually using the
library is extremely easy. (Although... if you were looking for a
step-by-step installation GUI, you've downloaded the wrong software!)
While the impatient can get going immediately with some of the sample
code at the bottom of this library, it's well worth reading this entire
document--most of the other documentation assumes that you are familiar
with these contents.
---------------------------------------------------------------------------
1. Compatibility
HTML Purifier is PHP 5 only, and is actively tested from PHP 5.0.5 and
up. It has no core dependencies with other libraries. PHP
4 support was deprecated on December 31, 2007 with HTML Purifier 3.0.0.
HTML Purifier is not compatible with zend.ze1_compatibility_mode.
These optional extensions can enhance the capabilities of HTML Purifier:
* iconv : Converts text to and from non-UTF-8 encodings
* bcmath : Used for unit conversion and imagecrash protection
* tidy : Used for pretty-printing HTML
These optional libraries can enhance the capabilities of HTML Purifier:
* CSSTidy : Clean CSS stylesheets using %Core.ExtractStyleBlocks
* Net_IDNA2 (PEAR) : IRI support using %Core.EnableIDNA
---------------------------------------------------------------------------
2. Reconnaissance
A big plus of HTML Purifier is its inerrant support of standards, so
your web-pages should be standards-compliant. (They should also use
semantic markup, but that's another issue altogether, one HTML Purifier
cannot fix without reading your mind.)
HTML Purifier can process these doctypes:
* XHTML 1.0 Transitional (default)
* XHTML 1.0 Strict
* HTML 4.01 Transitional
* HTML 4.01 Strict
* XHTML 1.1
...and these character encodings:
* UTF-8 (default)
* Any encoding iconv supports (with crippled internationalization support)
These defaults reflect what my choices would be if I were authoring an
HTML document, however, what you choose depends on the nature of your
codebase. If you don't know what doctype you are using, you can determine
the doctype from this identifier at the top of your source code:
<!DOCTYPE html PUBLIC "-//W3C//DTD XHTML 1.0 Transitional//EN"
"http://www.w3.org/TR/xhtml1/DTD/xhtml1-transitional.dtd">
...and the character encoding from this code:
<meta http-equiv="Content-type" content="text/html;charset=ENCODING">
If the character encoding declaration is missing, STOP NOW, and
read 'docs/enduser-utf8.html' (web accessible at
http://htmlpurifier.org/docs/enduser-utf8.html). In fact, even if it is
present, read this document anyway, as many websites specify their
document's character encoding incorrectly.
---------------------------------------------------------------------------
3. Including the library
The procedure is quite simple:
require_once '/path/to/library/HTMLPurifier.auto.php';
This will setup an autoloader, so the library's files are only included
when you use them.
Only the contents in the library/ folder are necessary, so you can remove
everything else when using HTML Purifier in a production environment.
If you installed HTML Purifier via PEAR, all you need to do is:
require_once 'HTMLPurifier.auto.php';
Please note that the usual PEAR practice of including just the classes you
want will not work with HTML Purifier's autoloading scheme.
Advanced users, read on; other users can skip to section 4.
Autoload compatibility
----------------------
HTML Purifier attempts to be as smart as possible when registering an
autoloader, but there are some cases where you will need to change
your own code to accomodate HTML Purifier. These are those cases:
PHP VERSION IS LESS THAN 5.1.2, AND YOU'VE DEFINED __autoload
Because spl_autoload_register() doesn't exist in early versions
of PHP 5, HTML Purifier has no way of adding itself to the autoload
stack. Modify your __autoload function to test
HTMLPurifier_Bootstrap::autoload($class)
For example, suppose your autoload function looks like this:
function __autoload($class) {
require str_replace('_', '/', $class) . '.php';
return true;
}
A modified version with HTML Purifier would look like this:
function __autoload($class) {
if (HTMLPurifier_Bootstrap::autoload($class)) return true;
require str_replace('_', '/', $class) . '.php';
return true;
}
Note that there *is* some custom behavior in our autoloader; the
original autoloader in our example would work for 99% of the time,
but would fail when including language files.
AN __autoload FUNCTION IS DECLARED AFTER OUR AUTOLOADER IS REGISTERED
spl_autoload_register() has the curious behavior of disabling
the existing __autoload() handler. Users need to explicitly
spl_autoload_register('__autoload'). Because we use SPL when it
is available, __autoload() will ALWAYS be disabled. If __autoload()
is declared before HTML Purifier is loaded, this is not a problem:
HTML Purifier will register the function for you. But if it is
declared afterwards, it will mysteriously not work. This
snippet of code (after your autoloader is defined) will fix it:
spl_autoload_register('__autoload')
Users should also be on guard if they use a version of PHP previous
to 5.1.2 without an autoloader--HTML Purifier will define __autoload()
for you, which can collide with an autoloader that was added by *you*
later.
For better performance
----------------------
Opcode caches, which greatly speed up PHP initialization for scripts
with large amounts of code (HTML Purifier included), don't like
autoloaders. We offer an include file that includes all of HTML Purifier's
files in one go in an opcode cache friendly manner:
// If /path/to/library isn't already in your include path, uncomment
// the below line:
// require '/path/to/library/HTMLPurifier.path.php';
require 'HTMLPurifier.includes.php';
Optional components still need to be included--you'll know if you try to
use a feature and you get a class doesn't exists error! The autoloader
can be used in conjunction with this approach to catch classes that are
missing. Simply add this afterwards:
require 'HTMLPurifier.autoload.php';
Standalone version
------------------
HTML Purifier has a standalone distribution; you can also generate
a standalone file from the full version by running the script
maintenance/generate-standalone.php . The standalone version has the
benefit of having most of its code in one file, so parsing is much
faster and the library is easier to manage.
If HTMLPurifier.standalone.php exists in the library directory, you
can use it like this:
require '/path/to/HTMLPurifier.standalone.php';
This is equivalent to including HTMLPurifier.includes.php, except that
the contents of standalone/ will be added to your path. To override this
behavior, specify a new HTMLPURIFIER_PREFIX where standalone files can
be found (usually, this will be one directory up, the "true" library
directory in full distributions). Don't forget to set your path too!
The autoloader can be added to the end to ensure the classes are
loaded when necessary; otherwise you can manually include them.
To use the autoloader, use this:
require 'HTMLPurifier.autoload.php';
For advanced users
------------------
HTMLPurifier.auto.php performs a number of operations that can be done
individually. These are:
HTMLPurifier.path.php
Puts /path/to/library in the include path. For high performance,
this should be done in php.ini.
HTMLPurifier.autoload.php
Registers our autoload handler HTMLPurifier_Bootstrap::autoload($class).
You can do these operations by yourself--in fact, you must modify your own
autoload handler if you are using a version of PHP earlier than PHP 5.1.2
(See "Autoload compatibility" above).
---------------------------------------------------------------------------
4. Configuration
HTML Purifier is designed to run out-of-the-box, but occasionally HTML
Purifier needs to be told what to do. If you answer no to any of these
questions, read on; otherwise, you can skip to the next section (or, if you're
into configuring things just for the heck of it, skip to 4.3).
* Am I using UTF-8?
* Am I using XHTML 1.0 Transitional?
If you answered no to any of these questions, instantiate a configuration
object and read on:
$config = HTMLPurifier_Config::createDefault();
4.1. Setting a different character encoding
You really shouldn't use any other encoding except UTF-8, especially if you
plan to support multilingual websites (read section three for more details).
However, switching to UTF-8 is not always immediately feasible, so we can
adapt.
HTML Purifier uses iconv to support other character encodings, as such,
any encoding that iconv supports <http://www.gnu.org/software/libiconv/>
HTML Purifier supports with this code:
$config->set('Core.Encoding', /* put your encoding here */);
An example usage for Latin-1 websites (the most common encoding for English
websites):
$config->set('Core.Encoding', 'ISO-8859-1');
Note that HTML Purifier's support for non-Unicode encodings is crippled by the
fact that any character not supported by that encoding will be silently
dropped, EVEN if it is ampersand escaped. If you want to work around
this, you are welcome to read docs/enduser-utf8.html for a fix,
but please be cognizant of the issues the "solution" creates (for this
reason, I do not include the solution in this document).
4.2. Setting a different doctype
For those of you using HTML 4.01 Transitional, you can disable
XHTML output like this:
$config->set('HTML.Doctype', 'HTML 4.01 Transitional');
Other supported doctypes include:
* HTML 4.01 Strict
* HTML 4.01 Transitional
* XHTML 1.0 Strict
* XHTML 1.0 Transitional
* XHTML 1.1
4.3. Other settings
There are more configuration directives which can be read about
here: <http://htmlpurifier.org/live/configdoc/plain.html> They're a bit boring,
but they can help out for those of you who like to exert maximum control over
your code. Some of the more interesting ones are configurable at the
demo <http://htmlpurifier.org/demo.php> and are well worth looking into
for your own system.
For example, you can fine tune allowed elements and attributes, convert
relative URLs to absolute ones, and even autoparagraph input text! These
are, respectively, %HTML.Allowed, %URI.MakeAbsolute and %URI.Base, and
%AutoFormat.AutoParagraph. The %Namespace.Directive naming convention
translates to:
$config->set('Namespace.Directive', $value);
E.g.
$config->set('HTML.Allowed', 'p,b,a[href],i');
$config->set('URI.Base', 'http://www.example.com');
$config->set('URI.MakeAbsolute', true);
$config->set('AutoFormat.AutoParagraph', true);
---------------------------------------------------------------------------
5. Caching
HTML Purifier generates some cache files (generally one or two) to speed up
its execution. For maximum performance, make sure that
library/HTMLPurifier/DefinitionCache/Serializer is writeable by the webserver.
If you are in the library/ folder of HTML Purifier, you can set the
appropriate permissions using:
chmod -R 0755 HTMLPurifier/DefinitionCache/Serializer
If the above command doesn't work, you may need to assign write permissions
to all. This may be necessary if your webserver runs as nobody, but is
not recommended since it means any other user can write files in the
directory. Use:
chmod -R 0777 HTMLPurifier/DefinitionCache/Serializer
You can also chmod files via your FTP client; this option
is usually accessible by right clicking the corresponding directory and
then selecting "chmod" or "file permissions".
Starting with 2.0.1, HTML Purifier will generate friendly error messages
that will tell you exactly what you have to chmod the directory to, if in doubt,
follow its advice.
If you are unable or unwilling to give write permissions to the cache
directory, you can either disable the cache (and suffer a performance
hit):
$config->set('Core.DefinitionCache', null);
Or move the cache directory somewhere else (no trailing slash):
$config->set('Cache.SerializerPath', '/home/user/absolute/path');
---------------------------------------------------------------------------
6. Using the code
The interface is mind-numbingly simple:
$purifier = new HTMLPurifier($config);
$clean_html = $purifier->purify( $dirty_html );
That's it! For more examples, check out docs/examples/ (they aren't very
different though). Also, docs/enduser-slow.html gives advice on what to
do if HTML Purifier is slowing down your application.
---------------------------------------------------------------------------
7. Quick install
First, make sure library/HTMLPurifier/DefinitionCache/Serializer is
writable by the webserver (see Section 5: Caching above for details).
If your website is in UTF-8 and XHTML Transitional, use this code:
<?php
require_once '/path/to/htmlpurifier/library/HTMLPurifier.auto.php';
$config = HTMLPurifier_Config::createDefault();
$purifier = new HTMLPurifier($config);
$clean_html = $purifier->purify($dirty_html);
?>
If your website is in a different encoding or doctype, use this code:
<?php
require_once '/path/to/htmlpurifier/library/HTMLPurifier.auto.php';
$config = HTMLPurifier_Config::createDefault();
$config->set('Core.Encoding', 'ISO-8859-1'); // replace with your encoding
$config->set('HTML.Doctype', 'HTML 4.01 Transitional'); // replace with your doctype
$purifier = new HTMLPurifier($config);
$clean_html = $purifier->purify($dirty_html);
?>
vim: et sw=4 sts=4

60
library/ezyang/htmlpurifier/INSTALL.fr.utf8 Normal file
View file

@ -0,0 +1,60 @@

Installation
Comment installer HTML Purifier
Attention : Ce document est encodé en UTF-8, si les lettres avec des accents
ne s'affichent pas, prenez un meilleur éditeur de texte.
L'installation de HTML Purifier est très simple, parce qu'il n'a pas besoin
de configuration. Pour les utilisateurs impatients, le code se trouve dans le
pied de page, mais je recommande de lire le document.
1. Compatibilité
HTML Purifier fonctionne avec PHP 5. PHP 5.0.5 est la dernière version testée.
Il ne dépend pas d'autres librairies.
Les extensions optionnelles sont iconv (généralement déjà installée) et tidy
(répendue aussi). Si vous utilisez UTF-8 et que vous ne voulez pas l'indentation,
vous pouvez utiliser HTML Purifier sans ces extensions.
2. Inclure la librairie
Quand vous devez l'utilisez, incluez le :
require_once('/path/to/library/HTMLPurifier.auto.php');
Ne pas l'inclure si ce n'est pas nécessaire, car HTML Purifier est lourd.
HTML Purifier utilise "autoload". Si vous avez défini la fonction __autoload,
vous devez ajouter cette fonction :
spl_autoload_register('__autoload')
Plus d'informations dans le document "INSTALL".
3. Installation rapide
Si votre site Web est en UTF-8 et XHTML Transitional, utilisez :
<?php
require_once('/path/to/htmlpurifier/library/HTMLPurifier.auto.php');
$purificateur = new HTMLPurifier();
$html_propre = $purificateur->purify($html_a_purifier);
?>
Sinon, utilisez :
<?php
require_once('/path/to/html/purifier/library/HTMLPurifier.auto.load');
$config = $HTMLPurifier_Config::createDefault();
$config->set('Core', 'Encoding', 'ISO-8859-1'); //Remplacez par votre
encodage
$config->set('Core', 'XHTML', true); //Remplacer par false si HTML 4.01
$purificateur = new HTMLPurifier($config);
$html_propre = $purificateur->purify($html_a_purifier);
?>
vim: et sw=4 sts=4

504
library/ezyang/htmlpurifier/LICENSE Normal file
View file

@ -0,0 +1,504 @@
GNU LESSER GENERAL PUBLIC LICENSE
Version 2.1, February 1999
Copyright (C) 1991, 1999 Free Software Foundation, Inc.
51 Franklin Street, Fifth Floor, Boston, MA 02110-1301 USA
Everyone is permitted to copy and distribute verbatim copies
of this license document, but changing it is not allowed.
[This is the first released version of the Lesser GPL. It also counts
as the successor of the GNU Library Public License, version 2, hence
the version number 2.1.]
Preamble
The licenses for most software are designed to take away your
freedom to share and change it. By contrast, the GNU General Public
Licenses are intended to guarantee your freedom to share and change
free software--to make sure the software is free for all its users.
This license, the Lesser General Public License, applies to some
specially designated software packages--typically libraries--of the
Free Software Foundation and other authors who decide to use it. You
can use it too, but we suggest you first think carefully about whether
this license or the ordinary General Public License is the better
strategy to use in any particular case, based on the explanations below.
When we speak of free software, we are referring to freedom of use,
not price. Our General Public Licenses are designed to make sure that
you have the freedom to distribute copies of free software (and charge
for this service if you wish); that you receive source code or can get
it if you want it; that you can change the software and use pieces of
it in new free programs; and that you are informed that you can do
these things.
To protect your rights, we need to make restrictions that forbid
distributors to deny you these rights or to ask you to surrender these
rights. These restrictions translate to certain responsibilities for
you if you distribute copies of the library or if you modify it.
For example, if you distribute copies of the library, whether gratis
or for a fee, you must give the recipients all the rights that we gave
you. You must make sure that they, too, receive or can get the source
code. If you link other code with the library, you must provide
complete object files to the recipients, so that they can relink them
with the library after making changes to the library and recompiling
it. And you must show them these terms so they know their rights.
We protect your rights with a two-step method: (1) we copyright the
library, and (2) we offer you this license, which gives you legal
permission to copy, distribute and/or modify the library.
To protect each distributor, we want to make it very clear that
there is no warranty for the free library. Also, if the library is
modified by someone else and passed on, the recipients should know
that what they have is not the original version, so that the original
author's reputation will not be affected by problems that might be
introduced by others.
Finally, software patents pose a constant threat to the existence of
any free program. We wish to make sure that a company cannot
effectively restrict the users of a free program by obtaining a
restrictive license from a patent holder. Therefore, we insist that
any patent license obtained for a version of the library must be
consistent with the full freedom of use specified in this license.
Most GNU software, including some libraries, is covered by the
ordinary GNU General Public License. This license, the GNU Lesser
General Public License, applies to certain designated libraries, and
is quite different from the ordinary General Public License. We use
this license for certain libraries in order to permit linking those
libraries into non-free programs.
When a program is linked with a library, whether statically or using
a shared library, the combination of the two is legally speaking a
combined work, a derivative of the original library. The ordinary
General Public License therefore permits such linking only if the
entire combination fits its criteria of freedom. The Lesser General
Public License permits more lax criteria for linking other code with
the library.
We call this license the "Lesser" General Public License because it
does Less to protect the user's freedom than the ordinary General
Public License. It also provides other free software developers Less
of an advantage over competing non-free programs. These disadvantages
are the reason we use the ordinary General Public License for many
libraries. However, the Lesser license provides advantages in certain
special circumstances.
For example, on rare occasions, there may be a special need to
encourage the widest possible use of a certain library, so that it becomes
a de-facto standard. To achieve this, non-free programs must be
allowed to use the library. A more frequent case is that a free
library does the same job as widely used non-free libraries. In this
case, there is little to gain by limiting the free library to free
software only, so we use the Lesser General Public License.
In other cases, permission to use a particular library in non-free
programs enables a greater number of people to use a large body of
free software. For example, permission to use the GNU C Library in
non-free programs enables many more people to use the whole GNU
operating system, as well as its variant, the GNU/Linux operating
system.
Although the Lesser General Public License is Less protective of the
users' freedom, it does ensure that the user of a program that is
linked with the Library has the freedom and the wherewithal to run
that program using a modified version of the Library.
The precise terms and conditions for copying, distribution and
modification follow. Pay close attention to the difference between a
"work based on the library" and a "work that uses the library". The
former contains code derived from the library, whereas the latter must
be combined with the library in order to run.
GNU LESSER GENERAL PUBLIC LICENSE
TERMS AND CONDITIONS FOR COPYING, DISTRIBUTION AND MODIFICATION
0. This License Agreement applies to any software library or other
program which contains a notice placed by the copyright holder or
other authorized party saying it may be distributed under the terms of
this Lesser General Public License (also called "this License").
Each licensee is addressed as "you".
A "library" means a collection of software functions and/or data
prepared so as to be conveniently linked with application programs
(which use some of those functions and data) to form executables.
The "Library", below, refers to any such software library or work
which has been distributed under these terms. A "work based on the
Library" means either the Library or any derivative work under
copyright law: that is to say, a work containing the Library or a
portion of it, either verbatim or with modifications and/or translated
straightforwardly into another language. (Hereinafter, translation is
included without limitation in the term "modification".)
"Source code" for a work means the preferred form of the work for
making modifications to it. For a library, complete source code means
all the source code for all modules it contains, plus any associated
interface definition files, plus the scripts used to control compilation
and installation of the library.
Activities other than copying, distribution and modification are not
covered by this License; they are outside its scope. The act of
running a program using the Library is not restricted, and output from
such a program is covered only if its contents constitute a work based
on the Library (independent of the use of the Library in a tool for
writing it). Whether that is true depends on what the Library does
and what the program that uses the Library does.
1. You may copy and distribute verbatim copies of the Library's
complete source code as you receive it, in any medium, provided that
you conspicuously and appropriately publish on each copy an
appropriate copyright notice and disclaimer of warranty; keep intact
all the notices that refer to this License and to the absence of any
warranty; and distribute a copy of this License along with the
Library.
You may charge a fee for the physical act of transferring a copy,
and you may at your option offer warranty protection in exchange for a
fee.
2. You may modify your copy or copies of the Library or any portion
of it, thus forming a work based on the Library, and copy and
distribute such modifications or work under the terms of Section 1
above, provided that you also meet all of these conditions:
a) The modified work must itself be a software library.
b) You must cause the files modified to carry prominent notices
stating that you changed the files and the date of any change.
c) You must cause the whole of the work to be licensed at no
charge to all third parties under the terms of this License.
d) If a facility in the modified Library refers to a function or a
table of data to be supplied by an application program that uses
the facility, other than as an argument passed when the facility
is invoked, then you must make a good faith effort to ensure that,
in the event an application does not supply such function or
table, the facility still operates, and performs whatever part of
its purpose remains meaningful.
(For example, a function in a library to compute square roots has
a purpose that is entirely well-defined independent of the
application. Therefore, Subsection 2d requires that any
application-supplied function or table used by this function must
be optional: if the application does not supply it, the square
root function must still compute square roots.)
These requirements apply to the modified work as a whole. If
identifiable sections of that work are not derived from the Library,
and can be reasonably considered independent and separate works in
themselves, then this License, and its terms, do not apply to those
sections when you distribute them as separate works. But when you
distribute the same sections as part of a whole which is a work based
on the Library, the distribution of the whole must be on the terms of
this License, whose permissions for other licensees extend to the
entire whole, and thus to each and every part regardless of who wrote
it.
Thus, it is not the intent of this section to claim rights or contest
your rights to work written entirely by you; rather, the intent is to
exercise the right to control the distribution of derivative or
collective works based on the Library.
In addition, mere aggregation of another work not based on the Library
with the Library (or with a work based on the Library) on a volume of
a storage or distribution medium does not bring the other work under
the scope of this License.
3. You may opt to apply the terms of the ordinary GNU General Public
License instead of this License to a given copy of the Library. To do
this, you must alter all the notices that refer to this License, so
that they refer to the ordinary GNU General Public License, version 2,
instead of to this License. (If a newer version than version 2 of the
ordinary GNU General Public License has appeared, then you can specify
that version instead if you wish.) Do not make any other change in
these notices.
Once this change is made in a given copy, it is irreversible for
that copy, so the ordinary GNU General Public License applies to all
subsequent copies and derivative works made from that copy.
This option is useful when you wish to copy part of the code of
the Library into a program that is not a library.
4. You may copy and distribute the Library (or a portion or
derivative of it, under Section 2) in object code or executable form
under the terms of Sections 1 and 2 above provided that you accompany
it with the complete corresponding machine-readable source code, which
must be distributed under the terms of Sections 1 and 2 above on a
medium customarily used for software interchange.
If distribution of object code is made by offering access to copy
from a designated place, then offering equivalent access to copy the
source code from the same place satisfies the requirement to
distribute the source code, even though third parties are not
compelled to copy the source along with the object code.
5. A program that contains no derivative of any portion of the
Library, but is designed to work with the Library by being compiled or
linked with it, is called a "work that uses the Library". Such a
work, in isolation, is not a derivative work of the Library, and
therefore falls outside the scope of this License.
However, linking a "work that uses the Library" with the Library
creates an executable that is a derivative of the Library (because it
contains portions of the Library), rather than a "work that uses the
library". The executable is therefore covered by this License.
Section 6 states terms for distribution of such executables.
When a "work that uses the Library" uses material from a header file
that is part of the Library, the object code for the work may be a
derivative work of the Library even though the source code is not.
Whether this is true is especially significant if the work can be
linked without the Library, or if the work is itself a library. The
threshold for this to be true is not precisely defined by law.
If such an object file uses only numerical parameters, data
structure layouts and accessors, and small macros and small inline
functions (ten lines or less in length), then the use of the object
file is unrestricted, regardless of whether it is legally a derivative
work. (Executables containing this object code plus portions of the
Library will still fall under Section 6.)
Otherwise, if the work is a derivative of the Library, you may
distribute the object code for the work under the terms of Section 6.
Any executables containing that work also fall under Section 6,
whether or not they are linked directly with the Library itself.
6. As an exception to the Sections above, you may also combine or
link a "work that uses the Library" with the Library to produce a
work containing portions of the Library, and distribute that work
under terms of your choice, provided that the terms permit
modification of the work for the customer's own use and reverse
engineering for debugging such modifications.
You must give prominent notice with each copy of the work that the
Library is used in it and that the Library and its use are covered by
this License. You must supply a copy of this License. If the work
during execution displays copyright notices, you must include the
copyright notice for the Library among them, as well as a reference
directing the user to the copy of this License. Also, you must do one
of these things:
a) Accompany the work with the complete corresponding
machine-readable source code for the Library including whatever
changes were used in the work (which must be distributed under
Sections 1 and 2 above); and, if the work is an executable linked
with the Library, with the complete machine-readable "work that
uses the Library", as object code and/or source code, so that the
user can modify the Library and then relink to produce a modified
executable containing the modified Library. (It is understood
that the user who changes the contents of definitions files in the
Library will not necessarily be able to recompile the application
to use the modified definitions.)
b) Use a suitable shared library mechanism for linking with the
Library. A suitable mechanism is one that (1) uses at run time a
copy of the library already present on the user's computer system,
rather than copying library functions into the executable, and (2)
will operate properly with a modified version of the library, if
the user installs one, as long as the modified version is
interface-compatible with the version that the work was made with.
c) Accompany the work with a written offer, valid for at
least three years, to give the same user the materials
specified in Subsection 6a, above, for a charge no more
than the cost of performing this distribution.
d) If distribution of the work is made by offering access to copy
from a designated place, offer equivalent access to copy the above
specified materials from the same place.
e) Verify that the user has already received a copy of these
materials or that you have already sent this user a copy.
For an executable, the required form of the "work that uses the
Library" must include any data and utility programs needed for
reproducing the executable from it. However, as a special exception,
the materials to be distributed need not include anything that is
normally distributed (in either source or binary form) with the major
components (compiler, kernel, and so on) of the operating system on
which the executable runs, unless that component itself accompanies
the executable.
It may happen that this requirement contradicts the license
restrictions of other proprietary libraries that do not normally
accompany the operating system. Such a contradiction means you cannot
use both them and the Library together in an executable that you
distribute.
7. You may place library facilities that are a work based on the
Library side-by-side in a single library together with other library
facilities not covered by this License, and distribute such a combined
library, provided that the separate distribution of the work based on
the Library and of the other library facilities is otherwise
permitted, and provided that you do these two things:
a) Accompany the combined library with a copy of the same work
based on the Library, uncombined with any other library
facilities. This must be distributed under the terms of the
Sections above.
b) Give prominent notice with the combined library of the fact
that part of it is a work based on the Library, and explaining
where to find the accompanying uncombined form of the same work.
8. You may not copy, modify, sublicense, link with, or distribute
the Library except as expressly provided under this License. Any
attempt otherwise to copy, modify, sublicense, link with, or
distribute the Library is void, and will automatically terminate your
rights under this License. However, parties who have received copies,
or rights, from you under this License will not have their licenses
terminated so long as such parties remain in full compliance.
9. You are not required to accept this License, since you have not
signed it. However, nothing else grants you permission to modify or
distribute the Library or its derivative works. These actions are
prohibited by law if you do not accept this License. Therefore, by
modifying or distributing the Library (or any work based on the
Library), you indicate your acceptance of this License to do so, and
all its terms and conditions for copying, distributing or modifying
the Library or works based on it.
10. Each time you redistribute the Library (or any work based on the
Library), the recipient automatically receives a license from the
original licensor to copy, distribute, link with or modify the Library
subject to these terms and conditions. You may not impose any further
restrictions on the recipients' exercise of the rights granted herein.
You are not responsible for enforcing compliance by third parties with
this License.
11. If, as a consequence of a court judgment or allegation of patent
infringement or for any other reason (not limited to patent issues),
conditions are imposed on you (whether by court order, agreement or
otherwise) that contradict the conditions of this License, they do not
excuse you from the conditions of this License. If you cannot
distribute so as to satisfy simultaneously your obligations under this
License and any other pertinent obligations, then as a consequence you
may not distribute the Library at all. For example, if a patent
license would not permit royalty-free redistribution of the Library by
all those who receive copies directly or indirectly through you, then
the only way you could satisfy both it and this License would be to
refrain entirely from distribution of the Library.
If any portion of this section is held invalid or unenforceable under any
particular circumstance, the balance of the section is intended to apply,
and the section as a whole is intended to apply in other circumstances.
It is not the purpose of this section to induce you to infringe any
patents or other property right claims or to contest validity of any
such claims; this section has the sole purpose of protecting the
integrity of the free software distribution system which is
implemented by public license practices. Many people have made
generous contributions to the wide range of software distributed
through that system in reliance on consistent application of that
system; it is up to the author/donor to decide if he or she is willing
to distribute software through any other system and a licensee cannot
impose that choice.
This section is intended to make thoroughly clear what is believed to
be a consequence of the rest of this License.
12. If the distribution and/or use of the Library is restricted in
certain countries either by patents or by copyrighted interfaces, the
original copyright holder who places the Library under this License may add
an explicit geographical distribution limitation excluding those countries,
so that distribution is permitted only in or among countries not thus
excluded. In such case, this License incorporates the limitation as if
written in the body of this License.
13. The Free Software Foundation may publish revised and/or new
versions of the Lesser General Public License from time to time.
Such new versions will be similar in spirit to the present version,
but may differ in detail to address new problems or concerns.
Each version is given a distinguishing version number. If the Library
specifies a version number of this License which applies to it and
"any later version", you have the option of following the terms and
conditions either of that version or of any later version published by
the Free Software Foundation. If the Library does not specify a
license version number, you may choose any version ever published by
the Free Software Foundation.
14. If you wish to incorporate parts of the Library into other free
programs whose distribution conditions are incompatible with these,
write to the author to ask for permission. For software which is
copyrighted by the Free Software Foundation, write to the Free
Software Foundation; we sometimes make exceptions for this. Our
decision will be guided by the two goals of preserving the free status
of all derivatives of our free software and of promoting the sharing
and reuse of software generally.
NO WARRANTY
15. BECAUSE THE LIBRARY IS LICENSED FREE OF CHARGE, THERE IS NO
WARRANTY FOR THE LIBRARY, TO THE EXTENT PERMITTED BY APPLICABLE LAW.
EXCEPT WHEN OTHERWISE STATED IN WRITING THE COPYRIGHT HOLDERS AND/OR
OTHER PARTIES PROVIDE THE LIBRARY "AS IS" WITHOUT WARRANTY OF ANY
KIND, EITHER EXPRESSED OR IMPLIED, INCLUDING, BUT NOT LIMITED TO, THE
IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR
PURPOSE. THE ENTIRE RISK AS TO THE QUALITY AND PERFORMANCE OF THE
LIBRARY IS WITH YOU. SHOULD THE LIBRARY PROVE DEFECTIVE, YOU ASSUME
THE COST OF ALL NECESSARY SERVICING, REPAIR OR CORRECTION.
16. IN NO EVENT UNLESS REQUIRED BY APPLICABLE LAW OR AGREED TO IN
WRITING WILL ANY COPYRIGHT HOLDER, OR ANY OTHER PARTY WHO MAY MODIFY
AND/OR REDISTRIBUTE THE LIBRARY AS PERMITTED ABOVE, BE LIABLE TO YOU
FOR DAMAGES, INCLUDING ANY GENERAL, SPECIAL, INCIDENTAL OR
CONSEQUENTIAL DAMAGES ARISING OUT OF THE USE OR INABILITY TO USE THE
LIBRARY (INCLUDING BUT NOT LIMITED TO LOSS OF DATA OR DATA BEING
RENDERED INACCURATE OR LOSSES SUSTAINED BY YOU OR THIRD PARTIES OR A
FAILURE OF THE LIBRARY TO OPERATE WITH ANY OTHER SOFTWARE), EVEN IF
SUCH HOLDER OR OTHER PARTY HAS BEEN ADVISED OF THE POSSIBILITY OF SUCH
DAMAGES.
END OF TERMS AND CONDITIONS
How to Apply These Terms to Your New Libraries
If you develop a new library, and you want it to be of the greatest
possible use to the public, we recommend making it free software that
everyone can redistribute and change. You can do so by permitting
redistribution under these terms (or, alternatively, under the terms of the
ordinary General Public License).
To apply these terms, attach the following notices to the library. It is
safest to attach them to the start of each source file to most effectively
convey the exclusion of warranty; and each file should have at least the
"copyright" line and a pointer to where the full notice is found.
<one line to give the library's name and a brief idea of what it does.>
Copyright (C) <year> <name of author>
This library is free software; you can redistribute it and/or
modify it under the terms of the GNU Lesser General Public
License as published by the Free Software Foundation; either
version 2.1 of the License, or (at your option) any later version.
This library is distributed in the hope that it will be useful,
but WITHOUT ANY WARRANTY; without even the implied warranty of
MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
Lesser General Public License for more details.
You should have received a copy of the GNU Lesser General Public
License along with this library; if not, write to the Free Software
Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301 USA
Also add information on how to contact you by electronic and paper mail.
You should also get your employer (if you work as a programmer) or your
school, if any, to sign a "copyright disclaimer" for the library, if
necessary. Here is a sample; alter the names:
Yoyodyne, Inc., hereby disclaims all copyright interest in the
library `Frob' (a library for tweaking knobs) written by James Random Hacker.
<signature of Ty Coon>, 1 April 1990
Ty Coon, President of Vice
That's all there is to it!
vim: et sw=4 sts=4

1094
library/ezyang/htmlpurifier/NEWS Normal file
View file

File diff suppressed because it is too large Load diff

24
library/ezyang/htmlpurifier/README Normal file
View file

@ -0,0 +1,24 @@
README
All about HTML Purifier
HTML Purifier is an HTML filtering solution that uses a unique combination
of robust whitelists and agressive parsing to ensure that not only are
XSS attacks thwarted, but the resulting HTML is standards compliant.
HTML Purifier is oriented towards richly formatted documents from
untrusted sources that require CSS and a full tag-set. This library can
be configured to accept a more restrictive set of tags, but it won't be
as efficient as more bare-bones parsers. It will, however, do the job
right, which may be more important.
Places to go:
* See INSTALL for a quick installation guide
* See docs/ for developer-oriented documentation, code examples and
an in-depth installation guide.
* See WYSIWYG for information on editors like TinyMCE and FCKeditor
HTML Purifier can be found on the web at: http://htmlpurifier.org/
vim: et sw=4 sts=4

150
library/ezyang/htmlpurifier/TODO Normal file
View file

@ -0,0 +1,150 @@
TODO List
= KEY ====================
# Flagship
- Regular
? Maybe I'll Do It
==========================
If no interest is expressed for a feature that may require a considerable
amount of effort to implement, it may get endlessly delayed. Do not be
afraid to cast your vote for the next feature to be implemented!
Things to do as soon as possible:
- http://htmlpurifier.org/phorum/read.php?3,5560,6307#msg-6307
- Think about allowing explicit order of operations hooks for transforms
- Fix "<.<" bug (trailing < is removed if not EOD)
- Build in better internal state dumps and debugging tools for remote
debugging
- Allowed/Allowed* have strange interactions when both set
? Transform lone embeds into object tags
- Deprecated config options that emit warnings when you set them (with'
a way of muting the warning if you really want to)
- Make HTML.Trusted work with Output.FlashCompat
- HTML.Trusted and HTML.SafeObject have funny interaction; general
problem is what to do when a module "supersedes" another
(see also tables and basic tables.) This is a little dicier
because HTML.SafeObject has some extra functionality that
trusted might find useful. See http://htmlpurifier.org/phorum/read.php?3,5762,6100
FUTURE VERSIONS
---------------
4.8 release [OMG CONFIG PONIES]
! Fix Printer. It's from the old days when we didn't have decent XML classes
! Factor demo.php into a set of Printer classes, and then create a stub
file for users here (inside the actual HTML Purifier library)
- Fix error handling with form construction
- Do encoding validation in Printers, or at least, where user data comes in
- Config: Add examples to everything (make built-in which also automatically
gives output)
- Add "register" field to config schemas to eliminate dependence on
naming conventions (try to remember why we ultimately decided on tihs)
5.0 release [HTML 5]
# Swap out code to use html5lib tokenizer and tree-builder
! Allow turning off of FixNesting and required attribute insertion
5.1 release [It's All About Trust] (floating)
# Implement untrusted, dangerous elements/attributes
# Implement IDREF support (harder than it seems, since you cannot have
IDREFs to non-existent IDs)
- Implement <area> (client and server side image maps are blocking
on IDREF support)
# Frameset XHTML 1.0 and HTML 4.01 doctypes
- Figure out how to simultaneously set %CSS.Trusted and %HTML.Trusted (?)
5.2 release [Error'ed]
# Error logging for filtering/cleanup procedures
# Additional support for poorly written HTML
- Microsoft Word HTML cleaning (i.e. MsoNormal, but research essential!)
- Friendly strict handling of <address> (block -> <br>)
- XSS-attempt detection--certain errors are flagged XSS-like
- Append something to duplicate IDs so they're still usable (impl. note: the
dupe detector would also need to detect the suffix as well)
6.0 release [Beyond HTML]
# Legit token based CSS parsing (will require revamping almost every
AttrDef class). Probably will use CSSTidy
# More control over allowed CSS properties using a modularization
# IRI support (this includes IDN)
- Standardize token armor for all areas of processing
7.0 release [To XML and Beyond]
- Extended HTML capabilities based on namespacing and tag transforms (COMPLEX)
- Hooks for adding custom processors to custom namespaced tags and
attributes, offer default implementation
- Lots of documentation and samples
Ongoing
- More refactoring to take advantage of PHP5's facilities
- Refactor unit tests into lots of test methods
- Plugins for major CMSes (COMPLEX)
- phpBB
- Also, a FAQ for extension writers with HTML Purifier
AutoFormat
- Smileys
- Syntax highlighting (with GeSHi) with <pre> and possibly <?php
- Look at http://drupal.org/project/Modules/category/63 for ideas
Neat feature related
! Support exporting configuration, so users can easily tweak settings
in the demo, and then copy-paste into their own setup
- Advanced URI filtering schemes (see docs/proposal-new-directives.txt)
- Allow scoped="scoped" attribute in <style> tags; may be troublesome
because regular CSS has no way of uniquely identifying nodes, so we'd
have to generate IDs
- Explain how to use HTML Purifier in non-PHP languages / create
a simple command line stub (or complicated?)
- Fixes for Firefox's inability to handle COL alignment props (Bug 915)
- Automatically add non-breaking spaces to empty table cells when
empty-cells:show is applied to have compatibility with Internet Explorer
- Table of Contents generation (XHTML Compiler might be reusable). May also
be out-of-band information.
- Full set of color keywords. Also, a way to add onto them without
finalizing the configuration object.
- Write a var_export and memcached DefinitionCache - Denis
- Built-in support for target="_blank" on all external links
- Convert RTL/LTR override characters to <bdo> tags, or vice versa on demand.
Also, enable disabling of directionality
? Externalize inline CSS to promote clean HTML, proposed by Sander Tekelenburg
? Remove redundant tags, ex. <u><u>Underlined</u></u>. Implementation notes:
1. Analyzing which tags to remove duplicants
2. Ensure attributes are merged into the parent tag
3. Extend the tag exclusion system to specify whether or not the
contents should be dropped or not (currently, there's code that could do
something like this if it didn't drop the inner text too.)
? Make AutoParagraph also support paragraph-izing double <br> tags, and not
just double newlines. This is kind of tough to do in the current framework,
though, and might be reasonably approximated by search replacing double <br>s
with newlines before running it through HTML Purifier.
Maintenance related (slightly boring)
# CHMOD install script for PEAR installs
! Factor out command line parser into its own class, and unit test it
- Reduce size of internal data-structures (esp. HTMLDefinition)
- Allow merging configurations. Thus,
a -> b -> default
c -> d -> default
becomes
a -> b -> c -> d -> default
Maybe allow more fine-grained tuning of this behavior. Alternatively,
encourage people to use short plist depths before building them up.
- Time PHPT tests
ChildDef related (very boring)
- Abstract ChildDef_BlockQuote to work with all elements that only
allow blocks in them, required or optional
- Implement lenient <ruby> child validation
Wontfix
- Non-lossy smart alternate character encoding transformations (unless
patch provided)
- Pretty-printing HTML: users can use Tidy on the output on entire page
- Native content compression, whitespace stripping: use gzip if this is
really important
vim: et sw=4 sts=4

1
library/ezyang/htmlpurifier/VERSION Normal file
View file

@ -0,0 +1 @@
4.7.0

4
library/ezyang/htmlpurifier/WHATSNEW Normal file
View file

@ -0,0 +1,4 @@
HTML Purifier 4.7.0 is a bugfix release, collecting two years
worth of accumulated bug fixes. Highlighted bugfixes are updated
YouTube filter code, corrected rgb() CSS parsing, and one new
configuration option, %AutoFormat.RemoveEmpty.Predicate.

20
library/ezyang/htmlpurifier/WYSIWYG Normal file
View file

@ -0,0 +1,20 @@
WYSIWYG - What You See Is What You Get
HTML Purifier: A Pretty Good Fit for TinyMCE and FCKeditor
Javascript-based WYSIWYG editors, simply stated, are quite amazing. But I've
always been wary about using them due to security issues: they handle the
client-side magic, but once you've been served a piping hot load of unfiltered
HTML, what should be done then? In some situations, you can serve it uncleaned,
since you only offer these facilities to trusted(?) authors.
Unfortunantely, for blog comments and anonymous input, BBCode, Textile and
other markup languages still reign supreme. Put simply: filtering HTML is
hard work, and these WYSIWYG authors don't offer anything to alleviate that
trouble. Therein lies the solution:
HTML Purifier is perfect for filtering pure-HTML input from WYSIWYG editors.
Enough said.
vim: et sw=4 sts=4

22
library/ezyang/htmlpurifier/composer.json Normal file
View file

@ -0,0 +1,22 @@
{
"name": "ezyang/htmlpurifier",
"description": "Standards compliant HTML filter written in PHP",
"type": "library",
"keywords": ["html"],
"homepage": "http://htmlpurifier.org/",
"license": "LGPL",
"authors": [
{
"name": "Edward Z. Yang",
"email": "admin@htmlpurifier.org",
"homepage": "http://ezyang.com"
}
],
"require": {
"php": ">=5.2"
},
"autoload": {
"psr-0": { "HTMLPurifier": "library/" },
"files": ["library/HTMLPurifier.composer.php"]
}
}

91
library/ezyang/htmlpurifier/extras/ConfigDoc/HTMLXSLTProcessor.php Normal file
View file

@ -0,0 +1,91 @@
<?php
/**
* Decorator/extender XSLT processor specifically for HTML documents.
*/
class ConfigDoc_HTMLXSLTProcessor
{
/**
* Instance of XSLTProcessor
*/
protected $xsltProcessor;
public function __construct($proc = false)
{
if ($proc === false) $proc = new XSLTProcessor();
$this->xsltProcessor = $proc;
}
/**
* @note Allows a string $xsl filename to be passed
*/
public function importStylesheet($xsl)
{
if (is_string($xsl)) {
$xsl_file = $xsl;
$xsl = new DOMDocument();
$xsl->load($xsl_file);
}
return $this->xsltProcessor->importStylesheet($xsl);
}
/**
* Transforms an XML file into compatible XHTML based on the stylesheet
* @param $xml XML DOM tree, or string filename
* @return string HTML output
* @todo Rename to transformToXHTML, as transformToHTML is misleading
*/
public function transformToHTML($xml)
{
if (is_string($xml)) {
$dom = new DOMDocument();
$dom->load($xml);
} else {
$dom = $xml;
}
$out = $this->xsltProcessor->transformToXML($dom);
// fudges for HTML backwards compatibility
// assumes that document is XHTML
$out = str_replace('/>', ' />', $out); // <br /> not <br/>
$out = str_replace(' xmlns=""', '', $out); // rm unnecessary xmlns
if (class_exists('Tidy')) {
// cleanup output
$config = array(
'indent' => true,
'output-xhtml' => true,
'wrap' => 80
);
$tidy = new Tidy;
$tidy->parseString($out, $config, 'utf8');
$tidy->cleanRepair();
$out = (string) $tidy;
}
return $out;
}
/**
* Bulk sets parameters for the XSL stylesheet
* @param array $options Associative array of options to set
*/
public function setParameters($options)
{
foreach ($options as $name => $value) {
$this->xsltProcessor->setParameter('', $name, $value);
}
}
/**
* Forward any other calls to the XSLT processor
*/
public function __call($name, $arguments)
{
call_user_func_array(array($this->xsltProcessor, $name), $arguments);
}
}
// vim: et sw=4 sts=4

164
library/ezyang/htmlpurifier/extras/FSTools.php Normal file
View file

@ -0,0 +1,164 @@
<?php
/**
* Filesystem tools not provided by default; can recursively create, copy
* and delete folders. Some template methods are provided for extensibility.
*
* @note This class must be instantiated to be used, although it does
* not maintain state.
*/
class FSTools
{
private static $singleton;
/**
* Returns a global instance of FSTools
*/
public static function singleton()
{
if (empty(FSTools::$singleton)) FSTools::$singleton = new FSTools();
return FSTools::$singleton;
}
/**
* Sets our global singleton to something else; useful for overloading
* functions.
*/
public static function setSingleton($singleton)
{
FSTools::$singleton = $singleton;
}
/**
* Recursively creates a directory
* @param string $folder Name of folder to create
* @note Adapted from the PHP manual comment 76612
*/
public function mkdirr($folder)
{
$folders = preg_split("#[\\\\/]#", $folder);
$base = '';
for($i = 0, $c = count($folders); $i < $c; $i++) {
if(empty($folders[$i])) {
if (!$i) {
// special case for root level
$base .= DIRECTORY_SEPARATOR;
}
continue;
}
$base .= $folders[$i];
if(!is_dir($base)){
$this->mkdir($base);
}
$base .= DIRECTORY_SEPARATOR;
}
}
/**
* Copy a file, or recursively copy a folder and its contents; modified
* so that copied files, if PHP, have includes removed
* @note Adapted from http://aidanlister.com/repos/v/function.copyr.php
*/
public function copyr($source, $dest)
{
// Simple copy for a file
if (is_file($source)) {
return $this->copy($source, $dest);
}
// Make destination directory
if (!is_dir($dest)) {
$this->mkdir($dest);
}
// Loop through the folder
$dir = $this->dir($source);
while ( false !== ($entry = $dir->read()) ) {
// Skip pointers
if ($entry == '.' || $entry == '..') {
continue;
}
if (!$this->copyable($entry)) {
continue;
}
// Deep copy directories
if ($dest !== "$source/$entry") {
$this->copyr("$source/$entry", "$dest/$entry");
}
}
// Clean up
$dir->close();
return true;
}
/**
* Overloadable function that tests a filename for copyability. By
* default, everything should be copied; you can restrict things to
* ignore hidden files, unreadable files, etc. This function
* applies to copyr().
*/
public function copyable($file)
{
return true;
}
/**
* Delete a file, or a folder and its contents
* @note Adapted from http://aidanlister.com/repos/v/function.rmdirr.php
*/
public function rmdirr($dirname)
{
// Sanity check
if (!$this->file_exists($dirname)) {
return false;
}
// Simple delete for a file
if ($this->is_file($dirname) || $this->is_link($dirname)) {
return $this->unlink($dirname);
}
// Loop through the folder
$dir = $this->dir($dirname);
while (false !== $entry = $dir->read()) {
// Skip pointers
if ($entry == '.' || $entry == '..') {
continue;
}
// Recurse
$this->rmdirr($dirname . DIRECTORY_SEPARATOR . $entry);
}
// Clean up
$dir->close();
return $this->rmdir($dirname);
}
/**
* Recursively globs a directory.
*/
public function globr($dir, $pattern, $flags = NULL)
{
$files = $this->glob("$dir/$pattern", $flags);
if ($files === false) $files = array();
$sub_dirs = $this->glob("$dir/*", GLOB_ONLYDIR);
if ($sub_dirs === false) $sub_dirs = array();
foreach ($sub_dirs as $sub_dir) {
$sub_files = $this->globr($sub_dir, $pattern, $flags);
$files = array_merge($files, $sub_files);
}
return $files;
}
/**
* Allows for PHP functions to be called and be stubbed.
* @warning This function will not work for functions that need
* to pass references; manually define a stub function for those.
*/
public function __call($name, $args)
{
return call_user_func_array($name, $args);
}
}
// vim: et sw=4 sts=4

141
library/ezyang/htmlpurifier/extras/FSTools/File.php Normal file
View file

@ -0,0 +1,141 @@
<?php
/**
* Represents a file in the filesystem
*
* @warning Be sure to distinguish between get() and write() versus
* read() and put(), the former operates on the entire file, while
* the latter operates on a handle.
*/
class FSTools_File
{
/** Filename of file this object represents */
protected $name;
/** Handle for the file */
protected $handle = false;
/** Instance of FSTools for interfacing with filesystem */
protected $fs;
/**
* Filename of file you wish to instantiate.
* @note This file need not exist
*/
public function __construct($name, $fs = false)
{
$this->name = $name;
$this->fs = $fs ? $fs : FSTools::singleton();
}
/** Returns the filename of the file. */
public function getName() {return $this->name;}
/** Returns directory of the file without trailing slash */
public function getDirectory() {return $this->fs->dirname($this->name);}
/**
* Retrieves the contents of a file
* @todo Throw an exception if file doesn't exist
*/
public function get()
{
return $this->fs->file_get_contents($this->name);
}
/** Writes contents to a file, creates new file if necessary */
public function write($contents)
{
return $this->fs->file_put_contents($this->name, $contents);
}
/** Deletes the file */
public function delete()
{
return $this->fs->unlink($this->name);
}
/** Returns true if file exists and is a file. */
public function exists()
{
return $this->fs->is_file($this->name);
}
/** Returns last file modification time */
public function getMTime()
{
return $this->fs->filemtime($this->name);
}
/**
* Chmod a file
* @note We ignore errors because of some weird owner trickery due
* to SVN duality
*/
public function chmod($octal_code)
{
return @$this->fs->chmod($this->name, $octal_code);
}
/** Opens file's handle */
public function open($mode)
{
if ($this->handle) $this->close();
$this->handle = $this->fs->fopen($this->name, $mode);
return true;
}
/** Closes file's handle */
public function close()
{
if (!$this->handle) return false;
$status = $this->fs->fclose($this->handle);
$this->handle = false;
return $status;
}
/** Retrieves a line from an open file, with optional max length $length */
public function getLine($length = null)
{
if (!$this->handle) $this->open('r');
if ($length === null) return $this->fs->fgets($this->handle);
else return $this->fs->fgets($this->handle, $length);
}
/** Retrieves a character from an open file */
public function getChar()
{
if (!$this->handle) $this->open('r');
return $this->fs->fgetc($this->handle);
}
/** Retrieves an $length bytes of data from an open data */
public function read($length)
{
if (!$this->handle) $this->open('r');
return $this->fs->fread($this->handle, $length);
}
/** Writes to an open file */
public function put($string)
{
if (!$this->handle) $this->open('a');
return $this->fs->fwrite($this->handle, $string);
}
/** Returns TRUE if the end of the file has been reached */
public function eof()
{
if (!$this->handle) return true;
return $this->fs->feof($this->handle);
}
public function __destruct()
{
if ($this->handle) $this->close();
}
}
// vim: et sw=4 sts=4

11
library/ezyang/htmlpurifier/extras/HTMLPurifierExtras.auto.php Normal file
View file

@ -0,0 +1,11 @@
<?php
/**
* This is a stub include that automatically configures the include path.
*/
set_include_path(dirname(__FILE__) . PATH_SEPARATOR . get_include_path() );
require_once 'HTMLPurifierExtras.php';
require_once 'HTMLPurifierExtras.autoload.php';
// vim: et sw=4 sts=4

26
library/ezyang/htmlpurifier/extras/HTMLPurifierExtras.autoload.php Normal file
View file

@ -0,0 +1,26 @@
<?php
/**
* @file
* Convenience file that registers autoload handler for HTML Purifier.
*
* @warning
* This autoloader does not contain the compatibility code seen in
* HTMLPurifier_Bootstrap; the user is expected to make any necessary
* changes to use this library.
*/
if (function_exists('spl_autoload_register')) {
spl_autoload_register(array('HTMLPurifierExtras', 'autoload'));
if (function_exists('__autoload')) {
// Be polite and ensure that userland autoload gets retained
spl_autoload_register('__autoload');
}
} elseif (!function_exists('__autoload')) {
function __autoload($class)
{
return HTMLPurifierExtras::autoload($class);
}
}
// vim: et sw=4 sts=4

31
library/ezyang/htmlpurifier/extras/HTMLPurifierExtras.php Normal file
View file

@ -0,0 +1,31 @@
<?php
/**
* Meta-class for HTML Purifier's extra class hierarchies, similar to
* HTMLPurifier_Bootstrap.
*/
class HTMLPurifierExtras
{
public static function autoload($class)
{
$path = HTMLPurifierExtras::getPath($class);
if (!$path) return false;
require $path;
return true;
}
public static function getPath($class)
{
if (
strncmp('FSTools', $class, 7) !== 0 &&
strncmp('ConfigDoc', $class, 9) !== 0
) return false;
// Custom implementations can go here
// Standard implementation:
return str_replace('_', '/', $class) . '.php';
}
}
// vim: et sw=4 sts=4

32
library/ezyang/htmlpurifier/extras/README Normal file
View file

@ -0,0 +1,32 @@
HTML Purifier Extras
The Method Behind The Madness!
The extras/ folder in HTML Purifier contains--you guessed it--extra things
for HTML Purifier. Specifically, these are two extra libraries called
FSTools and ConfigSchema. They're extra for a reason: you don't need them
if you're using HTML Purifier for normal usage: filtering HTML. However,
if you're a developer, and would like to test HTML Purifier, or need to
use one of HTML Purifier's maintenance scripts, chances are they'll need
these libraries. Who knows: maybe you'll find them useful too!
Here are the libraries:
FSTools
-------
Short for File System Tools, this is a poor-man's object-oriented wrapper for
the filesystem. It currently consists of two classes:
- FSTools: This is a singleton that contains a manner of useful functions
such as recursive glob, directory removal, etc, as well as the ability
to call arbitrary native PHP functions through it like $FS->fopen(...).
This makes it a lot simpler to mock these filesystem calls for unit testing.
- FSTools_File: This object represents a single file, and has almost any
method imaginable one would need.
Check the files themselves for more information.
vim: et sw=4 sts=4

0
library/HTMLPurifier.auto.php → library/ezyang/htmlpurifier/library/HTMLPurifier.auto.php
View file

8
library/HTMLPurifier.autoload.php → library/ezyang/htmlpurifier/library/HTMLPurifier.autoload.php
View file

@ -3,6 +3,7 @@
/**
* @file
* Convenience file that registers autoload handler for HTML Purifier.
* It also does some sanity checks.
*/
if (function_exists('spl_autoload_register') && function_exists('spl_autoload_unregister')) {
@ -13,9 +14,14 @@ if (function_exists('spl_autoload_register') && function_exists('spl_autoload_un
spl_autoload_register('__autoload');
}
} elseif (!function_exists('__autoload')) {
function __autoload($class) {
function __autoload($class)
{
return HTMLPurifier_Bootstrap::autoload($class);
}
}
if (ini_get('zend.ze1_compatibility_mode')) {
trigger_error("HTML Purifier is not compatible with zend.ze1_compatibility_mode; please turn it off", E_USER_ERROR);
}
// vim: et sw=4 sts=4

4
library/ezyang/htmlpurifier/library/HTMLPurifier.composer.php Normal file
View file

@ -0,0 +1,4 @@
<?php
if (!defined('HTMLPURIFIER_PREFIX')) {
define('HTMLPURIFIER_PREFIX', dirname(__FILE__));
}

8
library/HTMLPurifier.func.php → library/ezyang/htmlpurifier/library/HTMLPurifier.func.php
View file

@ -8,11 +8,13 @@
/**
* Purify HTML.
* @param $html String HTML to purify
* @param $config Configuration to use, can be any value accepted by
* @param string $html String HTML to purify
* @param mixed $config Configuration to use, can be any value accepted by
* HTMLPurifier_Config::create()
* @return string
*/
function HTMLPurifier($html, $config = null) {
function HTMLPurifier($html, $config = null)
{
static $purifier = false;
if (!$purifier) {
$purifier = new HTMLPurifier();

21
library/HTMLPurifier.includes.php → library/ezyang/htmlpurifier/library/HTMLPurifier.includes.php
View file

@ -7,7 +7,7 @@
* primary concern and you are using an opcode cache. PLEASE DO NOT EDIT THIS
* FILE, changes will be overwritten the next time the script is run.
*
* @version 4.1.1
* @version 4.7.0
*
* @warning
* You must *not* include any other HTML Purifier files before this file,
@ -19,6 +19,7 @@
*/
require 'HTMLPurifier.php';
require 'HTMLPurifier/Arborize.php';
require 'HTMLPurifier/AttrCollections.php';
require 'HTMLPurifier/AttrDef.php';
require 'HTMLPurifier/AttrTransform.php';
@ -54,9 +55,11 @@ require 'HTMLPurifier/Language.php';
require 'HTMLPurifier/LanguageFactory.php';
require 'HTMLPurifier/Length.php';
require 'HTMLPurifier/Lexer.php';
require 'HTMLPurifier/Node.php';
require 'HTMLPurifier/PercentEncoder.php';
require 'HTMLPurifier/PropertyList.php';
require 'HTMLPurifier/PropertyListIterator.php';
require 'HTMLPurifier/Queue.php';
require 'HTMLPurifier/Strategy.php';
require 'HTMLPurifier/StringHash.php';
require 'HTMLPurifier/StringHashParser.php';
@ -72,7 +75,9 @@ require 'HTMLPurifier/URISchemeRegistry.php';
require 'HTMLPurifier/UnitConverter.php';
require 'HTMLPurifier/VarParser.php';
require 'HTMLPurifier/VarParserException.php';
require 'HTMLPurifier/Zipper.php';
require 'HTMLPurifier/AttrDef/CSS.php';
require 'HTMLPurifier/AttrDef/Clone.php';
require 'HTMLPurifier/AttrDef/Enum.php';
require 'HTMLPurifier/AttrDef/Integer.php';
require 'HTMLPurifier/AttrDef/Lang.php';
@ -90,6 +95,7 @@ require 'HTMLPurifier/AttrDef/CSS/DenyElementDecorator.php';
require 'HTMLPurifier/AttrDef/CSS/Filter.php';
require 'HTMLPurifier/AttrDef/CSS/Font.php';
require 'HTMLPurifier/AttrDef/CSS/FontFamily.php';
require 'HTMLPurifier/AttrDef/CSS/Ident.php';
require 'HTMLPurifier/AttrDef/CSS/ImportantDecorator.php';
require 'HTMLPurifier/AttrDef/CSS/Length.php';
require 'HTMLPurifier/AttrDef/CSS/ListStyle.php';
@ -125,14 +131,17 @@ require 'HTMLPurifier/AttrTransform/Lang.php';
require 'HTMLPurifier/AttrTransform/Length.php';
require 'HTMLPurifier/AttrTransform/Name.php';
require 'HTMLPurifier/AttrTransform/NameSync.php';
require 'HTMLPurifier/AttrTransform/Nofollow.php';
require 'HTMLPurifier/AttrTransform/SafeEmbed.php';
require 'HTMLPurifier/AttrTransform/SafeObject.php';
require 'HTMLPurifier/AttrTransform/SafeParam.php';
require 'HTMLPurifier/AttrTransform/ScriptRequired.php';
require 'HTMLPurifier/AttrTransform/TargetBlank.php';
require 'HTMLPurifier/AttrTransform/Textarea.php';
require 'HTMLPurifier/ChildDef/Chameleon.php';
require 'HTMLPurifier/ChildDef/Custom.php';
require 'HTMLPurifier/ChildDef/Empty.php';
require 'HTMLPurifier/ChildDef/List.php';
require 'HTMLPurifier/ChildDef/Required.php';
require 'HTMLPurifier/ChildDef/Optional.php';
require 'HTMLPurifier/ChildDef/StrictBlockquote.php';
@ -147,10 +156,12 @@ require 'HTMLPurifier/HTMLModule/CommonAttributes.php';
require 'HTMLPurifier/HTMLModule/Edit.php';
require 'HTMLPurifier/HTMLModule/Forms.php';
require 'HTMLPurifier/HTMLModule/Hypertext.php';
require 'HTMLPurifier/HTMLModule/Iframe.php';
require 'HTMLPurifier/HTMLModule/Image.php';
require 'HTMLPurifier/HTMLModule/Legacy.php';
require 'HTMLPurifier/HTMLModule/List.php';
require 'HTMLPurifier/HTMLModule/Name.php';
require 'HTMLPurifier/HTMLModule/Nofollow.php';
require 'HTMLPurifier/HTMLModule/NonXMLCommonAttributes.php';
require 'HTMLPurifier/HTMLModule/Object.php';
require 'HTMLPurifier/HTMLModule/Presentation.php';
@ -158,10 +169,12 @@ require 'HTMLPurifier/HTMLModule/Proprietary.php';
require 'HTMLPurifier/HTMLModule/Ruby.php';
require 'HTMLPurifier/HTMLModule/SafeEmbed.php';
require 'HTMLPurifier/HTMLModule/SafeObject.php';
require 'HTMLPurifier/HTMLModule/SafeScripting.php';
require 'HTMLPurifier/HTMLModule/Scripting.php';
require 'HTMLPurifier/HTMLModule/StyleAttribute.php';
require 'HTMLPurifier/HTMLModule/Tables.php';
require 'HTMLPurifier/HTMLModule/Target.php';
require 'HTMLPurifier/HTMLModule/TargetBlank.php';
require 'HTMLPurifier/HTMLModule/Text.php';
require 'HTMLPurifier/HTMLModule/Tidy.php';
require 'HTMLPurifier/HTMLModule/XMLCommonAttributes.php';
@ -180,6 +193,9 @@ require 'HTMLPurifier/Injector/RemoveSpansWithoutAttributes.php';
require 'HTMLPurifier/Injector/SafeObject.php';
require 'HTMLPurifier/Lexer/DOMLex.php';
require 'HTMLPurifier/Lexer/DirectLex.php';
require 'HTMLPurifier/Node/Comment.php';
require 'HTMLPurifier/Node/Element.php';
require 'HTMLPurifier/Node/Text.php';
require 'HTMLPurifier/Strategy/Composite.php';
require 'HTMLPurifier/Strategy/Core.php';
require 'HTMLPurifier/Strategy/FixNesting.php';
@ -196,10 +212,13 @@ require 'HTMLPurifier/Token/Start.php';
require 'HTMLPurifier/Token/Text.php';
require 'HTMLPurifier/URIFilter/DisableExternal.php';
require 'HTMLPurifier/URIFilter/DisableExternalResources.php';
require 'HTMLPurifier/URIFilter/DisableResources.php';
require 'HTMLPurifier/URIFilter/HostBlacklist.php';
require 'HTMLPurifier/URIFilter/MakeAbsolute.php';
require 'HTMLPurifier/URIFilter/Munge.php';
require 'HTMLPurifier/URIFilter/SafeIframe.php';
require 'HTMLPurifier/URIScheme/data.php';
require 'HTMLPurifier/URIScheme/file.php';
require 'HTMLPurifier/URIScheme/ftp.php';
require 'HTMLPurifier/URIScheme/http.php';
require 'HTMLPurifier/URIScheme/https.php';

4
library/HTMLPurifier.kses.php → library/ezyang/htmlpurifier/library/HTMLPurifier.kses.php
View file

@ -7,7 +7,8 @@
require_once dirname(__FILE__) . '/HTMLPurifier.auto.php';
function kses($string, $allowed_html, $allowed_protocols = null) {
function kses($string, $allowed_html, $allowed_protocols = null)
{
$config = HTMLPurifier_Config::createDefault();
$allowed_elements = array();
$allowed_attributes = array();
@ -19,7 +20,6 @@ function kses($string, $allowed_html, $allowed_protocols = null) {
}
$config->set('HTML.AllowedElements', $allowed_elements);
$config->set('HTML.AllowedAttributes', $allowed_attributes);
$allowed_schemes = array();
if ($allowed_protocols !== null) {
$config->set('URI.AllowedSchemes', $allowed_protocols);
}

0
library/HTMLPurifier.path.php → library/ezyang/htmlpurifier/library/HTMLPurifier.path.php
View file

153
library/HTMLPurifier.php → library/ezyang/htmlpurifier/library/HTMLPurifier.php
View file

@ -19,7 +19,7 @@
*/
/*
HTML Purifier 4.1.1 - Standards Compliant HTML Filtering
HTML Purifier 4.7.0 - Standards Compliant HTML Filtering
Copyright (C) 2006-2008 Edward Z. Yang
This library is free software; you can redistribute it and/or
@ -54,66 +54,97 @@
class HTMLPurifier
{
/** Version of HTML Purifier */
public $version = '4.1.1';
/** Constant with version of HTML Purifier */
const VERSION = '4.1.1';
/** Global configuration object */
public $config;
/** Array of extra HTMLPurifier_Filter objects to run on HTML, for backwards compatibility */
private $filters = array();
/** Single instance of HTML Purifier */
private static $instance;
protected $strategy, $generator;
/**
* Version of HTML Purifier.
* @type string
*/
public $version = '4.7.0';
/**
* Resultant HTMLPurifier_Context of last run purification. Is an array
* of contexts if the last called method was purifyArray().
* Constant with version of HTML Purifier.
*/
const VERSION = '4.7.0';
/**
* Global configuration object.
* @type HTMLPurifier_Config
*/
public $config;
/**
* Array of extra filter objects to run on HTML,
* for backwards compatibility.
* @type HTMLPurifier_Filter[]
*/
private $filters = array();
/**
* Single instance of HTML Purifier.
* @type HTMLPurifier
*/
private static $instance;
/**
* @type HTMLPurifier_Strategy_Core
*/
protected $strategy;
/**
* @type HTMLPurifier_Generator
*/
protected $generator;
/**
* Resultant context of last run purification.
* Is an array of contexts if the last called method was purifyArray().
* @type HTMLPurifier_Context
*/
public $context;
/**
* Initializes the purifier.
* @param $config Optional HTMLPurifier_Config object for all instances of
* the purifier, if omitted, a default configuration is
* supplied (which can be overridden on a per-use basis).
*
* @param HTMLPurifier_Config $config Optional HTMLPurifier_Config object
* for all instances of the purifier, if omitted, a default
* configuration is supplied (which can be overridden on a
* per-use basis).
* The parameter can also be any type that
* HTMLPurifier_Config::create() supports.
*/
public function __construct($config = null) {
public function __construct($config = null)
{
$this->config = HTMLPurifier_Config::create($config);
$this->strategy = new HTMLPurifier_Strategy_Core();
$this->strategy = new HTMLPurifier_Strategy_Core();
}
/**
* Adds a filter to process the output. First come first serve
* @param $filter HTMLPurifier_Filter object
*
* @param HTMLPurifier_Filter $filter HTMLPurifier_Filter object
*/
public function addFilter($filter) {
trigger_error('HTMLPurifier->addFilter() is deprecated, use configuration directives in the Filter namespace or Filter.Custom', E_USER_WARNING);
public function addFilter($filter)
{
trigger_error(
'HTMLPurifier->addFilter() is deprecated, use configuration directives' .
' in the Filter namespace or Filter.Custom',
E_USER_WARNING
);
$this->filters[] = $filter;
}
/**
* Filters an HTML snippet/document to be XSS-free and standards-compliant.
*
* @param $html String of HTML to purify
* @param $config HTMLPurifier_Config object for this operation, if omitted,
* defaults to the config object specified during this
* @param string $html String of HTML to purify
* @param HTMLPurifier_Config $config Config object for this operation,
* if omitted, defaults to the config object specified during this
* object's construction. The parameter can also be any type
* that HTMLPurifier_Config::create() supports.
* @return Purified HTML
*
* @return string Purified HTML
*/
public function purify($html, $config = null) {
public function purify($html, $config = null)
{
// :TODO: make the config merge in, instead of replace
$config = $config ? HTMLPurifier_Config::create($config) : $this->config;
@ -151,8 +182,12 @@ class HTMLPurifier
unset($filter_flags['Custom']);
$filters = array();
foreach ($filter_flags as $filter => $flag) {
if (!$flag) continue;
if (strpos($filter, '.') !== false) continue;
if (!$flag) {
continue;
}
if (strpos($filter, '.') !== false) {
continue;
}
$class = "HTMLPurifier_Filter_$filter";
$filters[] = new $class;
}
@ -175,9 +210,12 @@ class HTMLPurifier
// list of un-purified tokens
$lexer->tokenizeHTML(
// un-purified HTML
$html, $config, $context
$html,
$config,
$context
),
$config, $context
$config,
$context
)
);
@ -192,11 +230,15 @@ class HTMLPurifier
/**
* Filters an array of HTML snippets
* @param $config Optional HTMLPurifier_Config object for this operation.
*
* @param string[] $array_of_html Array of html snippets
* @param HTMLPurifier_Config $config Optional config object for this operation.
* See HTMLPurifier::purify() for more details.
* @return Array of purified HTML
*
* @return string[] Array of purified HTML
*/
public function purifyArray($array_of_html, $config = null) {
public function purifyArray($array_of_html, $config = null)
{
$context_array = array();
foreach ($array_of_html as $key => $html) {
$array_of_html[$key] = $this->purify($html, $config);
@ -208,11 +250,16 @@ class HTMLPurifier
/**
* Singleton for enforcing just one HTML Purifier in your system
* @param $prototype Optional prototype HTMLPurifier instance to
* overload singleton with, or HTMLPurifier_Config
* instance to configure the generated version with.
*
* @param HTMLPurifier|HTMLPurifier_Config $prototype Optional prototype
* HTMLPurifier instance to overload singleton with,
* or HTMLPurifier_Config instance to configure the
* generated version with.
*
* @return HTMLPurifier
*/
public static function instance($prototype = null) {
public static function instance($prototype = null)
{
if (!self::$instance || $prototype) {
if ($prototype instanceof HTMLPurifier) {
self::$instance = $prototype;
@ -226,12 +273,20 @@ class HTMLPurifier
}
/**
* Singleton for enforcing just one HTML Purifier in your system
*
* @param HTMLPurifier|HTMLPurifier_Config $prototype Optional prototype
* HTMLPurifier instance to overload singleton with,
* or HTMLPurifier_Config instance to configure the
* generated version with.
*
* @return HTMLPurifier
* @note Backwards compatibility, see instance()
*/
public static function getInstance($prototype = null) {
public static function getInstance($prototype = null)
{
return HTMLPurifier::instance($prototype);
}
}
// vim: et sw=4 sts=4

19
library/HTMLPurifier.safe-includes.php → library/ezyang/htmlpurifier/library/HTMLPurifier.safe-includes.php
View file

@ -13,6 +13,7 @@
$__dir = dirname(__FILE__);
require_once $__dir . '/HTMLPurifier.php';
require_once $__dir . '/HTMLPurifier/Arborize.php';
require_once $__dir . '/HTMLPurifier/AttrCollections.php';
require_once $__dir . '/HTMLPurifier/AttrDef.php';
require_once $__dir . '/HTMLPurifier/AttrTransform.php';
@ -48,9 +49,11 @@ require_once $__dir . '/HTMLPurifier/Language.php';
require_once $__dir . '/HTMLPurifier/LanguageFactory.php';
require_once $__dir . '/HTMLPurifier/Length.php';
require_once $__dir . '/HTMLPurifier/Lexer.php';
require_once $__dir . '/HTMLPurifier/Node.php';
require_once $__dir . '/HTMLPurifier/PercentEncoder.php';
require_once $__dir . '/HTMLPurifier/PropertyList.php';
require_once $__dir . '/HTMLPurifier/PropertyListIterator.php';
require_once $__dir . '/HTMLPurifier/Queue.php';
require_once $__dir . '/HTMLPurifier/Strategy.php';
require_once $__dir . '/HTMLPurifier/StringHash.php';
require_once $__dir . '/HTMLPurifier/StringHashParser.php';
@ -66,7 +69,9 @@ require_once $__dir . '/HTMLPurifier/URISchemeRegistry.php';
require_once $__dir . '/HTMLPurifier/UnitConverter.php';
require_once $__dir . '/HTMLPurifier/VarParser.php';
require_once $__dir . '/HTMLPurifier/VarParserException.php';
require_once $__dir . '/HTMLPurifier/Zipper.php';
require_once $__dir . '/HTMLPurifier/AttrDef/CSS.php';
require_once $__dir . '/HTMLPurifier/AttrDef/Clone.php';
require_once $__dir . '/HTMLPurifier/AttrDef/Enum.php';
require_once $__dir . '/HTMLPurifier/AttrDef/Integer.php';
require_once $__dir . '/HTMLPurifier/AttrDef/Lang.php';
@ -84,6 +89,7 @@ require_once $__dir . '/HTMLPurifier/AttrDef/CSS/DenyElementDecorator.php';
require_once $__dir . '/HTMLPurifier/AttrDef/CSS/Filter.php';
require_once $__dir . '/HTMLPurifier/AttrDef/CSS/Font.php';
require_once $__dir . '/HTMLPurifier/AttrDef/CSS/FontFamily.php';
require_once $__dir . '/HTMLPurifier/AttrDef/CSS/Ident.php';
require_once $__dir . '/HTMLPurifier/AttrDef/CSS/ImportantDecorator.php';
require_once $__dir . '/HTMLPurifier/AttrDef/CSS/Length.php';
require_once $__dir . '/HTMLPurifier/AttrDef/CSS/ListStyle.php';
@ -119,14 +125,17 @@ require_once $__dir . '/HTMLPurifier/AttrTransform/Lang.php';
require_once $__dir . '/HTMLPurifier/AttrTransform/Length.php';
require_once $__dir . '/HTMLPurifier/AttrTransform/Name.php';
require_once $__dir . '/HTMLPurifier/AttrTransform/NameSync.php';
require_once $__dir . '/HTMLPurifier/AttrTransform/Nofollow.php';
require_once $__dir . '/HTMLPurifier/AttrTransform/SafeEmbed.php';
require_once $__dir . '/HTMLPurifier/AttrTransform/SafeObject.php';
require_once $__dir . '/HTMLPurifier/AttrTransform/SafeParam.php';
require_once $__dir . '/HTMLPurifier/AttrTransform/ScriptRequired.php';
require_once $__dir . '/HTMLPurifier/AttrTransform/TargetBlank.php';
require_once $__dir . '/HTMLPurifier/AttrTransform/Textarea.php';
require_once $__dir . '/HTMLPurifier/ChildDef/Chameleon.php';
require_once $__dir . '/HTMLPurifier/ChildDef/Custom.php';
require_once $__dir . '/HTMLPurifier/ChildDef/Empty.php';
require_once $__dir . '/HTMLPurifier/ChildDef/List.php';
require_once $__dir . '/HTMLPurifier/ChildDef/Required.php';
require_once $__dir . '/HTMLPurifier/ChildDef/Optional.php';
require_once $__dir . '/HTMLPurifier/ChildDef/StrictBlockquote.php';
@ -141,10 +150,12 @@ require_once $__dir . '/HTMLPurifier/HTMLModule/CommonAttributes.php';
require_once $__dir . '/HTMLPurifier/HTMLModule/Edit.php';
require_once $__dir . '/HTMLPurifier/HTMLModule/Forms.php';
require_once $__dir . '/HTMLPurifier/HTMLModule/Hypertext.php';
require_once $__dir . '/HTMLPurifier/HTMLModule/Iframe.php';
require_once $__dir . '/HTMLPurifier/HTMLModule/Image.php';
require_once $__dir . '/HTMLPurifier/HTMLModule/Legacy.php';
require_once $__dir . '/HTMLPurifier/HTMLModule/List.php';
require_once $__dir . '/HTMLPurifier/HTMLModule/Name.php';
require_once $__dir . '/HTMLPurifier/HTMLModule/Nofollow.php';
require_once $__dir . '/HTMLPurifier/HTMLModule/NonXMLCommonAttributes.php';
require_once $__dir . '/HTMLPurifier/HTMLModule/Object.php';
require_once $__dir . '/HTMLPurifier/HTMLModule/Presentation.php';
@ -152,10 +163,12 @@ require_once $__dir . '/HTMLPurifier/HTMLModule/Proprietary.php';
require_once $__dir . '/HTMLPurifier/HTMLModule/Ruby.php';
require_once $__dir . '/HTMLPurifier/HTMLModule/SafeEmbed.php';
require_once $__dir . '/HTMLPurifier/HTMLModule/SafeObject.php';
require_once $__dir . '/HTMLPurifier/HTMLModule/SafeScripting.php';
require_once $__dir . '/HTMLPurifier/HTMLModule/Scripting.php';
require_once $__dir . '/HTMLPurifier/HTMLModule/StyleAttribute.php';
require_once $__dir . '/HTMLPurifier/HTMLModule/Tables.php';
require_once $__dir . '/HTMLPurifier/HTMLModule/Target.php';
require_once $__dir . '/HTMLPurifier/HTMLModule/TargetBlank.php';
require_once $__dir . '/HTMLPurifier/HTMLModule/Text.php';
require_once $__dir . '/HTMLPurifier/HTMLModule/Tidy.php';
require_once $__dir . '/HTMLPurifier/HTMLModule/XMLCommonAttributes.php';
@ -174,6 +187,9 @@ require_once $__dir . '/HTMLPurifier/Injector/RemoveSpansWithoutAttributes.php';
require_once $__dir . '/HTMLPurifier/Injector/SafeObject.php';
require_once $__dir . '/HTMLPurifier/Lexer/DOMLex.php';
require_once $__dir . '/HTMLPurifier/Lexer/DirectLex.php';
require_once $__dir . '/HTMLPurifier/Node/Comment.php';
require_once $__dir . '/HTMLPurifier/Node/Element.php';
require_once $__dir . '/HTMLPurifier/Node/Text.php';
require_once $__dir . '/HTMLPurifier/Strategy/Composite.php';
require_once $__dir . '/HTMLPurifier/Strategy/Core.php';
require_once $__dir . '/HTMLPurifier/Strategy/FixNesting.php';
@ -190,10 +206,13 @@ require_once $__dir . '/HTMLPurifier/Token/Start.php';
require_once $__dir . '/HTMLPurifier/Token/Text.php';
require_once $__dir . '/HTMLPurifier/URIFilter/DisableExternal.php';
require_once $__dir . '/HTMLPurifier/URIFilter/DisableExternalResources.php';
require_once $__dir . '/HTMLPurifier/URIFilter/DisableResources.php';
require_once $__dir . '/HTMLPurifier/URIFilter/HostBlacklist.php';
require_once $__dir . '/HTMLPurifier/URIFilter/MakeAbsolute.php';
require_once $__dir . '/HTMLPurifier/URIFilter/Munge.php';
require_once $__dir . '/HTMLPurifier/URIFilter/SafeIframe.php';
require_once $__dir . '/HTMLPurifier/URIScheme/data.php';
require_once $__dir . '/HTMLPurifier/URIScheme/file.php';
require_once $__dir . '/HTMLPurifier/URIScheme/ftp.php';
require_once $__dir . '/HTMLPurifier/URIScheme/http.php';
require_once $__dir . '/HTMLPurifier/URIScheme/https.php';

71
library/ezyang/htmlpurifier/library/HTMLPurifier/Arborize.php Normal file
View file

@ -0,0 +1,71 @@
<?php
/**
* Converts a stream of HTMLPurifier_Token into an HTMLPurifier_Node,
* and back again.
*
* @note This transformation is not an equivalence. We mutate the input
* token stream to make it so; see all [MUT] markers in code.
*/
class HTMLPurifier_Arborize
{
public static function arborize($tokens, $config, $context) {
$definition = $config->getHTMLDefinition();
$parent = new HTMLPurifier_Token_Start($definition->info_parent);
$stack = array($parent->toNode());
foreach ($tokens as $token) {
$token->skip = null; // [MUT]
$token->carryover = null; // [MUT]
if ($token instanceof HTMLPurifier_Token_End) {
$token->start = null; // [MUT]
$r = array_pop($stack);
assert($r->name === $token->name);
assert(empty($token->attr));
$r->endCol = $token->col;
$r->endLine = $token->line;
$r->endArmor = $token->armor;
continue;
}
$node = $token->toNode();
$stack[count($stack)-1]->children[] = $node;
if ($token instanceof HTMLPurifier_Token_Start) {
$stack[] = $node;
}
}
assert(count($stack) == 1);
return $stack[0];
}
public static function flatten($node, $config, $context) {
$level = 0;
$nodes = array($level => new HTMLPurifier_Queue(array($node)));
$closingTokens = array();
$tokens = array();
do {
while (!$nodes[$level]->isEmpty()) {
$node = $nodes[$level]->shift(); // FIFO
list($start, $end) = $node->toTokenPair();
if ($level > 0) {
$tokens[] = $start;
}
if ($end !== NULL) {
$closingTokens[$level][] = $end;
}
if ($node instanceof HTMLPurifier_Node_Element) {
$level++;
$nodes[$level] = new HTMLPurifier_Queue();
foreach ($node->children as $childNode) {
$nodes[$level]->push($childNode);
}
}
}
$level--;
if ($level && isset($closingTokens[$level])) {
while ($token = array_pop($closingTokens[$level])) {
$tokens[] = $token;
}
}
} while ($level > 0);
return $tokens;
}
}

53
library/HTMLPurifier/AttrCollections.php → library/ezyang/htmlpurifier/library/HTMLPurifier/AttrCollections.php
View file

@ -8,7 +8,8 @@ class HTMLPurifier_AttrCollections
{
/**
* Associative array of attribute collections, indexed by name
* Associative array of attribute collections, indexed by name.
* @type array
*/
public $info = array();
@ -16,10 +17,11 @@ class HTMLPurifier_AttrCollections
* Performs all expansions on internal data for use by other inclusions
* It also collects all attribute collection extensions from
* modules
* @param $attr_types HTMLPurifier_AttrTypes instance
* @param $modules Hash array of HTMLPurifier_HTMLModule members
* @param HTMLPurifier_AttrTypes $attr_types HTMLPurifier_AttrTypes instance
* @param HTMLPurifier_HTMLModule[] $modules Hash array of HTMLPurifier_HTMLModule members
*/
public function __construct($attr_types, $modules) {
public function __construct($attr_types, $modules)
{
// load extensions from the modules
foreach ($modules as $module) {
foreach ($module->attr_collections as $coll_i => $coll) {
@ -30,7 +32,9 @@ class HTMLPurifier_AttrCollections
if ($attr_i === 0 && isset($this->info[$coll_i][$attr_i])) {
// merge in includes
$this->info[$coll_i][$attr_i] = array_merge(
$this->info[$coll_i][$attr_i], $attr);
$this->info[$coll_i][$attr_i],
$attr
);
continue;
}
$this->info[$coll_i][$attr_i] = $attr;
@ -49,20 +53,29 @@ class HTMLPurifier_AttrCollections
/**
* Takes a reference to an attribute associative array and performs
* all inclusions specified by the zero index.
* @param &$attr Reference to attribute array
* @param array &$attr Reference to attribute array
*/
public function performInclusions(&$attr) {
if (!isset($attr[0])) return;
public function performInclusions(&$attr)
{
if (!isset($attr[0])) {
return;
}
$merge = $attr[0];
$seen = array(); // recursion guard
// loop through all the inclusions
for ($i = 0; isset($merge[$i]); $i++) {
if (isset($seen[$merge[$i]])) continue;
if (isset($seen[$merge[$i]])) {
continue;
}
$seen[$merge[$i]] = true;
// foreach attribute of the inclusion, copy it over
if (!isset($this->info[$merge[$i]])) continue;
if (!isset($this->info[$merge[$i]])) {
continue;
}
foreach ($this->info[$merge[$i]] as $key => $value) {
if (isset($attr[$key])) continue; // also catches more inclusions
if (isset($attr[$key])) {
continue;
} // also catches more inclusions
$attr[$key] = $value;
}
if (isset($this->info[$merge[$i]][0])) {
@ -76,20 +89,24 @@ class HTMLPurifier_AttrCollections
/**
* Expands all string identifiers in an attribute array by replacing
* them with the appropriate values inside HTMLPurifier_AttrTypes
* @param &$attr Reference to attribute array
* @param $attr_types HTMLPurifier_AttrTypes instance
* @param array &$attr Reference to attribute array
* @param HTMLPurifier_AttrTypes $attr_types HTMLPurifier_AttrTypes instance
*/
public function expandIdentifiers(&$attr, $attr_types) {
public function expandIdentifiers(&$attr, $attr_types)
{
// because foreach will process new elements we add, make sure we
// skip duplicates
$processed = array();
foreach ($attr as $def_i => $def) {
// skip inclusions
if ($def_i === 0) continue;
if ($def_i === 0) {
continue;
}
if (isset($processed[$def_i])) continue;
if (isset($processed[$def_i])) {
continue;
}
// determine whether or not attribute is required
if ($required = (strpos($def_i, '*') !== false)) {
@ -120,9 +137,7 @@ class HTMLPurifier_AttrCollections
unset($attr[$def_i]);
}
}
}
}
// vim: et sw=4 sts=4

51
library/HTMLPurifier/AttrDef.php → library/ezyang/htmlpurifier/library/HTMLPurifier/AttrDef.php
View file

@ -14,23 +14,25 @@ abstract class HTMLPurifier_AttrDef
{
/**
* Tells us whether or not an HTML attribute is minimized. Has no
* meaning in other contexts.
* Tells us whether or not an HTML attribute is minimized.
* Has no meaning in other contexts.
* @type bool
*/
public $minimized = false;
/**
* Tells us whether or not an HTML attribute is required. Has no
* meaning in other contexts
* Tells us whether or not an HTML attribute is required.
* Has no meaning in other contexts
* @type bool
*/
public $required = false;
/**
* Validates and cleans passed string according to a definition.
*
* @param $string String to be validated and cleaned.
* @param $config Mandatory HTMLPurifier_Config object.
* @param $context Mandatory HTMLPurifier_AttrContext object.
* @param string $string String to be validated and cleaned.
* @param HTMLPurifier_Config $config Mandatory HTMLPurifier_Config object.
* @param HTMLPurifier_Context $context Mandatory HTMLPurifier_Context object.
*/
abstract public function validate($string, $config, $context);
@ -55,7 +57,8 @@ abstract class HTMLPurifier_AttrDef
* parsing XML, thus, this behavior may still be correct. We
* assume that newlines have been normalized.
*/
public function parseCDATA($string) {
public function parseCDATA($string)
{
$string = trim($string);
$string = str_replace(array("\n", "\t", "\r"), ' ', $string);
return $string;
@ -63,10 +66,11 @@ abstract class HTMLPurifier_AttrDef
/**
* Factory method for creating this class from a string.
* @param $string String construction info
* @return Created AttrDef object corresponding to $string
* @param string $string String construction info
* @return HTMLPurifier_AttrDef Created AttrDef object corresponding to $string
*/
public function make($string) {
public function make($string)
{
// default implementation, return a flyweight of this object.
// If $string has an effect on the returned object (i.e. you
// need to overload this method), it is best
@ -77,8 +81,11 @@ abstract class HTMLPurifier_AttrDef
/**
* Removes spaces from rgb(0, 0, 0) so that shorthand CSS properties work
* properly. THIS IS A HACK!
* @param string $string a CSS colour definition
* @return string
*/
protected function mungeRgb($string) {
protected function mungeRgb($string)
{
return preg_replace('/rgb\((\d+)\s*,\s*(\d+)\s*,\s*(\d+)\)/', 'rgb(\1,\2,\3)', $string);
}
@ -86,7 +93,8 @@ abstract class HTMLPurifier_AttrDef
* Parses a possibly escaped CSS string and returns the "pure"
* version of it.
*/
protected function expandCSSEscape($string) {
protected function expandCSSEscape($string)
{
// flexibly parse it
$ret = '';
for ($i = 0, $c = strlen($string); $i < $c; $i++) {
@ -99,25 +107,32 @@ abstract class HTMLPurifier_AttrDef
if (ctype_xdigit($string[$i])) {
$code = $string[$i];
for ($a = 1, $i++; $i < $c && $a < 6; $i++, $a++) {
if (!ctype_xdigit($string[$i])) break;
if (!ctype_xdigit($string[$i])) {
break;
}
$code .= $string[$i];
}
// We have to be extremely careful when adding
// new characters, to make sure we're not breaking
// the encoding.
$char = HTMLPurifier_Encoder::unichr(hexdec($code));
if (HTMLPurifier_Encoder::cleanUTF8($char) === '') continue;
if (HTMLPurifier_Encoder::cleanUTF8($char) === '') {
continue;
}
$ret .= $char;
if ($i < $c && trim($string[$i]) !== '') $i--;
if ($i < $c && trim($string[$i]) !== '') {
$i--;
}
continue;
}
if ($string[$i] === "\n") {
continue;
}
if ($string[$i] === "\n") continue;
}
$ret .= $string[$i];
}
return $ret;
}
}
// vim: et sw=4 sts=4

39
library/HTMLPurifier/AttrDef/CSS.php → library/ezyang/htmlpurifier/library/HTMLPurifier/AttrDef/CSS.php
View file

@ -14,8 +14,14 @@
class HTMLPurifier_AttrDef_CSS extends HTMLPurifier_AttrDef
{
public function validate($css, $config, $context) {
/**
* @param string $css
* @param HTMLPurifier_Config $config
* @param HTMLPurifier_Context $context
* @return bool|string
*/
public function validate($css, $config, $context)
{
$css = $this->parseCDATA($css);
$definition = $config->getCSSDefinition();
@ -36,34 +42,47 @@ class HTMLPurifier_AttrDef_CSS extends HTMLPurifier_AttrDef
$context->register('CurrentCSSProperty', $property);
foreach ($declarations as $declaration) {
if (!$declaration) continue;
if (!strpos($declaration, ':')) continue;
if (!$declaration) {
continue;
}
if (!strpos($declaration, ':')) {
continue;
}
list($property, $value) = explode(':', $declaration, 2);
$property = trim($property);
$value = trim($value);
$value = trim($value);
$ok = false;
do {
if (isset($definition->info[$property])) {
$ok = true;
break;
}
if (ctype_lower($property)) break;
if (ctype_lower($property)) {
break;
}
$property = strtolower($property);
if (isset($definition->info[$property])) {
$ok = true;
break;
}
} while(0);
if (!$ok) continue;
} while (0);
if (!$ok) {
continue;
}
// inefficient call, since the validator will do this again
if (strtolower(trim($value)) !== 'inherit') {
// inherit works for everything (but only on the base property)
$result = $definition->info[$property]->validate(
$value, $config, $context );
$value,
$config,
$context
);
} else {
$result = 'inherit';
}
if ($result === false) continue;
if ($result === false) {
continue;
}
$propvalues[$property] = $result;
}

34
library/ezyang/htmlpurifier/library/HTMLPurifier/AttrDef/CSS/AlphaValue.php Normal file
View file

@ -0,0 +1,34 @@
<?php
class HTMLPurifier_AttrDef_CSS_AlphaValue extends HTMLPurifier_AttrDef_CSS_Number
{
public function __construct()
{
parent::__construct(false); // opacity is non-negative, but we will clamp it
}
/**
* @param string $number
* @param HTMLPurifier_Config $config
* @param HTMLPurifier_Context $context
* @return string
*/
public function validate($number, $config, $context)
{
$result = parent::validate($number, $config, $context);
if ($result === false) {
return $result;
}
$float = (float)$result;
if ($float < 0.0) {
$result = '0';
}
if ($float > 1.0) {
$result = '1';
}
return $result;
}
}
// vim: et sw=4 sts=4

60
library/HTMLPurifier/AttrDef/CSS/Background.php → library/ezyang/htmlpurifier/library/HTMLPurifier/AttrDef/CSS/Background.php
View file

@ -9,11 +9,16 @@ class HTMLPurifier_AttrDef_CSS_Background extends HTMLPurifier_AttrDef
/**
* Local copy of component validators.
* @type HTMLPurifier_AttrDef[]
* @note See HTMLPurifier_AttrDef_Font::$info for a similar impl.
*/
protected $info;
public function __construct($config) {
/**
* @param HTMLPurifier_Config $config
*/
public function __construct($config)
{
$def = $config->getCSSDefinition();
$this->info['background-color'] = $def->info['background-color'];
$this->info['background-image'] = $def->info['background-image'];
@ -22,40 +27,55 @@ class HTMLPurifier_AttrDef_CSS_Background extends HTMLPurifier_AttrDef
$this->info['background-position'] = $def->info['background-position'];
}
public function validate($string, $config, $context) {
/**
* @param string $string
* @param HTMLPurifier_Config $config
* @param HTMLPurifier_Context $context
* @return bool|string
*/
public function validate($string, $config, $context)
{
// regular pre-processing
$string = $this->parseCDATA($string);
if ($string === '') return false;
if ($string === '') {
return false;
}
// munge rgb() decl if necessary
$string = $this->mungeRgb($string);
// assumes URI doesn't have spaces in it
$bits = explode(' ', strtolower($string)); // bits to process
$bits = explode(' ', $string); // bits to process
$caught = array();
$caught['color'] = false;
$caught['image'] = false;
$caught['repeat'] = false;
$caught['color'] = false;
$caught['image'] = false;
$caught['repeat'] = false;
$caught['attachment'] = false;
$caught['position'] = false;
$i = 0; // number of catches
$none = false;
foreach ($bits as $bit) {
if ($bit === '') continue;
if ($bit === '') {
continue;
}
foreach ($caught as $key => $status) {
if ($key != 'position') {
if ($status !== false) continue;
if ($status !== false) {
continue;
}
$r = $this->info['background-' . $key]->validate($bit, $config, $context);
} else {
$r = $bit;
}
if ($r === false) continue;
if ($r === false) {
continue;
}
if ($key == 'position') {
if ($caught[$key] === false) $caught[$key] = '';
if ($caught[$key] === false) {
$caught[$key] = '';
}
$caught[$key] .= $r . ' ';
} else {
$caught[$key] = $r;
@ -65,7 +85,9 @@ class HTMLPurifier_AttrDef_CSS_Background extends HTMLPurifier_AttrDef
}
}
if (!$i) return false;
if (!$i) {
return false;
}
if ($caught['position'] !== false) {
$caught['position'] = $this->info['background-position']->
validate($caught['position'], $config, $context);
@ -73,15 +95,17 @@ class HTMLPurifier_AttrDef_CSS_Background extends HTMLPurifier_AttrDef
$ret = array();
foreach ($caught as $value) {
if ($value === false) continue;
if ($value === false) {
continue;
}
$ret[] = $value;
}
if (empty($ret)) return false;
if (empty($ret)) {
return false;
}
return implode(' ', $ret);
}
}
// vim: et sw=4 sts=4

54
library/HTMLPurifier/AttrDef/CSS/BackgroundPosition.php → library/ezyang/htmlpurifier/library/HTMLPurifier/AttrDef/CSS/BackgroundPosition.php
View file

@ -44,15 +44,30 @@
class HTMLPurifier_AttrDef_CSS_BackgroundPosition extends HTMLPurifier_AttrDef
{
/**
* @type HTMLPurifier_AttrDef_CSS_Length
*/
protected $length;
/**
* @type HTMLPurifier_AttrDef_CSS_Percentage
*/
protected $percentage;
public function __construct() {
$this->length = new HTMLPurifier_AttrDef_CSS_Length();
public function __construct()
{
$this->length = new HTMLPurifier_AttrDef_CSS_Length();
$this->percentage = new HTMLPurifier_AttrDef_CSS_Percentage();
}
public function validate($string, $config, $context) {
/**
* @param string $string
* @param HTMLPurifier_Config $config
* @param HTMLPurifier_Context $context
* @return bool|string
*/
public function validate($string, $config, $context)
{
$string = $this->parseCDATA($string);
$bits = explode(' ', $string);
@ -74,7 +89,9 @@ class HTMLPurifier_AttrDef_CSS_BackgroundPosition extends HTMLPurifier_AttrDef
);
foreach ($bits as $bit) {
if ($bit === '') continue;
if ($bit === '') {
continue;
}
// test for keyword
$lbit = ctype_lower($bit) ? $bit : strtolower($bit);
@ -104,30 +121,37 @@ class HTMLPurifier_AttrDef_CSS_BackgroundPosition extends HTMLPurifier_AttrDef
$measures[] = $r;
$i++;
}
}
if (!$i) return false; // no valid values were caught
if (!$i) {
return false;
} // no valid values were caught
$ret = array();
// first keyword
if ($keywords['h']) $ret[] = $keywords['h'];
elseif ($keywords['ch']) {
if ($keywords['h']) {
$ret[] = $keywords['h'];
} elseif ($keywords['ch']) {
$ret[] = $keywords['ch'];
$keywords['cv'] = false; // prevent re-use: center = center center
} elseif (count($measures)) {
$ret[] = array_shift($measures);
}
elseif (count($measures)) $ret[] = array_shift($measures);
if ($keywords['v']) $ret[] = $keywords['v'];
elseif ($keywords['cv']) $ret[] = $keywords['cv'];
elseif (count($measures)) $ret[] = array_shift($measures);
if ($keywords['v']) {
$ret[] = $keywords['v'];
} elseif ($keywords['cv']) {
$ret[] = $keywords['cv'];
} elseif (count($measures)) {
$ret[] = array_shift($measures);
}
if (empty($ret)) return false;
if (empty($ret)) {
return false;
}
return implode(' ', $ret);
}
}
// vim: et sw=4 sts=4

21
library/HTMLPurifier/AttrDef/CSS/Border.php → library/ezyang/htmlpurifier/library/HTMLPurifier/AttrDef/CSS/Border.php
View file

@ -8,17 +8,29 @@ class HTMLPurifier_AttrDef_CSS_Border extends HTMLPurifier_AttrDef
/**
* Local copy of properties this property is shorthand for.
* @type HTMLPurifier_AttrDef[]
*/
protected $info = array();
public function __construct($config) {
/**
* @param HTMLPurifier_Config $config
*/
public function __construct($config)
{
$def = $config->getCSSDefinition();
$this->info['border-width'] = $def->info['border-width'];
$this->info['border-style'] = $def->info['border-style'];
$this->info['border-top-color'] = $def->info['border-top-color'];
}
public function validate($string, $config, $context) {
/**
* @param string $string
* @param HTMLPurifier_Config $config
* @param HTMLPurifier_Context $context
* @return bool|string
*/
public function validate($string, $config, $context)
{
$string = $this->parseCDATA($string);
$string = $this->mungeRgb($string);
$bits = explode(' ', $string);
@ -26,7 +38,9 @@ class HTMLPurifier_AttrDef_CSS_Border extends HTMLPurifier_AttrDef
$ret = ''; // return value
foreach ($bits as $bit) {
foreach ($this->info as $propname => $validator) {
if (isset($done[$propname])) continue;
if (isset($done[$propname])) {
continue;
}
$r = $validator->validate($bit, $config, $context);
if ($r !== false) {
$ret .= $r . ' ';
@ -37,7 +51,6 @@ class HTMLPurifier_AttrDef_CSS_Border extends HTMLPurifier_AttrDef
}
return rtrim($ret);
}
}
// vim: et sw=4 sts=4

67
library/HTMLPurifier/AttrDef/CSS/Color.php → library/ezyang/htmlpurifier/library/HTMLPurifier/AttrDef/CSS/Color.php
View file

@ -6,29 +6,47 @@
class HTMLPurifier_AttrDef_CSS_Color extends HTMLPurifier_AttrDef
{
public function validate($color, $config, $context) {
/**
* @param string $color
* @param HTMLPurifier_Config $config
* @param HTMLPurifier_Context $context
* @return bool|string
*/
public function validate($color, $config, $context)
{
static $colors = null;
if ($colors === null) $colors = $config->get('Core.ColorKeywords');
if ($colors === null) {
$colors = $config->get('Core.ColorKeywords');
}
$color = trim($color);
if ($color === '') return false;
if ($color === '') {
return false;
}
$lower = strtolower($color);
if (isset($colors[$lower])) return $colors[$lower];
if (isset($colors[$lower])) {
return $colors[$lower];
}
if (strpos($color, 'rgb(') !== false) {
// rgb literal handling
$length = strlen($color);
if (strpos($color, ')') !== $length - 1) return false;
if (strpos($color, ')') !== $length - 1) {
return false;
}
$triad = substr($color, 4, $length - 4 - 1);
$parts = explode(',', $triad);
if (count($parts) !== 3) return false;
if (count($parts) !== 3) {
return false;
}
$type = false; // to ensure that they're all the same type
$new_parts = array();
foreach ($parts as $part) {
$part = trim($part);
if ($part === '') return false;
if ($part === '') {
return false;
}
$length = strlen($part);
if ($part[$length - 1] === '%') {
// handle percents
@ -37,9 +55,13 @@ class HTMLPurifier_AttrDef_CSS_Color extends HTMLPurifier_AttrDef
} elseif ($type !== 'percentage') {
return false;
}
$num = (float) substr($part, 0, $length - 1);
if ($num < 0) $num = 0;
if ($num > 100) $num = 100;
$num = (float)substr($part, 0, $length - 1);
if ($num < 0) {
$num = 0;
}
if ($num > 100) {
$num = 100;
}
$new_parts[] = "$num%";
} else {
// handle integers
@ -48,10 +70,14 @@ class HTMLPurifier_AttrDef_CSS_Color extends HTMLPurifier_AttrDef
} elseif ($type !== 'integer') {
return false;
}
$num = (int) $part;
if ($num < 0) $num = 0;
if ($num > 255) $num = 255;
$new_parts[] = (string) $num;
$num = (int)$part;
if ($num < 0) {
$num = 0;
}
if ($num > 255) {
$num = 255;
}
$new_parts[] = (string)$num;
}
}
$new_triad = implode(',', $new_parts);
@ -65,14 +91,15 @@ class HTMLPurifier_AttrDef_CSS_Color extends HTMLPurifier_AttrDef
$color = '#' . $color;
}
$length = strlen($hex);
if ($length !== 3 && $length !== 6) return false;
if (!ctype_xdigit($hex)) return false;
if ($length !== 3 && $length !== 6) {
return false;
}
if (!ctype_xdigit($hex)) {
return false;
}
}
return $color;
}
}
// vim: et sw=4 sts=4

Some files were not shown because too many files have changed in this diff Show more