friendica/friendica
6
2
Fork 1
mirror of https://github.com/friendica/friendica synced 2026-01-13 20:08:43 +01:00
Code Issues Projects Releases 3 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
commit c28109ca94
465 changed files with 22433 additions and 10865 deletions
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

@ -1,3906 +0,0 @@
<?php
/**
* Experimental HTML5-based parser using Jeroen van der Meer's PH5P library.
* Occupies space in the HTML5 pseudo-namespace, which may cause conflicts.
*
* @note
* Recent changes to PHP's DOM extension have resulted in some fatal
* error conditions with the original version of PH5P. Pending changes,
* this lexer will punt to DirectLex if DOM throughs an exception.
*/
class HTMLPurifier_Lexer_PH5P extends HTMLPurifier_Lexer_DOMLex {
public function tokenizeHTML($html, $config, $context) {
$new_html = $this->normalize($html, $config, $context);
$new_html = $this->wrapHTML($new_html, $config, $context);
try {
$parser = new HTML5($new_html);
$doc = $parser->save();
} catch (DOMException $e) {
// Uh oh, it failed. Punt to DirectLex.
$lexer = new HTMLPurifier_Lexer_DirectLex();
$context->register('PH5PError', $e); // save the error, so we can detect it
return $lexer->tokenizeHTML($html, $config, $context); // use original HTML
}
$tokens = array();
$this->tokenizeDOM(
$doc->getElementsByTagName('html')->item(0)-> // <html>
getElementsByTagName('body')->item(0)-> // <body>
getElementsByTagName('div')->item(0) // <div>
, $tokens);
return $tokens;
}
}
/*
Copyright 2007 Jeroen van der Meer <http://jero.net/>
Permission is hereby granted, free of charge, to any person obtaining a
copy of this software and associated documentation files (the
"Software"), to deal in the Software without restriction, including
without limitation the rights to use, copy, modify, merge, publish,
distribute, sublicense, and/or sell copies of the Software, and to
permit persons to whom the Software is furnished to do so, subject to
the following conditions:
The above copyright notice and this permission notice shall be included
in all copies or substantial portions of the Software.
THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS
OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.
IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY
CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT,
TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN CONNECTION WITH THE
SOFTWARE OR THE USE OR OTHER DEALINGS IN THE SOFTWARE.
*/
class HTML5 {
private $data;
private $char;
private $EOF;
private $state;
private $tree;
private $token;
private $content_model;
private $escape = false;
private $entities = array('AElig;','AElig','AMP;','AMP','Aacute;','Aacute',
'Acirc;','Acirc','Agrave;','Agrave','Alpha;','Aring;','Aring','Atilde;',
'Atilde','Auml;','Auml','Beta;','COPY;','COPY','Ccedil;','Ccedil','Chi;',
'Dagger;','Delta;','ETH;','ETH','Eacute;','Eacute','Ecirc;','Ecirc','Egrave;',
'Egrave','Epsilon;','Eta;','Euml;','Euml','GT;','GT','Gamma;','Iacute;',
'Iacute','Icirc;','Icirc','Igrave;','Igrave','Iota;','Iuml;','Iuml','Kappa;',
'LT;','LT','Lambda;','Mu;','Ntilde;','Ntilde','Nu;','OElig;','Oacute;',
'Oacute','Ocirc;','Ocirc','Ograve;','Ograve','Omega;','Omicron;','Oslash;',
'Oslash','Otilde;','Otilde','Ouml;','Ouml','Phi;','Pi;','Prime;','Psi;',
'QUOT;','QUOT','REG;','REG','Rho;','Scaron;','Sigma;','THORN;','THORN',
'TRADE;','Tau;','Theta;','Uacute;','Uacute','Ucirc;','Ucirc','Ugrave;',
'Ugrave','Upsilon;','Uuml;','Uuml','Xi;','Yacute;','Yacute','Yuml;','Zeta;',
'aacute;','aacute','acirc;','acirc','acute;','acute','aelig;','aelig',
'agrave;','agrave','alefsym;','alpha;','amp;','amp','and;','ang;','apos;',
'aring;','aring','asymp;','atilde;','atilde','auml;','auml','bdquo;','beta;',
'brvbar;','brvbar','bull;','cap;','ccedil;','ccedil','cedil;','cedil',
'cent;','cent','chi;','circ;','clubs;','cong;','copy;','copy','crarr;',
'cup;','curren;','curren','dArr;','dagger;','darr;','deg;','deg','delta;',
'diams;','divide;','divide','eacute;','eacute','ecirc;','ecirc','egrave;',
'egrave','empty;','emsp;','ensp;','epsilon;','equiv;','eta;','eth;','eth',
'euml;','euml','euro;','exist;','fnof;','forall;','frac12;','frac12',
'frac14;','frac14','frac34;','frac34','frasl;','gamma;','ge;','gt;','gt',
'hArr;','harr;','hearts;','hellip;','iacute;','iacute','icirc;','icirc',
'iexcl;','iexcl','igrave;','igrave','image;','infin;','int;','iota;',
'iquest;','iquest','isin;','iuml;','iuml','kappa;','lArr;','lambda;','lang;',
'laquo;','laquo','larr;','lceil;','ldquo;','le;','lfloor;','lowast;','loz;',
'lrm;','lsaquo;','lsquo;','lt;','lt','macr;','macr','mdash;','micro;','micro',
'middot;','middot','minus;','mu;','nabla;','nbsp;','nbsp','ndash;','ne;',
'ni;','not;','not','notin;','nsub;','ntilde;','ntilde','nu;','oacute;',
'oacute','ocirc;','ocirc','oelig;','ograve;','ograve','oline;','omega;',
'omicron;','oplus;','or;','ordf;','ordf','ordm;','ordm','oslash;','oslash',
'otilde;','otilde','otimes;','ouml;','ouml','para;','para','part;','permil;',
'perp;','phi;','pi;','piv;','plusmn;','plusmn','pound;','pound','prime;',
'prod;','prop;','psi;','quot;','quot','rArr;','radic;','rang;','raquo;',
'raquo','rarr;','rceil;','rdquo;','real;','reg;','reg','rfloor;','rho;',
'rlm;','rsaquo;','rsquo;','sbquo;','scaron;','sdot;','sect;','sect','shy;',
'shy','sigma;','sigmaf;','sim;','spades;','sub;','sube;','sum;','sup1;',
'sup1','sup2;','sup2','sup3;','sup3','sup;','supe;','szlig;','szlig','tau;',
'there4;','theta;','thetasym;','thinsp;','thorn;','thorn','tilde;','times;',
'times','trade;','uArr;','uacute;','uacute','uarr;','ucirc;','ucirc',
'ugrave;','ugrave','uml;','uml','upsih;','upsilon;','uuml;','uuml','weierp;',
'xi;','yacute;','yacute','yen;','yen','yuml;','yuml','zeta;','zwj;','zwnj;');
const PCDATA = 0;
const RCDATA = 1;
const CDATA = 2;
const PLAINTEXT = 3;
const DOCTYPE = 0;
const STARTTAG = 1;
const ENDTAG = 2;
const COMMENT = 3;
const CHARACTR = 4;
const EOF = 5;
public function __construct($data) {
$data = str_replace("\r\n", "\n", $data);
$data = str_replace("\r", null, $data);
$this->data = $data;
$this->char = -1;
$this->EOF = strlen($data);
$this->tree = new HTML5TreeConstructer;
$this->content_model = self::PCDATA;
$this->state = 'data';
while($this->state !== null) {
$this->{$this->state.'State'}();
}
}
public function save() {
return $this->tree->save();
}
private function char() {
return ($this->char < $this->EOF)
? $this->data[$this->char]
: false;
}
private function character($s, $l = 0) {
if($s + $l < $this->EOF) {
if($l === 0) {
return $this->data[$s];
} else {
return substr($this->data, $s, $l);
}
}
}
private function characters($char_class, $start) {
return preg_replace('#^(['.$char_class.']+).*#s', '\\1', substr($this->data, $start));
}
private function dataState() {
// Consume the next input character
$this->char++;
$char = $this->char();
if($char === '&' && ($this->content_model === self::PCDATA || $this->content_model === self::RCDATA)) {
/* U+0026 AMPERSAND (&)
When the content model flag is set to one of the PCDATA or RCDATA
states: switch to the entity data state. Otherwise: treat it as per
the "anything else" entry below. */
$this->state = 'entityData';
} elseif($char === '-') {
/* If the content model flag is set to either the RCDATA state or
the CDATA state, and the escape flag is false, and there are at
least three characters before this one in the input stream, and the
last four characters in the input stream, including this one, are
U+003C LESS-THAN SIGN, U+0021 EXCLAMATION MARK, U+002D HYPHEN-MINUS,
and U+002D HYPHEN-MINUS ("<!--"), then set the escape flag to true. */
if(($this->content_model === self::RCDATA || $this->content_model ===
self::CDATA) && $this->escape === false &&
$this->char >= 3 && $this->character($this->char - 4, 4) === '<!--') {
$this->escape = true;
}
/* In any case, emit the input character as a character token. Stay
in the data state. */
$this->emitToken(array(
'type' => self::CHARACTR,
'data' => $char
));
/* U+003C LESS-THAN SIGN (<) */
} elseif($char === '<' && ($this->content_model === self::PCDATA ||
(($this->content_model === self::RCDATA ||
$this->content_model === self::CDATA) && $this->escape === false))) {
/* When the content model flag is set to the PCDATA state: switch
to the tag open state.
When the content model flag is set to either the RCDATA state or
the CDATA state and the escape flag is false: switch to the tag
open state.
Otherwise: treat it as per the "anything else" entry below. */
$this->state = 'tagOpen';
/* U+003E GREATER-THAN SIGN (>) */
} elseif($char === '>') {
/* If the content model flag is set to either the RCDATA state or
the CDATA state, and the escape flag is true, and the last three
characters in the input stream including this one are U+002D
HYPHEN-MINUS, U+002D HYPHEN-MINUS, U+003E GREATER-THAN SIGN ("-->"),
set the escape flag to false. */
if(($this->content_model === self::RCDATA ||
$this->content_model === self::CDATA) && $this->escape === true &&
$this->character($this->char, 3) === '-->') {
$this->escape = false;
}
/* In any case, emit the input character as a character token.
Stay in the data state. */
$this->emitToken(array(
'type' => self::CHARACTR,
'data' => $char
));
} elseif($this->char === $this->EOF) {
/* EOF
Emit an end-of-file token. */
$this->EOF();
} elseif($this->content_model === self::PLAINTEXT) {
/* When the content model flag is set to the PLAINTEXT state
THIS DIFFERS GREATLY FROM THE SPEC: Get the remaining characters of
the text and emit it as a character token. */
$this->emitToken(array(
'type' => self::CHARACTR,
'data' => substr($this->data, $this->char)
));
$this->EOF();
} else {
/* Anything else
THIS DIFFERS GREATLY FROM THE SPEC: Get as many character that
otherwise would also be treated as a character token and emit it
as a single character token. Stay in the data state. */
$len = strcspn($this->data, '<&', $this->char);
$char = substr($this->data, $this->char, $len);
$this->char += $len - 1;
$this->emitToken(array(
'type' => self::CHARACTR,
'data' => $char
));
$this->state = 'data';
}
}
private function entityDataState() {
// Attempt to consume an entity.
$entity = $this->entity();
// If nothing is returned, emit a U+0026 AMPERSAND character token.
// Otherwise, emit the character token that was returned.
$char = (!$entity) ? '&' : $entity;
$this->emitToken(array(
'type' => self::CHARACTR,
'data' => $char
));
// Finally, switch to the data state.
$this->state = 'data';
}
private function tagOpenState() {
switch($this->content_model) {
case self::RCDATA:
case self::CDATA:
/* If the next input character is a U+002F SOLIDUS (/) character,
consume it and switch to the close tag open state. If the next
input character is not a U+002F SOLIDUS (/) character, emit a
U+003C LESS-THAN SIGN character token and switch to the data
state to process the next input character. */
if($this->character($this->char + 1) === '/') {
$this->char++;
$this->state = 'closeTagOpen';
} else {
$this->emitToken(array(
'type' => self::CHARACTR,
'data' => '<'
));
$this->state = 'data';
}
break;
case self::PCDATA:
// If the content model flag is set to the PCDATA state
// Consume the next input character:
$this->char++;
$char = $this->char();
if($char === '!') {
/* U+0021 EXCLAMATION MARK (!)
Switch to the markup declaration open state. */
$this->state = 'markupDeclarationOpen';
} elseif($char === '/') {
/* U+002F SOLIDUS (/)
Switch to the close tag open state. */
$this->state = 'closeTagOpen';
} elseif(preg_match('/^[A-Za-z]$/', $char)) {
/* U+0041 LATIN LETTER A through to U+005A LATIN LETTER Z
Create a new start tag token, set its tag name to the lowercase
version of the input character (add 0x0020 to the character's code
point), then switch to the tag name state. (Don't emit the token
yet; further details will be filled in before it is emitted.) */
$this->token = array(
'name' => strtolower($char),
'type' => self::STARTTAG,
'attr' => array()
);
$this->state = 'tagName';
} elseif($char === '>') {
/* U+003E GREATER-THAN SIGN (>)
Parse error. Emit a U+003C LESS-THAN SIGN character token and a
U+003E GREATER-THAN SIGN character token. Switch to the data state. */
$this->emitToken(array(
'type' => self::CHARACTR,
'data' => '<>'
));
$this->state = 'data';
} elseif($char === '?') {
/* U+003F QUESTION MARK (?)
Parse error. Switch to the bogus comment state. */
$this->state = 'bogusComment';
} else {
/* Anything else
Parse error. Emit a U+003C LESS-THAN SIGN character token and
reconsume the current input character in the data state. */
$this->emitToken(array(
'type' => self::CHARACTR,
'data' => '<'
));
$this->char--;
$this->state = 'data';
}
break;
}
}
private function closeTagOpenState() {
$next_node = strtolower($this->characters('A-Za-z', $this->char + 1));
$the_same = count($this->tree->stack) > 0 && $next_node === end($this->tree->stack)->nodeName;
if(($this->content_model === self::RCDATA || $this->content_model === self::CDATA) &&
(!$the_same || ($the_same && (!preg_match('/[\t\n\x0b\x0c >\/]/',
$this->character($this->char + 1 + strlen($next_node))) || $this->EOF === $this->char)))) {
/* If the content model flag is set to the RCDATA or CDATA states then
examine the next few characters. If they do not match the tag name of
the last start tag token emitted (case insensitively), or if they do but
they are not immediately followed by one of the following characters:
* U+0009 CHARACTER TABULATION
* U+000A LINE FEED (LF)
* U+000B LINE TABULATION
* U+000C FORM FEED (FF)
* U+0020 SPACE
* U+003E GREATER-THAN SIGN (>)
* U+002F SOLIDUS (/)
* EOF
...then there is a parse error. Emit a U+003C LESS-THAN SIGN character
token, a U+002F SOLIDUS character token, and switch to the data state
to process the next input character. */
$this->emitToken(array(
'type' => self::CHARACTR,
'data' => '</'
));
$this->state = 'data';
} else {
/* Otherwise, if the content model flag is set to the PCDATA state,
or if the next few characters do match that tag name, consume the
next input character: */
$this->char++;
$char = $this->char();
if(preg_match('/^[A-Za-z]$/', $char)) {
/* U+0041 LATIN LETTER A through to U+005A LATIN LETTER Z
Create a new end tag token, set its tag name to the lowercase version
of the input character (add 0x0020 to the character's code point), then
switch to the tag name state. (Don't emit the token yet; further details
will be filled in before it is emitted.) */
$this->token = array(
'name' => strtolower($char),
'type' => self::ENDTAG
);
$this->state = 'tagName';
} elseif($char === '>') {
/* U+003E GREATER-THAN SIGN (>)
Parse error. Switch to the data state. */
$this->state = 'data';
} elseif($this->char === $this->EOF) {
/* EOF
Parse error. Emit a U+003C LESS-THAN SIGN character token and a U+002F
SOLIDUS character token. Reconsume the EOF character in the data state. */
$this->emitToken(array(
'type' => self::CHARACTR,
'data' => '</'
));
$this->char--;
$this->state = 'data';
} else {
/* Parse error. Switch to the bogus comment state. */
$this->state = 'bogusComment';
}
}
}
private function tagNameState() {
// Consume the next input character:
$this->char++;
$char = $this->character($this->char);
if(preg_match('/^[\t\n\x0b\x0c ]$/', $char)) {
/* U+0009 CHARACTER TABULATION
U+000A LINE FEED (LF)
U+000B LINE TABULATION
U+000C FORM FEED (FF)
U+0020 SPACE
Switch to the before attribute name state. */
$this->state = 'beforeAttributeName';
} elseif($char === '>') {
/* U+003E GREATER-THAN SIGN (>)
Emit the current tag token. Switch to the data state. */
$this->emitToken($this->token);
$this->state = 'data';
} elseif($this->char === $this->EOF) {
/* EOF
Parse error. Emit the current tag token. Reconsume the EOF
character in the data state. */
$this->emitToken($this->token);
$this->char--;
$this->state = 'data';
} elseif($char === '/') {
/* U+002F SOLIDUS (/)
Parse error unless this is a permitted slash. Switch to the before
attribute name state. */
$this->state = 'beforeAttributeName';
} else {
/* Anything else
Append the current input character to the current tag token's tag name.
Stay in the tag name state. */
$this->token['name'] .= strtolower($char);
$this->state = 'tagName';
}
}
private function beforeAttributeNameState() {
// Consume the next input character:
$this->char++;
$char = $this->character($this->char);
if(preg_match('/^[\t\n\x0b\x0c ]$/', $char)) {
/* U+0009 CHARACTER TABULATION
U+000A LINE FEED (LF)
U+000B LINE TABULATION
U+000C FORM FEED (FF)
U+0020 SPACE
Stay in the before attribute name state. */
$this->state = 'beforeAttributeName';
} elseif($char === '>') {
/* U+003E GREATER-THAN SIGN (>)
Emit the current tag token. Switch to the data state. */
$this->emitToken($this->token);
$this->state = 'data';
} elseif($char === '/') {
/* U+002F SOLIDUS (/)
Parse error unless this is a permitted slash. Stay in the before
attribute name state. */
$this->state = 'beforeAttributeName';
} elseif($this->char === $this->EOF) {
/* EOF
Parse error. Emit the current tag token. Reconsume the EOF
character in the data state. */
$this->emitToken($this->token);
$this->char--;
$this->state = 'data';
} else {
/* Anything else
Start a new attribute in the current tag token. Set that attribute's
name to the current input character, and its value to the empty string.
Switch to the attribute name state. */
$this->token['attr'][] = array(
'name' => strtolower($char),
'value' => null
);
$this->state = 'attributeName';
}
}
private function attributeNameState() {
// Consume the next input character:
$this->char++;
$char = $this->character($this->char);
if(preg_match('/^[\t\n\x0b\x0c ]$/', $char)) {
/* U+0009 CHARACTER TABULATION
U+000A LINE FEED (LF)
U+000B LINE TABULATION
U+000C FORM FEED (FF)
U+0020 SPACE
Stay in the before attribute name state. */
$this->state = 'afterAttributeName';
} elseif($char === '=') {
/* U+003D EQUALS SIGN (=)
Switch to the before attribute value state. */
$this->state = 'beforeAttributeValue';
} elseif($char === '>') {
/* U+003E GREATER-THAN SIGN (>)
Emit the current tag token. Switch to the data state. */
$this->emitToken($this->token);
$this->state = 'data';
} elseif($char === '/' && $this->character($this->char + 1) !== '>') {
/* U+002F SOLIDUS (/)
Parse error unless this is a permitted slash. Switch to the before
attribute name state. */
$this->state = 'beforeAttributeName';
} elseif($this->char === $this->EOF) {
/* EOF
Parse error. Emit the current tag token. Reconsume the EOF
character in the data state. */
$this->emitToken($this->token);
$this->char--;
$this->state = 'data';
} else {
/* Anything else
Append the current input character to the current attribute's name.
Stay in the attribute name state. */
$last = count($this->token['attr']) - 1;
$this->token['attr'][$last]['name'] .= strtolower($char);
$this->state = 'attributeName';
}
}
private function afterAttributeNameState() {
// Consume the next input character:
$this->char++;
$char = $this->character($this->char);
if(preg_match('/^[\t\n\x0b\x0c ]$/', $char)) {
/* U+0009 CHARACTER TABULATION
U+000A LINE FEED (LF)
U+000B LINE TABULATION
U+000C FORM FEED (FF)
U+0020 SPACE
Stay in the after attribute name state. */
$this->state = 'afterAttributeName';
} elseif($char === '=') {
/* U+003D EQUALS SIGN (=)
Switch to the before attribute value state. */
$this->state = 'beforeAttributeValue';
} elseif($char === '>') {
/* U+003E GREATER-THAN SIGN (>)
Emit the current tag token. Switch to the data state. */
$this->emitToken($this->token);
$this->state = 'data';
} elseif($char === '/' && $this->character($this->char + 1) !== '>') {
/* U+002F SOLIDUS (/)
Parse error unless this is a permitted slash. Switch to the
before attribute name state. */
$this->state = 'beforeAttributeName';
} elseif($this->char === $this->EOF) {
/* EOF
Parse error. Emit the current tag token. Reconsume the EOF
character in the data state. */
$this->emitToken($this->token);
$this->char--;
$this->state = 'data';
} else {
/* Anything else
Start a new attribute in the current tag token. Set that attribute's
name to the current input character, and its value to the empty string.
Switch to the attribute name state. */
$this->token['attr'][] = array(
'name' => strtolower($char),
'value' => null
);
$this->state = 'attributeName';
}
}
private function beforeAttributeValueState() {
// Consume the next input character:
$this->char++;
$char = $this->character($this->char);
if(preg_match('/^[\t\n\x0b\x0c ]$/', $char)) {
/* U+0009 CHARACTER TABULATION
U+000A LINE FEED (LF)
U+000B LINE TABULATION
U+000C FORM FEED (FF)
U+0020 SPACE
Stay in the before attribute value state. */
$this->state = 'beforeAttributeValue';
} elseif($char === '"') {
/* U+0022 QUOTATION MARK (")
Switch to the attribute value (double-quoted) state. */
$this->state = 'attributeValueDoubleQuoted';
} elseif($char === '&') {
/* U+0026 AMPERSAND (&)
Switch to the attribute value (unquoted) state and reconsume
this input character. */
$this->char--;
$this->state = 'attributeValueUnquoted';
} elseif($char === '\'') {
/* U+0027 APOSTROPHE (')
Switch to the attribute value (single-quoted) state. */
$this->state = 'attributeValueSingleQuoted';
} elseif($char === '>') {
/* U+003E GREATER-THAN SIGN (>)
Emit the current tag token. Switch to the data state. */
$this->emitToken($this->token);
$this->state = 'data';
} else {
/* Anything else
Append the current input character to the current attribute's value.
Switch to the attribute value (unquoted) state. */
$last = count($this->token['attr']) - 1;
$this->token['attr'][$last]['value'] .= $char;
$this->state = 'attributeValueUnquoted';
}
}
private function attributeValueDoubleQuotedState() {
// Consume the next input character:
$this->char++;
$char = $this->character($this->char);
if($char === '"') {
/* U+0022 QUOTATION MARK (")
Switch to the before attribute name state. */
$this->state = 'beforeAttributeName';
} elseif($char === '&') {
/* U+0026 AMPERSAND (&)
Switch to the entity in attribute value state. */
$this->entityInAttributeValueState('double');
} elseif($this->char === $this->EOF) {
/* EOF
Parse error. Emit the current tag token. Reconsume the character
in the data state. */
$this->emitToken($this->token);
$this->char--;
$this->state = 'data';
} else {
/* Anything else
Append the current input character to the current attribute's value.
Stay in the attribute value (double-quoted) state. */
$last = count($this->token['attr']) - 1;
$this->token['attr'][$last]['value'] .= $char;
$this->state = 'attributeValueDoubleQuoted';
}
}
private function attributeValueSingleQuotedState() {
// Consume the next input character:
$this->char++;
$char = $this->character($this->char);
if($char === '\'') {
/* U+0022 QUOTATION MARK (')
Switch to the before attribute name state. */
$this->state = 'beforeAttributeName';
} elseif($char === '&') {
/* U+0026 AMPERSAND (&)
Switch to the entity in attribute value state. */
$this->entityInAttributeValueState('single');
} elseif($this->char === $this->EOF) {
/* EOF
Parse error. Emit the current tag token. Reconsume the character
in the data state. */
$this->emitToken($this->token);
$this->char--;
$this->state = 'data';
} else {
/* Anything else
Append the current input character to the current attribute's value.
Stay in the attribute value (single-quoted) state. */
$last = count($this->token['attr']) - 1;
$this->token['attr'][$last]['value'] .= $char;
$this->state = 'attributeValueSingleQuoted';
}
}
private function attributeValueUnquotedState() {
// Consume the next input character:
$this->char++;
$char = $this->character($this->char);
if(preg_match('/^[\t\n\x0b\x0c ]$/', $char)) {
/* U+0009 CHARACTER TABULATION
U+000A LINE FEED (LF)
U+000B LINE TABULATION
U+000C FORM FEED (FF)
U+0020 SPACE
Switch to the before attribute name state. */
$this->state = 'beforeAttributeName';
} elseif($char === '&') {
/* U+0026 AMPERSAND (&)
Switch to the entity in attribute value state. */
$this->entityInAttributeValueState();
} elseif($char === '>') {
/* U+003E GREATER-THAN SIGN (>)
Emit the current tag token. Switch to the data state. */
$this->emitToken($this->token);
$this->state = 'data';
} else {
/* Anything else
Append the current input character to the current attribute's value.
Stay in the attribute value (unquoted) state. */
$last = count($this->token['attr']) - 1;
$this->token['attr'][$last]['value'] .= $char;
$this->state = 'attributeValueUnquoted';
}
}
private function entityInAttributeValueState() {
// Attempt to consume an entity.
$entity = $this->entity();
// If nothing is returned, append a U+0026 AMPERSAND character to the
// current attribute's value. Otherwise, emit the character token that
// was returned.
$char = (!$entity)
? '&'
: $entity;
$last = count($this->token['attr']) - 1;
$this->token['attr'][$last]['value'] .= $char;
}
private function bogusCommentState() {
/* Consume every character up to the first U+003E GREATER-THAN SIGN
character (>) or the end of the file (EOF), whichever comes first. Emit
a comment token whose data is the concatenation of all the characters
starting from and including the character that caused the state machine
to switch into the bogus comment state, up to and including the last
consumed character before the U+003E character, if any, or up to the
end of the file otherwise. (If the comment was started by the end of
the file (EOF), the token is empty.) */
$data = $this->characters('^>', $this->char);
$this->emitToken(array(
'data' => $data,
'type' => self::COMMENT
));
$this->char += strlen($data);
/* Switch to the data state. */
$this->state = 'data';
/* If the end of the file was reached, reconsume the EOF character. */
if($this->char === $this->EOF) {
$this->char = $this->EOF - 1;
}
}
private function markupDeclarationOpenState() {
/* If the next two characters are both U+002D HYPHEN-MINUS (-)
characters, consume those two characters, create a comment token whose
data is the empty string, and switch to the comment state. */
if($this->character($this->char + 1, 2) === '--') {
$this->char += 2;
$this->state = 'comment';
$this->token = array(
'data' => null,
'type' => self::COMMENT
);
/* Otherwise if the next seven chacacters are a case-insensitive match
for the word "DOCTYPE", then consume those characters and switch to the
DOCTYPE state. */
} elseif(strtolower($this->character($this->char + 1, 7)) === 'doctype') {
$this->char += 7;
$this->state = 'doctype';
/* Otherwise, is is a parse error. Switch to the bogus comment state.
The next character that is consumed, if any, is the first character
that will be in the comment. */
} else {
$this->char++;
$this->state = 'bogusComment';
}
}
private function commentState() {
/* Consume the next input character: */
$this->char++;
$char = $this->char();
/* U+002D HYPHEN-MINUS (-) */
if($char === '-') {
/* Switch to the comment dash state */
$this->state = 'commentDash';
/* EOF */
} elseif($this->char === $this->EOF) {
/* Parse error. Emit the comment token. Reconsume the EOF character
in the data state. */
$this->emitToken($this->token);
$this->char--;
$this->state = 'data';
/* Anything else */
} else {
/* Append the input character to the comment token's data. Stay in
the comment state. */
$this->token['data'] .= $char;
}
}
private function commentDashState() {
/* Consume the next input character: */
$this->char++;
$char = $this->char();
/* U+002D HYPHEN-MINUS (-) */
if($char === '-') {
/* Switch to the comment end state */
$this->state = 'commentEnd';
/* EOF */
} elseif($this->char === $this->EOF) {
/* Parse error. Emit the comment token. Reconsume the EOF character
in the data state. */
$this->emitToken($this->token);
$this->char--;
$this->state = 'data';
/* Anything else */
} else {
/* Append a U+002D HYPHEN-MINUS (-) character and the input
character to the comment token's data. Switch to the comment state. */
$this->token['data'] .= '-'.$char;
$this->state = 'comment';
}
}
private function commentEndState() {
/* Consume the next input character: */
$this->char++;
$char = $this->char();
if($char === '>') {
$this->emitToken($this->token);
$this->state = 'data';
} elseif($char === '-') {
$this->token['data'] .= '-';
} elseif($this->char === $this->EOF) {
$this->emitToken($this->token);
$this->char--;
$this->state = 'data';
} else {
$this->token['data'] .= '--'.$char;
$this->state = 'comment';
}
}
private function doctypeState() {
/* Consume the next input character: */
$this->char++;
$char = $this->char();
if(preg_match('/^[\t\n\x0b\x0c ]$/', $char)) {
$this->state = 'beforeDoctypeName';
} else {
$this->char--;
$this->state = 'beforeDoctypeName';
}
}
private function beforeDoctypeNameState() {
/* Consume the next input character: */
$this->char++;
$char = $this->char();
if(preg_match('/^[\t\n\x0b\x0c ]$/', $char)) {
// Stay in the before DOCTYPE name state.
} elseif(preg_match('/^[a-z]$/', $char)) {
$this->token = array(
'name' => strtoupper($char),
'type' => self::DOCTYPE,
'error' => true
);
$this->state = 'doctypeName';
} elseif($char === '>') {
$this->emitToken(array(
'name' => null,
'type' => self::DOCTYPE,
'error' => true
));
$this->state = 'data';
} elseif($this->char === $this->EOF) {
$this->emitToken(array(
'name' => null,
'type' => self::DOCTYPE,
'error' => true
));
$this->char--;
$this->state = 'data';
} else {
$this->token = array(
'name' => $char,
'type' => self::DOCTYPE,
'error' => true
);
$this->state = 'doctypeName';
}
}
private function doctypeNameState() {
/* Consume the next input character: */
$this->char++;
$char = $this->char();
if(preg_match('/^[\t\n\x0b\x0c ]$/', $char)) {
$this->state = 'AfterDoctypeName';
} elseif($char === '>') {
$this->emitToken($this->token);
$this->state = 'data';
} elseif(preg_match('/^[a-z]$/', $char)) {
$this->token['name'] .= strtoupper($char);
} elseif($this->char === $this->EOF) {
$this->emitToken($this->token);
$this->char--;
$this->state = 'data';
} else {
$this->token['name'] .= $char;
}
$this->token['error'] = ($this->token['name'] === 'HTML')
? false
: true;
}
private function afterDoctypeNameState() {
/* Consume the next input character: */
$this->char++;
$char = $this->char();
if(preg_match('/^[\t\n\x0b\x0c ]$/', $char)) {
// Stay in the DOCTYPE name state.
} elseif($char === '>') {
$this->emitToken($this->token);
$this->state = 'data';
} elseif($this->char === $this->EOF) {
$this->emitToken($this->token);
$this->char--;
$this->state = 'data';
} else {
$this->token['error'] = true;
$this->state = 'bogusDoctype';
}
}
private function bogusDoctypeState() {
/* Consume the next input character: */
$this->char++;
$char = $this->char();
if($char === '>') {
$this->emitToken($this->token);
$this->state = 'data';
} elseif($this->char === $this->EOF) {
$this->emitToken($this->token);
$this->char--;
$this->state = 'data';
} else {
// Stay in the bogus DOCTYPE state.
}
}
private function entity() {
$start = $this->char;
// This section defines how to consume an entity. This definition is
// used when parsing entities in text and in attributes.
// The behaviour depends on the identity of the next character (the
// one immediately after the U+0026 AMPERSAND character):
switch($this->character($this->char + 1)) {
// U+0023 NUMBER SIGN (#)
case '#':
// The behaviour further depends on the character after the
// U+0023 NUMBER SIGN:
switch($this->character($this->char + 1)) {
// U+0078 LATIN SMALL LETTER X
// U+0058 LATIN CAPITAL LETTER X
case 'x':
case 'X':
// Follow the steps below, but using the range of
// characters U+0030 DIGIT ZERO through to U+0039 DIGIT
// NINE, U+0061 LATIN SMALL LETTER A through to U+0066
// LATIN SMALL LETTER F, and U+0041 LATIN CAPITAL LETTER
// A, through to U+0046 LATIN CAPITAL LETTER F (in other
// words, 0-9, A-F, a-f).
$char = 1;
$char_class = '0-9A-Fa-f';
break;
// Anything else
default:
// Follow the steps below, but using the range of
// characters U+0030 DIGIT ZERO through to U+0039 DIGIT
// NINE (i.e. just 0-9).
$char = 0;
$char_class = '0-9';
break;
}
// Consume as many characters as match the range of characters
// given above.
$this->char++;
$e_name = $this->characters($char_class, $this->char + $char + 1);
$entity = $this->character($start, $this->char);
$cond = strlen($e_name) > 0;
// The rest of the parsing happens bellow.
break;
// Anything else
default:
// Consume the maximum number of characters possible, with the
// consumed characters case-sensitively matching one of the
// identifiers in the first column of the entities table.
$e_name = $this->characters('0-9A-Za-z;', $this->char + 1);
$len = strlen($e_name);
for($c = 1; $c <= $len; $c++) {
$id = substr($e_name, 0, $c);
$this->char++;
if(in_array($id, $this->entities)) {
if ($e_name[$c-1] !== ';') {
if ($c < $len && $e_name[$c] == ';') {
$this->char++; // consume extra semicolon
}
}
$entity = $id;
break;
}
}
$cond = isset($entity);
// The rest of the parsing happens bellow.
break;
}
if(!$cond) {
// If no match can be made, then this is a parse error. No
// characters are consumed, and nothing is returned.
$this->char = $start;
return false;
}
// Return a character token for the character corresponding to the
// entity name (as given by the second column of the entities table).
return html_entity_decode('&'.$entity.';', ENT_QUOTES, 'UTF-8');
}
private function emitToken($token) {
$emit = $this->tree->emitToken($token);
if(is_int($emit)) {
$this->content_model = $emit;
} elseif($token['type'] === self::ENDTAG) {
$this->content_model = self::PCDATA;
}
}
private function EOF() {
$this->state = null;
$this->tree->emitToken(array(
'type' => self::EOF
));
}
}
class HTML5TreeConstructer {
public $stack = array();
private $phase;
private $mode;
private $dom;
private $foster_parent = null;
private $a_formatting = array();
private $head_pointer = null;
private $form_pointer = null;
private $scoping = array('button','caption','html','marquee','object','table','td','th');
private $formatting = array('a','b','big','em','font','i','nobr','s','small','strike','strong','tt','u');
private $special = array('address','area','base','basefont','bgsound',
'blockquote','body','br','center','col','colgroup','dd','dir','div','dl',
'dt','embed','fieldset','form','frame','frameset','h1','h2','h3','h4','h5',
'h6','head','hr','iframe','image','img','input','isindex','li','link',
'listing','menu','meta','noembed','noframes','noscript','ol','optgroup',
'option','p','param','plaintext','pre','script','select','spacer','style',
'tbody','textarea','tfoot','thead','title','tr','ul','wbr');
// The different phases.
const INIT_PHASE = 0;
const ROOT_PHASE = 1;
const MAIN_PHASE = 2;
const END_PHASE = 3;
// The different insertion modes for the main phase.
const BEFOR_HEAD = 0;
const IN_HEAD = 1;
const AFTER_HEAD = 2;
const IN_BODY = 3;
const IN_TABLE = 4;
const IN_CAPTION = 5;
const IN_CGROUP = 6;
const IN_TBODY = 7;
const IN_ROW = 8;
const IN_CELL = 9;
const IN_SELECT = 10;
const AFTER_BODY = 11;
const IN_FRAME = 12;
const AFTR_FRAME = 13;
// The different types of elements.
const SPECIAL = 0;
const SCOPING = 1;
const FORMATTING = 2;
const PHRASING = 3;
const MARKER = 0;
public function __construct() {
$this->phase = self::INIT_PHASE;
$this->mode = self::BEFOR_HEAD;
$this->dom = new DOMDocument;
$this->dom->encoding = 'UTF-8';
$this->dom->preserveWhiteSpace = true;
$this->dom->substituteEntities = true;
$this->dom->strictErrorChecking = false;
}
// Process tag tokens
public function emitToken($token) {
switch($this->phase) {
case self::INIT_PHASE: return $this->initPhase($token); break;
case self::ROOT_PHASE: return $this->rootElementPhase($token); break;
case self::MAIN_PHASE: return $this->mainPhase($token); break;
case self::END_PHASE : return $this->trailingEndPhase($token); break;
}
}
private function initPhase($token) {
/* Initially, the tree construction stage must handle each token
emitted from the tokenisation stage as follows: */
/* A DOCTYPE token that is marked as being in error
A comment token
A start tag token
An end tag token
A character token that is not one of one of U+0009 CHARACTER TABULATION,
U+000A LINE FEED (LF), U+000B LINE TABULATION, U+000C FORM FEED (FF),
or U+0020 SPACE
An end-of-file token */
if((isset($token['error']) && $token['error']) ||
$token['type'] === HTML5::COMMENT ||
$token['type'] === HTML5::STARTTAG ||
$token['type'] === HTML5::ENDTAG ||
$token['type'] === HTML5::EOF ||
($token['type'] === HTML5::CHARACTR && isset($token['data']) &&
!preg_match('/^[\t\n\x0b\x0c ]+$/', $token['data']))) {
/* This specification does not define how to handle this case. In
particular, user agents may ignore the entirety of this specification
altogether for such documents, and instead invoke special parse modes
with a greater emphasis on backwards compatibility. */
$this->phase = self::ROOT_PHASE;
return $this->rootElementPhase($token);
/* A DOCTYPE token marked as being correct */
} elseif(isset($token['error']) && !$token['error']) {
/* Append a DocumentType node to the Document node, with the name
attribute set to the name given in the DOCTYPE token (which will be
"HTML"), and the other attributes specific to DocumentType objects
set to null, empty lists, or the empty string as appropriate. */
$doctype = new DOMDocumentType(null, null, 'HTML');
/* Then, switch to the root element phase of the tree construction
stage. */
$this->phase = self::ROOT_PHASE;
/* A character token that is one of one of U+0009 CHARACTER TABULATION,
U+000A LINE FEED (LF), U+000B LINE TABULATION, U+000C FORM FEED (FF),
or U+0020 SPACE */
} elseif(isset($token['data']) && preg_match('/^[\t\n\x0b\x0c ]+$/',
$token['data'])) {
/* Append that character to the Document node. */
$text = $this->dom->createTextNode($token['data']);
$this->dom->appendChild($text);
}
}
private function rootElementPhase($token) {
/* After the initial phase, as each token is emitted from the tokenisation
stage, it must be processed as described in this section. */
/* A DOCTYPE token */
if($token['type'] === HTML5::DOCTYPE) {
// Parse error. Ignore the token.
/* A comment token */
} elseif($token['type'] === HTML5::COMMENT) {
/* Append a Comment node to the Document object with the data
attribute set to the data given in the comment token. */
$comment = $this->dom->createComment($token['data']);
$this->dom->appendChild($comment);
/* A character token that is one of one of U+0009 CHARACTER TABULATION,
U+000A LINE FEED (LF), U+000B LINE TABULATION, U+000C FORM FEED (FF),
or U+0020 SPACE */
} elseif($token['type'] === HTML5::CHARACTR &&
preg_match('/^[\t\n\x0b\x0c ]+$/', $token['data'])) {
/* Append that character to the Document node. */
$text = $this->dom->createTextNode($token['data']);
$this->dom->appendChild($text);
/* A character token that is not one of U+0009 CHARACTER TABULATION,
U+000A LINE FEED (LF), U+000B LINE TABULATION, U+000C FORM FEED
(FF), or U+0020 SPACE
A start tag token
An end tag token
An end-of-file token */
} elseif(($token['type'] === HTML5::CHARACTR &&
!preg_match('/^[\t\n\x0b\x0c ]+$/', $token['data'])) ||
$token['type'] === HTML5::STARTTAG ||
$token['type'] === HTML5::ENDTAG ||
$token['type'] === HTML5::EOF) {
/* Create an HTMLElement node with the tag name html, in the HTML
namespace. Append it to the Document object. Switch to the main
phase and reprocess the current token. */
$html = $this->dom->createElement('html');
$this->dom->appendChild($html);
$this->stack[] = $html;
$this->phase = self::MAIN_PHASE;
return $this->mainPhase($token);
}
}
private function mainPhase($token) {
/* Tokens in the main phase must be handled as follows: */
/* A DOCTYPE token */
if($token['type'] === HTML5::DOCTYPE) {
// Parse error. Ignore the token.
/* A start tag token with the tag name "html" */
} elseif($token['type'] === HTML5::STARTTAG && $token['name'] === 'html') {
/* If this start tag token was not the first start tag token, then
it is a parse error. */
/* For each attribute on the token, check to see if the attribute
is already present on the top element of the stack of open elements.
If it is not, add the attribute and its corresponding value to that
element. */
foreach($token['attr'] as $attr) {
if(!$this->stack[0]->hasAttribute($attr['name'])) {
$this->stack[0]->setAttribute($attr['name'], $attr['value']);
}
}
/* An end-of-file token */
} elseif($token['type'] === HTML5::EOF) {
/* Generate implied end tags. */
$this->generateImpliedEndTags();
/* Anything else. */
} else {
/* Depends on the insertion mode: */
switch($this->mode) {
case self::BEFOR_HEAD: return $this->beforeHead($token); break;
case self::IN_HEAD: return $this->inHead($token); break;
case self::AFTER_HEAD: return $this->afterHead($token); break;
case self::IN_BODY: return $this->inBody($token); break;
case self::IN_TABLE: return $this->inTable($token); break;
case self::IN_CAPTION: return $this->inCaption($token); break;
case self::IN_CGROUP: return $this->inColumnGroup($token); break;
case self::IN_TBODY: return $this->inTableBody($token); break;
case self::IN_ROW: return $this->inRow($token); break;
case self::IN_CELL: return $this->inCell($token); break;
case self::IN_SELECT: return $this->inSelect($token); break;
case self::AFTER_BODY: return $this->afterBody($token); break;
case self::IN_FRAME: return $this->inFrameset($token); break;
case self::AFTR_FRAME: return $this->afterFrameset($token); break;
case self::END_PHASE: return $this->trailingEndPhase($token); break;
}
}
}
private function beforeHead($token) {
/* Handle the token as follows: */
/* A character token that is one of one of U+0009 CHARACTER TABULATION,
U+000A LINE FEED (LF), U+000B LINE TABULATION, U+000C FORM FEED (FF),
or U+0020 SPACE */
if($token['type'] === HTML5::CHARACTR &&
preg_match('/^[\t\n\x0b\x0c ]+$/', $token['data'])) {
/* Append the character to the current node. */
$this->insertText($token['data']);
/* A comment token */
} elseif($token['type'] === HTML5::COMMENT) {
/* Append a Comment node to the current node with the data attribute
set to the data given in the comment token. */
$this->insertComment($token['data']);
/* A start tag token with the tag name "head" */
} elseif($token['type'] === HTML5::STARTTAG && $token['name'] === 'head') {
/* Create an element for the token, append the new element to the
current node and push it onto the stack of open elements. */
$element = $this->insertElement($token);
/* Set the head element pointer to this new element node. */
$this->head_pointer = $element;
/* Change the insertion mode to "in head". */
$this->mode = self::IN_HEAD;
/* A start tag token whose tag name is one of: "base", "link", "meta",
"script", "style", "title". Or an end tag with the tag name "html".
Or a character token that is not one of U+0009 CHARACTER TABULATION,
U+000A LINE FEED (LF), U+000B LINE TABULATION, U+000C FORM FEED (FF),
or U+0020 SPACE. Or any other start tag token */
} elseif($token['type'] === HTML5::STARTTAG ||
($token['type'] === HTML5::ENDTAG && $token['name'] === 'html') ||
($token['type'] === HTML5::CHARACTR && !preg_match('/^[\t\n\x0b\x0c ]$/',
$token['data']))) {
/* Act as if a start tag token with the tag name "head" and no
attributes had been seen, then reprocess the current token. */
$this->beforeHead(array(
'name' => 'head',
'type' => HTML5::STARTTAG,
'attr' => array()
));
return $this->inHead($token);
/* Any other end tag */
} elseif($token['type'] === HTML5::ENDTAG) {
/* Parse error. Ignore the token. */
}
}
private function inHead($token) {
/* Handle the token as follows: */
/* A character token that is one of one of U+0009 CHARACTER TABULATION,
U+000A LINE FEED (LF), U+000B LINE TABULATION, U+000C FORM FEED (FF),
or U+0020 SPACE.
THIS DIFFERS FROM THE SPEC: If the current node is either a title, style
or script element, append the character to the current node regardless
of its content. */
if(($token['type'] === HTML5::CHARACTR &&
preg_match('/^[\t\n\x0b\x0c ]+$/', $token['data'])) || (
$token['type'] === HTML5::CHARACTR && in_array(end($this->stack)->nodeName,
array('title', 'style', 'script')))) {
/* Append the character to the current node. */
$this->insertText($token['data']);
/* A comment token */
} elseif($token['type'] === HTML5::COMMENT) {
/* Append a Comment node to the current node with the data attribute
set to the data given in the comment token. */
$this->insertComment($token['data']);
} elseif($token['type'] === HTML5::ENDTAG &&
in_array($token['name'], array('title', 'style', 'script'))) {
array_pop($this->stack);
return HTML5::PCDATA;
/* A start tag with the tag name "title" */
} elseif($token['type'] === HTML5::STARTTAG && $token['name'] === 'title') {
/* Create an element for the token and append the new element to the
node pointed to by the head element pointer, or, if that is null
(innerHTML case), to the current node. */
if($this->head_pointer !== null) {
$element = $this->insertElement($token, false);
$this->head_pointer->appendChild($element);
} else {
$element = $this->insertElement($token);
}
/* Switch the tokeniser's content model flag to the RCDATA state. */
return HTML5::RCDATA;
/* A start tag with the tag name "style" */
} elseif($token['type'] === HTML5::STARTTAG && $token['name'] === 'style') {
/* Create an element for the token and append the new element to the
node pointed to by the head element pointer, or, if that is null
(innerHTML case), to the current node. */
if($this->head_pointer !== null) {
$element = $this->insertElement($token, false);
$this->head_pointer->appendChild($element);
} else {
$this->insertElement($token);
}
/* Switch the tokeniser's content model flag to the CDATA state. */
return HTML5::CDATA;
/* A start tag with the tag name "script" */
} elseif($token['type'] === HTML5::STARTTAG && $token['name'] === 'script') {
/* Create an element for the token. */
$element = $this->insertElement($token, false);
$this->head_pointer->appendChild($element);
/* Switch the tokeniser's content model flag to the CDATA state. */
return HTML5::CDATA;
/* A start tag with the tag name "base", "link", or "meta" */
} elseif($token['type'] === HTML5::STARTTAG && in_array($token['name'],
array('base', 'link', 'meta'))) {
/* Create an element for the token and append the new element to the
node pointed to by the head element pointer, or, if that is null
(innerHTML case), to the current node. */
if($this->head_pointer !== null) {
$element = $this->insertElement($token, false);
$this->head_pointer->appendChild($element);
array_pop($this->stack);
} else {
$this->insertElement($token);
}
/* An end tag with the tag name "head" */
} elseif($token['type'] === HTML5::ENDTAG && $token['name'] === 'head') {
/* If the current node is a head element, pop the current node off
the stack of open elements. */
if($this->head_pointer->isSameNode(end($this->stack))) {
array_pop($this->stack);
/* Otherwise, this is a parse error. */
} else {
// k
}
/* Change the insertion mode to "after head". */
$this->mode = self::AFTER_HEAD;
/* A start tag with the tag name "head" or an end tag except "html". */
} elseif(($token['type'] === HTML5::STARTTAG && $token['name'] === 'head') ||
($token['type'] === HTML5::ENDTAG && $token['name'] !== 'html')) {
// Parse error. Ignore the token.
/* Anything else */
} else {
/* If the current node is a head element, act as if an end tag
token with the tag name "head" had been seen. */
if($this->head_pointer->isSameNode(end($this->stack))) {
$this->inHead(array(
'name' => 'head',
'type' => HTML5::ENDTAG
));
/* Otherwise, change the insertion mode to "after head". */
} else {
$this->mode = self::AFTER_HEAD;
}
/* Then, reprocess the current token. */
return $this->afterHead($token);
}
}
private function afterHead($token) {
/* Handle the token as follows: */
/* A character token that is one of one of U+0009 CHARACTER TABULATION,
U+000A LINE FEED (LF), U+000B LINE TABULATION, U+000C FORM FEED (FF),
or U+0020 SPACE */
if($token['type'] === HTML5::CHARACTR &&
preg_match('/^[\t\n\x0b\x0c ]+$/', $token['data'])) {
/* Append the character to the current node. */
$this->insertText($token['data']);
/* A comment token */
} elseif($token['type'] === HTML5::COMMENT) {
/* Append a Comment node to the current node with the data attribute
set to the data given in the comment token. */
$this->insertComment($token['data']);
/* A start tag token with the tag name "body" */
} elseif($token['type'] === HTML5::STARTTAG && $token['name'] === 'body') {
/* Insert a body element for the token. */
$this->insertElement($token);
/* Change the insertion mode to "in body". */
$this->mode = self::IN_BODY;
/* A start tag token with the tag name "frameset" */
} elseif($token['type'] === HTML5::STARTTAG && $token['name'] === 'frameset') {
/* Insert a frameset element for the token. */
$this->insertElement($token);
/* Change the insertion mode to "in frameset". */
$this->mode = self::IN_FRAME;
/* A start tag token whose tag name is one of: "base", "link", "meta",
"script", "style", "title" */
} elseif($token['type'] === HTML5::STARTTAG && in_array($token['name'],
array('base', 'link', 'meta', 'script', 'style', 'title'))) {
/* Parse error. Switch the insertion mode back to "in head" and
reprocess the token. */
$this->mode = self::IN_HEAD;
return $this->inHead($token);
/* Anything else */
} else {
/* Act as if a start tag token with the tag name "body" and no
attributes had been seen, and then reprocess the current token. */
$this->afterHead(array(
'name' => 'body',
'type' => HTML5::STARTTAG,
'attr' => array()
));
return $this->inBody($token);
}
}
private function inBody($token) {
/* Handle the token as follows: */
switch($token['type']) {
/* A character token */
case HTML5::CHARACTR:
/* Reconstruct the active formatting elements, if any. */
$this->reconstructActiveFormattingElements();
/* Append the token's character to the current node. */
$this->insertText($token['data']);
break;
/* A comment token */
case HTML5::COMMENT:
/* Append a Comment node to the current node with the data
attribute set to the data given in the comment token. */
$this->insertComment($token['data']);
break;
case HTML5::STARTTAG:
switch($token['name']) {
/* A start tag token whose tag name is one of: "script",
"style" */
case 'script': case 'style':
/* Process the token as if the insertion mode had been "in
head". */
return $this->inHead($token);
break;
/* A start tag token whose tag name is one of: "base", "link",
"meta", "title" */
case 'base': case 'link': case 'meta': case 'title':
/* Parse error. Process the token as if the insertion mode
had been "in head". */
return $this->inHead($token);
break;
/* A start tag token with the tag name "body" */
case 'body':
/* Parse error. If the second element on the stack of open
elements is not a body element, or, if the stack of open
elements has only one node on it, then ignore the token.
(innerHTML case) */
if(count($this->stack) === 1 || $this->stack[1]->nodeName !== 'body') {
// Ignore
/* Otherwise, for each attribute on the token, check to see
if the attribute is already present on the body element (the
second element) on the stack of open elements. If it is not,
add the attribute and its corresponding value to that
element. */
} else {
foreach($token['attr'] as $attr) {
if(!$this->stack[1]->hasAttribute($attr['name'])) {
$this->stack[1]->setAttribute($attr['name'], $attr['value']);
}
}
}
break;
/* A start tag whose tag name is one of: "address",
"blockquote", "center", "dir", "div", "dl", "fieldset",
"listing", "menu", "ol", "p", "ul" */
case 'address': case 'blockquote': case 'center': case 'dir':
case 'div': case 'dl': case 'fieldset': case 'listing':
case 'menu': case 'ol': case 'p': case 'ul':
/* If the stack of open elements has a p element in scope,
then act as if an end tag with the tag name p had been
seen. */
if($this->elementInScope('p')) {
$this->emitToken(array(
'name' => 'p',
'type' => HTML5::ENDTAG
));
}
/* Insert an HTML element for the token. */
$this->insertElement($token);
break;
/* A start tag whose tag name is "form" */
case 'form':
/* If the form element pointer is not null, ignore the
token with a parse error. */
if($this->form_pointer !== null) {
// Ignore.
/* Otherwise: */
} else {
/* If the stack of open elements has a p element in
scope, then act as if an end tag with the tag name p
had been seen. */
if($this->elementInScope('p')) {
$this->emitToken(array(
'name' => 'p',
'type' => HTML5::ENDTAG
));
}
/* Insert an HTML element for the token, and set the
form element pointer to point to the element created. */
$element = $this->insertElement($token);
$this->form_pointer = $element;
}
break;
/* A start tag whose tag name is "li", "dd" or "dt" */
case 'li': case 'dd': case 'dt':
/* If the stack of open elements has a p element in scope,
then act as if an end tag with the tag name p had been
seen. */
if($this->elementInScope('p')) {
$this->emitToken(array(
'name' => 'p',
'type' => HTML5::ENDTAG
));
}
$stack_length = count($this->stack) - 1;
for($n = $stack_length; 0 <= $n; $n--) {
/* 1. Initialise node to be the current node (the
bottommost node of the stack). */
$stop = false;
$node = $this->stack[$n];
$cat = $this->getElementCategory($node->tagName);
/* 2. If node is an li, dd or dt element, then pop all
the nodes from the current node up to node, including
node, then stop this algorithm. */
if($token['name'] === $node->tagName || ($token['name'] !== 'li'
&& ($node->tagName === 'dd' || $node->tagName === 'dt'))) {
for($x = $stack_length; $x >= $n ; $x--) {
array_pop($this->stack);
}
break;
}
/* 3. If node is not in the formatting category, and is
not in the phrasing category, and is not an address or
div element, then stop this algorithm. */
if($cat !== self::FORMATTING && $cat !== self::PHRASING &&
$node->tagName !== 'address' && $node->tagName !== 'div') {
break;
}
}
/* Finally, insert an HTML element with the same tag
name as the token's. */
$this->insertElement($token);
break;
/* A start tag token whose tag name is "plaintext" */
case 'plaintext':
/* If the stack of open elements has a p element in scope,
then act as if an end tag with the tag name p had been
seen. */
if($this->elementInScope('p')) {
$this->emitToken(array(
'name' => 'p',
'type' => HTML5::ENDTAG
));
}
/* Insert an HTML element for the token. */
$this->insertElement($token);
return HTML5::PLAINTEXT;
break;
/* A start tag whose tag name is one of: "h1", "h2", "h3", "h4",
"h5", "h6" */
case 'h1': case 'h2': case 'h3': case 'h4': case 'h5': case 'h6':
/* If the stack of open elements has a p element in scope,
then act as if an end tag with the tag name p had been seen. */
if($this->elementInScope('p')) {
$this->emitToken(array(
'name' => 'p',
'type' => HTML5::ENDTAG
));
}
/* If the stack of open elements has in scope an element whose
tag name is one of "h1", "h2", "h3", "h4", "h5", or "h6", then
this is a parse error; pop elements from the stack until an
element with one of those tag names has been popped from the
stack. */
while($this->elementInScope(array('h1', 'h2', 'h3', 'h4', 'h5', 'h6'))) {
array_pop($this->stack);
}
/* Insert an HTML element for the token. */
$this->insertElement($token);
break;
/* A start tag whose tag name is "a" */
case 'a':
/* If the list of active formatting elements contains
an element whose tag name is "a" between the end of the
list and the last marker on the list (or the start of
the list if there is no marker on the list), then this
is a parse error; act as if an end tag with the tag name
"a" had been seen, then remove that element from the list
of active formatting elements and the stack of open
elements if the end tag didn't already remove it (it
might not have if the element is not in table scope). */
$leng = count($this->a_formatting);
for($n = $leng - 1; $n >= 0; $n--) {
if($this->a_formatting[$n] === self::MARKER) {
break;
} elseif($this->a_formatting[$n]->nodeName === 'a') {
$this->emitToken(array(
'name' => 'a',
'type' => HTML5::ENDTAG
));
break;
}
}
/* Reconstruct the active formatting elements, if any. */
$this->reconstructActiveFormattingElements();
/* Insert an HTML element for the token. */
$el = $this->insertElement($token);
/* Add that element to the list of active formatting
elements. */
$this->a_formatting[] = $el;
break;
/* A start tag whose tag name is one of: "b", "big", "em", "font",
"i", "nobr", "s", "small", "strike", "strong", "tt", "u" */
case 'b': case 'big': case 'em': case 'font': case 'i':
case 'nobr': case 's': case 'small': case 'strike':
case 'strong': case 'tt': case 'u':
/* Reconstruct the active formatting elements, if any. */
$this->reconstructActiveFormattingElements();
/* Insert an HTML element for the token. */
$el = $this->insertElement($token);
/* Add that element to the list of active formatting
elements. */
$this->a_formatting[] = $el;
break;
/* A start tag token whose tag name is "button" */
case 'button':
/* If the stack of open elements has a button element in scope,
then this is a parse error; act as if an end tag with the tag
name "button" had been seen, then reprocess the token. (We don't
do that. Unnecessary.) */
if($this->elementInScope('button')) {
$this->inBody(array(
'name' => 'button',
'type' => HTML5::ENDTAG
));
}
/* Reconstruct the active formatting elements, if any. */
$this->reconstructActiveFormattingElements();
/* Insert an HTML element for the token. */
$this->insertElement($token);
/* Insert a marker at the end of the list of active
formatting elements. */
$this->a_formatting[] = self::MARKER;
break;
/* A start tag token whose tag name is one of: "marquee", "object" */
case 'marquee': case 'object':
/* Reconstruct the active formatting elements, if any. */
$this->reconstructActiveFormattingElements();
/* Insert an HTML element for the token. */
$this->insertElement($token);
/* Insert a marker at the end of the list of active
formatting elements. */
$this->a_formatting[] = self::MARKER;
break;
/* A start tag token whose tag name is "xmp" */
case 'xmp':
/* Reconstruct the active formatting elements, if any. */
$this->reconstructActiveFormattingElements();
/* Insert an HTML element for the token. */
$this->insertElement($token);
/* Switch the content model flag to the CDATA state. */
return HTML5::CDATA;
break;
/* A start tag whose tag name is "table" */
case 'table':
/* If the stack of open elements has a p element in scope,
then act as if an end tag with the tag name p had been seen. */
if($this->elementInScope('p')) {
$this->emitToken(array(
'name' => 'p',
'type' => HTML5::ENDTAG
));
}
/* Insert an HTML element for the token. */
$this->insertElement($token);
/* Change the insertion mode to "in table". */
$this->mode = self::IN_TABLE;
break;
/* A start tag whose tag name is one of: "area", "basefont",
"bgsound", "br", "embed", "img", "param", "spacer", "wbr" */
case 'area': case 'basefont': case 'bgsound': case 'br':
case 'embed': case 'img': case 'param': case 'spacer':
case 'wbr':
/* Reconstruct the active formatting elements, if any. */
$this->reconstructActiveFormattingElements();
/* Insert an HTML element for the token. */
$this->insertElement($token);
/* Immediately pop the current node off the stack of open elements. */
array_pop($this->stack);
break;
/* A start tag whose tag name is "hr" */
case 'hr':
/* If the stack of open elements has a p element in scope,
then act as if an end tag with the tag name p had been seen. */
if($this->elementInScope('p')) {
$this->emitToken(array(
'name' => 'p',
'type' => HTML5::ENDTAG
));
}
/* Insert an HTML element for the token. */
$this->insertElement($token);
/* Immediately pop the current node off the stack of open elements. */
array_pop($this->stack);
break;
/* A start tag whose tag name is "image" */
case 'image':
/* Parse error. Change the token's tag name to "img" and
reprocess it. (Don't ask.) */
$token['name'] = 'img';
return $this->inBody($token);
break;
/* A start tag whose tag name is "input" */
case 'input':
/* Reconstruct the active formatting elements, if any. */
$this->reconstructActiveFormattingElements();
/* Insert an input element for the token. */
$element = $this->insertElement($token, false);
/* If the form element pointer is not null, then associate the
input element with the form element pointed to by the form
element pointer. */
$this->form_pointer !== null
? $this->form_pointer->appendChild($element)
: end($this->stack)->appendChild($element);
/* Pop that input element off the stack of open elements. */
array_pop($this->stack);
break;
/* A start tag whose tag name is "isindex" */
case 'isindex':
/* Parse error. */
// w/e
/* If the form element pointer is not null,
then ignore the token. */
if($this->form_pointer === null) {
/* Act as if a start tag token with the tag name "form" had
been seen. */
$this->inBody(array(
'name' => 'body',
'type' => HTML5::STARTTAG,
'attr' => array()
));
/* Act as if a start tag token with the tag name "hr" had
been seen. */
$this->inBody(array(
'name' => 'hr',
'type' => HTML5::STARTTAG,
'attr' => array()
));
/* Act as if a start tag token with the tag name "p" had
been seen. */
$this->inBody(array(
'name' => 'p',
'type' => HTML5::STARTTAG,
'attr' => array()
));
/* Act as if a start tag token with the tag name "label"
had been seen. */
$this->inBody(array(
'name' => 'label',
'type' => HTML5::STARTTAG,
'attr' => array()
));
/* Act as if a stream of character tokens had been seen. */
$this->insertText('This is a searchable index. '.
'Insert your search keywords here: ');
/* Act as if a start tag token with the tag name "input"
had been seen, with all the attributes from the "isindex"
token, except with the "name" attribute set to the value
"isindex" (ignoring any explicit "name" attribute). */
$attr = $token['attr'];
$attr[] = array('name' => 'name', 'value' => 'isindex');
$this->inBody(array(
'name' => 'input',
'type' => HTML5::STARTTAG,
'attr' => $attr
));
/* Act as if a stream of character tokens had been seen
(see below for what they should say). */
$this->insertText('This is a searchable index. '.
'Insert your search keywords here: ');
/* Act as if an end tag token with the tag name "label"
had been seen. */
$this->inBody(array(
'name' => 'label',
'type' => HTML5::ENDTAG
));
/* Act as if an end tag token with the tag name "p" had
been seen. */
$this->inBody(array(
'name' => 'p',
'type' => HTML5::ENDTAG
));
/* Act as if a start tag token with the tag name "hr" had
been seen. */
$this->inBody(array(
'name' => 'hr',
'type' => HTML5::ENDTAG
));
/* Act as if an end tag token with the tag name "form" had
been seen. */
$this->inBody(array(
'name' => 'form',
'type' => HTML5::ENDTAG
));
}
break;
/* A start tag whose tag name is "textarea" */
case 'textarea':
$this->insertElement($token);
/* Switch the tokeniser's content model flag to the
RCDATA state. */
return HTML5::RCDATA;
break;
/* A start tag whose tag name is one of: "iframe", "noembed",
"noframes" */
case 'iframe': case 'noembed': case 'noframes':
$this->insertElement($token);
/* Switch the tokeniser's content model flag to the CDATA state. */
return HTML5::CDATA;
break;
/* A start tag whose tag name is "select" */
case 'select':
/* Reconstruct the active formatting elements, if any. */
$this->reconstructActiveFormattingElements();
/* Insert an HTML element for the token. */
$this->insertElement($token);
/* Change the insertion mode to "in select". */
$this->mode = self::IN_SELECT;
break;
/* A start or end tag whose tag name is one of: "caption", "col",
"colgroup", "frame", "frameset", "head", "option", "optgroup",
"tbody", "td", "tfoot", "th", "thead", "tr". */
case 'caption': case 'col': case 'colgroup': case 'frame':
case 'frameset': case 'head': case 'option': case 'optgroup':
case 'tbody': case 'td': case 'tfoot': case 'th': case 'thead':
case 'tr':
// Parse error. Ignore the token.
break;
/* A start or end tag whose tag name is one of: "event-source",
"section", "nav", "article", "aside", "header", "footer",
"datagrid", "command" */
case 'event-source': case 'section': case 'nav': case 'article':
case 'aside': case 'header': case 'footer': case 'datagrid':
case 'command':
// Work in progress!
break;
/* A start tag token not covered by the previous entries */
default:
/* Reconstruct the active formatting elements, if any. */
$this->reconstructActiveFormattingElements();
$this->insertElement($token, true, true);
break;
}
break;
case HTML5::ENDTAG:
switch($token['name']) {
/* An end tag with the tag name "body" */
case 'body':
/* If the second element in the stack of open elements is
not a body element, this is a parse error. Ignore the token.
(innerHTML case) */
if(count($this->stack) < 2 || $this->stack[1]->nodeName !== 'body') {
// Ignore.
/* If the current node is not the body element, then this
is a parse error. */
} elseif(end($this->stack)->nodeName !== 'body') {
// Parse error.
}
/* Change the insertion mode to "after body". */
$this->mode = self::AFTER_BODY;
break;
/* An end tag with the tag name "html" */
case 'html':
/* Act as if an end tag with tag name "body" had been seen,
then, if that token wasn't ignored, reprocess the current
token. */
$this->inBody(array(
'name' => 'body',
'type' => HTML5::ENDTAG
));
return $this->afterBody($token);
break;
/* An end tag whose tag name is one of: "address", "blockquote",
"center", "dir", "div", "dl", "fieldset", "listing", "menu",
"ol", "pre", "ul" */
case 'address': case 'blockquote': case 'center': case 'dir':
case 'div': case 'dl': case 'fieldset': case 'listing':
case 'menu': case 'ol': case 'pre': case 'ul':
/* If the stack of open elements has an element in scope
with the same tag name as that of the token, then generate
implied end tags. */
if($this->elementInScope($token['name'])) {
$this->generateImpliedEndTags();
/* Now, if the current node is not an element with
the same tag name as that of the token, then this
is a parse error. */
// w/e
/* If the stack of open elements has an element in
scope with the same tag name as that of the token,
then pop elements from this stack until an element
with that tag name has been popped from the stack. */
for($n = count($this->stack) - 1; $n >= 0; $n--) {
if($this->stack[$n]->nodeName === $token['name']) {
$n = -1;
}
array_pop($this->stack);
}
}
break;
/* An end tag whose tag name is "form" */
case 'form':
/* If the stack of open elements has an element in scope
with the same tag name as that of the token, then generate
implied end tags. */
if($this->elementInScope($token['name'])) {
$this->generateImpliedEndTags();
}
if(end($this->stack)->nodeName !== $token['name']) {
/* Now, if the current node is not an element with the
same tag name as that of the token, then this is a parse
error. */
// w/e
} else {
/* Otherwise, if the current node is an element with
the same tag name as that of the token pop that element
from the stack. */
array_pop($this->stack);
}
/* In any case, set the form element pointer to null. */
$this->form_pointer = null;
break;
/* An end tag whose tag name is "p" */
case 'p':
/* If the stack of open elements has a p element in scope,
then generate implied end tags, except for p elements. */
if($this->elementInScope('p')) {
$this->generateImpliedEndTags(array('p'));
/* If the current node is not a p element, then this is
a parse error. */
// k
/* If the stack of open elements has a p element in
scope, then pop elements from this stack until the stack
no longer has a p element in scope. */
for($n = count($this->stack) - 1; $n >= 0; $n--) {
if($this->elementInScope('p')) {
array_pop($this->stack);
} else {
break;
}
}
}
break;
/* An end tag whose tag name is "dd", "dt", or "li" */
case 'dd': case 'dt': case 'li':
/* If the stack of open elements has an element in scope
whose tag name matches the tag name of the token, then
generate implied end tags, except for elements with the
same tag name as the token. */
if($this->elementInScope($token['name'])) {
$this->generateImpliedEndTags(array($token['name']));
/* If the current node is not an element with the same
tag name as the token, then this is a parse error. */
// w/e
/* If the stack of open elements has an element in scope
whose tag name matches the tag name of the token, then
pop elements from this stack until an element with that
tag name has been popped from the stack. */
for($n = count($this->stack) - 1; $n >= 0; $n--) {
if($this->stack[$n]->nodeName === $token['name']) {
$n = -1;
}
array_pop($this->stack);
}
}
break;
/* An end tag whose tag name is one of: "h1", "h2", "h3", "h4",
"h5", "h6" */
case 'h1': case 'h2': case 'h3': case 'h4': case 'h5': case 'h6':
$elements = array('h1', 'h2', 'h3', 'h4', 'h5', 'h6');
/* If the stack of open elements has in scope an element whose
tag name is one of "h1", "h2", "h3", "h4", "h5", or "h6", then
generate implied end tags. */
if($this->elementInScope($elements)) {
$this->generateImpliedEndTags();
/* Now, if the current node is not an element with the same
tag name as that of the token, then this is a parse error. */
// w/e
/* If the stack of open elements has in scope an element
whose tag name is one of "h1", "h2", "h3", "h4", "h5", or
"h6", then pop elements from the stack until an element
with one of those tag names has been popped from the stack. */
while($this->elementInScope($elements)) {
array_pop($this->stack);
}
}
break;
/* An end tag whose tag name is one of: "a", "b", "big", "em",
"font", "i", "nobr", "s", "small", "strike", "strong", "tt", "u" */
case 'a': case 'b': case 'big': case 'em': case 'font':
case 'i': case 'nobr': case 's': case 'small': case 'strike':
case 'strong': case 'tt': case 'u':
/* 1. Let the formatting element be the last element in
the list of active formatting elements that:
* is between the end of the list and the last scope
marker in the list, if any, or the start of the list
otherwise, and
* has the same tag name as the token.
*/
while(true) {
for($a = count($this->a_formatting) - 1; $a >= 0; $a--) {
if($this->a_formatting[$a] === self::MARKER) {
break;
} elseif($this->a_formatting[$a]->tagName === $token['name']) {
$formatting_element = $this->a_formatting[$a];
$in_stack = in_array($formatting_element, $this->stack, true);
$fe_af_pos = $a;
break;
}
}
/* If there is no such node, or, if that node is
also in the stack of open elements but the element
is not in scope, then this is a parse error. Abort
these steps. The token is ignored. */
if(!isset($formatting_element) || ($in_stack &&
!$this->elementInScope($token['name']))) {
break;
/* Otherwise, if there is such a node, but that node
is not in the stack of open elements, then this is a
parse error; remove the element from the list, and
abort these steps. */
} elseif(isset($formatting_element) && !$in_stack) {
unset($this->a_formatting[$fe_af_pos]);
$this->a_formatting = array_merge($this->a_formatting);
break;
}
/* 2. Let the furthest block be the topmost node in the
stack of open elements that is lower in the stack
than the formatting element, and is not an element in
the phrasing or formatting categories. There might
not be one. */
$fe_s_pos = array_search($formatting_element, $this->stack, true);
$length = count($this->stack);
for($s = $fe_s_pos + 1; $s < $length; $s++) {
$category = $this->getElementCategory($this->stack[$s]->nodeName);
if($category !== self::PHRASING && $category !== self::FORMATTING) {
$furthest_block = $this->stack[$s];
}
}
/* 3. If there is no furthest block, then the UA must
skip the subsequent steps and instead just pop all
the nodes from the bottom of the stack of open
elements, from the current node up to the formatting
element, and remove the formatting element from the
list of active formatting elements. */
if(!isset($furthest_block)) {
for($n = $length - 1; $n >= $fe_s_pos; $n--) {
array_pop($this->stack);
}
unset($this->a_formatting[$fe_af_pos]);
$this->a_formatting = array_merge($this->a_formatting);
break;
}
/* 4. Let the common ancestor be the element
immediately above the formatting element in the stack
of open elements. */
$common_ancestor = $this->stack[$fe_s_pos - 1];
/* 5. If the furthest block has a parent node, then
remove the furthest block from its parent node. */
if($furthest_block->parentNode !== null) {
$furthest_block->parentNode->removeChild($furthest_block);
}
/* 6. Let a bookmark note the position of the
formatting element in the list of active formatting
elements relative to the elements on either side
of it in the list. */
$bookmark = $fe_af_pos;
/* 7. Let node and last node be the furthest block.
Follow these steps: */
$node = $furthest_block;
$last_node = $furthest_block;
while(true) {
for($n = array_search($node, $this->stack, true) - 1; $n >= 0; $n--) {
/* 7.1 Let node be the element immediately
prior to node in the stack of open elements. */
$node = $this->stack[$n];
/* 7.2 If node is not in the list of active
formatting elements, then remove node from
the stack of open elements and then go back
to step 1. */
if(!in_array($node, $this->a_formatting, true)) {
unset($this->stack[$n]);
$this->stack = array_merge($this->stack);
} else {
break;
}
}
/* 7.3 Otherwise, if node is the formatting
element, then go to the next step in the overall
algorithm. */
if($node === $formatting_element) {
break;
/* 7.4 Otherwise, if last node is the furthest
block, then move the aforementioned bookmark to
be immediately after the node in the list of
active formatting elements. */
} elseif($last_node === $furthest_block) {
$bookmark = array_search($node, $this->a_formatting, true) + 1;
}
/* 7.5 If node has any children, perform a
shallow clone of node, replace the entry for
node in the list of active formatting elements
with an entry for the clone, replace the entry
for node in the stack of open elements with an
entry for the clone, and let node be the clone. */
if($node->hasChildNodes()) {
$clone = $node->cloneNode();
$s_pos = array_search($node, $this->stack, true);
$a_pos = array_search($node, $this->a_formatting, true);
$this->stack[$s_pos] = $clone;
$this->a_formatting[$a_pos] = $clone;
$node = $clone;
}
/* 7.6 Insert last node into node, first removing
it from its previous parent node if any. */
if($last_node->parentNode !== null) {
$last_node->parentNode->removeChild($last_node);
}
$node->appendChild($last_node);
/* 7.7 Let last node be node. */
$last_node = $node;
}
/* 8. Insert whatever last node ended up being in
the previous step into the common ancestor node,
first removing it from its previous parent node if
any. */
if($last_node->parentNode !== null) {
$last_node->parentNode->removeChild($last_node);
}
$common_ancestor->appendChild($last_node);
/* 9. Perform a shallow clone of the formatting
element. */
$clone = $formatting_element->cloneNode();
/* 10. Take all of the child nodes of the furthest
block and append them to the clone created in the
last step. */
while($furthest_block->hasChildNodes()) {
$child = $furthest_block->firstChild;
$furthest_block->removeChild($child);
$clone->appendChild($child);
}
/* 11. Append that clone to the furthest block. */
$furthest_block->appendChild($clone);
/* 12. Remove the formatting element from the list
of active formatting elements, and insert the clone
into the list of active formatting elements at the
position of the aforementioned bookmark. */
$fe_af_pos = array_search($formatting_element, $this->a_formatting, true);
unset($this->a_formatting[$fe_af_pos]);
$this->a_formatting = array_merge($this->a_formatting);
$af_part1 = array_slice($this->a_formatting, 0, $bookmark - 1);
$af_part2 = array_slice($this->a_formatting, $bookmark, count($this->a_formatting));
$this->a_formatting = array_merge($af_part1, array($clone), $af_part2);
/* 13. Remove the formatting element from the stack
of open elements, and insert the clone into the stack
of open elements immediately after (i.e. in a more
deeply nested position than) the position of the
furthest block in that stack. */
$fe_s_pos = array_search($formatting_element, $this->stack, true);
$fb_s_pos = array_search($furthest_block, $this->stack, true);
unset($this->stack[$fe_s_pos]);
$s_part1 = array_slice($this->stack, 0, $fb_s_pos);
$s_part2 = array_slice($this->stack, $fb_s_pos + 1, count($this->stack));
$this->stack = array_merge($s_part1, array($clone), $s_part2);
/* 14. Jump back to step 1 in this series of steps. */
unset($formatting_element, $fe_af_pos, $fe_s_pos, $furthest_block);
}
break;
/* An end tag token whose tag name is one of: "button",
"marquee", "object" */
case 'button': case 'marquee': case 'object':
/* If the stack of open elements has an element in scope whose
tag name matches the tag name of the token, then generate implied
tags. */
if($this->elementInScope($token['name'])) {
$this->generateImpliedEndTags();
/* Now, if the current node is not an element with the same
tag name as the token, then this is a parse error. */
// k
/* Now, if the stack of open elements has an element in scope
whose tag name matches the tag name of the token, then pop
elements from the stack until that element has been popped from
the stack, and clear the list of active formatting elements up
to the last marker. */
for($n = count($this->stack) - 1; $n >= 0; $n--) {
if($this->stack[$n]->nodeName === $token['name']) {
$n = -1;
}
array_pop($this->stack);
}
$marker = end(array_keys($this->a_formatting, self::MARKER, true));
for($n = count($this->a_formatting) - 1; $n > $marker; $n--) {
array_pop($this->a_formatting);
}
}
break;
/* Or an end tag whose tag name is one of: "area", "basefont",
"bgsound", "br", "embed", "hr", "iframe", "image", "img",
"input", "isindex", "noembed", "noframes", "param", "select",
"spacer", "table", "textarea", "wbr" */
case 'area': case 'basefont': case 'bgsound': case 'br':
case 'embed': case 'hr': case 'iframe': case 'image':
case 'img': case 'input': case 'isindex': case 'noembed':
case 'noframes': case 'param': case 'select': case 'spacer':
case 'table': case 'textarea': case 'wbr':
// Parse error. Ignore the token.
break;
/* An end tag token not covered by the previous entries */
default:
for($n = count($this->stack) - 1; $n >= 0; $n--) {
/* Initialise node to be the current node (the bottommost
node of the stack). */
$node = end($this->stack);
/* If node has the same tag name as the end tag token,
then: */
if($token['name'] === $node->nodeName) {
/* Generate implied end tags. */
$this->generateImpliedEndTags();
/* If the tag name of the end tag token does not
match the tag name of the current node, this is a
parse error. */
// k
/* Pop all the nodes from the current node up to
node, including node, then stop this algorithm. */
for($x = count($this->stack) - $n; $x >= $n; $x--) {
array_pop($this->stack);
}
} else {
$category = $this->getElementCategory($node);
if($category !== self::SPECIAL && $category !== self::SCOPING) {
/* Otherwise, if node is in neither the formatting
category nor the phrasing category, then this is a
parse error. Stop this algorithm. The end tag token
is ignored. */
return false;
}
}
}
break;
}
break;
}
}
private function inTable($token) {
$clear = array('html', 'table');
/* A character token that is one of one of U+0009 CHARACTER TABULATION,
U+000A LINE FEED (LF), U+000B LINE TABULATION, U+000C FORM FEED (FF),
or U+0020 SPACE */
if($token['type'] === HTML5::CHARACTR &&
preg_match('/^[\t\n\x0b\x0c ]+$/', $token['data'])) {
/* Append the character to the current node. */
$text = $this->dom->createTextNode($token['data']);
end($this->stack)->appendChild($text);
/* A comment token */
} elseif($token['type'] === HTML5::COMMENT) {
/* Append a Comment node to the current node with the data
attribute set to the data given in the comment token. */
$comment = $this->dom->createComment($token['data']);
end($this->stack)->appendChild($comment);
/* A start tag whose tag name is "caption" */
} elseif($token['type'] === HTML5::STARTTAG &&
$token['name'] === 'caption') {
/* Clear the stack back to a table context. */
$this->clearStackToTableContext($clear);
/* Insert a marker at the end of the list of active
formatting elements. */
$this->a_formatting[] = self::MARKER;
/* Insert an HTML element for the token, then switch the
insertion mode to "in caption". */
$this->insertElement($token);
$this->mode = self::IN_CAPTION;
/* A start tag whose tag name is "colgroup" */
} elseif($token['type'] === HTML5::STARTTAG &&
$token['name'] === 'colgroup') {
/* Clear the stack back to a table context. */
$this->clearStackToTableContext($clear);
/* Insert an HTML element for the token, then switch the
insertion mode to "in column group". */
$this->insertElement($token);
$this->mode = self::IN_CGROUP;
/* A start tag whose tag name is "col" */
} elseif($token['type'] === HTML5::STARTTAG &&
$token['name'] === 'col') {
$this->inTable(array(
'name' => 'colgroup',
'type' => HTML5::STARTTAG,
'attr' => array()
));
$this->inColumnGroup($token);
/* A start tag whose tag name is one of: "tbody", "tfoot", "thead" */
} elseif($token['type'] === HTML5::STARTTAG && in_array($token['name'],
array('tbody', 'tfoot', 'thead'))) {
/* Clear the stack back to a table context. */
$this->clearStackToTableContext($clear);
/* Insert an HTML element for the token, then switch the insertion
mode to "in table body". */
$this->insertElement($token);
$this->mode = self::IN_TBODY;
/* A start tag whose tag name is one of: "td", "th", "tr" */
} elseif($token['type'] === HTML5::STARTTAG &&
in_array($token['name'], array('td', 'th', 'tr'))) {
/* Act as if a start tag token with the tag name "tbody" had been
seen, then reprocess the current token. */
$this->inTable(array(
'name' => 'tbody',
'type' => HTML5::STARTTAG,
'attr' => array()
));
return $this->inTableBody($token);
/* A start tag whose tag name is "table" */
} elseif($token['type'] === HTML5::STARTTAG &&
$token['name'] === 'table') {
/* Parse error. Act as if an end tag token with the tag name "table"
had been seen, then, if that token wasn't ignored, reprocess the
current token. */
$this->inTable(array(
'name' => 'table',
'type' => HTML5::ENDTAG
));
return $this->mainPhase($token);
/* An end tag whose tag name is "table" */
} elseif($token['type'] === HTML5::ENDTAG &&
$token['name'] === 'table') {
/* If the stack of open elements does not have an element in table
scope with the same tag name as the token, this is a parse error.
Ignore the token. (innerHTML case) */
if(!$this->elementInScope($token['name'], true)) {
return false;
/* Otherwise: */
} else {
/* Generate implied end tags. */
$this->generateImpliedEndTags();
/* Now, if the current node is not a table element, then this
is a parse error. */
// w/e
/* Pop elements from this stack until a table element has been
popped from the stack. */
while(true) {
$current = end($this->stack)->nodeName;
array_pop($this->stack);
if($current === 'table') {
break;
}
}
/* Reset the insertion mode appropriately. */
$this->resetInsertionMode();
}
/* An end tag whose tag name is one of: "body", "caption", "col",
"colgroup", "html", "tbody", "td", "tfoot", "th", "thead", "tr" */
} elseif($token['type'] === HTML5::ENDTAG && in_array($token['name'],
array('body', 'caption', 'col', 'colgroup', 'html', 'tbody', 'td',
'tfoot', 'th', 'thead', 'tr'))) {
// Parse error. Ignore the token.
/* Anything else */
} else {
/* Parse error. Process the token as if the insertion mode was "in
body", with the following exception: */
/* If the current node is a table, tbody, tfoot, thead, or tr
element, then, whenever a node would be inserted into the current
node, it must instead be inserted into the foster parent element. */
if(in_array(end($this->stack)->nodeName,
array('table', 'tbody', 'tfoot', 'thead', 'tr'))) {
/* The foster parent element is the parent element of the last
table element in the stack of open elements, if there is a
table element and it has such a parent element. If there is no
table element in the stack of open elements (innerHTML case),
then the foster parent element is the first element in the
stack of open elements (the html element). Otherwise, if there
is a table element in the stack of open elements, but the last
table element in the stack of open elements has no parent, or
its parent node is not an element, then the foster parent
element is the element before the last table element in the
stack of open elements. */
for($n = count($this->stack) - 1; $n >= 0; $n--) {
if($this->stack[$n]->nodeName === 'table') {
$table = $this->stack[$n];
break;
}
}
if(isset($table) && $table->parentNode !== null) {
$this->foster_parent = $table->parentNode;
} elseif(!isset($table)) {
$this->foster_parent = $this->stack[0];
} elseif(isset($table) && ($table->parentNode === null ||
$table->parentNode->nodeType !== XML_ELEMENT_NODE)) {
$this->foster_parent = $this->stack[$n - 1];
}
}
$this->inBody($token);
}
}
private function inCaption($token) {
/* An end tag whose tag name is "caption" */
if($token['type'] === HTML5::ENDTAG && $token['name'] === 'caption') {
/* If the stack of open elements does not have an element in table
scope with the same tag name as the token, this is a parse error.
Ignore the token. (innerHTML case) */
if(!$this->elementInScope($token['name'], true)) {
// Ignore
/* Otherwise: */
} else {
/* Generate implied end tags. */
$this->generateImpliedEndTags();
/* Now, if the current node is not a caption element, then this
is a parse error. */
// w/e
/* Pop elements from this stack until a caption element has
been popped from the stack. */
while(true) {
$node = end($this->stack)->nodeName;
array_pop($this->stack);
if($node === 'caption') {
break;
}
}
/* Clear the list of active formatting elements up to the last
marker. */
$this->clearTheActiveFormattingElementsUpToTheLastMarker();
/* Switch the insertion mode to "in table". */
$this->mode = self::IN_TABLE;
}
/* A start tag whose tag name is one of: "caption", "col", "colgroup",
"tbody", "td", "tfoot", "th", "thead", "tr", or an end tag whose tag
name is "table" */
} elseif(($token['type'] === HTML5::STARTTAG && in_array($token['name'],
array('caption', 'col', 'colgroup', 'tbody', 'td', 'tfoot', 'th',
'thead', 'tr'))) || ($token['type'] === HTML5::ENDTAG &&
$token['name'] === 'table')) {
/* Parse error. Act as if an end tag with the tag name "caption"
had been seen, then, if that token wasn't ignored, reprocess the
current token. */
$this->inCaption(array(
'name' => 'caption',
'type' => HTML5::ENDTAG
));
return $this->inTable($token);
/* An end tag whose tag name is one of: "body", "col", "colgroup",
"html", "tbody", "td", "tfoot", "th", "thead", "tr" */
} elseif($token['type'] === HTML5::ENDTAG && in_array($token['name'],
array('body', 'col', 'colgroup', 'html', 'tbody', 'tfoot', 'th',
'thead', 'tr'))) {
// Parse error. Ignore the token.
/* Anything else */
} else {
/* Process the token as if the insertion mode was "in body". */
$this->inBody($token);
}
}
private function inColumnGroup($token) {
/* A character token that is one of one of U+0009 CHARACTER TABULATION,
U+000A LINE FEED (LF), U+000B LINE TABULATION, U+000C FORM FEED (FF),
or U+0020 SPACE */
if($token['type'] === HTML5::CHARACTR &&
preg_match('/^[\t\n\x0b\x0c ]+$/', $token['data'])) {
/* Append the character to the current node. */
$text = $this->dom->createTextNode($token['data']);
end($this->stack)->appendChild($text);
/* A comment token */
} elseif($token['type'] === HTML5::COMMENT) {
/* Append a Comment node to the current node with the data
attribute set to the data given in the comment token. */
$comment = $this->dom->createComment($token['data']);
end($this->stack)->appendChild($comment);
/* A start tag whose tag name is "col" */
} elseif($token['type'] === HTML5::STARTTAG && $token['name'] === 'col') {
/* Insert a col element for the token. Immediately pop the current
node off the stack of open elements. */
$this->insertElement($token);
array_pop($this->stack);
/* An end tag whose tag name is "colgroup" */
} elseif($token['type'] === HTML5::ENDTAG &&
$token['name'] === 'colgroup') {
/* If the current node is the root html element, then this is a
parse error, ignore the token. (innerHTML case) */
if(end($this->stack)->nodeName === 'html') {
// Ignore
/* Otherwise, pop the current node (which will be a colgroup
element) from the stack of open elements. Switch the insertion
mode to "in table". */
} else {
array_pop($this->stack);
$this->mode = self::IN_TABLE;
}
/* An end tag whose tag name is "col" */
} elseif($token['type'] === HTML5::ENDTAG && $token['name'] === 'col') {
/* Parse error. Ignore the token. */
/* Anything else */
} else {
/* Act as if an end tag with the tag name "colgroup" had been seen,
and then, if that token wasn't ignored, reprocess the current token. */
$this->inColumnGroup(array(
'name' => 'colgroup',
'type' => HTML5::ENDTAG
));
return $this->inTable($token);
}
}
private function inTableBody($token) {
$clear = array('tbody', 'tfoot', 'thead', 'html');
/* A start tag whose tag name is "tr" */
if($token['type'] === HTML5::STARTTAG && $token['name'] === 'tr') {
/* Clear the stack back to a table body context. */
$this->clearStackToTableContext($clear);
/* Insert a tr element for the token, then switch the insertion
mode to "in row". */
$this->insertElement($token);
$this->mode = self::IN_ROW;
/* A start tag whose tag name is one of: "th", "td" */
} elseif($token['type'] === HTML5::STARTTAG &&
($token['name'] === 'th' || $token['name'] === 'td')) {
/* Parse error. Act as if a start tag with the tag name "tr" had
been seen, then reprocess the current token. */
$this->inTableBody(array(
'name' => 'tr',
'type' => HTML5::STARTTAG,
'attr' => array()
));
return $this->inRow($token);
/* An end tag whose tag name is one of: "tbody", "tfoot", "thead" */
} elseif($token['type'] === HTML5::ENDTAG &&
in_array($token['name'], array('tbody', 'tfoot', 'thead'))) {
/* If the stack of open elements does not have an element in table
scope with the same tag name as the token, this is a parse error.
Ignore the token. */
if(!$this->elementInScope($token['name'], true)) {
// Ignore
/* Otherwise: */
} else {
/* Clear the stack back to a table body context. */
$this->clearStackToTableContext($clear);
/* Pop the current node from the stack of open elements. Switch
the insertion mode to "in table". */
array_pop($this->stack);
$this->mode = self::IN_TABLE;
}
/* A start tag whose tag name is one of: "caption", "col", "colgroup",
"tbody", "tfoot", "thead", or an end tag whose tag name is "table" */
} elseif(($token['type'] === HTML5::STARTTAG && in_array($token['name'],
array('caption', 'col', 'colgroup', 'tbody', 'tfoor', 'thead'))) ||
($token['type'] === HTML5::STARTTAG && $token['name'] === 'table')) {
/* If the stack of open elements does not have a tbody, thead, or
tfoot element in table scope, this is a parse error. Ignore the
token. (innerHTML case) */
if(!$this->elementInScope(array('tbody', 'thead', 'tfoot'), true)) {
// Ignore.
/* Otherwise: */
} else {
/* Clear the stack back to a table body context. */
$this->clearStackToTableContext($clear);
/* Act as if an end tag with the same tag name as the current
node ("tbody", "tfoot", or "thead") had been seen, then
reprocess the current token. */
$this->inTableBody(array(
'name' => end($this->stack)->nodeName,
'type' => HTML5::ENDTAG
));
return $this->mainPhase($token);
}
/* An end tag whose tag name is one of: "body", "caption", "col",
"colgroup", "html", "td", "th", "tr" */
} elseif($token['type'] === HTML5::ENDTAG && in_array($token['name'],
array('body', 'caption', 'col', 'colgroup', 'html', 'td', 'th', 'tr'))) {
/* Parse error. Ignore the token. */
/* Anything else */
} else {
/* Process the token as if the insertion mode was "in table". */
$this->inTable($token);
}
}
private function inRow($token) {
$clear = array('tr', 'html');
/* A start tag whose tag name is one of: "th", "td" */
if($token['type'] === HTML5::STARTTAG &&
($token['name'] === 'th' || $token['name'] === 'td')) {
/* Clear the stack back to a table row context. */
$this->clearStackToTableContext($clear);
/* Insert an HTML element for the token, then switch the insertion
mode to "in cell". */
$this->insertElement($token);
$this->mode = self::IN_CELL;
/* Insert a marker at the end of the list of active formatting
elements. */
$this->a_formatting[] = self::MARKER;
/* An end tag whose tag name is "tr" */
} elseif($token['type'] === HTML5::ENDTAG && $token['name'] === 'tr') {
/* If the stack of open elements does not have an element in table
scope with the same tag name as the token, this is a parse error.
Ignore the token. (innerHTML case) */
if(!$this->elementInScope($token['name'], true)) {
// Ignore.
/* Otherwise: */
} else {
/* Clear the stack back to a table row context. */
$this->clearStackToTableContext($clear);
/* Pop the current node (which will be a tr element) from the
stack of open elements. Switch the insertion mode to "in table
body". */
array_pop($this->stack);
$this->mode = self::IN_TBODY;
}
/* A start tag whose tag name is one of: "caption", "col", "colgroup",
"tbody", "tfoot", "thead", "tr" or an end tag whose tag name is "table" */
} elseif($token['type'] === HTML5::STARTTAG && in_array($token['name'],
array('caption', 'col', 'colgroup', 'tbody', 'tfoot', 'thead', 'tr'))) {
/* Act as if an end tag with the tag name "tr" had been seen, then,
if that token wasn't ignored, reprocess the current token. */
$this->inRow(array(
'name' => 'tr',
'type' => HTML5::ENDTAG
));
return $this->inCell($token);
/* An end tag whose tag name is one of: "tbody", "tfoot", "thead" */
} elseif($token['type'] === HTML5::ENDTAG &&
in_array($token['name'], array('tbody', 'tfoot', 'thead'))) {
/* If the stack of open elements does not have an element in table
scope with the same tag name as the token, this is a parse error.
Ignore the token. */
if(!$this->elementInScope($token['name'], true)) {
// Ignore.
/* Otherwise: */
} else {
/* Otherwise, act as if an end tag with the tag name "tr" had
been seen, then reprocess the current token. */
$this->inRow(array(
'name' => 'tr',
'type' => HTML5::ENDTAG
));
return $this->inCell($token);
}
/* An end tag whose tag name is one of: "body", "caption", "col",
"colgroup", "html", "td", "th" */
} elseif($token['type'] === HTML5::ENDTAG && in_array($token['name'],
array('body', 'caption', 'col', 'colgroup', 'html', 'td', 'th', 'tr'))) {
/* Parse error. Ignore the token. */
/* Anything else */
} else {
/* Process the token as if the insertion mode was "in table". */
$this->inTable($token);
}
}
private function inCell($token) {
/* An end tag whose tag name is one of: "td", "th" */
if($token['type'] === HTML5::ENDTAG &&
($token['name'] === 'td' || $token['name'] === 'th')) {
/* If the stack of open elements does not have an element in table
scope with the same tag name as that of the token, then this is a
parse error and the token must be ignored. */
if(!$this->elementInScope($token['name'], true)) {
// Ignore.
/* Otherwise: */
} else {
/* Generate implied end tags, except for elements with the same
tag name as the token. */
$this->generateImpliedEndTags(array($token['name']));
/* Now, if the current node is not an element with the same tag
name as the token, then this is a parse error. */
// k
/* Pop elements from this stack until an element with the same
tag name as the token has been popped from the stack. */
while(true) {
$node = end($this->stack)->nodeName;
array_pop($this->stack);
if($node === $token['name']) {
break;
}
}
/* Clear the list of active formatting elements up to the last
marker. */
$this->clearTheActiveFormattingElementsUpToTheLastMarker();
/* Switch the insertion mode to "in row". (The current node
will be a tr element at this point.) */
$this->mode = self::IN_ROW;
}
/* A start tag whose tag name is one of: "caption", "col", "colgroup",
"tbody", "td", "tfoot", "th", "thead", "tr" */
} elseif($token['type'] === HTML5::STARTTAG && in_array($token['name'],
array('caption', 'col', 'colgroup', 'tbody', 'td', 'tfoot', 'th',
'thead', 'tr'))) {
/* If the stack of open elements does not have a td or th element
in table scope, then this is a parse error; ignore the token.
(innerHTML case) */
if(!$this->elementInScope(array('td', 'th'), true)) {
// Ignore.
/* Otherwise, close the cell (see below) and reprocess the current
token. */
} else {
$this->closeCell();
return $this->inRow($token);
}
/* A start tag whose tag name is one of: "caption", "col", "colgroup",
"tbody", "td", "tfoot", "th", "thead", "tr" */
} elseif($token['type'] === HTML5::STARTTAG && in_array($token['name'],
array('caption', 'col', 'colgroup', 'tbody', 'td', 'tfoot', 'th',
'thead', 'tr'))) {
/* If the stack of open elements does not have a td or th element
in table scope, then this is a parse error; ignore the token.
(innerHTML case) */
if(!$this->elementInScope(array('td', 'th'), true)) {
// Ignore.
/* Otherwise, close the cell (see below) and reprocess the current
token. */
} else {
$this->closeCell();
return $this->inRow($token);
}
/* An end tag whose tag name is one of: "body", "caption", "col",
"colgroup", "html" */
} elseif($token['type'] === HTML5::ENDTAG && in_array($token['name'],
array('body', 'caption', 'col', 'colgroup', 'html'))) {
/* Parse error. Ignore the token. */
/* An end tag whose tag name is one of: "table", "tbody", "tfoot",
"thead", "tr" */
} elseif($token['type'] === HTML5::ENDTAG && in_array($token['name'],
array('table', 'tbody', 'tfoot', 'thead', 'tr'))) {
/* If the stack of open elements does not have an element in table
scope with the same tag name as that of the token (which can only
happen for "tbody", "tfoot" and "thead", or, in the innerHTML case),
then this is a parse error and the token must be ignored. */
if(!$this->elementInScope($token['name'], true)) {
// Ignore.
/* Otherwise, close the cell (see below) and reprocess the current
token. */
} else {
$this->closeCell();
return $this->inRow($token);
}
/* Anything else */
} else {
/* Process the token as if the insertion mode was "in body". */
$this->inBody($token);
}
}
private function inSelect($token) {
/* Handle the token as follows: */
/* A character token */
if($token['type'] === HTML5::CHARACTR) {
/* Append the token's character to the current node. */
$this->insertText($token['data']);
/* A comment token */
} elseif($token['type'] === HTML5::COMMENT) {
/* Append a Comment node to the current node with the data
attribute set to the data given in the comment token. */
$this->insertComment($token['data']);
/* A start tag token whose tag name is "option" */
} elseif($token['type'] === HTML5::STARTTAG &&
$token['name'] === 'option') {
/* If the current node is an option element, act as if an end tag
with the tag name "option" had been seen. */
if(end($this->stack)->nodeName === 'option') {
$this->inSelect(array(
'name' => 'option',
'type' => HTML5::ENDTAG
));
}
/* Insert an HTML element for the token. */
$this->insertElement($token);
/* A start tag token whose tag name is "optgroup" */
} elseif($token['type'] === HTML5::STARTTAG &&
$token['name'] === 'optgroup') {
/* If the current node is an option element, act as if an end tag
with the tag name "option" had been seen. */
if(end($this->stack)->nodeName === 'option') {
$this->inSelect(array(
'name' => 'option',
'type' => HTML5::ENDTAG
));
}
/* If the current node is an optgroup element, act as if an end tag
with the tag name "optgroup" had been seen. */
if(end($this->stack)->nodeName === 'optgroup') {
$this->inSelect(array(
'name' => 'optgroup',
'type' => HTML5::ENDTAG
));
}
/* Insert an HTML element for the token. */
$this->insertElement($token);
/* An end tag token whose tag name is "optgroup" */
} elseif($token['type'] === HTML5::ENDTAG &&
$token['name'] === 'optgroup') {
/* First, if the current node is an option element, and the node
immediately before it in the stack of open elements is an optgroup
element, then act as if an end tag with the tag name "option" had
been seen. */
$elements_in_stack = count($this->stack);
if($this->stack[$elements_in_stack - 1]->nodeName === 'option' &&
$this->stack[$elements_in_stack - 2]->nodeName === 'optgroup') {
$this->inSelect(array(
'name' => 'option',
'type' => HTML5::ENDTAG
));
}
/* If the current node is an optgroup element, then pop that node
from the stack of open elements. Otherwise, this is a parse error,
ignore the token. */
if($this->stack[$elements_in_stack - 1] === 'optgroup') {
array_pop($this->stack);
}
/* An end tag token whose tag name is "option" */
} elseif($token['type'] === HTML5::ENDTAG &&
$token['name'] === 'option') {
/* If the current node is an option element, then pop that node
from the stack of open elements. Otherwise, this is a parse error,
ignore the token. */
if(end($this->stack)->nodeName === 'option') {
array_pop($this->stack);
}
/* An end tag whose tag name is "select" */
} elseif($token['type'] === HTML5::ENDTAG &&
$token['name'] === 'select') {
/* If the stack of open elements does not have an element in table
scope with the same tag name as the token, this is a parse error.
Ignore the token. (innerHTML case) */
if(!$this->elementInScope($token['name'], true)) {
// w/e
/* Otherwise: */
} else {
/* Pop elements from the stack of open elements until a select
element has been popped from the stack. */
while(true) {
$current = end($this->stack)->nodeName;
array_pop($this->stack);
if($current === 'select') {
break;
}
}
/* Reset the insertion mode appropriately. */
$this->resetInsertionMode();
}
/* A start tag whose tag name is "select" */
} elseif($token['name'] === 'select' &&
$token['type'] === HTML5::STARTTAG) {
/* Parse error. Act as if the token had been an end tag with the
tag name "select" instead. */
$this->inSelect(array(
'name' => 'select',
'type' => HTML5::ENDTAG
));
/* An end tag whose tag name is one of: "caption", "table", "tbody",
"tfoot", "thead", "tr", "td", "th" */
} elseif(in_array($token['name'], array('caption', 'table', 'tbody',
'tfoot', 'thead', 'tr', 'td', 'th')) && $token['type'] === HTML5::ENDTAG) {
/* Parse error. */
// w/e
/* If the stack of open elements has an element in table scope with
the same tag name as that of the token, then act as if an end tag
with the tag name "select" had been seen, and reprocess the token.
Otherwise, ignore the token. */
if($this->elementInScope($token['name'], true)) {
$this->inSelect(array(
'name' => 'select',
'type' => HTML5::ENDTAG
));
$this->mainPhase($token);
}
/* Anything else */
} else {
/* Parse error. Ignore the token. */
}
}
private function afterBody($token) {
/* Handle the token as follows: */
/* A character token that is one of one of U+0009 CHARACTER TABULATION,
U+000A LINE FEED (LF), U+000B LINE TABULATION, U+000C FORM FEED (FF),
or U+0020 SPACE */
if($token['type'] === HTML5::CHARACTR &&
preg_match('/^[\t\n\x0b\x0c ]+$/', $token['data'])) {
/* Process the token as it would be processed if the insertion mode
was "in body". */
$this->inBody($token);
/* A comment token */
} elseif($token['type'] === HTML5::COMMENT) {
/* Append a Comment node to the first element in the stack of open
elements (the html element), with the data attribute set to the
data given in the comment token. */
$comment = $this->dom->createComment($token['data']);
$this->stack[0]->appendChild($comment);
/* An end tag with the tag name "html" */
} elseif($token['type'] === HTML5::ENDTAG && $token['name'] === 'html') {
/* If the parser was originally created in order to handle the
setting of an element's innerHTML attribute, this is a parse error;
ignore the token. (The element will be an html element in this
case.) (innerHTML case) */
/* Otherwise, switch to the trailing end phase. */
$this->phase = self::END_PHASE;
/* Anything else */
} else {
/* Parse error. Set the insertion mode to "in body" and reprocess
the token. */
$this->mode = self::IN_BODY;
return $this->inBody($token);
}
}
private function inFrameset($token) {
/* Handle the token as follows: */
/* A character token that is one of one of U+0009 CHARACTER TABULATION,
U+000A LINE FEED (LF), U+000B LINE TABULATION, U+000C FORM FEED (FF),
U+000D CARRIAGE RETURN (CR), or U+0020 SPACE */
if($token['type'] === HTML5::CHARACTR &&
preg_match('/^[\t\n\x0b\x0c ]+$/', $token['data'])) {
/* Append the character to the current node. */
$this->insertText($token['data']);
/* A comment token */
} elseif($token['type'] === HTML5::COMMENT) {
/* Append a Comment node to the current node with the data
attribute set to the data given in the comment token. */
$this->insertComment($token['data']);
/* A start tag with the tag name "frameset" */
} elseif($token['name'] === 'frameset' &&
$token['type'] === HTML5::STARTTAG) {
$this->insertElement($token);
/* An end tag with the tag name "frameset" */
} elseif($token['name'] === 'frameset' &&
$token['type'] === HTML5::ENDTAG) {
/* If the current node is the root html element, then this is a
parse error; ignore the token. (innerHTML case) */
if(end($this->stack)->nodeName === 'html') {
// Ignore
} else {
/* Otherwise, pop the current node from the stack of open
elements. */
array_pop($this->stack);
/* If the parser was not originally created in order to handle
the setting of an element's innerHTML attribute (innerHTML case),
and the current node is no longer a frameset element, then change
the insertion mode to "after frameset". */
$this->mode = self::AFTR_FRAME;
}
/* A start tag with the tag name "frame" */
} elseif($token['name'] === 'frame' &&
$token['type'] === HTML5::STARTTAG) {
/* Insert an HTML element for the token. */
$this->insertElement($token);
/* Immediately pop the current node off the stack of open elements. */
array_pop($this->stack);
/* A start tag with the tag name "noframes" */
} elseif($token['name'] === 'noframes' &&
$token['type'] === HTML5::STARTTAG) {
/* Process the token as if the insertion mode had been "in body". */
$this->inBody($token);
/* Anything else */
} else {
/* Parse error. Ignore the token. */
}
}
private function afterFrameset($token) {
/* Handle the token as follows: */
/* A character token that is one of one of U+0009 CHARACTER TABULATION,
U+000A LINE FEED (LF), U+000B LINE TABULATION, U+000C FORM FEED (FF),
U+000D CARRIAGE RETURN (CR), or U+0020 SPACE */
if($token['type'] === HTML5::CHARACTR &&
preg_match('/^[\t\n\x0b\x0c ]+$/', $token['data'])) {
/* Append the character to the current node. */
$this->insertText($token['data']);
/* A comment token */
} elseif($token['type'] === HTML5::COMMENT) {
/* Append a Comment node to the current node with the data
attribute set to the data given in the comment token. */
$this->insertComment($token['data']);
/* An end tag with the tag name "html" */
} elseif($token['name'] === 'html' &&
$token['type'] === HTML5::ENDTAG) {
/* Switch to the trailing end phase. */
$this->phase = self::END_PHASE;
/* A start tag with the tag name "noframes" */
} elseif($token['name'] === 'noframes' &&
$token['type'] === HTML5::STARTTAG) {
/* Process the token as if the insertion mode had been "in body". */
$this->inBody($token);
/* Anything else */
} else {
/* Parse error. Ignore the token. */
}
}
private function trailingEndPhase($token) {
/* After the main phase, as each token is emitted from the tokenisation
stage, it must be processed as described in this section. */
/* A DOCTYPE token */
if($token['type'] === HTML5::DOCTYPE) {
// Parse error. Ignore the token.
/* A comment token */
} elseif($token['type'] === HTML5::COMMENT) {
/* Append a Comment node to the Document object with the data
attribute set to the data given in the comment token. */
$comment = $this->dom->createComment($token['data']);
$this->dom->appendChild($comment);
/* A character token that is one of one of U+0009 CHARACTER TABULATION,
U+000A LINE FEED (LF), U+000B LINE TABULATION, U+000C FORM FEED (FF),
or U+0020 SPACE */
} elseif($token['type'] === HTML5::CHARACTR &&
preg_match('/^[\t\n\x0b\x0c ]+$/', $token['data'])) {
/* Process the token as it would be processed in the main phase. */
$this->mainPhase($token);
/* A character token that is not one of U+0009 CHARACTER TABULATION,
U+000A LINE FEED (LF), U+000B LINE TABULATION, U+000C FORM FEED (FF),
or U+0020 SPACE. Or a start tag token. Or an end tag token. */
} elseif(($token['type'] === HTML5::CHARACTR &&
preg_match('/^[\t\n\x0b\x0c ]+$/', $token['data'])) ||
$token['type'] === HTML5::STARTTAG || $token['type'] === HTML5::ENDTAG) {
/* Parse error. Switch back to the main phase and reprocess the
token. */
$this->phase = self::MAIN_PHASE;
return $this->mainPhase($token);
/* An end-of-file token */
} elseif($token['type'] === HTML5::EOF) {
/* OMG DONE!! */
}
}
private function insertElement($token, $append = true, $check = false) {
// Proprietary workaround for libxml2's limitations with tag names
if ($check) {
// Slightly modified HTML5 tag-name modification,
// removing anything that's not an ASCII letter, digit, or hyphen
$token['name'] = preg_replace('/[^a-z0-9-]/i', '', $token['name']);
// Remove leading hyphens and numbers
$token['name'] = ltrim($token['name'], '-0..9');
// In theory, this should ever be needed, but just in case
if ($token['name'] === '') $token['name'] = 'span'; // arbitrary generic choice
}
$el = $this->dom->createElement($token['name']);
foreach($token['attr'] as $attr) {
if(!$el->hasAttribute($attr['name'])) {
$el->setAttribute($attr['name'], $attr['value']);
}
}
$this->appendToRealParent($el);
$this->stack[] = $el;
return $el;
}
private function insertText($data) {
$text = $this->dom->createTextNode($data);
$this->appendToRealParent($text);
}
private function insertComment($data) {
$comment = $this->dom->createComment($data);
$this->appendToRealParent($comment);
}
private function appendToRealParent($node) {
if($this->foster_parent === null) {
end($this->stack)->appendChild($node);
} elseif($this->foster_parent !== null) {
/* If the foster parent element is the parent element of the
last table element in the stack of open elements, then the new
node must be inserted immediately before the last table element
in the stack of open elements in the foster parent element;
otherwise, the new node must be appended to the foster parent
element. */
for($n = count($this->stack) - 1; $n >= 0; $n--) {
if($this->stack[$n]->nodeName === 'table' &&
$this->stack[$n]->parentNode !== null) {
$table = $this->stack[$n];
break;
}
}
if(isset($table) && $this->foster_parent->isSameNode($table->parentNode))
$this->foster_parent->insertBefore($node, $table);
else
$this->foster_parent->appendChild($node);
$this->foster_parent = null;
}
}
private function elementInScope($el, $table = false) {
if(is_array($el)) {
foreach($el as $element) {
if($this->elementInScope($element, $table)) {
return true;
}
}
return false;
}
$leng = count($this->stack);
for($n = 0; $n < $leng; $n++) {
/* 1. Initialise node to be the current node (the bottommost node of
the stack). */
$node = $this->stack[$leng - 1 - $n];
if($node->tagName === $el) {
/* 2. If node is the target node, terminate in a match state. */
return true;
} elseif($node->tagName === 'table') {
/* 3. Otherwise, if node is a table element, terminate in a failure
state. */
return false;
} elseif($table === true && in_array($node->tagName, array('caption', 'td',
'th', 'button', 'marquee', 'object'))) {
/* 4. Otherwise, if the algorithm is the "has an element in scope"
variant (rather than the "has an element in table scope" variant),
and node is one of the following, terminate in a failure state. */
return false;
} elseif($node === $node->ownerDocument->documentElement) {
/* 5. Otherwise, if node is an html element (root element), terminate
in a failure state. (This can only happen if the node is the topmost
node of the stack of open elements, and prevents the next step from
being invoked if there are no more elements in the stack.) */
return false;
}
/* Otherwise, set node to the previous entry in the stack of open
elements and return to step 2. (This will never fail, since the loop
will always terminate in the previous step if the top of the stack
is reached.) */
}
}
private function reconstructActiveFormattingElements() {
/* 1. If there are no entries in the list of active formatting elements,
then there is nothing to reconstruct; stop this algorithm. */
$formatting_elements = count($this->a_formatting);
if($formatting_elements === 0) {
return false;
}
/* 3. Let entry be the last (most recently added) element in the list
of active formatting elements. */
$entry = end($this->a_formatting);
/* 2. If the last (most recently added) entry in the list of active
formatting elements is a marker, or if it is an element that is in the
stack of open elements, then there is nothing to reconstruct; stop this
algorithm. */
if($entry === self::MARKER || in_array($entry, $this->stack, true)) {
return false;
}
for($a = $formatting_elements - 1; $a >= 0; true) {
/* 4. If there are no entries before entry in the list of active
formatting elements, then jump to step 8. */
if($a === 0) {
$step_seven = false;
break;
}
/* 5. Let entry be the entry one earlier than entry in the list of
active formatting elements. */
</