2008-06-25 01:10:51 +00:00
|
|
|
<?php
|
|
|
|
|
|
|
|
|
|
/**
|
|
|
|
|
* Experimental HTML5-based parser using Jeroen van der Meer's PH5P library.
|
|
|
|
|
* Occupies space in the HTML5 pseudo-namespace, which may cause conflicts.
|
2013-07-16 11:56:14 +00:00
|
|
|
*
|
2008-06-25 01:10:51 +00:00
|
|
|
* @note
|
|
|
|
|
* Recent changes to PHP's DOM extension have resulted in some fatal
|
|
|
|
|
* error conditions with the original version of PH5P. Pending changes,
|
2013-07-16 11:56:14 +00:00
|
|
|
* this lexer will punt to DirectLex if DOM throws an exception.
|
2008-06-25 01:10:51 +00:00
|
|
|
*/
|
|
|
|
|
|
2013-07-16 11:56:14 +00:00
|
|
|
class HTMLPurifier_Lexer_PH5P extends HTMLPurifier_Lexer_DOMLex
|
|
|
|
|
{
|
|
|
|
|
/**
|
|
|
|
|
* @param string $html
|
|
|
|
|
* @param HTMLPurifier_Config $config
|
|
|
|
|
* @param HTMLPurifier_Context $context
|
|
|
|
|
* @return HTMLPurifier_Token[]
|
|
|
|
|
*/
|
|
|
|
|
public function tokenizeHTML($html, $config, $context)
|
|
|
|
|
{
|
2008-06-25 01:10:51 +00:00
|
|
|
$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>
|
2014-08-31 07:50:33 +00:00
|
|
|
getElementsByTagName('body')->item(0) // <body>
|
2013-07-16 11:56:14 +00:00
|
|
|
,
|
|
|
|
|
$tokens
|
|
|
|
|
);
|
2008-06-25 01:10:51 +00:00
|
|
|
return $tokens;
|
|
|
|
|
}
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
/*
|
|
|
|
|
|
2013-07-16 11:56:14 +00:00
|
|
|
Copyright 2007 Jeroen van der Meer <http://jero.net/>
|
2008-06-25 01:10:51 +00:00
|
|
|
|
2013-07-16 11:56:14 +00:00
|
|
|
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:
|
2008-06-25 01:10:51 +00:00
|
|
|
|
2013-07-16 11:56:14 +00:00
|
|
|
The above copyright notice and this permission notice shall be included
|
|
|
|
|
in all copies or substantial portions of the Software.
|
2008-06-25 01:10:51 +00:00
|
|
|
|
2013-07-16 11:56:14 +00:00
|
|
|
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.
|
2008-06-25 01:10:51 +00:00
|
|
|
|
|
|
|
|
*/
|
|
|
|
|
|
2013-07-16 11:56:14 +00:00
|
|
|
class HTML5
|
|
|
|
|
{
|
2008-06-25 01:10:51 +00:00
|
|
|
private $data;
|
|
|
|
|
private $char;
|
|
|
|
|
private $EOF;
|
|
|
|
|
private $state;
|
|
|
|
|
private $tree;
|
|
|
|
|
private $token;
|
|
|
|
|
private $content_model;
|
|
|
|
|
private $escape = false;
|
2013-07-16 11:56:14 +00:00
|
|
|
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;
|
2008-06-25 01:10:51 +00:00
|
|
|
const PLAINTEXT = 3;
|
|
|
|
|
|
2013-07-16 11:56:14 +00:00
|
|
|
const DOCTYPE = 0;
|
2008-06-25 01:10:51 +00:00
|
|
|
const STARTTAG = 1;
|
2013-07-16 11:56:14 +00:00
|
|
|
const ENDTAG = 2;
|
|
|
|
|
const COMMENT = 3;
|
2008-06-25 01:10:51 +00:00
|
|
|
const CHARACTR = 4;
|
2013-07-16 11:56:14 +00:00
|
|
|
const EOF = 5;
|
2008-06-25 01:10:51 +00:00
|
|
|
|
2013-07-16 11:56:14 +00:00
|
|
|
public function __construct($data)
|
|
|
|
|
{
|
2008-06-25 01:10:51 +00:00
|
|
|
$this->data = $data;
|
|
|
|
|
$this->char = -1;
|
2013-07-16 11:56:14 +00:00
|
|
|
$this->EOF = strlen($data);
|
2008-06-25 01:10:51 +00:00
|
|
|
$this->tree = new HTML5TreeConstructer;
|
|
|
|
|
$this->content_model = self::PCDATA;
|
|
|
|
|
|
|
|
|
|
$this->state = 'data';
|
|
|
|
|
|
2013-07-16 11:56:14 +00:00
|
|
|
while ($this->state !== null) {
|
|
|
|
|
$this->{$this->state . 'State'}();
|
2008-06-25 01:10:51 +00:00
|
|
|
}
|
|
|
|
|
}
|
|
|
|
|
|
2013-07-16 11:56:14 +00:00
|
|
|
public function save()
|
|
|
|
|
{
|
2008-06-25 01:10:51 +00:00
|
|
|
return $this->tree->save();
|
|
|
|
|
}
|
|
|
|
|
|
2013-07-16 11:56:14 +00:00
|
|
|
private function char()
|
|
|
|
|
{
|
2008-06-25 01:10:51 +00:00
|
|
|
return ($this->char < $this->EOF)
|
|
|
|
|
? $this->data[$this->char]
|
|
|
|
|
: false;
|
|
|
|
|
}
|
|
|
|
|
|
2013-07-16 11:56:14 +00:00
|
|
|
private function character($s, $l = 0)
|
|
|
|
|
{
|
|
|
|
|
if ($s + $l < $this->EOF) {
|
|
|
|
|
if ($l === 0) {
|
2008-06-25 01:10:51 +00:00
|
|
|
return $this->data[$s];
|
|
|
|
|
} else {
|
|
|
|
|
return substr($this->data, $s, $l);
|
|
|
|
|
}
|
|
|
|
|
}
|
|
|
|
|
}
|
|
|
|
|
|
2013-07-16 11:56:14 +00:00
|
|
|
private function characters($char_class, $start)
|
|
|
|
|
{
|
|
|
|
|
return preg_replace('#^([' . $char_class . ']+).*#s', '\\1', substr($this->data, $start));
|
2008-06-25 01:10:51 +00:00
|
|
|
}
|
|
|
|
|
|
2013-07-16 11:56:14 +00:00
|
|
|
private function dataState()
|
|
|
|
|
{
|
2008-06-25 01:10:51 +00:00
|
|
|
// Consume the next input character
|
|
|
|
|
$this->char++;
|
|
|
|
|
$char = $this->char();
|
|
|
|
|
|
2013-07-16 11:56:14 +00:00
|
|
|
if ($char === '&' && ($this->content_model === self::PCDATA || $this->content_model === self::RCDATA)) {
|
2008-06-25 01:10:51 +00:00
|
|
|
/* 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. */
|
|
|
|
|
$this->state = 'entityData';
|
|
|
|
|
|
2013-07-16 11:56:14 +00:00
|
|
|
} elseif ($char === '-') {
|
2008-06-25 01:10:51 +00:00
|
|
|
/* 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. */
|
2013-07-16 11:56:14 +00:00
|
|
|
if (($this->content_model === self::RCDATA || $this->content_model ===
|
|
|
|
|
self::CDATA) && $this->escape === false &&
|
|
|
|
|
$this->char >= 3 && $this->character($this->char - 4, 4) === '<!--'
|
|
|
|
|
) {
|
2008-06-25 01:10:51 +00:00
|
|
|
$this->escape = true;
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
/* In any case, emit the input character as a character token. Stay
|
|
|
|
|
in the data state. */
|
2013-07-16 11:56:14 +00:00
|
|
|
$this->emitToken(
|
|
|
|
|
array(
|
|
|
|
|
'type' => self::CHARACTR,
|
|
|
|
|
'data' => $char
|
|
|
|
|
)
|
|
|
|
|
);
|
2008-06-25 01:10:51 +00:00
|
|
|
|
2013-07-16 11:56:14 +00:00
|
|
|
/* U+003C LESS-THAN SIGN (<) */
|
|
|
|
|
} elseif ($char === '<' && ($this->content_model === self::PCDATA ||
|
|
|
|
|
(($this->content_model === self::RCDATA ||
|
|
|
|
|
$this->content_model === self::CDATA) && $this->escape === false))
|
|
|
|
|
) {
|
2008-06-25 01:10:51 +00:00
|
|
|
/* 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. */
|
|
|
|
|
$this->state = 'tagOpen';
|
|
|
|
|
|
2013-07-16 11:56:14 +00:00
|
|
|
/* U+003E GREATER-THAN SIGN (>) */
|
|
|
|
|
} elseif ($char === '>') {
|
2008-06-25 01:10:51 +00:00
|
|
|
/* 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. */
|
2013-07-16 11:56:14 +00:00
|
|
|
if (($this->content_model === self::RCDATA ||
|
|
|
|
|
$this->content_model === self::CDATA) && $this->escape === true &&
|
|
|
|
|
$this->character($this->char, 3) === '-->'
|
|
|
|
|
) {
|
2008-06-25 01:10:51 +00:00
|
|
|
$this->escape = false;
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
/* In any case, emit the input character as a character token.
|
|
|
|
|
Stay in the data state. */
|
2013-07-16 11:56:14 +00:00
|
|
|
$this->emitToken(
|
|
|
|
|
array(
|
|
|
|
|
'type' => self::CHARACTR,
|
|
|
|
|
'data' => $char
|
|
|
|
|
)
|
|
|
|
|
);
|
2008-06-25 01:10:51 +00:00
|
|
|
|
2013-07-16 11:56:14 +00:00
|
|
|
} elseif ($this->char === $this->EOF) {
|
2008-06-25 01:10:51 +00:00
|
|
|
/* EOF
|
|
|
|
|
Emit an end-of-file token. */
|
|
|
|
|
$this->EOF();
|
|
|
|
|
|
2013-07-16 11:56:14 +00:00
|
|
|
} elseif ($this->content_model === self::PLAINTEXT) {
|
2008-06-25 01:10:51 +00:00
|
|
|
/* 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. */
|
2013-07-16 11:56:14 +00:00
|
|
|
$this->emitToken(
|
|
|
|
|
array(
|
|
|
|
|
'type' => self::CHARACTR,
|
|
|
|
|
'data' => substr($this->data, $this->char)
|
|
|
|
|
)
|
|
|
|
|
);
|
2008-06-25 01:10:51 +00:00
|
|
|
|
|
|
|
|
$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. */
|
2013-07-16 11:56:14 +00:00
|
|
|
$len = strcspn($this->data, '<&', $this->char);
|
2008-06-25 01:10:51 +00:00
|
|
|
$char = substr($this->data, $this->char, $len);
|
|
|
|
|
$this->char += $len - 1;
|
|
|
|
|
|
2013-07-16 11:56:14 +00:00
|
|
|
$this->emitToken(
|
|
|
|
|
array(
|
|
|
|
|
'type' => self::CHARACTR,
|
|
|
|
|
'data' => $char
|
|
|
|
|
)
|
|
|
|
|
);
|
2008-06-25 01:10:51 +00:00
|
|
|
|
|
|
|
|
$this->state = 'data';
|
|
|
|
|
}
|
|
|
|
|
}
|
|
|
|
|
|
2013-07-16 11:56:14 +00:00
|
|
|
private function entityDataState()
|
|
|
|
|
{
|
2008-06-25 01:10:51 +00:00
|
|
|
// 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;
|
2013-07-16 11:56:14 +00:00
|
|
|
$this->emitToken(
|
|
|
|
|
array(
|
|
|
|
|
'type' => self::CHARACTR,
|
|
|
|
|
'data' => $char
|
|
|
|
|
)
|
|
|
|
|
);
|
2008-06-25 01:10:51 +00:00
|
|
|
|
|
|
|
|
// Finally, switch to the data state.
|
|
|
|
|
$this->state = 'data';
|
|
|
|
|
}
|
|
|
|
|
|
2013-07-16 11:56:14 +00:00
|
|
|
private function tagOpenState()
|
|
|
|
|
{
|
|
|
|
|
switch ($this->content_model) {
|
2008-06-25 01:10:51 +00:00
|
|
|
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. */
|
2013-07-16 11:56:14 +00:00
|
|
|
if ($this->character($this->char + 1) === '/') {
|
2008-06-25 01:10:51 +00:00
|
|
|
$this->char++;
|
|
|
|
|
$this->state = 'closeTagOpen';
|
|
|
|
|
|
|
|
|
|
} else {
|
2013-07-16 11:56:14 +00:00
|
|
|
$this->emitToken(
|
|
|
|
|
array(
|
|
|
|
|
'type' => self::CHARACTR,
|
|
|
|
|
'data' => '<'
|
|
|
|
|
)
|
|
|
|
|
);
|
2008-06-25 01:10:51 +00:00
|
|
|
|
|
|
|
|
$this->state = 'data';
|
|
|
|
|
}
|
2013-07-16 11:56:14 +00:00
|
|
|
break;
|
2008-06-25 01:10:51 +00:00
|
|
|
|
|
|
|
|
case self::PCDATA:
|
|
|
|
|
// If the content model flag is set to the PCDATA state
|
|
|
|
|
// Consume the next input character:
|
|
|
|
|
$this->char++;
|
|
|
|
|
$char = $this->char();
|
|
|
|
|
|
2013-07-16 11:56:14 +00:00
|
|
|
if ($char === '!') {
|
2008-06-25 01:10:51 +00:00
|
|
|
/* U+0021 EXCLAMATION MARK (!)
|
|
|
|
|
Switch to the markup declaration open state. */
|
|
|
|
|
$this->state = 'markupDeclarationOpen';
|
|
|
|
|
|
2013-07-16 11:56:14 +00:00
|
|
|
} elseif ($char === '/') {
|
2008-06-25 01:10:51 +00:00
|
|
|
/* U+002F SOLIDUS (/)
|
|
|
|
|
Switch to the close tag open state. */
|
|
|
|
|
$this->state = 'closeTagOpen';
|
|
|
|
|
|
2013-07-16 11:56:14 +00:00
|
|
|
} elseif (preg_match('/^[A-Za-z]$/', $char)) {
|
2008-06-25 01:10:51 +00:00
|
|
|
/* 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.) */
|
|
|
|
|
$this->token = array(
|
2013-07-16 11:56:14 +00:00
|
|
|
'name' => strtolower($char),
|
|
|
|
|
'type' => self::STARTTAG,
|
|
|
|
|
'attr' => array()
|
2008-06-25 01:10:51 +00:00
|
|
|
);
|
|
|
|
|
|
|
|
|
|
$this->state = 'tagName';
|
|
|
|
|
|
2013-07-16 11:56:14 +00:00
|
|
|
} elseif ($char === '>') {
|
2008-06-25 01:10:51 +00:00
|
|
|
/* 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. */
|
2013-07-16 11:56:14 +00:00
|
|
|
$this->emitToken(
|
|
|
|
|
array(
|
|
|
|
|
'type' => self::CHARACTR,
|
|
|
|
|
'data' => '<>'
|
|
|
|
|
)
|
|
|
|
|
);
|
2008-06-25 01:10:51 +00:00
|
|
|
|
|
|
|
|
$this->state = 'data';
|
|
|
|
|
|
2013-07-16 11:56:14 +00:00
|
|
|
} elseif ($char === '?') {
|
2008-06-25 01:10:51 +00:00
|
|
|
/* 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. */
|
2013-07-16 11:56:14 +00:00
|
|
|
$this->emitToken(
|
|
|
|
|
array(
|
|
|
|
|
'type' => self::CHARACTR,
|
|
|
|
|
'data' => '<'
|
|
|
|
|
)
|
|
|
|
|
);
|
2008-06-25 01:10:51 +00:00
|
|
|
|
|
|
|
|
$this->char--;
|
|
|
|
|
$this->state = 'data';
|
|
|
|
|
}
|
2013-07-16 11:56:14 +00:00
|
|
|
break;
|
2008-06-25 01:10:51 +00:00
|
|
|
}
|
|
|
|
|
}
|
|
|
|
|
|
2013-07-16 11:56:14 +00:00
|
|
|
private function closeTagOpenState()
|
|
|
|
|
{
|
2008-06-25 01:10:51 +00:00
|
|
|
$next_node = strtolower($this->characters('A-Za-z', $this->char + 1));
|
|
|
|
|
$the_same = count($this->tree->stack) > 0 && $next_node === end($this->tree->stack)->nodeName;
|
|
|
|
|
|
2013-07-16 11:56:14 +00:00
|
|
|
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)))
|
|
|
|
|
) {
|
2008-06-25 01:10:51 +00:00
|
|
|
/* 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. */
|
2013-07-16 11:56:14 +00:00
|
|
|
$this->emitToken(
|
|
|
|
|
array(
|
|
|
|
|
'type' => self::CHARACTR,
|
|
|
|
|
'data' => '</'
|
|
|
|
|
)
|
|
|
|
|
);
|
2008-06-25 01:10:51 +00:00
|
|
|
|
|
|
|
|
$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 = $this->char();
|
|
|
|
|
|
2013-07-16 11:56:14 +00:00
|
|
|
if (preg_match('/^[A-Za-z]$/', $char)) {
|
2008-06-25 01:10:51 +00:00
|
|
|
/* 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.) */
|
|
|
|
|
$this->token = array(
|
2013-07-16 11:56:14 +00:00
|
|
|
'name' => strtolower($char),
|
|
|
|
|
'type' => self::ENDTAG
|
2008-06-25 01:10:51 +00:00
|
|
|
);
|
|
|
|
|
|
|
|
|
|
$this->state = 'tagName';
|
|
|
|
|
|
2013-07-16 11:56:14 +00:00
|
|
|
} elseif ($char === '>') {
|
2008-06-25 01:10:51 +00:00
|
|
|
/* U+003E GREATER-THAN SIGN (>)
|
|
|
|
|
Parse error. Switch to the data state. */
|
|
|
|
|
$this->state = 'data';
|
|
|
|
|
|
2013-07-16 11:56:14 +00:00
|
|
|
} elseif ($this->char === $this->EOF) {
|
2008-06-25 01:10:51 +00:00
|
|
|
/* 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. */
|
2013-07-16 11:56:14 +00:00
|
|
|
$this->emitToken(
|
|
|
|
|
array(
|
|
|
|
|
'type' => self::CHARACTR,
|
|
|
|
|
'data' => '</'
|
|
|
|
|
)
|
|
|
|
|
);
|
2008-06-25 01:10:51 +00:00
|
|
|
|
|
|
|
|
$this->char--;
|
|
|
|
|
$this->state = 'data';
|
|
|
|
|
|
|
|
|
|
} else {
|
|
|
|
|
/* Parse error. Switch to the bogus comment state. */
|
|
|
|
|
$this->state = 'bogusComment';
|
|
|
|
|
}
|
|
|
|
|
}
|
|
|
|
|
}
|
|
|
|
|
|
2013-07-16 11:56:14 +00:00
|
|
|
private function tagNameState()
|
|
|
|
|
{
|
2008-06-25 01:10:51 +00:00
|
|
|
// Consume the next input character:
|
|
|
|
|
$this->char++;
|
|
|
|
|
$char = $this->character($this->char);
|
|
|
|
|
|
2013-07-16 11:56:14 +00:00
|
|
|
if (preg_match('/^[\t\n\x0b\x0c ]$/', $char)) {
|
2008-06-25 01:10:51 +00:00
|
|
|
/* 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. */
|
|
|
|
|
$this->state = 'beforeAttributeName';
|
|
|
|
|
|
2013-07-16 11:56:14 +00:00
|
|
|
} elseif ($char === '>') {
|
2008-06-25 01:10:51 +00:00
|
|
|
/* U+003E GREATER-THAN SIGN (>)
|
|
|
|
|
Emit the current tag token. Switch to the data state. */
|
|
|
|
|
$this->emitToken($this->token);
|
|
|
|
|
$this->state = 'data';
|
|
|
|
|
|
2013-07-16 11:56:14 +00:00
|
|
|
} elseif ($this->char === $this->EOF) {
|
2008-06-25 01:10:51 +00:00
|
|
|
/* EOF
|
|
|
|
|
Parse error. Emit the current tag token. Reconsume the EOF
|
|
|
|
|
character in the data state. */
|
|
|
|
|
$this->emitToken($this->token);
|
|
|
|
|
|
|
|
|
|
$this->char--;
|
|
|
|
|
$this->state = 'data';
|
|
|
|
|
|
2013-07-16 11:56:14 +00:00
|
|
|
} elseif ($char === '/') {
|
2008-06-25 01:10:51 +00:00
|
|
|
/* 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';
|
|
|
|
|
}
|
|
|
|
|
}
|
|
|
|
|
|
2013-07-16 11:56:14 +00:00
|
|
|
private function beforeAttributeNameState()
|
|
|
|
|
{
|
2008-06-25 01:10:51 +00:00
|
|
|
// Consume the next input character:
|
|
|
|
|
$this->char++;
|
|
|
|
|
$char = $this->character($this->char);
|
|
|
|
|
|
2013-07-16 11:56:14 +00:00
|
|
|
if (preg_match('/^[\t\n\x0b\x0c ]$/', $char)) {
|
2008-06-25 01:10:51 +00:00
|
|
|
/* 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. */
|
|
|
|
|
$this->state = 'beforeAttributeName';
|
|
|
|
|
|
2013-07-16 11:56:14 +00:00
|
|
|
} elseif ($char === '>') {
|
2008-06-25 01:10:51 +00:00
|
|
|
/* U+003E GREATER-THAN SIGN (>)
|
|
|
|
|
Emit the current tag token. Switch to the data state. */
|
|
|
|
|
$this->emitToken($this->token);
|
|
|
|
|
$this->state = 'data';
|
|
|
|
|
|
2013-07-16 11:56:14 +00:00
|
|
|
} elseif ($char === '/') {
|
2008-06-25 01:10:51 +00:00
|
|
|
/* U+002F SOLIDUS (/)
|
|
|
|
|
Parse error unless this is a permitted slash. Stay in the before
|
|
|
|
|
attribute name state. */
|
|
|
|
|
$this->state = 'beforeAttributeName';
|
|
|
|
|
|
2013-07-16 11:56:14 +00:00
|
|
|
} elseif ($this->char === $this->EOF) {
|
2008-06-25 01:10:51 +00:00
|
|
|
/* 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. */
|
|
|
|
|
$this->token['attr'][] = array(
|
2013-07-16 11:56:14 +00:00
|
|
|
'name' => strtolower($char),
|
2008-06-25 01:10:51 +00:00
|
|
|
'value' => null
|
|
|
|
|
);
|
|
|
|
|
|
|
|
|
|
$this->state = 'attributeName';
|
|
|
|
|
}
|
|
|
|
|
}
|
|
|
|
|
|
2013-07-16 11:56:14 +00:00
|
|
|
private function attributeNameState()
|
|
|
|
|
{
|
2008-06-25 01:10:51 +00:00
|
|
|
// Consume the next input character:
|
|
|
|
|
$this->char++;
|
|
|
|
|
$char = $this->character($this->char);
|
|
|
|
|
|
2013-07-16 11:56:14 +00:00
|
|
|
if (preg_match('/^[\t\n\x0b\x0c ]$/', $char)) {
|
2008-06-25 01:10:51 +00:00
|
|
|
/* 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. */
|
|
|
|
|
$this->state = 'afterAttributeName';
|
|
|
|
|
|
2013-07-16 11:56:14 +00:00
|
|
|
} elseif ($char === '=') {
|
2008-06-25 01:10:51 +00:00
|
|
|
/* U+003D EQUALS SIGN (=)
|
|
|
|
|
Switch to the before attribute value state. */
|
|
|
|
|
$this->state = 'beforeAttributeValue';
|
|
|
|
|
|
2013-07-16 11:56:14 +00:00
|
|
|
} elseif ($char === '>') {
|
2008-06-25 01:10:51 +00:00
|
|
|
/* U+003E GREATER-THAN SIGN (>)
|
|
|
|
|
Emit the current tag token. Switch to the data state. */
|
|
|
|
|
$this->emitToken($this->token);
|
|
|
|
|
$this->state = 'data';
|
|
|
|
|
|
2013-07-16 11:56:14 +00:00
|
|
|
} elseif ($char === '/' && $this->character($this->char + 1) !== '>') {
|
2008-06-25 01:10:51 +00:00
|
|
|
/* U+002F SOLIDUS (/)
|
|
|
|
|
Parse error unless this is a permitted slash. Switch to the before
|
|
|
|
|
attribute name state. */
|
|
|
|
|
$this->state = 'beforeAttributeName';
|
|
|
|
|
|
2013-07-16 11:56:14 +00:00
|
|
|
} elseif ($this->char === $this->EOF) {
|
2008-06-25 01:10:51 +00:00
|
|
|
/* 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';
|
|
|
|
|
}
|
|
|
|
|
}
|
|
|
|
|
|
2013-07-16 11:56:14 +00:00
|
|
|
private function afterAttributeNameState()
|
|
|
|
|
{
|
2008-06-25 01:10:51 +00:00
|
|
|
// Consume the next input character:
|
|
|
|
|
$this->char++;
|
|
|
|
|
$char = $this->character($this->char);
|
|
|
|
|
|
2013-07-16 11:56:14 +00:00
|
|
|
if (preg_match('/^[\t\n\x0b\x0c ]$/', $char)) {
|
2008-06-25 01:10:51 +00:00
|
|
|
/* 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. */
|
|
|
|
|
$this->state = 'afterAttributeName';
|
|
|
|
|
|
2013-07-16 11:56:14 +00:00
|
|
|
} elseif ($char === '=') {
|
2008-06-25 01:10:51 +00:00
|
|
|
/* U+003D EQUALS SIGN (=)
|
|
|
|
|
Switch to the before attribute value state. */
|
|
|
|
|
$this->state = 'beforeAttributeValue';
|
|
|
|
|
|
2013-07-16 11:56:14 +00:00
|
|
|
} elseif ($char === '>') {
|
2008-06-25 01:10:51 +00:00
|
|
|
/* U+003E GREATER-THAN SIGN (>)
|
|
|
|
|
Emit the current tag token. Switch to the data state. */
|
|
|
|
|
$this->emitToken($this->token);
|
|
|
|
|
$this->state = 'data';
|
|
|
|
|
|
2013-07-16 11:56:14 +00:00
|
|
|
} elseif ($char === '/' && $this->character($this->char + 1) !== '>') {
|
2008-06-25 01:10:51 +00:00
|
|
|
/* U+002F SOLIDUS (/)
|
|
|
|
|
Parse error unless this is a permitted slash. Switch to the
|
|
|
|
|
before attribute name state. */
|
|
|
|
|
$this->state = 'beforeAttributeName';
|
|
|
|
|
|
2013-07-16 11:56:14 +00:00
|
|
|
} elseif ($this->char === $this->EOF) {
|
2008-06-25 01:10:51 +00:00
|
|
|
/* 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. */
|
|
|
|
|
$this->token['attr'][] = array(
|
2013-07-16 11:56:14 +00:00
|
|
|
'name' => strtolower($char),
|
2008-06-25 01:10:51 +00:00
|
|
|
'value' => null
|
|
|
|
|
);
|
|
|
|
|
|
|
|
|
|
$this->state = 'attributeName';
|
|
|
|
|
}
|
|
|
|
|
}
|
|
|
|
|
|
2013-07-16 11:56:14 +00:00
|
|
|
private function beforeAttributeValueState()
|
|
|
|
|
{
|
2008-06-25 01:10:51 +00:00
|
|
|
// Consume the next input character:
|
|
|
|
|
$this->char++;
|
|
|
|
|
$char = $this->character($this->char);
|
|
|
|
|
|
2013-07-16 11:56:14 +00:00
|
|
|
if (preg_match('/^[\t\n\x0b\x0c ]$/', $char)) {
|
2008-06-25 01:10:51 +00:00
|
|
|
/* 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. */
|
|
|
|
|
$this->state = 'beforeAttributeValue';
|
|
|
|
|
|
2013-07-16 11:56:14 +00:00
|
|
|
} elseif ($char === '"') {
|
2008-06-25 01:10:51 +00:00
|
|
|
/* U+0022 QUOTATION MARK (")
|
|
|
|
|
Switch to the attribute value (double-quoted) state. */
|
|
|
|
|
$this->state = 'attributeValueDoubleQuoted';
|
|
|
|
|
|
2013-07-16 11:56:14 +00:00
|
|
|
} elseif ($char === '&') {
|
2008-06-25 01:10:51 +00:00
|
|
|
/* U+0026 AMPERSAND (&)
|
|
|
|
|
Switch to the attribute value (unquoted) state and reconsume
|
|
|
|
|
this input character. */
|
|
|
|
|
$this->char--;
|
|
|
|
|
$this->state = 'attributeValueUnquoted';
|
|
|
|
|
|
2013-07-16 11:56:14 +00:00
|
|
|
} elseif ($char === '\'') {
|
2008-06-25 01:10:51 +00:00
|
|
|
/* U+0027 APOSTROPHE (')
|
|
|
|
|
Switch to the attribute value (single-quoted) state. */
|
|
|
|
|
$this->state = 'attributeValueSingleQuoted';
|
|
|
|
|
|
2013-07-16 11:56:14 +00:00
|
|
|
} elseif ($char === '>') {
|
2008-06-25 01:10:51 +00:00
|
|
|
/* 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';
|
|
|
|
|
}
|
|
|
|
|
}
|
|
|
|
|
|
2013-07-16 11:56:14 +00:00
|
|
|
private function attributeValueDoubleQuotedState()
|
|
|
|
|
{
|
2008-06-25 01:10:51 +00:00
|
|
|
// Consume the next input character:
|
|
|
|
|
$this->char++;
|
|
|
|
|
$char = $this->character($this->char);
|
|
|
|
|
|
2013-07-16 11:56:14 +00:00
|
|
|
if ($char === '"') {
|
2008-06-25 01:10:51 +00:00
|
|
|
/* U+0022 QUOTATION MARK (")
|
|
|
|
|
Switch to the before attribute name state. */
|
|
|
|
|
$this->state = 'beforeAttributeName';
|
|
|
|
|
|
2013-07-16 11:56:14 +00:00
|
|
|
} elseif ($char === '&') {
|
2008-06-25 01:10:51 +00:00
|
|
|
/* U+0026 AMPERSAND (&)
|
|
|
|
|
Switch to the entity in attribute value state. */
|
|
|
|
|
$this->entityInAttributeValueState('double');
|
|
|
|
|
|
2013-07-16 11:56:14 +00:00
|
|
|
} elseif ($this->char === $this->EOF) {
|
2008-06-25 01:10:51 +00:00
|
|
|
/* 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';
|
|
|
|
|
}
|
|
|
|
|
}
|
|
|
|
|
|
2013-07-16 11:56:14 +00:00
|
|
|
private function attributeValueSingleQuotedState()
|
|
|
|
|
{
|
2008-06-25 01:10:51 +00:00
|
|
|
// Consume the next input character:
|
|
|
|
|
$this->char++;
|
|
|
|
|
$char = $this->character($this->char);
|
|
|
|
|
|
2013-07-16 11:56:14 +00:00
|
|
|
if ($char === '\'') {
|
2008-06-25 01:10:51 +00:00
|
|
|
/* U+0022 QUOTATION MARK (')
|
|
|
|
|
Switch to the before attribute name state. */
|
|
|
|
|
$this->state = 'beforeAttributeName';
|
|
|
|
|
|
2013-07-16 11:56:14 +00:00
|
|
|
} elseif ($char === '&') {
|
2008-06-25 01:10:51 +00:00
|
|
|
/* U+0026 AMPERSAND (&)
|
|
|
|
|
Switch to the entity in attribute value state. */
|
|
|
|
|
$this->entityInAttributeValueState('single');
|
|
|
|
|
|
2013-07-16 11:56:14 +00:00
|
|
|
} elseif ($this->char === $this->EOF) {
|
2008-06-25 01:10:51 +00:00
|
|
|
/* 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';
|
|
|
|
|
}
|
|
|
|
|
}
|
|
|
|
|
|
2013-07-16 11:56:14 +00:00
|
|
|
private function attributeValueUnquotedState()
|
|
|
|
|
{
|
2008-06-25 01:10:51 +00:00
|
|
|
// Consume the next input character:
|
|
|
|
|
$this->char++;
|
|
|
|
|
$char = $this->character($this->char);
|
|
|
|
|
|
2013-07-16 11:56:14 +00:00
|
|
|
if (preg_match('/^[\t\n\x0b\x0c ]$/', $char)) {
|
2008-06-25 01:10:51 +00:00
|
|
|
/* 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. */
|
|
|
|
|
$this->state = 'beforeAttributeName';
|
|
|
|
|
|
2013-07-16 11:56:14 +00:00
|
|
|
} elseif ($char === '&') {
|
2008-06-25 01:10:51 +00:00
|
|
|
/* U+0026 AMPERSAND (&)
|
|
|
|
|
Switch to the entity in attribute value state. */
|
|
|
|
|
$this->entityInAttributeValueState();
|
|
|
|
|
|
2013-07-16 11:56:14 +00:00
|
|
|
} elseif ($char === '>') {
|
2008-06-25 01:10:51 +00:00
|
|
|
/* 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';
|
|
|
|
|
}
|
|
|
|
|
}
|
|
|
|
|
|
2013-07-16 11:56:14 +00:00
|
|
|
private function entityInAttributeValueState()
|
|
|
|
|
{
|
2008-06-25 01:10:51 +00:00
|
|
|
// 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;
|
|
|
|
|
}
|
|
|
|
|
|
2013-07-16 11:56:14 +00:00
|
|
|
private function bogusCommentState()
|
|
|
|
|
{
|
2008-06-25 01:10:51 +00:00
|
|
|
/* 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);
|
2013-07-16 11:56:14 +00:00
|
|
|
$this->emitToken(
|
|
|
|
|
array(
|
|
|
|
|
'data' => $data,
|
|
|
|
|
'type' => self::COMMENT
|
|
|
|
|
)
|
|
|
|
|
);
|
2008-06-25 01:10:51 +00:00
|
|
|
|
|
|
|
|
$this->char += strlen($data);
|
|
|
|
|
|
|
|
|
|
/* Switch to the data state. */
|
|
|
|
|
$this->state = 'data';
|
|
|
|
|
|
|
|
|
|
/* If the end of the file was reached, reconsume the EOF character. */
|
2013-07-16 11:56:14 +00:00
|
|
|
if ($this->char === $this->EOF) {
|
2008-06-25 01:10:51 +00:00
|
|
|
$this->char = $this->EOF - 1;
|
|
|
|
|
}
|
|
|
|
|
}
|
|
|
|
|
|
2013-07-16 11:56:14 +00:00
|
|
|
private function markupDeclarationOpenState()
|
|
|
|
|
{
|
2008-06-25 01:10:51 +00:00
|
|
|
/* If the next two characters are both U+002D HYPHEN-MINUS (-)
|
|
|
|
|
characters, consume those two characters, create a comment token whose
|
|
|
|
|
data is the empty string, and switch to the comment state. */
|
2013-07-16 11:56:14 +00:00
|
|
|
if ($this->character($this->char + 1, 2) === '--') {
|
2008-06-25 01:10:51 +00:00
|
|
|
$this->char += 2;
|
|
|
|
|
$this->state = 'comment';
|
|
|
|
|
$this->token = array(
|
|
|
|
|
'data' => null,
|
|
|
|
|
'type' => self::COMMENT
|
|
|
|
|
);
|
|
|
|
|
|
2013-07-16 11:56:14 +00:00
|
|
|
/* Otherwise if the next seven chacacters are a case-insensitive match
|
|
|
|
|
for the word "DOCTYPE", then consume those characters and switch to the
|
|
|
|
|
DOCTYPE state. */
|
|
|
|
|
} elseif (strtolower($this->character($this->char + 1, 7)) === 'doctype') {
|
2008-06-25 01:10:51 +00:00
|
|
|
$this->char += 7;
|
|
|
|
|
$this->state = 'doctype';
|
|
|
|
|
|
2013-07-16 11:56:14 +00:00
|
|
|
/* 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. */
|
2008-06-25 01:10:51 +00:00
|
|
|
} else {
|
|
|
|
|
$this->char++;
|
|
|
|
|
$this->state = 'bogusComment';
|
|
|
|
|
}
|
|
|
|
|
}
|
|
|
|
|
|
2013-07-16 11:56:14 +00:00
|
|
|
private function commentState()
|
|
|
|
|
{
|
2008-06-25 01:10:51 +00:00
|
|
|
/* Consume the next input character: */
|
|
|
|
|
$this->char++;
|
|
|
|
|
$char = $this->char();
|
|
|
|
|
|
|
|
|
|
/* U+002D HYPHEN-MINUS (-) */
|
2013-07-16 11:56:14 +00:00
|
|
|
if ($char === '-') {
|
2008-06-25 01:10:51 +00:00
|
|
|
/* Switch to the comment dash state */
|
|
|
|
|
$this->state = 'commentDash';
|
|
|
|
|
|
2013-07-16 11:56:14 +00:00
|
|
|
/* EOF */
|
|
|
|
|
} elseif ($this->char === $this->EOF) {
|
2008-06-25 01:10:51 +00:00
|
|
|
/* Parse error. Emit the comment token. Reconsume the EOF character
|
|
|
|
|
in the data state. */
|
|
|
|
|
$this->emitToken($this->token);
|
|
|
|
|
$this->char--;
|
|
|
|
|
$this->state = 'data';
|
|
|
|
|
|
2013-07-16 11:56:14 +00:00
|
|
|
/* Anything else */
|
2008-06-25 01:10:51 +00:00
|
|
|
} else {
|
|
|
|
|
/* Append the input character to the comment token's data. Stay in
|
|
|
|
|
the comment state. */
|
|
|
|
|
$this->token['data'] .= $char;
|
|
|
|
|
}
|
|
|
|
|
}
|
|
|
|
|
|
2013-07-16 11:56:14 +00:00
|
|
|
private function commentDashState()
|
|
|
|
|
{
|
2008-06-25 01:10:51 +00:00
|
|
|
/* Consume the next input character: */
|
|
|
|
|
$this->char++;
|
|
|
|
|
$char = $this->char();
|
|
|
|
|
|
|
|
|
|
/* U+002D HYPHEN-MINUS (-) */
|
2013-07-16 11:56:14 +00:00
|
|
|
if ($char === '-') {
|
2008-06-25 01:10:51 +00:00
|
|
|
/* Switch to the comment end state */
|
|
|
|
|
$this->state = 'commentEnd';
|
|
|
|
|
|
2013-07-16 11:56:14 +00:00
|
|
|
/* EOF */
|
|
|
|
|
} elseif ($this->char === $this->EOF) {
|
2008-06-25 01:10:51 +00:00
|
|
|
/* Parse error. Emit the comment token. Reconsume the EOF character
|
|
|
|
|
in the data state. */
|
|
|
|
|
$this->emitToken($this->token);
|
|
|
|
|
$this->char--;
|
|
|
|
|
$this->state = 'data';
|
|
|
|
|
|
2013-07-16 11:56:14 +00:00
|
|
|
/* Anything else */
|
2008-06-25 01:10:51 +00:00
|
|
|
} else {
|
|
|
|
|
/* Append a U+002D HYPHEN-MINUS (-) character and the input
|
|
|
|
|
character to the comment token's data. Switch to the comment state. */
|
2013-07-16 11:56:14 +00:00
|
|
|
$this->token['data'] .= '-' . $char;
|
2008-06-25 01:10:51 +00:00
|
|
|
$this->state = 'comment';
|
|
|
|
|
}
|
|
|
|
|
}
|
|
|
|
|
|
2013-07-16 11:56:14 +00:00
|
|
|
private function commentEndState()
|
|
|
|
|
{
|
2008-06-25 01:10:51 +00:00
|
|
|
/* Consume the next input character: */
|
|
|
|
|
$this->char++;
|
|
|
|
|
$char = $this->char();
|
|
|
|
|
|
2013-07-16 11:56:14 +00:00
|
|
|
if ($char === '>') {
|
2008-06-25 01:10:51 +00:00
|
|
|
$this->emitToken($this->token);
|
|
|
|
|
$this->state = 'data';
|
|
|
|
|
|
2013-07-16 11:56:14 +00:00
|
|
|
} elseif ($char === '-') {
|
2008-06-25 01:10:51 +00:00
|
|
|
$this->token['data'] .= '-';
|
|
|
|
|
|
2013-07-16 11:56:14 +00:00
|
|
|
} elseif ($this->char === $this->EOF) {
|
2008-06-25 01:10:51 +00:00
|
|
|
$this->emitToken($this->token);
|
|
|
|
|
$this->char--;
|
|
|
|
|
$this->state = 'data';
|
|
|
|
|
|
|
|
|
|
} else {
|
2013-07-16 11:56:14 +00:00
|
|
|
$this->token['data'] .= '--' . $char;
|
2008-06-25 01:10:51 +00:00
|
|
|
$this->state = 'comment';
|
|
|
|
|
}
|
|
|
|
|
}
|
|
|
|
|
|
2013-07-16 11:56:14 +00:00
|
|
|
private function doctypeState()
|
|
|
|
|
{
|
2008-06-25 01:10:51 +00:00
|
|
|
/* Consume the next input character: */
|
|
|
|
|
$this->char++;
|
|
|
|
|
$char = $this->char();
|
|
|
|
|
|
2013-07-16 11:56:14 +00:00
|
|
|
if (preg_match('/^[\t\n\x0b\x0c ]$/', $char)) {
|
2008-06-25 01:10:51 +00:00
|
|
|
$this->state = 'beforeDoctypeName';
|
|
|
|
|
|
|
|
|
|
} else {
|
|
|
|
|
$this->char--;
|
|
|
|
|
$this->state = 'beforeDoctypeName';
|
|
|
|
|
}
|
|
|
|
|
}
|
|
|
|
|
|
2013-07-16 11:56:14 +00:00
|
|
|
private function beforeDoctypeNameState()
|
|
|
|
|
{
|
2008-06-25 01:10:51 +00:00
|
|
|
/* Consume the next input character: */
|
|
|
|
|
$this->char++;
|
|
|
|
|
$char = $this->char();
|
|
|
|
|
|
2013-07-16 11:56:14 +00:00
|
|
|
if (preg_match('/^[\t\n\x0b\x0c ]$/', $char)) {
|
2008-06-25 01:10:51 +00:00
|
|
|
// Stay in the before DOCTYPE name state.
|
|
|
|
|
|
2013-07-16 11:56:14 +00:00
|
|
|
} elseif (preg_match('/^[a-z]$/', $char)) {
|
2008-06-25 01:10:51 +00:00
|
|
|
$this->token = array(
|
|
|
|
|
'name' => strtoupper($char),
|
|
|
|
|
'type' => self::DOCTYPE,
|
|
|
|
|
'error' => true
|
|
|
|
|
);
|
|
|
|
|
|
|
|
|
|
$this->state = 'doctypeName';
|
|
|
|
|
|
2013-07-16 11:56:14 +00:00
|
|
|
} elseif ($char === '>') {
|
|
|
|
|
$this->emitToken(
|
|
|
|
|
array(
|
|
|
|
|
'name' => null,
|
|
|
|
|
'type' => self::DOCTYPE,
|
|
|
|
|
'error' => true
|
|
|
|
|
)
|
|
|
|
|
);
|
2008-06-25 01:10:51 +00:00
|
|
|
|
|
|
|
|
$this->state = 'data';
|
|
|
|
|
|
2013-07-16 11:56:14 +00:00
|
|
|
} elseif ($this->char === $this->EOF) {
|
|
|
|
|
$this->emitToken(
|
|
|
|
|
array(
|
|
|
|
|
'name' => null,
|
|
|
|
|
'type' => self::DOCTYPE,
|
|
|
|
|
'error' => true
|
|
|
|
|
)
|
|
|
|
|
);
|
2008-06-25 01:10:51 +00:00
|
|
|
|
|
|
|
|
$this->char--;
|
|
|
|
|
$this->state = 'data';
|
|
|
|
|
|
|
|
|
|
} else {
|
|
|
|
|
$this->token = array(
|
|
|
|
|
'name' => $char,
|
|
|
|
|
'type' => self::DOCTYPE,
|
|
|
|
|
'error' => true
|
|
|
|
|
);
|
|
|
|
|
|
|
|
|
|
$this->state = 'doctypeName';
|
|
|
|
|
}
|
|
|
|
|
}
|
|
|
|
|
|
2013-07-16 11:56:14 +00:00
|
|
|
private function doctypeNameState()
|
|
|
|
|
{
|
2008-06-25 01:10:51 +00:00
|
|
|
/* Consume the next input character: */
|
|
|
|
|
$this->char++;
|
|
|
|
|
$char = $this->char();
|
|
|
|
|
|
2013-07-16 11:56:14 +00:00
|
|
|
if (preg_match('/^[\t\n\x0b\x0c ]$/', $char)) {
|
2008-06-25 01:10:51 +00:00
|
|
|
$this->state = 'AfterDoctypeName';
|
|
|
|
|
|
2013-07-16 11:56:14 +00:00
|
|
|
} elseif ($char === '>') {
|
2008-06-25 01:10:51 +00:00
|
|
|
$this->emitToken($this->token);
|
|
|
|
|
$this->state = 'data';
|
|
|
|
|
|
2013-07-16 11:56:14 +00:00
|
|
|
} elseif (preg_match('/^[a-z]$/', $char)) {
|
2008-06-25 01:10:51 +00:00
|
|
|
$this->token['name'] .= strtoupper($char);
|
|
|
|
|
|
2013-07-16 11:56:14 +00:00
|
|
|
} elseif ($this->char === $this->EOF) {
|
2008-06-25 01:10:51 +00:00
|
|
|
$this->emitToken($this->token);
|
|
|
|
|
$this->char--;
|
|
|
|
|
$this->state = 'data';
|
|
|
|
|
|
|
|
|
|
} else {
|
|
|
|
|
$this->token['name'] .= $char;
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
$this->token['error'] = ($this->token['name'] === 'HTML')
|
|
|
|
|
? false
|
|
|
|
|
: true;
|
|
|
|
|
}
|
|
|
|
|
|
2013-07-16 11:56:14 +00:00
|
|
|
private function afterDoctypeNameState()
|
|
|
|
|
{
|
2008-06-25 01:10:51 +00:00
|
|
|
/* Consume the next input character: */
|
|
|
|
|
$this->char++;
|
|
|
|
|
$char = $this->char();
|
|
|
|
|
|
2013-07-16 11:56:14 +00:00
|
|
|
if (preg_match('/^[\t\n\x0b\x0c ]$/', $char)) {
|
2008-06-25 01:10:51 +00:00
|
|
|
// Stay in the DOCTYPE name state.
|
|
|
|
|
|
2013-07-16 11:56:14 +00:00
|
|
|
} elseif ($char === '>') {
|
2008-06-25 01:10:51 +00:00
|
|
|
$this->emitToken($this->token);
|
|
|
|
|
$this->state = 'data';
|
|
|
|
|
|
2013-07-16 11:56:14 +00:00
|
|
|
} elseif ($this->char === $this->EOF) {
|
2008-06-25 01:10:51 +00:00
|
|
|
$this->emitToken($this->token);
|
|
|
|
|
$this->char--;
|
|
|
|
|
$this->state = 'data';
|
|
|
|
|
|
|
|
|
|
} else {
|
|
|
|
|
$this->token['error'] = true;
|
|
|
|
|
$this->state = 'bogusDoctype';
|
|
|
|
|
}
|
|
|
|
|
}
|
|
|
|
|
|
2013-07-16 11:56:14 +00:00
|
|
|
private function bogusDoctypeState()
|
|
|
|
|
{
|
2008-06-25 01:10:51 +00:00
|
|
|
/* Consume the next input character: */
|
|
|
|
|
$this->char++;
|
|
|
|
|
$char = $this->char();
|
|
|
|
|
|
2013-07-16 11:56:14 +00:00
|
|
|
if ($char === '>') {
|
2008-06-25 01:10:51 +00:00
|
|
|
$this->emitToken($this->token);
|
|
|
|
|
$this->state = 'data';
|
|
|
|
|
|
2013-07-16 11:56:14 +00:00
|
|
|
} elseif ($this->char === $this->EOF) {
|
2008-06-25 01:10:51 +00:00
|
|
|
$this->emitToken($this->token);
|
|
|
|
|
$this->char--;
|
|
|
|
|
$this->state = 'data';
|
|
|
|
|
|
|
|
|
|
} else {
|
|
|
|
|
// Stay in the bogus DOCTYPE state.
|
|
|
|
|
}
|
|
|
|
|
}
|
|
|
|
|
|
2013-07-16 11:56:14 +00:00
|
|
|
private function entity()
|
|
|
|
|
{
|
2008-06-25 01:10:51 +00:00
|
|
|
$start = $this->char;
|
|
|
|
|
|
|
|
|
|
// This section defines how to consume an entity. This definition is
|
|
|
|
|
// used when parsing entities in text and in attributes.
|
|
|
|
|
|
|
|
|
|
// The behaviour depends on the identity of the next character (the
|
2013-07-16 11:56:14 +00:00
|
|
|
// one immediately after the U+0026 AMPERSAND character):
|
2008-06-25 01:10:51 +00:00
|
|
|
|
2013-07-16 11:56:14 +00:00
|
|
|
switch ($this->character($this->char + 1)) {
|
2008-06-25 01:10:51 +00:00
|
|
|
// U+0023 NUMBER SIGN (#)
|
|
|
|
|
case '#':
|
|
|
|
|
|
|
|
|
|
// The behaviour further depends on the character after the
|
|
|
|
|
// U+0023 NUMBER SIGN:
|
2013-07-16 11:56:14 +00:00
|
|
|
switch ($this->character($this->char + 1)) {
|
2008-06-25 01:10:51 +00:00
|
|
|
// 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';
|
2013-07-16 11:56:14 +00:00
|
|
|
break;
|
2008-06-25 01:10:51 +00:00
|
|
|
|
|
|
|
|
// 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';
|
2013-07-16 11:56:14 +00:00
|
|
|
break;
|
2008-06-25 01:10:51 +00:00
|
|
|
}
|
|
|
|
|
|
|
|
|
|
// 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.
|
2013-07-16 11:56:14 +00:00
|
|
|
break;
|
2008-06-25 01:10:51 +00:00
|
|
|
|
|
|
|
|
// 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);
|
|
|
|
|
|
2013-07-16 11:56:14 +00:00
|
|
|
for ($c = 1; $c <= $len; $c++) {
|
2008-06-25 01:10:51 +00:00
|
|
|
$id = substr($e_name, 0, $c);
|
|
|
|
|
$this->char++;
|
|
|
|
|
|
2013-07-16 11:56:14 +00:00
|
|
|
if (in_array($id, $this->entities)) {
|
|
|
|
|
if ($e_name[$c - 1] !== ';') {
|
2008-06-25 01:10:51 +00:00
|
|
|
if ($c < $len && $e_name[$c] == ';') {
|
|
|
|
|
$this->char++; // consume extra semicolon
|
|
|
|
|
}
|
|
|
|
|
}
|
|
|
|
|
$entity = $id;
|
|
|
|
|
break;
|
|
|
|
|
}
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
$cond = isset($entity);
|
|
|
|
|
// The rest of the parsing happens bellow.
|
2013-07-16 11:56:14 +00:00
|
|
|
break;
|
2008-06-25 01:10:51 +00:00
|
|
|
}
|
|
|
|
|
|
2013-07-16 11:56:14 +00:00
|
|
|
if (!$cond) {
|
2008-06-25 01:10:51 +00:00
|
|
|
// 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).
|
2013-07-16 11:56:14 +00:00
|
|
|
return html_entity_decode('&' . $entity . ';', ENT_QUOTES, 'UTF-8');
|
2008-06-25 01:10:51 +00:00
|
|
|
}
|
|
|
|
|
|
2013-07-16 11:56:14 +00:00
|
|
|
private function emitToken($token)
|
|
|
|
|
{
|
2008-06-25 01:10:51 +00:00
|
|
|
$emit = $this->tree->emitToken($token);
|
|
|
|
|
|
2013-07-16 11:56:14 +00:00
|
|
|
if (is_int($emit)) {
|
2008-06-25 01:10:51 +00:00
|
|
|
$this->content_model = $emit;
|
|
|
|
|
|
2013-07-16 11:56:14 +00:00
|
|
|
} elseif ($token['type'] === self::ENDTAG) {
|
2008-06-25 01:10:51 +00:00
|
|
|
$this->content_model = self::PCDATA;
|
|
|
|
|
}
|
|
|
|
|
}
|
|
|
|
|
|
2013-07-16 11:56:14 +00:00
|
|
|
private function EOF()
|
|
|
|
|
{
|
2008-06-25 01:10:51 +00:00
|
|
|
$this->state = null;
|
2013-07-16 11:56:14 +00:00
|
|
|
$this->tree->emitToken(
|
|
|
|
|
array(
|
|
|
|
|
'type' => self::EOF
|
|
|
|
|
)
|
|
|
|
|
);
|
2008-06-25 01:10:51 +00:00
|
|
|
}
|
|
|
|
|
}
|
|
|
|
|
|
2013-07-16 11:56:14 +00:00
|
|
|
class HTML5TreeConstructer
|
|
|
|
|
{
|
2008-06-25 01:10:51 +00:00
|
|
|
public $stack = array();
|
|
|
|
|
|
|
|
|
|
private $phase;
|
|
|
|
|
private $mode;
|
|
|
|
|
private $dom;
|
|
|
|
|
private $foster_parent = null;
|
2013-07-16 11:56:14 +00:00
|
|
|
private $a_formatting = array();
|
2008-06-25 01:10:51 +00:00
|
|
|
|
|
|
|
|
private $head_pointer = null;
|
|
|
|
|
private $form_pointer = null;
|
|
|
|
|
|
2013-07-16 11:56:14 +00:00
|
|
|
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'
|
|
|
|
|
);
|
2008-06-25 01:10:51 +00:00
|
|
|
|
|
|
|
|
// The different phases.
|
|
|
|
|
const INIT_PHASE = 0;
|
|
|
|
|
const ROOT_PHASE = 1;
|
|
|
|
|
const MAIN_PHASE = 2;
|
2013-07-16 11:56:14 +00:00
|
|
|
const END_PHASE = 3;
|
2008-06-25 01:10:51 +00:00
|
|
|
|
|
|
|
|
// The different insertion modes for the main phase.
|
|
|
|
|
const BEFOR_HEAD = 0;
|
2013-07-16 11:56:14 +00:00
|
|
|
const IN_HEAD = 1;
|
2008-06-25 01:10:51 +00:00
|
|
|
const AFTER_HEAD = 2;
|
2013-07-16 11:56:14 +00:00
|
|
|
const IN_BODY = 3;
|
|
|
|
|
const IN_TABLE = 4;
|
2008-06-25 01:10:51 +00:00
|
|
|
const IN_CAPTION = 5;
|
2013-07-16 11:56:14 +00:00
|
|
|
const IN_CGROUP = 6;
|
|
|
|
|
const IN_TBODY = 7;
|
|
|
|
|
const IN_ROW = 8;
|
|
|
|
|
const IN_CELL = 9;
|
|
|
|
|
const IN_SELECT = 10;
|
2008-06-25 01:10:51 +00:00
|
|
|
const AFTER_BODY = 11;
|
2013-07-16 11:56:14 +00:00
|
|
|
const IN_FRAME = 12;
|
2008-06-25 01:10:51 +00:00
|
|
|
const AFTR_FRAME = 13;
|
|
|
|
|
|
|
|
|
|
// The different types of elements.
|
2013-07-16 11:56:14 +00:00
|
|
|
const SPECIAL = 0;
|
|
|
|
|
const SCOPING = 1;
|
2008-06-25 01:10:51 +00:00
|
|
|
const FORMATTING = 2;
|
2013-07-16 11:56:14 +00:00
|
|
|
const PHRASING = 3;
|
2008-06-25 01:10:51 +00:00
|
|
|
|
2013-07-16 11:56:14 +00:00
|
|
|
const MARKER = 0;
|
2008-06-25 01:10:51 +00:00
|
|
|
|
2013-07-16 11:56:14 +00:00
|
|
|
public function __construct()
|
|
|
|
|
{
|
2008-06-25 01:10:51 +00:00
|
|
|
$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;
|
|
|
|
|
$this->dom->strictErrorChecking = false;
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
// Process tag tokens
|
2013-07-16 11:56:14 +00:00
|
|
|
public function emitToken($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;
|
2008-06-25 01:10:51 +00:00
|
|
|
}
|
|
|
|
|
}
|
|
|
|
|
|
2013-07-16 11:56:14 +00:00
|
|
|
private function initPhase($token)
|
|
|
|
|
{
|
2008-06-25 01:10:51 +00:00
|
|
|
/* Initially, the tree construction stage must handle each token
|
|
|
|
|
emitted from the tokenisation stage as follows: */
|
|
|
|
|
|
|
|
|
|
/* A DOCTYPE token that is marked as being in error
|
|
|
|
|
A comment token
|
|
|
|
|
A start tag token
|
|
|
|
|
An end tag token
|
|
|
|
|
A character token that is not one of one of U+0009 CHARACTER TABULATION,
|
|
|
|
|
U+000A LINE FEED (LF), U+000B LINE TABULATION, U+000C FORM FEED (FF),
|
|
|
|
|
or U+0020 SPACE
|
|
|
|
|
An end-of-file token */
|
2013-07-16 11:56:14 +00:00
|
|
|
if ((isset($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']))
|
|
|
|
|
) {
|
2008-06-25 01:10:51 +00:00
|
|
|
/* 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);
|
|
|
|
|
|
2013-07-16 11:56:14 +00:00
|
|
|
/* A DOCTYPE token marked as being correct */
|
|
|
|
|
} elseif (isset($token['error']) && !$token['error']) {
|
2008-06-25 01:10:51 +00:00
|
|
|
/* 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. */
|
|
|
|
|
$this->phase = self::ROOT_PHASE;
|
|
|
|
|
|
2013-07-16 11:56:14 +00:00
|
|
|
/* A character token that is one of one of U+0009 CHARACTER TABULATION,
|
|
|
|
|
U+000A LINE FEED (LF), U+000B LINE TABULATION, U+000C FORM FEED (FF),
|
|
|
|
|
or U+0020 SPACE */
|
|
|
|
|
} elseif (isset($token['data']) && preg_match(
|
|
|
|
|
'/^[\t\n\x0b\x0c ]+$/',
|
|
|
|
|
$token['data']
|
|
|
|
|
)
|
|
|
|
|
) {
|
2008-06-25 01:10:51 +00:00
|
|
|
/* Append that character to the Document node. */
|
|
|
|
|
$text = $this->dom->createTextNode($token['data']);
|
|
|
|
|
$this->dom->appendChild($text);
|
|
|
|
|
}
|
|
|
|
|
}
|
|
|
|
|
|
2013-07-16 11:56:14 +00:00
|
|
|
private function rootElementPhase($token)
|
|
|
|
|
{
|
2008-06-25 01:10:51 +00:00
|
|
|
/* After the initial phase, as each token is emitted from the tokenisation
|
|
|
|
|
stage, it must be processed as described in this section. */
|
|
|
|
|
|
|
|
|
|
/* A DOCTYPE token */
|
2013-07-16 11:56:14 +00:00
|
|
|
if ($token['type'] === HTML5::DOCTYPE) {
|
2008-06-25 01:10:51 +00:00
|
|
|
// Parse error. Ignore the token.
|
|
|
|
|
|
2013-07-16 11:56:14 +00:00
|
|
|
/* A comment token */
|
|
|
|
|
} elseif ($token['type'] === HTML5::COMMENT) {
|
2008-06-25 01:10:51 +00:00
|
|
|
/* 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);
|
|
|
|
|
|
2013-07-16 11:56:14 +00:00
|
|
|
/* 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'])
|
|
|
|
|
) {
|
2008-06-25 01:10:51 +00:00
|
|
|
/* Append that character to the Document node. */
|
|
|
|
|
$text = $this->dom->createTextNode($token['data']);
|
|
|
|
|
$this->dom->appendChild($text);
|
|
|
|
|
|
2013-07-16 11:56:14 +00:00
|
|
|
/* 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
|
|
|
|
|
) {
|
2008-06-25 01:10:51 +00:00
|
|
|
/* 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);
|
|
|
|
|
}
|
|
|
|
|
}
|
|
|
|
|
|
2013-07-16 11:56:14 +00:00
|
|
|
private function mainPhase($token)
|
|
|
|
|
{
|
2008-06-25 01:10:51 +00:00
|
|
|
/* Tokens in the main phase must be handled as follows: */
|
|
|
|
|
|
|
|
|
|
/* A DOCTYPE token */
|
2013-07-16 11:56:14 +00:00
|
|
|
if ($token['type'] === HTML5::DOCTYPE) {
|
2008-06-25 01:10:51 +00:00
|
|
|
// Parse error. Ignore the token.
|
|
|
|
|
|
2013-07-16 11:56:14 +00:00
|
|
|
/* A start tag token with the tag name "html" */
|
|
|
|
|
} elseif ($token['type'] === HTML5::STARTTAG && $token['name'] === 'html') {
|
2008-06-25 01:10:51 +00:00
|
|
|
/* If this start tag token was not the first start tag token, then
|
|
|
|
|
it is a parse error. */
|
|
|
|
|
|
|
|
|
|
/* For each attribute on the token, check to see if the attribute
|
|
|
|
|
is already present on the top element of the stack of open elements.
|
|
|
|
|
If it is not, add the attribute and its corresponding value to that
|
|
|
|
|
element. */
|
2013-07-16 11:56:14 +00:00
|
|
|
foreach ($token['attr'] as $attr) {
|
|
|
|
|
if (!$this->stack[0]->hasAttribute($attr['name'])) {
|
2008-06-25 01:10:51 +00:00
|
|
|
$this->stack[0]->setAttribute($attr['name'], $attr['value']);
|
|
|
|
|
}
|
|
|
|
|
}
|
|
|
|
|
|
2013-07-16 11:56:14 +00:00
|
|
|
/* An end-of-file token */
|
|
|
|
|
} elseif ($token['type'] === HTML5::EOF) {
|
2008-06-25 01:10:51 +00:00
|
|
|
/* Generate implied end tags. */
|
|
|
|
|
$this->generateImpliedEndTags();
|
|
|
|
|
|
2013-07-16 11:56:14 +00:00
|
|
|
/* Anything else. */
|
2008-06-25 01:10:51 +00:00
|
|
|
} else {
|
|
|
|
|
/* Depends on the insertion mode: */
|
2013-07-16 11:56:14 +00:00
|
|
|
switch ($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;
|
2008-06-25 01:10:51 +00:00
|
|
|
}
|
|
|
|
|
}
|
|
|
|
|
}
|
|
|
|
|
|
2013-07-16 11:56:14 +00:00
|
|
|
private function beforeHead($token)
|
|
|
|
|
{
|
2008-06-25 01:10:51 +00:00
|
|
|
/* Handle the token as follows: */
|
|
|
|
|
|
|
|
|
|
/* A character token that is one of one of U+0009 CHARACTER TABULATION,
|
|
|
|
|
U+000A LINE FEED (LF), U+000B LINE TABULATION, U+000C FORM FEED (FF),
|
|
|
|
|
or U+0020 SPACE */
|
2013-07-16 11:56:14 +00:00
|
|
|
if ($token['type'] === HTML5::CHARACTR &&
|
|
|
|
|
preg_match('/^[\t\n\x0b\x0c ]+$/', $token['data'])
|
|
|
|
|
) {
|
2008-06-25 01:10:51 +00:00
|
|
|
/* Append the character to the current node. */
|
|
|
|
|
$this->insertText($token['data']);
|
|
|
|
|
|
2013-07-16 11:56:14 +00:00
|
|
|
/* A comment token */
|
|
|
|
|
} elseif ($token['type'] === HTML5::COMMENT) {
|
2008-06-25 01:10:51 +00:00
|
|
|
/* 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']);
|
|
|
|
|
|
2013-07-16 11:56:14 +00:00
|
|
|
/* A start tag token with the tag name "head" */
|
|
|
|
|
} elseif ($token['type'] === HTML5::STARTTAG && $token['name'] === 'head') {
|
2008-06-25 01:10:51 +00:00
|
|
|
/* 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". */
|
|
|
|
|
$this->mode = self::IN_HEAD;
|
|
|
|
|
|
2013-07-16 11:56:14 +00:00
|
|
|
/* A start tag token whose tag name is one of: "base", "link", "meta",
|
|
|
|
|
"script", "style", "title". Or an end tag with the tag name "html".
|
|
|
|
|
Or a character token that is not one of U+0009 CHARACTER TABULATION,
|
|
|
|
|
U+000A LINE FEED (LF), U+000B LINE TABULATION, U+000C FORM FEED (FF),
|
|
|
|
|
or U+0020 SPACE. Or any other start tag token */
|
|
|
|
|
} elseif ($token['type'] === HTML5::STARTTAG ||
|
|
|
|
|
($token['type'] === HTML5::ENDTAG && $token['name'] === 'html') ||
|
|
|
|
|
($token['type'] === HTML5::CHARACTR && !preg_match(
|
|
|
|
|
'/^[\t\n\x0b\x0c ]$/',
|
|
|
|
|
$token['data']
|
|
|
|
|
))
|
|
|
|
|
) {
|
2008-06-25 01:10:51 +00:00
|
|
|
/* Act as if a start tag token with the tag name "head" and no
|
|
|
|
|
attributes had been seen, then reprocess the current token. */
|
2013-07-16 11:56:14 +00:00
|
|
|
$this->beforeHead(
|
|
|
|
|
array(
|
|
|
|
|
'name' => 'head',
|
|
|
|
|
'type' => HTML5::STARTTAG,
|
|
|
|
|
'attr' => array()
|
|
|
|
|
)
|
|
|
|
|
);
|
2008-06-25 01:10:51 +00:00
|
|
|
|
|
|
|
|
return $this->inHead($token);
|
|
|
|
|
|
2013-07-16 11:56:14 +00:00
|
|
|
/* Any other end tag */
|
|
|
|
|
} elseif ($token['type'] === HTML5::ENDTAG) {
|
2008-06-25 01:10:51 +00:00
|
|
|
/* Parse error. Ignore the token. */
|
|
|
|
|
}
|
|
|
|
|
}
|
|
|
|
|
|
2013-07-16 11:56:14 +00:00
|
|
|
private function inHead($token)
|
|
|
|
|
{
|
2008-06-25 01:10:51 +00:00
|
|
|
/* 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. */
|
2013-07-16 11:56:14 +00:00
|
|
|
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')
|
|
|
|
|
))
|
|
|
|
|
) {
|
2008-06-25 01:10:51 +00:00
|
|
|
/* Append the character to the current node. */
|
|
|
|
|
$this->insertText($token['data']);
|
|
|
|
|
|
2013-07-16 11:56:14 +00:00
|
|
|
/* A comment token */
|
|
|
|
|
} elseif ($token['type'] === HTML5::COMMENT) {
|
2008-06-25 01:10:51 +00:00
|
|
|
/* 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']);
|
|
|
|
|
|
2013-07-16 11:56:14 +00:00
|
|
|
} elseif ($token['type'] === HTML5::ENDTAG &&
|
|
|
|
|
in_array($token['name'], array('title', 'style', 'script'))
|
|
|
|
|
) {
|
2008-06-25 01:10:51 +00:00
|
|
|
array_pop($this->stack);
|
|
|
|
|
return HTML5::PCDATA;
|
|
|
|
|
|
2013-07-16 11:56:14 +00:00
|
|
|
/* A start tag with the tag name "title" */
|
|
|
|
|
} elseif ($token['type'] === HTML5::STARTTAG && $token['name'] === 'title') {
|
2008-06-25 01:10:51 +00:00
|
|
|
/* Create an element for the token and append the new element to the
|
|
|
|
|
node pointed to by the head element pointer, or, if that is null
|
|
|
|
|
(innerHTML case), to the current node. */
|
2013-07-16 11:56:14 +00:00
|
|
|
if ($this->head_pointer !== null) {
|
2008-06-25 01:10:51 +00:00
|
|
|
$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;
|
|
|
|
|
|
2013-07-16 11:56:14 +00:00
|
|
|
/* A start tag with the tag name "style" */
|
|
|
|
|
} elseif ($token['type'] === HTML5::STARTTAG && $token['name'] === 'style') {
|
2008-06-25 01:10:51 +00:00
|
|
|
/* Create an element for the token and append the new element to the
|
|
|
|
|
node pointed to by the head element pointer, or, if that is null
|
|
|
|
|
(innerHTML case), to the current node. */
|
2013-07-16 11:56:14 +00:00
|
|
|
if ($this->head_pointer !== null) {
|
2008-06-25 01:10:51 +00:00
|
|
|
$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;
|
|
|
|
|
|
2013-07-16 11:56:14 +00:00
|
|
|
/* A start tag with the tag name "script" */
|
|
|
|
|
} elseif ($token['type'] === HTML5::STARTTAG && $token['name'] === 'script') {
|
2008-06-25 01:10:51 +00:00
|
|
|
/* 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;
|
|
|
|
|
|
2013-07-16 11:56:14 +00:00
|
|
|
/* A start tag with the tag name "base", "link", or "meta" */
|
|
|
|
|
} elseif ($token['type'] === HTML5::STARTTAG && in_array(
|
|
|
|
|
$token['name'],
|
|
|
|
|
array('base', 'link', 'meta')
|
|
|
|
|
)
|
|
|
|
|
) {
|
2008-06-25 01:10:51 +00:00
|
|
|
/* Create an element for the token and append the new element to the
|
|
|
|
|
node pointed to by the head element pointer, or, if that is null
|
|
|
|
|
(innerHTML case), to the current node. */
|
2013-07-16 11:56:14 +00:00
|
|
|
if ($this->head_pointer !== null) {
|
2008-06-25 01:10:51 +00:00
|
|
|
$element = $this->insertElement($token, false);
|
|
|
|
|
$this->head_pointer->appendChild($element);
|
|
|
|
|
array_pop($this->stack);
|
|
|
|
|
|
|
|
|
|
} else {
|
|
|
|
|
$this->insertElement($token);
|
|
|
|
|
}
|
|
|
|
|
|
2013-07-16 11:56:14 +00:00
|
|
|
/* An end tag with the tag name "head" */
|
|
|
|
|
} elseif ($token['type'] === HTML5::ENDTAG && $token['name'] === 'head') {
|
2008-06-25 01:10:51 +00:00
|
|
|
/* If the current node is a head element, pop the current node off
|
|
|
|
|
the stack of open elements. */
|
2013-07-16 11:56:14 +00:00
|
|
|
if ($this->head_pointer->isSameNode(end($this->stack))) {
|
2008-06-25 01:10:51 +00:00
|
|
|
array_pop($this->stack);
|
|
|
|
|
|
2013-07-16 11:56:14 +00:00
|
|
|
/* Otherwise, this is a parse error. */
|
2008-06-25 01:10:51 +00:00
|
|
|
} else {
|
|
|
|
|
// k
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
/* Change the insertion mode to "after head". */
|
|
|
|
|
$this->mode = self::AFTER_HEAD;
|
|
|
|
|
|
2013-07-16 11:56:14 +00:00
|
|
|
/* A start tag with the tag name "head" or an end tag except "html". */
|
|
|
|
|
} elseif (($token['type'] === HTML5::STARTTAG && $token['name'] === 'head') ||
|
|
|
|
|
($token['type'] === HTML5::ENDTAG && $token['name'] !== 'html')
|
|
|
|
|
) {
|
2008-06-25 01:10:51 +00:00
|
|
|
// Parse error. Ignore the token.
|
|
|
|
|
|
2013-07-16 11:56:14 +00:00
|
|
|
/* Anything else */
|
2008-06-25 01:10:51 +00:00
|
|
|
} else {
|
|
|
|
|
/* If the current node is a head element, act as if an end tag
|
|
|
|
|
token with the tag name "head" had been seen. */
|
2013-07-16 11:56:14 +00:00
|
|
|
if ($this->head_pointer->isSameNode(end($this->stack))) {
|
|
|
|
|
$this->inHead(
|
|
|
|
|
array(
|
|
|
|
|
'name' => 'head',
|
|
|
|
|
'type' => HTML5::ENDTAG
|
|
|
|
|
)
|
|
|
|
|
);
|
2008-06-25 01:10:51 +00:00
|
|
|
|
2013-07-16 11:56:14 +00:00
|
|
|
/* Otherwise, change the insertion mode to "after head". */
|
2008-06-25 01:10:51 +00:00
|
|
|
} else {
|
|
|
|
|
$this->mode = self::AFTER_HEAD;
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
/* Then, reprocess the current token. */
|
|
|
|
|
return $this->afterHead($token);
|
|
|
|
|
}
|
|
|
|
|
}
|
|
|
|
|
|
2013-07-16 11:56:14 +00:00
|
|
|
private function afterHead($token)
|
|
|
|
|
{
|
2008-06-25 01:10:51 +00:00
|
|
|
/* Handle the token as follows: */
|
|
|
|
|
|
|
|
|
|
/* A character token that is one of one of U+0009 CHARACTER TABULATION,
|
|
|
|
|
U+000A LINE FEED (LF), U+000B LINE TABULATION, U+000C FORM FEED (FF),
|
|
|
|
|
or U+0020 SPACE */
|
2013-07-16 11:56:14 +00:00
|
|
|
if ($token['type'] === HTML5::CHARACTR &&
|
|
|
|
|
preg_match('/^[\t\n\x0b\x0c ]+$/', $token['data'])
|
|
|
|
|
) {
|
2008-06-25 01:10:51 +00:00
|
|
|
/* Append the character to the current node. */
|
|
|
|
|
$this->insertText($token['data']);
|
|
|
|
|
|
2013-07-16 11:56:14 +00:00
|
|
|
/* A comment token */
|
|
|
|
|
} elseif ($token['type'] === HTML5::COMMENT) {
|
2008-06-25 01:10:51 +00:00
|
|
|
/* 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']);
|
|
|
|
|
|
2013-07-16 11:56:14 +00:00
|
|
|
/* A start tag token with the tag name "body" */
|
|
|
|
|
} elseif ($token['type'] === HTML5::STARTTAG && $token['name'] === 'body') {
|
2008-06-25 01:10:51 +00:00
|
|
|
/* Insert a body element for the token. */
|
|
|
|
|
$this->insertElement($token);
|
|
|
|
|
|
|
|
|
|
/* Change the insertion mode to "in body". */
|
|
|
|
|
$this->mode = self::IN_BODY;
|
|
|
|
|
|
2013-07-16 11:56:14 +00:00
|
|
|
/* A start tag token with the tag name "frameset" */
|
|
|
|
|
} elseif ($token['type'] === HTML5::STARTTAG && $token['name'] === 'frameset') {
|
2008-06-25 01:10:51 +00:00
|
|
|
/* Insert a frameset element for the token. */
|
|
|
|
|
$this->insertElement($token);
|
|
|
|
|
|
|
|
|
|
/* Change the insertion mode to "in frameset". */
|
|
|
|
|
$this->mode = self::IN_FRAME;
|
|
|
|
|
|
2013-07-16 11:56:14 +00:00
|
|
|
/* A start tag token whose tag name is one of: "base", "link", "meta",
|
|
|
|
|
"script", "style", "title" */
|
|
|
|
|
} elseif ($token['type'] === HTML5::STARTTAG && in_array(
|
|
|
|
|
$token['name'],
|
|
|
|
|
array('base', 'link', 'meta', 'script', 'style', 'title')
|
|
|
|
|
)
|
|
|
|
|
) {
|
2008-06-25 01:10:51 +00:00
|
|
|
/* Parse error. Switch the insertion mode back to "in head" and
|
|
|
|
|
reprocess the token. */
|
|
|
|
|
$this->mode = self::IN_HEAD;
|
|
|
|
|
return $this->inHead($token);
|
|
|
|
|
|
2013-07-16 11:56:14 +00:00
|
|
|
/* Anything else */
|
2008-06-25 01:10:51 +00:00
|
|
|
} 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. */
|
2013-07-16 11:56:14 +00:00
|
|
|
$this->afterHead(
|
|
|
|
|
array(
|
|
|
|
|
'name' => 'body',
|
|
|
|
|
'type' => HTML5::STARTTAG,
|
|
|
|
|
'attr' => array()
|
|
|
|
|
)
|
|
|
|
|
);
|
2008-06-25 01:10:51 +00:00
|
|
|
|
|
|
|
|
return $this->inBody($token);
|
|
|
|
|
}
|
|
|
|
|
}
|
|
|
|
|
|
2013-07-16 11:56:14 +00:00
|
|
|
private function inBody($token)
|
|
|
|
|
{
|
2008-06-25 01:10:51 +00:00
|
|
|
/* Handle the token as follows: */
|
|
|
|
|
|
2013-07-16 11:56:14 +00:00
|
|
|
switch ($token['type']) {
|
2008-06-25 01:10:51 +00:00
|
|
|
/* 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']);
|
2013-07-16 11:56:14 +00:00
|
|
|
break;
|
2008-06-25 01:10:51 +00:00
|
|
|
|
|
|
|
|
/* 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']);
|
2013-07-16 11:56:14 +00:00
|
|
|
break;
|
2008-06-25 01:10:51 +00:00
|
|
|
|
|
|
|
|
case HTML5::STARTTAG:
|
2013-07-16 11:56:14 +00:00
|
|
|
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;
|
2008-06-25 01:10:51 +00:00
|
|
|
|
2013-07-16 11:56:14 +00:00
|
|
|
/* 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;
|
2008-06-25 01:10:51 +00:00
|
|
|
|
2013-07-16 11:56:14 +00:00
|
|
|
/* 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'], $attr['value']);
|
|
|
|
|
}
|
2008-06-25 01:10:51 +00:00
|
|
|
}
|
|
|
|
|
}
|
2013-07-16 11:56:14 +00:00
|
|
|
break;
|
2008-06-25 01:10:51 +00:00
|
|
|
|
2013-07-16 11:56:14 +00:00
|
|
|
/* A start tag whose tag name is one of: "address",
|
|
|
|
|
"blockquote", "center", "dir", "div", "dl", "fieldset",
|
|
|
|
|
"listing", "menu", "ol", "p", "ul" */
|
|
|
|
|
case 'address':
|
|
|
|
|
case 'blockquote':
|
|
|
|
|
case 'center':
|
|
|
|
|
case 'dir':
|
|
|
|
|
case 'div':
|
|
|
|
|
case 'dl':
|
|
|
|
|
case 'fieldset':
|
|
|
|
|
case 'listing':
|
|
|
|
|
case 'menu':
|
|
|
|
|
case 'ol':
|
|
|
|
|
case 'p':
|
|
|
|
|
case 'ul':
|
|
|
|
|
/* If the stack of open elements has a p element in scope,
|
|
|
|
|
then act as if an end tag with the tag name p had been
|
|
|
|
|
seen. */
|
|
|
|
|
if ($this->elementInScope('p')) {
|
|
|
|
|
$this->emitToken(
|
|
|
|
|
array(
|
|
|
|
|
'name' => 'p',
|
|
|
|
|
'type' => HTML5::ENDTAG
|
|
|
|
|
)
|
|
|
|
|
);
|
2008-06-25 01:10:51 +00:00
|
|
|
}
|
|
|
|
|
|
2013-07-16 11:56:14 +00:00
|
|
|
/* Insert an HTML element for the token. */
|
|
|
|
|
$this->insertElement($token);
|
|
|
|
|
break;
|
2008-06-25 01:10:51 +00:00
|
|
|
|
2013-07-16 11:56:14 +00:00
|
|
|
/* 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 ($this->form_pointer !== null) {
|
|
|
|
|
// Ignore.
|
2008-06-25 01:10:51 +00:00
|
|
|
|
2013-07-16 11:56:14 +00:00
|
|
|
/* Otherwise: */
|
|
|
|
|
} else {
|
|
|
|
|
/* If the stack of open elements has a p element in
|
|
|
|
|
scope, then act as if an end tag with the tag name p
|
|
|
|
|
had been seen. */
|
|
|
|
|
if ($this->elementInScope('p')) {
|
|
|
|
|
$this->emitToken(
|
|
|
|
|
array(
|
|
|
|
|
'name' => 'p',
|
|
|
|
|
'type' => HTML5::ENDTAG
|
|
|
|
|
)
|
|
|
|
|
);
|
2008-06-25 01:10:51 +00:00
|
|
|
}
|
|
|
|
|
|
2013-07-16 11:56:14 +00:00
|
|
|
/* 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 = $element;
|
2008-06-25 01:10:51 +00:00
|
|
|
}
|
2013-07-16 11:56:14 +00:00
|
|
|
break;
|
2008-06-25 01:10:51 +00:00
|
|
|
|
2013-07-16 11:56:14 +00:00
|
|
|
/* A start tag whose tag name is "li", "dd" or "dt" */
|
|
|
|
|
case 'li':
|
|
|
|
|
case 'dd':
|
|
|
|
|
case 'dt':
|
|
|
|
|
/* If the stack of open elements has a p element in scope,
|
|
|
|
|
then act as if an end tag with the tag name p had been
|
|
|
|
|
seen. */
|
|
|
|
|
if ($this->elementInScope('p')) {
|
|
|
|
|
$this->emitToken(
|
|
|
|
|
array(
|
|
|
|
|
'name' => 'p',
|
|
|
|
|
'type' => HTML5::ENDTAG
|
|
|
|
|
)
|
|
|
|
|
);
|
2008-06-25 01:10:51 +00:00
|
|
|
}
|
|
|
|
|
|
2013-07-16 11:56:14 +00:00
|
|
|
$stack_length = count($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);
|
|
|
|
|
}
|
2008-06-25 01:10:51 +00:00
|
|
|
|
2013-07-16 11:56:14 +00:00
|
|
|
break;
|
|
|
|
|
}
|
2008-06-25 01:10:51 +00:00
|
|
|
|
2013-07-16 11:56:14 +00:00
|
|
|
/* 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;
|
|
|
|
|
}
|
|
|
|
|
}
|
2008-06-25 01:10:51 +00:00
|
|
|
|
2013-07-16 11:56:14 +00:00
|
|
|
/* Finally, insert an HTML element with the same tag
|
|
|
|
|
name as the token's. */
|
|
|
|
|
$this->insertElement($token);
|
|
|
|
|
break;
|
2008-06-25 01:10:51 +00:00
|
|
|
|
2013-07-16 11:56:14 +00:00
|
|
|
/* 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
|
|
|
|
|
)
|
|
|
|
|
);
|
|
|
|
|
}
|
2008-06-25 01:10:51 +00:00
|
|
|
|
2013-07-16 11:56:14 +00:00
|
|
|
/* Insert an HTML element for the token. */
|
|
|
|
|
$this->insertElement($token);
|
2008-06-25 01:10:51 +00:00
|
|
|
|
2013-07-16 11:56:14 +00:00
|
|
|
return HTML5::PLAINTEXT;
|
|
|
|
|
break;
|
2008-06-25 01:10:51 +00:00
|
|
|
|
2013-07-16 11:56:14 +00:00
|
|
|
/* 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')) {
|
|
|
|
|
$this->emitToken(
|
|
|
|
|
array(
|
|
|
|
|
'name' => 'p',
|
|
|
|
|
'type' => HTML5::ENDTAG
|
|
|
|
|
)
|
|
|
|
|
);
|
2008-06-25 01:10:51 +00:00
|
|
|
}
|
|
|
|
|
|
2013-07-16 11:56:14 +00:00
|
|
|
/* If the stack of open elements has in scope an element whose
|
|
|
|
|
tag name is one of "h1", "h2", "h3", "h4", "h5", or "h6", then
|
|
|
|
|
this is a parse error; pop elements from the stack until an
|
|
|
|
|
element with one of those tag names has been popped from the
|
|
|
|
|
stack. */
|
|
|
|
|
while ($this->elementInScope(array('h1', 'h2', 'h3', 'h4', 'h5', 'h6'))) {
|
|
|
|
|
array_pop($this->stack);
|
|
|
|
|
}
|
2008-06-25 01:10:51 +00:00
|
|
|
|
2013-07-16 11:56:14 +00:00
|
|
|
/* Insert an HTML element for the token. */
|
|
|
|
|
$this->insertElement($token);
|
|
|
|
|
break;
|
2008-06-25 01:10:51 +00:00
|
|
|
|
2013-07-16 11:56:14 +00:00
|
|
|
/* 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[$n] === self::MARKER) {
|
|
|
|
|
break;
|
2008-06-25 01:10:51 +00:00
|
|
|
|
2013-07-16 11:56:14 +00:00
|
|
|
} elseif ($this->a_formatting[$n]->nodeName === 'a') {
|
|
|
|
|
$this->emitToken(
|
|
|
|
|
array(
|
|
|
|
|
'name' => 'a',
|
|
|
|
|
'type' => HTML5::ENDTAG
|
|
|
|
|
)
|
|
|
|
|
);
|
|
|
|
|
break;
|
|
|
|
|
}
|
|
|
|
|
}
|
2008-06-25 01:10:51 +00:00
|
|
|
|
2013-07-16 11:56:14 +00:00
|
|
|
/* Reconstruct the active formatting elements, if any. */
|
|
|
|
|
$this->reconstructActiveFormattingElements();
|
2008-06-25 01:10:51 +00:00
|
|
|
|
2013-07-16 11:56:14 +00:00
|
|
|
/* Insert an HTML element for the token. */
|
|
|
|
|
$el = $this->insertElement($token);
|
2008-06-25 01:10:51 +00:00
|
|
|
|
2013-07-16 11:56:14 +00:00
|
|
|
/* Add that element to the list of active formatting
|
|
|
|
|
elements. */
|
|
|
|
|
$this->a_formatting[] = $el;
|
|
|
|
|
break;
|
2008-06-25 01:10:51 +00:00
|
|
|
|
2013-07-16 11:56:14 +00:00
|
|
|
/* 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[] = $el;
|
|
|
|
|
break;
|
2008-06-25 01:10:51 +00:00
|
|
|
|
2013-07-16 11:56:14 +00:00
|
|
|
/* A start tag token whose tag name is "button" */
|
|
|
|
|
case 'button':
|
|
|
|
|
/* If the stack of open elements has a button element in scope,
|
|
|
|
|
then this is a parse error; act as if an end tag with the tag
|
|
|
|
|
name "button" had been seen, then reprocess the token. (We don't
|
|
|
|
|
do that. Unnecessary.) */
|
|
|
|
|
if ($this->elementInScope('button')) {
|
|
|
|
|
$this->inBody(
|
|
|
|
|
array(
|
|
|
|
|
'name' => 'button',
|
|
|
|
|
'type' => HTML5::ENDTAG
|
|
|
|
|
)
|
|
|
|
|
);
|
|
|
|
|
}
|
2008-06-25 01:10:51 +00:00
|
|
|
|
2013-07-16 11:56:14 +00:00
|
|
|
/* Reconstruct the active formatting elements, if any. */
|
|
|
|
|
$this->reconstructActiveFormattingElements();
|
2008-06-25 01:10:51 +00:00
|
|
|
|
2013-07-16 11:56:14 +00:00
|
|
|
/* Insert an HTML element for the token. */
|
|
|
|
|
$this->insertElement($token);
|
2008-06-25 01:10:51 +00:00
|
|
|
|
2013-07-16 11:56:14 +00:00
|
|
|
/* Insert a marker at the end of the list of active
|
|
|
|
|
formatting elements. */
|
|
|
|
|
$this->a_formatting[] = self::MARKER;
|
|
|
|
|
break;
|
2008-06-25 01:10:51 +00:00
|
|
|
|
2013-07-16 11:56:14 +00:00
|
|
|
/* 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();
|
2008-06-25 01:10:51 +00:00
|
|
|
|
2013-07-16 11:56:14 +00:00
|
|
|
/* Insert an HTML element for the token. */
|
|
|
|
|
$this->insertElement($token);
|
2008-06-25 01:10:51 +00:00
|
|
|
|
2013-07-16 11:56:14 +00:00
|
|
|
/* Insert a marker at the end of the list of active
|
|
|
|
|
formatting elements. */
|
|
|
|
|
$this->a_formatting[] = self::MARKER;
|
|
|
|
|
break;
|
2008-06-25 01:10:51 +00:00
|
|
|
|
2013-07-16 11:56:14 +00:00
|
|
|
/* A start tag token whose tag name is "xmp" */
|
|
|
|
|
case 'xmp':
|
|
|
|
|
/* Reconstruct the active formatting elements, if any. */
|
|
|
|
|
$this->reconstructActiveFormattingElements();
|
2008-06-25 01:10:51 +00:00
|
|
|
|
2013-07-16 11:56:14 +00:00
|
|
|
/* Insert an HTML element for the token. */
|
|
|
|
|
$this->insertElement($token);
|
2008-06-25 01:10:51 +00:00
|
|
|
|
2013-07-16 11:56:14 +00:00
|
|
|
/* Switch the content model flag to the CDATA state. */
|
|
|
|
|
return HTML5::CDATA;
|
|
|
|
|
break;
|
2008-06-25 01:10:51 +00:00
|
|
|
|
2013-07-16 11:56:14 +00:00
|
|
|
/* 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
|
|
|
|
|
)
|
|
|
|
|
);
|
|
|
|
|
}
|
2008-06-25 01:10:51 +00:00
|
|
|
|
2013-07-16 11:56:14 +00:00
|
|
|
/* Insert an HTML element for the token. */
|
|
|
|
|
$this->insertElement($token);
|
2008-06-25 01:10:51 +00:00
|
|
|
|
2013-07-16 11:56:14 +00:00
|
|
|
/* Change the insertion mode to "in table". */
|
|
|
|
|
$this->mode = self::IN_TABLE;
|
|
|
|
|
break;
|
2008-06-25 01:10:51 +00:00
|
|
|
|
2013-07-16 11:56:14 +00:00
|
|
|
/* 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($this->stack);
|
|
|
|
|
break;
|
2008-06-25 01:10:51 +00:00
|
|
|
|
2013-07-16 11:56:14 +00:00
|
|
|
/* A start tag whose tag name is "hr" */
|
|
|
|
|
case 'hr':
|
|
|
|
|
/* If the stack of open elements has a p element in scope,
|
|
|
|
|
then act as if an end tag with the tag name p had been seen. */
|
|
|
|
|
if ($this->elementInScope('p')) {
|
|
|
|
|
$this->emitToken(
|
|
|
|
|
array(
|
|
|
|
|
'name' => 'p',
|
|
|
|
|
'type' => HTML5::ENDTAG
|
|
|
|
|
)
|
|
|
|
|
);
|
|
|
|
|
}
|
2008-06-25 01:10:51 +00:00
|
|
|
|
2013-07-16 11:56:14 +00:00
|
|
|
/* Insert an HTML element for the token. */
|
|
|
|
|
$this->insertElement($token);
|
2008-06-25 01:10:51 +00:00
|
|
|
|
2013-07-16 11:56:14 +00:00
|
|
|
/* Immediately pop the current node off the stack of open elements. */
|
|
|
|
|
array_pop($this->stack);
|
|
|
|
|
break;
|
2008-06-25 01:10:51 +00:00
|
|
|
|
2013-07-16 11:56:14 +00:00
|
|
|
/* 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;
|
2008-06-25 01:10:51 +00:00
|
|
|
|
2013-07-16 11:56:14 +00:00
|
|
|
/* A start tag whose tag name is "input" */
|
|
|
|
|
case 'input':
|
|
|
|
|
/* Reconstruct the active formatting elements, if any. */
|
|
|
|
|
$this->reconstructActiveFormattingElements();
|
2008-06-25 01:10:51 +00:00
|
|
|
|
2013-07-16 11:56:14 +00:00
|
|
|
/* Insert an input element for the token. */
|
|
|
|
|
$element = $this->insertElement($token, false);
|
2008-06-25 01:10:51 +00:00
|
|
|
|
2013-07-16 11:56:14 +00:00
|
|
|
/* 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);
|
2008-06-25 01:10:51 +00:00
|
|
|
|
2013-07-16 11:56:14 +00:00
|
|
|
/* Pop that input element off the stack of open elements. */
|
|
|
|
|
array_pop($this->stack);
|
|
|
|
|
break;
|
2008-06-25 01:10:51 +00:00
|
|
|
|
2013-07-16 11:56:14 +00:00
|
|
|
/* A start tag whose tag name is "isindex" */
|
|
|
|
|
case 'isindex':
|
|
|
|
|
/* Parse error. */
|
|
|
|
|
// w/e
|
2008-06-25 01:10:51 +00:00
|
|
|
|
2013-07-16 11:56:14 +00:00
|
|
|
/* If the form element pointer is not null,
|
|
|
|
|
then ignore the token. */
|
|
|
|
|
if ($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;
|
2008-06-25 01:10:51 +00:00
|
|
|
|
2013-07-16 11:56:14 +00:00
|
|
|
/* A start tag whose tag name is "textarea" */
|
|
|
|
|
case 'textarea':
|
|
|
|
|
$this->insertElement($token);
|
2008-06-25 01:10:51 +00:00
|
|
|
|
2013-07-16 11:56:14 +00:00
|
|
|
/* Switch the tokeniser's content model flag to the
|
|
|
|
|
RCDATA state. */
|
|
|
|
|
return HTML5::RCDATA;
|
|
|
|
|
break;
|
2008-06-25 01:10:51 +00:00
|
|
|
|
2013-07-16 11:56:14 +00:00
|
|
|
/* A start tag whose tag name is one of: "iframe", "noembed",
|
|
|
|
|
"noframes" */
|
|
|
|
|
case 'iframe':
|
|
|
|
|
case 'noembed':
|
|
|
|
|
case 'noframes':
|
|
|
|
|
$this->insertElement($token);
|
2008-06-25 01:10:51 +00:00
|
|
|
|
2013-07-16 11:56:14 +00:00
|
|
|
/* Switch the tokeniser's content model flag to the CDATA state. */
|
|
|
|
|
return HTML5::CDATA;
|
|
|
|
|
break;
|
2008-06-25 01:10:51 +00:00
|
|
|
|
2013-07-16 11:56:14 +00:00
|
|
|
/* A start tag whose tag name is "select" */
|
|
|
|
|
case 'select':
|
|
|
|
|
/* Reconstruct the active formatting elements, if any. */
|
|
|
|
|
$this->reconstructActiveFormattingElements();
|
2008-06-25 01:10:51 +00:00
|
|
|
|
2013-07-16 11:56:14 +00:00
|
|
|
/* Insert an HTML element for the token. */
|
|
|
|
|
$this->insertElement($token);
|
2008-06-25 01:10:51 +00:00
|
|
|
|
2013-07-16 11:56:14 +00:00
|
|
|
/* Change the insertion mode to "in select". */
|
|
|
|
|
$this->mode = self::IN_SELECT;
|
|
|
|
|
break;
|
2008-06-25 01:10:51 +00:00
|
|
|
|
2013-07-16 11:56:14 +00:00
|
|
|
/* 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;
|
2008-06-25 01:10:51 +00:00
|
|
|
|
2013-07-16 11:56:14 +00:00
|
|
|
/* 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();
|
2008-06-25 01:10:51 +00:00
|
|
|
|
2013-07-16 11:56:14 +00:00
|
|
|
$this->insertElement($token, true, true);
|
|
|
|
|
break;
|
|
|
|
|
}
|
2008-06-25 01:10:51 +00:00
|
|
|
break;
|
|
|
|
|
|
|
|
|
|
case HTML5::ENDTAG:
|
2013-07-16 11:56:14 +00:00
|
|
|
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.
|
|
|
|
|
}
|
2008-06-25 01:10:51 +00:00
|
|
|
|
2013-07-16 11:56:14 +00:00
|
|
|
/* Change the insertion mode to "after body". */
|
|
|
|
|
$this->mode = self::AFTER_BODY;
|
|
|
|
|
break;
|
2008-06-25 01:10:51 +00:00
|
|
|
|
2013-07-16 11:56:14 +00:00
|
|
|
/* 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
|
|
|
|
|
)
|
|
|
|
|
);
|
2008-06-25 01:10:51 +00:00
|
|
|
|
2013-07-16 11:56:14 +00:00
|
|
|
return $this->afterBody($token);
|
|
|
|
|
break;
|
2008-06-25 01:10:51 +00:00
|
|
|
|
2013-07-16 11:56:14 +00:00
|
|
|
/* 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'])) {
|
|
|
|
|
$this->generateImpliedEndTags();
|
2008-06-25 01:10:51 +00:00
|
|
|
|
2013-07-16 11:56:14 +00:00
|
|
|
/* Now, if the current node is not an element with
|
|
|
|
|
the same tag name as that of the token, then this
|
|
|
|
|
is a parse error. */
|
|
|
|
|
// w/e
|
|
|
|
|
|
|
|
|
|
/* If the stack of open elements has an element in
|
|
|
|
|
scope with the same tag name as that of the token,
|
|
|
|
|
then pop elements from this stack until an element
|
|
|
|
|
with that tag name has been popped from the stack. */
|
|
|
|
|
for ($n = count($this->stack) - 1; $n >= 0; $n--) {
|
|
|
|
|
if ($this->stack[$n]->nodeName === $token['name']) {
|
|
|
|
|
$n = -1;
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
array_pop($this->stack);
|
2008-06-25 01:10:51 +00:00
|
|
|
}
|
2013-07-16 11:56:14 +00:00
|
|
|
}
|
|
|
|
|
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'])) {
|
|
|
|
|
$this->generateImpliedEndTags();
|
2008-06-25 01:10:51 +00:00
|
|
|
|
|
|
|
|
}
|
|
|
|
|
|
2013-07-16 11:56:14 +00:00
|
|
|
if (end($this->stack)->nodeName !== $token['name']) {
|
|
|
|
|
/* Now, if the current node is not an element with the
|
|
|
|
|
same tag name as that of the token, then this is a parse
|
|
|
|
|
error. */
|
|
|
|
|
// w/e
|
2008-06-25 01:10:51 +00:00
|
|
|
|
2013-07-16 11:56:14 +00:00
|
|
|
} else {
|
|
|
|
|
/* Otherwise, if the current node is an element with
|
|
|
|
|
the same tag name as that of the token pop that element
|
|
|
|
|
from the stack. */
|
|
|
|
|
array_pop($this->stack);
|
|
|
|
|
}
|
2008-06-25 01:10:51 +00:00
|
|
|
|
2013-07-16 11:56:14 +00:00
|
|
|
/* In any case, set the form element pointer to null. */
|
|
|
|
|
$this->form_pointer = null;
|
|
|
|
|
break;
|
2008-06-25 01:10:51 +00:00
|
|
|
|
2013-07-16 11:56:14 +00:00
|
|
|
/* An end tag whose tag name is "p" */
|
|
|
|
|
case 'p':
|
|
|
|
|
/* If the stack of open elements has a p element in scope,
|
|
|
|
|
then generate implied end tags, except for p elements. */
|
|
|
|
|
if ($this->elementInScope('p')) {
|
|
|
|
|
$this->generateImpliedEndTags(array('p'));
|
2008-06-25 01:10:51 +00:00
|
|
|
|
2013-07-16 11:56:14 +00:00
|
|
|
/* If the current node is not a p element, then this is
|
|
|
|
|
a parse error. */
|
|
|
|
|
// k
|
2008-06-25 01:10:51 +00:00
|
|
|
|
2013-07-16 11:56:14 +00:00
|
|
|
/* If the stack of open elements has a p element in
|
|
|
|
|
scope, then pop elements from this stack until the stack
|
|
|
|
|
no longer has a p element in scope. */
|
|
|
|
|
for ($n = count($this->stack) - 1; $n >= 0; $n--) {
|
|
|
|
|
if ($this->elementInScope('p')) {
|
|
|
|
|
array_pop($this->stack);
|
2008-06-25 01:10:51 +00:00
|
|
|
|
2013-07-16 11:56:14 +00:00
|
|
|
} else {
|
|
|
|
|
break;
|
|
|
|
|
}
|
2008-06-25 01:10:51 +00:00
|
|
|
}
|
|
|
|
|
}
|
2013-07-16 11:56:14 +00:00
|
|
|
break;
|
2008-06-25 01:10:51 +00:00
|
|
|
|
2013-07-16 11:56:14 +00:00
|
|
|
/* An end tag whose tag name is "dd", "dt", or "li" */
|
|
|
|
|
case 'dd':
|
|
|
|
|
case 'dt':
|
|
|
|
|
case 'li':
|
2008-06-25 01:10:51 +00:00
|
|
|
/* If the stack of open elements has an element in scope
|
|
|
|
|
whose tag name matches the tag name of the token, then
|
2013-07-16 11:56:14 +00:00
|
|
|
generate implied end tags, except for elements with the
|
|
|
|
|
same tag name as the token. */
|
|
|
|
|
if ($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']) {
|
|
|
|
|
$n = -1;
|
|
|
|
|
}
|
2008-06-25 01:10:51 +00:00
|
|
|
|
2013-07-16 11:56:14 +00:00
|
|
|
array_pop($this->stack);
|
|
|
|
|
}
|
2008-06-25 01:10:51 +00:00
|
|
|
}
|
2013-07-16 11:56:14 +00:00
|
|
|
break;
|
2008-06-25 01:10:51 +00:00
|
|
|
|
2013-07-16 11:56:14 +00:00
|
|
|
/* 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)) {
|
|
|
|
|
$this->generateImpliedEndTags();
|
2008-06-25 01:10:51 +00:00
|
|
|
|
2013-07-16 11:56:14 +00:00
|
|
|
/* Now, if the current node is not an element with the same
|
|
|
|
|
tag name as that of the token, then this is a parse error. */
|
|
|
|
|
// w/e
|
2008-06-25 01:10:51 +00:00
|
|
|
|
2013-07-16 11:56:14 +00:00
|
|
|
/* If the stack of open elements has in scope an element
|
|
|
|
|
whose tag name is one of "h1", "h2", "h3", "h4", "h5", or
|
|
|
|
|
"h6", then pop elements from the stack until an element
|
|
|
|
|
with one of those tag names has been popped from the stack. */
|
|
|
|
|
while ($this->elementInScope($elements)) {
|
|
|
|
|
array_pop($this->stack);
|
|
|
|
|
}
|
2008-06-25 01:10:51 +00:00
|
|
|
}
|
2013-07-16 11:56:14 +00:00
|
|
|
break;
|
2008-06-25 01:10:51 +00:00
|
|
|
|
2013-07-16 11:56:14 +00:00
|
|
|
/* 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($token['name']))
|
|
|
|
|
) {
|
2008-06-25 01:10:51 +00:00
|
|
|
break;
|
|
|
|
|
|
2013-07-16 11:56:14 +00:00
|
|
|
/* Otherwise, if there is such a node, but that node
|
|
|
|
|
is not in the stack of open elements, then this is a
|
|
|
|
|
parse error; remove the element from the list, and
|
|
|
|
|
abort these steps. */
|
|
|
|
|
} elseif (isset($formatting_element) && !$in_stack) {
|
|
|
|
|
unset($this->a_formatting[$fe_af_pos]);
|
|
|
|
|
$this->a_formatting = array_merge($this->a_formatting);
|
2008-06-25 01:10:51 +00:00
|
|
|
break;
|
|
|
|
|
}
|
|
|
|
|
|
2013-07-16 11:56:14 +00:00
|
|
|
/* 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);
|
2008-06-25 01:10:51 +00:00
|
|
|
|
2013-07-16 11:56:14 +00:00
|
|
|
for ($s = $fe_s_pos + 1; $s < $length; $s++) {
|
|
|
|
|
$category = $this->getElementCategory($this->stack[$s]->nodeName);
|
2008-06-25 01:10:51 +00:00
|
|
|
|
2013-07-16 11:56:14 +00:00
|
|
|
if ($category !== self::PHRASING && $category !== self::FORMATTING) {
|
|
|
|
|
$furthest_block = $this->stack[$s];
|
|
|
|
|
}
|
2008-06-25 01:10:51 +00:00
|
|
|
}
|
|
|
|
|
|
2013-07-16 11:56:14 +00:00
|
|
|
/* 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);
|
|
|
|
|
}
|
2008-06-25 01:10:51 +00:00
|
|
|
|
2013-07-16 11:56:14 +00:00
|
|
|
unset($this->a_formatting[$fe_af_pos]);
|
|
|
|
|
$this->a_formatting = array_merge($this->a_formatting);
|
|
|
|
|
break;
|
|
|
|
|
}
|
2008-06-25 01:10:51 +00:00
|
|
|
|
2013-07-16 11:56:14 +00:00
|
|
|
/* 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];
|
2008-06-25 01:10:51 +00:00
|
|
|
|
2013-07-16 11:56:14 +00:00
|
|
|
/* 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);
|
|
|
|
|
}
|
2008-06-25 01:10:51 +00:00
|
|
|
|
2013-07-16 11:56:14 +00:00
|
|
|
/* 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;
|
|
|
|
|
}
|
|
|
|
|
}
|
2008-06-25 01:10:51 +00:00
|
|
|
|
2013-07-16 11:56:14 +00:00
|
|
|
/* 7.3 Otherwise, if node is the formatting
|
|
|
|
|
element, then go to the next step in the overall
|
|
|
|
|
algorithm. */
|
|
|
|
|
if ($node === $formatting_element) {
|
2008-06-25 01:10:51 +00:00
|
|
|
break;
|
2013-07-16 11:56:14 +00:00
|
|
|
|
|
|
|
|
/* 7.4 Otherwise, if last node is the furthest
|
|
|
|
|
block, then move the aforementioned bookmark to
|
|
|
|
|
be immediately after the node in the list of
|
|
|
|
|
active formatting elements. */
|
|
|
|
|
} elseif ($last_node === $furthest_block) {
|
|
|
|
|
$bookmark = array_search($node, $this->a_formatting, true) + 1;
|
2008-06-25 01:10:51 +00:00
|
|
|
}
|
|
|
|
|
|
2013-07-16 11:56:14 +00:00
|
|
|
/* 7.5 If node has any children, perform a
|
|
|
|
|
shallow clone of node, replace the entry for
|
|
|
|
|
node in the list of active formatting elements
|
|
|
|
|
with an entry for the clone, replace the entry
|
|
|
|
|
for node in the stack of open elements with an
|
|
|
|
|
entry for the clone, and let node be the clone. */
|
|
|
|
|
if ($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 = $clone;
|
|
|
|
|
}
|
2008-06-25 01:10:51 +00:00
|
|
|
|
2013-07-16 11:56:14 +00:00
|
|
|
/* 7.6 Insert last node into node, first removing
|
|
|
|
|
it from its previous parent node if any. */
|
|
|
|
|
if ($last_node->parentNode !== null) {
|
|
|
|
|
$last_node->parentNode->removeChild($last_node);
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
$node->appendChild($last_node);
|
2008-06-25 01:10:51 +00:00
|
|
|
|
2013-07-16 11:56:14 +00:00
|
|
|
/* 7.7 Let last node be node. */
|
|
|
|
|
$last_node = $node;
|
2008-06-25 01:10:51 +00:00
|
|
|
}
|
|
|
|
|
|
2013-07-16 11:56:14 +00:00
|
|
|
/* 8. Insert whatever last node ended up being in
|
|
|
|
|
the previous step into the common ancestor node,
|
|
|
|
|
first removing it from its previous parent node if
|
|
|
|
|
any. */
|
|
|
|
|
if ($last_node->parentNode !== null) {
|
2008-06-25 01:10:51 +00:00
|
|
|
$last_node->parentNode->removeChild($last_node);
|
|
|
|
|
}
|
|
|
|
|
|
2013-07-16 11:56:14 +00:00
|
|
|
$common_ancestor->appendChild($last_node);
|
2008-06-25 01:10:51 +00:00
|
|
|
|
2013-07-16 11:56:14 +00:00
|
|
|
/* 9. Perform a shallow clone of the formatting
|
|
|
|
|
element. */
|
|
|
|
|
$clone = $formatting_element->cloneNode();
|
2008-06-25 01:10:51 +00:00
|
|
|
|
2013-07-16 11:56:14 +00:00
|
|
|
/* 10. Take all of the child nodes of the furthest
|
|
|
|
|
block and append them to the clone created in the
|
|
|
|
|
last step. */
|
|
|
|
|
while ($furthest_block->hasChildNodes()) {
|
|
|
|
|
$child = $furthest_block->firstChild;
|
|
|
|
|
$furthest_block->removeChild($child);
|
|
|
|
|
$clone->appendChild($child);
|
|
|
|
|
}
|
2008-06-25 01:10:51 +00:00
|
|
|
|
2013-07-16 11:56:14 +00:00
|
|
|
/* 11. Append that clone to the furthest block. */
|
|
|
|
|
$furthest_block->appendChild($clone);
|
2008-06-25 01:10:51 +00:00
|
|
|
|
2013-07-16 11:56:14 +00:00
|
|
|
/* 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);
|
2008-06-25 01:10:51 +00:00
|
|
|
|
2013-07-16 11:56:14 +00:00
|
|
|
$af_part1 = array_slice($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, $furthest_block);
|
2008-06-25 01:10:51 +00:00
|
|
|
}
|
2013-07-16 11:56:14 +00:00
|
|
|
break;
|
2008-06-25 01:10:51 +00:00
|
|
|
|
2013-07-16 11:56:14 +00:00
|
|
|
/* An end tag token whose tag name is one of: "button",
|
|
|
|
|
"marquee", "object" */
|
|
|
|
|
case 'button':
|
|
|
|
|
case 'marquee':
|
|
|
|
|
case 'object':
|
|
|
|
|
/* If the stack of open elements has an element in scope whose
|
|
|
|
|
tag name matches the tag name of the token, then generate implied
|
|
|
|
|
tags. */
|
|
|
|
|
if ($this->elementInScope($token['name'])) {
|
|
|
|
|
$this->generateImpliedEndTags();
|
2008-06-25 01:10:51 +00:00
|
|
|
|
2013-07-16 11:56:14 +00:00
|
|
|
/* Now, if the current node is not an element with the same
|
|
|
|
|
tag name as the token, then this is a parse error. */
|
|
|
|
|
// k
|
2008-06-25 01:10:51 +00:00
|
|
|
|
2013-07-16 11:56:14 +00:00
|
|
|
/* Now, if the stack of open elements has an element in scope
|
|
|
|
|
whose tag name matches the tag name of the token, then pop
|
|
|
|
|
elements from the stack until that element has been popped from
|
|
|
|
|
the stack, and clear the list of active formatting elements up
|
|
|
|
|
to the last marker. */
|
|
|
|
|
for ($n = count($this->stack) - 1; $n >= 0; $n--) {
|
|
|
|
|
if ($this->stack[$n]->nodeName === $token['name']) {
|
|
|
|
|
$n = -1;
|
|
|
|
|
}
|
2008-06-25 01:10:51 +00:00
|
|
|
|
2013-07-16 11:56:14 +00:00
|
|
|
array_pop($this->stack);
|
|
|
|
|
}
|
2008-06-25 01:10:51 +00:00
|
|
|
|
2013-07-16 11:56:14 +00:00
|
|
|
$marker = end(array_keys($this->a_formatting, self::MARKER, true));
|
2008-06-25 01:10:51 +00:00
|
|
|
|
2013-07-16 11:56:14 +00:00
|
|
|
for ($n = count($this->a_formatting) - 1; $n > $marker; $n--) {
|
|
|
|
|
array_pop($this->a_formatting);
|
|
|
|
|
}
|
|
|
|
|
}
|
|
|
|
|
break;
|
2008-06-25 01:10:51 +00:00
|
|
|
|
2013-07-16 11:56:14 +00:00
|
|
|
/* 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;
|
2008-06-25 01:10:51 +00:00
|
|
|
|
2013-07-16 11:56:14 +00:00
|
|
|
/* 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);
|
|
|
|
|
}
|
2008-06-25 01:10:51 +00:00
|
|
|
|
2013-07-16 11:56:14 +00:00
|
|
|
} else {
|
|
|
|
|
$category = $this->getElementCategory($node);
|
|
|
|
|
|
|
|
|
|
if ($category !== self::SPECIAL && $category !== self::SCOPING) {
|
|
|
|
|
/* Otherwise, if node is in neither the formatting
|
|
|
|
|
category nor the phrasing category, then this is a
|
|
|
|
|
parse error. Stop this algorithm. The end tag token
|
|
|
|
|
is ignored. */
|
|
|
|
|
return false;
|
|
|
|
|
}
|
2008-06-25 01:10:51 +00:00
|
|
|
}
|
|
|
|
|
}
|
2013-07-16 11:56:14 +00:00
|
|
|
break;
|
|
|
|
|
}
|
2008-06-25 01:10:51 +00:00
|
|
|
break;
|
|
|
|
|
}
|
|
|
|
|
}
|
|
|
|
|
|
2013-07-16 11:56:14 +00:00
|
|
|
private function inTable($token)
|
|
|
|
|
{
|
2008-06-25 01:10:51 +00:00
|
|
|
$clear = array('html', 'table');
|
|
|
|
|
|
|
|
|
|
/* A character token that is one of one of U+0009 CHARACTER TABULATION,
|
|
|
|
|
U+000A LINE FEED (LF), U+000B LINE TABULATION, U+000C FORM FEED (FF),
|
|
|
|
|
or U+0020 SPACE */
|
2013-07-16 11:56:14 +00:00
|
|
|
if ($token['type'] === HTML5::CHARACTR &&
|
|
|
|
|
preg_match('/^[\t\n\x0b\x0c ]+$/', $token['data'])
|
|
|
|
|
) {
|
2008-06-25 01:10:51 +00:00
|
|
|
/* Append the character to the current node. */
|
|
|
|
|
$text = $this->dom->createTextNode($token['data']);
|
|
|
|
|
end($this->stack)->appendChild($text);
|
|
|
|
|
|
2013-07-16 11:56:14 +00:00
|
|
|
/* A comment token */
|
|
|
|
|
} elseif ($token['type'] === HTML5::COMMENT) {
|
2008-06-25 01:10:51 +00:00
|
|
|
/* 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);
|
|
|
|
|
|
2013-07-16 11:56:14 +00:00
|
|
|
/* A start tag whose tag name is "caption" */
|
|
|
|
|
} elseif ($token['type'] === HTML5::STARTTAG &&
|
|
|
|
|
$token['name'] === 'caption'
|
|
|
|
|
) {
|
2008-06-25 01:10:51 +00:00
|
|
|
/* 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);
|
|
|
|
|
$this->mode = self::IN_CAPTION;
|
|
|
|
|
|
2013-07-16 11:56:14 +00:00
|
|
|
/* A start tag whose tag name is "colgroup" */
|
|
|
|
|
} elseif ($token['type'] === HTML5::STARTTAG &&
|
|
|
|
|
$token['name'] === 'colgroup'
|
|
|
|
|
) {
|
2008-06-25 01:10:51 +00:00
|
|
|
/* 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);
|
|
|
|
|
$this->mode = self::IN_CGROUP;
|
|
|
|
|
|
2013-07-16 11:56:14 +00:00
|
|
|
/* A start tag whose tag name is "col" */
|
|
|
|
|
} elseif ($token['type'] === HTML5::STARTTAG &&
|
|
|
|
|
$token['name'] === 'col'
|
|
|
|
|
) {
|
|
|
|
|
$this->inTable(
|
|
|
|
|
array(
|
|
|
|
|
'name' => 'colgroup',
|
|
|
|
|
'type' => HTML5::STARTTAG,
|
|
|
|
|
'attr' => array()
|
|
|
|
|
)
|
|
|
|
|
);
|
2008-06-25 01:10:51 +00:00
|
|
|
|
|
|
|
|
$this->inColumnGroup($token);
|
|
|
|
|
|
2013-07-16 11:56:14 +00:00
|
|
|
/* 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')
|
|
|
|
|
)
|
|
|
|
|
) {
|
2008-06-25 01:10:51 +00:00
|
|
|
/* 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);
|
|
|
|
|
$this->mode = self::IN_TBODY;
|
|
|
|
|
|
2013-07-16 11:56:14 +00:00
|
|
|
/* A start tag whose tag name is one of: "td", "th", "tr" */
|
|
|
|
|
} elseif ($token['type'] === HTML5::STARTTAG &&
|
|
|
|
|
in_array($token['name'], array('td', 'th', 'tr'))
|
|
|
|
|
) {
|
2008-06-25 01:10:51 +00:00
|
|
|
/* Act as if a start tag token with the tag name "tbody" had been
|
|
|
|
|
seen, then reprocess the current token. */
|
2013-07-16 11:56:14 +00:00
|
|
|
$this->inTable(
|
|
|
|
|
array(
|
|
|
|
|
'name' => 'tbody',
|
|
|
|
|
'type' => HTML5::STARTTAG,
|
|
|
|
|
'attr' => array()
|
|
|
|
|
)
|
|
|
|
|
);
|
2008-06-25 01:10:51 +00:00
|
|
|
|
|
|
|
|
return $this->inTableBody($token);
|
|
|
|
|
|
2013-07-16 11:56:14 +00:00
|
|
|
/* A start tag whose tag name is "table" */
|
|
|
|
|
} elseif ($token['type'] === HTML5::STARTTAG &&
|
|
|
|
|
$token['name'] === 'table'
|
|
|
|
|
) {
|
2008-06-25 01:10:51 +00:00
|
|
|
/* 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. */
|
2013-07-16 11:56:14 +00:00
|
|
|
$this->inTable(
|
|
|
|
|
array(
|
|
|
|
|
'name' => 'table',
|
|
|
|
|
'type' => HTML5::ENDTAG
|
|
|
|
|
)
|
|
|
|
|
);
|
2008-06-25 01:10:51 +00:00
|
|
|
|
|
|
|
|
return $this->mainPhase($token);
|
|
|
|
|
|
2013-07-16 11:56:14 +00:00
|
|
|
/* An end tag whose tag name is "table" */
|
|
|
|
|
} elseif ($token['type'] === HTML5::ENDTAG &&
|
|
|
|
|
$token['name'] === 'table'
|
|
|
|
|
) {
|
2008-06-25 01:10:51 +00:00
|
|
|
/* If the stack of open elements does not have an element in table
|
|
|
|
|
scope with the same tag name as the token, this is a parse error.
|
|
|
|
|
Ignore the token. (innerHTML case) */
|
2013-07-16 11:56:14 +00:00
|
|
|
if (!$this->elementInScope($token['name'], true)) {
|
2008-06-25 01:10:51 +00:00
|
|
|
return false;
|
|
|
|
|
|
2013-07-16 11:56:14 +00:00
|
|
|
/* Otherwise: */
|
2008-06-25 01:10:51 +00:00
|
|
|
} 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. */
|
2013-07-16 11:56:14 +00:00
|
|
|
while (true) {
|
2008-06-25 01:10:51 +00:00
|
|
|
$current = end($this->stack)->nodeName;
|
|
|
|
|
array_pop($this->stack);
|
|
|
|
|
|
2013-07-16 11:56:14 +00:00
|
|
|
if ($current === 'table') {
|
2008-06-25 01:10:51 +00:00
|
|
|
break;
|
|
|
|
|
}
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
/* Reset the insertion mode appropriately. */
|
|
|
|
|
$this->resetInsertionMode();
|
|
|
|
|
}
|
|
|
|
|
|
2013-07-16 11:56:14 +00:00
|
|
|
/* An end tag whose tag name is one of: "body", "caption", "col",
|
|
|
|
|
"colgroup", "html", "tbody", "td", "tfoot", "th", "thead", "tr" */
|
|
|
|
|
} elseif ($token['type'] === HTML5::ENDTAG && in_array(
|
|
|
|
|
$token['name'],
|
|
|
|
|
array(
|
|
|
|
|
'body',
|
|
|
|
|
'caption',
|
|
|
|
|
'col',
|
|
|
|
|
'colgroup',
|
|
|
|
|
'html',
|
|
|
|
|
'tbody',
|
|
|
|
|
'td',
|
|
|
|
|
'tfoot',
|
|
|
|
|
'th',
|
|
|
|
|
'thead',
|
|
|
|
|
'tr'
|
|
|
|
|
)
|
|
|
|
|
)
|
|
|
|
|
) {
|
2008-06-25 01:10:51 +00:00
|
|
|
// Parse error. Ignore the token.
|
|
|
|
|
|
2013-07-16 11:56:14 +00:00
|
|
|
/* Anything else */
|
2008-06-25 01:10:51 +00:00
|
|
|
} else {
|
|
|
|
|
/* Parse error. Process the token as if the insertion mode was "in
|
|
|
|
|
body", with the following exception: */
|
|
|
|
|
|
|
|
|
|
/* If the current node is a table, tbody, tfoot, thead, or tr
|
|
|
|
|
element, then, whenever a node would be inserted into the current
|
|
|
|
|
node, it must instead be inserted into the foster parent element. */
|
2013-07-16 11:56:14 +00:00
|
|
|
if (in_array(
|
|
|
|
|
end($this->stack)->nodeName,
|
|
|
|
|
array('table', 'tbody', 'tfoot', 'thead', 'tr')
|
|
|
|
|
)
|
|
|
|
|
) {
|
2008-06-25 01:10:51 +00:00
|
|
|
/* 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. */
|
2013-07-16 11:56:14 +00:00
|
|
|
for ($n = count($this->stack) - 1; $n >= 0; $n--) {
|
|
|
|
|
if ($this->stack[$n]->nodeName === 'table') {
|
2008-06-25 01:10:51 +00:00
|
|
|
$table = $this->stack[$n];
|
|
|
|
|
break;
|
|
|
|
|
}
|
|
|
|
|
}
|
|
|
|
|
|
2013-07-16 11:56:14 +00:00
|
|
|
if (isset($table) && $table->parentNode !== null) {
|
2008-06-25 01:10:51 +00:00
|
|
|
$this->foster_parent = $table->parentNode;
|
|
|
|
|
|
2013-07-16 11:56:14 +00:00
|
|
|
} elseif (!isset($table)) {
|
2008-06-25 01:10:51 +00:00
|
|
|
$this->foster_parent = $this->stack[0];
|
|
|
|
|
|
2013-07-16 11:56:14 +00:00
|
|
|
} elseif (isset($table) && ($table->parentNode === null ||
|
|
|
|
|
$table->parentNode->nodeType !== XML_ELEMENT_NODE)
|
|
|
|
|
) {
|
2008-06-25 01:10:51 +00:00
|
|
|
$this->foster_parent = $this->stack[$n - 1];
|
|
|
|
|
}
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
$this->inBody($token);
|
|
|
|
|
}
|
|
|
|
|
}
|
|
|
|
|
|
2013-07-16 11:56:14 +00:00
|
|
|
private function inCaption($token)
|
|
|
|
|
{
|
2008-06-25 01:10:51 +00:00
|
|
|
/* An end tag whose tag name is "caption" */
|
2013-07-16 11:56:14 +00:00
|
|
|
if ($token['type'] === HTML5::ENDTAG && $token['name'] === 'caption') {
|
2008-06-25 01:10:51 +00:00
|
|
|
/* If the stack of open elements does not have an element in table
|
|
|
|
|
scope with the same tag name as the token, this is a parse error.
|
|
|
|
|
Ignore the token. (innerHTML case) */
|
2013-07-16 11:56:14 +00:00
|
|
|
if (!$this->elementInScope($token['name'], true)) {
|
2008-06-25 01:10:51 +00:00
|
|
|
// Ignore
|
|
|
|
|
|
2013-07-16 11:56:14 +00:00
|
|
|
/* Otherwise: */
|
2008-06-25 01:10:51 +00:00
|
|
|
} 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. */
|
2013-07-16 11:56:14 +00:00
|
|
|
while (true) {
|
2008-06-25 01:10:51 +00:00
|
|
|
$node = end($this->stack)->nodeName;
|
|
|
|
|
array_pop($this->stack);
|
|
|
|
|
|
2013-07-16 11:56:14 +00:00
|
|
|
if ($node === 'caption') {
|
2008-06-25 01:10:51 +00:00
|
|
|
break;
|
|
|
|
|
}
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
/* Clear the list of active formatting elements up to the last
|
|
|
|
|
marker. */
|
|
|
|
|
$this->clearTheActiveFormattingElementsUpToTheLastMarker();
|
|
|
|
|
|
|
|
|
|
/* Switch the insertion mode to "in table". */
|
|
|
|
|
$this->mode = self::IN_TABLE;
|
|
|
|
|
}
|
|
|
|
|
|
2013-07-16 11:56:14 +00:00
|
|
|
/* A start tag whose tag name is one of: "caption", "col", "colgroup",
|
|
|
|
|
"tbody", "td", "tfoot", "th", "thead", "tr", or an end tag whose tag
|
|
|
|
|
name is "table" */
|
|
|
|
|
} elseif (($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')
|
|
|
|
|
) {
|
2008-06-25 01:10:51 +00:00
|
|
|
/* 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. */
|
2013-07-16 11:56:14 +00:00
|
|
|
$this->inCaption(
|
|
|
|
|
array(
|
|
|
|
|
'name' => 'caption',
|
|
|
|
|
'type' => HTML5::ENDTAG
|
|
|
|
|
)
|
|
|
|
|
);
|
2008-06-25 01:10:51 +00:00
|
|
|
|
|
|
|
|
return $this->inTable($token);
|
|
|
|
|
|
2013-07-16 11:56:14 +00:00
|
|
|
/* 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'
|
|
|
|
|
)
|
|
|
|
|
)
|
|
|
|
|
) {
|
2008-06-25 01:10:51 +00:00
|
|
|
// Parse error. Ignore the token.
|
|
|
|
|
|
2013-07-16 11:56:14 +00:00
|
|
|
/* Anything else */
|
2008-06-25 01:10:51 +00:00
|
|
|
} else {
|
|
|
|
|
/* Process the token as if the insertion mode was "in body". */
|
|
|
|
|
$this->inBody($token);
|
|
|
|
|
}
|
|
|
|
|
}
|
|
|
|
|
|
2013-07-16 11:56:14 +00:00
|
|
|
private function inColumnGroup($token)
|
|
|
|
|
{
|
2008-06-25 01:10:51 +00:00
|
|
|
/* A character token that is one of one of U+0009 CHARACTER TABULATION,
|
|
|
|
|
U+000A LINE FEED (LF), U+000B LINE TABULATION, U+000C FORM FEED (FF),
|
|
|
|
|
or U+0020 SPACE */
|
2013-07-16 11:56:14 +00:00
|
|
|
if ($token['type'] === HTML5::CHARACTR &&
|
|
|
|
|
preg_match('/^[\t\n\x0b\x0c ]+$/', $token['data'])
|
|
|
|
|
) {
|
2008-06-25 01:10:51 +00:00
|
|
|
/* Append the character to the current node. */
|
|
|
|
|
$text = $this->dom->createTextNode($token['data']);
|
|
|
|
|
end($this->stack)->appendChild($text);
|
|
|
|
|
|
2013-07-16 11:56:14 +00:00
|
|
|
/* A comment token */
|
|
|
|
|
} elseif ($token['type'] === HTML5::COMMENT) {
|
2008-06-25 01:10:51 +00:00
|
|
|
/* 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);
|
|
|
|
|
|
2013-07-16 11:56:14 +00:00
|
|
|
/* A start tag whose tag name is "col" */
|
|
|
|
|
} elseif ($token['type'] === HTML5::STARTTAG && $token['name'] === 'col') {
|
2008-06-25 01:10:51 +00:00
|
|
|
/* Insert a col element for the token. Immediately pop the current
|
|
|
|
|
node off the stack of open elements. */
|
|
|
|
|
$this->insertElement($token);
|
|
|
|
|
array_pop($this->stack);
|
|
|
|
|
|
2013-07-16 11:56:14 +00:00
|
|
|
/* An end tag whose tag name is "colgroup" */
|
|
|
|
|
} elseif ($token['type'] === HTML5::ENDTAG &&
|
|
|
|
|
$token['name'] === 'colgroup'
|
|
|
|
|
) {
|
2008-06-25 01:10:51 +00:00
|
|
|
/* If the current node is the root html element, then this is a
|
|
|
|
|
parse error, ignore the token. (innerHTML case) */
|
2013-07-16 11:56:14 +00:00
|
|
|
if (end($this->stack)->nodeName === 'html') {
|
2008-06-25 01:10:51 +00:00
|
|
|
// Ignore
|
|
|
|
|
|
2013-07-16 11:56:14 +00:00
|
|
|
/* Otherwise, pop the current node (which will be a colgroup
|
|
|
|
|
element) from the stack of open elements. Switch the insertion
|
|
|
|
|
mode to "in table". */
|
2008-06-25 01:10:51 +00:00
|
|
|
} else {
|
|
|
|
|
array_pop($this->stack);
|
|
|
|
|
$this->mode = self::IN_TABLE;
|
|
|
|
|
}
|
|
|
|
|
|
2013-07-16 11:56:14 +00:00
|
|
|
/* An end tag whose tag name is "col" */
|
|
|
|
|
} elseif ($token['type'] === HTML5::ENDTAG && $token['name'] === 'col') {
|
2008-06-25 01:10:51 +00:00
|
|
|
/* Parse error. Ignore the token. */
|
|
|
|
|
|
2013-07-16 11:56:14 +00:00
|
|
|
/* Anything else */
|
2008-06-25 01:10:51 +00:00
|
|
|
} 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. */
|
2013-07-16 11:56:14 +00:00
|
|
|
$this->inColumnGroup(
|
|
|
|
|
array(
|
|
|
|
|
'name' => 'colgroup',
|
|
|
|
|
'type' => HTML5::ENDTAG
|
|
|
|
|
)
|
|
|
|
|
);
|
2008-06-25 01:10:51 +00:00
|
|
|
|
|
|
|
|
return $this->inTable($token);
|
|
|
|
|
}
|
|
|
|
|
}
|
|
|
|
|
|
2013-07-16 11:56:14 +00:00
|
|
|
private function inTableBody($token)
|
|
|
|
|
{
|
2008-06-25 01:10:51 +00:00
|
|
|
$clear = array('tbody', 'tfoot', 'thead', 'html');
|
|
|
|
|
|
|
|
|
|
/* A start tag whose tag name is "tr" */
|
2013-07-16 11:56:14 +00:00
|
|
|
if ($token['type'] === HTML5::STARTTAG && $token['name'] === 'tr') {
|
2008-06-25 01:10:51 +00:00
|
|
|
/* 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);
|
|
|
|
|
$this->mode = self::IN_ROW;
|
|
|
|
|
|
2013-07-16 11:56:14 +00:00
|
|
|
/* A start tag whose tag name is one of: "th", "td" */
|
|
|
|
|
} elseif ($token['type'] === HTML5::STARTTAG &&
|
|
|
|
|
($token['name'] === 'th' || $token['name'] === 'td')
|
|
|
|
|
) {
|
2008-06-25 01:10:51 +00:00
|
|
|
/* Parse error. Act as if a start tag with the tag name "tr" had
|
|
|
|
|
been seen, then reprocess the current token. */
|
2013-07-16 11:56:14 +00:00
|
|
|
$this->inTableBody(
|
|
|
|
|
array(
|
|
|
|
|
'name' => 'tr',
|
|
|
|
|
'type' => HTML5::STARTTAG,
|
|
|
|
|
'attr' => array()
|
|
|
|
|
)
|
|
|
|
|
);
|
2008-06-25 01:10:51 +00:00
|
|
|
|
|
|
|
|
return $this->inRow($token);
|
|
|
|
|
|
2013-07-16 11:56:14 +00:00
|
|
|
/* 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'))
|
|
|
|
|
) {
|
2008-06-25 01:10:51 +00:00
|
|
|
/* 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. */
|
2013-07-16 11:56:14 +00:00
|
|
|
if (!$this->elementInScope($token['name'], true)) {
|
2008-06-25 01:10:51 +00:00
|
|
|
// Ignore
|
|
|
|
|
|
2013-07-16 11:56:14 +00:00
|
|
|
/* Otherwise: */
|
2008-06-25 01:10:51 +00:00
|
|
|
} 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);
|
|
|
|
|
$this->mode = self::IN_TABLE;
|
|
|
|
|
}
|
|
|
|
|
|
2013-07-16 11:56:14 +00:00
|
|
|
/* A start tag whose tag name is one of: "caption", "col", "colgroup",
|
|
|
|
|
"tbody", "tfoot", "thead", or an end tag whose tag name is "table" */
|
|
|
|
|
} elseif (($token['type'] === HTML5::STARTTAG && in_array(
|
|
|
|
|
$token['name'],
|
|
|
|
|
array('caption', 'col', 'colgroup', 'tbody', 'tfoor', 'thead')
|
|
|
|
|
)) ||
|
|
|
|
|
($token['type'] === HTML5::STARTTAG && $token['name'] === 'table')
|
|
|
|
|
) {
|
2008-06-25 01:10:51 +00:00
|
|
|
/* If the stack of open elements does not have a tbody, thead, or
|
|
|
|
|
tfoot element in table scope, this is a parse error. Ignore the
|
|
|
|
|
token. (innerHTML case) */
|
2013-07-16 11:56:14 +00:00
|
|
|
if (!$this->elementInScope(array('tbody', 'thead', 'tfoot'), true)) {
|
2008-06-25 01:10:51 +00:00
|
|
|
// Ignore.
|
|
|
|
|
|
2013-07-16 11:56:14 +00:00
|
|
|
/* Otherwise: */
|
2008-06-25 01:10:51 +00:00
|
|
|
} 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. */
|
2013-07-16 11:56:14 +00:00
|
|
|
$this->inTableBody(
|
|
|
|
|
array(
|
|
|
|
|
'name' => end($this->stack)->nodeName,
|
|
|
|
|
'type' => HTML5::ENDTAG
|
|
|
|
|
)
|
|
|
|
|
);
|
2008-06-25 01:10:51 +00:00
|
|
|
|
|
|
|
|
return $this->mainPhase($token);
|
|
|
|
|
}
|
|
|
|
|
|
2013-07-16 11:56:14 +00:00
|
|
|
/* 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')
|
|
|
|
|
)
|
|
|
|
|
) {
|
2008-06-25 01:10:51 +00:00
|
|
|
/* Parse error. Ignore the token. */
|
|
|
|
|
|
2013-07-16 11:56:14 +00:00
|
|
|
/* Anything else */
|
2008-06-25 01:10:51 +00:00
|
|
|
} else {
|
|
|
|
|
/* Process the token as if the insertion mode was "in table". */
|
|
|
|
|
$this->inTable($token);
|
|
|
|
|
}
|
|
|
|
|
}
|
|
|
|
|
|
2013-07-16 11:56:14 +00:00
|
|
|
private function inRow($token)
|
|
|
|
|
{
|
2008-06-25 01:10:51 +00:00
|
|
|
$clear = array('tr', 'html');
|
|
|
|
|
|
|
|
|
|
/* A start tag whose tag name is one of: "th", "td" */
|
2013-07-16 11:56:14 +00:00
|
|
|
if ($token['type'] === HTML5::STARTTAG &&
|
|
|
|
|
($token['name'] === 'th' || $token['name'] === 'td')
|
|
|
|
|
) {
|
2008-06-25 01:10:51 +00:00
|
|
|
/* 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. */
|
|
|
|
|
$this->a_formatting[] = self::MARKER;
|
|
|
|
|
|
2013-07-16 11:56:14 +00:00
|
|
|
/* An end tag whose tag name is "tr" */
|
|
|
|
|
} elseif ($token['type'] === HTML5::ENDTAG && $token['name'] === 'tr') {
|
2008-06-25 01:10:51 +00:00
|
|
|
/* If the stack of open elements does not have an element in table
|
|
|
|
|
scope with the same tag name as the token, this is a parse error.
|
|
|
|
|
Ignore the token. (innerHTML case) */
|
2013-07-16 11:56:14 +00:00
|
|
|
if (!$this->elementInScope($token['name'], true)) {
|
2008-06-25 01:10:51 +00:00
|
|
|
// Ignore.
|
|
|
|
|
|
2013-07-16 11:56:14 +00:00
|
|
|
/* Otherwise: */
|
2008-06-25 01:10:51 +00:00
|
|
|
} 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);
|
|
|
|
|
$this->mode = self::IN_TBODY;
|
|
|
|
|
}
|
|
|
|
|
|
2013-07-16 11:56:14 +00:00
|
|
|
/* A start tag whose tag name is one of: "caption", "col", "colgroup",
|
|
|
|
|
"tbody", "tfoot", "thead", "tr" or an end tag whose tag name is "table" */
|
|
|
|
|
} elseif ($token['type'] === HTML5::STARTTAG && in_array(
|
|
|
|
|
$token['name'],
|
|
|
|
|
array('caption', 'col', 'colgroup', 'tbody', 'tfoot', 'thead', 'tr')
|
|
|
|
|
)
|
|
|
|
|
) {
|
2008-06-25 01:10:51 +00:00
|
|
|
/* 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. */
|
2013-07-16 11:56:14 +00:00
|
|
|
$this->inRow(
|
|
|
|
|
array(
|
|
|
|
|
'name' => 'tr',
|
|
|
|
|
'type' => HTML5::ENDTAG
|
|
|
|
|
)
|
|
|
|
|
);
|
2008-06-25 01:10:51 +00:00
|
|
|
|
|
|
|
|
return $this->inCell($token);
|
|
|
|
|
|
2013-07-16 11:56:14 +00:00
|
|
|
/* 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'))
|
|
|
|
|
) {
|
2008-06-25 01:10:51 +00:00
|
|
|
/* 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. */
|
2013-07-16 11:56:14 +00:00
|
|
|
if (!$this->elementInScope($token['name'], true)) {
|
2008-06-25 01:10:51 +00:00
|
|
|
// Ignore.
|
|
|
|
|
|
2013-07-16 11:56:14 +00:00
|
|
|
/* Otherwise: */
|
2008-06-25 01:10:51 +00:00
|
|
|
} else {
|
|
|
|
|
/* Otherwise, act as if an end tag with the tag name "tr" had
|
|
|
|
|
been seen, then reprocess the current token. */
|
2013-07-16 11:56:14 +00:00
|
|
|
$this->inRow(
|
|
|
|
|
array(
|
|
|
|
|
'name' => 'tr',
|
|
|
|
|
'type' => HTML5::ENDTAG
|
|
|
|
|
)
|
|
|
|
|
);
|
2008-06-25 01:10:51 +00:00
|
|
|
|
|
|
|
|
return $this->inCell($token);
|
|
|
|
|
}
|
|
|
|
|
|
2013-07-16 11:56:14 +00:00
|
|
|
/* 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')
|
|
|
|
|
)
|
|
|
|
|
) {
|
2008-06-25 01:10:51 +00:00
|
|
|
/* Parse error. Ignore the token. */
|
|
|
|
|
|
2013-07-16 11:56:14 +00:00
|
|
|
/* Anything else */
|
2008-06-25 01:10:51 +00:00
|
|
|
} else {
|
|
|
|
|
/* Process the token as if the insertion mode was "in table". */
|
|
|
|
|
$this->inTable($token);
|
|
|
|
|
}
|
|
|
|
|
}
|
|
|
|
|
|
2013-07-16 11:56:14 +00:00
|
|
|
private function inCell($token)
|
|
|
|
|
{
|
2008-06-25 01:10:51 +00:00
|
|
|
/* An end tag whose tag name is one of: "td", "th" */
|
2013-07-16 11:56:14 +00:00
|
|
|
if ($token['type'] === HTML5::ENDTAG &&
|
|
|
|
|
($token['name'] === 'td' || $token['name'] === 'th')
|
|
|
|
|
) {
|
2008-06-25 01:10:51 +00:00
|
|
|
/* If the stack of open elements does not have an element in table
|
|
|
|
|
scope with the same tag name as that of the token, then this is a
|
|
|
|
|
parse error and the token must be ignored. */
|
2013-07-16 11:56:14 +00:00
|
|
|
if (!$this->elementInScope($token['name'], true)) {
|
2008-06-25 01:10:51 +00:00
|
|
|
// Ignore.
|
|
|
|
|
|
2013-07-16 11:56:14 +00:00
|
|
|
/* Otherwise: */
|
2008-06-25 01:10:51 +00:00
|
|
|
} 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. */
|
2013-07-16 11:56:14 +00:00
|
|
|
while (true) {
|
2008-06-25 01:10:51 +00:00
|
|
|
$node = end($this->stack)->nodeName;
|
|
|
|
|
array_pop($this->stack);
|
|
|
|
|
|
2013-07-16 11:56:14 +00:00
|
|
|
if ($node === $token['name']) {
|
2008-06-25 01:10:51 +00:00
|
|
|
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.) */
|
|
|
|
|
$this->mode = self::IN_ROW;
|
|
|
|
|
}
|
|
|
|
|
|
2013-07-16 11:56:14 +00:00
|
|
|
/* A start tag whose tag name is one of: "caption", "col", "colgroup",
|
|
|
|
|
"tbody", "td", "tfoot", "th", "thead", "tr" */
|
|
|
|
|
} elseif ($token['type'] === HTML5::STARTTAG && in_array(
|
|
|
|
|
$token['name'],
|
|
|
|
|
array(
|
|
|
|
|
'caption',
|
|
|
|
|
'col',
|
|
|
|
|
'colgroup',
|
|
|
|
|
'tbody',
|
|
|
|
|
'td',
|
|
|
|
|
'tfoot',
|
|
|
|
|
'th',
|
|
|
|
|
'thead',
|
|
|
|
|
'tr'
|
|
|
|
|
)
|
|
|
|
|
)
|
|
|
|
|
) {
|
2008-06-25 01:10:51 +00:00
|
|
|
/* If the stack of open elements does not have a td or th element
|
|
|
|
|
in table scope, then this is a parse error; ignore the token.
|
|
|
|
|
(innerHTML case) */
|
2013-07-16 11:56:14 +00:00
|
|
|
if (!$this->elementInScope(array('td', 'th'), true)) {
|
2008-06-25 01:10:51 +00:00
|
|
|
// Ignore.
|
|
|
|
|
|
2013-07-16 11:56:14 +00:00
|
|
|
/* Otherwise, close the cell (see below) and reprocess the current
|
|
|
|
|
token. */
|
2008-06-25 01:10:51 +00:00
|
|
|
} else {
|
|
|
|
|
$this->closeCell();
|
|
|
|
|
return $this->inRow($token);
|
|
|
|
|
}
|
|
|
|
|
|
2013-07-16 11:56:14 +00:00
|
|
|
/* 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(
|
|
|
|
|
$token['name'],
|
|
|
|
|
array(
|
|
|
|
|
'caption',
|
|
|
|
|
'col',
|
|
|
|
|
'colgroup',
|
|
|
|
|
'tbody',
|
|
|
|
|
'td',
|
|
|
|
|
'tfoot',
|
|
|
|
|
'th',
|
|
|
|
|
'thead',
|
|
|
|
|
'tr'
|
|
|
|
|
)
|
|
|
|
|
)
|
|
|
|
|
) {
|
2008-06-25 01:10:51 +00:00
|
|
|
/* If the stack of open elements does not have a td or th element
|
|
|
|
|
in table scope, then this is a parse error; ignore the token.
|
|
|
|
|
(innerHTML case) */
|
2013-07-16 11:56:14 +00:00
|
|
|
if (!$this->elementInScope(array('td', 'th'), true)) {
|
2008-06-25 01:10:51 +00:00
|
|
|
// Ignore.
|
|
|
|
|
|
2013-07-16 11:56:14 +00:00
|
|
|
/* Otherwise, close the cell (see below) and reprocess the current
|
|
|
|
|
token. */
|
2008-06-25 01:10:51 +00:00
|
|
|
} else {
|
|
|
|
|
$this->closeCell();
|
|
|
|
|
return $this->inRow($token);
|
|
|
|
|
}
|
|
|
|
|
|
2013-07-16 11:56:14 +00:00
|
|
|
/* An end tag whose tag name is one of: "body", "caption", "col",
|
|
|
|
|
"colgroup", "html" */
|
|
|
|
|
} elseif ($token['type'] === HTML5::ENDTAG && in_array(
|
|
|
|
|
$token['name'],
|
|
|
|
|
array('body', 'caption', 'col', 'colgroup', 'html')
|
|
|
|
|
)
|
|
|
|
|
) {
|
2008-06-25 01:10:51 +00:00
|
|
|
/* Parse error. Ignore the token. */
|
|
|
|
|
|
2013-07-16 11:56:14 +00:00
|
|
|
/* An end tag whose tag name is one of: "table", "tbody", "tfoot",
|
|
|
|
|
"thead", "tr" */
|
|
|
|
|
} elseif ($token['type'] === HTML5::ENDTAG && in_array(
|
|
|
|
|
$token['name'],
|
|
|
|
|
array('table', 'tbody', 'tfoot', 'thead', 'tr')
|
|
|
|
|
)
|
|
|
|
|
) {
|
2008-06-25 01:10:51 +00:00
|
|
|
/* If the stack of open elements does not have an element in table
|
|
|
|
|
scope with the same tag name as that of the token (which can only
|
|
|
|
|
happen for "tbody", "tfoot" and "thead", or, in the innerHTML case),
|
|
|
|
|
then this is a parse error and the token must be ignored. */
|
2013-07-16 11:56:14 +00:00
|
|
|
if (!$this->elementInScope($token['name'], true)) {
|
2008-06-25 01:10:51 +00:00
|
|
|
// Ignore.
|
|
|
|
|
|
2013-07-16 11:56:14 +00:00
|
|
|
/* Otherwise, close the cell (see below) and reprocess the current
|
|
|
|
|
token. */
|
2008-06-25 01:10:51 +00:00
|
|
|
} else {
|
|
|
|
|
$this->closeCell();
|
|
|
|
|
return $this->inRow($token);
|
|
|
|
|
}
|
|
|
|
|
|
2013-07-16 11:56:14 +00:00
|
|
|
/* Anything else */
|
2008-06-25 01:10:51 +00:00
|
|
|
} else {
|
|
|
|
|
/* Process the token as if the insertion mode was "in body". */
|
|
|
|
|
$this->inBody($token);
|
|
|
|
|
}
|
|
|
|
|
}
|
|
|
|
|
|
2013-07-16 11:56:14 +00:00
|
|
|
private function inSelect($token)
|
|
|
|
|
{
|
2008-06-25 01:10:51 +00:00
|
|
|
/* Handle the token as follows: */
|
|
|
|
|
|
|
|
|
|
/* A character token */
|
2013-07-16 11:56:14 +00:00
|
|
|
if ($token['type'] === HTML5::CHARACTR) {
|
2008-06-25 01:10:51 +00:00
|
|
|
/* Append the token's character to the current node. */
|
|
|
|
|
$this->insertText($token['data']);
|
|
|
|
|
|
2013-07-16 11:56:14 +00:00
|
|
|
/* A comment token */
|
|
|
|
|
} elseif ($token['type'] === HTML5::COMMENT) {
|
2008-06-25 01:10:51 +00:00
|
|
|
/* 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']);
|
|
|
|
|
|
2013-07-16 11:56:14 +00:00
|
|
|
/* A start tag token whose tag name is "option" */
|
|
|
|
|
} elseif ($token['type'] === HTML5::STARTTAG &&
|
|
|
|
|
$token['name'] === 'option'
|
|
|
|
|
) {
|
2008-06-25 01:10:51 +00:00
|
|
|
/* If the current node is an option element, act as if an end tag
|
|
|
|
|
with the tag name "option" had been seen. */
|
2013-07-16 11:56:14 +00:00
|
|
|
if (end($this->stack)->nodeName === 'option') {
|
|
|
|
|
$this->inSelect(
|
|
|
|
|
array(
|
|
|
|
|
'name' => 'option',
|
|
|
|
|
'type' => HTML5::ENDTAG
|
|
|
|
|
)
|
|
|
|
|
);
|
2008-06-25 01:10:51 +00:00
|
|
|
}
|
|
|
|
|
|
|
|
|
|
/* Insert an HTML element for the token. */
|
|
|
|
|
$this->insertElement($token);
|
|
|
|
|
|
2013-07-16 11:56:14 +00:00
|
|
|
/* A start tag token whose tag name is "optgroup" */
|
|
|
|
|
} elseif ($token['type'] === HTML5::STARTTAG &&
|
|
|
|
|
$token['name'] === 'optgroup'
|
|
|
|
|
) {
|
2008-06-25 01:10:51 +00:00
|
|
|
/* If the current node is an option element, act as if an end tag
|
|
|
|
|
with the tag name "option" had been seen. */
|
2013-07-16 11:56:14 +00:00
|
|
|
if (end($this->stack)->nodeName === 'option') {
|
|
|
|
|
$this->inSelect(
|
|
|
|
|
array(
|
|
|
|
|
'name' => 'option',
|
|
|
|
|
'type' => HTML5::ENDTAG
|
|
|
|
|
)
|
|
|
|
|
);
|
2008-06-25 01:10:51 +00:00
|
|
|
}
|
|
|
|
|
|
|
|
|
|
/* If the current node is an optgroup element, act as if an end tag
|
|
|
|
|
with the tag name "optgroup" had been seen. */
|
2013-07-16 11:56:14 +00:00
|
|
|
if (end($this->stack)->nodeName === 'optgroup') {
|
|
|
|
|
$this->inSelect(
|
|
|
|
|
array(
|
|
|
|
|
'name' => 'optgroup',
|
|
|
|
|
'type' => HTML5::ENDTAG
|
|
|
|
|
)
|
|
|
|
|
);
|
2008-06-25 01:10:51 +00:00
|
|
|
}
|
|
|
|
|
|
|
|
|
|
/* Insert an HTML element for the token. */
|
|
|
|
|
$this->insertElement($token);
|
|
|
|
|
|
2013-07-16 11:56:14 +00:00
|
|
|
/* An end tag token whose tag name is "optgroup" */
|
|
|
|
|
} elseif ($token['type'] === HTML5::ENDTAG &&
|
|
|
|
|
$token['name'] === 'optgroup'
|
|
|
|
|
) {
|
2008-06-25 01:10:51 +00:00
|
|
|
/* 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);
|
|
|
|
|
|
2013-07-16 11:56:14 +00:00
|
|
|
if ($this->stack[$elements_in_stack - 1]->nodeName === 'option' &&
|
|
|
|
|
$this->stack[$elements_in_stack - 2]->nodeName === 'optgroup'
|
|
|
|
|
) {
|
|
|
|
|
$this->inSelect(
|
|
|
|
|
array(
|
|
|
|
|
'name' => 'option',
|
|
|
|
|
'type' => HTML5::ENDTAG
|
|
|
|
|
)
|
|
|
|
|
);
|
2008-06-25 01:10:51 +00:00
|
|
|
}
|
|
|
|
|
|
|
|
|
|
/* If the current node is an optgroup element, then pop that node
|
|
|
|
|
from the stack of open elements. Otherwise, this is a parse error,
|
|
|
|
|
ignore the token. */
|
2013-07-16 11:56:14 +00:00
|
|
|
if ($this->stack[$elements_in_stack - 1] === 'optgroup') {
|
2008-06-25 01:10:51 +00:00
|
|
|
array_pop($this->stack);
|
|
|
|
|
}
|
|
|
|
|
|
2013-07-16 11:56:14 +00:00
|
|
|
/* An end tag token whose tag name is "option" */
|
|
|
|
|
} elseif ($token['type'] === HTML5::ENDTAG &&
|
|
|
|
|
$token['name'] === 'option'
|
|
|
|
|
) {
|
2008-06-25 01:10:51 +00:00
|
|
|
/* If the current node is an option element, then pop that node
|
|
|
|
|
from the stack of open elements. Otherwise, this is a parse error,
|
|
|
|
|
ignore the token. */
|
2013-07-16 11:56:14 +00:00
|
|
|
if (end($this->stack)->nodeName === 'option') {
|
2008-06-25 01:10:51 +00:00
|
|
|
array_pop($this->stack);
|
|
|
|
|
}
|
|
|
|
|
|
2013-07-16 11:56:14 +00:00
|
|
|
/* An end tag whose tag name is "select" */
|
|
|
|
|
} elseif ($token['type'] === HTML5::ENDTAG &&
|
|
|
|
|
$token['name'] === 'select'
|
|
|
|
|
) {
|
2008-06-25 01:10:51 +00:00
|
|
|
/* If the stack of open elements does not have an element in table
|
|
|
|
|
scope with the same tag name as the token, this is a parse error.
|
|
|
|
|
Ignore the token. (innerHTML case) */
|
2013-07-16 11:56:14 +00:00
|
|
|
if (!$this->elementInScope($token['name'], true)) {
|
2008-06-25 01:10:51 +00:00
|
|
|
// w/e
|
|
|
|
|
|
2013-07-16 11:56:14 +00:00
|
|
|
/* Otherwise: */
|
2008-06-25 01:10:51 +00:00
|
|
|
} else {
|
|
|
|
|
/* Pop elements from the stack of open elements until a select
|
|
|
|
|
element has been popped from the stack. */
|
2013-07-16 11:56:14 +00:00
|
|
|
while (true) {
|
2008-06-25 01:10:51 +00:00
|
|
|
$current = end($this->stack)->nodeName;
|
|
|
|
|
array_pop($this->stack);
|
|
|
|
|
|
2013-07-16 11:56:14 +00:00
|
|
|
if ($current === 'select') {
|
2008-06-25 01:10:51 +00:00
|
|
|
break;
|
|
|
|
|
}
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
/* Reset the insertion mode appropriately. */
|
|
|
|
|
$this->resetInsertionMode();
|
|
|
|
|
}
|
|
|
|
|
|
2013-07-16 11:56:14 +00:00
|
|
|
/* A start tag whose tag name is "select" */
|
|
|
|
|
} elseif ($token['name'] === 'select' &&
|
|
|
|
|
$token['type'] === HTML5::STARTTAG
|
|
|
|
|
) {
|
2008-06-25 01:10:51 +00:00
|
|
|
/* Parse error. Act as if the token had been an end tag with the
|
|
|
|
|
tag name "select" instead. */
|
2013-07-16 11:56:14 +00:00
|
|
|
$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'
|
|
|
|
|
)
|
|
|
|
|
) && $token['type'] === HTML5::ENDTAG
|
|
|
|
|
) {
|
2008-06-25 01:10:51 +00:00
|
|
|
/* Parse error. */
|
|
|
|
|
// w/e
|
|
|
|
|
|
|
|
|
|
/* If the stack of open elements has an element in table scope with
|
|
|
|
|
the same tag name as that of the token, then act as if an end tag
|
|
|
|
|
with the tag name "select" had been seen, and reprocess the token.
|
|
|
|
|
Otherwise, ignore the token. */
|
2013-07-16 11:56:14 +00:00
|
|
|
if ($this->elementInScope($token['name'], true)) {
|
|
|
|
|
$this->inSelect(
|
|
|
|
|
array(
|
|
|
|
|
'name' => 'select',
|
|
|
|
|
'type' => HTML5::ENDTAG
|
|
|
|
|
)
|
|
|
|
|
);
|
2008-06-25 01:10:51 +00:00
|
|
|
|
|
|
|
|
$this->mainPhase($token);
|
|
|
|
|
}
|
|
|
|
|
|
2013-07-16 11:56:14 +00:00
|
|
|
/* Anything else */
|
2008-06-25 01:10:51 +00:00
|
|
|
} else {
|
|
|
|
|
/* Parse error. Ignore the token. */
|
|
|
|
|
}
|
|
|
|
|
}
|
|
|
|
|
|
2013-07-16 11:56:14 +00:00
|
|
|
private function afterBody($token)
|
|
|
|
|
{
|
2008-06-25 01:10:51 +00:00
|
|
|
/* Handle the token as follows: */
|
|
|
|
|
|
|
|
|
|
/* A character token that is one of one of U+0009 CHARACTER TABULATION,
|
|
|
|
|
U+000A LINE FEED (LF), U+000B LINE TABULATION, U+000C FORM FEED (FF),
|
|
|
|
|
or U+0020 SPACE */
|
2013-07-16 11:56:14 +00:00
|
|
|
if ($token['type'] === HTML5::CHARACTR &&
|
|
|
|
|
preg_match('/^[\t\n\x0b\x0c ]+$/', $token['data'])
|
|
|
|
|
) {
|
2008-06-25 01:10:51 +00:00
|
|
|
/* Process the token as it would be processed if the insertion mode
|
|
|
|
|
was "in body". */
|
|
|
|
|
$this->inBody($token);
|
|
|
|
|
|
2013-07-16 11:56:14 +00:00
|
|
|
/* A comment token */
|
|
|
|
|
} elseif ($token['type'] === HTML5::COMMENT) {
|
2008-06-25 01:10:51 +00:00
|
|
|
/* 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);
|
|
|
|
|
|
2013-07-16 11:56:14 +00:00
|
|
|
/* An end tag with the tag name "html" */
|
|
|
|
|
} elseif ($token['type'] === HTML5::ENDTAG && $token['name'] === 'html') {
|
2008-06-25 01:10:51 +00:00
|
|
|
/* 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;
|
|
|
|
|
|
2013-07-16 11:56:14 +00:00
|
|
|
/* Anything else */
|
2008-06-25 01:10:51 +00:00
|
|
|
} else {
|
|
|
|
|
/* Parse error. Set the insertion mode to "in body" and reprocess
|
|
|
|
|
the token. */
|
|
|
|
|
$this->mode = self::IN_BODY;
|
|
|
|
|
return $this->inBody($token);
|
|
|
|
|
}
|
|
|
|
|
}
|
|
|
|
|
|
2013-07-16 11:56:14 +00:00
|
|
|
private function inFrameset($token)
|
|
|
|
|
{
|
2008-06-25 01:10:51 +00:00
|
|
|
/* Handle the token as follows: */
|
|
|
|
|
|
|
|
|
|
/* A character token that is one of one of U+0009 CHARACTER TABULATION,
|
|
|
|
|
U+000A LINE FEED (LF), U+000B LINE TABULATION, U+000C FORM FEED (FF),
|
|
|
|
|
U+000D CARRIAGE RETURN (CR), or U+0020 SPACE */
|
2013-07-16 11:56:14 +00:00
|
|
|
if ($token['type'] === HTML5::CHARACTR &&
|
|
|
|
|
preg_match('/^[\t\n\x0b\x0c ]+$/', $token['data'])
|
|
|
|
|
) {
|
2008-06-25 01:10:51 +00:00
|
|
|
/* Append the character to the current node. */
|
|
|
|
|
$this->insertText($token['data']);
|
|
|
|
|
|
2013-07-16 11:56:14 +00:00
|
|
|
/* A comment token */
|
|
|
|
|
} elseif ($token['type'] === HTML5::COMMENT) {
|
2008-06-25 01:10:51 +00:00
|
|
|
/* 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']);
|
|
|
|
|
|
2013-07-16 11:56:14 +00:00
|
|
|
/* A start tag with the tag name "frameset" */
|
|
|
|
|
} elseif ($token['name'] === 'frameset' &&
|
|
|
|
|
$token['type'] === HTML5::STARTTAG
|
|
|
|
|
) {
|
2008-06-25 01:10:51 +00:00
|
|
|
$this->insertElement($token);
|
|
|
|
|
|
2013-07-16 11:56:14 +00:00
|
|
|
/* An end tag with the tag name "frameset" */
|
|
|
|
|
} elseif ($token['name'] === 'frameset' &&
|
|
|
|
|
$token['type'] === HTML5::ENDTAG
|
|
|
|
|
) {
|
2008-06-25 01:10:51 +00:00
|
|
|
/* If the current node is the root html element, then this is a
|
|
|
|
|
parse error; ignore the token. (innerHTML case) */
|
2013-07-16 11:56:14 +00:00
|
|
|
if (end($this->stack)->nodeName === 'html') {
|
2008-06-25 01:10:51 +00:00
|
|
|
// 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". */
|
|
|
|
|
$this->mode = self::AFTR_FRAME;
|
|
|
|
|
}
|
|
|
|
|
|
2013-07-16 11:56:14 +00:00
|
|
|
/* A start tag with the tag name "frame" */
|
|
|
|
|
} elseif ($token['name'] === 'frame' &&
|
|
|
|
|
$token['type'] === HTML5::STARTTAG
|
|
|
|
|
) {
|
2008-06-25 01:10:51 +00:00
|
|
|
/* Insert an HTML element for the token. */
|
|
|
|
|
$this->insertElement($token);
|
|
|
|
|
|
|
|
|
|
/* Immediately pop the current node off the stack of open elements. */
|
|
|
|
|
array_pop($this->stack);
|
|
|
|
|
|
2013-07-16 11:56:14 +00:00
|
|
|
/* A start tag with the tag name "noframes" */
|
|
|
|
|
} elseif ($token['name'] === 'noframes' &&
|
|
|
|
|
$token['type'] === HTML5::STARTTAG
|
|
|
|
|
) {
|
2008-06-25 01:10:51 +00:00
|
|
|
/* Process the token as if the insertion mode had been "in body". */
|
|
|
|
|
$this->inBody($token);
|
|
|
|
|
|
2013-07-16 11:56:14 +00:00
|
|
|
/* Anything else */
|
2008-06-25 01:10:51 +00:00
|
|
|
} else {
|
|
|
|
|
/* Parse error. Ignore the token. */
|
|
|
|
|
}
|
|
|
|
|
}
|
|
|
|
|
|
2013-07-16 11:56:14 +00:00
|
|
|
private function afterFrameset($token)
|
|
|
|
|
{
|
2008-06-25 01:10:51 +00:00
|
|
|
/* Handle the token as follows: */
|
|
|
|
|
|
|
|
|
|
/* A character token that is one of one of U+0009 CHARACTER TABULATION,
|
|
|
|
|
U+000A LINE FEED (LF), U+000B LINE TABULATION, U+000C FORM FEED (FF),
|
|
|
|
|
U+000D CARRIAGE RETURN (CR), or U+0020 SPACE */
|
2013-07-16 11:56:14 +00:00
|
|
|
if ($token['type'] === HTML5::CHARACTR &&
|
|
|
|
|
preg_match('/^[\t\n\x0b\x0c ]+$/', $token['data'])
|
|
|
|
|
) {
|
2008-06-25 01:10:51 +00:00
|
|
|
/* Append the character to the current node. */
|
|
|
|
|
$this->insertText($token['data']);
|
|
|
|
|
|
2013-07-16 11:56:14 +00:00
|
|
|
/* A comment token */
|
|
|
|
|
} elseif ($token['type'] === HTML5::COMMENT) {
|
2008-06-25 01:10:51 +00:00
|
|
|
/* 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']);
|
|
|
|
|
|
2013-07-16 11:56:14 +00:00
|
|
|
/* An end tag with the tag name "html" */
|
|
|
|
|
} elseif ($token['name'] === 'html' &&
|
|
|
|
|
$token['type'] === HTML5::ENDTAG
|
|
|
|
|
) {
|
2008-06-25 01:10:51 +00:00
|
|
|
/* Switch to the trailing end phase. */
|
|
|
|
|
$this->phase = self::END_PHASE;
|
|
|
|
|
|
2013-07-16 11:56:14 +00:00
|
|
|
/* A start tag with the tag name "noframes" */
|
|
|
|
|
} elseif ($token['name'] === 'noframes' &&
|
|
|
|
|
$token['type'] === HTML5::STARTTAG
|
|
|
|
|
) {
|
2008-06-25 01:10:51 +00:00
|
|
|
/* Process the token as if the insertion mode had been "in body". */
|
|
|
|
|
$this->inBody($token);
|
|
|
|
|
|
2013-07-16 11:56:14 +00:00
|
|
|
/* Anything else */
|
2008-06-25 01:10:51 +00:00
|
|
|
} else {
|
|
|
|
|
/* Parse error. Ignore the token. */
|
|
|
|
|
}
|
|
|
|
|
}
|
|
|
|
|
|
2013-07-16 11:56:14 +00:00
|
|
|
private function trailingEndPhase($token)
|
|
|
|
|
{
|
2008-06-25 01:10:51 +00:00
|
|
|
/* After the main phase, as each token is emitted from the tokenisation
|
|
|
|
|
stage, it must be processed as described in this section. */
|
|
|
|
|
|
|
|
|
|
/* A DOCTYPE token */
|
2013-07-16 11:56:14 +00:00
|
|
|
if ($token['type'] === HTML5::DOCTYPE) {
|
2008-06-25 01:10:51 +00:00
|
|
|
// Parse error. Ignore the token.
|
|
|
|
|
|
2013-07-16 11:56:14 +00:00
|
|
|
/* A comment token */
|
|
|
|
|
} elseif ($token['type'] === HTML5::COMMENT) {
|
2008-06-25 01:10:51 +00:00
|
|
|
/* 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);
|
|
|
|
|
|
2013-07-16 11:56:14 +00:00
|
|
|
/* 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'])
|
|
|
|
|
) {
|
2008-06-25 01:10:51 +00:00
|
|
|
/* Process the token as it would be processed in the main phase. */
|
|
|
|
|
$this->mainPhase($token);
|
|
|
|
|
|
2013-07-16 11:56:14 +00:00
|
|
|
/* 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
|
|
|
|
|
) {
|
2008-06-25 01:10:51 +00:00
|
|
|
/* Parse error. Switch back to the main phase and reprocess the
|
|
|
|
|
token. */
|
|
|
|
|
$this->phase = self::MAIN_PHASE;
|
|
|
|
|
return $this->mainPhase($token);
|
|
|
|
|
|
2013-07-16 11:56:14 +00:00
|
|
|
/* An end-of-file token */
|
|
|
|
|
} elseif ($token['type'] === HTML5::EOF) {
|
2008-06-25 01:10:51 +00:00
|
|
|
/* OMG DONE!! */
|
|
|
|
|
}
|
|
|
|
|
}
|
|
|
|
|
|
2013-07-16 11:56:14 +00:00
|
|
|
private function insertElement($token, $append = true, $check = false)
|
|
|
|
|
{
|
2008-06-25 01:10:51 +00:00
|
|
|
// Proprietary workaround for libxml2's limitations with tag names
|
|
|
|
|
if ($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
|
2013-07-16 11:56:14 +00:00
|
|
|
if ($token['name'] === '') {
|
|
|
|
|
$token['name'] = 'span';
|
|
|
|
|
} // arbitrary generic choice
|
2008-06-25 01:10:51 +00:00
|
|
|
}
|
2013-07-16 11:56:14 +00:00
|
|
|
|
2008-06-25 01:10:51 +00:00
|
|
|
$el = $this->dom->createElement($token['name']);
|
|
|
|
|
|
2013-07-16 11:56:14 +00:00
|
|
|
foreach ($token['attr'] as $attr) {
|
|
|
|
|
if (!$el->hasAttribute($attr['name'])) {
|
2008-06-25 01:10:51 +00:00
|
|
|
$el->setAttribute($attr['name'], $attr['value']);
|
|
|
|
|
}
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
$this->appendToRealParent($el);
|
|
|
|
|
$this->stack[] = $el;
|
|
|
|
|
|
|
|
|
|
return $el;
|
|
|
|
|
}
|
|
|
|
|
|
2013-07-16 11:56:14 +00:00
|
|
|
private function insertText($data)
|
|
|
|
|
{
|
2008-06-25 01:10:51 +00:00
|
|
|
$text = $this->dom->createTextNode($data);
|
|
|
|
|
$this->appendToRealParent($text);
|
|
|
|
|
}
|
|
|
|
|
|
2013-07-16 11:56:14 +00:00
|
|
|
private function insertComment($data)
|
|
|
|
|
{
|
2008-06-25 01:10:51 +00:00
|
|
|
$comment = $this->dom->createComment($data);
|
|
|
|
|
$this->appendToRealParent($comment);
|
|
|
|
|
}
|
|
|
|
|
|
2013-07-16 11:56:14 +00:00
|
|
|
private function appendToRealParent($node)
|
|
|
|
|
{
|
|
|
|
|
if ($this->foster_parent === null) {
|
2008-06-25 01:10:51 +00:00
|
|
|
end($this->stack)->appendChild($node);
|
|
|
|
|
|
2013-07-16 11:56:14 +00:00
|
|
|
} elseif ($this->foster_parent !== null) {
|
2008-06-25 01:10:51 +00:00
|
|
|
/* If the foster parent element is the parent element of the
|
|
|
|
|
last table element in the stack of open elements, then the new
|
|
|
|
|
node must be inserted immediately before the last table element
|
|
|
|
|
in the stack of open elements in the foster parent element;
|
|
|
|
|
otherwise, the new node must be appended to the foster parent
|
|
|
|
|
element. */
|
2013-07-16 11:56:14 +00:00
|
|
|
for ($n = count($this->stack) - 1; $n >= 0; $n--) {
|
|
|
|
|
if ($this->stack[$n]->nodeName === 'table' &&
|
|
|
|
|
$this->stack[$n]->parentNode !== null
|
|
|
|
|
) {
|
2008-06-25 01:10:51 +00:00
|
|
|
$table = $this->stack[$n];
|
|
|
|
|
break;
|
|
|
|
|
}
|
|
|
|
|
}
|
|
|
|
|
|
2013-07-16 11:56:14 +00:00
|
|
|
if (isset($table) && $this->foster_parent->isSameNode($table->parentNode)) {
|
2008-06-25 01:10:51 +00:00
|
|
|
$this->foster_parent->insertBefore($node, $table);
|
2013-07-16 11:56:14 +00:00
|
|
|
} else {
|
2008-06-25 01:10:51 +00:00
|
|
|
$this->foster_parent->appendChild($node);
|
2013-07-16 11:56:14 +00:00
|
|
|
}
|
2008-06-25 01:10:51 +00:00
|
|
|
|
|
|
|
|
$this->foster_parent = null;
|
|
|
|
|
}
|
|
|
|
|
}
|
|
|
|
|
|
2013-07-16 11:56:14 +00:00
|
|
|
private function elementInScope($el, $table = false)
|
|
|
|
|
{
|
|
|
|
|
if (is_array($el)) {
|
|
|
|
|
foreach ($el as $element) {
|
|
|
|
|
if ($this->elementInScope($element, $table)) {
|
2008-06-25 01:10:51 +00:00
|
|
|
return true;
|
|
|
|
|
}
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
return false;
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
$leng = count($this->stack);
|
|
|
|
|
|
2013-07-16 11:56:14 +00:00
|
|
|
for ($n = 0; $n < $leng; $n++) {
|
2008-06-25 01:10:51 +00:00
|
|
|
/* 1. Initialise node to be the current node (the bottommost node of
|
|
|
|
|
the stack). */
|
|
|
|
|
$node = $this->stack[$leng - 1 - $n];
|
|
|
|
|
|
2013-07-16 11:56:14 +00:00
|
|
|
if ($node->tagName === $el) {
|
2008-06-25 01:10:51 +00:00
|
|
|
/* 2. If node is the target node, terminate in a match state. */
|
|
|
|
|
return true;
|
|
|
|
|
|
2013-07-16 11:56:14 +00:00
|
|
|
} elseif ($node->tagName === 'table') {
|
2008-06-25 01:10:51 +00:00
|
|
|
/* 3. Otherwise, if node is a table element, terminate in a failure
|
|
|
|
|
state. */
|
|
|
|
|
return false;
|
|
|
|
|
|
2013-07-16 11:56:14 +00:00
|
|
|
} elseif ($table === true && in_array(
|
|
|
|
|
$node->tagName,
|
|
|
|
|
array(
|
|
|
|
|
'caption',
|
|
|
|
|
'td',
|
|
|
|
|
'th',
|
|
|
|
|
'button',
|
|
|
|
|
'marquee',
|
|
|
|
|
'object'
|
|
|
|
|
)
|
|
|
|
|
)
|
|
|
|
|
) {
|
2008-06-25 01:10:51 +00:00
|
|
|
/* 4. Otherwise, if the algorithm is the "has an element in scope"
|
|
|
|
|
variant (rather than the "has an element in table scope" variant),
|
|
|
|
|
and node is one of the following, terminate in a failure state. */
|
|
|
|
|
return false;
|
|
|
|
|
|
2013-07-16 11:56:14 +00:00
|
|
|
} elseif ($node === $node->ownerDocument->documentElement) {
|
2008-06-25 01:10:51 +00:00
|
|
|
/* 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.) */
|
|
|
|
|
}
|
|
|
|
|
}
|
|
|
|
|
|
2013-07-16 11:56:14 +00:00
|
|
|
private function reconstructActiveFormattingElements()
|
|
|
|
|
{
|
2008-06-25 01:10:51 +00:00
|
|
|
/* 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);
|
|
|
|
|
|
2013-07-16 11:56:14 +00:00
|
|
|
if ($formatting_elements === 0) {
|
2008-06-25 01:10:51 +00:00
|
|
|
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. */
|
2013-07-16 11:56:14 +00:00
|
|
|
if ($entry === self::MARKER || in_array($entry, $this->stack, true)) {
|
2008-06-25 01:10:51 +00:00
|
|
|
return false;
|
|
|
|
|
}
|
|
|
|
|
|
2013-07-16 11:56:14 +00:00
|
|
|
for ($a = $formatting_elements - 1; $a >= 0; true) {
|
2008-06-25 01:10:51 +00:00
|
|
|
/* 4. If there are no entries before entry in the list of active
|
|
|
|
|
formatting elements, then jump to step 8. */
|
2013-07-16 11:56:14 +00:00
|
|
|
if ($a === 0) {
|
2008-06-25 01:10:51 +00:00
|
|
|
$step_seven = false;
|
|
|
|
|
break;
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
/* 5. Let entry be the entry one earlier than entry in the list of
|
|
|
|
|
active formatting elements. */
|
|
|
|
|
$a--;
|
|
|
|
|
$entry = $this->a_formatting[$a];
|
|
|
|
|
|
|
|
|
|
/* 6. If entry is neither a marker nor an element that is also in
|
|
|
|
|
thetack of open elements, go to step 4. */
|
2013-07-16 11:56:14 +00:00
|
|
|
if ($entry === self::MARKER || in_array($entry, $this->stack, true)) {
|
2008-06-25 01:10:51 +00:00
|
|
|
break;
|
|
|
|
|
}
|
|
|
|
|
}
|
|
|
|
|
|
2013-07-16 11:56:14 +00:00
|
|
|
while (true) {
|
2008-06-25 01:10:51 +00:00
|
|
|
/* 7. Let entry be the element one later than entry in the list of
|
|
|
|
|
active formatting elements. */
|
2013-07-16 11:56:14 +00:00
|
|
|
if (isset($step_seven) && $step_seven === true) {
|
2008-06-25 01:10:51 +00:00
|
|
|
$a++;
|
|
|
|
|
$entry = $this->a_formatting[$a];
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
/* 8. Perform a shallow clone of the element entry to obtain clone. */
|
|
|
|
|
$clone = $entry->cloneNode();
|
|
|
|
|
|
|
|
|
|
/* 9. Append clone to the current node and push it onto the stack
|
|
|
|
|
of open elements so that it is the new current node. */
|
|
|
|
|
end($this->stack)->appendChild($clone);
|
|
|
|
|
$this->stack[] = $clone;
|
|
|
|
|
|
|
|
|
|
/* 10. Replace the entry for entry in the list with an entry for
|
|
|
|
|
clone. */
|
|
|
|
|
$this->a_formatting[$a] = $clone;
|
|
|
|
|
|
|
|
|
|
/* 11. If the entry for clone in the list of active formatting
|
|
|
|
|
elements is not the last entry in the list, return to step 7. */
|
2013-07-16 11:56:14 +00:00
|
|
|
if (end($this->a_formatting) !== $clone) {
|
2008-06-25 01:10:51 +00:00
|
|
|
$step_seven = true;
|
|
|
|
|
} else {
|
|
|
|
|
break;
|
|
|
|
|
}
|
|
|
|
|
}
|
|
|
|
|
}
|
|
|
|
|
|
2013-07-16 11:56:14 +00:00
|
|
|
private function clearTheActiveFormattingElementsUpToTheLastMarker()
|
|
|
|
|
{
|
2008-06-25 01:10:51 +00:00
|
|
|
/* When the steps below require the UA to clear the list of active
|
|
|
|
|
formatting elements up to the last marker, the UA must perform the
|
|
|
|
|
following steps: */
|
|
|
|
|
|
2013-07-16 11:56:14 +00:00
|
|
|
while (true) {
|
2008-06-25 01:10:51 +00:00
|
|
|
/* 1. Let entry be the last (most recently added) entry in the list
|
|
|
|
|
of active formatting elements. */
|
|
|
|
|
$entry = end($this->a_formatting);
|
|
|
|
|
|
|
|
|
|
/* 2. Remove entry from the list of active formatting elements. */
|
|
|
|
|
array_pop($this->a_formatting);
|
|
|
|
|
|
|
|
|
|
/* 3. If entry was a marker, then stop the algorithm at this point.
|
|
|
|
|
The list has been cleared up to the last marker. */
|
2013-07-16 11:56:14 +00:00
|
|
|
if ($entry === self::MARKER) {
|
2008-06-25 01:10:51 +00:00
|
|
|
break;
|
|
|
|
|
}
|
|
|
|
|
}
|
|
|
|
|
}
|
|
|
|
|
|
2013-07-16 11:56:14 +00:00
|
|
|
private function generateImpliedEndTags($exclude = array())
|
|
|
|
|
{
|
2008-06-25 01:10:51 +00:00
|
|
|
/* When the steps below require the UA to generate implied end tags,
|
|
|
|
|
then, if the current node is a dd element, a dt element, an li element,
|
|
|
|
|
a p element, a td element, a th element, or a tr element, the UA must
|
|
|
|
|
act as if an end tag with the respective tag name had been seen and
|
|
|
|
|
then generate implied end tags again. */
|
|
|
|
|
$node = end($this->stack);
|
|
|
|
|
$elements = array_diff(array('dd', 'dt', 'li', 'p', 'td', 'th', 'tr'), $exclude);
|
|
|
|
|
|
2013-07-16 11:56:14 +00:00
|
|
|
while (in_array(end($this->stack)->nodeName, $elements)) {
|
2008-06-25 01:10:51 +00:00
|
|
|
array_pop($this->stack);
|
|
|
|
|
}
|
|
|
|
|
}
|
|
|
|
|
|
2013-07-16 11:56:14 +00:00
|
|
|
private function getElementCategory($node)
|
|
|
|
|
{
|
2008-06-25 01:10:51 +00:00
|
|
|
$name = $node->tagName;
|
2013-07-16 11:56:14 +00:00
|
|
|
if (in_array($name, $this->special)) {
|
2008-06-25 01:10:51 +00:00
|
|
|
return self::SPECIAL;
|
2013-07-16 11:56:14 +00:00
|
|
|
} elseif (in_array($name, $this->scoping)) {
|
2008-06-25 01:10:51 +00:00
|
|
|
return self::SCOPING;
|
2013-07-16 11:56:14 +00:00
|
|
|
} elseif (in_array($name, $this->formatting)) {
|
2008-06-25 01:10:51 +00:00
|
|
|
return self::FORMATTING;
|
2013-07-16 11:56:14 +00:00
|
|
|
} else {
|
2008-06-25 01:10:51 +00:00
|
|
|
return self::PHRASING;
|
2013-07-16 11:56:14 +00:00
|
|
|
}
|
2008-06-25 01:10:51 +00:00
|
|
|
}
|
|
|
|
|
|
2013-07-16 11:56:14 +00:00
|
|
|
private function clearStackToTableContext($elements)
|
|
|
|
|
{
|
2008-06-25 01:10:51 +00:00
|
|
|
/* When the steps above require the UA to clear the stack back to a
|
|
|
|
|
table context, it means that the UA must, while the current node is not
|
|
|
|
|
a table element or an html element, pop elements from the stack of open
|
|
|
|
|
elements. If this causes any elements to be popped from the stack, then
|
|
|
|
|
this is a parse error. */
|
2013-07-16 11:56:14 +00:00
|
|
|
while (true) {
|
2008-06-25 01:10:51 +00:00
|
|
|
$node = end($this->stack)->nodeName;
|
|
|
|
|
|
2013-07-16 11:56:14 +00:00
|
|
|
if (in_array($node, $elements)) {
|
2008-06-25 01:10:51 +00:00
|
|
|
break;
|
|
|
|
|
} else {
|
|
|
|
|
array_pop($this->stack);
|
|
|
|
|
}
|
|
|
|
|
}
|
|
|
|
|
}
|
|
|
|
|
|
2013-07-16 11:56:14 +00:00
|
|
|
private function resetInsertionMode()
|
|
|
|
|
{
|
2008-06-25 01:10:51 +00:00
|
|
|
/* 1. Let last be false. */
|
|
|
|
|
$last = false;
|
|
|
|
|
$leng = count($this->stack);
|
|
|
|
|
|
2013-07-16 11:56:14 +00:00
|
|
|
for ($n = $leng - 1; $n >= 0; $n--) {
|
2008-06-25 01:10:51 +00:00
|
|
|
/* 2. Let node be the last node in the stack of open elements. */
|
|
|
|
|
$node = $this->stack[$n];
|
|
|
|
|
|
|
|
|
|
/* 3. If node is the first node in the stack of open elements, then
|
|
|
|
|
set last to true. If the element whose innerHTML attribute is being
|
|
|
|
|
set is neither a td element nor a th element, then set node to the
|
|
|
|
|
element whose innerHTML attribute is being set. (innerHTML case) */
|
2013-07-16 11:56:14 +00:00
|
|
|
if ($this->stack[0]->isSameNode($node)) {
|
2008-06-25 01:10:51 +00:00
|
|
|
$last = true;
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
/* 4. If node is a select element, then switch the insertion mode to
|
|
|
|
|
"in select" and abort these steps. (innerHTML case) */
|
2013-07-16 11:56:14 +00:00
|
|
|
if ($node->nodeName === 'select') {
|
2008-06-25 01:10:51 +00:00
|
|
|
$this->mode = self::IN_SELECT;
|
|
|
|
|
break;
|
|
|
|
|
|
2013-07-16 11:56:14 +00:00
|
|
|
/* 5. If node is a td or th element, then switch the insertion mode
|
|
|
|
|
to "in cell" and abort these steps. */
|
|
|
|
|
} elseif ($node->nodeName === 'td' || $node->nodeName === 'th') {
|
2008-06-25 01:10:51 +00:00
|
|
|
$this->mode = self::IN_CELL;
|
|
|
|
|
break;
|
|
|
|
|
|
2013-07-16 11:56:14 +00:00
|
|
|
/* 6. If node is a tr element, then switch the insertion mode to
|
|
|
|
|
"in row" and abort these steps. */
|
|
|
|
|
} elseif ($node->nodeName === 'tr') {
|
2008-06-25 01:10:51 +00:00
|
|
|
$this->mode = self::IN_ROW;
|
|
|
|
|
break;
|
|
|
|
|
|
2013-07-16 11:56:14 +00:00
|
|
|
/* 7. If node is a tbody, thead, or tfoot element, then switch the
|
|
|
|
|
insertion mode to "in table body" and abort these steps. */
|
|
|
|
|
} elseif (in_array($node->nodeName, array('tbody', 'thead', 'tfoot'))) {
|
2008-06-25 01:10:51 +00:00
|
|
|
$this->mode = self::IN_TBODY;
|
|
|
|
|
break;
|
|
|
|
|
|
2013-07-16 11:56:14 +00:00
|
|
|
/* 8. If node is a caption element, then switch the insertion mode
|
|
|
|
|
to "in caption" and abort these steps. */
|
|
|
|
|
} elseif ($node->nodeName === 'caption') {
|
2008-06-25 01:10:51 +00:00
|
|
|
$this->mode = self::IN_CAPTION;
|
|
|
|
|
break;
|
|
|
|
|
|
2013-07-16 11:56:14 +00:00
|
|
|
/* 9. If node is a colgroup element, then switch the insertion mode
|
|
|
|
|
to "in column group" and abort these steps. (innerHTML case) */
|
|
|
|
|
} elseif ($node->nodeName === 'colgroup') {
|
2008-06-25 01:10:51 +00:00
|
|
|
$this->mode = self::IN_CGROUP;
|
|
|
|
|
break;
|
|
|
|
|
|
2013-07-16 11:56:14 +00:00
|
|
|
/* 10. If node is a table element, then switch the insertion mode
|
|
|
|
|
to "in table" and abort these steps. */
|
|
|
|
|
} elseif ($node->nodeName === 'table') {
|
2008-06-25 01:10:51 +00:00
|
|
|
$this->mode = self::IN_TABLE;
|
|
|
|
|
break;
|
|
|
|
|
|
2013-07-16 11:56:14 +00:00
|
|
|
/* 11. If node is a head element, then switch the insertion mode
|
|
|
|
|
to "in body" ("in body"! not "in head"!) and abort these steps.
|
|
|
|
|
(innerHTML case) */
|
|
|
|
|
} elseif ($node->nodeName === 'head') {
|
2008-06-25 01:10:51 +00:00
|
|
|
$this->mode = self::IN_BODY;
|
|
|
|
|
break;
|
|
|
|
|
|
2013-07-16 11:56:14 +00:00
|
|
|
/* 12. If node is a body element, then switch the insertion mode to
|
|
|
|
|
"in body" and abort these steps. */
|
|
|
|
|
} elseif ($node->nodeName === 'body') {
|
2008-06-25 01:10:51 +00:00
|
|
|
$this->mode = self::IN_BODY;
|
|
|
|
|
break;
|
|
|
|
|
|
2013-07-16 11:56:14 +00:00
|
|
|
/* 13. If node is a frameset element, then switch the insertion
|
|
|
|
|
mode to "in frameset" and abort these steps. (innerHTML case) */
|
|
|
|
|
} elseif ($node->nodeName === 'frameset') {
|
2008-06-25 01:10:51 +00:00
|
|
|
$this->mode = self::IN_FRAME;
|
|
|
|
|
break;
|
|
|
|
|
|
2013-07-16 11:56:14 +00:00
|
|
|
/* 14. If node is an html element, then: if the head element
|
|
|
|
|
pointer is null, switch the insertion mode to "before head",
|
|
|
|
|
otherwise, switch the insertion mode to "after head". In either
|
|
|
|
|
case, abort these steps. (innerHTML case) */
|
|
|
|
|
} elseif ($node->nodeName === 'html') {
|
2008-06-25 01:10:51 +00:00
|
|
|
$this->mode = ($this->head_pointer === null)
|
|
|
|
|
? self::BEFOR_HEAD
|
|
|
|
|
: self::AFTER_HEAD;
|
|
|
|
|
|
|
|
|
|
break;
|
|
|
|
|
|
2013-07-16 11:56:14 +00:00
|
|
|
/* 15. If last is true, then set the insertion mode to "in body"
|
|
|
|
|
and abort these steps. (innerHTML case) */
|
|
|
|
|
} elseif ($last) {
|
2008-06-25 01:10:51 +00:00
|
|
|
$this->mode = self::IN_BODY;
|
|
|
|
|
break;
|
|
|
|
|
}
|
|
|
|
|
}
|
|
|
|
|
}
|
|
|
|
|
|
2013-07-16 11:56:14 +00:00
|
|
|
private function closeCell()
|
|
|
|
|
{
|
2008-06-25 01:10:51 +00:00
|
|
|
/* If the stack of open elements has a td or th element in table scope,
|
|
|
|
|
then act as if an end tag token with that tag name had been seen. */
|
2013-07-16 11:56:14 +00:00
|
|
|
foreach (array('td', 'th') as $cell) {
|
|
|
|
|
if ($this->elementInScope($cell, true)) {
|
|
|
|
|
$this->inCell(
|
|
|
|
|
array(
|
|
|
|
|
'name' => $cell,
|
|
|
|
|
'type' => HTML5::ENDTAG
|
|
|
|
|
)
|
|
|
|
|
);
|
2008-06-25 01:10:51 +00:00
|
|
|
|
|
|
|
|
break;
|
|
|
|
|
}
|
|
|
|
|
}
|
|
|
|
|
}
|
|
|
|
|
|
2013-07-16 11:56:14 +00:00
|
|
|
public function save()
|
|
|
|
|
{
|
2008-06-25 01:10:51 +00:00
|
|
|
return $this->dom;
|
|
|
|
|
}
|
|
|
|
|
}
|
